Merge branch 'master' into for-next

Sync with Linus' tree so that patches against newer codebase can be applied.

Signed-off-by: Jiri Kosina <jkosina@suse.cz>

854 files changed, 45899 insertions, 21933 deletions

diff --git a/fs/9p/Makefile b/fs/9p/Makefile
index ff7be98f84f2..9619ccadd2fc 100644
--- a/fs/9p/Makefile
+++ b/fs/9p/Makefile
@@ -10,10 +10,7 @@ obj-$(CONFIG_9P_FS) := 9p.o
 	vfs_dentry.o \
 	v9fs.o \
 	fid.o  \
-	xattr.o \
-	xattr_user.o \
-	xattr_trusted.o
+	xattr.o
 
 9p-$(CONFIG_9P_FSCACHE) += cache.o
 9p-$(CONFIG_9P_FS_POSIX_ACL) += acl.o
-9p-$(CONFIG_9P_FS_SECURITY) += xattr_security.o
diff --git a/fs/9p/acl.c b/fs/9p/acl.c
index 31c010372660..9da967f38387 100644
--- a/fs/9p/acl.c
+++ b/fs/9p/acl.c
@@ -67,8 +67,8 @@ int v9fs_get_acl(struct inode *inode, struct p9_fid *fid)
 		return 0;
 	}
 	/* get the default/access acl values and cache them */
-	dacl = __v9fs_get_acl(fid, POSIX_ACL_XATTR_DEFAULT);
-	pacl = __v9fs_get_acl(fid, POSIX_ACL_XATTR_ACCESS);
+	dacl = __v9fs_get_acl(fid, XATTR_NAME_POSIX_ACL_DEFAULT);
+	pacl = __v9fs_get_acl(fid, XATTR_NAME_POSIX_ACL_ACCESS);
 
 	if (!IS_ERR(dacl) && !IS_ERR(pacl)) {
 		set_cached_acl(inode, ACL_TYPE_DEFAULT, dacl);
@@ -133,10 +133,10 @@ static int v9fs_set_acl(struct p9_fid *fid, int type, struct posix_acl *acl)
 		goto err_free_out;
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		name = POSIX_ACL_XATTR_ACCESS;
+		name = XATTR_NAME_POSIX_ACL_ACCESS;
 		break;
 	case ACL_TYPE_DEFAULT:
-		name = POSIX_ACL_XATTR_DEFAULT;
+		name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		break;
 	default:
 		BUG();
@@ -212,42 +212,22 @@ int v9fs_acl_mode(struct inode *dir, umode_t *modep,
 	return 0;
 }
 
-static int v9fs_remote_get_acl(struct dentry *dentry, const char *name,
-			       void *buffer, size_t size, int type)
-{
-	char *full_name;
-
-	switch (type) {
-	case ACL_TYPE_ACCESS:
-		full_name =  POSIX_ACL_XATTR_ACCESS;
-		break;
-	case ACL_TYPE_DEFAULT:
-		full_name = POSIX_ACL_XATTR_DEFAULT;
-		break;
-	default:
-		BUG();
-	}
-	return v9fs_xattr_get(dentry, full_name, buffer, size);
-}
-
-static int v9fs_xattr_get_acl(struct dentry *dentry, const char *name,
-			      void *buffer, size_t size, int type)
+static int v9fs_xattr_get_acl(const struct xattr_handler *handler,
+			      struct dentry *dentry, const char *name,
+			      void *buffer, size_t size)
 {
 	struct v9fs_session_info *v9ses;
 	struct posix_acl *acl;
 	int error;
 
-	if (strcmp(name, "") != 0)
-		return -EINVAL;
-
 	v9ses = v9fs_dentry2v9ses(dentry);
 	/*
 	 * We allow set/get/list of acl when access=client is not specified
 	 */
 	if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT)
-		return v9fs_remote_get_acl(dentry, name, buffer, size, type);
+		return v9fs_xattr_get(dentry, handler->name, buffer, size);
 
-	acl = v9fs_get_cached_acl(d_inode(dentry), type);
+	acl = v9fs_get_cached_acl(d_inode(dentry), handler->flags);
 	if (IS_ERR(acl))
 		return PTR_ERR(acl);
 	if (acl == NULL)
@@ -258,46 +238,23 @@ static int v9fs_xattr_get_acl(struct dentry *dentry, const char *name,
 	return error;
 }
 
-static int v9fs_remote_set_acl(struct dentry *dentry, const char *name,
-			      const void *value, size_t size,
-			      int flags, int type)
-{
-	char *full_name;
-
-	switch (type) {
-	case ACL_TYPE_ACCESS:
-		full_name =  POSIX_ACL_XATTR_ACCESS;
-		break;
-	case ACL_TYPE_DEFAULT:
-		full_name = POSIX_ACL_XATTR_DEFAULT;
-		break;
-	default:
-		BUG();
-	}
-	return v9fs_xattr_set(dentry, full_name, value, size, flags);
-}
-
-
-static int v9fs_xattr_set_acl(struct dentry *dentry, const char *name,
-			      const void *value, size_t size,
-			      int flags, int type)
+static int v9fs_xattr_set_acl(const struct xattr_handler *handler,
+			      struct dentry *dentry, const char *name,
+			      const void *value, size_t size, int flags)
 {
 	int retval;
 	struct posix_acl *acl;
 	struct v9fs_session_info *v9ses;
 	struct inode *inode = d_inode(dentry);
 
-	if (strcmp(name, "") != 0)
-		return -EINVAL;
-
 	v9ses = v9fs_dentry2v9ses(dentry);
 	/*
 	 * set the attribute on the remote. Without even looking at the
 	 * xattr value. We leave it to the server to validate
 	 */
 	if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT)
-		return v9fs_remote_set_acl(dentry, name,
-					   value, size, flags, type);
+		return v9fs_xattr_set(dentry, handler->name, value, size,
+				      flags);
 
 	if (S_ISLNK(inode->i_mode))
 		return -EOPNOTSUPP;
@@ -316,9 +273,8 @@ static int v9fs_xattr_set_acl(struct dentry *dentry, const char *name,
 	} else
 		acl = NULL;
 
-	switch (type) {
+	switch (handler->flags) {
 	case ACL_TYPE_ACCESS:
-		name = POSIX_ACL_XATTR_ACCESS;
 		if (acl) {
 			umode_t mode = inode->i_mode;
 			retval = posix_acl_equiv_mode(acl, &mode);
@@ -349,7 +305,6 @@ static int v9fs_xattr_set_acl(struct dentry *dentry, const char *name,
 		}
 		break;
 	case ACL_TYPE_DEFAULT:
-		name = POSIX_ACL_XATTR_DEFAULT;
 		if (!S_ISDIR(inode->i_mode)) {
 			retval = acl ? -EINVAL : 0;
 			goto err_out;
@@ -358,23 +313,23 @@ static int v9fs_xattr_set_acl(struct dentry *dentry, const char *name,
 	default:
 		BUG();
 	}
-	retval = v9fs_xattr_set(dentry, name, value, size, flags);
+	retval = v9fs_xattr_set(dentry, handler->name, value, size, flags);
 	if (!retval)
-		set_cached_acl(inode, type, acl);
+		set_cached_acl(inode, handler->flags, acl);
 err_out:
 	posix_acl_release(acl);
 	return retval;
 }
 
 const struct xattr_handler v9fs_xattr_acl_access_handler = {
-	.prefix	= POSIX_ACL_XATTR_ACCESS,
+	.name	= XATTR_NAME_POSIX_ACL_ACCESS,
 	.flags	= ACL_TYPE_ACCESS,
 	.get	= v9fs_xattr_get_acl,
 	.set	= v9fs_xattr_set_acl,
 };
 
 const struct xattr_handler v9fs_xattr_acl_default_handler = {
-	.prefix	= POSIX_ACL_XATTR_DEFAULT,
+	.name	= XATTR_NAME_POSIX_ACL_DEFAULT,
 	.flags	= ACL_TYPE_DEFAULT,
 	.get	= v9fs_xattr_get_acl,
 	.set	= v9fs_xattr_set_acl,
diff --git a/fs/9p/cache.c b/fs/9p/cache.c
index a69260f27555..103ca5e1267b 100644
--- a/fs/9p/cache.c
+++ b/fs/9p/cache.c
@@ -243,14 +243,14 @@ void v9fs_cache_inode_set_cookie(struct inode *inode, struct file *filp)
 	if (!v9inode->fscache)
 		return;
 
-	spin_lock(&v9inode->fscache_lock);
+	mutex_lock(&v9inode->fscache_lock);
 
 	if ((filp->f_flags & O_ACCMODE) != O_RDONLY)
 		v9fs_cache_inode_flush_cookie(inode);
 	else
 		v9fs_cache_inode_get_cookie(inode);
 
-	spin_unlock(&v9inode->fscache_lock);
+	mutex_unlock(&v9inode->fscache_lock);
 }
 
 void v9fs_cache_inode_reset_cookie(struct inode *inode)
@@ -264,7 +264,7 @@ void v9fs_cache_inode_reset_cookie(struct inode *inode)
 
 	old = v9inode->fscache;
 
-	spin_lock(&v9inode->fscache_lock);
+	mutex_lock(&v9inode->fscache_lock);
 	fscache_relinquish_cookie(v9inode->fscache, 1);
 
 	v9ses = v9fs_inode2v9ses(inode);
@@ -274,7 +274,7 @@ void v9fs_cache_inode_reset_cookie(struct inode *inode)
 	p9_debug(P9_DEBUG_FSC, "inode %p revalidating cookie old %p new %p\n",
 		 inode, old, v9inode->fscache);
 
-	spin_unlock(&v9inode->fscache_lock);
+	mutex_unlock(&v9inode->fscache_lock);
 }
 
 int __v9fs_fscache_release_page(struct page *page, gfp_t gfp)
diff --git a/fs/9p/cache.h b/fs/9p/cache.h
index 2f9675491095..247e47e54bcc 100644
--- a/fs/9p/cache.h
+++ b/fs/9p/cache.h
@@ -21,6 +21,7 @@
  */
 
 #ifndef _9P_CACHE_H
+#define _9P_CACHE_H
 #ifdef CONFIG_9P_FSCACHE
 #include <linux/fscache.h>
 #include <linux/spinlock.h>
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 6caca025019d..072e7599583a 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -575,7 +575,7 @@ static int v9fs_init_inode_cache(void)
 	v9fs_inode_cache = kmem_cache_create("v9fs_inode_cache",
 					  sizeof(struct v9fs_inode),
 					  0, (SLAB_RECLAIM_ACCOUNT|
-					      SLAB_MEM_SPREAD),
+					      SLAB_MEM_SPREAD|SLAB_ACCOUNT),
 					  v9fs_inode_init_once);
 	if (!v9fs_inode_cache)
 		return -ENOMEM;
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index 0923f2cf3c80..6877050384a1 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -123,7 +123,7 @@ struct v9fs_session_info {
 
 struct v9fs_inode {
 #ifdef CONFIG_9P_FSCACHE
-	spinlock_t fscache_lock;
+	struct mutex fscache_lock;
 	struct fscache_cookie *fscache;
 #endif
 	struct p9_qid qid;
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index e9e04376c52c..ac9225e86bf3 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -153,7 +153,7 @@ static void v9fs_invalidate_page(struct page *page, unsigned int offset,
 	 * If called with zero offset, we should release
 	 * the private state assocated with the page
 	 */
-	if (offset == 0 && length == PAGE_CACHE_SIZE)
+	if (offset == 0 && length == PAGE_SIZE)
 		v9fs_fscache_invalidate_page(page);
 }
 
@@ -166,10 +166,10 @@ static int v9fs_vfs_writepage_locked(struct page *page)
 	struct bio_vec bvec;
 	int err, len;
 
-	if (page->index == size >> PAGE_CACHE_SHIFT)
-		len = size & ~PAGE_CACHE_MASK;
+	if (page->index == size >> PAGE_SHIFT)
+		len = size & ~PAGE_MASK;
 	else
-		len = PAGE_CACHE_SIZE;
+		len = PAGE_SIZE;
 
 	bvec.bv_page = page;
 	bvec.bv_offset = 0;
@@ -271,7 +271,7 @@ static int v9fs_write_begin(struct file *filp, struct address_space *mapping,
 	int retval = 0;
 	struct page *page;
 	struct v9fs_inode *v9inode;
-	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+	pgoff_t index = pos >> PAGE_SHIFT;
 	struct inode *inode = mapping->host;
 
 
@@ -288,11 +288,11 @@ start:
 	if (PageUptodate(page))
 		goto out;
 
-	if (len == PAGE_CACHE_SIZE)
+	if (len == PAGE_SIZE)
 		goto out;
 
 	retval = v9fs_fid_readpage(v9inode->writeback_fid, page);
-	page_cache_release(page);
+	put_page(page);
 	if (!retval)
 		goto start;
 out:
@@ -313,7 +313,7 @@ static int v9fs_write_end(struct file *filp, struct address_space *mapping,
 		/*
 		 * zero out the rest of the area
 		 */
-		unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+		unsigned from = pos & (PAGE_SIZE - 1);
 
 		zero_user(page, from + copied, len - copied);
 		flush_dcache_page(page);
@@ -331,7 +331,7 @@ static int v9fs_write_end(struct file *filp, struct address_space *mapping,
 	}
 	set_page_dirty(page);
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 
 	return copied;
 }
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 7bf835f85bc8..b84c291ba1eb 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -421,8 +421,8 @@ v9fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		struct inode *inode = file_inode(file);
 		loff_t i_size;
 		unsigned long pg_start, pg_end;
-		pg_start = origin >> PAGE_CACHE_SHIFT;
-		pg_end = (origin + retval - 1) >> PAGE_CACHE_SHIFT;
+		pg_start = origin >> PAGE_SHIFT;
+		pg_end = (origin + retval - 1) >> PAGE_SHIFT;
 		if (inode->i_mapping && inode->i_mapping->nrpages)
 			invalidate_inode_pages2_range(inode->i_mapping,
 						      pg_start, pg_end);
@@ -449,14 +449,14 @@ static int v9fs_file_fsync(struct file *filp, loff_t start, loff_t end,
 	if (retval)
 		return retval;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	p9_debug(P9_DEBUG_VFS, "filp %p datasync %x\n", filp, datasync);
 
 	fid = filp->private_data;
 	v9fs_blank_wstat(&wstat);
 
 	retval = p9_client_wstat(fid, &wstat);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	return retval;
 }
@@ -472,13 +472,13 @@ int v9fs_file_fsync_dotl(struct file *filp, loff_t start, loff_t end,
 	if (retval)
 		return retval;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	p9_debug(P9_DEBUG_VFS, "filp %p datasync %x\n", filp, datasync);
 
 	fid = filp->private_data;
 
 	retval = p9_client_fsync(fid, datasync);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	return retval;
 }
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index b1dc51888048..3a08b3e6ff1d 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -244,7 +244,7 @@ struct inode *v9fs_alloc_inode(struct super_block *sb)
 		return NULL;
 #ifdef CONFIG_9P_FSCACHE
 	v9inode->fscache = NULL;
-	spin_lock_init(&v9inode->fscache_lock);
+	mutex_init(&v9inode->fscache_lock);
 #endif
 	v9inode->writeback_fid = NULL;
 	v9inode->cache_validity = 0;
@@ -451,9 +451,9 @@ void v9fs_evict_inode(struct inode *inode)
 {
 	struct v9fs_inode *v9inode = V9FS_I(inode);
 
-	truncate_inode_pages_final(inode->i_mapping);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
-	filemap_fdatawrite(inode->i_mapping);
+	filemap_fdatawrite(&inode->i_data);
 
 	v9fs_cache_inode_put_cookie(inode);
 	/* clunk the fid stashed in writeback_fid */
@@ -1223,18 +1223,26 @@ ino_t v9fs_qid2ino(struct p9_qid *qid)
 }
 
 /**
- * v9fs_vfs_follow_link - follow a symlink path
+ * v9fs_vfs_get_link - follow a symlink path
  * @dentry: dentry for symlink
- * @cookie: place to pass the data to put_link()
+ * @inode: inode for symlink
+ * @done: delayed call for when we are done with the return value
  */
 
-static const char *v9fs_vfs_follow_link(struct dentry *dentry, void **cookie)
+static const char *v9fs_vfs_get_link(struct dentry *dentry,
+				     struct inode *inode,
+				     struct delayed_call *done)
 {
-	struct v9fs_session_info *v9ses = v9fs_dentry2v9ses(dentry);
-	struct p9_fid *fid = v9fs_fid_lookup(dentry);
+	struct v9fs_session_info *v9ses;
+	struct p9_fid *fid;
 	struct p9_wstat *st;
 	char *res;
 
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
+	v9ses = v9fs_dentry2v9ses(dentry);
+	fid = v9fs_fid_lookup(dentry);
 	p9_debug(P9_DEBUG_VFS, "%pd\n", dentry);
 
 	if (IS_ERR(fid))
@@ -1259,7 +1267,8 @@ static const char *v9fs_vfs_follow_link(struct dentry *dentry, void **cookie)
 
 	p9stat_free(st);
 	kfree(st);
-	return *cookie = res;
+	set_delayed_call(done, kfree_link, res);
+	return res;
 }
 
 /**
@@ -1368,9 +1377,6 @@ v9fs_vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rde
 		 dir->i_ino, dentry, mode,
 		 MAJOR(rdev), MINOR(rdev));
 
-	if (!new_valid_dev(rdev))
-		return -EINVAL;
-
 	/* build extension */
 	if (S_ISBLK(mode))
 		sprintf(name, "b %u %u", MAJOR(rdev), MINOR(rdev));
@@ -1455,8 +1461,7 @@ static const struct inode_operations v9fs_file_inode_operations = {
 
 static const struct inode_operations v9fs_symlink_inode_operations = {
 	.readlink = generic_readlink,
-	.follow_link = v9fs_vfs_follow_link,
-	.put_link = kfree_put_link,
+	.get_link = v9fs_vfs_get_link,
 	.getattr = v9fs_vfs_getattr,
 	.setattr = v9fs_vfs_setattr,
 };
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index e8aa57dc8d6d..a34702c998f5 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -829,9 +829,6 @@ v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
 		 dir->i_ino, dentry, omode,
 		 MAJOR(rdev), MINOR(rdev));
 
-	if (!new_valid_dev(rdev))
-		return -EINVAL;
-
 	v9ses = v9fs_inode2v9ses(dir);
 	dir_dentry = dentry->d_parent;
 	dfid = v9fs_fid_lookup(dir_dentry);
@@ -902,26 +899,34 @@ error:
 }
 
 /**
- * v9fs_vfs_follow_link_dotl - follow a symlink path
+ * v9fs_vfs_get_link_dotl - follow a symlink path
  * @dentry: dentry for symlink
- * @cookie: place to pass the data to put_link()
+ * @inode: inode for symlink
+ * @done: destructor for return value
  */
 
 static const char *
-v9fs_vfs_follow_link_dotl(struct dentry *dentry, void **cookie)
+v9fs_vfs_get_link_dotl(struct dentry *dentry,
+		       struct inode *inode,
+		       struct delayed_call *done)
 {
-	struct p9_fid *fid = v9fs_fid_lookup(dentry);
+	struct p9_fid *fid;
 	char *target;
 	int retval;
 
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
 	p9_debug(P9_DEBUG_VFS, "%pd\n", dentry);
 
+	fid = v9fs_fid_lookup(dentry);
 	if (IS_ERR(fid))
 		return ERR_CAST(fid);
 	retval = p9_client_readlink(fid, &target);
 	if (retval)
 		return ERR_PTR(retval);
-	return *cookie = target;
+	set_delayed_call(done, kfree_link, target);
+	return target;
 }
 
 int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode)
@@ -987,8 +992,7 @@ const struct inode_operations v9fs_file_inode_operations_dotl = {
 
 const struct inode_operations v9fs_symlink_inode_operations_dotl = {
 	.readlink = generic_readlink,
-	.follow_link = v9fs_vfs_follow_link_dotl,
-	.put_link = kfree_put_link,
+	.get_link = v9fs_vfs_get_link_dotl,
 	.getattr = v9fs_vfs_getattr_dotl,
 	.setattr = v9fs_vfs_setattr_dotl,
 	.setxattr = generic_setxattr,
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index bf495cedec26..de3ed8629196 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -87,7 +87,7 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
 		sb->s_op = &v9fs_super_ops;
 	sb->s_bdi = &v9ses->bdi;
 	if (v9ses->cache)
-		sb->s_bdi->ra_pages = (VM_MAX_READAHEAD * 1024)/PAGE_CACHE_SIZE;
+		sb->s_bdi->ra_pages = (VM_MAX_READAHEAD * 1024)/PAGE_SIZE;
 
 	sb->s_flags |= MS_ACTIVE | MS_DIRSYNC | MS_NOATIME;
 	if (!v9ses->cache)
diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c
index 0cf44b6cccd6..9dd9b47a6c1a 100644
--- a/fs/9p/xattr.c
+++ b/fs/9p/xattr.c
@@ -137,6 +137,44 @@ ssize_t v9fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
 	return v9fs_xattr_get(dentry, NULL, buffer, buffer_size);
 }
 
+static int v9fs_xattr_handler_get(const struct xattr_handler *handler,
+				  struct dentry *dentry, const char *name,
+				  void *buffer, size_t size)
+{
+	const char *full_name = xattr_full_name(handler, name);
+
+	return v9fs_xattr_get(dentry, full_name, buffer, size);
+}
+
+static int v9fs_xattr_handler_set(const struct xattr_handler *handler,
+				  struct dentry *dentry, const char *name,
+				  const void *value, size_t size, int flags)
+{
+	const char *full_name = xattr_full_name(handler, name);
+
+	return v9fs_xattr_set(dentry, full_name, value, size, flags);
+}
+
+static struct xattr_handler v9fs_xattr_user_handler = {
+	.prefix	= XATTR_USER_PREFIX,
+	.get	= v9fs_xattr_handler_get,
+	.set	= v9fs_xattr_handler_set,
+};
+
+static struct xattr_handler v9fs_xattr_trusted_handler = {
+	.prefix	= XATTR_TRUSTED_PREFIX,
+	.get	= v9fs_xattr_handler_get,
+	.set	= v9fs_xattr_handler_set,
+};
+
+#ifdef CONFIG_9P_FS_SECURITY
+static struct xattr_handler v9fs_xattr_security_handler = {
+	.prefix	= XATTR_SECURITY_PREFIX,
+	.get	= v9fs_xattr_handler_get,
+	.set	= v9fs_xattr_handler_set,
+};
+#endif
+
 const struct xattr_handler *v9fs_xattr_handlers[] = {
 	&v9fs_xattr_user_handler,
 	&v9fs_xattr_trusted_handler,
diff --git a/fs/9p/xattr.h b/fs/9p/xattr.h
index d3e2ea3840be..c63c3bea5de5 100644
--- a/fs/9p/xattr.h
+++ b/fs/9p/xattr.h
@@ -19,9 +19,6 @@
 #include <net/9p/client.h>
 
 extern const struct xattr_handler *v9fs_xattr_handlers[];
-extern struct xattr_handler v9fs_xattr_user_handler;
-extern struct xattr_handler v9fs_xattr_trusted_handler;
-extern struct xattr_handler v9fs_xattr_security_handler;
 extern const struct xattr_handler v9fs_xattr_acl_access_handler;
 extern const struct xattr_handler v9fs_xattr_acl_default_handler;
 
diff --git a/fs/9p/xattr_security.c b/fs/9p/xattr_security.c
deleted file mode 100644
index cb247a142a6e..000000000000
--- a/fs/9p/xattr_security.c
+++ /dev/null
@@ -1,80 +0,0 @@
-/*
- * Copyright IBM Corporation, 2010
- * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2.1 of the GNU Lesser General Public License
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- *
- */
-
-
-#include <linux/module.h>
-#include <linux/string.h>
-#include <linux/fs.h>
-#include <linux/slab.h>
-#include "xattr.h"
-
-static int v9fs_xattr_security_get(struct dentry *dentry, const char *name,
-			void *buffer, size_t size, int type)
-{
-	int retval;
-	char *full_name;
-	size_t name_len;
-	size_t prefix_len = XATTR_SECURITY_PREFIX_LEN;
-
-	if (name == NULL)
-		return -EINVAL;
-
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
-
-	name_len = strlen(name);
-	full_name = kmalloc(prefix_len + name_len + 1 , GFP_KERNEL);
-	if (!full_name)
-		return -ENOMEM;
-	memcpy(full_name, XATTR_SECURITY_PREFIX, prefix_len);
-	memcpy(full_name+prefix_len, name, name_len);
-	full_name[prefix_len + name_len] = '\0';
-
-	retval = v9fs_xattr_get(dentry, full_name, buffer, size);
-	kfree(full_name);
-	return retval;
-}
-
-static int v9fs_xattr_security_set(struct dentry *dentry, const char *name,
-			const void *value, size_t size, int flags, int type)
-{
-	int retval;
-	char *full_name;
-	size_t name_len;
-	size_t prefix_len = XATTR_SECURITY_PREFIX_LEN;
-
-	if (name == NULL)
-		return -EINVAL;
-
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
-
-	name_len = strlen(name);
-	full_name = kmalloc(prefix_len + name_len + 1 , GFP_KERNEL);
-	if (!full_name)
-		return -ENOMEM;
-	memcpy(full_name, XATTR_SECURITY_PREFIX, prefix_len);
-	memcpy(full_name + prefix_len, name, name_len);
-	full_name[prefix_len + name_len] = '\0';
-
-	retval = v9fs_xattr_set(dentry, full_name, value, size, flags);
-	kfree(full_name);
-	return retval;
-}
-
-struct xattr_handler v9fs_xattr_security_handler = {
-	.prefix	= XATTR_SECURITY_PREFIX,
-	.get	= v9fs_xattr_security_get,
-	.set	= v9fs_xattr_security_set,
-};
diff --git a/fs/9p/xattr_trusted.c b/fs/9p/xattr_trusted.c
deleted file mode 100644
index e30d33b8a3fb..000000000000
--- a/fs/9p/xattr_trusted.c
+++ /dev/null
@@ -1,80 +0,0 @@
-/*
- * Copyright IBM Corporation, 2010
- * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2.1 of the GNU Lesser General Public License
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- *
- */
-
-
-#include <linux/module.h>
-#include <linux/string.h>
-#include <linux/fs.h>
-#include <linux/slab.h>
-#include "xattr.h"
-
-static int v9fs_xattr_trusted_get(struct dentry *dentry, const char *name,
-			void *buffer, size_t size, int type)
-{
-	int retval;
-	char *full_name;
-	size_t name_len;
-	size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN;
-
-	if (name == NULL)
-		return -EINVAL;
-
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
-
-	name_len = strlen(name);
-	full_name = kmalloc(prefix_len + name_len + 1 , GFP_KERNEL);
-	if (!full_name)
-		return -ENOMEM;
-	memcpy(full_name, XATTR_TRUSTED_PREFIX, prefix_len);
-	memcpy(full_name+prefix_len, name, name_len);
-	full_name[prefix_len + name_len] = '\0';
-
-	retval = v9fs_xattr_get(dentry, full_name, buffer, size);
-	kfree(full_name);
-	return retval;
-}
-
-static int v9fs_xattr_trusted_set(struct dentry *dentry, const char *name,
-			const void *value, size_t size, int flags, int type)
-{
-	int retval;
-	char *full_name;
-	size_t name_len;
-	size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN;
-
-	if (name == NULL)
-		return -EINVAL;
-
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
-
-	name_len = strlen(name);
-	full_name = kmalloc(prefix_len + name_len + 1 , GFP_KERNEL);
-	if (!full_name)
-		return -ENOMEM;
-	memcpy(full_name, XATTR_TRUSTED_PREFIX, prefix_len);
-	memcpy(full_name + prefix_len, name, name_len);
-	full_name[prefix_len + name_len] = '\0';
-
-	retval = v9fs_xattr_set(dentry, full_name, value, size, flags);
-	kfree(full_name);
-	return retval;
-}
-
-struct xattr_handler v9fs_xattr_trusted_handler = {
-	.prefix	= XATTR_TRUSTED_PREFIX,
-	.get	= v9fs_xattr_trusted_get,
-	.set	= v9fs_xattr_trusted_set,
-};
diff --git a/fs/9p/xattr_user.c b/fs/9p/xattr_user.c
deleted file mode 100644
index d0b701b72080..000000000000
--- a/fs/9p/xattr_user.c
+++ /dev/null
@@ -1,80 +0,0 @@
-/*
- * Copyright IBM Corporation, 2010
- * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2.1 of the GNU Lesser General Public License
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- *
- */
-
-
-#include <linux/module.h>
-#include <linux/string.h>
-#include <linux/fs.h>
-#include <linux/slab.h>
-#include "xattr.h"
-
-static int v9fs_xattr_user_get(struct dentry *dentry, const char *name,
-			void *buffer, size_t size, int type)
-{
-	int retval;
-	char *full_name;
-	size_t name_len;
-	size_t prefix_len = XATTR_USER_PREFIX_LEN;
-
-	if (name == NULL)
-		return -EINVAL;
-
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
-
-	name_len = strlen(name);
-	full_name = kmalloc(prefix_len + name_len + 1 , GFP_KERNEL);
-	if (!full_name)
-		return -ENOMEM;
-	memcpy(full_name, XATTR_USER_PREFIX, prefix_len);
-	memcpy(full_name+prefix_len, name, name_len);
-	full_name[prefix_len + name_len] = '\0';
-
-	retval = v9fs_xattr_get(dentry, full_name, buffer, size);
-	kfree(full_name);
-	return retval;
-}
-
-static int v9fs_xattr_user_set(struct dentry *dentry, const char *name,
-			const void *value, size_t size, int flags, int type)
-{
-	int retval;
-	char *full_name;
-	size_t name_len;
-	size_t prefix_len = XATTR_USER_PREFIX_LEN;
-
-	if (name == NULL)
-		return -EINVAL;
-
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
-
-	name_len = strlen(name);
-	full_name = kmalloc(prefix_len + name_len + 1 , GFP_KERNEL);
-	if (!full_name)
-		return -ENOMEM;
-	memcpy(full_name, XATTR_USER_PREFIX, prefix_len);
-	memcpy(full_name + prefix_len, name, name_len);
-	full_name[prefix_len + name_len] = '\0';
-
-	retval = v9fs_xattr_set(dentry, full_name, value, size, flags);
-	kfree(full_name);
-	return retval;
-}
-
-struct xattr_handler v9fs_xattr_user_handler = {
-	.prefix	= XATTR_USER_PREFIX,
-	.get	= v9fs_xattr_user_get,
-	.set	= v9fs_xattr_user_set,
-};
diff --git a/fs/Kconfig b/fs/Kconfig
index da3f32f1a4e4..6725f59c18e6 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -46,6 +46,13 @@ config FS_DAX
 	  or if unsure, say N.  Saying Y will increase the size of the kernel
 	  by about 5kB.
 
+config FS_DAX_PMD
+	bool
+	default FS_DAX
+	depends on FS_DAX
+	depends on ZONE_DEVICE
+	depends on TRANSPARENT_HUGEPAGE
+
 endif # BLOCK
 
 # Posix ACL utility routines
@@ -67,6 +74,18 @@ config FILE_LOCKING
           for filesystems like NFS and for the flock() system
           call. Disabling this option saves about 11k.
 
+config MANDATORY_FILE_LOCKING
+	bool "Enable Mandatory file locking"
+	depends on FILE_LOCKING
+	default y
+	help
+	  This option enables files appropriately marked files on appropriely
+	  mounted filesystems to support mandatory locking.
+
+	  To the best of my knowledge this is dead code that no one cares about.
+
+source "fs/crypto/Kconfig"
+
 source "fs/notify/Kconfig"
 
 source "fs/quota/Kconfig"
@@ -190,6 +209,7 @@ menuconfig MISC_FILESYSTEMS
 
 if MISC_FILESYSTEMS
 
+source "fs/orangefs/Kconfig"
 source "fs/adfs/Kconfig"
 source "fs/affs/Kconfig"
 source "fs/ecryptfs/Kconfig"
diff --git a/fs/Makefile b/fs/Makefile
index 79f522575cba..85b6e13b62d3 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -30,6 +30,7 @@ obj-$(CONFIG_EVENTFD)		+= eventfd.o
 obj-$(CONFIG_USERFAULTFD)	+= userfaultfd.o
 obj-$(CONFIG_AIO)               += aio.o
 obj-$(CONFIG_FS_DAX)		+= dax.o
+obj-$(CONFIG_FS_ENCRYPTION)	+= crypto/
 obj-$(CONFIG_FILE_LOCKING)      += locks.o
 obj-$(CONFIG_COMPAT)		+= compat.o compat_ioctl.o
 obj-$(CONFIG_BINFMT_AOUT)	+= binfmt_aout.o
@@ -105,6 +106,7 @@ obj-$(CONFIG_AUTOFS4_FS)	+= autofs4/
 obj-$(CONFIG_ADFS_FS)		+= adfs/
 obj-$(CONFIG_FUSE_FS)		+= fuse/
 obj-$(CONFIG_OVERLAY_FS)	+= overlayfs/
+obj-$(CONFIG_ORANGEFS_FS)       += orangefs/
 obj-$(CONFIG_UDF_FS)		+= udf/
 obj-$(CONFIG_SUN_OPENPROMFS)	+= openpromfs/
 obj-$(CONFIG_OMFS_FS)		+= omfs/
diff --git a/fs/adfs/adfs.h b/fs/adfs/adfs.h
index 24575d9d882d..fadf408bdd46 100644
--- a/fs/adfs/adfs.h
+++ b/fs/adfs/adfs.h
@@ -44,24 +44,24 @@ struct adfs_dir_ops;
  */
 struct adfs_sb_info {
 	union { struct {
-		struct adfs_discmap *s_map;	/* bh list containing map	 */
-		struct adfs_dir_ops *s_dir;	/* directory operations		 */
+		struct adfs_discmap *s_map;	/* bh list containing map */
+		const struct adfs_dir_ops *s_dir; /* directory operations */
 		};
-		struct rcu_head rcu;		/* used only at shutdown time	 */
+		struct rcu_head rcu;	/* used only at shutdown time	 */
 	};
-	kuid_t		s_uid;		/* owner uid				 */
-	kgid_t		s_gid;		/* owner gid				 */
-	umode_t		s_owner_mask;	/* ADFS owner perm -> unix perm		 */
-	umode_t		s_other_mask;	/* ADFS other perm -> unix perm		 */
+	kuid_t		s_uid;		/* owner uid */
+	kgid_t		s_gid;		/* owner gid */
+	umode_t		s_owner_mask;	/* ADFS owner perm -> unix perm */
+	umode_t		s_other_mask;	/* ADFS other perm -> unix perm	*/
 	int		s_ftsuffix;	/* ,xyz hex filetype suffix option */
 
-	__u32		s_ids_per_zone;	/* max. no ids in one zone		 */
-	__u32		s_idlen;	/* length of ID in map			 */
-	__u32		s_map_size;	/* sector size of a map			 */
-	unsigned long	s_size;		/* total size (in blocks) of this fs	 */
-	signed int	s_map2blk;	/* shift left by this for map->sector	 */
-	unsigned int	s_log2sharesize;/* log2 share size			 */
-	__le32		s_version;	/* disc format version			 */
+	__u32		s_ids_per_zone;	/* max. no ids in one zone */
+	__u32		s_idlen;	/* length of ID in map */
+	__u32		s_map_size;	/* sector size of a map	*/
+	unsigned long	s_size;		/* total size (in blocks) of this fs */
+	signed int	s_map2blk;	/* shift left by this for map->sector*/
+	unsigned int	s_log2sharesize;/* log2 share size */
+	__le32		s_version;	/* disc format version */
 	unsigned int	s_namelen;	/* maximum number of characters in name	 */
 };
 
@@ -168,8 +168,8 @@ void __adfs_error(struct super_block *sb, const char *function,
 extern const struct inode_operations adfs_dir_inode_operations;
 extern const struct file_operations adfs_dir_operations;
 extern const struct dentry_operations adfs_dentry_operations;
-extern struct adfs_dir_ops adfs_f_dir_ops;
-extern struct adfs_dir_ops adfs_fplus_dir_ops;
+extern const struct adfs_dir_ops adfs_f_dir_ops;
+extern const struct adfs_dir_ops adfs_fplus_dir_ops;
 
 extern int adfs_dir_update(struct super_block *sb, struct object_info *obj,
 			   int wait);
diff --git a/fs/adfs/dir.c b/fs/adfs/dir.c
index 51c279a29845..fd4cf2c48e48 100644
--- a/fs/adfs/dir.c
+++ b/fs/adfs/dir.c
@@ -21,7 +21,7 @@ adfs_readdir(struct file *file, struct dir_context *ctx)
 {
 	struct inode *inode = file_inode(file);
 	struct super_block *sb = inode->i_sb;
-	struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir;
+	const struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir;
 	struct object_info obj;
 	struct adfs_dir dir;
 	int ret = 0;
@@ -69,7 +69,7 @@ adfs_dir_update(struct super_block *sb, struct object_info *obj, int wait)
 {
 	int ret = -EINVAL;
 #ifdef CONFIG_ADFS_FS_RW
-	struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir;
+	const struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir;
 	struct adfs_dir dir;
 
 	printk(KERN_INFO "adfs_dir_update: object %06X in dir %06X\n",
@@ -129,7 +129,7 @@ static int
 adfs_dir_lookup_byname(struct inode *inode, struct qstr *name, struct object_info *obj)
 {
 	struct super_block *sb = inode->i_sb;
-	struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir;
+	const struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir;
 	struct adfs_dir dir;
 	int ret;
 
diff --git a/fs/adfs/dir_f.c b/fs/adfs/dir_f.c
index 4bbe853ee50a..0fbfd0b04ae0 100644
--- a/fs/adfs/dir_f.c
+++ b/fs/adfs/dir_f.c
@@ -476,7 +476,7 @@ adfs_f_free(struct adfs_dir *dir)
 	dir->sb = NULL;
 }
 
-struct adfs_dir_ops adfs_f_dir_ops = {
+const struct adfs_dir_ops adfs_f_dir_ops = {
 	.read		= adfs_f_read,
 	.setpos		= adfs_f_setpos,
 	.getnext	= adfs_f_getnext,
diff --git a/fs/adfs/dir_fplus.c b/fs/adfs/dir_fplus.c
index 82d14cdf70f9..c92cfb638c18 100644
--- a/fs/adfs/dir_fplus.c
+++ b/fs/adfs/dir_fplus.c
@@ -256,7 +256,7 @@ adfs_fplus_free(struct adfs_dir *dir)
 	dir->sb = NULL;
 }
 
-struct adfs_dir_ops adfs_fplus_dir_ops = {
+const struct adfs_dir_ops adfs_fplus_dir_ops = {
 	.read		= adfs_fplus_read,
 	.setpos		= adfs_fplus_setpos,
 	.getnext	= adfs_fplus_getnext,
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index 4d4a0df8344f..c9fdfb112933 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -271,7 +271,7 @@ static int __init init_inodecache(void)
 	adfs_inode_cachep = kmem_cache_create("adfs_inode_cache",
 					     sizeof(struct adfs_inode_info),
 					     0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD),
+						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
 					     init_once);
 	if (adfs_inode_cachep == NULL)
 		return -ENOMEM;
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index c69a87eaf57d..cc2b2efc9211 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -138,7 +138,7 @@ extern int	affs_remove_hash(struct inode *dir, struct buffer_head *rem_bh);
 extern int	affs_remove_header(struct dentry *dentry);
 extern u32	affs_checksum_block(struct super_block *sb, struct buffer_head *bh);
 extern void	affs_fix_checksum(struct super_block *sb, struct buffer_head *bh);
-extern void	secs_to_datestamp(time_t secs, struct affs_date *ds);
+extern void	secs_to_datestamp(time64_t secs, struct affs_date *ds);
 extern umode_t	prot_to_mode(u32 prot);
 extern void	mode_to_prot(struct inode *inode);
 __printf(3, 4)
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index 5fa92bc790ef..d6c7a51c93e4 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -8,6 +8,7 @@
  *  Please send bug reports to: hjw@zvw.de
  */
 
+#include <linux/math64.h>
 #include "affs.h"
 
 /*
@@ -366,22 +367,22 @@ affs_fix_checksum(struct super_block *sb, struct buffer_head *bh)
 }
 
 void
-secs_to_datestamp(time_t secs, struct affs_date *ds)
+secs_to_datestamp(time64_t secs, struct affs_date *ds)
 {
 	u32	 days;
 	u32	 minute;
+	s32	 rem;
 
 	secs -= sys_tz.tz_minuteswest * 60 + ((8 * 365 + 2) * 24 * 60 * 60);
 	if (secs < 0)
 		secs = 0;
-	days    = secs / 86400;
-	secs   -= days * 86400;
-	minute  = secs / 60;
-	secs   -= minute * 60;
+	days    = div_s64_rem(secs, 86400, &rem);
+	minute  = rem / 60;
+	rem    -= minute * 60;
 
 	ds->days = cpu_to_be32(days);
 	ds->mins = cpu_to_be32(minute);
-	ds->ticks = cpu_to_be32(secs * 50);
+	ds->ticks = cpu_to_be32(rem * 50);
 }
 
 umode_t
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 659c579c4588..0cde550050e8 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -33,11 +33,11 @@ affs_file_release(struct inode *inode, struct file *filp)
 		 inode->i_ino, atomic_read(&AFFS_I(inode)->i_opencnt));
 
 	if (atomic_dec_and_test(&AFFS_I(inode)->i_opencnt)) {
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		if (inode->i_size != AFFS_I(inode)->mmu_private)
 			affs_truncate(inode);
 		affs_free_prealloc(inode);
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 	}
 
 	return 0;
@@ -510,11 +510,9 @@ affs_do_readpage_ofs(struct page *page, unsigned to)
 
 	pr_debug("%s(%lu, %ld, 0, %d)\n", __func__, inode->i_ino,
 		 page->index, to);
-	BUG_ON(to > PAGE_CACHE_SIZE);
-	kmap(page);
-	data = page_address(page);
+	BUG_ON(to > PAGE_SIZE);
 	bsize = AFFS_SB(sb)->s_data_blksize;
-	tmp = page->index << PAGE_CACHE_SHIFT;
+	tmp = page->index << PAGE_SHIFT;
 	bidx = tmp / bsize;
 	boff = tmp % bsize;
 
@@ -524,14 +522,15 @@ affs_do_readpage_ofs(struct page *page, unsigned to)
 			return PTR_ERR(bh);
 		tmp = min(bsize - boff, to - pos);
 		BUG_ON(pos + tmp > to || tmp > bsize);
+		data = kmap_atomic(page);
 		memcpy(data + pos, AFFS_DATA(bh) + boff, tmp);
+		kunmap_atomic(data);
 		affs_brelse(bh);
 		bidx++;
 		pos += tmp;
 		boff = 0;
 	}
 	flush_dcache_page(page);
-	kunmap(page);
 	return 0;
 }
 
@@ -614,10 +613,10 @@ affs_readpage_ofs(struct file *file, struct page *page)
 	int err;
 
 	pr_debug("%s(%lu, %ld)\n", __func__, inode->i_ino, page->index);
-	to = PAGE_CACHE_SIZE;
-	if (((page->index + 1) << PAGE_CACHE_SHIFT) > inode->i_size) {
-		to = inode->i_size & ~PAGE_CACHE_MASK;
-		memset(page_address(page) + to, 0, PAGE_CACHE_SIZE - to);
+	to = PAGE_SIZE;
+	if (((page->index + 1) << PAGE_SHIFT) > inode->i_size) {
+		to = inode->i_size & ~PAGE_MASK;
+		memset(page_address(page) + to, 0, PAGE_SIZE - to);
 	}
 
 	err = affs_do_readpage_ofs(page, to);
@@ -647,7 +646,7 @@ static int affs_write_begin_ofs(struct file *file, struct address_space *mapping
 			return err;
 	}
 
-	index = pos >> PAGE_CACHE_SHIFT;
+	index = pos >> PAGE_SHIFT;
 	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
 		return -ENOMEM;
@@ -657,10 +656,10 @@ static int affs_write_begin_ofs(struct file *file, struct address_space *mapping
 		return 0;
 
 	/* XXX: inefficient but safe in the face of short writes */
-	err = affs_do_readpage_ofs(page, PAGE_CACHE_SIZE);
+	err = affs_do_readpage_ofs(page, PAGE_SIZE);
 	if (err) {
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 	}
 	return err;
 }
@@ -678,7 +677,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
 	u32 tmp;
 	int written;
 
-	from = pos & (PAGE_CACHE_SIZE - 1);
+	from = pos & (PAGE_SIZE - 1);
 	to = pos + len;
 	/*
 	 * XXX: not sure if this can handle short copies (len < copied), but
@@ -693,7 +692,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
 
 	bh = NULL;
 	written = 0;
-	tmp = (page->index << PAGE_CACHE_SHIFT) + from;
+	tmp = (page->index << PAGE_SHIFT) + from;
 	bidx = tmp / bsize;
 	boff = tmp % bsize;
 	if (boff) {
@@ -789,13 +788,13 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
 
 done:
 	affs_brelse(bh);
-	tmp = (page->index << PAGE_CACHE_SHIFT) + from;
+	tmp = (page->index << PAGE_SHIFT) + from;
 	if (tmp > inode->i_size)
 		inode->i_size = AFFS_I(inode)->mmu_private = tmp;
 
 err_first_bh:
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 
 	return written;
 
@@ -958,12 +957,12 @@ int affs_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
 	if (err)
 		return err;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	ret = write_inode_now(inode, 0);
 	err = sync_blockdev(inode->i_sb->s_bdev);
 	if (!ret)
 		ret = err;
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return ret;
 }
 const struct file_operations affs_file_operations = {
diff --git a/fs/affs/inode.c b/fs/affs/inode.c
index 17349500592d..0fdb0f5b2239 100644
--- a/fs/affs/inode.c
+++ b/fs/affs/inode.c
@@ -140,6 +140,7 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino)
 		break;
 	case ST_SOFTLINK:
 		inode->i_mode |= S_IFLNK;
+		inode_nohighmem(inode);
 		inode->i_op = &affs_symlink_inode_operations;
 		inode->i_data.a_ops = &affs_symlink_aops;
 		break;
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index 181e05b46e72..00d3002a6780 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -344,6 +344,7 @@ affs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
 		return -ENOSPC;
 
 	inode->i_op = &affs_symlink_inode_operations;
+	inode_nohighmem(inode);
 	inode->i_data.a_ops = &affs_symlink_aops;
 	inode->i_mode = S_IFLNK | 0777;
 	mode_to_prot(inode);
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 5b50c4ca43a7..2a6713b6b9f4 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -32,7 +32,7 @@ affs_commit_super(struct super_block *sb, int wait)
 	struct affs_root_tail *tail = AFFS_ROOT_TAIL(sb, bh);
 
 	lock_buffer(bh);
-	secs_to_datestamp(get_seconds(), &tail->disk_change);
+	secs_to_datestamp(ktime_get_real_seconds(), &tail->disk_change);
 	affs_fix_checksum(sb, bh);
 	unlock_buffer(bh);
 
@@ -132,7 +132,7 @@ static int __init init_inodecache(void)
 	affs_inode_cachep = kmem_cache_create("affs_inode_cache",
 					     sizeof(struct affs_inode_info),
 					     0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD),
+						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
 					     init_once);
 	if (affs_inode_cachep == NULL)
 		return -ENOMEM;
diff --git a/fs/affs/symlink.c b/fs/affs/symlink.c
index ea5b69a18ba9..69b03dbb792f 100644
--- a/fs/affs/symlink.c
+++ b/fs/affs/symlink.c
@@ -14,13 +14,13 @@ static int affs_symlink_readpage(struct file *file, struct page *page)
 {
 	struct buffer_head *bh;
 	struct inode *inode = page->mapping->host;
-	char *link = kmap(page);
+	char *link = page_address(page);
 	struct slink_front *lf;
 	int			 i, j;
 	char			 c;
 	char			 lc;
 
-	pr_debug("follow_link(ino=%lu)\n", inode->i_ino);
+	pr_debug("get_link(ino=%lu)\n", inode->i_ino);
 
 	bh = affs_bread(inode->i_sb, inode->i_ino);
 	if (!bh)
@@ -57,12 +57,10 @@ static int affs_symlink_readpage(struct file *file, struct page *page)
 	link[i] = '\0';
 	affs_brelse(bh);
 	SetPageUptodate(page);
-	kunmap(page);
 	unlock_page(page);
 	return 0;
 fail:
 	SetPageError(page);
-	kunmap(page);
 	unlock_page(page);
 	return -EIO;
 }
@@ -73,7 +71,6 @@ const struct address_space_operations affs_symlink_aops = {
 
 const struct inode_operations affs_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 	.setattr	= affs_notify_change,
 };
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index e10e17788f06..5fda2bc53cd7 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -181,7 +181,7 @@ error:
 static inline void afs_dir_put_page(struct page *page)
 {
 	kunmap(page);
-	page_cache_release(page);
+	put_page(page);
 }
 
 /*
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 999bc3caec92..6344aee4ac4b 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -164,7 +164,7 @@ int afs_page_filler(void *data, struct page *page)
 		_debug("cache said ENOBUFS");
 	default:
 	go_on:
-		offset = page->index << PAGE_CACHE_SHIFT;
+		offset = page->index << PAGE_SHIFT;
 		len = min_t(size_t, i_size_read(inode) - offset, PAGE_SIZE);
 
 		/* read the contents of the file from the server into the
@@ -319,7 +319,7 @@ static void afs_invalidatepage(struct page *page, unsigned int offset,
 	BUG_ON(!PageLocked(page));
 
 	/* we clean up only if the entire page is being invalidated */
-	if (offset == 0 && length == PAGE_CACHE_SIZE) {
+	if (offset == 0 && length == PAGE_SIZE) {
 #ifdef CONFIG_AFS_FSCACHE
 		if (PageFsCache(page)) {
 			struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
diff --git a/fs/afs/flock.c b/fs/afs/flock.c
index 4baf1d2b39e4..d91a9c9cfbd0 100644
--- a/fs/afs/flock.c
+++ b/fs/afs/flock.c
@@ -483,7 +483,7 @@ static int afs_do_getlk(struct file *file, struct file_lock *fl)
 
 	fl->fl_type = F_UNLCK;
 
-	mutex_lock(&vnode->vfs_inode.i_mutex);
+	inode_lock(&vnode->vfs_inode);
 
 	/* check local lock records first */
 	ret = 0;
@@ -505,7 +505,7 @@ static int afs_do_getlk(struct file *file, struct file_lock *fl)
 	}
 
 error:
-	mutex_unlock(&vnode->vfs_inode.i_mutex);
+	inode_unlock(&vnode->vfs_inode);
 	_leave(" = %d [%hd]", ret, fl->fl_type);
 	return ret;
 }
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index e06f5a23352a..86cc7264c21c 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -56,6 +56,7 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key)
 	case AFS_FTYPE_SYMLINK:
 		inode->i_mode	= S_IFLNK | vnode->status.mode;
 		inode->i_op	= &page_symlink_inode_operations;
+		inode_nohighmem(inode);
 		break;
 	default:
 		printk("kAFS: AFS vnode with undefined type\n");
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index ccd0b212e82a..81dd075356b9 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -93,7 +93,7 @@ int afs_mntpt_check_symlink(struct afs_vnode *vnode, struct key *key)
 
 	kunmap(page);
 out_free:
-	page_cache_release(page);
+	put_page(page);
 out:
 	_leave(" = %d", ret);
 	return ret;
@@ -189,7 +189,7 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
 		buf = kmap_atomic(page);
 		memcpy(devname, buf, size);
 		kunmap_atomic(buf);
-		page_cache_release(page);
+		put_page(page);
 		page = NULL;
 	}
 
@@ -211,7 +211,7 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
 	return mnt;
 
 error:
-	page_cache_release(page);
+	put_page(page);
 error_no_page:
 	free_page((unsigned long) options);
 error_no_options:
diff --git a/fs/afs/proc.c b/fs/afs/proc.c
index 24a905b076fd..2853b4095344 100644
--- a/fs/afs/proc.c
+++ b/fs/afs/proc.c
@@ -230,14 +230,9 @@ static ssize_t afs_proc_cells_write(struct file *file, const char __user *buf,
 	if (size <= 1 || size >= PAGE_SIZE)
 		return -EINVAL;
 
-	kbuf = kmalloc(size + 1, GFP_KERNEL);
-	if (!kbuf)
-		return -ENOMEM;
-
-	ret = -EFAULT;
-	if (copy_from_user(kbuf, buf, size) != 0)
-		goto done;
-	kbuf[size] = 0;
+	kbuf = memdup_user_nul(buf, size);
+	if (IS_ERR(kbuf))
+		return PTR_ERR(kbuf);
 
 	/* trim to first NL */
 	name = memchr(kbuf, '\n', size);
@@ -315,15 +310,9 @@ static ssize_t afs_proc_rootcell_write(struct file *file,
 	if (size <= 1 || size >= PAGE_SIZE)
 		return -EINVAL;
 
-	ret = -ENOMEM;
-	kbuf = kmalloc(size + 1, GFP_KERNEL);
-	if (!kbuf)
-		goto nomem;
-
-	ret = -EFAULT;
-	if (copy_from_user(kbuf, buf, size) != 0)
-		goto infault;
-	kbuf[size] = 0;
+	kbuf = memdup_user_nul(buf, size);
+	if (IS_ERR(kbuf))
+		return PTR_ERR(kbuf);
 
 	/* trim to first NL */
 	s = memchr(kbuf, '\n', size);
@@ -337,9 +326,7 @@ static ssize_t afs_proc_rootcell_write(struct file *file,
 	if (ret >= 0)
 		ret = size;	/* consume everything, always */
 
-infault:
 	kfree(kbuf);
-nomem:
 	_leave(" = %d", ret);
 	return ret;
 }
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 1fb4a5129f7d..fbdb022b75a2 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -91,7 +91,7 @@ int __init afs_fs_init(void)
 	afs_inode_cachep = kmem_cache_create("afs_inode_cache",
 					     sizeof(struct afs_vnode),
 					     0,
-					     SLAB_HWCACHE_ALIGN,
+					     SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT,
 					     afs_i_init_once);
 	if (!afs_inode_cachep) {
 		printk(KERN_NOTICE "kAFS: Failed to allocate inode cache\n");
@@ -315,8 +315,8 @@ static int afs_fill_super(struct super_block *sb,
 	_enter("");
 
 	/* fill in the superblock */
-	sb->s_blocksize		= PAGE_CACHE_SIZE;
-	sb->s_blocksize_bits	= PAGE_CACHE_SHIFT;
+	sb->s_blocksize		= PAGE_SIZE;
+	sb->s_blocksize_bits	= PAGE_SHIFT;
 	sb->s_magic		= AFS_FS_MAGIC;
 	sb->s_op		= &afs_super_ops;
 	sb->s_bdi		= &as->volume->bdi;
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 0714abcd7f32..65de439bdc4f 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -93,10 +93,10 @@ static int afs_fill_page(struct afs_vnode *vnode, struct key *key,
 	_enter(",,%llu", (unsigned long long)pos);
 
 	i_size = i_size_read(&vnode->vfs_inode);
-	if (pos + PAGE_CACHE_SIZE > i_size)
+	if (pos + PAGE_SIZE > i_size)
 		len = i_size - pos;
 	else
-		len = PAGE_CACHE_SIZE;
+		len = PAGE_SIZE;
 
 	ret = afs_vnode_fetch_data(vnode, key, pos, len, page);
 	if (ret < 0) {
@@ -123,9 +123,9 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
 	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
 	struct page *page;
 	struct key *key = file->private_data;
-	unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+	unsigned from = pos & (PAGE_SIZE - 1);
 	unsigned to = from + len;
-	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+	pgoff_t index = pos >> PAGE_SHIFT;
 	int ret;
 
 	_enter("{%x:%u},{%lx},%u,%u",
@@ -151,8 +151,8 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
 	*pagep = page;
 	/* page won't leak in error case: it eventually gets cleaned off LRU */
 
-	if (!PageUptodate(page) && len != PAGE_CACHE_SIZE) {
-		ret = afs_fill_page(vnode, key, index << PAGE_CACHE_SHIFT, page);
+	if (!PageUptodate(page) && len != PAGE_SIZE) {
+		ret = afs_fill_page(vnode, key, index << PAGE_SHIFT, page);
 		if (ret < 0) {
 			kfree(candidate);
 			_leave(" = %d [prep]", ret);
@@ -266,7 +266,7 @@ int afs_write_end(struct file *file, struct address_space *mapping,
 	if (PageDirty(page))
 		_debug("dirtied");
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 
 	return copied;
 }
@@ -480,7 +480,7 @@ static int afs_writepages_region(struct address_space *mapping,
 
 		if (page->index > end) {
 			*_next = index;
-			page_cache_release(page);
+			put_page(page);
 			_leave(" = 0 [%lx]", *_next);
 			return 0;
 		}
@@ -494,7 +494,7 @@ static int afs_writepages_region(struct address_space *mapping,
 
 		if (page->mapping != mapping) {
 			unlock_page(page);
-			page_cache_release(page);
+			put_page(page);
 			continue;
 		}
 
@@ -515,7 +515,7 @@ static int afs_writepages_region(struct address_space *mapping,
 
 		ret = afs_write_back_from_locked_page(wb, page);
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 		if (ret < 0) {
 			_leave(" = %d", ret);
 			return ret;
@@ -551,13 +551,13 @@ int afs_writepages(struct address_space *mapping,
 						    &next);
 		mapping->writeback_index = next;
 	} else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) {
-		end = (pgoff_t)(LLONG_MAX >> PAGE_CACHE_SHIFT);
+		end = (pgoff_t)(LLONG_MAX >> PAGE_SHIFT);
 		ret = afs_writepages_region(mapping, wbc, 0, end, &next);
 		if (wbc->nr_to_write > 0)
 			mapping->writeback_index = next;
 	} else {
-		start = wbc->range_start >> PAGE_CACHE_SHIFT;
-		end = wbc->range_end >> PAGE_CACHE_SHIFT;
+		start = wbc->range_start >> PAGE_SHIFT;
+		end = wbc->range_end >> PAGE_SHIFT;
 		ret = afs_writepages_region(mapping, wbc, start, end, &next);
 	}
 
@@ -693,7 +693,7 @@ int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
 	if (ret)
 		return ret;
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	/* use a writeback record as a marker in the queue - when this reaches
 	 * the front of the queue, all the outstanding writes are either
@@ -735,7 +735,7 @@ int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	afs_put_writeback(wb);
 	_leave(" = %d", ret);
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return ret;
 }
 
diff --git a/fs/attr.c b/fs/attr.c
index 6530ced19697..25b24d0f6c88 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -195,7 +195,7 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de
 	struct timespec now;
 	unsigned int ia_valid = attr->ia_valid;
 
-	WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex));
+	WARN_ON_ONCE(!inode_is_locked(inode));
 
 	if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) {
 		if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index c37149b929be..f0d268b97d19 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -1,15 +1,11 @@
-/* -*- c -*- ------------------------------------------------------------- *
- *   
- * linux/fs/autofs/autofs_i.h
- *
- *   Copyright 1997-1998 Transmeta Corporation - All Rights Reserved
- *   Copyright 2005-2006 Ian Kent <raven@themaw.net>
+/*
+ *  Copyright 1997-1998 Transmeta Corporation - All Rights Reserved
+ *  Copyright 2005-2006 Ian Kent <raven@themaw.net>
  *
  * This file is part of the Linux kernel and is made available under
  * the terms of the GNU General Public License, version 2, or at your
  * option, any later version, incorporated herein by reference.
- *
- * ----------------------------------------------------------------------- */
+ */
 
 /* Internal header file for autofs */
 
@@ -35,28 +31,23 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <asm/current.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* #define DEBUG */
 
-#define DPRINTK(fmt, ...)				\
-	pr_debug("pid %d: %s: " fmt "\n",		\
-		current->pid, __func__, ##__VA_ARGS__)
-
-#define AUTOFS_WARN(fmt, ...)				\
-	printk(KERN_WARNING "pid %d: %s: " fmt "\n",	\
-		current->pid, __func__, ##__VA_ARGS__)
-
-#define AUTOFS_ERROR(fmt, ...)				\
-	printk(KERN_ERR "pid %d: %s: " fmt "\n",	\
-		current->pid, __func__, ##__VA_ARGS__)
-
-/* Unified info structure.  This is pointed to by both the dentry and
-   inode structures.  Each file in the filesystem has an instance of this
-   structure.  It holds a reference to the dentry, so dentries are never
-   flushed while the file exists.  All name lookups are dealt with at the
-   dentry level, although the filesystem can interfere in the validation
-   process.  Readdir is implemented by traversing the dentry lists. */
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+#define pr_fmt(fmt) KBUILD_MODNAME ":pid:%d:%s: " fmt, current->pid, __func__
+
+/*
+ * Unified info structure.  This is pointed to by both the dentry and
+ * inode structures.  Each file in the filesystem has an instance of this
+ * structure.  It holds a reference to the dentry, so dentries are never
+ * flushed while the file exists.  All name lookups are dealt with at the
+ * dentry level, although the filesystem can interfere in the validation
+ * process.  Readdir is implemented by traversing the dentry lists.
+ */
 struct autofs_info {
 	struct dentry	*dentry;
 	struct inode	*inode;
@@ -78,7 +69,7 @@ struct autofs_info {
 	kgid_t gid;
 };
 
-#define AUTOFS_INF_EXPIRING	(1<<0) /* dentry is in the process of expiring */
+#define AUTOFS_INF_EXPIRING	(1<<0) /* dentry in the process of expiring */
 #define AUTOFS_INF_NO_RCU	(1<<1) /* the dentry is being considered
 					* for expiry, so RCU_walk is
 					* not permitted
@@ -140,10 +131,11 @@ static inline struct autofs_info *autofs4_dentry_ino(struct dentry *dentry)
 }
 
 /* autofs4_oz_mode(): do we see the man behind the curtain?  (The
-   processes which do manipulations for us in user space sees the raw
-   filesystem without "magic".) */
-
-static inline int autofs4_oz_mode(struct autofs_sb_info *sbi) {
+ * processes which do manipulations for us in user space sees the raw
+ * filesystem without "magic".)
+ */
+static inline int autofs4_oz_mode(struct autofs_sb_info *sbi)
+{
 	return sbi->catatonic || task_pgrp(current) == sbi->oz_pgrp;
 }
 
@@ -154,12 +146,12 @@ void autofs4_free_ino(struct autofs_info *);
 int is_autofs4_dentry(struct dentry *);
 int autofs4_expire_wait(struct dentry *dentry, int rcu_walk);
 int autofs4_expire_run(struct super_block *, struct vfsmount *,
-			struct autofs_sb_info *,
-			struct autofs_packet_expire __user *);
+		       struct autofs_sb_info *,
+		       struct autofs_packet_expire __user *);
 int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt,
 			    struct autofs_sb_info *sbi, int when);
 int autofs4_expire_multi(struct super_block *, struct vfsmount *,
-			struct autofs_sb_info *, int __user *);
+			 struct autofs_sb_info *, int __user *);
 struct dentry *autofs4_expire_direct(struct super_block *sb,
 				     struct vfsmount *mnt,
 				     struct autofs_sb_info *sbi, int how);
@@ -224,8 +216,8 @@ static inline int autofs_prepare_pipe(struct file *pipe)
 
 /* Queue management functions */
 
-int autofs4_wait(struct autofs_sb_info *,struct dentry *, enum autofs_notify);
-int autofs4_wait_release(struct autofs_sb_info *,autofs_wqt_t,int);
+int autofs4_wait(struct autofs_sb_info *, struct dentry *, enum autofs_notify);
+int autofs4_wait_release(struct autofs_sb_info *, autofs_wqt_t, int);
 void autofs4_catatonic_mode(struct autofs_sb_info *);
 
 static inline u32 autofs4_get_dev(struct autofs_sb_info *sbi)
@@ -242,37 +234,37 @@ static inline void __autofs4_add_expiring(struct dentry *dentry)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
+
 	if (ino) {
 		if (list_empty(&ino->expiring))
 			list_add(&ino->expiring, &sbi->expiring_list);
 	}
-	return;
 }
 
 static inline void autofs4_add_expiring(struct dentry *dentry)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
+
 	if (ino) {
 		spin_lock(&sbi->lookup_lock);
 		if (list_empty(&ino->expiring))
 			list_add(&ino->expiring, &sbi->expiring_list);
 		spin_unlock(&sbi->lookup_lock);
 	}
-	return;
 }
 
 static inline void autofs4_del_expiring(struct dentry *dentry)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
+
 	if (ino) {
 		spin_lock(&sbi->lookup_lock);
 		if (!list_empty(&ino->expiring))
 			list_del_init(&ino->expiring);
 		spin_unlock(&sbi->lookup_lock);
 	}
-	return;
 }
 
 extern void autofs4_kill_sb(struct super_block *);
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index ac7d921ed984..c7fcc7438843 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -72,13 +72,13 @@ static int check_dev_ioctl_version(int cmd, struct autofs_dev_ioctl *param)
 {
 	int err = 0;
 
-	if ((AUTOFS_DEV_IOCTL_VERSION_MAJOR != param->ver_major) ||
-	    (AUTOFS_DEV_IOCTL_VERSION_MINOR < param->ver_minor)) {
-		AUTOFS_WARN("ioctl control interface version mismatch: "
-		     "kernel(%u.%u), user(%u.%u), cmd(%d)",
-		     AUTOFS_DEV_IOCTL_VERSION_MAJOR,
-		     AUTOFS_DEV_IOCTL_VERSION_MINOR,
-		     param->ver_major, param->ver_minor, cmd);
+	if ((param->ver_major != AUTOFS_DEV_IOCTL_VERSION_MAJOR) ||
+	    (param->ver_minor > AUTOFS_DEV_IOCTL_VERSION_MINOR)) {
+		pr_warn("ioctl control interface version mismatch: "
+			"kernel(%u.%u), user(%u.%u), cmd(%d)\n",
+			AUTOFS_DEV_IOCTL_VERSION_MAJOR,
+			AUTOFS_DEV_IOCTL_VERSION_MINOR,
+			param->ver_major, param->ver_minor, cmd);
 		err = -EINVAL;
 	}
 
@@ -93,7 +93,8 @@ static int check_dev_ioctl_version(int cmd, struct autofs_dev_ioctl *param)
  * Copy parameter control struct, including a possible path allocated
  * at the end of the struct.
  */
-static struct autofs_dev_ioctl *copy_dev_ioctl(struct autofs_dev_ioctl __user *in)
+static struct autofs_dev_ioctl *
+		copy_dev_ioctl(struct autofs_dev_ioctl __user *in)
 {
 	struct autofs_dev_ioctl tmp, *res;
 
@@ -116,7 +117,6 @@ static struct autofs_dev_ioctl *copy_dev_ioctl(struct autofs_dev_ioctl __user *i
 static inline void free_dev_ioctl(struct autofs_dev_ioctl *param)
 {
 	kfree(param);
-	return;
 }
 
 /*
@@ -129,24 +129,24 @@ static int validate_dev_ioctl(int cmd, struct autofs_dev_ioctl *param)
 
 	err = check_dev_ioctl_version(cmd, param);
 	if (err) {
-		AUTOFS_WARN("invalid device control module version "
-		     "supplied for cmd(0x%08x)", cmd);
+		pr_warn("invalid device control module version "
+			"supplied for cmd(0x%08x)\n", cmd);
 		goto out;
 	}
 
 	if (param->size > sizeof(*param)) {
 		err = invalid_str(param->path, param->size - sizeof(*param));
 		if (err) {
-			AUTOFS_WARN(
-			  "path string terminator missing for cmd(0x%08x)",
+			pr_warn(
+			  "path string terminator missing for cmd(0x%08x)\n",
 			  cmd);
 			goto out;
 		}
 
 		err = check_name(param->path);
 		if (err) {
-			AUTOFS_WARN("invalid path supplied for cmd(0x%08x)",
-				    cmd);
+			pr_warn("invalid path supplied for cmd(0x%08x)\n",
+				cmd);
 			goto out;
 		}
 	}
@@ -197,7 +197,9 @@ static int find_autofs_mount(const char *pathname,
 			     void *data)
 {
 	struct path path;
-	int err = kern_path_mountpoint(AT_FDCWD, pathname, &path, 0);
+	int err;
+
+	err = kern_path_mountpoint(AT_FDCWD, pathname, &path, 0);
 	if (err)
 		return err;
 	err = -ENOENT;
@@ -225,6 +227,7 @@ static int test_by_dev(struct path *path, void *p)
 static int test_by_type(struct path *path, void *p)
 {
 	struct autofs_info *ino = autofs4_dentry_ino(path->dentry);
+
 	return ino && ino->sbi->type & *(unsigned *)p;
 }
 
@@ -370,7 +373,7 @@ static int autofs_dev_ioctl_setpipefd(struct file *fp,
 		new_pid = get_task_pid(current, PIDTYPE_PGID);
 
 		if (ns_of_pid(new_pid) != ns_of_pid(sbi->oz_pgrp)) {
-			AUTOFS_WARN("Not allowed to change PID namespace");
+			pr_warn("not allowed to change PID namespace\n");
 			err = -EINVAL;
 			goto out;
 		}
@@ -456,8 +459,10 @@ static int autofs_dev_ioctl_requester(struct file *fp,
 		err = 0;
 		autofs4_expire_wait(path.dentry, 0);
 		spin_lock(&sbi->fs_lock);
-		param->requester.uid = from_kuid_munged(current_user_ns(), ino->uid);
-		param->requester.gid = from_kgid_munged(current_user_ns(), ino->gid);
+		param->requester.uid =
+			from_kuid_munged(current_user_ns(), ino->uid);
+		param->requester.gid =
+			from_kgid_munged(current_user_ns(), ino->gid);
 		spin_unlock(&sbi->fs_lock);
 	}
 	path_put(&path);
@@ -619,7 +624,8 @@ static ioctl_fn lookup_dev_ioctl(unsigned int cmd)
 }
 
 /* ioctl dispatcher */
-static int _autofs_dev_ioctl(unsigned int command, struct autofs_dev_ioctl __user *user)
+static int _autofs_dev_ioctl(unsigned int command,
+			     struct autofs_dev_ioctl __user *user)
 {
 	struct autofs_dev_ioctl *param;
 	struct file *fp;
@@ -655,7 +661,7 @@ static int _autofs_dev_ioctl(unsigned int command, struct autofs_dev_ioctl __use
 
 	fn = lookup_dev_ioctl(cmd);
 	if (!fn) {
-		AUTOFS_WARN("unknown command 0x%08x", command);
+		pr_warn("unknown command 0x%08x\n", command);
 		return -ENOTTY;
 	}
 
@@ -711,6 +717,7 @@ out:
 static long autofs_dev_ioctl(struct file *file, uint command, ulong u)
 {
 	int err;
+
 	err = _autofs_dev_ioctl(command, (struct autofs_dev_ioctl __user *) u);
 	return (long) err;
 }
@@ -733,8 +740,8 @@ static const struct file_operations _dev_ioctl_fops = {
 
 static struct miscdevice _autofs_dev_ioctl_misc = {
 	.minor		= AUTOFS_MINOR,
-	.name  		= AUTOFS_DEVICE_NAME,
-	.fops  		= &_dev_ioctl_fops
+	.name		= AUTOFS_DEVICE_NAME,
+	.fops		= &_dev_ioctl_fops
 };
 
 MODULE_ALIAS_MISCDEV(AUTOFS_MINOR);
@@ -747,7 +754,7 @@ int __init autofs_dev_ioctl_init(void)
 
 	r = misc_register(&_autofs_dev_ioctl_misc);
 	if (r) {
-		AUTOFS_ERROR("misc_register failed for control device");
+		pr_err("misc_register failed for control device\n");
 		return r;
 	}
 
@@ -757,6 +764,4 @@ int __init autofs_dev_ioctl_init(void)
 void autofs_dev_ioctl_exit(void)
 {
 	misc_deregister(&_autofs_dev_ioctl_misc);
-	return;
 }
-
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 1cebc3c52fa5..9510d8d2e9cd 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -1,16 +1,12 @@
-/* -*- c -*- --------------------------------------------------------------- *
- *
- * linux/fs/autofs/expire.c
- *
- *  Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
- *  Copyright 1999-2000 Jeremy Fitzhardinge <jeremy@goop.org>
- *  Copyright 2001-2006 Ian Kent <raven@themaw.net>
+/*
+ * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
+ * Copyright 1999-2000 Jeremy Fitzhardinge <jeremy@goop.org>
+ * Copyright 2001-2006 Ian Kent <raven@themaw.net>
  *
  * This file is part of the Linux kernel and is made available under
  * the terms of the GNU General Public License, version 2, or at your
  * option, any later version, incorporated herein by reference.
- *
- * ------------------------------------------------------------------------- */
+ */
 
 #include "autofs_i.h"
 
@@ -18,7 +14,7 @@ static unsigned long now;
 
 /* Check if a dentry can be expired */
 static inline int autofs4_can_expire(struct dentry *dentry,
-					unsigned long timeout, int do_now)
+				     unsigned long timeout, int do_now)
 {
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
 
@@ -41,7 +37,7 @@ static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry)
 	struct path path = {.mnt = mnt, .dentry = dentry};
 	int status = 1;
 
-	DPRINTK("dentry %p %pd", dentry, dentry);
+	pr_debug("dentry %p %pd\n", dentry, dentry);
 
 	path_get(&path);
 
@@ -58,14 +54,16 @@ static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry)
 
 	/* Update the expiry counter if fs is busy */
 	if (!may_umount_tree(path.mnt)) {
-		struct autofs_info *ino = autofs4_dentry_ino(top);
+		struct autofs_info *ino;
+
+		ino = autofs4_dentry_ino(top);
 		ino->last_used = jiffies;
 		goto done;
 	}
 
 	status = 0;
 done:
-	DPRINTK("returning = %d", status);
+	pr_debug("returning = %d\n", status);
 	path_put(&path);
 	return status;
 }
@@ -74,7 +72,7 @@ done:
  * Calculate and dget next entry in the subdirs list under root.
  */
 static struct dentry *get_next_positive_subdir(struct dentry *prev,
-						struct dentry *root)
+					       struct dentry *root)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(root->d_sb);
 	struct list_head *next;
@@ -121,7 +119,7 @@ cont:
  * Calculate and dget next entry in top down tree traversal.
  */
 static struct dentry *get_next_positive_dentry(struct dentry *prev,
-						struct dentry *root)
+					       struct dentry *root)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(root->d_sb);
 	struct list_head *next;
@@ -187,15 +185,17 @@ again:
  * autofs submounts.
  */
 static int autofs4_direct_busy(struct vfsmount *mnt,
-				struct dentry *top,
-				unsigned long timeout,
-				int do_now)
+			       struct dentry *top,
+			       unsigned long timeout,
+			       int do_now)
 {
-	DPRINTK("top %p %pd", top, top);
+	pr_debug("top %p %pd\n", top, top);
 
 	/* If it's busy update the expiry counters */
 	if (!may_umount_tree(mnt)) {
-		struct autofs_info *ino = autofs4_dentry_ino(top);
+		struct autofs_info *ino;
+
+		ino = autofs4_dentry_ino(top);
 		if (ino)
 			ino->last_used = jiffies;
 		return 1;
@@ -208,7 +208,8 @@ static int autofs4_direct_busy(struct vfsmount *mnt,
 	return 0;
 }
 
-/* Check a directory tree of mount points for busyness
+/*
+ * Check a directory tree of mount points for busyness
  * The tree is not busy iff no mountpoints are busy
  */
 static int autofs4_tree_busy(struct vfsmount *mnt,
@@ -219,7 +220,7 @@ static int autofs4_tree_busy(struct vfsmount *mnt,
 	struct autofs_info *top_ino = autofs4_dentry_ino(top);
 	struct dentry *p;
 
-	DPRINTK("top %p %pd", top, top);
+	pr_debug("top %p %pd\n", top, top);
 
 	/* Negative dentry - give up */
 	if (!simple_positive(top))
@@ -227,7 +228,7 @@ static int autofs4_tree_busy(struct vfsmount *mnt,
 
 	p = NULL;
 	while ((p = get_next_positive_dentry(p, top))) {
-		DPRINTK("dentry %p %pd", p, p);
+		pr_debug("dentry %p %pd\n", p, p);
 
 		/*
 		 * Is someone visiting anywhere in the subtree ?
@@ -273,11 +274,11 @@ static struct dentry *autofs4_check_leaves(struct vfsmount *mnt,
 {
 	struct dentry *p;
 
-	DPRINTK("parent %p %pd", parent, parent);
+	pr_debug("parent %p %pd\n", parent, parent);
 
 	p = NULL;
 	while ((p = get_next_positive_dentry(p, parent))) {
-		DPRINTK("dentry %p %pd", p, p);
+		pr_debug("dentry %p %pd\n", p, p);
 
 		if (d_mountpoint(p)) {
 			/* Can we umount this guy */
@@ -362,7 +363,7 @@ static struct dentry *should_expire(struct dentry *dentry,
 	 *	   offset (autofs-5.0+).
 	 */
 	if (d_mountpoint(dentry)) {
-		DPRINTK("checking mountpoint %p %pd", dentry, dentry);
+		pr_debug("checking mountpoint %p %pd\n", dentry, dentry);
 
 		/* Can we umount this guy */
 		if (autofs4_mount_busy(mnt, dentry))
@@ -375,7 +376,7 @@ static struct dentry *should_expire(struct dentry *dentry,
 	}
 
 	if (d_really_is_positive(dentry) && d_is_symlink(dentry)) {
-		DPRINTK("checking symlink %p %pd", dentry, dentry);
+		pr_debug("checking symlink %p %pd\n", dentry, dentry);
 		/*
 		 * A symlink can't be "busy" in the usual sense so
 		 * just check last used for expire timeout.
@@ -404,6 +405,7 @@ static struct dentry *should_expire(struct dentry *dentry,
 	} else {
 		/* Path walk currently on this dentry? */
 		struct dentry *expired;
+
 		ino_count = atomic_read(&ino->count) + 1;
 		if (d_count(dentry) > ino_count)
 			return NULL;
@@ -471,7 +473,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 	return NULL;
 
 found:
-	DPRINTK("returning %p %pd", expired, expired);
+	pr_debug("returning %p %pd\n", expired, expired);
 	ino->flags |= AUTOFS_INF_EXPIRING;
 	smp_mb();
 	ino->flags &= ~AUTOFS_INF_NO_RCU;
@@ -503,12 +505,12 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk)
 	if (ino->flags & AUTOFS_INF_EXPIRING) {
 		spin_unlock(&sbi->fs_lock);
 
-		DPRINTK("waiting for expire %p name=%pd", dentry, dentry);
+		pr_debug("waiting for expire %p name=%pd\n", dentry, dentry);
 
 		status = autofs4_wait(sbi, dentry, NFY_NONE);
 		wait_for_completion(&ino->expire_complete);
 
-		DPRINTK("expire done status=%d", status);
+		pr_debug("expire done status=%d\n", status);
 
 		if (d_unhashed(dentry))
 			return -EAGAIN;
@@ -522,21 +524,22 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk)
 
 /* Perform an expiry operation */
 int autofs4_expire_run(struct super_block *sb,
-		      struct vfsmount *mnt,
-		      struct autofs_sb_info *sbi,
-		      struct autofs_packet_expire __user *pkt_p)
+		       struct vfsmount *mnt,
+		       struct autofs_sb_info *sbi,
+		       struct autofs_packet_expire __user *pkt_p)
 {
 	struct autofs_packet_expire pkt;
 	struct autofs_info *ino;
 	struct dentry *dentry;
 	int ret = 0;
 
-	memset(&pkt,0,sizeof pkt);
+	memset(&pkt, 0, sizeof(pkt));
 
 	pkt.hdr.proto_version = sbi->version;
 	pkt.hdr.type = autofs_ptype_expire;
 
-	if ((dentry = autofs4_expire_indirect(sb, mnt, sbi, 0)) == NULL)
+	dentry = autofs4_expire_indirect(sb, mnt, sbi, 0);
+	if (!dentry)
 		return -EAGAIN;
 
 	pkt.len = dentry->d_name.len;
@@ -544,7 +547,7 @@ int autofs4_expire_run(struct super_block *sb,
 	pkt.name[pkt.len] = '\0';
 	dput(dentry);
 
-	if ( copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire)) )
+	if (copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire)))
 		ret = -EFAULT;
 
 	spin_lock(&sbi->fs_lock);
@@ -573,7 +576,8 @@ int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt,
 		struct autofs_info *ino = autofs4_dentry_ino(dentry);
 
 		/* This is synchronous because it makes the daemon a
-                   little easier */
+		 * little easier
+		 */
 		ret = autofs4_wait(sbi, dentry, NFY_EXPIRE);
 
 		spin_lock(&sbi->fs_lock);
@@ -588,8 +592,10 @@ int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt,
 	return ret;
 }
 
-/* Call repeatedly until it returns -EAGAIN, meaning there's nothing
-   more to be done */
+/*
+ * Call repeatedly until it returns -EAGAIN, meaning there's nothing
+ * more to be done.
+ */
 int autofs4_expire_multi(struct super_block *sb, struct vfsmount *mnt,
 			struct autofs_sb_info *sbi, int __user *arg)
 {
diff --git a/fs/autofs4/init.c b/fs/autofs4/init.c
index b3db517e89ec..8cf0e63389ae 100644
--- a/fs/autofs4/init.c
+++ b/fs/autofs4/init.c
@@ -1,14 +1,10 @@
-/* -*- c -*- --------------------------------------------------------------- *
- *
- * linux/fs/autofs/init.c
- *
- *  Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
+/*
+ * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
  *
  * This file is part of the Linux kernel and is made available under
  * the terms of the GNU General Public License, version 2, or at your
  * option, any later version, incorporated herein by reference.
- *
- * ------------------------------------------------------------------------- */
+ */
 
 #include <linux/module.h>
 #include <linux/init.h>
diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c
index a3ae0b2aeb5a..61b21051bd5a 100644
--- a/fs/autofs4/inode.c
+++ b/fs/autofs4/inode.c
@@ -1,15 +1,11 @@
-/* -*- c -*- --------------------------------------------------------------- *
- *
- * linux/fs/autofs/inode.c
- *
- *  Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
- *  Copyright 2005-2006 Ian Kent <raven@themaw.net>
+/*
+ * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
+ * Copyright 2005-2006 Ian Kent <raven@themaw.net>
  *
  * This file is part of the Linux kernel and is made available under
  * the terms of the GNU General Public License, version 2, or at your
  * option, any later version, incorporated herein by reference.
- *
- * ------------------------------------------------------------------------- */
+ */
 
 #include <linux/kernel.h>
 #include <linux/slab.h>
@@ -24,7 +20,9 @@
 
 struct autofs_info *autofs4_new_ino(struct autofs_sb_info *sbi)
 {
-	struct autofs_info *ino = kzalloc(sizeof(*ino), GFP_KERNEL);
+	struct autofs_info *ino;
+
+	ino = kzalloc(sizeof(*ino), GFP_KERNEL);
 	if (ino) {
 		INIT_LIST_HEAD(&ino->active);
 		INIT_LIST_HEAD(&ino->expiring);
@@ -62,7 +60,7 @@ void autofs4_kill_sb(struct super_block *sb)
 		put_pid(sbi->oz_pgrp);
 	}
 
-	DPRINTK("shutting down");
+	pr_debug("shutting down\n");
 	kill_litter_super(sb);
 	if (sbi)
 		kfree_rcu(sbi, rcu);
@@ -94,7 +92,12 @@ static int autofs4_show_options(struct seq_file *m, struct dentry *root)
 		seq_printf(m, ",direct");
 	else
 		seq_printf(m, ",indirect");
-
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	if (sbi->pipe)
+		seq_printf(m, ",pipe_ino=%ld", sbi->pipe->f_inode->i_ino);
+	else
+		seq_printf(m, ",pipe_ino=-1");
+#endif
 	return 0;
 }
 
@@ -147,6 +150,7 @@ static int parse_options(char *options, int *pipefd, kuid_t *uid, kgid_t *gid,
 
 	while ((p = strsep(&options, ",")) != NULL) {
 		int token;
+
 		if (!*p)
 			continue;
 
@@ -204,9 +208,9 @@ static int parse_options(char *options, int *pipefd, kuid_t *uid, kgid_t *gid,
 
 int autofs4_fill_super(struct super_block *s, void *data, int silent)
 {
-	struct inode * root_inode;
-	struct dentry * root;
-	struct file * pipe;
+	struct inode *root_inode;
+	struct dentry *root;
+	struct file *pipe;
 	int pipefd;
 	struct autofs_sb_info *sbi;
 	struct autofs_info *ino;
@@ -217,7 +221,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
 	if (!sbi)
 		return -ENOMEM;
-	DPRINTK("starting up, sbi = %p",sbi);
+	pr_debug("starting up, sbi = %p\n", sbi);
 
 	s->s_fs_info = sbi;
 	sbi->magic = AUTOFS_SBI_MAGIC;
@@ -266,14 +270,14 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 	if (parse_options(data, &pipefd, &root_inode->i_uid, &root_inode->i_gid,
 			  &pgrp, &pgrp_set, &sbi->type, &sbi->min_proto,
 			  &sbi->max_proto)) {
-		printk("autofs: called with bogus options\n");
+		pr_err("called with bogus options\n");
 		goto fail_dput;
 	}
 
 	if (pgrp_set) {
 		sbi->oz_pgrp = find_get_pid(pgrp);
 		if (!sbi->oz_pgrp) {
-			pr_warn("autofs: could not find process group %d\n",
+			pr_err("could not find process group %d\n",
 				pgrp);
 			goto fail_dput;
 		}
@@ -290,10 +294,10 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 	/* Couldn't this be tested earlier? */
 	if (sbi->max_proto < AUTOFS_MIN_PROTO_VERSION ||
 	    sbi->min_proto > AUTOFS_MAX_PROTO_VERSION) {
-		printk("autofs: kernel does not match daemon version "
+		pr_err("kernel does not match daemon version "
 		       "daemon (%d, %d) kernel (%d, %d)\n",
-			sbi->min_proto, sbi->max_proto,
-			AUTOFS_MIN_PROTO_VERSION, AUTOFS_MAX_PROTO_VERSION);
+		       sbi->min_proto, sbi->max_proto,
+		       AUTOFS_MIN_PROTO_VERSION, AUTOFS_MAX_PROTO_VERSION);
 		goto fail_dput;
 	}
 
@@ -304,11 +308,11 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 		sbi->version = sbi->max_proto;
 	sbi->sub_version = AUTOFS_PROTO_SUBVERSION;
 
-	DPRINTK("pipe fd = %d, pgrp = %u", pipefd, pid_nr(sbi->oz_pgrp));
+	pr_debug("pipe fd = %d, pgrp = %u\n", pipefd, pid_nr(sbi->oz_pgrp));
 	pipe = fget(pipefd);
 
 	if (!pipe) {
-		printk("autofs: could not open pipe file descriptor\n");
+		pr_err("could not open pipe file descriptor\n");
 		goto fail_dput;
 	}
 	ret = autofs_prepare_pipe(pipe);
@@ -323,12 +327,12 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 	 */
 	s->s_root = root;
 	return 0;
-	
+
 	/*
 	 * Failure ... clean up.
 	 */
 fail_fput:
-	printk("autofs: pipe file descriptor does not contain proper ops\n");
+	pr_err("pipe file descriptor does not contain proper ops\n");
 	fput(pipe);
 	/* fall through */
 fail_dput:
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index c6d7d3dbd52a..7ab923940d18 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -1,16 +1,12 @@
-/* -*- c -*- --------------------------------------------------------------- *
- *
- * linux/fs/autofs/root.c
- *
- *  Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
- *  Copyright 1999-2000 Jeremy Fitzhardinge <jeremy@goop.org>
- *  Copyright 2001-2006 Ian Kent <raven@themaw.net>
+/*
+ * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
+ * Copyright 1999-2000 Jeremy Fitzhardinge <jeremy@goop.org>
+ * Copyright 2001-2006 Ian Kent <raven@themaw.net>
  *
  * This file is part of the Linux kernel and is made available under
  * the terms of the GNU General Public License, version 2, or at your
  * option, any later version, incorporated herein by reference.
- *
- * ------------------------------------------------------------------------- */
+ */
 
 #include <linux/capability.h>
 #include <linux/errno.h>
@@ -23,16 +19,18 @@
 
 #include "autofs_i.h"
 
-static int autofs4_dir_symlink(struct inode *,struct dentry *,const char *);
-static int autofs4_dir_unlink(struct inode *,struct dentry *);
-static int autofs4_dir_rmdir(struct inode *,struct dentry *);
-static int autofs4_dir_mkdir(struct inode *,struct dentry *,umode_t);
-static long autofs4_root_ioctl(struct file *,unsigned int,unsigned long);
+static int autofs4_dir_symlink(struct inode *, struct dentry *, const char *);
+static int autofs4_dir_unlink(struct inode *, struct dentry *);
+static int autofs4_dir_rmdir(struct inode *, struct dentry *);
+static int autofs4_dir_mkdir(struct inode *, struct dentry *, umode_t);
+static long autofs4_root_ioctl(struct file *, unsigned int, unsigned long);
 #ifdef CONFIG_COMPAT
-static long autofs4_root_compat_ioctl(struct file *,unsigned int,unsigned long);
+static long autofs4_root_compat_ioctl(struct file *,
+				      unsigned int, unsigned long);
 #endif
 static int autofs4_dir_open(struct inode *inode, struct file *file);
-static struct dentry *autofs4_lookup(struct inode *,struct dentry *, unsigned int);
+static struct dentry *autofs4_lookup(struct inode *,
+				     struct dentry *, unsigned int);
 static struct vfsmount *autofs4_d_automount(struct path *);
 static int autofs4_d_manage(struct dentry *, bool);
 static void autofs4_dentry_release(struct dentry *);
@@ -74,7 +72,9 @@ const struct dentry_operations autofs4_dentry_operations = {
 static void autofs4_add_active(struct dentry *dentry)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
-	struct autofs_info *ino = autofs4_dentry_ino(dentry);
+	struct autofs_info *ino;
+
+	ino = autofs4_dentry_ino(dentry);
 	if (ino) {
 		spin_lock(&sbi->lookup_lock);
 		if (!ino->active_count) {
@@ -84,13 +84,14 @@ static void autofs4_add_active(struct dentry *dentry)
 		ino->active_count++;
 		spin_unlock(&sbi->lookup_lock);
 	}
-	return;
 }
 
 static void autofs4_del_active(struct dentry *dentry)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
-	struct autofs_info *ino = autofs4_dentry_ino(dentry);
+	struct autofs_info *ino;
+
+	ino = autofs4_dentry_ino(dentry);
 	if (ino) {
 		spin_lock(&sbi->lookup_lock);
 		ino->active_count--;
@@ -100,7 +101,6 @@ static void autofs4_del_active(struct dentry *dentry)
 		}
 		spin_unlock(&sbi->lookup_lock);
 	}
-	return;
 }
 
 static int autofs4_dir_open(struct inode *inode, struct file *file)
@@ -108,7 +108,7 @@ static int autofs4_dir_open(struct inode *inode, struct file *file)
 	struct dentry *dentry = file->f_path.dentry;
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
 
-	DPRINTK("file=%p dentry=%p %pd", file, dentry, dentry);
+	pr_debug("file=%p dentry=%p %pd\n", file, dentry, dentry);
 
 	if (autofs4_oz_mode(sbi))
 		goto out;
@@ -138,7 +138,7 @@ static void autofs4_dentry_release(struct dentry *de)
 	struct autofs_info *ino = autofs4_dentry_ino(de);
 	struct autofs_sb_info *sbi = autofs4_sbi(de->d_sb);
 
-	DPRINTK("releasing %p", de);
+	pr_debug("releasing %p\n", de);
 
 	if (!ino)
 		return;
@@ -278,9 +278,9 @@ static int autofs4_mount_wait(struct dentry *dentry, bool rcu_walk)
 	if (ino->flags & AUTOFS_INF_PENDING) {
 		if (rcu_walk)
 			return -ECHILD;
-		DPRINTK("waiting for mount name=%pd", dentry);
+		pr_debug("waiting for mount name=%pd\n", dentry);
 		status = autofs4_wait(sbi, dentry, NFY_MOUNT);
-		DPRINTK("mount wait done status=%d", status);
+		pr_debug("mount wait done status=%d\n", status);
 	}
 	ino->last_used = jiffies;
 	return status;
@@ -320,7 +320,9 @@ static struct dentry *autofs4_mountpoint_changed(struct path *path)
 	if (autofs_type_indirect(sbi->type) && d_unhashed(dentry)) {
 		struct dentry *parent = dentry->d_parent;
 		struct autofs_info *ino;
-		struct dentry *new = d_lookup(parent, &dentry->d_name);
+		struct dentry *new;
+
+		new = d_lookup(parent, &dentry->d_name);
 		if (!new)
 			return NULL;
 		ino = autofs4_dentry_ino(new);
@@ -338,7 +340,7 @@ static struct vfsmount *autofs4_d_automount(struct path *path)
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
 	int status;
 
-	DPRINTK("dentry=%p %pd", dentry, dentry);
+	pr_debug("dentry=%p %pd\n", dentry, dentry);
 
 	/* The daemon never triggers a mount. */
 	if (autofs4_oz_mode(sbi))
@@ -425,7 +427,7 @@ static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk)
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
 	int status;
 
-	DPRINTK("dentry=%p %pd", dentry, dentry);
+	pr_debug("dentry=%p %pd\n", dentry, dentry);
 
 	/* The daemon never waits. */
 	if (autofs4_oz_mode(sbi)) {
@@ -455,6 +457,7 @@ static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk)
 		 * a mount-trap.
 		 */
 		struct inode *inode;
+
 		if (ino->flags & (AUTOFS_INF_EXPIRING | AUTOFS_INF_NO_RCU))
 			return 0;
 		if (d_mountpoint(dentry))
@@ -494,13 +497,14 @@ static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk)
 }
 
 /* Lookups in the root directory */
-static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
+static struct dentry *autofs4_lookup(struct inode *dir,
+				     struct dentry *dentry, unsigned int flags)
 {
 	struct autofs_sb_info *sbi;
 	struct autofs_info *ino;
 	struct dentry *active;
 
-	DPRINTK("name = %pd", dentry);
+	pr_debug("name = %pd\n", dentry);
 
 	/* File name too long to exist */
 	if (dentry->d_name.len > NAME_MAX)
@@ -508,14 +512,14 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, u
 
 	sbi = autofs4_sbi(dir->i_sb);
 
-	DPRINTK("pid = %u, pgrp = %u, catatonic = %d, oz_mode = %d",
-		current->pid, task_pgrp_nr(current), sbi->catatonic,
-		autofs4_oz_mode(sbi));
+	pr_debug("pid = %u, pgrp = %u, catatonic = %d, oz_mode = %d\n",
+		 current->pid, task_pgrp_nr(current), sbi->catatonic,
+		 autofs4_oz_mode(sbi));
 
 	active = autofs4_lookup_active(dentry);
-	if (active) {
+	if (active)
 		return active;
-	} else {
+	else {
 		/*
 		 * A dentry that is not within the root can never trigger a
 		 * mount operation, unless the directory already exists, so we
@@ -526,7 +530,8 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, u
 			return ERR_PTR(-ENOENT);
 
 		/* Mark entries in the root as mount triggers */
-		if (autofs_type_indirect(sbi->type) && IS_ROOT(dentry->d_parent))
+		if (IS_ROOT(dentry->d_parent) &&
+		    autofs_type_indirect(sbi->type))
 			__managed_dentry_set_managed(dentry);
 
 		ino = autofs4_new_ino(sbi);
@@ -537,8 +542,6 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, u
 		ino->dentry = dentry;
 
 		autofs4_add_active(dentry);
-
-		d_instantiate(dentry, NULL);
 	}
 	return NULL;
 }
@@ -554,7 +557,7 @@ static int autofs4_dir_symlink(struct inode *dir,
 	size_t size = strlen(symname);
 	char *cp;
 
-	DPRINTK("%s <- %pd", symname, dentry);
+	pr_debug("%s <- %pd\n", symname, dentry);
 
 	if (!autofs4_oz_mode(sbi))
 		return -EACCES;
@@ -613,7 +616,7 @@ static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry)
 	struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
 	struct autofs_info *p_ino;
-	
+
 	/* This allows root to remove symlinks */
 	if (!autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -664,7 +667,6 @@ static void autofs_set_leaf_automount_flags(struct dentry *dentry)
 	if (IS_ROOT(parent->d_parent))
 		return;
 	managed_dentry_clear_managed(parent);
-	return;
 }
 
 static void autofs_clear_leaf_automount_flags(struct dentry *dentry)
@@ -687,7 +689,6 @@ static void autofs_clear_leaf_automount_flags(struct dentry *dentry)
 	if (d_child->next == &parent->d_subdirs &&
 	    d_child->prev == &parent->d_subdirs)
 		managed_dentry_set_managed(parent);
-	return;
 }
 
 static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry)
@@ -695,8 +696,8 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry)
 	struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
 	struct autofs_info *p_ino;
-	
-	DPRINTK("dentry %p, removing %pd", dentry, dentry);
+
+	pr_debug("dentry %p, removing %pd\n", dentry, dentry);
 
 	if (!autofs4_oz_mode(sbi))
 		return -EACCES;
@@ -728,7 +729,8 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry)
 	return 0;
 }
 
-static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int autofs4_dir_mkdir(struct inode *dir,
+			     struct dentry *dentry, umode_t mode)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
@@ -738,7 +740,7 @@ static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, umode_t m
 	if (!autofs4_oz_mode(sbi))
 		return -EACCES;
 
-	DPRINTK("dentry %p, creating %pd", dentry, dentry);
+	pr_debug("dentry %p, creating %pd\n", dentry, dentry);
 
 	BUG_ON(!ino);
 
@@ -768,14 +770,18 @@ static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, umode_t m
 /* Get/set timeout ioctl() operation */
 #ifdef CONFIG_COMPAT
 static inline int autofs4_compat_get_set_timeout(struct autofs_sb_info *sbi,
-					 compat_ulong_t __user *p)
+						 compat_ulong_t __user *p)
 {
-	int rv;
 	unsigned long ntimeout;
+	int rv;
+
+	rv = get_user(ntimeout, p);
+	if (rv)
+		goto error;
 
-	if ((rv = get_user(ntimeout, p)) ||
-	     (rv = put_user(sbi->exp_timeout/HZ, p)))
-		return rv;
+	rv = put_user(sbi->exp_timeout/HZ, p);
+	if (rv)
+		goto error;
 
 	if (ntimeout > UINT_MAX/HZ)
 		sbi->exp_timeout = 0;
@@ -783,18 +789,24 @@ static inline int autofs4_compat_get_set_timeout(struct autofs_sb_info *sbi,
 		sbi->exp_timeout = ntimeout * HZ;
 
 	return 0;
+error:
+	return rv;
 }
 #endif
 
 static inline int autofs4_get_set_timeout(struct autofs_sb_info *sbi,
-					 unsigned long __user *p)
+					  unsigned long __user *p)
 {
-	int rv;
 	unsigned long ntimeout;
+	int rv;
+
+	rv = get_user(ntimeout, p);
+	if (rv)
+		goto error;
 
-	if ((rv = get_user(ntimeout, p)) ||
-	     (rv = put_user(sbi->exp_timeout/HZ, p)))
-		return rv;
+	rv = put_user(sbi->exp_timeout/HZ, p);
+	if (rv)
+		goto error;
 
 	if (ntimeout > ULONG_MAX/HZ)
 		sbi->exp_timeout = 0;
@@ -802,16 +814,20 @@ static inline int autofs4_get_set_timeout(struct autofs_sb_info *sbi,
 		sbi->exp_timeout = ntimeout * HZ;
 
 	return 0;
+error:
+	return rv;
 }
 
 /* Return protocol version */
-static inline int autofs4_get_protover(struct autofs_sb_info *sbi, int __user *p)
+static inline int autofs4_get_protover(struct autofs_sb_info *sbi,
+				       int __user *p)
 {
 	return put_user(sbi->version, p);
 }
 
 /* Return protocol sub version */
-static inline int autofs4_get_protosubver(struct autofs_sb_info *sbi, int __user *p)
+static inline int autofs4_get_protosubver(struct autofs_sb_info *sbi,
+					  int __user *p)
 {
 	return put_user(sbi->sub_version, p);
 }
@@ -826,7 +842,7 @@ static inline int autofs4_ask_umount(struct vfsmount *mnt, int __user *p)
 	if (may_umount(mnt))
 		status = 1;
 
-	DPRINTK("returning %d", status);
+	pr_debug("returning %d\n", status);
 
 	status = put_user(status, p);
 
@@ -834,9 +850,9 @@ static inline int autofs4_ask_umount(struct vfsmount *mnt, int __user *p)
 }
 
 /* Identify autofs4_dentries - this is so we can tell if there's
-   an extra dentry refcount or not.  We only hold a refcount on the
-   dentry if its non-negative (ie, d_inode != NULL)
-*/
+ * an extra dentry refcount or not.  We only hold a refcount on the
+ * dentry if its non-negative (ie, d_inode != NULL)
+ */
 int is_autofs4_dentry(struct dentry *dentry)
 {
 	return dentry && d_really_is_positive(dentry) &&
@@ -854,21 +870,21 @@ static int autofs4_root_ioctl_unlocked(struct inode *inode, struct file *filp,
 	struct autofs_sb_info *sbi = autofs4_sbi(inode->i_sb);
 	void __user *p = (void __user *)arg;
 
-	DPRINTK("cmd = 0x%08x, arg = 0x%08lx, sbi = %p, pgrp = %u",
-		cmd,arg,sbi,task_pgrp_nr(current));
+	pr_debug("cmd = 0x%08x, arg = 0x%08lx, sbi = %p, pgrp = %u\n",
+		 cmd, arg, sbi, task_pgrp_nr(current));
 
 	if (_IOC_TYPE(cmd) != _IOC_TYPE(AUTOFS_IOC_FIRST) ||
 	     _IOC_NR(cmd) - _IOC_NR(AUTOFS_IOC_FIRST) >= AUTOFS_IOC_COUNT)
 		return -ENOTTY;
-	
+
 	if (!autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN))
 		return -EPERM;
-	
-	switch(cmd) {
+
+	switch (cmd) {
 	case AUTOFS_IOC_READY:	/* Wait queue: go ahead and retry */
-		return autofs4_wait_release(sbi,(autofs_wqt_t)arg,0);
+		return autofs4_wait_release(sbi, (autofs_wqt_t) arg, 0);
 	case AUTOFS_IOC_FAIL:	/* Wait queue: fail with ENOENT */
-		return autofs4_wait_release(sbi,(autofs_wqt_t)arg,-ENOENT);
+		return autofs4_wait_release(sbi, (autofs_wqt_t) arg, -ENOENT);
 	case AUTOFS_IOC_CATATONIC: /* Enter catatonic mode (daemon shutdown) */
 		autofs4_catatonic_mode(sbi);
 		return 0;
@@ -888,13 +904,15 @@ static int autofs4_root_ioctl_unlocked(struct inode *inode, struct file *filp,
 
 	/* return a single thing to expire */
 	case AUTOFS_IOC_EXPIRE:
-		return autofs4_expire_run(inode->i_sb,filp->f_path.mnt,sbi, p);
+		return autofs4_expire_run(inode->i_sb,
+					  filp->f_path.mnt, sbi, p);
 	/* same as above, but can send multiple expires through pipe */
 	case AUTOFS_IOC_EXPIRE_MULTI:
-		return autofs4_expire_multi(inode->i_sb,filp->f_path.mnt,sbi, p);
+		return autofs4_expire_multi(inode->i_sb,
+					    filp->f_path.mnt, sbi, p);
 
 	default:
-		return -ENOSYS;
+		return -EINVAL;
 	}
 }
 
@@ -902,12 +920,13 @@ static long autofs4_root_ioctl(struct file *filp,
 			       unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
+
 	return autofs4_root_ioctl_unlocked(inode, filp, cmd, arg);
 }
 
 #ifdef CONFIG_COMPAT
 static long autofs4_root_compat_ioctl(struct file *filp,
-			     unsigned int cmd, unsigned long arg)
+				      unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
 	int ret;
@@ -916,7 +935,7 @@ static long autofs4_root_compat_ioctl(struct file *filp,
 		ret = autofs4_root_ioctl_unlocked(inode, filp, cmd, arg);
 	else
 		ret = autofs4_root_ioctl_unlocked(inode, filp, cmd,
-			(unsigned long)compat_ptr(arg));
+					      (unsigned long) compat_ptr(arg));
 
 	return ret;
 }
diff --git a/fs/autofs4/symlink.c b/fs/autofs4/symlink.c
index da0c33481bc0..99aab00dc217 100644
--- a/fs/autofs4/symlink.c
+++ b/fs/autofs4/symlink.c
@@ -1,21 +1,24 @@
-/* -*- c -*- --------------------------------------------------------------- *
- *
- * linux/fs/autofs/symlink.c
- *
- *  Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
+/*
+ * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
  *
  * This file is part of the Linux kernel and is made available under
  * the terms of the GNU General Public License, version 2, or at your
  * option, any later version, incorporated herein by reference.
- *
- * ------------------------------------------------------------------------- */
+ */
 
 #include "autofs_i.h"
 
-static const char *autofs4_follow_link(struct dentry *dentry, void **cookie)
+static const char *autofs4_get_link(struct dentry *dentry,
+				    struct inode *inode,
+				    struct delayed_call *done)
 {
-	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
-	struct autofs_info *ino = autofs4_dentry_ino(dentry);
+	struct autofs_sb_info *sbi;
+	struct autofs_info *ino;
+
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+	sbi = autofs4_sbi(dentry->d_sb);
+	ino = autofs4_dentry_ino(dentry);
 	if (ino && !autofs4_oz_mode(sbi))
 		ino->last_used = jiffies;
 	return d_inode(dentry)->i_private;
@@ -23,5 +26,5 @@ static const char *autofs4_follow_link(struct dentry *dentry, void **cookie)
 
 const struct inode_operations autofs4_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= autofs4_follow_link
+	.get_link	= autofs4_get_link
 };
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 35b755e79c2d..0146d911f468 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -1,15 +1,11 @@
-/* -*- c -*- --------------------------------------------------------------- *
- *
- * linux/fs/autofs/waitq.c
- *
- *  Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
- *  Copyright 2001-2006 Ian Kent <raven@themaw.net>
+/*
+ * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
+ * Copyright 2001-2006 Ian Kent <raven@themaw.net>
  *
  * This file is part of the Linux kernel and is made available under
  * the terms of the GNU General Public License, version 2, or at your
  * option, any later version, incorporated herein by reference.
- *
- * ------------------------------------------------------------------------- */
+ */
 
 #include <linux/slab.h>
 #include <linux/time.h>
@@ -18,7 +14,8 @@
 #include "autofs_i.h"
 
 /* We make this a static variable rather than a part of the superblock; it
-   is better if we don't reassign numbers easily even across filesystems */
+ * is better if we don't reassign numbers easily even across filesystems
+ */
 static autofs_wqt_t autofs4_next_wait_queue = 1;
 
 /* These are the signals we allow interrupting a pending mount */
@@ -34,7 +31,7 @@ void autofs4_catatonic_mode(struct autofs_sb_info *sbi)
 		return;
 	}
 
-	DPRINTK("entering catatonic mode");
+	pr_debug("entering catatonic mode\n");
 
 	sbi->catatonic = 1;
 	wq = sbi->queues;
@@ -69,17 +66,19 @@ static int autofs4_write(struct autofs_sb_info *sbi,
 	set_fs(KERNEL_DS);
 
 	mutex_lock(&sbi->pipe_mutex);
-	while (bytes &&
-	       (wr = __vfs_write(file,data,bytes,&file->f_pos)) > 0) {
+	wr = __vfs_write(file, data, bytes, &file->f_pos);
+	while (bytes && wr) {
 		data += wr;
 		bytes -= wr;
+		wr = __vfs_write(file, data, bytes, &file->f_pos);
 	}
 	mutex_unlock(&sbi->pipe_mutex);
 
 	set_fs(fs);
 
 	/* Keep the currently executing process from receiving a
-	   SIGPIPE unless it was already supposed to get one */
+	 * SIGPIPE unless it was already supposed to get one
+	 */
 	if (wr == -EPIPE && !sigpipe) {
 		spin_lock_irqsave(&current->sighand->siglock, flags);
 		sigdelset(&current->pending.signal, SIGPIPE);
@@ -89,7 +88,7 @@ static int autofs4_write(struct autofs_sb_info *sbi,
 
 	return (bytes > 0);
 }
-	
+
 static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
 				 struct autofs_wait_queue *wq,
 				 int type)
@@ -102,10 +101,11 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
 	struct file *pipe = NULL;
 	size_t pktsz;
 
-	DPRINTK("wait id = 0x%08lx, name = %.*s, type=%d",
-		(unsigned long) wq->wait_queue_token, wq->name.len, wq->name.name, type);
+	pr_debug("wait id = 0x%08lx, name = %.*s, type=%d\n",
+		 (unsigned long) wq->wait_queue_token,
+		 wq->name.len, wq->name.name, type);
 
-	memset(&pkt,0,sizeof pkt); /* For security reasons */
+	memset(&pkt, 0, sizeof(pkt)); /* For security reasons */
 
 	pkt.hdr.proto_version = sbi->version;
 	pkt.hdr.type = type;
@@ -126,7 +126,8 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
 	}
 	case autofs_ptype_expire_multi:
 	{
-		struct autofs_packet_expire_multi *ep = &pkt.v4_pkt.expire_multi;
+		struct autofs_packet_expire_multi *ep =
+					&pkt.v4_pkt.expire_multi;
 
 		pktsz = sizeof(*ep);
 
@@ -163,7 +164,7 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
 		break;
 	}
 	default:
-		printk("autofs4_notify_daemon: bad type %d!\n", type);
+		pr_warn("bad type %d!\n", type);
 		mutex_unlock(&sbi->wq_mutex);
 		return;
 	}
@@ -231,7 +232,7 @@ autofs4_find_wait(struct autofs_sb_info *sbi, struct qstr *qstr)
 		if (wq->name.hash == qstr->hash &&
 		    wq->name.len == qstr->len &&
 		    wq->name.name &&
-			 !memcmp(wq->name.name, qstr->name, qstr->len))
+		    !memcmp(wq->name.name, qstr->name, qstr->len))
 			break;
 	}
 	return wq;
@@ -248,7 +249,7 @@ autofs4_find_wait(struct autofs_sb_info *sbi, struct qstr *qstr)
 static int validate_request(struct autofs_wait_queue **wait,
 			    struct autofs_sb_info *sbi,
 			    struct qstr *qstr,
-			    struct dentry*dentry, enum autofs_notify notify)
+			    struct dentry *dentry, enum autofs_notify notify)
 {
 	struct autofs_wait_queue *wq;
 	struct autofs_info *ino;
@@ -322,8 +323,10 @@ static int validate_request(struct autofs_wait_queue **wait,
 		 * continue on and create a new request.
 		 */
 		if (!IS_ROOT(dentry)) {
-			if (d_really_is_positive(dentry) && d_unhashed(dentry)) {
+			if (d_unhashed(dentry) &&
+			    d_really_is_positive(dentry)) {
 				struct dentry *parent = dentry->d_parent;
+
 				new = d_lookup(parent, &dentry->d_name);
 				if (new)
 					dentry = new;
@@ -340,8 +343,8 @@ static int validate_request(struct autofs_wait_queue **wait,
 	return 1;
 }
 
-int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
-		enum autofs_notify notify)
+int autofs4_wait(struct autofs_sb_info *sbi,
+		 struct dentry *dentry, enum autofs_notify notify)
 {
 	struct autofs_wait_queue *wq;
 	struct qstr qstr;
@@ -411,7 +414,7 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
 
 	if (!wq) {
 		/* Create a new wait queue */
-		wq = kmalloc(sizeof(struct autofs_wait_queue),GFP_KERNEL);
+		wq = kmalloc(sizeof(struct autofs_wait_queue), GFP_KERNEL);
 		if (!wq) {
 			kfree(qstr.name);
 			mutex_unlock(&sbi->wq_mutex);
@@ -450,17 +453,19 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
 					autofs_ptype_expire_indirect;
 		}
 
-		DPRINTK("new wait id = 0x%08lx, name = %.*s, nfy=%d\n",
-			(unsigned long) wq->wait_queue_token, wq->name.len,
-			wq->name.name, notify);
+		pr_debug("new wait id = 0x%08lx, name = %.*s, nfy=%d\n",
+			 (unsigned long) wq->wait_queue_token, wq->name.len,
+			 wq->name.name, notify);
 
-		/* autofs4_notify_daemon() may block; it will unlock ->wq_mutex */
+		/*
+		 * autofs4_notify_daemon() may block; it will unlock ->wq_mutex
+		 */
 		autofs4_notify_daemon(sbi, wq, type);
 	} else {
 		wq->wait_ctr++;
-		DPRINTK("existing wait id = 0x%08lx, name = %.*s, nfy=%d",
-			(unsigned long) wq->wait_queue_token, wq->name.len,
-			wq->name.name, notify);
+		pr_debug("existing wait id = 0x%08lx, name = %.*s, nfy=%d\n",
+			 (unsigned long) wq->wait_queue_token, wq->name.len,
+			 wq->name.name, notify);
 		mutex_unlock(&sbi->wq_mutex);
 		kfree(qstr.name);
 	}
@@ -471,12 +476,14 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
 	 */
 	if (wq->name.name) {
 		/* Block all but "shutdown" signals while waiting */
-		sigset_t oldset;
+		unsigned long shutdown_sigs_mask;
 		unsigned long irqflags;
+		sigset_t oldset;
 
 		spin_lock_irqsave(&current->sighand->siglock, irqflags);
 		oldset = current->blocked;
-		siginitsetinv(&current->blocked, SHUTDOWN_SIGS & ~oldset.sig[0]);
+		shutdown_sigs_mask = SHUTDOWN_SIGS & ~oldset.sig[0];
+		siginitsetinv(&current->blocked, shutdown_sigs_mask);
 		recalc_sigpending();
 		spin_unlock_irqrestore(&current->sighand->siglock, irqflags);
 
@@ -487,7 +494,7 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
 		recalc_sigpending();
 		spin_unlock_irqrestore(&current->sighand->siglock, irqflags);
 	} else {
-		DPRINTK("skipped sleeping");
+		pr_debug("skipped sleeping\n");
 	}
 
 	status = wq->status;
@@ -562,4 +569,3 @@ int autofs4_wait_release(struct autofs_sb_info *sbi, autofs_wqt_t wait_queue_tok
 
 	return 0;
 }
-
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index 861b1e1c4777..103f5d7c3083 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -192,7 +192,7 @@ EXPORT_SYMBOL(make_bad_inode);
  *	Returns true if the inode in question has been marked as bad.
  */
  
-int is_bad_inode(struct inode *inode)
+bool is_bad_inode(struct inode *inode)
 {
 	return (inode->i_op == &bad_inode_ops);	
 }
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 46aedacfa6a8..cc0e08252913 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -42,7 +42,7 @@ static struct inode *befs_iget(struct super_block *, unsigned long);
 static struct inode *befs_alloc_inode(struct super_block *sb);
 static void befs_destroy_inode(struct inode *inode);
 static void befs_destroy_inodecache(void);
-static const char *befs_follow_link(struct dentry *, void **);
+static int befs_symlink_readpage(struct file *, struct page *);
 static int befs_utf2nls(struct super_block *sb, const char *in, int in_len,
 			char **out, int *out_len);
 static int befs_nls2utf(struct super_block *sb, const char *in, int in_len,
@@ -79,10 +79,8 @@ static const struct address_space_operations befs_aops = {
 	.bmap		= befs_bmap,
 };
 
-static const struct inode_operations befs_symlink_inode_operations = {
-	.readlink	= generic_readlink,
-	.follow_link	= befs_follow_link,
-	.put_link	= kfree_put_link,
+static const struct address_space_operations befs_symlink_aops = {
+	.readpage	= befs_symlink_readpage,
 };
 
 /* 
@@ -398,7 +396,9 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino)
 		inode->i_fop = &befs_dir_operations;
 	} else if (S_ISLNK(inode->i_mode)) {
 		if (befs_ino->i_flags & BEFS_LONG_SYMLINK) {
-			inode->i_op = &befs_symlink_inode_operations;
+			inode->i_op = &page_symlink_inode_operations;
+			inode_nohighmem(inode);
+			inode->i_mapping->a_ops = &befs_symlink_aops;
 		} else {
 			inode->i_link = befs_ino->i_data.symlink;
 			inode->i_op = &simple_symlink_inode_operations;
@@ -434,7 +434,7 @@ befs_init_inodecache(void)
 	befs_inode_cachep = kmem_cache_create("befs_inode_cache",
 					      sizeof (struct befs_inode_info),
 					      0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD),
+						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
 					      init_once);
 	if (befs_inode_cachep == NULL) {
 		pr_err("%s: Couldn't initialize inode slabcache\n", __func__);
@@ -463,31 +463,33 @@ befs_destroy_inodecache(void)
  * The data stream become link name. Unless the LONG_SYMLINK
  * flag is set.
  */
-static const char *
-befs_follow_link(struct dentry *dentry, void **cookie)
+static int befs_symlink_readpage(struct file *unused, struct page *page)
 {
-	struct super_block *sb = dentry->d_sb;
-	struct befs_inode_info *befs_ino = BEFS_I(d_inode(dentry));
+	struct inode *inode = page->mapping->host;
+	struct super_block *sb = inode->i_sb;
+	struct befs_inode_info *befs_ino = BEFS_I(inode);
 	befs_data_stream *data = &befs_ino->i_data.ds;
 	befs_off_t len = data->size;
-	char *link;
+	char *link = page_address(page);
 
-	if (len == 0) {
+	if (len == 0 || len > PAGE_SIZE) {
 		befs_error(sb, "Long symlink with illegal length");
-		return ERR_PTR(-EIO);
+		goto fail;
 	}
 	befs_debug(sb, "Follow long symlink");
 
-	link = kmalloc(len, GFP_NOFS);
-	if (!link)
-		return ERR_PTR(-ENOMEM);
 	if (befs_read_lsymlink(sb, data, link, len) != len) {
-		kfree(link);
 		befs_error(sb, "Failed to read entire long symlink");
-		return ERR_PTR(-EIO);
+		goto fail;
 	}
 	link[len - 1] = '\0';
-	return *cookie = link;
+	SetPageUptodate(page);
+	unlock_page(page);
+	return 0;
+fail:
+	SetPageError(page);
+	unlock_page(page);
+	return -EIO;
 }
 
 /*
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index fdcb4d69f430..1e5c896f6b79 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -270,7 +270,7 @@ static int __init init_inodecache(void)
 	bfs_inode_cachep = kmem_cache_create("bfs_inode_cache",
 					     sizeof(struct bfs_inode_info),
 					     0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD),
+						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
 					     init_once);
 	if (bfs_inode_cachep == NULL)
 		return -ENOMEM;
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 6b659967898e..81381cc0dd17 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -35,6 +35,7 @@
 #include <linux/utsname.h>
 #include <linux/coredump.h>
 #include <linux/sched.h>
+#include <linux/dax.h>
 #include <asm/uaccess.h>
 #include <asm/param.h>
 #include <asm/page.h>
@@ -487,9 +488,10 @@ static inline int arch_elf_pt_proc(struct elfhdr *ehdr,
 }
 
 /**
- * arch_check_elf() - check a PT_LOPROC..PT_HIPROC ELF program header
+ * arch_check_elf() - check an ELF executable
  * @ehdr:	The main ELF header
  * @has_interp:	True if the ELF has an interpreter, else false.
+ * @interp_ehdr: The interpreter's ELF header
  * @state:	Architecture-specific state preserved throughout the process
  *		of loading the ELF.
  *
@@ -501,6 +503,7 @@ static inline int arch_elf_pt_proc(struct elfhdr *ehdr,
  *         with that return code.
  */
 static inline int arch_check_elf(struct elfhdr *ehdr, bool has_interp,
+				 struct elfhdr *interp_ehdr,
 				 struct arch_elf_state *state)
 {
 	/* Dummy implementation, always proceed */
@@ -650,7 +653,7 @@ static unsigned long randomize_stack_top(unsigned long stack_top)
 
 	if ((current->flags & PF_RANDOMIZE) &&
 		!(current->personality & ADDR_NO_RANDOMIZE)) {
-		random_variable = (unsigned long) get_random_int();
+		random_variable = get_random_long();
 		random_variable &= STACK_RND_MASK;
 		random_variable <<= PAGE_SHIFT;
 	}
@@ -759,16 +762,16 @@ static int load_elf_binary(struct linux_binprm *bprm)
 			 */
 			would_dump(bprm, interpreter);
 
-			retval = kernel_read(interpreter, 0, bprm->buf,
-					     BINPRM_BUF_SIZE);
-			if (retval != BINPRM_BUF_SIZE) {
+			/* Get the exec headers */
+			retval = kernel_read(interpreter, 0,
+					     (void *)&loc->interp_elf_ex,
+					     sizeof(loc->interp_elf_ex));
+			if (retval != sizeof(loc->interp_elf_ex)) {
 				if (retval >= 0)
 					retval = -EIO;
 				goto out_free_dentry;
 			}
 
-			/* Get the exec headers */
-			loc->interp_elf_ex = *((struct elfhdr *)bprm->buf);
 			break;
 		}
 		elf_ppnt++;
@@ -828,7 +831,9 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	 * still possible to return an error to the code that invoked
 	 * the exec syscall.
 	 */
-	retval = arch_check_elf(&loc->elf_ex, !!interpreter, &arch_state);
+	retval = arch_check_elf(&loc->elf_ex,
+				!!interpreter, &loc->interp_elf_ex,
+				&arch_state);
 	if (retval)
 		goto out_free_dentry;
 
@@ -1236,6 +1241,15 @@ static unsigned long vma_dump_size(struct vm_area_struct *vma,
 	if (vma->vm_flags & VM_DONTDUMP)
 		return 0;
 
+	/* support for DAX */
+	if (vma_is_dax(vma)) {
+		if ((vma->vm_flags & VM_SHARED) && FILTER(DAX_SHARED))
+			goto whole;
+		if (!(vma->vm_flags & VM_SHARED) && FILTER(DAX_PRIVATE))
+			goto whole;
+		return 0;
+	}
+
 	/* Hugetlb memory check */
 	if (vma->vm_flags & VM_HUGETLB) {
 		if ((vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_SHARED))
@@ -2278,7 +2292,7 @@ static int elf_core_dump(struct coredump_params *cprm)
 				void *kaddr = kmap(page);
 				stop = !dump_emit(cprm, kaddr, PAGE_SIZE);
 				kunmap(page);
-				page_cache_release(page);
+				put_page(page);
 			} else
 				stop = !dump_skip(cprm, PAGE_SIZE);
 			if (stop)
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index d3634bfb7fe1..083ea2bc60ab 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -35,6 +35,7 @@
 #include <linux/elf-fdpic.h>
 #include <linux/elfcore.h>
 #include <linux/coredump.h>
+#include <linux/dax.h>
 
 #include <asm/uaccess.h>
 #include <asm/param.h>
@@ -103,19 +104,36 @@ static void __exit exit_elf_fdpic_binfmt(void)
 core_initcall(init_elf_fdpic_binfmt);
 module_exit(exit_elf_fdpic_binfmt);
 
-static int is_elf_fdpic(struct elfhdr *hdr, struct file *file)
+static int is_elf(struct elfhdr *hdr, struct file *file)
 {
 	if (memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0)
 		return 0;
 	if (hdr->e_type != ET_EXEC && hdr->e_type != ET_DYN)
 		return 0;
-	if (!elf_check_arch(hdr) || !elf_check_fdpic(hdr))
+	if (!elf_check_arch(hdr))
 		return 0;
 	if (!file->f_op->mmap)
 		return 0;
 	return 1;
 }
 
+#ifndef elf_check_fdpic
+#define elf_check_fdpic(x) 0
+#endif
+
+#ifndef elf_check_const_displacement
+#define elf_check_const_displacement(x) 0
+#endif
+
+static int is_constdisp(struct elfhdr *hdr)
+{
+	if (!elf_check_fdpic(hdr))
+		return 1;
+	if (elf_check_const_displacement(hdr))
+		return 1;
+	return 0;
+}
+
 /*****************************************************************************/
 /*
  * read the program headers table into memory
@@ -191,8 +209,18 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
 
 	/* check that this is a binary we know how to deal with */
 	retval = -ENOEXEC;
-	if (!is_elf_fdpic(&exec_params.hdr, bprm->file))
+	if (!is_elf(&exec_params.hdr, bprm->file))
+		goto error;
+	if (!elf_check_fdpic(&exec_params.hdr)) {
+#ifdef CONFIG_MMU
+		/* binfmt_elf handles non-fdpic elf except on nommu */
 		goto error;
+#else
+		/* nommu can only load ET_DYN (PIE) ELF */
+		if (exec_params.hdr.e_type != ET_DYN)
+			goto error;
+#endif
+	}
 
 	/* read the program header table */
 	retval = elf_fdpic_fetch_phdrs(&exec_params, bprm->file);
@@ -269,13 +297,13 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
 
 	}
 
-	if (elf_check_const_displacement(&exec_params.hdr))
+	if (is_constdisp(&exec_params.hdr))
 		exec_params.flags |= ELF_FDPIC_FLAG_CONSTDISP;
 
 	/* perform insanity checks on the interpreter */
 	if (interpreter_name) {
 		retval = -ELIBBAD;
-		if (!is_elf_fdpic(&interp_params.hdr, interpreter))
+		if (!is_elf(&interp_params.hdr, interpreter))
 			goto error;
 
 		interp_params.flags = ELF_FDPIC_FLAG_PRESENT;
@@ -306,9 +334,9 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
 
 	retval = -ENOEXEC;
 	if (stack_size == 0)
-		goto error;
+		stack_size = 131072UL; /* same as exec.c's default commit */
 
-	if (elf_check_const_displacement(&interp_params.hdr))
+	if (is_constdisp(&interp_params.hdr))
 		interp_params.flags |= ELF_FDPIC_FLAG_CONSTDISP;
 
 	/* flush all traces of the currently running executable */
@@ -319,7 +347,10 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
 	/* there's now no turning back... the old userspace image is dead,
 	 * defunct, deceased, etc.
 	 */
-	set_personality(PER_LINUX_FDPIC);
+	if (elf_check_fdpic(&exec_params.hdr))
+		set_personality(PER_LINUX_FDPIC);
+	else
+		set_personality(PER_LINUX);
 	if (elf_read_implies_exec(&exec_params.hdr, executable_stack))
 		current->personality |= READ_IMPLIES_EXEC;
 
@@ -374,10 +405,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
 		PAGE_ALIGN(current->mm->start_brk);
 
 #else
-	/* create a stack and brk area big enough for everyone
-	 * - the brk heap starts at the bottom and works up
-	 * - the stack starts at the top and works down
-	 */
+	/* create a stack area and zero-size brk area */
 	stack_size = (stack_size + PAGE_SIZE - 1) & PAGE_MASK;
 	if (stack_size < PAGE_SIZE * 2)
 		stack_size = PAGE_SIZE * 2;
@@ -400,8 +428,6 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
 
 	current->mm->brk = current->mm->start_brk;
 	current->mm->context.end_brk = current->mm->start_brk;
-	current->mm->context.end_brk +=
-		(stack_size > PAGE_SIZE) ? (stack_size - PAGE_SIZE) : 0;
 	current->mm->start_stack = current->mm->start_brk + stack_size;
 #endif
 
@@ -1206,6 +1232,20 @@ static int maydump(struct vm_area_struct *vma, unsigned long mm_flags)
 		return 0;
 	}
 
+	/* support for DAX */
+	if (vma_is_dax(vma)) {
+		if (vma->vm_flags & VM_SHARED) {
+			dump_ok = test_bit(MMF_DUMP_DAX_SHARED, &mm_flags);
+			kdcore("%08lx: %08lx: %s (DAX shared)", vma->vm_start,
+			       vma->vm_flags, dump_ok ? "yes" : "no");
+		} else {
+			dump_ok = test_bit(MMF_DUMP_DAX_PRIVATE, &mm_flags);
+			kdcore("%08lx: %08lx: %s (DAX private)", vma->vm_start,
+			       vma->vm_flags, dump_ok ? "yes" : "no");
+		}
+		return dump_ok;
+	}
+
 	/* By default, dump shared memory if mapped from an anonymous file. */
 	if (vma->vm_flags & VM_SHARED) {
 		if (file_inode(vma->vm_file)->i_nlink == 0) {
@@ -1493,7 +1533,7 @@ static bool elf_fdpic_dump_segments(struct coredump_params *cprm)
 				void *kaddr = kmap(page);
 				res = dump_emit(cprm, kaddr, PAGE_SIZE);
 				kunmap(page);
-				page_cache_release(page);
+				put_page(page);
 			} else {
 				res = dump_skip(cprm, PAGE_SIZE);
 			}
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 78f005f37847..3a3ced779fc7 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -638,11 +638,11 @@ static ssize_t bm_entry_write(struct file *file, const char __user *buffer,
 	case 3:
 		/* Delete this handler. */
 		root = dget(file->f_path.dentry->d_sb->s_root);
-		mutex_lock(&d_inode(root)->i_mutex);
+		inode_lock(d_inode(root));
 
 		kill_node(e);
 
-		mutex_unlock(&d_inode(root)->i_mutex);
+		inode_unlock(d_inode(root));
 		dput(root);
 		break;
 	default:
@@ -675,7 +675,7 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer,
 		return PTR_ERR(e);
 
 	root = dget(sb->s_root);
-	mutex_lock(&d_inode(root)->i_mutex);
+	inode_lock(d_inode(root));
 	dentry = lookup_one_len(e->name, root, strlen(e->name));
 	err = PTR_ERR(dentry);
 	if (IS_ERR(dentry))
@@ -711,7 +711,7 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer,
 out2:
 	dput(dentry);
 out:
-	mutex_unlock(&d_inode(root)->i_mutex);
+	inode_unlock(d_inode(root));
 	dput(root);
 
 	if (err) {
@@ -754,12 +754,12 @@ static ssize_t bm_status_write(struct file *file, const char __user *buffer,
 	case 3:
 		/* Delete all handlers. */
 		root = dget(file->f_path.dentry->d_sb->s_root);
-		mutex_lock(&d_inode(root)->i_mutex);
+		inode_lock(d_inode(root));
 
 		while (!list_empty(&entries))
 			kill_node(list_entry(entries.next, Node, list));
 
-		mutex_unlock(&d_inode(root)->i_mutex);
+		inode_unlock(d_inode(root));
 		dput(root);
 		break;
 	default:
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 0a793c7930eb..20a2c02b77c4 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -50,12 +50,21 @@ struct block_device *I_BDEV(struct inode *inode)
 }
 EXPORT_SYMBOL(I_BDEV);
 
-static void bdev_write_inode(struct inode *inode)
+static void bdev_write_inode(struct block_device *bdev)
 {
+	struct inode *inode = bdev->bd_inode;
+	int ret;
+
 	spin_lock(&inode->i_lock);
 	while (inode->i_state & I_DIRTY) {
 		spin_unlock(&inode->i_lock);
-		WARN_ON_ONCE(write_inode_now(inode, true));
+		ret = write_inode_now(inode, true);
+		if (ret) {
+			char name[BDEVNAME_SIZE];
+			pr_warn_ratelimited("VFS: Dirty inode writeback failed "
+					    "for block device %s (err=%d).\n",
+					    bdevname(bdev, name), ret);
+		}
 		spin_lock(&inode->i_lock);
 	}
 	spin_unlock(&inode->i_lock);
@@ -66,7 +75,7 @@ void kill_bdev(struct block_device *bdev)
 {
 	struct address_space *mapping = bdev->bd_inode->i_mapping;
 
-	if (mapping->nrpages == 0 && mapping->nrshadows == 0)
+	if (mapping->nrpages == 0 && mapping->nrexceptional == 0)
 		return;
 
 	invalidate_bh_lrus();
@@ -147,11 +156,16 @@ blkdev_get_block(struct inode *inode, sector_t iblock,
 	return 0;
 }
 
+static struct inode *bdev_file_inode(struct file *file)
+{
+	return file->f_mapping->host;
+}
+
 static ssize_t
 blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
-	struct inode *inode = file->f_mapping->host;
+	struct inode *inode = bdev_file_inode(file);
 
 	if (IS_DAX(inode))
 		return dax_do_io(iocb, inode, iter, offset, blkdev_get_block,
@@ -317,7 +331,7 @@ static int blkdev_write_end(struct file *file, struct address_space *mapping,
 	ret = block_write_end(file, mapping, pos, len, copied, page, fsdata);
 
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 
 	return ret;
 }
@@ -329,18 +343,18 @@ static int blkdev_write_end(struct file *file, struct address_space *mapping,
  */
 static loff_t block_llseek(struct file *file, loff_t offset, int whence)
 {
-	struct inode *bd_inode = file->f_mapping->host;
+	struct inode *bd_inode = bdev_file_inode(file);
 	loff_t retval;
 
-	mutex_lock(&bd_inode->i_mutex);
+	inode_lock(bd_inode);
 	retval = fixed_size_llseek(file, offset, whence, i_size_read(bd_inode));
-	mutex_unlock(&bd_inode->i_mutex);
+	inode_unlock(bd_inode);
 	return retval;
 }
 	
 int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
 {
-	struct inode *bd_inode = filp->f_mapping->host;
+	struct inode *bd_inode = bdev_file_inode(filp);
 	struct block_device *bdev = I_BDEV(bd_inode);
 	int error;
 	
@@ -381,9 +395,17 @@ int bdev_read_page(struct block_device *bdev, sector_t sector,
 			struct page *page)
 {
 	const struct block_device_operations *ops = bdev->bd_disk->fops;
+	int result = -EOPNOTSUPP;
+
 	if (!ops->rw_page || bdev_get_integrity(bdev))
-		return -EOPNOTSUPP;
-	return ops->rw_page(bdev, sector + get_start_sect(bdev), page, READ);
+		return result;
+
+	result = blk_queue_enter(bdev->bd_queue, false);
+	if (result)
+		return result;
+	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, READ);
+	blk_queue_exit(bdev->bd_queue);
+	return result;
 }
 EXPORT_SYMBOL_GPL(bdev_read_page);
 
@@ -412,14 +434,20 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 	int result;
 	int rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE;
 	const struct block_device_operations *ops = bdev->bd_disk->fops;
+
 	if (!ops->rw_page || bdev_get_integrity(bdev))
 		return -EOPNOTSUPP;
+	result = blk_queue_enter(bdev->bd_queue, false);
+	if (result)
+		return result;
+
 	set_page_writeback(page);
 	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, rw);
 	if (result)
 		end_page_writeback(page);
 	else
 		unlock_page(page);
+	blk_queue_exit(bdev->bd_queue);
 	return result;
 }
 EXPORT_SYMBOL_GPL(bdev_write_page);
@@ -427,10 +455,7 @@ EXPORT_SYMBOL_GPL(bdev_write_page);
 /**
  * bdev_direct_access() - Get the address for directly-accessibly memory
  * @bdev: The device containing the memory
- * @sector: The offset within the device
- * @addr: Where to put the address of the memory
- * @pfn: The Page Frame Number for the memory
- * @size: The number of bytes requested
+ * @dax: control and output parameters for ->direct_access
  *
  * If a block device is made up of directly addressable memory, this function
  * will tell the caller the PFN and the address of the memory.  The address
@@ -441,10 +466,10 @@ EXPORT_SYMBOL_GPL(bdev_write_page);
  * Return: negative errno if an error occurs, otherwise the number of bytes
  * accessible at this address.
  */
-long bdev_direct_access(struct block_device *bdev, sector_t sector,
-			void __pmem **addr, unsigned long *pfn, long size)
+long bdev_direct_access(struct block_device *bdev, struct blk_dax_ctl *dax)
 {
-	long avail;
+	sector_t sector = dax->sector;
+	long avail, size = dax->size;
 	const struct block_device_operations *ops = bdev->bd_disk->fops;
 
 	/*
@@ -463,9 +488,11 @@ long bdev_direct_access(struct block_device *bdev, sector_t sector,
 	sector += get_start_sect(bdev);
 	if (sector % (PAGE_SIZE / 512))
 		return -EINVAL;
-	avail = ops->direct_access(bdev, sector, addr, pfn);
+	avail = ops->direct_access(bdev, sector, &dax->addr, &dax->pfn);
 	if (!avail)
 		return -ERANGE;
+	if (avail > 0 && avail & ~PAGE_MASK)
+		return -ENXIO;
 	return min(avail, size);
 }
 EXPORT_SYMBOL_GPL(bdev_direct_access);
@@ -548,7 +575,11 @@ static const struct super_operations bdev_sops = {
 static struct dentry *bd_mount(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data)
 {
-	return mount_pseudo(fs_type, "bdev:", &bdev_sops, NULL, BDEVFS_MAGIC);
+	struct dentry *dent;
+	dent = mount_pseudo(fs_type, "bdev:", &bdev_sops, NULL, BDEVFS_MAGIC);
+	if (dent)
+		dent->d_sb->s_iflags |= SB_I_CGROUPWB;
+	return dent;
 }
 
 static struct file_system_type bd_type = {
@@ -567,7 +598,7 @@ void __init bdev_cache_init(void)
 
 	bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode),
 			0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
-				SLAB_MEM_SPREAD|SLAB_PANIC),
+				SLAB_MEM_SPREAD|SLAB_ACCOUNT|SLAB_PANIC),
 			init_once);
 	err = register_filesystem(&bd_type);
 	if (err)
@@ -673,7 +704,7 @@ static struct block_device *bd_acquire(struct inode *inode)
 	spin_lock(&bdev_lock);
 	bdev = inode->i_bdev;
 	if (bdev) {
-		ihold(bdev->bd_inode);
+		bdgrab(bdev);
 		spin_unlock(&bdev_lock);
 		return bdev;
 	}
@@ -689,7 +720,7 @@ static struct block_device *bd_acquire(struct inode *inode)
 			 * So, we can access it via ->i_mapping always
 			 * without igrab().
 			 */
-			ihold(bdev->bd_inode);
+			bdgrab(bdev);
 			inode->i_bdev = bdev;
 			inode->i_mapping = bdev->bd_inode->i_mapping;
 			list_add(&inode->i_devices, &bdev->bd_inodes);
@@ -712,7 +743,7 @@ void bd_forget(struct inode *inode)
 	spin_unlock(&bdev_lock);
 
 	if (bdev)
-		iput(bdev->bd_inode);
+		bdput(bdev);
 }
 
 /**
@@ -1019,12 +1050,9 @@ EXPORT_SYMBOL_GPL(bd_unlink_disk_holder);
 static void flush_disk(struct block_device *bdev, bool kill_dirty)
 {
 	if (__invalidate_device(bdev, kill_dirty)) {
-		char name[BDEVNAME_SIZE] = "";
-
-		if (bdev->bd_disk)
-			disk_name(bdev->bd_disk, 0, name);
 		printk(KERN_WARNING "VFS: busy inodes on changed media or "
-		       "resized disk %s\n", name);
+		       "resized disk %s\n",
+		       bdev->bd_disk ? bdev->bd_disk->disk_name : "");
 	}
 
 	if (!bdev->bd_disk)
@@ -1048,12 +1076,9 @@ void check_disk_size_change(struct gendisk *disk, struct block_device *bdev)
 	disk_size = (loff_t)get_capacity(disk) << 9;
 	bdev_size = i_size_read(bdev->bd_inode);
 	if (disk_size != bdev_size) {
-		char name[BDEVNAME_SIZE];
-
-		disk_name(disk, 0, name);
 		printk(KERN_INFO
 		       "%s: detected capacity change from %lld to %lld\n",
-		       name, bdev_size, disk_size);
+		       disk->disk_name, bdev_size, disk_size);
 		i_size_write(bdev->bd_inode, disk_size);
 		flush_disk(bdev, false);
 	}
@@ -1121,10 +1146,10 @@ void bd_set_size(struct block_device *bdev, loff_t size)
 {
 	unsigned bsize = bdev_logical_block_size(bdev);
 
-	mutex_lock(&bdev->bd_inode->i_mutex);
+	inode_lock(bdev->bd_inode);
 	i_size_write(bdev->bd_inode, size);
-	mutex_unlock(&bdev->bd_inode->i_mutex);
-	while (bsize < PAGE_CACHE_SIZE) {
+	inode_unlock(bdev->bd_inode);
+	while (bsize < PAGE_SIZE) {
 		if (size & bsize)
 			break;
 		bsize <<= 1;
@@ -1180,7 +1205,11 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 		bdev->bd_disk = disk;
 		bdev->bd_queue = disk->queue;
 		bdev->bd_contains = bdev;
-		bdev->bd_inode->i_flags = disk->fops->direct_access ? S_DAX : 0;
+		if (IS_ENABLED(CONFIG_BLK_DEV_DAX) && disk->fops->direct_access)
+			bdev->bd_inode->i_flags = S_DAX;
+		else
+			bdev->bd_inode->i_flags = 0;
+
 		if (!partno) {
 			ret = -ENXIO;
 			bdev->bd_part = disk_get_part(disk, partno);
@@ -1207,8 +1236,11 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 				}
 			}
 
-			if (!ret)
+			if (!ret) {
 				bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
+				if (!blkdev_dax_capable(bdev))
+					bdev->bd_inode->i_flags &= ~S_DAX;
+			}
 
 			/*
 			 * If the device is invalidated, rescan partition
@@ -1222,6 +1254,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 				else if (ret == -ENOMEDIUM)
 					invalidate_partitions(disk, bdev);
 			}
+
 			if (ret)
 				goto out_clear;
 		} else {
@@ -1242,12 +1275,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 				goto out_clear;
 			}
 			bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
-			/*
-			 * If the partition is not aligned on a page
-			 * boundary, we can't do dax I/O to it.
-			 */
-			if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512)) ||
-			    (bdev->bd_part->nr_sects % (PAGE_SIZE / 512)))
+			if (!blkdev_dax_capable(bdev))
 				bdev->bd_inode->i_flags &= ~S_DAX;
 		}
 	} else {
@@ -1500,11 +1528,14 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 		WARN_ON_ONCE(bdev->bd_holders);
 		sync_blockdev(bdev);
 		kill_bdev(bdev);
+
+		bdev_write_inode(bdev);
 		/*
-		 * ->release can cause the queue to disappear, so flush all
-		 * dirty data before.
+		 * Detaching bdev inode from its wb in __destroy_inode()
+		 * is too late: the queue which embeds its bdi (along with
+		 * root wb) can be gone as soon as we put_disk() below.
 		 */
-		bdev_write_inode(bdev->bd_inode);
+		inode_detach_wb(bdev->bd_inode);
 	}
 	if (bdev->bd_contains == bdev) {
 		if (disk->fops->release)
@@ -1579,14 +1610,14 @@ EXPORT_SYMBOL(blkdev_put);
 
 static int blkdev_close(struct inode * inode, struct file * filp)
 {
-	struct block_device *bdev = I_BDEV(filp->f_mapping->host);
+	struct block_device *bdev = I_BDEV(bdev_file_inode(filp));
 	blkdev_put(bdev, filp->f_mode);
 	return 0;
 }
 
 static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 {
-	struct block_device *bdev = I_BDEV(file->f_mapping->host);
+	struct block_device *bdev = I_BDEV(bdev_file_inode(file));
 	fmode_t mode = file->f_mode;
 
 	/*
@@ -1611,7 +1642,7 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
-	struct inode *bd_inode = file->f_mapping->host;
+	struct inode *bd_inode = bdev_file_inode(file);
 	loff_t size = i_size_read(bd_inode);
 	struct blk_plug plug;
 	ssize_t ret;
@@ -1643,7 +1674,7 @@ EXPORT_SYMBOL_GPL(blkdev_write_iter);
 ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct file *file = iocb->ki_filp;
-	struct inode *bd_inode = file->f_mapping->host;
+	struct inode *bd_inode = bdev_file_inode(file);
 	loff_t size = i_size_read(bd_inode);
 	loff_t pos = iocb->ki_pos;
 
@@ -1670,25 +1701,102 @@ static int blkdev_releasepage(struct page *page, gfp_t wait)
 	return try_to_free_buffers(page);
 }
 
+static int blkdev_writepages(struct address_space *mapping,
+			     struct writeback_control *wbc)
+{
+	if (dax_mapping(mapping)) {
+		struct block_device *bdev = I_BDEV(mapping->host);
+
+		return dax_writeback_mapping_range(mapping, bdev, wbc);
+	}
+	return generic_writepages(mapping, wbc);
+}
+
 static const struct address_space_operations def_blk_aops = {
 	.readpage	= blkdev_readpage,
 	.readpages	= blkdev_readpages,
 	.writepage	= blkdev_writepage,
 	.write_begin	= blkdev_write_begin,
 	.write_end	= blkdev_write_end,
-	.writepages	= generic_writepages,
+	.writepages	= blkdev_writepages,
 	.releasepage	= blkdev_releasepage,
 	.direct_IO	= blkdev_direct_IO,
 	.is_dirty_writeback = buffer_check_dirty_writeback,
 };
 
+#ifdef CONFIG_FS_DAX
+/*
+ * In the raw block case we do not need to contend with truncation nor
+ * unwritten file extents.  Without those concerns there is no need for
+ * additional locking beyond the mmap_sem context that these routines
+ * are already executing under.
+ *
+ * Note, there is no protection if the block device is dynamically
+ * resized (partition grow/shrink) during a fault. A stable block device
+ * size is already not enforced in the blkdev_direct_IO path.
+ *
+ * For DAX, it is the responsibility of the block device driver to
+ * ensure the whole-disk device size is stable while requests are in
+ * flight.
+ *
+ * Finally, unlike the filemap_page_mkwrite() case there is no
+ * filesystem superblock to sync against freezing.  We still include a
+ * pfn_mkwrite callback for dax drivers to receive write fault
+ * notifications.
+ */
+static int blkdev_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	return __dax_fault(vma, vmf, blkdev_get_block, NULL);
+}
+
+static int blkdev_dax_pfn_mkwrite(struct vm_area_struct *vma,
+		struct vm_fault *vmf)
+{
+	return dax_pfn_mkwrite(vma, vmf);
+}
+
+static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
+		pmd_t *pmd, unsigned int flags)
+{
+	return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL);
+}
+
+static const struct vm_operations_struct blkdev_dax_vm_ops = {
+	.fault		= blkdev_dax_fault,
+	.pmd_fault	= blkdev_dax_pmd_fault,
+	.pfn_mkwrite	= blkdev_dax_pfn_mkwrite,
+};
+
+static const struct vm_operations_struct blkdev_default_vm_ops = {
+	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
+};
+
+static int blkdev_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct inode *bd_inode = bdev_file_inode(file);
+
+	file_accessed(file);
+	if (IS_DAX(bd_inode)) {
+		vma->vm_ops = &blkdev_dax_vm_ops;
+		vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
+	} else {
+		vma->vm_ops = &blkdev_default_vm_ops;
+	}
+
+	return 0;
+}
+#else
+#define blkdev_mmap generic_file_mmap
+#endif
+
 const struct file_operations def_blk_fops = {
 	.open		= blkdev_open,
 	.release	= blkdev_close,
 	.llseek		= block_llseek,
 	.read_iter	= blkdev_read_iter,
 	.write_iter	= blkdev_write_iter,
-	.mmap		= generic_file_mmap,
+	.mmap		= blkdev_mmap,
 	.fsync		= blkdev_fsync,
 	.unlocked_ioctl	= block_ioctl,
 #ifdef CONFIG_COMPAT
diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index 6d1d0b93b1aa..128ce17a80b0 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -9,11 +9,12 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 	   export.o tree-log.o free-space-cache.o zlib.o lzo.o \
 	   compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \
 	   reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \
-	   uuid-tree.o props.o hash.o
+	   uuid-tree.o props.o hash.o free-space-tree.o
 
 btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o
 btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o
 
 btrfs-$(CONFIG_BTRFS_FS_RUN_SANITY_TESTS) += tests/free-space-tests.o \
 	tests/extent-buffer-tests.o tests/btrfs-tests.o \
-	tests/extent-io-tests.o tests/inode-tests.o tests/qgroup-tests.o
+	tests/extent-io-tests.o tests/inode-tests.o tests/qgroup-tests.o \
+	tests/free-space-tree-tests.o
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 9a0124a95851..6d263bb1621c 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -37,10 +37,10 @@ struct posix_acl *btrfs_get_acl(struct inode *inode, int type)
 
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		name = POSIX_ACL_XATTR_ACCESS;
+		name = XATTR_NAME_POSIX_ACL_ACCESS;
 		break;
 	case ACL_TYPE_DEFAULT:
-		name = POSIX_ACL_XATTR_DEFAULT;
+		name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		break;
 	default:
 		BUG();
@@ -48,7 +48,7 @@ struct posix_acl *btrfs_get_acl(struct inode *inode, int type)
 
 	size = __btrfs_getxattr(inode, name, "", 0);
 	if (size > 0) {
-		value = kzalloc(size, GFP_NOFS);
+		value = kzalloc(size, GFP_KERNEL);
 		if (!value)
 			return ERR_PTR(-ENOMEM);
 		size = __btrfs_getxattr(inode, name, value, size);
@@ -81,7 +81,7 @@ static int __btrfs_set_acl(struct btrfs_trans_handle *trans,
 
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		name = POSIX_ACL_XATTR_ACCESS;
+		name = XATTR_NAME_POSIX_ACL_ACCESS;
 		if (acl) {
 			ret = posix_acl_equiv_mode(acl, &inode->i_mode);
 			if (ret < 0)
@@ -94,7 +94,7 @@ static int __btrfs_set_acl(struct btrfs_trans_handle *trans,
 	case ACL_TYPE_DEFAULT:
 		if (!S_ISDIR(inode->i_mode))
 			return acl ? -EINVAL : 0;
-		name = POSIX_ACL_XATTR_DEFAULT;
+		name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		break;
 	default:
 		return -EINVAL;
@@ -102,7 +102,7 @@ static int __btrfs_set_acl(struct btrfs_trans_handle *trans,
 
 	if (acl) {
 		size = posix_acl_xattr_size(acl->a_count);
-		value = kmalloc(size, GFP_NOFS);
+		value = kmalloc(size, GFP_KERNEL);
 		if (!value) {
 			ret = -ENOMEM;
 			goto out;
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 3e36e4adc4a3..5fb60ea7eee2 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -97,7 +97,7 @@ static struct __btrfs_workqueue *
 __btrfs_alloc_workqueue(const char *name, unsigned int flags, int limit_active,
 			 int thresh)
 {
-	struct __btrfs_workqueue *ret = kzalloc(sizeof(*ret), GFP_NOFS);
+	struct __btrfs_workqueue *ret = kzalloc(sizeof(*ret), GFP_KERNEL);
 
 	if (!ret)
 		return NULL;
@@ -148,7 +148,7 @@ struct btrfs_workqueue *btrfs_alloc_workqueue(const char *name,
 					      int limit_active,
 					      int thresh)
 {
-	struct btrfs_workqueue *ret = kzalloc(sizeof(*ret), GFP_NOFS);
+	struct btrfs_workqueue *ret = kzalloc(sizeof(*ret), GFP_KERNEL);
 
 	if (!ret)
 		return NULL;
@@ -328,8 +328,8 @@ static inline void __btrfs_queue_work(struct __btrfs_workqueue *wq,
 		list_add_tail(&work->ordered_list, &wq->ordered_list);
 		spin_unlock_irqrestore(&wq->list_lock, flags);
 	}
-	queue_work(wq->normal_wq, &work->normal_work);
 	trace_btrfs_work_queued(work);
+	queue_work(wq->normal_wq, &work->normal_work);
 }
 
 void btrfs_queue_work(struct btrfs_workqueue *wq,
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 6dcdb2ec9211..80e8472d618b 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -148,8 +148,7 @@ int __init btrfs_prelim_ref_init(void)
 
 void btrfs_prelim_ref_exit(void)
 {
-	if (btrfs_prelim_ref_cache)
-		kmem_cache_destroy(btrfs_prelim_ref_cache);
+	kmem_cache_destroy(btrfs_prelim_ref_cache);
 }
 
 /*
@@ -355,7 +354,7 @@ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info,
 
 	index = srcu_read_lock(&fs_info->subvol_srcu);
 
-	root = btrfs_read_fs_root_no_name(fs_info, &root_key);
+	root = btrfs_get_fs_root(fs_info, &root_key, false);
 	if (IS_ERR(root)) {
 		srcu_read_unlock(&fs_info->subvol_srcu, index);
 		ret = PTR_ERR(root);
@@ -520,13 +519,10 @@ static inline int ref_for_same_block(struct __prelim_ref *ref1,
 static int __add_missing_keys(struct btrfs_fs_info *fs_info,
 			      struct list_head *head)
 {
-	struct list_head *pos;
+	struct __prelim_ref *ref;
 	struct extent_buffer *eb;
 
-	list_for_each(pos, head) {
-		struct __prelim_ref *ref;
-		ref = list_entry(pos, struct __prelim_ref, list);
-
+	list_for_each_entry(ref, head, list) {
 		if (ref->parent)
 			continue;
 		if (ref->key_for_search.type)
@@ -563,31 +559,20 @@ static int __add_missing_keys(struct btrfs_fs_info *fs_info,
  */
 static void __merge_refs(struct list_head *head, int mode)
 {
-	struct list_head *pos1;
+	struct __prelim_ref *pos1;
 
-	list_for_each(pos1, head) {
-		struct list_head *n2;
-		struct list_head *pos2;
-		struct __prelim_ref *ref1;
+	list_for_each_entry(pos1, head, list) {
+		struct __prelim_ref *pos2 = pos1, *tmp;
 
-		ref1 = list_entry(pos1, struct __prelim_ref, list);
-
-		for (pos2 = pos1->next, n2 = pos2->next; pos2 != head;
-		     pos2 = n2, n2 = pos2->next) {
-			struct __prelim_ref *ref2;
-			struct __prelim_ref *xchg;
+		list_for_each_entry_safe_continue(pos2, tmp, head, list) {
+			struct __prelim_ref *ref1 = pos1, *ref2 = pos2;
 			struct extent_inode_elem *eie;
 
-			ref2 = list_entry(pos2, struct __prelim_ref, list);
-
 			if (!ref_for_same_block(ref1, ref2))
 				continue;
 			if (mode == 1) {
-				if (!ref1->parent && ref2->parent) {
-					xchg = ref1;
-					ref1 = ref2;
-					ref2 = xchg;
-				}
+				if (!ref1->parent && ref2->parent)
+					swap(ref1, ref2);
 			} else {
 				if (ref1->parent != ref2->parent)
 					continue;
@@ -1417,7 +1402,8 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 			read_extent_buffer(eb, dest + bytes_left,
 					   name_off, name_len);
 		if (eb != eb_in) {
-			btrfs_tree_read_unlock_blocking(eb);
+			if (!path->skip_locking)
+				btrfs_tree_read_unlock_blocking(eb);
 			free_extent_buffer(eb);
 		}
 		ret = btrfs_find_item(fs_root, path, parent, 0,
@@ -1437,9 +1423,10 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 		eb = path->nodes[0];
 		/* make sure we can use eb after releasing the path */
 		if (eb != eb_in) {
-			atomic_inc(&eb->refs);
-			btrfs_tree_read_lock(eb);
-			btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+			if (!path->skip_locking)
+				btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+			path->nodes[0] = NULL;
+			path->locks[0] = 0;
 		}
 		btrfs_release_path(path);
 		iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref);
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 0ef5cc13fae2..61205e3bbefa 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -192,6 +192,10 @@ struct btrfs_inode {
 	/* File creation time. */
 	struct timespec i_otime;
 
+	/* Hook into fs_info->delayed_iputs */
+	struct list_head delayed_iput;
+	long delayed_iput_count;
+
 	struct inode vfs_inode;
 };
 
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index 0340c57bf377..516e19d1d202 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -95,6 +95,7 @@
 #include <linux/genhd.h>
 #include <linux/blkdev.h>
 #include <linux/vmalloc.h>
+#include <linux/string.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "hash.h"
@@ -105,6 +106,7 @@
 #include "locking.h"
 #include "check-integrity.h"
 #include "rcu-string.h"
+#include "compression.h"
 
 #define BTRFSIC_BLOCK_HASHTABLE_SIZE 0x10000
 #define BTRFSIC_BLOCK_LINK_HASHTABLE_SIZE 0x10000
@@ -176,7 +178,7 @@ struct btrfsic_block {
  * Elements of this type are allocated dynamically and required because
  * each block object can refer to and can be ref from multiple blocks.
  * The key to lookup them in the hashtable is the dev_bytenr of
- * the block ref to plus the one from the block refered from.
+ * the block ref to plus the one from the block referred from.
  * The fact that they are searchable via a hashtable and that a
  * ref_cnt is maintained is not required for the btrfs integrity
  * check algorithm itself, it is only used to make the output more
@@ -531,13 +533,9 @@ static struct btrfsic_block *btrfsic_block_hashtable_lookup(
 	    (((unsigned int)(dev_bytenr >> 16)) ^
 	     ((unsigned int)((uintptr_t)bdev))) &
 	     (BTRFSIC_BLOCK_HASHTABLE_SIZE - 1);
-	struct list_head *elem;
-
-	list_for_each(elem, h->table + hashval) {
-		struct btrfsic_block *const b =
-		    list_entry(elem, struct btrfsic_block,
-			       collision_resolving_node);
+	struct btrfsic_block *b;
 
+	list_for_each_entry(b, h->table + hashval, collision_resolving_node) {
 		if (b->dev_state->bdev == bdev && b->dev_bytenr == dev_bytenr)
 			return b;
 	}
@@ -588,13 +586,9 @@ static struct btrfsic_block_link *btrfsic_block_link_hashtable_lookup(
 	     ((unsigned int)((uintptr_t)bdev_ref_to)) ^
 	     ((unsigned int)((uintptr_t)bdev_ref_from))) &
 	     (BTRFSIC_BLOCK_LINK_HASHTABLE_SIZE - 1);
-	struct list_head *elem;
-
-	list_for_each(elem, h->table + hashval) {
-		struct btrfsic_block_link *const l =
-		    list_entry(elem, struct btrfsic_block_link,
-			       collision_resolving_node);
+	struct btrfsic_block_link *l;
 
+	list_for_each_entry(l, h->table + hashval, collision_resolving_node) {
 		BUG_ON(NULL == l->block_ref_to);
 		BUG_ON(NULL == l->block_ref_from);
 		if (l->block_ref_to->dev_state->bdev == bdev_ref_to &&
@@ -639,13 +633,9 @@ static struct btrfsic_dev_state *btrfsic_dev_state_hashtable_lookup(
 	const unsigned int hashval =
 	    (((unsigned int)((uintptr_t)bdev)) &
 	     (BTRFSIC_DEV2STATE_HASHTABLE_SIZE - 1));
-	struct list_head *elem;
-
-	list_for_each(elem, h->table + hashval) {
-		struct btrfsic_dev_state *const ds =
-		    list_entry(elem, struct btrfsic_dev_state,
-			       collision_resolving_node);
+	struct btrfsic_dev_state *ds;
 
+	list_for_each_entry(ds, h->table + hashval, collision_resolving_node) {
 		if (ds->bdev == bdev)
 			return ds;
 	}
@@ -767,7 +757,7 @@ static int btrfsic_process_superblock(struct btrfsic_state *state,
 			BUG_ON(NULL == l);
 
 			ret = btrfsic_read_block(state, &tmp_next_block_ctx);
-			if (ret < (int)PAGE_CACHE_SIZE) {
+			if (ret < (int)PAGE_SIZE) {
 				printk(KERN_INFO
 				       "btrfsic: read @logical %llu failed!\n",
 				       tmp_next_block_ctx.start);
@@ -1241,15 +1231,15 @@ static void btrfsic_read_from_block_data(
 	size_t offset_in_page;
 	char *kaddr;
 	char *dst = (char *)dstv;
-	size_t start_offset = block_ctx->start & ((u64)PAGE_CACHE_SIZE - 1);
-	unsigned long i = (start_offset + offset) >> PAGE_CACHE_SHIFT;
+	size_t start_offset = block_ctx->start & ((u64)PAGE_SIZE - 1);
+	unsigned long i = (start_offset + offset) >> PAGE_SHIFT;
 
 	WARN_ON(offset + len > block_ctx->len);
-	offset_in_page = (start_offset + offset) & (PAGE_CACHE_SIZE - 1);
+	offset_in_page = (start_offset + offset) & (PAGE_SIZE - 1);
 
 	while (len > 0) {
-		cur = min(len, ((size_t)PAGE_CACHE_SIZE - offset_in_page));
-		BUG_ON(i >= DIV_ROUND_UP(block_ctx->len, PAGE_CACHE_SIZE));
+		cur = min(len, ((size_t)PAGE_SIZE - offset_in_page));
+		BUG_ON(i >= DIV_ROUND_UP(block_ctx->len, PAGE_SIZE));
 		kaddr = block_ctx->datav[i];
 		memcpy(dst, kaddr + offset_in_page, cur);
 
@@ -1615,8 +1605,8 @@ static void btrfsic_release_block_ctx(struct btrfsic_block_data_ctx *block_ctx)
 
 		BUG_ON(!block_ctx->datav);
 		BUG_ON(!block_ctx->pagev);
-		num_pages = (block_ctx->len + (u64)PAGE_CACHE_SIZE - 1) >>
-			    PAGE_CACHE_SHIFT;
+		num_pages = (block_ctx->len + (u64)PAGE_SIZE - 1) >>
+			    PAGE_SHIFT;
 		while (num_pages > 0) {
 			num_pages--;
 			if (block_ctx->datav[num_pages]) {
@@ -1647,15 +1637,15 @@ static int btrfsic_read_block(struct btrfsic_state *state,
 	BUG_ON(block_ctx->datav);
 	BUG_ON(block_ctx->pagev);
 	BUG_ON(block_ctx->mem_to_free);
-	if (block_ctx->dev_bytenr & ((u64)PAGE_CACHE_SIZE - 1)) {
+	if (block_ctx->dev_bytenr & ((u64)PAGE_SIZE - 1)) {
 		printk(KERN_INFO
 		       "btrfsic: read_block() with unaligned bytenr %llu\n",
 		       block_ctx->dev_bytenr);
 		return -1;
 	}
 
-	num_pages = (block_ctx->len + (u64)PAGE_CACHE_SIZE - 1) >>
-		    PAGE_CACHE_SHIFT;
+	num_pages = (block_ctx->len + (u64)PAGE_SIZE - 1) >>
+		    PAGE_SHIFT;
 	block_ctx->mem_to_free = kzalloc((sizeof(*block_ctx->datav) +
 					  sizeof(*block_ctx->pagev)) *
 					 num_pages, GFP_NOFS);
@@ -1686,8 +1676,8 @@ static int btrfsic_read_block(struct btrfsic_state *state,
 
 		for (j = i; j < num_pages; j++) {
 			ret = bio_add_page(bio, block_ctx->pagev[j],
-					   PAGE_CACHE_SIZE, 0);
-			if (PAGE_CACHE_SIZE != ret)
+					   PAGE_SIZE, 0);
+			if (PAGE_SIZE != ret)
 				break;
 		}
 		if (j == i) {
@@ -1703,7 +1693,7 @@ static int btrfsic_read_block(struct btrfsic_state *state,
 			return -1;
 		}
 		bio_put(bio);
-		dev_bytenr += (j - i) * PAGE_CACHE_SIZE;
+		dev_bytenr += (j - i) * PAGE_SIZE;
 		i = j;
 	}
 	for (i = 0; i < num_pages; i++) {
@@ -1720,29 +1710,20 @@ static int btrfsic_read_block(struct btrfsic_state *state,
 
 static void btrfsic_dump_database(struct btrfsic_state *state)
 {
-	struct list_head *elem_all;
+	const struct btrfsic_block *b_all;
 
 	BUG_ON(NULL == state);
 
 	printk(KERN_INFO "all_blocks_list:\n");
-	list_for_each(elem_all, &state->all_blocks_list) {
-		const struct btrfsic_block *const b_all =
-		    list_entry(elem_all, struct btrfsic_block,
-			       all_blocks_node);
-		struct list_head *elem_ref_to;
-		struct list_head *elem_ref_from;
+	list_for_each_entry(b_all, &state->all_blocks_list, all_blocks_node) {
+		const struct btrfsic_block_link *l;
 
 		printk(KERN_INFO "%c-block @%llu (%s/%llu/%d)\n",
 		       btrfsic_get_block_type(state, b_all),
 		       b_all->logical_bytenr, b_all->dev_state->name,
 		       b_all->dev_bytenr, b_all->mirror_num);
 
-		list_for_each(elem_ref_to, &b_all->ref_to_list) {
-			const struct btrfsic_block_link *const l =
-			    list_entry(elem_ref_to,
-				       struct btrfsic_block_link,
-				       node_ref_to);
-
+		list_for_each_entry(l, &b_all->ref_to_list, node_ref_to) {
 			printk(KERN_INFO " %c @%llu (%s/%llu/%d)"
 			       " refers %u* to"
 			       " %c @%llu (%s/%llu/%d)\n",
@@ -1757,12 +1738,7 @@ static void btrfsic_dump_database(struct btrfsic_state *state)
 			       l->block_ref_to->mirror_num);
 		}
 
-		list_for_each(elem_ref_from, &b_all->ref_from_list) {
-			const struct btrfsic_block_link *const l =
-			    list_entry(elem_ref_from,
-				       struct btrfsic_block_link,
-				       node_ref_from);
-
+		list_for_each_entry(l, &b_all->ref_from_list, node_ref_from) {
 			printk(KERN_INFO " %c @%llu (%s/%llu/%d)"
 			       " is ref %u* from"
 			       " %c @%llu (%s/%llu/%d)\n",
@@ -1793,9 +1769,9 @@ static int btrfsic_test_for_metadata(struct btrfsic_state *state,
 	u32 crc = ~(u32)0;
 	unsigned int i;
 
-	if (num_pages * PAGE_CACHE_SIZE < state->metablock_size)
+	if (num_pages * PAGE_SIZE < state->metablock_size)
 		return 1; /* not metadata */
-	num_pages = state->metablock_size >> PAGE_CACHE_SHIFT;
+	num_pages = state->metablock_size >> PAGE_SHIFT;
 	h = (struct btrfs_header *)datav[0];
 
 	if (memcmp(h->fsid, state->root->fs_info->fsid, BTRFS_UUID_SIZE))
@@ -1803,8 +1779,8 @@ static int btrfsic_test_for_metadata(struct btrfsic_state *state,
 
 	for (i = 0; i < num_pages; i++) {
 		u8 *data = i ? datav[i] : (datav[i] + BTRFS_CSUM_SIZE);
-		size_t sublen = i ? PAGE_CACHE_SIZE :
-				    (PAGE_CACHE_SIZE - BTRFS_CSUM_SIZE);
+		size_t sublen = i ? PAGE_SIZE :
+				    (PAGE_SIZE - BTRFS_CSUM_SIZE);
 
 		crc = btrfs_crc32c(crc, data, sublen);
 	}
@@ -1845,20 +1821,19 @@ again:
 					       &state->block_hashtable);
 	if (NULL != block) {
 		u64 bytenr = 0;
-		struct list_head *elem_ref_to;
-		struct list_head *tmp_ref_to;
+		struct btrfsic_block_link *l, *tmp;
 
 		if (block->is_superblock) {
 			bytenr = btrfs_super_bytenr((struct btrfs_super_block *)
 						    mapped_datav[0]);
-			if (num_pages * PAGE_CACHE_SIZE <
+			if (num_pages * PAGE_SIZE <
 			    BTRFS_SUPER_INFO_SIZE) {
 				printk(KERN_INFO
 				       "btrfsic: cannot work with too short bios!\n");
 				return;
 			}
 			is_metadata = 1;
-			BUG_ON(BTRFS_SUPER_INFO_SIZE & (PAGE_CACHE_SIZE - 1));
+			BUG_ON(BTRFS_SUPER_INFO_SIZE & (PAGE_SIZE - 1));
 			processed_len = BTRFS_SUPER_INFO_SIZE;
 			if (state->print_mask &
 			    BTRFSIC_PRINT_MASK_TREE_BEFORE_SB_WRITE) {
@@ -1869,7 +1844,7 @@ again:
 		}
 		if (is_metadata) {
 			if (!block->is_superblock) {
-				if (num_pages * PAGE_CACHE_SIZE <
+				if (num_pages * PAGE_SIZE <
 				    state->metablock_size) {
 					printk(KERN_INFO
 					       "btrfsic: cannot work with too short bios!\n");
@@ -1905,7 +1880,7 @@ again:
 			}
 			block->logical_bytenr = bytenr;
 		} else {
-			if (num_pages * PAGE_CACHE_SIZE <
+			if (num_pages * PAGE_SIZE <
 			    state->datablock_size) {
 				printk(KERN_INFO
 				       "btrfsic: cannot work with too short bios!\n");
@@ -1967,13 +1942,8 @@ again:
 		 * because it still carries valueable information
 		 * like whether it was ever written and IO completed.
 		 */
-		list_for_each_safe(elem_ref_to, tmp_ref_to,
-				   &block->ref_to_list) {
-			struct btrfsic_block_link *const l =
-			    list_entry(elem_ref_to,
-				       struct btrfsic_block_link,
-				       node_ref_to);
-
+		list_for_each_entry_safe(l, tmp, &block->ref_to_list,
+					 node_ref_to) {
 			if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE)
 				btrfsic_print_rem_link(state, l);
 			l->ref_cnt--;
@@ -2043,7 +2013,7 @@ again:
 			block->logical_bytenr = bytenr;
 			block->is_metadata = 1;
 			if (block->is_superblock) {
-				BUG_ON(PAGE_CACHE_SIZE !=
+				BUG_ON(PAGE_SIZE !=
 				       BTRFS_SUPER_INFO_SIZE);
 				ret = btrfsic_process_written_superblock(
 						state,
@@ -2202,8 +2172,8 @@ again:
 continue_loop:
 	BUG_ON(!processed_len);
 	dev_bytenr += processed_len;
-	mapped_datav += processed_len >> PAGE_CACHE_SHIFT;
-	num_pages -= processed_len >> PAGE_CACHE_SHIFT;
+	mapped_datav += processed_len >> PAGE_SHIFT;
+	num_pages -= processed_len >> PAGE_SHIFT;
 	goto again;
 }
 
@@ -2436,7 +2406,7 @@ static int btrfsic_check_all_ref_blocks(struct btrfsic_state *state,
 					struct btrfsic_block *const block,
 					int recursion_level)
 {
-	struct list_head *elem_ref_to;
+	const struct btrfsic_block_link *l;
 	int ret = 0;
 
 	if (recursion_level >= 3 + BTRFS_MAX_LEVEL) {
@@ -2464,11 +2434,7 @@ static int btrfsic_check_all_ref_blocks(struct btrfsic_state *state,
 	 * This algorithm is recursive because the amount of used stack
 	 * space is very small and the max recursion depth is limited.
 	 */
-	list_for_each(elem_ref_to, &block->ref_to_list) {
-		const struct btrfsic_block_link *const l =
-		    list_entry(elem_ref_to, struct btrfsic_block_link,
-			       node_ref_to);
-
+	list_for_each_entry(l, &block->ref_to_list, node_ref_to) {
 		if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE)
 			printk(KERN_INFO
 			       "rl=%d, %c @%llu (%s/%llu/%d)"
@@ -2561,7 +2527,7 @@ static int btrfsic_is_block_ref_by_superblock(
 		const struct btrfsic_block *block,
 		int recursion_level)
 {
-	struct list_head *elem_ref_from;
+	const struct btrfsic_block_link *l;
 
 	if (recursion_level >= 3 + BTRFS_MAX_LEVEL) {
 		/* refer to comment at "abort cyclic linkage (case 1)" */
@@ -2576,11 +2542,7 @@ static int btrfsic_is_block_ref_by_superblock(
 	 * This algorithm is recursive because the amount of used stack space
 	 * is very small and the max recursion depth is limited.
 	 */
-	list_for_each(elem_ref_from, &block->ref_from_list) {
-		const struct btrfsic_block_link *const l =
-		    list_entry(elem_ref_from, struct btrfsic_block_link,
-			       node_ref_from);
-
+	list_for_each_entry(l, &block->ref_from_list, node_ref_from) {
 		if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE)
 			printk(KERN_INFO
 			       "rl=%d, %c @%llu (%s/%llu/%d)"
@@ -2669,7 +2631,7 @@ static void btrfsic_dump_tree_sub(const struct btrfsic_state *state,
 				  const struct btrfsic_block *block,
 				  int indent_level)
 {
-	struct list_head *elem_ref_to;
+	const struct btrfsic_block_link *l;
 	int indent_add;
 	static char buf[80];
 	int cursor_position;
@@ -2704,11 +2666,7 @@ static void btrfsic_dump_tree_sub(const struct btrfsic_state *state,
 	}
 
 	cursor_position = indent_level;
-	list_for_each(elem_ref_to, &block->ref_to_list) {
-		const struct btrfsic_block_link *const l =
-		    list_entry(elem_ref_to, struct btrfsic_block_link,
-			       node_ref_to);
-
+	list_for_each_entry(l, &block->ref_to_list, node_ref_to) {
 		while (cursor_position < indent_level) {
 			printk(" ");
 			cursor_position++;
@@ -2996,7 +2954,7 @@ static void __btrfsic_submit_bio(int rw, struct bio *bio)
 			goto leave;
 		cur_bytenr = dev_bytenr;
 		for (i = 0; i < bio->bi_vcnt; i++) {
-			BUG_ON(bio->bi_io_vec[i].bv_len != PAGE_CACHE_SIZE);
+			BUG_ON(bio->bi_io_vec[i].bv_len != PAGE_SIZE);
 			mapped_datav[i] = kmap(bio->bi_io_vec[i].bv_page);
 			if (!mapped_datav[i]) {
 				while (i > 0) {
@@ -3079,16 +3037,16 @@ int btrfsic_mount(struct btrfs_root *root,
 	struct list_head *dev_head = &fs_devices->devices;
 	struct btrfs_device *device;
 
-	if (root->nodesize & ((u64)PAGE_CACHE_SIZE - 1)) {
+	if (root->nodesize & ((u64)PAGE_SIZE - 1)) {
 		printk(KERN_INFO
-		       "btrfsic: cannot handle nodesize %d not being a multiple of PAGE_CACHE_SIZE %ld!\n",
-		       root->nodesize, PAGE_CACHE_SIZE);
+		       "btrfsic: cannot handle nodesize %d not being a multiple of PAGE_SIZE %ld!\n",
+		       root->nodesize, PAGE_SIZE);
 		return -1;
 	}
-	if (root->sectorsize & ((u64)PAGE_CACHE_SIZE - 1)) {
+	if (root->sectorsize & ((u64)PAGE_SIZE - 1)) {
 		printk(KERN_INFO
-		       "btrfsic: cannot handle sectorsize %d not being a multiple of PAGE_CACHE_SIZE %ld!\n",
-		       root->sectorsize, PAGE_CACHE_SIZE);
+		       "btrfsic: cannot handle sectorsize %d not being a multiple of PAGE_SIZE %ld!\n",
+		       root->sectorsize, PAGE_SIZE);
 		return -1;
 	}
 	state = kzalloc(sizeof(*state), GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
@@ -3120,7 +3078,7 @@ int btrfsic_mount(struct btrfs_root *root,
 
 	list_for_each_entry(device, dev_head, dev_list) {
 		struct btrfsic_dev_state *ds;
-		char *p;
+		const char *p;
 
 		if (!device->bdev || !device->name)
 			continue;
@@ -3136,11 +3094,7 @@ int btrfsic_mount(struct btrfs_root *root,
 		ds->state = state;
 		bdevname(ds->bdev, ds->name);
 		ds->name[BDEVNAME_SIZE - 1] = '\0';
-		for (p = ds->name; *p != '\0'; p++);
-		while (p > ds->name && *p != '/')
-			p--;
-		if (*p == '/')
-			p++;
+		p = kbasename(ds->name);
 		strlcpy(ds->name, p, sizeof(ds->name));
 		btrfsic_dev_state_hashtable_add(ds,
 						&btrfsic_dev_state_hashtable);
@@ -3165,8 +3119,7 @@ int btrfsic_mount(struct btrfs_root *root,
 void btrfsic_unmount(struct btrfs_root *root,
 		     struct btrfs_fs_devices *fs_devices)
 {
-	struct list_head *elem_all;
-	struct list_head *tmp_all;
+	struct btrfsic_block *b_all, *tmp_all;
 	struct btrfsic_state *state;
 	struct list_head *dev_head = &fs_devices->devices;
 	struct btrfs_device *device;
@@ -3206,20 +3159,12 @@ void btrfsic_unmount(struct btrfs_root *root,
 	 * just free all memory that was allocated dynamically.
 	 * Free the blocks and the block_links.
 	 */
-	list_for_each_safe(elem_all, tmp_all, &state->all_blocks_list) {
-		struct btrfsic_block *const b_all =
-		    list_entry(elem_all, struct btrfsic_block,
-			       all_blocks_node);
-		struct list_head *elem_ref_to;
-		struct list_head *tmp_ref_to;
-
-		list_for_each_safe(elem_ref_to, tmp_ref_to,
-				   &b_all->ref_to_list) {
-			struct btrfsic_block_link *const l =
-			    list_entry(elem_ref_to,
-				       struct btrfsic_block_link,
-				       node_ref_to);
+	list_for_each_entry_safe(b_all, tmp_all, &state->all_blocks_list,
+				 all_blocks_node) {
+		struct btrfsic_block_link *l, *tmp;
 
+		list_for_each_entry_safe(l, tmp, &b_all->ref_to_list,
+					 node_ref_to) {
 			if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE)
 				btrfsic_print_rem_link(state, l);
 
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 97b049ad0594..ff61a41ac90b 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -119,7 +119,7 @@ static int check_compressed_csum(struct inode *inode,
 		csum = ~(u32)0;
 
 		kaddr = kmap_atomic(page);
-		csum = btrfs_csum_data(kaddr, csum, PAGE_CACHE_SIZE);
+		csum = btrfs_csum_data(kaddr, csum, PAGE_SIZE);
 		btrfs_csum_final(csum, (char *)&csum);
 		kunmap_atomic(kaddr);
 
@@ -190,7 +190,7 @@ csum_failed:
 	for (index = 0; index < cb->nr_pages; index++) {
 		page = cb->compressed_pages[index];
 		page->mapping = NULL;
-		page_cache_release(page);
+		put_page(page);
 	}
 
 	/* do io completion on the original bio */
@@ -224,8 +224,8 @@ out:
 static noinline void end_compressed_writeback(struct inode *inode,
 					      const struct compressed_bio *cb)
 {
-	unsigned long index = cb->start >> PAGE_CACHE_SHIFT;
-	unsigned long end_index = (cb->start + cb->len - 1) >> PAGE_CACHE_SHIFT;
+	unsigned long index = cb->start >> PAGE_SHIFT;
+	unsigned long end_index = (cb->start + cb->len - 1) >> PAGE_SHIFT;
 	struct page *pages[16];
 	unsigned long nr_pages = end_index - index + 1;
 	int i;
@@ -247,7 +247,7 @@ static noinline void end_compressed_writeback(struct inode *inode,
 			if (cb->errors)
 				SetPageError(pages[i]);
 			end_page_writeback(pages[i]);
-			page_cache_release(pages[i]);
+			put_page(pages[i]);
 		}
 		nr_pages -= ret;
 		index += ret;
@@ -304,7 +304,7 @@ static void end_compressed_bio_write(struct bio *bio)
 	for (index = 0; index < cb->nr_pages; index++) {
 		page = cb->compressed_pages[index];
 		page->mapping = NULL;
-		page_cache_release(page);
+		put_page(page);
 	}
 
 	/* finally free the cb struct */
@@ -341,7 +341,7 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 	int ret;
 	int skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
 
-	WARN_ON(start & ((u64)PAGE_CACHE_SIZE - 1));
+	WARN_ON(start & ((u64)PAGE_SIZE - 1));
 	cb = kmalloc(compressed_bio_size(root, compressed_len), GFP_NOFS);
 	if (!cb)
 		return -ENOMEM;
@@ -374,14 +374,14 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 		page->mapping = inode->i_mapping;
 		if (bio->bi_iter.bi_size)
 			ret = io_tree->ops->merge_bio_hook(WRITE, page, 0,
-							   PAGE_CACHE_SIZE,
+							   PAGE_SIZE,
 							   bio, 0);
 		else
 			ret = 0;
 
 		page->mapping = NULL;
-		if (ret || bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) <
-		    PAGE_CACHE_SIZE) {
+		if (ret || bio_add_page(bio, page, PAGE_SIZE, 0) <
+		    PAGE_SIZE) {
 			bio_get(bio);
 
 			/*
@@ -410,15 +410,15 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 			BUG_ON(!bio);
 			bio->bi_private = cb;
 			bio->bi_end_io = end_compressed_bio_write;
-			bio_add_page(bio, page, PAGE_CACHE_SIZE, 0);
+			bio_add_page(bio, page, PAGE_SIZE, 0);
 		}
-		if (bytes_left < PAGE_CACHE_SIZE) {
+		if (bytes_left < PAGE_SIZE) {
 			btrfs_info(BTRFS_I(inode)->root->fs_info,
 					"bytes left %lu compress len %lu nr %lu",
 			       bytes_left, cb->compressed_len, cb->nr_pages);
 		}
-		bytes_left -= PAGE_CACHE_SIZE;
-		first_byte += PAGE_CACHE_SIZE;
+		bytes_left -= PAGE_SIZE;
+		first_byte += PAGE_SIZE;
 		cond_resched();
 	}
 	bio_get(bio);
@@ -457,17 +457,17 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 	int misses = 0;
 
 	page = cb->orig_bio->bi_io_vec[cb->orig_bio->bi_vcnt - 1].bv_page;
-	last_offset = (page_offset(page) + PAGE_CACHE_SIZE);
+	last_offset = (page_offset(page) + PAGE_SIZE);
 	em_tree = &BTRFS_I(inode)->extent_tree;
 	tree = &BTRFS_I(inode)->io_tree;
 
 	if (isize == 0)
 		return 0;
 
-	end_index = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT;
+	end_index = (i_size_read(inode) - 1) >> PAGE_SHIFT;
 
 	while (last_offset < compressed_end) {
-		pg_index = last_offset >> PAGE_CACHE_SHIFT;
+		pg_index = last_offset >> PAGE_SHIFT;
 
 		if (pg_index > end_index)
 			break;
@@ -482,18 +482,17 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 			goto next;
 		}
 
-		page = __page_cache_alloc(mapping_gfp_mask(mapping) &
-								~__GFP_FS);
+		page = __page_cache_alloc(mapping_gfp_constraint(mapping,
+								 ~__GFP_FS));
 		if (!page)
 			break;
 
-		if (add_to_page_cache_lru(page, mapping, pg_index,
-								GFP_NOFS)) {
-			page_cache_release(page);
+		if (add_to_page_cache_lru(page, mapping, pg_index, GFP_NOFS)) {
+			put_page(page);
 			goto next;
 		}
 
-		end = last_offset + PAGE_CACHE_SIZE - 1;
+		end = last_offset + PAGE_SIZE - 1;
 		/*
 		 * at this point, we have a locked page in the page cache
 		 * for these bytes in the file.  But, we have to make
@@ -503,27 +502,27 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 		lock_extent(tree, last_offset, end);
 		read_lock(&em_tree->lock);
 		em = lookup_extent_mapping(em_tree, last_offset,
-					   PAGE_CACHE_SIZE);
+					   PAGE_SIZE);
 		read_unlock(&em_tree->lock);
 
 		if (!em || last_offset < em->start ||
-		    (last_offset + PAGE_CACHE_SIZE > extent_map_end(em)) ||
+		    (last_offset + PAGE_SIZE > extent_map_end(em)) ||
 		    (em->block_start >> 9) != cb->orig_bio->bi_iter.bi_sector) {
 			free_extent_map(em);
 			unlock_extent(tree, last_offset, end);
 			unlock_page(page);
-			page_cache_release(page);
+			put_page(page);
 			break;
 		}
 		free_extent_map(em);
 
 		if (page->index == end_index) {
 			char *userpage;
-			size_t zero_offset = isize & (PAGE_CACHE_SIZE - 1);
+			size_t zero_offset = isize & (PAGE_SIZE - 1);
 
 			if (zero_offset) {
 				int zeros;
-				zeros = PAGE_CACHE_SIZE - zero_offset;
+				zeros = PAGE_SIZE - zero_offset;
 				userpage = kmap_atomic(page);
 				memset(userpage + zero_offset, 0, zeros);
 				flush_dcache_page(page);
@@ -532,19 +531,19 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 		}
 
 		ret = bio_add_page(cb->orig_bio, page,
-				   PAGE_CACHE_SIZE, 0);
+				   PAGE_SIZE, 0);
 
-		if (ret == PAGE_CACHE_SIZE) {
+		if (ret == PAGE_SIZE) {
 			nr_pages++;
-			page_cache_release(page);
+			put_page(page);
 		} else {
 			unlock_extent(tree, last_offset, end);
 			unlock_page(page);
-			page_cache_release(page);
+			put_page(page);
 			break;
 		}
 next:
-		last_offset += PAGE_CACHE_SIZE;
+		last_offset += PAGE_SIZE;
 	}
 	return 0;
 }
@@ -568,7 +567,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	struct extent_map_tree *em_tree;
 	struct compressed_bio *cb;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	unsigned long uncompressed_len = bio->bi_vcnt * PAGE_CACHE_SIZE;
+	unsigned long uncompressed_len = bio->bi_vcnt * PAGE_SIZE;
 	unsigned long compressed_len;
 	unsigned long nr_pages;
 	unsigned long pg_index;
@@ -590,7 +589,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	read_lock(&em_tree->lock);
 	em = lookup_extent_mapping(em_tree,
 				   page_offset(bio->bi_io_vec->bv_page),
-				   PAGE_CACHE_SIZE);
+				   PAGE_SIZE);
 	read_unlock(&em_tree->lock);
 	if (!em)
 		return -EIO;
@@ -618,7 +617,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	cb->compress_type = extent_compress_type(bio_flags);
 	cb->orig_bio = bio;
 
-	nr_pages = DIV_ROUND_UP(compressed_len, PAGE_CACHE_SIZE);
+	nr_pages = DIV_ROUND_UP(compressed_len, PAGE_SIZE);
 	cb->compressed_pages = kcalloc(nr_pages, sizeof(struct page *),
 				       GFP_NOFS);
 	if (!cb->compressed_pages)
@@ -638,14 +637,10 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	faili = nr_pages - 1;
 	cb->nr_pages = nr_pages;
 
-	/* In the parent-locked case, we only locked the range we are
-	 * interested in.  In all other cases, we can opportunistically
-	 * cache decompressed data that goes beyond the requested range. */
-	if (!(bio_flags & EXTENT_BIO_PARENT_LOCKED))
-		add_ra_bio_pages(inode, em_start + em_len, cb);
+	add_ra_bio_pages(inode, em_start + em_len, cb);
 
 	/* include any pages we added in add_ra-bio_pages */
-	uncompressed_len = bio->bi_vcnt * PAGE_CACHE_SIZE;
+	uncompressed_len = bio->bi_vcnt * PAGE_SIZE;
 	cb->len = uncompressed_len;
 
 	comp_bio = compressed_bio_alloc(bdev, cur_disk_byte, GFP_NOFS);
@@ -658,18 +653,18 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	for (pg_index = 0; pg_index < nr_pages; pg_index++) {
 		page = cb->compressed_pages[pg_index];
 		page->mapping = inode->i_mapping;
-		page->index = em_start >> PAGE_CACHE_SHIFT;
+		page->index = em_start >> PAGE_SHIFT;
 
 		if (comp_bio->bi_iter.bi_size)
 			ret = tree->ops->merge_bio_hook(READ, page, 0,
-							PAGE_CACHE_SIZE,
+							PAGE_SIZE,
 							comp_bio, 0);
 		else
 			ret = 0;
 
 		page->mapping = NULL;
-		if (ret || bio_add_page(comp_bio, page, PAGE_CACHE_SIZE, 0) <
-		    PAGE_CACHE_SIZE) {
+		if (ret || bio_add_page(comp_bio, page, PAGE_SIZE, 0) <
+		    PAGE_SIZE) {
 			bio_get(comp_bio);
 
 			ret = btrfs_bio_wq_end_io(root->fs_info, comp_bio,
@@ -707,9 +702,9 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 			comp_bio->bi_private = cb;
 			comp_bio->bi_end_io = end_compressed_bio_read;
 
-			bio_add_page(comp_bio, page, PAGE_CACHE_SIZE, 0);
+			bio_add_page(comp_bio, page, PAGE_SIZE, 0);
 		}
-		cur_disk_byte += PAGE_CACHE_SIZE;
+		cur_disk_byte += PAGE_SIZE;
 	}
 	bio_get(comp_bio);
 
@@ -1018,8 +1013,8 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
 
 	/* copy bytes from the working buffer into the pages */
 	while (working_bytes > 0) {
-		bytes = min(PAGE_CACHE_SIZE - *pg_offset,
-			    PAGE_CACHE_SIZE - buf_offset);
+		bytes = min(PAGE_SIZE - *pg_offset,
+			    PAGE_SIZE - buf_offset);
 		bytes = min(bytes, working_bytes);
 		kaddr = kmap_atomic(page_out);
 		memcpy(kaddr + *pg_offset, buf + buf_offset, bytes);
@@ -1032,7 +1027,7 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
 		current_buf_start += bytes;
 
 		/* check if we need to pick another page */
-		if (*pg_offset == PAGE_CACHE_SIZE) {
+		if (*pg_offset == PAGE_SIZE) {
 			(*pg_index)++;
 			if (*pg_index >= vcnt)
 				return 0;
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 13a4dc0436c9..f49d8b8c0f00 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -48,6 +48,15 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 void btrfs_clear_biovec_end(struct bio_vec *bvec, int vcnt,
 				   unsigned long pg_index,
 				   unsigned long pg_offset);
+
+enum btrfs_compression_type {
+	BTRFS_COMPRESS_NONE  = 0,
+	BTRFS_COMPRESS_ZLIB  = 1,
+	BTRFS_COMPRESS_LZO   = 2,
+	BTRFS_COMPRESS_TYPES = 2,
+	BTRFS_COMPRESS_LAST  = 3,
+};
+
 struct btrfs_compress_op {
 	struct list_head *(*alloc_workspace)(void);
 
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 5b8e235c4b6d..ec7928a27aaa 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -19,6 +19,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/rbtree.h>
+#include <linux/vmalloc.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
@@ -311,7 +312,7 @@ struct tree_mod_root {
 
 struct tree_mod_elem {
 	struct rb_node node;
-	u64 index;		/* shifted logical */
+	u64 logical;
 	u64 seq;
 	enum mod_log_op op;
 
@@ -435,11 +436,11 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
 
 /*
  * key order of the log:
- *       index -> sequence
+ *       node/leaf start address -> sequence
  *
- * the index is the shifted logical of the *new* root node for root replace
- * operations, or the shifted logical of the affected block for all other
- * operations.
+ * The 'start address' is the logical address of the *new* root node
+ * for root replace operations, or the logical address of the affected
+ * block for all other operations.
  *
  * Note: must be called with write lock (tree_mod_log_write_lock).
  */
@@ -460,9 +461,9 @@ __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm)
 	while (*new) {
 		cur = container_of(*new, struct tree_mod_elem, node);
 		parent = *new;
-		if (cur->index < tm->index)
+		if (cur->logical < tm->logical)
 			new = &((*new)->rb_left);
-		else if (cur->index > tm->index)
+		else if (cur->logical > tm->logical)
 			new = &((*new)->rb_right);
 		else if (cur->seq < tm->seq)
 			new = &((*new)->rb_left);
@@ -523,7 +524,7 @@ alloc_tree_mod_elem(struct extent_buffer *eb, int slot,
 	if (!tm)
 		return NULL;
 
-	tm->index = eb->start >> PAGE_CACHE_SHIFT;
+	tm->logical = eb->start;
 	if (op != MOD_LOG_KEY_ADD) {
 		btrfs_node_key(eb, &tm->key, slot);
 		tm->blockptr = btrfs_node_blockptr(eb, slot);
@@ -588,7 +589,7 @@ tree_mod_log_insert_move(struct btrfs_fs_info *fs_info,
 		goto free_tms;
 	}
 
-	tm->index = eb->start >> PAGE_CACHE_SHIFT;
+	tm->logical = eb->start;
 	tm->slot = src_slot;
 	tm->move.dst_slot = dst_slot;
 	tm->move.nr_items = nr_items;
@@ -699,7 +700,7 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info,
 		goto free_tms;
 	}
 
-	tm->index = new_root->start >> PAGE_CACHE_SHIFT;
+	tm->logical = new_root->start;
 	tm->old_root.logical = old_root->start;
 	tm->old_root.level = btrfs_header_level(old_root);
 	tm->generation = btrfs_header_generation(old_root);
@@ -739,16 +740,15 @@ __tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq,
 	struct rb_node *node;
 	struct tree_mod_elem *cur = NULL;
 	struct tree_mod_elem *found = NULL;
-	u64 index = start >> PAGE_CACHE_SHIFT;
 
 	tree_mod_log_read_lock(fs_info);
 	tm_root = &fs_info->tree_mod_log;
 	node = tm_root->rb_node;
 	while (node) {
 		cur = container_of(node, struct tree_mod_elem, node);
-		if (cur->index < index) {
+		if (cur->logical < start) {
 			node = node->rb_left;
-		} else if (cur->index > index) {
+		} else if (cur->logical > start) {
 			node = node->rb_right;
 		} else if (cur->seq < min_seq) {
 			node = node->rb_left;
@@ -1230,9 +1230,10 @@ __tree_mod_log_oldest_root(struct btrfs_fs_info *fs_info,
 		return NULL;
 
 	/*
-	 * the very last operation that's logged for a root is the replacement
-	 * operation (if it is replaced at all). this has the index of the *new*
-	 * root, making it the very first operation that's logged for this root.
+	 * the very last operation that's logged for a root is the
+	 * replacement operation (if it is replaced at all). this has
+	 * the logical address of the *new* root, making it the very
+	 * first operation that's logged for this root.
 	 */
 	while (1) {
 		tm = tree_mod_log_search_oldest(fs_info, root_logical,
@@ -1336,7 +1337,7 @@ __tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb,
 		if (!next)
 			break;
 		tm = container_of(next, struct tree_mod_elem, node);
-		if (tm->index != first_tm->index)
+		if (tm->logical != first_tm->logical)
 			break;
 	}
 	tree_mod_log_read_unlock(fs_info);
@@ -1555,7 +1556,7 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
 		return 0;
 	}
 
-	search_start = buf->start & ~((u64)(1024 * 1024 * 1024) - 1);
+	search_start = buf->start & ~((u64)SZ_1G - 1);
 
 	if (parent)
 		btrfs_set_lock_blocking(parent);
@@ -2248,7 +2249,6 @@ static void reada_for_search(struct btrfs_root *root,
 	u64 target;
 	u64 nread = 0;
 	u64 gen;
-	int direction = path->reada;
 	struct extent_buffer *eb;
 	u32 nr;
 	u32 blocksize;
@@ -2276,16 +2276,16 @@ static void reada_for_search(struct btrfs_root *root,
 	nr = slot;
 
 	while (1) {
-		if (direction < 0) {
+		if (path->reada == READA_BACK) {
 			if (nr == 0)
 				break;
 			nr--;
-		} else if (direction > 0) {
+		} else if (path->reada == READA_FORWARD) {
 			nr++;
 			if (nr >= nritems)
 				break;
 		}
-		if (path->reada < 0 && objectid) {
+		if (path->reada == READA_BACK && objectid) {
 			btrfs_node_key(node, &disk_key, nr);
 			if (btrfs_disk_key_objectid(&disk_key) != objectid)
 				break;
@@ -2493,7 +2493,7 @@ read_block_for_search(struct btrfs_trans_handle *trans,
 	btrfs_set_path_blocking(p);
 
 	free_extent_buffer(tmp);
-	if (p->reada)
+	if (p->reada != READA_NONE)
 		reada_for_search(root, p, level, slot, key->objectid);
 
 	btrfs_release_path(p);
@@ -5362,10 +5362,13 @@ int btrfs_compare_trees(struct btrfs_root *left_root,
 		goto out;
 	}
 
-	tmp_buf = kmalloc(left_root->nodesize, GFP_NOFS);
+	tmp_buf = kmalloc(left_root->nodesize, GFP_KERNEL | __GFP_NOWARN);
 	if (!tmp_buf) {
-		ret = -ENOMEM;
-		goto out;
+		tmp_buf = vmalloc(left_root->nodesize);
+		if (!tmp_buf) {
+			ret = -ENOMEM;
+			goto out;
+		}
 	}
 
 	left_path->search_commit_root = 1;
@@ -5566,7 +5569,7 @@ int btrfs_compare_trees(struct btrfs_root *left_root,
 out:
 	btrfs_free_path(left_path);
 	btrfs_free_path(right_path);
-	kfree(tmp_buf);
+	kvfree(tmp_buf);
 	return ret;
 }
 
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index a2e73f6053a8..84a6a5b3384a 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -35,6 +35,7 @@
 #include <linux/btrfs.h>
 #include <linux/workqueue.h>
 #include <linux/security.h>
+#include <linux/sizes.h>
 #include "extent_io.h"
 #include "extent_map.h"
 #include "async-thread.h"
@@ -96,6 +97,12 @@ struct btrfs_ordered_sum;
 /* for storing items that use the BTRFS_UUID_KEY* types */
 #define BTRFS_UUID_TREE_OBJECTID 9ULL
 
+/* tracks free space in block groups. */
+#define BTRFS_FREE_SPACE_TREE_OBJECTID 10ULL
+
+/* device stats in the device tree */
+#define BTRFS_DEV_STATS_OBJECTID 0ULL
+
 /* for storing balance parameters in the root tree */
 #define BTRFS_BALANCE_OBJECTID -4ULL
 
@@ -174,7 +181,7 @@ struct btrfs_ordered_sum;
 /* csum types */
 #define BTRFS_CSUM_TYPE_CRC32	0
 
-static int btrfs_csum_sizes[] = { 4 };
+static const int btrfs_csum_sizes[] = { 4 };
 
 /* four bytes for CRC32 */
 #define BTRFS_EMPTY_DIR_SIZE 0
@@ -196,9 +203,9 @@ static int btrfs_csum_sizes[] = { 4 };
 /* ioprio of readahead is set to idle */
 #define BTRFS_IOPRIO_READA (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0))
 
-#define BTRFS_DIRTY_METADATA_THRESH	(32 * 1024 * 1024)
+#define BTRFS_DIRTY_METADATA_THRESH	SZ_32M
 
-#define BTRFS_MAX_EXTENT_SIZE (128 * 1024 * 1024)
+#define BTRFS_MAX_EXTENT_SIZE SZ_128M
 
 /*
  * The key defines the order in the tree, and so it also defines (optimal)
@@ -500,6 +507,8 @@ struct btrfs_super_block {
  * Compat flags that we support.  If any incompat flags are set other than the
  * ones specified below then we will fail to mount
  */
+#define BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE	(1ULL << 0)
+
 #define BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF	(1ULL << 0)
 #define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL	(1ULL << 1)
 #define BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS	(1ULL << 2)
@@ -526,7 +535,10 @@ struct btrfs_super_block {
 #define BTRFS_FEATURE_COMPAT_SUPP		0ULL
 #define BTRFS_FEATURE_COMPAT_SAFE_SET		0ULL
 #define BTRFS_FEATURE_COMPAT_SAFE_CLEAR		0ULL
-#define BTRFS_FEATURE_COMPAT_RO_SUPP		0ULL
+
+#define BTRFS_FEATURE_COMPAT_RO_SUPP			\
+	(BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE)
+
 #define BTRFS_FEATURE_COMPAT_RO_SAFE_SET	0ULL
 #define BTRFS_FEATURE_COMPAT_RO_SAFE_CLEAR	0ULL
 
@@ -590,14 +602,15 @@ struct btrfs_node {
  * The slots array records the index of the item or block pointer
  * used while walking the tree.
  */
+enum { READA_NONE = 0, READA_BACK, READA_FORWARD };
 struct btrfs_path {
 	struct extent_buffer *nodes[BTRFS_MAX_LEVEL];
 	int slots[BTRFS_MAX_LEVEL];
 	/* if there is real range locking, this locks field will change */
-	int locks[BTRFS_MAX_LEVEL];
-	int reada;
+	u8 locks[BTRFS_MAX_LEVEL];
+	u8 reada;
 	/* keep some upper locks as we walk down */
-	int lowest_level;
+	u8 lowest_level;
 
 	/*
 	 * set by btrfs_split_item, tells search_slot to keep all locks
@@ -705,14 +718,6 @@ struct btrfs_timespec {
 	__le32 nsec;
 } __attribute__ ((__packed__));
 
-enum btrfs_compression_type {
-	BTRFS_COMPRESS_NONE  = 0,
-	BTRFS_COMPRESS_ZLIB  = 1,
-	BTRFS_COMPRESS_LZO   = 2,
-	BTRFS_COMPRESS_TYPES = 2,
-	BTRFS_COMPRESS_LAST  = 3,
-};
-
 struct btrfs_inode_item {
 	/* nfs style generation number */
 	__le64 generation;
@@ -783,7 +788,7 @@ struct btrfs_root_item {
 
 	/*
 	 * This generation number is used to test if the new fields are valid
-	 * and up to date while reading the root item. Everytime the root item
+	 * and up to date while reading the root item. Every time the root item
 	 * is written out, the "generation" field is copied into this field. If
 	 * anyone ever mounted the fs with an older kernel, we will have
 	 * mismatching generation values here and thus must invalidate the
@@ -992,8 +997,10 @@ struct btrfs_dev_replace {
 	pid_t lock_owner;
 	atomic_t nesting_level;
 	struct mutex lock_finishing_cancel_unmount;
-	struct mutex lock_management_lock;
-	struct mutex lock;
+	rwlock_t lock;
+	atomic_t read_locks;
+	atomic_t blocking_readers;
+	wait_queue_head_t read_lock_wq;
 
 	struct btrfs_scrub_progress scrub_progress;
 };
@@ -1088,6 +1095,13 @@ struct btrfs_block_group_item {
 	__le64 flags;
 } __attribute__ ((__packed__));
 
+struct btrfs_free_space_info {
+	__le32 extent_count;
+	__le32 flags;
+} __attribute__ ((__packed__));
+
+#define BTRFS_FREE_SPACE_USING_BITMAPS (1ULL << 0)
+
 #define BTRFS_QGROUP_LEVEL_SHIFT		48
 static inline u64 btrfs_qgroup_level(u64 qgroupid)
 {
@@ -1205,10 +1219,10 @@ struct btrfs_space_info {
 	 * we've called update_block_group and dropped the bytes_used counter
 	 * and increased the bytes_pinned counter.  However this means that
 	 * bytes_pinned does not reflect the bytes that will be pinned once the
-	 * delayed refs are flushed, so this counter is inc'ed everytime we call
-	 * btrfs_free_extent so it is a realtime count of what will be freed
-	 * once the transaction is committed.  It will be zero'ed everytime the
-	 * transaction commits.
+	 * delayed refs are flushed, so this counter is inc'ed every time we
+	 * call btrfs_free_extent so it is a realtime count of what will be
+	 * freed once the transaction is committed.  It will be zero'ed every
+	 * time the transaction commits.
 	 */
 	struct percpu_counter total_bytes_pinned;
 
@@ -1296,6 +1310,9 @@ struct btrfs_caching_control {
 	atomic_t count;
 };
 
+/* Once caching_thread() finds this much free space, it will wake up waiters. */
+#define CACHING_CTL_WAKE_UP (1024 * 1024 * 2)
+
 struct btrfs_io_ctl {
 	void *cur, *orig;
 	struct page *page;
@@ -1321,8 +1338,20 @@ struct btrfs_block_group_cache {
 	u64 delalloc_bytes;
 	u64 bytes_super;
 	u64 flags;
-	u64 sectorsize;
 	u64 cache_generation;
+	u32 sectorsize;
+
+	/*
+	 * If the free space extent count exceeds this number, convert the block
+	 * group to bitmaps.
+	 */
+	u32 bitmap_high_thresh;
+
+	/*
+	 * If the free space extent count drops below this number, convert the
+	 * block group back to extents.
+	 */
+	u32 bitmap_low_thresh;
 
 	/*
 	 * It is just used for the delayed data space allocation because
@@ -1378,6 +1407,15 @@ struct btrfs_block_group_cache {
 	struct list_head io_list;
 
 	struct btrfs_io_ctl io_ctl;
+
+	/* Lock for free space tree operations. */
+	struct mutex free_space_lock;
+
+	/*
+	 * Does the block group need to be added to the free space tree?
+	 * Protected by free_space_lock.
+	 */
+	int needs_free_space;
 };
 
 /* delayed seq elem */
@@ -1429,6 +1467,7 @@ struct btrfs_fs_info {
 	struct btrfs_root *csum_root;
 	struct btrfs_root *quota_root;
 	struct btrfs_root *uuid_root;
+	struct btrfs_root *free_space_root;
 
 	/* the log root tree is a directory of all the other log roots */
 	struct btrfs_root *log_root_tree;
@@ -1572,7 +1611,7 @@ struct btrfs_fs_info {
 
 	spinlock_t delayed_iput_lock;
 	struct list_head delayed_iputs;
-	struct rw_semaphore delayed_iput_sem;
+	struct mutex cleaner_delayed_iput_mutex;
 
 	/* this protects tree_mod_seq_list */
 	spinlock_t tree_mod_seq_lock;
@@ -1780,6 +1819,9 @@ struct btrfs_fs_info {
 	spinlock_t reada_lock;
 	struct radix_tree_root reada_tree;
 
+	/* readahead works cnt */
+	atomic_t reada_works_cnt;
+
 	/* Extent buffer radix tree */
 	spinlock_t buffer_lock;
 	struct radix_tree_root buffer_radix;
@@ -1816,6 +1858,8 @@ struct btrfs_fs_info {
 	 * and will be latter freed. Protected by fs_info->chunk_mutex.
 	 */
 	struct list_head pinned_chunks;
+
+	int creating_free_space_tree;
 };
 
 struct btrfs_subvolume_writers {
@@ -2092,6 +2136,27 @@ struct btrfs_ioctl_defrag_range_args {
  */
 #define BTRFS_BLOCK_GROUP_ITEM_KEY 192
 
+/*
+ * Every block group is represented in the free space tree by a free space info
+ * item, which stores some accounting information. It is keyed on
+ * (block_group_start, FREE_SPACE_INFO, block_group_length).
+ */
+#define BTRFS_FREE_SPACE_INFO_KEY 198
+
+/*
+ * A free space extent tracks an extent of space that is free in a block group.
+ * It is keyed on (start, FREE_SPACE_EXTENT, length).
+ */
+#define BTRFS_FREE_SPACE_EXTENT_KEY 199
+
+/*
+ * When a block group becomes very fragmented, we convert it to use bitmaps
+ * instead of extents. A free space bitmap is keyed on
+ * (start, FREE_SPACE_BITMAP, length); the corresponding item is a bitmap with
+ * (length / sectorsize) bits.
+ */
+#define BTRFS_FREE_SPACE_BITMAP_KEY 200
+
 #define BTRFS_DEV_EXTENT_KEY	204
 #define BTRFS_DEV_ITEM_KEY	216
 #define BTRFS_CHUNK_ITEM_KEY	228
@@ -2120,13 +2185,43 @@ struct btrfs_ioctl_defrag_range_args {
  */
 #define BTRFS_QGROUP_RELATION_KEY       246
 
+/*
+ * Obsolete name, see BTRFS_TEMPORARY_ITEM_KEY.
+ */
 #define BTRFS_BALANCE_ITEM_KEY	248
 
 /*
- * Persistantly stores the io stats in the device tree.
- * One key for all stats, (0, BTRFS_DEV_STATS_KEY, devid).
+ * The key type for tree items that are stored persistently, but do not need to
+ * exist for extended period of time. The items can exist in any tree.
+ *
+ * [subtype, BTRFS_TEMPORARY_ITEM_KEY, data]
+ *
+ * Existing items:
+ *
+ * - balance status item
+ *   (BTRFS_BALANCE_OBJECTID, BTRFS_TEMPORARY_ITEM_KEY, 0)
  */
-#define BTRFS_DEV_STATS_KEY	249
+#define BTRFS_TEMPORARY_ITEM_KEY	248
+
+/*
+ * Obsolete name, see BTRFS_PERSISTENT_ITEM_KEY
+ */
+#define BTRFS_DEV_STATS_KEY		249
+
+/*
+ * The key type for tree items that are stored persistently and usually exist
+ * for a long period, eg. filesystem lifetime. The item kinds can be status
+ * information, stats or preference values. The item can exist in any tree.
+ *
+ * [subtype, BTRFS_PERSISTENT_ITEM_KEY, data]
+ *
+ * Existing items:
+ *
+ * - device statistics, store IO stats in the device tree, one key for all
+ *   stats
+ *   (BTRFS_DEV_STATS_OBJECTID, BTRFS_DEV_STATS_KEY, 0)
+ */
+#define BTRFS_PERSISTENT_ITEM_KEY	249
 
 /*
  * Persistantly stores the device replace state in the device tree.
@@ -2176,7 +2271,7 @@ struct btrfs_ioctl_defrag_range_args {
 #define BTRFS_MOUNT_ENOSPC_DEBUG	 (1 << 15)
 #define BTRFS_MOUNT_AUTO_DEFRAG		(1 << 16)
 #define BTRFS_MOUNT_INODE_MAP_CACHE	(1 << 17)
-#define BTRFS_MOUNT_RECOVERY		(1 << 18)
+#define BTRFS_MOUNT_USEBACKUPROOT	(1 << 18)
 #define BTRFS_MOUNT_SKIP_BALANCE	(1 << 19)
 #define BTRFS_MOUNT_CHECK_INTEGRITY	(1 << 20)
 #define BTRFS_MOUNT_CHECK_INTEGRITY_INCLUDING_EXTENT_DATA (1 << 21)
@@ -2184,9 +2279,11 @@ struct btrfs_ioctl_defrag_range_args {
 #define BTRFS_MOUNT_RESCAN_UUID_TREE	(1 << 23)
 #define BTRFS_MOUNT_FRAGMENT_DATA	(1 << 24)
 #define BTRFS_MOUNT_FRAGMENT_METADATA	(1 << 25)
+#define BTRFS_MOUNT_FREE_SPACE_TREE	(1 << 26)
+#define BTRFS_MOUNT_NOLOGREPLAY		(1 << 27)
 
 #define BTRFS_DEFAULT_COMMIT_INTERVAL	(30)
-#define BTRFS_DEFAULT_MAX_INLINE	(8192)
+#define BTRFS_DEFAULT_MAX_INLINE	(2048)
 
 #define btrfs_clear_opt(o, opt)		((o) &= ~BTRFS_MOUNT_##opt)
 #define btrfs_set_opt(o, opt)		((o) |= BTRFS_MOUNT_##opt)
@@ -2287,6 +2384,9 @@ struct btrfs_map_token {
 	unsigned long offset;
 };
 
+#define BTRFS_BYTES_TO_BLKS(fs_info, bytes) \
+				((bytes) >> (fs_info)->sb->s_blocksize_bits)
+
 static inline void btrfs_init_map_token (struct btrfs_map_token *token)
 {
 	token->kaddr = NULL;
@@ -2506,6 +2606,11 @@ BTRFS_SETGET_FUNCS(disk_block_group_flags,
 BTRFS_SETGET_STACK_FUNCS(block_group_flags,
 			struct btrfs_block_group_item, flags, 64);
 
+/* struct btrfs_free_space_info */
+BTRFS_SETGET_FUNCS(free_space_extent_count, struct btrfs_free_space_info,
+		   extent_count, 32);
+BTRFS_SETGET_FUNCS(free_space_flags, struct btrfs_free_space_info, flags, 32);
+
 /* struct btrfs_inode_ref */
 BTRFS_SETGET_FUNCS(inode_ref_name_len, struct btrfs_inode_ref, name_len, 16);
 BTRFS_SETGET_FUNCS(inode_ref_index, struct btrfs_inode_ref, index, 64);
@@ -3367,7 +3472,7 @@ static inline bool btrfs_mixed_space_info(struct btrfs_space_info *space_info)
 
 static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping)
 {
-	return mapping_gfp_mask(mapping) & ~__GFP_FS;
+	return mapping_gfp_constraint(mapping, ~__GFP_FS);
 }
 
 /* extent-tree.c */
@@ -3377,8 +3482,7 @@ u64 btrfs_csum_bytes_to_leaves(struct btrfs_root *root, u64 csum_bytes);
 static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_root *root,
 						 unsigned num_items)
 {
-	return (root->nodesize + root->nodesize * (BTRFS_MAX_LEVEL - 1)) *
-		2 * num_items;
+	return root->nodesize * BTRFS_MAX_LEVEL * 2 * num_items;
 }
 
 /*
@@ -3416,6 +3520,7 @@ int btrfs_cross_ref_exist(struct btrfs_trans_handle *trans,
 struct btrfs_block_group_cache *btrfs_lookup_block_group(
 						 struct btrfs_fs_info *info,
 						 u64 bytenr);
+void btrfs_get_block_group(struct btrfs_block_group_cache *cache);
 void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
 int get_block_group_index(struct btrfs_block_group_cache *cache);
 struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
@@ -3479,6 +3584,9 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root, u64 bytes_used,
 			   u64 type, u64 chunk_objectid, u64 chunk_offset,
 			   u64 size);
+struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
+				struct btrfs_fs_info *fs_info,
+				const u64 chunk_offset);
 int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root, u64 group_start,
 			     struct extent_map *em);
@@ -3566,9 +3674,13 @@ int btrfs_delayed_refs_qgroup_accounting(struct btrfs_trans_handle *trans,
 int __get_raid_index(u64 flags);
 int btrfs_start_write_no_snapshoting(struct btrfs_root *root);
 void btrfs_end_write_no_snapshoting(struct btrfs_root *root);
+void btrfs_wait_for_snapshot_creation(struct btrfs_root *root);
 void check_system_chunk(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root,
 			const u64 type);
+u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
+		       struct btrfs_fs_info *info, u64 start, u64 end);
+
 /* ctree.c */
 int btrfs_bin_search(struct extent_buffer *eb, struct btrfs_key *key,
 		     int level, int *slot);
@@ -3733,6 +3845,7 @@ static inline void free_fs_info(struct btrfs_fs_info *fs_info)
 	kfree(fs_info->csum_root);
 	kfree(fs_info->quota_root);
 	kfree(fs_info->uuid_root);
+	kfree(fs_info->free_space_root);
 	kfree(fs_info->super_copy);
 	kfree(fs_info->super_for_commit);
 	security_free_mnt_opts(&fs_info->security_opts);
@@ -3902,7 +4015,6 @@ void btrfs_extent_item_to_extent_map(struct inode *inode,
 /* inode.c */
 struct btrfs_delalloc_work {
 	struct inode *inode;
-	int wait;
 	int delay_iput;
 	struct completion completion;
 	struct list_head list;
@@ -3910,7 +4022,7 @@ struct btrfs_delalloc_work {
 };
 
 struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
-						    int wait, int delay_iput);
+						    int delay_iput);
 void btrfs_wait_and_free_delalloc_work(struct btrfs_delalloc_work *work);
 
 struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *page,
@@ -3948,7 +4060,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root,
 			struct inode *dir, u64 objectid,
 			const char *name, int name_len);
-int btrfs_truncate_page(struct inode *inode, loff_t from, loff_t len,
+int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
 			int front);
 int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *root,
@@ -4010,6 +4122,7 @@ void btrfs_test_inode_set_ops(struct inode *inode);
 
 /* ioctl.c */
 long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+int btrfs_ioctl_get_supported_features(void __user *arg);
 void btrfs_update_iflags(struct inode *inode);
 void btrfs_inherit_iflags(struct inode *inode, struct inode *dir);
 int btrfs_is_empty_uuid(u8 *uuid);
@@ -4020,7 +4133,8 @@ void btrfs_get_block_group_info(struct list_head *groups_list,
 				struct btrfs_ioctl_space_info *space);
 void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
 			       struct btrfs_ioctl_balance_args *bargs);
-
+ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
+			   struct file *dst_file, u64 dst_loff);
 
 /* file.c */
 int btrfs_auto_defrag_init(void);
@@ -4051,6 +4165,11 @@ int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode,
 		      loff_t pos, size_t write_bytes,
 		      struct extent_state **cached);
 int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end);
+ssize_t btrfs_copy_file_range(struct file *file_in, loff_t pos_in,
+			      struct file *file_out, loff_t pos_out,
+			      size_t len, unsigned int flags);
+int btrfs_clone_file_range(struct file *file_in, loff_t pos_in,
+			   struct file *file_out, loff_t pos_out, u64 len);
 
 /* tree-defrag.c */
 int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
@@ -4066,7 +4185,8 @@ void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info);
 ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
 
 /* super.c */
-int btrfs_parse_options(struct btrfs_root *root, char *options);
+int btrfs_parse_options(struct btrfs_root *root, char *options,
+			unsigned long new_flags);
 int btrfs_sync_fs(struct super_block *sb, int wait);
 
 #ifdef CONFIG_PRINTK
@@ -4243,16 +4363,98 @@ static inline void __btrfs_set_fs_incompat(struct btrfs_fs_info *fs_info,
 	}
 }
 
+#define btrfs_clear_fs_incompat(__fs_info, opt) \
+	__btrfs_clear_fs_incompat((__fs_info), BTRFS_FEATURE_INCOMPAT_##opt)
+
+static inline void __btrfs_clear_fs_incompat(struct btrfs_fs_info *fs_info,
+					     u64 flag)
+{
+	struct btrfs_super_block *disk_super;
+	u64 features;
+
+	disk_super = fs_info->super_copy;
+	features = btrfs_super_incompat_flags(disk_super);
+	if (features & flag) {
+		spin_lock(&fs_info->super_lock);
+		features = btrfs_super_incompat_flags(disk_super);
+		if (features & flag) {
+			features &= ~flag;
+			btrfs_set_super_incompat_flags(disk_super, features);
+			btrfs_info(fs_info, "clearing %llu feature flag",
+					 flag);
+		}
+		spin_unlock(&fs_info->super_lock);
+	}
+}
+
 #define btrfs_fs_incompat(fs_info, opt) \
 	__btrfs_fs_incompat((fs_info), BTRFS_FEATURE_INCOMPAT_##opt)
 
-static inline int __btrfs_fs_incompat(struct btrfs_fs_info *fs_info, u64 flag)
+static inline bool __btrfs_fs_incompat(struct btrfs_fs_info *fs_info, u64 flag)
 {
 	struct btrfs_super_block *disk_super;
 	disk_super = fs_info->super_copy;
 	return !!(btrfs_super_incompat_flags(disk_super) & flag);
 }
 
+#define btrfs_set_fs_compat_ro(__fs_info, opt) \
+	__btrfs_set_fs_compat_ro((__fs_info), BTRFS_FEATURE_COMPAT_RO_##opt)
+
+static inline void __btrfs_set_fs_compat_ro(struct btrfs_fs_info *fs_info,
+					    u64 flag)
+{
+	struct btrfs_super_block *disk_super;
+	u64 features;
+
+	disk_super = fs_info->super_copy;
+	features = btrfs_super_compat_ro_flags(disk_super);
+	if (!(features & flag)) {
+		spin_lock(&fs_info->super_lock);
+		features = btrfs_super_compat_ro_flags(disk_super);
+		if (!(features & flag)) {
+			features |= flag;
+			btrfs_set_super_compat_ro_flags(disk_super, features);
+			btrfs_info(fs_info, "setting %llu ro feature flag",
+				   flag);
+		}
+		spin_unlock(&fs_info->super_lock);
+	}
+}
+
+#define btrfs_clear_fs_compat_ro(__fs_info, opt) \
+	__btrfs_clear_fs_compat_ro((__fs_info), BTRFS_FEATURE_COMPAT_RO_##opt)
+
+static inline void __btrfs_clear_fs_compat_ro(struct btrfs_fs_info *fs_info,
+					      u64 flag)
+{
+	struct btrfs_super_block *disk_super;
+	u64 features;
+
+	disk_super = fs_info->super_copy;
+	features = btrfs_super_compat_ro_flags(disk_super);
+	if (features & flag) {
+		spin_lock(&fs_info->super_lock);
+		features = btrfs_super_compat_ro_flags(disk_super);
+		if (features & flag) {
+			features &= ~flag;
+			btrfs_set_super_compat_ro_flags(disk_super, features);
+			btrfs_info(fs_info, "clearing %llu ro feature flag",
+				   flag);
+		}
+		spin_unlock(&fs_info->super_lock);
+	}
+}
+
+#define btrfs_fs_compat_ro(fs_info, opt) \
+	__btrfs_fs_compat_ro((fs_info), BTRFS_FEATURE_COMPAT_RO_##opt)
+
+static inline int __btrfs_fs_compat_ro(struct btrfs_fs_info *fs_info, u64 flag)
+{
+	struct btrfs_super_block *disk_super;
+	disk_super = fs_info->super_copy;
+	return !!(btrfs_super_compat_ro_flags(disk_super) & flag);
+}
+
 /*
  * Call btrfs_abort_transaction as early as possible when an error condition is
  * detected, that way the exact line number is reported.
@@ -4358,8 +4560,8 @@ struct reada_control *btrfs_reada_add(struct btrfs_root *root,
 			      struct btrfs_key *start, struct btrfs_key *end);
 int btrfs_reada_wait(void *handle);
 void btrfs_reada_detach(void *handle);
-int btree_readahead_hook(struct btrfs_root *root, struct extent_buffer *eb,
-			 u64 start, int err);
+int btree_readahead_hook(struct btrfs_fs_info *fs_info,
+			 struct extent_buffer *eb, u64 start, int err);
 
 static inline int is_fstree(u64 rootid)
 {
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index e0941fbb913c..6cef0062f929 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -43,8 +43,7 @@ int __init btrfs_delayed_inode_init(void)
 
 void btrfs_delayed_inode_exit(void)
 {
-	if (delayed_node_cache)
-		kmem_cache_destroy(delayed_node_cache);
+	kmem_cache_destroy(delayed_node_cache);
 }
 
 static inline void btrfs_init_delayed_node(
@@ -54,16 +53,11 @@ static inline void btrfs_init_delayed_node(
 	delayed_node->root = root;
 	delayed_node->inode_id = inode_id;
 	atomic_set(&delayed_node->refs, 0);
-	delayed_node->count = 0;
-	delayed_node->flags = 0;
 	delayed_node->ins_root = RB_ROOT;
 	delayed_node->del_root = RB_ROOT;
 	mutex_init(&delayed_node->mutex);
-	delayed_node->index_cnt = 0;
 	INIT_LIST_HEAD(&delayed_node->n_list);
 	INIT_LIST_HEAD(&delayed_node->p_list);
-	delayed_node->bytes_reserved = 0;
-	memset(&delayed_node->inode_item, 0, sizeof(delayed_node->inode_item));
 }
 
 static inline int btrfs_is_continuous_delayed_item(
@@ -132,7 +126,7 @@ again:
 	if (node)
 		return node;
 
-	node = kmem_cache_alloc(delayed_node_cache, GFP_NOFS);
+	node = kmem_cache_zalloc(delayed_node_cache, GFP_NOFS);
 	if (!node)
 		return ERR_PTR(-ENOMEM);
 	btrfs_init_delayed_node(node, root, ino);
@@ -656,9 +650,14 @@ static int btrfs_delayed_inode_reserve_metadata(
 			goto out;
 
 		ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes);
-		if (!WARN_ON(ret))
+		if (!ret)
 			goto out;
 
+		if (btrfs_test_opt(root, ENOSPC_DEBUG)) {
+			btrfs_debug(root->fs_info,
+				    "block rsv migrate returned %d", ret);
+			WARN_ON(1);
+		}
 		/*
 		 * Ok this is a problem, let's just steal from the global rsv
 		 * since this really shouldn't happen that often.
@@ -1694,7 +1693,7 @@ int btrfs_should_delete_dir_index(struct list_head *del_list,
  *
  */
 int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
-				    struct list_head *ins_list)
+				    struct list_head *ins_list, bool *emitted)
 {
 	struct btrfs_dir_item *di;
 	struct btrfs_delayed_item *curr, *next;
@@ -1738,6 +1737,7 @@ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
 
 		if (over)
 			return 1;
+		*emitted = true;
 	}
 	return 0;
 }
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index f70119f25421..0167853c84ae 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -144,7 +144,7 @@ void btrfs_put_delayed_items(struct list_head *ins_list,
 int btrfs_should_delete_dir_index(struct list_head *del_list,
 				  u64 index);
 int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
-				    struct list_head *ins_list);
+				    struct list_head *ins_list, bool *emitted);
 
 /* for init */
 int __init btrfs_delayed_inode_init(void);
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index e06dd75ad13f..430b3689b112 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -493,12 +493,12 @@ update_existing_head_ref(struct btrfs_delayed_ref_root *delayed_refs,
 				memcpy(&existing_ref->extent_op->key,
 				       &ref->extent_op->key,
 				       sizeof(ref->extent_op->key));
-				existing_ref->extent_op->update_key = 1;
+				existing_ref->extent_op->update_key = true;
 			}
 			if (ref->extent_op->update_flags) {
 				existing_ref->extent_op->flags_to_set |=
 					ref->extent_op->flags_to_set;
-				existing_ref->extent_op->update_flags = 1;
+				existing_ref->extent_op->update_flags = true;
 			}
 			btrfs_free_delayed_extent_op(ref->extent_op);
 		}
@@ -929,14 +929,10 @@ btrfs_find_delayed_ref_head(struct btrfs_trans_handle *trans, u64 bytenr)
 
 void btrfs_delayed_ref_exit(void)
 {
-	if (btrfs_delayed_ref_head_cachep)
-		kmem_cache_destroy(btrfs_delayed_ref_head_cachep);
-	if (btrfs_delayed_tree_ref_cachep)
-		kmem_cache_destroy(btrfs_delayed_tree_ref_cachep);
-	if (btrfs_delayed_data_ref_cachep)
-		kmem_cache_destroy(btrfs_delayed_data_ref_cachep);
-	if (btrfs_delayed_extent_op_cachep)
-		kmem_cache_destroy(btrfs_delayed_extent_op_cachep);
+	kmem_cache_destroy(btrfs_delayed_ref_head_cachep);
+	kmem_cache_destroy(btrfs_delayed_tree_ref_cachep);
+	kmem_cache_destroy(btrfs_delayed_data_ref_cachep);
+	kmem_cache_destroy(btrfs_delayed_extent_op_cachep);
 }
 
 int btrfs_delayed_ref_init(void)
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index 00ed02cbf3e9..c24b653c7343 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -75,11 +75,11 @@ struct btrfs_delayed_ref_node {
 
 struct btrfs_delayed_extent_op {
 	struct btrfs_disk_key key;
+	u8 level;
+	bool update_key;
+	bool update_flags;
+	bool is_data;
 	u64 flags_to_set;
-	int level;
-	unsigned int update_key:1;
-	unsigned int update_flags:1;
-	unsigned int is_data:1;
 };
 
 /*
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 1e668fb7dd4c..26bcb487f958 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -202,13 +202,13 @@ int btrfs_run_dev_replace(struct btrfs_trans_handle *trans,
 	struct btrfs_dev_replace_item *ptr;
 	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
 
-	btrfs_dev_replace_lock(dev_replace);
+	btrfs_dev_replace_lock(dev_replace, 0);
 	if (!dev_replace->is_valid ||
 	    !dev_replace->item_needs_writeback) {
-		btrfs_dev_replace_unlock(dev_replace);
+		btrfs_dev_replace_unlock(dev_replace, 0);
 		return 0;
 	}
-	btrfs_dev_replace_unlock(dev_replace);
+	btrfs_dev_replace_unlock(dev_replace, 0);
 
 	key.objectid = 0;
 	key.type = BTRFS_DEV_REPLACE_KEY;
@@ -264,7 +264,7 @@ int btrfs_run_dev_replace(struct btrfs_trans_handle *trans,
 	ptr = btrfs_item_ptr(eb, path->slots[0],
 			     struct btrfs_dev_replace_item);
 
-	btrfs_dev_replace_lock(dev_replace);
+	btrfs_dev_replace_lock(dev_replace, 1);
 	if (dev_replace->srcdev)
 		btrfs_set_dev_replace_src_devid(eb, ptr,
 			dev_replace->srcdev->devid);
@@ -287,7 +287,7 @@ int btrfs_run_dev_replace(struct btrfs_trans_handle *trans,
 	btrfs_set_dev_replace_cursor_right(eb, ptr,
 		dev_replace->cursor_right);
 	dev_replace->item_needs_writeback = 0;
-	btrfs_dev_replace_unlock(dev_replace);
+	btrfs_dev_replace_unlock(dev_replace, 1);
 
 	btrfs_mark_buffer_dirty(eb);
 
@@ -356,7 +356,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 		return PTR_ERR(trans);
 	}
 
-	btrfs_dev_replace_lock(dev_replace);
+	btrfs_dev_replace_lock(dev_replace, 1);
 	switch (dev_replace->replace_state) {
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED:
@@ -394,8 +394,10 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 	dev_replace->cursor_right = 0;
 	dev_replace->is_valid = 1;
 	dev_replace->item_needs_writeback = 1;
+	atomic64_set(&dev_replace->num_write_errors, 0);
+	atomic64_set(&dev_replace->num_uncorrectable_read_errors, 0);
 	args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR;
-	btrfs_dev_replace_unlock(dev_replace);
+	btrfs_dev_replace_unlock(dev_replace, 1);
 
 	ret = btrfs_sysfs_add_device_link(tgt_device->fs_devices, tgt_device);
 	if (ret)
@@ -407,7 +409,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
-		btrfs_dev_replace_lock(dev_replace);
+		btrfs_dev_replace_lock(dev_replace, 1);
 		goto leave;
 	}
 
@@ -433,7 +435,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 leave:
 	dev_replace->srcdev = NULL;
 	dev_replace->tgtdev = NULL;
-	btrfs_dev_replace_unlock(dev_replace);
+	btrfs_dev_replace_unlock(dev_replace, 1);
 	btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
 	return ret;
 }
@@ -471,18 +473,18 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	/* don't allow cancel or unmount to disturb the finishing procedure */
 	mutex_lock(&dev_replace->lock_finishing_cancel_unmount);
 
-	btrfs_dev_replace_lock(dev_replace);
+	btrfs_dev_replace_lock(dev_replace, 0);
 	/* was the operation canceled, or is it finished? */
 	if (dev_replace->replace_state !=
 	    BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED) {
-		btrfs_dev_replace_unlock(dev_replace);
+		btrfs_dev_replace_unlock(dev_replace, 0);
 		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 		return 0;
 	}
 
 	tgt_device = dev_replace->tgtdev;
 	src_device = dev_replace->srcdev;
-	btrfs_dev_replace_unlock(dev_replace);
+	btrfs_dev_replace_unlock(dev_replace, 0);
 
 	/*
 	 * flush all outstanding I/O and inode extent mappings before the
@@ -507,7 +509,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	/* keep away write_all_supers() during the finishing procedure */
 	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
 	mutex_lock(&root->fs_info->chunk_mutex);
-	btrfs_dev_replace_lock(dev_replace);
+	btrfs_dev_replace_lock(dev_replace, 1);
 	dev_replace->replace_state =
 		scrub_ret ? BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED
 			  : BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED;
@@ -528,7 +530,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 			        rcu_str_deref(src_device->name),
 			      src_device->devid,
 			      rcu_str_deref(tgt_device->name), scrub_ret);
-		btrfs_dev_replace_unlock(dev_replace);
+		btrfs_dev_replace_unlock(dev_replace, 1);
 		mutex_unlock(&root->fs_info->chunk_mutex);
 		mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
 		mutex_unlock(&uuid_mutex);
@@ -565,7 +567,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list);
 	fs_info->fs_devices->rw_devices++;
 
-	btrfs_dev_replace_unlock(dev_replace);
+	btrfs_dev_replace_unlock(dev_replace, 1);
 
 	btrfs_rm_dev_replace_blocked(fs_info);
 
@@ -614,7 +616,7 @@ static void btrfs_dev_replace_update_device_in_mapping_tree(
 		em = lookup_extent_mapping(em_tree, start, (u64)-1);
 		if (!em)
 			break;
-		map = (struct map_lookup *)em->bdev;
+		map = em->map_lookup;
 		for (i = 0; i < map->num_stripes; i++)
 			if (srcdev == map->stripes[i].dev)
 				map->stripes[i].dev = tgtdev;
@@ -649,7 +651,7 @@ void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info,
 	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
 	struct btrfs_device *srcdev;
 
-	btrfs_dev_replace_lock(dev_replace);
+	btrfs_dev_replace_lock(dev_replace, 0);
 	/* even if !dev_replace_is_valid, the values are good enough for
 	 * the replace_status ioctl */
 	args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR;
@@ -675,7 +677,7 @@ void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info,
 			div_u64(btrfs_device_get_total_bytes(srcdev), 1000));
 		break;
 	}
-	btrfs_dev_replace_unlock(dev_replace);
+	btrfs_dev_replace_unlock(dev_replace, 0);
 }
 
 int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info,
@@ -698,13 +700,13 @@ static u64 __btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info)
 		return -EROFS;
 
 	mutex_lock(&dev_replace->lock_finishing_cancel_unmount);
-	btrfs_dev_replace_lock(dev_replace);
+	btrfs_dev_replace_lock(dev_replace, 1);
 	switch (dev_replace->replace_state) {
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED:
 		result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NOT_STARTED;
-		btrfs_dev_replace_unlock(dev_replace);
+		btrfs_dev_replace_unlock(dev_replace, 1);
 		goto leave;
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
@@ -717,7 +719,7 @@ static u64 __btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info)
 	dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED;
 	dev_replace->time_stopped = get_seconds();
 	dev_replace->item_needs_writeback = 1;
-	btrfs_dev_replace_unlock(dev_replace);
+	btrfs_dev_replace_unlock(dev_replace, 1);
 	btrfs_scrub_cancel(fs_info);
 
 	trans = btrfs_start_transaction(root, 0);
@@ -740,7 +742,7 @@ void btrfs_dev_replace_suspend_for_unmount(struct btrfs_fs_info *fs_info)
 	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
 
 	mutex_lock(&dev_replace->lock_finishing_cancel_unmount);
-	btrfs_dev_replace_lock(dev_replace);
+	btrfs_dev_replace_lock(dev_replace, 1);
 	switch (dev_replace->replace_state) {
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED:
@@ -756,7 +758,7 @@ void btrfs_dev_replace_suspend_for_unmount(struct btrfs_fs_info *fs_info)
 		break;
 	}
 
-	btrfs_dev_replace_unlock(dev_replace);
+	btrfs_dev_replace_unlock(dev_replace, 1);
 	mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 }
 
@@ -766,12 +768,12 @@ int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info)
 	struct task_struct *task;
 	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
 
-	btrfs_dev_replace_lock(dev_replace);
+	btrfs_dev_replace_lock(dev_replace, 1);
 	switch (dev_replace->replace_state) {
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED:
-		btrfs_dev_replace_unlock(dev_replace);
+		btrfs_dev_replace_unlock(dev_replace, 1);
 		return 0;
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
 		break;
@@ -784,10 +786,10 @@ int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info)
 		btrfs_info(fs_info, "cannot continue dev_replace, tgtdev is missing");
 		btrfs_info(fs_info,
 			"you may cancel the operation after 'mount -o degraded'");
-		btrfs_dev_replace_unlock(dev_replace);
+		btrfs_dev_replace_unlock(dev_replace, 1);
 		return 0;
 	}
-	btrfs_dev_replace_unlock(dev_replace);
+	btrfs_dev_replace_unlock(dev_replace, 1);
 
 	WARN_ON(atomic_xchg(
 		&fs_info->mutually_exclusive_operation_running, 1));
@@ -802,7 +804,7 @@ static int btrfs_dev_replace_kthread(void *data)
 	struct btrfs_ioctl_dev_replace_args *status_args;
 	u64 progress;
 
-	status_args = kzalloc(sizeof(*status_args), GFP_NOFS);
+	status_args = kzalloc(sizeof(*status_args), GFP_KERNEL);
 	if (status_args) {
 		btrfs_dev_replace_status(fs_info, status_args);
 		progress = status_args->status.progress_1000;
@@ -858,55 +860,65 @@ int btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace)
 		 * not called and the the filesystem is remounted
 		 * in degraded state. This does not stop the
 		 * dev_replace procedure. It needs to be canceled
-		 * manually if the cancelation is wanted.
+		 * manually if the cancellation is wanted.
 		 */
 		break;
 	}
 	return 1;
 }
 
-void btrfs_dev_replace_lock(struct btrfs_dev_replace *dev_replace)
+void btrfs_dev_replace_lock(struct btrfs_dev_replace *dev_replace, int rw)
 {
-	/* the beginning is just an optimization for the typical case */
-	if (atomic_read(&dev_replace->nesting_level) == 0) {
-acquire_lock:
-		/* this is not a nested case where the same thread
-		 * is trying to acqurire the same lock twice */
-		mutex_lock(&dev_replace->lock);
-		mutex_lock(&dev_replace->lock_management_lock);
-		dev_replace->lock_owner = current->pid;
-		atomic_inc(&dev_replace->nesting_level);
-		mutex_unlock(&dev_replace->lock_management_lock);
-		return;
+	if (rw == 1) {
+		/* write */
+again:
+		wait_event(dev_replace->read_lock_wq,
+			   atomic_read(&dev_replace->blocking_readers) == 0);
+		write_lock(&dev_replace->lock);
+		if (atomic_read(&dev_replace->blocking_readers)) {
+			write_unlock(&dev_replace->lock);
+			goto again;
+		}
+	} else {
+		read_lock(&dev_replace->lock);
+		atomic_inc(&dev_replace->read_locks);
 	}
+}
 
-	mutex_lock(&dev_replace->lock_management_lock);
-	if (atomic_read(&dev_replace->nesting_level) > 0 &&
-	    dev_replace->lock_owner == current->pid) {
-		WARN_ON(!mutex_is_locked(&dev_replace->lock));
-		atomic_inc(&dev_replace->nesting_level);
-		mutex_unlock(&dev_replace->lock_management_lock);
-		return;
+void btrfs_dev_replace_unlock(struct btrfs_dev_replace *dev_replace, int rw)
+{
+	if (rw == 1) {
+		/* write */
+		ASSERT(atomic_read(&dev_replace->blocking_readers) == 0);
+		write_unlock(&dev_replace->lock);
+	} else {
+		ASSERT(atomic_read(&dev_replace->read_locks) > 0);
+		atomic_dec(&dev_replace->read_locks);
+		read_unlock(&dev_replace->lock);
 	}
+}
 
-	mutex_unlock(&dev_replace->lock_management_lock);
-	goto acquire_lock;
+/* inc blocking cnt and release read lock */
+void btrfs_dev_replace_set_lock_blocking(
+					struct btrfs_dev_replace *dev_replace)
+{
+	/* only set blocking for read lock */
+	ASSERT(atomic_read(&dev_replace->read_locks) > 0);
+	atomic_inc(&dev_replace->blocking_readers);
+	read_unlock(&dev_replace->lock);
 }
 
-void btrfs_dev_replace_unlock(struct btrfs_dev_replace *dev_replace)
+/* acquire read lock and dec blocking cnt */
+void btrfs_dev_replace_clear_lock_blocking(
+					struct btrfs_dev_replace *dev_replace)
 {
-	WARN_ON(!mutex_is_locked(&dev_replace->lock));
-	mutex_lock(&dev_replace->lock_management_lock);
-	WARN_ON(atomic_read(&dev_replace->nesting_level) < 1);
-	WARN_ON(dev_replace->lock_owner != current->pid);
-	atomic_dec(&dev_replace->nesting_level);
-	if (atomic_read(&dev_replace->nesting_level) == 0) {
-		dev_replace->lock_owner = 0;
-		mutex_unlock(&dev_replace->lock_management_lock);
-		mutex_unlock(&dev_replace->lock);
-	} else {
-		mutex_unlock(&dev_replace->lock_management_lock);
-	}
+	/* only set blocking for read lock */
+	ASSERT(atomic_read(&dev_replace->read_locks) > 0);
+	ASSERT(atomic_read(&dev_replace->blocking_readers) > 0);
+	read_lock(&dev_replace->lock);
+	if (atomic_dec_and_test(&dev_replace->blocking_readers) &&
+	    waitqueue_active(&dev_replace->read_lock_wq))
+		wake_up(&dev_replace->read_lock_wq);
 }
 
 void btrfs_bio_counter_inc_noblocked(struct btrfs_fs_info *fs_info)
diff --git a/fs/btrfs/dev-replace.h b/fs/btrfs/dev-replace.h
index 20035cbbf021..29e3ef5f96bd 100644
--- a/fs/btrfs/dev-replace.h
+++ b/fs/btrfs/dev-replace.h
@@ -34,8 +34,11 @@ int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info,
 void btrfs_dev_replace_suspend_for_unmount(struct btrfs_fs_info *fs_info);
 int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info);
 int btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace);
-void btrfs_dev_replace_lock(struct btrfs_dev_replace *dev_replace);
-void btrfs_dev_replace_unlock(struct btrfs_dev_replace *dev_replace);
+void btrfs_dev_replace_lock(struct btrfs_dev_replace *dev_replace, int rw);
+void btrfs_dev_replace_unlock(struct btrfs_dev_replace *dev_replace, int rw);
+void btrfs_dev_replace_set_lock_blocking(struct btrfs_dev_replace *dev_replace);
+void btrfs_dev_replace_clear_lock_blocking(
+					struct btrfs_dev_replace *dev_replace);
 
 static inline void btrfs_dev_replace_stats_inc(atomic64_t *stat_value)
 {
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 2d4667594681..4e47849d7427 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -25,7 +25,6 @@
 #include <linux/buffer_head.h>
 #include <linux/workqueue.h>
 #include <linux/kthread.h>
-#include <linux/freezer.h>
 #include <linux/slab.h>
 #include <linux/migrate.h>
 #include <linux/ratelimit.h>
@@ -42,6 +41,7 @@
 #include "locking.h"
 #include "tree-log.h"
 #include "free-space-cache.h"
+#include "free-space-tree.h"
 #include "inode-map.h"
 #include "check-integrity.h"
 #include "rcu-string.h"
@@ -49,11 +49,18 @@
 #include "raid56.h"
 #include "sysfs.h"
 #include "qgroup.h"
+#include "compression.h"
 
 #ifdef CONFIG_X86
 #include <asm/cpufeature.h>
 #endif
 
+#define BTRFS_SUPER_FLAG_SUPP	(BTRFS_HEADER_FLAG_WRITTEN |\
+				 BTRFS_HEADER_FLAG_RELOC |\
+				 BTRFS_SUPER_FLAG_ERROR |\
+				 BTRFS_SUPER_FLAG_SEEDING |\
+				 BTRFS_SUPER_FLAG_METADUMP)
+
 static const struct extent_io_ops btree_extent_io_ops;
 static void end_workqueue_fn(struct btrfs_work *work);
 static void free_fs_root(struct btrfs_root *root);
@@ -103,8 +110,7 @@ int __init btrfs_end_io_wq_init(void)
 
 void btrfs_end_io_wq_exit(void)
 {
-	if (btrfs_end_io_wq_cache)
-		kmem_cache_destroy(btrfs_end_io_wq_cache);
+	kmem_cache_destroy(btrfs_end_io_wq_cache);
 }
 
 /*
@@ -175,6 +181,7 @@ static struct btrfs_lockdep_keyset {
 	{ .id = BTRFS_TREE_RELOC_OBJECTID,	.name_stem = "treloc"	},
 	{ .id = BTRFS_DATA_RELOC_TREE_OBJECTID,	.name_stem = "dreloc"	},
 	{ .id = BTRFS_UUID_TREE_OBJECTID,	.name_stem = "uuid"	},
+	{ .id = BTRFS_FREE_SPACE_TREE_OBJECTID,	.name_stem = "free-space" },
 	{ .id = 0,				.name_stem = "tree"	},
 };
 
@@ -295,7 +302,7 @@ static int csum_tree_block(struct btrfs_fs_info *fs_info,
 		err = map_private_extent_buffer(buf, offset, 32,
 					&kaddr, &map_start, &map_len);
 		if (err)
-			return 1;
+			return err;
 		cur_len = min(len, map_len - (offset - map_start));
 		crc = btrfs_csum_data(kaddr + offset - map_start,
 				      crc, cur_len);
@@ -305,7 +312,7 @@ static int csum_tree_block(struct btrfs_fs_info *fs_info,
 	if (csum_size > sizeof(inline_result)) {
 		result = kzalloc(csum_size, GFP_NOFS);
 		if (!result)
-			return 1;
+			return -ENOMEM;
 	} else {
 		result = (char *)&inline_result;
 	}
@@ -326,7 +333,7 @@ static int csum_tree_block(struct btrfs_fs_info *fs_info,
 				val, found, btrfs_header_level(buf));
 			if (result != (char *)&inline_result)
 				kfree(result);
-			return 1;
+			return -EUCLEAN;
 		}
 	} else {
 		write_extent_buffer(buf, result, 0, csum_size);
@@ -362,7 +369,7 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
 	}
 
 	lock_extent_bits(io_tree, eb->start, eb->start + eb->len - 1,
-			 0, &cached_state);
+			 &cached_state);
 	if (extent_buffer_uptodate(eb) &&
 	    btrfs_header_generation(eb) == parent_transid) {
 		ret = 0;
@@ -505,11 +512,21 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page)
 	eb = (struct extent_buffer *)page->private;
 	if (page != eb->pages[0])
 		return 0;
+
 	found_start = btrfs_header_bytenr(eb);
-	if (WARN_ON(found_start != start || !PageUptodate(page)))
-		return 0;
-	csum_tree_block(fs_info, eb, 0);
-	return 0;
+	/*
+	 * Please do not consolidate these warnings into a single if.
+	 * It is useful to know what went wrong.
+	 */
+	if (WARN_ON(found_start != start))
+		return -EUCLEAN;
+	if (WARN_ON(!PageUptodate(page)))
+		return -EUCLEAN;
+
+	ASSERT(memcmp_extent_buffer(eb, fs_info->fsid,
+			btrfs_header_fsid(), BTRFS_FSID_SIZE) == 0);
+
+	return csum_tree_block(fs_info, eb, 0);
 }
 
 static int check_tree_block_fsid(struct btrfs_fs_info *fs_info,
@@ -604,6 +621,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 	int found_level;
 	struct extent_buffer *eb;
 	struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
+	struct btrfs_fs_info *fs_info = root->fs_info;
 	int ret = 0;
 	int reads_done;
 
@@ -629,21 +647,21 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 
 	found_start = btrfs_header_bytenr(eb);
 	if (found_start != eb->start) {
-		btrfs_err_rl(eb->fs_info, "bad tree block start %llu %llu",
-			       found_start, eb->start);
+		btrfs_err_rl(fs_info, "bad tree block start %llu %llu",
+			     found_start, eb->start);
 		ret = -EIO;
 		goto err;
 	}
-	if (check_tree_block_fsid(root->fs_info, eb)) {
-		btrfs_err_rl(eb->fs_info, "bad fsid on block %llu",
-			       eb->start);
+	if (check_tree_block_fsid(fs_info, eb)) {
+		btrfs_err_rl(fs_info, "bad fsid on block %llu",
+			     eb->start);
 		ret = -EIO;
 		goto err;
 	}
 	found_level = btrfs_header_level(eb);
 	if (found_level >= BTRFS_MAX_LEVEL) {
-		btrfs_err(root->fs_info, "bad tree block level %d",
-			   (int)btrfs_header_level(eb));
+		btrfs_err(fs_info, "bad tree block level %d",
+			  (int)btrfs_header_level(eb));
 		ret = -EIO;
 		goto err;
 	}
@@ -651,11 +669,9 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 	btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb),
 				       eb, found_level);
 
-	ret = csum_tree_block(root->fs_info, eb, 1);
-	if (ret) {
-		ret = -EIO;
+	ret = csum_tree_block(fs_info, eb, 1);
+	if (ret)
 		goto err;
-	}
 
 	/*
 	 * If this is a leaf block and it is corrupt, set the corrupt bit so
@@ -672,7 +688,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 err:
 	if (reads_done &&
 	    test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
-		btree_readahead_hook(root, eb, eb->start, ret);
+		btree_readahead_hook(fs_info, eb, eb->start, ret);
 
 	if (ret) {
 		/*
@@ -691,14 +707,13 @@ out:
 static int btree_io_failed_hook(struct page *page, int failed_mirror)
 {
 	struct extent_buffer *eb;
-	struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
 
 	eb = (struct extent_buffer *)page->private;
 	set_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
 	eb->read_mirror = failed_mirror;
 	atomic_dec(&eb->io_pages);
 	if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
-		btree_readahead_hook(root, eb, eb->start, -EIO);
+		btree_readahead_hook(eb->fs_info, eb, eb->start, -EIO);
 	return -EIO;	/* we fixed nothing */
 }
 
@@ -808,7 +823,7 @@ static void run_one_async_done(struct btrfs_work *work)
 	    waitqueue_active(&fs_info->async_submit_wait))
 		wake_up(&fs_info->async_submit_wait);
 
-	/* If an error occured we just want to clean up the bio and move on */
+	/* If an error occurred we just want to clean up the bio and move on */
 	if (async->error) {
 		async->bio->bi_error = async->error;
 		bio_endio(async->bio);
@@ -923,7 +938,7 @@ static int check_async_write(struct inode *inode, unsigned long bio_flags)
 	if (bio_flags & EXTENT_BIO_TREE_LOG)
 		return 0;
 #ifdef CONFIG_X86
-	if (cpu_has_xmm4_2)
+	if (static_cpu_has(X86_FEATURE_XMM4_2))
 		return 0;
 #endif
 	return 1;
@@ -1047,7 +1062,7 @@ static void btree_invalidatepage(struct page *page, unsigned int offset,
 			   (unsigned long long)page_offset(page));
 		ClearPagePrivate(page);
 		set_page_private(page, 0);
-		page_cache_release(page);
+		put_page(page);
 	}
 }
 
@@ -1288,9 +1303,10 @@ static void __setup_root(u32 nodesize, u32 sectorsize, u32 stripesize,
 	spin_lock_init(&root->root_item_lock);
 }
 
-static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info)
+static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info,
+		gfp_t flags)
 {
-	struct btrfs_root *root = kzalloc(sizeof(*root), GFP_NOFS);
+	struct btrfs_root *root = kzalloc(sizeof(*root), flags);
 	if (root)
 		root->fs_info = fs_info;
 	return root;
@@ -1302,7 +1318,7 @@ struct btrfs_root *btrfs_alloc_dummy_root(void)
 {
 	struct btrfs_root *root;
 
-	root = btrfs_alloc_root(NULL);
+	root = btrfs_alloc_root(NULL, GFP_KERNEL);
 	if (!root)
 		return ERR_PTR(-ENOMEM);
 	__setup_root(4096, 4096, 4096, root, NULL, 1);
@@ -1324,7 +1340,7 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
 	int ret = 0;
 	uuid_le uuid;
 
-	root = btrfs_alloc_root(fs_info);
+	root = btrfs_alloc_root(fs_info, GFP_KERNEL);
 	if (!root)
 		return ERR_PTR(-ENOMEM);
 
@@ -1400,7 +1416,7 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
 	struct btrfs_root *tree_root = fs_info->tree_root;
 	struct extent_buffer *leaf;
 
-	root = btrfs_alloc_root(fs_info);
+	root = btrfs_alloc_root(fs_info, GFP_NOFS);
 	if (!root)
 		return ERR_PTR(-ENOMEM);
 
@@ -1498,7 +1514,7 @@ static struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
 	if (!path)
 		return ERR_PTR(-ENOMEM);
 
-	root = btrfs_alloc_root(fs_info);
+	root = btrfs_alloc_root(fs_info, GFP_NOFS);
 	if (!root) {
 		ret = -ENOMEM;
 		goto alloc_fail;
@@ -1582,8 +1598,23 @@ int btrfs_init_fs_root(struct btrfs_root *root)
 	ret = get_anon_bdev(&root->anon_dev);
 	if (ret)
 		goto free_writers;
+
+	mutex_lock(&root->objectid_mutex);
+	ret = btrfs_find_highest_objectid(root,
+					&root->highest_objectid);
+	if (ret) {
+		mutex_unlock(&root->objectid_mutex);
+		goto free_root_dev;
+	}
+
+	ASSERT(root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
+
+	mutex_unlock(&root->objectid_mutex);
+
 	return 0;
 
+free_root_dev:
+	free_anon_bdev(root->anon_dev);
 free_writers:
 	btrfs_free_subvolume_writers(root->subv_writers);
 fail:
@@ -1650,6 +1681,9 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
 	if (location->objectid == BTRFS_UUID_TREE_OBJECTID)
 		return fs_info->uuid_root ? fs_info->uuid_root :
 					    ERR_PTR(-ENOENT);
+	if (location->objectid == BTRFS_FREE_SPACE_TREE_OBJECTID)
+		return fs_info->free_space_root ? fs_info->free_space_root :
+						  ERR_PTR(-ENOENT);
 again:
 	root = btrfs_lookup_fs_root(fs_info, location->objectid);
 	if (root) {
@@ -1730,7 +1764,7 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
 	if (err)
 		return err;
 
-	bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE;
+	bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
 	bdi->congested_fn	= btrfs_congested_fn;
 	bdi->congested_data	= info;
 	bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK;
@@ -1762,7 +1796,6 @@ static int cleaner_kthread(void *arg)
 	int again;
 	struct btrfs_trans_handle *trans;
 
-	set_freezable();
 	do {
 		again = 0;
 
@@ -1782,7 +1815,10 @@ static int cleaner_kthread(void *arg)
 			goto sleep;
 		}
 
+		mutex_lock(&root->fs_info->cleaner_delayed_iput_mutex);
 		btrfs_run_delayed_iputs(root);
+		mutex_unlock(&root->fs_info->cleaner_delayed_iput_mutex);
+
 		again = btrfs_clean_one_deleted_snapshot(root);
 		mutex_unlock(&root->fs_info->cleaner_mutex);
 
@@ -1802,7 +1838,7 @@ static int cleaner_kthread(void *arg)
 		 */
 		btrfs_delete_unused_bgs(root->fs_info);
 sleep:
-		if (!try_to_freeze() && !again) {
+		if (!again) {
 			set_current_state(TASK_INTERRUPTIBLE);
 			if (!kthread_should_stop())
 				schedule();
@@ -1892,14 +1928,12 @@ sleep:
 		if (unlikely(test_bit(BTRFS_FS_STATE_ERROR,
 				      &root->fs_info->fs_state)))
 			btrfs_cleanup_transaction(root);
-		if (!try_to_freeze()) {
-			set_current_state(TASK_INTERRUPTIBLE);
-			if (!kthread_should_stop() &&
-			    (!btrfs_transaction_blocked(root->fs_info) ||
-			     cannot_commit))
-				schedule_timeout(delay);
-			__set_current_state(TASK_RUNNING);
-		}
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (!kthread_should_stop() &&
+				(!btrfs_transaction_blocked(root->fs_info) ||
+				 cannot_commit))
+			schedule_timeout(delay);
+		__set_current_state(TASK_RUNNING);
 	} while (!kthread_should_stop());
 	return 0;
 }
@@ -2148,6 +2182,7 @@ static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root)
 	free_root_extent_buffers(info->uuid_root);
 	if (chunk_root)
 		free_root_extent_buffers(info->chunk_root);
+	free_root_extent_buffers(info->free_space_root);
 }
 
 void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info)
@@ -2243,9 +2278,11 @@ static void btrfs_init_dev_replace_locks(struct btrfs_fs_info *fs_info)
 	fs_info->dev_replace.lock_owner = 0;
 	atomic_set(&fs_info->dev_replace.nesting_level, 0);
 	mutex_init(&fs_info->dev_replace.lock_finishing_cancel_unmount);
-	mutex_init(&fs_info->dev_replace.lock_management_lock);
-	mutex_init(&fs_info->dev_replace.lock);
+	rwlock_init(&fs_info->dev_replace.lock);
+	atomic_set(&fs_info->dev_replace.read_locks, 0);
+	atomic_set(&fs_info->dev_replace.blocking_readers, 0);
 	init_waitqueue_head(&fs_info->replace_wait);
+	init_waitqueue_head(&fs_info->dev_replace.read_lock_wq);
 }
 
 static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info)
@@ -2356,7 +2393,7 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info,
 		return -EIO;
 	}
 
-	log_tree_root = btrfs_alloc_root(fs_info);
+	log_tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
 	if (!log_tree_root)
 		return -ENOMEM;
 
@@ -2448,6 +2485,15 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info,
 		fs_info->uuid_root = root;
 	}
 
+	if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
+		location.objectid = BTRFS_FREE_SPACE_TREE_OBJECTID;
+		root = btrfs_read_tree_root(tree_root, &location);
+		if (IS_ERR(root))
+			return PTR_ERR(root);
+		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
+		fs_info->free_space_root = root;
+	}
+
 	return 0;
 }
 
@@ -2472,8 +2518,8 @@ int open_ctree(struct super_block *sb,
 	int backup_index = 0;
 	int max_active;
 
-	tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info);
-	chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info);
+	tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
+	chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
 	if (!tree_root || !chunk_root) {
 		err = -ENOMEM;
 		goto fail;
@@ -2496,7 +2542,7 @@ int open_ctree(struct super_block *sb,
 		err = ret;
 		goto fail_bdi;
 	}
-	fs_info->dirty_metadata_batch = PAGE_CACHE_SIZE *
+	fs_info->dirty_metadata_batch = PAGE_SIZE *
 					(1 + ilog2(nr_cpu_ids));
 
 	ret = percpu_counter_init(&fs_info->delalloc_bytes, 0, GFP_KERNEL);
@@ -2542,8 +2588,8 @@ int open_ctree(struct super_block *sb,
 	mutex_init(&fs_info->delete_unused_bgs_mutex);
 	mutex_init(&fs_info->reloc_mutex);
 	mutex_init(&fs_info->delalloc_root_mutex);
+	mutex_init(&fs_info->cleaner_delayed_iput_mutex);
 	seqlock_init(&fs_info->profiles_lock);
-	init_rwsem(&fs_info->delayed_iput_sem);
 
 	INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
 	INIT_LIST_HEAD(&fs_info->space_info);
@@ -2565,6 +2611,7 @@ int open_ctree(struct super_block *sb,
 	atomic_set(&fs_info->nr_async_bios, 0);
 	atomic_set(&fs_info->defrag_running, 0);
 	atomic_set(&fs_info->qgroup_op_seq, 0);
+	atomic_set(&fs_info->reada_works_cnt, 0);
 	atomic64_set(&fs_info->tree_mod_seq, 0);
 	fs_info->sb = sb;
 	fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE;
@@ -2575,7 +2622,7 @@ int open_ctree(struct super_block *sb,
 	fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
 	fs_info->avg_delayed_ref_runtime = NSEC_PER_SEC >> 6; /* div by 64 */
 	/* readahead state */
-	INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT);
+	INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
 	spin_lock_init(&fs_info->reada_lock);
 
 	fs_info->thread_pool_size = min_t(unsigned long,
@@ -2584,7 +2631,7 @@ int open_ctree(struct super_block *sb,
 	INIT_LIST_HEAD(&fs_info->ordered_roots);
 	spin_lock_init(&fs_info->ordered_root_lock);
 	fs_info->delayed_root = kmalloc(sizeof(struct btrfs_delayed_root),
-					GFP_NOFS);
+					GFP_KERNEL);
 	if (!fs_info->delayed_root) {
 		err = -ENOMEM;
 		goto fail_iput;
@@ -2668,6 +2715,7 @@ int open_ctree(struct super_block *sb,
 	if (btrfs_check_super_csum(bh->b_data)) {
 		printk(KERN_ERR "BTRFS: superblock checksum mismatch\n");
 		err = -EINVAL;
+		brelse(bh);
 		goto fail_alloc;
 	}
 
@@ -2711,7 +2759,7 @@ int open_ctree(struct super_block *sb,
 	 */
 	fs_info->compress_type = BTRFS_COMPRESS_ZLIB;
 
-	ret = btrfs_parse_options(tree_root, options);
+	ret = btrfs_parse_options(tree_root, options, sb->s_flags);
 	if (ret) {
 		err = ret;
 		goto fail_alloc;
@@ -2727,26 +2775,6 @@ int open_ctree(struct super_block *sb,
 		goto fail_alloc;
 	}
 
-	/*
-	 * Leafsize and nodesize were always equal, this is only a sanity check.
-	 */
-	if (le32_to_cpu(disk_super->__unused_leafsize) !=
-	    btrfs_super_nodesize(disk_super)) {
-		printk(KERN_ERR "BTRFS: couldn't mount because metadata "
-		       "blocksizes don't match.  node %d leaf %d\n",
-		       btrfs_super_nodesize(disk_super),
-		       le32_to_cpu(disk_super->__unused_leafsize));
-		err = -EINVAL;
-		goto fail_alloc;
-	}
-	if (btrfs_super_nodesize(disk_super) > BTRFS_MAX_METADATA_BLOCKSIZE) {
-		printk(KERN_ERR "BTRFS: couldn't mount because metadata "
-		       "blocksize (%d) was too large\n",
-		       btrfs_super_nodesize(disk_super));
-		err = -EINVAL;
-		goto fail_alloc;
-	}
-
 	features = btrfs_super_incompat_flags(disk_super);
 	features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF;
 	if (tree_root->fs_info->compress_type == BTRFS_COMPRESS_LZO)
@@ -2759,7 +2787,7 @@ int open_ctree(struct super_block *sb,
 	 * flag our filesystem as having big metadata blocks if
 	 * they are bigger than the page size
 	 */
-	if (btrfs_super_nodesize(disk_super) > PAGE_CACHE_SIZE) {
+	if (btrfs_super_nodesize(disk_super) > PAGE_SIZE) {
 		if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA))
 			printk(KERN_INFO "BTRFS: flagging fs with big metadata feature\n");
 		features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
@@ -2809,7 +2837,7 @@ int open_ctree(struct super_block *sb,
 
 	fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super);
 	fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages,
-				    4 * 1024 * 1024 / PAGE_CACHE_SIZE);
+				    SZ_4M / PAGE_SIZE);
 
 	tree_root->nodesize = nodesize;
 	tree_root->sectorsize = sectorsize;
@@ -2818,17 +2846,6 @@ int open_ctree(struct super_block *sb,
 	sb->s_blocksize = sectorsize;
 	sb->s_blocksize_bits = blksize_bits(sectorsize);
 
-	if (btrfs_super_magic(disk_super) != BTRFS_MAGIC) {
-		printk(KERN_ERR "BTRFS: valid FS not found on %s\n", sb->s_id);
-		goto fail_sb_buffer;
-	}
-
-	if (sectorsize != PAGE_SIZE) {
-		printk(KERN_ERR "BTRFS: incompatible sector size (%lu) "
-		       "found on %s\n", (unsigned long)sectorsize, sb->s_id);
-		goto fail_sb_buffer;
-	}
-
 	mutex_lock(&fs_info->chunk_mutex);
 	ret = btrfs_read_sys_array(tree_root);
 	mutex_unlock(&fs_info->chunk_mutex);
@@ -2900,6 +2917,18 @@ retry_root_backup:
 	tree_root->commit_root = btrfs_root_node(tree_root);
 	btrfs_set_root_refs(&tree_root->root_item, 1);
 
+	mutex_lock(&tree_root->objectid_mutex);
+	ret = btrfs_find_highest_objectid(tree_root,
+					&tree_root->highest_objectid);
+	if (ret) {
+		mutex_unlock(&tree_root->objectid_mutex);
+		goto recovery_tree_root;
+	}
+
+	ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
+
+	mutex_unlock(&tree_root->objectid_mutex);
+
 	ret = btrfs_read_roots(fs_info, tree_root);
 	if (ret)
 		goto recovery_tree_root;
@@ -3009,8 +3038,9 @@ retry_root_backup:
 	if (ret)
 		goto fail_trans_kthread;
 
-	/* do not make disk changes in broken FS */
-	if (btrfs_super_log_root(disk_super) != 0) {
+	/* do not make disk changes in broken FS or nologreplay is given */
+	if (btrfs_super_log_root(disk_super) != 0 &&
+	    !btrfs_test_opt(tree_root, NOLOGREPLAY)) {
 		ret = btrfs_replay_log(fs_info, fs_devices);
 		if (ret) {
 			err = ret;
@@ -3051,6 +3081,18 @@ retry_root_backup:
 	if (sb->s_flags & MS_RDONLY)
 		return 0;
 
+	if (btrfs_test_opt(tree_root, FREE_SPACE_TREE) &&
+	    !btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
+		pr_info("BTRFS: creating free space tree\n");
+		ret = btrfs_create_free_space_tree(fs_info);
+		if (ret) {
+			pr_warn("BTRFS: failed to create free space tree %d\n",
+				ret);
+			close_ctree(tree_root);
+			return ret;
+		}
+	}
+
 	down_read(&fs_info->cleanup_work_sem);
 	if ((ret = btrfs_orphan_cleanup(fs_info->fs_root)) ||
 	    (ret = btrfs_orphan_cleanup(fs_info->tree_root))) {
@@ -3076,6 +3118,18 @@ retry_root_backup:
 
 	btrfs_qgroup_rescan_resume(fs_info);
 
+	if (btrfs_test_opt(tree_root, CLEAR_CACHE) &&
+	    btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
+		pr_info("BTRFS: clearing free space tree\n");
+		ret = btrfs_clear_free_space_tree(fs_info);
+		if (ret) {
+			pr_warn("BTRFS: failed to clear free space tree %d\n",
+				ret);
+			close_ctree(tree_root);
+			return ret;
+		}
+	}
+
 	if (!fs_info->uuid_root) {
 		pr_info("BTRFS: creating UUID tree\n");
 		ret = btrfs_create_uuid_tree(fs_info);
@@ -3102,6 +3156,12 @@ retry_root_backup:
 
 	fs_info->open = 1;
 
+	/*
+	 * backuproot only affect mount behavior, and if open_ctree succeeded,
+	 * no need to keep the flag
+	 */
+	btrfs_clear_opt(fs_info->mount_opt, USEBACKUPROOT);
+
 	return 0;
 
 fail_qgroup:
@@ -3156,7 +3216,7 @@ fail:
 	return err;
 
 recovery_tree_root:
-	if (!btrfs_test_opt(tree_root, RECOVERY))
+	if (!btrfs_test_opt(tree_root, USEBACKUPROOT))
 		goto fail_tree_roots;
 
 	free_root_pointers(fs_info, 0);
@@ -3780,6 +3840,9 @@ void close_ctree(struct btrfs_root *root)
 	fs_info->closing = 1;
 	smp_mb();
 
+	/* wait for the qgroup rescan worker to stop */
+	btrfs_qgroup_wait_for_completion(fs_info);
+
 	/* wait for the uuid_scan task to finish */
 	down(&fs_info->uuid_tree_rescan_sem);
 	/* avoid complains from lockdep et al., set sem back to initial state */
@@ -3899,11 +3962,6 @@ int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
 	return !ret;
 }
 
-int btrfs_set_buffer_uptodate(struct extent_buffer *buf)
-{
-	return set_extent_buffer_uptodate(buf);
-}
-
 void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
 {
 	struct btrfs_root *root;
@@ -3959,7 +4017,6 @@ static void __btrfs_btree_balance_dirty(struct btrfs_root *root,
 		balance_dirty_pages_ratelimited(
 				   root->fs_info->btree_inode->i_mapping);
 	}
-	return;
 }
 
 void btrfs_btree_balance_dirty(struct btrfs_root *root)
@@ -3982,8 +4039,17 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
 			      int read_only)
 {
 	struct btrfs_super_block *sb = fs_info->super_copy;
+	u64 nodesize = btrfs_super_nodesize(sb);
+	u64 sectorsize = btrfs_super_sectorsize(sb);
 	int ret = 0;
 
+	if (btrfs_super_magic(sb) != BTRFS_MAGIC) {
+		printk(KERN_ERR "BTRFS: no valid FS found\n");
+		ret = -EINVAL;
+	}
+	if (btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP)
+		printk(KERN_WARNING "BTRFS: unrecognized super flag: %llu\n",
+				btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP);
 	if (btrfs_super_root_level(sb) >= BTRFS_MAX_LEVEL) {
 		printk(KERN_ERR "BTRFS: tree_root level too big: %d >= %d\n",
 				btrfs_super_root_level(sb), BTRFS_MAX_LEVEL);
@@ -4001,31 +4067,46 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
 	}
 
 	/*
-	 * The common minimum, we don't know if we can trust the nodesize/sectorsize
-	 * items yet, they'll be verified later. Issue just a warning.
+	 * Check sectorsize and nodesize first, other check will need it.
+	 * Check all possible sectorsize(4K, 8K, 16K, 32K, 64K) here.
 	 */
-	if (!IS_ALIGNED(btrfs_super_root(sb), 4096))
+	if (!is_power_of_2(sectorsize) || sectorsize < 4096 ||
+	    sectorsize > BTRFS_MAX_METADATA_BLOCKSIZE) {
+		printk(KERN_ERR "BTRFS: invalid sectorsize %llu\n", sectorsize);
+		ret = -EINVAL;
+	}
+	/* Only PAGE SIZE is supported yet */
+	if (sectorsize != PAGE_SIZE) {
+		printk(KERN_ERR "BTRFS: sectorsize %llu not supported yet, only support %lu\n",
+				sectorsize, PAGE_SIZE);
+		ret = -EINVAL;
+	}
+	if (!is_power_of_2(nodesize) || nodesize < sectorsize ||
+	    nodesize > BTRFS_MAX_METADATA_BLOCKSIZE) {
+		printk(KERN_ERR "BTRFS: invalid nodesize %llu\n", nodesize);
+		ret = -EINVAL;
+	}
+	if (nodesize != le32_to_cpu(sb->__unused_leafsize)) {
+		printk(KERN_ERR "BTRFS: invalid leafsize %u, should be %llu\n",
+				le32_to_cpu(sb->__unused_leafsize),
+				nodesize);
+		ret = -EINVAL;
+	}
+
+	/* Root alignment check */
+	if (!IS_ALIGNED(btrfs_super_root(sb), sectorsize)) {
 		printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
 				btrfs_super_root(sb));
-	if (!IS_ALIGNED(btrfs_super_chunk_root(sb), 4096))
+		ret = -EINVAL;
+	}
+	if (!IS_ALIGNED(btrfs_super_chunk_root(sb), sectorsize)) {
 		printk(KERN_WARNING "BTRFS: chunk_root block unaligned: %llu\n",
 				btrfs_super_chunk_root(sb));
-	if (!IS_ALIGNED(btrfs_super_log_root(sb), 4096))
-		printk(KERN_WARNING "BTRFS: log_root block unaligned: %llu\n",
-				btrfs_super_log_root(sb));
-
-	/*
-	 * Check the lower bound, the alignment and other constraints are
-	 * checked later.
-	 */
-	if (btrfs_super_nodesize(sb) < 4096) {
-		printk(KERN_ERR "BTRFS: nodesize too small: %u < 4096\n",
-				btrfs_super_nodesize(sb));
 		ret = -EINVAL;
 	}
-	if (btrfs_super_sectorsize(sb) < 4096) {
-		printk(KERN_ERR "BTRFS: sectorsize too small: %u < 4096\n",
-				btrfs_super_sectorsize(sb));
+	if (!IS_ALIGNED(btrfs_super_log_root(sb), sectorsize)) {
+		printk(KERN_WARNING "BTRFS: log_root block unaligned: %llu\n",
+				btrfs_super_log_root(sb));
 		ret = -EINVAL;
 	}
 
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index adeb31830b9c..8e79d0070bcf 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -19,7 +19,7 @@
 #ifndef __DISKIO__
 #define __DISKIO__
 
-#define BTRFS_SUPER_INFO_OFFSET (64 * 1024)
+#define BTRFS_SUPER_INFO_OFFSET SZ_64K
 #define BTRFS_SUPER_INFO_SIZE 4096
 
 #define BTRFS_SUPER_MIRROR_MAX	 3
@@ -35,7 +35,7 @@ enum btrfs_wq_endio_type {
 
 static inline u64 btrfs_sb_offset(int mirror)
 {
-	u64 start = 16 * 1024;
+	u64 start = SZ_16K;
 	if (mirror)
 		return start << (BTRFS_SUPER_MIRROR_SHIFT * mirror);
 	return BTRFS_SUPER_INFO_OFFSET;
@@ -116,7 +116,6 @@ static inline void btrfs_put_fs_root(struct btrfs_root *root)
 void btrfs_mark_buffer_dirty(struct extent_buffer *buf);
 int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
 			  int atomic);
-int btrfs_set_buffer_uptodate(struct extent_buffer *buf);
 int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid);
 u32 btrfs_csum_data(char *data, u32 seed, size_t len);
 void btrfs_csum_final(u32 crc, char *result);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 99a8e57da8a1..84e060eb0de8 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -33,6 +33,7 @@
 #include "raid56.h"
 #include "locking.h"
 #include "free-space-cache.h"
+#include "free-space-tree.h"
 #include "math.h"
 #include "sysfs.h"
 #include "qgroup.h"
@@ -124,7 +125,7 @@ static int block_group_bits(struct btrfs_block_group_cache *cache, u64 bits)
 	return (cache->flags & bits) == bits;
 }
 
-static void btrfs_get_block_group(struct btrfs_block_group_cache *cache)
+void btrfs_get_block_group(struct btrfs_block_group_cache *cache)
 {
 	atomic_inc(&cache->count);
 }
@@ -357,8 +358,8 @@ static void fragment_free_space(struct btrfs_root *root,
  * we need to check the pinned_extents for any extents that can't be used yet
  * since their free space will be released as soon as the transaction commits.
  */
-static u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
-			      struct btrfs_fs_info *info, u64 start, u64 end)
+u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
+		       struct btrfs_fs_info *info, u64 start, u64 end)
 {
 	u64 extent_start, extent_end, size, total_added = 0;
 	int ret;
@@ -395,11 +396,10 @@ static u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
 	return total_added;
 }
 
-static noinline void caching_thread(struct btrfs_work *work)
+static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl)
 {
 	struct btrfs_block_group_cache *block_group;
 	struct btrfs_fs_info *fs_info;
-	struct btrfs_caching_control *caching_ctl;
 	struct btrfs_root *extent_root;
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
@@ -407,17 +407,16 @@ static noinline void caching_thread(struct btrfs_work *work)
 	u64 total_found = 0;
 	u64 last = 0;
 	u32 nritems;
-	int ret = -ENOMEM;
+	int ret;
 	bool wakeup = true;
 
-	caching_ctl = container_of(work, struct btrfs_caching_control, work);
 	block_group = caching_ctl->block_group;
 	fs_info = block_group->fs_info;
 	extent_root = fs_info->extent_root;
 
 	path = btrfs_alloc_path();
 	if (!path)
-		goto out;
+		return -ENOMEM;
 
 	last = max_t(u64, block_group->key.objectid, BTRFS_SUPER_INFO_OFFSET);
 
@@ -438,20 +437,16 @@ static noinline void caching_thread(struct btrfs_work *work)
 	 */
 	path->skip_locking = 1;
 	path->search_commit_root = 1;
-	path->reada = 1;
+	path->reada = READA_FORWARD;
 
 	key.objectid = last;
 	key.offset = 0;
 	key.type = BTRFS_EXTENT_ITEM_KEY;
-again:
-	mutex_lock(&caching_ctl->mutex);
-	/* need to make sure the commit_root doesn't disappear */
-	down_read(&fs_info->commit_root_sem);
 
 next:
 	ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0);
 	if (ret < 0)
-		goto err;
+		goto out;
 
 	leaf = path->nodes[0];
 	nritems = btrfs_header_nritems(leaf);
@@ -477,12 +472,14 @@ next:
 				up_read(&fs_info->commit_root_sem);
 				mutex_unlock(&caching_ctl->mutex);
 				cond_resched();
-				goto again;
+				mutex_lock(&caching_ctl->mutex);
+				down_read(&fs_info->commit_root_sem);
+				goto next;
 			}
 
 			ret = btrfs_next_leaf(extent_root, path);
 			if (ret < 0)
-				goto err;
+				goto out;
 			if (ret)
 				break;
 			leaf = path->nodes[0];
@@ -521,7 +518,7 @@ next:
 			else
 				last = key.objectid + key.offset;
 
-			if (total_found > (1024 * 1024 * 2)) {
+			if (total_found > CACHING_CTL_WAKE_UP) {
 				total_found = 0;
 				if (wakeup)
 					wake_up(&caching_ctl->wait);
@@ -534,9 +531,37 @@ next:
 	total_found += add_new_free_space(block_group, fs_info, last,
 					  block_group->key.objectid +
 					  block_group->key.offset);
+	caching_ctl->progress = (u64)-1;
+
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
+static noinline void caching_thread(struct btrfs_work *work)
+{
+	struct btrfs_block_group_cache *block_group;
+	struct btrfs_fs_info *fs_info;
+	struct btrfs_caching_control *caching_ctl;
+	struct btrfs_root *extent_root;
+	int ret;
+
+	caching_ctl = container_of(work, struct btrfs_caching_control, work);
+	block_group = caching_ctl->block_group;
+	fs_info = block_group->fs_info;
+	extent_root = fs_info->extent_root;
+
+	mutex_lock(&caching_ctl->mutex);
+	down_read(&fs_info->commit_root_sem);
+
+	if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE))
+		ret = load_free_space_tree(caching_ctl);
+	else
+		ret = load_extent_tree_free(caching_ctl);
+
 	spin_lock(&block_group->lock);
 	block_group->caching_ctl = NULL;
-	block_group->cached = BTRFS_CACHE_FINISHED;
+	block_group->cached = ret ? BTRFS_CACHE_ERROR : BTRFS_CACHE_FINISHED;
 	spin_unlock(&block_group->lock);
 
 #ifdef CONFIG_BTRFS_DEBUG
@@ -555,20 +580,11 @@ next:
 #endif
 
 	caching_ctl->progress = (u64)-1;
-err:
-	btrfs_free_path(path);
-	up_read(&fs_info->commit_root_sem);
-
-	free_excluded_extents(extent_root, block_group);
 
+	up_read(&fs_info->commit_root_sem);
+	free_excluded_extents(fs_info->extent_root, block_group);
 	mutex_unlock(&caching_ctl->mutex);
-out:
-	if (ret) {
-		spin_lock(&block_group->lock);
-		block_group->caching_ctl = NULL;
-		block_group->cached = BTRFS_CACHE_ERROR;
-		spin_unlock(&block_group->lock);
-	}
+
 	wake_up(&caching_ctl->wait);
 
 	put_caching_control(caching_ctl);
@@ -680,8 +696,8 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
 		}
 	} else {
 		/*
-		 * We are not going to do the fast caching, set cached to the
-		 * appropriate value and wakeup any waiters.
+		 * We're either using the free space tree or no caching at all.
+		 * Set cached to the appropriate value and wakeup any waiters.
 		 */
 		spin_lock(&cache->lock);
 		if (load_cache_only) {
@@ -2115,7 +2131,7 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	path->reada = 1;
+	path->reada = READA_FORWARD;
 	path->leave_spinning = 1;
 	/* this will setup the path even if it fails to insert the back ref */
 	ret = insert_inline_extent_backref(trans, fs_info->extent_root, path,
@@ -2141,7 +2157,7 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(leaf);
 	btrfs_release_path(path);
 
-	path->reada = 1;
+	path->reada = READA_FORWARD;
 	path->leave_spinning = 1;
 	/* now insert the actual backref */
 	ret = insert_extent_backref(trans, root->fs_info->extent_root,
@@ -2254,7 +2270,7 @@ static int run_delayed_extent_op(struct btrfs_trans_handle *trans,
 	}
 
 again:
-	path->reada = 1;
+	path->reada = READA_FORWARD;
 	path->leave_spinning = 1;
 	ret = btrfs_search_slot(trans, root->fs_info->extent_root, &key,
 				path, 0, 1);
@@ -2910,6 +2926,9 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 	if (trans->aborted)
 		return 0;
 
+	if (root->fs_info->creating_free_space_tree)
+		return 0;
+
 	if (root == root->fs_info->extent_root)
 		root = root->fs_info->tree_root;
 
@@ -2988,9 +3007,9 @@ int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 
 	extent_op->flags_to_set = flags;
-	extent_op->update_flags = 1;
-	extent_op->update_key = 0;
-	extent_op->is_data = is_data ? 1 : 0;
+	extent_op->update_flags = true;
+	extent_op->update_key = false;
+	extent_op->is_data = is_data ? true : false;
 	extent_op->level = level;
 
 	ret = btrfs_add_delayed_extent_op(root->fs_info, trans, bytenr,
@@ -3328,7 +3347,7 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group,
 	 * If this block group is smaller than 100 megs don't bother caching the
 	 * block group.
 	 */
-	if (block_group->key.offset < (100 * 1024 * 1024)) {
+	if (block_group->key.offset < (100 * SZ_1M)) {
 		spin_lock(&block_group->lock);
 		block_group->disk_cache_state = BTRFS_DC_WRITTEN;
 		spin_unlock(&block_group->lock);
@@ -3428,12 +3447,12 @@ again:
 	 * taking up quite a bit since it's not folded into the other space
 	 * cache.
 	 */
-	num_pages = div_u64(block_group->key.offset, 256 * 1024 * 1024);
+	num_pages = div_u64(block_group->key.offset, SZ_256M);
 	if (!num_pages)
 		num_pages = 1;
 
 	num_pages *= 16;
-	num_pages *= PAGE_CACHE_SIZE;
+	num_pages *= PAGE_SIZE;
 
 	ret = btrfs_check_data_free_space(inode, 0, num_pages);
 	if (ret)
@@ -3684,11 +3703,21 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 
 	/*
-	 * We don't need the lock here since we are protected by the transaction
-	 * commit.  We want to do the cache_save_setup first and then run the
+	 * Even though we are in the critical section of the transaction commit,
+	 * we can still have concurrent tasks adding elements to this
+	 * transaction's list of dirty block groups. These tasks correspond to
+	 * endio free space workers started when writeback finishes for a
+	 * space cache, which run inode.c:btrfs_finish_ordered_io(), and can
+	 * allocate new block groups as a result of COWing nodes of the root
+	 * tree when updating the free space inode. The writeback for the space
+	 * caches is triggered by an earlier call to
+	 * btrfs_start_dirty_block_groups() and iterations of the following
+	 * loop.
+	 * Also we want to do the cache_save_setup first and then run the
 	 * delayed refs to make sure we have the best chance at doing this all
 	 * in one shot.
 	 */
+	spin_lock(&cur_trans->dirty_bgs_lock);
 	while (!list_empty(&cur_trans->dirty_bgs)) {
 		cache = list_first_entry(&cur_trans->dirty_bgs,
 					 struct btrfs_block_group_cache,
@@ -3700,11 +3729,13 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans,
 		 * finish and then do it all again
 		 */
 		if (!list_empty(&cache->io_list)) {
+			spin_unlock(&cur_trans->dirty_bgs_lock);
 			list_del_init(&cache->io_list);
 			btrfs_wait_cache_io(root, trans, cache,
 					    &cache->io_ctl, path,
 					    cache->key.objectid);
 			btrfs_put_block_group(cache);
+			spin_lock(&cur_trans->dirty_bgs_lock);
 		}
 
 		/*
@@ -3712,6 +3743,7 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans,
 		 * on any pending IO
 		 */
 		list_del_init(&cache->dirty_list);
+		spin_unlock(&cur_trans->dirty_bgs_lock);
 		should_put = 1;
 
 		cache_save_setup(cache, trans, path);
@@ -3736,6 +3768,25 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans,
 		}
 		if (!ret) {
 			ret = write_one_cache_group(trans, root, path, cache);
+			/*
+			 * One of the free space endio workers might have
+			 * created a new block group while updating a free space
+			 * cache's inode (at inode.c:btrfs_finish_ordered_io())
+			 * and hasn't released its transaction handle yet, in
+			 * which case the new block group is still attached to
+			 * its transaction handle and its creation has not
+			 * finished yet (no block group item in the extent tree
+			 * yet, etc). If this is the case, wait for all free
+			 * space endio workers to finish and retry. This is a
+			 * a very rare case so no need for a more efficient and
+			 * complex approach.
+			 */
+			if (ret == -ENOENT) {
+				wait_event(cur_trans->writer_wait,
+				   atomic_read(&cur_trans->num_writers) == 1);
+				ret = write_one_cache_group(trans, root, path,
+							    cache);
+			}
 			if (ret)
 				btrfs_abort_transaction(trans, root, ret);
 		}
@@ -3743,7 +3794,9 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans,
 		/* if its not on the io list, we need to put the block group */
 		if (should_put)
 			btrfs_put_block_group(cache);
+		spin_lock(&cur_trans->dirty_bgs_lock);
 	}
+	spin_unlock(&cur_trans->dirty_bgs_lock);
 
 	while (!list_empty(io)) {
 		cache = list_first_entry(io, struct btrfs_block_group_cache,
@@ -4086,8 +4139,10 @@ commit_trans:
 		    !atomic_read(&root->fs_info->open_ioctl_trans)) {
 			need_commit--;
 
-			if (need_commit > 0)
+			if (need_commit > 0) {
+				btrfs_start_delalloc_roots(fs_info, 0, -1);
 				btrfs_wait_ordered_roots(fs_info, -1);
+			}
 
 			trans = btrfs_join_transaction(root);
 			if (IS_ERR(trans))
@@ -4100,11 +4155,12 @@ commit_trans:
 				if (ret)
 					return ret;
 				/*
-				 * make sure that all running delayed iput are
-				 * done
+				 * The cleaner kthread might still be doing iput
+				 * operations. Wait for it to finish so that
+				 * more space is released.
 				 */
-				down_write(&root->fs_info->delayed_iput_sem);
-				up_write(&root->fs_info->delayed_iput_sem);
+				mutex_lock(&root->fs_info->cleaner_delayed_iput_mutex);
+				mutex_unlock(&root->fs_info->cleaner_delayed_iput_mutex);
 				goto again;
 			} else {
 				btrfs_end_transaction(trans, root);
@@ -4239,14 +4295,13 @@ static int should_alloc_chunk(struct btrfs_root *root,
 	 */
 	if (force == CHUNK_ALLOC_LIMITED) {
 		thresh = btrfs_super_total_bytes(root->fs_info->super_copy);
-		thresh = max_t(u64, 64 * 1024 * 1024,
-			       div_factor_fine(thresh, 1));
+		thresh = max_t(u64, SZ_64M, div_factor_fine(thresh, 1));
 
 		if (num_bytes - num_allocated < thresh)
 			return 1;
 	}
 
-	if (num_allocated + 2 * 1024 * 1024 < div_factor(num_bytes, 8))
+	if (num_allocated + SZ_2M < div_factor(num_bytes, 8))
 		return 0;
 	return 1;
 }
@@ -4446,7 +4501,7 @@ out:
 	 * transaction.
 	 */
 	if (trans->can_flush_pending_bgs &&
-	    trans->chunk_bytes_reserved >= (2 * 1024 * 1024ull)) {
+	    trans->chunk_bytes_reserved >= (u64)SZ_2M) {
 		btrfs_create_pending_block_groups(trans, trans->root);
 		btrfs_trans_release_chunk_metadata(trans);
 	}
@@ -4544,7 +4599,7 @@ static inline int calc_reclaim_items_nr(struct btrfs_root *root, u64 to_reclaim)
 	return nr;
 }
 
-#define EXTENT_SIZE_PER_ITEM	(256 * 1024)
+#define EXTENT_SIZE_PER_ITEM	SZ_256K
 
 /*
  * shrink metadata reservation for delalloc
@@ -4584,7 +4639,7 @@ static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig,
 	loops = 0;
 	while (delalloc_bytes && loops < 3) {
 		max_reclaim = min(delalloc_bytes, to_reclaim);
-		nr_pages = max_reclaim >> PAGE_CACHE_SHIFT;
+		nr_pages = max_reclaim >> PAGE_SHIFT;
 		btrfs_writeback_inodes_sb_nr(root, nr_pages, items);
 		/*
 		 * We need to wait for the async pages to actually start before
@@ -4749,8 +4804,7 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_root *root,
 	u64 expected;
 	u64 to_reclaim;
 
-	to_reclaim = min_t(u64, num_online_cpus() * 1024 * 1024,
-				16 * 1024 * 1024);
+	to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M);
 	spin_lock(&space_info->lock);
 	if (can_overcommit(root, space_info, to_reclaim,
 			   BTRFS_RESERVE_FLUSH_ALL)) {
@@ -4761,8 +4815,7 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_root *root,
 	used = space_info->bytes_used + space_info->bytes_reserved +
 	       space_info->bytes_pinned + space_info->bytes_readonly +
 	       space_info->bytes_may_use;
-	if (can_overcommit(root, space_info, 1024 * 1024,
-			   BTRFS_RESERVE_FLUSH_ALL))
+	if (can_overcommit(root, space_info, SZ_1M, BTRFS_RESERVE_FLUSH_ALL))
 		expected = div_factor_fine(space_info->total_bytes, 95);
 	else
 		expected = div_factor_fine(space_info->total_bytes, 90);
@@ -4785,7 +4838,7 @@ static inline int need_do_async_reclaim(struct btrfs_space_info *space_info,
 	u64 thresh = div_factor_fine(space_info->total_bytes, 98);
 
 	/* If we're just plain full then async reclaim just slows us down. */
-	if (space_info->bytes_used >= thresh)
+	if ((space_info->bytes_used + space_info->bytes_reserved) >= thresh)
 		return 0;
 
 	return (used >= thresh && !btrfs_fs_closing(fs_info) &&
@@ -5318,29 +5371,35 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
 	spin_lock(&sinfo->lock);
 	spin_lock(&block_rsv->lock);
 
-	block_rsv->size = min_t(u64, num_bytes, 512 * 1024 * 1024);
-
-	num_bytes = sinfo->bytes_used + sinfo->bytes_pinned +
-		    sinfo->bytes_reserved + sinfo->bytes_readonly +
-		    sinfo->bytes_may_use;
-
-	if (sinfo->total_bytes > num_bytes) {
-		num_bytes = sinfo->total_bytes - num_bytes;
-		block_rsv->reserved += num_bytes;
-		sinfo->bytes_may_use += num_bytes;
-		trace_btrfs_space_reservation(fs_info, "space_info",
-				      sinfo->flags, num_bytes, 1);
-	}
-
-	if (block_rsv->reserved >= block_rsv->size) {
+	block_rsv->size = min_t(u64, num_bytes, SZ_512M);
+
+	if (block_rsv->reserved < block_rsv->size) {
+		num_bytes = sinfo->bytes_used + sinfo->bytes_pinned +
+			sinfo->bytes_reserved + sinfo->bytes_readonly +
+			sinfo->bytes_may_use;
+		if (sinfo->total_bytes > num_bytes) {
+			num_bytes = sinfo->total_bytes - num_bytes;
+			num_bytes = min(num_bytes,
+					block_rsv->size - block_rsv->reserved);
+			block_rsv->reserved += num_bytes;
+			sinfo->bytes_may_use += num_bytes;
+			trace_btrfs_space_reservation(fs_info, "space_info",
+						      sinfo->flags, num_bytes,
+						      1);
+		}
+	} else if (block_rsv->reserved > block_rsv->size) {
 		num_bytes = block_rsv->reserved - block_rsv->size;
 		sinfo->bytes_may_use -= num_bytes;
 		trace_btrfs_space_reservation(fs_info, "space_info",
 				      sinfo->flags, num_bytes, 0);
 		block_rsv->reserved = block_rsv->size;
-		block_rsv->full = 1;
 	}
 
+	if (block_rsv->reserved == block_rsv->size)
+		block_rsv->full = 1;
+	else
+		block_rsv->full = 0;
+
 	spin_unlock(&block_rsv->lock);
 	spin_unlock(&sinfo->lock);
 }
@@ -5699,7 +5758,7 @@ out_fail:
 
 		/*
 		 * This is tricky, but first we need to figure out how much we
-		 * free'd from any free-ers that occured during this
+		 * free'd from any free-ers that occurred during this
 		 * reservation, so we reset ->csum_bytes to the csum_bytes
 		 * before we dropped our lock, and then call the free for the
 		 * number of bytes that were freed while we were trying our
@@ -5915,19 +5974,6 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 			set_extent_dirty(info->pinned_extents,
 					 bytenr, bytenr + num_bytes - 1,
 					 GFP_NOFS | __GFP_NOFAIL);
-			/*
-			 * No longer have used bytes in this block group, queue
-			 * it for deletion.
-			 */
-			if (old_val == 0) {
-				spin_lock(&info->unused_bgs_lock);
-				if (list_empty(&cache->bg_list)) {
-					btrfs_get_block_group(cache);
-					list_add_tail(&cache->bg_list,
-						      &info->unused_bgs);
-				}
-				spin_unlock(&info->unused_bgs_lock);
-			}
 		}
 
 		spin_lock(&trans->transaction->dirty_bgs_lock);
@@ -5939,6 +5985,22 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 		}
 		spin_unlock(&trans->transaction->dirty_bgs_lock);
 
+		/*
+		 * No longer have used bytes in this block group, queue it for
+		 * deletion. We do this after adding the block group to the
+		 * dirty list to avoid races between cleaner kthread and space
+		 * cache writeout.
+		 */
+		if (!alloc && old_val == 0) {
+			spin_lock(&info->unused_bgs_lock);
+			if (list_empty(&cache->bg_list)) {
+				btrfs_get_block_group(cache);
+				list_add_tail(&cache->bg_list,
+					      &info->unused_bgs);
+			}
+			spin_unlock(&info->unused_bgs_lock);
+		}
+
 		btrfs_put_block_group(cache);
 		total -= num_bytes;
 		bytenr += num_bytes;
@@ -6219,11 +6281,11 @@ fetch_cluster_info(struct btrfs_root *root, struct btrfs_space_info *space_info,
 		return ret;
 
 	if (ssd)
-		*empty_cluster = 2 * 1024 * 1024;
+		*empty_cluster = SZ_2M;
 	if (space_info->flags & BTRFS_BLOCK_GROUP_METADATA) {
 		ret = &root->fs_info->meta_alloc_cluster;
 		if (!ssd)
-			*empty_cluster = 64 * 1024;
+			*empty_cluster = SZ_64K;
 	} else if ((space_info->flags & BTRFS_BLOCK_GROUP_DATA) && ssd) {
 		ret = &root->fs_info->data_alloc_cluster;
 	}
@@ -6435,7 +6497,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	path->reada = 1;
+	path->reada = READA_FORWARD;
 	path->leave_spinning = 1;
 
 	is_data = owner_objectid >= BTRFS_FIRST_FREE_OBJECTID;
@@ -6658,6 +6720,13 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 			}
 		}
 
+		ret = add_to_free_space_tree(trans, root->fs_info, bytenr,
+					     num_bytes);
+		if (ret) {
+			btrfs_abort_transaction(trans, extent_root, ret);
+			goto out;
+		}
+
 		ret = update_block_group(trans, root, bytenr, num_bytes, 0);
 		if (ret) {
 			btrfs_abort_transaction(trans, extent_root, ret);
@@ -6955,7 +7024,7 @@ btrfs_lock_cluster(struct btrfs_block_group_cache *block_group,
 		   struct btrfs_free_cluster *cluster,
 		   int delalloc)
 {
-	struct btrfs_block_group_cache *used_bg;
+	struct btrfs_block_group_cache *used_bg = NULL;
 	bool locked = false;
 again:
 	spin_lock(&cluster->refill_lock);
@@ -7669,6 +7738,11 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(path->nodes[0]);
 	btrfs_free_path(path);
 
+	ret = remove_from_free_space_tree(trans, fs_info, ins->objectid,
+					  ins->offset);
+	if (ret)
+		return ret;
+
 	ret = update_block_group(trans, root, ins->objectid, ins->offset, 1);
 	if (ret) { /* -ENOENT, logic error */
 		btrfs_err(fs_info, "update block group failed for %llu %llu",
@@ -7749,6 +7823,11 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(leaf);
 	btrfs_free_path(path);
 
+	ret = remove_from_free_space_tree(trans, fs_info, ins->objectid,
+					  num_bytes);
+	if (ret)
+		return ret;
+
 	ret = update_block_group(trans, root, ins->objectid, root->nodesize,
 				 1);
 	if (ret) { /* -ENOENT, logic error */
@@ -7831,7 +7910,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);
 
 	btrfs_set_lock_blocking(buf);
-	btrfs_set_buffer_uptodate(buf);
+	set_extent_buffer_uptodate(buf);
 
 	if (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID) {
 		buf->log_index = root->log_transid % 2;
@@ -7977,12 +8056,9 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 		else
 			memset(&extent_op->key, 0, sizeof(extent_op->key));
 		extent_op->flags_to_set = flags;
-		if (skinny_metadata)
-			extent_op->update_key = 0;
-		else
-			extent_op->update_key = 1;
-		extent_op->update_flags = 1;
-		extent_op->is_data = 0;
+		extent_op->update_key = skinny_metadata ? false : true;
+		extent_op->update_flags = true;
+		extent_op->is_data = false;
 		extent_op->level = level;
 
 		ret = btrfs_add_delayed_tree_ref(root->fs_info, trans,
@@ -8105,21 +8181,47 @@ reada:
 }
 
 /*
- * TODO: Modify related function to add related node/leaf to dirty_extent_root,
- * for later qgroup accounting.
- *
- * Current, this function does nothing.
+ * These may not be seen by the usual inc/dec ref code so we have to
+ * add them here.
  */
+static int record_one_subtree_extent(struct btrfs_trans_handle *trans,
+				     struct btrfs_root *root, u64 bytenr,
+				     u64 num_bytes)
+{
+	struct btrfs_qgroup_extent_record *qrecord;
+	struct btrfs_delayed_ref_root *delayed_refs;
+
+	qrecord = kmalloc(sizeof(*qrecord), GFP_NOFS);
+	if (!qrecord)
+		return -ENOMEM;
+
+	qrecord->bytenr = bytenr;
+	qrecord->num_bytes = num_bytes;
+	qrecord->old_roots = NULL;
+
+	delayed_refs = &trans->transaction->delayed_refs;
+	spin_lock(&delayed_refs->lock);
+	if (btrfs_qgroup_insert_dirty_extent(delayed_refs, qrecord))
+		kfree(qrecord);
+	spin_unlock(&delayed_refs->lock);
+
+	return 0;
+}
+
 static int account_leaf_items(struct btrfs_trans_handle *trans,
 			      struct btrfs_root *root,
 			      struct extent_buffer *eb)
 {
 	int nr = btrfs_header_nritems(eb);
-	int i, extent_type;
+	int i, extent_type, ret;
 	struct btrfs_key key;
 	struct btrfs_file_extent_item *fi;
 	u64 bytenr, num_bytes;
 
+	/* We can be called directly from walk_up_proc() */
+	if (!root->fs_info->quota_enabled)
+		return 0;
+
 	for (i = 0; i < nr; i++) {
 		btrfs_item_key_to_cpu(eb, &key, i);
 
@@ -8138,6 +8240,10 @@ static int account_leaf_items(struct btrfs_trans_handle *trans,
 			continue;
 
 		num_bytes = btrfs_file_extent_disk_num_bytes(eb, fi);
+
+		ret = record_one_subtree_extent(trans, root, bytenr, num_bytes);
+		if (ret)
+			return ret;
 	}
 	return 0;
 }
@@ -8206,8 +8312,6 @@ static int adjust_slots_upwards(struct btrfs_root *root,
 
 /*
  * root_eb is the subtree root and is locked before this function is called.
- * TODO: Modify this function to mark all (including complete shared node)
- * to dirty_extent_root to allow it get accounted in qgroup.
  */
 static int account_shared_subtree(struct btrfs_trans_handle *trans,
 				  struct btrfs_root *root,
@@ -8285,6 +8389,11 @@ walk_down:
 			btrfs_tree_read_lock(eb);
 			btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
 			path->locks[level] = BTRFS_READ_LOCK_BLOCKING;
+
+			ret = record_one_subtree_extent(trans, root, child_bytenr,
+							root->nodesize);
+			if (ret)
+				goto out;
 		}
 
 		if (level == 0) {
@@ -9088,7 +9197,7 @@ static int inc_block_group_ro(struct btrfs_block_group_cache *cache, int force)
 	if ((sinfo->flags &
 	     (BTRFS_BLOCK_GROUP_SYSTEM | BTRFS_BLOCK_GROUP_METADATA)) &&
 	    !force)
-		min_allocable_bytes = 1 * 1024 * 1024;
+		min_allocable_bytes = SZ_1M;
 	else
 		min_allocable_bytes = 0;
 
@@ -9277,15 +9386,23 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
 	u64 dev_min = 1;
 	u64 dev_nr = 0;
 	u64 target;
+	int debug;
 	int index;
 	int full = 0;
 	int ret = 0;
 
+	debug = btrfs_test_opt(root, ENOSPC_DEBUG);
+
 	block_group = btrfs_lookup_block_group(root->fs_info, bytenr);
 
 	/* odd, couldn't find the block group, leave it alone */
-	if (!block_group)
+	if (!block_group) {
+		if (debug)
+			btrfs_warn(root->fs_info,
+				   "can't find block group for bytenr %llu",
+				   bytenr);
 		return -1;
+	}
 
 	min_free = btrfs_block_group_used(&block_group->item);
 
@@ -9339,8 +9456,13 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
 		 * this is just a balance, so if we were marked as full
 		 * we know there is no space for a new chunk
 		 */
-		if (full)
+		if (full) {
+			if (debug)
+				btrfs_warn(root->fs_info,
+					"no space to alloc new chunk for block group %llu",
+					block_group->key.objectid);
 			goto out;
+		}
 
 		index = get_block_group_index(block_group);
 	}
@@ -9387,6 +9509,10 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
 			ret = -1;
 		}
 	}
+	if (debug && ret == -1)
+		btrfs_warn(root->fs_info,
+			"no space to allocate a new chunk for block group %llu",
+			block_group->key.objectid);
 	mutex_unlock(&root->fs_info->chunk_mutex);
 	btrfs_end_transaction(trans, root);
 out:
@@ -9620,6 +9746,8 @@ btrfs_create_block_group_cache(struct btrfs_root *root, u64 start, u64 size)
 	cache->full_stripe_len = btrfs_full_stripe_len(root,
 					       &root->fs_info->mapping_tree,
 					       start);
+	set_free_space_tree_thresholds(cache);
+
 	atomic_set(&cache->count, 1);
 	spin_lock_init(&cache->lock);
 	init_rwsem(&cache->data_rwsem);
@@ -9631,6 +9759,7 @@ btrfs_create_block_group_cache(struct btrfs_root *root, u64 start, u64 size)
 	INIT_LIST_HEAD(&cache->io_list);
 	btrfs_init_free_space_ctl(cache);
 	atomic_set(&cache->trimming, 0);
+	mutex_init(&cache->free_space_lock);
 
 	return cache;
 }
@@ -9655,7 +9784,7 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
-	path->reada = 1;
+	path->reada = READA_FORWARD;
 
 	cache_gen = btrfs_super_cache_generation(root->fs_info->super_copy);
 	if (btrfs_test_opt(root, SPACE_CACHE) &&
@@ -9841,6 +9970,8 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans,
 					       key.objectid, key.offset);
 		if (ret)
 			btrfs_abort_transaction(trans, extent_root, ret);
+		add_block_group_free_space(trans, root->fs_info, block_group);
+		/* already aborted the transaction if it failed. */
 next:
 		list_del_init(&block_group->bg_list);
 	}
@@ -9871,6 +10002,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 	cache->flags = type;
 	cache->last_byte_to_unpin = (u64)-1;
 	cache->cached = BTRFS_CACHE_FINISHED;
+	cache->needs_free_space = 1;
 	ret = exclude_super_stripes(root, cache);
 	if (ret) {
 		/*
@@ -10241,6 +10373,10 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 
 	unlock_chunks(root);
 
+	ret = remove_block_group_free_space(trans, root->fs_info, block_group);
+	if (ret)
+		goto out;
+
 	btrfs_put_block_group(block_group);
 	btrfs_put_block_group(block_group);
 
@@ -10256,6 +10392,47 @@ out:
 	return ret;
 }
 
+struct btrfs_trans_handle *
+btrfs_start_trans_remove_block_group(struct btrfs_fs_info *fs_info,
+				     const u64 chunk_offset)
+{
+	struct extent_map_tree *em_tree = &fs_info->mapping_tree.map_tree;
+	struct extent_map *em;
+	struct map_lookup *map;
+	unsigned int num_items;
+
+	read_lock(&em_tree->lock);
+	em = lookup_extent_mapping(em_tree, chunk_offset, 1);
+	read_unlock(&em_tree->lock);
+	ASSERT(em && em->start == chunk_offset);
+
+	/*
+	 * We need to reserve 3 + N units from the metadata space info in order
+	 * to remove a block group (done at btrfs_remove_chunk() and at
+	 * btrfs_remove_block_group()), which are used for:
+	 *
+	 * 1 unit for adding the free space inode's orphan (located in the tree
+	 * of tree roots).
+	 * 1 unit for deleting the block group item (located in the extent
+	 * tree).
+	 * 1 unit for deleting the free space item (located in tree of tree
+	 * roots).
+	 * N units for deleting N device extent items corresponding to each
+	 * stripe (located in the device tree).
+	 *
+	 * In order to remove a block group we also need to reserve units in the
+	 * system space info in order to update the chunk tree (update one or
+	 * more device items and remove one chunk item), but this is done at
+	 * btrfs_remove_chunk() through a call to check_system_chunk().
+	 */
+	map = em->map_lookup;
+	num_items = 3 + map->num_stripes;
+	free_extent_map(em);
+
+	return btrfs_start_transaction_fallback_global_rsv(fs_info->extent_root,
+							   num_items, 1);
+}
+
 /*
  * Process the unused_bgs list and remove any that don't have any allocated
  * space inside of them.
@@ -10279,22 +10456,25 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		block_group = list_first_entry(&fs_info->unused_bgs,
 					       struct btrfs_block_group_cache,
 					       bg_list);
-		space_info = block_group->space_info;
 		list_del_init(&block_group->bg_list);
+
+		space_info = block_group->space_info;
+
 		if (ret || btrfs_mixed_space_info(space_info)) {
 			btrfs_put_block_group(block_group);
 			continue;
 		}
 		spin_unlock(&fs_info->unused_bgs_lock);
 
-		mutex_lock(&root->fs_info->delete_unused_bgs_mutex);
+		mutex_lock(&fs_info->delete_unused_bgs_mutex);
 
 		/* Don't want to race with allocators so take the groups_sem */
 		down_write(&space_info->groups_sem);
 		spin_lock(&block_group->lock);
 		if (block_group->reserved ||
 		    btrfs_block_group_used(&block_group->item) ||
-		    block_group->ro) {
+		    block_group->ro ||
+		    list_is_singular(&block_group->list)) {
 			/*
 			 * We want to bail if we made new allocations or have
 			 * outstanding allocations in this block group.  We do
@@ -10319,8 +10499,8 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		 * Want to do this before we do anything else so we can recover
 		 * properly if we fail to join the transaction.
 		 */
-		/* 1 for btrfs_orphan_reserve_metadata() */
-		trans = btrfs_start_transaction(root, 1);
+		trans = btrfs_start_trans_remove_block_group(fs_info,
+						     block_group->key.objectid);
 		if (IS_ERR(trans)) {
 			btrfs_dec_block_group_ro(root, block_group);
 			ret = PTR_ERR(trans);
@@ -10400,17 +10580,21 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		 * until transaction commit to do the actual discard.
 		 */
 		if (trimming) {
-			WARN_ON(!list_empty(&block_group->bg_list));
-			spin_lock(&trans->transaction->deleted_bgs_lock);
+			spin_lock(&fs_info->unused_bgs_lock);
+			/*
+			 * A concurrent scrub might have added us to the list
+			 * fs_info->unused_bgs, so use a list_move operation
+			 * to add the block group to the deleted_bgs list.
+			 */
 			list_move(&block_group->bg_list,
 				  &trans->transaction->deleted_bgs);
-			spin_unlock(&trans->transaction->deleted_bgs_lock);
+			spin_unlock(&fs_info->unused_bgs_lock);
 			btrfs_get_block_group(block_group);
 		}
 end_trans:
 		btrfs_end_transaction(trans, root);
 next:
-		mutex_unlock(&root->fs_info->delete_unused_bgs_mutex);
+		mutex_unlock(&fs_info->delete_unused_bgs_mutex);
 		btrfs_put_block_group(block_group);
 		spin_lock(&fs_info->unused_bgs_lock);
 	}
@@ -10428,7 +10612,7 @@ int btrfs_init_space_info(struct btrfs_fs_info *fs_info)
 
 	disk_super = fs_info->super_copy;
 	if (!btrfs_super_root(disk_super))
-		return 1;
+		return -EINVAL;
 
 	features = btrfs_super_incompat_flags(disk_super);
 	if (features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS)
@@ -10658,3 +10842,23 @@ int btrfs_start_write_no_snapshoting(struct btrfs_root *root)
 	}
 	return 1;
 }
+
+static int wait_snapshoting_atomic_t(atomic_t *a)
+{
+	schedule();
+	return 0;
+}
+
+void btrfs_wait_for_snapshot_creation(struct btrfs_root *root)
+{
+	while (true) {
+		int ret;
+
+		ret = btrfs_start_write_no_snapshoting(root);
+		if (ret)
+			break;
+		wait_on_atomic_t(&root->will_be_snapshoted,
+				 wait_snapshoting_atomic_t,
+				 TASK_UNINTERRUPTIBLE);
+	}
+}
diff --git a/fs/btrfs/extent-tree.h b/fs/btrfs/extent-tree.h
deleted file mode 100644
index e69de29bb2d1..000000000000
--- a/fs/btrfs/extent-tree.h
+++ /dev/null
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 33a01ea41465..d247fc0eea19 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -206,10 +206,8 @@ void extent_io_exit(void)
 	 * destroy caches.
 	 */
 	rcu_barrier();
-	if (extent_state_cache)
-		kmem_cache_destroy(extent_state_cache);
-	if (extent_buffer_cache)
-		kmem_cache_destroy(extent_buffer_cache);
+	kmem_cache_destroy(extent_state_cache);
+	kmem_cache_destroy(extent_buffer_cache);
 	if (btrfs_bioset)
 		bioset_free(btrfs_bioset);
 }
@@ -232,7 +230,7 @@ static struct extent_state *alloc_extent_state(gfp_t mask)
 	if (!state)
 		return state;
 	state->state = 0;
-	state->private = 0;
+	state->failrec = NULL;
 	RB_CLEAR_NODE(&state->rb_node);
 	btrfs_leak_debug_add(&state->leak_list, &states);
 	atomic_set(&state->refs, 1);
@@ -616,7 +614,7 @@ static int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	if (bits & (EXTENT_IOBITS | EXTENT_BOUNDARY))
 		clear = 1;
 again:
-	if (!prealloc && (mask & __GFP_WAIT)) {
+	if (!prealloc && gfpflags_allow_blocking(mask)) {
 		/*
 		 * Don't care for allocation failure here because we might end
 		 * up not needing the pre-allocated extent state at all, which
@@ -741,7 +739,7 @@ search_again:
 	if (start > end)
 		goto out;
 	spin_unlock(&tree->lock);
-	if (mask & __GFP_WAIT)
+	if (gfpflags_allow_blocking(mask))
 		cond_resched();
 	goto again;
 }
@@ -874,7 +872,7 @@ __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 
 	bits |= EXTENT_FIRST_DELALLOC;
 again:
-	if (!prealloc && (mask & __GFP_WAIT)) {
+	if (!prealloc && gfpflags_allow_blocking(mask)) {
 		prealloc = alloc_extent_state(mask);
 		BUG_ON(!prealloc);
 	}
@@ -1052,7 +1050,7 @@ search_again:
 	if (start > end)
 		goto out;
 	spin_unlock(&tree->lock);
-	if (mask & __GFP_WAIT)
+	if (gfpflags_allow_blocking(mask))
 		cond_resched();
 	goto again;
 }
@@ -1100,7 +1098,7 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	btrfs_debug_check_extent_io_range(tree, start, end);
 
 again:
-	if (!prealloc && (mask & __GFP_WAIT)) {
+	if (!prealloc && gfpflags_allow_blocking(mask)) {
 		/*
 		 * Best effort, don't worry if extent state allocation fails
 		 * here for the first iteration. We might have a cached state
@@ -1278,27 +1276,13 @@ search_again:
 	if (start > end)
 		goto out;
 	spin_unlock(&tree->lock);
-	if (mask & __GFP_WAIT)
+	if (gfpflags_allow_blocking(mask))
 		cond_resched();
 	first_iteration = false;
 	goto again;
 }
 
 /* wrappers around set/clear extent bit */
-int set_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end,
-		     gfp_t mask)
-{
-	return set_extent_bit(tree, start, end, EXTENT_DIRTY, NULL,
-			      NULL, mask);
-}
-
-int set_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-		    unsigned bits, gfp_t mask)
-{
-	return set_extent_bit(tree, start, end, bits, NULL,
-			      NULL, mask);
-}
-
 int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 			   unsigned bits, gfp_t mask,
 			   struct extent_changeset *changeset)
@@ -1323,17 +1307,6 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 				  cached, mask, NULL);
 }
 
-int clear_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-		      unsigned bits, gfp_t mask)
-{
-	int wake = 0;
-
-	if (bits & EXTENT_LOCKED)
-		wake = 1;
-
-	return clear_extent_bit(tree, start, end, bits, wake, 0, NULL, mask);
-}
-
 int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 			     unsigned bits, gfp_t mask,
 			     struct extent_changeset *changeset)
@@ -1348,63 +1321,18 @@ int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 				  changeset);
 }
 
-int set_extent_delalloc(struct extent_io_tree *tree, u64 start, u64 end,
-			struct extent_state **cached_state, gfp_t mask)
-{
-	return set_extent_bit(tree, start, end,
-			      EXTENT_DELALLOC | EXTENT_UPTODATE,
-			      NULL, cached_state, mask);
-}
-
-int set_extent_defrag(struct extent_io_tree *tree, u64 start, u64 end,
-		      struct extent_state **cached_state, gfp_t mask)
-{
-	return set_extent_bit(tree, start, end,
-			      EXTENT_DELALLOC | EXTENT_UPTODATE | EXTENT_DEFRAG,
-			      NULL, cached_state, mask);
-}
-
-int clear_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end,
-		       gfp_t mask)
-{
-	return clear_extent_bit(tree, start, end,
-				EXTENT_DIRTY | EXTENT_DELALLOC |
-				EXTENT_DO_ACCOUNTING, 0, 0, NULL, mask);
-}
-
-int set_extent_new(struct extent_io_tree *tree, u64 start, u64 end,
-		     gfp_t mask)
-{
-	return set_extent_bit(tree, start, end, EXTENT_NEW, NULL,
-			      NULL, mask);
-}
-
-int set_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end,
-			struct extent_state **cached_state, gfp_t mask)
-{
-	return set_extent_bit(tree, start, end, EXTENT_UPTODATE, NULL,
-			      cached_state, mask);
-}
-
-int clear_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end,
-			  struct extent_state **cached_state, gfp_t mask)
-{
-	return clear_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, 0,
-				cached_state, mask);
-}
-
 /*
  * either insert or lock state struct between start and end use mask to tell
  * us if waiting is desired.
  */
 int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-		     unsigned bits, struct extent_state **cached_state)
+		     struct extent_state **cached_state)
 {
 	int err;
 	u64 failed_start;
 
 	while (1) {
-		err = __set_extent_bit(tree, start, end, EXTENT_LOCKED | bits,
+		err = __set_extent_bit(tree, start, end, EXTENT_LOCKED,
 				       EXTENT_LOCKED, &failed_start,
 				       cached_state, GFP_NOFS, NULL);
 		if (err == -EEXIST) {
@@ -1417,11 +1345,6 @@ int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 	return err;
 }
 
-int lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
-{
-	return lock_extent_bits(tree, start, end, 0, NULL);
-}
-
 int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
 {
 	int err;
@@ -1438,39 +1361,25 @@ int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
 	return 1;
 }
 
-int unlock_extent_cached(struct extent_io_tree *tree, u64 start, u64 end,
-			 struct extent_state **cached, gfp_t mask)
+void extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end)
 {
-	return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
-				mask);
-}
-
-int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end)
-{
-	return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, NULL,
-				GFP_NOFS);
-}
-
-int extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end)
-{
-	unsigned long index = start >> PAGE_CACHE_SHIFT;
-	unsigned long end_index = end >> PAGE_CACHE_SHIFT;
+	unsigned long index = start >> PAGE_SHIFT;
+	unsigned long end_index = end >> PAGE_SHIFT;
 	struct page *page;
 
 	while (index <= end_index) {
 		page = find_get_page(inode->i_mapping, index);
 		BUG_ON(!page); /* Pages should be in the extent_io_tree */
 		clear_page_dirty_for_io(page);
-		page_cache_release(page);
+		put_page(page);
 		index++;
 	}
-	return 0;
 }
 
-int extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end)
+void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end)
 {
-	unsigned long index = start >> PAGE_CACHE_SHIFT;
-	unsigned long end_index = end >> PAGE_CACHE_SHIFT;
+	unsigned long index = start >> PAGE_SHIFT;
+	unsigned long end_index = end >> PAGE_SHIFT;
 	struct page *page;
 
 	while (index <= end_index) {
@@ -1478,29 +1387,27 @@ int extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end)
 		BUG_ON(!page); /* Pages should be in the extent_io_tree */
 		__set_page_dirty_nobuffers(page);
 		account_page_redirty(page);
-		page_cache_release(page);
+		put_page(page);
 		index++;
 	}
-	return 0;
 }
 
 /*
  * helper function to set both pages and extents in the tree writeback
  */
-static int set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end)
+static void set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end)
 {
-	unsigned long index = start >> PAGE_CACHE_SHIFT;
-	unsigned long end_index = end >> PAGE_CACHE_SHIFT;
+	unsigned long index = start >> PAGE_SHIFT;
+	unsigned long end_index = end >> PAGE_SHIFT;
 	struct page *page;
 
 	while (index <= end_index) {
 		page = find_get_page(tree->mapping, index);
 		BUG_ON(!page); /* Pages should be in the extent_io_tree */
 		set_page_writeback(page);
-		page_cache_release(page);
+		put_page(page);
 		index++;
 	}
-	return 0;
 }
 
 /* find the first state struct with 'bits' set after 'start', and
@@ -1649,8 +1556,8 @@ static noinline void __unlock_for_delalloc(struct inode *inode,
 {
 	int ret;
 	struct page *pages[16];
-	unsigned long index = start >> PAGE_CACHE_SHIFT;
-	unsigned long end_index = end >> PAGE_CACHE_SHIFT;
+	unsigned long index = start >> PAGE_SHIFT;
+	unsigned long end_index = end >> PAGE_SHIFT;
 	unsigned long nr_pages = end_index - index + 1;
 	int i;
 
@@ -1664,7 +1571,7 @@ static noinline void __unlock_for_delalloc(struct inode *inode,
 		for (i = 0; i < ret; i++) {
 			if (pages[i] != locked_page)
 				unlock_page(pages[i]);
-			page_cache_release(pages[i]);
+			put_page(pages[i]);
 		}
 		nr_pages -= ret;
 		index += ret;
@@ -1677,9 +1584,9 @@ static noinline int lock_delalloc_pages(struct inode *inode,
 					u64 delalloc_start,
 					u64 delalloc_end)
 {
-	unsigned long index = delalloc_start >> PAGE_CACHE_SHIFT;
+	unsigned long index = delalloc_start >> PAGE_SHIFT;
 	unsigned long start_index = index;
-	unsigned long end_index = delalloc_end >> PAGE_CACHE_SHIFT;
+	unsigned long end_index = delalloc_end >> PAGE_SHIFT;
 	unsigned long pages_locked = 0;
 	struct page *pages[16];
 	unsigned long nrpages;
@@ -1712,11 +1619,11 @@ static noinline int lock_delalloc_pages(struct inode *inode,
 				    pages[i]->mapping != inode->i_mapping) {
 					ret = -EAGAIN;
 					unlock_page(pages[i]);
-					page_cache_release(pages[i]);
+					put_page(pages[i]);
 					goto done;
 				}
 			}
-			page_cache_release(pages[i]);
+			put_page(pages[i]);
 			pages_locked++;
 		}
 		nrpages -= ret;
@@ -1729,7 +1636,7 @@ done:
 		__unlock_for_delalloc(inode, locked_page,
 			      delalloc_start,
 			      ((u64)(start_index + pages_locked - 1)) <<
-			      PAGE_CACHE_SHIFT);
+			      PAGE_SHIFT);
 	}
 	return ret;
 }
@@ -1789,7 +1696,7 @@ again:
 		free_extent_state(cached_state);
 		cached_state = NULL;
 		if (!loops) {
-			max_bytes = PAGE_CACHE_SIZE;
+			max_bytes = PAGE_SIZE;
 			loops = 1;
 			goto again;
 		} else {
@@ -1800,7 +1707,7 @@ again:
 	BUG_ON(ret); /* Only valid values are 0 and -EAGAIN */
 
 	/* step three, lock the state bits for the whole range */
-	lock_extent_bits(tree, delalloc_start, delalloc_end, 0, &cached_state);
+	lock_extent_bits(tree, delalloc_start, delalloc_end, &cached_state);
 
 	/* then test to make sure it is all still delalloc */
 	ret = test_range_bit(tree, delalloc_start, delalloc_end,
@@ -1820,7 +1727,7 @@ out_failed:
 	return found;
 }
 
-int extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
+void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
 				 struct page *locked_page,
 				 unsigned clear_bits,
 				 unsigned long page_ops)
@@ -1828,14 +1735,14 @@ int extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
 	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
 	int ret;
 	struct page *pages[16];
-	unsigned long index = start >> PAGE_CACHE_SHIFT;
-	unsigned long end_index = end >> PAGE_CACHE_SHIFT;
+	unsigned long index = start >> PAGE_SHIFT;
+	unsigned long end_index = end >> PAGE_SHIFT;
 	unsigned long nr_pages = end_index - index + 1;
 	int i;
 
 	clear_extent_bit(tree, start, end, clear_bits, 1, 0, NULL, GFP_NOFS);
 	if (page_ops == 0)
-		return 0;
+		return;
 
 	if ((page_ops & PAGE_SET_ERROR) && nr_pages > 0)
 		mapping_set_error(inode->i_mapping, -EIO);
@@ -1850,7 +1757,7 @@ int extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
 				SetPagePrivate2(pages[i]);
 
 			if (pages[i] == locked_page) {
-				page_cache_release(pages[i]);
+				put_page(pages[i]);
 				continue;
 			}
 			if (page_ops & PAGE_CLEAR_DIRTY)
@@ -1863,13 +1770,12 @@ int extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
 				end_page_writeback(pages[i]);
 			if (page_ops & PAGE_UNLOCK)
 				unlock_page(pages[i]);
-			page_cache_release(pages[i]);
+			put_page(pages[i]);
 		}
 		nr_pages -= ret;
 		index += ret;
 		cond_resched();
 	}
-	return 0;
 }
 
 /*
@@ -1936,7 +1842,8 @@ out:
  * set the private field for a given byte offset in the tree.  If there isn't
  * an extent_state there already, this does nothing.
  */
-static int set_state_private(struct extent_io_tree *tree, u64 start, u64 private)
+static noinline int set_state_failrec(struct extent_io_tree *tree, u64 start,
+		struct io_failure_record *failrec)
 {
 	struct rb_node *node;
 	struct extent_state *state;
@@ -1957,13 +1864,14 @@ static int set_state_private(struct extent_io_tree *tree, u64 start, u64 private
 		ret = -ENOENT;
 		goto out;
 	}
-	state->private = private;
+	state->failrec = failrec;
 out:
 	spin_unlock(&tree->lock);
 	return ret;
 }
 
-int get_state_private(struct extent_io_tree *tree, u64 start, u64 *private)
+static noinline int get_state_failrec(struct extent_io_tree *tree, u64 start,
+		struct io_failure_record **failrec)
 {
 	struct rb_node *node;
 	struct extent_state *state;
@@ -1984,7 +1892,7 @@ int get_state_private(struct extent_io_tree *tree, u64 start, u64 *private)
 		ret = -ENOENT;
 		goto out;
 	}
-	*private = state->private;
+	*failrec = state->failrec;
 out:
 	spin_unlock(&tree->lock);
 	return ret;
@@ -2053,7 +1961,7 @@ int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
 static void check_page_uptodate(struct extent_io_tree *tree, struct page *page)
 {
 	u64 start = page_offset(page);
-	u64 end = start + PAGE_CACHE_SIZE - 1;
+	u64 end = start + PAGE_SIZE - 1;
 	if (test_range_bit(tree, start, end, EXTENT_UPTODATE, 1, NULL))
 		SetPageUptodate(page);
 }
@@ -2064,7 +1972,7 @@ int free_io_failure(struct inode *inode, struct io_failure_record *rec)
 	int err = 0;
 	struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree;
 
-	set_state_private(failure_tree, rec->start, 0);
+	set_state_failrec(failure_tree, rec->start, NULL);
 	ret = clear_extent_bits(failure_tree, rec->start,
 				rec->start + rec->len - 1,
 				EXTENT_LOCKED | EXTENT_DIRTY, GFP_NOFS);
@@ -2163,11 +2071,11 @@ int repair_eb_io_failure(struct btrfs_root *root, struct extent_buffer *eb,
 		struct page *p = eb->pages[i];
 
 		ret = repair_io_failure(root->fs_info->btree_inode, start,
-					PAGE_CACHE_SIZE, start, p,
+					PAGE_SIZE, start, p,
 					start - page_offset(p), mirror_num);
 		if (ret)
 			break;
-		start += PAGE_CACHE_SIZE;
+		start += PAGE_SIZE;
 	}
 
 	return ret;
@@ -2181,7 +2089,6 @@ int clean_io_failure(struct inode *inode, u64 start, struct page *page,
 		     unsigned int pg_offset)
 {
 	u64 private;
-	u64 private_failure;
 	struct io_failure_record *failrec;
 	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
 	struct extent_state *state;
@@ -2194,12 +2101,11 @@ int clean_io_failure(struct inode *inode, u64 start, struct page *page,
 	if (!ret)
 		return 0;
 
-	ret = get_state_private(&BTRFS_I(inode)->io_failure_tree, start,
-				&private_failure);
+	ret = get_state_failrec(&BTRFS_I(inode)->io_failure_tree, start,
+			&failrec);
 	if (ret)
 		return 0;
 
-	failrec = (struct io_failure_record *)(unsigned long) private_failure;
 	BUG_ON(!failrec->this_mirror);
 
 	if (failrec->in_validation) {
@@ -2259,7 +2165,7 @@ void btrfs_free_io_failure_record(struct inode *inode, u64 start, u64 end)
 
 		next = next_state(state);
 
-		failrec = (struct io_failure_record *)(unsigned long)state->private;
+		failrec = state->failrec;
 		free_extent_state(state);
 		kfree(failrec);
 
@@ -2269,10 +2175,9 @@ void btrfs_free_io_failure_record(struct inode *inode, u64 start, u64 end)
 }
 
 int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
-				struct io_failure_record **failrec_ret)
+		struct io_failure_record **failrec_ret)
 {
 	struct io_failure_record *failrec;
-	u64 private;
 	struct extent_map *em;
 	struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree;
 	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
@@ -2280,7 +2185,7 @@ int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
 	int ret;
 	u64 logical;
 
-	ret = get_state_private(failure_tree, start, &private);
+	ret = get_state_failrec(failure_tree, start, &failrec);
 	if (ret) {
 		failrec = kzalloc(sizeof(*failrec), GFP_NOFS);
 		if (!failrec)
@@ -2329,8 +2234,7 @@ int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
 		ret = set_extent_bits(failure_tree, start, end,
 					EXTENT_LOCKED | EXTENT_DIRTY, GFP_NOFS);
 		if (ret >= 0)
-			ret = set_state_private(failure_tree, start,
-						(u64)(unsigned long)failrec);
+			ret = set_state_failrec(failure_tree, start, failrec);
 		/* set the bits in the inode's tree */
 		if (ret >= 0)
 			ret = set_extent_bits(tree, start, end, EXTENT_DAMAGED,
@@ -2340,7 +2244,6 @@ int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
 			return ret;
 		}
 	} else {
-		failrec = (struct io_failure_record *)(unsigned long)private;
 		pr_debug("Get IO Failure Record: (found) logical=%llu, start=%llu, len=%llu, validation=%d\n",
 			 failrec->logical, failrec->start, failrec->len,
 			 failrec->in_validation);
@@ -2516,7 +2419,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 
 /* lots and lots of room for performance fixes in the end_bio funcs */
 
-int end_extent_writepage(struct page *page, int err, u64 start, u64 end)
+void end_extent_writepage(struct page *page, int err, u64 start, u64 end)
 {
 	int uptodate = (err == 0);
 	struct extent_io_tree *tree;
@@ -2537,7 +2440,6 @@ int end_extent_writepage(struct page *page, int err, u64 start, u64 end)
 		ret = ret < 0 ? ret : -EIO;
 		mapping_set_error(page->mapping, ret);
 	}
-	return 0;
 }
 
 /*
@@ -2564,8 +2466,8 @@ static void end_bio_extent_writepage(struct bio *bio)
 		 * advance bv_offset and adjust bv_len to compensate.
 		 * Print a warning for nonzero offsets, and an error
 		 * if they don't add up to a full page.  */
-		if (bvec->bv_offset || bvec->bv_len != PAGE_CACHE_SIZE) {
-			if (bvec->bv_offset + bvec->bv_len != PAGE_CACHE_SIZE)
+		if (bvec->bv_offset || bvec->bv_len != PAGE_SIZE) {
+			if (bvec->bv_offset + bvec->bv_len != PAGE_SIZE)
 				btrfs_err(BTRFS_I(page->mapping->host)->root->fs_info,
 				   "partial page write in btrfs with offset %u and length %u",
 					bvec->bv_offset, bvec->bv_len);
@@ -2579,9 +2481,7 @@ static void end_bio_extent_writepage(struct bio *bio)
 		start = page_offset(page);
 		end = start + bvec->bv_offset + bvec->bv_len - 1;
 
-		if (end_extent_writepage(page, bio->bi_error, start, end))
-			continue;
-
+		end_extent_writepage(page, bio->bi_error, start, end);
 		end_page_writeback(page);
 	}
 
@@ -2641,8 +2541,8 @@ static void end_bio_extent_readpage(struct bio *bio)
 		 * advance bv_offset and adjust bv_len to compensate.
 		 * Print a warning for nonzero offsets, and an error
 		 * if they don't add up to a full page.  */
-		if (bvec->bv_offset || bvec->bv_len != PAGE_CACHE_SIZE) {
-			if (bvec->bv_offset + bvec->bv_len != PAGE_CACHE_SIZE)
+		if (bvec->bv_offset || bvec->bv_len != PAGE_SIZE) {
+			if (bvec->bv_offset + bvec->bv_len != PAGE_SIZE)
 				btrfs_err(BTRFS_I(page->mapping->host)->root->fs_info,
 				   "partial page read in btrfs with offset %u and length %u",
 					bvec->bv_offset, bvec->bv_len);
@@ -2698,13 +2598,13 @@ static void end_bio_extent_readpage(struct bio *bio)
 readpage_ok:
 		if (likely(uptodate)) {
 			loff_t i_size = i_size_read(inode);
-			pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
+			pgoff_t end_index = i_size >> PAGE_SHIFT;
 			unsigned off;
 
 			/* Zero out the end if this page straddles i_size */
-			off = i_size & (PAGE_CACHE_SIZE-1);
+			off = i_size & (PAGE_SIZE-1);
 			if (page->index == end_index && off)
-				zero_user_segment(page, off, PAGE_CACHE_SIZE);
+				zero_user_segment(page, off, PAGE_SIZE);
 			SetPageUptodate(page);
 		} else {
 			ClearPageUptodate(page);
@@ -2868,7 +2768,7 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
 	struct bio *bio;
 	int contig = 0;
 	int old_compressed = prev_bio_flags & EXTENT_BIO_COMPRESSED;
-	size_t page_size = min_t(size_t, size, PAGE_CACHE_SIZE);
+	size_t page_size = min_t(size_t, size, PAGE_SIZE);
 
 	if (bio_ret && *bio_ret) {
 		bio = *bio_ret;
@@ -2921,7 +2821,7 @@ static void attach_extent_buffer_page(struct extent_buffer *eb,
 {
 	if (!PagePrivate(page)) {
 		SetPagePrivate(page);
-		page_cache_get(page);
+		get_page(page);
 		set_page_private(page, (unsigned long)eb);
 	} else {
 		WARN_ON(page->private != (unsigned long)eb);
@@ -2932,7 +2832,7 @@ void set_page_extent_mapped(struct page *page)
 {
 	if (!PagePrivate(page)) {
 		SetPagePrivate(page);
-		page_cache_get(page);
+		get_page(page);
 		set_page_private(page, EXTENT_PAGE_PRIVATE);
 	}
 }
@@ -2980,7 +2880,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 {
 	struct inode *inode = page->mapping->host;
 	u64 start = page_offset(page);
-	u64 page_end = start + PAGE_CACHE_SIZE - 1;
+	u64 page_end = start + PAGE_SIZE - 1;
 	u64 end;
 	u64 cur = start;
 	u64 extent_offset;
@@ -2992,12 +2892,11 @@ static int __do_readpage(struct extent_io_tree *tree,
 	struct block_device *bdev;
 	int ret;
 	int nr = 0;
-	int parent_locked = *bio_flags & EXTENT_BIO_PARENT_LOCKED;
 	size_t pg_offset = 0;
 	size_t iosize;
 	size_t disk_io_size;
 	size_t blocksize = inode->i_sb->s_blocksize;
-	unsigned long this_bio_flag = *bio_flags & EXTENT_BIO_PARENT_LOCKED;
+	unsigned long this_bio_flag = 0;
 
 	set_page_extent_mapped(page);
 
@@ -3010,12 +2909,12 @@ static int __do_readpage(struct extent_io_tree *tree,
 		}
 	}
 
-	if (page->index == last_byte >> PAGE_CACHE_SHIFT) {
+	if (page->index == last_byte >> PAGE_SHIFT) {
 		char *userpage;
-		size_t zero_offset = last_byte & (PAGE_CACHE_SIZE - 1);
+		size_t zero_offset = last_byte & (PAGE_SIZE - 1);
 
 		if (zero_offset) {
-			iosize = PAGE_CACHE_SIZE - zero_offset;
+			iosize = PAGE_SIZE - zero_offset;
 			userpage = kmap_atomic(page);
 			memset(userpage + zero_offset, 0, iosize);
 			flush_dcache_page(page);
@@ -3023,32 +2922,30 @@ static int __do_readpage(struct extent_io_tree *tree,
 		}
 	}
 	while (cur <= end) {
-		unsigned long pnr = (last_byte >> PAGE_CACHE_SHIFT) + 1;
+		unsigned long pnr = (last_byte >> PAGE_SHIFT) + 1;
 		bool force_bio_submit = false;
 
 		if (cur >= last_byte) {
 			char *userpage;
 			struct extent_state *cached = NULL;
 
-			iosize = PAGE_CACHE_SIZE - pg_offset;
+			iosize = PAGE_SIZE - pg_offset;
 			userpage = kmap_atomic(page);
 			memset(userpage + pg_offset, 0, iosize);
 			flush_dcache_page(page);
 			kunmap_atomic(userpage);
 			set_extent_uptodate(tree, cur, cur + iosize - 1,
 					    &cached, GFP_NOFS);
-			if (!parent_locked)
-				unlock_extent_cached(tree, cur,
-						     cur + iosize - 1,
-						     &cached, GFP_NOFS);
+			unlock_extent_cached(tree, cur,
+					     cur + iosize - 1,
+					     &cached, GFP_NOFS);
 			break;
 		}
 		em = __get_extent_map(inode, page, pg_offset, cur,
 				      end - cur + 1, get_extent, em_cached);
 		if (IS_ERR_OR_NULL(em)) {
 			SetPageError(page);
-			if (!parent_locked)
-				unlock_extent(tree, cur, end);
+			unlock_extent(tree, cur, end);
 			break;
 		}
 		extent_offset = cur - em->start;
@@ -3133,12 +3030,9 @@ static int __do_readpage(struct extent_io_tree *tree,
 
 			set_extent_uptodate(tree, cur, cur + iosize - 1,
 					    &cached, GFP_NOFS);
-			if (parent_locked)
-				free_extent_state(cached);
-			else
-				unlock_extent_cached(tree, cur,
-						     cur + iosize - 1,
-						     &cached, GFP_NOFS);
+			unlock_extent_cached(tree, cur,
+					     cur + iosize - 1,
+					     &cached, GFP_NOFS);
 			cur = cur + iosize;
 			pg_offset += iosize;
 			continue;
@@ -3147,8 +3041,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 		if (test_range_bit(tree, cur, cur_end,
 				   EXTENT_UPTODATE, 1, NULL)) {
 			check_page_uptodate(tree, page);
-			if (!parent_locked)
-				unlock_extent(tree, cur, cur + iosize - 1);
+			unlock_extent(tree, cur, cur + iosize - 1);
 			cur = cur + iosize;
 			pg_offset += iosize;
 			continue;
@@ -3158,8 +3051,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 		 */
 		if (block_start == EXTENT_MAP_INLINE) {
 			SetPageError(page);
-			if (!parent_locked)
-				unlock_extent(tree, cur, cur + iosize - 1);
+			unlock_extent(tree, cur, cur + iosize - 1);
 			cur = cur + iosize;
 			pg_offset += iosize;
 			continue;
@@ -3178,8 +3070,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 			*bio_flags = this_bio_flag;
 		} else {
 			SetPageError(page);
-			if (!parent_locked)
-				unlock_extent(tree, cur, cur + iosize - 1);
+			unlock_extent(tree, cur, cur + iosize - 1);
 		}
 		cur = cur + iosize;
 		pg_offset += iosize;
@@ -3221,7 +3112,7 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
 	for (index = 0; index < nr_pages; index++) {
 		__do_readpage(tree, pages[index], get_extent, em_cached, bio,
 			      mirror_num, bio_flags, rw, prev_em_start);
-		page_cache_release(pages[index]);
+		put_page(pages[index]);
 	}
 }
 
@@ -3243,10 +3134,10 @@ static void __extent_readpages(struct extent_io_tree *tree,
 		page_start = page_offset(pages[index]);
 		if (!end) {
 			start = page_start;
-			end = start + PAGE_CACHE_SIZE - 1;
+			end = start + PAGE_SIZE - 1;
 			first_index = index;
 		} else if (end + 1 == page_start) {
-			end += PAGE_CACHE_SIZE;
+			end += PAGE_SIZE;
 		} else {
 			__do_contiguous_readpages(tree, &pages[first_index],
 						  index - first_index, start,
@@ -3254,7 +3145,7 @@ static void __extent_readpages(struct extent_io_tree *tree,
 						  bio, mirror_num, bio_flags,
 						  rw, prev_em_start);
 			start = page_start;
-			end = start + PAGE_CACHE_SIZE - 1;
+			end = start + PAGE_SIZE - 1;
 			first_index = index;
 		}
 	}
@@ -3276,12 +3167,13 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 	struct inode *inode = page->mapping->host;
 	struct btrfs_ordered_extent *ordered;
 	u64 start = page_offset(page);
-	u64 end = start + PAGE_CACHE_SIZE - 1;
+	u64 end = start + PAGE_SIZE - 1;
 	int ret;
 
 	while (1) {
 		lock_extent(tree, start, end);
-		ordered = btrfs_lookup_ordered_extent(inode, start);
+		ordered = btrfs_lookup_ordered_range(inode, start,
+						PAGE_SIZE);
 		if (!ordered)
 			break;
 		unlock_extent(tree, start, end);
@@ -3308,20 +3200,6 @@ int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
 	return ret;
 }
 
-int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page,
-				 get_extent_t *get_extent, int mirror_num)
-{
-	struct bio *bio = NULL;
-	unsigned long bio_flags = EXTENT_BIO_PARENT_LOCKED;
-	int ret;
-
-	ret = __do_readpage(tree, page, get_extent, NULL, &bio, mirror_num,
-			    &bio_flags, READ, NULL);
-	if (bio)
-		ret = submit_one_bio(READ, bio, mirror_num, bio_flags);
-	return ret;
-}
-
 static noinline void update_nr_written(struct page *page,
 				      struct writeback_control *wbc,
 				      unsigned long nr_written)
@@ -3349,7 +3227,7 @@ static noinline_for_stack int writepage_delalloc(struct inode *inode,
 			      unsigned long *nr_written)
 {
 	struct extent_io_tree *tree = epd->tree;
-	u64 page_end = delalloc_start + PAGE_CACHE_SIZE - 1;
+	u64 page_end = delalloc_start + PAGE_SIZE - 1;
 	u64 nr_delalloc;
 	u64 delalloc_to_write = 0;
 	u64 delalloc_end = 0;
@@ -3386,13 +3264,11 @@ static noinline_for_stack int writepage_delalloc(struct inode *inode,
 			goto done;
 		}
 		/*
-		 * delalloc_end is already one less than the total
-		 * length, so we don't subtract one from
-		 * PAGE_CACHE_SIZE
+		 * delalloc_end is already one less than the total length, so
+		 * we don't subtract one from PAGE_SIZE
 		 */
 		delalloc_to_write += (delalloc_end - delalloc_start +
-				      PAGE_CACHE_SIZE) >>
-				      PAGE_CACHE_SHIFT;
+				      PAGE_SIZE) >> PAGE_SHIFT;
 		delalloc_start = delalloc_end + 1;
 	}
 	if (wbc->nr_to_write < delalloc_to_write) {
@@ -3441,7 +3317,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 {
 	struct extent_io_tree *tree = epd->tree;
 	u64 start = page_offset(page);
-	u64 page_end = start + PAGE_CACHE_SIZE - 1;
+	u64 page_end = start + PAGE_SIZE - 1;
 	u64 end;
 	u64 cur = start;
 	u64 extent_offset;
@@ -3556,7 +3432,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 		if (ret) {
 			SetPageError(page);
 		} else {
-			unsigned long max_nr = (i_size >> PAGE_CACHE_SHIFT) + 1;
+			unsigned long max_nr = (i_size >> PAGE_SHIFT) + 1;
 
 			set_range_writeback(tree, cur, cur + iosize - 1);
 			if (!PageWriteback(page)) {
@@ -3599,12 +3475,12 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	struct inode *inode = page->mapping->host;
 	struct extent_page_data *epd = data;
 	u64 start = page_offset(page);
-	u64 page_end = start + PAGE_CACHE_SIZE - 1;
+	u64 page_end = start + PAGE_SIZE - 1;
 	int ret;
 	int nr = 0;
 	size_t pg_offset = 0;
 	loff_t i_size = i_size_read(inode);
-	unsigned long end_index = i_size >> PAGE_CACHE_SHIFT;
+	unsigned long end_index = i_size >> PAGE_SHIFT;
 	int write_flags;
 	unsigned long nr_written = 0;
 
@@ -3619,10 +3495,10 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 
 	ClearPageError(page);
 
-	pg_offset = i_size & (PAGE_CACHE_SIZE - 1);
+	pg_offset = i_size & (PAGE_SIZE - 1);
 	if (page->index > end_index ||
 	   (page->index == end_index && !pg_offset)) {
-		page->mapping->a_ops->invalidatepage(page, 0, PAGE_CACHE_SIZE);
+		page->mapping->a_ops->invalidatepage(page, 0, PAGE_SIZE);
 		unlock_page(page);
 		return 0;
 	}
@@ -3632,7 +3508,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 
 		userpage = kmap_atomic(page);
 		memset(userpage + pg_offset, 0,
-		       PAGE_CACHE_SIZE - pg_offset);
+		       PAGE_SIZE - pg_offset);
 		kunmap_atomic(userpage);
 		flush_dcache_page(page);
 	}
@@ -3870,7 +3746,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 		clear_page_dirty_for_io(p);
 		set_page_writeback(p);
 		ret = submit_extent_page(rw, tree, wbc, p, offset >> 9,
-					 PAGE_CACHE_SIZE, 0, bdev, &epd->bio,
+					 PAGE_SIZE, 0, bdev, &epd->bio,
 					 -1, end_bio_extent_buffer_writepage,
 					 0, epd->bio_flags, bio_flags, false);
 		epd->bio_flags = bio_flags;
@@ -3882,7 +3758,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 			ret = -EIO;
 			break;
 		}
-		offset += PAGE_CACHE_SIZE;
+		offset += PAGE_SIZE;
 		update_nr_written(p, wbc, 1);
 		unlock_page(p);
 	}
@@ -3926,8 +3802,8 @@ int btree_write_cache_pages(struct address_space *mapping,
 		index = mapping->writeback_index; /* Start from prev offset */
 		end = -1;
 	} else {
-		index = wbc->range_start >> PAGE_CACHE_SHIFT;
-		end = wbc->range_end >> PAGE_CACHE_SHIFT;
+		index = wbc->range_start >> PAGE_SHIFT;
+		end = wbc->range_end >> PAGE_SHIFT;
 		scanned = 1;
 	}
 	if (wbc->sync_mode == WB_SYNC_ALL)
@@ -4070,8 +3946,8 @@ static int extent_write_cache_pages(struct extent_io_tree *tree,
 		index = mapping->writeback_index; /* Start from prev offset */
 		end = -1;
 	} else {
-		index = wbc->range_start >> PAGE_CACHE_SHIFT;
-		end = wbc->range_end >> PAGE_CACHE_SHIFT;
+		index = wbc->range_start >> PAGE_SHIFT;
+		end = wbc->range_end >> PAGE_SHIFT;
 		scanned = 1;
 	}
 	if (wbc->sync_mode == WB_SYNC_ALL)
@@ -4205,8 +4081,8 @@ int extent_write_locked_range(struct extent_io_tree *tree, struct inode *inode,
 	int ret = 0;
 	struct address_space *mapping = inode->i_mapping;
 	struct page *page;
-	unsigned long nr_pages = (end - start + PAGE_CACHE_SIZE) >>
-		PAGE_CACHE_SHIFT;
+	unsigned long nr_pages = (end - start + PAGE_SIZE) >>
+		PAGE_SHIFT;
 
 	struct extent_page_data epd = {
 		.bio = NULL,
@@ -4224,18 +4100,18 @@ int extent_write_locked_range(struct extent_io_tree *tree, struct inode *inode,
 	};
 
 	while (start <= end) {
-		page = find_get_page(mapping, start >> PAGE_CACHE_SHIFT);
+		page = find_get_page(mapping, start >> PAGE_SHIFT);
 		if (clear_page_dirty_for_io(page))
 			ret = __extent_writepage(page, &wbc_writepages, &epd);
 		else {
 			if (tree->ops && tree->ops->writepage_end_io_hook)
 				tree->ops->writepage_end_io_hook(page, start,
-						 start + PAGE_CACHE_SIZE - 1,
+						 start + PAGE_SIZE - 1,
 						 NULL, 1);
 			unlock_page(page);
 		}
-		page_cache_release(page);
-		start += PAGE_CACHE_SIZE;
+		put_page(page);
+		start += PAGE_SIZE;
 	}
 
 	flush_epd_write_bio(&epd);
@@ -4285,7 +4161,7 @@ int extent_readpages(struct extent_io_tree *tree,
 		list_del(&page->lru);
 		if (add_to_page_cache_lru(page, mapping,
 					page->index, GFP_NOFS)) {
-			page_cache_release(page);
+			put_page(page);
 			continue;
 		}
 
@@ -4319,14 +4195,14 @@ int extent_invalidatepage(struct extent_io_tree *tree,
 {
 	struct extent_state *cached_state = NULL;
 	u64 start = page_offset(page);
-	u64 end = start + PAGE_CACHE_SIZE - 1;
+	u64 end = start + PAGE_SIZE - 1;
 	size_t blocksize = page->mapping->host->i_sb->s_blocksize;
 
 	start += ALIGN(offset, blocksize);
 	if (start > end)
 		return 0;
 
-	lock_extent_bits(tree, start, end, 0, &cached_state);
+	lock_extent_bits(tree, start, end, &cached_state);
 	wait_on_page_writeback(page);
 	clear_extent_bit(tree, start, end,
 			 EXTENT_LOCKED | EXTENT_DIRTY | EXTENT_DELALLOC |
@@ -4345,7 +4221,7 @@ static int try_release_extent_state(struct extent_map_tree *map,
 				    struct page *page, gfp_t mask)
 {
 	u64 start = page_offset(page);
-	u64 end = start + PAGE_CACHE_SIZE - 1;
+	u64 end = start + PAGE_SIZE - 1;
 	int ret = 1;
 
 	if (test_range_bit(tree, start, end,
@@ -4384,10 +4260,10 @@ int try_release_extent_mapping(struct extent_map_tree *map,
 {
 	struct extent_map *em;
 	u64 start = page_offset(page);
-	u64 end = start + PAGE_CACHE_SIZE - 1;
+	u64 end = start + PAGE_SIZE - 1;
 
-	if ((mask & __GFP_WAIT) &&
-	    page->mapping->host->i_size > 16 * 1024 * 1024) {
+	if (gfpflags_allow_blocking(mask) &&
+	    page->mapping->host->i_size > SZ_16M) {
 		u64 len;
 		while (start <= end) {
 			len = end - start + 1;
@@ -4536,7 +4412,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		last_for_get_extent = isize;
 	}
 
-	lock_extent_bits(&BTRFS_I(inode)->io_tree, start, start + len - 1, 0,
+	lock_extent_bits(&BTRFS_I(inode)->io_tree, start, start + len - 1,
 			 &cached_state);
 
 	em = get_extent_skip_holes(inode, start, last_for_get_extent,
@@ -4709,14 +4585,14 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb)
 			ClearPagePrivate(page);
 			set_page_private(page, 0);
 			/* One for the page private */
-			page_cache_release(page);
+			put_page(page);
 		}
 
 		if (mapped)
 			spin_unlock(&page->mapping->private_lock);
 
 		/* One for when we alloced the page */
-		page_cache_release(page);
+		put_page(page);
 	} while (index != 0);
 }
 
@@ -4797,24 +4673,14 @@ struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src)
 	return new;
 }
 
-struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
-						u64 start)
+struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
+						  u64 start, unsigned long len)
 {
 	struct extent_buffer *eb;
-	unsigned long len;
 	unsigned long num_pages;
 	unsigned long i;
 
-	if (!fs_info) {
-		/*
-		 * Called only from tests that don't always have a fs_info
-		 * available, but we know that nodesize is 4096
-		 */
-		len = 4096;
-	} else {
-		len = fs_info->tree_root->nodesize;
-	}
-	num_pages = num_extent_pages(0, len);
+	num_pages = num_extent_pages(start, len);
 
 	eb = __alloc_extent_buffer(fs_info, start, len);
 	if (!eb)
@@ -4837,6 +4703,24 @@ err:
 	return NULL;
 }
 
+struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
+						u64 start)
+{
+	unsigned long len;
+
+	if (!fs_info) {
+		/*
+		 * Called only from tests that don't always have a fs_info
+		 * available, but we know that nodesize is 4096
+		 */
+		len = 4096;
+	} else {
+		len = fs_info->tree_root->nodesize;
+	}
+
+	return __alloc_dummy_extent_buffer(fs_info, start, len);
+}
+
 static void check_buffer_tree_ref(struct extent_buffer *eb)
 {
 	int refs;
@@ -4893,7 +4777,7 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
 
 	rcu_read_lock();
 	eb = radix_tree_lookup(&fs_info->buffer_radix,
-			       start >> PAGE_CACHE_SHIFT);
+			       start >> PAGE_SHIFT);
 	if (eb && atomic_inc_not_zero(&eb->refs)) {
 		rcu_read_unlock();
 		/*
@@ -4943,7 +4827,7 @@ again:
 		goto free_eb;
 	spin_lock(&fs_info->buffer_lock);
 	ret = radix_tree_insert(&fs_info->buffer_radix,
-				start >> PAGE_CACHE_SHIFT, eb);
+				start >> PAGE_SHIFT, eb);
 	spin_unlock(&fs_info->buffer_lock);
 	radix_tree_preload_end();
 	if (ret == -EEXIST) {
@@ -4976,7 +4860,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	unsigned long len = fs_info->tree_root->nodesize;
 	unsigned long num_pages = num_extent_pages(start, len);
 	unsigned long i;
-	unsigned long index = start >> PAGE_CACHE_SHIFT;
+	unsigned long index = start >> PAGE_SHIFT;
 	struct extent_buffer *eb;
 	struct extent_buffer *exists = NULL;
 	struct page *p;
@@ -5010,7 +4894,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 			if (atomic_inc_not_zero(&exists->refs)) {
 				spin_unlock(&mapping->private_lock);
 				unlock_page(p);
-				page_cache_release(p);
+				put_page(p);
 				mark_extent_buffer_accessed(exists, p);
 				goto free_eb;
 			}
@@ -5022,7 +4906,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 			 */
 			ClearPagePrivate(p);
 			WARN_ON(PageDirty(p));
-			page_cache_release(p);
+			put_page(p);
 		}
 		attach_extent_buffer_page(eb, p);
 		spin_unlock(&mapping->private_lock);
@@ -5045,7 +4929,7 @@ again:
 
 	spin_lock(&fs_info->buffer_lock);
 	ret = radix_tree_insert(&fs_info->buffer_radix,
-				start >> PAGE_CACHE_SHIFT, eb);
+				start >> PAGE_SHIFT, eb);
 	spin_unlock(&fs_info->buffer_lock);
 	radix_tree_preload_end();
 	if (ret == -EEXIST) {
@@ -5108,7 +4992,7 @@ static int release_extent_buffer(struct extent_buffer *eb)
 
 			spin_lock(&fs_info->buffer_lock);
 			radix_tree_delete(&fs_info->buffer_radix,
-					  eb->start >> PAGE_CACHE_SHIFT);
+					  eb->start >> PAGE_SHIFT);
 			spin_unlock(&fs_info->buffer_lock);
 		} else {
 			spin_unlock(&eb->refs_lock);
@@ -5227,7 +5111,7 @@ int set_extent_buffer_dirty(struct extent_buffer *eb)
 	return was_dirty;
 }
 
-int clear_extent_buffer_uptodate(struct extent_buffer *eb)
+void clear_extent_buffer_uptodate(struct extent_buffer *eb)
 {
 	unsigned long i;
 	struct page *page;
@@ -5240,10 +5124,9 @@ int clear_extent_buffer_uptodate(struct extent_buffer *eb)
 		if (page)
 			ClearPageUptodate(page);
 	}
-	return 0;
 }
 
-int set_extent_buffer_uptodate(struct extent_buffer *eb)
+void set_extent_buffer_uptodate(struct extent_buffer *eb)
 {
 	unsigned long i;
 	struct page *page;
@@ -5255,7 +5138,6 @@ int set_extent_buffer_uptodate(struct extent_buffer *eb)
 		page = eb->pages[i];
 		SetPageUptodate(page);
 	}
-	return 0;
 }
 
 int extent_buffer_uptodate(struct extent_buffer *eb)
@@ -5284,8 +5166,8 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 
 	if (start) {
 		WARN_ON(start < eb->start);
-		start_i = (start >> PAGE_CACHE_SHIFT) -
-			(eb->start >> PAGE_CACHE_SHIFT);
+		start_i = (start >> PAGE_SHIFT) -
+			(eb->start >> PAGE_SHIFT);
 	} else {
 		start_i = 0;
 	}
@@ -5368,18 +5250,18 @@ void read_extent_buffer(struct extent_buffer *eb, void *dstv,
 	struct page *page;
 	char *kaddr;
 	char *dst = (char *)dstv;
-	size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1);
-	unsigned long i = (start_offset + start) >> PAGE_CACHE_SHIFT;
+	size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1);
+	unsigned long i = (start_offset + start) >> PAGE_SHIFT;
 
 	WARN_ON(start > eb->len);
 	WARN_ON(start + len > eb->start + eb->len);
 
-	offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
+	offset = (start_offset + start) & (PAGE_SIZE - 1);
 
 	while (len > 0) {
 		page = eb->pages[i];
 
-		cur = min(len, (PAGE_CACHE_SIZE - offset));
+		cur = min(len, (PAGE_SIZE - offset));
 		kaddr = page_address(page);
 		memcpy(dst, kaddr + offset, cur);
 
@@ -5399,19 +5281,19 @@ int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dstv,
 	struct page *page;
 	char *kaddr;
 	char __user *dst = (char __user *)dstv;
-	size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1);
-	unsigned long i = (start_offset + start) >> PAGE_CACHE_SHIFT;
+	size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1);
+	unsigned long i = (start_offset + start) >> PAGE_SHIFT;
 	int ret = 0;
 
 	WARN_ON(start > eb->len);
 	WARN_ON(start + len > eb->start + eb->len);
 
-	offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
+	offset = (start_offset + start) & (PAGE_SIZE - 1);
 
 	while (len > 0) {
 		page = eb->pages[i];
 
-		cur = min(len, (PAGE_CACHE_SIZE - offset));
+		cur = min(len, (PAGE_SIZE - offset));
 		kaddr = page_address(page);
 		if (copy_to_user(dst, kaddr + offset, cur)) {
 			ret = -EFAULT;
@@ -5432,13 +5314,13 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
 			       unsigned long *map_start,
 			       unsigned long *map_len)
 {
-	size_t offset = start & (PAGE_CACHE_SIZE - 1);
+	size_t offset = start & (PAGE_SIZE - 1);
 	char *kaddr;
 	struct page *p;
-	size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1);
-	unsigned long i = (start_offset + start) >> PAGE_CACHE_SHIFT;
+	size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1);
+	unsigned long i = (start_offset + start) >> PAGE_SHIFT;
 	unsigned long end_i = (start_offset + start + min_len - 1) >>
-		PAGE_CACHE_SHIFT;
+		PAGE_SHIFT;
 
 	if (i != end_i)
 		return -EINVAL;
@@ -5448,7 +5330,7 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
 		*map_start = 0;
 	} else {
 		offset = 0;
-		*map_start = ((u64)i << PAGE_CACHE_SHIFT) - start_offset;
+		*map_start = ((u64)i << PAGE_SHIFT) - start_offset;
 	}
 
 	if (start + min_len > eb->len) {
@@ -5461,7 +5343,7 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
 	p = eb->pages[i];
 	kaddr = page_address(p);
 	*map = kaddr + offset;
-	*map_len = PAGE_CACHE_SIZE - offset;
+	*map_len = PAGE_SIZE - offset;
 	return 0;
 }
 
@@ -5474,19 +5356,19 @@ int memcmp_extent_buffer(struct extent_buffer *eb, const void *ptrv,
 	struct page *page;
 	char *kaddr;
 	char *ptr = (char *)ptrv;
-	size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1);
-	unsigned long i = (start_offset + start) >> PAGE_CACHE_SHIFT;
+	size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1);
+	unsigned long i = (start_offset + start) >> PAGE_SHIFT;
 	int ret = 0;
 
 	WARN_ON(start > eb->len);
 	WARN_ON(start + len > eb->start + eb->len);
 
-	offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
+	offset = (start_offset + start) & (PAGE_SIZE - 1);
 
 	while (len > 0) {
 		page = eb->pages[i];
 
-		cur = min(len, (PAGE_CACHE_SIZE - offset));
+		cur = min(len, (PAGE_SIZE - offset));
 
 		kaddr = page_address(page);
 		ret = memcmp(ptr, kaddr + offset, cur);
@@ -5509,19 +5391,19 @@ void write_extent_buffer(struct extent_buffer *eb, const void *srcv,
 	struct page *page;
 	char *kaddr;
 	char *src = (char *)srcv;
-	size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1);
-	unsigned long i = (start_offset + start) >> PAGE_CACHE_SHIFT;
+	size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1);
+	unsigned long i = (start_offset + start) >> PAGE_SHIFT;
 
 	WARN_ON(start > eb->len);
 	WARN_ON(start + len > eb->start + eb->len);
 
-	offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
+	offset = (start_offset + start) & (PAGE_SIZE - 1);
 
 	while (len > 0) {
 		page = eb->pages[i];
 		WARN_ON(!PageUptodate(page));
 
-		cur = min(len, PAGE_CACHE_SIZE - offset);
+		cur = min(len, PAGE_SIZE - offset);
 		kaddr = page_address(page);
 		memcpy(kaddr + offset, src, cur);
 
@@ -5539,19 +5421,19 @@ void memset_extent_buffer(struct extent_buffer *eb, char c,
 	size_t offset;
 	struct page *page;
 	char *kaddr;
-	size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1);
-	unsigned long i = (start_offset + start) >> PAGE_CACHE_SHIFT;
+	size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1);
+	unsigned long i = (start_offset + start) >> PAGE_SHIFT;
 
 	WARN_ON(start > eb->len);
 	WARN_ON(start + len > eb->start + eb->len);
 
-	offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
+	offset = (start_offset + start) & (PAGE_SIZE - 1);
 
 	while (len > 0) {
 		page = eb->pages[i];
 		WARN_ON(!PageUptodate(page));
 
-		cur = min(len, PAGE_CACHE_SIZE - offset);
+		cur = min(len, PAGE_SIZE - offset);
 		kaddr = page_address(page);
 		memset(kaddr + offset, c, cur);
 
@@ -5570,19 +5452,19 @@ void copy_extent_buffer(struct extent_buffer *dst, struct extent_buffer *src,
 	size_t offset;
 	struct page *page;
 	char *kaddr;
-	size_t start_offset = dst->start & ((u64)PAGE_CACHE_SIZE - 1);
-	unsigned long i = (start_offset + dst_offset) >> PAGE_CACHE_SHIFT;
+	size_t start_offset = dst->start & ((u64)PAGE_SIZE - 1);
+	unsigned long i = (start_offset + dst_offset) >> PAGE_SHIFT;
 
 	WARN_ON(src->len != dst_len);
 
 	offset = (start_offset + dst_offset) &
-		(PAGE_CACHE_SIZE - 1);
+		(PAGE_SIZE - 1);
 
 	while (len > 0) {
 		page = dst->pages[i];
 		WARN_ON(!PageUptodate(page));
 
-		cur = min(len, (unsigned long)(PAGE_CACHE_SIZE - offset));
+		cur = min(len, (unsigned long)(PAGE_SIZE - offset));
 
 		kaddr = page_address(page);
 		read_extent_buffer(src, kaddr + offset, src_offset, cur);
@@ -5594,6 +5476,155 @@ void copy_extent_buffer(struct extent_buffer *dst, struct extent_buffer *src,
 	}
 }
 
+/*
+ * The extent buffer bitmap operations are done with byte granularity because
+ * bitmap items are not guaranteed to be aligned to a word and therefore a
+ * single word in a bitmap may straddle two pages in the extent buffer.
+ */
+#define BIT_BYTE(nr) ((nr) / BITS_PER_BYTE)
+#define BYTE_MASK ((1 << BITS_PER_BYTE) - 1)
+#define BITMAP_FIRST_BYTE_MASK(start) \
+	((BYTE_MASK << ((start) & (BITS_PER_BYTE - 1))) & BYTE_MASK)
+#define BITMAP_LAST_BYTE_MASK(nbits) \
+	(BYTE_MASK >> (-(nbits) & (BITS_PER_BYTE - 1)))
+
+/*
+ * eb_bitmap_offset() - calculate the page and offset of the byte containing the
+ * given bit number
+ * @eb: the extent buffer
+ * @start: offset of the bitmap item in the extent buffer
+ * @nr: bit number
+ * @page_index: return index of the page in the extent buffer that contains the
+ * given bit number
+ * @page_offset: return offset into the page given by page_index
+ *
+ * This helper hides the ugliness of finding the byte in an extent buffer which
+ * contains a given bit.
+ */
+static inline void eb_bitmap_offset(struct extent_buffer *eb,
+				    unsigned long start, unsigned long nr,
+				    unsigned long *page_index,
+				    size_t *page_offset)
+{
+	size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1);
+	size_t byte_offset = BIT_BYTE(nr);
+	size_t offset;
+
+	/*
+	 * The byte we want is the offset of the extent buffer + the offset of
+	 * the bitmap item in the extent buffer + the offset of the byte in the
+	 * bitmap item.
+	 */
+	offset = start_offset + start + byte_offset;
+
+	*page_index = offset >> PAGE_SHIFT;
+	*page_offset = offset & (PAGE_SIZE - 1);
+}
+
+/**
+ * extent_buffer_test_bit - determine whether a bit in a bitmap item is set
+ * @eb: the extent buffer
+ * @start: offset of the bitmap item in the extent buffer
+ * @nr: bit number to test
+ */
+int extent_buffer_test_bit(struct extent_buffer *eb, unsigned long start,
+			   unsigned long nr)
+{
+	char *kaddr;
+	struct page *page;
+	unsigned long i;
+	size_t offset;
+
+	eb_bitmap_offset(eb, start, nr, &i, &offset);
+	page = eb->pages[i];
+	WARN_ON(!PageUptodate(page));
+	kaddr = page_address(page);
+	return 1U & (kaddr[offset] >> (nr & (BITS_PER_BYTE - 1)));
+}
+
+/**
+ * extent_buffer_bitmap_set - set an area of a bitmap
+ * @eb: the extent buffer
+ * @start: offset of the bitmap item in the extent buffer
+ * @pos: bit number of the first bit
+ * @len: number of bits to set
+ */
+void extent_buffer_bitmap_set(struct extent_buffer *eb, unsigned long start,
+			      unsigned long pos, unsigned long len)
+{
+	char *kaddr;
+	struct page *page;
+	unsigned long i;
+	size_t offset;
+	const unsigned int size = pos + len;
+	int bits_to_set = BITS_PER_BYTE - (pos % BITS_PER_BYTE);
+	unsigned int mask_to_set = BITMAP_FIRST_BYTE_MASK(pos);
+
+	eb_bitmap_offset(eb, start, pos, &i, &offset);
+	page = eb->pages[i];
+	WARN_ON(!PageUptodate(page));
+	kaddr = page_address(page);
+
+	while (len >= bits_to_set) {
+		kaddr[offset] |= mask_to_set;
+		len -= bits_to_set;
+		bits_to_set = BITS_PER_BYTE;
+		mask_to_set = ~0U;
+		if (++offset >= PAGE_SIZE && len > 0) {
+			offset = 0;
+			page = eb->pages[++i];
+			WARN_ON(!PageUptodate(page));
+			kaddr = page_address(page);
+		}
+	}
+	if (len) {
+		mask_to_set &= BITMAP_LAST_BYTE_MASK(size);
+		kaddr[offset] |= mask_to_set;
+	}
+}
+
+
+/**
+ * extent_buffer_bitmap_clear - clear an area of a bitmap
+ * @eb: the extent buffer
+ * @start: offset of the bitmap item in the extent buffer
+ * @pos: bit number of the first bit
+ * @len: number of bits to clear
+ */
+void extent_buffer_bitmap_clear(struct extent_buffer *eb, unsigned long start,
+				unsigned long pos, unsigned long len)
+{
+	char *kaddr;
+	struct page *page;
+	unsigned long i;
+	size_t offset;
+	const unsigned int size = pos + len;
+	int bits_to_clear = BITS_PER_BYTE - (pos % BITS_PER_BYTE);
+	unsigned int mask_to_clear = BITMAP_FIRST_BYTE_MASK(pos);
+
+	eb_bitmap_offset(eb, start, pos, &i, &offset);
+	page = eb->pages[i];
+	WARN_ON(!PageUptodate(page));
+	kaddr = page_address(page);
+
+	while (len >= bits_to_clear) {
+		kaddr[offset] &= ~mask_to_clear;
+		len -= bits_to_clear;
+		bits_to_clear = BITS_PER_BYTE;
+		mask_to_clear = ~0U;
+		if (++offset >= PAGE_SIZE && len > 0) {
+			offset = 0;
+			page = eb->pages[++i];
+			WARN_ON(!PageUptodate(page));
+			kaddr = page_address(page);
+		}
+	}
+	if (len) {
+		mask_to_clear &= BITMAP_LAST_BYTE_MASK(size);
+		kaddr[offset] &= ~mask_to_clear;
+	}
+}
+
 static inline bool areas_overlap(unsigned long src, unsigned long dst, unsigned long len)
 {
 	unsigned long distance = (src > dst) ? src - dst : dst - src;
@@ -5628,7 +5659,7 @@ void memcpy_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
 	size_t cur;
 	size_t dst_off_in_page;
 	size_t src_off_in_page;
-	size_t start_offset = dst->start & ((u64)PAGE_CACHE_SIZE - 1);
+	size_t start_offset = dst->start & ((u64)PAGE_SIZE - 1);
 	unsigned long dst_i;
 	unsigned long src_i;
 
@@ -5647,17 +5678,17 @@ void memcpy_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
 
 	while (len > 0) {
 		dst_off_in_page = (start_offset + dst_offset) &
-			(PAGE_CACHE_SIZE - 1);
+			(PAGE_SIZE - 1);
 		src_off_in_page = (start_offset + src_offset) &
-			(PAGE_CACHE_SIZE - 1);
+			(PAGE_SIZE - 1);
 
-		dst_i = (start_offset + dst_offset) >> PAGE_CACHE_SHIFT;
-		src_i = (start_offset + src_offset) >> PAGE_CACHE_SHIFT;
+		dst_i = (start_offset + dst_offset) >> PAGE_SHIFT;
+		src_i = (start_offset + src_offset) >> PAGE_SHIFT;
 
-		cur = min(len, (unsigned long)(PAGE_CACHE_SIZE -
+		cur = min(len, (unsigned long)(PAGE_SIZE -
 					       src_off_in_page));
 		cur = min_t(unsigned long, cur,
-			(unsigned long)(PAGE_CACHE_SIZE - dst_off_in_page));
+			(unsigned long)(PAGE_SIZE - dst_off_in_page));
 
 		copy_pages(dst->pages[dst_i], dst->pages[src_i],
 			   dst_off_in_page, src_off_in_page, cur);
@@ -5676,7 +5707,7 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
 	size_t src_off_in_page;
 	unsigned long dst_end = dst_offset + len - 1;
 	unsigned long src_end = src_offset + len - 1;
-	size_t start_offset = dst->start & ((u64)PAGE_CACHE_SIZE - 1);
+	size_t start_offset = dst->start & ((u64)PAGE_SIZE - 1);
 	unsigned long dst_i;
 	unsigned long src_i;
 
@@ -5695,13 +5726,13 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
 		return;
 	}
 	while (len > 0) {
-		dst_i = (start_offset + dst_end) >> PAGE_CACHE_SHIFT;
-		src_i = (start_offset + src_end) >> PAGE_CACHE_SHIFT;
+		dst_i = (start_offset + dst_end) >> PAGE_SHIFT;
+		src_i = (start_offset + src_end) >> PAGE_SHIFT;
 
 		dst_off_in_page = (start_offset + dst_end) &
-			(PAGE_CACHE_SIZE - 1);
+			(PAGE_SIZE - 1);
 		src_off_in_page = (start_offset + src_end) &
-			(PAGE_CACHE_SIZE - 1);
+			(PAGE_SIZE - 1);
 
 		cur = min_t(unsigned long, len, src_off_in_page + 1);
 		cur = min(cur, dst_off_in_page + 1);
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index f4c1ae11855f..b5e0ade90e88 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -29,7 +29,6 @@
  */
 #define EXTENT_BIO_COMPRESSED 1
 #define EXTENT_BIO_TREE_LOG 2
-#define EXTENT_BIO_PARENT_LOCKED 4
 #define EXTENT_BIO_FLAG_SHIFT 16
 
 /* these are bit numbers for test/set bit */
@@ -62,6 +61,7 @@
 struct extent_state;
 struct btrfs_root;
 struct btrfs_io_bio;
+struct io_failure_record;
 
 typedef	int (extent_submit_bio_hook_t)(struct inode *inode, int rw,
 				       struct bio *bio, int mirror_num,
@@ -112,8 +112,7 @@ struct extent_state {
 	atomic_t refs;
 	unsigned state;
 
-	/* for use by the FS */
-	u64 private;
+	struct io_failure_record *failrec;
 
 #ifdef CONFIG_BTRFS_DEBUG
 	struct list_head leak_list;
@@ -121,7 +120,7 @@ struct extent_state {
 };
 
 #define INLINE_EXTENT_BUFFER_PAGES 16
-#define MAX_INLINE_EXTENT_BUFFER_SIZE (INLINE_EXTENT_BUFFER_PAGES * PAGE_CACHE_SIZE)
+#define MAX_INLINE_EXTENT_BUFFER_SIZE (INLINE_EXTENT_BUFFER_PAGES * PAGE_SIZE)
 struct extent_buffer {
 	u64 start;
 	unsigned long len;
@@ -199,17 +198,17 @@ int try_release_extent_mapping(struct extent_map_tree *map,
 			       struct extent_io_tree *tree, struct page *page,
 			       gfp_t mask);
 int try_release_extent_buffer(struct page *page);
-int lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
 int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-		     unsigned bits, struct extent_state **cached);
-int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end);
-int unlock_extent_cached(struct extent_io_tree *tree, u64 start, u64 end,
-			 struct extent_state **cached, gfp_t mask);
+		     struct extent_state **cached);
+
+static inline int lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
+{
+	return lock_extent_bits(tree, start, end, NULL);
+}
+
 int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
 int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
 			  get_extent_t *get_extent, int mirror_num);
-int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page,
-				 get_extent_t *get_extent, int mirror_num);
 int __init extent_io_init(void);
 void extent_io_exit(void);
 
@@ -221,39 +220,105 @@ void free_extent_state(struct extent_state *state);
 int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		   unsigned bits, int filled,
 		   struct extent_state *cached_state);
-int clear_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-		      unsigned bits, gfp_t mask);
 int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 			     unsigned bits, gfp_t mask,
 			     struct extent_changeset *changeset);
 int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		     unsigned bits, int wake, int delete,
 		     struct extent_state **cached, gfp_t mask);
-int set_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-		    unsigned bits, gfp_t mask);
+
+static inline int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end)
+{
+	return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, NULL,
+				GFP_NOFS);
+}
+
+static inline int unlock_extent_cached(struct extent_io_tree *tree, u64 start,
+		u64 end, struct extent_state **cached, gfp_t mask)
+{
+	return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
+				mask);
+}
+
+static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start,
+		u64 end, unsigned bits, gfp_t mask)
+{
+	int wake = 0;
+
+	if (bits & EXTENT_LOCKED)
+		wake = 1;
+
+	return clear_extent_bit(tree, start, end, bits, wake, 0, NULL, mask);
+}
+
 int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 			   unsigned bits, gfp_t mask,
 			   struct extent_changeset *changeset);
 int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		   unsigned bits, u64 *failed_start,
 		   struct extent_state **cached_state, gfp_t mask);
-int set_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end,
-			struct extent_state **cached_state, gfp_t mask);
-int clear_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end,
-			  struct extent_state **cached_state, gfp_t mask);
-int set_extent_new(struct extent_io_tree *tree, u64 start, u64 end,
-		   gfp_t mask);
-int set_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end,
-		     gfp_t mask);
-int clear_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end,
-		       gfp_t mask);
+
+static inline int set_extent_bits(struct extent_io_tree *tree, u64 start,
+		u64 end, unsigned bits, gfp_t mask)
+{
+	return set_extent_bit(tree, start, end, bits, NULL, NULL, mask);
+}
+
+static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
+		u64 end, struct extent_state **cached_state, gfp_t mask)
+{
+	return clear_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, 0,
+				cached_state, mask);
+}
+
+static inline int set_extent_dirty(struct extent_io_tree *tree, u64 start,
+		u64 end, gfp_t mask)
+{
+	return set_extent_bit(tree, start, end, EXTENT_DIRTY, NULL,
+			      NULL, mask);
+}
+
+static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start,
+		u64 end, gfp_t mask)
+{
+	return clear_extent_bit(tree, start, end,
+				EXTENT_DIRTY | EXTENT_DELALLOC |
+				EXTENT_DO_ACCOUNTING, 0, 0, NULL, mask);
+}
+
 int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		       unsigned bits, unsigned clear_bits,
 		       struct extent_state **cached_state, gfp_t mask);
-int set_extent_delalloc(struct extent_io_tree *tree, u64 start, u64 end,
-			struct extent_state **cached_state, gfp_t mask);
-int set_extent_defrag(struct extent_io_tree *tree, u64 start, u64 end,
-		      struct extent_state **cached_state, gfp_t mask);
+
+static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start,
+		u64 end, struct extent_state **cached_state, gfp_t mask)
+{
+	return set_extent_bit(tree, start, end,
+			      EXTENT_DELALLOC | EXTENT_UPTODATE,
+			      NULL, cached_state, mask);
+}
+
+static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start,
+		u64 end, struct extent_state **cached_state, gfp_t mask)
+{
+	return set_extent_bit(tree, start, end,
+			      EXTENT_DELALLOC | EXTENT_UPTODATE | EXTENT_DEFRAG,
+			      NULL, cached_state, mask);
+}
+
+static inline int set_extent_new(struct extent_io_tree *tree, u64 start,
+		u64 end, gfp_t mask)
+{
+	return set_extent_bit(tree, start, end, EXTENT_NEW, NULL, NULL, mask);
+}
+
+static inline int set_extent_uptodate(struct extent_io_tree *tree, u64 start,
+		u64 end, struct extent_state **cached_state, gfp_t mask)
+{
+	return set_extent_bit(tree, start, end, EXTENT_UPTODATE, NULL,
+			      cached_state, mask);
+}
+
 int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
 			  u64 *start_ret, u64 *end_ret, unsigned bits,
 			  struct extent_state **cached_state);
@@ -277,13 +342,14 @@ int extent_readpages(struct extent_io_tree *tree,
 		     get_extent_t get_extent);
 int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		__u64 start, __u64 len, get_extent_t *get_extent);
-int get_state_private(struct extent_io_tree *tree, u64 start, u64 *private);
 void set_page_extent_mapped(struct page *page);
 
 struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 					  u64 start);
+struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
+						  u64 start, unsigned long len);
 struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
-		u64 start);
+						u64 start);
 struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src);
 struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
 					 u64 start);
@@ -299,8 +365,8 @@ void wait_on_extent_buffer_writeback(struct extent_buffer *eb);
 
 static inline unsigned long num_extent_pages(u64 start, u64 len)
 {
-	return ((start + len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT) -
-		(start >> PAGE_CACHE_SHIFT);
+	return ((start + len + PAGE_SIZE - 1) >> PAGE_SHIFT) -
+		(start >> PAGE_SHIFT);
 }
 
 static inline void extent_buffer_get(struct extent_buffer *eb)
@@ -328,19 +394,25 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
 			   unsigned long src_offset, unsigned long len);
 void memset_extent_buffer(struct extent_buffer *eb, char c,
 			  unsigned long start, unsigned long len);
+int extent_buffer_test_bit(struct extent_buffer *eb, unsigned long start,
+			   unsigned long pos);
+void extent_buffer_bitmap_set(struct extent_buffer *eb, unsigned long start,
+			      unsigned long pos, unsigned long len);
+void extent_buffer_bitmap_clear(struct extent_buffer *eb, unsigned long start,
+				unsigned long pos, unsigned long len);
 void clear_extent_buffer_dirty(struct extent_buffer *eb);
 int set_extent_buffer_dirty(struct extent_buffer *eb);
-int set_extent_buffer_uptodate(struct extent_buffer *eb);
-int clear_extent_buffer_uptodate(struct extent_buffer *eb);
+void set_extent_buffer_uptodate(struct extent_buffer *eb);
+void clear_extent_buffer_uptodate(struct extent_buffer *eb);
 int extent_buffer_uptodate(struct extent_buffer *eb);
 int extent_buffer_under_io(struct extent_buffer *eb);
 int map_private_extent_buffer(struct extent_buffer *eb, unsigned long offset,
 		      unsigned long min_len, char **map,
 		      unsigned long *map_start,
 		      unsigned long *map_len);
-int extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end);
-int extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end);
-int extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
+void extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end);
+void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end);
+void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
 				 struct page *locked_page,
 				 unsigned bits_to_clear,
 				 unsigned long page_ops);
@@ -357,7 +429,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
 		      int mirror_num);
 int clean_io_failure(struct inode *inode, u64 start, struct page *page,
 		     unsigned int pg_offset);
-int end_extent_writepage(struct page *page, int err, u64 start, u64 end);
+void end_extent_writepage(struct page *page, int err, u64 start, u64 end);
 int repair_eb_io_failure(struct btrfs_root *root, struct extent_buffer *eb,
 			 int mirror_num);
 
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 6a98bddd8f33..318b048eb254 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -4,6 +4,7 @@
 #include <linux/hardirq.h>
 #include "ctree.h"
 #include "extent_map.h"
+#include "compression.h"
 
 
 static struct kmem_cache *extent_map_cache;
@@ -20,8 +21,7 @@ int __init extent_map_init(void)
 
 void extent_map_exit(void)
 {
-	if (extent_map_cache)
-		kmem_cache_destroy(extent_map_cache);
+	kmem_cache_destroy(extent_map_cache);
 }
 
 /**
@@ -62,7 +62,7 @@ struct extent_map *alloc_extent_map(void)
 
 /**
  * free_extent_map - drop reference count of an extent_map
- * @em:		extent map beeing releasead
+ * @em:		extent map being releasead
  *
  * Drops the reference out on @em by one and free the structure
  * if the reference count hits zero.
@@ -76,7 +76,7 @@ void free_extent_map(struct extent_map *em)
 		WARN_ON(extent_map_in_tree(em));
 		WARN_ON(!list_empty(&em->list));
 		if (test_bit(EXTENT_FLAG_FS_MAPPING, &em->flags))
-			kfree(em->bdev);
+			kfree(em->map_lookup);
 		kmem_cache_free(extent_map_cache, em);
 	}
 }
@@ -422,7 +422,7 @@ struct extent_map *search_extent_mapping(struct extent_map_tree *tree,
 /**
  * remove_extent_mapping - removes an extent_map from the extent tree
  * @tree:	extent tree to remove from
- * @em:		extent map beeing removed
+ * @em:		extent map being removed
  *
  * Removes @em from @tree.  No reference counts are dropped, and no checks
  * are done to see if the range is in use
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index b2991fd8583e..eb8b8fae036b 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -32,7 +32,15 @@ struct extent_map {
 	u64 block_len;
 	u64 generation;
 	unsigned long flags;
-	struct block_device *bdev;
+	union {
+		struct block_device *bdev;
+
+		/*
+		 * used for chunk mappings
+		 * flags & EXTENT_FLAG_FS_MAPPING must be set
+		 */
+		struct map_lookup *map_lookup;
+	};
 	atomic_t refs;
 	unsigned int compress_type;
 	struct list_head list;
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 58ece6558430..7a7d6e253cfc 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -25,13 +25,14 @@
 #include "transaction.h"
 #include "volumes.h"
 #include "print-tree.h"
+#include "compression.h"
 
 #define __MAX_CSUM_ITEMS(r, size) ((unsigned long)(((BTRFS_LEAF_DATA_SIZE(r) - \
 				   sizeof(struct btrfs_item) * 2) / \
 				  size) - 1))
 
 #define MAX_CSUM_ITEMS(r, size) (min_t(u32, __MAX_CSUM_ITEMS(r, size), \
-				       PAGE_CACHE_SIZE))
+				       PAGE_SIZE))
 
 #define MAX_ORDERED_SUM_BYTES(r) ((PAGE_SIZE - \
 				   sizeof(struct btrfs_ordered_sum)) / \
@@ -172,6 +173,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 	u64 item_start_offset = 0;
 	u64 item_last_offset = 0;
 	u64 disk_bytenr;
+	u64 page_bytes_left;
 	u32 diff;
 	int nblocks;
 	int bio_index = 0;
@@ -201,8 +203,8 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 		csum = (u8 *)dst;
 	}
 
-	if (bio->bi_iter.bi_size > PAGE_CACHE_SIZE * 8)
-		path->reada = 2;
+	if (bio->bi_iter.bi_size > PAGE_SIZE * 8)
+		path->reada = READA_FORWARD;
 
 	WARN_ON(bio->bi_vcnt <= 0);
 
@@ -220,6 +222,8 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 	disk_bytenr = (u64)bio->bi_iter.bi_sector << 9;
 	if (dio)
 		offset = logical_offset;
+
+	page_bytes_left = bvec->bv_len;
 	while (bio_index < bio->bi_vcnt) {
 		if (!dio)
 			offset = page_offset(bvec->bv_page) + bvec->bv_offset;
@@ -243,7 +247,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 				if (BTRFS_I(inode)->root->root_key.objectid ==
 				    BTRFS_DATA_RELOC_TREE_OBJECTID) {
 					set_extent_bits(io_tree, offset,
-						offset + bvec->bv_len - 1,
+						offset + root->sectorsize - 1,
 						EXTENT_NODATASUM, GFP_NOFS);
 				} else {
 					btrfs_info(BTRFS_I(inode)->root->fs_info,
@@ -281,13 +285,29 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 found:
 		csum += count * csum_size;
 		nblocks -= count;
-		bio_index += count;
+
 		while (count--) {
-			disk_bytenr += bvec->bv_len;
-			offset += bvec->bv_len;
-			bvec++;
+			disk_bytenr += root->sectorsize;
+			offset += root->sectorsize;
+			page_bytes_left -= root->sectorsize;
+			if (!page_bytes_left) {
+				bio_index++;
+				/*
+				 * make sure we're still inside the
+				 * bio before we update page_bytes_left
+				 */
+				if (bio_index >= bio->bi_vcnt) {
+					WARN_ON_ONCE(count);
+					goto done;
+				}
+				bvec++;
+				page_bytes_left = bvec->bv_len;
+			}
+
 		}
 	}
+
+done:
 	btrfs_free_path(path);
 	return 0;
 }
@@ -328,7 +348,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 
 	if (search_commit) {
 		path->skip_locking = 1;
-		path->reada = 2;
+		path->reada = READA_FORWARD;
 		path->search_commit_root = 1;
 	}
 
@@ -432,6 +452,8 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
 	struct bio_vec *bvec = bio->bi_io_vec;
 	int bio_index = 0;
 	int index;
+	int nr_sectors;
+	int i;
 	unsigned long total_bytes = 0;
 	unsigned long this_sum_bytes = 0;
 	u64 offset;
@@ -459,41 +481,56 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
 		if (!contig)
 			offset = page_offset(bvec->bv_page) + bvec->bv_offset;
 
-		if (offset >= ordered->file_offset + ordered->len ||
-		    offset < ordered->file_offset) {
-			unsigned long bytes_left;
-			sums->len = this_sum_bytes;
-			this_sum_bytes = 0;
-			btrfs_add_ordered_sum(inode, ordered, sums);
-			btrfs_put_ordered_extent(ordered);
+		data = kmap_atomic(bvec->bv_page);
 
-			bytes_left = bio->bi_iter.bi_size - total_bytes;
+		nr_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
+						bvec->bv_len + root->sectorsize
+						- 1);
+
+		for (i = 0; i < nr_sectors; i++) {
+			if (offset >= ordered->file_offset + ordered->len ||
+				offset < ordered->file_offset) {
+				unsigned long bytes_left;
+
+				kunmap_atomic(data);
+				sums->len = this_sum_bytes;
+				this_sum_bytes = 0;
+				btrfs_add_ordered_sum(inode, ordered, sums);
+				btrfs_put_ordered_extent(ordered);
+
+				bytes_left = bio->bi_iter.bi_size - total_bytes;
+
+				sums = kzalloc(btrfs_ordered_sum_size(root, bytes_left),
+					GFP_NOFS);
+				BUG_ON(!sums); /* -ENOMEM */
+				sums->len = bytes_left;
+				ordered = btrfs_lookup_ordered_extent(inode,
+								offset);
+				ASSERT(ordered); /* Logic error */
+				sums->bytenr = ((u64)bio->bi_iter.bi_sector << 9)
+					+ total_bytes;
+				index = 0;
+
+				data = kmap_atomic(bvec->bv_page);
+			}
 
-			sums = kzalloc(btrfs_ordered_sum_size(root, bytes_left),
-				       GFP_NOFS);
-			BUG_ON(!sums); /* -ENOMEM */
-			sums->len = bytes_left;
-			ordered = btrfs_lookup_ordered_extent(inode, offset);
-			BUG_ON(!ordered); /* Logic error */
-			sums->bytenr = ((u64)bio->bi_iter.bi_sector << 9) +
-				       total_bytes;
-			index = 0;
+			sums->sums[index] = ~(u32)0;
+			sums->sums[index]
+				= btrfs_csum_data(data + bvec->bv_offset
+						+ (i * root->sectorsize),
+						sums->sums[index],
+						root->sectorsize);
+			btrfs_csum_final(sums->sums[index],
+					(char *)(sums->sums + index));
+			index++;
+			offset += root->sectorsize;
+			this_sum_bytes += root->sectorsize;
+			total_bytes += root->sectorsize;
 		}
 
-		data = kmap_atomic(bvec->bv_page);
-		sums->sums[index] = ~(u32)0;
-		sums->sums[index] = btrfs_csum_data(data + bvec->bv_offset,
-						    sums->sums[index],
-						    bvec->bv_len);
 		kunmap_atomic(data);
-		btrfs_csum_final(sums->sums[index],
-				 (char *)(sums->sums + index));
 
 		bio_index++;
-		index++;
-		total_bytes += bvec->bv_len;
-		this_sum_bytes += bvec->bv_len;
-		offset += bvec->bv_len;
 		bvec++;
 	}
 	this_sum_bytes = 0;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 6bd5ce9d75f0..8d7b5a45c005 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -41,6 +41,7 @@
 #include "locking.h"
 #include "volumes.h"
 #include "qgroup.h"
+#include "compression.h"
 
 static struct kmem_cache *btrfs_inode_defrag_cachep;
 /*
@@ -406,19 +407,18 @@ int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info)
 /* simple helper to fault in pages and copy.  This should go away
  * and be replaced with calls into generic code.
  */
-static noinline int btrfs_copy_from_user(loff_t pos, int num_pages,
-					 size_t write_bytes,
+static noinline int btrfs_copy_from_user(loff_t pos, size_t write_bytes,
 					 struct page **prepared_pages,
 					 struct iov_iter *i)
 {
 	size_t copied = 0;
 	size_t total_copied = 0;
 	int pg = 0;
-	int offset = pos & (PAGE_CACHE_SIZE - 1);
+	int offset = pos & (PAGE_SIZE - 1);
 
 	while (write_bytes > 0) {
 		size_t count = min_t(size_t,
-				     PAGE_CACHE_SIZE - offset, write_bytes);
+				     PAGE_SIZE - offset, write_bytes);
 		struct page *page = prepared_pages[pg];
 		/*
 		 * Copy data from userspace to the current page
@@ -448,7 +448,7 @@ static noinline int btrfs_copy_from_user(loff_t pos, int num_pages,
 		if (unlikely(copied == 0))
 			break;
 
-		if (copied < PAGE_CACHE_SIZE - offset) {
+		if (copied < PAGE_SIZE - offset) {
 			offset += copied;
 		} else {
 			pg++;
@@ -473,7 +473,7 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages)
 		 */
 		ClearPageChecked(pages[i]);
 		unlock_page(pages[i]);
-		page_cache_release(pages[i]);
+		put_page(pages[i]);
 	}
 }
 
@@ -499,7 +499,7 @@ int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode,
 	loff_t isize = i_size_read(inode);
 
 	start_pos = pos & ~((u64)root->sectorsize - 1);
-	num_bytes = ALIGN(write_bytes + pos - start_pos, root->sectorsize);
+	num_bytes = round_up(write_bytes + pos - start_pos, root->sectorsize);
 
 	end_of_last_block = start_pos + num_bytes - 1;
 	err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block,
@@ -756,8 +756,16 @@ next_slot:
 		}
 
 		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
-		if (key.objectid > ino ||
-		    key.type > BTRFS_EXTENT_DATA_KEY || key.offset >= end)
+
+		if (key.objectid > ino)
+			break;
+		if (WARN_ON_ONCE(key.objectid < ino) ||
+		    key.type < BTRFS_EXTENT_DATA_KEY) {
+			ASSERT(del_nr == 0);
+			path->slots[0]++;
+			goto next_slot;
+		}
+		if (key.type > BTRFS_EXTENT_DATA_KEY || key.offset >= end)
 			break;
 
 		fi = btrfs_item_ptr(leaf, path->slots[0],
@@ -776,8 +784,8 @@ next_slot:
 				btrfs_file_extent_inline_len(leaf,
 						     path->slots[0], fi);
 		} else {
-			WARN_ON(1);
-			extent_end = search_start;
+			/* can't happen */
+			BUG();
 		}
 
 		/*
@@ -1283,12 +1291,13 @@ out:
  * on error we return an unlocked page and the error value
  * on success we return a locked page and 0
  */
-static int prepare_uptodate_page(struct page *page, u64 pos,
+static int prepare_uptodate_page(struct inode *inode,
+				 struct page *page, u64 pos,
 				 bool force_uptodate)
 {
 	int ret = 0;
 
-	if (((pos & (PAGE_CACHE_SIZE - 1)) || force_uptodate) &&
+	if (((pos & (PAGE_SIZE - 1)) || force_uptodate) &&
 	    !PageUptodate(page)) {
 		ret = btrfs_readpage(NULL, page);
 		if (ret)
@@ -1298,6 +1307,10 @@ static int prepare_uptodate_page(struct page *page, u64 pos,
 			unlock_page(page);
 			return -EIO;
 		}
+		if (page->mapping != inode->i_mapping) {
+			unlock_page(page);
+			return -EAGAIN;
+		}
 	}
 	return 0;
 }
@@ -1310,12 +1323,13 @@ static noinline int prepare_pages(struct inode *inode, struct page **pages,
 				  size_t write_bytes, bool force_uptodate)
 {
 	int i;
-	unsigned long index = pos >> PAGE_CACHE_SHIFT;
+	unsigned long index = pos >> PAGE_SHIFT;
 	gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
 	int err = 0;
 	int faili;
 
 	for (i = 0; i < num_pages; i++) {
+again:
 		pages[i] = find_or_create_page(inode->i_mapping, index + i,
 					       mask | __GFP_WRITE);
 		if (!pages[i]) {
@@ -1325,13 +1339,17 @@ static noinline int prepare_pages(struct inode *inode, struct page **pages,
 		}
 
 		if (i == 0)
-			err = prepare_uptodate_page(pages[i], pos,
+			err = prepare_uptodate_page(inode, pages[i], pos,
 						    force_uptodate);
-		if (i == num_pages - 1)
-			err = prepare_uptodate_page(pages[i],
+		if (!err && i == num_pages - 1)
+			err = prepare_uptodate_page(inode, pages[i],
 						    pos + write_bytes, false);
 		if (err) {
-			page_cache_release(pages[i]);
+			put_page(pages[i]);
+			if (err == -EAGAIN) {
+				err = 0;
+				goto again;
+			}
 			faili = i - 1;
 			goto fail;
 		}
@@ -1342,7 +1360,7 @@ static noinline int prepare_pages(struct inode *inode, struct page **pages,
 fail:
 	while (faili >= 0) {
 		unlock_page(pages[faili]);
-		page_cache_release(pages[faili]);
+		put_page(pages[faili]);
 		faili--;
 	}
 	return err;
@@ -1362,21 +1380,24 @@ fail:
 static noinline int
 lock_and_cleanup_extent_if_need(struct inode *inode, struct page **pages,
 				size_t num_pages, loff_t pos,
+				size_t write_bytes,
 				u64 *lockstart, u64 *lockend,
 				struct extent_state **cached_state)
 {
+	struct btrfs_root *root = BTRFS_I(inode)->root;
 	u64 start_pos;
 	u64 last_pos;
 	int i;
 	int ret = 0;
 
-	start_pos = pos & ~((u64)PAGE_CACHE_SIZE - 1);
-	last_pos = start_pos + ((u64)num_pages << PAGE_CACHE_SHIFT) - 1;
+	start_pos = round_down(pos, root->sectorsize);
+	last_pos = start_pos
+		+ round_up(pos + write_bytes - start_pos, root->sectorsize) - 1;
 
 	if (start_pos < inode->i_size) {
 		struct btrfs_ordered_extent *ordered;
 		lock_extent_bits(&BTRFS_I(inode)->io_tree,
-				 start_pos, last_pos, 0, cached_state);
+				 start_pos, last_pos, cached_state);
 		ordered = btrfs_lookup_ordered_range(inode, start_pos,
 						     last_pos - start_pos + 1);
 		if (ordered &&
@@ -1387,7 +1408,7 @@ lock_and_cleanup_extent_if_need(struct inode *inode, struct page **pages,
 					     cached_state, GFP_NOFS);
 			for (i = 0; i < num_pages; i++) {
 				unlock_page(pages[i]);
-				page_cache_release(pages[i]);
+				put_page(pages[i]);
 			}
 			btrfs_start_ordered_extent(inode, ordered, 1);
 			btrfs_put_ordered_extent(ordered);
@@ -1476,8 +1497,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 	bool force_page_uptodate = false;
 	bool need_unlock;
 
-	nrptrs = min(DIV_ROUND_UP(iov_iter_count(i), PAGE_CACHE_SIZE),
-			PAGE_CACHE_SIZE / (sizeof(struct page *)));
+	nrptrs = min(DIV_ROUND_UP(iov_iter_count(i), PAGE_SIZE),
+			PAGE_SIZE / (sizeof(struct page *)));
 	nrptrs = min(nrptrs, current->nr_dirtied_pause - current->nr_dirtied);
 	nrptrs = max(nrptrs, 8);
 	pages = kmalloc_array(nrptrs, sizeof(struct page *), GFP_KERNEL);
@@ -1485,15 +1506,18 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 		return -ENOMEM;
 
 	while (iov_iter_count(i) > 0) {
-		size_t offset = pos & (PAGE_CACHE_SIZE - 1);
+		size_t offset = pos & (PAGE_SIZE - 1);
+		size_t sector_offset;
 		size_t write_bytes = min(iov_iter_count(i),
-					 nrptrs * (size_t)PAGE_CACHE_SIZE -
+					 nrptrs * (size_t)PAGE_SIZE -
 					 offset);
 		size_t num_pages = DIV_ROUND_UP(write_bytes + offset,
-						PAGE_CACHE_SIZE);
+						PAGE_SIZE);
 		size_t reserve_bytes;
 		size_t dirty_pages;
 		size_t copied;
+		size_t dirty_sectors;
+		size_t num_sectors;
 
 		WARN_ON(num_pages > nrptrs);
 
@@ -1506,29 +1530,29 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 			break;
 		}
 
-		reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
+		sector_offset = pos & (root->sectorsize - 1);
+		reserve_bytes = round_up(write_bytes + sector_offset,
+				root->sectorsize);
 
-		if (BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
-					     BTRFS_INODE_PREALLOC)) {
-			ret = check_can_nocow(inode, pos, &write_bytes);
-			if (ret < 0)
-				break;
-			if (ret > 0) {
-				/*
-				 * For nodata cow case, no need to reserve
-				 * data space.
-				 */
-				only_release_metadata = true;
-				/*
-				 * our prealloc extent may be smaller than
-				 * write_bytes, so scale down.
-				 */
-				num_pages = DIV_ROUND_UP(write_bytes + offset,
-							 PAGE_CACHE_SIZE);
-				reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
-				goto reserve_metadata;
-			}
+		if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
+					      BTRFS_INODE_PREALLOC)) &&
+		    check_can_nocow(inode, pos, &write_bytes) > 0) {
+			/*
+			 * For nodata cow case, no need to reserve
+			 * data space.
+			 */
+			only_release_metadata = true;
+			/*
+			 * our prealloc extent may be smaller than
+			 * write_bytes, so scale down.
+			 */
+			num_pages = DIV_ROUND_UP(write_bytes + offset,
+						 PAGE_SIZE);
+			reserve_bytes = round_up(write_bytes + sector_offset,
+					root->sectorsize);
+			goto reserve_metadata;
 		}
+
 		ret = btrfs_check_data_free_space(inode, pos, write_bytes);
 		if (ret < 0)
 			break;
@@ -1559,8 +1583,8 @@ again:
 			break;
 
 		ret = lock_and_cleanup_extent_if_need(inode, pages, num_pages,
-						      pos, &lockstart, &lockend,
-						      &cached_state);
+						pos, write_bytes, &lockstart,
+						&lockend, &cached_state);
 		if (ret < 0) {
 			if (ret == -EAGAIN)
 				goto again;
@@ -1570,8 +1594,7 @@ again:
 			ret = 0;
 		}
 
-		copied = btrfs_copy_from_user(pos, num_pages,
-					   write_bytes, pages, i);
+		copied = btrfs_copy_from_user(pos, write_bytes, pages, i);
 
 		/*
 		 * if we have trouble faulting in the pages, fall
@@ -1586,7 +1609,7 @@ again:
 		} else {
 			force_page_uptodate = false;
 			dirty_pages = DIV_ROUND_UP(copied + offset,
-						   PAGE_CACHE_SIZE);
+						   PAGE_SIZE);
 		}
 
 		/*
@@ -1596,9 +1619,16 @@ again:
 		 * we still have an outstanding extent for the chunk we actually
 		 * managed to copy.
 		 */
-		if (num_pages > dirty_pages) {
-			release_bytes = (num_pages - dirty_pages) <<
-				PAGE_CACHE_SHIFT;
+		num_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
+						reserve_bytes);
+		dirty_sectors = round_up(copied + sector_offset,
+					root->sectorsize);
+		dirty_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
+						dirty_sectors);
+
+		if (num_sectors > dirty_sectors) {
+			release_bytes = (write_bytes - copied)
+				& ~((u64)root->sectorsize - 1);
 			if (copied > 0) {
 				spin_lock(&BTRFS_I(inode)->lock);
 				BTRFS_I(inode)->outstanding_extents++;
@@ -1611,13 +1641,14 @@ again:
 				u64 __pos;
 
 				__pos = round_down(pos, root->sectorsize) +
-					(dirty_pages << PAGE_CACHE_SHIFT);
+					(dirty_pages << PAGE_SHIFT);
 				btrfs_delalloc_release_space(inode, __pos,
 							     release_bytes);
 			}
 		}
 
-		release_bytes = dirty_pages << PAGE_CACHE_SHIFT;
+		release_bytes = round_up(copied + sector_offset,
+					root->sectorsize);
 
 		if (copied > 0)
 			ret = btrfs_dirty_pages(root, inode, pages,
@@ -1638,8 +1669,7 @@ again:
 
 		if (only_release_metadata && copied > 0) {
 			lockstart = round_down(pos, root->sectorsize);
-			lockend = lockstart +
-				(dirty_pages << PAGE_CACHE_SHIFT) - 1;
+			lockend = round_up(pos + copied, root->sectorsize) - 1;
 
 			set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
 				       lockend, EXTENT_NORESERVE, NULL,
@@ -1652,7 +1682,7 @@ again:
 		cond_resched();
 
 		balance_dirty_pages_ratelimited(inode->i_mapping);
-		if (dirty_pages < (root->nodesize >> PAGE_CACHE_SHIFT) + 1)
+		if (dirty_pages < (root->nodesize >> PAGE_SHIFT) + 1)
 			btrfs_btree_balance_dirty(root);
 
 		pos += copied;
@@ -1708,8 +1738,8 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb,
 		goto out;
 	written += written_buffered;
 	iocb->ki_pos = pos + written_buffered;
-	invalidate_mapping_pages(file->f_mapping, pos >> PAGE_CACHE_SHIFT,
-				 endbyte >> PAGE_CACHE_SHIFT);
+	invalidate_mapping_pages(file->f_mapping, pos >> PAGE_SHIFT,
+				 endbyte >> PAGE_SHIFT);
 out:
 	return written ? written : err;
 }
@@ -1745,18 +1775,20 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	ssize_t err;
 	loff_t pos;
 	size_t count;
+	loff_t oldsize;
+	int clean_page = 0;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	err = generic_write_checks(iocb, from);
 	if (err <= 0) {
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 		return err;
 	}
 
 	current->backing_dev_info = inode_to_bdi(inode);
 	err = file_remove_privs(file);
 	if (err) {
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 		goto out;
 	}
 
@@ -1767,7 +1799,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	 * to stop this write operation to ensure FS consistency.
 	 */
 	if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state)) {
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 		err = -EROFS;
 		goto out;
 	}
@@ -1783,14 +1815,17 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	pos = iocb->ki_pos;
 	count = iov_iter_count(from);
 	start_pos = round_down(pos, root->sectorsize);
-	if (start_pos > i_size_read(inode)) {
+	oldsize = i_size_read(inode);
+	if (start_pos > oldsize) {
 		/* Expand hole size to cover write data, preventing empty gap */
 		end_pos = round_up(pos + count, root->sectorsize);
-		err = btrfs_cont_expand(inode, i_size_read(inode), end_pos);
+		err = btrfs_cont_expand(inode, oldsize, end_pos);
 		if (err) {
-			mutex_unlock(&inode->i_mutex);
+			inode_unlock(inode);
 			goto out;
 		}
+		if (start_pos > round_up(oldsize, root->sectorsize))
+			clean_page = 1;
 	}
 
 	if (sync)
@@ -1802,14 +1837,17 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 		num_written = __btrfs_buffered_write(file, from, pos);
 		if (num_written > 0)
 			iocb->ki_pos = pos + num_written;
+		if (clean_page)
+			pagecache_isize_extended(inode, oldsize,
+						i_size_read(inode));
 	}
 
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	/*
 	 * We also have to set last_sub_trans to the current log transid,
 	 * otherwise subsequent syncs to a file that's been synced in this
-	 * transaction will appear to have already occured.
+	 * transaction will appear to have already occurred.
 	 */
 	spin_lock(&BTRFS_I(inode)->lock);
 	BTRFS_I(inode)->last_sub_trans = root->log_transid;
@@ -1867,15 +1905,20 @@ static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end)
  */
 int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 {
-	struct dentry *dentry = file->f_path.dentry;
+	struct dentry *dentry = file_dentry(file);
 	struct inode *inode = d_inode(dentry);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_trans_handle *trans;
 	struct btrfs_log_ctx ctx;
 	int ret = 0;
 	bool full_sync = 0;
-	const u64 len = end - start + 1;
+	u64 len;
 
+	/*
+	 * The range length can be represented by u64, we have to do the typecasts
+	 * to avoid signed overflow if it's [0, LLONG_MAX] eg. from fsync()
+	 */
+	len = (u64)end - (u64)start + 1;
 	trace_btrfs_sync_file(file, datasync);
 
 	/*
@@ -1888,7 +1931,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	if (ret)
 		return ret;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	atomic_inc(&root->log_batch);
 	full_sync = test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
 			     &BTRFS_I(inode)->runtime_flags);
@@ -1940,7 +1983,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		ret = start_ordered_ops(inode, start, end);
 	}
 	if (ret) {
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 		goto out;
 	}
 	atomic_inc(&root->log_batch);
@@ -1975,10 +2018,11 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	 */
 	smp_mb();
 	if (btrfs_inode_in_log(inode, root->fs_info->generation) ||
-	    (BTRFS_I(inode)->last_trans <=
-	     root->fs_info->last_trans_committed &&
-	     (full_sync ||
-	      !btrfs_have_ordered_extents_in_range(inode, start, len)))) {
+	    (full_sync && BTRFS_I(inode)->last_trans <=
+	     root->fs_info->last_trans_committed) ||
+	    (!btrfs_have_ordered_extents_in_range(inode, start, len) &&
+	     BTRFS_I(inode)->last_trans
+	     <= root->fs_info->last_trans_committed)) {
 		/*
 		 * We'v had everything committed since the last time we were
 		 * modified so clear this flag in case it was set for whatever
@@ -1986,7 +2030,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		 */
 		clear_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
 			  &BTRFS_I(inode)->runtime_flags);
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 		goto out;
 	}
 
@@ -2010,7 +2054,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 		goto out;
 	}
 	trans->sync = true;
@@ -2033,7 +2077,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	 * file again, but that will end up using the synchronization
 	 * inside btrfs_sync_log to keep things safe.
 	 */
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	/*
 	 * If any of the ordered extents had an error, just return it to user
@@ -2063,8 +2107,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 			}
 		}
 		if (!full_sync) {
-			ret = btrfs_wait_ordered_range(inode, start,
-						       end - start + 1);
+			ret = btrfs_wait_ordered_range(inode, start, len);
 			if (ret) {
 				btrfs_end_transaction(trans, root);
 				goto out;
@@ -2273,18 +2316,18 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	int ret = 0;
 	int err = 0;
 	unsigned int rsv_count;
-	bool same_page;
+	bool same_block;
 	bool no_holes = btrfs_fs_incompat(root->fs_info, NO_HOLES);
 	u64 ino_size;
-	bool truncated_page = false;
+	bool truncated_block = false;
 	bool updated_inode = false;
 
 	ret = btrfs_wait_ordered_range(inode, offset, len);
 	if (ret)
 		return ret;
 
-	mutex_lock(&inode->i_mutex);
-	ino_size = round_up(inode->i_size, PAGE_CACHE_SIZE);
+	inode_lock(inode);
+	ino_size = round_up(inode->i_size, root->sectorsize);
 	ret = find_first_non_hole(inode, &offset, &len);
 	if (ret < 0)
 		goto out_only_mutex;
@@ -2297,33 +2340,32 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	lockstart = round_up(offset, BTRFS_I(inode)->root->sectorsize);
 	lockend = round_down(offset + len,
 			     BTRFS_I(inode)->root->sectorsize) - 1;
-	same_page = ((offset >> PAGE_CACHE_SHIFT) ==
-		    ((offset + len - 1) >> PAGE_CACHE_SHIFT));
-
+	same_block = (BTRFS_BYTES_TO_BLKS(root->fs_info, offset))
+		== (BTRFS_BYTES_TO_BLKS(root->fs_info, offset + len - 1));
 	/*
-	 * We needn't truncate any page which is beyond the end of the file
+	 * We needn't truncate any block which is beyond the end of the file
 	 * because we are sure there is no data there.
 	 */
 	/*
-	 * Only do this if we are in the same page and we aren't doing the
-	 * entire page.
+	 * Only do this if we are in the same block and we aren't doing the
+	 * entire block.
 	 */
-	if (same_page && len < PAGE_CACHE_SIZE) {
+	if (same_block && len < root->sectorsize) {
 		if (offset < ino_size) {
-			truncated_page = true;
-			ret = btrfs_truncate_page(inode, offset, len, 0);
+			truncated_block = true;
+			ret = btrfs_truncate_block(inode, offset, len, 0);
 		} else {
 			ret = 0;
 		}
 		goto out_only_mutex;
 	}
 
-	/* zero back part of the first page */
+	/* zero back part of the first block */
 	if (offset < ino_size) {
-		truncated_page = true;
-		ret = btrfs_truncate_page(inode, offset, 0, 0);
+		truncated_block = true;
+		ret = btrfs_truncate_block(inode, offset, 0, 0);
 		if (ret) {
-			mutex_unlock(&inode->i_mutex);
+			inode_unlock(inode);
 			return ret;
 		}
 	}
@@ -2356,9 +2398,10 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 		if (!ret) {
 			/* zero the front end of the last page */
 			if (tail_start + tail_len < ino_size) {
-				truncated_page = true;
-				ret = btrfs_truncate_page(inode,
-						tail_start + tail_len, 0, 1);
+				truncated_block = true;
+				ret = btrfs_truncate_block(inode,
+							tail_start + tail_len,
+							0, 1);
 				if (ret)
 					goto out_only_mutex;
 			}
@@ -2376,7 +2419,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 		truncate_pagecache_range(inode, lockstart, lockend);
 
 		lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend,
-				 0, &cached_state);
+				 &cached_state);
 		ordered = btrfs_lookup_first_ordered_extent(inode, lockend);
 
 		/*
@@ -2399,7 +2442,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 		ret = btrfs_wait_ordered_range(inode, lockstart,
 					       lockend - lockstart + 1);
 		if (ret) {
-			mutex_unlock(&inode->i_mutex);
+			inode_unlock(inode);
 			return ret;
 		}
 	}
@@ -2524,7 +2567,7 @@ out_trans:
 		goto out_free;
 
 	inode_inc_iversion(inode);
-	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+	inode->i_mtime = inode->i_ctime = current_fs_time(inode->i_sb);
 
 	trans->block_rsv = &root->fs_info->trans_block_rsv;
 	ret = btrfs_update_inode(trans, root, inode);
@@ -2538,7 +2581,7 @@ out:
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			     &cached_state, GFP_NOFS);
 out_only_mutex:
-	if (!updated_inode && truncated_page && !ret && !err) {
+	if (!updated_inode && truncated_block && !ret && !err) {
 		/*
 		 * If we only end up zeroing part of a page, we still need to
 		 * update the inode item, so that all the time fields are
@@ -2554,7 +2597,7 @@ out_only_mutex:
 			ret = btrfs_end_transaction(trans, root);
 		}
 	}
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	if (ret && !err)
 		err = ret;
 	return err;
@@ -2591,7 +2634,7 @@ static int add_falloc_range(struct list_head *head, u64 start, u64 len)
 		return 0;
 	}
 insert:
-	range = kmalloc(sizeof(*range), GFP_NOFS);
+	range = kmalloc(sizeof(*range), GFP_KERNEL);
 	if (!range)
 		return -ENOMEM;
 	range->start = start;
@@ -2638,10 +2681,13 @@ static long btrfs_fallocate(struct file *file, int mode,
 	if (ret < 0)
 		return ret;
 
-	mutex_lock(&inode->i_mutex);
-	ret = inode_newsize_ok(inode, alloc_end);
-	if (ret)
-		goto out;
+	inode_lock(inode);
+
+	if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) {
+		ret = inode_newsize_ok(inode, offset + len);
+		if (ret)
+			goto out;
+	}
 
 	/*
 	 * TODO: Move these two operations after we have checked
@@ -2658,10 +2704,10 @@ static long btrfs_fallocate(struct file *file, int mode,
 	} else if (offset + len > inode->i_size) {
 		/*
 		 * If we are fallocating from the end of the file onward we
-		 * need to zero out the end of the page if i_size lands in the
-		 * middle of a page.
+		 * need to zero out the end of the block if i_size lands in the
+		 * middle of a block.
 		 */
-		ret = btrfs_truncate_page(inode, inode->i_size, 0, 0);
+		ret = btrfs_truncate_block(inode, inode->i_size, 0, 0);
 		if (ret)
 			goto out;
 	}
@@ -2683,7 +2729,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 		 * transaction
 		 */
 		lock_extent_bits(&BTRFS_I(inode)->io_tree, alloc_start,
-				 locked_end, 0, &cached_state);
+				 locked_end, &cached_state);
 		ordered = btrfs_lookup_first_ordered_extent(inode,
 							    alloc_end - 1);
 		if (ordered &&
@@ -2692,7 +2738,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 			btrfs_put_ordered_extent(ordered);
 			unlock_extent_cached(&BTRFS_I(inode)->io_tree,
 					     alloc_start, locked_end,
-					     &cached_state, GFP_NOFS);
+					     &cached_state, GFP_KERNEL);
 			/*
 			 * we can't wait on the range with the transaction
 			 * running or with the extent lock held
@@ -2774,7 +2820,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 		if (IS_ERR(trans)) {
 			ret = PTR_ERR(trans);
 		} else {
-			inode->i_ctime = CURRENT_TIME;
+			inode->i_ctime = current_fs_time(inode->i_sb);
 			i_size_write(inode, actual_end);
 			btrfs_ordered_update_i_size(inode, actual_end, NULL);
 			ret = btrfs_update_inode(trans, root, inode);
@@ -2786,7 +2832,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 	}
 out_unlock:
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end,
-			     &cached_state, GFP_NOFS);
+			     &cached_state, GFP_KERNEL);
 out:
 	/*
 	 * As we waited the extent range, the data_rsv_map must be empty
@@ -2796,7 +2842,7 @@ out:
 	 * So this is completely used as cleanup.
 	 */
 	btrfs_qgroup_free_data(inode, alloc_start, alloc_end - alloc_start);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	/* Let go of our reservation. */
 	btrfs_free_reserved_data_space(inode, alloc_start,
 				       alloc_end - alloc_start);
@@ -2830,7 +2876,7 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
 	lockend--;
 	len = lockend - lockstart + 1;
 
-	lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend, 0,
+	lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			 &cached_state);
 
 	while (start < inode->i_size) {
@@ -2872,7 +2918,7 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int whence)
 	struct inode *inode = file->f_mapping->host;
 	int ret;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	switch (whence) {
 	case SEEK_END:
 	case SEEK_CUR:
@@ -2881,20 +2927,20 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int whence)
 	case SEEK_DATA:
 	case SEEK_HOLE:
 		if (offset >= i_size_read(inode)) {
-			mutex_unlock(&inode->i_mutex);
+			inode_unlock(inode);
 			return -ENXIO;
 		}
 
 		ret = find_desired_extent(inode, &offset, whence);
 		if (ret) {
-			mutex_unlock(&inode->i_mutex);
+			inode_unlock(inode);
 			return ret;
 		}
 	}
 
 	offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return offset;
 }
 
@@ -2912,12 +2958,14 @@ const struct file_operations btrfs_file_operations = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= btrfs_ioctl,
 #endif
+	.copy_file_range = btrfs_copy_file_range,
+	.clone_file_range = btrfs_clone_file_range,
+	.dedupe_file_range = btrfs_dedupe_file_range,
 };
 
 void btrfs_auto_defrag_exit(void)
 {
-	if (btrfs_inode_defrag_cachep)
-		kmem_cache_destroy(btrfs_inode_defrag_cachep);
+	kmem_cache_destroy(btrfs_inode_defrag_cachep);
 }
 
 int btrfs_auto_defrag_init(void)
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 0948d34cb84a..5e6062c26129 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -29,8 +29,8 @@
 #include "inode-map.h"
 #include "volumes.h"
 
-#define BITS_PER_BITMAP		(PAGE_CACHE_SIZE * 8)
-#define MAX_CACHE_BYTES_PER_GIG	(32 * 1024)
+#define BITS_PER_BITMAP		(PAGE_SIZE * 8)
+#define MAX_CACHE_BYTES_PER_GIG	SZ_32K
 
 struct btrfs_trim_range {
 	u64 start;
@@ -85,8 +85,8 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root,
 	}
 
 	mapping_set_gfp_mask(inode->i_mapping,
-			mapping_gfp_mask(inode->i_mapping) &
-			~(__GFP_FS | __GFP_HIGHMEM));
+			mapping_gfp_constraint(inode->i_mapping,
+			~(__GFP_FS | __GFP_HIGHMEM)));
 
 	return inode;
 }
@@ -295,7 +295,7 @@ static int readahead_cache(struct inode *inode)
 		return -ENOMEM;
 
 	file_ra_state_init(ra, inode->i_mapping);
-	last_index = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT;
+	last_index = (i_size_read(inode) - 1) >> PAGE_SHIFT;
 
 	page_cache_sync_readahead(inode->i_mapping, ra, NULL, 0, last_index);
 
@@ -310,14 +310,14 @@ static int io_ctl_init(struct btrfs_io_ctl *io_ctl, struct inode *inode,
 	int num_pages;
 	int check_crcs = 0;
 
-	num_pages = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE);
+	num_pages = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
 
 	if (btrfs_ino(inode) != BTRFS_FREE_INO_OBJECTID)
 		check_crcs = 1;
 
 	/* Make sure we can fit our crcs into the first page */
 	if (write && check_crcs &&
-	    (num_pages * sizeof(u32)) >= PAGE_CACHE_SIZE)
+	    (num_pages * sizeof(u32)) >= PAGE_SIZE)
 		return -ENOSPC;
 
 	memset(io_ctl, 0, sizeof(struct btrfs_io_ctl));
@@ -354,9 +354,9 @@ static void io_ctl_map_page(struct btrfs_io_ctl *io_ctl, int clear)
 	io_ctl->page = io_ctl->pages[io_ctl->index++];
 	io_ctl->cur = page_address(io_ctl->page);
 	io_ctl->orig = io_ctl->cur;
-	io_ctl->size = PAGE_CACHE_SIZE;
+	io_ctl->size = PAGE_SIZE;
 	if (clear)
-		memset(io_ctl->cur, 0, PAGE_CACHE_SIZE);
+		memset(io_ctl->cur, 0, PAGE_SIZE);
 }
 
 static void io_ctl_drop_pages(struct btrfs_io_ctl *io_ctl)
@@ -369,7 +369,7 @@ static void io_ctl_drop_pages(struct btrfs_io_ctl *io_ctl)
 		if (io_ctl->pages[i]) {
 			ClearPageChecked(io_ctl->pages[i]);
 			unlock_page(io_ctl->pages[i]);
-			page_cache_release(io_ctl->pages[i]);
+			put_page(io_ctl->pages[i]);
 		}
 	}
 }
@@ -475,7 +475,7 @@ static void io_ctl_set_crc(struct btrfs_io_ctl *io_ctl, int index)
 		offset = sizeof(u32) * io_ctl->num_pages;
 
 	crc = btrfs_csum_data(io_ctl->orig + offset, crc,
-			      PAGE_CACHE_SIZE - offset);
+			      PAGE_SIZE - offset);
 	btrfs_csum_final(crc, (char *)&crc);
 	io_ctl_unmap_page(io_ctl);
 	tmp = page_address(io_ctl->pages[0]);
@@ -503,7 +503,7 @@ static int io_ctl_check_crc(struct btrfs_io_ctl *io_ctl, int index)
 
 	io_ctl_map_page(io_ctl, 0);
 	crc = btrfs_csum_data(io_ctl->orig + offset, crc,
-			      PAGE_CACHE_SIZE - offset);
+			      PAGE_SIZE - offset);
 	btrfs_csum_final(crc, (char *)&crc);
 	if (val != crc) {
 		btrfs_err_rl(io_ctl->root->fs_info,
@@ -561,7 +561,7 @@ static int io_ctl_add_bitmap(struct btrfs_io_ctl *io_ctl, void *bitmap)
 		io_ctl_map_page(io_ctl, 0);
 	}
 
-	memcpy(io_ctl->cur, bitmap, PAGE_CACHE_SIZE);
+	memcpy(io_ctl->cur, bitmap, PAGE_SIZE);
 	io_ctl_set_crc(io_ctl, io_ctl->index - 1);
 	if (io_ctl->index < io_ctl->num_pages)
 		io_ctl_map_page(io_ctl, 0);
@@ -621,7 +621,7 @@ static int io_ctl_read_bitmap(struct btrfs_io_ctl *io_ctl,
 	if (ret)
 		return ret;
 
-	memcpy(entry->bitmap, io_ctl->cur, PAGE_CACHE_SIZE);
+	memcpy(entry->bitmap, io_ctl->cur, PAGE_SIZE);
 	io_ctl_unmap_page(io_ctl);
 
 	return 0;
@@ -775,7 +775,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
 		} else {
 			ASSERT(num_bitmaps);
 			num_bitmaps--;
-			e->bitmap = kzalloc(PAGE_CACHE_SIZE, GFP_NOFS);
+			e->bitmap = kzalloc(PAGE_SIZE, GFP_NOFS);
 			if (!e->bitmap) {
 				kmem_cache_free(
 					btrfs_free_space_cachep, e);
@@ -891,7 +891,7 @@ out:
 		spin_unlock(&block_group->lock);
 		ret = 0;
 
-		btrfs_warn(fs_info, "failed to load free space cache for block group %llu, rebuild it now",
+		btrfs_warn(fs_info, "failed to load free space cache for block group %llu, rebuilding it now",
 			block_group->key.objectid);
 	}
 
@@ -1086,14 +1086,11 @@ write_pinned_extent_entries(struct btrfs_root *root,
 static noinline_for_stack int
 write_bitmap_entries(struct btrfs_io_ctl *io_ctl, struct list_head *bitmap_list)
 {
-	struct list_head *pos, *n;
+	struct btrfs_free_space *entry, *next;
 	int ret;
 
 	/* Write out the bitmaps */
-	list_for_each_safe(pos, n, bitmap_list) {
-		struct btrfs_free_space *entry =
-			list_entry(pos, struct btrfs_free_space, list);
-
+	list_for_each_entry_safe(entry, next, bitmap_list, list) {
 		ret = io_ctl_add_bitmap(io_ctl, entry->bitmap);
 		if (ret)
 			return -ENOSPC;
@@ -1119,13 +1116,10 @@ static int flush_dirty_cache(struct inode *inode)
 static void noinline_for_stack
 cleanup_bitmap_list(struct list_head *bitmap_list)
 {
-	struct list_head *pos, *n;
+	struct btrfs_free_space *entry, *next;
 
-	list_for_each_safe(pos, n, bitmap_list) {
-		struct btrfs_free_space *entry =
-			list_entry(pos, struct btrfs_free_space, list);
+	list_for_each_entry_safe(entry, next, bitmap_list, list)
 		list_del_init(&entry->list);
-	}
 }
 
 static void noinline_for_stack
@@ -1261,7 +1255,7 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
 		goto out;
 
 	lock_extent_bits(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1,
-			 0, &cached_state);
+			 &cached_state);
 
 	io_ctl_set_generation(io_ctl, trans->transid);
 
@@ -1656,18 +1650,17 @@ static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl)
 	 * at or below 32k, so we need to adjust how much memory we allow to be
 	 * used by extent based free space tracking
 	 */
-	if (size < 1024 * 1024 * 1024)
+	if (size < SZ_1G)
 		max_bytes = MAX_CACHE_BYTES_PER_GIG;
 	else
-		max_bytes = MAX_CACHE_BYTES_PER_GIG *
-			div_u64(size, 1024 * 1024 * 1024);
+		max_bytes = MAX_CACHE_BYTES_PER_GIG * div_u64(size, SZ_1G);
 
 	/*
 	 * we want to account for 1 more bitmap than what we have so we can make
 	 * sure we don't go over our overall goal of MAX_CACHE_BYTES_PER_GIG as
 	 * we add more bitmaps.
 	 */
-	bitmap_bytes = (ctl->total_bitmaps + 1) * PAGE_CACHE_SIZE;
+	bitmap_bytes = (ctl->total_bitmaps + 1) * PAGE_SIZE;
 
 	if (bitmap_bytes >= max_bytes) {
 		ctl->extents_thresh = 0;
@@ -2016,7 +2009,7 @@ static bool use_bitmap(struct btrfs_free_space_ctl *ctl,
 	return true;
 }
 
-static struct btrfs_free_space_op free_space_op = {
+static const struct btrfs_free_space_op free_space_op = {
 	.recalc_thresholds	= recalculate_thresholds,
 	.use_bitmap		= use_bitmap,
 };
@@ -2118,7 +2111,7 @@ new_bitmap:
 		}
 
 		/* allocate the bitmap */
-		info->bitmap = kzalloc(PAGE_CACHE_SIZE, GFP_NOFS);
+		info->bitmap = kzalloc(PAGE_SIZE, GFP_NOFS);
 		spin_lock(&ctl->tree_lock);
 		if (!info->bitmap) {
 			ret = -ENOMEM;
@@ -2489,8 +2482,7 @@ void btrfs_init_free_space_ctl(struct btrfs_block_group_cache *block_group)
 	 * track of free space, and if we pass 1/2 of that we want to
 	 * start converting things over to using bitmaps
 	 */
-	ctl->extents_thresh = ((1024 * 32) / 2) /
-				sizeof(struct btrfs_free_space);
+	ctl->extents_thresh = (SZ_32K / 2) / sizeof(struct btrfs_free_space);
 }
 
 /*
@@ -2972,7 +2964,7 @@ setup_cluster_bitmap(struct btrfs_block_group_cache *block_group,
 		     u64 cont1_bytes, u64 min_bytes)
 {
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
-	struct btrfs_free_space *entry;
+	struct btrfs_free_space *entry = NULL;
 	int ret = -ENOSPC;
 	u64 bitmap_offset = offset_to_bitmap(ctl, offset);
 
@@ -2983,8 +2975,10 @@ setup_cluster_bitmap(struct btrfs_block_group_cache *block_group,
 	 * The bitmap that covers offset won't be in the list unless offset
 	 * is just its start offset.
 	 */
-	entry = list_first_entry(bitmaps, struct btrfs_free_space, list);
-	if (entry->offset != bitmap_offset) {
+	if (!list_empty(bitmaps))
+		entry = list_first_entry(bitmaps, struct btrfs_free_space, list);
+
+	if (!entry || entry->offset != bitmap_offset) {
 		entry = tree_search_offset(ctl, bitmap_offset, 1, 0);
 		if (entry && list_empty(&entry->list))
 			list_add(&entry->list, bitmaps);
@@ -3586,7 +3580,7 @@ again:
 	}
 
 	if (!map) {
-		map = kzalloc(PAGE_CACHE_SIZE, GFP_NOFS);
+		map = kzalloc(PAGE_SIZE, GFP_NOFS);
 		if (!map) {
 			kmem_cache_free(btrfs_free_space_cachep, info);
 			return -ENOMEM;
diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h
index f251865eb6f3..33178c490ace 100644
--- a/fs/btrfs/free-space-cache.h
+++ b/fs/btrfs/free-space-cache.h
@@ -37,7 +37,7 @@ struct btrfs_free_space_ctl {
 	int total_bitmaps;
 	int unit;
 	u64 start;
-	struct btrfs_free_space_op *op;
+	const struct btrfs_free_space_op *op;
 	void *private;
 	struct mutex cache_writeout_mutex;
 	struct list_head trimming_ranges;
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
new file mode 100644
index 000000000000..53dbeaf6ce94
--- /dev/null
+++ b/fs/btrfs/free-space-tree.c
@@ -0,0 +1,1605 @@
+/*
+ * Copyright (C) 2015 Facebook.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#include <linux/kernel.h>
+#include <linux/vmalloc.h>
+#include "ctree.h"
+#include "disk-io.h"
+#include "locking.h"
+#include "free-space-tree.h"
+#include "transaction.h"
+
+static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
+					struct btrfs_fs_info *fs_info,
+					struct btrfs_block_group_cache *block_group,
+					struct btrfs_path *path);
+
+void set_free_space_tree_thresholds(struct btrfs_block_group_cache *cache)
+{
+	u32 bitmap_range;
+	size_t bitmap_size;
+	u64 num_bitmaps, total_bitmap_size;
+
+	/*
+	 * We convert to bitmaps when the disk space required for using extents
+	 * exceeds that required for using bitmaps.
+	 */
+	bitmap_range = cache->sectorsize * BTRFS_FREE_SPACE_BITMAP_BITS;
+	num_bitmaps = div_u64(cache->key.offset + bitmap_range - 1,
+			      bitmap_range);
+	bitmap_size = sizeof(struct btrfs_item) + BTRFS_FREE_SPACE_BITMAP_SIZE;
+	total_bitmap_size = num_bitmaps * bitmap_size;
+	cache->bitmap_high_thresh = div_u64(total_bitmap_size,
+					    sizeof(struct btrfs_item));
+
+	/*
+	 * We allow for a small buffer between the high threshold and low
+	 * threshold to avoid thrashing back and forth between the two formats.
+	 */
+	if (cache->bitmap_high_thresh > 100)
+		cache->bitmap_low_thresh = cache->bitmap_high_thresh - 100;
+	else
+		cache->bitmap_low_thresh = 0;
+}
+
+static int add_new_free_space_info(struct btrfs_trans_handle *trans,
+				   struct btrfs_fs_info *fs_info,
+				   struct btrfs_block_group_cache *block_group,
+				   struct btrfs_path *path)
+{
+	struct btrfs_root *root = fs_info->free_space_root;
+	struct btrfs_free_space_info *info;
+	struct btrfs_key key;
+	struct extent_buffer *leaf;
+	int ret;
+
+	key.objectid = block_group->key.objectid;
+	key.type = BTRFS_FREE_SPACE_INFO_KEY;
+	key.offset = block_group->key.offset;
+
+	ret = btrfs_insert_empty_item(trans, root, path, &key, sizeof(*info));
+	if (ret)
+		goto out;
+
+	leaf = path->nodes[0];
+	info = btrfs_item_ptr(leaf, path->slots[0],
+			      struct btrfs_free_space_info);
+	btrfs_set_free_space_extent_count(leaf, info, 0);
+	btrfs_set_free_space_flags(leaf, info, 0);
+	btrfs_mark_buffer_dirty(leaf);
+
+	ret = 0;
+out:
+	btrfs_release_path(path);
+	return ret;
+}
+
+struct btrfs_free_space_info *
+search_free_space_info(struct btrfs_trans_handle *trans,
+		       struct btrfs_fs_info *fs_info,
+		       struct btrfs_block_group_cache *block_group,
+		       struct btrfs_path *path, int cow)
+{
+	struct btrfs_root *root = fs_info->free_space_root;
+	struct btrfs_key key;
+	int ret;
+
+	key.objectid = block_group->key.objectid;
+	key.type = BTRFS_FREE_SPACE_INFO_KEY;
+	key.offset = block_group->key.offset;
+
+	ret = btrfs_search_slot(trans, root, &key, path, 0, cow);
+	if (ret < 0)
+		return ERR_PTR(ret);
+	if (ret != 0) {
+		btrfs_warn(fs_info, "missing free space info for %llu\n",
+			   block_group->key.objectid);
+		ASSERT(0);
+		return ERR_PTR(-ENOENT);
+	}
+
+	return btrfs_item_ptr(path->nodes[0], path->slots[0],
+			      struct btrfs_free_space_info);
+}
+
+/*
+ * btrfs_search_slot() but we're looking for the greatest key less than the
+ * passed key.
+ */
+static int btrfs_search_prev_slot(struct btrfs_trans_handle *trans,
+				  struct btrfs_root *root,
+				  struct btrfs_key *key, struct btrfs_path *p,
+				  int ins_len, int cow)
+{
+	int ret;
+
+	ret = btrfs_search_slot(trans, root, key, p, ins_len, cow);
+	if (ret < 0)
+		return ret;
+
+	if (ret == 0) {
+		ASSERT(0);
+		return -EIO;
+	}
+
+	if (p->slots[0] == 0) {
+		ASSERT(0);
+		return -EIO;
+	}
+	p->slots[0]--;
+
+	return 0;
+}
+
+static inline u32 free_space_bitmap_size(u64 size, u32 sectorsize)
+{
+	return DIV_ROUND_UP((u32)div_u64(size, sectorsize), BITS_PER_BYTE);
+}
+
+static unsigned long *alloc_bitmap(u32 bitmap_size)
+{
+	void *mem;
+
+	/*
+	 * The allocation size varies, observed numbers were < 4K up to 16K.
+	 * Using vmalloc unconditionally would be too heavy, we'll try
+	 * contiguous allocations first.
+	 */
+	if  (bitmap_size <= PAGE_SIZE)
+		return kzalloc(bitmap_size, GFP_NOFS);
+
+	mem = kzalloc(bitmap_size, GFP_NOFS | __GFP_NOWARN);
+	if (mem)
+		return mem;
+
+	return __vmalloc(bitmap_size, GFP_NOFS | __GFP_HIGHMEM | __GFP_ZERO,
+			 PAGE_KERNEL);
+}
+
+int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
+				  struct btrfs_fs_info *fs_info,
+				  struct btrfs_block_group_cache *block_group,
+				  struct btrfs_path *path)
+{
+	struct btrfs_root *root = fs_info->free_space_root;
+	struct btrfs_free_space_info *info;
+	struct btrfs_key key, found_key;
+	struct extent_buffer *leaf;
+	unsigned long *bitmap;
+	char *bitmap_cursor;
+	u64 start, end;
+	u64 bitmap_range, i;
+	u32 bitmap_size, flags, expected_extent_count;
+	u32 extent_count = 0;
+	int done = 0, nr;
+	int ret;
+
+	bitmap_size = free_space_bitmap_size(block_group->key.offset,
+					     block_group->sectorsize);
+	bitmap = alloc_bitmap(bitmap_size);
+	if (!bitmap) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	start = block_group->key.objectid;
+	end = block_group->key.objectid + block_group->key.offset;
+
+	key.objectid = end - 1;
+	key.type = (u8)-1;
+	key.offset = (u64)-1;
+
+	while (!done) {
+		ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1);
+		if (ret)
+			goto out;
+
+		leaf = path->nodes[0];
+		nr = 0;
+		path->slots[0]++;
+		while (path->slots[0] > 0) {
+			btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1);
+
+			if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) {
+				ASSERT(found_key.objectid == block_group->key.objectid);
+				ASSERT(found_key.offset == block_group->key.offset);
+				done = 1;
+				break;
+			} else if (found_key.type == BTRFS_FREE_SPACE_EXTENT_KEY) {
+				u64 first, last;
+
+				ASSERT(found_key.objectid >= start);
+				ASSERT(found_key.objectid < end);
+				ASSERT(found_key.objectid + found_key.offset <= end);
+
+				first = div_u64(found_key.objectid - start,
+						block_group->sectorsize);
+				last = div_u64(found_key.objectid + found_key.offset - start,
+					       block_group->sectorsize);
+				bitmap_set(bitmap, first, last - first);
+
+				extent_count++;
+				nr++;
+				path->slots[0]--;
+			} else {
+				ASSERT(0);
+			}
+		}
+
+		ret = btrfs_del_items(trans, root, path, path->slots[0], nr);
+		if (ret)
+			goto out;
+		btrfs_release_path(path);
+	}
+
+	info = search_free_space_info(trans, fs_info, block_group, path, 1);
+	if (IS_ERR(info)) {
+		ret = PTR_ERR(info);
+		goto out;
+	}
+	leaf = path->nodes[0];
+	flags = btrfs_free_space_flags(leaf, info);
+	flags |= BTRFS_FREE_SPACE_USING_BITMAPS;
+	btrfs_set_free_space_flags(leaf, info, flags);
+	expected_extent_count = btrfs_free_space_extent_count(leaf, info);
+	btrfs_mark_buffer_dirty(leaf);
+	btrfs_release_path(path);
+
+	if (extent_count != expected_extent_count) {
+		btrfs_err(fs_info, "incorrect extent count for %llu; counted %u, expected %u",
+			  block_group->key.objectid, extent_count,
+			  expected_extent_count);
+		ASSERT(0);
+		ret = -EIO;
+		goto out;
+	}
+
+	bitmap_cursor = (char *)bitmap;
+	bitmap_range = block_group->sectorsize * BTRFS_FREE_SPACE_BITMAP_BITS;
+	i = start;
+	while (i < end) {
+		unsigned long ptr;
+		u64 extent_size;
+		u32 data_size;
+
+		extent_size = min(end - i, bitmap_range);
+		data_size = free_space_bitmap_size(extent_size,
+						   block_group->sectorsize);
+
+		key.objectid = i;
+		key.type = BTRFS_FREE_SPACE_BITMAP_KEY;
+		key.offset = extent_size;
+
+		ret = btrfs_insert_empty_item(trans, root, path, &key,
+					      data_size);
+		if (ret)
+			goto out;
+
+		leaf = path->nodes[0];
+		ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
+		write_extent_buffer(leaf, bitmap_cursor, ptr,
+				    data_size);
+		btrfs_mark_buffer_dirty(leaf);
+		btrfs_release_path(path);
+
+		i += extent_size;
+		bitmap_cursor += data_size;
+	}
+
+	ret = 0;
+out:
+	kvfree(bitmap);
+	if (ret)
+		btrfs_abort_transaction(trans, root, ret);
+	return ret;
+}
+
+int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
+				  struct btrfs_fs_info *fs_info,
+				  struct btrfs_block_group_cache *block_group,
+				  struct btrfs_path *path)
+{
+	struct btrfs_root *root = fs_info->free_space_root;
+	struct btrfs_free_space_info *info;
+	struct btrfs_key key, found_key;
+	struct extent_buffer *leaf;
+	unsigned long *bitmap;
+	u64 start, end;
+	/* Initialize to silence GCC. */
+	u64 extent_start = 0;
+	u64 offset;
+	u32 bitmap_size, flags, expected_extent_count;
+	int prev_bit = 0, bit, bitnr;
+	u32 extent_count = 0;
+	int done = 0, nr;
+	int ret;
+
+	bitmap_size = free_space_bitmap_size(block_group->key.offset,
+					     block_group->sectorsize);
+	bitmap = alloc_bitmap(bitmap_size);
+	if (!bitmap) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	start = block_group->key.objectid;
+	end = block_group->key.objectid + block_group->key.offset;
+
+	key.objectid = end - 1;
+	key.type = (u8)-1;
+	key.offset = (u64)-1;
+
+	while (!done) {
+		ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1);
+		if (ret)
+			goto out;
+
+		leaf = path->nodes[0];
+		nr = 0;
+		path->slots[0]++;
+		while (path->slots[0] > 0) {
+			btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1);
+
+			if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) {
+				ASSERT(found_key.objectid == block_group->key.objectid);
+				ASSERT(found_key.offset == block_group->key.offset);
+				done = 1;
+				break;
+			} else if (found_key.type == BTRFS_FREE_SPACE_BITMAP_KEY) {
+				unsigned long ptr;
+				char *bitmap_cursor;
+				u32 bitmap_pos, data_size;
+
+				ASSERT(found_key.objectid >= start);
+				ASSERT(found_key.objectid < end);
+				ASSERT(found_key.objectid + found_key.offset <= end);
+
+				bitmap_pos = div_u64(found_key.objectid - start,
+						     block_group->sectorsize *
+						     BITS_PER_BYTE);
+				bitmap_cursor = ((char *)bitmap) + bitmap_pos;
+				data_size = free_space_bitmap_size(found_key.offset,
+								   block_group->sectorsize);
+
+				ptr = btrfs_item_ptr_offset(leaf, path->slots[0] - 1);
+				read_extent_buffer(leaf, bitmap_cursor, ptr,
+						   data_size);
+
+				nr++;
+				path->slots[0]--;
+			} else {
+				ASSERT(0);
+			}
+		}
+
+		ret = btrfs_del_items(trans, root, path, path->slots[0], nr);
+		if (ret)
+			goto out;
+		btrfs_release_path(path);
+	}
+
+	info = search_free_space_info(trans, fs_info, block_group, path, 1);
+	if (IS_ERR(info)) {
+		ret = PTR_ERR(info);
+		goto out;
+	}
+	leaf = path->nodes[0];
+	flags = btrfs_free_space_flags(leaf, info);
+	flags &= ~BTRFS_FREE_SPACE_USING_BITMAPS;
+	btrfs_set_free_space_flags(leaf, info, flags);
+	expected_extent_count = btrfs_free_space_extent_count(leaf, info);
+	btrfs_mark_buffer_dirty(leaf);
+	btrfs_release_path(path);
+
+	offset = start;
+	bitnr = 0;
+	while (offset < end) {
+		bit = !!test_bit(bitnr, bitmap);
+		if (prev_bit == 0 && bit == 1) {
+			extent_start = offset;
+		} else if (prev_bit == 1 && bit == 0) {
+			key.objectid = extent_start;
+			key.type = BTRFS_FREE_SPACE_EXTENT_KEY;
+			key.offset = offset - extent_start;
+
+			ret = btrfs_insert_empty_item(trans, root, path, &key, 0);
+			if (ret)
+				goto out;
+			btrfs_release_path(path);
+
+			extent_count++;
+		}
+		prev_bit = bit;
+		offset += block_group->sectorsize;
+		bitnr++;
+	}
+	if (prev_bit == 1) {
+		key.objectid = extent_start;
+		key.type = BTRFS_FREE_SPACE_EXTENT_KEY;
+		key.offset = end - extent_start;
+
+		ret = btrfs_insert_empty_item(trans, root, path, &key, 0);
+		if (ret)
+			goto out;
+		btrfs_release_path(path);
+
+		extent_count++;
+	}
+
+	if (extent_count != expected_extent_count) {
+		btrfs_err(fs_info, "incorrect extent count for %llu; counted %u, expected %u",
+			  block_group->key.objectid, extent_count,
+			  expected_extent_count);
+		ASSERT(0);
+		ret = -EIO;
+		goto out;
+	}
+
+	ret = 0;
+out:
+	kvfree(bitmap);
+	if (ret)
+		btrfs_abort_transaction(trans, root, ret);
+	return ret;
+}
+
+static int update_free_space_extent_count(struct btrfs_trans_handle *trans,
+					  struct btrfs_fs_info *fs_info,
+					  struct btrfs_block_group_cache *block_group,
+					  struct btrfs_path *path,
+					  int new_extents)
+{
+	struct btrfs_free_space_info *info;
+	u32 flags;
+	u32 extent_count;
+	int ret = 0;
+
+	if (new_extents == 0)
+		return 0;
+
+	info = search_free_space_info(trans, fs_info, block_group, path, 1);
+	if (IS_ERR(info)) {
+		ret = PTR_ERR(info);
+		goto out;
+	}
+	flags = btrfs_free_space_flags(path->nodes[0], info);
+	extent_count = btrfs_free_space_extent_count(path->nodes[0], info);
+
+	extent_count += new_extents;
+	btrfs_set_free_space_extent_count(path->nodes[0], info, extent_count);
+	btrfs_mark_buffer_dirty(path->nodes[0]);
+	btrfs_release_path(path);
+
+	if (!(flags & BTRFS_FREE_SPACE_USING_BITMAPS) &&
+	    extent_count > block_group->bitmap_high_thresh) {
+		ret = convert_free_space_to_bitmaps(trans, fs_info, block_group,
+						    path);
+	} else if ((flags & BTRFS_FREE_SPACE_USING_BITMAPS) &&
+		   extent_count < block_group->bitmap_low_thresh) {
+		ret = convert_free_space_to_extents(trans, fs_info, block_group,
+						    path);
+	}
+
+out:
+	return ret;
+}
+
+int free_space_test_bit(struct btrfs_block_group_cache *block_group,
+			struct btrfs_path *path, u64 offset)
+{
+	struct extent_buffer *leaf;
+	struct btrfs_key key;
+	u64 found_start, found_end;
+	unsigned long ptr, i;
+
+	leaf = path->nodes[0];
+	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+	ASSERT(key.type == BTRFS_FREE_SPACE_BITMAP_KEY);
+
+	found_start = key.objectid;
+	found_end = key.objectid + key.offset;
+	ASSERT(offset >= found_start && offset < found_end);
+
+	ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
+	i = div_u64(offset - found_start, block_group->sectorsize);
+	return !!extent_buffer_test_bit(leaf, ptr, i);
+}
+
+static void free_space_set_bits(struct btrfs_block_group_cache *block_group,
+				struct btrfs_path *path, u64 *start, u64 *size,
+				int bit)
+{
+	struct extent_buffer *leaf;
+	struct btrfs_key key;
+	u64 end = *start + *size;
+	u64 found_start, found_end;
+	unsigned long ptr, first, last;
+
+	leaf = path->nodes[0];
+	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+	ASSERT(key.type == BTRFS_FREE_SPACE_BITMAP_KEY);
+
+	found_start = key.objectid;
+	found_end = key.objectid + key.offset;
+	ASSERT(*start >= found_start && *start < found_end);
+	ASSERT(end > found_start);
+
+	if (end > found_end)
+		end = found_end;
+
+	ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
+	first = div_u64(*start - found_start, block_group->sectorsize);
+	last = div_u64(end - found_start, block_group->sectorsize);
+	if (bit)
+		extent_buffer_bitmap_set(leaf, ptr, first, last - first);
+	else
+		extent_buffer_bitmap_clear(leaf, ptr, first, last - first);
+	btrfs_mark_buffer_dirty(leaf);
+
+	*size -= end - *start;
+	*start = end;
+}
+
+/*
+ * We can't use btrfs_next_item() in modify_free_space_bitmap() because
+ * btrfs_next_leaf() doesn't get the path for writing. We can forgo the fancy
+ * tree walking in btrfs_next_leaf() anyways because we know exactly what we're
+ * looking for.
+ */
+static int free_space_next_bitmap(struct btrfs_trans_handle *trans,
+				  struct btrfs_root *root, struct btrfs_path *p)
+{
+	struct btrfs_key key;
+
+	if (p->slots[0] + 1 < btrfs_header_nritems(p->nodes[0])) {
+		p->slots[0]++;
+		return 0;
+	}
+
+	btrfs_item_key_to_cpu(p->nodes[0], &key, p->slots[0]);
+	btrfs_release_path(p);
+
+	key.objectid += key.offset;
+	key.type = (u8)-1;
+	key.offset = (u64)-1;
+
+	return btrfs_search_prev_slot(trans, root, &key, p, 0, 1);
+}
+
+/*
+ * If remove is 1, then we are removing free space, thus clearing bits in the
+ * bitmap. If remove is 0, then we are adding free space, thus setting bits in
+ * the bitmap.
+ */
+static int modify_free_space_bitmap(struct btrfs_trans_handle *trans,
+				    struct btrfs_fs_info *fs_info,
+				    struct btrfs_block_group_cache *block_group,
+				    struct btrfs_path *path,
+				    u64 start, u64 size, int remove)
+{
+	struct btrfs_root *root = fs_info->free_space_root;
+	struct btrfs_key key;
+	u64 end = start + size;
+	u64 cur_start, cur_size;
+	int prev_bit, next_bit;
+	int new_extents;
+	int ret;
+
+	/*
+	 * Read the bit for the block immediately before the extent of space if
+	 * that block is within the block group.
+	 */
+	if (start > block_group->key.objectid) {
+		u64 prev_block = start - block_group->sectorsize;
+
+		key.objectid = prev_block;
+		key.type = (u8)-1;
+		key.offset = (u64)-1;
+
+		ret = btrfs_search_prev_slot(trans, root, &key, path, 0, 1);
+		if (ret)
+			goto out;
+
+		prev_bit = free_space_test_bit(block_group, path, prev_block);
+
+		/* The previous block may have been in the previous bitmap. */
+		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+		if (start >= key.objectid + key.offset) {
+			ret = free_space_next_bitmap(trans, root, path);
+			if (ret)
+				goto out;
+		}
+	} else {
+		key.objectid = start;
+		key.type = (u8)-1;
+		key.offset = (u64)-1;
+
+		ret = btrfs_search_prev_slot(trans, root, &key, path, 0, 1);
+		if (ret)
+			goto out;
+
+		prev_bit = -1;
+	}
+
+	/*
+	 * Iterate over all of the bitmaps overlapped by the extent of space,
+	 * clearing/setting bits as required.
+	 */
+	cur_start = start;
+	cur_size = size;
+	while (1) {
+		free_space_set_bits(block_group, path, &cur_start, &cur_size,
+				    !remove);
+		if (cur_size == 0)
+			break;
+		ret = free_space_next_bitmap(trans, root, path);
+		if (ret)
+			goto out;
+	}
+
+	/*
+	 * Read the bit for the block immediately after the extent of space if
+	 * that block is within the block group.
+	 */
+	if (end < block_group->key.objectid + block_group->key.offset) {
+		/* The next block may be in the next bitmap. */
+		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+		if (end >= key.objectid + key.offset) {
+			ret = free_space_next_bitmap(trans, root, path);
+			if (ret)
+				goto out;
+		}
+
+		next_bit = free_space_test_bit(block_group, path, end);
+	} else {
+		next_bit = -1;
+	}
+
+	if (remove) {
+		new_extents = -1;
+		if (prev_bit == 1) {
+			/* Leftover on the left. */
+			new_extents++;
+		}
+		if (next_bit == 1) {
+			/* Leftover on the right. */
+			new_extents++;
+		}
+	} else {
+		new_extents = 1;
+		if (prev_bit == 1) {
+			/* Merging with neighbor on the left. */
+			new_extents--;
+		}
+		if (next_bit == 1) {
+			/* Merging with neighbor on the right. */
+			new_extents--;
+		}
+	}
+
+	btrfs_release_path(path);
+	ret = update_free_space_extent_count(trans, fs_info, block_group, path,
+					     new_extents);
+
+out:
+	return ret;
+}
+
+static int remove_free_space_extent(struct btrfs_trans_handle *trans,
+				    struct btrfs_fs_info *fs_info,
+				    struct btrfs_block_group_cache *block_group,
+				    struct btrfs_path *path,
+				    u64 start, u64 size)
+{
+	struct btrfs_root *root = fs_info->free_space_root;
+	struct btrfs_key key;
+	u64 found_start, found_end;
+	u64 end = start + size;
+	int new_extents = -1;
+	int ret;
+
+	key.objectid = start;
+	key.type = (u8)-1;
+	key.offset = (u64)-1;
+
+	ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1);
+	if (ret)
+		goto out;
+
+	btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+
+	ASSERT(key.type == BTRFS_FREE_SPACE_EXTENT_KEY);
+
+	found_start = key.objectid;
+	found_end = key.objectid + key.offset;
+	ASSERT(start >= found_start && end <= found_end);
+
+	/*
+	 * Okay, now that we've found the free space extent which contains the
+	 * free space that we are removing, there are four cases:
+	 *
+	 * 1. We're using the whole extent: delete the key we found and
+	 * decrement the free space extent count.
+	 * 2. We are using part of the extent starting at the beginning: delete
+	 * the key we found and insert a new key representing the leftover at
+	 * the end. There is no net change in the number of extents.
+	 * 3. We are using part of the extent ending at the end: delete the key
+	 * we found and insert a new key representing the leftover at the
+	 * beginning. There is no net change in the number of extents.
+	 * 4. We are using part of the extent in the middle: delete the key we
+	 * found and insert two new keys representing the leftovers on each
+	 * side. Where we used to have one extent, we now have two, so increment
+	 * the extent count. We may need to convert the block group to bitmaps
+	 * as a result.
+	 */
+
+	/* Delete the existing key (cases 1-4). */
+	ret = btrfs_del_item(trans, root, path);
+	if (ret)
+		goto out;
+
+	/* Add a key for leftovers at the beginning (cases 3 and 4). */
+	if (start > found_start) {
+		key.objectid = found_start;
+		key.type = BTRFS_FREE_SPACE_EXTENT_KEY;
+		key.offset = start - found_start;
+
+		btrfs_release_path(path);
+		ret = btrfs_insert_empty_item(trans, root, path, &key, 0);
+		if (ret)
+			goto out;
+		new_extents++;
+	}
+
+	/* Add a key for leftovers at the end (cases 2 and 4). */
+	if (end < found_end) {
+		key.objectid = end;
+		key.type = BTRFS_FREE_SPACE_EXTENT_KEY;
+		key.offset = found_end - end;
+
+		btrfs_release_path(path);
+		ret = btrfs_insert_empty_item(trans, root, path, &key, 0);
+		if (ret)
+			goto out;
+		new_extents++;
+	}
+
+	btrfs_release_path(path);
+	ret = update_free_space_extent_count(trans, fs_info, block_group, path,
+					     new_extents);
+
+out:
+	return ret;
+}
+
+int __remove_from_free_space_tree(struct btrfs_trans_handle *trans,
+				  struct btrfs_fs_info *fs_info,
+				  struct btrfs_block_group_cache *block_group,
+				  struct btrfs_path *path, u64 start, u64 size)
+{
+	struct btrfs_free_space_info *info;
+	u32 flags;
+	int ret;
+
+	if (block_group->needs_free_space) {
+		ret = __add_block_group_free_space(trans, fs_info, block_group,
+						   path);
+		if (ret)
+			return ret;
+	}
+
+	info = search_free_space_info(NULL, fs_info, block_group, path, 0);
+	if (IS_ERR(info))
+		return PTR_ERR(info);
+	flags = btrfs_free_space_flags(path->nodes[0], info);
+	btrfs_release_path(path);
+
+	if (flags & BTRFS_FREE_SPACE_USING_BITMAPS) {
+		return modify_free_space_bitmap(trans, fs_info, block_group,
+						path, start, size, 1);
+	} else {
+		return remove_free_space_extent(trans, fs_info, block_group,
+						path, start, size);
+	}
+}
+
+int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
+				struct btrfs_fs_info *fs_info,
+				u64 start, u64 size)
+{
+	struct btrfs_block_group_cache *block_group;
+	struct btrfs_path *path;
+	int ret;
+
+	if (!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE))
+		return 0;
+
+	path = btrfs_alloc_path();
+	if (!path) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	block_group = btrfs_lookup_block_group(fs_info, start);
+	if (!block_group) {
+		ASSERT(0);
+		ret = -ENOENT;
+		goto out;
+	}
+
+	mutex_lock(&block_group->free_space_lock);
+	ret = __remove_from_free_space_tree(trans, fs_info, block_group, path,
+					    start, size);
+	mutex_unlock(&block_group->free_space_lock);
+
+	btrfs_put_block_group(block_group);
+out:
+	btrfs_free_path(path);
+	if (ret)
+		btrfs_abort_transaction(trans, fs_info->free_space_root, ret);
+	return ret;
+}
+
+static int add_free_space_extent(struct btrfs_trans_handle *trans,
+				 struct btrfs_fs_info *fs_info,
+				 struct btrfs_block_group_cache *block_group,
+				 struct btrfs_path *path,
+				 u64 start, u64 size)
+{
+	struct btrfs_root *root = fs_info->free_space_root;
+	struct btrfs_key key, new_key;
+	u64 found_start, found_end;
+	u64 end = start + size;
+	int new_extents = 1;
+	int ret;
+
+	/*
+	 * We are adding a new extent of free space, but we need to merge
+	 * extents. There are four cases here:
+	 *
+	 * 1. The new extent does not have any immediate neighbors to merge
+	 * with: add the new key and increment the free space extent count. We
+	 * may need to convert the block group to bitmaps as a result.
+	 * 2. The new extent has an immediate neighbor before it: remove the
+	 * previous key and insert a new key combining both of them. There is no
+	 * net change in the number of extents.
+	 * 3. The new extent has an immediate neighbor after it: remove the next
+	 * key and insert a new key combining both of them. There is no net
+	 * change in the number of extents.
+	 * 4. The new extent has immediate neighbors on both sides: remove both
+	 * of the keys and insert a new key combining all of them. Where we used
+	 * to have two extents, we now have one, so decrement the extent count.
+	 */
+
+	new_key.objectid = start;
+	new_key.type = BTRFS_FREE_SPACE_EXTENT_KEY;
+	new_key.offset = size;
+
+	/* Search for a neighbor on the left. */
+	if (start == block_group->key.objectid)
+		goto right;
+	key.objectid = start - 1;
+	key.type = (u8)-1;
+	key.offset = (u64)-1;
+
+	ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1);
+	if (ret)
+		goto out;
+
+	btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+
+	if (key.type != BTRFS_FREE_SPACE_EXTENT_KEY) {
+		ASSERT(key.type == BTRFS_FREE_SPACE_INFO_KEY);
+		btrfs_release_path(path);
+		goto right;
+	}
+
+	found_start = key.objectid;
+	found_end = key.objectid + key.offset;
+	ASSERT(found_start >= block_group->key.objectid &&
+	       found_end > block_group->key.objectid);
+	ASSERT(found_start < start && found_end <= start);
+
+	/*
+	 * Delete the neighbor on the left and absorb it into the new key (cases
+	 * 2 and 4).
+	 */
+	if (found_end == start) {
+		ret = btrfs_del_item(trans, root, path);
+		if (ret)
+			goto out;
+		new_key.objectid = found_start;
+		new_key.offset += key.offset;
+		new_extents--;
+	}
+	btrfs_release_path(path);
+
+right:
+	/* Search for a neighbor on the right. */
+	if (end == block_group->key.objectid + block_group->key.offset)
+		goto insert;
+	key.objectid = end;
+	key.type = (u8)-1;
+	key.offset = (u64)-1;
+
+	ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1);
+	if (ret)
+		goto out;
+
+	btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+
+	if (key.type != BTRFS_FREE_SPACE_EXTENT_KEY) {
+		ASSERT(key.type == BTRFS_FREE_SPACE_INFO_KEY);
+		btrfs_release_path(path);
+		goto insert;
+	}
+
+	found_start = key.objectid;
+	found_end = key.objectid + key.offset;
+	ASSERT(found_start >= block_group->key.objectid &&
+	       found_end > block_group->key.objectid);
+	ASSERT((found_start < start && found_end <= start) ||
+	       (found_start >= end && found_end > end));
+
+	/*
+	 * Delete the neighbor on the right and absorb it into the new key
+	 * (cases 3 and 4).
+	 */
+	if (found_start == end) {
+		ret = btrfs_del_item(trans, root, path);
+		if (ret)
+			goto out;
+		new_key.offset += key.offset;
+		new_extents--;
+	}
+	btrfs_release_path(path);
+
+insert:
+	/* Insert the new key (cases 1-4). */
+	ret = btrfs_insert_empty_item(trans, root, path, &new_key, 0);
+	if (ret)
+		goto out;
+
+	btrfs_release_path(path);
+	ret = update_free_space_extent_count(trans, fs_info, block_group, path,
+					     new_extents);
+
+out:
+	return ret;
+}
+
+int __add_to_free_space_tree(struct btrfs_trans_handle *trans,
+			     struct btrfs_fs_info *fs_info,
+			     struct btrfs_block_group_cache *block_group,
+			     struct btrfs_path *path, u64 start, u64 size)
+{
+	struct btrfs_free_space_info *info;
+	u32 flags;
+	int ret;
+
+	if (block_group->needs_free_space) {
+		ret = __add_block_group_free_space(trans, fs_info, block_group,
+						   path);
+		if (ret)
+			return ret;
+	}
+
+	info = search_free_space_info(NULL, fs_info, block_group, path, 0);
+	if (IS_ERR(info))
+		return PTR_ERR(info);
+	flags = btrfs_free_space_flags(path->nodes[0], info);
+	btrfs_release_path(path);
+
+	if (flags & BTRFS_FREE_SPACE_USING_BITMAPS) {
+		return modify_free_space_bitmap(trans, fs_info, block_group,
+						path, start, size, 0);
+	} else {
+		return add_free_space_extent(trans, fs_info, block_group, path,
+					     start, size);
+	}
+}
+
+int add_to_free_space_tree(struct btrfs_trans_handle *trans,
+			   struct btrfs_fs_info *fs_info,
+			   u64 start, u64 size)
+{
+	struct btrfs_block_group_cache *block_group;
+	struct btrfs_path *path;
+	int ret;
+
+	if (!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE))
+		return 0;
+
+	path = btrfs_alloc_path();
+	if (!path) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	block_group = btrfs_lookup_block_group(fs_info, start);
+	if (!block_group) {
+		ASSERT(0);
+		ret = -ENOENT;
+		goto out;
+	}
+
+	mutex_lock(&block_group->free_space_lock);
+	ret = __add_to_free_space_tree(trans, fs_info, block_group, path, start,
+				       size);
+	mutex_unlock(&block_group->free_space_lock);
+
+	btrfs_put_block_group(block_group);
+out:
+	btrfs_free_path(path);
+	if (ret)
+		btrfs_abort_transaction(trans, fs_info->free_space_root, ret);
+	return ret;
+}
+
+/*
+ * Populate the free space tree by walking the extent tree. Operations on the
+ * extent tree that happen as a result of writes to the free space tree will go
+ * through the normal add/remove hooks.
+ */
+static int populate_free_space_tree(struct btrfs_trans_handle *trans,
+				    struct btrfs_fs_info *fs_info,
+				    struct btrfs_block_group_cache *block_group)
+{
+	struct btrfs_root *extent_root = fs_info->extent_root;
+	struct btrfs_path *path, *path2;
+	struct btrfs_key key;
+	u64 start, end;
+	int ret;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+	path->reada = 1;
+
+	path2 = btrfs_alloc_path();
+	if (!path2) {
+		btrfs_free_path(path);
+		return -ENOMEM;
+	}
+
+	ret = add_new_free_space_info(trans, fs_info, block_group, path2);
+	if (ret)
+		goto out;
+
+	mutex_lock(&block_group->free_space_lock);
+
+	/*
+	 * Iterate through all of the extent and metadata items in this block
+	 * group, adding the free space between them and the free space at the
+	 * end. Note that EXTENT_ITEM and METADATA_ITEM are less than
+	 * BLOCK_GROUP_ITEM, so an extent may precede the block group that it's
+	 * contained in.
+	 */
+	key.objectid = block_group->key.objectid;
+	key.type = BTRFS_EXTENT_ITEM_KEY;
+	key.offset = 0;
+
+	ret = btrfs_search_slot_for_read(extent_root, &key, path, 1, 0);
+	if (ret < 0)
+		goto out_locked;
+	ASSERT(ret == 0);
+
+	start = block_group->key.objectid;
+	end = block_group->key.objectid + block_group->key.offset;
+	while (1) {
+		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+
+		if (key.type == BTRFS_EXTENT_ITEM_KEY ||
+		    key.type == BTRFS_METADATA_ITEM_KEY) {
+			if (key.objectid >= end)
+				break;
+
+			if (start < key.objectid) {
+				ret = __add_to_free_space_tree(trans, fs_info,
+							       block_group,
+							       path2, start,
+							       key.objectid -
+							       start);
+				if (ret)
+					goto out_locked;
+			}
+			start = key.objectid;
+			if (key.type == BTRFS_METADATA_ITEM_KEY)
+				start += fs_info->tree_root->nodesize;
+			else
+				start += key.offset;
+		} else if (key.type == BTRFS_BLOCK_GROUP_ITEM_KEY) {
+			if (key.objectid != block_group->key.objectid)
+				break;
+		}
+
+		ret = btrfs_next_item(extent_root, path);
+		if (ret < 0)
+			goto out_locked;
+		if (ret)
+			break;
+	}
+	if (start < end) {
+		ret = __add_to_free_space_tree(trans, fs_info, block_group,
+					       path2, start, end - start);
+		if (ret)
+			goto out_locked;
+	}
+
+	ret = 0;
+out_locked:
+	mutex_unlock(&block_group->free_space_lock);
+out:
+	btrfs_free_path(path2);
+	btrfs_free_path(path);
+	return ret;
+}
+
+int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_trans_handle *trans;
+	struct btrfs_root *tree_root = fs_info->tree_root;
+	struct btrfs_root *free_space_root;
+	struct btrfs_block_group_cache *block_group;
+	struct rb_node *node;
+	int ret;
+
+	trans = btrfs_start_transaction(tree_root, 0);
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
+
+	fs_info->creating_free_space_tree = 1;
+	free_space_root = btrfs_create_tree(trans, fs_info,
+					    BTRFS_FREE_SPACE_TREE_OBJECTID);
+	if (IS_ERR(free_space_root)) {
+		ret = PTR_ERR(free_space_root);
+		goto abort;
+	}
+	fs_info->free_space_root = free_space_root;
+
+	node = rb_first(&fs_info->block_group_cache_tree);
+	while (node) {
+		block_group = rb_entry(node, struct btrfs_block_group_cache,
+				       cache_node);
+		ret = populate_free_space_tree(trans, fs_info, block_group);
+		if (ret)
+			goto abort;
+		node = rb_next(node);
+	}
+
+	btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE);
+	fs_info->creating_free_space_tree = 0;
+
+	ret = btrfs_commit_transaction(trans, tree_root);
+	if (ret)
+		return ret;
+
+	return 0;
+
+abort:
+	fs_info->creating_free_space_tree = 0;
+	btrfs_abort_transaction(trans, tree_root, ret);
+	btrfs_end_transaction(trans, tree_root);
+	return ret;
+}
+
+static int clear_free_space_tree(struct btrfs_trans_handle *trans,
+				 struct btrfs_root *root)
+{
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	int nr;
+	int ret;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	path->leave_spinning = 1;
+
+	key.objectid = 0;
+	key.type = 0;
+	key.offset = 0;
+
+	while (1) {
+		ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+		if (ret < 0)
+			goto out;
+
+		nr = btrfs_header_nritems(path->nodes[0]);
+		if (!nr)
+			break;
+
+		path->slots[0] = 0;
+		ret = btrfs_del_items(trans, root, path, 0, nr);
+		if (ret)
+			goto out;
+
+		btrfs_release_path(path);
+	}
+
+	ret = 0;
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
+int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_trans_handle *trans;
+	struct btrfs_root *tree_root = fs_info->tree_root;
+	struct btrfs_root *free_space_root = fs_info->free_space_root;
+	int ret;
+
+	trans = btrfs_start_transaction(tree_root, 0);
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
+
+	btrfs_clear_fs_compat_ro(fs_info, FREE_SPACE_TREE);
+	fs_info->free_space_root = NULL;
+
+	ret = clear_free_space_tree(trans, free_space_root);
+	if (ret)
+		goto abort;
+
+	ret = btrfs_del_root(trans, tree_root, &free_space_root->root_key);
+	if (ret)
+		goto abort;
+
+	list_del(&free_space_root->dirty_list);
+
+	btrfs_tree_lock(free_space_root->node);
+	clean_tree_block(trans, tree_root->fs_info, free_space_root->node);
+	btrfs_tree_unlock(free_space_root->node);
+	btrfs_free_tree_block(trans, free_space_root, free_space_root->node,
+			      0, 1);
+
+	free_extent_buffer(free_space_root->node);
+	free_extent_buffer(free_space_root->commit_root);
+	kfree(free_space_root);
+
+	ret = btrfs_commit_transaction(trans, tree_root);
+	if (ret)
+		return ret;
+
+	return 0;
+
+abort:
+	btrfs_abort_transaction(trans, tree_root, ret);
+	btrfs_end_transaction(trans, tree_root);
+	return ret;
+}
+
+static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
+					struct btrfs_fs_info *fs_info,
+					struct btrfs_block_group_cache *block_group,
+					struct btrfs_path *path)
+{
+	u64 start, end;
+	int ret;
+
+	start = block_group->key.objectid;
+	end = block_group->key.objectid + block_group->key.offset;
+
+	block_group->needs_free_space = 0;
+
+	ret = add_new_free_space_info(trans, fs_info, block_group, path);
+	if (ret)
+		return ret;
+
+	return __add_to_free_space_tree(trans, fs_info, block_group, path,
+					block_group->key.objectid,
+					block_group->key.offset);
+}
+
+int add_block_group_free_space(struct btrfs_trans_handle *trans,
+			       struct btrfs_fs_info *fs_info,
+			       struct btrfs_block_group_cache *block_group)
+{
+	struct btrfs_path *path = NULL;
+	int ret = 0;
+
+	if (!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE))
+		return 0;
+
+	mutex_lock(&block_group->free_space_lock);
+	if (!block_group->needs_free_space)
+		goto out;
+
+	path = btrfs_alloc_path();
+	if (!path) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = __add_block_group_free_space(trans, fs_info, block_group, path);
+
+out:
+	btrfs_free_path(path);
+	mutex_unlock(&block_group->free_space_lock);
+	if (ret)
+		btrfs_abort_transaction(trans, fs_info->free_space_root, ret);
+	return ret;
+}
+
+int remove_block_group_free_space(struct btrfs_trans_handle *trans,
+				  struct btrfs_fs_info *fs_info,
+				  struct btrfs_block_group_cache *block_group)
+{
+	struct btrfs_root *root = fs_info->free_space_root;
+	struct btrfs_path *path;
+	struct btrfs_key key, found_key;
+	struct extent_buffer *leaf;
+	u64 start, end;
+	int done = 0, nr;
+	int ret;
+
+	if (!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE))
+		return 0;
+
+	if (block_group->needs_free_space) {
+		/* We never added this block group to the free space tree. */
+		return 0;
+	}
+
+	path = btrfs_alloc_path();
+	if (!path) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	start = block_group->key.objectid;
+	end = block_group->key.objectid + block_group->key.offset;
+
+	key.objectid = end - 1;
+	key.type = (u8)-1;
+	key.offset = (u64)-1;
+
+	while (!done) {
+		ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1);
+		if (ret)
+			goto out;
+
+		leaf = path->nodes[0];
+		nr = 0;
+		path->slots[0]++;
+		while (path->slots[0] > 0) {
+			btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1);
+
+			if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) {
+				ASSERT(found_key.objectid == block_group->key.objectid);
+				ASSERT(found_key.offset == block_group->key.offset);
+				done = 1;
+				nr++;
+				path->slots[0]--;
+				break;
+			} else if (found_key.type == BTRFS_FREE_SPACE_EXTENT_KEY ||
+				   found_key.type == BTRFS_FREE_SPACE_BITMAP_KEY) {
+				ASSERT(found_key.objectid >= start);
+				ASSERT(found_key.objectid < end);
+				ASSERT(found_key.objectid + found_key.offset <= end);
+				nr++;
+				path->slots[0]--;
+			} else {
+				ASSERT(0);
+			}
+		}
+
+		ret = btrfs_del_items(trans, root, path, path->slots[0], nr);
+		if (ret)
+			goto out;
+		btrfs_release_path(path);
+	}
+
+	ret = 0;
+out:
+	btrfs_free_path(path);
+	if (ret)
+		btrfs_abort_transaction(trans, root, ret);
+	return ret;
+}
+
+static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl,
+				   struct btrfs_path *path,
+				   u32 expected_extent_count)
+{
+	struct btrfs_block_group_cache *block_group;
+	struct btrfs_fs_info *fs_info;
+	struct btrfs_root *root;
+	struct btrfs_key key;
+	int prev_bit = 0, bit;
+	/* Initialize to silence GCC. */
+	u64 extent_start = 0;
+	u64 end, offset;
+	u64 total_found = 0;
+	u32 extent_count = 0;
+	int ret;
+
+	block_group = caching_ctl->block_group;
+	fs_info = block_group->fs_info;
+	root = fs_info->free_space_root;
+
+	end = block_group->key.objectid + block_group->key.offset;
+
+	while (1) {
+		ret = btrfs_next_item(root, path);
+		if (ret < 0)
+			goto out;
+		if (ret)
+			break;
+
+		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+
+		if (key.type == BTRFS_FREE_SPACE_INFO_KEY)
+			break;
+
+		ASSERT(key.type == BTRFS_FREE_SPACE_BITMAP_KEY);
+		ASSERT(key.objectid < end && key.objectid + key.offset <= end);
+
+		caching_ctl->progress = key.objectid;
+
+		offset = key.objectid;
+		while (offset < key.objectid + key.offset) {
+			bit = free_space_test_bit(block_group, path, offset);
+			if (prev_bit == 0 && bit == 1) {
+				extent_start = offset;
+			} else if (prev_bit == 1 && bit == 0) {
+				total_found += add_new_free_space(block_group,
+								  fs_info,
+								  extent_start,
+								  offset);
+				if (total_found > CACHING_CTL_WAKE_UP) {
+					total_found = 0;
+					wake_up(&caching_ctl->wait);
+				}
+				extent_count++;
+			}
+			prev_bit = bit;
+			offset += block_group->sectorsize;
+		}
+	}
+	if (prev_bit == 1) {
+		total_found += add_new_free_space(block_group, fs_info,
+						  extent_start, end);
+		extent_count++;
+	}
+
+	if (extent_count != expected_extent_count) {
+		btrfs_err(fs_info, "incorrect extent count for %llu; counted %u, expected %u",
+			  block_group->key.objectid, extent_count,
+			  expected_extent_count);
+		ASSERT(0);
+		ret = -EIO;
+		goto out;
+	}
+
+	caching_ctl->progress = (u64)-1;
+
+	ret = 0;
+out:
+	return ret;
+}
+
+static int load_free_space_extents(struct btrfs_caching_control *caching_ctl,
+				   struct btrfs_path *path,
+				   u32 expected_extent_count)
+{
+	struct btrfs_block_group_cache *block_group;
+	struct btrfs_fs_info *fs_info;
+	struct btrfs_root *root;
+	struct btrfs_key key;
+	u64 end;
+	u64 total_found = 0;
+	u32 extent_count = 0;
+	int ret;
+
+	block_group = caching_ctl->block_group;
+	fs_info = block_group->fs_info;
+	root = fs_info->free_space_root;
+
+	end = block_group->key.objectid + block_group->key.offset;
+
+	while (1) {
+		ret = btrfs_next_item(root, path);
+		if (ret < 0)
+			goto out;
+		if (ret)
+			break;
+
+		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+
+		if (key.type == BTRFS_FREE_SPACE_INFO_KEY)
+			break;
+
+		ASSERT(key.type == BTRFS_FREE_SPACE_EXTENT_KEY);
+		ASSERT(key.objectid < end && key.objectid + key.offset <= end);
+
+		caching_ctl->progress = key.objectid;
+
+		total_found += add_new_free_space(block_group, fs_info,
+						  key.objectid,
+						  key.objectid + key.offset);
+		if (total_found > CACHING_CTL_WAKE_UP) {
+			total_found = 0;
+			wake_up(&caching_ctl->wait);
+		}
+		extent_count++;
+	}
+
+	if (extent_count != expected_extent_count) {
+		btrfs_err(fs_info, "incorrect extent count for %llu; counted %u, expected %u",
+			  block_group->key.objectid, extent_count,
+			  expected_extent_count);
+		ASSERT(0);
+		ret = -EIO;
+		goto out;
+	}
+
+	caching_ctl->progress = (u64)-1;
+
+	ret = 0;
+out:
+	return ret;
+}
+
+int load_free_space_tree(struct btrfs_caching_control *caching_ctl)
+{
+	struct btrfs_block_group_cache *block_group;
+	struct btrfs_fs_info *fs_info;
+	struct btrfs_free_space_info *info;
+	struct btrfs_path *path;
+	u32 extent_count, flags;
+	int ret;
+
+	block_group = caching_ctl->block_group;
+	fs_info = block_group->fs_info;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	/*
+	 * Just like caching_thread() doesn't want to deadlock on the extent
+	 * tree, we don't want to deadlock on the free space tree.
+	 */
+	path->skip_locking = 1;
+	path->search_commit_root = 1;
+	path->reada = 1;
+
+	info = search_free_space_info(NULL, fs_info, block_group, path, 0);
+	if (IS_ERR(info)) {
+		ret = PTR_ERR(info);
+		goto out;
+	}
+	extent_count = btrfs_free_space_extent_count(path->nodes[0], info);
+	flags = btrfs_free_space_flags(path->nodes[0], info);
+
+	/*
+	 * We left path pointing to the free space info item, so now
+	 * load_free_space_foo can just iterate through the free space tree from
+	 * there.
+	 */
+	if (flags & BTRFS_FREE_SPACE_USING_BITMAPS)
+		ret = load_free_space_bitmaps(caching_ctl, path, extent_count);
+	else
+		ret = load_free_space_extents(caching_ctl, path, extent_count);
+
+out:
+	btrfs_free_path(path);
+	return ret;
+}
diff --git a/fs/btrfs/free-space-tree.h b/fs/btrfs/free-space-tree.h
new file mode 100644
index 000000000000..54ffced3bce8
--- /dev/null
+++ b/fs/btrfs/free-space-tree.h
@@ -0,0 +1,72 @@
+/*
+ * Copyright (C) 2015 Facebook.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#ifndef __BTRFS_FREE_SPACE_TREE
+#define __BTRFS_FREE_SPACE_TREE
+
+/*
+ * The default size for new free space bitmap items. The last bitmap in a block
+ * group may be truncated, and none of the free space tree code assumes that
+ * existing bitmaps are this size.
+ */
+#define BTRFS_FREE_SPACE_BITMAP_SIZE 256
+#define BTRFS_FREE_SPACE_BITMAP_BITS (BTRFS_FREE_SPACE_BITMAP_SIZE * BITS_PER_BYTE)
+
+void set_free_space_tree_thresholds(struct btrfs_block_group_cache *block_group);
+int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info);
+int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info);
+int load_free_space_tree(struct btrfs_caching_control *caching_ctl);
+int add_block_group_free_space(struct btrfs_trans_handle *trans,
+			       struct btrfs_fs_info *fs_info,
+			       struct btrfs_block_group_cache *block_group);
+int remove_block_group_free_space(struct btrfs_trans_handle *trans,
+				  struct btrfs_fs_info *fs_info,
+				  struct btrfs_block_group_cache *block_group);
+int add_to_free_space_tree(struct btrfs_trans_handle *trans,
+			   struct btrfs_fs_info *fs_info,
+			   u64 start, u64 size);
+int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
+				struct btrfs_fs_info *fs_info,
+				u64 start, u64 size);
+
+/* Exposed for testing. */
+struct btrfs_free_space_info *
+search_free_space_info(struct btrfs_trans_handle *trans,
+		       struct btrfs_fs_info *fs_info,
+		       struct btrfs_block_group_cache *block_group,
+		       struct btrfs_path *path, int cow);
+int __add_to_free_space_tree(struct btrfs_trans_handle *trans,
+			     struct btrfs_fs_info *fs_info,
+			     struct btrfs_block_group_cache *block_group,
+			     struct btrfs_path *path, u64 start, u64 size);
+int __remove_from_free_space_tree(struct btrfs_trans_handle *trans,
+				  struct btrfs_fs_info *fs_info,
+				  struct btrfs_block_group_cache *block_group,
+				  struct btrfs_path *path, u64 start, u64 size);
+int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
+				  struct btrfs_fs_info *fs_info,
+				  struct btrfs_block_group_cache *block_group,
+				  struct btrfs_path *path);
+int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
+				  struct btrfs_fs_info *fs_info,
+				  struct btrfs_block_group_cache *block_group,
+				  struct btrfs_path *path);
+int free_space_test_bit(struct btrfs_block_group_cache *block_group,
+			struct btrfs_path *path, u64 offset);
+
+#endif
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 767a6056ac45..70107f7c9307 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -48,7 +48,7 @@ static int caching_kthread(void *data)
 	/* Since the commit root is read-only, we can safely skip locking. */
 	path->skip_locking = 1;
 	path->search_commit_root = 1;
-	path->reada = 2;
+	path->reada = READA_FORWARD;
 
 	key.objectid = BTRFS_FIRST_FREE_OBJECTID;
 	key.offset = 0;
@@ -282,8 +282,8 @@ void btrfs_unpin_free_ino(struct btrfs_root *root)
 	}
 }
 
-#define INIT_THRESHOLD	(((1024 * 32) / 2) / sizeof(struct btrfs_free_space))
-#define INODES_PER_BITMAP (PAGE_CACHE_SIZE * 8)
+#define INIT_THRESHOLD	((SZ_32K / 2) / sizeof(struct btrfs_free_space))
+#define INODES_PER_BITMAP (PAGE_SIZE * 8)
 
 /*
  * The goal is to keep the memory used by the free_ino tree won't
@@ -317,7 +317,7 @@ static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl)
 	}
 
 	ctl->extents_thresh = (max_bitmaps - ctl->total_bitmaps) *
-				PAGE_CACHE_SIZE / sizeof(*info);
+				PAGE_SIZE / sizeof(*info);
 }
 
 /*
@@ -334,7 +334,7 @@ static bool use_bitmap(struct btrfs_free_space_ctl *ctl,
 	return true;
 }
 
-static struct btrfs_free_space_op free_ino_op = {
+static const struct btrfs_free_space_op free_ino_op = {
 	.recalc_thresholds	= recalculate_thresholds,
 	.use_bitmap		= use_bitmap,
 };
@@ -356,7 +356,7 @@ static bool pinned_use_bitmap(struct btrfs_free_space_ctl *ctl,
 	return false;
 }
 
-static struct btrfs_free_space_op pinned_free_ino_op = {
+static const struct btrfs_free_space_op pinned_free_ino_op = {
 	.recalc_thresholds	= pinned_recalc_thresholds,
 	.use_bitmap		= pinned_use_bitmap,
 };
@@ -481,12 +481,12 @@ again:
 
 	spin_lock(&ctl->tree_lock);
 	prealloc = sizeof(struct btrfs_free_space) * ctl->free_extents;
-	prealloc = ALIGN(prealloc, PAGE_CACHE_SIZE);
-	prealloc += ctl->total_bitmaps * PAGE_CACHE_SIZE;
+	prealloc = ALIGN(prealloc, PAGE_SIZE);
+	prealloc += ctl->total_bitmaps * PAGE_SIZE;
 	spin_unlock(&ctl->tree_lock);
 
 	/* Just to make sure we have enough space */
-	prealloc += 8 * PAGE_CACHE_SIZE;
+	prealloc += 8 * PAGE_SIZE;
 
 	ret = btrfs_delalloc_reserve_space(inode, 0, prealloc);
 	if (ret)
@@ -515,7 +515,7 @@ out:
 	return ret;
 }
 
-static int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid)
+int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid)
 {
 	struct btrfs_path *path;
 	int ret;
@@ -555,14 +555,10 @@ int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid)
 	int ret;
 	mutex_lock(&root->objectid_mutex);
 
-	if (unlikely(root->highest_objectid < BTRFS_FIRST_FREE_OBJECTID)) {
-		ret = btrfs_find_highest_objectid(root,
-						  &root->highest_objectid);
-		if (ret)
-			goto out;
-	}
-
 	if (unlikely(root->highest_objectid >= BTRFS_LAST_FREE_OBJECTID)) {
+		btrfs_warn(root->fs_info,
+			   "the objectid of root %llu reaches its highest value",
+			   root->root_key.objectid);
 		ret = -ENOSPC;
 		goto out;
 	}
diff --git a/fs/btrfs/inode-map.h b/fs/btrfs/inode-map.h
index ddb347bfee23..c8e864b2d530 100644
--- a/fs/btrfs/inode-map.h
+++ b/fs/btrfs/inode-map.h
@@ -9,5 +9,6 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
 			 struct btrfs_trans_handle *trans);
 
 int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid);
+int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid);
 
 #endif
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 4439fbb4ff45..2aaba58b4856 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -66,6 +66,13 @@ struct btrfs_iget_args {
 	struct btrfs_root *root;
 };
 
+struct btrfs_dio_data {
+	u64 outstanding_extents;
+	u64 reserve;
+	u64 unsubmitted_oe_range_start;
+	u64 unsubmitted_oe_range_end;
+};
+
 static const struct inode_operations btrfs_dir_inode_operations;
 static const struct inode_operations btrfs_symlink_inode_operations;
 static const struct inode_operations btrfs_dir_ro_inode_operations;
@@ -74,17 +81,16 @@ static const struct inode_operations btrfs_file_inode_operations;
 static const struct address_space_operations btrfs_aops;
 static const struct address_space_operations btrfs_symlink_aops;
 static const struct file_operations btrfs_dir_file_operations;
-static struct extent_io_ops btrfs_extent_io_ops;
+static const struct extent_io_ops btrfs_extent_io_ops;
 
 static struct kmem_cache *btrfs_inode_cachep;
-static struct kmem_cache *btrfs_delalloc_work_cachep;
 struct kmem_cache *btrfs_trans_handle_cachep;
 struct kmem_cache *btrfs_transaction_cachep;
 struct kmem_cache *btrfs_path_cachep;
 struct kmem_cache *btrfs_free_space_cachep;
 
 #define S_SHIFT 12
-static unsigned char btrfs_type_by_mode[S_IFMT >> S_SHIFT] = {
+static const unsigned char btrfs_type_by_mode[S_IFMT >> S_SHIFT] = {
 	[S_IFREG >> S_SHIFT]	= BTRFS_FT_REG_FILE,
 	[S_IFDIR >> S_SHIFT]	= BTRFS_FT_DIR,
 	[S_IFCHR >> S_SHIFT]	= BTRFS_FT_CHRDEV,
@@ -188,7 +194,7 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
 		while (compressed_size > 0) {
 			cpage = compressed_pages[i];
 			cur_size = min_t(unsigned long, compressed_size,
-				       PAGE_CACHE_SIZE);
+				       PAGE_SIZE);
 
 			kaddr = kmap_atomic(cpage);
 			write_extent_buffer(leaf, kaddr, ptr, cur_size);
@@ -202,13 +208,13 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
 						  compress_type);
 	} else {
 		page = find_get_page(inode->i_mapping,
-				     start >> PAGE_CACHE_SHIFT);
+				     start >> PAGE_SHIFT);
 		btrfs_set_file_extent_compression(leaf, ei, 0);
 		kaddr = kmap_atomic(page);
-		offset = start & (PAGE_CACHE_SIZE - 1);
+		offset = start & (PAGE_SIZE - 1);
 		write_extent_buffer(leaf, kaddr + offset, ptr, size);
 		kunmap_atomic(kaddr);
-		page_cache_release(page);
+		put_page(page);
 	}
 	btrfs_mark_buffer_dirty(leaf);
 	btrfs_release_path(path);
@@ -257,7 +263,7 @@ static noinline int cow_file_range_inline(struct btrfs_root *root,
 		data_len = compressed_size;
 
 	if (start > 0 ||
-	    actual_end > PAGE_CACHE_SIZE ||
+	    actual_end > root->sectorsize ||
 	    data_len > BTRFS_MAX_INLINE_DATA_SIZE(root) ||
 	    (!compressed_size &&
 	    (actual_end & (root->sectorsize - 1)) == 0) ||
@@ -316,7 +322,7 @@ out:
 	 * And at reserve time, it's always aligned to page size, so
 	 * just free one page here.
 	 */
-	btrfs_qgroup_free_data(inode, 0, PAGE_CACHE_SIZE);
+	btrfs_qgroup_free_data(inode, 0, PAGE_SIZE);
 	btrfs_free_path(path);
 	btrfs_end_transaction(trans, root);
 	return ret;
@@ -414,23 +420,23 @@ static noinline void compress_file_range(struct inode *inode,
 	unsigned long nr_pages_ret = 0;
 	unsigned long total_compressed = 0;
 	unsigned long total_in = 0;
-	unsigned long max_compressed = 128 * 1024;
-	unsigned long max_uncompressed = 128 * 1024;
+	unsigned long max_compressed = SZ_128K;
+	unsigned long max_uncompressed = SZ_128K;
 	int i;
 	int will_compress;
 	int compress_type = root->fs_info->compress_type;
 	int redirty = 0;
 
 	/* if this is a small write inside eof, kick off a defrag */
-	if ((end - start + 1) < 16 * 1024 &&
+	if ((end - start + 1) < SZ_16K &&
 	    (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size))
 		btrfs_add_inode_defrag(NULL, inode);
 
 	actual_end = min_t(u64, isize, end + 1);
 again:
 	will_compress = 0;
-	nr_pages = (end >> PAGE_CACHE_SHIFT) - (start >> PAGE_CACHE_SHIFT) + 1;
-	nr_pages = min(nr_pages, (128 * 1024UL) / PAGE_CACHE_SIZE);
+	nr_pages = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1;
+	nr_pages = min_t(unsigned long, nr_pages, SZ_128K / PAGE_SIZE);
 
 	/*
 	 * we don't want to send crud past the end of i_size through
@@ -508,7 +514,7 @@ again:
 
 		if (!ret) {
 			unsigned long offset = total_compressed &
-				(PAGE_CACHE_SIZE - 1);
+				(PAGE_SIZE - 1);
 			struct page *page = pages[nr_pages_ret - 1];
 			char *kaddr;
 
@@ -518,7 +524,7 @@ again:
 			if (offset) {
 				kaddr = kmap_atomic(page);
 				memset(kaddr + offset, 0,
-				       PAGE_CACHE_SIZE - offset);
+				       PAGE_SIZE - offset);
 				kunmap_atomic(kaddr);
 			}
 			will_compress = 1;
@@ -574,7 +580,7 @@ cont:
 		 * one last check to make sure the compression is really a
 		 * win, compare the page count read with the blocks on disk
 		 */
-		total_in = ALIGN(total_in, PAGE_CACHE_SIZE);
+		total_in = ALIGN(total_in, PAGE_SIZE);
 		if (total_compressed >= total_in) {
 			will_compress = 0;
 		} else {
@@ -588,7 +594,7 @@ cont:
 		 */
 		for (i = 0; i < nr_pages_ret; i++) {
 			WARN_ON(pages[i]->mapping);
-			page_cache_release(pages[i]);
+			put_page(pages[i]);
 		}
 		kfree(pages);
 		pages = NULL;
@@ -644,7 +650,7 @@ cleanup_and_bail_uncompressed:
 free_pages_out:
 	for (i = 0; i < nr_pages_ret; i++) {
 		WARN_ON(pages[i]->mapping);
-		page_cache_release(pages[i]);
+		put_page(pages[i]);
 	}
 	kfree(pages);
 }
@@ -658,7 +664,7 @@ static void free_async_extent_pages(struct async_extent *async_extent)
 
 	for (i = 0; i < async_extent->nr_pages; i++) {
 		WARN_ON(async_extent->pages[i]->mapping);
-		page_cache_release(async_extent->pages[i]);
+		put_page(async_extent->pages[i]);
 	}
 	kfree(async_extent->pages);
 	async_extent->nr_pages = 0;
@@ -944,7 +950,7 @@ static noinline int cow_file_range(struct inode *inode,
 	disk_num_bytes = num_bytes;
 
 	/* if this is a small write inside eof, kick off defrag */
-	if (num_bytes < 64 * 1024 &&
+	if (num_bytes < SZ_64K &&
 	    (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size))
 		btrfs_add_inode_defrag(NULL, inode);
 
@@ -960,7 +966,7 @@ static noinline int cow_file_range(struct inode *inode,
 				     PAGE_END_WRITEBACK);
 
 			*nr_written = *nr_written +
-			     (end - start + PAGE_CACHE_SIZE) / PAGE_CACHE_SIZE;
+			     (end - start + PAGE_SIZE) / PAGE_SIZE;
 			*page_started = 1;
 			goto out;
 		} else if (ret < 0) {
@@ -1100,14 +1106,14 @@ static noinline void async_cow_submit(struct btrfs_work *work)
 	async_cow = container_of(work, struct async_cow, work);
 
 	root = async_cow->root;
-	nr_pages = (async_cow->end - async_cow->start + PAGE_CACHE_SIZE) >>
-		PAGE_CACHE_SHIFT;
+	nr_pages = (async_cow->end - async_cow->start + PAGE_SIZE) >>
+		PAGE_SHIFT;
 
 	/*
 	 * atomic_sub_return implies a barrier for waitqueue_active
 	 */
 	if (atomic_sub_return(nr_pages, &root->fs_info->async_delalloc_pages) <
-	    5 * 1024 * 1024 &&
+	    5 * SZ_1M &&
 	    waitqueue_active(&root->fs_info->async_submit_wait))
 		wake_up(&root->fs_info->async_submit_wait);
 
@@ -1132,7 +1138,7 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	unsigned long nr_pages;
 	u64 cur_end;
-	int limit = 10 * 1024 * 1024;
+	int limit = 10 * SZ_1M;
 
 	clear_extent_bit(&BTRFS_I(inode)->io_tree, start, end, EXTENT_LOCKED,
 			 1, 0, NULL, GFP_NOFS);
@@ -1148,7 +1154,7 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
 		    !btrfs_test_opt(root, FORCE_COMPRESS))
 			cur_end = end;
 		else
-			cur_end = min(end, start + 512 * 1024 - 1);
+			cur_end = min(end, start + SZ_512K - 1);
 
 		async_cow->end = cur_end;
 		INIT_LIST_HEAD(&async_cow->extents);
@@ -1158,8 +1164,8 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
 				async_cow_start, async_cow_submit,
 				async_cow_free);
 
-		nr_pages = (cur_end - start + PAGE_CACHE_SIZE) >>
-			PAGE_CACHE_SHIFT;
+		nr_pages = (cur_end - start + PAGE_SIZE) >>
+			PAGE_SHIFT;
 		atomic_add(nr_pages, &root->fs_info->async_delalloc_pages);
 
 		btrfs_queue_work(root->fs_info->delalloc_workers,
@@ -1304,8 +1310,14 @@ next_slot:
 		num_bytes = 0;
 		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
 
-		if (found_key.objectid > ino ||
-		    found_key.type > BTRFS_EXTENT_DATA_KEY ||
+		if (found_key.objectid > ino)
+			break;
+		if (WARN_ON_ONCE(found_key.objectid < ino) ||
+		    found_key.type < BTRFS_EXTENT_DATA_KEY) {
+			path->slots[0]++;
+			goto next_slot;
+		}
+		if (found_key.type > BTRFS_EXTENT_DATA_KEY ||
 		    found_key.offset > end)
 			break;
 
@@ -1948,7 +1960,7 @@ static noinline int add_pending_csums(struct btrfs_trans_handle *trans,
 int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
 			      struct extent_state **cached_state)
 {
-	WARN_ON((end & (PAGE_CACHE_SIZE - 1)) == 0);
+	WARN_ON((end & (PAGE_SIZE - 1)) == 0);
 	return set_extent_delalloc(&BTRFS_I(inode)->io_tree, start, end,
 				   cached_state, GFP_NOFS);
 }
@@ -1981,16 +1993,17 @@ again:
 
 	inode = page->mapping->host;
 	page_start = page_offset(page);
-	page_end = page_offset(page) + PAGE_CACHE_SIZE - 1;
+	page_end = page_offset(page) + PAGE_SIZE - 1;
 
-	lock_extent_bits(&BTRFS_I(inode)->io_tree, page_start, page_end, 0,
+	lock_extent_bits(&BTRFS_I(inode)->io_tree, page_start, page_end,
 			 &cached_state);
 
 	/* already ordered? We're done */
 	if (PagePrivate2(page))
 		goto out;
 
-	ordered = btrfs_lookup_ordered_extent(inode, page_start);
+	ordered = btrfs_lookup_ordered_range(inode, page_start,
+					PAGE_SIZE);
 	if (ordered) {
 		unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start,
 				     page_end, &cached_state, GFP_NOFS);
@@ -2001,7 +2014,7 @@ again:
 	}
 
 	ret = btrfs_delalloc_reserve_space(inode, page_start,
-					   PAGE_CACHE_SIZE);
+					   PAGE_SIZE);
 	if (ret) {
 		mapping_set_error(page->mapping, ret);
 		end_extent_writepage(page, ret, page_start, page_end);
@@ -2017,7 +2030,7 @@ out:
 			     &cached_state, GFP_NOFS);
 out_page:
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 	kfree(fixup);
 }
 
@@ -2050,7 +2063,7 @@ static int btrfs_writepage_start_hook(struct page *page, u64 start, u64 end)
 		return -EAGAIN;
 
 	SetPageChecked(page);
-	page_cache_get(page);
+	get_page(page);
 	btrfs_init_work(&fixup->work, btrfs_fixup_helper,
 			btrfs_writepage_fixup_worker, NULL, NULL);
 	fixup->page = page;
@@ -2476,7 +2489,7 @@ static noinline int relink_extent_backref(struct btrfs_path *path,
 	lock_start = backref->file_pos;
 	lock_end = backref->file_pos + backref->num_bytes - 1;
 	lock_extent_bits(&BTRFS_I(inode)->io_tree, lock_start, lock_end,
-			 0, &cached);
+			 &cached);
 
 	ordered = btrfs_lookup_first_ordered_extent(inode, lock_end);
 	if (ordered) {
@@ -2868,7 +2881,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 
 	lock_extent_bits(io_tree, ordered_extent->file_offset,
 			 ordered_extent->file_offset + ordered_extent->len - 1,
-			 0, &cached_state);
+			 &cached_state);
 
 	ret = test_range_bit(io_tree, ordered_extent->file_offset,
 			ordered_extent->file_offset + ordered_extent->len - 1,
@@ -3100,56 +3113,46 @@ static int btrfs_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 				      start, (size_t)(end - start + 1));
 }
 
-struct delayed_iput {
-	struct list_head list;
-	struct inode *inode;
-};
-
-/* JDM: If this is fs-wide, why can't we add a pointer to
- * btrfs_inode instead and avoid the allocation? */
 void btrfs_add_delayed_iput(struct inode *inode)
 {
 	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
-	struct delayed_iput *delayed;
+	struct btrfs_inode *binode = BTRFS_I(inode);
 
 	if (atomic_add_unless(&inode->i_count, -1, 1))
 		return;
 
-	delayed = kmalloc(sizeof(*delayed), GFP_NOFS | __GFP_NOFAIL);
-	delayed->inode = inode;
-
 	spin_lock(&fs_info->delayed_iput_lock);
-	list_add_tail(&delayed->list, &fs_info->delayed_iputs);
+	if (binode->delayed_iput_count == 0) {
+		ASSERT(list_empty(&binode->delayed_iput));
+		list_add_tail(&binode->delayed_iput, &fs_info->delayed_iputs);
+	} else {
+		binode->delayed_iput_count++;
+	}
 	spin_unlock(&fs_info->delayed_iput_lock);
 }
 
 void btrfs_run_delayed_iputs(struct btrfs_root *root)
 {
-	LIST_HEAD(list);
 	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct delayed_iput *delayed;
-	int empty;
-
-	spin_lock(&fs_info->delayed_iput_lock);
-	empty = list_empty(&fs_info->delayed_iputs);
-	spin_unlock(&fs_info->delayed_iput_lock);
-	if (empty)
-		return;
-
-	down_read(&fs_info->delayed_iput_sem);
 
 	spin_lock(&fs_info->delayed_iput_lock);
-	list_splice_init(&fs_info->delayed_iputs, &list);
-	spin_unlock(&fs_info->delayed_iput_lock);
-
-	while (!list_empty(&list)) {
-		delayed = list_entry(list.next, struct delayed_iput, list);
-		list_del(&delayed->list);
-		iput(delayed->inode);
-		kfree(delayed);
+	while (!list_empty(&fs_info->delayed_iputs)) {
+		struct btrfs_inode *inode;
+
+		inode = list_first_entry(&fs_info->delayed_iputs,
+				struct btrfs_inode, delayed_iput);
+		if (inode->delayed_iput_count) {
+			inode->delayed_iput_count--;
+			list_move_tail(&inode->delayed_iput,
+					&fs_info->delayed_iputs);
+		} else {
+			list_del_init(&inode->delayed_iput);
+		}
+		spin_unlock(&fs_info->delayed_iput_lock);
+		iput(&inode->vfs_inode);
+		spin_lock(&fs_info->delayed_iput_lock);
 	}
-
-	up_read(&root->fs_info->delayed_iput_sem);
+	spin_unlock(&fs_info->delayed_iput_lock);
 }
 
 /*
@@ -3345,7 +3348,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 		ret = -ENOMEM;
 		goto out;
 	}
-	path->reada = -1;
+	path->reada = READA_BACK;
 
 	key.objectid = BTRFS_ORPHAN_OBJECTID;
 	key.type = BTRFS_ORPHAN_ITEM_KEY;
@@ -3544,10 +3547,10 @@ static noinline int acls_after_inode_item(struct extent_buffer *leaf,
 	int scanned = 0;
 
 	if (!xattr_access) {
-		xattr_access = btrfs_name_hash(POSIX_ACL_XATTR_ACCESS,
-					strlen(POSIX_ACL_XATTR_ACCESS));
-		xattr_default = btrfs_name_hash(POSIX_ACL_XATTR_DEFAULT,
-					strlen(POSIX_ACL_XATTR_DEFAULT));
+		xattr_access = btrfs_name_hash(XATTR_NAME_POSIX_ACL_ACCESS,
+					strlen(XATTR_NAME_POSIX_ACL_ACCESS));
+		xattr_default = btrfs_name_hash(XATTR_NAME_POSIX_ACL_DEFAULT,
+					strlen(XATTR_NAME_POSIX_ACL_DEFAULT));
 	}
 
 	slot++;
@@ -3768,6 +3771,7 @@ cache_acl:
 		break;
 	case S_IFLNK:
 		inode->i_op = &btrfs_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &btrfs_symlink_aops;
 		break;
 	default:
@@ -4010,7 +4014,8 @@ err:
 	btrfs_i_size_write(dir, dir->i_size - name_len * 2);
 	inode_inc_iversion(inode);
 	inode_inc_iversion(dir);
-	inode->i_ctime = dir->i_mtime = dir->i_ctime = CURRENT_TIME;
+	inode->i_ctime = dir->i_mtime =
+		dir->i_ctime = current_fs_time(inode->i_sb);
 	ret = btrfs_update_inode(trans, root, dir);
 out:
 	return ret;
@@ -4040,9 +4045,7 @@ int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
  */
 static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir)
 {
-	struct btrfs_trans_handle *trans;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
-	int ret;
 
 	/*
 	 * 1 for the possible orphan item
@@ -4051,27 +4054,7 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir)
 	 * 1 for the inode ref
 	 * 1 for the inode
 	 */
-	trans = btrfs_start_transaction(root, 5);
-	if (!IS_ERR(trans) || PTR_ERR(trans) != -ENOSPC)
-		return trans;
-
-	if (PTR_ERR(trans) == -ENOSPC) {
-		u64 num_bytes = btrfs_calc_trans_metadata_size(root, 5);
-
-		trans = btrfs_start_transaction(root, 0);
-		if (IS_ERR(trans))
-			return trans;
-		ret = btrfs_cond_migrate_bytes(root->fs_info,
-					       &root->fs_info->trans_block_rsv,
-					       num_bytes, 5);
-		if (ret) {
-			btrfs_end_transaction(trans, root);
-			return ERR_PTR(ret);
-		}
-		trans->block_rsv = &root->fs_info->trans_block_rsv;
-		trans->bytes_reserved = num_bytes;
-	}
-	return trans;
+	return btrfs_start_transaction_fallback_global_rsv(root, 5, 5);
 }
 
 static int btrfs_unlink(struct inode *dir, struct dentry *dentry)
@@ -4175,7 +4158,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 
 	btrfs_i_size_write(dir, dir->i_size - name_len * 2);
 	inode_inc_iversion(dir);
-	dir->i_mtime = dir->i_ctime = CURRENT_TIME;
+	dir->i_mtime = dir->i_ctime = current_fs_time(dir->i_sb);
 	ret = btrfs_update_inode_fallback(trans, root, dir);
 	if (ret)
 		btrfs_abort_transaction(trans, root, ret);
@@ -4230,11 +4213,20 @@ static int truncate_space_check(struct btrfs_trans_handle *trans,
 {
 	int ret;
 
+	/*
+	 * This is only used to apply pressure to the enospc system, we don't
+	 * intend to use this reservation at all.
+	 */
 	bytes_deleted = btrfs_csum_bytes_to_leaves(root, bytes_deleted);
+	bytes_deleted *= root->nodesize;
 	ret = btrfs_block_rsv_add(root, &root->fs_info->trans_block_rsv,
 				  bytes_deleted, BTRFS_RESERVE_NO_FLUSH);
-	if (!ret)
+	if (!ret) {
+		trace_btrfs_space_reservation(root->fs_info, "transaction",
+					      trans->transid,
+					      bytes_deleted, 1);
 		trans->bytes_reserved += bytes_deleted;
+	}
 	return ret;
 
 }
@@ -4255,7 +4247,7 @@ static int truncate_inline_extent(struct inode *inode,
 
 	if (btrfs_file_extent_compression(leaf, fi) != BTRFS_COMPRESS_NONE) {
 		loff_t offset = new_size;
-		loff_t page_end = ALIGN(offset, PAGE_CACHE_SIZE);
+		loff_t page_end = ALIGN(offset, PAGE_SIZE);
 
 		/*
 		 * Zero out the remaining of the last page of our inline extent,
@@ -4267,7 +4259,8 @@ static int truncate_inline_extent(struct inode *inode,
 		 * read the extent item from disk (data not in the page cache).
 		 */
 		btrfs_release_path(path);
-		return btrfs_truncate_page(inode, offset, page_end - offset, 0);
+		return btrfs_truncate_block(inode, offset, page_end - offset,
+					0);
 	}
 
 	btrfs_set_file_extent_ram_bytes(leaf, fi, size);
@@ -4333,7 +4326,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
-	path->reada = -1;
+	path->reada = READA_BACK;
 
 	/*
 	 * We want to drop from the next block forward in case this new size is
@@ -4364,7 +4357,7 @@ search_again:
 	 * up a huge file in a single leaf.  Most of the time that
 	 * bytes_deleted is > 0, it will be huge by the time we get here
 	 */
-	if (be_nice && bytes_deleted > 32 * 1024 * 1024) {
+	if (be_nice && bytes_deleted > SZ_32M) {
 		if (btrfs_should_end_transaction(trans, root)) {
 			err = -EAGAIN;
 			goto error;
@@ -4607,7 +4600,7 @@ error:
 
 	btrfs_free_path(path);
 
-	if (be_nice && bytes_deleted > 32 * 1024 * 1024) {
+	if (be_nice && bytes_deleted > SZ_32M) {
 		unsigned long updates = trans->delayed_ref_updates;
 		if (updates) {
 			trans->delayed_ref_updates = 0;
@@ -4620,17 +4613,17 @@ error:
 }
 
 /*
- * btrfs_truncate_page - read, zero a chunk and write a page
+ * btrfs_truncate_block - read, zero a chunk and write a block
  * @inode - inode that we're zeroing
  * @from - the offset to start zeroing
  * @len - the length to zero, 0 to zero the entire range respective to the
  *	offset
  * @front - zero up to the offset instead of from the offset on
  *
- * This will find the page for the "from" offset and cow the page and zero the
+ * This will find the block for the "from" offset and cow the block and zero the
  * part we want to zero.  This is used with truncate and hole punching.
  */
-int btrfs_truncate_page(struct inode *inode, loff_t from, loff_t len,
+int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
 			int front)
 {
 	struct address_space *mapping = inode->i_mapping;
@@ -4640,19 +4633,20 @@ int btrfs_truncate_page(struct inode *inode, loff_t from, loff_t len,
 	struct extent_state *cached_state = NULL;
 	char *kaddr;
 	u32 blocksize = root->sectorsize;
-	pgoff_t index = from >> PAGE_CACHE_SHIFT;
-	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	pgoff_t index = from >> PAGE_SHIFT;
+	unsigned offset = from & (blocksize - 1);
 	struct page *page;
 	gfp_t mask = btrfs_alloc_write_mask(mapping);
 	int ret = 0;
-	u64 page_start;
-	u64 page_end;
+	u64 block_start;
+	u64 block_end;
 
 	if ((offset & (blocksize - 1)) == 0 &&
 	    (!len || ((len & (blocksize - 1)) == 0)))
 		goto out;
+
 	ret = btrfs_delalloc_reserve_space(inode,
-			round_down(from, PAGE_CACHE_SIZE), PAGE_CACHE_SIZE);
+			round_down(from, blocksize), blocksize);
 	if (ret)
 		goto out;
 
@@ -4660,21 +4654,21 @@ again:
 	page = find_or_create_page(mapping, index, mask);
 	if (!page) {
 		btrfs_delalloc_release_space(inode,
-				round_down(from, PAGE_CACHE_SIZE),
-				PAGE_CACHE_SIZE);
+				round_down(from, blocksize),
+				blocksize);
 		ret = -ENOMEM;
 		goto out;
 	}
 
-	page_start = page_offset(page);
-	page_end = page_start + PAGE_CACHE_SIZE - 1;
+	block_start = round_down(from, blocksize);
+	block_end = block_start + blocksize - 1;
 
 	if (!PageUptodate(page)) {
 		ret = btrfs_readpage(NULL, page);
 		lock_page(page);
 		if (page->mapping != mapping) {
 			unlock_page(page);
-			page_cache_release(page);
+			put_page(page);
 			goto again;
 		}
 		if (!PageUptodate(page)) {
@@ -4684,55 +4678,57 @@ again:
 	}
 	wait_on_page_writeback(page);
 
-	lock_extent_bits(io_tree, page_start, page_end, 0, &cached_state);
+	lock_extent_bits(io_tree, block_start, block_end, &cached_state);
 	set_page_extent_mapped(page);
 
-	ordered = btrfs_lookup_ordered_extent(inode, page_start);
+	ordered = btrfs_lookup_ordered_extent(inode, block_start);
 	if (ordered) {
-		unlock_extent_cached(io_tree, page_start, page_end,
+		unlock_extent_cached(io_tree, block_start, block_end,
 				     &cached_state, GFP_NOFS);
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 		btrfs_start_ordered_extent(inode, ordered, 1);
 		btrfs_put_ordered_extent(ordered);
 		goto again;
 	}
 
-	clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, page_end,
+	clear_extent_bit(&BTRFS_I(inode)->io_tree, block_start, block_end,
 			  EXTENT_DIRTY | EXTENT_DELALLOC |
 			  EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
 			  0, 0, &cached_state, GFP_NOFS);
 
-	ret = btrfs_set_extent_delalloc(inode, page_start, page_end,
+	ret = btrfs_set_extent_delalloc(inode, block_start, block_end,
 					&cached_state);
 	if (ret) {
-		unlock_extent_cached(io_tree, page_start, page_end,
+		unlock_extent_cached(io_tree, block_start, block_end,
 				     &cached_state, GFP_NOFS);
 		goto out_unlock;
 	}
 
-	if (offset != PAGE_CACHE_SIZE) {
+	if (offset != blocksize) {
 		if (!len)
-			len = PAGE_CACHE_SIZE - offset;
+			len = blocksize - offset;
 		kaddr = kmap(page);
 		if (front)
-			memset(kaddr, 0, offset);
+			memset(kaddr + (block_start - page_offset(page)),
+				0, offset);
 		else
-			memset(kaddr + offset, 0, len);
+			memset(kaddr + (block_start - page_offset(page)) +  offset,
+				0, len);
 		flush_dcache_page(page);
 		kunmap(page);
 	}
 	ClearPageChecked(page);
 	set_page_dirty(page);
-	unlock_extent_cached(io_tree, page_start, page_end, &cached_state,
+	unlock_extent_cached(io_tree, block_start, block_end, &cached_state,
 			     GFP_NOFS);
 
 out_unlock:
 	if (ret)
-		btrfs_delalloc_release_space(inode, page_start,
-					     PAGE_CACHE_SIZE);
+		btrfs_delalloc_release_space(inode, block_start,
+					     blocksize);
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 out:
 	return ret;
 }
@@ -4801,11 +4797,11 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 	int err = 0;
 
 	/*
-	 * If our size started in the middle of a page we need to zero out the
-	 * rest of the page before we expand the i_size, otherwise we could
+	 * If our size started in the middle of a block we need to zero out the
+	 * rest of the block before we expand the i_size, otherwise we could
 	 * expose stale data.
 	 */
-	err = btrfs_truncate_page(inode, oldsize, 0, 0);
+	err = btrfs_truncate_block(inode, oldsize, 0, 0);
 	if (err)
 		return err;
 
@@ -4815,7 +4811,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 	while (1) {
 		struct btrfs_ordered_extent *ordered;
 
-		lock_extent_bits(io_tree, hole_start, block_end - 1, 0,
+		lock_extent_bits(io_tree, hole_start, block_end - 1,
 				 &cached_state);
 		ordered = btrfs_lookup_ordered_range(inode, hole_start,
 						     block_end - hole_start);
@@ -4891,26 +4887,6 @@ next:
 	return err;
 }
 
-static int wait_snapshoting_atomic_t(atomic_t *a)
-{
-	schedule();
-	return 0;
-}
-
-static void wait_for_snapshot_creation(struct btrfs_root *root)
-{
-	while (true) {
-		int ret;
-
-		ret = btrfs_start_write_no_snapshoting(root);
-		if (ret)
-			break;
-		wait_on_atomic_t(&root->will_be_snapshoted,
-				 wait_snapshoting_atomic_t,
-				 TASK_UNINTERRUPTIBLE);
-	}
-}
-
 static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -4934,7 +4910,6 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 	}
 
 	if (newsize > oldsize) {
-		truncate_pagecache(inode, newsize);
 		/*
 		 * Don't do an expanding truncate while snapshoting is ongoing.
 		 * This is to ensure the snapshot captures a fully consistent
@@ -4942,7 +4917,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 		 * truncation, it must capture all writes that happened before
 		 * this truncation.
 		 */
-		wait_for_snapshot_creation(root);
+		btrfs_wait_for_snapshot_creation(root);
 		ret = btrfs_cont_expand(inode, oldsize, newsize);
 		if (ret) {
 			btrfs_end_write_no_snapshoting(root);
@@ -4957,6 +4932,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 
 		i_size_write(inode, newsize);
 		btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL);
+		pagecache_isize_extended(inode, oldsize, newsize);
 		ret = btrfs_update_inode(trans, root, inode);
 		btrfs_end_write_no_snapshoting(root);
 		btrfs_end_transaction(trans, root);
@@ -5127,7 +5103,7 @@ static void evict_inode_truncate_pages(struct inode *inode)
 		end = state->end;
 		spin_unlock(&io_tree->lock);
 
-		lock_extent_bits(io_tree, start, end, 0, &cached_state);
+		lock_extent_bits(io_tree, start, end, &cached_state);
 
 		/*
 		 * If still has DELALLOC flag, the extent didn't reach disk,
@@ -5320,7 +5296,6 @@ void btrfs_evict_inode(struct inode *inode)
 no_delete:
 	btrfs_remove_delayed_node(inode);
 	clear_inode(inode);
-	return;
 }
 
 /*
@@ -5628,7 +5603,7 @@ static struct inode *new_simple_dir(struct super_block *s,
 	inode->i_op = &btrfs_dir_ro_inode_operations;
 	inode->i_fop = &simple_dir_operations;
 	inode->i_mode = S_IFDIR | S_IRUGO | S_IWUSR | S_IXUGO;
-	inode->i_mtime = CURRENT_TIME;
+	inode->i_mtime = current_fs_time(inode->i_sb);
 	inode->i_atime = inode->i_mtime;
 	inode->i_ctime = inode->i_mtime;
 	BTRFS_I(inode)->i_otime = inode->i_mtime;
@@ -5757,6 +5732,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	char *name_ptr;
 	int name_len;
 	int is_curr = 0;	/* ctx->pos points to the current index? */
+	bool emitted;
 
 	/* FIXME, use a real flag for deciding about the key type */
 	if (root->fs_info->tree_root == root)
@@ -5769,7 +5745,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	if (!path)
 		return -ENOMEM;
 
-	path->reada = 1;
+	path->reada = READA_FORWARD;
 
 	if (key_type == BTRFS_DIR_INDEX_KEY) {
 		INIT_LIST_HEAD(&ins_list);
@@ -5785,6 +5761,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	if (ret < 0)
 		goto err;
 
+	emitted = false;
 	while (1) {
 		leaf = path->nodes[0];
 		slot = path->slots[0];
@@ -5828,7 +5805,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 			if (name_len <= sizeof(tmp_name)) {
 				name_ptr = tmp_name;
 			} else {
-				name_ptr = kmalloc(name_len, GFP_NOFS);
+				name_ptr = kmalloc(name_len, GFP_KERNEL);
 				if (!name_ptr) {
 					ret = -ENOMEM;
 					goto err;
@@ -5864,6 +5841,7 @@ skip:
 
 			if (over)
 				goto nopos;
+			emitted = true;
 			di_len = btrfs_dir_name_len(leaf, di) +
 				 btrfs_dir_data_len(leaf, di) + sizeof(*di);
 			di_cur += di_len;
@@ -5876,11 +5854,20 @@ next:
 	if (key_type == BTRFS_DIR_INDEX_KEY) {
 		if (is_curr)
 			ctx->pos++;
-		ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list);
+		ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list, &emitted);
 		if (ret)
 			goto nopos;
 	}
 
+	/*
+	 * If we haven't emitted any dir entry, we must not touch ctx->pos as
+	 * it was was set to the termination value in previous call. We assume
+	 * that "." and ".." were emitted if we reach this point and set the
+	 * termination value as well for an empty directory.
+	 */
+	if (ctx->pos > 2 && !emitted)
+		goto nopos;
+
 	/* Reached end of directory/root. Bump pos past the last item. */
 	ctx->pos++;
 
@@ -6200,7 +6187,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	inode_init_owner(inode, dir, mode);
 	inode_set_bytes(inode, 0);
 
-	inode->i_mtime = CURRENT_TIME;
+	inode->i_mtime = current_fs_time(inode->i_sb);
 	inode->i_atime = inode->i_mtime;
 	inode->i_ctime = inode->i_mtime;
 	BTRFS_I(inode)->i_otime = inode->i_mtime;
@@ -6313,7 +6300,8 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 	btrfs_i_size_write(parent_inode, parent_inode->i_size +
 			   name_len * 2);
 	inode_inc_iversion(parent_inode);
-	parent_inode->i_mtime = parent_inode->i_ctime = CURRENT_TIME;
+	parent_inode->i_mtime = parent_inode->i_ctime =
+		current_fs_time(parent_inode->i_sb);
 	ret = btrfs_update_inode(trans, root, parent_inode);
 	if (ret)
 		btrfs_abort_transaction(trans, root, ret);
@@ -6360,9 +6348,6 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 	u64 objectid;
 	u64 index = 0;
 
-	if (!new_valid_dev(rdev))
-		return -EINVAL;
-
 	/*
 	 * 2 for inode item and ref
 	 * 2 for dir items
@@ -6500,7 +6485,7 @@ out_unlock_inode:
 static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 		      struct dentry *dentry)
 {
-	struct btrfs_trans_handle *trans;
+	struct btrfs_trans_handle *trans = NULL;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct inode *inode = d_inode(old_dentry);
 	u64 index;
@@ -6526,6 +6511,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 	trans = btrfs_start_transaction(root, 5);
 	if (IS_ERR(trans)) {
 		err = PTR_ERR(trans);
+		trans = NULL;
 		goto fail;
 	}
 
@@ -6533,7 +6519,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 	BTRFS_I(inode)->dir_index = 0ULL;
 	inc_nlink(inode);
 	inode_inc_iversion(inode);
-	inode->i_ctime = CURRENT_TIME;
+	inode->i_ctime = current_fs_time(inode->i_sb);
 	ihold(inode);
 	set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags);
 
@@ -6559,9 +6545,10 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 		btrfs_log_new_name(trans, inode, NULL, parent);
 	}
 
-	btrfs_end_transaction(trans, root);
 	btrfs_balance_delayed_items(root);
 fail:
+	if (trans)
+		btrfs_end_transaction(trans, root);
 	if (drop_inode) {
 		inode_dec_link_count(inode);
 		iput(inode);
@@ -6706,7 +6693,7 @@ static int merge_extent_mapping(struct extent_map_tree *em_tree,
 }
 
 static noinline int uncompress_inline(struct btrfs_path *path,
-				      struct inode *inode, struct page *page,
+				      struct page *page,
 				      size_t pg_offset, u64 extent_offset,
 				      struct btrfs_file_extent_item *item)
 {
@@ -6730,7 +6717,7 @@ static noinline int uncompress_inline(struct btrfs_path *path,
 
 	read_extent_buffer(leaf, tmp, ptr, inline_size);
 
-	max_size = min_t(unsigned long, PAGE_CACHE_SIZE, max_size);
+	max_size = min_t(unsigned long, PAGE_SIZE, max_size);
 	ret = btrfs_decompress(compress_type, tmp, page,
 			       extent_offset, inline_size, max_size);
 	kfree(tmp);
@@ -6803,7 +6790,7 @@ again:
 		 * Chances are we'll be called again, so go ahead and do
 		 * readahead
 		 */
-		path->reada = 1;
+		path->reada = READA_FORWARD;
 	}
 
 	ret = btrfs_lookup_file_extent(trans, root, path,
@@ -6892,8 +6879,8 @@ next:
 
 		size = btrfs_file_extent_inline_len(leaf, path->slots[0], item);
 		extent_offset = page_offset(page) + pg_offset - extent_start;
-		copy_size = min_t(u64, PAGE_CACHE_SIZE - pg_offset,
-				size - extent_offset);
+		copy_size = min_t(u64, PAGE_SIZE - pg_offset,
+				  size - extent_offset);
 		em->start = extent_start + extent_offset;
 		em->len = ALIGN(copy_size, root->sectorsize);
 		em->orig_block_len = em->len;
@@ -6902,8 +6889,7 @@ next:
 		if (create == 0 && !PageUptodate(page)) {
 			if (btrfs_file_extent_compression(leaf, item) !=
 			    BTRFS_COMPRESS_NONE) {
-				ret = uncompress_inline(path, inode, page,
-							pg_offset,
+				ret = uncompress_inline(path, page, pg_offset,
 							extent_offset, item);
 				if (ret) {
 					err = ret;
@@ -6913,9 +6899,9 @@ next:
 				map = kmap(page);
 				read_extent_buffer(leaf, map + pg_offset, ptr,
 						   copy_size);
-				if (pg_offset + copy_size < PAGE_CACHE_SIZE) {
+				if (pg_offset + copy_size < PAGE_SIZE) {
 					memset(map + pg_offset + copy_size, 0,
-					       PAGE_CACHE_SIZE - pg_offset -
+					       PAGE_SIZE - pg_offset -
 					       copy_size);
 				}
 				kunmap(page);
@@ -7158,21 +7144,41 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
 	if (ret)
 		return ERR_PTR(ret);
 
-	em = create_pinned_em(inode, start, ins.offset, start, ins.objectid,
-			      ins.offset, ins.offset, ins.offset, 0);
-	if (IS_ERR(em)) {
-		btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
-		return em;
-	}
-
+	/*
+	 * Create the ordered extent before the extent map. This is to avoid
+	 * races with the fast fsync path that would lead to it logging file
+	 * extent items that point to disk extents that were not yet written to.
+	 * The fast fsync path collects ordered extents into a local list and
+	 * then collects all the new extent maps, so we must create the ordered
+	 * extent first and make sure the fast fsync path collects any new
+	 * ordered extents after collecting new extent maps as well.
+	 * The fsync path simply can not rely on inode_dio_wait() because it
+	 * causes deadlock with AIO.
+	 */
 	ret = btrfs_add_ordered_extent_dio(inode, start, ins.objectid,
 					   ins.offset, ins.offset, 0);
 	if (ret) {
 		btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
-		free_extent_map(em);
 		return ERR_PTR(ret);
 	}
 
+	em = create_pinned_em(inode, start, ins.offset, start, ins.objectid,
+			      ins.offset, ins.offset, ins.offset, 0);
+	if (IS_ERR(em)) {
+		struct btrfs_ordered_extent *oe;
+
+		btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
+		oe = btrfs_lookup_ordered_extent(inode, start);
+		ASSERT(oe);
+		if (WARN_ON(!oe))
+			return em;
+		set_bit(BTRFS_ORDERED_IOERR, &oe->flags);
+		set_bit(BTRFS_ORDERED_IO_DONE, &oe->flags);
+		btrfs_remove_ordered_extent(inode, oe);
+		/* Once for our lookup and once for the ordered extents tree. */
+		btrfs_put_ordered_extent(oe);
+		btrfs_put_ordered_extent(oe);
+	}
 	return em;
 }
 
@@ -7330,12 +7336,12 @@ bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end)
 	int start_idx;
 	int end_idx;
 
-	start_idx = start >> PAGE_CACHE_SHIFT;
+	start_idx = start >> PAGE_SHIFT;
 
 	/*
 	 * end is the last byte in the last page.  end == start is legal
 	 */
-	end_idx = end >> PAGE_CACHE_SHIFT;
+	end_idx = end >> PAGE_SHIFT;
 
 	rcu_read_lock();
 
@@ -7376,7 +7382,7 @@ bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end)
 		 * include/linux/pagemap.h for details.
 		 */
 		if (unlikely(page != *pagep)) {
-			page_cache_release(page);
+			put_page(page);
 			page = NULL;
 		}
 	}
@@ -7384,7 +7390,7 @@ bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end)
 	if (page) {
 		if (page->index <= end_idx)
 			found = true;
-		page_cache_release(page);
+		put_page(page);
 	}
 
 	rcu_read_unlock();
@@ -7399,7 +7405,7 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
 
 	while (1) {
 		lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend,
-				 0, cached_state);
+				 cached_state);
 		/*
 		 * We're concerned with the entire range that we're going to be
 		 * doing DIO to, so we need to make sure theres no ordered
@@ -7424,30 +7430,47 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
 				     cached_state, GFP_NOFS);
 
 		if (ordered) {
-			btrfs_start_ordered_extent(inode, ordered, 1);
+			/*
+			 * If we are doing a DIO read and the ordered extent we
+			 * found is for a buffered write, we can not wait for it
+			 * to complete and retry, because if we do so we can
+			 * deadlock with concurrent buffered writes on page
+			 * locks. This happens only if our DIO read covers more
+			 * than one extent map, if at this point has already
+			 * created an ordered extent for a previous extent map
+			 * and locked its range in the inode's io tree, and a
+			 * concurrent write against that previous extent map's
+			 * range and this range started (we unlock the ranges
+			 * in the io tree only when the bios complete and
+			 * buffered writes always lock pages before attempting
+			 * to lock range in the io tree).
+			 */
+			if (writing ||
+			    test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags))
+				btrfs_start_ordered_extent(inode, ordered, 1);
+			else
+				ret = -ENOTBLK;
 			btrfs_put_ordered_extent(ordered);
 		} else {
-			/* Screw you mmap */
-			ret = btrfs_fdatawrite_range(inode, lockstart, lockend);
-			if (ret)
-				break;
-			ret = filemap_fdatawait_range(inode->i_mapping,
-						      lockstart,
-						      lockend);
-			if (ret)
-				break;
-
 			/*
-			 * If we found a page that couldn't be invalidated just
-			 * fall back to buffered.
+			 * We could trigger writeback for this range (and wait
+			 * for it to complete) and then invalidate the pages for
+			 * this range (through invalidate_inode_pages2_range()),
+			 * but that can lead us to a deadlock with a concurrent
+			 * call to readpages() (a buffered read or a defrag call
+			 * triggered a readahead) on a page lock due to an
+			 * ordered dio extent we created before but did not have
+			 * yet a corresponding bio submitted (whence it can not
+			 * complete), which makes readpages() wait for that
+			 * ordered extent to complete while holding a lock on
+			 * that page.
 			 */
-			ret = invalidate_inode_pages2_range(inode->i_mapping,
-					lockstart >> PAGE_CACHE_SHIFT,
-					lockend >> PAGE_CACHE_SHIFT);
-			if (ret)
-				break;
+			ret = -ENOTBLK;
 		}
 
+		if (ret)
+			break;
+
 		cond_resched();
 	}
 
@@ -7501,10 +7524,27 @@ static struct extent_map *create_pinned_em(struct inode *inode, u64 start,
 	return em;
 }
 
-struct btrfs_dio_data {
-	u64 outstanding_extents;
-	u64 reserve;
-};
+static void adjust_dio_outstanding_extents(struct inode *inode,
+					   struct btrfs_dio_data *dio_data,
+					   const u64 len)
+{
+	unsigned num_extents;
+
+	num_extents = (unsigned) div64_u64(len + BTRFS_MAX_EXTENT_SIZE - 1,
+					   BTRFS_MAX_EXTENT_SIZE);
+	/*
+	 * If we have an outstanding_extents count still set then we're
+	 * within our reservation, otherwise we need to adjust our inode
+	 * counter appropriately.
+	 */
+	if (dio_data->outstanding_extents) {
+		dio_data->outstanding_extents -= num_extents;
+	} else {
+		spin_lock(&BTRFS_I(inode)->lock);
+		BTRFS_I(inode)->outstanding_extents += num_extents;
+		spin_unlock(&BTRFS_I(inode)->lock);
+	}
+}
 
 static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 				   struct buffer_head *bh_result, int create)
@@ -7541,8 +7581,11 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 	 * If this errors out it's because we couldn't invalidate pagecache for
 	 * this range and we need to fallback to buffered.
 	 */
-	if (lock_extent_direct(inode, lockstart, lockend, &cached_state, create))
-		return -ENOTBLK;
+	if (lock_extent_direct(inode, lockstart, lockend, &cached_state,
+			       create)) {
+		ret = -ENOTBLK;
+		goto err;
+	}
 
 	em = btrfs_get_extent(inode, NULL, 0, start, len, 0);
 	if (IS_ERR(em)) {
@@ -7660,22 +7703,11 @@ unlock:
 		if (start + len > i_size_read(inode))
 			i_size_write(inode, start + len);
 
-		/*
-		 * If we have an outstanding_extents count still set then we're
-		 * within our reservation, otherwise we need to adjust our inode
-		 * counter appropriately.
-		 */
-		if (dio_data->outstanding_extents) {
-			(dio_data->outstanding_extents)--;
-		} else {
-			spin_lock(&BTRFS_I(inode)->lock);
-			BTRFS_I(inode)->outstanding_extents++;
-			spin_unlock(&BTRFS_I(inode)->lock);
-		}
-
+		adjust_dio_outstanding_extents(inode, dio_data, len);
 		btrfs_free_reserved_data_space(inode, start, len);
 		WARN_ON(dio_data->reserve < len);
 		dio_data->reserve -= len;
+		dio_data->unsubmitted_oe_range_end = start + len;
 		current->journal_info = dio_data;
 	}
 
@@ -7699,8 +7731,17 @@ unlock:
 unlock_err:
 	clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			 unlock_bits, 1, 0, &cached_state, GFP_NOFS);
+err:
 	if (dio_data)
 		current->journal_info = dio_data;
+	/*
+	 * Compensate the delalloc release we do in btrfs_direct_IO() when we
+	 * write less data then expected, so that we don't underflow our inode's
+	 * outstanding extents counter.
+	 */
+	if (create && dio_data)
+		adjust_dio_outstanding_extents(inode, dio_data, len);
+
 	return ret;
 }
 
@@ -7760,9 +7801,9 @@ static int btrfs_check_dio_repairable(struct inode *inode,
 }
 
 static int dio_read_error(struct inode *inode, struct bio *failed_bio,
-			  struct page *page, u64 start, u64 end,
-			  int failed_mirror, bio_end_io_t *repair_endio,
-			  void *repair_arg)
+			struct page *page, unsigned int pgoff,
+			u64 start, u64 end, int failed_mirror,
+			bio_end_io_t *repair_endio, void *repair_arg)
 {
 	struct io_failure_record *failrec;
 	struct bio *bio;
@@ -7783,7 +7824,9 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
 		return -EIO;
 	}
 
-	if (failed_bio->bi_vcnt > 1)
+	if ((failed_bio->bi_vcnt > 1)
+		|| (failed_bio->bi_io_vec->bv_len
+			> BTRFS_I(inode)->root->sectorsize))
 		read_mode = READ_SYNC | REQ_FAILFAST_DEV;
 	else
 		read_mode = READ_SYNC;
@@ -7791,7 +7834,7 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
 	isector = start - btrfs_io_bio(failed_bio)->logical;
 	isector >>= inode->i_sb->s_blocksize_bits;
 	bio = btrfs_create_repair_bio(inode, failed_bio, failrec, page,
-				      0, isector, repair_endio, repair_arg);
+				pgoff, isector, repair_endio, repair_arg);
 	if (!bio) {
 		free_io_failure(inode, failrec);
 		return -EIO;
@@ -7821,12 +7864,17 @@ struct btrfs_retry_complete {
 static void btrfs_retry_endio_nocsum(struct bio *bio)
 {
 	struct btrfs_retry_complete *done = bio->bi_private;
+	struct inode *inode;
 	struct bio_vec *bvec;
 	int i;
 
 	if (bio->bi_error)
 		goto end;
 
+	ASSERT(bio->bi_vcnt == 1);
+	inode = bio->bi_io_vec->bv_page->mapping->host;
+	ASSERT(bio->bi_io_vec->bv_len == BTRFS_I(inode)->root->sectorsize);
+
 	done->uptodate = 1;
 	bio_for_each_segment_all(bvec, bio, i)
 		clean_io_failure(done->inode, done->start, bvec->bv_page, 0);
@@ -7838,25 +7886,35 @@ end:
 static int __btrfs_correct_data_nocsum(struct inode *inode,
 				       struct btrfs_io_bio *io_bio)
 {
+	struct btrfs_fs_info *fs_info;
 	struct bio_vec *bvec;
 	struct btrfs_retry_complete done;
 	u64 start;
+	unsigned int pgoff;
+	u32 sectorsize;
+	int nr_sectors;
 	int i;
 	int ret;
 
+	fs_info = BTRFS_I(inode)->root->fs_info;
+	sectorsize = BTRFS_I(inode)->root->sectorsize;
+
 	start = io_bio->logical;
 	done.inode = inode;
 
 	bio_for_each_segment_all(bvec, &io_bio->bio, i) {
-try_again:
+		nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len);
+		pgoff = bvec->bv_offset;
+
+next_block_or_try_again:
 		done.uptodate = 0;
 		done.start = start;
 		init_completion(&done.done);
 
-		ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page, start,
-				     start + bvec->bv_len - 1,
-				     io_bio->mirror_num,
-				     btrfs_retry_endio_nocsum, &done);
+		ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page,
+				pgoff, start, start + sectorsize - 1,
+				io_bio->mirror_num,
+				btrfs_retry_endio_nocsum, &done);
 		if (ret)
 			return ret;
 
@@ -7864,10 +7922,15 @@ try_again:
 
 		if (!done.uptodate) {
 			/* We might have another mirror, so try again */
-			goto try_again;
+			goto next_block_or_try_again;
 		}
 
-		start += bvec->bv_len;
+		start += sectorsize;
+
+		if (nr_sectors--) {
+			pgoff += sectorsize;
+			goto next_block_or_try_again;
+		}
 	}
 
 	return 0;
@@ -7877,7 +7940,9 @@ static void btrfs_retry_endio(struct bio *bio)
 {
 	struct btrfs_retry_complete *done = bio->bi_private;
 	struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
+	struct inode *inode;
 	struct bio_vec *bvec;
+	u64 start;
 	int uptodate;
 	int ret;
 	int i;
@@ -7886,13 +7951,20 @@ static void btrfs_retry_endio(struct bio *bio)
 		goto end;
 
 	uptodate = 1;
+
+	start = done->start;
+
+	ASSERT(bio->bi_vcnt == 1);
+	inode = bio->bi_io_vec->bv_page->mapping->host;
+	ASSERT(bio->bi_io_vec->bv_len == BTRFS_I(inode)->root->sectorsize);
+
 	bio_for_each_segment_all(bvec, bio, i) {
 		ret = __readpage_endio_check(done->inode, io_bio, i,
-					     bvec->bv_page, 0,
-					     done->start, bvec->bv_len);
+					bvec->bv_page, bvec->bv_offset,
+					done->start, bvec->bv_len);
 		if (!ret)
 			clean_io_failure(done->inode, done->start,
-					 bvec->bv_page, 0);
+					bvec->bv_page, bvec->bv_offset);
 		else
 			uptodate = 0;
 	}
@@ -7906,20 +7978,34 @@ end:
 static int __btrfs_subio_endio_read(struct inode *inode,
 				    struct btrfs_io_bio *io_bio, int err)
 {
+	struct btrfs_fs_info *fs_info;
 	struct bio_vec *bvec;
 	struct btrfs_retry_complete done;
 	u64 start;
 	u64 offset = 0;
+	u32 sectorsize;
+	int nr_sectors;
+	unsigned int pgoff;
+	int csum_pos;
 	int i;
 	int ret;
 
+	fs_info = BTRFS_I(inode)->root->fs_info;
+	sectorsize = BTRFS_I(inode)->root->sectorsize;
+
 	err = 0;
 	start = io_bio->logical;
 	done.inode = inode;
 
 	bio_for_each_segment_all(bvec, &io_bio->bio, i) {
-		ret = __readpage_endio_check(inode, io_bio, i, bvec->bv_page,
-					     0, start, bvec->bv_len);
+		nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len);
+
+		pgoff = bvec->bv_offset;
+next_block:
+		csum_pos = BTRFS_BYTES_TO_BLKS(fs_info, offset);
+		ret = __readpage_endio_check(inode, io_bio, csum_pos,
+					bvec->bv_page, pgoff, start,
+					sectorsize);
 		if (likely(!ret))
 			goto next;
 try_again:
@@ -7927,10 +8013,10 @@ try_again:
 		done.start = start;
 		init_completion(&done.done);
 
-		ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page, start,
-				     start + bvec->bv_len - 1,
-				     io_bio->mirror_num,
-				     btrfs_retry_endio, &done);
+		ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page,
+				pgoff, start, start + sectorsize - 1,
+				io_bio->mirror_num,
+				btrfs_retry_endio, &done);
 		if (ret) {
 			err = ret;
 			goto next;
@@ -7943,8 +8029,15 @@ try_again:
 			goto try_again;
 		}
 next:
-		offset += bvec->bv_len;
-		start += bvec->bv_len;
+		offset += sectorsize;
+		start += sectorsize;
+
+		ASSERT(nr_sectors);
+
+		if (--nr_sectors) {
+			pgoff += sectorsize;
+			goto next_block;
+		}
 	}
 
 	return err;
@@ -7982,6 +8075,7 @@ static void btrfs_endio_direct_read(struct bio *bio)
 
 	kfree(dip);
 
+	dio_bio->bi_error = bio->bi_error;
 	dio_end_io(dio_bio, bio->bi_error);
 
 	if (io_bio->end_io)
@@ -7989,22 +8083,22 @@ static void btrfs_endio_direct_read(struct bio *bio)
 	bio_put(bio);
 }
 
-static void btrfs_endio_direct_write(struct bio *bio)
+static void btrfs_endio_direct_write_update_ordered(struct inode *inode,
+						    const u64 offset,
+						    const u64 bytes,
+						    const int uptodate)
 {
-	struct btrfs_dio_private *dip = bio->bi_private;
-	struct inode *inode = dip->inode;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_ordered_extent *ordered = NULL;
-	u64 ordered_offset = dip->logical_offset;
-	u64 ordered_bytes = dip->bytes;
-	struct bio *dio_bio;
+	u64 ordered_offset = offset;
+	u64 ordered_bytes = bytes;
 	int ret;
 
 again:
 	ret = btrfs_dec_test_first_ordered_pending(inode, &ordered,
 						   &ordered_offset,
 						   ordered_bytes,
-						   !bio->bi_error);
+						   uptodate);
 	if (!ret)
 		goto out_test;
 
@@ -8017,16 +8111,26 @@ out_test:
 	 * our bio might span multiple ordered extents.  If we haven't
 	 * completed the accounting for the whole dio, go back and try again
 	 */
-	if (ordered_offset < dip->logical_offset + dip->bytes) {
-		ordered_bytes = dip->logical_offset + dip->bytes -
-			ordered_offset;
+	if (ordered_offset < offset + bytes) {
+		ordered_bytes = offset + bytes - ordered_offset;
 		ordered = NULL;
 		goto again;
 	}
-	dio_bio = dip->dio_bio;
+}
+
+static void btrfs_endio_direct_write(struct bio *bio)
+{
+	struct btrfs_dio_private *dip = bio->bi_private;
+	struct bio *dio_bio = dip->dio_bio;
+
+	btrfs_endio_direct_write_update_ordered(dip->inode,
+						dip->logical_offset,
+						dip->bytes,
+						!bio->bi_error);
 
 	kfree(dip);
 
+	dio_bio->bi_error = bio->bi_error;
 	dio_end_io(dio_bio, bio->bi_error);
 	bio_put(bio);
 }
@@ -8187,9 +8291,11 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 	u64 file_offset = dip->logical_offset;
 	u64 submit_len = 0;
 	u64 map_length;
-	int nr_pages = 0;
-	int ret;
+	u32 blocksize = root->sectorsize;
 	int async_submit = 0;
+	int nr_sectors;
+	int ret;
+	int i;
 
 	map_length = orig_bio->bi_iter.bi_size;
 	ret = btrfs_map_block(root->fs_info, rw, start_sector << 9,
@@ -8219,9 +8325,12 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 	atomic_inc(&dip->pending_bios);
 
 	while (bvec <= (orig_bio->bi_io_vec + orig_bio->bi_vcnt - 1)) {
-		if (map_length < submit_len + bvec->bv_len ||
-		    bio_add_page(bio, bvec->bv_page, bvec->bv_len,
-				 bvec->bv_offset) < bvec->bv_len) {
+		nr_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info, bvec->bv_len);
+		i = 0;
+next_block:
+		if (unlikely(map_length < submit_len + blocksize ||
+		    bio_add_page(bio, bvec->bv_page, blocksize,
+			    bvec->bv_offset + (i * blocksize)) < blocksize)) {
 			/*
 			 * inc the count before we submit the bio so
 			 * we know the end IO handler won't happen before
@@ -8242,7 +8351,6 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 			file_offset += submit_len;
 
 			submit_len = 0;
-			nr_pages = 0;
 
 			bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev,
 						  start_sector, GFP_NOFS);
@@ -8260,9 +8368,14 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 				bio_put(bio);
 				goto out_err;
 			}
+
+			goto next_block;
 		} else {
-			submit_len += bvec->bv_len;
-			nr_pages++;
+			submit_len += blocksize;
+			if (--nr_sectors) {
+				i++;
+				goto next_block;
+			}
 			bvec++;
 		}
 	}
@@ -8331,6 +8444,21 @@ static void btrfs_submit_direct(int rw, struct bio *dio_bio,
 		dip->subio_endio = btrfs_subio_endio_read;
 	}
 
+	/*
+	 * Reset the range for unsubmitted ordered extents (to a 0 length range)
+	 * even if we fail to submit a bio, because in such case we do the
+	 * corresponding error handling below and it must not be done a second
+	 * time by btrfs_direct_IO().
+	 */
+	if (write) {
+		struct btrfs_dio_data *dio_data = current->journal_info;
+
+		dio_data->unsubmitted_oe_range_end = dip->logical_offset +
+			dip->bytes;
+		dio_data->unsubmitted_oe_range_start =
+			dio_data->unsubmitted_oe_range_end;
+	}
+
 	ret = btrfs_submit_direct_hook(rw, dip, skip_sum);
 	if (!ret)
 		return;
@@ -8359,24 +8487,15 @@ free_ordered:
 		dip = NULL;
 		io_bio = NULL;
 	} else {
-		if (write) {
-			struct btrfs_ordered_extent *ordered;
-
-			ordered = btrfs_lookup_ordered_extent(inode,
-							      file_offset);
-			set_bit(BTRFS_ORDERED_IOERR, &ordered->flags);
-			/*
-			 * Decrements our ref on the ordered extent and removes
-			 * the ordered extent from the inode's ordered tree,
-			 * doing all the proper resource cleanup such as for the
-			 * reserved space and waking up any waiters for this
-			 * ordered extent (through btrfs_remove_ordered_extent).
-			 */
-			btrfs_finish_ordered_io(ordered);
-		} else {
+		if (write)
+			btrfs_endio_direct_write_update_ordered(inode,
+						file_offset,
+						dio_bio->bi_iter.bi_size,
+						0);
+		else
 			unlock_extent(&BTRFS_I(inode)->io_tree, file_offset,
 			      file_offset + dio_bio->bi_iter.bi_size - 1);
-		}
+
 		dio_bio->bi_error = -EIO;
 		/*
 		 * Releases and cleans up our dio_bio, no need to bio_put()
@@ -8460,7 +8579,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		 * not unlock the i_mutex at this case.
 		 */
 		if (offset + count <= inode->i_size) {
-			mutex_unlock(&inode->i_mutex);
+			inode_unlock(inode);
 			relock = true;
 		}
 		ret = btrfs_delalloc_reserve_space(inode, offset, count);
@@ -8476,6 +8595,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		 * originally calculated.  Abuse current->journal_info for this.
 		 */
 		dio_data.reserve = round_up(count, root->sectorsize);
+		dio_data.unsubmitted_oe_range_start = (u64)offset;
+		dio_data.unsubmitted_oe_range_end = (u64)offset;
 		current->journal_info = &dio_data;
 	} else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
 				     &BTRFS_I(inode)->runtime_flags)) {
@@ -8494,6 +8615,19 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 			if (dio_data.reserve)
 				btrfs_delalloc_release_space(inode, offset,
 							     dio_data.reserve);
+			/*
+			 * On error we might have left some ordered extents
+			 * without submitting corresponding bios for them, so
+			 * cleanup them up to avoid other tasks getting them
+			 * and waiting for them to complete forever.
+			 */
+			if (dio_data.unsubmitted_oe_range_start <
+			    dio_data.unsubmitted_oe_range_end)
+				btrfs_endio_direct_write_update_ordered(inode,
+					dio_data.unsubmitted_oe_range_start,
+					dio_data.unsubmitted_oe_range_end -
+					dio_data.unsubmitted_oe_range_start,
+					0);
 		} else if (ret >= 0 && (size_t)ret < count)
 			btrfs_delalloc_release_space(inode, offset,
 						     count - (size_t)ret);
@@ -8502,7 +8636,7 @@ out:
 	if (wakeup)
 		inode_dio_end(inode);
 	if (relock)
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 
 	return ret;
 }
@@ -8531,15 +8665,28 @@ int btrfs_readpage(struct file *file, struct page *page)
 static int btrfs_writepage(struct page *page, struct writeback_control *wbc)
 {
 	struct extent_io_tree *tree;
-
+	struct inode *inode = page->mapping->host;
+	int ret;
 
 	if (current->flags & PF_MEMALLOC) {
 		redirty_page_for_writepage(wbc, page);
 		unlock_page(page);
 		return 0;
 	}
+
+	/*
+	 * If we are under memory pressure we will call this directly from the
+	 * VM, we need to make sure we have the inode referenced for the ordered
+	 * extent.  If not just return like we didn't do anything.
+	 */
+	if (!igrab(inode)) {
+		redirty_page_for_writepage(wbc, page);
+		return AOP_WRITEPAGE_ACTIVATE;
+	}
 	tree = &BTRFS_I(page->mapping->host)->io_tree;
-	return extent_write_full_page(tree, page, btrfs_get_extent, wbc);
+	ret = extent_write_full_page(tree, page, btrfs_get_extent, wbc);
+	btrfs_add_delayed_iput(inode);
+	return ret;
 }
 
 static int btrfs_writepages(struct address_space *mapping,
@@ -8572,7 +8719,7 @@ static int __btrfs_releasepage(struct page *page, gfp_t gfp_flags)
 	if (ret == 1) {
 		ClearPagePrivate(page);
 		set_page_private(page, 0);
-		page_cache_release(page);
+		put_page(page);
 	}
 	return ret;
 }
@@ -8592,7 +8739,9 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
 	struct btrfs_ordered_extent *ordered;
 	struct extent_state *cached_state = NULL;
 	u64 page_start = page_offset(page);
-	u64 page_end = page_start + PAGE_CACHE_SIZE - 1;
+	u64 page_end = page_start + PAGE_SIZE - 1;
+	u64 start;
+	u64 end;
 	int inode_evicting = inode->i_state & I_FREEING;
 
 	/*
@@ -8611,15 +8760,19 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
 	}
 
 	if (!inode_evicting)
-		lock_extent_bits(tree, page_start, page_end, 0, &cached_state);
-	ordered = btrfs_lookup_ordered_extent(inode, page_start);
+		lock_extent_bits(tree, page_start, page_end, &cached_state);
+again:
+	start = page_start;
+	ordered = btrfs_lookup_ordered_range(inode, start,
+					page_end - start + 1);
 	if (ordered) {
+		end = min(page_end, ordered->file_offset + ordered->len - 1);
 		/*
 		 * IO on this page will never be started, so we need
 		 * to account for any ordered extents now
 		 */
 		if (!inode_evicting)
-			clear_extent_bit(tree, page_start, page_end,
+			clear_extent_bit(tree, start, end,
 					 EXTENT_DIRTY | EXTENT_DELALLOC |
 					 EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
 					 EXTENT_DEFRAG, 1, 0, &cached_state,
@@ -8636,22 +8789,26 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
 
 			spin_lock_irq(&tree->lock);
 			set_bit(BTRFS_ORDERED_TRUNCATED, &ordered->flags);
-			new_len = page_start - ordered->file_offset;
+			new_len = start - ordered->file_offset;
 			if (new_len < ordered->truncated_len)
 				ordered->truncated_len = new_len;
 			spin_unlock_irq(&tree->lock);
 
 			if (btrfs_dec_test_ordered_pending(inode, &ordered,
-							   page_start,
-							   PAGE_CACHE_SIZE, 1))
+							   start,
+							   end - start + 1, 1))
 				btrfs_finish_ordered_io(ordered);
 		}
 		btrfs_put_ordered_extent(ordered);
 		if (!inode_evicting) {
 			cached_state = NULL;
-			lock_extent_bits(tree, page_start, page_end, 0,
+			lock_extent_bits(tree, start, end,
 					 &cached_state);
 		}
+
+		start = end + 1;
+		if (start < page_end)
+			goto again;
 	}
 
 	/*
@@ -8665,7 +8822,7 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
 	 * 2) Not written to disk
 	 *    This means the reserved space should be freed here.
 	 */
-	btrfs_qgroup_free_data(inode, page_start, PAGE_CACHE_SIZE);
+	btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE);
 	if (!inode_evicting) {
 		clear_extent_bit(tree, page_start, page_end,
 				 EXTENT_LOCKED | EXTENT_DIRTY |
@@ -8680,7 +8837,7 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
 	if (PagePrivate(page)) {
 		ClearPagePrivate(page);
 		set_page_private(page, 0);
-		page_cache_release(page);
+		put_page(page);
 	}
 }
 
@@ -8712,15 +8869,28 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	loff_t size;
 	int ret;
 	int reserved = 0;
+	u64 reserved_space;
 	u64 page_start;
 	u64 page_end;
+	u64 end;
+
+	reserved_space = PAGE_SIZE;
 
 	sb_start_pagefault(inode->i_sb);
 	page_start = page_offset(page);
-	page_end = page_start + PAGE_CACHE_SIZE - 1;
+	page_end = page_start + PAGE_SIZE - 1;
+	end = page_end;
 
+	/*
+	 * Reserving delalloc space after obtaining the page lock can lead to
+	 * deadlock. For example, if a dirty page is locked by this function
+	 * and the call to btrfs_delalloc_reserve_space() ends up triggering
+	 * dirty page write out, then the btrfs_writepage() function could
+	 * end up waiting indefinitely to get a lock on the page currently
+	 * being processed by btrfs_page_mkwrite() function.
+	 */
 	ret = btrfs_delalloc_reserve_space(inode, page_start,
-					   PAGE_CACHE_SIZE);
+					   reserved_space);
 	if (!ret) {
 		ret = file_update_time(vma->vm_file);
 		reserved = 1;
@@ -8747,14 +8917,14 @@ again:
 	}
 	wait_on_page_writeback(page);
 
-	lock_extent_bits(io_tree, page_start, page_end, 0, &cached_state);
+	lock_extent_bits(io_tree, page_start, page_end, &cached_state);
 	set_page_extent_mapped(page);
 
 	/*
 	 * we can't set the delalloc bits if there are pending ordered
 	 * extents.  Drop our locks and wait for them to finish
 	 */
-	ordered = btrfs_lookup_ordered_extent(inode, page_start);
+	ordered = btrfs_lookup_ordered_range(inode, page_start, page_end);
 	if (ordered) {
 		unlock_extent_cached(io_tree, page_start, page_end,
 				     &cached_state, GFP_NOFS);
@@ -8764,6 +8934,18 @@ again:
 		goto again;
 	}
 
+	if (page->index == ((size - 1) >> PAGE_SHIFT)) {
+		reserved_space = round_up(size - page_start, root->sectorsize);
+		if (reserved_space < PAGE_SIZE) {
+			end = page_start + reserved_space - 1;
+			spin_lock(&BTRFS_I(inode)->lock);
+			BTRFS_I(inode)->outstanding_extents++;
+			spin_unlock(&BTRFS_I(inode)->lock);
+			btrfs_delalloc_release_space(inode, page_start,
+						PAGE_SIZE - reserved_space);
+		}
+	}
+
 	/*
 	 * XXX - page_mkwrite gets called every time the page is dirtied, even
 	 * if it was already dirty, so for space accounting reasons we need to
@@ -8771,12 +8953,12 @@ again:
 	 * is probably a better way to do this, but for now keep consistent with
 	 * prepare_pages in the normal write path.
 	 */
-	clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, page_end,
+	clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, end,
 			  EXTENT_DIRTY | EXTENT_DELALLOC |
 			  EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
 			  0, 0, &cached_state, GFP_NOFS);
 
-	ret = btrfs_set_extent_delalloc(inode, page_start, page_end,
+	ret = btrfs_set_extent_delalloc(inode, page_start, end,
 					&cached_state);
 	if (ret) {
 		unlock_extent_cached(io_tree, page_start, page_end,
@@ -8787,14 +8969,14 @@ again:
 	ret = 0;
 
 	/* page is wholly or partially inside EOF */
-	if (page_start + PAGE_CACHE_SIZE > size)
-		zero_start = size & ~PAGE_CACHE_MASK;
+	if (page_start + PAGE_SIZE > size)
+		zero_start = size & ~PAGE_MASK;
 	else
-		zero_start = PAGE_CACHE_SIZE;
+		zero_start = PAGE_SIZE;
 
-	if (zero_start != PAGE_CACHE_SIZE) {
+	if (zero_start != PAGE_SIZE) {
 		kaddr = kmap(page);
-		memset(kaddr + zero_start, 0, PAGE_CACHE_SIZE - zero_start);
+		memset(kaddr + zero_start, 0, PAGE_SIZE - zero_start);
 		flush_dcache_page(page);
 		kunmap(page);
 	}
@@ -8815,7 +8997,7 @@ out_unlock:
 	}
 	unlock_page(page);
 out:
-	btrfs_delalloc_release_space(inode, page_start, PAGE_CACHE_SIZE);
+	btrfs_delalloc_release_space(inode, page_start, reserved_space);
 out_noreserve:
 	sb_end_pagefault(inode->i_sb);
 	return ret;
@@ -9021,6 +9203,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	ei->dir_index = 0;
 	ei->last_unlink_trans = 0;
 	ei->last_log_commit = 0;
+	ei->delayed_iput_count = 0;
 
 	spin_lock_init(&ei->lock);
 	ei->outstanding_extents = 0;
@@ -9045,6 +9228,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	mutex_init(&ei->delalloc_mutex);
 	btrfs_ordered_inode_tree_init(&ei->ordered_tree);
 	INIT_LIST_HEAD(&ei->delalloc_inodes);
+	INIT_LIST_HEAD(&ei->delayed_iput);
 	RB_CLEAR_NODE(&ei->rb_node);
 
 	return inode;
@@ -9139,25 +9323,19 @@ void btrfs_destroy_cachep(void)
 	 * destroy cache.
 	 */
 	rcu_barrier();
-	if (btrfs_inode_cachep)
-		kmem_cache_destroy(btrfs_inode_cachep);
-	if (btrfs_trans_handle_cachep)
-		kmem_cache_destroy(btrfs_trans_handle_cachep);
-	if (btrfs_transaction_cachep)
-		kmem_cache_destroy(btrfs_transaction_cachep);
-	if (btrfs_path_cachep)
-		kmem_cache_destroy(btrfs_path_cachep);
-	if (btrfs_free_space_cachep)
-		kmem_cache_destroy(btrfs_free_space_cachep);
-	if (btrfs_delalloc_work_cachep)
-		kmem_cache_destroy(btrfs_delalloc_work_cachep);
+	kmem_cache_destroy(btrfs_inode_cachep);
+	kmem_cache_destroy(btrfs_trans_handle_cachep);
+	kmem_cache_destroy(btrfs_transaction_cachep);
+	kmem_cache_destroy(btrfs_path_cachep);
+	kmem_cache_destroy(btrfs_free_space_cachep);
 }
 
 int btrfs_init_cachep(void)
 {
 	btrfs_inode_cachep = kmem_cache_create("btrfs_inode",
 			sizeof(struct btrfs_inode), 0,
-			SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, init_once);
+			SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD | SLAB_ACCOUNT,
+			init_once);
 	if (!btrfs_inode_cachep)
 		goto fail;
 
@@ -9185,13 +9363,6 @@ int btrfs_init_cachep(void)
 	if (!btrfs_free_space_cachep)
 		goto fail;
 
-	btrfs_delalloc_work_cachep = kmem_cache_create("btrfs_delalloc_work",
-			sizeof(struct btrfs_delalloc_work), 0,
-			SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD,
-			NULL);
-	if (!btrfs_delalloc_work_cachep)
-		goto fail;
-
 	return 0;
 fail:
 	btrfs_destroy_cachep();
@@ -9207,7 +9378,6 @@ static int btrfs_getattr(struct vfsmount *mnt,
 
 	generic_fillattr(inode, stat);
 	stat->dev = BTRFS_I(inode)->root->anon_dev;
-	stat->blksize = PAGE_CACHE_SIZE;
 
 	spin_lock(&BTRFS_I(inode)->lock);
 	delalloc_bytes = BTRFS_I(inode)->delalloc_bytes;
@@ -9225,7 +9395,6 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct btrfs_root *dest = BTRFS_I(new_dir)->root;
 	struct inode *new_inode = d_inode(new_dentry);
 	struct inode *old_inode = d_inode(old_dentry);
-	struct timespec ctime = CURRENT_TIME;
 	u64 index = 0;
 	u64 root_objectid;
 	int ret;
@@ -9322,9 +9491,9 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	inode_inc_iversion(old_dir);
 	inode_inc_iversion(new_dir);
 	inode_inc_iversion(old_inode);
-	old_dir->i_ctime = old_dir->i_mtime = ctime;
-	new_dir->i_ctime = new_dir->i_mtime = ctime;
-	old_inode->i_ctime = ctime;
+	old_dir->i_ctime = old_dir->i_mtime =
+	new_dir->i_ctime = new_dir->i_mtime =
+	old_inode->i_ctime = current_fs_time(old_dir->i_sb);
 
 	if (old_dentry->d_parent != new_dentry->d_parent)
 		btrfs_record_unlink_dir(trans, old_dir, old_inode, 1);
@@ -9349,7 +9518,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	if (new_inode) {
 		inode_inc_iversion(new_inode);
-		new_inode->i_ctime = CURRENT_TIME;
+		new_inode->i_ctime = current_fs_time(new_inode->i_sb);
 		if (unlikely(btrfs_ino(new_inode) ==
 			     BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
 			root_objectid = BTRFS_I(new_inode)->location.objectid;
@@ -9415,14 +9584,10 @@ static void btrfs_run_delalloc_work(struct btrfs_work *work)
 	delalloc_work = container_of(work, struct btrfs_delalloc_work,
 				     work);
 	inode = delalloc_work->inode;
-	if (delalloc_work->wait) {
-		btrfs_wait_ordered_range(inode, 0, (u64)-1);
-	} else {
+	filemap_flush(inode->i_mapping);
+	if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
+				&BTRFS_I(inode)->runtime_flags))
 		filemap_flush(inode->i_mapping);
-		if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
-			     &BTRFS_I(inode)->runtime_flags))
-			filemap_flush(inode->i_mapping);
-	}
 
 	if (delalloc_work->delay_iput)
 		btrfs_add_delayed_iput(inode);
@@ -9432,18 +9597,17 @@ static void btrfs_run_delalloc_work(struct btrfs_work *work)
 }
 
 struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
-						    int wait, int delay_iput)
+						    int delay_iput)
 {
 	struct btrfs_delalloc_work *work;
 
-	work = kmem_cache_zalloc(btrfs_delalloc_work_cachep, GFP_NOFS);
+	work = kmalloc(sizeof(*work), GFP_NOFS);
 	if (!work)
 		return NULL;
 
 	init_completion(&work->completion);
 	INIT_LIST_HEAD(&work->list);
 	work->inode = inode;
-	work->wait = wait;
 	work->delay_iput = delay_iput;
 	WARN_ON_ONCE(!inode);
 	btrfs_init_work(&work->work, btrfs_flush_delalloc_helper,
@@ -9455,7 +9619,7 @@ struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
 void btrfs_wait_and_free_delalloc_work(struct btrfs_delalloc_work *work)
 {
 	wait_for_completion(&work->completion);
-	kmem_cache_free(btrfs_delalloc_work_cachep, work);
+	kfree(work);
 }
 
 /*
@@ -9491,7 +9655,7 @@ static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput,
 		}
 		spin_unlock(&root->delalloc_lock);
 
-		work = btrfs_alloc_delalloc_work(inode, 0, delay_iput);
+		work = btrfs_alloc_delalloc_work(inode, delay_iput);
 		if (!work) {
 			if (delay_iput)
 				btrfs_add_delayed_iput(inode);
@@ -9633,9 +9797,11 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 	/*
 	 * 2 items for inode item and ref
 	 * 2 items for dir items
+	 * 1 item for updating parent inode item
+	 * 1 item for the inline extent item
 	 * 1 item for xattr if selinux is on
 	 */
-	trans = btrfs_start_transaction(root, 5);
+	trans = btrfs_start_transaction(root, 7);
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 
@@ -9666,10 +9832,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 	if (err)
 		goto out_unlock_inode;
 
-	err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
-	if (err)
-		goto out_unlock_inode;
-
 	path = btrfs_alloc_path();
 	if (!path) {
 		err = -ENOMEM;
@@ -9702,10 +9864,18 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 	btrfs_free_path(path);
 
 	inode->i_op = &btrfs_symlink_inode_operations;
+	inode_nohighmem(inode);
 	inode->i_mapping->a_ops = &btrfs_symlink_aops;
 	inode_set_bytes(inode, name_len);
 	btrfs_i_size_write(inode, name_len);
 	err = btrfs_update_inode(trans, root, inode);
+	/*
+	 * Last step, add directory indexes for our symlink inode. This is the
+	 * last step to avoid extra cleanup of these indexes if an error happens
+	 * elsewhere above.
+	 */
+	if (!err)
+		err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
 	if (err) {
 		drop_inode = 1;
 		goto out_unlock_inode;
@@ -9756,7 +9926,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 			}
 		}
 
-		cur_bytes = min(num_bytes, 256ULL * 1024 * 1024);
+		cur_bytes = min_t(u64, num_bytes, SZ_256M);
 		cur_bytes = max(cur_bytes, min_size);
 		/*
 		 * If we are severely fragmented we could end up with really
@@ -9826,7 +9996,7 @@ next:
 		*alloc_hint = ins.objectid + ins.offset;
 
 		inode_inc_iversion(inode);
-		inode->i_ctime = CURRENT_TIME;
+		inode->i_ctime = current_fs_time(inode->i_sb);
 		BTRFS_I(inode)->flags |= BTRFS_INODE_PREALLOC;
 		if (!(mode & FALLOC_FL_KEEP_SIZE) &&
 		    (actual_len > inode->i_size) &&
@@ -9991,7 +10161,7 @@ static const struct inode_operations btrfs_dir_inode_operations = {
 	.setattr	= btrfs_setattr,
 	.mknod		= btrfs_mknod,
 	.setxattr	= btrfs_setxattr,
-	.getxattr	= btrfs_getxattr,
+	.getxattr	= generic_getxattr,
 	.listxattr	= btrfs_listxattr,
 	.removexattr	= btrfs_removexattr,
 	.permission	= btrfs_permission,
@@ -10020,7 +10190,7 @@ static const struct file_operations btrfs_dir_file_operations = {
 	.fsync		= btrfs_sync_file,
 };
 
-static struct extent_io_ops btrfs_extent_io_ops = {
+static const struct extent_io_ops btrfs_extent_io_ops = {
 	.fill_delalloc = run_delalloc_range,
 	.submit_bio_hook = btrfs_submit_bio_hook,
 	.merge_bio_hook = btrfs_merge_bio_hook,
@@ -10068,7 +10238,7 @@ static const struct inode_operations btrfs_file_inode_operations = {
 	.getattr	= btrfs_getattr,
 	.setattr	= btrfs_setattr,
 	.setxattr	= btrfs_setxattr,
-	.getxattr	= btrfs_getxattr,
+	.getxattr	= generic_getxattr,
 	.listxattr      = btrfs_listxattr,
 	.removexattr	= btrfs_removexattr,
 	.permission	= btrfs_permission,
@@ -10082,7 +10252,7 @@ static const struct inode_operations btrfs_special_inode_operations = {
 	.setattr	= btrfs_setattr,
 	.permission	= btrfs_permission,
 	.setxattr	= btrfs_setxattr,
-	.getxattr	= btrfs_getxattr,
+	.getxattr	= generic_getxattr,
 	.listxattr	= btrfs_listxattr,
 	.removexattr	= btrfs_removexattr,
 	.get_acl	= btrfs_get_acl,
@@ -10091,13 +10261,12 @@ static const struct inode_operations btrfs_special_inode_operations = {
 };
 static const struct inode_operations btrfs_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 	.getattr	= btrfs_getattr,
 	.setattr	= btrfs_setattr,
 	.permission	= btrfs_permission,
 	.setxattr	= btrfs_setxattr,
-	.getxattr	= btrfs_getxattr,
+	.getxattr	= generic_getxattr,
 	.listxattr	= btrfs_listxattr,
 	.removexattr	= btrfs_removexattr,
 	.update_time	= btrfs_update_time,
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index da94138eb85e..5a23806ae418 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -59,6 +59,8 @@
 #include "props.h"
 #include "sysfs.h"
 #include "qgroup.h"
+#include "tree-log.h"
+#include "compression.h"
 
 #ifdef CONFIG_64BIT
 /* If we have a 32-bit userspace and 64-bit kernel, then the UAPI
@@ -240,7 +242,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 	if (ret)
 		return ret;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	ip_oldflags = ip->flags;
 	i_oldflags = inode->i_flags;
@@ -347,7 +349,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 
 	btrfs_update_iflags(inode);
 	inode_inc_iversion(inode);
-	inode->i_ctime = CURRENT_TIME;
+	inode->i_ctime = current_fs_time(inode->i_sb);
 	ret = btrfs_update_inode(trans, root, inode);
 
 	btrfs_end_transaction(trans, root);
@@ -358,7 +360,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 	}
 
  out_unlock:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	mnt_drop_write_file(file);
 	return ret;
 }
@@ -443,7 +445,7 @@ static noinline int create_subvol(struct inode *dir,
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct btrfs_root *new_root;
 	struct btrfs_block_rsv block_rsv;
-	struct timespec cur_time = CURRENT_TIME;
+	struct timespec cur_time = current_fs_time(dir->i_sb);
 	struct inode *inode;
 	int ret;
 	int err;
@@ -568,6 +570,10 @@ static noinline int create_subvol(struct inode *dir,
 		goto fail;
 	}
 
+	mutex_lock(&new_root->objectid_mutex);
+	new_root->highest_objectid = new_dirid;
+	mutex_unlock(&new_root->objectid_mutex);
+
 	/*
 	 * insert the directory item
 	 */
@@ -655,22 +661,28 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 	if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state))
 		return -EINVAL;
 
+	pending_snapshot = kzalloc(sizeof(*pending_snapshot), GFP_NOFS);
+	if (!pending_snapshot)
+		return -ENOMEM;
+
+	pending_snapshot->root_item = kzalloc(sizeof(struct btrfs_root_item),
+			GFP_NOFS);
+	pending_snapshot->path = btrfs_alloc_path();
+	if (!pending_snapshot->root_item || !pending_snapshot->path) {
+		ret = -ENOMEM;
+		goto free_pending;
+	}
+
 	atomic_inc(&root->will_be_snapshoted);
 	smp_mb__after_atomic();
 	btrfs_wait_for_no_snapshoting_writes(root);
 
 	ret = btrfs_start_delalloc_inodes(root, 0);
 	if (ret)
-		goto out;
+		goto dec_and_free;
 
 	btrfs_wait_ordered_extents(root, -1);
 
-	pending_snapshot = kzalloc(sizeof(*pending_snapshot), GFP_NOFS);
-	if (!pending_snapshot) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
 	btrfs_init_block_rsv(&pending_snapshot->block_rsv,
 			     BTRFS_BLOCK_RSV_TEMP);
 	/*
@@ -686,7 +698,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 					&pending_snapshot->qgroup_reserved,
 					false);
 	if (ret)
-		goto free;
+		goto dec_and_free;
 
 	pending_snapshot->dentry = dentry;
 	pending_snapshot->root = root;
@@ -737,11 +749,14 @@ fail:
 	btrfs_subvolume_release_metadata(BTRFS_I(dir)->root,
 					 &pending_snapshot->block_rsv,
 					 pending_snapshot->qgroup_reserved);
-free:
-	kfree(pending_snapshot);
-out:
+dec_and_free:
 	if (atomic_dec_and_test(&root->will_be_snapshoted))
 		wake_up_atomic_t(&root->will_be_snapshoted);
+free_pending:
+	kfree(pending_snapshot->root_item);
+	btrfs_free_path(pending_snapshot->path);
+	kfree(pending_snapshot);
+
 	return ret;
 }
 
@@ -831,10 +846,6 @@ static noinline int btrfs_mksubvol(struct path *parent,
 	if (IS_ERR(dentry))
 		goto out_unlock;
 
-	error = -EEXIST;
-	if (d_really_is_positive(dentry))
-		goto out_dput;
-
 	error = btrfs_may_create(dir, dentry);
 	if (error)
 		goto out_dput;
@@ -868,7 +879,7 @@ out_up_read:
 out_dput:
 	dput(dentry);
 out_unlock:
-	mutex_unlock(&dir->i_mutex);
+	inode_unlock(dir);
 	return error;
 }
 
@@ -887,7 +898,7 @@ static int check_defrag_in_cache(struct inode *inode, u64 offset, u32 thresh)
 	u64 end;
 
 	read_lock(&em_tree->lock);
-	em = lookup_extent_mapping(em_tree, offset, PAGE_CACHE_SIZE);
+	em = lookup_extent_mapping(em_tree, offset, PAGE_SIZE);
 	read_unlock(&em_tree->lock);
 
 	if (em) {
@@ -977,7 +988,7 @@ static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start)
 	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct extent_map *em;
-	u64 len = PAGE_CACHE_SIZE;
+	u64 len = PAGE_SIZE;
 
 	/*
 	 * hopefully we have this extent in the tree already, try without
@@ -992,7 +1003,7 @@ static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start)
 		u64 end = start + len - 1;
 
 		/* get the big lock and read metadata off disk */
-		lock_extent_bits(io_tree, start, end, 0, &cached);
+		lock_extent_bits(io_tree, start, end, &cached);
 		em = btrfs_get_extent(inode, NULL, 0, start, len, 0);
 		unlock_extent_cached(io_tree, start, end, &cached, GFP_NOFS);
 
@@ -1016,7 +1027,7 @@ static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em)
 	if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE)
 		ret = false;
 	else if ((em->block_start + em->block_len == next->block_start) &&
-		 (em->block_len > 128 * 1024 && next->block_len > 128 * 1024))
+		 (em->block_len > SZ_128K && next->block_len > SZ_128K))
 		ret = false;
 
 	free_extent_map(next);
@@ -1113,15 +1124,15 @@ static int cluster_pages_for_defrag(struct inode *inode,
 	struct extent_io_tree *tree;
 	gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
 
-	file_end = (isize - 1) >> PAGE_CACHE_SHIFT;
+	file_end = (isize - 1) >> PAGE_SHIFT;
 	if (!isize || start_index > file_end)
 		return 0;
 
 	page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1);
 
 	ret = btrfs_delalloc_reserve_space(inode,
-			start_index << PAGE_CACHE_SHIFT,
-			page_cnt << PAGE_CACHE_SHIFT);
+			start_index << PAGE_SHIFT,
+			page_cnt << PAGE_SHIFT);
 	if (ret)
 		return ret;
 	i_done = 0;
@@ -1137,10 +1148,10 @@ again:
 			break;
 
 		page_start = page_offset(page);
-		page_end = page_start + PAGE_CACHE_SIZE - 1;
+		page_end = page_start + PAGE_SIZE - 1;
 		while (1) {
 			lock_extent_bits(tree, page_start, page_end,
-					 0, &cached_state);
+					 &cached_state);
 			ordered = btrfs_lookup_ordered_extent(inode,
 							      page_start);
 			unlock_extent_cached(tree, page_start, page_end,
@@ -1158,7 +1169,7 @@ again:
 			 */
 			if (page->mapping != inode->i_mapping) {
 				unlock_page(page);
-				page_cache_release(page);
+				put_page(page);
 				goto again;
 			}
 		}
@@ -1168,7 +1179,7 @@ again:
 			lock_page(page);
 			if (!PageUptodate(page)) {
 				unlock_page(page);
-				page_cache_release(page);
+				put_page(page);
 				ret = -EIO;
 				break;
 			}
@@ -1176,7 +1187,7 @@ again:
 
 		if (page->mapping != inode->i_mapping) {
 			unlock_page(page);
-			page_cache_release(page);
+			put_page(page);
 			goto again;
 		}
 
@@ -1197,10 +1208,10 @@ again:
 		wait_on_page_writeback(pages[i]);
 
 	page_start = page_offset(pages[0]);
-	page_end = page_offset(pages[i_done - 1]) + PAGE_CACHE_SIZE;
+	page_end = page_offset(pages[i_done - 1]) + PAGE_SIZE;
 
 	lock_extent_bits(&BTRFS_I(inode)->io_tree,
-			 page_start, page_end - 1, 0, &cached_state);
+			 page_start, page_end - 1, &cached_state);
 	clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start,
 			  page_end - 1, EXTENT_DIRTY | EXTENT_DELALLOC |
 			  EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0,
@@ -1211,8 +1222,8 @@ again:
 		BTRFS_I(inode)->outstanding_extents++;
 		spin_unlock(&BTRFS_I(inode)->lock);
 		btrfs_delalloc_release_space(inode,
-				start_index << PAGE_CACHE_SHIFT,
-				(page_cnt - i_done) << PAGE_CACHE_SHIFT);
+				start_index << PAGE_SHIFT,
+				(page_cnt - i_done) << PAGE_SHIFT);
 	}
 
 
@@ -1229,17 +1240,17 @@ again:
 		set_page_extent_mapped(pages[i]);
 		set_page_dirty(pages[i]);
 		unlock_page(pages[i]);
-		page_cache_release(pages[i]);
+		put_page(pages[i]);
 	}
 	return i_done;
 out:
 	for (i = 0; i < i_done; i++) {
 		unlock_page(pages[i]);
-		page_cache_release(pages[i]);
+		put_page(pages[i]);
 	}
 	btrfs_delalloc_release_space(inode,
-			start_index << PAGE_CACHE_SHIFT,
-			page_cnt << PAGE_CACHE_SHIFT);
+			start_index << PAGE_SHIFT,
+			page_cnt << PAGE_SHIFT);
 	return ret;
 
 }
@@ -1262,9 +1273,9 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 	int defrag_count = 0;
 	int compress_type = BTRFS_COMPRESS_ZLIB;
 	u32 extent_thresh = range->extent_thresh;
-	unsigned long max_cluster = (256 * 1024) >> PAGE_CACHE_SHIFT;
+	unsigned long max_cluster = SZ_256K >> PAGE_SHIFT;
 	unsigned long cluster = max_cluster;
-	u64 new_align = ~((u64)128 * 1024 - 1);
+	u64 new_align = ~((u64)SZ_128K - 1);
 	struct page **pages = NULL;
 
 	if (isize == 0)
@@ -1281,7 +1292,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 	}
 
 	if (extent_thresh == 0)
-		extent_thresh = 256 * 1024;
+		extent_thresh = SZ_256K;
 
 	/*
 	 * if we were not given a file, allocate a readahead
@@ -1306,25 +1317,25 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 	/* find the last page to defrag */
 	if (range->start + range->len > range->start) {
 		last_index = min_t(u64, isize - 1,
-			 range->start + range->len - 1) >> PAGE_CACHE_SHIFT;
+			 range->start + range->len - 1) >> PAGE_SHIFT;
 	} else {
-		last_index = (isize - 1) >> PAGE_CACHE_SHIFT;
+		last_index = (isize - 1) >> PAGE_SHIFT;
 	}
 
 	if (newer_than) {
 		ret = find_new_extents(root, inode, newer_than,
-				       &newer_off, 64 * 1024);
+				       &newer_off, SZ_64K);
 		if (!ret) {
 			range->start = newer_off;
 			/*
 			 * we always align our defrag to help keep
 			 * the extents in the file evenly spaced
 			 */
-			i = (newer_off & new_align) >> PAGE_CACHE_SHIFT;
+			i = (newer_off & new_align) >> PAGE_SHIFT;
 		} else
 			goto out_ra;
 	} else {
-		i = range->start >> PAGE_CACHE_SHIFT;
+		i = range->start >> PAGE_SHIFT;
 	}
 	if (!max_to_defrag)
 		max_to_defrag = last_index - i + 1;
@@ -1337,7 +1348,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 		inode->i_mapping->writeback_index = i;
 
 	while (i <= last_index && defrag_count < max_to_defrag &&
-	       (i < DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE))) {
+	       (i < DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE))) {
 		/*
 		 * make sure we stop running if someone unmounts
 		 * the FS
@@ -1351,7 +1362,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 			break;
 		}
 
-		if (!should_defrag_range(inode, (u64)i << PAGE_CACHE_SHIFT,
+		if (!should_defrag_range(inode, (u64)i << PAGE_SHIFT,
 					 extent_thresh, &last_len, &skip,
 					 &defrag_end, range->flags &
 					 BTRFS_DEFRAG_RANGE_COMPRESS)) {
@@ -1360,14 +1371,14 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 			 * the should_defrag function tells us how much to skip
 			 * bump our counter by the suggested amount
 			 */
-			next = DIV_ROUND_UP(skip, PAGE_CACHE_SIZE);
+			next = DIV_ROUND_UP(skip, PAGE_SIZE);
 			i = max(i + 1, next);
 			continue;
 		}
 
 		if (!newer_than) {
-			cluster = (PAGE_CACHE_ALIGN(defrag_end) >>
-				   PAGE_CACHE_SHIFT) - i;
+			cluster = (PAGE_ALIGN(defrag_end) >>
+				   PAGE_SHIFT) - i;
 			cluster = min(cluster, max_cluster);
 		} else {
 			cluster = max_cluster;
@@ -1380,18 +1391,18 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 			ra_index += cluster;
 		}
 
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)
 			BTRFS_I(inode)->force_compress = compress_type;
 		ret = cluster_pages_for_defrag(inode, pages, i, cluster);
 		if (ret < 0) {
-			mutex_unlock(&inode->i_mutex);
+			inode_unlock(inode);
 			goto out_ra;
 		}
 
 		defrag_count += ret;
 		balance_dirty_pages_ratelimited(inode->i_mapping);
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 
 		if (newer_than) {
 			if (newer_off == (u64)-1)
@@ -1401,21 +1412,20 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 				i += ret;
 
 			newer_off = max(newer_off + 1,
-					(u64)i << PAGE_CACHE_SHIFT);
+					(u64)i << PAGE_SHIFT);
 
-			ret = find_new_extents(root, inode,
-					       newer_than, &newer_off,
-					       64 * 1024);
+			ret = find_new_extents(root, inode, newer_than,
+					       &newer_off, SZ_64K);
 			if (!ret) {
 				range->start = newer_off;
-				i = (newer_off & new_align) >> PAGE_CACHE_SHIFT;
+				i = (newer_off & new_align) >> PAGE_SHIFT;
 			} else {
 				break;
 			}
 		} else {
 			if (ret > 0) {
 				i += ret;
-				last_len += ret << PAGE_CACHE_SHIFT;
+				last_len += ret << PAGE_SHIFT;
 			} else {
 				i++;
 				last_len = 0;
@@ -1453,9 +1463,9 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 
 out_ra:
 	if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS) {
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		BTRFS_I(inode)->force_compress = BTRFS_COMPRESS_NONE;
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 	}
 	if (!file)
 		kfree(ra);
@@ -1571,7 +1581,7 @@ static noinline int btrfs_ioctl_resize(struct file *file,
 		new_size = old_size + new_size;
 	}
 
-	if (new_size < 256 * 1024 * 1024) {
+	if (new_size < SZ_256M) {
 		ret = -EINVAL;
 		goto out_free;
 	}
@@ -1644,7 +1654,7 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
 
 		src_inode = file_inode(src.file);
 		if (src_inode->i_sb != file_inode(file)->i_sb) {
-			btrfs_info(BTRFS_I(src_inode)->root->fs_info,
+			btrfs_info(BTRFS_I(file_inode(file))->root->fs_info,
 				   "Snapshot src from another FS");
 			ret = -EXDEV;
 		} else if (!inode_owner_or_capable(src_inode)) {
@@ -1712,7 +1722,7 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file,
 	if (vol_args->flags & BTRFS_SUBVOL_RDONLY)
 		readonly = true;
 	if (vol_args->flags & BTRFS_SUBVOL_QGROUP_INHERIT) {
-		if (vol_args->size > PAGE_CACHE_SIZE) {
+		if (vol_args->size > PAGE_SIZE) {
 			ret = -EINVAL;
 			goto free_args;
 		}
@@ -2085,8 +2095,6 @@ static noinline int search_ioctl(struct inode *inode,
 		key.offset = (u64)-1;
 		root = btrfs_read_fs_root_no_name(info, &key);
 		if (IS_ERR(root)) {
-			btrfs_err(info, "could not find root %llu",
-			       sk->tree_id);
 			btrfs_free_path(path);
 			return -ENOENT;
 		}
@@ -2160,7 +2168,7 @@ static noinline int btrfs_ioctl_tree_search_v2(struct file *file,
 	struct inode *inode;
 	int ret;
 	size_t buf_size;
-	const size_t buf_limit = 16 * 1024 * 1024;
+	const size_t buf_limit = SZ_16M;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -2418,7 +2426,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 		goto out_dput;
 	}
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	/*
 	 * Don't allow to delete a subvolume with send in progress. This is
@@ -2464,6 +2472,8 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 	trans->block_rsv = &block_rsv;
 	trans->bytes_reserved = block_rsv.size;
 
+	btrfs_record_snapshot_destroy(trans, dir);
+
 	ret = btrfs_unlink_subvol(trans, root, dir,
 				dest->root_key.objectid,
 				dentry->d_name.name,
@@ -2531,7 +2541,7 @@ out_up_write:
 		spin_unlock(&dest->root_item_lock);
 	}
 out_unlock_inode:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	if (!err) {
 		d_invalidate(dentry);
 		btrfs_invalidate_inodes(dest);
@@ -2547,7 +2557,7 @@ out_unlock_inode:
 out_dput:
 	dput(dentry);
 out_unlock_dir:
-	mutex_unlock(&dir->i_mutex);
+	inode_unlock(dir);
 out_drop_write:
 	mnt_drop_write_file(file);
 out:
@@ -2782,24 +2792,29 @@ out:
 static struct page *extent_same_get_page(struct inode *inode, pgoff_t index)
 {
 	struct page *page;
-	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
 
 	page = grab_cache_page(inode->i_mapping, index);
 	if (!page)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	if (!PageUptodate(page)) {
-		if (extent_read_full_page_nolock(tree, page, btrfs_get_extent,
-						 0))
-			return NULL;
+		int ret;
+
+		ret = btrfs_readpage(NULL, page);
+		if (ret)
+			return ERR_PTR(ret);
 		lock_page(page);
 		if (!PageUptodate(page)) {
 			unlock_page(page);
-			page_cache_release(page);
-			return NULL;
+			put_page(page);
+			return ERR_PTR(-EIO);
+		}
+		if (page->mapping != inode->i_mapping) {
+			unlock_page(page);
+			put_page(page);
+			return ERR_PTR(-EAGAIN);
 		}
 	}
-	unlock_page(page);
 
 	return page;
 }
@@ -2808,20 +2823,34 @@ static int gather_extent_pages(struct inode *inode, struct page **pages,
 			       int num_pages, u64 off)
 {
 	int i;
-	pgoff_t index = off >> PAGE_CACHE_SHIFT;
+	pgoff_t index = off >> PAGE_SHIFT;
 
 	for (i = 0; i < num_pages; i++) {
+again:
 		pages[i] = extent_same_get_page(inode, index + i);
-		if (!pages[i])
-			return -ENOMEM;
+		if (IS_ERR(pages[i])) {
+			int err = PTR_ERR(pages[i]);
+
+			if (err == -EAGAIN)
+				goto again;
+			pages[i] = NULL;
+			return err;
+		}
 	}
 	return 0;
 }
 
-static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
+static int lock_extent_range(struct inode *inode, u64 off, u64 len,
+			     bool retry_range_locking)
 {
-	/* do any pending delalloc/csum calc on src, one way or
-	   another, and lock file content */
+	/*
+	 * Do any pending delalloc/csum calculations on inode, one way or
+	 * another, and lock file content.
+	 * The locking order is:
+	 *
+	 *   1) pages
+	 *   2) range in the inode's io tree
+	 */
 	while (1) {
 		struct btrfs_ordered_extent *ordered;
 		lock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
@@ -2839,14 +2868,17 @@ static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
 		unlock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
 		if (ordered)
 			btrfs_put_ordered_extent(ordered);
+		if (!retry_range_locking)
+			return -EAGAIN;
 		btrfs_wait_ordered_range(inode, off, len);
 	}
+	return 0;
 }
 
 static void btrfs_double_inode_unlock(struct inode *inode1, struct inode *inode2)
 {
-	mutex_unlock(&inode1->i_mutex);
-	mutex_unlock(&inode2->i_mutex);
+	inode_unlock(inode1);
+	inode_unlock(inode2);
 }
 
 static void btrfs_double_inode_lock(struct inode *inode1, struct inode *inode2)
@@ -2854,8 +2886,8 @@ static void btrfs_double_inode_lock(struct inode *inode1, struct inode *inode2)
 	if (inode1 < inode2)
 		swap(inode1, inode2);
 
-	mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
-	mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
+	inode_lock_nested(inode1, I_MUTEX_PARENT);
+	inode_lock_nested(inode2, I_MUTEX_CHILD);
 }
 
 static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1,
@@ -2865,15 +2897,24 @@ static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1,
 	unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
 }
 
-static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
-				     struct inode *inode2, u64 loff2, u64 len)
+static int btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
+				    struct inode *inode2, u64 loff2, u64 len,
+				    bool retry_range_locking)
 {
+	int ret;
+
 	if (inode1 < inode2) {
 		swap(inode1, inode2);
 		swap(loff1, loff2);
 	}
-	lock_extent_range(inode1, loff1, len);
-	lock_extent_range(inode2, loff2, len);
+	ret = lock_extent_range(inode1, loff1, len, retry_range_locking);
+	if (ret)
+		return ret;
+	ret = lock_extent_range(inode2, loff2, len, retry_range_locking);
+	if (ret)
+		unlock_extent(&BTRFS_I(inode1)->io_tree, loff1,
+			      loff1 + len - 1);
+	return ret;
 }
 
 struct cmp_pages {
@@ -2889,11 +2930,15 @@ static void btrfs_cmp_data_free(struct cmp_pages *cmp)
 
 	for (i = 0; i < cmp->num_pages; i++) {
 		pg = cmp->src_pages[i];
-		if (pg)
-			page_cache_release(pg);
+		if (pg) {
+			unlock_page(pg);
+			put_page(pg);
+		}
 		pg = cmp->dst_pages[i];
-		if (pg)
-			page_cache_release(pg);
+		if (pg) {
+			unlock_page(pg);
+			put_page(pg);
+		}
 	}
 	kfree(cmp->src_pages);
 	kfree(cmp->dst_pages);
@@ -2904,7 +2949,7 @@ static int btrfs_cmp_data_prepare(struct inode *src, u64 loff,
 				  u64 len, struct cmp_pages *cmp)
 {
 	int ret;
-	int num_pages = PAGE_CACHE_ALIGN(len) >> PAGE_CACHE_SHIFT;
+	int num_pages = PAGE_ALIGN(len) >> PAGE_SHIFT;
 	struct page **src_pgarr, **dst_pgarr;
 
 	/*
@@ -2913,8 +2958,8 @@ static int btrfs_cmp_data_prepare(struct inode *src, u64 loff,
 	 * of the array is bounded by len, which is in turn bounded by
 	 * BTRFS_MAX_DEDUPE_LEN.
 	 */
-	src_pgarr = kzalloc(num_pages * sizeof(struct page *), GFP_NOFS);
-	dst_pgarr = kzalloc(num_pages * sizeof(struct page *), GFP_NOFS);
+	src_pgarr = kcalloc(num_pages, sizeof(struct page *), GFP_KERNEL);
+	dst_pgarr = kcalloc(num_pages, sizeof(struct page *), GFP_KERNEL);
 	if (!src_pgarr || !dst_pgarr) {
 		kfree(src_pgarr);
 		kfree(dst_pgarr);
@@ -2942,18 +2987,20 @@ static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst,
 	int ret = 0;
 	int i;
 	struct page *src_page, *dst_page;
-	unsigned int cmp_len = PAGE_CACHE_SIZE;
+	unsigned int cmp_len = PAGE_SIZE;
 	void *addr, *dst_addr;
 
 	i = 0;
 	while (len) {
-		if (len < PAGE_CACHE_SIZE)
+		if (len < PAGE_SIZE)
 			cmp_len = len;
 
 		BUG_ON(i >= cmp->num_pages);
 
 		src_page = cmp->src_pages[i];
 		dst_page = cmp->dst_pages[i];
+		ASSERT(PageLocked(src_page));
+		ASSERT(PageLocked(dst_page));
 
 		addr = kmap_atomic(src_page);
 		dst_addr = kmap_atomic(dst_page);
@@ -2962,7 +3009,7 @@ static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst,
 		flush_dcache_page(dst_page);
 
 		if (memcmp(addr, dst_addr, cmp_len))
-			ret = BTRFS_SAME_DATA_DIFFERS;
+			ret = -EBADE;
 
 		kunmap_atomic(addr);
 		kunmap_atomic(dst_addr);
@@ -3014,11 +3061,14 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
 		return 0;
 
 	if (same_inode) {
-		mutex_lock(&src->i_mutex);
+		inode_lock(src);
 
 		ret = extent_same_check_offsets(src, loff, &len, olen);
 		if (ret)
 			goto out_unlock;
+		ret = extent_same_check_offsets(src, dst_loff, &len, olen);
+		if (ret)
+			goto out_unlock;
 
 		/*
 		 * Single inode case wants the same checks, except we
@@ -3066,14 +3116,46 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
 		goto out_unlock;
 	}
 
+again:
 	ret = btrfs_cmp_data_prepare(src, loff, dst, dst_loff, olen, &cmp);
 	if (ret)
 		goto out_unlock;
 
 	if (same_inode)
-		lock_extent_range(src, same_lock_start, same_lock_len);
+		ret = lock_extent_range(src, same_lock_start, same_lock_len,
+					false);
 	else
-		btrfs_double_extent_lock(src, loff, dst, dst_loff, len);
+		ret = btrfs_double_extent_lock(src, loff, dst, dst_loff, len,
+					       false);
+	/*
+	 * If one of the inodes has dirty pages in the respective range or
+	 * ordered extents, we need to flush dellaloc and wait for all ordered
+	 * extents in the range. We must unlock the pages and the ranges in the
+	 * io trees to avoid deadlocks when flushing delalloc (requires locking
+	 * pages) and when waiting for ordered extents to complete (they require
+	 * range locking).
+	 */
+	if (ret == -EAGAIN) {
+		/*
+		 * Ranges in the io trees already unlocked. Now unlock all
+		 * pages before waiting for all IO to complete.
+		 */
+		btrfs_cmp_data_free(&cmp);
+		if (same_inode) {
+			btrfs_wait_ordered_range(src, same_lock_start,
+						 same_lock_len);
+		} else {
+			btrfs_wait_ordered_range(src, loff, len);
+			btrfs_wait_ordered_range(dst, dst_loff, len);
+		}
+		goto again;
+	}
+	ASSERT(ret == 0);
+	if (WARN_ON(ret)) {
+		/* ranges in the io trees already unlocked */
+		btrfs_cmp_data_free(&cmp);
+		return ret;
+	}
 
 	/* pass original length for comparison so we stay within i_size */
 	ret = btrfs_cmp_data(src, loff, dst, dst_loff, olen, &cmp);
@@ -3089,121 +3171,39 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
 	btrfs_cmp_data_free(&cmp);
 out_unlock:
 	if (same_inode)
-		mutex_unlock(&src->i_mutex);
+		inode_unlock(src);
 	else
 		btrfs_double_inode_unlock(src, dst);
 
 	return ret;
 }
 
-#define BTRFS_MAX_DEDUPE_LEN	(16 * 1024 * 1024)
+#define BTRFS_MAX_DEDUPE_LEN	SZ_16M
 
-static long btrfs_ioctl_file_extent_same(struct file *file,
-			struct btrfs_ioctl_same_args __user *argp)
+ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
+				struct file *dst_file, u64 dst_loff)
 {
-	struct btrfs_ioctl_same_args *same = NULL;
-	struct btrfs_ioctl_same_extent_info *info;
-	struct inode *src = file_inode(file);
-	u64 off;
-	u64 len;
-	int i;
-	int ret;
-	unsigned long size;
+	struct inode *src = file_inode(src_file);
+	struct inode *dst = file_inode(dst_file);
 	u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize;
-	bool is_admin = capable(CAP_SYS_ADMIN);
-	u16 count;
+	ssize_t res;
 
-	if (!(file->f_mode & FMODE_READ))
-		return -EINVAL;
+	if (olen > BTRFS_MAX_DEDUPE_LEN)
+		olen = BTRFS_MAX_DEDUPE_LEN;
 
-	ret = mnt_want_write_file(file);
-	if (ret)
-		return ret;
-
-	if (get_user(count, &argp->dest_count)) {
-		ret = -EFAULT;
-		goto out;
-	}
-
-	size = offsetof(struct btrfs_ioctl_same_args __user, info[count]);
-
-	same = memdup_user(argp, size);
-
-	if (IS_ERR(same)) {
-		ret = PTR_ERR(same);
-		same = NULL;
-		goto out;
-	}
-
-	off = same->logical_offset;
-	len = same->length;
-
-	/*
-	 * Limit the total length we will dedupe for each operation.
-	 * This is intended to bound the total time spent in this
-	 * ioctl to something sane.
-	 */
-	if (len > BTRFS_MAX_DEDUPE_LEN)
-		len = BTRFS_MAX_DEDUPE_LEN;
-
-	if (WARN_ON_ONCE(bs < PAGE_CACHE_SIZE)) {
+	if (WARN_ON_ONCE(bs < PAGE_SIZE)) {
 		/*
 		 * Btrfs does not support blocksize < page_size. As a
 		 * result, btrfs_cmp_data() won't correctly handle
 		 * this situation without an update.
 		 */
-		ret = -EINVAL;
-		goto out;
-	}
-
-	ret = -EISDIR;
-	if (S_ISDIR(src->i_mode))
-		goto out;
-
-	ret = -EACCES;
-	if (!S_ISREG(src->i_mode))
-		goto out;
-
-	/* pre-format output fields to sane values */
-	for (i = 0; i < count; i++) {
-		same->info[i].bytes_deduped = 0ULL;
-		same->info[i].status = 0;
-	}
-
-	for (i = 0, info = same->info; i < count; i++, info++) {
-		struct inode *dst;
-		struct fd dst_file = fdget(info->fd);
-		if (!dst_file.file) {
-			info->status = -EBADF;
-			continue;
-		}
-		dst = file_inode(dst_file.file);
-
-		if (!(is_admin || (dst_file.file->f_mode & FMODE_WRITE))) {
-			info->status = -EINVAL;
-		} else if (file->f_path.mnt != dst_file.file->f_path.mnt) {
-			info->status = -EXDEV;
-		} else if (S_ISDIR(dst->i_mode)) {
-			info->status = -EISDIR;
-		} else if (!S_ISREG(dst->i_mode)) {
-			info->status = -EACCES;
-		} else {
-			info->status = btrfs_extent_same(src, off, len, dst,
-							info->logical_offset);
-			if (info->status == 0)
-				info->bytes_deduped += len;
-		}
-		fdput(dst_file);
+		return -EINVAL;
 	}
 
-	ret = copy_to_user(argp, same, size);
-	if (ret)
-		ret = -EFAULT;
-
-out:
-	mnt_drop_write_file(file);
-	kfree(same);
-	return ret;
+	res = btrfs_extent_same(src, loff, olen, dst, dst_loff);
+	if (res)
+		return res;
+	return olen;
 }
 
 static int clone_finish_inode_update(struct btrfs_trans_handle *trans,
@@ -3218,7 +3218,7 @@ static int clone_finish_inode_update(struct btrfs_trans_handle *trans,
 
 	inode_inc_iversion(inode);
 	if (!no_time_update)
-		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+		inode->i_mtime = inode->i_ctime = current_fs_time(inode->i_sb);
 	/*
 	 * We round up to the block size at eof when determining which
 	 * extents to clone above, but shouldn't round up the file size.
@@ -3478,7 +3478,7 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 		return ret;
 	}
 
-	path->reada = 2;
+	path->reada = READA_FORWARD;
 	/* clone data */
 	key.objectid = btrfs_ino(src);
 	key.type = BTRFS_EXTENT_DATA_KEY;
@@ -3779,17 +3779,16 @@ out:
 	return ret;
 }
 
-static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
-				       u64 off, u64 olen, u64 destoff)
+static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
+					u64 off, u64 olen, u64 destoff)
 {
 	struct inode *inode = file_inode(file);
+	struct inode *src = file_inode(file_src);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct fd src_file;
-	struct inode *src;
 	int ret;
 	u64 len = olen;
 	u64 bs = root->fs_info->sb->s_blocksize;
-	int same_inode = 0;
+	int same_inode = src == inode;
 
 	/*
 	 * TODO:
@@ -3802,54 +3801,25 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 	 *   be either compressed or non-compressed.
 	 */
 
-	/* the destination must be opened for writing */
-	if (!(file->f_mode & FMODE_WRITE) || (file->f_flags & O_APPEND))
-		return -EINVAL;
-
 	if (btrfs_root_readonly(root))
 		return -EROFS;
 
-	ret = mnt_want_write_file(file);
-	if (ret)
-		return ret;
-
-	src_file = fdget(srcfd);
-	if (!src_file.file) {
-		ret = -EBADF;
-		goto out_drop_write;
-	}
-
-	ret = -EXDEV;
-	if (src_file.file->f_path.mnt != file->f_path.mnt)
-		goto out_fput;
-
-	src = file_inode(src_file.file);
-
-	ret = -EINVAL;
-	if (src == inode)
-		same_inode = 1;
-
-	/* the src must be open for reading */
-	if (!(src_file.file->f_mode & FMODE_READ))
-		goto out_fput;
+	if (file_src->f_path.mnt != file->f_path.mnt ||
+	    src->i_sb != inode->i_sb)
+		return -EXDEV;
 
 	/* don't make the dst file partly checksummed */
 	if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
 	    (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM))
-		goto out_fput;
+		return -EINVAL;
 
-	ret = -EISDIR;
 	if (S_ISDIR(src->i_mode) || S_ISDIR(inode->i_mode))
-		goto out_fput;
-
-	ret = -EXDEV;
-	if (src->i_sb != inode->i_sb)
-		goto out_fput;
+		return -EISDIR;
 
 	if (!same_inode) {
 		btrfs_double_inode_lock(src, inode);
 	} else {
-		mutex_lock(&src->i_mutex);
+		inode_lock(src);
 	}
 
 	/* determine range to clone */
@@ -3895,9 +3865,15 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 		u64 lock_start = min_t(u64, off, destoff);
 		u64 lock_len = max_t(u64, off, destoff) + len - lock_start;
 
-		lock_extent_range(src, lock_start, lock_len);
+		ret = lock_extent_range(src, lock_start, lock_len, true);
 	} else {
-		btrfs_double_extent_lock(src, off, inode, destoff, len);
+		ret = btrfs_double_extent_lock(src, off, inode, destoff, len,
+					       true);
+	}
+	ASSERT(ret == 0);
+	if (WARN_ON(ret)) {
+		/* ranges in the io trees already unlocked */
+		goto out_unlock;
 	}
 
 	ret = btrfs_clone(src, inode, off, olen, len, destoff, 0);
@@ -3914,28 +3890,33 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 	 * Truncate page cache pages so that future reads will see the cloned
 	 * data immediately and not the previous data.
 	 */
-	truncate_inode_pages_range(&inode->i_data, destoff,
-				   PAGE_CACHE_ALIGN(destoff + len) - 1);
+	truncate_inode_pages_range(&inode->i_data,
+				round_down(destoff, PAGE_SIZE),
+				round_up(destoff + len, PAGE_SIZE) - 1);
 out_unlock:
 	if (!same_inode)
 		btrfs_double_inode_unlock(src, inode);
 	else
-		mutex_unlock(&src->i_mutex);
-out_fput:
-	fdput(src_file);
-out_drop_write:
-	mnt_drop_write_file(file);
+		inode_unlock(src);
 	return ret;
 }
 
-static long btrfs_ioctl_clone_range(struct file *file, void __user *argp)
+ssize_t btrfs_copy_file_range(struct file *file_in, loff_t pos_in,
+			      struct file *file_out, loff_t pos_out,
+			      size_t len, unsigned int flags)
 {
-	struct btrfs_ioctl_clone_range_args args;
+	ssize_t ret;
 
-	if (copy_from_user(&args, argp, sizeof(args)))
-		return -EFAULT;
-	return btrfs_ioctl_clone(file, args.src_fd, args.src_offset,
-				 args.src_length, args.dest_offset);
+	ret = btrfs_clone_files(file_out, file_in, pos_in, len, pos_out);
+	if (ret == 0)
+		ret = len;
+	return ret;
+}
+
+int btrfs_clone_file_range(struct file *src_file, loff_t off,
+		struct file *dst_file, loff_t destoff, u64 len)
+{
+	return btrfs_clone_files(dst_file, src_file, off, len, destoff);
 }
 
 /*
@@ -4143,11 +4124,11 @@ static long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg)
 	/* we generally have at most 6 or so space infos, one for each raid
 	 * level.  So, a whole page should be more than enough for everyone
 	 */
-	if (alloc_size > PAGE_CACHE_SIZE)
+	if (alloc_size > PAGE_SIZE)
 		return -ENOMEM;
 
 	space_args.total_spaces = 0;
-	dest = kmalloc(alloc_size, GFP_NOFS);
+	dest = kmalloc(alloc_size, GFP_KERNEL);
 	if (!dest)
 		return -ENOMEM;
 	dest_orig = dest;
@@ -4524,7 +4505,7 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_root *root,
 		goto out;
 	}
 
-	size = min_t(u32, loi->size, 64 * 1024);
+	size = min_t(u32, loi->size, SZ_64K);
 	inodes = init_data_container(size);
 	if (IS_ERR(inodes)) {
 		ret = PTR_ERR(inodes);
@@ -4673,7 +4654,7 @@ locked:
 		goto out_bargs;
 	}
 
-	bctl = kzalloc(sizeof(*bctl), GFP_NOFS);
+	bctl = kzalloc(sizeof(*bctl), GFP_KERNEL);
 	if (!bctl) {
 		ret = -ENOMEM;
 		goto out_bargs;
@@ -4759,7 +4740,7 @@ static long btrfs_ioctl_balance_progress(struct btrfs_root *root,
 		goto out;
 	}
 
-	bargs = kzalloc(sizeof(*bargs), GFP_NOFS);
+	bargs = kzalloc(sizeof(*bargs), GFP_KERNEL);
 	if (!bargs) {
 		ret = -ENOMEM;
 		goto out;
@@ -5019,7 +5000,7 @@ static long btrfs_ioctl_quota_rescan_status(struct file *file, void __user *arg)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	qsa = kzalloc(sizeof(*qsa), GFP_NOFS);
+	qsa = kzalloc(sizeof(*qsa), GFP_KERNEL);
 	if (!qsa)
 		return -ENOMEM;
 
@@ -5052,7 +5033,7 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file,
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_root_item *root_item = &root->root_item;
 	struct btrfs_trans_handle *trans;
-	struct timespec ct = CURRENT_TIME;
+	struct timespec ct = current_fs_time(inode->i_sb);
 	int ret = 0;
 	int received_uuid_changed;
 
@@ -5149,7 +5130,7 @@ static long btrfs_ioctl_set_received_subvol_32(struct file *file,
 		goto out;
 	}
 
-	args64 = kmalloc(sizeof(*args64), GFP_NOFS);
+	args64 = kmalloc(sizeof(*args64), GFP_KERNEL);
 	if (!args64) {
 		ret = -ENOMEM;
 		goto out;
@@ -5283,10 +5264,9 @@ out_unlock:
 	  .compat_ro_flags = BTRFS_FEATURE_COMPAT_RO_##suffix, \
 	  .incompat_flags = BTRFS_FEATURE_INCOMPAT_##suffix }
 
-static int btrfs_ioctl_get_supported_features(struct file *file,
-					      void __user *arg)
+int btrfs_ioctl_get_supported_features(void __user *arg)
 {
-	static struct btrfs_ioctl_feature_flags features[3] = {
+	static const struct btrfs_ioctl_feature_flags features[3] = {
 		INIT_FEATURE_FLAGS(SUPP),
 		INIT_FEATURE_FLAGS(SAFE_SET),
 		INIT_FEATURE_FLAGS(SAFE_CLEAR)
@@ -5485,10 +5465,6 @@ long btrfs_ioctl(struct file *file, unsigned int
 		return btrfs_ioctl_dev_info(root, argp);
 	case BTRFS_IOC_BALANCE:
 		return btrfs_ioctl_balance(file, NULL);
-	case BTRFS_IOC_CLONE:
-		return btrfs_ioctl_clone(file, arg, 0, 0, 0);
-	case BTRFS_IOC_CLONE_RANGE:
-		return btrfs_ioctl_clone_range(file, argp);
 	case BTRFS_IOC_TRANS_START:
 		return btrfs_ioctl_trans_start(file);
 	case BTRFS_IOC_TRANS_END:
@@ -5566,10 +5542,8 @@ long btrfs_ioctl(struct file *file, unsigned int
 		return btrfs_ioctl_get_fslabel(file, argp);
 	case BTRFS_IOC_SET_FSLABEL:
 		return btrfs_ioctl_set_fslabel(file, argp);
-	case BTRFS_IOC_FILE_EXTENT_SAME:
-		return btrfs_ioctl_file_extent_same(file, argp);
 	case BTRFS_IOC_GET_SUPPORTED_FEATURES:
-		return btrfs_ioctl_get_supported_features(file, argp);
+		return btrfs_ioctl_get_supported_features(argp);
 	case BTRFS_IOC_GET_FEATURES:
 		return btrfs_ioctl_get_features(file, argp);
 	case BTRFS_IOC_SET_FEATURES:
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 8077461fc56a..d13128c70ddd 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -56,7 +56,6 @@ void btrfs_set_lock_blocking_rw(struct extent_buffer *eb, int rw)
 		atomic_dec(&eb->spinning_readers);
 		read_unlock(&eb->lock);
 	}
-	return;
 }
 
 /*
@@ -96,7 +95,6 @@ void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw)
 		    waitqueue_active(&eb->read_lock_wq))
 			wake_up(&eb->read_lock_wq);
 	}
-	return;
 }
 
 /*
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index a2f051347731..1adfbe7be6b8 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -55,8 +55,8 @@ static struct list_head *lzo_alloc_workspace(void)
 		return ERR_PTR(-ENOMEM);
 
 	workspace->mem = vmalloc(LZO1X_MEM_COMPRESS);
-	workspace->buf = vmalloc(lzo1x_worst_compress(PAGE_CACHE_SIZE));
-	workspace->cbuf = vmalloc(lzo1x_worst_compress(PAGE_CACHE_SIZE));
+	workspace->buf = vmalloc(lzo1x_worst_compress(PAGE_SIZE));
+	workspace->cbuf = vmalloc(lzo1x_worst_compress(PAGE_SIZE));
 	if (!workspace->mem || !workspace->buf || !workspace->cbuf)
 		goto fail;
 
@@ -116,7 +116,7 @@ static int lzo_compress_pages(struct list_head *ws,
 	*total_out = 0;
 	*total_in = 0;
 
-	in_page = find_get_page(mapping, start >> PAGE_CACHE_SHIFT);
+	in_page = find_get_page(mapping, start >> PAGE_SHIFT);
 	data_in = kmap(in_page);
 
 	/*
@@ -133,10 +133,10 @@ static int lzo_compress_pages(struct list_head *ws,
 	tot_out = LZO_LEN;
 	pages[0] = out_page;
 	nr_pages = 1;
-	pg_bytes_left = PAGE_CACHE_SIZE - LZO_LEN;
+	pg_bytes_left = PAGE_SIZE - LZO_LEN;
 
 	/* compress at most one page of data each time */
-	in_len = min(len, PAGE_CACHE_SIZE);
+	in_len = min(len, PAGE_SIZE);
 	while (tot_in < len) {
 		ret = lzo1x_1_compress(data_in, in_len, workspace->cbuf,
 				       &out_len, workspace->mem);
@@ -201,7 +201,7 @@ static int lzo_compress_pages(struct list_head *ws,
 				cpage_out = kmap(out_page);
 				pages[nr_pages++] = out_page;
 
-				pg_bytes_left = PAGE_CACHE_SIZE;
+				pg_bytes_left = PAGE_SIZE;
 				out_offset = 0;
 			}
 		}
@@ -221,12 +221,12 @@ static int lzo_compress_pages(struct list_head *ws,
 
 		bytes_left = len - tot_in;
 		kunmap(in_page);
-		page_cache_release(in_page);
+		put_page(in_page);
 
-		start += PAGE_CACHE_SIZE;
-		in_page = find_get_page(mapping, start >> PAGE_CACHE_SHIFT);
+		start += PAGE_SIZE;
+		in_page = find_get_page(mapping, start >> PAGE_SHIFT);
 		data_in = kmap(in_page);
-		in_len = min(bytes_left, PAGE_CACHE_SIZE);
+		in_len = min(bytes_left, PAGE_SIZE);
 	}
 
 	if (tot_out > tot_in)
@@ -248,7 +248,7 @@ out:
 
 	if (in_page) {
 		kunmap(in_page);
-		page_cache_release(in_page);
+		put_page(in_page);
 	}
 
 	return ret;
@@ -266,7 +266,7 @@ static int lzo_decompress_biovec(struct list_head *ws,
 	char *data_in;
 	unsigned long page_in_index = 0;
 	unsigned long page_out_index = 0;
-	unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_CACHE_SIZE);
+	unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE);
 	unsigned long buf_start;
 	unsigned long buf_offset = 0;
 	unsigned long bytes;
@@ -289,7 +289,7 @@ static int lzo_decompress_biovec(struct list_head *ws,
 	tot_in = LZO_LEN;
 	in_offset = LZO_LEN;
 	tot_len = min_t(size_t, srclen, tot_len);
-	in_page_bytes_left = PAGE_CACHE_SIZE - LZO_LEN;
+	in_page_bytes_left = PAGE_SIZE - LZO_LEN;
 
 	tot_out = 0;
 	pg_offset = 0;
@@ -345,12 +345,12 @@ cont:
 
 				data_in = kmap(pages_in[++page_in_index]);
 
-				in_page_bytes_left = PAGE_CACHE_SIZE;
+				in_page_bytes_left = PAGE_SIZE;
 				in_offset = 0;
 			}
 		}
 
-		out_len = lzo1x_worst_compress(PAGE_CACHE_SIZE);
+		out_len = lzo1x_worst_compress(PAGE_SIZE);
 		ret = lzo1x_decompress_safe(buf, in_len, workspace->buf,
 					    &out_len);
 		if (need_unmap)
@@ -399,7 +399,7 @@ static int lzo_decompress(struct list_head *ws, unsigned char *data_in,
 	in_len = read_compress_length(data_in);
 	data_in += LZO_LEN;
 
-	out_len = PAGE_CACHE_SIZE;
+	out_len = PAGE_SIZE;
 	ret = lzo1x_decompress_safe(data_in, in_len, workspace->buf, &out_len);
 	if (ret != LZO_E_OK) {
 		printk(KERN_WARNING "BTRFS: decompress failed!\n");
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 8c27292ea9ea..0de7da5a610d 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -25,6 +25,7 @@
 #include "btrfs_inode.h"
 #include "extent_io.h"
 #include "disk-io.h"
+#include "compression.h"
 
 static struct kmem_cache *btrfs_ordered_extent_cache;
 
@@ -1009,7 +1010,7 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
 	for (; node; node = rb_prev(node)) {
 		test = rb_entry(node, struct btrfs_ordered_extent, rb_node);
 
-		/* We treat this entry as if it doesnt exist */
+		/* We treat this entry as if it doesn't exist */
 		if (test_bit(BTRFS_ORDERED_UPDATED_ISIZE, &test->flags))
 			continue;
 		if (test->file_offset + test->len <= disk_i_size)
@@ -1114,6 +1115,5 @@ int __init ordered_data_init(void)
 
 void ordered_data_exit(void)
 {
-	if (btrfs_ordered_extent_cache)
-		kmem_cache_destroy(btrfs_ordered_extent_cache);
+	kmem_cache_destroy(btrfs_ordered_extent_cache);
 }
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 647ab12fdf5d..147dc6ca5de1 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -295,8 +295,27 @@ void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l)
 			       btrfs_dev_extent_chunk_offset(l, dev_extent),
 			       btrfs_dev_extent_length(l, dev_extent));
 			break;
-		case BTRFS_DEV_STATS_KEY:
-			printk(KERN_INFO "\t\tdevice stats\n");
+		case BTRFS_PERSISTENT_ITEM_KEY:
+			printk(KERN_INFO "\t\tpersistent item objectid %llu offset %llu\n",
+					key.objectid, key.offset);
+			switch (key.objectid) {
+			case BTRFS_DEV_STATS_OBJECTID:
+				printk(KERN_INFO "\t\tdevice stats\n");
+				break;
+			default:
+				printk(KERN_INFO "\t\tunknown persistent item\n");
+			}
+			break;
+		case BTRFS_TEMPORARY_ITEM_KEY:
+			printk(KERN_INFO "\t\ttemporary item objectid %llu offset %llu\n",
+					key.objectid, key.offset);
+			switch (key.objectid) {
+			case BTRFS_BALANCE_OBJECTID:
+				printk(KERN_INFO "\t\tbalance status\n");
+				break;
+			default:
+				printk(KERN_INFO "\t\tunknown temporary item\n");
+			}
 			break;
 		case BTRFS_DEV_REPLACE_KEY:
 			printk(KERN_INFO "\t\tdev replace\n");
diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c
index f9e60231f685..36992128c746 100644
--- a/fs/btrfs/props.c
+++ b/fs/btrfs/props.c
@@ -22,6 +22,7 @@
 #include "hash.h"
 #include "transaction.h"
 #include "xattr.h"
+#include "compression.h"
 
 #define BTRFS_PROP_HANDLERS_HT_BITS 8
 static DEFINE_HASHTABLE(prop_handlers_ht, BTRFS_PROP_HANDLERS_HT_BITS);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 46476c226395..9e119552ed32 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -993,9 +993,10 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans,
 	mutex_lock(&fs_info->qgroup_ioctl_lock);
 	if (!fs_info->quota_root)
 		goto out;
-	spin_lock(&fs_info->qgroup_lock);
 	fs_info->quota_enabled = 0;
 	fs_info->pending_quota_state = 0;
+	btrfs_qgroup_wait_for_completion(fs_info);
+	spin_lock(&fs_info->qgroup_lock);
 	quota_root = fs_info->quota_root;
 	fs_info->quota_root = NULL;
 	fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_ON;
@@ -1461,6 +1462,9 @@ struct btrfs_qgroup_extent_record
 	struct btrfs_qgroup_extent_record *entry;
 	u64 bytenr = record->bytenr;
 
+	assert_spin_locked(&delayed_refs->lock);
+	trace_btrfs_qgroup_insert_dirty_extent(record);
+
 	while (*p) {
 		parent_node = *p;
 		entry = rb_entry(parent_node, struct btrfs_qgroup_extent_record,
@@ -1591,6 +1595,9 @@ static int qgroup_update_counters(struct btrfs_fs_info *fs_info,
 		cur_old_count = btrfs_qgroup_get_old_refcnt(qg, seq);
 		cur_new_count = btrfs_qgroup_get_new_refcnt(qg, seq);
 
+		trace_qgroup_update_counters(qg->qgroupid, cur_old_count,
+					     cur_new_count);
+
 		/* Rfer update part */
 		if (cur_old_count == 0 && cur_new_count > 0) {
 			qg->rfer += num_bytes;
@@ -1680,6 +1687,9 @@ btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans,
 		goto out_free;
 	BUG_ON(!fs_info->quota_root);
 
+	trace_btrfs_qgroup_account_extent(bytenr, num_bytes, nr_old_roots,
+					  nr_new_roots);
+
 	qgroups = ulist_alloc(GFP_NOFS);
 	if (!qgroups) {
 		ret = -ENOMEM;
@@ -1749,6 +1759,8 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans,
 		record = rb_entry(node, struct btrfs_qgroup_extent_record,
 				  node);
 
+		trace_btrfs_qgroup_account_extents(record);
+
 		if (!ret) {
 			/*
 			 * Use (u64)-1 as time_seq to do special search, which
@@ -1839,8 +1851,10 @@ out:
 }
 
 /*
- * copy the acounting information between qgroups. This is necessary when a
- * snapshot or a subvolume is created
+ * Copy the acounting information between qgroups. This is necessary
+ * when a snapshot or a subvolume is created. Throwing an error will
+ * cause a transaction abort so we take extra care here to only error
+ * when a readonly fs is a reasonable outcome.
  */
 int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 			 struct btrfs_fs_info *fs_info, u64 srcid, u64 objectid,
@@ -1870,15 +1884,15 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 		       2 * inherit->num_excl_copies;
 		for (i = 0; i < nums; ++i) {
 			srcgroup = find_qgroup_rb(fs_info, *i_qgroups);
-			if (!srcgroup) {
-				ret = -EINVAL;
-				goto out;
-			}
 
-			if ((srcgroup->qgroupid >> 48) <= (objectid >> 48)) {
-				ret = -EINVAL;
-				goto out;
-			}
+			/*
+			 * Zero out invalid groups so we can ignore
+			 * them later.
+			 */
+			if (!srcgroup ||
+			    ((srcgroup->qgroupid >> 48) <= (objectid >> 48)))
+				*i_qgroups = 0ULL;
+
 			++i_qgroups;
 		}
 	}
@@ -1913,17 +1927,19 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 	 */
 	if (inherit) {
 		i_qgroups = (u64 *)(inherit + 1);
-		for (i = 0; i < inherit->num_qgroups; ++i) {
+		for (i = 0; i < inherit->num_qgroups; ++i, ++i_qgroups) {
+			if (*i_qgroups == 0)
+				continue;
 			ret = add_qgroup_relation_item(trans, quota_root,
 						       objectid, *i_qgroups);
-			if (ret)
+			if (ret && ret != -EEXIST)
 				goto out;
 			ret = add_qgroup_relation_item(trans, quota_root,
 						       *i_qgroups, objectid);
-			if (ret)
+			if (ret && ret != -EEXIST)
 				goto out;
-			++i_qgroups;
 		}
+		ret = 0;
 	}
 
 
@@ -1984,17 +2000,22 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 
 	i_qgroups = (u64 *)(inherit + 1);
 	for (i = 0; i < inherit->num_qgroups; ++i) {
-		ret = add_relation_rb(quota_root->fs_info, objectid,
-				      *i_qgroups);
-		if (ret)
-			goto unlock;
+		if (*i_qgroups) {
+			ret = add_relation_rb(quota_root->fs_info, objectid,
+					      *i_qgroups);
+			if (ret)
+				goto unlock;
+		}
 		++i_qgroups;
 	}
 
-	for (i = 0; i <  inherit->num_ref_copies; ++i) {
+	for (i = 0; i <  inherit->num_ref_copies; ++i, i_qgroups += 2) {
 		struct btrfs_qgroup *src;
 		struct btrfs_qgroup *dst;
 
+		if (!i_qgroups[0] || !i_qgroups[1])
+			continue;
+
 		src = find_qgroup_rb(fs_info, i_qgroups[0]);
 		dst = find_qgroup_rb(fs_info, i_qgroups[1]);
 
@@ -2005,12 +2026,14 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 
 		dst->rfer = src->rfer - level_size;
 		dst->rfer_cmpr = src->rfer_cmpr - level_size;
-		i_qgroups += 2;
 	}
-	for (i = 0; i <  inherit->num_excl_copies; ++i) {
+	for (i = 0; i <  inherit->num_excl_copies; ++i, i_qgroups += 2) {
 		struct btrfs_qgroup *src;
 		struct btrfs_qgroup *dst;
 
+		if (!i_qgroups[0] || !i_qgroups[1])
+			continue;
+
 		src = find_qgroup_rb(fs_info, i_qgroups[0]);
 		dst = find_qgroup_rb(fs_info, i_qgroups[1]);
 
@@ -2021,7 +2044,6 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 
 		dst->excl = src->excl + level_size;
 		dst->excl_cmpr = src->excl_cmpr + level_size;
-		i_qgroups += 2;
 	}
 
 unlock:
@@ -2198,7 +2220,6 @@ qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
 	int slot;
 	int ret;
 
-	path->leave_spinning = 1;
 	mutex_lock(&fs_info->qgroup_rescan_lock);
 	ret = btrfs_search_slot_for_read(fs_info->extent_root,
 					 &fs_info->qgroup_rescan_progress,
@@ -2286,7 +2307,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 		goto out;
 
 	err = 0;
-	while (!err) {
+	while (!err && !btrfs_fs_closing(fs_info)) {
 		trans = btrfs_start_transaction(fs_info->fs_root, 0);
 		if (IS_ERR(trans)) {
 			err = PTR_ERR(trans);
@@ -2307,7 +2328,8 @@ out:
 	btrfs_free_path(path);
 
 	mutex_lock(&fs_info->qgroup_rescan_lock);
-	fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN;
+	if (!btrfs_fs_closing(fs_info))
+		fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN;
 
 	if (err > 0 &&
 	    fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT) {
@@ -2336,7 +2358,9 @@ out:
 	}
 	btrfs_end_transaction(trans, fs_info->quota_root);
 
-	if (err >= 0) {
+	if (btrfs_fs_closing(fs_info)) {
+		btrfs_info(fs_info, "qgroup scan paused");
+	} else if (err >= 0) {
 		btrfs_info(fs_info, "qgroup scan completed%s",
 			err > 0 ? " (inconsistency flag cleared)" : "");
 	} else {
@@ -2384,12 +2408,11 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 	memset(&fs_info->qgroup_rescan_progress, 0,
 		sizeof(fs_info->qgroup_rescan_progress));
 	fs_info->qgroup_rescan_progress.objectid = progress_objectid;
+	init_completion(&fs_info->qgroup_rescan_completion);
 
 	spin_unlock(&fs_info->qgroup_lock);
 	mutex_unlock(&fs_info->qgroup_rescan_lock);
 
-	init_completion(&fs_info->qgroup_rescan_completion);
-
 	memset(&fs_info->qgroup_rescan_work, 0,
 	       sizeof(fs_info->qgroup_rescan_work));
 	btrfs_init_work(&fs_info->qgroup_rescan_work,
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 1a33d3eb36de..0b7792e02dd5 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -270,7 +270,7 @@ static void cache_rbio_pages(struct btrfs_raid_bio *rbio)
 		s = kmap(rbio->bio_pages[i]);
 		d = kmap(rbio->stripe_pages[i]);
 
-		memcpy(d, s, PAGE_CACHE_SIZE);
+		memcpy(d, s, PAGE_SIZE);
 
 		kunmap(rbio->bio_pages[i]);
 		kunmap(rbio->stripe_pages[i]);
@@ -503,7 +503,6 @@ static void cache_rbio(struct btrfs_raid_bio *rbio)
 	}
 
 	spin_unlock_irqrestore(&table->cache_lock, flags);
-	return;
 }
 
 /*
@@ -610,13 +609,28 @@ static int rbio_can_merge(struct btrfs_raid_bio *last,
 	return 1;
 }
 
+static int rbio_stripe_page_index(struct btrfs_raid_bio *rbio, int stripe,
+				  int index)
+{
+	return stripe * rbio->stripe_npages + index;
+}
+
+/*
+ * these are just the pages from the rbio array, not from anything
+ * the FS sent down to us
+ */
+static struct page *rbio_stripe_page(struct btrfs_raid_bio *rbio, int stripe,
+				     int index)
+{
+	return rbio->stripe_pages[rbio_stripe_page_index(rbio, stripe, index)];
+}
+
 /*
  * helper to index into the pstripe
  */
 static struct page *rbio_pstripe_page(struct btrfs_raid_bio *rbio, int index)
 {
-	index += (rbio->nr_data * rbio->stripe_len) >> PAGE_CACHE_SHIFT;
-	return rbio->stripe_pages[index];
+	return rbio_stripe_page(rbio, rbio->nr_data, index);
 }
 
 /*
@@ -627,10 +641,7 @@ static struct page *rbio_qstripe_page(struct btrfs_raid_bio *rbio, int index)
 {
 	if (rbio->nr_data + 1 == rbio->real_stripes)
 		return NULL;
-
-	index += ((rbio->nr_data + 1) * rbio->stripe_len) >>
-		PAGE_CACHE_SHIFT;
-	return rbio->stripe_pages[index];
+	return rbio_stripe_page(rbio, rbio->nr_data + 1, index);
 }
 
 /*
@@ -890,6 +901,7 @@ static void raid_write_end_io(struct bio *bio)
 {
 	struct btrfs_raid_bio *rbio = bio->bi_private;
 	int err = bio->bi_error;
+	int max_errors;
 
 	if (err)
 		fail_bio_stripe(rbio, bio);
@@ -902,11 +914,12 @@ static void raid_write_end_io(struct bio *bio)
 	err = 0;
 
 	/* OK, we have read all the stripes we need to. */
-	if (atomic_read(&rbio->error) > rbio->bbio->max_errors)
+	max_errors = (rbio->operation == BTRFS_RBIO_PARITY_SCRUB) ?
+		     0 : rbio->bbio->max_errors;
+	if (atomic_read(&rbio->error) > max_errors)
 		err = -EIO;
 
 	rbio_orig_end_io(rbio, err);
-	return;
 }
 
 /*
@@ -949,8 +962,7 @@ static struct page *page_in_rbio(struct btrfs_raid_bio *rbio,
  */
 static unsigned long rbio_nr_pages(unsigned long stripe_len, int nr_stripes)
 {
-	unsigned long nr = stripe_len * nr_stripes;
-	return DIV_ROUND_UP(nr, PAGE_CACHE_SIZE);
+	return DIV_ROUND_UP(stripe_len, PAGE_SIZE) * nr_stripes;
 }
 
 /*
@@ -968,8 +980,8 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_root *root,
 	void *p;
 
 	rbio = kzalloc(sizeof(*rbio) + num_pages * sizeof(struct page *) * 2 +
-		       DIV_ROUND_UP(stripe_npages, BITS_PER_LONG / 8),
-			GFP_NOFS);
+		       DIV_ROUND_UP(stripe_npages, BITS_PER_LONG) *
+		       sizeof(long), GFP_NOFS);
 	if (!rbio)
 		return ERR_PTR(-ENOMEM);
 
@@ -1023,18 +1035,17 @@ static int alloc_rbio_pages(struct btrfs_raid_bio *rbio)
 		if (!page)
 			return -ENOMEM;
 		rbio->stripe_pages[i] = page;
-		ClearPageUptodate(page);
 	}
 	return 0;
 }
 
-/* allocate pages for just the p/q stripes */
+/* only allocate pages for p/q stripes */
 static int alloc_rbio_parity_pages(struct btrfs_raid_bio *rbio)
 {
 	int i;
 	struct page *page;
 
-	i = (rbio->nr_data * rbio->stripe_len) >> PAGE_CACHE_SHIFT;
+	i = rbio_stripe_page_index(rbio, rbio->nr_data, 0);
 
 	for (; i < rbio->nr_pages; i++) {
 		if (rbio->stripe_pages[i])
@@ -1067,7 +1078,7 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio,
 	u64 disk_start;
 
 	stripe = &rbio->bbio->stripes[stripe_nr];
-	disk_start = stripe->physical + (page_index << PAGE_CACHE_SHIFT);
+	disk_start = stripe->physical + (page_index << PAGE_SHIFT);
 
 	/* if the device is missing, just fail this stripe */
 	if (!stripe->dev->bdev)
@@ -1085,8 +1096,8 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio,
 		if (last_end == disk_start && stripe->dev->bdev &&
 		    !last->bi_error &&
 		    last->bi_bdev == stripe->dev->bdev) {
-			ret = bio_add_page(last, page, PAGE_CACHE_SIZE, 0);
-			if (ret == PAGE_CACHE_SIZE)
+			ret = bio_add_page(last, page, PAGE_SIZE, 0);
+			if (ret == PAGE_SIZE)
 				return 0;
 		}
 	}
@@ -1100,7 +1111,7 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio,
 	bio->bi_bdev = stripe->dev->bdev;
 	bio->bi_iter.bi_sector = disk_start >> 9;
 
-	bio_add_page(bio, page, PAGE_CACHE_SIZE, 0);
+	bio_add_page(bio, page, PAGE_SIZE, 0);
 	bio_list_add(bio_list, bio);
 	return 0;
 }
@@ -1123,18 +1134,6 @@ static void validate_rbio_for_rmw(struct btrfs_raid_bio *rbio)
 }
 
 /*
- * these are just the pages from the rbio array, not from anything
- * the FS sent down to us
- */
-static struct page *rbio_stripe_page(struct btrfs_raid_bio *rbio, int stripe, int page)
-{
-	int index;
-	index = stripe * (rbio->stripe_len >> PAGE_CACHE_SHIFT);
-	index += page;
-	return rbio->stripe_pages[index];
-}
-
-/*
  * helper function to walk our bio list and populate the bio_pages array with
  * the result.  This seems expensive, but it is faster than constantly
  * searching through the bio list as we setup the IO in finish_rmw or stripe
@@ -1155,7 +1154,7 @@ static void index_rbio_pages(struct btrfs_raid_bio *rbio)
 	bio_list_for_each(bio, &rbio->bio_list) {
 		start = (u64)bio->bi_iter.bi_sector << 9;
 		stripe_offset = start - rbio->bbio->raid_map[0];
-		page_index = stripe_offset >> PAGE_CACHE_SHIFT;
+		page_index = stripe_offset >> PAGE_SHIFT;
 
 		for (i = 0; i < bio->bi_vcnt; i++) {
 			p = bio->bi_io_vec[i].bv_page;
@@ -1177,7 +1176,6 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 {
 	struct btrfs_bio *bbio = rbio->bbio;
 	void *pointers[rbio->real_stripes];
-	int stripe_len = rbio->stripe_len;
 	int nr_data = rbio->nr_data;
 	int stripe;
 	int pagenr;
@@ -1185,7 +1183,6 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 	int q_stripe = -1;
 	struct bio_list bio_list;
 	struct bio *bio;
-	int pages_per_stripe = stripe_len >> PAGE_CACHE_SHIFT;
 	int ret;
 
 	bio_list_init(&bio_list);
@@ -1228,7 +1225,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 	else
 		clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags);
 
-	for (pagenr = 0; pagenr < pages_per_stripe; pagenr++) {
+	for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
 		struct page *p;
 		/* first collect one page from each data stripe */
 		for (stripe = 0; stripe < nr_data; stripe++) {
@@ -1256,7 +1253,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 		} else {
 			/* raid5 */
 			memcpy(pointers[nr_data], pointers[0], PAGE_SIZE);
-			run_xor(pointers + 1, nr_data - 1, PAGE_CACHE_SIZE);
+			run_xor(pointers + 1, nr_data - 1, PAGE_SIZE);
 		}
 
 
@@ -1270,7 +1267,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 	 * everything else.
 	 */
 	for (stripe = 0; stripe < rbio->real_stripes; stripe++) {
-		for (pagenr = 0; pagenr < pages_per_stripe; pagenr++) {
+		for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
 			struct page *page;
 			if (stripe < rbio->nr_data) {
 				page = page_in_rbio(rbio, stripe, pagenr, 1);
@@ -1294,7 +1291,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 		if (!bbio->tgtdev_map[stripe])
 			continue;
 
-		for (pagenr = 0; pagenr < pages_per_stripe; pagenr++) {
+		for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
 			struct page *page;
 			if (stripe < rbio->nr_data) {
 				page = page_in_rbio(rbio, stripe, pagenr, 1);
@@ -1508,7 +1505,6 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio)
 	int bios_to_read = 0;
 	struct bio_list bio_list;
 	int ret;
-	int nr_pages = DIV_ROUND_UP(rbio->stripe_len, PAGE_CACHE_SIZE);
 	int pagenr;
 	int stripe;
 	struct bio *bio;
@@ -1527,7 +1523,7 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio)
 	 * stripe
 	 */
 	for (stripe = 0; stripe < rbio->nr_data; stripe++) {
-		for (pagenr = 0; pagenr < nr_pages; pagenr++) {
+		for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
 			struct page *page;
 			/*
 			 * we want to find all the pages missing from
@@ -1803,7 +1799,6 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
 	int pagenr, stripe;
 	void **pointers;
 	int faila = -1, failb = -1;
-	int nr_pages = DIV_ROUND_UP(rbio->stripe_len, PAGE_CACHE_SIZE);
 	struct page *page;
 	int err;
 	int i;
@@ -1826,7 +1821,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
 
 	index_rbio_pages(rbio);
 
-	for (pagenr = 0; pagenr < nr_pages; pagenr++) {
+	for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
 		/*
 		 * Now we just use bitmap to mark the horizontal stripes in
 		 * which we have data when doing parity scrub.
@@ -1919,7 +1914,7 @@ pstripe:
 			/* Copy parity block into failed block to start with */
 			memcpy(pointers[faila],
 			       pointers[rbio->nr_data],
-			       PAGE_CACHE_SIZE);
+			       PAGE_SIZE);
 
 			/* rearrange the pointer array */
 			p = pointers[faila];
@@ -1928,7 +1923,7 @@ pstripe:
 			pointers[rbio->nr_data - 1] = p;
 
 			/* xor in the rest */
-			run_xor(pointers, rbio->nr_data - 1, PAGE_CACHE_SIZE);
+			run_xor(pointers, rbio->nr_data - 1, PAGE_SIZE);
 		}
 		/* if we're doing this rebuild as part of an rmw, go through
 		 * and set all of our private rbio pages in the
@@ -1937,7 +1932,7 @@ pstripe:
 		 * other endio functions will fiddle the uptodate bits
 		 */
 		if (rbio->operation == BTRFS_RBIO_WRITE) {
-			for (i = 0;  i < nr_pages; i++) {
+			for (i = 0;  i < rbio->stripe_npages; i++) {
 				if (faila != -1) {
 					page = rbio_stripe_page(rbio, faila, i);
 					SetPageUptodate(page);
@@ -2033,7 +2028,6 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
 	int bios_to_read = 0;
 	struct bio_list bio_list;
 	int ret;
-	int nr_pages = DIV_ROUND_UP(rbio->stripe_len, PAGE_CACHE_SIZE);
 	int pagenr;
 	int stripe;
 	struct bio *bio;
@@ -2057,7 +2051,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
 			continue;
 		}
 
-		for (pagenr = 0; pagenr < nr_pages; pagenr++) {
+		for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
 			struct page *p;
 
 			/*
@@ -2256,7 +2250,7 @@ void raid56_add_scrub_pages(struct btrfs_raid_bio *rbio, struct page *page,
 	ASSERT(logical + PAGE_SIZE <= rbio->bbio->raid_map[0] +
 				rbio->stripe_len * rbio->nr_data);
 	stripe_offset = (int)(logical - rbio->bbio->raid_map[0]);
-	index = stripe_offset >> PAGE_CACHE_SHIFT;
+	index = stripe_offset >> PAGE_SHIFT;
 	rbio->bio_pages[index] = page;
 }
 
@@ -2281,37 +2275,11 @@ static int alloc_rbio_essential_pages(struct btrfs_raid_bio *rbio)
 			if (!page)
 				return -ENOMEM;
 			rbio->stripe_pages[index] = page;
-			ClearPageUptodate(page);
 		}
 	}
 	return 0;
 }
 
-/*
- * end io function used by finish_rmw.  When we finally
- * get here, we've written a full stripe
- */
-static void raid_write_parity_end_io(struct bio *bio)
-{
-	struct btrfs_raid_bio *rbio = bio->bi_private;
-	int err = bio->bi_error;
-
-	if (bio->bi_error)
-		fail_bio_stripe(rbio, bio);
-
-	bio_put(bio);
-
-	if (!atomic_dec_and_test(&rbio->stripes_pending))
-		return;
-
-	err = 0;
-
-	if (atomic_read(&rbio->error))
-		err = -EIO;
-
-	rbio_orig_end_io(rbio, err);
-}
-
 static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
 					 int need_check)
 {
@@ -2397,14 +2365,14 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
 		} else {
 			/* raid5 */
 			memcpy(pointers[nr_data], pointers[0], PAGE_SIZE);
-			run_xor(pointers + 1, nr_data - 1, PAGE_CACHE_SIZE);
+			run_xor(pointers + 1, nr_data - 1, PAGE_SIZE);
 		}
 
 		/* Check scrubbing pairty and repair it */
 		p = rbio_stripe_page(rbio, rbio->scrubp, pagenr);
 		parity = kmap(p);
-		if (memcmp(parity, pointers[rbio->scrubp], PAGE_CACHE_SIZE))
-			memcpy(parity, pointers[rbio->scrubp], PAGE_CACHE_SIZE);
+		if (memcmp(parity, pointers[rbio->scrubp], PAGE_SIZE))
+			memcpy(parity, pointers[rbio->scrubp], PAGE_SIZE);
 		else
 			/* Parity is right, needn't writeback */
 			bitmap_clear(rbio->dbitmap, pagenr, 1);
@@ -2464,7 +2432,7 @@ submit_write:
 			break;
 
 		bio->bi_private = rbio;
-		bio->bi_end_io = raid_write_parity_end_io;
+		bio->bi_end_io = raid_write_end_io;
 		submit_bio(WRITE, bio);
 	}
 	return;
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 619f92963e27..298631eaee78 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -72,7 +72,7 @@ struct reada_extent {
 	spinlock_t		lock;
 	struct reada_zone	*zones[BTRFS_MAX_MIRRORS];
 	int			nzones;
-	struct btrfs_device	*scheduled_for;
+	int			scheduled;
 };
 
 struct reada_zone {
@@ -101,67 +101,53 @@ static void reada_start_machine(struct btrfs_fs_info *fs_info);
 static void __reada_start_machine(struct btrfs_fs_info *fs_info);
 
 static int reada_add_block(struct reada_control *rc, u64 logical,
-			   struct btrfs_key *top, int level, u64 generation);
+			   struct btrfs_key *top, u64 generation);
 
 /* recurses */
 /* in case of err, eb might be NULL */
-static int __readahead_hook(struct btrfs_root *root, struct extent_buffer *eb,
-			    u64 start, int err)
+static void __readahead_hook(struct btrfs_fs_info *fs_info,
+			     struct reada_extent *re, struct extent_buffer *eb,
+			     u64 start, int err)
 {
 	int level = 0;
 	int nritems;
 	int i;
 	u64 bytenr;
 	u64 generation;
-	struct reada_extent *re;
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct list_head list;
-	unsigned long index = start >> PAGE_CACHE_SHIFT;
-	struct btrfs_device *for_dev;
 
 	if (eb)
 		level = btrfs_header_level(eb);
 
-	/* find extent */
-	spin_lock(&fs_info->reada_lock);
-	re = radix_tree_lookup(&fs_info->reada_tree, index);
-	if (re)
-		re->refcnt++;
-	spin_unlock(&fs_info->reada_lock);
-
-	if (!re)
-		return -1;
-
 	spin_lock(&re->lock);
 	/*
 	 * just take the full list from the extent. afterwards we
 	 * don't need the lock anymore
 	 */
 	list_replace_init(&re->extctl, &list);
-	for_dev = re->scheduled_for;
-	re->scheduled_for = NULL;
+	re->scheduled = 0;
 	spin_unlock(&re->lock);
 
-	if (err == 0) {
-		nritems = level ? btrfs_header_nritems(eb) : 0;
-		generation = btrfs_header_generation(eb);
-		/*
-		 * FIXME: currently we just set nritems to 0 if this is a leaf,
-		 * effectively ignoring the content. In a next step we could
-		 * trigger more readahead depending from the content, e.g.
-		 * fetch the checksums for the extents in the leaf.
-		 */
-	} else {
-		/*
-		 * this is the error case, the extent buffer has not been
-		 * read correctly. We won't access anything from it and
-		 * just cleanup our data structures. Effectively this will
-		 * cut the branch below this node from read ahead.
-		 */
-		nritems = 0;
-		generation = 0;
-	}
+	/*
+	 * this is the error case, the extent buffer has not been
+	 * read correctly. We won't access anything from it and
+	 * just cleanup our data structures. Effectively this will
+	 * cut the branch below this node from read ahead.
+	 */
+	if (err)
+		goto cleanup;
 
+	/*
+	 * FIXME: currently we just set nritems to 0 if this is a leaf,
+	 * effectively ignoring the content. In a next step we could
+	 * trigger more readahead depending from the content, e.g.
+	 * fetch the checksums for the extents in the leaf.
+	 */
+	if (!level)
+		goto cleanup;
+
+	nritems = btrfs_header_nritems(eb);
+	generation = btrfs_header_generation(eb);
 	for (i = 0; i < nritems; i++) {
 		struct reada_extctl *rec;
 		u64 n_gen;
@@ -188,19 +174,20 @@ static int __readahead_hook(struct btrfs_root *root, struct extent_buffer *eb,
 			 */
 #ifdef DEBUG
 			if (rec->generation != generation) {
-				btrfs_debug(root->fs_info,
-					   "generation mismatch for (%llu,%d,%llu) %llu != %llu",
-				       key.objectid, key.type, key.offset,
-				       rec->generation, generation);
+				btrfs_debug(fs_info,
+					    "generation mismatch for (%llu,%d,%llu) %llu != %llu",
+					    key.objectid, key.type, key.offset,
+					    rec->generation, generation);
 			}
 #endif
 			if (rec->generation == generation &&
 			    btrfs_comp_cpu_keys(&key, &rc->key_end) < 0 &&
 			    btrfs_comp_cpu_keys(&next_key, &rc->key_start) > 0)
-				reada_add_block(rc, bytenr, &next_key,
-						level - 1, n_gen);
+				reada_add_block(rc, bytenr, &next_key, n_gen);
 		}
 	}
+
+cleanup:
 	/*
 	 * free extctl records
 	 */
@@ -222,26 +209,37 @@ static int __readahead_hook(struct btrfs_root *root, struct extent_buffer *eb,
 
 		reada_extent_put(fs_info, re);	/* one ref for each entry */
 	}
-	reada_extent_put(fs_info, re);	/* our ref */
-	if (for_dev)
-		atomic_dec(&for_dev->reada_in_flight);
 
-	return 0;
+	return;
 }
 
 /*
  * start is passed separately in case eb in NULL, which may be the case with
  * failed I/O
  */
-int btree_readahead_hook(struct btrfs_root *root, struct extent_buffer *eb,
-			 u64 start, int err)
+int btree_readahead_hook(struct btrfs_fs_info *fs_info,
+			 struct extent_buffer *eb, u64 start, int err)
 {
-	int ret;
+	int ret = 0;
+	struct reada_extent *re;
 
-	ret = __readahead_hook(root, eb, start, err);
+	/* find extent */
+	spin_lock(&fs_info->reada_lock);
+	re = radix_tree_lookup(&fs_info->reada_tree,
+			       start >> PAGE_SHIFT);
+	if (re)
+		re->refcnt++;
+	spin_unlock(&fs_info->reada_lock);
+	if (!re) {
+		ret = -1;
+		goto start_machine;
+	}
 
-	reada_start_machine(root->fs_info);
+	__readahead_hook(fs_info, re, eb, start, err);
+	reada_extent_put(fs_info, re);	/* our ref */
 
+start_machine:
+	reada_start_machine(fs_info);
 	return ret;
 }
 
@@ -259,19 +257,15 @@ static struct reada_zone *reada_find_zone(struct btrfs_fs_info *fs_info,
 	zone = NULL;
 	spin_lock(&fs_info->reada_lock);
 	ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone,
-				     logical >> PAGE_CACHE_SHIFT, 1);
-	if (ret == 1)
+				     logical >> PAGE_SHIFT, 1);
+	if (ret == 1 && logical >= zone->start && logical <= zone->end) {
 		kref_get(&zone->refcnt);
-	spin_unlock(&fs_info->reada_lock);
-
-	if (ret == 1) {
-		if (logical >= zone->start && logical < zone->end)
-			return zone;
-		spin_lock(&fs_info->reada_lock);
-		kref_put(&zone->refcnt, reada_zone_release);
 		spin_unlock(&fs_info->reada_lock);
+		return zone;
 	}
 
+	spin_unlock(&fs_info->reada_lock);
+
 	cache = btrfs_lookup_block_group(fs_info, logical);
 	if (!cache)
 		return NULL;
@@ -280,7 +274,7 @@ static struct reada_zone *reada_find_zone(struct btrfs_fs_info *fs_info,
 	end = start + cache->key.offset - 1;
 	btrfs_put_block_group(cache);
 
-	zone = kzalloc(sizeof(*zone), GFP_NOFS);
+	zone = kzalloc(sizeof(*zone), GFP_KERNEL);
 	if (!zone)
 		return NULL;
 
@@ -300,15 +294,17 @@ static struct reada_zone *reada_find_zone(struct btrfs_fs_info *fs_info,
 
 	spin_lock(&fs_info->reada_lock);
 	ret = radix_tree_insert(&dev->reada_zones,
-				(unsigned long)(zone->end >> PAGE_CACHE_SHIFT),
+				(unsigned long)(zone->end >> PAGE_SHIFT),
 				zone);
 
 	if (ret == -EEXIST) {
 		kfree(zone);
 		ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone,
-					     logical >> PAGE_CACHE_SHIFT, 1);
-		if (ret == 1)
+					     logical >> PAGE_SHIFT, 1);
+		if (ret == 1 && logical >= zone->start && logical <= zone->end)
 			kref_get(&zone->refcnt);
+		else
+			zone = NULL;
 	}
 	spin_unlock(&fs_info->reada_lock);
 
@@ -317,7 +313,7 @@ static struct reada_zone *reada_find_zone(struct btrfs_fs_info *fs_info,
 
 static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 					      u64 logical,
-					      struct btrfs_key *top, int level)
+					      struct btrfs_key *top)
 {
 	int ret;
 	struct reada_extent *re = NULL;
@@ -330,9 +326,9 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 	u64 length;
 	int real_stripes;
 	int nzones = 0;
-	int i;
-	unsigned long index = logical >> PAGE_CACHE_SHIFT;
+	unsigned long index = logical >> PAGE_SHIFT;
 	int dev_replace_is_ongoing;
+	int have_zone = 0;
 
 	spin_lock(&fs_info->reada_lock);
 	re = radix_tree_lookup(&fs_info->reada_tree, index);
@@ -343,7 +339,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 	if (re)
 		return re;
 
-	re = kzalloc(sizeof(*re), GFP_NOFS);
+	re = kzalloc(sizeof(*re), GFP_KERNEL);
 	if (!re)
 		return NULL;
 
@@ -375,11 +371,16 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 		struct reada_zone *zone;
 
 		dev = bbio->stripes[nzones].dev;
+
+		/* cannot read ahead on missing device. */
+		 if (!dev->bdev)
+			continue;
+
 		zone = reada_find_zone(fs_info, dev, logical, bbio);
 		if (!zone)
-			break;
+			continue;
 
-		re->zones[nzones] = zone;
+		re->zones[re->nzones++] = zone;
 		spin_lock(&zone->lock);
 		if (!zone->elems)
 			kref_get(&zone->refcnt);
@@ -389,14 +390,13 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 		kref_put(&zone->refcnt, reada_zone_release);
 		spin_unlock(&fs_info->reada_lock);
 	}
-	re->nzones = nzones;
-	if (nzones == 0) {
+	if (re->nzones == 0) {
 		/* not a single zone found, error and out */
 		goto error;
 	}
 
 	/* insert extent in reada_tree + all per-device trees, all or nothing */
-	btrfs_dev_replace_lock(&fs_info->dev_replace);
+	btrfs_dev_replace_lock(&fs_info->dev_replace, 0);
 	spin_lock(&fs_info->reada_lock);
 	ret = radix_tree_insert(&fs_info->reada_tree, index, re);
 	if (ret == -EEXIST) {
@@ -404,19 +404,20 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 		BUG_ON(!re_exist);
 		re_exist->refcnt++;
 		spin_unlock(&fs_info->reada_lock);
-		btrfs_dev_replace_unlock(&fs_info->dev_replace);
+		btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
 		goto error;
 	}
 	if (ret) {
 		spin_unlock(&fs_info->reada_lock);
-		btrfs_dev_replace_unlock(&fs_info->dev_replace);
+		btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
 		goto error;
 	}
 	prev_dev = NULL;
 	dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(
 			&fs_info->dev_replace);
-	for (i = 0; i < nzones; ++i) {
-		dev = bbio->stripes[i].dev;
+	for (nzones = 0; nzones < re->nzones; ++nzones) {
+		dev = re->zones[nzones]->device;
+
 		if (dev == prev_dev) {
 			/*
 			 * in case of DUP, just add the first zone. As both
@@ -427,15 +428,9 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 			 */
 			continue;
 		}
-		if (!dev->bdev) {
-			/*
-			 * cannot read ahead on missing device, but for RAID5/6,
-			 * REQ_GET_READ_MIRRORS return 1. So don't skip missing
-			 * device for such case.
-			 */
-			if (nzones > 1)
-				continue;
-		}
+		if (!dev->bdev)
+			continue;
+
 		if (dev_replace_is_ongoing &&
 		    dev == fs_info->dev_replace.tgtdev) {
 			/*
@@ -447,8 +442,8 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 		prev_dev = dev;
 		ret = radix_tree_insert(&dev->reada_extents, index, re);
 		if (ret) {
-			while (--i >= 0) {
-				dev = bbio->stripes[i].dev;
+			while (--nzones >= 0) {
+				dev = re->zones[nzones]->device;
 				BUG_ON(dev == NULL);
 				/* ignore whether the entry was inserted */
 				radix_tree_delete(&dev->reada_extents, index);
@@ -456,21 +451,24 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 			BUG_ON(fs_info == NULL);
 			radix_tree_delete(&fs_info->reada_tree, index);
 			spin_unlock(&fs_info->reada_lock);
-			btrfs_dev_replace_unlock(&fs_info->dev_replace);
+			btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
 			goto error;
 		}
+		have_zone = 1;
 	}
 	spin_unlock(&fs_info->reada_lock);
-	btrfs_dev_replace_unlock(&fs_info->dev_replace);
+	btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
+
+	if (!have_zone)
+		goto error;
 
 	btrfs_put_bbio(bbio);
 	return re;
 
 error:
-	while (nzones) {
+	for (nzones = 0; nzones < re->nzones; ++nzones) {
 		struct reada_zone *zone;
 
-		--nzones;
 		zone = re->zones[nzones];
 		kref_get(&zone->refcnt);
 		spin_lock(&zone->lock);
@@ -497,7 +495,7 @@ static void reada_extent_put(struct btrfs_fs_info *fs_info,
 			     struct reada_extent *re)
 {
 	int i;
-	unsigned long index = re->logical >> PAGE_CACHE_SHIFT;
+	unsigned long index = re->logical >> PAGE_SHIFT;
 
 	spin_lock(&fs_info->reada_lock);
 	if (--re->refcnt) {
@@ -531,8 +529,6 @@ static void reada_extent_put(struct btrfs_fs_info *fs_info,
 		kref_put(&zone->refcnt, reada_zone_release);
 		spin_unlock(&fs_info->reada_lock);
 	}
-	if (re->scheduled_for)
-		atomic_dec(&re->scheduled_for->reada_in_flight);
 
 	kfree(re);
 }
@@ -542,7 +538,7 @@ static void reada_zone_release(struct kref *kref)
 	struct reada_zone *zone = container_of(kref, struct reada_zone, refcnt);
 
 	radix_tree_delete(&zone->device->reada_zones,
-			  zone->end >> PAGE_CACHE_SHIFT);
+			  zone->end >> PAGE_SHIFT);
 
 	kfree(zone);
 }
@@ -556,17 +552,17 @@ static void reada_control_release(struct kref *kref)
 }
 
 static int reada_add_block(struct reada_control *rc, u64 logical,
-			   struct btrfs_key *top, int level, u64 generation)
+			   struct btrfs_key *top, u64 generation)
 {
 	struct btrfs_root *root = rc->root;
 	struct reada_extent *re;
 	struct reada_extctl *rec;
 
-	re = reada_find_extent(root, logical, top, level); /* takes one ref */
+	re = reada_find_extent(root, logical, top); /* takes one ref */
 	if (!re)
 		return -1;
 
-	rec = kzalloc(sizeof(*rec), GFP_NOFS);
+	rec = kzalloc(sizeof(*rec), GFP_KERNEL);
 	if (!rec) {
 		reada_extent_put(root->fs_info, re);
 		return -ENOMEM;
@@ -591,7 +587,7 @@ static int reada_add_block(struct reada_control *rc, u64 logical,
 static void reada_peer_zones_set_lock(struct reada_zone *zone, int lock)
 {
 	int i;
-	unsigned long index = zone->end >> PAGE_CACHE_SHIFT;
+	unsigned long index = zone->end >> PAGE_SHIFT;
 
 	for (i = 0; i < zone->ndevs; ++i) {
 		struct reada_zone *peer;
@@ -626,7 +622,7 @@ static int reada_pick_zone(struct btrfs_device *dev)
 					     (void **)&zone, index, 1);
 		if (ret == 0)
 			break;
-		index = (zone->end >> PAGE_CACHE_SHIFT) + 1;
+		index = (zone->end >> PAGE_SHIFT) + 1;
 		if (zone->locked) {
 			if (zone->elems > top_locked_elems) {
 				top_locked_elems = zone->elems;
@@ -662,7 +658,6 @@ static int reada_start_machine_dev(struct btrfs_fs_info *fs_info,
 	u64 logical;
 	int ret;
 	int i;
-	int need_kick = 0;
 
 	spin_lock(&fs_info->reada_lock);
 	if (dev->reada_curr_zone == NULL) {
@@ -678,8 +673,8 @@ static int reada_start_machine_dev(struct btrfs_fs_info *fs_info,
 	 * plugging to speed things up
 	 */
 	ret = radix_tree_gang_lookup(&dev->reada_extents, (void **)&re,
-				     dev->reada_next >> PAGE_CACHE_SHIFT, 1);
-	if (ret == 0 || re->logical >= dev->reada_curr_zone->end) {
+				     dev->reada_next >> PAGE_SHIFT, 1);
+	if (ret == 0 || re->logical > dev->reada_curr_zone->end) {
 		ret = reada_pick_zone(dev);
 		if (!ret) {
 			spin_unlock(&fs_info->reada_lock);
@@ -687,7 +682,7 @@ static int reada_start_machine_dev(struct btrfs_fs_info *fs_info,
 		}
 		re = NULL;
 		ret = radix_tree_gang_lookup(&dev->reada_extents, (void **)&re,
-					dev->reada_next >> PAGE_CACHE_SHIFT, 1);
+					dev->reada_next >> PAGE_SHIFT, 1);
 	}
 	if (ret == 0) {
 		spin_unlock(&fs_info->reada_lock);
@@ -698,6 +693,15 @@ static int reada_start_machine_dev(struct btrfs_fs_info *fs_info,
 
 	spin_unlock(&fs_info->reada_lock);
 
+	spin_lock(&re->lock);
+	if (re->scheduled || list_empty(&re->extctl)) {
+		spin_unlock(&re->lock);
+		reada_extent_put(fs_info, re);
+		return 0;
+	}
+	re->scheduled = 1;
+	spin_unlock(&re->lock);
+
 	/*
 	 * find mirror num
 	 */
@@ -709,29 +713,20 @@ static int reada_start_machine_dev(struct btrfs_fs_info *fs_info,
 	}
 	logical = re->logical;
 
-	spin_lock(&re->lock);
-	if (re->scheduled_for == NULL) {
-		re->scheduled_for = dev;
-		need_kick = 1;
-	}
-	spin_unlock(&re->lock);
-
-	reada_extent_put(fs_info, re);
-
-	if (!need_kick)
-		return 0;
-
 	atomic_inc(&dev->reada_in_flight);
 	ret = reada_tree_block_flagged(fs_info->extent_root, logical,
 			mirror_num, &eb);
 	if (ret)
-		__readahead_hook(fs_info->extent_root, NULL, logical, ret);
+		__readahead_hook(fs_info, re, NULL, logical, ret);
 	else if (eb)
-		__readahead_hook(fs_info->extent_root, eb, eb->start, ret);
+		__readahead_hook(fs_info, re, eb, eb->start, ret);
 
 	if (eb)
 		free_extent_buffer(eb);
 
+	atomic_dec(&dev->reada_in_flight);
+	reada_extent_put(fs_info, re);
+
 	return 1;
 
 }
@@ -752,6 +747,8 @@ static void reada_start_machine_worker(struct btrfs_work *work)
 	set_task_ioprio(current, BTRFS_IOPRIO_READA);
 	__reada_start_machine(fs_info);
 	set_task_ioprio(current, old_ioprio);
+
+	atomic_dec(&fs_info->reada_works_cnt);
 }
 
 static void __reada_start_machine(struct btrfs_fs_info *fs_info)
@@ -783,15 +780,19 @@ static void __reada_start_machine(struct btrfs_fs_info *fs_info)
 	 * enqueue to workers to finish it. This will distribute the load to
 	 * the cores.
 	 */
-	for (i = 0; i < 2; ++i)
+	for (i = 0; i < 2; ++i) {
 		reada_start_machine(fs_info);
+		if (atomic_read(&fs_info->reada_works_cnt) >
+		    BTRFS_MAX_MIRRORS * 2)
+			break;
+	}
 }
 
 static void reada_start_machine(struct btrfs_fs_info *fs_info)
 {
 	struct reada_machine_work *rmw;
 
-	rmw = kzalloc(sizeof(*rmw), GFP_NOFS);
+	rmw = kzalloc(sizeof(*rmw), GFP_KERNEL);
 	if (!rmw) {
 		/* FIXME we cannot handle this properly right now */
 		BUG();
@@ -801,6 +802,7 @@ static void reada_start_machine(struct btrfs_fs_info *fs_info)
 	rmw->fs_info = fs_info;
 
 	btrfs_queue_work(fs_info->readahead_workers, &rmw->work);
+	atomic_inc(&fs_info->reada_works_cnt);
 }
 
 #ifdef DEBUG
@@ -836,7 +838,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all)
 				printk(KERN_CONT " curr off %llu",
 					device->reada_next - zone->start);
 			printk(KERN_CONT "\n");
-			index = (zone->end >> PAGE_CACHE_SHIFT) + 1;
+			index = (zone->end >> PAGE_SHIFT) + 1;
 		}
 		cnt = 0;
 		index = 0;
@@ -848,10 +850,9 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all)
 			if (ret == 0)
 				break;
 			printk(KERN_DEBUG
-				"  re: logical %llu size %u empty %d for %lld",
+				"  re: logical %llu size %u empty %d scheduled %d",
 				re->logical, fs_info->tree_root->nodesize,
-				list_empty(&re->extctl), re->scheduled_for ?
-				re->scheduled_for->devid : -1);
+				list_empty(&re->extctl), re->scheduled);
 
 			for (i = 0; i < re->nzones; ++i) {
 				printk(KERN_CONT " zone %llu-%llu devs",
@@ -863,7 +864,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all)
 				}
 			}
 			printk(KERN_CONT "\n");
-			index = (re->logical >> PAGE_CACHE_SHIFT) + 1;
+			index = (re->logical >> PAGE_SHIFT) + 1;
 			if (++cnt > 15)
 				break;
 		}
@@ -878,31 +879,25 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all)
 					     index, 1);
 		if (ret == 0)
 			break;
-		if (!re->scheduled_for) {
-			index = (re->logical >> PAGE_CACHE_SHIFT) + 1;
+		if (!re->scheduled) {
+			index = (re->logical >> PAGE_SHIFT) + 1;
 			continue;
 		}
 		printk(KERN_DEBUG
-			"re: logical %llu size %u list empty %d for %lld",
+			"re: logical %llu size %u list empty %d scheduled %d",
 			re->logical, fs_info->tree_root->nodesize,
-			list_empty(&re->extctl),
-			re->scheduled_for ? re->scheduled_for->devid : -1);
+			list_empty(&re->extctl), re->scheduled);
 		for (i = 0; i < re->nzones; ++i) {
 			printk(KERN_CONT " zone %llu-%llu devs",
 				re->zones[i]->start,
 				re->zones[i]->end);
-			for (i = 0; i < re->nzones; ++i) {
-				printk(KERN_CONT " zone %llu-%llu devs",
-					re->zones[i]->start,
-					re->zones[i]->end);
-				for (j = 0; j < re->zones[i]->ndevs; ++j) {
-					printk(KERN_CONT " %lld",
-						re->zones[i]->devs[j]->devid);
-				}
+			for (j = 0; j < re->zones[i]->ndevs; ++j) {
+				printk(KERN_CONT " %lld",
+				       re->zones[i]->devs[j]->devid);
 			}
 		}
 		printk(KERN_CONT "\n");
-		index = (re->logical >> PAGE_CACHE_SHIFT) + 1;
+		index = (re->logical >> PAGE_SHIFT) + 1;
 	}
 	spin_unlock(&fs_info->reada_lock);
 }
@@ -917,7 +912,6 @@ struct reada_control *btrfs_reada_add(struct btrfs_root *root,
 	struct reada_control *rc;
 	u64 start;
 	u64 generation;
-	int level;
 	int ret;
 	struct extent_buffer *node;
 	static struct btrfs_key max_key = {
@@ -926,7 +920,7 @@ struct reada_control *btrfs_reada_add(struct btrfs_root *root,
 		.offset = (u64)-1
 	};
 
-	rc = kzalloc(sizeof(*rc), GFP_NOFS);
+	rc = kzalloc(sizeof(*rc), GFP_KERNEL);
 	if (!rc)
 		return ERR_PTR(-ENOMEM);
 
@@ -940,11 +934,10 @@ struct reada_control *btrfs_reada_add(struct btrfs_root *root,
 
 	node = btrfs_root_node(root);
 	start = node->start;
-	level = btrfs_header_level(node);
 	generation = btrfs_header_generation(node);
 	free_extent_buffer(node);
 
-	ret = reada_add_block(rc, start, &max_key, level, generation);
+	ret = reada_add_block(rc, start, &max_key, generation);
 	if (ret) {
 		kfree(rc);
 		return ERR_PTR(ret);
@@ -959,8 +952,11 @@ struct reada_control *btrfs_reada_add(struct btrfs_root *root,
 int btrfs_reada_wait(void *handle)
 {
 	struct reada_control *rc = handle;
+	struct btrfs_fs_info *fs_info = rc->root->fs_info;
 
 	while (atomic_read(&rc->elems)) {
+		if (!atomic_read(&fs_info->reada_works_cnt))
+			reada_start_machine(fs_info);
 		wait_event_timeout(rc->wait, atomic_read(&rc->elems) == 0,
 				   5 * HZ);
 		dump_devs(rc->root->fs_info,
@@ -977,9 +973,13 @@ int btrfs_reada_wait(void *handle)
 int btrfs_reada_wait(void *handle)
 {
 	struct reada_control *rc = handle;
+	struct btrfs_fs_info *fs_info = rc->root->fs_info;
 
 	while (atomic_read(&rc->elems)) {
-		wait_event(rc->wait, atomic_read(&rc->elems) == 0);
+		if (!atomic_read(&fs_info->reada_works_cnt))
+			reada_start_machine(fs_info);
+		wait_event_timeout(rc->wait, atomic_read(&rc->elems) == 0,
+				   (HZ + 9) / 10);
 	}
 
 	kref_put(&rc->refcnt, reada_control_release);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index b4ca5454ef1a..08ef890deca6 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -575,7 +575,8 @@ static int is_cowonly_root(u64 root_objectid)
 	    root_objectid == BTRFS_TREE_LOG_OBJECTID ||
 	    root_objectid == BTRFS_CSUM_TREE_OBJECTID ||
 	    root_objectid == BTRFS_UUID_TREE_OBJECTID ||
-	    root_objectid == BTRFS_QUOTA_TREE_OBJECTID)
+	    root_objectid == BTRFS_QUOTA_TREE_OBJECTID ||
+	    root_objectid == BTRFS_FREE_SPACE_TREE_OBJECTID)
 		return 1;
 	return 0;
 }
@@ -708,8 +709,8 @@ struct backref_node *build_backref_tree(struct reloc_control *rc,
 		err = -ENOMEM;
 		goto out;
 	}
-	path1->reada = 1;
-	path2->reada = 2;
+	path1->reada = READA_FORWARD;
+	path2->reada = READA_FORWARD;
 
 	node = alloc_backref_node(cache);
 	if (!node) {
@@ -1849,6 +1850,7 @@ again:
 			eb = read_tree_block(dest, old_bytenr, old_ptr_gen);
 			if (IS_ERR(eb)) {
 				ret = PTR_ERR(eb);
+				break;
 			} else if (!extent_buffer_uptodate(eb)) {
 				ret = -EIO;
 				free_extent_buffer(eb);
@@ -2130,7 +2132,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
-	path->reada = 1;
+	path->reada = READA_FORWARD;
 
 	reloc_root = root->reloc_root;
 	root_item = &reloc_root->root_item;
@@ -3030,7 +3032,7 @@ int prealloc_file_extent_cluster(struct inode *inode,
 	int ret = 0;
 
 	BUG_ON(cluster->start != cluster->boundary[0]);
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	ret = btrfs_check_data_free_space(inode, cluster->start,
 					  cluster->end + 1 - cluster->start);
@@ -3057,7 +3059,7 @@ int prealloc_file_extent_cluster(struct inode *inode,
 	btrfs_free_reserved_data_space(inode, cluster->start,
 				       cluster->end + 1 - cluster->start);
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return ret;
 }
 
@@ -3128,10 +3130,10 @@ static int relocate_file_extent_cluster(struct inode *inode,
 	if (ret)
 		goto out;
 
-	index = (cluster->start - offset) >> PAGE_CACHE_SHIFT;
-	last_index = (cluster->end - offset) >> PAGE_CACHE_SHIFT;
+	index = (cluster->start - offset) >> PAGE_SHIFT;
+	last_index = (cluster->end - offset) >> PAGE_SHIFT;
 	while (index <= last_index) {
-		ret = btrfs_delalloc_reserve_metadata(inode, PAGE_CACHE_SIZE);
+		ret = btrfs_delalloc_reserve_metadata(inode, PAGE_SIZE);
 		if (ret)
 			goto out;
 
@@ -3144,7 +3146,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
 						   mask);
 			if (!page) {
 				btrfs_delalloc_release_metadata(inode,
-							PAGE_CACHE_SIZE);
+							PAGE_SIZE);
 				ret = -ENOMEM;
 				goto out;
 			}
@@ -3161,16 +3163,16 @@ static int relocate_file_extent_cluster(struct inode *inode,
 			lock_page(page);
 			if (!PageUptodate(page)) {
 				unlock_page(page);
-				page_cache_release(page);
+				put_page(page);
 				btrfs_delalloc_release_metadata(inode,
-							PAGE_CACHE_SIZE);
+							PAGE_SIZE);
 				ret = -EIO;
 				goto out;
 			}
 		}
 
 		page_start = page_offset(page);
-		page_end = page_start + PAGE_CACHE_SIZE - 1;
+		page_end = page_start + PAGE_SIZE - 1;
 
 		lock_extent(&BTRFS_I(inode)->io_tree, page_start, page_end);
 
@@ -3190,7 +3192,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
 		unlock_extent(&BTRFS_I(inode)->io_tree,
 			      page_start, page_end);
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 
 		index++;
 		balance_dirty_pages_ratelimited(inode->i_mapping);
@@ -3527,7 +3529,7 @@ static int find_data_references(struct reloc_control *rc,
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
-	path->reada = 1;
+	path->reada = READA_FORWARD;
 
 	root = read_fs_root(rc->extent_root->fs_info, ref_root);
 	if (IS_ERR(root)) {
@@ -3917,7 +3919,7 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
-	path->reada = 1;
+	path->reada = READA_FORWARD;
 
 	ret = prepare_to_relocate(rc);
 	if (ret) {
@@ -4343,7 +4345,7 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
-	path->reada = -1;
+	path->reada = READA_BACK;
 
 	key.objectid = BTRFS_TREE_RELOC_OBJECTID;
 	key.type = BTRFS_ROOT_ITEM_KEY;
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 7cf8509deda7..9fcd6dfc3266 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -310,8 +310,16 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root)
 		set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state);
 
 		err = btrfs_insert_fs_root(root->fs_info, root);
+		/*
+		 * The root might have been inserted already, as before we look
+		 * for orphan roots, log replay might have happened, which
+		 * triggers a transaction commit and qgroup accounting, which
+		 * in turn reads and inserts fs roots while doing backref
+		 * walking.
+		 */
+		if (err == -EEXIST)
+			err = 0;
 		if (err) {
-			BUG_ON(err == -EEXIST);
 			btrfs_free_fs_root(root);
 			break;
 		}
@@ -488,7 +496,7 @@ void btrfs_update_root_times(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root)
 {
 	struct btrfs_root_item *item = &root->root_item;
-	struct timespec ct = CURRENT_TIME;
+	struct timespec ct = current_fs_time(root->fs_info->sb);
 
 	spin_lock(&root->root_item_lock);
 	btrfs_set_root_ctransid(item, trans->transid);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 550de89a8661..4678f03e878e 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -248,14 +248,9 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check);
 static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
 				     struct scrub_block *sblocks_for_recheck);
 static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
-				struct scrub_block *sblock, int is_metadata,
-				int have_csum, u8 *csum, u64 generation,
-				u16 csum_size, int retry_failed_mirror);
-static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info,
-					 struct scrub_block *sblock,
-					 int is_metadata, int have_csum,
-					 const u8 *csum, u64 generation,
-					 u16 csum_size);
+				struct scrub_block *sblock,
+				int retry_failed_mirror);
+static void scrub_recheck_block_checksum(struct scrub_block *sblock);
 static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad,
 					     struct scrub_block *sblock_good);
 static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad,
@@ -466,7 +461,7 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace)
 	struct btrfs_fs_info *fs_info = dev->dev_root->fs_info;
 	int ret;
 
-	sctx = kzalloc(sizeof(*sctx), GFP_NOFS);
+	sctx = kzalloc(sizeof(*sctx), GFP_KERNEL);
 	if (!sctx)
 		goto nomem;
 	atomic_set(&sctx->refs, 1);
@@ -477,7 +472,7 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace)
 	for (i = 0; i < SCRUB_BIOS_PER_SCTX; ++i) {
 		struct scrub_bio *sbio;
 
-		sbio = kzalloc(sizeof(*sbio), GFP_NOFS);
+		sbio = kzalloc(sizeof(*sbio), GFP_KERNEL);
 		if (!sbio)
 			goto nomem;
 		sctx->bios[i] = sbio;
@@ -616,7 +611,7 @@ static void scrub_print_warning(const char *errstr, struct scrub_block *sblock)
 	u64 flags = 0;
 	u64 ref_root;
 	u32 item_size;
-	u8 ref_level;
+	u8 ref_level = 0;
 	int ret;
 
 	WARN_ON(sblock->page_count < 1);
@@ -708,7 +703,7 @@ static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx)
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 
-	index = offset >> PAGE_CACHE_SHIFT;
+	index = offset >> PAGE_SHIFT;
 
 	page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
 	if (!page) {
@@ -889,11 +884,9 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
 	struct btrfs_fs_info *fs_info;
 	u64 length;
 	u64 logical;
-	u64 generation;
 	unsigned int failed_mirror_index;
 	unsigned int is_metadata;
 	unsigned int have_csum;
-	u8 *csum;
 	struct scrub_block *sblocks_for_recheck; /* holds one for each mirror */
 	struct scrub_block *sblock_bad;
 	int ret;
@@ -918,13 +911,11 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
 	}
 	length = sblock_to_check->page_count * PAGE_SIZE;
 	logical = sblock_to_check->pagev[0]->logical;
-	generation = sblock_to_check->pagev[0]->generation;
 	BUG_ON(sblock_to_check->pagev[0]->mirror_num < 1);
 	failed_mirror_index = sblock_to_check->pagev[0]->mirror_num - 1;
 	is_metadata = !(sblock_to_check->pagev[0]->flags &
 			BTRFS_EXTENT_FLAG_DATA);
 	have_csum = sblock_to_check->pagev[0]->have_csum;
-	csum = sblock_to_check->pagev[0]->csum;
 	dev = sblock_to_check->pagev[0]->dev;
 
 	if (sctx->is_dev_replace && !is_metadata && !have_csum) {
@@ -987,8 +978,7 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
 	sblock_bad = sblocks_for_recheck + failed_mirror_index;
 
 	/* build and submit the bios for the failed mirror, check checksums */
-	scrub_recheck_block(fs_info, sblock_bad, is_metadata, have_csum,
-			    csum, generation, sctx->csum_size, 1);
+	scrub_recheck_block(fs_info, sblock_bad, 1);
 
 	if (!sblock_bad->header_error && !sblock_bad->checksum_error &&
 	    sblock_bad->no_io_error_seen) {
@@ -1101,9 +1091,7 @@ nodatasum_case:
 		sblock_other = sblocks_for_recheck + mirror_index;
 
 		/* build and submit the bios, check checksums */
-		scrub_recheck_block(fs_info, sblock_other, is_metadata,
-				    have_csum, csum, generation,
-				    sctx->csum_size, 0);
+		scrub_recheck_block(fs_info, sblock_other, 0);
 
 		if (!sblock_other->header_error &&
 		    !sblock_other->checksum_error &&
@@ -1215,9 +1203,7 @@ nodatasum_case:
 			 * is verified, but most likely the data comes out
 			 * of the page cache.
 			 */
-			scrub_recheck_block(fs_info, sblock_bad,
-					    is_metadata, have_csum, csum,
-					    generation, sctx->csum_size, 1);
+			scrub_recheck_block(fs_info, sblock_bad, 1);
 			if (!sblock_bad->header_error &&
 			    !sblock_bad->checksum_error &&
 			    sblock_bad->no_io_error_seen)
@@ -1318,6 +1304,9 @@ static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
 	struct btrfs_fs_info *fs_info = sctx->dev_root->fs_info;
 	u64 length = original_sblock->page_count * PAGE_SIZE;
 	u64 logical = original_sblock->pagev[0]->logical;
+	u64 generation = original_sblock->pagev[0]->generation;
+	u64 flags = original_sblock->pagev[0]->flags;
+	u64 have_csum = original_sblock->pagev[0]->have_csum;
 	struct scrub_recover *recover;
 	struct btrfs_bio *bbio;
 	u64 sublen;
@@ -1372,6 +1361,7 @@ static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
 
 			sblock = sblocks_for_recheck + mirror_index;
 			sblock->sctx = sctx;
+
 			page = kzalloc(sizeof(*page), GFP_NOFS);
 			if (!page) {
 leave_nomem:
@@ -1383,7 +1373,15 @@ leave_nomem:
 			}
 			scrub_page_get(page);
 			sblock->pagev[page_index] = page;
+			page->sblock = sblock;
+			page->flags = flags;
+			page->generation = generation;
 			page->logical = logical;
+			page->have_csum = have_csum;
+			if (have_csum)
+				memcpy(page->csum,
+				       original_sblock->pagev[0]->csum,
+				       sctx->csum_size);
 
 			scrub_stripe_index_and_offset(logical,
 						      bbio->map_type,
@@ -1474,15 +1472,12 @@ static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info,
  * the pages that are errored in the just handled mirror can be repaired.
  */
 static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
-				struct scrub_block *sblock, int is_metadata,
-				int have_csum, u8 *csum, u64 generation,
-				u16 csum_size, int retry_failed_mirror)
+				struct scrub_block *sblock,
+				int retry_failed_mirror)
 {
 	int page_num;
 
 	sblock->no_io_error_seen = 1;
-	sblock->header_error = 0;
-	sblock->checksum_error = 0;
 
 	for (page_num = 0; page_num < sblock->page_count; page_num++) {
 		struct bio *bio;
@@ -1518,11 +1513,7 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
 	}
 
 	if (sblock->no_io_error_seen)
-		scrub_recheck_block_checksum(fs_info, sblock, is_metadata,
-					     have_csum, csum, generation,
-					     csum_size);
-
-	return;
+		scrub_recheck_block_checksum(sblock);
 }
 
 static inline int scrub_check_fsid(u8 fsid[],
@@ -1535,61 +1526,16 @@ static inline int scrub_check_fsid(u8 fsid[],
 	return !ret;
 }
 
-static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info,
-					 struct scrub_block *sblock,
-					 int is_metadata, int have_csum,
-					 const u8 *csum, u64 generation,
-					 u16 csum_size)
+static void scrub_recheck_block_checksum(struct scrub_block *sblock)
 {
-	int page_num;
-	u8 calculated_csum[BTRFS_CSUM_SIZE];
-	u32 crc = ~(u32)0;
-	void *mapped_buffer;
-
-	WARN_ON(!sblock->pagev[0]->page);
-	if (is_metadata) {
-		struct btrfs_header *h;
-
-		mapped_buffer = kmap_atomic(sblock->pagev[0]->page);
-		h = (struct btrfs_header *)mapped_buffer;
-
-		if (sblock->pagev[0]->logical != btrfs_stack_header_bytenr(h) ||
-		    !scrub_check_fsid(h->fsid, sblock->pagev[0]) ||
-		    memcmp(h->chunk_tree_uuid, fs_info->chunk_tree_uuid,
-			   BTRFS_UUID_SIZE)) {
-			sblock->header_error = 1;
-		} else if (generation != btrfs_stack_header_generation(h)) {
-			sblock->header_error = 1;
-			sblock->generation_error = 1;
-		}
-		csum = h->csum;
-	} else {
-		if (!have_csum)
-			return;
-
-		mapped_buffer = kmap_atomic(sblock->pagev[0]->page);
-	}
-
-	for (page_num = 0;;) {
-		if (page_num == 0 && is_metadata)
-			crc = btrfs_csum_data(
-				((u8 *)mapped_buffer) + BTRFS_CSUM_SIZE,
-				crc, PAGE_SIZE - BTRFS_CSUM_SIZE);
-		else
-			crc = btrfs_csum_data(mapped_buffer, crc, PAGE_SIZE);
-
-		kunmap_atomic(mapped_buffer);
-		page_num++;
-		if (page_num >= sblock->page_count)
-			break;
-		WARN_ON(!sblock->pagev[page_num]->page);
-
-		mapped_buffer = kmap_atomic(sblock->pagev[page_num]->page);
-	}
+	sblock->header_error = 0;
+	sblock->checksum_error = 0;
+	sblock->generation_error = 0;
 
-	btrfs_csum_final(crc, calculated_csum);
-	if (memcmp(calculated_csum, csum, csum_size))
-		sblock->checksum_error = 1;
+	if (sblock->pagev[0]->flags & BTRFS_EXTENT_FLAG_DATA)
+		scrub_checksum_data(sblock);
+	else
+		scrub_checksum_tree_block(sblock);
 }
 
 static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad,
@@ -1690,7 +1636,7 @@ static int scrub_write_page_to_dev_replace(struct scrub_block *sblock,
 	if (spage->io_error) {
 		void *mapped_buffer = kmap_atomic(spage->page);
 
-		memset(mapped_buffer, 0, PAGE_CACHE_SIZE);
+		memset(mapped_buffer, 0, PAGE_SIZE);
 		flush_dcache_page(spage->page);
 		kunmap_atomic(mapped_buffer);
 	}
@@ -1708,7 +1654,7 @@ static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx,
 again:
 	if (!wr_ctx->wr_curr_bio) {
 		wr_ctx->wr_curr_bio = kzalloc(sizeof(*wr_ctx->wr_curr_bio),
-					      GFP_NOFS);
+					      GFP_KERNEL);
 		if (!wr_ctx->wr_curr_bio) {
 			mutex_unlock(&wr_ctx->wr_lock);
 			return -ENOMEM;
@@ -1725,7 +1671,8 @@ again:
 		sbio->dev = wr_ctx->tgtdev;
 		bio = sbio->bio;
 		if (!bio) {
-			bio = btrfs_io_bio_alloc(GFP_NOFS, wr_ctx->pages_per_wr_bio);
+			bio = btrfs_io_bio_alloc(GFP_KERNEL,
+					wr_ctx->pages_per_wr_bio);
 			if (!bio) {
 				mutex_unlock(&wr_ctx->wr_lock);
 				return -ENOMEM;
@@ -1833,6 +1780,18 @@ static int scrub_checksum(struct scrub_block *sblock)
 	u64 flags;
 	int ret;
 
+	/*
+	 * No need to initialize these stats currently,
+	 * because this function only use return value
+	 * instead of these stats value.
+	 *
+	 * Todo:
+	 * always use stats
+	 */
+	sblock->header_error = 0;
+	sblock->generation_error = 0;
+	sblock->checksum_error = 0;
+
 	WARN_ON(sblock->page_count < 1);
 	flags = sblock->pagev[0]->flags;
 	ret = 0;
@@ -1858,7 +1817,6 @@ static int scrub_checksum_data(struct scrub_block *sblock)
 	struct page *page;
 	void *buffer;
 	u32 crc = ~(u32)0;
-	int fail = 0;
 	u64 len;
 	int index;
 
@@ -1889,9 +1847,9 @@ static int scrub_checksum_data(struct scrub_block *sblock)
 
 	btrfs_csum_final(crc, csum);
 	if (memcmp(csum, on_disk_csum, sctx->csum_size))
-		fail = 1;
+		sblock->checksum_error = 1;
 
-	return fail;
+	return sblock->checksum_error;
 }
 
 static int scrub_checksum_tree_block(struct scrub_block *sblock)
@@ -1907,8 +1865,6 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock)
 	u64 mapped_size;
 	void *p;
 	u32 crc = ~(u32)0;
-	int fail = 0;
-	int crc_fail = 0;
 	u64 len;
 	int index;
 
@@ -1923,19 +1879,20 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock)
 	 * a) don't have an extent buffer and
 	 * b) the page is already kmapped
 	 */
-
 	if (sblock->pagev[0]->logical != btrfs_stack_header_bytenr(h))
-		++fail;
+		sblock->header_error = 1;
 
-	if (sblock->pagev[0]->generation != btrfs_stack_header_generation(h))
-		++fail;
+	if (sblock->pagev[0]->generation != btrfs_stack_header_generation(h)) {
+		sblock->header_error = 1;
+		sblock->generation_error = 1;
+	}
 
 	if (!scrub_check_fsid(h->fsid, sblock->pagev[0]))
-		++fail;
+		sblock->header_error = 1;
 
 	if (memcmp(h->chunk_tree_uuid, fs_info->chunk_tree_uuid,
 		   BTRFS_UUID_SIZE))
-		++fail;
+		sblock->header_error = 1;
 
 	len = sctx->nodesize - BTRFS_CSUM_SIZE;
 	mapped_size = PAGE_SIZE - BTRFS_CSUM_SIZE;
@@ -1960,9 +1917,9 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock)
 
 	btrfs_csum_final(crc, calculated_csum);
 	if (memcmp(calculated_csum, on_disk_csum, sctx->csum_size))
-		++crc_fail;
+		sblock->checksum_error = 1;
 
-	return fail || crc_fail;
+	return sblock->header_error || sblock->checksum_error;
 }
 
 static int scrub_checksum_super(struct scrub_block *sblock)
@@ -2120,7 +2077,8 @@ again:
 		sbio->dev = spage->dev;
 		bio = sbio->bio;
 		if (!bio) {
-			bio = btrfs_io_bio_alloc(GFP_NOFS, sctx->pages_per_rd_bio);
+			bio = btrfs_io_bio_alloc(GFP_KERNEL,
+					sctx->pages_per_rd_bio);
 			if (!bio)
 				return -ENOMEM;
 			sbio->bio = bio;
@@ -2176,39 +2134,27 @@ static void scrub_missing_raid56_worker(struct btrfs_work *work)
 {
 	struct scrub_block *sblock = container_of(work, struct scrub_block, work);
 	struct scrub_ctx *sctx = sblock->sctx;
-	struct btrfs_fs_info *fs_info = sctx->dev_root->fs_info;
-	unsigned int is_metadata;
-	unsigned int have_csum;
-	u8 *csum;
-	u64 generation;
 	u64 logical;
 	struct btrfs_device *dev;
 
-	is_metadata = !(sblock->pagev[0]->flags & BTRFS_EXTENT_FLAG_DATA);
-	have_csum = sblock->pagev[0]->have_csum;
-	csum = sblock->pagev[0]->csum;
-	generation = sblock->pagev[0]->generation;
 	logical = sblock->pagev[0]->logical;
 	dev = sblock->pagev[0]->dev;
 
-	if (sblock->no_io_error_seen) {
-		scrub_recheck_block_checksum(fs_info, sblock, is_metadata,
-					     have_csum, csum, generation,
-					     sctx->csum_size);
-	}
+	if (sblock->no_io_error_seen)
+		scrub_recheck_block_checksum(sblock);
 
 	if (!sblock->no_io_error_seen) {
 		spin_lock(&sctx->stat_lock);
 		sctx->stat.read_errors++;
 		spin_unlock(&sctx->stat_lock);
-		btrfs_err_rl_in_rcu(fs_info,
+		btrfs_err_rl_in_rcu(sctx->dev_root->fs_info,
 			"IO error rebuilding logical %llu for dev %s",
 			logical, rcu_str_deref(dev->name));
 	} else if (sblock->header_error || sblock->checksum_error) {
 		spin_lock(&sctx->stat_lock);
 		sctx->stat.uncorrectable_errors++;
 		spin_unlock(&sctx->stat_lock);
-		btrfs_err_rl_in_rcu(fs_info,
+		btrfs_err_rl_in_rcu(sctx->dev_root->fs_info,
 			"failed to rebuild valid logical %llu for dev %s",
 			logical, rcu_str_deref(dev->name));
 	} else {
@@ -2297,7 +2243,7 @@ static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
 	struct scrub_block *sblock;
 	int index;
 
-	sblock = kzalloc(sizeof(*sblock), GFP_NOFS);
+	sblock = kzalloc(sizeof(*sblock), GFP_KERNEL);
 	if (!sblock) {
 		spin_lock(&sctx->stat_lock);
 		sctx->stat.malloc_errors++;
@@ -2315,7 +2261,7 @@ static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
 		struct scrub_page *spage;
 		u64 l = min_t(u64, len, PAGE_SIZE);
 
-		spage = kzalloc(sizeof(*spage), GFP_NOFS);
+		spage = kzalloc(sizeof(*spage), GFP_KERNEL);
 		if (!spage) {
 leave_nomem:
 			spin_lock(&sctx->stat_lock);
@@ -2342,7 +2288,7 @@ leave_nomem:
 			spage->have_csum = 0;
 		}
 		sblock->page_count++;
-		spage->page = alloc_page(GFP_NOFS);
+		spage->page = alloc_page(GFP_KERNEL);
 		if (!spage->page)
 			goto leave_nomem;
 		len -= l;
@@ -2500,8 +2446,7 @@ static void scrub_block_complete(struct scrub_block *sblock)
 	}
 }
 
-static int scrub_find_csum(struct scrub_ctx *sctx, u64 logical, u64 len,
-			   u8 *csum)
+static int scrub_find_csum(struct scrub_ctx *sctx, u64 logical, u8 *csum)
 {
 	struct btrfs_ordered_sum *sum = NULL;
 	unsigned long index;
@@ -2565,7 +2510,7 @@ static int scrub_extent(struct scrub_ctx *sctx, u64 logical, u64 len,
 
 		if (flags & BTRFS_EXTENT_FLAG_DATA) {
 			/* push csums to sbio */
-			have_csum = scrub_find_csum(sctx, logical, l, csum);
+			have_csum = scrub_find_csum(sctx, logical, csum);
 			if (have_csum == 0)
 				++sctx->stat.no_csum;
 			if (sctx->is_dev_replace && !have_csum) {
@@ -2598,7 +2543,7 @@ static int scrub_pages_for_parity(struct scrub_parity *sparity,
 	struct scrub_block *sblock;
 	int index;
 
-	sblock = kzalloc(sizeof(*sblock), GFP_NOFS);
+	sblock = kzalloc(sizeof(*sblock), GFP_KERNEL);
 	if (!sblock) {
 		spin_lock(&sctx->stat_lock);
 		sctx->stat.malloc_errors++;
@@ -2618,7 +2563,7 @@ static int scrub_pages_for_parity(struct scrub_parity *sparity,
 		struct scrub_page *spage;
 		u64 l = min_t(u64, len, PAGE_SIZE);
 
-		spage = kzalloc(sizeof(*spage), GFP_NOFS);
+		spage = kzalloc(sizeof(*spage), GFP_KERNEL);
 		if (!spage) {
 leave_nomem:
 			spin_lock(&sctx->stat_lock);
@@ -2648,7 +2593,7 @@ leave_nomem:
 			spage->have_csum = 0;
 		}
 		sblock->page_count++;
-		spage->page = alloc_page(GFP_NOFS);
+		spage->page = alloc_page(GFP_KERNEL);
 		if (!spage->page)
 			goto leave_nomem;
 		len -= l;
@@ -2703,7 +2648,7 @@ static int scrub_extent_for_parity(struct scrub_parity *sparity,
 
 		if (flags & BTRFS_EXTENT_FLAG_DATA) {
 			/* push csums to sbio */
-			have_csum = scrub_find_csum(sctx, logical, l, csum);
+			have_csum = scrub_find_csum(sctx, logical, csum);
 			if (have_csum == 0)
 				goto skip;
 		}
@@ -2870,7 +2815,7 @@ out:
 
 static inline int scrub_calc_parity_bitmap_len(int nsectors)
 {
-	return DIV_ROUND_UP(nsectors, BITS_PER_LONG) * (BITS_PER_LONG / 8);
+	return DIV_ROUND_UP(nsectors, BITS_PER_LONG) * sizeof(long);
 }
 
 static void scrub_parity_get(struct scrub_parity *sparity)
@@ -3012,6 +2957,9 @@ static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx,
 			     logic_start + map->stripe_len)) {
 				btrfs_err(fs_info, "scrub: tree block %llu spanning stripes, ignored. logical=%llu",
 					  key.objectid, logic_start);
+				spin_lock(&sctx->stat_lock);
+				sctx->stat.uncorrectable_errors++;
+				spin_unlock(&sctx->stat_lock);
 				goto next;
 			}
 again:
@@ -3361,6 +3309,9 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 					   "scrub: tree block %llu spanning "
 					   "stripes, ignored. logical=%llu",
 				       key.objectid, logical);
+				spin_lock(&sctx->stat_lock);
+				sctx->stat.uncorrectable_errors++;
+				spin_unlock(&sctx->stat_lock);
 				goto next;
 			}
 
@@ -3481,7 +3432,9 @@ out:
 static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx,
 					  struct btrfs_device *scrub_dev,
 					  u64 chunk_offset, u64 length,
-					  u64 dev_offset, int is_dev_replace)
+					  u64 dev_offset,
+					  struct btrfs_block_group_cache *cache,
+					  int is_dev_replace)
 {
 	struct btrfs_mapping_tree *map_tree =
 		&sctx->dev_root->fs_info->mapping_tree;
@@ -3494,10 +3447,20 @@ static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx,
 	em = lookup_extent_mapping(&map_tree->map_tree, chunk_offset, 1);
 	read_unlock(&map_tree->map_tree.lock);
 
-	if (!em)
-		return -EINVAL;
+	if (!em) {
+		/*
+		 * Might have been an unused block group deleted by the cleaner
+		 * kthread or relocation.
+		 */
+		spin_lock(&cache->lock);
+		if (!cache->removed)
+			ret = -EINVAL;
+		spin_unlock(&cache->lock);
 
-	map = (struct map_lookup *)em->bdev;
+		return ret;
+	}
+
+	map = em->map_lookup;
 	if (em->start != chunk_offset)
 		goto out;
 
@@ -3532,6 +3495,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 	u64 length;
 	u64 chunk_offset;
 	int ret = 0;
+	int ro_set;
 	int slot;
 	struct extent_buffer *l;
 	struct btrfs_key key;
@@ -3543,7 +3507,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 	if (!path)
 		return -ENOMEM;
 
-	path->reada = 2;
+	path->reada = READA_FORWARD;
 	path->search_commit_root = 1;
 	path->skip_locking = 1;
 
@@ -3617,7 +3581,21 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		scrub_pause_on(fs_info);
 		ret = btrfs_inc_block_group_ro(root, cache);
 		scrub_pause_off(fs_info);
-		if (ret) {
+
+		if (ret == 0) {
+			ro_set = 1;
+		} else if (ret == -ENOSPC) {
+			/*
+			 * btrfs_inc_block_group_ro return -ENOSPC when it
+			 * failed in creating new chunk for metadata.
+			 * It is not a problem for scrub/replace, because
+			 * metadata are always cowed, and our scrub paused
+			 * commit_transactions.
+			 */
+			ro_set = 0;
+		} else {
+			btrfs_warn(fs_info, "failed setting block group ro, ret=%d\n",
+				   ret);
 			btrfs_put_block_group(cache);
 			break;
 		}
@@ -3626,7 +3604,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		dev_replace->cursor_left = found_key.offset;
 		dev_replace->item_needs_writeback = 1;
 		ret = scrub_chunk(sctx, scrub_dev, chunk_offset, length,
-				  found_key.offset, is_dev_replace);
+				  found_key.offset, cache, is_dev_replace);
 
 		/*
 		 * flush, submit all pending read and write bios, afterwards
@@ -3660,7 +3638,30 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 
 		scrub_pause_off(fs_info);
 
-		btrfs_dec_block_group_ro(root, cache);
+		if (ro_set)
+			btrfs_dec_block_group_ro(root, cache);
+
+		/*
+		 * We might have prevented the cleaner kthread from deleting
+		 * this block group if it was already unused because we raced
+		 * and set it to RO mode first. So add it back to the unused
+		 * list, otherwise it might not ever be deleted unless a manual
+		 * balance is triggered or it becomes used and unused again.
+		 */
+		spin_lock(&cache->lock);
+		if (!cache->removed && !cache->ro && cache->reserved == 0 &&
+		    btrfs_block_group_used(&cache->item) == 0) {
+			spin_unlock(&cache->lock);
+			spin_lock(&fs_info->unused_bgs_lock);
+			if (list_empty(&cache->bg_list)) {
+				btrfs_get_block_group(cache);
+				list_add_tail(&cache->bg_list,
+					      &fs_info->unused_bgs);
+			}
+			spin_unlock(&fs_info->unused_bgs_lock);
+		} else {
+			spin_unlock(&cache->lock);
+		}
 
 		btrfs_put_block_group(cache);
 		if (ret)
@@ -3734,27 +3735,27 @@ static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info,
 	if (fs_info->scrub_workers_refcnt == 0) {
 		if (is_dev_replace)
 			fs_info->scrub_workers =
-				btrfs_alloc_workqueue("btrfs-scrub", flags,
+				btrfs_alloc_workqueue("scrub", flags,
 						      1, 4);
 		else
 			fs_info->scrub_workers =
-				btrfs_alloc_workqueue("btrfs-scrub", flags,
+				btrfs_alloc_workqueue("scrub", flags,
 						      max_active, 4);
 		if (!fs_info->scrub_workers)
 			goto fail_scrub_workers;
 
 		fs_info->scrub_wr_completion_workers =
-			btrfs_alloc_workqueue("btrfs-scrubwrc", flags,
+			btrfs_alloc_workqueue("scrubwrc", flags,
 					      max_active, 2);
 		if (!fs_info->scrub_wr_completion_workers)
 			goto fail_scrub_wr_completion_workers;
 
 		fs_info->scrub_nocow_workers =
-			btrfs_alloc_workqueue("btrfs-scrubnc", flags, 1, 0);
+			btrfs_alloc_workqueue("scrubnc", flags, 1, 0);
 		if (!fs_info->scrub_nocow_workers)
 			goto fail_scrub_nocow_workers;
 		fs_info->scrub_parity_workers =
-			btrfs_alloc_workqueue("btrfs-scrubparity", flags,
+			btrfs_alloc_workqueue("scrubparity", flags,
 					      max_active, 2);
 		if (!fs_info->scrub_parity_workers)
 			goto fail_scrub_parity_workers;
@@ -3858,16 +3859,16 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 		return -EIO;
 	}
 
-	btrfs_dev_replace_lock(&fs_info->dev_replace);
+	btrfs_dev_replace_lock(&fs_info->dev_replace, 0);
 	if (dev->scrub_device ||
 	    (!is_dev_replace &&
 	     btrfs_dev_replace_is_ongoing(&fs_info->dev_replace))) {
-		btrfs_dev_replace_unlock(&fs_info->dev_replace);
+		btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
 		mutex_unlock(&fs_info->scrub_lock);
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 		return -EINPROGRESS;
 	}
-	btrfs_dev_replace_unlock(&fs_info->dev_replace);
+	btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
 
 	ret = scrub_workers_get(fs_info, is_dev_replace);
 	if (ret) {
@@ -4210,7 +4211,7 @@ static int check_extent_to_block(struct inode *inode, u64 start, u64 len,
 
 	io_tree = &BTRFS_I(inode)->io_tree;
 
-	lock_extent_bits(io_tree, lockstart, lockend, 0, &cached_state);
+	lock_extent_bits(io_tree, lockstart, lockend, &cached_state);
 	ordered = btrfs_lookup_ordered_range(inode, lockstart, len);
 	if (ordered) {
 		btrfs_put_ordered_extent(ordered);
@@ -4280,7 +4281,7 @@ static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root,
 		return PTR_ERR(inode);
 
 	/* Avoid truncate/dio/punch hole.. */
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	inode_dio_wait(inode);
 
 	physical_for_dev_replace = nocow_ctx->physical_for_dev_replace;
@@ -4293,8 +4294,8 @@ static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root,
 		goto out;
 	}
 
-	while (len >= PAGE_CACHE_SIZE) {
-		index = offset >> PAGE_CACHE_SHIFT;
+	while (len >= PAGE_SIZE) {
+		index = offset >> PAGE_SHIFT;
 again:
 		page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
 		if (!page) {
@@ -4325,7 +4326,7 @@ again:
 			 */
 			if (page->mapping != inode->i_mapping) {
 				unlock_page(page);
-				page_cache_release(page);
+				put_page(page);
 				goto again;
 			}
 			if (!PageUptodate(page)) {
@@ -4347,19 +4348,19 @@ again:
 			ret = err;
 next_page:
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 
 		if (ret)
 			break;
 
-		offset += PAGE_CACHE_SIZE;
-		physical_for_dev_replace += PAGE_CACHE_SIZE;
-		nocow_ctx_logical += PAGE_CACHE_SIZE;
-		len -= PAGE_CACHE_SIZE;
+		offset += PAGE_SIZE;
+		physical_for_dev_replace += PAGE_SIZE;
+		nocow_ctx_logical += PAGE_SIZE;
+		len -= PAGE_SIZE;
 	}
 	ret = COPY_COMPLETE;
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	iput(inode);
 	return ret;
 }
@@ -4389,8 +4390,8 @@ static int write_page_nocow(struct scrub_ctx *sctx,
 	bio->bi_iter.bi_size = 0;
 	bio->bi_iter.bi_sector = physical_for_dev_replace >> 9;
 	bio->bi_bdev = dev->bdev;
-	ret = bio_add_page(bio, page, PAGE_CACHE_SIZE, 0);
-	if (ret != PAGE_CACHE_SIZE) {
+	ret = bio_add_page(bio, page, PAGE_SIZE, 0);
+	if (ret != PAGE_SIZE) {
 leave_with_eio:
 		bio_put(bio);
 		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 355a458cba1a..8d358c547c59 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -34,6 +34,7 @@
 #include "disk-io.h"
 #include "btrfs_inode.h"
 #include "transaction.h"
+#include "compression.h"
 
 static int g_verbose = 0;
 
@@ -304,7 +305,7 @@ static struct fs_path *fs_path_alloc(void)
 {
 	struct fs_path *p;
 
-	p = kmalloc(sizeof(*p), GFP_NOFS);
+	p = kmalloc(sizeof(*p), GFP_KERNEL);
 	if (!p)
 		return NULL;
 	p->reversed = 0;
@@ -363,11 +364,11 @@ static int fs_path_ensure_buf(struct fs_path *p, int len)
 	 * First time the inline_buf does not suffice
 	 */
 	if (p->buf == p->inline_buf) {
-		tmp_buf = kmalloc(len, GFP_NOFS);
+		tmp_buf = kmalloc(len, GFP_KERNEL);
 		if (tmp_buf)
 			memcpy(tmp_buf, p->buf, old_buf_len);
 	} else {
-		tmp_buf = krealloc(p->buf, len, GFP_NOFS);
+		tmp_buf = krealloc(p->buf, len, GFP_KERNEL);
 	}
 	if (!tmp_buf)
 		return -ENOMEM;
@@ -995,7 +996,7 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path,
 	 * values are small.
 	 */
 	buf_len = PATH_MAX;
-	buf = kmalloc(buf_len, GFP_NOFS);
+	buf = kmalloc(buf_len, GFP_KERNEL);
 	if (!buf) {
 		ret = -ENOMEM;
 		goto out;
@@ -1042,7 +1043,7 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path,
 				buf = NULL;
 			} else {
 				char *tmp = krealloc(buf, buf_len,
-						     GFP_NOFS | __GFP_NOWARN);
+						GFP_KERNEL | __GFP_NOWARN);
 
 				if (!tmp)
 					kfree(buf);
@@ -1303,7 +1304,7 @@ static int find_extent_clone(struct send_ctx *sctx,
 	/* We only use this path under the commit sem */
 	tmp_path->need_commit_sem = 0;
 
-	backref_ctx = kmalloc(sizeof(*backref_ctx), GFP_NOFS);
+	backref_ctx = kmalloc(sizeof(*backref_ctx), GFP_KERNEL);
 	if (!backref_ctx) {
 		ret = -ENOMEM;
 		goto out;
@@ -1469,7 +1470,21 @@ static int read_symlink(struct btrfs_root *root,
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
 	if (ret < 0)
 		goto out;
-	BUG_ON(ret);
+	if (ret) {
+		/*
+		 * An empty symlink inode. Can happen in rare error paths when
+		 * creating a symlink (transaction committed before the inode
+		 * eviction handler removed the symlink inode items and a crash
+		 * happened in between or the subvol was snapshoted in between).
+		 * Print an informative message to dmesg/syslog so that the user
+		 * can delete the symlink.
+		 */
+		btrfs_err(root->fs_info,
+			  "Found empty symlink inode %llu at root %llu",
+			  ino, root->root_key.objectid);
+		ret = -EIO;
+		goto out;
+	}
 
 	ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
 			struct btrfs_file_extent_item);
@@ -1970,7 +1985,7 @@ static int name_cache_insert(struct send_ctx *sctx,
 	nce_head = radix_tree_lookup(&sctx->name_cache,
 			(unsigned long)nce->ino);
 	if (!nce_head) {
-		nce_head = kmalloc(sizeof(*nce_head), GFP_NOFS);
+		nce_head = kmalloc(sizeof(*nce_head), GFP_KERNEL);
 		if (!nce_head) {
 			kfree(nce);
 			return -ENOMEM;
@@ -2165,7 +2180,7 @@ out_cache:
 	/*
 	 * Store the result of the lookup in the name cache.
 	 */
-	nce = kmalloc(sizeof(*nce) + fs_path_len(dest) + 1, GFP_NOFS);
+	nce = kmalloc(sizeof(*nce) + fs_path_len(dest) + 1, GFP_KERNEL);
 	if (!nce) {
 		ret = -ENOMEM;
 		goto out;
@@ -2301,7 +2316,7 @@ static int send_subvol_begin(struct send_ctx *sctx)
 	if (!path)
 		return -ENOMEM;
 
-	name = kmalloc(BTRFS_PATH_NAME_MAX, GFP_NOFS);
+	name = kmalloc(BTRFS_PATH_NAME_MAX, GFP_KERNEL);
 	if (!name) {
 		btrfs_free_path(path);
 		return -ENOMEM;
@@ -2716,7 +2731,7 @@ static int __record_ref(struct list_head *head, u64 dir,
 {
 	struct recorded_ref *ref;
 
-	ref = kmalloc(sizeof(*ref), GFP_NOFS);
+	ref = kmalloc(sizeof(*ref), GFP_KERNEL);
 	if (!ref)
 		return -ENOMEM;
 
@@ -2741,7 +2756,7 @@ static int dup_ref(struct recorded_ref *ref, struct list_head *list)
 {
 	struct recorded_ref *new;
 
-	new = kmalloc(sizeof(*ref), GFP_NOFS);
+	new = kmalloc(sizeof(*ref), GFP_KERNEL);
 	if (!new)
 		return -ENOMEM;
 
@@ -2804,7 +2819,7 @@ add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino)
 	struct rb_node *parent = NULL;
 	struct orphan_dir_info *entry, *odi;
 
-	odi = kmalloc(sizeof(*odi), GFP_NOFS);
+	odi = kmalloc(sizeof(*odi), GFP_KERNEL);
 	if (!odi)
 		return ERR_PTR(-ENOMEM);
 	odi->ino = dir_ino;
@@ -2959,7 +2974,7 @@ static int add_waiting_dir_move(struct send_ctx *sctx, u64 ino, bool orphanized)
 	struct rb_node *parent = NULL;
 	struct waiting_dir_move *entry, *dm;
 
-	dm = kmalloc(sizeof(*dm), GFP_NOFS);
+	dm = kmalloc(sizeof(*dm), GFP_KERNEL);
 	if (!dm)
 		return -ENOMEM;
 	dm->ino = ino;
@@ -3026,7 +3041,7 @@ static int add_pending_dir_move(struct send_ctx *sctx,
 	int exists = 0;
 	int ret;
 
-	pm = kmalloc(sizeof(*pm), GFP_NOFS);
+	pm = kmalloc(sizeof(*pm), GFP_KERNEL);
 	if (!pm)
 		return -ENOMEM;
 	pm->parent_ino = parent_ino;
@@ -4266,7 +4281,7 @@ static int __find_xattr(int num, struct btrfs_key *di_key,
 	    strncmp(name, ctx->name, name_len) == 0) {
 		ctx->found_idx = num;
 		ctx->found_data_len = data_len;
-		ctx->found_data = kmemdup(data, data_len, GFP_NOFS);
+		ctx->found_data = kmemdup(data, data_len, GFP_KERNEL);
 		if (!ctx->found_data)
 			return -ENOMEM;
 		return 1;
@@ -4434,9 +4449,9 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len)
 	struct page *page;
 	char *addr;
 	struct btrfs_key key;
-	pgoff_t index = offset >> PAGE_CACHE_SHIFT;
+	pgoff_t index = offset >> PAGE_SHIFT;
 	pgoff_t last_index;
-	unsigned pg_offset = offset & ~PAGE_CACHE_MASK;
+	unsigned pg_offset = offset & ~PAGE_MASK;
 	ssize_t ret = 0;
 
 	key.objectid = sctx->cur_ino;
@@ -4456,7 +4471,7 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len)
 	if (len == 0)
 		goto out;
 
-	last_index = (offset + len - 1) >> PAGE_CACHE_SHIFT;
+	last_index = (offset + len - 1) >> PAGE_SHIFT;
 
 	/* initial readahead */
 	memset(&sctx->ra, 0, sizeof(struct file_ra_state));
@@ -4466,8 +4481,8 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len)
 
 	while (index <= last_index) {
 		unsigned cur_len = min_t(unsigned, len,
-					 PAGE_CACHE_SIZE - pg_offset);
-		page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
+					 PAGE_SIZE - pg_offset);
+		page = find_or_create_page(inode->i_mapping, index, GFP_KERNEL);
 		if (!page) {
 			ret = -ENOMEM;
 			break;
@@ -4478,7 +4493,7 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len)
 			lock_page(page);
 			if (!PageUptodate(page)) {
 				unlock_page(page);
-				page_cache_release(page);
+				put_page(page);
 				ret = -EIO;
 				break;
 			}
@@ -4488,7 +4503,7 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len)
 		memcpy(sctx->read_buf + ret, addr + pg_offset, cur_len);
 		kunmap(page);
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 		index++;
 		pg_offset = 0;
 		len -= cur_len;
@@ -4789,7 +4804,7 @@ static int clone_range(struct send_ctx *sctx,
 		type = btrfs_file_extent_type(leaf, ei);
 		if (type == BTRFS_FILE_EXTENT_INLINE) {
 			ext_len = btrfs_file_extent_inline_len(leaf, slot, ei);
-			ext_len = PAGE_CACHE_ALIGN(ext_len);
+			ext_len = PAGE_ALIGN(ext_len);
 		} else {
 			ext_len = btrfs_file_extent_num_bytes(leaf, ei);
 		}
@@ -4871,7 +4886,7 @@ static int send_write_or_clone(struct send_ctx *sctx,
 		 * but there may be items after this page.  Make
 		 * sure to send the whole thing
 		 */
-		len = PAGE_CACHE_ALIGN(len);
+		len = PAGE_ALIGN(len);
 	} else {
 		len = btrfs_file_extent_num_bytes(path->nodes[0], ei);
 	}
@@ -5975,7 +5990,7 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 		goto out;
 	}
 
-	sctx = kzalloc(sizeof(struct send_ctx), GFP_NOFS);
+	sctx = kzalloc(sizeof(struct send_ctx), GFP_KERNEL);
 	if (!sctx) {
 		ret = -ENOMEM;
 		goto out;
@@ -5983,7 +5998,7 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 
 	INIT_LIST_HEAD(&sctx->new_refs);
 	INIT_LIST_HEAD(&sctx->deleted_refs);
-	INIT_RADIX_TREE(&sctx->name_cache, GFP_NOFS);
+	INIT_RADIX_TREE(&sctx->name_cache, GFP_KERNEL);
 	INIT_LIST_HEAD(&sctx->name_cache_list);
 
 	sctx->flags = arg->flags;
diff --git a/fs/btrfs/send.h b/fs/btrfs/send.h
index 48d425aef05b..02e00166c4da 100644
--- a/fs/btrfs/send.h
+++ b/fs/btrfs/send.h
@@ -22,8 +22,8 @@
 #define BTRFS_SEND_STREAM_MAGIC "btrfs-stream"
 #define BTRFS_SEND_STREAM_VERSION 1
 
-#define BTRFS_SEND_BUF_SIZE (1024 * 64)
-#define BTRFS_SEND_READ_SIZE (1024 * 48)
+#define BTRFS_SEND_BUF_SIZE SZ_64K
+#define BTRFS_SEND_READ_SIZE (48 * SZ_1K)
 
 enum btrfs_tlv_type {
 	BTRFS_TLV_U8,
diff --git a/fs/btrfs/struct-funcs.c b/fs/btrfs/struct-funcs.c
index b976597b0721..e05619f241be 100644
--- a/fs/btrfs/struct-funcs.c
+++ b/fs/btrfs/struct-funcs.c
@@ -66,7 +66,7 @@ u##bits btrfs_get_token_##bits(struct extent_buffer *eb, void *ptr,	\
 									\
 	if (token && token->kaddr && token->offset <= offset &&		\
 	    token->eb == eb &&						\
-	   (token->offset + PAGE_CACHE_SIZE >= offset + size)) {	\
+	   (token->offset + PAGE_SIZE >= offset + size)) {	\
 		kaddr = token->kaddr;					\
 		p = kaddr + part_offset - token->offset;		\
 		res = get_unaligned_le##bits(p + off);			\
@@ -104,7 +104,7 @@ void btrfs_set_token_##bits(struct extent_buffer *eb,			\
 									\
 	if (token && token->kaddr && token->offset <= offset &&		\
 	    token->eb == eb &&						\
-	   (token->offset + PAGE_CACHE_SIZE >= offset + size)) {	\
+	   (token->offset + PAGE_SIZE >= offset + size)) {	\
 		kaddr = token->kaddr;					\
 		p = kaddr + part_offset - token->offset;		\
 		put_unaligned_le##bits(val, p + off);			\
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 24154e422945..00b8f37cc306 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -295,21 +295,23 @@ enum {
 	Opt_nossd, Opt_ssd_spread, Opt_thread_pool, Opt_noacl, Opt_compress,
 	Opt_compress_type, Opt_compress_force, Opt_compress_force_type,
 	Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard,
-	Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed,
-	Opt_enospc_debug, Opt_subvolrootid, Opt_defrag, Opt_inode_cache,
-	Opt_no_space_cache, Opt_recovery, Opt_skip_balance,
-	Opt_check_integrity, Opt_check_integrity_including_extent_data,
+	Opt_space_cache, Opt_space_cache_version, Opt_clear_cache,
+	Opt_user_subvol_rm_allowed, Opt_enospc_debug, Opt_subvolrootid,
+	Opt_defrag, Opt_inode_cache, Opt_no_space_cache, Opt_recovery,
+	Opt_skip_balance, Opt_check_integrity,
+	Opt_check_integrity_including_extent_data,
 	Opt_check_integrity_print_mask, Opt_fatal_errors, Opt_rescan_uuid_tree,
 	Opt_commit_interval, Opt_barrier, Opt_nodefrag, Opt_nodiscard,
 	Opt_noenospc_debug, Opt_noflushoncommit, Opt_acl, Opt_datacow,
-	Opt_datasum, Opt_treelog, Opt_noinode_cache,
+	Opt_datasum, Opt_treelog, Opt_noinode_cache, Opt_usebackuproot,
+	Opt_nologreplay, Opt_norecovery,
 #ifdef CONFIG_BTRFS_DEBUG
 	Opt_fragment_data, Opt_fragment_metadata, Opt_fragment_all,
 #endif
 	Opt_err,
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
 	{Opt_degraded, "degraded"},
 	{Opt_subvol, "subvol=%s"},
 	{Opt_subvolid, "subvolid=%s"},
@@ -334,12 +336,15 @@ static match_table_t tokens = {
 	{Opt_noacl, "noacl"},
 	{Opt_notreelog, "notreelog"},
 	{Opt_treelog, "treelog"},
+	{Opt_nologreplay, "nologreplay"},
+	{Opt_norecovery, "norecovery"},
 	{Opt_flushoncommit, "flushoncommit"},
 	{Opt_noflushoncommit, "noflushoncommit"},
 	{Opt_ratio, "metadata_ratio=%d"},
 	{Opt_discard, "discard"},
 	{Opt_nodiscard, "nodiscard"},
 	{Opt_space_cache, "space_cache"},
+	{Opt_space_cache_version, "space_cache=%s"},
 	{Opt_clear_cache, "clear_cache"},
 	{Opt_user_subvol_rm_allowed, "user_subvol_rm_allowed"},
 	{Opt_enospc_debug, "enospc_debug"},
@@ -350,7 +355,8 @@ static match_table_t tokens = {
 	{Opt_inode_cache, "inode_cache"},
 	{Opt_noinode_cache, "noinode_cache"},
 	{Opt_no_space_cache, "nospace_cache"},
-	{Opt_recovery, "recovery"},
+	{Opt_recovery, "recovery"}, /* deprecated */
+	{Opt_usebackuproot, "usebackuproot"},
 	{Opt_skip_balance, "skip_balance"},
 	{Opt_check_integrity, "check_int"},
 	{Opt_check_integrity_including_extent_data, "check_int_data"},
@@ -371,7 +377,8 @@ static match_table_t tokens = {
  * reading in a new superblock is parsed here.
  * XXX JDM: This needs to be cleaned up for remount.
  */
-int btrfs_parse_options(struct btrfs_root *root, char *options)
+int btrfs_parse_options(struct btrfs_root *root, char *options,
+			unsigned long new_flags)
 {
 	struct btrfs_fs_info *info = root->fs_info;
 	substring_t args[MAX_OPT_ARGS];
@@ -381,13 +388,22 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 	int ret = 0;
 	char *compress_type;
 	bool compress_force = false;
+	enum btrfs_compression_type saved_compress_type;
+	bool saved_compress_force;
+	int no_compress = 0;
 
 	cache_gen = btrfs_super_cache_generation(root->fs_info->super_copy);
-	if (cache_gen)
+	if (btrfs_fs_compat_ro(root->fs_info, FREE_SPACE_TREE))
+		btrfs_set_opt(info->mount_opt, FREE_SPACE_TREE);
+	else if (cache_gen)
 		btrfs_set_opt(info->mount_opt, SPACE_CACHE);
 
+	/*
+	 * Even the options are empty, we still need to do extra check
+	 * against new flags
+	 */
 	if (!options)
-		goto out;
+		goto check;
 
 	/*
 	 * strsep changes the string, duplicate it because parse_options
@@ -458,6 +474,10 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			/* Fallthrough */
 		case Opt_compress:
 		case Opt_compress_type:
+			saved_compress_type = btrfs_test_opt(root, COMPRESS) ?
+				info->compress_type : BTRFS_COMPRESS_NONE;
+			saved_compress_force =
+				btrfs_test_opt(root, FORCE_COMPRESS);
 			if (token == Opt_compress ||
 			    token == Opt_compress_force ||
 			    strcmp(args[0].from, "zlib") == 0) {
@@ -466,6 +486,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 				btrfs_set_opt(info->mount_opt, COMPRESS);
 				btrfs_clear_opt(info->mount_opt, NODATACOW);
 				btrfs_clear_opt(info->mount_opt, NODATASUM);
+				no_compress = 0;
 			} else if (strcmp(args[0].from, "lzo") == 0) {
 				compress_type = "lzo";
 				info->compress_type = BTRFS_COMPRESS_LZO;
@@ -473,25 +494,21 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 				btrfs_clear_opt(info->mount_opt, NODATACOW);
 				btrfs_clear_opt(info->mount_opt, NODATASUM);
 				btrfs_set_fs_incompat(info, COMPRESS_LZO);
+				no_compress = 0;
 			} else if (strncmp(args[0].from, "no", 2) == 0) {
 				compress_type = "no";
 				btrfs_clear_opt(info->mount_opt, COMPRESS);
 				btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
 				compress_force = false;
+				no_compress++;
 			} else {
 				ret = -EINVAL;
 				goto out;
 			}
 
 			if (compress_force) {
-				btrfs_set_and_info(root, FORCE_COMPRESS,
-						   "force %s compression",
-						   compress_type);
+				btrfs_set_opt(info->mount_opt, FORCE_COMPRESS);
 			} else {
-				if (!btrfs_test_opt(root, COMPRESS))
-					btrfs_info(root->fs_info,
-						   "btrfs: use %s compression",
-						   compress_type);
 				/*
 				 * If we remount from compress-force=xxx to
 				 * compress=xxx, we need clear FORCE_COMPRESS
@@ -500,6 +517,17 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 				 */
 				btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
 			}
+			if ((btrfs_test_opt(root, COMPRESS) &&
+			     (info->compress_type != saved_compress_type ||
+			      compress_force != saved_compress_force)) ||
+			    (!btrfs_test_opt(root, COMPRESS) &&
+			     no_compress == 1)) {
+				btrfs_info(root->fs_info,
+					   "%s %s compression",
+					   (compress_force) ? "force" : "use",
+					   compress_type);
+			}
+			compress_force = false;
 			break;
 		case Opt_ssd:
 			btrfs_set_and_info(root, SSD,
@@ -587,6 +615,11 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			btrfs_clear_and_info(root, NOTREELOG,
 					     "enabling tree log");
 			break;
+		case Opt_norecovery:
+		case Opt_nologreplay:
+			btrfs_set_and_info(root, NOLOGREPLAY,
+					   "disabling log replay at mount time");
+			break;
 		case Opt_flushoncommit:
 			btrfs_set_and_info(root, FLUSHONCOMMIT,
 					   "turning on flush-on-commit");
@@ -617,15 +650,35 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 					     "turning off discard");
 			break;
 		case Opt_space_cache:
-			btrfs_set_and_info(root, SPACE_CACHE,
-					   "enabling disk space caching");
+		case Opt_space_cache_version:
+			if (token == Opt_space_cache ||
+			    strcmp(args[0].from, "v1") == 0) {
+				btrfs_clear_opt(root->fs_info->mount_opt,
+						FREE_SPACE_TREE);
+				btrfs_set_and_info(root, SPACE_CACHE,
+						   "enabling disk space caching");
+			} else if (strcmp(args[0].from, "v2") == 0) {
+				btrfs_clear_opt(root->fs_info->mount_opt,
+						SPACE_CACHE);
+				btrfs_set_and_info(root, FREE_SPACE_TREE,
+						   "enabling free space tree");
+			} else {
+				ret = -EINVAL;
+				goto out;
+			}
 			break;
 		case Opt_rescan_uuid_tree:
 			btrfs_set_opt(info->mount_opt, RESCAN_UUID_TREE);
 			break;
 		case Opt_no_space_cache:
-			btrfs_clear_and_info(root, SPACE_CACHE,
-					     "disabling disk space caching");
+			if (btrfs_test_opt(root, SPACE_CACHE)) {
+				btrfs_clear_and_info(root, SPACE_CACHE,
+						     "disabling disk space caching");
+			}
+			if (btrfs_test_opt(root, FREE_SPACE_TREE)) {
+				btrfs_clear_and_info(root, FREE_SPACE_TREE,
+						     "disabling free space tree");
+			}
 			break;
 		case Opt_inode_cache:
 			btrfs_set_pending_and_info(info, INODE_MAP_CACHE,
@@ -657,8 +710,12 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 					     "disabling auto defrag");
 			break;
 		case Opt_recovery:
-			btrfs_info(root->fs_info, "enabling auto recovery");
-			btrfs_set_opt(info->mount_opt, RECOVERY);
+			btrfs_warn(root->fs_info,
+				   "'recovery' is deprecated, use 'usebackuproot' instead");
+		case Opt_usebackuproot:
+			btrfs_info(root->fs_info,
+				   "trying to use backup root at mount time");
+			btrfs_set_opt(info->mount_opt, USEBACKUPROOT);
 			break;
 		case Opt_skip_balance:
 			btrfs_set_opt(info->mount_opt, SKIP_BALANCE);
@@ -753,9 +810,27 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			break;
 		}
 	}
+check:
+	/*
+	 * Extra check for current option against current flag
+	 */
+	if (btrfs_test_opt(root, NOLOGREPLAY) && !(new_flags & MS_RDONLY)) {
+		btrfs_err(root->fs_info,
+			  "nologreplay must be used with ro mount option");
+		ret = -EINVAL;
+	}
 out:
+	if (btrfs_fs_compat_ro(root->fs_info, FREE_SPACE_TREE) &&
+	    !btrfs_test_opt(root, FREE_SPACE_TREE) &&
+	    !btrfs_test_opt(root, CLEAR_CACHE)) {
+		btrfs_err(root->fs_info, "cannot disable free space tree");
+		ret = -EINVAL;
+
+	}
 	if (!ret && btrfs_test_opt(root, SPACE_CACHE))
 		btrfs_info(root->fs_info, "disk space caching is enabled");
+	if (!ret && btrfs_test_opt(root, FREE_SPACE_TREE))
+		btrfs_info(root->fs_info, "using free space tree");
 	kfree(orig);
 	return ret;
 }
@@ -1154,6 +1229,8 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 		seq_puts(seq, ",ssd");
 	if (btrfs_test_opt(root, NOTREELOG))
 		seq_puts(seq, ",notreelog");
+	if (btrfs_test_opt(root, NOLOGREPLAY))
+		seq_puts(seq, ",nologreplay");
 	if (btrfs_test_opt(root, FLUSHONCOMMIT))
 		seq_puts(seq, ",flushoncommit");
 	if (btrfs_test_opt(root, DISCARD))
@@ -1162,6 +1239,8 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 		seq_puts(seq, ",noacl");
 	if (btrfs_test_opt(root, SPACE_CACHE))
 		seq_puts(seq, ",space_cache");
+	else if (btrfs_test_opt(root, FREE_SPACE_TREE))
+		seq_puts(seq, ",space_cache=v2");
 	else
 		seq_puts(seq, ",nospace_cache");
 	if (btrfs_test_opt(root, RESCAN_UUID_TREE))
@@ -1178,8 +1257,6 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 		seq_puts(seq, ",inode_cache");
 	if (btrfs_test_opt(root, SKIP_BALANCE))
 		seq_puts(seq, ",skip_balance");
-	if (btrfs_test_opt(root, RECOVERY))
-		seq_puts(seq, ",recovery");
 #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
 	if (btrfs_test_opt(root, CHECK_INTEGRITY_INCLUDING_EXTENT_DATA))
 		seq_puts(seq, ",check_int_data");
@@ -1514,9 +1591,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 		if ((flags ^ s->s_flags) & MS_RDONLY)
 			error = -EBUSY;
 	} else {
-		char b[BDEVNAME_SIZE];
-
-		strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
+		snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
 		btrfs_sb(s)->bdev_holder = fs_type;
 		error = btrfs_fill_super(s, fs_devices, data,
 					 flags & MS_SILENT ? 1 : 0);
@@ -1637,7 +1712,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 		}
 	}
 
-	ret = btrfs_parse_options(root, data);
+	ret = btrfs_parse_options(root, data, *flags);
 	if (ret) {
 		ret = -EINVAL;
 		goto restore;
@@ -1865,7 +1940,7 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
 		 * btrfs starts at an offset of at least 1MB when doing chunk
 		 * allocation.
 		 */
-		skip_space = 1024 * 1024;
+		skip_space = SZ_1M;
 
 		/* user can set the offset in fs_info->alloc_start. */
 		if (fs_info->alloc_start &&
@@ -1956,6 +2031,8 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
  * there are other factors that may change the result (like a new metadata
  * chunk).
  *
+ * If metadata is exhausted, f_bavail will be 0.
+ *
  * FIXME: not accurate for mixed block groups, total and free/used are ok,
  * available appears slightly larger.
  */
@@ -1967,11 +2044,13 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct btrfs_space_info *found;
 	u64 total_used = 0;
 	u64 total_free_data = 0;
+	u64 total_free_meta = 0;
 	int bits = dentry->d_sb->s_blocksize_bits;
 	__be32 *fsid = (__be32 *)fs_info->fsid;
 	unsigned factor = 1;
 	struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
 	int ret;
+	u64 thresh = 0;
 
 	/*
 	 * holding chunk_muext to avoid allocating new chunks, holding
@@ -1997,6 +2076,8 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 				}
 			}
 		}
+		if (found->flags & BTRFS_BLOCK_GROUP_METADATA)
+			total_free_meta += found->disk_total - found->disk_used;
 
 		total_used += found->disk_used;
 	}
@@ -2019,6 +2100,24 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail += div_u64(total_free_data, factor);
 	buf->f_bavail = buf->f_bavail >> bits;
 
+	/*
+	 * We calculate the remaining metadata space minus global reserve. If
+	 * this is (supposedly) smaller than zero, there's no space. But this
+	 * does not hold in practice, the exhausted state happens where's still
+	 * some positive delta. So we apply some guesswork and compare the
+	 * delta to a 4M threshold.  (Practically observed delta was ~2M.)
+	 *
+	 * We probably cannot calculate the exact threshold value because this
+	 * depends on the internal reservations requested by various
+	 * operations, so some operations that consume a few metadata will
+	 * succeed even if the Avail is zero. But this is better than the other
+	 * way around.
+	 */
+	thresh = 4 * 1024 * 1024;
+
+	if (total_free_meta - thresh < block_rsv->size)
+		buf->f_bavail = 0;
+
 	buf->f_type = BTRFS_SUPER_MAGIC;
 	buf->f_bsize = dentry->d_sb->s_blocksize;
 	buf->f_namelen = BTRFS_NAME_LEN;
@@ -2091,6 +2190,9 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
 			break;
 		ret = !(fs_devices->num_devices == fs_devices->total_devices);
 		break;
+	case BTRFS_IOC_GET_SUPPORTED_FEATURES:
+		ret = btrfs_ioctl_get_supported_features((void __user*)arg);
+		break;
 	}
 
 	kfree(vol);
@@ -2189,7 +2291,7 @@ static void btrfs_interface_exit(void)
 	misc_deregister(&btrfs_misc);
 }
 
-static void btrfs_print_info(void)
+static void btrfs_print_mod_info(void)
 {
 	printk(KERN_INFO "Btrfs loaded"
 #ifdef CONFIG_BTRFS_DEBUG
@@ -2225,6 +2327,9 @@ static int btrfs_run_sanity_tests(void)
 	if (ret)
 		goto out;
 	ret = btrfs_test_qgroups();
+	if (ret)
+		goto out;
+	ret = btrfs_test_free_space_tree();
 out:
 	btrfs_destroy_test_fs();
 	return ret;
@@ -2288,7 +2393,7 @@ static int __init init_btrfs_fs(void)
 
 	btrfs_init_lockdep();
 
-	btrfs_print_info();
+	btrfs_print_mod_info();
 
 	err = btrfs_run_sanity_tests();
 	if (err)
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index e0ac85949067..539e7b5e3f86 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -202,6 +202,7 @@ BTRFS_FEAT_ATTR_INCOMPAT(extended_iref, EXTENDED_IREF);
 BTRFS_FEAT_ATTR_INCOMPAT(raid56, RAID56);
 BTRFS_FEAT_ATTR_INCOMPAT(skinny_metadata, SKINNY_METADATA);
 BTRFS_FEAT_ATTR_INCOMPAT(no_holes, NO_HOLES);
+BTRFS_FEAT_ATTR_COMPAT_RO(free_space_tree, FREE_SPACE_TREE);
 
 static struct attribute *btrfs_supported_feature_attrs[] = {
 	BTRFS_FEAT_ATTR_PTR(mixed_backref),
@@ -213,6 +214,7 @@ static struct attribute *btrfs_supported_feature_attrs[] = {
 	BTRFS_FEAT_ATTR_PTR(raid56),
 	BTRFS_FEAT_ATTR_PTR(skinny_metadata),
 	BTRFS_FEAT_ATTR_PTR(no_holes),
+	BTRFS_FEAT_ATTR_PTR(free_space_tree),
 	NULL
 };
 
@@ -780,6 +782,39 @@ failure:
 	return error;
 }
 
+
+/*
+ * Change per-fs features in /sys/fs/btrfs/UUID/features to match current
+ * values in superblock. Call after any changes to incompat/compat_ro flags
+ */
+void btrfs_sysfs_feature_update(struct btrfs_fs_info *fs_info,
+		u64 bit, enum btrfs_feature_set set)
+{
+	struct btrfs_fs_devices *fs_devs;
+	struct kobject *fsid_kobj;
+	u64 features;
+	int ret;
+
+	if (!fs_info)
+		return;
+
+	features = get_features(fs_info, set);
+	ASSERT(bit & supported_feature_masks[set]);
+
+	fs_devs = fs_info->fs_devices;
+	fsid_kobj = &fs_devs->fsid_kobj;
+
+	if (!fsid_kobj->state_initialized)
+		return;
+
+	/*
+	 * FIXME: this is too heavy to update just one value, ideally we'd like
+	 * to use sysfs_update_group but some refactoring is needed first.
+	 */
+	sysfs_remove_group(fsid_kobj, &btrfs_feature_attr_group);
+	ret = sysfs_create_group(fsid_kobj, &btrfs_feature_attr_group);
+}
+
 static int btrfs_init_debugfs(void)
 {
 #ifdef CONFIG_DEBUG_FS
diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h
index 9c09522125a6..d7da1a4c2f6c 100644
--- a/fs/btrfs/sysfs.h
+++ b/fs/btrfs/sysfs.h
@@ -56,7 +56,7 @@ static struct btrfs_feature_attr btrfs_attr_##_name = {			     \
 #define BTRFS_FEAT_ATTR_COMPAT(name, feature) \
 	BTRFS_FEAT_ATTR(name, FEAT_COMPAT, BTRFS_FEATURE_COMPAT, feature)
 #define BTRFS_FEAT_ATTR_COMPAT_RO(name, feature) \
-	BTRFS_FEAT_ATTR(name, FEAT_COMPAT_RO, BTRFS_FEATURE_COMPAT, feature)
+	BTRFS_FEAT_ATTR(name, FEAT_COMPAT_RO, BTRFS_FEATURE_COMPAT_RO, feature)
 #define BTRFS_FEAT_ATTR_INCOMPAT(name, feature) \
 	BTRFS_FEAT_ATTR(name, FEAT_INCOMPAT, BTRFS_FEATURE_INCOMPAT, feature)
 
@@ -90,4 +90,7 @@ int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs,
 				struct kobject *parent);
 int btrfs_sysfs_add_device(struct btrfs_fs_devices *fs_devs);
 void btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs);
+void btrfs_sysfs_feature_update(struct btrfs_fs_info *fs_info,
+		u64 bit, enum btrfs_feature_set set);
+
 #endif /* _BTRFS_SYSFS_H_ */
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index 9626252ee6b4..f54bf450bad3 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -21,6 +21,9 @@
 #include <linux/magic.h>
 #include "btrfs-tests.h"
 #include "../ctree.h"
+#include "../free-space-cache.h"
+#include "../free-space-tree.h"
+#include "../transaction.h"
 #include "../volumes.h"
 #include "../disk-io.h"
 #include "../qgroup.h"
@@ -79,18 +82,18 @@ void btrfs_destroy_test_fs(void)
 struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(void)
 {
 	struct btrfs_fs_info *fs_info = kzalloc(sizeof(struct btrfs_fs_info),
-						GFP_NOFS);
+						GFP_KERNEL);
 
 	if (!fs_info)
 		return fs_info;
 	fs_info->fs_devices = kzalloc(sizeof(struct btrfs_fs_devices),
-				      GFP_NOFS);
+				      GFP_KERNEL);
 	if (!fs_info->fs_devices) {
 		kfree(fs_info);
 		return NULL;
 	}
 	fs_info->super_copy = kzalloc(sizeof(struct btrfs_super_block),
-				      GFP_NOFS);
+				      GFP_KERNEL);
 	if (!fs_info->super_copy) {
 		kfree(fs_info->fs_devices);
 		kfree(fs_info);
@@ -122,6 +125,9 @@ struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(void)
 	INIT_LIST_HEAD(&fs_info->tree_mod_seq_list);
 	INIT_RADIX_TREE(&fs_info->buffer_radix, GFP_ATOMIC);
 	INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC);
+	extent_io_tree_init(&fs_info->freed_extents[0], NULL);
+	extent_io_tree_init(&fs_info->freed_extents[1], NULL);
+	fs_info->pinned_extents = &fs_info->freed_extents[0];
 	return fs_info;
 }
 
@@ -131,7 +137,6 @@ static void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info)
 	void **slot;
 
 	spin_lock(&fs_info->buffer_lock);
-restart:
 	radix_tree_for_each_slot(slot, &fs_info->buffer_radix, &iter, 0) {
 		struct extent_buffer *eb;
 
@@ -141,7 +146,7 @@ restart:
 		/* Shouldn't happen but that kind of thinking creates CVE's */
 		if (radix_tree_exception(eb)) {
 			if (radix_tree_deref_retry(eb))
-				goto restart;
+				slot = radix_tree_iter_retry(&iter);
 			continue;
 		}
 		spin_unlock(&fs_info->buffer_lock);
@@ -169,3 +174,49 @@ void btrfs_free_dummy_root(struct btrfs_root *root)
 	kfree(root);
 }
 
+struct btrfs_block_group_cache *
+btrfs_alloc_dummy_block_group(unsigned long length)
+{
+	struct btrfs_block_group_cache *cache;
+
+	cache = kzalloc(sizeof(*cache), GFP_KERNEL);
+	if (!cache)
+		return NULL;
+	cache->free_space_ctl = kzalloc(sizeof(*cache->free_space_ctl),
+					GFP_KERNEL);
+	if (!cache->free_space_ctl) {
+		kfree(cache);
+		return NULL;
+	}
+
+	cache->key.objectid = 0;
+	cache->key.offset = length;
+	cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+	cache->sectorsize = 4096;
+	cache->full_stripe_len = 4096;
+
+	INIT_LIST_HEAD(&cache->list);
+	INIT_LIST_HEAD(&cache->cluster_list);
+	INIT_LIST_HEAD(&cache->bg_list);
+	btrfs_init_free_space_ctl(cache);
+	mutex_init(&cache->free_space_lock);
+
+	return cache;
+}
+
+void btrfs_free_dummy_block_group(struct btrfs_block_group_cache *cache)
+{
+	if (!cache)
+		return;
+	__btrfs_remove_free_space_cache(cache->free_space_ctl);
+	kfree(cache->free_space_ctl);
+	kfree(cache);
+}
+
+void btrfs_init_dummy_trans(struct btrfs_trans_handle *trans)
+{
+	memset(trans, 0, sizeof(*trans));
+	trans->transid = 1;
+	INIT_LIST_HEAD(&trans->qgroup_ref_list);
+	trans->type = __TRANS_DUMMY;
+}
diff --git a/fs/btrfs/tests/btrfs-tests.h b/fs/btrfs/tests/btrfs-tests.h
index fd3954224480..054b8c73c951 100644
--- a/fs/btrfs/tests/btrfs-tests.h
+++ b/fs/btrfs/tests/btrfs-tests.h
@@ -24,17 +24,23 @@
 #define test_msg(fmt, ...) pr_info("BTRFS: selftest: " fmt, ##__VA_ARGS__)
 
 struct btrfs_root;
+struct btrfs_trans_handle;
 
 int btrfs_test_free_space_cache(void);
 int btrfs_test_extent_buffer_operations(void);
 int btrfs_test_extent_io(void);
 int btrfs_test_inodes(void);
 int btrfs_test_qgroups(void);
+int btrfs_test_free_space_tree(void);
 int btrfs_init_test_fs(void);
 void btrfs_destroy_test_fs(void);
 struct inode *btrfs_new_test_inode(void);
 struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(void);
 void btrfs_free_dummy_root(struct btrfs_root *root);
+struct btrfs_block_group_cache *
+btrfs_alloc_dummy_block_group(unsigned long length);
+void btrfs_free_dummy_block_group(struct btrfs_block_group_cache *cache);
+void btrfs_init_dummy_trans(struct btrfs_trans_handle *trans);
 #else
 static inline int btrfs_test_free_space_cache(void)
 {
@@ -63,6 +69,10 @@ static inline int btrfs_test_qgroups(void)
 {
 	return 0;
 }
+static inline int btrfs_test_free_space_tree(void)
+{
+	return 0;
+}
 #endif
 
 #endif
diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c
index 9e9f2368177d..70948b13bc81 100644
--- a/fs/btrfs/tests/extent-io-tests.c
+++ b/fs/btrfs/tests/extent-io-tests.c
@@ -18,6 +18,8 @@
 
 #include <linux/pagemap.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/sizes.h>
 #include "btrfs-tests.h"
 #include "../extent_io.h"
 
@@ -30,8 +32,8 @@ static noinline int process_page_range(struct inode *inode, u64 start, u64 end,
 {
 	int ret;
 	struct page *pages[16];
-	unsigned long index = start >> PAGE_CACHE_SHIFT;
-	unsigned long end_index = end >> PAGE_CACHE_SHIFT;
+	unsigned long index = start >> PAGE_SHIFT;
+	unsigned long end_index = end >> PAGE_SHIFT;
 	unsigned long nr_pages = end_index - index + 1;
 	int i;
 	int count = 0;
@@ -47,9 +49,9 @@ static noinline int process_page_range(struct inode *inode, u64 start, u64 end,
 				count++;
 			if (flags & PROCESS_UNLOCK && PageLocked(pages[i]))
 				unlock_page(pages[i]);
-			page_cache_release(pages[i]);
+			put_page(pages[i]);
 			if (flags & PROCESS_RELEASE)
-				page_cache_release(pages[i]);
+				put_page(pages[i]);
 		}
 		nr_pages -= ret;
 		index += ret;
@@ -70,12 +72,14 @@ static int test_find_delalloc(void)
 	struct page *page;
 	struct page *locked_page = NULL;
 	unsigned long index = 0;
-	u64 total_dirty = 256 * 1024 * 1024;
-	u64 max_bytes = 128 * 1024 * 1024;
+	u64 total_dirty = SZ_256M;
+	u64 max_bytes = SZ_128M;
 	u64 start, end, test_start;
 	u64 found;
 	int ret = -EINVAL;
 
+	test_msg("Running find delalloc tests\n");
+
 	inode = btrfs_new_test_inode();
 	if (!inode) {
 		test_msg("Failed to allocate test inode\n");
@@ -89,8 +93,8 @@ static int test_find_delalloc(void)
 	 * everything to make sure our pages don't get evicted and screw up our
 	 * test.
 	 */
-	for (index = 0; index < (total_dirty >> PAGE_CACHE_SHIFT); index++) {
-		page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
+	for (index = 0; index < (total_dirty >> PAGE_SHIFT); index++) {
+		page = find_or_create_page(inode->i_mapping, index, GFP_KERNEL);
 		if (!page) {
 			test_msg("Failed to allocate test page\n");
 			ret = -ENOMEM;
@@ -100,7 +104,7 @@ static int test_find_delalloc(void)
 		if (index) {
 			unlock_page(page);
 		} else {
-			page_cache_get(page);
+			get_page(page);
 			locked_page = page;
 		}
 	}
@@ -109,7 +113,7 @@ static int test_find_delalloc(void)
 	 * |--- delalloc ---|
 	 * |---  search  ---|
 	 */
-	set_extent_delalloc(&tmp, 0, 4095, NULL, GFP_NOFS);
+	set_extent_delalloc(&tmp, 0, 4095, NULL, GFP_KERNEL);
 	start = 0;
 	end = 0;
 	found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
@@ -125,7 +129,7 @@ static int test_find_delalloc(void)
 	}
 	unlock_extent(&tmp, start, end);
 	unlock_page(locked_page);
-	page_cache_release(locked_page);
+	put_page(locked_page);
 
 	/*
 	 * Test this scenario
@@ -133,14 +137,14 @@ static int test_find_delalloc(void)
 	 * |--- delalloc ---|
 	 *           |--- search ---|
 	 */
-	test_start = 64 * 1024 * 1024;
+	test_start = SZ_64M;
 	locked_page = find_lock_page(inode->i_mapping,
-				     test_start >> PAGE_CACHE_SHIFT);
+				     test_start >> PAGE_SHIFT);
 	if (!locked_page) {
 		test_msg("Couldn't find the locked page\n");
 		goto out_bits;
 	}
-	set_extent_delalloc(&tmp, 4096, max_bytes - 1, NULL, GFP_NOFS);
+	set_extent_delalloc(&tmp, 4096, max_bytes - 1, NULL, GFP_KERNEL);
 	start = test_start;
 	end = 0;
 	found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
@@ -161,7 +165,7 @@ static int test_find_delalloc(void)
 	}
 	unlock_extent(&tmp, start, end);
 	/* locked_page was unlocked above */
-	page_cache_release(locked_page);
+	put_page(locked_page);
 
 	/*
 	 * Test this scenario
@@ -170,7 +174,7 @@ static int test_find_delalloc(void)
 	 */
 	test_start = max_bytes + 4096;
 	locked_page = find_lock_page(inode->i_mapping, test_start >>
-				     PAGE_CACHE_SHIFT);
+				     PAGE_SHIFT);
 	if (!locked_page) {
 		test_msg("Could'nt find the locked page\n");
 		goto out_bits;
@@ -195,7 +199,7 @@ static int test_find_delalloc(void)
 	 *
 	 * We are re-using our test_start from above since it works out well.
 	 */
-	set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, NULL, GFP_NOFS);
+	set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, NULL, GFP_KERNEL);
 	start = test_start;
 	end = 0;
 	found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
@@ -220,14 +224,14 @@ static int test_find_delalloc(void)
 	 * Now to test where we run into a page that is no longer dirty in the
 	 * range we want to find.
 	 */
-	page = find_get_page(inode->i_mapping, (max_bytes + (1 * 1024 * 1024))
-			     >> PAGE_CACHE_SHIFT);
+	page = find_get_page(inode->i_mapping,
+			     (max_bytes + SZ_1M) >> PAGE_SHIFT);
 	if (!page) {
 		test_msg("Couldn't find our page\n");
 		goto out_bits;
 	}
 	ClearPageDirty(page);
-	page_cache_release(page);
+	put_page(page);
 
 	/* We unlocked it in the previous test */
 	lock_page(locked_page);
@@ -235,7 +239,7 @@ static int test_find_delalloc(void)
 	end = 0;
 	/*
 	 * Currently if we fail to find dirty pages in the delalloc range we
-	 * will adjust max_bytes down to PAGE_CACHE_SIZE and then re-search.  If
+	 * will adjust max_bytes down to PAGE_SIZE and then re-search.  If
 	 * this changes at any point in the future we will need to fix this
 	 * tests expected behavior.
 	 */
@@ -245,9 +249,9 @@ static int test_find_delalloc(void)
 		test_msg("Didn't find our range\n");
 		goto out_bits;
 	}
-	if (start != test_start && end != test_start + PAGE_CACHE_SIZE - 1) {
+	if (start != test_start && end != test_start + PAGE_SIZE - 1) {
 		test_msg("Expected start %Lu end %Lu, got start %Lu end %Lu\n",
-			 test_start, test_start + PAGE_CACHE_SIZE - 1, start,
+			 test_start, test_start + PAGE_SIZE - 1, start,
 			 end);
 		goto out_bits;
 	}
@@ -258,18 +262,149 @@ static int test_find_delalloc(void)
 	}
 	ret = 0;
 out_bits:
-	clear_extent_bits(&tmp, 0, total_dirty - 1, (unsigned)-1, GFP_NOFS);
+	clear_extent_bits(&tmp, 0, total_dirty - 1, (unsigned)-1, GFP_KERNEL);
 out:
 	if (locked_page)
-		page_cache_release(locked_page);
+		put_page(locked_page);
 	process_page_range(inode, 0, total_dirty - 1,
 			   PROCESS_UNLOCK | PROCESS_RELEASE);
 	iput(inode);
 	return ret;
 }
 
+static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
+			     unsigned long len)
+{
+	unsigned long i, x;
+
+	memset(bitmap, 0, len);
+	memset_extent_buffer(eb, 0, 0, len);
+	if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
+		test_msg("Bitmap was not zeroed\n");
+		return -EINVAL;
+	}
+
+	bitmap_set(bitmap, 0, len * BITS_PER_BYTE);
+	extent_buffer_bitmap_set(eb, 0, 0, len * BITS_PER_BYTE);
+	if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
+		test_msg("Setting all bits failed\n");
+		return -EINVAL;
+	}
+
+	bitmap_clear(bitmap, 0, len * BITS_PER_BYTE);
+	extent_buffer_bitmap_clear(eb, 0, 0, len * BITS_PER_BYTE);
+	if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
+		test_msg("Clearing all bits failed\n");
+		return -EINVAL;
+	}
+
+	bitmap_set(bitmap, (PAGE_SIZE - sizeof(long) / 2) * BITS_PER_BYTE,
+		   sizeof(long) * BITS_PER_BYTE);
+	extent_buffer_bitmap_set(eb, PAGE_SIZE - sizeof(long) / 2, 0,
+				 sizeof(long) * BITS_PER_BYTE);
+	if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
+		test_msg("Setting straddling pages failed\n");
+		return -EINVAL;
+	}
+
+	bitmap_set(bitmap, 0, len * BITS_PER_BYTE);
+	bitmap_clear(bitmap,
+		     (PAGE_SIZE - sizeof(long) / 2) * BITS_PER_BYTE,
+		     sizeof(long) * BITS_PER_BYTE);
+	extent_buffer_bitmap_set(eb, 0, 0, len * BITS_PER_BYTE);
+	extent_buffer_bitmap_clear(eb, PAGE_SIZE - sizeof(long) / 2, 0,
+				   sizeof(long) * BITS_PER_BYTE);
+	if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
+		test_msg("Clearing straddling pages failed\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Generate a wonky pseudo-random bit pattern for the sake of not using
+	 * something repetitive that could miss some hypothetical off-by-n bug.
+	 */
+	x = 0;
+	for (i = 0; i < len / sizeof(long); i++) {
+		x = (0x19660dULL * (u64)x + 0x3c6ef35fULL) & 0xffffffffUL;
+		bitmap[i] = x;
+	}
+	write_extent_buffer(eb, bitmap, 0, len);
+
+	for (i = 0; i < len * BITS_PER_BYTE; i++) {
+		int bit, bit1;
+
+		bit = !!test_bit(i, bitmap);
+		bit1 = !!extent_buffer_test_bit(eb, 0, i);
+		if (bit1 != bit) {
+			test_msg("Testing bit pattern failed\n");
+			return -EINVAL;
+		}
+
+		bit1 = !!extent_buffer_test_bit(eb, i / BITS_PER_BYTE,
+						i % BITS_PER_BYTE);
+		if (bit1 != bit) {
+			test_msg("Testing bit pattern with offset failed\n");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int test_eb_bitmaps(void)
+{
+	unsigned long len = PAGE_SIZE * 4;
+	unsigned long *bitmap;
+	struct extent_buffer *eb;
+	int ret;
+
+	test_msg("Running extent buffer bitmap tests\n");
+
+	bitmap = kmalloc(len, GFP_KERNEL);
+	if (!bitmap) {
+		test_msg("Couldn't allocate test bitmap\n");
+		return -ENOMEM;
+	}
+
+	eb = __alloc_dummy_extent_buffer(NULL, 0, len);
+	if (!eb) {
+		test_msg("Couldn't allocate test extent buffer\n");
+		kfree(bitmap);
+		return -ENOMEM;
+	}
+
+	ret = __test_eb_bitmaps(bitmap, eb, len);
+	if (ret)
+		goto out;
+
+	/* Do it over again with an extent buffer which isn't page-aligned. */
+	free_extent_buffer(eb);
+	eb = __alloc_dummy_extent_buffer(NULL, PAGE_SIZE / 2, len);
+	if (!eb) {
+		test_msg("Couldn't allocate test extent buffer\n");
+		kfree(bitmap);
+		return -ENOMEM;
+	}
+
+	ret = __test_eb_bitmaps(bitmap, eb, len);
+out:
+	free_extent_buffer(eb);
+	kfree(bitmap);
+	return ret;
+}
+
 int btrfs_test_extent_io(void)
 {
-	test_msg("Running find delalloc tests\n");
-	return test_find_delalloc();
+	int ret;
+
+	test_msg("Running extent I/O tests\n");
+
+	ret = test_find_delalloc();
+	if (ret)
+		goto out;
+
+	ret = test_eb_bitmaps();
+out:
+	test_msg("Extent I/O tests finished\n");
+	return ret;
 }
diff --git a/fs/btrfs/tests/free-space-tests.c b/fs/btrfs/tests/free-space-tests.c
index c8c3d70c31ff..514247515312 100644
--- a/fs/btrfs/tests/free-space-tests.c
+++ b/fs/btrfs/tests/free-space-tests.c
@@ -22,42 +22,7 @@
 #include "../disk-io.h"
 #include "../free-space-cache.h"
 
-#define BITS_PER_BITMAP		(PAGE_CACHE_SIZE * 8)
-static struct btrfs_block_group_cache *init_test_block_group(void)
-{
-	struct btrfs_block_group_cache *cache;
-
-	cache = kzalloc(sizeof(*cache), GFP_NOFS);
-	if (!cache)
-		return NULL;
-	cache->free_space_ctl = kzalloc(sizeof(*cache->free_space_ctl),
-					GFP_NOFS);
-	if (!cache->free_space_ctl) {
-		kfree(cache);
-		return NULL;
-	}
-	cache->fs_info = btrfs_alloc_dummy_fs_info();
-	if (!cache->fs_info) {
-		kfree(cache->free_space_ctl);
-		kfree(cache);
-		return NULL;
-	}
-
-	cache->key.objectid = 0;
-	cache->key.offset = 1024 * 1024 * 1024;
-	cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
-	cache->sectorsize = 4096;
-	cache->full_stripe_len = 4096;
-
-	spin_lock_init(&cache->lock);
-	INIT_LIST_HEAD(&cache->list);
-	INIT_LIST_HEAD(&cache->cluster_list);
-	INIT_LIST_HEAD(&cache->bg_list);
-
-	btrfs_init_free_space_ctl(cache);
-
-	return cache;
-}
+#define BITS_PER_BITMAP		(PAGE_SIZE * 8)
 
 /*
  * This test just does basic sanity checking, making sure we can add an exten
@@ -71,59 +36,59 @@ static int test_extents(struct btrfs_block_group_cache *cache)
 	test_msg("Running extent only tests\n");
 
 	/* First just make sure we can remove an entire entry */
-	ret = btrfs_add_free_space(cache, 0, 4 * 1024 * 1024);
+	ret = btrfs_add_free_space(cache, 0, SZ_4M);
 	if (ret) {
 		test_msg("Error adding initial extents %d\n", ret);
 		return ret;
 	}
 
-	ret = btrfs_remove_free_space(cache, 0, 4 * 1024 * 1024);
+	ret = btrfs_remove_free_space(cache, 0, SZ_4M);
 	if (ret) {
 		test_msg("Error removing extent %d\n", ret);
 		return ret;
 	}
 
-	if (test_check_exists(cache, 0, 4 * 1024 * 1024)) {
+	if (test_check_exists(cache, 0, SZ_4M)) {
 		test_msg("Full remove left some lingering space\n");
 		return -1;
 	}
 
 	/* Ok edge and middle cases now */
-	ret = btrfs_add_free_space(cache, 0, 4 * 1024 * 1024);
+	ret = btrfs_add_free_space(cache, 0, SZ_4M);
 	if (ret) {
 		test_msg("Error adding half extent %d\n", ret);
 		return ret;
 	}
 
-	ret = btrfs_remove_free_space(cache, 3 * 1024 * 1024, 1 * 1024 * 1024);
+	ret = btrfs_remove_free_space(cache, 3 * SZ_1M, SZ_1M);
 	if (ret) {
 		test_msg("Error removing tail end %d\n", ret);
 		return ret;
 	}
 
-	ret = btrfs_remove_free_space(cache, 0, 1 * 1024 * 1024);
+	ret = btrfs_remove_free_space(cache, 0, SZ_1M);
 	if (ret) {
 		test_msg("Error removing front end %d\n", ret);
 		return ret;
 	}
 
-	ret = btrfs_remove_free_space(cache, 2 * 1024 * 1024, 4096);
+	ret = btrfs_remove_free_space(cache, SZ_2M, 4096);
 	if (ret) {
 		test_msg("Error removing middle piece %d\n", ret);
 		return ret;
 	}
 
-	if (test_check_exists(cache, 0, 1 * 1024 * 1024)) {
+	if (test_check_exists(cache, 0, SZ_1M)) {
 		test_msg("Still have space at the front\n");
 		return -1;
 	}
 
-	if (test_check_exists(cache, 2 * 1024 * 1024, 4096)) {
+	if (test_check_exists(cache, SZ_2M, 4096)) {
 		test_msg("Still have space in the middle\n");
 		return -1;
 	}
 
-	if (test_check_exists(cache, 3 * 1024 * 1024, 1 * 1024 * 1024)) {
+	if (test_check_exists(cache, 3 * SZ_1M, SZ_1M)) {
 		test_msg("Still have space at the end\n");
 		return -1;
 	}
@@ -141,30 +106,30 @@ static int test_bitmaps(struct btrfs_block_group_cache *cache)
 
 	test_msg("Running bitmap only tests\n");
 
-	ret = test_add_free_space_entry(cache, 0, 4 * 1024 * 1024, 1);
+	ret = test_add_free_space_entry(cache, 0, SZ_4M, 1);
 	if (ret) {
 		test_msg("Couldn't create a bitmap entry %d\n", ret);
 		return ret;
 	}
 
-	ret = btrfs_remove_free_space(cache, 0, 4 * 1024 * 1024);
+	ret = btrfs_remove_free_space(cache, 0, SZ_4M);
 	if (ret) {
 		test_msg("Error removing bitmap full range %d\n", ret);
 		return ret;
 	}
 
-	if (test_check_exists(cache, 0, 4 * 1024 * 1024)) {
+	if (test_check_exists(cache, 0, SZ_4M)) {
 		test_msg("Left some space in bitmap\n");
 		return -1;
 	}
 
-	ret = test_add_free_space_entry(cache, 0, 4 * 1024 * 1024, 1);
+	ret = test_add_free_space_entry(cache, 0, SZ_4M, 1);
 	if (ret) {
 		test_msg("Couldn't add to our bitmap entry %d\n", ret);
 		return ret;
 	}
 
-	ret = btrfs_remove_free_space(cache, 1 * 1024 * 1024, 2 * 1024 * 1024);
+	ret = btrfs_remove_free_space(cache, SZ_1M, SZ_2M);
 	if (ret) {
 		test_msg("Couldn't remove middle chunk %d\n", ret);
 		return ret;
@@ -177,23 +142,21 @@ static int test_bitmaps(struct btrfs_block_group_cache *cache)
 	next_bitmap_offset = (u64)(BITS_PER_BITMAP * 4096);
 
 	/* Test a bit straddling two bitmaps */
-	ret = test_add_free_space_entry(cache, next_bitmap_offset -
-				   (2 * 1024 * 1024), 4 * 1024 * 1024, 1);
+	ret = test_add_free_space_entry(cache, next_bitmap_offset - SZ_2M,
+					SZ_4M, 1);
 	if (ret) {
 		test_msg("Couldn't add space that straddles two bitmaps %d\n",
 				ret);
 		return ret;
 	}
 
-	ret = btrfs_remove_free_space(cache, next_bitmap_offset -
-				      (1 * 1024 * 1024), 2 * 1024 * 1024);
+	ret = btrfs_remove_free_space(cache, next_bitmap_offset - SZ_1M, SZ_2M);
 	if (ret) {
 		test_msg("Couldn't remove overlapping space %d\n", ret);
 		return ret;
 	}
 
-	if (test_check_exists(cache, next_bitmap_offset - (1 * 1024 * 1024),
-			 2 * 1024 * 1024)) {
+	if (test_check_exists(cache, next_bitmap_offset - SZ_1M, SZ_2M)) {
 		test_msg("Left some space when removing overlapping\n");
 		return -1;
 	}
@@ -216,43 +179,43 @@ static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache)
 	 * bitmap, but the free space completely in the extent and then
 	 * completely in the bitmap.
 	 */
-	ret = test_add_free_space_entry(cache, 4 * 1024 * 1024, 1 * 1024 * 1024, 1);
+	ret = test_add_free_space_entry(cache, SZ_4M, SZ_1M, 1);
 	if (ret) {
 		test_msg("Couldn't create bitmap entry %d\n", ret);
 		return ret;
 	}
 
-	ret = test_add_free_space_entry(cache, 0, 1 * 1024 * 1024, 0);
+	ret = test_add_free_space_entry(cache, 0, SZ_1M, 0);
 	if (ret) {
 		test_msg("Couldn't add extent entry %d\n", ret);
 		return ret;
 	}
 
-	ret = btrfs_remove_free_space(cache, 0, 1 * 1024 * 1024);
+	ret = btrfs_remove_free_space(cache, 0, SZ_1M);
 	if (ret) {
 		test_msg("Couldn't remove extent entry %d\n", ret);
 		return ret;
 	}
 
-	if (test_check_exists(cache, 0, 1 * 1024 * 1024)) {
+	if (test_check_exists(cache, 0, SZ_1M)) {
 		test_msg("Left remnants after our remove\n");
 		return -1;
 	}
 
 	/* Now to add back the extent entry and remove from the bitmap */
-	ret = test_add_free_space_entry(cache, 0, 1 * 1024 * 1024, 0);
+	ret = test_add_free_space_entry(cache, 0, SZ_1M, 0);
 	if (ret) {
 		test_msg("Couldn't re-add extent entry %d\n", ret);
 		return ret;
 	}
 
-	ret = btrfs_remove_free_space(cache, 4 * 1024 * 1024, 1 * 1024 * 1024);
+	ret = btrfs_remove_free_space(cache, SZ_4M, SZ_1M);
 	if (ret) {
 		test_msg("Couldn't remove from bitmap %d\n", ret);
 		return ret;
 	}
 
-	if (test_check_exists(cache, 4 * 1024 * 1024, 1 * 1024 * 1024)) {
+	if (test_check_exists(cache, SZ_4M, SZ_1M)) {
 		test_msg("Left remnants in the bitmap\n");
 		return -1;
 	}
@@ -261,19 +224,19 @@ static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache)
 	 * Ok so a little more evil, extent entry and bitmap at the same offset,
 	 * removing an overlapping chunk.
 	 */
-	ret = test_add_free_space_entry(cache, 1 * 1024 * 1024, 4 * 1024 * 1024, 1);
+	ret = test_add_free_space_entry(cache, SZ_1M, SZ_4M, 1);
 	if (ret) {
 		test_msg("Couldn't add to a bitmap %d\n", ret);
 		return ret;
 	}
 
-	ret = btrfs_remove_free_space(cache, 512 * 1024, 3 * 1024 * 1024);
+	ret = btrfs_remove_free_space(cache, SZ_512K, 3 * SZ_1M);
 	if (ret) {
 		test_msg("Couldn't remove overlapping space %d\n", ret);
 		return ret;
 	}
 
-	if (test_check_exists(cache, 512 * 1024, 3 * 1024 * 1024)) {
+	if (test_check_exists(cache, SZ_512K, 3 * SZ_1M)) {
 		test_msg("Left over pieces after removing overlapping\n");
 		return -1;
 	}
@@ -281,25 +244,25 @@ static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache)
 	__btrfs_remove_free_space_cache(cache->free_space_ctl);
 
 	/* Now with the extent entry offset into the bitmap */
-	ret = test_add_free_space_entry(cache, 4 * 1024 * 1024, 4 * 1024 * 1024, 1);
+	ret = test_add_free_space_entry(cache, SZ_4M, SZ_4M, 1);
 	if (ret) {
 		test_msg("Couldn't add space to the bitmap %d\n", ret);
 		return ret;
 	}
 
-	ret = test_add_free_space_entry(cache, 2 * 1024 * 1024, 2 * 1024 * 1024, 0);
+	ret = test_add_free_space_entry(cache, SZ_2M, SZ_2M, 0);
 	if (ret) {
 		test_msg("Couldn't add extent to the cache %d\n", ret);
 		return ret;
 	}
 
-	ret = btrfs_remove_free_space(cache, 3 * 1024 * 1024, 4 * 1024 * 1024);
+	ret = btrfs_remove_free_space(cache, 3 * SZ_1M, SZ_4M);
 	if (ret) {
 		test_msg("Problem removing overlapping space %d\n", ret);
 		return ret;
 	}
 
-	if (test_check_exists(cache, 3 * 1024 * 1024, 4 * 1024 * 1024)) {
+	if (test_check_exists(cache, 3 * SZ_1M, SZ_4M)) {
 		test_msg("Left something behind when removing space");
 		return -1;
 	}
@@ -315,29 +278,26 @@ static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache)
 	 *        [ del ]
 	 */
 	__btrfs_remove_free_space_cache(cache->free_space_ctl);
-	ret = test_add_free_space_entry(cache, bitmap_offset + 4 * 1024 * 1024,
-				   4 * 1024 * 1024, 1);
+	ret = test_add_free_space_entry(cache, bitmap_offset + SZ_4M, SZ_4M, 1);
 	if (ret) {
 		test_msg("Couldn't add bitmap %d\n", ret);
 		return ret;
 	}
 
-	ret = test_add_free_space_entry(cache, bitmap_offset - 1 * 1024 * 1024,
-				   5 * 1024 * 1024, 0);
+	ret = test_add_free_space_entry(cache, bitmap_offset - SZ_1M,
+					5 * SZ_1M, 0);
 	if (ret) {
 		test_msg("Couldn't add extent entry %d\n", ret);
 		return ret;
 	}
 
-	ret = btrfs_remove_free_space(cache, bitmap_offset + 1 * 1024 * 1024,
-				      5 * 1024 * 1024);
+	ret = btrfs_remove_free_space(cache, bitmap_offset + SZ_1M, 5 * SZ_1M);
 	if (ret) {
 		test_msg("Failed to free our space %d\n", ret);
 		return ret;
 	}
 
-	if (test_check_exists(cache, bitmap_offset + 1 * 1024 * 1024,
-			 5 * 1024 * 1024)) {
+	if (test_check_exists(cache, bitmap_offset + SZ_1M, 5 * SZ_1M)) {
 		test_msg("Left stuff over\n");
 		return -1;
 	}
@@ -350,19 +310,19 @@ static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache)
 	 * to return -EAGAIN back from btrfs_remove_extent, make sure this
 	 * doesn't happen.
 	 */
-	ret = test_add_free_space_entry(cache, 1 * 1024 * 1024, 2 * 1024 * 1024, 1);
+	ret = test_add_free_space_entry(cache, SZ_1M, SZ_2M, 1);
 	if (ret) {
 		test_msg("Couldn't add bitmap entry %d\n", ret);
 		return ret;
 	}
 
-	ret = test_add_free_space_entry(cache, 3 * 1024 * 1024, 1 * 1024 * 1024, 0);
+	ret = test_add_free_space_entry(cache, 3 * SZ_1M, SZ_1M, 0);
 	if (ret) {
 		test_msg("Couldn't add extent entry %d\n", ret);
 		return ret;
 	}
 
-	ret = btrfs_remove_free_space(cache, 1 * 1024 * 1024, 3 * 1024 * 1024);
+	ret = btrfs_remove_free_space(cache, SZ_1M, 3 * SZ_1M);
 	if (ret) {
 		test_msg("Error removing bitmap and extent overlapping %d\n", ret);
 		return ret;
@@ -445,9 +405,11 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	int ret;
 	u64 offset;
 	u64 max_extent_size;
-
-	bool (*use_bitmap_op)(struct btrfs_free_space_ctl *,
-			      struct btrfs_free_space *);
+	const struct btrfs_free_space_op test_free_space_ops = {
+		.recalc_thresholds = cache->free_space_ctl->op->recalc_thresholds,
+		.use_bitmap = test_use_bitmap,
+	};
+	const struct btrfs_free_space_op *orig_free_space_ops;
 
 	test_msg("Running space stealing from bitmap to extent\n");
 
@@ -469,22 +431,21 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	 * that forces use of bitmaps as soon as we have at least 1
 	 * extent entry.
 	 */
-	use_bitmap_op = cache->free_space_ctl->op->use_bitmap;
-	cache->free_space_ctl->op->use_bitmap = test_use_bitmap;
+	orig_free_space_ops = cache->free_space_ctl->op;
+	cache->free_space_ctl->op = &test_free_space_ops;
 
 	/*
 	 * Extent entry covering free space range [128Mb - 256Kb, 128Mb - 128Kb[
 	 */
-	ret = test_add_free_space_entry(cache, 128 * 1024 * 1024 - 256 * 1024,
-					128 * 1024, 0);
+	ret = test_add_free_space_entry(cache, SZ_128M - SZ_256K, SZ_128K, 0);
 	if (ret) {
 		test_msg("Couldn't add extent entry %d\n", ret);
 		return ret;
 	}
 
 	/* Bitmap entry covering free space range [128Mb + 512Kb, 256Mb[ */
-	ret = test_add_free_space_entry(cache, 128 * 1024 * 1024 + 512 * 1024,
-					128 * 1024 * 1024 - 512 * 1024, 1);
+	ret = test_add_free_space_entry(cache, SZ_128M + SZ_512K,
+					SZ_128M - SZ_512K, 1);
 	if (ret) {
 		test_msg("Couldn't add bitmap entry %d\n", ret);
 		return ret;
@@ -502,21 +463,19 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	 * [128Mb + 512Kb, 128Mb + 768Kb[
 	 */
 	ret = btrfs_remove_free_space(cache,
-				      128 * 1024 * 1024 + 768 * 1024,
-				      128 * 1024 * 1024 - 768 * 1024);
+				      SZ_128M + 768 * SZ_1K,
+				      SZ_128M - 768 * SZ_1K);
 	if (ret) {
 		test_msg("Failed to free part of bitmap space %d\n", ret);
 		return ret;
 	}
 
 	/* Confirm that only those 2 ranges are marked as free. */
-	if (!test_check_exists(cache, 128 * 1024 * 1024 - 256 * 1024,
-			       128 * 1024)) {
+	if (!test_check_exists(cache, SZ_128M - SZ_256K, SZ_128K)) {
 		test_msg("Free space range missing\n");
 		return -ENOENT;
 	}
-	if (!test_check_exists(cache, 128 * 1024 * 1024 + 512 * 1024,
-			       256 * 1024)) {
+	if (!test_check_exists(cache, SZ_128M + SZ_512K, SZ_256K)) {
 		test_msg("Free space range missing\n");
 		return -ENOENT;
 	}
@@ -525,8 +484,8 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	 * Confirm that the bitmap range [128Mb + 768Kb, 256Mb[ isn't marked
 	 * as free anymore.
 	 */
-	if (test_check_exists(cache, 128 * 1024 * 1024 + 768 * 1024,
-			      128 * 1024 * 1024 - 768 * 1024)) {
+	if (test_check_exists(cache, SZ_128M + 768 * SZ_1K,
+			      SZ_128M - 768 * SZ_1K)) {
 		test_msg("Bitmap region not removed from space cache\n");
 		return -EINVAL;
 	}
@@ -535,8 +494,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	 * Confirm that the region [128Mb + 256Kb, 128Mb + 512Kb[, which is
 	 * covered by the bitmap, isn't marked as free.
 	 */
-	if (test_check_exists(cache, 128 * 1024 * 1024 + 256 * 1024,
-			      256 * 1024)) {
+	if (test_check_exists(cache, SZ_128M + SZ_256K, SZ_256K)) {
 		test_msg("Invalid bitmap region marked as free\n");
 		return -EINVAL;
 	}
@@ -545,8 +503,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	 * Confirm that the region [128Mb, 128Mb + 256Kb[, which is covered
 	 * by the bitmap too, isn't marked as free either.
 	 */
-	if (test_check_exists(cache, 128 * 1024 * 1024,
-			      256 * 1024)) {
+	if (test_check_exists(cache, SZ_128M, SZ_256K)) {
 		test_msg("Invalid bitmap region marked as free\n");
 		return -EINVAL;
 	}
@@ -556,13 +513,13 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	 * lets make sure the free space cache marks it as free in the bitmap,
 	 * and doesn't insert a new extent entry to represent this region.
 	 */
-	ret = btrfs_add_free_space(cache, 128 * 1024 * 1024, 512 * 1024);
+	ret = btrfs_add_free_space(cache, SZ_128M, SZ_512K);
 	if (ret) {
 		test_msg("Error adding free space: %d\n", ret);
 		return ret;
 	}
 	/* Confirm the region is marked as free. */
-	if (!test_check_exists(cache, 128 * 1024 * 1024, 512 * 1024)) {
+	if (!test_check_exists(cache, SZ_128M, SZ_512K)) {
 		test_msg("Bitmap region not marked as free\n");
 		return -ENOENT;
 	}
@@ -581,8 +538,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	 * The goal is to test that the bitmap entry space stealing doesn't
 	 * steal this space region.
 	 */
-	ret = btrfs_add_free_space(cache, 128 * 1024 * 1024 + 16 * 1024 * 1024,
-				   4096);
+	ret = btrfs_add_free_space(cache, SZ_128M + SZ_16M, 4096);
 	if (ret) {
 		test_msg("Error adding free space: %d\n", ret);
 		return ret;
@@ -601,15 +557,13 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	 * expand the range covered by the existing extent entry that represents
 	 * the free space [128Mb - 256Kb, 128Mb - 128Kb[.
 	 */
-	ret = btrfs_add_free_space(cache, 128 * 1024 * 1024 - 128 * 1024,
-				   128 * 1024);
+	ret = btrfs_add_free_space(cache, SZ_128M - SZ_128K, SZ_128K);
 	if (ret) {
 		test_msg("Error adding free space: %d\n", ret);
 		return ret;
 	}
 	/* Confirm the region is marked as free. */
-	if (!test_check_exists(cache, 128 * 1024 * 1024 - 128 * 1024,
-			       128 * 1024)) {
+	if (!test_check_exists(cache, SZ_128M - SZ_128K, SZ_128K)) {
 		test_msg("Extent region not marked as free\n");
 		return -ENOENT;
 	}
@@ -637,21 +591,20 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	 * that represents the 1Mb free space, and therefore we're able to
 	 * allocate the whole free space at once.
 	 */
-	if (!test_check_exists(cache, 128 * 1024 * 1024 - 256 * 1024,
-			       1 * 1024 * 1024)) {
+	if (!test_check_exists(cache, SZ_128M - SZ_256K, SZ_1M)) {
 		test_msg("Expected region not marked as free\n");
 		return -ENOENT;
 	}
 
-	if (cache->free_space_ctl->free_space != (1 * 1024 * 1024 + 4096)) {
+	if (cache->free_space_ctl->free_space != (SZ_1M + 4096)) {
 		test_msg("Cache free space is not 1Mb + 4Kb\n");
 		return -EINVAL;
 	}
 
 	offset = btrfs_find_space_for_alloc(cache,
-					    0, 1 * 1024 * 1024, 0,
+					    0, SZ_1M, 0,
 					    &max_extent_size);
-	if (offset != (128 * 1024 * 1024 - 256 * 1024)) {
+	if (offset != (SZ_128M - SZ_256K)) {
 		test_msg("Failed to allocate 1Mb from space cache, returned offset is: %llu\n",
 			 offset);
 		return -EINVAL;
@@ -670,7 +623,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	offset = btrfs_find_space_for_alloc(cache,
 					    0, 4096, 0,
 					    &max_extent_size);
-	if (offset != (128 * 1024 * 1024 + 16 * 1024 * 1024)) {
+	if (offset != (SZ_128M + SZ_16M)) {
 		test_msg("Failed to allocate 4Kb from space cache, returned offset is: %llu\n",
 			 offset);
 		return -EINVAL;
@@ -691,16 +644,14 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	/*
 	 * Extent entry covering free space range [128Mb + 128Kb, 128Mb + 256Kb[
 	 */
-	ret = test_add_free_space_entry(cache, 128 * 1024 * 1024 + 128 * 1024,
-					128 * 1024, 0);
+	ret = test_add_free_space_entry(cache, SZ_128M + SZ_128K, SZ_128K, 0);
 	if (ret) {
 		test_msg("Couldn't add extent entry %d\n", ret);
 		return ret;
 	}
 
 	/* Bitmap entry covering free space range [0, 128Mb - 512Kb[ */
-	ret = test_add_free_space_entry(cache, 0,
-					128 * 1024 * 1024 - 512 * 1024, 1);
+	ret = test_add_free_space_entry(cache, 0, SZ_128M - SZ_512K, 1);
 	if (ret) {
 		test_msg("Couldn't add bitmap entry %d\n", ret);
 		return ret;
@@ -717,22 +668,18 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	 * [128Mb + 128b, 128Mb + 256Kb[
 	 * [128Mb - 768Kb, 128Mb - 512Kb[
 	 */
-	ret = btrfs_remove_free_space(cache,
-				      0,
-				      128 * 1024 * 1024 - 768 * 1024);
+	ret = btrfs_remove_free_space(cache, 0, SZ_128M - 768 * SZ_1K);
 	if (ret) {
 		test_msg("Failed to free part of bitmap space %d\n", ret);
 		return ret;
 	}
 
 	/* Confirm that only those 2 ranges are marked as free. */
-	if (!test_check_exists(cache, 128 * 1024 * 1024 + 128 * 1024,
-			       128 * 1024)) {
+	if (!test_check_exists(cache, SZ_128M + SZ_128K, SZ_128K)) {
 		test_msg("Free space range missing\n");
 		return -ENOENT;
 	}
-	if (!test_check_exists(cache, 128 * 1024 * 1024 - 768 * 1024,
-			       256 * 1024)) {
+	if (!test_check_exists(cache, SZ_128M - 768 * SZ_1K, SZ_256K)) {
 		test_msg("Free space range missing\n");
 		return -ENOENT;
 	}
@@ -741,8 +688,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	 * Confirm that the bitmap range [0, 128Mb - 768Kb[ isn't marked
 	 * as free anymore.
 	 */
-	if (test_check_exists(cache, 0,
-			      128 * 1024 * 1024 - 768 * 1024)) {
+	if (test_check_exists(cache, 0, SZ_128M - 768 * SZ_1K)) {
 		test_msg("Bitmap region not removed from space cache\n");
 		return -EINVAL;
 	}
@@ -751,8 +697,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	 * Confirm that the region [128Mb - 512Kb, 128Mb[, which is
 	 * covered by the bitmap, isn't marked as free.
 	 */
-	if (test_check_exists(cache, 128 * 1024 * 1024 - 512 * 1024,
-			      512 * 1024)) {
+	if (test_check_exists(cache, SZ_128M - SZ_512K, SZ_512K)) {
 		test_msg("Invalid bitmap region marked as free\n");
 		return -EINVAL;
 	}
@@ -762,15 +707,13 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	 * lets make sure the free space cache marks it as free in the bitmap,
 	 * and doesn't insert a new extent entry to represent this region.
 	 */
-	ret = btrfs_add_free_space(cache, 128 * 1024 * 1024 - 512 * 1024,
-				   512 * 1024);
+	ret = btrfs_add_free_space(cache, SZ_128M - SZ_512K, SZ_512K);
 	if (ret) {
 		test_msg("Error adding free space: %d\n", ret);
 		return ret;
 	}
 	/* Confirm the region is marked as free. */
-	if (!test_check_exists(cache, 128 * 1024 * 1024 - 512 * 1024,
-			       512 * 1024)) {
+	if (!test_check_exists(cache, SZ_128M - SZ_512K, SZ_512K)) {
 		test_msg("Bitmap region not marked as free\n");
 		return -ENOENT;
 	}
@@ -789,7 +732,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	 * The goal is to test that the bitmap entry space stealing doesn't
 	 * steal this space region.
 	 */
-	ret = btrfs_add_free_space(cache, 32 * 1024 * 1024, 8192);
+	ret = btrfs_add_free_space(cache, SZ_32M, 8192);
 	if (ret) {
 		test_msg("Error adding free space: %d\n", ret);
 		return ret;
@@ -800,13 +743,13 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	 * expand the range covered by the existing extent entry that represents
 	 * the free space [128Mb + 128Kb, 128Mb + 256Kb[.
 	 */
-	ret = btrfs_add_free_space(cache, 128 * 1024 * 1024, 128 * 1024);
+	ret = btrfs_add_free_space(cache, SZ_128M, SZ_128K);
 	if (ret) {
 		test_msg("Error adding free space: %d\n", ret);
 		return ret;
 	}
 	/* Confirm the region is marked as free. */
-	if (!test_check_exists(cache, 128 * 1024 * 1024, 128 * 1024)) {
+	if (!test_check_exists(cache, SZ_128M, SZ_128K)) {
 		test_msg("Extent region not marked as free\n");
 		return -ENOENT;
 	}
@@ -834,21 +777,19 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	 * that represents the 1Mb free space, and therefore we're able to
 	 * allocate the whole free space at once.
 	 */
-	if (!test_check_exists(cache, 128 * 1024 * 1024 - 768 * 1024,
-			       1 * 1024 * 1024)) {
+	if (!test_check_exists(cache, SZ_128M - 768 * SZ_1K, SZ_1M)) {
 		test_msg("Expected region not marked as free\n");
 		return -ENOENT;
 	}
 
-	if (cache->free_space_ctl->free_space != (1 * 1024 * 1024 + 8192)) {
+	if (cache->free_space_ctl->free_space != (SZ_1M + 8192)) {
 		test_msg("Cache free space is not 1Mb + 8Kb\n");
 		return -EINVAL;
 	}
 
-	offset = btrfs_find_space_for_alloc(cache,
-					    0, 1 * 1024 * 1024, 0,
+	offset = btrfs_find_space_for_alloc(cache, 0, SZ_1M, 0,
 					    &max_extent_size);
-	if (offset != (128 * 1024 * 1024 - 768 * 1024)) {
+	if (offset != (SZ_128M - 768 * SZ_1K)) {
 		test_msg("Failed to allocate 1Mb from space cache, returned offset is: %llu\n",
 			 offset);
 		return -EINVAL;
@@ -867,7 +808,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	offset = btrfs_find_space_for_alloc(cache,
 					    0, 8192, 0,
 					    &max_extent_size);
-	if (offset != (32 * 1024 * 1024)) {
+	if (offset != SZ_32M) {
 		test_msg("Failed to allocate 8Kb from space cache, returned offset is: %llu\n",
 			 offset);
 		return -EINVAL;
@@ -877,7 +818,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	if (ret)
 		return ret;
 
-	cache->free_space_ctl->op->use_bitmap = use_bitmap_op;
+	cache->free_space_ctl->op = orig_free_space_ops;
 	__btrfs_remove_free_space_cache(cache->free_space_ctl);
 
 	return 0;
@@ -891,15 +832,17 @@ int btrfs_test_free_space_cache(void)
 
 	test_msg("Running btrfs free space cache tests\n");
 
-	cache = init_test_block_group();
+	cache = btrfs_alloc_dummy_block_group(1024 * 1024 * 1024);
 	if (!cache) {
 		test_msg("Couldn't run the tests\n");
 		return 0;
 	}
 
 	root = btrfs_alloc_dummy_root();
-	if (!root)
+	if (IS_ERR(root)) {
+		ret = PTR_ERR(root);
 		goto out;
+	}
 
 	root->fs_info = btrfs_alloc_dummy_fs_info();
 	if (!root->fs_info)
@@ -920,9 +863,7 @@ int btrfs_test_free_space_cache(void)
 
 	ret = test_steal_space_from_bitmap_to_extent(cache);
 out:
-	__btrfs_remove_free_space_cache(cache->free_space_ctl);
-	kfree(cache->free_space_ctl);
-	kfree(cache);
+	btrfs_free_dummy_block_group(cache);
 	btrfs_free_dummy_root(root);
 	test_msg("Free space cache tests finished\n");
 	return ret;
diff --git a/fs/btrfs/tests/free-space-tree-tests.c b/fs/btrfs/tests/free-space-tree-tests.c
new file mode 100644
index 000000000000..7cea4462acd5
--- /dev/null
+++ b/fs/btrfs/tests/free-space-tree-tests.c
@@ -0,0 +1,572 @@
+/*
+ * Copyright (C) 2015 Facebook.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#include "btrfs-tests.h"
+#include "../ctree.h"
+#include "../disk-io.h"
+#include "../free-space-tree.h"
+#include "../transaction.h"
+
+struct free_space_extent {
+	u64 start, length;
+};
+
+/*
+ * The test cases align their operations to this in order to hit some of the
+ * edge cases in the bitmap code.
+ */
+#define BITMAP_RANGE (BTRFS_FREE_SPACE_BITMAP_BITS * 4096)
+
+static int __check_free_space_extents(struct btrfs_trans_handle *trans,
+				      struct btrfs_fs_info *fs_info,
+				      struct btrfs_block_group_cache *cache,
+				      struct btrfs_path *path,
+				      struct free_space_extent *extents,
+				      unsigned int num_extents)
+{
+	struct btrfs_free_space_info *info;
+	struct btrfs_key key;
+	int prev_bit = 0, bit;
+	u64 extent_start = 0, offset, end;
+	u32 flags, extent_count;
+	unsigned int i;
+	int ret;
+
+	info = search_free_space_info(trans, fs_info, cache, path, 0);
+	if (IS_ERR(info)) {
+		test_msg("Could not find free space info\n");
+		ret = PTR_ERR(info);
+		goto out;
+	}
+	flags = btrfs_free_space_flags(path->nodes[0], info);
+	extent_count = btrfs_free_space_extent_count(path->nodes[0], info);
+
+	if (extent_count != num_extents) {
+		test_msg("Extent count is wrong\n");
+		ret = -EINVAL;
+		goto out;
+	}
+	if (flags & BTRFS_FREE_SPACE_USING_BITMAPS) {
+		if (path->slots[0] != 0)
+			goto invalid;
+		end = cache->key.objectid + cache->key.offset;
+		i = 0;
+		while (++path->slots[0] < btrfs_header_nritems(path->nodes[0])) {
+			btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+			if (key.type != BTRFS_FREE_SPACE_BITMAP_KEY)
+				goto invalid;
+			offset = key.objectid;
+			while (offset < key.objectid + key.offset) {
+				bit = free_space_test_bit(cache, path, offset);
+				if (prev_bit == 0 && bit == 1) {
+					extent_start = offset;
+				} else if (prev_bit == 1 && bit == 0) {
+					if (i >= num_extents)
+						goto invalid;
+					if (i >= num_extents ||
+					    extent_start != extents[i].start ||
+					    offset - extent_start != extents[i].length)
+						goto invalid;
+					i++;
+				}
+				prev_bit = bit;
+				offset += cache->sectorsize;
+			}
+		}
+		if (prev_bit == 1) {
+			if (i >= num_extents ||
+			    extent_start != extents[i].start ||
+			    end - extent_start != extents[i].length)
+				goto invalid;
+			i++;
+		}
+		if (i != num_extents)
+			goto invalid;
+	} else {
+		if (btrfs_header_nritems(path->nodes[0]) != num_extents + 1 ||
+		    path->slots[0] != 0)
+			goto invalid;
+		for (i = 0; i < num_extents; i++) {
+			path->slots[0]++;
+			btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+			if (key.type != BTRFS_FREE_SPACE_EXTENT_KEY ||
+			    key.objectid != extents[i].start ||
+			    key.offset != extents[i].length)
+				goto invalid;
+		}
+	}
+
+	ret = 0;
+out:
+	btrfs_release_path(path);
+	return ret;
+invalid:
+	test_msg("Free space tree is invalid\n");
+	ret = -EINVAL;
+	goto out;
+}
+
+static int check_free_space_extents(struct btrfs_trans_handle *trans,
+				    struct btrfs_fs_info *fs_info,
+				    struct btrfs_block_group_cache *cache,
+				    struct btrfs_path *path,
+				    struct free_space_extent *extents,
+				    unsigned int num_extents)
+{
+	struct btrfs_free_space_info *info;
+	u32 flags;
+	int ret;
+
+	info = search_free_space_info(trans, fs_info, cache, path, 0);
+	if (IS_ERR(info)) {
+		test_msg("Could not find free space info\n");
+		btrfs_release_path(path);
+		return PTR_ERR(info);
+	}
+	flags = btrfs_free_space_flags(path->nodes[0], info);
+	btrfs_release_path(path);
+
+	ret = __check_free_space_extents(trans, fs_info, cache, path, extents,
+					 num_extents);
+	if (ret)
+		return ret;
+
+	/* Flip it to the other format and check that for good measure. */
+	if (flags & BTRFS_FREE_SPACE_USING_BITMAPS) {
+		ret = convert_free_space_to_extents(trans, fs_info, cache, path);
+		if (ret) {
+			test_msg("Could not convert to extents\n");
+			return ret;
+		}
+	} else {
+		ret = convert_free_space_to_bitmaps(trans, fs_info, cache, path);
+		if (ret) {
+			test_msg("Could not convert to bitmaps\n");
+			return ret;
+		}
+	}
+	return __check_free_space_extents(trans, fs_info, cache, path, extents,
+					  num_extents);
+}
+
+static int test_empty_block_group(struct btrfs_trans_handle *trans,
+				  struct btrfs_fs_info *fs_info,
+				  struct btrfs_block_group_cache *cache,
+				  struct btrfs_path *path)
+{
+	struct free_space_extent extents[] = {
+		{cache->key.objectid, cache->key.offset},
+	};
+
+	return check_free_space_extents(trans, fs_info, cache, path,
+					extents, ARRAY_SIZE(extents));
+}
+
+static int test_remove_all(struct btrfs_trans_handle *trans,
+			   struct btrfs_fs_info *fs_info,
+			   struct btrfs_block_group_cache *cache,
+			   struct btrfs_path *path)
+{
+	struct free_space_extent extents[] = {};
+	int ret;
+
+	ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+					    cache->key.objectid,
+					    cache->key.offset);
+	if (ret) {
+		test_msg("Could not remove free space\n");
+		return ret;
+	}
+
+	return check_free_space_extents(trans, fs_info, cache, path,
+					extents, ARRAY_SIZE(extents));
+}
+
+static int test_remove_beginning(struct btrfs_trans_handle *trans,
+				 struct btrfs_fs_info *fs_info,
+				 struct btrfs_block_group_cache *cache,
+				 struct btrfs_path *path)
+{
+	struct free_space_extent extents[] = {
+		{cache->key.objectid + BITMAP_RANGE,
+			cache->key.offset - BITMAP_RANGE},
+	};
+	int ret;
+
+	ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+					    cache->key.objectid, BITMAP_RANGE);
+	if (ret) {
+		test_msg("Could not remove free space\n");
+		return ret;
+	}
+
+	return check_free_space_extents(trans, fs_info, cache, path,
+					extents, ARRAY_SIZE(extents));
+
+}
+
+static int test_remove_end(struct btrfs_trans_handle *trans,
+			   struct btrfs_fs_info *fs_info,
+			   struct btrfs_block_group_cache *cache,
+			   struct btrfs_path *path)
+{
+	struct free_space_extent extents[] = {
+		{cache->key.objectid, cache->key.offset - BITMAP_RANGE},
+	};
+	int ret;
+
+	ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+					    cache->key.objectid +
+					    cache->key.offset - BITMAP_RANGE,
+					    BITMAP_RANGE);
+	if (ret) {
+		test_msg("Could not remove free space\n");
+		return ret;
+	}
+
+	return check_free_space_extents(trans, fs_info, cache, path,
+					extents, ARRAY_SIZE(extents));
+}
+
+static int test_remove_middle(struct btrfs_trans_handle *trans,
+			      struct btrfs_fs_info *fs_info,
+			      struct btrfs_block_group_cache *cache,
+			      struct btrfs_path *path)
+{
+	struct free_space_extent extents[] = {
+		{cache->key.objectid, BITMAP_RANGE},
+		{cache->key.objectid + 2 * BITMAP_RANGE,
+			cache->key.offset - 2 * BITMAP_RANGE},
+	};
+	int ret;
+
+	ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+					    cache->key.objectid + BITMAP_RANGE,
+					    BITMAP_RANGE);
+	if (ret) {
+		test_msg("Could not remove free space\n");
+		return ret;
+	}
+
+	return check_free_space_extents(trans, fs_info, cache, path,
+					extents, ARRAY_SIZE(extents));
+}
+
+static int test_merge_left(struct btrfs_trans_handle *trans,
+			   struct btrfs_fs_info *fs_info,
+			   struct btrfs_block_group_cache *cache,
+			   struct btrfs_path *path)
+{
+	struct free_space_extent extents[] = {
+		{cache->key.objectid, 2 * BITMAP_RANGE},
+	};
+	int ret;
+
+	ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+					    cache->key.objectid,
+					    cache->key.offset);
+	if (ret) {
+		test_msg("Could not remove free space\n");
+		return ret;
+	}
+
+	ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+				       cache->key.objectid, BITMAP_RANGE);
+	if (ret) {
+		test_msg("Could not add free space\n");
+		return ret;
+	}
+
+	ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+				       cache->key.objectid + BITMAP_RANGE,
+				       BITMAP_RANGE);
+	if (ret) {
+		test_msg("Could not add free space\n");
+		return ret;
+	}
+
+	return check_free_space_extents(trans, fs_info, cache, path,
+					extents, ARRAY_SIZE(extents));
+}
+
+static int test_merge_right(struct btrfs_trans_handle *trans,
+			   struct btrfs_fs_info *fs_info,
+			   struct btrfs_block_group_cache *cache,
+			   struct btrfs_path *path)
+{
+	struct free_space_extent extents[] = {
+		{cache->key.objectid + BITMAP_RANGE, 2 * BITMAP_RANGE},
+	};
+	int ret;
+
+	ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+					    cache->key.objectid,
+					    cache->key.offset);
+	if (ret) {
+		test_msg("Could not remove free space\n");
+		return ret;
+	}
+
+	ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+				       cache->key.objectid + 2 * BITMAP_RANGE,
+				       BITMAP_RANGE);
+	if (ret) {
+		test_msg("Could not add free space\n");
+		return ret;
+	}
+
+	ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+				       cache->key.objectid + BITMAP_RANGE,
+				       BITMAP_RANGE);
+	if (ret) {
+		test_msg("Could not add free space\n");
+		return ret;
+	}
+
+	return check_free_space_extents(trans, fs_info, cache, path,
+					extents, ARRAY_SIZE(extents));
+}
+
+static int test_merge_both(struct btrfs_trans_handle *trans,
+			   struct btrfs_fs_info *fs_info,
+			   struct btrfs_block_group_cache *cache,
+			   struct btrfs_path *path)
+{
+	struct free_space_extent extents[] = {
+		{cache->key.objectid, 3 * BITMAP_RANGE},
+	};
+	int ret;
+
+	ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+					    cache->key.objectid,
+					    cache->key.offset);
+	if (ret) {
+		test_msg("Could not remove free space\n");
+		return ret;
+	}
+
+	ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+				       cache->key.objectid, BITMAP_RANGE);
+	if (ret) {
+		test_msg("Could not add free space\n");
+		return ret;
+	}
+
+	ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+				       cache->key.objectid + 2 * BITMAP_RANGE,
+				       BITMAP_RANGE);
+	if (ret) {
+		test_msg("Could not add free space\n");
+		return ret;
+	}
+
+	ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+				       cache->key.objectid + BITMAP_RANGE,
+				       BITMAP_RANGE);
+	if (ret) {
+		test_msg("Could not add free space\n");
+		return ret;
+	}
+
+	return check_free_space_extents(trans, fs_info, cache, path,
+					extents, ARRAY_SIZE(extents));
+}
+
+static int test_merge_none(struct btrfs_trans_handle *trans,
+			   struct btrfs_fs_info *fs_info,
+			   struct btrfs_block_group_cache *cache,
+			   struct btrfs_path *path)
+{
+	struct free_space_extent extents[] = {
+		{cache->key.objectid, BITMAP_RANGE},
+		{cache->key.objectid + 2 * BITMAP_RANGE, BITMAP_RANGE},
+		{cache->key.objectid + 4 * BITMAP_RANGE, BITMAP_RANGE},
+	};
+	int ret;
+
+	ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+					    cache->key.objectid,
+					    cache->key.offset);
+	if (ret) {
+		test_msg("Could not remove free space\n");
+		return ret;
+	}
+
+	ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+				       cache->key.objectid, BITMAP_RANGE);
+	if (ret) {
+		test_msg("Could not add free space\n");
+		return ret;
+	}
+
+	ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+				       cache->key.objectid + 4 * BITMAP_RANGE,
+				       BITMAP_RANGE);
+	if (ret) {
+		test_msg("Could not add free space\n");
+		return ret;
+	}
+
+	ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+				       cache->key.objectid + 2 * BITMAP_RANGE,
+				       BITMAP_RANGE);
+	if (ret) {
+		test_msg("Could not add free space\n");
+		return ret;
+	}
+
+	return check_free_space_extents(trans, fs_info, cache, path,
+					extents, ARRAY_SIZE(extents));
+}
+
+typedef int (*test_func_t)(struct btrfs_trans_handle *,
+			   struct btrfs_fs_info *,
+			   struct btrfs_block_group_cache *,
+			   struct btrfs_path *);
+
+static int run_test(test_func_t test_func, int bitmaps)
+{
+	struct btrfs_root *root = NULL;
+	struct btrfs_block_group_cache *cache = NULL;
+	struct btrfs_trans_handle trans;
+	struct btrfs_path *path = NULL;
+	int ret;
+
+	root = btrfs_alloc_dummy_root();
+	if (IS_ERR(root)) {
+		test_msg("Couldn't allocate dummy root\n");
+		ret = PTR_ERR(root);
+		goto out;
+	}
+
+	root->fs_info = btrfs_alloc_dummy_fs_info();
+	if (!root->fs_info) {
+		test_msg("Couldn't allocate dummy fs info\n");
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	btrfs_set_super_compat_ro_flags(root->fs_info->super_copy,
+					BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE);
+	root->fs_info->free_space_root = root;
+	root->fs_info->tree_root = root;
+
+	root->node = alloc_test_extent_buffer(root->fs_info, 4096);
+	if (!root->node) {
+		test_msg("Couldn't allocate dummy buffer\n");
+		ret = -ENOMEM;
+		goto out;
+	}
+	btrfs_set_header_level(root->node, 0);
+	btrfs_set_header_nritems(root->node, 0);
+	root->alloc_bytenr += 8192;
+
+	cache = btrfs_alloc_dummy_block_group(8 * BITMAP_RANGE);
+	if (!cache) {
+		test_msg("Couldn't allocate dummy block group cache\n");
+		ret = -ENOMEM;
+		goto out;
+	}
+	cache->bitmap_low_thresh = 0;
+	cache->bitmap_high_thresh = (u32)-1;
+	cache->needs_free_space = 1;
+	cache->fs_info = root->fs_info;
+
+	btrfs_init_dummy_trans(&trans);
+
+	path = btrfs_alloc_path();
+	if (!path) {
+		test_msg("Couldn't allocate path\n");
+		return -ENOMEM;
+	}
+
+	ret = add_block_group_free_space(&trans, root->fs_info, cache);
+	if (ret) {
+		test_msg("Could not add block group free space\n");
+		goto out;
+	}
+
+	if (bitmaps) {
+		ret = convert_free_space_to_bitmaps(&trans, root->fs_info,
+						    cache, path);
+		if (ret) {
+			test_msg("Could not convert block group to bitmaps\n");
+			goto out;
+		}
+	}
+
+	ret = test_func(&trans, root->fs_info, cache, path);
+	if (ret)
+		goto out;
+
+	ret = remove_block_group_free_space(&trans, root->fs_info, cache);
+	if (ret) {
+		test_msg("Could not remove block group free space\n");
+		goto out;
+	}
+
+	if (btrfs_header_nritems(root->node) != 0) {
+		test_msg("Free space tree has leftover items\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = 0;
+out:
+	btrfs_free_path(path);
+	btrfs_free_dummy_block_group(cache);
+	btrfs_free_dummy_root(root);
+	return ret;
+}
+
+static int run_test_both_formats(test_func_t test_func)
+{
+	int ret;
+
+	ret = run_test(test_func, 0);
+	if (ret)
+		return ret;
+	return run_test(test_func, 1);
+}
+
+int btrfs_test_free_space_tree(void)
+{
+	test_func_t tests[] = {
+		test_empty_block_group,
+		test_remove_all,
+		test_remove_beginning,
+		test_remove_end,
+		test_remove_middle,
+		test_merge_left,
+		test_merge_right,
+		test_merge_both,
+		test_merge_none,
+	};
+	int i;
+
+	test_msg("Running free space tree tests\n");
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		int ret = run_test_both_formats(tests[i]);
+		if (ret) {
+			test_msg("%pf failed\n", tests[i]);
+			return ret;
+		}
+	}
+
+	return 0;
+}
diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c
index 054fc0d97131..863a6a3af1f8 100644
--- a/fs/btrfs/tests/inode-tests.c
+++ b/fs/btrfs/tests/inode-tests.c
@@ -22,6 +22,7 @@
 #include "../disk-io.h"
 #include "../extent_io.h"
 #include "../volumes.h"
+#include "../compression.h"
 
 static void insert_extent(struct btrfs_root *root, u64 start, u64 len,
 			  u64 ram_bytes, u64 offset, u64 disk_bytenr,
@@ -100,7 +101,7 @@ static void insert_inode_item_key(struct btrfs_root *root)
 static void setup_file_extents(struct btrfs_root *root)
 {
 	int slot = 0;
-	u64 disk_bytenr = 1 * 1024 * 1024;
+	u64 disk_bytenr = SZ_1M;
 	u64 offset = 0;
 
 	/* First we want a hole */
@@ -974,7 +975,7 @@ static int test_extent_accounting(void)
 			       (BTRFS_MAX_EXTENT_SIZE >> 1) + 4095,
 			       EXTENT_DELALLOC | EXTENT_DIRTY |
 			       EXTENT_UPTODATE | EXTENT_DO_ACCOUNTING, 0, 0,
-			       NULL, GFP_NOFS);
+			       NULL, GFP_KERNEL);
 	if (ret) {
 		test_msg("clear_extent_bit returned %d\n", ret);
 		goto out;
@@ -1045,7 +1046,7 @@ static int test_extent_accounting(void)
 			       BTRFS_MAX_EXTENT_SIZE+8191,
 			       EXTENT_DIRTY | EXTENT_DELALLOC |
 			       EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0,
-			       NULL, GFP_NOFS);
+			       NULL, GFP_KERNEL);
 	if (ret) {
 		test_msg("clear_extent_bit returned %d\n", ret);
 		goto out;
@@ -1079,7 +1080,7 @@ static int test_extent_accounting(void)
 	ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1,
 			       EXTENT_DIRTY | EXTENT_DELALLOC |
 			       EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0,
-			       NULL, GFP_NOFS);
+			       NULL, GFP_KERNEL);
 	if (ret) {
 		test_msg("clear_extent_bit returned %d\n", ret);
 		goto out;
@@ -1096,7 +1097,7 @@ out:
 		clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1,
 				 EXTENT_DIRTY | EXTENT_DELALLOC |
 				 EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0,
-				 NULL, GFP_NOFS);
+				 NULL, GFP_KERNEL);
 	iput(inode);
 	btrfs_free_dummy_root(root);
 	return ret;
diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c
index 846d277b1901..8ea5d34bc5a2 100644
--- a/fs/btrfs/tests/qgroup-tests.c
+++ b/fs/btrfs/tests/qgroup-tests.c
@@ -23,14 +23,6 @@
 #include "../qgroup.h"
 #include "../backref.h"
 
-static void init_dummy_trans(struct btrfs_trans_handle *trans)
-{
-	memset(trans, 0, sizeof(*trans));
-	trans->transid = 1;
-	INIT_LIST_HEAD(&trans->qgroup_ref_list);
-	trans->type = __TRANS_DUMMY;
-}
-
 static int insert_normal_tree_ref(struct btrfs_root *root, u64 bytenr,
 				  u64 num_bytes, u64 parent, u64 root_objectid)
 {
@@ -44,7 +36,7 @@ static int insert_normal_tree_ref(struct btrfs_root *root, u64 bytenr,
 	u32 size = sizeof(*item) + sizeof(*iref) + sizeof(*block_info);
 	int ret;
 
-	init_dummy_trans(&trans);
+	btrfs_init_dummy_trans(&trans);
 
 	ins.objectid = bytenr;
 	ins.type = BTRFS_EXTENT_ITEM_KEY;
@@ -94,7 +86,7 @@ static int add_tree_ref(struct btrfs_root *root, u64 bytenr, u64 num_bytes,
 	u64 refs;
 	int ret;
 
-	init_dummy_trans(&trans);
+	btrfs_init_dummy_trans(&trans);
 
 	key.objectid = bytenr;
 	key.type = BTRFS_EXTENT_ITEM_KEY;
@@ -144,7 +136,7 @@ static int remove_extent_item(struct btrfs_root *root, u64 bytenr,
 	struct btrfs_path *path;
 	int ret;
 
-	init_dummy_trans(&trans);
+	btrfs_init_dummy_trans(&trans);
 
 	key.objectid = bytenr;
 	key.type = BTRFS_EXTENT_ITEM_KEY;
@@ -178,7 +170,7 @@ static int remove_extent_ref(struct btrfs_root *root, u64 bytenr,
 	u64 refs;
 	int ret;
 
-	init_dummy_trans(&trans);
+	btrfs_init_dummy_trans(&trans);
 
 	key.objectid = bytenr;
 	key.type = BTRFS_EXTENT_ITEM_KEY;
@@ -232,7 +224,7 @@ static int test_no_shared_qgroup(struct btrfs_root *root)
 	struct ulist *new_roots = NULL;
 	int ret;
 
-	init_dummy_trans(&trans);
+	btrfs_init_dummy_trans(&trans);
 
 	test_msg("Qgroup basic add\n");
 	ret = btrfs_create_qgroup(NULL, fs_info, 5);
@@ -326,7 +318,7 @@ static int test_multiple_refs(struct btrfs_root *root)
 	struct ulist *new_roots = NULL;
 	int ret;
 
-	init_dummy_trans(&trans);
+	btrfs_init_dummy_trans(&trans);
 
 	test_msg("Qgroup multiple refs test\n");
 
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 418c6a2ad7d8..43885e51b882 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -75,6 +75,23 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction)
 			list_del_init(&em->list);
 			free_extent_map(em);
 		}
+		/*
+		 * If any block groups are found in ->deleted_bgs then it's
+		 * because the transaction was aborted and a commit did not
+		 * happen (things failed before writing the new superblock
+		 * and calling btrfs_finish_extent_commit()), so we can not
+		 * discard the physical locations of the block groups.
+		 */
+		while (!list_empty(&transaction->deleted_bgs)) {
+			struct btrfs_block_group_cache *cache;
+
+			cache = list_first_entry(&transaction->deleted_bgs,
+						 struct btrfs_block_group_cache,
+						 bg_list);
+			list_del_init(&cache->bg_list);
+			btrfs_put_block_group_trimming(cache);
+			btrfs_put_block_group(cache);
+		}
 		kmem_cache_free(btrfs_transaction_cachep, transaction);
 	}
 }
@@ -274,7 +291,6 @@ loop:
 	cur_trans->num_dirty_bgs = 0;
 	spin_lock_init(&cur_trans->dirty_bgs_lock);
 	INIT_LIST_HEAD(&cur_trans->deleted_bgs);
-	spin_lock_init(&cur_trans->deleted_bgs_lock);
 	spin_lock_init(&cur_trans->dropped_roots_lock);
 	list_add_tail(&cur_trans->list, &fs_info->trans_list);
 	extent_io_tree_init(&cur_trans->dirty_pages,
@@ -592,6 +608,40 @@ struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
 	return start_transaction(root, num_items, TRANS_START,
 				 BTRFS_RESERVE_FLUSH_ALL);
 }
+struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv(
+					struct btrfs_root *root,
+					unsigned int num_items,
+					int min_factor)
+{
+	struct btrfs_trans_handle *trans;
+	u64 num_bytes;
+	int ret;
+
+	trans = btrfs_start_transaction(root, num_items);
+	if (!IS_ERR(trans) || PTR_ERR(trans) != -ENOSPC)
+		return trans;
+
+	trans = btrfs_start_transaction(root, 0);
+	if (IS_ERR(trans))
+		return trans;
+
+	num_bytes = btrfs_calc_trans_metadata_size(root, num_items);
+	ret = btrfs_cond_migrate_bytes(root->fs_info,
+				       &root->fs_info->trans_block_rsv,
+				       num_bytes,
+				       min_factor);
+	if (ret) {
+		btrfs_end_transaction(trans, root);
+		return ERR_PTR(ret);
+	}
+
+	trans->block_rsv = &root->fs_info->trans_block_rsv;
+	trans->bytes_reserved = num_bytes;
+	trace_btrfs_space_reservation(root->fs_info, "transaction",
+				      trans->transid, num_bytes, 1);
+
+	return trans;
+}
 
 struct btrfs_trans_handle *btrfs_start_transaction_lflush(
 					struct btrfs_root *root,
@@ -603,17 +653,20 @@ struct btrfs_trans_handle *btrfs_start_transaction_lflush(
 
 struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root)
 {
-	return start_transaction(root, 0, TRANS_JOIN, 0);
+	return start_transaction(root, 0, TRANS_JOIN,
+				 BTRFS_RESERVE_NO_FLUSH);
 }
 
 struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root)
 {
-	return start_transaction(root, 0, TRANS_JOIN_NOLOCK, 0);
+	return start_transaction(root, 0, TRANS_JOIN_NOLOCK,
+				 BTRFS_RESERVE_NO_FLUSH);
 }
 
 struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *root)
 {
-	return start_transaction(root, 0, TRANS_USERSPACE, 0);
+	return start_transaction(root, 0, TRANS_USERSPACE,
+				 BTRFS_RESERVE_NO_FLUSH);
 }
 
 /*
@@ -631,7 +684,8 @@ struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *root
  */
 struct btrfs_trans_handle *btrfs_attach_transaction(struct btrfs_root *root)
 {
-	return start_transaction(root, 0, TRANS_ATTACH, 0);
+	return start_transaction(root, 0, TRANS_ATTACH,
+				 BTRFS_RESERVE_NO_FLUSH);
 }
 
 /*
@@ -646,7 +700,8 @@ btrfs_attach_transaction_barrier(struct btrfs_root *root)
 {
 	struct btrfs_trans_handle *trans;
 
-	trans = start_transaction(root, 0, TRANS_ATTACH, 0);
+	trans = start_transaction(root, 0, TRANS_ATTACH,
+				  BTRFS_RESERVE_NO_FLUSH);
 	if (IS_ERR(trans) && PTR_ERR(trans) == -ENOENT)
 		btrfs_wait_for_commit(root, 0);
 
@@ -1280,7 +1335,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	struct dentry *dentry;
 	struct extent_buffer *tmp;
 	struct extent_buffer *old;
-	struct timespec cur_time = CURRENT_TIME;
+	struct timespec cur_time;
 	int ret = 0;
 	u64 to_reserve = 0;
 	u64 index = 0;
@@ -1288,17 +1343,11 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	u64 root_flags;
 	uuid_le new_uuid;
 
-	path = btrfs_alloc_path();
-	if (!path) {
-		pending->error = -ENOMEM;
-		return 0;
-	}
+	ASSERT(pending->path);
+	path = pending->path;
 
-	new_root_item = kmalloc(sizeof(*new_root_item), GFP_NOFS);
-	if (!new_root_item) {
-		pending->error = -ENOMEM;
-		goto root_item_alloc_fail;
-	}
+	ASSERT(pending->root_item);
+	new_root_item = pending->root_item;
 
 	pending->error = btrfs_find_free_objectid(tree_root, &objectid);
 	if (pending->error)
@@ -1328,12 +1377,16 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	rsv = trans->block_rsv;
 	trans->block_rsv = &pending->block_rsv;
 	trans->bytes_reserved = trans->block_rsv->reserved;
-
+	trace_btrfs_space_reservation(root->fs_info, "transaction",
+				      trans->transid,
+				      trans->bytes_reserved, 1);
 	dentry = pending->dentry;
 	parent_inode = pending->dir;
 	parent_root = BTRFS_I(parent_inode)->root;
 	record_root_in_trans(trans, parent_root);
 
+	cur_time = current_fs_time(parent_inode->i_sb);
+
 	/*
 	 * insert the directory item
 	 */
@@ -1476,7 +1529,8 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 
 	btrfs_i_size_write(parent_inode, parent_inode->i_size +
 					 dentry->d_name.len * 2);
-	parent_inode->i_mtime = parent_inode->i_ctime = CURRENT_TIME;
+	parent_inode->i_mtime = parent_inode->i_ctime =
+		current_fs_time(parent_inode->i_sb);
 	ret = btrfs_update_inode_fallback(trans, parent_root, parent_inode);
 	if (ret) {
 		btrfs_abort_transaction(trans, root, ret);
@@ -1531,8 +1585,10 @@ clear_skip_qgroup:
 	btrfs_clear_skip_qgroup(trans);
 no_free_objectid:
 	kfree(new_root_item);
-root_item_alloc_fail:
+	pending->root_item = NULL;
 	btrfs_free_path(path);
+	pending->path = NULL;
+
 	return ret;
 }
 
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index b05b2f64d913..72be51f7ca2f 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -77,8 +77,8 @@ struct btrfs_transaction {
 	 */
 	struct mutex cache_write_mutex;
 	spinlock_t dirty_bgs_lock;
+	/* Protected by spin lock fs_info->unused_bgs_lock. */
 	struct list_head deleted_bgs;
-	spinlock_t deleted_bgs_lock;
 	spinlock_t dropped_roots_lock;
 	struct btrfs_delayed_ref_root delayed_refs;
 	int aborted;
@@ -137,8 +137,10 @@ struct btrfs_pending_snapshot {
 	struct dentry *dentry;
 	struct inode *dir;
 	struct btrfs_root *root;
+	struct btrfs_root_item *root_item;
 	struct btrfs_root *snap;
 	struct btrfs_qgroup_inherit *inherit;
+	struct btrfs_path *path;
 	/* block reservation for the operation */
 	struct btrfs_block_rsv block_rsv;
 	u64 qgroup_reserved;
@@ -185,6 +187,10 @@ int btrfs_end_transaction(struct btrfs_trans_handle *trans,
 			  struct btrfs_root *root);
 struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
 						   unsigned int num_items);
+struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv(
+					struct btrfs_root *root,
+					unsigned int num_items,
+					int min_factor);
 struct btrfs_trans_handle *btrfs_start_transaction_lflush(
 					struct btrfs_root *root,
 					unsigned int num_items);
diff --git a/fs/btrfs/tree-defrag.c b/fs/btrfs/tree-defrag.c
index f31db4325339..cb65089127cc 100644
--- a/fs/btrfs/tree-defrag.c
+++ b/fs/btrfs/tree-defrag.c
@@ -89,6 +89,12 @@ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 	btrfs_release_path(path);
+	/*
+	 * We don't need a lock on a leaf. btrfs_realloc_node() will lock all
+	 * leafs from path->nodes[1], so set lowest_level to 1 to avoid later
+	 * a deadlock (attempting to write lock an already write locked leaf).
+	 */
+	path->lowest_level = 1;
 	wret = btrfs_search_slot(trans, root, &key, path, 0, 1);
 
 	if (wret < 0) {
@@ -99,9 +105,12 @@ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
 		ret = 0;
 		goto out;
 	}
-	path->slots[1] = btrfs_header_nritems(path->nodes[1]);
-	next_key_ret = btrfs_find_next_key(root, path, &key, 1,
-					   min_trans);
+	/*
+	 * The node at level 1 must always be locked when our path has
+	 * keep_locks set and lowest_level is 1, regardless of the value of
+	 * path->slots[1].
+	 */
+	BUG_ON(path->locks[1] == 0);
 	ret = btrfs_realloc_node(trans, root,
 				 path->nodes[1], 0,
 				 &last_ret,
@@ -110,6 +119,18 @@ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
 		WARN_ON(ret == -EAGAIN);
 		goto out;
 	}
+	/*
+	 * Now that we reallocated the node we can find the next key. Note that
+	 * btrfs_find_next_key() can release our path and do another search
+	 * without COWing, this is because even with path->keep_locks = 1,
+	 * btrfs_search_slot() / ctree.c:unlock_up() does not keeps a lock on a
+	 * node when path->slots[node_level - 1] does not point to the last
+	 * item or a slot beyond the last item (ctree.c:unlock_up()). Therefore
+	 * we search for the next key after reallocating our node.
+	 */
+	path->slots[1] = btrfs_header_nritems(path->nodes[1]);
+	next_key_ret = btrfs_find_next_key(root, path, &key, 1,
+					   min_trans);
 	if (next_key_ret == 0) {
 		memcpy(&root->defrag_progress, &key, sizeof(key));
 		ret = -EAGAIN;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 323e12cc9d2f..517d0ccb351e 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -26,6 +26,7 @@
 #include "print-tree.h"
 #include "backref.h"
 #include "hash.h"
+#include "compression.h"
 
 /* magic values for the inode_only field in btrfs_log_inode:
  *
@@ -1045,7 +1046,7 @@ again:
 
 		/*
 		 * NOTE: we have searched root tree and checked the
-		 * coresponding ref, it does not need to check again.
+		 * corresponding ref, it does not need to check again.
 		 */
 		*search_done = 1;
 	}
@@ -4127,7 +4128,9 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 				     struct inode *inode,
 				     struct btrfs_path *path,
 				     struct list_head *logged_list,
-				     struct btrfs_log_ctx *ctx)
+				     struct btrfs_log_ctx *ctx,
+				     const u64 start,
+				     const u64 end)
 {
 	struct extent_map *em, *n;
 	struct list_head extents;
@@ -4166,7 +4169,13 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 	}
 
 	list_sort(NULL, &extents, extent_cmp);
-
+	/*
+	 * Collect any new ordered extents within the range. This is to
+	 * prevent logging file extent items without waiting for the disk
+	 * location they point to being written. We do this only to deal
+	 * with races against concurrent lockless direct IO writes.
+	 */
+	btrfs_get_logged_extents(inode, logged_list, start, end);
 process:
 	while (!list_empty(&extents)) {
 		em = list_entry(extents.next, struct extent_map, list);
@@ -4406,6 +4415,127 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
+/*
+ * When we are logging a new inode X, check if it doesn't have a reference that
+ * matches the reference from some other inode Y created in a past transaction
+ * and that was renamed in the current transaction. If we don't do this, then at
+ * log replay time we can lose inode Y (and all its files if it's a directory):
+ *
+ * mkdir /mnt/x
+ * echo "hello world" > /mnt/x/foobar
+ * sync
+ * mv /mnt/x /mnt/y
+ * mkdir /mnt/x                 # or touch /mnt/x
+ * xfs_io -c fsync /mnt/x
+ * <power fail>
+ * mount fs, trigger log replay
+ *
+ * After the log replay procedure, we would lose the first directory and all its
+ * files (file foobar).
+ * For the case where inode Y is not a directory we simply end up losing it:
+ *
+ * echo "123" > /mnt/foo
+ * sync
+ * mv /mnt/foo /mnt/bar
+ * echo "abc" > /mnt/foo
+ * xfs_io -c fsync /mnt/foo
+ * <power fail>
+ *
+ * We also need this for cases where a snapshot entry is replaced by some other
+ * entry (file or directory) otherwise we end up with an unreplayable log due to
+ * attempts to delete the snapshot entry (entry of type BTRFS_ROOT_ITEM_KEY) as
+ * if it were a regular entry:
+ *
+ * mkdir /mnt/x
+ * btrfs subvolume snapshot /mnt /mnt/x/snap
+ * btrfs subvolume delete /mnt/x/snap
+ * rmdir /mnt/x
+ * mkdir /mnt/x
+ * fsync /mnt/x or fsync some new file inside it
+ * <power fail>
+ *
+ * The snapshot delete, rmdir of x, mkdir of a new x and the fsync all happen in
+ * the same transaction.
+ */
+static int btrfs_check_ref_name_override(struct extent_buffer *eb,
+					 const int slot,
+					 const struct btrfs_key *key,
+					 struct inode *inode)
+{
+	int ret;
+	struct btrfs_path *search_path;
+	char *name = NULL;
+	u32 name_len = 0;
+	u32 item_size = btrfs_item_size_nr(eb, slot);
+	u32 cur_offset = 0;
+	unsigned long ptr = btrfs_item_ptr_offset(eb, slot);
+
+	search_path = btrfs_alloc_path();
+	if (!search_path)
+		return -ENOMEM;
+	search_path->search_commit_root = 1;
+	search_path->skip_locking = 1;
+
+	while (cur_offset < item_size) {
+		u64 parent;
+		u32 this_name_len;
+		u32 this_len;
+		unsigned long name_ptr;
+		struct btrfs_dir_item *di;
+
+		if (key->type == BTRFS_INODE_REF_KEY) {
+			struct btrfs_inode_ref *iref;
+
+			iref = (struct btrfs_inode_ref *)(ptr + cur_offset);
+			parent = key->offset;
+			this_name_len = btrfs_inode_ref_name_len(eb, iref);
+			name_ptr = (unsigned long)(iref + 1);
+			this_len = sizeof(*iref) + this_name_len;
+		} else {
+			struct btrfs_inode_extref *extref;
+
+			extref = (struct btrfs_inode_extref *)(ptr +
+							       cur_offset);
+			parent = btrfs_inode_extref_parent(eb, extref);
+			this_name_len = btrfs_inode_extref_name_len(eb, extref);
+			name_ptr = (unsigned long)&extref->name;
+			this_len = sizeof(*extref) + this_name_len;
+		}
+
+		if (this_name_len > name_len) {
+			char *new_name;
+
+			new_name = krealloc(name, this_name_len, GFP_NOFS);
+			if (!new_name) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			name_len = this_name_len;
+			name = new_name;
+		}
+
+		read_extent_buffer(eb, name, name_ptr, this_name_len);
+		di = btrfs_lookup_dir_item(NULL, BTRFS_I(inode)->root,
+					   search_path, parent,
+					   name, this_name_len, 0);
+		if (di && !IS_ERR(di)) {
+			ret = 1;
+			goto out;
+		} else if (IS_ERR(di)) {
+			ret = PTR_ERR(di);
+			goto out;
+		}
+		btrfs_release_path(search_path);
+
+		cur_offset += this_len;
+	}
+	ret = 0;
+out:
+	btrfs_free_path(search_path);
+	kfree(name);
+	return ret;
+}
+
 /* log a single inode in the tree log.
  * At least one parent directory for this inode must exist in the tree
  * or be logged already.
@@ -4492,7 +4622,22 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 
 	mutex_lock(&BTRFS_I(inode)->log_mutex);
 
-	btrfs_get_logged_extents(inode, &logged_list, start, end);
+	/*
+	 * Collect ordered extents only if we are logging data. This is to
+	 * ensure a subsequent request to log this inode in LOG_INODE_ALL mode
+	 * will process the ordered extents if they still exists at the time,
+	 * because when we collect them we test and set for the flag
+	 * BTRFS_ORDERED_LOGGED to prevent multiple log requests to process the
+	 * same ordered extents. The consequence for the LOG_INODE_ALL log mode
+	 * not processing the ordered extents is that we end up logging the
+	 * corresponding file extent items, based on the extent maps in the
+	 * inode's extent_map_tree's modified_list, without logging the
+	 * respective checksums (since the may still be only attached to the
+	 * ordered extents and have not been inserted in the csum tree by
+	 * btrfs_finish_ordered_io() yet).
+	 */
+	if (inode_only == LOG_INODE_ALL)
+		btrfs_get_logged_extents(inode, &logged_list, start, end);
 
 	/*
 	 * a brute force approach to making sure we get the most uptodate
@@ -4578,6 +4723,22 @@ again:
 		if (min_key.type == BTRFS_INODE_ITEM_KEY)
 			need_log_inode_item = false;
 
+		if ((min_key.type == BTRFS_INODE_REF_KEY ||
+		     min_key.type == BTRFS_INODE_EXTREF_KEY) &&
+		    BTRFS_I(inode)->generation == trans->transid) {
+			ret = btrfs_check_ref_name_override(path->nodes[0],
+							    path->slots[0],
+							    &min_key, inode);
+			if (ret < 0) {
+				err = ret;
+				goto out_unlock;
+			} else if (ret > 0) {
+				err = 1;
+				btrfs_set_log_full_commit(root->fs_info, trans);
+				goto out_unlock;
+			}
+		}
+
 		/* Skip xattrs, we log them later with btrfs_log_all_xattrs() */
 		if (min_key.type == BTRFS_XATTR_ITEM_KEY) {
 			if (ins_nr == 0)
@@ -4701,7 +4862,7 @@ log_extents:
 			goto out_unlock;
 		}
 		ret = btrfs_log_changed_extents(trans, root, inode, dst_path,
-						&logged_list, ctx);
+						&logged_list, ctx, start, end);
 		if (ret) {
 			err = ret;
 			goto out_unlock;
@@ -4764,6 +4925,42 @@ out_unlock:
 }
 
 /*
+ * Check if we must fallback to a transaction commit when logging an inode.
+ * This must be called after logging the inode and is used only in the context
+ * when fsyncing an inode requires the need to log some other inode - in which
+ * case we can't lock the i_mutex of each other inode we need to log as that
+ * can lead to deadlocks with concurrent fsync against other inodes (as we can
+ * log inodes up or down in the hierarchy) or rename operations for example. So
+ * we take the log_mutex of the inode after we have logged it and then check for
+ * its last_unlink_trans value - this is safe because any task setting
+ * last_unlink_trans must take the log_mutex and it must do this before it does
+ * the actual unlink operation, so if we do this check before a concurrent task
+ * sets last_unlink_trans it means we've logged a consistent version/state of
+ * all the inode items, otherwise we are not sure and must do a transaction
+ * commit (the concurrent task migth have only updated last_unlink_trans before
+ * we logged the inode or it might have also done the unlink).
+ */
+static bool btrfs_must_commit_transaction(struct btrfs_trans_handle *trans,
+					  struct inode *inode)
+{
+	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
+	bool ret = false;
+
+	mutex_lock(&BTRFS_I(inode)->log_mutex);
+	if (BTRFS_I(inode)->last_unlink_trans > fs_info->last_trans_committed) {
+		/*
+		 * Make sure any commits to the log are forced to be full
+		 * commits.
+		 */
+		btrfs_set_log_full_commit(fs_info, trans);
+		ret = true;
+	}
+	mutex_unlock(&BTRFS_I(inode)->log_mutex);
+
+	return ret;
+}
+
+/*
  * follow the dentry parent pointers up the chain and see if any
  * of the directories in it require a full commit before they can
  * be logged.  Returns zero if nothing special needs to be done or 1 if
@@ -4776,7 +4973,6 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
 					       u64 last_committed)
 {
 	int ret = 0;
-	struct btrfs_root *root;
 	struct dentry *old_parent = NULL;
 	struct inode *orig_inode = inode;
 
@@ -4808,14 +5004,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
 			BTRFS_I(inode)->logged_trans = trans->transid;
 		smp_mb();
 
-		if (BTRFS_I(inode)->last_unlink_trans > last_committed) {
-			root = BTRFS_I(inode)->root;
-
-			/*
-			 * make sure any commits to the log are forced
-			 * to be full commits
-			 */
-			btrfs_set_log_full_commit(root->fs_info, trans);
+		if (btrfs_must_commit_transaction(trans, inode)) {
 			ret = 1;
 			break;
 		}
@@ -4974,6 +5163,9 @@ process_leaf:
 			btrfs_release_path(path);
 			ret = btrfs_log_inode(trans, root, di_inode,
 					      log_mode, 0, LLONG_MAX, ctx);
+			if (!ret &&
+			    btrfs_must_commit_transaction(trans, di_inode))
+				ret = 1;
 			iput(di_inode);
 			if (ret)
 				goto next_dir_inode;
@@ -5088,6 +5280,9 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans,
 
 			ret = btrfs_log_inode(trans, root, dir_inode,
 					      LOG_INODE_ALL, 0, LLONG_MAX, ctx);
+			if (!ret &&
+			    btrfs_must_commit_transaction(trans, dir_inode))
+				ret = 1;
 			iput(dir_inode);
 			if (ret)
 				goto out;
@@ -5439,6 +5634,9 @@ error:
  * They revolve around files there were unlinked from the directory, and
  * this function updates the parent directory so that a full commit is
  * properly done if it is fsync'd later after the unlinks are done.
+ *
+ * Must be called before the unlink operations (updates to the subvolume tree,
+ * inodes, etc) are done.
  */
 void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans,
 			     struct inode *dir, struct inode *inode,
@@ -5454,8 +5652,11 @@ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans,
 	 * into the file.  When the file is logged we check it and
 	 * don't log the parents if the file is fully on disk.
 	 */
-	if (S_ISREG(inode->i_mode))
+	if (S_ISREG(inode->i_mode)) {
+		mutex_lock(&BTRFS_I(inode)->log_mutex);
 		BTRFS_I(inode)->last_unlink_trans = trans->transid;
+		mutex_unlock(&BTRFS_I(inode)->log_mutex);
+	}
 
 	/*
 	 * if this directory was already logged any new
@@ -5486,7 +5687,29 @@ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans,
 	return;
 
 record:
+	mutex_lock(&BTRFS_I(dir)->log_mutex);
 	BTRFS_I(dir)->last_unlink_trans = trans->transid;
+	mutex_unlock(&BTRFS_I(dir)->log_mutex);
+}
+
+/*
+ * Make sure that if someone attempts to fsync the parent directory of a deleted
+ * snapshot, it ends up triggering a transaction commit. This is to guarantee
+ * that after replaying the log tree of the parent directory's root we will not
+ * see the snapshot anymore and at log replay time we will not see any log tree
+ * corresponding to the deleted snapshot's root, which could lead to replaying
+ * it after replaying the log tree of the parent directory (which would replay
+ * the snapshot delete operation).
+ *
+ * Must be called before the actual snapshot destroy operation (updates to the
+ * parent root and tree of tree roots trees, etc) are done.
+ */
+void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans,
+				   struct inode *dir)
+{
+	mutex_lock(&BTRFS_I(dir)->log_mutex);
+	BTRFS_I(dir)->last_unlink_trans = trans->transid;
+	mutex_unlock(&BTRFS_I(dir)->log_mutex);
 }
 
 /*
diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h
index 6916a781ea02..a9f1b75d080d 100644
--- a/fs/btrfs/tree-log.h
+++ b/fs/btrfs/tree-log.h
@@ -79,6 +79,8 @@ int btrfs_pin_log_trans(struct btrfs_root *root);
 void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans,
 			     struct inode *dir, struct inode *inode,
 			     int for_rename);
+void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans,
+				   struct inode *dir);
 int btrfs_log_new_name(struct btrfs_trans_handle *trans,
 			struct inode *inode, struct inode *old_dir,
 			struct dentry *parent);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 17ed76d18eb6..bd0f45fb38c4 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -108,7 +108,7 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
 	},
 };
 
-const u64 const btrfs_raid_group[BTRFS_NR_RAID_TYPES] = {
+const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES] = {
 	[BTRFS_RAID_RAID10] = BTRFS_BLOCK_GROUP_RAID10,
 	[BTRFS_RAID_RAID1]  = BTRFS_BLOCK_GROUP_RAID1,
 	[BTRFS_RAID_DUP]    = BTRFS_BLOCK_GROUP_DUP,
@@ -125,6 +125,7 @@ static int btrfs_relocate_sys_chunks(struct btrfs_root *root);
 static void __btrfs_reset_dev_stats(struct btrfs_device *dev);
 static void btrfs_dev_stat_print_on_error(struct btrfs_device *dev);
 static void btrfs_dev_stat_print_on_load(struct btrfs_device *device);
+static void btrfs_close_one_device(struct btrfs_device *device);
 
 DEFINE_MUTEX(uuid_mutex);
 static LIST_HEAD(fs_uuids);
@@ -137,7 +138,7 @@ static struct btrfs_fs_devices *__alloc_fs_devices(void)
 {
 	struct btrfs_fs_devices *fs_devs;
 
-	fs_devs = kzalloc(sizeof(*fs_devs), GFP_NOFS);
+	fs_devs = kzalloc(sizeof(*fs_devs), GFP_KERNEL);
 	if (!fs_devs)
 		return ERR_PTR(-ENOMEM);
 
@@ -219,7 +220,7 @@ static struct btrfs_device *__alloc_device(void)
 {
 	struct btrfs_device *dev;
 
-	dev = kzalloc(sizeof(*dev), GFP_NOFS);
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
@@ -232,8 +233,9 @@ static struct btrfs_device *__alloc_device(void)
 	spin_lock_init(&dev->reada_lock);
 	atomic_set(&dev->reada_in_flight, 0);
 	atomic_set(&dev->dev_stats_ccnt, 0);
-	INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_WAIT);
-	INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_WAIT);
+	btrfs_device_data_ordered_init(dev);
+	INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
+	INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
 
 	return dev;
 }
@@ -731,7 +733,8 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
 		 * uuid mutex so nothing we touch in here is going to disappear.
 		 */
 		if (orig_dev->name) {
-			name = rcu_string_strdup(orig_dev->name->str, GFP_NOFS);
+			name = rcu_string_strdup(orig_dev->name->str,
+					GFP_KERNEL);
 			if (!name) {
 				kfree(device);
 				goto error;
@@ -1022,16 +1025,16 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 	}
 
 	/* make sure our super fits in the device */
-	if (bytenr + PAGE_CACHE_SIZE >= i_size_read(bdev->bd_inode))
+	if (bytenr + PAGE_SIZE >= i_size_read(bdev->bd_inode))
 		goto error_bdev_put;
 
 	/* make sure our super fits in the page */
-	if (sizeof(*disk_super) > PAGE_CACHE_SIZE)
+	if (sizeof(*disk_super) > PAGE_SIZE)
 		goto error_bdev_put;
 
 	/* make sure our super doesn't straddle pages on disk */
-	index = bytenr >> PAGE_CACHE_SHIFT;
-	if ((bytenr + sizeof(*disk_super) - 1) >> PAGE_CACHE_SHIFT != index)
+	index = bytenr >> PAGE_SHIFT;
+	if ((bytenr + sizeof(*disk_super) - 1) >> PAGE_SHIFT != index)
 		goto error_bdev_put;
 
 	/* pull in the page with our super */
@@ -1044,7 +1047,7 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 	p = kmap(page);
 
 	/* align our pointer to the offset of the super block */
-	disk_super = p + (bytenr & ~PAGE_CACHE_MASK);
+	disk_super = p + (bytenr & ~PAGE_MASK);
 
 	if (btrfs_super_bytenr(disk_super) != bytenr ||
 	    btrfs_super_magic(disk_super) != BTRFS_MAGIC)
@@ -1072,7 +1075,7 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 
 error_unmap:
 	kunmap(page);
-	page_cache_release(page);
+	put_page(page);
 
 error_bdev_put:
 	blkdev_put(bdev, flags);
@@ -1102,7 +1105,7 @@ int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
-	path->reada = 2;
+	path->reada = READA_FORWARD;
 
 	key.objectid = device->devid;
 	key.offset = start;
@@ -1182,7 +1185,7 @@ again:
 		struct map_lookup *map;
 		int i;
 
-		map = (struct map_lookup *)em->bdev;
+		map = em->map_lookup;
 		for (i = 0; i < map->num_stripes; i++) {
 			u64 end;
 
@@ -1257,6 +1260,15 @@ int find_free_dev_extent_start(struct btrfs_transaction *transaction,
 	int ret;
 	int slot;
 	struct extent_buffer *l;
+	u64 min_search_start;
+
+	/*
+	 * We don't want to overwrite the superblock on the drive nor any area
+	 * used by the boot loader (grub for example), so we make sure to start
+	 * at an offset of at least 1MB.
+	 */
+	min_search_start = max(root->fs_info->alloc_start, 1024ull * 1024);
+	search_start = max(search_start, min_search_start);
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -1271,7 +1283,7 @@ again:
 		goto out;
 	}
 
-	path->reada = 2;
+	path->reada = READA_FORWARD;
 	path->search_commit_root = 1;
 	path->skip_locking = 1;
 
@@ -1397,18 +1409,9 @@ int find_free_dev_extent(struct btrfs_trans_handle *trans,
 			 struct btrfs_device *device, u64 num_bytes,
 			 u64 *start, u64 *len)
 {
-	struct btrfs_root *root = device->dev_root;
-	u64 search_start;
-
 	/* FIXME use last free of some kind */
-
-	/*
-	 * we don't want to overwrite the superblock on the drive,
-	 * so we make sure to start at an offset of at least 1MB
-	 */
-	search_start = max(root->fs_info->alloc_start, 1024ull * 1024);
 	return find_free_dev_extent_start(trans->transaction, device,
-					  num_bytes, search_start, start, len);
+					  num_bytes, 0, start, len);
 }
 
 static int btrfs_free_dev_extent(struct btrfs_trans_handle *trans,
@@ -1642,7 +1645,6 @@ static void update_dev_time(char *path_name)
 		return;
 	file_update_time(filp);
 	filp_close(filp, NULL);
-	return;
 }
 
 static int btrfs_rm_dev_item(struct btrfs_root *root,
@@ -1713,12 +1715,12 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 	} while (read_seqretry(&root->fs_info->profiles_lock, seq));
 
 	num_devices = root->fs_info->fs_devices->num_devices;
-	btrfs_dev_replace_lock(&root->fs_info->dev_replace);
+	btrfs_dev_replace_lock(&root->fs_info->dev_replace, 0);
 	if (btrfs_dev_replace_is_ongoing(&root->fs_info->dev_replace)) {
 		WARN_ON(num_devices < 1);
 		num_devices--;
 	}
-	btrfs_dev_replace_unlock(&root->fs_info->dev_replace);
+	btrfs_dev_replace_unlock(&root->fs_info->dev_replace, 0);
 
 	if ((all_avail & BTRFS_BLOCK_GROUP_RAID10) && num_devices <= 4) {
 		ret = BTRFS_ERROR_DEV_RAID10_MIN_NOT_MET;
@@ -1973,8 +1975,7 @@ void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info,
 	if (srcdev->writeable) {
 		fs_devices->rw_devices--;
 		/* zero out the old super if it is writable */
-		btrfs_scratch_superblocks(srcdev->bdev,
-					rcu_str_deref(srcdev->name));
+		btrfs_scratch_superblocks(srcdev->bdev, srcdev->name->str);
 	}
 
 	if (srcdev->bdev)
@@ -2024,8 +2025,7 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 	btrfs_sysfs_rm_device_link(fs_info->fs_devices, tgtdev);
 
 	if (tgtdev->bdev) {
-		btrfs_scratch_superblocks(tgtdev->bdev,
-					rcu_str_deref(tgtdev->name));
+		btrfs_scratch_superblocks(tgtdev->bdev, tgtdev->name->str);
 		fs_info->fs_devices->open_devices--;
 	}
 	fs_info->fs_devices->num_devices--;
@@ -2288,7 +2288,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 		goto error;
 	}
 
-	name = rcu_string_strdup(device_path, GFP_NOFS);
+	name = rcu_string_strdup(device_path, GFP_KERNEL);
 	if (!name) {
 		kfree(device);
 		ret = -ENOMEM;
@@ -2749,7 +2749,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 	    em->start + em->len < chunk_offset) {
 		/*
 		 * This is a logic error, but we don't want to just rely on the
-		 * user having built with ASSERT enabled, so if ASSERT doens't
+		 * user having built with ASSERT enabled, so if ASSERT doesn't
 		 * do anything we still error out.
 		 */
 		ASSERT(0);
@@ -2757,7 +2757,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 			free_extent_map(em);
 		return -EINVAL;
 	}
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	lock_chunks(root->fs_info->chunk_root);
 	check_system_chunk(trans, extent_root, map->type);
 	unlock_chunks(root->fs_info->chunk_root);
@@ -2853,7 +2853,8 @@ static int btrfs_relocate_chunk(struct btrfs_root *root, u64 chunk_offset)
 	if (ret)
 		return ret;
 
-	trans = btrfs_start_transaction(root, 0);
+	trans = btrfs_start_trans_remove_block_group(root->fs_info,
+						     chunk_offset);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
 		btrfs_std_error(root->fs_info, ret, NULL);
@@ -2966,7 +2967,7 @@ static int insert_balance_item(struct btrfs_root *root,
 	}
 
 	key.objectid = BTRFS_BALANCE_OBJECTID;
-	key.type = BTRFS_BALANCE_ITEM_KEY;
+	key.type = BTRFS_TEMPORARY_ITEM_KEY;
 	key.offset = 0;
 
 	ret = btrfs_insert_empty_item(trans, root, path, &key,
@@ -3015,7 +3016,7 @@ static int del_balance_item(struct btrfs_root *root)
 	}
 
 	key.objectid = BTRFS_BALANCE_OBJECTID;
-	key.type = BTRFS_BALANCE_ITEM_KEY;
+	key.type = BTRFS_TEMPORARY_ITEM_KEY;
 	key.offset = 0;
 
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
@@ -3123,7 +3124,7 @@ static int chunk_profiles_filter(u64 chunk_type,
 	return 1;
 }
 
-static int chunk_usage_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset,
+static int chunk_usage_range_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset,
 			      struct btrfs_balance_args *bargs)
 {
 	struct btrfs_block_group_cache *cache;
@@ -3156,7 +3157,7 @@ static int chunk_usage_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset,
 	return ret;
 }
 
-static int chunk_usage_range_filter(struct btrfs_fs_info *fs_info,
+static int chunk_usage_filter(struct btrfs_fs_info *fs_info,
 		u64 chunk_offset, struct btrfs_balance_args *bargs)
 {
 	struct btrfs_block_group_cache *cache;
@@ -3400,13 +3401,14 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info)
 	u32 count_data = 0;
 	u32 count_meta = 0;
 	u32 count_sys = 0;
+	int chunk_reserved = 0;
 
 	/* step one make some room on all the devices */
 	devices = &fs_info->fs_devices->devices;
 	list_for_each_entry(device, devices, dev_list) {
 		old_size = btrfs_device_get_total_bytes(device);
 		size_to_free = div_factor(old_size, 1);
-		size_to_free = min(size_to_free, (u64)1 * 1024 * 1024);
+		size_to_free = min_t(u64, size_to_free, SZ_1M);
 		if (!device->writeable ||
 		    btrfs_device_get_total_bytes(device) -
 		    btrfs_device_get_bytes_used(device) > size_to_free ||
@@ -3501,6 +3503,7 @@ again:
 
 		ret = should_balance_chunk(chunk_root, leaf, chunk,
 					   found_key.offset);
+
 		btrfs_release_path(path);
 		if (!ret) {
 			mutex_unlock(&fs_info->delete_unused_bgs_mutex);
@@ -3537,6 +3540,24 @@ again:
 			goto loop;
 		}
 
+		if ((chunk_type & BTRFS_BLOCK_GROUP_DATA) && !chunk_reserved) {
+			trans = btrfs_start_transaction(chunk_root, 0);
+			if (IS_ERR(trans)) {
+				mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+				ret = PTR_ERR(trans);
+				goto error;
+			}
+
+			ret = btrfs_force_chunk_alloc(trans, chunk_root,
+						      BTRFS_BLOCK_GROUP_DATA);
+			btrfs_end_transaction(trans, chunk_root);
+			if (ret < 0) {
+				mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+				goto error;
+			}
+			chunk_reserved = 1;
+		}
+
 		ret = btrfs_relocate_chunk(chunk_root,
 					   found_key.offset);
 		mutex_unlock(&fs_info->delete_unused_bgs_mutex);
@@ -3666,12 +3687,12 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 	}
 
 	num_devices = fs_info->fs_devices->num_devices;
-	btrfs_dev_replace_lock(&fs_info->dev_replace);
+	btrfs_dev_replace_lock(&fs_info->dev_replace, 0);
 	if (btrfs_dev_replace_is_ongoing(&fs_info->dev_replace)) {
 		BUG_ON(num_devices < 1);
 		num_devices--;
 	}
-	btrfs_dev_replace_unlock(&fs_info->dev_replace);
+	btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
 	allowed = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
 	if (num_devices == 1)
 		allowed |= BTRFS_BLOCK_GROUP_DUP;
@@ -3704,14 +3725,6 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 		goto out;
 	}
 
-	/* allow dup'ed data chunks only in mixed mode */
-	if (!mixed && (bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
-	    (bctl->data.target & BTRFS_BLOCK_GROUP_DUP)) {
-		btrfs_err(fs_info, "dup for data is not allowed");
-		ret = -EINVAL;
-		goto out;
-	}
-
 	/* allow to reduce meta or sys integrity only if force set */
 	allowed = BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 |
 			BTRFS_BLOCK_GROUP_RAID10 |
@@ -3737,6 +3750,13 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 		}
 	} while (read_seqretry(&fs_info->profiles_lock, seq));
 
+	if (btrfs_get_num_tolerated_disk_barrier_failures(bctl->meta.target) <
+		btrfs_get_num_tolerated_disk_barrier_failures(bctl->data.target)) {
+		btrfs_warn(fs_info,
+	"metadata profile 0x%llx has lower redundancy than data profile 0x%llx",
+			bctl->meta.target, bctl->data.target);
+	}
+
 	if (bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) {
 		fs_info->num_tolerated_disk_barrier_failures = min(
 			btrfs_calc_num_tolerated_disk_barrier_failures(fs_info),
@@ -3848,7 +3868,7 @@ int btrfs_recover_balance(struct btrfs_fs_info *fs_info)
 		return -ENOMEM;
 
 	key.objectid = BTRFS_BALANCE_OBJECTID;
-	key.type = BTRFS_BALANCE_ITEM_KEY;
+	key.type = BTRFS_TEMPORARY_ITEM_KEY;
 	key.offset = 0;
 
 	ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0);
@@ -4099,7 +4119,7 @@ out:
  * Callback for btrfs_uuid_tree_iterate().
  * returns:
  * 0	check succeeded, the entry is not outdated.
- * < 0	if an error occured.
+ * < 0	if an error occurred.
  * > 0	if the check failed, which means the caller shall remove the entry.
  */
 static int btrfs_check_uuid_tree_entry(struct btrfs_fs_info *fs_info,
@@ -4249,7 +4269,7 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size)
 	if (!path)
 		return -ENOMEM;
 
-	path->reada = 2;
+	path->reada = READA_FORWARD;
 
 	lock_chunks(root);
 
@@ -4441,7 +4461,7 @@ static int btrfs_cmp_device_info(const void *a, const void *b)
 static u32 find_raid56_stripe_len(u32 data_devices, u32 dev_stripe_target)
 {
 	/* TODO allow them to set a preferred stripe size */
-	return 64 * 1024;
+	return SZ_64K;
 }
 
 static void check_raid56_incompat_flag(struct btrfs_fs_info *info, u64 type)
@@ -4509,21 +4529,21 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	ncopies = btrfs_raid_array[index].ncopies;
 
 	if (type & BTRFS_BLOCK_GROUP_DATA) {
-		max_stripe_size = 1024 * 1024 * 1024;
+		max_stripe_size = SZ_1G;
 		max_chunk_size = 10 * max_stripe_size;
 		if (!devs_max)
 			devs_max = BTRFS_MAX_DEVS(info->chunk_root);
 	} else if (type & BTRFS_BLOCK_GROUP_METADATA) {
 		/* for larger filesystems, use larger metadata chunks */
-		if (fs_devices->total_rw_bytes > 50ULL * 1024 * 1024 * 1024)
-			max_stripe_size = 1024 * 1024 * 1024;
+		if (fs_devices->total_rw_bytes > 50ULL * SZ_1G)
+			max_stripe_size = SZ_1G;
 		else
-			max_stripe_size = 256 * 1024 * 1024;
+			max_stripe_size = SZ_256M;
 		max_chunk_size = max_stripe_size;
 		if (!devs_max)
 			devs_max = BTRFS_MAX_DEVS(info->chunk_root);
 	} else if (type & BTRFS_BLOCK_GROUP_SYSTEM) {
-		max_stripe_size = 32 * 1024 * 1024;
+		max_stripe_size = SZ_32M;
 		max_chunk_size = 2 * max_stripe_size;
 		if (!devs_max)
 			devs_max = BTRFS_MAX_DEVS_SYS_CHUNK;
@@ -4700,7 +4720,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 		goto error;
 	}
 	set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
-	em->bdev = (struct block_device *)map;
+	em->map_lookup = map;
 	em->start = start;
 	em->len = num_bytes;
 	em->block_start = 0;
@@ -4774,7 +4794,7 @@ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
 	u64 dev_offset;
 	u64 stripe_size;
 	int i = 0;
-	int ret;
+	int ret = 0;
 
 	em_tree = &extent_root->fs_info->mapping_tree.map_tree;
 	read_lock(&em_tree->lock);
@@ -4795,7 +4815,7 @@ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
 		return -EINVAL;
 	}
 
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	item_size = btrfs_chunk_item_size(map->num_stripes);
 	stripe_size = em->orig_block_len;
 
@@ -4805,20 +4825,32 @@ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 
+	/*
+	 * Take the device list mutex to prevent races with the final phase of
+	 * a device replace operation that replaces the device object associated
+	 * with the map's stripes, because the device object's id can change
+	 * at any time during that final phase of the device replace operation
+	 * (dev-replace.c:btrfs_dev_replace_finishing()).
+	 */
+	mutex_lock(&chunk_root->fs_info->fs_devices->device_list_mutex);
 	for (i = 0; i < map->num_stripes; i++) {
 		device = map->stripes[i].dev;
 		dev_offset = map->stripes[i].physical;
 
 		ret = btrfs_update_device(trans, device);
 		if (ret)
-			goto out;
+			break;
 		ret = btrfs_alloc_dev_extent(trans, device,
 					     chunk_root->root_key.objectid,
 					     BTRFS_FIRST_CHUNK_TREE_OBJECTID,
 					     chunk_offset, dev_offset,
 					     stripe_size);
 		if (ret)
-			goto out;
+			break;
+	}
+	if (ret) {
+		mutex_unlock(&chunk_root->fs_info->fs_devices->device_list_mutex);
+		goto out;
 	}
 
 	stripe = &chunk->stripe;
@@ -4831,6 +4863,7 @@ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
 		memcpy(stripe->dev_uuid, device->uuid, BTRFS_UUID_SIZE);
 		stripe++;
 	}
+	mutex_unlock(&chunk_root->fs_info->fs_devices->device_list_mutex);
 
 	btrfs_set_stack_chunk_length(chunk, chunk_size);
 	btrfs_set_stack_chunk_owner(chunk, extent_root->root_key.objectid);
@@ -4937,7 +4970,7 @@ int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset)
 	if (!em)
 		return 1;
 
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	for (i = 0; i < map->num_stripes; i++) {
 		if (map->stripes[i].dev->missing) {
 			miss_ndevs++;
@@ -5017,7 +5050,7 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 		return 1;
 	}
 
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	if (map->type & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1))
 		ret = map->num_stripes;
 	else if (map->type & BTRFS_BLOCK_GROUP_RAID10)
@@ -5030,10 +5063,10 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 		ret = 1;
 	free_extent_map(em);
 
-	btrfs_dev_replace_lock(&fs_info->dev_replace);
+	btrfs_dev_replace_lock(&fs_info->dev_replace, 0);
 	if (btrfs_dev_replace_is_ongoing(&fs_info->dev_replace))
 		ret++;
-	btrfs_dev_replace_unlock(&fs_info->dev_replace);
+	btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
 
 	return ret;
 }
@@ -5053,7 +5086,7 @@ unsigned long btrfs_full_stripe_len(struct btrfs_root *root,
 	BUG_ON(!em);
 
 	BUG_ON(em->start > logical || em->start + em->len < logical);
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
 		len = map->stripe_len * nr_data_stripes(map);
 	free_extent_map(em);
@@ -5074,7 +5107,7 @@ int btrfs_is_parity_mirror(struct btrfs_mapping_tree *map_tree,
 	BUG_ON(!em);
 
 	BUG_ON(em->start > logical || em->start + em->len < logical);
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
 		ret = 1;
 	free_extent_map(em);
@@ -5233,7 +5266,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 		return -EINVAL;
 	}
 
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	offset = logical - em->start;
 
 	stripe_len = map->stripe_len;
@@ -5293,10 +5326,12 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 	if (!bbio_ret)
 		goto out;
 
-	btrfs_dev_replace_lock(dev_replace);
+	btrfs_dev_replace_lock(dev_replace, 0);
 	dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(dev_replace);
 	if (!dev_replace_is_ongoing)
-		btrfs_dev_replace_unlock(dev_replace);
+		btrfs_dev_replace_unlock(dev_replace, 0);
+	else
+		btrfs_dev_replace_set_lock_blocking(dev_replace);
 
 	if (dev_replace_is_ongoing && mirror_num == map->num_stripes + 1 &&
 	    !(rw & (REQ_WRITE | REQ_DISCARD | REQ_GET_READ_MIRRORS)) &&
@@ -5347,35 +5382,33 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 		 * target drive.
 		 */
 		for (i = 0; i < tmp_num_stripes; i++) {
-			if (tmp_bbio->stripes[i].dev->devid == srcdev_devid) {
-				/*
-				 * In case of DUP, in order to keep it
-				 * simple, only add the mirror with the
-				 * lowest physical address
-				 */
-				if (found &&
-				    physical_of_found <=
-				     tmp_bbio->stripes[i].physical)
-					continue;
-				index_srcdev = i;
-				found = 1;
-				physical_of_found =
-					tmp_bbio->stripes[i].physical;
-			}
+			if (tmp_bbio->stripes[i].dev->devid != srcdev_devid)
+				continue;
+
+			/*
+			 * In case of DUP, in order to keep it simple, only add
+			 * the mirror with the lowest physical address
+			 */
+			if (found &&
+			    physical_of_found <= tmp_bbio->stripes[i].physical)
+				continue;
+
+			index_srcdev = i;
+			found = 1;
+			physical_of_found = tmp_bbio->stripes[i].physical;
 		}
 
-		if (found) {
-			mirror_num = index_srcdev + 1;
-			patch_the_first_stripe_for_dev_replace = 1;
-			physical_to_patch_in_first_stripe = physical_of_found;
-		} else {
+		btrfs_put_bbio(tmp_bbio);
+
+		if (!found) {
 			WARN_ON(1);
 			ret = -EIO;
-			btrfs_put_bbio(tmp_bbio);
 			goto out;
 		}
 
-		btrfs_put_bbio(tmp_bbio);
+		mirror_num = index_srcdev + 1;
+		patch_the_first_stripe_for_dev_replace = 1;
+		physical_to_patch_in_first_stripe = physical_of_found;
 	} else if (mirror_num > map->num_stripes) {
 		mirror_num = 0;
 	}
@@ -5721,8 +5754,10 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 		bbio->mirror_num = map->num_stripes + 1;
 	}
 out:
-	if (dev_replace_is_ongoing)
-		btrfs_dev_replace_unlock(dev_replace);
+	if (dev_replace_is_ongoing) {
+		btrfs_dev_replace_clear_lock_blocking(dev_replace);
+		btrfs_dev_replace_unlock(dev_replace, 0);
+	}
 	free_extent_map(em);
 	return ret;
 }
@@ -5775,7 +5810,7 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
 		free_extent_map(em);
 		return -EIO;
 	}
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 
 	length = em->len;
 	rmap_len = map->stripe_len;
@@ -6038,7 +6073,8 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
 	bbio->fs_info = root->fs_info;
 	atomic_set(&bbio->stripes_pending, bbio->num_stripes);
 
-	if (bbio->raid_map) {
+	if ((bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) &&
+	    ((rw & WRITE) || (mirror_num > 1))) {
 		/* In this case, map_length has been set to the length of
 		   a single stripe; not the whole write */
 		if (rw & WRITE) {
@@ -6179,6 +6215,7 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 	struct extent_map *em;
 	u64 logical;
 	u64 length;
+	u64 stripe_len;
 	u64 devid;
 	u8 uuid[BTRFS_UUID_SIZE];
 	int num_stripes;
@@ -6187,6 +6224,37 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 
 	logical = key->offset;
 	length = btrfs_chunk_length(leaf, chunk);
+	stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
+	num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
+	/* Validation check */
+	if (!num_stripes) {
+		btrfs_err(root->fs_info, "invalid chunk num_stripes: %u",
+			  num_stripes);
+		return -EIO;
+	}
+	if (!IS_ALIGNED(logical, root->sectorsize)) {
+		btrfs_err(root->fs_info,
+			  "invalid chunk logical %llu", logical);
+		return -EIO;
+	}
+	if (!length || !IS_ALIGNED(length, root->sectorsize)) {
+		btrfs_err(root->fs_info,
+			"invalid chunk length %llu", length);
+		return -EIO;
+	}
+	if (!is_power_of_2(stripe_len)) {
+		btrfs_err(root->fs_info, "invalid chunk stripe length: %llu",
+			  stripe_len);
+		return -EIO;
+	}
+	if (~(BTRFS_BLOCK_GROUP_TYPE_MASK | BTRFS_BLOCK_GROUP_PROFILE_MASK) &
+	    btrfs_chunk_type(leaf, chunk)) {
+		btrfs_err(root->fs_info, "unrecognized chunk type: %llu",
+			  ~(BTRFS_BLOCK_GROUP_TYPE_MASK |
+			    BTRFS_BLOCK_GROUP_PROFILE_MASK) &
+			  btrfs_chunk_type(leaf, chunk));
+		return -EIO;
+	}
 
 	read_lock(&map_tree->map_tree.lock);
 	em = lookup_extent_mapping(&map_tree->map_tree, logical, 1);
@@ -6203,7 +6271,6 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 	em = alloc_extent_map();
 	if (!em)
 		return -ENOMEM;
-	num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
 	map = kmalloc(map_lookup_size(num_stripes), GFP_NOFS);
 	if (!map) {
 		free_extent_map(em);
@@ -6211,7 +6278,7 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 	}
 
 	set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
-	em->bdev = (struct block_device *)map;
+	em->map_lookup = map;
 	em->start = logical;
 	em->len = length;
 	em->orig_start = 0;
@@ -6446,11 +6513,11 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 	sb = btrfs_find_create_tree_block(root, BTRFS_SUPER_INFO_OFFSET);
 	if (!sb)
 		return -ENOMEM;
-	btrfs_set_buffer_uptodate(sb);
+	set_extent_buffer_uptodate(sb);
 	btrfs_set_buffer_lockdep_class(root->root_key.objectid, sb, 0);
 	/*
 	 * The sb extent buffer is artifical and just used to read the system array.
-	 * btrfs_set_buffer_uptodate() call does not properly mark all it's
+	 * set_extent_buffer_uptodate() call does not properly mark all it's
 	 * pages up-to-date when the page is larger: extent does not cover the
 	 * whole page and consequently check_page_uptodate does not find all
 	 * the page's extents up-to-date (the hole beyond sb),
@@ -6460,7 +6527,7 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 	 * but sb spans only this function. Add an explicit SetPageUptodate call
 	 * to silence the warning eg. on PowerPC 64.
 	 */
-	if (PAGE_CACHE_SIZE > BTRFS_SUPER_INFO_SIZE)
+	if (PAGE_SIZE > BTRFS_SUPER_INFO_SIZE)
 		SetPageUptodate(sb->pages[0]);
 
 	write_extent_buffer(sb, super_copy, 0, BTRFS_SUPER_INFO_SIZE);
@@ -6493,6 +6560,14 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 				goto out_short_read;
 
 			num_stripes = btrfs_chunk_num_stripes(sb, chunk);
+			if (!num_stripes) {
+				printk(KERN_ERR
+	    "BTRFS: invalid number of stripes %u in sys_array at offset %u\n",
+					num_stripes, cur_offset);
+				ret = -EIO;
+				break;
+			}
+
 			len = btrfs_chunk_item_size(num_stripes);
 			if (cur_offset + len > array_size)
 				goto out_short_read;
@@ -6501,6 +6576,9 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 			if (ret)
 				break;
 		} else {
+			printk(KERN_ERR
+		"BTRFS: unexpected item type %u in sys_array at offset %u\n",
+				(u32)key.type, cur_offset);
 			ret = -EIO;
 			break;
 		}
@@ -6632,8 +6710,8 @@ int btrfs_init_dev_stats(struct btrfs_fs_info *fs_info)
 		int item_size;
 		struct btrfs_dev_stats_item *ptr;
 
-		key.objectid = 0;
-		key.type = BTRFS_DEV_STATS_KEY;
+		key.objectid = BTRFS_DEV_STATS_OBJECTID;
+		key.type = BTRFS_PERSISTENT_ITEM_KEY;
 		key.offset = device->devid;
 		ret = btrfs_search_slot(NULL, dev_root, &key, path, 0, 0);
 		if (ret) {
@@ -6680,8 +6758,8 @@ static int update_dev_stat_item(struct btrfs_trans_handle *trans,
 	int ret;
 	int i;
 
-	key.objectid = 0;
-	key.type = BTRFS_DEV_STATS_KEY;
+	key.objectid = BTRFS_DEV_STATS_OBJECTID;
+	key.type = BTRFS_PERSISTENT_ITEM_KEY;
 	key.offset = device->devid;
 
 	path = btrfs_alloc_path();
@@ -6902,7 +6980,7 @@ void btrfs_update_commit_device_bytes_used(struct btrfs_root *root,
 	/* In order to kick the device replace finish process */
 	lock_chunks(root);
 	list_for_each_entry(em, &transaction->pending_chunks, list) {
-		map = (struct map_lookup *)em->bdev;
+		map = em->map_lookup;
 
 		for (i = 0; i < map->num_stripes; i++) {
 			dev = map->stripes[i].dev;
@@ -6930,7 +7008,7 @@ void btrfs_reset_fs_info_ptr(struct btrfs_fs_info *fs_info)
 	}
 }
 
-void btrfs_close_one_device(struct btrfs_device *device)
+static void btrfs_close_one_device(struct btrfs_device *device)
 {
 	struct btrfs_fs_devices *fs_devices = device->fs_devices;
 	struct btrfs_device *new_device;
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index ec5712372732..1939ebde63df 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -26,7 +26,7 @@
 
 extern struct mutex uuid_mutex;
 
-#define BTRFS_STRIPE_LEN	(64 * 1024)
+#define BTRFS_STRIPE_LEN	SZ_64K
 
 struct buffer_head;
 struct btrfs_pending_bios {
@@ -382,7 +382,7 @@ struct map_lookup {
 #define BTRFS_BALANCE_ARGS_LIMIT	(1ULL << 5)
 #define BTRFS_BALANCE_ARGS_LIMIT_RANGE	(1ULL << 6)
 #define BTRFS_BALANCE_ARGS_STRIPES_RANGE (1ULL << 7)
-#define BTRFS_BALANCE_ARGS_USAGE_RANGE	(1ULL << 8)
+#define BTRFS_BALANCE_ARGS_USAGE_RANGE	(1ULL << 10)
 
 #define BTRFS_BALANCE_ARGS_MASK			\
 	(BTRFS_BALANCE_ARGS_PROFILES |		\
@@ -566,6 +566,5 @@ static inline void unlock_chunks(struct btrfs_root *root)
 struct list_head *btrfs_get_fs_uuids(void);
 void btrfs_set_fs_info_ptr(struct btrfs_fs_info *fs_info);
 void btrfs_reset_fs_info_ptr(struct btrfs_fs_info *fs_info);
-void btrfs_close_one_device(struct btrfs_device *device);
 
 #endif
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 6f518c90e1c1..145d2b89e62d 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -126,7 +126,7 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
 	 * locks the inode's i_mutex before calling setxattr or removexattr.
 	 */
 	if (flags & XATTR_REPLACE) {
-		ASSERT(mutex_is_locked(&inode->i_mutex));
+		ASSERT(inode_is_locked(inode));
 		di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode),
 					name, name_len, 0);
 		if (!di)
@@ -249,7 +249,7 @@ int __btrfs_setxattr(struct btrfs_trans_handle *trans,
 		goto out;
 
 	inode_inc_iversion(inode);
-	inode->i_ctime = CURRENT_TIME;
+	inode->i_ctime = current_fs_time(inode->i_sb);
 	set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags);
 	ret = btrfs_update_inode(trans, root, inode);
 	BUG_ON(ret);
@@ -260,16 +260,12 @@ out:
 
 ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size)
 {
-	struct btrfs_key key, found_key;
+	struct btrfs_key key;
 	struct inode *inode = d_inode(dentry);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_path *path;
-	struct extent_buffer *leaf;
-	struct btrfs_dir_item *di;
-	int ret = 0, slot;
+	int ret = 0;
 	size_t total_size = 0, size_left = size;
-	unsigned long name_ptr;
-	size_t name_len;
 
 	/*
 	 * ok we want all objects associated with this id.
@@ -283,7 +279,7 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size)
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
-	path->reada = 2;
+	path->reada = READA_FORWARD;
 
 	/* search for our xattrs */
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
@@ -291,6 +287,13 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size)
 		goto err;
 
 	while (1) {
+		struct extent_buffer *leaf;
+		int slot;
+		struct btrfs_dir_item *di;
+		struct btrfs_key found_key;
+		u32 item_size;
+		u32 cur;
+
 		leaf = path->nodes[0];
 		slot = path->slots[0];
 
@@ -313,32 +316,48 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size)
 		/* check to make sure this item is what we want */
 		if (found_key.objectid != key.objectid)
 			break;
-		if (found_key.type != BTRFS_XATTR_ITEM_KEY)
+		if (found_key.type > BTRFS_XATTR_ITEM_KEY)
 			break;
+		if (found_key.type < BTRFS_XATTR_ITEM_KEY)
+			goto next_item;
 
 		di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
-		if (verify_dir_item(root, leaf, di))
-			goto next;
-
-		name_len = btrfs_dir_name_len(leaf, di);
-		total_size += name_len + 1;
+		item_size = btrfs_item_size_nr(leaf, slot);
+		cur = 0;
+		while (cur < item_size) {
+			u16 name_len = btrfs_dir_name_len(leaf, di);
+			u16 data_len = btrfs_dir_data_len(leaf, di);
+			u32 this_len = sizeof(*di) + name_len + data_len;
+			unsigned long name_ptr = (unsigned long)(di + 1);
+
+			if (verify_dir_item(root, leaf, di)) {
+				ret = -EIO;
+				goto err;
+			}
 
-		/* we are just looking for how big our buffer needs to be */
-		if (!size)
-			goto next;
+			total_size += name_len + 1;
+			/*
+			 * We are just looking for how big our buffer needs to
+			 * be.
+			 */
+			if (!size)
+				goto next;
 
-		if (!buffer || (name_len + 1) > size_left) {
-			ret = -ERANGE;
-			goto err;
-		}
+			if (!buffer || (name_len + 1) > size_left) {
+				ret = -ERANGE;
+				goto err;
+			}
 
-		name_ptr = (unsigned long)(di + 1);
-		read_extent_buffer(leaf, buffer, name_ptr, name_len);
-		buffer[name_len] = '\0';
+			read_extent_buffer(leaf, buffer, name_ptr, name_len);
+			buffer[name_len] = '\0';
 
-		size_left -= name_len + 1;
-		buffer += name_len + 1;
+			size_left -= name_len + 1;
+			buffer += name_len + 1;
 next:
+			cur += this_len;
+			di = (struct btrfs_dir_item *)((char *)di + this_len);
+		}
+next_item:
 		path->slots[0]++;
 	}
 	ret = total_size;
@@ -349,137 +368,89 @@ err:
 	return ret;
 }
 
-/*
- * List of handlers for synthetic system.* attributes.  All real ondisk
- * attributes are handled directly.
- */
-const struct xattr_handler *btrfs_xattr_handlers[] = {
-#ifdef CONFIG_BTRFS_FS_POSIX_ACL
-	&posix_acl_access_xattr_handler,
-	&posix_acl_default_xattr_handler,
-#endif
-	NULL,
-};
-
-/*
- * Check if the attribute is in a supported namespace.
- *
- * This is applied after the check for the synthetic attributes in the system
- * namespace.
- */
-static int btrfs_is_valid_xattr(const char *name)
+static int btrfs_xattr_handler_get(const struct xattr_handler *handler,
+				   struct dentry *dentry, const char *name,
+				   void *buffer, size_t size)
 {
-	int len = strlen(name);
-	int prefixlen = 0;
-
-	if (!strncmp(name, XATTR_SECURITY_PREFIX,
-			XATTR_SECURITY_PREFIX_LEN))
-		prefixlen = XATTR_SECURITY_PREFIX_LEN;
-	else if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
-		prefixlen = XATTR_SYSTEM_PREFIX_LEN;
-	else if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN))
-		prefixlen = XATTR_TRUSTED_PREFIX_LEN;
-	else if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN))
-		prefixlen = XATTR_USER_PREFIX_LEN;
-	else if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN))
-		prefixlen = XATTR_BTRFS_PREFIX_LEN;
-	else
-		return -EOPNOTSUPP;
-
-	/*
-	 * The name cannot consist of just prefix
-	 */
-	if (len <= prefixlen)
-		return -EINVAL;
+	struct inode *inode = d_inode(dentry);
 
-	return 0;
+	name = xattr_full_name(handler, name);
+	return __btrfs_getxattr(inode, name, buffer, size);
 }
 
-ssize_t btrfs_getxattr(struct dentry *dentry, const char *name,
-		       void *buffer, size_t size)
+static int btrfs_xattr_handler_set(const struct xattr_handler *handler,
+				   struct dentry *dentry, const char *name,
+				   const void *buffer, size_t size,
+				   int flags)
 {
-	int ret;
+	struct inode *inode = d_inode(dentry);
 
-	/*
-	 * If this is a request for a synthetic attribute in the system.*
-	 * namespace use the generic infrastructure to resolve a handler
-	 * for it via sb->s_xattr.
-	 */
-	if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
-		return generic_getxattr(dentry, name, buffer, size);
+	name = xattr_full_name(handler, name);
+	return __btrfs_setxattr(NULL, inode, name, buffer, size, flags);
+}
 
-	ret = btrfs_is_valid_xattr(name);
-	if (ret)
-		return ret;
-	return __btrfs_getxattr(d_inode(dentry), name, buffer, size);
+static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler,
+					struct dentry *dentry,
+					const char *name, const void *value,
+					size_t size, int flags)
+{
+	name = xattr_full_name(handler, name);
+	return btrfs_set_prop(d_inode(dentry), name, value, size, flags);
 }
 
+static const struct xattr_handler btrfs_security_xattr_handler = {
+	.prefix = XATTR_SECURITY_PREFIX,
+	.get = btrfs_xattr_handler_get,
+	.set = btrfs_xattr_handler_set,
+};
+
+static const struct xattr_handler btrfs_trusted_xattr_handler = {
+	.prefix = XATTR_TRUSTED_PREFIX,
+	.get = btrfs_xattr_handler_get,
+	.set = btrfs_xattr_handler_set,
+};
+
+static const struct xattr_handler btrfs_user_xattr_handler = {
+	.prefix = XATTR_USER_PREFIX,
+	.get = btrfs_xattr_handler_get,
+	.set = btrfs_xattr_handler_set,
+};
+
+static const struct xattr_handler btrfs_btrfs_xattr_handler = {
+	.prefix = XATTR_BTRFS_PREFIX,
+	.get = btrfs_xattr_handler_get,
+	.set = btrfs_xattr_handler_set_prop,
+};
+
+const struct xattr_handler *btrfs_xattr_handlers[] = {
+	&btrfs_security_xattr_handler,
+#ifdef CONFIG_BTRFS_FS_POSIX_ACL
+	&posix_acl_access_xattr_handler,
+	&posix_acl_default_xattr_handler,
+#endif
+	&btrfs_trusted_xattr_handler,
+	&btrfs_user_xattr_handler,
+	&btrfs_btrfs_xattr_handler,
+	NULL,
+};
+
 int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 		   size_t size, int flags)
 {
 	struct btrfs_root *root = BTRFS_I(d_inode(dentry))->root;
-	int ret;
 
-	/*
-	 * The permission on security.* and system.* is not checked
-	 * in permission().
-	 */
 	if (btrfs_root_readonly(root))
 		return -EROFS;
-
-	/*
-	 * If this is a request for a synthetic attribute in the system.*
-	 * namespace use the generic infrastructure to resolve a handler
-	 * for it via sb->s_xattr.
-	 */
-	if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
-		return generic_setxattr(dentry, name, value, size, flags);
-
-	ret = btrfs_is_valid_xattr(name);
-	if (ret)
-		return ret;
-
-	if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN))
-		return btrfs_set_prop(d_inode(dentry), name,
-				      value, size, flags);
-
-	if (size == 0)
-		value = "";  /* empty EA, do not remove */
-
-	return __btrfs_setxattr(NULL, d_inode(dentry), name, value, size,
-				flags);
+	return generic_setxattr(dentry, name, value, size, flags);
 }
 
 int btrfs_removexattr(struct dentry *dentry, const char *name)
 {
 	struct btrfs_root *root = BTRFS_I(d_inode(dentry))->root;
-	int ret;
 
-	/*
-	 * The permission on security.* and system.* is not checked
-	 * in permission().
-	 */
 	if (btrfs_root_readonly(root))
 		return -EROFS;
-
-	/*
-	 * If this is a request for a synthetic attribute in the system.*
-	 * namespace use the generic infrastructure to resolve a handler
-	 * for it via sb->s_xattr.
-	 */
-	if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
-		return generic_removexattr(dentry, name);
-
-	ret = btrfs_is_valid_xattr(name);
-	if (ret)
-		return ret;
-
-	if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN))
-		return btrfs_set_prop(d_inode(dentry), name,
-				      NULL, 0, XATTR_REPLACE);
-
-	return __btrfs_setxattr(NULL, d_inode(dentry), name, NULL, 0,
-				XATTR_REPLACE);
+	return generic_removexattr(dentry, name);
 }
 
 static int btrfs_initxattrs(struct inode *inode,
@@ -492,7 +463,7 @@ static int btrfs_initxattrs(struct inode *inode,
 
 	for (xattr = xattr_array; xattr->name != NULL; xattr++) {
 		name = kmalloc(XATTR_SECURITY_PREFIX_LEN +
-			       strlen(xattr->name) + 1, GFP_NOFS);
+			       strlen(xattr->name) + 1, GFP_KERNEL);
 		if (!name) {
 			err = -ENOMEM;
 			break;
diff --git a/fs/btrfs/xattr.h b/fs/btrfs/xattr.h
index 5049608d1388..96807b3d22f5 100644
--- a/fs/btrfs/xattr.h
+++ b/fs/btrfs/xattr.h
@@ -28,8 +28,6 @@ extern ssize_t __btrfs_getxattr(struct inode *inode, const char *name,
 extern int __btrfs_setxattr(struct btrfs_trans_handle *trans,
 			    struct inode *inode, const char *name,
 			    const void *value, size_t size, int flags);
-extern ssize_t btrfs_getxattr(struct dentry *dentry, const char *name,
-		void *buffer, size_t size);
 extern int btrfs_setxattr(struct dentry *dentry, const char *name,
 		const void *value, size_t size, int flags);
 extern int btrfs_removexattr(struct dentry *dentry, const char *name);
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index 82990b8f872b..88d274e8ecf2 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -59,7 +59,7 @@ static struct list_head *zlib_alloc_workspace(void)
 	workspacesize = max(zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL),
 			zlib_inflate_workspacesize());
 	workspace->strm.workspace = vmalloc(workspacesize);
-	workspace->buf = kmalloc(PAGE_CACHE_SIZE, GFP_NOFS);
+	workspace->buf = kmalloc(PAGE_SIZE, GFP_NOFS);
 	if (!workspace->strm.workspace || !workspace->buf)
 		goto fail;
 
@@ -103,7 +103,7 @@ static int zlib_compress_pages(struct list_head *ws,
 	workspace->strm.total_in = 0;
 	workspace->strm.total_out = 0;
 
-	in_page = find_get_page(mapping, start >> PAGE_CACHE_SHIFT);
+	in_page = find_get_page(mapping, start >> PAGE_SHIFT);
 	data_in = kmap(in_page);
 
 	out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
@@ -117,8 +117,8 @@ static int zlib_compress_pages(struct list_head *ws,
 
 	workspace->strm.next_in = data_in;
 	workspace->strm.next_out = cpage_out;
-	workspace->strm.avail_out = PAGE_CACHE_SIZE;
-	workspace->strm.avail_in = min(len, PAGE_CACHE_SIZE);
+	workspace->strm.avail_out = PAGE_SIZE;
+	workspace->strm.avail_in = min(len, PAGE_SIZE);
 
 	while (workspace->strm.total_in < len) {
 		ret = zlib_deflate(&workspace->strm, Z_SYNC_FLUSH);
@@ -156,7 +156,7 @@ static int zlib_compress_pages(struct list_head *ws,
 			cpage_out = kmap(out_page);
 			pages[nr_pages] = out_page;
 			nr_pages++;
-			workspace->strm.avail_out = PAGE_CACHE_SIZE;
+			workspace->strm.avail_out = PAGE_SIZE;
 			workspace->strm.next_out = cpage_out;
 		}
 		/* we're all done */
@@ -170,14 +170,14 @@ static int zlib_compress_pages(struct list_head *ws,
 
 			bytes_left = len - workspace->strm.total_in;
 			kunmap(in_page);
-			page_cache_release(in_page);
+			put_page(in_page);
 
-			start += PAGE_CACHE_SIZE;
+			start += PAGE_SIZE;
 			in_page = find_get_page(mapping,
-						start >> PAGE_CACHE_SHIFT);
+						start >> PAGE_SHIFT);
 			data_in = kmap(in_page);
 			workspace->strm.avail_in = min(bytes_left,
-							   PAGE_CACHE_SIZE);
+							   PAGE_SIZE);
 			workspace->strm.next_in = data_in;
 		}
 	}
@@ -205,7 +205,7 @@ out:
 
 	if (in_page) {
 		kunmap(in_page);
-		page_cache_release(in_page);
+		put_page(in_page);
 	}
 	return ret;
 }
@@ -223,18 +223,18 @@ static int zlib_decompress_biovec(struct list_head *ws, struct page **pages_in,
 	size_t total_out = 0;
 	unsigned long page_in_index = 0;
 	unsigned long page_out_index = 0;
-	unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_CACHE_SIZE);
+	unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE);
 	unsigned long buf_start;
 	unsigned long pg_offset;
 
 	data_in = kmap(pages_in[page_in_index]);
 	workspace->strm.next_in = data_in;
-	workspace->strm.avail_in = min_t(size_t, srclen, PAGE_CACHE_SIZE);
+	workspace->strm.avail_in = min_t(size_t, srclen, PAGE_SIZE);
 	workspace->strm.total_in = 0;
 
 	workspace->strm.total_out = 0;
 	workspace->strm.next_out = workspace->buf;
-	workspace->strm.avail_out = PAGE_CACHE_SIZE;
+	workspace->strm.avail_out = PAGE_SIZE;
 	pg_offset = 0;
 
 	/* If it's deflate, and it's got no preset dictionary, then
@@ -274,7 +274,7 @@ static int zlib_decompress_biovec(struct list_head *ws, struct page **pages_in,
 		}
 
 		workspace->strm.next_out = workspace->buf;
-		workspace->strm.avail_out = PAGE_CACHE_SIZE;
+		workspace->strm.avail_out = PAGE_SIZE;
 
 		if (workspace->strm.avail_in == 0) {
 			unsigned long tmp;
@@ -288,7 +288,7 @@ static int zlib_decompress_biovec(struct list_head *ws, struct page **pages_in,
 			workspace->strm.next_in = data_in;
 			tmp = srclen - workspace->strm.total_in;
 			workspace->strm.avail_in = min(tmp,
-							   PAGE_CACHE_SIZE);
+							   PAGE_SIZE);
 		}
 	}
 	if (ret != Z_STREAM_END)
@@ -325,7 +325,7 @@ static int zlib_decompress(struct list_head *ws, unsigned char *data_in,
 	workspace->strm.total_in = 0;
 
 	workspace->strm.next_out = workspace->buf;
-	workspace->strm.avail_out = PAGE_CACHE_SIZE;
+	workspace->strm.avail_out = PAGE_SIZE;
 	workspace->strm.total_out = 0;
 	/* If it's deflate, and it's got no preset dictionary, then
 	   we can tell zlib to skip the adler32 check. */
@@ -368,8 +368,8 @@ static int zlib_decompress(struct list_head *ws, unsigned char *data_in,
 		else
 			buf_offset = 0;
 
-		bytes = min(PAGE_CACHE_SIZE - pg_offset,
-			    PAGE_CACHE_SIZE - buf_offset);
+		bytes = min(PAGE_SIZE - pg_offset,
+			    PAGE_SIZE - buf_offset);
 		bytes = min(bytes, bytes_left);
 
 		kaddr = kmap_atomic(dest_page);
@@ -380,7 +380,7 @@ static int zlib_decompress(struct list_head *ws, unsigned char *data_in,
 		bytes_left -= bytes;
 next:
 		workspace->strm.next_out = workspace->buf;
-		workspace->strm.avail_out = PAGE_CACHE_SIZE;
+		workspace->strm.avail_out = PAGE_SIZE;
 	}
 
 	if (ret != Z_STREAM_END && bytes_left != 0)
diff --git a/fs/buffer.c b/fs/buffer.c
index 82283abb2795..af0d9a82a8ed 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -129,18 +129,15 @@ __clear_page_buffers(struct page *page)
 {
 	ClearPagePrivate(page);
 	set_page_private(page, 0);
-	page_cache_release(page);
+	put_page(page);
 }
 
 static void buffer_io_error(struct buffer_head *bh, char *msg)
 {
-	char b[BDEVNAME_SIZE];
-
 	if (!test_bit(BH_Quiet, &bh->b_state))
 		printk_ratelimited(KERN_ERR
-			"Buffer I/O error on dev %s, logical block %llu%s\n",
-			bdevname(bh->b_bdev, b),
-			(unsigned long long)bh->b_blocknr, msg);
+			"Buffer I/O error on dev %pg, logical block %llu%s\n",
+			bh->b_bdev, (unsigned long long)bh->b_blocknr, msg);
 }
 
 /*
@@ -210,7 +207,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
 	struct page *page;
 	int all_mapped = 1;
 
-	index = block >> (PAGE_CACHE_SHIFT - bd_inode->i_blkbits);
+	index = block >> (PAGE_SHIFT - bd_inode->i_blkbits);
 	page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED);
 	if (!page)
 		goto out;
@@ -237,20 +234,18 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
 	 * elsewhere, don't buffer_error if we had some unmapped buffers
 	 */
 	if (all_mapped) {
-		char b[BDEVNAME_SIZE];
-
 		printk("__find_get_block_slow() failed. "
 			"block=%llu, b_blocknr=%llu\n",
 			(unsigned long long)block,
 			(unsigned long long)bh->b_blocknr);
 		printk("b_state=0x%08lx, b_size=%zu\n",
 			bh->b_state, bh->b_size);
-		printk("device %s blocksize: %d\n", bdevname(bdev, b),
+		printk("device %pg blocksize: %d\n", bdev,
 			1 << bd_inode->i_blkbits);
 	}
 out_unlock:
 	spin_unlock(&bd_mapping->private_lock);
-	page_cache_release(page);
+	put_page(page);
 out:
 	return ret;
 }
@@ -531,10 +526,8 @@ repeat:
 
 static void do_thaw_one(struct super_block *sb, void *unused)
 {
-	char b[BDEVNAME_SIZE];
 	while (sb->s_bdev && !thaw_bdev(sb->s_bdev, sb))
-		printk(KERN_WARNING "Emergency Thaw on %s\n",
-		       bdevname(sb->s_bdev, b));
+		printk(KERN_WARNING "Emergency Thaw on %pg\n", sb->s_bdev);
 }
 
 static void do_thaw_all(struct work_struct *work)
@@ -628,17 +621,17 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode);
  * If warn is true, then emit a warning if the page is not uptodate and has
  * not been truncated.
  *
- * The caller must hold mem_cgroup_begin_page_stat() lock.
+ * The caller must hold lock_page_memcg().
  */
 static void __set_page_dirty(struct page *page, struct address_space *mapping,
-			     struct mem_cgroup *memcg, int warn)
+			     int warn)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&mapping->tree_lock, flags);
 	if (page->mapping) {	/* Race with truncate? */
 		WARN_ON_ONCE(warn && !PageUptodate(page));
-		account_page_dirtied(page, mapping, memcg);
+		account_page_dirtied(page, mapping);
 		radix_tree_tag_set(&mapping->page_tree,
 				page_index(page), PAGECACHE_TAG_DIRTY);
 	}
@@ -673,7 +666,6 @@ static void __set_page_dirty(struct page *page, struct address_space *mapping,
 int __set_page_dirty_buffers(struct page *page)
 {
 	int newly_dirty;
-	struct mem_cgroup *memcg;
 	struct address_space *mapping = page_mapping(page);
 
 	if (unlikely(!mapping))
@@ -690,17 +682,17 @@ int __set_page_dirty_buffers(struct page *page)
 		} while (bh != head);
 	}
 	/*
-	 * Use mem_group_begin_page_stat() to keep PageDirty synchronized with
-	 * per-memcg dirty page counters.
+	 * Lock out page->mem_cgroup migration to keep PageDirty
+	 * synchronized with per-memcg dirty page counters.
 	 */
-	memcg = mem_cgroup_begin_page_stat(page);
+	lock_page_memcg(page);
 	newly_dirty = !TestSetPageDirty(page);
 	spin_unlock(&mapping->private_lock);
 
 	if (newly_dirty)
-		__set_page_dirty(page, mapping, memcg, 1);
+		__set_page_dirty(page, mapping, 1);
 
-	mem_cgroup_end_page_stat(memcg);
+	unlock_page_memcg(page);
 
 	if (newly_dirty)
 		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
@@ -999,7 +991,7 @@ grow_dev_page(struct block_device *bdev, sector_t block,
 	int ret = 0;		/* Will call free_more_memory() */
 	gfp_t gfp_mask;
 
-	gfp_mask = (mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS) | gfp;
+	gfp_mask = mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS) | gfp;
 
 	/*
 	 * XXX: __getblk_slow() can not really deal with failure and
@@ -1048,7 +1040,7 @@ done:
 	ret = (block < end_block) ? 1 : -ENXIO;
 failed:
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 	return ret;
 }
 
@@ -1074,12 +1066,10 @@ grow_buffers(struct block_device *bdev, sector_t block, int size, gfp_t gfp)
 	 * pagecache index.  (this comparison is done using sector_t types).
 	 */
 	if (unlikely(index != block >> sizebits)) {
-		char b[BDEVNAME_SIZE];
-
 		printk(KERN_ERR "%s: requested out-of-range block %llu for "
-			"device %s\n",
+			"device %pg\n",
 			__func__, (unsigned long long)block,
-			bdevname(bdev, b));
+			bdev);
 		return -EIO;
 	}
 
@@ -1176,15 +1166,14 @@ void mark_buffer_dirty(struct buffer_head *bh)
 	if (!test_set_buffer_dirty(bh)) {
 		struct page *page = bh->b_page;
 		struct address_space *mapping = NULL;
-		struct mem_cgroup *memcg;
 
-		memcg = mem_cgroup_begin_page_stat(page);
+		lock_page_memcg(page);
 		if (!TestSetPageDirty(page)) {
 			mapping = page_mapping(page);
 			if (mapping)
-				__set_page_dirty(page, mapping, memcg, 0);
+				__set_page_dirty(page, mapping, 0);
 		}
-		mem_cgroup_end_page_stat(memcg);
+		unlock_page_memcg(page);
 		if (mapping)
 			__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 	}
@@ -1544,7 +1533,7 @@ void block_invalidatepage(struct page *page, unsigned int offset,
 	/*
 	 * Check for overflow
 	 */
-	BUG_ON(stop > PAGE_CACHE_SIZE || stop < length);
+	BUG_ON(stop > PAGE_SIZE || stop < length);
 
 	head = page_buffers(page);
 	bh = head;
@@ -1727,7 +1716,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page,
 	blocksize = bh->b_size;
 	bbits = block_size_bits(blocksize);
 
-	block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits);
+	block = (sector_t)page->index << (PAGE_SHIFT - bbits);
 	last_block = (i_size_read(inode) - 1) >> bbits;
 
 	/*
@@ -1905,7 +1894,7 @@ EXPORT_SYMBOL(page_zero_new_buffers);
 int __block_write_begin(struct page *page, loff_t pos, unsigned len,
 		get_block_t *get_block)
 {
-	unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+	unsigned from = pos & (PAGE_SIZE - 1);
 	unsigned to = from + len;
 	struct inode *inode = page->mapping->host;
 	unsigned block_start, block_end;
@@ -1915,15 +1904,15 @@ int __block_write_begin(struct page *page, loff_t pos, unsigned len,
 	struct buffer_head *bh, *head, *wait[2], **wait_bh=wait;
 
 	BUG_ON(!PageLocked(page));
-	BUG_ON(from > PAGE_CACHE_SIZE);
-	BUG_ON(to > PAGE_CACHE_SIZE);
+	BUG_ON(from > PAGE_SIZE);
+	BUG_ON(to > PAGE_SIZE);
 	BUG_ON(from > to);
 
 	head = create_page_buffers(page, inode, 0);
 	blocksize = head->b_size;
 	bbits = block_size_bits(blocksize);
 
-	block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits);
+	block = (sector_t)page->index << (PAGE_SHIFT - bbits);
 
 	for(bh = head, block_start = 0; bh != head || !block_start;
 	    block++, block_start=block_end, bh = bh->b_this_page) {
@@ -2031,7 +2020,7 @@ static int __block_commit_write(struct inode *inode, struct page *page,
 int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
 		unsigned flags, struct page **pagep, get_block_t *get_block)
 {
-	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+	pgoff_t index = pos >> PAGE_SHIFT;
 	struct page *page;
 	int status;
 
@@ -2042,7 +2031,7 @@ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
 	status = __block_write_begin(page, pos, len, get_block);
 	if (unlikely(status)) {
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 		page = NULL;
 	}
 
@@ -2058,7 +2047,7 @@ int block_write_end(struct file *file, struct address_space *mapping,
 	struct inode *inode = mapping->host;
 	unsigned start;
 
-	start = pos & (PAGE_CACHE_SIZE - 1);
+	start = pos & (PAGE_SIZE - 1);
 
 	if (unlikely(copied < len)) {
 		/*
@@ -2110,7 +2099,7 @@ int generic_write_end(struct file *file, struct address_space *mapping,
 	}
 
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 
 	if (old_size < pos)
 		pagecache_isize_extended(inode, old_size, pos);
@@ -2147,9 +2136,9 @@ int block_is_partially_uptodate(struct page *page, unsigned long from,
 
 	head = page_buffers(page);
 	blocksize = head->b_size;
-	to = min_t(unsigned, PAGE_CACHE_SIZE - from, count);
+	to = min_t(unsigned, PAGE_SIZE - from, count);
 	to = from + to;
-	if (from < blocksize && to > PAGE_CACHE_SIZE - blocksize)
+	if (from < blocksize && to > PAGE_SIZE - blocksize)
 		return 0;
 
 	bh = head;
@@ -2192,7 +2181,7 @@ int block_read_full_page(struct page *page, get_block_t *get_block)
 	blocksize = head->b_size;
 	bbits = block_size_bits(blocksize);
 
-	iblock = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits);
+	iblock = (sector_t)page->index << (PAGE_SHIFT - bbits);
 	lblock = (i_size_read(inode)+blocksize-1) >> bbits;
 	bh = head;
 	nr = 0;
@@ -2306,16 +2295,16 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
 	unsigned zerofrom, offset, len;
 	int err = 0;
 
-	index = pos >> PAGE_CACHE_SHIFT;
-	offset = pos & ~PAGE_CACHE_MASK;
+	index = pos >> PAGE_SHIFT;
+	offset = pos & ~PAGE_MASK;
 
-	while (index > (curidx = (curpos = *bytes)>>PAGE_CACHE_SHIFT)) {
-		zerofrom = curpos & ~PAGE_CACHE_MASK;
+	while (index > (curidx = (curpos = *bytes)>>PAGE_SHIFT)) {
+		zerofrom = curpos & ~PAGE_MASK;
 		if (zerofrom & (blocksize-1)) {
 			*bytes |= (blocksize-1);
 			(*bytes)++;
 		}
-		len = PAGE_CACHE_SIZE - zerofrom;
+		len = PAGE_SIZE - zerofrom;
 
 		err = pagecache_write_begin(file, mapping, curpos, len,
 						AOP_FLAG_UNINTERRUPTIBLE,
@@ -2340,7 +2329,7 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
 
 	/* page covers the boundary, find the boundary offset */
 	if (index == curidx) {
-		zerofrom = curpos & ~PAGE_CACHE_MASK;
+		zerofrom = curpos & ~PAGE_MASK;
 		/* if we will expand the thing last block will be filled */
 		if (offset <= zerofrom) {
 			goto out;
@@ -2386,7 +2375,7 @@ int cont_write_begin(struct file *file, struct address_space *mapping,
 	if (err)
 		return err;
 
-	zerofrom = *bytes & ~PAGE_CACHE_MASK;
+	zerofrom = *bytes & ~PAGE_MASK;
 	if (pos+len > *bytes && zerofrom & (blocksize-1)) {
 		*bytes |= (blocksize-1);
 		(*bytes)++;
@@ -2420,9 +2409,9 @@ EXPORT_SYMBOL(block_commit_write);
  * unlock the page.
  *
  * Direct callers of this function should protect against filesystem freezing
- * using sb_start_write() - sb_end_write() functions.
+ * using sb_start_pagefault() - sb_end_pagefault() functions.
  */
-int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
+int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 			 get_block_t get_block)
 {
 	struct page *page = vmf->page;
@@ -2441,10 +2430,10 @@ int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 	}
 
 	/* page is wholly or partially inside EOF */
-	if (((page->index + 1) << PAGE_CACHE_SHIFT) > size)
-		end = size & ~PAGE_CACHE_MASK;
+	if (((page->index + 1) << PAGE_SHIFT) > size)
+		end = size & ~PAGE_MASK;
 	else
-		end = PAGE_CACHE_SIZE;
+		end = PAGE_SIZE;
 
 	ret = __block_write_begin(page, 0, end, get_block);
 	if (!ret)
@@ -2459,26 +2448,6 @@ out_unlock:
 	unlock_page(page);
 	return ret;
 }
-EXPORT_SYMBOL(__block_page_mkwrite);
-
-int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
-		   get_block_t get_block)
-{
-	int ret;
-	struct super_block *sb = file_inode(vma->vm_file)->i_sb;
-
-	sb_start_pagefault(sb);
-
-	/*
-	 * Update file times before taking page lock. We may end up failing the
-	 * fault so this update may be superfluous but who really cares...
-	 */
-	file_update_time(vma->vm_file);
-
-	ret = __block_page_mkwrite(vma, vmf, get_block);
-	sb_end_pagefault(sb);
-	return block_page_mkwrite_return(ret);
-}
 EXPORT_SYMBOL(block_page_mkwrite);
 
 /*
@@ -2539,8 +2508,8 @@ int nobh_write_begin(struct address_space *mapping,
 	int ret = 0;
 	int is_mapped_to_disk = 1;
 
-	index = pos >> PAGE_CACHE_SHIFT;
-	from = pos & (PAGE_CACHE_SIZE - 1);
+	index = pos >> PAGE_SHIFT;
+	from = pos & (PAGE_SIZE - 1);
 	to = from + len;
 
 	page = grab_cache_page_write_begin(mapping, index, flags);
@@ -2574,7 +2543,7 @@ int nobh_write_begin(struct address_space *mapping,
 		goto out_release;
 	}
 
-	block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits);
+	block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits);
 
 	/*
 	 * We loop across all blocks in the page, whether or not they are
@@ -2582,7 +2551,7 @@ int nobh_write_begin(struct address_space *mapping,
 	 * page is fully mapped-to-disk.
 	 */
 	for (block_start = 0, block_in_page = 0, bh = head;
-		  block_start < PAGE_CACHE_SIZE;
+		  block_start < PAGE_SIZE;
 		  block_in_page++, block_start += blocksize, bh = bh->b_this_page) {
 		int create;
 
@@ -2654,7 +2623,7 @@ failed:
 
 out_release:
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 	*pagep = NULL;
 
 	return ret;
@@ -2684,7 +2653,7 @@ int nobh_write_end(struct file *file, struct address_space *mapping,
 	}
 
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 
 	while (head) {
 		bh = head;
@@ -2706,7 +2675,7 @@ int nobh_writepage(struct page *page, get_block_t *get_block,
 {
 	struct inode * const inode = page->mapping->host;
 	loff_t i_size = i_size_read(inode);
-	const pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
+	const pgoff_t end_index = i_size >> PAGE_SHIFT;
 	unsigned offset;
 	int ret;
 
@@ -2715,7 +2684,7 @@ int nobh_writepage(struct page *page, get_block_t *get_block,
 		goto out;
 
 	/* Is the page fully outside i_size? (truncate in progress) */
-	offset = i_size & (PAGE_CACHE_SIZE-1);
+	offset = i_size & (PAGE_SIZE-1);
 	if (page->index >= end_index+1 || !offset) {
 		/*
 		 * The page may have dirty, unmapped buffers.  For example,
@@ -2738,7 +2707,7 @@ int nobh_writepage(struct page *page, get_block_t *get_block,
 	 * the  page size, the remaining memory is zeroed when mapped, and
 	 * writes to that region are not written out to the file."
 	 */
-	zero_user_segment(page, offset, PAGE_CACHE_SIZE);
+	zero_user_segment(page, offset, PAGE_SIZE);
 out:
 	ret = mpage_writepage(page, get_block, wbc);
 	if (ret == -EAGAIN)
@@ -2751,8 +2720,8 @@ EXPORT_SYMBOL(nobh_writepage);
 int nobh_truncate_page(struct address_space *mapping,
 			loff_t from, get_block_t *get_block)
 {
-	pgoff_t index = from >> PAGE_CACHE_SHIFT;
-	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	pgoff_t index = from >> PAGE_SHIFT;
+	unsigned offset = from & (PAGE_SIZE-1);
 	unsigned blocksize;
 	sector_t iblock;
 	unsigned length, pos;
@@ -2769,7 +2738,7 @@ int nobh_truncate_page(struct address_space *mapping,
 		return 0;
 
 	length = blocksize - length;
-	iblock = (sector_t)index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+	iblock = (sector_t)index << (PAGE_SHIFT - inode->i_blkbits);
 
 	page = grab_cache_page(mapping, index);
 	err = -ENOMEM;
@@ -2779,7 +2748,7 @@ int nobh_truncate_page(struct address_space *mapping,
 	if (page_has_buffers(page)) {
 has_buffers:
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 		return block_truncate_page(mapping, from, get_block);
 	}
 
@@ -2803,7 +2772,7 @@ has_buffers:
 	if (!PageUptodate(page)) {
 		err = mapping->a_ops->readpage(NULL, page);
 		if (err) {
-			page_cache_release(page);
+			put_page(page);
 			goto out;
 		}
 		lock_page(page);
@@ -2820,7 +2789,7 @@ has_buffers:
 
 unlock:
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 out:
 	return err;
 }
@@ -2829,8 +2798,8 @@ EXPORT_SYMBOL(nobh_truncate_page);
 int block_truncate_page(struct address_space *mapping,
 			loff_t from, get_block_t *get_block)
 {
-	pgoff_t index = from >> PAGE_CACHE_SHIFT;
-	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	pgoff_t index = from >> PAGE_SHIFT;
+	unsigned offset = from & (PAGE_SIZE-1);
 	unsigned blocksize;
 	sector_t iblock;
 	unsigned length, pos;
@@ -2847,7 +2816,7 @@ int block_truncate_page(struct address_space *mapping,
 		return 0;
 
 	length = blocksize - length;
-	iblock = (sector_t)index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+	iblock = (sector_t)index << (PAGE_SHIFT - inode->i_blkbits);
 	
 	page = grab_cache_page(mapping, index);
 	err = -ENOMEM;
@@ -2896,7 +2865,7 @@ int block_truncate_page(struct address_space *mapping,
 
 unlock:
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 out:
 	return err;
 }
@@ -2910,7 +2879,7 @@ int block_write_full_page(struct page *page, get_block_t *get_block,
 {
 	struct inode * const inode = page->mapping->host;
 	loff_t i_size = i_size_read(inode);
-	const pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
+	const pgoff_t end_index = i_size >> PAGE_SHIFT;
 	unsigned offset;
 
 	/* Is the page fully inside i_size? */
@@ -2919,14 +2888,14 @@ int block_write_full_page(struct page *page, get_block_t *get_block,
 					       end_buffer_async_write);
 
 	/* Is the page fully outside i_size? (truncate in progress) */
-	offset = i_size & (PAGE_CACHE_SIZE-1);
+	offset = i_size & (PAGE_SIZE-1);
 	if (page->index >= end_index+1 || !offset) {
 		/*
 		 * The page may have dirty, unmapped buffers.  For example,
 		 * they may have been added in ext3_writepage().  Make them
 		 * freeable here, so the page does not leak.
 		 */
-		do_invalidatepage(page, 0, PAGE_CACHE_SIZE);
+		do_invalidatepage(page, 0, PAGE_SIZE);
 		unlock_page(page);
 		return 0; /* don't care */
 	}
@@ -2938,7 +2907,7 @@ int block_write_full_page(struct page *page, get_block_t *get_block,
 	 * the  page size, the remaining memory is zeroed when mapped, and
 	 * writes to that region are not written out to the file."
 	 */
-	zero_user_segment(page, offset, PAGE_CACHE_SIZE);
+	zero_user_segment(page, offset, PAGE_SIZE);
 	return __block_write_full_page(inode, page, get_block, wbc,
 							end_buffer_async_write);
 }
diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c
index f601def05bdf..1ee54ffd3a24 100644
--- a/fs/cachefiles/daemon.c
+++ b/fs/cachefiles/daemon.c
@@ -162,6 +162,8 @@ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer,
 				      size_t buflen, loff_t *pos)
 {
 	struct cachefiles_cache *cache = file->private_data;
+	unsigned long long b_released;
+	unsigned f_released;
 	char buffer[256];
 	int n;
 
@@ -174,6 +176,8 @@ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer,
 	cachefiles_has_space(cache, 0, 0);
 
 	/* summarise */
+	f_released = atomic_xchg(&cache->f_released, 0);
+	b_released = atomic_long_xchg(&cache->b_released, 0);
 	clear_bit(CACHEFILES_STATE_CHANGED, &cache->flags);
 
 	n = snprintf(buffer, sizeof(buffer),
@@ -183,15 +187,18 @@ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer,
 		     " fstop=%llx"
 		     " brun=%llx"
 		     " bcull=%llx"
-		     " bstop=%llx",
+		     " bstop=%llx"
+		     " freleased=%x"
+		     " breleased=%llx",
 		     test_bit(CACHEFILES_CULLING, &cache->flags) ? '1' : '0',
 		     (unsigned long long) cache->frun,
 		     (unsigned long long) cache->fcull,
 		     (unsigned long long) cache->fstop,
 		     (unsigned long long) cache->brun,
 		     (unsigned long long) cache->bcull,
-		     (unsigned long long) cache->bstop
-		     );
+		     (unsigned long long) cache->bstop,
+		     f_released,
+		     b_released);
 
 	if (n > buflen)
 		return -EMSGSIZE;
@@ -226,15 +233,9 @@ static ssize_t cachefiles_daemon_write(struct file *file,
 		return -EOPNOTSUPP;
 
 	/* drag the command string into the kernel so we can parse it */
-	data = kmalloc(datalen + 1, GFP_KERNEL);
-	if (!data)
-		return -ENOMEM;
-
-	ret = -EFAULT;
-	if (copy_from_user(data, _data, datalen) != 0)
-		goto error;
-
-	data[datalen] = '\0';
+	data = memdup_user_nul(_data, datalen);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
 
 	ret = -EINVAL;
 	if (memchr(data, '\0', datalen))
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index afa023dded5b..861d611b8c05 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -291,15 +291,8 @@ static void cachefiles_drop_object(struct fscache_object *_object)
 	}
 
 	/* note that the object is now inactive */
-	if (test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)) {
-		write_lock(&cache->active_lock);
-		if (!test_and_clear_bit(CACHEFILES_OBJECT_ACTIVE,
-					&object->flags))
-			BUG();
-		rb_erase(&object->active_node, &cache->active_nodes);
-		wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE);
-		write_unlock(&cache->active_lock);
-	}
+	if (test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags))
+		cachefiles_mark_object_inactive(cache, object);
 
 	dput(object->dentry);
 	object->dentry = NULL;
@@ -446,7 +439,7 @@ static int cachefiles_attr_changed(struct fscache_object *_object)
 		return 0;
 
 	cachefiles_begin_secure(cache, &saved_cred);
-	mutex_lock(&d_inode(object->backer)->i_mutex);
+	inode_lock(d_inode(object->backer));
 
 	/* if there's an extension to a partial page at the end of the backing
 	 * file, we need to discard the partial page so that we pick up new
@@ -465,7 +458,7 @@ static int cachefiles_attr_changed(struct fscache_object *_object)
 	ret = notify_change(object->backer, &newattrs, NULL);
 
 truncate_failed:
-	mutex_unlock(&d_inode(object->backer)->i_mutex);
+	inode_unlock(d_inode(object->backer));
 	cachefiles_end_secure(cache, saved_cred);
 
 	if (ret == -EIO) {
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index aecd0859eacb..2fcde1a34b7c 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -30,7 +30,7 @@ extern unsigned cachefiles_debug;
 #define CACHEFILES_DEBUG_KLEAVE	2
 #define CACHEFILES_DEBUG_KDEBUG	4
 
-#define cachefiles_gfp (__GFP_WAIT | __GFP_NORETRY | __GFP_NOMEMALLOC)
+#define cachefiles_gfp (__GFP_RECLAIM | __GFP_NORETRY | __GFP_NOMEMALLOC)
 
 /*
  * node records
@@ -66,6 +66,8 @@ struct cachefiles_cache {
 	struct rb_root			active_nodes;	/* active nodes (can't be culled) */
 	rwlock_t			active_lock;	/* lock for active_nodes */
 	atomic_t			gravecounter;	/* graveyard uniquifier */
+	atomic_t			f_released;	/* number of objects released lately */
+	atomic_long_t			b_released;	/* number of blocks released lately */
 	unsigned			frun_percent;	/* when to stop culling (% files) */
 	unsigned			fcull_percent;	/* when to start culling (% files) */
 	unsigned			fstop_percent;	/* when to stop allocating (% files) */
@@ -157,6 +159,8 @@ extern char *cachefiles_cook_key(const u8 *raw, int keylen, uint8_t type);
 /*
  * namei.c
  */
+extern void cachefiles_mark_object_inactive(struct cachefiles_cache *cache,
+					    struct cachefiles_object *object);
 extern int cachefiles_delete_object(struct cachefiles_cache *cache,
 				    struct cachefiles_object *object);
 extern int cachefiles_walk_to_object(struct cachefiles_object *parent,
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index fc1056f5c96a..4ae75006e73b 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -258,6 +258,28 @@ requeue:
 }
 
 /*
+ * Mark an object as being inactive.
+ */
+void cachefiles_mark_object_inactive(struct cachefiles_cache *cache,
+				     struct cachefiles_object *object)
+{
+	write_lock(&cache->active_lock);
+	rb_erase(&object->active_node, &cache->active_nodes);
+	clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
+	write_unlock(&cache->active_lock);
+
+	wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE);
+
+	/* This object can now be culled, so we need to let the daemon know
+	 * that there is something it can remove if it needs to.
+	 */
+	atomic_long_add(d_backing_inode(object->dentry)->i_blocks,
+			&cache->b_released);
+	if (atomic_inc_return(&cache->f_released))
+		cachefiles_state_changed(cache);
+}
+
+/*
  * delete an object representation from the cache
  * - file backed objects are unlinked
  * - directory backed objects are stuffed into the graveyard for userspace to
@@ -295,7 +317,7 @@ static int cachefiles_bury_object(struct cachefiles_cache *cache,
 				cachefiles_mark_object_buried(cache, rep, why);
 		}
 
-		mutex_unlock(&d_inode(dir)->i_mutex);
+		inode_unlock(d_inode(dir));
 
 		if (ret == -EIO)
 			cachefiles_io_error(cache, "Unlink failed");
@@ -306,7 +328,7 @@ static int cachefiles_bury_object(struct cachefiles_cache *cache,
 
 	/* directories have to be moved to the graveyard */
 	_debug("move stale object to graveyard");
-	mutex_unlock(&d_inode(dir)->i_mutex);
+	inode_unlock(d_inode(dir));
 
 try_again:
 	/* first step is to make up a grave dentry in the graveyard */
@@ -423,13 +445,13 @@ int cachefiles_delete_object(struct cachefiles_cache *cache,
 
 	dir = dget_parent(object->dentry);
 
-	mutex_lock_nested(&d_inode(dir)->i_mutex, I_MUTEX_PARENT);
+	inode_lock_nested(d_inode(dir), I_MUTEX_PARENT);
 
 	if (test_bit(FSCACHE_OBJECT_KILLED_BY_CACHE, &object->fscache.flags)) {
 		/* object allocation for the same key preemptively deleted this
 		 * object's file so that it could create its own file */
 		_debug("object preemptively buried");
-		mutex_unlock(&d_inode(dir)->i_mutex);
+		inode_unlock(d_inode(dir));
 		ret = 0;
 	} else {
 		/* we need to check that our parent is _still_ our parent - it
@@ -442,7 +464,7 @@ int cachefiles_delete_object(struct cachefiles_cache *cache,
 			/* it got moved, presumably by cachefilesd culling it,
 			 * so it's no longer in the key path and we can ignore
 			 * it */
-			mutex_unlock(&d_inode(dir)->i_mutex);
+			inode_unlock(d_inode(dir));
 			ret = 0;
 		}
 	}
@@ -501,7 +523,7 @@ lookup_again:
 	/* search the current directory for the element name */
 	_debug("lookup '%s'", name);
 
-	mutex_lock_nested(&d_inode(dir)->i_mutex, I_MUTEX_PARENT);
+	inode_lock_nested(d_inode(dir), I_MUTEX_PARENT);
 
 	start = jiffies;
 	next = lookup_one_len(name, dir, nlen);
@@ -585,7 +607,7 @@ lookup_again:
 	/* process the next component */
 	if (key) {
 		_debug("advance");
-		mutex_unlock(&d_inode(dir)->i_mutex);
+		inode_unlock(d_inode(dir));
 		dput(dir);
 		dir = next;
 		next = NULL;
@@ -623,7 +645,7 @@ lookup_again:
 	/* note that we're now using this object */
 	ret = cachefiles_mark_object_active(cache, object);
 
-	mutex_unlock(&d_inode(dir)->i_mutex);
+	inode_unlock(d_inode(dir));
 	dput(dir);
 	dir = NULL;
 
@@ -655,6 +677,8 @@ lookup_again:
 			aops = d_backing_inode(object->dentry)->i_mapping->a_ops;
 			if (!aops->bmap)
 				goto check_error;
+			if (object->dentry->d_sb->s_blocksize > PAGE_SIZE)
+				goto check_error;
 
 			object->backer = object->dentry;
 		} else {
@@ -682,11 +706,7 @@ mark_active_timed_out:
 
 check_error:
 	_debug("check error %d", ret);
-	write_lock(&cache->active_lock);
-	rb_erase(&object->active_node, &cache->active_nodes);
-	clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
-	wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE);
-	write_unlock(&cache->active_lock);
+	cachefiles_mark_object_inactive(cache, object);
 release_dentry:
 	dput(object->dentry);
 	object->dentry = NULL;
@@ -703,7 +723,7 @@ lookup_error:
 		cachefiles_io_error(cache, "Lookup failed");
 	next = NULL;
 error:
-	mutex_unlock(&d_inode(dir)->i_mutex);
+	inode_unlock(d_inode(dir));
 	dput(next);
 error_out2:
 	dput(dir);
@@ -727,7 +747,7 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
 	_enter(",,%s", dirname);
 
 	/* search the current directory for the element name */
-	mutex_lock(&d_inode(dir)->i_mutex);
+	inode_lock(d_inode(dir));
 
 	start = jiffies;
 	subdir = lookup_one_len(dirname, dir, strlen(dirname));
@@ -766,7 +786,7 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
 		       d_backing_inode(subdir)->i_ino);
 	}
 
-	mutex_unlock(&d_inode(dir)->i_mutex);
+	inode_unlock(d_inode(dir));
 
 	/* we need to make sure the subdir is a directory */
 	ASSERT(d_backing_inode(subdir));
@@ -798,19 +818,19 @@ check_error:
 	return ERR_PTR(ret);
 
 mkdir_error:
-	mutex_unlock(&d_inode(dir)->i_mutex);
+	inode_unlock(d_inode(dir));
 	dput(subdir);
 	pr_err("mkdir %s failed with error %d\n", dirname, ret);
 	return ERR_PTR(ret);
 
 lookup_error:
-	mutex_unlock(&d_inode(dir)->i_mutex);
+	inode_unlock(d_inode(dir));
 	ret = PTR_ERR(subdir);
 	pr_err("Lookup %s failed with error %d\n", dirname, ret);
 	return ERR_PTR(ret);
 
 nomem_d_alloc:
-	mutex_unlock(&d_inode(dir)->i_mutex);
+	inode_unlock(d_inode(dir));
 	_leave(" = -ENOMEM");
 	return ERR_PTR(-ENOMEM);
 }
@@ -835,7 +855,7 @@ static struct dentry *cachefiles_check_active(struct cachefiles_cache *cache,
 	//       dir, filename);
 
 	/* look up the victim */
-	mutex_lock_nested(&d_inode(dir)->i_mutex, I_MUTEX_PARENT);
+	inode_lock_nested(d_inode(dir), I_MUTEX_PARENT);
 
 	start = jiffies;
 	victim = lookup_one_len(filename, dir, strlen(filename));
@@ -850,7 +870,7 @@ static struct dentry *cachefiles_check_active(struct cachefiles_cache *cache,
 	 * at the netfs's request whilst the cull was in progress
 	 */
 	if (d_is_negative(victim)) {
-		mutex_unlock(&d_inode(dir)->i_mutex);
+		inode_unlock(d_inode(dir));
 		dput(victim);
 		_leave(" = -ENOENT [absent]");
 		return ERR_PTR(-ENOENT);
@@ -879,13 +899,13 @@ static struct dentry *cachefiles_check_active(struct cachefiles_cache *cache,
 
 object_in_use:
 	read_unlock(&cache->active_lock);
-	mutex_unlock(&d_inode(dir)->i_mutex);
+	inode_unlock(d_inode(dir));
 	dput(victim);
 	//_leave(" = -EBUSY [in use]");
 	return ERR_PTR(-EBUSY);
 
 lookup_error:
-	mutex_unlock(&d_inode(dir)->i_mutex);
+	inode_unlock(d_inode(dir));
 	ret = PTR_ERR(victim);
 	if (ret == -ENOENT) {
 		/* file or dir now absent - probably retired by netfs */
@@ -945,7 +965,7 @@ int cachefiles_cull(struct cachefiles_cache *cache, struct dentry *dir,
 	return 0;
 
 error_unlock:
-	mutex_unlock(&d_inode(dir)->i_mutex);
+	inode_unlock(d_inode(dir));
 error:
 	dput(victim);
 	if (ret == -ENOENT) {
@@ -980,7 +1000,7 @@ int cachefiles_check_in_use(struct cachefiles_cache *cache, struct dentry *dir,
 	if (IS_ERR(victim))
 		return PTR_ERR(victim);
 
-	mutex_unlock(&d_inode(dir)->i_mutex);
+	inode_unlock(d_inode(dir));
 	dput(victim);
 	//_leave(" = 0");
 	return 0;
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index 3cbb0e834694..afbdc418966d 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -194,10 +194,10 @@ static void cachefiles_read_copier(struct fscache_operation *_op)
 			error = -EIO;
 		}
 
-		page_cache_release(monitor->back_page);
+		put_page(monitor->back_page);
 
 		fscache_end_io(op, monitor->netfs_page, error);
-		page_cache_release(monitor->netfs_page);
+		put_page(monitor->netfs_page);
 		fscache_retrieval_complete(op, 1);
 		fscache_put_retrieval(op);
 		kfree(monitor);
@@ -288,8 +288,8 @@ monitor_backing_page:
 	_debug("- monitor add");
 
 	/* install the monitor */
-	page_cache_get(monitor->netfs_page);
-	page_cache_get(backpage);
+	get_page(monitor->netfs_page);
+	get_page(backpage);
 	monitor->back_page = backpage;
 	monitor->monitor.private = backpage;
 	add_page_wait_queue(backpage, &monitor->monitor);
@@ -310,7 +310,7 @@ backing_page_already_present:
 	_debug("- present");
 
 	if (newpage) {
-		page_cache_release(newpage);
+		put_page(newpage);
 		newpage = NULL;
 	}
 
@@ -342,7 +342,7 @@ success:
 
 out:
 	if (backpage)
-		page_cache_release(backpage);
+		put_page(backpage);
 	if (monitor) {
 		fscache_put_retrieval(monitor->op);
 		kfree(monitor);
@@ -363,7 +363,7 @@ io_error:
 	goto out;
 
 nomem_page:
-	page_cache_release(newpage);
+	put_page(newpage);
 nomem_monitor:
 	fscache_put_retrieval(monitor->op);
 	kfree(monitor);
@@ -414,9 +414,6 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
 	ASSERT(inode->i_mapping->a_ops->readpages);
 
 	/* calculate the shift required to use bmap */
-	if (inode->i_sb->s_blocksize > PAGE_SIZE)
-		goto enobufs;
-
 	shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits;
 
 	op->op.flags &= FSCACHE_OP_KEEP_FLAGS;
@@ -533,7 +530,7 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 					    netpage->index, cachefiles_gfp);
 		if (ret < 0) {
 			if (ret == -EEXIST) {
-				page_cache_release(netpage);
+				put_page(netpage);
 				fscache_retrieval_complete(op, 1);
 				continue;
 			}
@@ -541,10 +538,10 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 		}
 
 		/* install a monitor */
-		page_cache_get(netpage);
+		get_page(netpage);
 		monitor->netfs_page = netpage;
 
-		page_cache_get(backpage);
+		get_page(backpage);
 		monitor->back_page = backpage;
 		monitor->monitor.private = backpage;
 		add_page_wait_queue(backpage, &monitor->monitor);
@@ -558,10 +555,10 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 			unlock_page(backpage);
 		}
 
-		page_cache_release(backpage);
+		put_page(backpage);
 		backpage = NULL;
 
-		page_cache_release(netpage);
+		put_page(netpage);
 		netpage = NULL;
 		continue;
 
@@ -606,7 +603,7 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 					    netpage->index, cachefiles_gfp);
 		if (ret < 0) {
 			if (ret == -EEXIST) {
-				page_cache_release(netpage);
+				put_page(netpage);
 				fscache_retrieval_complete(op, 1);
 				continue;
 			}
@@ -615,14 +612,14 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 
 		copy_highpage(netpage, backpage);
 
-		page_cache_release(backpage);
+		put_page(backpage);
 		backpage = NULL;
 
 		fscache_mark_page_cached(op, netpage);
 
 		/* the netpage is unlocked and marked up to date here */
 		fscache_end_io(op, netpage, 0);
-		page_cache_release(netpage);
+		put_page(netpage);
 		netpage = NULL;
 		fscache_retrieval_complete(op, 1);
 		continue;
@@ -635,11 +632,11 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 out:
 	/* tidy up */
 	if (newpage)
-		page_cache_release(newpage);
+		put_page(newpage);
 	if (netpage)
-		page_cache_release(netpage);
+		put_page(netpage);
 	if (backpage)
-		page_cache_release(backpage);
+		put_page(backpage);
 	if (monitor) {
 		fscache_put_retrieval(op);
 		kfree(monitor);
@@ -647,7 +644,7 @@ out:
 
 	list_for_each_entry_safe(netpage, _n, list, lru) {
 		list_del(&netpage->lru);
-		page_cache_release(netpage);
+		put_page(netpage);
 		fscache_retrieval_complete(op, 1);
 	}
 
@@ -711,9 +708,6 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
 	ASSERT(inode->i_mapping->a_ops->readpages);
 
 	/* calculate the shift required to use bmap */
-	if (inode->i_sb->s_blocksize > PAGE_SIZE)
-		goto all_enobufs;
-
 	shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits;
 
 	pagevec_init(&pagevec, 0);
@@ -885,7 +879,7 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page)
 	loff_t pos, eof;
 	size_t len;
 	void *data;
-	int ret;
+	int ret = -ENOBUFS;
 
 	ASSERT(op != NULL);
 	ASSERT(page != NULL);
@@ -905,6 +899,15 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page)
 	cache = container_of(object->fscache.cache,
 			     struct cachefiles_cache, cache);
 
+	pos = (loff_t)page->index << PAGE_SHIFT;
+
+	/* We mustn't write more data than we have, so we have to beware of a
+	 * partial page at EOF.
+	 */
+	eof = object->fscache.store_limit_l;
+	if (pos >= eof)
+		goto error;
+
 	/* write the page to the backing filesystem and let it store it in its
 	 * own time */
 	path.mnt = cache->mnt;
@@ -912,40 +915,38 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page)
 	file = dentry_open(&path, O_RDWR | O_LARGEFILE, cache->cache_cred);
 	if (IS_ERR(file)) {
 		ret = PTR_ERR(file);
-	} else {
-		pos = (loff_t) page->index << PAGE_SHIFT;
-
-		/* we mustn't write more data than we have, so we have
-		 * to beware of a partial page at EOF */
-		eof = object->fscache.store_limit_l;
-		len = PAGE_SIZE;
-		if (eof & ~PAGE_MASK) {
-			ASSERTCMP(pos, <, eof);
-			if (eof - pos < PAGE_SIZE) {
-				_debug("cut short %llx to %llx",
-				       pos, eof);
-				len = eof - pos;
-				ASSERTCMP(pos + len, ==, eof);
-			}
-		}
-
-		data = kmap(page);
-		ret = __kernel_write(file, data, len, &pos);
-		kunmap(page);
-		if (ret != len)
-			ret = -EIO;
-		fput(file);
+		goto error_2;
 	}
 
-	if (ret < 0) {
-		if (ret == -EIO)
-			cachefiles_io_error_obj(
-				object, "Write page to backing file failed");
-		ret = -ENOBUFS;
+	len = PAGE_SIZE;
+	if (eof & ~PAGE_MASK) {
+		if (eof - pos < PAGE_SIZE) {
+			_debug("cut short %llx to %llx",
+			       pos, eof);
+			len = eof - pos;
+			ASSERTCMP(pos + len, ==, eof);
+		}
 	}
 
-	_leave(" = %d", ret);
-	return ret;
+	data = kmap(page);
+	ret = __kernel_write(file, data, len, &pos);
+	kunmap(page);
+	fput(file);
+	if (ret != len)
+		goto error_eio;
+
+	_leave(" = 0");
+	return 0;
+
+error_eio:
+	ret = -EIO;
+error_2:
+	if (ret == -EIO)
+		cachefiles_io_error_obj(object,
+					"Write page to backing file failed");
+error:
+	_leave(" = -ENOBUFS [%d]", ret);
+	return -ENOBUFS;
 }
 
 /*
diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
index 8f84646f10e9..f19708487e2f 100644
--- a/fs/ceph/acl.c
+++ b/fs/ceph/acl.c
@@ -49,10 +49,10 @@ struct posix_acl *ceph_get_acl(struct inode *inode, int type)
 
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		name = POSIX_ACL_XATTR_ACCESS;
+		name = XATTR_NAME_POSIX_ACL_ACCESS;
 		break;
 	case ACL_TYPE_DEFAULT:
-		name = POSIX_ACL_XATTR_DEFAULT;
+		name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		break;
 	default:
 		BUG();
@@ -92,7 +92,7 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		name = POSIX_ACL_XATTR_ACCESS;
+		name = XATTR_NAME_POSIX_ACL_ACCESS;
 		if (acl) {
 			ret = posix_acl_equiv_mode(acl, &new_mode);
 			if (ret < 0)
@@ -106,7 +106,7 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 			ret = acl ? -EINVAL : 0;
 			goto out;
 		}
-		name = POSIX_ACL_XATTR_DEFAULT;
+		name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		break;
 	default:
 		ret = -EINVAL;
@@ -202,11 +202,11 @@ int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
 	ceph_pagelist_encode_32(pagelist, acl && default_acl ? 2 : 1);
 
 	if (acl) {
-		size_t len = strlen(POSIX_ACL_XATTR_ACCESS);
+		size_t len = strlen(XATTR_NAME_POSIX_ACL_ACCESS);
 		err = ceph_pagelist_reserve(pagelist, len + val_size1 + 8);
 		if (err)
 			goto out_err;
-		ceph_pagelist_encode_string(pagelist, POSIX_ACL_XATTR_ACCESS,
+		ceph_pagelist_encode_string(pagelist, XATTR_NAME_POSIX_ACL_ACCESS,
 					    len);
 		err = posix_acl_to_xattr(&init_user_ns, acl,
 					 tmp_buf, val_size1);
@@ -216,12 +216,12 @@ int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
 		ceph_pagelist_append(pagelist, tmp_buf, val_size1);
 	}
 	if (default_acl) {
-		size_t len = strlen(POSIX_ACL_XATTR_DEFAULT);
+		size_t len = strlen(XATTR_NAME_POSIX_ACL_DEFAULT);
 		err = ceph_pagelist_reserve(pagelist, len + val_size2 + 8);
 		if (err)
 			goto out_err;
 		err = ceph_pagelist_encode_string(pagelist,
-						  POSIX_ACL_XATTR_DEFAULT, len);
+						  XATTR_NAME_POSIX_ACL_DEFAULT, len);
 		err = posix_acl_to_xattr(&init_user_ns, default_acl,
 					 tmp_buf, val_size2);
 		if (err < 0)
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 9d23e788d1df..4801571f51cb 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -143,7 +143,7 @@ static void ceph_invalidatepage(struct page *page, unsigned int offset,
 	inode = page->mapping->host;
 	ci = ceph_inode(inode);
 
-	if (offset != 0 || length != PAGE_CACHE_SIZE) {
+	if (offset != 0 || length != PAGE_SIZE) {
 		dout("%p invalidatepage %p idx %lu partial dirty page %u~%u\n",
 		     inode, page, page->index, offset, length);
 		return;
@@ -175,8 +175,8 @@ static void ceph_invalidatepage(struct page *page, unsigned int offset,
 
 static int ceph_releasepage(struct page *page, gfp_t g)
 {
-	struct inode *inode = page->mapping ? page->mapping->host : NULL;
-	dout("%p releasepage %p idx %lu\n", inode, page, page->index);
+	dout("%p releasepage %p idx %lu\n", page->mapping->host,
+	     page, page->index);
 	WARN_ON(PageDirty(page));
 
 	/* Can we release the page from the cache? */
@@ -197,10 +197,10 @@ static int readpage_nounlock(struct file *filp, struct page *page)
 		&ceph_inode_to_client(inode)->client->osdc;
 	int err = 0;
 	u64 off = page_offset(page);
-	u64 len = PAGE_CACHE_SIZE;
+	u64 len = PAGE_SIZE;
 
 	if (off >= i_size_read(inode)) {
-		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+		zero_user_segment(page, 0, PAGE_SIZE);
 		SetPageUptodate(page);
 		return 0;
 	}
@@ -212,7 +212,7 @@ static int readpage_nounlock(struct file *filp, struct page *page)
 		 */
 		if (off == 0)
 			return -EINVAL;
-		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+		zero_user_segment(page, 0, PAGE_SIZE);
 		SetPageUptodate(page);
 		return 0;
 	}
@@ -234,9 +234,9 @@ static int readpage_nounlock(struct file *filp, struct page *page)
 		ceph_fscache_readpage_cancel(inode, page);
 		goto out;
 	}
-	if (err < PAGE_CACHE_SIZE)
+	if (err < PAGE_SIZE)
 		/* zero fill remainder of page */
-		zero_user_segment(page, err, PAGE_CACHE_SIZE);
+		zero_user_segment(page, err, PAGE_SIZE);
 	else
 		flush_dcache_page(page);
 
@@ -276,12 +276,12 @@ static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg)
 	for (i = 0; i < num_pages; i++) {
 		struct page *page = osd_data->pages[i];
 
-		if (rc < 0 && rc != ENOENT)
+		if (rc < 0 && rc != -ENOENT)
 			goto unlock;
-		if (bytes < (int)PAGE_CACHE_SIZE) {
+		if (bytes < (int)PAGE_SIZE) {
 			/* zero (remainder of) page */
 			int s = bytes < 0 ? 0 : bytes;
-			zero_user_segment(page, s, PAGE_CACHE_SIZE);
+			zero_user_segment(page, s, PAGE_SIZE);
 		}
  		dout("finish_read %p uptodate %p idx %lu\n", inode, page,
 		     page->index);
@@ -290,8 +290,8 @@ static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg)
 		ceph_readpage_to_fscache(inode, page);
 unlock:
 		unlock_page(page);
-		page_cache_release(page);
-		bytes -= PAGE_CACHE_SIZE;
+		put_page(page);
+		bytes -= PAGE_SIZE;
 	}
 	kfree(osd_data->pages);
 }
@@ -336,7 +336,7 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
 		if (max && nr_pages == max)
 			break;
 	}
-	len = nr_pages << PAGE_CACHE_SHIFT;
+	len = nr_pages << PAGE_SHIFT;
 	dout("start_read %p nr_pages %d is %lld~%lld\n", inode, nr_pages,
 	     off, len);
 	vino = ceph_vino(inode);
@@ -364,7 +364,7 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
 		if (add_to_page_cache_lru(page, &inode->i_data, page->index,
 					  GFP_KERNEL)) {
 			ceph_fscache_uncache_page(inode, page);
-			page_cache_release(page);
+			put_page(page);
 			dout("start_read %p add_to_page_cache failed %p\n",
 			     inode, page);
 			nr_pages = i;
@@ -415,8 +415,8 @@ static int ceph_readpages(struct file *file, struct address_space *mapping,
 	if (rc == 0)
 		goto out;
 
-	if (fsc->mount_options->rsize >= PAGE_CACHE_SIZE)
-		max = (fsc->mount_options->rsize + PAGE_CACHE_SIZE - 1)
+	if (fsc->mount_options->rsize >= PAGE_SIZE)
+		max = (fsc->mount_options->rsize + PAGE_SIZE - 1)
 			>> PAGE_SHIFT;
 
 	dout("readpages %p file %p nr_pages %d max %d\n", inode,
@@ -484,7 +484,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	long writeback_stat;
 	u64 truncate_size;
 	u32 truncate_seq;
-	int err = 0, len = PAGE_CACHE_SIZE;
+	int err = 0, len = PAGE_SIZE;
 
 	dout("writepage %p idx %lu\n", page, page->index);
 
@@ -606,71 +606,71 @@ static void writepages_finish(struct ceph_osd_request *req,
 	struct inode *inode = req->r_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_osd_data *osd_data;
-	unsigned wrote;
 	struct page *page;
-	int num_pages;
-	int i;
+	int num_pages, total_pages = 0;
+	int i, j;
+	int rc = req->r_result;
 	struct ceph_snap_context *snapc = req->r_snapc;
 	struct address_space *mapping = inode->i_mapping;
-	int rc = req->r_result;
-	u64 bytes = req->r_ops[0].extent.length;
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
-	long writeback_stat;
-	unsigned issued = ceph_caps_issued(ci);
+	bool remove_page;
 
-	osd_data = osd_req_op_extent_osd_data(req, 0);
-	BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_PAGES);
-	num_pages = calc_pages_for((u64)osd_data->alignment,
-					(u64)osd_data->length);
-	if (rc >= 0) {
-		/*
-		 * Assume we wrote the pages we originally sent.  The
-		 * osd might reply with fewer pages if our writeback
-		 * raced with a truncation and was adjusted at the osd,
-		 * so don't believe the reply.
-		 */
-		wrote = num_pages;
-	} else {
-		wrote = 0;
+
+	dout("writepages_finish %p rc %d\n", inode, rc);
+	if (rc < 0)
 		mapping_set_error(mapping, rc);
-	}
-	dout("writepages_finish %p rc %d bytes %llu wrote %d (pages)\n",
-	     inode, rc, bytes, wrote);
 
-	/* clean all pages */
-	for (i = 0; i < num_pages; i++) {
-		page = osd_data->pages[i];
-		BUG_ON(!page);
-		WARN_ON(!PageUptodate(page));
+	/*
+	 * We lost the cache cap, need to truncate the page before
+	 * it is unlocked, otherwise we'd truncate it later in the
+	 * page truncation thread, possibly losing some data that
+	 * raced its way in
+	 */
+	remove_page = !(ceph_caps_issued(ci) &
+			(CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO));
 
-		writeback_stat =
-			atomic_long_dec_return(&fsc->writeback_count);
-		if (writeback_stat <
-		    CONGESTION_OFF_THRESH(fsc->mount_options->congestion_kb))
-			clear_bdi_congested(&fsc->backing_dev_info,
-					    BLK_RW_ASYNC);
+	/* clean all pages */
+	for (i = 0; i < req->r_num_ops; i++) {
+		if (req->r_ops[i].op != CEPH_OSD_OP_WRITE)
+			break;
 
-		ceph_put_snap_context(page_snap_context(page));
-		page->private = 0;
-		ClearPagePrivate(page);
-		dout("unlocking %d %p\n", i, page);
-		end_page_writeback(page);
+		osd_data = osd_req_op_extent_osd_data(req, i);
+		BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_PAGES);
+		num_pages = calc_pages_for((u64)osd_data->alignment,
+					   (u64)osd_data->length);
+		total_pages += num_pages;
+		for (j = 0; j < num_pages; j++) {
+			page = osd_data->pages[j];
+			BUG_ON(!page);
+			WARN_ON(!PageUptodate(page));
+
+			if (atomic_long_dec_return(&fsc->writeback_count) <
+			     CONGESTION_OFF_THRESH(
+					fsc->mount_options->congestion_kb))
+				clear_bdi_congested(&fsc->backing_dev_info,
+						    BLK_RW_ASYNC);
+
+			ceph_put_snap_context(page_snap_context(page));
+			page->private = 0;
+			ClearPagePrivate(page);
+			dout("unlocking %p\n", page);
+			end_page_writeback(page);
+
+			if (remove_page)
+				generic_error_remove_page(inode->i_mapping,
+							  page);
 
-		/*
-		 * We lost the cache cap, need to truncate the page before
-		 * it is unlocked, otherwise we'd truncate it later in the
-		 * page truncation thread, possibly losing some data that
-		 * raced its way in
-		 */
-		if ((issued & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0)
-			generic_error_remove_page(inode->i_mapping, page);
+			unlock_page(page);
+		}
+		dout("writepages_finish %p wrote %llu bytes cleaned %d pages\n",
+		     inode, osd_data->length, rc >= 0 ? num_pages : 0);
 
-		unlock_page(page);
+		ceph_release_pages(osd_data->pages, num_pages);
 	}
-	dout("%p wrote+cleaned %d pages\n", inode, wrote);
-	ceph_put_wrbuffer_cap_refs(ci, num_pages, snapc);
 
-	ceph_release_pages(osd_data->pages, num_pages);
+	ceph_put_wrbuffer_cap_refs(ci, total_pages, snapc);
+
+	osd_data = osd_req_op_extent_osd_data(req, 0);
 	if (osd_data->pages_from_pool)
 		mempool_free(osd_data->pages,
 			     ceph_sb_to_client(inode->i_sb)->wb_pagevec_pool);
@@ -725,9 +725,9 @@ static int ceph_writepages_start(struct address_space *mapping,
 	}
 	if (fsc->mount_options->wsize && fsc->mount_options->wsize < wsize)
 		wsize = fsc->mount_options->wsize;
-	if (wsize < PAGE_CACHE_SIZE)
-		wsize = PAGE_CACHE_SIZE;
-	max_pages_ever = wsize >> PAGE_CACHE_SHIFT;
+	if (wsize < PAGE_SIZE)
+		wsize = PAGE_SIZE;
+	max_pages_ever = wsize >> PAGE_SHIFT;
 
 	pagevec_init(&pvec, 0);
 
@@ -737,8 +737,8 @@ static int ceph_writepages_start(struct address_space *mapping,
 		end = -1;
 		dout(" cyclic, start at %lu\n", start);
 	} else {
-		start = wbc->range_start >> PAGE_CACHE_SHIFT;
-		end = wbc->range_end >> PAGE_CACHE_SHIFT;
+		start = wbc->range_start >> PAGE_SHIFT;
+		end = wbc->range_end >> PAGE_SHIFT;
 		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
 			range_whole = 1;
 		should_loop = 0;
@@ -778,17 +778,15 @@ retry:
 	while (!done && index <= end) {
 		unsigned i;
 		int first;
-		pgoff_t next;
-		int pvec_pages, locked_pages;
-		struct page **pages = NULL;
+		pgoff_t strip_unit_end = 0;
+		int num_ops = 0, op_idx;
+		int pvec_pages, locked_pages = 0;
+		struct page **pages = NULL, **data_pages;
 		mempool_t *pool = NULL;	/* Becomes non-null if mempool used */
 		struct page *page;
 		int want;
-		u64 offset, len;
-		long writeback_stat;
+		u64 offset = 0, len = 0;
 
-		next = 0;
-		locked_pages = 0;
 		max_pages = max_pages_ever;
 
 get_more_pages:
@@ -824,8 +822,8 @@ get_more_pages:
 				unlock_page(page);
 				break;
 			}
-			if (next && (page->index != next)) {
-				dout("not consecutive %p\n", page);
+			if (strip_unit_end && (page->index > strip_unit_end)) {
+				dout("end of strip unit %p\n", page);
 				unlock_page(page);
 				break;
 			}
@@ -867,36 +865,31 @@ get_more_pages:
 			/*
 			 * We have something to write.  If this is
 			 * the first locked page this time through,
-			 * allocate an osd request and a page array
-			 * that it will use.
+			 * calculate max possinle write size and
+			 * allocate a page array
 			 */
 			if (locked_pages == 0) {
-				BUG_ON(pages);
+				u64 objnum;
+				u64 objoff;
+
 				/* prepare async write request */
 				offset = (u64)page_offset(page);
 				len = wsize;
-				req = ceph_osdc_new_request(&fsc->client->osdc,
-							&ci->i_layout, vino,
-							offset, &len, 0,
-							do_sync ? 2 : 1,
-							CEPH_OSD_OP_WRITE,
-							CEPH_OSD_FLAG_WRITE |
-							CEPH_OSD_FLAG_ONDISK,
-							snapc, truncate_seq,
-							truncate_size, true);
-				if (IS_ERR(req)) {
-					rc = PTR_ERR(req);
+
+				rc = ceph_calc_file_object_mapping(&ci->i_layout,
+								offset, len,
+								&objnum, &objoff,
+								&len);
+				if (rc < 0) {
 					unlock_page(page);
 					break;
 				}
 
-				if (do_sync)
-					osd_req_op_init(req, 1,
-							CEPH_OSD_OP_STARTSYNC, 0);
-
-				req->r_callback = writepages_finish;
-				req->r_inode = inode;
+				num_ops = 1 + do_sync;
+				strip_unit_end = page->index +
+					((len - 1) >> PAGE_SHIFT);
 
+				BUG_ON(pages);
 				max_pages = calc_pages_for(0, (u64)len);
 				pages = kmalloc(max_pages * sizeof (*pages),
 						GFP_NOFS);
@@ -905,6 +898,20 @@ get_more_pages:
 					pages = mempool_alloc(pool, GFP_NOFS);
 					BUG_ON(!pages);
 				}
+
+				len = 0;
+			} else if (page->index !=
+				   (offset + len) >> PAGE_SHIFT) {
+				if (num_ops >= (pool ?  CEPH_OSD_SLAB_OPS :
+							CEPH_OSD_MAX_OPS)) {
+					redirty_page_for_writepage(wbc, page);
+					unlock_page(page);
+					break;
+				}
+
+				num_ops++;
+				offset = (u64)page_offset(page);
+				len = 0;
 			}
 
 			/* note position of first page in pvec */
@@ -913,18 +920,16 @@ get_more_pages:
 			dout("%p will write page %p idx %lu\n",
 			     inode, page, page->index);
 
-			writeback_stat =
-			       atomic_long_inc_return(&fsc->writeback_count);
-			if (writeback_stat > CONGESTION_ON_THRESH(
+			if (atomic_long_inc_return(&fsc->writeback_count) >
+			    CONGESTION_ON_THRESH(
 				    fsc->mount_options->congestion_kb)) {
 				set_bdi_congested(&fsc->backing_dev_info,
 						  BLK_RW_ASYNC);
 			}
 
-			set_page_writeback(page);
 			pages[locked_pages] = page;
 			locked_pages++;
-			next = page->index + 1;
+			len += PAGE_SIZE;
 		}
 
 		/* did we get anything? */
@@ -944,38 +949,119 @@ get_more_pages:
 			/* shift unused pages over in the pvec...  we
 			 * will need to release them below. */
 			for (j = i; j < pvec_pages; j++) {
-				dout(" pvec leftover page %p\n",
-				     pvec.pages[j]);
+				dout(" pvec leftover page %p\n", pvec.pages[j]);
 				pvec.pages[j-i+first] = pvec.pages[j];
 			}
 			pvec.nr -= i-first;
 		}
 
-		/* Format the osd request message and submit the write */
+new_request:
 		offset = page_offset(pages[0]);
-		len = (u64)locked_pages << PAGE_CACHE_SHIFT;
-		if (snap_size == -1) {
-			len = min(len, (u64)i_size_read(inode) - offset);
-			 /* writepages_finish() clears writeback pages
-			  * according to the data length, so make sure
-			  * data length covers all locked pages */
-			len = max(len, 1 +
-				((u64)(locked_pages - 1) << PAGE_CACHE_SHIFT));
-		} else {
-			len = min(len, snap_size - offset);
+		len = wsize;
+
+		req = ceph_osdc_new_request(&fsc->client->osdc,
+					&ci->i_layout, vino,
+					offset, &len, 0, num_ops,
+					CEPH_OSD_OP_WRITE,
+					CEPH_OSD_FLAG_WRITE |
+					CEPH_OSD_FLAG_ONDISK,
+					snapc, truncate_seq,
+					truncate_size, false);
+		if (IS_ERR(req)) {
+			req = ceph_osdc_new_request(&fsc->client->osdc,
+						&ci->i_layout, vino,
+						offset, &len, 0,
+						min(num_ops,
+						    CEPH_OSD_SLAB_OPS),
+						CEPH_OSD_OP_WRITE,
+						CEPH_OSD_FLAG_WRITE |
+						CEPH_OSD_FLAG_ONDISK,
+						snapc, truncate_seq,
+						truncate_size, true);
+			BUG_ON(IS_ERR(req));
 		}
-		dout("writepages got %d pages at %llu~%llu\n",
-		     locked_pages, offset, len);
+		BUG_ON(len < page_offset(pages[locked_pages - 1]) +
+			     PAGE_SIZE - offset);
 
-		osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0,
+		req->r_callback = writepages_finish;
+		req->r_inode = inode;
+
+		/* Format the osd request message and submit the write */
+		len = 0;
+		data_pages = pages;
+		op_idx = 0;
+		for (i = 0; i < locked_pages; i++) {
+			u64 cur_offset = page_offset(pages[i]);
+			if (offset + len != cur_offset) {
+				if (op_idx + do_sync + 1 == req->r_num_ops)
+					break;
+				osd_req_op_extent_dup_last(req, op_idx,
+							   cur_offset - offset);
+				dout("writepages got pages at %llu~%llu\n",
+				     offset, len);
+				osd_req_op_extent_osd_data_pages(req, op_idx,
+							data_pages, len, 0,
 							!!pool, false);
+				osd_req_op_extent_update(req, op_idx, len);
 
-		pages = NULL;	/* request message now owns the pages array */
-		pool = NULL;
+				len = 0;
+				offset = cur_offset; 
+				data_pages = pages + i;
+				op_idx++;
+			}
+
+			set_page_writeback(pages[i]);
+			len += PAGE_SIZE;
+		}
+
+		if (snap_size != -1) {
+			len = min(len, snap_size - offset);
+		} else if (i == locked_pages) {
+			/* writepages_finish() clears writeback pages
+			 * according to the data length, so make sure
+			 * data length covers all locked pages */
+			u64 min_len = len + 1 - PAGE_SIZE;
+			len = min(len, (u64)i_size_read(inode) - offset);
+			len = max(len, min_len);
+		}
+		dout("writepages got pages at %llu~%llu\n", offset, len);
 
-		/* Update the write op length in case we changed it */
+		osd_req_op_extent_osd_data_pages(req, op_idx, data_pages, len,
+						 0, !!pool, false);
+		osd_req_op_extent_update(req, op_idx, len);
+
+		if (do_sync) {
+			op_idx++;
+			osd_req_op_init(req, op_idx, CEPH_OSD_OP_STARTSYNC, 0);
+		}
+		BUG_ON(op_idx + 1 != req->r_num_ops);
 
-		osd_req_op_extent_update(req, 0, len);
+		pool = NULL;
+		if (i < locked_pages) {
+			BUG_ON(num_ops <= req->r_num_ops);
+			num_ops -= req->r_num_ops;
+			num_ops += do_sync;
+			locked_pages -= i;
+
+			/* allocate new pages array for next request */
+			data_pages = pages;
+			pages = kmalloc(locked_pages * sizeof (*pages),
+					GFP_NOFS);
+			if (!pages) {
+				pool = fsc->wb_pagevec_pool;
+				pages = mempool_alloc(pool, GFP_NOFS);
+				BUG_ON(!pages);
+			}
+			memcpy(pages, data_pages + i,
+			       locked_pages * sizeof(*pages));
+			memset(data_pages + i, 0,
+			       locked_pages * sizeof(*pages));
+		} else {
+			BUG_ON(num_ops != req->r_num_ops);
+			index = pages[i - 1]->index + 1;
+			/* request message now owns the pages array */
+			pages = NULL;
+		}
 
 		vino = ceph_vino(inode);
 		ceph_osdc_build_request(req, offset, snapc, vino.snap,
@@ -985,9 +1071,10 @@ get_more_pages:
 		BUG_ON(rc);
 		req = NULL;
 
-		/* continue? */
-		index = next;
-		wbc->nr_to_write -= locked_pages;
+		wbc->nr_to_write -= i;
+		if (pages)
+			goto new_request;
+
 		if (wbc->nr_to_write <= 0)
 			done = 1;
 
@@ -1048,8 +1135,8 @@ static int ceph_update_writeable_page(struct file *file,
 {
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	loff_t page_off = pos & PAGE_CACHE_MASK;
-	int pos_in_page = pos & ~PAGE_CACHE_MASK;
+	loff_t page_off = pos & PAGE_MASK;
+	int pos_in_page = pos & ~PAGE_MASK;
 	int end_in_page = pos_in_page + len;
 	loff_t i_size;
 	int r;
@@ -1104,20 +1191,20 @@ retry_locked:
 	}
 
 	/* full page? */
-	if (pos_in_page == 0 && len == PAGE_CACHE_SIZE)
+	if (pos_in_page == 0 && len == PAGE_SIZE)
 		return 0;
 
 	/* past end of file? */
-	i_size = inode->i_size;   /* caller holds i_mutex */
+	i_size = i_size_read(inode);
 
 	if (page_off >= i_size ||
 	    (pos_in_page == 0 && (pos+len) >= i_size &&
-	     end_in_page - pos_in_page != PAGE_CACHE_SIZE)) {
+	     end_in_page - pos_in_page != PAGE_SIZE)) {
 		dout(" zeroing %p 0 - %d and %d - %d\n",
-		     page, pos_in_page, end_in_page, (int)PAGE_CACHE_SIZE);
+		     page, pos_in_page, end_in_page, (int)PAGE_SIZE);
 		zero_user_segments(page,
 				   0, pos_in_page,
-				   end_in_page, PAGE_CACHE_SIZE);
+				   end_in_page, PAGE_SIZE);
 		return 0;
 	}
 
@@ -1141,7 +1228,7 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping,
 {
 	struct inode *inode = file_inode(file);
 	struct page *page;
-	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+	pgoff_t index = pos >> PAGE_SHIFT;
 	int r;
 
 	do {
@@ -1149,14 +1236,13 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping,
 		page = grab_cache_page_write_begin(mapping, index, 0);
 		if (!page)
 			return -ENOMEM;
-		*pagep = page;
 
 		dout("write_begin file %p inode %p page %p %d~%d\n", file,
 		     inode, page, (int)pos, (int)len);
 
 		r = ceph_update_writeable_page(file, pos, len, page);
 		if (r < 0)
-			page_cache_release(page);
+			put_page(page);
 		else
 			*pagep = page;
 	} while (r == -EAGAIN);
@@ -1173,7 +1259,7 @@ static int ceph_write_end(struct file *file, struct address_space *mapping,
 			  struct page *page, void *fsdata)
 {
 	struct inode *inode = file_inode(file);
-	unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+	unsigned from = pos & (PAGE_SIZE - 1);
 	int check_cap = 0;
 
 	dout("write_end file %p inode %p page %p %d~%d (%d)\n", file,
@@ -1184,8 +1270,7 @@ static int ceph_write_end(struct file *file, struct address_space *mapping,
 		zero_user_segment(page, from+copied, len);
 
 	/* did file size increase? */
-	/* (no need for i_size_read(); we caller holds i_mutex */
-	if (pos+copied > inode->i_size)
+	if (pos+copied > i_size_read(inode))
 		check_cap = ceph_inode_set_size(inode, pos+copied);
 
 	if (!PageUptodate(page))
@@ -1194,7 +1279,7 @@ static int ceph_write_end(struct file *file, struct address_space *mapping,
 	set_page_dirty(page);
 
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 
 	if (check_cap)
 		ceph_check_caps(ceph_inode(inode), CHECK_CAPS_AUTHONLY, NULL);
@@ -1237,11 +1322,11 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_file_info *fi = vma->vm_file->private_data;
 	struct page *pinned_page = NULL;
-	loff_t off = vmf->pgoff << PAGE_CACHE_SHIFT;
+	loff_t off = vmf->pgoff << PAGE_SHIFT;
 	int want, got, ret;
 
 	dout("filemap_fault %p %llx.%llx %llu~%zd trying to get caps\n",
-	     inode, ceph_vinop(inode), off, (size_t)PAGE_CACHE_SIZE);
+	     inode, ceph_vinop(inode), off, (size_t)PAGE_SIZE);
 	if (fi->fmode & CEPH_FILE_MODE_LAZY)
 		want = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
 	else
@@ -1258,7 +1343,7 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		}
 	}
 	dout("filemap_fault %p %llu~%zd got cap refs on %s\n",
-	     inode, off, (size_t)PAGE_CACHE_SIZE, ceph_cap_string(got));
+	     inode, off, (size_t)PAGE_SIZE, ceph_cap_string(got));
 
 	if ((got & (CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO)) ||
 	    ci->i_inline_version == CEPH_INLINE_NONE)
@@ -1267,24 +1352,24 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		ret = -EAGAIN;
 
 	dout("filemap_fault %p %llu~%zd dropping cap refs on %s ret %d\n",
-	     inode, off, (size_t)PAGE_CACHE_SIZE, ceph_cap_string(got), ret);
+	     inode, off, (size_t)PAGE_SIZE, ceph_cap_string(got), ret);
 	if (pinned_page)
-		page_cache_release(pinned_page);
+		put_page(pinned_page);
 	ceph_put_cap_refs(ci, got);
 
 	if (ret != -EAGAIN)
 		return ret;
 
 	/* read inline data */
-	if (off >= PAGE_CACHE_SIZE) {
+	if (off >= PAGE_SIZE) {
 		/* does not support inline data > PAGE_SIZE */
 		ret = VM_FAULT_SIGBUS;
 	} else {
 		int ret1;
 		struct address_space *mapping = inode->i_mapping;
 		struct page *page = find_or_create_page(mapping, 0,
-						mapping_gfp_mask(mapping) &
-						~__GFP_FS);
+						mapping_gfp_constraint(mapping,
+						~__GFP_FS));
 		if (!page) {
 			ret = VM_FAULT_OOM;
 			goto out;
@@ -1293,12 +1378,12 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 					 CEPH_STAT_CAP_INLINE_DATA, true);
 		if (ret1 < 0 || off >= i_size_read(inode)) {
 			unlock_page(page);
-			page_cache_release(page);
+			put_page(page);
 			ret = VM_FAULT_SIGBUS;
 			goto out;
 		}
-		if (ret1 < PAGE_CACHE_SIZE)
-			zero_user_segment(page, ret1, PAGE_CACHE_SIZE);
+		if (ret1 < PAGE_SIZE)
+			zero_user_segment(page, ret1, PAGE_SIZE);
 		else
 			flush_dcache_page(page);
 		SetPageUptodate(page);
@@ -1307,7 +1392,7 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	}
 out:
 	dout("filemap_fault %p %llu~%zd read inline data ret %d\n",
-	     inode, off, (size_t)PAGE_CACHE_SIZE, ret);
+	     inode, off, (size_t)PAGE_SIZE, ret);
 	return ret;
 }
 
@@ -1345,10 +1430,10 @@ static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 		}
 	}
 
-	if (off + PAGE_CACHE_SIZE <= size)
-		len = PAGE_CACHE_SIZE;
+	if (off + PAGE_SIZE <= size)
+		len = PAGE_SIZE;
 	else
-		len = size & ~PAGE_CACHE_MASK;
+		len = size & ~PAGE_MASK;
 
 	dout("page_mkwrite %p %llx.%llx %llu~%zd getting caps i_size %llu\n",
 	     inode, ceph_vinop(inode), off, len, size);
@@ -1378,11 +1463,13 @@ static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 	ret = VM_FAULT_NOPAGE;
 	if ((off > size) ||
-	    (page->mapping != inode->i_mapping))
+	    (page->mapping != inode->i_mapping)) {
+		unlock_page(page);
 		goto out;
+	}
 
 	ret = ceph_update_writeable_page(vma->vm_file, off, len, page);
-	if (ret == 0) {
+	if (ret >= 0) {
 		/* success.  we'll keep the page locked. */
 		set_page_dirty(page);
 		ret = VM_FAULT_LOCKED;
@@ -1393,8 +1480,6 @@ static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 			ret = VM_FAULT_SIGBUS;
 	}
 out:
-	if (ret != VM_FAULT_LOCKED)
-		unlock_page(page);
 	if (ret == VM_FAULT_LOCKED ||
 	    ci->i_inline_version != CEPH_INLINE_NONE) {
 		int dirty;
@@ -1428,12 +1513,13 @@ void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
 		if (i_size_read(inode) == 0)
 			return;
 		page = find_or_create_page(mapping, 0,
-					   mapping_gfp_mask(mapping) & ~__GFP_FS);
+					   mapping_gfp_constraint(mapping,
+					   ~__GFP_FS));
 		if (!page)
 			return;
 		if (PageUptodate(page)) {
 			unlock_page(page);
-			page_cache_release(page);
+			put_page(page);
 			return;
 		}
 	}
@@ -1448,14 +1534,14 @@ void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
 	}
 
 	if (page != locked_page) {
-		if (len < PAGE_CACHE_SIZE)
-			zero_user_segment(page, len, PAGE_CACHE_SIZE);
+		if (len < PAGE_SIZE)
+			zero_user_segment(page, len, PAGE_SIZE);
 		else
 			flush_dcache_page(page);
 
 		SetPageUptodate(page);
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 	}
 }
 
@@ -1492,7 +1578,7 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page)
 				from_pagecache = true;
 				lock_page(page);
 			} else {
-				page_cache_release(page);
+				put_page(page);
 				page = NULL;
 			}
 		}
@@ -1500,8 +1586,8 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page)
 
 	if (page) {
 		len = i_size_read(inode);
-		if (len > PAGE_CACHE_SIZE)
-			len = PAGE_CACHE_SIZE;
+		if (len > PAGE_SIZE)
+			len = PAGE_SIZE;
 	} else {
 		page = __page_cache_alloc(GFP_NOFS);
 		if (!page) {
@@ -1523,7 +1609,7 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page)
 				    ceph_vino(inode), 0, &len, 0, 1,
 				    CEPH_OSD_OP_CREATE,
 				    CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE,
-				    ceph_empty_snapc, 0, 0, false);
+				    NULL, 0, 0, false);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto out;
@@ -1541,9 +1627,8 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page)
 				    ceph_vino(inode), 0, &len, 1, 3,
 				    CEPH_OSD_OP_WRITE,
 				    CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE,
-				    ceph_empty_snapc,
-				    ci->i_truncate_seq, ci->i_truncate_size,
-				    false);
+				    NULL, ci->i_truncate_seq,
+				    ci->i_truncate_size, false);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto out;
@@ -1585,7 +1670,7 @@ out:
 	if (page && page != locked_page) {
 		if (from_pagecache) {
 			unlock_page(page);
-			page_cache_release(page);
+			put_page(page);
 		} else
 			__free_pages(page, 0);
 	}
@@ -1664,8 +1749,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool)
 		goto out;
 	}
 
-	rd_req = ceph_osdc_alloc_request(&fsc->client->osdc,
-					 ceph_empty_snapc,
+	rd_req = ceph_osdc_alloc_request(&fsc->client->osdc, NULL,
 					 1, false, GFP_NOFS);
 	if (!rd_req) {
 		err = -ENOMEM;
@@ -1679,8 +1763,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool)
 		 "%llx.00000000", ci->i_vino.ino);
 	rd_req->r_base_oid.name_len = strlen(rd_req->r_base_oid.name);
 
-	wr_req = ceph_osdc_alloc_request(&fsc->client->osdc,
-					 ceph_empty_snapc,
+	wr_req = ceph_osdc_alloc_request(&fsc->client->osdc, NULL,
 					 1, false, GFP_NOFS);
 	if (!wr_req) {
 		err = -ENOMEM;
@@ -1757,6 +1840,10 @@ int ceph_pool_perm_check(struct ceph_inode_info *ci, int need)
 	u32 pool;
 	int ret, flags;
 
+	/* does not support pool namespace yet */
+	if (ci->i_pool_ns_len)
+		return -EIO;
+
 	if (ceph_test_mount_opt(ceph_inode_to_client(&ci->vfs_inode),
 				NOPOOLPERM))
 		return 0;
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
index 834f9f3723fb..a351480dbabc 100644
--- a/fs/ceph/cache.c
+++ b/fs/ceph/cache.c
@@ -88,7 +88,7 @@ static uint16_t ceph_fscache_inode_get_key(const void *cookie_netfs_data,
 	const struct ceph_inode_info* ci = cookie_netfs_data;
 	uint16_t klen;
 
-	/* use ceph virtual inode (id + snaphot) */
+	/* use ceph virtual inode (id + snapshot) */
 	klen = sizeof(ci->i_vino);
 	if (klen > maxbuf)
 		return 0;
@@ -106,7 +106,7 @@ static uint16_t ceph_fscache_inode_get_aux(const void *cookie_netfs_data,
 
 	memset(&aux, 0, sizeof(aux));
 	aux.mtime = inode->i_mtime;
-	aux.size = inode->i_size;
+	aux.size = i_size_read(inode);
 
 	memcpy(buffer, &aux, sizeof(aux));
 
@@ -117,9 +117,7 @@ static void ceph_fscache_inode_get_attr(const void *cookie_netfs_data,
 					uint64_t *size)
 {
 	const struct ceph_inode_info* ci = cookie_netfs_data;
-	const struct inode* inode = &ci->vfs_inode;
-
-	*size = inode->i_size;
+	*size = i_size_read(&ci->vfs_inode);
 }
 
 static enum fscache_checkaux ceph_fscache_inode_check_aux(
@@ -134,7 +132,7 @@ static enum fscache_checkaux ceph_fscache_inode_check_aux(
 
 	memset(&aux, 0, sizeof(aux));
 	aux.mtime = inode->i_mtime;
-	aux.size = inode->i_size;
+	aux.size = i_size_read(inode);
 
 	if (memcmp(data, &aux, sizeof(aux)) != 0)
 		return FSCACHE_CHECKAUX_OBSOLETE;
@@ -197,7 +195,7 @@ void ceph_fscache_register_inode_cookie(struct ceph_fs_client* fsc,
 		return;
 
 	/* Avoid multiple racing open requests */
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	if (ci->fscache)
 		goto done;
@@ -207,7 +205,7 @@ void ceph_fscache_register_inode_cookie(struct ceph_fs_client* fsc,
 					     ci, true);
 	fscache_check_consistency(ci->fscache);
 done:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 }
 
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 27b566874bc1..cfaeef18cbca 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -991,7 +991,7 @@ static int send_cap_msg(struct ceph_mds_session *session,
 			u32 seq, u64 flush_tid, u64 oldest_flush_tid,
 			u32 issue_seq, u32 mseq, u64 size, u64 max_size,
 			struct timespec *mtime, struct timespec *atime,
-			u64 time_warp_seq,
+			struct timespec *ctime, u64 time_warp_seq,
 			kuid_t uid, kgid_t gid, umode_t mode,
 			u64 xattr_version,
 			struct ceph_buffer *xattrs_buf,
@@ -1042,6 +1042,8 @@ static int send_cap_msg(struct ceph_mds_session *session,
 		ceph_encode_timespec(&fc->mtime, mtime);
 	if (atime)
 		ceph_encode_timespec(&fc->atime, atime);
+	if (ctime)
+		ceph_encode_timespec(&fc->ctime, ctime);
 	fc->time_warp_seq = cpu_to_le32(time_warp_seq);
 
 	fc->uid = cpu_to_le32(from_kuid(&init_user_ns, uid));
@@ -1116,7 +1118,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
 	int held, revoking, dropping, keep;
 	u64 seq, issue_seq, mseq, time_warp_seq, follows;
 	u64 size, max_size;
-	struct timespec mtime, atime;
+	struct timespec mtime, atime, ctime;
 	int wake = 0;
 	umode_t mode;
 	kuid_t uid;
@@ -1180,6 +1182,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
 	ci->i_requested_max_size = max_size;
 	mtime = inode->i_mtime;
 	atime = inode->i_atime;
+	ctime = inode->i_ctime;
 	time_warp_seq = ci->i_time_warp_seq;
 	uid = inode->i_uid;
 	gid = inode->i_gid;
@@ -1198,7 +1201,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
 	ret = send_cap_msg(session, ceph_vino(inode).ino, cap_id,
 		op, keep, want, flushing, seq,
 		flush_tid, oldest_flush_tid, issue_seq, mseq,
-		size, max_size, &mtime, &atime, time_warp_seq,
+		size, max_size, &mtime, &atime, &ctime, time_warp_seq,
 		uid, gid, mode, xattr_version, xattr_blob,
 		follows, inline_data);
 	if (ret < 0) {
@@ -1320,7 +1323,7 @@ retry:
 			     capsnap->dirty, 0, capsnap->flush_tid, 0,
 			     0, mseq, capsnap->size, 0,
 			     &capsnap->mtime, &capsnap->atime,
-			     capsnap->time_warp_seq,
+			     &capsnap->ctime, capsnap->time_warp_seq,
 			     capsnap->uid, capsnap->gid, capsnap->mode,
 			     capsnap->xattr_version, capsnap->xattr_blob,
 			     capsnap->follows, capsnap->inline_data);
@@ -1655,9 +1658,8 @@ retry_locked:
 	    !S_ISDIR(inode->i_mode) &&		/* ignore readdir cache */
 	    ci->i_wrbuffer_ref == 0 &&		/* no dirty pages... */
 	    inode->i_data.nrpages &&		/* have cached pages */
-	    (file_wanted == 0 ||		/* no open files */
-	     (revoking & (CEPH_CAP_FILE_CACHE|
-			  CEPH_CAP_FILE_LAZYIO))) && /*  or revoking cache */
+	    (revoking & (CEPH_CAP_FILE_CACHE|
+			 CEPH_CAP_FILE_LAZYIO)) && /*  or revoking cache */
 	    !tried_invalidate) {
 		dout("check_caps trying to invalidate on %p\n", inode);
 		if (try_nonblocking_invalidate(inode) < 0) {
@@ -1971,49 +1973,46 @@ out:
 }
 
 /*
- * wait for any uncommitted directory operations to commit.
+ * wait for any unsafe requests to complete.
  */
-static int unsafe_dirop_wait(struct inode *inode)
+static int unsafe_request_wait(struct inode *inode)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct list_head *head = &ci->i_unsafe_dirops;
-	struct ceph_mds_request *req;
-	u64 last_tid;
-	int ret = 0;
-
-	if (!S_ISDIR(inode->i_mode))
-		return 0;
+	struct ceph_mds_request *req1 = NULL, *req2 = NULL;
+	int ret, err = 0;
 
 	spin_lock(&ci->i_unsafe_lock);
-	if (list_empty(head))
-		goto out;
-
-	req = list_last_entry(head, struct ceph_mds_request,
-			      r_unsafe_dir_item);
-	last_tid = req->r_tid;
-
-	do {
-		ceph_mdsc_get_request(req);
-		spin_unlock(&ci->i_unsafe_lock);
+	if (S_ISDIR(inode->i_mode) && !list_empty(&ci->i_unsafe_dirops)) {
+		req1 = list_last_entry(&ci->i_unsafe_dirops,
+					struct ceph_mds_request,
+					r_unsafe_dir_item);
+		ceph_mdsc_get_request(req1);
+	}
+	if (!list_empty(&ci->i_unsafe_iops)) {
+		req2 = list_last_entry(&ci->i_unsafe_iops,
+					struct ceph_mds_request,
+					r_unsafe_target_item);
+		ceph_mdsc_get_request(req2);
+	}
+	spin_unlock(&ci->i_unsafe_lock);
 
-		dout("unsafe_dirop_wait %p wait on tid %llu (until %llu)\n",
-		     inode, req->r_tid, last_tid);
-		ret = !wait_for_completion_timeout(&req->r_safe_completion,
-					ceph_timeout_jiffies(req->r_timeout));
+	dout("unsafe_requeset_wait %p wait on tid %llu %llu\n",
+	     inode, req1 ? req1->r_tid : 0ULL, req2 ? req2->r_tid : 0ULL);
+	if (req1) {
+		ret = !wait_for_completion_timeout(&req1->r_safe_completion,
+					ceph_timeout_jiffies(req1->r_timeout));
 		if (ret)
-			ret = -EIO;  /* timed out */
-
-		ceph_mdsc_put_request(req);
-
-		spin_lock(&ci->i_unsafe_lock);
-		if (ret || list_empty(head))
-			break;
-		req = list_first_entry(head, struct ceph_mds_request,
-				       r_unsafe_dir_item);
-	} while (req->r_tid < last_tid);
-out:
-	spin_unlock(&ci->i_unsafe_lock);
-	return ret;
+			err = -EIO;
+		ceph_mdsc_put_request(req1);
+	}
+	if (req2) {
+		ret = !wait_for_completion_timeout(&req2->r_safe_completion,
+					ceph_timeout_jiffies(req2->r_timeout));
+		if (ret)
+			err = -EIO;
+		ceph_mdsc_put_request(req2);
+	}
+	return err;
 }
 
 int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync)
@@ -2034,12 +2033,12 @@ int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	if (datasync)
 		goto out;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	dirty = try_flush_caps(inode, &flush_tid);
 	dout("fsync dirty caps are %s\n", ceph_cap_string(dirty));
 
-	ret = unsafe_dirop_wait(inode);
+	ret = unsafe_request_wait(inode);
 
 	/*
 	 * only wait on non-file metadata writeback (the mds
@@ -2050,7 +2049,7 @@ int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 		ret = wait_event_interruptible(ci->i_cap_wq,
 					caps_are_flushed(inode, flush_tid));
 	}
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 out:
 	dout("fsync %p%s result=%d\n", inode, datasync ? " datasync" : "", ret);
 	return ret;
@@ -2511,7 +2510,7 @@ int ceph_get_caps(struct ceph_inode_info *ci, int need, int want,
 					*pinned_page = page;
 					break;
 				}
-				page_cache_release(page);
+				put_page(page);
 			}
 			/*
 			 * drop cap refs first because getattr while
@@ -2757,7 +2756,8 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 			     void *inline_data, int inline_len,
 			     struct ceph_buffer *xattr_buf,
 			     struct ceph_mds_session *session,
-			     struct ceph_cap *cap, int issued)
+			     struct ceph_cap *cap, int issued,
+			     u32 pool_ns_len)
 	__releases(ci->i_ceph_lock)
 	__releases(mdsc->snap_rwsem)
 {
@@ -2877,6 +2877,8 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 	if (newcaps & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR)) {
 		/* file layout may have changed */
 		ci->i_layout = grant->layout;
+		ci->i_pool_ns_len = pool_ns_len;
+
 		/* size/truncate_seq? */
 		queue_trunc = ceph_fill_file_size(inode, issued,
 					le32_to_cpu(grant->truncate_seq),
@@ -3415,6 +3417,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	u32  inline_len = 0;
 	void *snaptrace;
 	size_t snaptrace_len;
+	u32 pool_ns_len = 0;
 	void *p, *end;
 
 	dout("handle_caps from mds%d\n", mds);
@@ -3467,6 +3470,21 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		p += inline_len;
 	}
 
+	if (le16_to_cpu(msg->hdr.version) >= 8) {
+		u64 flush_tid;
+		u32 caller_uid, caller_gid;
+		u32 osd_epoch_barrier;
+		/* version >= 5 */
+		ceph_decode_32_safe(&p, end, osd_epoch_barrier, bad);
+		/* version >= 6 */
+		ceph_decode_64_safe(&p, end, flush_tid, bad);
+		/* version >= 7 */
+		ceph_decode_32_safe(&p, end, caller_uid, bad);
+		ceph_decode_32_safe(&p, end, caller_gid, bad);
+		/* version >= 8 */
+		ceph_decode_32_safe(&p, end, pool_ns_len, bad);
+	}
+
 	/* lookup ino */
 	inode = ceph_find_inode(sb, vino);
 	ci = ceph_inode(inode);
@@ -3522,7 +3540,8 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 				  &cap, &issued);
 		handle_cap_grant(mdsc, inode, h,
 				 inline_version, inline_data, inline_len,
-				 msg->middle, session, cap, issued);
+				 msg->middle, session, cap, issued,
+				 pool_ns_len);
 		if (realm)
 			ceph_put_snap_realm(mdsc, realm);
 		goto done_unlocked;
@@ -3546,7 +3565,8 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		issued |= __ceph_caps_dirty(ci);
 		handle_cap_grant(mdsc, inode, h,
 				 inline_version, inline_data, inline_len,
-				 msg->middle, session, cap, issued);
+				 msg->middle, session, cap, issued,
+				 pool_ns_len);
 		goto done_unlocked;
 
 	case CEPH_CAP_OP_FLUSH_ACK:
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 9314b4ea2375..4fb2bbc2a272 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -38,7 +38,7 @@ int ceph_init_dentry(struct dentry *dentry)
 	if (dentry->d_fsdata)
 		return 0;
 
-	di = kmem_cache_alloc(ceph_dentry_cachep, GFP_KERNEL | __GFP_ZERO);
+	di = kmem_cache_zalloc(ceph_dentry_cachep, GFP_KERNEL);
 	if (!di)
 		return -ENOMEM;          /* oh well */
 
@@ -68,23 +68,6 @@ out_unlock:
 	return 0;
 }
 
-struct inode *ceph_get_dentry_parent_inode(struct dentry *dentry)
-{
-	struct inode *inode = NULL;
-
-	if (!dentry)
-		return NULL;
-
-	spin_lock(&dentry->d_lock);
-	if (!IS_ROOT(dentry)) {
-		inode = d_inode(dentry->d_parent);
-		ihold(inode);
-	}
-	spin_unlock(&dentry->d_lock);
-	return inode;
-}
-
-
 /*
  * for readdir, we encode the directory frag and offset within that
  * frag into f_pos.
@@ -146,7 +129,7 @@ static int __dcache_readdir(struct file *file,  struct dir_context *ctx,
 	struct inode *dir = d_inode(parent);
 	struct dentry *dentry, *last = NULL;
 	struct ceph_dentry_info *di;
-	unsigned nsize = PAGE_CACHE_SIZE / sizeof(struct dentry *);
+	unsigned nsize = PAGE_SIZE / sizeof(struct dentry *);
 	int err = 0;
 	loff_t ptr_pos = 0;
 	struct ceph_readdir_cache_control cache_ctl = {};
@@ -171,7 +154,7 @@ static int __dcache_readdir(struct file *file,  struct dir_context *ctx,
 		}
 
 		err = -EAGAIN;
-		pgoff = ptr_pos >> PAGE_CACHE_SHIFT;
+		pgoff = ptr_pos >> PAGE_SHIFT;
 		if (!cache_ctl.page || pgoff != page_index(cache_ctl.page)) {
 			ceph_readdir_cache_release(&cache_ctl);
 			cache_ctl.page = find_lock_page(&dir->i_data, pgoff);
@@ -507,7 +490,7 @@ static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int whence)
 	loff_t old_offset = ceph_make_fpos(fi->frag, fi->next_offset);
 	loff_t retval;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	retval = -EINVAL;
 	switch (whence) {
 	case SEEK_CUR:
@@ -542,7 +525,7 @@ static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int whence)
 		}
 	}
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return retval;
 }
 
@@ -624,6 +607,7 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	int op;
+	int mask;
 	int err;
 
 	dout("lookup %p dentry %p '%pd'\n",
@@ -666,8 +650,12 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
 		return ERR_CAST(req);
 	req->r_dentry = dget(dentry);
 	req->r_num_caps = 2;
-	/* we only need inode linkage */
-	req->r_args.getattr.mask = cpu_to_le32(CEPH_STAT_CAP_INODE);
+
+	mask = CEPH_STAT_CAP_INODE | CEPH_CAP_AUTH_SHARED;
+	if (ceph_security_xattr_wanted(dir))
+		mask |= CEPH_CAP_XATTR_SHARED;
+	req->r_args.getattr.mask = cpu_to_le32(mask);
+
 	req->r_locked_dir = dir;
 	err = ceph_mdsc_do_request(mdsc, NULL, req);
 	err = ceph_handle_snapdir(req, dentry, err);
@@ -1095,6 +1083,7 @@ static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry)
 static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	int valid = 0;
+	struct dentry *parent;
 	struct inode *dir;
 
 	if (flags & LOOKUP_RCU)
@@ -1103,7 +1092,8 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 	dout("d_revalidate %p '%pd' inode %p offset %lld\n", dentry,
 	     dentry, d_inode(dentry), ceph_dentry(dentry)->offset);
 
-	dir = ceph_get_dentry_parent_inode(dentry);
+	parent = dget_parent(dentry);
+	dir = d_inode(parent);
 
 	/* always trust cached snapped dentries, snapdir dentry */
 	if (ceph_snap(dir) != CEPH_NOSNAP) {
@@ -1121,13 +1111,48 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 			valid = 1;
 	}
 
+	if (!valid) {
+		struct ceph_mds_client *mdsc =
+			ceph_sb_to_client(dir->i_sb)->mdsc;
+		struct ceph_mds_request *req;
+		int op, mask, err;
+
+		op = ceph_snap(dir) == CEPH_SNAPDIR ?
+			CEPH_MDS_OP_LOOKUPSNAP : CEPH_MDS_OP_LOOKUP;
+		req = ceph_mdsc_create_request(mdsc, op, USE_ANY_MDS);
+		if (!IS_ERR(req)) {
+			req->r_dentry = dget(dentry);
+			req->r_num_caps = 2;
+
+			mask = CEPH_STAT_CAP_INODE | CEPH_CAP_AUTH_SHARED;
+			if (ceph_security_xattr_wanted(dir))
+				mask |= CEPH_CAP_XATTR_SHARED;
+			req->r_args.getattr.mask = mask;
+
+			req->r_locked_dir = dir;
+			err = ceph_mdsc_do_request(mdsc, NULL, req);
+			if (err == 0 || err == -ENOENT) {
+				if (dentry == req->r_dentry) {
+					valid = !d_unhashed(dentry);
+				} else {
+					d_invalidate(req->r_dentry);
+					err = -EAGAIN;
+				}
+			}
+			ceph_mdsc_put_request(req);
+			dout("d_revalidate %p lookup result=%d\n",
+			     dentry, err);
+		}
+	}
+
 	dout("d_revalidate %p %s\n", dentry, valid ? "valid" : "invalid");
 	if (valid) {
 		ceph_dentry_lru_touch(dentry);
 	} else {
 		ceph_dir_clear_complete(dir);
 	}
-	iput(dir);
+
+	dput(parent);
 	return valid;
 }
 
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index fe02ae7f056a..6e72c98162d5 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -71,12 +71,18 @@ static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino)
 	inode = ceph_find_inode(sb, vino);
 	if (!inode) {
 		struct ceph_mds_request *req;
+		int mask;
 
 		req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPINO,
 					       USE_ANY_MDS);
 		if (IS_ERR(req))
 			return ERR_CAST(req);
 
+		mask = CEPH_STAT_CAP_INODE;
+		if (ceph_security_xattr_wanted(d_inode(sb->s_root)))
+			mask |= CEPH_CAP_XATTR_SHARED;
+		req->r_args.getattr.mask = cpu_to_le32(mask);
+
 		req->r_ino1 = vino;
 		req->r_num_caps = 1;
 		err = ceph_mdsc_do_request(mdsc, NULL, req);
@@ -128,6 +134,7 @@ static struct dentry *__get_parent(struct super_block *sb,
 	struct ceph_mds_request *req;
 	struct inode *inode;
 	struct dentry *dentry;
+	int mask;
 	int err;
 
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPPARENT,
@@ -144,6 +151,12 @@ static struct dentry *__get_parent(struct super_block *sb,
 			.snap = CEPH_NOSNAP,
 		};
 	}
+
+	mask = CEPH_STAT_CAP_INODE;
+	if (ceph_security_xattr_wanted(d_inode(sb->s_root)))
+		mask |= CEPH_CAP_XATTR_SHARED;
+	req->r_args.getattr.mask = cpu_to_le32(mask);
+
 	req->r_num_caps = 1;
 	err = ceph_mdsc_do_request(mdsc, NULL, req);
 	inode = req->r_target_inode;
@@ -215,7 +228,7 @@ static int ceph_get_name(struct dentry *parent, char *name,
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	mutex_lock(&d_inode(parent)->i_mutex);
+	inode_lock(d_inode(parent));
 
 	req->r_inode = d_inode(child);
 	ihold(d_inode(child));
@@ -224,7 +237,7 @@ static int ceph_get_name(struct dentry *parent, char *name,
 	req->r_num_caps = 2;
 	err = ceph_mdsc_do_request(mdsc, NULL, req);
 
-	mutex_unlock(&d_inode(parent)->i_mutex);
+	inode_unlock(d_inode(parent));
 
 	if (!err) {
 		struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 0c62868b5c56..a79f9269831e 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -34,6 +34,74 @@
  * need to wait for MDS acknowledgement.
  */
 
+/*
+ * Calculate the length sum of direct io vectors that can
+ * be combined into one page vector.
+ */
+static size_t dio_get_pagev_size(const struct iov_iter *it)
+{
+    const struct iovec *iov = it->iov;
+    const struct iovec *iovend = iov + it->nr_segs;
+    size_t size;
+
+    size = iov->iov_len - it->iov_offset;
+    /*
+     * An iov can be page vectored when both the current tail
+     * and the next base are page aligned.
+     */
+    while (PAGE_ALIGNED((iov->iov_base + iov->iov_len)) &&
+           (++iov < iovend && PAGE_ALIGNED((iov->iov_base)))) {
+        size += iov->iov_len;
+    }
+    dout("dio_get_pagevlen len = %zu\n", size);
+    return size;
+}
+
+/*
+ * Allocate a page vector based on (@it, @nbytes).
+ * The return value is the tuple describing a page vector,
+ * that is (@pages, @page_align, @num_pages).
+ */
+static struct page **
+dio_get_pages_alloc(const struct iov_iter *it, size_t nbytes,
+		    size_t *page_align, int *num_pages)
+{
+	struct iov_iter tmp_it = *it;
+	size_t align;
+	struct page **pages;
+	int ret = 0, idx, npages;
+
+	align = (unsigned long)(it->iov->iov_base + it->iov_offset) &
+		(PAGE_SIZE - 1);
+	npages = calc_pages_for(align, nbytes);
+	pages = kmalloc(sizeof(*pages) * npages, GFP_KERNEL);
+	if (!pages) {
+		pages = vmalloc(sizeof(*pages) * npages);
+		if (!pages)
+			return ERR_PTR(-ENOMEM);
+	}
+
+	for (idx = 0; idx < npages; ) {
+		size_t start;
+		ret = iov_iter_get_pages(&tmp_it, pages + idx, nbytes,
+					 npages - idx, &start);
+		if (ret < 0)
+			goto fail;
+
+		iov_iter_advance(&tmp_it, ret);
+		nbytes -= ret;
+		idx += (ret + start + PAGE_SIZE - 1) / PAGE_SIZE;
+	}
+
+	BUG_ON(nbytes != 0);
+	*num_pages = npages;
+	*page_align = align;
+	dout("dio_get_pages_alloc: got %d pages align %zu\n", npages, align);
+	return pages;
+fail:
+	ceph_put_page_vector(pages, idx, false);
+	return ERR_PTR(ret);
+}
 
 /*
  * Prepare an open request.  Preallocate ceph_cap to avoid an
@@ -89,7 +157,7 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
 	case S_IFDIR:
 		dout("init_file %p %p 0%o (regular)\n", inode, file,
 		     inode->i_mode);
-		cf = kmem_cache_alloc(ceph_file_cachep, GFP_KERNEL | __GFP_ZERO);
+		cf = kmem_cache_zalloc(ceph_file_cachep, GFP_KERNEL);
 		if (cf == NULL) {
 			ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */
 			return -ENOMEM;
@@ -232,6 +300,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 	struct ceph_mds_request *req;
 	struct dentry *dn;
 	struct ceph_acls_info acls = {};
+       int mask;
 	int err;
 
 	dout("atomic_open %p dentry %p '%pd' %s flags %d mode 0%o\n",
@@ -267,6 +336,12 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 			acls.pagelist = NULL;
 		}
 	}
+
+       mask = CEPH_STAT_CAP_INODE | CEPH_CAP_AUTH_SHARED;
+       if (ceph_security_xattr_wanted(dir))
+               mask |= CEPH_CAP_XATTR_SHARED;
+       req->r_args.open.mask = cpu_to_le32(mask);
+
 	req->r_locked_dir = dir;           /* caller holds dir->i_mutex */
 	err = ceph_mdsc_do_request(mdsc,
 				   (flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
@@ -329,8 +404,9 @@ int ceph_release(struct inode *inode, struct file *file)
 }
 
 enum {
-	CHECK_EOF = 1,
-	READ_INLINE = 2,
+	HAVE_RETRIED = 1,
+	CHECK_EOF =    2,
+	READ_INLINE =  3,
 };
 
 /*
@@ -343,17 +419,15 @@ enum {
 static int striped_read(struct inode *inode,
 			u64 off, u64 len,
 			struct page **pages, int num_pages,
-			int *checkeof, bool o_direct,
-			unsigned long buf_align)
+			int *checkeof)
 {
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	u64 pos, this_len, left;
-	int io_align, page_align;
-	int pages_left;
-	int read;
+	loff_t i_size;
+	int page_align, pages_left;
+	int read, ret;
 	struct page **page_pos;
-	int ret;
 	bool hit_stripe, was_short;
 
 	/*
@@ -364,13 +438,9 @@ static int striped_read(struct inode *inode,
 	page_pos = pages;
 	pages_left = num_pages;
 	read = 0;
-	io_align = off & ~PAGE_MASK;
 
 more:
-	if (o_direct)
-		page_align = (pos - io_align + buf_align) & ~PAGE_MASK;
-	else
-		page_align = pos & ~PAGE_MASK;
+	page_align = pos & ~PAGE_MASK;
 	this_len = left;
 	ret = ceph_osdc_readpages(&fsc->client->osdc, ceph_vino(inode),
 				  &ci->i_layout, pos, &this_len,
@@ -384,20 +454,19 @@ more:
 	dout("striped_read %llu~%llu (read %u) got %d%s%s\n", pos, left, read,
 	     ret, hit_stripe ? " HITSTRIPE" : "", was_short ? " SHORT" : "");
 
+	i_size = i_size_read(inode);
 	if (ret >= 0) {
 		int didpages;
-		if (was_short && (pos + ret < inode->i_size)) {
-			int zlen = min(this_len - ret,
-				       inode->i_size - pos - ret);
-			int zoff = (o_direct ? buf_align : io_align) +
-				    read + ret;
+		if (was_short && (pos + ret < i_size)) {
+			int zlen = min(this_len - ret, i_size - pos - ret);
+			int zoff = (off & ~PAGE_MASK) + read + ret;
 			dout(" zero gap %llu to %llu\n",
 				pos + ret, pos + ret + zlen);
 			ceph_zero_page_vector_range(zoff, zlen, pages);
 			ret += zlen;
 		}
 
-		didpages = (page_align + ret) >> PAGE_CACHE_SHIFT;
+		didpages = (page_align + ret) >> PAGE_SHIFT;
 		pos += ret;
 		read = pos - off;
 		left -= ret;
@@ -405,14 +474,14 @@ more:
 		pages_left -= didpages;
 
 		/* hit stripe and need continue*/
-		if (left && hit_stripe && pos < inode->i_size)
+		if (left && hit_stripe && pos < i_size)
 			goto more;
 	}
 
 	if (read > 0) {
 		ret = read;
 		/* did we bounce off eof? */
-		if (pos + left > inode->i_size)
+		if (pos + left > i_size)
 			*checkeof = CHECK_EOF;
 	}
 
@@ -453,63 +522,222 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *i,
 	if (ret < 0)
 		return ret;
 
-	if (iocb->ki_flags & IOCB_DIRECT) {
-		while (iov_iter_count(i)) {
-			size_t start;
-			ssize_t n;
+	num_pages = calc_pages_for(off, len);
+	pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
+	if (IS_ERR(pages))
+		return PTR_ERR(pages);
+	ret = striped_read(inode, off, len, pages,
+				num_pages, checkeof);
+	if (ret > 0) {
+		int l, k = 0;
+		size_t left = ret;
+
+		while (left) {
+			size_t page_off = off & ~PAGE_MASK;
+			size_t copy = min_t(size_t, left,
+					    PAGE_SIZE - page_off);
+			l = copy_page_to_iter(pages[k++], page_off, copy, i);
+			off += l;
+			left -= l;
+			if (l < copy)
+				break;
+		}
+	}
+	ceph_release_page_vector(pages, num_pages);
 
-			n = iov_iter_get_pages_alloc(i, &pages, INT_MAX, &start);
-			if (n < 0)
-				return n;
+	if (off > iocb->ki_pos) {
+		ret = off - iocb->ki_pos;
+		iocb->ki_pos = off;
+	}
 
-			num_pages = (n + start + PAGE_SIZE - 1) / PAGE_SIZE;
+	dout("sync_read result %d\n", ret);
+	return ret;
+}
 
-			ret = striped_read(inode, off, n,
-					   pages, num_pages, checkeof,
-					   1, start);
+struct ceph_aio_request {
+	struct kiocb *iocb;
+	size_t total_len;
+	int write;
+	int error;
+	struct list_head osd_reqs;
+	unsigned num_reqs;
+	atomic_t pending_reqs;
+	struct timespec mtime;
+	struct ceph_cap_flush *prealloc_cf;
+};
 
-			ceph_put_page_vector(pages, num_pages, true);
+struct ceph_aio_work {
+	struct work_struct work;
+	struct ceph_osd_request *req;
+};
 
-			if (ret <= 0)
-				break;
-			off += ret;
-			iov_iter_advance(i, ret);
-			if (ret < n)
-				break;
+static void ceph_aio_retry_work(struct work_struct *work);
+
+static void ceph_aio_complete(struct inode *inode,
+			      struct ceph_aio_request *aio_req)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	int ret;
+
+	if (!atomic_dec_and_test(&aio_req->pending_reqs))
+		return;
+
+	ret = aio_req->error;
+	if (!ret)
+		ret = aio_req->total_len;
+
+	dout("ceph_aio_complete %p rc %d\n", inode, ret);
+
+	if (ret >= 0 && aio_req->write) {
+		int dirty;
+
+		loff_t endoff = aio_req->iocb->ki_pos + aio_req->total_len;
+		if (endoff > i_size_read(inode)) {
+			if (ceph_inode_set_size(inode, endoff))
+				ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
 		}
-	} else {
-		num_pages = calc_pages_for(off, len);
-		pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
-		if (IS_ERR(pages))
-			return PTR_ERR(pages);
-		ret = striped_read(inode, off, len, pages,
-					num_pages, checkeof, 0, 0);
-		if (ret > 0) {
-			int l, k = 0;
-			size_t left = ret;
-
-			while (left) {
-				size_t page_off = off & ~PAGE_MASK;
-				size_t copy = min_t(size_t,
-						    PAGE_SIZE - page_off, left);
-				l = copy_page_to_iter(pages[k++], page_off,
-						      copy, i);
-				off += l;
-				left -= l;
-				if (l < copy)
-					break;
+
+		spin_lock(&ci->i_ceph_lock);
+		ci->i_inline_version = CEPH_INLINE_NONE;
+		dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR,
+					       &aio_req->prealloc_cf);
+		spin_unlock(&ci->i_ceph_lock);
+		if (dirty)
+			__mark_inode_dirty(inode, dirty);
+
+	}
+
+	ceph_put_cap_refs(ci, (aio_req->write ? CEPH_CAP_FILE_WR :
+						CEPH_CAP_FILE_RD));
+
+	aio_req->iocb->ki_complete(aio_req->iocb, ret, 0);
+
+	ceph_free_cap_flush(aio_req->prealloc_cf);
+	kfree(aio_req);
+}
+
+static void ceph_aio_complete_req(struct ceph_osd_request *req,
+				  struct ceph_msg *msg)
+{
+	int rc = req->r_result;
+	struct inode *inode = req->r_inode;
+	struct ceph_aio_request *aio_req = req->r_priv;
+	struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0);
+	int num_pages = calc_pages_for((u64)osd_data->alignment,
+				       osd_data->length);
+
+	dout("ceph_aio_complete_req %p rc %d bytes %llu\n",
+	     inode, rc, osd_data->length);
+
+	if (rc == -EOLDSNAPC) {
+		struct ceph_aio_work *aio_work;
+		BUG_ON(!aio_req->write);
+
+		aio_work = kmalloc(sizeof(*aio_work), GFP_NOFS);
+		if (aio_work) {
+			INIT_WORK(&aio_work->work, ceph_aio_retry_work);
+			aio_work->req = req;
+			queue_work(ceph_inode_to_client(inode)->wb_wq,
+				   &aio_work->work);
+			return;
+		}
+		rc = -ENOMEM;
+	} else if (!aio_req->write) {
+		if (rc == -ENOENT)
+			rc = 0;
+		if (rc >= 0 && osd_data->length > rc) {
+			int zoff = osd_data->alignment + rc;
+			int zlen = osd_data->length - rc;
+			/*
+			 * If read is satisfied by single OSD request,
+			 * it can pass EOF. Otherwise read is within
+			 * i_size.
+			 */
+			if (aio_req->num_reqs == 1) {
+				loff_t i_size = i_size_read(inode);
+				loff_t endoff = aio_req->iocb->ki_pos + rc;
+				if (endoff < i_size)
+					zlen = min_t(size_t, zlen,
+						     i_size - endoff);
+				aio_req->total_len = rc + zlen;
 			}
+
+			if (zlen > 0)
+				ceph_zero_page_vector_range(zoff, zlen,
+							    osd_data->pages);
 		}
-		ceph_release_page_vector(pages, num_pages);
 	}
 
-	if (off > iocb->ki_pos) {
-		ret = off - iocb->ki_pos;
-		iocb->ki_pos = off;
+	ceph_put_page_vector(osd_data->pages, num_pages, false);
+	ceph_osdc_put_request(req);
+
+	if (rc < 0)
+		cmpxchg(&aio_req->error, 0, rc);
+
+	ceph_aio_complete(inode, aio_req);
+	return;
+}
+
+static void ceph_aio_retry_work(struct work_struct *work)
+{
+	struct ceph_aio_work *aio_work =
+		container_of(work, struct ceph_aio_work, work);
+	struct ceph_osd_request *orig_req = aio_work->req;
+	struct ceph_aio_request *aio_req = orig_req->r_priv;
+	struct inode *inode = orig_req->r_inode;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_snap_context *snapc;
+	struct ceph_osd_request *req;
+	int ret;
+
+	spin_lock(&ci->i_ceph_lock);
+	if (__ceph_have_pending_cap_snap(ci)) {
+		struct ceph_cap_snap *capsnap =
+			list_last_entry(&ci->i_cap_snaps,
+					struct ceph_cap_snap,
+					ci_item);
+		snapc = ceph_get_snap_context(capsnap->context);
+	} else {
+		BUG_ON(!ci->i_head_snapc);
+		snapc = ceph_get_snap_context(ci->i_head_snapc);
+	}
+	spin_unlock(&ci->i_ceph_lock);
+
+	req = ceph_osdc_alloc_request(orig_req->r_osdc, snapc, 2,
+			false, GFP_NOFS);
+	if (!req) {
+		ret = -ENOMEM;
+		req = orig_req;
+		goto out;
 	}
 
-	dout("sync_read result %d\n", ret);
-	return ret;
+	req->r_flags =	CEPH_OSD_FLAG_ORDERSNAP |
+			CEPH_OSD_FLAG_ONDISK |
+			CEPH_OSD_FLAG_WRITE;
+	req->r_base_oloc = orig_req->r_base_oloc;
+	req->r_base_oid = orig_req->r_base_oid;
+
+	req->r_ops[0] = orig_req->r_ops[0];
+	osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC, 0);
+
+	ceph_osdc_build_request(req, req->r_ops[0].extent.offset,
+				snapc, CEPH_NOSNAP, &aio_req->mtime);
+
+	ceph_osdc_put_request(orig_req);
+
+	req->r_callback = ceph_aio_complete_req;
+	req->r_inode = inode;
+	req->r_priv = aio_req;
+
+	ret = ceph_osdc_start_request(req->r_osdc, req, false);
+out:
+	if (ret < 0) {
+		req->r_result = ret;
+		ceph_aio_complete_req(req, NULL);
+	}
+
+	ceph_put_snap_context(snapc);
+	kfree(aio_work);
 }
 
 /*
@@ -545,16 +773,10 @@ static void ceph_sync_write_unsafe(struct ceph_osd_request *req, bool unsafe)
 }
 
 
-/*
- * Synchronous write, straight from __user pointer or user pages.
- *
- * If write spans object boundary, just do multiple writes.  (For a
- * correct atomic write, we should e.g. take write locks on all
- * objects, rollback on failure, etc.)
- */
 static ssize_t
-ceph_sync_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
-		       struct ceph_snap_context *snapc)
+ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
+		       struct ceph_snap_context *snapc,
+		       struct ceph_cap_flush **pcf)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
@@ -563,44 +785,52 @@ ceph_sync_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 	struct ceph_vino vino;
 	struct ceph_osd_request *req;
 	struct page **pages;
-	int num_pages;
-	int written = 0;
+	struct ceph_aio_request *aio_req = NULL;
+	int num_pages = 0;
 	int flags;
-	int check_caps = 0;
 	int ret;
-	struct timespec mtime = CURRENT_TIME;
-	size_t count = iov_iter_count(from);
+	struct timespec mtime = current_fs_time(inode->i_sb);
+	size_t count = iov_iter_count(iter);
+	loff_t pos = iocb->ki_pos;
+	bool write = iov_iter_rw(iter) == WRITE;
 
-	if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
+	if (write && ceph_snap(file_inode(file)) != CEPH_NOSNAP)
 		return -EROFS;
 
-	dout("sync_direct_write on file %p %lld~%u\n", file, pos,
-	     (unsigned)count);
+	dout("sync_direct_read_write (%s) on file %p %lld~%u\n",
+	     (write ? "write" : "read"), file, pos, (unsigned)count);
 
 	ret = filemap_write_and_wait_range(inode->i_mapping, pos, pos + count);
 	if (ret < 0)
 		return ret;
 
-	ret = invalidate_inode_pages2_range(inode->i_mapping,
-					    pos >> PAGE_CACHE_SHIFT,
-					    (pos + count) >> PAGE_CACHE_SHIFT);
-	if (ret < 0)
-		dout("invalidate_inode_pages2_range returned %d\n", ret);
+	if (write) {
+		ret = invalidate_inode_pages2_range(inode->i_mapping,
+					pos >> PAGE_SHIFT,
+					(pos + count) >> PAGE_SHIFT);
+		if (ret < 0)
+			dout("invalidate_inode_pages2_range returned %d\n", ret);
 
-	flags = CEPH_OSD_FLAG_ORDERSNAP |
-		CEPH_OSD_FLAG_ONDISK |
-		CEPH_OSD_FLAG_WRITE;
+		flags = CEPH_OSD_FLAG_ORDERSNAP |
+			CEPH_OSD_FLAG_ONDISK |
+			CEPH_OSD_FLAG_WRITE;
+	} else {
+		flags = CEPH_OSD_FLAG_READ;
+	}
 
-	while (iov_iter_count(from) > 0) {
-		u64 len = iov_iter_single_seg_count(from);
-		size_t start;
-		ssize_t n;
+	while (iov_iter_count(iter) > 0) {
+		u64 size = dio_get_pagev_size(iter);
+		size_t start = 0;
+		ssize_t len;
 
 		vino = ceph_vino(inode);
 		req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
-					    vino, pos, &len, 0,
-					    2,/*include a 'startsync' command*/
-					    CEPH_OSD_OP_WRITE, flags, snapc,
+					    vino, pos, &size, 0,
+					    /*include a 'startsync' command*/
+					    write ? 2 : 1,
+					    write ? CEPH_OSD_OP_WRITE :
+						    CEPH_OSD_OP_READ,
+					    flags, snapc,
 					    ci->i_truncate_seq,
 					    ci->i_truncate_size,
 					    false);
@@ -609,58 +839,136 @@ ceph_sync_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 			break;
 		}
 
-		osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC, 0);
-
-		n = iov_iter_get_pages_alloc(from, &pages, len, &start);
-		if (unlikely(n < 0)) {
-			ret = n;
+		len = size;
+		pages = dio_get_pages_alloc(iter, len, &start, &num_pages);
+		if (IS_ERR(pages)) {
 			ceph_osdc_put_request(req);
+			ret = PTR_ERR(pages);
 			break;
 		}
 
-		num_pages = (n + start + PAGE_SIZE - 1) / PAGE_SIZE;
 		/*
-		 * throw out any page cache pages in this range. this
-		 * may block.
+		 * To simplify error handling, allow AIO when IO within i_size
+		 * or IO can be satisfied by single OSD request.
 		 */
-		truncate_inode_pages_range(inode->i_mapping, pos,
-				   (pos+n) | (PAGE_CACHE_SIZE-1));
-		osd_req_op_extent_osd_data_pages(req, 0, pages, n, start,
-						false, false);
+		if (pos == iocb->ki_pos && !is_sync_kiocb(iocb) &&
+		    (len == count || pos + count <= i_size_read(inode))) {
+			aio_req = kzalloc(sizeof(*aio_req), GFP_KERNEL);
+			if (aio_req) {
+				aio_req->iocb = iocb;
+				aio_req->write = write;
+				INIT_LIST_HEAD(&aio_req->osd_reqs);
+				if (write) {
+					aio_req->mtime = mtime;
+					swap(aio_req->prealloc_cf, *pcf);
+				}
+			}
+			/* ignore error */
+		}
+
+		if (write) {
+			/*
+			 * throw out any page cache pages in this range. this
+			 * may block.
+			 */
+			truncate_inode_pages_range(inode->i_mapping, pos,
+					(pos+len) | (PAGE_SIZE - 1));
+
+			osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC, 0);
+		}
+
+
+		osd_req_op_extent_osd_data_pages(req, 0, pages, len, start,
+						 false, false);
 
-		/* BUG_ON(vino.snap != CEPH_NOSNAP); */
 		ceph_osdc_build_request(req, pos, snapc, vino.snap, &mtime);
 
-		ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
+		if (aio_req) {
+			aio_req->total_len += len;
+			aio_req->num_reqs++;
+			atomic_inc(&aio_req->pending_reqs);
+
+			req->r_callback = ceph_aio_complete_req;
+			req->r_inode = inode;
+			req->r_priv = aio_req;
+			list_add_tail(&req->r_unsafe_item, &aio_req->osd_reqs);
+
+			pos += len;
+			iov_iter_advance(iter, len);
+			continue;
+		}
+
+		ret = ceph_osdc_start_request(req->r_osdc, req, false);
 		if (!ret)
 			ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
 
+		size = i_size_read(inode);
+		if (!write) {
+			if (ret == -ENOENT)
+				ret = 0;
+			if (ret >= 0 && ret < len && pos + ret < size) {
+				int zlen = min_t(size_t, len - ret,
+						 size - pos - ret);
+				ceph_zero_page_vector_range(start + ret, zlen,
+							    pages);
+				ret += zlen;
+			}
+			if (ret >= 0)
+				len = ret;
+		}
+
 		ceph_put_page_vector(pages, num_pages, false);
 
 		ceph_osdc_put_request(req);
-		if (ret)
+		if (ret < 0)
 			break;
-		pos += n;
-		written += n;
-		iov_iter_advance(from, n);
 
-		if (pos > i_size_read(inode)) {
-			check_caps = ceph_inode_set_size(inode, pos);
-			if (check_caps)
+		pos += len;
+		iov_iter_advance(iter, len);
+
+		if (!write && pos >= size)
+			break;
+
+		if (write && pos > size) {
+			if (ceph_inode_set_size(inode, pos))
 				ceph_check_caps(ceph_inode(inode),
 						CHECK_CAPS_AUTHONLY,
 						NULL);
 		}
 	}
 
-	if (ret != -EOLDSNAPC && written > 0) {
+	if (aio_req) {
+		if (aio_req->num_reqs == 0) {
+			kfree(aio_req);
+			return ret;
+		}
+
+		ceph_get_cap_refs(ci, write ? CEPH_CAP_FILE_WR :
+					      CEPH_CAP_FILE_RD);
+
+		while (!list_empty(&aio_req->osd_reqs)) {
+			req = list_first_entry(&aio_req->osd_reqs,
+					       struct ceph_osd_request,
+					       r_unsafe_item);
+			list_del_init(&req->r_unsafe_item);
+			if (ret >= 0)
+				ret = ceph_osdc_start_request(req->r_osdc,
+							      req, false);
+			if (ret < 0) {
+				req->r_result = ret;
+				ceph_aio_complete_req(req, NULL);
+			}
+		}
+		return -EIOCBQUEUED;
+	}
+
+	if (ret != -EOLDSNAPC && pos > iocb->ki_pos) {
+		ret = pos - iocb->ki_pos;
 		iocb->ki_pos = pos;
-		ret = written;
 	}
 	return ret;
 }
 
-
 /*
  * Synchronous write, straight from __user pointer or user pages.
  *
@@ -685,7 +993,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 	int flags;
 	int check_caps = 0;
 	int ret;
-	struct timespec mtime = CURRENT_TIME;
+	struct timespec mtime = current_fs_time(inode->i_sb);
 	size_t count = iov_iter_count(from);
 
 	if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
@@ -698,8 +1006,8 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 		return ret;
 
 	ret = invalidate_inode_pages2_range(inode->i_mapping,
-					    pos >> PAGE_CACHE_SHIFT,
-					    (pos + count) >> PAGE_CACHE_SHIFT);
+					    pos >> PAGE_SHIFT,
+					    (pos + count) >> PAGE_SHIFT);
 	if (ret < 0)
 		dout("invalidate_inode_pages2_range returned %d\n", ret);
 
@@ -728,7 +1036,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 		 * write from beginning of first page,
 		 * regardless of io alignment
 		 */
-		num_pages = (len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+		num_pages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
 		pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
 		if (IS_ERR(pages)) {
@@ -830,8 +1138,14 @@ again:
 		     ceph_cap_string(got));
 
 		if (ci->i_inline_version == CEPH_INLINE_NONE) {
-			/* hmm, this isn't really async... */
-			ret = ceph_sync_read(iocb, to, &retry_op);
+			if (!retry_op && (iocb->ki_flags & IOCB_DIRECT)) {
+				ret = ceph_direct_read_write(iocb, to,
+							     NULL, NULL);
+				if (ret >= 0 && ret < len)
+					retry_op = CHECK_EOF;
+			} else {
+				ret = ceph_sync_read(iocb, to, &retry_op);
+			}
 		} else {
 			retry_op = READ_INLINE;
 		}
@@ -845,11 +1159,11 @@ again:
 	dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n",
 	     inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret);
 	if (pinned_page) {
-		page_cache_release(pinned_page);
+		put_page(pinned_page);
 		pinned_page = NULL;
 	}
 	ceph_put_cap_refs(ci, got);
-	if (retry_op && ret >= 0) {
+	if (retry_op > HAVE_RETRIED && ret >= 0) {
 		int statret;
 		struct page *page = NULL;
 		loff_t i_size;
@@ -874,10 +1188,10 @@ again:
 		if (retry_op == READ_INLINE) {
 			BUG_ON(ret > 0 || read > 0);
 			if (iocb->ki_pos < i_size &&
-			    iocb->ki_pos < PAGE_CACHE_SIZE) {
+			    iocb->ki_pos < PAGE_SIZE) {
 				loff_t end = min_t(loff_t, i_size,
 						   iocb->ki_pos + len);
-				end = min_t(loff_t, end, PAGE_CACHE_SIZE);
+				end = min_t(loff_t, end, PAGE_SIZE);
 				if (statret < end)
 					zero_user_segment(page, statret, end);
 				ret = copy_page_to_iter(page,
@@ -901,12 +1215,11 @@ again:
 		if (retry_op == CHECK_EOF && iocb->ki_pos < i_size &&
 		    ret < len) {
 			dout("sync_read hit hole, ppos %lld < size %lld"
-			     ", reading more\n", iocb->ki_pos,
-			     inode->i_size);
+			     ", reading more\n", iocb->ki_pos, i_size);
 
 			read += ret;
 			len -= ret;
-			retry_op = 0;
+			retry_op = HAVE_RETRIED;
 			goto again;
 		}
 	}
@@ -947,7 +1260,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (!prealloc_cf)
 		return -ENOMEM;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	/* We can write back this queue in page reclaim */
 	current->backing_dev_info = inode_to_bdi(inode);
@@ -985,7 +1298,7 @@ retry_snap:
 	}
 
 	dout("aio_write %p %llx.%llx %llu~%zd getting caps. i_size %llu\n",
-	     inode, ceph_vinop(inode), pos, count, inode->i_size);
+	     inode, ceph_vinop(inode), pos, count, i_size_read(inode));
 	if (fi->fmode & CEPH_FILE_MODE_LAZY)
 		want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO;
 	else
@@ -1003,7 +1316,7 @@ retry_snap:
 	    (iocb->ki_flags & IOCB_DIRECT) || (fi->flags & CEPH_F_SYNC)) {
 		struct ceph_snap_context *snapc;
 		struct iov_iter data;
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 
 		spin_lock(&ci->i_ceph_lock);
 		if (__ceph_have_pending_cap_snap(ci)) {
@@ -1021,8 +1334,8 @@ retry_snap:
 		/* we might need to revert back to that point */
 		data = *from;
 		if (iocb->ki_flags & IOCB_DIRECT)
-			written = ceph_sync_direct_write(iocb, &data, pos,
-							 snapc);
+			written = ceph_direct_read_write(iocb, &data, snapc,
+							 &prealloc_cf);
 		else
 			written = ceph_sync_write(iocb, &data, pos, snapc);
 		if (written == -EOLDSNAPC) {
@@ -1030,14 +1343,14 @@ retry_snap:
 				"got EOLDSNAPC, retrying\n",
 				inode, ceph_vinop(inode),
 				pos, (unsigned)count);
-			mutex_lock(&inode->i_mutex);
+			inode_lock(inode);
 			goto retry_snap;
 		}
 		if (written > 0)
 			iov_iter_advance(from, written);
 		ceph_put_snap_context(snapc);
 	} else {
-		loff_t old_size = inode->i_size;
+		loff_t old_size = i_size_read(inode);
 		/*
 		 * No need to acquire the i_truncate_mutex. Because
 		 * the MDS revokes Fwb caps before sending truncate
@@ -1048,9 +1361,9 @@ retry_snap:
 		written = generic_perform_write(file, from, pos);
 		if (likely(written >= 0))
 			iocb->ki_pos = pos + written;
-		if (inode->i_size > old_size)
+		if (i_size_read(inode) > old_size)
 			ceph_fscache_update_objectsize(inode);
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 	}
 
 	if (written >= 0) {
@@ -1080,7 +1393,7 @@ retry_snap:
 	goto out_unlocked;
 
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 out_unlocked:
 	ceph_free_cap_flush(prealloc_cf);
 	current->backing_dev_info = NULL;
@@ -1093,9 +1406,10 @@ out_unlocked:
 static loff_t ceph_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct inode *inode = file->f_mapping->host;
+	loff_t i_size;
 	int ret;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	if (whence == SEEK_END || whence == SEEK_DATA || whence == SEEK_HOLE) {
 		ret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE, false);
@@ -1105,9 +1419,10 @@ static loff_t ceph_llseek(struct file *file, loff_t offset, int whence)
 		}
 	}
 
+	i_size = i_size_read(inode);
 	switch (whence) {
 	case SEEK_END:
-		offset += inode->i_size;
+		offset += i_size;
 		break;
 	case SEEK_CUR:
 		/*
@@ -1123,24 +1438,24 @@ static loff_t ceph_llseek(struct file *file, loff_t offset, int whence)
 		offset += file->f_pos;
 		break;
 	case SEEK_DATA:
-		if (offset >= inode->i_size) {
+		if (offset >= i_size) {
 			ret = -ENXIO;
 			goto out;
 		}
 		break;
 	case SEEK_HOLE:
-		if (offset >= inode->i_size) {
+		if (offset >= i_size) {
 			ret = -ENXIO;
 			goto out;
 		}
-		offset = inode->i_size;
+		offset = i_size;
 		break;
 	}
 
 	offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
 
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return offset;
 }
 
@@ -1148,21 +1463,21 @@ static inline void ceph_zero_partial_page(
 	struct inode *inode, loff_t offset, unsigned size)
 {
 	struct page *page;
-	pgoff_t index = offset >> PAGE_CACHE_SHIFT;
+	pgoff_t index = offset >> PAGE_SHIFT;
 
 	page = find_lock_page(inode->i_mapping, index);
 	if (page) {
 		wait_on_page_writeback(page);
-		zero_user(page, offset & (PAGE_CACHE_SIZE - 1), size);
+		zero_user(page, offset & (PAGE_SIZE - 1), size);
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 	}
 }
 
 static void ceph_zero_pagecache_range(struct inode *inode, loff_t offset,
 				      loff_t length)
 {
-	loff_t nearly = round_up(offset, PAGE_CACHE_SIZE);
+	loff_t nearly = round_up(offset, PAGE_SIZE);
 	if (offset < nearly) {
 		loff_t size = nearly - offset;
 		if (length < size)
@@ -1171,8 +1486,8 @@ static void ceph_zero_pagecache_range(struct inode *inode, loff_t offset,
 		offset += size;
 		length -= size;
 	}
-	if (length >= PAGE_CACHE_SIZE) {
-		loff_t size = round_down(length, PAGE_CACHE_SIZE);
+	if (length >= PAGE_SIZE) {
+		loff_t size = round_down(length, PAGE_SIZE);
 		truncate_pagecache_range(inode, offset, offset + size - 1);
 		offset += size;
 		length -= size;
@@ -1296,7 +1611,7 @@ static long ceph_fallocate(struct file *file, int mode,
 	if (!prealloc_cf)
 		return -ENOMEM;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	if (ceph_snap(inode) != CEPH_NOSNAP) {
 		ret = -EROFS;
@@ -1351,7 +1666,7 @@ static long ceph_fallocate(struct file *file, int mode,
 
 	ceph_put_cap_refs(ci, got);
 unlock:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	ceph_free_cap_flush(prealloc_cf);
 	return ret;
 }
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 96d2bd829902..edfade037738 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -396,6 +396,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	ci->i_symlink = NULL;
 
 	memset(&ci->i_dir_layout, 0, sizeof(ci->i_dir_layout));
+	ci->i_pool_ns_len = 0;
 
 	ci->i_fragtree = RB_ROOT;
 	mutex_init(&ci->i_fragtree_mutex);
@@ -452,6 +453,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 
 	INIT_LIST_HEAD(&ci->i_unsafe_writes);
 	INIT_LIST_HEAD(&ci->i_unsafe_dirops);
+	INIT_LIST_HEAD(&ci->i_unsafe_iops);
 	spin_lock_init(&ci->i_unsafe_lock);
 
 	ci->i_snap_realm = NULL;
@@ -547,7 +549,11 @@ int ceph_fill_file_size(struct inode *inode, int issued,
 	if (ceph_seq_cmp(truncate_seq, ci->i_truncate_seq) > 0 ||
 	    (truncate_seq == ci->i_truncate_seq && size > inode->i_size)) {
 		dout("size %lld -> %llu\n", inode->i_size, size);
-		inode->i_size = size;
+		if (size > 0 && S_ISDIR(inode->i_mode)) {
+			pr_err("fill_file_size non-zero size for directory\n");
+			size = 0;
+		}
+		i_size_write(inode, size);
 		inode->i_blocks = (size + (1<<9) - 1) >> 9;
 		ci->i_reported_size = size;
 		if (truncate_seq != ci->i_truncate_seq) {
@@ -755,6 +761,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 		if (ci->i_layout.fl_pg_pool != info->layout.fl_pg_pool)
 			ci->i_ceph_flags &= ~CEPH_I_POOL_PERM;
 		ci->i_layout = info->layout;
+		ci->i_pool_ns_len = iinfo->pool_ns_len;
 
 		queue_trunc = ceph_fill_file_size(inode, issued,
 					le32_to_cpu(info->truncate_seq),
@@ -807,7 +814,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 			spin_unlock(&ci->i_ceph_lock);
 
 			err = -EINVAL;
-			if (WARN_ON(symlen != inode->i_size))
+			if (WARN_ON(symlen != i_size_read(inode)))
 				goto out;
 
 			err = -ENOMEM;
@@ -974,13 +981,8 @@ out_unlock:
 /*
  * splice a dentry to an inode.
  * caller must hold directory i_mutex for this to be safe.
- *
- * we will only rehash the resulting dentry if @prehash is
- * true; @prehash will be set to false (for the benefit of
- * the caller) if we fail.
  */
-static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
-				    bool *prehash)
+static struct dentry *splice_dentry(struct dentry *dn, struct inode *in)
 {
 	struct dentry *realdn;
 
@@ -993,8 +995,6 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
 	if (IS_ERR(realdn)) {
 		pr_err("splice_dentry error %ld %p inode %p ino %llx.%llx\n",
 		       PTR_ERR(realdn), dn, in, ceph_vinop(in));
-		if (prehash)
-			*prehash = false; /* don't rehash on error */
 		dn = realdn; /* note realdn contains the error */
 		goto out;
 	} else if (realdn) {
@@ -1010,8 +1010,6 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
 		dout("dn %p attached to %p ino %llx.%llx\n",
 		     dn, d_inode(dn), ceph_vinop(d_inode(dn)));
 	}
-	if ((!prehash || *prehash) && d_unhashed(dn))
-		d_rehash(dn);
 out:
 	return dn;
 }
@@ -1244,10 +1242,8 @@ retry_lookup:
 				dout("d_delete %p\n", dn);
 				d_delete(dn);
 			} else {
-				dout("d_instantiate %p NULL\n", dn);
-				d_instantiate(dn, NULL);
 				if (have_lease && d_unhashed(dn))
-					d_rehash(dn);
+					d_add(dn, NULL);
 				update_dentry_lease(dn, rinfo->dlease,
 						    session,
 						    req->r_request_started);
@@ -1259,7 +1255,7 @@ retry_lookup:
 		if (d_really_is_negative(dn)) {
 			ceph_dir_clear_ordered(dir);
 			ihold(in);
-			dn = splice_dentry(dn, in, &have_lease);
+			dn = splice_dentry(dn, in);
 			if (IS_ERR(dn)) {
 				err = PTR_ERR(dn);
 				goto done;
@@ -1269,6 +1265,7 @@ retry_lookup:
 			dout(" %p links to %p %llx.%llx, not %llx.%llx\n",
 			     dn, d_inode(dn), ceph_vinop(d_inode(dn)),
 			     ceph_vinop(in));
+			d_invalidate(dn);
 			have_lease = false;
 		}
 
@@ -1289,7 +1286,7 @@ retry_lookup:
 		dout(" linking snapped dir %p to dn %p\n", in, dn);
 		ceph_dir_clear_ordered(dir);
 		ihold(in);
-		dn = splice_dentry(dn, in, NULL);
+		dn = splice_dentry(dn, in);
 		if (IS_ERR(dn)) {
 			err = PTR_ERR(dn);
 			goto done;
@@ -1341,7 +1338,7 @@ void ceph_readdir_cache_release(struct ceph_readdir_cache_control *ctl)
 {
 	if (ctl->page) {
 		kunmap(ctl->page);
-		page_cache_release(ctl->page);
+		put_page(ctl->page);
 		ctl->page = NULL;
 	}
 }
@@ -1351,21 +1348,26 @@ static int fill_readdir_cache(struct inode *dir, struct dentry *dn,
 			      struct ceph_mds_request *req)
 {
 	struct ceph_inode_info *ci = ceph_inode(dir);
-	unsigned nsize = PAGE_CACHE_SIZE / sizeof(struct dentry*);
+	unsigned nsize = PAGE_SIZE / sizeof(struct dentry*);
 	unsigned idx = ctl->index % nsize;
 	pgoff_t pgoff = ctl->index / nsize;
 
 	if (!ctl->page || pgoff != page_index(ctl->page)) {
 		ceph_readdir_cache_release(ctl);
-		ctl->page  = grab_cache_page(&dir->i_data, pgoff);
+		if (idx == 0)
+			ctl->page = grab_cache_page(&dir->i_data, pgoff);
+		else
+			ctl->page = find_lock_page(&dir->i_data, pgoff);
 		if (!ctl->page) {
 			ctl->index = -1;
-			return -ENOMEM;
+			return idx == 0 ? -ENOMEM : 0;
 		}
 		/* reading/filling the cache are serialized by
 		 * i_mutex, no need to use page lock */
 		unlock_page(ctl->page);
 		ctl->dentries = kmap(ctl->page);
+		if (idx == 0)
+			memset(ctl->dentries, 0, PAGE_SIZE);
 	}
 
 	if (req->r_dir_release_cnt == atomic64_read(&ci->i_release_count) &&
@@ -1388,7 +1390,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 	struct qstr dname;
 	struct dentry *dn;
 	struct inode *in;
-	int err = 0, ret, i;
+	int err = 0, skipped = 0, ret, i;
 	struct inode *snapdir = NULL;
 	struct ceph_mds_request_head *rhead = req->r_request->front.iov_base;
 	struct ceph_dentry_info *di;
@@ -1500,7 +1502,17 @@ retry_lookup:
 		}
 
 		if (d_really_is_negative(dn)) {
-			struct dentry *realdn = splice_dentry(dn, in, NULL);
+			struct dentry *realdn;
+
+			if (ceph_security_xattr_deadlock(in)) {
+				dout(" skip splicing dn %p to inode %p"
+				     " (security xattr deadlock)\n", dn, in);
+				iput(in);
+				skipped++;
+				goto next_item;
+			}
+
+			realdn = splice_dentry(dn, in);
 			if (IS_ERR(realdn)) {
 				err = PTR_ERR(realdn);
 				d_drop(dn);
@@ -1517,7 +1529,7 @@ retry_lookup:
 				    req->r_session,
 				    req->r_request_started);
 
-		if (err == 0 && cache_ctl.index >= 0) {
+		if (err == 0 && skipped == 0 && cache_ctl.index >= 0) {
 			ret = fill_readdir_cache(d_inode(parent), dn,
 						 &cache_ctl, req);
 			if (ret < 0)
@@ -1528,7 +1540,7 @@ next_item:
 			dput(dn);
 	}
 out:
-	if (err == 0) {
+	if (err == 0 && skipped == 0) {
 		req->r_did_prepopulate = true;
 		req->r_readdir_cache_idx = cache_ctl.index;
 	}
@@ -1548,7 +1560,7 @@ int ceph_inode_set_size(struct inode *inode, loff_t size)
 
 	spin_lock(&ci->i_ceph_lock);
 	dout("set_size %p %llu -> %llu\n", inode, inode->i_size, size);
-	inode->i_size = size;
+	i_size_write(inode, size);
 	inode->i_blocks = (size + (1 << 9) - 1) >> 9;
 
 	/* tell the MDS if we are approaching max_size */
@@ -1755,7 +1767,7 @@ retry:
  */
 static const struct inode_operations ceph_symlink_iops = {
 	.readlink = generic_readlink,
-	.follow_link = simple_follow_link,
+	.get_link = simple_get_link,
 	.setattr = ceph_setattr,
 	.getattr = ceph_getattr,
 	.setxattr = ceph_setxattr,
@@ -1910,7 +1922,7 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
 		     inode->i_size, attr->ia_size);
 		if ((issued & CEPH_CAP_FILE_EXCL) &&
 		    attr->ia_size > inode->i_size) {
-			inode->i_size = attr->ia_size;
+			i_size_write(inode, attr->ia_size);
 			inode->i_blocks =
 				(attr->ia_size + (1 << 9) - 1) >> 9;
 			inode->i_ctime = attr->ia_ctime;
@@ -1958,7 +1970,7 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
 	if (dirtied) {
 		inode_dirty_flags = __ceph_mark_dirty_caps(ci, dirtied,
 							   &prealloc_cf);
-		inode->i_ctime = CURRENT_TIME;
+		inode->i_ctime = current_fs_time(inode->i_sb);
 	}
 
 	release &= issued;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 51cb02da75d9..541ead4d8965 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -100,6 +100,14 @@ static int parse_reply_info_in(void **p, void *end,
 	} else
 		info->inline_version = CEPH_INLINE_NONE;
 
+	if (features & CEPH_FEATURE_FS_FILE_LAYOUT_V2) {
+		ceph_decode_32_safe(p, end, info->pool_ns_len, bad);
+		ceph_decode_need(p, end, info->pool_ns_len, bad);
+		*p += info->pool_ns_len;
+	} else {
+		info->pool_ns_len = 0;
+	}
+
 	return 0;
 bad:
 	return err;
@@ -633,13 +641,8 @@ static void __register_request(struct ceph_mds_client *mdsc,
 		mdsc->oldest_tid = req->r_tid;
 
 	if (dir) {
-		struct ceph_inode_info *ci = ceph_inode(dir);
-
 		ihold(dir);
-		spin_lock(&ci->i_unsafe_lock);
 		req->r_unsafe_dir = dir;
-		list_add_tail(&req->r_unsafe_dir_item, &ci->i_unsafe_dirops);
-		spin_unlock(&ci->i_unsafe_lock);
 	}
 }
 
@@ -665,13 +668,20 @@ static void __unregister_request(struct ceph_mds_client *mdsc,
 	rb_erase(&req->r_node, &mdsc->request_tree);
 	RB_CLEAR_NODE(&req->r_node);
 
-	if (req->r_unsafe_dir) {
+	if (req->r_unsafe_dir && req->r_got_unsafe) {
 		struct ceph_inode_info *ci = ceph_inode(req->r_unsafe_dir);
-
 		spin_lock(&ci->i_unsafe_lock);
 		list_del_init(&req->r_unsafe_dir_item);
 		spin_unlock(&ci->i_unsafe_lock);
+	}
+	if (req->r_target_inode && req->r_got_unsafe) {
+		struct ceph_inode_info *ci = ceph_inode(req->r_target_inode);
+		spin_lock(&ci->i_unsafe_lock);
+		list_del_init(&req->r_unsafe_target_item);
+		spin_unlock(&ci->i_unsafe_lock);
+	}
 
+	if (req->r_unsafe_dir) {
 		iput(req->r_unsafe_dir);
 		req->r_unsafe_dir = NULL;
 	}
@@ -1430,6 +1440,13 @@ static int trim_caps_cb(struct inode *inode, struct ceph_cap *cap, void *arg)
 		if ((used | wanted) & CEPH_CAP_ANY_WR)
 			goto out;
 	}
+	/* The inode has cached pages, but it's no longer used.
+	 * we can safely drop it */
+	if (wanted == 0 && used == CEPH_CAP_FILE_CACHE &&
+	    !(oissued & CEPH_CAP_FILE_CACHE)) {
+	  used = 0;
+	  oissued = 0;
+	}
 	if ((used | wanted) & ~oissued & mine)
 		goto out;   /* we need these caps */
 
@@ -1438,7 +1455,7 @@ static int trim_caps_cb(struct inode *inode, struct ceph_cap *cap, void *arg)
 		/* we aren't the only cap.. just remove us */
 		__ceph_remove_cap(cap, true);
 	} else {
-		/* try to drop referring dentries */
+		/* try dropping referring dentries */
 		spin_unlock(&ci->i_ceph_lock);
 		d_prune_aliases(inode);
 		dout("trim_caps_cb %p cap %p  pruned, count now %d\n",
@@ -1593,7 +1610,7 @@ again:
 	while (!list_empty(&tmp_list)) {
 		if (!msg) {
 			msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPRELEASE,
-					PAGE_CACHE_SIZE, GFP_NOFS, false);
+					PAGE_SIZE, GFP_NOFS, false);
 			if (!msg)
 				goto out_err;
 			head = msg->front.iov_base;
@@ -1704,6 +1721,7 @@ ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode)
 	req->r_started = jiffies;
 	req->r_resend_mds = -1;
 	INIT_LIST_HEAD(&req->r_unsafe_dir_item);
+	INIT_LIST_HEAD(&req->r_unsafe_target_item);
 	req->r_fmode = -1;
 	kref_init(&req->r_kref);
 	INIT_LIST_HEAD(&req->r_wait);
@@ -1711,7 +1729,7 @@ ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode)
 	init_completion(&req->r_safe_completion);
 	INIT_LIST_HEAD(&req->r_unsafe_item);
 
-	req->r_stamp = CURRENT_TIME;
+	req->r_stamp = current_fs_time(mdsc->fsc->sb);
 
 	req->r_op = op;
 	req->r_direct_mode = mode;
@@ -1935,7 +1953,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 
 	len = sizeof(*head) +
 		pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64)) +
-		sizeof(struct timespec);
+		sizeof(struct ceph_timespec);
 
 	/* calculate (max) length for cap releases */
 	len += sizeof(struct ceph_mds_request_release) *
@@ -2288,6 +2306,14 @@ int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
 		ceph_get_cap_refs(ceph_inode(req->r_old_dentry_dir),
 				  CEPH_CAP_PIN);
 
+	/* deny access to directories with pool_ns layouts */
+	if (req->r_inode && S_ISDIR(req->r_inode->i_mode) &&
+	    ceph_inode(req->r_inode)->i_pool_ns_len)
+		return -EIO;
+	if (req->r_locked_dir &&
+	    ceph_inode(req->r_locked_dir)->i_pool_ns_len)
+		return -EIO;
+
 	/* issue */
 	mutex_lock(&mdsc->mutex);
 	__register_request(mdsc, req, dir);
@@ -2477,6 +2503,14 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 	} else {
 		req->r_got_unsafe = true;
 		list_add_tail(&req->r_unsafe_item, &req->r_session->s_unsafe);
+		if (req->r_unsafe_dir) {
+			struct ceph_inode_info *ci =
+					ceph_inode(req->r_unsafe_dir);
+			spin_lock(&ci->i_unsafe_lock);
+			list_add_tail(&req->r_unsafe_dir_item,
+				      &ci->i_unsafe_dirops);
+			spin_unlock(&ci->i_unsafe_lock);
+		}
 	}
 
 	dout("handle_reply tid %lld result %d\n", tid, result);
@@ -2506,6 +2540,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 
 	/* insert trace into our cache */
 	mutex_lock(&req->r_fill_mutex);
+	current->journal_info = req;
 	err = ceph_fill_trace(mdsc->fsc->sb, req, req->r_session);
 	if (err == 0) {
 		if (result == 0 && (req->r_op == CEPH_MDS_OP_READDIR ||
@@ -2513,11 +2548,19 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 			ceph_readdir_prepopulate(req, req->r_session);
 		ceph_unreserve_caps(mdsc, &req->r_caps_reservation);
 	}
+	current->journal_info = NULL;
 	mutex_unlock(&req->r_fill_mutex);
 
 	up_read(&mdsc->snap_rwsem);
 	if (realm)
 		ceph_put_snap_realm(mdsc, realm);
+
+	if (err == 0 && req->r_got_unsafe && req->r_target_inode) {
+		struct ceph_inode_info *ci = ceph_inode(req->r_target_inode);
+		spin_lock(&ci->i_unsafe_lock);
+		list_add_tail(&req->r_unsafe_target_item, &ci->i_unsafe_iops);
+		spin_unlock(&ci->i_unsafe_lock);
+	}
 out_err:
 	mutex_lock(&mdsc->mutex);
 	if (!req->r_aborted) {
@@ -3723,7 +3766,6 @@ void ceph_mdsc_handle_map(struct ceph_mds_client *mdsc, struct ceph_msg *msg)
 	dout("handle_map epoch %u len %d\n", epoch, (int)maplen);
 
 	/* do we need it? */
-	ceph_monc_got_mdsmap(&mdsc->fsc->client->monc, epoch);
 	mutex_lock(&mdsc->mutex);
 	if (mdsc->mdsmap && epoch <= mdsc->mdsmap->m_epoch) {
 		dout("handle_map epoch %u <= our %u\n",
@@ -3750,6 +3792,8 @@ void ceph_mdsc_handle_map(struct ceph_mds_client *mdsc, struct ceph_msg *msg)
 	mdsc->fsc->sb->s_maxbytes = mdsc->mdsmap->m_max_file_size;
 
 	__wake_requests(mdsc, &mdsc->waiting_for_map);
+	ceph_monc_got_map(&mdsc->fsc->client->monc, CEPH_SUB_MDSMAP,
+			  mdsc->mdsmap->m_epoch);
 
 	mutex_unlock(&mdsc->mutex);
 	schedule_delayed(mdsc);
@@ -3917,17 +3961,19 @@ static struct ceph_msg *mds_alloc_msg(struct ceph_connection *con,
 	return msg;
 }
 
-static int sign_message(struct ceph_connection *con, struct ceph_msg *msg)
+static int mds_sign_message(struct ceph_msg *msg)
 {
-       struct ceph_mds_session *s = con->private;
+       struct ceph_mds_session *s = msg->con->private;
        struct ceph_auth_handshake *auth = &s->s_auth;
+
        return ceph_auth_sign_message(auth, msg);
 }
 
-static int check_message_signature(struct ceph_connection *con, struct ceph_msg *msg)
+static int mds_check_message_signature(struct ceph_msg *msg)
 {
-       struct ceph_mds_session *s = con->private;
+       struct ceph_mds_session *s = msg->con->private;
        struct ceph_auth_handshake *auth = &s->s_auth;
+
        return ceph_auth_check_message_signature(auth, msg);
 }
 
@@ -3940,8 +3986,8 @@ static const struct ceph_connection_operations mds_con_ops = {
 	.invalidate_authorizer = invalidate_authorizer,
 	.peer_reset = peer_reset,
 	.alloc_msg = mds_alloc_msg,
-	.sign_message = sign_message,
-	.check_message_signature = check_message_signature,
+	.sign_message = mds_sign_message,
+	.check_message_signature = mds_check_message_signature,
 };
 
 /* eof */
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index f575eafe2261..ee69a537dba5 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -44,6 +44,7 @@ struct ceph_mds_reply_info_in {
 	u64 inline_version;
 	u32 inline_len;
 	char *inline_data;
+	u32 pool_ns_len;
 };
 
 /*
@@ -96,7 +97,7 @@ struct ceph_mds_reply_info_parsed {
 /*
  * cap releases are batched and sent to the MDS en masse.
  */
-#define CEPH_CAPS_PER_RELEASE ((PAGE_CACHE_SIZE -			\
+#define CEPH_CAPS_PER_RELEASE ((PAGE_SIZE -			\
 				sizeof(struct ceph_mds_cap_release)) /	\
 			       sizeof(struct ceph_mds_cap_item))
 
@@ -236,6 +237,9 @@ struct ceph_mds_request {
 	struct inode	*r_unsafe_dir;
 	struct list_head r_unsafe_dir_item;
 
+	/* unsafe requests that modify the target inode */
+	struct list_head r_unsafe_target_item;
+
 	struct ceph_mds_session *r_session;
 
 	int               r_attempts;   /* resend attempts */
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 4aa7122a8d38..9caaa7ffc93f 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -296,8 +296,6 @@ static int cmpu64_rev(const void *a, const void *b)
 }
 
 
-struct ceph_snap_context *ceph_empty_snapc;
-
 /*
  * build the snap context for a given realm.
  */
@@ -987,17 +985,3 @@ out:
 		up_write(&mdsc->snap_rwsem);
 	return;
 }
-
-int __init ceph_snap_init(void)
-{
-	ceph_empty_snapc = ceph_create_snap_context(0, GFP_NOFS);
-	if (!ceph_empty_snapc)
-		return -ENOMEM;
-	ceph_empty_snapc->seq = 1;
-	return 0;
-}
-
-void ceph_snap_exit(void)
-{
-	ceph_put_snap_context(ceph_empty_snapc);
-}
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index f446afada328..f12d5e2955c2 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -439,8 +439,8 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
 
 	if (fsopt->flags & CEPH_MOUNT_OPT_DIRSTAT)
 		seq_puts(m, ",dirstat");
-	if ((fsopt->flags & CEPH_MOUNT_OPT_RBYTES) == 0)
-		seq_puts(m, ",norbytes");
+	if ((fsopt->flags & CEPH_MOUNT_OPT_RBYTES))
+		seq_puts(m, ",rbytes");
 	if (fsopt->flags & CEPH_MOUNT_OPT_NOASYNCREADDIR)
 		seq_puts(m, ",noasyncreaddir");
 	if ((fsopt->flags & CEPH_MOUNT_OPT_DCACHE) == 0)
@@ -530,7 +530,7 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 		goto fail;
 	}
 	fsc->client->extra_mon_dispatch = extra_mon_dispatch;
-	fsc->client->monc.want_mdsmap = 1;
+	ceph_monc_want_map(&fsc->client->monc, CEPH_SUB_MDSMAP, 0, true);
 
 	fsc->mount_options = fsopt;
 
@@ -560,7 +560,7 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 
 	/* set up mempools */
 	err = -ENOMEM;
-	page_count = fsc->mount_options->wsize >> PAGE_CACHE_SHIFT;
+	page_count = fsc->mount_options->wsize >> PAGE_SHIFT;
 	size = sizeof (struct page *) * (page_count ? page_count : 1);
 	fsc->wb_pagevec_pool = mempool_create_kmalloc_pool(10, size);
 	if (!fsc->wb_pagevec_pool)
@@ -639,8 +639,8 @@ static int __init init_caches(void)
 	ceph_inode_cachep = kmem_cache_create("ceph_inode_info",
 				      sizeof(struct ceph_inode_info),
 				      __alignof__(struct ceph_inode_info),
-				      (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD),
-				      ceph_inode_init_once);
+				      SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|
+				      SLAB_ACCOUNT, ceph_inode_init_once);
 	if (ceph_inode_cachep == NULL)
 		return -ENOMEM;
 
@@ -793,22 +793,20 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc,
 	struct dentry *root;
 	int first = 0;   /* first vfsmount for this super_block */
 
-	dout("mount start\n");
+	dout("mount start %p\n", fsc);
 	mutex_lock(&fsc->client->mount_mutex);
 
-	err = __ceph_open_session(fsc->client, started);
-	if (err < 0)
-		goto out;
+	if (!fsc->sb->s_root) {
+		err = __ceph_open_session(fsc->client, started);
+		if (err < 0)
+			goto out;
 
-	dout("mount opening root\n");
-	root = open_root_dentry(fsc, "", started);
-	if (IS_ERR(root)) {
-		err = PTR_ERR(root);
-		goto out;
-	}
-	if (fsc->sb->s_root) {
-		dput(root);
-	} else {
+		dout("mount opening root\n");
+		root = open_root_dentry(fsc, "", started);
+		if (IS_ERR(root)) {
+			err = PTR_ERR(root);
+			goto out;
+		}
 		fsc->sb->s_root = root;
 		first = 1;
 
@@ -818,6 +816,7 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc,
 	}
 
 	if (path[0] == 0) {
+		root = fsc->sb->s_root;
 		dget(root);
 	} else {
 		dout("mount opening base mountpoint\n");
@@ -833,16 +832,14 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc,
 	mutex_unlock(&fsc->client->mount_mutex);
 	return root;
 
-out:
-	mutex_unlock(&fsc->client->mount_mutex);
-	return ERR_PTR(err);
-
 fail:
 	if (first) {
 		dput(fsc->sb->s_root);
 		fsc->sb->s_root = NULL;
 	}
-	goto out;
+out:
+	mutex_unlock(&fsc->client->mount_mutex);
+	return ERR_PTR(err);
 }
 
 static int ceph_set_super(struct super_block *s, void *data)
@@ -915,13 +912,13 @@ static int ceph_register_bdi(struct super_block *sb,
 	int err;
 
 	/* set ra_pages based on rasize mount option? */
-	if (fsc->mount_options->rasize >= PAGE_CACHE_SIZE)
+	if (fsc->mount_options->rasize >= PAGE_SIZE)
 		fsc->backing_dev_info.ra_pages =
-			(fsc->mount_options->rasize + PAGE_CACHE_SIZE - 1)
+			(fsc->mount_options->rasize + PAGE_SIZE - 1)
 			>> PAGE_SHIFT;
 	else
 		fsc->backing_dev_info.ra_pages =
-			VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE;
+			VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
 
 	err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%ld",
 			   atomic_long_inc_return(&bdi_seq));
@@ -1042,19 +1039,14 @@ static int __init init_ceph(void)
 
 	ceph_flock_init();
 	ceph_xattr_init();
-	ret = ceph_snap_init();
-	if (ret)
-		goto out_xattr;
 	ret = register_filesystem(&ceph_fs_type);
 	if (ret)
-		goto out_snap;
+		goto out_xattr;
 
 	pr_info("loaded (mds proto %d)\n", CEPH_MDSC_PROTOCOL);
 
 	return 0;
 
-out_snap:
-	ceph_snap_exit();
 out_xattr:
 	ceph_xattr_exit();
 	destroy_caches();
@@ -1066,7 +1058,6 @@ static void __exit exit_ceph(void)
 {
 	dout("exit_ceph\n");
 	unregister_filesystem(&ceph_fs_type);
-	ceph_snap_exit();
 	ceph_xattr_exit();
 	destroy_caches();
 }
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 2f2460d23a06..e705c4d612d7 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -37,8 +37,7 @@
 #define CEPH_MOUNT_OPT_FSCACHE         (1<<10) /* use fscache */
 #define CEPH_MOUNT_OPT_NOPOOLPERM      (1<<11) /* no pool permission check */
 
-#define CEPH_MOUNT_OPT_DEFAULT    (CEPH_MOUNT_OPT_RBYTES | \
-				   CEPH_MOUNT_OPT_DCACHE)
+#define CEPH_MOUNT_OPT_DEFAULT    CEPH_MOUNT_OPT_DCACHE
 
 #define ceph_set_mount_opt(fsc, opt) \
 	(fsc)->mount_options->flags |= CEPH_MOUNT_OPT_##opt;
@@ -287,6 +286,7 @@ struct ceph_inode_info {
 
 	struct ceph_dir_layout i_dir_layout;
 	struct ceph_file_layout i_layout;
+	size_t i_pool_ns_len;
 	char *i_symlink;
 
 	/* for dirs */
@@ -342,6 +342,7 @@ struct ceph_inode_info {
 
 	struct list_head i_unsafe_writes; /* uncommitted sync writes */
 	struct list_head i_unsafe_dirops; /* uncommitted mds dir ops */
+	struct list_head i_unsafe_iops;   /* uncommitted mds inode ops */
 	spinlock_t i_unsafe_lock;
 
 	struct ceph_snap_realm *i_snap_realm; /* snap realm (if caps) */
@@ -467,7 +468,7 @@ static inline struct inode *ceph_find_inode(struct super_block *sb,
 #define CEPH_I_POOL_PERM	(1 << 4)  /* pool rd/wr bits are valid */
 #define CEPH_I_POOL_RD		(1 << 5)  /* can read from pool */
 #define CEPH_I_POOL_WR		(1 << 6)  /* can write to pool */
-
+#define CEPH_I_SEC_INITED	(1 << 7)  /* security initialized */
 
 static inline void __ceph_dir_set_complete(struct ceph_inode_info *ci,
 					   long long release_count,
@@ -719,7 +720,6 @@ static inline int default_congestion_kb(void)
 
 
 /* snap.c */
-extern struct ceph_snap_context *ceph_empty_snapc;
 struct ceph_snap_realm *ceph_lookup_snap_realm(struct ceph_mds_client *mdsc,
 					       u64 ino);
 extern void ceph_get_snap_realm(struct ceph_mds_client *mdsc,
@@ -736,8 +736,6 @@ extern void ceph_queue_cap_snap(struct ceph_inode_info *ci);
 extern int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
 				  struct ceph_cap_snap *capsnap);
 extern void ceph_cleanup_empty_realms(struct ceph_mds_client *mdsc);
-extern int ceph_snap_init(void);
-extern void ceph_snap_exit(void);
 
 /*
  * a cap_snap is "pending" if it is still awaiting an in-progress
@@ -806,6 +804,20 @@ extern void __init ceph_xattr_init(void);
 extern void ceph_xattr_exit(void);
 extern const struct xattr_handler *ceph_xattr_handlers[];
 
+#ifdef CONFIG_SECURITY
+extern bool ceph_security_xattr_deadlock(struct inode *in);
+extern bool ceph_security_xattr_wanted(struct inode *in);
+#else
+static inline bool ceph_security_xattr_deadlock(struct inode *in)
+{
+	return false;
+}
+static inline bool ceph_security_xattr_wanted(struct inode *in)
+{
+	return false;
+}
+#endif
+
 /* acl.c */
 struct ceph_acls_info {
 	void *default_acl;
@@ -945,7 +957,6 @@ extern void ceph_dentry_lru_touch(struct dentry *dn);
 extern void ceph_dentry_lru_del(struct dentry *dn);
 extern void ceph_invalidate_dentry_lease(struct dentry *dentry);
 extern unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn);
-extern struct inode *ceph_get_dentry_parent_inode(struct dentry *dentry);
 extern void ceph_readdir_cache_release(struct ceph_readdir_cache_control *ctl);
 
 /*
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 819163d8313b..9410abdef3ce 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -714,31 +714,62 @@ void __ceph_build_xattrs_blob(struct ceph_inode_info *ci)
 	}
 }
 
+static inline int __get_request_mask(struct inode *in) {
+	struct ceph_mds_request *req = current->journal_info;
+	int mask = 0;
+	if (req && req->r_target_inode == in) {
+		if (req->r_op == CEPH_MDS_OP_LOOKUP ||
+		    req->r_op == CEPH_MDS_OP_LOOKUPINO ||
+		    req->r_op == CEPH_MDS_OP_LOOKUPPARENT ||
+		    req->r_op == CEPH_MDS_OP_GETATTR) {
+			mask = le32_to_cpu(req->r_args.getattr.mask);
+		} else if (req->r_op == CEPH_MDS_OP_OPEN ||
+			   req->r_op == CEPH_MDS_OP_CREATE) {
+			mask = le32_to_cpu(req->r_args.open.mask);
+		}
+	}
+	return mask;
+}
+
 ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value,
 		      size_t size)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	int err;
 	struct ceph_inode_xattr *xattr;
 	struct ceph_vxattr *vxattr = NULL;
+	int req_mask;
+	int err;
 
 	if (!ceph_is_valid_xattr(name))
 		return -ENODATA;
 
 	/* let's see if a virtual xattr was requested */
 	vxattr = ceph_match_vxattr(inode, name);
-	if (vxattr && !(vxattr->exists_cb && !vxattr->exists_cb(ci))) {
-		err = vxattr->getxattr_cb(ci, value, size);
+	if (vxattr) {
+		err = -ENODATA;
+		if (!(vxattr->exists_cb && !vxattr->exists_cb(ci)))
+			err = vxattr->getxattr_cb(ci, value, size);
 		return err;
 	}
 
+	req_mask = __get_request_mask(inode);
+
 	spin_lock(&ci->i_ceph_lock);
 	dout("getxattr %p ver=%lld index_ver=%lld\n", inode,
 	     ci->i_xattrs.version, ci->i_xattrs.index_version);
 
 	if (ci->i_xattrs.version == 0 ||
-	    !__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 1)) {
+	    !((req_mask & CEPH_CAP_XATTR_SHARED) ||
+	      __ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 1))) {
 		spin_unlock(&ci->i_ceph_lock);
+
+		/* security module gets xattr while filling trace */
+		if (current->journal_info != NULL) {
+			pr_warn_ratelimited("sync getxattr %p "
+					    "during filling trace\n", inode);
+			return -EBUSY;
+		}
+
 		/* get xattrs from mds (if we don't already have them) */
 		err = ceph_do_getattr(inode, CEPH_STAT_CAP_XATTR, true);
 		if (err)
@@ -765,6 +796,9 @@ ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value,
 
 	memcpy(value, xattr->val, xattr->val_len);
 
+	if (current->journal_info != NULL &&
+	    !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN))
+		ci->i_ceph_flags |= CEPH_I_SEC_INITED;
 out:
 	spin_unlock(&ci->i_ceph_lock);
 	return err;
@@ -999,7 +1033,7 @@ retry:
 		dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL,
 					       &prealloc_cf);
 		ci->i_xattrs.dirty = true;
-		inode->i_ctime = CURRENT_TIME;
+		inode->i_ctime = current_fs_time(inode->i_sb);
 	}
 
 	spin_unlock(&ci->i_ceph_lock);
@@ -1015,7 +1049,15 @@ do_sync:
 do_sync_unlocked:
 	if (lock_snap_rwsem)
 		up_read(&mdsc->snap_rwsem);
-	err = ceph_sync_setxattr(dentry, name, value, size, flags);
+
+	/* security module set xattr while filling trace */
+	if (current->journal_info != NULL) {
+		pr_warn_ratelimited("sync setxattr %p "
+				    "during filling trace\n", inode);
+		err = -EBUSY;
+	} else {
+		err = ceph_sync_setxattr(dentry, name, value, size, flags);
+	}
 out:
 	ceph_free_cap_flush(prealloc_cf);
 	kfree(newname);
@@ -1136,7 +1178,7 @@ retry:
 	dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL,
 				       &prealloc_cf);
 	ci->i_xattrs.dirty = true;
-	inode->i_ctime = CURRENT_TIME;
+	inode->i_ctime = current_fs_time(inode->i_sb);
 	spin_unlock(&ci->i_ceph_lock);
 	if (lock_snap_rwsem)
 		up_read(&mdsc->snap_rwsem);
@@ -1164,3 +1206,25 @@ int ceph_removexattr(struct dentry *dentry, const char *name)
 
 	return __ceph_removexattr(dentry, name);
 }
+
+#ifdef CONFIG_SECURITY
+bool ceph_security_xattr_wanted(struct inode *in)
+{
+	return in->i_security != NULL;
+}
+
+bool ceph_security_xattr_deadlock(struct inode *in)
+{
+	struct ceph_inode_info *ci;
+	bool ret;
+	if (in->i_security == NULL)
+		return false;
+	ci = ceph_inode(in);
+	spin_lock(&ci->i_ceph_lock);
+	ret = !(ci->i_ceph_flags & CEPH_I_SEC_INITED) &&
+	      !(ci->i_xattrs.version > 0 &&
+		__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 0));
+	spin_unlock(&ci->i_ceph_lock);
+	return ret;
+}
+#endif
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 7febcf2475c5..788e19195991 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -50,7 +50,7 @@ void cifs_vfs_err(const char *fmt, ...)
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
-	pr_err("CIFS VFS: %pV", &vaf);
+	pr_err_ratelimited("CIFS VFS: %pV", &vaf);
 
 	va_end(args);
 }
@@ -255,7 +255,6 @@ static const struct file_operations cifs_debug_data_proc_fops = {
 static ssize_t cifs_stats_proc_write(struct file *file,
 		const char __user *buffer, size_t count, loff_t *ppos)
 {
-	char c;
 	bool bv;
 	int rc;
 	struct list_head *tmp1, *tmp2, *tmp3;
@@ -263,11 +262,8 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 	struct cifs_ses *ses;
 	struct cifs_tcon *tcon;
 
-	rc = get_user(c, buffer);
-	if (rc)
-		return rc;
-
-	if (strtobool(&c, &bv) == 0) {
+	rc = kstrtobool_from_user(buffer, count, &bv);
+	if (rc == 0) {
 #ifdef CONFIG_CIFS_STATS2
 		atomic_set(&totBufAllocCount, 0);
 		atomic_set(&totSmBufAllocCount, 0);
@@ -290,6 +286,8 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 			}
 		}
 		spin_unlock(&cifs_tcp_ses_lock);
+	} else {
+		return rc;
 	}
 
 	return count;
@@ -433,17 +431,17 @@ static int cifsFYI_proc_open(struct inode *inode, struct file *file)
 static ssize_t cifsFYI_proc_write(struct file *file, const char __user *buffer,
 		size_t count, loff_t *ppos)
 {
-	char c;
+	char c[2] = { '\0' };
 	bool bv;
 	int rc;
 
-	rc = get_user(c, buffer);
+	rc = get_user(c[0], buffer);
 	if (rc)
 		return rc;
-	if (strtobool(&c, &bv) == 0)
+	if (strtobool(c, &bv) == 0)
 		cifsFYI = bv;
-	else if ((c > '1') && (c <= '9'))
-		cifsFYI = (int) (c - '0'); /* see cifs_debug.h for meanings */
+	else if ((c[0] > '1') && (c[0] <= '9'))
+		cifsFYI = (int) (c[0] - '0'); /* see cifs_debug.h for meanings */
 
 	return count;
 }
@@ -471,20 +469,12 @@ static int cifs_linux_ext_proc_open(struct inode *inode, struct file *file)
 static ssize_t cifs_linux_ext_proc_write(struct file *file,
 		const char __user *buffer, size_t count, loff_t *ppos)
 {
-	char c;
-	bool bv;
 	int rc;
 
-	rc = get_user(c, buffer);
+	rc = kstrtobool_from_user(buffer, count, &linuxExtEnabled);
 	if (rc)
 		return rc;
 
-	rc = strtobool(&c, &bv);
-	if (rc)
-		return rc;
-
-	linuxExtEnabled = bv;
-
 	return count;
 }
 
@@ -511,20 +501,12 @@ static int cifs_lookup_cache_proc_open(struct inode *inode, struct file *file)
 static ssize_t cifs_lookup_cache_proc_write(struct file *file,
 		const char __user *buffer, size_t count, loff_t *ppos)
 {
-	char c;
-	bool bv;
 	int rc;
 
-	rc = get_user(c, buffer);
+	rc = kstrtobool_from_user(buffer, count, &lookupCacheEnabled);
 	if (rc)
 		return rc;
 
-	rc = strtobool(&c, &bv);
-	if (rc)
-		return rc;
-
-	lookupCacheEnabled = bv;
-
 	return count;
 }
 
@@ -551,20 +533,12 @@ static int traceSMB_proc_open(struct inode *inode, struct file *file)
 static ssize_t traceSMB_proc_write(struct file *file, const char __user *buffer,
 		size_t count, loff_t *ppos)
 {
-	char c;
-	bool bv;
 	int rc;
 
-	rc = get_user(c, buffer);
+	rc = kstrtobool_from_user(buffer, count, &traceSMB);
 	if (rc)
 		return rc;
 
-	rc = strtobool(&c, &bv);
-	if (rc)
-		return rc;
-
-	traceSMB = bv;
-
 	return count;
 }
 
@@ -622,7 +596,6 @@ static ssize_t cifs_security_flags_proc_write(struct file *file,
 	int rc;
 	unsigned int flags;
 	char flags_string[12];
-	char c;
 	bool bv;
 
 	if ((count < 1) || (count > 11))
@@ -635,11 +608,10 @@ static ssize_t cifs_security_flags_proc_write(struct file *file,
 
 	if (count < 3) {
 		/* single char or single char followed by null */
-		c = flags_string[0];
-		if (strtobool(&c, &bv) == 0) {
+		if (strtobool(flags_string, &bv) == 0) {
 			global_secflags = bv ? CIFSSEC_MAX : CIFSSEC_DEF;
 			return count;
-		} else if (!isdigit(c)) {
+		} else if (!isdigit(flags_string[0])) {
 			cifs_dbg(VFS, "Invalid SecurityFlags: %s\n",
 					flags_string);
 			return -EINVAL;
diff --git a/fs/cifs/cifs_debug.h b/fs/cifs/cifs_debug.h
index f40fbaca1b2a..c611ca2339d7 100644
--- a/fs/cifs/cifs_debug.h
+++ b/fs/cifs/cifs_debug.h
@@ -25,7 +25,7 @@
 void cifs_dump_mem(char *label, void *data, int length);
 void cifs_dump_detail(void *);
 void cifs_dump_mids(struct TCP_Server_Info *);
-extern int traceSMB;		/* flag which enables the function below */
+extern bool traceSMB;		/* flag which enables the function below */
 void dump_smb(void *, int);
 #define CIFS_INFO	0x01
 #define CIFS_RC		0x02
@@ -51,14 +51,13 @@ __printf(1, 2) void cifs_vfs_err(const char *fmt, ...);
 /* information message: e.g., configuration, major event */
 #define cifs_dbg(type, fmt, ...)					\
 do {									\
-	if (type == FYI) {						\
-		if (cifsFYI & CIFS_INFO) {				\
-			pr_debug("%s: " fmt, __FILE__, ##__VA_ARGS__);	\
-		}							\
+	if (type == FYI && cifsFYI & CIFS_INFO) {			\
+		pr_debug_ratelimited("%s: "				\
+			    fmt, __FILE__, ##__VA_ARGS__);		\
 	} else if (type == VFS) {					\
 		cifs_vfs_err(fmt, ##__VA_ARGS__);			\
 	} else if (type == NOISY && type != 0) {			\
-		pr_debug(fmt, ##__VA_ARGS__);				\
+		pr_debug_ratelimited(fmt, ##__VA_ARGS__);		\
 	}								\
 } while (0)
 
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index 7dc886c9a78f..e956cba94338 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -175,7 +175,7 @@ char *cifs_compose_mount_options(const char *sb_mountdata,
 	 * string to the length of the original string to allow for worst case.
 	 */
 	md_len = strlen(sb_mountdata) + INET6_ADDRSTRLEN;
-	mountdata = kzalloc(md_len + 1, GFP_KERNEL);
+	mountdata = kzalloc(md_len + sizeof("ip=") + 1, GFP_KERNEL);
 	if (mountdata == NULL) {
 		rc = -ENOMEM;
 		goto compose_mount_options_err;
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index afa09fce8151..4897dacf8944 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -33,6 +33,7 @@
 #include <linux/ctype.h>
 #include <linux/random.h>
 #include <linux/highmem.h>
+#include <crypto/skcipher.h>
 
 static int
 cifs_crypto_shash_md5_allocate(struct TCP_Server_Info *server)
@@ -714,7 +715,7 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
 
 	ses->auth_key.response = kmalloc(baselen + tilen, GFP_KERNEL);
 	if (!ses->auth_key.response) {
-		rc = ENOMEM;
+		rc = -ENOMEM;
 		ses->auth_key.len = 0;
 		goto setup_ntlmv2_rsp_ret;
 	}
@@ -789,38 +790,46 @@ int
 calc_seckey(struct cifs_ses *ses)
 {
 	int rc;
-	struct crypto_blkcipher *tfm_arc4;
+	struct crypto_skcipher *tfm_arc4;
 	struct scatterlist sgin, sgout;
-	struct blkcipher_desc desc;
+	struct skcipher_request *req;
 	unsigned char sec_key[CIFS_SESS_KEY_SIZE]; /* a nonce */
 
 	get_random_bytes(sec_key, CIFS_SESS_KEY_SIZE);
 
-	tfm_arc4 = crypto_alloc_blkcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC);
+	tfm_arc4 = crypto_alloc_skcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(tfm_arc4)) {
 		rc = PTR_ERR(tfm_arc4);
 		cifs_dbg(VFS, "could not allocate crypto API arc4\n");
 		return rc;
 	}
 
-	desc.tfm = tfm_arc4;
-
-	rc = crypto_blkcipher_setkey(tfm_arc4, ses->auth_key.response,
+	rc = crypto_skcipher_setkey(tfm_arc4, ses->auth_key.response,
 					CIFS_SESS_KEY_SIZE);
 	if (rc) {
 		cifs_dbg(VFS, "%s: Could not set response as a key\n",
 			 __func__);
-		return rc;
+		goto out_free_cipher;
+	}
+
+	req = skcipher_request_alloc(tfm_arc4, GFP_KERNEL);
+	if (!req) {
+		rc = -ENOMEM;
+		cifs_dbg(VFS, "could not allocate crypto API arc4 request\n");
+		goto out_free_cipher;
 	}
 
 	sg_init_one(&sgin, sec_key, CIFS_SESS_KEY_SIZE);
 	sg_init_one(&sgout, ses->ntlmssp->ciphertext, CIFS_CPHTXT_SIZE);
 
-	rc = crypto_blkcipher_encrypt(&desc, &sgout, &sgin, CIFS_CPHTXT_SIZE);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, &sgin, &sgout, CIFS_CPHTXT_SIZE, NULL);
+
+	rc = crypto_skcipher_encrypt(req);
+	skcipher_request_free(req);
 	if (rc) {
 		cifs_dbg(VFS, "could not encrypt session key rc: %d\n", rc);
-		crypto_free_blkcipher(tfm_arc4);
-		return rc;
+		goto out_free_cipher;
 	}
 
 	/* make secondary_key/nonce as session key */
@@ -828,7 +837,8 @@ calc_seckey(struct cifs_ses *ses)
 	/* and make len as that of session key only */
 	ses->auth_key.len = CIFS_SESS_KEY_SIZE;
 
-	crypto_free_blkcipher(tfm_arc4);
+out_free_cipher:
+	crypto_free_skcipher(tfm_arc4);
 
 	return rc;
 }
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index e739950ca084..89201564c346 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -54,10 +54,10 @@
 #endif
 
 int cifsFYI = 0;
-int traceSMB = 0;
+bool traceSMB;
 bool enable_oplocks = true;
-unsigned int linuxExtEnabled = 1;
-unsigned int lookupCacheEnabled = 1;
+bool linuxExtEnabled = true;
+bool lookupCacheEnabled = true;
 unsigned int global_secflags = CIFSSEC_DEF;
 /* unsigned int ntlmv2_support = 0; */
 unsigned int sign_CIFS_PDUs = 1;
@@ -454,6 +454,10 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 		seq_puts(s, ",nocase");
 	if (tcon->retry)
 		seq_puts(s, ",hard");
+	if (tcon->use_persistent)
+		seq_puts(s, ",persistenthandles");
+	else if (tcon->use_resilient)
+		seq_puts(s, ",resilienthandles");
 	if (tcon->unix_ext)
 		seq_puts(s, ",unix");
 	else
@@ -503,6 +507,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 
 	seq_printf(s, ",rsize=%u", cifs_sb->rsize);
 	seq_printf(s, ",wsize=%u", cifs_sb->wsize);
+	seq_printf(s, ",echo_interval=%lu",
+			tcon->ses->server->echo_interval / HZ);
 	/* convert actimeo and display it in seconds */
 	seq_printf(s, ",actimeo=%lu", cifs_sb->actimeo / HZ);
 
@@ -636,9 +642,7 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb)
 		while (*s && *s != sep)
 			s++;
 
-		mutex_lock(&dir->i_mutex);
-		child = lookup_one_len(p, dentry, s - p);
-		mutex_unlock(&dir->i_mutex);
+		child = lookup_one_len_unlocked(p, dentry, s - p);
 		dput(dentry);
 		dentry = child;
 	} while (!IS_ERR(dentry));
@@ -748,6 +752,9 @@ cifs_loose_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 	ssize_t rc;
 	struct inode *inode = file_inode(iocb->ki_filp);
 
+	if (iocb->ki_filp->f_flags & O_DIRECT)
+		return cifs_user_readv(iocb, iter);
+
 	rc = cifs_revalidate_mapping(inode);
 	if (rc)
 		return rc;
@@ -762,6 +769,18 @@ static ssize_t cifs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	ssize_t written;
 	int rc;
 
+	if (iocb->ki_filp->f_flags & O_DIRECT) {
+		written = cifs_user_writev(iocb, from);
+		if (written > 0 && CIFS_CACHE_READ(cinode)) {
+			cifs_zap_mapping(inode);
+			cifs_dbg(FYI,
+				 "Set no oplock for inode=%p after a write operation\n",
+				 inode);
+			cinode->oplock = 0;
+		}
+		return written;
+	}
+
 	written = cifs_get_writer(cinode);
 	if (written)
 		return written;
@@ -896,8 +915,7 @@ const struct inode_operations cifs_file_inode_ops = {
 
 const struct inode_operations cifs_symlink_inode_ops = {
 	.readlink = generic_readlink,
-	.follow_link = cifs_follow_link,
-	.put_link = kfree_put_link,
+	.get_link = cifs_get_link,
 	.permission = cifs_permission,
 	/* BB add the following two eventually */
 	/* revalidate: cifs_revalidate,
@@ -910,6 +928,59 @@ const struct inode_operations cifs_symlink_inode_ops = {
 #endif
 };
 
+static int cifs_clone_file_range(struct file *src_file, loff_t off,
+		struct file *dst_file, loff_t destoff, u64 len)
+{
+	struct inode *src_inode = file_inode(src_file);
+	struct inode *target_inode = file_inode(dst_file);
+	struct cifsFileInfo *smb_file_src = src_file->private_data;
+	struct cifsFileInfo *smb_file_target = dst_file->private_data;
+	struct cifs_tcon *target_tcon = tlink_tcon(smb_file_target->tlink);
+	unsigned int xid;
+	int rc;
+
+	cifs_dbg(FYI, "clone range\n");
+
+	xid = get_xid();
+
+	if (!src_file->private_data || !dst_file->private_data) {
+		rc = -EBADF;
+		cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
+		goto out;
+	}
+
+	/*
+	 * Note: cifs case is easier than btrfs since server responsible for
+	 * checks for proper open modes and file type and if it wants
+	 * server could even support copy of range where source = target
+	 */
+	lock_two_nondirectories(target_inode, src_inode);
+
+	if (len == 0)
+		len = src_inode->i_size - off;
+
+	cifs_dbg(FYI, "about to flush pages\n");
+	/* should we flush first and last page first */
+	truncate_inode_pages_range(&target_inode->i_data, destoff,
+				   PAGE_ALIGN(destoff + len)-1);
+
+	if (target_tcon->ses->server->ops->duplicate_extents)
+		rc = target_tcon->ses->server->ops->duplicate_extents(xid,
+			smb_file_src, smb_file_target, off, len, destoff);
+	else
+		rc = -EOPNOTSUPP;
+
+	/* force revalidate of size and timestamps of target file now
+	   that target is updated on the server */
+	CIFS_I(target_inode)->time = 0;
+	/* although unlocking in the reverse order from locking is not
+	   strictly necessary here it is a little cleaner to be consistent */
+	unlock_two_nondirectories(src_inode, target_inode);
+out:
+	free_xid(xid);
+	return rc;
+}
+
 const struct file_operations cifs_file_ops = {
 	.read_iter = cifs_loose_read_iter,
 	.write_iter = cifs_file_write_iter,
@@ -921,9 +992,8 @@ const struct file_operations cifs_file_ops = {
 	.mmap  = cifs_file_mmap,
 	.splice_read = generic_file_splice_read,
 	.llseek = cifs_llseek,
-#ifdef CONFIG_CIFS_POSIX
 	.unlocked_ioctl	= cifs_ioctl,
-#endif /* CONFIG_CIFS_POSIX */
+	.clone_file_range = cifs_clone_file_range,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
 };
@@ -939,9 +1009,8 @@ const struct file_operations cifs_file_strict_ops = {
 	.mmap = cifs_file_strict_mmap,
 	.splice_read = generic_file_splice_read,
 	.llseek = cifs_llseek,
-#ifdef CONFIG_CIFS_POSIX
 	.unlocked_ioctl	= cifs_ioctl,
-#endif /* CONFIG_CIFS_POSIX */
+	.clone_file_range = cifs_clone_file_range,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
 };
@@ -957,9 +1026,8 @@ const struct file_operations cifs_file_direct_ops = {
 	.flush = cifs_flush,
 	.mmap = cifs_file_mmap,
 	.splice_read = generic_file_splice_read,
-#ifdef CONFIG_CIFS_POSIX
 	.unlocked_ioctl  = cifs_ioctl,
-#endif /* CONFIG_CIFS_POSIX */
+	.clone_file_range = cifs_clone_file_range,
 	.llseek = cifs_llseek,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
@@ -975,9 +1043,8 @@ const struct file_operations cifs_file_nobrl_ops = {
 	.mmap  = cifs_file_mmap,
 	.splice_read = generic_file_splice_read,
 	.llseek = cifs_llseek,
-#ifdef CONFIG_CIFS_POSIX
 	.unlocked_ioctl	= cifs_ioctl,
-#endif /* CONFIG_CIFS_POSIX */
+	.clone_file_range = cifs_clone_file_range,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
 };
@@ -992,9 +1059,8 @@ const struct file_operations cifs_file_strict_nobrl_ops = {
 	.mmap = cifs_file_strict_mmap,
 	.splice_read = generic_file_splice_read,
 	.llseek = cifs_llseek,
-#ifdef CONFIG_CIFS_POSIX
 	.unlocked_ioctl	= cifs_ioctl,
-#endif /* CONFIG_CIFS_POSIX */
+	.clone_file_range = cifs_clone_file_range,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
 };
@@ -1009,9 +1075,8 @@ const struct file_operations cifs_file_direct_nobrl_ops = {
 	.flush = cifs_flush,
 	.mmap = cifs_file_mmap,
 	.splice_read = generic_file_splice_read,
-#ifdef CONFIG_CIFS_POSIX
 	.unlocked_ioctl  = cifs_ioctl,
-#endif /* CONFIG_CIFS_POSIX */
+	.clone_file_range = cifs_clone_file_range,
 	.llseek = cifs_llseek,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
@@ -1022,6 +1087,7 @@ const struct file_operations cifs_dir_ops = {
 	.release = cifs_closedir,
 	.read    = generic_read_dir,
 	.unlocked_ioctl  = cifs_ioctl,
+	.clone_file_range = cifs_clone_file_range,
 	.llseek = generic_file_llseek,
 };
 
@@ -1040,7 +1106,7 @@ cifs_init_inodecache(void)
 	cifs_inode_cachep = kmem_cache_create("cifs_inode_cache",
 					      sizeof(struct cifsInodeInfo),
 					      0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD),
+						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
 					      cifs_init_once);
 	if (cifs_inode_cachep == NULL)
 		return -ENOMEM;
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index c3cc1609025f..83aac8ba50b0 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -31,19 +31,15 @@
  * so that it will fit. We use hash_64 to convert the value to 31 bits, and
  * then add 1, to ensure that we don't end up with a 0 as the value.
  */
-#if BITS_PER_LONG == 64
 static inline ino_t
 cifs_uniqueid_to_ino_t(u64 fileid)
 {
+	if ((sizeof(ino_t)) < (sizeof(u64)))
+		return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1;
+
 	return (ino_t)fileid;
+
 }
-#else
-static inline ino_t
-cifs_uniqueid_to_ino_t(u64 fileid)
-{
-	return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1;
-}
-#endif
 
 extern struct file_system_type cifs_fs_type;
 extern const struct address_space_operations cifs_addr_ops;
@@ -120,9 +116,8 @@ extern struct vfsmount *cifs_dfs_d_automount(struct path *path);
 #endif
 
 /* Functions related to symlinks */
-extern const char *cifs_follow_link(struct dentry *direntry, void **cookie);
-extern int cifs_readlink(struct dentry *direntry, char __user *buffer,
-			 int buflen);
+extern const char *cifs_get_link(struct dentry *, struct inode *,
+			struct delayed_call *);
 extern int cifs_symlink(struct inode *inode, struct dentry *direntry,
 			const char *symname);
 extern int	cifs_removexattr(struct dentry *, const char *);
@@ -131,7 +126,6 @@ extern int	cifs_setxattr(struct dentry *, const char *, const void *,
 extern ssize_t	cifs_getxattr(struct dentry *, const char *, void *, size_t);
 extern ssize_t	cifs_listxattr(struct dentry *, char *, size_t);
 extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
-
 #ifdef CONFIG_CIFS_NFSD_EXPORT
 extern const struct export_operations cifs_export_ops;
 #endif /* CONFIG_CIFS_NFSD_EXPORT */
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index b406a32deb1f..f2cc0b3d1af7 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -70,8 +70,10 @@
 #define SERVER_NAME_LENGTH 40
 #define SERVER_NAME_LEN_WITH_NULL     (SERVER_NAME_LENGTH + 1)
 
-/* SMB echo "timeout" -- FIXME: tunable? */
-#define SMB_ECHO_INTERVAL (60 * HZ)
+/* echo interval in seconds */
+#define SMB_ECHO_INTERVAL_MIN 1
+#define SMB_ECHO_INTERVAL_MAX 600
+#define SMB_ECHO_INTERVAL_DEFAULT 60
 
 #include "cifspdu.h"
 
@@ -225,7 +227,7 @@ struct smb_version_operations {
 	void (*print_stats)(struct seq_file *m, struct cifs_tcon *);
 	void (*dump_share_caps)(struct seq_file *, struct cifs_tcon *);
 	/* verify the message */
-	int (*check_message)(char *, unsigned int);
+	int (*check_message)(char *, unsigned int, struct TCP_Server_Info *);
 	bool (*is_oplock_break)(char *, struct TCP_Server_Info *);
 	void (*downgrade_oplock)(struct TCP_Server_Info *,
 					struct cifsInodeInfo *, bool);
@@ -493,7 +495,10 @@ struct smb_vol {
 	bool mfsymlinks:1; /* use Minshall+French Symlinks */
 	bool multiuser:1;
 	bool rwpidforward:1; /* pid forward for read/write operations */
-	bool nosharesock;
+	bool nosharesock:1;
+	bool persistent:1;
+	bool nopersistent:1;
+	bool resilient:1; /* noresilient not required since not fored for CA */
 	unsigned int rsize;
 	unsigned int wsize;
 	bool sockopt_tcp_nodelay:1;
@@ -504,6 +509,7 @@ struct smb_vol {
 	struct sockaddr_storage dstaddr; /* destination address */
 	struct sockaddr_storage srcaddr; /* allow binding to a local IP */
 	struct nls_table *local_nls;
+	unsigned int echo_interval; /* echo interval in secs */
 };
 
 #define CIFS_MOUNT_MASK (CIFS_MOUNT_NO_PERM | CIFS_MOUNT_SET_UID | \
@@ -624,7 +630,9 @@ struct TCP_Server_Info {
 #ifdef CONFIG_CIFS_SMB2
 	unsigned int	max_read;
 	unsigned int	max_write;
+	__u8		preauth_hash[512];
 #endif /* CONFIG_CIFS_SMB2 */
+	unsigned long echo_interval;
 };
 
 static inline unsigned int
@@ -706,7 +714,7 @@ compare_mid(__u16 mid, const struct smb_hdr *smb)
  *
  * Note that this might make for "interesting" allocation problems during
  * writeback however as we have to allocate an array of pointers for the
- * pages. A 16M write means ~32kb page array with PAGE_CACHE_SIZE == 4096.
+ * pages. A 16M write means ~32kb page array with PAGE_SIZE == 4096.
  *
  * For reads, there is a similar problem as we need to allocate an array
  * of kvecs to handle the receive, though that should only need to be done
@@ -725,7 +733,7 @@ compare_mid(__u16 mid, const struct smb_hdr *smb)
 
 /*
  * The default wsize is 1M. find_get_pages seems to return a maximum of 256
- * pages in a single call. With PAGE_CACHE_SIZE == 4k, this means we can fill
+ * pages in a single call. With PAGE_SIZE == 4k, this means we can fill
  * a single wsize request with a single call.
  */
 #define CIFS_DEFAULT_IOSIZE (1024 * 1024)
@@ -806,7 +814,10 @@ struct cifs_ses {
 	bool need_reconnect:1; /* connection reset, uid now invalid */
 #ifdef CONFIG_CIFS_SMB2
 	__u16 session_flags;
-	char smb3signingkey[SMB3_SIGN_KEY_SIZE]; /* for signing smb3 packets */
+	__u8 smb3signingkey[SMB3_SIGN_KEY_SIZE];
+	__u8 smb3encryptionkey[SMB3_SIGN_KEY_SIZE];
+	__u8 smb3decryptionkey[SMB3_SIGN_KEY_SIZE];
+	__u8 preauth_hash[512];
 #endif /* CONFIG_CIFS_SMB2 */
 };
 
@@ -895,6 +906,8 @@ struct cifs_tcon {
 	bool broken_posix_open; /* e.g. Samba server versions < 3.3.2, 3.2.9 */
 	bool broken_sparse_sup; /* if server or share does not support sparse */
 	bool need_reconnect:1; /* connection reset, tid now invalid */
+	bool use_resilient:1; /* use resilient instead of durable handles */
+	bool use_persistent:1; /* use persistent instead of durable handles */
 #ifdef CONFIG_CIFS_SMB2
 	bool print:1;		/* set if connection to printer share */
 	bool bad_network_name:1; /* set if ret status STATUS_BAD_NETWORK_NAME */
@@ -1015,6 +1028,7 @@ struct cifs_fid {
 	__u64 persistent_fid;	/* persist file id for smb2 */
 	__u64 volatile_fid;	/* volatile file id for smb2 */
 	__u8 lease_key[SMB2_LEASE_KEY_SIZE];	/* lease key for smb2 */
+	__u8 create_guid[16];
 #endif
 	struct cifs_pending_open *pending_open;
 	unsigned int epoch;
@@ -1582,11 +1596,11 @@ GLOBAL_EXTERN atomic_t midCount;
 
 /* Misc globals */
 GLOBAL_EXTERN bool enable_oplocks; /* enable or disable oplocks */
-GLOBAL_EXTERN unsigned int lookupCacheEnabled;
+GLOBAL_EXTERN bool lookupCacheEnabled;
 GLOBAL_EXTERN unsigned int global_secflags;	/* if on, session setup sent
 				with more secure ntlmssp2 challenge/resp */
 GLOBAL_EXTERN unsigned int sign_CIFS_PDUs;  /* enable smb packet signing */
-GLOBAL_EXTERN unsigned int linuxExtEnabled;/*enable Linux/Unix CIFS extensions*/
+GLOBAL_EXTERN bool linuxExtEnabled;/*enable Linux/Unix CIFS extensions*/
 GLOBAL_EXTERN unsigned int CIFSMaxBufSize;  /* max size not including hdr */
 GLOBAL_EXTERN unsigned int cifs_min_rcv;    /* min size of big ntwrk buf pool */
 GLOBAL_EXTERN unsigned int cifs_min_small;  /* min size of small buf pool */
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index c63fd1dde25b..eed7ff50faf0 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -102,7 +102,7 @@ extern int SendReceiveBlockingLock(const unsigned int xid,
 			struct smb_hdr *out_buf,
 			int *bytes_returned);
 extern int cifs_reconnect(struct TCP_Server_Info *server);
-extern int checkSMB(char *buf, unsigned int length);
+extern int checkSMB(char *buf, unsigned int len, struct TCP_Server_Info *srvr);
 extern bool is_valid_oplock_break(char *, struct TCP_Server_Info *);
 extern bool backup_cred(struct cifs_sb_info *);
 extern bool is_size_safe_to_change(struct cifsInodeInfo *, __u64 eof);
@@ -439,7 +439,8 @@ extern int setup_ntlm_response(struct cifs_ses *, const struct nls_table *);
 extern int setup_ntlmv2_rsp(struct cifs_ses *, const struct nls_table *);
 extern void cifs_crypto_shash_release(struct TCP_Server_Info *);
 extern int calc_seckey(struct cifs_ses *);
-extern int generate_smb3signingkey(struct cifs_ses *);
+extern int generate_smb30signingkey(struct cifs_ses *);
+extern int generate_smb311signingkey(struct cifs_ses *);
 
 #ifdef CONFIG_CIFS_WEAK_PW_HASH
 extern int calc_lanman_hash(const char *password, const char *cryptkey,
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 90b4f9f7de66..a894bf809ff7 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1396,11 +1396,10 @@ openRetry:
  * current bigbuf.
  */
 static int
-cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
+discard_remaining_data(struct TCP_Server_Info *server)
 {
 	unsigned int rfclen = get_rfc1002_length(server->smallbuf);
 	int remaining = rfclen + 4 - server->total_read;
-	struct cifs_readdata *rdata = mid->callback_data;
 
 	while (remaining > 0) {
 		int length;
@@ -1414,10 +1413,20 @@ cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 		remaining -= length;
 	}
 
-	dequeue_mid(mid, rdata->result);
 	return 0;
 }
 
+static int
+cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
+{
+	int length;
+	struct cifs_readdata *rdata = mid->callback_data;
+
+	length = discard_remaining_data(server);
+	dequeue_mid(mid, rdata->result);
+	return length;
+}
+
 int
 cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 {
@@ -1446,6 +1455,12 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 		return length;
 	server->total_read += length;
 
+	if (server->ops->is_status_pending &&
+	    server->ops->is_status_pending(buf, server, 0)) {
+		discard_remaining_data(server);
+		return -1;
+	}
+
 	/* Was the SMB read successful? */
 	rdata->result = server->ops->map_error(buf, false);
 	if (rdata->result != 0) {
@@ -1914,17 +1929,17 @@ cifs_writev_requeue(struct cifs_writedata *wdata)
 
 		wsize = server->ops->wp_retry_size(inode);
 		if (wsize < rest_len) {
-			nr_pages = wsize / PAGE_CACHE_SIZE;
+			nr_pages = wsize / PAGE_SIZE;
 			if (!nr_pages) {
 				rc = -ENOTSUPP;
 				break;
 			}
-			cur_len = nr_pages * PAGE_CACHE_SIZE;
-			tailsz = PAGE_CACHE_SIZE;
+			cur_len = nr_pages * PAGE_SIZE;
+			tailsz = PAGE_SIZE;
 		} else {
-			nr_pages = DIV_ROUND_UP(rest_len, PAGE_CACHE_SIZE);
+			nr_pages = DIV_ROUND_UP(rest_len, PAGE_SIZE);
 			cur_len = rest_len;
-			tailsz = rest_len - (nr_pages - 1) * PAGE_CACHE_SIZE;
+			tailsz = rest_len - (nr_pages - 1) * PAGE_SIZE;
 		}
 
 		wdata2 = cifs_writedata_alloc(nr_pages, cifs_writev_complete);
@@ -1942,7 +1957,7 @@ cifs_writev_requeue(struct cifs_writedata *wdata)
 		wdata2->sync_mode = wdata->sync_mode;
 		wdata2->nr_pages = nr_pages;
 		wdata2->offset = page_offset(wdata2->pages[0]);
-		wdata2->pagesz = PAGE_CACHE_SIZE;
+		wdata2->pagesz = PAGE_SIZE;
 		wdata2->tailsz = tailsz;
 		wdata2->bytes = cur_len;
 
@@ -1960,7 +1975,7 @@ cifs_writev_requeue(struct cifs_writedata *wdata)
 			if (rc != 0 && rc != -EAGAIN) {
 				SetPageError(wdata2->pages[j]);
 				end_page_writeback(wdata2->pages[j]);
-				page_cache_release(wdata2->pages[j]);
+				put_page(wdata2->pages[j]);
 			}
 		}
 
@@ -2003,7 +2018,7 @@ cifs_writev_complete(struct work_struct *work)
 		else if (wdata->result < 0)
 			SetPageError(page);
 		end_page_writeback(page);
-		page_cache_release(page);
+		put_page(page);
 	}
 	if (wdata->result != -EAGAIN)
 		mapping_set_error(inode->i_mapping, wdata->result);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 3f2228570d44..6f62ac821a84 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -87,12 +87,15 @@ enum {
 	Opt_sign, Opt_seal, Opt_noac,
 	Opt_fsc, Opt_mfsymlinks,
 	Opt_multiuser, Opt_sloppy, Opt_nosharesock,
+	Opt_persistent, Opt_nopersistent,
+	Opt_resilient, Opt_noresilient,
 
 	/* Mount options which take numeric value */
 	Opt_backupuid, Opt_backupgid, Opt_uid,
 	Opt_cruid, Opt_gid, Opt_file_mode,
 	Opt_dirmode, Opt_port,
 	Opt_rsize, Opt_wsize, Opt_actimeo,
+	Opt_echo_interval,
 
 	/* Mount options which take string value */
 	Opt_user, Opt_pass, Opt_ip,
@@ -169,6 +172,10 @@ static const match_table_t cifs_mount_option_tokens = {
 	{ Opt_multiuser, "multiuser" },
 	{ Opt_sloppy, "sloppy" },
 	{ Opt_nosharesock, "nosharesock" },
+	{ Opt_persistent, "persistenthandles"},
+	{ Opt_nopersistent, "nopersistenthandles"},
+	{ Opt_resilient, "resilienthandles"},
+	{ Opt_noresilient, "noresilienthandles"},
 
 	{ Opt_backupuid, "backupuid=%s" },
 	{ Opt_backupgid, "backupgid=%s" },
@@ -182,6 +189,7 @@ static const match_table_t cifs_mount_option_tokens = {
 	{ Opt_rsize, "rsize=%s" },
 	{ Opt_wsize, "wsize=%s" },
 	{ Opt_actimeo, "actimeo=%s" },
+	{ Opt_echo_interval, "echo_interval=%s" },
 
 	{ Opt_blank_user, "user=" },
 	{ Opt_blank_user, "username=" },
@@ -362,7 +370,6 @@ cifs_reconnect(struct TCP_Server_Info *server)
 	server->session_key.response = NULL;
 	server->session_key.len = 0;
 	server->lstrp = jiffies;
-	mutex_unlock(&server->srv_mutex);
 
 	/* mark submitted MIDs for retry and issue callback */
 	INIT_LIST_HEAD(&retry_list);
@@ -375,6 +382,7 @@ cifs_reconnect(struct TCP_Server_Info *server)
 		list_move(&mid_entry->qhead, &retry_list);
 	}
 	spin_unlock(&GlobalMid_Lock);
+	mutex_unlock(&server->srv_mutex);
 
 	cifs_dbg(FYI, "%s: issuing mid callbacks\n", __func__);
 	list_for_each_safe(tmp, tmp2, &retry_list) {
@@ -412,6 +420,7 @@ cifs_echo_request(struct work_struct *work)
 	int rc;
 	struct TCP_Server_Info *server = container_of(work,
 					struct TCP_Server_Info, echo.work);
+	unsigned long echo_interval = server->echo_interval;
 
 	/*
 	 * We cannot send an echo if it is disabled or until the
@@ -421,7 +430,7 @@ cifs_echo_request(struct work_struct *work)
 	 */
 	if (!server->ops->need_neg || server->ops->need_neg(server) ||
 	    (server->ops->can_echo && !server->ops->can_echo(server)) ||
-	    time_before(jiffies, server->lstrp + SMB_ECHO_INTERVAL - HZ))
+	    time_before(jiffies, server->lstrp + echo_interval - HZ))
 		goto requeue_echo;
 
 	rc = server->ops->echo ? server->ops->echo(server) : -ENOSYS;
@@ -430,7 +439,7 @@ cifs_echo_request(struct work_struct *work)
 			 server->hostname);
 
 requeue_echo:
-	queue_delayed_work(cifsiod_wq, &server->echo, SMB_ECHO_INTERVAL);
+	queue_delayed_work(cifsiod_wq, &server->echo, echo_interval);
 }
 
 static bool
@@ -481,9 +490,9 @@ server_unresponsive(struct TCP_Server_Info *server)
 	 *     a response in >60s.
 	 */
 	if (server->tcpStatus == CifsGood &&
-	    time_after(jiffies, server->lstrp + 2 * SMB_ECHO_INTERVAL)) {
-		cifs_dbg(VFS, "Server %s has not responded in %d seconds. Reconnecting...\n",
-			 server->hostname, (2 * SMB_ECHO_INTERVAL) / HZ);
+	    time_after(jiffies, server->lstrp + 2 * server->echo_interval)) {
+		cifs_dbg(VFS, "Server %s has not responded in %lu seconds. Reconnecting...\n",
+			 server->hostname, (2 * server->echo_interval) / HZ);
 		cifs_reconnect(server);
 		wake_up(&server->response_q);
 		return true;
@@ -822,7 +831,7 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 	 * 48 bytes is enough to display the header and a little bit
 	 * into the payload for debugging purposes.
 	 */
-	length = server->ops->check_message(buf, server->total_read);
+	length = server->ops->check_message(buf, server->total_read, server);
 	if (length != 0)
 		cifs_dump_mem("Bad SMB: ", buf,
 			min_t(unsigned int, server->total_read, 48));
@@ -1497,6 +1506,33 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 		case Opt_nosharesock:
 			vol->nosharesock = true;
 			break;
+		case Opt_nopersistent:
+			vol->nopersistent = true;
+			if (vol->persistent) {
+				cifs_dbg(VFS,
+				  "persistenthandles mount options conflict\n");
+				goto cifs_parse_mount_err;
+			}
+			break;
+		case Opt_persistent:
+			vol->persistent = true;
+			if ((vol->nopersistent) || (vol->resilient)) {
+				cifs_dbg(VFS,
+				  "persistenthandles mount options conflict\n");
+				goto cifs_parse_mount_err;
+			}
+			break;
+		case Opt_resilient:
+			vol->resilient = true;
+			if (vol->persistent) {
+				cifs_dbg(VFS,
+				  "persistenthandles mount options conflict\n");
+				goto cifs_parse_mount_err;
+			}
+			break;
+		case Opt_noresilient:
+			vol->resilient = false; /* already the default */
+			break;
 
 		/* Numeric Values */
 		case Opt_backupuid:
@@ -1591,6 +1627,14 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 				goto cifs_parse_mount_err;
 			}
 			break;
+		case Opt_echo_interval:
+			if (get_option_ul(args, &option)) {
+				cifs_dbg(VFS, "%s: Invalid echo interval value\n",
+					 __func__);
+				goto cifs_parse_mount_err;
+			}
+			vol->echo_interval = option;
+			break;
 
 		/* String Arguments */
 
@@ -2056,6 +2100,9 @@ static int match_server(struct TCP_Server_Info *server, struct smb_vol *vol)
 	if (!match_security(server, vol))
 		return 0;
 
+	if (server->echo_interval != vol->echo_interval)
+		return 0;
+
 	return 1;
 }
 
@@ -2175,6 +2222,12 @@ cifs_get_tcp_session(struct smb_vol *volume_info)
 	tcp_ses->tcpStatus = CifsNew;
 	++tcp_ses->srv_count;
 
+	if (volume_info->echo_interval >= SMB_ECHO_INTERVAL_MIN &&
+		volume_info->echo_interval <= SMB_ECHO_INTERVAL_MAX)
+		tcp_ses->echo_interval = volume_info->echo_interval * HZ;
+	else
+		tcp_ses->echo_interval = SMB_ECHO_INTERVAL_DEFAULT * HZ;
+
 	rc = ip_connect(tcp_ses);
 	if (rc < 0) {
 		cifs_dbg(VFS, "Error connecting to socket. Aborting operation.\n");
@@ -2204,7 +2257,7 @@ cifs_get_tcp_session(struct smb_vol *volume_info)
 	cifs_fscache_get_client_cookie(tcp_ses);
 
 	/* queue echo request delayed work */
-	queue_delayed_work(cifsiod_wq, &tcp_ses->echo, SMB_ECHO_INTERVAL);
+	queue_delayed_work(cifsiod_wq, &tcp_ses->echo, tcp_ses->echo_interval);
 
 	return tcp_ses;
 
@@ -2655,6 +2708,42 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 		cifs_dbg(FYI, "DFS disabled (%d)\n", tcon->Flags);
 	}
 	tcon->seal = volume_info->seal;
+	tcon->use_persistent = false;
+	/* check if SMB2 or later, CIFS does not support persistent handles */
+	if (volume_info->persistent) {
+		if (ses->server->vals->protocol_id == 0) {
+			cifs_dbg(VFS,
+			     "SMB3 or later required for persistent handles\n");
+			rc = -EOPNOTSUPP;
+			goto out_fail;
+#ifdef CONFIG_CIFS_SMB2
+		} else if (ses->server->capabilities &
+			   SMB2_GLOBAL_CAP_PERSISTENT_HANDLES)
+			tcon->use_persistent = true;
+		else /* persistent handles requested but not supported */ {
+			cifs_dbg(VFS,
+				"Persistent handles not supported on share\n");
+			rc = -EOPNOTSUPP;
+			goto out_fail;
+#endif /* CONFIG_CIFS_SMB2 */
+		}
+#ifdef CONFIG_CIFS_SMB2
+	} else if ((tcon->capabilities & SMB2_SHARE_CAP_CONTINUOUS_AVAILABILITY)
+	     && (ses->server->capabilities & SMB2_GLOBAL_CAP_PERSISTENT_HANDLES)
+	     && (volume_info->nopersistent == false)) {
+		cifs_dbg(FYI, "enabling persistent handles\n");
+		tcon->use_persistent = true;
+#endif /* CONFIG_CIFS_SMB2 */
+	} else if (volume_info->resilient) {
+		if (ses->server->vals->protocol_id == 0) {
+			cifs_dbg(VFS,
+			     "SMB2.1 or later required for resilient handles\n");
+			rc = -EOPNOTSUPP;
+			goto out_fail;
+		}
+		tcon->use_resilient = true;
+	}
+
 	/*
 	 * We can have only one retry value for a connection to a share so for
 	 * resources mounted more than once to the same server share the last
@@ -2910,8 +2999,7 @@ ip_rfc1001_connect(struct TCP_Server_Info *server)
 	if (ses_init_buf) {
 		ses_init_buf->trailer.session_req.called_len = 32;
 
-		if (server->server_RFC1001_name &&
-		    server->server_RFC1001_name[0] != 0)
+		if (server->server_RFC1001_name[0] != 0)
 			rfc1002mangle(ses_init_buf->trailer.
 				      session_req.called_name,
 				      server->server_RFC1001_name,
@@ -3503,6 +3591,15 @@ try_mount_again:
 		goto mount_fail_check;
 	}
 
+#ifdef CONFIG_CIFS_SMB2
+	if ((volume_info->persistent == true) && ((ses->server->capabilities &
+		SMB2_GLOBAL_CAP_PERSISTENT_HANDLES) == 0)) {
+		cifs_dbg(VFS, "persistent handles not supported by server\n");
+		rc = -EOPNOTSUPP;
+		goto mount_fail_check;
+	}
+#endif /* CONFIG_CIFS_SMB2*/
+
 	/* search for existing tcon to this server share */
 	tcon = cifs_get_tcon(ses, volume_info);
 	if (IS_ERR(tcon)) {
@@ -3533,7 +3630,7 @@ try_mount_again:
 	cifs_sb->rsize = server->ops->negotiate_rsize(tcon, volume_info);
 
 	/* tune readahead according to rsize */
-	cifs_sb->bdi.ra_pages = cifs_sb->rsize / PAGE_CACHE_SIZE;
+	cifs_sb->bdi.ra_pages = cifs_sb->rsize / PAGE_SIZE;
 
 remote_path_check:
 #ifdef CONFIG_CIFS_DFS_UPCALL
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 47c5c97e2dd3..c03d0744648b 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1833,7 +1833,7 @@ refind_writable:
 static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to)
 {
 	struct address_space *mapping = page->mapping;
-	loff_t offset = (loff_t)page->index << PAGE_CACHE_SHIFT;
+	loff_t offset = (loff_t)page->index << PAGE_SHIFT;
 	char *write_data;
 	int rc = -EFAULT;
 	int bytes_written = 0;
@@ -1849,7 +1849,7 @@ static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to)
 	write_data = kmap(page);
 	write_data += from;
 
-	if ((to > PAGE_CACHE_SIZE) || (from > to)) {
+	if ((to > PAGE_SIZE) || (from > to)) {
 		kunmap(page);
 		return -EIO;
 	}
@@ -1902,7 +1902,7 @@ wdata_alloc_and_fillpages(pgoff_t tofind, struct address_space *mapping,
 	 * find_get_pages_tag seems to return a max of 256 on each
 	 * iteration, so we must call it several times in order to
 	 * fill the array or the wsize is effectively limited to
-	 * 256 * PAGE_CACHE_SIZE.
+	 * 256 * PAGE_SIZE.
 	 */
 	*found_pages = 0;
 	pages = wdata->pages;
@@ -1991,7 +1991,7 @@ wdata_prepare_pages(struct cifs_writedata *wdata, unsigned int found_pages,
 
 	/* put any pages we aren't going to use */
 	for (i = nr_pages; i < found_pages; i++) {
-		page_cache_release(wdata->pages[i]);
+		put_page(wdata->pages[i]);
 		wdata->pages[i] = NULL;
 	}
 
@@ -2009,11 +2009,11 @@ wdata_send_pages(struct cifs_writedata *wdata, unsigned int nr_pages,
 	wdata->sync_mode = wbc->sync_mode;
 	wdata->nr_pages = nr_pages;
 	wdata->offset = page_offset(wdata->pages[0]);
-	wdata->pagesz = PAGE_CACHE_SIZE;
+	wdata->pagesz = PAGE_SIZE;
 	wdata->tailsz = min(i_size_read(mapping->host) -
 			page_offset(wdata->pages[nr_pages - 1]),
-			(loff_t)PAGE_CACHE_SIZE);
-	wdata->bytes = ((nr_pages - 1) * PAGE_CACHE_SIZE) + wdata->tailsz;
+			(loff_t)PAGE_SIZE);
+	wdata->bytes = ((nr_pages - 1) * PAGE_SIZE) + wdata->tailsz;
 
 	if (wdata->cfile != NULL)
 		cifsFileInfo_put(wdata->cfile);
@@ -2047,15 +2047,15 @@ static int cifs_writepages(struct address_space *mapping,
 	 * If wsize is smaller than the page cache size, default to writing
 	 * one page at a time via cifs_writepage
 	 */
-	if (cifs_sb->wsize < PAGE_CACHE_SIZE)
+	if (cifs_sb->wsize < PAGE_SIZE)
 		return generic_writepages(mapping, wbc);
 
 	if (wbc->range_cyclic) {
 		index = mapping->writeback_index; /* Start from prev offset */
 		end = -1;
 	} else {
-		index = wbc->range_start >> PAGE_CACHE_SHIFT;
-		end = wbc->range_end >> PAGE_CACHE_SHIFT;
+		index = wbc->range_start >> PAGE_SHIFT;
+		end = wbc->range_end >> PAGE_SHIFT;
 		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
 			range_whole = true;
 		scanned = true;
@@ -2071,7 +2071,7 @@ retry:
 		if (rc)
 			break;
 
-		tofind = min((wsize / PAGE_CACHE_SIZE) - 1, end - index) + 1;
+		tofind = min((wsize / PAGE_SIZE) - 1, end - index) + 1;
 
 		wdata = wdata_alloc_and_fillpages(tofind, mapping, end, &index,
 						  &found_pages);
@@ -2111,7 +2111,7 @@ retry:
 				else
 					SetPageError(wdata->pages[i]);
 				end_page_writeback(wdata->pages[i]);
-				page_cache_release(wdata->pages[i]);
+				put_page(wdata->pages[i]);
 			}
 			if (rc != -EAGAIN)
 				mapping_set_error(mapping, rc);
@@ -2154,7 +2154,7 @@ cifs_writepage_locked(struct page *page, struct writeback_control *wbc)
 
 	xid = get_xid();
 /* BB add check for wbc flags */
-	page_cache_get(page);
+	get_page(page);
 	if (!PageUptodate(page))
 		cifs_dbg(FYI, "ppw - page not up to date\n");
 
@@ -2170,7 +2170,7 @@ cifs_writepage_locked(struct page *page, struct writeback_control *wbc)
 	 */
 	set_page_writeback(page);
 retry_write:
-	rc = cifs_partialpagewrite(page, 0, PAGE_CACHE_SIZE);
+	rc = cifs_partialpagewrite(page, 0, PAGE_SIZE);
 	if (rc == -EAGAIN && wbc->sync_mode == WB_SYNC_ALL)
 		goto retry_write;
 	else if (rc == -EAGAIN)
@@ -2180,7 +2180,7 @@ retry_write:
 	else
 		SetPageUptodate(page);
 	end_page_writeback(page);
-	page_cache_release(page);
+	put_page(page);
 	free_xid(xid);
 	return rc;
 }
@@ -2214,12 +2214,12 @@ static int cifs_write_end(struct file *file, struct address_space *mapping,
 		if (copied == len)
 			SetPageUptodate(page);
 		ClearPageChecked(page);
-	} else if (!PageUptodate(page) && copied == PAGE_CACHE_SIZE)
+	} else if (!PageUptodate(page) && copied == PAGE_SIZE)
 		SetPageUptodate(page);
 
 	if (!PageUptodate(page)) {
 		char *page_data;
-		unsigned offset = pos & (PAGE_CACHE_SIZE - 1);
+		unsigned offset = pos & (PAGE_SIZE - 1);
 		unsigned int xid;
 
 		xid = get_xid();
@@ -2248,7 +2248,7 @@ static int cifs_write_end(struct file *file, struct address_space *mapping,
 	}
 
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 
 	return rc;
 }
@@ -2267,7 +2267,7 @@ int cifs_strict_fsync(struct file *file, loff_t start, loff_t end,
 	rc = filemap_write_and_wait_range(inode->i_mapping, start, end);
 	if (rc)
 		return rc;
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	xid = get_xid();
 
@@ -2292,7 +2292,7 @@ int cifs_strict_fsync(struct file *file, loff_t start, loff_t end,
 	}
 
 	free_xid(xid);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return rc;
 }
 
@@ -2309,7 +2309,7 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	rc = filemap_write_and_wait_range(inode->i_mapping, start, end);
 	if (rc)
 		return rc;
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	xid = get_xid();
 
@@ -2326,7 +2326,7 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	}
 
 	free_xid(xid);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return rc;
 }
 
@@ -2672,7 +2672,7 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from)
 	 * with a brlock that prevents writing.
 	 */
 	down_read(&cinode->lock_sem);
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	rc = generic_write_checks(iocb, from);
 	if (rc <= 0)
@@ -2685,7 +2685,7 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from)
 	else
 		rc = -EACCES;
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	if (rc > 0) {
 		ssize_t err = generic_write_sync(file, iocb->ki_pos - rc, rc);
@@ -3286,9 +3286,9 @@ cifs_readv_complete(struct work_struct *work)
 		    (rdata->result == -EAGAIN && got_bytes))
 			cifs_readpage_to_fscache(rdata->mapping->host, page);
 
-		got_bytes -= min_t(unsigned int, PAGE_CACHE_SIZE, got_bytes);
+		got_bytes -= min_t(unsigned int, PAGE_SIZE, got_bytes);
 
-		page_cache_release(page);
+		put_page(page);
 		rdata->pages[i] = NULL;
 	}
 	kref_put(&rdata->refcount, cifs_readdata_release);
@@ -3307,21 +3307,21 @@ cifs_readpages_read_into_pages(struct TCP_Server_Info *server,
 
 	/* determine the eof that the server (probably) has */
 	eof = CIFS_I(rdata->mapping->host)->server_eof;
-	eof_index = eof ? (eof - 1) >> PAGE_CACHE_SHIFT : 0;
+	eof_index = eof ? (eof - 1) >> PAGE_SHIFT : 0;
 	cifs_dbg(FYI, "eof=%llu eof_index=%lu\n", eof, eof_index);
 
 	rdata->got_bytes = 0;
-	rdata->tailsz = PAGE_CACHE_SIZE;
+	rdata->tailsz = PAGE_SIZE;
 	for (i = 0; i < nr_pages; i++) {
 		struct page *page = rdata->pages[i];
 
-		if (len >= PAGE_CACHE_SIZE) {
+		if (len >= PAGE_SIZE) {
 			/* enough data to fill the page */
 			iov.iov_base = kmap(page);
-			iov.iov_len = PAGE_CACHE_SIZE;
+			iov.iov_len = PAGE_SIZE;
 			cifs_dbg(FYI, "%u: idx=%lu iov_base=%p iov_len=%zu\n",
 				 i, page->index, iov.iov_base, iov.iov_len);
-			len -= PAGE_CACHE_SIZE;
+			len -= PAGE_SIZE;
 		} else if (len > 0) {
 			/* enough for partial page, fill and zero the rest */
 			iov.iov_base = kmap(page);
@@ -3329,7 +3329,7 @@ cifs_readpages_read_into_pages(struct TCP_Server_Info *server,
 			cifs_dbg(FYI, "%u: idx=%lu iov_base=%p iov_len=%zu\n",
 				 i, page->index, iov.iov_base, iov.iov_len);
 			memset(iov.iov_base + len,
-				'\0', PAGE_CACHE_SIZE - len);
+				'\0', PAGE_SIZE - len);
 			rdata->tailsz = len;
 			len = 0;
 		} else if (page->index > eof_index) {
@@ -3341,12 +3341,12 @@ cifs_readpages_read_into_pages(struct TCP_Server_Info *server,
 			 * to prevent the VFS from repeatedly attempting to
 			 * fill them until the writes are flushed.
 			 */
-			zero_user(page, 0, PAGE_CACHE_SIZE);
+			zero_user(page, 0, PAGE_SIZE);
 			lru_cache_add_file(page);
 			flush_dcache_page(page);
 			SetPageUptodate(page);
 			unlock_page(page);
-			page_cache_release(page);
+			put_page(page);
 			rdata->pages[i] = NULL;
 			rdata->nr_pages--;
 			continue;
@@ -3354,7 +3354,7 @@ cifs_readpages_read_into_pages(struct TCP_Server_Info *server,
 			/* no need to hold page hostage */
 			lru_cache_add_file(page);
 			unlock_page(page);
-			page_cache_release(page);
+			put_page(page);
 			rdata->pages[i] = NULL;
 			rdata->nr_pages--;
 			continue;
@@ -3380,7 +3380,7 @@ 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 = GFP_KERNEL & mapping_gfp_mask(mapping);
+	gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL);
 
 	INIT_LIST_HEAD(tmplist);
 
@@ -3391,19 +3391,19 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
 	 * should have access to this page, we're safe to simply set
 	 * PG_locked without checking it first.
 	 */
-	__set_page_locked(page);
+	__SetPageLocked(page);
 	rc = add_to_page_cache_locked(page, mapping,
 				      page->index, gfp);
 
 	/* give up if we can't stick it in the cache */
 	if (rc) {
-		__clear_page_locked(page);
+		__ClearPageLocked(page);
 		return rc;
 	}
 
 	/* move first page to the tmplist */
-	*offset = (loff_t)page->index << PAGE_CACHE_SHIFT;
-	*bytes = PAGE_CACHE_SIZE;
+	*offset = (loff_t)page->index << PAGE_SHIFT;
+	*bytes = PAGE_SIZE;
 	*nr_pages = 1;
 	list_move_tail(&page->lru, tmplist);
 
@@ -3415,16 +3415,16 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
 			break;
 
 		/* would this page push the read over the rsize? */
-		if (*bytes + PAGE_CACHE_SIZE > rsize)
+		if (*bytes + PAGE_SIZE > rsize)
 			break;
 
-		__set_page_locked(page);
+		__SetPageLocked(page);
 		if (add_to_page_cache_locked(page, mapping, page->index, gfp)) {
-			__clear_page_locked(page);
+			__ClearPageLocked(page);
 			break;
 		}
 		list_move_tail(&page->lru, tmplist);
-		(*bytes) += PAGE_CACHE_SIZE;
+		(*bytes) += PAGE_SIZE;
 		expected_index++;
 		(*nr_pages)++;
 	}
@@ -3493,7 +3493,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 		 * reach this point however since we set ra_pages to 0 when the
 		 * rsize is smaller than a cache page.
 		 */
-		if (unlikely(rsize < PAGE_CACHE_SIZE)) {
+		if (unlikely(rsize < PAGE_SIZE)) {
 			add_credits_and_wake_if(server, credits, 0);
 			return 0;
 		}
@@ -3512,7 +3512,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 				list_del(&page->lru);
 				lru_cache_add_file(page);
 				unlock_page(page);
-				page_cache_release(page);
+				put_page(page);
 			}
 			rc = -ENOMEM;
 			add_credits_and_wake_if(server, credits, 0);
@@ -3524,7 +3524,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 		rdata->offset = offset;
 		rdata->bytes = bytes;
 		rdata->pid = pid;
-		rdata->pagesz = PAGE_CACHE_SIZE;
+		rdata->pagesz = PAGE_SIZE;
 		rdata->read_into_pages = cifs_readpages_read_into_pages;
 		rdata->credits = credits;
 
@@ -3542,7 +3542,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 				page = rdata->pages[i];
 				lru_cache_add_file(page);
 				unlock_page(page);
-				page_cache_release(page);
+				put_page(page);
 			}
 			/* Fallback to the readpage in error/reconnect cases */
 			kref_put(&rdata->refcount, cifs_readdata_release);
@@ -3577,7 +3577,7 @@ static int cifs_readpage_worker(struct file *file, struct page *page,
 	read_data = kmap(page);
 	/* for reads over a certain size could initiate async read ahead */
 
-	rc = cifs_read(file, read_data, PAGE_CACHE_SIZE, poffset);
+	rc = cifs_read(file, read_data, PAGE_SIZE, poffset);
 
 	if (rc < 0)
 		goto io_error;
@@ -3587,8 +3587,8 @@ static int cifs_readpage_worker(struct file *file, struct page *page,
 	file_inode(file)->i_atime =
 		current_fs_time(file_inode(file)->i_sb);
 
-	if (PAGE_CACHE_SIZE > rc)
-		memset(read_data + rc, 0, PAGE_CACHE_SIZE - rc);
+	if (PAGE_SIZE > rc)
+		memset(read_data + rc, 0, PAGE_SIZE - rc);
 
 	flush_dcache_page(page);
 	SetPageUptodate(page);
@@ -3608,7 +3608,7 @@ read_complete:
 
 static int cifs_readpage(struct file *file, struct page *page)
 {
-	loff_t offset = (loff_t)page->index << PAGE_CACHE_SHIFT;
+	loff_t offset = (loff_t)page->index << PAGE_SHIFT;
 	int rc = -EACCES;
 	unsigned int xid;
 
@@ -3679,8 +3679,8 @@ static int cifs_write_begin(struct file *file, struct address_space *mapping,
 			struct page **pagep, void **fsdata)
 {
 	int oncethru = 0;
-	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
-	loff_t offset = pos & (PAGE_CACHE_SIZE - 1);
+	pgoff_t index = pos >> PAGE_SHIFT;
+	loff_t offset = pos & (PAGE_SIZE - 1);
 	loff_t page_start = pos & PAGE_MASK;
 	loff_t i_size;
 	struct page *page;
@@ -3703,7 +3703,7 @@ start:
 	 * the server. If the write is short, we'll end up doing a sync write
 	 * instead.
 	 */
-	if (len == PAGE_CACHE_SIZE)
+	if (len == PAGE_SIZE)
 		goto out;
 
 	/*
@@ -3718,7 +3718,7 @@ start:
 		    (offset == 0 && (pos + len) >= i_size)) {
 			zero_user_segments(page, 0, offset,
 					   offset + len,
-					   PAGE_CACHE_SIZE);
+					   PAGE_SIZE);
 			/*
 			 * PageChecked means that the parts of the page
 			 * to which we're not writing are considered up
@@ -3737,7 +3737,7 @@ start:
 		 * do a sync write instead since PG_uptodate isn't set.
 		 */
 		cifs_readpage_worker(file, page, &page_start);
-		page_cache_release(page);
+		put_page(page);
 		oncethru = 1;
 		goto start;
 	} else {
@@ -3764,7 +3764,7 @@ static void cifs_invalidate_page(struct page *page, unsigned int offset,
 {
 	struct cifsInodeInfo *cifsi = CIFS_I(page->mapping->host);
 
-	if (offset == 0 && length == PAGE_CACHE_SIZE)
+	if (offset == 0 && length == PAGE_SIZE)
 		cifs_fscache_invalidate_page(page, &cifsi->vfs_inode);
 }
 
@@ -3772,7 +3772,7 @@ static int cifs_launder_page(struct page *page)
 {
 	int rc = 0;
 	loff_t range_start = page_offset(page);
-	loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1);
+	loff_t range_end = range_start + (loff_t)(PAGE_SIZE - 1);
 	struct writeback_control wbc = {
 		.sync_mode = WB_SYNC_ALL,
 		.nr_to_write = 0,
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 6b66dd5d1540..5f9ad5c42180 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -59,7 +59,7 @@ static void cifs_set_ops(struct inode *inode)
 
 		/* check if server can support readpages */
 		if (cifs_sb_master_tcon(cifs_sb)->ses->server->maxBuf <
-				PAGE_CACHE_SIZE + MAX_CIFS_HDR_SIZE)
+				PAGE_SIZE + MAX_CIFS_HDR_SIZE)
 			inode->i_data.a_ops = &cifs_addr_ops_smallbuf;
 		else
 			inode->i_data.a_ops = &cifs_addr_ops;
@@ -814,8 +814,21 @@ cifs_get_inode_info(struct inode **inode, const char *full_path,
 			}
 		} else
 			fattr.cf_uniqueid = iunique(sb, ROOT_I);
-	} else
-		fattr.cf_uniqueid = CIFS_I(*inode)->uniqueid;
+	} else {
+		if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) &&
+		    validinum == false && server->ops->get_srv_inum) {
+			/*
+			 * Pass a NULL tcon to ensure we don't make a round
+			 * trip to the server. This only works for SMB2+.
+			 */
+			tmprc = server->ops->get_srv_inum(xid,
+				NULL, cifs_sb, full_path,
+				&fattr.cf_uniqueid, data);
+			if (tmprc)
+				fattr.cf_uniqueid = CIFS_I(*inode)->uniqueid;
+		} else
+			fattr.cf_uniqueid = CIFS_I(*inode)->uniqueid;
+	}
 
 	/* query for SFU type info if supported and needed */
 	if (fattr.cf_cifsattrs & ATTR_SYSTEM &&
@@ -856,6 +869,13 @@ cifs_get_inode_info(struct inode **inode, const char *full_path,
 	} else {
 		/* we already have inode, update it */
 
+		/* if uniqueid is different, return error */
+		if (unlikely(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM &&
+		    CIFS_I(*inode)->uniqueid != fattr.cf_uniqueid)) {
+			rc = -ESTALE;
+			goto cgii_exit;
+		}
+
 		/* if filetype is different, return error */
 		if (unlikely(((*inode)->i_mode & S_IFMT) !=
 		    (fattr.cf_mode & S_IFMT))) {
@@ -1831,11 +1851,11 @@ cifs_invalidate_mapping(struct inode *inode)
  * @word: long word containing the bit lock
  */
 static int
-cifs_wait_bit_killable(struct wait_bit_key *key)
+cifs_wait_bit_killable(struct wait_bit_key *key, int mode)
 {
-	if (fatal_signal_pending(current))
-		return -ERESTARTSYS;
 	freezable_schedule_unsafe();
+	if (signal_pending_state(mode, current))
+		return -ERESTARTSYS;
 	return 0;
 }
 
@@ -1999,8 +2019,8 @@ int cifs_getattr(struct vfsmount *mnt, struct dentry *dentry,
 
 static int cifs_truncate_page(struct address_space *mapping, loff_t from)
 {
-	pgoff_t index = from >> PAGE_CACHE_SHIFT;
-	unsigned offset = from & (PAGE_CACHE_SIZE - 1);
+	pgoff_t index = from >> PAGE_SHIFT;
+	unsigned offset = from & (PAGE_SIZE - 1);
 	struct page *page;
 	int rc = 0;
 
@@ -2008,9 +2028,9 @@ static int cifs_truncate_page(struct address_space *mapping, loff_t from)
 	if (!page)
 		return -ENOMEM;
 
-	zero_user_segment(page, offset, PAGE_CACHE_SIZE);
+	zero_user_segment(page, offset, PAGE_SIZE);
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 	return rc;
 }
 
diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
index 28a77bf1d559..7a3b84e300f8 100644
--- a/fs/cifs/ioctl.c
+++ b/fs/cifs/ioctl.c
@@ -34,68 +34,36 @@
 #include "cifs_ioctl.h"
 #include <linux/btrfs.h>
 
-static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file,
-			unsigned long srcfd, u64 off, u64 len, u64 destoff,
-			bool dup_extents)
+static int cifs_file_clone_range(unsigned int xid, struct file *src_file,
+			  struct file *dst_file)
 {
-	int rc;
-	struct cifsFileInfo *smb_file_target = dst_file->private_data;
+	struct inode *src_inode = file_inode(src_file);
 	struct inode *target_inode = file_inode(dst_file);
-	struct cifs_tcon *target_tcon;
-	struct fd src_file;
 	struct cifsFileInfo *smb_file_src;
-	struct inode *src_inode;
+	struct cifsFileInfo *smb_file_target;
 	struct cifs_tcon *src_tcon;
+	struct cifs_tcon *target_tcon;
+	int rc;
 
 	cifs_dbg(FYI, "ioctl clone range\n");
-	/* the destination must be opened for writing */
-	if (!(dst_file->f_mode & FMODE_WRITE)) {
-		cifs_dbg(FYI, "file target not open for write\n");
-		return -EINVAL;
-	}
-
-	/* check if target volume is readonly and take reference */
-	rc = mnt_want_write_file(dst_file);
-	if (rc) {
-		cifs_dbg(FYI, "mnt_want_write failed with rc %d\n", rc);
-		return rc;
-	}
 
-	src_file = fdget(srcfd);
-	if (!src_file.file) {
-		rc = -EBADF;
-		goto out_drop_write;
-	}
-
-	if (src_file.file->f_op->unlocked_ioctl != cifs_ioctl) {
-		rc = -EBADF;
-		cifs_dbg(VFS, "src file seems to be from a different filesystem type\n");
-		goto out_fput;
-	}
-
-	if ((!src_file.file->private_data) || (!dst_file->private_data)) {
+	if (!src_file->private_data || !dst_file->private_data) {
 		rc = -EBADF;
 		cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
-		goto out_fput;
+		goto out;
 	}
 
 	rc = -EXDEV;
 	smb_file_target = dst_file->private_data;
-	smb_file_src = src_file.file->private_data;
+	smb_file_src = src_file->private_data;
 	src_tcon = tlink_tcon(smb_file_src->tlink);
 	target_tcon = tlink_tcon(smb_file_target->tlink);
 
-	/* check if source and target are on same tree connection */
-	if (src_tcon != target_tcon) {
-		cifs_dbg(VFS, "file copy src and target on different volume\n");
-		goto out_fput;
+	if (src_tcon->ses != target_tcon->ses) {
+		cifs_dbg(VFS, "source and target of copy not on same server\n");
+		goto out;
 	}
 
-	src_inode = file_inode(src_file.file);
-	rc = -EINVAL;
-	if (S_ISDIR(src_inode->i_mode))
-		goto out_fput;
-
 	/*
 	 * Note: cifs case is easier than btrfs since server responsible for
 	 * checks for proper open modes and file type and if it wants
@@ -103,34 +71,66 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file,
 	 */
 	lock_two_nondirectories(target_inode, src_inode);
 
-	/* determine range to clone */
-	rc = -EINVAL;
-	if (off + len > src_inode->i_size || off + len < off)
-		goto out_unlock;
-	if (len == 0)
-		len = src_inode->i_size - off;
-
 	cifs_dbg(FYI, "about to flush pages\n");
 	/* should we flush first and last page first */
-	truncate_inode_pages_range(&target_inode->i_data, destoff,
-				   PAGE_CACHE_ALIGN(destoff + len)-1);
+	truncate_inode_pages(&target_inode->i_data, 0);
 
-	if (dup_extents && target_tcon->ses->server->ops->duplicate_extents)
-		rc = target_tcon->ses->server->ops->duplicate_extents(xid,
-			smb_file_src, smb_file_target, off, len, destoff);
-	else if (!dup_extents && target_tcon->ses->server->ops->clone_range)
+	if (target_tcon->ses->server->ops->clone_range)
 		rc = target_tcon->ses->server->ops->clone_range(xid,
-			smb_file_src, smb_file_target, off, len, destoff);
+			smb_file_src, smb_file_target, 0, src_inode->i_size, 0);
 	else
 		rc = -EOPNOTSUPP;
 
 	/* force revalidate of size and timestamps of target file now
 	   that target is updated on the server */
 	CIFS_I(target_inode)->time = 0;
-out_unlock:
 	/* although unlocking in the reverse order from locking is not
 	   strictly necessary here it is a little cleaner to be consistent */
 	unlock_two_nondirectories(src_inode, target_inode);
+out:
+	return rc;
+}
+
+static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file,
+			unsigned long srcfd)
+{
+	int rc;
+	struct fd src_file;
+	struct inode *src_inode;
+
+	cifs_dbg(FYI, "ioctl clone range\n");
+	/* the destination must be opened for writing */
+	if (!(dst_file->f_mode & FMODE_WRITE)) {
+		cifs_dbg(FYI, "file target not open for write\n");
+		return -EINVAL;
+	}
+
+	/* check if target volume is readonly and take reference */
+	rc = mnt_want_write_file(dst_file);
+	if (rc) {
+		cifs_dbg(FYI, "mnt_want_write failed with rc %d\n", rc);
+		return rc;
+	}
+
+	src_file = fdget(srcfd);
+	if (!src_file.file) {
+		rc = -EBADF;
+		goto out_drop_write;
+	}
+
+	if (src_file.file->f_op->unlocked_ioctl != cifs_ioctl) {
+		rc = -EBADF;
+		cifs_dbg(VFS, "src file seems to be from a different filesystem type\n");
+		goto out_fput;
+	}
+
+	src_inode = file_inode(src_file.file);
+	rc = -EINVAL;
+	if (S_ISDIR(src_inode->i_mode))
+		goto out_fput;
+
+	rc = cifs_file_clone_range(xid, src_file.file, dst_file);
+
 out_fput:
 	fdput(src_file);
 out_drop_write:
@@ -251,10 +251,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
 			}
 			break;
 		case CIFS_IOC_COPYCHUNK_FILE:
-			rc = cifs_ioctl_clone(xid, filep, arg, 0, 0, 0, false);
-			break;
-		case BTRFS_IOC_CLONE:
-			rc = cifs_ioctl_clone(xid, filep, arg, 0, 0, 0, true);
+			rc = cifs_ioctl_clone(xid, filep, arg);
 			break;
 		case CIFS_IOC_SET_INTEGRITY:
 			if (pSMBFile == NULL)
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index e3548f73bdea..062c2375549a 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -627,9 +627,9 @@ cifs_hl_exit:
 }
 
 const char *
-cifs_follow_link(struct dentry *direntry, void **cookie)
+cifs_get_link(struct dentry *direntry, struct inode *inode,
+	      struct delayed_call *done)
 {
-	struct inode *inode = d_inode(direntry);
 	int rc = -ENOMEM;
 	unsigned int xid;
 	char *full_path = NULL;
@@ -639,6 +639,9 @@ cifs_follow_link(struct dentry *direntry, void **cookie)
 	struct cifs_tcon *tcon;
 	struct TCP_Server_Info *server;
 
+	if (!direntry)
+		return ERR_PTR(-ECHILD);
+
 	xid = get_xid();
 
 	tlink = cifs_sb_tlink(cifs_sb);
@@ -678,7 +681,8 @@ cifs_follow_link(struct dentry *direntry, void **cookie)
 		kfree(target_path);
 		return ERR_PTR(rc);
 	}
-	return *cookie = target_path;
+	set_delayed_call(done, kfree_link, target_path);
+	return target_path;
 }
 
 int
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 8442b8b8e0be..813fe13c2ae1 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -310,7 +310,7 @@ check_smb_hdr(struct smb_hdr *smb)
 }
 
 int
-checkSMB(char *buf, unsigned int total_read)
+checkSMB(char *buf, unsigned int total_read, struct TCP_Server_Info *server)
 {
 	struct smb_hdr *smb = (struct smb_hdr *)buf;
 	__u32 rfclen = be32_to_cpu(smb->smb_buf_length);
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 0557c45e9c33..b30a4a6d98a0 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -847,6 +847,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx)
 		 * if buggy server returns . and .. late do we want to
 		 * check for that here?
 		 */
+		*tmp_buf = 0;
 		rc = cifs_filldir(current_entry, file, ctx,
 				  tmp_buf, max_len);
 		if (rc) {
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index 2ab297dae5a7..f9e766f464be 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -43,6 +43,7 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms,
 	struct smb2_file_all_info *smb2_data = NULL;
 	__u8 smb2_oplock[17];
 	struct cifs_fid *fid = oparms->fid;
+	struct network_resiliency_req nr_ioctl_req;
 
 	smb2_path = cifs_convert_path_to_utf16(oparms->path, oparms->cifs_sb);
 	if (smb2_path == NULL) {
@@ -67,6 +68,24 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms,
 	if (rc)
 		goto out;
 
+
+	 if (oparms->tcon->use_resilient) {
+		nr_ioctl_req.Timeout = 0; /* use server default (120 seconds) */
+		nr_ioctl_req.Reserved = 0;
+		rc = SMB2_ioctl(xid, oparms->tcon, fid->persistent_fid,
+			fid->volatile_fid, FSCTL_LMR_REQUEST_RESILIENCY, true,
+			(char *)&nr_ioctl_req, sizeof(nr_ioctl_req),
+			NULL, NULL /* no return info */);
+		if (rc == -EOPNOTSUPP) {
+			cifs_dbg(VFS,
+			     "resiliency not supported by server, disabling\n");
+			oparms->tcon->use_resilient = false;
+		} else if (rc)
+			cifs_dbg(FYI, "error %d setting resiliency\n", rc);
+
+		rc = 0;
+	}
+
 	if (buf) {
 		/* open response does not have IndexNumber field - get it */
 		rc = SMB2_get_srv_num(xid, oparms->tcon, fid->persistent_fid,
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 1c5907019045..389fb9f8c84e 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -38,7 +38,7 @@ check_smb2_hdr(struct smb2_hdr *hdr, __u64 mid)
 	 * Make sure that this really is an SMB, that it is a response,
 	 * and that the message ids match.
 	 */
-	if ((*(__le32 *)hdr->ProtocolId == SMB2_PROTO_NUMBER) &&
+	if ((hdr->ProtocolId == SMB2_PROTO_NUMBER) &&
 	    (mid == wire_mid)) {
 		if (hdr->Flags & SMB2_FLAGS_SERVER_TO_REDIR)
 			return 0;
@@ -50,9 +50,9 @@ check_smb2_hdr(struct smb2_hdr *hdr, __u64 mid)
 				cifs_dbg(VFS, "Received Request not response\n");
 		}
 	} else { /* bad signature or mid */
-		if (*(__le32 *)hdr->ProtocolId != SMB2_PROTO_NUMBER)
+		if (hdr->ProtocolId != SMB2_PROTO_NUMBER)
 			cifs_dbg(VFS, "Bad protocol string signature header %x\n",
-				 *(unsigned int *) hdr->ProtocolId);
+				 le32_to_cpu(hdr->ProtocolId));
 		if (mid != wire_mid)
 			cifs_dbg(VFS, "Mids do not match: %llu and %llu\n",
 				 mid, wire_mid);
@@ -93,11 +93,11 @@ static const __le16 smb2_rsp_struct_sizes[NUMBER_OF_SMB2_COMMANDS] = {
 };
 
 int
-smb2_check_message(char *buf, unsigned int length)
+smb2_check_message(char *buf, unsigned int length, struct TCP_Server_Info *srvr)
 {
 	struct smb2_hdr *hdr = (struct smb2_hdr *)buf;
 	struct smb2_pdu *pdu = (struct smb2_pdu *)hdr;
-	__u64 mid = le64_to_cpu(hdr->MessageId);
+	__u64 mid;
 	__u32 len = get_rfc1002_length(buf);
 	__u32 clc_len;  /* calculated length */
 	int command;
@@ -111,6 +111,30 @@ smb2_check_message(char *buf, unsigned int length)
 	 * ie Validate the wct via smb2_struct_sizes table above
 	 */
 
+	if (hdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) {
+		struct smb2_transform_hdr *thdr =
+			(struct smb2_transform_hdr *)buf;
+		struct cifs_ses *ses = NULL;
+		struct list_head *tmp;
+
+		/* decrypt frame now that it is completely read in */
+		spin_lock(&cifs_tcp_ses_lock);
+		list_for_each(tmp, &srvr->smb_ses_list) {
+			ses = list_entry(tmp, struct cifs_ses, smb_ses_list);
+			if (ses->Suid == thdr->SessionId)
+				break;
+
+			ses = NULL;
+		}
+		spin_unlock(&cifs_tcp_ses_lock);
+		if (ses == NULL) {
+			cifs_dbg(VFS, "no decryption - session id not found\n");
+			return 1;
+		}
+	}
+
+
+	mid = le64_to_cpu(hdr->MessageId);
 	if (length < sizeof(struct smb2_pdu)) {
 		if ((length >= sizeof(struct smb2_hdr)) && (hdr->Status != 0)) {
 			pdu->StructureSize2 = 0;
@@ -322,7 +346,7 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *hdr)
 
 	/* return pointer to beginning of data area, ie offset from SMB start */
 	if ((*off != 0) && (*len != 0))
-		return (char *)(&hdr->ProtocolId[0]) + *off;
+		return (char *)(&hdr->ProtocolId) + *off;
 	else
 		return NULL;
 }
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 18da19f4f811..3525ed756173 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -182,6 +182,11 @@ smb2_find_mid(struct TCP_Server_Info *server, char *buf)
 	struct smb2_hdr *hdr = (struct smb2_hdr *)buf;
 	__u64 wire_mid = le64_to_cpu(hdr->MessageId);
 
+	if (hdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) {
+		cifs_dbg(VFS, "encrypted frame parsing not supported yet");
+		return NULL;
+	}
+
 	spin_lock(&GlobalMid_Lock);
 	list_for_each_entry(mid, &server->pending_mid_q, qhead) {
 		if ((mid->mid == wire_mid) &&
@@ -810,7 +815,6 @@ smb2_set_file_size(const unsigned int xid, struct cifs_tcon *tcon,
 			    cfile->fid.volatile_fid, cfile->pid, &eof, false);
 }
 
-#ifdef CONFIG_CIFS_SMB311
 static int
 smb2_duplicate_extents(const unsigned int xid,
 			struct cifsFileInfo *srcfile,
@@ -854,8 +858,6 @@ smb2_duplicate_extents(const unsigned int xid,
 duplicate_extents_out:
 	return rc;
 }
-#endif /* CONFIG_CIFS_SMB311 */
-
 
 static int
 smb2_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
@@ -1695,7 +1697,7 @@ struct smb_version_operations smb30_operations = {
 	.get_lease_key = smb2_get_lease_key,
 	.set_lease_key = smb2_set_lease_key,
 	.new_lease_key = smb2_new_lease_key,
-	.generate_signingkey = generate_smb3signingkey,
+	.generate_signingkey = generate_smb30signingkey,
 	.calc_signature = smb3_calc_signature,
 	.set_integrity  = smb3_set_integrity,
 	.is_read_op = smb21_is_read_op,
@@ -1703,6 +1705,7 @@ struct smb_version_operations smb30_operations = {
 	.create_lease_buf = smb3_create_lease_buf,
 	.parse_lease_buf = smb3_parse_lease_buf,
 	.clone_range = smb2_clone_range,
+	.duplicate_extents = smb2_duplicate_extents,
 	.validate_negotiate = smb3_validate_negotiate,
 	.wp_retry_size = smb2_wp_retry_size,
 	.dir_needs_close = smb2_dir_needs_close,
@@ -1781,7 +1784,7 @@ struct smb_version_operations smb311_operations = {
 	.get_lease_key = smb2_get_lease_key,
 	.set_lease_key = smb2_set_lease_key,
 	.new_lease_key = smb2_new_lease_key,
-	.generate_signingkey = generate_smb3signingkey,
+	.generate_signingkey = generate_smb311signingkey,
 	.calc_signature = smb3_calc_signature,
 	.set_integrity  = smb3_set_integrity,
 	.is_read_op = smb21_is_read_op,
@@ -1840,7 +1843,7 @@ struct smb_version_values smb21_values = {
 struct smb_version_values smb30_values = {
 	.version_string = SMB30_VERSION_STRING,
 	.protocol_id = SMB30_PROT_ID,
-	.req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU,
+	.req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION,
 	.large_lock_type = 0,
 	.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
 	.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
@@ -1860,7 +1863,7 @@ struct smb_version_values smb30_values = {
 struct smb_version_values smb302_values = {
 	.version_string = SMB302_VERSION_STRING,
 	.protocol_id = SMB302_PROT_ID,
-	.req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU,
+	.req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION,
 	.large_lock_type = 0,
 	.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
 	.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
@@ -1881,7 +1884,7 @@ struct smb_version_values smb302_values = {
 struct smb_version_values smb311_values = {
 	.version_string = SMB311_VERSION_STRING,
 	.protocol_id = SMB311_PROT_ID,
-	.req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU,
+	.req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES,
 	.large_lock_type = 0,
 	.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
 	.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 61276929d139..42e1f440eb1e 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -97,10 +97,7 @@ smb2_hdr_assemble(struct smb2_hdr *hdr, __le16 smb2_cmd /* command */ ,
 	hdr->smb2_buf_length = cpu_to_be32(parmsize + sizeof(struct smb2_hdr)
 			- 4 /*  RFC 1001 length field itself not counted */);
 
-	hdr->ProtocolId[0] = 0xFE;
-	hdr->ProtocolId[1] = 'S';
-	hdr->ProtocolId[2] = 'M';
-	hdr->ProtocolId[3] = 'B';
+	hdr->ProtocolId = SMB2_PROTO_NUMBER;
 	hdr->StructureSize = cpu_to_le16(64);
 	hdr->Command = smb2_cmd;
 	hdr->CreditRequest = cpu_to_le16(2); /* BB make this dynamic */
@@ -1109,21 +1106,25 @@ parse_lease_state(struct TCP_Server_Info *server, struct smb2_create_rsp *rsp,
 {
 	char *data_offset;
 	struct create_context *cc;
-	unsigned int next = 0;
+	unsigned int next;
+	unsigned int remaining;
 	char *name;
 
 	data_offset = (char *)rsp + 4 + le32_to_cpu(rsp->CreateContextsOffset);
+	remaining = le32_to_cpu(rsp->CreateContextsLength);
 	cc = (struct create_context *)data_offset;
-	do {
-		cc = (struct create_context *)((char *)cc + next);
+	while (remaining >= sizeof(struct create_context)) {
 		name = le16_to_cpu(cc->NameOffset) + (char *)cc;
-		if (le16_to_cpu(cc->NameLength) != 4 ||
-		    strncmp(name, "RqLs", 4)) {
-			next = le32_to_cpu(cc->Next);
-			continue;
-		}
-		return server->ops->parse_lease_buf(cc, epoch);
-	} while (next != 0);
+		if (le16_to_cpu(cc->NameLength) == 4 &&
+		    strncmp(name, "RqLs", 4) == 0)
+			return server->ops->parse_lease_buf(cc, epoch);
+
+		next = le32_to_cpu(cc->Next);
+		if (!next)
+			break;
+		remaining -= next;
+		cc = (struct create_context *)((char *)cc + next);
+	}
 
 	return 0;
 }
@@ -1151,13 +1152,130 @@ add_lease_context(struct TCP_Server_Info *server, struct kvec *iov,
 	return 0;
 }
 
+static struct create_durable_v2 *
+create_durable_v2_buf(struct cifs_fid *pfid)
+{
+	struct create_durable_v2 *buf;
+
+	buf = kzalloc(sizeof(struct create_durable_v2), GFP_KERNEL);
+	if (!buf)
+		return NULL;
+
+	buf->ccontext.DataOffset = cpu_to_le16(offsetof
+					(struct create_durable_v2, dcontext));
+	buf->ccontext.DataLength = cpu_to_le32(sizeof(struct durable_context_v2));
+	buf->ccontext.NameOffset = cpu_to_le16(offsetof
+				(struct create_durable_v2, Name));
+	buf->ccontext.NameLength = cpu_to_le16(4);
+
+	buf->dcontext.Timeout = 0; /* Should this be configurable by workload */
+	buf->dcontext.Flags = cpu_to_le32(SMB2_DHANDLE_FLAG_PERSISTENT);
+	get_random_bytes(buf->dcontext.CreateGuid, 16);
+	memcpy(pfid->create_guid, buf->dcontext.CreateGuid, 16);
+
+	/* SMB2_CREATE_DURABLE_HANDLE_REQUEST is "DH2Q" */
+	buf->Name[0] = 'D';
+	buf->Name[1] = 'H';
+	buf->Name[2] = '2';
+	buf->Name[3] = 'Q';
+	return buf;
+}
+
+static struct create_durable_handle_reconnect_v2 *
+create_reconnect_durable_v2_buf(struct cifs_fid *fid)
+{
+	struct create_durable_handle_reconnect_v2 *buf;
+
+	buf = kzalloc(sizeof(struct create_durable_handle_reconnect_v2),
+			GFP_KERNEL);
+	if (!buf)
+		return NULL;
+
+	buf->ccontext.DataOffset =
+		cpu_to_le16(offsetof(struct create_durable_handle_reconnect_v2,
+				     dcontext));
+	buf->ccontext.DataLength =
+		cpu_to_le32(sizeof(struct durable_reconnect_context_v2));
+	buf->ccontext.NameOffset =
+		cpu_to_le16(offsetof(struct create_durable_handle_reconnect_v2,
+			    Name));
+	buf->ccontext.NameLength = cpu_to_le16(4);
+
+	buf->dcontext.Fid.PersistentFileId = fid->persistent_fid;
+	buf->dcontext.Fid.VolatileFileId = fid->volatile_fid;
+	buf->dcontext.Flags = cpu_to_le32(SMB2_DHANDLE_FLAG_PERSISTENT);
+	memcpy(buf->dcontext.CreateGuid, fid->create_guid, 16);
+
+	/* SMB2_CREATE_DURABLE_HANDLE_RECONNECT_V2 is "DH2C" */
+	buf->Name[0] = 'D';
+	buf->Name[1] = 'H';
+	buf->Name[2] = '2';
+	buf->Name[3] = 'C';
+	return buf;
+}
+
 static int
-add_durable_context(struct kvec *iov, unsigned int *num_iovec,
+add_durable_v2_context(struct kvec *iov, unsigned int *num_iovec,
 		    struct cifs_open_parms *oparms)
 {
 	struct smb2_create_req *req = iov[0].iov_base;
 	unsigned int num = *num_iovec;
 
+	iov[num].iov_base = create_durable_v2_buf(oparms->fid);
+	if (iov[num].iov_base == NULL)
+		return -ENOMEM;
+	iov[num].iov_len = sizeof(struct create_durable_v2);
+	if (!req->CreateContextsOffset)
+		req->CreateContextsOffset =
+			cpu_to_le32(sizeof(struct smb2_create_req) - 4 +
+								iov[1].iov_len);
+	le32_add_cpu(&req->CreateContextsLength, sizeof(struct create_durable_v2));
+	inc_rfc1001_len(&req->hdr, sizeof(struct create_durable_v2));
+	*num_iovec = num + 1;
+	return 0;
+}
+
+static int
+add_durable_reconnect_v2_context(struct kvec *iov, unsigned int *num_iovec,
+		    struct cifs_open_parms *oparms)
+{
+	struct smb2_create_req *req = iov[0].iov_base;
+	unsigned int num = *num_iovec;
+
+	/* indicate that we don't need to relock the file */
+	oparms->reconnect = false;
+
+	iov[num].iov_base = create_reconnect_durable_v2_buf(oparms->fid);
+	if (iov[num].iov_base == NULL)
+		return -ENOMEM;
+	iov[num].iov_len = sizeof(struct create_durable_handle_reconnect_v2);
+	if (!req->CreateContextsOffset)
+		req->CreateContextsOffset =
+			cpu_to_le32(sizeof(struct smb2_create_req) - 4 +
+								iov[1].iov_len);
+	le32_add_cpu(&req->CreateContextsLength,
+			sizeof(struct create_durable_handle_reconnect_v2));
+	inc_rfc1001_len(&req->hdr,
+			sizeof(struct create_durable_handle_reconnect_v2));
+	*num_iovec = num + 1;
+	return 0;
+}
+
+static int
+add_durable_context(struct kvec *iov, unsigned int *num_iovec,
+		    struct cifs_open_parms *oparms, bool use_persistent)
+{
+	struct smb2_create_req *req = iov[0].iov_base;
+	unsigned int num = *num_iovec;
+
+	if (use_persistent) {
+		if (oparms->reconnect)
+			return add_durable_reconnect_v2_context(iov, num_iovec,
+								oparms);
+		else
+			return add_durable_v2_context(iov, num_iovec, oparms);
+	}
+
 	if (oparms->reconnect) {
 		iov[num].iov_base = create_reconnect_durable_buf(oparms->fid);
 		/* indicate that we don't need to relock the file */
@@ -1275,7 +1393,9 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 			ccontext->Next =
 				cpu_to_le32(server->vals->create_lease_size);
 		}
-		rc = add_durable_context(iov, &num_iovecs, oparms);
+
+		rc = add_durable_context(iov, &num_iovecs, oparms,
+					tcon->use_persistent);
 		if (rc) {
 			cifs_small_buf_release(req);
 			kfree(copy_path);
@@ -1454,7 +1574,8 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 		goto ioctl_exit;
 	}
 
-	memcpy(*out_data, rsp->hdr.ProtocolId + le32_to_cpu(rsp->OutputOffset),
+	memcpy(*out_data,
+	       (char *)&rsp->hdr.ProtocolId + le32_to_cpu(rsp->OutputOffset),
 	       *plen);
 ioctl_exit:
 	free_rsp_buf(resp_buftype, rsp);
@@ -1974,7 +2095,7 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
 	}
 
 	if (*buf) {
-		memcpy(*buf, (char *)rsp->hdr.ProtocolId + rsp->DataOffset,
+		memcpy(*buf, (char *)&rsp->hdr.ProtocolId + rsp->DataOffset,
 		       *nbytes);
 		free_rsp_buf(resp_buftype, iov[0].iov_base);
 	} else if (resp_buftype != CIFS_NO_BUFFER) {
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index 451108284a2f..ff88d9feb01e 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -86,6 +86,7 @@
 #define MAX_SMB2_HDR_SIZE 0x78 /* 4 len + 64 hdr + (2*24 wct) + 2 bct + 2 pad */
 
 #define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe)
+#define SMB2_TRANSFORM_PROTO_NUM cpu_to_le32(0x424d53fd)
 
 /*
  * SMB2 Header Definition
@@ -102,7 +103,7 @@ struct smb2_hdr {
 	__be32 smb2_buf_length;	/* big endian on wire */
 				/* length is only two or three bytes - with
 				 one or two byte type preceding it that MBZ */
-	__u8   ProtocolId[4];	/* 0xFE 'S' 'M' 'B' */
+	__le32 ProtocolId;	/* 0xFE 'S' 'M' 'B' */
 	__le16 StructureSize;	/* 64 */
 	__le16 CreditCharge;	/* MBZ */
 	__le32 Status;		/* Error from server */
@@ -128,11 +129,10 @@ struct smb2_transform_hdr {
 				 one or two byte type preceding it that MBZ */
 	__u8   ProtocolId[4];	/* 0xFD 'S' 'M' 'B' */
 	__u8   Signature[16];
-	__u8   Nonce[11];
-	__u8   Reserved[5];
+	__u8   Nonce[16];
 	__le32 OriginalMessageSize;
 	__u16  Reserved1;
-	__le16 EncryptionAlgorithm;
+	__le16 Flags; /* EncryptionAlgorithm */
 	__u64  SessionId;
 } __packed;
 
@@ -590,6 +590,44 @@ struct create_durable {
 	} Data;
 } __packed;
 
+/* See MS-SMB2 2.2.13.2.11 */
+/* Flags */
+#define SMB2_DHANDLE_FLAG_PERSISTENT	0x00000002
+struct durable_context_v2 {
+	__le32 Timeout;
+	__le32 Flags;
+	__u64 Reserved;
+	__u8 CreateGuid[16];
+} __packed;
+
+struct create_durable_v2 {
+	struct create_context ccontext;
+	__u8   Name[8];
+	struct durable_context_v2 dcontext;
+} __packed;
+
+/* See MS-SMB2 2.2.13.2.12 */
+struct durable_reconnect_context_v2 {
+	struct {
+		__u64 PersistentFileId;
+		__u64 VolatileFileId;
+	} Fid;
+	__u8 CreateGuid[16];
+	__le32 Flags; /* see above DHANDLE_FLAG_PERSISTENT */
+} __packed;
+
+/* See MS-SMB2 2.2.14.2.12 */
+struct durable_reconnect_context_v2_rsp {
+	__le32 Timeout;
+	__le32 Flags; /* see above DHANDLE_FLAG_PERSISTENT */
+} __packed;
+
+struct create_durable_handle_reconnect_v2 {
+	struct create_context ccontext;
+	__u8   Name[8];
+	struct durable_reconnect_context_v2 dcontext;
+} __packed;
+
 #define COPY_CHUNK_RES_KEY_SIZE	24
 struct resume_key_req {
 	char ResumeKey[COPY_CHUNK_RES_KEY_SIZE];
@@ -643,6 +681,13 @@ struct fsctl_get_integrity_information_rsp {
 /* Integrity flags for above */
 #define FSCTL_INTEGRITY_FLAG_CHECKSUM_ENFORCEMENT_OFF	0x00000001
 
+/* See MS-SMB2 2.2.31.3 */
+struct network_resiliency_req {
+	__le32 Timeout;
+	__le32 Reserved;
+} __packed;
+/* There is no buffer for the response ie no struct network_resiliency_rsp */
+
 
 struct validate_negotiate_info_req {
 	__le32 Capabilities;
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 79dc650c18b2..4f07dc93608d 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -34,7 +34,8 @@ struct smb_rqst;
  *****************************************************************
  */
 extern int map_smb2_to_linux_error(char *buf, bool log_err);
-extern int smb2_check_message(char *buf, unsigned int length);
+extern int smb2_check_message(char *buf, unsigned int length,
+			      struct TCP_Server_Info *server);
 extern unsigned int smb2_calc_size(void *buf);
 extern char *smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *hdr);
 extern __le16 *cifs_convert_path_to_utf16(const char *from,
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index d4c5b6f109a7..8732a43b1008 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -222,8 +222,8 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 	return rc;
 }
 
-int
-generate_smb3signingkey(struct cifs_ses *ses)
+static int generate_key(struct cifs_ses *ses, struct kvec label,
+			struct kvec context, __u8 *key, unsigned int key_size)
 {
 	unsigned char zero = 0x0;
 	__u8 i[4] = {0, 0, 0, 1};
@@ -233,7 +233,7 @@ generate_smb3signingkey(struct cifs_ses *ses)
 	unsigned char *hashptr = prfhash;
 
 	memset(prfhash, 0x0, SMB2_HMACSHA256_SIZE);
-	memset(ses->smb3signingkey, 0x0, SMB3_SIGNKEY_SIZE);
+	memset(key, 0x0, key_size);
 
 	rc = smb3_crypto_shash_allocate(ses->server);
 	if (rc) {
@@ -262,7 +262,7 @@ generate_smb3signingkey(struct cifs_ses *ses)
 	}
 
 	rc = crypto_shash_update(&ses->server->secmech.sdeschmacsha256->shash,
-				"SMB2AESCMAC", 12);
+				label.iov_base, label.iov_len);
 	if (rc) {
 		cifs_dbg(VFS, "%s: Could not update with label\n", __func__);
 		goto smb3signkey_ret;
@@ -276,7 +276,7 @@ generate_smb3signingkey(struct cifs_ses *ses)
 	}
 
 	rc = crypto_shash_update(&ses->server->secmech.sdeschmacsha256->shash,
-				"SmbSign", 8);
+				context.iov_base, context.iov_len);
 	if (rc) {
 		cifs_dbg(VFS, "%s: Could not update with context\n", __func__);
 		goto smb3signkey_ret;
@@ -296,12 +296,102 @@ generate_smb3signingkey(struct cifs_ses *ses)
 		goto smb3signkey_ret;
 	}
 
-	memcpy(ses->smb3signingkey, hashptr, SMB3_SIGNKEY_SIZE);
+	memcpy(key, hashptr, key_size);
 
 smb3signkey_ret:
 	return rc;
 }
 
+struct derivation {
+	struct kvec label;
+	struct kvec context;
+};
+
+struct derivation_triplet {
+	struct derivation signing;
+	struct derivation encryption;
+	struct derivation decryption;
+};
+
+static int
+generate_smb3signingkey(struct cifs_ses *ses,
+			const struct derivation_triplet *ptriplet)
+{
+	int rc;
+
+	rc = generate_key(ses, ptriplet->signing.label,
+			  ptriplet->signing.context, ses->smb3signingkey,
+			  SMB3_SIGN_KEY_SIZE);
+	if (rc)
+		return rc;
+
+	rc = generate_key(ses, ptriplet->encryption.label,
+			  ptriplet->encryption.context, ses->smb3encryptionkey,
+			  SMB3_SIGN_KEY_SIZE);
+	if (rc)
+		return rc;
+
+	return generate_key(ses, ptriplet->decryption.label,
+			    ptriplet->decryption.context,
+			    ses->smb3decryptionkey, SMB3_SIGN_KEY_SIZE);
+}
+
+int
+generate_smb30signingkey(struct cifs_ses *ses)
+
+{
+	struct derivation_triplet triplet;
+	struct derivation *d;
+
+	d = &triplet.signing;
+	d->label.iov_base = "SMB2AESCMAC";
+	d->label.iov_len = 12;
+	d->context.iov_base = "SmbSign";
+	d->context.iov_len = 8;
+
+	d = &triplet.encryption;
+	d->label.iov_base = "SMB2AESCCM";
+	d->label.iov_len = 11;
+	d->context.iov_base = "ServerIn ";
+	d->context.iov_len = 10;
+
+	d = &triplet.decryption;
+	d->label.iov_base = "SMB2AESCCM";
+	d->label.iov_len = 11;
+	d->context.iov_base = "ServerOut";
+	d->context.iov_len = 10;
+
+	return generate_smb3signingkey(ses, &triplet);
+}
+
+int
+generate_smb311signingkey(struct cifs_ses *ses)
+
+{
+	struct derivation_triplet triplet;
+	struct derivation *d;
+
+	d = &triplet.signing;
+	d->label.iov_base = "SMB2AESCMAC";
+	d->label.iov_len = 12;
+	d->context.iov_base = "SmbSign";
+	d->context.iov_len = 8;
+
+	d = &triplet.encryption;
+	d->label.iov_base = "SMB2AESCCM";
+	d->label.iov_len = 11;
+	d->context.iov_base = "ServerIn ";
+	d->context.iov_len = 10;
+
+	d = &triplet.decryption;
+	d->label.iov_base = "SMB2AESCCM";
+	d->label.iov_len = 11;
+	d->context.iov_base = "ServerOut";
+	d->context.iov_len = 10;
+
+	return generate_smb3signingkey(ses, &triplet);
+}
+
 int
 smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 {
diff --git a/fs/cifs/smbencrypt.c b/fs/cifs/smbencrypt.c
index a4232ec4f2ba..699b7868108f 100644
--- a/fs/cifs/smbencrypt.c
+++ b/fs/cifs/smbencrypt.c
@@ -23,6 +23,7 @@
    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */
 
+#include <crypto/skcipher.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/fs.h>
@@ -70,31 +71,42 @@ smbhash(unsigned char *out, const unsigned char *in, unsigned char *key)
 {
 	int rc;
 	unsigned char key2[8];
-	struct crypto_blkcipher *tfm_des;
+	struct crypto_skcipher *tfm_des;
 	struct scatterlist sgin, sgout;
-	struct blkcipher_desc desc;
+	struct skcipher_request *req;
 
 	str_to_key(key, key2);
 
-	tfm_des = crypto_alloc_blkcipher("ecb(des)", 0, CRYPTO_ALG_ASYNC);
+	tfm_des = crypto_alloc_skcipher("ecb(des)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(tfm_des)) {
 		rc = PTR_ERR(tfm_des);
 		cifs_dbg(VFS, "could not allocate des crypto API\n");
 		goto smbhash_err;
 	}
 
-	desc.tfm = tfm_des;
+	req = skcipher_request_alloc(tfm_des, GFP_KERNEL);
+	if (!req) {
+		rc = -ENOMEM;
+		cifs_dbg(VFS, "could not allocate des crypto API\n");
+		goto smbhash_free_skcipher;
+	}
 
-	crypto_blkcipher_setkey(tfm_des, key2, 8);
+	crypto_skcipher_setkey(tfm_des, key2, 8);
 
 	sg_init_one(&sgin, in, 8);
 	sg_init_one(&sgout, out, 8);
 
-	rc = crypto_blkcipher_encrypt(&desc, &sgout, &sgin, 8);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, &sgin, &sgout, 8, NULL);
+
+	rc = crypto_skcipher_encrypt(req);
 	if (rc)
 		cifs_dbg(VFS, "could not encrypt crypt key rc: %d\n", rc);
 
-	crypto_free_blkcipher(tfm_des);
+	skcipher_request_free(req);
+
+smbhash_free_skcipher:
+	crypto_free_skcipher(tfm_des);
 smbhash_err:
 	return rc;
 }
diff --git a/fs/cifs/smbfsctl.h b/fs/cifs/smbfsctl.h
index a639d0dab453..f996daeea271 100644
--- a/fs/cifs/smbfsctl.h
+++ b/fs/cifs/smbfsctl.h
@@ -90,7 +90,7 @@
 #define FSCTL_SRV_ENUMERATE_SNAPSHOTS 0x00144064
 /* Retrieve an opaque file reference for server-side data movement ie copy */
 #define FSCTL_SRV_REQUEST_RESUME_KEY 0x00140078
-#define FSCTL_LMR_REQUEST_RESILIENCY 0x001401D4 /* BB add struct */
+#define FSCTL_LMR_REQUEST_RESILIENCY 0x001401D4
 #define FSCTL_LMR_GET_LINK_TRACK_INF 0x001400E8 /* BB add struct */
 #define FSCTL_LMR_SET_LINK_TRACK_INF 0x001400EC /* BB add struct */
 #define FSCTL_VALIDATE_NEGOTIATE_INFO 0x00140204
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 2a24c524fb9a..87abe8ed074c 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -576,14 +576,16 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst,
 	cifs_in_send_dec(server);
 	cifs_save_when_sent(mid);
 
-	if (rc < 0)
+	if (rc < 0) {
 		server->sequence_number -= 2;
+		cifs_delete_mid(mid);
+	}
+
 	mutex_unlock(&server->srv_mutex);
 
 	if (rc == 0)
 		return 0;
 
-	cifs_delete_mid(mid);
 	add_credits_and_wake_if(server, credits, optype);
 	return rc;
 }
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index ff9e1f8b16a4..f5dc2f0df4ad 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -190,8 +190,8 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name,
 #endif /* CONFIG_CIFS_ACL */
 	} else {
 		int temp;
-		temp = strncmp(ea_name, POSIX_ACL_XATTR_ACCESS,
-			strlen(POSIX_ACL_XATTR_ACCESS));
+		temp = strncmp(ea_name, XATTR_NAME_POSIX_ACL_ACCESS,
+			strlen(XATTR_NAME_POSIX_ACL_ACCESS));
 		if (temp == 0) {
 #ifdef CONFIG_CIFS_POSIX
 			if (sb->s_flags & MS_POSIXACL)
@@ -203,8 +203,8 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name,
 #else
 			cifs_dbg(FYI, "set POSIX ACL not supported\n");
 #endif
-		} else if (strncmp(ea_name, POSIX_ACL_XATTR_DEFAULT,
-				   strlen(POSIX_ACL_XATTR_DEFAULT)) == 0) {
+		} else if (strncmp(ea_name, XATTR_NAME_POSIX_ACL_DEFAULT,
+				   strlen(XATTR_NAME_POSIX_ACL_DEFAULT)) == 0) {
 #ifdef CONFIG_CIFS_POSIX
 			if (sb->s_flags & MS_POSIXACL)
 				rc = CIFSSMBSetPosixACL(xid, pTcon, full_path,
@@ -292,8 +292,8 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name,
 			rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon,
 				full_path, ea_name, ea_value, buf_size,
 				cifs_sb->local_nls, cifs_remap(cifs_sb));
-	} else if (strncmp(ea_name, POSIX_ACL_XATTR_ACCESS,
-			  strlen(POSIX_ACL_XATTR_ACCESS)) == 0) {
+	} else if (strncmp(ea_name, XATTR_NAME_POSIX_ACL_ACCESS,
+			  strlen(XATTR_NAME_POSIX_ACL_ACCESS)) == 0) {
 #ifdef CONFIG_CIFS_POSIX
 		if (sb->s_flags & MS_POSIXACL)
 			rc = CIFSSMBGetPosixACL(xid, pTcon, full_path,
@@ -303,8 +303,8 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name,
 #else
 		cifs_dbg(FYI, "Query POSIX ACL not supported yet\n");
 #endif /* CONFIG_CIFS_POSIX */
-	} else if (strncmp(ea_name, POSIX_ACL_XATTR_DEFAULT,
-			  strlen(POSIX_ACL_XATTR_DEFAULT)) == 0) {
+	} else if (strncmp(ea_name, XATTR_NAME_POSIX_ACL_DEFAULT,
+			  strlen(XATTR_NAME_POSIX_ACL_DEFAULT)) == 0) {
 #ifdef CONFIG_CIFS_POSIX
 		if (sb->s_flags & MS_POSIXACL)
 			rc = CIFSSMBGetPosixACL(xid, pTcon, full_path,
diff --git a/fs/coda/cnode.c b/fs/coda/cnode.c
index 7740b1c871c1..1bfb7ba4e85e 100644
--- a/fs/coda/cnode.c
+++ b/fs/coda/cnode.c
@@ -8,6 +8,7 @@
 
 #include <linux/coda.h>
 #include <linux/coda_psdev.h>
+#include <linux/pagemap.h>
 #include "coda_linux.h"
 
 static inline int coda_fideq(struct CodaFid *fid1, struct CodaFid *fid2)
@@ -17,8 +18,7 @@ static inline int coda_fideq(struct CodaFid *fid1, struct CodaFid *fid2)
 
 static const struct inode_operations coda_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 	.setattr	= coda_setattr,
 };
 
@@ -35,6 +35,7 @@ static void coda_fill_inode(struct inode *inode, struct coda_vattr *attr)
                 inode->i_fop = &coda_dir_operations;
         } else if (S_ISLNK(inode->i_mode)) {
 		inode->i_op = &coda_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_data.a_ops = &coda_symlink_aops;
 		inode->i_mapping = &inode->i_data;
 	} else
diff --git a/fs/coda/coda_linux.h b/fs/coda/coda_linux.h
index f829fe963f5b..5104d84c4f64 100644
--- a/fs/coda/coda_linux.h
+++ b/fs/coda/coda_linux.h
@@ -72,8 +72,7 @@ void coda_sysctl_clean(void);
 } while (0)
 
 
-#define CODA_FREE(ptr,size) \
-    do { if (size < PAGE_SIZE) kfree((ptr)); else vfree((ptr)); } while (0)
+#define CODA_FREE(ptr, size) kvfree((ptr))
 
 /* inode to cnode access functions */
 
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index fda9f4311212..42e731b8c80a 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -427,13 +427,13 @@ static int coda_readdir(struct file *coda_file, struct dir_context *ctx)
 	if (host_file->f_op->iterate) {
 		struct inode *host_inode = file_inode(host_file);
 
-		mutex_lock(&host_inode->i_mutex);
+		inode_lock(host_inode);
 		ret = -ENOENT;
 		if (!IS_DEADDIR(host_inode)) {
 			ret = host_file->f_op->iterate(host_file, ctx);
 			file_accessed(host_file);
 		}
-		mutex_unlock(&host_inode->i_mutex);
+		inode_unlock(host_inode);
 		return ret;
 	}
 	/* Venus: we must read Venus dirents from a file */
diff --git a/fs/coda/file.c b/fs/coda/file.c
index 1da3805f3ddc..f47c7483863b 100644
--- a/fs/coda/file.c
+++ b/fs/coda/file.c
@@ -71,12 +71,12 @@ coda_file_write_iter(struct kiocb *iocb, struct iov_iter *to)
 
 	host_file = cfi->cfi_container;
 	file_start_write(host_file);
-	mutex_lock(&coda_inode->i_mutex);
+	inode_lock(coda_inode);
 	ret = vfs_iter_write(cfi->cfi_container, to, &iocb->ki_pos);
 	coda_inode->i_size = file_inode(host_file)->i_size;
 	coda_inode->i_blocks = (coda_inode->i_size + 511) >> 9;
 	coda_inode->i_mtime = coda_inode->i_ctime = CURRENT_TIME_SEC;
-	mutex_unlock(&coda_inode->i_mutex);
+	inode_unlock(coda_inode);
 	file_end_write(host_file);
 	return ret;
 }
@@ -203,7 +203,7 @@ int coda_fsync(struct file *coda_file, loff_t start, loff_t end, int datasync)
 	err = filemap_write_and_wait_range(coda_inode->i_mapping, start, end);
 	if (err)
 		return err;
-	mutex_lock(&coda_inode->i_mutex);
+	inode_lock(coda_inode);
 
 	cfi = CODA_FTOC(coda_file);
 	BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
@@ -212,7 +212,7 @@ int coda_fsync(struct file *coda_file, loff_t start, loff_t end, int datasync)
 	err = vfs_fsync(host_file, datasync);
 	if (!err && !datasync)
 		err = venus_fsync(coda_inode->i_sb, coda_i2f(coda_inode));
-	mutex_unlock(&coda_inode->i_mutex);
+	inode_unlock(coda_inode);
 
 	return err;
 }
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index cac1390b87a3..57e81cbba0fa 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -74,9 +74,9 @@ static void init_once(void *foo)
 int __init coda_init_inodecache(void)
 {
 	coda_inode_cachep = kmem_cache_create("coda_inode_cache",
-				sizeof(struct coda_inode_info),
-				0, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD,
-				init_once);
+				sizeof(struct coda_inode_info), 0,
+				SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|
+				SLAB_ACCOUNT, init_once);
 	if (coda_inode_cachep == NULL)
 		return -ENOMEM;
 	return 0;
diff --git a/fs/coda/symlink.c b/fs/coda/symlink.c
index ab94ef63caef..03736e20d720 100644
--- a/fs/coda/symlink.c
+++ b/fs/coda/symlink.c
@@ -26,7 +26,7 @@ static int coda_symlink_filler(struct file *file, struct page *page)
 	int error;
 	struct coda_inode_info *cii;
 	unsigned int len = PAGE_SIZE;
-	char *p = kmap(page);
+	char *p = page_address(page);
 
 	cii = ITOC(inode);
 
@@ -34,13 +34,11 @@ static int coda_symlink_filler(struct file *file, struct page *page)
 	if (error)
 		goto fail;
 	SetPageUptodate(page);
-	kunmap(page);
 	unlock_page(page);
 	return 0;
 
 fail:
 	SetPageError(page);
-	kunmap(page);
 	unlock_page(page);
 	return error;
 }
diff --git a/fs/compat.c b/fs/compat.c
index 6fd272d455e4..a71936a3f4cb 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -792,7 +792,7 @@ COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name,
 		       const void __user *, data)
 {
 	char *kernel_type;
-	unsigned long data_page;
+	void *options;
 	char *kernel_dev;
 	int retval;
 
@@ -806,26 +806,25 @@ COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name,
 	if (IS_ERR(kernel_dev))
 		goto out1;
 
-	retval = copy_mount_options(data, &data_page);
-	if (retval < 0)
+	options = copy_mount_options(data);
+	retval = PTR_ERR(options);
+	if (IS_ERR(options))
 		goto out2;
 
-	retval = -EINVAL;
-
-	if (kernel_type && data_page) {
+	if (kernel_type && options) {
 		if (!strcmp(kernel_type, NCPFS_NAME)) {
-			do_ncp_super_data_conv((void *)data_page);
+			do_ncp_super_data_conv(options);
 		} else if (!strcmp(kernel_type, NFS4_NAME)) {
-			if (do_nfs4_super_data_conv((void *) data_page))
+			retval = -EINVAL;
+			if (do_nfs4_super_data_conv(options))
 				goto out3;
 		}
 	}
 
-	retval = do_mount(kernel_dev, dir_name, kernel_type,
-			flags, (void*)data_page);
+	retval = do_mount(kernel_dev, dir_name, kernel_type, flags, options);
 
  out3:
-	free_page(data_page);
+	kfree(options);
  out2:
 	kfree(kernel_dev);
  out1:
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 48851f6ea6ec..bd01b92aad98 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -58,6 +58,8 @@
 #include <linux/atalk.h>
 #include <linux/gfp.h>
 
+#include "internal.h"
+
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_sock.h>
 #include <net/bluetooth/rfcomm.h>
@@ -115,19 +117,38 @@
 #include <asm/fbio.h>
 #endif
 
-static int w_long(unsigned int fd, unsigned int cmd,
-		compat_ulong_t __user *argp)
+#define convert_in_user(srcptr, dstptr)			\
+({							\
+	typeof(*srcptr) val;				\
+							\
+	get_user(val, srcptr) || put_user(val, dstptr);	\
+})
+
+static int do_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
-	mm_segment_t old_fs = get_fs();
 	int err;
-	unsigned long val;
 
-	set_fs (KERNEL_DS);
-	err = sys_ioctl(fd, cmd, (unsigned long)&val);
-	set_fs (old_fs);
-	if (!err && put_user(val, argp))
+	err = security_file_ioctl(file, cmd, arg);
+	if (err)
+		return err;
+
+	return vfs_ioctl(file, cmd, arg);
+}
+
+static int w_long(struct file *file,
+		unsigned int cmd, compat_ulong_t __user *argp)
+{
+	int err;
+	unsigned long __user *valp = compat_alloc_user_space(sizeof(*valp));
+
+	if (valp == NULL)
 		return -EFAULT;
-	return err;
+	err = do_ioctl(file, cmd, (unsigned long)valp);
+	if (err)
+		return err;
+	if (convert_in_user(valp, argp))
+		return -EFAULT;
+	return 0;
 }
 
 struct compat_video_event {
@@ -139,23 +160,23 @@ struct compat_video_event {
 	} u;
 };
 
-static int do_video_get_event(unsigned int fd, unsigned int cmd,
-		struct compat_video_event __user *up)
+static int do_video_get_event(struct file *file,
+		unsigned int cmd, struct compat_video_event __user *up)
 {
-	struct video_event kevent;
-	mm_segment_t old_fs = get_fs();
+	struct video_event __user *kevent =
+		compat_alloc_user_space(sizeof(*kevent));
 	int err;
 
-	set_fs(KERNEL_DS);
-	err = sys_ioctl(fd, cmd, (unsigned long) &kevent);
-	set_fs(old_fs);
+	if (kevent == NULL)
+		return -EFAULT;
 
+	err = do_ioctl(file, cmd, (unsigned long)kevent);
 	if (!err) {
-		err  = put_user(kevent.type, &up->type);
-		err |= put_user(kevent.timestamp, &up->timestamp);
-		err |= put_user(kevent.u.size.w, &up->u.size.w);
-		err |= put_user(kevent.u.size.h, &up->u.size.h);
-		err |= put_user(kevent.u.size.aspect_ratio,
+		err  = convert_in_user(&kevent->type, &up->type);
+		err |= convert_in_user(&kevent->timestamp, &up->timestamp);
+		err |= convert_in_user(&kevent->u.size.w, &up->u.size.w);
+		err |= convert_in_user(&kevent->u.size.h, &up->u.size.h);
+		err |= convert_in_user(&kevent->u.size.aspect_ratio,
 				&up->u.size.aspect_ratio);
 		if (err)
 			err = -EFAULT;
@@ -169,8 +190,8 @@ struct compat_video_still_picture {
         int32_t size;
 };
 
-static int do_video_stillpicture(unsigned int fd, unsigned int cmd,
-	struct compat_video_still_picture __user *up)
+static int do_video_stillpicture(struct file *file,
+		unsigned int cmd, struct compat_video_still_picture __user *up)
 {
 	struct video_still_picture __user *up_native;
 	compat_uptr_t fp;
@@ -190,7 +211,7 @@ static int do_video_stillpicture(unsigned int fd, unsigned int cmd,
 	if (err)
 		return -EFAULT;
 
-	err = sys_ioctl(fd, cmd, (unsigned long) up_native);
+	err = do_ioctl(file, cmd, (unsigned long) up_native);
 
 	return err;
 }
@@ -200,8 +221,8 @@ struct compat_video_spu_palette {
 	compat_uptr_t palette;
 };
 
-static int do_video_set_spu_palette(unsigned int fd, unsigned int cmd,
-		struct compat_video_spu_palette __user *up)
+static int do_video_set_spu_palette(struct file *file,
+		unsigned int cmd, struct compat_video_spu_palette __user *up)
 {
 	struct video_spu_palette __user *up_native;
 	compat_uptr_t palp;
@@ -218,7 +239,7 @@ static int do_video_set_spu_palette(unsigned int fd, unsigned int cmd,
 	if (err)
 		return -EFAULT;
 
-	err = sys_ioctl(fd, cmd, (unsigned long) up_native);
+	err = do_ioctl(file, cmd, (unsigned long) up_native);
 
 	return err;
 }
@@ -276,7 +297,7 @@ static int sg_build_iovec(sg_io_hdr_t __user *sgio, void __user *dxferp, u16 iov
 	return 0;
 }
 
-static int sg_ioctl_trans(unsigned int fd, unsigned int cmd,
+static int sg_ioctl_trans(struct file *file, unsigned int cmd,
 			sg_io_hdr32_t __user *sgio32)
 {
 	sg_io_hdr_t __user *sgio;
@@ -289,7 +310,7 @@ static int sg_ioctl_trans(unsigned int fd, unsigned int cmd,
 	if (get_user(interface_id, &sgio32->interface_id))
 		return -EFAULT;
 	if (interface_id != 'S')
-		return sys_ioctl(fd, cmd, (unsigned long)sgio32);
+		return do_ioctl(file, cmd, (unsigned long)sgio32);
 
 	if (get_user(iovec_count, &sgio32->iovec_count))
 		return -EFAULT;
@@ -349,7 +370,7 @@ static int sg_ioctl_trans(unsigned int fd, unsigned int cmd,
 	if (put_user(compat_ptr(data), &sgio->usr_ptr))
 		return -EFAULT;
 
-	err = sys_ioctl(fd, cmd, (unsigned long) sgio);
+	err = do_ioctl(file, cmd, (unsigned long) sgio);
 
 	if (err >= 0) {
 		void __user *datap;
@@ -380,13 +401,13 @@ struct compat_sg_req_info { /* used by SG_GET_REQUEST_TABLE ioctl() */
 	int unused;
 };
 
-static int sg_grt_trans(unsigned int fd, unsigned int cmd, struct
-			compat_sg_req_info __user *o)
+static int sg_grt_trans(struct file *file,
+		unsigned int cmd, struct compat_sg_req_info __user *o)
 {
 	int err, i;
 	sg_req_info_t __user *r;
 	r = compat_alloc_user_space(sizeof(sg_req_info_t)*SG_MAX_QUEUE);
-	err = sys_ioctl(fd,cmd,(unsigned long)r);
+	err = do_ioctl(file, cmd, (unsigned long)r);
 	if (err < 0)
 		return err;
 	for (i = 0; i < SG_MAX_QUEUE; i++) {
@@ -412,8 +433,8 @@ struct sock_fprog32 {
 #define PPPIOCSPASS32	_IOW('t', 71, struct sock_fprog32)
 #define PPPIOCSACTIVE32	_IOW('t', 70, struct sock_fprog32)
 
-static int ppp_sock_fprog_ioctl_trans(unsigned int fd, unsigned int cmd,
-			struct sock_fprog32 __user *u_fprog32)
+static int ppp_sock_fprog_ioctl_trans(struct file *file,
+		unsigned int cmd, struct sock_fprog32 __user *u_fprog32)
 {
 	struct sock_fprog __user *u_fprog64 = compat_alloc_user_space(sizeof(struct sock_fprog));
 	void __user *fptr64;
@@ -435,7 +456,7 @@ static int ppp_sock_fprog_ioctl_trans(unsigned int fd, unsigned int cmd,
 	else
 		cmd = PPPIOCSACTIVE;
 
-	return sys_ioctl(fd, cmd, (unsigned long) u_fprog64);
+	return do_ioctl(file, cmd, (unsigned long) u_fprog64);
 }
 
 struct ppp_option_data32 {
@@ -451,7 +472,7 @@ struct ppp_idle32 {
 };
 #define PPPIOCGIDLE32		_IOR('t', 63, struct ppp_idle32)
 
-static int ppp_gidle(unsigned int fd, unsigned int cmd,
+static int ppp_gidle(struct file *file, unsigned int cmd,
 		struct ppp_idle32 __user *idle32)
 {
 	struct ppp_idle __user *idle;
@@ -460,7 +481,7 @@ static int ppp_gidle(unsigned int fd, unsigned int cmd,
 
 	idle = compat_alloc_user_space(sizeof(*idle));
 
-	err = sys_ioctl(fd, PPPIOCGIDLE, (unsigned long) idle);
+	err = do_ioctl(file, PPPIOCGIDLE, (unsigned long) idle);
 
 	if (!err) {
 		if (get_user(xmit, &idle->xmit_idle) ||
@@ -472,7 +493,7 @@ static int ppp_gidle(unsigned int fd, unsigned int cmd,
 	return err;
 }
 
-static int ppp_scompress(unsigned int fd, unsigned int cmd,
+static int ppp_scompress(struct file *file, unsigned int cmd,
 	struct ppp_option_data32 __user *odata32)
 {
 	struct ppp_option_data __user *odata;
@@ -492,7 +513,7 @@ static int ppp_scompress(unsigned int fd, unsigned int cmd,
 			 sizeof(__u32) + sizeof(int)))
 		return -EFAULT;
 
-	return sys_ioctl(fd, PPPIOCSCOMPRESS, (unsigned long) odata);
+	return do_ioctl(file, PPPIOCSCOMPRESS, (unsigned long) odata);
 }
 
 #ifdef CONFIG_BLOCK
@@ -512,12 +533,13 @@ struct mtpos32 {
 };
 #define MTIOCPOS32	_IOR('m', 3, struct mtpos32)
 
-static int mt_ioctl_trans(unsigned int fd, unsigned int cmd, void __user *argp)
+static int mt_ioctl_trans(struct file *file,
+		unsigned int cmd, void __user *argp)
 {
-	mm_segment_t old_fs = get_fs();
-	struct mtget get;
+	/* NULL initialization to make gcc shut up */
+	struct mtget __user *get = NULL;
 	struct mtget32 __user *umget32;
-	struct mtpos pos;
+	struct mtpos __user *pos = NULL;
 	struct mtpos32 __user *upos32;
 	unsigned long kcmd;
 	void *karg;
@@ -526,32 +548,34 @@ static int mt_ioctl_trans(unsigned int fd, unsigned int cmd, void __user *argp)
 	switch(cmd) {
 	case MTIOCPOS32:
 		kcmd = MTIOCPOS;
-		karg = &pos;
+		pos = compat_alloc_user_space(sizeof(*pos));
+		karg = pos;
 		break;
 	default:	/* MTIOCGET32 */
 		kcmd = MTIOCGET;
-		karg = &get;
+		get = compat_alloc_user_space(sizeof(*get));
+		karg = get;
 		break;
 	}
-	set_fs (KERNEL_DS);
-	err = sys_ioctl (fd, kcmd, (unsigned long)karg);
-	set_fs (old_fs);
+	if (karg == NULL)
+		return -EFAULT;
+	err = do_ioctl(file, kcmd, (unsigned long)karg);
 	if (err)
 		return err;
 	switch (cmd) {
 	case MTIOCPOS32:
 		upos32 = argp;
-		err = __put_user(pos.mt_blkno, &upos32->mt_blkno);
+		err = convert_in_user(&pos->mt_blkno, &upos32->mt_blkno);
 		break;
 	case MTIOCGET32:
 		umget32 = argp;
-		err = __put_user(get.mt_type, &umget32->mt_type);
-		err |= __put_user(get.mt_resid, &umget32->mt_resid);
-		err |= __put_user(get.mt_dsreg, &umget32->mt_dsreg);
-		err |= __put_user(get.mt_gstat, &umget32->mt_gstat);
-		err |= __put_user(get.mt_erreg, &umget32->mt_erreg);
-		err |= __put_user(get.mt_fileno, &umget32->mt_fileno);
-		err |= __put_user(get.mt_blkno, &umget32->mt_blkno);
+		err = convert_in_user(&get->mt_type, &umget32->mt_type);
+		err |= convert_in_user(&get->mt_resid, &umget32->mt_resid);
+		err |= convert_in_user(&get->mt_dsreg, &umget32->mt_dsreg);
+		err |= convert_in_user(&get->mt_gstat, &umget32->mt_gstat);
+		err |= convert_in_user(&get->mt_erreg, &umget32->mt_erreg);
+		err |= convert_in_user(&get->mt_fileno, &umget32->mt_fileno);
+		err |= convert_in_user(&get->mt_blkno, &umget32->mt_blkno);
 		break;
 	}
 	return err ? -EFAULT: 0;
@@ -605,42 +629,41 @@ struct serial_struct32 {
         compat_int_t    reserved[1];
 };
 
-static int serial_struct_ioctl(unsigned fd, unsigned cmd,
-			struct serial_struct32 __user *ss32)
+static int serial_struct_ioctl(struct file *file,
+		unsigned cmd, struct serial_struct32 __user *ss32)
 {
         typedef struct serial_struct32 SS32;
         int err;
-        struct serial_struct ss;
-        mm_segment_t oldseg = get_fs();
+	struct serial_struct __user *ss = compat_alloc_user_space(sizeof(*ss));
         __u32 udata;
 	unsigned int base;
+	unsigned char *iomem_base;
 
+	if (ss == NULL)
+		return -EFAULT;
         if (cmd == TIOCSSERIAL) {
-                if (!access_ok(VERIFY_READ, ss32, sizeof(SS32)))
-                        return -EFAULT;
-                if (__copy_from_user(&ss, ss32, offsetof(SS32, iomem_base)))
-			return -EFAULT;
-                if (__get_user(udata, &ss32->iomem_base))
+		if (copy_in_user(ss, ss32, offsetof(SS32, iomem_base)) ||
+		    get_user(udata, &ss32->iomem_base))
 			return -EFAULT;
-                ss.iomem_base = compat_ptr(udata);
-                if (__get_user(ss.iomem_reg_shift, &ss32->iomem_reg_shift) ||
-		    __get_user(ss.port_high, &ss32->port_high))
+		iomem_base = compat_ptr(udata);
+		if (put_user(iomem_base, &ss->iomem_base) ||
+		    convert_in_user(&ss32->iomem_reg_shift,
+		      &ss->iomem_reg_shift) ||
+		    convert_in_user(&ss32->port_high, &ss->port_high) ||
+		    put_user(0UL, &ss->iomap_base))
 			return -EFAULT;
-                ss.iomap_base = 0UL;
         }
-        set_fs(KERNEL_DS);
-                err = sys_ioctl(fd,cmd,(unsigned long)(&ss));
-        set_fs(oldseg);
+	err = do_ioctl(file, cmd, (unsigned long)ss);
         if (cmd == TIOCGSERIAL && err >= 0) {
-                if (!access_ok(VERIFY_WRITE, ss32, sizeof(SS32)))
-                        return -EFAULT;
-                if (__copy_to_user(ss32,&ss,offsetof(SS32,iomem_base)))
+		if (copy_in_user(ss32, ss, offsetof(SS32, iomem_base)) ||
+		    get_user(iomem_base, &ss->iomem_base))
 			return -EFAULT;
-		base = (unsigned long)ss.iomem_base  >> 32 ?
-			0xffffffff : (unsigned)(unsigned long)ss.iomem_base;
-		if (__put_user(base, &ss32->iomem_base) ||
-		    __put_user(ss.iomem_reg_shift, &ss32->iomem_reg_shift) ||
-		    __put_user(ss.port_high, &ss32->port_high))
+		base = (unsigned long)iomem_base  >> 32 ?
+			0xffffffff : (unsigned)(unsigned long)iomem_base;
+		if (put_user(base, &ss32->iomem_base) ||
+		    convert_in_user(&ss->iomem_reg_shift,
+		      &ss32->iomem_reg_shift) ||
+		    convert_in_user(&ss->port_high, &ss32->port_high))
 			return -EFAULT;
         }
         return err;
@@ -674,8 +697,8 @@ struct i2c_rdwr_aligned {
 	struct i2c_msg msgs[0];
 };
 
-static int do_i2c_rdwr_ioctl(unsigned int fd, unsigned int cmd,
-			struct i2c_rdwr_ioctl_data32    __user *udata)
+static int do_i2c_rdwr_ioctl(struct file *file,
+	unsigned int cmd, struct i2c_rdwr_ioctl_data32 __user *udata)
 {
 	struct i2c_rdwr_aligned		__user *tdata;
 	struct i2c_msg			__user *tmsgs;
@@ -686,7 +709,7 @@ static int do_i2c_rdwr_ioctl(unsigned int fd, unsigned int cmd,
 
 	if (get_user(nmsgs, &udata->nmsgs))
 		return -EFAULT;
-	if (nmsgs > I2C_RDRW_IOCTL_MAX_MSGS)
+	if (nmsgs > I2C_RDWR_IOCTL_MAX_MSGS)
 		return -EINVAL;
 
 	if (get_user(datap, &udata->msgs))
@@ -708,11 +731,11 @@ static int do_i2c_rdwr_ioctl(unsigned int fd, unsigned int cmd,
 		    put_user(compat_ptr(datap), &tmsgs[i].buf))
 			return -EFAULT;
 	}
-	return sys_ioctl(fd, cmd, (unsigned long)tdata);
+	return do_ioctl(file, cmd, (unsigned long)tdata);
 }
 
-static int do_i2c_smbus_ioctl(unsigned int fd, unsigned int cmd,
-			struct i2c_smbus_ioctl_data32   __user *udata)
+static int do_i2c_smbus_ioctl(struct file *file,
+		unsigned int cmd, struct i2c_smbus_ioctl_data32   __user *udata)
 {
 	struct i2c_smbus_ioctl_data	__user *tdata;
 	compat_caddr_t			datap;
@@ -734,7 +757,7 @@ static int do_i2c_smbus_ioctl(unsigned int fd, unsigned int cmd,
 	    __put_user(compat_ptr(datap), &tdata->data))
 		return -EFAULT;
 
-	return sys_ioctl(fd, cmd, (unsigned long)tdata);
+	return do_ioctl(file, cmd, (unsigned long)tdata);
 }
 
 #define RTC_IRQP_READ32		_IOR('p', 0x0b, compat_ulong_t)
@@ -742,29 +765,27 @@ static int do_i2c_smbus_ioctl(unsigned int fd, unsigned int cmd,
 #define RTC_EPOCH_READ32	_IOR('p', 0x0d, compat_ulong_t)
 #define RTC_EPOCH_SET32		_IOW('p', 0x0e, compat_ulong_t)
 
-static int rtc_ioctl(unsigned fd, unsigned cmd, void __user *argp)
+static int rtc_ioctl(struct file *file,
+		unsigned cmd, void __user *argp)
 {
-	mm_segment_t oldfs = get_fs();
-	compat_ulong_t val32;
-	unsigned long kval;
+	unsigned long __user *valp = compat_alloc_user_space(sizeof(*valp));
 	int ret;
 
+	if (valp == NULL)
+		return -EFAULT;
 	switch (cmd) {
 	case RTC_IRQP_READ32:
 	case RTC_EPOCH_READ32:
-		set_fs(KERNEL_DS);
-		ret = sys_ioctl(fd, (cmd == RTC_IRQP_READ32) ?
+		ret = do_ioctl(file, (cmd == RTC_IRQP_READ32) ?
 					RTC_IRQP_READ : RTC_EPOCH_READ,
-					(unsigned long)&kval);
-		set_fs(oldfs);
+					(unsigned long)valp);
 		if (ret)
 			return ret;
-		val32 = kval;
-		return put_user(val32, (unsigned int __user *)argp);
+		return convert_in_user(valp, (unsigned int __user *)argp);
 	case RTC_IRQP_SET32:
-		return sys_ioctl(fd, RTC_IRQP_SET, (unsigned long)argp);
+		return do_ioctl(file, RTC_IRQP_SET, (unsigned long)argp);
 	case RTC_EPOCH_SET32:
-		return sys_ioctl(fd, RTC_EPOCH_SET, (unsigned long)argp);
+		return do_ioctl(file, RTC_EPOCH_SET, (unsigned long)argp);
 	}
 
 	return -ENOIOCTLCMD;
@@ -1019,28 +1040,6 @@ COMPATIBLE_IOCTL(PPPIOCGL2TPSTATS)
 /* PPPOX */
 COMPATIBLE_IOCTL(PPPOEIOCSFWD)
 COMPATIBLE_IOCTL(PPPOEIOCDFWD)
-/* ppdev */
-COMPATIBLE_IOCTL(PPSETMODE)
-COMPATIBLE_IOCTL(PPRSTATUS)
-COMPATIBLE_IOCTL(PPRCONTROL)
-COMPATIBLE_IOCTL(PPWCONTROL)
-COMPATIBLE_IOCTL(PPFCONTROL)
-COMPATIBLE_IOCTL(PPRDATA)
-COMPATIBLE_IOCTL(PPWDATA)
-COMPATIBLE_IOCTL(PPCLAIM)
-COMPATIBLE_IOCTL(PPRELEASE)
-COMPATIBLE_IOCTL(PPYIELD)
-COMPATIBLE_IOCTL(PPEXCL)
-COMPATIBLE_IOCTL(PPDATADIR)
-COMPATIBLE_IOCTL(PPNEGOT)
-COMPATIBLE_IOCTL(PPWCTLONIRQ)
-COMPATIBLE_IOCTL(PPCLRIRQ)
-COMPATIBLE_IOCTL(PPSETPHASE)
-COMPATIBLE_IOCTL(PPGETMODES)
-COMPATIBLE_IOCTL(PPGETMODE)
-COMPATIBLE_IOCTL(PPGETPHASE)
-COMPATIBLE_IOCTL(PPGETFLAGS)
-COMPATIBLE_IOCTL(PPSETFLAGS)
 /* Big A */
 /* sparc only */
 /* Big Q for sound/OSS */
@@ -1240,6 +1239,9 @@ COMPATIBLE_IOCTL(HCIUNBLOCKADDR)
 COMPATIBLE_IOCTL(HCIINQUIRY)
 COMPATIBLE_IOCTL(HCIUARTSETPROTO)
 COMPATIBLE_IOCTL(HCIUARTGETPROTO)
+COMPATIBLE_IOCTL(HCIUARTGETDEVICE)
+COMPATIBLE_IOCTL(HCIUARTSETFLAGS)
+COMPATIBLE_IOCTL(HCIUARTGETFLAGS)
 COMPATIBLE_IOCTL(RFCOMMCREATEDEV)
 COMPATIBLE_IOCTL(RFCOMMRELEASEDEV)
 COMPATIBLE_IOCTL(RFCOMMGETDEVLIST)
@@ -1284,12 +1286,6 @@ COMPATIBLE_IOCTL(PCIIOC_CONTROLLER)
 COMPATIBLE_IOCTL(PCIIOC_MMAP_IS_IO)
 COMPATIBLE_IOCTL(PCIIOC_MMAP_IS_MEM)
 COMPATIBLE_IOCTL(PCIIOC_WRITE_COMBINE)
-/* NBD */
-COMPATIBLE_IOCTL(NBD_DO_IT)
-COMPATIBLE_IOCTL(NBD_CLEAR_SOCK)
-COMPATIBLE_IOCTL(NBD_CLEAR_QUE)
-COMPATIBLE_IOCTL(NBD_PRINT_DEBUG)
-COMPATIBLE_IOCTL(NBD_DISCONNECT)
 /* i2c */
 COMPATIBLE_IOCTL(I2C_SLAVE)
 COMPATIBLE_IOCTL(I2C_SLAVE_FORCE)
@@ -1436,53 +1432,53 @@ IGNORE_IOCTL(FBIOGCURSOR32)
  * a compat_ioctl operation in the place that handleѕ the
  * ioctl for the native case.
  */
-static long do_ioctl_trans(int fd, unsigned int cmd,
+static long do_ioctl_trans(unsigned int cmd,
 		 unsigned long arg, struct file *file)
 {
 	void __user *argp = compat_ptr(arg);
 
 	switch (cmd) {
 	case PPPIOCGIDLE32:
-		return ppp_gidle(fd, cmd, argp);
+		return ppp_gidle(file, cmd, argp);
 	case PPPIOCSCOMPRESS32:
-		return ppp_scompress(fd, cmd, argp);
+		return ppp_scompress(file, cmd, argp);
 	case PPPIOCSPASS32:
 	case PPPIOCSACTIVE32:
-		return ppp_sock_fprog_ioctl_trans(fd, cmd, argp);
+		return ppp_sock_fprog_ioctl_trans(file, cmd, argp);
 #ifdef CONFIG_BLOCK
 	case SG_IO:
-		return sg_ioctl_trans(fd, cmd, argp);
+		return sg_ioctl_trans(file, cmd, argp);
 	case SG_GET_REQUEST_TABLE:
-		return sg_grt_trans(fd, cmd, argp);
+		return sg_grt_trans(file, cmd, argp);
 	case MTIOCGET32:
 	case MTIOCPOS32:
-		return mt_ioctl_trans(fd, cmd, argp);
+		return mt_ioctl_trans(file, cmd, argp);
 #endif
 	/* Serial */
 	case TIOCGSERIAL:
 	case TIOCSSERIAL:
-		return serial_struct_ioctl(fd, cmd, argp);
+		return serial_struct_ioctl(file, cmd, argp);
 	/* i2c */
 	case I2C_FUNCS:
-		return w_long(fd, cmd, argp);
+		return w_long(file, cmd, argp);
 	case I2C_RDWR:
-		return do_i2c_rdwr_ioctl(fd, cmd, argp);
+		return do_i2c_rdwr_ioctl(file, cmd, argp);
 	case I2C_SMBUS:
-		return do_i2c_smbus_ioctl(fd, cmd, argp);
+		return do_i2c_smbus_ioctl(file, cmd, argp);
 	/* Not implemented in the native kernel */
 	case RTC_IRQP_READ32:
 	case RTC_IRQP_SET32:
 	case RTC_EPOCH_READ32:
 	case RTC_EPOCH_SET32:
-		return rtc_ioctl(fd, cmd, argp);
+		return rtc_ioctl(file, cmd, argp);
 
 	/* dvb */
 	case VIDEO_GET_EVENT:
-		return do_video_get_event(fd, cmd, argp);
+		return do_video_get_event(file, cmd, argp);
 	case VIDEO_STILLPICTURE:
-		return do_video_stillpicture(fd, cmd, argp);
+		return do_video_stillpicture(file, cmd, argp);
 	case VIDEO_SET_SPU_PALETTE:
-		return do_video_set_spu_palette(fd, cmd, argp);
+		return do_video_set_spu_palette(file, cmd, argp);
 	}
 
 	/*
@@ -1508,12 +1504,7 @@ static long do_ioctl_trans(int fd, unsigned int cmd,
 	case KDSKBMETA:
 	case KDSKBLED:
 	case KDSETLED:
-	/* NBD */
-	case NBD_SET_SOCK:
-	case NBD_SET_BLKSIZE:
-	case NBD_SET_SIZE:
-	case NBD_SET_SIZE_BLOCKS:
-		return do_vfs_ioctl(file, fd, cmd, arg);
+		return vfs_ioctl(file, cmd, arg);
 	}
 
 	return -ENOIOCTLCMD;
@@ -1580,6 +1571,11 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd,
 		goto out_fput;
 #endif
 
+	case FICLONE:
+	case FICLONERANGE:
+	case FIDEDUPERANGE:
+		goto do_ioctl;
+
 	case FIBMAP:
 	case FIGETBSZ:
 	case FIONREAD:
@@ -1602,7 +1598,7 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd,
 	if (compat_ioctl_check_table(XFORM(cmd)))
 		goto found_handler;
 
-	error = do_ioctl_trans(fd, cmd, arg, f.file);
+	error = do_ioctl_trans(cmd, arg, f.file);
 	if (error == -ENOIOCTLCMD)
 		error = -ENOTTY;
 
diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h
index b65d1ef532d5..ccc31fa6f1a7 100644
--- a/fs/configfs/configfs_internal.h
+++ b/fs/configfs/configfs_internal.h
@@ -53,13 +53,14 @@ struct configfs_dirent {
 #define CONFIGFS_ROOT		0x0001
 #define CONFIGFS_DIR		0x0002
 #define CONFIGFS_ITEM_ATTR	0x0004
+#define CONFIGFS_ITEM_BIN_ATTR	0x0008
 #define CONFIGFS_ITEM_LINK	0x0020
 #define CONFIGFS_USET_DIR	0x0040
 #define CONFIGFS_USET_DEFAULT	0x0080
 #define CONFIGFS_USET_DROPPING	0x0100
 #define CONFIGFS_USET_IN_MKDIR	0x0200
 #define CONFIGFS_USET_CREATING	0x0400
-#define CONFIGFS_NOT_PINNED	(CONFIGFS_ITEM_ATTR)
+#define CONFIGFS_NOT_PINNED	(CONFIGFS_ITEM_ATTR | CONFIGFS_ITEM_BIN_ATTR)
 
 extern struct mutex configfs_symlink_mutex;
 extern spinlock_t configfs_dirent_lock;
@@ -72,6 +73,8 @@ extern struct inode * configfs_new_inode(umode_t mode, struct configfs_dirent *,
 extern int configfs_create(struct dentry *, umode_t mode, void (*init)(struct inode *));
 
 extern int configfs_create_file(struct config_item *, const struct configfs_attribute *);
+extern int configfs_create_bin_file(struct config_item *,
+				    const struct configfs_bin_attribute *);
 extern int configfs_make_dirent(struct configfs_dirent *,
 				struct dentry *, void *, umode_t, int);
 extern int configfs_dirent_is_ready(struct configfs_dirent *);
@@ -88,7 +91,7 @@ extern void configfs_release_fs(void);
 extern struct rw_semaphore configfs_rename_sem;
 extern const struct file_operations configfs_dir_operations;
 extern const struct file_operations configfs_file_operations;
-extern const struct file_operations bin_fops;
+extern const struct file_operations configfs_bin_file_operations;
 extern const struct inode_operations configfs_dir_inode_operations;
 extern const struct inode_operations configfs_root_inode_operations;
 extern const struct inode_operations configfs_symlink_inode_operations;
@@ -119,6 +122,13 @@ static inline struct configfs_attribute * to_attr(struct dentry * dentry)
 	return ((struct configfs_attribute *) sd->s_element);
 }
 
+static inline struct configfs_bin_attribute *to_bin_attr(struct dentry *dentry)
+{
+	struct configfs_attribute *attr = to_attr(dentry);
+
+	return container_of(attr, struct configfs_bin_attribute, cb_attr);
+}
+
 static inline struct config_item *configfs_get_config_item(struct dentry *dentry)
 {
 	struct config_item * item = NULL;
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index c81ce7f200a6..ea59c891fc53 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -255,6 +255,12 @@ static void configfs_init_file(struct inode * inode)
 	inode->i_fop = &configfs_file_operations;
 }
 
+static void configfs_init_bin_file(struct inode *inode)
+{
+	inode->i_size = 0;
+	inode->i_fop = &configfs_bin_file_operations;
+}
+
 static void init_symlink(struct inode * inode)
 {
 	inode->i_op = &configfs_symlink_inode_operations;
@@ -423,15 +429,12 @@ static int configfs_attach_attr(struct configfs_dirent * sd, struct dentry * den
 	spin_unlock(&configfs_dirent_lock);
 
 	error = configfs_create(dentry, (attr->ca_mode & S_IALLUGO) | S_IFREG,
-				configfs_init_file);
-	if (error) {
+				(sd->s_type & CONFIGFS_ITEM_BIN_ATTR) ?
+					configfs_init_bin_file :
+					configfs_init_file);
+	if (error)
 		configfs_put(sd);
-		return error;
-	}
-
-	d_rehash(dentry);
-
-	return 0;
+	return error;
 }
 
 static struct dentry * configfs_lookup(struct inode *dir,
@@ -583,6 +586,7 @@ static int populate_attrs(struct config_item *item)
 {
 	struct config_item_type *t = item->ci_type;
 	struct configfs_attribute *attr;
+	struct configfs_bin_attribute *bin_attr;
 	int error = 0;
 	int i;
 
@@ -594,6 +598,13 @@ static int populate_attrs(struct config_item *item)
 				break;
 		}
 	}
+	if (t->ct_bin_attrs) {
+		for (i = 0; (bin_attr = t->ct_bin_attrs[i]) != NULL; i++) {
+			error = configfs_create_bin_file(item, bin_attr);
+			if (error)
+				break;
+		}
+	}
 
 	if (error)
 		detach_attrs(item);
@@ -624,13 +635,13 @@ static void detach_groups(struct config_group *group)
 
 		child = sd->s_dentry;
 
-		mutex_lock(&d_inode(child)->i_mutex);
+		inode_lock(d_inode(child));
 
 		configfs_detach_group(sd->s_element);
 		d_inode(child)->i_flags |= S_DEAD;
 		dont_mount(child);
 
-		mutex_unlock(&d_inode(child)->i_mutex);
+		inode_unlock(d_inode(child));
 
 		d_delete(child);
 		dput(child);
@@ -685,23 +696,29 @@ static int populate_groups(struct config_group *group)
 {
 	struct config_group *new_group;
 	int ret = 0;
-	int i;
 
-	if (group->default_groups) {
-		for (i = 0; group->default_groups[i]; i++) {
-			new_group = group->default_groups[i];
-
-			ret = create_default_group(group, new_group);
-			if (ret) {
-				detach_groups(group);
-				break;
-			}
+	list_for_each_entry(new_group, &group->default_groups, group_entry) {
+		ret = create_default_group(group, new_group);
+		if (ret) {
+			detach_groups(group);
+			break;
 		}
 	}
 
 	return ret;
 }
 
+void configfs_remove_default_groups(struct config_group *group)
+{
+	struct config_group *g, *n;
+
+	list_for_each_entry_safe(g, n, &group->default_groups, group_entry) {
+		list_del(&g->group_entry);
+		config_item_put(&g->cg_item);
+	}
+}
+EXPORT_SYMBOL(configfs_remove_default_groups);
+
 /*
  * All of link_obj/unlink_obj/link_group/unlink_group require that
  * subsys->su_mutex is held.
@@ -750,15 +767,10 @@ static void link_obj(struct config_item *parent_item, struct config_item *item)
 
 static void unlink_group(struct config_group *group)
 {
-	int i;
 	struct config_group *new_group;
 
-	if (group->default_groups) {
-		for (i = 0; group->default_groups[i]; i++) {
-			new_group = group->default_groups[i];
-			unlink_group(new_group);
-		}
-	}
+	list_for_each_entry(new_group, &group->default_groups, group_entry)
+		unlink_group(new_group);
 
 	group->cg_subsys = NULL;
 	unlink_obj(&group->cg_item);
@@ -766,7 +778,6 @@ static void unlink_group(struct config_group *group)
 
 static void link_group(struct config_group *parent_group, struct config_group *group)
 {
-	int i;
 	struct config_group *new_group;
 	struct configfs_subsystem *subsys = NULL; /* gcc is a turd */
 
@@ -780,12 +791,8 @@ static void link_group(struct config_group *parent_group, struct config_group *g
 		BUG();
 	group->cg_subsys = subsys;
 
-	if (group->default_groups) {
-		for (i = 0; group->default_groups[i]; i++) {
-			new_group = group->default_groups[i];
-			link_group(group, new_group);
-		}
-	}
+	list_for_each_entry(new_group, &group->default_groups, group_entry)
+		link_group(group, new_group);
 }
 
 /*
@@ -818,11 +825,11 @@ static int configfs_attach_item(struct config_item *parent_item,
 			 * the VFS may already have hit and used them. Thus,
 			 * we must lock them as rmdir() would.
 			 */
-			mutex_lock(&d_inode(dentry)->i_mutex);
+			inode_lock(d_inode(dentry));
 			configfs_remove_dir(item);
 			d_inode(dentry)->i_flags |= S_DEAD;
 			dont_mount(dentry);
-			mutex_unlock(&d_inode(dentry)->i_mutex);
+			inode_unlock(d_inode(dentry));
 			d_delete(dentry);
 		}
 	}
@@ -858,7 +865,7 @@ static int configfs_attach_group(struct config_item *parent_item,
 		 * We must also lock the inode to remove it safely in case of
 		 * error, as rmdir() would.
 		 */
-		mutex_lock_nested(&d_inode(dentry)->i_mutex, I_MUTEX_CHILD);
+		inode_lock_nested(d_inode(dentry), I_MUTEX_CHILD);
 		configfs_adjust_dir_dirent_depth_before_populate(sd);
 		ret = populate_groups(to_config_group(item));
 		if (ret) {
@@ -867,7 +874,7 @@ static int configfs_attach_group(struct config_item *parent_item,
 			dont_mount(dentry);
 		}
 		configfs_adjust_dir_dirent_depth_after_populate(sd);
-		mutex_unlock(&d_inode(dentry)->i_mutex);
+		inode_unlock(d_inode(dentry));
 		if (ret)
 			d_delete(dentry);
 	}
@@ -1054,11 +1061,55 @@ out:
 	return ret;
 }
 
+static int configfs_do_depend_item(struct dentry *subsys_dentry,
+				   struct config_item *target)
+{
+	struct configfs_dirent *p;
+	int ret;
+
+	spin_lock(&configfs_dirent_lock);
+	/* Scan the tree, return 0 if found */
+	ret = configfs_depend_prep(subsys_dentry, target);
+	if (ret)
+		goto out_unlock_dirent_lock;
+
+	/*
+	 * We are sure that the item is not about to be removed by rmdir(), and
+	 * not in the middle of attachment by mkdir().
+	 */
+	p = target->ci_dentry->d_fsdata;
+	p->s_dependent_count += 1;
+
+out_unlock_dirent_lock:
+	spin_unlock(&configfs_dirent_lock);
+
+	return ret;
+}
+
+static inline struct configfs_dirent *
+configfs_find_subsys_dentry(struct configfs_dirent *root_sd,
+			    struct config_item *subsys_item)
+{
+	struct configfs_dirent *p;
+	struct configfs_dirent *ret = NULL;
+
+	list_for_each_entry(p, &root_sd->s_children, s_sibling) {
+		if (p->s_type & CONFIGFS_DIR &&
+		    p->s_element == subsys_item) {
+			ret = p;
+			break;
+		}
+	}
+
+	return ret;
+}
+
+
 int configfs_depend_item(struct configfs_subsystem *subsys,
 			 struct config_item *target)
 {
 	int ret;
-	struct configfs_dirent *p, *root_sd, *subsys_sd = NULL;
+	struct configfs_dirent *subsys_sd;
 	struct config_item *s_item = &subsys->su_group.cg_item;
 	struct dentry *root;
 
@@ -1075,43 +1126,19 @@ int configfs_depend_item(struct configfs_subsystem *subsys,
 	 * subsystem is really registered, and so we need to lock out
 	 * configfs_[un]register_subsystem().
 	 */
-	mutex_lock(&d_inode(root)->i_mutex);
-
-	root_sd = root->d_fsdata;
-
-	list_for_each_entry(p, &root_sd->s_children, s_sibling) {
-		if (p->s_type & CONFIGFS_DIR) {
-			if (p->s_element == s_item) {
-				subsys_sd = p;
-				break;
-			}
-		}
-	}
+	inode_lock(d_inode(root));
 
+	subsys_sd = configfs_find_subsys_dentry(root->d_fsdata, s_item);
 	if (!subsys_sd) {
 		ret = -ENOENT;
 		goto out_unlock_fs;
 	}
 
 	/* Ok, now we can trust subsys/s_item */
+	ret = configfs_do_depend_item(subsys_sd->s_dentry, target);
 
-	spin_lock(&configfs_dirent_lock);
-	/* Scan the tree, return 0 if found */
-	ret = configfs_depend_prep(subsys_sd->s_dentry, target);
-	if (ret)
-		goto out_unlock_dirent_lock;
-
-	/*
-	 * We are sure that the item is not about to be removed by rmdir(), and
-	 * not in the middle of attachment by mkdir().
-	 */
-	p = target->ci_dentry->d_fsdata;
-	p->s_dependent_count += 1;
-
-out_unlock_dirent_lock:
-	spin_unlock(&configfs_dirent_lock);
 out_unlock_fs:
-	mutex_unlock(&d_inode(root)->i_mutex);
+	inode_unlock(d_inode(root));
 
 	/*
 	 * If we succeeded, the fs is pinned via other methods.  If not,
@@ -1128,8 +1155,7 @@ EXPORT_SYMBOL(configfs_depend_item);
  * configfs_depend_item() because we know that that the client driver is
  * pinned, thus the subsystem is pinned, and therefore configfs is pinned.
  */
-void configfs_undepend_item(struct configfs_subsystem *subsys,
-			    struct config_item *target)
+void configfs_undepend_item(struct config_item *target)
 {
 	struct configfs_dirent *sd;
 
@@ -1152,6 +1178,79 @@ void configfs_undepend_item(struct configfs_subsystem *subsys,
 }
 EXPORT_SYMBOL(configfs_undepend_item);
 
+/*
+ * caller_subsys is a caller's subsystem not target's. This is used to
+ * determine if we should lock root and check subsys or not. When we are
+ * in the same subsystem as our target there is no need to do locking as
+ * we know that subsys is valid and is not unregistered during this function
+ * as we are called from callback of one of his children and VFS holds a lock
+ * on some inode. Otherwise we have to lock our root to  ensure that target's
+ * subsystem it is not unregistered during this function.
+ */
+int configfs_depend_item_unlocked(struct configfs_subsystem *caller_subsys,
+				  struct config_item *target)
+{
+	struct configfs_subsystem *target_subsys;
+	struct config_group *root, *parent;
+	struct configfs_dirent *subsys_sd;
+	int ret = -ENOENT;
+
+	/* Disallow this function for configfs root */
+	if (configfs_is_root(target))
+		return -EINVAL;
+
+	parent = target->ci_group;
+	/*
+	 * This may happen when someone is trying to depend root
+	 * directory of some subsystem
+	 */
+	if (configfs_is_root(&parent->cg_item)) {
+		target_subsys = to_configfs_subsystem(to_config_group(target));
+		root = parent;
+	} else {
+		target_subsys = parent->cg_subsys;
+		/* Find a cofnigfs root as we may need it for locking */
+		for (root = parent; !configfs_is_root(&root->cg_item);
+		     root = root->cg_item.ci_group)
+			;
+	}
+
+	if (target_subsys != caller_subsys) {
+		/*
+		 * We are in other configfs subsystem, so we have to do
+		 * additional locking to prevent other subsystem from being
+		 * unregistered
+		 */
+		inode_lock(d_inode(root->cg_item.ci_dentry));
+
+		/*
+		 * As we are trying to depend item from other subsystem
+		 * we have to check if this subsystem is still registered
+		 */
+		subsys_sd = configfs_find_subsys_dentry(
+				root->cg_item.ci_dentry->d_fsdata,
+				&target_subsys->su_group.cg_item);
+		if (!subsys_sd)
+			goto out_root_unlock;
+	} else {
+		subsys_sd = target_subsys->su_group.cg_item.ci_dentry->d_fsdata;
+	}
+
+	/* Now we can execute core of depend item */
+	ret = configfs_do_depend_item(subsys_sd->s_dentry, target);
+
+	if (target_subsys != caller_subsys)
+out_root_unlock:
+		/*
+		 * We were called from subsystem other than our target so we
+		 * took some locks so now it's time to release them
+		 */
+		inode_unlock(d_inode(root->cg_item.ci_dentry));
+
+	return ret;
+}
+EXPORT_SYMBOL(configfs_depend_item_unlocked);
+
 static int configfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 {
 	int ret = 0;
@@ -1453,7 +1552,7 @@ int configfs_rename_dir(struct config_item * item, const char *new_name)
 	down_write(&configfs_rename_sem);
 	parent = item->parent->dentry;
 
-	mutex_lock(&d_inode(parent)->i_mutex);
+	inode_lock(d_inode(parent));
 
 	new_dentry = lookup_one_len(new_name, parent, strlen(new_name));
 	if (!IS_ERR(new_dentry)) {
@@ -1469,7 +1568,7 @@ int configfs_rename_dir(struct config_item * item, const char *new_name)
 			error = -EEXIST;
 		dput(new_dentry);
 	}
-	mutex_unlock(&d_inode(parent)->i_mutex);
+	inode_unlock(d_inode(parent));
 	up_write(&configfs_rename_sem);
 
 	return error;
@@ -1482,7 +1581,7 @@ static int configfs_dir_open(struct inode *inode, struct file *file)
 	struct configfs_dirent * parent_sd = dentry->d_fsdata;
 	int err;
 
-	mutex_lock(&d_inode(dentry)->i_mutex);
+	inode_lock(d_inode(dentry));
 	/*
 	 * Fake invisibility if dir belongs to a group/default groups hierarchy
 	 * being attached
@@ -1495,7 +1594,7 @@ static int configfs_dir_open(struct inode *inode, struct file *file)
 		else
 			err = 0;
 	}
-	mutex_unlock(&d_inode(dentry)->i_mutex);
+	inode_unlock(d_inode(dentry));
 
 	return err;
 }
@@ -1505,11 +1604,11 @@ static int configfs_dir_close(struct inode *inode, struct file *file)
 	struct dentry * dentry = file->f_path.dentry;
 	struct configfs_dirent * cursor = file->private_data;
 
-	mutex_lock(&d_inode(dentry)->i_mutex);
+	inode_lock(d_inode(dentry));
 	spin_lock(&configfs_dirent_lock);
 	list_del_init(&cursor->s_sibling);
 	spin_unlock(&configfs_dirent_lock);
-	mutex_unlock(&d_inode(dentry)->i_mutex);
+	inode_unlock(d_inode(dentry));
 
 	release_configfs_dirent(cursor);
 
@@ -1590,7 +1689,7 @@ static loff_t configfs_dir_lseek(struct file *file, loff_t offset, int whence)
 {
 	struct dentry * dentry = file->f_path.dentry;
 
-	mutex_lock(&d_inode(dentry)->i_mutex);
+	inode_lock(d_inode(dentry));
 	switch (whence) {
 		case 1:
 			offset += file->f_pos;
@@ -1598,7 +1697,7 @@ static loff_t configfs_dir_lseek(struct file *file, loff_t offset, int whence)
 			if (offset >= 0)
 				break;
 		default:
-			mutex_unlock(&d_inode(dentry)->i_mutex);
+			inode_unlock(d_inode(dentry));
 			return -EINVAL;
 	}
 	if (offset != file->f_pos) {
@@ -1624,7 +1723,7 @@ static loff_t configfs_dir_lseek(struct file *file, loff_t offset, int whence)
 			spin_unlock(&configfs_dirent_lock);
 		}
 	}
-	mutex_unlock(&d_inode(dentry)->i_mutex);
+	inode_unlock(d_inode(dentry));
 	return offset;
 }
 
@@ -1636,6 +1735,116 @@ const struct file_operations configfs_dir_operations = {
 	.iterate	= configfs_readdir,
 };
 
+/**
+ * configfs_register_group - creates a parent-child relation between two groups
+ * @parent_group:	parent group
+ * @group:		child group
+ *
+ * link groups, creates dentry for the child and attaches it to the
+ * parent dentry.
+ *
+ * Return: 0 on success, negative errno code on error
+ */
+int configfs_register_group(struct config_group *parent_group,
+			    struct config_group *group)
+{
+	struct configfs_subsystem *subsys = parent_group->cg_subsys;
+	struct dentry *parent;
+	int ret;
+
+	mutex_lock(&subsys->su_mutex);
+	link_group(parent_group, group);
+	mutex_unlock(&subsys->su_mutex);
+
+	parent = parent_group->cg_item.ci_dentry;
+
+	inode_lock_nested(d_inode(parent), I_MUTEX_PARENT);
+	ret = create_default_group(parent_group, group);
+	if (!ret) {
+		spin_lock(&configfs_dirent_lock);
+		configfs_dir_set_ready(group->cg_item.ci_dentry->d_fsdata);
+		spin_unlock(&configfs_dirent_lock);
+	}
+	inode_unlock(d_inode(parent));
+	return ret;
+}
+EXPORT_SYMBOL(configfs_register_group);
+
+/**
+ * configfs_unregister_group() - unregisters a child group from its parent
+ * @group: parent group to be unregistered
+ *
+ * Undoes configfs_register_group()
+ */
+void configfs_unregister_group(struct config_group *group)
+{
+	struct configfs_subsystem *subsys = group->cg_subsys;
+	struct dentry *dentry = group->cg_item.ci_dentry;
+	struct dentry *parent = group->cg_item.ci_parent->ci_dentry;
+
+	inode_lock_nested(d_inode(parent), I_MUTEX_PARENT);
+	spin_lock(&configfs_dirent_lock);
+	configfs_detach_prep(dentry, NULL);
+	spin_unlock(&configfs_dirent_lock);
+
+	configfs_detach_group(&group->cg_item);
+	d_inode(dentry)->i_flags |= S_DEAD;
+	dont_mount(dentry);
+	d_delete(dentry);
+	inode_unlock(d_inode(parent));
+
+	dput(dentry);
+
+	mutex_lock(&subsys->su_mutex);
+	unlink_group(group);
+	mutex_unlock(&subsys->su_mutex);
+}
+EXPORT_SYMBOL(configfs_unregister_group);
+
+/**
+ * configfs_register_default_group() - allocates and registers a child group
+ * @parent_group:	parent group
+ * @name:		child group name
+ * @item_type:		child item type description
+ *
+ * boilerplate to allocate and register a child group with its parent. We need
+ * kzalloc'ed memory because child's default_group is initially empty.
+ *
+ * Return: allocated config group or ERR_PTR() on error
+ */
+struct config_group *
+configfs_register_default_group(struct config_group *parent_group,
+				const char *name,
+				struct config_item_type *item_type)
+{
+	int ret;
+	struct config_group *group;
+
+	group = kzalloc(sizeof(*group), GFP_KERNEL);
+	if (!group)
+		return ERR_PTR(-ENOMEM);
+	config_group_init_type_name(group, name, item_type);
+
+	ret = configfs_register_group(parent_group, group);
+	if (ret) {
+		kfree(group);
+		return ERR_PTR(ret);
+	}
+	return group;
+}
+EXPORT_SYMBOL(configfs_register_default_group);
+
+/**
+ * configfs_unregister_default_group() - unregisters and frees a child group
+ * @group:	the group to act on
+ */
+void configfs_unregister_default_group(struct config_group *group)
+{
+	configfs_unregister_group(group);
+	kfree(group);
+}
+EXPORT_SYMBOL(configfs_unregister_default_group);
+
 int configfs_register_subsystem(struct configfs_subsystem *subsys)
 {
 	int err;
@@ -1654,7 +1863,7 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys)
 	sd = root->d_fsdata;
 	link_group(to_config_group(sd->s_element), group);
 
-	mutex_lock_nested(&d_inode(root)->i_mutex, I_MUTEX_PARENT);
+	inode_lock_nested(d_inode(root), I_MUTEX_PARENT);
 
 	err = -ENOMEM;
 	dentry = d_alloc_name(root, group->cg_item.ci_name);
@@ -1674,7 +1883,7 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys)
 		}
 	}
 
-	mutex_unlock(&d_inode(root)->i_mutex);
+	inode_unlock(d_inode(root));
 
 	if (err) {
 		unlink_group(group);
@@ -1695,9 +1904,9 @@ void configfs_unregister_subsystem(struct configfs_subsystem *subsys)
 		return;
 	}
 
-	mutex_lock_nested(&d_inode(root)->i_mutex,
+	inode_lock_nested(d_inode(root),
 			  I_MUTEX_PARENT);
-	mutex_lock_nested(&d_inode(dentry)->i_mutex, I_MUTEX_CHILD);
+	inode_lock_nested(d_inode(dentry), I_MUTEX_CHILD);
 	mutex_lock(&configfs_symlink_mutex);
 	spin_lock(&configfs_dirent_lock);
 	if (configfs_detach_prep(dentry, NULL)) {
@@ -1708,11 +1917,11 @@ void configfs_unregister_subsystem(struct configfs_subsystem *subsys)
 	configfs_detach_group(&group->cg_item);
 	d_inode(dentry)->i_flags |= S_DEAD;
 	dont_mount(dentry);
-	mutex_unlock(&d_inode(dentry)->i_mutex);
+	inode_unlock(d_inode(dentry));
 
 	d_delete(dentry);
 
-	mutex_unlock(&d_inode(root)->i_mutex);
+	inode_unlock(d_inode(root));
 
 	dput(dentry);
 
diff --git a/fs/configfs/file.c b/fs/configfs/file.c
index 403269ffcdf3..33b7ee34eda5 100644
--- a/fs/configfs/file.c
+++ b/fs/configfs/file.c
@@ -28,6 +28,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/mutex.h>
+#include <linux/vmalloc.h>
 #include <asm/uaccess.h>
 
 #include <linux/configfs.h>
@@ -48,6 +49,10 @@ struct configfs_buffer {
 	struct configfs_item_operations	* ops;
 	struct mutex		mutex;
 	int			needs_read_fill;
+	bool			read_in_progress;
+	bool			write_in_progress;
+	char			*bin_buffer;
+	int			bin_buffer_size;
 };
 
 
@@ -65,7 +70,6 @@ static int fill_read_buffer(struct dentry * dentry, struct configfs_buffer * buf
 {
 	struct configfs_attribute * attr = to_attr(dentry);
 	struct config_item * item = to_item(dentry->d_parent);
-	struct configfs_item_operations * ops = buffer->ops;
 	int ret = 0;
 	ssize_t count;
 
@@ -74,7 +78,8 @@ static int fill_read_buffer(struct dentry * dentry, struct configfs_buffer * buf
 	if (!buffer->page)
 		return -ENOMEM;
 
-	count = ops->show_attribute(item,attr,buffer->page);
+	count = attr->show(item, buffer->page);
+
 	buffer->needs_read_fill = 0;
 	BUG_ON(count > (ssize_t)SIMPLE_ATTR_SIZE);
 	if (count >= 0)
@@ -123,6 +128,87 @@ out:
 	return retval;
 }
 
+/**
+ *	configfs_read_bin_file - read a binary attribute.
+ *	@file:	file pointer.
+ *	@buf:	buffer to fill.
+ *	@count:	number of bytes to read.
+ *	@ppos:	starting offset in file.
+ *
+ *	Userspace wants to read a binary attribute file. The attribute
+ *	descriptor is in the file's ->d_fsdata. The target item is in the
+ *	directory's ->d_fsdata.
+ *
+ *	We check whether we need to refill the buffer. If so we will
+ *	call the attributes' attr->read() twice. The first time we
+ *	will pass a NULL as a buffer pointer, which the attributes' method
+ *	will use to return the size of the buffer required. If no error
+ *	occurs we will allocate the buffer using vmalloc and call
+ *	attr->read() again passing that buffer as an argument.
+ *	Then we just copy to user-space using simple_read_from_buffer.
+ */
+
+static ssize_t
+configfs_read_bin_file(struct file *file, char __user *buf,
+		       size_t count, loff_t *ppos)
+{
+	struct configfs_buffer *buffer = file->private_data;
+	struct dentry *dentry = file->f_path.dentry;
+	struct config_item *item = to_item(dentry->d_parent);
+	struct configfs_bin_attribute *bin_attr = to_bin_attr(dentry);
+	ssize_t retval = 0;
+	ssize_t len = min_t(size_t, count, PAGE_SIZE);
+
+	mutex_lock(&buffer->mutex);
+
+	/* we don't support switching read/write modes */
+	if (buffer->write_in_progress) {
+		retval = -ETXTBSY;
+		goto out;
+	}
+	buffer->read_in_progress = 1;
+
+	if (buffer->needs_read_fill) {
+		/* perform first read with buf == NULL to get extent */
+		len = bin_attr->read(item, NULL, 0);
+		if (len <= 0) {
+			retval = len;
+			goto out;
+		}
+
+		/* do not exceed the maximum value */
+		if (bin_attr->cb_max_size && len > bin_attr->cb_max_size) {
+			retval = -EFBIG;
+			goto out;
+		}
+
+		buffer->bin_buffer = vmalloc(len);
+		if (buffer->bin_buffer == NULL) {
+			retval = -ENOMEM;
+			goto out;
+		}
+		buffer->bin_buffer_size = len;
+
+		/* perform second read to fill buffer */
+		len = bin_attr->read(item, buffer->bin_buffer, len);
+		if (len < 0) {
+			retval = len;
+			vfree(buffer->bin_buffer);
+			buffer->bin_buffer_size = 0;
+			buffer->bin_buffer = NULL;
+			goto out;
+		}
+
+		buffer->needs_read_fill = 0;
+	}
+
+	retval = simple_read_from_buffer(buf, count, ppos, buffer->bin_buffer,
+					buffer->bin_buffer_size);
+out:
+	mutex_unlock(&buffer->mutex);
+	return retval;
+}
+
 
 /**
  *	fill_write_buffer - copy buffer from userspace.
@@ -171,9 +257,8 @@ flush_write_buffer(struct dentry * dentry, struct configfs_buffer * buffer, size
 {
 	struct configfs_attribute * attr = to_attr(dentry);
 	struct config_item * item = to_item(dentry->d_parent);
-	struct configfs_item_operations * ops = buffer->ops;
 
-	return ops->store_attribute(item,attr,buffer->page,count);
+	return attr->store(item, buffer->page, count);
 }
 
 
@@ -210,10 +295,80 @@ configfs_write_file(struct file *file, const char __user *buf, size_t count, lof
 	return len;
 }
 
-static int check_perm(struct inode * inode, struct file * file)
+/**
+ *	configfs_write_bin_file - write a binary attribute.
+ *	@file:	file pointer
+ *	@buf:	data to write
+ *	@count:	number of bytes
+ *	@ppos:	starting offset
+ *
+ *	Writing to a binary attribute file is similar to a normal read.
+ *	We buffer the consecutive writes (binary attribute files do not
+ *	support lseek) in a continuously growing buffer, but we don't
+ *	commit until the close of the file.
+ */
+
+static ssize_t
+configfs_write_bin_file(struct file *file, const char __user *buf,
+			size_t count, loff_t *ppos)
+{
+	struct configfs_buffer *buffer = file->private_data;
+	struct dentry *dentry = file->f_path.dentry;
+	struct configfs_bin_attribute *bin_attr = to_bin_attr(dentry);
+	void *tbuf = NULL;
+	ssize_t len;
+
+	mutex_lock(&buffer->mutex);
+
+	/* we don't support switching read/write modes */
+	if (buffer->read_in_progress) {
+		len = -ETXTBSY;
+		goto out;
+	}
+	buffer->write_in_progress = 1;
+
+	/* buffer grows? */
+	if (*ppos + count > buffer->bin_buffer_size) {
+
+		if (bin_attr->cb_max_size &&
+			*ppos + count > bin_attr->cb_max_size) {
+			len = -EFBIG;
+		}
+
+		tbuf = vmalloc(*ppos + count);
+		if (tbuf == NULL) {
+			len = -ENOMEM;
+			goto out;
+		}
+
+		/* copy old contents */
+		if (buffer->bin_buffer) {
+			memcpy(tbuf, buffer->bin_buffer,
+				buffer->bin_buffer_size);
+			vfree(buffer->bin_buffer);
+		}
+
+		/* clear the new area */
+		memset(tbuf + buffer->bin_buffer_size, 0,
+			*ppos + count - buffer->bin_buffer_size);
+		buffer->bin_buffer = tbuf;
+		buffer->bin_buffer_size = *ppos + count;
+	}
+
+	len = simple_write_to_buffer(buffer->bin_buffer,
+			buffer->bin_buffer_size, ppos, buf, count);
+	if (len > 0)
+		*ppos += len;
+out:
+	mutex_unlock(&buffer->mutex);
+	return len;
+}
+
+static int check_perm(struct inode * inode, struct file * file, int type)
 {
 	struct config_item *item = configfs_get_config_item(file->f_path.dentry->d_parent);
 	struct configfs_attribute * attr = to_attr(file->f_path.dentry);
+	struct configfs_bin_attribute *bin_attr = NULL;
 	struct configfs_buffer * buffer;
 	struct configfs_item_operations * ops = NULL;
 	int error = 0;
@@ -221,6 +376,9 @@ static int check_perm(struct inode * inode, struct file * file)
 	if (!item || !attr)
 		goto Einval;
 
+	if (type & CONFIGFS_ITEM_BIN_ATTR)
+		bin_attr = to_bin_attr(file->f_path.dentry);
+
 	/* Grab the module reference for this attribute if we have one */
 	if (!try_module_get(attr->ca_owner)) {
 		error = -ENODEV;
@@ -237,10 +395,14 @@ static int check_perm(struct inode * inode, struct file * file)
 	 * and we must have a store method.
 	 */
 	if (file->f_mode & FMODE_WRITE) {
+		if (!(inode->i_mode & S_IWUGO))
+			goto Eaccess;
 
-		if (!(inode->i_mode & S_IWUGO) || !ops->store_attribute)
+		if ((type & CONFIGFS_ITEM_ATTR) && !attr->store)
 			goto Eaccess;
 
+		if ((type & CONFIGFS_ITEM_BIN_ATTR) && !bin_attr->write)
+			goto Eaccess;
 	}
 
 	/* File needs read support.
@@ -248,7 +410,13 @@ static int check_perm(struct inode * inode, struct file * file)
 	 * must be a show method for it.
 	 */
 	if (file->f_mode & FMODE_READ) {
-		if (!(inode->i_mode & S_IRUGO) || !ops->show_attribute)
+		if (!(inode->i_mode & S_IRUGO))
+			goto Eaccess;
+
+		if ((type & CONFIGFS_ITEM_ATTR) && !attr->show)
+			goto Eaccess;
+
+		if ((type & CONFIGFS_ITEM_BIN_ATTR) && !bin_attr->read)
 			goto Eaccess;
 	}
 
@@ -262,6 +430,8 @@ static int check_perm(struct inode * inode, struct file * file)
 	}
 	mutex_init(&buffer->mutex);
 	buffer->needs_read_fill = 1;
+	buffer->read_in_progress = 0;
+	buffer->write_in_progress = 0;
 	buffer->ops = ops;
 	file->private_data = buffer;
 	goto Done;
@@ -279,12 +449,7 @@ static int check_perm(struct inode * inode, struct file * file)
 	return error;
 }
 
-static int configfs_open_file(struct inode * inode, struct file * filp)
-{
-	return check_perm(inode,filp);
-}
-
-static int configfs_release(struct inode * inode, struct file * filp)
+static int configfs_release(struct inode *inode, struct file *filp)
 {
 	struct config_item * item = to_item(filp->f_path.dentry->d_parent);
 	struct configfs_attribute * attr = to_attr(filp->f_path.dentry);
@@ -305,6 +470,47 @@ static int configfs_release(struct inode * inode, struct file * filp)
 	return 0;
 }
 
+static int configfs_open_file(struct inode *inode, struct file *filp)
+{
+	return check_perm(inode, filp, CONFIGFS_ITEM_ATTR);
+}
+
+static int configfs_open_bin_file(struct inode *inode, struct file *filp)
+{
+	return check_perm(inode, filp, CONFIGFS_ITEM_BIN_ATTR);
+}
+
+static int configfs_release_bin_file(struct inode *inode, struct file *filp)
+{
+	struct configfs_buffer *buffer = filp->private_data;
+	struct dentry *dentry = filp->f_path.dentry;
+	struct config_item *item = to_item(dentry->d_parent);
+	struct configfs_bin_attribute *bin_attr = to_bin_attr(dentry);
+	ssize_t len = 0;
+	int ret;
+
+	buffer->read_in_progress = 0;
+
+	if (buffer->write_in_progress) {
+		buffer->write_in_progress = 0;
+
+		len = bin_attr->write(item, buffer->bin_buffer,
+				buffer->bin_buffer_size);
+
+		/* vfree on NULL is safe */
+		vfree(buffer->bin_buffer);
+		buffer->bin_buffer = NULL;
+		buffer->bin_buffer_size = 0;
+		buffer->needs_read_fill = 1;
+	}
+
+	ret = configfs_release(inode, filp);
+	if (len < 0)
+		return len;
+	return ret;
+}
+
+
 const struct file_operations configfs_file_operations = {
 	.read		= configfs_read_file,
 	.write		= configfs_write_file,
@@ -313,6 +519,14 @@ const struct file_operations configfs_file_operations = {
 	.release	= configfs_release,
 };
 
+const struct file_operations configfs_bin_file_operations = {
+	.read		= configfs_read_bin_file,
+	.write		= configfs_write_bin_file,
+	.llseek		= NULL,		/* bin file is not seekable */
+	.open		= configfs_open_bin_file,
+	.release	= configfs_release_bin_file,
+};
+
 /**
  *	configfs_create_file - create an attribute file for an item.
  *	@item:	item we're creating for.
@@ -326,11 +540,32 @@ int configfs_create_file(struct config_item * item, const struct configfs_attrib
 	umode_t mode = (attr->ca_mode & S_IALLUGO) | S_IFREG;
 	int error = 0;
 
-	mutex_lock_nested(&d_inode(dir)->i_mutex, I_MUTEX_NORMAL);
+	inode_lock_nested(d_inode(dir), I_MUTEX_NORMAL);
 	error = configfs_make_dirent(parent_sd, NULL, (void *) attr, mode,
 				     CONFIGFS_ITEM_ATTR);
-	mutex_unlock(&d_inode(dir)->i_mutex);
+	inode_unlock(d_inode(dir));
 
 	return error;
 }
 
+/**
+ *	configfs_create_bin_file - create a binary attribute file for an item.
+ *	@item:	item we're creating for.
+ *	@attr:	atrribute descriptor.
+ */
+
+int configfs_create_bin_file(struct config_item *item,
+		const struct configfs_bin_attribute *bin_attr)
+{
+	struct dentry *dir = item->ci_dentry;
+	struct configfs_dirent *parent_sd = dir->d_fsdata;
+	umode_t mode = (bin_attr->cb_attr.ca_mode & S_IALLUGO) | S_IFREG;
+	int error = 0;
+
+	inode_lock_nested(dir->d_inode, I_MUTEX_NORMAL);
+	error = configfs_make_dirent(parent_sd, NULL, (void *) bin_attr, mode,
+				     CONFIGFS_ITEM_BIN_ATTR);
+	inode_unlock(dir->d_inode);
+
+	return error;
+}
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index eae87575e681..03d124ae27d7 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -75,7 +75,8 @@ int configfs_setattr(struct dentry * dentry, struct iattr * iattr)
 		sd_iattr->ia_mode = sd->s_mode;
 		sd_iattr->ia_uid = GLOBAL_ROOT_UID;
 		sd_iattr->ia_gid = GLOBAL_ROOT_GID;
-		sd_iattr->ia_atime = sd_iattr->ia_mtime = sd_iattr->ia_ctime = CURRENT_TIME;
+		sd_iattr->ia_atime = sd_iattr->ia_mtime =
+			sd_iattr->ia_ctime = current_fs_time(inode->i_sb);
 		sd->s_iattr = sd_iattr;
 	}
 	/* attributes were changed atleast once in past */
@@ -111,7 +112,8 @@ int configfs_setattr(struct dentry * dentry, struct iattr * iattr)
 static inline void set_default_inode_attr(struct inode * inode, umode_t mode)
 {
 	inode->i_mode = mode;
-	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+	inode->i_atime = inode->i_mtime =
+		inode->i_ctime = current_fs_time(inode->i_sb);
 }
 
 static inline void set_inode_attr(struct inode * inode, struct iattr * iattr)
@@ -195,13 +197,21 @@ int configfs_create(struct dentry * dentry, umode_t mode, void (*init)(struct in
 		return -ENOMEM;
 
 	p_inode = d_inode(dentry->d_parent);
-	p_inode->i_mtime = p_inode->i_ctime = CURRENT_TIME;
+	p_inode->i_mtime = p_inode->i_ctime = current_fs_time(p_inode->i_sb);
 	configfs_set_inode_lock_class(sd, inode);
 
 	init(inode);
-	d_instantiate(dentry, inode);
-	if (S_ISDIR(mode) || S_ISLNK(mode))
+	if (S_ISDIR(mode) || S_ISLNK(mode)) {
+		/*
+		 * ->symlink(), ->mkdir(), configfs_register_subsystem() or
+		 * create_default_group() - already hashed.
+		 */
+		d_instantiate(dentry, inode);
 		dget(dentry);  /* pin link and directory dentries in core */
+	} else {
+		/* ->lookup() */
+		d_add(dentry, inode);
+	}
 	return error;
 }
 
@@ -218,7 +228,7 @@ const unsigned char * configfs_get_name(struct configfs_dirent *sd)
 	if (sd->s_type & (CONFIGFS_DIR | CONFIGFS_ITEM_LINK))
 		return sd->s_dentry->d_name.name;
 
-	if (sd->s_type & CONFIGFS_ITEM_ATTR) {
+	if (sd->s_type & (CONFIGFS_ITEM_ATTR | CONFIGFS_ITEM_BIN_ATTR)) {
 		attr = sd->s_element;
 		return attr->ca_name;
 	}
@@ -255,7 +265,7 @@ void configfs_hash_and_remove(struct dentry * dir, const char * name)
 		/* no inode means this hasn't been made visible yet */
 		return;
 
-	mutex_lock(&d_inode(dir)->i_mutex);
+	inode_lock(d_inode(dir));
 	list_for_each_entry(sd, &parent_sd->s_children, s_sibling) {
 		if (!sd->s_element)
 			continue;
@@ -268,5 +278,5 @@ void configfs_hash_and_remove(struct dentry * dir, const char * name)
 			break;
 		}
 	}
-	mutex_unlock(&d_inode(dir)->i_mutex);
+	inode_unlock(d_inode(dir));
 }
diff --git a/fs/configfs/item.c b/fs/configfs/item.c
index b863a09cd2f1..8b2a994042dd 100644
--- a/fs/configfs/item.c
+++ b/fs/configfs/item.c
@@ -182,6 +182,7 @@ void config_group_init(struct config_group *group)
 {
 	config_item_init(&group->cg_item);
 	INIT_LIST_HEAD(&group->cg_children);
+	INIT_LIST_HEAD(&group->default_groups);
 }
 EXPORT_SYMBOL(config_group_init);
 
diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
index a8f3b589a2df..cfd91320e869 100644
--- a/fs/configfs/mount.c
+++ b/fs/configfs/mount.c
@@ -71,8 +71,8 @@ static int configfs_fill_super(struct super_block *sb, void *data, int silent)
 	struct inode *inode;
 	struct dentry *root;
 
-	sb->s_blocksize = PAGE_CACHE_SIZE;
-	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
+	sb->s_blocksize = PAGE_SIZE;
+	sb->s_blocksize_bits = PAGE_SHIFT;
 	sb->s_magic = CONFIGFS_MAGIC;
 	sb->s_op = &configfs_ops;
 	sb->s_time_gran = 1;
diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
index ec5c8325b503..db6d69289608 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -279,27 +279,33 @@ static int configfs_getlink(struct dentry *dentry, char * path)
 
 }
 
-static const char *configfs_follow_link(struct dentry *dentry, void **cookie)
+static const char *configfs_get_link(struct dentry *dentry,
+				     struct inode *inode,
+				     struct delayed_call *done)
 {
-	unsigned long page = get_zeroed_page(GFP_KERNEL);
+	char *body;
 	int error;
 
-	if (!page)
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
+	body = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!body)
 		return ERR_PTR(-ENOMEM);
 
-	error = configfs_getlink(dentry, (char *)page);
+	error = configfs_getlink(dentry, body);
 	if (!error) {
-		return *cookie = (void *)page;
+		set_delayed_call(done, kfree_link, body);
+		return body;
 	}
 
-	free_page(page);
+	kfree(body);
 	return ERR_PTR(error);
 }
 
 const struct inode_operations configfs_symlink_inode_operations = {
-	.follow_link = configfs_follow_link,
+	.get_link = configfs_get_link,
 	.readlink = generic_readlink,
-	.put_link = free_page_put_link,
 	.setattr = configfs_setattr,
 };
 
diff --git a/fs/coredump.c b/fs/coredump.c
index a8f75640ac86..47c32c3bfa1d 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -32,6 +32,10 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/oom.h>
 #include <linux/compat.h>
+#include <linux/sched.h>
+#include <linux/fs.h>
+#include <linux/path.h>
+#include <linux/timekeeping.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
@@ -117,6 +121,26 @@ int cn_esc_printf(struct core_name *cn, const char *fmt, ...)
 	ret = cn_vprintf(cn, fmt, arg);
 	va_end(arg);
 
+	if (ret == 0) {
+		/*
+		 * Ensure that this coredump name component can't cause the
+		 * resulting corefile path to consist of a ".." or ".".
+		 */
+		if ((cn->used - cur == 1 && cn->corename[cur] == '.') ||
+				(cn->used - cur == 2 && cn->corename[cur] == '.'
+				&& cn->corename[cur+1] == '.'))
+			cn->corename[cur] = '!';
+
+		/*
+		 * Empty names are fishy and could be used to create a "//" in a
+		 * corefile name, causing the coredump to happen one directory
+		 * level too high. Enforce that all components of the core
+		 * pattern are at least one character long.
+		 */
+		if (cn->used == cur)
+			ret = cn_printf(cn, "!");
+	}
+
 	for (; cur < cn->used; ++cur) {
 		if (cn->corename[cur] == '/')
 			cn->corename[cur] = '!';
@@ -232,9 +256,10 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm)
 				break;
 			/* UNIX time of coredump */
 			case 't': {
-				struct timeval tv;
-				do_gettimeofday(&tv);
-				err = cn_printf(cn, "%lu", tv.tv_sec);
+				time64_t time;
+
+				time = ktime_get_real_seconds();
+				err = cn_printf(cn, "%lld", time);
 				break;
 			}
 			/* hostname */
@@ -280,23 +305,24 @@ out:
 	return ispipe;
 }
 
-static int zap_process(struct task_struct *start, int exit_code)
+static int zap_process(struct task_struct *start, int exit_code, int flags)
 {
 	struct task_struct *t;
 	int nr = 0;
 
+	/* ignore all signals except SIGKILL, see prepare_signal() */
+	start->signal->flags = SIGNAL_GROUP_COREDUMP | flags;
 	start->signal->group_exit_code = exit_code;
 	start->signal->group_stop_count = 0;
 
-	t = start;
-	do {
+	for_each_thread(start, t) {
 		task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
 		if (t != current && t->mm) {
 			sigaddset(&t->pending.signal, SIGKILL);
 			signal_wake_up(t, 1);
 			nr++;
 		}
-	} while_each_thread(start, t);
+	}
 
 	return nr;
 }
@@ -311,10 +337,8 @@ static int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
 	spin_lock_irq(&tsk->sighand->siglock);
 	if (!signal_group_exit(tsk->signal)) {
 		mm->core_state = core_state;
-		nr = zap_process(tsk, exit_code);
 		tsk->signal->group_exit_task = tsk;
-		/* ignore all signals except SIGKILL, see prepare_signal() */
-		tsk->signal->flags = SIGNAL_GROUP_COREDUMP;
+		nr = zap_process(tsk, exit_code, 0);
 		clear_tsk_thread_flag(tsk, TIF_SIGPENDING);
 	}
 	spin_unlock_irq(&tsk->sighand->siglock);
@@ -360,18 +384,18 @@ static int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
 			continue;
 		if (g->flags & PF_KTHREAD)
 			continue;
-		p = g;
-		do {
-			if (p->mm) {
-				if (unlikely(p->mm == mm)) {
-					lock_task_sighand(p, &flags);
-					nr += zap_process(p, exit_code);
-					p->signal->flags = SIGNAL_GROUP_EXIT;
-					unlock_task_sighand(p, &flags);
-				}
-				break;
+
+		for_each_thread(g, p) {
+			if (unlikely(!p->mm))
+				continue;
+			if (unlikely(p->mm == mm)) {
+				lock_task_sighand(p, &flags);
+				nr += zap_process(p, exit_code,
+							SIGNAL_GROUP_EXIT);
+				unlock_task_sighand(p, &flags);
 			}
-		} while_each_thread(g, p);
+			break;
+		}
 	}
 	rcu_read_unlock();
 done:
@@ -628,6 +652,8 @@ void do_coredump(const siginfo_t *siginfo)
 		}
 	} else {
 		struct inode *inode;
+		int open_flags = O_CREAT | O_RDWR | O_NOFOLLOW |
+				 O_LARGEFILE | O_EXCL;
 
 		if (cprm.limit < binfmt->min_coredump)
 			goto fail_unlock;
@@ -666,10 +692,27 @@ void do_coredump(const siginfo_t *siginfo)
 		 * what matters is that at least one of the two processes
 		 * writes its coredump successfully, not which one.
 		 */
-		cprm.file = filp_open(cn.corename,
-				 O_CREAT | 2 | O_NOFOLLOW |
-				 O_LARGEFILE | O_EXCL,
-				 0600);
+		if (need_suid_safe) {
+			/*
+			 * Using user namespaces, normal user tasks can change
+			 * their current->fs->root to point to arbitrary
+			 * directories. Since the intention of the "only dump
+			 * with a fully qualified path" rule is to control where
+			 * coredumps may be placed using root privileges,
+			 * current->fs->root must not be used. Instead, use the
+			 * root directory of init_task.
+			 */
+			struct path root;
+
+			task_lock(&init_task);
+			get_fs_root(init_task.fs, &root);
+			task_unlock(&init_task);
+			cprm.file = file_open_root(root.dentry, root.mnt,
+				cn.corename, open_flags, 0600);
+			path_put(&root);
+		} else {
+			cprm.file = filp_open(cn.corename, open_flags, 0600);
+		}
 		if (IS_ERR(cprm.file))
 			goto fail_unlock;
 
diff --git a/fs/cramfs/README b/fs/cramfs/README
index 445d1c2d7646..9d4e7ea311f4 100644
--- a/fs/cramfs/README
+++ b/fs/cramfs/README
@@ -86,26 +86,26 @@ Block Size
 
 (Block size in cramfs refers to the size of input data that is
 compressed at a time.  It's intended to be somewhere around
-PAGE_CACHE_SIZE for cramfs_readpage's convenience.)
+PAGE_SIZE for cramfs_readpage's convenience.)
 
 The superblock ought to indicate the block size that the fs was
 written for, since comments in <linux/pagemap.h> indicate that
-PAGE_CACHE_SIZE may grow in future (if I interpret the comment
+PAGE_SIZE may grow in future (if I interpret the comment
 correctly).
 
-Currently, mkcramfs #define's PAGE_CACHE_SIZE as 4096 and uses that
-for blksize, whereas Linux-2.3.39 uses its PAGE_CACHE_SIZE, which in
+Currently, mkcramfs #define's PAGE_SIZE as 4096 and uses that
+for blksize, whereas Linux-2.3.39 uses its PAGE_SIZE, which in
 turn is defined as PAGE_SIZE (which can be as large as 32KB on arm).
 This discrepancy is a bug, though it's not clear which should be
 changed.
 
-One option is to change mkcramfs to take its PAGE_CACHE_SIZE from
+One option is to change mkcramfs to take its PAGE_SIZE from
 <asm/page.h>.  Personally I don't like this option, but it does
 require the least amount of change: just change `#define
-PAGE_CACHE_SIZE (4096)' to `#include <asm/page.h>'.  The disadvantage
+PAGE_SIZE (4096)' to `#include <asm/page.h>'.  The disadvantage
 is that the generated cramfs cannot always be shared between different
 kernels, not even necessarily kernels of the same architecture if
-PAGE_CACHE_SIZE is subject to change between kernel versions
+PAGE_SIZE is subject to change between kernel versions
 (currently possible with arm and ia64).
 
 The remaining options try to make cramfs more sharable.
@@ -126,22 +126,22 @@ size.  The options are:
   1. Always 4096 bytes.
 
   2. Writer chooses blocksize; kernel adapts but rejects blocksize >
-     PAGE_CACHE_SIZE.
+     PAGE_SIZE.
 
   3. Writer chooses blocksize; kernel adapts even to blocksize >
-     PAGE_CACHE_SIZE.
+     PAGE_SIZE.
 
 It's easy enough to change the kernel to use a smaller value than
-PAGE_CACHE_SIZE: just make cramfs_readpage read multiple blocks.
+PAGE_SIZE: just make cramfs_readpage read multiple blocks.
 
-The cost of option 1 is that kernels with a larger PAGE_CACHE_SIZE
+The cost of option 1 is that kernels with a larger PAGE_SIZE
 value don't get as good compression as they can.
 
 The cost of option 2 relative to option 1 is that the code uses
 variables instead of #define'd constants.  The gain is that people
-with kernels having larger PAGE_CACHE_SIZE can make use of that if
+with kernels having larger PAGE_SIZE can make use of that if
 they don't mind their cramfs being inaccessible to kernels with
-smaller PAGE_CACHE_SIZE values.
+smaller PAGE_SIZE values.
 
 Option 3 is easy to implement if we don't mind being CPU-inefficient:
 e.g. get readpage to decompress to a buffer of size MAX_BLKSIZE (which
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 355c522f3585..3a32ddf98095 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -100,6 +100,7 @@ static struct inode *get_cramfs_inode(struct super_block *sb,
 		break;
 	case S_IFLNK:
 		inode->i_op = &page_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_data.a_ops = &cramfs_aops;
 		break;
 	default:
@@ -136,7 +137,7 @@ static struct inode *get_cramfs_inode(struct super_block *sb,
  * page cache and dentry tree anyway..
  *
  * This also acts as a way to guarantee contiguous areas of up to
- * BLKS_PER_BUF*PAGE_CACHE_SIZE, so that the caller doesn't need to
+ * BLKS_PER_BUF*PAGE_SIZE, so that the caller doesn't need to
  * worry about end-of-buffer issues even when decompressing a full
  * page cache.
  */
@@ -151,7 +152,7 @@ static struct inode *get_cramfs_inode(struct super_block *sb,
  */
 #define BLKS_PER_BUF_SHIFT	(2)
 #define BLKS_PER_BUF		(1 << BLKS_PER_BUF_SHIFT)
-#define BUFFER_SIZE		(BLKS_PER_BUF*PAGE_CACHE_SIZE)
+#define BUFFER_SIZE		(BLKS_PER_BUF*PAGE_SIZE)
 
 static unsigned char read_buffers[READ_BUFFERS][BUFFER_SIZE];
 static unsigned buffer_blocknr[READ_BUFFERS];
@@ -172,8 +173,8 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i
 
 	if (!len)
 		return NULL;
-	blocknr = offset >> PAGE_CACHE_SHIFT;
-	offset &= PAGE_CACHE_SIZE - 1;
+	blocknr = offset >> PAGE_SHIFT;
+	offset &= PAGE_SIZE - 1;
 
 	/* Check if an existing buffer already has the data.. */
 	for (i = 0; i < READ_BUFFERS; i++) {
@@ -183,14 +184,14 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i
 			continue;
 		if (blocknr < buffer_blocknr[i])
 			continue;
-		blk_offset = (blocknr - buffer_blocknr[i]) << PAGE_CACHE_SHIFT;
+		blk_offset = (blocknr - buffer_blocknr[i]) << PAGE_SHIFT;
 		blk_offset += offset;
 		if (blk_offset + len > BUFFER_SIZE)
 			continue;
 		return read_buffers[i] + blk_offset;
 	}
 
-	devsize = mapping->host->i_size >> PAGE_CACHE_SHIFT;
+	devsize = mapping->host->i_size >> PAGE_SHIFT;
 
 	/* Ok, read in BLKS_PER_BUF pages completely first. */
 	for (i = 0; i < BLKS_PER_BUF; i++) {
@@ -212,7 +213,7 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i
 			wait_on_page_locked(page);
 			if (!PageUptodate(page)) {
 				/* asynchronous error */
-				page_cache_release(page);
+				put_page(page);
 				pages[i] = NULL;
 			}
 		}
@@ -228,12 +229,12 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i
 		struct page *page = pages[i];
 
 		if (page) {
-			memcpy(data, kmap(page), PAGE_CACHE_SIZE);
+			memcpy(data, kmap(page), PAGE_SIZE);
 			kunmap(page);
-			page_cache_release(page);
+			put_page(page);
 		} else
-			memset(data, 0, PAGE_CACHE_SIZE);
-		data += PAGE_CACHE_SIZE;
+			memset(data, 0, PAGE_SIZE);
+		data += PAGE_SIZE;
 	}
 	return read_buffers[buffer] + offset;
 }
@@ -352,7 +353,7 @@ static int cramfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 
 	buf->f_type = CRAMFS_MAGIC;
-	buf->f_bsize = PAGE_CACHE_SIZE;
+	buf->f_bsize = PAGE_SIZE;
 	buf->f_blocks = CRAMFS_SB(sb)->blocks;
 	buf->f_bfree = 0;
 	buf->f_bavail = 0;
@@ -495,7 +496,7 @@ static int cramfs_readpage(struct file *file, struct page *page)
 	int bytes_filled;
 	void *pgdata;
 
-	maxblock = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	maxblock = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	bytes_filled = 0;
 	pgdata = kmap(page);
 
@@ -515,14 +516,14 @@ static int cramfs_readpage(struct file *file, struct page *page)
 
 		if (compr_len == 0)
 			; /* hole */
-		else if (unlikely(compr_len > (PAGE_CACHE_SIZE << 1))) {
+		else if (unlikely(compr_len > (PAGE_SIZE << 1))) {
 			pr_err("bad compressed blocksize %u\n",
 				compr_len);
 			goto err;
 		} else {
 			mutex_lock(&read_mutex);
 			bytes_filled = cramfs_uncompress_block(pgdata,
-				 PAGE_CACHE_SIZE,
+				 PAGE_SIZE,
 				 cramfs_read(sb, start_offset, compr_len),
 				 compr_len);
 			mutex_unlock(&read_mutex);
@@ -531,7 +532,7 @@ static int cramfs_readpage(struct file *file, struct page *page)
 		}
 	}
 
-	memset(pgdata + bytes_filled, 0, PAGE_CACHE_SIZE - bytes_filled);
+	memset(pgdata + bytes_filled, 0, PAGE_SIZE - bytes_filled);
 	flush_dcache_page(page);
 	kunmap(page);
 	SetPageUptodate(page);
diff --git a/fs/crypto/Kconfig b/fs/crypto/Kconfig
new file mode 100644
index 000000000000..92348faf9865
--- /dev/null
+++ b/fs/crypto/Kconfig
@@ -0,0 +1,18 @@
+config FS_ENCRYPTION
+	tristate "FS Encryption (Per-file encryption)"
+	depends on BLOCK
+	select CRYPTO
+	select CRYPTO_AES
+	select CRYPTO_CBC
+	select CRYPTO_ECB
+	select CRYPTO_XTS
+	select CRYPTO_CTS
+	select CRYPTO_CTR
+	select CRYPTO_SHA256
+	select KEYS
+	select ENCRYPTED_KEYS
+	help
+	  Enable encryption of files and directories.  This
+	  feature is similar to ecryptfs, but it is more memory
+	  efficient since it avoids caching the encrypted and
+	  decrypted pages in the page cache.
diff --git a/fs/crypto/Makefile b/fs/crypto/Makefile
new file mode 100644
index 000000000000..f17684c48739
--- /dev/null
+++ b/fs/crypto/Makefile
@@ -0,0 +1,3 @@
+obj-$(CONFIG_FS_ENCRYPTION)	+= fscrypto.o
+
+fscrypto-y := crypto.o fname.o policy.o keyinfo.o
diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
new file mode 100644
index 000000000000..2fc8c43ce531
--- /dev/null
+++ b/fs/crypto/crypto.c
@@ -0,0 +1,568 @@
+/*
+ * This contains encryption functions for per-file encryption.
+ *
+ * Copyright (C) 2015, Google, Inc.
+ * Copyright (C) 2015, Motorola Mobility
+ *
+ * Written by Michael Halcrow, 2014.
+ *
+ * Filename encryption additions
+ *	Uday Savagaonkar, 2014
+ * Encryption policy handling additions
+ *	Ildar Muslukhov, 2014
+ * Add fscrypt_pullback_bio_page()
+ *	Jaegeuk Kim, 2015.
+ *
+ * This has not yet undergone a rigorous security audit.
+ *
+ * The usage of AES-XTS should conform to recommendations in NIST
+ * Special Publication 800-38E and IEEE P1619/D16.
+ */
+
+#include <linux/pagemap.h>
+#include <linux/mempool.h>
+#include <linux/module.h>
+#include <linux/scatterlist.h>
+#include <linux/ratelimit.h>
+#include <linux/bio.h>
+#include <linux/dcache.h>
+#include <linux/namei.h>
+#include <linux/fscrypto.h>
+#include <linux/ecryptfs.h>
+
+static unsigned int num_prealloc_crypto_pages = 32;
+static unsigned int num_prealloc_crypto_ctxs = 128;
+
+module_param(num_prealloc_crypto_pages, uint, 0444);
+MODULE_PARM_DESC(num_prealloc_crypto_pages,
+		"Number of crypto pages to preallocate");
+module_param(num_prealloc_crypto_ctxs, uint, 0444);
+MODULE_PARM_DESC(num_prealloc_crypto_ctxs,
+		"Number of crypto contexts to preallocate");
+
+static mempool_t *fscrypt_bounce_page_pool = NULL;
+
+static LIST_HEAD(fscrypt_free_ctxs);
+static DEFINE_SPINLOCK(fscrypt_ctx_lock);
+
+static struct workqueue_struct *fscrypt_read_workqueue;
+static DEFINE_MUTEX(fscrypt_init_mutex);
+
+static struct kmem_cache *fscrypt_ctx_cachep;
+struct kmem_cache *fscrypt_info_cachep;
+
+/**
+ * fscrypt_release_ctx() - Releases an encryption context
+ * @ctx: The encryption context to release.
+ *
+ * If the encryption context was allocated from the pre-allocated pool, returns
+ * it to that pool. Else, frees it.
+ *
+ * If there's a bounce page in the context, this frees that.
+ */
+void fscrypt_release_ctx(struct fscrypt_ctx *ctx)
+{
+	unsigned long flags;
+
+	if (ctx->flags & FS_WRITE_PATH_FL && ctx->w.bounce_page) {
+		mempool_free(ctx->w.bounce_page, fscrypt_bounce_page_pool);
+		ctx->w.bounce_page = NULL;
+	}
+	ctx->w.control_page = NULL;
+	if (ctx->flags & FS_CTX_REQUIRES_FREE_ENCRYPT_FL) {
+		kmem_cache_free(fscrypt_ctx_cachep, ctx);
+	} else {
+		spin_lock_irqsave(&fscrypt_ctx_lock, flags);
+		list_add(&ctx->free_list, &fscrypt_free_ctxs);
+		spin_unlock_irqrestore(&fscrypt_ctx_lock, flags);
+	}
+}
+EXPORT_SYMBOL(fscrypt_release_ctx);
+
+/**
+ * fscrypt_get_ctx() - Gets an encryption context
+ * @inode:       The inode for which we are doing the crypto
+ * @gfp_flags:   The gfp flag for memory allocation
+ *
+ * Allocates and initializes an encryption context.
+ *
+ * Return: An allocated and initialized encryption context on success; error
+ * value or NULL otherwise.
+ */
+struct fscrypt_ctx *fscrypt_get_ctx(struct inode *inode, gfp_t gfp_flags)
+{
+	struct fscrypt_ctx *ctx = NULL;
+	struct fscrypt_info *ci = inode->i_crypt_info;
+	unsigned long flags;
+
+	if (ci == NULL)
+		return ERR_PTR(-ENOKEY);
+
+	/*
+	 * We first try getting the ctx from a free list because in
+	 * the common case the ctx will have an allocated and
+	 * initialized crypto tfm, so it's probably a worthwhile
+	 * optimization. For the bounce page, we first try getting it
+	 * from the kernel allocator because that's just about as fast
+	 * as getting it from a list and because a cache of free pages
+	 * should generally be a "last resort" option for a filesystem
+	 * to be able to do its job.
+	 */
+	spin_lock_irqsave(&fscrypt_ctx_lock, flags);
+	ctx = list_first_entry_or_null(&fscrypt_free_ctxs,
+					struct fscrypt_ctx, free_list);
+	if (ctx)
+		list_del(&ctx->free_list);
+	spin_unlock_irqrestore(&fscrypt_ctx_lock, flags);
+	if (!ctx) {
+		ctx = kmem_cache_zalloc(fscrypt_ctx_cachep, gfp_flags);
+		if (!ctx)
+			return ERR_PTR(-ENOMEM);
+		ctx->flags |= FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
+	} else {
+		ctx->flags &= ~FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
+	}
+	ctx->flags &= ~FS_WRITE_PATH_FL;
+	return ctx;
+}
+EXPORT_SYMBOL(fscrypt_get_ctx);
+
+/**
+ * fscrypt_complete() - The completion callback for page encryption
+ * @req: The asynchronous encryption request context
+ * @res: The result of the encryption operation
+ */
+static void fscrypt_complete(struct crypto_async_request *req, int res)
+{
+	struct fscrypt_completion_result *ecr = req->data;
+
+	if (res == -EINPROGRESS)
+		return;
+	ecr->res = res;
+	complete(&ecr->completion);
+}
+
+typedef enum {
+	FS_DECRYPT = 0,
+	FS_ENCRYPT,
+} fscrypt_direction_t;
+
+static int do_page_crypto(struct inode *inode,
+			fscrypt_direction_t rw, pgoff_t index,
+			struct page *src_page, struct page *dest_page,
+			gfp_t gfp_flags)
+{
+	u8 xts_tweak[FS_XTS_TWEAK_SIZE];
+	struct skcipher_request *req = NULL;
+	DECLARE_FS_COMPLETION_RESULT(ecr);
+	struct scatterlist dst, src;
+	struct fscrypt_info *ci = inode->i_crypt_info;
+	struct crypto_skcipher *tfm = ci->ci_ctfm;
+	int res = 0;
+
+	req = skcipher_request_alloc(tfm, gfp_flags);
+	if (!req) {
+		printk_ratelimited(KERN_ERR
+				"%s: crypto_request_alloc() failed\n",
+				__func__);
+		return -ENOMEM;
+	}
+
+	skcipher_request_set_callback(
+		req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+		fscrypt_complete, &ecr);
+
+	BUILD_BUG_ON(FS_XTS_TWEAK_SIZE < sizeof(index));
+	memcpy(xts_tweak, &index, sizeof(index));
+	memset(&xts_tweak[sizeof(index)], 0,
+			FS_XTS_TWEAK_SIZE - sizeof(index));
+
+	sg_init_table(&dst, 1);
+	sg_set_page(&dst, dest_page, PAGE_SIZE, 0);
+	sg_init_table(&src, 1);
+	sg_set_page(&src, src_page, PAGE_SIZE, 0);
+	skcipher_request_set_crypt(req, &src, &dst, PAGE_SIZE,
+					xts_tweak);
+	if (rw == FS_DECRYPT)
+		res = crypto_skcipher_decrypt(req);
+	else
+		res = crypto_skcipher_encrypt(req);
+	if (res == -EINPROGRESS || res == -EBUSY) {
+		BUG_ON(req->base.data != &ecr);
+		wait_for_completion(&ecr.completion);
+		res = ecr.res;
+	}
+	skcipher_request_free(req);
+	if (res) {
+		printk_ratelimited(KERN_ERR
+			"%s: crypto_skcipher_encrypt() returned %d\n",
+			__func__, res);
+		return res;
+	}
+	return 0;
+}
+
+static struct page *alloc_bounce_page(struct fscrypt_ctx *ctx, gfp_t gfp_flags)
+{
+	ctx->w.bounce_page = mempool_alloc(fscrypt_bounce_page_pool, gfp_flags);
+	if (ctx->w.bounce_page == NULL)
+		return ERR_PTR(-ENOMEM);
+	ctx->flags |= FS_WRITE_PATH_FL;
+	return ctx->w.bounce_page;
+}
+
+/**
+ * fscypt_encrypt_page() - Encrypts a page
+ * @inode:          The inode for which the encryption should take place
+ * @plaintext_page: The page to encrypt. Must be locked.
+ * @gfp_flags:      The gfp flag for memory allocation
+ *
+ * Allocates a ciphertext page and encrypts plaintext_page into it using the ctx
+ * encryption context.
+ *
+ * Called on the page write path.  The caller must call
+ * fscrypt_restore_control_page() on the returned ciphertext page to
+ * release the bounce buffer and the encryption context.
+ *
+ * Return: An allocated page with the encrypted content on success. Else, an
+ * error value or NULL.
+ */
+struct page *fscrypt_encrypt_page(struct inode *inode,
+				struct page *plaintext_page, gfp_t gfp_flags)
+{
+	struct fscrypt_ctx *ctx;
+	struct page *ciphertext_page = NULL;
+	int err;
+
+	BUG_ON(!PageLocked(plaintext_page));
+
+	ctx = fscrypt_get_ctx(inode, gfp_flags);
+	if (IS_ERR(ctx))
+		return (struct page *)ctx;
+
+	/* The encryption operation will require a bounce page. */
+	ciphertext_page = alloc_bounce_page(ctx, gfp_flags);
+	if (IS_ERR(ciphertext_page))
+		goto errout;
+
+	ctx->w.control_page = plaintext_page;
+	err = do_page_crypto(inode, FS_ENCRYPT, plaintext_page->index,
+					plaintext_page, ciphertext_page,
+					gfp_flags);
+	if (err) {
+		ciphertext_page = ERR_PTR(err);
+		goto errout;
+	}
+	SetPagePrivate(ciphertext_page);
+	set_page_private(ciphertext_page, (unsigned long)ctx);
+	lock_page(ciphertext_page);
+	return ciphertext_page;
+
+errout:
+	fscrypt_release_ctx(ctx);
+	return ciphertext_page;
+}
+EXPORT_SYMBOL(fscrypt_encrypt_page);
+
+/**
+ * f2crypt_decrypt_page() - Decrypts a page in-place
+ * @page: The page to decrypt. Must be locked.
+ *
+ * Decrypts page in-place using the ctx encryption context.
+ *
+ * Called from the read completion callback.
+ *
+ * Return: Zero on success, non-zero otherwise.
+ */
+int fscrypt_decrypt_page(struct page *page)
+{
+	BUG_ON(!PageLocked(page));
+
+	return do_page_crypto(page->mapping->host,
+			FS_DECRYPT, page->index, page, page, GFP_NOFS);
+}
+EXPORT_SYMBOL(fscrypt_decrypt_page);
+
+int fscrypt_zeroout_range(struct inode *inode, pgoff_t lblk,
+				sector_t pblk, unsigned int len)
+{
+	struct fscrypt_ctx *ctx;
+	struct page *ciphertext_page = NULL;
+	struct bio *bio;
+	int ret, err = 0;
+
+	BUG_ON(inode->i_sb->s_blocksize != PAGE_SIZE);
+
+	ctx = fscrypt_get_ctx(inode, GFP_NOFS);
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
+
+	ciphertext_page = alloc_bounce_page(ctx, GFP_NOWAIT);
+	if (IS_ERR(ciphertext_page)) {
+		err = PTR_ERR(ciphertext_page);
+		goto errout;
+	}
+
+	while (len--) {
+		err = do_page_crypto(inode, FS_ENCRYPT, lblk,
+					ZERO_PAGE(0), ciphertext_page,
+					GFP_NOFS);
+		if (err)
+			goto errout;
+
+		bio = bio_alloc(GFP_NOWAIT, 1);
+		if (!bio) {
+			err = -ENOMEM;
+			goto errout;
+		}
+		bio->bi_bdev = inode->i_sb->s_bdev;
+		bio->bi_iter.bi_sector =
+			pblk << (inode->i_sb->s_blocksize_bits - 9);
+		ret = bio_add_page(bio, ciphertext_page,
+					inode->i_sb->s_blocksize, 0);
+		if (ret != inode->i_sb->s_blocksize) {
+			/* should never happen! */
+			WARN_ON(1);
+			bio_put(bio);
+			err = -EIO;
+			goto errout;
+		}
+		err = submit_bio_wait(WRITE, bio);
+		if ((err == 0) && bio->bi_error)
+			err = -EIO;
+		bio_put(bio);
+		if (err)
+			goto errout;
+		lblk++;
+		pblk++;
+	}
+	err = 0;
+errout:
+	fscrypt_release_ctx(ctx);
+	return err;
+}
+EXPORT_SYMBOL(fscrypt_zeroout_range);
+
+/*
+ * Validate dentries for encrypted directories to make sure we aren't
+ * potentially caching stale data after a key has been added or
+ * removed.
+ */
+static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct dentry *dir;
+	struct fscrypt_info *ci;
+	int dir_has_key, cached_with_key;
+
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	dir = dget_parent(dentry);
+	if (!d_inode(dir)->i_sb->s_cop->is_encrypted(d_inode(dir))) {
+		dput(dir);
+		return 0;
+	}
+
+	ci = d_inode(dir)->i_crypt_info;
+	if (ci && ci->ci_keyring_key &&
+	    (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
+					  (1 << KEY_FLAG_REVOKED) |
+					  (1 << KEY_FLAG_DEAD))))
+		ci = NULL;
+
+	/* this should eventually be an flag in d_flags */
+	spin_lock(&dentry->d_lock);
+	cached_with_key = dentry->d_flags & DCACHE_ENCRYPTED_WITH_KEY;
+	spin_unlock(&dentry->d_lock);
+	dir_has_key = (ci != NULL);
+	dput(dir);
+
+	/*
+	 * If the dentry was cached without the key, and it is a
+	 * negative dentry, it might be a valid name.  We can't check
+	 * if the key has since been made available due to locking
+	 * reasons, so we fail the validation so ext4_lookup() can do
+	 * this check.
+	 *
+	 * We also fail the validation if the dentry was created with
+	 * the key present, but we no longer have the key, or vice versa.
+	 */
+	if ((!cached_with_key && d_is_negative(dentry)) ||
+			(!cached_with_key && dir_has_key) ||
+			(cached_with_key && !dir_has_key))
+		return 0;
+	return 1;
+}
+
+const struct dentry_operations fscrypt_d_ops = {
+	.d_revalidate = fscrypt_d_revalidate,
+};
+EXPORT_SYMBOL(fscrypt_d_ops);
+
+/*
+ * Call fscrypt_decrypt_page on every single page, reusing the encryption
+ * context.
+ */
+static void completion_pages(struct work_struct *work)
+{
+	struct fscrypt_ctx *ctx =
+		container_of(work, struct fscrypt_ctx, r.work);
+	struct bio *bio = ctx->r.bio;
+	struct bio_vec *bv;
+	int i;
+
+	bio_for_each_segment_all(bv, bio, i) {
+		struct page *page = bv->bv_page;
+		int ret = fscrypt_decrypt_page(page);
+
+		if (ret) {
+			WARN_ON_ONCE(1);
+			SetPageError(page);
+		} else {
+			SetPageUptodate(page);
+		}
+		unlock_page(page);
+	}
+	fscrypt_release_ctx(ctx);
+	bio_put(bio);
+}
+
+void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *ctx, struct bio *bio)
+{
+	INIT_WORK(&ctx->r.work, completion_pages);
+	ctx->r.bio = bio;
+	queue_work(fscrypt_read_workqueue, &ctx->r.work);
+}
+EXPORT_SYMBOL(fscrypt_decrypt_bio_pages);
+
+void fscrypt_pullback_bio_page(struct page **page, bool restore)
+{
+	struct fscrypt_ctx *ctx;
+	struct page *bounce_page;
+
+	/* The bounce data pages are unmapped. */
+	if ((*page)->mapping)
+		return;
+
+	/* The bounce data page is unmapped. */
+	bounce_page = *page;
+	ctx = (struct fscrypt_ctx *)page_private(bounce_page);
+
+	/* restore control page */
+	*page = ctx->w.control_page;
+
+	if (restore)
+		fscrypt_restore_control_page(bounce_page);
+}
+EXPORT_SYMBOL(fscrypt_pullback_bio_page);
+
+void fscrypt_restore_control_page(struct page *page)
+{
+	struct fscrypt_ctx *ctx;
+
+	ctx = (struct fscrypt_ctx *)page_private(page);
+	set_page_private(page, (unsigned long)NULL);
+	ClearPagePrivate(page);
+	unlock_page(page);
+	fscrypt_release_ctx(ctx);
+}
+EXPORT_SYMBOL(fscrypt_restore_control_page);
+
+static void fscrypt_destroy(void)
+{
+	struct fscrypt_ctx *pos, *n;
+
+	list_for_each_entry_safe(pos, n, &fscrypt_free_ctxs, free_list)
+		kmem_cache_free(fscrypt_ctx_cachep, pos);
+	INIT_LIST_HEAD(&fscrypt_free_ctxs);
+	mempool_destroy(fscrypt_bounce_page_pool);
+	fscrypt_bounce_page_pool = NULL;
+}
+
+/**
+ * fscrypt_initialize() - allocate major buffers for fs encryption.
+ *
+ * We only call this when we start accessing encrypted files, since it
+ * results in memory getting allocated that wouldn't otherwise be used.
+ *
+ * Return: Zero on success, non-zero otherwise.
+ */
+int fscrypt_initialize(void)
+{
+	int i, res = -ENOMEM;
+
+	if (fscrypt_bounce_page_pool)
+		return 0;
+
+	mutex_lock(&fscrypt_init_mutex);
+	if (fscrypt_bounce_page_pool)
+		goto already_initialized;
+
+	for (i = 0; i < num_prealloc_crypto_ctxs; i++) {
+		struct fscrypt_ctx *ctx;
+
+		ctx = kmem_cache_zalloc(fscrypt_ctx_cachep, GFP_NOFS);
+		if (!ctx)
+			goto fail;
+		list_add(&ctx->free_list, &fscrypt_free_ctxs);
+	}
+
+	fscrypt_bounce_page_pool =
+		mempool_create_page_pool(num_prealloc_crypto_pages, 0);
+	if (!fscrypt_bounce_page_pool)
+		goto fail;
+
+already_initialized:
+	mutex_unlock(&fscrypt_init_mutex);
+	return 0;
+fail:
+	fscrypt_destroy();
+	mutex_unlock(&fscrypt_init_mutex);
+	return res;
+}
+EXPORT_SYMBOL(fscrypt_initialize);
+
+/**
+ * fscrypt_init() - Set up for fs encryption.
+ */
+static int __init fscrypt_init(void)
+{
+	fscrypt_read_workqueue = alloc_workqueue("fscrypt_read_queue",
+							WQ_HIGHPRI, 0);
+	if (!fscrypt_read_workqueue)
+		goto fail;
+
+	fscrypt_ctx_cachep = KMEM_CACHE(fscrypt_ctx, SLAB_RECLAIM_ACCOUNT);
+	if (!fscrypt_ctx_cachep)
+		goto fail_free_queue;
+
+	fscrypt_info_cachep = KMEM_CACHE(fscrypt_info, SLAB_RECLAIM_ACCOUNT);
+	if (!fscrypt_info_cachep)
+		goto fail_free_ctx;
+
+	return 0;
+
+fail_free_ctx:
+	kmem_cache_destroy(fscrypt_ctx_cachep);
+fail_free_queue:
+	destroy_workqueue(fscrypt_read_workqueue);
+fail:
+	return -ENOMEM;
+}
+module_init(fscrypt_init)
+
+/**
+ * fscrypt_exit() - Shutdown the fs encryption system
+ */
+static void __exit fscrypt_exit(void)
+{
+	fscrypt_destroy();
+
+	if (fscrypt_read_workqueue)
+		destroy_workqueue(fscrypt_read_workqueue);
+	kmem_cache_destroy(fscrypt_ctx_cachep);
+	kmem_cache_destroy(fscrypt_info_cachep);
+}
+module_exit(fscrypt_exit);
+
+MODULE_LICENSE("GPL");
diff --git a/fs/f2fs/crypto_fname.c b/fs/crypto/fname.c
index ab377d496a39..5d6d49113efa 100644
--- a/fs/f2fs/crypto_fname.c
+++ b/fs/crypto/fname.c
@@ -1,46 +1,32 @@
 /*
- * linux/fs/f2fs/crypto_fname.c
- *
- * Copied from linux/fs/ext4/crypto.c
+ * This contains functions for filename crypto management
  *
  * Copyright (C) 2015, Google, Inc.
  * Copyright (C) 2015, Motorola Mobility
  *
- * This contains functions for filename crypto management in f2fs
- *
  * Written by Uday Savagaonkar, 2014.
- *
- * Adjust f2fs dentry structure
- *	Jaegeuk Kim, 2015.
+ * Modified by Jaegeuk Kim, 2015.
  *
  * This has not yet undergone a rigorous security audit.
  */
-#include <crypto/hash.h>
-#include <crypto/sha.h>
+
 #include <keys/encrypted-type.h>
 #include <keys/user-type.h>
-#include <linux/crypto.h>
-#include <linux/gfp.h>
-#include <linux/kernel.h>
-#include <linux/key.h>
-#include <linux/list.h>
-#include <linux/mempool.h>
-#include <linux/random.h>
 #include <linux/scatterlist.h>
-#include <linux/spinlock_types.h>
-#include <linux/f2fs_fs.h>
 #include <linux/ratelimit.h>
+#include <linux/fscrypto.h>
 
-#include "f2fs.h"
-#include "f2fs_crypto.h"
-#include "xattr.h"
+static u32 size_round_up(size_t size, size_t blksize)
+{
+	return ((size + blksize - 1) / blksize) * blksize;
+}
 
 /**
- * f2fs_dir_crypt_complete() -
+ * dir_crypt_complete() -
  */
-static void f2fs_dir_crypt_complete(struct crypto_async_request *req, int res)
+static void dir_crypt_complete(struct crypto_async_request *req, int res)
 {
-	struct f2fs_completion_result *ecr = req->data;
+	struct fscrypt_completion_result *ecr = req->data;
 
 	if (res == -EINPROGRESS)
 		return;
@@ -48,45 +34,35 @@ static void f2fs_dir_crypt_complete(struct crypto_async_request *req, int res)
 	complete(&ecr->completion);
 }
 
-bool f2fs_valid_filenames_enc_mode(uint32_t mode)
-{
-	return (mode == F2FS_ENCRYPTION_MODE_AES_256_CTS);
-}
-
-static unsigned max_name_len(struct inode *inode)
-{
-	return S_ISLNK(inode->i_mode) ? inode->i_sb->s_blocksize :
-					F2FS_NAME_LEN;
-}
-
 /**
- * f2fs_fname_encrypt() -
+ * fname_encrypt() -
  *
  * This function encrypts the input filename, and returns the length of the
  * ciphertext. Errors are returned as negative numbers.  We trust the caller to
  * allocate sufficient memory to oname string.
  */
-static int f2fs_fname_encrypt(struct inode *inode,
-			const struct qstr *iname, struct f2fs_str *oname)
+static int fname_encrypt(struct inode *inode,
+			const struct qstr *iname, struct fscrypt_str *oname)
 {
 	u32 ciphertext_len;
-	struct ablkcipher_request *req = NULL;
-	DECLARE_F2FS_COMPLETION_RESULT(ecr);
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
-	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+	struct skcipher_request *req = NULL;
+	DECLARE_FS_COMPLETION_RESULT(ecr);
+	struct fscrypt_info *ci = inode->i_crypt_info;
+	struct crypto_skcipher *tfm = ci->ci_ctfm;
 	int res = 0;
-	char iv[F2FS_CRYPTO_BLOCK_SIZE];
+	char iv[FS_CRYPTO_BLOCK_SIZE];
 	struct scatterlist src_sg, dst_sg;
-	int padding = 4 << (ci->ci_flags & F2FS_POLICY_FLAGS_PAD_MASK);
+	int padding = 4 << (ci->ci_flags & FS_POLICY_FLAGS_PAD_MASK);
 	char *workbuf, buf[32], *alloc_buf = NULL;
-	unsigned lim = max_name_len(inode);
+	unsigned lim;
 
+	lim = inode->i_sb->s_cop->max_namelen(inode);
 	if (iname->len <= 0 || iname->len > lim)
 		return -EIO;
 
-	ciphertext_len = (iname->len < F2FS_CRYPTO_BLOCK_SIZE) ?
-		F2FS_CRYPTO_BLOCK_SIZE : iname->len;
-	ciphertext_len = f2fs_fname_crypto_round_up(ciphertext_len, padding);
+	ciphertext_len = (iname->len < FS_CRYPTO_BLOCK_SIZE) ?
+					FS_CRYPTO_BLOCK_SIZE : iname->len;
+	ciphertext_len = size_round_up(ciphertext_len, padding);
 	ciphertext_len = (ciphertext_len > lim) ? lim : ciphertext_len;
 
 	if (ciphertext_len <= sizeof(buf)) {
@@ -99,16 +75,16 @@ static int f2fs_fname_encrypt(struct inode *inode,
 	}
 
 	/* Allocate request */
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
 	if (!req) {
 		printk_ratelimited(KERN_ERR
 			"%s: crypto_request_alloc() failed\n", __func__);
 		kfree(alloc_buf);
 		return -ENOMEM;
 	}
-	ablkcipher_request_set_callback(req,
+	skcipher_request_set_callback(req,
 			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
-			f2fs_dir_crypt_complete, &ecr);
+			dir_crypt_complete, &ecr);
 
 	/* Copy the input */
 	memcpy(workbuf, iname->name, iname->len);
@@ -116,79 +92,78 @@ static int f2fs_fname_encrypt(struct inode *inode,
 		memset(workbuf + iname->len, 0, ciphertext_len - iname->len);
 
 	/* Initialize IV */
-	memset(iv, 0, F2FS_CRYPTO_BLOCK_SIZE);
+	memset(iv, 0, FS_CRYPTO_BLOCK_SIZE);
 
 	/* Create encryption request */
 	sg_init_one(&src_sg, workbuf, ciphertext_len);
 	sg_init_one(&dst_sg, oname->name, ciphertext_len);
-	ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv);
-	res = crypto_ablkcipher_encrypt(req);
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv);
+	res = crypto_skcipher_encrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
-		BUG_ON(req->base.data != &ecr);
 		wait_for_completion(&ecr.completion);
 		res = ecr.res;
 	}
 	kfree(alloc_buf);
-	ablkcipher_request_free(req);
-	if (res < 0) {
+	skcipher_request_free(req);
+	if (res < 0)
 		printk_ratelimited(KERN_ERR
 				"%s: Error (error code %d)\n", __func__, res);
-	}
+
 	oname->len = ciphertext_len;
 	return res;
 }
 
 /*
- * f2fs_fname_decrypt()
+ * fname_decrypt()
  *	This function decrypts the input filename, and returns
  *	the length of the plaintext.
  *	Errors are returned as negative numbers.
  *	We trust the caller to allocate sufficient memory to oname string.
  */
-static int f2fs_fname_decrypt(struct inode *inode,
-			const struct f2fs_str *iname, struct f2fs_str *oname)
+static int fname_decrypt(struct inode *inode,
+				const struct fscrypt_str *iname,
+				struct fscrypt_str *oname)
 {
-	struct ablkcipher_request *req = NULL;
-	DECLARE_F2FS_COMPLETION_RESULT(ecr);
+	struct skcipher_request *req = NULL;
+	DECLARE_FS_COMPLETION_RESULT(ecr);
 	struct scatterlist src_sg, dst_sg;
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
-	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+	struct fscrypt_info *ci = inode->i_crypt_info;
+	struct crypto_skcipher *tfm = ci->ci_ctfm;
 	int res = 0;
-	char iv[F2FS_CRYPTO_BLOCK_SIZE];
-	unsigned lim = max_name_len(inode);
+	char iv[FS_CRYPTO_BLOCK_SIZE];
+	unsigned lim;
 
+	lim = inode->i_sb->s_cop->max_namelen(inode);
 	if (iname->len <= 0 || iname->len > lim)
 		return -EIO;
 
 	/* Allocate request */
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
 	if (!req) {
 		printk_ratelimited(KERN_ERR
 			"%s: crypto_request_alloc() failed\n",  __func__);
 		return -ENOMEM;
 	}
-	ablkcipher_request_set_callback(req,
+	skcipher_request_set_callback(req,
 		CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
-		f2fs_dir_crypt_complete, &ecr);
+		dir_crypt_complete, &ecr);
 
 	/* Initialize IV */
-	memset(iv, 0, F2FS_CRYPTO_BLOCK_SIZE);
+	memset(iv, 0, FS_CRYPTO_BLOCK_SIZE);
 
 	/* Create decryption request */
 	sg_init_one(&src_sg, iname->name, iname->len);
 	sg_init_one(&dst_sg, oname->name, oname->len);
-	ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv);
-	res = crypto_ablkcipher_decrypt(req);
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv);
+	res = crypto_skcipher_decrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
-		BUG_ON(req->base.data != &ecr);
 		wait_for_completion(&ecr.completion);
 		res = ecr.res;
 	}
-	ablkcipher_request_free(req);
+	skcipher_request_free(req);
 	if (res < 0) {
 		printk_ratelimited(KERN_ERR
-			"%s: Error in f2fs_fname_decrypt (error code %d)\n",
-			__func__, res);
+				"%s: Error (error code %d)\n", __func__, res);
 		return res;
 	}
 
@@ -200,7 +175,7 @@ static const char *lookup_table =
 	"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,";
 
 /**
- * f2fs_fname_encode_digest() -
+ * digest_encode() -
  *
  * Encodes the input digest using characters from the set [a-zA-Z0-9_+].
  * The encoded string is roughly 4/3 times the size of the input string.
@@ -249,148 +224,152 @@ static int digest_decode(const char *src, int len, char *dst)
 	return cp - dst;
 }
 
-/**
- * f2fs_fname_crypto_round_up() -
- *
- * Return: The next multiple of block size
- */
-u32 f2fs_fname_crypto_round_up(u32 size, u32 blksize)
+u32 fscrypt_fname_encrypted_size(struct inode *inode, u32 ilen)
 {
-	return ((size + blksize - 1) / blksize) * blksize;
+	int padding = 32;
+	struct fscrypt_info *ci = inode->i_crypt_info;
+
+	if (ci)
+		padding = 4 << (ci->ci_flags & FS_POLICY_FLAGS_PAD_MASK);
+	if (ilen < FS_CRYPTO_BLOCK_SIZE)
+		ilen = FS_CRYPTO_BLOCK_SIZE;
+	return size_round_up(ilen, padding);
 }
+EXPORT_SYMBOL(fscrypt_fname_encrypted_size);
 
 /**
- * f2fs_fname_crypto_alloc_obuff() -
+ * fscrypt_fname_crypto_alloc_obuff() -
  *
  * Allocates an output buffer that is sufficient for the crypto operation
  * specified by the context and the direction.
  */
-int f2fs_fname_crypto_alloc_buffer(struct inode *inode,
-				   u32 ilen, struct f2fs_str *crypto_str)
+int fscrypt_fname_alloc_buffer(struct inode *inode,
+				u32 ilen, struct fscrypt_str *crypto_str)
 {
-	unsigned int olen;
-	int padding = 16;
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
+	unsigned int olen = fscrypt_fname_encrypted_size(inode, ilen);
 
-	if (ci)
-		padding = 4 << (ci->ci_flags & F2FS_POLICY_FLAGS_PAD_MASK);
-	if (padding < F2FS_CRYPTO_BLOCK_SIZE)
-		padding = F2FS_CRYPTO_BLOCK_SIZE;
-	olen = f2fs_fname_crypto_round_up(ilen, padding);
 	crypto_str->len = olen;
-	if (olen < F2FS_FNAME_CRYPTO_DIGEST_SIZE * 2)
-		olen = F2FS_FNAME_CRYPTO_DIGEST_SIZE * 2;
-	/* Allocated buffer can hold one more character to null-terminate the
-	 * string */
+	if (olen < FS_FNAME_CRYPTO_DIGEST_SIZE * 2)
+		olen = FS_FNAME_CRYPTO_DIGEST_SIZE * 2;
+	/*
+	 * Allocated buffer can hold one more character to null-terminate the
+	 * string
+	 */
 	crypto_str->name = kmalloc(olen + 1, GFP_NOFS);
 	if (!(crypto_str->name))
 		return -ENOMEM;
 	return 0;
 }
+EXPORT_SYMBOL(fscrypt_fname_alloc_buffer);
 
 /**
- * f2fs_fname_crypto_free_buffer() -
+ * fscrypt_fname_crypto_free_buffer() -
  *
  * Frees the buffer allocated for crypto operation.
  */
-void f2fs_fname_crypto_free_buffer(struct f2fs_str *crypto_str)
+void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str)
 {
 	if (!crypto_str)
 		return;
 	kfree(crypto_str->name);
 	crypto_str->name = NULL;
 }
+EXPORT_SYMBOL(fscrypt_fname_free_buffer);
 
 /**
- * f2fs_fname_disk_to_usr() - converts a filename from disk space to user space
+ * fscrypt_fname_disk_to_usr() - converts a filename from disk space to user
+ * space
  */
-int f2fs_fname_disk_to_usr(struct inode *inode,
-			f2fs_hash_t *hash,
-			const struct f2fs_str *iname,
-			struct f2fs_str *oname)
+int fscrypt_fname_disk_to_usr(struct inode *inode,
+			u32 hash, u32 minor_hash,
+			const struct fscrypt_str *iname,
+			struct fscrypt_str *oname)
 {
 	const struct qstr qname = FSTR_TO_QSTR(iname);
 	char buf[24];
 	int ret;
 
-	if (is_dot_dotdot(&qname)) {
+	if (fscrypt_is_dot_dotdot(&qname)) {
 		oname->name[0] = '.';
 		oname->name[iname->len - 1] = '.';
 		oname->len = iname->len;
 		return oname->len;
 	}
 
-	if (F2FS_I(inode)->i_crypt_info)
-		return f2fs_fname_decrypt(inode, iname, oname);
+	if (iname->len < FS_CRYPTO_BLOCK_SIZE)
+		return -EUCLEAN;
 
-	if (iname->len <= F2FS_FNAME_CRYPTO_DIGEST_SIZE) {
+	if (inode->i_crypt_info)
+		return fname_decrypt(inode, iname, oname);
+
+	if (iname->len <= FS_FNAME_CRYPTO_DIGEST_SIZE) {
 		ret = digest_encode(iname->name, iname->len, oname->name);
 		oname->len = ret;
 		return ret;
 	}
 	if (hash) {
-		memcpy(buf, hash, 4);
-		memset(buf + 4, 0, 4);
-	} else
+		memcpy(buf, &hash, 4);
+		memcpy(buf + 4, &minor_hash, 4);
+	} else {
 		memset(buf, 0, 8);
+	}
 	memcpy(buf + 8, iname->name + iname->len - 16, 16);
 	oname->name[0] = '_';
 	ret = digest_encode(buf, 24, oname->name + 1);
 	oname->len = ret + 1;
 	return ret + 1;
 }
+EXPORT_SYMBOL(fscrypt_fname_disk_to_usr);
 
 /**
- * f2fs_fname_usr_to_disk() - converts a filename from user space to disk space
+ * fscrypt_fname_usr_to_disk() - converts a filename from user space to disk
+ * space
  */
-int f2fs_fname_usr_to_disk(struct inode *inode,
+int fscrypt_fname_usr_to_disk(struct inode *inode,
 			const struct qstr *iname,
-			struct f2fs_str *oname)
+			struct fscrypt_str *oname)
 {
-	int res;
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
-
-	if (is_dot_dotdot(iname)) {
+	if (fscrypt_is_dot_dotdot(iname)) {
 		oname->name[0] = '.';
 		oname->name[iname->len - 1] = '.';
 		oname->len = iname->len;
 		return oname->len;
 	}
-
-	if (ci) {
-		res = f2fs_fname_encrypt(inode, iname, oname);
-		return res;
-	}
-	/* Without a proper key, a user is not allowed to modify the filenames
+	if (inode->i_crypt_info)
+		return fname_encrypt(inode, iname, oname);
+	/*
+	 * Without a proper key, a user is not allowed to modify the filenames
 	 * in a directory. Consequently, a user space name cannot be mapped to
-	 * a disk-space name */
+	 * a disk-space name
+	 */
 	return -EACCES;
 }
+EXPORT_SYMBOL(fscrypt_fname_usr_to_disk);
 
-int f2fs_fname_setup_filename(struct inode *dir, const struct qstr *iname,
-			      int lookup, struct f2fs_filename *fname)
+int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
+			      int lookup, struct fscrypt_name *fname)
 {
-	struct f2fs_crypt_info *ci;
 	int ret = 0, bigname = 0;
 
-	memset(fname, 0, sizeof(struct f2fs_filename));
+	memset(fname, 0, sizeof(struct fscrypt_name));
 	fname->usr_fname = iname;
 
-	if (!f2fs_encrypted_inode(dir) || is_dot_dotdot(iname)) {
+	if (!dir->i_sb->s_cop->is_encrypted(dir) ||
+				fscrypt_is_dot_dotdot(iname)) {
 		fname->disk_name.name = (unsigned char *)iname->name;
 		fname->disk_name.len = iname->len;
 		return 0;
 	}
-	ret = f2fs_get_encryption_info(dir);
-	if (ret)
+	ret = get_crypt_info(dir);
+	if (ret && ret != -EOPNOTSUPP)
 		return ret;
-	ci = F2FS_I(dir)->i_crypt_info;
-	if (ci) {
-		ret = f2fs_fname_crypto_alloc_buffer(dir, iname->len,
-						     &fname->crypto_buf);
+
+	if (dir->i_crypt_info) {
+		ret = fscrypt_fname_alloc_buffer(dir, iname->len,
+							&fname->crypto_buf);
 		if (ret < 0)
 			return ret;
-		ret = f2fs_fname_encrypt(dir, iname, &fname->crypto_buf);
+		ret = fname_encrypt(dir, iname, &fname->crypto_buf);
 		if (ret < 0)
 			goto errout;
 		fname->disk_name.name = fname->crypto_buf.name;
@@ -400,18 +379,19 @@ int f2fs_fname_setup_filename(struct inode *dir, const struct qstr *iname,
 	if (!lookup)
 		return -EACCES;
 
-	/* We don't have the key and we are doing a lookup; decode the
+	/*
+	 * We don't have the key and we are doing a lookup; decode the
 	 * user-supplied name
 	 */
 	if (iname->name[0] == '_')
 		bigname = 1;
-	if ((bigname && (iname->len != 33)) ||
-	    (!bigname && (iname->len > 43)))
+	if ((bigname && (iname->len != 33)) || (!bigname && (iname->len > 43)))
 		return -ENOENT;
 
 	fname->crypto_buf.name = kmalloc(32, GFP_KERNEL);
 	if (fname->crypto_buf.name == NULL)
 		return -ENOMEM;
+
 	ret = digest_decode(iname->name + bigname, iname->len - bigname,
 				fname->crypto_buf.name);
 	if (ret < 0) {
@@ -421,20 +401,24 @@ int f2fs_fname_setup_filename(struct inode *dir, const struct qstr *iname,
 	fname->crypto_buf.len = ret;
 	if (bigname) {
 		memcpy(&fname->hash, fname->crypto_buf.name, 4);
+		memcpy(&fname->minor_hash, fname->crypto_buf.name + 4, 4);
 	} else {
 		fname->disk_name.name = fname->crypto_buf.name;
 		fname->disk_name.len = fname->crypto_buf.len;
 	}
 	return 0;
+
 errout:
-	f2fs_fname_crypto_free_buffer(&fname->crypto_buf);
+	fscrypt_fname_free_buffer(&fname->crypto_buf);
 	return ret;
 }
+EXPORT_SYMBOL(fscrypt_setup_filename);
 
-void f2fs_fname_free_filename(struct f2fs_filename *fname)
+void fscrypt_free_filename(struct fscrypt_name *fname)
 {
 	kfree(fname->crypto_buf.name);
 	fname->crypto_buf.name = NULL;
 	fname->usr_fname = NULL;
 	fname->disk_name.name = NULL;
 }
+EXPORT_SYMBOL(fscrypt_free_filename);
diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c
new file mode 100644
index 000000000000..06f5aa478bf2
--- /dev/null
+++ b/fs/crypto/keyinfo.c
@@ -0,0 +1,272 @@
+/*
+ * key management facility for FS encryption support.
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This contains encryption key functions.
+ *
+ * Written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar, 2015.
+ */
+
+#include <keys/encrypted-type.h>
+#include <keys/user-type.h>
+#include <linux/random.h>
+#include <linux/scatterlist.h>
+#include <uapi/linux/keyctl.h>
+#include <linux/fscrypto.h>
+
+static void derive_crypt_complete(struct crypto_async_request *req, int rc)
+{
+	struct fscrypt_completion_result *ecr = req->data;
+
+	if (rc == -EINPROGRESS)
+		return;
+
+	ecr->res = rc;
+	complete(&ecr->completion);
+}
+
+/**
+ * derive_key_aes() - Derive a key using AES-128-ECB
+ * @deriving_key: Encryption key used for derivation.
+ * @source_key:   Source key to which to apply derivation.
+ * @derived_key:  Derived key.
+ *
+ * Return: Zero on success; non-zero otherwise.
+ */
+static int derive_key_aes(u8 deriving_key[FS_AES_128_ECB_KEY_SIZE],
+				u8 source_key[FS_AES_256_XTS_KEY_SIZE],
+				u8 derived_key[FS_AES_256_XTS_KEY_SIZE])
+{
+	int res = 0;
+	struct skcipher_request *req = NULL;
+	DECLARE_FS_COMPLETION_RESULT(ecr);
+	struct scatterlist src_sg, dst_sg;
+	struct crypto_skcipher *tfm = crypto_alloc_skcipher("ecb(aes)", 0, 0);
+
+	if (IS_ERR(tfm)) {
+		res = PTR_ERR(tfm);
+		tfm = NULL;
+		goto out;
+	}
+	crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
+	if (!req) {
+		res = -ENOMEM;
+		goto out;
+	}
+	skcipher_request_set_callback(req,
+			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+			derive_crypt_complete, &ecr);
+	res = crypto_skcipher_setkey(tfm, deriving_key,
+					FS_AES_128_ECB_KEY_SIZE);
+	if (res < 0)
+		goto out;
+
+	sg_init_one(&src_sg, source_key, FS_AES_256_XTS_KEY_SIZE);
+	sg_init_one(&dst_sg, derived_key, FS_AES_256_XTS_KEY_SIZE);
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg,
+					FS_AES_256_XTS_KEY_SIZE, NULL);
+	res = crypto_skcipher_encrypt(req);
+	if (res == -EINPROGRESS || res == -EBUSY) {
+		wait_for_completion(&ecr.completion);
+		res = ecr.res;
+	}
+out:
+	skcipher_request_free(req);
+	crypto_free_skcipher(tfm);
+	return res;
+}
+
+static void put_crypt_info(struct fscrypt_info *ci)
+{
+	if (!ci)
+		return;
+
+	key_put(ci->ci_keyring_key);
+	crypto_free_skcipher(ci->ci_ctfm);
+	kmem_cache_free(fscrypt_info_cachep, ci);
+}
+
+int get_crypt_info(struct inode *inode)
+{
+	struct fscrypt_info *crypt_info;
+	u8 full_key_descriptor[FS_KEY_DESC_PREFIX_SIZE +
+				(FS_KEY_DESCRIPTOR_SIZE * 2) + 1];
+	struct key *keyring_key = NULL;
+	struct fscrypt_key *master_key;
+	struct fscrypt_context ctx;
+	const struct user_key_payload *ukp;
+	struct crypto_skcipher *ctfm;
+	const char *cipher_str;
+	u8 raw_key[FS_MAX_KEY_SIZE];
+	u8 mode;
+	int res;
+
+	res = fscrypt_initialize();
+	if (res)
+		return res;
+
+	if (!inode->i_sb->s_cop->get_context)
+		return -EOPNOTSUPP;
+retry:
+	crypt_info = ACCESS_ONCE(inode->i_crypt_info);
+	if (crypt_info) {
+		if (!crypt_info->ci_keyring_key ||
+				key_validate(crypt_info->ci_keyring_key) == 0)
+			return 0;
+		fscrypt_put_encryption_info(inode, crypt_info);
+		goto retry;
+	}
+
+	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+	if (res < 0) {
+		if (!fscrypt_dummy_context_enabled(inode))
+			return res;
+		ctx.contents_encryption_mode = FS_ENCRYPTION_MODE_AES_256_XTS;
+		ctx.filenames_encryption_mode = FS_ENCRYPTION_MODE_AES_256_CTS;
+		ctx.flags = 0;
+	} else if (res != sizeof(ctx)) {
+		return -EINVAL;
+	}
+	res = 0;
+
+	crypt_info = kmem_cache_alloc(fscrypt_info_cachep, GFP_NOFS);
+	if (!crypt_info)
+		return -ENOMEM;
+
+	crypt_info->ci_flags = ctx.flags;
+	crypt_info->ci_data_mode = ctx.contents_encryption_mode;
+	crypt_info->ci_filename_mode = ctx.filenames_encryption_mode;
+	crypt_info->ci_ctfm = NULL;
+	crypt_info->ci_keyring_key = NULL;
+	memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor,
+				sizeof(crypt_info->ci_master_key));
+	if (S_ISREG(inode->i_mode))
+		mode = crypt_info->ci_data_mode;
+	else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+		mode = crypt_info->ci_filename_mode;
+	else
+		BUG();
+
+	switch (mode) {
+	case FS_ENCRYPTION_MODE_AES_256_XTS:
+		cipher_str = "xts(aes)";
+		break;
+	case FS_ENCRYPTION_MODE_AES_256_CTS:
+		cipher_str = "cts(cbc(aes))";
+		break;
+	default:
+		printk_once(KERN_WARNING
+			    "%s: unsupported key mode %d (ino %u)\n",
+			    __func__, mode, (unsigned) inode->i_ino);
+		res = -ENOKEY;
+		goto out;
+	}
+	if (fscrypt_dummy_context_enabled(inode)) {
+		memset(raw_key, 0x42, FS_AES_256_XTS_KEY_SIZE);
+		goto got_key;
+	}
+	memcpy(full_key_descriptor, FS_KEY_DESC_PREFIX,
+					FS_KEY_DESC_PREFIX_SIZE);
+	sprintf(full_key_descriptor + FS_KEY_DESC_PREFIX_SIZE,
+					"%*phN", FS_KEY_DESCRIPTOR_SIZE,
+					ctx.master_key_descriptor);
+	full_key_descriptor[FS_KEY_DESC_PREFIX_SIZE +
+					(2 * FS_KEY_DESCRIPTOR_SIZE)] = '\0';
+	keyring_key = request_key(&key_type_logon, full_key_descriptor, NULL);
+	if (IS_ERR(keyring_key)) {
+		res = PTR_ERR(keyring_key);
+		keyring_key = NULL;
+		goto out;
+	}
+	crypt_info->ci_keyring_key = keyring_key;
+	if (keyring_key->type != &key_type_logon) {
+		printk_once(KERN_WARNING
+				"%s: key type must be logon\n", __func__);
+		res = -ENOKEY;
+		goto out;
+	}
+	down_read(&keyring_key->sem);
+	ukp = user_key_payload(keyring_key);
+	if (ukp->datalen != sizeof(struct fscrypt_key)) {
+		res = -EINVAL;
+		up_read(&keyring_key->sem);
+		goto out;
+	}
+	master_key = (struct fscrypt_key *)ukp->data;
+	BUILD_BUG_ON(FS_AES_128_ECB_KEY_SIZE != FS_KEY_DERIVATION_NONCE_SIZE);
+
+	if (master_key->size != FS_AES_256_XTS_KEY_SIZE) {
+		printk_once(KERN_WARNING
+				"%s: key size incorrect: %d\n",
+				__func__, master_key->size);
+		res = -ENOKEY;
+		up_read(&keyring_key->sem);
+		goto out;
+	}
+	res = derive_key_aes(ctx.nonce, master_key->raw, raw_key);
+	up_read(&keyring_key->sem);
+	if (res)
+		goto out;
+got_key:
+	ctfm = crypto_alloc_skcipher(cipher_str, 0, 0);
+	if (!ctfm || IS_ERR(ctfm)) {
+		res = ctfm ? PTR_ERR(ctfm) : -ENOMEM;
+		printk(KERN_DEBUG
+		       "%s: error %d (inode %u) allocating crypto tfm\n",
+		       __func__, res, (unsigned) inode->i_ino);
+		goto out;
+	}
+	crypt_info->ci_ctfm = ctfm;
+	crypto_skcipher_clear_flags(ctfm, ~0);
+	crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_REQ_WEAK_KEY);
+	res = crypto_skcipher_setkey(ctfm, raw_key, fscrypt_key_size(mode));
+	if (res)
+		goto out;
+
+	memzero_explicit(raw_key, sizeof(raw_key));
+	if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) != NULL) {
+		put_crypt_info(crypt_info);
+		goto retry;
+	}
+	return 0;
+
+out:
+	if (res == -ENOKEY)
+		res = 0;
+	put_crypt_info(crypt_info);
+	memzero_explicit(raw_key, sizeof(raw_key));
+	return res;
+}
+
+void fscrypt_put_encryption_info(struct inode *inode, struct fscrypt_info *ci)
+{
+	struct fscrypt_info *prev;
+
+	if (ci == NULL)
+		ci = ACCESS_ONCE(inode->i_crypt_info);
+	if (ci == NULL)
+		return;
+
+	prev = cmpxchg(&inode->i_crypt_info, ci, NULL);
+	if (prev != ci)
+		return;
+
+	put_crypt_info(ci);
+}
+EXPORT_SYMBOL(fscrypt_put_encryption_info);
+
+int fscrypt_get_encryption_info(struct inode *inode)
+{
+	struct fscrypt_info *ci = inode->i_crypt_info;
+
+	if (!ci ||
+		(ci->ci_keyring_key &&
+		 (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
+					       (1 << KEY_FLAG_REVOKED) |
+					       (1 << KEY_FLAG_DEAD)))))
+		return get_crypt_info(inode);
+	return 0;
+}
+EXPORT_SYMBOL(fscrypt_get_encryption_info);
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
new file mode 100644
index 000000000000..0f9961eede1e
--- /dev/null
+++ b/fs/crypto/policy.c
@@ -0,0 +1,229 @@
+/*
+ * Encryption policy functions for per-file encryption support.
+ *
+ * Copyright (C) 2015, Google, Inc.
+ * Copyright (C) 2015, Motorola Mobility.
+ *
+ * Written by Michael Halcrow, 2015.
+ * Modified by Jaegeuk Kim, 2015.
+ */
+
+#include <linux/random.h>
+#include <linux/string.h>
+#include <linux/fscrypto.h>
+
+static int inode_has_encryption_context(struct inode *inode)
+{
+	if (!inode->i_sb->s_cop->get_context)
+		return 0;
+	return (inode->i_sb->s_cop->get_context(inode, NULL, 0L) > 0);
+}
+
+/*
+ * check whether the policy is consistent with the encryption context
+ * for the inode
+ */
+static int is_encryption_context_consistent_with_policy(struct inode *inode,
+				const struct fscrypt_policy *policy)
+{
+	struct fscrypt_context ctx;
+	int res;
+
+	if (!inode->i_sb->s_cop->get_context)
+		return 0;
+
+	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+	if (res != sizeof(ctx))
+		return 0;
+
+	return (memcmp(ctx.master_key_descriptor, policy->master_key_descriptor,
+			FS_KEY_DESCRIPTOR_SIZE) == 0 &&
+			(ctx.flags == policy->flags) &&
+			(ctx.contents_encryption_mode ==
+			 policy->contents_encryption_mode) &&
+			(ctx.filenames_encryption_mode ==
+			 policy->filenames_encryption_mode));
+}
+
+static int create_encryption_context_from_policy(struct inode *inode,
+				const struct fscrypt_policy *policy)
+{
+	struct fscrypt_context ctx;
+	int res;
+
+	if (!inode->i_sb->s_cop->set_context)
+		return -EOPNOTSUPP;
+
+	if (inode->i_sb->s_cop->prepare_context) {
+		res = inode->i_sb->s_cop->prepare_context(inode);
+		if (res)
+			return res;
+	}
+
+	ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1;
+	memcpy(ctx.master_key_descriptor, policy->master_key_descriptor,
+					FS_KEY_DESCRIPTOR_SIZE);
+
+	if (!fscrypt_valid_contents_enc_mode(
+				policy->contents_encryption_mode)) {
+		printk(KERN_WARNING
+		       "%s: Invalid contents encryption mode %d\n", __func__,
+			policy->contents_encryption_mode);
+		return -EINVAL;
+	}
+
+	if (!fscrypt_valid_filenames_enc_mode(
+				policy->filenames_encryption_mode)) {
+		printk(KERN_WARNING
+			"%s: Invalid filenames encryption mode %d\n", __func__,
+			policy->filenames_encryption_mode);
+		return -EINVAL;
+	}
+
+	if (policy->flags & ~FS_POLICY_FLAGS_VALID)
+		return -EINVAL;
+
+	ctx.contents_encryption_mode = policy->contents_encryption_mode;
+	ctx.filenames_encryption_mode = policy->filenames_encryption_mode;
+	ctx.flags = policy->flags;
+	BUILD_BUG_ON(sizeof(ctx.nonce) != FS_KEY_DERIVATION_NONCE_SIZE);
+	get_random_bytes(ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE);
+
+	return inode->i_sb->s_cop->set_context(inode, &ctx, sizeof(ctx), NULL);
+}
+
+int fscrypt_process_policy(struct inode *inode,
+				const struct fscrypt_policy *policy)
+{
+	if (policy->version != 0)
+		return -EINVAL;
+
+	if (!inode_has_encryption_context(inode)) {
+		if (!inode->i_sb->s_cop->empty_dir)
+			return -EOPNOTSUPP;
+		if (!inode->i_sb->s_cop->empty_dir(inode))
+			return -ENOTEMPTY;
+		return create_encryption_context_from_policy(inode, policy);
+	}
+
+	if (is_encryption_context_consistent_with_policy(inode, policy))
+		return 0;
+
+	printk(KERN_WARNING "%s: Policy inconsistent with encryption context\n",
+	       __func__);
+	return -EINVAL;
+}
+EXPORT_SYMBOL(fscrypt_process_policy);
+
+int fscrypt_get_policy(struct inode *inode, struct fscrypt_policy *policy)
+{
+	struct fscrypt_context ctx;
+	int res;
+
+	if (!inode->i_sb->s_cop->get_context ||
+			!inode->i_sb->s_cop->is_encrypted(inode))
+		return -ENODATA;
+
+	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+	if (res != sizeof(ctx))
+		return -ENODATA;
+	if (ctx.format != FS_ENCRYPTION_CONTEXT_FORMAT_V1)
+		return -EINVAL;
+
+	policy->version = 0;
+	policy->contents_encryption_mode = ctx.contents_encryption_mode;
+	policy->filenames_encryption_mode = ctx.filenames_encryption_mode;
+	policy->flags = ctx.flags;
+	memcpy(&policy->master_key_descriptor, ctx.master_key_descriptor,
+				FS_KEY_DESCRIPTOR_SIZE);
+	return 0;
+}
+EXPORT_SYMBOL(fscrypt_get_policy);
+
+int fscrypt_has_permitted_context(struct inode *parent, struct inode *child)
+{
+	struct fscrypt_info *parent_ci, *child_ci;
+	int res;
+
+	if ((parent == NULL) || (child == NULL)) {
+		printk(KERN_ERR	"parent %p child %p\n", parent, child);
+		BUG_ON(1);
+	}
+
+	/* no restrictions if the parent directory is not encrypted */
+	if (!parent->i_sb->s_cop->is_encrypted(parent))
+		return 1;
+	/* if the child directory is not encrypted, this is always a problem */
+	if (!parent->i_sb->s_cop->is_encrypted(child))
+		return 0;
+	res = fscrypt_get_encryption_info(parent);
+	if (res)
+		return 0;
+	res = fscrypt_get_encryption_info(child);
+	if (res)
+		return 0;
+	parent_ci = parent->i_crypt_info;
+	child_ci = child->i_crypt_info;
+	if (!parent_ci && !child_ci)
+		return 1;
+	if (!parent_ci || !child_ci)
+		return 0;
+
+	return (memcmp(parent_ci->ci_master_key,
+			child_ci->ci_master_key,
+			FS_KEY_DESCRIPTOR_SIZE) == 0 &&
+		(parent_ci->ci_data_mode == child_ci->ci_data_mode) &&
+		(parent_ci->ci_filename_mode == child_ci->ci_filename_mode) &&
+		(parent_ci->ci_flags == child_ci->ci_flags));
+}
+EXPORT_SYMBOL(fscrypt_has_permitted_context);
+
+/**
+ * fscrypt_inherit_context() - Sets a child context from its parent
+ * @parent: Parent inode from which the context is inherited.
+ * @child:  Child inode that inherits the context from @parent.
+ * @fs_data:  private data given by FS.
+ * @preload:  preload child i_crypt_info
+ *
+ * Return: Zero on success, non-zero otherwise
+ */
+int fscrypt_inherit_context(struct inode *parent, struct inode *child,
+						void *fs_data, bool preload)
+{
+	struct fscrypt_context ctx;
+	struct fscrypt_info *ci;
+	int res;
+
+	if (!parent->i_sb->s_cop->set_context)
+		return -EOPNOTSUPP;
+
+	res = fscrypt_get_encryption_info(parent);
+	if (res < 0)
+		return res;
+
+	ci = parent->i_crypt_info;
+	if (ci == NULL)
+		return -ENOKEY;
+
+	ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1;
+	if (fscrypt_dummy_context_enabled(parent)) {
+		ctx.contents_encryption_mode = FS_ENCRYPTION_MODE_AES_256_XTS;
+		ctx.filenames_encryption_mode = FS_ENCRYPTION_MODE_AES_256_CTS;
+		ctx.flags = 0;
+		memset(ctx.master_key_descriptor, 0x42, FS_KEY_DESCRIPTOR_SIZE);
+		res = 0;
+	} else {
+		ctx.contents_encryption_mode = ci->ci_data_mode;
+		ctx.filenames_encryption_mode = ci->ci_filename_mode;
+		ctx.flags = ci->ci_flags;
+		memcpy(ctx.master_key_descriptor, ci->ci_master_key,
+				FS_KEY_DESCRIPTOR_SIZE);
+	}
+	get_random_bytes(ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE);
+	res = parent->i_sb->s_cop->set_context(child, &ctx,
+						sizeof(ctx), fs_data);
+	if (res)
+		return res;
+	return preload ? fscrypt_get_encryption_info(child): 0;
+}
+EXPORT_SYMBOL(fscrypt_inherit_context);
diff --git a/fs/dax.c b/fs/dax.c
index a86d3cc2b389..75ba46d82a76 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -24,52 +24,91 @@
 #include <linux/memcontrol.h>
 #include <linux/mm.h>
 #include <linux/mutex.h>
+#include <linux/pagevec.h>
 #include <linux/pmem.h>
 #include <linux/sched.h>
 #include <linux/uio.h>
 #include <linux/vmstat.h>
+#include <linux/pfn_t.h>
+#include <linux/sizes.h>
 
-int dax_clear_blocks(struct inode *inode, sector_t block, long size)
+static long dax_map_atomic(struct block_device *bdev, struct blk_dax_ctl *dax)
 {
-	struct block_device *bdev = inode->i_sb->s_bdev;
-	sector_t sector = block << (inode->i_blkbits - 9);
+	struct request_queue *q = bdev->bd_queue;
+	long rc = -EIO;
+
+	dax->addr = (void __pmem *) ERR_PTR(-EIO);
+	if (blk_queue_enter(q, true) != 0)
+		return rc;
+
+	rc = bdev_direct_access(bdev, dax);
+	if (rc < 0) {
+		dax->addr = (void __pmem *) ERR_PTR(rc);
+		blk_queue_exit(q);
+		return rc;
+	}
+	return rc;
+}
+
+static void dax_unmap_atomic(struct block_device *bdev,
+		const struct blk_dax_ctl *dax)
+{
+	if (IS_ERR(dax->addr))
+		return;
+	blk_queue_exit(bdev->bd_queue);
+}
+
+struct page *read_dax_sector(struct block_device *bdev, sector_t n)
+{
+	struct page *page = alloc_pages(GFP_KERNEL, 0);
+	struct blk_dax_ctl dax = {
+		.size = PAGE_SIZE,
+		.sector = n & ~((((int) PAGE_SIZE) / 512) - 1),
+	};
+	long rc;
+
+	if (!page)
+		return ERR_PTR(-ENOMEM);
+
+	rc = dax_map_atomic(bdev, &dax);
+	if (rc < 0)
+		return ERR_PTR(rc);
+	memcpy_from_pmem(page_address(page), dax.addr, PAGE_SIZE);
+	dax_unmap_atomic(bdev, &dax);
+	return page;
+}
+
+/*
+ * dax_clear_sectors() is called from within transaction context from XFS,
+ * and hence this means the stack from this point must follow GFP_NOFS
+ * semantics for all operations.
+ */
+int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size)
+{
+	struct blk_dax_ctl dax = {
+		.sector = _sector,
+		.size = _size,
+	};
 
 	might_sleep();
 	do {
-		void __pmem *addr;
-		unsigned long pfn;
-		long count;
+		long count, sz;
 
-		count = bdev_direct_access(bdev, sector, &addr, &pfn, size);
+		count = dax_map_atomic(bdev, &dax);
 		if (count < 0)
 			return count;
-		BUG_ON(size < count);
-		while (count > 0) {
-			unsigned pgsz = PAGE_SIZE - offset_in_page(addr);
-			if (pgsz > count)
-				pgsz = count;
-			clear_pmem(addr, pgsz);
-			addr += pgsz;
-			size -= pgsz;
-			count -= pgsz;
-			BUG_ON(pgsz & 511);
-			sector += pgsz / 512;
-			cond_resched();
-		}
-	} while (size);
+		sz = min_t(long, count, SZ_128K);
+		clear_pmem(dax.addr, sz);
+		dax.size -= sz;
+		dax.sector += sz / 512;
+		dax_unmap_atomic(bdev, &dax);
+		cond_resched();
+	} while (dax.size);
 
 	wmb_pmem();
 	return 0;
 }
-EXPORT_SYMBOL_GPL(dax_clear_blocks);
-
-static long dax_get_addr(struct buffer_head *bh, void __pmem **addr,
-		unsigned blkbits)
-{
-	unsigned long pfn;
-	sector_t sector = bh->b_blocknr << (blkbits - 9);
-	return bdev_direct_access(bh->b_bdev, sector, addr, &pfn, bh->b_size);
-}
+EXPORT_SYMBOL_GPL(dax_clear_sectors);
 
 /* the clear_pmem() calls are ordered by a wmb_pmem() in the caller */
 static void dax_new_buf(void __pmem *addr, unsigned size, unsigned first,
@@ -100,19 +139,29 @@ static bool buffer_size_valid(struct buffer_head *bh)
 	return bh->b_state != 0;
 }
 
+
+static sector_t to_sector(const struct buffer_head *bh,
+		const struct inode *inode)
+{
+	sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9);
+
+	return sector;
+}
+
 static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
 		      loff_t start, loff_t end, get_block_t get_block,
 		      struct buffer_head *bh)
 {
-	ssize_t retval = 0;
-	loff_t pos = start;
-	loff_t max = start;
-	loff_t bh_max = start;
-	void __pmem *addr;
-	bool hole = false;
-	bool need_wmb = false;
-
-	if (iov_iter_rw(iter) != WRITE)
+	loff_t pos = start, max = start, bh_max = start;
+	bool hole = false, need_wmb = false;
+	struct block_device *bdev = NULL;
+	int rw = iov_iter_rw(iter), rc;
+	long map_len = 0;
+	struct blk_dax_ctl dax = {
+		.addr = (void __pmem *) ERR_PTR(-EIO),
+	};
+
+	if (rw == READ)
 		end = min(end, i_size_read(inode));
 
 	while (pos < end) {
@@ -127,13 +176,13 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
 			if (pos == bh_max) {
 				bh->b_size = PAGE_ALIGN(end - pos);
 				bh->b_state = 0;
-				retval = get_block(inode, block, bh,
-						   iov_iter_rw(iter) == WRITE);
-				if (retval)
+				rc = get_block(inode, block, bh, rw == WRITE);
+				if (rc)
 					break;
 				if (!buffer_size_valid(bh))
 					bh->b_size = 1 << blkbits;
 				bh_max = pos - first + bh->b_size;
+				bdev = bh->b_bdev;
 			} else {
 				unsigned done = bh->b_size -
 						(bh_max - (pos - first));
@@ -141,45 +190,53 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
 				bh->b_size -= done;
 			}
 
-			hole = iov_iter_rw(iter) != WRITE && !buffer_written(bh);
+			hole = rw == READ && !buffer_written(bh);
 			if (hole) {
-				addr = NULL;
 				size = bh->b_size - first;
 			} else {
-				retval = dax_get_addr(bh, &addr, blkbits);
-				if (retval < 0)
+				dax_unmap_atomic(bdev, &dax);
+				dax.sector = to_sector(bh, inode);
+				dax.size = bh->b_size;
+				map_len = dax_map_atomic(bdev, &dax);
+				if (map_len < 0) {
+					rc = map_len;
 					break;
+				}
 				if (buffer_unwritten(bh) || buffer_new(bh)) {
-					dax_new_buf(addr, retval, first, pos,
-									end);
+					dax_new_buf(dax.addr, map_len, first,
+							pos, end);
 					need_wmb = true;
 				}
-				addr += first;
-				size = retval - first;
+				dax.addr += first;
+				size = map_len - first;
 			}
 			max = min(pos + size, end);
 		}
 
 		if (iov_iter_rw(iter) == WRITE) {
-			len = copy_from_iter_pmem(addr, max - pos, iter);
+			len = copy_from_iter_pmem(dax.addr, max - pos, iter);
 			need_wmb = true;
 		} else if (!hole)
-			len = copy_to_iter((void __force *)addr, max - pos,
+			len = copy_to_iter((void __force *) dax.addr, max - pos,
 					iter);
 		else
 			len = iov_iter_zero(max - pos, iter);
 
-		if (!len)
+		if (!len) {
+			rc = -EFAULT;
 			break;
+		}
 
 		pos += len;
-		addr += len;
+		if (!IS_ERR(dax.addr))
+			dax.addr += len;
 	}
 
 	if (need_wmb)
 		wmb_pmem();
+	dax_unmap_atomic(bdev, &dax);
 
-	return (pos == start) ? retval : pos - start;
+	return (pos == start) ? rc : pos - start;
 }
 
 /**
@@ -208,13 +265,14 @@ ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode,
 	loff_t end = pos + iov_iter_count(iter);
 
 	memset(&bh, 0, sizeof(bh));
+	bh.b_bdev = inode->i_sb->s_bdev;
 
 	if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ) {
 		struct address_space *mapping = inode->i_mapping;
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		retval = filemap_write_and_wait_range(mapping, pos, end - 1);
 		if (retval) {
-			mutex_unlock(&inode->i_mutex);
+			inode_unlock(inode);
 			goto out;
 		}
 	}
@@ -226,10 +284,15 @@ ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode,
 	retval = dax_io(inode, iter, pos, end, get_block, &bh);
 
 	if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ)
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
+
+	if (end_io) {
+		int err;
 
-	if ((retval > 0) && end_io)
-		end_io(iocb, pos, retval, bh.b_private);
+		err = end_io(iocb, pos, retval, bh.b_private);
+		if (err)
+			retval = err;
+	}
 
 	if (!(flags & DIO_SKIP_DIO_COUNT))
 		inode_dio_end(inode);
@@ -260,7 +323,7 @@ static int dax_load_hole(struct address_space *mapping, struct page *page,
 	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	if (vmf->pgoff >= size) {
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 		return VM_FAULT_SIGBUS;
 	}
 
@@ -268,28 +331,231 @@ static int dax_load_hole(struct address_space *mapping, struct page *page,
 	return VM_FAULT_LOCKED;
 }
 
-static int copy_user_bh(struct page *to, struct buffer_head *bh,
-			unsigned blkbits, unsigned long vaddr)
+static int copy_user_bh(struct page *to, struct inode *inode,
+		struct buffer_head *bh, unsigned long vaddr)
 {
-	void __pmem *vfrom;
+	struct blk_dax_ctl dax = {
+		.sector = to_sector(bh, inode),
+		.size = bh->b_size,
+	};
+	struct block_device *bdev = bh->b_bdev;
 	void *vto;
 
-	if (dax_get_addr(bh, &vfrom, blkbits) < 0)
-		return -EIO;
+	if (dax_map_atomic(bdev, &dax) < 0)
+		return PTR_ERR(dax.addr);
 	vto = kmap_atomic(to);
-	copy_user_page(vto, (void __force *)vfrom, vaddr, to);
+	copy_user_page(vto, (void __force *)dax.addr, vaddr, to);
 	kunmap_atomic(vto);
+	dax_unmap_atomic(bdev, &dax);
 	return 0;
 }
 
+#define NO_SECTOR -1
+#define DAX_PMD_INDEX(page_index) (page_index & (PMD_MASK >> PAGE_SHIFT))
+
+static int dax_radix_entry(struct address_space *mapping, pgoff_t index,
+		sector_t sector, bool pmd_entry, bool dirty)
+{
+	struct radix_tree_root *page_tree = &mapping->page_tree;
+	pgoff_t pmd_index = DAX_PMD_INDEX(index);
+	int type, error = 0;
+	void *entry;
+
+	WARN_ON_ONCE(pmd_entry && !dirty);
+	if (dirty)
+		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+
+	spin_lock_irq(&mapping->tree_lock);
+
+	entry = radix_tree_lookup(page_tree, pmd_index);
+	if (entry && RADIX_DAX_TYPE(entry) == RADIX_DAX_PMD) {
+		index = pmd_index;
+		goto dirty;
+	}
+
+	entry = radix_tree_lookup(page_tree, index);
+	if (entry) {
+		type = RADIX_DAX_TYPE(entry);
+		if (WARN_ON_ONCE(type != RADIX_DAX_PTE &&
+					type != RADIX_DAX_PMD)) {
+			error = -EIO;
+			goto unlock;
+		}
+
+		if (!pmd_entry || type == RADIX_DAX_PMD)
+			goto dirty;
+
+		/*
+		 * We only insert dirty PMD entries into the radix tree.  This
+		 * means we don't need to worry about removing a dirty PTE
+		 * entry and inserting a clean PMD entry, thus reducing the
+		 * range we would flush with a follow-up fsync/msync call.
+		 */
+		radix_tree_delete(&mapping->page_tree, index);
+		mapping->nrexceptional--;
+	}
+
+	if (sector == NO_SECTOR) {
+		/*
+		 * This can happen during correct operation if our pfn_mkwrite
+		 * fault raced against a hole punch operation.  If this
+		 * happens the pte that was hole punched will have been
+		 * unmapped and the radix tree entry will have been removed by
+		 * the time we are called, but the call will still happen.  We
+		 * will return all the way up to wp_pfn_shared(), where the
+		 * pte_same() check will fail, eventually causing page fault
+		 * to be retried by the CPU.
+		 */
+		goto unlock;
+	}
+
+	error = radix_tree_insert(page_tree, index,
+			RADIX_DAX_ENTRY(sector, pmd_entry));
+	if (error)
+		goto unlock;
+
+	mapping->nrexceptional++;
+ dirty:
+	if (dirty)
+		radix_tree_tag_set(page_tree, index, PAGECACHE_TAG_DIRTY);
+ unlock:
+	spin_unlock_irq(&mapping->tree_lock);
+	return error;
+}
+
+static int dax_writeback_one(struct block_device *bdev,
+		struct address_space *mapping, pgoff_t index, void *entry)
+{
+	struct radix_tree_root *page_tree = &mapping->page_tree;
+	int type = RADIX_DAX_TYPE(entry);
+	struct radix_tree_node *node;
+	struct blk_dax_ctl dax;
+	void **slot;
+	int ret = 0;
+
+	spin_lock_irq(&mapping->tree_lock);
+	/*
+	 * Regular page slots are stabilized by the page lock even
+	 * without the tree itself locked.  These unlocked entries
+	 * need verification under the tree lock.
+	 */
+	if (!__radix_tree_lookup(page_tree, index, &node, &slot))
+		goto unlock;
+	if (*slot != entry)
+		goto unlock;
+
+	/* another fsync thread may have already written back this entry */
+	if (!radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))
+		goto unlock;
+
+	if (WARN_ON_ONCE(type != RADIX_DAX_PTE && type != RADIX_DAX_PMD)) {
+		ret = -EIO;
+		goto unlock;
+	}
+
+	dax.sector = RADIX_DAX_SECTOR(entry);
+	dax.size = (type == RADIX_DAX_PMD ? PMD_SIZE : PAGE_SIZE);
+	spin_unlock_irq(&mapping->tree_lock);
+
+	/*
+	 * We cannot hold tree_lock while calling dax_map_atomic() because it
+	 * eventually calls cond_resched().
+	 */
+	ret = dax_map_atomic(bdev, &dax);
+	if (ret < 0)
+		return ret;
+
+	if (WARN_ON_ONCE(ret < dax.size)) {
+		ret = -EIO;
+		goto unmap;
+	}
+
+	wb_cache_pmem(dax.addr, dax.size);
+
+	spin_lock_irq(&mapping->tree_lock);
+	radix_tree_tag_clear(page_tree, index, PAGECACHE_TAG_TOWRITE);
+	spin_unlock_irq(&mapping->tree_lock);
+ unmap:
+	dax_unmap_atomic(bdev, &dax);
+	return ret;
+
+ unlock:
+	spin_unlock_irq(&mapping->tree_lock);
+	return ret;
+}
+
+/*
+ * Flush the mapping to the persistent domain within the byte range of [start,
+ * end]. This is required by data integrity operations to ensure file data is
+ * on persistent storage prior to completion of the operation.
+ */
+int dax_writeback_mapping_range(struct address_space *mapping,
+		struct block_device *bdev, struct writeback_control *wbc)
+{
+	struct inode *inode = mapping->host;
+	pgoff_t start_index, end_index, pmd_index;
+	pgoff_t indices[PAGEVEC_SIZE];
+	struct pagevec pvec;
+	bool done = false;
+	int i, ret = 0;
+	void *entry;
+
+	if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT))
+		return -EIO;
+
+	if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL)
+		return 0;
+
+	start_index = wbc->range_start >> PAGE_SHIFT;
+	end_index = wbc->range_end >> PAGE_SHIFT;
+	pmd_index = DAX_PMD_INDEX(start_index);
+
+	rcu_read_lock();
+	entry = radix_tree_lookup(&mapping->page_tree, pmd_index);
+	rcu_read_unlock();
+
+	/* see if the start of our range is covered by a PMD entry */
+	if (entry && RADIX_DAX_TYPE(entry) == RADIX_DAX_PMD)
+		start_index = pmd_index;
+
+	tag_pages_for_writeback(mapping, start_index, end_index);
+
+	pagevec_init(&pvec, 0);
+	while (!done) {
+		pvec.nr = find_get_entries_tag(mapping, start_index,
+				PAGECACHE_TAG_TOWRITE, PAGEVEC_SIZE,
+				pvec.pages, indices);
+
+		if (pvec.nr == 0)
+			break;
+
+		for (i = 0; i < pvec.nr; i++) {
+			if (indices[i] > end_index) {
+				done = true;
+				break;
+			}
+
+			ret = dax_writeback_one(bdev, mapping, indices[i],
+					pvec.pages[i]);
+			if (ret < 0)
+				return ret;
+		}
+	}
+	wmb_pmem();
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dax_writeback_mapping_range);
+
 static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
 			struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	struct address_space *mapping = inode->i_mapping;
-	sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9);
 	unsigned long vaddr = (unsigned long)vmf->virtual_address;
-	void __pmem *addr;
-	unsigned long pfn;
+	struct address_space *mapping = inode->i_mapping;
+	struct block_device *bdev = bh->b_bdev;
+	struct blk_dax_ctl dax = {
+		.sector = to_sector(bh, inode),
+		.size = bh->b_size,
+	};
 	pgoff_t size;
 	int error;
 
@@ -308,20 +574,23 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
 		goto out;
 	}
 
-	error = bdev_direct_access(bh->b_bdev, sector, &addr, &pfn, bh->b_size);
-	if (error < 0)
-		goto out;
-	if (error < PAGE_SIZE) {
-		error = -EIO;
+	if (dax_map_atomic(bdev, &dax) < 0) {
+		error = PTR_ERR(dax.addr);
 		goto out;
 	}
 
 	if (buffer_unwritten(bh) || buffer_new(bh)) {
-		clear_pmem(addr, PAGE_SIZE);
+		clear_pmem(dax.addr, PAGE_SIZE);
 		wmb_pmem();
 	}
+	dax_unmap_atomic(bdev, &dax);
 
-	error = vm_insert_mixed(vma, vaddr, pfn);
+	error = dax_radix_entry(mapping, vmf->pgoff, dax.sector, false,
+			vmf->flags & FAULT_FLAG_WRITE);
+	if (error)
+		goto out;
+
+	error = vm_insert_mixed(vma, vaddr, dax.pfn);
 
  out:
 	i_mmap_unlock_read(mapping);
@@ -366,18 +635,19 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 
 	memset(&bh, 0, sizeof(bh));
 	block = (sector_t)vmf->pgoff << (PAGE_SHIFT - blkbits);
+	bh.b_bdev = inode->i_sb->s_bdev;
 	bh.b_size = PAGE_SIZE;
 
  repeat:
 	page = find_get_page(mapping, vmf->pgoff);
 	if (page) {
 		if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) {
-			page_cache_release(page);
+			put_page(page);
 			return VM_FAULT_RETRY;
 		}
 		if (unlikely(page->mapping != mapping)) {
 			unlock_page(page);
-			page_cache_release(page);
+			put_page(page);
 			goto repeat;
 		}
 		size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
@@ -415,7 +685,7 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	if (vmf->cow_page) {
 		struct page *new_page = vmf->cow_page;
 		if (buffer_written(&bh))
-			error = copy_user_bh(new_page, &bh, blkbits, vaddr);
+			error = copy_user_bh(new_page, inode, &bh, vaddr);
 		else
 			clear_user_highpage(new_page, vaddr);
 		if (error)
@@ -441,10 +711,11 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 
 	if (page) {
 		unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT,
-							PAGE_CACHE_SIZE, 0);
+							PAGE_SIZE, 0);
 		delete_from_page_cache(page);
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
+		page = NULL;
 	}
 
 	/*
@@ -476,7 +747,7 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
  unlock_page:
 	if (page) {
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 	}
 	goto out;
 }
@@ -516,6 +787,24 @@ EXPORT_SYMBOL_GPL(dax_fault);
  */
 #define PG_PMD_COLOUR	((PMD_SIZE >> PAGE_SHIFT) - 1)
 
+static void __dax_dbg(struct buffer_head *bh, unsigned long address,
+		const char *reason, const char *fn)
+{
+	if (bh) {
+		char bname[BDEVNAME_SIZE];
+		bdevname(bh->b_bdev, bname);
+		pr_debug("%s: %s addr: %lx dev %s state %lx start %lld "
+			"length %zd fallback: %s\n", fn, current->comm,
+			address, bname, bh->b_state, (u64)bh->b_blocknr,
+			bh->b_size, reason);
+	} else {
+		pr_debug("%s: %s addr: %lx fallback: %s\n", fn,
+			current->comm, address, reason);
+	}
+}
+
+#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,
 		pmd_t *pmd, unsigned int flags, get_block_t get_block,
 		dax_iodone_t complete_unwritten)
@@ -527,57 +816,83 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	unsigned blkbits = inode->i_blkbits;
 	unsigned long pmd_addr = address & PMD_MASK;
 	bool write = flags & FAULT_FLAG_WRITE;
-	long length;
-	void __pmem *kaddr;
+	struct block_device *bdev;
 	pgoff_t size, pgoff;
-	sector_t block, sector;
-	unsigned long pfn;
-	int result = 0;
+	sector_t block;
+	int error, result = 0;
+	bool alloc = false;
+
+	/* dax pmd mappings require pfn_t_devmap() */
+	if (!IS_ENABLED(CONFIG_FS_DAX_PMD))
+		return VM_FAULT_FALLBACK;
 
 	/* Fall back to PTEs if we're going to COW */
-	if (write && !(vma->vm_flags & VM_SHARED))
+	if (write && !(vma->vm_flags & VM_SHARED)) {
+		split_huge_pmd(vma, pmd, address);
+		dax_pmd_dbg(NULL, address, "cow write");
 		return VM_FAULT_FALLBACK;
+	}
 	/* If the PMD would extend outside the VMA */
-	if (pmd_addr < vma->vm_start)
+	if (pmd_addr < vma->vm_start) {
+		dax_pmd_dbg(NULL, address, "vma start unaligned");
 		return VM_FAULT_FALLBACK;
-	if ((pmd_addr + PMD_SIZE) > vma->vm_end)
+	}
+	if ((pmd_addr + PMD_SIZE) > vma->vm_end) {
+		dax_pmd_dbg(NULL, address, "vma end unaligned");
 		return VM_FAULT_FALLBACK;
+	}
 
 	pgoff = linear_page_index(vma, pmd_addr);
 	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	if (pgoff >= size)
 		return VM_FAULT_SIGBUS;
 	/* If the PMD would cover blocks out of the file */
-	if ((pgoff | PG_PMD_COLOUR) >= size)
+	if ((pgoff | PG_PMD_COLOUR) >= size) {
+		dax_pmd_dbg(NULL, address,
+				"offset + huge page size > file size");
 		return VM_FAULT_FALLBACK;
+	}
 
 	memset(&bh, 0, sizeof(bh));
+	bh.b_bdev = inode->i_sb->s_bdev;
 	block = (sector_t)pgoff << (PAGE_SHIFT - blkbits);
 
 	bh.b_size = PMD_SIZE;
-	length = get_block(inode, block, &bh, write);
-	if (length)
+
+	if (get_block(inode, block, &bh, 0) != 0)
 		return VM_FAULT_SIGBUS;
-	i_mmap_lock_read(mapping);
+
+	if (!buffer_mapped(&bh) && write) {
+		if (get_block(inode, block, &bh, 1) != 0)
+			return VM_FAULT_SIGBUS;
+		alloc = true;
+	}
+
+	bdev = bh.b_bdev;
 
 	/*
 	 * If the filesystem isn't willing to tell us the length of a hole,
 	 * just fall back to PTEs.  Calling get_block 512 times in a loop
 	 * would be silly.
 	 */
-	if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE)
-		goto fallback;
+	if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE) {
+		dax_pmd_dbg(&bh, address, "allocated block too small");
+		return VM_FAULT_FALLBACK;
+	}
 
 	/*
 	 * If we allocated new storage, make sure no process has any
 	 * zero pages covering this hole
 	 */
-	if (buffer_new(&bh)) {
-		i_mmap_unlock_read(mapping);
-		unmap_mapping_range(mapping, pgoff << PAGE_SHIFT, PMD_SIZE, 0);
-		i_mmap_lock_read(mapping);
+	if (alloc) {
+		loff_t lstart = pgoff << PAGE_SHIFT;
+		loff_t lend = lstart + PMD_SIZE - 1; /* inclusive */
+
+		truncate_pagecache_range(inode, lstart, lend);
 	}
 
+	i_mmap_lock_read(mapping);
+
 	/*
 	 * If a truncate happened while we were allocating blocks, we may
 	 * leave blocks allocated to the file that are beyond EOF.  We can't
@@ -589,50 +904,108 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		result = VM_FAULT_SIGBUS;
 		goto out;
 	}
-	if ((pgoff | PG_PMD_COLOUR) >= size)
+	if ((pgoff | PG_PMD_COLOUR) >= size) {
+		dax_pmd_dbg(&bh, address,
+				"offset + huge page size > file size");
 		goto fallback;
+	}
 
 	if (!write && !buffer_mapped(&bh) && buffer_uptodate(&bh)) {
 		spinlock_t *ptl;
 		pmd_t entry;
 		struct page *zero_page = get_huge_zero_page();
 
-		if (unlikely(!zero_page))
+		if (unlikely(!zero_page)) {
+			dax_pmd_dbg(&bh, address, "no zero page");
 			goto fallback;
+		}
 
 		ptl = pmd_lock(vma->vm_mm, pmd);
 		if (!pmd_none(*pmd)) {
 			spin_unlock(ptl);
+			dax_pmd_dbg(&bh, address, "pmd already present");
 			goto fallback;
 		}
 
+		dev_dbg(part_to_dev(bdev->bd_part),
+				"%s: %s addr: %lx pfn: <zero> sect: %llx\n",
+				__func__, current->comm, address,
+				(unsigned long long) to_sector(&bh, inode));
+
 		entry = mk_pmd(zero_page, vma->vm_page_prot);
 		entry = pmd_mkhuge(entry);
 		set_pmd_at(vma->vm_mm, pmd_addr, pmd, entry);
 		result = VM_FAULT_NOPAGE;
 		spin_unlock(ptl);
 	} else {
-		sector = bh.b_blocknr << (blkbits - 9);
-		length = bdev_direct_access(bh.b_bdev, sector, &kaddr, &pfn,
-						bh.b_size);
+		struct blk_dax_ctl dax = {
+			.sector = to_sector(&bh, inode),
+			.size = PMD_SIZE,
+		};
+		long length = dax_map_atomic(bdev, &dax);
+
 		if (length < 0) {
 			result = VM_FAULT_SIGBUS;
 			goto out;
 		}
-		if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR))
+		if (length < PMD_SIZE) {
+			dax_pmd_dbg(&bh, address, "dax-length too small");
+			dax_unmap_atomic(bdev, &dax);
+			goto fallback;
+		}
+		if (pfn_t_to_pfn(dax.pfn) & PG_PMD_COLOUR) {
+			dax_pmd_dbg(&bh, address, "pfn unaligned");
+			dax_unmap_atomic(bdev, &dax);
 			goto fallback;
+		}
+
+		if (!pfn_t_devmap(dax.pfn)) {
+			dax_unmap_atomic(bdev, &dax);
+			dax_pmd_dbg(&bh, address, "pfn not in memmap");
+			goto fallback;
+		}
 
 		if (buffer_unwritten(&bh) || buffer_new(&bh)) {
-			int i;
-			for (i = 0; i < PTRS_PER_PMD; i++)
-				clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE);
+			clear_pmem(dax.addr, PMD_SIZE);
 			wmb_pmem();
 			count_vm_event(PGMAJFAULT);
 			mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
 			result |= VM_FAULT_MAJOR;
 		}
+		dax_unmap_atomic(bdev, &dax);
+
+		/*
+		 * For PTE faults we insert a radix tree entry for reads, and
+		 * leave it clean.  Then on the first write we dirty the radix
+		 * tree entry via the dax_pfn_mkwrite() path.  This sequence
+		 * allows the dax_pfn_mkwrite() call to be simpler and avoid a
+		 * call into get_block() to translate the pgoff to a sector in
+		 * order to be able to create a new radix tree entry.
+		 *
+		 * 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()
+		 * 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.
+		 */
+		if (write) {
+			error = dax_radix_entry(mapping, pgoff, dax.sector,
+					true, true);
+			if (error) {
+				dax_pmd_dbg(&bh, address,
+						"PMD radix insertion failed");
+				goto fallback;
+			}
+		}
 
-		result |= vmf_insert_pfn_pmd(vma, address, pmd, pfn, write);
+		dev_dbg(part_to_dev(bdev->bd_part),
+				"%s: %s addr: %lx pfn: %lx sect: %llx\n",
+				__func__, current->comm, address,
+				pfn_t_to_pfn(dax.pfn),
+				(unsigned long long) dax.sector);
+		result |= vmf_insert_pfn_pmd(vma, address, pmd,
+				dax.pfn, write);
 	}
 
  out:
@@ -684,15 +1057,27 @@ EXPORT_SYMBOL_GPL(dax_pmd_fault);
  * dax_pfn_mkwrite - handle first write to DAX page
  * @vma: The virtual memory area where the fault occurred
  * @vmf: The description of the fault
- *
  */
 int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	struct super_block *sb = file_inode(vma->vm_file)->i_sb;
+	struct file *file = vma->vm_file;
+	int error;
 
-	sb_start_pagefault(sb);
-	file_update_time(vma->vm_file);
-	sb_end_pagefault(sb);
+	/*
+	 * We pass NO_SECTOR to dax_radix_entry() because we expect that a
+	 * RADIX_DAX_PTE entry already exists in the radix tree from a
+	 * previous call to __dax_fault().  We just want to look up that PTE
+	 * entry using vmf->pgoff and make sure the dirty tag is set.  This
+	 * saves us from having to make a call to get_block() here to look
+	 * up the sector.
+	 */
+	error = dax_radix_entry(file->f_mapping, vmf->pgoff, NO_SECTOR, false,
+			true);
+
+	if (error == -ENOMEM)
+		return VM_FAULT_OOM;
+	if (error)
+		return VM_FAULT_SIGBUS;
 	return VM_FAULT_NOPAGE;
 }
 EXPORT_SYMBOL_GPL(dax_pfn_mkwrite);
@@ -709,7 +1094,7 @@ EXPORT_SYMBOL_GPL(dax_pfn_mkwrite);
  * you are truncating a file, the helper function dax_truncate_page() may be
  * more convenient.
  *
- * We work in terms of PAGE_CACHE_SIZE here for commonality with
+ * We work in terms of PAGE_SIZE here for commonality with
  * block_truncate_page(), but we could go down to PAGE_SIZE if the filesystem
  * took care of disposing of the unnecessary blocks.  Even if the filesystem
  * block size is smaller than PAGE_SIZE, we have to zero the rest of the page
@@ -719,27 +1104,33 @@ int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length,
 							get_block_t get_block)
 {
 	struct buffer_head bh;
-	pgoff_t index = from >> PAGE_CACHE_SHIFT;
-	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	pgoff_t index = from >> PAGE_SHIFT;
+	unsigned offset = from & (PAGE_SIZE-1);
 	int err;
 
 	/* Block boundary? Nothing to do */
 	if (!length)
 		return 0;
-	BUG_ON((offset + length) > PAGE_CACHE_SIZE);
+	BUG_ON((offset + length) > PAGE_SIZE);
 
 	memset(&bh, 0, sizeof(bh));
-	bh.b_size = PAGE_CACHE_SIZE;
+	bh.b_bdev = inode->i_sb->s_bdev;
+	bh.b_size = PAGE_SIZE;
 	err = get_block(inode, index, &bh, 0);
 	if (err < 0)
 		return err;
 	if (buffer_written(&bh)) {
-		void __pmem *addr;
-		err = dax_get_addr(&bh, &addr, inode->i_blkbits);
-		if (err < 0)
-			return err;
-		clear_pmem(addr + offset, length);
+		struct block_device *bdev = bh.b_bdev;
+		struct blk_dax_ctl dax = {
+			.sector = to_sector(&bh, inode),
+			.size = PAGE_SIZE,
+		};
+
+		if (dax_map_atomic(bdev, &dax) < 0)
+			return PTR_ERR(dax.addr);
+		clear_pmem(dax.addr + offset, length);
 		wmb_pmem();
+		dax_unmap_atomic(bdev, &dax);
 	}
 
 	return 0;
@@ -755,7 +1146,7 @@ EXPORT_SYMBOL_GPL(dax_zero_page_range);
  * Similar to block_truncate_page(), this function can be called by a
  * filesystem when it is truncating a DAX file to handle the partial page.
  *
- * We work in terms of PAGE_CACHE_SIZE here for commonality with
+ * We work in terms of PAGE_SIZE here for commonality with
  * block_truncate_page(), but we could go down to PAGE_SIZE if the filesystem
  * took care of disposing of the unnecessary blocks.  Even if the filesystem
  * block size is smaller than PAGE_SIZE, we have to zero the rest of the page
@@ -763,7 +1154,7 @@ EXPORT_SYMBOL_GPL(dax_zero_page_range);
  */
 int dax_truncate_page(struct inode *inode, loff_t from, get_block_t get_block)
 {
-	unsigned length = PAGE_CACHE_ALIGN(from) - from;
+	unsigned length = PAGE_ALIGN(from) - from;
 	return dax_zero_page_range(inode, from, length, get_block);
 }
 EXPORT_SYMBOL_GPL(dax_truncate_page);
diff --git a/fs/dcache.c b/fs/dcache.c
index 5c33aeb0f68f..d5ecc6e477da 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -269,9 +269,6 @@ static inline int dname_external(const struct dentry *dentry)
 	return dentry->d_name.name != dentry->d_iname;
 }
 
-/*
- * Make sure other CPUs see the inode attached before the type is set.
- */
 static inline void __d_set_inode_and_type(struct dentry *dentry,
 					  struct inode *inode,
 					  unsigned type_flags)
@@ -279,28 +276,18 @@ static inline void __d_set_inode_and_type(struct dentry *dentry,
 	unsigned flags;
 
 	dentry->d_inode = inode;
-	smp_wmb();
 	flags = READ_ONCE(dentry->d_flags);
 	flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU);
 	flags |= type_flags;
 	WRITE_ONCE(dentry->d_flags, flags);
 }
 
-/*
- * Ideally, we want to make sure that other CPUs see the flags cleared before
- * the inode is detached, but this is really a violation of RCU principles
- * since the ordering suggests we should always set inode before flags.
- *
- * We should instead replace or discard the entire dentry - but that sucks
- * performancewise on mass deletion/rename.
- */
 static inline void __d_clear_type_and_inode(struct dentry *dentry)
 {
 	unsigned flags = READ_ONCE(dentry->d_flags);
 
 	flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU);
 	WRITE_ONCE(dentry->d_flags, flags);
-	smp_wmb();
 	dentry->d_inode = NULL;
 }
 
@@ -370,9 +357,11 @@ static void dentry_unlink_inode(struct dentry * dentry)
 	__releases(dentry->d_inode->i_lock)
 {
 	struct inode *inode = dentry->d_inode;
+
+	raw_write_seqcount_begin(&dentry->d_seq);
 	__d_clear_type_and_inode(dentry);
 	hlist_del_init(&dentry->d_u.d_alias);
-	dentry_rcuwalk_invalidate(dentry);
+	raw_write_seqcount_end(&dentry->d_seq);
 	spin_unlock(&dentry->d_lock);
 	spin_unlock(&inode->i_lock);
 	if (!inode->i_nlink)
@@ -1571,7 +1560,8 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 	dentry->d_iname[DNAME_INLINE_LEN-1] = 0;
 	if (name->len > DNAME_INLINE_LEN-1) {
 		size_t size = offsetof(struct external_name, name[1]);
-		struct external_name *p = kmalloc(size + name->len, GFP_KERNEL);
+		struct external_name *p = kmalloc(size + name->len,
+						  GFP_KERNEL_ACCOUNT);
 		if (!p) {
 			kmem_cache_free(dentry_cache, dentry); 
 			return NULL;
@@ -1677,7 +1667,8 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
 				DCACHE_OP_REVALIDATE	|
 				DCACHE_OP_WEAK_REVALIDATE	|
 				DCACHE_OP_DELETE	|
-				DCACHE_OP_SELECT_INODE));
+				DCACHE_OP_SELECT_INODE	|
+				DCACHE_OP_REAL));
 	dentry->d_op = op;
 	if (!op)
 		return;
@@ -1695,6 +1686,8 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
 		dentry->d_flags |= DCACHE_OP_PRUNE;
 	if (op->d_select_inode)
 		dentry->d_flags |= DCACHE_OP_SELECT_INODE;
+	if (op->d_real)
+		dentry->d_flags |= DCACHE_OP_REAL;
 
 }
 EXPORT_SYMBOL(d_set_d_op);
@@ -1734,7 +1727,7 @@ static unsigned d_flags_for_inode(struct inode *inode)
 	}
 
 	if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) {
-		if (unlikely(inode->i_op->follow_link)) {
+		if (unlikely(inode->i_op->get_link)) {
 			add_flags = DCACHE_SYMLINK_TYPE;
 			goto type_determined;
 		}
@@ -1755,12 +1748,12 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
 	unsigned add_flags = d_flags_for_inode(inode);
 
 	spin_lock(&dentry->d_lock);
-	if (inode)
-		hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
+	hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
+	raw_write_seqcount_begin(&dentry->d_seq);
 	__d_set_inode_and_type(dentry, inode, add_flags);
-	dentry_rcuwalk_invalidate(dentry);
+	raw_write_seqcount_end(&dentry->d_seq);
+	__fsnotify_d_instantiate(dentry);
 	spin_unlock(&dentry->d_lock);
-	fsnotify_d_instantiate(dentry, inode);
 }
 
 /**
@@ -1781,91 +1774,16 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
 void d_instantiate(struct dentry *entry, struct inode * inode)
 {
 	BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
-	if (inode)
+	if (inode) {
 		spin_lock(&inode->i_lock);
-	__d_instantiate(entry, inode);
-	if (inode)
+		__d_instantiate(entry, inode);
 		spin_unlock(&inode->i_lock);
+	}
 	security_d_instantiate(entry, inode);
 }
 EXPORT_SYMBOL(d_instantiate);
 
 /**
- * d_instantiate_unique - instantiate a non-aliased dentry
- * @entry: dentry to instantiate
- * @inode: inode to attach to this dentry
- *
- * Fill in inode information in the entry. On success, it returns NULL.
- * If an unhashed alias of "entry" already exists, then we return the
- * aliased dentry instead and drop one reference to inode.
- *
- * Note that in order to avoid conflicts with rename() etc, the caller
- * had better be holding the parent directory semaphore.
- *
- * This also assumes that the inode count has been incremented
- * (or otherwise set) by the caller to indicate that it is now
- * in use by the dcache.
- */
-static struct dentry *__d_instantiate_unique(struct dentry *entry,
-					     struct inode *inode)
-{
-	struct dentry *alias;
-	int len = entry->d_name.len;
-	const char *name = entry->d_name.name;
-	unsigned int hash = entry->d_name.hash;
-
-	if (!inode) {
-		__d_instantiate(entry, NULL);
-		return NULL;
-	}
-
-	hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
-		/*
-		 * Don't need alias->d_lock here, because aliases with
-		 * d_parent == entry->d_parent are not subject to name or
-		 * parent changes, because the parent inode i_mutex is held.
-		 */
-		if (alias->d_name.hash != hash)
-			continue;
-		if (alias->d_parent != entry->d_parent)
-			continue;
-		if (alias->d_name.len != len)
-			continue;
-		if (dentry_cmp(alias, name, len))
-			continue;
-		__dget(alias);
-		return alias;
-	}
-
-	__d_instantiate(entry, inode);
-	return NULL;
-}
-
-struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode)
-{
-	struct dentry *result;
-
-	BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
-
-	if (inode)
-		spin_lock(&inode->i_lock);
-	result = __d_instantiate_unique(entry, inode);
-	if (inode)
-		spin_unlock(&inode->i_lock);
-
-	if (!result) {
-		security_d_instantiate(entry, inode);
-		return NULL;
-	}
-
-	BUG_ON(!d_unhashed(result));
-	iput(inode);
-	return result;
-}
-
-EXPORT_SYMBOL(d_instantiate_unique);
-
-/**
  * d_instantiate_no_diralias - instantiate a non-aliased dentry
  * @entry: dentry to complete
  * @inode: inode to attach to this dentry
@@ -2445,6 +2363,86 @@ void d_rehash(struct dentry * entry)
 }
 EXPORT_SYMBOL(d_rehash);
 
+
+/* inode->i_lock held if inode is non-NULL */
+
+static inline void __d_add(struct dentry *dentry, struct inode *inode)
+{
+	if (inode) {
+		__d_instantiate(dentry, inode);
+		spin_unlock(&inode->i_lock);
+	}
+	security_d_instantiate(dentry, inode);
+	d_rehash(dentry);
+}
+
+/**
+ * d_add - add dentry to hash queues
+ * @entry: dentry to add
+ * @inode: The inode to attach to this dentry
+ *
+ * This adds the entry to the hash queues and initializes @inode.
+ * The entry was actually filled in earlier during d_alloc().
+ */
+
+void d_add(struct dentry *entry, struct inode *inode)
+{
+	if (inode)
+		spin_lock(&inode->i_lock);
+	__d_add(entry, inode);
+}
+EXPORT_SYMBOL(d_add);
+
+/**
+ * d_exact_alias - find and hash an exact unhashed alias
+ * @entry: dentry to add
+ * @inode: The inode to go with this dentry
+ *
+ * If an unhashed dentry with the same name/parent and desired
+ * inode already exists, hash and return it.  Otherwise, return
+ * NULL.
+ *
+ * Parent directory should be locked.
+ */
+struct dentry *d_exact_alias(struct dentry *entry, struct inode *inode)
+{
+	struct dentry *alias;
+	int len = entry->d_name.len;
+	const char *name = entry->d_name.name;
+	unsigned int hash = entry->d_name.hash;
+
+	spin_lock(&inode->i_lock);
+	hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
+		/*
+		 * Don't need alias->d_lock here, because aliases with
+		 * d_parent == entry->d_parent are not subject to name or
+		 * parent changes, because the parent inode i_mutex is held.
+		 */
+		if (alias->d_name.hash != hash)
+			continue;
+		if (alias->d_parent != entry->d_parent)
+			continue;
+		if (alias->d_name.len != len)
+			continue;
+		if (dentry_cmp(alias, name, len))
+			continue;
+		spin_lock(&alias->d_lock);
+		if (!d_unhashed(alias)) {
+			spin_unlock(&alias->d_lock);
+			alias = NULL;
+		} else {
+			__dget_dlock(alias);
+			_d_rehash(alias);
+			spin_unlock(&alias->d_lock);
+		}
+		spin_unlock(&inode->i_lock);
+		return alias;
+	}
+	spin_unlock(&inode->i_lock);
+	return NULL;
+}
+EXPORT_SYMBOL(d_exact_alias);
+
 /**
  * dentry_update_name_case - update case insensitive dentry with a new name
  * @dentry: dentry to be updated
@@ -2461,7 +2459,7 @@ EXPORT_SYMBOL(d_rehash);
  */
 void dentry_update_name_case(struct dentry *dentry, struct qstr *name)
 {
-	BUG_ON(!mutex_is_locked(&dentry->d_parent->d_inode->i_mutex));
+	BUG_ON(!inode_is_locked(dentry->d_parent->d_inode));
 	BUG_ON(dentry->d_name.len != name->len); /* d_lookup gives this */
 
 	spin_lock(&dentry->d_lock);
@@ -2737,7 +2735,7 @@ static int __d_unalias(struct inode *inode,
 	if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex))
 		goto out_err;
 	m1 = &dentry->d_sb->s_vfs_rename_mutex;
-	if (!mutex_trylock(&alias->d_parent->d_inode->i_mutex))
+	if (!inode_trylock(alias->d_parent->d_inode))
 		goto out_err;
 	m2 = &alias->d_parent->d_inode->i_mutex;
 out_unalias:
@@ -2781,10 +2779,9 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
 
 	BUG_ON(!d_unhashed(dentry));
 
-	if (!inode) {
-		__d_instantiate(dentry, NULL);
+	if (!inode)
 		goto out;
-	}
+
 	spin_lock(&inode->i_lock);
 	if (S_ISDIR(inode->i_mode)) {
 		struct dentry *new = __d_find_any_alias(inode);
@@ -2818,12 +2815,8 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
 			return new;
 		}
 	}
-	/* already taking inode->i_lock, so d_add() by hand */
-	__d_instantiate(dentry, inode);
-	spin_unlock(&inode->i_lock);
 out:
-	security_d_instantiate(dentry, inode);
-	d_rehash(dentry);
+	__d_add(dentry, inode);
 	return NULL;
 }
 EXPORT_SYMBOL(d_splice_alias);
@@ -3303,18 +3296,18 @@ out:
  * @new_dentry: new dentry
  * @old_dentry: old dentry
  *
- * Returns 1 if new_dentry is a subdirectory of the parent (at any depth).
- * Returns 0 otherwise.
+ * Returns true if new_dentry is a subdirectory of the parent (at any depth).
+ * Returns false otherwise.
  * Caller must ensure that "new_dentry" is pinned before calling is_subdir()
  */
   
-int is_subdir(struct dentry *new_dentry, struct dentry *old_dentry)
+bool is_subdir(struct dentry *new_dentry, struct dentry *old_dentry)
 {
-	int result;
+	bool result;
 	unsigned seq;
 
 	if (new_dentry == old_dentry)
-		return 1;
+		return true;
 
 	do {
 		/* for restarting inner loop in case of seq retry */
@@ -3325,9 +3318,9 @@ int is_subdir(struct dentry *new_dentry, struct dentry *old_dentry)
 		 */
 		rcu_read_lock();
 		if (d_ancestor(old_dentry, new_dentry))
-			result = 1;
+			result = true;
 		else
-			result = 0;
+			result = false;
 		rcu_read_unlock();
 	} while (read_seqretry(&rename_lock, seq));
 
@@ -3415,7 +3408,7 @@ static void __init dcache_init(void)
 	 * of the dcache. 
 	 */
 	dentry_cache = KMEM_CACHE(dentry,
-		SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD);
+		SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD|SLAB_ACCOUNT);
 
 	/* Hash may have been set up in dcache_init_early */
 	if (!hashdist)
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 5d8f35f1382a..8580831ed237 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -265,20 +265,24 @@ static struct dentry *start_creating(const char *name, struct dentry *parent)
 	if (!parent)
 		parent = debugfs_mount->mnt_root;
 
-	mutex_lock(&d_inode(parent)->i_mutex);
+	inode_lock(d_inode(parent));
 	dentry = lookup_one_len(name, parent, strlen(name));
 	if (!IS_ERR(dentry) && d_really_is_positive(dentry)) {
 		dput(dentry);
 		dentry = ERR_PTR(-EEXIST);
 	}
-	if (IS_ERR(dentry))
-		mutex_unlock(&d_inode(parent)->i_mutex);
+
+	if (IS_ERR(dentry)) {
+		inode_unlock(d_inode(parent));
+		simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+	}
+
 	return dentry;
 }
 
 static struct dentry *failed_creating(struct dentry *dentry)
 {
-	mutex_unlock(&d_inode(dentry->d_parent)->i_mutex);
+	inode_unlock(d_inode(dentry->d_parent));
 	dput(dentry);
 	simple_release_fs(&debugfs_mount, &debugfs_mount_count);
 	return NULL;
@@ -286,7 +290,7 @@ static struct dentry *failed_creating(struct dentry *dentry)
 
 static struct dentry *end_creating(struct dentry *dentry)
 {
-	mutex_unlock(&d_inode(dentry->d_parent)->i_mutex);
+	inode_unlock(d_inode(dentry->d_parent));
 	return dentry;
 }
 
@@ -453,7 +457,7 @@ struct dentry *debugfs_create_automount(const char *name,
 	if (unlikely(!inode))
 		return failed_creating(dentry);
 
-	inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
+	make_empty_dir_inode(inode);
 	inode->i_flags |= S_AUTOMOUNT;
 	inode->i_private = data;
 	dentry->d_fsdata = (void *)f;
@@ -556,9 +560,9 @@ void debugfs_remove(struct dentry *dentry)
 	if (!parent || d_really_is_negative(parent))
 		return;
 
-	mutex_lock(&d_inode(parent)->i_mutex);
+	inode_lock(d_inode(parent));
 	ret = __debugfs_remove(dentry, parent);
-	mutex_unlock(&d_inode(parent)->i_mutex);
+	inode_unlock(d_inode(parent));
 	if (!ret)
 		simple_release_fs(&debugfs_mount, &debugfs_mount_count);
 }
@@ -590,7 +594,7 @@ void debugfs_remove_recursive(struct dentry *dentry)
 
 	parent = dentry;
  down:
-	mutex_lock(&d_inode(parent)->i_mutex);
+	inode_lock(d_inode(parent));
  loop:
 	/*
 	 * The parent->d_subdirs is protected by the d_lock. Outside that
@@ -605,7 +609,7 @@ void debugfs_remove_recursive(struct dentry *dentry)
 		/* perhaps simple_empty(child) makes more sense */
 		if (!list_empty(&child->d_subdirs)) {
 			spin_unlock(&parent->d_lock);
-			mutex_unlock(&d_inode(parent)->i_mutex);
+			inode_unlock(d_inode(parent));
 			parent = child;
 			goto down;
 		}
@@ -626,10 +630,10 @@ void debugfs_remove_recursive(struct dentry *dentry)
 	}
 	spin_unlock(&parent->d_lock);
 
-	mutex_unlock(&d_inode(parent)->i_mutex);
+	inode_unlock(d_inode(parent));
 	child = parent;
 	parent = parent->d_parent;
-	mutex_lock(&d_inode(parent)->i_mutex);
+	inode_lock(d_inode(parent));
 
 	if (child != dentry)
 		/* go up */
@@ -637,7 +641,7 @@ void debugfs_remove_recursive(struct dentry *dentry)
 
 	if (!__debugfs_remove(child, parent))
 		simple_release_fs(&debugfs_mount, &debugfs_mount_count);
-	mutex_unlock(&d_inode(parent)->i_mutex);
+	inode_unlock(d_inode(parent));
 }
 EXPORT_SYMBOL_GPL(debugfs_remove_recursive);
 
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index c35ffdc12bba..655f21f99160 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -255,7 +255,7 @@ static int mknod_ptmx(struct super_block *sb)
 	if (!uid_valid(root_uid) || !gid_valid(root_gid))
 		return -EINVAL;
 
-	mutex_lock(&d_inode(root)->i_mutex);
+	inode_lock(d_inode(root));
 
 	/* If we have already created ptmx node, return */
 	if (fsi->ptmx_dentry) {
@@ -292,7 +292,7 @@ static int mknod_ptmx(struct super_block *sb)
 	fsi->ptmx_dentry = dentry;
 	rc = 0;
 out:
-	mutex_unlock(&d_inode(root)->i_mutex);
+	inode_unlock(d_inode(root));
 	return rc;
 }
 
@@ -575,6 +575,26 @@ void devpts_kill_index(struct inode *ptmx_inode, int idx)
 	mutex_unlock(&allocated_ptys_lock);
 }
 
+/*
+ * pty code needs to hold extra references in case of last /dev/tty close
+ */
+
+void devpts_add_ref(struct inode *ptmx_inode)
+{
+	struct super_block *sb = pts_sb_from_inode(ptmx_inode);
+
+	atomic_inc(&sb->s_active);
+	ihold(ptmx_inode);
+}
+
+void devpts_del_ref(struct inode *ptmx_inode)
+{
+	struct super_block *sb = pts_sb_from_inode(ptmx_inode);
+
+	iput(ptmx_inode);
+	deactivate_super(sb);
+}
+
 /**
  * devpts_pty_new -- create a new inode in /dev/pts/
  * @ptmx_inode: inode of the master
@@ -615,7 +635,7 @@ struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index,
 
 	sprintf(s, "%d", index);
 
-	mutex_lock(&d_inode(root)->i_mutex);
+	inode_lock(d_inode(root));
 
 	dentry = d_alloc_name(root, s);
 	if (dentry) {
@@ -626,7 +646,7 @@ struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index,
 		inode = ERR_PTR(-ENOMEM);
 	}
 
-	mutex_unlock(&d_inode(root)->i_mutex);
+	inode_unlock(d_inode(root));
 
 	return inode;
 }
@@ -671,7 +691,7 @@ void devpts_pty_kill(struct inode *inode)
 
 	BUG_ON(inode->i_rdev == MKDEV(TTYAUX_MAJOR, PTMX_MINOR));
 
-	mutex_lock(&d_inode(root)->i_mutex);
+	inode_lock(d_inode(root));
 
 	dentry = d_find_alias(inode);
 
@@ -680,7 +700,7 @@ void devpts_pty_kill(struct inode *inode)
 	dput(dentry);	/* d_alloc_name() in devpts_pty_new() */
 	dput(dentry);		/* d_find_alias above */
 
-	mutex_unlock(&d_inode(root)->i_mutex);
+	inode_unlock(d_inode(root));
 }
 
 static int __init init_devpts_fs(void)
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 3ae0e0427191..472037732daf 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -109,6 +109,8 @@ struct dio_submit {
 struct dio {
 	int flags;			/* doesn't change */
 	int rw;
+	blk_qc_t bio_cookie;
+	struct block_device *bio_bdev;
 	struct inode *inode;
 	loff_t i_size;			/* i_size when submitted */
 	dio_iodone_t *end_io;		/* IO completion function */
@@ -170,7 +172,7 @@ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio)
 		 */
 		if (dio->page_errors == 0)
 			dio->page_errors = ret;
-		page_cache_get(page);
+		get_page(page);
 		dio->pages[0] = page;
 		sdio->head = 0;
 		sdio->tail = 1;
@@ -251,8 +253,13 @@ static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret,
 	if (ret == 0)
 		ret = transferred;
 
-	if (dio->end_io && dio->result)
-		dio->end_io(dio->iocb, offset, transferred, dio->private);
+	if (dio->end_io) {
+		int err;
+
+		err = dio->end_io(dio->iocb, offset, ret, dio->private);
+		if (err)
+			ret = err;
+	}
 
 	if (!(dio->flags & DIO_SKIP_DIO_COUNT))
 		inode_dio_end(dio->inode);
@@ -361,7 +368,7 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio,
 
 	/*
 	 * bio_alloc() is guaranteed to return a bio when called with
-	 * __GFP_WAIT and we request a valid number of vectors.
+	 * __GFP_RECLAIM and we request a valid number of vectors.
 	 */
 	bio = bio_alloc(GFP_KERNEL, nr_vecs);
 
@@ -397,11 +404,14 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio)
 	if (dio->is_async && dio->rw == READ && dio->should_dirty)
 		bio_set_pages_dirty(bio);
 
-	if (sdio->submit_io)
+	dio->bio_bdev = bio->bi_bdev;
+
+	if (sdio->submit_io) {
 		sdio->submit_io(dio->rw, bio, dio->inode,
 			       sdio->logical_offset_in_bio);
-	else
-		submit_bio(dio->rw, bio);
+		dio->bio_cookie = BLK_QC_T_NONE;
+	} else
+		dio->bio_cookie = submit_bio(dio->rw, bio);
 
 	sdio->bio = NULL;
 	sdio->boundary = 0;
@@ -414,7 +424,7 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio)
 static inline void dio_cleanup(struct dio *dio, struct dio_submit *sdio)
 {
 	while (sdio->head < sdio->tail)
-		page_cache_release(dio->pages[sdio->head++]);
+		put_page(dio->pages[sdio->head++]);
 }
 
 /*
@@ -440,7 +450,9 @@ static struct bio *dio_await_one(struct dio *dio)
 		__set_current_state(TASK_UNINTERRUPTIBLE);
 		dio->waiter = current;
 		spin_unlock_irqrestore(&dio->bio_lock, flags);
-		io_schedule();
+		if (!(dio->iocb->ki_flags & IOCB_HIPRI) ||
+		    !blk_poll(bdev_get_queue(dio->bio_bdev), dio->bio_cookie))
+			io_schedule();
 		/* wake up sets us TASK_RUNNING */
 		spin_lock_irqsave(&dio->bio_lock, flags);
 		dio->waiter = NULL;
@@ -466,8 +478,8 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio)
 		dio->io_error = -EIO;
 
 	if (dio->is_async && dio->rw == READ && dio->should_dirty) {
-		bio_check_pages_dirty(bio);	/* transfers ownership */
 		err = bio->bi_error;
+		bio_check_pages_dirty(bio);	/* transfers ownership */
 	} else {
 		bio_for_each_segment_all(bvec, bio, i) {
 			struct page *page = bvec->bv_page;
@@ -475,7 +487,7 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio)
 			if (dio->rw == READ && !PageCompound(page) &&
 					dio->should_dirty)
 				set_page_dirty_lock(page);
-			page_cache_release(page);
+			put_page(page);
 		}
 		err = bio->bi_error;
 		bio_put(bio);
@@ -684,7 +696,7 @@ static inline int dio_bio_add_page(struct dio_submit *sdio)
 		 */
 		if ((sdio->cur_page_len + sdio->cur_page_offset) == PAGE_SIZE)
 			sdio->pages_in_io--;
-		page_cache_get(sdio->cur_page);
+		get_page(sdio->cur_page);
 		sdio->final_block_in_bio = sdio->cur_page_block +
 			(sdio->cur_page_len >> sdio->blkbits);
 		ret = 0;
@@ -798,13 +810,13 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page,
 	 */
 	if (sdio->cur_page) {
 		ret = dio_send_cur_page(dio, sdio, map_bh);
-		page_cache_release(sdio->cur_page);
+		put_page(sdio->cur_page);
 		sdio->cur_page = NULL;
 		if (ret)
 			return ret;
 	}
 
-	page_cache_get(page);		/* It is in dio */
+	get_page(page);		/* It is in dio */
 	sdio->cur_page = page;
 	sdio->cur_page_offset = offset;
 	sdio->cur_page_len = len;
@@ -818,7 +830,7 @@ out:
 	if (sdio->boundary) {
 		ret = dio_send_cur_page(dio, sdio, map_bh);
 		dio_bio_submit(dio, sdio);
-		page_cache_release(sdio->cur_page);
+		put_page(sdio->cur_page);
 		sdio->cur_page = NULL;
 	}
 	return ret;
@@ -935,7 +947,7 @@ static int do_direct_IO(struct dio *dio, struct dio_submit *sdio,
 
 				ret = get_more_blocks(dio, sdio, map_bh);
 				if (ret) {
-					page_cache_release(page);
+					put_page(page);
 					goto out;
 				}
 				if (!buffer_mapped(map_bh))
@@ -976,7 +988,7 @@ do_holes:
 
 				/* AKPM: eargh, -ENOTBLK is a hack */
 				if (dio->rw & WRITE) {
-					page_cache_release(page);
+					put_page(page);
 					return -ENOTBLK;
 				}
 
@@ -989,7 +1001,7 @@ do_holes:
 				if (sdio->block_in_file >=
 						i_size_aligned >> blkbits) {
 					/* We hit eof */
-					page_cache_release(page);
+					put_page(page);
 					goto out;
 				}
 				zero_user(page, from, 1 << blkbits);
@@ -1029,7 +1041,7 @@ do_holes:
 						  sdio->next_block_for_io,
 						  map_bh);
 			if (ret) {
-				page_cache_release(page);
+				put_page(page);
 				goto out;
 			}
 			sdio->next_block_for_io += this_chunk_blocks;
@@ -1045,7 +1057,7 @@ next_block:
 		}
 
 		/* Drop the ref which was taken in get_user_pages() */
-		page_cache_release(page);
+		put_page(page);
 	}
 out:
 	return ret;
@@ -1151,18 +1163,28 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 					iocb->ki_filp->f_mapping;
 
 			/* will be released by direct_io_worker */
-			mutex_lock(&inode->i_mutex);
+			inode_lock(inode);
 
 			retval = filemap_write_and_wait_range(mapping, offset,
 							      end - 1);
 			if (retval) {
-				mutex_unlock(&inode->i_mutex);
+				inode_unlock(inode);
 				kmem_cache_free(dio_cache, dio);
 				goto out;
 			}
 		}
 	}
 
+	/* Once we sampled i_size check for reads beyond EOF */
+	dio->i_size = i_size_read(inode);
+	if (iov_iter_rw(iter) == READ && offset >= dio->i_size) {
+		if (dio->flags & DIO_LOCKING)
+			inode_unlock(inode);
+		kmem_cache_free(dio_cache, dio);
+		retval = 0;
+		goto out;
+	}
+
 	/*
 	 * For file extending writes updating i_size before data writeouts
 	 * complete can expose uninitialized blocks in dumb filesystems.
@@ -1216,7 +1238,6 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 	sdio.next_block_for_io = -1;
 
 	dio->iocb = iocb;
-	dio->i_size = i_size_read(inode);
 
 	spin_lock_init(&dio->bio_lock);
 	dio->refcount = 1;
@@ -1260,7 +1281,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 		ret2 = dio_send_cur_page(dio, &sdio, &map_bh);
 		if (retval == 0)
 			retval = ret2;
-		page_cache_release(sdio.cur_page);
+		put_page(sdio.cur_page);
 		sdio.cur_page = NULL;
 	}
 	if (sdio.bio)
@@ -1280,7 +1301,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 	 * of protecting us from looking up uninitialized blocks.
 	 */
 	if (iov_iter_rw(iter) == READ && (dio->flags & DIO_LOCKING))
-		mutex_unlock(&dio->inode->i_mutex);
+		inode_unlock(dio->inode);
 
 	/*
 	 * The only time we want to leave bios in flight is when a successful
diff --git a/fs/dlm/config.c b/fs/dlm/config.c
index d521bddf876d..1669f6291c95 100644
--- a/fs/dlm/config.c
+++ b/fs/dlm/config.c
@@ -61,35 +61,8 @@ static struct config_item *make_node(struct config_group *, const char *);
 static void drop_node(struct config_group *, struct config_item *);
 static void release_node(struct config_item *);
 
-static ssize_t show_cluster(struct config_item *i, struct configfs_attribute *a,
-			    char *buf);
-static ssize_t store_cluster(struct config_item *i,
-			     struct configfs_attribute *a,
-			     const char *buf, size_t len);
-static ssize_t show_comm(struct config_item *i, struct configfs_attribute *a,
-			 char *buf);
-static ssize_t store_comm(struct config_item *i, struct configfs_attribute *a,
-			  const char *buf, size_t len);
-static ssize_t show_node(struct config_item *i, struct configfs_attribute *a,
-			 char *buf);
-static ssize_t store_node(struct config_item *i, struct configfs_attribute *a,
-			  const char *buf, size_t len);
-
-static ssize_t comm_nodeid_read(struct dlm_comm *cm, char *buf);
-static ssize_t comm_nodeid_write(struct dlm_comm *cm, const char *buf,
-				size_t len);
-static ssize_t comm_local_read(struct dlm_comm *cm, char *buf);
-static ssize_t comm_local_write(struct dlm_comm *cm, const char *buf,
-				size_t len);
-static ssize_t comm_addr_write(struct dlm_comm *cm, const char *buf,
-				size_t len);
-static ssize_t comm_addr_list_read(struct dlm_comm *cm, char *buf);
-static ssize_t node_nodeid_read(struct dlm_node *nd, char *buf);
-static ssize_t node_nodeid_write(struct dlm_node *nd, const char *buf,
-				size_t len);
-static ssize_t node_weight_read(struct dlm_node *nd, char *buf);
-static ssize_t node_weight_write(struct dlm_node *nd, const char *buf,
-				size_t len);
+static struct configfs_attribute *comm_attrs[];
+static struct configfs_attribute *node_attrs[];
 
 struct dlm_cluster {
 	struct config_group group;
@@ -108,6 +81,12 @@ struct dlm_cluster {
 	char cl_cluster_name[DLM_LOCKSPACE_LEN];
 };
 
+static struct dlm_cluster *config_item_to_cluster(struct config_item *i)
+{
+	return i ? container_of(to_config_group(i), struct dlm_cluster, group) :
+		   NULL;
+}
+
 enum {
 	CLUSTER_ATTR_TCP_PORT = 0,
 	CLUSTER_ATTR_BUFFER_SIZE,
@@ -124,33 +103,24 @@ enum {
 	CLUSTER_ATTR_CLUSTER_NAME,
 };
 
-struct cluster_attribute {
-	struct configfs_attribute attr;
-	ssize_t (*show)(struct dlm_cluster *, char *);
-	ssize_t (*store)(struct dlm_cluster *, const char *, size_t);
-};
-
-static ssize_t cluster_cluster_name_read(struct dlm_cluster *cl, char *buf)
+static ssize_t cluster_cluster_name_show(struct config_item *item, char *buf)
 {
+	struct dlm_cluster *cl = config_item_to_cluster(item);
 	return sprintf(buf, "%s\n", cl->cl_cluster_name);
 }
 
-static ssize_t cluster_cluster_name_write(struct dlm_cluster *cl,
+static ssize_t cluster_cluster_name_store(struct config_item *item,
 					  const char *buf, size_t len)
 {
+	struct dlm_cluster *cl = config_item_to_cluster(item);
+
 	strlcpy(dlm_config.ci_cluster_name, buf,
 				sizeof(dlm_config.ci_cluster_name));
 	strlcpy(cl->cl_cluster_name, buf, sizeof(cl->cl_cluster_name));
 	return len;
 }
 
-static struct cluster_attribute cluster_attr_cluster_name = {
-	.attr   = { .ca_owner = THIS_MODULE,
-                    .ca_name = "cluster_name",
-                    .ca_mode = S_IRUGO | S_IWUSR },
-	.show   = cluster_cluster_name_read,
-	.store  = cluster_cluster_name_write,
-};
+CONFIGFS_ATTR(cluster_, cluster_name);
 
 static ssize_t cluster_set(struct dlm_cluster *cl, unsigned int *cl_field,
 			   int *info_field, int check_zero,
@@ -175,17 +145,19 @@ static ssize_t cluster_set(struct dlm_cluster *cl, unsigned int *cl_field,
 }
 
 #define CLUSTER_ATTR(name, check_zero)                                        \
-static ssize_t name##_write(struct dlm_cluster *cl, const char *buf, size_t len) \
+static ssize_t cluster_##name##_store(struct config_item *item, \
+		const char *buf, size_t len) \
 {                                                                             \
+	struct dlm_cluster *cl = config_item_to_cluster(item);		      \
 	return cluster_set(cl, &cl->cl_##name, &dlm_config.ci_##name,         \
 			   check_zero, buf, len);                             \
 }                                                                             \
-static ssize_t name##_read(struct dlm_cluster *cl, char *buf)                 \
+static ssize_t cluster_##name##_show(struct config_item *item, char *buf)     \
 {                                                                             \
+	struct dlm_cluster *cl = config_item_to_cluster(item);		      \
 	return snprintf(buf, PAGE_SIZE, "%u\n", cl->cl_##name);               \
 }                                                                             \
-static struct cluster_attribute cluster_attr_##name =                         \
-__CONFIGFS_ATTR(name, 0644, name##_read, name##_write)
+CONFIGFS_ATTR(cluster_, name);
 
 CLUSTER_ATTR(tcp_port, 1);
 CLUSTER_ATTR(buffer_size, 1);
@@ -201,19 +173,19 @@ CLUSTER_ATTR(new_rsb_count, 0);
 CLUSTER_ATTR(recover_callbacks, 0);
 
 static struct configfs_attribute *cluster_attrs[] = {
-	[CLUSTER_ATTR_TCP_PORT] = &cluster_attr_tcp_port.attr,
-	[CLUSTER_ATTR_BUFFER_SIZE] = &cluster_attr_buffer_size.attr,
-	[CLUSTER_ATTR_RSBTBL_SIZE] = &cluster_attr_rsbtbl_size.attr,
-	[CLUSTER_ATTR_RECOVER_TIMER] = &cluster_attr_recover_timer.attr,
-	[CLUSTER_ATTR_TOSS_SECS] = &cluster_attr_toss_secs.attr,
-	[CLUSTER_ATTR_SCAN_SECS] = &cluster_attr_scan_secs.attr,
-	[CLUSTER_ATTR_LOG_DEBUG] = &cluster_attr_log_debug.attr,
-	[CLUSTER_ATTR_PROTOCOL] = &cluster_attr_protocol.attr,
-	[CLUSTER_ATTR_TIMEWARN_CS] = &cluster_attr_timewarn_cs.attr,
-	[CLUSTER_ATTR_WAITWARN_US] = &cluster_attr_waitwarn_us.attr,
-	[CLUSTER_ATTR_NEW_RSB_COUNT] = &cluster_attr_new_rsb_count.attr,
-	[CLUSTER_ATTR_RECOVER_CALLBACKS] = &cluster_attr_recover_callbacks.attr,
-	[CLUSTER_ATTR_CLUSTER_NAME] = &cluster_attr_cluster_name.attr,
+	[CLUSTER_ATTR_TCP_PORT] = &cluster_attr_tcp_port,
+	[CLUSTER_ATTR_BUFFER_SIZE] = &cluster_attr_buffer_size,
+	[CLUSTER_ATTR_RSBTBL_SIZE] = &cluster_attr_rsbtbl_size,
+	[CLUSTER_ATTR_RECOVER_TIMER] = &cluster_attr_recover_timer,
+	[CLUSTER_ATTR_TOSS_SECS] = &cluster_attr_toss_secs,
+	[CLUSTER_ATTR_SCAN_SECS] = &cluster_attr_scan_secs,
+	[CLUSTER_ATTR_LOG_DEBUG] = &cluster_attr_log_debug,
+	[CLUSTER_ATTR_PROTOCOL] = &cluster_attr_protocol,
+	[CLUSTER_ATTR_TIMEWARN_CS] = &cluster_attr_timewarn_cs,
+	[CLUSTER_ATTR_WAITWARN_US] = &cluster_attr_waitwarn_us,
+	[CLUSTER_ATTR_NEW_RSB_COUNT] = &cluster_attr_new_rsb_count,
+	[CLUSTER_ATTR_RECOVER_CALLBACKS] = &cluster_attr_recover_callbacks,
+	[CLUSTER_ATTR_CLUSTER_NAME] = &cluster_attr_cluster_name,
 	NULL,
 };
 
@@ -224,83 +196,11 @@ enum {
 	COMM_ATTR_ADDR_LIST,
 };
 
-struct comm_attribute {
-	struct configfs_attribute attr;
-	ssize_t (*show)(struct dlm_comm *, char *);
-	ssize_t (*store)(struct dlm_comm *, const char *, size_t);
-};
-
-static struct comm_attribute comm_attr_nodeid = {
-	.attr   = { .ca_owner = THIS_MODULE,
-                    .ca_name = "nodeid",
-                    .ca_mode = S_IRUGO | S_IWUSR },
-	.show   = comm_nodeid_read,
-	.store  = comm_nodeid_write,
-};
-
-static struct comm_attribute comm_attr_local = {
-	.attr   = { .ca_owner = THIS_MODULE,
-                    .ca_name = "local",
-                    .ca_mode = S_IRUGO | S_IWUSR },
-	.show   = comm_local_read,
-	.store  = comm_local_write,
-};
-
-static struct comm_attribute comm_attr_addr = {
-	.attr   = { .ca_owner = THIS_MODULE,
-                    .ca_name = "addr",
-                    .ca_mode = S_IWUSR },
-	.store  = comm_addr_write,
-};
-
-static struct comm_attribute comm_attr_addr_list = {
-	.attr   = { .ca_owner = THIS_MODULE,
-                    .ca_name = "addr_list",
-                    .ca_mode = S_IRUGO },
-	.show   = comm_addr_list_read,
-};
-
-static struct configfs_attribute *comm_attrs[] = {
-	[COMM_ATTR_NODEID] = &comm_attr_nodeid.attr,
-	[COMM_ATTR_LOCAL] = &comm_attr_local.attr,
-	[COMM_ATTR_ADDR] = &comm_attr_addr.attr,
-	[COMM_ATTR_ADDR_LIST] = &comm_attr_addr_list.attr,
-	NULL,
-};
-
 enum {
 	NODE_ATTR_NODEID = 0,
 	NODE_ATTR_WEIGHT,
 };
 
-struct node_attribute {
-	struct configfs_attribute attr;
-	ssize_t (*show)(struct dlm_node *, char *);
-	ssize_t (*store)(struct dlm_node *, const char *, size_t);
-};
-
-static struct node_attribute node_attr_nodeid = {
-	.attr   = { .ca_owner = THIS_MODULE,
-                    .ca_name = "nodeid",
-                    .ca_mode = S_IRUGO | S_IWUSR },
-	.show   = node_nodeid_read,
-	.store  = node_nodeid_write,
-};
-
-static struct node_attribute node_attr_weight = {
-	.attr   = { .ca_owner = THIS_MODULE,
-                    .ca_name = "weight",
-                    .ca_mode = S_IRUGO | S_IWUSR },
-	.show   = node_weight_read,
-	.store  = node_weight_write,
-};
-
-static struct configfs_attribute *node_attrs[] = {
-	[NODE_ATTR_NODEID] = &node_attr_nodeid.attr,
-	[NODE_ATTR_WEIGHT] = &node_attr_weight.attr,
-	NULL,
-};
-
 struct dlm_clusters {
 	struct configfs_subsystem subsys;
 };
@@ -349,8 +249,6 @@ static struct configfs_group_operations clusters_ops = {
 
 static struct configfs_item_operations cluster_ops = {
 	.release = release_cluster,
-	.show_attribute = show_cluster,
-	.store_attribute = store_cluster,
 };
 
 static struct configfs_group_operations spaces_ops = {
@@ -369,8 +267,6 @@ static struct configfs_group_operations comms_ops = {
 
 static struct configfs_item_operations comm_ops = {
 	.release = release_comm,
-	.show_attribute = show_comm,
-	.store_attribute = store_comm,
 };
 
 static struct configfs_group_operations nodes_ops = {
@@ -380,8 +276,6 @@ static struct configfs_group_operations nodes_ops = {
 
 static struct configfs_item_operations node_ops = {
 	.release = release_node,
-	.show_attribute = show_node,
-	.store_attribute = store_node,
 };
 
 static struct config_item_type clusters_type = {
@@ -427,12 +321,6 @@ static struct config_item_type node_type = {
 	.ct_owner = THIS_MODULE,
 };
 
-static struct dlm_cluster *config_item_to_cluster(struct config_item *i)
-{
-	return i ? container_of(to_config_group(i), struct dlm_cluster, group) :
-		   NULL;
-}
-
 static struct dlm_space *config_item_to_space(struct config_item *i)
 {
 	return i ? container_of(to_config_group(i), struct dlm_space, group) :
@@ -455,24 +343,20 @@ static struct config_group *make_cluster(struct config_group *g,
 	struct dlm_cluster *cl = NULL;
 	struct dlm_spaces *sps = NULL;
 	struct dlm_comms *cms = NULL;
-	void *gps = NULL;
 
 	cl = kzalloc(sizeof(struct dlm_cluster), GFP_NOFS);
-	gps = kcalloc(3, sizeof(struct config_group *), GFP_NOFS);
 	sps = kzalloc(sizeof(struct dlm_spaces), GFP_NOFS);
 	cms = kzalloc(sizeof(struct dlm_comms), GFP_NOFS);
 
-	if (!cl || !gps || !sps || !cms)
+	if (!cl || !sps || !cms)
 		goto fail;
 
 	config_group_init_type_name(&cl->group, name, &cluster_type);
 	config_group_init_type_name(&sps->ss_group, "spaces", &spaces_type);
 	config_group_init_type_name(&cms->cs_group, "comms", &comms_type);
 
-	cl->group.default_groups = gps;
-	cl->group.default_groups[0] = &sps->ss_group;
-	cl->group.default_groups[1] = &cms->cs_group;
-	cl->group.default_groups[2] = NULL;
+	configfs_add_default_group(&sps->ss_group, &cl->group);
+	configfs_add_default_group(&cms->cs_group, &cl->group);
 
 	cl->cl_tcp_port = dlm_config.ci_tcp_port;
 	cl->cl_buffer_size = dlm_config.ci_buffer_size;
@@ -495,7 +379,6 @@ static struct config_group *make_cluster(struct config_group *g,
 
  fail:
 	kfree(cl);
-	kfree(gps);
 	kfree(sps);
 	kfree(cms);
 	return ERR_PTR(-ENOMEM);
@@ -504,14 +387,8 @@ static struct config_group *make_cluster(struct config_group *g,
 static void drop_cluster(struct config_group *g, struct config_item *i)
 {
 	struct dlm_cluster *cl = config_item_to_cluster(i);
-	struct config_item *tmp;
-	int j;
 
-	for (j = 0; cl->group.default_groups[j]; j++) {
-		tmp = &cl->group.default_groups[j]->cg_item;
-		cl->group.default_groups[j] = NULL;
-		config_item_put(tmp);
-	}
+	configfs_remove_default_groups(&cl->group);
 
 	space_list = NULL;
 	comm_list = NULL;
@@ -522,7 +399,6 @@ static void drop_cluster(struct config_group *g, struct config_item *i)
 static void release_cluster(struct config_item *i)
 {
 	struct dlm_cluster *cl = config_item_to_cluster(i);
-	kfree(cl->group.default_groups);
 	kfree(cl);
 }
 
@@ -530,21 +406,17 @@ static struct config_group *make_space(struct config_group *g, const char *name)
 {
 	struct dlm_space *sp = NULL;
 	struct dlm_nodes *nds = NULL;
-	void *gps = NULL;
 
 	sp = kzalloc(sizeof(struct dlm_space), GFP_NOFS);
-	gps = kcalloc(2, sizeof(struct config_group *), GFP_NOFS);
 	nds = kzalloc(sizeof(struct dlm_nodes), GFP_NOFS);
 
-	if (!sp || !gps || !nds)
+	if (!sp || !nds)
 		goto fail;
 
 	config_group_init_type_name(&sp->group, name, &space_type);
-	config_group_init_type_name(&nds->ns_group, "nodes", &nodes_type);
 
-	sp->group.default_groups = gps;
-	sp->group.default_groups[0] = &nds->ns_group;
-	sp->group.default_groups[1] = NULL;
+	config_group_init_type_name(&nds->ns_group, "nodes", &nodes_type);
+	configfs_add_default_group(&nds->ns_group, &sp->group);
 
 	INIT_LIST_HEAD(&sp->members);
 	mutex_init(&sp->members_lock);
@@ -553,7 +425,6 @@ static struct config_group *make_space(struct config_group *g, const char *name)
 
  fail:
 	kfree(sp);
-	kfree(gps);
 	kfree(nds);
 	return ERR_PTR(-ENOMEM);
 }
@@ -561,24 +432,16 @@ static struct config_group *make_space(struct config_group *g, const char *name)
 static void drop_space(struct config_group *g, struct config_item *i)
 {
 	struct dlm_space *sp = config_item_to_space(i);
-	struct config_item *tmp;
-	int j;
 
 	/* assert list_empty(&sp->members) */
 
-	for (j = 0; sp->group.default_groups[j]; j++) {
-		tmp = &sp->group.default_groups[j]->cg_item;
-		sp->group.default_groups[j] = NULL;
-		config_item_put(tmp);
-	}
-
+	configfs_remove_default_groups(&sp->group);
 	config_item_put(i);
 }
 
 static void release_space(struct config_item *i)
 {
 	struct dlm_space *sp = config_item_to_space(i);
-	kfree(sp->group.default_groups);
 	kfree(sp);
 }
 
@@ -687,66 +550,30 @@ void dlm_config_exit(void)
  * Functions for user space to read/write attributes
  */
 
-static ssize_t show_cluster(struct config_item *i, struct configfs_attribute *a,
-			    char *buf)
+static ssize_t comm_nodeid_show(struct config_item *item, char *buf)
 {
-	struct dlm_cluster *cl = config_item_to_cluster(i);
-	struct cluster_attribute *cla =
-			container_of(a, struct cluster_attribute, attr);
-	return cla->show ? cla->show(cl, buf) : 0;
+	return sprintf(buf, "%d\n", config_item_to_comm(item)->nodeid);
 }
 
-static ssize_t store_cluster(struct config_item *i,
-			     struct configfs_attribute *a,
-			     const char *buf, size_t len)
-{
-	struct dlm_cluster *cl = config_item_to_cluster(i);
-	struct cluster_attribute *cla =
-		container_of(a, struct cluster_attribute, attr);
-	return cla->store ? cla->store(cl, buf, len) : -EINVAL;
-}
-
-static ssize_t show_comm(struct config_item *i, struct configfs_attribute *a,
-			 char *buf)
-{
-	struct dlm_comm *cm = config_item_to_comm(i);
-	struct comm_attribute *cma =
-			container_of(a, struct comm_attribute, attr);
-	return cma->show ? cma->show(cm, buf) : 0;
-}
-
-static ssize_t store_comm(struct config_item *i, struct configfs_attribute *a,
-			  const char *buf, size_t len)
-{
-	struct dlm_comm *cm = config_item_to_comm(i);
-	struct comm_attribute *cma =
-		container_of(a, struct comm_attribute, attr);
-	return cma->store ? cma->store(cm, buf, len) : -EINVAL;
-}
-
-static ssize_t comm_nodeid_read(struct dlm_comm *cm, char *buf)
-{
-	return sprintf(buf, "%d\n", cm->nodeid);
-}
-
-static ssize_t comm_nodeid_write(struct dlm_comm *cm, const char *buf,
+static ssize_t comm_nodeid_store(struct config_item *item, const char *buf,
 				 size_t len)
 {
-	int rc = kstrtoint(buf, 0, &cm->nodeid);
+	int rc = kstrtoint(buf, 0, &config_item_to_comm(item)->nodeid);
 
 	if (rc)
 		return rc;
 	return len;
 }
 
-static ssize_t comm_local_read(struct dlm_comm *cm, char *buf)
+static ssize_t comm_local_show(struct config_item *item, char *buf)
 {
-	return sprintf(buf, "%d\n", cm->local);
+	return sprintf(buf, "%d\n", config_item_to_comm(item)->local);
 }
 
-static ssize_t comm_local_write(struct dlm_comm *cm, const char *buf,
+static ssize_t comm_local_store(struct config_item *item, const char *buf,
 				size_t len)
 {
+	struct dlm_comm *cm = config_item_to_comm(item);
 	int rc = kstrtoint(buf, 0, &cm->local);
 
 	if (rc)
@@ -756,8 +583,10 @@ static ssize_t comm_local_write(struct dlm_comm *cm, const char *buf,
 	return len;
 }
 
-static ssize_t comm_addr_write(struct dlm_comm *cm, const char *buf, size_t len)
+static ssize_t comm_addr_store(struct config_item *item, const char *buf,
+		size_t len)
 {
+	struct dlm_comm *cm = config_item_to_comm(item);
 	struct sockaddr_storage *addr;
 	int rv;
 
@@ -783,8 +612,9 @@ static ssize_t comm_addr_write(struct dlm_comm *cm, const char *buf, size_t len)
 	return len;
 }
 
-static ssize_t comm_addr_list_read(struct dlm_comm *cm, char *buf)
+static ssize_t comm_addr_list_show(struct config_item *item, char *buf)
 {
+	struct dlm_comm *cm = config_item_to_comm(item);
 	ssize_t s;
 	ssize_t allowance;
 	int i;
@@ -827,32 +657,28 @@ static ssize_t comm_addr_list_read(struct dlm_comm *cm, char *buf)
 	return 4096 - allowance;
 }
 
-static ssize_t show_node(struct config_item *i, struct configfs_attribute *a,
-			 char *buf)
-{
-	struct dlm_node *nd = config_item_to_node(i);
-	struct node_attribute *nda =
-			container_of(a, struct node_attribute, attr);
-	return nda->show ? nda->show(nd, buf) : 0;
-}
+CONFIGFS_ATTR(comm_, nodeid);
+CONFIGFS_ATTR(comm_, local);
+CONFIGFS_ATTR_WO(comm_, addr);
+CONFIGFS_ATTR_RO(comm_, addr_list);
 
-static ssize_t store_node(struct config_item *i, struct configfs_attribute *a,
-			  const char *buf, size_t len)
-{
-	struct dlm_node *nd = config_item_to_node(i);
-	struct node_attribute *nda =
-		container_of(a, struct node_attribute, attr);
-	return nda->store ? nda->store(nd, buf, len) : -EINVAL;
-}
+static struct configfs_attribute *comm_attrs[] = {
+	[COMM_ATTR_NODEID] = &comm_attr_nodeid,
+	[COMM_ATTR_LOCAL] = &comm_attr_local,
+	[COMM_ATTR_ADDR] = &comm_attr_addr,
+	[COMM_ATTR_ADDR_LIST] = &comm_attr_addr_list,
+	NULL,
+};
 
-static ssize_t node_nodeid_read(struct dlm_node *nd, char *buf)
+static ssize_t node_nodeid_show(struct config_item *item, char *buf)
 {
-	return sprintf(buf, "%d\n", nd->nodeid);
+	return sprintf(buf, "%d\n", config_item_to_node(item)->nodeid);
 }
 
-static ssize_t node_nodeid_write(struct dlm_node *nd, const char *buf,
+static ssize_t node_nodeid_store(struct config_item *item, const char *buf,
 				 size_t len)
 {
+	struct dlm_node *nd = config_item_to_node(item);
 	uint32_t seq = 0;
 	int rc = kstrtoint(buf, 0, &nd->nodeid);
 
@@ -863,21 +689,30 @@ static ssize_t node_nodeid_write(struct dlm_node *nd, const char *buf,
 	return len;
 }
 
-static ssize_t node_weight_read(struct dlm_node *nd, char *buf)
+static ssize_t node_weight_show(struct config_item *item, char *buf)
 {
-	return sprintf(buf, "%d\n", nd->weight);
+	return sprintf(buf, "%d\n", config_item_to_node(item)->weight);
 }
 
-static ssize_t node_weight_write(struct dlm_node *nd, const char *buf,
+static ssize_t node_weight_store(struct config_item *item, const char *buf,
 				 size_t len)
 {
-	int rc = kstrtoint(buf, 0, &nd->weight);
+	int rc = kstrtoint(buf, 0, &config_item_to_node(item)->weight);
 
 	if (rc)
 		return rc;
 	return len;
 }
 
+CONFIGFS_ATTR(node_, nodeid);
+CONFIGFS_ATTR(node_, weight);
+
+static struct configfs_attribute *node_attrs[] = {
+	[NODE_ATTR_NODEID] = &node_attr_nodeid,
+	[NODE_ATTR_WEIGHT] = &node_attr_weight,
+	NULL,
+};
+
 /*
  * Functions for the dlm to get the info that's been configured
  */
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 87e9d796cf7d..1ab012a27d9f 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -124,7 +124,10 @@ struct connection {
 	struct connection *othercon;
 	struct work_struct rwork; /* Receive workqueue */
 	struct work_struct swork; /* Send workqueue */
-	void (*orig_error_report)(struct sock *sk);
+	void (*orig_error_report)(struct sock *);
+	void (*orig_data_ready)(struct sock *);
+	void (*orig_state_change)(struct sock *);
+	void (*orig_write_space)(struct sock *);
 };
 #define sock2con(x) ((struct connection *)(x)->sk_user_data)
 
@@ -421,7 +424,7 @@ static void lowcomms_write_space(struct sock *sk)
 
 	if (test_and_clear_bit(CF_APP_LIMITED, &con->flags)) {
 		con->sock->sk->sk_write_pending--;
-		clear_bit(SOCK_ASYNC_NOSPACE, &con->sock->flags);
+		clear_bit(SOCKWQ_ASYNC_NOSPACE, &con->sock->flags);
 	}
 
 	if (!test_and_set_bit(CF_WRITE_PENDING, &con->flags))
@@ -467,16 +470,24 @@ int dlm_lowcomms_connect_node(int nodeid)
 
 static void lowcomms_error_report(struct sock *sk)
 {
-	struct connection *con = sock2con(sk);
+	struct connection *con;
 	struct sockaddr_storage saddr;
+	int buflen;
+	void (*orig_report)(struct sock *) = NULL;
 
-	if (nodeid_to_addr(con->nodeid, &saddr, NULL, false)) {
+	read_lock_bh(&sk->sk_callback_lock);
+	con = sock2con(sk);
+	if (con == NULL)
+		goto out;
+
+	orig_report = con->orig_error_report;
+	if (con->sock == NULL ||
+	    kernel_getpeername(con->sock, (struct sockaddr *)&saddr, &buflen)) {
 		printk_ratelimited(KERN_ERR "dlm: node %d: socket error "
 				   "sending to node %d, port %d, "
 				   "sk_err=%d/%d\n", dlm_our_nodeid(),
 				   con->nodeid, dlm_config.ci_tcp_port,
 				   sk->sk_err, sk->sk_err_soft);
-		return;
 	} else if (saddr.ss_family == AF_INET) {
 		struct sockaddr_in *sin4 = (struct sockaddr_in *)&saddr;
 
@@ -499,22 +510,54 @@ static void lowcomms_error_report(struct sock *sk)
 				   dlm_config.ci_tcp_port, sk->sk_err,
 				   sk->sk_err_soft);
 	}
-	con->orig_error_report(sk);
+out:
+	read_unlock_bh(&sk->sk_callback_lock);
+	if (orig_report)
+		orig_report(sk);
+}
+
+/* Note: sk_callback_lock must be locked before calling this function. */
+static void save_callbacks(struct connection *con, struct sock *sk)
+{
+	lock_sock(sk);
+	con->orig_data_ready = sk->sk_data_ready;
+	con->orig_state_change = sk->sk_state_change;
+	con->orig_write_space = sk->sk_write_space;
+	con->orig_error_report = sk->sk_error_report;
+	release_sock(sk);
+}
+
+static void restore_callbacks(struct connection *con, struct sock *sk)
+{
+	write_lock_bh(&sk->sk_callback_lock);
+	lock_sock(sk);
+	sk->sk_user_data = NULL;
+	sk->sk_data_ready = con->orig_data_ready;
+	sk->sk_state_change = con->orig_state_change;
+	sk->sk_write_space = con->orig_write_space;
+	sk->sk_error_report = con->orig_error_report;
+	release_sock(sk);
+	write_unlock_bh(&sk->sk_callback_lock);
 }
 
 /* Make a socket active */
 static void add_sock(struct socket *sock, struct connection *con)
 {
+	struct sock *sk = sock->sk;
+
+	write_lock_bh(&sk->sk_callback_lock);
 	con->sock = sock;
 
+	sk->sk_user_data = con;
+	if (!test_bit(CF_IS_OTHERCON, &con->flags))
+		save_callbacks(con, sk);
 	/* Install a data_ready callback */
-	con->sock->sk->sk_data_ready = lowcomms_data_ready;
-	con->sock->sk->sk_write_space = lowcomms_write_space;
-	con->sock->sk->sk_state_change = lowcomms_state_change;
-	con->sock->sk->sk_user_data = con;
-	con->sock->sk->sk_allocation = GFP_NOFS;
-	con->orig_error_report = con->sock->sk->sk_error_report;
-	con->sock->sk->sk_error_report = lowcomms_error_report;
+	sk->sk_data_ready = lowcomms_data_ready;
+	sk->sk_write_space = lowcomms_write_space;
+	sk->sk_state_change = lowcomms_state_change;
+	sk->sk_allocation = GFP_NOFS;
+	sk->sk_error_report = lowcomms_error_report;
+	write_unlock_bh(&sk->sk_callback_lock);
 }
 
 /* Add the port number to an IPv6 or 4 sockaddr and return the address
@@ -549,6 +592,8 @@ static void close_connection(struct connection *con, bool and_other,
 
 	mutex_lock(&con->sock_mutex);
 	if (con->sock) {
+		if (!test_bit(CF_IS_OTHERCON, &con->flags))
+			restore_callbacks(con, con->sock->sk);
 		sock_release(con->sock);
 		con->sock = NULL;
 	}
@@ -595,7 +640,7 @@ static int receive_from_sock(struct connection *con)
 		con->rx_page = alloc_page(GFP_ATOMIC);
 		if (con->rx_page == NULL)
 			goto out_resched;
-		cbuf_init(&con->cb, PAGE_CACHE_SIZE);
+		cbuf_init(&con->cb, PAGE_SIZE);
 	}
 
 	/*
@@ -612,7 +657,7 @@ static int receive_from_sock(struct connection *con)
 	 * buffer and the start of the currently used section (cb.base)
 	 */
 	if (cbuf_data(&con->cb) >= con->cb.base) {
-		iov[0].iov_len = PAGE_CACHE_SIZE - cbuf_data(&con->cb);
+		iov[0].iov_len = PAGE_SIZE - cbuf_data(&con->cb);
 		iov[1].iov_len = con->cb.base;
 		iov[1].iov_base = page_address(con->rx_page);
 		nvec = 2;
@@ -630,7 +675,7 @@ static int receive_from_sock(struct connection *con)
 	ret = dlm_process_incoming_buffer(con->nodeid,
 					  page_address(con->rx_page),
 					  con->cb.base, con->cb.len,
-					  PAGE_CACHE_SIZE);
+					  PAGE_SIZE);
 	if (ret == -EBADMSG) {
 		log_print("lowcomms: addr=%p, base=%u, len=%u, read=%d",
 			  page_address(con->rx_page), con->cb.base,
@@ -1190,6 +1235,8 @@ static struct socket *tcp_create_listen_sock(struct connection *con,
 	if (result < 0) {
 		log_print("Failed to set SO_REUSEADDR on socket: %d", result);
 	}
+	sock->sk->sk_user_data = con;
+
 	con->rx_action = tcp_accept_from_sock;
 	con->connect_action = tcp_connect_to_sock;
 
@@ -1271,6 +1318,7 @@ static int sctp_listen_for_all(void)
 	if (result < 0)
 		log_print("Could not set SCTP NODELAY error %d\n", result);
 
+	write_lock_bh(&sock->sk->sk_callback_lock);
 	/* Init con struct */
 	sock->sk->sk_user_data = con;
 	con->sock = sock;
@@ -1278,6 +1326,8 @@ static int sctp_listen_for_all(void)
 	con->rx_action = sctp_accept_from_sock;
 	con->connect_action = sctp_connect_to_sock;
 
+	write_unlock_bh(&sock->sk->sk_callback_lock);
+
 	/* Bind to all addresses. */
 	if (sctp_bind_addrs(con, dlm_config.ci_tcp_port))
 		goto create_delsock;
@@ -1366,7 +1416,7 @@ void *dlm_lowcomms_get_buffer(int nodeid, int len, gfp_t allocation, char **ppc)
 	spin_lock(&con->writequeue_lock);
 	e = list_entry(con->writequeue.prev, struct writequeue_entry, list);
 	if ((&e->list == &con->writequeue) ||
-	    (PAGE_CACHE_SIZE - e->end < len)) {
+	    (PAGE_SIZE - e->end < len)) {
 		e = NULL;
 	} else {
 		offset = e->end;
@@ -1448,7 +1498,7 @@ static void send_to_sock(struct connection *con)
 					      msg_flags);
 			if (ret == -EAGAIN || ret == 0) {
 				if (ret == -EAGAIN &&
-				    test_bit(SOCK_ASYNC_NOSPACE, &con->sock->flags) &&
+				    test_bit(SOCKWQ_ASYNC_NOSPACE, &con->sock->flags) &&
 				    !test_and_set_bit(CF_APP_LIMITED, &con->flags)) {
 					/* Notify TCP that we're limited by the
 					 * application window size.
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index 173b3873a4f4..58c2f4a21b7f 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -515,14 +515,9 @@ static ssize_t device_write(struct file *file, const char __user *buf,
 	if (count > sizeof(struct dlm_write_request) + DLM_RESNAME_MAXLEN)
 		return -EINVAL;
 
-	kbuf = kzalloc(count + 1, GFP_NOFS);
-	if (!kbuf)
-		return -ENOMEM;
-
-	if (copy_from_user(kbuf, buf, count)) {
-		error = -EFAULT;
-		goto out_free;
-	}
+	kbuf = memdup_user_nul(buf, count);
+	if (IS_ERR(kbuf))
+		return PTR_ERR(kbuf);
 
 	if (check_version(kbuf)) {
 		error = -EBADE;
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 80d6901493cf..d09cb4cdd09f 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -23,6 +23,8 @@
  * 02111-1307, USA.
  */
 
+#include <crypto/hash.h>
+#include <crypto/skcipher.h>
 #include <linux/fs.h>
 #include <linux/mount.h>
 #include <linux/pagemap.h>
@@ -30,7 +32,6 @@
 #include <linux/compiler.h>
 #include <linux/key.h>
 #include <linux/namei.h>
-#include <linux/crypto.h>
 #include <linux/file.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
@@ -74,6 +75,19 @@ void ecryptfs_from_hex(char *dst, char *src, int dst_size)
 	}
 }
 
+static int ecryptfs_hash_digest(struct crypto_shash *tfm,
+				char *src, int len, char *dst)
+{
+	SHASH_DESC_ON_STACK(desc, tfm);
+	int err;
+
+	desc->tfm = tfm;
+	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+	err = crypto_shash_digest(desc, src, len, dst);
+	shash_desc_zero(desc);
+	return err;
+}
+
 /**
  * ecryptfs_calculate_md5 - calculates the md5 of @src
  * @dst: Pointer to 16 bytes of allocated memory
@@ -88,45 +102,26 @@ static int ecryptfs_calculate_md5(char *dst,
 				  struct ecryptfs_crypt_stat *crypt_stat,
 				  char *src, int len)
 {
-	struct scatterlist sg;
-	struct hash_desc desc = {
-		.tfm = crypt_stat->hash_tfm,
-		.flags = CRYPTO_TFM_REQ_MAY_SLEEP
-	};
+	struct crypto_shash *tfm;
 	int rc = 0;
 
 	mutex_lock(&crypt_stat->cs_hash_tfm_mutex);
-	sg_init_one(&sg, (u8 *)src, len);
-	if (!desc.tfm) {
-		desc.tfm = crypto_alloc_hash(ECRYPTFS_DEFAULT_HASH, 0,
-					     CRYPTO_ALG_ASYNC);
-		if (IS_ERR(desc.tfm)) {
-			rc = PTR_ERR(desc.tfm);
+	tfm = crypt_stat->hash_tfm;
+	if (!tfm) {
+		tfm = crypto_alloc_shash(ECRYPTFS_DEFAULT_HASH, 0, 0);
+		if (IS_ERR(tfm)) {
+			rc = PTR_ERR(tfm);
 			ecryptfs_printk(KERN_ERR, "Error attempting to "
 					"allocate crypto context; rc = [%d]\n",
 					rc);
 			goto out;
 		}
-		crypt_stat->hash_tfm = desc.tfm;
-	}
-	rc = crypto_hash_init(&desc);
-	if (rc) {
-		printk(KERN_ERR
-		       "%s: Error initializing crypto hash; rc = [%d]\n",
-		       __func__, rc);
-		goto out;
+		crypt_stat->hash_tfm = tfm;
 	}
-	rc = crypto_hash_update(&desc, &sg, len);
+	rc = ecryptfs_hash_digest(tfm, src, len, dst);
 	if (rc) {
 		printk(KERN_ERR
-		       "%s: Error updating crypto hash; rc = [%d]\n",
-		       __func__, rc);
-		goto out;
-	}
-	rc = crypto_hash_final(&desc, dst);
-	if (rc) {
-		printk(KERN_ERR
-		       "%s: Error finalizing crypto hash; rc = [%d]\n",
+		       "%s: Error computing crypto hash; rc = [%d]\n",
 		       __func__, rc);
 		goto out;
 	}
@@ -234,10 +229,8 @@ void ecryptfs_destroy_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat)
 {
 	struct ecryptfs_key_sig *key_sig, *key_sig_tmp;
 
-	if (crypt_stat->tfm)
-		crypto_free_ablkcipher(crypt_stat->tfm);
-	if (crypt_stat->hash_tfm)
-		crypto_free_hash(crypt_stat->hash_tfm);
+	crypto_free_skcipher(crypt_stat->tfm);
+	crypto_free_shash(crypt_stat->hash_tfm);
 	list_for_each_entry_safe(key_sig, key_sig_tmp,
 				 &crypt_stat->keysig_list, crypt_stat_list) {
 		list_del(&key_sig->crypt_stat_list);
@@ -293,7 +286,7 @@ int virt_to_scatterlist(const void *addr, int size, struct scatterlist *sg,
 		pg = virt_to_page(addr);
 		offset = offset_in_page(addr);
 		sg_set_page(&sg[i], pg, 0, offset);
-		remainder_of_page = PAGE_CACHE_SIZE - offset;
+		remainder_of_page = PAGE_SIZE - offset;
 		if (size >= remainder_of_page) {
 			sg[i].length = remainder_of_page;
 			addr += remainder_of_page;
@@ -342,7 +335,7 @@ static int crypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat,
 			     struct scatterlist *src_sg, int size,
 			     unsigned char *iv, int op)
 {
-	struct ablkcipher_request *req = NULL;
+	struct skcipher_request *req = NULL;
 	struct extent_crypt_result ecr;
 	int rc = 0;
 
@@ -358,20 +351,20 @@ static int crypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat,
 	init_completion(&ecr.completion);
 
 	mutex_lock(&crypt_stat->cs_tfm_mutex);
-	req = ablkcipher_request_alloc(crypt_stat->tfm, GFP_NOFS);
+	req = skcipher_request_alloc(crypt_stat->tfm, GFP_NOFS);
 	if (!req) {
 		mutex_unlock(&crypt_stat->cs_tfm_mutex);
 		rc = -ENOMEM;
 		goto out;
 	}
 
-	ablkcipher_request_set_callback(req,
+	skcipher_request_set_callback(req,
 			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 			extent_crypt_complete, &ecr);
 	/* Consider doing this once, when the file is opened */
 	if (!(crypt_stat->flags & ECRYPTFS_KEY_SET)) {
-		rc = crypto_ablkcipher_setkey(crypt_stat->tfm, crypt_stat->key,
-					      crypt_stat->key_size);
+		rc = crypto_skcipher_setkey(crypt_stat->tfm, crypt_stat->key,
+					    crypt_stat->key_size);
 		if (rc) {
 			ecryptfs_printk(KERN_ERR,
 					"Error setting key; rc = [%d]\n",
@@ -383,9 +376,9 @@ static int crypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat,
 		crypt_stat->flags |= ECRYPTFS_KEY_SET;
 	}
 	mutex_unlock(&crypt_stat->cs_tfm_mutex);
-	ablkcipher_request_set_crypt(req, src_sg, dst_sg, size, iv);
-	rc = op == ENCRYPT ? crypto_ablkcipher_encrypt(req) :
-			     crypto_ablkcipher_decrypt(req);
+	skcipher_request_set_crypt(req, src_sg, dst_sg, size, iv);
+	rc = op == ENCRYPT ? crypto_skcipher_encrypt(req) :
+			     crypto_skcipher_decrypt(req);
 	if (rc == -EINPROGRESS || rc == -EBUSY) {
 		struct extent_crypt_result *ecr = req->base.data;
 
@@ -394,7 +387,7 @@ static int crypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat,
 		reinit_completion(&ecr->completion);
 	}
 out:
-	ablkcipher_request_free(req);
+	skcipher_request_free(req);
 	return rc;
 }
 
@@ -407,7 +400,7 @@ static loff_t lower_offset_for_page(struct ecryptfs_crypt_stat *crypt_stat,
 				    struct page *page)
 {
 	return ecryptfs_lower_header_size(crypt_stat) +
-	       ((loff_t)page->index << PAGE_CACHE_SHIFT);
+	       ((loff_t)page->index << PAGE_SHIFT);
 }
 
 /**
@@ -435,7 +428,7 @@ static int crypt_extent(struct ecryptfs_crypt_stat *crypt_stat,
 	size_t extent_size = crypt_stat->extent_size;
 	int rc;
 
-	extent_base = (((loff_t)page_index) * (PAGE_CACHE_SIZE / extent_size));
+	extent_base = (((loff_t)page_index) * (PAGE_SIZE / extent_size));
 	rc = ecryptfs_derive_iv(extent_iv, crypt_stat,
 				(extent_base + extent_offset));
 	if (rc) {
@@ -505,7 +498,7 @@ int ecryptfs_encrypt_page(struct page *page)
 	}
 
 	for (extent_offset = 0;
-	     extent_offset < (PAGE_CACHE_SIZE / crypt_stat->extent_size);
+	     extent_offset < (PAGE_SIZE / crypt_stat->extent_size);
 	     extent_offset++) {
 		rc = crypt_extent(crypt_stat, enc_extent_page, page,
 				  extent_offset, ENCRYPT);
@@ -519,7 +512,7 @@ int ecryptfs_encrypt_page(struct page *page)
 	lower_offset = lower_offset_for_page(crypt_stat, page);
 	enc_extent_virt = kmap(enc_extent_page);
 	rc = ecryptfs_write_lower(ecryptfs_inode, enc_extent_virt, lower_offset,
-				  PAGE_CACHE_SIZE);
+				  PAGE_SIZE);
 	kunmap(enc_extent_page);
 	if (rc < 0) {
 		ecryptfs_printk(KERN_ERR,
@@ -567,7 +560,7 @@ int ecryptfs_decrypt_page(struct page *page)
 
 	lower_offset = lower_offset_for_page(crypt_stat, page);
 	page_virt = kmap(page);
-	rc = ecryptfs_read_lower(page_virt, lower_offset, PAGE_CACHE_SIZE,
+	rc = ecryptfs_read_lower(page_virt, lower_offset, PAGE_SIZE,
 				 ecryptfs_inode);
 	kunmap(page);
 	if (rc < 0) {
@@ -578,7 +571,7 @@ int ecryptfs_decrypt_page(struct page *page)
 	}
 
 	for (extent_offset = 0;
-	     extent_offset < (PAGE_CACHE_SIZE / crypt_stat->extent_size);
+	     extent_offset < (PAGE_SIZE / crypt_stat->extent_size);
 	     extent_offset++) {
 		rc = crypt_extent(crypt_stat, page, page,
 				  extent_offset, DECRYPT);
@@ -622,7 +615,7 @@ int ecryptfs_init_crypt_ctx(struct ecryptfs_crypt_stat *crypt_stat)
 						    crypt_stat->cipher, "cbc");
 	if (rc)
 		goto out_unlock;
-	crypt_stat->tfm = crypto_alloc_ablkcipher(full_alg_name, 0, 0);
+	crypt_stat->tfm = crypto_alloc_skcipher(full_alg_name, 0, 0);
 	if (IS_ERR(crypt_stat->tfm)) {
 		rc = PTR_ERR(crypt_stat->tfm);
 		crypt_stat->tfm = NULL;
@@ -631,7 +624,7 @@ int ecryptfs_init_crypt_ctx(struct ecryptfs_crypt_stat *crypt_stat)
 				full_alg_name);
 		goto out_free;
 	}
-	crypto_ablkcipher_set_flags(crypt_stat->tfm, CRYPTO_TFM_REQ_WEAK_KEY);
+	crypto_skcipher_set_flags(crypt_stat->tfm, CRYPTO_TFM_REQ_WEAK_KEY);
 	rc = 0;
 out_free:
 	kfree(full_alg_name);
@@ -666,11 +659,11 @@ void ecryptfs_set_default_sizes(struct ecryptfs_crypt_stat *crypt_stat)
 	if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR)
 		crypt_stat->metadata_size = ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE;
 	else {
-		if (PAGE_CACHE_SIZE <= ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE)
+		if (PAGE_SIZE <= ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE)
 			crypt_stat->metadata_size =
 				ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE;
 		else
-			crypt_stat->metadata_size = PAGE_CACHE_SIZE;
+			crypt_stat->metadata_size = PAGE_SIZE;
 	}
 }
 
@@ -1449,7 +1442,7 @@ int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry)
 						ECRYPTFS_VALIDATE_HEADER_SIZE);
 	if (rc) {
 		/* metadata is not in the file header, so try xattrs */
-		memset(page_virt, 0, PAGE_CACHE_SIZE);
+		memset(page_virt, 0, PAGE_SIZE);
 		rc = ecryptfs_read_xattr_region(page_virt, ecryptfs_inode);
 		if (rc) {
 			printk(KERN_DEBUG "Valid eCryptfs headers not found in "
@@ -1482,7 +1475,7 @@ int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry)
 	}
 out:
 	if (page_virt) {
-		memset(page_virt, 0, PAGE_CACHE_SIZE);
+		memset(page_virt, 0, PAGE_SIZE);
 		kmem_cache_free(ecryptfs_header_cache, page_virt);
 	}
 	return rc;
@@ -1499,16 +1492,14 @@ out:
  */
 static int
 ecryptfs_encrypt_filename(struct ecryptfs_filename *filename,
-			  struct ecryptfs_crypt_stat *crypt_stat,
 			  struct ecryptfs_mount_crypt_stat *mount_crypt_stat)
 {
 	int rc = 0;
 
 	filename->encrypted_filename = NULL;
 	filename->encrypted_filename_size = 0;
-	if ((crypt_stat && (crypt_stat->flags & ECRYPTFS_ENCFN_USE_MOUNT_FNEK))
-	    || (mount_crypt_stat && (mount_crypt_stat->flags
-				     & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK))) {
+	if (mount_crypt_stat && (mount_crypt_stat->flags
+				     & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK)) {
 		size_t packet_size;
 		size_t remaining_bytes;
 
@@ -1591,7 +1582,7 @@ out:
  * event, regardless of whether this function succeeds for fails.
  */
 static int
-ecryptfs_process_key_cipher(struct crypto_blkcipher **key_tfm,
+ecryptfs_process_key_cipher(struct crypto_skcipher **key_tfm,
 			    char *cipher_name, size_t *key_size)
 {
 	char dummy_key[ECRYPTFS_MAX_KEY_BYTES];
@@ -1609,21 +1600,18 @@ ecryptfs_process_key_cipher(struct crypto_blkcipher **key_tfm,
 						    "ecb");
 	if (rc)
 		goto out;
-	*key_tfm = crypto_alloc_blkcipher(full_alg_name, 0, CRYPTO_ALG_ASYNC);
+	*key_tfm = crypto_alloc_skcipher(full_alg_name, 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(*key_tfm)) {
 		rc = PTR_ERR(*key_tfm);
 		printk(KERN_ERR "Unable to allocate crypto cipher with name "
 		       "[%s]; rc = [%d]\n", full_alg_name, rc);
 		goto out;
 	}
-	crypto_blkcipher_set_flags(*key_tfm, CRYPTO_TFM_REQ_WEAK_KEY);
-	if (*key_size == 0) {
-		struct blkcipher_alg *alg = crypto_blkcipher_alg(*key_tfm);
-
-		*key_size = alg->max_keysize;
-	}
+	crypto_skcipher_set_flags(*key_tfm, CRYPTO_TFM_REQ_WEAK_KEY);
+	if (*key_size == 0)
+		*key_size = crypto_skcipher_default_keysize(*key_tfm);
 	get_random_bytes(dummy_key, *key_size);
-	rc = crypto_blkcipher_setkey(*key_tfm, dummy_key, *key_size);
+	rc = crypto_skcipher_setkey(*key_tfm, dummy_key, *key_size);
 	if (rc) {
 		printk(KERN_ERR "Error attempting to set key of size [%zd] for "
 		       "cipher [%s]; rc = [%d]\n", *key_size, full_alg_name,
@@ -1660,8 +1648,7 @@ int ecryptfs_destroy_crypto(void)
 	list_for_each_entry_safe(key_tfm, key_tfm_tmp, &key_tfm_list,
 				 key_tfm_list) {
 		list_del(&key_tfm->key_tfm_list);
-		if (key_tfm->key_tfm)
-			crypto_free_blkcipher(key_tfm->key_tfm);
+		crypto_free_skcipher(key_tfm->key_tfm);
 		kmem_cache_free(ecryptfs_key_tfm_cache, key_tfm);
 	}
 	mutex_unlock(&key_tfm_list_mutex);
@@ -1747,7 +1734,7 @@ int ecryptfs_tfm_exists(char *cipher_name, struct ecryptfs_key_tfm **key_tfm)
  * Searches for cached item first, and creates new if not found.
  * Returns 0 on success, non-zero if adding new cipher failed
  */
-int ecryptfs_get_tfm_and_mutex_for_cipher_name(struct crypto_blkcipher **tfm,
+int ecryptfs_get_tfm_and_mutex_for_cipher_name(struct crypto_skcipher **tfm,
 					       struct mutex **tfm_mutex,
 					       char *cipher_name)
 {
@@ -1944,7 +1931,6 @@ out:
 int ecryptfs_encrypt_and_encode_filename(
 	char **encoded_name,
 	size_t *encoded_name_size,
-	struct ecryptfs_crypt_stat *crypt_stat,
 	struct ecryptfs_mount_crypt_stat *mount_crypt_stat,
 	const char *name, size_t name_size)
 {
@@ -1953,9 +1939,8 @@ int ecryptfs_encrypt_and_encode_filename(
 
 	(*encoded_name) = NULL;
 	(*encoded_name_size) = 0;
-	if ((crypt_stat && (crypt_stat->flags & ECRYPTFS_ENCRYPT_FILENAMES))
-	    || (mount_crypt_stat && (mount_crypt_stat->flags
-				     & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES))) {
+	if (mount_crypt_stat && (mount_crypt_stat->flags
+				     & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)) {
 		struct ecryptfs_filename *filename;
 
 		filename = kzalloc(sizeof(*filename), GFP_KERNEL);
@@ -1968,8 +1953,7 @@ int ecryptfs_encrypt_and_encode_filename(
 		}
 		filename->filename = (char *)name;
 		filename->filename_size = name_size;
-		rc = ecryptfs_encrypt_filename(filename, crypt_stat,
-					       mount_crypt_stat);
+		rc = ecryptfs_encrypt_filename(filename, mount_crypt_stat);
 		if (rc) {
 			printk(KERN_ERR "%s: Error attempting to encrypt "
 			       "filename; rc = [%d]\n", __func__, rc);
@@ -1980,11 +1964,9 @@ int ecryptfs_encrypt_and_encode_filename(
 			NULL, &encoded_name_no_prefix_size,
 			filename->encrypted_filename,
 			filename->encrypted_filename_size);
-		if ((crypt_stat && (crypt_stat->flags
-				    & ECRYPTFS_ENCFN_USE_MOUNT_FNEK))
-		    || (mount_crypt_stat
+		if (mount_crypt_stat
 			&& (mount_crypt_stat->flags
-			    & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK)))
+			    & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK))
 			(*encoded_name_size) =
 				(ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE
 				 + encoded_name_no_prefix_size);
@@ -2002,11 +1984,9 @@ int ecryptfs_encrypt_and_encode_filename(
 			kfree(filename);
 			goto out;
 		}
-		if ((crypt_stat && (crypt_stat->flags
-				    & ECRYPTFS_ENCFN_USE_MOUNT_FNEK))
-		    || (mount_crypt_stat
+		if (mount_crypt_stat
 			&& (mount_crypt_stat->flags
-			    & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK))) {
+			    & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK)) {
 			memcpy((*encoded_name),
 			       ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX,
 			       ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE);
@@ -2120,7 +2100,7 @@ out:
 int ecryptfs_set_f_namelen(long *namelen, long lower_namelen,
 			   struct ecryptfs_mount_crypt_stat *mount_crypt_stat)
 {
-	struct blkcipher_desc desc;
+	struct crypto_skcipher *tfm;
 	struct mutex *tfm_mutex;
 	size_t cipher_blocksize;
 	int rc;
@@ -2130,7 +2110,7 @@ int ecryptfs_set_f_namelen(long *namelen, long lower_namelen,
 		return 0;
 	}
 
-	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&desc.tfm, &tfm_mutex,
+	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&tfm, &tfm_mutex,
 			mount_crypt_stat->global_default_fn_cipher_name);
 	if (unlikely(rc)) {
 		(*namelen) = 0;
@@ -2138,7 +2118,7 @@ int ecryptfs_set_f_namelen(long *namelen, long lower_namelen,
 	}
 
 	mutex_lock(tfm_mutex);
-	cipher_blocksize = crypto_blkcipher_blocksize(desc.tfm);
+	cipher_blocksize = crypto_skcipher_blocksize(tfm);
 	mutex_unlock(tfm_mutex);
 
 	/* Return an exact amount for the common cases */
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 7b39260c7bba..d123fbaa28e0 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -28,6 +28,7 @@
 #ifndef ECRYPTFS_KERNEL_H
 #define ECRYPTFS_KERNEL_H
 
+#include <crypto/skcipher.h>
 #include <keys/user-type.h>
 #include <keys/encrypted-type.h>
 #include <linux/fs.h>
@@ -38,7 +39,6 @@
 #include <linux/nsproxy.h>
 #include <linux/backing-dev.h>
 #include <linux/ecryptfs.h>
-#include <linux/crypto.h>
 
 #define ECRYPTFS_DEFAULT_IV_BYTES 16
 #define ECRYPTFS_DEFAULT_EXTENT_SIZE 4096
@@ -233,9 +233,9 @@ struct ecryptfs_crypt_stat {
 	size_t extent_shift;
 	unsigned int extent_mask;
 	struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
-	struct crypto_ablkcipher *tfm;
-	struct crypto_hash *hash_tfm; /* Crypto context for generating
-				       * the initialization vectors */
+	struct crypto_skcipher *tfm;
+	struct crypto_shash *hash_tfm; /* Crypto context for generating
+					* the initialization vectors */
 	unsigned char cipher[ECRYPTFS_MAX_CIPHER_NAME_SIZE + 1];
 	unsigned char key[ECRYPTFS_MAX_KEY_BYTES];
 	unsigned char root_iv[ECRYPTFS_MAX_IV_BYTES];
@@ -309,7 +309,7 @@ struct ecryptfs_global_auth_tok {
  * keeps a list of crypto API contexts around to use when needed.
  */
 struct ecryptfs_key_tfm {
-	struct crypto_blkcipher *key_tfm;
+	struct crypto_skcipher *key_tfm;
 	size_t key_size;
 	struct mutex key_tfm_mutex;
 	struct list_head key_tfm_list;
@@ -569,7 +569,6 @@ int ecryptfs_fill_zeros(struct file *file, loff_t new_length);
 int ecryptfs_encrypt_and_encode_filename(
 	char **encoded_name,
 	size_t *encoded_name_size,
-	struct ecryptfs_crypt_stat *crypt_stat,
 	struct ecryptfs_mount_crypt_stat *mount_crypt_stat,
 	const char *name, size_t name_size);
 struct dentry *ecryptfs_lower_dentry(struct dentry *this_dentry);
@@ -659,7 +658,7 @@ ecryptfs_add_new_key_tfm(struct ecryptfs_key_tfm **key_tfm, char *cipher_name,
 int ecryptfs_init_crypto(void);
 int ecryptfs_destroy_crypto(void);
 int ecryptfs_tfm_exists(char *cipher_name, struct ecryptfs_key_tfm **key_tfm);
-int ecryptfs_get_tfm_and_mutex_for_cipher_name(struct crypto_blkcipher **tfm,
+int ecryptfs_get_tfm_and_mutex_for_cipher_name(struct crypto_skcipher **tfm,
 					       struct mutex **tfm_mutex,
 					       char *cipher_name);
 int ecryptfs_keyring_auth_tok_for_sig(struct key **auth_tok_key,
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index e2e47ba5d313..224b49e71aa4 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -29,7 +29,6 @@
 #include <linux/dcache.h>
 #include <linux/namei.h>
 #include <linux/mount.h>
-#include <linux/crypto.h>
 #include <linux/fs_stack.h>
 #include <linux/slab.h>
 #include <linux/xattr.h>
@@ -41,13 +40,13 @@ static struct dentry *lock_parent(struct dentry *dentry)
 	struct dentry *dir;
 
 	dir = dget_parent(dentry);
-	mutex_lock_nested(&(d_inode(dir)->i_mutex), I_MUTEX_PARENT);
+	inode_lock_nested(d_inode(dir), I_MUTEX_PARENT);
 	return dir;
 }
 
 static void unlock_dir(struct dentry *dir)
 {
-	mutex_unlock(&d_inode(dir)->i_mutex);
+	inode_unlock(d_inode(dir));
 	dput(dir);
 }
 
@@ -282,9 +281,7 @@ ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry,
 	if (rc) {
 		ecryptfs_do_unlink(directory_inode, ecryptfs_dentry,
 				   ecryptfs_inode);
-		make_bad_inode(ecryptfs_inode);
-		unlock_new_inode(ecryptfs_inode);
-		iput(ecryptfs_inode);
+		iget_failed(ecryptfs_inode);
 		goto out;
 	}
 	unlock_new_inode(ecryptfs_inode);
@@ -399,11 +396,9 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
 	int rc = 0;
 
 	lower_dir_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry->d_parent);
-	mutex_lock(&d_inode(lower_dir_dentry)->i_mutex);
-	lower_dentry = lookup_one_len(ecryptfs_dentry->d_name.name,
+	lower_dentry = lookup_one_len_unlocked(ecryptfs_dentry->d_name.name,
 				      lower_dir_dentry,
 				      ecryptfs_dentry->d_name.len);
-	mutex_unlock(&d_inode(lower_dir_dentry)->i_mutex);
 	if (IS_ERR(lower_dentry)) {
 		rc = PTR_ERR(lower_dentry);
 		ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned "
@@ -421,18 +416,16 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
 	dput(lower_dentry);
 	rc = ecryptfs_encrypt_and_encode_filename(
 		&encrypted_and_encoded_name, &encrypted_and_encoded_name_size,
-		NULL, mount_crypt_stat, ecryptfs_dentry->d_name.name,
+		mount_crypt_stat, ecryptfs_dentry->d_name.name,
 		ecryptfs_dentry->d_name.len);
 	if (rc) {
 		printk(KERN_ERR "%s: Error attempting to encrypt and encode "
 		       "filename; rc = [%d]\n", __func__, rc);
 		goto out;
 	}
-	mutex_lock(&d_inode(lower_dir_dentry)->i_mutex);
-	lower_dentry = lookup_one_len(encrypted_and_encoded_name,
+	lower_dentry = lookup_one_len_unlocked(encrypted_and_encoded_name,
 				      lower_dir_dentry,
 				      encrypted_and_encoded_name_size);
-	mutex_unlock(&d_inode(lower_dir_dentry)->i_mutex);
 	if (IS_ERR(lower_dentry)) {
 		rc = PTR_ERR(lower_dentry);
 		ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned "
@@ -504,7 +497,6 @@ static int ecryptfs_symlink(struct inode *dir, struct dentry *dentry,
 		dir->i_sb)->mount_crypt_stat;
 	rc = ecryptfs_encrypt_and_encode_filename(&encoded_symname,
 						  &encoded_symlen,
-						  NULL,
 						  mount_crypt_stat, symname,
 						  strlen(symname));
 	if (rc)
@@ -674,16 +666,24 @@ out:
 	return rc ? ERR_PTR(rc) : buf;
 }
 
-static const char *ecryptfs_follow_link(struct dentry *dentry, void **cookie)
+static const char *ecryptfs_get_link(struct dentry *dentry,
+				     struct inode *inode,
+				     struct delayed_call *done)
 {
 	size_t len;
-	char *buf = ecryptfs_readlink_lower(dentry, &len);
+	char *buf;
+
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
+	buf = ecryptfs_readlink_lower(dentry, &len);
 	if (IS_ERR(buf))
 		return buf;
 	fsstack_copy_attr_atime(d_inode(dentry),
 				d_inode(ecryptfs_dentry_to_lower(dentry)));
 	buf[len] = '\0';
-	return *cookie = buf;
+	set_delayed_call(done, kfree_link, buf);
+	return buf;
 }
 
 /**
@@ -763,10 +763,10 @@ static int truncate_upper(struct dentry *dentry, struct iattr *ia,
 	} else { /* ia->ia_size < i_size_read(inode) */
 		/* We're chopping off all the pages down to the page
 		 * in which ia->ia_size is located. Fill in the end of
-		 * that page from (ia->ia_size & ~PAGE_CACHE_MASK) to
-		 * PAGE_CACHE_SIZE with zeros. */
-		size_t num_zeros = (PAGE_CACHE_SIZE
-				    - (ia->ia_size & ~PAGE_CACHE_MASK));
+		 * that page from (ia->ia_size & ~PAGE_MASK) to
+		 * PAGE_SIZE with zeros. */
+		size_t num_zeros = (PAGE_SIZE
+				    - (ia->ia_size & ~PAGE_MASK));
 
 		if (!(crypt_stat->flags & ECRYPTFS_ENCRYPTED)) {
 			truncate_setsize(inode, ia->ia_size);
@@ -863,9 +863,9 @@ int ecryptfs_truncate(struct dentry *dentry, loff_t new_length)
 	if (!rc && lower_ia.ia_valid & ATTR_SIZE) {
 		struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
 
-		mutex_lock(&d_inode(lower_dentry)->i_mutex);
+		inode_lock(d_inode(lower_dentry));
 		rc = notify_change(lower_dentry, &lower_ia, NULL);
-		mutex_unlock(&d_inode(lower_dentry)->i_mutex);
+		inode_unlock(d_inode(lower_dentry));
 	}
 	return rc;
 }
@@ -964,9 +964,9 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia)
 	if (lower_ia.ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID))
 		lower_ia.ia_valid &= ~ATTR_MODE;
 
-	mutex_lock(&d_inode(lower_dentry)->i_mutex);
+	inode_lock(d_inode(lower_dentry));
 	rc = notify_change(lower_dentry, &lower_ia, NULL);
-	mutex_unlock(&d_inode(lower_dentry)->i_mutex);
+	inode_unlock(d_inode(lower_dentry));
 out:
 	fsstack_copy_attr_all(inode, lower_inode);
 	return rc;
@@ -1042,10 +1042,10 @@ ecryptfs_getxattr_lower(struct dentry *lower_dentry, const char *name,
 		rc = -EOPNOTSUPP;
 		goto out;
 	}
-	mutex_lock(&d_inode(lower_dentry)->i_mutex);
+	inode_lock(d_inode(lower_dentry));
 	rc = d_inode(lower_dentry)->i_op->getxattr(lower_dentry, name, value,
 						   size);
-	mutex_unlock(&d_inode(lower_dentry)->i_mutex);
+	inode_unlock(d_inode(lower_dentry));
 out:
 	return rc;
 }
@@ -1069,9 +1069,9 @@ ecryptfs_listxattr(struct dentry *dentry, char *list, size_t size)
 		rc = -EOPNOTSUPP;
 		goto out;
 	}
-	mutex_lock(&d_inode(lower_dentry)->i_mutex);
+	inode_lock(d_inode(lower_dentry));
 	rc = d_inode(lower_dentry)->i_op->listxattr(lower_dentry, list, size);
-	mutex_unlock(&d_inode(lower_dentry)->i_mutex);
+	inode_unlock(d_inode(lower_dentry));
 out:
 	return rc;
 }
@@ -1086,17 +1086,16 @@ static int ecryptfs_removexattr(struct dentry *dentry, const char *name)
 		rc = -EOPNOTSUPP;
 		goto out;
 	}
-	mutex_lock(&d_inode(lower_dentry)->i_mutex);
+	inode_lock(d_inode(lower_dentry));
 	rc = d_inode(lower_dentry)->i_op->removexattr(lower_dentry, name);
-	mutex_unlock(&d_inode(lower_dentry)->i_mutex);
+	inode_unlock(d_inode(lower_dentry));
 out:
 	return rc;
 }
 
 const struct inode_operations ecryptfs_symlink_iops = {
 	.readlink = generic_readlink,
-	.follow_link = ecryptfs_follow_link,
-	.put_link = kfree_put_link,
+	.get_link = ecryptfs_get_link,
 	.permission = ecryptfs_permission,
 	.setattr = ecryptfs_setattr,
 	.getattr = ecryptfs_getattr_link,
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index 6bd67e2011f0..3cf1546dca82 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -25,11 +25,12 @@
  * 02111-1307, USA.
  */
 
+#include <crypto/hash.h>
+#include <crypto/skcipher.h>
 #include <linux/string.h>
 #include <linux/pagemap.h>
 #include <linux/key.h>
 #include <linux/random.h>
-#include <linux/crypto.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
 #include "ecryptfs_kernel.h"
@@ -601,12 +602,13 @@ struct ecryptfs_write_tag_70_packet_silly_stack {
 	struct ecryptfs_auth_tok *auth_tok;
 	struct scatterlist src_sg[2];
 	struct scatterlist dst_sg[2];
-	struct blkcipher_desc desc;
+	struct crypto_skcipher *skcipher_tfm;
+	struct skcipher_request *skcipher_req;
 	char iv[ECRYPTFS_MAX_IV_BYTES];
 	char hash[ECRYPTFS_TAG_70_DIGEST_SIZE];
 	char tmp_hash[ECRYPTFS_TAG_70_DIGEST_SIZE];
-	struct hash_desc hash_desc;
-	struct scatterlist hash_sg;
+	struct crypto_shash *hash_tfm;
+	struct shash_desc *hash_desc;
 };
 
 /**
@@ -629,14 +631,12 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 	struct key *auth_tok_key = NULL;
 	int rc = 0;
 
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	s = kzalloc(sizeof(*s), GFP_KERNEL);
 	if (!s) {
 		printk(KERN_ERR "%s: Out of memory whilst trying to kmalloc "
 		       "[%zd] bytes of kernel memory\n", __func__, sizeof(*s));
-		rc = -ENOMEM;
-		goto out;
+		return -ENOMEM;
 	}
-	s->desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 	(*packet_size) = 0;
 	rc = ecryptfs_find_auth_tok_for_sig(
 		&auth_tok_key,
@@ -649,7 +649,7 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 		goto out;
 	}
 	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(
-		&s->desc.tfm,
+		&s->skcipher_tfm,
 		&s->tfm_mutex, mount_crypt_stat->global_default_fn_cipher_name);
 	if (unlikely(rc)) {
 		printk(KERN_ERR "Internal error whilst attempting to get "
@@ -658,7 +658,7 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 		goto out;
 	}
 	mutex_lock(s->tfm_mutex);
-	s->block_size = crypto_blkcipher_blocksize(s->desc.tfm);
+	s->block_size = crypto_skcipher_blocksize(s->skcipher_tfm);
 	/* Plus one for the \0 separator between the random prefix
 	 * and the plaintext filename */
 	s->num_rand_bytes = (ECRYPTFS_FILENAME_MIN_RANDOM_PREPEND_BYTES + 1);
@@ -691,6 +691,19 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 		rc = -EINVAL;
 		goto out_unlock;
 	}
+
+	s->skcipher_req = skcipher_request_alloc(s->skcipher_tfm, GFP_KERNEL);
+	if (!s->skcipher_req) {
+		printk(KERN_ERR "%s: Out of kernel memory whilst attempting to "
+		       "skcipher_request_alloc for %s\n", __func__,
+		       crypto_skcipher_driver_name(s->skcipher_tfm));
+		rc = -ENOMEM;
+		goto out_unlock;
+	}
+
+	skcipher_request_set_callback(s->skcipher_req,
+				      CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
+
 	s->block_aligned_filename = kzalloc(s->block_aligned_filename_size,
 					    GFP_KERNEL);
 	if (!s->block_aligned_filename) {
@@ -700,7 +713,6 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 		rc = -ENOMEM;
 		goto out_unlock;
 	}
-	s->i = 0;
 	dest[s->i++] = ECRYPTFS_TAG_70_PACKET_TYPE;
 	rc = ecryptfs_write_packet_length(&dest[s->i],
 					  (ECRYPTFS_SIG_SIZE
@@ -738,40 +750,36 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 		       "password tokens\n", __func__);
 		goto out_free_unlock;
 	}
-	sg_init_one(
-		&s->hash_sg,
-		(u8 *)s->auth_tok->token.password.session_key_encryption_key,
-		s->auth_tok->token.password.session_key_encryption_key_bytes);
-	s->hash_desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
-	s->hash_desc.tfm = crypto_alloc_hash(ECRYPTFS_TAG_70_DIGEST, 0,
-					     CRYPTO_ALG_ASYNC);
-	if (IS_ERR(s->hash_desc.tfm)) {
-			rc = PTR_ERR(s->hash_desc.tfm);
+	s->hash_tfm = crypto_alloc_shash(ECRYPTFS_TAG_70_DIGEST, 0, 0);
+	if (IS_ERR(s->hash_tfm)) {
+			rc = PTR_ERR(s->hash_tfm);
 			printk(KERN_ERR "%s: Error attempting to "
 			       "allocate hash crypto context; rc = [%d]\n",
 			       __func__, rc);
 			goto out_free_unlock;
 	}
-	rc = crypto_hash_init(&s->hash_desc);
-	if (rc) {
-		printk(KERN_ERR
-		       "%s: Error initializing crypto hash; rc = [%d]\n",
-		       __func__, rc);
-		goto out_release_free_unlock;
-	}
-	rc = crypto_hash_update(
-		&s->hash_desc, &s->hash_sg,
-		s->auth_tok->token.password.session_key_encryption_key_bytes);
-	if (rc) {
-		printk(KERN_ERR
-		       "%s: Error updating crypto hash; rc = [%d]\n",
-		       __func__, rc);
+
+	s->hash_desc = kmalloc(sizeof(*s->hash_desc) +
+			       crypto_shash_descsize(s->hash_tfm), GFP_KERNEL);
+	if (!s->hash_desc) {
+		printk(KERN_ERR "%s: Out of kernel memory whilst attempting to "
+		       "kmalloc [%zd] bytes\n", __func__,
+		       sizeof(*s->hash_desc) +
+		       crypto_shash_descsize(s->hash_tfm));
+		rc = -ENOMEM;
 		goto out_release_free_unlock;
 	}
-	rc = crypto_hash_final(&s->hash_desc, s->hash);
+
+	s->hash_desc->tfm = s->hash_tfm;
+	s->hash_desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+
+	rc = crypto_shash_digest(s->hash_desc,
+				 (u8 *)s->auth_tok->token.password.session_key_encryption_key,
+				 s->auth_tok->token.password.session_key_encryption_key_bytes,
+				 s->hash);
 	if (rc) {
 		printk(KERN_ERR
-		       "%s: Error finalizing crypto hash; rc = [%d]\n",
+		       "%s: Error computing crypto hash; rc = [%d]\n",
 		       __func__, rc);
 		goto out_release_free_unlock;
 	}
@@ -780,27 +788,12 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 			s->hash[(s->j % ECRYPTFS_TAG_70_DIGEST_SIZE)];
 		if ((s->j % ECRYPTFS_TAG_70_DIGEST_SIZE)
 		    == (ECRYPTFS_TAG_70_DIGEST_SIZE - 1)) {
-			sg_init_one(&s->hash_sg, (u8 *)s->hash,
-				    ECRYPTFS_TAG_70_DIGEST_SIZE);
-			rc = crypto_hash_init(&s->hash_desc);
-			if (rc) {
-				printk(KERN_ERR
-				       "%s: Error initializing crypto hash; "
-				       "rc = [%d]\n", __func__, rc);
-				goto out_release_free_unlock;
-			}
-			rc = crypto_hash_update(&s->hash_desc, &s->hash_sg,
-						ECRYPTFS_TAG_70_DIGEST_SIZE);
+			rc = crypto_shash_digest(s->hash_desc, (u8 *)s->hash,
+						ECRYPTFS_TAG_70_DIGEST_SIZE,
+						s->tmp_hash);
 			if (rc) {
 				printk(KERN_ERR
-				       "%s: Error updating crypto hash; "
-				       "rc = [%d]\n", __func__, rc);
-				goto out_release_free_unlock;
-			}
-			rc = crypto_hash_final(&s->hash_desc, s->tmp_hash);
-			if (rc) {
-				printk(KERN_ERR
-				       "%s: Error finalizing crypto hash; "
+				       "%s: Error computing crypto hash; "
 				       "rc = [%d]\n", __func__, rc);
 				goto out_release_free_unlock;
 			}
@@ -834,10 +827,8 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 	 * of the IV here, so we just use 0's for the IV. Note the
 	 * constraint that ECRYPTFS_FILENAME_MIN_RANDOM_PREPEND_BYTES
 	 * >= ECRYPTFS_MAX_IV_BYTES. */
-	memset(s->iv, 0, ECRYPTFS_MAX_IV_BYTES);
-	s->desc.info = s->iv;
-	rc = crypto_blkcipher_setkey(
-		s->desc.tfm,
+	rc = crypto_skcipher_setkey(
+		s->skcipher_tfm,
 		s->auth_tok->token.password.session_key_encryption_key,
 		mount_crypt_stat->global_default_fn_cipher_key_bytes);
 	if (rc < 0) {
@@ -850,8 +841,9 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 		       mount_crypt_stat->global_default_fn_cipher_key_bytes);
 		goto out_release_free_unlock;
 	}
-	rc = crypto_blkcipher_encrypt_iv(&s->desc, s->dst_sg, s->src_sg,
-					 s->block_aligned_filename_size);
+	skcipher_request_set_crypt(s->skcipher_req, s->src_sg, s->dst_sg,
+				   s->block_aligned_filename_size, s->iv);
+	rc = crypto_skcipher_encrypt(s->skcipher_req);
 	if (rc) {
 		printk(KERN_ERR "%s: Error attempting to encrypt filename; "
 		       "rc = [%d]\n", __func__, rc);
@@ -861,7 +853,7 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 	(*packet_size) = s->i;
 	(*remaining_bytes) -= (*packet_size);
 out_release_free_unlock:
-	crypto_free_hash(s->hash_desc.tfm);
+	crypto_free_shash(s->hash_tfm);
 out_free_unlock:
 	kzfree(s->block_aligned_filename);
 out_unlock:
@@ -871,6 +863,8 @@ out:
 		up_write(&(auth_tok_key->sem));
 		key_put(auth_tok_key);
 	}
+	skcipher_request_free(s->skcipher_req);
+	kzfree(s->hash_desc);
 	kfree(s);
 	return rc;
 }
@@ -888,7 +882,8 @@ struct ecryptfs_parse_tag_70_packet_silly_stack {
 	struct ecryptfs_auth_tok *auth_tok;
 	struct scatterlist src_sg[2];
 	struct scatterlist dst_sg[2];
-	struct blkcipher_desc desc;
+	struct crypto_skcipher *skcipher_tfm;
+	struct skcipher_request *skcipher_req;
 	char fnek_sig_hex[ECRYPTFS_SIG_SIZE_HEX + 1];
 	char iv[ECRYPTFS_MAX_IV_BYTES];
 	char cipher_string[ECRYPTFS_MAX_CIPHER_NAME_SIZE + 1];
@@ -922,14 +917,12 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size,
 	(*packet_size) = 0;
 	(*filename_size) = 0;
 	(*filename) = NULL;
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	s = kzalloc(sizeof(*s), GFP_KERNEL);
 	if (!s) {
 		printk(KERN_ERR "%s: Out of memory whilst trying to kmalloc "
 		       "[%zd] bytes of kernel memory\n", __func__, sizeof(*s));
-		rc = -ENOMEM;
-		goto out;
+		return -ENOMEM;
 	}
-	s->desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 	if (max_packet_size < ECRYPTFS_TAG_70_MIN_METADATA_SIZE) {
 		printk(KERN_WARNING "%s: max_packet_size is [%zd]; it must be "
 		       "at least [%d]\n", __func__, max_packet_size,
@@ -992,7 +985,7 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size,
 		       rc);
 		goto out;
 	}
-	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&s->desc.tfm,
+	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&s->skcipher_tfm,
 							&s->tfm_mutex,
 							s->cipher_string);
 	if (unlikely(rc)) {
@@ -1030,12 +1023,23 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size,
 		       __func__, rc, s->block_aligned_filename_size);
 		goto out_free_unlock;
 	}
+
+	s->skcipher_req = skcipher_request_alloc(s->skcipher_tfm, GFP_KERNEL);
+	if (!s->skcipher_req) {
+		printk(KERN_ERR "%s: Out of kernel memory whilst attempting to "
+		       "skcipher_request_alloc for %s\n", __func__,
+		       crypto_skcipher_driver_name(s->skcipher_tfm));
+		rc = -ENOMEM;
+		goto out_free_unlock;
+	}
+
+	skcipher_request_set_callback(s->skcipher_req,
+				      CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
+
 	/* The characters in the first block effectively do the job of
 	 * the IV here, so we just use 0's for the IV. Note the
 	 * constraint that ECRYPTFS_FILENAME_MIN_RANDOM_PREPEND_BYTES
 	 * >= ECRYPTFS_MAX_IV_BYTES. */
-	memset(s->iv, 0, ECRYPTFS_MAX_IV_BYTES);
-	s->desc.info = s->iv;
 	/* TODO: Support other key modules than passphrase for
 	 * filename encryption */
 	if (s->auth_tok->token_type != ECRYPTFS_PASSWORD) {
@@ -1044,8 +1048,8 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size,
 		       "password tokens\n", __func__);
 		goto out_free_unlock;
 	}
-	rc = crypto_blkcipher_setkey(
-		s->desc.tfm,
+	rc = crypto_skcipher_setkey(
+		s->skcipher_tfm,
 		s->auth_tok->token.password.session_key_encryption_key,
 		mount_crypt_stat->global_default_fn_cipher_key_bytes);
 	if (rc < 0) {
@@ -1058,14 +1062,14 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size,
 		       mount_crypt_stat->global_default_fn_cipher_key_bytes);
 		goto out_free_unlock;
 	}
-	rc = crypto_blkcipher_decrypt_iv(&s->desc, s->dst_sg, s->src_sg,
-					 s->block_aligned_filename_size);
+	skcipher_request_set_crypt(s->skcipher_req, s->src_sg, s->dst_sg,
+				   s->block_aligned_filename_size, s->iv);
+	rc = crypto_skcipher_decrypt(s->skcipher_req);
 	if (rc) {
 		printk(KERN_ERR "%s: Error attempting to decrypt filename; "
 		       "rc = [%d]\n", __func__, rc);
 		goto out_free_unlock;
 	}
-	s->i = 0;
 	while (s->decrypted_filename[s->i] != '\0'
 	       && s->i < s->block_aligned_filename_size)
 		s->i++;
@@ -1108,6 +1112,7 @@ out:
 		up_write(&(auth_tok_key->sem));
 		key_put(auth_tok_key);
 	}
+	skcipher_request_free(s->skcipher_req);
 	kfree(s);
 	return rc;
 }
@@ -1667,9 +1672,8 @@ decrypt_passphrase_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 	struct scatterlist dst_sg[2];
 	struct scatterlist src_sg[2];
 	struct mutex *tfm_mutex;
-	struct blkcipher_desc desc = {
-		.flags = CRYPTO_TFM_REQ_MAY_SLEEP
-	};
+	struct crypto_skcipher *tfm;
+	struct skcipher_request *req = NULL;
 	int rc = 0;
 
 	if (unlikely(ecryptfs_verbosity > 0)) {
@@ -1680,7 +1684,7 @@ decrypt_passphrase_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 			auth_tok->token.password.session_key_encryption_key,
 			auth_tok->token.password.session_key_encryption_key_bytes);
 	}
-	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&desc.tfm, &tfm_mutex,
+	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&tfm, &tfm_mutex,
 							crypt_stat->cipher);
 	if (unlikely(rc)) {
 		printk(KERN_ERR "Internal error whilst attempting to get "
@@ -1711,8 +1715,20 @@ decrypt_passphrase_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 		goto out;
 	}
 	mutex_lock(tfm_mutex);
-	rc = crypto_blkcipher_setkey(
-		desc.tfm, auth_tok->token.password.session_key_encryption_key,
+	req = skcipher_request_alloc(tfm, GFP_KERNEL);
+	if (!req) {
+		mutex_unlock(tfm_mutex);
+		printk(KERN_ERR "%s: Out of kernel memory whilst attempting to "
+		       "skcipher_request_alloc for %s\n", __func__,
+		       crypto_skcipher_driver_name(tfm));
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP,
+				      NULL, NULL);
+	rc = crypto_skcipher_setkey(
+		tfm, auth_tok->token.password.session_key_encryption_key,
 		crypt_stat->key_size);
 	if (unlikely(rc < 0)) {
 		mutex_unlock(tfm_mutex);
@@ -1720,8 +1736,10 @@ decrypt_passphrase_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 		rc = -EINVAL;
 		goto out;
 	}
-	rc = crypto_blkcipher_decrypt(&desc, dst_sg, src_sg,
-				      auth_tok->session_key.encrypted_key_size);
+	skcipher_request_set_crypt(req, src_sg, dst_sg,
+				   auth_tok->session_key.encrypted_key_size,
+				   NULL);
+	rc = crypto_skcipher_decrypt(req);
 	mutex_unlock(tfm_mutex);
 	if (unlikely(rc)) {
 		printk(KERN_ERR "Error decrypting; rc = [%d]\n", rc);
@@ -1738,6 +1756,7 @@ decrypt_passphrase_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 				  crypt_stat->key_size);
 	}
 out:
+	skcipher_request_free(req);
 	return rc;
 }
 
@@ -1779,7 +1798,7 @@ int ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat,
 	 * added the our &auth_tok_list */
 	next_packet_is_auth_tok_packet = 1;
 	while (next_packet_is_auth_tok_packet) {
-		size_t max_packet_size = ((PAGE_CACHE_SIZE - 8) - i);
+		size_t max_packet_size = ((PAGE_SIZE - 8) - i);
 
 		switch (src[i]) {
 		case ECRYPTFS_TAG_3_PACKET_TYPE:
@@ -2191,16 +2210,14 @@ write_tag_3_packet(char *dest, size_t *remaining_bytes,
 	size_t max_packet_size;
 	struct ecryptfs_mount_crypt_stat *mount_crypt_stat =
 		crypt_stat->mount_crypt_stat;
-	struct blkcipher_desc desc = {
-		.tfm = NULL,
-		.flags = CRYPTO_TFM_REQ_MAY_SLEEP
-	};
+	struct crypto_skcipher *tfm;
+	struct skcipher_request *req;
 	int rc = 0;
 
 	(*packet_size) = 0;
 	ecryptfs_from_hex(key_rec->sig, auth_tok->token.password.signature,
 			  ECRYPTFS_SIG_SIZE);
-	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&desc.tfm, &tfm_mutex,
+	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&tfm, &tfm_mutex,
 							crypt_stat->cipher);
 	if (unlikely(rc)) {
 		printk(KERN_ERR "Internal error whilst attempting to get "
@@ -2209,12 +2226,11 @@ write_tag_3_packet(char *dest, size_t *remaining_bytes,
 		goto out;
 	}
 	if (mount_crypt_stat->global_default_cipher_key_size == 0) {
-		struct blkcipher_alg *alg = crypto_blkcipher_alg(desc.tfm);
-
 		printk(KERN_WARNING "No key size specified at mount; "
-		       "defaulting to [%d]\n", alg->max_keysize);
+		       "defaulting to [%d]\n",
+		       crypto_skcipher_default_keysize(tfm));
 		mount_crypt_stat->global_default_cipher_key_size =
-			alg->max_keysize;
+			crypto_skcipher_default_keysize(tfm);
 	}
 	if (crypt_stat->key_size == 0)
 		crypt_stat->key_size =
@@ -2284,20 +2300,36 @@ write_tag_3_packet(char *dest, size_t *remaining_bytes,
 		goto out;
 	}
 	mutex_lock(tfm_mutex);
-	rc = crypto_blkcipher_setkey(desc.tfm, session_key_encryption_key,
-				     crypt_stat->key_size);
+	rc = crypto_skcipher_setkey(tfm, session_key_encryption_key,
+				    crypt_stat->key_size);
 	if (rc < 0) {
 		mutex_unlock(tfm_mutex);
 		ecryptfs_printk(KERN_ERR, "Error setting key for crypto "
 				"context; rc = [%d]\n", rc);
 		goto out;
 	}
+
+	req = skcipher_request_alloc(tfm, GFP_KERNEL);
+	if (!req) {
+		mutex_unlock(tfm_mutex);
+		ecryptfs_printk(KERN_ERR, "Out of kernel memory whilst "
+				"attempting to skcipher_request_alloc for "
+				"%s\n", crypto_skcipher_driver_name(tfm));
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP,
+				      NULL, NULL);
+
 	rc = 0;
 	ecryptfs_printk(KERN_DEBUG, "Encrypting [%zd] bytes of the key\n",
 			crypt_stat->key_size);
-	rc = crypto_blkcipher_encrypt(&desc, dst_sg, src_sg,
-				      (*key_rec).enc_key_size);
+	skcipher_request_set_crypt(req, src_sg, dst_sg,
+				   (*key_rec).enc_key_size, NULL);
+	rc = crypto_skcipher_encrypt(req);
 	mutex_unlock(tfm_mutex);
+	skcipher_request_free(req);
 	if (rc) {
 		printk(KERN_ERR "Error encrypting; rc = [%d]\n", rc);
 		goto out;
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 4f4d0474bee9..1698132d0e57 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -29,7 +29,6 @@
 #include <linux/module.h>
 #include <linux/namei.h>
 #include <linux/skbuff.h>
-#include <linux/crypto.h>
 #include <linux/mount.h>
 #include <linux/pagemap.h>
 #include <linux/key.h>
@@ -663,6 +662,7 @@ static struct ecryptfs_cache_info {
 	struct kmem_cache **cache;
 	const char *name;
 	size_t size;
+	unsigned long flags;
 	void (*ctor)(void *obj);
 } ecryptfs_cache_infos[] = {
 	{
@@ -684,6 +684,7 @@ static struct ecryptfs_cache_info {
 		.cache = &ecryptfs_inode_info_cache,
 		.name = "ecryptfs_inode_cache",
 		.size = sizeof(struct ecryptfs_inode_info),
+		.flags = SLAB_ACCOUNT,
 		.ctor = inode_info_init_once,
 	},
 	{
@@ -694,12 +695,12 @@ static struct ecryptfs_cache_info {
 	{
 		.cache = &ecryptfs_header_cache,
 		.name = "ecryptfs_headers",
-		.size = PAGE_CACHE_SIZE,
+		.size = PAGE_SIZE,
 	},
 	{
 		.cache = &ecryptfs_xattr_cache,
 		.name = "ecryptfs_xattr_cache",
-		.size = PAGE_CACHE_SIZE,
+		.size = PAGE_SIZE,
 	},
 	{
 		.cache = &ecryptfs_key_record_cache,
@@ -755,8 +756,8 @@ static int ecryptfs_init_kmem_caches(void)
 		struct ecryptfs_cache_info *info;
 
 		info = &ecryptfs_cache_infos[i];
-		*(info->cache) = kmem_cache_create(info->name, info->size,
-				0, SLAB_HWCACHE_ALIGN, info->ctor);
+		*(info->cache) = kmem_cache_create(info->name, info->size, 0,
+				SLAB_HWCACHE_ALIGN | info->flags, info->ctor);
 		if (!*(info->cache)) {
 			ecryptfs_free_kmem_caches();
 			ecryptfs_printk(KERN_WARNING, "%s: "
@@ -817,7 +818,7 @@ static int __init ecryptfs_init(void)
 {
 	int rc;
 
-	if (ECRYPTFS_DEFAULT_EXTENT_SIZE > PAGE_CACHE_SIZE) {
+	if (ECRYPTFS_DEFAULT_EXTENT_SIZE > PAGE_SIZE) {
 		rc = -EINVAL;
 		ecryptfs_printk(KERN_ERR, "The eCryptfs extent size is "
 				"larger than the host's page size, and so "
@@ -825,7 +826,7 @@ static int __init ecryptfs_init(void)
 				"default eCryptfs extent size is [%u] bytes; "
 				"the page size is [%lu] bytes.\n",
 				ECRYPTFS_DEFAULT_EXTENT_SIZE,
-				(unsigned long)PAGE_CACHE_SIZE);
+				(unsigned long)PAGE_SIZE);
 		goto out;
 	}
 	rc = ecryptfs_init_kmem_caches();
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index caba848ac763..e6b1d80952b9 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -30,7 +30,6 @@
 #include <linux/page-flags.h>
 #include <linux/mount.h>
 #include <linux/file.h>
-#include <linux/crypto.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
 #include <asm/unaligned.h>
@@ -123,7 +122,7 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page,
 				       struct ecryptfs_crypt_stat *crypt_stat)
 {
 	loff_t extent_num_in_page = 0;
-	loff_t num_extents_per_page = (PAGE_CACHE_SIZE
+	loff_t num_extents_per_page = (PAGE_SIZE
 				       / crypt_stat->extent_size);
 	int rc = 0;
 
@@ -139,7 +138,7 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page,
 			char *page_virt;
 
 			page_virt = kmap_atomic(page);
-			memset(page_virt, 0, PAGE_CACHE_SIZE);
+			memset(page_virt, 0, PAGE_SIZE);
 			/* TODO: Support more than one header extent */
 			if (view_extent_num == 0) {
 				size_t written;
@@ -165,8 +164,8 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page,
 				 - crypt_stat->metadata_size);
 
 			rc = ecryptfs_read_lower_page_segment(
-				page, (lower_offset >> PAGE_CACHE_SHIFT),
-				(lower_offset & ~PAGE_CACHE_MASK),
+				page, (lower_offset >> PAGE_SHIFT),
+				(lower_offset & ~PAGE_MASK),
 				crypt_stat->extent_size, page->mapping->host);
 			if (rc) {
 				printk(KERN_ERR "%s: Error attempting to read "
@@ -199,7 +198,7 @@ static int ecryptfs_readpage(struct file *file, struct page *page)
 
 	if (!crypt_stat || !(crypt_stat->flags & ECRYPTFS_ENCRYPTED)) {
 		rc = ecryptfs_read_lower_page_segment(page, page->index, 0,
-						      PAGE_CACHE_SIZE,
+						      PAGE_SIZE,
 						      page->mapping->host);
 	} else if (crypt_stat->flags & ECRYPTFS_VIEW_AS_ENCRYPTED) {
 		if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR) {
@@ -216,7 +215,7 @@ static int ecryptfs_readpage(struct file *file, struct page *page)
 
 		} else {
 			rc = ecryptfs_read_lower_page_segment(
-				page, page->index, 0, PAGE_CACHE_SIZE,
+				page, page->index, 0, PAGE_SIZE,
 				page->mapping->host);
 			if (rc) {
 				printk(KERN_ERR "Error reading page; rc = "
@@ -251,12 +250,12 @@ static int fill_zeros_to_end_of_page(struct page *page, unsigned int to)
 	struct inode *inode = page->mapping->host;
 	int end_byte_in_page;
 
-	if ((i_size_read(inode) / PAGE_CACHE_SIZE) != page->index)
+	if ((i_size_read(inode) / PAGE_SIZE) != page->index)
 		goto out;
-	end_byte_in_page = i_size_read(inode) % PAGE_CACHE_SIZE;
+	end_byte_in_page = i_size_read(inode) % PAGE_SIZE;
 	if (to > end_byte_in_page)
 		end_byte_in_page = to;
-	zero_user_segment(page, end_byte_in_page, PAGE_CACHE_SIZE);
+	zero_user_segment(page, end_byte_in_page, PAGE_SIZE);
 out:
 	return 0;
 }
@@ -280,7 +279,7 @@ static int ecryptfs_write_begin(struct file *file,
 			loff_t pos, unsigned len, unsigned flags,
 			struct page **pagep, void **fsdata)
 {
-	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+	pgoff_t index = pos >> PAGE_SHIFT;
 	struct page *page;
 	loff_t prev_page_end_size;
 	int rc = 0;
@@ -290,14 +289,14 @@ static int ecryptfs_write_begin(struct file *file,
 		return -ENOMEM;
 	*pagep = page;
 
-	prev_page_end_size = ((loff_t)index << PAGE_CACHE_SHIFT);
+	prev_page_end_size = ((loff_t)index << PAGE_SHIFT);
 	if (!PageUptodate(page)) {
 		struct ecryptfs_crypt_stat *crypt_stat =
 			&ecryptfs_inode_to_private(mapping->host)->crypt_stat;
 
 		if (!(crypt_stat->flags & ECRYPTFS_ENCRYPTED)) {
 			rc = ecryptfs_read_lower_page_segment(
-				page, index, 0, PAGE_CACHE_SIZE, mapping->host);
+				page, index, 0, PAGE_SIZE, mapping->host);
 			if (rc) {
 				printk(KERN_ERR "%s: Error attempting to read "
 				       "lower page segment; rc = [%d]\n",
@@ -323,7 +322,7 @@ static int ecryptfs_write_begin(struct file *file,
 				SetPageUptodate(page);
 			} else {
 				rc = ecryptfs_read_lower_page_segment(
-					page, index, 0, PAGE_CACHE_SIZE,
+					page, index, 0, PAGE_SIZE,
 					mapping->host);
 				if (rc) {
 					printk(KERN_ERR "%s: Error reading "
@@ -337,9 +336,9 @@ static int ecryptfs_write_begin(struct file *file,
 		} else {
 			if (prev_page_end_size
 			    >= i_size_read(page->mapping->host)) {
-				zero_user(page, 0, PAGE_CACHE_SIZE);
+				zero_user(page, 0, PAGE_SIZE);
 				SetPageUptodate(page);
-			} else if (len < PAGE_CACHE_SIZE) {
+			} else if (len < PAGE_SIZE) {
 				rc = ecryptfs_decrypt_page(page);
 				if (rc) {
 					printk(KERN_ERR "%s: Error decrypting "
@@ -372,11 +371,11 @@ static int ecryptfs_write_begin(struct file *file,
 	 * of page?  Zero it out. */
 	if ((i_size_read(mapping->host) == prev_page_end_size)
 	    && (pos != 0))
-		zero_user(page, 0, PAGE_CACHE_SIZE);
+		zero_user(page, 0, PAGE_SIZE);
 out:
 	if (unlikely(rc)) {
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 		*pagep = NULL;
 	}
 	return rc;
@@ -436,15 +435,15 @@ static int ecryptfs_write_inode_size_to_xattr(struct inode *ecryptfs_inode)
 		rc = -ENOMEM;
 		goto out;
 	}
-	mutex_lock(&lower_inode->i_mutex);
+	inode_lock(lower_inode);
 	size = lower_inode->i_op->getxattr(lower_dentry, ECRYPTFS_XATTR_NAME,
-					   xattr_virt, PAGE_CACHE_SIZE);
+					   xattr_virt, PAGE_SIZE);
 	if (size < 0)
 		size = 8;
 	put_unaligned_be64(i_size_read(ecryptfs_inode), xattr_virt);
 	rc = lower_inode->i_op->setxattr(lower_dentry, ECRYPTFS_XATTR_NAME,
 					 xattr_virt, size, 0);
-	mutex_unlock(&lower_inode->i_mutex);
+	inode_unlock(lower_inode);
 	if (rc)
 		printk(KERN_ERR "Error whilst attempting to write inode size "
 		       "to lower file xattr; rc = [%d]\n", rc);
@@ -480,8 +479,8 @@ static int ecryptfs_write_end(struct file *file,
 			loff_t pos, unsigned len, unsigned copied,
 			struct page *page, void *fsdata)
 {
-	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
-	unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+	pgoff_t index = pos >> PAGE_SHIFT;
+	unsigned from = pos & (PAGE_SIZE - 1);
 	unsigned to = from + copied;
 	struct inode *ecryptfs_inode = mapping->host;
 	struct ecryptfs_crypt_stat *crypt_stat =
@@ -501,7 +500,7 @@ static int ecryptfs_write_end(struct file *file,
 		goto out;
 	}
 	if (!PageUptodate(page)) {
-		if (copied < PAGE_CACHE_SIZE) {
+		if (copied < PAGE_SIZE) {
 			rc = 0;
 			goto out;
 		}
@@ -534,7 +533,7 @@ static int ecryptfs_write_end(struct file *file,
 		rc = copied;
 out:
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 	return rc;
 }
 
diff --git a/fs/ecryptfs/read_write.c b/fs/ecryptfs/read_write.c
index 09fe622274e4..158a3a39f82d 100644
--- a/fs/ecryptfs/read_write.c
+++ b/fs/ecryptfs/read_write.c
@@ -74,7 +74,7 @@ int ecryptfs_write_lower_page_segment(struct inode *ecryptfs_inode,
 	loff_t offset;
 	int rc;
 
-	offset = ((((loff_t)page_for_lower->index) << PAGE_CACHE_SHIFT)
+	offset = ((((loff_t)page_for_lower->index) << PAGE_SHIFT)
 		  + offset_in_page);
 	virt = kmap(page_for_lower);
 	rc = ecryptfs_write_lower(ecryptfs_inode, virt, offset, size);
@@ -123,9 +123,9 @@ int ecryptfs_write(struct inode *ecryptfs_inode, char *data, loff_t offset,
 	else
 		pos = offset;
 	while (pos < (offset + size)) {
-		pgoff_t ecryptfs_page_idx = (pos >> PAGE_CACHE_SHIFT);
-		size_t start_offset_in_page = (pos & ~PAGE_CACHE_MASK);
-		size_t num_bytes = (PAGE_CACHE_SIZE - start_offset_in_page);
+		pgoff_t ecryptfs_page_idx = (pos >> PAGE_SHIFT);
+		size_t start_offset_in_page = (pos & ~PAGE_MASK);
+		size_t num_bytes = (PAGE_SIZE - start_offset_in_page);
 		loff_t total_remaining_bytes = ((offset + size) - pos);
 
 		if (fatal_signal_pending(current)) {
@@ -165,7 +165,7 @@ int ecryptfs_write(struct inode *ecryptfs_inode, char *data, loff_t offset,
 			 * Fill in zero values to the end of the page */
 			memset(((char *)ecryptfs_page_virt
 				+ start_offset_in_page), 0,
-				PAGE_CACHE_SIZE - start_offset_in_page);
+				PAGE_SIZE - start_offset_in_page);
 		}
 
 		/* pos >= offset, we are now writing the data request */
@@ -186,7 +186,7 @@ int ecryptfs_write(struct inode *ecryptfs_inode, char *data, loff_t offset,
 						ecryptfs_page,
 						start_offset_in_page,
 						data_offset);
-		page_cache_release(ecryptfs_page);
+		put_page(ecryptfs_page);
 		if (rc) {
 			printk(KERN_ERR "%s: Error encrypting "
 			       "page; rc = [%d]\n", __func__, rc);
@@ -262,7 +262,7 @@ int ecryptfs_read_lower_page_segment(struct page *page_for_ecryptfs,
 	loff_t offset;
 	int rc;
 
-	offset = ((((loff_t)page_index) << PAGE_CACHE_SHIFT) + offset_in_page);
+	offset = ((((loff_t)page_index) << PAGE_SHIFT) + offset_in_page);
 	virt = kmap(page_for_ecryptfs);
 	rc = ecryptfs_read_lower(virt, offset, size, ecryptfs_inode);
 	if (rc > 0)
diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c
index afa1b81c3418..77a486d3a51b 100644
--- a/fs/ecryptfs/super.c
+++ b/fs/ecryptfs/super.c
@@ -29,7 +29,6 @@
 #include <linux/slab.h>
 #include <linux/seq_file.h>
 #include <linux/file.h>
-#include <linux/crypto.h>
 #include <linux/statfs.h>
 #include <linux/magic.h>
 #include "ecryptfs_kernel.h"
diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c
index 90001da9abfd..d48e0d261d78 100644
--- a/fs/efivarfs/file.c
+++ b/fs/efivarfs/file.c
@@ -10,6 +10,7 @@
 #include <linux/efi.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
+#include <linux/mount.h>
 
 #include "internal.h"
 
@@ -50,9 +51,9 @@ static ssize_t efivarfs_file_write(struct file *file,
 		d_delete(file->f_path.dentry);
 		dput(file->f_path.dentry);
 	} else {
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		i_size_write(inode, datasize + sizeof(attributes));
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 	}
 
 	bytes = count;
@@ -103,9 +104,78 @@ out_free:
 	return size;
 }
 
+static int
+efivarfs_ioc_getxflags(struct file *file, void __user *arg)
+{
+	struct inode *inode = file->f_mapping->host;
+	unsigned int i_flags;
+	unsigned int flags = 0;
+
+	i_flags = inode->i_flags;
+	if (i_flags & S_IMMUTABLE)
+		flags |= FS_IMMUTABLE_FL;
+
+	if (copy_to_user(arg, &flags, sizeof(flags)))
+		return -EFAULT;
+	return 0;
+}
+
+static int
+efivarfs_ioc_setxflags(struct file *file, void __user *arg)
+{
+	struct inode *inode = file->f_mapping->host;
+	unsigned int flags;
+	unsigned int i_flags = 0;
+	int error;
+
+	if (!inode_owner_or_capable(inode))
+		return -EACCES;
+
+	if (copy_from_user(&flags, arg, sizeof(flags)))
+		return -EFAULT;
+
+	if (flags & ~FS_IMMUTABLE_FL)
+		return -EOPNOTSUPP;
+
+	if (!capable(CAP_LINUX_IMMUTABLE))
+		return -EPERM;
+
+	if (flags & FS_IMMUTABLE_FL)
+		i_flags |= S_IMMUTABLE;
+
+
+	error = mnt_want_write_file(file);
+	if (error)
+		return error;
+
+	inode_lock(inode);
+	inode_set_flags(inode, i_flags, S_IMMUTABLE);
+	inode_unlock(inode);
+
+	mnt_drop_write_file(file);
+
+	return 0;
+}
+
+long
+efivarfs_file_ioctl(struct file *file, unsigned int cmd, unsigned long p)
+{
+	void __user *arg = (void __user *)p;
+
+	switch (cmd) {
+	case FS_IOC_GETFLAGS:
+		return efivarfs_ioc_getxflags(file, arg);
+	case FS_IOC_SETFLAGS:
+		return efivarfs_ioc_setxflags(file, arg);
+	}
+
+	return -ENOTTY;
+}
+
 const struct file_operations efivarfs_file_operations = {
 	.open	= simple_open,
 	.read	= efivarfs_file_read,
 	.write	= efivarfs_file_write,
 	.llseek	= no_llseek,
+	.unlocked_ioctl = efivarfs_file_ioctl,
 };
diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c
index 3381b9da9ee6..e2ab6d0497f2 100644
--- a/fs/efivarfs/inode.c
+++ b/fs/efivarfs/inode.c
@@ -15,7 +15,8 @@
 #include "internal.h"
 
 struct inode *efivarfs_get_inode(struct super_block *sb,
-				const struct inode *dir, int mode, dev_t dev)
+				const struct inode *dir, int mode,
+				dev_t dev, bool is_removable)
 {
 	struct inode *inode = new_inode(sb);
 
@@ -23,6 +24,7 @@ struct inode *efivarfs_get_inode(struct super_block *sb,
 		inode->i_ino = get_next_ino();
 		inode->i_mode = mode;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+		inode->i_flags = is_removable ? 0 : S_IMMUTABLE;
 		switch (mode & S_IFMT) {
 		case S_IFREG:
 			inode->i_fop = &efivarfs_file_operations;
@@ -102,22 +104,17 @@ static void efivarfs_hex_to_guid(const char *str, efi_guid_t *guid)
 static int efivarfs_create(struct inode *dir, struct dentry *dentry,
 			  umode_t mode, bool excl)
 {
-	struct inode *inode;
+	struct inode *inode = NULL;
 	struct efivar_entry *var;
 	int namelen, i = 0, err = 0;
+	bool is_removable = false;
 
 	if (!efivarfs_valid_name(dentry->d_name.name, dentry->d_name.len))
 		return -EINVAL;
 
-	inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0);
-	if (!inode)
-		return -ENOMEM;
-
 	var = kzalloc(sizeof(struct efivar_entry), GFP_KERNEL);
-	if (!var) {
-		err = -ENOMEM;
-		goto out;
-	}
+	if (!var)
+		return -ENOMEM;
 
 	/* length of the variable name itself: remove GUID and separator */
 	namelen = dentry->d_name.len - EFI_VARIABLE_GUID_LEN - 1;
@@ -125,6 +122,16 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry,
 	efivarfs_hex_to_guid(dentry->d_name.name + namelen + 1,
 			&var->var.VendorGuid);
 
+	if (efivar_variable_is_removable(var->var.VendorGuid,
+					 dentry->d_name.name, namelen))
+		is_removable = true;
+
+	inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0, is_removable);
+	if (!inode) {
+		err = -ENOMEM;
+		goto out;
+	}
+
 	for (i = 0; i < namelen; i++)
 		var->var.VariableName[i] = dentry->d_name.name[i];
 
@@ -138,7 +145,8 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry,
 out:
 	if (err) {
 		kfree(var);
-		iput(inode);
+		if (inode)
+			iput(inode);
 	}
 	return err;
 }
diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h
index b5ff16addb7c..b4505188e799 100644
--- a/fs/efivarfs/internal.h
+++ b/fs/efivarfs/internal.h
@@ -15,7 +15,8 @@ extern const struct file_operations efivarfs_file_operations;
 extern const struct inode_operations efivarfs_dir_inode_operations;
 extern bool efivarfs_valid_name(const char *str, int len);
 extern struct inode *efivarfs_get_inode(struct super_block *sb,
-			const struct inode *dir, int mode, dev_t dev);
+			const struct inode *dir, int mode, dev_t dev,
+			bool is_removable);
 
 extern struct list_head efivarfs_list;
 
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index 86a2121828c3..553c5d2db4a4 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -118,8 +118,9 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 	struct dentry *dentry, *root = sb->s_root;
 	unsigned long size = 0;
 	char *name;
-	int len, i;
+	int len;
 	int err = -ENOMEM;
+	bool is_removable = false;
 
 	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry)
@@ -128,15 +129,17 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 	memcpy(entry->var.VariableName, name16, name_size);
 	memcpy(&(entry->var.VendorGuid), &vendor, sizeof(efi_guid_t));
 
-	len = ucs2_strlen(entry->var.VariableName);
+	len = ucs2_utf8size(entry->var.VariableName);
 
 	/* name, plus '-', plus GUID, plus NUL*/
 	name = kmalloc(len + 1 + EFI_VARIABLE_GUID_LEN + 1, GFP_KERNEL);
 	if (!name)
 		goto fail;
 
-	for (i = 0; i < len; i++)
-		name[i] = entry->var.VariableName[i] & 0xFF;
+	ucs2_as_utf8(name, entry->var.VariableName, len);
+
+	if (efivar_variable_is_removable(entry->var.VendorGuid, name, len))
+		is_removable = true;
 
 	name[len] = '-';
 
@@ -144,7 +147,8 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 
 	name[len + EFI_VARIABLE_GUID_LEN+1] = '\0';
 
-	inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0);
+	inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0,
+				   is_removable);
 	if (!inode)
 		goto fail_name;
 
@@ -160,10 +164,10 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 	efivar_entry_size(entry, &size);
 	efivar_entry_add(entry, &efivarfs_list);
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	inode->i_private = entry;
 	i_size_write(inode, size + sizeof(entry->var.Attributes));
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	d_add(dentry, inode);
 
 	return 0;
@@ -193,14 +197,14 @@ static int efivarfs_fill_super(struct super_block *sb, void *data, int silent)
 	efivarfs_sb = sb;
 
 	sb->s_maxbytes          = MAX_LFS_FILESIZE;
-	sb->s_blocksize         = PAGE_CACHE_SIZE;
-	sb->s_blocksize_bits    = PAGE_CACHE_SHIFT;
+	sb->s_blocksize         = PAGE_SIZE;
+	sb->s_blocksize_bits    = PAGE_SHIFT;
 	sb->s_magic             = EFIVARFS_MAGIC;
 	sb->s_op                = &efivarfs_ops;
 	sb->s_d_op		= &efivarfs_d_ops;
 	sb->s_time_gran         = 1;
 
-	inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0);
+	inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0, true);
 	if (!inode)
 		return -ENOMEM;
 	inode->i_op = &efivarfs_dir_inode_operations;
diff --git a/fs/efs/inode.c b/fs/efs/inode.c
index 079d20306ee1..cdf0872382af 100644
--- a/fs/efs/inode.c
+++ b/fs/efs/inode.c
@@ -151,6 +151,7 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino)
 			break;
 		case S_IFLNK:
 			inode->i_op = &page_symlink_inode_operations;
+			inode_nohighmem(inode);
 			inode->i_data.a_ops = &efs_symlink_aops;
 			break;
 		case S_IFCHR:
diff --git a/fs/efs/super.c b/fs/efs/super.c
index c8411a30f7da..cb68dac4f9d3 100644
--- a/fs/efs/super.c
+++ b/fs/efs/super.c
@@ -94,9 +94,9 @@ static void init_once(void *foo)
 static int __init init_inodecache(void)
 {
 	efs_inode_cachep = kmem_cache_create("efs_inode_cache",
-				sizeof(struct efs_inode_info),
-				0, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD,
-				init_once);
+				sizeof(struct efs_inode_info), 0,
+				SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|
+				SLAB_ACCOUNT, init_once);
 	if (efs_inode_cachep == NULL)
 		return -ENOMEM;
 	return 0;
diff --git a/fs/efs/symlink.c b/fs/efs/symlink.c
index 75117d0dac2b..4870cc82deb0 100644
--- a/fs/efs/symlink.c
+++ b/fs/efs/symlink.c
@@ -13,7 +13,7 @@
 
 static int efs_symlink_readpage(struct file *file, struct page *page)
 {
-	char *link = kmap(page);
+	char *link = page_address(page);
 	struct buffer_head * bh;
 	struct inode * inode = page->mapping->host;
 	efs_block_t size = inode->i_size;
@@ -39,12 +39,10 @@ static int efs_symlink_readpage(struct file *file, struct page *page)
 	}
 	link[size] = '\0';
 	SetPageUptodate(page);
-	kunmap(page);
 	unlock_page(page);
 	return 0;
 fail:
 	SetPageError(page);
-	kunmap(page);
 	unlock_page(page);
 	return err;
 }
diff --git a/fs/eventfd.c b/fs/eventfd.c
index ed70cf9fdc7b..1231cd1999d8 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -121,8 +121,46 @@ static unsigned int eventfd_poll(struct file *file, poll_table *wait)
 	u64 count;
 
 	poll_wait(file, &ctx->wqh, wait);
-	smp_rmb();
-	count = ctx->count;
+
+	/*
+	 * All writes to ctx->count occur within ctx->wqh.lock.  This read
+	 * can be done outside ctx->wqh.lock because we know that poll_wait
+	 * takes that lock (through add_wait_queue) if our caller will sleep.
+	 *
+	 * The read _can_ therefore seep into add_wait_queue's critical
+	 * section, but cannot move above it!  add_wait_queue's spin_lock acts
+	 * as an acquire barrier and ensures that the read be ordered properly
+	 * against the writes.  The following CAN happen and is safe:
+	 *
+	 *     poll                               write
+	 *     -----------------                  ------------
+	 *     lock ctx->wqh.lock (in poll_wait)
+	 *     count = ctx->count
+	 *     __add_wait_queue
+	 *     unlock ctx->wqh.lock
+	 *                                        lock ctx->qwh.lock
+	 *                                        ctx->count += n
+	 *                                        if (waitqueue_active)
+	 *                                          wake_up_locked_poll
+	 *                                        unlock ctx->qwh.lock
+	 *     eventfd_poll returns 0
+	 *
+	 * but the following, which would miss a wakeup, cannot happen:
+	 *
+	 *     poll                               write
+	 *     -----------------                  ------------
+	 *     count = ctx->count (INVALID!)
+	 *                                        lock ctx->qwh.lock
+	 *                                        ctx->count += n
+	 *                                        **waitqueue_active is false**
+	 *                                        **no wake_up_locked_poll!**
+	 *                                        unlock ctx->qwh.lock
+	 *     lock ctx->wqh.lock (in poll_wait)
+	 *     __add_wait_queue
+	 *     unlock ctx->wqh.lock
+	 *     eventfd_poll returns 0
+	 */
+	count = READ_ONCE(ctx->count);
 
 	if (count > 0)
 		events |= POLLIN;
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 1e009cad8d5c..8a74a2a52e0f 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -92,7 +92,12 @@
  */
 
 /* Epoll private bits inside the event mask */
-#define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET)
+#define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET | EPOLLEXCLUSIVE)
+
+#define EPOLLINOUT_BITS (POLLIN | POLLOUT)
+
+#define EPOLLEXCLUSIVE_OK_BITS (EPOLLINOUT_BITS | POLLERR | POLLHUP | \
+				EPOLLWAKEUP | EPOLLET | EPOLLEXCLUSIVE)
 
 /* Maximum number of nesting allowed inside epoll sets */
 #define EP_MAX_NESTS 4
@@ -1002,6 +1007,7 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k
 	unsigned long flags;
 	struct epitem *epi = ep_item_from_wait(wait);
 	struct eventpoll *ep = epi->ep;
+	int ewake = 0;
 
 	if ((unsigned long)key & POLLFREE) {
 		ep_pwq_from_wait(wait)->whead = NULL;
@@ -1066,8 +1072,25 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k
 	 * Wake up ( if active ) both the eventpoll wait list and the ->poll()
 	 * wait list.
 	 */
-	if (waitqueue_active(&ep->wq))
+	if (waitqueue_active(&ep->wq)) {
+		if ((epi->event.events & EPOLLEXCLUSIVE) &&
+					!((unsigned long)key & POLLFREE)) {
+			switch ((unsigned long)key & EPOLLINOUT_BITS) {
+			case POLLIN:
+				if (epi->event.events & POLLIN)
+					ewake = 1;
+				break;
+			case POLLOUT:
+				if (epi->event.events & POLLOUT)
+					ewake = 1;
+				break;
+			case 0:
+				ewake = 1;
+				break;
+			}
+		}
 		wake_up_locked(&ep->wq);
+	}
 	if (waitqueue_active(&ep->poll_wait))
 		pwake++;
 
@@ -1078,6 +1101,9 @@ out_unlock:
 	if (pwake)
 		ep_poll_safewake(&ep->poll_wait);
 
+	if (epi->event.events & EPOLLEXCLUSIVE)
+		return ewake;
+
 	return 1;
 }
 
@@ -1095,7 +1121,10 @@ static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
 		init_waitqueue_func_entry(&pwq->wait, ep_poll_callback);
 		pwq->whead = whead;
 		pwq->base = epi;
-		add_wait_queue(whead, &pwq->wait);
+		if (epi->event.events & EPOLLEXCLUSIVE)
+			add_wait_queue_exclusive(whead, &pwq->wait);
+		else
+			add_wait_queue(whead, &pwq->wait);
 		list_add_tail(&pwq->llink, &epi->pwqlist);
 		epi->nwait++;
 	} else {
@@ -1587,7 +1616,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 {
 	int res = 0, eavail, timed_out = 0;
 	unsigned long flags;
-	long slack = 0;
+	u64 slack = 0;
 	wait_queue_t wait;
 	ktime_t expires, *to = NULL;
 
@@ -1862,6 +1891,19 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 		goto error_tgt_fput;
 
 	/*
+	 * epoll adds to the wakeup queue at EPOLL_CTL_ADD time only,
+	 * so EPOLLEXCLUSIVE is not allowed for a EPOLL_CTL_MOD operation.
+	 * Also, we do not currently supported nested exclusive wakeups.
+	 */
+	if (epds.events & EPOLLEXCLUSIVE) {
+		if (op == EPOLL_CTL_MOD)
+			goto error_tgt_fput;
+		if (op == EPOLL_CTL_ADD && (is_file_epoll(tf.file) ||
+				(epds.events & ~EPOLLEXCLUSIVE_OK_BITS)))
+			goto error_tgt_fput;
+	}
+
+	/*
 	 * At this point it is safe to assume that the "private_data" contains
 	 * our own data structure.
 	 */
@@ -1932,8 +1974,10 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 		break;
 	case EPOLL_CTL_MOD:
 		if (epi) {
-			epds.events |= POLLERR | POLLHUP;
-			error = ep_modify(ep, epi, &epds);
+			if (!(epi->event.events & EPOLLEXCLUSIVE)) {
+				epds.events |= POLLERR | POLLHUP;
+				error = ep_modify(ep, epi, &epds);
+			}
 		} else
 			error = -ENOENT;
 		break;
diff --git a/fs/exec.c b/fs/exec.c
index b06623a9347f..c4010b8207a1 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -56,6 +56,7 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/oom.h>
 #include <linux/compat.h>
+#include <linux/vmalloc.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
@@ -119,7 +120,7 @@ SYSCALL_DEFINE1(uselib, const char __user *, library)
 	int error = PTR_ERR(tmp);
 	static const struct open_flags uselib_flags = {
 		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
-		.acc_mode = MAY_READ | MAY_EXEC | MAY_OPEN,
+		.acc_mode = MAY_READ | MAY_EXEC,
 		.intent = LOOKUP_OPEN,
 		.lookup_flags = LOOKUP_FOLLOW,
 	};
@@ -198,8 +199,12 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 			return NULL;
 	}
 #endif
-	ret = get_user_pages(current, bprm->mm, pos,
-			1, write, 1, &page, NULL);
+	/*
+	 * We are doing an exec().  'current' is the process
+	 * doing the exec and bprm->mm is the new process's mm.
+	 */
+	ret = get_user_pages_remote(current, bprm->mm, pos, 1, write,
+			1, &page, NULL);
 	if (ret <= 0)
 		return NULL;
 
@@ -763,7 +768,7 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags)
 	int err;
 	struct open_flags open_exec_flags = {
 		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
-		.acc_mode = MAY_EXEC | MAY_OPEN,
+		.acc_mode = MAY_EXEC,
 		.intent = LOOKUP_OPEN,
 		.lookup_flags = LOOKUP_FOLLOW,
 	};
@@ -831,6 +836,97 @@ int kernel_read(struct file *file, loff_t offset,
 
 EXPORT_SYMBOL(kernel_read);
 
+int kernel_read_file(struct file *file, void **buf, loff_t *size,
+		     loff_t max_size, enum kernel_read_file_id id)
+{
+	loff_t i_size, pos;
+	ssize_t bytes = 0;
+	int ret;
+
+	if (!S_ISREG(file_inode(file)->i_mode) || max_size < 0)
+		return -EINVAL;
+
+	ret = security_kernel_read_file(file, id);
+	if (ret)
+		return ret;
+
+	i_size = i_size_read(file_inode(file));
+	if (max_size > 0 && i_size > max_size)
+		return -EFBIG;
+	if (i_size <= 0)
+		return -EINVAL;
+
+	*buf = vmalloc(i_size);
+	if (!*buf)
+		return -ENOMEM;
+
+	pos = 0;
+	while (pos < i_size) {
+		bytes = kernel_read(file, pos, (char *)(*buf) + pos,
+				    i_size - pos);
+		if (bytes < 0) {
+			ret = bytes;
+			goto out;
+		}
+
+		if (bytes == 0)
+			break;
+		pos += bytes;
+	}
+
+	if (pos != i_size) {
+		ret = -EIO;
+		goto out;
+	}
+
+	ret = security_kernel_post_read_file(file, *buf, i_size, id);
+	if (!ret)
+		*size = pos;
+
+out:
+	if (ret < 0) {
+		vfree(*buf);
+		*buf = NULL;
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(kernel_read_file);
+
+int kernel_read_file_from_path(char *path, void **buf, loff_t *size,
+			       loff_t max_size, enum kernel_read_file_id id)
+{
+	struct file *file;
+	int ret;
+
+	if (!path || !*path)
+		return -EINVAL;
+
+	file = filp_open(path, O_RDONLY, 0);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	ret = kernel_read_file(file, buf, size, max_size, id);
+	fput(file);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(kernel_read_file_from_path);
+
+int kernel_read_file_from_fd(int fd, void **buf, loff_t *size, loff_t max_size,
+			     enum kernel_read_file_id id)
+{
+	struct fd f = fdget(fd);
+	int ret = -EBADF;
+
+	if (!f.file)
+		goto out;
+
+	ret = kernel_read_file(f.file, buf, size, max_size, id);
+out:
+	fdput(f);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(kernel_read_file_from_fd);
+
 ssize_t read_code(struct file *file, unsigned long addr, loff_t pos, size_t len)
 {
 	ssize_t res = vfs_read(file, (void __user *)addr, len, &pos);
@@ -1307,13 +1403,13 @@ static void bprm_fill_uid(struct linux_binprm *bprm)
 		return;
 
 	/* Be careful if suid/sgid is set */
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	/* reload atomically mode/uid/gid now that lock held */
 	mode = inode->i_mode;
 	uid = inode->i_uid;
 	gid = inode->i_gid;
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	/* We ignore suid/sgid if there are no mappings for them in the ns */
 	if (!kuid_has_mapping(bprm->cred->user_ns, uid) ||
diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c
index e5bb2abf77f9..547b93cbea63 100644
--- a/fs/exofs/dir.c
+++ b/fs/exofs/dir.c
@@ -41,16 +41,16 @@ static inline unsigned exofs_chunk_size(struct inode *inode)
 static inline void exofs_put_page(struct page *page)
 {
 	kunmap(page);
-	page_cache_release(page);
+	put_page(page);
 }
 
 static unsigned exofs_last_byte(struct inode *inode, unsigned long page_nr)
 {
 	loff_t last_byte = inode->i_size;
 
-	last_byte -= page_nr << PAGE_CACHE_SHIFT;
-	if (last_byte > PAGE_CACHE_SIZE)
-		last_byte = PAGE_CACHE_SIZE;
+	last_byte -= page_nr << PAGE_SHIFT;
+	if (last_byte > PAGE_SIZE)
+		last_byte = PAGE_SIZE;
 	return last_byte;
 }
 
@@ -85,13 +85,13 @@ static void exofs_check_page(struct page *page)
 	unsigned chunk_size = exofs_chunk_size(dir);
 	char *kaddr = page_address(page);
 	unsigned offs, rec_len;
-	unsigned limit = PAGE_CACHE_SIZE;
+	unsigned limit = PAGE_SIZE;
 	struct exofs_dir_entry *p;
 	char *error;
 
 	/* if the page is the last one in the directory */
-	if ((dir->i_size >> PAGE_CACHE_SHIFT) == page->index) {
-		limit = dir->i_size & ~PAGE_CACHE_MASK;
+	if ((dir->i_size >> PAGE_SHIFT) == page->index) {
+		limit = dir->i_size & ~PAGE_MASK;
 		if (limit & (chunk_size - 1))
 			goto Ebadsize;
 		if (!limit)
@@ -138,7 +138,7 @@ bad_entry:
 	EXOFS_ERR(
 		"ERROR [exofs_check_page]: bad entry in directory(0x%lx): %s - "
 		"offset=%lu, inode=0x%llu, rec_len=%d, name_len=%d\n",
-		dir->i_ino, error, (page->index<<PAGE_CACHE_SHIFT)+offs,
+		dir->i_ino, error, (page->index<<PAGE_SHIFT)+offs,
 		_LLU(le64_to_cpu(p->inode_no)),
 		rec_len, p->name_len);
 	goto fail;
@@ -147,7 +147,7 @@ Eend:
 	EXOFS_ERR("ERROR [exofs_check_page]: "
 		"entry in directory(0x%lx) spans the page boundary"
 		"offset=%lu, inode=0x%llx\n",
-		dir->i_ino, (page->index<<PAGE_CACHE_SHIFT)+offs,
+		dir->i_ino, (page->index<<PAGE_SHIFT)+offs,
 		_LLU(le64_to_cpu(p->inode_no)));
 fail:
 	SetPageChecked(page);
@@ -237,8 +237,8 @@ exofs_readdir(struct file *file, struct dir_context *ctx)
 {
 	loff_t pos = ctx->pos;
 	struct inode *inode = file_inode(file);
-	unsigned int offset = pos & ~PAGE_CACHE_MASK;
-	unsigned long n = pos >> PAGE_CACHE_SHIFT;
+	unsigned int offset = pos & ~PAGE_MASK;
+	unsigned long n = pos >> PAGE_SHIFT;
 	unsigned long npages = dir_pages(inode);
 	unsigned chunk_mask = ~(exofs_chunk_size(inode)-1);
 	int need_revalidate = (file->f_version != inode->i_version);
@@ -254,7 +254,7 @@ exofs_readdir(struct file *file, struct dir_context *ctx)
 		if (IS_ERR(page)) {
 			EXOFS_ERR("ERROR: bad page in directory(0x%lx)\n",
 				  inode->i_ino);
-			ctx->pos += PAGE_CACHE_SIZE - offset;
+			ctx->pos += PAGE_SIZE - offset;
 			return PTR_ERR(page);
 		}
 		kaddr = page_address(page);
@@ -262,7 +262,7 @@ exofs_readdir(struct file *file, struct dir_context *ctx)
 			if (offset) {
 				offset = exofs_validate_entry(kaddr, offset,
 								chunk_mask);
-				ctx->pos = (n<<PAGE_CACHE_SHIFT) + offset;
+				ctx->pos = (n<<PAGE_SHIFT) + offset;
 			}
 			file->f_version = inode->i_version;
 			need_revalidate = 0;
@@ -449,7 +449,7 @@ int exofs_add_link(struct dentry *dentry, struct inode *inode)
 		kaddr = page_address(page);
 		dir_end = kaddr + exofs_last_byte(dir, n);
 		de = (struct exofs_dir_entry *)kaddr;
-		kaddr += PAGE_CACHE_SIZE - reclen;
+		kaddr += PAGE_SIZE - reclen;
 		while ((char *)de <= kaddr) {
 			if ((char *)de == dir_end) {
 				name_len = 0;
@@ -602,7 +602,7 @@ int exofs_make_empty(struct inode *inode, struct inode *parent)
 	kunmap_atomic(kaddr);
 	err = exofs_commit_chunk(page, 0, chunk_size);
 fail:
-	page_cache_release(page);
+	put_page(page);
 	return err;
 }
 
diff --git a/fs/exofs/file.c b/fs/exofs/file.c
index 906de66e8e7e..28645f0640f7 100644
--- a/fs/exofs/file.c
+++ b/fs/exofs/file.c
@@ -52,9 +52,9 @@ static int exofs_file_fsync(struct file *filp, loff_t start, loff_t end,
 	if (ret)
 		return ret;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	ret = sync_inode_metadata(filp->f_mapping->host, 1);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return ret;
 }
 
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index 73c64daa0f55..49e1bd00b4ec 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -317,7 +317,7 @@ static int read_exec(struct page_collect *pcol)
 
 	if (!pcol->ios) {
 		int ret = ore_get_rw_state(&pcol->sbi->layout, &oi->oc, true,
-					     pcol->pg_first << PAGE_CACHE_SHIFT,
+					     pcol->pg_first << PAGE_SHIFT,
 					     pcol->length, &pcol->ios);
 
 		if (ret)
@@ -383,7 +383,7 @@ static int readpage_strip(void *data, struct page *page)
 	struct inode *inode = pcol->inode;
 	struct exofs_i_info *oi = exofs_i(inode);
 	loff_t i_size = i_size_read(inode);
-	pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
+	pgoff_t end_index = i_size >> PAGE_SHIFT;
 	size_t len;
 	int ret;
 
@@ -397,9 +397,9 @@ static int readpage_strip(void *data, struct page *page)
 	pcol->that_locked_page = page;
 
 	if (page->index < end_index)
-		len = PAGE_CACHE_SIZE;
+		len = PAGE_SIZE;
 	else if (page->index == end_index)
-		len = i_size & ~PAGE_CACHE_MASK;
+		len = i_size & ~PAGE_MASK;
 	else
 		len = 0;
 
@@ -442,8 +442,8 @@ try_again:
 			goto fail;
 	}
 
-	if (len != PAGE_CACHE_SIZE)
-		zero_user(page, len, PAGE_CACHE_SIZE - len);
+	if (len != PAGE_SIZE)
+		zero_user(page, len, PAGE_SIZE - len);
 
 	EXOFS_DBGMSG2("    readpage_strip(0x%lx, 0x%lx) len=0x%zx\n",
 		     inode->i_ino, page->index, len);
@@ -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 {
@@ -612,7 +609,7 @@ static void __r4w_put_page(void *priv, struct page *page)
 
 	if ((pcol->that_locked_page != page) && (ZERO_PAGE(0) != page)) {
 		EXOFS_DBGMSG2("index=0x%lx\n", page->index);
-		page_cache_release(page);
+		put_page(page);
 		return;
 	}
 	EXOFS_DBGMSG2("that_locked_page index=0x%lx\n",
@@ -636,7 +633,7 @@ static int write_exec(struct page_collect *pcol)
 
 	BUG_ON(pcol->ios);
 	ret = ore_get_rw_state(&pcol->sbi->layout, &oi->oc, false,
-				 pcol->pg_first << PAGE_CACHE_SHIFT,
+				 pcol->pg_first << PAGE_SHIFT,
 				 pcol->length, &pcol->ios);
 	if (unlikely(ret))
 		goto err;
@@ -699,7 +696,7 @@ static int writepage_strip(struct page *page,
 	struct inode *inode = pcol->inode;
 	struct exofs_i_info *oi = exofs_i(inode);
 	loff_t i_size = i_size_read(inode);
-	pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
+	pgoff_t end_index = i_size >> PAGE_SHIFT;
 	size_t len;
 	int ret;
 
@@ -711,9 +708,9 @@ static int writepage_strip(struct page *page,
 
 	if (page->index < end_index)
 		/* in this case, the page is within the limits of the file */
-		len = PAGE_CACHE_SIZE;
+		len = PAGE_SIZE;
 	else {
-		len = i_size & ~PAGE_CACHE_MASK;
+		len = i_size & ~PAGE_MASK;
 
 		if (page->index > end_index || !len) {
 			/* in this case, the page is outside the limits
@@ -793,10 +790,10 @@ static int exofs_writepages(struct address_space *mapping,
 	long start, end, expected_pages;
 	int ret;
 
-	start = wbc->range_start >> PAGE_CACHE_SHIFT;
+	start = wbc->range_start >> PAGE_SHIFT;
 	end = (wbc->range_end == LLONG_MAX) ?
 			start + mapping->nrpages :
-			wbc->range_end >> PAGE_CACHE_SHIFT;
+			wbc->range_end >> PAGE_SHIFT;
 
 	if (start || end)
 		expected_pages = end - start + 1;
@@ -884,15 +881,15 @@ int exofs_write_begin(struct file *file, struct address_space *mapping,
 	}
 
 	 /* read modify write */
-	if (!PageUptodate(page) && (len != PAGE_CACHE_SIZE)) {
+	if (!PageUptodate(page) && (len != PAGE_SIZE)) {
 		loff_t i_size = i_size_read(mapping->host);
-		pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
+		pgoff_t end_index = i_size >> PAGE_SHIFT;
 		size_t rlen;
 
 		if (page->index < end_index)
-			rlen = PAGE_CACHE_SIZE;
+			rlen = PAGE_SIZE;
 		else if (page->index == end_index)
-			rlen = i_size & ~PAGE_CACHE_MASK;
+			rlen = i_size & ~PAGE_MASK;
 		else
 			rlen = 0;
 
@@ -1227,6 +1224,7 @@ struct inode *exofs_iget(struct super_block *sb, unsigned long ino)
 			inode->i_link = (char *)oi->i_data;
 		} else {
 			inode->i_op = &page_symlink_inode_operations;
+			inode_nohighmem(inode);
 			inode->i_mapping->a_ops = &exofs_aops;
 		}
 	} else {
diff --git a/fs/exofs/namei.c b/fs/exofs/namei.c
index 09a6bb1ad63c..622a686bb08b 100644
--- a/fs/exofs/namei.c
+++ b/fs/exofs/namei.c
@@ -80,9 +80,6 @@ static int exofs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
 	struct inode *inode;
 	int err;
 
-	if (!new_valid_dev(rdev))
-		return -EINVAL;
-
 	inode = exofs_new_inode(dir, mode);
 	err = PTR_ERR(inode);
 	if (!IS_ERR(inode)) {
@@ -114,6 +111,7 @@ static int exofs_symlink(struct inode *dir, struct dentry *dentry,
 	if (l > sizeof(oi->i_data)) {
 		/* slow symlink */
 		inode->i_op = &page_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &exofs_aops;
 		memset(oi->i_data, 0, sizeof(oi->i_data));
 
@@ -294,11 +292,11 @@ static int exofs_rename(struct inode *old_dir, struct dentry *old_dentry,
 out_dir:
 	if (dir_de) {
 		kunmap(dir_page);
-		page_cache_release(dir_page);
+		put_page(dir_page);
 	}
 out_old:
 	kunmap(old_page);
-	page_cache_release(old_page);
+	put_page(old_page);
 out:
 	return err;
 }
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index b795c567b5e1..6658a50530a0 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -194,8 +194,8 @@ static int init_inodecache(void)
 {
 	exofs_inode_cachep = kmem_cache_create("exofs_inode_cache",
 				sizeof(struct exofs_i_info), 0,
-				SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD,
-				exofs_init_once);
+				SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD |
+				SLAB_ACCOUNT, exofs_init_once);
 	if (exofs_inode_cachep == NULL)
 		return -ENOMEM;
 	return 0;
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 714cd37a6ba3..c46f1a190b8d 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -124,10 +124,10 @@ static struct dentry *reconnect_one(struct vfsmount *mnt,
 	int err;
 
 	parent = ERR_PTR(-EACCES);
-	mutex_lock(&dentry->d_inode->i_mutex);
+	inode_lock(dentry->d_inode);
 	if (mnt->mnt_sb->s_export_op->get_parent)
 		parent = mnt->mnt_sb->s_export_op->get_parent(dentry);
-	mutex_unlock(&dentry->d_inode->i_mutex);
+	inode_unlock(dentry->d_inode);
 
 	if (IS_ERR(parent)) {
 		dprintk("%s: get_parent of %ld failed, err %d\n",
@@ -143,9 +143,9 @@ static struct dentry *reconnect_one(struct vfsmount *mnt,
 	if (err)
 		goto out_err;
 	dprintk("%s: found name: %s\n", __func__, nbuf);
-	mutex_lock(&parent->d_inode->i_mutex);
+	inode_lock(parent->d_inode);
 	tmp = lookup_one_len(nbuf, parent, strlen(nbuf));
-	mutex_unlock(&parent->d_inode->i_mutex);
+	inode_unlock(parent->d_inode);
 	if (IS_ERR(tmp)) {
 		dprintk("%s: lookup failed: %d\n", __func__, PTR_ERR(tmp));
 		goto out_err;
@@ -503,10 +503,10 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
 		 */
 		err = exportfs_get_name(mnt, target_dir, nbuf, result);
 		if (!err) {
-			mutex_lock(&target_dir->d_inode->i_mutex);
+			inode_lock(target_dir->d_inode);
 			nresult = lookup_one_len(nbuf, target_dir,
 						 strlen(nbuf));
-			mutex_unlock(&target_dir->d_inode->i_mutex);
+			inode_unlock(target_dir->d_inode);
 			if (!IS_ERR(nresult)) {
 				if (nresult->d_inode) {
 					dput(result);
diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c
index 0c6638b40f21..7ff6fcfa685d 100644
--- a/fs/ext2/dir.c
+++ b/fs/ext2/dir.c
@@ -37,7 +37,7 @@ static inline unsigned ext2_rec_len_from_disk(__le16 dlen)
 {
 	unsigned len = le16_to_cpu(dlen);
 
-#if (PAGE_CACHE_SIZE >= 65536)
+#if (PAGE_SIZE >= 65536)
 	if (len == EXT2_MAX_REC_LEN)
 		return 1 << 16;
 #endif
@@ -46,7 +46,7 @@ static inline unsigned ext2_rec_len_from_disk(__le16 dlen)
 
 static inline __le16 ext2_rec_len_to_disk(unsigned len)
 {
-#if (PAGE_CACHE_SIZE >= 65536)
+#if (PAGE_SIZE >= 65536)
 	if (len == (1 << 16))
 		return cpu_to_le16(EXT2_MAX_REC_LEN);
 	else
@@ -67,7 +67,7 @@ static inline unsigned ext2_chunk_size(struct inode *inode)
 static inline void ext2_put_page(struct page *page)
 {
 	kunmap(page);
-	page_cache_release(page);
+	put_page(page);
 }
 
 /*
@@ -79,9 +79,9 @@ ext2_last_byte(struct inode *inode, unsigned long page_nr)
 {
 	unsigned last_byte = inode->i_size;
 
-	last_byte -= page_nr << PAGE_CACHE_SHIFT;
-	if (last_byte > PAGE_CACHE_SIZE)
-		last_byte = PAGE_CACHE_SIZE;
+	last_byte -= page_nr << PAGE_SHIFT;
+	if (last_byte > PAGE_SIZE)
+		last_byte = PAGE_SIZE;
 	return last_byte;
 }
 
@@ -118,12 +118,12 @@ static void ext2_check_page(struct page *page, int quiet)
 	char *kaddr = page_address(page);
 	u32 max_inumber = le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count);
 	unsigned offs, rec_len;
-	unsigned limit = PAGE_CACHE_SIZE;
+	unsigned limit = PAGE_SIZE;
 	ext2_dirent *p;
 	char *error;
 
-	if ((dir->i_size >> PAGE_CACHE_SHIFT) == page->index) {
-		limit = dir->i_size & ~PAGE_CACHE_MASK;
+	if ((dir->i_size >> PAGE_SHIFT) == page->index) {
+		limit = dir->i_size & ~PAGE_MASK;
 		if (limit & (chunk_size - 1))
 			goto Ebadsize;
 		if (!limit)
@@ -176,7 +176,7 @@ bad_entry:
 	if (!quiet)
 		ext2_error(sb, __func__, "bad entry in directory #%lu: : %s - "
 			"offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
-			dir->i_ino, error, (page->index<<PAGE_CACHE_SHIFT)+offs,
+			dir->i_ino, error, (page->index<<PAGE_SHIFT)+offs,
 			(unsigned long) le32_to_cpu(p->inode),
 			rec_len, p->name_len);
 	goto fail;
@@ -186,7 +186,7 @@ Eend:
 		ext2_error(sb, "ext2_check_page",
 			"entry in directory #%lu spans the page boundary"
 			"offset=%lu, inode=%lu",
-			dir->i_ino, (page->index<<PAGE_CACHE_SHIFT)+offs,
+			dir->i_ino, (page->index<<PAGE_SHIFT)+offs,
 			(unsigned long) le32_to_cpu(p->inode));
 	}
 fail:
@@ -287,8 +287,8 @@ ext2_readdir(struct file *file, struct dir_context *ctx)
 	loff_t pos = ctx->pos;
 	struct inode *inode = file_inode(file);
 	struct super_block *sb = inode->i_sb;
-	unsigned int offset = pos & ~PAGE_CACHE_MASK;
-	unsigned long n = pos >> PAGE_CACHE_SHIFT;
+	unsigned int offset = pos & ~PAGE_MASK;
+	unsigned long n = pos >> PAGE_SHIFT;
 	unsigned long npages = dir_pages(inode);
 	unsigned chunk_mask = ~(ext2_chunk_size(inode)-1);
 	unsigned char *types = NULL;
@@ -309,14 +309,14 @@ ext2_readdir(struct file *file, struct dir_context *ctx)
 			ext2_error(sb, __func__,
 				   "bad page in #%lu",
 				   inode->i_ino);
-			ctx->pos += PAGE_CACHE_SIZE - offset;
+			ctx->pos += PAGE_SIZE - offset;
 			return PTR_ERR(page);
 		}
 		kaddr = page_address(page);
 		if (unlikely(need_revalidate)) {
 			if (offset) {
 				offset = ext2_validate_entry(kaddr, offset, chunk_mask);
-				ctx->pos = (n<<PAGE_CACHE_SHIFT) + offset;
+				ctx->pos = (n<<PAGE_SHIFT) + offset;
 			}
 			file->f_version = inode->i_version;
 			need_revalidate = 0;
@@ -406,7 +406,7 @@ struct ext2_dir_entry_2 *ext2_find_entry (struct inode * dir,
 		if (++n >= npages)
 			n = 0;
 		/* next page is past the blocks we've got */
-		if (unlikely(n > (dir->i_blocks >> (PAGE_CACHE_SHIFT - 9)))) {
+		if (unlikely(n > (dir->i_blocks >> (PAGE_SHIFT - 9)))) {
 			ext2_error(dir->i_sb, __func__,
 				"dir %lu size %lld exceeds block count %llu",
 				dir->i_ino, dir->i_size,
@@ -511,7 +511,7 @@ int ext2_add_link (struct dentry *dentry, struct inode *inode)
 		kaddr = page_address(page);
 		dir_end = kaddr + ext2_last_byte(dir, n);
 		de = (ext2_dirent *)kaddr;
-		kaddr += PAGE_CACHE_SIZE - reclen;
+		kaddr += PAGE_SIZE - reclen;
 		while ((char *)de <= kaddr) {
 			if ((char *)de == dir_end) {
 				/* We hit i_size */
@@ -655,7 +655,7 @@ int ext2_make_empty(struct inode *inode, struct inode *parent)
 	kunmap_atomic(kaddr);
 	err = ext2_commit_chunk(page, 0, chunk_size);
 fail:
-	page_cache_release(page);
+	put_page(page);
 	return err;
 }
 
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 8d15febd0aa3..170939f379d7 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -61,6 +61,8 @@ struct ext2_block_alloc_info {
 #define rsv_start rsv_window._rsv_start
 #define rsv_end rsv_window._rsv_end
 
+struct mb_cache;
+
 /*
  * second extended-fs super-block data in memory
  */
@@ -111,6 +113,7 @@ struct ext2_sb_info {
 	 * of the mount options.
 	 */
 	spinlock_t s_lock;
+	struct mb_cache *s_mb_cache;
 };
 
 static inline spinlock_t *
@@ -684,6 +687,9 @@ struct ext2_inode_info {
 	struct rw_semaphore xattr_sem;
 #endif
 	rwlock_t i_meta_lock;
+#ifdef CONFIG_FS_DAX
+	struct rw_semaphore dax_sem;
+#endif
 
 	/*
 	 * truncate_mutex is for serialising ext2_truncate() against
@@ -699,6 +705,14 @@ struct ext2_inode_info {
 #endif
 };
 
+#ifdef CONFIG_FS_DAX
+#define dax_sem_down_write(ext2_inode)	down_write(&(ext2_inode)->dax_sem)
+#define dax_sem_up_write(ext2_inode)	up_write(&(ext2_inode)->dax_sem)
+#else
+#define dax_sem_down_write(ext2_inode)
+#define dax_sem_up_write(ext2_inode)
+#endif
+
 /*
  * Inode dynamic state flags
  */
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 1982c3f11aec..c1400b109805 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -27,27 +27,88 @@
 #include "acl.h"
 
 #ifdef CONFIG_FS_DAX
+/*
+ * The lock ordering for ext2 DAX fault paths is:
+ *
+ * mmap_sem (MM)
+ *   sb_start_pagefault (vfs, freeze)
+ *     ext2_inode_info->dax_sem
+ *       address_space->i_mmap_rwsem or page_lock (mutually exclusive in DAX)
+ *         ext2_inode_info->truncate_mutex
+ *
+ * The default page_lock and i_size verification done by non-DAX fault paths
+ * is sufficient because ext2 doesn't support hole punching.
+ */
 static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	return dax_fault(vma, vmf, ext2_get_block, NULL);
+	struct inode *inode = file_inode(vma->vm_file);
+	struct ext2_inode_info *ei = EXT2_I(inode);
+	int ret;
+
+	if (vmf->flags & FAULT_FLAG_WRITE) {
+		sb_start_pagefault(inode->i_sb);
+		file_update_time(vma->vm_file);
+	}
+	down_read(&ei->dax_sem);
+
+	ret = __dax_fault(vma, vmf, ext2_get_block, NULL);
+
+	up_read(&ei->dax_sem);
+	if (vmf->flags & FAULT_FLAG_WRITE)
+		sb_end_pagefault(inode->i_sb);
+	return ret;
 }
 
 static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 						pmd_t *pmd, unsigned int flags)
 {
-	return dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block, NULL);
+	struct inode *inode = file_inode(vma->vm_file);
+	struct ext2_inode_info *ei = EXT2_I(inode);
+	int ret;
+
+	if (flags & FAULT_FLAG_WRITE) {
+		sb_start_pagefault(inode->i_sb);
+		file_update_time(vma->vm_file);
+	}
+	down_read(&ei->dax_sem);
+
+	ret = __dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block, NULL);
+
+	up_read(&ei->dax_sem);
+	if (flags & FAULT_FLAG_WRITE)
+		sb_end_pagefault(inode->i_sb);
+	return ret;
 }
 
-static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
+		struct vm_fault *vmf)
 {
-	return dax_mkwrite(vma, vmf, ext2_get_block, NULL);
+	struct inode *inode = file_inode(vma->vm_file);
+	struct ext2_inode_info *ei = EXT2_I(inode);
+	loff_t size;
+	int ret;
+
+	sb_start_pagefault(inode->i_sb);
+	file_update_time(vma->vm_file);
+	down_read(&ei->dax_sem);
+
+	/* check that the faulting page hasn't raced with truncate */
+	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (vmf->pgoff >= size)
+		ret = VM_FAULT_SIGBUS;
+	else
+		ret = dax_pfn_mkwrite(vma, vmf);
+
+	up_read(&ei->dax_sem);
+	sb_end_pagefault(inode->i_sb);
+	return ret;
 }
 
 static const struct vm_operations_struct ext2_dax_vm_ops = {
 	.fault		= ext2_dax_fault,
 	.pmd_fault	= ext2_dax_pmd_fault,
-	.page_mkwrite	= ext2_dax_mkwrite,
-	.pfn_mkwrite	= dax_pfn_mkwrite,
+	.page_mkwrite	= ext2_dax_fault,
+	.pfn_mkwrite	= ext2_dax_pfn_mkwrite,
 };
 
 static int ext2_file_mmap(struct file *file, struct vm_area_struct *vma)
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index c60a248c640c..6bd58e6ff038 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -737,8 +737,10 @@ static int ext2_get_blocks(struct inode *inode,
 		 * so that it's not found by another thread before it's
 		 * initialised
 		 */
-		err = dax_clear_blocks(inode, le32_to_cpu(chain[depth-1].key),
-						1 << inode->i_blkbits);
+		err = dax_clear_sectors(inode->i_sb->s_bdev,
+				le32_to_cpu(chain[depth-1].key) <<
+				(inode->i_blkbits - 9),
+				1 << inode->i_blkbits);
 		if (err) {
 			mutex_unlock(&ei->truncate_mutex);
 			goto cleanup;
@@ -874,6 +876,14 @@ ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 static int
 ext2_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
+#ifdef CONFIG_FS_DAX
+	if (dax_mapping(mapping)) {
+		return dax_writeback_mapping_range(mapping,
+						   mapping->host->i_sb->s_bdev,
+						   wbc);
+	}
+#endif
+
 	return mpage_writepages(mapping, wbc, ext2_get_block);
 }
 
@@ -1085,6 +1095,7 @@ static void ext2_free_branches(struct inode *inode, __le32 *p, __le32 *q, int de
 		ext2_free_data(inode, p, q);
 }
 
+/* dax_sem must be held when calling this function */
 static void __ext2_truncate_blocks(struct inode *inode, loff_t offset)
 {
 	__le32 *i_data = EXT2_I(inode)->i_data;
@@ -1100,6 +1111,10 @@ static void __ext2_truncate_blocks(struct inode *inode, loff_t offset)
 	blocksize = inode->i_sb->s_blocksize;
 	iblock = (offset + blocksize-1) >> EXT2_BLOCK_SIZE_BITS(inode->i_sb);
 
+#ifdef CONFIG_FS_DAX
+	WARN_ON(!rwsem_is_locked(&ei->dax_sem));
+#endif
+
 	n = ext2_block_to_path(inode, iblock, offsets, NULL);
 	if (n == 0)
 		return;
@@ -1185,7 +1200,10 @@ static void ext2_truncate_blocks(struct inode *inode, loff_t offset)
 		return;
 	if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
 		return;
+
+	dax_sem_down_write(EXT2_I(inode));
 	__ext2_truncate_blocks(inode, offset);
+	dax_sem_up_write(EXT2_I(inode));
 }
 
 static int ext2_setsize(struct inode *inode, loff_t newsize)
@@ -1213,8 +1231,10 @@ static int ext2_setsize(struct inode *inode, loff_t newsize)
 	if (error)
 		return error;
 
+	dax_sem_down_write(EXT2_I(inode));
 	truncate_setsize(inode, newsize);
 	__ext2_truncate_blocks(inode, newsize);
+	dax_sem_up_write(EXT2_I(inode));
 
 	inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC;
 	if (inode_needs_sync(inode)) {
@@ -1286,7 +1306,7 @@ void ext2_set_inode_flags(struct inode *inode)
 		inode->i_flags |= S_NOATIME;
 	if (flags & EXT2_DIRSYNC_FL)
 		inode->i_flags |= S_DIRSYNC;
-	if (test_opt(inode->i_sb, DAX))
+	if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode))
 		inode->i_flags |= S_DAX;
 }
 
@@ -1410,6 +1430,7 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
 				sizeof(ei->i_data) - 1);
 		} else {
 			inode->i_op = &ext2_symlink_inode_operations;
+			inode_nohighmem(inode);
 			if (test_opt(inode->i_sb, NOBH))
 				inode->i_mapping->a_ops = &ext2_nobh_aops;
 			else
diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c
index 5d46c09863f0..b386af2e45f4 100644
--- a/fs/ext2/ioctl.c
+++ b/fs/ext2/ioctl.c
@@ -51,10 +51,10 @@ long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 
 		flags = ext2_mask_flags(inode->i_mode, flags);
 
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		/* Is it quota file? Do not allow user to mess with it */
 		if (IS_NOQUOTA(inode)) {
-			mutex_unlock(&inode->i_mutex);
+			inode_unlock(inode);
 			ret = -EPERM;
 			goto setflags_out;
 		}
@@ -68,7 +68,7 @@ long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		 */
 		if ((flags ^ oldflags) & (EXT2_APPEND_FL | EXT2_IMMUTABLE_FL)) {
 			if (!capable(CAP_LINUX_IMMUTABLE)) {
-				mutex_unlock(&inode->i_mutex);
+				inode_unlock(inode);
 				ret = -EPERM;
 				goto setflags_out;
 			}
@@ -80,7 +80,7 @@ long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 
 		ext2_set_inode_flags(inode);
 		inode->i_ctime = CURRENT_TIME_SEC;
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 
 		mark_inode_dirty(inode);
 setflags_out:
@@ -102,10 +102,10 @@ setflags_out:
 			goto setversion_out;
 		}
 
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		inode->i_ctime = CURRENT_TIME_SEC;
 		inode->i_generation = generation;
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 
 		mark_inode_dirty(inode);
 setversion_out:
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index b4841e3066a5..d34843925b23 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -143,9 +143,6 @@ static int ext2_mknod (struct inode * dir, struct dentry *dentry, umode_t mode,
 	struct inode * inode;
 	int err;
 
-	if (!new_valid_dev(rdev))
-		return -EINVAL;
-
 	err = dquot_initialize(dir);
 	if (err)
 		return err;
@@ -186,6 +183,7 @@ static int ext2_symlink (struct inode * dir, struct dentry * dentry,
 	if (l > sizeof (EXT2_I(inode)->i_data)) {
 		/* slow symlink */
 		inode->i_op = &ext2_symlink_inode_operations;
+		inode_nohighmem(inode);
 		if (test_opt(inode->i_sb, NOBH))
 			inode->i_mapping->a_ops = &ext2_nobh_aops;
 		else
@@ -400,7 +398,7 @@ static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry,
 			ext2_set_link(old_inode, dir_de, dir_page, new_dir, 0);
 		else {
 			kunmap(dir_page);
-			page_cache_release(dir_page);
+			put_page(dir_page);
 		}
 		inode_dec_link_count(old_dir);
 	}
@@ -410,11 +408,11 @@ static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry,
 out_dir:
 	if (dir_de) {
 		kunmap(dir_page);
-		page_cache_release(dir_page);
+		put_page(dir_page);
 	}
 out_old:
 	kunmap(old_page);
-	page_cache_release(old_page);
+	put_page(old_page);
 out:
 	return err;
 }
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 900e19cf9ef6..b78caf25f746 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -131,7 +131,10 @@ static void ext2_put_super (struct super_block * sb)
 
 	dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
 
-	ext2_xattr_put_super(sb);
+	if (sbi->s_mb_cache) {
+		ext2_xattr_destroy_cache(sbi->s_mb_cache);
+		sbi->s_mb_cache = NULL;
+	}
 	if (!(sb->s_flags & MS_RDONLY)) {
 		struct ext2_super_block *es = sbi->s_es;
 
@@ -192,6 +195,9 @@ static void init_once(void *foo)
 	init_rwsem(&ei->xattr_sem);
 #endif
 	mutex_init(&ei->truncate_mutex);
+#ifdef CONFIG_FS_DAX
+	init_rwsem(&ei->dax_sem);
+#endif
 	inode_init_once(&ei->vfs_inode);
 }
 
@@ -200,7 +206,7 @@ static int __init init_inodecache(void)
 	ext2_inode_cachep = kmem_cache_create("ext2_inode_cache",
 					     sizeof(struct ext2_inode_info),
 					     0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD),
+						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
 					     init_once);
 	if (ext2_inode_cachep == NULL)
 		return -ENOMEM;
@@ -566,6 +572,8 @@ static int parse_options(char *options, struct super_block *sb)
 			/* Fall through */
 		case Opt_dax:
 #ifdef CONFIG_FS_DAX
+			ext2_msg(sb, KERN_WARNING,
+		"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
 			set_opt(sbi->s_mount_opt, DAX);
 #else
 			ext2_msg(sb, KERN_INFO, "dax option not supported");
@@ -1099,6 +1107,14 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 		ext2_msg(sb, KERN_ERR, "error: insufficient memory");
 		goto failed_mount3;
 	}
+
+#ifdef CONFIG_EXT2_FS_XATTR
+	sbi->s_mb_cache = ext2_xattr_create_cache();
+	if (!sbi->s_mb_cache) {
+		ext2_msg(sb, KERN_ERR, "Failed to create an mb_cache");
+		goto failed_mount3;
+	}
+#endif
 	/*
 	 * set up enough so that it can read an inode
 	 */
@@ -1144,6 +1160,8 @@ cantfind_ext2:
 			sb->s_id);
 	goto failed_mount;
 failed_mount3:
+	if (sbi->s_mb_cache)
+		ext2_xattr_destroy_cache(sbi->s_mb_cache);
 	percpu_counter_destroy(&sbi->s_freeblocks_counter);
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
@@ -1550,20 +1568,17 @@ MODULE_ALIAS_FS("ext2");
 
 static int __init init_ext2_fs(void)
 {
-	int err = init_ext2_xattr();
-	if (err)
-		return err;
+	int err;
+
 	err = init_inodecache();
 	if (err)
-		goto out1;
+		return err;
         err = register_filesystem(&ext2_fs_type);
 	if (err)
 		goto out;
 	return 0;
 out:
 	destroy_inodecache();
-out1:
-	exit_ext2_xattr();
 	return err;
 }
 
@@ -1571,7 +1586,6 @@ static void __exit exit_ext2_fs(void)
 {
 	unregister_filesystem(&ext2_fs_type);
 	destroy_inodecache();
-	exit_ext2_xattr();
 }
 
 MODULE_AUTHOR("Remy Card and others");
diff --git a/fs/ext2/symlink.c b/fs/ext2/symlink.c
index ae17179f3810..3495d8ae4b33 100644
--- a/fs/ext2/symlink.c
+++ b/fs/ext2/symlink.c
@@ -22,8 +22,7 @@
 
 const struct inode_operations ext2_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 	.setattr	= ext2_setattr,
 #ifdef CONFIG_EXT2_FS_XATTR
 	.setxattr	= generic_setxattr,
@@ -35,7 +34,7 @@ const struct inode_operations ext2_symlink_inode_operations = {
  
 const struct inode_operations ext2_fast_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= simple_follow_link,
+	.get_link	= simple_get_link,
 	.setattr	= ext2_setattr,
 #ifdef CONFIG_EXT2_FS_XATTR
 	.setxattr	= generic_setxattr,
diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c
index 0b6bfd3a398b..1a5e3bff0b63 100644
--- a/fs/ext2/xattr.c
+++ b/fs/ext2/xattr.c
@@ -77,10 +77,8 @@
 		printk("\n"); \
 	} while (0)
 # define ea_bdebug(bh, f...) do { \
-		char b[BDEVNAME_SIZE]; \
-		printk(KERN_DEBUG "block %s:%lu: ", \
-			bdevname(bh->b_bdev, b), \
-			(unsigned long) bh->b_blocknr); \
+		printk(KERN_DEBUG "block %pg:%lu: ", \
+			bh->b_bdev, (unsigned long) bh->b_blocknr); \
 		printk(f); \
 		printk("\n"); \
 	} while (0)
@@ -92,14 +90,12 @@
 static int ext2_xattr_set2(struct inode *, struct buffer_head *,
 			   struct ext2_xattr_header *);
 
-static int ext2_xattr_cache_insert(struct buffer_head *);
+static int ext2_xattr_cache_insert(struct mb_cache *, struct buffer_head *);
 static struct buffer_head *ext2_xattr_cache_find(struct inode *,
 						 struct ext2_xattr_header *);
 static void ext2_xattr_rehash(struct ext2_xattr_header *,
 			      struct ext2_xattr_entry *);
 
-static struct mb_cache *ext2_xattr_cache;
-
 static const struct xattr_handler *ext2_xattr_handler_map[] = {
 	[EXT2_XATTR_INDEX_USER]		     = &ext2_xattr_user_handler,
 #ifdef CONFIG_EXT2_FS_POSIX_ACL
@@ -154,6 +150,7 @@ ext2_xattr_get(struct inode *inode, int name_index, const char *name,
 	size_t name_len, size;
 	char *end;
 	int error;
+	struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
 
 	ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld",
 		  name_index, name, buffer, (long)buffer_size);
@@ -198,7 +195,7 @@ bad_block:	ext2_error(inode->i_sb, "ext2_xattr_get",
 			goto found;
 		entry = next;
 	}
-	if (ext2_xattr_cache_insert(bh))
+	if (ext2_xattr_cache_insert(ext2_mb_cache, bh))
 		ea_idebug(inode, "cache insert failed");
 	error = -ENODATA;
 	goto cleanup;
@@ -211,7 +208,7 @@ found:
 	    le16_to_cpu(entry->e_value_offs) + size > inode->i_sb->s_blocksize)
 		goto bad_block;
 
-	if (ext2_xattr_cache_insert(bh))
+	if (ext2_xattr_cache_insert(ext2_mb_cache, bh))
 		ea_idebug(inode, "cache insert failed");
 	if (buffer) {
 		error = -ERANGE;
@@ -249,6 +246,7 @@ ext2_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size)
 	char *end;
 	size_t rest = buffer_size;
 	int error;
+	struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
 
 	ea_idebug(inode, "buffer=%p, buffer_size=%ld",
 		  buffer, (long)buffer_size);
@@ -283,7 +281,7 @@ bad_block:	ext2_error(inode->i_sb, "ext2_xattr_list",
 			goto bad_block;
 		entry = next;
 	}
-	if (ext2_xattr_cache_insert(bh))
+	if (ext2_xattr_cache_insert(ext2_mb_cache, bh))
 		ea_idebug(inode, "cache insert failed");
 
 	/* list the attribute names */
@@ -292,17 +290,21 @@ bad_block:	ext2_error(inode->i_sb, "ext2_xattr_list",
 		const struct xattr_handler *handler =
 			ext2_xattr_handler(entry->e_name_index);
 
-		if (handler) {
-			size_t size = handler->list(dentry, buffer, rest,
-						    entry->e_name,
-						    entry->e_name_len,
-						    handler->flags);
+		if (handler && (!handler->list || handler->list(dentry))) {
+			const char *prefix = handler->prefix ?: handler->name;
+			size_t prefix_len = strlen(prefix);
+			size_t size = prefix_len + entry->e_name_len + 1;
+
 			if (buffer) {
 				if (size > rest) {
 					error = -ERANGE;
 					goto cleanup;
 				}
-				buffer += size;
+				memcpy(buffer, prefix, prefix_len);
+				buffer += prefix_len;
+				memcpy(buffer, entry->e_name, entry->e_name_len);
+				buffer += entry->e_name_len;
+				*buffer++ = 0;
 			}
 			rest -= size;
 		}
@@ -481,22 +483,23 @@ bad_block:		ext2_error(sb, "ext2_xattr_set",
 	/* Here we know that we can set the new attribute. */
 
 	if (header) {
-		struct mb_cache_entry *ce;
-
 		/* assert(header == HDR(bh)); */
-		ce = mb_cache_entry_get(ext2_xattr_cache, bh->b_bdev,
-					bh->b_blocknr);
 		lock_buffer(bh);
 		if (header->h_refcount == cpu_to_le32(1)) {
+			__u32 hash = le32_to_cpu(header->h_hash);
+
 			ea_bdebug(bh, "modifying in-place");
-			if (ce)
-				mb_cache_entry_free(ce);
+			/*
+			 * This must happen under buffer lock for
+			 * ext2_xattr_set2() to reliably detect modified block
+			 */
+			mb_cache_entry_delete_block(EXT2_SB(sb)->s_mb_cache,
+						    hash, bh->b_blocknr);
+
 			/* keep the buffer locked while modifying it. */
 		} else {
 			int offset;
 
-			if (ce)
-				mb_cache_entry_release(ce);
 			unlock_buffer(bh);
 			ea_bdebug(bh, "cloning");
 			header = kmalloc(bh->b_size, GFP_KERNEL);
@@ -624,6 +627,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 	struct super_block *sb = inode->i_sb;
 	struct buffer_head *new_bh = NULL;
 	int error;
+	struct mb_cache *ext2_mb_cache = EXT2_SB(sb)->s_mb_cache;
 
 	if (header) {
 		new_bh = ext2_xattr_cache_find(inode, header);
@@ -651,7 +655,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 			   don't need to change the reference count. */
 			new_bh = old_bh;
 			get_bh(new_bh);
-			ext2_xattr_cache_insert(new_bh);
+			ext2_xattr_cache_insert(ext2_mb_cache, new_bh);
 		} else {
 			/* We need to allocate a new block */
 			ext2_fsblk_t goal = ext2_group_first_block_no(sb,
@@ -672,7 +676,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 			memcpy(new_bh->b_data, header, new_bh->b_size);
 			set_buffer_uptodate(new_bh);
 			unlock_buffer(new_bh);
-			ext2_xattr_cache_insert(new_bh);
+			ext2_xattr_cache_insert(ext2_mb_cache, new_bh);
 			
 			ext2_xattr_update_super_block(sb);
 		}
@@ -705,19 +709,21 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 
 	error = 0;
 	if (old_bh && old_bh != new_bh) {
-		struct mb_cache_entry *ce;
-
 		/*
 		 * If there was an old block and we are no longer using it,
 		 * release the old block.
 		 */
-		ce = mb_cache_entry_get(ext2_xattr_cache, old_bh->b_bdev,
-					old_bh->b_blocknr);
 		lock_buffer(old_bh);
 		if (HDR(old_bh)->h_refcount == cpu_to_le32(1)) {
+			__u32 hash = le32_to_cpu(HDR(old_bh)->h_hash);
+
+			/*
+			 * This must happen under buffer lock for
+			 * ext2_xattr_set2() to reliably detect freed block
+			 */
+			mb_cache_entry_delete_block(ext2_mb_cache,
+						    hash, old_bh->b_blocknr);
 			/* Free the old block. */
-			if (ce)
-				mb_cache_entry_free(ce);
 			ea_bdebug(old_bh, "freeing");
 			ext2_free_blocks(inode, old_bh->b_blocknr, 1);
 			mark_inode_dirty(inode);
@@ -728,8 +734,6 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 		} else {
 			/* Decrement the refcount only. */
 			le32_add_cpu(&HDR(old_bh)->h_refcount, -1);
-			if (ce)
-				mb_cache_entry_release(ce);
 			dquot_free_block_nodirty(inode, 1);
 			mark_inode_dirty(inode);
 			mark_buffer_dirty(old_bh);
@@ -755,7 +759,6 @@ void
 ext2_xattr_delete_inode(struct inode *inode)
 {
 	struct buffer_head *bh = NULL;
-	struct mb_cache_entry *ce;
 
 	down_write(&EXT2_I(inode)->xattr_sem);
 	if (!EXT2_I(inode)->i_file_acl)
@@ -775,19 +778,22 @@ ext2_xattr_delete_inode(struct inode *inode)
 			EXT2_I(inode)->i_file_acl);
 		goto cleanup;
 	}
-	ce = mb_cache_entry_get(ext2_xattr_cache, bh->b_bdev, bh->b_blocknr);
 	lock_buffer(bh);
 	if (HDR(bh)->h_refcount == cpu_to_le32(1)) {
-		if (ce)
-			mb_cache_entry_free(ce);
+		__u32 hash = le32_to_cpu(HDR(bh)->h_hash);
+
+		/*
+		 * This must happen under buffer lock for ext2_xattr_set2() to
+		 * reliably detect freed block
+		 */
+		mb_cache_entry_delete_block(EXT2_SB(inode->i_sb)->s_mb_cache,
+					    hash, bh->b_blocknr);
 		ext2_free_blocks(inode, EXT2_I(inode)->i_file_acl, 1);
 		get_bh(bh);
 		bforget(bh);
 		unlock_buffer(bh);
 	} else {
 		le32_add_cpu(&HDR(bh)->h_refcount, -1);
-		if (ce)
-			mb_cache_entry_release(ce);
 		ea_bdebug(bh, "refcount now=%d",
 			le32_to_cpu(HDR(bh)->h_refcount));
 		unlock_buffer(bh);
@@ -804,18 +810,6 @@ cleanup:
 }
 
 /*
- * ext2_xattr_put_super()
- *
- * This is called when a file system is unmounted.
- */
-void
-ext2_xattr_put_super(struct super_block *sb)
-{
-	mb_cache_shrink(sb->s_bdev);
-}
-
-
-/*
  * ext2_xattr_cache_insert()
  *
  * Create a new entry in the extended attribute cache, and insert
@@ -824,28 +818,20 @@ ext2_xattr_put_super(struct super_block *sb)
  * Returns 0, or a negative error number on failure.
  */
 static int
-ext2_xattr_cache_insert(struct buffer_head *bh)
+ext2_xattr_cache_insert(struct mb_cache *cache, struct buffer_head *bh)
 {
 	__u32 hash = le32_to_cpu(HDR(bh)->h_hash);
-	struct mb_cache_entry *ce;
 	int error;
 
-	ce = mb_cache_entry_alloc(ext2_xattr_cache, GFP_NOFS);
-	if (!ce)
-		return -ENOMEM;
-	error = mb_cache_entry_insert(ce, bh->b_bdev, bh->b_blocknr, hash);
+	error = mb_cache_entry_create(cache, GFP_NOFS, hash, bh->b_blocknr, 1);
 	if (error) {
-		mb_cache_entry_free(ce);
 		if (error == -EBUSY) {
 			ea_bdebug(bh, "already in cache (%d cache entries)",
 				atomic_read(&ext2_xattr_cache->c_entry_count));
 			error = 0;
 		}
-	} else {
-		ea_bdebug(bh, "inserting [%x] (%d cache entries)", (int)hash,
-			  atomic_read(&ext2_xattr_cache->c_entry_count));
-		mb_cache_entry_release(ce);
-	}
+	} else
+		ea_bdebug(bh, "inserting [%x]", (int)hash);
 	return error;
 }
 
@@ -902,22 +888,16 @@ ext2_xattr_cache_find(struct inode *inode, struct ext2_xattr_header *header)
 {
 	__u32 hash = le32_to_cpu(header->h_hash);
 	struct mb_cache_entry *ce;
+	struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
 
 	if (!header->h_hash)
 		return NULL;  /* never share */
 	ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
 again:
-	ce = mb_cache_entry_find_first(ext2_xattr_cache, inode->i_sb->s_bdev,
-				       hash);
+	ce = mb_cache_entry_find_first(ext2_mb_cache, hash);
 	while (ce) {
 		struct buffer_head *bh;
 
-		if (IS_ERR(ce)) {
-			if (PTR_ERR(ce) == -EAGAIN)
-				goto again;
-			break;
-		}
-
 		bh = sb_bread(inode->i_sb, ce->e_block);
 		if (!bh) {
 			ext2_error(inode->i_sb, "ext2_xattr_cache_find",
@@ -925,7 +905,21 @@ again:
 				inode->i_ino, (unsigned long) ce->e_block);
 		} else {
 			lock_buffer(bh);
-			if (le32_to_cpu(HDR(bh)->h_refcount) >
+			/*
+			 * We have to be careful about races with freeing or
+			 * rehashing of xattr block. Once we hold buffer lock
+			 * xattr block's state is stable so we can check
+			 * whether the block got freed / rehashed or not.
+			 * Since we unhash mbcache entry under buffer lock when
+			 * freeing / rehashing xattr block, checking whether
+			 * entry is still hashed is reliable.
+			 */
+			if (hlist_bl_unhashed(&ce->e_hash_list)) {
+				mb_cache_entry_put(ext2_mb_cache, ce);
+				unlock_buffer(bh);
+				brelse(bh);
+				goto again;
+			} else if (le32_to_cpu(HDR(bh)->h_refcount) >
 				   EXT2_XATTR_REFCOUNT_MAX) {
 				ea_idebug(inode, "block %ld refcount %d>%d",
 					  (unsigned long) ce->e_block,
@@ -934,13 +928,14 @@ again:
 			} else if (!ext2_xattr_cmp(header, HDR(bh))) {
 				ea_bdebug(bh, "b_count=%d",
 					  atomic_read(&(bh->b_count)));
-				mb_cache_entry_release(ce);
+				mb_cache_entry_touch(ext2_mb_cache, ce);
+				mb_cache_entry_put(ext2_mb_cache, ce);
 				return bh;
 			}
 			unlock_buffer(bh);
 			brelse(bh);
 		}
-		ce = mb_cache_entry_find_next(ce, inode->i_sb->s_bdev, hash);
+		ce = mb_cache_entry_find_next(ext2_mb_cache, ce);
 	}
 	return NULL;
 }
@@ -1013,17 +1008,15 @@ static void ext2_xattr_rehash(struct ext2_xattr_header *header,
 
 #undef BLOCK_HASH_SHIFT
 
-int __init
-init_ext2_xattr(void)
+#define HASH_BUCKET_BITS 10
+
+struct mb_cache *ext2_xattr_create_cache(void)
 {
-	ext2_xattr_cache = mb_cache_create("ext2_xattr", 6);
-	if (!ext2_xattr_cache)
-		return -ENOMEM;
-	return 0;
+	return mb_cache_create(HASH_BUCKET_BITS);
 }
 
-void
-exit_ext2_xattr(void)
+void ext2_xattr_destroy_cache(struct mb_cache *cache)
 {
-	mb_cache_destroy(ext2_xattr_cache);
+	if (cache)
+		mb_cache_destroy(cache);
 }
diff --git a/fs/ext2/xattr.h b/fs/ext2/xattr.h
index 60edf298644e..6f82ab1b00ca 100644
--- a/fs/ext2/xattr.h
+++ b/fs/ext2/xattr.h
@@ -53,6 +53,8 @@ struct ext2_xattr_entry {
 #define EXT2_XATTR_SIZE(size) \
 	(((size) + EXT2_XATTR_ROUND) & ~EXT2_XATTR_ROUND)
 
+struct mb_cache;
+
 # ifdef CONFIG_EXT2_FS_XATTR
 
 extern const struct xattr_handler ext2_xattr_user_handler;
@@ -65,10 +67,9 @@ extern int ext2_xattr_get(struct inode *, int, const char *, void *, size_t);
 extern int ext2_xattr_set(struct inode *, int, const char *, const void *, size_t, int);
 
 extern void ext2_xattr_delete_inode(struct inode *);
-extern void ext2_xattr_put_super(struct super_block *);
 
-extern int init_ext2_xattr(void);
-extern void exit_ext2_xattr(void);
+extern struct mb_cache *ext2_xattr_create_cache(void);
+extern void ext2_xattr_destroy_cache(struct mb_cache *cache);
 
 extern const struct xattr_handler *ext2_xattr_handlers[];
 
@@ -93,19 +94,7 @@ ext2_xattr_delete_inode(struct inode *inode)
 {
 }
 
-static inline void
-ext2_xattr_put_super(struct super_block *sb)
-{
-}
-
-static inline int
-init_ext2_xattr(void)
-{
-	return 0;
-}
-
-static inline void
-exit_ext2_xattr(void)
+static inline void ext2_xattr_destroy_cache(struct mb_cache *cache)
 {
 }
 
diff --git a/fs/ext2/xattr_security.c b/fs/ext2/xattr_security.c
index 702fc6840246..ba97f243b050 100644
--- a/fs/ext2/xattr_security.c
+++ b/fs/ext2/xattr_security.c
@@ -7,37 +7,20 @@
 #include <linux/security.h>
 #include "xattr.h"
 
-static size_t
-ext2_xattr_security_list(struct dentry *dentry, char *list, size_t list_size,
-			 const char *name, size_t name_len, int type)
-{
-	const int prefix_len = XATTR_SECURITY_PREFIX_LEN;
-	const size_t total_len = prefix_len + name_len + 1;
-
-	if (list && total_len <= list_size) {
-		memcpy(list, XATTR_SECURITY_PREFIX, prefix_len);
-		memcpy(list+prefix_len, name, name_len);
-		list[prefix_len + name_len] = '\0';
-	}
-	return total_len;
-}
-
 static int
-ext2_xattr_security_get(struct dentry *dentry, const char *name,
-		       void *buffer, size_t size, int type)
+ext2_xattr_security_get(const struct xattr_handler *handler,
+			struct dentry *dentry, const char *name,
+			void *buffer, size_t size)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_SECURITY, name,
 			      buffer, size);
 }
 
 static int
-ext2_xattr_security_set(struct dentry *dentry, const char *name,
-		const void *value, size_t size, int flags, int type)
+ext2_xattr_security_set(const struct xattr_handler *handler,
+			struct dentry *dentry, const char *name,
+			const void *value, size_t size, int flags)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	return ext2_xattr_set(d_inode(dentry), EXT2_XATTR_INDEX_SECURITY, name,
 			      value, size, flags);
 }
@@ -68,7 +51,6 @@ ext2_init_security(struct inode *inode, struct inode *dir,
 
 const struct xattr_handler ext2_xattr_security_handler = {
 	.prefix	= XATTR_SECURITY_PREFIX,
-	.list	= ext2_xattr_security_list,
 	.get	= ext2_xattr_security_get,
 	.set	= ext2_xattr_security_set,
 };
diff --git a/fs/ext2/xattr_trusted.c b/fs/ext2/xattr_trusted.c
index 42b6e9874bcc..2c94d1930626 100644
--- a/fs/ext2/xattr_trusted.c
+++ b/fs/ext2/xattr_trusted.c
@@ -8,40 +8,26 @@
 #include "ext2.h"
 #include "xattr.h"
 
-static size_t
-ext2_xattr_trusted_list(struct dentry *dentry, char *list, size_t list_size,
-		const char *name, size_t name_len, int type)
+static bool
+ext2_xattr_trusted_list(struct dentry *dentry)
 {
-	const int prefix_len = XATTR_TRUSTED_PREFIX_LEN;
-	const size_t total_len = prefix_len + name_len + 1;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return 0;
-
-	if (list && total_len <= list_size) {
-		memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len);
-		memcpy(list+prefix_len, name, name_len);
-		list[prefix_len + name_len] = '\0';
-	}
-	return total_len;
+	return capable(CAP_SYS_ADMIN);
 }
 
 static int
-ext2_xattr_trusted_get(struct dentry *dentry, const char *name,
-		void *buffer, size_t size, int type)
+ext2_xattr_trusted_get(const struct xattr_handler *handler,
+		       struct dentry *dentry, const char *name,
+		       void *buffer, size_t size)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_TRUSTED, name,
 			      buffer, size);
 }
 
 static int
-ext2_xattr_trusted_set(struct dentry *dentry, const char *name,
-		const void *value, size_t size, int flags, int type)
+ext2_xattr_trusted_set(const struct xattr_handler *handler,
+		       struct dentry *dentry, const char *name,
+		       const void *value, size_t size, int flags)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	return ext2_xattr_set(d_inode(dentry), EXT2_XATTR_INDEX_TRUSTED, name,
 			      value, size, flags);
 }
diff --git a/fs/ext2/xattr_user.c b/fs/ext2/xattr_user.c
index ecdc4605192c..72a2a96d677f 100644
--- a/fs/ext2/xattr_user.c
+++ b/fs/ext2/xattr_user.c
@@ -10,30 +10,17 @@
 #include "ext2.h"
 #include "xattr.h"
 
-static size_t
-ext2_xattr_user_list(struct dentry *dentry, char *list, size_t list_size,
-		const char *name, size_t name_len, int type)
+static bool
+ext2_xattr_user_list(struct dentry *dentry)
 {
-	const size_t prefix_len = XATTR_USER_PREFIX_LEN;
-	const size_t total_len = prefix_len + name_len + 1;
-
-	if (!test_opt(dentry->d_sb, XATTR_USER))
-		return 0;
-
-	if (list && total_len <= list_size) {
-		memcpy(list, XATTR_USER_PREFIX, prefix_len);
-		memcpy(list+prefix_len, name, name_len);
-		list[prefix_len + name_len] = '\0';
-	}
-	return total_len;
+	return test_opt(dentry->d_sb, XATTR_USER);
 }
 
 static int
-ext2_xattr_user_get(struct dentry *dentry, const char *name,
-		void *buffer, size_t size, int type)
+ext2_xattr_user_get(const struct xattr_handler *handler,
+		    struct dentry *dentry, const char *name,
+		    void *buffer, size_t size)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	if (!test_opt(dentry->d_sb, XATTR_USER))
 		return -EOPNOTSUPP;
 	return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_USER,
@@ -41,11 +28,10 @@ ext2_xattr_user_get(struct dentry *dentry, const char *name,
 }
 
 static int
-ext2_xattr_user_set(struct dentry *dentry, const char *name,
-		const void *value, size_t size, int flags, int type)
+ext2_xattr_user_set(const struct xattr_handler *handler,
+		    struct dentry *dentry, const char *name,
+		    const void *value, size_t size, int flags)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	if (!test_opt(dentry->d_sb, XATTR_USER))
 		return -EOPNOTSUPP;
 
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index ec0668a60678..fe1f50fe764f 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -191,7 +191,6 @@ static int ext4_init_block_bitmap(struct super_block *sb,
 	/* If checksum is bad mark all blocks used to prevent allocation
 	 * essentially implementing a per-group read-only flag. */
 	if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
-		ext4_error(sb, "Checksum bad for group %u", block_group);
 		grp = ext4_get_group_info(sb, block_group);
 		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
 			percpu_counter_sub(&sbi->s_freeclusters_counter,
@@ -442,14 +441,16 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
 	}
 	ext4_lock_group(sb, block_group);
 	if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
-
 		err = ext4_init_block_bitmap(sb, bh, block_group, desc);
 		set_bitmap_uptodate(bh);
 		set_buffer_uptodate(bh);
 		ext4_unlock_group(sb, block_group);
 		unlock_buffer(bh);
-		if (err)
+		if (err) {
+			ext4_error(sb, "Failed to init block bitmap for group "
+				   "%u: %d", block_group, err);
 			goto out;
+		}
 		goto verify;
 	}
 	ext4_unlock_group(sb, block_group);
diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c
index af06830bfc00..6a6c27373b54 100644
--- a/fs/ext4/crypto.c
+++ b/fs/ext4/crypto.c
@@ -18,11 +18,9 @@
  * Special Publication 800-38E and IEEE P1619/D16.
  */
 
-#include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <crypto/skcipher.h>
 #include <keys/user-type.h>
 #include <keys/encrypted-type.h>
-#include <linux/crypto.h>
 #include <linux/ecryptfs.h>
 #include <linux/gfp.h>
 #include <linux/kernel.h>
@@ -34,6 +32,7 @@
 #include <linux/random.h>
 #include <linux/scatterlist.h>
 #include <linux/spinlock_types.h>
+#include <linux/namei.h>
 
 #include "ext4_extents.h"
 #include "xattr.h"
@@ -93,7 +92,8 @@ void ext4_release_crypto_ctx(struct ext4_crypto_ctx *ctx)
  * Return: An allocated and initialized encryption context on success; error
  * value or NULL otherwise.
  */
-struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode)
+struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode,
+					    gfp_t gfp_flags)
 {
 	struct ext4_crypto_ctx *ctx = NULL;
 	int res = 0;
@@ -120,7 +120,7 @@ struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode)
 		list_del(&ctx->free_list);
 	spin_unlock_irqrestore(&ext4_crypto_ctx_lock, flags);
 	if (!ctx) {
-		ctx = kmem_cache_zalloc(ext4_crypto_ctx_cachep, GFP_NOFS);
+		ctx = kmem_cache_zalloc(ext4_crypto_ctx_cachep, gfp_flags);
 		if (!ctx) {
 			res = -ENOMEM;
 			goto out;
@@ -257,25 +257,26 @@ static int ext4_page_crypto(struct inode *inode,
 			    ext4_direction_t rw,
 			    pgoff_t index,
 			    struct page *src_page,
-			    struct page *dest_page)
+			    struct page *dest_page,
+			    gfp_t gfp_flags)
 
 {
 	u8 xts_tweak[EXT4_XTS_TWEAK_SIZE];
-	struct ablkcipher_request *req = NULL;
+	struct skcipher_request *req = NULL;
 	DECLARE_EXT4_COMPLETION_RESULT(ecr);
 	struct scatterlist dst, src;
 	struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
-	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+	struct crypto_skcipher *tfm = ci->ci_ctfm;
 	int res = 0;
 
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	req = skcipher_request_alloc(tfm, gfp_flags);
 	if (!req) {
 		printk_ratelimited(KERN_ERR
 				   "%s: crypto_request_alloc() failed\n",
 				   __func__);
 		return -ENOMEM;
 	}
-	ablkcipher_request_set_callback(
+	skcipher_request_set_callback(
 		req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 		ext4_crypt_complete, &ecr);
 
@@ -285,33 +286,34 @@ static int ext4_page_crypto(struct inode *inode,
 	       EXT4_XTS_TWEAK_SIZE - sizeof(index));
 
 	sg_init_table(&dst, 1);
-	sg_set_page(&dst, dest_page, PAGE_CACHE_SIZE, 0);
+	sg_set_page(&dst, dest_page, PAGE_SIZE, 0);
 	sg_init_table(&src, 1);
-	sg_set_page(&src, src_page, PAGE_CACHE_SIZE, 0);
-	ablkcipher_request_set_crypt(req, &src, &dst, PAGE_CACHE_SIZE,
-				     xts_tweak);
+	sg_set_page(&src, src_page, PAGE_SIZE, 0);
+	skcipher_request_set_crypt(req, &src, &dst, PAGE_SIZE,
+				   xts_tweak);
 	if (rw == EXT4_DECRYPT)
-		res = crypto_ablkcipher_decrypt(req);
+		res = crypto_skcipher_decrypt(req);
 	else
-		res = crypto_ablkcipher_encrypt(req);
+		res = crypto_skcipher_encrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
 		wait_for_completion(&ecr.completion);
 		res = ecr.res;
 	}
-	ablkcipher_request_free(req);
+	skcipher_request_free(req);
 	if (res) {
 		printk_ratelimited(
 			KERN_ERR
-			"%s: crypto_ablkcipher_encrypt() returned %d\n",
+			"%s: crypto_skcipher_encrypt() returned %d\n",
 			__func__, res);
 		return res;
 	}
 	return 0;
 }
 
-static struct page *alloc_bounce_page(struct ext4_crypto_ctx *ctx)
+static struct page *alloc_bounce_page(struct ext4_crypto_ctx *ctx,
+				      gfp_t gfp_flags)
 {
-	ctx->w.bounce_page = mempool_alloc(ext4_bounce_page_pool, GFP_NOWAIT);
+	ctx->w.bounce_page = mempool_alloc(ext4_bounce_page_pool, gfp_flags);
 	if (ctx->w.bounce_page == NULL)
 		return ERR_PTR(-ENOMEM);
 	ctx->flags |= EXT4_WRITE_PATH_FL;
@@ -334,7 +336,8 @@ static struct page *alloc_bounce_page(struct ext4_crypto_ctx *ctx)
  * error value or NULL.
  */
 struct page *ext4_encrypt(struct inode *inode,
-			  struct page *plaintext_page)
+			  struct page *plaintext_page,
+			  gfp_t gfp_flags)
 {
 	struct ext4_crypto_ctx *ctx;
 	struct page *ciphertext_page = NULL;
@@ -342,17 +345,17 @@ struct page *ext4_encrypt(struct inode *inode,
 
 	BUG_ON(!PageLocked(plaintext_page));
 
-	ctx = ext4_get_crypto_ctx(inode);
+	ctx = ext4_get_crypto_ctx(inode, gfp_flags);
 	if (IS_ERR(ctx))
 		return (struct page *) ctx;
 
 	/* The encryption operation will require a bounce page. */
-	ciphertext_page = alloc_bounce_page(ctx);
+	ciphertext_page = alloc_bounce_page(ctx, gfp_flags);
 	if (IS_ERR(ciphertext_page))
 		goto errout;
 	ctx->w.control_page = plaintext_page;
 	err = ext4_page_crypto(inode, EXT4_ENCRYPT, plaintext_page->index,
-			       plaintext_page, ciphertext_page);
+			       plaintext_page, ciphertext_page, gfp_flags);
 	if (err) {
 		ciphertext_page = ERR_PTR(err);
 	errout:
@@ -380,18 +383,16 @@ int ext4_decrypt(struct page *page)
 {
 	BUG_ON(!PageLocked(page));
 
-	return ext4_page_crypto(page->mapping->host,
-				EXT4_DECRYPT, page->index, page, page);
+	return ext4_page_crypto(page->mapping->host, EXT4_DECRYPT,
+				page->index, page, page, GFP_NOFS);
 }
 
-int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex)
+int ext4_encrypted_zeroout(struct inode *inode, ext4_lblk_t lblk,
+			   ext4_fsblk_t pblk, ext4_lblk_t len)
 {
 	struct ext4_crypto_ctx	*ctx;
 	struct page		*ciphertext_page = NULL;
 	struct bio		*bio;
-	ext4_lblk_t		lblk = ex->ee_block;
-	ext4_fsblk_t		pblk = ext4_ext_pblock(ex);
-	unsigned int		len = ext4_ext_get_actual_len(ex);
 	int			ret, err = 0;
 
 #if 0
@@ -400,13 +401,13 @@ int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex)
 		 (unsigned long) inode->i_ino, lblk, len);
 #endif
 
-	BUG_ON(inode->i_sb->s_blocksize != PAGE_CACHE_SIZE);
+	BUG_ON(inode->i_sb->s_blocksize != PAGE_SIZE);
 
-	ctx = ext4_get_crypto_ctx(inode);
+	ctx = ext4_get_crypto_ctx(inode, GFP_NOFS);
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
-	ciphertext_page = alloc_bounce_page(ctx);
+	ciphertext_page = alloc_bounce_page(ctx, GFP_NOWAIT);
 	if (IS_ERR(ciphertext_page)) {
 		err = PTR_ERR(ciphertext_page);
 		goto errout;
@@ -414,11 +415,12 @@ int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex)
 
 	while (len--) {
 		err = ext4_page_crypto(inode, EXT4_ENCRYPT, lblk,
-				       ZERO_PAGE(0), ciphertext_page);
+				       ZERO_PAGE(0), ciphertext_page,
+				       GFP_NOFS);
 		if (err)
 			goto errout;
 
-		bio = bio_alloc(GFP_KERNEL, 1);
+		bio = bio_alloc(GFP_NOWAIT, 1);
 		if (!bio) {
 			err = -ENOMEM;
 			goto errout;
@@ -469,3 +471,66 @@ uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size)
 		return size;
 	return 0;
 }
+
+/*
+ * Validate dentries for encrypted directories to make sure we aren't
+ * potentially caching stale data after a key has been added or
+ * removed.
+ */
+static int ext4_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct dentry *dir;
+	struct ext4_crypt_info *ci;
+	int dir_has_key, cached_with_key;
+
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	dir = dget_parent(dentry);
+	if (!ext4_encrypted_inode(d_inode(dir))) {
+		dput(dir);
+		return 0;
+	}
+	ci = EXT4_I(d_inode(dir))->i_crypt_info;
+	if (ci && ci->ci_keyring_key &&
+	    (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
+					  (1 << KEY_FLAG_REVOKED) |
+					  (1 << KEY_FLAG_DEAD))))
+		ci = NULL;
+
+	/* this should eventually be an flag in d_flags */
+	cached_with_key = dentry->d_fsdata != NULL;
+	dir_has_key = (ci != NULL);
+	dput(dir);
+
+	/*
+	 * If the dentry was cached without the key, and it is a
+	 * negative dentry, it might be a valid name.  We can't check
+	 * if the key has since been made available due to locking
+	 * reasons, so we fail the validation so ext4_lookup() can do
+	 * this check.
+	 *
+	 * We also fail the validation if the dentry was created with
+	 * the key present, but we no longer have the key, or vice versa.
+	 */
+	if ((!cached_with_key && d_is_negative(dentry)) ||
+	    (!cached_with_key && dir_has_key) ||
+	    (cached_with_key && !dir_has_key)) {
+#if 0				/* Revalidation debug */
+		char buf[80];
+		char *cp = simple_dname(dentry, buf, sizeof(buf));
+
+		if (IS_ERR(cp))
+			cp = (char *) "???";
+		pr_err("revalidate: %s %p %d %d %d\n", cp, dentry->d_fsdata,
+		       cached_with_key, d_is_negative(dentry),
+		       dir_has_key);
+#endif
+		return 0;
+	}
+	return 1;
+}
+
+const struct dentry_operations ext4_encrypted_d_ops = {
+	.d_revalidate = ext4_d_revalidate,
+};
diff --git a/fs/ext4/crypto_fname.c b/fs/ext4/crypto_fname.c
index 2fbef8a14760..1a2f360405db 100644
--- a/fs/ext4/crypto_fname.c
+++ b/fs/ext4/crypto_fname.c
@@ -11,11 +11,9 @@
  *
  */
 
-#include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <crypto/skcipher.h>
 #include <keys/encrypted-type.h>
 #include <keys/user-type.h>
-#include <linux/crypto.h>
 #include <linux/gfp.h>
 #include <linux/kernel.h>
 #include <linux/key.h>
@@ -65,10 +63,10 @@ static int ext4_fname_encrypt(struct inode *inode,
 			      struct ext4_str *oname)
 {
 	u32 ciphertext_len;
-	struct ablkcipher_request *req = NULL;
+	struct skcipher_request *req = NULL;
 	DECLARE_EXT4_COMPLETION_RESULT(ecr);
 	struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
-	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+	struct crypto_skcipher *tfm = ci->ci_ctfm;
 	int res = 0;
 	char iv[EXT4_CRYPTO_BLOCK_SIZE];
 	struct scatterlist src_sg, dst_sg;
@@ -95,14 +93,14 @@ static int ext4_fname_encrypt(struct inode *inode,
 	}
 
 	/* Allocate request */
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
 	if (!req) {
 		printk_ratelimited(
 		    KERN_ERR "%s: crypto_request_alloc() failed\n", __func__);
 		kfree(alloc_buf);
 		return -ENOMEM;
 	}
-	ablkcipher_request_set_callback(req,
+	skcipher_request_set_callback(req,
 		CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 		ext4_dir_crypt_complete, &ecr);
 
@@ -117,14 +115,14 @@ static int ext4_fname_encrypt(struct inode *inode,
 	/* Create encryption request */
 	sg_init_one(&src_sg, workbuf, ciphertext_len);
 	sg_init_one(&dst_sg, oname->name, ciphertext_len);
-	ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv);
-	res = crypto_ablkcipher_encrypt(req);
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv);
+	res = crypto_skcipher_encrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
 		wait_for_completion(&ecr.completion);
 		res = ecr.res;
 	}
 	kfree(alloc_buf);
-	ablkcipher_request_free(req);
+	skcipher_request_free(req);
 	if (res < 0) {
 		printk_ratelimited(
 		    KERN_ERR "%s: Error (error code %d)\n", __func__, res);
@@ -145,11 +143,11 @@ static int ext4_fname_decrypt(struct inode *inode,
 			      struct ext4_str *oname)
 {
 	struct ext4_str tmp_in[2], tmp_out[1];
-	struct ablkcipher_request *req = NULL;
+	struct skcipher_request *req = NULL;
 	DECLARE_EXT4_COMPLETION_RESULT(ecr);
 	struct scatterlist src_sg, dst_sg;
 	struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
-	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+	struct crypto_skcipher *tfm = ci->ci_ctfm;
 	int res = 0;
 	char iv[EXT4_CRYPTO_BLOCK_SIZE];
 	unsigned lim = max_name_len(inode);
@@ -162,13 +160,13 @@ static int ext4_fname_decrypt(struct inode *inode,
 	tmp_out[0].name = oname->name;
 
 	/* Allocate request */
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
 	if (!req) {
 		printk_ratelimited(
 		    KERN_ERR "%s: crypto_request_alloc() failed\n",  __func__);
 		return -ENOMEM;
 	}
-	ablkcipher_request_set_callback(req,
+	skcipher_request_set_callback(req,
 		CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 		ext4_dir_crypt_complete, &ecr);
 
@@ -178,13 +176,13 @@ static int ext4_fname_decrypt(struct inode *inode,
 	/* Create encryption request */
 	sg_init_one(&src_sg, iname->name, iname->len);
 	sg_init_one(&dst_sg, oname->name, oname->len);
-	ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv);
-	res = crypto_ablkcipher_decrypt(req);
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv);
+	res = crypto_skcipher_decrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
 		wait_for_completion(&ecr.completion);
 		res = ecr.res;
 	}
-	ablkcipher_request_free(req);
+	skcipher_request_free(req);
 	if (res < 0) {
 		printk_ratelimited(
 		    KERN_ERR "%s: Error in ext4_fname_encrypt (error code %d)\n",
diff --git a/fs/ext4/crypto_key.c b/fs/ext4/crypto_key.c
index c5882b36e558..0129d688d1f7 100644
--- a/fs/ext4/crypto_key.c
+++ b/fs/ext4/crypto_key.c
@@ -8,6 +8,7 @@
  * Written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar, 2015.
  */
 
+#include <crypto/skcipher.h>
 #include <keys/encrypted-type.h>
 #include <keys/user-type.h>
 #include <linux/random.h>
@@ -41,45 +42,42 @@ static int ext4_derive_key_aes(char deriving_key[EXT4_AES_128_ECB_KEY_SIZE],
 			       char derived_key[EXT4_AES_256_XTS_KEY_SIZE])
 {
 	int res = 0;
-	struct ablkcipher_request *req = NULL;
+	struct skcipher_request *req = NULL;
 	DECLARE_EXT4_COMPLETION_RESULT(ecr);
 	struct scatterlist src_sg, dst_sg;
-	struct crypto_ablkcipher *tfm = crypto_alloc_ablkcipher("ecb(aes)", 0,
-								0);
+	struct crypto_skcipher *tfm = crypto_alloc_skcipher("ecb(aes)", 0, 0);
 
 	if (IS_ERR(tfm)) {
 		res = PTR_ERR(tfm);
 		tfm = NULL;
 		goto out;
 	}
-	crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
 	if (!req) {
 		res = -ENOMEM;
 		goto out;
 	}
-	ablkcipher_request_set_callback(req,
+	skcipher_request_set_callback(req,
 			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 			derive_crypt_complete, &ecr);
-	res = crypto_ablkcipher_setkey(tfm, deriving_key,
-				       EXT4_AES_128_ECB_KEY_SIZE);
+	res = crypto_skcipher_setkey(tfm, deriving_key,
+				     EXT4_AES_128_ECB_KEY_SIZE);
 	if (res < 0)
 		goto out;
 	sg_init_one(&src_sg, source_key, EXT4_AES_256_XTS_KEY_SIZE);
 	sg_init_one(&dst_sg, derived_key, EXT4_AES_256_XTS_KEY_SIZE);
-	ablkcipher_request_set_crypt(req, &src_sg, &dst_sg,
-				     EXT4_AES_256_XTS_KEY_SIZE, NULL);
-	res = crypto_ablkcipher_encrypt(req);
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg,
+				   EXT4_AES_256_XTS_KEY_SIZE, NULL);
+	res = crypto_skcipher_encrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
 		wait_for_completion(&ecr.completion);
 		res = ecr.res;
 	}
 
 out:
-	if (req)
-		ablkcipher_request_free(req);
-	if (tfm)
-		crypto_free_ablkcipher(tfm);
+	skcipher_request_free(req);
+	crypto_free_skcipher(tfm);
 	return res;
 }
 
@@ -90,7 +88,7 @@ void ext4_free_crypt_info(struct ext4_crypt_info *ci)
 
 	if (ci->ci_keyring_key)
 		key_put(ci->ci_keyring_key);
-	crypto_free_ablkcipher(ci->ci_ctfm);
+	crypto_free_skcipher(ci->ci_ctfm);
 	kmem_cache_free(ext4_crypt_info_cachep, ci);
 }
 
@@ -122,7 +120,7 @@ int _ext4_get_encryption_info(struct inode *inode)
 	struct ext4_encryption_context ctx;
 	const struct user_key_payload *ukp;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	struct crypto_ablkcipher *ctfm;
+	struct crypto_skcipher *ctfm;
 	const char *cipher_str;
 	char raw_key[EXT4_MAX_KEY_SIZE];
 	char mode;
@@ -213,9 +211,11 @@ retry:
 		res = -ENOKEY;
 		goto out;
 	}
+	down_read(&keyring_key->sem);
 	ukp = user_key_payload(keyring_key);
 	if (ukp->datalen != sizeof(struct ext4_encryption_key)) {
 		res = -EINVAL;
+		up_read(&keyring_key->sem);
 		goto out;
 	}
 	master_key = (struct ext4_encryption_key *)ukp->data;
@@ -226,14 +226,16 @@ retry:
 			    "ext4: key size incorrect: %d\n",
 			    master_key->size);
 		res = -ENOKEY;
+		up_read(&keyring_key->sem);
 		goto out;
 	}
 	res = ext4_derive_key_aes(ctx.nonce, master_key->raw,
 				  raw_key);
+	up_read(&keyring_key->sem);
 	if (res)
 		goto out;
 got_key:
-	ctfm = crypto_alloc_ablkcipher(cipher_str, 0, 0);
+	ctfm = crypto_alloc_skcipher(cipher_str, 0, 0);
 	if (!ctfm || IS_ERR(ctfm)) {
 		res = ctfm ? PTR_ERR(ctfm) : -ENOMEM;
 		printk(KERN_DEBUG
@@ -242,11 +244,11 @@ got_key:
 		goto out;
 	}
 	crypt_info->ci_ctfm = ctfm;
-	crypto_ablkcipher_clear_flags(ctfm, ~0);
-	crypto_tfm_set_flags(crypto_ablkcipher_tfm(ctfm),
+	crypto_skcipher_clear_flags(ctfm, ~0);
+	crypto_tfm_set_flags(crypto_skcipher_tfm(ctfm),
 			     CRYPTO_TFM_REQ_WEAK_KEY);
-	res = crypto_ablkcipher_setkey(ctfm, raw_key,
-				       ext4_encryption_key_size(mode));
+	res = crypto_skcipher_setkey(ctfm, raw_key,
+				     ext4_encryption_key_size(mode));
 	if (res)
 		goto out;
 	memzero_explicit(raw_key, sizeof(raw_key));
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 1d1bca74f844..561d7308b393 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -111,6 +111,12 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 	int dir_has_error = 0;
 	struct ext4_str fname_crypto_str = {.name = NULL, .len = 0};
 
+	if (ext4_encrypted_inode(inode)) {
+		err = ext4_get_encryption_info(inode);
+		if (err && err != -ENOKEY)
+			return err;
+	}
+
 	if (is_dx_dir(inode)) {
 		err = ext4_dx_readdir(file, ctx);
 		if (err != ERR_BAD_DX_DIR) {
@@ -149,16 +155,19 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 		err = ext4_map_blocks(NULL, inode, &map, 0);
 		if (err > 0) {
 			pgoff_t index = map.m_pblk >>
-					(PAGE_CACHE_SHIFT - inode->i_blkbits);
+					(PAGE_SHIFT - inode->i_blkbits);
 			if (!ra_has_index(&file->f_ra, index))
 				page_cache_sync_readahead(
 					sb->s_bdev->bd_inode->i_mapping,
 					&file->f_ra, file,
 					index, 1);
-			file->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT;
+			file->f_ra.prev_pos = (loff_t)index << PAGE_SHIFT;
 			bh = ext4_bread(NULL, inode, map.m_lblk, 0);
-			if (IS_ERR(bh))
-				return PTR_ERR(bh);
+			if (IS_ERR(bh)) {
+				err = PTR_ERR(bh);
+				bh = NULL;
+				goto errout;
+			}
 		}
 
 		if (!bh) {
@@ -276,7 +285,7 @@ errout:
 static inline int is_32bit_api(void)
 {
 #ifdef CONFIG_COMPAT
-	return is_compat_task();
+	return in_compat_syscall();
 #else
 	return (BITS_PER_LONG == 32);
 #endif
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 750063f7a50c..349afebe21ee 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -26,6 +26,7 @@
 #include <linux/seqlock.h>
 #include <linux/mutex.h>
 #include <linux/timer.h>
+#include <linux/version.h>
 #include <linux/wait.h>
 #include <linux/blockgroup_lock.h>
 #include <linux/percpu_counter.h>
@@ -41,6 +42,18 @@
  */
 
 /*
+ * with AGGRESSIVE_CHECK allocator runs consistency checks over
+ * structures. these checks slow things down a lot
+ */
+#define AGGRESSIVE_CHECK__
+
+/*
+ * with DOUBLE_CHECK defined mballoc creates persistent in-core
+ * bitmaps, maintains and uses them to check for double allocations
+ */
+#define DOUBLE_CHECK__
+
+/*
  * Define EXT4FS_DEBUG to produce debug messages
  */
 #undef EXT4FS_DEBUG
@@ -181,9 +194,9 @@ typedef struct ext4_io_end {
 	struct bio		*bio;		/* Linked list of completed
 						 * bios covering the extent */
 	unsigned int		flag;		/* unwritten or not */
+	atomic_t		count;		/* reference counter */
 	loff_t			offset;		/* offset in the file */
 	ssize_t			size;		/* size of the extent */
-	atomic_t		count;		/* reference counter */
 } ext4_io_end_t;
 
 struct ext4_io_submit {
@@ -377,14 +390,22 @@ struct flex_groups {
 #define EXT4_PROJINHERIT_FL		0x20000000 /* Create with parents projid */
 #define EXT4_RESERVED_FL		0x80000000 /* reserved for ext4 lib */
 
-#define EXT4_FL_USER_VISIBLE		0x004BDFFF /* User visible flags */
-#define EXT4_FL_USER_MODIFIABLE		0x004380FF /* User modifiable flags */
+#define EXT4_FL_USER_VISIBLE		0x304BDFFF /* User visible flags */
+#define EXT4_FL_USER_MODIFIABLE		0x204380FF /* User modifiable flags */
+
+#define EXT4_FL_XFLAG_VISIBLE		(EXT4_SYNC_FL | \
+					 EXT4_IMMUTABLE_FL | \
+					 EXT4_APPEND_FL | \
+					 EXT4_NODUMP_FL | \
+					 EXT4_NOATIME_FL | \
+					 EXT4_PROJINHERIT_FL)
 
 /* Flags that should be inherited by new inodes from their parent. */
 #define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
 			   EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
 			   EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
-			   EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL)
+			   EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL |\
+			   EXT4_PROJINHERIT_FL)
 
 /* Flags that are appropriate for regular files (all but dir-specific ones). */
 #define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL))
@@ -554,10 +575,12 @@ enum {
 #define EXT4_GET_BLOCKS_NO_NORMALIZE		0x0040
 	/* Request will not result in inode size update (user for fallocate) */
 #define EXT4_GET_BLOCKS_KEEP_SIZE		0x0080
-	/* Do not take i_data_sem locking in ext4_map_blocks */
-#define EXT4_GET_BLOCKS_NO_LOCK			0x0100
 	/* Convert written extents to unwritten */
-#define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN	0x0200
+#define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN	0x0100
+	/* Write zeros to newly created written extents */
+#define EXT4_GET_BLOCKS_ZERO			0x0200
+#define EXT4_GET_BLOCKS_CREATE_ZERO		(EXT4_GET_BLOCKS_CREATE |\
+					EXT4_GET_BLOCKS_ZERO)
 
 /*
  * The bit position of these flags must not overlap with any of the
@@ -615,6 +638,46 @@ enum {
 #define EXT4_IOC_GET_ENCRYPTION_PWSALT	_IOW('f', 20, __u8[16])
 #define EXT4_IOC_GET_ENCRYPTION_POLICY	_IOW('f', 21, struct ext4_encryption_policy)
 
+#ifndef FS_IOC_FSGETXATTR
+/* Until the uapi changes get merged for project quota... */
+
+#define FS_IOC_FSGETXATTR		_IOR('X', 31, struct fsxattr)
+#define FS_IOC_FSSETXATTR		_IOW('X', 32, struct fsxattr)
+
+/*
+ * Structure for FS_IOC_FSGETXATTR and FS_IOC_FSSETXATTR.
+ */
+struct fsxattr {
+	__u32		fsx_xflags;	/* xflags field value (get/set) */
+	__u32		fsx_extsize;	/* extsize field value (get/set)*/
+	__u32		fsx_nextents;	/* nextents field value (get)	*/
+	__u32		fsx_projid;	/* project identifier (get/set) */
+	unsigned char	fsx_pad[12];
+};
+
+/*
+ * Flags for the fsx_xflags field
+ */
+#define FS_XFLAG_REALTIME	0x00000001	/* data in realtime volume */
+#define FS_XFLAG_PREALLOC	0x00000002	/* preallocated file extents */
+#define FS_XFLAG_IMMUTABLE	0x00000008	/* file cannot be modified */
+#define FS_XFLAG_APPEND		0x00000010	/* all writes append */
+#define FS_XFLAG_SYNC		0x00000020	/* all writes synchronous */
+#define FS_XFLAG_NOATIME	0x00000040	/* do not update access time */
+#define FS_XFLAG_NODUMP		0x00000080	/* do not include in backups */
+#define FS_XFLAG_RTINHERIT	0x00000100	/* create with rt bit set */
+#define FS_XFLAG_PROJINHERIT	0x00000200	/* create with parents projid */
+#define FS_XFLAG_NOSYMLINKS	0x00000400	/* disallow symlink creation */
+#define FS_XFLAG_EXTSIZE	0x00000800	/* extent size allocator hint */
+#define FS_XFLAG_EXTSZINHERIT	0x00001000	/* inherit inode extent size */
+#define FS_XFLAG_NODEFRAG	0x00002000  	/* do not defragment */
+#define FS_XFLAG_FILESTREAM	0x00004000	/* use filestream allocator */
+#define FS_XFLAG_HASATTR	0x80000000	/* no DIFLAG for this */
+#endif /* !defined(FS_IOC_FSGETXATTR) */
+
+#define EXT4_IOC_FSGETXATTR		FS_IOC_FSGETXATTR
+#define EXT4_IOC_FSSETXATTR		FS_IOC_FSSETXATTR
+
 #if defined(__KERNEL__) && defined(CONFIG_COMPAT)
 /*
  * ioctl commands in 32 bit emulation
@@ -727,19 +790,55 @@ struct move_extent {
 	<= (EXT4_GOOD_OLD_INODE_SIZE +			\
 	    (einode)->i_extra_isize))			\
 
+/*
+ * We use an encoding that preserves the times for extra epoch "00":
+ *
+ * extra  msb of                         adjust for signed
+ * epoch  32-bit                         32-bit tv_sec to
+ * bits   time    decoded 64-bit tv_sec  64-bit tv_sec      valid time range
+ * 0 0    1    -0x80000000..-0x00000001  0x000000000 1901-12-13..1969-12-31
+ * 0 0    0    0x000000000..0x07fffffff  0x000000000 1970-01-01..2038-01-19
+ * 0 1    1    0x080000000..0x0ffffffff  0x100000000 2038-01-19..2106-02-07
+ * 0 1    0    0x100000000..0x17fffffff  0x100000000 2106-02-07..2174-02-25
+ * 1 0    1    0x180000000..0x1ffffffff  0x200000000 2174-02-25..2242-03-16
+ * 1 0    0    0x200000000..0x27fffffff  0x200000000 2242-03-16..2310-04-04
+ * 1 1    1    0x280000000..0x2ffffffff  0x300000000 2310-04-04..2378-04-22
+ * 1 1    0    0x300000000..0x37fffffff  0x300000000 2378-04-22..2446-05-10
+ *
+ * Note that previous versions of the kernel on 64-bit systems would
+ * incorrectly use extra epoch bits 1,1 for dates between 1901 and
+ * 1970.  e2fsck will correct this, assuming that it is run on the
+ * affected filesystem before 2242.
+ */
+
 static inline __le32 ext4_encode_extra_time(struct timespec *time)
 {
-       return cpu_to_le32((sizeof(time->tv_sec) > 4 ?
-			   (time->tv_sec >> 32) & EXT4_EPOCH_MASK : 0) |
-                          ((time->tv_nsec << EXT4_EPOCH_BITS) & EXT4_NSEC_MASK));
+	u32 extra = sizeof(time->tv_sec) > 4 ?
+		((time->tv_sec - (s32)time->tv_sec) >> 32) & EXT4_EPOCH_MASK : 0;
+	return cpu_to_le32(extra | (time->tv_nsec << EXT4_EPOCH_BITS));
 }
 
 static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra)
 {
-       if (sizeof(time->tv_sec) > 4)
-	       time->tv_sec |= (__u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK)
-			       << 32;
-       time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS;
+	if (unlikely(sizeof(time->tv_sec) > 4 &&
+			(extra & cpu_to_le32(EXT4_EPOCH_MASK)))) {
+#if LINUX_VERSION_CODE < KERNEL_VERSION(4,20,0)
+		/* Handle legacy encoding of pre-1970 dates with epoch
+		 * bits 1,1.  We assume that by kernel version 4.20,
+		 * everyone will have run fsck over the affected
+		 * filesystems to correct the problem.  (This
+		 * backwards compatibility may be removed before this
+		 * time, at the discretion of the ext4 developers.)
+		 */
+		u64 extra_bits = le32_to_cpu(extra) & EXT4_EPOCH_MASK;
+		if (extra_bits == 3 && ((time->tv_sec) & 0x80000000) != 0)
+			extra_bits = 0;
+		time->tv_sec += extra_bits << 32;
+#else
+		time->tv_sec += (u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) << 32;
+#endif
+	}
+	time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS;
 }
 
 #define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode)			       \
@@ -813,6 +912,29 @@ do {									       \
 #include "extents_status.h"
 
 /*
+ * Lock subclasses for i_data_sem in the ext4_inode_info structure.
+ *
+ * These are needed to avoid lockdep false positives when we need to
+ * allocate blocks to the quota inode during ext4_map_blocks(), while
+ * holding i_data_sem for a normal (non-quota) inode.  Since we don't
+ * do quota tracking for the quota inode, this avoids deadlock (as
+ * well as infinite recursion, since it isn't turtles all the way
+ * down...)
+ *
+ *  I_DATA_SEM_NORMAL - Used for most inodes
+ *  I_DATA_SEM_OTHER  - Used by move_inode.c for the second normal inode
+ *			  where the second inode has larger inode number
+ *			  than the first
+ *  I_DATA_SEM_QUOTA  - Used for quota inodes only
+ */
+enum {
+	I_DATA_SEM_NORMAL = 0,
+	I_DATA_SEM_OTHER,
+	I_DATA_SEM_QUOTA,
+};
+
+
+/*
  * fourth extended file system inode data in memory
  */
 struct ext4_inode_info {
@@ -873,6 +995,15 @@ struct ext4_inode_info {
 	 * by other means, so we have i_data_sem.
 	 */
 	struct rw_semaphore i_data_sem;
+	/*
+	 * i_mmap_sem is for serializing page faults with truncate / punch hole
+	 * operations. We have to make sure that new page cannot be faulted in
+	 * a section of the inode that is being punched. We cannot easily use
+	 * i_data_sem for this since we need protection for the whole punch
+	 * operation and i_data_sem ranks below transaction start so we have
+	 * to occasionally drop it.
+	 */
+	struct rw_semaphore i_mmap_sem;
 	struct inode vfs_inode;
 	struct jbd2_inode *jinode;
 
@@ -928,13 +1059,8 @@ struct ext4_inode_info {
 	 * transaction reserved
 	 */
 	struct list_head i_rsv_conversion_list;
-	/*
-	 * Completed IOs that need unwritten extents handling and don't have
-	 * transaction reserved
-	 */
-	atomic_t i_ioend_count;	/* Number of outstanding io_end structs */
-	atomic_t i_unwritten; /* Nr. of inflight conversions pending */
 	struct work_struct i_rsv_conversion_work;
+	atomic_t i_unwritten; /* Nr. of inflight conversions pending */
 
 	spinlock_t i_block_reservation_lock;
 
@@ -956,6 +1082,7 @@ struct ext4_inode_info {
 	/* Encryption params */
 	struct ext4_crypt_info *i_crypt_info;
 #endif
+	kprojid_t i_projid;
 };
 
 /*
@@ -1211,7 +1338,7 @@ struct ext4_super_block {
 #endif
 
 /* Number of quota types we support */
-#define EXT4_MAXQUOTAS 2
+#define EXT4_MAXQUOTAS 3
 
 /*
  * fourth extended-fs super-block data in memory
@@ -1407,25 +1534,6 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 		 ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
 }
 
-static inline void ext4_set_io_unwritten_flag(struct inode *inode,
-					      struct ext4_io_end *io_end)
-{
-	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
-		io_end->flag |= EXT4_IO_END_UNWRITTEN;
-		atomic_inc(&EXT4_I(inode)->i_unwritten);
-	}
-}
-
-static inline ext4_io_end_t *ext4_inode_aio(struct inode *inode)
-{
-	return inode->i_private;
-}
-
-static inline void ext4_inode_aio_set(struct inode *inode, ext4_io_end_t *io)
-{
-	inode->i_private = io;
-}
-
 /*
  * Inode dynamic state flags
  */
@@ -1717,7 +1825,8 @@ EXT4_FEATURE_INCOMPAT_FUNCS(encrypt,		ENCRYPT)
 					 EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\
 					 EXT4_FEATURE_RO_COMPAT_BIGALLOC |\
 					 EXT4_FEATURE_RO_COMPAT_METADATA_CSUM|\
-					 EXT4_FEATURE_RO_COMPAT_QUOTA)
+					 EXT4_FEATURE_RO_COMPAT_QUOTA |\
+					 EXT4_FEATURE_RO_COMPAT_PROJECT)
 
 #define EXTN_FEATURE_FUNCS(ver) \
 static inline bool ext4_has_unknown_ext##ver##_compat_features(struct super_block *sb) \
@@ -1759,6 +1868,11 @@ static inline bool ext4_has_incompat_features(struct super_block *sb)
 #define	EXT4_DEF_RESUID		0
 #define	EXT4_DEF_RESGID		0
 
+/*
+ * Default project ID
+ */
+#define	EXT4_DEF_PROJID		0
+
 #define EXT4_DEF_INODE_READAHEAD_BLKS	32
 
 /*
@@ -1870,7 +1984,7 @@ ext4_rec_len_from_disk(__le16 dlen, unsigned blocksize)
 {
 	unsigned len = le16_to_cpu(dlen);
 
-#if (PAGE_CACHE_SIZE >= 65536)
+#if (PAGE_SIZE >= 65536)
 	if (len == EXT4_MAX_REC_LEN || len == 0)
 		return blocksize;
 	return (len & 65532) | ((len & 3) << 16);
@@ -1883,7 +1997,7 @@ static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize)
 {
 	if ((len > blocksize) || (blocksize > (1 << 18)) || (len & 3))
 		BUG();
-#if (PAGE_CACHE_SIZE >= 65536)
+#if (PAGE_SIZE >= 65536)
 	if (len < 65536)
 		return cpu_to_le16(len);
 	if (len == blocksize) {
@@ -2191,13 +2305,17 @@ extern struct kmem_cache *ext4_crypt_info_cachep;
 bool ext4_valid_contents_enc_mode(uint32_t mode);
 uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size);
 extern struct workqueue_struct *ext4_read_workqueue;
-struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode);
+struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode,
+					    gfp_t gfp_flags);
 void ext4_release_crypto_ctx(struct ext4_crypto_ctx *ctx);
 void ext4_restore_control_page(struct page *data_page);
 struct page *ext4_encrypt(struct inode *inode,
-			  struct page *plaintext_page);
+			  struct page *plaintext_page,
+			  gfp_t gfp_flags);
 int ext4_decrypt(struct page *page);
-int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex);
+int ext4_encrypted_zeroout(struct inode *inode, ext4_lblk_t lblk,
+			   ext4_fsblk_t pblk, ext4_lblk_t len);
+extern const struct dentry_operations ext4_encrypted_d_ops;
 
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
 int ext4_init_crypto(void);
@@ -2401,12 +2519,14 @@ extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
 int ext4_inode_is_fast_symlink(struct inode *inode);
 struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int);
 struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int);
-int ext4_get_block_write(struct inode *inode, sector_t iblock,
-			 struct buffer_head *bh_result, int create);
-int ext4_get_block_dax(struct inode *inode, sector_t iblock,
-			 struct buffer_head *bh_result, int create);
+int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
+			     struct buffer_head *bh_result, int create);
+int ext4_dax_mmap_get_block(struct inode *inode, sector_t iblock,
+			    struct buffer_head *bh_result, int create);
 int ext4_get_block(struct inode *inode, sector_t iblock,
-				struct buffer_head *bh_result, int create);
+		   struct buffer_head *bh_result, int create);
+int ext4_dio_get_block(struct inode *inode, sector_t iblock,
+		       struct buffer_head *bh_result, int create);
 int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 			   struct buffer_head *bh, int create);
 int ext4_walk_page_buffers(handle_t *handle,
@@ -2447,9 +2567,16 @@ extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
 extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
 			     loff_t lstart, loff_t lend);
 extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
+extern int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
 extern qsize_t *ext4_get_reserved_space(struct inode *inode);
+extern int ext4_get_projid(struct inode *inode, kprojid_t *projid);
 extern void ext4_da_update_reserve_space(struct inode *inode,
 					int used, int quota_claim);
+extern int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk,
+			      ext4_fsblk_t pblk, ext4_lblk_t len);
+extern int ext4_get_next_extent(struct inode *inode, ext4_lblk_t lblk,
+				unsigned int map_len,
+				struct extent_status *result);
 
 /* indirect.c */
 extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
@@ -2788,7 +2915,7 @@ do {								\
 static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
 {
 	WARN_ON_ONCE(S_ISREG(inode->i_mode) &&
-		     !mutex_is_locked(&inode->i_mutex));
+		     !inode_is_locked(inode));
 	down_write(&EXT4_I(inode)->i_data_sem);
 	if (newsize > EXT4_I(inode)->i_disksize)
 		EXT4_I(inode)->i_disksize = newsize;
@@ -2811,6 +2938,9 @@ static inline int ext4_update_inode_size(struct inode *inode, loff_t newsize)
 	return changed;
 }
 
+int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
+				      loff_t len);
+
 struct ext4_group_info {
 	unsigned long   bb_state;
 	struct rb_root  bb_free_root;
@@ -2949,8 +3079,7 @@ extern int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
 					 struct page *page);
 extern int ext4_try_add_inline_entry(handle_t *handle,
 				     struct ext4_filename *fname,
-				     struct dentry *dentry,
-				     struct inode *inode);
+				     struct inode *dir, struct inode *inode);
 extern int ext4_try_create_inline_dir(handle_t *handle,
 				      struct inode *parent,
 				      struct inode *inode);
@@ -3174,15 +3303,33 @@ static inline void ext4_inode_resume_unlocked_dio(struct inode *inode)
 #define EXT4_WQ_HASH_SZ		37
 #define ext4_ioend_wq(v)   (&ext4__ioend_wq[((unsigned long)(v)) %\
 					    EXT4_WQ_HASH_SZ])
-#define ext4_aio_mutex(v)  (&ext4__aio_mutex[((unsigned long)(v)) %\
-					     EXT4_WQ_HASH_SZ])
 extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
-extern struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ];
 
 #define EXT4_RESIZING	0
 extern int ext4_resize_begin(struct super_block *sb);
 extern void ext4_resize_end(struct super_block *sb);
 
+static inline void ext4_set_io_unwritten_flag(struct inode *inode,
+					      struct ext4_io_end *io_end)
+{
+	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+		io_end->flag |= EXT4_IO_END_UNWRITTEN;
+		atomic_inc(&EXT4_I(inode)->i_unwritten);
+	}
+}
+
+static inline void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end)
+{
+	struct inode *inode = io_end->inode;
+
+	if (io_end->flag & EXT4_IO_END_UNWRITTEN) {
+		io_end->flag &= ~EXT4_IO_END_UNWRITTEN;
+		/* Wake up anyone waiting on unwritten extent conversion */
+		if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten))
+			wake_up_all(ext4_ioend_wq(inode));
+	}
+}
+
 #endif	/* __KERNEL__ */
 
 #define EFSBADCRC	EBADMSG		/* Bad CRC detected */
diff --git a/fs/ext4/ext4_crypto.h b/fs/ext4/ext4_crypto.h
index ac7d4e813796..1f73c29717e1 100644
--- a/fs/ext4/ext4_crypto.h
+++ b/fs/ext4/ext4_crypto.h
@@ -77,7 +77,7 @@ struct ext4_crypt_info {
 	char		ci_data_mode;
 	char		ci_filename_mode;
 	char		ci_flags;
-	struct crypto_ablkcipher *ci_ctfm;
+	struct crypto_skcipher *ci_ctfm;
 	struct key	*ci_keyring_key;
 	char		ci_master_key[EXT4_KEY_DESCRIPTOR_SIZE];
 };
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 3c9381547094..8ecf84b8f5a1 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -11,7 +11,7 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public Licens
+ * You should have received a copy of the GNU General Public License
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-
  */
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 551353b1b17a..95bf4679ac54 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -15,7 +15,7 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public Licens
+ * You should have received a copy of the GNU General Public License
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-
  */
@@ -1736,6 +1736,12 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
 	 */
 	if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN)
 		return 0;
+	/*
+	 * The check for IO to unwritten extent is somewhat racy as we
+	 * increment i_unwritten / set EXT4_STATE_DIO_UNWRITTEN only after
+	 * dropping i_data_sem. But reserved blocks should save us in that
+	 * case.
+	 */
 	if (ext4_ext_is_unwritten(ex1) &&
 	    (ext4_test_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN) ||
 	     atomic_read(&EXT4_I(inode)->i_unwritten) ||
@@ -2293,59 +2299,69 @@ static int ext4_fill_fiemap_extents(struct inode *inode,
 }
 
 /*
- * ext4_ext_put_gap_in_cache:
- * calculate boundaries of the gap that the requested block fits into
- * and cache this gap
+ * ext4_ext_determine_hole - determine hole around given block
+ * @inode:	inode we lookup in
+ * @path:	path in extent tree to @lblk
+ * @lblk:	pointer to logical block around which we want to determine hole
+ *
+ * Determine hole length (and start if easily possible) around given logical
+ * block. We don't try too hard to find the beginning of the hole but @path
+ * actually points to extent before @lblk, we provide it.
+ *
+ * The function returns the length of a hole starting at @lblk. We update @lblk
+ * to the beginning of the hole if we managed to find it.
  */
-static void
-ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path,
-				ext4_lblk_t block)
+static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode,
+					   struct ext4_ext_path *path,
+					   ext4_lblk_t *lblk)
 {
 	int depth = ext_depth(inode);
-	ext4_lblk_t len;
-	ext4_lblk_t lblock;
 	struct ext4_extent *ex;
-	struct extent_status es;
+	ext4_lblk_t len;
 
 	ex = path[depth].p_ext;
 	if (ex == NULL) {
 		/* there is no extent yet, so gap is [0;-] */
-		lblock = 0;
+		*lblk = 0;
 		len = EXT_MAX_BLOCKS;
-		ext_debug("cache gap(whole file):");
-	} else if (block < le32_to_cpu(ex->ee_block)) {
-		lblock = block;
-		len = le32_to_cpu(ex->ee_block) - block;
-		ext_debug("cache gap(before): %u [%u:%u]",
-				block,
-				le32_to_cpu(ex->ee_block),
-				 ext4_ext_get_actual_len(ex));
-	} else if (block >= le32_to_cpu(ex->ee_block)
+	} else if (*lblk < le32_to_cpu(ex->ee_block)) {
+		len = le32_to_cpu(ex->ee_block) - *lblk;
+	} else if (*lblk >= le32_to_cpu(ex->ee_block)
 			+ ext4_ext_get_actual_len(ex)) {
 		ext4_lblk_t next;
-		lblock = le32_to_cpu(ex->ee_block)
-			+ ext4_ext_get_actual_len(ex);
 
+		*lblk = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex);
 		next = ext4_ext_next_allocated_block(path);
-		ext_debug("cache gap(after): [%u:%u] %u",
-				le32_to_cpu(ex->ee_block),
-				ext4_ext_get_actual_len(ex),
-				block);
-		BUG_ON(next == lblock);
-		len = next - lblock;
+		BUG_ON(next == *lblk);
+		len = next - *lblk;
 	} else {
 		BUG();
 	}
+	return len;
+}
+
+/*
+ * ext4_ext_put_gap_in_cache:
+ * calculate boundaries of the gap that the requested block fits into
+ * and cache this gap
+ */
+static void
+ext4_ext_put_gap_in_cache(struct inode *inode, ext4_lblk_t hole_start,
+			  ext4_lblk_t hole_len)
+{
+	struct extent_status es;
 
-	ext4_es_find_delayed_extent_range(inode, lblock, lblock + len - 1, &es);
+	ext4_es_find_delayed_extent_range(inode, hole_start,
+					  hole_start + hole_len - 1, &es);
 	if (es.es_len) {
 		/* There's delayed extent containing lblock? */
-		if (es.es_lblk <= lblock)
+		if (es.es_lblk <= hole_start)
 			return;
-		len = min(es.es_lblk - lblock, len);
+		hole_len = min(es.es_lblk - hole_start, hole_len);
 	}
-	ext_debug(" -> %u:%u\n", lblock, len);
-	ext4_es_insert_extent(inode, lblock, len, ~0, EXTENT_STATUS_HOLE);
+	ext_debug(" -> %u:%u\n", hole_start, hole_len);
+	ext4_es_insert_extent(inode, hole_start, hole_len, ~0,
+			      EXTENT_STATUS_HOLE);
 }
 
 /*
@@ -3119,19 +3135,11 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
 {
 	ext4_fsblk_t ee_pblock;
 	unsigned int ee_len;
-	int ret;
 
 	ee_len    = ext4_ext_get_actual_len(ex);
 	ee_pblock = ext4_ext_pblock(ex);
-
-	if (ext4_encrypted_inode(inode))
-		return ext4_encrypted_zeroout(inode, ex);
-
-	ret = sb_issue_zeroout(inode->i_sb, ee_pblock, ee_len, GFP_NOFS);
-	if (ret > 0)
-		ret = 0;
-
-	return ret;
+	return ext4_issue_zeroout(inode, le32_to_cpu(ex->ee_block), ee_pblock,
+				  ee_len);
 }
 
 /*
@@ -3935,8 +3943,8 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start,
 static int
 convert_initialized_extent(handle_t *handle, struct inode *inode,
 			   struct ext4_map_blocks *map,
-			   struct ext4_ext_path **ppath, int flags,
-			   unsigned int allocated, ext4_fsblk_t newblock)
+			   struct ext4_ext_path **ppath,
+			   unsigned int allocated)
 {
 	struct ext4_ext_path *path = *ppath;
 	struct ext4_extent *ex;
@@ -4015,7 +4023,6 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
 	struct ext4_ext_path *path = *ppath;
 	int ret = 0;
 	int err = 0;
-	ext4_io_end_t *io = ext4_inode_aio(inode);
 
 	ext_debug("ext4_ext_handle_unwritten_extents: inode %lu, logical "
 		  "block %llu, max_blocks %u, flags %x, allocated %u\n",
@@ -4038,20 +4045,19 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
 					 flags | EXT4_GET_BLOCKS_CONVERT);
 		if (ret <= 0)
 			goto out;
-		/*
-		 * Flag the inode(non aio case) or end_io struct (aio case)
-		 * that this IO needs to conversion to written when IO is
-		 * completed
-		 */
-		if (io)
-			ext4_set_io_unwritten_flag(inode, io);
-		else
-			ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
 		map->m_flags |= EXT4_MAP_UNWRITTEN;
 		goto out;
 	}
 	/* IO end_io complete, convert the filled extent to written */
 	if (flags & EXT4_GET_BLOCKS_CONVERT) {
+		if (flags & EXT4_GET_BLOCKS_ZERO) {
+			if (allocated > map->m_len)
+				allocated = map->m_len;
+			err = ext4_issue_zeroout(inode, map->m_lblk, newblock,
+						 allocated);
+			if (err < 0)
+				goto out2;
+		}
 		ret = ext4_convert_unwritten_extents_endio(handle, inode, map,
 							   ppath);
 		if (ret >= 0) {
@@ -4283,9 +4289,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	unsigned int allocated = 0, offset = 0;
 	unsigned int allocated_clusters = 0;
 	struct ext4_allocation_request ar;
-	ext4_io_end_t *io = ext4_inode_aio(inode);
 	ext4_lblk_t cluster_offset;
-	int set_unwritten = 0;
 	bool map_from_cluster = false;
 
 	ext_debug("blocks %u/%u requested for inode %lu\n",
@@ -4347,7 +4351,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 			    (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) {
 				allocated = convert_initialized_extent(
 						handle, inode, map, &path,
-						flags, allocated, newblock);
+						allocated);
 				goto out2;
 			} else if (!ext4_ext_is_unwritten(ex))
 				goto out;
@@ -4368,11 +4372,22 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	 * we couldn't try to create block if create flag is zero
 	 */
 	if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
+		ext4_lblk_t hole_start, hole_len;
+
+		hole_start = map->m_lblk;
+		hole_len = ext4_ext_determine_hole(inode, path, &hole_start);
 		/*
 		 * put just found gap into cache to speed up
 		 * subsequent requests
 		 */
-		ext4_ext_put_gap_in_cache(inode, path, map->m_lblk);
+		ext4_ext_put_gap_in_cache(inode, hole_start, hole_len);
+
+		/* Update hole_len to reflect hole size after map->m_lblk */
+		if (hole_start != map->m_lblk)
+			hole_len -= map->m_lblk - hole_start;
+		map->m_pblk = 0;
+		map->m_len = min_t(unsigned int, map->m_len, hole_len);
+
 		goto out2;
 	}
 
@@ -4482,15 +4497,6 @@ got_allocated_blocks:
 	if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT){
 		ext4_ext_mark_unwritten(&newex);
 		map->m_flags |= EXT4_MAP_UNWRITTEN;
-		/*
-		 * io_end structure was created for every IO write to an
-		 * unwritten extent. To avoid unnecessary conversion,
-		 * here we flag the IO that really needs the conversion.
-		 * For non asycn direct IO case, flag the inode state
-		 * that we need to perform conversion when IO is done.
-		 */
-		if (flags & EXT4_GET_BLOCKS_PRE_IO)
-			set_unwritten = 1;
 	}
 
 	err = 0;
@@ -4501,14 +4507,6 @@ got_allocated_blocks:
 		err = ext4_ext_insert_extent(handle, inode, &path,
 					     &newex, flags);
 
-	if (!err && set_unwritten) {
-		if (io)
-			ext4_set_io_unwritten_flag(inode, io);
-		else
-			ext4_set_inode_state(inode,
-					     EXT4_STATE_DIO_UNWRITTEN);
-	}
-
 	if (err && free_on_err) {
 		int fb_flags = flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE ?
 			EXT4_FREE_BLOCKS_NO_QUOT_UPDATE : 0;
@@ -4685,10 +4683,6 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
 	if (len <= EXT_UNWRITTEN_MAX_LEN)
 		flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
 
-	/* Wait all existing dio workers, newcomers will block on i_mutex */
-	ext4_inode_block_unlocked_dio(inode);
-	inode_dio_wait(inode);
-
 	/*
 	 * credits to insert 1 extent into extent tree
 	 */
@@ -4752,8 +4746,6 @@ retry:
 		goto retry;
 	}
 
-	ext4_inode_resume_unlocked_dio(inode);
-
 	return ret > 0 ? ret2 : ret;
 }
 
@@ -4770,7 +4762,6 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	int partial_begin, partial_end;
 	loff_t start, end;
 	ext4_lblk_t lblk;
-	struct address_space *mapping = inode->i_mapping;
 	unsigned int blkbits = inode->i_blkbits;
 
 	trace_ext4_zero_range(inode, offset, len, mode);
@@ -4786,17 +4777,6 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	}
 
 	/*
-	 * Write out all dirty pages to avoid race conditions
-	 * Then release them.
-	 */
-	if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
-		ret = filemap_write_and_wait_range(mapping, offset,
-						   offset + len - 1);
-		if (ret)
-			return ret;
-	}
-
-	/*
 	 * Round up offset. This is not fallocate, we neet to zero out
 	 * blocks, so convert interior block aligned part of the range to
 	 * unwritten and possibly manually zero out unaligned parts of the
@@ -4817,7 +4797,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	else
 		max_blocks -= lblk;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	/*
 	 * Indirect files do not support unwritten extnets
@@ -4839,6 +4819,10 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	if (mode & FALLOC_FL_KEEP_SIZE)
 		flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
 
+	/* Wait all existing dio workers, newcomers will block on i_mutex */
+	ext4_inode_block_unlocked_dio(inode);
+	inode_dio_wait(inode);
+
 	/* Preallocate the range including the unaligned edges */
 	if (partial_begin || partial_end) {
 		ret = ext4_alloc_file_blocks(file,
@@ -4847,7 +4831,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 				 round_down(offset, 1 << blkbits)) >> blkbits,
 				new_size, flags, mode);
 		if (ret)
-			goto out_mutex;
+			goto out_dio;
 
 	}
 
@@ -4856,16 +4840,23 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN |
 			  EXT4_EX_NOCACHE);
 
-		/* Now release the pages and zero block aligned part of pages*/
+		/*
+		 * Prevent page faults from reinstantiating pages we have
+		 * released from page cache.
+		 */
+		down_write(&EXT4_I(inode)->i_mmap_sem);
+		ret = ext4_update_disksize_before_punch(inode, offset, len);
+		if (ret) {
+			up_write(&EXT4_I(inode)->i_mmap_sem);
+			goto out_dio;
+		}
+		/* Now release the pages and zero block aligned part of pages */
 		truncate_pagecache_range(inode, start, end - 1);
 		inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
 
-		/* Wait all existing dio workers, newcomers will block on i_mutex */
-		ext4_inode_block_unlocked_dio(inode);
-		inode_dio_wait(inode);
-
 		ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
 					     flags, mode);
+		up_write(&EXT4_I(inode)->i_mmap_sem);
 		if (ret)
 			goto out_dio;
 	}
@@ -4909,7 +4900,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 out_dio:
 	ext4_inode_resume_unlocked_dio(inode);
 out_mutex:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return ret;
 }
 
@@ -4980,7 +4971,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	if (mode & FALLOC_FL_KEEP_SIZE)
 		flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	/*
 	 * We only support preallocation for extent-based files only
@@ -4998,8 +4989,13 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 			goto out;
 	}
 
+	/* Wait all existing dio workers, newcomers will block on i_mutex */
+	ext4_inode_block_unlocked_dio(inode);
+	inode_dio_wait(inode);
+
 	ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
 				     flags, mode);
+	ext4_inode_resume_unlocked_dio(inode);
 	if (ret)
 		goto out;
 
@@ -5008,7 +5004,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 						EXT4_I(inode)->i_sync_tid);
 	}
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
 	return ret;
 }
@@ -5494,21 +5490,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 			return ret;
 	}
 
-	/*
-	 * Need to round down offset to be aligned with page size boundary
-	 * for page size > block size.
-	 */
-	ioffset = round_down(offset, PAGE_SIZE);
-
-	/* Write out all dirty pages */
-	ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
-					   LLONG_MAX);
-	if (ret)
-		return ret;
-
-	/* Take mutex lock */
-	mutex_lock(&inode->i_mutex);
-
+	inode_lock(inode);
 	/*
 	 * There is no need to overlap collapse range with EOF, in which case
 	 * it is effectively a truncate operation
@@ -5524,17 +5506,43 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 		goto out_mutex;
 	}
 
-	truncate_pagecache(inode, ioffset);
-
 	/* Wait for existing dio to complete */
 	ext4_inode_block_unlocked_dio(inode);
 	inode_dio_wait(inode);
 
+	/*
+	 * Prevent page faults from reinstantiating pages we have released from
+	 * page cache.
+	 */
+	down_write(&EXT4_I(inode)->i_mmap_sem);
+	/*
+	 * Need to round down offset to be aligned with page size boundary
+	 * for page size > block size.
+	 */
+	ioffset = round_down(offset, PAGE_SIZE);
+	/*
+	 * Write tail of the last page before removed range since it will get
+	 * removed from the page cache below.
+	 */
+	ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, offset);
+	if (ret)
+		goto out_mmap;
+	/*
+	 * Write data that will be shifted to preserve them when discarding
+	 * page cache below. We are also protected from pages becoming dirty
+	 * by i_mmap_sem.
+	 */
+	ret = filemap_write_and_wait_range(inode->i_mapping, offset + len,
+					   LLONG_MAX);
+	if (ret)
+		goto out_mmap;
+	truncate_pagecache(inode, ioffset);
+
 	credits = ext4_writepage_trans_blocks(inode);
 	handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
 	if (IS_ERR(handle)) {
 		ret = PTR_ERR(handle);
-		goto out_dio;
+		goto out_mmap;
 	}
 
 	down_write(&EXT4_I(inode)->i_data_sem);
@@ -5573,10 +5581,11 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 
 out_stop:
 	ext4_journal_stop(handle);
-out_dio:
+out_mmap:
+	up_write(&EXT4_I(inode)->i_mmap_sem);
 	ext4_inode_resume_unlocked_dio(inode);
 out_mutex:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return ret;
 }
 
@@ -5627,21 +5636,7 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 			return ret;
 	}
 
-	/*
-	 * Need to round down to align start offset to page size boundary
-	 * for page size > block size.
-	 */
-	ioffset = round_down(offset, PAGE_SIZE);
-
-	/* Write out all dirty pages */
-	ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
-			LLONG_MAX);
-	if (ret)
-		return ret;
-
-	/* Take mutex lock */
-	mutex_lock(&inode->i_mutex);
-
+	inode_lock(inode);
 	/* Currently just for extent based files */
 	if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
 		ret = -EOPNOTSUPP;
@@ -5660,17 +5655,32 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 		goto out_mutex;
 	}
 
-	truncate_pagecache(inode, ioffset);
-
 	/* Wait for existing dio to complete */
 	ext4_inode_block_unlocked_dio(inode);
 	inode_dio_wait(inode);
 
+	/*
+	 * Prevent page faults from reinstantiating pages we have released from
+	 * page cache.
+	 */
+	down_write(&EXT4_I(inode)->i_mmap_sem);
+	/*
+	 * Need to round down to align start offset to page size boundary
+	 * for page size > block size.
+	 */
+	ioffset = round_down(offset, PAGE_SIZE);
+	/* Write out all dirty pages */
+	ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
+			LLONG_MAX);
+	if (ret)
+		goto out_mmap;
+	truncate_pagecache(inode, ioffset);
+
 	credits = ext4_writepage_trans_blocks(inode);
 	handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
 	if (IS_ERR(handle)) {
 		ret = PTR_ERR(handle);
-		goto out_dio;
+		goto out_mmap;
 	}
 
 	/* Expand file to avoid data loss if there is error while shifting */
@@ -5741,10 +5751,11 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 
 out_stop:
 	ext4_journal_stop(handle);
-out_dio:
+out_mmap:
+	up_write(&EXT4_I(inode)->i_mmap_sem);
 	ext4_inode_resume_unlocked_dio(inode);
 out_mutex:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return ret;
 }
 
@@ -5779,8 +5790,8 @@ ext4_swap_extents(handle_t *handle, struct inode *inode1,
 
 	BUG_ON(!rwsem_is_locked(&EXT4_I(inode1)->i_data_sem));
 	BUG_ON(!rwsem_is_locked(&EXT4_I(inode2)->i_data_sem));
-	BUG_ON(!mutex_is_locked(&inode1->i_mutex));
-	BUG_ON(!mutex_is_locked(&inode2->i_mutex));
+	BUG_ON(!inode_is_locked(inode1));
+	BUG_ON(!inode_is_locked(inode2));
 
 	*erp = ext4_es_remove_extent(inode1, lblk1, count);
 	if (unlikely(*erp))
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index ac748b3af1c1..e38b987ac7f5 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -823,8 +823,8 @@ out:
 		es->es_lblk = es1->es_lblk;
 		es->es_len = es1->es_len;
 		es->es_pblk = es1->es_pblk;
-		if (!ext4_es_is_referenced(es))
-			ext4_es_set_referenced(es);
+		if (!ext4_es_is_referenced(es1))
+			ext4_es_set_referenced(es1);
 		stats->es_stats_cache_hits++;
 	} else {
 		stats->es_stats_cache_misses++;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 113837e7ba98..fa2208bae2e1 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -93,31 +93,29 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(iocb->ki_filp);
-	struct mutex *aio_mutex = NULL;
 	struct blk_plug plug;
 	int o_direct = iocb->ki_flags & IOCB_DIRECT;
+	int unaligned_aio = 0;
 	int overwrite = 0;
 	ssize_t ret;
 
+	inode_lock(inode);
+	ret = generic_write_checks(iocb, from);
+	if (ret <= 0)
+		goto out;
+
 	/*
-	 * Unaligned direct AIO must be serialized; see comment above
-	 * In the case of O_APPEND, assume that we must always serialize
+	 * Unaligned direct AIO must be serialized among each other as zeroing
+	 * of partial blocks of two competing unaligned AIOs can result in data
+	 * corruption.
 	 */
-	if (o_direct &&
-	    ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
+	if (o_direct && ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
 	    !is_sync_kiocb(iocb) &&
-	    (iocb->ki_flags & IOCB_APPEND ||
-	     ext4_unaligned_aio(inode, from, iocb->ki_pos))) {
-		aio_mutex = ext4_aio_mutex(inode);
-		mutex_lock(aio_mutex);
+	    ext4_unaligned_aio(inode, from, iocb->ki_pos)) {
+		unaligned_aio = 1;
 		ext4_unwritten_wait(inode);
 	}
 
-	mutex_lock(&inode->i_mutex);
-	ret = generic_write_checks(iocb, from);
-	if (ret <= 0)
-		goto out;
-
 	/*
 	 * If we have encountered a bitmap-format file, the size limit
 	 * is smaller than s_maxbytes, which is for extent-mapped files.
@@ -139,7 +137,7 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		blk_start_plug(&plug);
 
 		/* check whether we do a DIO overwrite or not */
-		if (ext4_should_dioread_nolock(inode) && !aio_mutex &&
+		if (ext4_should_dioread_nolock(inode) && !unaligned_aio &&
 		    !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
 			struct ext4_map_blocks map;
 			unsigned int blkbits = inode->i_blkbits;
@@ -169,7 +167,7 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	}
 
 	ret = __generic_file_write_iter(iocb, from);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	if (ret > 0) {
 		ssize_t err;
@@ -181,55 +179,43 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (o_direct)
 		blk_finish_plug(&plug);
 
-	if (aio_mutex)
-		mutex_unlock(aio_mutex);
 	return ret;
 
 out:
-	mutex_unlock(&inode->i_mutex);
-	if (aio_mutex)
-		mutex_unlock(aio_mutex);
+	inode_unlock(inode);
 	return ret;
 }
 
 #ifdef CONFIG_FS_DAX
-static void ext4_end_io_unwritten(struct buffer_head *bh, int uptodate)
-{
-	struct inode *inode = bh->b_assoc_map->host;
-	/* XXX: breaks on 32-bit > 16TB. Is that even supported? */
-	loff_t offset = (loff_t)(uintptr_t)bh->b_private << inode->i_blkbits;
-	int err;
-	if (!uptodate)
-		return;
-	WARN_ON(!buffer_unwritten(bh));
-	err = ext4_convert_unwritten_extents(NULL, inode, offset, bh->b_size);
-}
-
 static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	int result;
 	handle_t *handle = NULL;
-	struct super_block *sb = file_inode(vma->vm_file)->i_sb;
+	struct inode *inode = file_inode(vma->vm_file);
+	struct super_block *sb = inode->i_sb;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
 
 	if (write) {
 		sb_start_pagefault(sb);
 		file_update_time(vma->vm_file);
+		down_read(&EXT4_I(inode)->i_mmap_sem);
 		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
 						EXT4_DATA_TRANS_BLOCKS(sb));
-	}
+	} else
+		down_read(&EXT4_I(inode)->i_mmap_sem);
 
 	if (IS_ERR(handle))
 		result = VM_FAULT_SIGBUS;
 	else
-		result = __dax_fault(vma, vmf, ext4_get_block_dax,
-						ext4_end_io_unwritten);
+		result = __dax_fault(vma, vmf, ext4_dax_mmap_get_block, NULL);
 
 	if (write) {
 		if (!IS_ERR(handle))
 			ext4_journal_stop(handle);
+		up_read(&EXT4_I(inode)->i_mmap_sem);
 		sb_end_pagefault(sb);
-	}
+	} else
+		up_read(&EXT4_I(inode)->i_mmap_sem);
 
 	return result;
 }
@@ -246,44 +232,73 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	if (write) {
 		sb_start_pagefault(sb);
 		file_update_time(vma->vm_file);
+		down_read(&EXT4_I(inode)->i_mmap_sem);
 		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
 				ext4_chunk_trans_blocks(inode,
 							PMD_SIZE / PAGE_SIZE));
-	}
+	} else
+		down_read(&EXT4_I(inode)->i_mmap_sem);
 
 	if (IS_ERR(handle))
 		result = VM_FAULT_SIGBUS;
 	else
 		result = __dax_pmd_fault(vma, addr, pmd, flags,
-				ext4_get_block_dax, ext4_end_io_unwritten);
+				ext4_dax_mmap_get_block, NULL);
 
 	if (write) {
 		if (!IS_ERR(handle))
 			ext4_journal_stop(handle);
+		up_read(&EXT4_I(inode)->i_mmap_sem);
 		sb_end_pagefault(sb);
-	}
+	} else
+		up_read(&EXT4_I(inode)->i_mmap_sem);
 
 	return result;
 }
 
-static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+/*
+ * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_fault()
+ * handler we check for races agaist truncate. Note that since we cycle through
+ * i_mmap_sem, we are sure that also any hole punching that began before we
+ * were called is finished by now and so if it included part of the file we
+ * are working on, our pte will get unmapped and the check for pte_same() in
+ * wp_pfn_shared() fails. Thus fault gets retried and things work out as
+ * desired.
+ */
+static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma,
+				struct vm_fault *vmf)
 {
-	return dax_mkwrite(vma, vmf, ext4_get_block_dax,
-				ext4_end_io_unwritten);
+	struct inode *inode = file_inode(vma->vm_file);
+	struct super_block *sb = inode->i_sb;
+	loff_t size;
+	int ret;
+
+	sb_start_pagefault(sb);
+	file_update_time(vma->vm_file);
+	down_read(&EXT4_I(inode)->i_mmap_sem);
+	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (vmf->pgoff >= size)
+		ret = VM_FAULT_SIGBUS;
+	else
+		ret = dax_pfn_mkwrite(vma, vmf);
+	up_read(&EXT4_I(inode)->i_mmap_sem);
+	sb_end_pagefault(sb);
+
+	return ret;
 }
 
 static const struct vm_operations_struct ext4_dax_vm_ops = {
 	.fault		= ext4_dax_fault,
 	.pmd_fault	= ext4_dax_pmd_fault,
-	.page_mkwrite	= ext4_dax_mkwrite,
-	.pfn_mkwrite	= dax_pfn_mkwrite,
+	.page_mkwrite	= ext4_dax_fault,
+	.pfn_mkwrite	= ext4_dax_pfn_mkwrite,
 };
 #else
 #define ext4_dax_vm_ops	ext4_file_vm_ops
 #endif
 
 static const struct vm_operations_struct ext4_file_vm_ops = {
-	.fault		= filemap_fault,
+	.fault		= ext4_filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite   = ext4_page_mkwrite,
 };
@@ -314,6 +329,7 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 	struct super_block *sb = inode->i_sb;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct vfsmount *mnt = filp->f_path.mnt;
+	struct dentry *dir;
 	struct path path;
 	char buf[64], *cp;
 	int ret;
@@ -357,6 +373,18 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 		if (ext4_encryption_info(inode) == NULL)
 			return -ENOKEY;
 	}
+
+	dir = dget_parent(file_dentry(filp));
+	if (ext4_encrypted_inode(d_inode(dir)) &&
+	    !ext4_is_child_context_consistent_with_parent(d_inode(dir), inode)) {
+		ext4_warning(inode->i_sb,
+			     "Inconsistent encryption contexts: %lu/%lu\n",
+			     (unsigned long) d_inode(dir)->i_ino,
+			     (unsigned long) inode->i_ino);
+		dput(dir);
+		return -EPERM;
+	}
+	dput(dir);
 	/*
 	 * Set up the jbd2_inode if we are opening the inode for
 	 * writing and the journal is present
@@ -387,7 +415,7 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
  */
 static int ext4_find_unwritten_pgoff(struct inode *inode,
 				     int whence,
-				     struct ext4_map_blocks *map,
+				     ext4_lblk_t end_blk,
 				     loff_t *offset)
 {
 	struct pagevec pvec;
@@ -402,10 +430,10 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 	blkbits = inode->i_sb->s_blocksize_bits;
 	startoff = *offset;
 	lastoff = startoff;
-	endoff = (loff_t)(map->m_lblk + map->m_len) << blkbits;
+	endoff = (loff_t)end_blk << blkbits;
 
-	index = startoff >> PAGE_CACHE_SHIFT;
-	end = endoff >> PAGE_CACHE_SHIFT;
+	index = startoff >> PAGE_SHIFT;
+	end = endoff >> PAGE_SHIFT;
 
 	pagevec_init(&pvec, 0);
 	do {
@@ -520,18 +548,17 @@ out:
 static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize)
 {
 	struct inode *inode = file->f_mapping->host;
-	struct ext4_map_blocks map;
 	struct extent_status es;
 	ext4_lblk_t start, last, end;
 	loff_t dataoff, isize;
 	int blkbits;
-	int ret = 0;
+	int ret;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	isize = i_size_read(inode);
 	if (offset >= isize) {
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 		return -ENXIO;
 	}
 
@@ -542,44 +569,35 @@ static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize)
 	dataoff = offset;
 
 	do {
-		map.m_lblk = last;
-		map.m_len = end - last + 1;
-		ret = ext4_map_blocks(NULL, inode, &map, 0);
-		if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) {
-			if (last != start)
-				dataoff = (loff_t)last << blkbits;
-			break;
+		ret = ext4_get_next_extent(inode, last, end - last + 1, &es);
+		if (ret <= 0) {
+			/* No extent found -> no data */
+			if (ret == 0)
+				ret = -ENXIO;
+			inode_unlock(inode);
+			return ret;
 		}
 
-		/*
-		 * If there is a delay extent at this offset,
-		 * it will be as a data.
-		 */
-		ext4_es_find_delayed_extent_range(inode, last, last, &es);
-		if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) {
-			if (last != start)
-				dataoff = (loff_t)last << blkbits;
+		last = es.es_lblk;
+		if (last != start)
+			dataoff = (loff_t)last << blkbits;
+		if (!ext4_es_is_unwritten(&es))
 			break;
-		}
 
 		/*
 		 * If there is a unwritten extent at this offset,
 		 * it will be as a data or a hole according to page
 		 * cache that has data or not.
 		 */
-		if (map.m_flags & EXT4_MAP_UNWRITTEN) {
-			int unwritten;
-			unwritten = ext4_find_unwritten_pgoff(inode, SEEK_DATA,
-							      &map, &dataoff);
-			if (unwritten)
-				break;
-		}
-
-		last++;
+		if (ext4_find_unwritten_pgoff(inode, SEEK_DATA,
+					      es.es_lblk + es.es_len, &dataoff))
+			break;
+		last += es.es_len;
 		dataoff = (loff_t)last << blkbits;
+		cond_resched();
 	} while (last <= end);
 
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	if (dataoff > isize)
 		return -ENXIO;
@@ -593,18 +611,17 @@ static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize)
 static loff_t ext4_seek_hole(struct file *file, loff_t offset, loff_t maxsize)
 {
 	struct inode *inode = file->f_mapping->host;
-	struct ext4_map_blocks map;
 	struct extent_status es;
 	ext4_lblk_t start, last, end;
 	loff_t holeoff, isize;
 	int blkbits;
-	int ret = 0;
+	int ret;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	isize = i_size_read(inode);
 	if (offset >= isize) {
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 		return -ENXIO;
 	}
 
@@ -615,47 +632,33 @@ static loff_t ext4_seek_hole(struct file *file, loff_t offset, loff_t maxsize)
 	holeoff = offset;
 
 	do {
-		map.m_lblk = last;
-		map.m_len = end - last + 1;
-		ret = ext4_map_blocks(NULL, inode, &map, 0);
-		if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) {
-			last += ret;
-			holeoff = (loff_t)last << blkbits;
-			continue;
+		ret = ext4_get_next_extent(inode, last, end - last + 1, &es);
+		if (ret < 0) {
+			inode_unlock(inode);
+			return ret;
 		}
-
-		/*
-		 * If there is a delay extent at this offset,
-		 * we will skip this extent.
-		 */
-		ext4_es_find_delayed_extent_range(inode, last, last, &es);
-		if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) {
-			last = es.es_lblk + es.es_len;
-			holeoff = (loff_t)last << blkbits;
-			continue;
+		/* Found a hole? */
+		if (ret == 0 || es.es_lblk > last) {
+			if (last != start)
+				holeoff = (loff_t)last << blkbits;
+			break;
 		}
-
 		/*
 		 * If there is a unwritten extent at this offset,
 		 * it will be as a data or a hole according to page
 		 * cache that has data or not.
 		 */
-		if (map.m_flags & EXT4_MAP_UNWRITTEN) {
-			int unwritten;
-			unwritten = ext4_find_unwritten_pgoff(inode, SEEK_HOLE,
-							      &map, &holeoff);
-			if (!unwritten) {
-				last += ret;
-				holeoff = (loff_t)last << blkbits;
-				continue;
-			}
-		}
+		if (ext4_es_is_unwritten(&es) &&
+		    ext4_find_unwritten_pgoff(inode, SEEK_HOLE,
+					      last + es.es_len, &holeoff))
+			break;
 
-		/* find a hole */
-		break;
+		last += es.es_len;
+		holeoff = (loff_t)last << blkbits;
+		cond_resched();
 	} while (last <= end);
 
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	if (holeoff > isize)
 		holeoff = isize;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 1b8024d26f65..237b877d316d 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -76,7 +76,6 @@ static int ext4_init_inode_bitmap(struct super_block *sb,
 	/* If checksum is bad mark all blocks and inodes use to prevent
 	 * allocation, essentially implementing a per-group read-only flag. */
 	if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
-		ext4_error(sb, "Checksum bad for group %u", block_group);
 		grp = ext4_get_group_info(sb, block_group);
 		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
 			percpu_counter_sub(&sbi->s_freeclusters_counter,
@@ -191,8 +190,11 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 		set_buffer_verified(bh);
 		ext4_unlock_group(sb, block_group);
 		unlock_buffer(bh);
-		if (err)
+		if (err) {
+			ext4_error(sb, "Failed to init inode bitmap for group "
+				   "%u: %d", block_group, err);
 			goto out;
+		}
 		return bh;
 	}
 	ext4_unlock_group(sb, block_group);
@@ -785,7 +787,7 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 	sbi = EXT4_SB(sb);
 
 	/*
-	 * Initalize owners and quota early so that we don't have to account
+	 * Initialize owners and quota early so that we don't have to account
 	 * for quota initialization worst case in standard inode creating
 	 * transaction
 	 */
@@ -799,6 +801,13 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 		inode->i_gid = dir->i_gid;
 	} else
 		inode_init_owner(inode, dir, mode);
+
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_PROJECT) &&
+	    ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT))
+		ei->i_projid = EXT4_I(dir)->i_projid;
+	else
+		ei->i_projid = make_kprojid(&init_user_ns, EXT4_DEF_PROJID);
+
 	err = dquot_initialize(inode);
 	if (err)
 		goto out;
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 355ef9c36c87..3027fa681de5 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -555,8 +555,23 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
 		goto got_it;
 	}
 
-	/* Next simple case - plain lookup or failed read of indirect block */
-	if ((flags & EXT4_GET_BLOCKS_CREATE) == 0 || err == -EIO)
+	/* Next simple case - plain lookup failed */
+	if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
+		unsigned epb = inode->i_sb->s_blocksize / sizeof(u32);
+		int i;
+
+		/* Count number blocks in a subtree under 'partial' */
+		count = 1;
+		for (i = 0; partial + i != chain + depth - 1; i++)
+			count *= epb;
+		/* Fill in size of a hole we found */
+		map->m_pblk = 0;
+		map->m_len = min_t(unsigned int, map->m_len, count);
+		goto cleanup;
+	}
+
+	/* Failed read of indirect block */
+	if (err == -EIO)
 		goto cleanup;
 
 	/*
@@ -693,21 +708,21 @@ retry:
 		}
 		if (IS_DAX(inode))
 			ret = dax_do_io(iocb, inode, iter, offset,
-					ext4_get_block, NULL, 0);
+					ext4_dio_get_block, NULL, 0);
 		else
 			ret = __blockdev_direct_IO(iocb, inode,
 						   inode->i_sb->s_bdev, iter,
-						   offset, ext4_get_block, NULL,
-						   NULL, 0);
+						   offset, ext4_dio_get_block,
+						   NULL, NULL, 0);
 		inode_dio_end(inode);
 	} else {
 locked:
 		if (IS_DAX(inode))
 			ret = dax_do_io(iocb, inode, iter, offset,
-					ext4_get_block, NULL, DIO_LOCKING);
+					ext4_dio_get_block, NULL, DIO_LOCKING);
 		else
 			ret = blockdev_direct_IO(iocb, inode, iter, offset,
-						 ext4_get_block);
+						 ext4_dio_get_block);
 
 		if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) {
 			loff_t isize = i_size_read(inode);
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index d884989cc83d..7bc6c855cc18 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -482,7 +482,7 @@ static int ext4_read_inline_page(struct inode *inode, struct page *page)
 	ret = ext4_read_inline_data(inode, kaddr, len, &iloc);
 	flush_dcache_page(page);
 	kunmap_atomic(kaddr);
-	zero_user_segment(page, len, PAGE_CACHE_SIZE);
+	zero_user_segment(page, len, PAGE_SIZE);
 	SetPageUptodate(page);
 	brelse(iloc.bh);
 
@@ -507,7 +507,7 @@ int ext4_readpage_inline(struct inode *inode, struct page *page)
 	if (!page->index)
 		ret = ext4_read_inline_page(inode, page);
 	else if (!PageUptodate(page)) {
-		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+		zero_user_segment(page, 0, PAGE_SIZE);
 		SetPageUptodate(page);
 	}
 
@@ -581,9 +581,10 @@ retry:
 	if (ret)
 		goto out;
 
-	if (ext4_should_dioread_nolock(inode))
-		ret = __block_write_begin(page, from, to, ext4_get_block_write);
-	else
+	if (ext4_should_dioread_nolock(inode)) {
+		ret = __block_write_begin(page, from, to,
+					  ext4_get_block_unwritten);
+	} else
 		ret = __block_write_begin(page, from, to, ext4_get_block);
 
 	if (!ret && ext4_should_journal_data(inode)) {
@@ -594,7 +595,7 @@ retry:
 
 	if (ret) {
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 		page = NULL;
 		ext4_orphan_add(handle, inode);
 		up_write(&EXT4_I(inode)->xattr_sem);
@@ -620,7 +621,7 @@ retry:
 out:
 	if (page) {
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 	}
 	if (sem_held)
 		up_write(&EXT4_I(inode)->xattr_sem);
@@ -689,7 +690,7 @@ int ext4_try_to_write_inline_data(struct address_space *mapping,
 	if (!ext4_has_inline_data(inode)) {
 		ret = 0;
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 		goto out_up_read;
 	}
 
@@ -814,7 +815,7 @@ static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping,
 	if (ret) {
 		up_read(&EXT4_I(inode)->xattr_sem);
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 		ext4_truncate_failed_write(inode);
 		return ret;
 	}
@@ -828,7 +829,7 @@ out:
 	up_read(&EXT4_I(inode)->xattr_sem);
 	if (page) {
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 	}
 	return ret;
 }
@@ -918,7 +919,7 @@ retry_journal:
 out_release_page:
 	up_read(&EXT4_I(inode)->xattr_sem);
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 out_journal:
 	ext4_journal_stop(handle);
 out:
@@ -946,7 +947,7 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
 		i_size_changed = 1;
 	}
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 
 	/*
 	 * Don't mark the inode dirty under page lock. First, it unnecessarily
@@ -995,12 +996,11 @@ void ext4_show_inline_dir(struct inode *dir, struct buffer_head *bh,
  */
 static int ext4_add_dirent_to_inline(handle_t *handle,
 				     struct ext4_filename *fname,
-				     struct dentry *dentry,
+				     struct inode *dir,
 				     struct inode *inode,
 				     struct ext4_iloc *iloc,
 				     void *inline_start, int inline_size)
 {
-	struct inode	*dir = d_inode(dentry->d_parent);
 	int		err;
 	struct ext4_dir_entry_2 *de;
 
@@ -1245,12 +1245,11 @@ out:
  * the new created block.
  */
 int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname,
-			      struct dentry *dentry, struct inode *inode)
+			      struct inode *dir, struct inode *inode)
 {
 	int ret, inline_size;
 	void *inline_start;
 	struct ext4_iloc iloc;
-	struct inode *dir = d_inode(dentry->d_parent);
 
 	ret = ext4_get_inode_loc(dir, &iloc);
 	if (ret)
@@ -1264,7 +1263,7 @@ int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname,
 						 EXT4_INLINE_DOTDOT_SIZE;
 	inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE;
 
-	ret = ext4_add_dirent_to_inline(handle, fname, dentry, inode, &iloc,
+	ret = ext4_add_dirent_to_inline(handle, fname, dir, inode, &iloc,
 					inline_start, inline_size);
 	if (ret != -ENOSPC)
 		goto out;
@@ -1285,7 +1284,7 @@ int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname,
 	if (inline_size) {
 		inline_start = ext4_get_inline_xattr_pos(dir, &iloc);
 
-		ret = ext4_add_dirent_to_inline(handle, fname, dentry,
+		ret = ext4_add_dirent_to_inline(handle, fname, dir,
 						inode, &iloc, inline_start,
 						inline_size);
 
@@ -1698,7 +1697,6 @@ int ext4_delete_inline_entry(handle_t *handle,
 	if (err)
 		goto out;
 
-	BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
 	err = ext4_mark_inode_dirty(handle, dir);
 	if (unlikely(err))
 		goto out;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index e8d620a484f6..981a1fc30eaa 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -216,7 +216,6 @@ void ext4_evict_inode(struct inode *inode)
 		}
 		truncate_inode_pages_final(&inode->i_data);
 
-		WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count));
 		goto no_delete;
 	}
 
@@ -228,8 +227,6 @@ void ext4_evict_inode(struct inode *inode)
 		ext4_begin_ordered_truncate(inode, 0);
 	truncate_inode_pages_final(&inode->i_data);
 
-	WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count));
-
 	/*
 	 * Protect us against freezing - iput() caller didn't have to have any
 	 * protection against it
@@ -383,6 +380,21 @@ static int __check_block_validity(struct inode *inode, const char *func,
 	return 0;
 }
 
+int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk,
+		       ext4_lblk_t len)
+{
+	int ret;
+
+	if (ext4_encrypted_inode(inode))
+		return ext4_encrypted_zeroout(inode, lblk, pblk, len);
+
+	ret = sb_issue_zeroout(inode->i_sb, pblk, len, GFP_NOFS);
+	if (ret > 0)
+		ret = 0;
+
+	return ret;
+}
+
 #define check_block_validity(inode, map)	\
 	__check_block_validity((inode), __func__, __LINE__, (map))
 
@@ -403,8 +415,7 @@ static void ext4_map_blocks_es_recheck(handle_t *handle,
 	 * out taking i_data_sem.  So at the time the unwritten extent
 	 * could be converted.
 	 */
-	if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
-		down_read(&EXT4_I(inode)->i_data_sem);
+	down_read(&EXT4_I(inode)->i_data_sem);
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
 		retval = ext4_ext_map_blocks(handle, inode, map, flags &
 					     EXT4_GET_BLOCKS_KEEP_SIZE);
@@ -412,8 +423,7 @@ static void ext4_map_blocks_es_recheck(handle_t *handle,
 		retval = ext4_ind_map_blocks(handle, inode, map, flags &
 					     EXT4_GET_BLOCKS_KEEP_SIZE);
 	}
-	if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
-		up_read((&EXT4_I(inode)->i_data_sem));
+	up_read((&EXT4_I(inode)->i_data_sem));
 
 	/*
 	 * We don't check m_len because extent will be collpased in status
@@ -445,13 +455,13 @@ static void ext4_map_blocks_es_recheck(handle_t *handle,
  * Otherwise, call with ext4_ind_map_blocks() to handle indirect mapping
  * based files
  *
- * On success, it returns the number of blocks being mapped or allocated.
- * if create==0 and the blocks are pre-allocated and unwritten block,
- * the result buffer head is unmapped. If the create ==1, it will make sure
- * the buffer head is mapped.
+ * On success, it returns the number of blocks being mapped or allocated.  if
+ * create==0 and the blocks are pre-allocated and unwritten, the resulting @map
+ * is marked as unwritten. If the create == 1, it will mark @map as mapped.
  *
  * It returns 0 if plain look up failed (blocks have not been allocated), in
- * that case, buffer head is unmapped
+ * that case, @map is returned as unmapped but we still do fill map->m_len to
+ * indicate the length of a hole starting at map->m_lblk.
  *
  * It returns the error in case of allocation failure.
  */
@@ -494,6 +504,11 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 				retval = map->m_len;
 			map->m_len = retval;
 		} else if (ext4_es_is_delayed(&es) || ext4_es_is_hole(&es)) {
+			map->m_pblk = 0;
+			retval = es.es_len - (map->m_lblk - es.es_lblk);
+			if (retval > map->m_len)
+				retval = map->m_len;
+			map->m_len = retval;
 			retval = 0;
 		} else {
 			BUG_ON(1);
@@ -509,8 +524,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 	 * Try to see if we can get the block without requesting a new
 	 * file system block.
 	 */
-	if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
-		down_read(&EXT4_I(inode)->i_data_sem);
+	down_read(&EXT4_I(inode)->i_data_sem);
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
 		retval = ext4_ext_map_blocks(handle, inode, map, flags &
 					     EXT4_GET_BLOCKS_KEEP_SIZE);
@@ -541,8 +555,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 		if (ret < 0)
 			retval = ret;
 	}
-	if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
-		up_read((&EXT4_I(inode)->i_data_sem));
+	up_read((&EXT4_I(inode)->i_data_sem));
 
 found:
 	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
@@ -626,13 +639,29 @@ found:
 		}
 
 		/*
+		 * We have to zeroout blocks before inserting them into extent
+		 * status tree. Otherwise someone could look them up there and
+		 * use them before they are really zeroed.
+		 */
+		if (flags & EXT4_GET_BLOCKS_ZERO &&
+		    map->m_flags & EXT4_MAP_MAPPED &&
+		    map->m_flags & EXT4_MAP_NEW) {
+			ret = ext4_issue_zeroout(inode, map->m_lblk,
+						 map->m_pblk, map->m_len);
+			if (ret) {
+				retval = ret;
+				goto out_sem;
+			}
+		}
+
+		/*
 		 * If the extent has been zeroed out, we don't need to update
 		 * extent status tree.
 		 */
 		if ((flags & EXT4_GET_BLOCKS_PRE_IO) &&
 		    ext4_es_lookup_extent(inode, map->m_lblk, &es)) {
 			if (ext4_es_is_written(&es))
-				goto has_zeroout;
+				goto out_sem;
 		}
 		status = map->m_flags & EXT4_MAP_UNWRITTEN ?
 				EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
@@ -643,11 +672,13 @@ found:
 			status |= EXTENT_STATUS_DELAYED;
 		ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
 					    map->m_pblk, status);
-		if (ret < 0)
+		if (ret < 0) {
 			retval = ret;
+			goto out_sem;
+		}
 	}
 
-has_zeroout:
+out_sem:
 	up_write((&EXT4_I(inode)->i_data_sem));
 	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
 		ret = check_block_validity(inode, map);
@@ -657,16 +688,39 @@ has_zeroout:
 	return retval;
 }
 
-/* Maximum number of blocks we map for direct IO at once. */
-#define DIO_MAX_BLOCKS 4096
+/*
+ * Update EXT4_MAP_FLAGS in bh->b_state. For buffer heads attached to pages
+ * we have to be careful as someone else may be manipulating b_state as well.
+ */
+static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags)
+{
+	unsigned long old_state;
+	unsigned long new_state;
+
+	flags &= EXT4_MAP_FLAGS;
+
+	/* Dummy buffer_head? Set non-atomically. */
+	if (!bh->b_page) {
+		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | flags;
+		return;
+	}
+	/*
+	 * Someone else may be modifying b_state. Be careful! This is ugly but
+	 * once we get rid of using bh as a container for mapping information
+	 * to pass to / from get_block functions, this can go away.
+	 */
+	do {
+		old_state = READ_ONCE(bh->b_state);
+		new_state = (old_state & ~EXT4_MAP_FLAGS) | flags;
+	} while (unlikely(
+		 cmpxchg(&bh->b_state, old_state, new_state) != old_state));
+}
 
 static int _ext4_get_block(struct inode *inode, sector_t iblock,
 			   struct buffer_head *bh, int flags)
 {
-	handle_t *handle = ext4_journal_current_handle();
 	struct ext4_map_blocks map;
-	int ret = 0, started = 0;
-	int dio_credits;
+	int ret = 0;
 
 	if (ext4_has_inline_data(inode))
 		return -ERANGE;
@@ -674,43 +728,14 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
 	map.m_lblk = iblock;
 	map.m_len = bh->b_size >> inode->i_blkbits;
 
-	if (flags && !(flags & EXT4_GET_BLOCKS_NO_LOCK) && !handle) {
-		/* Direct IO write... */
-		if (map.m_len > DIO_MAX_BLOCKS)
-			map.m_len = DIO_MAX_BLOCKS;
-		dio_credits = ext4_chunk_trans_blocks(inode, map.m_len);
-		handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
-					    dio_credits);
-		if (IS_ERR(handle)) {
-			ret = PTR_ERR(handle);
-			return ret;
-		}
-		started = 1;
-	}
-
-	ret = ext4_map_blocks(handle, inode, &map, flags);
+	ret = ext4_map_blocks(ext4_journal_current_handle(), inode, &map,
+			      flags);
 	if (ret > 0) {
-		ext4_io_end_t *io_end = ext4_inode_aio(inode);
-
 		map_bh(bh, inode->i_sb, map.m_pblk);
-		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
-		if (IS_DAX(inode) && buffer_unwritten(bh)) {
-			/*
-			 * dgc: I suspect unwritten conversion on ext4+DAX is
-			 * fundamentally broken here when there are concurrent
-			 * read/write in progress on this inode.
-			 */
-			WARN_ON_ONCE(io_end);
-			bh->b_assoc_map = inode->i_mapping;
-			bh->b_private = (void *)(unsigned long)iblock;
-		}
-		if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN)
-			set_buffer_defer_completion(bh);
+		ext4_update_bh_state(bh, map.m_flags);
 		bh->b_size = inode->i_sb->s_blocksize * map.m_len;
 		ret = 0;
 	}
-	if (started)
-		ext4_journal_stop(handle);
 	return ret;
 }
 
@@ -722,6 +747,153 @@ int ext4_get_block(struct inode *inode, sector_t iblock,
 }
 
 /*
+ * Get block function used when preparing for buffered write if we require
+ * creating an unwritten extent if blocks haven't been allocated.  The extent
+ * will be converted to written after the IO is complete.
+ */
+int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
+			     struct buffer_head *bh_result, int create)
+{
+	ext4_debug("ext4_get_block_unwritten: inode %lu, create flag %d\n",
+		   inode->i_ino, create);
+	return _ext4_get_block(inode, iblock, bh_result,
+			       EXT4_GET_BLOCKS_IO_CREATE_EXT);
+}
+
+/* Maximum number of blocks we map for direct IO at once. */
+#define DIO_MAX_BLOCKS 4096
+
+/*
+ * Get blocks function for the cases that need to start a transaction -
+ * generally difference cases of direct IO and DAX IO. It also handles retries
+ * in case of ENOSPC.
+ */
+static int ext4_get_block_trans(struct inode *inode, sector_t iblock,
+				struct buffer_head *bh_result, int flags)
+{
+	int dio_credits;
+	handle_t *handle;
+	int retries = 0;
+	int ret;
+
+	/* Trim mapping request to maximum we can map at once for DIO */
+	if (bh_result->b_size >> inode->i_blkbits > DIO_MAX_BLOCKS)
+		bh_result->b_size = DIO_MAX_BLOCKS << inode->i_blkbits;
+	dio_credits = ext4_chunk_trans_blocks(inode,
+				      bh_result->b_size >> inode->i_blkbits);
+retry:
+	handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, dio_credits);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	ret = _ext4_get_block(inode, iblock, bh_result, flags);
+	ext4_journal_stop(handle);
+
+	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+		goto retry;
+	return ret;
+}
+
+/* Get block function for DIO reads and writes to inodes without extents */
+int ext4_dio_get_block(struct inode *inode, sector_t iblock,
+		       struct buffer_head *bh, int create)
+{
+	/* We don't expect handle for direct IO */
+	WARN_ON_ONCE(ext4_journal_current_handle());
+
+	if (!create)
+		return _ext4_get_block(inode, iblock, bh, 0);
+	return ext4_get_block_trans(inode, iblock, bh, EXT4_GET_BLOCKS_CREATE);
+}
+
+/*
+ * Get block function for AIO DIO writes when we create unwritten extent if
+ * blocks are not allocated yet. The extent will be converted to written
+ * after IO is complete.
+ */
+static int ext4_dio_get_block_unwritten_async(struct inode *inode,
+		sector_t iblock, struct buffer_head *bh_result,	int create)
+{
+	int ret;
+
+	/* We don't expect handle for direct IO */
+	WARN_ON_ONCE(ext4_journal_current_handle());
+
+	ret = ext4_get_block_trans(inode, iblock, bh_result,
+				   EXT4_GET_BLOCKS_IO_CREATE_EXT);
+
+	/*
+	 * When doing DIO using unwritten extents, we need io_end to convert
+	 * unwritten extents to written on IO completion. We allocate io_end
+	 * once we spot unwritten extent and store it in b_private. Generic
+	 * DIO code keeps b_private set and furthermore passes the value to
+	 * our completion callback in 'private' argument.
+	 */
+	if (!ret && buffer_unwritten(bh_result)) {
+		if (!bh_result->b_private) {
+			ext4_io_end_t *io_end;
+
+			io_end = ext4_init_io_end(inode, GFP_KERNEL);
+			if (!io_end)
+				return -ENOMEM;
+			bh_result->b_private = io_end;
+			ext4_set_io_unwritten_flag(inode, io_end);
+		}
+		set_buffer_defer_completion(bh_result);
+	}
+
+	return ret;
+}
+
+/*
+ * Get block function for non-AIO DIO writes when we create unwritten extent if
+ * blocks are not allocated yet. The extent will be converted to written
+ * after IO is complete from ext4_ext_direct_IO() function.
+ */
+static int ext4_dio_get_block_unwritten_sync(struct inode *inode,
+		sector_t iblock, struct buffer_head *bh_result,	int create)
+{
+	int ret;
+
+	/* We don't expect handle for direct IO */
+	WARN_ON_ONCE(ext4_journal_current_handle());
+
+	ret = ext4_get_block_trans(inode, iblock, bh_result,
+				   EXT4_GET_BLOCKS_IO_CREATE_EXT);
+
+	/*
+	 * Mark inode as having pending DIO writes to unwritten extents.
+	 * ext4_ext_direct_IO() checks this flag and converts extents to
+	 * written.
+	 */
+	if (!ret && buffer_unwritten(bh_result))
+		ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
+
+	return ret;
+}
+
+static int ext4_dio_get_block_overwrite(struct inode *inode, sector_t iblock,
+		   struct buffer_head *bh_result, int create)
+{
+	int ret;
+
+	ext4_debug("ext4_dio_get_block_overwrite: inode %lu, create flag %d\n",
+		   inode->i_ino, create);
+	/* We don't expect handle for direct IO */
+	WARN_ON_ONCE(ext4_journal_current_handle());
+
+	ret = _ext4_get_block(inode, iblock, bh_result, 0);
+	/*
+	 * Blocks should have been preallocated! ext4_file_write_iter() checks
+	 * that.
+	 */
+	WARN_ON_ONCE(!buffer_mapped(bh_result) || buffer_unwritten(bh_result));
+
+	return ret;
+}
+
+
+/*
  * `handle' can be NULL if create is zero
  */
 struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
@@ -879,14 +1051,11 @@ int do_journal_get_write_access(handle_t *handle,
 	return ret;
 }
 
-static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock,
-		   struct buffer_head *bh_result, int create);
-
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
 static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
 				  get_block_t *get_block)
 {
-	unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+	unsigned from = pos & (PAGE_SIZE - 1);
 	unsigned to = from + len;
 	struct inode *inode = page->mapping->host;
 	unsigned block_start, block_end;
@@ -898,15 +1067,15 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
 	bool decrypt = false;
 
 	BUG_ON(!PageLocked(page));
-	BUG_ON(from > PAGE_CACHE_SIZE);
-	BUG_ON(to > PAGE_CACHE_SIZE);
+	BUG_ON(from > PAGE_SIZE);
+	BUG_ON(to > PAGE_SIZE);
 	BUG_ON(from > to);
 
 	if (!page_has_buffers(page))
 		create_empty_buffers(page, blocksize, 0);
 	head = page_buffers(page);
 	bbits = ilog2(blocksize);
-	block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits);
+	block = (sector_t)page->index << (PAGE_SHIFT - bbits);
 
 	for (bh = head, block_start = 0; bh != head || !block_start;
 	    block++, block_start = block_end, bh = bh->b_this_page) {
@@ -988,8 +1157,8 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
 	 * we allocate blocks but write fails for some reason
 	 */
 	needed_blocks = ext4_writepage_trans_blocks(inode) + 1;
-	index = pos >> PAGE_CACHE_SHIFT;
-	from = pos & (PAGE_CACHE_SIZE - 1);
+	index = pos >> PAGE_SHIFT;
+	from = pos & (PAGE_SIZE - 1);
 	to = from + len;
 
 	if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) {
@@ -1017,7 +1186,7 @@ retry_grab:
 retry_journal:
 	handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks);
 	if (IS_ERR(handle)) {
-		page_cache_release(page);
+		put_page(page);
 		return PTR_ERR(handle);
 	}
 
@@ -1025,7 +1194,7 @@ retry_journal:
 	if (page->mapping != mapping) {
 		/* The page got truncated from under us */
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 		ext4_journal_stop(handle);
 		goto retry_grab;
 	}
@@ -1035,13 +1204,14 @@ retry_journal:
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
 	if (ext4_should_dioread_nolock(inode))
 		ret = ext4_block_write_begin(page, pos, len,
-					     ext4_get_block_write);
+					     ext4_get_block_unwritten);
 	else
 		ret = ext4_block_write_begin(page, pos, len,
 					     ext4_get_block);
 #else
 	if (ext4_should_dioread_nolock(inode))
-		ret = __block_write_begin(page, pos, len, ext4_get_block_write);
+		ret = __block_write_begin(page, pos, len,
+					  ext4_get_block_unwritten);
 	else
 		ret = __block_write_begin(page, pos, len, ext4_get_block);
 #endif
@@ -1080,7 +1250,7 @@ retry_journal:
 		if (ret == -ENOSPC &&
 		    ext4_should_retry_alloc(inode->i_sb, &retries))
 			goto retry_journal;
-		page_cache_release(page);
+		put_page(page);
 		return ret;
 	}
 	*pagep = page;
@@ -1123,7 +1293,7 @@ static int ext4_write_end(struct file *file,
 		ret = ext4_jbd2_file_inode(handle, inode);
 		if (ret) {
 			unlock_page(page);
-			page_cache_release(page);
+			put_page(page);
 			goto errout;
 		}
 	}
@@ -1143,7 +1313,7 @@ static int ext4_write_end(struct file *file,
 	 */
 	i_size_changed = ext4_update_inode_size(inode, pos + copied);
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 
 	if (old_size < pos)
 		pagecache_isize_extended(inode, old_size, pos);
@@ -1227,7 +1397,7 @@ static int ext4_journalled_write_end(struct file *file,
 	int size_changed = 0;
 
 	trace_ext4_journalled_write_end(inode, pos, len, copied);
-	from = pos & (PAGE_CACHE_SIZE - 1);
+	from = pos & (PAGE_SIZE - 1);
 	to = from + len;
 
 	BUG_ON(!ext4_handle_valid(handle));
@@ -1251,7 +1421,7 @@ static int ext4_journalled_write_end(struct file *file,
 	ext4_set_inode_state(inode, EXT4_STATE_JDATA);
 	EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 
 	if (old_size < pos)
 		pagecache_isize_extended(inode, old_size, pos);
@@ -1365,7 +1535,7 @@ static void ext4_da_page_release_reservation(struct page *page,
 	int num_clusters;
 	ext4_fsblk_t lblk;
 
-	BUG_ON(stop > PAGE_CACHE_SIZE || stop < length);
+	BUG_ON(stop > PAGE_SIZE || stop < length);
 
 	head = page_buffers(page);
 	bh = head;
@@ -1381,7 +1551,7 @@ static void ext4_da_page_release_reservation(struct page *page,
 			clear_buffer_delay(bh);
 		} else if (contiguous_blks) {
 			lblk = page->index <<
-			       (PAGE_CACHE_SHIFT - inode->i_blkbits);
+			       (PAGE_SHIFT - inode->i_blkbits);
 			lblk += (curr_off >> inode->i_blkbits) -
 				contiguous_blks;
 			ext4_es_remove_extent(inode, lblk, contiguous_blks);
@@ -1391,7 +1561,7 @@ static void ext4_da_page_release_reservation(struct page *page,
 	} while ((bh = bh->b_this_page) != head);
 
 	if (contiguous_blks) {
-		lblk = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+		lblk = page->index << (PAGE_SHIFT - inode->i_blkbits);
 		lblk += (curr_off >> inode->i_blkbits) - contiguous_blks;
 		ext4_es_remove_extent(inode, lblk, contiguous_blks);
 	}
@@ -1400,7 +1570,7 @@ static void ext4_da_page_release_reservation(struct page *page,
 	 * need to release the reserved space for that cluster. */
 	num_clusters = EXT4_NUM_B2C(sbi, to_release);
 	while (num_clusters > 0) {
-		lblk = (page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits)) +
+		lblk = (page->index << (PAGE_SHIFT - inode->i_blkbits)) +
 			((num_clusters - 1) << sbi->s_cluster_bits);
 		if (sbi->s_cluster_ratio == 1 ||
 		    !ext4_find_delalloc_cluster(inode, lblk))
@@ -1447,8 +1617,8 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd,
 	end   = mpd->next_page - 1;
 	if (invalidate) {
 		ext4_lblk_t start, last;
-		start = index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
-		last = end << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+		start = index << (PAGE_SHIFT - inode->i_blkbits);
+		last = end << (PAGE_SHIFT - inode->i_blkbits);
 		ext4_es_remove_extent(inode, start, last - start + 1);
 	}
 
@@ -1464,7 +1634,7 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd,
 			BUG_ON(!PageLocked(page));
 			BUG_ON(PageWriteback(page));
 			if (invalidate) {
-				block_invalidatepage(page, 0, PAGE_CACHE_SIZE);
+				block_invalidatepage(page, 0, PAGE_SIZE);
 				ClearPageUptodate(page);
 			}
 			unlock_page(page);
@@ -1669,7 +1839,7 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 		return ret;
 
 	map_bh(bh, inode->i_sb, map.m_pblk);
-	bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+	ext4_update_bh_state(bh, map.m_flags);
 
 	if (buffer_unwritten(bh)) {
 		/* A delayed write to unwritten bh should be marked
@@ -1835,10 +2005,10 @@ static int ext4_writepage(struct page *page,
 
 	trace_ext4_writepage(page);
 	size = i_size_read(inode);
-	if (page->index == size >> PAGE_CACHE_SHIFT)
-		len = size & ~PAGE_CACHE_MASK;
+	if (page->index == size >> PAGE_SHIFT)
+		len = size & ~PAGE_MASK;
 	else
-		len = PAGE_CACHE_SIZE;
+		len = PAGE_SIZE;
 
 	page_bufs = page_buffers(page);
 	/*
@@ -1862,7 +2032,7 @@ static int ext4_writepage(struct page *page,
 				   ext4_bh_delay_or_unwritten)) {
 		redirty_page_for_writepage(wbc, page);
 		if ((current->flags & PF_MEMALLOC) ||
-		    (inode->i_sb->s_blocksize == PAGE_CACHE_SIZE)) {
+		    (inode->i_sb->s_blocksize == PAGE_SIZE)) {
 			/*
 			 * For memory cleaning there's no point in writing only
 			 * some buffers. So just bail out. Warn if we came here
@@ -1904,10 +2074,10 @@ static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page)
 	int err;
 
 	BUG_ON(page->index != mpd->first_page);
-	if (page->index == size >> PAGE_CACHE_SHIFT)
-		len = size & ~PAGE_CACHE_MASK;
+	if (page->index == size >> PAGE_SHIFT)
+		len = size & ~PAGE_MASK;
 	else
-		len = PAGE_CACHE_SIZE;
+		len = PAGE_SIZE;
 	clear_page_dirty_for_io(page);
 	err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc, false);
 	if (!err)
@@ -2041,7 +2211,7 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
 	int nr_pages, i;
 	struct inode *inode = mpd->inode;
 	struct buffer_head *head, *bh;
-	int bpp_bits = PAGE_CACHE_SHIFT - inode->i_blkbits;
+	int bpp_bits = PAGE_SHIFT - inode->i_blkbits;
 	pgoff_t start, end;
 	ext4_lblk_t lblk;
 	sector_t pblock;
@@ -2102,7 +2272,7 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
 			 * supports blocksize < pagesize as we will try to
 			 * convert potentially unmapped parts of inode.
 			 */
-			mpd->io_submit.io_end->size += PAGE_CACHE_SIZE;
+			mpd->io_submit.io_end->size += PAGE_SIZE;
 			/* Page fully mapped - let IO run! */
 			err = mpage_submit_page(mpd, page);
 			if (err < 0) {
@@ -2254,7 +2424,7 @@ update_disksize:
 	 * Update on-disk size after IO is submitted.  Races with
 	 * truncate are avoided by checking i_size under i_data_sem.
 	 */
-	disksize = ((loff_t)mpd->first_page) << PAGE_CACHE_SHIFT;
+	disksize = ((loff_t)mpd->first_page) << PAGE_SHIFT;
 	if (disksize > EXT4_I(inode)->i_disksize) {
 		int err2;
 		loff_t i_size;
@@ -2390,7 +2560,7 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 			mpd->next_page = page->index + 1;
 			/* Add all dirty buffers to mpd */
 			lblk = ((ext4_lblk_t)page->index) <<
-				(PAGE_CACHE_SHIFT - blkbits);
+				(PAGE_SHIFT - blkbits);
 			head = page_buffers(page);
 			err = mpage_process_page_bufs(mpd, head, head, lblk);
 			if (err <= 0)
@@ -2434,6 +2604,10 @@ static int ext4_writepages(struct address_space *mapping,
 
 	trace_ext4_writepages(inode, wbc);
 
+	if (dax_mapping(mapping))
+		return dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev,
+						   wbc);
+
 	/*
 	 * No pages to write? This is mainly a kludge to avoid starting
 	 * a transaction for special inodes like journal inode on last iput()
@@ -2471,7 +2645,7 @@ static int ext4_writepages(struct address_space *mapping,
 		 * We may need to convert up to one extent per block in
 		 * the page and we may dirty the inode.
 		 */
-		rsv_blocks = 1 + (PAGE_CACHE_SIZE >> inode->i_blkbits);
+		rsv_blocks = 1 + (PAGE_SIZE >> inode->i_blkbits);
 	}
 
 	/*
@@ -2502,8 +2676,8 @@ static int ext4_writepages(struct address_space *mapping,
 		mpd.first_page = writeback_index;
 		mpd.last_page = -1;
 	} else {
-		mpd.first_page = wbc->range_start >> PAGE_CACHE_SHIFT;
-		mpd.last_page = wbc->range_end >> PAGE_CACHE_SHIFT;
+		mpd.first_page = wbc->range_start >> PAGE_SHIFT;
+		mpd.last_page = wbc->range_end >> PAGE_SHIFT;
 	}
 
 	mpd.inode = inode;
@@ -2662,7 +2836,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 	struct inode *inode = mapping->host;
 	handle_t *handle;
 
-	index = pos >> PAGE_CACHE_SHIFT;
+	index = pos >> PAGE_SHIFT;
 
 	if (ext4_nonda_switch(inode->i_sb)) {
 		*fsdata = (void *)FALL_BACK_TO_NONDELALLOC;
@@ -2705,7 +2879,7 @@ retry_journal:
 	handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE,
 				ext4_da_write_credits(inode, pos, len));
 	if (IS_ERR(handle)) {
-		page_cache_release(page);
+		put_page(page);
 		return PTR_ERR(handle);
 	}
 
@@ -2713,7 +2887,7 @@ retry_journal:
 	if (page->mapping != mapping) {
 		/* The page got truncated from under us */
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 		ext4_journal_stop(handle);
 		goto retry_grab;
 	}
@@ -2741,7 +2915,7 @@ retry_journal:
 		    ext4_should_retry_alloc(inode->i_sb, &retries))
 			goto retry_journal;
 
-		page_cache_release(page);
+		put_page(page);
 		return ret;
 	}
 
@@ -2789,7 +2963,7 @@ static int ext4_da_write_end(struct file *file,
 				      len, copied, page, fsdata);
 
 	trace_ext4_da_write_end(inode, pos, len, copied);
-	start = pos & (PAGE_CACHE_SIZE - 1);
+	start = pos & (PAGE_SIZE - 1);
 	end = start + copied - 1;
 
 	/*
@@ -3011,7 +3185,7 @@ static int __ext4_journalled_invalidatepage(struct page *page,
 	/*
 	 * If it's a full truncate we just forget about the pending dirtying
 	 */
-	if (offset == 0 && length == PAGE_CACHE_SIZE)
+	if (offset == 0 && length == PAGE_SIZE)
 		ClearPageChecked(page);
 
 	return jbd2_journal_invalidatepage(journal, page, offset, length);
@@ -3040,58 +3214,105 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
 		return try_to_free_buffers(page);
 }
 
-/*
- * ext4_get_block used when preparing for a DIO write or buffer write.
- * We allocate an uinitialized extent if blocks haven't been allocated.
- * The extent will be converted to initialized after the IO is complete.
- */
-int ext4_get_block_write(struct inode *inode, sector_t iblock,
-		   struct buffer_head *bh_result, int create)
+#ifdef CONFIG_FS_DAX
+int ext4_dax_mmap_get_block(struct inode *inode, sector_t iblock,
+			    struct buffer_head *bh_result, int create)
 {
-	ext4_debug("ext4_get_block_write: inode %lu, create flag %d\n",
-		   inode->i_ino, create);
-	return _ext4_get_block(inode, iblock, bh_result,
-			       EXT4_GET_BLOCKS_IO_CREATE_EXT);
-}
+	int ret, err;
+	int credits;
+	struct ext4_map_blocks map;
+	handle_t *handle = NULL;
+	int flags = 0;
 
-static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock,
-		   struct buffer_head *bh_result, int create)
-{
-	ext4_debug("ext4_get_block_write_nolock: inode %lu, create flag %d\n",
+	ext4_debug("ext4_dax_mmap_get_block: inode %lu, create flag %d\n",
 		   inode->i_ino, create);
-	return _ext4_get_block(inode, iblock, bh_result,
-			       EXT4_GET_BLOCKS_NO_LOCK);
-}
+	map.m_lblk = iblock;
+	map.m_len = bh_result->b_size >> inode->i_blkbits;
+	credits = ext4_chunk_trans_blocks(inode, map.m_len);
+	if (create) {
+		flags |= EXT4_GET_BLOCKS_PRE_IO | EXT4_GET_BLOCKS_CREATE_ZERO;
+		handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits);
+		if (IS_ERR(handle)) {
+			ret = PTR_ERR(handle);
+			return ret;
+		}
+	}
 
-int ext4_get_block_dax(struct inode *inode, sector_t iblock,
-		   struct buffer_head *bh_result, int create)
-{
-	int flags = EXT4_GET_BLOCKS_PRE_IO | EXT4_GET_BLOCKS_UNWRIT_EXT;
-	if (create)
-		flags |= EXT4_GET_BLOCKS_CREATE;
-	ext4_debug("ext4_get_block_dax: inode %lu, create flag %d\n",
-		   inode->i_ino, create);
-	return _ext4_get_block(inode, iblock, bh_result, flags);
+	ret = ext4_map_blocks(handle, inode, &map, flags);
+	if (create) {
+		err = ext4_journal_stop(handle);
+		if (ret >= 0 && err < 0)
+			ret = err;
+	}
+	if (ret <= 0)
+		goto out;
+	if (map.m_flags & EXT4_MAP_UNWRITTEN) {
+		int err2;
+
+		/*
+		 * We are protected by i_mmap_sem so we know block cannot go
+		 * away from under us even though we dropped i_data_sem.
+		 * Convert extent to written and write zeros there.
+		 *
+		 * Note: We may get here even when create == 0.
+		 */
+		handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits);
+		if (IS_ERR(handle)) {
+			ret = PTR_ERR(handle);
+			goto out;
+		}
+
+		err = ext4_map_blocks(handle, inode, &map,
+		      EXT4_GET_BLOCKS_CONVERT | EXT4_GET_BLOCKS_CREATE_ZERO);
+		if (err < 0)
+			ret = err;
+		err2 = ext4_journal_stop(handle);
+		if (err2 < 0 && ret > 0)
+			ret = err2;
+	}
+out:
+	WARN_ON_ONCE(ret == 0 && create);
+	if (ret > 0) {
+		map_bh(bh_result, inode->i_sb, map.m_pblk);
+		/*
+		 * At least for now we have to clear BH_New so that DAX code
+		 * doesn't attempt to zero blocks again in a racy way.
+		 */
+		map.m_flags &= ~EXT4_MAP_NEW;
+		ext4_update_bh_state(bh_result, map.m_flags);
+		bh_result->b_size = map.m_len << inode->i_blkbits;
+		ret = 0;
+	}
+	return ret;
 }
+#endif
 
-static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
+static int ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
 			    ssize_t size, void *private)
 {
-        ext4_io_end_t *io_end = iocb->private;
+        ext4_io_end_t *io_end = private;
 
 	/* if not async direct IO just return */
 	if (!io_end)
-		return;
+		return 0;
 
 	ext_debug("ext4_end_io_dio(): io_end 0x%p "
 		  "for inode %lu, iocb 0x%p, offset %llu, size %zd\n",
- 		  iocb->private, io_end->inode->i_ino, iocb, offset,
-		  size);
+		  io_end, io_end->inode->i_ino, iocb, offset, size);
 
-	iocb->private = NULL;
+	/*
+	 * Error during AIO DIO. We cannot convert unwritten extents as the
+	 * data was not written. Just clear the unwritten flag and drop io_end.
+	 */
+	if (size <= 0) {
+		ext4_clear_io_unwritten_flag(io_end);
+		size = 0;
+	}
 	io_end->offset = offset;
 	io_end->size = size;
 	ext4_put_io_end(io_end);
+
+	return 0;
 }
 
 /*
@@ -3124,7 +3345,6 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	get_block_t *get_block_func = NULL;
 	int dio_flags = 0;
 	loff_t final_size = offset + count;
-	ext4_io_end_t *io_end = NULL;
 
 	/* Use the old path for reads and writes beyond i_size. */
 	if (iov_iter_rw(iter) != WRITE || final_size > inode->i_size)
@@ -3143,24 +3363,23 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	/* If we do a overwrite dio, i_mutex locking can be released */
 	overwrite = *((int *)iocb->private);
 
-	if (overwrite) {
-		down_read(&EXT4_I(inode)->i_data_sem);
-		mutex_unlock(&inode->i_mutex);
-	}
+	if (overwrite)
+		inode_unlock(inode);
 
 	/*
 	 * We could direct write to holes and fallocate.
 	 *
-	 * Allocated blocks to fill the hole are marked as
-	 * unwritten to prevent parallel buffered read to expose
-	 * the stale data before DIO complete the data IO.
+	 * Allocated blocks to fill the hole are marked as unwritten to prevent
+	 * parallel buffered read to expose the stale data before DIO complete
+	 * the data IO.
 	 *
-	 * As to previously fallocated extents, ext4 get_block will
-	 * just simply mark the buffer mapped but still keep the
-	 * extents unwritten.
+	 * As to previously fallocated extents, ext4 get_block will just simply
+	 * mark the buffer mapped but still keep the extents unwritten.
 	 *
-	 * For non AIO case, we will convert those unwritten extents
-	 * to written after return back from blockdev_direct_IO.
+	 * For non AIO case, we will convert those unwritten extents to written
+	 * after return back from blockdev_direct_IO. That way we save us from
+	 * allocating io_end structure and also the overhead of offloading
+	 * the extent convertion to a workqueue.
 	 *
 	 * For async DIO, the conversion needs to be deferred when the
 	 * IO is completed. The ext4 end_io callback function will be
@@ -3168,30 +3387,13 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	 * case, we allocate an io_end structure to hook to the iocb.
 	 */
 	iocb->private = NULL;
-	ext4_inode_aio_set(inode, NULL);
-	if (!is_sync_kiocb(iocb)) {
-		io_end = ext4_init_io_end(inode, GFP_NOFS);
-		if (!io_end) {
-			ret = -ENOMEM;
-			goto retake_lock;
-		}
-		/*
-		 * Grab reference for DIO. Will be dropped in ext4_end_io_dio()
-		 */
-		iocb->private = ext4_get_io_end(io_end);
-		/*
-		 * we save the io structure for current async direct
-		 * IO, so that later ext4_map_blocks() could flag the
-		 * io structure whether there is a unwritten extents
-		 * needs to be converted when IO is completed.
-		 */
-		ext4_inode_aio_set(inode, io_end);
-	}
-
-	if (overwrite) {
-		get_block_func = ext4_get_block_write_nolock;
+	if (overwrite)
+		get_block_func = ext4_dio_get_block_overwrite;
+	else if (is_sync_kiocb(iocb)) {
+		get_block_func = ext4_dio_get_block_unwritten_sync;
+		dio_flags = DIO_LOCKING;
 	} else {
-		get_block_func = ext4_get_block_write;
+		get_block_func = ext4_dio_get_block_unwritten_async;
 		dio_flags = DIO_LOCKING;
 	}
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
@@ -3206,27 +3408,6 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 					   get_block_func,
 					   ext4_end_io_dio, NULL, dio_flags);
 
-	/*
-	 * Put our reference to io_end. This can free the io_end structure e.g.
-	 * in sync IO case or in case of error. It can even perform extent
-	 * conversion if all bios we submitted finished before we got here.
-	 * Note that in that case iocb->private can be already set to NULL
-	 * here.
-	 */
-	if (io_end) {
-		ext4_inode_aio_set(inode, NULL);
-		ext4_put_io_end(io_end);
-		/*
-		 * When no IO was submitted ext4_end_io_dio() was not
-		 * called so we have to put iocb's reference.
-		 */
-		if (ret <= 0 && ret != -EIOCBQUEUED && iocb->private) {
-			WARN_ON(iocb->private != io_end);
-			WARN_ON(io_end->flag & EXT4_IO_END_UNWRITTEN);
-			ext4_put_io_end(io_end);
-			iocb->private = NULL;
-		}
-	}
 	if (ret > 0 && !overwrite && ext4_test_inode_state(inode,
 						EXT4_STATE_DIO_UNWRITTEN)) {
 		int err;
@@ -3241,14 +3422,11 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		ext4_clear_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
 	}
 
-retake_lock:
 	if (iov_iter_rw(iter) == WRITE)
 		inode_dio_end(inode);
 	/* take i_mutex locking again if we do a ovewrite dio */
-	if (overwrite) {
-		up_read(&EXT4_I(inode)->i_data_sem);
-		mutex_lock(&inode->i_mutex);
-	}
+	if (overwrite)
+		inode_lock(inode);
 
 	return ret;
 }
@@ -3376,8 +3554,8 @@ void ext4_set_aops(struct inode *inode)
 static int __ext4_block_zero_page_range(handle_t *handle,
 		struct address_space *mapping, loff_t from, loff_t length)
 {
-	ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
-	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	ext4_fsblk_t index = from >> PAGE_SHIFT;
+	unsigned offset = from & (PAGE_SIZE-1);
 	unsigned blocksize, pos;
 	ext4_lblk_t iblock;
 	struct inode *inode = mapping->host;
@@ -3385,14 +3563,14 @@ static int __ext4_block_zero_page_range(handle_t *handle,
 	struct page *page;
 	int err = 0;
 
-	page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT,
-				   mapping_gfp_mask(mapping) & ~__GFP_FS);
+	page = find_or_create_page(mapping, from >> PAGE_SHIFT,
+				   mapping_gfp_constraint(mapping, ~__GFP_FS));
 	if (!page)
 		return -ENOMEM;
 
 	blocksize = inode->i_sb->s_blocksize;
 
-	iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
+	iblock = index << (PAGE_SHIFT - inode->i_sb->s_blocksize_bits);
 
 	if (!page_has_buffers(page))
 		create_empty_buffers(page, blocksize, 0);
@@ -3434,7 +3612,7 @@ static int __ext4_block_zero_page_range(handle_t *handle,
 		    ext4_encrypted_inode(inode)) {
 			/* We expect the key to be set. */
 			BUG_ON(!ext4_has_encryption_key(inode));
-			BUG_ON(blocksize != PAGE_CACHE_SIZE);
+			BUG_ON(blocksize != PAGE_SIZE);
 			WARN_ON_ONCE(ext4_decrypt(page));
 		}
 	}
@@ -3458,7 +3636,7 @@ static int __ext4_block_zero_page_range(handle_t *handle,
 
 unlock:
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 	return err;
 }
 
@@ -3473,7 +3651,7 @@ static int ext4_block_zero_page_range(handle_t *handle,
 		struct address_space *mapping, loff_t from, loff_t length)
 {
 	struct inode *inode = mapping->host;
-	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	unsigned offset = from & (PAGE_SIZE-1);
 	unsigned blocksize = inode->i_sb->s_blocksize;
 	unsigned max = blocksize - (offset & (blocksize - 1));
 
@@ -3498,7 +3676,7 @@ static int ext4_block_zero_page_range(handle_t *handle,
 static int ext4_block_truncate_page(handle_t *handle,
 		struct address_space *mapping, loff_t from)
 {
-	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	unsigned offset = from & (PAGE_SIZE-1);
 	unsigned length;
 	unsigned blocksize;
 	struct inode *inode = mapping->host;
@@ -3559,6 +3737,35 @@ int ext4_can_truncate(struct inode *inode)
 }
 
 /*
+ * We have to make sure i_disksize gets properly updated before we truncate
+ * page cache due to hole punching or zero range. Otherwise i_disksize update
+ * can get lost as it may have been postponed to submission of writeback but
+ * that will never happen after we truncate page cache.
+ */
+int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
+				      loff_t len)
+{
+	handle_t *handle;
+	loff_t size = i_size_read(inode);
+
+	WARN_ON(!inode_is_locked(inode));
+	if (offset > size || offset + len < size)
+		return 0;
+
+	if (EXT4_I(inode)->i_disksize >= size)
+		return 0;
+
+	handle = ext4_journal_start(inode, EXT4_HT_MISC, 1);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+	ext4_update_i_disksize(inode, size);
+	ext4_mark_inode_dirty(handle, inode);
+	ext4_journal_stop(handle);
+
+	return 0;
+}
+
+/*
  * ext4_punch_hole: punches a hole in a file by releaseing the blocks
  * associated with the given offset and length
  *
@@ -3595,7 +3802,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 			return ret;
 	}
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	/* No need to punch hole beyond i_size */
 	if (offset >= inode->i_size)
@@ -3607,7 +3814,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 	 */
 	if (offset + length > inode->i_size) {
 		length = inode->i_size +
-		   PAGE_CACHE_SIZE - (inode->i_size & (PAGE_CACHE_SIZE - 1)) -
+		   PAGE_SIZE - (inode->i_size & (PAGE_SIZE - 1)) -
 		   offset;
 	}
 
@@ -3623,17 +3830,26 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 
 	}
 
+	/* Wait all existing dio workers, newcomers will block on i_mutex */
+	ext4_inode_block_unlocked_dio(inode);
+	inode_dio_wait(inode);
+
+	/*
+	 * Prevent page faults from reinstantiating pages we have released from
+	 * page cache.
+	 */
+	down_write(&EXT4_I(inode)->i_mmap_sem);
 	first_block_offset = round_up(offset, sb->s_blocksize);
 	last_block_offset = round_down((offset + length), sb->s_blocksize) - 1;
 
 	/* Now release the pages and zero block aligned part of pages*/
-	if (last_block_offset > first_block_offset)
+	if (last_block_offset > first_block_offset) {
+		ret = ext4_update_disksize_before_punch(inode, offset, length);
+		if (ret)
+			goto out_dio;
 		truncate_pagecache_range(inode, first_block_offset,
 					 last_block_offset);
-
-	/* Wait all existing dio workers, newcomers will block on i_mutex */
-	ext4_inode_block_unlocked_dio(inode);
-	inode_dio_wait(inode);
+	}
 
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 		credits = ext4_writepage_trans_blocks(inode);
@@ -3680,19 +3896,15 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
 
-	/* Now release the pages again to reduce race window */
-	if (last_block_offset > first_block_offset)
-		truncate_pagecache_range(inode, first_block_offset,
-					 last_block_offset);
-
 	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
 out_stop:
 	ext4_journal_stop(handle);
 out_dio:
+	up_write(&EXT4_I(inode)->i_mmap_sem);
 	ext4_inode_resume_unlocked_dio(inode);
 out_mutex:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return ret;
 }
 
@@ -3762,7 +3974,7 @@ void ext4_truncate(struct inode *inode)
 	 * have i_mutex locked because it's not necessary.
 	 */
 	if (!(inode->i_state & (I_NEW|I_FREEING)))
-		WARN_ON(!mutex_is_locked(&inode->i_mutex));
+		WARN_ON(!inode_is_locked(inode));
 	trace_ext4_truncate_enter(inode);
 
 	if (!ext4_can_truncate(inode))
@@ -4010,7 +4222,7 @@ void ext4_set_inode_flags(struct inode *inode)
 		new_fl |= S_NOATIME;
 	if (flags & EXT4_DIRSYNC_FL)
 		new_fl |= S_DIRSYNC;
-	if (test_opt(inode->i_sb, DAX))
+	if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode))
 		new_fl |= S_DAX;
 	inode_set_flags(inode, new_fl,
 			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX);
@@ -4076,6 +4288,14 @@ static inline void ext4_iget_extra_inode(struct inode *inode,
 		EXT4_I(inode)->i_inline_off = 0;
 }
 
+int ext4_get_projid(struct inode *inode, kprojid_t *projid)
+{
+	if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, EXT4_FEATURE_RO_COMPAT_PROJECT))
+		return -EOPNOTSUPP;
+	*projid = EXT4_I(inode)->i_projid;
+	return 0;
+}
+
 struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 {
 	struct ext4_iloc iloc;
@@ -4087,6 +4307,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 	int block;
 	uid_t i_uid;
 	gid_t i_gid;
+	projid_t i_projid;
 
 	inode = iget_locked(sb, ino);
 	if (!inode)
@@ -4136,12 +4357,20 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 	inode->i_mode = le16_to_cpu(raw_inode->i_mode);
 	i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
 	i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low);
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_PROJECT) &&
+	    EXT4_INODE_SIZE(sb) > EXT4_GOOD_OLD_INODE_SIZE &&
+	    EXT4_FITS_IN_INODE(raw_inode, ei, i_projid))
+		i_projid = (projid_t)le32_to_cpu(raw_inode->i_projid);
+	else
+		i_projid = EXT4_DEF_PROJID;
+
 	if (!(test_opt(inode->i_sb, NO_UID32))) {
 		i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
 		i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
 	}
 	i_uid_write(inode, i_uid);
 	i_gid_write(inode, i_gid);
+	ei->i_projid = make_kprojid(&init_user_ns, i_projid);
 	set_nlink(inode, le16_to_cpu(raw_inode->i_links_count));
 
 	ext4_clear_state_flags(ei);	/* Only relevant on 32-bit archs */
@@ -4283,6 +4512,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 			inode->i_op = &ext4_symlink_inode_operations;
 			ext4_set_aops(inode);
 		}
+		inode_nohighmem(inode);
 	} else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
 	      S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
 		inode->i_op = &ext4_special_inode_operations;
@@ -4439,6 +4669,7 @@ static int ext4_do_update_inode(handle_t *handle,
 	int need_datasync = 0, set_large_file = 0;
 	uid_t i_uid;
 	gid_t i_gid;
+	projid_t i_projid;
 
 	spin_lock(&ei->i_raw_lock);
 
@@ -4451,6 +4682,7 @@ static int ext4_do_update_inode(handle_t *handle,
 	raw_inode->i_mode = cpu_to_le16(inode->i_mode);
 	i_uid = i_uid_read(inode);
 	i_gid = i_gid_read(inode);
+	i_projid = from_kprojid(&init_user_ns, ei->i_projid);
 	if (!(test_opt(inode->i_sb, NO_UID32))) {
 		raw_inode->i_uid_low = cpu_to_le16(low_16_bits(i_uid));
 		raw_inode->i_gid_low = cpu_to_le16(low_16_bits(i_gid));
@@ -4528,6 +4760,15 @@ static int ext4_do_update_inode(handle_t *handle,
 				cpu_to_le16(ei->i_extra_isize);
 		}
 	}
+
+	BUG_ON(!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
+			EXT4_FEATURE_RO_COMPAT_PROJECT) &&
+	       i_projid != EXT4_DEF_PROJID);
+
+	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
+	    EXT4_FITS_IN_INODE(raw_inode, ei, i_projid))
+		raw_inode->i_projid = cpu_to_le32(i_projid);
+
 	ext4_inode_csum_set(inode, raw_inode, ei);
 	spin_unlock(&ei->i_raw_lock);
 	if (inode->i_sb->s_flags & MS_LAZYTIME)
@@ -4648,23 +4889,23 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode)
 	tid_t commit_tid = 0;
 	int ret;
 
-	offset = inode->i_size & (PAGE_CACHE_SIZE - 1);
+	offset = inode->i_size & (PAGE_SIZE - 1);
 	/*
 	 * All buffers in the last page remain valid? Then there's nothing to
-	 * do. We do the check mainly to optimize the common PAGE_CACHE_SIZE ==
+	 * do. We do the check mainly to optimize the common PAGE_SIZE ==
 	 * blocksize case
 	 */
-	if (offset > PAGE_CACHE_SIZE - (1 << inode->i_blkbits))
+	if (offset > PAGE_SIZE - (1 << inode->i_blkbits))
 		return;
 	while (1) {
 		page = find_lock_page(inode->i_mapping,
-				      inode->i_size >> PAGE_CACHE_SHIFT);
+				      inode->i_size >> PAGE_SHIFT);
 		if (!page)
 			return;
 		ret = __ext4_journalled_invalidatepage(page, offset,
-						PAGE_CACHE_SIZE - offset);
+						PAGE_SIZE - offset);
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 		if (ret != -EBUSY)
 			return;
 		commit_tid = 0;
@@ -4823,6 +5064,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 			} else
 				ext4_wait_for_tail_page_commit(inode);
 		}
+		down_write(&EXT4_I(inode)->i_mmap_sem);
 		/*
 		 * Truncate pagecache after we've waited for commit
 		 * in data=journal mode to make pages freeable.
@@ -4830,6 +5072,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 		truncate_pagecache(inode, inode->i_size);
 		if (shrink)
 			ext4_truncate(inode);
+		up_write(&EXT4_I(inode)->i_mmap_sem);
 	}
 
 	if (!rc) {
@@ -5081,6 +5324,8 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
 	might_sleep();
 	trace_ext4_mark_inode_dirty(inode, _RET_IP_);
 	err = ext4_reserve_inode_write(handle, inode, &iloc);
+	if (err)
+		return err;
 	if (ext4_handle_valid(handle) &&
 	    EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
 	    !ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) {
@@ -5111,9 +5356,7 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
 			}
 		}
 	}
-	if (!err)
-		err = ext4_mark_iloc_dirty(handle, inode, &iloc);
-	return err;
+	return ext4_mark_iloc_dirty(handle, inode, &iloc);
 }
 
 /*
@@ -5278,12 +5521,14 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 	sb_start_pagefault(inode->i_sb);
 	file_update_time(vma->vm_file);
+
+	down_read(&EXT4_I(inode)->i_mmap_sem);
 	/* Delalloc case is easy... */
 	if (test_opt(inode->i_sb, DELALLOC) &&
 	    !ext4_should_journal_data(inode) &&
 	    !ext4_nonda_switch(inode->i_sb)) {
 		do {
-			ret = __block_page_mkwrite(vma, vmf,
+			ret = block_page_mkwrite(vma, vmf,
 						   ext4_da_get_block_prep);
 		} while (ret == -ENOSPC &&
 		       ext4_should_retry_alloc(inode->i_sb, &retries));
@@ -5299,10 +5544,10 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 		goto out;
 	}
 
-	if (page->index == size >> PAGE_CACHE_SHIFT)
-		len = size & ~PAGE_CACHE_MASK;
+	if (page->index == size >> PAGE_SHIFT)
+		len = size & ~PAGE_MASK;
 	else
-		len = PAGE_CACHE_SIZE;
+		len = PAGE_SIZE;
 	/*
 	 * Return if we have all the buffers mapped. This avoids the need to do
 	 * journal_start/journal_stop which can block and take a long time
@@ -5320,7 +5565,7 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	unlock_page(page);
 	/* OK, we need to fill the hole... */
 	if (ext4_should_dioread_nolock(inode))
-		get_block = ext4_get_block_write;
+		get_block = ext4_get_block_unwritten;
 	else
 		get_block = ext4_get_block;
 retry_alloc:
@@ -5330,10 +5575,10 @@ retry_alloc:
 		ret = VM_FAULT_SIGBUS;
 		goto out;
 	}
-	ret = __block_page_mkwrite(vma, vmf, get_block);
+	ret = block_page_mkwrite(vma, vmf, get_block);
 	if (!ret && ext4_should_journal_data(inode)) {
 		if (ext4_walk_page_buffers(handle, page_buffers(page), 0,
-			  PAGE_CACHE_SIZE, NULL, do_journal_get_write_access)) {
+			  PAGE_SIZE, NULL, do_journal_get_write_access)) {
 			unlock_page(page);
 			ret = VM_FAULT_SIGBUS;
 			ext4_journal_stop(handle);
@@ -5347,6 +5592,86 @@ retry_alloc:
 out_ret:
 	ret = block_page_mkwrite_return(ret);
 out:
+	up_read(&EXT4_I(inode)->i_mmap_sem);
 	sb_end_pagefault(inode->i_sb);
 	return ret;
 }
+
+int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct inode *inode = file_inode(vma->vm_file);
+	int err;
+
+	down_read(&EXT4_I(inode)->i_mmap_sem);
+	err = filemap_fault(vma, vmf);
+	up_read(&EXT4_I(inode)->i_mmap_sem);
+
+	return err;
+}
+
+/*
+ * Find the first extent at or after @lblk in an inode that is not a hole.
+ * Search for @map_len blocks at most. The extent is returned in @result.
+ *
+ * The function returns 1 if we found an extent. The function returns 0 in
+ * case there is no extent at or after @lblk and in that case also sets
+ * @result->es_len to 0. In case of error, the error code is returned.
+ */
+int ext4_get_next_extent(struct inode *inode, ext4_lblk_t lblk,
+			 unsigned int map_len, struct extent_status *result)
+{
+	struct ext4_map_blocks map;
+	struct extent_status es = {};
+	int ret;
+
+	map.m_lblk = lblk;
+	map.m_len = map_len;
+
+	/*
+	 * For non-extent based files this loop may iterate several times since
+	 * we do not determine full hole size.
+	 */
+	while (map.m_len > 0) {
+		ret = ext4_map_blocks(NULL, inode, &map, 0);
+		if (ret < 0)
+			return ret;
+		/* There's extent covering m_lblk? Just return it. */
+		if (ret > 0) {
+			int status;
+
+			ext4_es_store_pblock(result, map.m_pblk);
+			result->es_lblk = map.m_lblk;
+			result->es_len = map.m_len;
+			if (map.m_flags & EXT4_MAP_UNWRITTEN)
+				status = EXTENT_STATUS_UNWRITTEN;
+			else
+				status = EXTENT_STATUS_WRITTEN;
+			ext4_es_store_status(result, status);
+			return 1;
+		}
+		ext4_es_find_delayed_extent_range(inode, map.m_lblk,
+						  map.m_lblk + map.m_len - 1,
+						  &es);
+		/* Is delalloc data before next block in extent tree? */
+		if (es.es_len && es.es_lblk < map.m_lblk + map.m_len) {
+			ext4_lblk_t offset = 0;
+
+			if (es.es_lblk < lblk)
+				offset = lblk - es.es_lblk;
+			result->es_lblk = es.es_lblk + offset;
+			ext4_es_store_pblock(result,
+					     ext4_es_pblock(&es) + offset);
+			result->es_len = es.es_len - offset;
+			ext4_es_store_status(result, ext4_es_status(&es));
+
+			return 1;
+		}
+		/* There's a hole at m_lblk, advance us after it */
+		map.m_lblk += map.m_len;
+		map_len -= map.m_len;
+		map.m_len = map_len;
+		cond_resched();
+	}
+	result->es_len = 0;
+	return 0;
+}
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 5e872fd40e5e..eae5917c534e 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -14,6 +14,7 @@
 #include <linux/mount.h>
 #include <linux/file.h>
 #include <linux/random.h>
+#include <linux/quotaops.h>
 #include <asm/uaccess.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
@@ -202,6 +203,238 @@ static int uuid_is_zero(__u8 u[16])
 	return 1;
 }
 
+static int ext4_ioctl_setflags(struct inode *inode,
+			       unsigned int flags)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	handle_t *handle = NULL;
+	int err = -EPERM, migrate = 0;
+	struct ext4_iloc iloc;
+	unsigned int oldflags, mask, i;
+	unsigned int jflag;
+
+	/* Is it quota file? Do not allow user to mess with it */
+	if (IS_NOQUOTA(inode))
+		goto flags_out;
+
+	oldflags = ei->i_flags;
+
+	/* The JOURNAL_DATA flag is modifiable only by root */
+	jflag = flags & EXT4_JOURNAL_DATA_FL;
+
+	/*
+	 * The IMMUTABLE and APPEND_ONLY flags can only be changed by
+	 * the relevant capability.
+	 *
+	 * This test looks nicer. Thanks to Pauline Middelink
+	 */
+	if ((flags ^ oldflags) & (EXT4_APPEND_FL | EXT4_IMMUTABLE_FL)) {
+		if (!capable(CAP_LINUX_IMMUTABLE))
+			goto flags_out;
+	}
+
+	/*
+	 * The JOURNAL_DATA flag can only be changed by
+	 * the relevant capability.
+	 */
+	if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
+		if (!capable(CAP_SYS_RESOURCE))
+			goto flags_out;
+	}
+	if ((flags ^ oldflags) & EXT4_EXTENTS_FL)
+		migrate = 1;
+
+	if (flags & EXT4_EOFBLOCKS_FL) {
+		/* we don't support adding EOFBLOCKS flag */
+		if (!(oldflags & EXT4_EOFBLOCKS_FL)) {
+			err = -EOPNOTSUPP;
+			goto flags_out;
+		}
+	} else if (oldflags & EXT4_EOFBLOCKS_FL)
+		ext4_truncate(inode);
+
+	handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
+	if (IS_ERR(handle)) {
+		err = PTR_ERR(handle);
+		goto flags_out;
+	}
+	if (IS_SYNC(inode))
+		ext4_handle_sync(handle);
+	err = ext4_reserve_inode_write(handle, inode, &iloc);
+	if (err)
+		goto flags_err;
+
+	for (i = 0, mask = 1; i < 32; i++, mask <<= 1) {
+		if (!(mask & EXT4_FL_USER_MODIFIABLE))
+			continue;
+		if (mask & flags)
+			ext4_set_inode_flag(inode, i);
+		else
+			ext4_clear_inode_flag(inode, i);
+	}
+
+	ext4_set_inode_flags(inode);
+	inode->i_ctime = ext4_current_time(inode);
+
+	err = ext4_mark_iloc_dirty(handle, inode, &iloc);
+flags_err:
+	ext4_journal_stop(handle);
+	if (err)
+		goto flags_out;
+
+	if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL))
+		err = ext4_change_inode_journal_flag(inode, jflag);
+	if (err)
+		goto flags_out;
+	if (migrate) {
+		if (flags & EXT4_EXTENTS_FL)
+			err = ext4_ext_migrate(inode);
+		else
+			err = ext4_ind_migrate(inode);
+	}
+
+flags_out:
+	return err;
+}
+
+#ifdef CONFIG_QUOTA
+static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
+{
+	struct inode *inode = file_inode(filp);
+	struct super_block *sb = inode->i_sb;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	int err, rc;
+	handle_t *handle;
+	kprojid_t kprojid;
+	struct ext4_iloc iloc;
+	struct ext4_inode *raw_inode;
+
+	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
+			EXT4_FEATURE_RO_COMPAT_PROJECT)) {
+		if (projid != EXT4_DEF_PROJID)
+			return -EOPNOTSUPP;
+		else
+			return 0;
+	}
+
+	if (EXT4_INODE_SIZE(sb) <= EXT4_GOOD_OLD_INODE_SIZE)
+		return -EOPNOTSUPP;
+
+	kprojid = make_kprojid(&init_user_ns, (projid_t)projid);
+
+	if (projid_eq(kprojid, EXT4_I(inode)->i_projid))
+		return 0;
+
+	err = mnt_want_write_file(filp);
+	if (err)
+		return err;
+
+	err = -EPERM;
+	inode_lock(inode);
+	/* Is it quota file? Do not allow user to mess with it */
+	if (IS_NOQUOTA(inode))
+		goto out_unlock;
+
+	err = ext4_get_inode_loc(inode, &iloc);
+	if (err)
+		goto out_unlock;
+
+	raw_inode = ext4_raw_inode(&iloc);
+	if (!EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) {
+		err = -EOVERFLOW;
+		brelse(iloc.bh);
+		goto out_unlock;
+	}
+	brelse(iloc.bh);
+
+	dquot_initialize(inode);
+
+	handle = ext4_journal_start(inode, EXT4_HT_QUOTA,
+		EXT4_QUOTA_INIT_BLOCKS(sb) +
+		EXT4_QUOTA_DEL_BLOCKS(sb) + 3);
+	if (IS_ERR(handle)) {
+		err = PTR_ERR(handle);
+		goto out_unlock;
+	}
+
+	err = ext4_reserve_inode_write(handle, inode, &iloc);
+	if (err)
+		goto out_stop;
+
+	if (sb_has_quota_limits_enabled(sb, PRJQUOTA)) {
+		struct dquot *transfer_to[MAXQUOTAS] = { };
+
+		transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid));
+		if (transfer_to[PRJQUOTA]) {
+			err = __dquot_transfer(inode, transfer_to);
+			dqput(transfer_to[PRJQUOTA]);
+			if (err)
+				goto out_dirty;
+		}
+	}
+	EXT4_I(inode)->i_projid = kprojid;
+	inode->i_ctime = ext4_current_time(inode);
+out_dirty:
+	rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
+	if (!err)
+		err = rc;
+out_stop:
+	ext4_journal_stop(handle);
+out_unlock:
+	inode_unlock(inode);
+	mnt_drop_write_file(filp);
+	return err;
+}
+#else
+static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
+{
+	if (projid != EXT4_DEF_PROJID)
+		return -EOPNOTSUPP;
+	return 0;
+}
+#endif
+
+/* Transfer internal flags to xflags */
+static inline __u32 ext4_iflags_to_xflags(unsigned long iflags)
+{
+	__u32 xflags = 0;
+
+	if (iflags & EXT4_SYNC_FL)
+		xflags |= FS_XFLAG_SYNC;
+	if (iflags & EXT4_IMMUTABLE_FL)
+		xflags |= FS_XFLAG_IMMUTABLE;
+	if (iflags & EXT4_APPEND_FL)
+		xflags |= FS_XFLAG_APPEND;
+	if (iflags & EXT4_NODUMP_FL)
+		xflags |= FS_XFLAG_NODUMP;
+	if (iflags & EXT4_NOATIME_FL)
+		xflags |= FS_XFLAG_NOATIME;
+	if (iflags & EXT4_PROJINHERIT_FL)
+		xflags |= FS_XFLAG_PROJINHERIT;
+	return xflags;
+}
+
+/* Transfer xflags flags to internal */
+static inline unsigned long ext4_xflags_to_iflags(__u32 xflags)
+{
+	unsigned long iflags = 0;
+
+	if (xflags & FS_XFLAG_SYNC)
+		iflags |= EXT4_SYNC_FL;
+	if (xflags & FS_XFLAG_IMMUTABLE)
+		iflags |= EXT4_IMMUTABLE_FL;
+	if (xflags & FS_XFLAG_APPEND)
+		iflags |= EXT4_APPEND_FL;
+	if (xflags & FS_XFLAG_NODUMP)
+		iflags |= EXT4_NODUMP_FL;
+	if (xflags & FS_XFLAG_NOATIME)
+		iflags |= EXT4_NOATIME_FL;
+	if (xflags & FS_XFLAG_PROJINHERIT)
+		iflags |= EXT4_PROJINHERIT_FL;
+
+	return iflags;
+}
+
 long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
@@ -217,11 +450,7 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
 		return put_user(flags, (int __user *) arg);
 	case EXT4_IOC_SETFLAGS: {
-		handle_t *handle = NULL;
-		int err, migrate = 0;
-		struct ext4_iloc iloc;
-		unsigned int oldflags, mask, i;
-		unsigned int jflag;
+		int err;
 
 		if (!inode_owner_or_capable(inode))
 			return -EACCES;
@@ -235,90 +464,9 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 
 		flags = ext4_mask_flags(inode->i_mode, flags);
 
-		err = -EPERM;
-		mutex_lock(&inode->i_mutex);
-		/* Is it quota file? Do not allow user to mess with it */
-		if (IS_NOQUOTA(inode))
-			goto flags_out;
-
-		oldflags = ei->i_flags;
-
-		/* The JOURNAL_DATA flag is modifiable only by root */
-		jflag = flags & EXT4_JOURNAL_DATA_FL;
-
-		/*
-		 * The IMMUTABLE and APPEND_ONLY flags can only be changed by
-		 * the relevant capability.
-		 *
-		 * This test looks nicer. Thanks to Pauline Middelink
-		 */
-		if ((flags ^ oldflags) & (EXT4_APPEND_FL | EXT4_IMMUTABLE_FL)) {
-			if (!capable(CAP_LINUX_IMMUTABLE))
-				goto flags_out;
-		}
-
-		/*
-		 * The JOURNAL_DATA flag can only be changed by
-		 * the relevant capability.
-		 */
-		if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
-			if (!capable(CAP_SYS_RESOURCE))
-				goto flags_out;
-		}
-		if ((flags ^ oldflags) & EXT4_EXTENTS_FL)
-			migrate = 1;
-
-		if (flags & EXT4_EOFBLOCKS_FL) {
-			/* we don't support adding EOFBLOCKS flag */
-			if (!(oldflags & EXT4_EOFBLOCKS_FL)) {
-				err = -EOPNOTSUPP;
-				goto flags_out;
-			}
-		} else if (oldflags & EXT4_EOFBLOCKS_FL)
-			ext4_truncate(inode);
-
-		handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
-		if (IS_ERR(handle)) {
-			err = PTR_ERR(handle);
-			goto flags_out;
-		}
-		if (IS_SYNC(inode))
-			ext4_handle_sync(handle);
-		err = ext4_reserve_inode_write(handle, inode, &iloc);
-		if (err)
-			goto flags_err;
-
-		for (i = 0, mask = 1; i < 32; i++, mask <<= 1) {
-			if (!(mask & EXT4_FL_USER_MODIFIABLE))
-				continue;
-			if (mask & flags)
-				ext4_set_inode_flag(inode, i);
-			else
-				ext4_clear_inode_flag(inode, i);
-		}
-
-		ext4_set_inode_flags(inode);
-		inode->i_ctime = ext4_current_time(inode);
-
-		err = ext4_mark_iloc_dirty(handle, inode, &iloc);
-flags_err:
-		ext4_journal_stop(handle);
-		if (err)
-			goto flags_out;
-
-		if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL))
-			err = ext4_change_inode_journal_flag(inode, jflag);
-		if (err)
-			goto flags_out;
-		if (migrate) {
-			if (flags & EXT4_EXTENTS_FL)
-				err = ext4_ext_migrate(inode);
-			else
-				err = ext4_ind_migrate(inode);
-		}
-
-flags_out:
-		mutex_unlock(&inode->i_mutex);
+		inode_lock(inode);
+		err = ext4_ioctl_setflags(inode, flags);
+		inode_unlock(inode);
 		mnt_drop_write_file(filp);
 		return err;
 	}
@@ -349,7 +497,7 @@ flags_out:
 			goto setversion_out;
 		}
 
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
 		if (IS_ERR(handle)) {
 			err = PTR_ERR(handle);
@@ -364,7 +512,7 @@ flags_out:
 		ext4_journal_stop(handle);
 
 unlock_out:
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 setversion_out:
 		mnt_drop_write_file(filp);
 		return err;
@@ -435,6 +583,11 @@ group_extend_out:
 				 "Online defrag not supported with bigalloc");
 			err = -EOPNOTSUPP;
 			goto mext_out;
+		} else if (IS_DAX(inode)) {
+			ext4_msg(sb, KERN_ERR,
+				 "Online defrag not supported with DAX");
+			err = -EOPNOTSUPP;
+			goto mext_out;
 		}
 
 		err = mnt_want_write_file(filp);
@@ -510,9 +663,9 @@ group_add_out:
 		 * ext4_ext_swap_inode_data before we switch the
 		 * inode format to prevent read.
 		 */
-		mutex_lock(&(inode->i_mutex));
+		inode_lock((inode));
 		err = ext4_ext_migrate(inode);
-		mutex_unlock(&(inode->i_mutex));
+		inode_unlock((inode));
 		mnt_drop_write_file(filp);
 		return err;
 	}
@@ -689,6 +842,60 @@ encryption_policy_out:
 		return -EOPNOTSUPP;
 #endif
 	}
+	case EXT4_IOC_FSGETXATTR:
+	{
+		struct fsxattr fa;
+
+		memset(&fa, 0, sizeof(struct fsxattr));
+		ext4_get_inode_flags(ei);
+		fa.fsx_xflags = ext4_iflags_to_xflags(ei->i_flags & EXT4_FL_USER_VISIBLE);
+
+		if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
+				EXT4_FEATURE_RO_COMPAT_PROJECT)) {
+			fa.fsx_projid = (__u32)from_kprojid(&init_user_ns,
+				EXT4_I(inode)->i_projid);
+		}
+
+		if (copy_to_user((struct fsxattr __user *)arg,
+				 &fa, sizeof(fa)))
+			return -EFAULT;
+		return 0;
+	}
+	case EXT4_IOC_FSSETXATTR:
+	{
+		struct fsxattr fa;
+		int err;
+
+		if (copy_from_user(&fa, (struct fsxattr __user *)arg,
+				   sizeof(fa)))
+			return -EFAULT;
+
+		/* Make sure caller has proper permission */
+		if (!inode_owner_or_capable(inode))
+			return -EACCES;
+
+		err = mnt_want_write_file(filp);
+		if (err)
+			return err;
+
+		flags = ext4_xflags_to_iflags(fa.fsx_xflags);
+		flags = ext4_mask_flags(inode->i_mode, flags);
+
+		inode_lock(inode);
+		flags = (ei->i_flags & ~EXT4_FL_XFLAG_VISIBLE) |
+			 (flags & EXT4_FL_XFLAG_VISIBLE);
+		err = ext4_ioctl_setflags(inode, flags);
+		inode_unlock(inode);
+		mnt_drop_write_file(filp);
+		if (err)
+			return err;
+
+		err = ext4_ioctl_setproject(filp, fa.fsx_projid);
+		if (err)
+			return err;
+
+		return 0;
+	}
 	default:
 		return -ENOTTY;
 	}
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index b4b3c1f91814..eeeade76012e 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -11,7 +11,7 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public Licens
+ * You should have received a copy of the GNU General Public License
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-
  */
@@ -119,7 +119,7 @@ MODULE_PARM_DESC(mballoc_debug, "Debugging level for ext4's mballoc");
  *
  *
  * one block each for bitmap and buddy information.  So for each group we
- * take up 2 blocks. A page can contain blocks_per_page (PAGE_CACHE_SIZE /
+ * take up 2 blocks. A page can contain blocks_per_page (PAGE_SIZE /
  * blocksize) blocks.  So it can have information regarding groups_per_page
  * which is blocks_per_page/2
  *
@@ -807,7 +807,7 @@ static void mb_regenerate_buddy(struct ext4_buddy *e4b)
  *
  * one block each for bitmap and buddy information.
  * So for each group we take up 2 blocks. A page can
- * contain blocks_per_page (PAGE_CACHE_SIZE / blocksize)  blocks.
+ * contain blocks_per_page (PAGE_SIZE / blocksize)  blocks.
  * So it can have information regarding groups_per_page which
  * is blocks_per_page/2
  *
@@ -815,7 +815,7 @@ static void mb_regenerate_buddy(struct ext4_buddy *e4b)
  * for this page; do not hold this lock when calling this routine!
  */
 
-static int ext4_mb_init_cache(struct page *page, char *incore)
+static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp)
 {
 	ext4_group_t ngroups;
 	int blocksize;
@@ -839,7 +839,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 	sb = inode->i_sb;
 	ngroups = ext4_get_groups_count(sb);
 	blocksize = 1 << inode->i_blkbits;
-	blocks_per_page = PAGE_CACHE_SIZE / blocksize;
+	blocks_per_page = PAGE_SIZE / blocksize;
 
 	groups_per_page = blocks_per_page >> 1;
 	if (groups_per_page == 0)
@@ -848,7 +848,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 	/* allocate buffer_heads to read bitmaps */
 	if (groups_per_page > 1) {
 		i = sizeof(struct buffer_head *) * groups_per_page;
-		bh = kzalloc(i, GFP_NOFS);
+		bh = kzalloc(i, gfp);
 		if (bh == NULL) {
 			err = -ENOMEM;
 			goto out;
@@ -983,7 +983,7 @@ out:
  * are on the same page e4b->bd_buddy_page is NULL and return value is 0.
  */
 static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
-		ext4_group_t group, struct ext4_buddy *e4b)
+		ext4_group_t group, struct ext4_buddy *e4b, gfp_t gfp)
 {
 	struct inode *inode = EXT4_SB(sb)->s_buddy_cache;
 	int block, pnum, poff;
@@ -993,7 +993,7 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
 	e4b->bd_buddy_page = NULL;
 	e4b->bd_bitmap_page = NULL;
 
-	blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
+	blocks_per_page = PAGE_SIZE / sb->s_blocksize;
 	/*
 	 * the buddy cache inode stores the block bitmap
 	 * and buddy information in consecutive blocks.
@@ -1002,7 +1002,7 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
 	block = group * 2;
 	pnum = block / blocks_per_page;
 	poff = block % blocks_per_page;
-	page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+	page = find_or_create_page(inode->i_mapping, pnum, gfp);
 	if (!page)
 		return -ENOMEM;
 	BUG_ON(page->mapping != inode->i_mapping);
@@ -1016,7 +1016,7 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
 
 	block++;
 	pnum = block / blocks_per_page;
-	page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+	page = find_or_create_page(inode->i_mapping, pnum, gfp);
 	if (!page)
 		return -ENOMEM;
 	BUG_ON(page->mapping != inode->i_mapping);
@@ -1028,11 +1028,11 @@ static void ext4_mb_put_buddy_page_lock(struct ext4_buddy *e4b)
 {
 	if (e4b->bd_bitmap_page) {
 		unlock_page(e4b->bd_bitmap_page);
-		page_cache_release(e4b->bd_bitmap_page);
+		put_page(e4b->bd_bitmap_page);
 	}
 	if (e4b->bd_buddy_page) {
 		unlock_page(e4b->bd_buddy_page);
-		page_cache_release(e4b->bd_buddy_page);
+		put_page(e4b->bd_buddy_page);
 	}
 }
 
@@ -1042,7 +1042,7 @@ static void ext4_mb_put_buddy_page_lock(struct ext4_buddy *e4b)
  * calling this routine!
  */
 static noinline_for_stack
-int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
+int ext4_mb_init_group(struct super_block *sb, ext4_group_t group, gfp_t gfp)
 {
 
 	struct ext4_group_info *this_grp;
@@ -1062,7 +1062,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
 	 * The call to ext4_mb_get_buddy_page_lock will mark the
 	 * page accessed.
 	 */
-	ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b);
+	ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b, gfp);
 	if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) {
 		/*
 		 * somebody initialized the group
@@ -1072,7 +1072,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
 	}
 
 	page = e4b.bd_bitmap_page;
-	ret = ext4_mb_init_cache(page, NULL);
+	ret = ext4_mb_init_cache(page, NULL, gfp);
 	if (ret)
 		goto err;
 	if (!PageUptodate(page)) {
@@ -1091,7 +1091,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
 	}
 	/* init buddy cache */
 	page = e4b.bd_buddy_page;
-	ret = ext4_mb_init_cache(page, e4b.bd_bitmap);
+	ret = ext4_mb_init_cache(page, e4b.bd_bitmap, gfp);
 	if (ret)
 		goto err;
 	if (!PageUptodate(page)) {
@@ -1109,8 +1109,8 @@ err:
  * calling this routine!
  */
 static noinline_for_stack int
-ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
-					struct ext4_buddy *e4b)
+ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group,
+		       struct ext4_buddy *e4b, gfp_t gfp)
 {
 	int blocks_per_page;
 	int block;
@@ -1125,7 +1125,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
 	might_sleep();
 	mb_debug(1, "load group %u\n", group);
 
-	blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
+	blocks_per_page = PAGE_SIZE / sb->s_blocksize;
 	grp = ext4_get_group_info(sb, group);
 
 	e4b->bd_blkbits = sb->s_blocksize_bits;
@@ -1140,7 +1140,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
 		 * we need full data about the group
 		 * to make a good selection
 		 */
-		ret = ext4_mb_init_group(sb, group);
+		ret = ext4_mb_init_group(sb, group, gfp);
 		if (ret)
 			return ret;
 	}
@@ -1167,12 +1167,12 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
 			 * is yet to initialize the same. So
 			 * wait for it to initialize.
 			 */
-			page_cache_release(page);
-		page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+			put_page(page);
+		page = find_or_create_page(inode->i_mapping, pnum, gfp);
 		if (page) {
 			BUG_ON(page->mapping != inode->i_mapping);
 			if (!PageUptodate(page)) {
-				ret = ext4_mb_init_cache(page, NULL);
+				ret = ext4_mb_init_cache(page, NULL, gfp);
 				if (ret) {
 					unlock_page(page);
 					goto err;
@@ -1203,12 +1203,13 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
 	page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED);
 	if (page == NULL || !PageUptodate(page)) {
 		if (page)
-			page_cache_release(page);
-		page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+			put_page(page);
+		page = find_or_create_page(inode->i_mapping, pnum, gfp);
 		if (page) {
 			BUG_ON(page->mapping != inode->i_mapping);
 			if (!PageUptodate(page)) {
-				ret = ext4_mb_init_cache(page, e4b->bd_bitmap);
+				ret = ext4_mb_init_cache(page, e4b->bd_bitmap,
+							 gfp);
 				if (ret) {
 					unlock_page(page);
 					goto err;
@@ -1237,22 +1238,28 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
 
 err:
 	if (page)
-		page_cache_release(page);
+		put_page(page);
 	if (e4b->bd_bitmap_page)
-		page_cache_release(e4b->bd_bitmap_page);
+		put_page(e4b->bd_bitmap_page);
 	if (e4b->bd_buddy_page)
-		page_cache_release(e4b->bd_buddy_page);
+		put_page(e4b->bd_buddy_page);
 	e4b->bd_buddy = NULL;
 	e4b->bd_bitmap = NULL;
 	return ret;
 }
 
+static int ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
+			      struct ext4_buddy *e4b)
+{
+	return ext4_mb_load_buddy_gfp(sb, group, e4b, GFP_NOFS);
+}
+
 static void ext4_mb_unload_buddy(struct ext4_buddy *e4b)
 {
 	if (e4b->bd_bitmap_page)
-		page_cache_release(e4b->bd_bitmap_page);
+		put_page(e4b->bd_bitmap_page);
 	if (e4b->bd_buddy_page)
-		page_cache_release(e4b->bd_buddy_page);
+		put_page(e4b->bd_buddy_page);
 }
 
 
@@ -2045,7 +2052,7 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac,
 
 	/* We only do this if the grp has never been initialized */
 	if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
-		int ret = ext4_mb_init_group(ac->ac_sb, group);
+		int ret = ext4_mb_init_group(ac->ac_sb, group, GFP_NOFS);
 		if (ret)
 			return ret;
 	}
@@ -2285,7 +2292,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 	if (group == 0)
 		seq_puts(seq, "#group: free  frags first ["
 			      " 2^0   2^1   2^2   2^3   2^4   2^5   2^6  "
-			      " 2^7   2^8   2^9   2^10  2^11  2^12  2^13  ]");
+			      " 2^7   2^8   2^9   2^10  2^11  2^12  2^13  ]\n");
 
 	i = (sb->s_blocksize_bits + 2) * sizeof(sg.info.bb_counters[0]) +
 		sizeof(struct ext4_group_info);
@@ -2826,8 +2833,8 @@ static void ext4_free_data_callback(struct super_block *sb,
 		/* No more items in the per group rb tree
 		 * balance refcounts from ext4_mb_free_metadata()
 		 */
-		page_cache_release(e4b.bd_buddy_page);
-		page_cache_release(e4b.bd_bitmap_page);
+		put_page(e4b.bd_buddy_page);
+		put_page(e4b.bd_bitmap_page);
 	}
 	ext4_unlock_group(sb, entry->efd_group);
 	kmem_cache_free(ext4_free_data_cachep, entry);
@@ -3333,8 +3340,8 @@ ext4_mb_check_group_pa(ext4_fsblk_t goal_block,
 		atomic_inc(&pa->pa_count);
 		return pa;
 	}
-	cur_distance = abs64(goal_block - cpa->pa_pstart);
-	new_distance = abs64(goal_block - pa->pa_pstart);
+	cur_distance = abs(goal_block - cpa->pa_pstart);
+	new_distance = abs(goal_block - pa->pa_pstart);
 
 	if (cur_distance <= new_distance)
 		return cpa;
@@ -4378,9 +4385,9 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac)
 		ext4_mb_put_pa(ac, ac->ac_sb, pa);
 	}
 	if (ac->ac_bitmap_page)
-		page_cache_release(ac->ac_bitmap_page);
+		put_page(ac->ac_bitmap_page);
 	if (ac->ac_buddy_page)
-		page_cache_release(ac->ac_buddy_page);
+		put_page(ac->ac_buddy_page);
 	if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC)
 		mutex_unlock(&ac->ac_lg->lg_mutex);
 	ext4_mb_collect_stats(ac);
@@ -4592,8 +4599,8 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 		 * otherwise we'll refresh it from
 		 * on-disk bitmap and lose not-yet-available
 		 * blocks */
-		page_cache_get(e4b->bd_buddy_page);
-		page_cache_get(e4b->bd_bitmap_page);
+		get_page(e4b->bd_buddy_page);
+		get_page(e4b->bd_bitmap_page);
 	}
 	while (*n) {
 		parent = *n;
@@ -4695,16 +4702,6 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 	}
 
 	/*
-	 * We need to make sure we don't reuse the freed block until
-	 * after the transaction is committed, which we can do by
-	 * treating the block as metadata, below.  We make an
-	 * exception if the inode is to be written in writeback mode
-	 * since writeback mode has weak data consistency guarantees.
-	 */
-	if (!ext4_should_writeback_data(inode))
-		flags |= EXT4_FREE_BLOCKS_METADATA;
-
-	/*
 	 * If the extent to be freed does not begin on a cluster
 	 * boundary, we need to deal with partial clusters at the
 	 * beginning and end of the extent.  Normally we will free
@@ -4738,14 +4735,13 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 
 	if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) {
 		int i;
+		int is_metadata = flags & EXT4_FREE_BLOCKS_METADATA;
 
 		for (i = 0; i < count; i++) {
 			cond_resched();
-			bh = sb_find_get_block(inode->i_sb, block + i);
-			if (!bh)
-				continue;
-			ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA,
-				    inode, bh, block + i);
+			if (is_metadata)
+				bh = sb_find_get_block(inode->i_sb, block + i);
+			ext4_forget(handle, is_metadata, inode, bh, block + i);
 		}
 	}
 
@@ -4815,16 +4811,23 @@ do_more:
 #endif
 	trace_ext4_mballoc_free(sb, inode, block_group, bit, count_clusters);
 
-	err = ext4_mb_load_buddy(sb, block_group, &e4b);
+	/* __GFP_NOFAIL: retry infinitely, ignore TIF_MEMDIE and memcg limit. */
+	err = ext4_mb_load_buddy_gfp(sb, block_group, &e4b,
+				     GFP_NOFS|__GFP_NOFAIL);
 	if (err)
 		goto error_return;
 
-	if ((flags & EXT4_FREE_BLOCKS_METADATA) && ext4_handle_valid(handle)) {
+	/*
+	 * We need to make sure we don't reuse the freed block until after the
+	 * transaction is committed. We make an exception if the inode is to be
+	 * written in writeback mode since writeback mode has weak data
+	 * consistency guarantees.
+	 */
+	if (ext4_handle_valid(handle) &&
+	    ((flags & EXT4_FREE_BLOCKS_METADATA) ||
+	     !ext4_should_writeback_data(inode))) {
 		struct ext4_free_data *new_entry;
 		/*
-		 * blocks being freed are metadata. these blocks shouldn't
-		 * be used until this transaction is committed
-		 *
 		 * We use __GFP_NOFAIL because ext4_free_blocks() is not allowed
 		 * to fail.
 		 */
@@ -5217,7 +5220,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 		grp = ext4_get_group_info(sb, group);
 		/* We only do this if the grp has never been initialized */
 		if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
-			ret = ext4_mb_init_group(sb, group);
+			ret = ext4_mb_init_group(sb, group, GFP_NOFS);
 			if (ret)
 				break;
 		}
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index d634e183b4d4..3ef1df6ae9ec 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -23,18 +23,6 @@
 #include "ext4.h"
 
 /*
- * with AGGRESSIVE_CHECK allocator runs consistency checks over
- * structures. these checks slow things down a lot
- */
-#define AGGRESSIVE_CHECK__
-
-/*
- * with DOUBLE_CHECK defined mballoc creates persistent in-core
- * bitmaps, maintains and uses them to check for double allocations
- */
-#define DOUBLE_CHECK__
-
-/*
  */
 #ifdef CONFIG_EXT4_DEBUG
 extern ushort ext4_mballoc_debug;
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index a4651894cc33..364ea4d4a943 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -361,7 +361,7 @@ static int ext4_ext_swap_inode_data(handle_t *handle, struct inode *inode,
 	 * blocks.
 	 *
 	 * While converting to extents we need not
-	 * update the orignal inode i_blocks for extent blocks
+	 * update the original inode i_blocks for extent blocks
 	 * via quota APIs. The quota update happened via tmp_inode already.
 	 */
 	spin_lock(&inode->i_lock);
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 0a512aa81bf7..24445275d330 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -91,21 +91,22 @@ static int read_mmp_block(struct super_block *sb, struct buffer_head **bh,
 	submit_bh(READ_SYNC | REQ_META | REQ_PRIO, *bh);
 	wait_on_buffer(*bh);
 	if (!buffer_uptodate(*bh)) {
-		brelse(*bh);
-		*bh = NULL;
 		ret = -EIO;
 		goto warn_exit;
 	}
-
 	mmp = (struct mmp_struct *)((*bh)->b_data);
-	if (le32_to_cpu(mmp->mmp_magic) != EXT4_MMP_MAGIC)
+	if (le32_to_cpu(mmp->mmp_magic) != EXT4_MMP_MAGIC) {
 		ret = -EFSCORRUPTED;
-	else if (!ext4_mmp_csum_verify(sb, mmp))
+		goto warn_exit;
+	}
+	if (!ext4_mmp_csum_verify(sb, mmp)) {
 		ret = -EFSBADCRC;
-	else
-		return 0;
-
+		goto warn_exit;
+	}
+	return 0;
 warn_exit:
+	brelse(*bh);
+	*bh = NULL;
 	ext4_warning(sb, "Error %d while reading MMP block %llu",
 		     ret, mmp_block);
 	return ret;
@@ -181,15 +182,13 @@ static int kmmpd(void *data)
 		    EXT4_FEATURE_INCOMPAT_MMP)) {
 			ext4_warning(sb, "kmmpd being stopped since MMP feature"
 				     " has been disabled.");
-			EXT4_SB(sb)->s_mmp_tsk = NULL;
-			goto failed;
+			goto exit_thread;
 		}
 
 		if (sb->s_flags & MS_RDONLY) {
 			ext4_warning(sb, "kmmpd being stopped since filesystem "
 				     "has been remounted as readonly.");
-			EXT4_SB(sb)->s_mmp_tsk = NULL;
-			goto failed;
+			goto exit_thread;
 		}
 
 		diff = jiffies - last_update_time;
@@ -211,9 +210,7 @@ static int kmmpd(void *data)
 			if (retval) {
 				ext4_error(sb, "error reading MMP data: %d",
 					   retval);
-
-				EXT4_SB(sb)->s_mmp_tsk = NULL;
-				goto failed;
+				goto exit_thread;
 			}
 
 			mmp_check = (struct mmp_struct *)(bh_check->b_data);
@@ -225,7 +222,9 @@ static int kmmpd(void *data)
 					     "The filesystem seems to have been"
 					     " multiply mounted.");
 				ext4_error(sb, "abort");
-				goto failed;
+				put_bh(bh_check);
+				retval = -EBUSY;
+				goto exit_thread;
 			}
 			put_bh(bh_check);
 		}
@@ -248,7 +247,8 @@ static int kmmpd(void *data)
 
 	retval = write_mmp_block(sb, bh);
 
-failed:
+exit_thread:
+	EXT4_SB(sb)->s_mmp_tsk = NULL;
 	kfree(data);
 	brelse(bh);
 	return retval;
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index fb6f11709ae6..325cef48b39a 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -60,10 +60,10 @@ ext4_double_down_write_data_sem(struct inode *first, struct inode *second)
 {
 	if (first < second) {
 		down_write(&EXT4_I(first)->i_data_sem);
-		down_write_nested(&EXT4_I(second)->i_data_sem, SINGLE_DEPTH_NESTING);
+		down_write_nested(&EXT4_I(second)->i_data_sem, I_DATA_SEM_OTHER);
 	} else {
 		down_write(&EXT4_I(second)->i_data_sem);
-		down_write_nested(&EXT4_I(first)->i_data_sem, SINGLE_DEPTH_NESTING);
+		down_write_nested(&EXT4_I(first)->i_data_sem, I_DATA_SEM_OTHER);
 
 	}
 }
@@ -156,7 +156,7 @@ mext_page_double_lock(struct inode *inode1, struct inode *inode2,
 	page[1] = grab_cache_page_write_begin(mapping[1], index2, fl);
 	if (!page[1]) {
 		unlock_page(page[0]);
-		page_cache_release(page[0]);
+		put_page(page[0]);
 		return -ENOMEM;
 	}
 	/*
@@ -192,7 +192,7 @@ mext_page_mkuptodate(struct page *page, unsigned from, unsigned to)
 		create_empty_buffers(page, blocksize, 0);
 
 	head = page_buffers(page);
-	block = (sector_t)page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+	block = (sector_t)page->index << (PAGE_SHIFT - inode->i_blkbits);
 	for (bh = head, block_start = 0; bh != head || !block_start;
 	     block++, block_start = block_end, bh = bh->b_this_page) {
 		block_end = block_start + blocksize;
@@ -265,11 +265,12 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
 	ext4_lblk_t orig_blk_offset, donor_blk_offset;
 	unsigned long blocksize = orig_inode->i_sb->s_blocksize;
 	unsigned int tmp_data_size, data_size, replaced_size;
-	int err2, jblocks, retries = 0;
+	int i, err2, jblocks, retries = 0;
 	int replaced_count = 0;
 	int from = data_offset_in_page << orig_inode->i_blkbits;
-	int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
+	int blocks_per_page = PAGE_SIZE >> orig_inode->i_blkbits;
 	struct super_block *sb = orig_inode->i_sb;
+	struct buffer_head *bh = NULL;
 
 	/*
 	 * It needs twice the amount of ordinary journal buffers because
@@ -380,8 +381,17 @@ data_copy:
 	}
 	/* Perform all necessary steps similar write_begin()/write_end()
 	 * but keeping in mind that i_size will not change */
-	*err = __block_write_begin(pagep[0], from, replaced_size,
-				   ext4_get_block);
+	if (!page_has_buffers(pagep[0]))
+		create_empty_buffers(pagep[0], 1 << orig_inode->i_blkbits, 0);
+	bh = page_buffers(pagep[0]);
+	for (i = 0; i < data_offset_in_page; i++)
+		bh = bh->b_this_page;
+	for (i = 0; i < block_len_in_page; i++) {
+		*err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0);
+		if (*err < 0)
+			break;
+		bh = bh->b_this_page;
+	}
 	if (!*err)
 		*err = block_commit_write(pagep[0], from, from + replaced_size);
 
@@ -394,9 +404,9 @@ data_copy:
 
 unlock_pages:
 	unlock_page(pagep[0]);
-	page_cache_release(pagep[0]);
+	put_page(pagep[0]);
 	unlock_page(pagep[1]);
-	page_cache_release(pagep[1]);
+	put_page(pagep[1]);
 stop_journal:
 	ext4_journal_stop(handle);
 	if (*err == -ENOSPC &&
@@ -474,6 +484,13 @@ mext_check_arguments(struct inode *orig_inode,
 		return -EBUSY;
 	}
 
+	if (IS_NOQUOTA(orig_inode) || IS_NOQUOTA(donor_inode)) {
+		ext4_debug("ext4 move extent: The argument files should "
+			"not be quota files [ino:orig %lu, donor %lu]\n",
+			orig_inode->i_ino, donor_inode->i_ino);
+		return -EBUSY;
+	}
+
 	/* Ext4 move extent supports only extent based file */
 	if (!(ext4_test_inode_flag(orig_inode, EXT4_INODE_EXTENTS))) {
 		ext4_debug("ext4 move extent: orig file is not extents "
@@ -544,7 +561,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
 	struct inode *orig_inode = file_inode(o_filp);
 	struct inode *donor_inode = file_inode(d_filp);
 	struct ext4_ext_path *path = NULL;
-	int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
+	int blocks_per_page = PAGE_SIZE >> orig_inode->i_blkbits;
 	ext4_lblk_t o_end, o_start = orig_blk;
 	ext4_lblk_t d_start = donor_blk;
 	int ret;
@@ -638,9 +655,9 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
 		if (o_end - o_start < cur_len)
 			cur_len = o_end - o_start;
 
-		orig_page_index = o_start >> (PAGE_CACHE_SHIFT -
+		orig_page_index = o_start >> (PAGE_SHIFT -
 					       orig_inode->i_blkbits);
-		donor_page_index = d_start >> (PAGE_CACHE_SHIFT -
+		donor_page_index = d_start >> (PAGE_SHIFT -
 					       donor_inode->i_blkbits);
 		offset_in_page = o_start % blocks_per_page;
 		if (cur_len > blocks_per_page- offset_in_page)
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index a969ab39f302..48e4b8907826 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -273,7 +273,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir,
 		struct ext4_filename *fname,
 		struct ext4_dir_entry_2 **res_dir);
 static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname,
-			     struct dentry *dentry, struct inode *inode);
+			     struct inode *dir, struct inode *inode);
 
 /* checksumming functions */
 void initialize_dirent_tail(struct ext4_dir_entry_tail *t,
@@ -1558,6 +1558,24 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
 	struct ext4_dir_entry_2 *de;
 	struct buffer_head *bh;
 
+       if (ext4_encrypted_inode(dir)) {
+               int res = ext4_get_encryption_info(dir);
+
+		/*
+		 * This should be a properly defined flag for
+		 * dentry->d_flags when we uplift this to the VFS.
+		 * d_fsdata is set to (void *) 1 if if the dentry is
+		 * created while the directory was encrypted and we
+		 * don't have access to the key.
+		 */
+	       dentry->d_fsdata = NULL;
+	       if (ext4_encryption_info(dir))
+		       dentry->d_fsdata = (void *) 1;
+	       d_set_d_op(dentry, &ext4_encrypted_d_ops);
+	       if (res && res != -ENOKEY)
+		       return ERR_PTR(res);
+       }
+
 	if (dentry->d_name.len > EXT4_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
@@ -1585,11 +1603,15 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
 			return ERR_PTR(-EFSCORRUPTED);
 		}
 		if (!IS_ERR(inode) && ext4_encrypted_inode(dir) &&
-		    (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-		     S_ISLNK(inode->i_mode)) &&
+		    (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
 		    !ext4_is_child_context_consistent_with_parent(dir,
 								  inode)) {
+			int nokey = ext4_encrypted_inode(inode) &&
+				!ext4_encryption_info(inode);
+
 			iput(inode);
+			if (nokey)
+				return ERR_PTR(-ENOKEY);
 			ext4_warning(inode->i_sb,
 				     "Inconsistent encryption contexts: %lu/%lu\n",
 				     (unsigned long) dir->i_ino,
@@ -1928,10 +1950,9 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname,
  * directory, and adds the dentry to the indexed directory.
  */
 static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname,
-			    struct dentry *dentry,
+			    struct inode *dir,
 			    struct inode *inode, struct buffer_head *bh)
 {
-	struct inode	*dir = d_inode(dentry->d_parent);
 	struct buffer_head *bh2;
 	struct dx_root	*root;
 	struct dx_frame	frames[2], *frame;
@@ -2086,8 +2107,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 		return retval;
 
 	if (ext4_has_inline_data(dir)) {
-		retval = ext4_try_add_inline_entry(handle, &fname,
-						   dentry, inode);
+		retval = ext4_try_add_inline_entry(handle, &fname, dir, inode);
 		if (retval < 0)
 			goto out;
 		if (retval == 1) {
@@ -2097,7 +2117,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 	}
 
 	if (is_dx(dir)) {
-		retval = ext4_dx_add_entry(handle, &fname, dentry, inode);
+		retval = ext4_dx_add_entry(handle, &fname, dir, inode);
 		if (!retval || (retval != ERR_BAD_DX_DIR))
 			goto out;
 		ext4_clear_inode_flag(dir, EXT4_INODE_INDEX);
@@ -2119,7 +2139,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 
 		if (blocks == 1 && !dx_fallback &&
 		    ext4_has_feature_dir_index(sb)) {
-			retval = make_indexed_dir(handle, &fname, dentry,
+			retval = make_indexed_dir(handle, &fname, dir,
 						  inode, bh);
 			bh = NULL; /* make_indexed_dir releases bh */
 			goto out;
@@ -2154,12 +2174,11 @@ out:
  * Returns 0 for success, or a negative error value
  */
 static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname,
-			     struct dentry *dentry, struct inode *inode)
+			     struct inode *dir, struct inode *inode)
 {
 	struct dx_frame frames[2], *frame;
 	struct dx_entry *entries, *at;
 	struct buffer_head *bh;
-	struct inode *dir = d_inode(dentry->d_parent);
 	struct super_block *sb = dir->i_sb;
 	struct ext4_dir_entry_2 *de;
 	int err;
@@ -2756,7 +2775,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
 		return 0;
 
 	WARN_ON_ONCE(!(inode->i_state & (I_NEW | I_FREEING)) &&
-		     !mutex_is_locked(&inode->i_mutex));
+		     !inode_is_locked(inode));
 	/*
 	 * Exit early if inode already is on orphan list. This is a big speedup
 	 * since we don't have to contend on the global s_orphan_lock.
@@ -2838,7 +2857,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
 		return 0;
 
 	WARN_ON_ONCE(!(inode->i_state & (I_NEW | I_FREEING)) &&
-		     !mutex_is_locked(&inode->i_mutex));
+		     !inode_is_locked(inode));
 	/* Do this quick check before taking global s_orphan_lock. */
 	if (list_empty(&ei->i_orphan))
 		return 0;
@@ -3132,6 +3151,7 @@ static int ext4_symlink(struct inode *dir,
 	if ((disk_link.len > EXT4_N_BLOCKS * 4)) {
 		if (!encryption_required)
 			inode->i_op = &ext4_symlink_inode_operations;
+		inode_nohighmem(inode);
 		ext4_set_aops(inode);
 		/*
 		 * We cannot call page_symlink() with transaction started
@@ -3211,6 +3231,12 @@ static int ext4_link(struct dentry *old_dentry,
 	if (ext4_encrypted_inode(dir) &&
 	    !ext4_is_child_context_consistent_with_parent(dir, inode))
 		return -EPERM;
+
+       if ((ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT)) &&
+	   (!projid_eq(EXT4_I(dir)->i_projid,
+		       EXT4_I(old_dentry->d_inode)->i_projid)))
+		return -EXDEV;
+
 	err = dquot_initialize(dir);
 	if (err)
 		return err;
@@ -3491,6 +3517,11 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 	int credits;
 	u8 old_file_type;
 
+	if ((ext4_test_inode_flag(new_dir, EXT4_INODE_PROJINHERIT)) &&
+	    (!projid_eq(EXT4_I(new_dir)->i_projid,
+			EXT4_I(old_dentry->d_inode)->i_projid)))
+		return -EXDEV;
+
 	retval = dquot_initialize(old.dir);
 	if (retval)
 		return retval;
@@ -3700,6 +3731,14 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 							   new.inode)))
 		return -EPERM;
 
+	if ((ext4_test_inode_flag(new_dir, EXT4_INODE_PROJINHERIT) &&
+	     !projid_eq(EXT4_I(new_dir)->i_projid,
+			EXT4_I(old_dentry->d_inode)->i_projid)) ||
+	    (ext4_test_inode_flag(old_dir, EXT4_INODE_PROJINHERIT) &&
+	     !projid_eq(EXT4_I(old_dir)->i_projid,
+			EXT4_I(new_dentry->d_inode)->i_projid)))
+		return -EXDEV;
+
 	retval = dquot_initialize(old.dir);
 	if (retval)
 		return retval;
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 17fbe3882b8e..e4fc8ea45d78 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -23,6 +23,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
+#include <linux/backing-dev.h>
 
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -52,9 +53,8 @@ void ext4_exit_pageio(void)
  */
 static void buffer_io_error(struct buffer_head *bh)
 {
-	char b[BDEVNAME_SIZE];
-	printk_ratelimited(KERN_ERR "Buffer I/O error on device %s, logical block %llu\n",
-			bdevname(bh->b_bdev, b),
+	printk_ratelimited(KERN_ERR "Buffer I/O error on device %pg, logical block %llu\n",
+		       bh->b_bdev,
 			(unsigned long long)bh->b_blocknr);
 }
 
@@ -129,9 +129,6 @@ static void ext4_release_io_end(ext4_io_end_t *io_end)
 	BUG_ON(io_end->flag & EXT4_IO_END_UNWRITTEN);
 	WARN_ON(io_end->handle);
 
-	if (atomic_dec_and_test(&EXT4_I(io_end->inode)->i_ioend_count))
-		wake_up_all(ext4_ioend_wq(io_end->inode));
-
 	for (bio = io_end->bio; bio; bio = next_bio) {
 		next_bio = bio->bi_private;
 		ext4_finish_bio(bio);
@@ -140,16 +137,6 @@ static void ext4_release_io_end(ext4_io_end_t *io_end)
 	kmem_cache_free(io_end_cachep, io_end);
 }
 
-static void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end)
-{
-	struct inode *inode = io_end->inode;
-
-	io_end->flag &= ~EXT4_IO_END_UNWRITTEN;
-	/* Wake up anyone waiting on unwritten extent conversion */
-	if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten))
-		wake_up_all(ext4_ioend_wq(inode));
-}
-
 /*
  * Check a range of space and convert unwritten extents to written. Note that
  * we are protected from truncate touching same part of extent tree by the
@@ -266,7 +253,6 @@ ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags)
 {
 	ext4_io_end_t *io = kmem_cache_zalloc(io_end_cachep, flags);
 	if (io) {
-		atomic_inc(&EXT4_I(inode)->i_ioend_count);
 		io->inode = inode;
 		INIT_LIST_HEAD(&io->list);
 		atomic_set(&io->count, 1);
@@ -447,8 +433,8 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 	 * the page size, the remaining memory is zeroed when mapped, and
 	 * writes to that region are not written out to the file."
 	 */
-	if (len < PAGE_CACHE_SIZE)
-		zero_user_segment(page, len, PAGE_CACHE_SIZE);
+	if (len < PAGE_SIZE)
+		zero_user_segment(page, len, PAGE_SIZE);
 	/*
 	 * In the first loop we prepare and mark buffers to submit. We have to
 	 * mark all buffers in the page before submitting so that
@@ -485,9 +471,20 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 
 	if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode) &&
 	    nr_to_submit) {
-		data_page = ext4_encrypt(inode, page);
+		gfp_t gfp_flags = GFP_NOFS;
+
+	retry_encrypt:
+		data_page = ext4_encrypt(inode, page, gfp_flags);
 		if (IS_ERR(data_page)) {
 			ret = PTR_ERR(data_page);
+			if (ret == -ENOMEM && wbc->sync_mode == WB_SYNC_ALL) {
+				if (io->io_bio) {
+					ext4_io_submit(io);
+					congestion_wait(BLK_RW_ASYNC, HZ/50);
+				}
+				gfp_flags |= __GFP_NOFAIL;
+				goto retry_encrypt;
+			}
 			data_page = NULL;
 			goto out;
 		}
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index d94af71a4e7f..dc54a4b60eba 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -23,7 +23,7 @@
  *
  * then this code just gives up and calls the buffer_head-based read function.
  * It does handle a page which has holes at the end - that is a common case:
- * the end-of-file on blocksize < PAGE_CACHE_SIZE setups.
+ * the end-of-file on blocksize < PAGE_SIZE setups.
  *
  */
 
@@ -140,7 +140,7 @@ int ext4_mpage_readpages(struct address_space *mapping,
 
 	struct inode *inode = mapping->host;
 	const unsigned blkbits = inode->i_blkbits;
-	const unsigned blocks_per_page = PAGE_CACHE_SIZE >> blkbits;
+	const unsigned blocks_per_page = PAGE_SIZE >> blkbits;
 	const unsigned blocksize = 1 << blkbits;
 	sector_t block_in_file;
 	sector_t last_block;
@@ -166,14 +166,14 @@ 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,
-					GFP_KERNEL & mapping_gfp_mask(mapping)))
+				  mapping_gfp_constraint(mapping, GFP_KERNEL)))
 				goto next_page;
 		}
 
 		if (page_has_buffers(page))
 			goto confused;
 
-		block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits);
+		block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits);
 		last_block = block_in_file + nr_pages * blocks_per_page;
 		last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits;
 		if (last_block > last_block_in_file)
@@ -217,7 +217,7 @@ int ext4_mpage_readpages(struct address_space *mapping,
 				set_error_page:
 					SetPageError(page);
 					zero_user_segment(page, 0,
-							  PAGE_CACHE_SIZE);
+							  PAGE_SIZE);
 					unlock_page(page);
 					goto next_page;
 				}
@@ -250,7 +250,7 @@ int ext4_mpage_readpages(struct address_space *mapping,
 		}
 		if (first_hole != blocks_per_page) {
 			zero_user_segment(page, first_hole << blkbits,
-					  PAGE_CACHE_SIZE);
+					  PAGE_SIZE);
 			if (first_hole == 0) {
 				SetPageUptodate(page);
 				unlock_page(page);
@@ -279,7 +279,7 @@ int ext4_mpage_readpages(struct address_space *mapping,
 
 			if (ext4_encrypted_inode(inode) &&
 			    S_ISREG(inode->i_mode)) {
-				ctx = ext4_get_crypto_ctx(inode);
+				ctx = ext4_get_crypto_ctx(inode, GFP_NOFS);
 				if (IS_ERR(ctx))
 					goto set_error_page;
 			}
@@ -319,7 +319,7 @@ int ext4_mpage_readpages(struct address_space *mapping,
 			unlock_page(page);
 	next_page:
 		if (pages)
-			page_cache_release(page);
+			put_page(page);
 	}
 	BUG_ON(pages && !list_empty(pages));
 	if (bio)
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index ad62d7acc315..34038e3598d5 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -198,7 +198,7 @@ static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size)
 	if (flex_gd == NULL)
 		goto out3;
 
-	if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_flex_group_data))
+	if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_group_data))
 		goto out2;
 	flex_gd->count = flexbg_size;
 
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 04d0f1b33409..304c712dbe12 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -55,7 +55,6 @@
 
 static struct ext4_lazy_init *ext4_li_info;
 static struct mutex ext4_li_mtx;
-static int ext4_mballoc_ready;
 static struct ratelimit_state ext4_mount_msg_ratelimit;
 
 static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
@@ -80,6 +79,36 @@ static void ext4_destroy_lazyinit_thread(void);
 static void ext4_unregister_li_request(struct super_block *sb);
 static void ext4_clear_request_list(void);
 
+/*
+ * Lock ordering
+ *
+ * Note the difference between i_mmap_sem (EXT4_I(inode)->i_mmap_sem) and
+ * i_mmap_rwsem (inode->i_mmap_rwsem)!
+ *
+ * page fault path:
+ * mmap_sem -> sb_start_pagefault -> i_mmap_sem (r) -> transaction start ->
+ *   page lock -> i_data_sem (rw)
+ *
+ * buffered write path:
+ * sb_start_write -> i_mutex -> mmap_sem
+ * sb_start_write -> i_mutex -> transaction start -> page lock ->
+ *   i_data_sem (rw)
+ *
+ * truncate:
+ * sb_start_write -> i_mutex -> EXT4_STATE_DIOREAD_LOCK (w) -> i_mmap_sem (w) ->
+ *   i_mmap_rwsem (w) -> page lock
+ * sb_start_write -> i_mutex -> EXT4_STATE_DIOREAD_LOCK (w) -> i_mmap_sem (w) ->
+ *   transaction start -> i_data_sem (rw)
+ *
+ * direct IO:
+ * sb_start_write -> i_mutex -> EXT4_STATE_DIOREAD_LOCK (r) -> mmap_sem
+ * sb_start_write -> i_mutex -> EXT4_STATE_DIOREAD_LOCK (r) ->
+ *   transaction start -> i_data_sem (rw)
+ *
+ * writepages:
+ * transaction start -> page lock(s) -> i_data_sem (rw)
+ */
+
 #if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT2)
 static struct file_system_type ext2_fs_type = {
 	.owner		= THIS_MODULE,
@@ -814,7 +843,6 @@ static void ext4_put_super(struct super_block *sb)
 	ext4_release_system_zone(sb);
 	ext4_mb_release(sb);
 	ext4_ext_release(sb);
-	ext4_xattr_put_super(sb);
 
 	if (!(sb->s_flags & MS_RDONLY)) {
 		ext4_clear_feature_journal_needs_recovery(sb);
@@ -914,7 +942,6 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	spin_lock_init(&ei->i_completed_io_lock);
 	ei->i_sync_tid = 0;
 	ei->i_datasync_tid = 0;
-	atomic_set(&ei->i_ioend_count, 0);
 	atomic_set(&ei->i_unwritten, 0);
 	INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work);
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
@@ -958,6 +985,7 @@ static void init_once(void *foo)
 	INIT_LIST_HEAD(&ei->i_orphan);
 	init_rwsem(&ei->xattr_sem);
 	init_rwsem(&ei->i_data_sem);
+	init_rwsem(&ei->i_mmap_sem);
 	inode_init_once(&ei->vfs_inode);
 }
 
@@ -966,7 +994,7 @@ static int __init init_inodecache(void)
 	ext4_inode_cachep = kmem_cache_create("ext4_inode_cache",
 					     sizeof(struct ext4_inode_info),
 					     0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD),
+						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
 					     init_once);
 	if (ext4_inode_cachep == NULL)
 		return -ENOMEM;
@@ -1061,13 +1089,13 @@ static int bdev_try_to_free_page(struct super_block *sb, struct page *page,
 		return 0;
 	if (journal)
 		return jbd2_journal_try_to_free_buffers(journal, page,
-							wait & ~__GFP_WAIT);
+						wait & ~__GFP_DIRECT_RECLAIM);
 	return try_to_free_buffers(page);
 }
 
 #ifdef CONFIG_QUOTA
-#define QTYPE2NAME(t) ((t) == USRQUOTA ? "user" : "group")
-#define QTYPE2MOPT(on, t) ((t) == USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA))
+static char *quotatypes[] = INITQFNAMES;
+#define QTYPE2NAME(t) (quotatypes[t])
 
 static int ext4_write_dquot(struct dquot *dquot);
 static int ext4_acquire_dquot(struct dquot *dquot);
@@ -1085,6 +1113,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
 static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
 			     unsigned int flags);
 static int ext4_enable_quotas(struct super_block *sb);
+static int ext4_get_next_id(struct super_block *sb, struct kqid *qid);
 
 static struct dquot **ext4_get_dquots(struct inode *inode)
 {
@@ -1100,6 +1129,8 @@ static const struct dquot_operations ext4_quota_operations = {
 	.write_info	= ext4_write_info,
 	.alloc_dquot	= dquot_alloc,
 	.destroy_dquot	= dquot_destroy,
+	.get_projid	= ext4_get_projid,
+	.get_next_id	= ext4_get_next_id,
 };
 
 static const struct quotactl_ops ext4_qctl_operations = {
@@ -1109,7 +1140,8 @@ static const struct quotactl_ops ext4_qctl_operations = {
 	.get_state	= dquot_get_state,
 	.set_info	= dquot_set_dqinfo,
 	.get_dqblk	= dquot_get_dqblk,
-	.set_dqblk	= dquot_set_dqblk
+	.set_dqblk	= dquot_set_dqblk,
+	.get_nextdqblk	= dquot_get_next_dqblk,
 };
 #endif
 
@@ -1292,9 +1324,9 @@ static int set_qf_name(struct super_block *sb, int qtype, substring_t *args)
 		return -1;
 	}
 	if (ext4_has_feature_quota(sb)) {
-		ext4_msg(sb, KERN_ERR, "Cannot set journaled quota options "
-			 "when QUOTA feature is enabled");
-		return -1;
+		ext4_msg(sb, KERN_INFO, "Journaled quota options "
+			 "ignored when QUOTA feature is enabled");
+		return 1;
 	}
 	qname = match_strdup(args);
 	if (!qname) {
@@ -1393,9 +1425,9 @@ static const struct mount_opts {
 	{Opt_err_ro, EXT4_MOUNT_ERRORS_RO, MOPT_SET | MOPT_CLEAR_ERR},
 	{Opt_err_cont, EXT4_MOUNT_ERRORS_CONT, MOPT_SET | MOPT_CLEAR_ERR},
 	{Opt_data_err_abort, EXT4_MOUNT_DATA_ERR_ABORT,
-	 MOPT_NO_EXT2 | MOPT_SET},
+	 MOPT_NO_EXT2},
 	{Opt_data_err_ignore, EXT4_MOUNT_DATA_ERR_ABORT,
-	 MOPT_NO_EXT2 | MOPT_CLEAR},
+	 MOPT_NO_EXT2},
 	{Opt_barrier, EXT4_MOUNT_BARRIER, MOPT_SET},
 	{Opt_nobarrier, EXT4_MOUNT_BARRIER, MOPT_CLEAR},
 	{Opt_noauto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_SET},
@@ -1657,18 +1689,26 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 			return -1;
 		}
 		if (ext4_has_feature_quota(sb)) {
-			ext4_msg(sb, KERN_ERR,
-				 "Cannot set journaled quota options "
+			ext4_msg(sb, KERN_INFO,
+				 "Quota format mount options ignored "
 				 "when QUOTA feature is enabled");
-			return -1;
+			return 1;
 		}
 		sbi->s_jquota_fmt = m->mount_opt;
 #endif
-#ifndef CONFIG_FS_DAX
 	} else if (token == Opt_dax) {
+#ifdef CONFIG_FS_DAX
+		ext4_msg(sb, KERN_WARNING,
+		"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
+			sbi->s_mount_opt |= m->mount_opt;
+#else
 		ext4_msg(sb, KERN_INFO, "dax option not supported");
 		return -1;
 #endif
+	} else if (token == Opt_data_err_abort) {
+		sbi->s_mount_opt |= m->mount_opt;
+	} else if (token == Opt_data_err_ignore) {
+		sbi->s_mount_opt &= ~m->mount_opt;
 	} else {
 		if (!args->from)
 			arg = 1;
@@ -1717,11 +1757,11 @@ static int parse_options(char *options, struct super_block *sb,
 #ifdef CONFIG_QUOTA
 	if (ext4_has_feature_quota(sb) &&
 	    (test_opt(sb, USRQUOTA) || test_opt(sb, GRPQUOTA))) {
-		ext4_msg(sb, KERN_ERR, "Cannot set quota options when QUOTA "
-			 "feature is enabled");
-		return 0;
-	}
-	if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
+		ext4_msg(sb, KERN_INFO, "Quota feature enabled, usrquota and grpquota "
+			 "mount options ignored.");
+		clear_opt(sb, USRQUOTA);
+		clear_opt(sb, GRPQUOTA);
+	} else if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
 		if (test_opt(sb, USRQUOTA) && sbi->s_qf_names[USRQUOTA])
 			clear_opt(sb, USRQUOTA);
 
@@ -1745,7 +1785,7 @@ static int parse_options(char *options, struct super_block *sb,
 		int blocksize =
 			BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
 
-		if (blocksize < PAGE_CACHE_SIZE) {
+		if (blocksize < PAGE_SIZE) {
 			ext4_msg(sb, KERN_ERR, "can't mount with "
 				 "dioread_nolock if block size != PAGE_SIZE");
 			return 0;
@@ -1878,6 +1918,8 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
 		SEQ_OPTS_PRINT("init_itable=%u", sbi->s_li_wait_mult);
 	if (nodefs || sbi->s_max_dir_size_kb)
 		SEQ_OPTS_PRINT("max_dir_size_kb=%u", sbi->s_max_dir_size_kb);
+	if (test_opt(sb, DATA_ERR_ABORT))
+		SEQ_OPTS_PUTS("data_err=abort");
 
 	ext4_show_quota_options(seq, sb);
 	return 0;
@@ -2250,10 +2292,10 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 					__func__, inode->i_ino, inode->i_size);
 			jbd_debug(2, "truncating inode %lu to %lld bytes\n",
 				  inode->i_ino, inode->i_size);
-			mutex_lock(&inode->i_mutex);
+			inode_lock(inode);
 			truncate_inode_pages(inode->i_mapping, inode->i_size);
 			ext4_truncate(inode);
-			mutex_unlock(&inode->i_mutex);
+			inode_unlock(inode);
 			nr_truncates++;
 		} else {
 			if (test_opt(sb, DEBUG))
@@ -2522,6 +2564,12 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly)
 			 "without CONFIG_QUOTA");
 		return 0;
 	}
+	if (ext4_has_feature_project(sb) && !readonly) {
+		ext4_msg(sb, KERN_ERR,
+			 "Filesystem with project quota feature cannot be mounted RDWR "
+			 "without CONFIG_QUOTA");
+		return 0;
+	}
 #endif  /* CONFIG_QUOTA */
 	return 1;
 }
@@ -3650,7 +3698,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		sb->s_qcop = &dquot_quotactl_sysfile_ops;
 	else
 		sb->s_qcop = &ext4_qctl_operations;
-	sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP;
+	sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ;
 #endif
 	memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid));
 
@@ -3754,16 +3802,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_journal->j_commit_callback = ext4_journal_commit_callback;
 
 no_journal:
-	if (ext4_mballoc_ready) {
-		sbi->s_mb_cache = ext4_xattr_create_cache(sb->s_id);
-		if (!sbi->s_mb_cache) {
-			ext4_msg(sb, KERN_ERR, "Failed to create an mb_cache");
-			goto failed_mount_wq;
-		}
+	sbi->s_mb_cache = ext4_xattr_create_cache();
+	if (!sbi->s_mb_cache) {
+		ext4_msg(sb, KERN_ERR, "Failed to create an mb_cache");
+		goto failed_mount_wq;
 	}
 
 	if ((DUMMY_ENCRYPTION_ENABLED(sbi) || ext4_has_feature_encrypt(sb)) &&
-	    (blocksize != PAGE_CACHE_SIZE)) {
+	    (blocksize != PAGE_SIZE)) {
 		ext4_msg(sb, KERN_ERR,
 			 "Unsupported blocksize for fs encryption");
 		goto failed_mount_wq;
@@ -3985,6 +4031,10 @@ failed_mount4:
 	if (EXT4_SB(sb)->rsv_conversion_wq)
 		destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq);
 failed_mount_wq:
+	if (sbi->s_mb_cache) {
+		ext4_xattr_destroy_cache(sbi->s_mb_cache);
+		sbi->s_mb_cache = NULL;
+	}
 	if (sbi->s_journal) {
 		jbd2_journal_destroy(sbi->s_journal);
 		sbi->s_journal = NULL;
@@ -4786,6 +4836,48 @@ restore_opts:
 	return err;
 }
 
+#ifdef CONFIG_QUOTA
+static int ext4_statfs_project(struct super_block *sb,
+			       kprojid_t projid, struct kstatfs *buf)
+{
+	struct kqid qid;
+	struct dquot *dquot;
+	u64 limit;
+	u64 curblock;
+
+	qid = make_kqid_projid(projid);
+	dquot = dqget(sb, qid);
+	if (IS_ERR(dquot))
+		return PTR_ERR(dquot);
+	spin_lock(&dq_data_lock);
+
+	limit = (dquot->dq_dqb.dqb_bsoftlimit ?
+		 dquot->dq_dqb.dqb_bsoftlimit :
+		 dquot->dq_dqb.dqb_bhardlimit) >> sb->s_blocksize_bits;
+	if (limit && buf->f_blocks > limit) {
+		curblock = dquot->dq_dqb.dqb_curspace >> sb->s_blocksize_bits;
+		buf->f_blocks = limit;
+		buf->f_bfree = buf->f_bavail =
+			(buf->f_blocks > curblock) ?
+			 (buf->f_blocks - curblock) : 0;
+	}
+
+	limit = dquot->dq_dqb.dqb_isoftlimit ?
+		dquot->dq_dqb.dqb_isoftlimit :
+		dquot->dq_dqb.dqb_ihardlimit;
+	if (limit && buf->f_files > limit) {
+		buf->f_files = limit;
+		buf->f_ffree =
+			(buf->f_files > dquot->dq_dqb.dqb_curinodes) ?
+			 (buf->f_files - dquot->dq_dqb.dqb_curinodes) : 0;
+	}
+
+	spin_unlock(&dq_data_lock);
+	dqput(dquot);
+	return 0;
+}
+#endif
+
 static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *sb = dentry->d_sb;
@@ -4818,6 +4910,11 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_fsid.val[0] = fsid & 0xFFFFFFFFUL;
 	buf->f_fsid.val[1] = (fsid >> 32) & 0xFFFFFFFFUL;
 
+#ifdef CONFIG_QUOTA
+	if (ext4_test_inode_flag(dentry->d_inode, EXT4_INODE_PROJINHERIT) &&
+	    sb_has_quota_limits_enabled(sb, PRJQUOTA))
+		ext4_statfs_project(sb, EXT4_I(dentry->d_inode)->i_projid, buf);
+#endif
 	return 0;
 }
 
@@ -4932,6 +5029,20 @@ static int ext4_quota_on_mount(struct super_block *sb, int type)
 					EXT4_SB(sb)->s_jquota_fmt, type);
 }
 
+static void lockdep_set_quota_inode(struct inode *inode, int subclass)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	/* The first argument of lockdep_set_subclass has to be
+	 * *exactly* the same as the argument to init_rwsem() --- in
+	 * this case, in init_once() --- or lockdep gets unhappy
+	 * because the name of the lock is set using the
+	 * stringification of the argument to init_rwsem().
+	 */
+	(void) ei;	/* shut up clang warning if !CONFIG_LOCKDEP */
+	lockdep_set_subclass(&ei->i_data_sem, subclass);
+}
+
 /*
  * Standard function to be called on quota_on
  */
@@ -4971,8 +5082,12 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
 		if (err)
 			return err;
 	}
-
-	return dquot_quota_on(sb, type, format_id, path);
+	lockdep_set_quota_inode(path->dentry->d_inode, I_DATA_SEM_QUOTA);
+	err = dquot_quota_on(sb, type, format_id, path);
+	if (err)
+		lockdep_set_quota_inode(path->dentry->d_inode,
+					     I_DATA_SEM_NORMAL);
+	return err;
 }
 
 static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
@@ -4982,7 +5097,8 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
 	struct inode *qf_inode;
 	unsigned long qf_inums[EXT4_MAXQUOTAS] = {
 		le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum),
-		le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum)
+		le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum),
+		le32_to_cpu(EXT4_SB(sb)->s_es->s_prj_quota_inum)
 	};
 
 	BUG_ON(!ext4_has_feature_quota(sb));
@@ -4998,8 +5114,11 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
 
 	/* Don't account quota for quota files to avoid recursion */
 	qf_inode->i_flags |= S_NOQUOTA;
+	lockdep_set_quota_inode(qf_inode, I_DATA_SEM_QUOTA);
 	err = dquot_enable(qf_inode, type, format_id, flags);
 	iput(qf_inode);
+	if (err)
+		lockdep_set_quota_inode(qf_inode, I_DATA_SEM_NORMAL);
 
 	return err;
 }
@@ -5010,7 +5129,8 @@ static int ext4_enable_quotas(struct super_block *sb)
 	int type, err = 0;
 	unsigned long qf_inums[EXT4_MAXQUOTAS] = {
 		le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum),
-		le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum)
+		le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum),
+		le32_to_cpu(EXT4_SB(sb)->s_es->s_prj_quota_inum)
 	};
 
 	sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE;
@@ -5155,6 +5275,17 @@ out:
 	return len;
 }
 
+static int ext4_get_next_id(struct super_block *sb, struct kqid *qid)
+{
+	const struct quota_format_ops	*ops;
+
+	if (!sb_has_quota_loaded(sb, qid->type))
+		return -ESRCH;
+	ops = sb_dqopt(sb)->ops[qid->type];
+	if (!ops || !ops->get_next_id)
+		return -ENOSYS;
+	return dquot_get_next_id(sb, qid);
+}
 #endif
 
 static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags,
@@ -5230,7 +5361,6 @@ MODULE_ALIAS_FS("ext4");
 
 /* Shared across all ext4 file systems */
 wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
-struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ];
 
 static int __init ext4_init_fs(void)
 {
@@ -5243,10 +5373,8 @@ static int __init ext4_init_fs(void)
 	/* Build-time check for flags consistency */
 	ext4_check_flag_values();
 
-	for (i = 0; i < EXT4_WQ_HASH_SZ; i++) {
-		mutex_init(&ext4__aio_mutex[i]);
+	for (i = 0; i < EXT4_WQ_HASH_SZ; i++)
 		init_waitqueue_head(&ext4__ioend_wq[i]);
-	}
 
 	err = ext4_init_es();
 	if (err)
@@ -5267,8 +5395,6 @@ static int __init ext4_init_fs(void)
 	err = ext4_init_mballoc();
 	if (err)
 		goto out2;
-	else
-		ext4_mballoc_ready = 1;
 	err = init_inodecache();
 	if (err)
 		goto out1;
@@ -5284,7 +5410,6 @@ out:
 	unregister_as_ext3();
 	destroy_inodecache();
 out1:
-	ext4_mballoc_ready = 0;
 	ext4_exit_mballoc();
 out2:
 	ext4_exit_sysfs();
diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c
index abe2401ce405..75ed5c2f0c16 100644
--- a/fs/ext4/symlink.c
+++ b/fs/ext4/symlink.c
@@ -23,17 +23,21 @@
 #include "xattr.h"
 
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
-static const char *ext4_encrypted_follow_link(struct dentry *dentry, void **cookie)
+static const char *ext4_encrypted_get_link(struct dentry *dentry,
+					   struct inode *inode,
+					   struct delayed_call *done)
 {
 	struct page *cpage = NULL;
 	char *caddr, *paddr = NULL;
 	struct ext4_str cstr, pstr;
-	struct inode *inode = d_inode(dentry);
 	struct ext4_encrypted_symlink_data *sd;
 	loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1);
 	int res;
 	u32 plen, max_size = inode->i_sb->s_blocksize;
 
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
 	res = ext4_get_encryption_info(inode);
 	if (res)
 		return ERR_PTR(res);
@@ -45,14 +49,14 @@ static const char *ext4_encrypted_follow_link(struct dentry *dentry, void **cook
 		cpage = read_mapping_page(inode->i_mapping, 0, NULL);
 		if (IS_ERR(cpage))
 			return ERR_CAST(cpage);
-		caddr = kmap(cpage);
+		caddr = page_address(cpage);
 		caddr[size] = 0;
 	}
 
 	/* Symlink is encrypted */
 	sd = (struct ext4_encrypted_symlink_data *)caddr;
 	cstr.name = sd->encrypted_path;
-	cstr.len  = le32_to_cpu(sd->len);
+	cstr.len  = le16_to_cpu(sd->len);
 	if ((cstr.len +
 	     sizeof(struct ext4_encrypted_symlink_data) - 1) >
 	    max_size) {
@@ -75,24 +79,20 @@ static const char *ext4_encrypted_follow_link(struct dentry *dentry, void **cook
 	/* Null-terminate the name */
 	if (res <= plen)
 		paddr[res] = '\0';
-	if (cpage) {
-		kunmap(cpage);
-		page_cache_release(cpage);
-	}
-	return *cookie = paddr;
+	if (cpage)
+		put_page(cpage);
+	set_delayed_call(done, kfree_link, paddr);
+	return paddr;
 errout:
-	if (cpage) {
-		kunmap(cpage);
-		page_cache_release(cpage);
-	}
+	if (cpage)
+		put_page(cpage);
 	kfree(paddr);
 	return ERR_PTR(res);
 }
 
 const struct inode_operations ext4_encrypted_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link    = ext4_encrypted_follow_link,
-	.put_link       = kfree_put_link,
+	.get_link	= ext4_encrypted_get_link,
 	.setattr	= ext4_setattr,
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
@@ -103,8 +103,7 @@ const struct inode_operations ext4_encrypted_symlink_inode_operations = {
 
 const struct inode_operations ext4_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 	.setattr	= ext4_setattr,
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
@@ -114,7 +113,7 @@ const struct inode_operations ext4_symlink_inode_operations = {
 
 const struct inode_operations ext4_fast_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link    = simple_follow_link,
+	.get_link	= simple_get_link,
 	.setattr	= ext4_setattr,
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index 1b57c72f4a00..1420a3c614af 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -358,7 +358,7 @@ static int name##_open(struct inode *inode, struct file *file) \
 	return single_open(file, ext4_seq_##name##_show, PDE_DATA(inode)); \
 } \
 \
-const struct file_operations ext4_seq_##name##_fops = { \
+static const struct file_operations ext4_seq_##name##_fops = { \
 	.owner		= THIS_MODULE, \
 	.open		= name##_open, \
 	.read		= seq_read, \
diff --git a/fs/ext4/truncate.h b/fs/ext4/truncate.h
index 011ba6670d99..c70d06a383e2 100644
--- a/fs/ext4/truncate.h
+++ b/fs/ext4/truncate.h
@@ -10,8 +10,10 @@
  */
 static inline void ext4_truncate_failed_write(struct inode *inode)
 {
+	down_write(&EXT4_I(inode)->i_mmap_sem);
 	truncate_inode_pages(inode->i_mapping, inode->i_size);
 	ext4_truncate(inode);
+	up_write(&EXT4_I(inode)->i_mmap_sem);
 }
 
 /*
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 984448c6f5f0..e79bd32b9b79 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -68,10 +68,8 @@
 		printk("\n"); \
 	} while (0)
 # define ea_bdebug(bh, f...) do { \
-		char b[BDEVNAME_SIZE]; \
-		printk(KERN_DEBUG "block %s:%lu: ", \
-			bdevname(bh->b_bdev, b), \
-			(unsigned long) bh->b_blocknr); \
+		printk(KERN_DEBUG "block %pg:%lu: ",		   \
+		       bh->b_bdev, (unsigned long) bh->b_blocknr); \
 		printk(f); \
 		printk("\n"); \
 	} while (0)
@@ -232,6 +230,27 @@ ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh)
 	return error;
 }
 
+static int
+__xattr_check_inode(struct inode *inode, struct ext4_xattr_ibody_header *header,
+			 void *end, const char *function, unsigned int line)
+{
+	struct ext4_xattr_entry *entry = IFIRST(header);
+	int error = -EFSCORRUPTED;
+
+	if (((void *) header >= end) ||
+	    (header->h_magic != le32_to_cpu(EXT4_XATTR_MAGIC)))
+		goto errout;
+	error = ext4_xattr_check_names(entry, end, entry);
+errout:
+	if (error)
+		__ext4_error_inode(inode, function, line, 0,
+				   "corrupted in-inode xattr");
+	return error;
+}
+
+#define xattr_check_inode(inode, header, end) \
+	__xattr_check_inode((inode), (header), (end), __func__, __LINE__)
+
 static inline int
 ext4_xattr_check_entry(struct ext4_xattr_entry *entry, size_t size)
 {
@@ -343,7 +362,7 @@ ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name,
 	header = IHDR(inode, raw_inode);
 	entry = IFIRST(header);
 	end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
-	error = ext4_xattr_check_names(entry, end, entry);
+	error = xattr_check_inode(inode, header, end);
 	if (error)
 		goto cleanup;
 	error = ext4_xattr_find_entry(&entry, name_index, name,
@@ -404,20 +423,24 @@ ext4_xattr_list_entries(struct dentry *dentry, struct ext4_xattr_entry *entry,
 		const struct xattr_handler *handler =
 			ext4_xattr_handler(entry->e_name_index);
 
-		if (handler) {
-			size_t size = handler->list(dentry, buffer, rest,
-						    entry->e_name,
-						    entry->e_name_len,
-						    handler->flags);
+		if (handler && (!handler->list || handler->list(dentry))) {
+			const char *prefix = handler->prefix ?: handler->name;
+			size_t prefix_len = strlen(prefix);
+			size_t size = prefix_len + entry->e_name_len + 1;
+
 			if (buffer) {
 				if (size > rest)
 					return -ERANGE;
-				buffer += size;
+				memcpy(buffer, prefix, prefix_len);
+				buffer += prefix_len;
+				memcpy(buffer, entry->e_name, entry->e_name_len);
+				buffer += entry->e_name_len;
+				*buffer++ = 0;
 			}
 			rest -= size;
 		}
 	}
-	return buffer_size - rest;
+	return buffer_size - rest;  /* total size */
 }
 
 static int
@@ -475,7 +498,7 @@ ext4_xattr_ibody_list(struct dentry *dentry, char *buffer, size_t buffer_size)
 	raw_inode = ext4_raw_inode(&iloc);
 	header = IHDR(inode, raw_inode);
 	end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
-	error = ext4_xattr_check_names(IFIRST(header), end, IFIRST(header));
+	error = xattr_check_inode(inode, header, end);
 	if (error)
 		goto cleanup;
 	error = ext4_xattr_list_entries(dentry, IFIRST(header),
@@ -543,30 +566,44 @@ static void
 ext4_xattr_release_block(handle_t *handle, struct inode *inode,
 			 struct buffer_head *bh)
 {
-	struct mb_cache_entry *ce = NULL;
-	int error = 0;
 	struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
+	u32 hash, ref;
+	int error = 0;
 
-	ce = mb_cache_entry_get(ext4_mb_cache, bh->b_bdev, bh->b_blocknr);
 	BUFFER_TRACE(bh, "get_write_access");
 	error = ext4_journal_get_write_access(handle, bh);
 	if (error)
 		goto out;
 
 	lock_buffer(bh);
-	if (BHDR(bh)->h_refcount == cpu_to_le32(1)) {
+	hash = le32_to_cpu(BHDR(bh)->h_hash);
+	ref = le32_to_cpu(BHDR(bh)->h_refcount);
+	if (ref == 1) {
 		ea_bdebug(bh, "refcount now=0; freeing");
-		if (ce)
-			mb_cache_entry_free(ce);
+		/*
+		 * This must happen under buffer lock for
+		 * ext4_xattr_block_set() to reliably detect freed block
+		 */
+		mb_cache_entry_delete_block(ext4_mb_cache, hash, bh->b_blocknr);
 		get_bh(bh);
 		unlock_buffer(bh);
 		ext4_free_blocks(handle, inode, bh, 0, 1,
 				 EXT4_FREE_BLOCKS_METADATA |
 				 EXT4_FREE_BLOCKS_FORGET);
 	} else {
-		le32_add_cpu(&BHDR(bh)->h_refcount, -1);
-		if (ce)
-			mb_cache_entry_release(ce);
+		ref--;
+		BHDR(bh)->h_refcount = cpu_to_le32(ref);
+		if (ref == EXT4_XATTR_REFCOUNT_MAX - 1) {
+			struct mb_cache_entry *ce;
+
+			ce = mb_cache_entry_get(ext4_mb_cache, hash,
+						bh->b_blocknr);
+			if (ce) {
+				ce->e_reusable = 1;
+				mb_cache_entry_put(ext4_mb_cache, ce);
+			}
+		}
+
 		/*
 		 * Beware of this ugliness: Releasing of xattr block references
 		 * from different inodes can race and so we have to protect
@@ -788,8 +825,6 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 	if (i->value && i->value_len > sb->s_blocksize)
 		return -ENOSPC;
 	if (s->base) {
-		ce = mb_cache_entry_get(ext4_mb_cache, bs->bh->b_bdev,
-					bs->bh->b_blocknr);
 		BUFFER_TRACE(bs->bh, "get_write_access");
 		error = ext4_journal_get_write_access(handle, bs->bh);
 		if (error)
@@ -797,10 +832,15 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 		lock_buffer(bs->bh);
 
 		if (header(s->base)->h_refcount == cpu_to_le32(1)) {
-			if (ce) {
-				mb_cache_entry_free(ce);
-				ce = NULL;
-			}
+			__u32 hash = le32_to_cpu(BHDR(bs->bh)->h_hash);
+
+			/*
+			 * This must happen under buffer lock for
+			 * ext4_xattr_block_set() to reliably detect modified
+			 * block
+			 */
+			mb_cache_entry_delete_block(ext4_mb_cache, hash,
+						    bs->bh->b_blocknr);
 			ea_bdebug(bs->bh, "modifying in-place");
 			error = ext4_xattr_set_entry(i, s);
 			if (!error) {
@@ -824,10 +864,6 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 			int offset = (char *)s->here - bs->bh->b_data;
 
 			unlock_buffer(bs->bh);
-			if (ce) {
-				mb_cache_entry_release(ce);
-				ce = NULL;
-			}
 			ea_bdebug(bs->bh, "cloning");
 			s->base = kmalloc(bs->bh->b_size, GFP_NOFS);
 			error = -ENOMEM;
@@ -870,6 +906,8 @@ inserted:
 			if (new_bh == bs->bh)
 				ea_bdebug(new_bh, "keeping");
 			else {
+				u32 ref;
+
 				/* The old block is released after updating
 				   the inode. */
 				error = dquot_alloc_block(inode,
@@ -882,9 +920,40 @@ inserted:
 				if (error)
 					goto cleanup_dquot;
 				lock_buffer(new_bh);
-				le32_add_cpu(&BHDR(new_bh)->h_refcount, 1);
+				/*
+				 * We have to be careful about races with
+				 * freeing, rehashing or adding references to
+				 * xattr block. Once we hold buffer lock xattr
+				 * block's state is stable so we can check
+				 * whether the block got freed / rehashed or
+				 * not.  Since we unhash mbcache entry under
+				 * buffer lock when freeing / rehashing xattr
+				 * block, checking whether entry is still
+				 * hashed is reliable. Same rules hold for
+				 * e_reusable handling.
+				 */
+				if (hlist_bl_unhashed(&ce->e_hash_list) ||
+				    !ce->e_reusable) {
+					/*
+					 * Undo everything and check mbcache
+					 * again.
+					 */
+					unlock_buffer(new_bh);
+					dquot_free_block(inode,
+							 EXT4_C2B(EXT4_SB(sb),
+								  1));
+					brelse(new_bh);
+					mb_cache_entry_put(ext4_mb_cache, ce);
+					ce = NULL;
+					new_bh = NULL;
+					goto inserted;
+				}
+				ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1;
+				BHDR(new_bh)->h_refcount = cpu_to_le32(ref);
+				if (ref >= EXT4_XATTR_REFCOUNT_MAX)
+					ce->e_reusable = 0;
 				ea_bdebug(new_bh, "reusing; refcount now=%d",
-					le32_to_cpu(BHDR(new_bh)->h_refcount));
+					  ref);
 				unlock_buffer(new_bh);
 				error = ext4_handle_dirty_xattr_block(handle,
 								      inode,
@@ -892,7 +961,8 @@ inserted:
 				if (error)
 					goto cleanup_dquot;
 			}
-			mb_cache_entry_release(ce);
+			mb_cache_entry_touch(ext4_mb_cache, ce);
+			mb_cache_entry_put(ext4_mb_cache, ce);
 			ce = NULL;
 		} else if (bs->bh && s->base == bs->bh->b_data) {
 			/* We were modifying this block in-place. */
@@ -957,7 +1027,7 @@ getblk_failed:
 
 cleanup:
 	if (ce)
-		mb_cache_entry_release(ce);
+		mb_cache_entry_put(ext4_mb_cache, ce);
 	brelse(new_bh);
 	if (!(bs->bh && s->base == bs->bh->b_data))
 		kfree(s->base);
@@ -991,8 +1061,7 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
 	is->s.here = is->s.first;
 	is->s.end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
 	if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
-		error = ext4_xattr_check_names(IFIRST(header), is->s.end,
-					       IFIRST(header));
+		error = xattr_check_inode(inode, header, is->s.end);
 		if (error)
 			return error;
 		/* Find the named attribute. */
@@ -1068,6 +1137,17 @@ static int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
 	return 0;
 }
 
+static int ext4_xattr_value_same(struct ext4_xattr_search *s,
+				 struct ext4_xattr_info *i)
+{
+	void *value;
+
+	if (le32_to_cpu(s->here->e_value_size) != i->value_len)
+		return 0;
+	value = ((void *)s->base) + le16_to_cpu(s->here->e_value_offs);
+	return !memcmp(value, i->value, i->value_len);
+}
+
 /*
  * ext4_xattr_set_handle()
  *
@@ -1144,6 +1224,13 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 		else if (!bs.s.not_found)
 			error = ext4_xattr_block_set(handle, inode, &i, &bs);
 	} else {
+		error = 0;
+		/* Xattr value did not change? Save us some work and bail out */
+		if (!is.s.not_found && ext4_xattr_value_same(&is.s, &i))
+			goto cleanup;
+		if (!bs.s.not_found && ext4_xattr_value_same(&bs.s, &i))
+			goto cleanup;
+
 		error = ext4_xattr_ibody_set(handle, inode, &i, &is);
 		if (!error && !bs.s.not_found) {
 			i.value = NULL;
@@ -1289,6 +1376,10 @@ retry:
 	last = entry;
 	total_ino = sizeof(struct ext4_xattr_ibody_header);
 
+	error = xattr_check_inode(inode, header, end);
+	if (error)
+		goto cleanup;
+
 	free = ext4_xattr_free_space(last, &min_offs, base, &total_ino);
 	if (free >= new_extra_isize) {
 		entry = IFIRST(header);
@@ -1510,17 +1601,6 @@ cleanup:
 }
 
 /*
- * ext4_xattr_put_super()
- *
- * This is called when a file system is unmounted.
- */
-void
-ext4_xattr_put_super(struct super_block *sb)
-{
-	mb_cache_shrink(sb->s_bdev);
-}
-
-/*
  * ext4_xattr_cache_insert()
  *
  * Create a new entry in the extended attribute cache, and insert
@@ -1531,26 +1611,19 @@ ext4_xattr_put_super(struct super_block *sb)
 static void
 ext4_xattr_cache_insert(struct mb_cache *ext4_mb_cache, struct buffer_head *bh)
 {
-	__u32 hash = le32_to_cpu(BHDR(bh)->h_hash);
-	struct mb_cache_entry *ce;
+	struct ext4_xattr_header *header = BHDR(bh);
+	__u32 hash = le32_to_cpu(header->h_hash);
+	int reusable = le32_to_cpu(header->h_refcount) <
+		       EXT4_XATTR_REFCOUNT_MAX;
 	int error;
 
-	ce = mb_cache_entry_alloc(ext4_mb_cache, GFP_NOFS);
-	if (!ce) {
-		ea_bdebug(bh, "out of memory");
-		return;
-	}
-	error = mb_cache_entry_insert(ce, bh->b_bdev, bh->b_blocknr, hash);
+	error = mb_cache_entry_create(ext4_mb_cache, GFP_NOFS, hash,
+				      bh->b_blocknr, reusable);
 	if (error) {
-		mb_cache_entry_free(ce);
-		if (error == -EBUSY) {
+		if (error == -EBUSY)
 			ea_bdebug(bh, "already in cache");
-			error = 0;
-		}
-	} else {
+	} else
 		ea_bdebug(bh, "inserting [%x]", (int)hash);
-		mb_cache_entry_release(ce);
-	}
 }
 
 /*
@@ -1612,33 +1685,20 @@ ext4_xattr_cache_find(struct inode *inode, struct ext4_xattr_header *header,
 	if (!header->h_hash)
 		return NULL;  /* never share */
 	ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
-again:
-	ce = mb_cache_entry_find_first(ext4_mb_cache, inode->i_sb->s_bdev,
-				       hash);
+	ce = mb_cache_entry_find_first(ext4_mb_cache, hash);
 	while (ce) {
 		struct buffer_head *bh;
 
-		if (IS_ERR(ce)) {
-			if (PTR_ERR(ce) == -EAGAIN)
-				goto again;
-			break;
-		}
 		bh = sb_bread(inode->i_sb, ce->e_block);
 		if (!bh) {
 			EXT4_ERROR_INODE(inode, "block %lu read error",
 					 (unsigned long) ce->e_block);
-		} else if (le32_to_cpu(BHDR(bh)->h_refcount) >=
-				EXT4_XATTR_REFCOUNT_MAX) {
-			ea_idebug(inode, "block %lu refcount %d>=%d",
-				  (unsigned long) ce->e_block,
-				  le32_to_cpu(BHDR(bh)->h_refcount),
-					  EXT4_XATTR_REFCOUNT_MAX);
 		} else if (ext4_xattr_cmp(header, BHDR(bh)) == 0) {
 			*pce = ce;
 			return bh;
 		}
 		brelse(bh);
-		ce = mb_cache_entry_find_next(ce, inode->i_sb->s_bdev, hash);
+		ce = mb_cache_entry_find_next(ext4_mb_cache, ce);
 	}
 	return NULL;
 }
@@ -1714,9 +1774,9 @@ static void ext4_xattr_rehash(struct ext4_xattr_header *header,
 #define	HASH_BUCKET_BITS	10
 
 struct mb_cache *
-ext4_xattr_create_cache(char *name)
+ext4_xattr_create_cache(void)
 {
-	return mb_cache_create(name, HASH_BUCKET_BITS);
+	return mb_cache_create(HASH_BUCKET_BITS);
 }
 
 void ext4_xattr_destroy_cache(struct mb_cache *cache)
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index ddc0957760ba..69dd3e6566e0 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -108,7 +108,6 @@ extern int ext4_xattr_set(struct inode *, int, const char *, const void *, size_
 extern int ext4_xattr_set_handle(handle_t *, struct inode *, int, const char *, const void *, size_t, int);
 
 extern void ext4_xattr_delete_inode(handle_t *, struct inode *);
-extern void ext4_xattr_put_super(struct super_block *);
 
 extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
 			    struct ext4_inode *raw_inode, handle_t *handle);
@@ -124,7 +123,7 @@ extern int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
 				       struct ext4_xattr_info *i,
 				       struct ext4_xattr_ibody_find *is);
 
-extern struct mb_cache *ext4_xattr_create_cache(char *name);
+extern struct mb_cache *ext4_xattr_create_cache(void);
 extern void ext4_xattr_destroy_cache(struct mb_cache *);
 
 #ifdef CONFIG_EXT4_FS_SECURITY
diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c
index 95d90e0560f0..3e81bdca071a 100644
--- a/fs/ext4/xattr_security.c
+++ b/fs/ext4/xattr_security.c
@@ -11,38 +11,20 @@
 #include "ext4.h"
 #include "xattr.h"
 
-static size_t
-ext4_xattr_security_list(struct dentry *dentry, char *list, size_t list_size,
-		const char *name, size_t name_len, int type)
-{
-	const size_t prefix_len = sizeof(XATTR_SECURITY_PREFIX)-1;
-	const size_t total_len = prefix_len + name_len + 1;
-
-
-	if (list && total_len <= list_size) {
-		memcpy(list, XATTR_SECURITY_PREFIX, prefix_len);
-		memcpy(list+prefix_len, name, name_len);
-		list[prefix_len + name_len] = '\0';
-	}
-	return total_len;
-}
-
 static int
-ext4_xattr_security_get(struct dentry *dentry, const char *name,
-		       void *buffer, size_t size, int type)
+ext4_xattr_security_get(const struct xattr_handler *handler,
+			struct dentry *dentry, const char *name,
+			void *buffer, size_t size)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	return ext4_xattr_get(d_inode(dentry), EXT4_XATTR_INDEX_SECURITY,
 			      name, buffer, size);
 }
 
 static int
-ext4_xattr_security_set(struct dentry *dentry, const char *name,
-		const void *value, size_t size, int flags, int type)
+ext4_xattr_security_set(const struct xattr_handler *handler,
+			struct dentry *dentry, const char *name,
+			const void *value, size_t size, int flags)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	return ext4_xattr_set(d_inode(dentry), EXT4_XATTR_INDEX_SECURITY,
 			      name, value, size, flags);
 }
@@ -76,7 +58,6 @@ ext4_init_security(handle_t *handle, struct inode *inode, struct inode *dir,
 
 const struct xattr_handler ext4_xattr_security_handler = {
 	.prefix	= XATTR_SECURITY_PREFIX,
-	.list	= ext4_xattr_security_list,
 	.get	= ext4_xattr_security_get,
 	.set	= ext4_xattr_security_set,
 };
diff --git a/fs/ext4/xattr_trusted.c b/fs/ext4/xattr_trusted.c
index 891ee2ddfbd6..2a3c6f9b8cb8 100644
--- a/fs/ext4/xattr_trusted.c
+++ b/fs/ext4/xattr_trusted.c
@@ -12,40 +12,26 @@
 #include "ext4.h"
 #include "xattr.h"
 
-static size_t
-ext4_xattr_trusted_list(struct dentry *dentry, char *list, size_t list_size,
-		const char *name, size_t name_len, int type)
+static bool
+ext4_xattr_trusted_list(struct dentry *dentry)
 {
-	const size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN;
-	const size_t total_len = prefix_len + name_len + 1;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return 0;
-
-	if (list && total_len <= list_size) {
-		memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len);
-		memcpy(list+prefix_len, name, name_len);
-		list[prefix_len + name_len] = '\0';
-	}
-	return total_len;
+	return capable(CAP_SYS_ADMIN);
 }
 
 static int
-ext4_xattr_trusted_get(struct dentry *dentry, const char *name, void *buffer,
-		size_t size, int type)
+ext4_xattr_trusted_get(const struct xattr_handler *handler,
+		       struct dentry *dentry, const char *name, void *buffer,
+		       size_t size)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	return ext4_xattr_get(d_inode(dentry), EXT4_XATTR_INDEX_TRUSTED,
 			      name, buffer, size);
 }
 
 static int
-ext4_xattr_trusted_set(struct dentry *dentry, const char *name,
-		const void *value, size_t size, int flags, int type)
+ext4_xattr_trusted_set(const struct xattr_handler *handler,
+		       struct dentry *dentry, const char *name,
+		       const void *value, size_t size, int flags)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	return ext4_xattr_set(d_inode(dentry), EXT4_XATTR_INDEX_TRUSTED,
 			      name, value, size, flags);
 }
diff --git a/fs/ext4/xattr_user.c b/fs/ext4/xattr_user.c
index 6ed932b3c043..d152f431e432 100644
--- a/fs/ext4/xattr_user.c
+++ b/fs/ext4/xattr_user.c
@@ -11,30 +11,17 @@
 #include "ext4.h"
 #include "xattr.h"
 
-static size_t
-ext4_xattr_user_list(struct dentry *dentry, char *list, size_t list_size,
-		     const char *name, size_t name_len, int type)
+static bool
+ext4_xattr_user_list(struct dentry *dentry)
 {
-	const size_t prefix_len = XATTR_USER_PREFIX_LEN;
-	const size_t total_len = prefix_len + name_len + 1;
-
-	if (!test_opt(dentry->d_sb, XATTR_USER))
-		return 0;
-
-	if (list && total_len <= list_size) {
-		memcpy(list, XATTR_USER_PREFIX, prefix_len);
-		memcpy(list+prefix_len, name, name_len);
-		list[prefix_len + name_len] = '\0';
-	}
-	return total_len;
+	return test_opt(dentry->d_sb, XATTR_USER);
 }
 
 static int
-ext4_xattr_user_get(struct dentry *dentry, const char *name,
-		    void *buffer, size_t size, int type)
+ext4_xattr_user_get(const struct xattr_handler *handler,
+		    struct dentry *dentry, const char *name,
+		    void *buffer, size_t size)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	if (!test_opt(dentry->d_sb, XATTR_USER))
 		return -EOPNOTSUPP;
 	return ext4_xattr_get(d_inode(dentry), EXT4_XATTR_INDEX_USER,
@@ -42,11 +29,10 @@ ext4_xattr_user_get(struct dentry *dentry, const char *name,
 }
 
 static int
-ext4_xattr_user_set(struct dentry *dentry, const char *name,
-		    const void *value, size_t size, int flags, int type)
+ext4_xattr_user_set(const struct xattr_handler *handler,
+		    struct dentry *dentry, const char *name,
+		    const void *value, size_t size, int flags)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	if (!test_opt(dentry->d_sb, XATTR_USER))
 		return -EOPNOTSUPP;
 	return ext4_xattr_set(d_inode(dentry), EXT4_XATTR_INDEX_USER,
diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig
index b0a9dc929f88..1f8982a957f1 100644
--- a/fs/f2fs/Kconfig
+++ b/fs/f2fs/Kconfig
@@ -1,6 +1,8 @@
 config F2FS_FS
 	tristate "F2FS filesystem support"
 	depends on BLOCK
+	select CRYPTO
+	select CRYPTO_CRC32
 	help
 	  F2FS is based on Log-structured File System (LFS), which supports
 	  versatile "flash-friendly" features. The design has been focused on
@@ -76,15 +78,7 @@ config F2FS_FS_ENCRYPTION
 	bool "F2FS Encryption"
 	depends on F2FS_FS
 	depends on F2FS_FS_XATTR
-	select CRYPTO_AES
-	select CRYPTO_CBC
-	select CRYPTO_ECB
-	select CRYPTO_XTS
-	select CRYPTO_CTS
-	select CRYPTO_CTR
-	select CRYPTO_SHA256
-	select KEYS
-	select ENCRYPTED_KEYS
+	select FS_ENCRYPTION
 	help
 	  Enable encryption of f2fs files and directories.  This
 	  feature is similar to ecryptfs, but it is more memory
diff --git a/fs/f2fs/Makefile b/fs/f2fs/Makefile
index 08e101ed914c..ca949ea7c02f 100644
--- a/fs/f2fs/Makefile
+++ b/fs/f2fs/Makefile
@@ -7,5 +7,3 @@ f2fs-$(CONFIG_F2FS_STAT_FS) += debug.o
 f2fs-$(CONFIG_F2FS_FS_XATTR) += xattr.o
 f2fs-$(CONFIG_F2FS_FS_POSIX_ACL) += acl.o
 f2fs-$(CONFIG_F2FS_IO_TRACE) += trace.o
-f2fs-$(CONFIG_F2FS_FS_ENCRYPTION) += crypto_policy.o crypto.o \
-		crypto_key.o crypto_fname.o
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index f661d80474be..0955312e5ca0 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -39,7 +39,7 @@ repeat:
 		cond_resched();
 		goto repeat;
 	}
-	f2fs_wait_on_page_writeback(page, META);
+	f2fs_wait_on_page_writeback(page, META, true);
 	SetPageUptodate(page);
 	return page;
 }
@@ -56,7 +56,8 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
 		.sbi = sbi,
 		.type = META,
 		.rw = READ_SYNC | REQ_META | REQ_PRIO,
-		.blk_addr = index,
+		.old_blkaddr = index,
+		.new_blkaddr = index,
 		.encrypted_page = NULL,
 	};
 
@@ -143,7 +144,6 @@ bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type)
 int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 							int type, bool sync)
 {
-	block_t prev_blk_addr = 0;
 	struct page *page;
 	block_t blkno = start;
 	struct f2fs_io_info fio = {
@@ -152,10 +152,12 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 		.rw = sync ? (READ_SYNC | REQ_META | REQ_PRIO) : READA,
 		.encrypted_page = NULL,
 	};
+	struct blk_plug plug;
 
 	if (unlikely(type == META_POR))
 		fio.rw &= ~REQ_META;
 
+	blk_start_plug(&plug);
 	for (; nrpages-- > 0; blkno++) {
 
 		if (!is_valid_blkaddr(sbi, blkno, type))
@@ -167,27 +169,24 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 					NAT_BLOCK_OFFSET(NM_I(sbi)->max_nid)))
 				blkno = 0;
 			/* get nat block addr */
-			fio.blk_addr = current_nat_addr(sbi,
+			fio.new_blkaddr = current_nat_addr(sbi,
 					blkno * NAT_ENTRY_PER_BLOCK);
 			break;
 		case META_SIT:
 			/* get sit block addr */
-			fio.blk_addr = current_sit_addr(sbi,
+			fio.new_blkaddr = current_sit_addr(sbi,
 					blkno * SIT_ENTRY_PER_BLOCK);
-			if (blkno != start && prev_blk_addr + 1 != fio.blk_addr)
-				goto out;
-			prev_blk_addr = fio.blk_addr;
 			break;
 		case META_SSA:
 		case META_CP:
 		case META_POR:
-			fio.blk_addr = blkno;
+			fio.new_blkaddr = blkno;
 			break;
 		default:
 			BUG();
 		}
 
-		page = grab_cache_page(META_MAPPING(sbi), fio.blk_addr);
+		page = grab_cache_page(META_MAPPING(sbi), fio.new_blkaddr);
 		if (!page)
 			continue;
 		if (PageUptodate(page)) {
@@ -196,11 +195,13 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 		}
 
 		fio.page = page;
+		fio.old_blkaddr = fio.new_blkaddr;
 		f2fs_submit_page_mbio(&fio);
 		f2fs_put_page(page, 0);
 	}
 out:
 	f2fs_submit_merged_bio(sbi, META, READ);
+	blk_finish_plug(&plug);
 	return blkno - start;
 }
 
@@ -232,13 +233,17 @@ static int f2fs_write_meta_page(struct page *page,
 	if (unlikely(f2fs_cp_error(sbi)))
 		goto redirty_out;
 
-	f2fs_wait_on_page_writeback(page, META);
 	write_meta_page(sbi, page);
 	dec_page_count(sbi, F2FS_DIRTY_META);
-	unlock_page(page);
 
 	if (wbc->for_reclaim)
+		f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, META, WRITE);
+
+	unlock_page(page);
+
+	if (unlikely(f2fs_cp_error(sbi)))
 		f2fs_submit_merged_bio(sbi, META, WRITE);
+
 	return 0;
 
 redirty_out:
@@ -252,13 +257,13 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
 	struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
 	long diff, written;
 
-	trace_f2fs_writepages(mapping->host, wbc, META);
-
 	/* collect a number of dirty meta pages and write together */
 	if (wbc->for_kupdate ||
 		get_pages(sbi, F2FS_DIRTY_META) < nr_pages_to_skip(sbi, META))
 		goto skip_write;
 
+	trace_f2fs_writepages(mapping->host, wbc, META);
+
 	/* if mounting is failed, skip writing node pages */
 	mutex_lock(&sbi->cp_mutex);
 	diff = nr_pages_to_write(sbi, META, wbc);
@@ -269,6 +274,7 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
 
 skip_write:
 	wbc->pages_skipped += get_pages(sbi, F2FS_DIRTY_META);
+	trace_f2fs_writepages(mapping->host, wbc, META);
 	return 0;
 }
 
@@ -276,15 +282,18 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
 						long nr_to_write)
 {
 	struct address_space *mapping = META_MAPPING(sbi);
-	pgoff_t index = 0, end = LONG_MAX, prev = LONG_MAX;
+	pgoff_t index = 0, end = ULONG_MAX, prev = ULONG_MAX;
 	struct pagevec pvec;
 	long nwritten = 0;
 	struct writeback_control wbc = {
 		.for_reclaim = 0,
 	};
+	struct blk_plug plug;
 
 	pagevec_init(&pvec, 0);
 
+	blk_start_plug(&plug);
+
 	while (index <= end) {
 		int i, nr_pages;
 		nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
@@ -296,7 +305,7 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 
-			if (prev == LONG_MAX)
+			if (prev == ULONG_MAX)
 				prev = page->index - 1;
 			if (nr_to_write != LONG_MAX && page->index != prev + 1) {
 				pagevec_release(&pvec);
@@ -315,6 +324,9 @@ continue_unlock:
 				goto continue_unlock;
 			}
 
+			f2fs_wait_on_page_writeback(page, META, true);
+
+			BUG_ON(PageWriteback(page));
 			if (!clear_page_dirty_for_io(page))
 				goto continue_unlock;
 
@@ -334,6 +346,8 @@ stop:
 	if (nwritten)
 		f2fs_submit_merged_bio(sbi, type, WRITE);
 
+	blk_finish_plug(&plug);
+
 	return nwritten;
 }
 
@@ -410,13 +424,13 @@ static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
 	spin_unlock(&im->ino_lock);
 }
 
-void add_dirty_inode(struct f2fs_sb_info *sbi, nid_t ino, int type)
+void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
 {
 	/* add new dirty ino entry into list */
 	__add_ino_entry(sbi, ino, type);
 }
 
-void remove_dirty_inode(struct f2fs_sb_info *sbi, nid_t ino, int type)
+void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
 {
 	/* remove dirty ino entry from list */
 	__remove_ino_entry(sbi, ino, type);
@@ -434,7 +448,7 @@ bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode)
 	return e ? true : false;
 }
 
-void release_dirty_inode(struct f2fs_sb_info *sbi)
+void release_ino_entry(struct f2fs_sb_info *sbi)
 {
 	struct ino_entry *e, *tmp;
 	int i;
@@ -621,7 +635,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 		goto invalid_cp1;
 
 	crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
-	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
+	if (!f2fs_crc_valid(sbi, crc, cp_block, crc_offset))
 		goto invalid_cp1;
 
 	pre_version = cur_cp_version(cp_block);
@@ -636,7 +650,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 		goto invalid_cp2;
 
 	crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
-	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
+	if (!f2fs_crc_valid(sbi, crc, cp_block, crc_offset))
 		goto invalid_cp2;
 
 	cur_version = cur_cp_version(cp_block);
@@ -696,6 +710,10 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
 	cp_block = (struct f2fs_checkpoint *)page_address(cur_page);
 	memcpy(sbi->ckpt, cp_block, blk_size);
 
+	/* Sanity checking of checkpoint */
+	if (sanity_check_ckpt(sbi))
+		goto fail_no_cp;
+
 	if (cp_blks <= 1)
 		goto done;
 
@@ -722,47 +740,48 @@ fail_no_cp:
 	return -EINVAL;
 }
 
-static int __add_dirty_inode(struct inode *inode, struct inode_entry *new)
+static void __add_dirty_inode(struct inode *inode, enum inode_type type)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+	int flag = (type == DIR_INODE) ? FI_DIRTY_DIR : FI_DIRTY_FILE;
 
-	if (is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR))
-		return -EEXIST;
+	if (is_inode_flag_set(fi, flag))
+		return;
 
-	set_inode_flag(F2FS_I(inode), FI_DIRTY_DIR);
-	F2FS_I(inode)->dirty_dir = new;
-	list_add_tail(&new->list, &sbi->dir_inode_list);
-	stat_inc_dirty_dir(sbi);
-	return 0;
+	set_inode_flag(fi, flag);
+	list_add_tail(&fi->dirty_list, &sbi->inode_list[type]);
+	stat_inc_dirty_inode(sbi, type);
+}
+
+static void __remove_dirty_inode(struct inode *inode, enum inode_type type)
+{
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+	int flag = (type == DIR_INODE) ? FI_DIRTY_DIR : FI_DIRTY_FILE;
+
+	if (get_dirty_pages(inode) ||
+			!is_inode_flag_set(F2FS_I(inode), flag))
+		return;
+
+	list_del_init(&fi->dirty_list);
+	clear_inode_flag(fi, flag);
+	stat_dec_dirty_inode(F2FS_I_SB(inode), type);
 }
 
 void update_dirty_page(struct inode *inode, struct page *page)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct inode_entry *new;
-	int ret = 0;
+	enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE;
 
 	if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
 			!S_ISLNK(inode->i_mode))
 		return;
 
-	if (!S_ISDIR(inode->i_mode)) {
-		inode_inc_dirty_pages(inode);
-		goto out;
-	}
-
-	new = f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
-	new->inode = inode;
-	INIT_LIST_HEAD(&new->list);
-
-	spin_lock(&sbi->dir_inode_lock);
-	ret = __add_dirty_inode(inode, new);
+	spin_lock(&sbi->inode_lock[type]);
+	__add_dirty_inode(inode, type);
 	inode_inc_dirty_pages(inode);
-	spin_unlock(&sbi->dir_inode_lock);
+	spin_unlock(&sbi->inode_lock[type]);
 
-	if (ret)
-		kmem_cache_free(inode_entry_slab, new);
-out:
 	SetPagePrivate(page);
 	f2fs_trace_pid(page);
 }
@@ -770,70 +789,60 @@ out:
 void add_dirty_dir_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct inode_entry *new =
-			f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
-	int ret = 0;
 
-	new->inode = inode;
-	INIT_LIST_HEAD(&new->list);
-
-	spin_lock(&sbi->dir_inode_lock);
-	ret = __add_dirty_inode(inode, new);
-	spin_unlock(&sbi->dir_inode_lock);
-
-	if (ret)
-		kmem_cache_free(inode_entry_slab, new);
+	spin_lock(&sbi->inode_lock[DIR_INODE]);
+	__add_dirty_inode(inode, DIR_INODE);
+	spin_unlock(&sbi->inode_lock[DIR_INODE]);
 }
 
-void remove_dirty_dir_inode(struct inode *inode)
+void remove_dirty_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct inode_entry *entry;
-
-	if (!S_ISDIR(inode->i_mode))
-		return;
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+	enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE;
 
-	spin_lock(&sbi->dir_inode_lock);
-	if (get_dirty_pages(inode) ||
-			!is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR)) {
-		spin_unlock(&sbi->dir_inode_lock);
+	if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
+			!S_ISLNK(inode->i_mode))
 		return;
-	}
 
-	entry = F2FS_I(inode)->dirty_dir;
-	list_del(&entry->list);
-	F2FS_I(inode)->dirty_dir = NULL;
-	clear_inode_flag(F2FS_I(inode), FI_DIRTY_DIR);
-	stat_dec_dirty_dir(sbi);
-	spin_unlock(&sbi->dir_inode_lock);
-	kmem_cache_free(inode_entry_slab, entry);
+	spin_lock(&sbi->inode_lock[type]);
+	__remove_dirty_inode(inode, type);
+	spin_unlock(&sbi->inode_lock[type]);
 
 	/* Only from the recovery routine */
-	if (is_inode_flag_set(F2FS_I(inode), FI_DELAY_IPUT)) {
-		clear_inode_flag(F2FS_I(inode), FI_DELAY_IPUT);
+	if (is_inode_flag_set(fi, FI_DELAY_IPUT)) {
+		clear_inode_flag(fi, FI_DELAY_IPUT);
 		iput(inode);
 	}
 }
 
-void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi)
+int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
 {
 	struct list_head *head;
-	struct inode_entry *entry;
 	struct inode *inode;
+	struct f2fs_inode_info *fi;
+	bool is_dir = (type == DIR_INODE);
+
+	trace_f2fs_sync_dirty_inodes_enter(sbi->sb, is_dir,
+				get_pages(sbi, is_dir ?
+				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
 retry:
 	if (unlikely(f2fs_cp_error(sbi)))
-		return;
+		return -EIO;
 
-	spin_lock(&sbi->dir_inode_lock);
+	spin_lock(&sbi->inode_lock[type]);
 
-	head = &sbi->dir_inode_list;
+	head = &sbi->inode_list[type];
 	if (list_empty(head)) {
-		spin_unlock(&sbi->dir_inode_lock);
-		return;
+		spin_unlock(&sbi->inode_lock[type]);
+		trace_f2fs_sync_dirty_inodes_exit(sbi->sb, is_dir,
+				get_pages(sbi, is_dir ?
+				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
+		return 0;
 	}
-	entry = list_entry(head->next, struct inode_entry, list);
-	inode = igrab(entry->inode);
-	spin_unlock(&sbi->dir_inode_lock);
+	fi = list_entry(head->next, struct f2fs_inode_info, dirty_list);
+	inode = igrab(&fi->vfs_inode);
+	spin_unlock(&sbi->inode_lock[type]);
 	if (inode) {
 		filemap_fdatawrite(inode->i_mapping);
 		iput(inode);
@@ -868,11 +877,9 @@ retry_flush_dents:
 	/* write all the dirty dentry pages */
 	if (get_pages(sbi, F2FS_DIRTY_DENTS)) {
 		f2fs_unlock_all(sbi);
-		sync_dirty_dir_inodes(sbi);
-		if (unlikely(f2fs_cp_error(sbi))) {
-			err = -EIO;
+		err = sync_dirty_inodes(sbi, DIR_INODE);
+		if (err)
 			goto out;
-		}
 		goto retry_flush_dents;
 	}
 
@@ -885,10 +892,9 @@ retry_flush_nodes:
 
 	if (get_pages(sbi, F2FS_DIRTY_NODES)) {
 		up_write(&sbi->node_write);
-		sync_node_pages(sbi, 0, &wbc);
-		if (unlikely(f2fs_cp_error(sbi))) {
+		err = sync_node_pages(sbi, 0, &wbc);
+		if (err) {
 			f2fs_unlock_all(sbi);
-			err = -EIO;
 			goto out;
 		}
 		goto retry_flush_nodes;
@@ -914,12 +920,12 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
 		if (!get_pages(sbi, F2FS_WRITEBACK))
 			break;
 
-		io_schedule();
+		io_schedule_timeout(5*HZ);
 	}
 	finish_wait(&sbi->cp_wait, &wait);
 }
 
-static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
+static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
@@ -933,6 +939,9 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	int cp_payload_blks = __cp_payload(sbi);
 	block_t discard_blk = NEXT_FREE_BLKADDR(sbi, curseg);
 	bool invalidate = false;
+	struct super_block *sb = sbi->sb;
+	struct curseg_info *seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
+	u64 kbytes_written;
 
 	/*
 	 * This avoids to conduct wrong roll-forward operations and uses
@@ -945,7 +954,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	while (get_pages(sbi, F2FS_DIRTY_META)) {
 		sync_meta_pages(sbi, META, LONG_MAX);
 		if (unlikely(f2fs_cp_error(sbi)))
-			return;
+			return -EIO;
 	}
 
 	next_free_nid(sbi, &last_nid);
@@ -1020,7 +1029,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP));
 	get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP));
 
-	crc32 = f2fs_crc32(ckpt, le32_to_cpu(ckpt->checksum_offset));
+	crc32 = f2fs_crc32(sbi, ckpt, le32_to_cpu(ckpt->checksum_offset));
 	*((__le32 *)((unsigned char *)ckpt +
 				le32_to_cpu(ckpt->checksum_offset)))
 				= cpu_to_le32(crc32);
@@ -1030,7 +1039,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	/* need to wait for end_io results */
 	wait_on_all_pages_writeback(sbi);
 	if (unlikely(f2fs_cp_error(sbi)))
-		return;
+		return -EIO;
 
 	/* write out checkpoint buffer at block 0 */
 	update_meta_page(sbi, ckpt, start_blk++);
@@ -1046,6 +1055,14 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	write_data_summaries(sbi, start_blk);
 	start_blk += data_sum_blocks;
+
+	/* Record write statistics in the hot node summary */
+	kbytes_written = sbi->kbytes_written;
+	if (sb->s_bdev->bd_part)
+		kbytes_written += BD_PART_WRITTEN(sbi);
+
+	seg_i->journal->info.kbytes_written = cpu_to_le64(kbytes_written);
+
 	if (__remain_node_summaries(cpc->reason)) {
 		write_node_summaries(sbi, start_blk);
 		start_blk += NR_CURSEG_NODE_TYPE;
@@ -1058,10 +1075,10 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	wait_on_all_pages_writeback(sbi);
 
 	if (unlikely(f2fs_cp_error(sbi)))
-		return;
+		return -EIO;
 
-	filemap_fdatawait_range(NODE_MAPPING(sbi), 0, LONG_MAX);
-	filemap_fdatawait_range(META_MAPPING(sbi), 0, LONG_MAX);
+	filemap_fdatawait_range(NODE_MAPPING(sbi), 0, LLONG_MAX);
+	filemap_fdatawait_range(META_MAPPING(sbi), 0, LLONG_MAX);
 
 	/* update user_block_counts */
 	sbi->last_valid_block_count = sbi->total_valid_block_count;
@@ -1081,22 +1098,25 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 		invalidate_mapping_pages(META_MAPPING(sbi), discard_blk,
 								discard_blk);
 
-	release_dirty_inode(sbi);
+	release_ino_entry(sbi);
 
 	if (unlikely(f2fs_cp_error(sbi)))
-		return;
+		return -EIO;
 
 	clear_prefree_segments(sbi, cpc);
 	clear_sbi_flag(sbi, SBI_IS_DIRTY);
+
+	return 0;
 }
 
 /*
  * We guarantee that this checkpoint procedure will not fail.
  */
-void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
+int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
 	unsigned long long ckpt_ver;
+	int err = 0;
 
 	mutex_lock(&sbi->cp_mutex);
 
@@ -1104,21 +1124,24 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 		(cpc->reason == CP_FASTBOOT || cpc->reason == CP_SYNC ||
 		(cpc->reason == CP_DISCARD && !sbi->discard_blks)))
 		goto out;
-	if (unlikely(f2fs_cp_error(sbi)))
+	if (unlikely(f2fs_cp_error(sbi))) {
+		err = -EIO;
 		goto out;
-	if (f2fs_readonly(sbi->sb))
+	}
+	if (f2fs_readonly(sbi->sb)) {
+		err = -EROFS;
 		goto out;
+	}
 
 	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "start block_ops");
 
-	if (block_operations(sbi))
+	err = block_operations(sbi);
+	if (err)
 		goto out;
 
 	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish block_ops");
 
-	f2fs_submit_merged_bio(sbi, DATA, WRITE);
-	f2fs_submit_merged_bio(sbi, NODE, WRITE);
-	f2fs_submit_merged_bio(sbi, META, WRITE);
+	f2fs_flush_merged_bios(sbi);
 
 	/*
 	 * update checkpoint pack index
@@ -1133,7 +1156,7 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	flush_sit_entries(sbi, cpc);
 
 	/* unlock all the fs_lock[] in do_checkpoint() */
-	do_checkpoint(sbi, cpc);
+	err = do_checkpoint(sbi, cpc);
 
 	unblock_operations(sbi);
 	stat_inc_cp_count(sbi->stat_info);
@@ -1143,10 +1166,11 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			"checkpoint: version = %llx", ckpt_ver);
 
 	/* do checkpoint periodically */
-	sbi->cp_expires = round_jiffies_up(jiffies + HZ * sbi->cp_interval);
+	f2fs_update_time(sbi, CP_TIME);
+	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint");
 out:
 	mutex_unlock(&sbi->cp_mutex);
-	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint");
+	return err;
 }
 
 void init_ino_entry_info(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/crypto.c b/fs/f2fs/crypto.c
deleted file mode 100644
index 4a62ef14e932..000000000000
--- a/fs/f2fs/crypto.c
+++ /dev/null
@@ -1,491 +0,0 @@
-/*
- * linux/fs/f2fs/crypto.c
- *
- * Copied from linux/fs/ext4/crypto.c
- *
- * Copyright (C) 2015, Google, Inc.
- * Copyright (C) 2015, Motorola Mobility
- *
- * This contains encryption functions for f2fs
- *
- * Written by Michael Halcrow, 2014.
- *
- * Filename encryption additions
- *	Uday Savagaonkar, 2014
- * Encryption policy handling additions
- *	Ildar Muslukhov, 2014
- * Remove ext4_encrypted_zeroout(),
- *   add f2fs_restore_and_release_control_page()
- *	Jaegeuk Kim, 2015.
- *
- * This has not yet undergone a rigorous security audit.
- *
- * The usage of AES-XTS should conform to recommendations in NIST
- * Special Publication 800-38E and IEEE P1619/D16.
- */
-#include <crypto/hash.h>
-#include <crypto/sha.h>
-#include <keys/user-type.h>
-#include <keys/encrypted-type.h>
-#include <linux/crypto.h>
-#include <linux/ecryptfs.h>
-#include <linux/gfp.h>
-#include <linux/kernel.h>
-#include <linux/key.h>
-#include <linux/list.h>
-#include <linux/mempool.h>
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/random.h>
-#include <linux/scatterlist.h>
-#include <linux/spinlock_types.h>
-#include <linux/f2fs_fs.h>
-#include <linux/ratelimit.h>
-#include <linux/bio.h>
-
-#include "f2fs.h"
-#include "xattr.h"
-
-/* Encryption added and removed here! (L: */
-
-static unsigned int num_prealloc_crypto_pages = 32;
-static unsigned int num_prealloc_crypto_ctxs = 128;
-
-module_param(num_prealloc_crypto_pages, uint, 0444);
-MODULE_PARM_DESC(num_prealloc_crypto_pages,
-		"Number of crypto pages to preallocate");
-module_param(num_prealloc_crypto_ctxs, uint, 0444);
-MODULE_PARM_DESC(num_prealloc_crypto_ctxs,
-		"Number of crypto contexts to preallocate");
-
-static mempool_t *f2fs_bounce_page_pool;
-
-static LIST_HEAD(f2fs_free_crypto_ctxs);
-static DEFINE_SPINLOCK(f2fs_crypto_ctx_lock);
-
-static struct workqueue_struct *f2fs_read_workqueue;
-static DEFINE_MUTEX(crypto_init);
-
-static struct kmem_cache *f2fs_crypto_ctx_cachep;
-struct kmem_cache *f2fs_crypt_info_cachep;
-
-/**
- * f2fs_release_crypto_ctx() - Releases an encryption context
- * @ctx: The encryption context to release.
- *
- * If the encryption context was allocated from the pre-allocated pool, returns
- * it to that pool. Else, frees it.
- *
- * If there's a bounce page in the context, this frees that.
- */
-void f2fs_release_crypto_ctx(struct f2fs_crypto_ctx *ctx)
-{
-	unsigned long flags;
-
-	if (ctx->flags & F2FS_WRITE_PATH_FL && ctx->w.bounce_page) {
-		mempool_free(ctx->w.bounce_page, f2fs_bounce_page_pool);
-		ctx->w.bounce_page = NULL;
-	}
-	ctx->w.control_page = NULL;
-	if (ctx->flags & F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL) {
-		kmem_cache_free(f2fs_crypto_ctx_cachep, ctx);
-	} else {
-		spin_lock_irqsave(&f2fs_crypto_ctx_lock, flags);
-		list_add(&ctx->free_list, &f2fs_free_crypto_ctxs);
-		spin_unlock_irqrestore(&f2fs_crypto_ctx_lock, flags);
-	}
-}
-
-/**
- * f2fs_get_crypto_ctx() - Gets an encryption context
- * @inode:       The inode for which we are doing the crypto
- *
- * Allocates and initializes an encryption context.
- *
- * Return: An allocated and initialized encryption context on success; error
- * value or NULL otherwise.
- */
-struct f2fs_crypto_ctx *f2fs_get_crypto_ctx(struct inode *inode)
-{
-	struct f2fs_crypto_ctx *ctx = NULL;
-	unsigned long flags;
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
-
-	if (ci == NULL)
-		return ERR_PTR(-ENOKEY);
-
-	/*
-	 * We first try getting the ctx from a free list because in
-	 * the common case the ctx will have an allocated and
-	 * initialized crypto tfm, so it's probably a worthwhile
-	 * optimization. For the bounce page, we first try getting it
-	 * from the kernel allocator because that's just about as fast
-	 * as getting it from a list and because a cache of free pages
-	 * should generally be a "last resort" option for a filesystem
-	 * to be able to do its job.
-	 */
-	spin_lock_irqsave(&f2fs_crypto_ctx_lock, flags);
-	ctx = list_first_entry_or_null(&f2fs_free_crypto_ctxs,
-					struct f2fs_crypto_ctx, free_list);
-	if (ctx)
-		list_del(&ctx->free_list);
-	spin_unlock_irqrestore(&f2fs_crypto_ctx_lock, flags);
-	if (!ctx) {
-		ctx = kmem_cache_zalloc(f2fs_crypto_ctx_cachep, GFP_NOFS);
-		if (!ctx)
-			return ERR_PTR(-ENOMEM);
-		ctx->flags |= F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
-	} else {
-		ctx->flags &= ~F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
-	}
-	ctx->flags &= ~F2FS_WRITE_PATH_FL;
-	return ctx;
-}
-
-/*
- * Call f2fs_decrypt on every single page, reusing the encryption
- * context.
- */
-static void completion_pages(struct work_struct *work)
-{
-	struct f2fs_crypto_ctx *ctx =
-		container_of(work, struct f2fs_crypto_ctx, r.work);
-	struct bio *bio = ctx->r.bio;
-	struct bio_vec *bv;
-	int i;
-
-	bio_for_each_segment_all(bv, bio, i) {
-		struct page *page = bv->bv_page;
-		int ret = f2fs_decrypt(ctx, page);
-
-		if (ret) {
-			WARN_ON_ONCE(1);
-			SetPageError(page);
-		} else
-			SetPageUptodate(page);
-		unlock_page(page);
-	}
-	f2fs_release_crypto_ctx(ctx);
-	bio_put(bio);
-}
-
-void f2fs_end_io_crypto_work(struct f2fs_crypto_ctx *ctx, struct bio *bio)
-{
-	INIT_WORK(&ctx->r.work, completion_pages);
-	ctx->r.bio = bio;
-	queue_work(f2fs_read_workqueue, &ctx->r.work);
-}
-
-static void f2fs_crypto_destroy(void)
-{
-	struct f2fs_crypto_ctx *pos, *n;
-
-	list_for_each_entry_safe(pos, n, &f2fs_free_crypto_ctxs, free_list)
-		kmem_cache_free(f2fs_crypto_ctx_cachep, pos);
-	INIT_LIST_HEAD(&f2fs_free_crypto_ctxs);
-	if (f2fs_bounce_page_pool)
-		mempool_destroy(f2fs_bounce_page_pool);
-	f2fs_bounce_page_pool = NULL;
-}
-
-/**
- * f2fs_crypto_initialize() - Set up for f2fs encryption.
- *
- * We only call this when we start accessing encrypted files, since it
- * results in memory getting allocated that wouldn't otherwise be used.
- *
- * Return: Zero on success, non-zero otherwise.
- */
-int f2fs_crypto_initialize(void)
-{
-	int i, res = -ENOMEM;
-
-	if (f2fs_bounce_page_pool)
-		return 0;
-
-	mutex_lock(&crypto_init);
-	if (f2fs_bounce_page_pool)
-		goto already_initialized;
-
-	for (i = 0; i < num_prealloc_crypto_ctxs; i++) {
-		struct f2fs_crypto_ctx *ctx;
-
-		ctx = kmem_cache_zalloc(f2fs_crypto_ctx_cachep, GFP_KERNEL);
-		if (!ctx)
-			goto fail;
-		list_add(&ctx->free_list, &f2fs_free_crypto_ctxs);
-	}
-
-	/* must be allocated at the last step to avoid race condition above */
-	f2fs_bounce_page_pool =
-		mempool_create_page_pool(num_prealloc_crypto_pages, 0);
-	if (!f2fs_bounce_page_pool)
-		goto fail;
-
-already_initialized:
-	mutex_unlock(&crypto_init);
-	return 0;
-fail:
-	f2fs_crypto_destroy();
-	mutex_unlock(&crypto_init);
-	return res;
-}
-
-/**
- * f2fs_exit_crypto() - Shutdown the f2fs encryption system
- */
-void f2fs_exit_crypto(void)
-{
-	f2fs_crypto_destroy();
-
-	if (f2fs_read_workqueue)
-		destroy_workqueue(f2fs_read_workqueue);
-	if (f2fs_crypto_ctx_cachep)
-		kmem_cache_destroy(f2fs_crypto_ctx_cachep);
-	if (f2fs_crypt_info_cachep)
-		kmem_cache_destroy(f2fs_crypt_info_cachep);
-}
-
-int __init f2fs_init_crypto(void)
-{
-	int res = -ENOMEM;
-
-	f2fs_read_workqueue = alloc_workqueue("f2fs_crypto", WQ_HIGHPRI, 0);
-	if (!f2fs_read_workqueue)
-		goto fail;
-
-	f2fs_crypto_ctx_cachep = KMEM_CACHE(f2fs_crypto_ctx,
-						SLAB_RECLAIM_ACCOUNT);
-	if (!f2fs_crypto_ctx_cachep)
-		goto fail;
-
-	f2fs_crypt_info_cachep = KMEM_CACHE(f2fs_crypt_info,
-						SLAB_RECLAIM_ACCOUNT);
-	if (!f2fs_crypt_info_cachep)
-		goto fail;
-
-	return 0;
-fail:
-	f2fs_exit_crypto();
-	return res;
-}
-
-void f2fs_restore_and_release_control_page(struct page **page)
-{
-	struct f2fs_crypto_ctx *ctx;
-	struct page *bounce_page;
-
-	/* The bounce data pages are unmapped. */
-	if ((*page)->mapping)
-		return;
-
-	/* The bounce data page is unmapped. */
-	bounce_page = *page;
-	ctx = (struct f2fs_crypto_ctx *)page_private(bounce_page);
-
-	/* restore control page */
-	*page = ctx->w.control_page;
-
-	f2fs_restore_control_page(bounce_page);
-}
-
-void f2fs_restore_control_page(struct page *data_page)
-{
-	struct f2fs_crypto_ctx *ctx =
-		(struct f2fs_crypto_ctx *)page_private(data_page);
-
-	set_page_private(data_page, (unsigned long)NULL);
-	ClearPagePrivate(data_page);
-	unlock_page(data_page);
-	f2fs_release_crypto_ctx(ctx);
-}
-
-/**
- * f2fs_crypt_complete() - The completion callback for page encryption
- * @req: The asynchronous encryption request context
- * @res: The result of the encryption operation
- */
-static void f2fs_crypt_complete(struct crypto_async_request *req, int res)
-{
-	struct f2fs_completion_result *ecr = req->data;
-
-	if (res == -EINPROGRESS)
-		return;
-	ecr->res = res;
-	complete(&ecr->completion);
-}
-
-typedef enum {
-	F2FS_DECRYPT = 0,
-	F2FS_ENCRYPT,
-} f2fs_direction_t;
-
-static int f2fs_page_crypto(struct f2fs_crypto_ctx *ctx,
-				struct inode *inode,
-				f2fs_direction_t rw,
-				pgoff_t index,
-				struct page *src_page,
-				struct page *dest_page)
-{
-	u8 xts_tweak[F2FS_XTS_TWEAK_SIZE];
-	struct ablkcipher_request *req = NULL;
-	DECLARE_F2FS_COMPLETION_RESULT(ecr);
-	struct scatterlist dst, src;
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
-	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
-	int res = 0;
-
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
-	if (!req) {
-		printk_ratelimited(KERN_ERR
-				"%s: crypto_request_alloc() failed\n",
-				__func__);
-		return -ENOMEM;
-	}
-	ablkcipher_request_set_callback(
-		req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
-		f2fs_crypt_complete, &ecr);
-
-	BUILD_BUG_ON(F2FS_XTS_TWEAK_SIZE < sizeof(index));
-	memcpy(xts_tweak, &index, sizeof(index));
-	memset(&xts_tweak[sizeof(index)], 0,
-			F2FS_XTS_TWEAK_SIZE - sizeof(index));
-
-	sg_init_table(&dst, 1);
-	sg_set_page(&dst, dest_page, PAGE_CACHE_SIZE, 0);
-	sg_init_table(&src, 1);
-	sg_set_page(&src, src_page, PAGE_CACHE_SIZE, 0);
-	ablkcipher_request_set_crypt(req, &src, &dst, PAGE_CACHE_SIZE,
-					xts_tweak);
-	if (rw == F2FS_DECRYPT)
-		res = crypto_ablkcipher_decrypt(req);
-	else
-		res = crypto_ablkcipher_encrypt(req);
-	if (res == -EINPROGRESS || res == -EBUSY) {
-		BUG_ON(req->base.data != &ecr);
-		wait_for_completion(&ecr.completion);
-		res = ecr.res;
-	}
-	ablkcipher_request_free(req);
-	if (res) {
-		printk_ratelimited(KERN_ERR
-			"%s: crypto_ablkcipher_encrypt() returned %d\n",
-			__func__, res);
-		return res;
-	}
-	return 0;
-}
-
-static struct page *alloc_bounce_page(struct f2fs_crypto_ctx *ctx)
-{
-	ctx->w.bounce_page = mempool_alloc(f2fs_bounce_page_pool, GFP_NOWAIT);
-	if (ctx->w.bounce_page == NULL)
-		return ERR_PTR(-ENOMEM);
-	ctx->flags |= F2FS_WRITE_PATH_FL;
-	return ctx->w.bounce_page;
-}
-
-/**
- * f2fs_encrypt() - Encrypts a page
- * @inode:          The inode for which the encryption should take place
- * @plaintext_page: The page to encrypt. Must be locked.
- *
- * Allocates a ciphertext page and encrypts plaintext_page into it using the ctx
- * encryption context.
- *
- * Called on the page write path.  The caller must call
- * f2fs_restore_control_page() on the returned ciphertext page to
- * release the bounce buffer and the encryption context.
- *
- * Return: An allocated page with the encrypted content on success. Else, an
- * error value or NULL.
- */
-struct page *f2fs_encrypt(struct inode *inode,
-			  struct page *plaintext_page)
-{
-	struct f2fs_crypto_ctx *ctx;
-	struct page *ciphertext_page = NULL;
-	int err;
-
-	BUG_ON(!PageLocked(plaintext_page));
-
-	ctx = f2fs_get_crypto_ctx(inode);
-	if (IS_ERR(ctx))
-		return (struct page *)ctx;
-
-	/* The encryption operation will require a bounce page. */
-	ciphertext_page = alloc_bounce_page(ctx);
-	if (IS_ERR(ciphertext_page))
-		goto err_out;
-
-	ctx->w.control_page = plaintext_page;
-	err = f2fs_page_crypto(ctx, inode, F2FS_ENCRYPT, plaintext_page->index,
-					plaintext_page, ciphertext_page);
-	if (err) {
-		ciphertext_page = ERR_PTR(err);
-		goto err_out;
-	}
-
-	SetPagePrivate(ciphertext_page);
-	set_page_private(ciphertext_page, (unsigned long)ctx);
-	lock_page(ciphertext_page);
-	return ciphertext_page;
-
-err_out:
-	f2fs_release_crypto_ctx(ctx);
-	return ciphertext_page;
-}
-
-/**
- * f2fs_decrypt() - Decrypts a page in-place
- * @ctx:  The encryption context.
- * @page: The page to decrypt. Must be locked.
- *
- * Decrypts page in-place using the ctx encryption context.
- *
- * Called from the read completion callback.
- *
- * Return: Zero on success, non-zero otherwise.
- */
-int f2fs_decrypt(struct f2fs_crypto_ctx *ctx, struct page *page)
-{
-	BUG_ON(!PageLocked(page));
-
-	return f2fs_page_crypto(ctx, page->mapping->host,
-				F2FS_DECRYPT, page->index, page, page);
-}
-
-/*
- * Convenience function which takes care of allocating and
- * deallocating the encryption context
- */
-int f2fs_decrypt_one(struct inode *inode, struct page *page)
-{
-	struct f2fs_crypto_ctx *ctx = f2fs_get_crypto_ctx(inode);
-	int ret;
-
-	if (IS_ERR(ctx))
-		return PTR_ERR(ctx);
-	ret = f2fs_decrypt(ctx, page);
-	f2fs_release_crypto_ctx(ctx);
-	return ret;
-}
-
-bool f2fs_valid_contents_enc_mode(uint32_t mode)
-{
-	return (mode == F2FS_ENCRYPTION_MODE_AES_256_XTS);
-}
-
-/**
- * f2fs_validate_encryption_key_size() - Validate the encryption key size
- * @mode: The key mode.
- * @size: The key size to validate.
- *
- * Return: The validated key size for @mode. Zero if invalid.
- */
-uint32_t f2fs_validate_encryption_key_size(uint32_t mode, uint32_t size)
-{
-	if (size == f2fs_encryption_key_size(mode))
-		return size;
-	return 0;
-}
diff --git a/fs/f2fs/crypto_key.c b/fs/f2fs/crypto_key.c
deleted file mode 100644
index 5de2d866a25c..000000000000
--- a/fs/f2fs/crypto_key.c
+++ /dev/null
@@ -1,254 +0,0 @@
-/*
- * linux/fs/f2fs/crypto_key.c
- *
- * Copied from linux/fs/f2fs/crypto_key.c
- *
- * Copyright (C) 2015, Google, Inc.
- *
- * This contains encryption key functions for f2fs
- *
- * Written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar, 2015.
- */
-#include <keys/encrypted-type.h>
-#include <keys/user-type.h>
-#include <linux/random.h>
-#include <linux/scatterlist.h>
-#include <uapi/linux/keyctl.h>
-#include <crypto/hash.h>
-#include <linux/f2fs_fs.h>
-
-#include "f2fs.h"
-#include "xattr.h"
-
-static void derive_crypt_complete(struct crypto_async_request *req, int rc)
-{
-	struct f2fs_completion_result *ecr = req->data;
-
-	if (rc == -EINPROGRESS)
-		return;
-
-	ecr->res = rc;
-	complete(&ecr->completion);
-}
-
-/**
- * f2fs_derive_key_aes() - Derive a key using AES-128-ECB
- * @deriving_key: Encryption key used for derivatio.
- * @source_key:   Source key to which to apply derivation.
- * @derived_key:  Derived key.
- *
- * Return: Zero on success; non-zero otherwise.
- */
-static int f2fs_derive_key_aes(char deriving_key[F2FS_AES_128_ECB_KEY_SIZE],
-				char source_key[F2FS_AES_256_XTS_KEY_SIZE],
-				char derived_key[F2FS_AES_256_XTS_KEY_SIZE])
-{
-	int res = 0;
-	struct ablkcipher_request *req = NULL;
-	DECLARE_F2FS_COMPLETION_RESULT(ecr);
-	struct scatterlist src_sg, dst_sg;
-	struct crypto_ablkcipher *tfm = crypto_alloc_ablkcipher("ecb(aes)", 0,
-								0);
-
-	if (IS_ERR(tfm)) {
-		res = PTR_ERR(tfm);
-		tfm = NULL;
-		goto out;
-	}
-	crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
-	if (!req) {
-		res = -ENOMEM;
-		goto out;
-	}
-	ablkcipher_request_set_callback(req,
-			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
-			derive_crypt_complete, &ecr);
-	res = crypto_ablkcipher_setkey(tfm, deriving_key,
-				F2FS_AES_128_ECB_KEY_SIZE);
-	if (res < 0)
-		goto out;
-
-	sg_init_one(&src_sg, source_key, F2FS_AES_256_XTS_KEY_SIZE);
-	sg_init_one(&dst_sg, derived_key, F2FS_AES_256_XTS_KEY_SIZE);
-	ablkcipher_request_set_crypt(req, &src_sg, &dst_sg,
-					F2FS_AES_256_XTS_KEY_SIZE, NULL);
-	res = crypto_ablkcipher_encrypt(req);
-	if (res == -EINPROGRESS || res == -EBUSY) {
-		BUG_ON(req->base.data != &ecr);
-		wait_for_completion(&ecr.completion);
-		res = ecr.res;
-	}
-out:
-	if (req)
-		ablkcipher_request_free(req);
-	if (tfm)
-		crypto_free_ablkcipher(tfm);
-	return res;
-}
-
-static void f2fs_free_crypt_info(struct f2fs_crypt_info *ci)
-{
-	if (!ci)
-		return;
-
-	key_put(ci->ci_keyring_key);
-	crypto_free_ablkcipher(ci->ci_ctfm);
-	kmem_cache_free(f2fs_crypt_info_cachep, ci);
-}
-
-void f2fs_free_encryption_info(struct inode *inode, struct f2fs_crypt_info *ci)
-{
-	struct f2fs_inode_info *fi = F2FS_I(inode);
-	struct f2fs_crypt_info *prev;
-
-	if (ci == NULL)
-		ci = ACCESS_ONCE(fi->i_crypt_info);
-	if (ci == NULL)
-		return;
-	prev = cmpxchg(&fi->i_crypt_info, ci, NULL);
-	if (prev != ci)
-		return;
-
-	f2fs_free_crypt_info(ci);
-}
-
-int _f2fs_get_encryption_info(struct inode *inode)
-{
-	struct f2fs_inode_info *fi = F2FS_I(inode);
-	struct f2fs_crypt_info *crypt_info;
-	char full_key_descriptor[F2FS_KEY_DESC_PREFIX_SIZE +
-				(F2FS_KEY_DESCRIPTOR_SIZE * 2) + 1];
-	struct key *keyring_key = NULL;
-	struct f2fs_encryption_key *master_key;
-	struct f2fs_encryption_context ctx;
-	const struct user_key_payload *ukp;
-	struct crypto_ablkcipher *ctfm;
-	const char *cipher_str;
-	char raw_key[F2FS_MAX_KEY_SIZE];
-	char mode;
-	int res;
-
-	res = f2fs_crypto_initialize();
-	if (res)
-		return res;
-retry:
-	crypt_info = ACCESS_ONCE(fi->i_crypt_info);
-	if (crypt_info) {
-		if (!crypt_info->ci_keyring_key ||
-				key_validate(crypt_info->ci_keyring_key) == 0)
-			return 0;
-		f2fs_free_encryption_info(inode, crypt_info);
-		goto retry;
-	}
-
-	res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
-				F2FS_XATTR_NAME_ENCRYPTION_CONTEXT,
-				&ctx, sizeof(ctx), NULL);
-	if (res < 0)
-		return res;
-	else if (res != sizeof(ctx))
-		return -EINVAL;
-	res = 0;
-
-	crypt_info = kmem_cache_alloc(f2fs_crypt_info_cachep, GFP_NOFS);
-	if (!crypt_info)
-		return -ENOMEM;
-
-	crypt_info->ci_flags = ctx.flags;
-	crypt_info->ci_data_mode = ctx.contents_encryption_mode;
-	crypt_info->ci_filename_mode = ctx.filenames_encryption_mode;
-	crypt_info->ci_ctfm = NULL;
-	crypt_info->ci_keyring_key = NULL;
-	memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor,
-				sizeof(crypt_info->ci_master_key));
-	if (S_ISREG(inode->i_mode))
-		mode = crypt_info->ci_data_mode;
-	else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
-		mode = crypt_info->ci_filename_mode;
-	else
-		BUG();
-
-	switch (mode) {
-	case F2FS_ENCRYPTION_MODE_AES_256_XTS:
-		cipher_str = "xts(aes)";
-		break;
-	case F2FS_ENCRYPTION_MODE_AES_256_CTS:
-		cipher_str = "cts(cbc(aes))";
-		break;
-	default:
-		printk_once(KERN_WARNING
-			    "f2fs: unsupported key mode %d (ino %u)\n",
-			    mode, (unsigned) inode->i_ino);
-		res = -ENOKEY;
-		goto out;
-	}
-
-	memcpy(full_key_descriptor, F2FS_KEY_DESC_PREFIX,
-					F2FS_KEY_DESC_PREFIX_SIZE);
-	sprintf(full_key_descriptor + F2FS_KEY_DESC_PREFIX_SIZE,
-					"%*phN", F2FS_KEY_DESCRIPTOR_SIZE,
-					ctx.master_key_descriptor);
-	full_key_descriptor[F2FS_KEY_DESC_PREFIX_SIZE +
-					(2 * F2FS_KEY_DESCRIPTOR_SIZE)] = '\0';
-	keyring_key = request_key(&key_type_logon, full_key_descriptor, NULL);
-	if (IS_ERR(keyring_key)) {
-		res = PTR_ERR(keyring_key);
-		keyring_key = NULL;
-		goto out;
-	}
-	crypt_info->ci_keyring_key = keyring_key;
-	BUG_ON(keyring_key->type != &key_type_logon);
-	ukp = user_key_payload(keyring_key);
-	if (ukp->datalen != sizeof(struct f2fs_encryption_key)) {
-		res = -EINVAL;
-		goto out;
-	}
-	master_key = (struct f2fs_encryption_key *)ukp->data;
-	BUILD_BUG_ON(F2FS_AES_128_ECB_KEY_SIZE !=
-				F2FS_KEY_DERIVATION_NONCE_SIZE);
-	BUG_ON(master_key->size != F2FS_AES_256_XTS_KEY_SIZE);
-	res = f2fs_derive_key_aes(ctx.nonce, master_key->raw,
-				  raw_key);
-	if (res)
-		goto out;
-
-	ctfm = crypto_alloc_ablkcipher(cipher_str, 0, 0);
-	if (!ctfm || IS_ERR(ctfm)) {
-		res = ctfm ? PTR_ERR(ctfm) : -ENOMEM;
-		printk(KERN_DEBUG
-		       "%s: error %d (inode %u) allocating crypto tfm\n",
-		       __func__, res, (unsigned) inode->i_ino);
-		goto out;
-	}
-	crypt_info->ci_ctfm = ctfm;
-	crypto_ablkcipher_clear_flags(ctfm, ~0);
-	crypto_tfm_set_flags(crypto_ablkcipher_tfm(ctfm),
-			     CRYPTO_TFM_REQ_WEAK_KEY);
-	res = crypto_ablkcipher_setkey(ctfm, raw_key,
-					f2fs_encryption_key_size(mode));
-	if (res)
-		goto out;
-
-	memzero_explicit(raw_key, sizeof(raw_key));
-	if (cmpxchg(&fi->i_crypt_info, NULL, crypt_info) != NULL) {
-		f2fs_free_crypt_info(crypt_info);
-		goto retry;
-	}
-	return 0;
-
-out:
-	if (res == -ENOKEY && !S_ISREG(inode->i_mode))
-		res = 0;
-
-	f2fs_free_crypt_info(crypt_info);
-	memzero_explicit(raw_key, sizeof(raw_key));
-	return res;
-}
-
-int f2fs_has_encryption_key(struct inode *inode)
-{
-	struct f2fs_inode_info *fi = F2FS_I(inode);
-
-	return (fi->i_crypt_info != NULL);
-}
diff --git a/fs/f2fs/crypto_policy.c b/fs/f2fs/crypto_policy.c
deleted file mode 100644
index d4a96af513c2..000000000000
--- a/fs/f2fs/crypto_policy.c
+++ /dev/null
@@ -1,209 +0,0 @@
-/*
- * copied from linux/fs/ext4/crypto_policy.c
- *
- * Copyright (C) 2015, Google, Inc.
- * Copyright (C) 2015, Motorola Mobility.
- *
- * This contains encryption policy functions for f2fs with some modifications
- * to support f2fs-specific xattr APIs.
- *
- * Written by Michael Halcrow, 2015.
- * Modified by Jaegeuk Kim, 2015.
- */
-#include <linux/random.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <linux/f2fs_fs.h>
-
-#include "f2fs.h"
-#include "xattr.h"
-
-static int f2fs_inode_has_encryption_context(struct inode *inode)
-{
-	int res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
-			F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, NULL, 0, NULL);
-	return (res > 0);
-}
-
-/*
- * check whether the policy is consistent with the encryption context
- * for the inode
- */
-static int f2fs_is_encryption_context_consistent_with_policy(
-	struct inode *inode, const struct f2fs_encryption_policy *policy)
-{
-	struct f2fs_encryption_context ctx;
-	int res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
-				F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
-				sizeof(ctx), NULL);
-
-	if (res != sizeof(ctx))
-		return 0;
-
-	return (memcmp(ctx.master_key_descriptor, policy->master_key_descriptor,
-				F2FS_KEY_DESCRIPTOR_SIZE) == 0 &&
-			(ctx.flags == policy->flags) &&
-			(ctx.contents_encryption_mode ==
-			 policy->contents_encryption_mode) &&
-			(ctx.filenames_encryption_mode ==
-			 policy->filenames_encryption_mode));
-}
-
-static int f2fs_create_encryption_context_from_policy(
-	struct inode *inode, const struct f2fs_encryption_policy *policy)
-{
-	struct f2fs_encryption_context ctx;
-
-	ctx.format = F2FS_ENCRYPTION_CONTEXT_FORMAT_V1;
-	memcpy(ctx.master_key_descriptor, policy->master_key_descriptor,
-			F2FS_KEY_DESCRIPTOR_SIZE);
-
-	if (!f2fs_valid_contents_enc_mode(policy->contents_encryption_mode)) {
-		printk(KERN_WARNING
-		       "%s: Invalid contents encryption mode %d\n", __func__,
-			policy->contents_encryption_mode);
-		return -EINVAL;
-	}
-
-	if (!f2fs_valid_filenames_enc_mode(policy->filenames_encryption_mode)) {
-		printk(KERN_WARNING
-		       "%s: Invalid filenames encryption mode %d\n", __func__,
-			policy->filenames_encryption_mode);
-		return -EINVAL;
-	}
-
-	if (policy->flags & ~F2FS_POLICY_FLAGS_VALID)
-		return -EINVAL;
-
-	ctx.contents_encryption_mode = policy->contents_encryption_mode;
-	ctx.filenames_encryption_mode = policy->filenames_encryption_mode;
-	ctx.flags = policy->flags;
-	BUILD_BUG_ON(sizeof(ctx.nonce) != F2FS_KEY_DERIVATION_NONCE_SIZE);
-	get_random_bytes(ctx.nonce, F2FS_KEY_DERIVATION_NONCE_SIZE);
-
-	return f2fs_setxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
-			F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
-			sizeof(ctx), NULL, XATTR_CREATE);
-}
-
-int f2fs_process_policy(const struct f2fs_encryption_policy *policy,
-			struct inode *inode)
-{
-	if (policy->version != 0)
-		return -EINVAL;
-
-	if (!S_ISDIR(inode->i_mode))
-		return -EINVAL;
-
-	if (!f2fs_inode_has_encryption_context(inode)) {
-		if (!f2fs_empty_dir(inode))
-			return -ENOTEMPTY;
-		return f2fs_create_encryption_context_from_policy(inode,
-								  policy);
-	}
-
-	if (f2fs_is_encryption_context_consistent_with_policy(inode, policy))
-		return 0;
-
-	printk(KERN_WARNING "%s: Policy inconsistent with encryption context\n",
-	       __func__);
-	return -EINVAL;
-}
-
-int f2fs_get_policy(struct inode *inode, struct f2fs_encryption_policy *policy)
-{
-	struct f2fs_encryption_context ctx;
-	int res;
-
-	if (!f2fs_encrypted_inode(inode))
-		return -ENODATA;
-
-	res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
-				F2FS_XATTR_NAME_ENCRYPTION_CONTEXT,
-				&ctx, sizeof(ctx), NULL);
-	if (res != sizeof(ctx))
-		return -ENODATA;
-	if (ctx.format != F2FS_ENCRYPTION_CONTEXT_FORMAT_V1)
-		return -EINVAL;
-
-	policy->version = 0;
-	policy->contents_encryption_mode = ctx.contents_encryption_mode;
-	policy->filenames_encryption_mode = ctx.filenames_encryption_mode;
-	policy->flags = ctx.flags;
-	memcpy(&policy->master_key_descriptor, ctx.master_key_descriptor,
-			F2FS_KEY_DESCRIPTOR_SIZE);
-	return 0;
-}
-
-int f2fs_is_child_context_consistent_with_parent(struct inode *parent,
-						struct inode *child)
-{
-	struct f2fs_crypt_info *parent_ci, *child_ci;
-	int res;
-
-	if ((parent == NULL) || (child == NULL)) {
-		pr_err("parent %p child %p\n", parent, child);
-		BUG_ON(1);
-	}
-
-	/* no restrictions if the parent directory is not encrypted */
-	if (!f2fs_encrypted_inode(parent))
-		return 1;
-	/* if the child directory is not encrypted, this is always a problem */
-	if (!f2fs_encrypted_inode(child))
-		return 0;
-	res = f2fs_get_encryption_info(parent);
-	if (res)
-		return 0;
-	res = f2fs_get_encryption_info(child);
-	if (res)
-		return 0;
-	parent_ci = F2FS_I(parent)->i_crypt_info;
-	child_ci = F2FS_I(child)->i_crypt_info;
-	if (!parent_ci && !child_ci)
-		return 1;
-	if (!parent_ci || !child_ci)
-		return 0;
-
-	return (memcmp(parent_ci->ci_master_key,
-			child_ci->ci_master_key,
-			F2FS_KEY_DESCRIPTOR_SIZE) == 0 &&
-		(parent_ci->ci_data_mode == child_ci->ci_data_mode) &&
-		(parent_ci->ci_filename_mode == child_ci->ci_filename_mode) &&
-		(parent_ci->ci_flags == child_ci->ci_flags));
-}
-
-/**
- * f2fs_inherit_context() - Sets a child context from its parent
- * @parent: Parent inode from which the context is inherited.
- * @child:  Child inode that inherits the context from @parent.
- *
- * Return: Zero on success, non-zero otherwise
- */
-int f2fs_inherit_context(struct inode *parent, struct inode *child,
-						struct page *ipage)
-{
-	struct f2fs_encryption_context ctx;
-	struct f2fs_crypt_info *ci;
-	int res;
-
-	res = f2fs_get_encryption_info(parent);
-	if (res < 0)
-		return res;
-
-	ci = F2FS_I(parent)->i_crypt_info;
-	BUG_ON(ci == NULL);
-
-	ctx.format = F2FS_ENCRYPTION_CONTEXT_FORMAT_V1;
-
-	ctx.contents_encryption_mode = ci->ci_data_mode;
-	ctx.filenames_encryption_mode = ci->ci_filename_mode;
-	ctx.flags = ci->ci_flags;
-	memcpy(ctx.master_key_descriptor, ci->ci_master_key,
-			F2FS_KEY_DESCRIPTOR_SIZE);
-
-	get_random_bytes(ctx.nonce, F2FS_KEY_DERIVATION_NONCE_SIZE);
-	return f2fs_setxattr(child, F2FS_XATTR_INDEX_ENCRYPTION,
-				F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
-				sizeof(ctx), ipage, XATTR_CREATE);
-}
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 972eab7ac071..5dafb9cef12e 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -34,9 +34,9 @@ static void f2fs_read_end_io(struct bio *bio)
 
 	if (f2fs_bio_encrypted(bio)) {
 		if (bio->bi_error) {
-			f2fs_release_crypto_ctx(bio->bi_private);
+			fscrypt_release_ctx(bio->bi_private);
 		} else {
-			f2fs_end_io_crypto_work(bio->bi_private, bio);
+			fscrypt_decrypt_bio_pages(bio->bi_private, bio);
 			return;
 		}
 	}
@@ -64,10 +64,9 @@ static void f2fs_write_end_io(struct bio *bio)
 	bio_for_each_segment_all(bvec, bio, i) {
 		struct page *page = bvec->bv_page;
 
-		f2fs_restore_and_release_control_page(&page);
+		fscrypt_pullback_bio_page(&page, true);
 
 		if (unlikely(bio->bi_error)) {
-			set_page_dirty(page);
 			set_bit(AS_EIO, &page->mapping->flags);
 			f2fs_stop_checkpoint(sbi);
 		}
@@ -75,8 +74,7 @@ static void f2fs_write_end_io(struct bio *bio)
 		dec_page_count(sbi, F2FS_WRITEBACK);
 	}
 
-	if (!get_pages(sbi, F2FS_WRITEBACK) &&
-			!list_empty(&sbi->cp_wait.task_list))
+	if (!get_pages(sbi, F2FS_WRITEBACK) && wq_has_sleeper(&sbi->cp_wait))
 		wake_up(&sbi->cp_wait);
 
 	bio_put(bio);
@@ -116,8 +114,54 @@ static void __submit_merged_bio(struct f2fs_bio_info *io)
 	io->bio = NULL;
 }
 
-void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
-				enum page_type type, int rw)
+static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode,
+						struct page *page, nid_t ino)
+{
+	struct bio_vec *bvec;
+	struct page *target;
+	int i;
+
+	if (!io->bio)
+		return false;
+
+	if (!inode && !page && !ino)
+		return true;
+
+	bio_for_each_segment_all(bvec, io->bio, i) {
+
+		if (bvec->bv_page->mapping)
+			target = bvec->bv_page;
+		else
+			target = fscrypt_control_page(bvec->bv_page);
+
+		if (inode && inode == target->mapping->host)
+			return true;
+		if (page && page == target)
+			return true;
+		if (ino && ino == ino_of_node(target))
+			return true;
+	}
+
+	return false;
+}
+
+static bool has_merged_page(struct f2fs_sb_info *sbi, struct inode *inode,
+						struct page *page, nid_t ino,
+						enum page_type type)
+{
+	enum page_type btype = PAGE_TYPE_OF_BIO(type);
+	struct f2fs_bio_info *io = &sbi->write_io[btype];
+	bool ret;
+
+	down_read(&io->io_rwsem);
+	ret = __has_merged_page(io, inode, page, ino);
+	up_read(&io->io_rwsem);
+	return ret;
+}
+
+static void __f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
+				struct inode *inode, struct page *page,
+				nid_t ino, enum page_type type, int rw)
 {
 	enum page_type btype = PAGE_TYPE_OF_BIO(type);
 	struct f2fs_bio_info *io;
@@ -126,6 +170,9 @@ void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
 
 	down_write(&io->io_rwsem);
 
+	if (!__has_merged_page(io, inode, page, ino))
+		goto out;
+
 	/* change META to META_FLUSH in the checkpoint procedure */
 	if (type >= META_FLUSH) {
 		io->fio.type = META_FLUSH;
@@ -135,9 +182,31 @@ void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
 			io->fio.rw = WRITE_FLUSH_FUA | REQ_META | REQ_PRIO;
 	}
 	__submit_merged_bio(io);
+out:
 	up_write(&io->io_rwsem);
 }
 
+void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, enum page_type type,
+									int rw)
+{
+	__f2fs_submit_merged_bio(sbi, NULL, NULL, 0, type, rw);
+}
+
+void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *sbi,
+				struct inode *inode, struct page *page,
+				nid_t ino, enum page_type type, int rw)
+{
+	if (has_merged_page(sbi, inode, page, ino, type))
+		__f2fs_submit_merged_bio(sbi, inode, page, ino, type, rw);
+}
+
+void f2fs_flush_merged_bios(struct f2fs_sb_info *sbi)
+{
+	f2fs_submit_merged_bio(sbi, DATA, WRITE);
+	f2fs_submit_merged_bio(sbi, NODE, WRITE);
+	f2fs_submit_merged_bio(sbi, META, WRITE);
+}
+
 /*
  * Fill the locked page with data located in the block address.
  * Return unlocked page.
@@ -145,15 +214,16 @@ void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
 int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 {
 	struct bio *bio;
-	struct page *page = fio->encrypted_page ? fio->encrypted_page : fio->page;
+	struct page *page = fio->encrypted_page ?
+			fio->encrypted_page : fio->page;
 
 	trace_f2fs_submit_page_bio(page, fio);
 	f2fs_trace_ios(fio, 0);
 
 	/* Allocate a new bio */
-	bio = __bio_alloc(fio->sbi, fio->blk_addr, 1, is_read_io(fio->rw));
+	bio = __bio_alloc(fio->sbi, fio->new_blkaddr, 1, is_read_io(fio->rw));
 
-	if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) {
+	if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
 		bio_put(bio);
 		return -EFAULT;
 	}
@@ -172,33 +242,36 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
 
 	io = is_read ? &sbi->read_io : &sbi->write_io[btype];
 
-	verify_block_addr(sbi, fio->blk_addr);
+	if (fio->old_blkaddr != NEW_ADDR)
+		verify_block_addr(sbi, fio->old_blkaddr);
+	verify_block_addr(sbi, fio->new_blkaddr);
 
 	down_write(&io->io_rwsem);
 
 	if (!is_read)
 		inc_page_count(sbi, F2FS_WRITEBACK);
 
-	if (io->bio && (io->last_block_in_bio != fio->blk_addr - 1 ||
+	if (io->bio && (io->last_block_in_bio != fio->new_blkaddr - 1 ||
 						io->fio.rw != fio->rw))
 		__submit_merged_bio(io);
 alloc_new:
 	if (io->bio == NULL) {
 		int bio_blocks = MAX_BIO_BLOCKS(sbi);
 
-		io->bio = __bio_alloc(sbi, fio->blk_addr, bio_blocks, is_read);
+		io->bio = __bio_alloc(sbi, fio->new_blkaddr,
+						bio_blocks, is_read);
 		io->fio = *fio;
 	}
 
 	bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page;
 
-	if (bio_add_page(io->bio, bio_page, PAGE_CACHE_SIZE, 0) <
-							PAGE_CACHE_SIZE) {
+	if (bio_add_page(io->bio, bio_page, PAGE_SIZE, 0) <
+							PAGE_SIZE) {
 		__submit_merged_bio(io);
 		goto alloc_new;
 	}
 
-	io->last_block_in_bio = fio->blk_addr;
+	io->last_block_in_bio = fio->new_blkaddr;
 	f2fs_trace_ios(fio, 0);
 
 	up_write(&io->io_rwsem);
@@ -218,14 +291,22 @@ void set_data_blkaddr(struct dnode_of_data *dn)
 	struct page *node_page = dn->node_page;
 	unsigned int ofs_in_node = dn->ofs_in_node;
 
-	f2fs_wait_on_page_writeback(node_page, NODE);
+	f2fs_wait_on_page_writeback(node_page, NODE, true);
 
 	rn = F2FS_NODE(node_page);
 
 	/* Get physical address of data block */
 	addr_array = blkaddr_in_node(rn);
 	addr_array[ofs_in_node] = cpu_to_le32(dn->data_blkaddr);
-	set_page_dirty(node_page);
+	if (set_page_dirty(node_page))
+		dn->node_changed = true;
+}
+
+void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr)
+{
+	dn->data_blkaddr = blkaddr;
+	set_data_blkaddr(dn);
+	f2fs_update_extent_cache(dn);
 }
 
 int reserve_new_block(struct dnode_of_data *dn)
@@ -325,13 +406,13 @@ got_it:
 	 * see, f2fs_add_link -> get_new_data_page -> init_inode_metadata.
 	 */
 	if (dn.data_blkaddr == NEW_ADDR) {
-		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+		zero_user_segment(page, 0, PAGE_SIZE);
 		SetPageUptodate(page);
 		unlock_page(page);
 		return page;
 	}
 
-	fio.blk_addr = dn.data_blkaddr;
+	fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr;
 	fio.page = page;
 	err = f2fs_submit_page_bio(&fio);
 	if (err)
@@ -412,7 +493,7 @@ struct page *get_new_data_page(struct inode *inode,
 	struct page *page;
 	struct dnode_of_data dn;
 	int err;
-repeat:
+
 	page = f2fs_grab_cache_page(mapping, index, true);
 	if (!page) {
 		/*
@@ -436,22 +517,21 @@ repeat:
 		goto got_it;
 
 	if (dn.data_blkaddr == NEW_ADDR) {
-		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+		zero_user_segment(page, 0, PAGE_SIZE);
 		SetPageUptodate(page);
 	} else {
 		f2fs_put_page(page, 1);
 
-		page = get_read_data_page(inode, index, READ_SYNC, true);
+		/* if ipage exists, blkaddr should be NEW_ADDR */
+		f2fs_bug_on(F2FS_I_SB(inode), ipage);
+		page = get_lock_data_page(inode, index, true);
 		if (IS_ERR(page))
-			goto repeat;
-
-		/* wait for read completion */
-		lock_page(page);
+			return page;
 	}
 got_it:
 	if (new_i_size && i_size_read(inode) <
-				((loff_t)(index + 1) << PAGE_CACHE_SHIFT)) {
-		i_size_write(inode, ((loff_t)(index + 1) << PAGE_CACHE_SHIFT));
+				((loff_t)(index + 1) << PAGE_SHIFT)) {
+		i_size_write(inode, ((loff_t)(index + 1) << PAGE_SHIFT));
 		/* Only the directory inode sets new_i_size */
 		set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR);
 	}
@@ -461,7 +541,6 @@ got_it:
 static int __allocate_data_block(struct dnode_of_data *dn)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
-	struct f2fs_inode_info *fi = F2FS_I(dn->inode);
 	struct f2fs_summary sum;
 	struct node_info ni;
 	int seg = CURSEG_WARM_DATA;
@@ -489,72 +568,41 @@ alloc:
 	set_data_blkaddr(dn);
 
 	/* update i_size */
-	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
+	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
 							dn->ofs_in_node;
-	if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_CACHE_SHIFT))
+	if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_SHIFT))
 		i_size_write(dn->inode,
-				((loff_t)(fofs + 1) << PAGE_CACHE_SHIFT));
-
-	/* direct IO doesn't use extent cache to maximize the performance */
-	f2fs_drop_largest_extent(dn->inode, fofs);
-
+				((loff_t)(fofs + 1) << PAGE_SHIFT));
 	return 0;
 }
 
-static void __allocate_data_blocks(struct inode *inode, loff_t offset,
-							size_t count)
+ssize_t f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
 {
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct dnode_of_data dn;
-	u64 start = F2FS_BYTES_TO_BLK(offset);
-	u64 len = F2FS_BYTES_TO_BLK(count);
-	bool allocated;
-	u64 end_offset;
-
-	while (len) {
-		f2fs_balance_fs(sbi);
-		f2fs_lock_op(sbi);
-
-		/* When reading holes, we need its node page */
-		set_new_dnode(&dn, inode, NULL, NULL, 0);
-		if (get_dnode_of_data(&dn, start, ALLOC_NODE))
-			goto out;
-
-		allocated = false;
-		end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
-
-		while (dn.ofs_in_node < end_offset && len) {
-			block_t blkaddr;
-
-			if (unlikely(f2fs_cp_error(sbi)))
-				goto sync_out;
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct f2fs_map_blocks map;
+	ssize_t ret = 0;
 
-			blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
-			if (blkaddr == NULL_ADDR || blkaddr == NEW_ADDR) {
-				if (__allocate_data_block(&dn))
-					goto sync_out;
-				allocated = true;
-			}
-			len--;
-			start++;
-			dn.ofs_in_node++;
-		}
+	map.m_lblk = F2FS_BYTES_TO_BLK(iocb->ki_pos);
+	map.m_len = F2FS_BLK_ALIGN(iov_iter_count(from));
+	map.m_next_pgofs = NULL;
 
-		if (allocated)
-			sync_inode_page(&dn);
+	if (f2fs_encrypted_inode(inode))
+		return 0;
 
-		f2fs_put_dnode(&dn);
-		f2fs_unlock_op(sbi);
+	if (iocb->ki_flags & IOCB_DIRECT) {
+		ret = f2fs_convert_inline_inode(inode);
+		if (ret)
+			return ret;
+		return f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_DIO);
 	}
-	return;
-
-sync_out:
-	if (allocated)
-		sync_inode_page(&dn);
-	f2fs_put_dnode(&dn);
-out:
-	f2fs_unlock_op(sbi);
-	return;
+	if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA) {
+		ret = f2fs_convert_inline_inode(inode);
+		if (ret)
+			return ret;
+	}
+	if (!f2fs_has_inline_data(inode))
+		return f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
+	return ret;
 }
 
 /*
@@ -566,7 +614,7 @@ out:
  *     b. do not use extent cache for better performance
  *     c. give the block addresses to blockdev
  */
-static int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
+int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 						int create, int flag)
 {
 	unsigned int maxblocks = map->m_len;
@@ -577,6 +625,7 @@ static int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 	int err = 0, ofs = 1;
 	struct extent_info ei;
 	bool allocated = false;
+	block_t blkaddr;
 
 	map->m_len = 0;
 	map->m_flags = 0;
@@ -584,138 +633,129 @@ static int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 	/* it only supports block size == page size */
 	pgofs =	(pgoff_t)map->m_lblk;
 
-	if (f2fs_lookup_extent_cache(inode, pgofs, &ei)) {
+	if (!create && f2fs_lookup_extent_cache(inode, pgofs, &ei)) {
 		map->m_pblk = ei.blk + pgofs - ei.fofs;
 		map->m_len = min((pgoff_t)maxblocks, ei.fofs + ei.len - pgofs);
 		map->m_flags = F2FS_MAP_MAPPED;
 		goto out;
 	}
 
+next_dnode:
 	if (create)
-		f2fs_lock_op(F2FS_I_SB(inode));
+		f2fs_lock_op(sbi);
 
 	/* When reading holes, we need its node page */
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
 	err = get_dnode_of_data(&dn, pgofs, mode);
 	if (err) {
-		if (err == -ENOENT)
+		if (err == -ENOENT) {
 			err = 0;
+			if (map->m_next_pgofs)
+				*map->m_next_pgofs =
+					get_next_page_offset(&dn, pgofs);
+		}
 		goto unlock_out;
 	}
 
-	if (dn.data_blkaddr == NEW_ADDR || dn.data_blkaddr == NULL_ADDR) {
+	end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
+
+next_block:
+	blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
+
+	if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) {
 		if (create) {
 			if (unlikely(f2fs_cp_error(sbi))) {
 				err = -EIO;
-				goto put_out;
+				goto sync_out;
+			}
+			if (flag == F2FS_GET_BLOCK_PRE_AIO) {
+				if (blkaddr == NULL_ADDR)
+					err = reserve_new_block(&dn);
+			} else {
+				err = __allocate_data_block(&dn);
 			}
-			err = __allocate_data_block(&dn);
 			if (err)
-				goto put_out;
+				goto sync_out;
 			allocated = true;
 			map->m_flags = F2FS_MAP_NEW;
+			blkaddr = dn.data_blkaddr;
 		} else {
+			if (flag == F2FS_GET_BLOCK_FIEMAP &&
+						blkaddr == NULL_ADDR) {
+				if (map->m_next_pgofs)
+					*map->m_next_pgofs = pgofs + 1;
+			}
 			if (flag != F2FS_GET_BLOCK_FIEMAP ||
-						dn.data_blkaddr != NEW_ADDR) {
+						blkaddr != NEW_ADDR) {
 				if (flag == F2FS_GET_BLOCK_BMAP)
 					err = -ENOENT;
-				goto put_out;
+				goto sync_out;
 			}
-
-			/*
-			 * preallocated unwritten block should be mapped
-			 * for fiemap.
-			 */
-			if (dn.data_blkaddr == NEW_ADDR)
-				map->m_flags = F2FS_MAP_UNWRITTEN;
 		}
 	}
 
-	map->m_flags |= F2FS_MAP_MAPPED;
-	map->m_pblk = dn.data_blkaddr;
-	map->m_len = 1;
+	if (map->m_len == 0) {
+		/* preallocated unwritten block should be mapped for fiemap. */
+		if (blkaddr == NEW_ADDR)
+			map->m_flags |= F2FS_MAP_UNWRITTEN;
+		map->m_flags |= F2FS_MAP_MAPPED;
+
+		map->m_pblk = blkaddr;
+		map->m_len = 1;
+	} else if ((map->m_pblk != NEW_ADDR &&
+			blkaddr == (map->m_pblk + ofs)) ||
+			(map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR) ||
+			flag == F2FS_GET_BLOCK_PRE_DIO ||
+			flag == F2FS_GET_BLOCK_PRE_AIO) {
+		ofs++;
+		map->m_len++;
+	} else {
+		goto sync_out;
+	}
 
-	end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
 	dn.ofs_in_node++;
 	pgofs++;
 
-get_next:
-	if (dn.ofs_in_node >= end_offset) {
+	if (map->m_len < maxblocks) {
+		if (dn.ofs_in_node < end_offset)
+			goto next_block;
+
 		if (allocated)
 			sync_inode_page(&dn);
-		allocated = false;
 		f2fs_put_dnode(&dn);
 
-		set_new_dnode(&dn, inode, NULL, NULL, 0);
-		err = get_dnode_of_data(&dn, pgofs, mode);
-		if (err) {
-			if (err == -ENOENT)
-				err = 0;
-			goto unlock_out;
+		if (create) {
+			f2fs_unlock_op(sbi);
+			f2fs_balance_fs(sbi, allocated);
 		}
-
-		end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+		allocated = false;
+		goto next_dnode;
 	}
 
-	if (maxblocks > map->m_len) {
-		block_t blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
-
-		if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) {
-			if (create) {
-				if (unlikely(f2fs_cp_error(sbi))) {
-					err = -EIO;
-					goto sync_out;
-				}
-				err = __allocate_data_block(&dn);
-				if (err)
-					goto sync_out;
-				allocated = true;
-				map->m_flags |= F2FS_MAP_NEW;
-				blkaddr = dn.data_blkaddr;
-			} else {
-				/*
-				 * we only merge preallocated unwritten blocks
-				 * for fiemap.
-				 */
-				if (flag != F2FS_GET_BLOCK_FIEMAP ||
-						blkaddr != NEW_ADDR)
-					goto sync_out;
-			}
-		}
-
-		/* Give more consecutive addresses for the readahead */
-		if ((map->m_pblk != NEW_ADDR &&
-				blkaddr == (map->m_pblk + ofs)) ||
-				(map->m_pblk == NEW_ADDR &&
-				blkaddr == NEW_ADDR)) {
-			ofs++;
-			dn.ofs_in_node++;
-			pgofs++;
-			map->m_len++;
-			goto get_next;
-		}
-	}
 sync_out:
 	if (allocated)
 		sync_inode_page(&dn);
-put_out:
 	f2fs_put_dnode(&dn);
 unlock_out:
-	if (create)
-		f2fs_unlock_op(F2FS_I_SB(inode));
+	if (create) {
+		f2fs_unlock_op(sbi);
+		f2fs_balance_fs(sbi, allocated);
+	}
 out:
 	trace_f2fs_map_blocks(inode, map, err);
 	return err;
 }
 
 static int __get_data_block(struct inode *inode, sector_t iblock,
-			struct buffer_head *bh, int create, int flag)
+			struct buffer_head *bh, int create, int flag,
+			pgoff_t *next_pgofs)
 {
 	struct f2fs_map_blocks map;
 	int ret;
 
 	map.m_lblk = iblock;
 	map.m_len = bh->b_size >> inode->i_blkbits;
+	map.m_next_pgofs = next_pgofs;
 
 	ret = f2fs_map_blocks(inode, &map, create, flag);
 	if (!ret) {
@@ -727,23 +767,29 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
 }
 
 static int get_data_block(struct inode *inode, sector_t iblock,
-			struct buffer_head *bh_result, int create, int flag)
+			struct buffer_head *bh_result, int create, int flag,
+			pgoff_t *next_pgofs)
 {
-	return __get_data_block(inode, iblock, bh_result, create, flag);
+	return __get_data_block(inode, iblock, bh_result, create,
+							flag, next_pgofs);
 }
 
 static int get_data_block_dio(struct inode *inode, sector_t iblock,
 			struct buffer_head *bh_result, int create)
 {
 	return __get_data_block(inode, iblock, bh_result, create,
-						F2FS_GET_BLOCK_DIO);
+						F2FS_GET_BLOCK_DIO, NULL);
 }
 
 static int get_data_block_bmap(struct inode *inode, sector_t iblock,
 			struct buffer_head *bh_result, int create)
 {
+	/* Block number less than F2FS MAX BLOCKS */
+	if (unlikely(iblock >= F2FS_I_SB(inode)->max_file_blocks))
+		return -EFBIG;
+
 	return __get_data_block(inode, iblock, bh_result, create,
-						F2FS_GET_BLOCK_BMAP);
+						F2FS_GET_BLOCK_BMAP, NULL);
 }
 
 static inline sector_t logical_to_blk(struct inode *inode, loff_t offset)
@@ -761,10 +807,10 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 {
 	struct buffer_head map_bh;
 	sector_t start_blk, last_blk;
-	loff_t isize = i_size_read(inode);
+	pgoff_t next_pgofs;
+	loff_t isize;
 	u64 logical = 0, phys = 0, size = 0;
 	u32 flags = 0;
-	bool past_eof = false, whole_file = false;
 	int ret = 0;
 
 	ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
@@ -777,82 +823,64 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			return ret;
 	}
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
-	if (len >= isize) {
-		whole_file = true;
-		len = isize;
-	}
+	isize = i_size_read(inode);
+	if (start >= isize)
+		goto out;
+
+	if (start + len > isize)
+		len = isize - start;
 
 	if (logical_to_blk(inode, len) == 0)
 		len = blk_to_logical(inode, 1);
 
 	start_blk = logical_to_blk(inode, start);
 	last_blk = logical_to_blk(inode, start + len - 1);
+
 next:
 	memset(&map_bh, 0, sizeof(struct buffer_head));
 	map_bh.b_size = len;
 
 	ret = get_data_block(inode, start_blk, &map_bh, 0,
-					F2FS_GET_BLOCK_FIEMAP);
+					F2FS_GET_BLOCK_FIEMAP, &next_pgofs);
 	if (ret)
 		goto out;
 
 	/* HOLE */
 	if (!buffer_mapped(&map_bh)) {
-		start_blk++;
-
-		if (!past_eof && blk_to_logical(inode, start_blk) >= isize)
-			past_eof = 1;
-
-		if (past_eof && size) {
-			flags |= FIEMAP_EXTENT_LAST;
-			ret = fiemap_fill_next_extent(fieinfo, logical,
-					phys, size, flags);
-		} else if (size) {
-			ret = fiemap_fill_next_extent(fieinfo, logical,
-					phys, size, flags);
-			size = 0;
-		}
+		start_blk = next_pgofs;
+		/* Go through holes util pass the EOF */
+		if (blk_to_logical(inode, start_blk) < isize)
+			goto prep_next;
+		/* Found a hole beyond isize means no more extents.
+		 * Note that the premise is that filesystems don't
+		 * punch holes beyond isize and keep size unchanged.
+		 */
+		flags |= FIEMAP_EXTENT_LAST;
+	}
 
-		/* if we have holes up to/past EOF then we're done */
-		if (start_blk > last_blk || past_eof || ret)
-			goto out;
-	} else {
-		if (start_blk > last_blk && !whole_file) {
-			ret = fiemap_fill_next_extent(fieinfo, logical,
-					phys, size, flags);
-			goto out;
-		}
+	if (size) {
+		if (f2fs_encrypted_inode(inode))
+			flags |= FIEMAP_EXTENT_DATA_ENCRYPTED;
 
-		/*
-		 * if size != 0 then we know we already have an extent
-		 * to add, so add it.
-		 */
-		if (size) {
-			ret = fiemap_fill_next_extent(fieinfo, logical,
-					phys, size, flags);
-			if (ret)
-				goto out;
-		}
+		ret = fiemap_fill_next_extent(fieinfo, logical,
+				phys, size, flags);
+	}
 
-		logical = blk_to_logical(inode, start_blk);
-		phys = blk_to_logical(inode, map_bh.b_blocknr);
-		size = map_bh.b_size;
-		flags = 0;
-		if (buffer_unwritten(&map_bh))
-			flags = FIEMAP_EXTENT_UNWRITTEN;
+	if (start_blk > last_blk || ret)
+		goto out;
 
-		start_blk += logical_to_blk(inode, size);
+	logical = blk_to_logical(inode, start_blk);
+	phys = blk_to_logical(inode, map_bh.b_blocknr);
+	size = map_bh.b_size;
+	flags = 0;
+	if (buffer_unwritten(&map_bh))
+		flags = FIEMAP_EXTENT_UNWRITTEN;
 
-		/*
-		 * If we are past the EOF, then we need to make sure as
-		 * soon as we find a hole that the last extent we found
-		 * is marked with FIEMAP_EXTENT_LAST
-		 */
-		if (!past_eof && logical + size >= isize)
-			past_eof = true;
-	}
+	start_blk += logical_to_blk(inode, size);
+
+prep_next:
 	cond_resched();
 	if (fatal_signal_pending(current))
 		ret = -EINTR;
@@ -862,7 +890,7 @@ out:
 	if (ret == 1)
 		ret = 0;
 
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return ret;
 }
 
@@ -891,6 +919,7 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
 	map.m_lblk = 0;
 	map.m_len = 0;
 	map.m_flags = 0;
+	map.m_next_pgofs = NULL;
 
 	for (page_idx = 0; nr_pages; page_idx++, nr_pages--) {
 
@@ -929,7 +958,7 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
 			map.m_len = last_block - block_in_file;
 
 			if (f2fs_map_blocks(inode, &map, 0,
-							F2FS_GET_BLOCK_READ))
+						F2FS_GET_BLOCK_READ))
 				goto set_error_page;
 		}
 got_it:
@@ -942,7 +971,7 @@ got_it:
 				goto confused;
 			}
 		} else {
-			zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+			zero_user_segment(page, 0, PAGE_SIZE);
 			SetPageUptodate(page);
 			unlock_page(page);
 			goto next_page;
@@ -958,12 +987,12 @@ submit_and_realloc:
 			bio = NULL;
 		}
 		if (bio == NULL) {
-			struct f2fs_crypto_ctx *ctx = NULL;
+			struct fscrypt_ctx *ctx = NULL;
 
 			if (f2fs_encrypted_inode(inode) &&
 					S_ISREG(inode->i_mode)) {
 
-				ctx = f2fs_get_crypto_ctx(inode);
+				ctx = fscrypt_get_ctx(inode, GFP_NOFS);
 				if (IS_ERR(ctx))
 					goto set_error_page;
 
@@ -976,7 +1005,7 @@ submit_and_realloc:
 				min_t(int, nr_pages, BIO_MAX_PAGES));
 			if (!bio) {
 				if (ctx)
-					f2fs_release_crypto_ctx(ctx);
+					fscrypt_release_ctx(ctx);
 				goto set_error_page;
 			}
 			bio->bi_bdev = bdev;
@@ -992,7 +1021,7 @@ submit_and_realloc:
 		goto next_page;
 set_error_page:
 		SetPageError(page);
-		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+		zero_user_segment(page, 0, PAGE_SIZE);
 		unlock_page(page);
 		goto next_page;
 confused:
@@ -1003,7 +1032,7 @@ confused:
 		unlock_page(page);
 next_page:
 		if (pages)
-			page_cache_release(page);
+			put_page(page);
 	}
 	BUG_ON(pages && !list_empty(pages));
 	if (bio)
@@ -1054,23 +1083,33 @@ int do_write_data_page(struct f2fs_io_info *fio)
 	if (err)
 		return err;
 
-	fio->blk_addr = dn.data_blkaddr;
+	fio->old_blkaddr = dn.data_blkaddr;
 
 	/* This page is already truncated */
-	if (fio->blk_addr == NULL_ADDR) {
+	if (fio->old_blkaddr == NULL_ADDR) {
 		ClearPageUptodate(page);
 		goto out_writepage;
 	}
 
 	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
+		gfp_t gfp_flags = GFP_NOFS;
 
 		/* wait for GCed encrypted page writeback */
 		f2fs_wait_on_encrypted_page_writeback(F2FS_I_SB(inode),
-							fio->blk_addr);
-
-		fio->encrypted_page = f2fs_encrypt(inode, fio->page);
+							fio->old_blkaddr);
+retry_encrypt:
+		fio->encrypted_page = fscrypt_encrypt_page(inode, fio->page,
+								gfp_flags);
 		if (IS_ERR(fio->encrypted_page)) {
 			err = PTR_ERR(fio->encrypted_page);
+			if (err == -ENOMEM) {
+				/* flush pending ios and wait for a while */
+				f2fs_flush_merged_bios(F2FS_I_SB(inode));
+				congestion_wait(BLK_RW_ASYNC, HZ/50);
+				gfp_flags |= __GFP_NOFAIL;
+				err = 0;
+				goto retry_encrypt;
+			}
 			goto out_writepage;
 		}
 	}
@@ -1081,16 +1120,15 @@ int do_write_data_page(struct f2fs_io_info *fio)
 	 * If current allocation needs SSR,
 	 * it had better in-place writes for updated data.
 	 */
-	if (unlikely(fio->blk_addr != NEW_ADDR &&
+	if (unlikely(fio->old_blkaddr != NEW_ADDR &&
 			!is_cold_data(page) &&
+			!IS_ATOMIC_WRITTEN_PAGE(page) &&
 			need_inplace_update(inode))) {
 		rewrite_data_page(fio);
 		set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE);
 		trace_f2fs_do_write_data_page(page, IPU);
 	} else {
 		write_data_page(&dn, fio);
-		set_data_blkaddr(&dn);
-		f2fs_update_extent_cache(&dn);
 		trace_f2fs_do_write_data_page(page, OPU);
 		set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
 		if (page->index == 0)
@@ -1108,7 +1146,7 @@ static int f2fs_write_data_page(struct page *page,
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	loff_t i_size = i_size_read(inode);
 	const pgoff_t end_index = ((unsigned long long) i_size)
-							>> PAGE_CACHE_SHIFT;
+							>> PAGE_SHIFT;
 	unsigned offset = 0;
 	bool need_balance_fs = false;
 	int err = 0;
@@ -1129,11 +1167,11 @@ static int f2fs_write_data_page(struct page *page,
 	 * If the offset is out-of-range of file size,
 	 * this page does not have to be written to disk.
 	 */
-	offset = i_size & (PAGE_CACHE_SIZE - 1);
+	offset = i_size & (PAGE_SIZE - 1);
 	if ((page->index >= end_index + 1) || !offset)
 		goto out;
 
-	zero_user_segment(page, offset, PAGE_CACHE_SIZE);
+	zero_user_segment(page, offset, PAGE_SIZE);
 write:
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		goto redirty_out;
@@ -1178,11 +1216,18 @@ out:
 	inode_dec_dirty_pages(inode);
 	if (err)
 		ClearPageUptodate(page);
+
+	if (wbc->for_reclaim) {
+		f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, DATA, WRITE);
+		remove_dirty_inode(inode);
+	}
+
 	unlock_page(page);
-	if (need_balance_fs)
-		f2fs_balance_fs(sbi);
-	if (wbc->for_reclaim)
+	f2fs_balance_fs(sbi, need_balance_fs);
+
+	if (unlikely(f2fs_cp_error(sbi)))
 		f2fs_submit_merged_bio(sbi, DATA, WRITE);
+
 	return 0;
 
 redirty_out:
@@ -1232,8 +1277,8 @@ next:
 			cycled = 0;
 		end = -1;
 	} else {
-		index = wbc->range_start >> PAGE_CACHE_SHIFT;
-		end = wbc->range_end >> PAGE_CACHE_SHIFT;
+		index = wbc->range_start >> PAGE_SHIFT;
+		end = wbc->range_end >> PAGE_SHIFT;
 		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
 			range_whole = 1;
 		cycled = 1; /* ignore range_cyclic tests */
@@ -1282,7 +1327,8 @@ continue_unlock:
 
 			if (PageWriteback(page)) {
 				if (wbc->sync_mode != WB_SYNC_NONE)
-					f2fs_wait_on_page_writeback(page, DATA);
+					f2fs_wait_on_page_writeback(page,
+								DATA, true);
 				else
 					goto continue_unlock;
 			}
@@ -1339,8 +1385,6 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 	int ret;
 	long diff;
 
-	trace_f2fs_writepages(mapping->host, wbc, DATA);
-
 	/* deal with chardevs and other special file */
 	if (!mapping->a_ops->writepage)
 		return 0;
@@ -1354,41 +1398,124 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 			available_free_memory(sbi, DIRTY_DENTS))
 		goto skip_write;
 
+	/* skip writing during file defragment */
+	if (is_inode_flag_set(F2FS_I(inode), FI_DO_DEFRAG))
+		goto skip_write;
+
 	/* during POR, we don't need to trigger writepage at all. */
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		goto skip_write;
 
+	trace_f2fs_writepages(mapping->host, wbc, DATA);
+
 	diff = nr_pages_to_write(sbi, DATA, wbc);
 
-	if (!S_ISDIR(inode->i_mode)) {
+	if (!S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_ALL) {
 		mutex_lock(&sbi->writepages);
 		locked = true;
 	}
 	ret = f2fs_write_cache_pages(mapping, wbc, __f2fs_writepage, mapping);
-	f2fs_submit_merged_bio(sbi, DATA, WRITE);
+	f2fs_submit_merged_bio_cond(sbi, inode, NULL, 0, DATA, WRITE);
 	if (locked)
 		mutex_unlock(&sbi->writepages);
 
-	remove_dirty_dir_inode(inode);
+	remove_dirty_inode(inode);
 
 	wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff);
 	return ret;
 
 skip_write:
 	wbc->pages_skipped += get_dirty_pages(inode);
+	trace_f2fs_writepages(mapping->host, wbc, DATA);
 	return 0;
 }
 
 static void f2fs_write_failed(struct address_space *mapping, loff_t to)
 {
 	struct inode *inode = mapping->host;
+	loff_t i_size = i_size_read(inode);
 
-	if (to > inode->i_size) {
-		truncate_pagecache(inode, inode->i_size);
-		truncate_blocks(inode, inode->i_size, true);
+	if (to > i_size) {
+		truncate_pagecache(inode, i_size);
+		truncate_blocks(inode, i_size, true);
 	}
 }
 
+static int prepare_write_begin(struct f2fs_sb_info *sbi,
+			struct page *page, loff_t pos, unsigned len,
+			block_t *blk_addr, bool *node_changed)
+{
+	struct inode *inode = page->mapping->host;
+	pgoff_t index = page->index;
+	struct dnode_of_data dn;
+	struct page *ipage;
+	bool locked = false;
+	struct extent_info ei;
+	int err = 0;
+
+	/*
+	 * we already allocated all the blocks, so we don't need to get
+	 * the block addresses when there is no need to fill the page.
+	 */
+	if (!f2fs_has_inline_data(inode) && !f2fs_encrypted_inode(inode) &&
+					len == PAGE_SIZE)
+		return 0;
+
+	if (f2fs_has_inline_data(inode) ||
+			(pos & PAGE_MASK) >= i_size_read(inode)) {
+		f2fs_lock_op(sbi);
+		locked = true;
+	}
+restart:
+	/* check inline_data */
+	ipage = get_node_page(sbi, inode->i_ino);
+	if (IS_ERR(ipage)) {
+		err = PTR_ERR(ipage);
+		goto unlock_out;
+	}
+
+	set_new_dnode(&dn, inode, ipage, ipage, 0);
+
+	if (f2fs_has_inline_data(inode)) {
+		if (pos + len <= MAX_INLINE_DATA) {
+			read_inline_data(page, ipage);
+			set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
+			set_inline_node(ipage);
+		} else {
+			err = f2fs_convert_inline_page(&dn, page);
+			if (err)
+				goto out;
+			if (dn.data_blkaddr == NULL_ADDR)
+				err = f2fs_get_block(&dn, index);
+		}
+	} else if (locked) {
+		err = f2fs_get_block(&dn, index);
+	} else {
+		if (f2fs_lookup_extent_cache(inode, index, &ei)) {
+			dn.data_blkaddr = ei.blk + index - ei.fofs;
+		} else {
+			/* hole case */
+			err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
+			if (err || (!err && dn.data_blkaddr == NULL_ADDR)) {
+				f2fs_put_dnode(&dn);
+				f2fs_lock_op(sbi);
+				locked = true;
+				goto restart;
+			}
+		}
+	}
+
+	/* convert_inline_page can make node_changed */
+	*blk_addr = dn.data_blkaddr;
+	*node_changed = dn.node_changed;
+out:
+	f2fs_put_dnode(&dn);
+unlock_out:
+	if (locked)
+		f2fs_unlock_op(sbi);
+	return err;
+}
+
 static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 		loff_t pos, unsigned len, unsigned flags,
 		struct page **pagep, void **fsdata)
@@ -1396,15 +1523,13 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 	struct inode *inode = mapping->host;
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct page *page = NULL;
-	struct page *ipage;
-	pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT;
-	struct dnode_of_data dn;
+	pgoff_t index = ((unsigned long long) pos) >> PAGE_SHIFT;
+	bool need_balance = false;
+	block_t blkaddr = NULL_ADDR;
 	int err = 0;
 
 	trace_f2fs_write_begin(inode, pos, len, flags);
 
-	f2fs_balance_fs(sbi);
-
 	/*
 	 * We should check this at this moment to avoid deadlock on inode page
 	 * and #0 page. The locking rule for inline_data conversion should be:
@@ -1424,64 +1549,51 @@ repeat:
 
 	*pagep = page;
 
-	f2fs_lock_op(sbi);
-
-	/* check inline_data */
-	ipage = get_node_page(sbi, inode->i_ino);
-	if (IS_ERR(ipage)) {
-		err = PTR_ERR(ipage);
-		goto unlock_fail;
-	}
-
-	set_new_dnode(&dn, inode, ipage, ipage, 0);
+	err = prepare_write_begin(sbi, page, pos, len,
+					&blkaddr, &need_balance);
+	if (err)
+		goto fail;
 
-	if (f2fs_has_inline_data(inode)) {
-		if (pos + len <= MAX_INLINE_DATA) {
-			read_inline_data(page, ipage);
-			set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
-			sync_inode_page(&dn);
-			goto put_next;
+	if (need_balance && has_not_enough_free_secs(sbi, 0)) {
+		unlock_page(page);
+		f2fs_balance_fs(sbi, true);
+		lock_page(page);
+		if (page->mapping != mapping) {
+			/* The page got truncated from under us */
+			f2fs_put_page(page, 1);
+			goto repeat;
 		}
-		err = f2fs_convert_inline_page(&dn, page);
-		if (err)
-			goto put_fail;
 	}
 
-	err = f2fs_get_block(&dn, index);
-	if (err)
-		goto put_fail;
-put_next:
-	f2fs_put_dnode(&dn);
-	f2fs_unlock_op(sbi);
-
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_wait_on_page_writeback(page, DATA, false);
 
 	/* wait for GCed encrypted page writeback */
 	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
-		f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr);
+		f2fs_wait_on_encrypted_page_writeback(sbi, blkaddr);
 
-	if (len == PAGE_CACHE_SIZE)
+	if (len == PAGE_SIZE)
 		goto out_update;
 	if (PageUptodate(page))
 		goto out_clear;
 
-	if ((pos & PAGE_CACHE_MASK) >= i_size_read(inode)) {
-		unsigned start = pos & (PAGE_CACHE_SIZE - 1);
+	if ((pos & PAGE_MASK) >= i_size_read(inode)) {
+		unsigned start = pos & (PAGE_SIZE - 1);
 		unsigned end = start + len;
 
 		/* Reading beyond i_size is simple: memset to zero */
-		zero_user_segments(page, 0, start, end, PAGE_CACHE_SIZE);
+		zero_user_segments(page, 0, start, end, PAGE_SIZE);
 		goto out_update;
 	}
 
-	if (dn.data_blkaddr == NEW_ADDR) {
-		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+	if (blkaddr == NEW_ADDR) {
+		zero_user_segment(page, 0, PAGE_SIZE);
 	} else {
 		struct f2fs_io_info fio = {
 			.sbi = sbi,
 			.type = DATA,
 			.rw = READ_SYNC,
-			.blk_addr = dn.data_blkaddr,
+			.old_blkaddr = blkaddr,
+			.new_blkaddr = blkaddr,
 			.page = page,
 			.encrypted_page = NULL,
 		};
@@ -1501,7 +1613,7 @@ put_next:
 
 		/* avoid symlink page */
 		if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
-			err = f2fs_decrypt_one(inode, page);
+			err = fscrypt_decrypt_page(page);
 			if (err)
 				goto fail;
 		}
@@ -1512,10 +1624,6 @@ out_clear:
 	clear_cold_data(page);
 	return 0;
 
-put_fail:
-	f2fs_put_dnode(&dn);
-unlock_fail:
-	f2fs_unlock_op(sbi);
 fail:
 	f2fs_put_page(page, 1);
 	f2fs_write_failed(mapping, pos + len);
@@ -1536,10 +1644,10 @@ static int f2fs_write_end(struct file *file,
 	if (pos + copied > i_size_read(inode)) {
 		i_size_write(inode, pos + copied);
 		mark_inode_dirty(inode);
-		update_inode_page(inode);
 	}
 
 	f2fs_put_page(page, 1);
+	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 	return copied;
 }
 
@@ -1560,38 +1668,21 @@ static int check_direct_IO(struct inode *inode, struct iov_iter *iter,
 static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 			      loff_t offset)
 {
-	struct file *file = iocb->ki_filp;
-	struct address_space *mapping = file->f_mapping;
+	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct inode *inode = mapping->host;
 	size_t count = iov_iter_count(iter);
 	int err;
 
-	/* we don't need to use inline_data strictly */
-	if (f2fs_has_inline_data(inode)) {
-		err = f2fs_convert_inline_inode(inode);
-		if (err)
-			return err;
-	}
-
-	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
-		return 0;
-
 	err = check_direct_IO(inode, iter, offset);
 	if (err)
 		return err;
 
-	trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
+	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
+		return 0;
 
-	if (iov_iter_rw(iter) == WRITE) {
-		__allocate_data_blocks(inode, offset, count);
-		if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) {
-			err = -EIO;
-			goto out;
-		}
-	}
+	trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
 
 	err = blockdev_direct_IO(iocb, inode, iter, offset, get_data_block_dio);
-out:
 	if (err < 0 && iov_iter_rw(iter) == WRITE)
 		f2fs_write_failed(mapping, offset + count);
 
@@ -1607,7 +1698,7 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset,
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 
 	if (inode->i_ino >= F2FS_ROOT_INO(sbi) &&
-		(offset % PAGE_CACHE_SIZE || length != PAGE_CACHE_SIZE))
+		(offset % PAGE_SIZE || length != PAGE_SIZE))
 		return;
 
 	if (PageDirty(page)) {
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 478e5d54154f..f4a61a5ff79f 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -38,12 +38,15 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->hit_rbtree = atomic64_read(&sbi->read_hit_rbtree);
 	si->hit_total = si->hit_largest + si->hit_cached + si->hit_rbtree;
 	si->total_ext = atomic64_read(&sbi->total_hit_ext);
-	si->ext_tree = sbi->total_ext_tree;
+	si->ext_tree = atomic_read(&sbi->total_ext_tree);
+	si->zombie_tree = atomic_read(&sbi->total_zombie_tree);
 	si->ext_node = atomic_read(&sbi->total_ext_node);
 	si->ndirty_node = get_pages(sbi, F2FS_DIRTY_NODES);
 	si->ndirty_dent = get_pages(sbi, F2FS_DIRTY_DENTS);
-	si->ndirty_dirs = sbi->n_dirty_dirs;
 	si->ndirty_meta = get_pages(sbi, F2FS_DIRTY_META);
+	si->ndirty_data = get_pages(sbi, F2FS_DIRTY_DATA);
+	si->ndirty_dirs = sbi->ndirty_inode[DIR_INODE];
+	si->ndirty_files = sbi->ndirty_inode[FILE_INODE];
 	si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES);
 	si->wb_pages = get_pages(sbi, F2FS_WRITEBACK);
 	si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg;
@@ -105,7 +108,7 @@ static void update_sit_info(struct f2fs_sb_info *sbi)
 
 	bimodal = 0;
 	total_vblocks = 0;
-	blks_per_sec = sbi->segs_per_sec * (1 << sbi->log_blocks_per_seg);
+	blks_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg;
 	hblks_per_sec = blks_per_sec / 2;
 	for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
 		vblocks = get_valid_blocks(sbi, segno, sbi->segs_per_sec);
@@ -161,7 +164,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 
 	/* build curseg */
 	si->base_mem += sizeof(struct curseg_info) * NR_CURSEG_TYPE;
-	si->base_mem += PAGE_CACHE_SIZE * NR_CURSEG_TYPE;
+	si->base_mem += PAGE_SIZE * NR_CURSEG_TYPE;
 
 	/* build dirty segmap */
 	si->base_mem += sizeof(struct dirty_seglist_info);
@@ -189,18 +192,18 @@ get_cache:
 	si->cache_mem += NM_I(sbi)->dirty_nat_cnt *
 					sizeof(struct nat_entry_set);
 	si->cache_mem += si->inmem_pages * sizeof(struct inmem_pages);
-	si->cache_mem += sbi->n_dirty_dirs * sizeof(struct inode_entry);
 	for (i = 0; i <= UPDATE_INO; i++)
 		si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry);
-	si->cache_mem += sbi->total_ext_tree * sizeof(struct extent_tree);
+	si->cache_mem += atomic_read(&sbi->total_ext_tree) *
+						sizeof(struct extent_tree);
 	si->cache_mem += atomic_read(&sbi->total_ext_node) *
 						sizeof(struct extent_node);
 
 	si->page_mem = 0;
 	npages = NODE_MAPPING(sbi)->nrpages;
-	si->page_mem += (unsigned long long)npages << PAGE_CACHE_SHIFT;
+	si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
 	npages = META_MAPPING(sbi)->nrpages;
-	si->page_mem += (unsigned long long)npages << PAGE_CACHE_SHIFT;
+	si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
 }
 
 static int stat_show(struct seq_file *s, void *v)
@@ -211,12 +214,10 @@ static int stat_show(struct seq_file *s, void *v)
 
 	mutex_lock(&f2fs_stat_mutex);
 	list_for_each_entry(si, &f2fs_stat_list, stat_list) {
-		char devname[BDEVNAME_SIZE];
-
 		update_general_status(si->sbi);
 
-		seq_printf(s, "\n=====[ partition info(%s). #%d ]=====\n",
-			bdevname(si->sbi->sb->s_bdev, devname), i++);
+		seq_printf(s, "\n=====[ partition info(%pg). #%d ]=====\n",
+			si->sbi->sb->s_bdev, i++);
 		seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ",
 			   si->sit_area_segs, si->nat_area_segs);
 		seq_printf(s, "[SSA: %d] [MAIN: %d",
@@ -269,7 +270,8 @@ static int stat_show(struct seq_file *s, void *v)
 			   si->dirty_count);
 		seq_printf(s, "  - Prefree: %d\n  - Free: %d (%d)\n\n",
 			   si->prefree_count, si->free_segs, si->free_secs);
-		seq_printf(s, "CP calls: %d\n", si->cp_count);
+		seq_printf(s, "CP calls: %d (BG: %d)\n",
+				si->cp_count, si->bg_cp_count);
 		seq_printf(s, "GC calls: %d (BG: %d)\n",
 			   si->call_count, si->bg_gc);
 		seq_printf(s, "  - data segments : %d (%d)\n",
@@ -290,8 +292,8 @@ static int stat_show(struct seq_file *s, void *v)
 				!si->total_ext ? 0 :
 				div64_u64(si->hit_total * 100, si->total_ext),
 				si->hit_total, si->total_ext);
-		seq_printf(s, "  - Inner Struct Count: tree: %d, node: %d\n",
-				si->ext_tree, si->ext_node);
+		seq_printf(s, "  - Inner Struct Count: tree: %d(%d), node: %d\n",
+				si->ext_tree, si->zombie_tree, si->ext_node);
 		seq_puts(s, "\nBalancing F2FS Async:\n");
 		seq_printf(s, "  - inmem: %4d, wb: %4d\n",
 			   si->inmem_pages, si->wb_pages);
@@ -299,6 +301,8 @@ static int stat_show(struct seq_file *s, void *v)
 			   si->ndirty_node, si->node_pages);
 		seq_printf(s, "  - dents: %4d in dirs:%4d\n",
 			   si->ndirty_dent, si->ndirty_dirs);
+		seq_printf(s, "  - datas: %4d in files:%4d\n",
+			   si->ndirty_data, si->ndirty_files);
 		seq_printf(s, "  - meta: %4d in %4d\n",
 			   si->ndirty_meta, si->meta_pages);
 		seq_printf(s, "  - NATs: %9d/%9d\n  - SITs: %9d/%9d\n",
@@ -406,20 +410,23 @@ void f2fs_destroy_stats(struct f2fs_sb_info *sbi)
 	kfree(si);
 }
 
-void __init f2fs_create_root_stats(void)
+int __init f2fs_create_root_stats(void)
 {
 	struct dentry *file;
 
 	f2fs_debugfs_root = debugfs_create_dir("f2fs", NULL);
 	if (!f2fs_debugfs_root)
-		return;
+		return -ENOMEM;
 
 	file = debugfs_create_file("status", S_IRUGO, f2fs_debugfs_root,
 			NULL, &stat_fops);
 	if (!file) {
 		debugfs_remove(f2fs_debugfs_root);
 		f2fs_debugfs_root = NULL;
+		return -ENOMEM;
 	}
+
+	return 0;
 }
 
 void f2fs_destroy_root_stats(void)
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 7c1678ba8f92..af819571bce7 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -17,8 +17,8 @@
 
 static unsigned long dir_blocks(struct inode *inode)
 {
-	return ((unsigned long long) (i_size_read(inode) + PAGE_CACHE_SIZE - 1))
-							>> PAGE_CACHE_SHIFT;
+	return ((unsigned long long) (i_size_read(inode) + PAGE_SIZE - 1))
+							>> PAGE_SHIFT;
 }
 
 static unsigned int dir_buckets(unsigned int level, int dir_level)
@@ -77,7 +77,7 @@ static unsigned long dir_block_index(unsigned int level,
 }
 
 static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
-				struct f2fs_filename *fname,
+				struct fscrypt_name *fname,
 				f2fs_hash_t namehash,
 				int *max_slots,
 				struct page **res_page)
@@ -103,15 +103,15 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
 	return de;
 }
 
-struct f2fs_dir_entry *find_target_dentry(struct f2fs_filename *fname,
+struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname,
 			f2fs_hash_t namehash, int *max_slots,
 			struct f2fs_dentry_ptr *d)
 {
 	struct f2fs_dir_entry *de;
 	unsigned long bit_pos = 0;
 	int max_len = 0;
-	struct f2fs_str de_name = FSTR_INIT(NULL, 0);
-	struct f2fs_str *name = &fname->disk_name;
+	struct fscrypt_str de_name = FSTR_INIT(NULL, 0);
+	struct fscrypt_str *name = &fname->disk_name;
 
 	if (max_slots)
 		*max_slots = 0;
@@ -157,7 +157,7 @@ found:
 
 static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 					unsigned int level,
-					struct f2fs_filename *fname,
+					struct fscrypt_name *fname,
 					struct page **res_page)
 {
 	struct qstr name = FSTR_TO_QSTR(&fname->disk_name);
@@ -172,8 +172,6 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 
 	namehash = f2fs_dentry_hash(&name);
 
-	f2fs_bug_on(F2FS_I_SB(dir), level > MAX_DIR_HASH_DEPTH);
-
 	nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level);
 	nblock = bucket_blocks(level);
 
@@ -220,12 +218,12 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
 	struct f2fs_dir_entry *de = NULL;
 	unsigned int max_depth;
 	unsigned int level;
-	struct f2fs_filename fname;
+	struct fscrypt_name fname;
 	int err;
 
 	*res_page = NULL;
 
-	err = f2fs_fname_setup_filename(dir, child, 1, &fname);
+	err = fscrypt_setup_filename(dir, child, 1, &fname);
 	if (err)
 		return NULL;
 
@@ -238,6 +236,14 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
 		goto out;
 
 	max_depth = F2FS_I(dir)->i_current_depth;
+	if (unlikely(max_depth > MAX_DIR_HASH_DEPTH)) {
+		f2fs_msg(F2FS_I_SB(dir)->sb, KERN_WARNING,
+				"Corrupted max_depth of %lu: %u",
+				dir->i_ino, max_depth);
+		max_depth = MAX_DIR_HASH_DEPTH;
+		F2FS_I(dir)->i_current_depth = max_depth;
+		mark_inode_dirty(dir);
+	}
 
 	for (level = 0; level < max_depth; level++) {
 		de = find_in_level(dir, level, &fname, res_page);
@@ -245,7 +251,7 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
 			break;
 	}
 out:
-	f2fs_fname_free_filename(&fname);
+	fscrypt_free_filename(&fname);
 	return de;
 }
 
@@ -290,7 +296,7 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
 {
 	enum page_type type = f2fs_has_inline_dentry(dir) ? NODE : DATA;
 	lock_page(page);
-	f2fs_wait_on_page_writeback(page, type);
+	f2fs_wait_on_page_writeback(page, type, true);
 	de->ino = cpu_to_le32(inode->i_ino);
 	set_de_type(de, inode->i_mode);
 	f2fs_dentry_kunmap(dir, page);
@@ -305,7 +311,7 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage)
 {
 	struct f2fs_inode *ri;
 
-	f2fs_wait_on_page_writeback(ipage, NODE);
+	f2fs_wait_on_page_writeback(ipage, NODE, true);
 
 	/* copy name info. to this inode page */
 	ri = F2FS_INODE(ipage);
@@ -335,24 +341,14 @@ int update_dent_inode(struct inode *inode, struct inode *to,
 void do_make_empty_dir(struct inode *inode, struct inode *parent,
 					struct f2fs_dentry_ptr *d)
 {
-	struct f2fs_dir_entry *de;
-
-	de = &d->dentry[0];
-	de->name_len = cpu_to_le16(1);
-	de->hash_code = 0;
-	de->ino = cpu_to_le32(inode->i_ino);
-	memcpy(d->filename[0], ".", 1);
-	set_de_type(de, inode->i_mode);
+	struct qstr dot = QSTR_INIT(".", 1);
+	struct qstr dotdot = QSTR_INIT("..", 2);
 
-	de = &d->dentry[1];
-	de->hash_code = 0;
-	de->name_len = cpu_to_le16(2);
-	de->ino = cpu_to_le32(parent->i_ino);
-	memcpy(d->filename[1], "..", 2);
-	set_de_type(de, parent->i_mode);
+	/* update dirent of "." */
+	f2fs_update_dentry(inode->i_ino, inode->i_mode, d, &dot, 0, 0);
 
-	test_and_set_bit_le(0, (void *)d->bitmap);
-	test_and_set_bit_le(1, (void *)d->bitmap);
+	/* update dirent of ".." */
+	f2fs_update_dentry(parent->i_ino, parent->i_mode, d, &dotdot, 0, 1);
 }
 
 static int make_empty_dir(struct inode *inode,
@@ -407,7 +403,7 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
 			goto put_error;
 
 		if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode)) {
-			err = f2fs_inherit_context(dir, inode, page);
+			err = fscrypt_inherit_context(dir, inode, page, false);
 			if (err)
 				goto put_error;
 		}
@@ -444,7 +440,7 @@ error:
 	/* once the failed inode becomes a bad inode, i_mode is S_IFREG */
 	truncate_inode_pages(&inode->i_data, 0);
 	truncate_blocks(inode, 0, false);
-	remove_dirty_dir_inode(inode);
+	remove_dirty_inode(inode);
 	remove_inode_page(inode);
 	return ERR_PTR(err);
 }
@@ -505,8 +501,12 @@ void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
 	memcpy(d->filename[bit_pos], name->name, name->len);
 	de->ino = cpu_to_le32(ino);
 	set_de_type(de, mode);
-	for (i = 0; i < slots; i++)
+	for (i = 0; i < slots; i++) {
 		test_and_set_bit_le(bit_pos + i, (void *)d->bitmap);
+		/* avoid wrong garbage data for readdir */
+		if (i)
+			(de + i)->name_len = 0;
+	}
 }
 
 /*
@@ -526,11 +526,11 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
 	struct f2fs_dentry_block *dentry_blk = NULL;
 	struct f2fs_dentry_ptr d;
 	struct page *page = NULL;
-	struct f2fs_filename fname;
+	struct fscrypt_name fname;
 	struct qstr new_name;
 	int slots, err;
 
-	err = f2fs_fname_setup_filename(dir, name, 0, &fname);
+	err = fscrypt_setup_filename(dir, name, 0, &fname);
 	if (err)
 		return err;
 
@@ -592,7 +592,7 @@ start:
 	++level;
 	goto start;
 add_dentry:
-	f2fs_wait_on_page_writeback(dentry_page, DATA);
+	f2fs_wait_on_page_writeback(dentry_page, DATA, true);
 
 	if (inode) {
 		down_write(&F2FS_I(inode)->i_sem);
@@ -629,7 +629,8 @@ fail:
 	kunmap(dentry_page);
 	f2fs_put_page(dentry_page, 1);
 out:
-	f2fs_fname_free_filename(&fname);
+	fscrypt_free_filename(&fname);
+	f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
 	return err;
 }
 
@@ -651,6 +652,7 @@ int f2fs_do_tmpfile(struct inode *inode, struct inode *dir)
 	clear_inode_flag(F2FS_I(inode), FI_NEW_INODE);
 fail:
 	up_write(&F2FS_I(inode)->i_sem);
+	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 	return err;
 }
 
@@ -695,11 +697,13 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 	int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
 	int i;
 
+	f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
+
 	if (f2fs_has_inline_dentry(dir))
 		return f2fs_delete_inline_entry(dentry, page, dir, inode);
 
 	lock_page(page);
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_wait_on_page_writeback(page, DATA, true);
 
 	dentry_blk = page_address(page);
 	bit_pos = dentry - dentry_blk->dentry;
@@ -767,12 +771,12 @@ bool f2fs_empty_dir(struct inode *dir)
 }
 
 bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
-				unsigned int start_pos, struct f2fs_str *fstr)
+			unsigned int start_pos, struct fscrypt_str *fstr)
 {
 	unsigned char d_type = DT_UNKNOWN;
 	unsigned int bit_pos;
 	struct f2fs_dir_entry *de = NULL;
-	struct f2fs_str de_name = FSTR_INIT(NULL, 0);
+	struct fscrypt_str de_name = FSTR_INIT(NULL, 0);
 
 	bit_pos = ((unsigned long)ctx->pos % d->max);
 
@@ -782,6 +786,12 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 			break;
 
 		de = &d->dentry[bit_pos];
+		if (de->name_len == 0) {
+			bit_pos++;
+			ctx->pos = start_pos + bit_pos;
+			continue;
+		}
+
 		if (de->file_type < F2FS_FT_MAX)
 			d_type = f2fs_filetype_table[de->file_type];
 		else
@@ -800,8 +810,9 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 
 			memcpy(de_name.name, d->filename[bit_pos], de_name.len);
 
-			ret = f2fs_fname_disk_to_usr(d->inode, &de->hash_code,
-							&de_name, fstr);
+			ret = fscrypt_fname_disk_to_usr(d->inode,
+						(u32)de->hash_code, 0,
+						&de_name, fstr);
 			kfree(de_name.name);
 			if (ret < 0)
 				return true;
@@ -829,16 +840,15 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 	struct file_ra_state *ra = &file->f_ra;
 	unsigned int n = ((unsigned long)ctx->pos / NR_DENTRY_IN_BLOCK);
 	struct f2fs_dentry_ptr d;
-	struct f2fs_str fstr = FSTR_INIT(NULL, 0);
+	struct fscrypt_str fstr = FSTR_INIT(NULL, 0);
 	int err = 0;
 
 	if (f2fs_encrypted_inode(inode)) {
-		err = f2fs_get_encryption_info(inode);
-		if (err)
+		err = fscrypt_get_encryption_info(inode);
+		if (err && err != -ENOKEY)
 			return err;
 
-		err = f2fs_fname_crypto_alloc_buffer(inode, F2FS_NAME_LEN,
-								&fstr);
+		err = fscrypt_fname_alloc_buffer(inode, F2FS_NAME_LEN, &fstr);
 		if (err < 0)
 			return err;
 	}
@@ -855,36 +865,46 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 
 	for (; n < npages; n++) {
 		dentry_page = get_lock_data_page(inode, n, false);
-		if (IS_ERR(dentry_page))
-			continue;
+		if (IS_ERR(dentry_page)) {
+			err = PTR_ERR(dentry_page);
+			if (err == -ENOENT)
+				continue;
+			else
+				goto out;
+		}
 
 		dentry_blk = kmap(dentry_page);
 
 		make_dentry_ptr(inode, &d, (void *)dentry_blk, 1);
 
-		if (f2fs_fill_dentries(ctx, &d, n * NR_DENTRY_IN_BLOCK, &fstr))
-			goto stop;
+		if (f2fs_fill_dentries(ctx, &d, n * NR_DENTRY_IN_BLOCK, &fstr)) {
+			kunmap(dentry_page);
+			f2fs_put_page(dentry_page, 1);
+			break;
+		}
 
 		ctx->pos = (n + 1) * NR_DENTRY_IN_BLOCK;
 		kunmap(dentry_page);
 		f2fs_put_page(dentry_page, 1);
-		dentry_page = NULL;
-	}
-stop:
-	if (dentry_page && !IS_ERR(dentry_page)) {
-		kunmap(dentry_page);
-		f2fs_put_page(dentry_page, 1);
 	}
 out:
-	f2fs_fname_crypto_free_buffer(&fstr);
+	fscrypt_fname_free_buffer(&fstr);
 	return err;
 }
 
+static int f2fs_dir_open(struct inode *inode, struct file *filp)
+{
+	if (f2fs_encrypted_inode(inode))
+		return fscrypt_get_encryption_info(inode) ? -EACCES : 0;
+	return 0;
+}
+
 const struct file_operations f2fs_dir_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= generic_read_dir,
 	.iterate	= f2fs_readdir,
 	.fsync		= f2fs_sync_file,
+	.open		= f2fs_dir_open,
 	.unlocked_ioctl	= f2fs_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl   = f2fs_compat_ioctl,
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index 7ddba812e11b..c859bb044728 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -33,10 +33,11 @@ static struct extent_node *__attach_extent_node(struct f2fs_sb_info *sbi,
 
 	en->ei = *ei;
 	INIT_LIST_HEAD(&en->list);
+	en->et = et;
 
 	rb_link_node(&en->rb_node, parent, p);
 	rb_insert_color(&en->rb_node, &et->root);
-	et->count++;
+	atomic_inc(&et->node_cnt);
 	atomic_inc(&sbi->total_ext_node);
 	return en;
 }
@@ -45,11 +46,29 @@ static void __detach_extent_node(struct f2fs_sb_info *sbi,
 				struct extent_tree *et, struct extent_node *en)
 {
 	rb_erase(&en->rb_node, &et->root);
-	et->count--;
+	atomic_dec(&et->node_cnt);
 	atomic_dec(&sbi->total_ext_node);
 
 	if (et->cached_en == en)
 		et->cached_en = NULL;
+	kmem_cache_free(extent_node_slab, en);
+}
+
+/*
+ * Flow to release an extent_node:
+ * 1. list_del_init
+ * 2. __detach_extent_node
+ * 3. kmem_cache_free.
+ */
+static void __release_extent_node(struct f2fs_sb_info *sbi,
+			struct extent_tree *et, struct extent_node *en)
+{
+	spin_lock(&sbi->extent_lock);
+	f2fs_bug_on(sbi, list_empty(&en->list));
+	list_del_init(&en->list);
+	spin_unlock(&sbi->extent_lock);
+
+	__detach_extent_node(sbi, et, en);
 }
 
 static struct extent_tree *__grab_extent_tree(struct inode *inode)
@@ -68,11 +87,13 @@ static struct extent_tree *__grab_extent_tree(struct inode *inode)
 		et->root = RB_ROOT;
 		et->cached_en = NULL;
 		rwlock_init(&et->lock);
-		atomic_set(&et->refcount, 0);
-		et->count = 0;
-		sbi->total_ext_tree++;
+		INIT_LIST_HEAD(&et->list);
+		atomic_set(&et->node_cnt, 0);
+		atomic_inc(&sbi->total_ext_tree);
+	} else {
+		atomic_dec(&sbi->total_zombie_tree);
+		list_del_init(&et->list);
 	}
-	atomic_inc(&et->refcount);
 	up_write(&sbi->extent_tree_lock);
 
 	/* never died until evict_inode */
@@ -127,32 +148,21 @@ static struct extent_node *__init_extent_tree(struct f2fs_sb_info *sbi,
 }
 
 static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,
-					struct extent_tree *et, bool free_all)
+					struct extent_tree *et)
 {
 	struct rb_node *node, *next;
 	struct extent_node *en;
-	unsigned int count = et->count;
+	unsigned int count = atomic_read(&et->node_cnt);
 
 	node = rb_first(&et->root);
 	while (node) {
 		next = rb_next(node);
 		en = rb_entry(node, struct extent_node, rb_node);
-
-		if (free_all) {
-			spin_lock(&sbi->extent_lock);
-			if (!list_empty(&en->list))
-				list_del_init(&en->list);
-			spin_unlock(&sbi->extent_lock);
-		}
-
-		if (free_all || list_empty(&en->list)) {
-			__detach_extent_node(sbi, et, en);
-			kmem_cache_free(extent_node_slab, en);
-		}
+		__release_extent_node(sbi, et, en);
 		node = next;
 	}
 
-	return count - et->count;
+	return count - atomic_read(&et->node_cnt);
 }
 
 static void __drop_largest_extent(struct inode *inode,
@@ -164,34 +174,33 @@ static void __drop_largest_extent(struct inode *inode,
 		largest->len = 0;
 }
 
-void f2fs_drop_largest_extent(struct inode *inode, pgoff_t fofs)
-{
-	if (!f2fs_may_extent_tree(inode))
-		return;
-
-	__drop_largest_extent(inode, fofs, 1);
-}
-
-void f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
+/* return true, if inode page is changed */
+bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct extent_tree *et;
 	struct extent_node *en;
 	struct extent_info ei;
 
-	if (!f2fs_may_extent_tree(inode))
-		return;
+	if (!f2fs_may_extent_tree(inode)) {
+		/* drop largest extent */
+		if (i_ext && i_ext->len) {
+			i_ext->len = 0;
+			return true;
+		}
+		return false;
+	}
 
 	et = __grab_extent_tree(inode);
 
-	if (!i_ext || le32_to_cpu(i_ext->len) < F2FS_MIN_EXTENT_LEN)
-		return;
+	if (!i_ext || !i_ext->len)
+		return false;
 
 	set_extent_info(&ei, le32_to_cpu(i_ext->fofs),
 		le32_to_cpu(i_ext->blk), le32_to_cpu(i_ext->len));
 
 	write_lock(&et->lock);
-	if (et->count)
+	if (atomic_read(&et->node_cnt))
 		goto out;
 
 	en = __init_extent_tree(sbi, et, &ei);
@@ -202,6 +211,7 @@ void f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
 	}
 out:
 	write_unlock(&et->lock);
+	return false;
 }
 
 static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
@@ -230,9 +240,10 @@ static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
 	if (en) {
 		*ei = en->ei;
 		spin_lock(&sbi->extent_lock);
-		if (!list_empty(&en->list))
+		if (!list_empty(&en->list)) {
 			list_move_tail(&en->list, &sbi->extent_list);
-		et->cached_en = en;
+			et->cached_en = en;
+		}
 		spin_unlock(&sbi->extent_lock);
 		ret = true;
 	}
@@ -327,7 +338,6 @@ lookup_neighbors:
 
 static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi,
 				struct extent_tree *et, struct extent_info *ei,
-				struct extent_node **den,
 				struct extent_node *prev_ex,
 				struct extent_node *next_ex)
 {
@@ -340,20 +350,25 @@ static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi,
 	}
 
 	if (next_ex && __is_front_mergeable(ei, &next_ex->ei)) {
-		if (en) {
-			__detach_extent_node(sbi, et, prev_ex);
-			*den = prev_ex;
-		}
+		if (en)
+			__release_extent_node(sbi, et, prev_ex);
 		next_ex->ei.fofs = ei->fofs;
 		next_ex->ei.blk = ei->blk;
 		next_ex->ei.len += ei->len;
 		en = next_ex;
 	}
 
-	if (en) {
-		__try_update_largest_extent(et, en);
+	if (!en)
+		return NULL;
+
+	__try_update_largest_extent(et, en);
+
+	spin_lock(&sbi->extent_lock);
+	if (!list_empty(&en->list)) {
+		list_move_tail(&en->list, &sbi->extent_list);
 		et->cached_en = en;
 	}
+	spin_unlock(&sbi->extent_lock);
 	return en;
 }
 
@@ -389,7 +404,12 @@ do_insert:
 		return NULL;
 
 	__try_update_largest_extent(et, en);
+
+	/* update in global extent list */
+	spin_lock(&sbi->extent_lock);
+	list_add_tail(&en->list, &sbi->extent_list);
 	et->cached_en = en;
+	spin_unlock(&sbi->extent_lock);
 	return en;
 }
 
@@ -477,7 +497,7 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 		if (parts)
 			__try_update_largest_extent(et, en);
 		else
-			__detach_extent_node(sbi, et, en);
+			__release_extent_node(sbi, et, en);
 
 		/*
 		 * if original extent is split into zero or two parts, extent
@@ -488,31 +508,15 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 			insert_p = NULL;
 			insert_parent = NULL;
 		}
-
-		/* update in global extent list */
-		spin_lock(&sbi->extent_lock);
-		if (!parts && !list_empty(&en->list))
-			list_del(&en->list);
-		if (en1)
-			list_add_tail(&en1->list, &sbi->extent_list);
-		spin_unlock(&sbi->extent_lock);
-
-		/* release extent node */
-		if (!parts)
-			kmem_cache_free(extent_node_slab, en);
-
 		en = next_en;
 	}
 
 	/* 3. update extent in extent cache */
 	if (blkaddr) {
-		struct extent_node *den = NULL;
 
 		set_extent_info(&ei, fofs, blkaddr, len);
-		en1 = __try_merge_extent_node(sbi, et, &ei, &den,
-							prev_en, next_en);
-		if (!en1)
-			en1 = __insert_extent_tree(sbi, et, &ei,
+		if (!__try_merge_extent_node(sbi, et, &ei, prev_en, next_en))
+			__insert_extent_tree(sbi, et, &ei,
 						insert_p, insert_parent);
 
 		/* give up extent_cache, if split and small updates happen */
@@ -522,24 +526,10 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 			et->largest.len = 0;
 			set_inode_flag(F2FS_I(inode), FI_NO_EXTENT);
 		}
-
-		spin_lock(&sbi->extent_lock);
-		if (en1) {
-			if (list_empty(&en1->list))
-				list_add_tail(&en1->list, &sbi->extent_list);
-			else
-				list_move_tail(&en1->list, &sbi->extent_list);
-		}
-		if (den && !list_empty(&den->list))
-			list_del(&den->list);
-		spin_unlock(&sbi->extent_lock);
-
-		if (den)
-			kmem_cache_free(extent_node_slab, den);
 	}
 
 	if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT))
-		__free_extent_tree(sbi, et, true);
+		__free_extent_tree(sbi, et);
 
 	write_unlock(&et->lock);
 
@@ -548,46 +538,42 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 
 unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
 {
-	struct extent_tree *treevec[EXT_TREE_VEC_SIZE];
-	struct extent_node *en, *tmp;
-	unsigned long ino = F2FS_ROOT_INO(sbi);
-	struct radix_tree_root *root = &sbi->extent_tree_root;
-	unsigned int found;
+	struct extent_tree *et, *next;
+	struct extent_node *en;
 	unsigned int node_cnt = 0, tree_cnt = 0;
 	int remained;
 
 	if (!test_opt(sbi, EXTENT_CACHE))
 		return 0;
 
+	if (!atomic_read(&sbi->total_zombie_tree))
+		goto free_node;
+
 	if (!down_write_trylock(&sbi->extent_tree_lock))
 		goto out;
 
 	/* 1. remove unreferenced extent tree */
-	while ((found = radix_tree_gang_lookup(root,
-				(void **)treevec, ino, EXT_TREE_VEC_SIZE))) {
-		unsigned i;
-
-		ino = treevec[found - 1]->ino + 1;
-		for (i = 0; i < found; i++) {
-			struct extent_tree *et = treevec[i];
-
-			if (!atomic_read(&et->refcount)) {
-				write_lock(&et->lock);
-				node_cnt += __free_extent_tree(sbi, et, true);
-				write_unlock(&et->lock);
-
-				radix_tree_delete(root, et->ino);
-				kmem_cache_free(extent_tree_slab, et);
-				sbi->total_ext_tree--;
-				tree_cnt++;
-
-				if (node_cnt + tree_cnt >= nr_shrink)
-					goto unlock_out;
-			}
+	list_for_each_entry_safe(et, next, &sbi->zombie_list, list) {
+		if (atomic_read(&et->node_cnt)) {
+			write_lock(&et->lock);
+			node_cnt += __free_extent_tree(sbi, et);
+			write_unlock(&et->lock);
 		}
+		f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
+		list_del_init(&et->list);
+		radix_tree_delete(&sbi->extent_tree_root, et->ino);
+		kmem_cache_free(extent_tree_slab, et);
+		atomic_dec(&sbi->total_ext_tree);
+		atomic_dec(&sbi->total_zombie_tree);
+		tree_cnt++;
+
+		if (node_cnt + tree_cnt >= nr_shrink)
+			goto unlock_out;
+		cond_resched();
 	}
 	up_write(&sbi->extent_tree_lock);
 
+free_node:
 	/* 2. remove LRU extent entries */
 	if (!down_write_trylock(&sbi->extent_tree_lock))
 		goto out;
@@ -595,34 +581,29 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
 	remained = nr_shrink - (node_cnt + tree_cnt);
 
 	spin_lock(&sbi->extent_lock);
-	list_for_each_entry_safe(en, tmp, &sbi->extent_list, list) {
-		if (!remained--)
+	for (; remained > 0; remained--) {
+		if (list_empty(&sbi->extent_list))
 			break;
-		list_del_init(&en->list);
-	}
-	spin_unlock(&sbi->extent_lock);
-
-	/*
-	 * reset ino for searching victims from beginning of global extent tree.
-	 */
-	ino = F2FS_ROOT_INO(sbi);
-
-	while ((found = radix_tree_gang_lookup(root,
-				(void **)treevec, ino, EXT_TREE_VEC_SIZE))) {
-		unsigned i;
+		en = list_first_entry(&sbi->extent_list,
+					struct extent_node, list);
+		et = en->et;
+		if (!write_trylock(&et->lock)) {
+			/* refresh this extent node's position in extent list */
+			list_move_tail(&en->list, &sbi->extent_list);
+			continue;
+		}
 
-		ino = treevec[found - 1]->ino + 1;
-		for (i = 0; i < found; i++) {
-			struct extent_tree *et = treevec[i];
+		list_del_init(&en->list);
+		spin_unlock(&sbi->extent_lock);
 
-			write_lock(&et->lock);
-			node_cnt += __free_extent_tree(sbi, et, false);
-			write_unlock(&et->lock);
+		__detach_extent_node(sbi, et, en);
 
-			if (node_cnt + tree_cnt >= nr_shrink)
-				goto unlock_out;
-		}
+		write_unlock(&et->lock);
+		node_cnt++;
+		spin_lock(&sbi->extent_lock);
 	}
+	spin_unlock(&sbi->extent_lock);
+
 unlock_out:
 	up_write(&sbi->extent_tree_lock);
 out:
@@ -637,11 +618,11 @@ unsigned int f2fs_destroy_extent_node(struct inode *inode)
 	struct extent_tree *et = F2FS_I(inode)->extent_tree;
 	unsigned int node_cnt = 0;
 
-	if (!et)
+	if (!et || !atomic_read(&et->node_cnt))
 		return 0;
 
 	write_lock(&et->lock);
-	node_cnt = __free_extent_tree(sbi, et, true);
+	node_cnt = __free_extent_tree(sbi, et);
 	write_unlock(&et->lock);
 
 	return node_cnt;
@@ -656,8 +637,12 @@ void f2fs_destroy_extent_tree(struct inode *inode)
 	if (!et)
 		return;
 
-	if (inode->i_nlink && !is_bad_inode(inode) && et->count) {
-		atomic_dec(&et->refcount);
+	if (inode->i_nlink && !is_bad_inode(inode) &&
+					atomic_read(&et->node_cnt)) {
+		down_write(&sbi->extent_tree_lock);
+		list_add_tail(&et->list, &sbi->zombie_list);
+		atomic_inc(&sbi->total_zombie_tree);
+		up_write(&sbi->extent_tree_lock);
 		return;
 	}
 
@@ -666,11 +651,10 @@ void f2fs_destroy_extent_tree(struct inode *inode)
 
 	/* delete extent tree entry in radix tree */
 	down_write(&sbi->extent_tree_lock);
-	atomic_dec(&et->refcount);
-	f2fs_bug_on(sbi, atomic_read(&et->refcount) || et->count);
+	f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
 	radix_tree_delete(&sbi->extent_tree_root, inode->i_ino);
 	kmem_cache_free(extent_tree_slab, et);
-	sbi->total_ext_tree--;
+	atomic_dec(&sbi->total_ext_tree);
 	up_write(&sbi->extent_tree_lock);
 
 	F2FS_I(inode)->extent_tree = NULL;
@@ -689,19 +673,21 @@ bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
 
 void f2fs_update_extent_cache(struct dnode_of_data *dn)
 {
-	struct f2fs_inode_info *fi = F2FS_I(dn->inode);
 	pgoff_t fofs;
+	block_t blkaddr;
 
 	if (!f2fs_may_extent_tree(dn->inode))
 		return;
 
-	f2fs_bug_on(F2FS_I_SB(dn->inode), dn->data_blkaddr == NEW_ADDR);
-
+	if (dn->data_blkaddr == NEW_ADDR)
+		blkaddr = NULL_ADDR;
+	else
+		blkaddr = dn->data_blkaddr;
 
-	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
-							dn->ofs_in_node;
+	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
+								dn->ofs_in_node;
 
-	if (f2fs_update_extent_tree_range(dn->inode, fofs, dn->data_blkaddr, 1))
+	if (f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, 1))
 		sync_inode_page(dn);
 }
 
@@ -722,7 +708,9 @@ void init_extent_cache_info(struct f2fs_sb_info *sbi)
 	init_rwsem(&sbi->extent_tree_lock);
 	INIT_LIST_HEAD(&sbi->extent_list);
 	spin_lock_init(&sbi->extent_lock);
-	sbi->total_ext_tree = 0;
+	atomic_set(&sbi->total_ext_tree, 0);
+	INIT_LIST_HEAD(&sbi->zombie_list);
+	atomic_set(&sbi->total_zombie_tree, 0);
 	atomic_set(&sbi->total_ext_node, 0);
 }
 
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 9db5500d63d9..7a4558d17f36 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -21,10 +21,12 @@
 #include <linux/sched.h>
 #include <linux/vmalloc.h>
 #include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/fscrypto.h>
+#include <crypto/hash.h>
 
 #ifdef CONFIG_F2FS_CHECK_FS
 #define f2fs_bug_on(sbi, condition)	BUG_ON(condition)
-#define f2fs_down_write(x, y)	down_write_nest_lock(x, y)
 #else
 #define f2fs_bug_on(sbi, condition)					\
 	do {								\
@@ -33,7 +35,6 @@
 			set_sbi_flag(sbi, SBI_NEED_FSCK);		\
 		}							\
 	} while (0)
-#define f2fs_down_write(x, y)	down_write(x)
 #endif
 
 /*
@@ -54,6 +55,7 @@
 #define F2FS_MOUNT_FASTBOOT		0x00001000
 #define F2FS_MOUNT_EXTENT_CACHE		0x00002000
 #define F2FS_MOUNT_FORCE_FG_GC		0x00004000
+#define F2FS_MOUNT_DATA_FLUSH		0x00008000
 
 #define clear_opt(sbi, option)	(sbi->mount_opt.opt &= ~F2FS_MOUNT_##option)
 #define set_opt(sbi, option)	(sbi->mount_opt.opt |= F2FS_MOUNT_##option)
@@ -82,27 +84,6 @@ struct f2fs_mount_info {
 #define F2FS_CLEAR_FEATURE(sb, mask)					\
 	F2FS_SB(sb)->raw_super->feature &= ~cpu_to_le32(mask)
 
-#define CRCPOLY_LE 0xedb88320
-
-static inline __u32 f2fs_crc32(void *buf, size_t len)
-{
-	unsigned char *p = (unsigned char *)buf;
-	__u32 crc = F2FS_SUPER_MAGIC;
-	int i;
-
-	while (len--) {
-		crc ^= *p++;
-		for (i = 0; i < 8; i++)
-			crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0);
-	}
-	return crc;
-}
-
-static inline bool f2fs_crc_valid(__u32 blk_crc, void *buf, size_t buf_size)
-{
-	return f2fs_crc32(buf, buf_size) == blk_crc;
-}
-
 /*
  * For checkpoint manager
  */
@@ -125,6 +106,7 @@ enum {
 #define BATCHED_TRIM_BLOCKS(sbi)	\
 		(BATCHED_TRIM_SEGMENTS(sbi) << (sbi)->log_blocks_per_seg)
 #define DEF_CP_INTERVAL			60	/* 60 secs */
+#define DEF_IDLE_INTERVAL		120	/* 2 mins */
 
 struct cp_control {
 	int reason;
@@ -158,13 +140,7 @@ struct ino_entry {
 	nid_t ino;		/* inode number */
 };
 
-/*
- * for the list of directory inodes or gc inodes.
- * NOTE: there are two slab users for this structure, if we add/modify/delete
- * fields in structure for one of slab users, it may affect fields or size of
- * other one, in this condition, it's better to split both of slab and related
- * data structure.
- */
+/* for the list of inodes to be GCed */
 struct inode_entry {
 	struct list_head list;	/* list head */
 	struct inode *inode;	/* vfs inode pointer */
@@ -186,37 +162,37 @@ struct fsync_inode_entry {
 	block_t last_inode;	/* block address locating the last inode */
 };
 
-#define nats_in_cursum(sum)		(le16_to_cpu(sum->n_nats))
-#define sits_in_cursum(sum)		(le16_to_cpu(sum->n_sits))
+#define nats_in_cursum(jnl)		(le16_to_cpu(jnl->n_nats))
+#define sits_in_cursum(jnl)		(le16_to_cpu(jnl->n_sits))
 
-#define nat_in_journal(sum, i)		(sum->nat_j.entries[i].ne)
-#define nid_in_journal(sum, i)		(sum->nat_j.entries[i].nid)
-#define sit_in_journal(sum, i)		(sum->sit_j.entries[i].se)
-#define segno_in_journal(sum, i)	(sum->sit_j.entries[i].segno)
+#define nat_in_journal(jnl, i)		(jnl->nat_j.entries[i].ne)
+#define nid_in_journal(jnl, i)		(jnl->nat_j.entries[i].nid)
+#define sit_in_journal(jnl, i)		(jnl->sit_j.entries[i].se)
+#define segno_in_journal(jnl, i)	(jnl->sit_j.entries[i].segno)
 
-#define MAX_NAT_JENTRIES(sum)	(NAT_JOURNAL_ENTRIES - nats_in_cursum(sum))
-#define MAX_SIT_JENTRIES(sum)	(SIT_JOURNAL_ENTRIES - sits_in_cursum(sum))
+#define MAX_NAT_JENTRIES(jnl)	(NAT_JOURNAL_ENTRIES - nats_in_cursum(jnl))
+#define MAX_SIT_JENTRIES(jnl)	(SIT_JOURNAL_ENTRIES - sits_in_cursum(jnl))
 
-static inline int update_nats_in_cursum(struct f2fs_summary_block *rs, int i)
+static inline int update_nats_in_cursum(struct f2fs_journal *journal, int i)
 {
-	int before = nats_in_cursum(rs);
-	rs->n_nats = cpu_to_le16(before + i);
+	int before = nats_in_cursum(journal);
+	journal->n_nats = cpu_to_le16(before + i);
 	return before;
 }
 
-static inline int update_sits_in_cursum(struct f2fs_summary_block *rs, int i)
+static inline int update_sits_in_cursum(struct f2fs_journal *journal, int i)
 {
-	int before = sits_in_cursum(rs);
-	rs->n_sits = cpu_to_le16(before + i);
+	int before = sits_in_cursum(journal);
+	journal->n_sits = cpu_to_le16(before + i);
 	return before;
 }
 
-static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size,
-								int type)
+static inline bool __has_cursum_space(struct f2fs_journal *journal,
+							int size, int type)
 {
 	if (type == NAT_JOURNAL)
-		return size <= MAX_NAT_JENTRIES(sum);
-	return size <= MAX_SIT_JENTRIES(sum);
+		return size <= MAX_NAT_JENTRIES(journal);
+	return size <= MAX_SIT_JENTRIES(journal);
 }
 
 /*
@@ -234,13 +210,11 @@ static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size,
 #define F2FS_IOC_ABORT_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 5)
 #define F2FS_IOC_GARBAGE_COLLECT	_IO(F2FS_IOCTL_MAGIC, 6)
 #define F2FS_IOC_WRITE_CHECKPOINT	_IO(F2FS_IOCTL_MAGIC, 7)
+#define F2FS_IOC_DEFRAGMENT		_IO(F2FS_IOCTL_MAGIC, 8)
 
-#define F2FS_IOC_SET_ENCRYPTION_POLICY					\
-		_IOR('f', 19, struct f2fs_encryption_policy)
-#define F2FS_IOC_GET_ENCRYPTION_PWSALT					\
-		_IOW('f', 20, __u8[16])
-#define F2FS_IOC_GET_ENCRYPTION_POLICY					\
-		_IOW('f', 21, struct f2fs_encryption_policy)
+#define F2FS_IOC_SET_ENCRYPTION_POLICY	FS_IOC_SET_ENCRYPTION_POLICY
+#define F2FS_IOC_GET_ENCRYPTION_POLICY	FS_IOC_GET_ENCRYPTION_POLICY
+#define F2FS_IOC_GET_ENCRYPTION_PWSALT	FS_IOC_GET_ENCRYPTION_PWSALT
 
 /*
  * should be same as XFS_IOC_GOINGDOWN.
@@ -256,33 +230,20 @@ static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size,
 /*
  * ioctl commands in 32 bit emulation
  */
-#define F2FS_IOC32_GETFLAGS             FS_IOC32_GETFLAGS
-#define F2FS_IOC32_SETFLAGS             FS_IOC32_SETFLAGS
+#define F2FS_IOC32_GETFLAGS		FS_IOC32_GETFLAGS
+#define F2FS_IOC32_SETFLAGS		FS_IOC32_SETFLAGS
+#define F2FS_IOC32_GETVERSION		FS_IOC32_GETVERSION
 #endif
 
+struct f2fs_defragment {
+	u64 start;
+	u64 len;
+};
+
 /*
  * For INODE and NODE manager
  */
 /* for directory operations */
-struct f2fs_str {
-	unsigned char *name;
-	u32 len;
-};
-
-struct f2fs_filename {
-	const struct qstr *usr_fname;
-	struct f2fs_str disk_name;
-	f2fs_hash_t hash;
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-	struct f2fs_str crypto_buf;
-#endif
-};
-
-#define FSTR_INIT(n, l)		{ .name = n, .len = l }
-#define FSTR_TO_QSTR(f)		QSTR_INIT((f)->name, (f)->len)
-#define fname_name(p)		((p)->disk_name.name)
-#define fname_len(p)		((p)->disk_name.len)
-
 struct f2fs_dentry_ptr {
 	struct inode *inode;
 	const void *bitmap;
@@ -350,6 +311,7 @@ struct extent_node {
 	struct rb_node rb_node;		/* rb node located in rb-tree */
 	struct list_head list;		/* node in global extent list of sbi */
 	struct extent_info ei;		/* extent info */
+	struct extent_tree *et;		/* extent tree pointer */
 };
 
 struct extent_tree {
@@ -357,9 +319,9 @@ struct extent_tree {
 	struct rb_root root;		/* root of extent info rb-tree */
 	struct extent_node *cached_en;	/* recently accessed extent node */
 	struct extent_info largest;	/* largested extent info */
+	struct list_head list;		/* to be used by sbi->zombie_list */
 	rwlock_t lock;			/* protect extent info rb-tree */
-	atomic_t refcount;		/* reference count of rb-tree */
-	unsigned int count;		/* # of extent node in rb-tree*/
+	atomic_t node_cnt;		/* # of extent node in rb-tree*/
 };
 
 /*
@@ -378,6 +340,7 @@ struct f2fs_map_blocks {
 	block_t m_lblk;
 	unsigned int m_len;
 	unsigned int m_flags;
+	pgoff_t *m_next_pgofs;		/* point next possible non-hole pgofs */
 };
 
 /* for flag in get_data_block */
@@ -385,6 +348,8 @@ struct f2fs_map_blocks {
 #define F2FS_GET_BLOCK_DIO		1
 #define F2FS_GET_BLOCK_FIEMAP		2
 #define F2FS_GET_BLOCK_BMAP		3
+#define F2FS_GET_BLOCK_PRE_DIO		4
+#define F2FS_GET_BLOCK_PRE_AIO		5
 
 /*
  * i_advise uses FADVISE_XXX_BIT. We can add additional hints later.
@@ -406,15 +371,6 @@ struct f2fs_map_blocks {
 #define file_enc_name(inode)	is_file(inode, FADVISE_ENC_NAME_BIT)
 #define file_set_enc_name(inode) set_file(inode, FADVISE_ENC_NAME_BIT)
 
-/* Encryption algorithms */
-#define F2FS_ENCRYPTION_MODE_INVALID		0
-#define F2FS_ENCRYPTION_MODE_AES_256_XTS	1
-#define F2FS_ENCRYPTION_MODE_AES_256_GCM	2
-#define F2FS_ENCRYPTION_MODE_AES_256_CBC	3
-#define F2FS_ENCRYPTION_MODE_AES_256_CTS	4
-
-#include "f2fs_crypto.h"
-
 #define DEF_DIR_LEVEL		0
 
 struct f2fs_inode_info {
@@ -434,17 +390,11 @@ struct f2fs_inode_info {
 	unsigned int clevel;		/* maximum level of given file name */
 	nid_t i_xattr_nid;		/* node id that contains xattrs */
 	unsigned long long xattr_ver;	/* cp version of xattr modification */
-	struct inode_entry *dirty_dir;	/* the pointer of dirty dir */
 
+	struct list_head dirty_list;	/* linked in global dirty list */
 	struct list_head inmem_pages;	/* inmemory pages managed by f2fs */
 	struct mutex inmem_lock;	/* lock for inmemory pages */
-
 	struct extent_tree *extent_tree;	/* cached extent_tree entry */
-
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-	/* Encryption params */
-	struct f2fs_crypt_info *i_crypt_info;
-#endif
 };
 
 static inline void get_extent_info(struct extent_info *ext,
@@ -511,6 +461,7 @@ struct f2fs_nm_info {
 	nid_t next_scan_nid;		/* the next nid to be scanned */
 	unsigned int ram_thresh;	/* control the memory footprint */
 	unsigned int ra_nid_pages;	/* # of nid pages to be readaheaded */
+	unsigned int dirty_nats_ratio;	/* control dirty nats ratio threshold */
 
 	/* NAT cache management */
 	struct radix_tree_root nat_root;/* root of the nat entry cache */
@@ -544,6 +495,9 @@ struct dnode_of_data {
 	nid_t nid;			/* node id of the direct node block */
 	unsigned int ofs_in_node;	/* data offset in the node page */
 	bool inode_page_locked;		/* inode page is locked or not */
+	bool node_changed;		/* is node block changed */
+	char cur_level;			/* level of hole node page */
+	char max_level;			/* level of current page located */
 	block_t	data_blkaddr;		/* block address of the node block */
 };
 
@@ -647,6 +601,7 @@ struct f2fs_sm_info {
 enum count_type {
 	F2FS_WRITEBACK,
 	F2FS_DIRTY_DENTS,
+	F2FS_DIRTY_DATA,
 	F2FS_DIRTY_NODES,
 	F2FS_DIRTY_META,
 	F2FS_INMEM_PAGES,
@@ -673,6 +628,7 @@ enum page_type {
 	META_FLUSH,
 	INMEM,		/* the below types are used by tracepoints only. */
 	INMEM_DROP,
+	INMEM_REVOKE,
 	IPU,
 	OPU,
 };
@@ -681,7 +637,8 @@ struct f2fs_io_info {
 	struct f2fs_sb_info *sbi;	/* f2fs_sb_info pointer */
 	enum page_type type;	/* contains DATA/NODE/META/META_FLUSH */
 	int rw;			/* contains R/RS/W/WS with REQ_META/REQ_PRIO */
-	block_t blk_addr;	/* block address to be written */
+	block_t new_blkaddr;	/* new block address to be written */
+	block_t old_blkaddr;	/* old block address before Cow */
 	struct page *page;	/* page to be written */
 	struct page *encrypted_page;	/* encrypted page */
 };
@@ -695,6 +652,12 @@ struct f2fs_bio_info {
 	struct rw_semaphore io_rwsem;	/* blocking op for bio */
 };
 
+enum inode_type {
+	DIR_INODE,			/* for dirty dir inode */
+	FILE_INODE,			/* for dirty regular/symlink inode */
+	NR_INODE_TYPE,
+};
+
 /* for inner inode cache management */
 struct inode_management {
 	struct radix_tree_root ino_root;	/* ino entry array */
@@ -711,11 +674,17 @@ enum {
 	SBI_POR_DOING,				/* recovery is doing or not */
 };
 
+enum {
+	CP_TIME,
+	REQ_TIME,
+	MAX_TIME,
+};
+
 struct f2fs_sb_info {
 	struct super_block *sb;			/* pointer to VFS super block */
 	struct proc_dir_entry *s_proc;		/* proc entry */
-	struct buffer_head *raw_super_buf;	/* buffer head of raw sb */
 	struct f2fs_super_block *raw_super;	/* raw super block pointer */
+	int valid_super_block;			/* valid super block no */
 	int s_flag;				/* flags for sbi */
 
 	/* for node-related operations */
@@ -737,23 +706,26 @@ struct f2fs_sb_info {
 	struct rw_semaphore node_write;		/* locking node writes */
 	struct mutex writepages;		/* mutex for writepages() */
 	wait_queue_head_t cp_wait;
-	long cp_expires, cp_interval;		/* next expected periodic cp */
+	unsigned long last_time[MAX_TIME];	/* to store time in jiffies */
+	long interval_time[MAX_TIME];		/* to store thresholds */
 
 	struct inode_management im[MAX_INO_ENTRY];      /* manage inode cache */
 
 	/* for orphan inode, use 0'th array */
 	unsigned int max_orphans;		/* max orphan inodes */
 
-	/* for directory inode management */
-	struct list_head dir_inode_list;	/* dir inode list */
-	spinlock_t dir_inode_lock;		/* for dir inode list lock */
+	/* for inode management */
+	struct list_head inode_list[NR_INODE_TYPE];	/* dirty inode list */
+	spinlock_t inode_lock[NR_INODE_TYPE];	/* for dirty inode list lock */
 
 	/* for extent tree cache */
 	struct radix_tree_root extent_tree_root;/* cache extent cache entries */
 	struct rw_semaphore extent_tree_lock;	/* locking extent radix tree */
 	struct list_head extent_list;		/* lru list for shrinker */
 	spinlock_t extent_lock;			/* locking extent lru list */
-	int total_ext_tree;			/* extent tree count */
+	atomic_t total_ext_tree;		/* extent tree count */
+	struct list_head zombie_list;		/* extent zombie tree list */
+	atomic_t total_zombie_tree;		/* extent zombie tree count */
 	atomic_t total_ext_node;		/* extent info count */
 
 	/* basic filesystem units */
@@ -771,6 +743,7 @@ struct f2fs_sb_info {
 	unsigned int total_node_count;		/* total node block count */
 	unsigned int total_valid_node_count;	/* valid node block count */
 	unsigned int total_valid_inode_count;	/* valid inode count */
+	loff_t max_file_blocks;			/* max block index of file */
 	int active_logs;			/* # of active logs */
 	int dir_level;				/* directory level */
 
@@ -809,7 +782,7 @@ struct f2fs_sb_info {
 	atomic_t inline_inode;			/* # of inline_data inodes */
 	atomic_t inline_dir;			/* # of inline_dentry inodes */
 	int bg_gc;				/* background gc calls */
-	unsigned int n_dirty_dirs;		/* # of dir inodes */
+	unsigned int ndirty_inode[NR_INODE_TYPE];	/* # of dirty inodes */
 #endif
 	unsigned int last_victim[2];		/* last victim segment # */
 	spinlock_t stat_lock;			/* lock for stat operations */
@@ -822,11 +795,73 @@ struct f2fs_sb_info {
 	struct list_head s_list;
 	struct mutex umount_mutex;
 	unsigned int shrinker_run_no;
+
+	/* For write statistics */
+	u64 sectors_written_start;
+	u64 kbytes_written;
+
+	/* Reference to checksum algorithm driver via cryptoapi */
+	struct crypto_shash *s_chksum_driver;
 };
 
+/* For write statistics. Suppose sector size is 512 bytes,
+ * and the return value is in kbytes. s is of struct f2fs_sb_info.
+ */
+#define BD_PART_WRITTEN(s)						 \
+(((u64)part_stat_read(s->sb->s_bdev->bd_part, sectors[1]) -		 \
+		s->sectors_written_start) >> 1)
+
+static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type)
+{
+	sbi->last_time[type] = jiffies;
+}
+
+static inline bool f2fs_time_over(struct f2fs_sb_info *sbi, int type)
+{
+	struct timespec ts = {sbi->interval_time[type], 0};
+	unsigned long interval = timespec_to_jiffies(&ts);
+
+	return time_after(jiffies, sbi->last_time[type] + interval);
+}
+
+static inline bool is_idle(struct f2fs_sb_info *sbi)
+{
+	struct block_device *bdev = sbi->sb->s_bdev;
+	struct request_queue *q = bdev_get_queue(bdev);
+	struct request_list *rl = &q->root_rl;
+
+	if (rl->count[BLK_RW_SYNC] || rl->count[BLK_RW_ASYNC])
+		return 0;
+
+	return f2fs_time_over(sbi, REQ_TIME);
+}
+
 /*
  * Inline functions
  */
+static inline u32 f2fs_crc32(struct f2fs_sb_info *sbi, const void *address,
+			   unsigned int length)
+{
+	SHASH_DESC_ON_STACK(shash, sbi->s_chksum_driver);
+	u32 *ctx = (u32 *)shash_desc_ctx(shash);
+	int err;
+
+	shash->tfm = sbi->s_chksum_driver;
+	shash->flags = 0;
+	*ctx = F2FS_SUPER_MAGIC;
+
+	err = crypto_shash_update(shash, address, length);
+	BUG_ON(err);
+
+	return *ctx;
+}
+
+static inline bool f2fs_crc_valid(struct f2fs_sb_info *sbi, __u32 blk_crc,
+				  void *buf, size_t buf_size)
+{
+	return f2fs_crc32(sbi, buf, buf_size) == blk_crc;
+}
+
 static inline struct f2fs_inode_info *F2FS_I(struct inode *inode)
 {
 	return container_of(inode, struct f2fs_inode_info, vfs_inode);
@@ -959,7 +994,7 @@ static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
 
 static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
 {
-	f2fs_down_write(&sbi->cp_rwsem, &sbi->cp_mutex);
+	down_write(&sbi->cp_rwsem);
 }
 
 static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
@@ -1059,8 +1094,8 @@ static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
 static inline void inode_inc_dirty_pages(struct inode *inode)
 {
 	atomic_inc(&F2FS_I(inode)->dirty_pages);
-	if (S_ISDIR(inode->i_mode))
-		inc_page_count(F2FS_I_SB(inode), F2FS_DIRTY_DENTS);
+	inc_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
+				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
 }
 
 static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type)
@@ -1075,9 +1110,8 @@ static inline void inode_dec_dirty_pages(struct inode *inode)
 		return;
 
 	atomic_dec(&F2FS_I(inode)->dirty_pages);
-
-	if (S_ISDIR(inode->i_mode))
-		dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_DENTS);
+	dec_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
+				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
 }
 
 static inline int get_pages(struct f2fs_sb_info *sbi, int count_type)
@@ -1092,8 +1126,7 @@ static inline int get_dirty_pages(struct inode *inode)
 
 static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type)
 {
-	unsigned int pages_per_sec = sbi->segs_per_sec *
-					(1 << sbi->log_blocks_per_seg);
+	unsigned int pages_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg;
 	return ((get_pages(sbi, block_type) + pages_per_sec - 1)
 			>> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
 }
@@ -1261,7 +1294,7 @@ static inline void f2fs_put_page(struct page *page, int unlock)
 		f2fs_bug_on(F2FS_P_SB(page), !PageLocked(page));
 		unlock_page(page);
 	}
-	page_cache_release(page);
+	put_page(page);
 }
 
 static inline void f2fs_put_dnode(struct dnode_of_data *dn)
@@ -1416,6 +1449,8 @@ enum {
 	FI_DROP_CACHE,		/* drop dirty page cache */
 	FI_DATA_EXIST,		/* indicate data exists */
 	FI_INLINE_DOTS,		/* indicate inline dot dentries */
+	FI_DO_DEFRAG,		/* indicate defragment is running */
+	FI_DIRTY_FILE,		/* indicate regular/symlink has dirty pages */
 };
 
 static inline void set_inode_flag(struct f2fs_inode_info *fi, int flag)
@@ -1478,9 +1513,9 @@ static inline int f2fs_has_inline_xattr(struct inode *inode)
 	return is_inode_flag_set(F2FS_I(inode), FI_INLINE_XATTR);
 }
 
-static inline unsigned int addrs_per_inode(struct f2fs_inode_info *fi)
+static inline unsigned int addrs_per_inode(struct inode *inode)
 {
-	if (f2fs_has_inline_xattr(&fi->vfs_inode))
+	if (f2fs_has_inline_xattr(inode))
 		return DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS;
 	return DEF_ADDRS_PER_INODE;
 }
@@ -1602,13 +1637,11 @@ static inline bool is_dot_dotdot(const struct qstr *str)
 
 static inline bool f2fs_may_extent_tree(struct inode *inode)
 {
-	mode_t mode = inode->i_mode;
-
 	if (!test_opt(F2FS_I_SB(inode), EXTENT_CACHE) ||
 			is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT))
 		return false;
 
-	return S_ISREG(mode);
+	return S_ISREG(inode->i_mode);
 }
 
 static inline void *f2fs_kvmalloc(size_t size, gfp_t flags)
@@ -1636,10 +1669,10 @@ static inline void *f2fs_kvzalloc(size_t size, gfp_t flags)
 	 (F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
 
 /* get offset of first page in next direct node */
-#define PGOFS_OF_NEXT_DNODE(pgofs, fi)				\
-	((pgofs < ADDRS_PER_INODE(fi)) ? ADDRS_PER_INODE(fi) :	\
-	(pgofs - ADDRS_PER_INODE(fi) + ADDRS_PER_BLOCK) /	\
-	ADDRS_PER_BLOCK * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi))
+#define PGOFS_OF_NEXT_DNODE(pgofs, inode)				\
+	((pgofs < ADDRS_PER_INODE(inode)) ? ADDRS_PER_INODE(inode) :	\
+	(pgofs - ADDRS_PER_INODE(inode) + ADDRS_PER_BLOCK) /	\
+	ADDRS_PER_BLOCK * ADDRS_PER_BLOCK + ADDRS_PER_INODE(inode))
 
 /*
  * file.c
@@ -1661,8 +1694,8 @@ long f2fs_compat_ioctl(struct file *, unsigned int, unsigned long);
 void f2fs_set_inode_flags(struct inode *);
 struct inode *f2fs_iget(struct super_block *, unsigned long);
 int try_to_free_nats(struct f2fs_sb_info *, int);
-void update_inode(struct inode *, struct page *);
-void update_inode_page(struct inode *);
+int update_inode(struct inode *, struct page *);
+int update_inode_page(struct inode *);
 int f2fs_write_inode(struct inode *, struct writeback_control *);
 void f2fs_evict_inode(struct inode *);
 void handle_failed_inode(struct inode *);
@@ -1678,10 +1711,10 @@ struct dentry *f2fs_get_parent(struct dentry *child);
 extern unsigned char f2fs_filetype_table[F2FS_FT_MAX];
 void set_de_type(struct f2fs_dir_entry *, umode_t);
 
-struct f2fs_dir_entry *find_target_dentry(struct f2fs_filename *,
+struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *,
 			f2fs_hash_t, int *, struct f2fs_dentry_ptr *);
 bool f2fs_fill_dentries(struct dir_context *, struct f2fs_dentry_ptr *,
-			unsigned int, struct f2fs_str *);
+			unsigned int, struct fscrypt_str *);
 void do_make_empty_dir(struct inode *, struct inode *,
 			struct f2fs_dentry_ptr *);
 struct page *init_inode_metadata(struct inode *, struct inode *,
@@ -1718,6 +1751,7 @@ int f2fs_commit_super(struct f2fs_sb_info *, bool);
 int f2fs_sync_fs(struct super_block *, int);
 extern __printf(3, 4)
 void f2fs_msg(struct super_block *, const char *, const char *, ...);
+int sanity_check_ckpt(struct f2fs_sb_info *sbi);
 
 /*
  * hash.c
@@ -1735,6 +1769,7 @@ int need_dentry_mark(struct f2fs_sb_info *, nid_t);
 bool is_checkpointed_node(struct f2fs_sb_info *, nid_t);
 bool need_inode_block_update(struct f2fs_sb_info *, nid_t);
 void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *);
+pgoff_t get_next_page_offset(struct dnode_of_data *, pgoff_t);
 int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int);
 int truncate_inode_blocks(struct inode *, pgoff_t);
 int truncate_xattr_node(struct inode *, struct page *);
@@ -1766,8 +1801,9 @@ void destroy_node_manager_caches(void);
  * segment.c
  */
 void register_inmem_page(struct inode *, struct page *);
-int commit_inmem_pages(struct inode *, bool);
-void f2fs_balance_fs(struct f2fs_sb_info *);
+void drop_inmem_pages(struct inode *);
+int commit_inmem_pages(struct inode *);
+void f2fs_balance_fs(struct f2fs_sb_info *, bool);
 void f2fs_balance_fs_bg(struct f2fs_sb_info *);
 int f2fs_issue_flush(struct f2fs_sb_info *);
 int create_flush_cmd_control(struct f2fs_sb_info *);
@@ -1787,16 +1823,17 @@ void write_meta_page(struct f2fs_sb_info *, struct page *);
 void write_node_page(unsigned int, struct f2fs_io_info *);
 void write_data_page(struct dnode_of_data *, struct f2fs_io_info *);
 void rewrite_data_page(struct f2fs_io_info *);
+void __f2fs_replace_block(struct f2fs_sb_info *, struct f2fs_summary *,
+					block_t, block_t, bool, bool);
 void f2fs_replace_block(struct f2fs_sb_info *, struct dnode_of_data *,
-				block_t, block_t, unsigned char, bool);
+				block_t, block_t, unsigned char, bool, bool);
 void allocate_data_block(struct f2fs_sb_info *, struct page *,
 		block_t, block_t *, struct f2fs_summary *, int);
-void f2fs_wait_on_page_writeback(struct page *, enum page_type);
+void f2fs_wait_on_page_writeback(struct page *, enum page_type, bool);
 void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *, block_t);
 void write_data_summaries(struct f2fs_sb_info *, block_t);
 void write_node_summaries(struct f2fs_sb_info *, block_t);
-int lookup_journal_in_cursum(struct f2fs_summary_block *,
-					int, unsigned int, int);
+int lookup_journal_in_cursum(struct f2fs_journal *, int, unsigned int, int);
 void flush_sit_entries(struct f2fs_sb_info *, struct cp_control *);
 int build_segment_manager(struct f2fs_sb_info *);
 void destroy_segment_manager(struct f2fs_sb_info *);
@@ -1813,9 +1850,9 @@ bool is_valid_blkaddr(struct f2fs_sb_info *, block_t, int);
 int ra_meta_pages(struct f2fs_sb_info *, block_t, int, int, bool);
 void ra_meta_pages_cond(struct f2fs_sb_info *, pgoff_t);
 long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long);
-void add_dirty_inode(struct f2fs_sb_info *, nid_t, int type);
-void remove_dirty_inode(struct f2fs_sb_info *, nid_t, int type);
-void release_dirty_inode(struct f2fs_sb_info *);
+void add_ino_entry(struct f2fs_sb_info *, nid_t, int type);
+void remove_ino_entry(struct f2fs_sb_info *, nid_t, int type);
+void release_ino_entry(struct f2fs_sb_info *);
 bool exist_written_data(struct f2fs_sb_info *, nid_t, int);
 int acquire_orphan_inode(struct f2fs_sb_info *);
 void release_orphan_inode(struct f2fs_sb_info *);
@@ -1825,9 +1862,9 @@ int recover_orphan_inodes(struct f2fs_sb_info *);
 int get_valid_checkpoint(struct f2fs_sb_info *);
 void update_dirty_page(struct inode *, struct page *);
 void add_dirty_dir_inode(struct inode *);
-void remove_dirty_dir_inode(struct inode *);
-void sync_dirty_dir_inodes(struct f2fs_sb_info *);
-void write_checkpoint(struct f2fs_sb_info *, struct cp_control *);
+void remove_dirty_inode(struct inode *);
+int sync_dirty_inodes(struct f2fs_sb_info *, enum inode_type);
+int write_checkpoint(struct f2fs_sb_info *, struct cp_control *);
 void init_ino_entry_info(struct f2fs_sb_info *);
 int __init create_checkpoint_caches(void);
 void destroy_checkpoint_caches(void);
@@ -1836,17 +1873,23 @@ void destroy_checkpoint_caches(void);
  * data.c
  */
 void f2fs_submit_merged_bio(struct f2fs_sb_info *, enum page_type, int);
+void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *, struct inode *,
+				struct page *, nid_t, enum page_type, int);
+void f2fs_flush_merged_bios(struct f2fs_sb_info *);
 int f2fs_submit_page_bio(struct f2fs_io_info *);
 void f2fs_submit_page_mbio(struct f2fs_io_info *);
 void set_data_blkaddr(struct dnode_of_data *);
+void f2fs_update_data_blkaddr(struct dnode_of_data *, block_t);
 int reserve_new_block(struct dnode_of_data *);
 int f2fs_get_block(struct dnode_of_data *, pgoff_t);
+ssize_t f2fs_preallocate_blocks(struct kiocb *, struct iov_iter *);
 int f2fs_reserve_block(struct dnode_of_data *, pgoff_t);
 struct page *get_read_data_page(struct inode *, pgoff_t, int, bool);
 struct page *find_data_page(struct inode *, pgoff_t);
 struct page *get_lock_data_page(struct inode *, pgoff_t, bool);
 struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool);
 int do_write_data_page(struct f2fs_io_info *);
+int f2fs_map_blocks(struct inode *, struct f2fs_map_blocks *, int, int);
 int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64);
 void f2fs_invalidate_page(struct page *, unsigned int, unsigned int);
 int f2fs_release_page(struct page *, gfp_t);
@@ -1856,7 +1899,7 @@ int f2fs_release_page(struct page *, gfp_t);
  */
 int start_gc_thread(struct f2fs_sb_info *);
 void stop_gc_thread(struct f2fs_sb_info *);
-block_t start_bidx_of_node(unsigned int, struct f2fs_inode_info *);
+block_t start_bidx_of_node(unsigned int, struct inode *);
 int f2fs_gc(struct f2fs_sb_info *, bool);
 void build_gc_manager(struct f2fs_sb_info *);
 
@@ -1877,8 +1920,9 @@ struct f2fs_stat_info {
 	int main_area_segs, main_area_sections, main_area_zones;
 	unsigned long long hit_largest, hit_cached, hit_rbtree;
 	unsigned long long hit_total, total_ext;
-	int ext_tree, ext_node;
-	int ndirty_node, ndirty_dent, ndirty_dirs, ndirty_meta;
+	int ext_tree, zombie_tree, ext_node;
+	int ndirty_node, ndirty_meta;
+	int ndirty_dent, ndirty_dirs, ndirty_data, ndirty_files;
 	int nats, dirty_nats, sits, dirty_sits, fnids;
 	int total_count, utilization;
 	int bg_gc, inmem_pages, wb_pages;
@@ -1888,7 +1932,7 @@ struct f2fs_stat_info {
 	int util_free, util_valid, util_invalid;
 	int rsvd_segs, overp_segs;
 	int dirty_count, node_pages, meta_pages;
-	int prefree_count, call_count, cp_count;
+	int prefree_count, call_count, cp_count, bg_cp_count;
 	int tot_segs, node_segs, data_segs, free_segs, free_secs;
 	int bg_node_segs, bg_data_segs;
 	int tot_blks, data_blks, node_blks;
@@ -1909,10 +1953,11 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
 }
 
 #define stat_inc_cp_count(si)		((si)->cp_count++)
+#define stat_inc_bg_cp_count(si)	((si)->bg_cp_count++)
 #define stat_inc_call_count(si)		((si)->call_count++)
 #define stat_inc_bggc_count(sbi)	((sbi)->bg_gc++)
-#define stat_inc_dirty_dir(sbi)		((sbi)->n_dirty_dirs++)
-#define stat_dec_dirty_dir(sbi)		((sbi)->n_dirty_dirs--)
+#define stat_inc_dirty_inode(sbi, type)	((sbi)->ndirty_inode[type]++)
+#define stat_dec_dirty_inode(sbi, type)	((sbi)->ndirty_inode[type]--)
 #define stat_inc_total_hit(sbi)		(atomic64_inc(&(sbi)->total_hit_ext))
 #define stat_inc_rbtree_node_hit(sbi)	(atomic64_inc(&(sbi)->read_hit_rbtree))
 #define stat_inc_largest_node_hit(sbi)	(atomic64_inc(&(sbi)->read_hit_largest))
@@ -1987,14 +2032,15 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
 
 int f2fs_build_stats(struct f2fs_sb_info *);
 void f2fs_destroy_stats(struct f2fs_sb_info *);
-void __init f2fs_create_root_stats(void);
+int __init f2fs_create_root_stats(void);
 void f2fs_destroy_root_stats(void);
 #else
 #define stat_inc_cp_count(si)
+#define stat_inc_bg_cp_count(si)
 #define stat_inc_call_count(si)
 #define stat_inc_bggc_count(si)
-#define stat_inc_dirty_dir(sbi)
-#define stat_dec_dirty_dir(sbi)
+#define stat_inc_dirty_inode(sbi, type)
+#define stat_dec_dirty_inode(sbi, type)
 #define stat_inc_total_hit(sb)
 #define stat_inc_rbtree_node_hit(sb)
 #define stat_inc_largest_node_hit(sbi)
@@ -2015,7 +2061,7 @@ void f2fs_destroy_root_stats(void);
 
 static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; }
 static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { }
-static inline void __init f2fs_create_root_stats(void) { }
+static inline int __init f2fs_create_root_stats(void) { return 0; }
 static inline void f2fs_destroy_root_stats(void) { }
 #endif
 
@@ -2044,7 +2090,7 @@ int f2fs_convert_inline_inode(struct inode *);
 int f2fs_write_inline_data(struct inode *, struct page *);
 bool recover_inline_data(struct inode *, struct page *);
 struct f2fs_dir_entry *find_in_inline_dir(struct inode *,
-				struct f2fs_filename *, struct page **);
+				struct fscrypt_name *, struct page **);
 struct f2fs_dir_entry *f2fs_parent_inline_dir(struct inode *, struct page **);
 int make_empty_inline_dir(struct inode *inode, struct inode *, struct page *);
 int f2fs_add_inline_entry(struct inode *, const struct qstr *, struct inode *,
@@ -2053,7 +2099,7 @@ void f2fs_delete_inline_entry(struct f2fs_dir_entry *, struct page *,
 						struct inode *, struct inode *);
 bool f2fs_empty_inline_dir(struct inode *);
 int f2fs_read_inline_dir(struct file *, struct dir_context *,
-						struct f2fs_str *);
+						struct fscrypt_str *);
 int f2fs_inline_data_fiemap(struct inode *,
 		struct fiemap_extent_info *, __u64, __u64);
 
@@ -2069,8 +2115,7 @@ void f2fs_leave_shrinker(struct f2fs_sb_info *);
  * extent_cache.c
  */
 unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *, int);
-void f2fs_drop_largest_extent(struct inode *, pgoff_t);
-void f2fs_init_extent_tree(struct inode *, struct f2fs_extent *);
+bool f2fs_init_extent_tree(struct inode *, struct f2fs_extent *);
 unsigned int f2fs_destroy_extent_node(struct inode *);
 void f2fs_destroy_extent_tree(struct inode *);
 bool f2fs_lookup_extent_cache(struct inode *, pgoff_t, struct extent_info *);
@@ -2084,13 +2129,9 @@ void destroy_extent_cache(void);
 /*
  * crypto support
  */
-static inline int f2fs_encrypted_inode(struct inode *inode)
+static inline bool f2fs_encrypted_inode(struct inode *inode)
 {
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
 	return file_is_encrypt(inode);
-#else
-	return 0;
-#endif
 }
 
 static inline void f2fs_set_encrypted_inode(struct inode *inode)
@@ -2102,26 +2143,18 @@ static inline void f2fs_set_encrypted_inode(struct inode *inode)
 
 static inline bool f2fs_bio_encrypted(struct bio *bio)
 {
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-	return unlikely(bio->bi_private != NULL);
-#else
-	return false;
-#endif
+	return bio->bi_private != NULL;
 }
 
 static inline int f2fs_sb_has_crypto(struct super_block *sb)
 {
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
 	return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_ENCRYPT);
-#else
-	return 0;
-#endif
 }
 
 static inline bool f2fs_may_encrypt(struct inode *inode)
 {
 #ifdef CONFIG_F2FS_FS_ENCRYPTION
-	mode_t mode = inode->i_mode;
+	umode_t mode = inode->i_mode;
 
 	return (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode));
 #else
@@ -2129,86 +2162,28 @@ static inline bool f2fs_may_encrypt(struct inode *inode)
 #endif
 }
 
-/* crypto_policy.c */
-int f2fs_is_child_context_consistent_with_parent(struct inode *,
-							struct inode *);
-int f2fs_inherit_context(struct inode *, struct inode *, struct page *);
-int f2fs_process_policy(const struct f2fs_encryption_policy *, struct inode *);
-int f2fs_get_policy(struct inode *, struct f2fs_encryption_policy *);
-
-/* crypt.c */
-extern struct kmem_cache *f2fs_crypt_info_cachep;
-bool f2fs_valid_contents_enc_mode(uint32_t);
-uint32_t f2fs_validate_encryption_key_size(uint32_t, uint32_t);
-struct f2fs_crypto_ctx *f2fs_get_crypto_ctx(struct inode *);
-void f2fs_release_crypto_ctx(struct f2fs_crypto_ctx *);
-struct page *f2fs_encrypt(struct inode *, struct page *);
-int f2fs_decrypt(struct f2fs_crypto_ctx *, struct page *);
-int f2fs_decrypt_one(struct inode *, struct page *);
-void f2fs_end_io_crypto_work(struct f2fs_crypto_ctx *, struct bio *);
-
-/* crypto_key.c */
-void f2fs_free_encryption_info(struct inode *, struct f2fs_crypt_info *);
-int _f2fs_get_encryption_info(struct inode *inode);
-
-/* crypto_fname.c */
-bool f2fs_valid_filenames_enc_mode(uint32_t);
-u32 f2fs_fname_crypto_round_up(u32, u32);
-int f2fs_fname_crypto_alloc_buffer(struct inode *, u32, struct f2fs_str *);
-int f2fs_fname_disk_to_usr(struct inode *, f2fs_hash_t *,
-			const struct f2fs_str *, struct f2fs_str *);
-int f2fs_fname_usr_to_disk(struct inode *, const struct qstr *,
-			struct f2fs_str *);
-
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-void f2fs_restore_and_release_control_page(struct page **);
-void f2fs_restore_control_page(struct page *);
-
-int __init f2fs_init_crypto(void);
-int f2fs_crypto_initialize(void);
-void f2fs_exit_crypto(void);
-
-int f2fs_has_encryption_key(struct inode *);
-
-static inline int f2fs_get_encryption_info(struct inode *inode)
-{
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
-
-	if (!ci ||
-		(ci->ci_keyring_key &&
-		 (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
-					       (1 << KEY_FLAG_REVOKED) |
-					       (1 << KEY_FLAG_DEAD)))))
-		return _f2fs_get_encryption_info(inode);
-	return 0;
-}
-
-void f2fs_fname_crypto_free_buffer(struct f2fs_str *);
-int f2fs_fname_setup_filename(struct inode *, const struct qstr *,
-				int lookup, struct f2fs_filename *);
-void f2fs_fname_free_filename(struct f2fs_filename *);
-#else
-static inline void f2fs_restore_and_release_control_page(struct page **p) { }
-static inline void f2fs_restore_control_page(struct page *p) { }
-
-static inline int __init f2fs_init_crypto(void) { return 0; }
-static inline void f2fs_exit_crypto(void) { }
-
-static inline int f2fs_has_encryption_key(struct inode *i) { return 0; }
-static inline int f2fs_get_encryption_info(struct inode *i) { return 0; }
-static inline void f2fs_fname_crypto_free_buffer(struct f2fs_str *p) { }
-
-static inline int f2fs_fname_setup_filename(struct inode *dir,
-					const struct qstr *iname,
-					int lookup, struct f2fs_filename *fname)
-{
-	memset(fname, 0, sizeof(struct f2fs_filename));
-	fname->usr_fname = iname;
-	fname->disk_name.name = (unsigned char *)iname->name;
-	fname->disk_name.len = iname->len;
-	return 0;
-}
-
-static inline void f2fs_fname_free_filename(struct f2fs_filename *fname) { }
+#ifndef CONFIG_F2FS_FS_ENCRYPTION
+#define fscrypt_set_d_op(i)
+#define fscrypt_get_ctx			fscrypt_notsupp_get_ctx
+#define fscrypt_release_ctx		fscrypt_notsupp_release_ctx
+#define fscrypt_encrypt_page		fscrypt_notsupp_encrypt_page
+#define fscrypt_decrypt_page		fscrypt_notsupp_decrypt_page
+#define fscrypt_decrypt_bio_pages	fscrypt_notsupp_decrypt_bio_pages
+#define fscrypt_pullback_bio_page	fscrypt_notsupp_pullback_bio_page
+#define fscrypt_restore_control_page	fscrypt_notsupp_restore_control_page
+#define fscrypt_zeroout_range		fscrypt_notsupp_zeroout_range
+#define fscrypt_process_policy		fscrypt_notsupp_process_policy
+#define fscrypt_get_policy		fscrypt_notsupp_get_policy
+#define fscrypt_has_permitted_context	fscrypt_notsupp_has_permitted_context
+#define fscrypt_inherit_context		fscrypt_notsupp_inherit_context
+#define fscrypt_get_encryption_info	fscrypt_notsupp_get_encryption_info
+#define fscrypt_put_encryption_info	fscrypt_notsupp_put_encryption_info
+#define fscrypt_setup_filename		fscrypt_notsupp_setup_filename
+#define fscrypt_free_filename		fscrypt_notsupp_free_filename
+#define fscrypt_fname_encrypted_size	fscrypt_notsupp_fname_encrypted_size
+#define fscrypt_fname_alloc_buffer	fscrypt_notsupp_fname_alloc_buffer
+#define fscrypt_fname_free_buffer	fscrypt_notsupp_fname_free_buffer
+#define fscrypt_fname_disk_to_usr	fscrypt_notsupp_fname_disk_to_usr
+#define fscrypt_fname_usr_to_disk	fscrypt_notsupp_fname_usr_to_disk
 #endif
 #endif
diff --git a/fs/f2fs/f2fs_crypto.h b/fs/f2fs/f2fs_crypto.h
deleted file mode 100644
index c2c1c2b63b25..000000000000
--- a/fs/f2fs/f2fs_crypto.h
+++ /dev/null
@@ -1,151 +0,0 @@
-/*
- * linux/fs/f2fs/f2fs_crypto.h
- *
- * Copied from linux/fs/ext4/ext4_crypto.h
- *
- * Copyright (C) 2015, Google, Inc.
- *
- * This contains encryption header content for f2fs
- *
- * Written by Michael Halcrow, 2015.
- * Modified by Jaegeuk Kim, 2015.
- */
-#ifndef _F2FS_CRYPTO_H
-#define _F2FS_CRYPTO_H
-
-#include <linux/fs.h>
-
-#define F2FS_KEY_DESCRIPTOR_SIZE	8
-
-/* Policy provided via an ioctl on the topmost directory */
-struct f2fs_encryption_policy {
-	char version;
-	char contents_encryption_mode;
-	char filenames_encryption_mode;
-	char flags;
-	char master_key_descriptor[F2FS_KEY_DESCRIPTOR_SIZE];
-} __attribute__((__packed__));
-
-#define F2FS_ENCRYPTION_CONTEXT_FORMAT_V1	1
-#define F2FS_KEY_DERIVATION_NONCE_SIZE		16
-
-#define F2FS_POLICY_FLAGS_PAD_4		0x00
-#define F2FS_POLICY_FLAGS_PAD_8		0x01
-#define F2FS_POLICY_FLAGS_PAD_16	0x02
-#define F2FS_POLICY_FLAGS_PAD_32	0x03
-#define F2FS_POLICY_FLAGS_PAD_MASK	0x03
-#define F2FS_POLICY_FLAGS_VALID		0x03
-
-/**
- * Encryption context for inode
- *
- * Protector format:
- *  1 byte: Protector format (1 = this version)
- *  1 byte: File contents encryption mode
- *  1 byte: File names encryption mode
- *  1 byte: Flags
- *  8 bytes: Master Key descriptor
- *  16 bytes: Encryption Key derivation nonce
- */
-struct f2fs_encryption_context {
-	char format;
-	char contents_encryption_mode;
-	char filenames_encryption_mode;
-	char flags;
-	char master_key_descriptor[F2FS_KEY_DESCRIPTOR_SIZE];
-	char nonce[F2FS_KEY_DERIVATION_NONCE_SIZE];
-} __attribute__((__packed__));
-
-/* Encryption parameters */
-#define F2FS_XTS_TWEAK_SIZE 16
-#define F2FS_AES_128_ECB_KEY_SIZE 16
-#define F2FS_AES_256_GCM_KEY_SIZE 32
-#define F2FS_AES_256_CBC_KEY_SIZE 32
-#define F2FS_AES_256_CTS_KEY_SIZE 32
-#define F2FS_AES_256_XTS_KEY_SIZE 64
-#define F2FS_MAX_KEY_SIZE 64
-
-#define F2FS_KEY_DESC_PREFIX "f2fs:"
-#define F2FS_KEY_DESC_PREFIX_SIZE 5
-
-struct f2fs_encryption_key {
-	__u32 mode;
-	char raw[F2FS_MAX_KEY_SIZE];
-	__u32 size;
-} __attribute__((__packed__));
-
-struct f2fs_crypt_info {
-	char		ci_data_mode;
-	char		ci_filename_mode;
-	char		ci_flags;
-	struct crypto_ablkcipher *ci_ctfm;
-	struct key	*ci_keyring_key;
-	char		ci_master_key[F2FS_KEY_DESCRIPTOR_SIZE];
-};
-
-#define F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL             0x00000001
-#define F2FS_WRITE_PATH_FL			      0x00000002
-
-struct f2fs_crypto_ctx {
-	union {
-		struct {
-			struct page *bounce_page;       /* Ciphertext page */
-			struct page *control_page;      /* Original page  */
-		} w;
-		struct {
-			struct bio *bio;
-			struct work_struct work;
-		} r;
-		struct list_head free_list;     /* Free list */
-	};
-	char flags;                      /* Flags */
-};
-
-struct f2fs_completion_result {
-	struct completion completion;
-	int res;
-};
-
-#define DECLARE_F2FS_COMPLETION_RESULT(ecr) \
-	struct f2fs_completion_result ecr = { \
-		COMPLETION_INITIALIZER((ecr).completion), 0 }
-
-static inline int f2fs_encryption_key_size(int mode)
-{
-	switch (mode) {
-	case F2FS_ENCRYPTION_MODE_AES_256_XTS:
-		return F2FS_AES_256_XTS_KEY_SIZE;
-	case F2FS_ENCRYPTION_MODE_AES_256_GCM:
-		return F2FS_AES_256_GCM_KEY_SIZE;
-	case F2FS_ENCRYPTION_MODE_AES_256_CBC:
-		return F2FS_AES_256_CBC_KEY_SIZE;
-	case F2FS_ENCRYPTION_MODE_AES_256_CTS:
-		return F2FS_AES_256_CTS_KEY_SIZE;
-	default:
-		BUG();
-	}
-	return 0;
-}
-
-#define F2FS_FNAME_NUM_SCATTER_ENTRIES	4
-#define F2FS_CRYPTO_BLOCK_SIZE		16
-#define F2FS_FNAME_CRYPTO_DIGEST_SIZE	32
-
-/**
- * For encrypted symlinks, the ciphertext length is stored at the beginning
- * of the string in little-endian format.
- */
-struct f2fs_encrypted_symlink_data {
-	__le16 len;
-	char encrypted_path[1];
-} __attribute__((__packed__));
-
-/**
- * This function is used to calculate the disk space required to
- * store a filename of length l in encrypted symlink format.
- */
-static inline u32 encrypted_symlink_data_len(u32 l)
-{
-	return (l + sizeof(struct f2fs_encrypted_symlink_data) - 1);
-}
-#endif	/* _F2FS_CRYPTO_H */
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index a197215ad52b..90d1157a09f9 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -40,8 +40,6 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
 	struct dnode_of_data dn;
 	int err;
 
-	f2fs_balance_fs(sbi);
-
 	sb_start_pagefault(inode->i_sb);
 
 	f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
@@ -57,6 +55,8 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
 	f2fs_put_dnode(&dn);
 	f2fs_unlock_op(sbi);
 
+	f2fs_balance_fs(sbi, dn.node_changed);
+
 	file_update_time(vma->vm_file);
 	lock_page(page);
 	if (unlikely(page->mapping != inode->i_mapping ||
@@ -74,11 +74,11 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
 		goto mapped;
 
 	/* page is wholly or partially inside EOF */
-	if (((loff_t)(page->index + 1) << PAGE_CACHE_SHIFT) >
+	if (((loff_t)(page->index + 1) << PAGE_SHIFT) >
 						i_size_read(inode)) {
 		unsigned offset;
-		offset = i_size_read(inode) & ~PAGE_CACHE_MASK;
-		zero_user_segment(page, offset, PAGE_CACHE_SIZE);
+		offset = i_size_read(inode) & ~PAGE_MASK;
+		zero_user_segment(page, offset, PAGE_SIZE);
 	}
 	set_page_dirty(page);
 	SetPageUptodate(page);
@@ -86,7 +86,7 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
 	trace_f2fs_vm_page_mkwrite(page, DATA);
 mapped:
 	/* fill the page */
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_wait_on_page_writeback(page, DATA, false);
 
 	/* wait for GCed encrypted page writeback */
 	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
@@ -96,6 +96,7 @@ mapped:
 	clear_cold_data(page);
 out:
 	sb_end_pagefault(inode->i_sb);
+	f2fs_update_time(sbi, REQ_TIME);
 	return block_page_mkwrite_return(err);
 }
 
@@ -201,7 +202,7 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	trace_f2fs_sync_file_enter(inode);
 
 	/* if fdatasync is triggered, let's do in-place-update */
-	if (get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
+	if (datasync || get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
 		set_inode_flag(fi, FI_NEED_IPU);
 	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
 	clear_inode_flag(fi, FI_NEED_IPU);
@@ -233,9 +234,6 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		goto out;
 	}
 go_write:
-	/* guarantee free sections for fsync */
-	f2fs_balance_fs(sbi);
-
 	/*
 	 * Both of fdatasync() and fsync() are able to be recovered from
 	 * sudden-power-off.
@@ -261,8 +259,10 @@ sync_nodes:
 	sync_node_pages(sbi, ino, &wbc);
 
 	/* if cp_error was enabled, we should avoid infinite loop */
-	if (unlikely(f2fs_cp_error(sbi)))
+	if (unlikely(f2fs_cp_error(sbi))) {
+		ret = -EIO;
 		goto out;
+	}
 
 	if (need_inode_block_update(sbi, ino)) {
 		mark_inode_dirty_sync(inode);
@@ -275,12 +275,13 @@ sync_nodes:
 		goto out;
 
 	/* once recovery info is written, don't need to tack this */
-	remove_dirty_inode(sbi, ino, APPEND_INO);
+	remove_ino_entry(sbi, ino, APPEND_INO);
 	clear_inode_flag(fi, FI_APPEND_WRITE);
 flush_out:
-	remove_dirty_inode(sbi, ino, UPDATE_INO);
+	remove_ino_entry(sbi, ino, UPDATE_INO);
 	clear_inode_flag(fi, FI_UPDATE_WRITE);
 	ret = f2fs_issue_flush(sbi);
+	f2fs_update_time(sbi, REQ_TIME);
 out:
 	trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
 	f2fs_trace_ios(NULL, 1);
@@ -300,7 +301,7 @@ static pgoff_t __get_first_dirty_index(struct address_space *mapping,
 	pagevec_init(&pvec, 0);
 	nr_pages = pagevec_lookup_tag(&pvec, mapping, &pgofs,
 					PAGECACHE_TAG_DIRTY, 1);
-	pgofs = nr_pages ? pvec.pages[0]->index : LONG_MAX;
+	pgofs = nr_pages ? pvec.pages[0]->index : ULONG_MAX;
 	pagevec_release(&pvec);
 	return pgofs;
 }
@@ -332,7 +333,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
 	loff_t isize;
 	int err = 0;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	isize = i_size_read(inode);
 	if (offset >= isize)
@@ -345,11 +346,11 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
 		goto found;
 	}
 
-	pgofs = (pgoff_t)(offset >> PAGE_CACHE_SHIFT);
+	pgofs = (pgoff_t)(offset >> PAGE_SHIFT);
 
 	dirty = __get_first_dirty_index(inode->i_mapping, pgofs, whence);
 
-	for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_CACHE_SHIFT) {
+	for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_SHIFT) {
 		set_new_dnode(&dn, inode, NULL, NULL, 0);
 		err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE_RA);
 		if (err && err != -ENOENT) {
@@ -357,20 +358,19 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
 		} else if (err == -ENOENT) {
 			/* direct node does not exists */
 			if (whence == SEEK_DATA) {
-				pgofs = PGOFS_OF_NEXT_DNODE(pgofs,
-							F2FS_I(inode));
+				pgofs = get_next_page_offset(&dn, pgofs);
 				continue;
 			} else {
 				goto found;
 			}
 		}
 
-		end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+		end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
 
 		/* find data/hole in dnode block */
 		for (; dn.ofs_in_node < end_offset;
 				dn.ofs_in_node++, pgofs++,
-				data_ofs = (loff_t)pgofs << PAGE_CACHE_SHIFT) {
+				data_ofs = (loff_t)pgofs << PAGE_SHIFT) {
 			block_t blkaddr;
 			blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
 
@@ -387,10 +387,10 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
 found:
 	if (whence == SEEK_HOLE && data_ofs > isize)
 		data_ofs = isize;
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return vfs_setpos(file, data_ofs, maxbytes);
 fail:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return -ENXIO;
 }
 
@@ -418,19 +418,20 @@ static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence)
 static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *inode = file_inode(file);
+	int err;
 
 	if (f2fs_encrypted_inode(inode)) {
-		int err = f2fs_get_encryption_info(inode);
+		err = fscrypt_get_encryption_info(inode);
 		if (err)
 			return 0;
+		if (!f2fs_encrypted_inode(inode))
+			return -ENOKEY;
 	}
 
 	/* we don't need to use inline_data strictly */
-	if (f2fs_has_inline_data(inode)) {
-		int err = f2fs_convert_inline_inode(inode);
-		if (err)
-			return err;
-	}
+	err = f2fs_convert_inline_inode(inode);
+	if (err)
+		return err;
 
 	file_accessed(file);
 	vma->vm_ops = &f2fs_file_vm_ops;
@@ -440,12 +441,22 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
 static int f2fs_file_open(struct inode *inode, struct file *filp)
 {
 	int ret = generic_file_open(inode, filp);
+	struct dentry *dir;
 
 	if (!ret && f2fs_encrypted_inode(inode)) {
-		ret = f2fs_get_encryption_info(inode);
+		ret = fscrypt_get_encryption_info(inode);
 		if (ret)
-			ret = -EACCES;
+			return -EACCES;
+		if (!fscrypt_has_encryption_key(inode))
+			return -ENOKEY;
 	}
+	dir = dget_parent(file_dentry(filp));
+	if (f2fs_encrypted_inode(d_inode(dir)) &&
+			!fscrypt_has_permitted_context(d_inode(dir), inode)) {
+		dput(dir);
+		return -EPERM;
+	}
+	dput(dir);
 	return ret;
 }
 
@@ -480,14 +491,14 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 		 * we will invalidate all blkaddr in the whole range.
 		 */
 		fofs = start_bidx_of_node(ofs_of_node(dn->node_page),
-						F2FS_I(dn->inode)) + ofs;
+							dn->inode) + ofs;
 		f2fs_update_extent_cache_range(dn, fofs, 0, len);
 		dec_valid_block_count(sbi, dn->inode, nr_free);
-		set_page_dirty(dn->node_page);
 		sync_inode_page(dn);
 	}
 	dn->ofs_in_node = ofs;
 
+	f2fs_update_time(sbi, REQ_TIME);
 	trace_f2fs_truncate_data_blocks_range(dn->inode, dn->nid,
 					 dn->ofs_in_node, nr_free);
 	return nr_free;
@@ -501,8 +512,8 @@ void truncate_data_blocks(struct dnode_of_data *dn)
 static int truncate_partial_data_page(struct inode *inode, u64 from,
 								bool cache_only)
 {
-	unsigned offset = from & (PAGE_CACHE_SIZE - 1);
-	pgoff_t index = from >> PAGE_CACHE_SHIFT;
+	unsigned offset = from & (PAGE_SIZE - 1);
+	pgoff_t index = from >> PAGE_SHIFT;
 	struct address_space *mapping = inode->i_mapping;
 	struct page *page;
 
@@ -521,9 +532,10 @@ static int truncate_partial_data_page(struct inode *inode, u64 from,
 	if (IS_ERR(page))
 		return 0;
 truncate_out:
-	f2fs_wait_on_page_writeback(page, DATA);
-	zero_user(page, offset, PAGE_CACHE_SIZE - offset);
-	if (!cache_only || !f2fs_encrypted_inode(inode) || !S_ISREG(inode->i_mode))
+	f2fs_wait_on_page_writeback(page, DATA, true);
+	zero_user(page, offset, PAGE_SIZE - offset);
+	if (!cache_only || !f2fs_encrypted_inode(inode) ||
+					!S_ISREG(inode->i_mode))
 		set_page_dirty(page);
 	f2fs_put_page(page, 1);
 	return 0;
@@ -568,7 +580,7 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
 		goto out;
 	}
 
-	count = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+	count = ADDRS_PER_PAGE(dn.node_page, inode);
 
 	count -= dn.ofs_in_node;
 	f2fs_bug_on(sbi, count < 0);
@@ -604,7 +616,7 @@ int f2fs_truncate(struct inode *inode, bool lock)
 	trace_f2fs_truncate(inode);
 
 	/* we should check inline_data size */
-	if (f2fs_has_inline_data(inode) && !f2fs_may_inline_data(inode)) {
+	if (!f2fs_may_inline_data(inode)) {
 		err = f2fs_convert_inline_inode(inode);
 		if (err)
 			return err;
@@ -671,7 +683,7 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 
 	if (attr->ia_valid & ATTR_SIZE) {
 		if (f2fs_encrypted_inode(inode) &&
-				f2fs_get_encryption_info(inode))
+				fscrypt_get_encryption_info(inode))
 			return -EACCES;
 
 		if (attr->ia_size <= i_size_read(inode)) {
@@ -679,13 +691,20 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 			err = f2fs_truncate(inode, true);
 			if (err)
 				return err;
-			f2fs_balance_fs(F2FS_I_SB(inode));
+			f2fs_balance_fs(F2FS_I_SB(inode), true);
 		} else {
 			/*
 			 * do not trim all blocks after i_size if target size is
 			 * larger than i_size.
 			 */
 			truncate_setsize(inode, attr->ia_size);
+
+			/* should convert inline inode here */
+			if (!f2fs_may_inline_data(inode)) {
+				err = f2fs_convert_inline_inode(inode);
+				if (err)
+					return err;
+			}
 			inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		}
 	}
@@ -727,7 +746,7 @@ static int fill_zero(struct inode *inode, pgoff_t index,
 	if (!len)
 		return 0;
 
-	f2fs_balance_fs(sbi);
+	f2fs_balance_fs(sbi, true);
 
 	f2fs_lock_op(sbi);
 	page = get_new_data_page(inode, NULL, index, false);
@@ -736,7 +755,7 @@ static int fill_zero(struct inode *inode, pgoff_t index,
 	if (IS_ERR(page))
 		return PTR_ERR(page);
 
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_wait_on_page_writeback(page, DATA, true);
 	zero_user(page, start, len);
 	set_page_dirty(page);
 	f2fs_put_page(page, 1);
@@ -761,7 +780,7 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
 			return err;
 		}
 
-		end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+		end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
 		count = min(end_offset - dn.ofs_in_node, pg_end - pg_start);
 
 		f2fs_bug_on(F2FS_I_SB(inode), count == 0 || count > end_offset);
@@ -778,19 +797,17 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
 {
 	pgoff_t pg_start, pg_end;
 	loff_t off_start, off_end;
-	int ret = 0;
+	int ret;
 
-	if (f2fs_has_inline_data(inode)) {
-		ret = f2fs_convert_inline_inode(inode);
-		if (ret)
-			return ret;
-	}
+	ret = f2fs_convert_inline_inode(inode);
+	if (ret)
+		return ret;
 
-	pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT;
-	pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT;
+	pg_start = ((unsigned long long) offset) >> PAGE_SHIFT;
+	pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT;
 
-	off_start = offset & (PAGE_CACHE_SIZE - 1);
-	off_end = (offset + len) & (PAGE_CACHE_SIZE - 1);
+	off_start = offset & (PAGE_SIZE - 1);
+	off_end = (offset + len) & (PAGE_SIZE - 1);
 
 	if (pg_start == pg_end) {
 		ret = fill_zero(inode, pg_start, off_start,
@@ -800,7 +817,7 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	} else {
 		if (off_start) {
 			ret = fill_zero(inode, pg_start++, off_start,
-						PAGE_CACHE_SIZE - off_start);
+						PAGE_SIZE - off_start);
 			if (ret)
 				return ret;
 		}
@@ -815,10 +832,10 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
 			loff_t blk_start, blk_end;
 			struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 
-			f2fs_balance_fs(sbi);
+			f2fs_balance_fs(sbi, true);
 
-			blk_start = (loff_t)pg_start << PAGE_CACHE_SHIFT;
-			blk_end = (loff_t)pg_end << PAGE_CACHE_SHIFT;
+			blk_start = (loff_t)pg_start << PAGE_SHIFT;
+			blk_end = (loff_t)pg_end << PAGE_SHIFT;
 			truncate_inode_pages_range(mapping, blk_start,
 					blk_end - 1);
 
@@ -849,10 +866,8 @@ static int __exchange_data_block(struct inode *inode, pgoff_t src,
 	} else {
 		new_addr = dn.data_blkaddr;
 		if (!is_checkpointed_data(sbi, new_addr)) {
-			dn.data_blkaddr = NULL_ADDR;
 			/* do not invalidate this block address */
-			set_data_blkaddr(&dn);
-			f2fs_update_extent_cache(&dn);
+			f2fs_update_data_blkaddr(&dn, NULL_ADDR);
 			do_replace = true;
 		}
 		f2fs_put_dnode(&dn);
@@ -879,7 +894,7 @@ static int __exchange_data_block(struct inode *inode, pgoff_t src,
 
 		get_node_info(sbi, dn.nid, &ni);
 		f2fs_replace_block(sbi, &dn, dn.data_blkaddr, new_addr,
-				ni.version, true);
+				ni.version, true, false);
 		f2fs_put_dnode(&dn);
 	} else {
 		struct page *psrc, *pdst;
@@ -887,7 +902,7 @@ static int __exchange_data_block(struct inode *inode, pgoff_t src,
 		psrc = get_lock_data_page(inode, src, true);
 		if (IS_ERR(psrc))
 			return PTR_ERR(psrc);
-		pdst = get_new_data_page(inode, NULL, dst, false);
+		pdst = get_new_data_page(inode, NULL, dst, true);
 		if (IS_ERR(pdst)) {
 			f2fs_put_page(psrc, 1);
 			return PTR_ERR(pdst);
@@ -903,9 +918,7 @@ static int __exchange_data_block(struct inode *inode, pgoff_t src,
 
 err_out:
 	if (!get_dnode_of_data(&dn, src, LOOKUP_NODE)) {
-		dn.data_blkaddr = new_addr;
-		set_data_blkaddr(&dn);
-		f2fs_update_extent_cache(&dn);
+		f2fs_update_data_blkaddr(&dn, new_addr);
 		f2fs_put_dnode(&dn);
 	}
 	return ret;
@@ -918,7 +931,7 @@ static int f2fs_do_collapse(struct inode *inode, pgoff_t start, pgoff_t end)
 	int ret = 0;
 
 	for (; end < nrpages; start++, end++) {
-		f2fs_balance_fs(sbi);
+		f2fs_balance_fs(sbi, true);
 		f2fs_lock_op(sbi);
 		ret = __exchange_data_block(inode, end, start, true);
 		f2fs_unlock_op(sbi);
@@ -941,16 +954,12 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	if (offset & (F2FS_BLKSIZE - 1) || len & (F2FS_BLKSIZE - 1))
 		return -EINVAL;
 
-	f2fs_balance_fs(F2FS_I_SB(inode));
-
-	if (f2fs_has_inline_data(inode)) {
-		ret = f2fs_convert_inline_inode(inode);
-		if (ret)
-			return ret;
-	}
+	ret = f2fs_convert_inline_inode(inode);
+	if (ret)
+		return ret;
 
-	pg_start = offset >> PAGE_CACHE_SHIFT;
-	pg_end = (offset + len) >> PAGE_CACHE_SHIFT;
+	pg_start = offset >> PAGE_SHIFT;
+	pg_end = (offset + len) >> PAGE_SHIFT;
 
 	/* write out all dirty pages from offset */
 	ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
@@ -991,13 +1000,9 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 	if (ret)
 		return ret;
 
-	f2fs_balance_fs(sbi);
-
-	if (f2fs_has_inline_data(inode)) {
-		ret = f2fs_convert_inline_inode(inode);
-		if (ret)
-			return ret;
-	}
+	ret = f2fs_convert_inline_inode(inode);
+	if (ret)
+		return ret;
 
 	ret = filemap_write_and_wait_range(mapping, offset, offset + len - 1);
 	if (ret)
@@ -1005,11 +1010,11 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 
 	truncate_pagecache_range(inode, offset, offset + len - 1);
 
-	pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT;
-	pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT;
+	pg_start = ((unsigned long long) offset) >> PAGE_SHIFT;
+	pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT;
 
-	off_start = offset & (PAGE_CACHE_SIZE - 1);
-	off_end = (offset + len) & (PAGE_CACHE_SIZE - 1);
+	off_start = offset & (PAGE_SIZE - 1);
+	off_end = (offset + len) & (PAGE_SIZE - 1);
 
 	if (pg_start == pg_end) {
 		ret = fill_zero(inode, pg_start, off_start,
@@ -1023,12 +1028,12 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 	} else {
 		if (off_start) {
 			ret = fill_zero(inode, pg_start++, off_start,
-						PAGE_CACHE_SIZE - off_start);
+						PAGE_SIZE - off_start);
 			if (ret)
 				return ret;
 
 			new_size = max_t(loff_t, new_size,
-					(loff_t)pg_start << PAGE_CACHE_SHIFT);
+					(loff_t)pg_start << PAGE_SHIFT);
 		}
 
 		for (index = pg_start; index < pg_end; index++) {
@@ -1053,18 +1058,13 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 
 			if (dn.data_blkaddr != NEW_ADDR) {
 				invalidate_blocks(sbi, dn.data_blkaddr);
-
-				dn.data_blkaddr = NEW_ADDR;
-				set_data_blkaddr(&dn);
-
-				dn.data_blkaddr = NULL_ADDR;
-				f2fs_update_extent_cache(&dn);
+				f2fs_update_data_blkaddr(&dn, NEW_ADDR);
 			}
 			f2fs_put_dnode(&dn);
 			f2fs_unlock_op(sbi);
 
 			new_size = max_t(loff_t, new_size,
-				(loff_t)(index + 1) << PAGE_CACHE_SHIFT);
+				(loff_t)(index + 1) << PAGE_SHIFT);
 		}
 
 		if (off_end) {
@@ -1104,13 +1104,11 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	if (offset & (F2FS_BLKSIZE - 1) || len & (F2FS_BLKSIZE - 1))
 		return -EINVAL;
 
-	f2fs_balance_fs(sbi);
+	ret = f2fs_convert_inline_inode(inode);
+	if (ret)
+		return ret;
 
-	if (f2fs_has_inline_data(inode)) {
-		ret = f2fs_convert_inline_inode(inode);
-		if (ret)
-			return ret;
-	}
+	f2fs_balance_fs(sbi, true);
 
 	ret = truncate_blocks(inode, i_size_read(inode), true);
 	if (ret)
@@ -1123,8 +1121,8 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 
 	truncate_pagecache(inode, offset);
 
-	pg_start = offset >> PAGE_CACHE_SHIFT;
-	pg_end = (offset + len) >> PAGE_CACHE_SHIFT;
+	pg_start = offset >> PAGE_SHIFT;
+	pg_end = (offset + len) >> PAGE_SHIFT;
 	delta = pg_end - pg_start;
 	nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE;
 
@@ -1154,23 +1152,21 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
 	loff_t off_start, off_end;
 	int ret = 0;
 
-	f2fs_balance_fs(sbi);
-
 	ret = inode_newsize_ok(inode, (len + offset));
 	if (ret)
 		return ret;
 
-	if (f2fs_has_inline_data(inode)) {
-		ret = f2fs_convert_inline_inode(inode);
-		if (ret)
-			return ret;
-	}
+	ret = f2fs_convert_inline_inode(inode);
+	if (ret)
+		return ret;
 
-	pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT;
-	pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT;
+	f2fs_balance_fs(sbi, true);
 
-	off_start = offset & (PAGE_CACHE_SIZE - 1);
-	off_end = (offset + len) & (PAGE_CACHE_SIZE - 1);
+	pg_start = ((unsigned long long) offset) >> PAGE_SHIFT;
+	pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT;
+
+	off_start = offset & (PAGE_SIZE - 1);
+	off_end = (offset + len) & (PAGE_SIZE - 1);
 
 	f2fs_lock_op(sbi);
 
@@ -1188,12 +1184,12 @@ noalloc:
 		if (pg_start == pg_end)
 			new_size = offset + len;
 		else if (index == pg_start && off_start)
-			new_size = (loff_t)(index + 1) << PAGE_CACHE_SHIFT;
+			new_size = (loff_t)(index + 1) << PAGE_SHIFT;
 		else if (index == pg_end)
-			new_size = ((loff_t)index << PAGE_CACHE_SHIFT) +
+			new_size = ((loff_t)index << PAGE_SHIFT) +
 								off_end;
 		else
-			new_size += PAGE_CACHE_SIZE;
+			new_size += PAGE_SIZE;
 	}
 
 	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
@@ -1226,7 +1222,7 @@ static long f2fs_fallocate(struct file *file, int mode,
 			FALLOC_FL_INSERT_RANGE))
 		return -EOPNOTSUPP;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	if (mode & FALLOC_FL_PUNCH_HOLE) {
 		if (offset >= inode->i_size)
@@ -1246,10 +1242,11 @@ static long f2fs_fallocate(struct file *file, int mode,
 	if (!ret) {
 		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		mark_inode_dirty(inode);
+		f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 	}
 
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	trace_f2fs_fallocate(inode, mode, offset, len, ret);
 	return ret;
@@ -1259,7 +1256,7 @@ static int f2fs_release_file(struct inode *inode, struct file *filp)
 {
 	/* some remained atomic pages should discarded */
 	if (f2fs_is_atomic_file(inode))
-		commit_inmem_pages(inode, true);
+		drop_inmem_pages(inode);
 	if (f2fs_is_volatile_file(inode)) {
 		set_inode_flag(F2FS_I(inode), FI_DROP_CACHE);
 		filemap_fdatawrite(inode->i_mapping);
@@ -1313,13 +1310,13 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
 
 	flags = f2fs_mask_flags(inode->i_mode, flags);
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	oldflags = fi->i_flags;
 
 	if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) {
 		if (!capable(CAP_LINUX_IMMUTABLE)) {
-			mutex_unlock(&inode->i_mutex);
+			inode_unlock(inode);
 			ret = -EPERM;
 			goto out;
 		}
@@ -1328,7 +1325,7 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
 	flags = flags & FS_FL_USER_MODIFIABLE;
 	flags |= oldflags & ~FS_FL_USER_MODIFIABLE;
 	fi->i_flags = flags;
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	f2fs_set_inode_flags(inode);
 	inode->i_ctime = CURRENT_TIME;
@@ -1353,8 +1350,6 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
 	if (!inode_owner_or_capable(inode))
 		return -EACCES;
 
-	f2fs_balance_fs(F2FS_I_SB(inode));
-
 	if (f2fs_is_atomic_file(inode))
 		return 0;
 
@@ -1363,6 +1358,8 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
 		return ret;
 
 	set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
+
 	return 0;
 }
 
@@ -1383,9 +1380,11 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
 
 	if (f2fs_is_atomic_file(inode)) {
 		clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
-		ret = commit_inmem_pages(inode, false);
-		if (ret)
+		ret = commit_inmem_pages(inode);
+		if (ret) {
+			set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
 			goto err_out;
+		}
 	}
 
 	ret = f2fs_sync_file(filp, 0, LLONG_MAX, 0);
@@ -1410,6 +1409,7 @@ static int f2fs_ioc_start_volatile_write(struct file *filp)
 		return ret;
 
 	set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
+	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 	return 0;
 }
 
@@ -1441,13 +1441,17 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp)
 	if (ret)
 		return ret;
 
-	f2fs_balance_fs(F2FS_I_SB(inode));
-
-	clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
-	clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
-	commit_inmem_pages(inode, true);
+	if (f2fs_is_atomic_file(inode)) {
+		clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+		drop_inmem_pages(inode);
+	}
+	if (f2fs_is_volatile_file(inode)) {
+		clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
+		ret = f2fs_sync_file(filp, 0, LLONG_MAX, 0);
+	}
 
 	mnt_drop_write_file(filp);
+	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 	return ret;
 }
 
@@ -1487,6 +1491,7 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
 	default:
 		return -EINVAL;
 	}
+	f2fs_update_time(sbi, REQ_TIME);
 	return 0;
 }
 
@@ -1517,6 +1522,7 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
 	if (copy_to_user((struct fstrim_range __user *)arg, &range,
 				sizeof(range)))
 		return -EFAULT;
+	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 	return 0;
 }
 
@@ -1532,38 +1538,30 @@ static bool uuid_is_nonzero(__u8 u[16])
 
 static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg)
 {
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-	struct f2fs_encryption_policy policy;
+	struct fscrypt_policy policy;
 	struct inode *inode = file_inode(filp);
 
-	if (copy_from_user(&policy, (struct f2fs_encryption_policy __user *)arg,
-				sizeof(policy)))
+	if (copy_from_user(&policy, (struct fscrypt_policy __user *)arg,
+							sizeof(policy)))
 		return -EFAULT;
 
-	return f2fs_process_policy(&policy, inode);
-#else
-	return -EOPNOTSUPP;
-#endif
+	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
+	return fscrypt_process_policy(inode, &policy);
 }
 
 static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg)
 {
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-	struct f2fs_encryption_policy policy;
+	struct fscrypt_policy policy;
 	struct inode *inode = file_inode(filp);
 	int err;
 
-	err = f2fs_get_policy(inode, &policy);
+	err = fscrypt_get_policy(inode, &policy);
 	if (err)
 		return err;
 
-	if (copy_to_user((struct f2fs_encryption_policy __user *)arg, &policy,
-							sizeof(policy)))
+	if (copy_to_user((struct fscrypt_policy __user *)arg, &policy, sizeof(policy)))
 		return -EFAULT;
 	return 0;
-#else
-	return -EOPNOTSUPP;
-#endif
 }
 
 static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg)
@@ -1586,13 +1584,13 @@ static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg)
 	generate_random_uuid(sbi->raw_super->encrypt_pw_salt);
 
 	err = f2fs_commit_super(sbi, false);
-
-	mnt_drop_write_file(filp);
 	if (err) {
 		/* undo new data */
 		memset(sbi->raw_super->encrypt_pw_salt, 0, 16);
+		mnt_drop_write_file(filp);
 		return err;
 	}
+	mnt_drop_write_file(filp);
 got_it:
 	if (copy_to_user((__u8 __user *)arg, sbi->raw_super->encrypt_pw_salt,
 									16))
@@ -1629,7 +1627,6 @@ static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct cp_control cpc;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -1637,13 +1634,196 @@ static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg)
 	if (f2fs_readonly(sbi->sb))
 		return -EROFS;
 
-	cpc.reason = __get_cp_reason(sbi);
+	return f2fs_sync_fs(sbi->sb, 1);
+}
 
-	mutex_lock(&sbi->gc_mutex);
-	write_checkpoint(sbi, &cpc);
-	mutex_unlock(&sbi->gc_mutex);
+static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
+					struct file *filp,
+					struct f2fs_defragment *range)
+{
+	struct inode *inode = file_inode(filp);
+	struct f2fs_map_blocks map = { .m_next_pgofs = NULL };
+	struct extent_info ei;
+	pgoff_t pg_start, pg_end;
+	unsigned int blk_per_seg = sbi->blocks_per_seg;
+	unsigned int total = 0, sec_num;
+	unsigned int pages_per_sec = sbi->segs_per_sec * blk_per_seg;
+	block_t blk_end = 0;
+	bool fragmented = false;
+	int err;
 
-	return 0;
+	/* if in-place-update policy is enabled, don't waste time here */
+	if (need_inplace_update(inode))
+		return -EINVAL;
+
+	pg_start = range->start >> PAGE_SHIFT;
+	pg_end = (range->start + range->len) >> PAGE_SHIFT;
+
+	f2fs_balance_fs(sbi, true);
+
+	inode_lock(inode);
+
+	/* writeback all dirty pages in the range */
+	err = filemap_write_and_wait_range(inode->i_mapping, range->start,
+						range->start + range->len - 1);
+	if (err)
+		goto out;
+
+	/*
+	 * lookup mapping info in extent cache, skip defragmenting if physical
+	 * block addresses are continuous.
+	 */
+	if (f2fs_lookup_extent_cache(inode, pg_start, &ei)) {
+		if (ei.fofs + ei.len >= pg_end)
+			goto out;
+	}
+
+	map.m_lblk = pg_start;
+
+	/*
+	 * lookup mapping info in dnode page cache, skip defragmenting if all
+	 * physical block addresses are continuous even if there are hole(s)
+	 * in logical blocks.
+	 */
+	while (map.m_lblk < pg_end) {
+		map.m_len = pg_end - map.m_lblk;
+		err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_READ);
+		if (err)
+			goto out;
+
+		if (!(map.m_flags & F2FS_MAP_FLAGS)) {
+			map.m_lblk++;
+			continue;
+		}
+
+		if (blk_end && blk_end != map.m_pblk) {
+			fragmented = true;
+			break;
+		}
+		blk_end = map.m_pblk + map.m_len;
+
+		map.m_lblk += map.m_len;
+	}
+
+	if (!fragmented)
+		goto out;
+
+	map.m_lblk = pg_start;
+	map.m_len = pg_end - pg_start;
+
+	sec_num = (map.m_len + pages_per_sec - 1) / pages_per_sec;
+
+	/*
+	 * make sure there are enough free section for LFS allocation, this can
+	 * avoid defragment running in SSR mode when free section are allocated
+	 * intensively
+	 */
+	if (has_not_enough_free_secs(sbi, sec_num)) {
+		err = -EAGAIN;
+		goto out;
+	}
+
+	while (map.m_lblk < pg_end) {
+		pgoff_t idx;
+		int cnt = 0;
+
+do_map:
+		map.m_len = pg_end - map.m_lblk;
+		err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_READ);
+		if (err)
+			goto clear_out;
+
+		if (!(map.m_flags & F2FS_MAP_FLAGS)) {
+			map.m_lblk++;
+			continue;
+		}
+
+		set_inode_flag(F2FS_I(inode), FI_DO_DEFRAG);
+
+		idx = map.m_lblk;
+		while (idx < map.m_lblk + map.m_len && cnt < blk_per_seg) {
+			struct page *page;
+
+			page = get_lock_data_page(inode, idx, true);
+			if (IS_ERR(page)) {
+				err = PTR_ERR(page);
+				goto clear_out;
+			}
+
+			set_page_dirty(page);
+			f2fs_put_page(page, 1);
+
+			idx++;
+			cnt++;
+			total++;
+		}
+
+		map.m_lblk = idx;
+
+		if (idx < pg_end && cnt < blk_per_seg)
+			goto do_map;
+
+		clear_inode_flag(F2FS_I(inode), FI_DO_DEFRAG);
+
+		err = filemap_fdatawrite(inode->i_mapping);
+		if (err)
+			goto out;
+	}
+clear_out:
+	clear_inode_flag(F2FS_I(inode), FI_DO_DEFRAG);
+out:
+	inode_unlock(inode);
+	if (!err)
+		range->len = (u64)total << PAGE_SHIFT;
+	return err;
+}
+
+static int f2fs_ioc_defragment(struct file *filp, unsigned long arg)
+{
+	struct inode *inode = file_inode(filp);
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct f2fs_defragment range;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (!S_ISREG(inode->i_mode))
+		return -EINVAL;
+
+	err = mnt_want_write_file(filp);
+	if (err)
+		return err;
+
+	if (f2fs_readonly(sbi->sb)) {
+		err = -EROFS;
+		goto out;
+	}
+
+	if (copy_from_user(&range, (struct f2fs_defragment __user *)arg,
+							sizeof(range))) {
+		err = -EFAULT;
+		goto out;
+	}
+
+	/* verify alignment of offset & size */
+	if (range.start & (F2FS_BLKSIZE - 1) ||
+		range.len & (F2FS_BLKSIZE - 1)) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	err = f2fs_defragment_range(sbi, filp, &range);
+	f2fs_update_time(sbi, REQ_TIME);
+	if (err < 0)
+		goto out;
+
+	if (copy_to_user((struct f2fs_defragment __user *)arg, &range,
+							sizeof(range)))
+		err = -EFAULT;
+out:
+	mnt_drop_write_file(filp);
+	return err;
 }
 
 long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
@@ -1679,6 +1859,8 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		return f2fs_ioc_gc(filp, arg);
 	case F2FS_IOC_WRITE_CHECKPOINT:
 		return f2fs_ioc_write_checkpoint(filp, arg);
+	case F2FS_IOC_DEFRAGMENT:
+		return f2fs_ioc_defragment(filp, arg);
 	default:
 		return -ENOTTY;
 	}
@@ -1686,14 +1868,32 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 
 static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
-	struct inode *inode = file_inode(iocb->ki_filp);
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+	ssize_t ret;
 
 	if (f2fs_encrypted_inode(inode) &&
-				!f2fs_has_encryption_key(inode) &&
-				f2fs_get_encryption_info(inode))
+				!fscrypt_has_encryption_key(inode) &&
+				fscrypt_get_encryption_info(inode))
 		return -EACCES;
 
-	return generic_file_write_iter(iocb, from);
+	inode_lock(inode);
+	ret = generic_write_checks(iocb, from);
+	if (ret > 0) {
+		ret = f2fs_preallocate_blocks(iocb, from);
+		if (!ret)
+			ret = __generic_file_write_iter(iocb, from);
+	}
+	inode_unlock(inode);
+
+	if (ret > 0) {
+		ssize_t err;
+
+		err = generic_write_sync(file, iocb->ki_pos - ret, ret);
+		if (err < 0)
+			ret = err;
+	}
+	return ret;
 }
 
 #ifdef CONFIG_COMPAT
@@ -1706,6 +1906,22 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case F2FS_IOC32_SETFLAGS:
 		cmd = F2FS_IOC_SETFLAGS;
 		break;
+	case F2FS_IOC32_GETVERSION:
+		cmd = F2FS_IOC_GETVERSION;
+		break;
+	case F2FS_IOC_START_ATOMIC_WRITE:
+	case F2FS_IOC_COMMIT_ATOMIC_WRITE:
+	case F2FS_IOC_START_VOLATILE_WRITE:
+	case F2FS_IOC_RELEASE_VOLATILE_WRITE:
+	case F2FS_IOC_ABORT_VOLATILE_WRITE:
+	case F2FS_IOC_SHUTDOWN:
+	case F2FS_IOC_SET_ENCRYPTION_POLICY:
+	case F2FS_IOC_GET_ENCRYPTION_PWSALT:
+	case F2FS_IOC_GET_ENCRYPTION_POLICY:
+	case F2FS_IOC_GARBAGE_COLLECT:
+	case F2FS_IOC_WRITE_CHECKPOINT:
+	case F2FS_IOC_DEFRAGMENT:
+		break;
 	default:
 		return -ENOIOCTLCMD;
 	}
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index fedbf67a0842..b0051a97824c 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -16,7 +16,6 @@
 #include <linux/kthread.h>
 #include <linux/delay.h>
 #include <linux/freezer.h>
-#include <linux/blkdev.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -173,9 +172,9 @@ static unsigned int get_max_cost(struct f2fs_sb_info *sbi,
 {
 	/* SSR allocates in a segment unit */
 	if (p->alloc_mode == SSR)
-		return 1 << sbi->log_blocks_per_seg;
+		return sbi->blocks_per_seg;
 	if (p->gc_mode == GC_GREEDY)
-		return (1 << sbi->log_blocks_per_seg) * p->ofs_unit;
+		return sbi->blocks_per_seg * p->ofs_unit;
 	else if (p->gc_mode == GC_CB)
 		return UINT_MAX;
 	else /* No other gc_mode */
@@ -246,6 +245,18 @@ static inline unsigned int get_gc_cost(struct f2fs_sb_info *sbi,
 		return get_cb_cost(sbi, segno);
 }
 
+static unsigned int count_bits(const unsigned long *addr,
+				unsigned int offset, unsigned int len)
+{
+	unsigned int end = offset + len, sum = 0;
+
+	while (offset < end) {
+		if (test_bit(offset++, addr))
+			++sum;
+	}
+	return sum;
+}
+
 /*
  * This function is called from two paths.
  * One is garbage collection and the other is SSR segment selection.
@@ -259,9 +270,9 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 {
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	struct victim_sel_policy p;
-	unsigned int secno, max_cost;
+	unsigned int secno, max_cost, last_victim;
 	unsigned int last_segment = MAIN_SEGS(sbi);
-	int nsearched = 0;
+	unsigned int nsearched = 0;
 
 	mutex_lock(&dirty_i->seglist_lock);
 
@@ -274,6 +285,7 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 	if (p.max_search == 0)
 		goto out;
 
+	last_victim = sbi->last_victim[p.gc_mode];
 	if (p.alloc_mode == LFS && gc_type == FG_GC) {
 		p.min_segno = check_bg_victims(sbi);
 		if (p.min_segno != NULL_SEGNO)
@@ -296,27 +308,35 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 		}
 
 		p.offset = segno + p.ofs_unit;
-		if (p.ofs_unit > 1)
+		if (p.ofs_unit > 1) {
 			p.offset -= segno % p.ofs_unit;
+			nsearched += count_bits(p.dirty_segmap,
+						p.offset - p.ofs_unit,
+						p.ofs_unit);
+		} else {
+			nsearched++;
+		}
+
 
 		secno = GET_SECNO(sbi, segno);
 
 		if (sec_usage_check(sbi, secno))
-			continue;
+			goto next;
 		if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap))
-			continue;
+			goto next;
 
 		cost = get_gc_cost(sbi, segno, &p);
 
 		if (p.min_cost > cost) {
 			p.min_segno = segno;
 			p.min_cost = cost;
-		} else if (unlikely(cost == max_cost)) {
-			continue;
 		}
-
-		if (nsearched++ >= p.max_search) {
-			sbi->last_victim[p.gc_mode] = segno;
+next:
+		if (nsearched >= p.max_search) {
+			if (!sbi->last_victim[p.gc_mode] && segno <= last_victim)
+				sbi->last_victim[p.gc_mode] = last_victim + 1;
+			else
+				sbi->last_victim[p.gc_mode] = segno + 1;
 			break;
 		}
 	}
@@ -400,7 +420,7 @@ static int check_valid_map(struct f2fs_sb_info *sbi,
  * On validity, copy that node with cold status, otherwise (invalid node)
  * ignore that.
  */
-static int gc_node_segment(struct f2fs_sb_info *sbi,
+static void gc_node_segment(struct f2fs_sb_info *sbi,
 		struct f2fs_summary *sum, unsigned int segno, int gc_type)
 {
 	bool initial = true;
@@ -420,7 +440,7 @@ next_step:
 
 		/* stop BG_GC if there is not enough free sections. */
 		if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0))
-			return 0;
+			return;
 
 		if (check_valid_map(sbi, segno, off) == 0)
 			continue;
@@ -447,7 +467,7 @@ next_step:
 
 		/* set page dirty and write it */
 		if (gc_type == FG_GC) {
-			f2fs_wait_on_page_writeback(node_page, NODE);
+			f2fs_wait_on_page_writeback(node_page, NODE, true);
 			set_page_dirty(node_page);
 		} else {
 			if (!PageWriteback(node_page))
@@ -461,20 +481,6 @@ next_step:
 		initial = false;
 		goto next_step;
 	}
-
-	if (gc_type == FG_GC) {
-		struct writeback_control wbc = {
-			.sync_mode = WB_SYNC_ALL,
-			.nr_to_write = LONG_MAX,
-			.for_reclaim = 0,
-		};
-		sync_node_pages(sbi, 0, &wbc);
-
-		/* return 1 only if FG_GC succefully reclaimed one */
-		if (get_valid_blocks(sbi, segno, 1) == 0)
-			return 1;
-	}
-	return 0;
 }
 
 /*
@@ -484,7 +490,7 @@ next_step:
  * as indirect or double indirect node blocks, are given, it must be a caller's
  * bug.
  */
-block_t start_bidx_of_node(unsigned int node_ofs, struct f2fs_inode_info *fi)
+block_t start_bidx_of_node(unsigned int node_ofs, struct inode *inode)
 {
 	unsigned int indirect_blks = 2 * NIDS_PER_BLOCK + 4;
 	unsigned int bidx;
@@ -501,7 +507,7 @@ block_t start_bidx_of_node(unsigned int node_ofs, struct f2fs_inode_info *fi)
 		int dec = (node_ofs - indirect_blks - 3) / (NIDS_PER_BLOCK + 1);
 		bidx = node_ofs - 5 - dec;
 	}
-	return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi);
+	return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE(inode);
 }
 
 static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
@@ -547,6 +553,7 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
 	struct f2fs_summary sum;
 	struct node_info ni;
 	struct page *page;
+	block_t newaddr;
 	int err;
 
 	/* do not read out */
@@ -568,21 +575,24 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
 	 * don't cache encrypted data into meta inode until previous dirty
 	 * data were writebacked to avoid racing between GC and flush.
 	 */
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_wait_on_page_writeback(page, DATA, true);
 
 	get_node_info(fio.sbi, dn.nid, &ni);
 	set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version);
 
 	/* read page */
 	fio.page = page;
-	fio.blk_addr = dn.data_blkaddr;
+	fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr;
 
-	fio.encrypted_page = pagecache_get_page(META_MAPPING(fio.sbi),
-					fio.blk_addr,
-					FGP_LOCK|FGP_CREAT,
-					GFP_NOFS);
-	if (!fio.encrypted_page)
-		goto put_out;
+	allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr,
+							&sum, CURSEG_COLD_DATA);
+
+	fio.encrypted_page = pagecache_get_page(META_MAPPING(fio.sbi), newaddr,
+					FGP_LOCK | FGP_CREAT, GFP_NOFS);
+	if (!fio.encrypted_page) {
+		err = -ENOMEM;
+		goto recover_block;
+	}
 
 	err = f2fs_submit_page_bio(&fio);
 	if (err)
@@ -591,33 +601,39 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
 	/* write page */
 	lock_page(fio.encrypted_page);
 
-	if (unlikely(!PageUptodate(fio.encrypted_page)))
+	if (unlikely(!PageUptodate(fio.encrypted_page))) {
+		err = -EIO;
 		goto put_page_out;
-	if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi)))
+	}
+	if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi))) {
+		err = -EIO;
 		goto put_page_out;
+	}
 
 	set_page_dirty(fio.encrypted_page);
-	f2fs_wait_on_page_writeback(fio.encrypted_page, DATA);
+	f2fs_wait_on_page_writeback(fio.encrypted_page, DATA, true);
 	if (clear_page_dirty_for_io(fio.encrypted_page))
 		dec_page_count(fio.sbi, F2FS_DIRTY_META);
 
 	set_page_writeback(fio.encrypted_page);
 
 	/* allocate block address */
-	f2fs_wait_on_page_writeback(dn.node_page, NODE);
-	allocate_data_block(fio.sbi, NULL, fio.blk_addr,
-					&fio.blk_addr, &sum, CURSEG_COLD_DATA);
+	f2fs_wait_on_page_writeback(dn.node_page, NODE, true);
+
 	fio.rw = WRITE_SYNC;
+	fio.new_blkaddr = newaddr;
 	f2fs_submit_page_mbio(&fio);
 
-	dn.data_blkaddr = fio.blk_addr;
-	set_data_blkaddr(&dn);
-	f2fs_update_extent_cache(&dn);
+	f2fs_update_data_blkaddr(&dn, newaddr);
 	set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
 	if (page->index == 0)
 		set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
 put_page_out:
 	f2fs_put_page(fio.encrypted_page, 1);
+recover_block:
+	if (err)
+		__f2fs_replace_block(fio.sbi, &sum, newaddr, fio.old_blkaddr,
+								true, true);
 put_out:
 	f2fs_put_dnode(&dn);
 out:
@@ -646,7 +662,7 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
 			.encrypted_page = NULL,
 		};
 		set_page_dirty(page);
-		f2fs_wait_on_page_writeback(page, DATA);
+		f2fs_wait_on_page_writeback(page, DATA, true);
 		if (clear_page_dirty_for_io(page))
 			inode_dec_dirty_pages(inode);
 		set_cold_data(page);
@@ -664,7 +680,7 @@ out:
  * If the parent node is not valid or the data block address is different,
  * the victim data block is ignored.
  */
-static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
+static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 		struct gc_inode_list *gc_list, unsigned int segno, int gc_type)
 {
 	struct super_block *sb = sbi->sb;
@@ -687,7 +703,7 @@ next_step:
 
 		/* stop BG_GC if there is not enough free sections. */
 		if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0))
-			return 0;
+			return;
 
 		if (check_valid_map(sbi, segno, off) == 0)
 			continue;
@@ -720,7 +736,7 @@ next_step:
 				continue;
 			}
 
-			start_bidx = start_bidx_of_node(nofs, F2FS_I(inode));
+			start_bidx = start_bidx_of_node(nofs, inode);
 			data_page = get_read_data_page(inode,
 					start_bidx + ofs_in_node, READA, true);
 			if (IS_ERR(data_page)) {
@@ -736,7 +752,7 @@ next_step:
 		/* phase 3 */
 		inode = find_gc_inode(gc_list, dni.ino);
 		if (inode) {
-			start_bidx = start_bidx_of_node(nofs, F2FS_I(inode))
+			start_bidx = start_bidx_of_node(nofs, inode)
 								+ ofs_in_node;
 			if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
 				move_encrypted_block(inode, start_bidx);
@@ -748,15 +764,6 @@ next_step:
 
 	if (++phase < 4)
 		goto next_step;
-
-	if (gc_type == FG_GC) {
-		f2fs_submit_merged_bio(sbi, DATA, WRITE);
-
-		/* return 1 only if FG_GC succefully reclaimed one */
-		if (get_valid_blocks(sbi, segno, 1) == 0)
-			return 1;
-	}
-	return 0;
 }
 
 static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
@@ -772,53 +779,92 @@ static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
 	return ret;
 }
 
-static int do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno,
+static int do_garbage_collect(struct f2fs_sb_info *sbi,
+				unsigned int start_segno,
 				struct gc_inode_list *gc_list, int gc_type)
 {
 	struct page *sum_page;
 	struct f2fs_summary_block *sum;
 	struct blk_plug plug;
-	int nfree = 0;
+	unsigned int segno = start_segno;
+	unsigned int end_segno = start_segno + sbi->segs_per_sec;
+	int seg_freed = 0;
+	unsigned char type = IS_DATASEG(get_seg_entry(sbi, segno)->type) ?
+						SUM_TYPE_DATA : SUM_TYPE_NODE;
 
-	/* read segment summary of victim */
-	sum_page = get_sum_page(sbi, segno);
+	/* readahead multi ssa blocks those have contiguous address */
+	if (sbi->segs_per_sec > 1)
+		ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno),
+					sbi->segs_per_sec, META_SSA, true);
+
+	/* reference all summary page */
+	while (segno < end_segno) {
+		sum_page = get_sum_page(sbi, segno++);
+		unlock_page(sum_page);
+	}
 
 	blk_start_plug(&plug);
 
-	sum = page_address(sum_page);
+	for (segno = start_segno; segno < end_segno; segno++) {
+		/* find segment summary of victim */
+		sum_page = find_get_page(META_MAPPING(sbi),
+					GET_SUM_BLOCK(sbi, segno));
+		f2fs_bug_on(sbi, !PageUptodate(sum_page));
+		f2fs_put_page(sum_page, 0);
 
-	/*
-	 * this is to avoid deadlock:
-	 * - lock_page(sum_page)         - f2fs_replace_block
-	 *  - check_valid_map()            - mutex_lock(sentry_lock)
-	 *   - mutex_lock(sentry_lock)     - change_curseg()
-	 *                                  - lock_page(sum_page)
-	 */
-	unlock_page(sum_page);
-
-	switch (GET_SUM_TYPE((&sum->footer))) {
-	case SUM_TYPE_NODE:
-		nfree = gc_node_segment(sbi, sum->entries, segno, gc_type);
-		break;
-	case SUM_TYPE_DATA:
-		nfree = gc_data_segment(sbi, sum->entries, gc_list,
-							segno, gc_type);
-		break;
+		sum = page_address(sum_page);
+		f2fs_bug_on(sbi, type != GET_SUM_TYPE((&sum->footer)));
+
+		/*
+		 * this is to avoid deadlock:
+		 * - lock_page(sum_page)         - f2fs_replace_block
+		 *  - check_valid_map()            - mutex_lock(sentry_lock)
+		 *   - mutex_lock(sentry_lock)     - change_curseg()
+		 *                                  - lock_page(sum_page)
+		 */
+
+		if (type == SUM_TYPE_NODE)
+			gc_node_segment(sbi, sum->entries, segno, gc_type);
+		else
+			gc_data_segment(sbi, sum->entries, gc_list, segno,
+								gc_type);
+
+		stat_inc_seg_count(sbi, type, gc_type);
+
+		f2fs_put_page(sum_page, 0);
+	}
+
+	if (gc_type == FG_GC) {
+		if (type == SUM_TYPE_NODE) {
+			struct writeback_control wbc = {
+				.sync_mode = WB_SYNC_ALL,
+				.nr_to_write = LONG_MAX,
+				.for_reclaim = 0,
+			};
+			sync_node_pages(sbi, 0, &wbc);
+		} else {
+			f2fs_submit_merged_bio(sbi, DATA, WRITE);
+		}
 	}
+
 	blk_finish_plug(&plug);
 
-	stat_inc_seg_count(sbi, GET_SUM_TYPE((&sum->footer)), gc_type);
+	if (gc_type == FG_GC) {
+		while (start_segno < end_segno)
+			if (get_valid_blocks(sbi, start_segno++, 1) == 0)
+				seg_freed++;
+	}
+
 	stat_inc_call_count(sbi->stat_info);
 
-	f2fs_put_page(sum_page, 0);
-	return nfree;
+	return seg_freed;
 }
 
 int f2fs_gc(struct f2fs_sb_info *sbi, bool sync)
 {
-	unsigned int segno, i;
+	unsigned int segno;
 	int gc_type = sync ? FG_GC : BG_GC;
-	int sec_freed = 0;
+	int sec_freed = 0, seg_freed;
 	int ret = -EINVAL;
 	struct cp_control cpc;
 	struct gc_inode_list gc_list = {
@@ -832,35 +878,31 @@ gc_more:
 
 	if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE)))
 		goto stop;
-	if (unlikely(f2fs_cp_error(sbi)))
+	if (unlikely(f2fs_cp_error(sbi))) {
+		ret = -EIO;
 		goto stop;
+	}
 
 	if (gc_type == BG_GC && has_not_enough_free_secs(sbi, sec_freed)) {
 		gc_type = FG_GC;
+		/*
+		 * If there is no victim and no prefree segment but still not
+		 * enough free sections, we should flush dent/node blocks and do
+		 * garbage collections.
+		 */
 		if (__get_victim(sbi, &segno, gc_type) || prefree_segments(sbi))
 			write_checkpoint(sbi, &cpc);
+		else if (has_not_enough_free_secs(sbi, 0))
+			write_checkpoint(sbi, &cpc);
 	}
 
 	if (segno == NULL_SEGNO && !__get_victim(sbi, &segno, gc_type))
 		goto stop;
 	ret = 0;
 
-	/* readahead multi ssa blocks those have contiguous address */
-	if (sbi->segs_per_sec > 1)
-		ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno), sbi->segs_per_sec,
-							META_SSA, true);
-
-	for (i = 0; i < sbi->segs_per_sec; i++) {
-		/*
-		 * for FG_GC case, halt gcing left segments once failed one
-		 * of segments in selected section to avoid long latency.
-		 */
-		if (!do_garbage_collect(sbi, segno + i, &gc_list, gc_type) &&
-				gc_type == FG_GC)
-			break;
-	}
+	seg_freed = do_garbage_collect(sbi, segno, &gc_list, gc_type);
 
-	if (i == sbi->segs_per_sec && gc_type == FG_GC)
+	if (gc_type == FG_GC && seg_freed == sbi->segs_per_sec)
 		sec_freed++;
 
 	if (gc_type == FG_GC)
diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h
index b4a65be9f7d3..a993967dcdb9 100644
--- a/fs/f2fs/gc.h
+++ b/fs/f2fs/gc.h
@@ -100,11 +100,3 @@ static inline bool has_enough_invalid_blocks(struct f2fs_sb_info *sbi)
 		return true;
 	return false;
 }
-
-static inline int is_idle(struct f2fs_sb_info *sbi)
-{
-	struct block_device *bdev = sbi->sb->s_bdev;
-	struct request_queue *q = bdev_get_queue(bdev);
-	struct request_list *rl = &q->root_rl;
-	return !(rl->count[BLK_RW_SYNC]) && !(rl->count[BLK_RW_ASYNC]);
-}
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index bda7126466c0..a2fbe6f427d3 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -16,9 +16,6 @@
 
 bool f2fs_may_inline_data(struct inode *inode)
 {
-	if (!test_opt(F2FS_I_SB(inode), INLINE_DATA))
-		return false;
-
 	if (f2fs_is_atomic_file(inode))
 		return false;
 
@@ -54,7 +51,7 @@ void read_inline_data(struct page *page, struct page *ipage)
 
 	f2fs_bug_on(F2FS_P_SB(page), page->index);
 
-	zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
+	zero_user_segment(page, MAX_INLINE_DATA, PAGE_SIZE);
 
 	/* Copy the whole inline data block */
 	src_addr = inline_data_addr(ipage);
@@ -74,7 +71,7 @@ bool truncate_inline_inode(struct page *ipage, u64 from)
 
 	addr = inline_data_addr(ipage);
 
-	f2fs_wait_on_page_writeback(ipage, NODE);
+	f2fs_wait_on_page_writeback(ipage, NODE, true);
 	memset(addr + from, 0, MAX_INLINE_DATA - from);
 
 	return true;
@@ -96,7 +93,7 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page)
 	}
 
 	if (page->index)
-		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+		zero_user_segment(page, 0, PAGE_SIZE);
 	else
 		read_inline_data(page, ipage);
 
@@ -108,7 +105,6 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page)
 
 int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 {
-	void *src_addr, *dst_addr;
 	struct f2fs_io_info fio = {
 		.sbi = F2FS_I_SB(dn->inode),
 		.type = DATA,
@@ -118,8 +114,6 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 	};
 	int dirty, err;
 
-	f2fs_bug_on(F2FS_I_SB(dn->inode), page->index);
-
 	if (!f2fs_exist_data(dn->inode))
 		goto clear_out;
 
@@ -127,21 +121,9 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 	if (err)
 		return err;
 
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_bug_on(F2FS_P_SB(page), PageWriteback(page));
 
-	if (PageUptodate(page))
-		goto no_update;
-
-	zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
-
-	/* Copy the whole inline data block */
-	src_addr = inline_data_addr(dn->inode_page);
-	dst_addr = kmap_atomic(page);
-	memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
-	flush_dcache_page(page);
-	kunmap_atomic(dst_addr);
-	SetPageUptodate(page);
-no_update:
+	read_inline_data(page, dn->inode_page);
 	set_page_dirty(page);
 
 	/* clear dirty state */
@@ -149,11 +131,9 @@ no_update:
 
 	/* write data page to try to make data consistent */
 	set_page_writeback(page);
-	fio.blk_addr = dn->data_blkaddr;
+	fio.old_blkaddr = dn->data_blkaddr;
 	write_data_page(dn, &fio);
-	set_data_blkaddr(dn);
-	f2fs_update_extent_cache(dn);
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_wait_on_page_writeback(page, DATA, true);
 	if (dirty)
 		inode_dec_dirty_pages(dn->inode);
 
@@ -162,6 +142,7 @@ no_update:
 
 	/* clear inline data and flag after data writeback */
 	truncate_inline_inode(dn->inode_page, 0);
+	clear_inline_node(dn->inode_page);
 clear_out:
 	stat_dec_inline_inode(dn->inode);
 	f2fs_clear_inline_inode(dn->inode);
@@ -177,6 +158,9 @@ int f2fs_convert_inline_inode(struct inode *inode)
 	struct page *ipage, *page;
 	int err = 0;
 
+	if (!f2fs_has_inline_data(inode))
+		return 0;
+
 	page = grab_cache_page(inode->i_mapping, 0);
 	if (!page)
 		return -ENOMEM;
@@ -199,6 +183,9 @@ out:
 	f2fs_unlock_op(sbi);
 
 	f2fs_put_page(page, 1);
+
+	f2fs_balance_fs(sbi, dn.node_changed);
+
 	return err;
 }
 
@@ -220,7 +207,7 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page)
 
 	f2fs_bug_on(F2FS_I_SB(inode), page->index);
 
-	f2fs_wait_on_page_writeback(dn.inode_page, NODE);
+	f2fs_wait_on_page_writeback(dn.inode_page, NODE, true);
 	src_addr = kmap_atomic(page);
 	dst_addr = inline_data_addr(dn.inode_page);
 	memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
@@ -230,6 +217,7 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page)
 	set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
 
 	sync_inode_page(&dn);
+	clear_inline_node(dn.inode_page);
 	f2fs_put_dnode(&dn);
 	return 0;
 }
@@ -258,7 +246,7 @@ process_inline:
 		ipage = get_node_page(sbi, inode->i_ino);
 		f2fs_bug_on(sbi, IS_ERR(ipage));
 
-		f2fs_wait_on_page_writeback(ipage, NODE);
+		f2fs_wait_on_page_writeback(ipage, NODE, true);
 
 		src_addr = inline_data_addr(npage);
 		dst_addr = inline_data_addr(ipage);
@@ -289,7 +277,7 @@ process_inline:
 }
 
 struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
-			struct f2fs_filename *fname, struct page **res_page)
+			struct fscrypt_name *fname, struct page **res_page)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
 	struct f2fs_inline_dentry *inline_dentry;
@@ -386,8 +374,8 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
 	if (err)
 		goto out;
 
-	f2fs_wait_on_page_writeback(page, DATA);
-	zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
+	f2fs_wait_on_page_writeback(page, DATA, true);
+	zero_user_segment(page, MAX_INLINE_DATA, PAGE_SIZE);
 
 	dentry_blk = kmap_atomic(page);
 
@@ -417,8 +405,8 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
 	stat_dec_inline_dir(dir);
 	clear_inode_flag(F2FS_I(dir), FI_INLINE_DENTRY);
 
-	if (i_size_read(dir) < PAGE_CACHE_SIZE) {
-		i_size_write(dir, PAGE_CACHE_SIZE);
+	if (i_size_read(dir) < PAGE_SIZE) {
+		i_size_write(dir, PAGE_SIZE);
 		set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
 	}
 
@@ -466,7 +454,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name,
 		}
 	}
 
-	f2fs_wait_on_page_writeback(ipage, NODE);
+	f2fs_wait_on_page_writeback(ipage, NODE, true);
 
 	name_hash = f2fs_dentry_hash(name);
 	make_dentry_ptr(NULL, &d, (void *)dentry_blk, 2);
@@ -504,7 +492,7 @@ void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page,
 	int i;
 
 	lock_page(page);
-	f2fs_wait_on_page_writeback(page, NODE);
+	f2fs_wait_on_page_writeback(page, NODE, true);
 
 	inline_dentry = inline_data_addr(page);
 	bit_pos = dentry - inline_dentry->dentry;
@@ -547,7 +535,7 @@ bool f2fs_empty_inline_dir(struct inode *dir)
 }
 
 int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
-				struct f2fs_str *fstr)
+				struct fscrypt_str *fstr)
 {
 	struct inode *inode = file_inode(file);
 	struct f2fs_inline_dentry *inline_dentry = NULL;
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 97e20decacb4..cb269c46ac25 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -83,7 +83,7 @@ static void __recover_inline_status(struct inode *inode, struct page *ipage)
 
 	while (start < end) {
 		if (*start++) {
-			f2fs_wait_on_page_writeback(ipage, NODE);
+			f2fs_wait_on_page_writeback(ipage, NODE, true);
 
 			set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
 			set_raw_inline(F2FS_I(inode), F2FS_INODE(ipage));
@@ -138,7 +138,8 @@ static int do_read_inode(struct inode *inode)
 	fi->i_pino = le32_to_cpu(ri->i_pino);
 	fi->i_dir_level = ri->i_dir_level;
 
-	f2fs_init_extent_tree(inode, &ri->i_ext);
+	if (f2fs_init_extent_tree(inode, &ri->i_ext))
+		set_page_dirty(node_page);
 
 	get_inline_info(fi, ri);
 
@@ -202,6 +203,7 @@ make_now:
 			inode->i_op = &f2fs_encrypted_symlink_inode_operations;
 		else
 			inode->i_op = &f2fs_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &f2fs_dblock_aops;
 	} else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
 			S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
@@ -221,11 +223,11 @@ bad_inode:
 	return ERR_PTR(ret);
 }
 
-void update_inode(struct inode *inode, struct page *node_page)
+int update_inode(struct inode *inode, struct page *node_page)
 {
 	struct f2fs_inode *ri;
 
-	f2fs_wait_on_page_writeback(node_page, NODE);
+	f2fs_wait_on_page_writeback(node_page, NODE, true);
 
 	ri = F2FS_INODE(node_page);
 
@@ -259,15 +261,20 @@ void update_inode(struct inode *inode, struct page *node_page)
 
 	__set_inode_rdev(inode, ri);
 	set_cold_node(inode, node_page);
-	set_page_dirty(node_page);
-
 	clear_inode_flag(F2FS_I(inode), FI_DIRTY_INODE);
+
+	/* deleted inode */
+	if (inode->i_nlink == 0)
+		clear_inline_node(node_page);
+
+	return set_page_dirty(node_page);
 }
 
-void update_inode_page(struct inode *inode)
+int update_inode_page(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct page *node_page;
+	int ret = 0;
 retry:
 	node_page = get_node_page(sbi, inode->i_ino);
 	if (IS_ERR(node_page)) {
@@ -278,10 +285,11 @@ retry:
 		} else if (err != -ENOENT) {
 			f2fs_stop_checkpoint(sbi);
 		}
-		return;
+		return 0;
 	}
-	update_inode(inode, node_page);
+	ret = update_inode(inode, node_page);
 	f2fs_put_page(node_page, 1);
+	return ret;
 }
 
 int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
@@ -299,9 +307,8 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
 	 * We need to balance fs here to prevent from producing dirty node pages
 	 * during the urgent cleaning time when runing out of free sections.
 	 */
-	update_inode_page(inode);
-
-	f2fs_balance_fs(sbi);
+	if (update_inode_page(inode))
+		f2fs_balance_fs(sbi, true);
 	return 0;
 }
 
@@ -317,7 +324,7 @@ void f2fs_evict_inode(struct inode *inode)
 
 	/* some remained atomic pages should discarded */
 	if (f2fs_is_atomic_file(inode))
-		commit_inmem_pages(inode, true);
+		drop_inmem_pages(inode);
 
 	trace_f2fs_evict_inode(inode);
 	truncate_inode_pages_final(&inode->i_data);
@@ -327,7 +334,7 @@ void f2fs_evict_inode(struct inode *inode)
 		goto out_clear;
 
 	f2fs_bug_on(sbi, get_dirty_pages(inode));
-	remove_dirty_dir_inode(inode);
+	remove_dirty_inode(inode);
 
 	f2fs_destroy_extent_tree(inode);
 
@@ -357,9 +364,9 @@ no_delete:
 	if (xnid)
 		invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid);
 	if (is_inode_flag_set(fi, FI_APPEND_WRITE))
-		add_dirty_inode(sbi, inode->i_ino, APPEND_INO);
+		add_ino_entry(sbi, inode->i_ino, APPEND_INO);
 	if (is_inode_flag_set(fi, FI_UPDATE_WRITE))
-		add_dirty_inode(sbi, inode->i_ino, UPDATE_INO);
+		add_ino_entry(sbi, inode->i_ino, UPDATE_INO);
 	if (is_inode_flag_set(fi, FI_FREE_NID)) {
 		if (err && err != -ENOENT)
 			alloc_nid_done(sbi, inode->i_ino);
@@ -382,10 +389,7 @@ no_delete:
 		}
 	}
 out_clear:
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-	if (fi->i_crypt_info)
-		f2fs_free_encryption_info(inode, fi->i_crypt_info);
-#endif
+	fscrypt_put_encryption_info(inode, NULL);
 	clear_inode(inode);
 }
 
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index e48b80c49090..013e57932d61 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -60,7 +60,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 	if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode))
 		f2fs_set_encrypted_inode(inode);
 
-	if (f2fs_may_inline_data(inode))
+	if (test_opt(sbi, INLINE_DATA) && f2fs_may_inline_data(inode))
 		set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
 	if (f2fs_may_inline_dentry(inode))
 		set_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY);
@@ -128,8 +128,6 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	nid_t ino = 0;
 	int err;
 
-	f2fs_balance_fs(sbi);
-
 	inode = f2fs_new_inode(dir, mode);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -142,6 +140,8 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	inode->i_mapping->a_ops = &f2fs_dblock_aops;
 	ino = inode->i_ino;
 
+	f2fs_balance_fs(sbi, true);
+
 	f2fs_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
 	if (err)
@@ -169,10 +169,10 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
 	int err;
 
 	if (f2fs_encrypted_inode(dir) &&
-		!f2fs_is_child_context_consistent_with_parent(dir, inode))
+			!fscrypt_has_permitted_context(dir, inode))
 		return -EPERM;
 
-	f2fs_balance_fs(sbi);
+	f2fs_balance_fs(sbi, true);
 
 	inode->i_ctime = CURRENT_TIME;
 	ihold(inode);
@@ -214,6 +214,15 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino)
 	struct page *page;
 	int err = 0;
 
+	if (f2fs_readonly(sbi->sb)) {
+		f2fs_msg(sbi->sb, KERN_INFO,
+			"skip recovering inline_dots inode (ino:%lu, pino:%u) "
+			"in readonly mountpoint", dir->i_ino, pino);
+		return 0;
+	}
+
+	f2fs_balance_fs(sbi, true);
+
 	f2fs_lock_op(sbi);
 
 	de = f2fs_find_entry(dir, &dot, &page);
@@ -251,6 +260,22 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 	struct page *page;
 	nid_t ino;
 	int err = 0;
+	unsigned int root_ino = F2FS_ROOT_INO(F2FS_I_SB(dir));
+
+	if (f2fs_encrypted_inode(dir)) {
+		int res = fscrypt_get_encryption_info(dir);
+
+		/*
+		 * DCACHE_ENCRYPTED_WITH_KEY is set if the dentry is
+		 * created while the directory was encrypted and we
+		 * don't have access to the key.
+		 */
+		if (fscrypt_has_encryption_key(dir))
+			fscrypt_set_encrypted_dentry(dentry);
+		fscrypt_set_d_op(dentry);
+		if (res && res != -ENOKEY)
+			return ERR_PTR(res);
+	}
 
 	if (dentry->d_name.len > F2FS_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
@@ -267,15 +292,29 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
 
+	if ((dir->i_ino == root_ino) && f2fs_has_inline_dots(dir)) {
+		err = __recover_dot_dentries(dir, root_ino);
+		if (err)
+			goto err_out;
+	}
+
 	if (f2fs_has_inline_dots(inode)) {
 		err = __recover_dot_dentries(inode, dir->i_ino);
 		if (err)
 			goto err_out;
 	}
+	if (!IS_ERR(inode) && f2fs_encrypted_inode(dir) &&
+			(S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
+			!fscrypt_has_permitted_context(dir, inode)) {
+		bool nokey = f2fs_encrypted_inode(inode) &&
+			!fscrypt_has_encryption_key(inode);
+		err = nokey ? -ENOKEY : -EPERM;
+		goto err_out;
+	}
 	return d_splice_alias(inode, dentry);
 
 err_out:
-	iget_failed(inode);
+	iput(inode);
 	return ERR_PTR(err);
 }
 
@@ -288,12 +327,13 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
 	int err = -ENOENT;
 
 	trace_f2fs_unlink_enter(dir, dentry);
-	f2fs_balance_fs(sbi);
 
 	de = f2fs_find_entry(dir, &dentry->d_name, &page);
 	if (!de)
 		goto fail;
 
+	f2fs_balance_fs(sbi, true);
+
 	f2fs_lock_op(sbi);
 	err = acquire_orphan_inode(sbi);
 	if (err) {
@@ -315,12 +355,15 @@ fail:
 	return err;
 }
 
-static const char *f2fs_follow_link(struct dentry *dentry, void **cookie)
+static const char *f2fs_get_link(struct dentry *dentry,
+				 struct inode *inode,
+				 struct delayed_call *done)
 {
-	const char *link = page_follow_link_light(dentry, cookie);
+	const char *link = page_get_link(dentry, inode, done);
 	if (!IS_ERR(link) && !*link) {
 		/* this is broken symlink case */
-		page_put_link(NULL, *cookie);
+		do_delayed_call(done);
+		clear_delayed_call(done);
 		link = ERR_PTR(-ENOENT);
 	}
 	return link;
@@ -332,16 +375,24 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
 	struct inode *inode;
 	size_t len = strlen(symname);
-	size_t p_len;
-	char *p_str;
-	struct f2fs_str disk_link = FSTR_INIT(NULL, 0);
-	struct f2fs_encrypted_symlink_data *sd = NULL;
+	struct fscrypt_str disk_link = FSTR_INIT((char *)symname, len + 1);
+	struct fscrypt_symlink_data *sd = NULL;
 	int err;
 
-	if (len > dir->i_sb->s_blocksize)
-		return -ENAMETOOLONG;
+	if (f2fs_encrypted_inode(dir)) {
+		err = fscrypt_get_encryption_info(dir);
+		if (err)
+			return err;
 
-	f2fs_balance_fs(sbi);
+		if (!fscrypt_has_encryption_key(dir))
+			return -EPERM;
+
+		disk_link.len = (fscrypt_fname_encrypted_size(dir, len) +
+				sizeof(struct fscrypt_symlink_data));
+	}
+
+	if (disk_link.len > dir->i_sb->s_blocksize)
+		return -ENAMETOOLONG;
 
 	inode = f2fs_new_inode(dir, S_IFLNK | S_IRWXUGO);
 	if (IS_ERR(inode))
@@ -351,8 +402,11 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 		inode->i_op = &f2fs_encrypted_symlink_inode_operations;
 	else
 		inode->i_op = &f2fs_symlink_inode_operations;
+	inode_nohighmem(inode);
 	inode->i_mapping->a_ops = &f2fs_dblock_aops;
 
+	f2fs_balance_fs(sbi, true);
+
 	f2fs_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
 	if (err)
@@ -360,42 +414,36 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 	f2fs_unlock_op(sbi);
 	alloc_nid_done(sbi, inode->i_ino);
 
-	if (f2fs_encrypted_inode(dir)) {
+	if (f2fs_encrypted_inode(inode)) {
 		struct qstr istr = QSTR_INIT(symname, len);
+		struct fscrypt_str ostr;
 
-		err = f2fs_get_encryption_info(inode);
-		if (err)
+		sd = kzalloc(disk_link.len, GFP_NOFS);
+		if (!sd) {
+			err = -ENOMEM;
 			goto err_out;
+		}
 
-		err = f2fs_fname_crypto_alloc_buffer(inode, len, &disk_link);
+		err = fscrypt_get_encryption_info(inode);
 		if (err)
 			goto err_out;
 
-		err = f2fs_fname_usr_to_disk(inode, &istr, &disk_link);
-		if (err < 0)
-			goto err_out;
-
-		p_len = encrypted_symlink_data_len(disk_link.len) + 1;
-
-		if (p_len > dir->i_sb->s_blocksize) {
-			err = -ENAMETOOLONG;
+		if (!fscrypt_has_encryption_key(inode)) {
+			err = -EPERM;
 			goto err_out;
 		}
 
-		sd = kzalloc(p_len, GFP_NOFS);
-		if (!sd) {
-			err = -ENOMEM;
+		ostr.name = sd->encrypted_path;
+		ostr.len = disk_link.len;
+		err = fscrypt_fname_usr_to_disk(inode, &istr, &ostr);
+		if (err < 0)
 			goto err_out;
-		}
-		memcpy(sd->encrypted_path, disk_link.name, disk_link.len);
-		sd->len = cpu_to_le16(disk_link.len);
-		p_str = (char *)sd;
-	} else {
-		p_len = len + 1;
-		p_str = (char *)symname;
+
+		sd->len = cpu_to_le16(ostr.len);
+		disk_link.name = (char *)sd;
 	}
 
-	err = page_symlink(inode, p_str, p_len);
+	err = page_symlink(inode, disk_link.name, disk_link.len);
 
 err_out:
 	d_instantiate(dentry, inode);
@@ -411,7 +459,8 @@ err_out:
 	 * performance regression.
 	 */
 	if (!err) {
-		filemap_write_and_wait_range(inode->i_mapping, 0, p_len - 1);
+		filemap_write_and_wait_range(inode->i_mapping, 0,
+							disk_link.len - 1);
 
 		if (IS_DIRSYNC(dir))
 			f2fs_sync_fs(sbi->sb, 1);
@@ -420,7 +469,6 @@ err_out:
 	}
 
 	kfree(sd);
-	f2fs_fname_crypto_free_buffer(&disk_link);
 	return err;
 out:
 	handle_failed_inode(inode);
@@ -433,8 +481,6 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	struct inode *inode;
 	int err;
 
-	f2fs_balance_fs(sbi);
-
 	inode = f2fs_new_inode(dir, S_IFDIR | mode);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -444,6 +490,8 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	inode->i_mapping->a_ops = &f2fs_dblock_aops;
 	mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO);
 
+	f2fs_balance_fs(sbi, true);
+
 	set_inode_flag(F2FS_I(inode), FI_INC_LINK);
 	f2fs_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
@@ -481,11 +529,6 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
 	struct inode *inode;
 	int err = 0;
 
-	if (!new_valid_dev(rdev))
-		return -EINVAL;
-
-	f2fs_balance_fs(sbi);
-
 	inode = f2fs_new_inode(dir, mode);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -493,6 +536,8 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
 	init_special_inode(inode, inode->i_mode, rdev);
 	inode->i_op = &f2fs_special_inode_operations;
 
+	f2fs_balance_fs(sbi, true);
+
 	f2fs_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
 	if (err)
@@ -519,9 +564,6 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
 	struct inode *inode;
 	int err;
 
-	if (!whiteout)
-		f2fs_balance_fs(sbi);
-
 	inode = f2fs_new_inode(dir, mode);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -535,6 +577,8 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
 		inode->i_mapping->a_ops = &f2fs_dblock_aops;
 	}
 
+	f2fs_balance_fs(sbi, true);
+
 	f2fs_lock_op(sbi);
 	err = acquire_orphan_inode(sbi);
 	if (err)
@@ -572,7 +616,7 @@ out:
 static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 {
 	if (f2fs_encrypted_inode(dir)) {
-		int err = f2fs_get_encryption_info(dir);
+		int err = fscrypt_get_encryption_info(dir);
 		if (err)
 			return err;
 	}
@@ -598,17 +642,15 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct f2fs_dir_entry *old_dir_entry = NULL;
 	struct f2fs_dir_entry *old_entry;
 	struct f2fs_dir_entry *new_entry;
+	bool is_old_inline = f2fs_has_inline_dentry(old_dir);
 	int err = -ENOENT;
 
 	if ((old_dir != new_dir) && f2fs_encrypted_inode(new_dir) &&
-		!f2fs_is_child_context_consistent_with_parent(new_dir,
-							old_inode)) {
+			!fscrypt_has_permitted_context(new_dir, old_inode)) {
 		err = -EPERM;
 		goto out;
 	}
 
-	f2fs_balance_fs(sbi);
-
 	old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
 	if (!old_entry)
 		goto out;
@@ -638,14 +680,17 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (!new_entry)
 			goto out_whiteout;
 
+		f2fs_balance_fs(sbi, true);
+
 		f2fs_lock_op(sbi);
 
 		err = acquire_orphan_inode(sbi);
 		if (err)
 			goto put_out_dir;
 
-		if (update_dent_inode(old_inode, new_inode,
-						&new_dentry->d_name)) {
+		err = update_dent_inode(old_inode, new_inode,
+						&new_dentry->d_name);
+		if (err) {
 			release_orphan_inode(sbi);
 			goto put_out_dir;
 		}
@@ -669,6 +714,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		update_inode_page(old_inode);
 		update_inode_page(new_inode);
 	} else {
+		f2fs_balance_fs(sbi, true);
+
 		f2fs_lock_op(sbi);
 
 		err = f2fs_add_link(new_dentry, old_inode);
@@ -681,6 +728,26 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			inc_nlink(new_dir);
 			update_inode_page(new_dir);
 		}
+
+		/*
+		 * old entry and new entry can locate in the same inline
+		 * dentry in inode, when attaching new entry in inline dentry,
+		 * it could force inline dentry conversion, after that,
+		 * old_entry and old_page will point to wrong address, in
+		 * order to avoid this, let's do the check and update here.
+		 */
+		if (is_old_inline && !f2fs_has_inline_dentry(old_dir)) {
+			f2fs_put_page(old_page, 0);
+			old_page = NULL;
+
+			old_entry = f2fs_find_entry(old_dir,
+						&old_dentry->d_name, &old_page);
+			if (!old_entry) {
+				err = -EIO;
+				f2fs_unlock_op(sbi);
+				goto out_whiteout;
+			}
+		}
 	}
 
 	down_write(&F2FS_I(old_inode)->i_sem);
@@ -759,15 +826,11 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 	int err = -ENOENT;
 
 	if ((f2fs_encrypted_inode(old_dir) || f2fs_encrypted_inode(new_dir)) &&
-		(old_dir != new_dir) &&
-		(!f2fs_is_child_context_consistent_with_parent(new_dir,
-								old_inode) ||
-		!f2fs_is_child_context_consistent_with_parent(old_dir,
-								new_inode)))
+			(old_dir != new_dir) &&
+			(!fscrypt_has_permitted_context(new_dir, old_inode) ||
+			 !fscrypt_has_permitted_context(old_dir, new_inode)))
 		return -EPERM;
 
-	f2fs_balance_fs(sbi);
-
 	old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
 	if (!old_entry)
 		goto out;
@@ -810,6 +873,8 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 			goto out_new_dir;
 	}
 
+	f2fs_balance_fs(sbi, true);
+
 	f2fs_lock_op(sbi);
 
 	err = update_dent_inode(old_inode, new_inode, &new_dentry->d_name);
@@ -925,89 +990,88 @@ static int f2fs_rename2(struct inode *old_dir, struct dentry *old_dentry,
 	return f2fs_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
 }
 
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-static const char *f2fs_encrypted_follow_link(struct dentry *dentry, void **cookie)
+static const char *f2fs_encrypted_get_link(struct dentry *dentry,
+					   struct inode *inode,
+					   struct delayed_call *done)
 {
 	struct page *cpage = NULL;
 	char *caddr, *paddr = NULL;
-	struct f2fs_str cstr;
-	struct f2fs_str pstr = FSTR_INIT(NULL, 0);
-	struct inode *inode = d_inode(dentry);
-	struct f2fs_encrypted_symlink_data *sd;
+	struct fscrypt_str cstr = FSTR_INIT(NULL, 0);
+	struct fscrypt_str pstr = FSTR_INIT(NULL, 0);
+	struct fscrypt_symlink_data *sd;
 	loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1);
 	u32 max_size = inode->i_sb->s_blocksize;
 	int res;
 
-	res = f2fs_get_encryption_info(inode);
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
+	res = fscrypt_get_encryption_info(inode);
 	if (res)
 		return ERR_PTR(res);
 
 	cpage = read_mapping_page(inode->i_mapping, 0, NULL);
 	if (IS_ERR(cpage))
 		return ERR_CAST(cpage);
-	caddr = kmap(cpage);
+	caddr = page_address(cpage);
 	caddr[size] = 0;
 
 	/* Symlink is encrypted */
-	sd = (struct f2fs_encrypted_symlink_data *)caddr;
+	sd = (struct fscrypt_symlink_data *)caddr;
+	cstr.name = sd->encrypted_path;
 	cstr.len = le16_to_cpu(sd->len);
-	cstr.name = kmalloc(cstr.len, GFP_NOFS);
-	if (!cstr.name) {
-		res = -ENOMEM;
-		goto errout;
-	}
-	memcpy(cstr.name, sd->encrypted_path, cstr.len);
 
 	/* this is broken symlink case */
-	if (cstr.name[0] == 0 && cstr.len == 0) {
+	if (unlikely(cstr.len == 0)) {
 		res = -ENOENT;
 		goto errout;
 	}
 
-	if ((cstr.len + sizeof(struct f2fs_encrypted_symlink_data) - 1) >
-								max_size) {
+	if ((cstr.len + sizeof(struct fscrypt_symlink_data) - 1) > max_size) {
 		/* Symlink data on the disk is corrupted */
 		res = -EIO;
 		goto errout;
 	}
-	res = f2fs_fname_crypto_alloc_buffer(inode, cstr.len, &pstr);
+	res = fscrypt_fname_alloc_buffer(inode, cstr.len, &pstr);
 	if (res)
 		goto errout;
 
-	res = f2fs_fname_disk_to_usr(inode, NULL, &cstr, &pstr);
+	res = fscrypt_fname_disk_to_usr(inode, 0, 0, &cstr, &pstr);
 	if (res < 0)
 		goto errout;
 
-	kfree(cstr.name);
+	/* this is broken symlink case */
+	if (unlikely(pstr.name[0] == 0)) {
+		res = -ENOENT;
+		goto errout;
+	}
 
 	paddr = pstr.name;
 
 	/* Null-terminate the name */
 	paddr[res] = '\0';
 
-	kunmap(cpage);
-	page_cache_release(cpage);
-	return *cookie = paddr;
+	put_page(cpage);
+	set_delayed_call(done, kfree_link, paddr);
+	return paddr;
 errout:
-	kfree(cstr.name);
-	f2fs_fname_crypto_free_buffer(&pstr);
-	kunmap(cpage);
-	page_cache_release(cpage);
+	fscrypt_fname_free_buffer(&pstr);
+	put_page(cpage);
 	return ERR_PTR(res);
 }
 
 const struct inode_operations f2fs_encrypted_symlink_inode_operations = {
 	.readlink       = generic_readlink,
-	.follow_link    = f2fs_encrypted_follow_link,
-	.put_link       = kfree_put_link,
+	.get_link       = f2fs_encrypted_get_link,
 	.getattr	= f2fs_getattr,
 	.setattr	= f2fs_setattr,
+#ifdef CONFIG_F2FS_FS_XATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
 	.listxattr	= f2fs_listxattr,
 	.removexattr	= generic_removexattr,
-};
 #endif
+};
 
 const struct inode_operations f2fs_dir_inode_operations = {
 	.create		= f2fs_create,
@@ -1034,8 +1098,7 @@ const struct inode_operations f2fs_dir_inode_operations = {
 
 const struct inode_operations f2fs_symlink_inode_operations = {
 	.readlink       = generic_readlink,
-	.follow_link    = f2fs_follow_link,
-	.put_link       = page_put_link,
+	.get_link       = f2fs_get_link,
 	.getattr	= f2fs_getattr,
 	.setattr	= f2fs_setattr,
 #ifdef CONFIG_F2FS_FS_XATTR
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 7bcbc6e9c40d..1a33de9d84b1 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -46,11 +46,11 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
 	 */
 	if (type == FREE_NIDS) {
 		mem_size = (nm_i->fcnt * sizeof(struct free_nid)) >>
-							PAGE_CACHE_SHIFT;
+							PAGE_SHIFT;
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
 	} else if (type == NAT_ENTRIES) {
 		mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >>
-							PAGE_CACHE_SHIFT;
+							PAGE_SHIFT;
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
 	} else if (type == DIRTY_DENTS) {
 		if (sbi->sb->s_bdi->wb.dirty_exceeded)
@@ -62,16 +62,17 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
 
 		for (i = 0; i <= UPDATE_INO; i++)
 			mem_size += (sbi->im[i].ino_num *
-				sizeof(struct ino_entry)) >> PAGE_CACHE_SHIFT;
+				sizeof(struct ino_entry)) >> PAGE_SHIFT;
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
 	} else if (type == EXTENT_CACHE) {
-		mem_size = (sbi->total_ext_tree * sizeof(struct extent_tree) +
+		mem_size = (atomic_read(&sbi->total_ext_tree) *
+				sizeof(struct extent_tree) +
 				atomic_read(&sbi->total_ext_node) *
-				sizeof(struct extent_node)) >> PAGE_CACHE_SHIFT;
+				sizeof(struct extent_node)) >> PAGE_SHIFT;
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
 	} else {
-		if (sbi->sb->s_bdi->wb.dirty_exceeded)
-			return false;
+		if (!sbi->sb->s_bdi->wb.dirty_exceeded)
+			return true;
 	}
 	return res;
 }
@@ -120,7 +121,7 @@ static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid)
 
 	src_addr = page_address(src_page);
 	dst_addr = page_address(dst_page);
-	memcpy(dst_addr, src_addr, PAGE_CACHE_SIZE);
+	memcpy(dst_addr, src_addr, PAGE_SIZE);
 	set_page_dirty(dst_page);
 	f2fs_put_page(src_page, 1);
 
@@ -256,18 +257,21 @@ static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid)
 	return new;
 }
 
-static void cache_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid,
+static void cache_nat_entry(struct f2fs_sb_info *sbi, nid_t nid,
 						struct f2fs_nat_entry *ne)
 {
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct nat_entry *e;
 
-	down_write(&nm_i->nat_tree_lock);
 	e = __lookup_nat_cache(nm_i, nid);
 	if (!e) {
 		e = grab_nat_entry(nm_i, nid);
 		node_info_from_raw_nat(&e->ni, ne);
+	} else {
+		f2fs_bug_on(sbi, nat_get_ino(e) != ne->ino ||
+				nat_get_blkaddr(e) != ne->block_addr ||
+				nat_get_version(e) != ne->version);
 	}
-	up_write(&nm_i->nat_tree_lock);
 }
 
 static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
@@ -355,7 +359,7 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
-	struct f2fs_summary_block *sum = curseg->sum_blk;
+	struct f2fs_journal *journal = curseg->journal;
 	nid_t start_nid = START_NID(nid);
 	struct f2fs_nat_block *nat_blk;
 	struct page *page = NULL;
@@ -372,21 +376,20 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
 		ni->ino = nat_get_ino(e);
 		ni->blk_addr = nat_get_blkaddr(e);
 		ni->version = nat_get_version(e);
-	}
-	up_read(&nm_i->nat_tree_lock);
-	if (e)
+		up_read(&nm_i->nat_tree_lock);
 		return;
+	}
 
 	memset(&ne, 0, sizeof(struct f2fs_nat_entry));
 
 	/* Check current segment summary */
-	mutex_lock(&curseg->curseg_mutex);
-	i = lookup_journal_in_cursum(sum, NAT_JOURNAL, nid, 0);
+	down_read(&curseg->journal_rwsem);
+	i = lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 0);
 	if (i >= 0) {
-		ne = nat_in_journal(sum, i);
+		ne = nat_in_journal(journal, i);
 		node_info_from_raw_nat(ni, &ne);
 	}
-	mutex_unlock(&curseg->curseg_mutex);
+	up_read(&curseg->journal_rwsem);
 	if (i >= 0)
 		goto cache;
 
@@ -397,18 +400,52 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
 	node_info_from_raw_nat(ni, &ne);
 	f2fs_put_page(page, 1);
 cache:
+	up_read(&nm_i->nat_tree_lock);
 	/* cache nat entry */
-	cache_nat_entry(NM_I(sbi), nid, &ne);
+	down_write(&nm_i->nat_tree_lock);
+	cache_nat_entry(sbi, nid, &ne);
+	up_write(&nm_i->nat_tree_lock);
+}
+
+pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs)
+{
+	const long direct_index = ADDRS_PER_INODE(dn->inode);
+	const long direct_blks = ADDRS_PER_BLOCK;
+	const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK;
+	unsigned int skipped_unit = ADDRS_PER_BLOCK;
+	int cur_level = dn->cur_level;
+	int max_level = dn->max_level;
+	pgoff_t base = 0;
+
+	if (!dn->max_level)
+		return pgofs + 1;
+
+	while (max_level-- > cur_level)
+		skipped_unit *= NIDS_PER_BLOCK;
+
+	switch (dn->max_level) {
+	case 3:
+		base += 2 * indirect_blks;
+	case 2:
+		base += 2 * direct_blks;
+	case 1:
+		base += direct_index;
+		break;
+	default:
+		f2fs_bug_on(F2FS_I_SB(dn->inode), 1);
+	}
+
+	return ((pgofs - base) / skipped_unit + 1) * skipped_unit + base;
 }
 
 /*
  * The maximum depth is four.
  * Offset[0] will have raw inode offset.
  */
-static int get_node_path(struct f2fs_inode_info *fi, long block,
+static int get_node_path(struct inode *inode, long block,
 				int offset[4], unsigned int noffset[4])
 {
-	const long direct_index = ADDRS_PER_INODE(fi);
+	const long direct_index = ADDRS_PER_INODE(inode);
 	const long direct_blks = ADDRS_PER_BLOCK;
 	const long dptrs_per_blk = NIDS_PER_BLOCK;
 	const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK;
@@ -493,10 +530,10 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
 	int offset[4];
 	unsigned int noffset[4];
 	nid_t nids[4];
-	int level, i;
+	int level, i = 0;
 	int err = 0;
 
-	level = get_node_path(F2FS_I(dn->inode), index, offset, noffset);
+	level = get_node_path(dn->inode, index, offset, noffset);
 
 	nids[0] = dn->inode->i_ino;
 	npage[0] = dn->inode_page;
@@ -583,6 +620,10 @@ release_pages:
 release_out:
 	dn->inode_page = NULL;
 	dn->node_page = NULL;
+	if (err == -ENOENT) {
+		dn->cur_level = i;
+		dn->max_level = level;
+	}
 	return err;
 }
 
@@ -676,7 +717,8 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs,
 			ret = truncate_dnode(&rdn);
 			if (ret < 0)
 				goto out_err;
-			set_nid(page, i, 0, false);
+			if (set_nid(page, i, 0, false))
+				dn->node_changed = true;
 		}
 	} else {
 		child_nofs = nofs + ofs * (NIDS_PER_BLOCK + 1) + 1;
@@ -689,7 +731,8 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs,
 			rdn.nid = child_nid;
 			ret = truncate_nodes(&rdn, child_nofs, 0, depth - 1);
 			if (ret == (NIDS_PER_BLOCK + 1)) {
-				set_nid(page, i, 0, false);
+				if (set_nid(page, i, 0, false))
+					dn->node_changed = true;
 				child_nofs += ret;
 			} else if (ret < 0 && ret != -ENOENT) {
 				goto out_err;
@@ -750,7 +793,8 @@ static int truncate_partial_nodes(struct dnode_of_data *dn,
 		err = truncate_dnode(dn);
 		if (err < 0)
 			goto fail;
-		set_nid(pages[idx], i, 0, false);
+		if (set_nid(pages[idx], i, 0, false))
+			dn->node_changed = true;
 	}
 
 	if (offset[idx + 1] == 0) {
@@ -787,7 +831,7 @@ int truncate_inode_blocks(struct inode *inode, pgoff_t from)
 
 	trace_f2fs_truncate_inode_blocks_enter(inode, from);
 
-	level = get_node_path(F2FS_I(inode), from, offset, noffset);
+	level = get_node_path(inode, from, offset, noffset);
 restart:
 	page = get_node_page(sbi, inode->i_ino);
 	if (IS_ERR(page)) {
@@ -856,7 +900,7 @@ skip_partial:
 				f2fs_put_page(page, 1);
 				goto restart;
 			}
-			f2fs_wait_on_page_writeback(page, NODE);
+			f2fs_wait_on_page_writeback(page, NODE, true);
 			ri->i_nid[offset[0] - NODE_DIR1_BLOCK] = 0;
 			set_page_dirty(page);
 			unlock_page(page);
@@ -971,11 +1015,12 @@ struct page *new_node_page(struct dnode_of_data *dn,
 	new_ni.ino = dn->inode->i_ino;
 	set_node_addr(sbi, &new_ni, NEW_ADDR, false);
 
-	f2fs_wait_on_page_writeback(page, NODE);
+	f2fs_wait_on_page_writeback(page, NODE, true);
 	fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true);
 	set_cold_node(dn->inode, page);
 	SetPageUptodate(page);
-	set_page_dirty(page);
+	if (set_page_dirty(page))
+		dn->node_changed = true;
 
 	if (f2fs_has_xattr_block(ofs))
 		F2FS_I(dn->inode)->i_xattr_nid = dn->nid;
@@ -1023,7 +1068,7 @@ static int read_node_page(struct page *page, int rw)
 	if (PageUptodate(page))
 		return LOCKED_PAGE;
 
-	fio.blk_addr = ni.blk_addr;
+	fio.new_blkaddr = fio.old_blkaddr = ni.blk_addr;
 	return f2fs_submit_page_bio(&fio);
 }
 
@@ -1035,12 +1080,15 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
 	struct page *apage;
 	int err;
 
-	apage = find_get_page(NODE_MAPPING(sbi), nid);
-	if (apage && PageUptodate(apage)) {
-		f2fs_put_page(apage, 0);
+	if (!nid)
+		return;
+	f2fs_bug_on(sbi, check_nid_range(sbi, nid));
+
+	rcu_read_lock();
+	apage = radix_tree_lookup(&NODE_MAPPING(sbi)->page_tree, nid);
+	rcu_read_unlock();
+	if (apage)
 		return;
-	}
-	f2fs_put_page(apage, 0);
 
 	apage = grab_cache_page(NODE_MAPPING(sbi), nid);
 	if (!apage)
@@ -1050,51 +1098,38 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
 	f2fs_put_page(apage, err ? 1 : 0);
 }
 
-struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid)
+/*
+ * readahead MAX_RA_NODE number of node pages.
+ */
+static void ra_node_pages(struct page *parent, int start)
 {
-	struct page *page;
-	int err;
-repeat:
-	page = grab_cache_page(NODE_MAPPING(sbi), nid);
-	if (!page)
-		return ERR_PTR(-ENOMEM);
+	struct f2fs_sb_info *sbi = F2FS_P_SB(parent);
+	struct blk_plug plug;
+	int i, end;
+	nid_t nid;
 
-	err = read_node_page(page, READ_SYNC);
-	if (err < 0) {
-		f2fs_put_page(page, 1);
-		return ERR_PTR(err);
-	} else if (err != LOCKED_PAGE) {
-		lock_page(page);
-	}
+	blk_start_plug(&plug);
 
-	if (unlikely(!PageUptodate(page) || nid != nid_of_node(page))) {
-		ClearPageUptodate(page);
-		f2fs_put_page(page, 1);
-		return ERR_PTR(-EIO);
-	}
-	if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
-		f2fs_put_page(page, 1);
-		goto repeat;
+	/* Then, try readahead for siblings of the desired node */
+	end = start + MAX_RA_NODE;
+	end = min(end, NIDS_PER_BLOCK);
+	for (i = start; i < end; i++) {
+		nid = get_nid(parent, i, false);
+		ra_node_page(sbi, nid);
 	}
-	return page;
+
+	blk_finish_plug(&plug);
 }
 
-/*
- * Return a locked page for the desired node page.
- * And, readahead MAX_RA_NODE number of node pages.
- */
-struct page *get_node_page_ra(struct page *parent, int start)
+static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
+					struct page *parent, int start)
 {
-	struct f2fs_sb_info *sbi = F2FS_P_SB(parent);
-	struct blk_plug plug;
 	struct page *page;
-	int err, i, end;
-	nid_t nid;
+	int err;
 
-	/* First, try getting the desired direct node. */
-	nid = get_nid(parent, start, false);
 	if (!nid)
 		return ERR_PTR(-ENOENT);
+	f2fs_bug_on(sbi, check_nid_range(sbi, nid));
 repeat:
 	page = grab_cache_page(NODE_MAPPING(sbi), nid);
 	if (!page)
@@ -1108,46 +1143,91 @@ repeat:
 		goto page_hit;
 	}
 
-	blk_start_plug(&plug);
-
-	/* Then, try readahead for siblings of the desired node */
-	end = start + MAX_RA_NODE;
-	end = min(end, NIDS_PER_BLOCK);
-	for (i = start + 1; i < end; i++) {
-		nid = get_nid(parent, i, false);
-		if (!nid)
-			continue;
-		ra_node_page(sbi, nid);
-	}
-
-	blk_finish_plug(&plug);
+	if (parent)
+		ra_node_pages(parent, start + 1);
 
 	lock_page(page);
+
+	if (unlikely(!PageUptodate(page))) {
+		f2fs_put_page(page, 1);
+		return ERR_PTR(-EIO);
+	}
 	if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
 		f2fs_put_page(page, 1);
 		goto repeat;
 	}
 page_hit:
-	if (unlikely(!PageUptodate(page))) {
-		f2fs_put_page(page, 1);
-		return ERR_PTR(-EIO);
-	}
+	f2fs_bug_on(sbi, nid != nid_of_node(page));
 	return page;
 }
 
+struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid)
+{
+	return __get_node_page(sbi, nid, NULL, 0);
+}
+
+struct page *get_node_page_ra(struct page *parent, int start)
+{
+	struct f2fs_sb_info *sbi = F2FS_P_SB(parent);
+	nid_t nid = get_nid(parent, start, false);
+
+	return __get_node_page(sbi, nid, parent, start);
+}
+
 void sync_inode_page(struct dnode_of_data *dn)
 {
+	int ret = 0;
+
 	if (IS_INODE(dn->node_page) || dn->inode_page == dn->node_page) {
-		update_inode(dn->inode, dn->node_page);
+		ret = update_inode(dn->inode, dn->node_page);
 	} else if (dn->inode_page) {
 		if (!dn->inode_page_locked)
 			lock_page(dn->inode_page);
-		update_inode(dn->inode, dn->inode_page);
+		ret = update_inode(dn->inode, dn->inode_page);
 		if (!dn->inode_page_locked)
 			unlock_page(dn->inode_page);
 	} else {
-		update_inode_page(dn->inode);
+		ret = update_inode_page(dn->inode);
 	}
+	dn->node_changed = ret ? true: false;
+}
+
+static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
+{
+	struct inode *inode;
+	struct page *page;
+
+	/* should flush inline_data before evict_inode */
+	inode = ilookup(sbi->sb, ino);
+	if (!inode)
+		return;
+
+	page = pagecache_get_page(inode->i_mapping, 0, FGP_NOWAIT, 0);
+	if (!page)
+		goto iput_out;
+
+	if (!trylock_page(page))
+		goto release_out;
+
+	if (!PageUptodate(page))
+		goto page_out;
+
+	if (!PageDirty(page))
+		goto page_out;
+
+	if (!clear_page_dirty_for_io(page))
+		goto page_out;
+
+	if (!f2fs_write_inline_data(inode, page))
+		inode_dec_dirty_pages(inode);
+	else
+		set_page_dirty(page);
+page_out:
+	unlock_page(page);
+release_out:
+	f2fs_put_page(page, 0);
+iput_out:
+	iput(inode);
 }
 
 int sync_node_pages(struct f2fs_sb_info *sbi, nid_t ino,
@@ -1156,13 +1236,13 @@ int sync_node_pages(struct f2fs_sb_info *sbi, nid_t ino,
 	pgoff_t index, end;
 	struct pagevec pvec;
 	int step = ino ? 2 : 0;
-	int nwritten = 0, wrote = 0;
+	int nwritten = 0;
 
 	pagevec_init(&pvec, 0);
 
 next_step:
 	index = 0;
-	end = LONG_MAX;
+	end = ULONG_MAX;
 
 	while (index <= end) {
 		int i, nr_pages;
@@ -1175,6 +1255,11 @@ next_step:
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 
+			if (unlikely(f2fs_cp_error(sbi))) {
+				pagevec_release(&pvec);
+				return -EIO;
+			}
+
 			/*
 			 * flushing sequence with step:
 			 * 0. indirect nodes
@@ -1194,6 +1279,7 @@ next_step:
 			 * If an fsync mode,
 			 * we should not skip writing node pages.
 			 */
+lock_node:
 			if (ino && ino_of_node(page) == ino)
 				lock_page(page);
 			else if (!trylock_page(page))
@@ -1212,6 +1298,17 @@ continue_unlock:
 				goto continue_unlock;
 			}
 
+			/* flush inline_data */
+			if (!ino && is_inline_node(page)) {
+				clear_inline_node(page);
+				unlock_page(page);
+				flush_inline_data(sbi, ino_of_node(page));
+				goto lock_node;
+			}
+
+			f2fs_wait_on_page_writeback(page, NODE, true);
+
+			BUG_ON(PageWriteback(page));
 			if (!clear_page_dirty_for_io(page))
 				goto continue_unlock;
 
@@ -1229,8 +1326,6 @@ continue_unlock:
 
 			if (NODE_MAPPING(sbi)->a_ops->writepage(page, wbc))
 				unlock_page(page);
-			else
-				wrote++;
 
 			if (--wbc->nr_to_write == 0)
 				break;
@@ -1248,15 +1343,12 @@ continue_unlock:
 		step++;
 		goto next_step;
 	}
-
-	if (wrote)
-		f2fs_submit_merged_bio(sbi, NODE, WRITE);
 	return nwritten;
 }
 
 int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino)
 {
-	pgoff_t index = 0, end = LONG_MAX;
+	pgoff_t index = 0, end = ULONG_MAX;
 	struct pagevec pvec;
 	int ret2 = 0, ret = 0;
 
@@ -1278,7 +1370,7 @@ int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino)
 				continue;
 
 			if (ino && ino_of_node(page) == ino) {
-				f2fs_wait_on_page_writeback(page, NODE);
+				f2fs_wait_on_page_writeback(page, NODE, true);
 				if (TestClearPageError(page))
 					ret = -EIO;
 			}
@@ -1317,8 +1409,6 @@ static int f2fs_write_node_page(struct page *page,
 	if (unlikely(f2fs_cp_error(sbi)))
 		goto redirty_out;
 
-	f2fs_wait_on_page_writeback(page, NODE);
-
 	/* get old block addr of this node page */
 	nid = nid_of_node(page);
 	f2fs_bug_on(sbi, page->index != nid);
@@ -1342,14 +1432,18 @@ static int f2fs_write_node_page(struct page *page,
 	}
 
 	set_page_writeback(page);
-	fio.blk_addr = ni.blk_addr;
+	fio.old_blkaddr = ni.blk_addr;
 	write_node_page(nid, &fio);
-	set_node_addr(sbi, &ni, fio.blk_addr, is_fsync_dnode(page));
+	set_node_addr(sbi, &ni, fio.new_blkaddr, is_fsync_dnode(page));
 	dec_page_count(sbi, F2FS_DIRTY_NODES);
 	up_read(&sbi->node_write);
-	unlock_page(page);
 
 	if (wbc->for_reclaim)
+		f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, NODE, WRITE);
+
+	unlock_page(page);
+
+	if (unlikely(f2fs_cp_error(sbi)))
 		f2fs_submit_merged_bio(sbi, NODE, WRITE);
 
 	return 0;
@@ -1365,8 +1459,6 @@ static int f2fs_write_node_pages(struct address_space *mapping,
 	struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
 	long diff;
 
-	trace_f2fs_writepages(mapping->host, wbc, NODE);
-
 	/* balancing f2fs's metadata in background */
 	f2fs_balance_fs_bg(sbi);
 
@@ -1374,6 +1466,8 @@ static int f2fs_write_node_pages(struct address_space *mapping,
 	if (get_pages(sbi, F2FS_DIRTY_NODES) < nr_pages_to_skip(sbi, NODE))
 		goto skip_write;
 
+	trace_f2fs_writepages(mapping->host, wbc, NODE);
+
 	diff = nr_pages_to_write(sbi, NODE, wbc);
 	wbc->sync_mode = WB_SYNC_NONE;
 	sync_node_pages(sbi, 0, wbc);
@@ -1382,6 +1476,7 @@ static int f2fs_write_node_pages(struct address_space *mapping,
 
 skip_write:
 	wbc->pages_skipped += get_pages(sbi, F2FS_DIRTY_NODES);
+	trace_f2fs_writepages(mapping->host, wbc, NODE);
 	return 0;
 }
 
@@ -1440,13 +1535,10 @@ static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
 
 	if (build) {
 		/* do not add allocated nids */
-		down_read(&nm_i->nat_tree_lock);
 		ne = __lookup_nat_cache(nm_i, nid);
-		if (ne &&
-			(!get_nat_flag(ne, IS_CHECKPOINTED) ||
+		if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) ||
 				nat_get_blkaddr(ne) != NULL_ADDR))
 			allocated = true;
-		up_read(&nm_i->nat_tree_lock);
 		if (allocated)
 			return 0;
 	}
@@ -1520,7 +1612,7 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
-	struct f2fs_summary_block *sum = curseg->sum_blk;
+	struct f2fs_journal *journal = curseg->journal;
 	int i = 0;
 	nid_t nid = nm_i->next_scan_nid;
 
@@ -1532,6 +1624,8 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
 	ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES,
 							META_NAT, true);
 
+	down_read(&nm_i->nat_tree_lock);
+
 	while (1) {
 		struct page *page = get_current_nat_page(sbi, nid);
 
@@ -1550,16 +1644,19 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
 	nm_i->next_scan_nid = nid;
 
 	/* find free nids from current sum_pages */
-	mutex_lock(&curseg->curseg_mutex);
-	for (i = 0; i < nats_in_cursum(sum); i++) {
-		block_t addr = le32_to_cpu(nat_in_journal(sum, i).block_addr);
-		nid = le32_to_cpu(nid_in_journal(sum, i));
+	down_read(&curseg->journal_rwsem);
+	for (i = 0; i < nats_in_cursum(journal); i++) {
+		block_t addr;
+
+		addr = le32_to_cpu(nat_in_journal(journal, i).block_addr);
+		nid = le32_to_cpu(nid_in_journal(journal, i));
 		if (addr == NULL_ADDR)
 			add_free_nid(sbi, nid, true);
 		else
 			remove_free_nid(nm_i, nid);
 	}
-	mutex_unlock(&curseg->curseg_mutex);
+	up_read(&curseg->journal_rwsem);
+	up_read(&nm_i->nat_tree_lock);
 
 	ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid),
 					nm_i->ra_nid_pages, META_NAT, false);
@@ -1582,8 +1679,6 @@ retry:
 
 	/* We should not use stale free nids created by build_free_nids */
 	if (nm_i->fcnt && !on_build_free_nids(nm_i)) {
-		struct node_info ni;
-
 		f2fs_bug_on(sbi, list_empty(&nm_i->free_nid_list));
 		list_for_each_entry(i, &nm_i->free_nid_list, list)
 			if (i->state == NID_NEW)
@@ -1594,13 +1689,6 @@ retry:
 		i->state = NID_ALLOC;
 		nm_i->fcnt--;
 		spin_unlock(&nm_i->free_nid_list_lock);
-
-		/* check nid is allocated already */
-		get_node_info(sbi, *nid, &ni);
-		if (ni.blk_addr != NULL_ADDR) {
-			alloc_nid_done(sbi, *nid);
-			goto retry;
-		}
 		return true;
 	}
 	spin_unlock(&nm_i->free_nid_list_lock);
@@ -1703,7 +1791,7 @@ void recover_inline_xattr(struct inode *inode, struct page *page)
 	src_addr = inline_xattr_addr(page);
 	inline_size = inline_xattr_size(inode);
 
-	f2fs_wait_on_page_writeback(ipage, NODE);
+	f2fs_wait_on_page_writeback(ipage, NODE, true);
 	memcpy(dst_addr, src_addr, inline_size);
 update_inode:
 	update_inode(inode, ipage);
@@ -1831,28 +1919,26 @@ static void remove_nats_in_journal(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
-	struct f2fs_summary_block *sum = curseg->sum_blk;
+	struct f2fs_journal *journal = curseg->journal;
 	int i;
 
-	mutex_lock(&curseg->curseg_mutex);
-	for (i = 0; i < nats_in_cursum(sum); i++) {
+	down_write(&curseg->journal_rwsem);
+	for (i = 0; i < nats_in_cursum(journal); i++) {
 		struct nat_entry *ne;
 		struct f2fs_nat_entry raw_ne;
-		nid_t nid = le32_to_cpu(nid_in_journal(sum, i));
+		nid_t nid = le32_to_cpu(nid_in_journal(journal, i));
 
-		raw_ne = nat_in_journal(sum, i);
+		raw_ne = nat_in_journal(journal, i);
 
-		down_write(&nm_i->nat_tree_lock);
 		ne = __lookup_nat_cache(nm_i, nid);
 		if (!ne) {
 			ne = grab_nat_entry(nm_i, nid);
 			node_info_from_raw_nat(&ne->ni, &raw_ne);
 		}
 		__set_nat_cache_dirty(nm_i, ne);
-		up_write(&nm_i->nat_tree_lock);
 	}
-	update_nats_in_cursum(sum, -i);
-	mutex_unlock(&curseg->curseg_mutex);
+	update_nats_in_cursum(journal, -i);
+	up_write(&curseg->journal_rwsem);
 }
 
 static void __adjust_nat_entry_set(struct nat_entry_set *nes,
@@ -1877,24 +1963,23 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
 					struct nat_entry_set *set)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
-	struct f2fs_summary_block *sum = curseg->sum_blk;
+	struct f2fs_journal *journal = curseg->journal;
 	nid_t start_nid = set->set * NAT_ENTRY_PER_BLOCK;
 	bool to_journal = true;
 	struct f2fs_nat_block *nat_blk;
 	struct nat_entry *ne, *cur;
 	struct page *page = NULL;
-	struct f2fs_nm_info *nm_i = NM_I(sbi);
 
 	/*
 	 * there are two steps to flush nat entries:
 	 * #1, flush nat entries to journal in current hot data summary block.
 	 * #2, flush nat entries to nat page.
 	 */
-	if (!__has_cursum_space(sum, set->entry_cnt, NAT_JOURNAL))
+	if (!__has_cursum_space(journal, set->entry_cnt, NAT_JOURNAL))
 		to_journal = false;
 
 	if (to_journal) {
-		mutex_lock(&curseg->curseg_mutex);
+		down_write(&curseg->journal_rwsem);
 	} else {
 		page = get_next_nat_page(sbi, start_nid);
 		nat_blk = page_address(page);
@@ -1911,35 +1996,29 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
 			continue;
 
 		if (to_journal) {
-			offset = lookup_journal_in_cursum(sum,
+			offset = lookup_journal_in_cursum(journal,
 							NAT_JOURNAL, nid, 1);
 			f2fs_bug_on(sbi, offset < 0);
-			raw_ne = &nat_in_journal(sum, offset);
-			nid_in_journal(sum, offset) = cpu_to_le32(nid);
+			raw_ne = &nat_in_journal(journal, offset);
+			nid_in_journal(journal, offset) = cpu_to_le32(nid);
 		} else {
 			raw_ne = &nat_blk->entries[nid - start_nid];
 		}
 		raw_nat_from_node_info(raw_ne, &ne->ni);
-
-		down_write(&NM_I(sbi)->nat_tree_lock);
 		nat_reset_flag(ne);
 		__clear_nat_cache_dirty(NM_I(sbi), ne);
-		up_write(&NM_I(sbi)->nat_tree_lock);
-
 		if (nat_get_blkaddr(ne) == NULL_ADDR)
 			add_free_nid(sbi, nid, false);
 	}
 
 	if (to_journal)
-		mutex_unlock(&curseg->curseg_mutex);
+		up_write(&curseg->journal_rwsem);
 	else
 		f2fs_put_page(page, 1);
 
 	f2fs_bug_on(sbi, set->entry_cnt);
 
-	down_write(&nm_i->nat_tree_lock);
 	radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set);
-	up_write(&nm_i->nat_tree_lock);
 	kmem_cache_free(nat_entry_set_slab, set);
 }
 
@@ -1950,7 +2029,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
-	struct f2fs_summary_block *sum = curseg->sum_blk;
+	struct f2fs_journal *journal = curseg->journal;
 	struct nat_entry_set *setvec[SETVEC_SIZE];
 	struct nat_entry_set *set, *tmp;
 	unsigned int found;
@@ -1959,29 +2038,32 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 
 	if (!nm_i->dirty_nat_cnt)
 		return;
+
+	down_write(&nm_i->nat_tree_lock);
+
 	/*
 	 * if there are no enough space in journal to store dirty nat
 	 * entries, remove all entries from journal and merge them
 	 * into nat entry set.
 	 */
-	if (!__has_cursum_space(sum, nm_i->dirty_nat_cnt, NAT_JOURNAL))
+	if (!__has_cursum_space(journal, nm_i->dirty_nat_cnt, NAT_JOURNAL))
 		remove_nats_in_journal(sbi);
 
-	down_write(&nm_i->nat_tree_lock);
 	while ((found = __gang_lookup_nat_set(nm_i,
 					set_idx, SETVEC_SIZE, setvec))) {
 		unsigned idx;
 		set_idx = setvec[found - 1]->set + 1;
 		for (idx = 0; idx < found; idx++)
 			__adjust_nat_entry_set(setvec[idx], &sets,
-							MAX_NAT_JENTRIES(sum));
+						MAX_NAT_JENTRIES(journal));
 	}
-	up_write(&nm_i->nat_tree_lock);
 
 	/* flush dirty nats in nat entry set */
 	list_for_each_entry_safe(set, tmp, &sets, set_list)
 		__flush_nat_entry_set(sbi, set);
 
+	up_write(&nm_i->nat_tree_lock);
+
 	f2fs_bug_on(sbi, nm_i->dirty_nat_cnt);
 }
 
@@ -2006,6 +2088,7 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
 	nm_i->nat_cnt = 0;
 	nm_i->ram_thresh = DEF_RAM_THRESHOLD;
 	nm_i->ra_nid_pages = DEF_RA_NID_PAGES;
+	nm_i->dirty_nats_ratio = DEF_DIRTY_NAT_RATIO_THRESHOLD;
 
 	INIT_RADIX_TREE(&nm_i->free_nid_root, GFP_ATOMIC);
 	INIT_LIST_HEAD(&nm_i->free_nid_list);
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index e4fffd2d98c4..1f4f9d4569d9 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -25,6 +25,9 @@
 /* control the memory footprint threshold (10MB per 1GB ram) */
 #define DEF_RAM_THRESHOLD	10
 
+/* control dirty nats ratio threshold (default: 10% over max nid count) */
+#define DEF_DIRTY_NAT_RATIO_THRESHOLD		10
+
 /* vector size for gang look-up from nat cache that consists of radix tree */
 #define NATVEC_SIZE	64
 #define SETVEC_SIZE	32
@@ -117,6 +120,12 @@ static inline void raw_nat_from_node_info(struct f2fs_nat_entry *raw_ne,
 	raw_ne->version = ni->version;
 }
 
+static inline bool excess_dirty_nats(struct f2fs_sb_info *sbi)
+{
+	return NM_I(sbi)->dirty_nat_cnt >= NM_I(sbi)->max_nid *
+					NM_I(sbi)->dirty_nats_ratio / 100;
+}
+
 enum mem_type {
 	FREE_NIDS,	/* indicates the free nid list */
 	NAT_ENTRIES,	/* indicates the cached nat entry */
@@ -183,7 +192,7 @@ static inline pgoff_t current_nat_addr(struct f2fs_sb_info *sbi, nid_t start)
 
 	block_addr = (pgoff_t)(nm_i->nat_blkaddr +
 		(seg_off << sbi->log_blocks_per_seg << 1) +
-		(block_off & ((1 << sbi->log_blocks_per_seg) - 1)));
+		(block_off & (sbi->blocks_per_seg - 1)));
 
 	if (f2fs_test_bit(block_off, nm_i->nat_bitmap))
 		block_addr += sbi->blocks_per_seg;
@@ -317,17 +326,17 @@ static inline bool IS_DNODE(struct page *node_page)
 	return true;
 }
 
-static inline void set_nid(struct page *p, int off, nid_t nid, bool i)
+static inline int set_nid(struct page *p, int off, nid_t nid, bool i)
 {
 	struct f2fs_node *rn = F2FS_NODE(p);
 
-	f2fs_wait_on_page_writeback(p, NODE);
+	f2fs_wait_on_page_writeback(p, NODE, true);
 
 	if (i)
 		rn->i.i_nid[off - NODE_DIR1_BLOCK] = cpu_to_le32(nid);
 	else
 		rn->in.nid[off] = cpu_to_le32(nid);
-	set_page_dirty(p);
+	return set_page_dirty(p);
 }
 
 static inline nid_t get_nid(struct page *p, int off, bool i)
@@ -370,6 +379,21 @@ static inline int is_node(struct page *page, int type)
 #define is_fsync_dnode(page)	is_node(page, FSYNC_BIT_SHIFT)
 #define is_dent_dnode(page)	is_node(page, DENT_BIT_SHIFT)
 
+static inline int is_inline_node(struct page *page)
+{
+	return PageChecked(page);
+}
+
+static inline void set_inline_node(struct page *page)
+{
+	SetPageChecked(page);
+}
+
+static inline void clear_inline_node(struct page *page)
+{
+	ClearPageChecked(page);
+}
+
 static inline void set_cold_node(struct inode *inode, struct page *page)
 {
 	struct f2fs_node *rn = F2FS_NODE(page);
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index cbf74f47cce8..011942f94d64 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -168,6 +168,32 @@ static void recover_inode(struct inode *inode, struct page *page)
 			ino_of_node(page), name);
 }
 
+static bool is_same_inode(struct inode *inode, struct page *ipage)
+{
+	struct f2fs_inode *ri = F2FS_INODE(ipage);
+	struct timespec disk;
+
+	if (!IS_INODE(ipage))
+		return true;
+
+	disk.tv_sec = le64_to_cpu(ri->i_ctime);
+	disk.tv_nsec = le32_to_cpu(ri->i_ctime_nsec);
+	if (timespec_compare(&inode->i_ctime, &disk) > 0)
+		return false;
+
+	disk.tv_sec = le64_to_cpu(ri->i_atime);
+	disk.tv_nsec = le32_to_cpu(ri->i_atime_nsec);
+	if (timespec_compare(&inode->i_atime, &disk) > 0)
+		return false;
+
+	disk.tv_sec = le64_to_cpu(ri->i_mtime);
+	disk.tv_nsec = le32_to_cpu(ri->i_mtime_nsec);
+	if (timespec_compare(&inode->i_mtime, &disk) > 0)
+		return false;
+
+	return true;
+}
+
 static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 {
 	unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
@@ -197,7 +223,10 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 			goto next;
 
 		entry = get_fsync_inode(head, ino_of_node(page));
-		if (!entry) {
+		if (entry) {
+			if (!is_same_inode(entry->inode, page))
+				goto next;
+		} else {
 			if (IS_INODE(page) && is_dent_dnode(page)) {
 				err = recover_inode_page(sbi, page);
 				if (err)
@@ -321,8 +350,7 @@ got_it:
 		inode = dn->inode;
 	}
 
-	bidx = start_bidx_of_node(offset, F2FS_I(inode)) +
-			le16_to_cpu(sum.ofs_in_node);
+	bidx = start_bidx_of_node(offset, inode) + le16_to_cpu(sum.ofs_in_node);
 
 	/*
 	 * if inode page is locked, unlock temporarily, but its reference
@@ -357,10 +385,9 @@ truncate_out:
 static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 					struct page *page, block_t blkaddr)
 {
-	struct f2fs_inode_info *fi = F2FS_I(inode);
-	unsigned int start, end;
 	struct dnode_of_data dn;
 	struct node_info ni;
+	unsigned int start, end;
 	int err = 0, recovered = 0;
 
 	/* step 1: recover xattr */
@@ -380,8 +407,8 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 		goto out;
 
 	/* step 3: recover data indices */
-	start = start_bidx_of_node(ofs_of_node(page), fi);
-	end = start + ADDRS_PER_PAGE(page, fi);
+	start = start_bidx_of_node(ofs_of_node(page), inode);
+	end = start + ADDRS_PER_PAGE(page, inode);
 
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
 
@@ -389,7 +416,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 	if (err)
 		goto out;
 
-	f2fs_wait_on_page_writeback(dn.node_page, NODE);
+	f2fs_wait_on_page_writeback(dn.node_page, NODE, true);
 
 	get_node_info(sbi, dn.nid, &ni);
 	f2fs_bug_on(sbi, ni.ino != ino_of_node(page));
@@ -438,7 +465,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 
 			/* write dummy data page */
 			f2fs_replace_block(sbi, &dn, src, dest,
-							ni.version, false);
+						ni.version, false, false);
 			recovered++;
 		}
 	}
@@ -459,8 +486,7 @@ out:
 	return err;
 }
 
-static int recover_data(struct f2fs_sb_info *sbi,
-				struct list_head *head, int type)
+static int recover_data(struct f2fs_sb_info *sbi, struct list_head *head)
 {
 	unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
 	struct curseg_info *curseg;
@@ -469,7 +495,7 @@ static int recover_data(struct f2fs_sb_info *sbi,
 	block_t blkaddr;
 
 	/* get node pages in the current segment */
-	curseg = CURSEG_I(sbi, type);
+	curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
 	blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
 
 	while (1) {
@@ -556,7 +582,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
 	need_writecp = true;
 
 	/* step #2: recover data */
-	err = recover_data(sbi, &inode_list, CURSEG_WARM_NODE);
+	err = recover_data(sbi, &inode_list);
 	if (!err)
 		f2fs_bug_on(sbi, !list_empty(&inode_list));
 out:
@@ -565,7 +591,7 @@ out:
 
 	/* truncate meta pages to be used by the recovery */
 	truncate_inode_pages_range(META_MAPPING(sbi),
-			(loff_t)MAIN_BLKADDR(sbi) << PAGE_CACHE_SHIFT, -1);
+			(loff_t)MAIN_BLKADDR(sbi) << PAGE_SHIFT, -1);
 
 	if (err) {
 		truncate_inode_pages_final(NODE_MAPPING(sbi));
@@ -595,7 +621,7 @@ out:
 			.reason = CP_RECOVERY,
 		};
 		mutex_unlock(&sbi->cp_mutex);
-		write_checkpoint(sbi, &cpc);
+		err = write_checkpoint(sbi, &cpc);
 	} else {
 		mutex_unlock(&sbi->cp_mutex);
 	}
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index f77b3258454a..540669d6978e 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -86,6 +86,7 @@ static inline unsigned long __reverse_ffs(unsigned long word)
 /*
  * __find_rev_next(_zero)_bit is copied from lib/find_next_bit.c because
  * f2fs_set_bit makes MSB and LSB reversed in a byte.
+ * @size must be integral times of unsigned long.
  * Example:
  *                             MSB <--> LSB
  *   f2fs_set_bit(0, bitmap) => 1000 0000
@@ -95,94 +96,73 @@ static unsigned long __find_rev_next_bit(const unsigned long *addr,
 			unsigned long size, unsigned long offset)
 {
 	const unsigned long *p = addr + BIT_WORD(offset);
-	unsigned long result = offset & ~(BITS_PER_LONG - 1);
+	unsigned long result = size;
 	unsigned long tmp;
 
 	if (offset >= size)
 		return size;
 
-	size -= result;
+	size -= (offset & ~(BITS_PER_LONG - 1));
 	offset %= BITS_PER_LONG;
-	if (!offset)
-		goto aligned;
-
-	tmp = __reverse_ulong((unsigned char *)p);
-	tmp &= ~0UL >> offset;
-
-	if (size < BITS_PER_LONG)
-		goto found_first;
-	if (tmp)
-		goto found_middle;
-
-	size -= BITS_PER_LONG;
-	result += BITS_PER_LONG;
-	p++;
-aligned:
-	while (size & ~(BITS_PER_LONG-1)) {
+
+	while (1) {
+		if (*p == 0)
+			goto pass;
+
 		tmp = __reverse_ulong((unsigned char *)p);
+
+		tmp &= ~0UL >> offset;
+		if (size < BITS_PER_LONG)
+			tmp &= (~0UL << (BITS_PER_LONG - size));
 		if (tmp)
-			goto found_middle;
-		result += BITS_PER_LONG;
+			goto found;
+pass:
+		if (size <= BITS_PER_LONG)
+			break;
 		size -= BITS_PER_LONG;
+		offset = 0;
 		p++;
 	}
-	if (!size)
-		return result;
-
-	tmp = __reverse_ulong((unsigned char *)p);
-found_first:
-	tmp &= (~0UL << (BITS_PER_LONG - size));
-	if (!tmp)		/* Are any bits set? */
-		return result + size;   /* Nope. */
-found_middle:
-	return result + __reverse_ffs(tmp);
+	return result;
+found:
+	return result - size + __reverse_ffs(tmp);
 }
 
 static unsigned long __find_rev_next_zero_bit(const unsigned long *addr,
 			unsigned long size, unsigned long offset)
 {
 	const unsigned long *p = addr + BIT_WORD(offset);
-	unsigned long result = offset & ~(BITS_PER_LONG - 1);
+	unsigned long result = size;
 	unsigned long tmp;
 
 	if (offset >= size)
 		return size;
 
-	size -= result;
+	size -= (offset & ~(BITS_PER_LONG - 1));
 	offset %= BITS_PER_LONG;
-	if (!offset)
-		goto aligned;
-
-	tmp = __reverse_ulong((unsigned char *)p);
-	tmp |= ~((~0UL << offset) >> offset);
-
-	if (size < BITS_PER_LONG)
-		goto found_first;
-	if (tmp != ~0UL)
-		goto found_middle;
-
-	size -= BITS_PER_LONG;
-	result += BITS_PER_LONG;
-	p++;
-aligned:
-	while (size & ~(BITS_PER_LONG - 1)) {
+
+	while (1) {
+		if (*p == ~0UL)
+			goto pass;
+
 		tmp = __reverse_ulong((unsigned char *)p);
+
+		if (offset)
+			tmp |= ~0UL << (BITS_PER_LONG - offset);
+		if (size < BITS_PER_LONG)
+			tmp |= ~0UL >> size;
 		if (tmp != ~0UL)
-			goto found_middle;
-		result += BITS_PER_LONG;
+			goto found;
+pass:
+		if (size <= BITS_PER_LONG)
+			break;
 		size -= BITS_PER_LONG;
+		offset = 0;
 		p++;
 	}
-	if (!size)
-		return result;
-
-	tmp = __reverse_ulong((unsigned char *)p);
-found_first:
-	tmp |= ~(~0UL << (BITS_PER_LONG - size));
-	if (tmp == ~0UL)	/* Are any bits zero? */
-		return result + size;   /* Nope. */
-found_middle:
-	return result + __reverse_ffz(tmp);
+	return result;
+found:
+	return result - size + __reverse_ffz(tmp);
 }
 
 void register_inmem_page(struct inode *inode, struct page *page)
@@ -211,69 +191,145 @@ void register_inmem_page(struct inode *inode, struct page *page)
 	trace_f2fs_register_inmem_page(page, INMEM);
 }
 
-int commit_inmem_pages(struct inode *inode, bool abort)
+static int __revoke_inmem_pages(struct inode *inode,
+				struct list_head *head, bool drop, bool recover)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct inmem_pages *cur, *tmp;
+	int err = 0;
+
+	list_for_each_entry_safe(cur, tmp, head, list) {
+		struct page *page = cur->page;
+
+		if (drop)
+			trace_f2fs_commit_inmem_page(page, INMEM_DROP);
+
+		lock_page(page);
+
+		if (recover) {
+			struct dnode_of_data dn;
+			struct node_info ni;
+
+			trace_f2fs_commit_inmem_page(page, INMEM_REVOKE);
+
+			set_new_dnode(&dn, inode, NULL, NULL, 0);
+			if (get_dnode_of_data(&dn, page->index, LOOKUP_NODE)) {
+				err = -EAGAIN;
+				goto next;
+			}
+			get_node_info(sbi, dn.nid, &ni);
+			f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
+					cur->old_addr, ni.version, true, true);
+			f2fs_put_dnode(&dn);
+		}
+next:
+		ClearPageUptodate(page);
+		set_page_private(page, 0);
+		ClearPageUptodate(page);
+		f2fs_put_page(page, 1);
+
+		list_del(&cur->list);
+		kmem_cache_free(inmem_entry_slab, cur);
+		dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
+	}
+	return err;
+}
+
+void drop_inmem_pages(struct inode *inode)
+{
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+
+	mutex_lock(&fi->inmem_lock);
+	__revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
+	mutex_unlock(&fi->inmem_lock);
+}
+
+static int __commit_inmem_pages(struct inode *inode,
+					struct list_head *revoke_list)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct inmem_pages *cur, *tmp;
-	bool submit_bio = false;
 	struct f2fs_io_info fio = {
 		.sbi = sbi,
 		.type = DATA,
 		.rw = WRITE_SYNC | REQ_PRIO,
 		.encrypted_page = NULL,
 	};
+	bool submit_bio = false;
 	int err = 0;
 
-	/*
-	 * The abort is true only when f2fs_evict_inode is called.
-	 * Basically, the f2fs_evict_inode doesn't produce any data writes, so
-	 * that we don't need to call f2fs_balance_fs.
-	 * Otherwise, f2fs_gc in f2fs_balance_fs can wait forever until this
-	 * inode becomes free by iget_locked in f2fs_iget.
-	 */
-	if (!abort) {
-		f2fs_balance_fs(sbi);
-		f2fs_lock_op(sbi);
-	}
-
-	mutex_lock(&fi->inmem_lock);
 	list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) {
-		lock_page(cur->page);
-		if (!abort) {
-			if (cur->page->mapping == inode->i_mapping) {
-				set_page_dirty(cur->page);
-				f2fs_wait_on_page_writeback(cur->page, DATA);
-				if (clear_page_dirty_for_io(cur->page))
-					inode_dec_dirty_pages(inode);
-				trace_f2fs_commit_inmem_page(cur->page, INMEM);
-				fio.page = cur->page;
-				err = do_write_data_page(&fio);
-				if (err) {
-					unlock_page(cur->page);
-					break;
-				}
-				clear_cold_data(cur->page);
-				submit_bio = true;
+		struct page *page = cur->page;
+
+		lock_page(page);
+		if (page->mapping == inode->i_mapping) {
+			trace_f2fs_commit_inmem_page(page, INMEM);
+
+			set_page_dirty(page);
+			f2fs_wait_on_page_writeback(page, DATA, true);
+			if (clear_page_dirty_for_io(page))
+				inode_dec_dirty_pages(inode);
+
+			fio.page = page;
+			err = do_write_data_page(&fio);
+			if (err) {
+				unlock_page(page);
+				break;
 			}
-		} else {
-			trace_f2fs_commit_inmem_page(cur->page, INMEM_DROP);
+
+			/* record old blkaddr for revoking */
+			cur->old_addr = fio.old_blkaddr;
+
+			clear_cold_data(page);
+			submit_bio = true;
 		}
-		set_page_private(cur->page, 0);
-		ClearPagePrivate(cur->page);
-		f2fs_put_page(cur->page, 1);
+		unlock_page(page);
+		list_move_tail(&cur->list, revoke_list);
+	}
 
-		list_del(&cur->list);
-		kmem_cache_free(inmem_entry_slab, cur);
-		dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
+	if (submit_bio)
+		f2fs_submit_merged_bio_cond(sbi, inode, NULL, 0, DATA, WRITE);
+
+	if (!err)
+		__revoke_inmem_pages(inode, revoke_list, false, false);
+
+	return err;
+}
+
+int commit_inmem_pages(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+	struct list_head revoke_list;
+	int err;
+
+	INIT_LIST_HEAD(&revoke_list);
+	f2fs_balance_fs(sbi, true);
+	f2fs_lock_op(sbi);
+
+	mutex_lock(&fi->inmem_lock);
+	err = __commit_inmem_pages(inode, &revoke_list);
+	if (err) {
+		int ret;
+		/*
+		 * try to revoke all committed pages, but still we could fail
+		 * due to no memory or other reason, if that happened, EAGAIN
+		 * will be returned, which means in such case, transaction is
+		 * already not integrity, caller should use journal to do the
+		 * recovery or rewrite & commit last transaction. For other
+		 * error number, revoking was done by filesystem itself.
+		 */
+		ret = __revoke_inmem_pages(inode, &revoke_list, false, true);
+		if (ret)
+			err = ret;
+
+		/* drop all uncommitted pages */
+		__revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
 	}
 	mutex_unlock(&fi->inmem_lock);
 
-	if (!abort) {
-		f2fs_unlock_op(sbi);
-		if (submit_bio)
-			f2fs_submit_merged_bio(sbi, DATA, WRITE);
-	}
+	f2fs_unlock_op(sbi);
 	return err;
 }
 
@@ -281,8 +337,10 @@ int commit_inmem_pages(struct inode *inode, bool abort)
  * This function balances dirty node and dentry pages.
  * In addition, it controls garbage collection.
  */
-void f2fs_balance_fs(struct f2fs_sb_info *sbi)
+void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
 {
+	if (!need)
+		return;
 	/*
 	 * We should do GC or end up with checkpoint, if there are so many dirty
 	 * dir/node pages without enough free segments.
@@ -308,10 +366,20 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 
 	/* checkpoint is the only way to shrink partial cached entries */
 	if (!available_free_memory(sbi, NAT_ENTRIES) ||
-			excess_prefree_segs(sbi) ||
 			!available_free_memory(sbi, INO_ENTRIES) ||
-			jiffies > sbi->cp_expires)
+			excess_prefree_segs(sbi) ||
+			excess_dirty_nats(sbi) ||
+			(is_idle(sbi) && f2fs_time_over(sbi, CP_TIME))) {
+		if (test_opt(sbi, DATA_FLUSH)) {
+			struct blk_plug plug;
+
+			blk_start_plug(&plug);
+			sync_dirty_inodes(sbi, FILE_INODE);
+			blk_finish_plug(&plug);
+		}
 		f2fs_sync_fs(sbi->sb, true);
+		stat_inc_bg_cp_count(sbi->stat_info);
+	}
 }
 
 static int issue_flush_thread(void *data)
@@ -515,7 +583,7 @@ static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
 
 bool discard_next_dnode(struct f2fs_sb_info *sbi, block_t blkaddr)
 {
-	int err = -ENOTSUPP;
+	int err = -EOPNOTSUPP;
 
 	if (test_opt(sbi, DISCARD)) {
 		struct seg_entry *se = get_seg_entry(sbi,
@@ -817,12 +885,12 @@ int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra)
 		}
 	}
 
-	sum_in_page = (PAGE_CACHE_SIZE - 2 * SUM_JOURNAL_SIZE -
+	sum_in_page = (PAGE_SIZE - 2 * SUM_JOURNAL_SIZE -
 			SUM_FOOTER_SIZE) / SUMMARY_SIZE;
 	if (valid_sum_count <= sum_in_page)
 		return 1;
 	else if ((valid_sum_count - sum_in_page) <=
-		(PAGE_CACHE_SIZE - SUM_FOOTER_SIZE) / SUMMARY_SIZE)
+		(PAGE_SIZE - SUM_FOOTER_SIZE) / SUMMARY_SIZE)
 		return 2;
 	return 3;
 }
@@ -841,9 +909,9 @@ void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr)
 	void *dst = page_address(page);
 
 	if (src)
-		memcpy(dst, src, PAGE_CACHE_SIZE);
+		memcpy(dst, src, PAGE_SIZE);
 	else
-		memset(dst, 0, PAGE_CACHE_SIZE);
+		memset(dst, 0, PAGE_SIZE);
 	set_page_dirty(page);
 	f2fs_put_page(page, 1);
 }
@@ -854,6 +922,31 @@ static void write_sum_page(struct f2fs_sb_info *sbi,
 	update_meta_page(sbi, (void *)sum_blk, blk_addr);
 }
 
+static void write_current_sum_page(struct f2fs_sb_info *sbi,
+						int type, block_t blk_addr)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	struct page *page = grab_meta_page(sbi, blk_addr);
+	struct f2fs_summary_block *src = curseg->sum_blk;
+	struct f2fs_summary_block *dst;
+
+	dst = (struct f2fs_summary_block *)page_address(page);
+
+	mutex_lock(&curseg->curseg_mutex);
+
+	down_read(&curseg->journal_rwsem);
+	memcpy(&dst->journal, curseg->journal, SUM_JOURNAL_SIZE);
+	up_read(&curseg->journal_rwsem);
+
+	memcpy(dst->entries, src->entries, SUM_ENTRY_SIZE);
+	memcpy(&dst->footer, &src->footer, SUM_FOOTER_SIZE);
+
+	mutex_unlock(&curseg->curseg_mutex);
+
+	set_page_dirty(page);
+	f2fs_put_page(page, 1);
+}
+
 static int is_next_segment_free(struct f2fs_sb_info *sbi, int type)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
@@ -886,9 +979,8 @@ static void get_new_segment(struct f2fs_sb_info *sbi,
 
 	if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) {
 		segno = find_next_zero_bit(free_i->free_segmap,
-					MAIN_SEGS(sbi), *newseg + 1);
-		if (segno - *newseg < sbi->segs_per_sec -
-					(*newseg % sbi->segs_per_sec))
+				(hint + 1) * sbi->segs_per_sec, *newseg + 1);
+		if (segno < (hint + 1) * sbi->segs_per_sec)
 			goto got_it;
 	}
 find_other_zone:
@@ -1134,6 +1226,7 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 	__u64 end = start + F2FS_BYTES_TO_BLK(range->len) - 1;
 	unsigned int start_segno, end_segno;
 	struct cp_control cpc;
+	int err = 0;
 
 	if (start >= MAX_BLKADDR(sbi) || range->len < sbi->blocksize)
 		return -EINVAL;
@@ -1164,12 +1257,12 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 				sbi->segs_per_sec) - 1, end_segno);
 
 		mutex_lock(&sbi->gc_mutex);
-		write_checkpoint(sbi, &cpc);
+		err = write_checkpoint(sbi, &cpc);
 		mutex_unlock(&sbi->gc_mutex);
 	}
 out:
 	range->len = F2FS_BLK_TO_BYTES(cpc.trimmed);
-	return 0;
+	return err;
 }
 
 static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type)
@@ -1292,8 +1385,8 @@ static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
 {
 	int type = __get_segment_type(fio->page, fio->type);
 
-	allocate_data_block(fio->sbi, fio->page, fio->blk_addr,
-					&fio->blk_addr, sum, type);
+	allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
+					&fio->new_blkaddr, sum, type);
 
 	/* writeout dirty page into bdev */
 	f2fs_submit_page_mbio(fio);
@@ -1305,7 +1398,8 @@ void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
 		.sbi = sbi,
 		.type = META,
 		.rw = WRITE_SYNC | REQ_META | REQ_PRIO,
-		.blk_addr = page->index,
+		.old_blkaddr = page->index,
+		.new_blkaddr = page->index,
 		.page = page,
 		.encrypted_page = NULL,
 	};
@@ -1335,19 +1429,19 @@ void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio)
 	get_node_info(sbi, dn->nid, &ni);
 	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
 	do_write_page(&sum, fio);
-	dn->data_blkaddr = fio->blk_addr;
+	f2fs_update_data_blkaddr(dn, fio->new_blkaddr);
 }
 
 void rewrite_data_page(struct f2fs_io_info *fio)
 {
+	fio->new_blkaddr = fio->old_blkaddr;
 	stat_inc_inplace_blocks(fio->sbi);
 	f2fs_submit_page_mbio(fio);
 }
 
-static void __f2fs_replace_block(struct f2fs_sb_info *sbi,
-				struct f2fs_summary *sum,
+void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 				block_t old_blkaddr, block_t new_blkaddr,
-				bool recover_curseg)
+				bool recover_curseg, bool recover_newaddr)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
 	struct curseg_info *curseg;
@@ -1390,7 +1484,7 @@ static void __f2fs_replace_block(struct f2fs_sb_info *sbi,
 	curseg->next_blkoff = GET_BLKOFF_FROM_SEG0(sbi, new_blkaddr);
 	__add_sum_entry(sbi, type, sum);
 
-	if (!recover_curseg)
+	if (!recover_curseg || recover_newaddr)
 		update_sit_entry(sbi, new_blkaddr, 1);
 	if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
 		update_sit_entry(sbi, old_blkaddr, -1);
@@ -1414,66 +1508,30 @@ static void __f2fs_replace_block(struct f2fs_sb_info *sbi,
 
 void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
 				block_t old_addr, block_t new_addr,
-				unsigned char version, bool recover_curseg)
+				unsigned char version, bool recover_curseg,
+				bool recover_newaddr)
 {
 	struct f2fs_summary sum;
 
 	set_summary(&sum, dn->nid, dn->ofs_in_node, version);
 
-	__f2fs_replace_block(sbi, &sum, old_addr, new_addr, recover_curseg);
+	__f2fs_replace_block(sbi, &sum, old_addr, new_addr,
+					recover_curseg, recover_newaddr);
 
-	dn->data_blkaddr = new_addr;
-	set_data_blkaddr(dn);
-	f2fs_update_extent_cache(dn);
-}
-
-static inline bool is_merged_page(struct f2fs_sb_info *sbi,
-					struct page *page, enum page_type type)
-{
-	enum page_type btype = PAGE_TYPE_OF_BIO(type);
-	struct f2fs_bio_info *io = &sbi->write_io[btype];
-	struct bio_vec *bvec;
-	struct page *target;
-	int i;
-
-	down_read(&io->io_rwsem);
-	if (!io->bio) {
-		up_read(&io->io_rwsem);
-		return false;
-	}
-
-	bio_for_each_segment_all(bvec, io->bio, i) {
-
-		if (bvec->bv_page->mapping) {
-			target = bvec->bv_page;
-		} else {
-			struct f2fs_crypto_ctx *ctx;
-
-			/* encrypted page */
-			ctx = (struct f2fs_crypto_ctx *)page_private(
-								bvec->bv_page);
-			target = ctx->w.control_page;
-		}
-
-		if (page == target) {
-			up_read(&io->io_rwsem);
-			return true;
-		}
-	}
-
-	up_read(&io->io_rwsem);
-	return false;
+	f2fs_update_data_blkaddr(dn, new_addr);
 }
 
 void f2fs_wait_on_page_writeback(struct page *page,
-				enum page_type type)
+				enum page_type type, bool ordered)
 {
 	if (PageWriteback(page)) {
 		struct f2fs_sb_info *sbi = F2FS_P_SB(page);
 
-		if (is_merged_page(sbi, page, type))
-			f2fs_submit_merged_bio(sbi, type, WRITE);
-		wait_on_page_writeback(page);
+		f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, type, WRITE);
+		if (ordered)
+			wait_on_page_writeback(page);
+		else
+			wait_for_stable_page(page);
 	}
 }
 
@@ -1489,7 +1547,7 @@ void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi,
 
 	cpage = find_lock_page(META_MAPPING(sbi), blkaddr);
 	if (cpage) {
-		f2fs_wait_on_page_writeback(cpage, DATA);
+		f2fs_wait_on_page_writeback(cpage, DATA, true);
 		f2fs_put_page(cpage, 1);
 	}
 }
@@ -1510,12 +1568,11 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi)
 
 	/* Step 1: restore nat cache */
 	seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA);
-	memcpy(&seg_i->sum_blk->n_nats, kaddr, SUM_JOURNAL_SIZE);
+	memcpy(seg_i->journal, kaddr, SUM_JOURNAL_SIZE);
 
 	/* Step 2: restore sit cache */
 	seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA);
-	memcpy(&seg_i->sum_blk->n_sits, kaddr + SUM_JOURNAL_SIZE,
-						SUM_JOURNAL_SIZE);
+	memcpy(seg_i->journal, kaddr + SUM_JOURNAL_SIZE, SUM_JOURNAL_SIZE);
 	offset = 2 * SUM_JOURNAL_SIZE;
 
 	/* Step 3: restore summary entries */
@@ -1539,7 +1596,7 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi)
 			s = (struct f2fs_summary *)(kaddr + offset);
 			seg_i->sum_blk->entries[j] = *s;
 			offset += SUMMARY_SIZE;
-			if (offset + SUMMARY_SIZE <= PAGE_CACHE_SIZE -
+			if (offset + SUMMARY_SIZE <= PAGE_SIZE -
 						SUM_FOOTER_SIZE)
 				continue;
 
@@ -1611,7 +1668,14 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 	/* set uncompleted segment to curseg */
 	curseg = CURSEG_I(sbi, type);
 	mutex_lock(&curseg->curseg_mutex);
-	memcpy(curseg->sum_blk, sum, PAGE_CACHE_SIZE);
+
+	/* update journal info */
+	down_write(&curseg->journal_rwsem);
+	memcpy(curseg->journal, &sum->journal, SUM_JOURNAL_SIZE);
+	up_write(&curseg->journal_rwsem);
+
+	memcpy(curseg->sum_blk->entries, sum->entries, SUM_ENTRY_SIZE);
+	memcpy(&curseg->sum_blk->footer, &sum->footer, SUM_FOOTER_SIZE);
 	curseg->next_segno = segno;
 	reset_curseg(sbi, type, 0);
 	curseg->alloc_type = ckpt->alloc_type[type];
@@ -1666,13 +1730,12 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr)
 
 	/* Step 1: write nat cache */
 	seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA);
-	memcpy(kaddr, &seg_i->sum_blk->n_nats, SUM_JOURNAL_SIZE);
+	memcpy(kaddr, seg_i->journal, SUM_JOURNAL_SIZE);
 	written_size += SUM_JOURNAL_SIZE;
 
 	/* Step 2: write sit cache */
 	seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA);
-	memcpy(kaddr + written_size, &seg_i->sum_blk->n_sits,
-						SUM_JOURNAL_SIZE);
+	memcpy(kaddr + written_size, seg_i->journal, SUM_JOURNAL_SIZE);
 	written_size += SUM_JOURNAL_SIZE;
 
 	/* Step 3: write summary entries */
@@ -1694,7 +1757,7 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr)
 			*summary = seg_i->sum_blk->entries[j];
 			written_size += SUMMARY_SIZE;
 
-			if (written_size + SUMMARY_SIZE <= PAGE_CACHE_SIZE -
+			if (written_size + SUMMARY_SIZE <= PAGE_SIZE -
 							SUM_FOOTER_SIZE)
 				continue;
 
@@ -1718,12 +1781,8 @@ static void write_normal_summaries(struct f2fs_sb_info *sbi,
 	else
 		end = type + NR_CURSEG_NODE_TYPE;
 
-	for (i = type; i < end; i++) {
-		struct curseg_info *sum = CURSEG_I(sbi, i);
-		mutex_lock(&sum->curseg_mutex);
-		write_sum_page(sbi, sum->sum_blk, blkaddr + (i - type));
-		mutex_unlock(&sum->curseg_mutex);
-	}
+	for (i = type; i < end; i++)
+		write_current_sum_page(sbi, i, blkaddr + (i - type));
 }
 
 void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
@@ -1739,24 +1798,24 @@ void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
 	write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE);
 }
 
-int lookup_journal_in_cursum(struct f2fs_summary_block *sum, int type,
+int lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
 					unsigned int val, int alloc)
 {
 	int i;
 
 	if (type == NAT_JOURNAL) {
-		for (i = 0; i < nats_in_cursum(sum); i++) {
-			if (le32_to_cpu(nid_in_journal(sum, i)) == val)
+		for (i = 0; i < nats_in_cursum(journal); i++) {
+			if (le32_to_cpu(nid_in_journal(journal, i)) == val)
 				return i;
 		}
-		if (alloc && nats_in_cursum(sum) < NAT_JOURNAL_ENTRIES)
-			return update_nats_in_cursum(sum, 1);
+		if (alloc && __has_cursum_space(journal, 1, NAT_JOURNAL))
+			return update_nats_in_cursum(journal, 1);
 	} else if (type == SIT_JOURNAL) {
-		for (i = 0; i < sits_in_cursum(sum); i++)
-			if (le32_to_cpu(segno_in_journal(sum, i)) == val)
+		for (i = 0; i < sits_in_cursum(journal); i++)
+			if (le32_to_cpu(segno_in_journal(journal, i)) == val)
 				return i;
-		if (alloc && sits_in_cursum(sum) < SIT_JOURNAL_ENTRIES)
-			return update_sits_in_cursum(sum, 1);
+		if (alloc && __has_cursum_space(journal, 1, SIT_JOURNAL))
+			return update_sits_in_cursum(journal, 1);
 	}
 	return -1;
 }
@@ -1785,7 +1844,7 @@ static struct page *get_next_sit_page(struct f2fs_sb_info *sbi,
 
 	src_addr = page_address(src_page);
 	dst_addr = page_address(dst_page);
-	memcpy(dst_addr, src_addr, PAGE_CACHE_SIZE);
+	memcpy(dst_addr, src_addr, PAGE_SIZE);
 
 	set_page_dirty(dst_page);
 	f2fs_put_page(src_page, 1);
@@ -1860,20 +1919,22 @@ static void add_sits_in_set(struct f2fs_sb_info *sbi)
 static void remove_sits_in_journal(struct f2fs_sb_info *sbi)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
-	struct f2fs_summary_block *sum = curseg->sum_blk;
+	struct f2fs_journal *journal = curseg->journal;
 	int i;
 
-	for (i = sits_in_cursum(sum) - 1; i >= 0; i--) {
+	down_write(&curseg->journal_rwsem);
+	for (i = 0; i < sits_in_cursum(journal); i++) {
 		unsigned int segno;
 		bool dirtied;
 
-		segno = le32_to_cpu(segno_in_journal(sum, i));
+		segno = le32_to_cpu(segno_in_journal(journal, i));
 		dirtied = __mark_sit_entry_dirty(sbi, segno);
 
 		if (!dirtied)
 			add_sit_entry(segno, &SM_I(sbi)->sit_entry_set);
 	}
-	update_sits_in_cursum(sum, -sits_in_cursum(sum));
+	update_sits_in_cursum(journal, -i);
+	up_write(&curseg->journal_rwsem);
 }
 
 /*
@@ -1885,13 +1946,12 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	struct sit_info *sit_i = SIT_I(sbi);
 	unsigned long *bitmap = sit_i->dirty_sentries_bitmap;
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
-	struct f2fs_summary_block *sum = curseg->sum_blk;
+	struct f2fs_journal *journal = curseg->journal;
 	struct sit_entry_set *ses, *tmp;
 	struct list_head *head = &SM_I(sbi)->sit_entry_set;
 	bool to_journal = true;
 	struct seg_entry *se;
 
-	mutex_lock(&curseg->curseg_mutex);
 	mutex_lock(&sit_i->sentry_lock);
 
 	if (!sit_i->dirty_sentries)
@@ -1908,7 +1968,7 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	 * entries, remove all entries from journal and add and account
 	 * them in sit entry set.
 	 */
-	if (!__has_cursum_space(sum, sit_i->dirty_sentries, SIT_JOURNAL))
+	if (!__has_cursum_space(journal, sit_i->dirty_sentries, SIT_JOURNAL))
 		remove_sits_in_journal(sbi);
 
 	/*
@@ -1925,10 +1985,12 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 		unsigned int segno = start_segno;
 
 		if (to_journal &&
-			!__has_cursum_space(sum, ses->entry_cnt, SIT_JOURNAL))
+			!__has_cursum_space(journal, ses->entry_cnt, SIT_JOURNAL))
 			to_journal = false;
 
-		if (!to_journal) {
+		if (to_journal) {
+			down_write(&curseg->journal_rwsem);
+		} else {
 			page = get_next_sit_page(sbi, start_segno);
 			raw_sit = page_address(page);
 		}
@@ -1946,13 +2008,13 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			}
 
 			if (to_journal) {
-				offset = lookup_journal_in_cursum(sum,
+				offset = lookup_journal_in_cursum(journal,
 							SIT_JOURNAL, segno, 1);
 				f2fs_bug_on(sbi, offset < 0);
-				segno_in_journal(sum, offset) =
+				segno_in_journal(journal, offset) =
 							cpu_to_le32(segno);
 				seg_info_to_raw_sit(se,
-						&sit_in_journal(sum, offset));
+					&sit_in_journal(journal, offset));
 			} else {
 				sit_offset = SIT_ENTRY_OFFSET(sit_i, segno);
 				seg_info_to_raw_sit(se,
@@ -1964,7 +2026,9 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			ses->entry_cnt--;
 		}
 
-		if (!to_journal)
+		if (to_journal)
+			up_write(&curseg->journal_rwsem);
+		else
 			f2fs_put_page(page, 1);
 
 		f2fs_bug_on(sbi, ses->entry_cnt);
@@ -1979,7 +2043,6 @@ out:
 			add_discard_addrs(sbi, cpc);
 	}
 	mutex_unlock(&sit_i->sentry_lock);
-	mutex_unlock(&curseg->curseg_mutex);
 
 	set_prefree_as_free_segments(sbi);
 }
@@ -2108,9 +2171,14 @@ static int build_curseg(struct f2fs_sb_info *sbi)
 
 	for (i = 0; i < NR_CURSEG_TYPE; i++) {
 		mutex_init(&array[i].curseg_mutex);
-		array[i].sum_blk = kzalloc(PAGE_CACHE_SIZE, GFP_KERNEL);
+		array[i].sum_blk = kzalloc(PAGE_SIZE, GFP_KERNEL);
 		if (!array[i].sum_blk)
 			return -ENOMEM;
+		init_rwsem(&array[i].journal_rwsem);
+		array[i].journal = kzalloc(sizeof(struct f2fs_journal),
+							GFP_KERNEL);
+		if (!array[i].journal)
+			return -ENOMEM;
 		array[i].segno = NULL_SEGNO;
 		array[i].next_blkoff = 0;
 	}
@@ -2121,11 +2189,11 @@ static void build_sit_entries(struct f2fs_sb_info *sbi)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
-	struct f2fs_summary_block *sum = curseg->sum_blk;
+	struct f2fs_journal *journal = curseg->journal;
 	int sit_blk_cnt = SIT_BLK_CNT(sbi);
 	unsigned int i, start, end;
 	unsigned int readed, start_blk = 0;
-	int nrpages = MAX_BIO_BLOCKS(sbi);
+	int nrpages = MAX_BIO_BLOCKS(sbi) * 8;
 
 	do {
 		readed = ra_meta_pages(sbi, start_blk, nrpages, META_SIT, true);
@@ -2139,16 +2207,16 @@ static void build_sit_entries(struct f2fs_sb_info *sbi)
 			struct f2fs_sit_entry sit;
 			struct page *page;
 
-			mutex_lock(&curseg->curseg_mutex);
-			for (i = 0; i < sits_in_cursum(sum); i++) {
-				if (le32_to_cpu(segno_in_journal(sum, i))
+			down_read(&curseg->journal_rwsem);
+			for (i = 0; i < sits_in_cursum(journal); i++) {
+				if (le32_to_cpu(segno_in_journal(journal, i))
 								== start) {
-					sit = sit_in_journal(sum, i);
-					mutex_unlock(&curseg->curseg_mutex);
+					sit = sit_in_journal(journal, i);
+					up_read(&curseg->journal_rwsem);
 					goto got_it;
 				}
 			}
-			mutex_unlock(&curseg->curseg_mutex);
+			up_read(&curseg->journal_rwsem);
 
 			page = get_current_sit_page(sbi, start);
 			sit_blk = (struct f2fs_sit_block *)page_address(page);
@@ -2383,8 +2451,10 @@ static void destroy_curseg(struct f2fs_sb_info *sbi)
 	if (!array)
 		return;
 	SM_I(sbi)->curseg_array = NULL;
-	for (i = 0; i < NR_CURSEG_TYPE; i++)
+	for (i = 0; i < NR_CURSEG_TYPE; i++) {
 		kfree(array[i].sum_blk);
+		kfree(array[i].journal);
+	}
 	kfree(array);
 }
 
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index ee44d346ea44..975c33df65c7 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -183,7 +183,7 @@ struct segment_allocation {
  * this value is set in page as a private data which indicate that
  * the page is atomically written, and it is in inmem_pages list.
  */
-#define ATOMIC_WRITTEN_PAGE		0x0000ffff
+#define ATOMIC_WRITTEN_PAGE		((unsigned long)-1)
 
 #define IS_ATOMIC_WRITTEN_PAGE(page)			\
 		(page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE)
@@ -191,6 +191,7 @@ struct segment_allocation {
 struct inmem_pages {
 	struct list_head list;
 	struct page *page;
+	block_t old_addr;		/* for revoking when fail to commit */
 };
 
 struct sit_info {
@@ -257,6 +258,8 @@ struct victim_selection {
 struct curseg_info {
 	struct mutex curseg_mutex;		/* lock for consistency */
 	struct f2fs_summary_block *sum_blk;	/* cached summary block */
+	struct rw_semaphore journal_rwsem;	/* protect journal area */
+	struct f2fs_journal *journal;		/* cached journal info */
 	unsigned char alloc_type;		/* current allocation type */
 	unsigned int segno;			/* current segment number */
 	unsigned short next_blkoff;		/* next block offset to write */
diff --git a/fs/f2fs/shrinker.c b/fs/f2fs/shrinker.c
index da0d8e0b55a5..93606f281bf9 100644
--- a/fs/f2fs/shrinker.c
+++ b/fs/f2fs/shrinker.c
@@ -32,7 +32,8 @@ static unsigned long __count_free_nids(struct f2fs_sb_info *sbi)
 
 static unsigned long __count_extent_cache(struct f2fs_sb_info *sbi)
 {
-	return sbi->total_ext_tree + atomic_read(&sbi->total_ext_node);
+	return atomic_read(&sbi->total_zombie_tree) +
+				atomic_read(&sbi->total_ext_node);
 }
 
 unsigned long f2fs_shrink_count(struct shrinker *shrink,
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 3a65e0132352..006f87d69921 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -67,6 +67,7 @@ enum {
 	Opt_extent_cache,
 	Opt_noextent_cache,
 	Opt_noinline_data,
+	Opt_data_flush,
 	Opt_err,
 };
 
@@ -91,6 +92,7 @@ static match_table_t f2fs_tokens = {
 	{Opt_extent_cache, "extent_cache"},
 	{Opt_noextent_cache, "noextent_cache"},
 	{Opt_noinline_data, "noinline_data"},
+	{Opt_data_flush, "data_flush"},
 	{Opt_err, NULL},
 };
 
@@ -124,6 +126,19 @@ static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
 	return NULL;
 }
 
+static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
+		struct f2fs_sb_info *sbi, char *buf)
+{
+	struct super_block *sb = sbi->sb;
+
+	if (!sb->s_bdev->bd_part)
+		return snprintf(buf, PAGE_SIZE, "0\n");
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n",
+		(unsigned long long)(sbi->kbytes_written +
+			BD_PART_WRITTEN(sbi)));
+}
+
 static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
 			struct f2fs_sb_info *sbi, char *buf)
 {
@@ -202,6 +217,9 @@ static struct f2fs_attr f2fs_attr_##_name = {			\
 		f2fs_sbi_show, f2fs_sbi_store,			\
 		offsetof(struct struct_name, elname))
 
+#define F2FS_GENERAL_RO_ATTR(name) \
+static struct f2fs_attr f2fs_attr_##name = __ATTR(name, 0444, name##_show, NULL)
+
 F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_min_sleep_time, min_sleep_time);
 F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_max_sleep_time, max_sleep_time);
 F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time);
@@ -214,9 +232,12 @@ F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks);
 F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh);
 F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ra_nid_pages, ra_nid_pages);
+F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, dirty_nats_ratio, dirty_nats_ratio);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level);
-F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, cp_interval);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, interval_time[CP_TIME]);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]);
+F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes);
 
 #define ATTR_LIST(name) (&f2fs_attr_##name.attr)
 static struct attribute *f2fs_attrs[] = {
@@ -234,7 +255,10 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(dir_level),
 	ATTR_LIST(ram_thresh),
 	ATTR_LIST(ra_nid_pages),
+	ATTR_LIST(dirty_nats_ratio),
 	ATTR_LIST(cp_interval),
+	ATTR_LIST(idle_interval),
+	ATTR_LIST(lifetime_write_kbytes),
 	NULL,
 };
 
@@ -406,6 +430,9 @@ static int parse_options(struct super_block *sb, char *options)
 		case Opt_noinline_data:
 			clear_opt(sbi, INLINE_DATA);
 			break;
+		case Opt_data_flush:
+			set_opt(sbi, DATA_FLUSH);
+			break;
 		default:
 			f2fs_msg(sb, KERN_ERR,
 				"Unrecognized mount option \"%s\" or missing value",
@@ -432,6 +459,7 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
 	fi->i_current_depth = 1;
 	fi->i_advise = 0;
 	init_rwsem(&fi->i_sem);
+	INIT_LIST_HEAD(&fi->dirty_list);
 	INIT_LIST_HEAD(&fi->inmem_pages);
 	mutex_init(&fi->inmem_lock);
 
@@ -442,10 +470,6 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
 
 	/* Will be used by directory only */
 	fi->i_dir_level = F2FS_SB(sb)->dir_level;
-
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-	fi->i_crypt_info = NULL;
-#endif
 	return &fi->vfs_inode;
 }
 
@@ -466,7 +490,7 @@ static int f2fs_drop_inode(struct inode *inode)
 
 			/* some remained atomic pages should discarded */
 			if (f2fs_is_atomic_file(inode))
-				commit_inmem_pages(inode, true);
+				drop_inmem_pages(inode);
 
 			/* should remain fi->extent_tree for writepage */
 			f2fs_destroy_extent_node(inode);
@@ -479,11 +503,7 @@ static int f2fs_drop_inode(struct inode *inode)
 
 			sb_end_intwrite(inode->i_sb);
 
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-			if (F2FS_I(inode)->i_crypt_info)
-				f2fs_free_encryption_info(inode,
-					F2FS_I(inode)->i_crypt_info);
-#endif
+			fscrypt_put_encryption_info(inode, NULL);
 			spin_lock(&inode->i_lock);
 			atomic_dec(&inode->i_count);
 		}
@@ -548,12 +568,16 @@ static void f2fs_put_super(struct super_block *sb)
 	 * normally superblock is clean, so we need to release this.
 	 * In addition, EIO will skip do checkpoint, we need this as well.
 	 */
-	release_dirty_inode(sbi);
+	release_ino_entry(sbi);
 	release_discard_addrs(sbi);
 
 	f2fs_leave_shrinker(sbi);
 	mutex_unlock(&sbi->umount_mutex);
 
+	/* our cp_error case, we can wait for any writeback page */
+	if (get_pages(sbi, F2FS_WRITEBACK))
+		f2fs_flush_merged_bios(sbi);
+
 	iput(sbi->node_inode);
 	iput(sbi->meta_inode);
 
@@ -566,13 +590,16 @@ static void f2fs_put_super(struct super_block *sb)
 	wait_for_completion(&sbi->s_kobj_unregister);
 
 	sb->s_fs_info = NULL;
-	brelse(sbi->raw_super_buf);
+	if (sbi->s_chksum_driver)
+		crypto_free_shash(sbi->s_chksum_driver);
+	kfree(sbi->raw_super);
 	kfree(sbi);
 }
 
 int f2fs_sync_fs(struct super_block *sb, int sync)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	int err = 0;
 
 	trace_f2fs_sync_fs(sb, sync);
 
@@ -582,14 +609,12 @@ int f2fs_sync_fs(struct super_block *sb, int sync)
 		cpc.reason = __get_cp_reason(sbi);
 
 		mutex_lock(&sbi->gc_mutex);
-		write_checkpoint(sbi, &cpc);
+		err = write_checkpoint(sbi, &cpc);
 		mutex_unlock(&sbi->gc_mutex);
-	} else {
-		f2fs_balance_fs(sbi);
 	}
 	f2fs_trace_ios(NULL, 1);
 
-	return 0;
+	return err;
 }
 
 static int f2fs_freeze(struct super_block *sb)
@@ -686,6 +711,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 		seq_puts(seq, ",extent_cache");
 	else
 		seq_puts(seq, ",noextent_cache");
+	if (test_opt(sbi, DATA_FLUSH))
+		seq_puts(seq, ",data_flush");
 	seq_printf(seq, ",active_logs=%u", sbi->active_logs);
 
 	return 0;
@@ -757,8 +784,6 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	bool need_stop_gc = false;
 	bool no_extent_cache = !test_opt(sbi, EXTENT_CACHE);
 
-	sync_filesystem(sb);
-
 	/*
 	 * Save the old mount options in case we
 	 * need to restore them.
@@ -766,6 +791,13 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	org_mount_opt = sbi->mount_opt;
 	active_logs = sbi->active_logs;
 
+	if (*flags & MS_RDONLY) {
+		set_opt(sbi, FASTBOOT);
+		set_sbi_flag(sbi, SBI_IS_DIRTY);
+	}
+
+	sync_filesystem(sb);
+
 	sbi->mount_opt.opt = 0;
 	default_options(sbi);
 
@@ -853,6 +885,41 @@ static struct super_operations f2fs_sops = {
 	.remount_fs	= f2fs_remount,
 };
 
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+static int f2fs_get_context(struct inode *inode, void *ctx, size_t len)
+{
+	return f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
+				F2FS_XATTR_NAME_ENCRYPTION_CONTEXT,
+				ctx, len, NULL);
+}
+
+static int f2fs_set_context(struct inode *inode, const void *ctx, size_t len,
+							void *fs_data)
+{
+	return f2fs_setxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
+				F2FS_XATTR_NAME_ENCRYPTION_CONTEXT,
+				ctx, len, fs_data, XATTR_CREATE);
+}
+
+static unsigned f2fs_max_namelen(struct inode *inode)
+{
+	return S_ISLNK(inode->i_mode) ?
+			inode->i_sb->s_blocksize : F2FS_NAME_LEN;
+}
+
+static struct fscrypt_operations f2fs_cryptops = {
+	.get_context	= f2fs_get_context,
+	.set_context	= f2fs_set_context,
+	.is_encrypted	= f2fs_encrypted_inode,
+	.empty_dir	= f2fs_empty_dir,
+	.max_namelen	= f2fs_max_namelen,
+};
+#else
+static struct fscrypt_operations f2fs_cryptops = {
+	.is_encrypted	= f2fs_encrypted_inode,
+};
+#endif
+
 static struct inode *f2fs_nfs_get_inode(struct super_block *sb,
 		u64 ino, u32 generation)
 {
@@ -898,7 +965,7 @@ static const struct export_operations f2fs_export_ops = {
 	.get_parent = f2fs_get_parent,
 };
 
-static loff_t max_file_size(unsigned bits)
+static loff_t max_file_blocks(void)
 {
 	loff_t result = (DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS);
 	loff_t leaf_count = ADDRS_PER_BLOCK;
@@ -914,13 +981,128 @@ static loff_t max_file_size(unsigned bits)
 	leaf_count *= NIDS_PER_BLOCK;
 	result += leaf_count;
 
-	result <<= bits;
 	return result;
 }
 
+static int __f2fs_commit_super(struct buffer_head *bh,
+			struct f2fs_super_block *super)
+{
+	lock_buffer(bh);
+	if (super)
+		memcpy(bh->b_data + F2FS_SUPER_OFFSET, super, sizeof(*super));
+	set_buffer_uptodate(bh);
+	set_buffer_dirty(bh);
+	unlock_buffer(bh);
+
+	/* it's rare case, we can do fua all the time */
+	return __sync_dirty_buffer(bh, WRITE_FLUSH_FUA);
+}
+
+static inline bool sanity_check_area_boundary(struct super_block *sb,
+					struct buffer_head *bh)
+{
+	struct f2fs_super_block *raw_super = (struct f2fs_super_block *)
+					(bh->b_data + F2FS_SUPER_OFFSET);
+	u32 segment0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr);
+	u32 cp_blkaddr = le32_to_cpu(raw_super->cp_blkaddr);
+	u32 sit_blkaddr = le32_to_cpu(raw_super->sit_blkaddr);
+	u32 nat_blkaddr = le32_to_cpu(raw_super->nat_blkaddr);
+	u32 ssa_blkaddr = le32_to_cpu(raw_super->ssa_blkaddr);
+	u32 main_blkaddr = le32_to_cpu(raw_super->main_blkaddr);
+	u32 segment_count_ckpt = le32_to_cpu(raw_super->segment_count_ckpt);
+	u32 segment_count_sit = le32_to_cpu(raw_super->segment_count_sit);
+	u32 segment_count_nat = le32_to_cpu(raw_super->segment_count_nat);
+	u32 segment_count_ssa = le32_to_cpu(raw_super->segment_count_ssa);
+	u32 segment_count_main = le32_to_cpu(raw_super->segment_count_main);
+	u32 segment_count = le32_to_cpu(raw_super->segment_count);
+	u32 log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);
+	u64 main_end_blkaddr = main_blkaddr +
+				(segment_count_main << log_blocks_per_seg);
+	u64 seg_end_blkaddr = segment0_blkaddr +
+				(segment_count << log_blocks_per_seg);
+
+	if (segment0_blkaddr != cp_blkaddr) {
+		f2fs_msg(sb, KERN_INFO,
+			"Mismatch start address, segment0(%u) cp_blkaddr(%u)",
+			segment0_blkaddr, cp_blkaddr);
+		return true;
+	}
+
+	if (cp_blkaddr + (segment_count_ckpt << log_blocks_per_seg) !=
+							sit_blkaddr) {
+		f2fs_msg(sb, KERN_INFO,
+			"Wrong CP boundary, start(%u) end(%u) blocks(%u)",
+			cp_blkaddr, sit_blkaddr,
+			segment_count_ckpt << log_blocks_per_seg);
+		return true;
+	}
+
+	if (sit_blkaddr + (segment_count_sit << log_blocks_per_seg) !=
+							nat_blkaddr) {
+		f2fs_msg(sb, KERN_INFO,
+			"Wrong SIT boundary, start(%u) end(%u) blocks(%u)",
+			sit_blkaddr, nat_blkaddr,
+			segment_count_sit << log_blocks_per_seg);
+		return true;
+	}
+
+	if (nat_blkaddr + (segment_count_nat << log_blocks_per_seg) !=
+							ssa_blkaddr) {
+		f2fs_msg(sb, KERN_INFO,
+			"Wrong NAT boundary, start(%u) end(%u) blocks(%u)",
+			nat_blkaddr, ssa_blkaddr,
+			segment_count_nat << log_blocks_per_seg);
+		return true;
+	}
+
+	if (ssa_blkaddr + (segment_count_ssa << log_blocks_per_seg) !=
+							main_blkaddr) {
+		f2fs_msg(sb, KERN_INFO,
+			"Wrong SSA boundary, start(%u) end(%u) blocks(%u)",
+			ssa_blkaddr, main_blkaddr,
+			segment_count_ssa << log_blocks_per_seg);
+		return true;
+	}
+
+	if (main_end_blkaddr > seg_end_blkaddr) {
+		f2fs_msg(sb, KERN_INFO,
+			"Wrong MAIN_AREA boundary, start(%u) end(%u) block(%u)",
+			main_blkaddr,
+			segment0_blkaddr +
+				(segment_count << log_blocks_per_seg),
+			segment_count_main << log_blocks_per_seg);
+		return true;
+	} else if (main_end_blkaddr < seg_end_blkaddr) {
+		int err = 0;
+		char *res;
+
+		/* fix in-memory information all the time */
+		raw_super->segment_count = cpu_to_le32((main_end_blkaddr -
+				segment0_blkaddr) >> log_blocks_per_seg);
+
+		if (f2fs_readonly(sb) || bdev_read_only(sb->s_bdev)) {
+			res = "internally";
+		} else {
+			err = __f2fs_commit_super(bh, NULL);
+			res = err ? "failed" : "done";
+		}
+		f2fs_msg(sb, KERN_INFO,
+			"Fix alignment : %s, start(%u) end(%u) block(%u)",
+			res, main_blkaddr,
+			segment0_blkaddr +
+				(segment_count << log_blocks_per_seg),
+			segment_count_main << log_blocks_per_seg);
+		if (err)
+			return true;
+	}
+	return false;
+}
+
 static int sanity_check_raw_super(struct super_block *sb,
-			struct f2fs_super_block *raw_super)
+				struct buffer_head *bh)
 {
+	struct f2fs_super_block *raw_super = (struct f2fs_super_block *)
+					(bh->b_data + F2FS_SUPER_OFFSET);
 	unsigned int blocksize;
 
 	if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) {
@@ -931,10 +1113,10 @@ static int sanity_check_raw_super(struct super_block *sb,
 	}
 
 	/* Currently, support only 4KB page cache size */
-	if (F2FS_BLKSIZE != PAGE_CACHE_SIZE) {
+	if (F2FS_BLKSIZE != PAGE_SIZE) {
 		f2fs_msg(sb, KERN_INFO,
 			"Invalid page_cache_size (%lu), supports only 4KB\n",
-			PAGE_CACHE_SIZE);
+			PAGE_SIZE);
 		return 1;
 	}
 
@@ -947,6 +1129,14 @@ static int sanity_check_raw_super(struct super_block *sb,
 		return 1;
 	}
 
+	/* check log blocks per segment */
+	if (le32_to_cpu(raw_super->log_blocks_per_seg) != 9) {
+		f2fs_msg(sb, KERN_INFO,
+			"Invalid log blocks per segment (%u)\n",
+			le32_to_cpu(raw_super->log_blocks_per_seg));
+		return 1;
+	}
+
 	/* Currently, support 512/1024/2048/4096 bytes sector size */
 	if (le32_to_cpu(raw_super->log_sectorsize) >
 				F2FS_MAX_LOG_SECTOR_SIZE ||
@@ -965,10 +1155,27 @@ static int sanity_check_raw_super(struct super_block *sb,
 			le32_to_cpu(raw_super->log_sectorsize));
 		return 1;
 	}
+
+	/* check reserved ino info */
+	if (le32_to_cpu(raw_super->node_ino) != 1 ||
+		le32_to_cpu(raw_super->meta_ino) != 2 ||
+		le32_to_cpu(raw_super->root_ino) != 3) {
+		f2fs_msg(sb, KERN_INFO,
+			"Invalid Fs Meta Ino: node(%u) meta(%u) root(%u)",
+			le32_to_cpu(raw_super->node_ino),
+			le32_to_cpu(raw_super->meta_ino),
+			le32_to_cpu(raw_super->root_ino));
+		return 1;
+	}
+
+	/* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */
+	if (sanity_check_area_boundary(sb, bh))
+		return 1;
+
 	return 0;
 }
 
-static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
+int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 {
 	unsigned int total, fsmeta;
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
@@ -1018,7 +1225,8 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 		atomic_set(&sbi->nr_pages[i], 0);
 
 	sbi->dir_level = DEF_DIR_LEVEL;
-	sbi->cp_interval = DEF_CP_INTERVAL;
+	sbi->interval_time[CP_TIME] = DEF_CP_INTERVAL;
+	sbi->interval_time[REQ_TIME] = DEF_IDLE_INTERVAL;
 	clear_sbi_flag(sbi, SBI_NEED_FSCK);
 
 	INIT_LIST_HEAD(&sbi->s_list);
@@ -1027,98 +1235,86 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 
 /*
  * Read f2fs raw super block.
- * Because we have two copies of super block, so read the first one at first,
- * if the first one is invalid, move to read the second one.
+ * Because we have two copies of super block, so read both of them
+ * to get the first valid one. If any one of them is broken, we pass
+ * them recovery flag back to the caller.
  */
 static int read_raw_super_block(struct super_block *sb,
 			struct f2fs_super_block **raw_super,
-			struct buffer_head **raw_super_buf,
-			int *recovery)
+			int *valid_super_block, int *recovery)
 {
-	int block = 0;
-	struct buffer_head *buffer;
+	int block;
+	struct buffer_head *bh;
 	struct f2fs_super_block *super;
 	int err = 0;
 
-retry:
-	buffer = sb_bread(sb, block);
-	if (!buffer) {
-		*recovery = 1;
-		f2fs_msg(sb, KERN_ERR, "Unable to read %dth superblock",
+	super = kzalloc(sizeof(struct f2fs_super_block), GFP_KERNEL);
+	if (!super)
+		return -ENOMEM;
+
+	for (block = 0; block < 2; block++) {
+		bh = sb_bread(sb, block);
+		if (!bh) {
+			f2fs_msg(sb, KERN_ERR, "Unable to read %dth superblock",
 				block + 1);
-		if (block == 0) {
-			block++;
-			goto retry;
-		} else {
 			err = -EIO;
-			goto out;
+			continue;
 		}
-	}
 
-	super = (struct f2fs_super_block *)
-		((char *)(buffer)->b_data + F2FS_SUPER_OFFSET);
-
-	/* sanity checking of raw super */
-	if (sanity_check_raw_super(sb, super)) {
-		brelse(buffer);
-		*recovery = 1;
-		f2fs_msg(sb, KERN_ERR,
-			"Can't find valid F2FS filesystem in %dth superblock",
-								block + 1);
-		if (block == 0) {
-			block++;
-			goto retry;
-		} else {
+		/* sanity checking of raw super */
+		if (sanity_check_raw_super(sb, bh)) {
+			f2fs_msg(sb, KERN_ERR,
+				"Can't find valid F2FS filesystem in %dth superblock",
+				block + 1);
 			err = -EINVAL;
-			goto out;
+			brelse(bh);
+			continue;
 		}
-	}
 
-	if (!*raw_super) {
-		*raw_super_buf = buffer;
-		*raw_super = super;
-	} else {
-		/* already have a valid superblock */
-		brelse(buffer);
+		if (!*raw_super) {
+			memcpy(super, bh->b_data + F2FS_SUPER_OFFSET,
+							sizeof(*super));
+			*valid_super_block = block;
+			*raw_super = super;
+		}
+		brelse(bh);
 	}
 
-	/* check the validity of the second superblock */
-	if (block == 0) {
-		block++;
-		goto retry;
-	}
+	/* Fail to read any one of the superblocks*/
+	if (err < 0)
+		*recovery = 1;
 
-out:
 	/* No valid superblock */
 	if (!*raw_super)
-		return err;
+		kfree(super);
+	else
+		err = 0;
 
-	return 0;
+	return err;
 }
 
 int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
 {
-	struct buffer_head *sbh = sbi->raw_super_buf;
-	sector_t block = sbh->b_blocknr;
+	struct buffer_head *bh;
 	int err;
 
 	/* write back-up superblock first */
-	sbh->b_blocknr = block ? 0 : 1;
-	mark_buffer_dirty(sbh);
-	err = sync_dirty_buffer(sbh);
-
-	sbh->b_blocknr = block;
+	bh = sb_getblk(sbi->sb, sbi->valid_super_block ? 0: 1);
+	if (!bh)
+		return -EIO;
+	err = __f2fs_commit_super(bh, F2FS_RAW_SUPER(sbi));
+	brelse(bh);
 
 	/* if we are in recovery path, skip writing valid superblock */
 	if (recover || err)
-		goto out;
+		return err;
 
 	/* write current valid superblock */
-	mark_buffer_dirty(sbh);
-	err = sync_dirty_buffer(sbh);
-out:
-	clear_buffer_write_io_error(sbh);
-	set_buffer_uptodate(sbh);
+	bh = sb_getblk(sbi->sb, sbi->valid_super_block);
+	if (!bh)
+		return -EIO;
+	err = __f2fs_commit_super(bh, F2FS_RAW_SUPER(sbi));
+	brelse(bh);
 	return err;
 }
 
@@ -1126,17 +1322,17 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct f2fs_sb_info *sbi;
 	struct f2fs_super_block *raw_super;
-	struct buffer_head *raw_super_buf;
 	struct inode *root;
 	long err;
 	bool retry = true, need_fsck = false;
 	char *options = NULL;
-	int recovery, i;
+	int recovery, i, valid_super_block;
+	struct curseg_info *seg_i;
 
 try_onemore:
 	err = -EINVAL;
 	raw_super = NULL;
-	raw_super_buf = NULL;
+	valid_super_block = -1;
 	recovery = 0;
 
 	/* allocate memory for f2fs-specific super block info */
@@ -1144,13 +1340,23 @@ try_onemore:
 	if (!sbi)
 		return -ENOMEM;
 
+	/* Load the checksum driver */
+	sbi->s_chksum_driver = crypto_alloc_shash("crc32", 0, 0);
+	if (IS_ERR(sbi->s_chksum_driver)) {
+		f2fs_msg(sb, KERN_ERR, "Cannot load crc32 driver.");
+		err = PTR_ERR(sbi->s_chksum_driver);
+		sbi->s_chksum_driver = NULL;
+		goto free_sbi;
+	}
+
 	/* set a block size */
 	if (unlikely(!sb_set_blocksize(sb, F2FS_BLKSIZE))) {
 		f2fs_msg(sb, KERN_ERR, "unable to set blocksize");
 		goto free_sbi;
 	}
 
-	err = read_raw_super_block(sb, &raw_super, &raw_super_buf, &recovery);
+	err = read_raw_super_block(sb, &raw_super, &valid_super_block,
+								&recovery);
 	if (err)
 		goto free_sbi;
 
@@ -1167,11 +1373,14 @@ try_onemore:
 	if (err)
 		goto free_options;
 
-	sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize));
+	sbi->max_file_blocks = max_file_blocks();
+	sb->s_maxbytes = sbi->max_file_blocks <<
+				le32_to_cpu(raw_super->log_blocksize);
 	sb->s_max_links = F2FS_LINK_MAX;
 	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
 
 	sb->s_op = &f2fs_sops;
+	sb->s_cop = &f2fs_cryptops;
 	sb->s_xattr = f2fs_xattr_handlers;
 	sb->s_export_op = &f2fs_export_ops;
 	sb->s_magic = F2FS_SUPER_MAGIC;
@@ -1183,7 +1392,7 @@ try_onemore:
 	/* init f2fs-specific super block info */
 	sbi->sb = sb;
 	sbi->raw_super = raw_super;
-	sbi->raw_super_buf = raw_super_buf;
+	sbi->valid_super_block = valid_super_block;
 	mutex_init(&sbi->gc_mutex);
 	mutex_init(&sbi->writepages);
 	mutex_init(&sbi->cp_mutex);
@@ -1220,13 +1429,6 @@ try_onemore:
 		goto free_meta_inode;
 	}
 
-	/* sanity checking of checkpoint */
-	err = -EINVAL;
-	if (sanity_check_ckpt(sbi)) {
-		f2fs_msg(sb, KERN_ERR, "Invalid F2FS checkpoint");
-		goto free_cp;
-	}
-
 	sbi->total_valid_node_count =
 				le32_to_cpu(sbi->ckpt->valid_node_count);
 	sbi->total_valid_inode_count =
@@ -1236,8 +1438,10 @@ try_onemore:
 				le64_to_cpu(sbi->ckpt->valid_block_count);
 	sbi->last_valid_block_count = sbi->total_valid_block_count;
 	sbi->alloc_valid_block_count = 0;
-	INIT_LIST_HEAD(&sbi->dir_inode_list);
-	spin_lock_init(&sbi->dir_inode_lock);
+	for (i = 0; i < NR_INODE_TYPE; i++) {
+		INIT_LIST_HEAD(&sbi->inode_list[i]);
+		spin_lock_init(&sbi->inode_lock[i]);
+	}
 
 	init_extent_cache_info(sbi);
 
@@ -1257,6 +1461,17 @@ try_onemore:
 		goto free_nm;
 	}
 
+	/* For write statistics */
+	if (sb->s_bdev->bd_part)
+		sbi->sectors_written_start =
+			(u64)part_stat_read(sb->s_bdev->bd_part, sectors[1]);
+
+	/* Read accumulated write IO statistics if exists */
+	seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
+	if (__exist_node_summaries(sbi))
+		sbi->kbytes_written =
+			le64_to_cpu(seg_i->journal->info.kbytes_written);
+
 	build_gc_manager(sbi);
 
 	/* get an inode for node space */
@@ -1351,16 +1566,20 @@ try_onemore:
 
 	/* recover broken superblock */
 	if (recovery && !f2fs_readonly(sb) && !bdev_read_only(sb->s_bdev)) {
-		f2fs_msg(sb, KERN_INFO, "Recover invalid superblock");
-		f2fs_commit_super(sbi, true);
+		err = f2fs_commit_super(sbi, true);
+		f2fs_msg(sb, KERN_INFO,
+			"Try to recover %dth superblock, ret: %ld",
+			sbi->valid_super_block ? 1 : 2, err);
 	}
 
-	sbi->cp_expires = round_jiffies_up(jiffies);
-
+	f2fs_update_time(sbi, CP_TIME);
+	f2fs_update_time(sbi, REQ_TIME);
 	return 0;
 
 free_kobj:
 	kobject_del(&sbi->s_kobj);
+	kobject_put(&sbi->s_kobj);
+	wait_for_completion(&sbi->s_kobj_unregister);
 free_proc:
 	if (sbi->s_proc) {
 		remove_proc_entry("segment_info", sbi->s_proc);
@@ -1379,7 +1598,6 @@ free_nm:
 	destroy_node_manager(sbi);
 free_sm:
 	destroy_segment_manager(sbi);
-free_cp:
 	kfree(sbi->ckpt);
 free_meta_inode:
 	make_bad_inode(sbi->meta_inode);
@@ -1387,8 +1605,10 @@ free_meta_inode:
 free_options:
 	kfree(options);
 free_sb_buf:
-	brelse(raw_super_buf);
+	kfree(raw_super);
 free_sbi:
+	if (sbi->s_chksum_driver)
+		crypto_free_shash(sbi->s_chksum_driver);
 	kfree(sbi);
 
 	/* give only one another chance */
@@ -1424,8 +1644,9 @@ MODULE_ALIAS_FS("f2fs");
 
 static int __init init_inodecache(void)
 {
-	f2fs_inode_cachep = f2fs_kmem_cache_create("f2fs_inode_cache",
-			sizeof(struct f2fs_inode_info));
+	f2fs_inode_cachep = kmem_cache_create("f2fs_inode_cache",
+			sizeof(struct f2fs_inode_info), 0,
+			SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT, NULL);
 	if (!f2fs_inode_cachep)
 		return -ENOMEM;
 	return 0;
@@ -1467,25 +1688,23 @@ static int __init init_f2fs_fs(void)
 		err = -ENOMEM;
 		goto free_extent_cache;
 	}
-	err = f2fs_init_crypto();
-	if (err)
-		goto free_kset;
-
 	err = register_shrinker(&f2fs_shrinker_info);
 	if (err)
-		goto free_crypto;
+		goto free_kset;
 
 	err = register_filesystem(&f2fs_fs_type);
 	if (err)
 		goto free_shrinker;
-	f2fs_create_root_stats();
+	err = f2fs_create_root_stats();
+	if (err)
+		goto free_filesystem;
 	f2fs_proc_root = proc_mkdir("fs/f2fs", NULL);
 	return 0;
 
+free_filesystem:
+	unregister_filesystem(&f2fs_fs_type);
 free_shrinker:
 	unregister_shrinker(&f2fs_shrinker_info);
-free_crypto:
-	f2fs_exit_crypto();
 free_kset:
 	kset_unregister(f2fs_kset);
 free_extent_cache:
@@ -1508,7 +1727,6 @@ static void __exit exit_f2fs_fs(void)
 	f2fs_destroy_root_stats();
 	unregister_shrinker(&f2fs_shrinker_info);
 	unregister_filesystem(&f2fs_fs_type);
-	f2fs_exit_crypto();
 	destroy_extent_cache();
 	destroy_checkpoint_caches();
 	destroy_segment_manager_caches();
diff --git a/fs/f2fs/trace.c b/fs/f2fs/trace.c
index 145fb659ad44..562ce0821559 100644
--- a/fs/f2fs/trace.c
+++ b/fs/f2fs/trace.c
@@ -29,7 +29,8 @@ static inline void __print_last_io(void)
 			last_io.major, last_io.minor,
 			last_io.pid, "----------------",
 			last_io.type,
-			last_io.fio.rw, last_io.fio.blk_addr,
+			last_io.fio.rw,
+			last_io.fio.new_blkaddr,
 			last_io.len);
 	memset(&last_io, 0, sizeof(last_io));
 }
@@ -101,7 +102,8 @@ void f2fs_trace_ios(struct f2fs_io_info *fio, int flush)
 			last_io.pid == pid &&
 			last_io.type == __file_type(inode, pid) &&
 			last_io.fio.rw == fio->rw &&
-			last_io.fio.blk_addr + last_io.len == fio->blk_addr) {
+			last_io.fio.new_blkaddr + last_io.len ==
+							fio->new_blkaddr) {
 		last_io.len++;
 		return;
 	}
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 4de2286c0e4d..06a72dc0191a 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -25,49 +25,37 @@
 #include "f2fs.h"
 #include "xattr.h"
 
-static size_t f2fs_xattr_generic_list(struct dentry *dentry, char *list,
-		size_t list_size, const char *name, size_t len, int type)
+static int f2fs_xattr_generic_get(const struct xattr_handler *handler,
+		struct dentry *dentry, const char *name, void *buffer,
+		size_t size)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
-	int total_len, prefix_len = 0;
-	const char *prefix = NULL;
 
-	switch (type) {
+	switch (handler->flags) {
 	case F2FS_XATTR_INDEX_USER:
 		if (!test_opt(sbi, XATTR_USER))
 			return -EOPNOTSUPP;
-		prefix = XATTR_USER_PREFIX;
-		prefix_len = XATTR_USER_PREFIX_LEN;
 		break;
 	case F2FS_XATTR_INDEX_TRUSTED:
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
-		prefix = XATTR_TRUSTED_PREFIX;
-		prefix_len = XATTR_TRUSTED_PREFIX_LEN;
 		break;
 	case F2FS_XATTR_INDEX_SECURITY:
-		prefix = XATTR_SECURITY_PREFIX;
-		prefix_len = XATTR_SECURITY_PREFIX_LEN;
 		break;
 	default:
 		return -EINVAL;
 	}
-
-	total_len = prefix_len + len + 1;
-	if (list && total_len <= list_size) {
-		memcpy(list, prefix, prefix_len);
-		memcpy(list + prefix_len, name, len);
-		list[prefix_len + len] = '\0';
-	}
-	return total_len;
+	return f2fs_getxattr(d_inode(dentry), handler->flags, name,
+			     buffer, size, NULL);
 }
 
-static int f2fs_xattr_generic_get(struct dentry *dentry, const char *name,
-		void *buffer, size_t size, int type)
+static int f2fs_xattr_generic_set(const struct xattr_handler *handler,
+		struct dentry *dentry, const char *name, const void *value,
+		size_t size, int flags)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
 
-	switch (type) {
+	switch (handler->flags) {
 	case F2FS_XATTR_INDEX_USER:
 		if (!test_opt(sbi, XATTR_USER))
 			return -EOPNOTSUPP;
@@ -81,72 +69,39 @@ static int f2fs_xattr_generic_get(struct dentry *dentry, const char *name,
 	default:
 		return -EINVAL;
 	}
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
-	return f2fs_getxattr(d_inode(dentry), type, name, buffer, size, NULL);
+	return f2fs_setxattr(d_inode(dentry), handler->flags, name,
+					value, size, NULL, flags);
 }
 
-static int f2fs_xattr_generic_set(struct dentry *dentry, const char *name,
-		const void *value, size_t size, int flags, int type)
+static bool f2fs_xattr_user_list(struct dentry *dentry)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
 
-	switch (type) {
-	case F2FS_XATTR_INDEX_USER:
-		if (!test_opt(sbi, XATTR_USER))
-			return -EOPNOTSUPP;
-		break;
-	case F2FS_XATTR_INDEX_TRUSTED:
-		if (!capable(CAP_SYS_ADMIN))
-			return -EPERM;
-		break;
-	case F2FS_XATTR_INDEX_SECURITY:
-		break;
-	default:
-		return -EINVAL;
-	}
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
-
-	return f2fs_setxattr(d_inode(dentry), type, name,
-					value, size, NULL, flags);
+	return test_opt(sbi, XATTR_USER);
 }
 
-static size_t f2fs_xattr_advise_list(struct dentry *dentry, char *list,
-		size_t list_size, const char *name, size_t len, int type)
+static bool f2fs_xattr_trusted_list(struct dentry *dentry)
 {
-	const char *xname = F2FS_SYSTEM_ADVISE_PREFIX;
-	size_t size;
-
-	if (type != F2FS_XATTR_INDEX_ADVISE)
-		return 0;
-
-	size = strlen(xname) + 1;
-	if (list && size <= list_size)
-		memcpy(list, xname, size);
-	return size;
+	return capable(CAP_SYS_ADMIN);
 }
 
-static int f2fs_xattr_advise_get(struct dentry *dentry, const char *name,
-		void *buffer, size_t size, int type)
+static int f2fs_xattr_advise_get(const struct xattr_handler *handler,
+		struct dentry *dentry, const char *name, void *buffer,
+		size_t size)
 {
 	struct inode *inode = d_inode(dentry);
 
-	if (strcmp(name, "") != 0)
-		return -EINVAL;
-
 	if (buffer)
 		*((char *)buffer) = F2FS_I(inode)->i_advise;
 	return sizeof(char);
 }
 
-static int f2fs_xattr_advise_set(struct dentry *dentry, const char *name,
-		const void *value, size_t size, int flags, int type)
+static int f2fs_xattr_advise_set(const struct xattr_handler *handler,
+		struct dentry *dentry, const char *name, const void *value,
+		size_t size, int flags)
 {
 	struct inode *inode = d_inode(dentry);
 
-	if (strcmp(name, "") != 0)
-		return -EINVAL;
 	if (!inode_owner_or_capable(inode))
 		return -EPERM;
 	if (value == NULL)
@@ -185,7 +140,7 @@ int f2fs_init_security(struct inode *inode, struct inode *dir,
 const struct xattr_handler f2fs_xattr_user_handler = {
 	.prefix	= XATTR_USER_PREFIX,
 	.flags	= F2FS_XATTR_INDEX_USER,
-	.list	= f2fs_xattr_generic_list,
+	.list	= f2fs_xattr_user_list,
 	.get	= f2fs_xattr_generic_get,
 	.set	= f2fs_xattr_generic_set,
 };
@@ -193,15 +148,14 @@ const struct xattr_handler f2fs_xattr_user_handler = {
 const struct xattr_handler f2fs_xattr_trusted_handler = {
 	.prefix	= XATTR_TRUSTED_PREFIX,
 	.flags	= F2FS_XATTR_INDEX_TRUSTED,
-	.list	= f2fs_xattr_generic_list,
+	.list	= f2fs_xattr_trusted_list,
 	.get	= f2fs_xattr_generic_get,
 	.set	= f2fs_xattr_generic_set,
 };
 
 const struct xattr_handler f2fs_xattr_advise_handler = {
-	.prefix = F2FS_SYSTEM_ADVISE_PREFIX,
+	.name	= F2FS_SYSTEM_ADVISE_NAME,
 	.flags	= F2FS_XATTR_INDEX_ADVISE,
-	.list   = f2fs_xattr_advise_list,
 	.get    = f2fs_xattr_advise_get,
 	.set    = f2fs_xattr_advise_set,
 };
@@ -209,7 +163,6 @@ const struct xattr_handler f2fs_xattr_advise_handler = {
 const struct xattr_handler f2fs_xattr_security_handler = {
 	.prefix	= XATTR_SECURITY_PREFIX,
 	.flags	= F2FS_XATTR_INDEX_SECURITY,
-	.list	= f2fs_xattr_generic_list,
 	.get	= f2fs_xattr_generic_get,
 	.set	= f2fs_xattr_generic_set,
 };
@@ -347,7 +300,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 
 		if (ipage) {
 			inline_addr = inline_xattr_addr(ipage);
-			f2fs_wait_on_page_writeback(ipage, NODE);
+			f2fs_wait_on_page_writeback(ipage, NODE, true);
 		} else {
 			page = get_node_page(sbi, inode->i_ino);
 			if (IS_ERR(page)) {
@@ -355,7 +308,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 				return PTR_ERR(page);
 			}
 			inline_addr = inline_xattr_addr(page);
-			f2fs_wait_on_page_writeback(page, NODE);
+			f2fs_wait_on_page_writeback(page, NODE, true);
 		}
 		memcpy(inline_addr, txattr_addr, inline_size);
 		f2fs_put_page(page, 1);
@@ -376,7 +329,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 			return PTR_ERR(xpage);
 		}
 		f2fs_bug_on(sbi, new_nid);
-		f2fs_wait_on_page_writeback(xpage, NODE);
+		f2fs_wait_on_page_writeback(xpage, NODE, true);
 	} else {
 		struct dnode_of_data dn;
 		set_new_dnode(&dn, inode, NULL, NULL, new_nid);
@@ -457,20 +410,27 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
 	list_for_each_xattr(entry, base_addr) {
 		const struct xattr_handler *handler =
 			f2fs_xattr_handler(entry->e_name_index);
+		const char *prefix;
+		size_t prefix_len;
 		size_t size;
 
-		if (!handler)
+		if (!handler || (handler->list && !handler->list(dentry)))
 			continue;
 
-		size = handler->list(dentry, buffer, rest, entry->e_name,
-				entry->e_name_len, handler->flags);
-		if (buffer && size > rest) {
-			error = -ERANGE;
-			goto cleanup;
+		prefix = handler->prefix ?: handler->name;
+		prefix_len = strlen(prefix);
+		size = prefix_len + entry->e_name_len + 1;
+		if (buffer) {
+			if (size > rest) {
+				error = -ERANGE;
+				goto cleanup;
+			}
+			memcpy(buffer, prefix, prefix_len);
+			buffer += prefix_len;
+			memcpy(buffer, entry->e_name, entry->e_name_len);
+			buffer += entry->e_name_len;
+			*buffer++ = 0;
 		}
-
-		if (buffer)
-			buffer += size;
 		rest -= size;
 	}
 	error = buffer_size - rest;
@@ -611,7 +571,7 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name,
 	if (ipage)
 		return __f2fs_setxattr(inode, index, name, value,
 						size, ipage, flags);
-	f2fs_balance_fs(sbi);
+	f2fs_balance_fs(sbi, true);
 
 	f2fs_lock_op(sbi);
 	/* protect xattr_ver */
@@ -620,5 +580,6 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name,
 	up_write(&F2FS_I(inode)->i_sem);
 	f2fs_unlock_op(sbi);
 
+	f2fs_update_time(sbi, REQ_TIME);
 	return err;
 }
diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h
index 71a7100d5492..f990de20cdcd 100644
--- a/fs/f2fs/xattr.h
+++ b/fs/f2fs/xattr.h
@@ -27,7 +27,7 @@
 #define F2FS_XATTR_REFCOUNT_MAX         1024
 
 /* Name indexes */
-#define F2FS_SYSTEM_ADVISE_PREFIX		"system.advise"
+#define F2FS_SYSTEM_ADVISE_NAME			"system.advise"
 #define F2FS_XATTR_INDEX_USER			1
 #define F2FS_XATTR_INDEX_POSIX_ACL_ACCESS	2
 #define F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT	3
@@ -126,7 +126,8 @@ extern ssize_t f2fs_listxattr(struct dentry *, char *, size_t);
 
 #define f2fs_xattr_handlers	NULL
 static inline int f2fs_setxattr(struct inode *inode, int index,
-		const char *name, const void *value, size_t size, int flags)
+		const char *name, const void *value, size_t size,
+		struct page *page, int flags)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/fs/fat/Kconfig b/fs/fat/Kconfig
index 182f9ffe2b51..3ff1772f612e 100644
--- a/fs/fat/Kconfig
+++ b/fs/fat/Kconfig
@@ -93,8 +93,24 @@ config FAT_DEFAULT_IOCHARSET
 	  that most of your FAT filesystems use, and can be overridden
 	  with the "iocharset" mount option for FAT filesystems.
 	  Note that "utf8" is not recommended for FAT filesystems.
-	  If unsure, you shouldn't set "utf8" here.
+	  If unsure, you shouldn't set "utf8" here - select the next option
+	  instead if you would like to use UTF-8 encoded file names by default.
 	  See <file:Documentation/filesystems/vfat.txt> for more information.
 
 	  Enable any character sets you need in File Systems/Native Language
 	  Support.
+
+config FAT_DEFAULT_UTF8
+	bool "Enable FAT UTF-8 option by default"
+	depends on VFAT_FS
+	default n
+	help
+	  Set this if you would like to have "utf8" mount option set
+	  by default when mounting FAT filesystems.
+
+	  Even if you say Y here can always disable UTF-8 for
+	  particular mount by adding "utf8=0" to mount options.
+
+	  Say Y if you use UTF-8 encoding for file names, N otherwise.
+
+	  See <file:Documentation/filesystems/vfat.txt> for more information.
diff --git a/fs/fat/cache.c b/fs/fat/cache.c
index 93fc62232ec2..5d384921524d 100644
--- a/fs/fat/cache.c
+++ b/fs/fat/cache.c
@@ -301,15 +301,59 @@ static int fat_bmap_cluster(struct inode *inode, int cluster)
 	return dclus;
 }
 
-int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
-	     unsigned long *mapped_blocks, int create)
+int fat_get_mapped_cluster(struct inode *inode, sector_t sector,
+			   sector_t last_block,
+			   unsigned long *mapped_blocks, sector_t *bmap)
 {
 	struct super_block *sb = inode->i_sb;
 	struct msdos_sb_info *sbi = MSDOS_SB(sb);
+	int cluster, offset;
+
+	cluster = sector >> (sbi->cluster_bits - sb->s_blocksize_bits);
+	offset  = sector & (sbi->sec_per_clus - 1);
+	cluster = fat_bmap_cluster(inode, cluster);
+	if (cluster < 0)
+		return cluster;
+	else if (cluster) {
+		*bmap = fat_clus_to_blknr(sbi, cluster) + offset;
+		*mapped_blocks = sbi->sec_per_clus - offset;
+		if (*mapped_blocks > last_block - sector)
+			*mapped_blocks = last_block - sector;
+	}
+
+	return 0;
+}
+
+static int is_exceed_eof(struct inode *inode, sector_t sector,
+			 sector_t *last_block, int create)
+{
+	struct super_block *sb = inode->i_sb;
 	const unsigned long blocksize = sb->s_blocksize;
 	const unsigned char blocksize_bits = sb->s_blocksize_bits;
+
+	*last_block = (i_size_read(inode) + (blocksize - 1)) >> blocksize_bits;
+	if (sector >= *last_block) {
+		if (!create)
+			return 1;
+
+		/*
+		 * ->mmu_private can access on only allocation path.
+		 * (caller must hold ->i_mutex)
+		 */
+		*last_block = (MSDOS_I(inode)->mmu_private + (blocksize - 1))
+			>> blocksize_bits;
+		if (sector >= *last_block)
+			return 1;
+	}
+
+	return 0;
+}
+
+int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
+	     unsigned long *mapped_blocks, int create, bool from_bmap)
+{
+	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
 	sector_t last_block;
-	int cluster, offset;
 
 	*phys = 0;
 	*mapped_blocks = 0;
@@ -321,31 +365,16 @@ int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
 		return 0;
 	}
 
-	last_block = (i_size_read(inode) + (blocksize - 1)) >> blocksize_bits;
-	if (sector >= last_block) {
-		if (!create)
+	if (!from_bmap) {
+		if (is_exceed_eof(inode, sector, &last_block, create))
 			return 0;
-
-		/*
-		 * ->mmu_private can access on only allocation path.
-		 * (caller must hold ->i_mutex)
-		 */
-		last_block = (MSDOS_I(inode)->mmu_private + (blocksize - 1))
-			>> blocksize_bits;
+	} else {
+		last_block = inode->i_blocks >>
+				(inode->i_sb->s_blocksize_bits - 9);
 		if (sector >= last_block)
 			return 0;
 	}
 
-	cluster = sector >> (sbi->cluster_bits - sb->s_blocksize_bits);
-	offset  = sector & (sbi->sec_per_clus - 1);
-	cluster = fat_bmap_cluster(inode, cluster);
-	if (cluster < 0)
-		return cluster;
-	else if (cluster) {
-		*phys = fat_clus_to_blknr(sbi, cluster) + offset;
-		*mapped_blocks = sbi->sec_per_clus - offset;
-		if (*mapped_blocks > last_block - sector)
-			*mapped_blocks = last_block - sector;
-	}
-	return 0;
+	return fat_get_mapped_cluster(inode, sector, last_block, mapped_blocks,
+				      phys);
 }
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 4afc4d9d2e41..d0b95c95079b 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -91,7 +91,7 @@ next:
 
 	*bh = NULL;
 	iblock = *pos >> sb->s_blocksize_bits;
-	err = fat_bmap(dir, iblock, &phys, &mapped_blocks, 0);
+	err = fat_bmap(dir, iblock, &phys, &mapped_blocks, 0, false);
 	if (err || !phys)
 		return -1;	/* beyond EOF or error */
 
@@ -610,9 +610,9 @@ parse_record:
 		int status = fat_parse_long(inode, &cpos, &bh, &de,
 					    &unicode, &nr_slots);
 		if (status < 0) {
-			ctx->pos = cpos;
+			bh = NULL;
 			ret = status;
-			goto out;
+			goto end_of_dir;
 		} else if (status == PARSE_INVALID)
 			goto record_end;
 		else if (status == PARSE_NOT_LONGNAME)
@@ -654,8 +654,9 @@ parse_record:
 	fill_len = short_len;
 
 start_filldir:
-	if (!fake_offset)
-		ctx->pos = cpos - (nr_slots + 1) * sizeof(struct msdos_dir_entry);
+	ctx->pos = cpos - (nr_slots + 1) * sizeof(struct msdos_dir_entry);
+	if (fake_offset && ctx->pos < 2)
+		ctx->pos = 2;
 
 	if (!memcmp(de->name, MSDOS_DOT, MSDOS_NAME)) {
 		if (!dir_emit_dot(file, ctx))
@@ -681,14 +682,19 @@ record_end:
 	fake_offset = 0;
 	ctx->pos = cpos;
 	goto get_new;
+
 end_of_dir:
-	ctx->pos = cpos;
+	if (fake_offset && cpos < 2)
+		ctx->pos = 2;
+	else
+		ctx->pos = cpos;
 fill_failed:
 	brelse(bh);
 	if (unicode)
 		__putname(unicode);
 out:
 	mutex_unlock(&sbi->s_lock);
+
 	return ret;
 }
 
@@ -763,7 +769,7 @@ static int fat_ioctl_readdir(struct inode *inode, struct file *file,
 
 	buf.dirent = dirent;
 	buf.result = 0;
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	buf.ctx.pos = file->f_pos;
 	ret = -ENOENT;
 	if (!IS_DEADDIR(inode)) {
@@ -771,7 +777,7 @@ static int fat_ioctl_readdir(struct inode *inode, struct file *file,
 				    short_only, both ? &buf : NULL);
 		file->f_pos = buf.ctx.pos;
 	}
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	if (ret >= 0)
 		ret = buf.result;
 	return ret;
diff --git a/fs/fat/fat.h b/fs/fat/fat.h
index be5e15323bab..e6b764a17a9c 100644
--- a/fs/fat/fat.h
+++ b/fs/fat/fat.h
@@ -87,7 +87,7 @@ struct msdos_sb_info {
 	unsigned int vol_id;		/*volume ID*/
 
 	int fatent_shift;
-	struct fatent_operations *fatent_ops;
+	const struct fatent_operations *fatent_ops;
 	struct inode *fat_inode;
 	struct inode *fsinfo_inode;
 
@@ -285,8 +285,11 @@ static inline void fatwchar_to16(__u8 *dst, const wchar_t *src, size_t len)
 extern void fat_cache_inval_inode(struct inode *inode);
 extern int fat_get_cluster(struct inode *inode, int cluster,
 			   int *fclus, int *dclus);
+extern int fat_get_mapped_cluster(struct inode *inode, sector_t sector,
+				  sector_t last_block,
+				  unsigned long *mapped_blocks, sector_t *bmap);
 extern int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
-		    unsigned long *mapped_blocks, int create);
+		    unsigned long *mapped_blocks, int create, bool from_bmap);
 
 /* fat/dir.c */
 extern const struct file_operations fat_dir_operations;
@@ -384,6 +387,7 @@ static inline unsigned long fat_dir_hash(int logstart)
 {
 	return hash_32(logstart, FAT_HASH_BITS);
 }
+extern int fat_add_cluster(struct inode *inode);
 
 /* fat/misc.c */
 extern __printf(3, 4) __cold
diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c
index 8226557130a2..1d9a8c4e9de0 100644
--- a/fs/fat/fatent.c
+++ b/fs/fat/fatent.c
@@ -99,7 +99,7 @@ err:
 static int fat_ent_bread(struct super_block *sb, struct fat_entry *fatent,
 			 int offset, sector_t blocknr)
 {
-	struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops;
+	const struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops;
 
 	WARN_ON(blocknr < MSDOS_SB(sb)->fat_start);
 	fatent->fat_inode = MSDOS_SB(sb)->fat_inode;
@@ -246,7 +246,7 @@ static int fat32_ent_next(struct fat_entry *fatent)
 	return 0;
 }
 
-static struct fatent_operations fat12_ops = {
+static const struct fatent_operations fat12_ops = {
 	.ent_blocknr	= fat12_ent_blocknr,
 	.ent_set_ptr	= fat12_ent_set_ptr,
 	.ent_bread	= fat12_ent_bread,
@@ -255,7 +255,7 @@ static struct fatent_operations fat12_ops = {
 	.ent_next	= fat12_ent_next,
 };
 
-static struct fatent_operations fat16_ops = {
+static const struct fatent_operations fat16_ops = {
 	.ent_blocknr	= fat_ent_blocknr,
 	.ent_set_ptr	= fat16_ent_set_ptr,
 	.ent_bread	= fat_ent_bread,
@@ -264,7 +264,7 @@ static struct fatent_operations fat16_ops = {
 	.ent_next	= fat16_ent_next,
 };
 
-static struct fatent_operations fat32_ops = {
+static const struct fatent_operations fat32_ops = {
 	.ent_blocknr	= fat_ent_blocknr,
 	.ent_set_ptr	= fat32_ent_set_ptr,
 	.ent_bread	= fat_ent_bread,
@@ -320,7 +320,7 @@ static inline int fat_ent_update_ptr(struct super_block *sb,
 				     int offset, sector_t blocknr)
 {
 	struct msdos_sb_info *sbi = MSDOS_SB(sb);
-	struct fatent_operations *ops = sbi->fatent_ops;
+	const struct fatent_operations *ops = sbi->fatent_ops;
 	struct buffer_head **bhs = fatent->bhs;
 
 	/* Is this fatent's blocks including this entry? */
@@ -349,7 +349,7 @@ int fat_ent_read(struct inode *inode, struct fat_entry *fatent, int entry)
 {
 	struct super_block *sb = inode->i_sb;
 	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
-	struct fatent_operations *ops = sbi->fatent_ops;
+	const struct fatent_operations *ops = sbi->fatent_ops;
 	int err, offset;
 	sector_t blocknr;
 
@@ -407,7 +407,7 @@ int fat_ent_write(struct inode *inode, struct fat_entry *fatent,
 		  int new, int wait)
 {
 	struct super_block *sb = inode->i_sb;
-	struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops;
+	const struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops;
 	int err;
 
 	ops->ent_put(fatent, new);
@@ -432,7 +432,7 @@ static inline int fat_ent_next(struct msdos_sb_info *sbi,
 static inline int fat_ent_read_block(struct super_block *sb,
 				     struct fat_entry *fatent)
 {
-	struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops;
+	const struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops;
 	sector_t blocknr;
 	int offset;
 
@@ -463,7 +463,7 @@ int fat_alloc_clusters(struct inode *inode, int *cluster, int nr_cluster)
 {
 	struct super_block *sb = inode->i_sb;
 	struct msdos_sb_info *sbi = MSDOS_SB(sb);
-	struct fatent_operations *ops = sbi->fatent_ops;
+	const struct fatent_operations *ops = sbi->fatent_ops;
 	struct fat_entry fatent, prev_ent;
 	struct buffer_head *bhs[MAX_BUF_PER_PAGE];
 	int i, count, err, nr_bhs, idx_clus;
@@ -551,7 +551,7 @@ int fat_free_clusters(struct inode *inode, int cluster)
 {
 	struct super_block *sb = inode->i_sb;
 	struct msdos_sb_info *sbi = MSDOS_SB(sb);
-	struct fatent_operations *ops = sbi->fatent_ops;
+	const struct fatent_operations *ops = sbi->fatent_ops;
 	struct fat_entry fatent;
 	struct buffer_head *bhs[MAX_BUF_PER_PAGE];
 	int i, err, nr_bhs;
@@ -636,7 +636,7 @@ EXPORT_SYMBOL_GPL(fat_free_clusters);
 static void fat_ent_reada(struct super_block *sb, struct fat_entry *fatent,
 			  unsigned long reada_blocks)
 {
-	struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops;
+	const struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops;
 	sector_t blocknr;
 	int i, offset;
 
@@ -649,7 +649,7 @@ static void fat_ent_reada(struct super_block *sb, struct fat_entry *fatent,
 int fat_count_free_clusters(struct super_block *sb)
 {
 	struct msdos_sb_info *sbi = MSDOS_SB(sb);
-	struct fatent_operations *ops = sbi->fatent_ops;
+	const struct fatent_operations *ops = sbi->fatent_ops;
 	struct fat_entry fatent;
 	unsigned long reada_blocks, reada_mask, cur_block;
 	int err = 0, free;
diff --git a/fs/fat/file.c b/fs/fat/file.c
index a08f1039909a..f70185668832 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -14,15 +14,19 @@
 #include <linux/backing-dev.h>
 #include <linux/fsnotify.h>
 #include <linux/security.h>
+#include <linux/falloc.h>
 #include "fat.h"
 
+static long fat_fallocate(struct file *file, int mode,
+			  loff_t offset, loff_t len);
+
 static int fat_ioctl_get_attributes(struct inode *inode, u32 __user *user_attr)
 {
 	u32 attr;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	attr = fat_make_attrs(inode);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	return put_user(attr, user_attr);
 }
@@ -43,7 +47,7 @@ static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr)
 	err = mnt_want_write_file(file);
 	if (err)
 		goto out;
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	/*
 	 * ATTR_VOLUME and ATTR_DIR cannot be changed; this also
@@ -105,7 +109,7 @@ static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr)
 	fat_save_attrs(inode, attr);
 	mark_inode_dirty(inode);
 out_unlock_inode:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	mnt_drop_write_file(file);
 out:
 	return err;
@@ -177,6 +181,7 @@ const struct file_operations fat_file_operations = {
 #endif
 	.fsync		= fat_file_fsync,
 	.splice_read	= generic_file_splice_read,
+	.fallocate	= fat_fallocate,
 };
 
 static int fat_cont_expand(struct inode *inode, loff_t size)
@@ -215,6 +220,62 @@ out:
 	return err;
 }
 
+/*
+ * Preallocate space for a file. This implements fat's fallocate file
+ * operation, which gets called from sys_fallocate system call. User
+ * space requests len bytes at offset. If FALLOC_FL_KEEP_SIZE is set
+ * we just allocate clusters without zeroing them out. Otherwise we
+ * allocate and zero out clusters via an expanding truncate.
+ */
+static long fat_fallocate(struct file *file, int mode,
+			  loff_t offset, loff_t len)
+{
+	int nr_cluster; /* Number of clusters to be allocated */
+	loff_t mm_bytes; /* Number of bytes to be allocated for file */
+	loff_t ondisksize; /* block aligned on-disk size in bytes*/
+	struct inode *inode = file->f_mapping->host;
+	struct super_block *sb = inode->i_sb;
+	struct msdos_sb_info *sbi = MSDOS_SB(sb);
+	int err = 0;
+
+	/* No support for hole punch or other fallocate flags. */
+	if (mode & ~FALLOC_FL_KEEP_SIZE)
+		return -EOPNOTSUPP;
+
+	/* No support for dir */
+	if (!S_ISREG(inode->i_mode))
+		return -EOPNOTSUPP;
+
+	inode_lock(inode);
+	if (mode & FALLOC_FL_KEEP_SIZE) {
+		ondisksize = inode->i_blocks << 9;
+		if ((offset + len) <= ondisksize)
+			goto error;
+
+		/* First compute the number of clusters to be allocated */
+		mm_bytes = offset + len - ondisksize;
+		nr_cluster = (mm_bytes + (sbi->cluster_size - 1)) >>
+			sbi->cluster_bits;
+
+		/* Start the allocation.We are not zeroing out the clusters */
+		while (nr_cluster-- > 0) {
+			err = fat_add_cluster(inode);
+			if (err)
+				goto error;
+		}
+	} else {
+		if ((offset + len) <= i_size_read(inode))
+			goto error;
+
+		/* This is just an expanding truncate */
+		err = fat_cont_expand(inode, (offset + len));
+	}
+
+error:
+	inode_unlock(inode);
+	return err;
+}
+
 /* Free all clusters after the skip'th cluster. */
 static int fat_free(struct inode *inode, int skip)
 {
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 509411dd3698..226281068a46 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -93,7 +93,7 @@ static struct fat_floppy_defaults {
 },
 };
 
-static int fat_add_cluster(struct inode *inode)
+int fat_add_cluster(struct inode *inode)
 {
 	int err, cluster;
 
@@ -115,10 +115,10 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock,
 	struct super_block *sb = inode->i_sb;
 	struct msdos_sb_info *sbi = MSDOS_SB(sb);
 	unsigned long mapped_blocks;
-	sector_t phys;
+	sector_t phys, last_block;
 	int err, offset;
 
-	err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create);
+	err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create, false);
 	if (err)
 		return err;
 	if (phys) {
@@ -135,8 +135,14 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock,
 		return -EIO;
 	}
 
+	last_block = inode->i_blocks >> (sb->s_blocksize_bits - 9);
 	offset = (unsigned long)iblock & (sbi->sec_per_clus - 1);
-	if (!offset) {
+	/*
+	 * allocate a cluster according to the following.
+	 * 1) no more available blocks
+	 * 2) not part of fallocate region
+	 */
+	if (!offset && !(iblock < last_block)) {
 		/* TODO: multiple cluster allocation would be desirable. */
 		err = fat_add_cluster(inode);
 		if (err)
@@ -148,7 +154,7 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock,
 	*max_blocks = min(mapped_blocks, *max_blocks);
 	MSDOS_I(inode)->mmu_private += *max_blocks << sb->s_blocksize_bits;
 
-	err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create);
+	err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create, false);
 	if (err)
 		return err;
 
@@ -273,13 +279,38 @@ static ssize_t fat_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	return ret;
 }
 
+static int fat_get_block_bmap(struct inode *inode, sector_t iblock,
+		struct buffer_head *bh_result, int create)
+{
+	struct super_block *sb = inode->i_sb;
+	unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
+	int err;
+	sector_t bmap;
+	unsigned long mapped_blocks;
+
+	BUG_ON(create != 0);
+
+	err = fat_bmap(inode, iblock, &bmap, &mapped_blocks, create, true);
+	if (err)
+		return err;
+
+	if (bmap) {
+		map_bh(bh_result, sb, bmap);
+		max_blocks = min(mapped_blocks, max_blocks);
+	}
+
+	bh_result->b_size = max_blocks << sb->s_blocksize_bits;
+
+	return 0;
+}
+
 static sector_t _fat_bmap(struct address_space *mapping, sector_t block)
 {
 	sector_t blocknr;
 
 	/* fat_get_cluster() assumes the requested blocknr isn't truncated. */
 	down_read(&MSDOS_I(mapping->host)->truncate_lock);
-	blocknr = generic_block_bmap(mapping, block, fat_get_block);
+	blocknr = generic_block_bmap(mapping, block, fat_get_block_bmap);
 	up_read(&MSDOS_I(mapping->host)->truncate_lock);
 
 	return blocknr;
@@ -449,6 +480,24 @@ static int fat_calc_dir_size(struct inode *inode)
 	return 0;
 }
 
+static int fat_validate_dir(struct inode *dir)
+{
+	struct super_block *sb = dir->i_sb;
+
+	if (dir->i_nlink < 2) {
+		/* Directory should have "."/".." entries at least. */
+		fat_fs_error(sb, "corrupted directory (invalid entries)");
+		return -EIO;
+	}
+	if (MSDOS_I(dir)->i_start == 0 ||
+	    MSDOS_I(dir)->i_start == MSDOS_SB(sb)->root_cluster) {
+		/* Directory should point valid cluster. */
+		fat_fs_error(sb, "corrupted directory (invalid i_start)");
+		return -EIO;
+	}
+	return 0;
+}
+
 /* doesn't deal with root inode */
 int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
 {
@@ -475,6 +524,10 @@ int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
 		MSDOS_I(inode)->mmu_private = inode->i_size;
 
 		set_nlink(inode, fat_subdirs(inode));
+
+		error = fat_validate_dir(inode);
+		if (error < 0)
+			return error;
 	} else { /* not a directory */
 		inode->i_generation |= 1;
 		inode->i_mode = fat_make_mode(sbi, de->attr,
@@ -553,13 +606,43 @@ out:
 
 EXPORT_SYMBOL_GPL(fat_build_inode);
 
+static int __fat_write_inode(struct inode *inode, int wait);
+
+static void fat_free_eofblocks(struct inode *inode)
+{
+	/* Release unwritten fallocated blocks on inode eviction. */
+	if ((inode->i_blocks << 9) >
+			round_up(MSDOS_I(inode)->mmu_private,
+				MSDOS_SB(inode->i_sb)->cluster_size)) {
+		int err;
+
+		fat_truncate_blocks(inode, MSDOS_I(inode)->mmu_private);
+		/* Fallocate results in updating the i_start/iogstart
+		 * for the zero byte file. So, make it return to
+		 * original state during evict and commit it to avoid
+		 * any corruption on the next access to the cluster
+		 * chain for the file.
+		 */
+		err = __fat_write_inode(inode, inode_needs_sync(inode));
+		if (err) {
+			fat_msg(inode->i_sb, KERN_WARNING, "Failed to "
+					"update on disk inode for unused "
+					"fallocated blocks, inode could be "
+					"corrupted. Please run fsck");
+		}
+
+	}
+}
+
 static void fat_evict_inode(struct inode *inode)
 {
 	truncate_inode_pages_final(&inode->i_data);
 	if (!inode->i_nlink) {
 		inode->i_size = 0;
 		fat_truncate_blocks(inode, 0);
-	}
+	} else
+		fat_free_eofblocks(inode);
+
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
 	fat_cache_inval_inode(inode);
@@ -677,7 +760,7 @@ static int __init fat_init_inodecache(void)
 	fat_inode_cachep = kmem_cache_create("fat_inode_cache",
 					     sizeof(struct msdos_inode_info),
 					     0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD),
+						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
 					     init_once);
 	if (fat_inode_cachep == NULL)
 		return -ENOMEM;
@@ -1044,7 +1127,7 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
 	}
 	opts->name_check = 'n';
 	opts->quiet = opts->showexec = opts->sys_immutable = opts->dotsOK =  0;
-	opts->utf8 = opts->unicode_xlate = 0;
+	opts->unicode_xlate = 0;
 	opts->numtail = 1;
 	opts->usefree = opts->nocase = 0;
 	opts->tz_set = 0;
@@ -1052,6 +1135,8 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
 	opts->errors = FAT_ERRORS_RO;
 	*debug = 0;
 
+	opts->utf8 = IS_ENABLED(CONFIG_FAT_DEFAULT_UTF8) && is_vfat;
+
 	if (!options)
 		goto out;
 
@@ -1146,7 +1231,12 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
 		case Opt_time_offset:
 			if (match_int(&args[0], &option))
 				return -EINVAL;
-			if (option < -12 * 60 || option > 12 * 60)
+			/*
+			 * GMT+-12 zones may have DST corrections so at least
+			 * 13 hours difference is needed. Make the limit 24
+			 * just in case someone invents something unusual.
+			 */
+			if (option < -24 * 60 || option > 24 * 60)
 				return -EINVAL;
 			opts->tz_set = 1;
 			opts->time_offset = option;
diff --git a/fs/fcntl.c b/fs/fcntl.c
index ee85cd4e136a..350a2c8cfd28 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -51,7 +51,8 @@ static int setfl(int fd, struct file * filp, unsigned long arg)
 	       if (arg & O_NDELAY)
 		   arg |= O_NONBLOCK;
 
-	if (arg & O_DIRECT) {
+	/* Pipe packetized mode is controlled by O_DIRECT flag */
+	if (!S_ISFIFO(filp->f_inode->i_mode) && (arg & O_DIRECT)) {
 		if (!filp->f_mapping || !filp->f_mapping->a_ops ||
 			!filp->f_mapping->a_ops->direct_IO)
 				return -EINVAL;
diff --git a/fs/fhandle.c b/fs/fhandle.c
index d59712dfa3e7..ca3c3dd01789 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -228,7 +228,7 @@ long do_handle_open(int mountdirfd,
 		path_put(&path);
 		return fd;
 	}
-	file = file_open_root(path.dentry, path.mnt, "", open_flag);
+	file = file_open_root(path.dentry, path.mnt, "", open_flag, 0);
 	if (IS_ERR(file)) {
 		put_unused_fd(fd);
 		retval =  PTR_ERR(file);
diff --git a/fs/file.c b/fs/file.c
index 39f8f15921da..1fbc5c0555a9 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -25,9 +25,9 @@
 
 int sysctl_nr_open __read_mostly = 1024*1024;
 int sysctl_nr_open_min = BITS_PER_LONG;
-/* our max() is unusable in constant expressions ;-/ */
-#define __const_max(x, y) ((x) < (y) ? (x) : (y))
-int sysctl_nr_open_max = __const_max(INT_MAX, ~(size_t)0/sizeof(void *)) &
+/* our min() is unusable in constant expressions ;-/ */
+#define __const_min(x, y) ((x) < (y) ? (x) : (y))
+int sysctl_nr_open_max = __const_min(INT_MAX, ~(size_t)0/sizeof(void *)) &
 			 -BITS_PER_LONG;
 
 static void *alloc_fdmem(size_t size)
@@ -37,11 +37,12 @@ static void *alloc_fdmem(size_t size)
 	 * 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|__GFP_NOWARN|__GFP_NORETRY);
+		void *data = kmalloc(size, GFP_KERNEL_ACCOUNT |
+				     __GFP_NOWARN | __GFP_NORETRY);
 		if (data != NULL)
 			return data;
 	}
-	return vmalloc(size);
+	return __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_HIGHMEM, PAGE_KERNEL);
 }
 
 static void __free_fdtable(struct fdtable *fdt)
@@ -126,7 +127,7 @@ static struct fdtable * alloc_fdtable(unsigned int nr)
 	if (unlikely(nr > sysctl_nr_open))
 		nr = ((sysctl_nr_open - 1) | (BITS_PER_LONG - 1)) + 1;
 
-	fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL);
+	fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL_ACCOUNT);
 	if (!fdt)
 		goto out;
 	fdt->max_fds = nr;
diff --git a/fs/filesystems.c b/fs/filesystems.c
index 5797d45a78cb..c5618db110be 100644
--- a/fs/filesystems.c
+++ b/fs/filesystems.c
@@ -46,9 +46,9 @@ void put_filesystem(struct file_system_type *fs)
 static struct file_system_type **find_filesystem(const char *name, unsigned len)
 {
 	struct file_system_type **p;
-	for (p=&file_systems; *p; p=&(*p)->next)
-		if (strlen((*p)->name) == len &&
-		    strncmp((*p)->name, name, len) == 0)
+	for (p = &file_systems; *p; p = &(*p)->next)
+		if (strncmp((*p)->name, name, len) == 0 &&
+		    !(*p)->name[len])
 			break;
 	return p;
 }
diff --git a/fs/freevxfs/vxfs_immed.c b/fs/freevxfs/vxfs_immed.c
index cb84f0fcc72a..bfc780c682fb 100644
--- a/fs/freevxfs/vxfs_immed.c
+++ b/fs/freevxfs/vxfs_immed.c
@@ -66,11 +66,11 @@ static int
 vxfs_immed_readpage(struct file *fp, struct page *pp)
 {
 	struct vxfs_inode_info	*vip = VXFS_INO(pp->mapping->host);
-	u_int64_t	offset = (u_int64_t)pp->index << PAGE_CACHE_SHIFT;
+	u_int64_t	offset = (u_int64_t)pp->index << PAGE_SHIFT;
 	caddr_t		kaddr;
 
 	kaddr = kmap(pp);
-	memcpy(kaddr, vip->vii_immed.vi_immed + offset, PAGE_CACHE_SIZE);
+	memcpy(kaddr, vip->vii_immed.vi_immed + offset, PAGE_SIZE);
 	kunmap(pp);
 	
 	flush_dcache_page(pp);
diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c
index ef73ed674a27..3e2ccade61ed 100644
--- a/fs/freevxfs/vxfs_inode.c
+++ b/fs/freevxfs/vxfs_inode.c
@@ -326,6 +326,7 @@ vxfs_iget(struct super_block *sbp, ino_t ino)
 	} else if (S_ISLNK(ip->i_mode)) {
 		if (!VXFS_ISIMMED(vip)) {
 			ip->i_op = &page_symlink_inode_operations;
+			inode_nohighmem(ip);
 			ip->i_mapping->a_ops = &vxfs_aops;
 		} else {
 			ip->i_op = &simple_symlink_inode_operations;
diff --git a/fs/freevxfs/vxfs_lookup.c b/fs/freevxfs/vxfs_lookup.c
index 1cff72df0389..a49e0cfbb686 100644
--- a/fs/freevxfs/vxfs_lookup.c
+++ b/fs/freevxfs/vxfs_lookup.c
@@ -45,7 +45,7 @@
 /*
  * Number of VxFS blocks per page.
  */
-#define VXFS_BLOCK_PER_PAGE(sbp)  ((PAGE_CACHE_SIZE / (sbp)->s_blocksize))
+#define VXFS_BLOCK_PER_PAGE(sbp)  ((PAGE_SIZE / (sbp)->s_blocksize))
 
 
 static struct dentry *	vxfs_lookup(struct inode *, struct dentry *, unsigned int);
@@ -175,7 +175,7 @@ vxfs_inode_by_name(struct inode *dip, struct dentry *dp)
 	if (de) {
 		ino = de->d_ino;
 		kunmap(pp);
-		page_cache_release(pp);
+		put_page(pp);
 	}
 	
 	return (ino);
@@ -255,8 +255,8 @@ vxfs_readdir(struct file *fp, struct dir_context *ctx)
 	nblocks = dir_blocks(ip);
 	pblocks = VXFS_BLOCK_PER_PAGE(sbp);
 
-	page = pos >> PAGE_CACHE_SHIFT;
-	offset = pos & ~PAGE_CACHE_MASK;
+	page = pos >> PAGE_SHIFT;
+	offset = pos & ~PAGE_MASK;
 	block = (u_long)(pos >> sbp->s_blocksize_bits) % pblocks;
 
 	for (; page < npages; page++, block = 0) {
@@ -289,7 +289,7 @@ vxfs_readdir(struct file *fp, struct dir_context *ctx)
 					continue;
 
 				offset = (char *)de - kaddr;
-				ctx->pos = ((page << PAGE_CACHE_SHIFT) | offset) + 2;
+				ctx->pos = ((page << PAGE_SHIFT) | offset) + 2;
 				if (!dir_emit(ctx, de->d_name, de->d_namelen,
 					de->d_ino, DT_UNKNOWN)) {
 					vxfs_put_page(pp);
@@ -301,6 +301,6 @@ vxfs_readdir(struct file *fp, struct dir_context *ctx)
 		vxfs_put_page(pp);
 		offset = 0;
 	}
-	ctx->pos = ((page << PAGE_CACHE_SHIFT) | offset) + 2;
+	ctx->pos = ((page << PAGE_SHIFT) | offset) + 2;
 	return 0;
 }
diff --git a/fs/freevxfs/vxfs_subr.c b/fs/freevxfs/vxfs_subr.c
index 5d318c44f855..e806694d4145 100644
--- a/fs/freevxfs/vxfs_subr.c
+++ b/fs/freevxfs/vxfs_subr.c
@@ -50,7 +50,7 @@ inline void
 vxfs_put_page(struct page *pp)
 {
 	kunmap(pp);
-	page_cache_release(pp);
+	put_page(pp);
 }
 
 /**
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 206a68b1db1a..592cea54cea0 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -33,7 +33,7 @@
 /*
  * 4MB minimal write chunk size
  */
-#define MIN_WRITEBACK_PAGES	(4096UL >> (PAGE_CACHE_SHIFT - 10))
+#define MIN_WRITEBACK_PAGES	(4096UL >> (PAGE_SHIFT - 10))
 
 struct wb_completion {
 	atomic_t		cnt;
@@ -223,6 +223,9 @@ static void wb_wait_for_completion(struct backing_dev_info *bdi,
 #define WB_FRN_HIST_MAX_SLOTS	(WB_FRN_HIST_THR_SLOTS / 2 + 1)
 					/* one round can affect upto 5 slots */
 
+static atomic_t isw_nr_in_flight = ATOMIC_INIT(0);
+static struct workqueue_struct *isw_wq;
+
 void __inode_attach_wb(struct inode *inode, struct page *page)
 {
 	struct backing_dev_info *bdi = inode_to_bdi(inode);
@@ -278,13 +281,15 @@ locked_inode_to_wb_and_lock_list(struct inode *inode)
 		wb_get(wb);
 		spin_unlock(&inode->i_lock);
 		spin_lock(&wb->list_lock);
-		wb_put(wb);		/* not gonna deref it anymore */
 
 		/* i_wb may have changed inbetween, can't use inode_to_wb() */
-		if (likely(wb == inode->i_wb))
-			return wb;	/* @inode already has ref */
+		if (likely(wb == inode->i_wb)) {
+			wb_put(wb);	/* @inode already has ref */
+			return wb;
+		}
 
 		spin_unlock(&wb->list_lock);
+		wb_put(wb);
 		cpu_relax();
 		spin_lock(&inode->i_lock);
 	}
@@ -424,6 +429,8 @@ skip_switch:
 
 	iput(inode);
 	kfree(isw);
+
+	atomic_dec(&isw_nr_in_flight);
 }
 
 static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head)
@@ -433,7 +440,7 @@ static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head)
 
 	/* needs to grab bh-unsafe locks, bounce to work item */
 	INIT_WORK(&isw->work, inode_switch_wbs_work_fn);
-	schedule_work(&isw->work);
+	queue_work(isw_wq, &isw->work);
 }
 
 /**
@@ -469,7 +476,8 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
 
 	/* while holding I_WB_SWITCH, no one else can update the association */
 	spin_lock(&inode->i_lock);
-	if (inode->i_state & (I_WB_SWITCH | I_FREEING) ||
+	if (!(inode->i_sb->s_flags & MS_ACTIVE) ||
+	    inode->i_state & (I_WB_SWITCH | I_FREEING) ||
 	    inode_to_wb(inode) == isw->new_wb) {
 		spin_unlock(&inode->i_lock);
 		goto out_free;
@@ -480,6 +488,8 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
 	ihold(inode);
 	isw->inode = inode;
 
+	atomic_inc(&isw_nr_in_flight);
+
 	/*
 	 * In addition to synchronizing among switchers, I_WB_SWITCH tells
 	 * the RCU protected stat update paths to grab the mapping's
@@ -677,9 +687,7 @@ void wbc_account_io(struct writeback_control *wbc, struct page *page,
 	if (!wbc->wb)
 		return;
 
-	rcu_read_lock();
 	id = mem_cgroup_css_from_page(page)->id;
-	rcu_read_unlock();
 
 	if (id == wbc->wb_id) {
 		wbc->wb_bytes += bytes;
@@ -842,6 +850,33 @@ restart:
 		wb_put(last_wb);
 }
 
+/**
+ * cgroup_writeback_umount - flush inode wb switches for umount
+ *
+ * This function is called when a super_block is about to be destroyed and
+ * flushes in-flight inode wb switches.  An inode wb switch goes through
+ * RCU and then workqueue, so the two need to be flushed in order to ensure
+ * that all previously scheduled switches are finished.  As wb switches are
+ * rare occurrences and synchronize_rcu() can take a while, perform
+ * flushing iff wb switches are in flight.
+ */
+void cgroup_writeback_umount(void)
+{
+	if (atomic_read(&isw_nr_in_flight)) {
+		synchronize_rcu();
+		flush_workqueue(isw_wq);
+	}
+}
+
+static int __init cgroup_writeback_init(void)
+{
+	isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0);
+	if (!isw_wq)
+		return -ENOMEM;
+	return 0;
+}
+fs_initcall(cgroup_writeback_init);
+
 #else	/* CONFIG_CGROUP_WRITEBACK */
 
 static struct bdi_writeback *
@@ -1304,10 +1339,10 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
  * we go e.g. from filesystem. Flusher thread uses __writeback_single_inode()
  * and does more profound writeback list handling in writeback_sb_inodes().
  */
-static int
-writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
-		       struct writeback_control *wbc)
+static int writeback_single_inode(struct inode *inode,
+				  struct writeback_control *wbc)
 {
+	struct bdi_writeback *wb;
 	int ret = 0;
 
 	spin_lock(&inode->i_lock);
@@ -1345,7 +1380,8 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
 	ret = __writeback_single_inode(inode, wbc);
 
 	wbc_detach_inode(wbc);
-	spin_lock(&wb->list_lock);
+
+	wb = inode_to_wb_and_lock_list(inode);
 	spin_lock(&inode->i_lock);
 	/*
 	 * If inode is clean, remove it from writeback lists. Otherwise don't
@@ -1420,6 +1456,7 @@ static long writeback_sb_inodes(struct super_block *sb,
 
 	while (!list_empty(&wb->b_io)) {
 		struct inode *inode = wb_inode(wb->b_io.prev);
+		struct bdi_writeback *tmp_wb;
 
 		if (inode->i_sb != sb) {
 			if (work->sb) {
@@ -1510,15 +1547,23 @@ static long writeback_sb_inodes(struct super_block *sb,
 			cond_resched();
 		}
 
-
-		spin_lock(&wb->list_lock);
+		/*
+		 * Requeue @inode if still dirty.  Be careful as @inode may
+		 * have been switched to another wb in the meantime.
+		 */
+		tmp_wb = inode_to_wb_and_lock_list(inode);
 		spin_lock(&inode->i_lock);
 		if (!(inode->i_state & I_DIRTY_ALL))
 			wrote++;
-		requeue_inode(inode, wb, &wbc);
+		requeue_inode(inode, tmp_wb, &wbc);
 		inode_sync_complete(inode);
 		spin_unlock(&inode->i_lock);
 
+		if (unlikely(tmp_wb != wb)) {
+			spin_unlock(&tmp_wb->list_lock);
+			spin_lock(&wb->list_lock);
+		}
+
 		/*
 		 * bail out to wb_writeback() often enough to check
 		 * background threshold and other termination conditions.
@@ -1981,9 +2026,9 @@ static noinline void block_dump___mark_inode_dirty(struct inode *inode)
  * page->mapping->host, so the page-dirtying time is recorded in the internal
  * blockdev inode.
  */
-#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
 void __mark_inode_dirty(struct inode *inode, int flags)
 {
+#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
 	struct super_block *sb = inode->i_sb;
 	int dirtytime;
 
@@ -2093,6 +2138,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 out_unlock_inode:
 	spin_unlock(&inode->i_lock);
 
+#undef I_DIRTY_INODE
 }
 EXPORT_SYMBOL(__mark_inode_dirty);
 
@@ -2304,7 +2350,6 @@ EXPORT_SYMBOL(sync_inodes_sb);
  */
 int write_inode_now(struct inode *inode, int sync)
 {
-	struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
 	struct writeback_control wbc = {
 		.nr_to_write = LONG_MAX,
 		.sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE,
@@ -2316,7 +2361,7 @@ int write_inode_now(struct inode *inode, int sync)
 		wbc.nr_to_write = 0;
 
 	might_sleep();
-	return writeback_single_inode(inode, wb, &wbc);
+	return writeback_single_inode(inode, &wbc);
 }
 EXPORT_SYMBOL(write_inode_now);
 
@@ -2333,7 +2378,7 @@ EXPORT_SYMBOL(write_inode_now);
  */
 int sync_inode(struct inode *inode, struct writeback_control *wbc)
 {
-	return writeback_single_inode(inode, &inode_to_bdi(inode)->wb, wbc);
+	return writeback_single_inode(inode, wbc);
 }
 EXPORT_SYMBOL(sync_inode);
 
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index d403c69bee08..4304072161aa 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -111,7 +111,7 @@ struct fscache_cookie *__fscache_acquire_cookie(
 
 	/* radix tree insertion won't use the preallocation pool unless it's
 	 * told it may not wait */
-	INIT_RADIX_TREE(&cookie->stores, GFP_NOFS & ~__GFP_WAIT);
+	INIT_RADIX_TREE(&cookie->stores, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
 
 	switch (cookie->def->type) {
 	case FSCACHE_COOKIE_TYPE_INDEX:
diff --git a/fs/fscache/netfs.c b/fs/fscache/netfs.c
index 6d941f56faf4..9b28649df3a1 100644
--- a/fs/fscache/netfs.c
+++ b/fs/fscache/netfs.c
@@ -22,6 +22,7 @@ static LIST_HEAD(fscache_netfs_list);
 int __fscache_register_netfs(struct fscache_netfs *netfs)
 {
 	struct fscache_netfs *ptr;
+	struct fscache_cookie *cookie;
 	int ret;
 
 	_enter("{%s}", netfs->name);
@@ -29,29 +30,25 @@ int __fscache_register_netfs(struct fscache_netfs *netfs)
 	INIT_LIST_HEAD(&netfs->link);
 
 	/* allocate a cookie for the primary index */
-	netfs->primary_index =
-		kmem_cache_zalloc(fscache_cookie_jar, GFP_KERNEL);
+	cookie = kmem_cache_zalloc(fscache_cookie_jar, GFP_KERNEL);
 
-	if (!netfs->primary_index) {
+	if (!cookie) {
 		_leave(" = -ENOMEM");
 		return -ENOMEM;
 	}
 
 	/* initialise the primary index cookie */
-	atomic_set(&netfs->primary_index->usage, 1);
-	atomic_set(&netfs->primary_index->n_children, 0);
-	atomic_set(&netfs->primary_index->n_active, 1);
+	atomic_set(&cookie->usage, 1);
+	atomic_set(&cookie->n_children, 0);
+	atomic_set(&cookie->n_active, 1);
 
-	netfs->primary_index->def		= &fscache_fsdef_netfs_def;
-	netfs->primary_index->parent		= &fscache_fsdef_index;
-	netfs->primary_index->netfs_data	= netfs;
-	netfs->primary_index->flags		= 1 << FSCACHE_COOKIE_ENABLED;
+	cookie->def		= &fscache_fsdef_netfs_def;
+	cookie->parent		= &fscache_fsdef_index;
+	cookie->netfs_data	= netfs;
+	cookie->flags		= 1 << FSCACHE_COOKIE_ENABLED;
 
-	atomic_inc(&netfs->primary_index->parent->usage);
-	atomic_inc(&netfs->primary_index->parent->n_children);
-
-	spin_lock_init(&netfs->primary_index->lock);
-	INIT_HLIST_HEAD(&netfs->primary_index->backing_objects);
+	spin_lock_init(&cookie->lock);
+	INIT_HLIST_HEAD(&cookie->backing_objects);
 
 	/* check the netfs type is not already present */
 	down_write(&fscache_addremove_sem);
@@ -62,6 +59,10 @@ int __fscache_register_netfs(struct fscache_netfs *netfs)
 			goto already_registered;
 	}
 
+	atomic_inc(&cookie->parent->usage);
+	atomic_inc(&cookie->parent->n_children);
+
+	netfs->primary_index = cookie;
 	list_add(&netfs->link, &fscache_netfs_list);
 	ret = 0;
 
@@ -70,11 +71,8 @@ int __fscache_register_netfs(struct fscache_netfs *netfs)
 already_registered:
 	up_write(&fscache_addremove_sem);
 
-	if (ret < 0) {
-		netfs->primary_index->parent = NULL;
-		__fscache_cookie_put(netfs->primary_index);
-		netfs->primary_index = NULL;
-	}
+	if (ret < 0)
+		kmem_cache_free(fscache_cookie_jar, cookie);
 
 	_leave(" = %d", ret);
 	return ret;
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 483bbc613bf0..3078b679fcd1 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -58,7 +58,7 @@ bool release_page_wait_timeout(struct fscache_cookie *cookie, struct page *page)
 
 /*
  * decide whether a page can be released, possibly by cancelling a store to it
- * - we're allowed to sleep if __GFP_WAIT is flagged
+ * - we're allowed to sleep if __GFP_DIRECT_RECLAIM is flagged
  */
 bool __fscache_maybe_release_page(struct fscache_cookie *cookie,
 				  struct page *page,
@@ -113,7 +113,7 @@ try_again:
 
 	wake_up_bit(&cookie->flags, 0);
 	if (xpage)
-		page_cache_release(xpage);
+		put_page(xpage);
 	__fscache_uncache_page(cookie, page);
 	return true;
 
@@ -122,7 +122,7 @@ page_busy:
 	 * allocator as the work threads writing to the cache may all end up
 	 * sleeping on memory allocation, so we may need to impose a timeout
 	 * too. */
-	if (!(gfp & __GFP_WAIT) || !(gfp & __GFP_FS)) {
+	if (!(gfp & __GFP_DIRECT_RECLAIM) || !(gfp & __GFP_FS)) {
 		fscache_stat(&fscache_n_store_vmscan_busy);
 		return false;
 	}
@@ -132,7 +132,7 @@ page_busy:
 		_debug("fscache writeout timeout page: %p{%lx}",
 			page, page->index);
 
-	gfp &= ~__GFP_WAIT;
+	gfp &= ~__GFP_DIRECT_RECLAIM;
 	goto try_again;
 }
 EXPORT_SYMBOL(__fscache_maybe_release_page);
@@ -164,7 +164,7 @@ static void fscache_end_page_write(struct fscache_object *object,
 	}
 	spin_unlock(&object->lock);
 	if (xpage)
-		page_cache_release(xpage);
+		put_page(xpage);
 }
 
 /*
@@ -816,7 +816,7 @@ static void fscache_write_op(struct fscache_operation *_op)
 		goto superseded;
 	page = results[0];
 	_debug("gang %d [%lx]", n, page->index);
-	if (page->index > op->store_limit) {
+	if (page->index >= op->store_limit) {
 		fscache_stat(&fscache_n_store_pages_over_limit);
 		goto superseded;
 	}
@@ -884,7 +884,7 @@ void fscache_invalidate_writes(struct fscache_cookie *cookie)
 		spin_unlock(&cookie->stores_lock);
 
 		for (i = n - 1; i >= 0; i--)
-			page_cache_release(results[i]);
+			put_page(results[i]);
 	}
 
 	_leave("");
@@ -982,7 +982,7 @@ int __fscache_write_page(struct fscache_cookie *cookie,
 
 	radix_tree_tag_set(&cookie->stores, page->index,
 			   FSCACHE_COOKIE_PENDING_TAG);
-	page_cache_get(page);
+	get_page(page);
 
 	/* we only want one writer at a time, but we do need to queue new
 	 * writers after exclusive ops */
@@ -1026,7 +1026,7 @@ submit_failed:
 	radix_tree_delete(&cookie->stores, page->index);
 	spin_unlock(&cookie->stores_lock);
 	wake_cookie = __fscache_unuse_cookie(cookie);
-	page_cache_release(page);
+	put_page(page);
 	ret = -ENOBUFS;
 	goto nobufs;
 
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index eae2c11268bc..c5b6b7165489 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -90,7 +90,7 @@ static struct list_head *cuse_conntbl_head(dev_t devt)
 
 static ssize_t cuse_read_iter(struct kiocb *kiocb, struct iov_iter *to)
 {
-	struct fuse_io_priv io = { .async = 0, .file = kiocb->ki_filp };
+	struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(kiocb->ki_filp);
 	loff_t pos = 0;
 
 	return fuse_direct_io(&io, to, &pos, FUSE_DIO_CUSE);
@@ -98,7 +98,7 @@ static ssize_t cuse_read_iter(struct kiocb *kiocb, struct iov_iter *to)
 
 static ssize_t cuse_write_iter(struct kiocb *kiocb, struct iov_iter *from)
 {
-	struct fuse_io_priv io = { .async = 0, .file = kiocb->ki_filp };
+	struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(kiocb->ki_filp);
 	loff_t pos = 0;
 	/*
 	 * No locking or generic_write_checks(), the server is
@@ -549,6 +549,8 @@ static int cuse_channel_release(struct inode *inode, struct file *file)
 		unregister_chrdev_region(cc->cdev->dev, 1);
 		cdev_del(cc->cdev);
 	}
+	/* Base reference is now owned by "fud" */
+	fuse_conn_put(&cc->fc);
 
 	rc = fuse_dev_release(inode, file);	/* puts the base reference */
 
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index ebb5e37455a0..cbece1221417 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -897,7 +897,7 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
 		return err;
 	}
 
-	page_cache_get(newpage);
+	get_page(newpage);
 
 	if (!(buf->flags & PIPE_BUF_FLAG_LRU))
 		lru_cache_add_file(newpage);
@@ -912,12 +912,12 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
 
 	if (err) {
 		unlock_page(newpage);
-		page_cache_release(newpage);
+		put_page(newpage);
 		return err;
 	}
 
 	unlock_page(oldpage);
-	page_cache_release(oldpage);
+	put_page(oldpage);
 	cs->len = 0;
 
 	return 0;
@@ -951,7 +951,7 @@ static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page,
 	fuse_copy_finish(cs);
 
 	buf = cs->pipebufs;
-	page_cache_get(page);
+	get_page(page);
 	buf->page = page;
 	buf->offset = offset;
 	buf->len = count;
@@ -1435,7 +1435,7 @@ out_unlock:
 
 out:
 	for (; page_nr < cs.nr_segs; page_nr++)
-		page_cache_release(bufs[page_nr].page);
+		put_page(bufs[page_nr].page);
 
 	kfree(bufs);
 	return ret;
@@ -1632,8 +1632,8 @@ static int fuse_notify_store(struct fuse_conn *fc, unsigned int size,
 		goto out_up_killsb;
 
 	mapping = inode->i_mapping;
-	index = outarg.offset >> PAGE_CACHE_SHIFT;
-	offset = outarg.offset & ~PAGE_CACHE_MASK;
+	index = outarg.offset >> PAGE_SHIFT;
+	offset = outarg.offset & ~PAGE_MASK;
 	file_size = i_size_read(inode);
 	end = outarg.offset + outarg.size;
 	if (end > file_size) {
@@ -1652,13 +1652,13 @@ static int fuse_notify_store(struct fuse_conn *fc, unsigned int size,
 		if (!page)
 			goto out_iput;
 
-		this_num = min_t(unsigned, num, PAGE_CACHE_SIZE - offset);
+		this_num = min_t(unsigned, num, PAGE_SIZE - offset);
 		err = fuse_copy_page(cs, &page, offset, this_num, 0);
 		if (!err && offset == 0 &&
-		    (this_num == PAGE_CACHE_SIZE || file_size == end))
+		    (this_num == PAGE_SIZE || file_size == end))
 			SetPageUptodate(page);
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 
 		if (err)
 			goto out_iput;
@@ -1697,7 +1697,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode,
 	size_t total_len = 0;
 	int num_pages;
 
-	offset = outarg->offset & ~PAGE_CACHE_MASK;
+	offset = outarg->offset & ~PAGE_MASK;
 	file_size = i_size_read(inode);
 
 	num = outarg->size;
@@ -1720,7 +1720,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode,
 	req->page_descs[0].offset = offset;
 	req->end = fuse_retrieve_end;
 
-	index = outarg->offset >> PAGE_CACHE_SHIFT;
+	index = outarg->offset >> PAGE_SHIFT;
 
 	while (num && req->num_pages < num_pages) {
 		struct page *page;
@@ -1730,7 +1730,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode,
 		if (!page)
 			break;
 
-		this_num = min_t(unsigned, num, PAGE_CACHE_SIZE - offset);
+		this_num = min_t(unsigned, num, PAGE_SIZE - offset);
 		req->pages[req->num_pages] = page;
 		req->page_descs[req->num_pages].length = this_num;
 		req->num_pages++;
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 5e2e08712d3b..4b855b65d457 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -944,7 +944,7 @@ int fuse_reverse_inval_entry(struct super_block *sb, u64 parent_nodeid,
 	if (!parent)
 		return -ENOENT;
 
-	mutex_lock(&parent->i_mutex);
+	inode_lock(parent);
 	if (!S_ISDIR(parent->i_mode))
 		goto unlock;
 
@@ -962,7 +962,7 @@ int fuse_reverse_inval_entry(struct super_block *sb, u64 parent_nodeid,
 	fuse_invalidate_entry(entry);
 
 	if (child_nodeid != 0 && d_really_is_positive(entry)) {
-		mutex_lock(&d_inode(entry)->i_mutex);
+		inode_lock(d_inode(entry));
 		if (get_node_id(d_inode(entry)) != child_nodeid) {
 			err = -ENOENT;
 			goto badentry;
@@ -983,7 +983,7 @@ int fuse_reverse_inval_entry(struct super_block *sb, u64 parent_nodeid,
 		clear_nlink(d_inode(entry));
 		err = 0;
  badentry:
-		mutex_unlock(&d_inode(entry)->i_mutex);
+		inode_unlock(d_inode(entry));
 		if (!err)
 			d_delete(entry);
 	} else {
@@ -992,7 +992,7 @@ int fuse_reverse_inval_entry(struct super_block *sb, u64 parent_nodeid,
 	dput(entry);
 
  unlock:
-	mutex_unlock(&parent->i_mutex);
+	inode_unlock(parent);
 	iput(parent);
 	return err;
 }
@@ -1365,15 +1365,19 @@ static int fuse_readdir(struct file *file, struct dir_context *ctx)
 	return err;
 }
 
-static const char *fuse_follow_link(struct dentry *dentry, void **cookie)
+static const char *fuse_get_link(struct dentry *dentry,
+				 struct inode *inode,
+				 struct delayed_call *done)
 {
-	struct inode *inode = d_inode(dentry);
 	struct fuse_conn *fc = get_fuse_conn(inode);
 	FUSE_ARGS(args);
 	char *link;
 	ssize_t ret;
 
-	link = (char *) __get_free_page(GFP_KERNEL);
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
+	link = kmalloc(PAGE_SIZE, GFP_KERNEL);
 	if (!link)
 		return ERR_PTR(-ENOMEM);
 
@@ -1385,11 +1389,11 @@ static const char *fuse_follow_link(struct dentry *dentry, void **cookie)
 	args.out.args[0].value = link;
 	ret = fuse_simple_request(fc, &args);
 	if (ret < 0) {
-		free_page((unsigned long) link);
+		kfree(link);
 		link = ERR_PTR(ret);
 	} else {
 		link[ret] = '\0';
-		*cookie = link;
+		set_delayed_call(done, kfree_link, link);
 	}
 	fuse_invalidate_atime(inode);
 	return link;
@@ -1500,7 +1504,7 @@ void fuse_set_nowrite(struct inode *inode)
 	struct fuse_conn *fc = get_fuse_conn(inode);
 	struct fuse_inode *fi = get_fuse_inode(inode);
 
-	BUG_ON(!mutex_is_locked(&inode->i_mutex));
+	BUG_ON(!inode_is_locked(inode));
 
 	spin_lock(&fc->lock);
 	BUG_ON(fi->writectr < 0);
@@ -1909,8 +1913,7 @@ static const struct inode_operations fuse_common_inode_operations = {
 
 static const struct inode_operations fuse_symlink_inode_operations = {
 	.setattr	= fuse_setattr,
-	.follow_link	= fuse_follow_link,
-	.put_link	= free_page_put_link,
+	.get_link	= fuse_get_link,
 	.readlink	= generic_readlink,
 	.getattr	= fuse_getattr,
 	.setxattr	= fuse_setxattr,
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index e0faf8f2c868..719924d6c706 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -207,7 +207,7 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir)
 		return err;
 
 	if (lock_inode)
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 
 	err = fuse_do_open(fc, get_node_id(inode), file, isdir);
 
@@ -215,7 +215,7 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir)
 		fuse_finish_open(inode, file);
 
 	if (lock_inode)
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 
 	return err;
 }
@@ -348,7 +348,7 @@ static bool fuse_range_is_writeback(struct inode *inode, pgoff_t idx_from,
 		pgoff_t curr_index;
 
 		BUG_ON(req->inode != inode);
-		curr_index = req->misc.write.in.offset >> PAGE_CACHE_SHIFT;
+		curr_index = req->misc.write.in.offset >> PAGE_SHIFT;
 		if (idx_from < curr_index + req->num_pages &&
 		    curr_index <= idx_to) {
 			found = true;
@@ -413,9 +413,9 @@ static int fuse_flush(struct file *file, fl_owner_t id)
 	if (err)
 		return err;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	fuse_sync_writes(inode);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	req = fuse_get_req_nofail_nopages(fc, file);
 	memset(&inarg, 0, sizeof(inarg));
@@ -450,7 +450,7 @@ int fuse_fsync_common(struct file *file, loff_t start, loff_t end,
 	if (is_bad_inode(inode))
 		return -EIO;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	/*
 	 * Start writeback against all dirty pages of the inode, then
@@ -486,7 +486,7 @@ int fuse_fsync_common(struct file *file, loff_t start, loff_t end,
 		err = 0;
 	}
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return err;
 }
 
@@ -528,6 +528,11 @@ static void fuse_release_user_pages(struct fuse_req *req, int write)
 	}
 }
 
+static void fuse_io_release(struct kref *kref)
+{
+	kfree(container_of(kref, struct fuse_io_priv, refcnt));
+}
+
 static ssize_t fuse_get_res_by_io(struct fuse_io_priv *io)
 {
 	if (io->err)
@@ -585,8 +590,9 @@ static void fuse_aio_complete(struct fuse_io_priv *io, int err, ssize_t pos)
 		}
 
 		io->iocb->ki_complete(io->iocb, res, 0);
-		kfree(io);
 	}
+
+	kref_put(&io->refcnt, fuse_io_release);
 }
 
 static void fuse_aio_complete_req(struct fuse_conn *fc, struct fuse_req *req)
@@ -613,6 +619,7 @@ static size_t fuse_async_req_send(struct fuse_conn *fc, struct fuse_req *req,
 		size_t num_bytes, struct fuse_io_priv *io)
 {
 	spin_lock(&io->lock);
+	kref_get(&io->refcnt);
 	io->size += num_bytes;
 	io->reqs++;
 	spin_unlock(&io->lock);
@@ -676,11 +683,11 @@ static void fuse_short_read(struct fuse_req *req, struct inode *inode,
 		 * present there.
 		 */
 		int i;
-		int start_idx = num_read >> PAGE_CACHE_SHIFT;
-		size_t off = num_read & (PAGE_CACHE_SIZE - 1);
+		int start_idx = num_read >> PAGE_SHIFT;
+		size_t off = num_read & (PAGE_SIZE - 1);
 
 		for (i = start_idx; i < req->num_pages; i++) {
-			zero_user_segment(req->pages[i], off, PAGE_CACHE_SIZE);
+			zero_user_segment(req->pages[i], off, PAGE_SIZE);
 			off = 0;
 		}
 	} else {
@@ -691,13 +698,13 @@ static void fuse_short_read(struct fuse_req *req, struct inode *inode,
 
 static int fuse_do_readpage(struct file *file, struct page *page)
 {
-	struct fuse_io_priv io = { .async = 0, .file = file };
+	struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(file);
 	struct inode *inode = page->mapping->host;
 	struct fuse_conn *fc = get_fuse_conn(inode);
 	struct fuse_req *req;
 	size_t num_read;
 	loff_t pos = page_offset(page);
-	size_t count = PAGE_CACHE_SIZE;
+	size_t count = PAGE_SIZE;
 	u64 attr_ver;
 	int err;
 
@@ -782,7 +789,7 @@ static void fuse_readpages_end(struct fuse_conn *fc, struct fuse_req *req)
 		else
 			SetPageError(page);
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 	}
 	if (req->ff)
 		fuse_file_put(req->ff, false);
@@ -793,7 +800,7 @@ static void fuse_send_readpages(struct fuse_req *req, struct file *file)
 	struct fuse_file *ff = file->private_data;
 	struct fuse_conn *fc = ff->fc;
 	loff_t pos = page_offset(req->pages[0]);
-	size_t count = req->num_pages << PAGE_CACHE_SHIFT;
+	size_t count = req->num_pages << PAGE_SHIFT;
 
 	req->out.argpages = 1;
 	req->out.page_zeroing = 1;
@@ -829,7 +836,7 @@ static int fuse_readpages_fill(void *_data, struct page *page)
 
 	if (req->num_pages &&
 	    (req->num_pages == FUSE_MAX_PAGES_PER_REQ ||
-	     (req->num_pages + 1) * PAGE_CACHE_SIZE > fc->max_read ||
+	     (req->num_pages + 1) * PAGE_SIZE > fc->max_read ||
 	     req->pages[req->num_pages - 1]->index + 1 != page->index)) {
 		int nr_alloc = min_t(unsigned, data->nr_pages,
 				     FUSE_MAX_PAGES_PER_REQ);
@@ -851,7 +858,7 @@ static int fuse_readpages_fill(void *_data, struct page *page)
 		return -EIO;
 	}
 
-	page_cache_get(page);
+	get_page(page);
 	req->pages[req->num_pages] = page;
 	req->page_descs[req->num_pages].length = PAGE_SIZE;
 	req->num_pages++;
@@ -984,7 +991,7 @@ static size_t fuse_send_write_pages(struct fuse_req *req, struct file *file,
 	size_t res;
 	unsigned offset;
 	unsigned i;
-	struct fuse_io_priv io = { .async = 0, .file = file };
+	struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(file);
 
 	for (i = 0; i < req->num_pages; i++)
 		fuse_wait_on_page_writeback(inode, req->pages[i]->index);
@@ -996,17 +1003,17 @@ static size_t fuse_send_write_pages(struct fuse_req *req, struct file *file,
 	for (i = 0; i < req->num_pages; i++) {
 		struct page *page = req->pages[i];
 
-		if (!req->out.h.error && !offset && count >= PAGE_CACHE_SIZE)
+		if (!req->out.h.error && !offset && count >= PAGE_SIZE)
 			SetPageUptodate(page);
 
-		if (count > PAGE_CACHE_SIZE - offset)
-			count -= PAGE_CACHE_SIZE - offset;
+		if (count > PAGE_SIZE - offset)
+			count -= PAGE_SIZE - offset;
 		else
 			count = 0;
 		offset = 0;
 
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 	}
 
 	return res;
@@ -1017,7 +1024,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req,
 			       struct iov_iter *ii, loff_t pos)
 {
 	struct fuse_conn *fc = get_fuse_conn(mapping->host);
-	unsigned offset = pos & (PAGE_CACHE_SIZE - 1);
+	unsigned offset = pos & (PAGE_SIZE - 1);
 	size_t count = 0;
 	int err;
 
@@ -1027,8 +1034,8 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req,
 	do {
 		size_t tmp;
 		struct page *page;
-		pgoff_t index = pos >> PAGE_CACHE_SHIFT;
-		size_t bytes = min_t(size_t, PAGE_CACHE_SIZE - offset,
+		pgoff_t index = pos >> PAGE_SHIFT;
+		size_t bytes = min_t(size_t, PAGE_SIZE - offset,
 				     iov_iter_count(ii));
 
 		bytes = min_t(size_t, bytes, fc->max_write - count);
@@ -1049,9 +1056,10 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req,
 		tmp = iov_iter_copy_from_user_atomic(page, ii, offset, bytes);
 		flush_dcache_page(page);
 
+		iov_iter_advance(ii, tmp);
 		if (!tmp) {
 			unlock_page(page);
-			page_cache_release(page);
+			put_page(page);
 			bytes = min(bytes, iov_iter_single_seg_count(ii));
 			goto again;
 		}
@@ -1061,11 +1069,10 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req,
 		req->page_descs[req->num_pages].length = tmp;
 		req->num_pages++;
 
-		iov_iter_advance(ii, tmp);
 		count += tmp;
 		pos += tmp;
 		offset += tmp;
-		if (offset == PAGE_CACHE_SIZE)
+		if (offset == PAGE_SIZE)
 			offset = 0;
 
 		if (!fc->big_writes)
@@ -1079,8 +1086,8 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req,
 static inline unsigned fuse_wr_pages(loff_t pos, size_t len)
 {
 	return min_t(unsigned,
-		     ((pos + len - 1) >> PAGE_CACHE_SHIFT) -
-		     (pos >> PAGE_CACHE_SHIFT) + 1,
+		     ((pos + len - 1) >> PAGE_SHIFT) -
+		     (pos >> PAGE_SHIFT) + 1,
 		     FUSE_MAX_PAGES_PER_REQ);
 }
 
@@ -1160,7 +1167,7 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		return generic_file_write_iter(iocb, from);
 	}
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	/* We can write back this queue in page reclaim */
 	current->backing_dev_info = inode_to_bdi(inode);
@@ -1198,8 +1205,8 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 			goto out;
 
 		invalidate_mapping_pages(file->f_mapping,
-					 pos >> PAGE_CACHE_SHIFT,
-					 endbyte >> PAGE_CACHE_SHIFT);
+					 pos >> PAGE_SHIFT,
+					 endbyte >> PAGE_SHIFT);
 
 		written += written_buffered;
 		iocb->ki_pos = pos + written_buffered;
@@ -1210,7 +1217,7 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	}
 out:
 	current->backing_dev_info = NULL;
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	return written ? written : err;
 }
@@ -1240,6 +1247,7 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii,
 			       size_t *nbytesp, int write)
 {
 	size_t nbytes = 0;  /* # bytes already packed in req */
+	ssize_t ret = 0;
 
 	/* Special case for kernel I/O: can copy directly into the buffer */
 	if (ii->type & ITER_KVEC) {
@@ -1259,13 +1267,12 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii,
 	while (nbytes < *nbytesp && req->num_pages < req->max_pages) {
 		unsigned npages;
 		size_t start;
-		ssize_t ret = iov_iter_get_pages(ii,
-					&req->pages[req->num_pages],
+		ret = iov_iter_get_pages(ii, &req->pages[req->num_pages],
 					*nbytesp - nbytes,
 					req->max_pages - req->num_pages,
 					&start);
 		if (ret < 0)
-			return ret;
+			break;
 
 		iov_iter_advance(ii, ret);
 		nbytes += ret;
@@ -1288,7 +1295,7 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii,
 
 	*nbytesp = nbytes;
 
-	return 0;
+	return ret;
 }
 
 static inline int fuse_iter_npages(const struct iov_iter *ii_p)
@@ -1308,10 +1315,11 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 	size_t nmax = write ? fc->max_write : fc->max_read;
 	loff_t pos = *ppos;
 	size_t count = iov_iter_count(iter);
-	pgoff_t idx_from = pos >> PAGE_CACHE_SHIFT;
-	pgoff_t idx_to = (pos + count - 1) >> PAGE_CACHE_SHIFT;
+	pgoff_t idx_from = pos >> PAGE_SHIFT;
+	pgoff_t idx_to = (pos + count - 1) >> PAGE_SHIFT;
 	ssize_t res = 0;
 	struct fuse_req *req;
+	int err = 0;
 
 	if (io->async)
 		req = fuse_get_req_for_background(fc, fuse_iter_npages(iter));
@@ -1322,21 +1330,19 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 
 	if (!cuse && fuse_range_is_writeback(inode, idx_from, idx_to)) {
 		if (!write)
-			mutex_lock(&inode->i_mutex);
+			inode_lock(inode);
 		fuse_sync_writes(inode);
 		if (!write)
-			mutex_unlock(&inode->i_mutex);
+			inode_unlock(inode);
 	}
 
 	while (count) {
 		size_t nres;
 		fl_owner_t owner = current->files;
 		size_t nbytes = min(count, nmax);
-		int err = fuse_get_user_pages(req, iter, &nbytes, write);
-		if (err) {
-			res = err;
+		err = fuse_get_user_pages(req, iter, &nbytes, write);
+		if (err && !nbytes)
 			break;
-		}
 
 		if (write)
 			nres = fuse_send_write(req, io, pos, nbytes, owner);
@@ -1346,11 +1352,11 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 		if (!io->async)
 			fuse_release_user_pages(req, !write);
 		if (req->out.h.error) {
-			if (!res)
-				res = req->out.h.error;
+			err = req->out.h.error;
 			break;
 		} else if (nres > nbytes) {
-			res = -EIO;
+			res = 0;
+			err = -EIO;
 			break;
 		}
 		count -= nres;
@@ -1374,7 +1380,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 	if (res > 0)
 		*ppos = pos;
 
-	return res;
+	return res > 0 ? res : err;
 }
 EXPORT_SYMBOL_GPL(fuse_direct_io);
 
@@ -1398,7 +1404,7 @@ static ssize_t __fuse_direct_read(struct fuse_io_priv *io,
 
 static ssize_t fuse_direct_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
-	struct fuse_io_priv io = { .async = 0, .file = iocb->ki_filp };
+	struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb->ki_filp);
 	return __fuse_direct_read(&io, to, &iocb->ki_pos);
 }
 
@@ -1406,21 +1412,21 @@ static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
-	struct fuse_io_priv io = { .async = 0, .file = file };
+	struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(file);
 	ssize_t res;
 
 	if (is_bad_inode(inode))
 		return -EIO;
 
 	/* Don't allow parallel writes to the same file */
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	res = generic_write_checks(iocb, from);
 	if (res > 0)
 		res = fuse_direct_io(&io, from, &iocb->ki_pos, FUSE_DIO_WRITE);
 	fuse_invalidate_attr(inode);
 	if (res > 0)
 		fuse_write_update_size(inode, iocb->ki_pos);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	return res;
 }
@@ -1460,7 +1466,7 @@ __acquires(fc->lock)
 {
 	struct fuse_inode *fi = get_fuse_inode(req->inode);
 	struct fuse_write_in *inarg = &req->misc.write.in;
-	__u64 data_size = req->num_pages * PAGE_CACHE_SIZE;
+	__u64 data_size = req->num_pages * PAGE_SIZE;
 
 	if (!fc->connected)
 		goto out_free;
@@ -1721,7 +1727,7 @@ static bool fuse_writepage_in_flight(struct fuse_req *new_req,
 	list_del(&new_req->writepages_entry);
 	list_for_each_entry(old_req, &fi->writepages, writepages_entry) {
 		BUG_ON(old_req->inode != new_req->inode);
-		curr_index = old_req->misc.write.in.offset >> PAGE_CACHE_SHIFT;
+		curr_index = old_req->misc.write.in.offset >> PAGE_SHIFT;
 		if (curr_index <= page->index &&
 		    page->index < curr_index + old_req->num_pages) {
 			found = true;
@@ -1736,7 +1742,7 @@ static bool fuse_writepage_in_flight(struct fuse_req *new_req,
 	new_req->num_pages = 1;
 	for (tmp = old_req; tmp != NULL; tmp = tmp->misc.write.next) {
 		BUG_ON(tmp->inode != new_req->inode);
-		curr_index = tmp->misc.write.in.offset >> PAGE_CACHE_SHIFT;
+		curr_index = tmp->misc.write.in.offset >> PAGE_SHIFT;
 		if (tmp->num_pages == 1 &&
 		    curr_index == page->index) {
 			old_req = tmp;
@@ -1793,7 +1799,7 @@ static int fuse_writepages_fill(struct page *page,
 
 	if (req && req->num_pages &&
 	    (is_writeback || req->num_pages == FUSE_MAX_PAGES_PER_REQ ||
-	     (req->num_pages + 1) * PAGE_CACHE_SIZE > fc->max_write ||
+	     (req->num_pages + 1) * PAGE_SIZE > fc->max_write ||
 	     data->orig_pages[req->num_pages - 1]->index + 1 != page->index)) {
 		fuse_writepages_send(data);
 		data->req = NULL;
@@ -1918,7 +1924,7 @@ static int fuse_write_begin(struct file *file, struct address_space *mapping,
 		loff_t pos, unsigned len, unsigned flags,
 		struct page **pagep, void **fsdata)
 {
-	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+	pgoff_t index = pos >> PAGE_SHIFT;
 	struct fuse_conn *fc = get_fuse_conn(file_inode(file));
 	struct page *page;
 	loff_t fsize;
@@ -1932,15 +1938,15 @@ static int fuse_write_begin(struct file *file, struct address_space *mapping,
 
 	fuse_wait_on_page_writeback(mapping->host, page->index);
 
-	if (PageUptodate(page) || len == PAGE_CACHE_SIZE)
+	if (PageUptodate(page) || len == PAGE_SIZE)
 		goto success;
 	/*
 	 * Check if the start this page comes after the end of file, in which
 	 * case the readpage can be optimized away.
 	 */
 	fsize = i_size_read(mapping->host);
-	if (fsize <= (pos & PAGE_CACHE_MASK)) {
-		size_t off = pos & ~PAGE_CACHE_MASK;
+	if (fsize <= (pos & PAGE_MASK)) {
+		size_t off = pos & ~PAGE_MASK;
 		if (off)
 			zero_user_segment(page, 0, off);
 		goto success;
@@ -1954,7 +1960,7 @@ success:
 
 cleanup:
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 error:
 	return err;
 }
@@ -1967,16 +1973,16 @@ static int fuse_write_end(struct file *file, struct address_space *mapping,
 
 	if (!PageUptodate(page)) {
 		/* Zero any unwritten bytes at the end of the page */
-		size_t endoff = (pos + copied) & ~PAGE_CACHE_MASK;
+		size_t endoff = (pos + copied) & ~PAGE_MASK;
 		if (endoff)
-			zero_user_segment(page, endoff, PAGE_CACHE_SIZE);
+			zero_user_segment(page, endoff, PAGE_SIZE);
 		SetPageUptodate(page);
 	}
 
 	fuse_write_update_size(inode, pos + copied);
 	set_page_dirty(page);
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 
 	return copied;
 }
@@ -2231,20 +2237,77 @@ static sector_t fuse_bmap(struct address_space *mapping, sector_t block)
 	return err ? 0 : outarg.block;
 }
 
+static loff_t fuse_lseek(struct file *file, loff_t offset, int whence)
+{
+	struct inode *inode = file->f_mapping->host;
+	struct fuse_conn *fc = get_fuse_conn(inode);
+	struct fuse_file *ff = file->private_data;
+	FUSE_ARGS(args);
+	struct fuse_lseek_in inarg = {
+		.fh = ff->fh,
+		.offset = offset,
+		.whence = whence
+	};
+	struct fuse_lseek_out outarg;
+	int err;
+
+	if (fc->no_lseek)
+		goto fallback;
+
+	args.in.h.opcode = FUSE_LSEEK;
+	args.in.h.nodeid = ff->nodeid;
+	args.in.numargs = 1;
+	args.in.args[0].size = sizeof(inarg);
+	args.in.args[0].value = &inarg;
+	args.out.numargs = 1;
+	args.out.args[0].size = sizeof(outarg);
+	args.out.args[0].value = &outarg;
+	err = fuse_simple_request(fc, &args);
+	if (err) {
+		if (err == -ENOSYS) {
+			fc->no_lseek = 1;
+			goto fallback;
+		}
+		return err;
+	}
+
+	return vfs_setpos(file, outarg.offset, inode->i_sb->s_maxbytes);
+
+fallback:
+	err = fuse_update_attributes(inode, NULL, file, NULL);
+	if (!err)
+		return generic_file_llseek(file, offset, whence);
+	else
+		return err;
+}
+
 static loff_t fuse_file_llseek(struct file *file, loff_t offset, int whence)
 {
 	loff_t retval;
 	struct inode *inode = file_inode(file);
 
-	/* No i_mutex protection necessary for SEEK_CUR and SEEK_SET */
-	if (whence == SEEK_CUR || whence == SEEK_SET)
-		return generic_file_llseek(file, offset, whence);
-
-	mutex_lock(&inode->i_mutex);
-	retval = fuse_update_attributes(inode, NULL, file, NULL);
-	if (!retval)
+	switch (whence) {
+	case SEEK_SET:
+	case SEEK_CUR:
+		 /* No i_mutex protection necessary for SEEK_CUR and SEEK_SET */
 		retval = generic_file_llseek(file, offset, whence);
-	mutex_unlock(&inode->i_mutex);
+		break;
+	case SEEK_END:
+		inode_lock(inode);
+		retval = fuse_update_attributes(inode, NULL, file, NULL);
+		if (!retval)
+			retval = generic_file_llseek(file, offset, whence);
+		inode_unlock(inode);
+		break;
+	case SEEK_HOLE:
+	case SEEK_DATA:
+		inode_lock(inode);
+		retval = fuse_lseek(file, offset, whence);
+		inode_unlock(inode);
+		break;
+	default:
+		retval = -EINVAL;
+	}
 
 	return retval;
 }
@@ -2786,6 +2849,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 	loff_t i_size;
 	size_t count = iov_iter_count(iter);
 	struct fuse_io_priv *io;
+	bool is_sync = is_sync_kiocb(iocb);
 
 	pos = offset;
 	inode = file->f_mapping->host;
@@ -2806,6 +2870,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 	if (!io)
 		return -ENOMEM;
 	spin_lock_init(&io->lock);
+	kref_init(&io->refcnt);
 	io->reqs = 1;
 	io->bytes = -1;
 	io->size = 0;
@@ -2825,12 +2890,18 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 	 * to wait on real async I/O requests, so we must submit this request
 	 * synchronously.
 	 */
-	if (!is_sync_kiocb(iocb) && (offset + count > i_size) &&
+	if (!is_sync && (offset + count > i_size) &&
 	    iov_iter_rw(iter) == WRITE)
 		io->async = false;
 
-	if (io->async && is_sync_kiocb(iocb))
+	if (io->async && is_sync) {
+		/*
+		 * Additional reference to keep io around after
+		 * calling fuse_aio_complete()
+		 */
+		kref_get(&io->refcnt);
 		io->done = &wait;
+	}
 
 	if (iov_iter_rw(iter) == WRITE) {
 		ret = fuse_direct_io(io, iter, &pos, FUSE_DIO_WRITE);
@@ -2843,14 +2914,14 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 		fuse_aio_complete(io, ret < 0 ? ret : 0, -1);
 
 		/* we have a non-extending, async request, so return */
-		if (!is_sync_kiocb(iocb))
+		if (!is_sync)
 			return -EIOCBQUEUED;
 
 		wait_for_completion(&wait);
 		ret = fuse_get_res_by_io(io);
 	}
 
-	kfree(io);
+	kref_put(&io->refcnt, fuse_io_release);
 
 	if (iov_iter_rw(iter) == WRITE) {
 		if (ret > 0)
@@ -2887,7 +2958,7 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
 		return -EOPNOTSUPP;
 
 	if (lock_inode) {
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		if (mode & FALLOC_FL_PUNCH_HOLE) {
 			loff_t endbyte = offset + length - 1;
 			err = filemap_write_and_wait_range(inode->i_mapping,
@@ -2933,7 +3004,7 @@ out:
 		clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
 
 	if (lock_inode)
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 
 	return err;
 }
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 405113101db8..eddbe02c4028 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -22,6 +22,7 @@
 #include <linux/rbtree.h>
 #include <linux/poll.h>
 #include <linux/workqueue.h>
+#include <linux/kref.h>
 
 /** Max number of pages that can be used in a single read request */
 #define FUSE_MAX_PAGES_PER_REQ 32
@@ -243,6 +244,7 @@ struct fuse_args {
 
 /** The request IO state (for asynchronous processing) */
 struct fuse_io_priv {
+	struct kref refcnt;
 	int async;
 	spinlock_t lock;
 	unsigned reqs;
@@ -256,6 +258,13 @@ struct fuse_io_priv {
 	struct completion *done;
 };
 
+#define FUSE_IO_PRIV_SYNC(f) \
+{					\
+	.refcnt = { ATOMIC_INIT(1) },	\
+	.async = 0,			\
+	.file = f,			\
+}
+
 /**
  * Request flags
  *
@@ -605,6 +614,9 @@ struct fuse_conn {
 	/** Does the filesystem support asynchronous direct-IO submission? */
 	unsigned async_dio:1;
 
+	/** Is lseek not implemented by fs? */
+	unsigned no_lseek:1;
+
 	/** The number of requests waiting for completion */
 	atomic_t num_waiting;
 
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 2913db2a5b99..1ce67668a8e1 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -339,11 +339,11 @@ int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid,
 
 	fuse_invalidate_attr(inode);
 	if (offset >= 0) {
-		pg_start = offset >> PAGE_CACHE_SHIFT;
+		pg_start = offset >> PAGE_SHIFT;
 		if (len <= 0)
 			pg_end = -1;
 		else
-			pg_end = (offset + len - 1) >> PAGE_CACHE_SHIFT;
+			pg_end = (offset + len - 1) >> PAGE_SHIFT;
 		invalidate_inode_pages2_range(inode->i_mapping,
 					      pg_start, pg_end);
 	}
@@ -864,7 +864,7 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
 		process_init_limits(fc, arg);
 
 		if (arg->minor >= 6) {
-			ra_pages = arg->max_readahead / PAGE_CACHE_SIZE;
+			ra_pages = arg->max_readahead / PAGE_SIZE;
 			if (arg->flags & FUSE_ASYNC_READ)
 				fc->async_read = 1;
 			if (!(arg->flags & FUSE_POSIX_LOCKS))
@@ -901,7 +901,7 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
 			if (arg->time_gran && arg->time_gran <= 1000000000)
 				fc->sb->s_time_gran = arg->time_gran;
 		} else {
-			ra_pages = fc->max_read / PAGE_CACHE_SIZE;
+			ra_pages = fc->max_read / PAGE_SIZE;
 			fc->no_lock = 1;
 			fc->no_flock = 1;
 		}
@@ -922,7 +922,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
 
 	arg->major = FUSE_KERNEL_VERSION;
 	arg->minor = FUSE_KERNEL_MINOR_VERSION;
-	arg->max_readahead = fc->bdi.ra_pages * PAGE_CACHE_SIZE;
+	arg->max_readahead = fc->bdi.ra_pages * PAGE_SIZE;
 	arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC |
 		FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK |
 		FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ |
@@ -955,7 +955,7 @@ static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb)
 	int err;
 
 	fc->bdi.name = "fuse";
-	fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
+	fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_SIZE;
 	/* fuse does it's own writeback accounting */
 	fc->bdi.capabilities = BDI_CAP_NO_ACCT_WB | BDI_CAP_STRICTLIMIT;
 
@@ -1053,8 +1053,8 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 			goto err;
 #endif
 	} else {
-		sb->s_blocksize = PAGE_CACHE_SIZE;
-		sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
+		sb->s_blocksize = PAGE_SIZE;
+		sb->s_blocksize_bits = PAGE_SHIFT;
 	}
 	sb->s_magic = FUSE_SUPER_MAGIC;
 	sb->s_op = &fuse_super_operations;
@@ -1255,8 +1255,8 @@ static int __init fuse_fs_init(void)
 	int err;
 
 	fuse_inode_cachep = kmem_cache_create("fuse_inode",
-					      sizeof(struct fuse_inode),
-					      0, SLAB_HWCACHE_ALIGN,
+					      sizeof(struct fuse_inode), 0,
+					      SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT,
 					      fuse_inode_init_once);
 	err = -ENOMEM;
 	if (!fuse_inode_cachep)
diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c
index 1be3b061c05c..791932617d1a 100644
--- a/fs/gfs2/acl.c
+++ b/fs/gfs2/acl.c
@@ -31,9 +31,9 @@ static const char *gfs2_acl_name(int type)
 {
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		return GFS2_POSIX_ACL_ACCESS;
+		return XATTR_POSIX_ACL_ACCESS;
 	case ACL_TYPE_DEFAULT:
-		return GFS2_POSIX_ACL_DEFAULT;
+		return XATTR_POSIX_ACL_DEFAULT;
 	}
 	return NULL;
 }
diff --git a/fs/gfs2/acl.h b/fs/gfs2/acl.h
index 2d65ec4cd4be..3af4f407a483 100644
--- a/fs/gfs2/acl.h
+++ b/fs/gfs2/acl.h
@@ -12,8 +12,6 @@
 
 #include "incore.h"
 
-#define GFS2_POSIX_ACL_ACCESS		"posix_acl_access"
-#define GFS2_POSIX_ACL_DEFAULT		"posix_acl_default"
 #define GFS2_ACL_MAX_ENTRIES(sdp) ((300 << (sdp)->sd_sb.sb_bsize_shift) >> 12)
 
 extern struct posix_acl *gfs2_get_acl(struct inode *inode, int type);
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 1caee0534587..1bbbee945f46 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -101,7 +101,7 @@ static int gfs2_writepage_common(struct page *page,
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	loff_t i_size = i_size_read(inode);
-	pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
+	pgoff_t end_index = i_size >> PAGE_SHIFT;
 	unsigned offset;
 
 	if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(ip->i_gl)))
@@ -109,9 +109,9 @@ static int gfs2_writepage_common(struct page *page,
 	if (current->journal_info)
 		goto redirty;
 	/* Is the page fully outside i_size? (truncate in progress) */
-	offset = i_size & (PAGE_CACHE_SIZE-1);
+	offset = i_size & (PAGE_SIZE-1);
 	if (page->index > end_index || (page->index == end_index && !offset)) {
-		page->mapping->a_ops->invalidatepage(page, 0, PAGE_CACHE_SIZE);
+		page->mapping->a_ops->invalidatepage(page, 0, PAGE_SIZE);
 		goto out;
 	}
 	return 1;
@@ -238,7 +238,7 @@ static int gfs2_write_jdata_pagevec(struct address_space *mapping,
 {
 	struct inode *inode = mapping->host;
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	unsigned nrblocks = nr_pages * (PAGE_CACHE_SIZE/inode->i_sb->s_blocksize);
+	unsigned nrblocks = nr_pages * (PAGE_SIZE/inode->i_sb->s_blocksize);
 	int i;
 	int ret;
 
@@ -366,8 +366,8 @@ static int gfs2_write_cache_jdata(struct address_space *mapping,
 			cycled = 0;
 		end = -1;
 	} else {
-		index = wbc->range_start >> PAGE_CACHE_SHIFT;
-		end = wbc->range_end >> PAGE_CACHE_SHIFT;
+		index = wbc->range_start >> PAGE_SHIFT;
+		end = wbc->range_end >> PAGE_SHIFT;
 		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
 			range_whole = 1;
 		cycled = 1; /* ignore range_cyclic tests */
@@ -458,7 +458,7 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
 	 * so we need to supply one here. It doesn't happen often.
 	 */
 	if (unlikely(page->index)) {
-		zero_user(page, 0, PAGE_CACHE_SIZE);
+		zero_user(page, 0, PAGE_SIZE);
 		SetPageUptodate(page);
 		return 0;
 	}
@@ -471,7 +471,7 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
 	if (dsize > (dibh->b_size - sizeof(struct gfs2_dinode)))
 		dsize = (dibh->b_size - sizeof(struct gfs2_dinode));
 	memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize);
-	memset(kaddr + dsize, 0, PAGE_CACHE_SIZE - dsize);
+	memset(kaddr + dsize, 0, PAGE_SIZE - dsize);
 	kunmap_atomic(kaddr);
 	flush_dcache_page(page);
 	brelse(dibh);
@@ -560,8 +560,8 @@ int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos,
                        unsigned size)
 {
 	struct address_space *mapping = ip->i_inode.i_mapping;
-	unsigned long index = *pos / PAGE_CACHE_SIZE;
-	unsigned offset = *pos & (PAGE_CACHE_SIZE - 1);
+	unsigned long index = *pos / PAGE_SIZE;
+	unsigned offset = *pos & (PAGE_SIZE - 1);
 	unsigned copied = 0;
 	unsigned amt;
 	struct page *page;
@@ -569,15 +569,15 @@ int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos,
 
 	do {
 		amt = size - copied;
-		if (offset + size > PAGE_CACHE_SIZE)
-			amt = PAGE_CACHE_SIZE - offset;
+		if (offset + size > PAGE_SIZE)
+			amt = PAGE_SIZE - offset;
 		page = read_cache_page(mapping, index, __gfs2_readpage, NULL);
 		if (IS_ERR(page))
 			return PTR_ERR(page);
 		p = kmap_atomic(page);
 		memcpy(buf + copied, p + offset, amt);
 		kunmap_atomic(p);
-		page_cache_release(page);
+		put_page(page);
 		copied += amt;
 		index++;
 		offset = 0;
@@ -651,8 +651,8 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping,
 	unsigned requested = 0;
 	int alloc_required;
 	int error = 0;
-	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
-	unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+	pgoff_t index = pos >> PAGE_SHIFT;
+	unsigned from = pos & (PAGE_SIZE - 1);
 	struct page *page;
 
 	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
@@ -697,7 +697,7 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping,
 		rblocks += gfs2_rg_blocks(ip, requested);
 
 	error = gfs2_trans_begin(sdp, rblocks,
-				 PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
+				 PAGE_SIZE/sdp->sd_sb.sb_bsize);
 	if (error)
 		goto out_trans_fail;
 
@@ -727,7 +727,7 @@ out:
 		return 0;
 
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 
 	gfs2_trans_end(sdp);
 	if (pos + len > ip->i_inode.i_size)
@@ -827,7 +827,7 @@ static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
 	if (!PageUptodate(page))
 		SetPageUptodate(page);
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 
 	if (copied) {
 		if (inode->i_size < to)
@@ -877,7 +877,7 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping,
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
 	struct buffer_head *dibh;
-	unsigned int from = pos & (PAGE_CACHE_SIZE - 1);
+	unsigned int from = pos & (PAGE_SIZE - 1);
 	unsigned int to = from + len;
 	int ret;
 	struct gfs2_trans *tr = current->journal_info;
@@ -888,7 +888,7 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping,
 	ret = gfs2_meta_inode_buffer(ip, &dibh);
 	if (unlikely(ret)) {
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 		goto failed;
 	}
 
@@ -914,7 +914,7 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping,
 failed:
 	gfs2_trans_end(sdp);
 	gfs2_inplace_release(ip);
-	if (ip->i_res->rs_qa_qd_num)
+	if (ip->i_qadata && ip->i_qadata->qa_qd_num)
 		gfs2_quota_unlock(ip);
 	if (inode == sdp->sd_rindex) {
 		gfs2_glock_dq(&m_ip->i_gh);
@@ -992,7 +992,7 @@ static void gfs2_invalidatepage(struct page *page, unsigned int offset,
 {
 	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
 	unsigned int stop = offset + length;
-	int partial_page = (offset || length < PAGE_CACHE_SIZE);
+	int partial_page = (offset || length < PAGE_SIZE);
 	struct buffer_head *bh, *head;
 	unsigned long pos = 0;
 
@@ -1082,7 +1082,7 @@ static ssize_t gfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	 * the first place, mapping->nr_pages will always be zero.
 	 */
 	if (mapping->nrpages) {
-		loff_t lstart = offset & (PAGE_CACHE_SIZE - 1);
+		loff_t lstart = offset & ~(PAGE_SIZE - 1);
 		loff_t len = iov_iter_count(iter);
 		loff_t end = PAGE_ALIGN(offset + len) - 1;
 
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 61296ecbd0e2..24ce1cdd434a 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -75,7 +75,7 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh,
 			dsize = dibh->b_size - sizeof(struct gfs2_dinode);
 
 		memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize);
-		memset(kaddr + dsize, 0, PAGE_CACHE_SIZE - dsize);
+		memset(kaddr + dsize, 0, PAGE_SIZE - dsize);
 		kunmap(page);
 
 		SetPageUptodate(page);
@@ -98,7 +98,7 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh,
 
 	if (release) {
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 	}
 
 	return 0;
@@ -787,8 +787,8 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 	if (error)
 		goto out_rlist;
 
-	if (gfs2_rs_active(ip->i_res)) /* needs to be done with the rgrp glock held */
-		gfs2_rs_deltree(ip->i_res);
+	if (gfs2_rs_active(&ip->i_res)) /* needs to be done with the rgrp glock held */
+		gfs2_rs_deltree(&ip->i_res);
 
 	error = gfs2_trans_begin(sdp, rg_blocks + RES_DINODE +
 				 RES_INDIRECT + RES_STATFS + RES_QUOTA,
@@ -932,8 +932,8 @@ static int gfs2_block_truncate_page(struct address_space *mapping, loff_t from)
 {
 	struct inode *inode = mapping->host;
 	struct gfs2_inode *ip = GFS2_I(inode);
-	unsigned long index = from >> PAGE_CACHE_SHIFT;
-	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	unsigned long index = from >> PAGE_SHIFT;
+	unsigned offset = from & (PAGE_SIZE-1);
 	unsigned blocksize, iblock, length, pos;
 	struct buffer_head *bh;
 	struct page *page;
@@ -945,7 +945,7 @@ static int gfs2_block_truncate_page(struct address_space *mapping, loff_t from)
 
 	blocksize = inode->i_sb->s_blocksize;
 	length = blocksize - (offset & (blocksize - 1));
-	iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
+	iblock = index << (PAGE_SHIFT - inode->i_sb->s_blocksize_bits);
 
 	if (!page_has_buffers(page))
 		create_empty_buffers(page, blocksize, 0);
@@ -989,7 +989,7 @@ static int gfs2_block_truncate_page(struct address_space *mapping, loff_t from)
 	mark_buffer_dirty(bh);
 unlock:
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 	return err;
 }
 
@@ -1291,13 +1291,9 @@ int gfs2_setattr_size(struct inode *inode, u64 newsize)
 	if (ret)
 		return ret;
 
-	ret = get_write_access(inode);
-	if (ret)
-		return ret;
-
 	inode_dio_wait(inode);
 
-	ret = gfs2_rs_alloc(ip);
+	ret = gfs2_rsqa_alloc(ip);
 	if (ret)
 		goto out;
 
@@ -1307,10 +1303,9 @@ int gfs2_setattr_size(struct inode *inode, u64 newsize)
 		goto out;
 	}
 
-	gfs2_rs_deltree(ip->i_res);
 	ret = do_shrink(inode, oldsize, newsize);
 out:
-	put_write_access(inode);
+	gfs2_rsqa_delete(ip, NULL);
 	return ret;
 }
 
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index 487527b42d94..4a01f30e9995 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -82,6 +82,8 @@
 
 #define gfs2_disk_hash2offset(h) (((u64)(h)) >> 1)
 #define gfs2_dir_offset2hash(p) ((u32)(((u64)(p)) << 1))
+#define GFS2_HASH_INDEX_MASK 0xffffc000
+#define GFS2_USE_HASH_FLAG 0x2000
 
 struct qstr gfs2_qdot __read_mostly;
 struct qstr gfs2_qdotdot __read_mostly;
@@ -108,7 +110,7 @@ static int gfs2_dir_get_existing_buffer(struct gfs2_inode *ip, u64 block,
 	struct buffer_head *bh;
 	int error;
 
-	error = gfs2_meta_read(ip->i_gl, block, DIO_WAIT, &bh);
+	error = gfs2_meta_read(ip->i_gl, block, DIO_WAIT, 0, &bh);
 	if (error)
 		return error;
 	if (gfs2_metatype_check(GFS2_SB(&ip->i_inode), bh, GFS2_METATYPE_JD)) {
@@ -305,7 +307,7 @@ static int gfs2_dir_read_data(struct gfs2_inode *ip, __be64 *buf,
 			BUG_ON(extlen < 1);
 			bh = gfs2_meta_ra(ip->i_gl, dblock, extlen);
 		} else {
-			error = gfs2_meta_read(ip->i_gl, dblock, DIO_WAIT, &bh);
+			error = gfs2_meta_read(ip->i_gl, dblock, DIO_WAIT, 0, &bh);
 			if (error)
 				goto fail;
 		}
@@ -388,8 +390,13 @@ static __be64 *gfs2_dir_get_hash_table(struct gfs2_inode *ip)
  */
 void gfs2_dir_hash_inval(struct gfs2_inode *ip)
 {
-	__be64 *hc = ip->i_hash_cache;
+	__be64 *hc;
+
+	spin_lock(&ip->i_inode.i_lock);
+	hc = ip->i_hash_cache;
 	ip->i_hash_cache = NULL;
+	spin_unlock(&ip->i_inode.i_lock);
+
 	kvfree(hc);
 }
 
@@ -438,6 +445,27 @@ static int gfs2_dirent_last(const struct gfs2_dirent *dent,
 	return 0;
 }
 
+/* Look for the dirent that contains the offset specified in data. Once we
+ * find that dirent, there must be space available there for the new dirent */
+static int gfs2_dirent_find_offset(const struct gfs2_dirent *dent,
+				  const struct qstr *name,
+				  void *ptr)
+{
+	unsigned required = GFS2_DIRENT_SIZE(name->len);
+	unsigned actual = GFS2_DIRENT_SIZE(be16_to_cpu(dent->de_name_len));
+	unsigned totlen = be16_to_cpu(dent->de_rec_len);
+
+	if (ptr < (void *)dent || ptr >= (void *)dent + totlen)
+		return 0;
+	if (gfs2_dirent_sentinel(dent))
+		actual = 0;
+	if (ptr < (void *)dent + actual)
+		return -1;
+	if ((void *)dent + totlen >= ptr + required)
+		return 1;
+	return -1;
+}
+
 static int gfs2_dirent_find_space(const struct gfs2_dirent *dent,
 				  const struct qstr *name,
 				  void *opaque)
@@ -677,6 +705,27 @@ static void dirent_del(struct gfs2_inode *dip, struct buffer_head *bh,
 	prev->de_rec_len = cpu_to_be16(prev_rec_len);
 }
 
+
+static struct gfs2_dirent *do_init_dirent(struct inode *inode,
+					  struct gfs2_dirent *dent,
+					  const struct qstr *name,
+					  struct buffer_head *bh,
+					  unsigned offset)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_dirent *ndent;
+	unsigned totlen;
+
+	totlen = be16_to_cpu(dent->de_rec_len);
+	BUG_ON(offset + name->len > totlen);
+	gfs2_trans_add_meta(ip->i_gl, bh);
+	ndent = (struct gfs2_dirent *)((char *)dent + offset);
+	dent->de_rec_len = cpu_to_be16(offset);
+	gfs2_qstr2dirent(name, totlen - offset, ndent);
+	return ndent;
+}
+
+
 /*
  * Takes a dent from which to grab space as an argument. Returns the
  * newly created dent.
@@ -686,31 +735,25 @@ static struct gfs2_dirent *gfs2_init_dirent(struct inode *inode,
 					    const struct qstr *name,
 					    struct buffer_head *bh)
 {
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_dirent *ndent;
-	unsigned offset = 0, totlen;
+	unsigned offset = 0;
 
 	if (!gfs2_dirent_sentinel(dent))
 		offset = GFS2_DIRENT_SIZE(be16_to_cpu(dent->de_name_len));
-	totlen = be16_to_cpu(dent->de_rec_len);
-	BUG_ON(offset + name->len > totlen);
-	gfs2_trans_add_meta(ip->i_gl, bh);
-	ndent = (struct gfs2_dirent *)((char *)dent + offset);
-	dent->de_rec_len = cpu_to_be16(offset);
-	gfs2_qstr2dirent(name, totlen - offset, ndent);
-	return ndent;
+	return do_init_dirent(inode, dent, name, bh, offset);
 }
 
-static struct gfs2_dirent *gfs2_dirent_alloc(struct inode *inode,
-					     struct buffer_head *bh,
-					     const struct qstr *name)
+static struct gfs2_dirent *gfs2_dirent_split_alloc(struct inode *inode,
+						   struct buffer_head *bh,
+						   const struct qstr *name,
+						   void *ptr)
 {
 	struct gfs2_dirent *dent;
 	dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size,
-				gfs2_dirent_find_space, name, NULL);
+				gfs2_dirent_find_offset, name, ptr);
 	if (!dent || IS_ERR(dent))
 		return dent;
-	return gfs2_init_dirent(inode, dent, name, bh);
+	return do_init_dirent(inode, dent, name, bh,
+			      (unsigned)(ptr - (void *)dent));
 }
 
 static int get_leaf(struct gfs2_inode *dip, u64 leaf_no,
@@ -718,7 +761,7 @@ static int get_leaf(struct gfs2_inode *dip, u64 leaf_no,
 {
 	int error;
 
-	error = gfs2_meta_read(dip->i_gl, leaf_no, DIO_WAIT, bhp);
+	error = gfs2_meta_read(dip->i_gl, leaf_no, DIO_WAIT, 0, bhp);
 	if (!error && gfs2_metatype_check(GFS2_SB(&dip->i_inode), *bhp, GFS2_METATYPE_LF)) {
 		/* pr_info("block num=%llu\n", leaf_no); */
 		error = -EIO;
@@ -755,7 +798,7 @@ static int get_first_leaf(struct gfs2_inode *dip, u32 index,
 	int error;
 
 	error = get_leaf_nr(dip, index, &leaf_no);
-	if (!error)
+	if (!IS_ERR_VALUE(error))
 		error = get_leaf(dip, leaf_no, bh_out);
 
 	return error;
@@ -971,7 +1014,7 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name)
 
 	index = name->hash >> (32 - dip->i_depth);
 	error = get_leaf_nr(dip, index, &leaf_no);
-	if (error)
+	if (IS_ERR_VALUE(error))
 		return error;
 
 	/*  Get the old leaf block  */
@@ -1046,10 +1089,11 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name)
 		if (!gfs2_dirent_sentinel(dent) &&
 		    be32_to_cpu(dent->de_hash) < divider) {
 			struct qstr str;
+			void *ptr = ((char *)dent - obh->b_data) + nbh->b_data;
 			str.name = (char*)(dent+1);
 			str.len = be16_to_cpu(dent->de_name_len);
 			str.hash = be32_to_cpu(dent->de_hash);
-			new = gfs2_dirent_alloc(inode, nbh, &str);
+			new = gfs2_dirent_split_alloc(inode, nbh, &str, ptr);
 			if (IS_ERR(new)) {
 				error = PTR_ERR(new);
 				break;
@@ -1181,10 +1225,10 @@ static int compare_dents(const void *a, const void *b)
 	int ret = 0;
 
 	dent_a = *(const struct gfs2_dirent **)a;
-	hash_a = be32_to_cpu(dent_a->de_hash);
+	hash_a = dent_a->de_cookie;
 
 	dent_b = *(const struct gfs2_dirent **)b;
-	hash_b = be32_to_cpu(dent_b->de_hash);
+	hash_b = dent_b->de_cookie;
 
 	if (hash_a > hash_b)
 		ret = 1;
@@ -1222,19 +1266,20 @@ static int compare_dents(const void *a, const void *b)
  */
 
 static int do_filldir_main(struct gfs2_inode *dip, struct dir_context *ctx,
-			   const struct gfs2_dirent **darr, u32 entries,
-			   int *copied)
+			   struct gfs2_dirent **darr, u32 entries,
+			   u32 sort_start, int *copied)
 {
 	const struct gfs2_dirent *dent, *dent_next;
 	u64 off, off_next;
 	unsigned int x, y;
 	int run = 0;
 
-	sort(darr, entries, sizeof(struct gfs2_dirent *), compare_dents, NULL);
+	if (sort_start < entries)
+		sort(&darr[sort_start], entries - sort_start,
+		     sizeof(struct gfs2_dirent *), compare_dents, NULL);
 
 	dent_next = darr[0];
-	off_next = be32_to_cpu(dent_next->de_hash);
-	off_next = gfs2_disk_hash2offset(off_next);
+	off_next = dent_next->de_cookie;
 
 	for (x = 0, y = 1; x < entries; x++, y++) {
 		dent = dent_next;
@@ -1242,8 +1287,7 @@ static int do_filldir_main(struct gfs2_inode *dip, struct dir_context *ctx,
 
 		if (y < entries) {
 			dent_next = darr[y];
-			off_next = be32_to_cpu(dent_next->de_hash);
-			off_next = gfs2_disk_hash2offset(off_next);
+			off_next = dent_next->de_cookie;
 
 			if (off < ctx->pos)
 				continue;
@@ -1290,6 +1334,40 @@ static void *gfs2_alloc_sort_buffer(unsigned size)
 	return ptr;
 }
 
+
+static int gfs2_set_cookies(struct gfs2_sbd *sdp, struct buffer_head *bh,
+			    unsigned leaf_nr, struct gfs2_dirent **darr,
+			    unsigned entries)
+{
+	int sort_id = -1;
+	int i;
+	
+	for (i = 0; i < entries; i++) {
+		unsigned offset;
+
+		darr[i]->de_cookie = be32_to_cpu(darr[i]->de_hash);
+		darr[i]->de_cookie = gfs2_disk_hash2offset(darr[i]->de_cookie);
+
+		if (!sdp->sd_args.ar_loccookie)
+			continue;
+		offset = (char *)(darr[i]) -
+			 (bh->b_data + gfs2_dirent_offset(bh->b_data));
+		offset /= GFS2_MIN_DIRENT_SIZE;
+		offset += leaf_nr * sdp->sd_max_dents_per_leaf;
+		if (offset >= GFS2_USE_HASH_FLAG ||
+		    leaf_nr >= GFS2_USE_HASH_FLAG) {
+			darr[i]->de_cookie |= GFS2_USE_HASH_FLAG;
+			if (sort_id < 0)
+				sort_id = i;
+			continue;
+		}
+		darr[i]->de_cookie &= GFS2_HASH_INDEX_MASK;
+		darr[i]->de_cookie |= offset;
+	}
+	return sort_id;
+}	
+
+
 static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx,
 			      int *copied, unsigned *depth,
 			      u64 leaf_no)
@@ -1299,12 +1377,11 @@ static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx,
 	struct buffer_head *bh;
 	struct gfs2_leaf *lf;
 	unsigned entries = 0, entries2 = 0;
-	unsigned leaves = 0;
-	const struct gfs2_dirent **darr, *dent;
+	unsigned leaves = 0, leaf = 0, offset, sort_offset;
+	struct gfs2_dirent **darr, *dent;
 	struct dirent_gather g;
 	struct buffer_head **larr;
-	int leaf = 0;
-	int error, i;
+	int error, i, need_sort = 0, sort_id;
 	u64 lfn = leaf_no;
 
 	do {
@@ -1320,6 +1397,11 @@ static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx,
 		brelse(bh);
 	} while(lfn);
 
+	if (*depth < GFS2_DIR_MAX_DEPTH || !sdp->sd_args.ar_loccookie) {
+		need_sort = 1;
+		sort_offset = 0;
+	}
+
 	if (!entries)
 		return 0;
 
@@ -1333,8 +1415,8 @@ static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx,
 	larr = gfs2_alloc_sort_buffer((leaves + entries + 99) * sizeof(void *));
 	if (!larr)
 		goto out;
-	darr = (const struct gfs2_dirent **)(larr + leaves);
-	g.pdent = darr;
+	darr = (struct gfs2_dirent **)(larr + leaves);
+	g.pdent = (const struct gfs2_dirent **)darr;
 	g.offset = 0;
 	lfn = leaf_no;
 
@@ -1345,6 +1427,7 @@ static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx,
 		lf = (struct gfs2_leaf *)bh->b_data;
 		lfn = be64_to_cpu(lf->lf_next);
 		if (lf->lf_entries) {
+			offset = g.offset;
 			entries2 += be16_to_cpu(lf->lf_entries);
 			dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size,
 						gfs2_dirent_gather, NULL, &g);
@@ -1362,17 +1445,26 @@ static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx,
 				goto out_free;
 			}
 			error = 0;
+			sort_id = gfs2_set_cookies(sdp, bh, leaf, &darr[offset],
+						   be16_to_cpu(lf->lf_entries));
+			if (!need_sort && sort_id >= 0) {
+				need_sort = 1;
+				sort_offset = offset + sort_id;
+			}
 			larr[leaf++] = bh;
 		} else {
+			larr[leaf++] = NULL;
 			brelse(bh);
 		}
 	} while(lfn);
 
 	BUG_ON(entries2 != entries);
-	error = do_filldir_main(ip, ctx, darr, entries, copied);
+	error = do_filldir_main(ip, ctx, darr, entries, need_sort ?
+				sort_offset : entries, copied);
 out_free:
 	for(i = 0; i < leaf; i++)
-		brelse(larr[i]);
+		if (larr[i])
+			brelse(larr[i]);
 	kvfree(larr);
 out:
 	return error;
@@ -1478,7 +1570,7 @@ int gfs2_dir_read(struct inode *inode, struct dir_context *ctx,
 	struct gfs2_inode *dip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct dirent_gather g;
-	const struct gfs2_dirent **darr, *dent;
+	struct gfs2_dirent **darr, *dent;
 	struct buffer_head *dibh;
 	int copied = 0;
 	int error;
@@ -1502,7 +1594,7 @@ int gfs2_dir_read(struct inode *inode, struct dir_context *ctx,
 	/* 96 is max number of dirents which can be stuffed into an inode */
 	darr = kmalloc(96 * sizeof(struct gfs2_dirent *), GFP_NOFS);
 	if (darr) {
-		g.pdent = darr;
+		g.pdent = (const struct gfs2_dirent **)darr;
 		g.offset = 0;
 		dent = gfs2_dirent_scan(inode, dibh->b_data, dibh->b_size,
 					gfs2_dirent_gather, NULL, &g);
@@ -1519,8 +1611,9 @@ int gfs2_dir_read(struct inode *inode, struct dir_context *ctx,
 			error = -EIO;
 			goto out;
 		}
+		gfs2_set_cookies(sdp, dibh, 0, darr, dip->i_entries);
 		error = do_filldir_main(dip, ctx, darr,
-					dip->i_entries, &copied);
+					dip->i_entries, 0, &copied);
 out:
 		kfree(darr);
 	}
@@ -1555,15 +1648,22 @@ struct inode *gfs2_dir_search(struct inode *dir, const struct qstr *name,
 
 	dent = gfs2_dirent_search(dir, name, gfs2_dirent_find, &bh);
 	if (dent) {
+		struct inode *inode;
+		u16 rahead;
+
 		if (IS_ERR(dent))
 			return ERR_CAST(dent);
 		dtype = be16_to_cpu(dent->de_type);
+		rahead = be16_to_cpu(dent->de_rahead);
 		addr = be64_to_cpu(dent->de_inum.no_addr);
 		formal_ino = be64_to_cpu(dent->de_inum.no_formal_ino);
 		brelse(bh);
 		if (fail_on_exist)
 			return ERR_PTR(-EEXIST);
-		return gfs2_inode_lookup(dir->i_sb, dtype, addr, formal_ino, 0);
+		inode = gfs2_inode_lookup(dir->i_sb, dtype, addr, formal_ino);
+		if (!IS_ERR(inode))
+			GFS2_I(inode)->i_rahead = rahead;
+		return inode;
 	}
 	return ERR_PTR(-ENOENT);
 }
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
index 5d15e9498b48..d5bda8513457 100644
--- a/fs/gfs2/export.c
+++ b/fs/gfs2/export.c
@@ -137,7 +137,7 @@ static struct dentry *gfs2_get_dentry(struct super_block *sb,
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 	struct inode *inode;
 
-	inode = gfs2_ilookup(sb, inum->no_addr, 0);
+	inode = gfs2_ilookup(sb, inum->no_addr);
 	if (inode) {
 		if (GFS2_I(inode)->i_no_formal_ino != inum->no_formal_ino) {
 			iput(inode);
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 9287a2d17b8c..208efc70ad49 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -298,9 +298,9 @@ static int gfs2_set_flags(struct file *filp, u32 __user *ptr)
 		gfsflags &= ~GFS2_DIF_TOPDIR;
 		if (gfsflags & GFS2_DIF_INHERIT_JDATA)
 			gfsflags ^= (GFS2_DIF_JDATA | GFS2_DIF_INHERIT_JDATA);
-		return do_gfs2_set_flags(filp, gfsflags, ~0);
+		return do_gfs2_set_flags(filp, gfsflags, ~GFS2_DIF_SYSTEM);
 	}
-	return do_gfs2_set_flags(filp, gfsflags, ~GFS2_DIF_JDATA);
+	return do_gfs2_set_flags(filp, gfsflags, ~(GFS2_DIF_SYSTEM | GFS2_DIF_JDATA));
 }
 
 static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
@@ -336,8 +336,8 @@ static void gfs2_size_hint(struct file *filep, loff_t offset, size_t size)
 	size_t blks = (size + sdp->sd_sb.sb_bsize - 1) >> sdp->sd_sb.sb_bsize_shift;
 	int hint = min_t(size_t, INT_MAX, blks);
 
-	if (hint > atomic_read(&ip->i_res->rs_sizehint))
-		atomic_set(&ip->i_res->rs_sizehint, hint);
+	if (hint > atomic_read(&ip->i_res.rs_sizehint))
+		atomic_set(&ip->i_res.rs_sizehint, hint);
 }
 
 /**
@@ -354,8 +354,8 @@ static int gfs2_allocate_page_backing(struct page *page)
 {
 	struct inode *inode = page->mapping->host;
 	struct buffer_head bh;
-	unsigned long size = PAGE_CACHE_SIZE;
-	u64 lblock = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+	unsigned long size = PAGE_SIZE;
+	u64 lblock = page->index << (PAGE_SHIFT - inode->i_blkbits);
 
 	do {
 		bh.b_state = 0;
@@ -386,7 +386,7 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct gfs2_alloc_parms ap = { .aflags = 0, };
 	unsigned long last_index;
-	u64 pos = page->index << PAGE_CACHE_SHIFT;
+	u64 pos = page->index << PAGE_SHIFT;
 	unsigned int data_blocks, ind_blocks, rblocks;
 	struct gfs2_holder gh;
 	loff_t size;
@@ -397,15 +397,11 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	/* Update file times before taking page lock */
 	file_update_time(vma->vm_file);
 
-	ret = get_write_access(inode);
+	ret = gfs2_rsqa_alloc(ip);
 	if (ret)
 		goto out;
 
-	ret = gfs2_rs_alloc(ip);
-	if (ret)
-		goto out_write_access;
-
-	gfs2_size_hint(vma->vm_file, pos, PAGE_CACHE_SIZE);
+	gfs2_size_hint(vma->vm_file, pos, PAGE_SIZE);
 
 	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
 	ret = gfs2_glock_nq(&gh);
@@ -415,7 +411,7 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
 	set_bit(GIF_SW_PAGED, &ip->i_flags);
 
-	if (!gfs2_write_alloc_required(ip, pos, PAGE_CACHE_SIZE)) {
+	if (!gfs2_write_alloc_required(ip, pos, PAGE_SIZE)) {
 		lock_page(page);
 		if (!PageUptodate(page) || page->mapping != inode->i_mapping) {
 			ret = -EAGAIN;
@@ -428,7 +424,7 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (ret)
 		goto out_unlock;
 
-	gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks);
+	gfs2_write_calc_reserv(ip, PAGE_SIZE, &data_blocks, &ind_blocks);
 	ap.target = data_blocks + ind_blocks;
 	ret = gfs2_quota_lock_check(ip, &ap);
 	if (ret)
@@ -451,7 +447,7 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	lock_page(page);
 	ret = -EINVAL;
 	size = i_size_read(inode);
-	last_index = (size - 1) >> PAGE_CACHE_SHIFT;
+	last_index = (size - 1) >> PAGE_SHIFT;
 	/* Check page index against inode size */
 	if (size == 0 || (page->index > last_index))
 		goto out_trans_end;
@@ -486,8 +482,6 @@ out_uninit:
 		set_page_dirty(page);
 		wait_for_stable_page(page);
 	}
-out_write_access:
-	put_write_access(inode);
 out:
 	sb_end_pagefault(inode->i_sb);
 	return block_page_mkwrite_return(ret);
@@ -623,7 +617,7 @@ static int gfs2_release(struct inode *inode, struct file *file)
 	if (!(file->f_mode & FMODE_WRITE))
 		return 0;
 
-	gfs2_rs_delete(ip, &inode->i_writecount);
+	gfs2_rsqa_delete(ip, &inode->i_writecount);
 	return 0;
 }
 
@@ -703,7 +697,7 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct gfs2_inode *ip = GFS2_I(file_inode(file));
 	int ret;
 
-	ret = gfs2_rs_alloc(ip);
+	ret = gfs2_rsqa_alloc(ip);
 	if (ret)
 		return ret;
 
@@ -879,7 +873,7 @@ static long __gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t
 			rblocks += data_blocks ? data_blocks : 1;
 
 		error = gfs2_trans_begin(sdp, rblocks,
-					 PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
+					 PAGE_SIZE/sdp->sd_sb.sb_bsize);
 		if (error)
 			goto out_trans_fail;
 
@@ -897,8 +891,8 @@ static long __gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t
 
 	if (!(mode & FALLOC_FL_KEEP_SIZE) && (pos + count) > inode->i_size) {
 		i_size_write(inode, pos + count);
-		/* Marks the inode as dirty */
 		file_update_time(file);
+		mark_inode_dirty(inode);
 	}
 
 	return generic_write_sync(file, pos, count);
@@ -920,7 +914,7 @@ static long gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t le
 	if ((mode & ~FALLOC_FL_KEEP_SIZE) || gfs2_is_jdata(ip))
 		return -EOPNOTSUPP;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
 	ret = gfs2_glock_nq(&gh);
@@ -938,20 +932,21 @@ static long gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t le
 	if (ret)
 		goto out_unlock;
 
-	ret = gfs2_rs_alloc(ip);
+	ret = gfs2_rsqa_alloc(ip);
 	if (ret)
 		goto out_putw;
 
 	ret = __gfs2_fallocate(file, mode, offset, len);
 	if (ret)
-		gfs2_rs_deltree(ip->i_res);
+		gfs2_rs_deltree(&ip->i_res);
+
 out_putw:
 	put_write_access(inode);
 out_unlock:
 	gfs2_glock_dq(&gh);
 out_uninit:
 	gfs2_holder_uninit(&gh);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return ret;
 }
 
@@ -962,7 +957,7 @@ static ssize_t gfs2_file_splice_write(struct pipe_inode_info *pipe,
 	int error;
 	struct gfs2_inode *ip = GFS2_I(out->f_mapping->host);
 
-	error = gfs2_rs_alloc(ip);
+	error = gfs2_rsqa_alloc(ip);
 	if (error)
 		return (ssize_t)error;
 
@@ -1018,7 +1013,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
 	struct gfs2_inode *ip = GFS2_I(file_inode(file));
 	struct gfs2_glock *gl;
 	unsigned int state;
-	int flags;
+	u16 flags;
 	int error = 0;
 	int sleeptime;
 
@@ -1032,7 +1027,10 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
 		if (fl_gh->gh_state == state)
 			goto out;
 		locks_lock_file_wait(file,
-				     &(struct file_lock){.fl_type = F_UNLCK});
+				     &(struct file_lock) {
+					     .fl_type = F_UNLCK,
+					     .fl_flags = FL_FLOCK
+				     });
 		gfs2_glock_dq(fl_gh);
 		gfs2_holder_reinit(state, flags, fl_gh);
 	} else {
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 9bd1244caf38..6539131c52a2 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -246,8 +246,8 @@ static inline void do_error(struct gfs2_glock *gl, const int ret)
  */
 
 static int do_promote(struct gfs2_glock *gl)
-__releases(&gl->gl_spin)
-__acquires(&gl->gl_spin)
+__releases(&gl->gl_lockref.lock)
+__acquires(&gl->gl_lockref.lock)
 {
 	const struct gfs2_glock_operations *glops = gl->gl_ops;
 	struct gfs2_holder *gh, *tmp;
@@ -260,10 +260,10 @@ restart:
 		if (may_grant(gl, gh)) {
 			if (gh->gh_list.prev == &gl->gl_holders &&
 			    glops->go_lock) {
-				spin_unlock(&gl->gl_spin);
+				spin_unlock(&gl->gl_lockref.lock);
 				/* FIXME: eliminate this eventually */
 				ret = glops->go_lock(gh);
-				spin_lock(&gl->gl_spin);
+				spin_lock(&gl->gl_lockref.lock);
 				if (ret) {
 					if (ret == 1)
 						return 2;
@@ -361,7 +361,7 @@ static void finish_xmote(struct gfs2_glock *gl, unsigned int ret)
 	unsigned state = ret & LM_OUT_ST_MASK;
 	int rv;
 
-	spin_lock(&gl->gl_spin);
+	spin_lock(&gl->gl_lockref.lock);
 	trace_gfs2_glock_state_change(gl, state);
 	state_change(gl, state);
 	gh = find_first_waiter(gl);
@@ -405,7 +405,7 @@ retry:
 			pr_err("wanted %u got %u\n", gl->gl_target, state);
 			GLOCK_BUG_ON(gl, 1);
 		}
-		spin_unlock(&gl->gl_spin);
+		spin_unlock(&gl->gl_lockref.lock);
 		return;
 	}
 
@@ -414,9 +414,9 @@ retry:
 		gfs2_demote_wake(gl);
 	if (state != LM_ST_UNLOCKED) {
 		if (glops->go_xmote_bh) {
-			spin_unlock(&gl->gl_spin);
+			spin_unlock(&gl->gl_lockref.lock);
 			rv = glops->go_xmote_bh(gl, gh);
-			spin_lock(&gl->gl_spin);
+			spin_lock(&gl->gl_lockref.lock);
 			if (rv) {
 				do_error(gl, rv);
 				goto out;
@@ -429,7 +429,7 @@ retry:
 out:
 	clear_bit(GLF_LOCK, &gl->gl_flags);
 out_locked:
-	spin_unlock(&gl->gl_spin);
+	spin_unlock(&gl->gl_lockref.lock);
 }
 
 /**
@@ -441,12 +441,12 @@ out_locked:
  */
 
 static void do_xmote(struct gfs2_glock *gl, struct gfs2_holder *gh, unsigned int target)
-__releases(&gl->gl_spin)
-__acquires(&gl->gl_spin)
+__releases(&gl->gl_lockref.lock)
+__acquires(&gl->gl_lockref.lock)
 {
 	const struct gfs2_glock_operations *glops = gl->gl_ops;
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
-	unsigned int lck_flags = gh ? gh->gh_flags : 0;
+	unsigned int lck_flags = (unsigned int)(gh ? gh->gh_flags : 0);
 	int ret;
 
 	lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP |
@@ -464,7 +464,7 @@ __acquires(&gl->gl_spin)
 	    (gl->gl_state == LM_ST_EXCLUSIVE) ||
 	    (lck_flags & (LM_FLAG_TRY|LM_FLAG_TRY_1CB)))
 		clear_bit(GLF_BLOCKING, &gl->gl_flags);
-	spin_unlock(&gl->gl_spin);
+	spin_unlock(&gl->gl_lockref.lock);
 	if (glops->go_sync)
 		glops->go_sync(gl);
 	if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags))
@@ -485,7 +485,7 @@ __acquires(&gl->gl_spin)
 			gfs2_glock_put(gl);
 	}
 
-	spin_lock(&gl->gl_spin);
+	spin_lock(&gl->gl_lockref.lock);
 }
 
 /**
@@ -513,8 +513,8 @@ static inline struct gfs2_holder *find_first_holder(const struct gfs2_glock *gl)
  */
 
 static void run_queue(struct gfs2_glock *gl, const int nonblock)
-__releases(&gl->gl_spin)
-__acquires(&gl->gl_spin)
+__releases(&gl->gl_lockref.lock)
+__acquires(&gl->gl_lockref.lock)
 {
 	struct gfs2_holder *gh = NULL;
 	int ret;
@@ -572,17 +572,24 @@ static void delete_work_func(struct work_struct *work)
 	struct inode *inode;
 	u64 no_addr = gl->gl_name.ln_number;
 
+	/* If someone's using this glock to create a new dinode, the block must
+	   have been freed by another node, then re-used, in which case our
+	   iopen callback is too late after the fact. Ignore it. */
+	if (test_bit(GLF_INODE_CREATING, &gl->gl_flags))
+		goto out;
+
 	ip = gl->gl_object;
 	/* Note: Unsafe to dereference ip as we don't hold right refs/locks */
 
 	if (ip)
-		inode = gfs2_ilookup(sdp->sd_vfs, no_addr, 1);
+		inode = gfs2_ilookup(sdp->sd_vfs, no_addr);
 	else
 		inode = gfs2_lookup_by_inum(sdp, no_addr, NULL, GFS2_BLKST_UNLINKED);
 	if (inode && !IS_ERR(inode)) {
 		d_prune_aliases(inode);
 		iput(inode);
 	}
+out:
 	gfs2_glock_put(gl);
 }
 
@@ -596,7 +603,7 @@ static void glock_work_func(struct work_struct *work)
 		finish_xmote(gl, gl->gl_reply);
 		drop_ref = 1;
 	}
-	spin_lock(&gl->gl_spin);
+	spin_lock(&gl->gl_lockref.lock);
 	if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
 	    gl->gl_state != LM_ST_UNLOCKED &&
 	    gl->gl_demote_state != LM_ST_EXCLUSIVE) {
@@ -612,7 +619,7 @@ static void glock_work_func(struct work_struct *work)
 		}
 	}
 	run_queue(gl, 0);
-	spin_unlock(&gl->gl_spin);
+	spin_unlock(&gl->gl_lockref.lock);
 	if (!delay)
 		gfs2_glock_put(gl);
 	else {
@@ -750,7 +757,7 @@ again:
  *
  */
 
-void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, unsigned flags,
+void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, u16 flags,
 		      struct gfs2_holder *gh)
 {
 	INIT_LIST_HEAD(&gh->gh_list);
@@ -774,7 +781,7 @@ void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, unsigned flags,
  *
  */
 
-void gfs2_holder_reinit(unsigned int state, unsigned flags, struct gfs2_holder *gh)
+void gfs2_holder_reinit(unsigned int state, u16 flags, struct gfs2_holder *gh)
 {
 	gh->gh_state = state;
 	gh->gh_flags = flags;
@@ -876,8 +883,8 @@ void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...)
  */
 
 static inline void add_to_queue(struct gfs2_holder *gh)
-__releases(&gl->gl_spin)
-__acquires(&gl->gl_spin)
+__releases(&gl->gl_lockref.lock)
+__acquires(&gl->gl_lockref.lock)
 {
 	struct gfs2_glock *gl = gh->gh_gl;
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
@@ -926,10 +933,10 @@ fail:
 do_cancel:
 	gh = list_entry(gl->gl_holders.next, struct gfs2_holder, gh_list);
 	if (!(gh->gh_flags & LM_FLAG_PRIORITY)) {
-		spin_unlock(&gl->gl_spin);
+		spin_unlock(&gl->gl_lockref.lock);
 		if (sdp->sd_lockstruct.ls_ops->lm_cancel)
 			sdp->sd_lockstruct.ls_ops->lm_cancel(gl);
-		spin_lock(&gl->gl_spin);
+		spin_lock(&gl->gl_lockref.lock);
 	}
 	return;
 
@@ -967,7 +974,7 @@ int gfs2_glock_nq(struct gfs2_holder *gh)
 	if (test_bit(GLF_LRU, &gl->gl_flags))
 		gfs2_glock_remove_from_lru(gl);
 
-	spin_lock(&gl->gl_spin);
+	spin_lock(&gl->gl_lockref.lock);
 	add_to_queue(gh);
 	if (unlikely((LM_FLAG_NOEXP & gh->gh_flags) &&
 		     test_and_clear_bit(GLF_FROZEN, &gl->gl_flags))) {
@@ -977,7 +984,7 @@ int gfs2_glock_nq(struct gfs2_holder *gh)
 			gl->gl_lockref.count--;
 	}
 	run_queue(gl, 1);
-	spin_unlock(&gl->gl_spin);
+	spin_unlock(&gl->gl_lockref.lock);
 
 	if (!(gh->gh_flags & GL_ASYNC))
 		error = gfs2_glock_wait(gh);
@@ -1010,17 +1017,18 @@ void gfs2_glock_dq(struct gfs2_holder *gh)
 	unsigned delay = 0;
 	int fast_path = 0;
 
-	spin_lock(&gl->gl_spin);
+	spin_lock(&gl->gl_lockref.lock);
 	if (gh->gh_flags & GL_NOCACHE)
 		handle_callback(gl, LM_ST_UNLOCKED, 0, false);
 
 	list_del_init(&gh->gh_list);
+	clear_bit(HIF_HOLDER, &gh->gh_iflags);
 	if (find_first_holder(gl) == NULL) {
 		if (glops->go_unlock) {
 			GLOCK_BUG_ON(gl, test_and_set_bit(GLF_LOCK, &gl->gl_flags));
-			spin_unlock(&gl->gl_spin);
+			spin_unlock(&gl->gl_lockref.lock);
 			glops->go_unlock(gh);
-			spin_lock(&gl->gl_spin);
+			spin_lock(&gl->gl_lockref.lock);
 			clear_bit(GLF_LOCK, &gl->gl_flags);
 		}
 		if (list_empty(&gl->gl_holders) &&
@@ -1033,7 +1041,7 @@ void gfs2_glock_dq(struct gfs2_holder *gh)
 		gfs2_glock_add_to_lru(gl);
 
 	trace_gfs2_glock_queue(gh, 0);
-	spin_unlock(&gl->gl_spin);
+	spin_unlock(&gl->gl_lockref.lock);
 	if (likely(fast_path))
 		return;
 
@@ -1080,7 +1088,7 @@ void gfs2_glock_dq_uninit(struct gfs2_holder *gh)
 
 int gfs2_glock_nq_num(struct gfs2_sbd *sdp, u64 number,
 		      const struct gfs2_glock_operations *glops,
-		      unsigned int state, int flags, struct gfs2_holder *gh)
+		      unsigned int state, u16 flags, struct gfs2_holder *gh)
 {
 	struct gfs2_glock *gl;
 	int error;
@@ -1217,9 +1225,9 @@ void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state)
 			delay = gl->gl_hold_time;
 	}
 
-	spin_lock(&gl->gl_spin);
+	spin_lock(&gl->gl_lockref.lock);
 	handle_callback(gl, state, delay, true);
-	spin_unlock(&gl->gl_spin);
+	spin_unlock(&gl->gl_lockref.lock);
 	if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
 		gfs2_glock_put(gl);
 }
@@ -1259,7 +1267,7 @@ static int gfs2_should_freeze(const struct gfs2_glock *gl)
  * @gl: Pointer to the glock
  * @ret: The return value from the dlm
  *
- * The gl_reply field is under the gl_spin lock so that it is ok
+ * The gl_reply field is under the gl_lockref.lock lock so that it is ok
  * to use a bitfield shared with other glock state fields.
  */
 
@@ -1267,20 +1275,20 @@ void gfs2_glock_complete(struct gfs2_glock *gl, int ret)
 {
 	struct lm_lockstruct *ls = &gl->gl_name.ln_sbd->sd_lockstruct;
 
-	spin_lock(&gl->gl_spin);
+	spin_lock(&gl->gl_lockref.lock);
 	gl->gl_reply = ret;
 
 	if (unlikely(test_bit(DFL_BLOCK_LOCKS, &ls->ls_recover_flags))) {
 		if (gfs2_should_freeze(gl)) {
 			set_bit(GLF_FROZEN, &gl->gl_flags);
-			spin_unlock(&gl->gl_spin);
+			spin_unlock(&gl->gl_lockref.lock);
 			return;
 		}
 	}
 
 	gl->gl_lockref.count++;
 	set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
-	spin_unlock(&gl->gl_spin);
+	spin_unlock(&gl->gl_lockref.lock);
 
 	if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
 		gfs2_glock_put(gl);
@@ -1326,14 +1334,14 @@ __acquires(&lru_lock)
 	while(!list_empty(list)) {
 		gl = list_entry(list->next, struct gfs2_glock, gl_lru);
 		list_del_init(&gl->gl_lru);
-		if (!spin_trylock(&gl->gl_spin)) {
+		if (!spin_trylock(&gl->gl_lockref.lock)) {
 add_back_to_lru:
 			list_add(&gl->gl_lru, &lru_list);
 			atomic_inc(&lru_count);
 			continue;
 		}
 		if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
-			spin_unlock(&gl->gl_spin);
+			spin_unlock(&gl->gl_lockref.lock);
 			goto add_back_to_lru;
 		}
 		clear_bit(GLF_LRU, &gl->gl_flags);
@@ -1343,7 +1351,7 @@ add_back_to_lru:
 		WARN_ON(!test_and_clear_bit(GLF_LOCK, &gl->gl_flags));
 		if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
 			gl->gl_lockref.count--;
-		spin_unlock(&gl->gl_spin);
+		spin_unlock(&gl->gl_lockref.lock);
 		cond_resched_lock(&lru_lock);
 	}
 }
@@ -1417,14 +1425,14 @@ static struct shrinker glock_shrinker = {
 static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp)
 {
 	struct gfs2_glock *gl;
-	struct rhash_head *pos, *next;
+	struct rhash_head *pos;
 	const struct bucket_table *tbl;
 	int i;
 
 	rcu_read_lock();
 	tbl = rht_dereference_rcu(gl_hash_table.tbl, &gl_hash_table);
 	for (i = 0; i < tbl->size; i++) {
-		rht_for_each_entry_safe(gl, pos, next, tbl, i, gl_node) {
+		rht_for_each_entry_rcu(gl, pos, tbl, i, gl_node) {
 			if ((gl->gl_name.ln_sbd == sdp) &&
 			    lockref_get_not_dead(&gl->gl_lockref))
 				examiner(gl);
@@ -1461,10 +1469,10 @@ static void clear_glock(struct gfs2_glock *gl)
 {
 	gfs2_glock_remove_from_lru(gl);
 
-	spin_lock(&gl->gl_spin);
+	spin_lock(&gl->gl_lockref.lock);
 	if (gl->gl_state != LM_ST_UNLOCKED)
 		handle_callback(gl, LM_ST_UNLOCKED, 0, false);
-	spin_unlock(&gl->gl_spin);
+	spin_unlock(&gl->gl_lockref.lock);
 	if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
 		gfs2_glock_put(gl);
 }
@@ -1482,9 +1490,9 @@ void gfs2_glock_thaw(struct gfs2_sbd *sdp)
 
 static void dump_glock(struct seq_file *seq, struct gfs2_glock *gl)
 {
-	spin_lock(&gl->gl_spin);
+	spin_lock(&gl->gl_lockref.lock);
 	gfs2_dump_glock(seq, gl);
-	spin_unlock(&gl->gl_spin);
+	spin_unlock(&gl->gl_lockref.lock);
 }
 
 static void dump_glock_func(struct gfs2_glock *gl)
@@ -1506,7 +1514,9 @@ void gfs2_gl_hash_clear(struct gfs2_sbd *sdp)
 	flush_workqueue(glock_workqueue);
 	glock_hash_walk(clear_glock, sdp);
 	flush_workqueue(glock_workqueue);
-	wait_event(sdp->sd_glock_wait, atomic_read(&sdp->sd_glock_disposal) == 0);
+	wait_event_timeout(sdp->sd_glock_wait,
+			   atomic_read(&sdp->sd_glock_disposal) == 0,
+			   HZ * 600);
 	glock_hash_walk(dump_glock_func, sdp);
 }
 
@@ -1518,10 +1528,10 @@ void gfs2_glock_finish_truncate(struct gfs2_inode *ip)
 	ret = gfs2_truncatei_resume(ip);
 	gfs2_assert_withdraw(gl->gl_name.ln_sbd, ret == 0);
 
-	spin_lock(&gl->gl_spin);
+	spin_lock(&gl->gl_lockref.lock);
 	clear_bit(GLF_LOCK, &gl->gl_flags);
 	run_queue(gl, 1);
-	spin_unlock(&gl->gl_spin);
+	spin_unlock(&gl->gl_lockref.lock);
 }
 
 static const char *state2str(unsigned state)
@@ -1539,7 +1549,7 @@ static const char *state2str(unsigned state)
 	return "??";
 }
 
-static const char *hflags2str(char *buf, unsigned flags, unsigned long iflags)
+static const char *hflags2str(char *buf, u16 flags, unsigned long iflags)
 {
 	char *p = buf;
 	if (flags & LM_FLAG_TRY)
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index 32572f71f027..46ab67fc16da 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -79,15 +79,15 @@ enum {
  * requested had acquired and released the lock.
  */
 
-#define LM_FLAG_TRY		0x00000001
-#define LM_FLAG_TRY_1CB		0x00000002
-#define LM_FLAG_NOEXP		0x00000004
-#define LM_FLAG_ANY		0x00000008
-#define LM_FLAG_PRIORITY	0x00000010
-#define GL_ASYNC		0x00000040
-#define GL_EXACT		0x00000080
-#define GL_SKIP			0x00000100
-#define GL_NOCACHE		0x00000400
+#define LM_FLAG_TRY		0x0001
+#define LM_FLAG_TRY_1CB		0x0002
+#define LM_FLAG_NOEXP		0x0004
+#define LM_FLAG_ANY		0x0008
+#define LM_FLAG_PRIORITY	0x0010
+#define GL_ASYNC		0x0040
+#define GL_EXACT		0x0080
+#define GL_SKIP			0x0100
+#define GL_NOCACHE		0x0400
   
 /*
  * lm_async_cb return flags
@@ -141,7 +141,7 @@ static inline struct gfs2_holder *gfs2_glock_is_locked_by_me(struct gfs2_glock *
 	struct pid *pid;
 
 	/* Look in glock's list of holders for one with current task as owner */
-	spin_lock(&gl->gl_spin);
+	spin_lock(&gl->gl_lockref.lock);
 	pid = task_pid(current);
 	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
 		if (!test_bit(HIF_HOLDER, &gh->gh_iflags))
@@ -151,7 +151,7 @@ static inline struct gfs2_holder *gfs2_glock_is_locked_by_me(struct gfs2_glock *
 	}
 	gh = NULL;
 out:
-	spin_unlock(&gl->gl_spin);
+	spin_unlock(&gl->gl_lockref.lock);
 
 	return gh;
 }
@@ -183,8 +183,8 @@ extern int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 			  int create, struct gfs2_glock **glp);
 extern void gfs2_glock_put(struct gfs2_glock *gl);
 extern void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state,
-			     unsigned flags, struct gfs2_holder *gh);
-extern void gfs2_holder_reinit(unsigned int state, unsigned flags,
+			     u16 flags, struct gfs2_holder *gh);
+extern void gfs2_holder_reinit(unsigned int state, u16 flags,
 			       struct gfs2_holder *gh);
 extern void gfs2_holder_uninit(struct gfs2_holder *gh);
 extern int gfs2_glock_nq(struct gfs2_holder *gh);
@@ -195,7 +195,7 @@ extern void gfs2_glock_dq_wait(struct gfs2_holder *gh);
 extern void gfs2_glock_dq_uninit(struct gfs2_holder *gh);
 extern int gfs2_glock_nq_num(struct gfs2_sbd *sdp, u64 number,
 			     const struct gfs2_glock_operations *glops,
-			     unsigned int state, int flags,
+			     unsigned int state, u16 flags,
 			     struct gfs2_holder *gh);
 extern int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs);
 extern void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs);
@@ -215,7 +215,7 @@ void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...);
  */
 
 static inline int gfs2_glock_nq_init(struct gfs2_glock *gl,
-				     unsigned int state, int flags,
+				     unsigned int state, u16 flags,
 				     struct gfs2_holder *gh)
 {
 	int error;
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 1f6c9c3fe5cb..437fd73e381e 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -13,6 +13,7 @@
 #include <linux/gfs2_ondisk.h>
 #include <linux/bio.h>
 #include <linux/posix_acl.h>
+#include <linux/security.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -146,11 +147,11 @@ static void rgrp_go_sync(struct gfs2_glock *gl)
 	struct gfs2_rgrpd *rgd;
 	int error;
 
-	spin_lock(&gl->gl_spin);
+	spin_lock(&gl->gl_lockref.lock);
 	rgd = gl->gl_object;
 	if (rgd)
 		gfs2_rgrp_brelse(rgd);
-	spin_unlock(&gl->gl_spin);
+	spin_unlock(&gl->gl_lockref.lock);
 
 	if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
 		return;
@@ -162,11 +163,11 @@ static void rgrp_go_sync(struct gfs2_glock *gl)
 	mapping_set_error(mapping, error);
 	gfs2_ail_empty_gl(gl);
 
-	spin_lock(&gl->gl_spin);
+	spin_lock(&gl->gl_lockref.lock);
 	rgd = gl->gl_object;
 	if (rgd)
 		gfs2_free_clones(rgd);
-	spin_unlock(&gl->gl_spin);
+	spin_unlock(&gl->gl_lockref.lock);
 }
 
 /**
@@ -262,6 +263,7 @@ static void inode_go_inval(struct gfs2_glock *gl, int flags)
 		if (ip) {
 			set_bit(GIF_INVALID, &ip->i_flags);
 			forget_all_cached_acls(&ip->i_inode);
+			security_inode_invalidate_secctx(&ip->i_inode);
 			gfs2_dir_hash_inval(ip);
 		}
 	}
@@ -542,7 +544,7 @@ static int freeze_go_demote_ok(const struct gfs2_glock *gl)
  * iopen_go_callback - schedule the dcache entry for the inode to be deleted
  * @gl: the glock
  *
- * gl_spin lock is held while calling this
+ * gl_lockref.lock lock is held while calling this
  */
 static void iopen_go_callback(struct gfs2_glock *gl, bool remote)
 {
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 121ed08d9d9f..a6a3389a07fc 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -259,8 +259,8 @@ struct gfs2_holder {
 
 	struct gfs2_glock *gh_gl;
 	struct pid *gh_owner_pid;
-	unsigned int gh_state;
-	unsigned gh_flags;
+	u16 gh_flags;
+	u16 gh_state;
 
 	int gh_error;
 	unsigned long gh_iflags; /* HIF_... */
@@ -270,6 +270,13 @@ struct gfs2_holder {
 /* Number of quota types we support */
 #define GFS2_MAXQUOTAS 2
 
+struct gfs2_qadata { /* quota allocation data */
+	/* Quota stuff */
+	struct gfs2_quota_data *qa_qd[2 * GFS2_MAXQUOTAS];
+	struct gfs2_holder qa_qd_ghs[2 * GFS2_MAXQUOTAS];
+	unsigned int qa_qd_num;
+};
+
 /* Resource group multi-block reservation, in order of appearance:
 
    Step 1. Function prepares to write, allocates a mb, sets the size hint.
@@ -288,11 +295,6 @@ struct gfs2_blkreserv {
 	struct gfs2_rbm rs_rbm;       /* Start of reservation */
 	u32 rs_free;                  /* how many blocks are still free */
 	u64 rs_inum;                  /* Inode number for reservation */
-
-	/* ancillary quota stuff */
-	struct gfs2_quota_data *rs_qa_qd[2 * GFS2_MAXQUOTAS];
-	struct gfs2_holder rs_qa_qd_ghs[2 * GFS2_MAXQUOTAS];
-	unsigned int rs_qa_qd_num;
 };
 
 /*
@@ -326,6 +328,7 @@ enum {
 	GLF_LRU				= 13,
 	GLF_OBJECT			= 14, /* Used only for tracing */
 	GLF_BLOCKING			= 15,
+	GLF_INODE_CREATING		= 16, /* Inode creation occurring */
 };
 
 struct gfs2_glock {
@@ -334,9 +337,8 @@ struct gfs2_glock {
 	struct lm_lockname gl_name;
 
 	struct lockref gl_lockref;
-#define gl_spin gl_lockref.lock
 
-	/* State fields protected by gl_spin */
+	/* State fields protected by gl_lockref.lock */
 	unsigned int gl_state:2,	/* Current state */
 		     gl_target:2,	/* Target state */
 		     gl_demote_state:2,	/* State requested by remote node */
@@ -392,7 +394,8 @@ struct gfs2_inode {
 	struct gfs2_glock *i_gl; /* Move into i_gh? */
 	struct gfs2_holder i_iopen_gh;
 	struct gfs2_holder i_gh; /* for prepare/commit_write only */
-	struct gfs2_blkreserv *i_res; /* rgrp multi-block reservation */
+	struct gfs2_qadata *i_qadata; /* quota allocation data */
+	struct gfs2_blkreserv i_res; /* rgrp multi-block reservation */
 	struct gfs2_rgrpd *i_rgd;
 	u64 i_goal;	/* goal block for allocations */
 	struct rw_semaphore i_rw_mutex;
@@ -403,6 +406,7 @@ struct gfs2_inode {
 	u32 i_diskflags;
 	u8 i_height;
 	u8 i_depth;
+	u16 i_rahead;
 };
 
 /*
@@ -559,6 +563,8 @@ struct gfs2_args {
 	unsigned int ar_errors:2;               /* errors=withdraw | panic */
 	unsigned int ar_nobarrier:1;            /* do not send barriers */
 	unsigned int ar_rgrplvb:1;		/* use lvbs for rgrp info */
+	unsigned int ar_loccookie:1;		/* use location based readdir
+						   cookies */
 	int ar_commit;				/* Commit interval */
 	int ar_statfs_quantum;			/* The fast statfs interval */
 	int ar_quota_quantum;			/* The quota interval */
@@ -686,6 +692,7 @@ struct gfs2_sbd {
 	u64 sd_heightsize[GFS2_MAX_META_HEIGHT + 1];
 	u32 sd_max_jheight; /* Max height of journaled file's meta tree */
 	u64 sd_jheightsize[GFS2_MAX_META_HEIGHT + 1];
+	u32 sd_max_dents_per_leaf; /* Max number of dirents in a leaf block */
 
 	struct gfs2_args sd_args;	/* Mount arguments */
 	struct gfs2_tune sd_tune;	/* Filesystem tuning structure */
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 063fdfcf8275..bb30f9a72c65 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -37,61 +37,9 @@
 #include "super.h"
 #include "glops.h"
 
-struct gfs2_skip_data {
-	u64 no_addr;
-	int skipped;
-	int non_block;
-};
-
-static int iget_test(struct inode *inode, void *opaque)
+struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr)
 {
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_skip_data *data = opaque;
-
-	if (ip->i_no_addr == data->no_addr) {
-		if (data->non_block &&
-		    inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE)) {
-			data->skipped = 1;
-			return 0;
-		}
-		return 1;
-	}
-	return 0;
-}
-
-static int iget_set(struct inode *inode, void *opaque)
-{
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_skip_data *data = opaque;
-
-	if (data->skipped)
-		return -ENOENT;
-	inode->i_ino = (unsigned long)(data->no_addr);
-	ip->i_no_addr = data->no_addr;
-	return 0;
-}
-
-struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr, int non_block)
-{
-	unsigned long hash = (unsigned long)no_addr;
-	struct gfs2_skip_data data;
-
-	data.no_addr = no_addr;
-	data.skipped = 0;
-	data.non_block = non_block;
-	return ilookup5(sb, hash, iget_test, &data);
-}
-
-static struct inode *gfs2_iget(struct super_block *sb, u64 no_addr,
-			       int non_block)
-{
-	struct gfs2_skip_data data;
-	unsigned long hash = (unsigned long)no_addr;
-
-	data.no_addr = no_addr;
-	data.skipped = 0;
-	data.non_block = non_block;
-	return iget5_locked(sb, hash, iget_test, iget_set, &data);
+	return ilookup(sb, (unsigned long)no_addr);
 }
 
 /**
@@ -132,21 +80,21 @@ static void gfs2_set_iop(struct inode *inode)
  * @sb: The super block
  * @no_addr: The inode number
  * @type: The type of the inode
- * non_block: Can we block on inodes that are being freed?
  *
  * Returns: A VFS inode, or an error
  */
 
 struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
-				u64 no_addr, u64 no_formal_ino, int non_block)
+				u64 no_addr, u64 no_formal_ino)
 {
 	struct inode *inode;
 	struct gfs2_inode *ip;
 	struct gfs2_glock *io_gl = NULL;
 	int error;
 
-	inode = gfs2_iget(sb, no_addr, non_block);
+	inode = iget_locked(sb, (unsigned long)no_addr);
 	ip = GFS2_I(inode);
+	ip->i_no_addr = no_addr;
 
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
@@ -191,13 +139,13 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
 fail_refresh:
 	ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
 	ip->i_iopen_gh.gh_gl->gl_object = NULL;
-	gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+	gfs2_glock_dq_wait(&ip->i_iopen_gh);
+	gfs2_holder_uninit(&ip->i_iopen_gh);
 fail_iopen:
 	if (io_gl)
 		gfs2_glock_put(io_gl);
 fail_put:
 	ip->i_gl->gl_object = NULL;
-	gfs2_glock_put(ip->i_gl);
 fail:
 	iget_failed(inode);
 	return ERR_PTR(error);
@@ -221,7 +169,7 @@ struct inode *gfs2_lookup_by_inum(struct gfs2_sbd *sdp, u64 no_addr,
 	if (error)
 		goto fail;
 
-	inode = gfs2_inode_lookup(sb, DT_UNKNOWN, no_addr, 0, 1);
+	inode = gfs2_inode_lookup(sb, DT_UNKNOWN, no_addr, 0);
 	if (IS_ERR(inode))
 		goto fail;
 
@@ -592,8 +540,8 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	struct inode *inode = NULL;
 	struct gfs2_inode *dip = GFS2_I(dir), *ip;
 	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
-	struct gfs2_glock *io_gl;
-	int error, free_vfs_inode = 0;
+	struct gfs2_glock *io_gl = NULL;
+	int error, free_vfs_inode = 1;
 	u32 aflags = 0;
 	unsigned blocks = 1;
 	struct gfs2_diradd da = { .bh = NULL, .save_loc = 1, };
@@ -601,7 +549,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	if (!name->len || name->len > GFS2_FNAMESIZE)
 		return -ENAMETOOLONG;
 
-	error = gfs2_rs_alloc(dip);
+	error = gfs2_rsqa_alloc(dip);
 	if (error)
 		return error;
 
@@ -650,10 +598,10 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 
 	error = posix_acl_create(dir, &mode, &default_acl, &acl);
 	if (error)
-		goto fail_free_vfs_inode;
+		goto fail_gunlock;
 
 	ip = GFS2_I(inode);
-	error = gfs2_rs_alloc(ip);
+	error = gfs2_rsqa_alloc(ip);
 	if (error)
 		goto fail_free_acls;
 
@@ -685,6 +633,11 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 		ip->i_entries = 2;
 		break;
 	}
+
+	/* Force SYSTEM flag on all files and subdirs of a SYSTEM directory */
+	if (dip->i_diskflags & GFS2_DIF_SYSTEM)
+		ip->i_diskflags |= GFS2_DIF_SYSTEM;
+
 	gfs2_set_inode_flags(inode);
 
 	if ((GFS2_I(d_inode(sdp->sd_root_dir)) == dip) ||
@@ -724,6 +677,8 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	if (error)
 		goto fail_gunlock2;
 
+	BUG_ON(test_and_set_bit(GLF_INODE_CREATING, &io_gl->gl_flags));
+
 	error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
 	if (error)
 		goto fail_gunlock2;
@@ -733,6 +688,9 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	gfs2_set_iop(inode);
 	insert_inode_hash(inode);
 
+	free_vfs_inode = 0; /* After this point, the inode is no longer
+			       considered free. Any failures need to undo
+			       the gfs2 structures. */
 	if (default_acl) {
 		error = gfs2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
 		posix_acl_release(default_acl);
@@ -763,27 +721,25 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	}
 	gfs2_glock_dq_uninit(ghs);
 	gfs2_glock_dq_uninit(ghs + 1);
+	clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);
 	return error;
 
 fail_gunlock3:
-	gfs2_glock_dq_uninit(ghs + 1);
-	if (ip->i_gl)
-		gfs2_glock_put(ip->i_gl);
-	goto fail_gunlock;
-
+	gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+	gfs2_glock_put(io_gl);
 fail_gunlock2:
+	if (io_gl)
+		clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);
 	gfs2_glock_dq_uninit(ghs + 1);
 fail_free_inode:
 	if (ip->i_gl)
 		gfs2_glock_put(ip->i_gl);
-	gfs2_rs_delete(ip, NULL);
+	gfs2_rsqa_delete(ip, NULL);
 fail_free_acls:
 	if (default_acl)
 		posix_acl_release(default_acl);
 	if (acl)
 		posix_acl_release(acl);
-fail_free_vfs_inode:
-	free_vfs_inode = 1;
 fail_gunlock:
 	gfs2_dir_no_add(&da);
 	gfs2_glock_dq_uninit(ghs);
@@ -898,7 +854,7 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir,
 	if (S_ISDIR(inode->i_mode))
 		return -EPERM;
 
-	error = gfs2_rs_alloc(dip);
+	error = gfs2_rsqa_alloc(dip);
 	if (error)
 		return error;
 
@@ -1371,7 +1327,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
 	if (error)
 		return error;
 
-	error = gfs2_rs_alloc(ndip);
+	error = gfs2_rsqa_alloc(ndip);
 	if (error)
 		return error;
 
@@ -1712,24 +1668,30 @@ static int gfs2_rename2(struct inode *odir, struct dentry *odentry,
 }
 
 /**
- * gfs2_follow_link - Follow a symbolic link
+ * gfs2_get_link - Follow a symbolic link
  * @dentry: The dentry of the link
- * @nd: Data that we pass to vfs_follow_link()
+ * @inode: The inode of the link
+ * @done: destructor for return value
  *
  * This can handle symlinks of any size.
  *
  * Returns: 0 on success or error code
  */
 
-static const char *gfs2_follow_link(struct dentry *dentry, void **cookie)
+static const char *gfs2_get_link(struct dentry *dentry,
+				 struct inode *inode,
+				 struct delayed_call *done)
 {
-	struct gfs2_inode *ip = GFS2_I(d_inode(dentry));
+	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_holder i_gh;
 	struct buffer_head *dibh;
 	unsigned int size;
 	char *buf;
 	int error;
 
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
 	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh);
 	error = gfs2_glock_nq(&i_gh);
 	if (error) {
@@ -1759,7 +1721,7 @@ static const char *gfs2_follow_link(struct dentry *dentry, void **cookie)
 out:
 	gfs2_glock_dq_uninit(&i_gh);
 	if (!IS_ERR(buf))
-		*cookie = buf;
+		set_delayed_call(done, kfree_link, buf);
 	return buf;
 }
 
@@ -1854,11 +1816,7 @@ static int setattr_chown(struct inode *inode, struct iattr *attr)
 	if (!(attr->ia_valid & ATTR_GID) || gid_eq(ogid, ngid))
 		ogid = ngid = NO_GID_QUOTA_CHANGE;
 
-	error = get_write_access(inode);
-	if (error)
-		return error;
-
-	error = gfs2_rs_alloc(ip);
+	error = gfs2_rsqa_alloc(ip);
 	if (error)
 		goto out;
 
@@ -1898,7 +1856,6 @@ out_end_trans:
 out_gunlock_q:
 	gfs2_quota_unlock(ip);
 out:
-	put_write_access(inode);
 	return error;
 }
 
@@ -1920,7 +1877,7 @@ static int gfs2_setattr(struct dentry *dentry, struct iattr *attr)
 	struct gfs2_holder i_gh;
 	int error;
 
-	error = gfs2_rs_alloc(ip);
+	error = gfs2_rsqa_alloc(ip);
 	if (error)
 		return error;
 
@@ -2002,7 +1959,7 @@ static int gfs2_setxattr(struct dentry *dentry, const char *name,
 	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
 	ret = gfs2_glock_nq(&gh);
 	if (ret == 0) {
-		ret = gfs2_rs_alloc(ip);
+		ret = gfs2_rsqa_alloc(ip);
 		if (ret == 0)
 			ret = generic_setxattr(dentry, name, data, size, flags);
 		gfs2_glock_dq(&gh);
@@ -2043,7 +2000,7 @@ static int gfs2_removexattr(struct dentry *dentry, const char *name)
 	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
 	ret = gfs2_glock_nq(&gh);
 	if (ret == 0) {
-		ret = gfs2_rs_alloc(ip);
+		ret = gfs2_rsqa_alloc(ip);
 		if (ret == 0)
 			ret = generic_removexattr(dentry, name);
 		gfs2_glock_dq(&gh);
@@ -2063,7 +2020,7 @@ static int gfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	if (ret)
 		return ret;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
 	if (ret)
@@ -2090,7 +2047,7 @@ static int gfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 
 	gfs2_glock_dq_uninit(&gh);
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return ret;
 }
 
@@ -2132,8 +2089,7 @@ const struct inode_operations gfs2_dir_iops = {
 
 const struct inode_operations gfs2_symlink_iops = {
 	.readlink = generic_readlink,
-	.follow_link = gfs2_follow_link,
-	.put_link = kfree_put_link,
+	.get_link = gfs2_get_link,
 	.permission = gfs2_permission,
 	.setattr = gfs2_setattr,
 	.getattr = gfs2_getattr,
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index ba4d9492d422..e1af0d4aa308 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -94,12 +94,11 @@ err:
 }
 
 extern struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, 
-				       u64 no_addr, u64 no_formal_ino,
-				       int non_block);
+				       u64 no_addr, u64 no_formal_ino);
 extern struct inode *gfs2_lookup_by_inum(struct gfs2_sbd *sdp, u64 no_addr,
 					 u64 *no_formal_ino,
 					 unsigned int blktype);
-extern struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr, int nonblock);
+extern struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr);
 
 extern int gfs2_inode_refresh(struct gfs2_inode *ip);
 
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 284c1542783e..8b907c5cc913 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -50,7 +50,7 @@ static inline void gfs2_update_stats(struct gfs2_lkstats *s, unsigned index,
 	s64 delta = sample - s->stats[index];
 	s->stats[index] += (delta >> 3);
 	index++;
-	s->stats[index] += ((abs64(delta) - s->stats[index]) >> 2);
+	s->stats[index] += ((abs(delta) - s->stats[index]) >> 2);
 }
 
 /**
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 536e7a6252cd..0ff028c15199 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -716,6 +716,9 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl,
 	}
 	trace_gfs2_log_flush(sdp, 1);
 
+	if (type == SHUTDOWN_FLUSH)
+		clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
+
 	sdp->sd_log_flush_head = sdp->sd_log_head;
 	sdp->sd_log_flush_wrapped = 0;
 	tr = sdp->sd_log_tr;
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index 241a399bf83d..f99f8e94de3f 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -41,7 +41,9 @@ static void gfs2_init_inode_once(void *foo)
 	inode_init_once(&ip->i_inode);
 	init_rwsem(&ip->i_rw_mutex);
 	INIT_LIST_HEAD(&ip->i_trunc_list);
-	ip->i_res = NULL;
+	ip->i_qadata = NULL;
+	memset(&ip->i_res, 0, sizeof(ip->i_res));
+	RB_CLEAR_NODE(&ip->i_res.rs_node);
 	ip->i_hash_cache = NULL;
 }
 
@@ -50,7 +52,7 @@ static void gfs2_init_glock_once(void *foo)
 	struct gfs2_glock *gl = foo;
 
 	INIT_HLIST_BL_NODE(&gl->gl_list);
-	spin_lock_init(&gl->gl_spin);
+	spin_lock_init(&gl->gl_lockref.lock);
 	INIT_LIST_HEAD(&gl->gl_holders);
 	INIT_LIST_HEAD(&gl->gl_lru);
 	INIT_LIST_HEAD(&gl->gl_ail_list);
@@ -112,7 +114,8 @@ static int __init init_gfs2_fs(void)
 	gfs2_inode_cachep = kmem_cache_create("gfs2_inode",
 					      sizeof(struct gfs2_inode),
 					      0,  SLAB_RECLAIM_ACCOUNT|
-					          SLAB_MEM_SPREAD,
+						  SLAB_MEM_SPREAD|
+						  SLAB_ACCOUNT,
 					      gfs2_init_inode_once);
 	if (!gfs2_inode_cachep)
 		goto fail;
@@ -135,10 +138,10 @@ static int __init init_gfs2_fs(void)
 	if (!gfs2_quotad_cachep)
 		goto fail;
 
-	gfs2_rsrv_cachep = kmem_cache_create("gfs2_mblk",
-					     sizeof(struct gfs2_blkreserv),
+	gfs2_qadata_cachep = kmem_cache_create("gfs2_qadata",
+					       sizeof(struct gfs2_qadata),
 					       0, 0, NULL);
-	if (!gfs2_rsrv_cachep)
+	if (!gfs2_qadata_cachep)
 		goto fail;
 
 	register_shrinker(&gfs2_qd_shrinker);
@@ -193,8 +196,8 @@ fail_lru:
 	unregister_shrinker(&gfs2_qd_shrinker);
 	gfs2_glock_exit();
 
-	if (gfs2_rsrv_cachep)
-		kmem_cache_destroy(gfs2_rsrv_cachep);
+	if (gfs2_qadata_cachep)
+		kmem_cache_destroy(gfs2_qadata_cachep);
 
 	if (gfs2_quotad_cachep)
 		kmem_cache_destroy(gfs2_quotad_cachep);
@@ -238,7 +241,7 @@ static void __exit exit_gfs2_fs(void)
 	rcu_barrier();
 
 	mempool_destroy(gfs2_page_pool);
-	kmem_cache_destroy(gfs2_rsrv_cachep);
+	kmem_cache_destroy(gfs2_qadata_cachep);
 	kmem_cache_destroy(gfs2_quotad_cachep);
 	kmem_cache_destroy(gfs2_rgrpd_cachep);
 	kmem_cache_destroy(gfs2_bufdata_cachep);
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 0e1d4be5865a..0448524c11bc 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -124,7 +124,7 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create)
 	if (mapping == NULL)
 		mapping = &sdp->sd_aspace;
 
-	shift = PAGE_CACHE_SHIFT - sdp->sd_sb.sb_bsize_shift;
+	shift = PAGE_SHIFT - sdp->sd_sb.sb_bsize_shift;
 	index = blkno >> shift;             /* convert block to page */
 	bufnum = blkno - (index << shift);  /* block buf index within page */
 
@@ -154,7 +154,7 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create)
 		map_bh(bh, sdp->sd_vfs, blkno);
 
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 
 	return bh;
 }
@@ -187,6 +187,52 @@ struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno)
 	return bh;
 }
 
+static void gfs2_meta_read_endio(struct bio *bio)
+{
+	struct bio_vec *bvec;
+	int i;
+
+	bio_for_each_segment_all(bvec, bio, i) {
+		struct page *page = bvec->bv_page;
+		struct buffer_head *bh = page_buffers(page);
+		unsigned int len = bvec->bv_len;
+
+		while (bh_offset(bh) < bvec->bv_offset)
+			bh = bh->b_this_page;
+		do {
+			struct buffer_head *next = bh->b_this_page;
+			len -= bh->b_size;
+			bh->b_end_io(bh, !bio->bi_error);
+			bh = next;
+		} while (bh && len);
+	}
+	bio_put(bio);
+}
+
+/*
+ * Submit several consecutive buffer head I/O requests as a single bio I/O
+ * request.  (See submit_bh_wbc.)
+ */
+static void gfs2_submit_bhs(int rw, struct buffer_head *bhs[], int num)
+{
+	struct buffer_head *bh = bhs[0];
+	struct bio *bio;
+	int i;
+
+	if (!num)
+		return;
+
+	bio = bio_alloc(GFP_NOIO, num);
+	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
+	bio->bi_bdev = bh->b_bdev;
+	for (i = 0; i < num; i++) {
+		bh = bhs[i];
+		bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
+	}
+	bio->bi_end_io = gfs2_meta_read_endio;
+	submit_bio(rw, bio);
+}
+
 /**
  * gfs2_meta_read - Read a block from disk
  * @gl: The glock covering the block
@@ -198,10 +244,11 @@ struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno)
  */
 
 int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
-		   struct buffer_head **bhp)
+		   int rahead, struct buffer_head **bhp)
 {
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
-	struct buffer_head *bh;
+	struct buffer_head *bh, *bhs[2];
+	int num = 0;
 
 	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) {
 		*bhp = NULL;
@@ -213,14 +260,31 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
 	lock_buffer(bh);
 	if (buffer_uptodate(bh)) {
 		unlock_buffer(bh);
-		return 0;
+		flags &= ~DIO_WAIT;
+	} else {
+		bh->b_end_io = end_buffer_read_sync;
+		get_bh(bh);
+		bhs[num++] = bh;
 	}
-	bh->b_end_io = end_buffer_read_sync;
-	get_bh(bh);
-	submit_bh(READ_SYNC | REQ_META | REQ_PRIO, bh);
+
+	if (rahead) {
+		bh = gfs2_getbuf(gl, blkno + 1, CREATE);
+
+		lock_buffer(bh);
+		if (buffer_uptodate(bh)) {
+			unlock_buffer(bh);
+			brelse(bh);
+		} else {
+			bh->b_end_io = end_buffer_read_sync;
+			bhs[num++] = bh;
+		}
+	}
+
+	gfs2_submit_bhs(READ_SYNC | REQ_META | REQ_PRIO, bhs, num);
 	if (!(flags & DIO_WAIT))
 		return 0;
 
+	bh = *bhp;
 	wait_on_buffer(bh);
 	if (unlikely(!buffer_uptodate(bh))) {
 		struct gfs2_trans *tr = current->journal_info;
@@ -341,8 +405,12 @@ int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num,
 	struct buffer_head *bh;
 	int ret = 0;
 	u32 mtype = height ? GFS2_METATYPE_IN : GFS2_METATYPE_DI;
+	int rahead = 0;
+
+	if (num == ip->i_no_addr)
+		rahead = ip->i_rahead;
 
-	ret = gfs2_meta_read(gl, num, DIO_WAIT, &bh);
+	ret = gfs2_meta_read(gl, num, DIO_WAIT, rahead, &bh);
 	if (ret == 0 && gfs2_metatype_check(sdp, bh, mtype)) {
 		brelse(bh);
 		ret = -EIO;
diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h
index 8ca161567a93..c5086c8af5ed 100644
--- a/fs/gfs2/meta_io.h
+++ b/fs/gfs2/meta_io.h
@@ -53,7 +53,7 @@ static inline struct gfs2_sbd *gfs2_mapping2sbd(struct address_space *mapping)
 
 extern struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno);
 extern int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
-			  struct buffer_head **bhp);
+			  int rahead, struct buffer_head **bhp);
 extern int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh);
 extern struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno,
 				       int create);
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 02586e7eb964..49b0bff18fe3 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -352,6 +352,9 @@ static int gfs2_read_sb(struct gfs2_sbd *sdp, int silent)
 	sdp->sd_jheightsize[x] = ~0;
 	gfs2_assert(sdp, sdp->sd_max_jheight <= GFS2_MAX_META_HEIGHT);
 
+	sdp->sd_max_dents_per_leaf = (sdp->sd_sb.sb_bsize -
+				      sizeof(struct gfs2_leaf)) /
+				     GFS2_MIN_DIRENT_SIZE;
 	return 0;
 }
 
@@ -451,7 +454,7 @@ static int gfs2_lookup_root(struct super_block *sb, struct dentry **dptr,
 	struct dentry *dentry;
 	struct inode *inode;
 
-	inode = gfs2_inode_lookup(sb, DT_DIR, no_addr, 0, 0);
+	inode = gfs2_inode_lookup(sb, DT_DIR, no_addr, 0);
 	if (IS_ERR(inode)) {
 		fs_err(sdp, "can't read in %s inode: %ld\n", name, PTR_ERR(inode));
 		return PTR_ERR(inode);
@@ -910,8 +913,7 @@ fail_qc_i:
 fail_ut_i:
 	iput(sdp->sd_sc_inode);
 fail:
-	if (pn)
-		iput(pn);
+	iput(pn);
 	return error;
 }
 
@@ -1291,6 +1293,9 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags,
 		up_write(&s->s_umount);
 		blkdev_put(bdev, mode);
 		down_write(&s->s_umount);
+	} else {
+		/* s_mode must be set before deactivate_locked_super calls */
+		s->s_mode = mode;
 	}
 
 	memset(&args, 0, sizeof(args));
@@ -1312,10 +1317,7 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags,
 		if ((flags ^ s->s_flags) & MS_RDONLY)
 			goto error_super;
 	} else {
-		char b[BDEVNAME_SIZE];
-
-		s->s_mode = mode;
-		strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
+		snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
 		sb_set_blocksize(s, block_size(bdev));
 		error = fill_super(s, &args, flags & MS_SILENT ? 1 : 0);
 		if (error)
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 3a31226531ea..ce7d69a2fdc0 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -388,7 +388,7 @@ static int bh_get(struct gfs2_quota_data *qd)
 	error = gfs2_block_map(&ip->i_inode, block, &bh_map, 0);
 	if (error)
 		goto fail;
-	error = gfs2_meta_read(ip->i_gl, bh_map.b_blocknr, DIO_WAIT, &bh);
+	error = gfs2_meta_read(ip->i_gl, bh_map.b_blocknr, DIO_WAIT, 0, &bh);
 	if (error)
 		goto fail;
 	error = -EIO;
@@ -527,37 +527,70 @@ static void qdsb_put(struct gfs2_quota_data *qd)
 	qd_put(qd);
 }
 
+/**
+ * gfs2_qa_alloc - make sure we have a quota allocations data structure,
+ *                 if necessary
+ * @ip: the inode for this reservation
+ */
+int gfs2_qa_alloc(struct gfs2_inode *ip)
+{
+	int error = 0;
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+
+	if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
+		return 0;
+
+	down_write(&ip->i_rw_mutex);
+	if (ip->i_qadata == NULL) {
+		ip->i_qadata = kmem_cache_zalloc(gfs2_qadata_cachep, GFP_NOFS);
+		if (!ip->i_qadata)
+			error = -ENOMEM;
+	}
+	up_write(&ip->i_rw_mutex);
+	return error;
+}
+
+void gfs2_qa_delete(struct gfs2_inode *ip, atomic_t *wcount)
+{
+	down_write(&ip->i_rw_mutex);
+	if (ip->i_qadata && ((wcount == NULL) || (atomic_read(wcount) <= 1))) {
+		kmem_cache_free(gfs2_qadata_cachep, ip->i_qadata);
+		ip->i_qadata = NULL;
+	}
+	up_write(&ip->i_rw_mutex);
+}
+
 int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_quota_data **qd;
 	int error;
 
-	if (ip->i_res == NULL) {
-		error = gfs2_rs_alloc(ip);
+	if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
+		return 0;
+
+	if (ip->i_qadata == NULL) {
+		error = gfs2_rsqa_alloc(ip);
 		if (error)
 			return error;
 	}
 
-	qd = ip->i_res->rs_qa_qd;
+	qd = ip->i_qadata->qa_qd;
 
-	if (gfs2_assert_warn(sdp, !ip->i_res->rs_qa_qd_num) ||
+	if (gfs2_assert_warn(sdp, !ip->i_qadata->qa_qd_num) ||
 	    gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags)))
 		return -EIO;
 
-	if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
-		return 0;
-
 	error = qdsb_get(sdp, make_kqid_uid(ip->i_inode.i_uid), qd);
 	if (error)
 		goto out;
-	ip->i_res->rs_qa_qd_num++;
+	ip->i_qadata->qa_qd_num++;
 	qd++;
 
 	error = qdsb_get(sdp, make_kqid_gid(ip->i_inode.i_gid), qd);
 	if (error)
 		goto out;
-	ip->i_res->rs_qa_qd_num++;
+	ip->i_qadata->qa_qd_num++;
 	qd++;
 
 	if (!uid_eq(uid, NO_UID_QUOTA_CHANGE) &&
@@ -565,7 +598,7 @@ int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
 		error = qdsb_get(sdp, make_kqid_uid(uid), qd);
 		if (error)
 			goto out;
-		ip->i_res->rs_qa_qd_num++;
+		ip->i_qadata->qa_qd_num++;
 		qd++;
 	}
 
@@ -574,7 +607,7 @@ int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
 		error = qdsb_get(sdp, make_kqid_gid(gid), qd);
 		if (error)
 			goto out;
-		ip->i_res->rs_qa_qd_num++;
+		ip->i_qadata->qa_qd_num++;
 		qd++;
 	}
 
@@ -587,17 +620,17 @@ out:
 void gfs2_quota_unhold(struct gfs2_inode *ip)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	unsigned int x;
+	u32 x;
 
-	if (ip->i_res == NULL)
+	if (ip->i_qadata == NULL)
 		return;
 	gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags));
 
-	for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) {
-		qdsb_put(ip->i_res->rs_qa_qd[x]);
-		ip->i_res->rs_qa_qd[x] = NULL;
+	for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
+		qdsb_put(ip->i_qadata->qa_qd[x]);
+		ip->i_qadata->qa_qd[x] = NULL;
 	}
-	ip->i_res->rs_qa_qd_num = 0;
+	ip->i_qadata->qa_qd_num = 0;
 }
 
 static int sort_qd(const void *a, const void *b)
@@ -668,7 +701,7 @@ static int gfs2_write_buf_to_page(struct gfs2_inode *ip, unsigned long index,
 	unsigned to_write = bytes, pg_off = off;
 	int done = 0;
 
-	blk = index << (PAGE_CACHE_SHIFT - sdp->sd_sb.sb_bsize_shift);
+	blk = index << (PAGE_SHIFT - sdp->sd_sb.sb_bsize_shift);
 	boff = off % bsize;
 
 	page = find_or_create_page(mapping, index, GFP_NOFS);
@@ -720,13 +753,13 @@ static int gfs2_write_buf_to_page(struct gfs2_inode *ip, unsigned long index,
 	flush_dcache_page(page);
 	kunmap_atomic(kaddr);
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 
 	return 0;
 
 unlock_out:
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 	return -EIO;
 }
 
@@ -740,13 +773,13 @@ static int gfs2_write_disk_quota(struct gfs2_inode *ip, struct gfs2_quota *qp,
 
 	nbytes = sizeof(struct gfs2_quota);
 
-	pg_beg = loc >> PAGE_CACHE_SHIFT;
-	pg_off = loc % PAGE_CACHE_SIZE;
+	pg_beg = loc >> PAGE_SHIFT;
+	pg_off = loc % PAGE_SIZE;
 
 	/* If the quota straddles a page boundary, split the write in two */
-	if ((pg_off + nbytes) > PAGE_CACHE_SIZE) {
+	if ((pg_off + nbytes) > PAGE_SIZE) {
 		pg_oflow = 1;
-		overflow = (pg_off + nbytes) - PAGE_CACHE_SIZE;
+		overflow = (pg_off + nbytes) - PAGE_SIZE;
 	}
 
 	ptr = qp;
@@ -843,7 +876,7 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda)
 	unsigned int nalloc = 0, blocks;
 	int error;
 
-	error = gfs2_rs_alloc(ip);
+	error = gfs2_rsqa_alloc(ip);
 	if (error)
 		return error;
 
@@ -855,7 +888,7 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda)
 		return -ENOMEM;
 
 	sort(qda, num_qd, sizeof(struct gfs2_quota_data *), sort_qd, NULL);
-	mutex_lock(&ip->i_inode.i_mutex);
+	inode_lock(&ip->i_inode);
 	for (qx = 0; qx < num_qd; qx++) {
 		error = gfs2_glock_nq_init(qda[qx]->qd_gl, LM_ST_EXCLUSIVE,
 					   GL_NOCACHE, &ghs[qx]);
@@ -920,7 +953,7 @@ out_alloc:
 out:
 	while (qx--)
 		gfs2_glock_dq_uninit(&ghs[qx]);
-	mutex_unlock(&ip->i_inode.i_mutex);
+	inode_unlock(&ip->i_inode);
 	kfree(ghs);
 	gfs2_log_flush(ip->i_gl->gl_name.ln_sbd, ip->i_gl, NORMAL_FLUSH);
 	return error;
@@ -1003,23 +1036,23 @@ int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_quota_data *qd;
-	unsigned int x;
+	u32 x;
 	int error = 0;
 
-	error = gfs2_quota_hold(ip, uid, gid);
-	if (error)
-		return error;
-
 	if (capable(CAP_SYS_RESOURCE) ||
 	    sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
 		return 0;
 
-	sort(ip->i_res->rs_qa_qd, ip->i_res->rs_qa_qd_num,
+	error = gfs2_quota_hold(ip, uid, gid);
+	if (error)
+		return error;
+
+	sort(ip->i_qadata->qa_qd, ip->i_qadata->qa_qd_num,
 	     sizeof(struct gfs2_quota_data *), sort_qd, NULL);
 
-	for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) {
-		qd = ip->i_res->rs_qa_qd[x];
-		error = do_glock(qd, NO_FORCE, &ip->i_res->rs_qa_qd_ghs[x]);
+	for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
+		qd = ip->i_qadata->qa_qd[x];
+		error = do_glock(qd, NO_FORCE, &ip->i_qadata->qa_qd_ghs[x]);
 		if (error)
 			break;
 	}
@@ -1028,7 +1061,7 @@ int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
 		set_bit(GIF_QD_LOCKED, &ip->i_flags);
 	else {
 		while (x--)
-			gfs2_glock_dq_uninit(&ip->i_res->rs_qa_qd_ghs[x]);
+			gfs2_glock_dq_uninit(&ip->i_qadata->qa_qd_ghs[x]);
 		gfs2_quota_unhold(ip);
 	}
 
@@ -1076,20 +1109,20 @@ void gfs2_quota_unlock(struct gfs2_inode *ip)
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_quota_data *qda[4];
 	unsigned int count = 0;
-	unsigned int x;
+	u32 x;
 	int found;
 
 	if (!test_and_clear_bit(GIF_QD_LOCKED, &ip->i_flags))
 		goto out;
 
-	for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) {
+	for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
 		struct gfs2_quota_data *qd;
 		int sync;
 
-		qd = ip->i_res->rs_qa_qd[x];
+		qd = ip->i_qadata->qa_qd[x];
 		sync = need_sync(qd);
 
-		gfs2_glock_dq_uninit(&ip->i_res->rs_qa_qd_ghs[x]);
+		gfs2_glock_dq_uninit(&ip->i_qadata->qa_qd_ghs[x]);
 		if (!sync)
 			continue;
 
@@ -1158,7 +1191,7 @@ int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid,
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_quota_data *qd;
 	s64 value, warn, limit;
-	unsigned int x;
+	u32 x;
 	int error = 0;
 
 	ap->allowed = UINT_MAX; /* Assume we are permitted a whole lot */
@@ -1168,8 +1201,8 @@ int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid,
         if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
                 return 0;
 
-	for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) {
-		qd = ip->i_res->rs_qa_qd[x];
+	for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
+		qd = ip->i_qadata->qa_qd[x];
 
 		if (!(qid_eq(qd->qd_id, make_kqid_uid(uid)) ||
 		      qid_eq(qd->qd_id, make_kqid_gid(gid))))
@@ -1216,15 +1249,17 @@ void gfs2_quota_change(struct gfs2_inode *ip, s64 change,
 		       kuid_t uid, kgid_t gid)
 {
 	struct gfs2_quota_data *qd;
-	unsigned int x;
+	u32 x;
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 
-	if (gfs2_assert_warn(GFS2_SB(&ip->i_inode), change))
+	if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON ||
+	    gfs2_assert_warn(sdp, change))
 		return;
 	if (ip->i_diskflags & GFS2_DIF_SYSTEM)
 		return;
 
-	for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) {
-		qd = ip->i_res->rs_qa_qd[x];
+	for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
+		qd = ip->i_qadata->qa_qd[x];
 
 		if (qid_eq(qd->qd_id, make_kqid_uid(uid)) ||
 		    qid_eq(qd->qd_id, make_kqid_gid(gid))) {
@@ -1635,11 +1670,11 @@ static int gfs2_set_dqblk(struct super_block *sb, struct kqid qid,
 	if (error)
 		return error;
 
-	error = gfs2_rs_alloc(ip);
+	error = gfs2_rsqa_alloc(ip);
 	if (error)
 		goto out_put;
 
-	mutex_lock(&ip->i_inode.i_mutex);
+	inode_lock(&ip->i_inode);
 	error = gfs2_glock_nq_init(qd->qd_gl, LM_ST_EXCLUSIVE, 0, &q_gh);
 	if (error)
 		goto out_unlockput;
@@ -1704,7 +1739,7 @@ out_i:
 out_q:
 	gfs2_glock_dq_uninit(&q_gh);
 out_unlockput:
-	mutex_unlock(&ip->i_inode.i_mutex);
+	inode_unlock(&ip->i_inode);
 out_put:
 	qd_put(qd);
 	return error;
diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h
index ad04b3acae2b..5e47c935a515 100644
--- a/fs/gfs2/quota.h
+++ b/fs/gfs2/quota.h
@@ -18,6 +18,8 @@ struct gfs2_sbd;
 #define NO_UID_QUOTA_CHANGE INVALID_UID
 #define NO_GID_QUOTA_CHANGE INVALID_GID
 
+extern int gfs2_qa_alloc(struct gfs2_inode *ip);
+extern void gfs2_qa_delete(struct gfs2_inode *ip, atomic_t *wcount);
 extern int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid);
 extern void gfs2_quota_unhold(struct gfs2_inode *ip);
 
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 475985d14758..99a0bdac8796 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -596,27 +596,13 @@ void gfs2_free_clones(struct gfs2_rgrpd *rgd)
 }
 
 /**
- * gfs2_rs_alloc - make sure we have a reservation assigned to the inode
+ * gfs2_rsqa_alloc - make sure we have a reservation assigned to the inode
+ *                 plus a quota allocations data structure, if necessary
  * @ip: the inode for this reservation
  */
-int gfs2_rs_alloc(struct gfs2_inode *ip)
+int gfs2_rsqa_alloc(struct gfs2_inode *ip)
 {
-	int error = 0;
-
-	down_write(&ip->i_rw_mutex);
-	if (ip->i_res)
-		goto out;
-
-	ip->i_res = kmem_cache_zalloc(gfs2_rsrv_cachep, GFP_NOFS);
-	if (!ip->i_res) {
-		error = -ENOMEM;
-		goto out;
-	}
-
-	RB_CLEAR_NODE(&ip->i_res->rs_node);
-out:
-	up_write(&ip->i_rw_mutex);
-	return error;
+	return gfs2_qa_alloc(ip);
 }
 
 static void dump_rs(struct seq_file *seq, const struct gfs2_blkreserv *rs)
@@ -678,21 +664,20 @@ void gfs2_rs_deltree(struct gfs2_blkreserv *rs)
 }
 
 /**
- * gfs2_rs_delete - delete a multi-block reservation
+ * gfs2_rsqa_delete - delete a multi-block reservation and quota allocation
  * @ip: The inode for this reservation
  * @wcount: The inode's write count, or NULL
  *
  */
-void gfs2_rs_delete(struct gfs2_inode *ip, atomic_t *wcount)
+void gfs2_rsqa_delete(struct gfs2_inode *ip, atomic_t *wcount)
 {
 	down_write(&ip->i_rw_mutex);
-	if (ip->i_res && ((wcount == NULL) || (atomic_read(wcount) <= 1))) {
-		gfs2_rs_deltree(ip->i_res);
-		BUG_ON(ip->i_res->rs_free);
-		kmem_cache_free(gfs2_rsrv_cachep, ip->i_res);
-		ip->i_res = NULL;
+	if ((wcount == NULL) || (atomic_read(wcount) <= 1)) {
+		gfs2_rs_deltree(&ip->i_res);
+		BUG_ON(ip->i_res.rs_free);
 	}
 	up_write(&ip->i_rw_mutex);
+	gfs2_qa_delete(ip, wcount);
 }
 
 /**
@@ -729,9 +714,9 @@ void gfs2_clear_rgrpd(struct gfs2_sbd *sdp)
 		rb_erase(n, &sdp->sd_rindex_tree);
 
 		if (gl) {
-			spin_lock(&gl->gl_spin);
+			spin_lock(&gl->gl_lockref.lock);
 			gl->gl_object = NULL;
-			spin_unlock(&gl->gl_spin);
+			spin_unlock(&gl->gl_lockref.lock);
 			gfs2_glock_add_to_lru(gl);
 			gfs2_glock_put(gl);
 		}
@@ -933,8 +918,8 @@ static int read_rindex_entry(struct gfs2_inode *ip)
 		goto fail;
 
 	rgd->rd_gl->gl_object = rgd;
-	rgd->rd_gl->gl_vm.start = rgd->rd_addr * bsize;
-	rgd->rd_gl->gl_vm.end = rgd->rd_gl->gl_vm.start + (rgd->rd_length * bsize) - 1;
+	rgd->rd_gl->gl_vm.start = (rgd->rd_addr * bsize) & PAGE_MASK;
+	rgd->rd_gl->gl_vm.end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1;
 	rgd->rd_rgl = (struct gfs2_rgrp_lvb *)rgd->rd_gl->gl_lksb.sb_lvbptr;
 	rgd->rd_flags &= ~(GFS2_RDF_UPTODATE | GFS2_RDF_PREFERRED);
 	if (rgd->rd_data > sdp->sd_max_rg_data)
@@ -1157,7 +1142,7 @@ static int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd)
 
 	for (x = 0; x < length; x++) {
 		bi = rgd->rd_bits + x;
-		error = gfs2_meta_read(gl, rgd->rd_addr + x, 0, &bi->bi_bh);
+		error = gfs2_meta_read(gl, rgd->rd_addr + x, 0, 0, &bi->bi_bh);
 		if (error)
 			goto fail;
 	}
@@ -1455,7 +1440,7 @@ static void rs_insert(struct gfs2_inode *ip)
 {
 	struct rb_node **newn, *parent = NULL;
 	int rc;
-	struct gfs2_blkreserv *rs = ip->i_res;
+	struct gfs2_blkreserv *rs = &ip->i_res;
 	struct gfs2_rgrpd *rgd = rs->rs_rbm.rgd;
 	u64 fsblock = gfs2_rbm_to_block(&rs->rs_rbm);
 
@@ -1502,7 +1487,7 @@ static void rg_mblk_search(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip,
 {
 	struct gfs2_rbm rbm = { .rgd = rgd, };
 	u64 goal;
-	struct gfs2_blkreserv *rs = ip->i_res;
+	struct gfs2_blkreserv *rs = &ip->i_res;
 	u32 extlen;
 	u32 free_blocks = rgd->rd_free_clone - rgd->rd_reserved;
 	int ret;
@@ -1573,7 +1558,7 @@ static u64 gfs2_next_unreserved_block(struct gfs2_rgrpd *rgd, u64 block,
 	}
 
 	if (n) {
-		while ((rs_cmp(block, length, rs) == 0) && (ip->i_res != rs)) {
+		while ((rs_cmp(block, length, rs) == 0) && (&ip->i_res != rs)) {
 			block = gfs2_rbm_to_block(&rs->rs_rbm) + rs->rs_free;
 			n = n->rb_right;
 			if (n == NULL)
@@ -1803,7 +1788,7 @@ static void try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked, u64 skip
 			continue;
 		*last_unlinked = block;
 
-		error = gfs2_glock_get(sdp, block, &gfs2_inode_glops, CREATE, &gl);
+		error = gfs2_glock_get(sdp, block, &gfs2_iopen_glops, CREATE, &gl);
 		if (error)
 			continue;
 
@@ -1983,7 +1968,7 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, struct gfs2_alloc_parms *ap)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_rgrpd *begin = NULL;
-	struct gfs2_blkreserv *rs = ip->i_res;
+	struct gfs2_blkreserv *rs = &ip->i_res;
 	int error = 0, rg_locked, flags = 0;
 	u64 last_unlinked = NO_BLOCK;
 	int loops = 0;
@@ -2112,7 +2097,7 @@ next_rgrp:
 
 void gfs2_inplace_release(struct gfs2_inode *ip)
 {
-	struct gfs2_blkreserv *rs = ip->i_res;
+	struct gfs2_blkreserv *rs = &ip->i_res;
 
 	if (rs->rs_rgd_gh.gh_gl)
 		gfs2_glock_dq_uninit(&rs->rs_rgd_gh);
@@ -2266,7 +2251,7 @@ static void gfs2_rgrp_error(struct gfs2_rgrpd *rgd)
 static void gfs2_adjust_reservation(struct gfs2_inode *ip,
 				    const struct gfs2_rbm *rbm, unsigned len)
 {
-	struct gfs2_blkreserv *rs = ip->i_res;
+	struct gfs2_blkreserv *rs = &ip->i_res;
 	struct gfs2_rgrpd *rgd = rbm->rgd;
 	unsigned rlen;
 	u64 block;
@@ -2309,8 +2294,8 @@ static void gfs2_set_alloc_start(struct gfs2_rbm *rbm,
 {
 	u64 goal;
 
-	if (gfs2_rs_active(ip->i_res)) {
-		*rbm = ip->i_res->rs_rbm;
+	if (gfs2_rs_active(&ip->i_res)) {
+		*rbm = ip->i_res.rs_rbm;
 		return;
 	}
 
@@ -2364,7 +2349,7 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks,
 	gfs2_alloc_extent(&rbm, dinode, nblocks);
 	block = gfs2_rbm_to_block(&rbm);
 	rbm.rgd->rd_last_alloc = block - rbm.rgd->rd_data0;
-	if (gfs2_rs_active(ip->i_res))
+	if (gfs2_rs_active(&ip->i_res))
 		gfs2_adjust_reservation(ip, &rbm, *nblocks);
 	ndata = *nblocks;
 	if (dinode)
diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h
index c0ab33fa3eed..66b51cf66dfa 100644
--- a/fs/gfs2/rgrp.h
+++ b/fs/gfs2/rgrp.h
@@ -49,9 +49,9 @@ extern void gfs2_inplace_release(struct gfs2_inode *ip);
 extern int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *n,
 			     bool dinode, u64 *generation);
 
-extern int gfs2_rs_alloc(struct gfs2_inode *ip);
+extern int gfs2_rsqa_alloc(struct gfs2_inode *ip);
 extern void gfs2_rs_deltree(struct gfs2_blkreserv *rs);
-extern void gfs2_rs_delete(struct gfs2_inode *ip, atomic_t *wcount);
+extern void gfs2_rsqa_delete(struct gfs2_inode *ip, atomic_t *wcount);
 extern void __gfs2_free_blocks(struct gfs2_inode *ip, u64 bstart, u32 blen, int meta);
 extern void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen);
 extern void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip);
@@ -78,7 +78,7 @@ extern int gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
 extern int gfs2_fitrim(struct file *filp, void __user *argp);
 
 /* This is how to tell if a reservation is in the rgrp tree: */
-static inline bool gfs2_rs_active(struct gfs2_blkreserv *rs)
+static inline bool gfs2_rs_active(const struct gfs2_blkreserv *rs)
 {
 	return rs && !RB_EMPTY_NODE(&rs->rs_node);
 }
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 894fb01a91da..f8a0cd821290 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -83,6 +83,8 @@ enum {
 	Opt_nobarrier,
 	Opt_rgrplvb,
 	Opt_norgrplvb,
+	Opt_loccookie,
+	Opt_noloccookie,
 	Opt_error,
 };
 
@@ -122,6 +124,8 @@ static const match_table_t tokens = {
 	{Opt_nobarrier, "nobarrier"},
 	{Opt_rgrplvb, "rgrplvb"},
 	{Opt_norgrplvb, "norgrplvb"},
+	{Opt_loccookie, "loccookie"},
+	{Opt_noloccookie, "noloccookie"},
 	{Opt_error, NULL}
 };
 
@@ -278,6 +282,12 @@ int gfs2_mount_args(struct gfs2_args *args, char *options)
 		case Opt_norgrplvb:
 			args->ar_rgrplvb = 0;
 			break;
+		case Opt_loccookie:
+			args->ar_loccookie = 1;
+			break;
+		case Opt_noloccookie:
+			args->ar_loccookie = 0;
+			break;
 		case Opt_error:
 		default:
 			pr_warn("invalid mount option: %s\n", o);
@@ -556,6 +566,7 @@ void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh,
 	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
 
 	gfs2_trans_add_meta(l_ip->i_gl, l_bh);
+	gfs2_trans_add_meta(m_ip->i_gl, m_bh);
 
 	spin_lock(&sdp->sd_statfs_spin);
 	m_sc->sc_total += l_sc->sc_total;
@@ -564,10 +575,8 @@ void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh,
 	memset(l_sc, 0, sizeof(struct gfs2_statfs_change));
 	memset(l_bh->b_data + sizeof(struct gfs2_dinode),
 	       0, sizeof(struct gfs2_statfs_change));
-	spin_unlock(&sdp->sd_statfs_spin);
-
-	gfs2_trans_add_meta(m_ip->i_gl, m_bh);
 	gfs2_statfs_change_out(m_sc, m_bh->b_data + sizeof(struct gfs2_dinode));
+	spin_unlock(&sdp->sd_statfs_spin);
 }
 
 int gfs2_statfs_sync(struct super_block *sb, int type)
@@ -842,10 +851,6 @@ static int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
 	gfs2_quota_sync(sdp->sd_vfs, 0);
 	gfs2_statfs_sync(sdp->sd_vfs, 0);
 
-	down_write(&sdp->sd_log_flush_lock);
-	clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
-	up_write(&sdp->sd_log_flush_lock);
-
 	gfs2_log_flush(sdp, NULL, SHUTDOWN_FLUSH);
 	wait_event(sdp->sd_reserving_log_wait, atomic_read(&sdp->sd_reserving_log) == 0);
 	gfs2_assert_warn(sdp, atomic_read(&sdp->sd_log_blks_free) == sdp->sd_jdesc->jd_blocks);
@@ -1419,6 +1424,8 @@ static int gfs2_show_options(struct seq_file *s, struct dentry *root)
 		seq_puts(s, ",demote_interface_used");
 	if (args->ar_rgrplvb)
 		seq_puts(s, ",rgrplvb");
+	if (args->ar_loccookie)
+		seq_puts(s, ",loccookie");
 	return 0;
 }
 
@@ -1512,6 +1519,7 @@ static void gfs2_evict_inode(struct inode *inode)
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_holder gh;
+	struct address_space *metamapping;
 	int error;
 
 	if (test_bit(GIF_FREE_VFS_INODE, &ip->i_flags)) {
@@ -1526,7 +1534,8 @@ static void gfs2_evict_inode(struct inode *inode)
 	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, &gh);
 	if (unlikely(error)) {
 		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
-		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+		gfs2_glock_dq_wait(&ip->i_iopen_gh);
+		gfs2_holder_uninit(&ip->i_iopen_gh);
 		goto out;
 	}
 
@@ -1542,12 +1551,16 @@ static void gfs2_evict_inode(struct inode *inode)
 			goto out_truncate;
 	}
 
-	ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
-	gfs2_glock_dq_wait(&ip->i_iopen_gh);
-	gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, &ip->i_iopen_gh);
-	error = gfs2_glock_nq(&ip->i_iopen_gh);
-	if (error)
-		goto out_truncate;
+	if (ip->i_iopen_gh.gh_gl &&
+	    test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) {
+		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
+		gfs2_glock_dq_wait(&ip->i_iopen_gh);
+		gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE,
+				   &ip->i_iopen_gh);
+		error = gfs2_glock_nq(&ip->i_iopen_gh);
+		if (error)
+			goto out_truncate;
+	}
 
 	/* Case 1 starts here */
 
@@ -1575,8 +1588,8 @@ static void gfs2_evict_inode(struct inode *inode)
 
 out_truncate:
 	gfs2_log_flush(sdp, ip->i_gl, NORMAL_FLUSH);
+	metamapping = gfs2_glock2aspace(ip->i_gl);
 	if (test_bit(GLF_DIRTY, &ip->i_gl->gl_flags)) {
-		struct address_space *metamapping = gfs2_glock2aspace(ip->i_gl);
 		filemap_fdatawrite(metamapping);
 		filemap_fdatawait(metamapping);
 	}
@@ -1589,25 +1602,28 @@ out_truncate:
 		goto out_unlock;
 	/* Needs to be done before glock release & also in a transaction */
 	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages(metamapping, 0);
 	gfs2_trans_end(sdp);
 
 out_unlock:
 	/* Error path for case 1 */
-	if (gfs2_rs_active(ip->i_res))
-		gfs2_rs_deltree(ip->i_res);
+	if (gfs2_rs_active(&ip->i_res))
+		gfs2_rs_deltree(&ip->i_res);
 
-	if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) {
-		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
-		gfs2_glock_dq(&ip->i_iopen_gh);
+	if (ip->i_iopen_gh.gh_gl) {
+		if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) {
+			ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
+			gfs2_glock_dq_wait(&ip->i_iopen_gh);
+		}
+		gfs2_holder_uninit(&ip->i_iopen_gh);
 	}
-	gfs2_holder_uninit(&ip->i_iopen_gh);
 	gfs2_glock_dq_uninit(&gh);
 	if (error && error != GLR_TRYFAILED && error != -EROFS)
 		fs_warn(sdp, "gfs2_evict_inode: %d\n", error);
 out:
 	/* Case 3 starts here */
 	truncate_inode_pages_final(&inode->i_data);
-	gfs2_rs_delete(ip, NULL);
+	gfs2_rsqa_delete(ip, NULL);
 	gfs2_ordered_del_inode(ip);
 	clear_inode(inode);
 	gfs2_dir_hash_inval(ip);
@@ -1619,7 +1635,8 @@ out:
 	if (ip->i_iopen_gh.gh_gl) {
 		ip->i_iopen_gh.gh_gl->gl_object = NULL;
 		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
-		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+		gfs2_glock_dq_wait(&ip->i_iopen_gh);
+		gfs2_holder_uninit(&ip->i_iopen_gh);
 	}
 }
 
@@ -1632,7 +1649,9 @@ static struct inode *gfs2_alloc_inode(struct super_block *sb)
 		ip->i_flags = 0;
 		ip->i_gl = NULL;
 		ip->i_rgd = NULL;
-		ip->i_res = NULL;
+		memset(&ip->i_res, 0, sizeof(ip->i_res));
+		RB_CLEAR_NODE(&ip->i_res.rs_node);
+		ip->i_rahead = 0;
 	}
 	return &ip->i_inode;
 }
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index b95d0d625f32..0c1bde395062 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -176,6 +176,8 @@ void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh)
 		unlock_buffer(bh);
 		if (bh->b_private == NULL)
 			bd = gfs2_alloc_bufdata(gl, bh, &gfs2_databuf_lops);
+		else
+			bd = bh->b_private;
 		lock_buffer(bh);
 		gfs2_log_lock(sdp);
 	}
@@ -236,6 +238,8 @@ void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh)
 		lock_page(bh->b_page);
 		if (bh->b_private == NULL)
 			bd = gfs2_alloc_bufdata(gl, bh, &gfs2_buf_lops);
+		else
+			bd = bh->b_private;
 		unlock_page(bh->b_page);
 		lock_buffer(bh);
 		gfs2_log_lock(sdp);
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index 86d2035ac669..cf645835710f 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -27,7 +27,7 @@ struct kmem_cache *gfs2_inode_cachep __read_mostly;
 struct kmem_cache *gfs2_bufdata_cachep __read_mostly;
 struct kmem_cache *gfs2_rgrpd_cachep __read_mostly;
 struct kmem_cache *gfs2_quotad_cachep __read_mostly;
-struct kmem_cache *gfs2_rsrv_cachep __read_mostly;
+struct kmem_cache *gfs2_qadata_cachep __read_mostly;
 mempool_t *gfs2_page_pool __read_mostly;
 
 void gfs2_assert_i(struct gfs2_sbd *sdp)
diff --git a/fs/gfs2/util.h b/fs/gfs2/util.h
index cbdcbdf39614..c81295f407f6 100644
--- a/fs/gfs2/util.h
+++ b/fs/gfs2/util.h
@@ -149,7 +149,7 @@ extern struct kmem_cache *gfs2_inode_cachep;
 extern struct kmem_cache *gfs2_bufdata_cachep;
 extern struct kmem_cache *gfs2_rgrpd_cachep;
 extern struct kmem_cache *gfs2_quotad_cachep;
-extern struct kmem_cache *gfs2_rsrv_cachep;
+extern struct kmem_cache *gfs2_qadata_cachep;
 extern mempool_t *gfs2_page_pool;
 
 static inline unsigned int gfs2_tune_get_i(struct gfs2_tune *gt,
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index 4c096fa9e2a1..e8dfb4740c04 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -119,7 +119,7 @@ static int ea_foreach(struct gfs2_inode *ip, ea_call_t ea_call, void *data)
 	__be64 *eablk, *end;
 	int error;
 
-	error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, &bh);
+	error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, 0, &bh);
 	if (error)
 		return error;
 
@@ -143,7 +143,7 @@ static int ea_foreach(struct gfs2_inode *ip, ea_call_t ea_call, void *data)
 			break;
 		bn = be64_to_cpu(*eablk);
 
-		error = gfs2_meta_read(ip->i_gl, bn, DIO_WAIT, &eabh);
+		error = gfs2_meta_read(ip->i_gl, bn, DIO_WAIT, 0, &eabh);
 		if (error)
 			break;
 		error = ea_foreach_i(ip, eabh, ea_call, data);
@@ -477,7 +477,7 @@ static int gfs2_iter_unstuffed(struct gfs2_inode *ip, struct gfs2_ea_header *ea,
 		return -ENOMEM;
 
 	for (x = 0; x < nptrs; x++) {
-		error = gfs2_meta_read(ip->i_gl, be64_to_cpu(*dataptrs), 0,
+		error = gfs2_meta_read(ip->i_gl, be64_to_cpu(*dataptrs), 0, 0,
 				       bh + x);
 		if (error) {
 			while (x--)
@@ -583,11 +583,13 @@ out:
  *
  * Returns: actual size of data on success, -errno on error
  */
-static int gfs2_xattr_get(struct dentry *dentry, const char *name,
-		void *buffer, size_t size, int type)
+static int gfs2_xattr_get(const struct xattr_handler *handler,
+			  struct dentry *dentry, const char *name,
+			  void *buffer, size_t size)
 {
 	struct gfs2_inode *ip = GFS2_I(d_inode(dentry));
 	struct gfs2_ea_location el;
+	int type = handler->flags;
 	int error;
 
 	if (!ip->i_eattr)
@@ -977,7 +979,7 @@ static int ea_set_block(struct gfs2_inode *ip, struct gfs2_ea_request *er,
 	if (ip->i_diskflags & GFS2_DIF_EA_INDIRECT) {
 		__be64 *end;
 
-		error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT,
+		error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, 0,
 				       &indbh);
 		if (error)
 			return error;
@@ -1227,61 +1229,12 @@ int __gfs2_xattr_set(struct inode *inode, const char *name,
 	return error;
 }
 
-static int gfs2_xattr_set(struct dentry *dentry, const char *name,
-		const void *value, size_t size, int flags, int type)
+static int gfs2_xattr_set(const struct xattr_handler *handler,
+			  struct dentry *dentry, const char *name,
+			  const void *value, size_t size, int flags)
 {
 	return __gfs2_xattr_set(d_inode(dentry), name, value,
-				size, flags, type);
-}
-
-
-static int ea_acl_chmod_unstuffed(struct gfs2_inode *ip,
-				  struct gfs2_ea_header *ea, char *data)
-{
-	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	unsigned int amount = GFS2_EA_DATA_LEN(ea);
-	unsigned int nptrs = DIV_ROUND_UP(amount, sdp->sd_jbsize);
-	int ret;
-
-	ret = gfs2_trans_begin(sdp, nptrs + RES_DINODE, 0);
-	if (ret)
-		return ret;
-
-	ret = gfs2_iter_unstuffed(ip, ea, data, NULL);
-	gfs2_trans_end(sdp);
-
-	return ret;
-}
-
-int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data)
-{
-	struct inode *inode = &ip->i_inode;
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	struct gfs2_ea_location el;
-	int error;
-
-	error = gfs2_ea_find(ip, GFS2_EATYPE_SYS, GFS2_POSIX_ACL_ACCESS, &el);
-	if (error)
-		return error;
-
-	if (GFS2_EA_IS_STUFFED(el.el_ea)) {
-		error = gfs2_trans_begin(sdp, RES_DINODE + RES_EATTR, 0);
-		if (error == 0) {
-			gfs2_trans_add_meta(ip->i_gl, el.el_bh);
-			memcpy(GFS2_EA2DATA(el.el_ea), data,
-			       GFS2_EA_DATA_LEN(el.el_ea));
-		}
-	} else {
-		error = ea_acl_chmod_unstuffed(ip, el.el_ea, data);
-	}
-
-	brelse(el.el_bh);
-	if (error)
-		return error;
-
-	error = gfs2_setattr_simple(inode, attr);
-	gfs2_trans_end(sdp);
-	return error;
+				size, flags, handler->flags);
 }
 
 static int ea_dealloc_indirect(struct gfs2_inode *ip)
@@ -1303,7 +1256,7 @@ static int ea_dealloc_indirect(struct gfs2_inode *ip)
 
 	memset(&rlist, 0, sizeof(struct gfs2_rgrp_list));
 
-	error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, &indbh);
+	error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, 0, &indbh);
 	if (error)
 		return error;
 
diff --git a/fs/gfs2/xattr.h b/fs/gfs2/xattr.h
index d392f8358f2f..2d887c88eb49 100644
--- a/fs/gfs2/xattr.h
+++ b/fs/gfs2/xattr.h
@@ -62,6 +62,5 @@ extern int gfs2_ea_dealloc(struct gfs2_inode *ip);
 /* Exported to acl.c */
 
 extern int gfs2_xattr_acl_get(struct gfs2_inode *ip, const char *name, char **data);
-extern int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data);
 
 #endif /* __EATTR_DOT_H__ */
diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c
index 221719eac5de..d77d844b668b 100644
--- a/fs/hfs/bnode.c
+++ b/fs/hfs/bnode.c
@@ -278,14 +278,14 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid)
 
 	mapping = tree->inode->i_mapping;
 	off = (loff_t)cnid * tree->node_size;
-	block = off >> PAGE_CACHE_SHIFT;
-	node->page_offset = off & ~PAGE_CACHE_MASK;
+	block = off >> PAGE_SHIFT;
+	node->page_offset = off & ~PAGE_MASK;
 	for (i = 0; i < tree->pages_per_bnode; i++) {
 		page = read_mapping_page(mapping, block++, NULL);
 		if (IS_ERR(page))
 			goto fail;
 		if (PageError(page)) {
-			page_cache_release(page);
+			put_page(page);
 			goto fail;
 		}
 		node->page[i] = page;
@@ -401,7 +401,7 @@ void hfs_bnode_free(struct hfs_bnode *node)
 
 	for (i = 0; i < node->tree->pages_per_bnode; i++)
 		if (node->page[i])
-			page_cache_release(node->page[i]);
+			put_page(node->page[i]);
 	kfree(node);
 }
 
@@ -429,11 +429,11 @@ struct hfs_bnode *hfs_bnode_create(struct hfs_btree *tree, u32 num)
 
 	pagep = node->page;
 	memset(kmap(*pagep) + node->page_offset, 0,
-	       min((int)PAGE_CACHE_SIZE, (int)tree->node_size));
+	       min((int)PAGE_SIZE, (int)tree->node_size));
 	set_page_dirty(*pagep);
 	kunmap(*pagep);
 	for (i = 1; i < tree->pages_per_bnode; i++) {
-		memset(kmap(*++pagep), 0, PAGE_CACHE_SIZE);
+		memset(kmap(*++pagep), 0, PAGE_SIZE);
 		set_page_dirty(*pagep);
 		kunmap(*pagep);
 	}
diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c
index 1ab19e660e69..37cdd955eceb 100644
--- a/fs/hfs/btree.c
+++ b/fs/hfs/btree.c
@@ -116,14 +116,14 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp ke
 	}
 
 	tree->node_size_shift = ffs(size) - 1;
-	tree->pages_per_bnode = (tree->node_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	tree->pages_per_bnode = (tree->node_size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
 	kunmap(page);
-	page_cache_release(page);
+	put_page(page);
 	return tree;
 
 fail_page:
-	page_cache_release(page);
+	put_page(page);
 free_inode:
 	tree->inode->i_mapping->a_ops = &hfs_aops;
 	iput(tree->inode);
@@ -257,9 +257,9 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree)
 	off = off16;
 
 	off += node->page_offset;
-	pagep = node->page + (off >> PAGE_CACHE_SHIFT);
+	pagep = node->page + (off >> PAGE_SHIFT);
 	data = kmap(*pagep);
-	off &= ~PAGE_CACHE_MASK;
+	off &= ~PAGE_MASK;
 	idx = 0;
 
 	for (;;) {
@@ -279,7 +279,7 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree)
 					}
 				}
 			}
-			if (++off >= PAGE_CACHE_SIZE) {
+			if (++off >= PAGE_SIZE) {
 				kunmap(*pagep);
 				data = kmap(*++pagep);
 				off = 0;
@@ -302,9 +302,9 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree)
 		len = hfs_brec_lenoff(node, 0, &off16);
 		off = off16;
 		off += node->page_offset;
-		pagep = node->page + (off >> PAGE_CACHE_SHIFT);
+		pagep = node->page + (off >> PAGE_SHIFT);
 		data = kmap(*pagep);
-		off &= ~PAGE_CACHE_MASK;
+		off &= ~PAGE_MASK;
 	}
 }
 
@@ -348,9 +348,9 @@ void hfs_bmap_free(struct hfs_bnode *node)
 		len = hfs_brec_lenoff(node, 0, &off);
 	}
 	off += node->page_offset + nidx / 8;
-	page = node->page[off >> PAGE_CACHE_SHIFT];
+	page = node->page[off >> PAGE_SHIFT];
 	data = kmap(page);
-	off &= ~PAGE_CACHE_MASK;
+	off &= ~PAGE_MASK;
 	m = 1 << (~nidx & 7);
 	byte = data[off];
 	if (!(byte & m)) {
diff --git a/fs/hfs/catalog.c b/fs/hfs/catalog.c
index db458ee3a546..1eb5d415d434 100644
--- a/fs/hfs/catalog.c
+++ b/fs/hfs/catalog.c
@@ -214,7 +214,7 @@ int hfs_cat_delete(u32 cnid, struct inode *dir, struct qstr *str)
 {
 	struct super_block *sb;
 	struct hfs_find_data fd;
-	struct list_head *pos;
+	struct hfs_readdir_data *rd;
 	int res, type;
 
 	hfs_dbg(CAT_MOD, "delete_cat: %s,%u\n", str ? str->name : NULL, cnid);
@@ -240,9 +240,7 @@ int hfs_cat_delete(u32 cnid, struct inode *dir, struct qstr *str)
 		}
 	}
 
-	list_for_each(pos, &HFS_I(dir)->open_dir_list) {
-		struct hfs_readdir_data *rd =
-			list_entry(pos, struct hfs_readdir_data, list);
+	list_for_each_entry(rd, &HFS_I(dir)->open_dir_list, list) {
 		if (fd.tree->keycmp(fd.search_key, (void *)&rd->key) < 0)
 			rd->file->f_pos--;
 	}
diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c
index 70788e03820a..e9f2b855f831 100644
--- a/fs/hfs/dir.c
+++ b/fs/hfs/dir.c
@@ -173,9 +173,9 @@ static int hfs_dir_release(struct inode *inode, struct file *file)
 {
 	struct hfs_readdir_data *rd = file->private_data;
 	if (rd) {
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		list_del(&rd->list);
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 		kfree(rd);
 	}
 	return 0;
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index b99ebddb10cb..cb1e5faa2fb7 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -91,8 +91,8 @@ static int hfs_releasepage(struct page *page, gfp_t mask)
 	if (!tree)
 		return 0;
 
-	if (tree->node_size >= PAGE_CACHE_SIZE) {
-		nidx = page->index >> (tree->node_size_shift - PAGE_CACHE_SHIFT);
+	if (tree->node_size >= PAGE_SIZE) {
+		nidx = page->index >> (tree->node_size_shift - PAGE_SHIFT);
 		spin_lock(&tree->hash_lock);
 		node = hfs_bnode_findhash(tree, nidx);
 		if (!node)
@@ -105,8 +105,8 @@ static int hfs_releasepage(struct page *page, gfp_t mask)
 		}
 		spin_unlock(&tree->hash_lock);
 	} else {
-		nidx = page->index << (PAGE_CACHE_SHIFT - tree->node_size_shift);
-		i = 1 << (PAGE_CACHE_SHIFT - tree->node_size_shift);
+		nidx = page->index << (PAGE_SHIFT - tree->node_size_shift);
+		i = 1 << (PAGE_SHIFT - tree->node_size_shift);
 		spin_lock(&tree->hash_lock);
 		do {
 			node = hfs_bnode_findhash(tree, nidx++);
@@ -570,13 +570,13 @@ static int hfs_file_release(struct inode *inode, struct file *file)
 	if (HFS_IS_RSRC(inode))
 		inode = HFS_I(inode)->rsrc_inode;
 	if (atomic_dec_and_test(&HFS_I(inode)->opencnt)) {
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		hfs_file_truncate(inode);
 		//if (inode->i_flags & S_DEAD) {
 		//	hfs_delete_cat(inode->i_ino, HFSPLUS_SB(sb).hidden_dir, NULL);
 		//	hfs_delete_inode(inode);
 		//}
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 	}
 	return 0;
 }
@@ -656,7 +656,7 @@ static int hfs_file_fsync(struct file *filp, loff_t start, loff_t end,
 	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
 	if (ret)
 		return ret;
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	/* sync the inode to buffers */
 	ret = write_inode_now(inode, 0);
@@ -668,7 +668,7 @@ static int hfs_file_fsync(struct file *filp, loff_t start, loff_t end,
 	err = sync_blockdev(sb->s_bdev);
 	if (!ret)
 		ret = err;
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return ret;
 }
 
diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c
index aa3f0d6d043c..a3ec3ae7d347 100644
--- a/fs/hfs/mdb.c
+++ b/fs/hfs/mdb.c
@@ -166,7 +166,7 @@ int hfs_mdb_get(struct super_block *sb)
 		pr_warn("continuing without an alternate MDB\n");
 	}
 
-	HFS_SB(sb)->bitmap = (__be32 *)__get_free_pages(GFP_KERNEL, PAGE_SIZE < 8192 ? 1 : 0);
+	HFS_SB(sb)->bitmap = kmalloc(8192, GFP_KERNEL);
 	if (!HFS_SB(sb)->bitmap)
 		goto out;
 
@@ -360,7 +360,7 @@ void hfs_mdb_put(struct super_block *sb)
 	unload_nls(HFS_SB(sb)->nls_io);
 	unload_nls(HFS_SB(sb)->nls_disk);
 
-	free_pages((unsigned long)HFS_SB(sb)->bitmap, PAGE_SIZE < 8192 ? 1 : 0);
+	kfree(HFS_SB(sb)->bitmap);
 	kfree(HFS_SB(sb));
 	sb->s_fs_info = NULL;
 }
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index 4574fdd3d421..1ca95c232bb5 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -483,8 +483,8 @@ static int __init init_hfs_fs(void)
 	int err;
 
 	hfs_inode_cachep = kmem_cache_create("hfs_inode_cache",
-		sizeof(struct hfs_inode_info), 0, SLAB_HWCACHE_ALIGN,
-		hfs_init_once);
+		sizeof(struct hfs_inode_info), 0,
+		SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT, hfs_init_once);
 	if (!hfs_inode_cachep)
 		return -ENOMEM;
 	err = register_filesystem(&hfs_fs_type);
diff --git a/fs/hfsplus/bitmap.c b/fs/hfsplus/bitmap.c
index d2954451519e..c0ae274c0a22 100644
--- a/fs/hfsplus/bitmap.c
+++ b/fs/hfsplus/bitmap.c
@@ -13,7 +13,7 @@
 #include "hfsplus_fs.h"
 #include "hfsplus_raw.h"
 
-#define PAGE_CACHE_BITS	(PAGE_CACHE_SIZE * 8)
+#define PAGE_CACHE_BITS	(PAGE_SIZE * 8)
 
 int hfsplus_block_allocate(struct super_block *sb, u32 size,
 		u32 offset, u32 *max)
diff --git a/fs/hfsplus/bnode.c b/fs/hfsplus/bnode.c
index 63924662aaf3..ce014ceb89ef 100644
--- a/fs/hfsplus/bnode.c
+++ b/fs/hfsplus/bnode.c
@@ -24,16 +24,16 @@ void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len)
 	int l;
 
 	off += node->page_offset;
-	pagep = node->page + (off >> PAGE_CACHE_SHIFT);
-	off &= ~PAGE_CACHE_MASK;
+	pagep = node->page + (off >> PAGE_SHIFT);
+	off &= ~PAGE_MASK;
 
-	l = min_t(int, len, PAGE_CACHE_SIZE - off);
+	l = min_t(int, len, PAGE_SIZE - off);
 	memcpy(buf, kmap(*pagep) + off, l);
 	kunmap(*pagep);
 
 	while ((len -= l) != 0) {
 		buf += l;
-		l = min_t(int, len, PAGE_CACHE_SIZE);
+		l = min_t(int, len, PAGE_SIZE);
 		memcpy(buf, kmap(*++pagep), l);
 		kunmap(*pagep);
 	}
@@ -77,17 +77,17 @@ void hfs_bnode_write(struct hfs_bnode *node, void *buf, int off, int len)
 	int l;
 
 	off += node->page_offset;
-	pagep = node->page + (off >> PAGE_CACHE_SHIFT);
-	off &= ~PAGE_CACHE_MASK;
+	pagep = node->page + (off >> PAGE_SHIFT);
+	off &= ~PAGE_MASK;
 
-	l = min_t(int, len, PAGE_CACHE_SIZE - off);
+	l = min_t(int, len, PAGE_SIZE - off);
 	memcpy(kmap(*pagep) + off, buf, l);
 	set_page_dirty(*pagep);
 	kunmap(*pagep);
 
 	while ((len -= l) != 0) {
 		buf += l;
-		l = min_t(int, len, PAGE_CACHE_SIZE);
+		l = min_t(int, len, PAGE_SIZE);
 		memcpy(kmap(*++pagep), buf, l);
 		set_page_dirty(*pagep);
 		kunmap(*pagep);
@@ -107,16 +107,16 @@ void hfs_bnode_clear(struct hfs_bnode *node, int off, int len)
 	int l;
 
 	off += node->page_offset;
-	pagep = node->page + (off >> PAGE_CACHE_SHIFT);
-	off &= ~PAGE_CACHE_MASK;
+	pagep = node->page + (off >> PAGE_SHIFT);
+	off &= ~PAGE_MASK;
 
-	l = min_t(int, len, PAGE_CACHE_SIZE - off);
+	l = min_t(int, len, PAGE_SIZE - off);
 	memset(kmap(*pagep) + off, 0, l);
 	set_page_dirty(*pagep);
 	kunmap(*pagep);
 
 	while ((len -= l) != 0) {
-		l = min_t(int, len, PAGE_CACHE_SIZE);
+		l = min_t(int, len, PAGE_SIZE);
 		memset(kmap(*++pagep), 0, l);
 		set_page_dirty(*pagep);
 		kunmap(*pagep);
@@ -136,20 +136,20 @@ void hfs_bnode_copy(struct hfs_bnode *dst_node, int dst,
 	tree = src_node->tree;
 	src += src_node->page_offset;
 	dst += dst_node->page_offset;
-	src_page = src_node->page + (src >> PAGE_CACHE_SHIFT);
-	src &= ~PAGE_CACHE_MASK;
-	dst_page = dst_node->page + (dst >> PAGE_CACHE_SHIFT);
-	dst &= ~PAGE_CACHE_MASK;
+	src_page = src_node->page + (src >> PAGE_SHIFT);
+	src &= ~PAGE_MASK;
+	dst_page = dst_node->page + (dst >> PAGE_SHIFT);
+	dst &= ~PAGE_MASK;
 
 	if (src == dst) {
-		l = min_t(int, len, PAGE_CACHE_SIZE - src);
+		l = min_t(int, len, PAGE_SIZE - src);
 		memcpy(kmap(*dst_page) + src, kmap(*src_page) + src, l);
 		kunmap(*src_page);
 		set_page_dirty(*dst_page);
 		kunmap(*dst_page);
 
 		while ((len -= l) != 0) {
-			l = min_t(int, len, PAGE_CACHE_SIZE);
+			l = min_t(int, len, PAGE_SIZE);
 			memcpy(kmap(*++dst_page), kmap(*++src_page), l);
 			kunmap(*src_page);
 			set_page_dirty(*dst_page);
@@ -161,12 +161,12 @@ void hfs_bnode_copy(struct hfs_bnode *dst_node, int dst,
 		do {
 			src_ptr = kmap(*src_page) + src;
 			dst_ptr = kmap(*dst_page) + dst;
-			if (PAGE_CACHE_SIZE - src < PAGE_CACHE_SIZE - dst) {
-				l = PAGE_CACHE_SIZE - src;
+			if (PAGE_SIZE - src < PAGE_SIZE - dst) {
+				l = PAGE_SIZE - src;
 				src = 0;
 				dst += l;
 			} else {
-				l = PAGE_CACHE_SIZE - dst;
+				l = PAGE_SIZE - dst;
 				src += l;
 				dst = 0;
 			}
@@ -195,11 +195,11 @@ void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len)
 	dst += node->page_offset;
 	if (dst > src) {
 		src += len - 1;
-		src_page = node->page + (src >> PAGE_CACHE_SHIFT);
-		src = (src & ~PAGE_CACHE_MASK) + 1;
+		src_page = node->page + (src >> PAGE_SHIFT);
+		src = (src & ~PAGE_MASK) + 1;
 		dst += len - 1;
-		dst_page = node->page + (dst >> PAGE_CACHE_SHIFT);
-		dst = (dst & ~PAGE_CACHE_MASK) + 1;
+		dst_page = node->page + (dst >> PAGE_SHIFT);
+		dst = (dst & ~PAGE_MASK) + 1;
 
 		if (src == dst) {
 			while (src < len) {
@@ -208,7 +208,7 @@ void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len)
 				set_page_dirty(*dst_page);
 				kunmap(*dst_page);
 				len -= src;
-				src = PAGE_CACHE_SIZE;
+				src = PAGE_SIZE;
 				src_page--;
 				dst_page--;
 			}
@@ -226,32 +226,32 @@ void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len)
 				dst_ptr = kmap(*dst_page) + dst;
 				if (src < dst) {
 					l = src;
-					src = PAGE_CACHE_SIZE;
+					src = PAGE_SIZE;
 					dst -= l;
 				} else {
 					l = dst;
 					src -= l;
-					dst = PAGE_CACHE_SIZE;
+					dst = PAGE_SIZE;
 				}
 				l = min(len, l);
 				memmove(dst_ptr - l, src_ptr - l, l);
 				kunmap(*src_page);
 				set_page_dirty(*dst_page);
 				kunmap(*dst_page);
-				if (dst == PAGE_CACHE_SIZE)
+				if (dst == PAGE_SIZE)
 					dst_page--;
 				else
 					src_page--;
 			} while ((len -= l));
 		}
 	} else {
-		src_page = node->page + (src >> PAGE_CACHE_SHIFT);
-		src &= ~PAGE_CACHE_MASK;
-		dst_page = node->page + (dst >> PAGE_CACHE_SHIFT);
-		dst &= ~PAGE_CACHE_MASK;
+		src_page = node->page + (src >> PAGE_SHIFT);
+		src &= ~PAGE_MASK;
+		dst_page = node->page + (dst >> PAGE_SHIFT);
+		dst &= ~PAGE_MASK;
 
 		if (src == dst) {
-			l = min_t(int, len, PAGE_CACHE_SIZE - src);
+			l = min_t(int, len, PAGE_SIZE - src);
 			memmove(kmap(*dst_page) + src,
 				kmap(*src_page) + src, l);
 			kunmap(*src_page);
@@ -259,7 +259,7 @@ void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len)
 			kunmap(*dst_page);
 
 			while ((len -= l) != 0) {
-				l = min_t(int, len, PAGE_CACHE_SIZE);
+				l = min_t(int, len, PAGE_SIZE);
 				memmove(kmap(*++dst_page),
 					kmap(*++src_page), l);
 				kunmap(*src_page);
@@ -272,13 +272,13 @@ void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len)
 			do {
 				src_ptr = kmap(*src_page) + src;
 				dst_ptr = kmap(*dst_page) + dst;
-				if (PAGE_CACHE_SIZE - src <
-						PAGE_CACHE_SIZE - dst) {
-					l = PAGE_CACHE_SIZE - src;
+				if (PAGE_SIZE - src <
+						PAGE_SIZE - dst) {
+					l = PAGE_SIZE - src;
 					src = 0;
 					dst += l;
 				} else {
-					l = PAGE_CACHE_SIZE - dst;
+					l = PAGE_SIZE - dst;
 					src += l;
 					dst = 0;
 				}
@@ -444,14 +444,14 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid)
 
 	mapping = tree->inode->i_mapping;
 	off = (loff_t)cnid << tree->node_size_shift;
-	block = off >> PAGE_CACHE_SHIFT;
-	node->page_offset = off & ~PAGE_CACHE_MASK;
+	block = off >> PAGE_SHIFT;
+	node->page_offset = off & ~PAGE_MASK;
 	for (i = 0; i < tree->pages_per_bnode; block++, i++) {
 		page = read_mapping_page(mapping, block, NULL);
 		if (IS_ERR(page))
 			goto fail;
 		if (PageError(page)) {
-			page_cache_release(page);
+			put_page(page);
 			goto fail;
 		}
 		node->page[i] = page;
@@ -569,7 +569,7 @@ void hfs_bnode_free(struct hfs_bnode *node)
 
 	for (i = 0; i < node->tree->pages_per_bnode; i++)
 		if (node->page[i])
-			page_cache_release(node->page[i]);
+			put_page(node->page[i]);
 	kfree(node);
 }
 
@@ -597,11 +597,11 @@ struct hfs_bnode *hfs_bnode_create(struct hfs_btree *tree, u32 num)
 
 	pagep = node->page;
 	memset(kmap(*pagep) + node->page_offset, 0,
-	       min_t(int, PAGE_CACHE_SIZE, tree->node_size));
+	       min_t(int, PAGE_SIZE, tree->node_size));
 	set_page_dirty(*pagep);
 	kunmap(*pagep);
 	for (i = 1; i < tree->pages_per_bnode; i++) {
-		memset(kmap(*++pagep), 0, PAGE_CACHE_SIZE);
+		memset(kmap(*++pagep), 0, PAGE_SIZE);
 		set_page_dirty(*pagep);
 		kunmap(*pagep);
 	}
diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c
index 3345c7553edc..d9d1a36ba826 100644
--- a/fs/hfsplus/btree.c
+++ b/fs/hfsplus/btree.c
@@ -236,15 +236,15 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id)
 	tree->node_size_shift = ffs(size) - 1;
 
 	tree->pages_per_bnode =
-		(tree->node_size + PAGE_CACHE_SIZE - 1) >>
-		PAGE_CACHE_SHIFT;
+		(tree->node_size + PAGE_SIZE - 1) >>
+		PAGE_SHIFT;
 
 	kunmap(page);
-	page_cache_release(page);
+	put_page(page);
 	return tree;
 
  fail_page:
-	page_cache_release(page);
+	put_page(page);
  free_inode:
 	tree->inode->i_mapping->a_ops = &hfsplus_aops;
 	iput(tree->inode);
@@ -380,9 +380,9 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree)
 	off = off16;
 
 	off += node->page_offset;
-	pagep = node->page + (off >> PAGE_CACHE_SHIFT);
+	pagep = node->page + (off >> PAGE_SHIFT);
 	data = kmap(*pagep);
-	off &= ~PAGE_CACHE_MASK;
+	off &= ~PAGE_MASK;
 	idx = 0;
 
 	for (;;) {
@@ -403,7 +403,7 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree)
 					}
 				}
 			}
-			if (++off >= PAGE_CACHE_SIZE) {
+			if (++off >= PAGE_SIZE) {
 				kunmap(*pagep);
 				data = kmap(*++pagep);
 				off = 0;
@@ -426,9 +426,9 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree)
 		len = hfs_brec_lenoff(node, 0, &off16);
 		off = off16;
 		off += node->page_offset;
-		pagep = node->page + (off >> PAGE_CACHE_SHIFT);
+		pagep = node->page + (off >> PAGE_SHIFT);
 		data = kmap(*pagep);
-		off &= ~PAGE_CACHE_MASK;
+		off &= ~PAGE_MASK;
 	}
 }
 
@@ -475,9 +475,9 @@ void hfs_bmap_free(struct hfs_bnode *node)
 		len = hfs_brec_lenoff(node, 0, &off);
 	}
 	off += node->page_offset + nidx / 8;
-	page = node->page[off >> PAGE_CACHE_SHIFT];
+	page = node->page[off >> PAGE_SHIFT];
 	data = kmap(page);
-	off &= ~PAGE_CACHE_MASK;
+	off &= ~PAGE_MASK;
 	m = 1 << (~nidx & 7);
 	byte = data[off];
 	if (!(byte & m)) {
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index d0f39dcbb58e..a4e867e08947 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -284,9 +284,9 @@ static int hfsplus_dir_release(struct inode *inode, struct file *file)
 {
 	struct hfsplus_readdir_data *rd = file->private_data;
 	if (rd) {
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		list_del(&rd->list);
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 		kfree(rd);
 	}
 	return 0;
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 6dd107d7421e..b28f39865c3a 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -87,9 +87,9 @@ static int hfsplus_releasepage(struct page *page, gfp_t mask)
 	}
 	if (!tree)
 		return 0;
-	if (tree->node_size >= PAGE_CACHE_SIZE) {
+	if (tree->node_size >= PAGE_SIZE) {
 		nidx = page->index >>
-			(tree->node_size_shift - PAGE_CACHE_SHIFT);
+			(tree->node_size_shift - PAGE_SHIFT);
 		spin_lock(&tree->hash_lock);
 		node = hfs_bnode_findhash(tree, nidx);
 		if (!node)
@@ -103,8 +103,8 @@ static int hfsplus_releasepage(struct page *page, gfp_t mask)
 		spin_unlock(&tree->hash_lock);
 	} else {
 		nidx = page->index <<
-			(PAGE_CACHE_SHIFT - tree->node_size_shift);
-		i = 1 << (PAGE_CACHE_SHIFT - tree->node_size_shift);
+			(PAGE_SHIFT - tree->node_size_shift);
+		i = 1 << (PAGE_SHIFT - tree->node_size_shift);
 		spin_lock(&tree->hash_lock);
 		do {
 			node = hfs_bnode_findhash(tree, nidx++);
@@ -229,14 +229,14 @@ static int hfsplus_file_release(struct inode *inode, struct file *file)
 	if (HFSPLUS_IS_RSRC(inode))
 		inode = HFSPLUS_I(inode)->rsrc_inode;
 	if (atomic_dec_and_test(&HFSPLUS_I(inode)->opencnt)) {
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		hfsplus_file_truncate(inode);
 		if (inode->i_flags & S_DEAD) {
 			hfsplus_delete_cat(inode->i_ino,
 					   HFSPLUS_SB(sb)->hidden_dir, NULL);
 			hfsplus_delete_inode(inode);
 		}
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 	}
 	return 0;
 }
@@ -286,7 +286,7 @@ int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end,
 	error = filemap_write_and_wait_range(inode->i_mapping, start, end);
 	if (error)
 		return error;
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	/*
 	 * Sync inode metadata into the catalog and extent trees.
@@ -327,7 +327,7 @@ int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end,
 	if (!test_bit(HFSPLUS_SB_NOBARRIER, &sbi->flags))
 		blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
 
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	return error;
 }
@@ -403,6 +403,7 @@ struct inode *hfsplus_new_inode(struct super_block *sb, umode_t mode)
 	} else if (S_ISLNK(inode->i_mode)) {
 		sbi->file_count++;
 		inode->i_op = &page_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &hfsplus_aops;
 		hip->clump_blocks = 1;
 	} else
@@ -526,6 +527,7 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd)
 			inode->i_mapping->a_ops = &hfsplus_aops;
 		} else if (S_ISLNK(inode->i_mode)) {
 			inode->i_op = &page_symlink_inode_operations;
+			inode_nohighmem(inode);
 			inode->i_mapping->a_ops = &hfsplus_aops;
 		} else {
 			init_special_inode(inode, inode->i_mode,
diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c
index 0624ce4e0702..32a49e292b6a 100644
--- a/fs/hfsplus/ioctl.c
+++ b/fs/hfsplus/ioctl.c
@@ -93,7 +93,7 @@ static int hfsplus_ioctl_setflags(struct file *file, int __user *user_flags)
 		goto out_drop_write;
 	}
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	if ((flags & (FS_IMMUTABLE_FL|FS_APPEND_FL)) ||
 	    inode->i_flags & (S_IMMUTABLE|S_APPEND)) {
@@ -126,7 +126,7 @@ static int hfsplus_ioctl_setflags(struct file *file, int __user *user_flags)
 	mark_inode_dirty(inode);
 
 out_unlock_inode:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 out_drop_write:
 	mnt_drop_write_file(file);
 out:
diff --git a/fs/hfsplus/posix_acl.c b/fs/hfsplus/posix_acl.c
index df0c9af68d05..afb33eda6d7d 100644
--- a/fs/hfsplus/posix_acl.c
+++ b/fs/hfsplus/posix_acl.c
@@ -21,10 +21,10 @@ struct posix_acl *hfsplus_get_posix_acl(struct inode *inode, int type)
 
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		xattr_name = POSIX_ACL_XATTR_ACCESS;
+		xattr_name = XATTR_NAME_POSIX_ACL_ACCESS;
 		break;
 	case ACL_TYPE_DEFAULT:
-		xattr_name = POSIX_ACL_XATTR_DEFAULT;
+		xattr_name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		break;
 	default:
 		return ERR_PTR(-EINVAL);
@@ -66,7 +66,7 @@ int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl,
 
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		xattr_name = POSIX_ACL_XATTR_ACCESS;
+		xattr_name = XATTR_NAME_POSIX_ACL_ACCESS;
 		if (acl) {
 			err = posix_acl_equiv_mode(acl, &inode->i_mode);
 			if (err < 0)
@@ -76,7 +76,7 @@ int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl,
 		break;
 
 	case ACL_TYPE_DEFAULT:
-		xattr_name = POSIX_ACL_XATTR_DEFAULT;
+		xattr_name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		if (!S_ISDIR(inode->i_mode))
 			return acl ? -EACCES : 0;
 		break;
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 7302d96ae8bf..c35911362ff9 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -438,7 +438,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 	err = -EFBIG;
 	last_fs_block = sbi->total_blocks - 1;
 	last_fs_page = (last_fs_block << sbi->alloc_blksz_shift) >>
-			PAGE_CACHE_SHIFT;
+			PAGE_SHIFT;
 
 	if ((last_fs_block > (sector_t)(~0ULL) >> (sbi->alloc_blksz_shift - 9)) ||
 	    (last_fs_page > (pgoff_t)(~0ULL))) {
@@ -663,7 +663,7 @@ static int __init init_hfsplus_fs(void)
 	int err;
 
 	hfsplus_inode_cachep = kmem_cache_create("hfsplus_icache",
-		HFSPLUS_INODE_SIZE, 0, SLAB_HWCACHE_ALIGN,
+		HFSPLUS_INODE_SIZE, 0, SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT,
 		hfsplus_init_once);
 	if (!hfsplus_inode_cachep)
 		return -ENOMEM;
diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c
index 416b1dbafe51..70e445ff0cff 100644
--- a/fs/hfsplus/xattr.c
+++ b/fs/hfsplus/xattr.c
@@ -220,7 +220,7 @@ check_attr_tree_state_again:
 
 	index = 0;
 	written = 0;
-	for (; written < node_size; index++, written += PAGE_CACHE_SIZE) {
+	for (; written < node_size; index++, written += PAGE_SIZE) {
 		void *kaddr;
 
 		page = read_mapping_page(mapping, index, NULL);
@@ -231,11 +231,11 @@ check_attr_tree_state_again:
 
 		kaddr = kmap_atomic(page);
 		memcpy(kaddr, buf + written,
-			min_t(size_t, PAGE_CACHE_SIZE, node_size - written));
+			min_t(size_t, PAGE_SIZE, node_size - written));
 		kunmap_atomic(kaddr);
 
 		set_page_dirty(page);
-		page_cache_release(page);
+		put_page(page);
 	}
 
 	hfsplus_mark_inode_dirty(attr_file, HFSPLUS_I_ATTR_DIRTY);
@@ -431,9 +431,6 @@ int hfsplus_setxattr(struct dentry *dentry, const char *name,
 	char *xattr_name;
 	int res;
 
-	if (!strcmp(name, ""))
-		return -EINVAL;
-
 	xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1,
 		GFP_KERNEL);
 	if (!xattr_name)
@@ -589,9 +586,6 @@ ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name,
 	int res;
 	char *xattr_name;
 
-	if (!strcmp(name, ""))
-		return -EINVAL;
-
 	xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1,
 			     GFP_KERNEL);
 	if (!xattr_name)
@@ -849,12 +843,10 @@ end_removexattr:
 	return err;
 }
 
-static int hfsplus_osx_getxattr(struct dentry *dentry, const char *name,
-					void *buffer, size_t size, int type)
+static int hfsplus_osx_getxattr(const struct xattr_handler *handler,
+				struct dentry *dentry, const char *name,
+				void *buffer, size_t size)
 {
-	if (!strcmp(name, ""))
-		return -EINVAL;
-
 	/*
 	 * Don't allow retrieving properly prefixed attributes
 	 * by prepending them with "osx."
@@ -871,12 +863,10 @@ static int hfsplus_osx_getxattr(struct dentry *dentry, const char *name,
 	return __hfsplus_getxattr(d_inode(dentry), name, buffer, size);
 }
 
-static int hfsplus_osx_setxattr(struct dentry *dentry, const char *name,
-		const void *buffer, size_t size, int flags, int type)
+static int hfsplus_osx_setxattr(const struct xattr_handler *handler,
+				struct dentry *dentry, const char *name,
+				const void *buffer, size_t size, int flags)
 {
-	if (!strcmp(name, ""))
-		return -EINVAL;
-
 	/*
 	 * Don't allow setting properly prefixed attributes
 	 * by prepending them with "osx."
@@ -893,19 +883,8 @@ static int hfsplus_osx_setxattr(struct dentry *dentry, const char *name,
 	return __hfsplus_setxattr(d_inode(dentry), name, buffer, size, flags);
 }
 
-static size_t hfsplus_osx_listxattr(struct dentry *dentry, char *list,
-		size_t list_size, const char *name, size_t name_len, int type)
-{
-	/*
-	 * This method is not used.
-	 * It is used hfsplus_listxattr() instead of generic_listxattr().
-	 */
-	return -EOPNOTSUPP;
-}
-
 const struct xattr_handler hfsplus_xattr_osx_handler = {
 	.prefix	= XATTR_MAC_OSX_PREFIX,
-	.list	= hfsplus_osx_listxattr,
 	.get	= hfsplus_osx_getxattr,
 	.set	= hfsplus_osx_setxattr,
 };
diff --git a/fs/hfsplus/xattr_security.c b/fs/hfsplus/xattr_security.c
index aacff00a9ff9..72a68a3a0c99 100644
--- a/fs/hfsplus/xattr_security.c
+++ b/fs/hfsplus/xattr_security.c
@@ -13,32 +13,24 @@
 #include "xattr.h"
 #include "acl.h"
 
-static int hfsplus_security_getxattr(struct dentry *dentry, const char *name,
-					void *buffer, size_t size, int type)
+static int hfsplus_security_getxattr(const struct xattr_handler *handler,
+				     struct dentry *dentry, const char *name,
+				     void *buffer, size_t size)
 {
 	return hfsplus_getxattr(dentry, name, buffer, size,
 				XATTR_SECURITY_PREFIX,
 				XATTR_SECURITY_PREFIX_LEN);
 }
 
-static int hfsplus_security_setxattr(struct dentry *dentry, const char *name,
-		const void *buffer, size_t size, int flags, int type)
+static int hfsplus_security_setxattr(const struct xattr_handler *handler,
+				     struct dentry *dentry, const char *name,
+				     const void *buffer, size_t size, int flags)
 {
 	return hfsplus_setxattr(dentry, name, buffer, size, flags,
 				XATTR_SECURITY_PREFIX,
 				XATTR_SECURITY_PREFIX_LEN);
 }
 
-static size_t hfsplus_security_listxattr(struct dentry *dentry, char *list,
-		size_t list_size, const char *name, size_t name_len, int type)
-{
-	/*
-	 * This method is not used.
-	 * It is used hfsplus_listxattr() instead of generic_listxattr().
-	 */
-	return -EOPNOTSUPP;
-}
-
 static int hfsplus_initxattrs(struct inode *inode,
 				const struct xattr *xattr_array,
 				void *fs_info)
@@ -92,7 +84,6 @@ int hfsplus_init_inode_security(struct inode *inode,
 
 const struct xattr_handler hfsplus_xattr_security_handler = {
 	.prefix	= XATTR_SECURITY_PREFIX,
-	.list	= hfsplus_security_listxattr,
 	.get	= hfsplus_security_getxattr,
 	.set	= hfsplus_security_setxattr,
 };
diff --git a/fs/hfsplus/xattr_trusted.c b/fs/hfsplus/xattr_trusted.c
index bcf65089b7f7..95a7704c7abb 100644
--- a/fs/hfsplus/xattr_trusted.c
+++ b/fs/hfsplus/xattr_trusted.c
@@ -11,34 +11,25 @@
 #include "hfsplus_fs.h"
 #include "xattr.h"
 
-static int hfsplus_trusted_getxattr(struct dentry *dentry, const char *name,
-					void *buffer, size_t size, int type)
+static int hfsplus_trusted_getxattr(const struct xattr_handler *handler,
+				    struct dentry *dentry, const char *name,
+				    void *buffer, size_t size)
 {
 	return hfsplus_getxattr(dentry, name, buffer, size,
 				XATTR_TRUSTED_PREFIX,
 				XATTR_TRUSTED_PREFIX_LEN);
 }
 
-static int hfsplus_trusted_setxattr(struct dentry *dentry, const char *name,
-		const void *buffer, size_t size, int flags, int type)
+static int hfsplus_trusted_setxattr(const struct xattr_handler *handler,
+				    struct dentry *dentry, const char *name,
+				    const void *buffer, size_t size, int flags)
 {
 	return hfsplus_setxattr(dentry, name, buffer, size, flags,
 				XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN);
 }
 
-static size_t hfsplus_trusted_listxattr(struct dentry *dentry, char *list,
-		size_t list_size, const char *name, size_t name_len, int type)
-{
-	/*
-	 * This method is not used.
-	 * It is used hfsplus_listxattr() instead of generic_listxattr().
-	 */
-	return -EOPNOTSUPP;
-}
-
 const struct xattr_handler hfsplus_xattr_trusted_handler = {
 	.prefix	= XATTR_TRUSTED_PREFIX,
-	.list	= hfsplus_trusted_listxattr,
 	.get	= hfsplus_trusted_getxattr,
 	.set	= hfsplus_trusted_setxattr,
 };
diff --git a/fs/hfsplus/xattr_user.c b/fs/hfsplus/xattr_user.c
index 5aa0e6dc4a1e..6fc269baf959 100644
--- a/fs/hfsplus/xattr_user.c
+++ b/fs/hfsplus/xattr_user.c
@@ -11,34 +11,25 @@
 #include "hfsplus_fs.h"
 #include "xattr.h"
 
-static int hfsplus_user_getxattr(struct dentry *dentry, const char *name,
-					void *buffer, size_t size, int type)
+static int hfsplus_user_getxattr(const struct xattr_handler *handler,
+				 struct dentry *dentry, const char *name,
+				 void *buffer, size_t size)
 {
 
 	return hfsplus_getxattr(dentry, name, buffer, size,
 				XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN);
 }
 
-static int hfsplus_user_setxattr(struct dentry *dentry, const char *name,
-		const void *buffer, size_t size, int flags, int type)
+static int hfsplus_user_setxattr(const struct xattr_handler *handler,
+				 struct dentry *dentry, const char *name,
+				 const void *buffer, size_t size, int flags)
 {
 	return hfsplus_setxattr(dentry, name, buffer, size, flags,
 				XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN);
 }
 
-static size_t hfsplus_user_listxattr(struct dentry *dentry, char *list,
-		size_t list_size, const char *name, size_t name_len, int type)
-{
-	/*
-	 * This method is not used.
-	 * It is used hfsplus_listxattr() instead of generic_listxattr().
-	 */
-	return -EOPNOTSUPP;
-}
-
 const struct xattr_handler hfsplus_xattr_user_handler = {
 	.prefix	= XATTR_USER_PREFIX,
-	.list	= hfsplus_user_listxattr,
 	.get	= hfsplus_user_getxattr,
 	.set	= hfsplus_user_setxattr,
 };
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 2ac99db3750e..7016653f3e41 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -223,7 +223,7 @@ static struct inode *hostfs_alloc_inode(struct super_block *sb)
 {
 	struct hostfs_inode_info *hi;
 
-	hi = kmalloc(sizeof(*hi), GFP_KERNEL);
+	hi = kmalloc(sizeof(*hi), GFP_KERNEL_ACCOUNT);
 	if (hi == NULL)
 		return NULL;
 	hi->fd = -1;
@@ -378,9 +378,9 @@ static int hostfs_fsync(struct file *file, loff_t start, loff_t end,
 	if (ret)
 		return ret;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	ret = fsync_file(HOSTFS_I(inode)->fd, datasync);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	return ret;
 }
@@ -410,12 +410,12 @@ static int hostfs_writepage(struct page *page, struct writeback_control *wbc)
 	struct inode *inode = mapping->host;
 	char *buffer;
 	loff_t base = page_offset(page);
-	int count = PAGE_CACHE_SIZE;
-	int end_index = inode->i_size >> PAGE_CACHE_SHIFT;
+	int count = PAGE_SIZE;
+	int end_index = inode->i_size >> PAGE_SHIFT;
 	int err;
 
 	if (page->index >= end_index)
-		count = inode->i_size & (PAGE_CACHE_SIZE-1);
+		count = inode->i_size & (PAGE_SIZE-1);
 
 	buffer = kmap(page);
 
@@ -447,7 +447,7 @@ static int hostfs_readpage(struct file *file, struct page *page)
 
 	buffer = kmap(page);
 	bytes_read = read_file(FILE_HOSTFS_I(file)->fd, &start, buffer,
-			PAGE_CACHE_SIZE);
+			PAGE_SIZE);
 	if (bytes_read < 0) {
 		ClearPageUptodate(page);
 		SetPageError(page);
@@ -455,7 +455,7 @@ static int hostfs_readpage(struct file *file, struct page *page)
 		goto out;
 	}
 
-	memset(buffer + bytes_read, 0, PAGE_CACHE_SIZE - bytes_read);
+	memset(buffer + bytes_read, 0, PAGE_SIZE - bytes_read);
 
 	ClearPageError(page);
 	SetPageUptodate(page);
@@ -471,7 +471,7 @@ static int hostfs_write_begin(struct file *file, struct address_space *mapping,
 			      loff_t pos, unsigned len, unsigned flags,
 			      struct page **pagep, void **fsdata)
 {
-	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+	pgoff_t index = pos >> PAGE_SHIFT;
 
 	*pagep = grab_cache_page_write_begin(mapping, index, flags);
 	if (!*pagep)
@@ -485,14 +485,14 @@ static int hostfs_write_end(struct file *file, struct address_space *mapping,
 {
 	struct inode *inode = mapping->host;
 	void *buffer;
-	unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+	unsigned from = pos & (PAGE_SIZE - 1);
 	int err;
 
 	buffer = kmap(page);
 	err = write_file(FILE_HOSTFS_I(file)->fd, &pos, buffer + from, copied);
 	kunmap(page);
 
-	if (!PageUptodate(page) && err == PAGE_CACHE_SIZE)
+	if (!PageUptodate(page) && err == PAGE_SIZE)
 		SetPageUptodate(page);
 
 	/*
@@ -502,7 +502,7 @@ static int hostfs_write_end(struct file *file, struct address_space *mapping,
 	if (err > 0 && (pos > inode->i_size))
 		inode->i_size = pos;
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 
 	return err;
 }
@@ -730,15 +730,13 @@ static int hostfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
 
 	init_special_inode(inode, mode, dev);
 	err = do_mknod(name, mode, MAJOR(dev), MINOR(dev));
-	if (!err)
+	if (err)
 		goto out_free;
 
 	err = read_name(inode, name);
 	__putname(name);
 	if (err)
 		goto out_put;
-	if (err)
-		goto out_put;
 
 	d_instantiate(dentry, inode);
 	return 0;
@@ -892,9 +890,14 @@ static const struct inode_operations hostfs_dir_iops = {
 	.setattr	= hostfs_setattr,
 };
 
-static const char *hostfs_follow_link(struct dentry *dentry, void **cookie)
+static const char *hostfs_get_link(struct dentry *dentry,
+				   struct inode *inode,
+				   struct delayed_call *done)
 {
-	char *link = __getname();
+	char *link;
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+	link = kmalloc(PATH_MAX, GFP_KERNEL);
 	if (link) {
 		char *path = dentry_name(dentry);
 		int err = -ENOMEM;
@@ -905,25 +908,20 @@ static const char *hostfs_follow_link(struct dentry *dentry, void **cookie)
 			__putname(path);
 		}
 		if (err < 0) {
-			__putname(link);
+			kfree(link);
 			return ERR_PTR(err);
 		}
 	} else {
 		return ERR_PTR(-ENOMEM);
 	}
 
-	return *cookie = link;
-}
-
-static void hostfs_put_link(struct inode *unused, void *cookie)
-{
-	__putname(cookie);
+	set_delayed_call(done, kfree_link, link);
+	return link;
 }
 
 static const struct inode_operations hostfs_link_iops = {
 	.readlink	= generic_readlink,
-	.follow_link	= hostfs_follow_link,
-	.put_link	= hostfs_put_link,
+	.get_link	= hostfs_get_link,
 };
 
 static int hostfs_fill_sb_common(struct super_block *sb, void *d, int silent)
diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c
index dc540bfcee1d..e57a53c13d86 100644
--- a/fs/hpfs/dir.c
+++ b/fs/hpfs/dir.c
@@ -33,7 +33,7 @@ static loff_t hpfs_dir_lseek(struct file *filp, loff_t off, int whence)
 	if (whence == SEEK_DATA || whence == SEEK_HOLE)
 		return -EINVAL;
 
-	mutex_lock(&i->i_mutex);
+	inode_lock(i);
 	hpfs_lock(s);
 
 	/*pr_info("dir lseek\n");*/
@@ -48,12 +48,12 @@ static loff_t hpfs_dir_lseek(struct file *filp, loff_t off, int whence)
 ok:
 	filp->f_pos = new_off;
 	hpfs_unlock(s);
-	mutex_unlock(&i->i_mutex);
+	inode_unlock(i);
 	return new_off;
 fail:
 	/*pr_warn("illegal lseek: %016llx\n", new_off);*/
 	hpfs_unlock(s);
-	mutex_unlock(&i->i_mutex);
+	inode_unlock(i);
 	return -ESPIPE;
 }
 
diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c
index 933c73780813..1f3c6d76200b 100644
--- a/fs/hpfs/inode.c
+++ b/fs/hpfs/inode.c
@@ -77,6 +77,7 @@ void hpfs_read_inode(struct inode *i)
 			kfree(ea);
 			i->i_mode = S_IFLNK | 0777;
 			i->i_op = &page_symlink_inode_operations;
+			inode_nohighmem(i);
 			i->i_data.a_ops = &hpfs_symlink_aops;
 			set_nlink(i, 1);
 			i->i_size = ea_size;
diff --git a/fs/hpfs/map.c b/fs/hpfs/map.c
index a69bbc1e87f8..a136929189f0 100644
--- a/fs/hpfs/map.c
+++ b/fs/hpfs/map.c
@@ -133,7 +133,7 @@ __le32 *hpfs_load_bitmap_directory(struct super_block *s, secno bmp)
 void hpfs_load_hotfix_map(struct super_block *s, struct hpfs_spare_block *spareblock)
 {
 	struct quad_buffer_head qbh;
-	u32 *directory;
+	__le32 *directory;
 	u32 n_hotfixes, n_used_hotfixes;
 	unsigned i;
 
diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c
index 9e92c9c2d319..bb8d67e2740a 100644
--- a/fs/hpfs/namei.c
+++ b/fs/hpfs/namei.c
@@ -227,8 +227,6 @@ static int hpfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, de
 	int err;
 	if ((err = hpfs_chk_name(name, &len))) return err==-ENOENT ? -EINVAL : err;
 	if (hpfs_sb(dir->i_sb)->sb_eas < 2) return -EPERM;
-	if (!new_valid_dev(rdev))
-		return -EINVAL;
 	hpfs_lock(dir->i_sb);
 	err = -ENOSPC;
 	fnode = hpfs_alloc_fnode(dir->i_sb, hpfs_i(dir)->i_dno, &fno, &bh);
@@ -334,6 +332,7 @@ static int hpfs_symlink(struct inode *dir, struct dentry *dentry, const char *sy
 	result->i_blocks = 1;
 	set_nlink(result, 1);
 	result->i_size = strlen(symlink);
+	inode_nohighmem(result);
 	result->i_op = &page_symlink_inode_operations;
 	result->i_data.a_ops = &hpfs_symlink_aops;
 
@@ -377,12 +376,11 @@ static int hpfs_unlink(struct inode *dir, struct dentry *dentry)
 	struct inode *inode = d_inode(dentry);
 	dnode_secno dno;
 	int r;
-	int rep = 0;
 	int err;
 
 	hpfs_lock(dir->i_sb);
 	hpfs_adjust_length(name, &len);
-again:
+
 	err = -ENOENT;
 	de = map_dirent(dir, hpfs_i(dir)->i_dno, name, len, &dno, &qbh);
 	if (!de)
@@ -402,33 +400,9 @@ again:
 		hpfs_error(dir->i_sb, "there was error when removing dirent");
 		err = -EFSERROR;
 		break;
-	case 2:		/* no space for deleting, try to truncate file */
-
+	case 2:		/* no space for deleting */
 		err = -ENOSPC;
-		if (rep++)
-			break;
-
-		dentry_unhash(dentry);
-		if (!d_unhashed(dentry)) {
-			hpfs_unlock(dir->i_sb);
-			return -ENOSPC;
-		}
-		if (generic_permission(inode, MAY_WRITE) ||
-		    !S_ISREG(inode->i_mode) ||
-		    get_write_access(inode)) {
-			d_rehash(dentry);
-		} else {
-			struct iattr newattrs;
-			/*pr_info("truncating file before delete.\n");*/
-			newattrs.ia_size = 0;
-			newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME;
-			err = notify_change(dentry, &newattrs, NULL);
-			put_write_access(inode);
-			if (!err)
-				goto again;
-		}
-		hpfs_unlock(dir->i_sb);
-		return -ENOSPC;
+		break;
 	default:
 		drop_nlink(inode);
 		err = 0;
@@ -502,7 +476,7 @@ out:
 
 static int hpfs_symlink_readpage(struct file *file, struct page *page)
 {
-	char *link = kmap(page);
+	char *link = page_address(page);
 	struct inode *i = page->mapping->host;
 	struct fnode *fnode;
 	struct buffer_head *bh;
@@ -518,14 +492,12 @@ static int hpfs_symlink_readpage(struct file *file, struct page *page)
 		goto fail;
 	hpfs_unlock(i->i_sb);
 	SetPageUptodate(page);
-	kunmap(page);
 	unlock_page(page);
 	return 0;
 
 fail:
 	hpfs_unlock(i->i_sb);
 	SetPageError(page);
-	kunmap(page);
 	unlock_page(page);
 	return err;
 }
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index a561591896bd..458cf463047b 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -261,7 +261,7 @@ static int init_inodecache(void)
 	hpfs_inode_cachep = kmem_cache_create("hpfs_inode_cache",
 					     sizeof(struct hpfs_inode_info),
 					     0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD),
+						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
 					     init_once);
 	if (hpfs_inode_cachep == NULL)
 		return -ENOMEM;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 316adb968b65..4ea71eba40a5 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -4,11 +4,11 @@
  * Nadia Yvette Chambers, 2002
  *
  * Copyright (C) 2002 Linus Torvalds.
+ * License: GPL
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/module.h>
 #include <linux/thread_info.h>
 #include <asm/current.h>
 #include <linux/sched.h>		/* remove ASAP */
@@ -141,7 +141,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 
 	vma_len = (loff_t)(vma->vm_end - vma->vm_start);
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	file_accessed(file);
 
 	ret = -ENOMEM;
@@ -157,7 +157,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	if (vma->vm_flags & VM_WRITE && inode->i_size < len)
 		inode->i_size = len;
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	return ret;
 }
@@ -213,12 +213,12 @@ hugetlbfs_read_actor(struct page *page, unsigned long offset,
 	int i, chunksize;
 
 	/* Find which 4k chunk and offset with in that chunk */
-	i = offset >> PAGE_CACHE_SHIFT;
-	offset = offset & ~PAGE_CACHE_MASK;
+	i = offset >> PAGE_SHIFT;
+	offset = offset & ~PAGE_MASK;
 
 	while (size) {
 		size_t n;
-		chunksize = PAGE_CACHE_SIZE;
+		chunksize = PAGE_SIZE;
 		if (offset)
 			chunksize -= offset;
 		if (chunksize > size)
@@ -237,7 +237,7 @@ hugetlbfs_read_actor(struct page *page, unsigned long offset,
 /*
  * Support for read() - Find the page attached to f_mapping and copy out the
  * data. Its *very* similar to do_generic_mapping_read(), we can't use that
- * since it has PAGE_CACHE_SIZE assumptions.
+ * since it has PAGE_SIZE assumptions.
  */
 static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
@@ -285,7 +285,7 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 			 * We have the page, copy it to user space buffer.
 			 */
 			copied = hugetlbfs_read_actor(page, offset, to, nr);
-			page_cache_release(page);
+			put_page(page);
 		}
 		offset += copied;
 		retval += copied;
@@ -324,20 +324,62 @@ static void remove_huge_page(struct page *page)
 	delete_from_page_cache(page);
 }
 
+static void
+hugetlb_vmdelete_list(struct rb_root *root, pgoff_t start, pgoff_t end)
+{
+	struct vm_area_struct *vma;
+
+	/*
+	 * end == 0 indicates that the entire range after
+	 * start should be unmapped.
+	 */
+	vma_interval_tree_foreach(vma, root, start, end ? end : ULONG_MAX) {
+		unsigned long v_offset;
+		unsigned long v_end;
+
+		/*
+		 * Can the expression below overflow on 32-bit arches?
+		 * No, because the interval tree returns us only those vmas
+		 * which overlap the truncated area starting at pgoff,
+		 * and no vma on a 32-bit arch can span beyond the 4GB.
+		 */
+		if (vma->vm_pgoff < start)
+			v_offset = (start - vma->vm_pgoff) << PAGE_SHIFT;
+		else
+			v_offset = 0;
+
+		if (!end)
+			v_end = vma->vm_end;
+		else {
+			v_end = ((end - vma->vm_pgoff) << PAGE_SHIFT)
+							+ vma->vm_start;
+			if (v_end > vma->vm_end)
+				v_end = vma->vm_end;
+		}
+
+		unmap_hugepage_range(vma, vma->vm_start + v_offset, v_end,
+									NULL);
+	}
+}
 
 /*
  * remove_inode_hugepages handles two distinct cases: truncation and hole
  * punch.  There are subtle differences in operation for each case.
-
+ *
  * truncation is indicated by end of range being LLONG_MAX
  *	In this case, we first scan the range and release found pages.
  *	After releasing pages, hugetlb_unreserve_pages cleans up region/reserv
- *	maps and global counts.
+ *	maps and global counts.  Page faults can not race with truncation
+ *	in this routine.  hugetlb_no_page() prevents page faults in the
+ *	truncated range.  It checks i_size before allocation, and again after
+ *	with the page table lock for the page held.  The same lock must be
+ *	acquired to unmap a page.
  * hole punch is indicated if end is not LLONG_MAX
  *	In the hole punch case we scan the range and release found pages.
  *	Only when releasing a page is the associated region/reserv map
  *	deleted.  The region/reserv map for ranges without associated
- *	pages are not modified.
+ *	pages are not modified.  Page faults can race with hole punch.
+ *	This is indicated if we find a mapped page.
  * Note: If the passed end of range value is beyond the end of file, but
  * not LLONG_MAX this routine still performs a hole punch operation.
  */
@@ -361,77 +403,81 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 	next = start;
 	while (next < end) {
 		/*
-		 * Make sure to never grab more pages that we
-		 * might possibly need.
+		 * Don't grab more pages than the number left in the range.
 		 */
 		if (end - next < lookup_nr)
 			lookup_nr = end - next;
 
 		/*
-		 * This pagevec_lookup() may return pages past 'end',
-		 * so we must check for page->index > end.
+		 * When no more pages are found, we are done.
 		 */
-		if (!pagevec_lookup(&pvec, mapping, next, lookup_nr)) {
-			if (next == start)
-				break;
-			next = start;
-			continue;
-		}
+		if (!pagevec_lookup(&pvec, mapping, next, lookup_nr))
+			break;
 
 		for (i = 0; i < pagevec_count(&pvec); ++i) {
 			struct page *page = pvec.pages[i];
+			bool rsv_on_error;
 			u32 hash;
 
+			/*
+			 * The page (index) could be beyond end.  This is
+			 * only possible in the punch hole case as end is
+			 * max page offset in the truncate case.
+			 */
+			next = page->index;
+			if (next >= end)
+				break;
+
 			hash = hugetlb_fault_mutex_hash(h, current->mm,
 							&pseudo_vma,
 							mapping, next, 0);
 			mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
-			lock_page(page);
-			if (page->index >= end) {
-				unlock_page(page);
-				mutex_unlock(&hugetlb_fault_mutex_table[hash]);
-				next = end;	/* we are done */
-				break;
-			}
-
 			/*
 			 * If page is mapped, it was faulted in after being
-			 * unmapped.  Do nothing in this race case.  In the
-			 * normal case page is not mapped.
+			 * unmapped in caller.  Unmap (again) now after taking
+			 * the fault mutex.  The mutex will prevent faults
+			 * until we finish removing the page.
+			 *
+			 * This race can only happen in the hole punch case.
+			 * Getting here in a truncate operation is a bug.
 			 */
-			if (!page_mapped(page)) {
-				bool rsv_on_error = !PagePrivate(page);
-				/*
-				 * We must free the huge page and remove
-				 * from page cache (remove_huge_page) BEFORE
-				 * removing the region/reserve map
-				 * (hugetlb_unreserve_pages).  In rare out
-				 * of memory conditions, removal of the
-				 * region/reserve map could fail.  Before
-				 * free'ing the page, note PagePrivate which
-				 * is used in case of error.
-				 */
-				remove_huge_page(page);
-				freed++;
-				if (!truncate_op) {
-					if (unlikely(hugetlb_unreserve_pages(
-							inode, next,
-							next + 1, 1)))
-						hugetlb_fix_reserve_counts(
-							inode, rsv_on_error);
-				}
+			if (unlikely(page_mapped(page))) {
+				BUG_ON(truncate_op);
+
+				i_mmap_lock_write(mapping);
+				hugetlb_vmdelete_list(&mapping->i_mmap,
+					next * pages_per_huge_page(h),
+					(next + 1) * pages_per_huge_page(h));
+				i_mmap_unlock_write(mapping);
 			}
 
-			if (page->index > next)
-				next = page->index;
+			lock_page(page);
+			/*
+			 * We must free the huge page and remove from page
+			 * cache (remove_huge_page) BEFORE removing the
+			 * region/reserve map (hugetlb_unreserve_pages).  In
+			 * rare out of memory conditions, removal of the
+			 * region/reserve map could fail.  Before free'ing
+			 * the page, note PagePrivate which is used in case
+			 * of error.
+			 */
+			rsv_on_error = !PagePrivate(page);
+			remove_huge_page(page);
+			freed++;
+			if (!truncate_op) {
+				if (unlikely(hugetlb_unreserve_pages(inode,
+							next, next + 1, 1)))
+					hugetlb_fix_reserve_counts(inode,
+								rsv_on_error);
+			}
 
-			++next;
 			unlock_page(page);
-
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 		}
+		++next;
 		huge_pagevec_release(&pvec);
+		cond_resched();
 	}
 
 	if (truncate_op)
@@ -450,41 +496,6 @@ static void hugetlbfs_evict_inode(struct inode *inode)
 	clear_inode(inode);
 }
 
-static inline void
-hugetlb_vmdelete_list(struct rb_root *root, pgoff_t start, pgoff_t end)
-{
-	struct vm_area_struct *vma;
-
-	/*
-	 * end == 0 indicates that the entire range after
-	 * start should be unmapped.
-	 */
-	vma_interval_tree_foreach(vma, root, start, end ? end : ULONG_MAX) {
-		unsigned long v_offset;
-
-		/*
-		 * Can the expression below overflow on 32-bit arches?
-		 * No, because the interval tree returns us only those vmas
-		 * which overlap the truncated area starting at pgoff,
-		 * and no vma on a 32-bit arch can span beyond the 4GB.
-		 */
-		if (vma->vm_pgoff < start)
-			v_offset = (start - vma->vm_pgoff) << PAGE_SHIFT;
-		else
-			v_offset = 0;
-
-		if (end) {
-			end = ((end - start) << PAGE_SHIFT) +
-			       vma->vm_start + v_offset;
-			if (end > vma->vm_end)
-				end = vma->vm_end;
-		} else
-			end = vma->vm_end;
-
-		unmap_hugepage_range(vma, vma->vm_start + v_offset, end, NULL);
-	}
-}
-
 static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
 {
 	pgoff_t pgoff;
@@ -519,7 +530,7 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	if (hole_end > hole_start) {
 		struct address_space *mapping = inode->i_mapping;
 
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		i_mmap_lock_write(mapping);
 		if (!RB_EMPTY_ROOT(&mapping->i_mmap))
 			hugetlb_vmdelete_list(&mapping->i_mmap,
@@ -527,7 +538,7 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 						hole_end  >> PAGE_SHIFT);
 		i_mmap_unlock_write(mapping);
 		remove_inode_hugepages(inode, hole_start, hole_end);
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 	}
 
 	return 0;
@@ -561,7 +572,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 	start = offset >> hpage_shift;
 	end = (offset + len + hpage_size - 1) >> hpage_shift;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	/* We need to check rlimit even when FALLOC_FL_KEEP_SIZE */
 	error = inode_newsize_ok(inode, offset + len);
@@ -647,11 +658,8 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 	if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size)
 		i_size_write(inode, offset + len);
 	inode->i_ctime = CURRENT_TIME;
-	spin_lock(&inode->i_lock);
-	inode->i_private = NULL;
-	spin_unlock(&inode->i_lock);
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return error;
 }
 
@@ -709,7 +717,7 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb,
 /*
  * Hugetlbfs is not reclaimable; therefore its i_mmap_rwsem will never
  * be taken from reclaim -- unlike regular filesystems. This needs an
- * annotation because huge_pmd_share() does an allocation under
+ * annotation because huge_pmd_share() does an allocation under hugetlb's
  * i_mmap_rwsem.
  */
 static struct lock_class_key hugetlbfs_i_mmap_rwsem_key;
@@ -739,7 +747,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 		/*
 		 * The policy is initialized here even if we are creating a
 		 * private inode because initialization simply creates an
-		 * an empty rb tree and calls spin_lock_init(), later when we
+		 * an empty rb tree and calls rwlock_init(), later when we
 		 * call mpol_free_shared_policy() it will just return because
 		 * the rb tree will still be empty.
 		 */
@@ -761,6 +769,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 			break;
 		case S_IFLNK:
 			inode->i_op = &page_symlink_inode_operations;
+			inode_nohighmem(inode);
 			break;
 		}
 		lockdep_annotate_inode_mutex_key(inode);
@@ -1202,7 +1211,6 @@ static struct file_system_type hugetlbfs_fs_type = {
 	.mount		= hugetlbfs_mount,
 	.kill_sb	= kill_litter_super,
 };
-MODULE_ALIAS_FS("hugetlbfs");
 
 static struct vfsmount *hugetlbfs_vfsmount[HUGE_MAX_HSTATE];
 
@@ -1322,7 +1330,7 @@ static int __init init_hugetlbfs_fs(void)
 	error = -ENOMEM;
 	hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache",
 					sizeof(struct hugetlbfs_inode_info),
-					0, 0, init_once);
+					0, SLAB_ACCOUNT, init_once);
 	if (hugetlbfs_inode_cachep == NULL)
 		goto out2;
 
@@ -1356,26 +1364,4 @@ static int __init init_hugetlbfs_fs(void)
  out2:
 	return error;
 }
-
-static void __exit exit_hugetlbfs_fs(void)
-{
-	struct hstate *h;
-	int i;
-
-
-	/*
-	 * Make sure all delayed rcu free inodes are flushed before we
-	 * destroy cache.
-	 */
-	rcu_barrier();
-	kmem_cache_destroy(hugetlbfs_inode_cachep);
-	i = 0;
-	for_each_hstate(h)
-		kern_unmount(hugetlbfs_vfsmount[i++]);
-	unregister_filesystem(&hugetlbfs_fs_type);
-}
-
-module_init(init_hugetlbfs_fs)
-module_exit(exit_hugetlbfs_fs)
-
-MODULE_LICENSE("GPL");
+fs_initcall(init_hugetlbfs_fs)
diff --git a/fs/inode.c b/fs/inode.c
index 78a17b8859e1..69b8b526c194 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -154,6 +154,12 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	inode->i_rdev = 0;
 	inode->dirtied_when = 0;
 
+#ifdef CONFIG_CGROUP_WRITEBACK
+	inode->i_wb_frn_winner = 0;
+	inode->i_wb_frn_avg_time = 0;
+	inode->i_wb_frn_history = 0;
+#endif
+
 	if (security_inode_alloc(inode))
 		goto out;
 	spin_lock_init(&inode->i_lock);
@@ -225,7 +231,7 @@ void __destroy_inode(struct inode *inode)
 	inode_detach_wb(inode);
 	security_inode_free(inode);
 	fsnotify_inode_delete(inode);
-	locks_free_lock_context(inode->i_flctx);
+	locks_free_lock_context(inode);
 	if (!inode->i_nlink) {
 		WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0);
 		atomic_long_dec(&inode->i_sb->s_remove_count);
@@ -495,7 +501,7 @@ void clear_inode(struct inode *inode)
 	 */
 	spin_lock_irq(&inode->i_data.tree_lock);
 	BUG_ON(inode->i_data.nrpages);
-	BUG_ON(inode->i_data.nrshadows);
+	BUG_ON(inode->i_data.nrexceptional);
 	spin_unlock_irq(&inode->i_data.tree_lock);
 	BUG_ON(!list_empty(&inode->i_data.private_list));
 	BUG_ON(!(inode->i_state & I_FREEING));
@@ -966,9 +972,9 @@ void lock_two_nondirectories(struct inode *inode1, struct inode *inode2)
 		swap(inode1, inode2);
 
 	if (inode1 && !S_ISDIR(inode1->i_mode))
-		mutex_lock(&inode1->i_mutex);
+		inode_lock(inode1);
 	if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1)
-		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_NONDIR2);
+		inode_lock_nested(inode2, I_MUTEX_NONDIR2);
 }
 EXPORT_SYMBOL(lock_two_nondirectories);
 
@@ -980,9 +986,9 @@ EXPORT_SYMBOL(lock_two_nondirectories);
 void unlock_two_nondirectories(struct inode *inode1, struct inode *inode2)
 {
 	if (inode1 && !S_ISDIR(inode1->i_mode))
-		mutex_unlock(&inode1->i_mutex);
+		inode_unlock(inode1);
 	if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1)
-		mutex_unlock(&inode2->i_mutex);
+		inode_unlock(inode2);
 }
 EXPORT_SYMBOL(unlock_two_nondirectories);
 
@@ -1597,6 +1603,7 @@ static int update_time(struct inode *inode, struct timespec *time, int flags)
 /**
  *	touch_atime	-	update the access time
  *	@path: the &struct path to update
+ *	@inode: inode to update
  *
  *	Update the accessed time on an inode and mark it for writeback.
  *	This function automatically handles read only file systems and media,
@@ -1882,7 +1889,7 @@ void __init inode_init(void)
 					 sizeof(struct inode),
 					 0,
 					 (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|
-					 SLAB_MEM_SPREAD),
+					 SLAB_MEM_SPREAD|SLAB_ACCOUNT),
 					 init_once);
 
 	/* Hash may have been set up in inode_init_early */
@@ -2027,3 +2034,9 @@ void inode_set_flags(struct inode *inode, unsigned int flags,
 				  new_flags) != old_flags));
 }
 EXPORT_SYMBOL(inode_set_flags);
+
+void inode_nohighmem(struct inode *inode)
+{
+	mapping_set_gfp_mask(inode->i_mapping, GFP_USER);
+}
+EXPORT_SYMBOL(inode_nohighmem);
diff --git a/fs/internal.h b/fs/internal.h
index 71859c4d0b41..b71deeecea17 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -55,7 +55,7 @@ extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
 /*
  * namespace.c
  */
-extern int copy_mount_options(const void __user *, unsigned long *);
+extern void *copy_mount_options(const void __user *);
 extern char *copy_mount_string(const void __user *);
 
 extern struct vfsmount *lookup_mnt(struct path *);
@@ -151,3 +151,10 @@ extern void mnt_pin_kill(struct mount *m);
  * fs/nsfs.c
  */
 extern struct dentry_operations ns_dentry_operations;
+
+/*
+ * fs/ioctl.c
+ */
+extern int do_vfs_ioctl(struct file *file, unsigned int fd, unsigned int cmd,
+		    unsigned long arg);
+extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 5d01d2638ca5..116a333e9c77 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -15,6 +15,7 @@
 #include <linux/writeback.h>
 #include <linux/buffer_head.h>
 #include <linux/falloc.h>
+#include "internal.h"
 
 #include <asm/ioctls.h>
 
@@ -32,8 +33,7 @@
  *
  * Returns 0 on success, -errno on error.
  */
-static long vfs_ioctl(struct file *filp, unsigned int cmd,
-		      unsigned long arg)
+long vfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	int error = -ENOTTY;
 
@@ -215,6 +215,29 @@ static int ioctl_fiemap(struct file *filp, unsigned long arg)
 	return error;
 }
 
+static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd,
+			     u64 off, u64 olen, u64 destoff)
+{
+	struct fd src_file = fdget(srcfd);
+	int ret;
+
+	if (!src_file.file)
+		return -EBADF;
+	ret = vfs_clone_file_range(src_file.file, off, dst_file, destoff, olen);
+	fdput(src_file);
+	return ret;
+}
+
+static long ioctl_file_clone_range(struct file *file, void __user *argp)
+{
+	struct file_clone_range args;
+
+	if (copy_from_user(&args, argp, sizeof(args)))
+		return -EFAULT;
+	return ioctl_file_clone(file, args.src_fd, args.src_offset,
+				args.src_length, args.dest_offset);
+}
+
 #ifdef CONFIG_BLOCK
 
 static inline sector_t logical_to_blk(struct inode *inode, loff_t offset)
@@ -411,9 +434,9 @@ int generic_block_fiemap(struct inode *inode,
 			 u64 len, get_block_t *get_block)
 {
 	int ret;
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	ret = __generic_block_fiemap(inode, fieinfo, start, len, get_block);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return ret;
 }
 EXPORT_SYMBOL(generic_block_fiemap);
@@ -545,6 +568,41 @@ static int ioctl_fsthaw(struct file *filp)
 	return thaw_super(sb);
 }
 
+static long ioctl_file_dedupe_range(struct file *file, void __user *arg)
+{
+	struct file_dedupe_range __user *argp = arg;
+	struct file_dedupe_range *same = NULL;
+	int ret;
+	unsigned long size;
+	u16 count;
+
+	if (get_user(count, &argp->dest_count)) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	size = offsetof(struct file_dedupe_range __user, info[count]);
+
+	same = memdup_user(argp, size);
+	if (IS_ERR(same)) {
+		ret = PTR_ERR(same);
+		same = NULL;
+		goto out;
+	}
+
+	ret = vfs_dedupe_file_range(file, same);
+	if (ret)
+		goto out;
+
+	ret = copy_to_user(argp, same, size);
+	if (ret)
+		ret = -EFAULT;
+
+out:
+	kfree(same);
+	return ret;
+}
+
 /*
  * When you add any new common ioctls to the switches above and below
  * please update compat_sys_ioctl() too.
@@ -600,6 +658,15 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
 	case FIGETBSZ:
 		return put_user(inode->i_sb->s_blocksize, argp);
 
+	case FICLONE:
+		return ioctl_file_clone(filp, arg, 0, 0, 0);
+
+	case FICLONERANGE:
+		return ioctl_file_clone_range(filp, argp);
+
+	case FIDEDUPERANGE:
+		return ioctl_file_dedupe_range(filp, argp);
+
 	default:
 		if (S_ISREG(inode->i_mode))
 			error = file_ioctl(filp, cmd, arg);
diff --git a/fs/isofs/compress.c b/fs/isofs/compress.c
index f311bf084015..2e4e834d1a98 100644
--- a/fs/isofs/compress.c
+++ b/fs/isofs/compress.c
@@ -26,7 +26,7 @@
 #include "zisofs.h"
 
 /* This should probably be global. */
-static char zisofs_sink_page[PAGE_CACHE_SIZE];
+static char zisofs_sink_page[PAGE_SIZE];
 
 /*
  * This contains the zlib memory allocation and the mutex for the
@@ -70,11 +70,11 @@ static loff_t zisofs_uncompress_block(struct inode *inode, loff_t block_start,
 		for ( i = 0 ; i < pcount ; i++ ) {
 			if (!pages[i])
 				continue;
-			memset(page_address(pages[i]), 0, PAGE_CACHE_SIZE);
+			memset(page_address(pages[i]), 0, PAGE_SIZE);
 			flush_dcache_page(pages[i]);
 			SetPageUptodate(pages[i]);
 		}
-		return ((loff_t)pcount) << PAGE_CACHE_SHIFT;
+		return ((loff_t)pcount) << PAGE_SHIFT;
 	}
 
 	/* Because zlib is not thread-safe, do all the I/O at the top. */
@@ -121,11 +121,11 @@ static loff_t zisofs_uncompress_block(struct inode *inode, loff_t block_start,
 			if (pages[curpage]) {
 				stream.next_out = page_address(pages[curpage])
 						+ poffset;
-				stream.avail_out = PAGE_CACHE_SIZE - poffset;
+				stream.avail_out = PAGE_SIZE - poffset;
 				poffset = 0;
 			} else {
 				stream.next_out = (void *)&zisofs_sink_page;
-				stream.avail_out = PAGE_CACHE_SIZE;
+				stream.avail_out = PAGE_SIZE;
 			}
 		}
 		if (!stream.avail_in) {
@@ -220,14 +220,14 @@ static int zisofs_fill_pages(struct inode *inode, int full_page, int pcount,
 	 * pages with the data we have anyway...
 	 */
 	start_off = page_offset(pages[full_page]);
-	end_off = min_t(loff_t, start_off + PAGE_CACHE_SIZE, inode->i_size);
+	end_off = min_t(loff_t, start_off + PAGE_SIZE, inode->i_size);
 
 	cstart_block = start_off >> zisofs_block_shift;
 	cend_block = (end_off + (1 << zisofs_block_shift) - 1)
 			>> zisofs_block_shift;
 
-	WARN_ON(start_off - (full_page << PAGE_CACHE_SHIFT) !=
-		((cstart_block << zisofs_block_shift) & PAGE_CACHE_MASK));
+	WARN_ON(start_off - (full_page << PAGE_SHIFT) !=
+		((cstart_block << zisofs_block_shift) & PAGE_MASK));
 
 	/* Find the pointer to this specific chunk */
 	/* Note: we're not using isonum_731() here because the data is known aligned */
@@ -260,10 +260,10 @@ static int zisofs_fill_pages(struct inode *inode, int full_page, int pcount,
 		ret = zisofs_uncompress_block(inode, block_start, block_end,
 					      pcount, pages, poffset, &err);
 		poffset += ret;
-		pages += poffset >> PAGE_CACHE_SHIFT;
-		pcount -= poffset >> PAGE_CACHE_SHIFT;
-		full_page -= poffset >> PAGE_CACHE_SHIFT;
-		poffset &= ~PAGE_CACHE_MASK;
+		pages += poffset >> PAGE_SHIFT;
+		pcount -= poffset >> PAGE_SHIFT;
+		full_page -= poffset >> PAGE_SHIFT;
+		poffset &= ~PAGE_MASK;
 
 		if (err) {
 			brelse(bh);
@@ -282,7 +282,7 @@ static int zisofs_fill_pages(struct inode *inode, int full_page, int pcount,
 
 	if (poffset && *pages) {
 		memset(page_address(*pages) + poffset, 0,
-		       PAGE_CACHE_SIZE - poffset);
+		       PAGE_SIZE - poffset);
 		flush_dcache_page(*pages);
 		SetPageUptodate(*pages);
 	}
@@ -302,12 +302,12 @@ static int zisofs_readpage(struct file *file, struct page *page)
 	int i, pcount, full_page;
 	unsigned int zisofs_block_shift = ISOFS_I(inode)->i_format_parm[1];
 	unsigned int zisofs_pages_per_cblock =
-		PAGE_CACHE_SHIFT <= zisofs_block_shift ?
-		(1 << (zisofs_block_shift - PAGE_CACHE_SHIFT)) : 0;
+		PAGE_SHIFT <= zisofs_block_shift ?
+		(1 << (zisofs_block_shift - PAGE_SHIFT)) : 0;
 	struct page *pages[max_t(unsigned, zisofs_pages_per_cblock, 1)];
 	pgoff_t index = page->index, end_index;
 
-	end_index = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	end_index = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	/*
 	 * If this page is wholly outside i_size we just return zero;
 	 * do_generic_file_read() will handle this for us
@@ -318,7 +318,7 @@ static int zisofs_readpage(struct file *file, struct page *page)
 		return 0;
 	}
 
-	if (PAGE_CACHE_SHIFT <= zisofs_block_shift) {
+	if (PAGE_SHIFT <= zisofs_block_shift) {
 		/* We have already been given one page, this is the one
 		   we must do. */
 		full_page = index & (zisofs_pages_per_cblock - 1);
@@ -351,7 +351,7 @@ static int zisofs_readpage(struct file *file, struct page *page)
 			kunmap(pages[i]);
 			unlock_page(pages[i]);
 			if (i != full_page)
-				page_cache_release(pages[i]);
+				put_page(pages[i]);
 		}
 	}			
 
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index d67a16f2a45d..131dedc920d8 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -94,7 +94,7 @@ static int __init init_inodecache(void)
 	isofs_inode_cachep = kmem_cache_create("isofs_inode_cache",
 					sizeof(struct iso_inode_info),
 					0, (SLAB_RECLAIM_ACCOUNT|
-					SLAB_MEM_SPREAD),
+					SLAB_MEM_SPREAD|SLAB_ACCOUNT),
 					init_once);
 	if (isofs_inode_cachep == NULL)
 		return -ENOMEM;
@@ -1021,7 +1021,7 @@ int isofs_get_blocks(struct inode *inode, sector_t iblock,
 		 * the page with useless information without generating any
 		 * I/O errors.
 		 */
-		if (b_off > ((inode->i_size + PAGE_CACHE_SIZE - 1) >> ISOFS_BUFFER_BITS(inode))) {
+		if (b_off > ((inode->i_size + PAGE_SIZE - 1) >> ISOFS_BUFFER_BITS(inode))) {
 			printk(KERN_DEBUG "%s: block >= EOF (%lu, %llu)\n",
 				__func__, b_off,
 				(unsigned long long)inode->i_size);
@@ -1417,6 +1417,7 @@ static int isofs_read_inode(struct inode *inode, int relocated)
 		inode->i_fop = &isofs_dir_operations;
 	} else if (S_ISLNK(inode->i_mode)) {
 		inode->i_op = &page_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_data.a_ops = &isofs_symlink_aops;
 	} else
 		/* XXX - parse_rock_ridge_inode() had already set i_rdev. */
diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c
index 735d7522a3a9..5384ceb35b1c 100644
--- a/fs/isofs/rock.c
+++ b/fs/isofs/rock.c
@@ -687,7 +687,7 @@ static int rock_ridge_symlink_readpage(struct file *file, struct page *page)
 	struct inode *inode = page->mapping->host;
 	struct iso_inode_info *ei = ISOFS_I(inode);
 	struct isofs_sb_info *sbi = ISOFS_SB(inode->i_sb);
-	char *link = kmap(page);
+	char *link = page_address(page);
 	unsigned long bufsize = ISOFS_BUFFER_SIZE(inode);
 	struct buffer_head *bh;
 	char *rpnt = link;
@@ -774,7 +774,6 @@ repeat:
 	brelse(bh);
 	*rpnt = '\0';
 	SetPageUptodate(page);
-	kunmap(page);
 	unlock_page(page);
 	return 0;
 
@@ -791,7 +790,6 @@ fail:
 	brelse(bh);
 error:
 	SetPageError(page);
-	kunmap(page);
 	unlock_page(page);
 	return -EIO;
 }
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 36345fefa3ff..2ad98d6e19f4 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -81,11 +81,11 @@ static void release_buffer_page(struct buffer_head *bh)
 	if (!trylock_page(page))
 		goto nope;
 
-	page_cache_get(page);
+	get_page(page);
 	__brelse(bh);
 	try_to_free_buffers(page);
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 	return;
 
 nope:
@@ -131,14 +131,12 @@ static int journal_submit_commit_record(journal_t *journal,
 	if (is_journal_aborted(journal))
 		return 0;
 
-	bh = jbd2_journal_get_descriptor_buffer(journal);
+	bh = jbd2_journal_get_descriptor_buffer(commit_transaction,
+						JBD2_COMMIT_BLOCK);
 	if (!bh)
 		return 1;
 
 	tmp = (struct commit_header *)bh->b_data;
-	tmp->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
-	tmp->h_blocktype = cpu_to_be32(JBD2_COMMIT_BLOCK);
-	tmp->h_sequence = cpu_to_be32(commit_transaction->t_tid);
 	tmp->h_commit_sec = cpu_to_be64(now.tv_sec);
 	tmp->h_commit_nsec = cpu_to_be32(now.tv_nsec);
 
@@ -222,7 +220,7 @@ static int journal_submit_data_buffers(journal_t *journal,
 	spin_lock(&journal->j_list_lock);
 	list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
 		mapping = jinode->i_vfs_inode->i_mapping;
-		set_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
+		jinode->i_flags |= JI_COMMIT_RUNNING;
 		spin_unlock(&journal->j_list_lock);
 		/*
 		 * submit the inode data buffers. We use writepage
@@ -236,8 +234,8 @@ static int journal_submit_data_buffers(journal_t *journal,
 			ret = err;
 		spin_lock(&journal->j_list_lock);
 		J_ASSERT(jinode->i_transaction == commit_transaction);
-		clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
-		smp_mb__after_atomic();
+		jinode->i_flags &= ~JI_COMMIT_RUNNING;
+		smp_mb();
 		wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
 	}
 	spin_unlock(&journal->j_list_lock);
@@ -258,7 +256,7 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
 	/* For locking, see the comment in journal_submit_data_buffers() */
 	spin_lock(&journal->j_list_lock);
 	list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
-		set_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
+		jinode->i_flags |= JI_COMMIT_RUNNING;
 		spin_unlock(&journal->j_list_lock);
 		err = filemap_fdatawait(jinode->i_vfs_inode->i_mapping);
 		if (err) {
@@ -274,8 +272,8 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
 				ret = err;
 		}
 		spin_lock(&journal->j_list_lock);
-		clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
-		smp_mb__after_atomic();
+		jinode->i_flags &= ~JI_COMMIT_RUNNING;
+		smp_mb();
 		wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
 	}
 
@@ -319,22 +317,6 @@ static void write_tag_block(journal_t *j, journal_block_tag_t *tag,
 		tag->t_blocknr_high = cpu_to_be32((block >> 31) >> 1);
 }
 
-static void jbd2_descr_block_csum_set(journal_t *j,
-				      struct buffer_head *bh)
-{
-	struct jbd2_journal_block_tail *tail;
-	__u32 csum;
-
-	if (!jbd2_journal_has_csum_v2or3(j))
-		return;
-
-	tail = (struct jbd2_journal_block_tail *)(bh->b_data + j->j_blocksize -
-			sizeof(struct jbd2_journal_block_tail));
-	tail->t_checksum = 0;
-	csum = jbd2_chksum(j, j->j_csum_seed, bh->b_data, j->j_blocksize);
-	tail->t_checksum = cpu_to_be32(csum);
-}
-
 static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag,
 				    struct buffer_head *bh, __u32 sequence)
 {
@@ -379,7 +361,6 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	ktime_t start_time;
 	u64 commit_time;
 	char *tagp = NULL;
-	journal_header_t *header;
 	journal_block_tag_t *tag = NULL;
 	int space_left = 0;
 	int first_tag = 0;
@@ -554,8 +535,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		jbd2_journal_abort(journal, err);
 
 	blk_start_plug(&plug);
-	jbd2_journal_write_revoke_records(journal, commit_transaction,
-					  &log_bufs, WRITE_SYNC);
+	jbd2_journal_write_revoke_records(commit_transaction, &log_bufs);
 
 	jbd_debug(3, "JBD2: commit phase 2b\n");
 
@@ -616,7 +596,9 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 
 			jbd_debug(4, "JBD2: get descriptor\n");
 
-			descriptor = jbd2_journal_get_descriptor_buffer(journal);
+			descriptor = jbd2_journal_get_descriptor_buffer(
+							commit_transaction,
+							JBD2_DESCRIPTOR_BLOCK);
 			if (!descriptor) {
 				jbd2_journal_abort(journal, -EIO);
 				continue;
@@ -625,11 +607,6 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 			jbd_debug(4, "JBD2: got buffer %llu (%p)\n",
 				(unsigned long long)descriptor->b_blocknr,
 				descriptor->b_data);
-			header = (journal_header_t *)descriptor->b_data;
-			header->h_magic     = cpu_to_be32(JBD2_MAGIC_NUMBER);
-			header->h_blocktype = cpu_to_be32(JBD2_DESCRIPTOR_BLOCK);
-			header->h_sequence  = cpu_to_be32(commit_transaction->t_tid);
-
 			tagp = &descriptor->b_data[sizeof(journal_header_t)];
 			space_left = descriptor->b_size -
 						sizeof(journal_header_t);
@@ -721,7 +698,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 
 			tag->t_flags |= cpu_to_be16(JBD2_FLAG_LAST_TAG);
 
-			jbd2_descr_block_csum_set(journal, descriptor);
+			jbd2_descriptor_block_csum_set(journal, descriptor);
 start_journal_io:
 			for (i = 0; i < bufs; i++) {
 				struct buffer_head *bh = wbuf[i];
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 81e622681c82..435f0b26ac20 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -805,10 +805,13 @@ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr,
  * But we don't bother doing that, so there will be coherency problems with
  * mmaps of blockdevs which hold live JBD-controlled filesystems.
  */
-struct buffer_head *jbd2_journal_get_descriptor_buffer(journal_t *journal)
+struct buffer_head *
+jbd2_journal_get_descriptor_buffer(transaction_t *transaction, int type)
 {
+	journal_t *journal = transaction->t_journal;
 	struct buffer_head *bh;
 	unsigned long long blocknr;
+	journal_header_t *header;
 	int err;
 
 	err = jbd2_journal_next_log_block(journal, &blocknr);
@@ -821,12 +824,31 @@ struct buffer_head *jbd2_journal_get_descriptor_buffer(journal_t *journal)
 		return NULL;
 	lock_buffer(bh);
 	memset(bh->b_data, 0, journal->j_blocksize);
+	header = (journal_header_t *)bh->b_data;
+	header->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
+	header->h_blocktype = cpu_to_be32(type);
+	header->h_sequence = cpu_to_be32(transaction->t_tid);
 	set_buffer_uptodate(bh);
 	unlock_buffer(bh);
 	BUFFER_TRACE(bh, "return this buffer");
 	return bh;
 }
 
+void jbd2_descriptor_block_csum_set(journal_t *j, struct buffer_head *bh)
+{
+	struct jbd2_journal_block_tail *tail;
+	__u32 csum;
+
+	if (!jbd2_journal_has_csum_v2or3(j))
+		return;
+
+	tail = (struct jbd2_journal_block_tail *)(bh->b_data + j->j_blocksize -
+			sizeof(struct jbd2_journal_block_tail));
+	tail->t_checksum = 0;
+	csum = jbd2_chksum(j, j->j_csum_seed, bh->b_data, j->j_blocksize);
+	tail->t_checksum = cpu_to_be32(csum);
+}
+
 /*
  * Return tid of the oldest transaction in the journal and block in the journal
  * where the transaction starts.
@@ -1408,11 +1430,12 @@ out:
 /**
  * jbd2_mark_journal_empty() - Mark on disk journal as empty.
  * @journal: The journal to update.
+ * @write_op: With which operation should we write the journal sb
  *
  * Update a journal's dynamic superblock fields to show that journal is empty.
  * Write updated superblock to disk waiting for IO to complete.
  */
-static void jbd2_mark_journal_empty(journal_t *journal)
+static void jbd2_mark_journal_empty(journal_t *journal, int write_op)
 {
 	journal_superblock_t *sb = journal->j_superblock;
 
@@ -1430,7 +1453,7 @@ static void jbd2_mark_journal_empty(journal_t *journal)
 	sb->s_start    = cpu_to_be32(0);
 	read_unlock(&journal->j_state_lock);
 
-	jbd2_write_superblock(journal, WRITE_FUA);
+	jbd2_write_superblock(journal, write_op);
 
 	/* Log is no longer empty */
 	write_lock(&journal->j_state_lock);
@@ -1716,7 +1739,13 @@ int jbd2_journal_destroy(journal_t *journal)
 	if (journal->j_sb_buffer) {
 		if (!is_journal_aborted(journal)) {
 			mutex_lock(&journal->j_checkpoint_mutex);
-			jbd2_mark_journal_empty(journal);
+
+			write_lock(&journal->j_state_lock);
+			journal->j_tail_sequence =
+				++journal->j_transaction_sequence;
+			write_unlock(&journal->j_state_lock);
+
+			jbd2_mark_journal_empty(journal, WRITE_FLUSH_FUA);
 			mutex_unlock(&journal->j_checkpoint_mutex);
 		} else
 			err = -EIO;
@@ -1975,7 +2004,7 @@ int jbd2_journal_flush(journal_t *journal)
 	 * the magic code for a fully-recovered superblock.  Any future
 	 * commits of data to the journal will restore the current
 	 * s_start value. */
-	jbd2_mark_journal_empty(journal);
+	jbd2_mark_journal_empty(journal, WRITE_FUA);
 	mutex_unlock(&journal->j_checkpoint_mutex);
 	write_lock(&journal->j_state_lock);
 	J_ASSERT(!journal->j_running_transaction);
@@ -2021,7 +2050,7 @@ int jbd2_journal_wipe(journal_t *journal, int write)
 	if (write) {
 		/* Lock to make assertions happy... */
 		mutex_lock(&journal->j_checkpoint_mutex);
-		jbd2_mark_journal_empty(journal);
+		jbd2_mark_journal_empty(journal, WRITE_FUA);
 		mutex_unlock(&journal->j_checkpoint_mutex);
 	}
 
@@ -2192,7 +2221,7 @@ void jbd2_journal_ack_err(journal_t *journal)
 
 int jbd2_journal_blocks_per_page(struct inode *inode)
 {
-	return 1 << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
+	return 1 << (PAGE_SHIFT - inode->i_sb->s_blocksize_bits);
 }
 
 /*
@@ -2565,7 +2594,7 @@ void jbd2_journal_release_jbd_inode(journal_t *journal,
 restart:
 	spin_lock(&journal->j_list_lock);
 	/* Is commit writing out inode - we have to wait */
-	if (test_bit(__JI_COMMIT_RUNNING, &jinode->i_flags)) {
+	if (jinode->i_flags & JI_COMMIT_RUNNING) {
 		wait_queue_head_t *wq;
 		DEFINE_WAIT_BIT(wait, &jinode->i_flags, __JI_COMMIT_RUNNING);
 		wq = bit_waitqueue(&jinode->i_flags, __JI_COMMIT_RUNNING);
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 76579c28edc7..805bc6bcd8ab 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -174,8 +174,7 @@ static int jread(struct buffer_head **bhp, journal_t *journal,
 	return 0;
 }
 
-static int jbd2_descr_block_csum_verify(journal_t *j,
-					void *buf)
+static int jbd2_descriptor_block_csum_verify(journal_t *j, void *buf)
 {
 	struct jbd2_journal_block_tail *tail;
 	__be32 provided;
@@ -522,8 +521,8 @@ static int do_one_pass(journal_t *journal,
 				descr_csum_size =
 					sizeof(struct jbd2_journal_block_tail);
 			if (descr_csum_size > 0 &&
-			    !jbd2_descr_block_csum_verify(journal,
-							  bh->b_data)) {
+			    !jbd2_descriptor_block_csum_verify(journal,
+							       bh->b_data)) {
 				printk(KERN_ERR "JBD2: Invalid checksum "
 				       "recovering block %lu in log\n",
 				       next_log_block);
@@ -811,26 +810,6 @@ static int do_one_pass(journal_t *journal,
 	return err;
 }
 
-static int jbd2_revoke_block_csum_verify(journal_t *j,
-					 void *buf)
-{
-	struct jbd2_journal_revoke_tail *tail;
-	__be32 provided;
-	__u32 calculated;
-
-	if (!jbd2_journal_has_csum_v2or3(j))
-		return 1;
-
-	tail = (struct jbd2_journal_revoke_tail *)(buf + j->j_blocksize -
-			sizeof(struct jbd2_journal_revoke_tail));
-	provided = tail->r_checksum;
-	tail->r_checksum = 0;
-	calculated = jbd2_chksum(j, j->j_csum_seed, buf, j->j_blocksize);
-	tail->r_checksum = provided;
-
-	return provided == cpu_to_be32(calculated);
-}
-
 /* Scan a revoke record, marking all blocks mentioned as revoked. */
 
 static int scan_revoke_records(journal_t *journal, struct buffer_head *bh,
@@ -846,11 +825,11 @@ static int scan_revoke_records(journal_t *journal, struct buffer_head *bh,
 	offset = sizeof(jbd2_journal_revoke_header_t);
 	rcount = be32_to_cpu(header->r_count);
 
-	if (!jbd2_revoke_block_csum_verify(journal, header))
+	if (!jbd2_descriptor_block_csum_verify(journal, header))
 		return -EFSBADCRC;
 
 	if (jbd2_journal_has_csum_v2or3(journal))
-		csum_size = sizeof(struct jbd2_journal_revoke_tail);
+		csum_size = sizeof(struct jbd2_journal_block_tail);
 	if (rcount > journal->j_blocksize - csum_size)
 		return -EINVAL;
 	max = rcount;
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index 705ae577882b..91171dc352cb 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -122,11 +122,11 @@ struct jbd2_revoke_table_s
 
 
 #ifdef __KERNEL__
-static void write_one_revoke_record(journal_t *, transaction_t *,
+static void write_one_revoke_record(transaction_t *,
 				    struct list_head *,
 				    struct buffer_head **, int *,
-				    struct jbd2_revoke_record_s *, int);
-static void flush_descriptor(journal_t *, struct buffer_head *, int, int);
+				    struct jbd2_revoke_record_s *);
+static void flush_descriptor(journal_t *, struct buffer_head *, int);
 #endif
 
 /* Utility functions to maintain the revoke table */
@@ -519,11 +519,10 @@ void jbd2_journal_switch_revoke_table(journal_t *journal)
  * Write revoke records to the journal for all entries in the current
  * revoke hash, deleting the entries as we go.
  */
-void jbd2_journal_write_revoke_records(journal_t *journal,
-				       transaction_t *transaction,
-				       struct list_head *log_bufs,
-				       int write_op)
+void jbd2_journal_write_revoke_records(transaction_t *transaction,
+				       struct list_head *log_bufs)
 {
+	journal_t *journal = transaction->t_journal;
 	struct buffer_head *descriptor;
 	struct jbd2_revoke_record_s *record;
 	struct jbd2_revoke_table_s *revoke;
@@ -544,16 +543,15 @@ void jbd2_journal_write_revoke_records(journal_t *journal,
 		while (!list_empty(hash_list)) {
 			record = (struct jbd2_revoke_record_s *)
 				hash_list->next;
-			write_one_revoke_record(journal, transaction, log_bufs,
-						&descriptor, &offset,
-						record, write_op);
+			write_one_revoke_record(transaction, log_bufs,
+						&descriptor, &offset, record);
 			count++;
 			list_del(&record->hash);
 			kmem_cache_free(jbd2_revoke_record_cache, record);
 		}
 	}
 	if (descriptor)
-		flush_descriptor(journal, descriptor, offset, write_op);
+		flush_descriptor(journal, descriptor, offset);
 	jbd_debug(1, "Wrote %d revoke records\n", count);
 }
 
@@ -562,18 +560,16 @@ void jbd2_journal_write_revoke_records(journal_t *journal,
  * block if the old one is full or if we have not already created one.
  */
 
-static void write_one_revoke_record(journal_t *journal,
-				    transaction_t *transaction,
+static void write_one_revoke_record(transaction_t *transaction,
 				    struct list_head *log_bufs,
 				    struct buffer_head **descriptorp,
 				    int *offsetp,
-				    struct jbd2_revoke_record_s *record,
-				    int write_op)
+				    struct jbd2_revoke_record_s *record)
 {
+	journal_t *journal = transaction->t_journal;
 	int csum_size = 0;
 	struct buffer_head *descriptor;
 	int sz, offset;
-	journal_header_t *header;
 
 	/* If we are already aborting, this all becomes a noop.  We
            still need to go round the loop in
@@ -587,7 +583,7 @@ static void write_one_revoke_record(journal_t *journal,
 
 	/* Do we need to leave space at the end for a checksum? */
 	if (jbd2_journal_has_csum_v2or3(journal))
-		csum_size = sizeof(struct jbd2_journal_revoke_tail);
+		csum_size = sizeof(struct jbd2_journal_block_tail);
 
 	if (jbd2_has_feature_64bit(journal))
 		sz = 8;
@@ -597,19 +593,16 @@ static void write_one_revoke_record(journal_t *journal,
 	/* Make sure we have a descriptor with space left for the record */
 	if (descriptor) {
 		if (offset + sz > journal->j_blocksize - csum_size) {
-			flush_descriptor(journal, descriptor, offset, write_op);
+			flush_descriptor(journal, descriptor, offset);
 			descriptor = NULL;
 		}
 	}
 
 	if (!descriptor) {
-		descriptor = jbd2_journal_get_descriptor_buffer(journal);
+		descriptor = jbd2_journal_get_descriptor_buffer(transaction,
+							JBD2_REVOKE_BLOCK);
 		if (!descriptor)
 			return;
-		header = (journal_header_t *)descriptor->b_data;
-		header->h_magic     = cpu_to_be32(JBD2_MAGIC_NUMBER);
-		header->h_blocktype = cpu_to_be32(JBD2_REVOKE_BLOCK);
-		header->h_sequence  = cpu_to_be32(transaction->t_tid);
 
 		/* Record it so that we can wait for IO completion later */
 		BUFFER_TRACE(descriptor, "file in log_bufs");
@@ -630,21 +623,6 @@ static void write_one_revoke_record(journal_t *journal,
 	*offsetp = offset;
 }
 
-static void jbd2_revoke_csum_set(journal_t *j, struct buffer_head *bh)
-{
-	struct jbd2_journal_revoke_tail *tail;
-	__u32 csum;
-
-	if (!jbd2_journal_has_csum_v2or3(j))
-		return;
-
-	tail = (struct jbd2_journal_revoke_tail *)(bh->b_data + j->j_blocksize -
-			sizeof(struct jbd2_journal_revoke_tail));
-	tail->r_checksum = 0;
-	csum = jbd2_chksum(j, j->j_csum_seed, bh->b_data, j->j_blocksize);
-	tail->r_checksum = cpu_to_be32(csum);
-}
-
 /*
  * Flush a revoke descriptor out to the journal.  If we are aborting,
  * this is a noop; otherwise we are generating a buffer which needs to
@@ -654,7 +632,7 @@ static void jbd2_revoke_csum_set(journal_t *j, struct buffer_head *bh)
 
 static void flush_descriptor(journal_t *journal,
 			     struct buffer_head *descriptor,
-			     int offset, int write_op)
+			     int offset)
 {
 	jbd2_journal_revoke_header_t *header;
 
@@ -665,12 +643,12 @@ static void flush_descriptor(journal_t *journal,
 
 	header = (jbd2_journal_revoke_header_t *)descriptor->b_data;
 	header->r_count = cpu_to_be32(offset);
-	jbd2_revoke_csum_set(journal, descriptor);
+	jbd2_descriptor_block_csum_set(journal, descriptor);
 
 	set_buffer_jwrite(descriptor);
 	BUFFER_TRACE(descriptor, "write");
 	set_buffer_dirty(descriptor);
-	write_dirty_buffer(descriptor, write_op);
+	write_dirty_buffer(descriptor, WRITE_SYNC);
 }
 #endif
 
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 98d04c5fe3d2..2c56c3e32194 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -764,13 +764,11 @@ void jbd2_journal_unlock_updates (journal_t *journal)
 
 static void warn_dirty_buffer(struct buffer_head *bh)
 {
-	char b[BDEVNAME_SIZE];
-
 	printk(KERN_WARNING
-	       "JBD2: Spotted dirty metadata buffer (dev = %s, blocknr = %llu). "
+	       "JBD2: Spotted dirty metadata buffer (dev = %pg, blocknr = %llu). "
 	       "There's a risk of filesystem corruption in case of system "
 	       "crash.\n",
-	       bdevname(bh->b_bdev, b), (unsigned long long)bh->b_blocknr);
+	       bh->b_bdev, (unsigned long long)bh->b_blocknr);
 }
 
 /* Call t_frozen trigger and copy buffer data into jh->b_frozen_data. */
@@ -968,14 +966,8 @@ repeat:
 		if (!frozen_buffer) {
 			JBUFFER_TRACE(jh, "allocate memory for buffer");
 			jbd_unlock_bh_state(bh);
-			frozen_buffer = jbd2_alloc(jh2bh(jh)->b_size, GFP_NOFS);
-			if (!frozen_buffer) {
-				printk(KERN_ERR "%s: OOM for frozen_buffer\n",
-				       __func__);
-				JBUFFER_TRACE(jh, "oom!");
-				error = -ENOMEM;
-				goto out;
-			}
+			frozen_buffer = jbd2_alloc(jh2bh(jh)->b_size,
+						   GFP_NOFS | __GFP_NOFAIL);
 			goto repeat;
 		}
 		jh->b_frozen_data = frozen_buffer;
@@ -1009,7 +1001,8 @@ out:
 }
 
 /* Fast check whether buffer is already attached to the required transaction */
-static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh)
+static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh,
+							bool undo)
 {
 	struct journal_head *jh;
 	bool ret = false;
@@ -1036,6 +1029,9 @@ static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh)
 	jh = READ_ONCE(bh->b_private);
 	if (!jh)
 		goto out;
+	/* For undo access buffer must have data copied */
+	if (undo && !jh->b_committed_data)
+		goto out;
 	if (jh->b_transaction != handle->h_transaction &&
 	    jh->b_next_transaction != handle->h_transaction)
 		goto out;
@@ -1073,7 +1069,7 @@ int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh)
 	struct journal_head *jh;
 	int rc;
 
-	if (jbd2_write_access_granted(handle, bh))
+	if (jbd2_write_access_granted(handle, bh, false))
 		return 0;
 
 	jh = jbd2_journal_add_journal_head(bh);
@@ -1210,7 +1206,7 @@ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh)
 	char *committed_data = NULL;
 
 	JBUFFER_TRACE(jh, "entry");
-	if (jbd2_write_access_granted(handle, bh))
+	if (jbd2_write_access_granted(handle, bh, true))
 		return 0;
 
 	jh = jbd2_journal_add_journal_head(bh);
@@ -1224,15 +1220,9 @@ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh)
 		goto out;
 
 repeat:
-	if (!jh->b_committed_data) {
-		committed_data = jbd2_alloc(jh2bh(jh)->b_size, GFP_NOFS);
-		if (!committed_data) {
-			printk(KERN_ERR "%s: No memory for committed data\n",
-				__func__);
-			err = -ENOMEM;
-			goto out;
-		}
-	}
+	if (!jh->b_committed_data)
+		committed_data = jbd2_alloc(jh2bh(jh)->b_size,
+					    GFP_NOFS|__GFP_NOFAIL);
 
 	jbd_lock_bh_state(bh);
 	if (!jh->b_committed_data) {
@@ -1937,8 +1927,8 @@ out:
  * @journal: journal for operation
  * @page: to try and free
  * @gfp_mask: we use the mask to detect how hard should we try to release
- * buffers. If __GFP_WAIT and __GFP_FS is set, we wait for commit code to
- * release the buffers.
+ * buffers. If __GFP_DIRECT_RECLAIM and __GFP_FS is set, we wait for commit
+ * code to release the buffers.
  *
  *
  * For all the buffers on this page,
@@ -2152,6 +2142,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh,
 
 		if (!buffer_dirty(bh)) {
 			/* bdflush has written it.  We can drop it now */
+			__jbd2_journal_remove_checkpoint(jh);
 			goto zap_buffer;
 		}
 
@@ -2181,6 +2172,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh,
 				/* The orphan record's transaction has
 				 * committed.  We can cleanse this buffer */
 				clear_buffer_jbddirty(bh);
+				__jbd2_journal_remove_checkpoint(jh);
 				goto zap_buffer;
 			}
 		}
@@ -2271,7 +2263,7 @@ int jbd2_journal_invalidatepage(journal_t *journal,
 	struct buffer_head *head, *bh, *next;
 	unsigned int stop = offset + length;
 	unsigned int curr_off = 0;
-	int partial_page = (offset || length < PAGE_CACHE_SIZE);
+	int partial_page = (offset || length < PAGE_SIZE);
 	int may_free = 1;
 	int ret = 0;
 
@@ -2280,7 +2272,7 @@ int jbd2_journal_invalidatepage(journal_t *journal,
 	if (!page_has_buffers(page))
 		return 0;
 
-	BUG_ON(stop > PAGE_CACHE_SIZE || stop < length);
+	BUG_ON(stop > PAGE_SIZE || stop < length);
 
 	/* We will potentially be playing with lists other than just the
 	 * data lists (especially for journaled data mode), so be
diff --git a/fs/jffs2/README.Locking b/fs/jffs2/README.Locking
index 3ea36554107f..8918ac905a3b 100644
--- a/fs/jffs2/README.Locking
+++ b/fs/jffs2/README.Locking
@@ -2,10 +2,6 @@
 	JFFS2 LOCKING DOCUMENTATION
 	---------------------------
 
-At least theoretically, JFFS2 does not require the Big Kernel Lock
-(BKL), which was always helpfully obtained for it by Linux 2.4 VFS
-code. It has its own locking, as described below.
-
 This document attempts to describe the existing locking rules for
 JFFS2. It is not expected to remain perfectly up to date, but ought to
 be fairly close.
@@ -69,6 +65,7 @@ Ordering constraints:
 	   any f->sem held.
 	2. Never attempt to lock two file mutexes in one thread.
 	   No ordering rules have been made for doing so.
+	3. Never lock a page cache page with f->sem held.
 
 
 	erase_completion_lock spinlock
diff --git a/fs/jffs2/background.c b/fs/jffs2/background.c
index bb9cebc9ca8a..e5c1783ab64a 100644
--- a/fs/jffs2/background.c
+++ b/fs/jffs2/background.c
@@ -80,7 +80,6 @@ static int jffs2_garbage_collect_thread(void *_c)
 	siginitset(&hupmask, sigmask(SIGHUP));
 	allow_signal(SIGKILL);
 	allow_signal(SIGSTOP);
-	allow_signal(SIGCONT);
 	allow_signal(SIGHUP);
 
 	c->gc_task = current;
@@ -121,20 +120,18 @@ static int jffs2_garbage_collect_thread(void *_c)
 		/* Put_super will send a SIGKILL and then wait on the sem.
 		 */
 		while (signal_pending(current) || freezing(current)) {
-			siginfo_t info;
 			unsigned long signr;
 
 			if (try_to_freeze())
 				goto again;
 
-			signr = dequeue_signal_lock(current, &current->blocked, &info);
+			signr = kernel_dequeue_signal(NULL);
 
 			switch(signr) {
 			case SIGSTOP:
 				jffs2_dbg(1, "%s(): SIGSTOP received\n",
 					  __func__);
-				set_current_state(TASK_STOPPED);
-				schedule();
+				kernel_signal_stop();
 				break;
 
 			case SIGKILL:
diff --git a/fs/jffs2/build.c b/fs/jffs2/build.c
index a3750f902adc..b288c8ae1236 100644
--- a/fs/jffs2/build.c
+++ b/fs/jffs2/build.c
@@ -17,6 +17,7 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/mtd/mtd.h>
+#include <linux/mm.h> /* kvfree() */
 #include "nodelist.h"
 
 static void jffs2_build_remove_unlinked_inode(struct jffs2_sb_info *,
@@ -49,7 +50,8 @@ next_inode(int *i, struct jffs2_inode_cache *ic, struct jffs2_sb_info *c)
 
 
 static void jffs2_build_inode_pass1(struct jffs2_sb_info *c,
-				    struct jffs2_inode_cache *ic)
+				    struct jffs2_inode_cache *ic,
+				    int *dir_hardlinks)
 {
 	struct jffs2_full_dirent *fd;
 
@@ -68,19 +70,21 @@ static void jffs2_build_inode_pass1(struct jffs2_sb_info *c,
 			dbg_fsbuild("child \"%s\" (ino #%u) of dir ino #%u doesn't exist!\n",
 				  fd->name, fd->ino, ic->ino);
 			jffs2_mark_node_obsolete(c, fd->raw);
+			/* Clear the ic/raw union so it doesn't cause problems later. */
+			fd->ic = NULL;
 			continue;
 		}
 
+		/* From this point, fd->raw is no longer used so we can set fd->ic */
+		fd->ic = child_ic;
+		child_ic->pino_nlink++;
+		/* If we appear (at this stage) to have hard-linked directories,
+		 * set a flag to trigger a scan later */
 		if (fd->type == DT_DIR) {
-			if (child_ic->pino_nlink) {
-				JFFS2_ERROR("child dir \"%s\" (ino #%u) of dir ino #%u appears to be a hard link\n",
-					    fd->name, fd->ino, ic->ino);
-				/* TODO: What do we do about it? */
-			} else {
-				child_ic->pino_nlink = ic->ino;
-			}
-		} else
-			child_ic->pino_nlink++;
+			child_ic->flags |= INO_FLAGS_IS_DIR;
+			if (child_ic->pino_nlink > 1)
+				*dir_hardlinks = 1;
+		}
 
 		dbg_fsbuild("increased nlink for child \"%s\" (ino #%u)\n", fd->name, fd->ino);
 		/* Can't free scan_dents so far. We might need them in pass 2 */
@@ -94,8 +98,7 @@ static void jffs2_build_inode_pass1(struct jffs2_sb_info *c,
 */
 static int jffs2_build_filesystem(struct jffs2_sb_info *c)
 {
-	int ret;
-	int i;
+	int ret, i, dir_hardlinks = 0;
 	struct jffs2_inode_cache *ic;
 	struct jffs2_full_dirent *fd;
 	struct jffs2_full_dirent *dead_fds = NULL;
@@ -119,7 +122,7 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c)
 	/* Now scan the directory tree, increasing nlink according to every dirent found. */
 	for_each_inode(i, c, ic) {
 		if (ic->scan_dents) {
-			jffs2_build_inode_pass1(c, ic);
+			jffs2_build_inode_pass1(c, ic, &dir_hardlinks);
 			cond_resched();
 		}
 	}
@@ -155,6 +158,20 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c)
 	}
 
 	dbg_fsbuild("pass 2a complete\n");
+
+	if (dir_hardlinks) {
+		/* If we detected directory hardlinks earlier, *hopefully*
+		 * they are gone now because some of the links were from
+		 * dead directories which still had some old dirents lying
+		 * around and not yet garbage-collected, but which have
+		 * been discarded above. So clear the pino_nlink field
+		 * in each directory, so that the final scan below can
+		 * print appropriate warnings. */
+		for_each_inode(i, c, ic) {
+			if (ic->flags & INO_FLAGS_IS_DIR)
+				ic->pino_nlink = 0;
+		}
+	}
 	dbg_fsbuild("freeing temporary data structures\n");
 
 	/* Finally, we can scan again and free the dirent structs */
@@ -162,6 +179,33 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c)
 		while(ic->scan_dents) {
 			fd = ic->scan_dents;
 			ic->scan_dents = fd->next;
+			/* We do use the pino_nlink field to count nlink of
+			 * directories during fs build, so set it to the
+			 * parent ino# now. Now that there's hopefully only
+			 * one. */
+			if (fd->type == DT_DIR) {
+				if (!fd->ic) {
+					/* We'll have complained about it and marked the coresponding
+					   raw node obsolete already. Just skip it. */
+					continue;
+				}
+
+				/* We *have* to have set this in jffs2_build_inode_pass1() */
+				BUG_ON(!(fd->ic->flags & INO_FLAGS_IS_DIR));
+
+				/* We clear ic->pino_nlink ∀ directories' ic *only* if dir_hardlinks
+				 * is set. Otherwise, we know this should never trigger anyway, so
+				 * we don't do the check. And ic->pino_nlink still contains the nlink
+				 * value (which is 1). */
+				if (dir_hardlinks && fd->ic->pino_nlink) {
+					JFFS2_ERROR("child dir \"%s\" (ino #%u) of dir ino #%u is also hard linked from dir ino #%u\n",
+						    fd->name, fd->ino, ic->ino, fd->ic->pino_nlink);
+					/* Should we unlink it from its previous parent? */
+				}
+
+				/* For directories, ic->pino_nlink holds that parent inode # */
+				fd->ic->pino_nlink = ic->ino;
+			}
 			jffs2_free_full_dirent(fd);
 		}
 		ic->scan_dents = NULL;
@@ -240,11 +284,7 @@ static void jffs2_build_remove_unlinked_inode(struct jffs2_sb_info *c,
 
 			/* Reduce nlink of the child. If it's now zero, stick it on the
 			   dead_fds list to be cleaned up later. Else just free the fd */
-
-			if (fd->type == DT_DIR)
-				child_ic->pino_nlink = 0;
-			else
-				child_ic->pino_nlink--;
+			child_ic->pino_nlink--;
 
 			if (!child_ic->pino_nlink) {
 				dbg_fsbuild("inode #%u (\"%s\") now has no links; adding to dead_fds list.\n",
@@ -383,12 +423,7 @@ int jffs2_do_mount_fs(struct jffs2_sb_info *c)
 	return 0;
 
  out_free:
-#ifndef __ECOS
-	if (jffs2_blocks_use_vmalloc(c))
-		vfree(c->blocks);
-	else
-#endif
-		kfree(c->blocks);
+	kvfree(c->blocks);
 
 	return ret;
 }
diff --git a/fs/jffs2/debug.c b/fs/jffs2/debug.c
index 1090eb64b90d..9d26b1b9fc01 100644
--- a/fs/jffs2/debug.c
+++ b/fs/jffs2/debug.c
@@ -95,15 +95,15 @@ __jffs2_dbg_fragtree_paranoia_check_nolock(struct jffs2_inode_info *f)
 			   rather than mucking around with actually reading the node
 			   and checking the compression type, which is the real way
 			   to tell a hole node. */
-			if (frag->ofs & (PAGE_CACHE_SIZE-1) && frag_prev(frag)
-					&& frag_prev(frag)->size < PAGE_CACHE_SIZE && frag_prev(frag)->node) {
+			if (frag->ofs & (PAGE_SIZE-1) && frag_prev(frag)
+					&& frag_prev(frag)->size < PAGE_SIZE && frag_prev(frag)->node) {
 				JFFS2_ERROR("REF_PRISTINE node at 0x%08x had a previous non-hole frag in the same page. Tell dwmw2.\n",
 					ref_offset(fn->raw));
 				bitched = 1;
 			}
 
-			if ((frag->ofs+frag->size) & (PAGE_CACHE_SIZE-1) && frag_next(frag)
-					&& frag_next(frag)->size < PAGE_CACHE_SIZE && frag_next(frag)->node) {
+			if ((frag->ofs+frag->size) & (PAGE_SIZE-1) && frag_next(frag)
+					&& frag_next(frag)->size < PAGE_SIZE && frag_next(frag)->node) {
 				JFFS2_ERROR("REF_PRISTINE node at 0x%08x (%08x-%08x) had a following non-hole frag in the same page. Tell dwmw2.\n",
 				       ref_offset(fn->raw), frag->ofs, frag->ofs+frag->size);
 				bitched = 1;
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index d211b8e18566..30c4c9ebb693 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -843,9 +843,14 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
 
 		pr_notice("%s(): Link succeeded, unlink failed (err %d). You now have a hard link\n",
 			  __func__, ret);
-		/* Might as well let the VFS know */
-		d_instantiate(new_dentry, d_inode(old_dentry));
-		ihold(d_inode(old_dentry));
+		/*
+		 * We can't keep the target in dcache after that.
+		 * For one thing, we can't afford dentry aliases for directories.
+		 * For another, if there was a victim, we _can't_ set new inode
+		 * for that sucker and we have to trigger mount eviction - the
+		 * caller won't do it on its own since we are returning an error.
+		 */
+		d_invalidate(new_dentry);
 		new_dir_i->i_mtime = new_dir_i->i_ctime = ITIME(now);
 		return ret;
 	}
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index f509f62e12f6..0e62dec3effc 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -39,10 +39,10 @@ int jffs2_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
 	if (ret)
 		return ret;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	/* Trigger GC to flush any pending writes for this inode */
 	jffs2_flush_wbuf_gc(c, inode->i_ino);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	return 0;
 }
@@ -87,14 +87,15 @@ static int jffs2_do_readpage_nolock (struct inode *inode, struct page *pg)
 	int ret;
 
 	jffs2_dbg(2, "%s(): ino #%lu, page at offset 0x%lx\n",
-		  __func__, inode->i_ino, pg->index << PAGE_CACHE_SHIFT);
+		  __func__, inode->i_ino, pg->index << PAGE_SHIFT);
 
 	BUG_ON(!PageLocked(pg));
 
 	pg_buf = kmap(pg);
 	/* FIXME: Can kmap fail? */
 
-	ret = jffs2_read_inode_range(c, f, pg_buf, pg->index << PAGE_CACHE_SHIFT, PAGE_CACHE_SIZE);
+	ret = jffs2_read_inode_range(c, f, pg_buf, pg->index << PAGE_SHIFT,
+				     PAGE_SIZE);
 
 	if (ret) {
 		ClearPageUptodate(pg);
@@ -137,39 +138,33 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 	struct page *pg;
 	struct inode *inode = mapping->host;
 	struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode);
-	struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
-	struct jffs2_raw_inode ri;
-	uint32_t alloc_len = 0;
-	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
-	uint32_t pageofs = index << PAGE_CACHE_SHIFT;
+	pgoff_t index = pos >> PAGE_SHIFT;
+	uint32_t pageofs = index << PAGE_SHIFT;
 	int ret = 0;
 
-	jffs2_dbg(1, "%s()\n", __func__);
-
-	if (pageofs > inode->i_size) {
-		ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len,
-					  ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE);
-		if (ret)
-			return ret;
-	}
-
-	mutex_lock(&f->sem);
 	pg = grab_cache_page_write_begin(mapping, index, flags);
-	if (!pg) {
-		if (alloc_len)
-			jffs2_complete_reservation(c);
-		mutex_unlock(&f->sem);
+	if (!pg)
 		return -ENOMEM;
-	}
 	*pagep = pg;
 
-	if (alloc_len) {
+	jffs2_dbg(1, "%s()\n", __func__);
+
+	if (pageofs > inode->i_size) {
 		/* Make new hole frag from old EOF to new page */
+		struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
+		struct jffs2_raw_inode ri;
 		struct jffs2_full_dnode *fn;
+		uint32_t alloc_len;
 
 		jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new page\n",
 			  (unsigned int)inode->i_size, pageofs);
 
+		ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len,
+					  ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE);
+		if (ret)
+			goto out_page;
+
+		mutex_lock(&f->sem);
 		memset(&ri, 0, sizeof(ri));
 
 		ri.magic = cpu_to_je16(JFFS2_MAGIC_BITMASK);
@@ -196,6 +191,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 		if (IS_ERR(fn)) {
 			ret = PTR_ERR(fn);
 			jffs2_complete_reservation(c);
+			mutex_unlock(&f->sem);
 			goto out_page;
 		}
 		ret = jffs2_add_full_dnode_to_inode(c, f, fn);
@@ -210,10 +206,12 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 			jffs2_mark_node_obsolete(c, fn->raw);
 			jffs2_free_full_dnode(fn);
 			jffs2_complete_reservation(c);
+			mutex_unlock(&f->sem);
 			goto out_page;
 		}
 		jffs2_complete_reservation(c);
 		inode->i_size = pageofs;
+		mutex_unlock(&f->sem);
 	}
 
 	/*
@@ -222,18 +220,18 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 	 * case of a short-copy.
 	 */
 	if (!PageUptodate(pg)) {
+		mutex_lock(&f->sem);
 		ret = jffs2_do_readpage_nolock(inode, pg);
+		mutex_unlock(&f->sem);
 		if (ret)
 			goto out_page;
 	}
-	mutex_unlock(&f->sem);
 	jffs2_dbg(1, "end write_begin(). pg->flags %lx\n", pg->flags);
 	return ret;
 
 out_page:
 	unlock_page(pg);
-	page_cache_release(pg);
-	mutex_unlock(&f->sem);
+	put_page(pg);
 	return ret;
 }
 
@@ -248,14 +246,14 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping,
 	struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode);
 	struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
 	struct jffs2_raw_inode *ri;
-	unsigned start = pos & (PAGE_CACHE_SIZE - 1);
+	unsigned start = pos & (PAGE_SIZE - 1);
 	unsigned end = start + copied;
 	unsigned aligned_start = start & ~3;
 	int ret = 0;
 	uint32_t writtenlen = 0;
 
 	jffs2_dbg(1, "%s(): ino #%lu, page at 0x%lx, range %d-%d, flags %lx\n",
-		  __func__, inode->i_ino, pg->index << PAGE_CACHE_SHIFT,
+		  __func__, inode->i_ino, pg->index << PAGE_SHIFT,
 		  start, end, pg->flags);
 
 	/* We need to avoid deadlock with page_cache_read() in
@@ -264,7 +262,7 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping,
 	   to re-lock it. */
 	BUG_ON(!PageUptodate(pg));
 
-	if (end == PAGE_CACHE_SIZE) {
+	if (end == PAGE_SIZE) {
 		/* When writing out the end of a page, write out the
 		   _whole_ page. This helps to reduce the number of
 		   nodes in files which have many short writes, like
@@ -278,7 +276,7 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping,
 		jffs2_dbg(1, "%s(): Allocation of raw inode failed\n",
 			  __func__);
 		unlock_page(pg);
-		page_cache_release(pg);
+		put_page(pg);
 		return -ENOMEM;
 	}
 
@@ -295,7 +293,7 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping,
 	kmap(pg);
 
 	ret = jffs2_write_inode_range(c, f, ri, page_address(pg) + aligned_start,
-				      (pg->index << PAGE_CACHE_SHIFT) + aligned_start,
+				      (pg->index << PAGE_SHIFT) + aligned_start,
 				      end - aligned_start, &writtenlen);
 
 	kunmap(pg);
@@ -332,6 +330,6 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping,
 	jffs2_dbg(1, "%s() returning %d\n",
 		  __func__, writtenlen > 0 ? writtenlen : ret);
 	unlock_page(pg);
-	page_cache_release(pg);
+	put_page(pg);
 	return writtenlen > 0 ? writtenlen : ret;
 }
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index 2caf1682036d..ae2ebb26b446 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -586,8 +586,8 @@ int jffs2_do_fill_super(struct super_block *sb, void *data, int silent)
 		goto out_root;
 
 	sb->s_maxbytes = 0xFFFFFFFF;
-	sb->s_blocksize = PAGE_CACHE_SIZE;
-	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
+	sb->s_blocksize = PAGE_SIZE;
+	sb->s_blocksize_bits = PAGE_SHIFT;
 	sb->s_magic = JFFS2_SUPER_MAGIC;
 	if (!(sb->s_flags & MS_RDONLY))
 		jffs2_start_garbage_collect_thread(c);
@@ -596,10 +596,7 @@ int jffs2_do_fill_super(struct super_block *sb, void *data, int silent)
 out_root:
 	jffs2_free_ino_caches(c);
 	jffs2_free_raw_node_refs(c);
-	if (jffs2_blocks_use_vmalloc(c))
-		vfree(c->blocks);
-	else
-		kfree(c->blocks);
+	kvfree(c->blocks);
  out_inohash:
 	jffs2_clear_xattr_subsystem(c);
 	kfree(c->inocache_list);
@@ -688,7 +685,7 @@ unsigned char *jffs2_gc_fetch_page(struct jffs2_sb_info *c,
 	struct inode *inode = OFNI_EDONI_2SFFJ(f);
 	struct page *pg;
 
-	pg = read_cache_page(inode->i_mapping, offset >> PAGE_CACHE_SHIFT,
+	pg = read_cache_page(inode->i_mapping, offset >> PAGE_SHIFT,
 			     (void *)jffs2_do_readpage_unlock, inode);
 	if (IS_ERR(pg))
 		return (void *)pg;
@@ -704,7 +701,7 @@ void jffs2_gc_release_page(struct jffs2_sb_info *c,
 	struct page *pg = (void *)*priv;
 
 	kunmap(pg);
-	page_cache_release(pg);
+	put_page(pg);
 }
 
 static int jffs2_flash_setup(struct jffs2_sb_info *c) {
diff --git a/fs/jffs2/gc.c b/fs/jffs2/gc.c
index 5a2dec2b064c..9ed0f26cf023 100644
--- a/fs/jffs2/gc.c
+++ b/fs/jffs2/gc.c
@@ -134,37 +134,59 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c)
 	if (mutex_lock_interruptible(&c->alloc_sem))
 		return -EINTR;
 
+
 	for (;;) {
+		/* We can't start doing GC until we've finished checking
+		   the node CRCs etc. */
+		int bucket, want_ino;
+
 		spin_lock(&c->erase_completion_lock);
 		if (!c->unchecked_size)
 			break;
-
-		/* We can't start doing GC yet. We haven't finished checking
-		   the node CRCs etc. Do it now. */
-
-		/* checked_ino is protected by the alloc_sem */
-		if (c->checked_ino > c->highest_ino && xattr) {
-			pr_crit("Checked all inodes but still 0x%x bytes of unchecked space?\n",
-				c->unchecked_size);
-			jffs2_dbg_dump_block_lists_nolock(c);
-			spin_unlock(&c->erase_completion_lock);
-			mutex_unlock(&c->alloc_sem);
-			return -ENOSPC;
-		}
-
 		spin_unlock(&c->erase_completion_lock);
 
 		if (!xattr)
 			xattr = jffs2_verify_xattr(c);
 
 		spin_lock(&c->inocache_lock);
+		/* Instead of doing the inodes in numeric order, doing a lookup
+		 * in the hash for each possible number, just walk the hash
+		 * buckets of *existing* inodes. This means that we process
+		 * them out-of-order, but it can be a lot faster if there's
+		 * a sparse inode# space. Which there often is. */
+		want_ino = c->check_ino;
+		for (bucket = c->check_ino % c->inocache_hashsize ; bucket < c->inocache_hashsize; bucket++) {
+			for (ic = c->inocache_list[bucket]; ic; ic = ic->next) {
+				if (ic->ino < want_ino)
+					continue;
+
+				if (ic->state != INO_STATE_CHECKEDABSENT &&
+				    ic->state != INO_STATE_PRESENT)
+					goto got_next; /* with inocache_lock held */
+
+				jffs2_dbg(1, "Skipping ino #%u already checked\n",
+					  ic->ino);
+			}
+			want_ino = 0;
+		}
 
-		ic = jffs2_get_ino_cache(c, c->checked_ino++);
+		/* Point c->check_ino past the end of the last bucket. */
+		c->check_ino = ((c->highest_ino + c->inocache_hashsize + 1) &
+				~c->inocache_hashsize) - 1;
 
-		if (!ic) {
-			spin_unlock(&c->inocache_lock);
-			continue;
-		}
+		spin_unlock(&c->inocache_lock);
+
+		pr_crit("Checked all inodes but still 0x%x bytes of unchecked space?\n",
+			c->unchecked_size);
+		jffs2_dbg_dump_block_lists_nolock(c);
+		mutex_unlock(&c->alloc_sem);
+		return -ENOSPC;
+
+	got_next:
+		/* For next time round the loop, we want c->checked_ino to indicate
+		 * the *next* one we want to check. And since we're walking the
+		 * buckets rather than doing it sequentially, it's: */
+		c->check_ino = ic->ino + c->inocache_hashsize;
 
 		if (!ic->pino_nlink) {
 			jffs2_dbg(1, "Skipping check of ino #%d with nlink/pino zero\n",
@@ -176,8 +198,6 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c)
 		switch(ic->state) {
 		case INO_STATE_CHECKEDABSENT:
 		case INO_STATE_PRESENT:
-			jffs2_dbg(1, "Skipping ino #%u already checked\n",
-				  ic->ino);
 			spin_unlock(&c->inocache_lock);
 			continue;
 
@@ -196,7 +216,7 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c)
 				  ic->ino);
 			/* We need to come back again for the _same_ inode. We've
 			 made no progress in this case, but that should be OK */
-			c->checked_ino--;
+			c->check_ino = ic->ino;
 
 			mutex_unlock(&c->alloc_sem);
 			sleep_on_spinunlock(&c->inocache_wq, &c->inocache_lock);
@@ -532,7 +552,7 @@ static int jffs2_garbage_collect_live(struct jffs2_sb_info *c,  struct jffs2_era
 				goto upnout;
 		}
 		/* We found a datanode. Do the GC */
-		if((start >> PAGE_CACHE_SHIFT) < ((end-1) >> PAGE_CACHE_SHIFT)) {
+		if((start >> PAGE_SHIFT) < ((end-1) >> PAGE_SHIFT)) {
 			/* It crosses a page boundary. Therefore, it must be a hole. */
 			ret = jffs2_garbage_collect_hole(c, jeb, f, fn, start, end);
 		} else {
@@ -1172,8 +1192,8 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era
 		struct jffs2_node_frag *frag;
 		uint32_t min, max;
 
-		min = start & ~(PAGE_CACHE_SIZE-1);
-		max = min + PAGE_CACHE_SIZE;
+		min = start & ~(PAGE_SIZE-1);
+		max = min + PAGE_SIZE;
 
 		frag = jffs2_lookup_node_frag(&f->fragtree, start);
 
@@ -1296,14 +1316,17 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era
 		BUG_ON(start > orig_start);
 	}
 
-	/* First, use readpage() to read the appropriate page into the page cache */
-	/* Q: What happens if we actually try to GC the _same_ page for which commit_write()
-	 *    triggered garbage collection in the first place?
-	 * A: I _think_ it's OK. read_cache_page shouldn't deadlock, we'll write out the
-	 *    page OK. We'll actually write it out again in commit_write, which is a little
-	 *    suboptimal, but at least we're correct.
-	 */
+	/* The rules state that we must obtain the page lock *before* f->sem, so
+	 * drop f->sem temporarily. Since we also hold c->alloc_sem, nothing's
+	 * actually going to *change* so we're safe; we only allow reading.
+	 *
+	 * It is important to note that jffs2_write_begin() will ensure that its
+	 * page is marked Uptodate before allocating space. That means that if we
+	 * end up here trying to GC the *same* page that jffs2_write_begin() is
+	 * trying to write out, read_cache_page() will not deadlock. */
+	mutex_unlock(&f->sem);
 	pg_ptr = jffs2_gc_fetch_page(c, f, start, &pg);
+	mutex_lock(&f->sem);
 
 	if (IS_ERR(pg_ptr)) {
 		pr_warn("read_cache_page() returned error: %ld\n",
@@ -1328,7 +1351,7 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era
 		cdatalen = min_t(uint32_t, alloclen - sizeof(ri), end - offset);
 		datalen = end - offset;
 
-		writebuf = pg_ptr + (offset & (PAGE_CACHE_SIZE -1));
+		writebuf = pg_ptr + (offset & (PAGE_SIZE -1));
 
 		comprtype = jffs2_compress(c, f, writebuf, &comprbuf, &datalen, &cdatalen);
 
diff --git a/fs/jffs2/jffs2_fs_sb.h b/fs/jffs2/jffs2_fs_sb.h
index 046fee8b6e9b..778275f48a87 100644
--- a/fs/jffs2/jffs2_fs_sb.h
+++ b/fs/jffs2/jffs2_fs_sb.h
@@ -49,7 +49,7 @@ struct jffs2_sb_info {
 	struct mtd_info *mtd;
 
 	uint32_t highest_ino;
-	uint32_t checked_ino;
+	uint32_t check_ino;		/* *NEXT* inode to be checked */
 
 	unsigned int flags;
 
diff --git a/fs/jffs2/nodelist.c b/fs/jffs2/nodelist.c
index 9a5449bc3afb..b86c78d178c6 100644
--- a/fs/jffs2/nodelist.c
+++ b/fs/jffs2/nodelist.c
@@ -90,7 +90,7 @@ uint32_t jffs2_truncate_fragtree(struct jffs2_sb_info *c, struct rb_root *list,
 
 	/* If the last fragment starts at the RAM page boundary, it is
 	 * REF_PRISTINE irrespective of its size. */
-	if (frag->node && (frag->ofs & (PAGE_CACHE_SIZE - 1)) == 0) {
+	if (frag->node && (frag->ofs & (PAGE_SIZE - 1)) == 0) {
 		dbg_fragtree2("marking the last fragment 0x%08x-0x%08x REF_PRISTINE.\n",
 			frag->ofs, frag->ofs + frag->size);
 		frag->node->raw->flash_offset = ref_offset(frag->node->raw) | REF_PRISTINE;
@@ -237,7 +237,7 @@ static int jffs2_add_frag_to_fragtree(struct jffs2_sb_info *c, struct rb_root *r
 		   If so, both 'this' and the new node get marked REF_NORMAL so
 		   the GC can take a look.
 		*/
-		if (lastend && (lastend-1) >> PAGE_CACHE_SHIFT == newfrag->ofs >> PAGE_CACHE_SHIFT) {
+		if (lastend && (lastend-1) >> PAGE_SHIFT == newfrag->ofs >> PAGE_SHIFT) {
 			if (this->node)
 				mark_ref_normal(this->node->raw);
 			mark_ref_normal(newfrag->node->raw);
@@ -382,7 +382,7 @@ int jffs2_add_full_dnode_to_inode(struct jffs2_sb_info *c, struct jffs2_inode_in
 
 	/* If we now share a page with other nodes, mark either previous
 	   or next node REF_NORMAL, as appropriate.  */
-	if (newfrag->ofs & (PAGE_CACHE_SIZE-1)) {
+	if (newfrag->ofs & (PAGE_SIZE-1)) {
 		struct jffs2_node_frag *prev = frag_prev(newfrag);
 
 		mark_ref_normal(fn->raw);
@@ -391,7 +391,7 @@ int jffs2_add_full_dnode_to_inode(struct jffs2_sb_info *c, struct jffs2_inode_in
 			mark_ref_normal(prev->node->raw);
 	}
 
-	if ((newfrag->ofs+newfrag->size) & (PAGE_CACHE_SIZE-1)) {
+	if ((newfrag->ofs+newfrag->size) & (PAGE_SIZE-1)) {
 		struct jffs2_node_frag *next = frag_next(newfrag);
 
 		if (next) {
diff --git a/fs/jffs2/nodelist.h b/fs/jffs2/nodelist.h
index fa35ff79ab35..0637271f3770 100644
--- a/fs/jffs2/nodelist.h
+++ b/fs/jffs2/nodelist.h
@@ -194,6 +194,7 @@ struct jffs2_inode_cache {
 #define INO_STATE_CLEARING	6	/* In clear_inode() */
 
 #define INO_FLAGS_XATTR_CHECKED	0x01	/* has no duplicate xattr_ref */
+#define INO_FLAGS_IS_DIR	0x02	/* is a directory */
 
 #define RAWNODE_CLASS_INODE_CACHE	0
 #define RAWNODE_CLASS_XATTR_DATUM	1
@@ -249,7 +250,10 @@ struct jffs2_readinode_info
 
 struct jffs2_full_dirent
 {
-	struct jffs2_raw_node_ref *raw;
+	union {
+		struct jffs2_raw_node_ref *raw;
+		struct jffs2_inode_cache *ic; /* Just during part of build */
+	};
 	struct jffs2_full_dirent *next;
 	uint32_t version;
 	uint32_t ino; /* == zero for unlink */
diff --git a/fs/jffs2/nodemgmt.c b/fs/jffs2/nodemgmt.c
index b6bd4affd9ad..cda0774c2c9c 100644
--- a/fs/jffs2/nodemgmt.c
+++ b/fs/jffs2/nodemgmt.c
@@ -846,8 +846,8 @@ int jffs2_thread_should_wake(struct jffs2_sb_info *c)
 		return 1;
 
 	if (c->unchecked_size) {
-		jffs2_dbg(1, "jffs2_thread_should_wake(): unchecked_size %d, checked_ino #%d\n",
-			  c->unchecked_size, c->checked_ino);
+		jffs2_dbg(1, "jffs2_thread_should_wake(): unchecked_size %d, check_ino #%d\n",
+			  c->unchecked_size, c->check_ino);
 		return 1;
 	}
 
diff --git a/fs/jffs2/security.c b/fs/jffs2/security.c
index d4b43fb7adb1..7a28facd7175 100644
--- a/fs/jffs2/security.c
+++ b/fs/jffs2/security.c
@@ -48,42 +48,24 @@ int jffs2_init_security(struct inode *inode, struct inode *dir,
 }
 
 /* ---- XATTR Handler for "security.*" ----------------- */
-static int jffs2_security_getxattr(struct dentry *dentry, const char *name,
-				   void *buffer, size_t size, int type)
+static int jffs2_security_getxattr(const struct xattr_handler *handler,
+				   struct dentry *dentry, const char *name,
+				   void *buffer, size_t size)
 {
-	if (!strcmp(name, ""))
-		return -EINVAL;
-
 	return do_jffs2_getxattr(d_inode(dentry), JFFS2_XPREFIX_SECURITY,
 				 name, buffer, size);
 }
 
-static int jffs2_security_setxattr(struct dentry *dentry, const char *name,
-		const void *buffer, size_t size, int flags, int type)
+static int jffs2_security_setxattr(const struct xattr_handler *handler,
+				   struct dentry *dentry, const char *name,
+				   const void *buffer, size_t size, int flags)
 {
-	if (!strcmp(name, ""))
-		return -EINVAL;
-
 	return do_jffs2_setxattr(d_inode(dentry), JFFS2_XPREFIX_SECURITY,
 				 name, buffer, size, flags);
 }
 
-static size_t jffs2_security_listxattr(struct dentry *dentry, char *list,
-		size_t list_size, const char *name, size_t name_len, int type)
-{
-	size_t retlen = XATTR_SECURITY_PREFIX_LEN + name_len + 1;
-
-	if (list && retlen <= list_size) {
-		strcpy(list, XATTR_SECURITY_PREFIX);
-		strcpy(list + XATTR_SECURITY_PREFIX_LEN, name);
-	}
-
-	return retlen;
-}
-
 const struct xattr_handler jffs2_security_xattr_handler = {
 	.prefix = XATTR_SECURITY_PREFIX,
-	.list = jffs2_security_listxattr,
 	.set = jffs2_security_setxattr,
 	.get = jffs2_security_getxattr
 };
diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c
index d86c5e3176a1..0a9a114bb9d1 100644
--- a/fs/jffs2/super.c
+++ b/fs/jffs2/super.c
@@ -331,10 +331,7 @@ static void jffs2_put_super (struct super_block *sb)
 
 	jffs2_free_ino_caches(c);
 	jffs2_free_raw_node_refs(c);
-	if (jffs2_blocks_use_vmalloc(c))
-		vfree(c->blocks);
-	else
-		kfree(c->blocks);
+	kvfree(c->blocks);
 	jffs2_flash_cleanup(c);
 	kfree(c->inocache_list);
 	jffs2_clear_xattr_subsystem(c);
@@ -387,7 +384,7 @@ static int __init init_jffs2_fs(void)
 	jffs2_inode_cachep = kmem_cache_create("jffs2_i",
 					     sizeof(struct jffs2_inode_info),
 					     0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD),
+						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
 					     jffs2_i_init_once);
 	if (!jffs2_inode_cachep) {
 		pr_err("error: Failed to initialise inode cache\n");
diff --git a/fs/jffs2/symlink.c b/fs/jffs2/symlink.c
index 8ce2f240125b..2cabd649d4fb 100644
--- a/fs/jffs2/symlink.c
+++ b/fs/jffs2/symlink.c
@@ -14,7 +14,7 @@
 const struct inode_operations jffs2_symlink_inode_operations =
 {
 	.readlink =	generic_readlink,
-	.follow_link =	simple_follow_link,
+	.get_link =	simple_get_link,
 	.setattr =	jffs2_setattr,
 	.setxattr =	jffs2_setxattr,
 	.getxattr =	jffs2_getxattr,
diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c
index 63f31c0733c5..b25d28a21212 100644
--- a/fs/jffs2/wbuf.c
+++ b/fs/jffs2/wbuf.c
@@ -1153,7 +1153,7 @@ static struct jffs2_sb_info *work_to_sb(struct work_struct *work)
 {
 	struct delayed_work *dwork;
 
-	dwork = container_of(work, struct delayed_work, work);
+	dwork = to_delayed_work(work);
 	return container_of(dwork, struct jffs2_sb_info, wbuf_dwork);
 }
 
@@ -1183,22 +1183,20 @@ void jffs2_dirty_trigger(struct jffs2_sb_info *c)
 
 int jffs2_nand_flash_setup(struct jffs2_sb_info *c)
 {
-	struct nand_ecclayout *oinfo = c->mtd->ecclayout;
-
 	if (!c->mtd->oobsize)
 		return 0;
 
 	/* Cleanmarker is out-of-band, so inline size zero */
 	c->cleanmarker_size = 0;
 
-	if (!oinfo || oinfo->oobavail == 0) {
+	if (c->mtd->oobavail == 0) {
 		pr_err("inconsistent device description\n");
 		return -EINVAL;
 	}
 
 	jffs2_dbg(1, "using OOB on NAND\n");
 
-	c->oobavail = oinfo->oobavail;
+	c->oobavail = c->mtd->oobavail;
 
 	/* Initialise write buffer */
 	init_rwsem(&c->wbuf_sem);
@@ -1264,7 +1262,7 @@ int jffs2_dataflash_setup(struct jffs2_sb_info *c) {
 	if ((c->flash_size % c->sector_size) != 0) {
 		c->flash_size = (c->flash_size / c->sector_size) * c->sector_size;
 		pr_warn("flash size adjusted to %dKiB\n", c->flash_size);
-	};
+	}
 
 	c->wbuf_ofs = 0xFFFFFFFF;
 	c->wbuf = kmalloc(c->wbuf_pagesize, GFP_KERNEL);
diff --git a/fs/jffs2/write.c b/fs/jffs2/write.c
index b634de4c8101..7fb187ab2682 100644
--- a/fs/jffs2/write.c
+++ b/fs/jffs2/write.c
@@ -172,8 +172,8 @@ struct jffs2_full_dnode *jffs2_write_dnode(struct jffs2_sb_info *c, struct jffs2
 	   beginning of a page and runs to the end of the file, or if
 	   it's a hole node, mark it REF_PRISTINE, else REF_NORMAL.
 	*/
-	if ((je32_to_cpu(ri->dsize) >= PAGE_CACHE_SIZE) ||
-	    ( ((je32_to_cpu(ri->offset)&(PAGE_CACHE_SIZE-1))==0) &&
+	if ((je32_to_cpu(ri->dsize) >= PAGE_SIZE) ||
+	    ( ((je32_to_cpu(ri->offset)&(PAGE_SIZE-1))==0) &&
 	      (je32_to_cpu(ri->dsize)+je32_to_cpu(ri->offset) ==  je32_to_cpu(ri->isize)))) {
 		flash_ofs |= REF_PRISTINE;
 	} else {
@@ -366,7 +366,8 @@ int jffs2_write_inode_range(struct jffs2_sb_info *c, struct jffs2_inode_info *f,
 			break;
 		}
 		mutex_lock(&f->sem);
-		datalen = min_t(uint32_t, writelen, PAGE_CACHE_SIZE - (offset & (PAGE_CACHE_SIZE-1)));
+		datalen = min_t(uint32_t, writelen,
+				PAGE_SIZE - (offset & (PAGE_SIZE-1)));
 		cdatalen = min_t(uint32_t, alloclen - sizeof(*ri), datalen);
 
 		comprtype = jffs2_compress(c, f, buf, &comprbuf, &datalen, &cdatalen);
diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c
index f092fee5be50..da3e18503c65 100644
--- a/fs/jffs2/xattr.c
+++ b/fs/jffs2/xattr.c
@@ -967,7 +967,8 @@ ssize_t jffs2_listxattr(struct dentry *dentry, char *buffer, size_t size)
 	struct jffs2_xattr_ref *ref, **pref;
 	struct jffs2_xattr_datum *xd;
 	const struct xattr_handler *xhandle;
-	ssize_t len, rc;
+	const char *prefix;
+	ssize_t prefix_len, len, rc;
 	int retry = 0;
 
 	rc = check_xattr_ref_inode(c, ic);
@@ -998,17 +999,23 @@ ssize_t jffs2_listxattr(struct dentry *dentry, char *buffer, size_t size)
 			}
 		}
 		xhandle = xprefix_to_handler(xd->xprefix);
-		if (!xhandle)
+		if (!xhandle || (xhandle->list && !xhandle->list(dentry)))
 			continue;
+		prefix = xhandle->prefix ?: xhandle->name;
+		prefix_len = strlen(prefix);
+		rc = prefix_len + xd->name_len + 1;
+
 		if (buffer) {
-			rc = xhandle->list(dentry, buffer+len, size-len,
-					   xd->xname, xd->name_len, xd->flags);
-		} else {
-			rc = xhandle->list(dentry, NULL, 0, xd->xname,
-					   xd->name_len, xd->flags);
+			if (rc > size - len) {
+				rc = -ERANGE;
+				goto out;
+			}
+			memcpy(buffer, prefix, prefix_len);
+			buffer += prefix_len;
+			memcpy(buffer, xd->xname, xd->name_len);
+			buffer += xd->name_len;
+			*buffer++ = 0;
 		}
-		if (rc < 0)
-			goto out;
 		len += rc;
 	}
 	rc = len;
diff --git a/fs/jffs2/xattr_trusted.c b/fs/jffs2/xattr_trusted.c
index ceaf9c693225..b2555ef07a12 100644
--- a/fs/jffs2/xattr_trusted.c
+++ b/fs/jffs2/xattr_trusted.c
@@ -16,35 +16,25 @@
 #include <linux/mtd/mtd.h>
 #include "nodelist.h"
 
-static int jffs2_trusted_getxattr(struct dentry *dentry, const char *name,
-		void *buffer, size_t size, int type)
+static int jffs2_trusted_getxattr(const struct xattr_handler *handler,
+				  struct dentry *dentry, const char *name,
+				  void *buffer, size_t size)
 {
-	if (!strcmp(name, ""))
-		return -EINVAL;
 	return do_jffs2_getxattr(d_inode(dentry), JFFS2_XPREFIX_TRUSTED,
 				 name, buffer, size);
 }
 
-static int jffs2_trusted_setxattr(struct dentry *dentry, const char *name,
-		const void *buffer, size_t size, int flags, int type)
+static int jffs2_trusted_setxattr(const struct xattr_handler *handler,
+				  struct dentry *dentry, const char *name,
+				  const void *buffer, size_t size, int flags)
 {
-	if (!strcmp(name, ""))
-		return -EINVAL;
 	return do_jffs2_setxattr(d_inode(dentry), JFFS2_XPREFIX_TRUSTED,
 				 name, buffer, size, flags);
 }
 
-static size_t jffs2_trusted_listxattr(struct dentry *dentry, char *list,
-		size_t list_size, const char *name, size_t name_len, int type)
+static bool jffs2_trusted_listxattr(struct dentry *dentry)
 {
-	size_t retlen = XATTR_TRUSTED_PREFIX_LEN + name_len + 1;
-
-	if (list && retlen<=list_size) {
-		strcpy(list, XATTR_TRUSTED_PREFIX);
-		strcpy(list + XATTR_TRUSTED_PREFIX_LEN, name);
-	}
-
-	return retlen;
+	return capable(CAP_SYS_ADMIN);
 }
 
 const struct xattr_handler jffs2_trusted_xattr_handler = {
diff --git a/fs/jffs2/xattr_user.c b/fs/jffs2/xattr_user.c
index a71391eba514..539bd630b5e4 100644
--- a/fs/jffs2/xattr_user.c
+++ b/fs/jffs2/xattr_user.c
@@ -16,40 +16,24 @@
 #include <linux/mtd/mtd.h>
 #include "nodelist.h"
 
-static int jffs2_user_getxattr(struct dentry *dentry, const char *name,
-			       void *buffer, size_t size, int type)
+static int jffs2_user_getxattr(const struct xattr_handler *handler,
+			       struct dentry *dentry, const char *name,
+			       void *buffer, size_t size)
 {
-	if (!strcmp(name, ""))
-		return -EINVAL;
 	return do_jffs2_getxattr(d_inode(dentry), JFFS2_XPREFIX_USER,
 				 name, buffer, size);
 }
 
-static int jffs2_user_setxattr(struct dentry *dentry, const char *name,
-		const void *buffer, size_t size, int flags, int type)
+static int jffs2_user_setxattr(const struct xattr_handler *handler,
+			       struct dentry *dentry, const char *name,
+			       const void *buffer, size_t size, int flags)
 {
-	if (!strcmp(name, ""))
-		return -EINVAL;
 	return do_jffs2_setxattr(d_inode(dentry), JFFS2_XPREFIX_USER,
 				 name, buffer, size, flags);
 }
 
-static size_t jffs2_user_listxattr(struct dentry *dentry, char *list,
-		size_t list_size, const char *name, size_t name_len, int type)
-{
-	size_t retlen = XATTR_USER_PREFIX_LEN + name_len + 1;
-
-	if (list && retlen <= list_size) {
-		strcpy(list, XATTR_USER_PREFIX);
-		strcpy(list + XATTR_USER_PREFIX_LEN, name);
-	}
-
-	return retlen;
-}
-
 const struct xattr_handler jffs2_user_xattr_handler = {
 	.prefix = XATTR_USER_PREFIX,
-	.list = jffs2_user_listxattr,
 	.set = jffs2_user_setxattr,
 	.get = jffs2_user_getxattr
 };
diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c
index 0c8ca830b113..49456853e9de 100644
--- a/fs/jfs/acl.c
+++ b/fs/jfs/acl.c
@@ -40,10 +40,10 @@ struct posix_acl *jfs_get_acl(struct inode *inode, int type)
 
 	switch(type) {
 		case ACL_TYPE_ACCESS:
-			ea_name = POSIX_ACL_XATTR_ACCESS;
+			ea_name = XATTR_NAME_POSIX_ACL_ACCESS;
 			break;
 		case ACL_TYPE_DEFAULT:
-			ea_name = POSIX_ACL_XATTR_DEFAULT;
+			ea_name = XATTR_NAME_POSIX_ACL_DEFAULT;
 			break;
 		default:
 			return ERR_PTR(-EINVAL);
@@ -82,7 +82,7 @@ static int __jfs_set_acl(tid_t tid, struct inode *inode, int type,
 
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		ea_name = POSIX_ACL_XATTR_ACCESS;
+		ea_name = XATTR_NAME_POSIX_ACL_ACCESS;
 		if (acl) {
 			rc = posix_acl_equiv_mode(acl, &inode->i_mode);
 			if (rc < 0)
@@ -94,7 +94,7 @@ static int __jfs_set_acl(tid_t tid, struct inode *inode, int type,
 		}
 		break;
 	case ACL_TYPE_DEFAULT:
-		ea_name = POSIX_ACL_XATTR_DEFAULT;
+		ea_name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		break;
 	default:
 		return -EINVAL;
diff --git a/fs/jfs/file.c b/fs/jfs/file.c
index 0e026a7bdcd4..4ce7735dd042 100644
--- a/fs/jfs/file.c
+++ b/fs/jfs/file.c
@@ -38,17 +38,17 @@ int jfs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	if (rc)
 		return rc;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	if (!(inode->i_state & I_DIRTY_ALL) ||
 	    (datasync && !(inode->i_state & I_DIRTY_DATASYNC))) {
 		/* Make sure committed changes hit the disk */
 		jfs_flush_journal(JFS_SBI(inode->i_sb)->log, 1);
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 		return rc;
 	}
 
 	rc |= jfs_commit_inode(inode, 1);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	return rc ? -EIO : 0;
 }
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index 41aa3ca6a6a4..9d9bae63ae2a 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -60,6 +60,7 @@ struct inode *jfs_iget(struct super_block *sb, unsigned long ino)
 	} else if (S_ISLNK(inode->i_mode)) {
 		if (inode->i_size >= IDATASIZE) {
 			inode->i_op = &page_symlink_inode_operations;
+			inode_nohighmem(inode);
 			inode->i_mapping->a_ops = &jfs_aops;
 		} else {
 			inode->i_op = &jfs_fast_symlink_inode_operations;
diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c
index 8db8b7d61e40..8653cac7e12e 100644
--- a/fs/jfs/ioctl.c
+++ b/fs/jfs/ioctl.c
@@ -96,7 +96,7 @@ long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		}
 
 		/* Lock against other parallel changes of flags */
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 
 		jfs_get_inode_flags(jfs_inode);
 		oldflags = jfs_inode->mode2;
@@ -109,7 +109,7 @@ long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 			((flags ^ oldflags) &
 			(JFS_APPEND_FL | JFS_IMMUTABLE_FL))) {
 			if (!capable(CAP_LINUX_IMMUTABLE)) {
-				mutex_unlock(&inode->i_mutex);
+				inode_unlock(inode);
 				err = -EPERM;
 				goto setflags_out;
 			}
@@ -120,7 +120,7 @@ long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		jfs_inode->mode2 = flags;
 
 		jfs_set_inode_flags(inode);
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 		inode->i_ctime = CURRENT_TIME_SEC;
 		mark_inode_dirty(inode);
 setflags_out:
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index a69bdf2a1085..a270cb7ff4e0 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -1835,17 +1835,16 @@ static int lbmLogInit(struct jfs_log * log)
 	for (i = 0; i < LOGPAGES;) {
 		char *buffer;
 		uint offset;
-		struct page *page;
+		struct page *page = alloc_page(GFP_KERNEL | __GFP_ZERO);
 
-		buffer = (char *) get_zeroed_page(GFP_KERNEL);
-		if (buffer == NULL)
+		if (!page)
 			goto error;
-		page = virt_to_page(buffer);
+		buffer = page_address(page);
 		for (offset = 0; offset < PAGE_SIZE; offset += LOGPSIZE) {
 			lbuf = kmalloc(sizeof(struct lbuf), GFP_KERNEL);
 			if (lbuf == NULL) {
 				if (offset == 0)
-					free_page((unsigned long) buffer);
+					__free_page(page);
 				goto error;
 			}
 			if (offset) /* we already have one reference */
diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c
index a3eb316b1ac3..b60e015cc757 100644
--- a/fs/jfs/jfs_metapage.c
+++ b/fs/jfs/jfs_metapage.c
@@ -80,7 +80,7 @@ static inline void lock_metapage(struct metapage *mp)
 static struct kmem_cache *metapage_cache;
 static mempool_t *metapage_mempool;
 
-#define MPS_PER_PAGE (PAGE_CACHE_SIZE >> L2PSIZE)
+#define MPS_PER_PAGE (PAGE_SIZE >> L2PSIZE)
 
 #if MPS_PER_PAGE > 1
 
@@ -316,7 +316,7 @@ static void last_write_complete(struct page *page)
 	struct metapage *mp;
 	unsigned int offset;
 
-	for (offset = 0; offset < PAGE_CACHE_SIZE; offset += PSIZE) {
+	for (offset = 0; offset < PAGE_SIZE; offset += PSIZE) {
 		mp = page_to_mp(page, offset);
 		if (mp && test_bit(META_io, &mp->flag)) {
 			if (mp->lsn)
@@ -366,12 +366,12 @@ static int metapage_writepage(struct page *page, struct writeback_control *wbc)
 	int bad_blocks = 0;
 
 	page_start = (sector_t)page->index <<
-		     (PAGE_CACHE_SHIFT - inode->i_blkbits);
+		     (PAGE_SHIFT - inode->i_blkbits);
 	BUG_ON(!PageLocked(page));
 	BUG_ON(PageWriteback(page));
 	set_page_writeback(page);
 
-	for (offset = 0; offset < PAGE_CACHE_SIZE; offset += PSIZE) {
+	for (offset = 0; offset < PAGE_SIZE; offset += PSIZE) {
 		mp = page_to_mp(page, offset);
 
 		if (!mp || !test_bit(META_dirty, &mp->flag))
@@ -416,7 +416,7 @@ static int metapage_writepage(struct page *page, struct writeback_control *wbc)
 			bio = NULL;
 		} else
 			inc_io(page);
-		xlen = (PAGE_CACHE_SIZE - offset) >> inode->i_blkbits;
+		xlen = (PAGE_SIZE - offset) >> inode->i_blkbits;
 		pblock = metapage_get_blocks(inode, lblock, &xlen);
 		if (!pblock) {
 			printk(KERN_ERR "JFS: metapage_get_blocks failed\n");
@@ -485,7 +485,7 @@ static int metapage_readpage(struct file *fp, struct page *page)
 	struct inode *inode = page->mapping->host;
 	struct bio *bio = NULL;
 	int block_offset;
-	int blocks_per_page = PAGE_CACHE_SIZE >> inode->i_blkbits;
+	int blocks_per_page = PAGE_SIZE >> inode->i_blkbits;
 	sector_t page_start;	/* address of page in fs blocks */
 	sector_t pblock;
 	int xlen;
@@ -494,7 +494,7 @@ static int metapage_readpage(struct file *fp, struct page *page)
 
 	BUG_ON(!PageLocked(page));
 	page_start = (sector_t)page->index <<
-		     (PAGE_CACHE_SHIFT - inode->i_blkbits);
+		     (PAGE_SHIFT - inode->i_blkbits);
 
 	block_offset = 0;
 	while (block_offset < blocks_per_page) {
@@ -542,7 +542,7 @@ static int metapage_releasepage(struct page *page, gfp_t gfp_mask)
 	int ret = 1;
 	int offset;
 
-	for (offset = 0; offset < PAGE_CACHE_SIZE; offset += PSIZE) {
+	for (offset = 0; offset < PAGE_SIZE; offset += PSIZE) {
 		mp = page_to_mp(page, offset);
 
 		if (!mp)
@@ -568,7 +568,7 @@ static int metapage_releasepage(struct page *page, gfp_t gfp_mask)
 static void metapage_invalidatepage(struct page *page, unsigned int offset,
 				    unsigned int length)
 {
-	BUG_ON(offset || length < PAGE_CACHE_SIZE);
+	BUG_ON(offset || length < PAGE_SIZE);
 
 	BUG_ON(PageWriteback(page));
 
@@ -599,10 +599,10 @@ struct metapage *__get_metapage(struct inode *inode, unsigned long lblock,
 		 inode->i_ino, lblock, absolute);
 
 	l2bsize = inode->i_blkbits;
-	l2BlocksPerPage = PAGE_CACHE_SHIFT - l2bsize;
+	l2BlocksPerPage = PAGE_SHIFT - l2bsize;
 	page_index = lblock >> l2BlocksPerPage;
 	page_offset = (lblock - (page_index << l2BlocksPerPage)) << l2bsize;
-	if ((page_offset + size) > PAGE_CACHE_SIZE) {
+	if ((page_offset + size) > PAGE_SIZE) {
 		jfs_err("MetaData crosses page boundary!!");
 		jfs_err("lblock = %lx, size  = %d", lblock, size);
 		dump_stack();
@@ -621,7 +621,7 @@ struct metapage *__get_metapage(struct inode *inode, unsigned long lblock,
 		mapping = inode->i_mapping;
 	}
 
-	if (new && (PSIZE == PAGE_CACHE_SIZE)) {
+	if (new && (PSIZE == PAGE_SIZE)) {
 		page = grab_cache_page(mapping, page_index);
 		if (!page) {
 			jfs_err("grab_cache_page failed!");
@@ -693,7 +693,7 @@ unlock:
 void grab_metapage(struct metapage * mp)
 {
 	jfs_info("grab_metapage: mp = 0x%p", mp);
-	page_cache_get(mp->page);
+	get_page(mp->page);
 	lock_page(mp->page);
 	mp->count++;
 	lock_metapage(mp);
@@ -706,12 +706,12 @@ void force_metapage(struct metapage *mp)
 	jfs_info("force_metapage: mp = 0x%p", mp);
 	set_bit(META_forcewrite, &mp->flag);
 	clear_bit(META_sync, &mp->flag);
-	page_cache_get(page);
+	get_page(page);
 	lock_page(page);
 	set_page_dirty(page);
 	write_one_page(page, 1);
 	clear_bit(META_forcewrite, &mp->flag);
-	page_cache_release(page);
+	put_page(page);
 }
 
 void hold_metapage(struct metapage *mp)
@@ -726,7 +726,7 @@ void put_metapage(struct metapage *mp)
 		unlock_page(mp->page);
 		return;
 	}
-	page_cache_get(mp->page);
+	get_page(mp->page);
 	mp->count++;
 	lock_metapage(mp);
 	unlock_page(mp->page);
@@ -746,7 +746,7 @@ void release_metapage(struct metapage * mp)
 	assert(mp->count);
 	if (--mp->count || mp->nohomeok) {
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 		return;
 	}
 
@@ -764,13 +764,13 @@ void release_metapage(struct metapage * mp)
 	drop_metapage(page, mp);
 
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 }
 
 void __invalidate_metapages(struct inode *ip, s64 addr, int len)
 {
 	sector_t lblock;
-	int l2BlocksPerPage = PAGE_CACHE_SHIFT - ip->i_blkbits;
+	int l2BlocksPerPage = PAGE_SHIFT - ip->i_blkbits;
 	int BlocksPerPage = 1 << l2BlocksPerPage;
 	/* All callers are interested in block device's mapping */
 	struct address_space *mapping =
@@ -788,7 +788,7 @@ void __invalidate_metapages(struct inode *ip, s64 addr, int len)
 		page = find_lock_page(mapping, lblock >> l2BlocksPerPage);
 		if (!page)
 			continue;
-		for (offset = 0; offset < PAGE_CACHE_SIZE; offset += PSIZE) {
+		for (offset = 0; offset < PAGE_SIZE; offset += PSIZE) {
 			mp = page_to_mp(page, offset);
 			if (!mp)
 				continue;
@@ -803,7 +803,7 @@ void __invalidate_metapages(struct inode *ip, s64 addr, int len)
 				remove_from_logsync(mp);
 		}
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 	}
 }
 
diff --git a/fs/jfs/jfs_metapage.h b/fs/jfs/jfs_metapage.h
index 337e9e51ac06..a869fb4a20d6 100644
--- a/fs/jfs/jfs_metapage.h
+++ b/fs/jfs/jfs_metapage.h
@@ -106,7 +106,7 @@ static inline void metapage_nohomeok(struct metapage *mp)
 	lock_page(page);
 	if (!mp->nohomeok++) {
 		mark_metapage_dirty(mp);
-		page_cache_get(page);
+		get_page(page);
 		wait_on_page_writeback(page);
 	}
 	unlock_page(page);
@@ -128,7 +128,7 @@ static inline void metapage_wait_for_io(struct metapage *mp)
 static inline void _metapage_homeok(struct metapage *mp)
 {
 	if (!--mp->nohomeok)
-		page_cache_release(mp->page);
+		put_page(mp->page);
 }
 
 static inline void metapage_homeok(struct metapage *mp)
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index 35976bdccafc..701f89370de7 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -983,6 +983,7 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry,
 		jfs_info("jfs_symlink: allocate extent ip:0x%p", ip);
 
 		ip->i_op = &jfs_symlink_inode_operations;
+		inode_nohighmem(ip);
 		ip->i_mapping->a_ops = &jfs_aops;
 
 		/*
@@ -1372,9 +1373,6 @@ static int jfs_mknod(struct inode *dir, struct dentry *dentry,
 	tid_t tid;
 	struct tblock *tblk;
 
-	if (!new_valid_dev(rdev))
-		return -EINVAL;
-
 	jfs_info("jfs_mknod: %pd", dentry);
 
 	rc = dquot_initialize(dir);
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 4cd9798f4948..78d599198bf5 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -496,9 +496,6 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
 
 	jfs_info("In jfs_read_super: s_flags=0x%lx", sb->s_flags);
 
-	if (!new_valid_dev(sb->s_bdev->bd_dev))
-		return -EOVERFLOW;
-
 	sbi = kzalloc(sizeof(struct jfs_sb_info), GFP_KERNEL);
 	if (!sbi)
 		return -ENOMEM;
@@ -599,7 +596,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
 	 * Page cache is indexed by long.
 	 * I would use MAX_LFS_FILESIZE, but it's only half as big
 	 */
-	sb->s_maxbytes = min(((u64) PAGE_CACHE_SIZE << 32) - 1,
+	sb->s_maxbytes = min(((u64) PAGE_SIZE << 32) - 1,
 			     (u64)sb->s_maxbytes);
 #endif
 	sb->s_time_gran = 1;
@@ -795,7 +792,7 @@ static ssize_t jfs_quota_write(struct super_block *sb, int type,
 	struct buffer_head tmp_bh;
 	struct buffer_head *bh;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	while (towrite > 0) {
 		tocopy = sb->s_blocksize - offset < towrite ?
 				sb->s_blocksize - offset : towrite;
@@ -827,7 +824,7 @@ static ssize_t jfs_quota_write(struct super_block *sb, int type,
 	}
 out:
 	if (len == towrite) {
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 		return err;
 	}
 	if (inode->i_size < off+len-towrite)
@@ -835,7 +832,7 @@ out:
 	inode->i_version++;
 	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 	mark_inode_dirty(inode);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return len - towrite;
 }
 
@@ -901,7 +898,7 @@ static int __init init_jfs_fs(void)
 
 	jfs_inode_cachep =
 	    kmem_cache_create("jfs_ip", sizeof(struct jfs_inode_info), 0,
-			    SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD,
+			    SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT,
 			    init_once);
 	if (jfs_inode_cachep == NULL)
 		return -ENOMEM;
diff --git a/fs/jfs/symlink.c b/fs/jfs/symlink.c
index 5929e2363cb8..f8db4fde0b0b 100644
--- a/fs/jfs/symlink.c
+++ b/fs/jfs/symlink.c
@@ -23,7 +23,7 @@
 
 const struct inode_operations jfs_fast_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= simple_follow_link,
+	.get_link	= simple_get_link,
 	.setattr	= jfs_setattr,
 	.setxattr	= jfs_setxattr,
 	.getxattr	= jfs_getxattr,
@@ -33,8 +33,7 @@ const struct inode_operations jfs_fast_symlink_inode_operations = {
 
 const struct inode_operations jfs_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 	.setattr	= jfs_setattr,
 	.setxattr	= jfs_setxattr,
 	.getxattr	= jfs_getxattr,
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 91e004518237..03b688d19f69 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -44,28 +44,122 @@ static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen)
 	return strlcpy(buf, kn->parent ? kn->name : "/", buflen);
 }
 
-static char * __must_check kernfs_path_locked(struct kernfs_node *kn, char *buf,
-					      size_t buflen)
+/* kernfs_node_depth - compute depth from @from to @to */
+static size_t kernfs_depth(struct kernfs_node *from, struct kernfs_node *to)
 {
-	char *p = buf + buflen;
-	int len;
+	size_t depth = 0;
 
-	*--p = '\0';
+	while (to->parent && to != from) {
+		depth++;
+		to = to->parent;
+	}
+	return depth;
+}
 
-	do {
-		len = strlen(kn->name);
-		if (p - buf < len + 1) {
-			buf[0] = '\0';
-			p = NULL;
-			break;
-		}
-		p -= len;
-		memcpy(p, kn->name, len);
-		*--p = '/';
-		kn = kn->parent;
-	} while (kn && kn->parent);
+static struct kernfs_node *kernfs_common_ancestor(struct kernfs_node *a,
+						  struct kernfs_node *b)
+{
+	size_t da, db;
+	struct kernfs_root *ra = kernfs_root(a), *rb = kernfs_root(b);
+
+	if (ra != rb)
+		return NULL;
+
+	da = kernfs_depth(ra->kn, a);
+	db = kernfs_depth(rb->kn, b);
+
+	while (da > db) {
+		a = a->parent;
+		da--;
+	}
+	while (db > da) {
+		b = b->parent;
+		db--;
+	}
 
-	return p;
+	/* worst case b and a will be the same at root */
+	while (b != a) {
+		b = b->parent;
+		a = a->parent;
+	}
+
+	return a;
+}
+
+/**
+ * kernfs_path_from_node_locked - find a pseudo-absolute path to @kn_to,
+ * where kn_from is treated as root of the path.
+ * @kn_from: kernfs node which should be treated as root for the path
+ * @kn_to: kernfs node to which path is needed
+ * @buf: buffer to copy the path into
+ * @buflen: size of @buf
+ *
+ * We need to handle couple of scenarios here:
+ * [1] when @kn_from is an ancestor of @kn_to at some level
+ * kn_from: /n1/n2/n3
+ * kn_to:   /n1/n2/n3/n4/n5
+ * result:  /n4/n5
+ *
+ * [2] when @kn_from is on a different hierarchy and we need to find common
+ * ancestor between @kn_from and @kn_to.
+ * kn_from: /n1/n2/n3/n4
+ * kn_to:   /n1/n2/n5
+ * result:  /../../n5
+ * OR
+ * kn_from: /n1/n2/n3/n4/n5   [depth=5]
+ * kn_to:   /n1/n2/n3         [depth=3]
+ * result:  /../..
+ *
+ * return value: length of the string.  If greater than buflen,
+ * then contents of buf are undefined.  On error, -1 is returned.
+ */
+static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
+					struct kernfs_node *kn_from,
+					char *buf, size_t buflen)
+{
+	struct kernfs_node *kn, *common;
+	const char parent_str[] = "/..";
+	size_t depth_from, depth_to, len = 0, nlen = 0;
+	char *p;
+	int i;
+
+	if (!kn_from)
+		kn_from = kernfs_root(kn_to)->kn;
+
+	if (kn_from == kn_to)
+		return strlcpy(buf, "/", buflen);
+
+	common = kernfs_common_ancestor(kn_from, kn_to);
+	if (WARN_ON(!common))
+		return -1;
+
+	depth_to = kernfs_depth(common, kn_to);
+	depth_from = kernfs_depth(common, kn_from);
+
+	if (buf)
+		buf[0] = '\0';
+
+	for (i = 0; i < depth_from; i++)
+		len += strlcpy(buf + len, parent_str,
+			       len < buflen ? buflen - len : 0);
+
+	/* Calculate how many bytes we need for the rest */
+	for (kn = kn_to; kn != common; kn = kn->parent)
+		nlen += strlen(kn->name) + 1;
+
+	if (len + nlen >= buflen)
+		return len + nlen;
+
+	p = buf + len + nlen;
+	*p = '\0';
+	for (kn = kn_to; kn != common; kn = kn->parent) {
+		nlen = strlen(kn->name);
+		p -= nlen;
+		memcpy(p, kn->name, nlen);
+		*(--p) = '/';
+	}
+
+	return len + nlen;
 }
 
 /**
@@ -115,6 +209,34 @@ size_t kernfs_path_len(struct kernfs_node *kn)
 }
 
 /**
+ * kernfs_path_from_node - build path of node @to relative to @from.
+ * @from: parent kernfs_node relative to which we need to build the path
+ * @to: kernfs_node of interest
+ * @buf: buffer to copy @to's path into
+ * @buflen: size of @buf
+ *
+ * Builds @to's path relative to @from in @buf. @from and @to must
+ * be on the same kernfs-root. If @from is not parent of @to, then a relative
+ * path (which includes '..'s) as needed to reach from @from to @to is
+ * returned.
+ *
+ * If @buf isn't long enough, the return value will be greater than @buflen
+ * and @buf contents are undefined.
+ */
+int kernfs_path_from_node(struct kernfs_node *to, struct kernfs_node *from,
+			  char *buf, size_t buflen)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&kernfs_rename_lock, flags);
+	ret = kernfs_path_from_node_locked(to, from, buf, buflen);
+	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(kernfs_path_from_node);
+
+/**
  * kernfs_path - build full path of a given node
  * @kn: kernfs_node of interest
  * @buf: buffer to copy @kn's name into
@@ -127,13 +249,12 @@ size_t kernfs_path_len(struct kernfs_node *kn)
  */
 char *kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen)
 {
-	unsigned long flags;
-	char *p;
+	int ret;
 
-	spin_lock_irqsave(&kernfs_rename_lock, flags);
-	p = kernfs_path_locked(kn, buf, buflen);
-	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
-	return p;
+	ret = kernfs_path_from_node(kn, NULL, buf, buflen);
+	if (ret < 0 || ret >= buflen)
+		return NULL;
+	return buf;
 }
 EXPORT_SYMBOL_GPL(kernfs_path);
 
@@ -164,17 +285,25 @@ void pr_cont_kernfs_name(struct kernfs_node *kn)
 void pr_cont_kernfs_path(struct kernfs_node *kn)
 {
 	unsigned long flags;
-	char *p;
+	int sz;
 
 	spin_lock_irqsave(&kernfs_rename_lock, flags);
 
-	p = kernfs_path_locked(kn, kernfs_pr_cont_buf,
-			       sizeof(kernfs_pr_cont_buf));
-	if (p)
-		pr_cont("%s", p);
-	else
-		pr_cont("<name too long>");
+	sz = kernfs_path_from_node_locked(kn, NULL, kernfs_pr_cont_buf,
+					  sizeof(kernfs_pr_cont_buf));
+	if (sz < 0) {
+		pr_cont("(error)");
+		goto out;
+	}
+
+	if (sz >= sizeof(kernfs_pr_cont_buf)) {
+		pr_cont("(name too long)");
+		goto out;
+	}
+
+	pr_cont("%s", kernfs_pr_cont_buf);
 
+out:
 	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
 }
 
@@ -541,14 +670,7 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 	if (!kn)
 		goto err_out1;
 
-	/*
-	 * If the ino of the sysfs entry created for a kmem cache gets
-	 * allocated from an ida layer, which is accounted to the memcg that
-	 * owns the cache, the memcg will get pinned forever. So do not account
-	 * ino ida allocations.
-	 */
-	ret = ida_simple_get(&root->ino_ida, 1, 0,
-			     GFP_KERNEL | __GFP_NOACCOUNT);
+	ret = ida_simple_get(&root->ino_ida, 1, 0, GFP_KERNEL);
 	if (ret < 0)
 		goto err_out2;
 	kn->ino = ret;
@@ -694,6 +816,38 @@ static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent,
 	return NULL;
 }
 
+static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent,
+					  const unsigned char *path,
+					  const void *ns)
+{
+	size_t len;
+	char *p, *name;
+
+	lockdep_assert_held(&kernfs_mutex);
+
+	/* grab kernfs_rename_lock to piggy back on kernfs_pr_cont_buf */
+	spin_lock_irq(&kernfs_rename_lock);
+
+	len = strlcpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf));
+
+	if (len >= sizeof(kernfs_pr_cont_buf)) {
+		spin_unlock_irq(&kernfs_rename_lock);
+		return NULL;
+	}
+
+	p = kernfs_pr_cont_buf;
+
+	while ((name = strsep(&p, "/")) && parent) {
+		if (*name == '\0')
+			continue;
+		parent = kernfs_find_ns(parent, name, ns);
+	}
+
+	spin_unlock_irq(&kernfs_rename_lock);
+
+	return parent;
+}
+
 /**
  * kernfs_find_and_get_ns - find and get kernfs_node with the given name
  * @parent: kernfs_node to search under
@@ -719,6 +873,29 @@ struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent,
 EXPORT_SYMBOL_GPL(kernfs_find_and_get_ns);
 
 /**
+ * kernfs_walk_and_get_ns - find and get kernfs_node with the given path
+ * @parent: kernfs_node to search under
+ * @path: path to look for
+ * @ns: the namespace tag to use
+ *
+ * Look for kernfs_node with path @path under @parent and get a reference
+ * if found.  This function may sleep and returns pointer to the found
+ * kernfs_node on success, %NULL on failure.
+ */
+struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent,
+					   const char *path, const void *ns)
+{
+	struct kernfs_node *kn;
+
+	mutex_lock(&kernfs_mutex);
+	kn = kernfs_walk_ns(parent, path, ns);
+	kernfs_get(kn);
+	mutex_unlock(&kernfs_mutex);
+
+	return kn;
+}
+
+/**
  * kernfs_create_root - create a new kernfs hierarchy
  * @scops: optional syscall operations for the hierarchy
  * @flags: KERNFS_ROOT_* flags
@@ -1472,9 +1649,9 @@ static loff_t kernfs_dir_fop_llseek(struct file *file, loff_t offset,
 	struct inode *inode = file_inode(file);
 	loff_t ret;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	ret = generic_file_llseek(file, offset, whence);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	return ret;
 }
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index 756dd56aaf60..16405ae88d2d 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -205,7 +205,7 @@ int kernfs_iop_removexattr(struct dentry *dentry, const char *name)
 	if (!attrs)
 		return -ENOMEM;
 
-	return simple_xattr_remove(&attrs->xattrs, name);
+	return simple_xattr_set(&attrs->xattrs, name, NULL, 0, XATTR_REPLACE);
 }
 
 ssize_t kernfs_iop_getxattr(struct dentry *dentry, const char *name, void *buf,
@@ -230,7 +230,7 @@ ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size)
 	if (!attrs)
 		return -ENOMEM;
 
-	return simple_xattr_list(&attrs->xattrs, buf, size);
+	return simple_xattr_list(d_inode(dentry), &attrs->xattrs, buf, size);
 }
 
 static inline void set_default_inode_attr(struct inode *inode, umode_t mode)
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 8eaf417187f1..f73541fbe7af 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -14,6 +14,7 @@
 #include <linux/magic.h>
 #include <linux/slab.h>
 #include <linux/pagemap.h>
+#include <linux/namei.h>
 
 #include "kernfs-internal.h"
 
@@ -62,6 +63,74 @@ struct kernfs_root *kernfs_root_from_sb(struct super_block *sb)
 	return NULL;
 }
 
+/*
+ * find the next ancestor in the path down to @child, where @parent was the
+ * ancestor whose descendant we want to find.
+ *
+ * Say the path is /a/b/c/d.  @child is d, @parent is NULL.  We return the root
+ * node.  If @parent is b, then we return the node for c.
+ * Passing in d as @parent is not ok.
+ */
+static struct kernfs_node *find_next_ancestor(struct kernfs_node *child,
+					      struct kernfs_node *parent)
+{
+	if (child == parent) {
+		pr_crit_once("BUG in find_next_ancestor: called with parent == child");
+		return NULL;
+	}
+
+	while (child->parent != parent) {
+		if (!child->parent)
+			return NULL;
+		child = child->parent;
+	}
+
+	return child;
+}
+
+/**
+ * kernfs_node_dentry - get a dentry for the given kernfs_node
+ * @kn: kernfs_node for which a dentry is needed
+ * @sb: the kernfs super_block
+ */
+struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
+				  struct super_block *sb)
+{
+	struct dentry *dentry;
+	struct kernfs_node *knparent = NULL;
+
+	BUG_ON(sb->s_op != &kernfs_sops);
+
+	dentry = dget(sb->s_root);
+
+	/* Check if this is the root kernfs_node */
+	if (!kn->parent)
+		return dentry;
+
+	knparent = find_next_ancestor(kn, NULL);
+	if (WARN_ON(!knparent))
+		return ERR_PTR(-EINVAL);
+
+	do {
+		struct dentry *dtmp;
+		struct kernfs_node *kntmp;
+
+		if (kn == knparent)
+			return dentry;
+		kntmp = find_next_ancestor(kn, knparent);
+		if (WARN_ON(!kntmp))
+			return ERR_PTR(-EINVAL);
+		mutex_lock(&d_inode(dentry)->i_mutex);
+		dtmp = lookup_one_len(kntmp->name, dentry, strlen(kntmp->name));
+		mutex_unlock(&d_inode(dentry)->i_mutex);
+		dput(dentry);
+		if (IS_ERR(dtmp))
+			return dtmp;
+		knparent = kntmp;
+		dentry = dtmp;
+	} while (true);
+}
+
 static int kernfs_fill_super(struct super_block *sb, unsigned long magic)
 {
 	struct kernfs_super_info *info = kernfs_info(sb);
@@ -69,8 +138,8 @@ static int kernfs_fill_super(struct super_block *sb, unsigned long magic)
 	struct dentry *root;
 
 	info->sb = sb;
-	sb->s_blocksize = PAGE_CACHE_SIZE;
-	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
+	sb->s_blocksize = PAGE_SIZE;
+	sb->s_blocksize_bits = PAGE_SHIFT;
 	sb->s_magic = magic;
 	sb->s_op = &kernfs_sops;
 	sb->s_time_gran = 1;
diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c
index db272528ab5b..117b8b3416f9 100644
--- a/fs/kernfs/symlink.c
+++ b/fs/kernfs/symlink.c
@@ -112,18 +112,25 @@ static int kernfs_getlink(struct dentry *dentry, char *path)
 	return error;
 }
 
-static const char *kernfs_iop_follow_link(struct dentry *dentry, void **cookie)
+static const char *kernfs_iop_get_link(struct dentry *dentry,
+				       struct inode *inode,
+				       struct delayed_call *done)
 {
-	int error = -ENOMEM;
-	unsigned long page = get_zeroed_page(GFP_KERNEL);
-	if (!page)
+	char *body;
+	int error;
+
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+	body = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!body)
 		return ERR_PTR(-ENOMEM);
-	error = kernfs_getlink(dentry, (char *)page);
+	error = kernfs_getlink(dentry, body);
 	if (unlikely(error < 0)) {
-		free_page((unsigned long)page);
+		kfree(body);
 		return ERR_PTR(error);
 	}
-	return *cookie = (char *)page;
+	set_delayed_call(done, kfree_link, body);
+	return body;
 }
 
 const struct inode_operations kernfs_symlink_iops = {
@@ -132,8 +139,7 @@ const struct inode_operations kernfs_symlink_iops = {
 	.getxattr	= kernfs_iop_getxattr,
 	.listxattr	= kernfs_iop_listxattr,
 	.readlink	= generic_readlink,
-	.follow_link	= kernfs_iop_follow_link,
-	.put_link	= free_page_put_link,
+	.get_link	= kernfs_iop_get_link,
 	.setattr	= kernfs_iop_setattr,
 	.getattr	= kernfs_iop_getattr,
 	.permission	= kernfs_iop_permission,
diff --git a/fs/libfs.c b/fs/libfs.c
index c7cbfb092e94..f3fa82ce9b70 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -25,7 +25,7 @@ int simple_getattr(struct vfsmount *mnt, struct dentry *dentry,
 {
 	struct inode *inode = d_inode(dentry);
 	generic_fillattr(inode, stat);
-	stat->blocks = inode->i_mapping->nrpages << (PAGE_CACHE_SHIFT - 9);
+	stat->blocks = inode->i_mapping->nrpages << (PAGE_SHIFT - 9);
 	return 0;
 }
 EXPORT_SYMBOL(simple_getattr);
@@ -33,7 +33,7 @@ EXPORT_SYMBOL(simple_getattr);
 int simple_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	buf->f_type = dentry->d_sb->s_magic;
-	buf->f_bsize = PAGE_CACHE_SIZE;
+	buf->f_bsize = PAGE_SIZE;
 	buf->f_namelen = NAME_MAX;
 	return 0;
 }
@@ -89,7 +89,7 @@ EXPORT_SYMBOL(dcache_dir_close);
 loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
 {
 	struct dentry *dentry = file->f_path.dentry;
-	mutex_lock(&d_inode(dentry)->i_mutex);
+	inode_lock(d_inode(dentry));
 	switch (whence) {
 		case 1:
 			offset += file->f_pos;
@@ -97,7 +97,7 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
 			if (offset >= 0)
 				break;
 		default:
-			mutex_unlock(&d_inode(dentry)->i_mutex);
+			inode_unlock(d_inode(dentry));
 			return -EINVAL;
 	}
 	if (offset != file->f_pos) {
@@ -124,7 +124,7 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
 			spin_unlock(&dentry->d_lock);
 		}
 	}
-	mutex_unlock(&d_inode(dentry)->i_mutex);
+	inode_unlock(d_inode(dentry));
 	return offset;
 }
 EXPORT_SYMBOL(dcache_dir_lseek);
@@ -395,7 +395,7 @@ int simple_write_begin(struct file *file, struct address_space *mapping,
 	struct page *page;
 	pgoff_t index;
 
-	index = pos >> PAGE_CACHE_SHIFT;
+	index = pos >> PAGE_SHIFT;
 
 	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
@@ -403,10 +403,10 @@ int simple_write_begin(struct file *file, struct address_space *mapping,
 
 	*pagep = page;
 
-	if (!PageUptodate(page) && (len != PAGE_CACHE_SIZE)) {
-		unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+	if (!PageUptodate(page) && (len != PAGE_SIZE)) {
+		unsigned from = pos & (PAGE_SIZE - 1);
 
-		zero_user_segments(page, 0, from, from + len, PAGE_CACHE_SIZE);
+		zero_user_segments(page, 0, from, from + len, PAGE_SIZE);
 	}
 	return 0;
 }
@@ -442,7 +442,7 @@ int simple_write_end(struct file *file, struct address_space *mapping,
 
 	/* zero the stale part of the page if we did a short copy */
 	if (copied < len) {
-		unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+		unsigned from = pos & (PAGE_SIZE - 1);
 
 		zero_user(page, from + copied, len - copied);
 	}
@@ -458,7 +458,7 @@ int simple_write_end(struct file *file, struct address_space *mapping,
 
 	set_page_dirty(page);
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 
 	return copied;
 }
@@ -477,8 +477,8 @@ int simple_fill_super(struct super_block *s, unsigned long magic,
 	struct dentry *dentry;
 	int i;
 
-	s->s_blocksize = PAGE_CACHE_SIZE;
-	s->s_blocksize_bits = PAGE_CACHE_SHIFT;
+	s->s_blocksize = PAGE_SIZE;
+	s->s_blocksize_bits = PAGE_SHIFT;
 	s->s_magic = magic;
 	s->s_op = &simple_super_operations;
 	s->s_time_gran = 1;
@@ -941,7 +941,7 @@ int __generic_file_fsync(struct file *file, loff_t start, loff_t end,
 	if (err)
 		return err;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	ret = sync_mapping_buffers(inode->i_mapping);
 	if (!(inode->i_state & I_DIRTY_ALL))
 		goto out;
@@ -953,7 +953,7 @@ int __generic_file_fsync(struct file *file, loff_t start, loff_t end,
 		ret = err;
 
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return ret;
 }
 EXPORT_SYMBOL(__generic_file_fsync);
@@ -994,12 +994,12 @@ int generic_check_addressable(unsigned blocksize_bits, u64 num_blocks)
 {
 	u64 last_fs_block = num_blocks - 1;
 	u64 last_fs_page =
-		last_fs_block >> (PAGE_CACHE_SHIFT - blocksize_bits);
+		last_fs_block >> (PAGE_SHIFT - blocksize_bits);
 
 	if (unlikely(num_blocks == 0))
 		return 0;
 
-	if ((blocksize_bits < 9) || (blocksize_bits > PAGE_CACHE_SHIFT))
+	if ((blocksize_bits < 9) || (blocksize_bits > PAGE_SHIFT))
 		return -EINVAL;
 
 	if ((last_fs_block > (sector_t)(~0ULL) >> (blocksize_bits - 9)) ||
@@ -1019,17 +1019,12 @@ int noop_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 }
 EXPORT_SYMBOL(noop_fsync);
 
-void kfree_put_link(struct inode *unused, void *cookie)
-{
-	kfree(cookie);
-}
-EXPORT_SYMBOL(kfree_put_link);
-
-void free_page_put_link(struct inode *unused, void *cookie)
+/* Because kfree isn't assignment-compatible with void(void*) ;-/ */
+void kfree_link(void *p)
 {
-	free_page((unsigned long) cookie);
+	kfree(p);
 }
-EXPORT_SYMBOL(free_page_put_link);
+EXPORT_SYMBOL(kfree_link);
 
 /*
  * nop .set_page_dirty method so that people can use .page_mkwrite on
@@ -1092,14 +1087,15 @@ simple_nosetlease(struct file *filp, long arg, struct file_lock **flp,
 }
 EXPORT_SYMBOL(simple_nosetlease);
 
-const char *simple_follow_link(struct dentry *dentry, void **cookie)
+const char *simple_get_link(struct dentry *dentry, struct inode *inode,
+			    struct delayed_call *done)
 {
-	return d_inode(dentry)->i_link;
+	return inode->i_link;
 }
-EXPORT_SYMBOL(simple_follow_link);
+EXPORT_SYMBOL(simple_get_link);
 
 const struct inode_operations simple_symlink_inode_operations = {
-	.follow_link = simple_follow_link,
+	.get_link = simple_get_link,
 	.readlink = generic_readlink
 };
 EXPORT_SYMBOL(simple_symlink_inode_operations);
diff --git a/fs/lockd/host.c b/fs/lockd/host.c
index 969d589c848d..d716c9993a26 100644
--- a/fs/lockd/host.c
+++ b/fs/lockd/host.c
@@ -116,7 +116,7 @@ static struct nlm_host *nlm_alloc_host(struct nlm_lookup_host_info *ni,
 		atomic_inc(&nsm->sm_count);
 	else {
 		host = NULL;
-		nsm = nsm_get_handle(ni->sap, ni->salen,
+		nsm = nsm_get_handle(ni->net, ni->sap, ni->salen,
 					ni->hostname, ni->hostname_len);
 		if (unlikely(nsm == NULL)) {
 			dprintk("lockd: %s failed; no nsm handle\n",
@@ -161,6 +161,7 @@ static struct nlm_host *nlm_alloc_host(struct nlm_lookup_host_info *ni,
 	host->h_nsmhandle  = nsm;
 	host->h_addrbuf    = nsm->sm_addrbuf;
 	host->net	   = ni->net;
+	strlcpy(host->nodename, utsname()->nodename, sizeof(host->nodename));
 
 out:
 	return host;
@@ -534,17 +535,18 @@ static struct nlm_host *next_host_state(struct hlist_head *cache,
 
 /**
  * nlm_host_rebooted - Release all resources held by rebooted host
+ * @net:  network namespace
  * @info: pointer to decoded results of NLM_SM_NOTIFY call
  *
  * We were notified that the specified host has rebooted.  Release
  * all resources held by that peer.
  */
-void nlm_host_rebooted(const struct nlm_reboot *info)
+void nlm_host_rebooted(const struct net *net, const struct nlm_reboot *info)
 {
 	struct nsm_handle *nsm;
 	struct nlm_host	*host;
 
-	nsm = nsm_reboot_lookup(info);
+	nsm = nsm_reboot_lookup(net, info);
 	if (unlikely(nsm == NULL))
 		return;
 
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index 47a32b6d9b90..19166d4a8d31 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -42,7 +42,7 @@ struct nsm_args {
 	u32			proc;
 
 	char			*mon_name;
-	char			*nodename;
+	const char		*nodename;
 };
 
 struct nsm_res {
@@ -51,7 +51,6 @@ struct nsm_res {
 };
 
 static const struct rpc_program	nsm_program;
-static				LIST_HEAD(nsm_handles);
 static				DEFINE_SPINLOCK(nsm_lock);
 
 /*
@@ -87,69 +86,18 @@ static struct rpc_clnt *nsm_create(struct net *net, const char *nodename)
 	return rpc_create(&args);
 }
 
-static struct rpc_clnt *nsm_client_set(struct lockd_net *ln,
-		struct rpc_clnt *clnt)
-{
-	spin_lock(&ln->nsm_clnt_lock);
-	if (ln->nsm_users == 0) {
-		if (clnt == NULL)
-			goto out;
-		ln->nsm_clnt = clnt;
-	}
-	clnt = ln->nsm_clnt;
-	ln->nsm_users++;
-out:
-	spin_unlock(&ln->nsm_clnt_lock);
-	return clnt;
-}
-
-static struct rpc_clnt *nsm_client_get(struct net *net, const char *nodename)
-{
-	struct rpc_clnt	*clnt, *new;
-	struct lockd_net *ln = net_generic(net, lockd_net_id);
-
-	clnt = nsm_client_set(ln, NULL);
-	if (clnt != NULL)
-		goto out;
-
-	clnt = new = nsm_create(net, nodename);
-	if (IS_ERR(clnt))
-		goto out;
-
-	clnt = nsm_client_set(ln, new);
-	if (clnt != new)
-		rpc_shutdown_client(new);
-out:
-	return clnt;
-}
-
-static void nsm_client_put(struct net *net)
-{
-	struct lockd_net *ln = net_generic(net, lockd_net_id);
-	struct rpc_clnt	*clnt = NULL;
-
-	spin_lock(&ln->nsm_clnt_lock);
-	ln->nsm_users--;
-	if (ln->nsm_users == 0) {
-		clnt = ln->nsm_clnt;
-		ln->nsm_clnt = NULL;
-	}
-	spin_unlock(&ln->nsm_clnt_lock);
-	if (clnt != NULL)
-		rpc_shutdown_client(clnt);
-}
-
 static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res,
-			 struct rpc_clnt *clnt)
+			 const struct nlm_host *host)
 {
 	int		status;
+	struct rpc_clnt *clnt;
 	struct nsm_args args = {
 		.priv		= &nsm->sm_priv,
 		.prog		= NLM_PROGRAM,
 		.vers		= 3,
 		.proc		= NLMPROC_NSM_NOTIFY,
 		.mon_name	= nsm->sm_mon_name,
-		.nodename	= clnt->cl_nodename,
+		.nodename	= host->nodename,
 	};
 	struct rpc_message msg = {
 		.rpc_argp	= &args,
@@ -158,6 +106,13 @@ static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res,
 
 	memset(res, 0, sizeof(*res));
 
+	clnt = nsm_create(host->net, host->nodename);
+	if (IS_ERR(clnt)) {
+		dprintk("lockd: failed to create NSM upcall transport, "
+			"status=%ld, net=%p\n", PTR_ERR(clnt), host->net);
+		return PTR_ERR(clnt);
+	}
+
 	msg.rpc_proc = &clnt->cl_procinfo[proc];
 	status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN);
 	if (status == -ECONNREFUSED) {
@@ -171,6 +126,8 @@ static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res,
 				status);
 	else
 		status = 0;
+
+	rpc_shutdown_client(clnt);
 	return status;
 }
 
@@ -190,32 +147,19 @@ int nsm_monitor(const struct nlm_host *host)
 	struct nsm_handle *nsm = host->h_nsmhandle;
 	struct nsm_res	res;
 	int		status;
-	struct rpc_clnt *clnt;
-	const char *nodename = NULL;
 
 	dprintk("lockd: nsm_monitor(%s)\n", nsm->sm_name);
 
 	if (nsm->sm_monitored)
 		return 0;
 
-	if (host->h_rpcclnt)
-		nodename = host->h_rpcclnt->cl_nodename;
-
 	/*
 	 * Choose whether to record the caller_name or IP address of
 	 * this peer in the local rpc.statd's database.
 	 */
 	nsm->sm_mon_name = nsm_use_hostnames ? nsm->sm_name : nsm->sm_addrbuf;
 
-	clnt = nsm_client_get(host->net, nodename);
-	if (IS_ERR(clnt)) {
-		status = PTR_ERR(clnt);
-		dprintk("lockd: failed to create NSM upcall transport, "
-				"status=%d, net=%p\n", status, host->net);
-		return status;
-	}
-
-	status = nsm_mon_unmon(nsm, NSMPROC_MON, &res, clnt);
+	status = nsm_mon_unmon(nsm, NSMPROC_MON, &res, host);
 	if (unlikely(res.status != 0))
 		status = -EIO;
 	if (unlikely(status < 0)) {
@@ -247,11 +191,9 @@ void nsm_unmonitor(const struct nlm_host *host)
 
 	if (atomic_read(&nsm->sm_count) == 1
 	 && nsm->sm_monitored && !nsm->sm_sticky) {
-		struct lockd_net *ln = net_generic(host->net, lockd_net_id);
-
 		dprintk("lockd: nsm_unmonitor(%s)\n", nsm->sm_name);
 
-		status = nsm_mon_unmon(nsm, NSMPROC_UNMON, &res, ln->nsm_clnt);
+		status = nsm_mon_unmon(nsm, NSMPROC_UNMON, &res, host);
 		if (res.status != 0)
 			status = -EIO;
 		if (status < 0)
@@ -259,38 +201,38 @@ void nsm_unmonitor(const struct nlm_host *host)
 					nsm->sm_name);
 		else
 			nsm->sm_monitored = 0;
-
-		nsm_client_put(host->net);
 	}
 }
 
-static struct nsm_handle *nsm_lookup_hostname(const char *hostname,
-					      const size_t len)
+static struct nsm_handle *nsm_lookup_hostname(const struct list_head *nsm_handles,
+					const char *hostname, const size_t len)
 {
 	struct nsm_handle *nsm;
 
-	list_for_each_entry(nsm, &nsm_handles, sm_link)
+	list_for_each_entry(nsm, nsm_handles, sm_link)
 		if (strlen(nsm->sm_name) == len &&
 		    memcmp(nsm->sm_name, hostname, len) == 0)
 			return nsm;
 	return NULL;
 }
 
-static struct nsm_handle *nsm_lookup_addr(const struct sockaddr *sap)
+static struct nsm_handle *nsm_lookup_addr(const struct list_head *nsm_handles,
+					const struct sockaddr *sap)
 {
 	struct nsm_handle *nsm;
 
-	list_for_each_entry(nsm, &nsm_handles, sm_link)
+	list_for_each_entry(nsm, nsm_handles, sm_link)
 		if (rpc_cmp_addr(nsm_addr(nsm), sap))
 			return nsm;
 	return NULL;
 }
 
-static struct nsm_handle *nsm_lookup_priv(const struct nsm_private *priv)
+static struct nsm_handle *nsm_lookup_priv(const struct list_head *nsm_handles,
+					const struct nsm_private *priv)
 {
 	struct nsm_handle *nsm;
 
-	list_for_each_entry(nsm, &nsm_handles, sm_link)
+	list_for_each_entry(nsm, nsm_handles, sm_link)
 		if (memcmp(nsm->sm_priv.data, priv->data,
 					sizeof(priv->data)) == 0)
 			return nsm;
@@ -353,6 +295,7 @@ static struct nsm_handle *nsm_create_handle(const struct sockaddr *sap,
 
 /**
  * nsm_get_handle - Find or create a cached nsm_handle
+ * @net: network namespace
  * @sap: pointer to socket address of handle to find
  * @salen: length of socket address
  * @hostname: pointer to C string containing hostname to find
@@ -365,11 +308,13 @@ static struct nsm_handle *nsm_create_handle(const struct sockaddr *sap,
  * @hostname cannot be found in the handle cache.  Returns NULL if
  * an error occurs.
  */
-struct nsm_handle *nsm_get_handle(const struct sockaddr *sap,
+struct nsm_handle *nsm_get_handle(const struct net *net,
+				  const struct sockaddr *sap,
 				  const size_t salen, const char *hostname,
 				  const size_t hostname_len)
 {
 	struct nsm_handle *cached, *new = NULL;
+	struct lockd_net *ln = net_generic(net, lockd_net_id);
 
 	if (hostname && memchr(hostname, '/', hostname_len) != NULL) {
 		if (printk_ratelimit()) {
@@ -384,9 +329,10 @@ retry:
 	spin_lock(&nsm_lock);
 
 	if (nsm_use_hostnames && hostname != NULL)
-		cached = nsm_lookup_hostname(hostname, hostname_len);
+		cached = nsm_lookup_hostname(&ln->nsm_handles,
+					hostname, hostname_len);
 	else
-		cached = nsm_lookup_addr(sap);
+		cached = nsm_lookup_addr(&ln->nsm_handles, sap);
 
 	if (cached != NULL) {
 		atomic_inc(&cached->sm_count);
@@ -400,7 +346,7 @@ retry:
 	}
 
 	if (new != NULL) {
-		list_add(&new->sm_link, &nsm_handles);
+		list_add(&new->sm_link, &ln->nsm_handles);
 		spin_unlock(&nsm_lock);
 		dprintk("lockd: created nsm_handle for %s (%s)\n",
 				new->sm_name, new->sm_addrbuf);
@@ -417,19 +363,22 @@ retry:
 
 /**
  * nsm_reboot_lookup - match NLMPROC_SM_NOTIFY arguments to an nsm_handle
+ * @net:  network namespace
  * @info: pointer to NLMPROC_SM_NOTIFY arguments
  *
  * Returns a matching nsm_handle if found in the nsm cache. The returned
  * nsm_handle's reference count is bumped. Otherwise returns NULL if some
  * error occurred.
  */
-struct nsm_handle *nsm_reboot_lookup(const struct nlm_reboot *info)
+struct nsm_handle *nsm_reboot_lookup(const struct net *net,
+				const struct nlm_reboot *info)
 {
 	struct nsm_handle *cached;
+	struct lockd_net *ln = net_generic(net, lockd_net_id);
 
 	spin_lock(&nsm_lock);
 
-	cached = nsm_lookup_priv(&info->priv);
+	cached = nsm_lookup_priv(&ln->nsm_handles, &info->priv);
 	if (unlikely(cached == NULL)) {
 		spin_unlock(&nsm_lock);
 		dprintk("lockd: never saw rebooted peer '%.*s' before\n",
diff --git a/fs/lockd/netns.h b/fs/lockd/netns.h
index 097bfa3adb1c..5426189406c1 100644
--- a/fs/lockd/netns.h
+++ b/fs/lockd/netns.h
@@ -12,9 +12,7 @@ struct lockd_net {
 	struct delayed_work grace_period_end;
 	struct lock_manager lockd_manager;
 
-	spinlock_t nsm_clnt_lock;
-	unsigned int nsm_users;
-	struct rpc_clnt *nsm_clnt;
+	struct list_head nsm_handles;
 };
 
 extern int lockd_net_id;
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index d678bcc3cbcb..154a107cd376 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -25,13 +25,17 @@
 #include <linux/mutex.h>
 #include <linux/kthread.h>
 #include <linux/freezer.h>
+#include <linux/inetdevice.h>
 
 #include <linux/sunrpc/types.h>
 #include <linux/sunrpc/stats.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/svcsock.h>
+#include <linux/sunrpc/svc_xprt.h>
 #include <net/ip.h>
+#include <net/addrconf.h>
+#include <net/ipv6.h>
 #include <linux/lockd/lockd.h>
 #include <linux/nfs.h>
 
@@ -44,7 +48,7 @@
 
 static struct svc_program	nlmsvc_program;
 
-struct nlmsvc_binding *		nlmsvc_ops;
+const struct nlmsvc_binding	*nlmsvc_ops;
 EXPORT_SYMBOL_GPL(nlmsvc_ops);
 
 static DEFINE_MUTEX(nlmsvc_mutex);
@@ -90,8 +94,7 @@ static unsigned long get_lockd_grace_period(void)
 
 static void grace_ender(struct work_struct *grace)
 {
-	struct delayed_work *dwork = container_of(grace, struct delayed_work,
-						  work);
+	struct delayed_work *dwork = to_delayed_work(grace);
 	struct lockd_net *ln = container_of(dwork, struct lockd_net,
 					    grace_period_end);
 
@@ -279,6 +282,68 @@ static void lockd_down_net(struct svc_serv *serv, struct net *net)
 	}
 }
 
+static int lockd_inetaddr_event(struct notifier_block *this,
+	unsigned long event, void *ptr)
+{
+	struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
+	struct sockaddr_in sin;
+
+	if (event != NETDEV_DOWN)
+		goto out;
+
+	if (nlmsvc_rqst) {
+		dprintk("lockd_inetaddr_event: removed %pI4\n",
+			&ifa->ifa_local);
+		sin.sin_family = AF_INET;
+		sin.sin_addr.s_addr = ifa->ifa_local;
+		svc_age_temp_xprts_now(nlmsvc_rqst->rq_server,
+			(struct sockaddr *)&sin);
+	}
+
+out:
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block lockd_inetaddr_notifier = {
+	.notifier_call = lockd_inetaddr_event,
+};
+
+#if IS_ENABLED(CONFIG_IPV6)
+static int lockd_inet6addr_event(struct notifier_block *this,
+	unsigned long event, void *ptr)
+{
+	struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr;
+	struct sockaddr_in6 sin6;
+
+	if (event != NETDEV_DOWN)
+		goto out;
+
+	if (nlmsvc_rqst) {
+		dprintk("lockd_inet6addr_event: removed %pI6\n", &ifa->addr);
+		sin6.sin6_family = AF_INET6;
+		sin6.sin6_addr = ifa->addr;
+		svc_age_temp_xprts_now(nlmsvc_rqst->rq_server,
+			(struct sockaddr *)&sin6);
+	}
+
+out:
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block lockd_inet6addr_notifier = {
+	.notifier_call = lockd_inet6addr_event,
+};
+#endif
+
+static void lockd_svc_exit_thread(void)
+{
+	unregister_inetaddr_notifier(&lockd_inetaddr_notifier);
+#if IS_ENABLED(CONFIG_IPV6)
+	unregister_inet6addr_notifier(&lockd_inet6addr_notifier);
+#endif
+	svc_exit_thread(nlmsvc_rqst);
+}
+
 static int lockd_start_svc(struct svc_serv *serv)
 {
 	int error;
@@ -315,7 +380,7 @@ static int lockd_start_svc(struct svc_serv *serv)
 	return 0;
 
 out_task:
-	svc_exit_thread(nlmsvc_rqst);
+	lockd_svc_exit_thread();
 	nlmsvc_task = NULL;
 out_rqst:
 	nlmsvc_rqst = NULL;
@@ -360,6 +425,10 @@ static struct svc_serv *lockd_create_svc(void)
 		printk(KERN_WARNING "lockd_up: create service failed\n");
 		return ERR_PTR(-ENOMEM);
 	}
+	register_inetaddr_notifier(&lockd_inetaddr_notifier);
+#if IS_ENABLED(CONFIG_IPV6)
+	register_inet6addr_notifier(&lockd_inet6addr_notifier);
+#endif
 	dprintk("lockd_up: service created\n");
 	return serv;
 }
@@ -428,7 +497,7 @@ lockd_down(struct net *net)
 	}
 	kthread_stop(nlmsvc_task);
 	dprintk("lockd_down: service stopped\n");
-	svc_exit_thread(nlmsvc_rqst);
+	lockd_svc_exit_thread();
 	dprintk("lockd_down: service destroyed\n");
 	nlmsvc_task = NULL;
 	nlmsvc_rqst = NULL;
@@ -592,7 +661,7 @@ static int lockd_init_net(struct net *net)
 	INIT_DELAYED_WORK(&ln->grace_period_end, grace_ender);
 	INIT_LIST_HEAD(&ln->lockd_manager.list);
 	ln->lockd_manager.block_opens = false;
-	spin_lock_init(&ln->nsm_clnt_lock);
+	INIT_LIST_HEAD(&ln->nsm_handles);
 	return 0;
 }
 
diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index b147d1ae71fd..09c576f26c7b 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -421,7 +421,7 @@ nlm4svc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp,
 		return rpc_system_err;
 	}
 
-	nlm_host_rebooted(argp);
+	nlm_host_rebooted(SVC_NET(rqstp), argp);
 	return rpc_success;
 }
 
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index 21171f0c6477..fb26b9f522e7 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -464,7 +464,7 @@ nlmsvc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp,
 		return rpc_system_err;
 	}
 
-	nlm_host_rebooted(argp);
+	nlm_host_rebooted(SVC_NET(rqstp), argp);
 	return rpc_success;
 }
 
diff --git a/fs/locks.c b/fs/locks.c
index 0d2b3267e2a3..7c5f91be9b65 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -119,7 +119,6 @@
 #include <linux/fdtable.h>
 #include <linux/fs.h>
 #include <linux/init.h>
-#include <linux/module.h>
 #include <linux/security.h>
 #include <linux/slab.h>
 #include <linux/syscalls.h>
@@ -230,16 +229,44 @@ locks_get_lock_context(struct inode *inode, int type)
 		ctx = smp_load_acquire(&inode->i_flctx);
 	}
 out:
+	trace_locks_get_lock_context(inode, type, ctx);
 	return ctx;
 }
 
+static void
+locks_dump_ctx_list(struct list_head *list, char *list_type)
+{
+	struct file_lock *fl;
+
+	list_for_each_entry(fl, list, fl_list) {
+		pr_warn("%s: fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n", list_type, fl->fl_owner, fl->fl_flags, fl->fl_type, fl->fl_pid);
+	}
+}
+
+static void
+locks_check_ctx_lists(struct inode *inode)
+{
+	struct file_lock_context *ctx = inode->i_flctx;
+
+	if (unlikely(!list_empty(&ctx->flc_flock) ||
+		     !list_empty(&ctx->flc_posix) ||
+		     !list_empty(&ctx->flc_lease))) {
+		pr_warn("Leaked locks on dev=0x%x:0x%x ino=0x%lx:\n",
+			MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev),
+			inode->i_ino);
+		locks_dump_ctx_list(&ctx->flc_flock, "FLOCK");
+		locks_dump_ctx_list(&ctx->flc_posix, "POSIX");
+		locks_dump_ctx_list(&ctx->flc_lease, "LEASE");
+	}
+}
+
 void
-locks_free_lock_context(struct file_lock_context *ctx)
+locks_free_lock_context(struct inode *inode)
 {
-	if (ctx) {
-		WARN_ON_ONCE(!list_empty(&ctx->flc_flock));
-		WARN_ON_ONCE(!list_empty(&ctx->flc_posix));
-		WARN_ON_ONCE(!list_empty(&ctx->flc_lease));
+	struct file_lock_context *ctx = inode->i_flctx;
+
+	if (unlikely(ctx)) {
+		locks_check_ctx_lists(inode);
 		kmem_cache_free(flctx_cache, ctx);
 	}
 }
@@ -934,7 +961,8 @@ out:
 	return error;
 }
 
-static int __posix_lock_file(struct inode *inode, struct file_lock *request, struct file_lock *conflock)
+static int posix_lock_inode(struct inode *inode, struct file_lock *request,
+			    struct file_lock *conflock)
 {
 	struct file_lock *fl, *tmp;
 	struct file_lock *new_fl = NULL;
@@ -1142,6 +1170,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 	if (new_fl2)
 		locks_free_lock(new_fl2);
 	locks_dispose_list(&dispose);
+	trace_posix_lock_inode(inode, request, error);
+
 	return error;
 }
 
@@ -1162,7 +1192,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 int posix_lock_file(struct file *filp, struct file_lock *fl,
 			struct file_lock *conflock)
 {
-	return __posix_lock_file(file_inode(filp), fl, conflock);
+	return posix_lock_inode(file_inode(filp), fl, conflock);
 }
 EXPORT_SYMBOL(posix_lock_file);
 
@@ -1178,7 +1208,7 @@ static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl)
 	int error;
 	might_sleep ();
 	for (;;) {
-		error = __posix_lock_file(inode, fl, NULL);
+		error = posix_lock_inode(inode, fl, NULL);
 		if (error != FILE_LOCK_DEFERRED)
 			break;
 		error = wait_event_interruptible(fl->fl_wait, !fl->fl_next);
@@ -1191,6 +1221,7 @@ static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl)
 	return error;
 }
 
+#ifdef CONFIG_MANDATORY_FILE_LOCKING
 /**
  * locks_mandatory_locked - Check for an active lock
  * @file: the file to check
@@ -1227,20 +1258,16 @@ int locks_mandatory_locked(struct file *file)
 
 /**
  * locks_mandatory_area - Check for a conflicting lock
- * @read_write: %FLOCK_VERIFY_WRITE for exclusive access, %FLOCK_VERIFY_READ
- *		for shared
- * @inode:      the file to check
+ * @inode:	the file to check
  * @filp:       how the file was opened (if it was)
- * @offset:     start of area to check
- * @count:      length of area to check
+ * @start:	first byte in the file to check
+ * @end:	lastbyte in the file to check
+ * @type:	%F_WRLCK for a write lock, else %F_RDLCK
  *
  * Searches the inode's list of locks to find any POSIX locks which conflict.
- * This function is called from rw_verify_area() and
- * locks_verify_truncate().
  */
-int locks_mandatory_area(int read_write, struct inode *inode,
-			 struct file *filp, loff_t offset,
-			 size_t count)
+int locks_mandatory_area(struct inode *inode, struct file *filp, loff_t start,
+			 loff_t end, unsigned char type)
 {
 	struct file_lock fl;
 	int error;
@@ -1252,15 +1279,15 @@ int locks_mandatory_area(int read_write, struct inode *inode,
 	fl.fl_flags = FL_POSIX | FL_ACCESS;
 	if (filp && !(filp->f_flags & O_NONBLOCK))
 		sleep = true;
-	fl.fl_type = (read_write == FLOCK_VERIFY_WRITE) ? F_WRLCK : F_RDLCK;
-	fl.fl_start = offset;
-	fl.fl_end = offset + count - 1;
+	fl.fl_type = type;
+	fl.fl_start = start;
+	fl.fl_end = end;
 
 	for (;;) {
 		if (filp) {
 			fl.fl_owner = filp;
 			fl.fl_flags &= ~FL_SLEEP;
-			error = __posix_lock_file(inode, &fl, NULL);
+			error = posix_lock_inode(inode, &fl, NULL);
 			if (!error)
 				break;
 		}
@@ -1268,7 +1295,7 @@ int locks_mandatory_area(int read_write, struct inode *inode,
 		if (sleep)
 			fl.fl_flags |= FL_SLEEP;
 		fl.fl_owner = current->files;
-		error = __posix_lock_file(inode, &fl, NULL);
+		error = posix_lock_inode(inode, &fl, NULL);
 		if (error != FILE_LOCK_DEFERRED)
 			break;
 		error = wait_event_interruptible(fl.fl_wait, !fl.fl_next);
@@ -1289,6 +1316,7 @@ int locks_mandatory_area(int read_write, struct inode *inode,
 }
 
 EXPORT_SYMBOL(locks_mandatory_area);
+#endif /* CONFIG_MANDATORY_FILE_LOCKING */
 
 static void lease_clear_pending(struct file_lock *fl, int arg)
 {
@@ -1503,12 +1531,10 @@ void lease_get_mtime(struct inode *inode, struct timespec *time)
 	ctx = smp_load_acquire(&inode->i_flctx);
 	if (ctx && !list_empty_careful(&ctx->flc_lease)) {
 		spin_lock(&ctx->flc_lock);
-		if (!list_empty(&ctx->flc_lease)) {
-			fl = list_first_entry(&ctx->flc_lease,
-						struct file_lock, fl_list);
-			if (fl->fl_type == F_WRLCK)
-				has_lease = true;
-		}
+		fl = list_first_entry_or_null(&ctx->flc_lease,
+					      struct file_lock, fl_list);
+		if (fl && (fl->fl_type == F_WRLCK))
+			has_lease = true;
 		spin_unlock(&ctx->flc_lock);
 	}
 
@@ -1624,12 +1650,12 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	 * bother, maybe that's a sign this just isn't a good file to
 	 * hand out a delegation on.
 	 */
-	if (is_deleg && !mutex_trylock(&inode->i_mutex))
+	if (is_deleg && !inode_trylock(inode))
 		return -EAGAIN;
 
 	if (is_deleg && arg == F_WRLCK) {
 		/* Write delegations are not currently supported: */
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 		WARN_ON_ONCE(1);
 		return -EINVAL;
 	}
@@ -1706,7 +1732,7 @@ out:
 	spin_unlock(&ctx->flc_lock);
 	locks_dispose_list(&dispose);
 	if (is_deleg)
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 	if (!error && !my_fl)
 		*flp = NULL;
 	return error;
@@ -2165,6 +2191,8 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
 	if (file_lock == NULL)
 		return -ENOLCK;
 
+	inode = file_inode(filp);
+
 	/*
 	 * This might block, so we do it before checking the inode.
 	 */
@@ -2172,8 +2200,6 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
 	if (copy_from_user(&flock, l, sizeof(flock)))
 		goto out;
 
-	inode = file_inode(filp);
-
 	/* Don't allow mandatory locks on files that may be memory mapped
 	 * and shared.
 	 */
@@ -2182,7 +2208,6 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
 		goto out;
 	}
 
-again:
 	error = flock_to_posix_lock(filp, file_lock, &flock);
 	if (error)
 		goto out;
@@ -2221,23 +2246,29 @@ again:
 	error = do_lock_file_wait(filp, cmd, file_lock);
 
 	/*
-	 * Attempt to detect a close/fcntl race and recover by
-	 * releasing the lock that was just acquired.
-	 */
-	/*
-	 * we need that spin_lock here - it prevents reordering between
-	 * update of i_flctx->flc_posix and check for it done in close().
-	 * rcu_read_lock() wouldn't do.
+	 * Attempt to detect a close/fcntl race and recover by releasing the
+	 * lock that was just acquired. There is no need to do that when we're
+	 * unlocking though, or for OFD locks.
 	 */
-	spin_lock(&current->files->file_lock);
-	f = fcheck(fd);
-	spin_unlock(&current->files->file_lock);
-	if (!error && f != filp && flock.l_type != F_UNLCK) {
-		flock.l_type = F_UNLCK;
-		goto again;
+	if (!error && file_lock->fl_type != F_UNLCK &&
+	    !(file_lock->fl_flags & FL_OFDLCK)) {
+		/*
+		 * We need that spin_lock here - it prevents reordering between
+		 * update of i_flctx->flc_posix and check for it done in
+		 * close(). rcu_read_lock() wouldn't do.
+		 */
+		spin_lock(&current->files->file_lock);
+		f = fcheck(fd);
+		spin_unlock(&current->files->file_lock);
+		if (f != filp) {
+			file_lock->fl_type = F_UNLCK;
+			error = do_lock_file_wait(filp, cmd, file_lock);
+			WARN_ON_ONCE(error);
+			error = -EBADF;
+		}
 	}
-
 out:
+	trace_fcntl_setlk(inode, file_lock, error);
 	locks_free_lock(file_lock);
 	return error;
 }
@@ -2322,7 +2353,6 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
 		goto out;
 	}
 
-again:
 	error = flock64_to_posix_lock(filp, file_lock, &flock);
 	if (error)
 		goto out;
@@ -2361,17 +2391,27 @@ again:
 	error = do_lock_file_wait(filp, cmd, file_lock);
 
 	/*
-	 * Attempt to detect a close/fcntl race and recover by
-	 * releasing the lock that was just acquired.
+	 * Attempt to detect a close/fcntl race and recover by releasing the
+	 * lock that was just acquired. There is no need to do that when we're
+	 * unlocking though, or for OFD locks.
 	 */
-	spin_lock(&current->files->file_lock);
-	f = fcheck(fd);
-	spin_unlock(&current->files->file_lock);
-	if (!error && f != filp && flock.l_type != F_UNLCK) {
-		flock.l_type = F_UNLCK;
-		goto again;
+	if (!error && file_lock->fl_type != F_UNLCK &&
+	    !(file_lock->fl_flags & FL_OFDLCK)) {
+		/*
+		 * We need that spin_lock here - it prevents reordering between
+		 * update of i_flctx->flc_posix and check for it done in
+		 * close(). rcu_read_lock() wouldn't do.
+		 */
+		spin_lock(&current->files->file_lock);
+		f = fcheck(fd);
+		spin_unlock(&current->files->file_lock);
+		if (f != filp) {
+			file_lock->fl_type = F_UNLCK;
+			error = do_lock_file_wait(filp, cmd, file_lock);
+			WARN_ON_ONCE(error);
+			error = -EBADF;
+		}
 	}
-
 out:
 	locks_free_lock(file_lock);
 	return error;
@@ -2385,6 +2425,7 @@ out:
  */
 void locks_remove_posix(struct file *filp, fl_owner_t owner)
 {
+	int error;
 	struct file_lock lock;
 	struct file_lock_context *ctx;
 
@@ -2407,10 +2448,11 @@ void locks_remove_posix(struct file *filp, fl_owner_t owner)
 	lock.fl_ops = NULL;
 	lock.fl_lmops = NULL;
 
-	vfs_lock_file(filp, F_SETLK, &lock, NULL);
+	error = vfs_lock_file(filp, F_SETLK, &lock, NULL);
 
 	if (lock.fl_ops && lock.fl_ops->fl_release_private)
 		lock.fl_ops->fl_release_private(&lock);
+	trace_locks_remove_posix(file_inode(filp), &lock, error);
 }
 
 EXPORT_SYMBOL(locks_remove_posix);
@@ -2706,7 +2748,7 @@ static int __init proc_locks_init(void)
 	proc_create("locks", 0, NULL, &proc_locks_operations);
 	return 0;
 }
-module_init(proc_locks_init);
+fs_initcall(proc_locks_init);
 #endif
 
 static int __init filelock_init(void)
diff --git a/fs/logfs/Kconfig b/fs/logfs/Kconfig
index 09ed066c0221..2b4503163930 100644
--- a/fs/logfs/Kconfig
+++ b/fs/logfs/Kconfig
@@ -1,6 +1,6 @@
 config LOGFS
 	tristate "LogFS file system"
-	depends on (MTD || BLOCK)
+	depends on MTD || (!MTD && BLOCK)
 	select ZLIB_INFLATE
 	select ZLIB_DEFLATE
 	select CRC32
diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c
index a709d80c8ebc..cc26f8f215f5 100644
--- a/fs/logfs/dev_bdev.c
+++ b/fs/logfs/dev_bdev.c
@@ -64,7 +64,7 @@ static void writeseg_end_io(struct bio *bio)
 
 	bio_for_each_segment_all(bvec, bio, i) {
 		end_page_writeback(bvec->bv_page);
-		page_cache_release(bvec->bv_page);
+		put_page(bvec->bv_page);
 	}
 	bio_put(bio);
 	if (atomic_dec_and_test(&super->s_pending_writes))
diff --git a/fs/logfs/dev_mtd.c b/fs/logfs/dev_mtd.c
index 9c501449450d..b76a62b1978f 100644
--- a/fs/logfs/dev_mtd.c
+++ b/fs/logfs/dev_mtd.c
@@ -46,9 +46,9 @@ static int loffs_mtd_write(struct super_block *sb, loff_t ofs, size_t len,
 
 	BUG_ON((ofs >= mtd->size) || (len > mtd->size - ofs));
 	BUG_ON(ofs != (ofs >> super->s_writeshift) << super->s_writeshift);
-	BUG_ON(len > PAGE_CACHE_SIZE);
-	page_start = ofs & PAGE_CACHE_MASK;
-	page_end = PAGE_CACHE_ALIGN(ofs + len) - 1;
+	BUG_ON(len > PAGE_SIZE);
+	page_start = ofs & PAGE_MASK;
+	page_end = PAGE_ALIGN(ofs + len) - 1;
 	ret = mtd_write(mtd, ofs, len, &retlen, buf);
 	if (ret || (retlen != len))
 		return -EIO;
@@ -82,7 +82,7 @@ static int logfs_mtd_erase_mapping(struct super_block *sb, loff_t ofs,
 		if (!page)
 			continue;
 		memset(page_address(page), 0xFF, PAGE_SIZE);
-		page_cache_release(page);
+		put_page(page);
 	}
 	return 0;
 }
@@ -195,7 +195,7 @@ static int __logfs_mtd_writeseg(struct super_block *sb, u64 ofs, pgoff_t index,
 		err = loffs_mtd_write(sb, page->index << PAGE_SHIFT, PAGE_SIZE,
 					page_address(page));
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 		if (err)
 			return err;
 	}
diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c
index f9b45d46d4c4..ddbed2be5366 100644
--- a/fs/logfs/dir.c
+++ b/fs/logfs/dir.c
@@ -183,7 +183,7 @@ static struct page *logfs_get_dd_page(struct inode *dir, struct dentry *dentry)
 		if (name->len != be16_to_cpu(dd->namelen) ||
 				memcmp(name->name, dd->name, name->len)) {
 			kunmap_atomic(dd);
-			page_cache_release(page);
+			put_page(page);
 			continue;
 		}
 
@@ -238,7 +238,7 @@ static int logfs_unlink(struct inode *dir, struct dentry *dentry)
 		return PTR_ERR(page);
 	}
 	index = page->index;
-	page_cache_release(page);
+	put_page(page);
 
 	mutex_lock(&super->s_dirop_mutex);
 	logfs_add_transaction(dir, ta);
@@ -316,7 +316,7 @@ static int logfs_readdir(struct file *file, struct dir_context *ctx)
 				be16_to_cpu(dd->namelen),
 				be64_to_cpu(dd->ino), dd->type);
 		kunmap(page);
-		page_cache_release(page);
+		put_page(page);
 		if (full)
 			break;
 	}
@@ -349,7 +349,7 @@ static struct dentry *logfs_lookup(struct inode *dir, struct dentry *dentry,
 	dd = kmap_atomic(page);
 	ino = be64_to_cpu(dd->ino);
 	kunmap_atomic(dd);
-	page_cache_release(page);
+	put_page(page);
 
 	inode = logfs_iget(dir->i_sb, ino);
 	if (IS_ERR(inode))
@@ -392,7 +392,7 @@ static int logfs_write_dir(struct inode *dir, struct dentry *dentry,
 
 		err = logfs_write_buf(dir, page, WF_LOCK);
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 		if (!err)
 			grow_dir(dir, index);
 		return err;
@@ -528,7 +528,8 @@ static int logfs_symlink(struct inode *dir, struct dentry *dentry,
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 
-	inode->i_op = &logfs_symlink_iops;
+	inode->i_op = &page_symlink_inode_operations;
+	inode_nohighmem(inode);
 	inode->i_mapping->a_ops = &logfs_reg_aops;
 
 	return __logfs_create(dir, dentry, inode, target, destlen);
@@ -560,7 +561,7 @@ static int logfs_get_dd(struct inode *dir, struct dentry *dentry,
 	map = kmap_atomic(page);
 	memcpy(dd, map, sizeof(*dd));
 	kunmap_atomic(map);
-	page_cache_release(page);
+	put_page(page);
 	return 0;
 }
 
@@ -776,12 +777,6 @@ fail:
 	return -EIO;
 }
 
-const struct inode_operations logfs_symlink_iops = {
-	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
-};
-
 const struct inode_operations logfs_dir_iops = {
 	.create		= logfs_create,
 	.link		= logfs_link,
diff --git a/fs/logfs/file.c b/fs/logfs/file.c
index 1a6f0167b16a..f01ddfb1a03b 100644
--- a/fs/logfs/file.c
+++ b/fs/logfs/file.c
@@ -15,21 +15,21 @@ static int logfs_write_begin(struct file *file, struct address_space *mapping,
 {
 	struct inode *inode = mapping->host;
 	struct page *page;
-	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+	pgoff_t index = pos >> PAGE_SHIFT;
 
 	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
 		return -ENOMEM;
 	*pagep = page;
 
-	if ((len == PAGE_CACHE_SIZE) || PageUptodate(page))
+	if ((len == PAGE_SIZE) || PageUptodate(page))
 		return 0;
-	if ((pos & PAGE_CACHE_MASK) >= i_size_read(inode)) {
-		unsigned start = pos & (PAGE_CACHE_SIZE - 1);
+	if ((pos & PAGE_MASK) >= i_size_read(inode)) {
+		unsigned start = pos & (PAGE_SIZE - 1);
 		unsigned end = start + len;
 
 		/* Reading beyond i_size is simple: memset to zero */
-		zero_user_segments(page, 0, start, end, PAGE_CACHE_SIZE);
+		zero_user_segments(page, 0, start, end, PAGE_SIZE);
 		return 0;
 	}
 	return logfs_readpage_nolock(page);
@@ -41,11 +41,11 @@ static int logfs_write_end(struct file *file, struct address_space *mapping,
 {
 	struct inode *inode = mapping->host;
 	pgoff_t index = page->index;
-	unsigned start = pos & (PAGE_CACHE_SIZE - 1);
+	unsigned start = pos & (PAGE_SIZE - 1);
 	unsigned end = start + copied;
 	int ret = 0;
 
-	BUG_ON(PAGE_CACHE_SIZE != inode->i_sb->s_blocksize);
+	BUG_ON(PAGE_SIZE != inode->i_sb->s_blocksize);
 	BUG_ON(page->index > I3_BLOCKS);
 
 	if (copied < len) {
@@ -61,8 +61,8 @@ static int logfs_write_end(struct file *file, struct address_space *mapping,
 	if (copied == 0)
 		goto out; /* FIXME: do we need to update inode? */
 
-	if (i_size_read(inode) < (index << PAGE_CACHE_SHIFT) + end) {
-		i_size_write(inode, (index << PAGE_CACHE_SHIFT) + end);
+	if (i_size_read(inode) < (index << PAGE_SHIFT) + end) {
+		i_size_write(inode, (index << PAGE_SHIFT) + end);
 		mark_inode_dirty_sync(inode);
 	}
 
@@ -75,7 +75,7 @@ static int logfs_write_end(struct file *file, struct address_space *mapping,
 	}
 out:
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 	return ret ? ret : copied;
 }
 
@@ -118,7 +118,7 @@ static int logfs_writepage(struct page *page, struct writeback_control *wbc)
 {
 	struct inode *inode = page->mapping->host;
 	loff_t i_size = i_size_read(inode);
-	pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
+	pgoff_t end_index = i_size >> PAGE_SHIFT;
 	unsigned offset;
 	u64 bix;
 	level_t level;
@@ -142,7 +142,7 @@ static int logfs_writepage(struct page *page, struct writeback_control *wbc)
 		return __logfs_writepage(page);
 
 	 /* Is the page fully outside i_size? (truncate in progress) */
-	offset = i_size & (PAGE_CACHE_SIZE-1);
+	offset = i_size & (PAGE_SIZE-1);
 	if (bix > end_index || offset == 0) {
 		unlock_page(page);
 		return 0; /* don't care */
@@ -155,7 +155,7 @@ static int logfs_writepage(struct page *page, struct writeback_control *wbc)
 	 * the  page size, the remaining memory is zeroed when mapped, and
 	 * writes to that region are not written out to the file."
 	 */
-	zero_user_segment(page, offset, PAGE_CACHE_SIZE);
+	zero_user_segment(page, offset, PAGE_SIZE);
 	return __logfs_writepage(page);
 }
 
@@ -204,12 +204,12 @@ long logfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		if (err)
 			return err;
 
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		oldflags = li->li_flags;
 		flags &= LOGFS_FL_USER_MODIFIABLE;
 		flags |= oldflags & ~LOGFS_FL_USER_MODIFIABLE;
 		li->li_flags = flags;
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 
 		inode->i_ctime = CURRENT_TIME;
 		mark_inode_dirty_sync(inode);
@@ -230,11 +230,11 @@ int logfs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	if (ret)
 		return ret;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	logfs_get_wblocks(sb, NULL, WF_LOCK);
 	logfs_write_anchor(sb);
 	logfs_put_wblocks(sb, NULL, WF_LOCK);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	return 0;
 }
diff --git a/fs/logfs/inode.c b/fs/logfs/inode.c
index af49e2d6941a..db9cfc598883 100644
--- a/fs/logfs/inode.c
+++ b/fs/logfs/inode.c
@@ -64,7 +64,8 @@ static void logfs_inode_setops(struct inode *inode)
 		inode->i_mapping->a_ops = &logfs_reg_aops;
 		break;
 	case S_IFLNK:
-		inode->i_op = &logfs_symlink_iops;
+		inode->i_op = &page_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &logfs_reg_aops;
 		break;
 	case S_IFSOCK:	/* fall through */
@@ -408,7 +409,8 @@ const struct super_operations logfs_super_operations = {
 int logfs_init_inode_cache(void)
 {
 	logfs_inode_cache = kmem_cache_create("logfs_inode_cache",
-			sizeof(struct logfs_inode), 0, SLAB_RECLAIM_ACCOUNT,
+			sizeof(struct logfs_inode), 0,
+			SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT,
 			logfs_init_once);
 	if (!logfs_inode_cache)
 		return -ENOMEM;
diff --git a/fs/logfs/logfs.h b/fs/logfs/logfs.h
index 5f0937609465..27d040e35faa 100644
--- a/fs/logfs/logfs.h
+++ b/fs/logfs/logfs.h
@@ -302,7 +302,7 @@ struct logfs_block {
 	struct inode *inode;
 	struct logfs_transaction *ta;
 	unsigned long alias_map[LOGFS_BLOCK_FACTOR / BITS_PER_LONG];
-	struct logfs_block_ops *ops;
+	const struct logfs_block_ops *ops;
 	int full;
 	int partial;
 	int reserved_bytes;
@@ -485,7 +485,7 @@ static inline int logfs_get_sb_bdev(struct logfs_super *s,
 #endif
 
 /* dev_mtd.c */
-#ifdef CONFIG_MTD
+#if IS_ENABLED(CONFIG_MTD)
 int logfs_get_sb_mtd(struct logfs_super *s, int mtdnr);
 #else
 static inline int logfs_get_sb_mtd(struct logfs_super *s, int mtdnr)
@@ -495,7 +495,6 @@ static inline int logfs_get_sb_mtd(struct logfs_super *s, int mtdnr)
 #endif
 
 /* dir.c */
-extern const struct inode_operations logfs_symlink_iops;
 extern const struct inode_operations logfs_dir_iops;
 extern const struct file_operations logfs_dir_fops;
 int logfs_replay_journal(struct super_block *sb);
@@ -579,7 +578,7 @@ int logfs_exist_block(struct inode *inode, u64 bix);
 int get_page_reserve(struct inode *inode, struct page *page);
 void logfs_get_wblocks(struct super_block *sb, struct page *page, int lock);
 void logfs_put_wblocks(struct super_block *sb, struct page *page, int lock);
-extern struct logfs_block_ops indirect_block_ops;
+extern const struct logfs_block_ops indirect_block_ops;
 
 /* segment.c */
 int logfs_erase_segment(struct super_block *sb, u32 ofs, int ensure_erase);
diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c
index 380d86e1ab45..3fb8c6d67303 100644
--- a/fs/logfs/readwrite.c
+++ b/fs/logfs/readwrite.c
@@ -281,7 +281,7 @@ static struct page *logfs_get_read_page(struct inode *inode, u64 bix,
 static void logfs_put_read_page(struct page *page)
 {
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 }
 
 static void logfs_lock_write_page(struct page *page)
@@ -323,7 +323,7 @@ repeat:
 			return NULL;
 		err = add_to_page_cache_lru(page, mapping, index, GFP_NOFS);
 		if (unlikely(err)) {
-			page_cache_release(page);
+			put_page(page);
 			if (err == -EEXIST)
 				goto repeat;
 			return NULL;
@@ -342,7 +342,7 @@ static void logfs_unlock_write_page(struct page *page)
 static void logfs_put_write_page(struct page *page)
 {
 	logfs_unlock_write_page(page);
-	page_cache_release(page);
+	put_page(page);
 }
 
 static struct page *logfs_get_page(struct inode *inode, u64 bix, level_t level,
@@ -562,20 +562,20 @@ static void indirect_free_block(struct super_block *sb,
 
 	if (PagePrivate(page)) {
 		ClearPagePrivate(page);
-		page_cache_release(page);
+		put_page(page);
 		set_page_private(page, 0);
 	}
 	__free_block(sb, block);
 }
 
 
-static struct logfs_block_ops inode_block_ops = {
+static const struct logfs_block_ops inode_block_ops = {
 	.write_block = inode_write_block,
 	.free_block = inode_free_block,
 	.write_alias = inode_write_alias,
 };
 
-struct logfs_block_ops indirect_block_ops = {
+const struct logfs_block_ops indirect_block_ops = {
 	.write_block = indirect_write_block,
 	.free_block = indirect_free_block,
 	.write_alias = indirect_write_alias,
@@ -655,7 +655,7 @@ static void alloc_data_block(struct inode *inode, struct page *page)
 	block->page = page;
 
 	SetPagePrivate(page);
-	page_cache_get(page);
+	get_page(page);
 	set_page_private(page, (unsigned long) block);
 
 	block->ops = &indirect_block_ops;
@@ -709,7 +709,7 @@ static u64 block_get_pointer(struct page *page, int index)
 
 static int logfs_read_empty(struct page *page)
 {
-	zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+	zero_user_segment(page, 0, PAGE_SIZE);
 	return 0;
 }
 
@@ -1660,7 +1660,7 @@ static int truncate_data_block(struct inode *inode, struct page *page,
 	if (err)
 		return err;
 
-	zero_user_segment(page, size - pageofs, PAGE_CACHE_SIZE);
+	zero_user_segment(page, size - pageofs, PAGE_SIZE);
 	return logfs_segment_write(inode, page, shadow);
 }
 
@@ -1919,7 +1919,7 @@ static void move_page_to_inode(struct inode *inode, struct page *page)
 	block->page = NULL;
 	if (PagePrivate(page)) {
 		ClearPagePrivate(page);
-		page_cache_release(page);
+		put_page(page);
 		set_page_private(page, 0);
 	}
 }
@@ -1940,7 +1940,7 @@ static void move_inode_to_page(struct page *page, struct inode *inode)
 
 	if (!PagePrivate(page)) {
 		SetPagePrivate(page);
-		page_cache_get(page);
+		get_page(page);
 		set_page_private(page, (unsigned long) block);
 	}
 
@@ -1971,7 +1971,7 @@ int logfs_read_inode(struct inode *inode)
 	logfs_disk_to_inode(di, inode);
 	kunmap_atomic(di);
 	move_page_to_inode(inode, page);
-	page_cache_release(page);
+	put_page(page);
 	return 0;
 }
 
diff --git a/fs/logfs/segment.c b/fs/logfs/segment.c
index 7f9b096d8d57..1efd6055f4b0 100644
--- a/fs/logfs/segment.c
+++ b/fs/logfs/segment.c
@@ -57,7 +57,7 @@ static struct page *get_mapping_page(struct super_block *sb, pgoff_t index,
 	filler_t *filler = super->s_devops->readpage;
 	struct page *page;
 
-	BUG_ON(mapping_gfp_mask(mapping) & __GFP_FS);
+	BUG_ON(mapping_gfp_constraint(mapping, __GFP_FS));
 	if (use_filler)
 		page = read_cache_page(mapping, index, filler, sb);
 	else {
@@ -90,9 +90,9 @@ int __logfs_buf_write(struct logfs_area *area, u64 ofs, void *buf, size_t len,
 
 		if (!PagePrivate(page)) {
 			SetPagePrivate(page);
-			page_cache_get(page);
+			get_page(page);
 		}
-		page_cache_release(page);
+		put_page(page);
 
 		buf += copylen;
 		len -= copylen;
@@ -117,9 +117,9 @@ static void pad_partial_page(struct logfs_area *area)
 		memset(page_address(page) + offset, 0xff, len);
 		if (!PagePrivate(page)) {
 			SetPagePrivate(page);
-			page_cache_get(page);
+			get_page(page);
 		}
-		page_cache_release(page);
+		put_page(page);
 	}
 }
 
@@ -129,20 +129,20 @@ static void pad_full_pages(struct logfs_area *area)
 	struct logfs_super *super = logfs_super(sb);
 	u64 ofs = dev_ofs(sb, area->a_segno, area->a_used_bytes);
 	u32 len = super->s_segsize - area->a_used_bytes;
-	pgoff_t index = PAGE_CACHE_ALIGN(ofs) >> PAGE_CACHE_SHIFT;
-	pgoff_t no_indizes = len >> PAGE_CACHE_SHIFT;
+	pgoff_t index = PAGE_ALIGN(ofs) >> PAGE_SHIFT;
+	pgoff_t no_indizes = len >> PAGE_SHIFT;
 	struct page *page;
 
 	while (no_indizes) {
 		page = get_mapping_page(sb, index, 0);
 		BUG_ON(!page); /* FIXME: reserve a pool */
 		SetPageUptodate(page);
-		memset(page_address(page), 0xff, PAGE_CACHE_SIZE);
+		memset(page_address(page), 0xff, PAGE_SIZE);
 		if (!PagePrivate(page)) {
 			SetPagePrivate(page);
-			page_cache_get(page);
+			get_page(page);
 		}
-		page_cache_release(page);
+		put_page(page);
 		index++;
 		no_indizes--;
 	}
@@ -197,7 +197,7 @@ static int btree_write_alias(struct super_block *sb, struct logfs_block *block,
 	return 0;
 }
 
-static struct logfs_block_ops btree_block_ops = {
+static const struct logfs_block_ops btree_block_ops = {
 	.write_block	= btree_write_block,
 	.free_block	= __free_block,
 	.write_alias	= btree_write_alias,
@@ -411,7 +411,7 @@ int wbuf_read(struct super_block *sb, u64 ofs, size_t len, void *buf)
 		if (IS_ERR(page))
 			return PTR_ERR(page);
 		memcpy(buf, page_address(page) + offset, copylen);
-		page_cache_release(page);
+		put_page(page);
 
 		buf += copylen;
 		len -= copylen;
@@ -499,7 +499,7 @@ static void move_btree_to_page(struct inode *inode, struct page *page,
 
 	if (!PagePrivate(page)) {
 		SetPagePrivate(page);
-		page_cache_get(page);
+		get_page(page);
 		set_page_private(page, (unsigned long) block);
 	}
 	block->ops = &indirect_block_ops;
@@ -554,7 +554,7 @@ void move_page_to_btree(struct page *page)
 
 	if (PagePrivate(page)) {
 		ClearPagePrivate(page);
-		page_cache_release(page);
+		put_page(page);
 		set_page_private(page, 0);
 	}
 	block->ops = &btree_block_ops;
@@ -723,9 +723,9 @@ void freeseg(struct super_block *sb, u32 segno)
 			continue;
 		if (PagePrivate(page)) {
 			ClearPagePrivate(page);
-			page_cache_release(page);
+			put_page(page);
 		}
-		page_cache_release(page);
+		put_page(page);
 	}
 }
 
diff --git a/fs/logfs/super.c b/fs/logfs/super.c
index 54360293bcb5..5751082dba52 100644
--- a/fs/logfs/super.c
+++ b/fs/logfs/super.c
@@ -48,7 +48,7 @@ void emergency_read_end(struct page *page)
 	if (page == emergency_page)
 		mutex_unlock(&emergency_mutex);
 	else
-		page_cache_release(page);
+		put_page(page);
 }
 
 static void dump_segfile(struct super_block *sb)
@@ -206,7 +206,7 @@ static int write_one_sb(struct super_block *sb,
 	logfs_set_segment_erased(sb, segno, ec, 0);
 	logfs_write_ds(sb, ds, segno, ec);
 	err = super->s_devops->write_sb(sb, page);
-	page_cache_release(page);
+	put_page(page);
 	return err;
 }
 
@@ -366,24 +366,24 @@ static struct page *find_super_block(struct super_block *sb)
 		return NULL;
 	last = super->s_devops->find_last_sb(sb, &super->s_sb_ofs[1]);
 	if (!last || IS_ERR(last)) {
-		page_cache_release(first);
+		put_page(first);
 		return NULL;
 	}
 
 	if (!logfs_check_ds(page_address(first))) {
-		page_cache_release(last);
+		put_page(last);
 		return first;
 	}
 
 	/* First one didn't work, try the second superblock */
 	if (!logfs_check_ds(page_address(last))) {
-		page_cache_release(first);
+		put_page(first);
 		return last;
 	}
 
 	/* Neither worked, sorry folks */
-	page_cache_release(first);
-	page_cache_release(last);
+	put_page(first);
+	put_page(last);
 	return NULL;
 }
 
@@ -425,7 +425,7 @@ static int __logfs_read_sb(struct super_block *sb)
 	super->s_data_levels = ds->ds_data_levels;
 	super->s_total_levels = super->s_ifile_levels + super->s_iblock_levels
 		+ super->s_data_levels;
-	page_cache_release(page);
+	put_page(page);
 	return 0;
 }
 
diff --git a/fs/mbcache.c b/fs/mbcache.c
index 187477ded6b3..eccda3a02de6 100644
--- a/fs/mbcache.c
+++ b/fs/mbcache.c
@@ -1,858 +1,433 @@
-/*
- * linux/fs/mbcache.c
- * (C) 2001-2002 Andreas Gruenbacher, <a.gruenbacher@computer.org>
- */
-
-/*
- * Filesystem Meta Information Block Cache (mbcache)
- *
- * The mbcache caches blocks of block devices that need to be located
- * by their device/block number, as well as by other criteria (such
- * as the block's contents).
- *
- * There can only be one cache entry in a cache per device and block number.
- * Additional indexes need not be unique in this sense. The number of
- * additional indexes (=other criteria) can be hardwired at compile time
- * or specified at cache create time.
- *
- * Each cache entry is of fixed size. An entry may be `valid' or `invalid'
- * in the cache. A valid entry is in the main hash tables of the cache,
- * and may also be in the lru list. An invalid entry is not in any hashes
- * or lists.
- *
- * A valid cache entry is only in the lru list if no handles refer to it.
- * Invalid cache entries will be freed when the last handle to the cache
- * entry is released. Entries that cannot be freed immediately are put
- * back on the lru list.
- */
-
-/*
- * Lock descriptions and usage:
- *
- * Each hash chain of both the block and index hash tables now contains
- * a built-in lock used to serialize accesses to the hash chain.
- *
- * Accesses to global data structures mb_cache_list and mb_cache_lru_list
- * are serialized via the global spinlock mb_cache_spinlock.
- *
- * Each mb_cache_entry contains a spinlock, e_entry_lock, to serialize
- * accesses to its local data, such as e_used and e_queued.
- *
- * Lock ordering:
- *
- * Each block hash chain's lock has the highest lock order, followed by an
- * index hash chain's lock, mb_cache_bg_lock (used to implement mb_cache_entry's
- * lock), and mb_cach_spinlock, with the lowest order.  While holding
- * either a block or index hash chain lock, a thread can acquire an
- * mc_cache_bg_lock, which in turn can also acquire mb_cache_spinlock.
- *
- * Synchronization:
- *
- * Since both mb_cache_entry_get and mb_cache_entry_find scan the block and
- * index hash chian, it needs to lock the corresponding hash chain.  For each
- * mb_cache_entry within the chain, it needs to lock the mb_cache_entry to
- * prevent either any simultaneous release or free on the entry and also
- * to serialize accesses to either the e_used or e_queued member of the entry.
- *
- * To avoid having a dangling reference to an already freed
- * mb_cache_entry, an mb_cache_entry is only freed when it is not on a
- * block hash chain and also no longer being referenced, both e_used,
- * and e_queued are 0's.  When an mb_cache_entry is explicitly freed it is
- * first removed from a block hash chain.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-#include <linux/hash.h>
-#include <linux/fs.h>
-#include <linux/mm.h>
+#include <linux/spinlock.h>
 #include <linux/slab.h>
-#include <linux/sched.h>
+#include <linux/list.h>
 #include <linux/list_bl.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/workqueue.h>
 #include <linux/mbcache.h>
-#include <linux/init.h>
-#include <linux/blockgroup_lock.h>
-#include <linux/log2.h>
-
-#ifdef MB_CACHE_DEBUG
-# define mb_debug(f...) do { \
-		printk(KERN_DEBUG f); \
-		printk("\n"); \
-	} while (0)
-#define mb_assert(c) do { if (!(c)) \
-		printk(KERN_ERR "assertion " #c " failed\n"); \
-	} while(0)
-#else
-# define mb_debug(f...) do { } while(0)
-# define mb_assert(c) do { } while(0)
-#endif
-#define mb_error(f...) do { \
-		printk(KERN_ERR f); \
-		printk("\n"); \
-	} while(0)
-
-#define MB_CACHE_WRITER ((unsigned short)~0U >> 1)
-
-#define MB_CACHE_ENTRY_LOCK_BITS	ilog2(NR_BG_LOCKS)
-#define	MB_CACHE_ENTRY_LOCK_INDEX(ce)			\
-	(hash_long((unsigned long)ce, MB_CACHE_ENTRY_LOCK_BITS))
-
-static DECLARE_WAIT_QUEUE_HEAD(mb_cache_queue);
-static struct blockgroup_lock *mb_cache_bg_lock;
-static struct kmem_cache *mb_cache_kmem_cache;
-
-MODULE_AUTHOR("Andreas Gruenbacher <a.gruenbacher@computer.org>");
-MODULE_DESCRIPTION("Meta block cache (for extended attributes)");
-MODULE_LICENSE("GPL");
-
-EXPORT_SYMBOL(mb_cache_create);
-EXPORT_SYMBOL(mb_cache_shrink);
-EXPORT_SYMBOL(mb_cache_destroy);
-EXPORT_SYMBOL(mb_cache_entry_alloc);
-EXPORT_SYMBOL(mb_cache_entry_insert);
-EXPORT_SYMBOL(mb_cache_entry_release);
-EXPORT_SYMBOL(mb_cache_entry_free);
-EXPORT_SYMBOL(mb_cache_entry_get);
-#if !defined(MB_CACHE_INDEXES_COUNT) || (MB_CACHE_INDEXES_COUNT > 0)
-EXPORT_SYMBOL(mb_cache_entry_find_first);
-EXPORT_SYMBOL(mb_cache_entry_find_next);
-#endif
 
 /*
- * Global data: list of all mbcache's, lru list, and a spinlock for
- * accessing cache data structures on SMP machines. The lru list is
- * global across all mbcaches.
+ * Mbcache is a simple key-value store. Keys need not be unique, however
+ * key-value pairs are expected to be unique (we use this fact in
+ * mb_cache_entry_delete_block()).
+ *
+ * Ext2 and ext4 use this cache for deduplication of extended attribute blocks.
+ * They use hash of a block contents as a key and block number as a value.
+ * That's why keys need not be unique (different xattr blocks may end up having
+ * the same hash). However block number always uniquely identifies a cache
+ * entry.
+ *
+ * We provide functions for creation and removal of entries, search by key,
+ * and a special "delete entry with given key-value pair" operation. Fixed
+ * size hash table is used for fast key lookups.
  */
 
-static LIST_HEAD(mb_cache_list);
-static LIST_HEAD(mb_cache_lru_list);
-static DEFINE_SPINLOCK(mb_cache_spinlock);
-
-static inline void
-__spin_lock_mb_cache_entry(struct mb_cache_entry *ce)
-{
-	spin_lock(bgl_lock_ptr(mb_cache_bg_lock,
-		MB_CACHE_ENTRY_LOCK_INDEX(ce)));
-}
-
-static inline void
-__spin_unlock_mb_cache_entry(struct mb_cache_entry *ce)
-{
-	spin_unlock(bgl_lock_ptr(mb_cache_bg_lock,
-		MB_CACHE_ENTRY_LOCK_INDEX(ce)));
-}
-
-static inline int
-__mb_cache_entry_is_block_hashed(struct mb_cache_entry *ce)
-{
-	return !hlist_bl_unhashed(&ce->e_block_list);
-}
+struct mb_cache {
+	/* Hash table of entries */
+	struct hlist_bl_head	*c_hash;
+	/* log2 of hash table size */
+	int			c_bucket_bits;
+	/* Maximum entries in cache to avoid degrading hash too much */
+	int			c_max_entries;
+	/* Protects c_list, c_entry_count */
+	spinlock_t		c_list_lock;
+	struct list_head	c_list;
+	/* Number of entries in cache */
+	unsigned long		c_entry_count;
+	struct shrinker		c_shrink;
+	/* Work for shrinking when the cache has too many entries */
+	struct work_struct	c_shrink_work;
+};
 
+static struct kmem_cache *mb_entry_cache;
 
-static inline void
-__mb_cache_entry_unhash_block(struct mb_cache_entry *ce)
-{
-	if (__mb_cache_entry_is_block_hashed(ce))
-		hlist_bl_del_init(&ce->e_block_list);
-}
+static unsigned long mb_cache_shrink(struct mb_cache *cache,
+				     unsigned int nr_to_scan);
 
-static inline int
-__mb_cache_entry_is_index_hashed(struct mb_cache_entry *ce)
+static inline struct hlist_bl_head *mb_cache_entry_head(struct mb_cache *cache,
+							u32 key)
 {
-	return !hlist_bl_unhashed(&ce->e_index.o_list);
+	return &cache->c_hash[hash_32(key, cache->c_bucket_bits)];
 }
 
-static inline void
-__mb_cache_entry_unhash_index(struct mb_cache_entry *ce)
-{
-	if (__mb_cache_entry_is_index_hashed(ce))
-		hlist_bl_del_init(&ce->e_index.o_list);
-}
+/*
+ * Number of entries to reclaim synchronously when there are too many entries
+ * in cache
+ */
+#define SYNC_SHRINK_BATCH 64
 
 /*
- * __mb_cache_entry_unhash_unlock()
- *
- * This function is called to unhash both the block and index hash
- * chain.
- * It assumes both the block and index hash chain is locked upon entry.
- * It also unlock both hash chains both exit
+ * mb_cache_entry_create - create entry in cache
+ * @cache - cache where the entry should be created
+ * @mask - gfp mask with which the entry should be allocated
+ * @key - key of the entry
+ * @block - block that contains data
+ * @reusable - is the block reusable by other inodes?
+ *
+ * Creates entry in @cache with key @key and records that data is stored in
+ * block @block. The function returns -EBUSY if entry with the same key
+ * and for the same block already exists in cache. Otherwise 0 is returned.
  */
-static inline void
-__mb_cache_entry_unhash_unlock(struct mb_cache_entry *ce)
+int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key,
+			  sector_t block, bool reusable)
 {
-	__mb_cache_entry_unhash_index(ce);
-	hlist_bl_unlock(ce->e_index_hash_p);
-	__mb_cache_entry_unhash_block(ce);
-	hlist_bl_unlock(ce->e_block_hash_p);
+	struct mb_cache_entry *entry, *dup;
+	struct hlist_bl_node *dup_node;
+	struct hlist_bl_head *head;
+
+	/* Schedule background reclaim if there are too many entries */
+	if (cache->c_entry_count >= cache->c_max_entries)
+		schedule_work(&cache->c_shrink_work);
+	/* Do some sync reclaim if background reclaim cannot keep up */
+	if (cache->c_entry_count >= 2*cache->c_max_entries)
+		mb_cache_shrink(cache, SYNC_SHRINK_BATCH);
+
+	entry = kmem_cache_alloc(mb_entry_cache, mask);
+	if (!entry)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&entry->e_list);
+	/* One ref for hash, one ref returned */
+	atomic_set(&entry->e_refcnt, 1);
+	entry->e_key = key;
+	entry->e_block = block;
+	entry->e_reusable = reusable;
+	head = mb_cache_entry_head(cache, key);
+	hlist_bl_lock(head);
+	hlist_bl_for_each_entry(dup, dup_node, head, e_hash_list) {
+		if (dup->e_key == key && dup->e_block == block) {
+			hlist_bl_unlock(head);
+			kmem_cache_free(mb_entry_cache, entry);
+			return -EBUSY;
+		}
+	}
+	hlist_bl_add_head(&entry->e_hash_list, head);
+	hlist_bl_unlock(head);
+
+	spin_lock(&cache->c_list_lock);
+	list_add_tail(&entry->e_list, &cache->c_list);
+	/* Grab ref for LRU list */
+	atomic_inc(&entry->e_refcnt);
+	cache->c_entry_count++;
+	spin_unlock(&cache->c_list_lock);
+
+	return 0;
 }
+EXPORT_SYMBOL(mb_cache_entry_create);
 
-static void
-__mb_cache_entry_forget(struct mb_cache_entry *ce, gfp_t gfp_mask)
+void __mb_cache_entry_free(struct mb_cache_entry *entry)
 {
-	struct mb_cache *cache = ce->e_cache;
-
-	mb_assert(!(ce->e_used || ce->e_queued || atomic_read(&ce->e_refcnt)));
-	kmem_cache_free(cache->c_entry_cache, ce);
-	atomic_dec(&cache->c_entry_count);
+	kmem_cache_free(mb_entry_cache, entry);
 }
+EXPORT_SYMBOL(__mb_cache_entry_free);
 
-static void
-__mb_cache_entry_release(struct mb_cache_entry *ce)
+static struct mb_cache_entry *__entry_find(struct mb_cache *cache,
+					   struct mb_cache_entry *entry,
+					   u32 key)
 {
-	/* First lock the entry to serialize access to its local data. */
-	__spin_lock_mb_cache_entry(ce);
-	/* Wake up all processes queuing for this cache entry. */
-	if (ce->e_queued)
-		wake_up_all(&mb_cache_queue);
-	if (ce->e_used >= MB_CACHE_WRITER)
-		ce->e_used -= MB_CACHE_WRITER;
-	/*
-	 * Make sure that all cache entries on lru_list have
-	 * both e_used and e_qued of 0s.
-	 */
-	ce->e_used--;
-	if (!(ce->e_used || ce->e_queued || atomic_read(&ce->e_refcnt))) {
-		if (!__mb_cache_entry_is_block_hashed(ce)) {
-			__spin_unlock_mb_cache_entry(ce);
-			goto forget;
+	struct mb_cache_entry *old_entry = entry;
+	struct hlist_bl_node *node;
+	struct hlist_bl_head *head;
+
+	head = mb_cache_entry_head(cache, key);
+	hlist_bl_lock(head);
+	if (entry && !hlist_bl_unhashed(&entry->e_hash_list))
+		node = entry->e_hash_list.next;
+	else
+		node = hlist_bl_first(head);
+	while (node) {
+		entry = hlist_bl_entry(node, struct mb_cache_entry,
+				       e_hash_list);
+		if (entry->e_key == key && entry->e_reusable) {
+			atomic_inc(&entry->e_refcnt);
+			goto out;
 		}
-		/*
-		 * Need access to lru list, first drop entry lock,
-		 * then reacquire the lock in the proper order.
-		 */
-		spin_lock(&mb_cache_spinlock);
-		if (list_empty(&ce->e_lru_list))
-			list_add_tail(&ce->e_lru_list, &mb_cache_lru_list);
-		spin_unlock(&mb_cache_spinlock);
+		node = node->next;
 	}
-	__spin_unlock_mb_cache_entry(ce);
-	return;
-forget:
-	mb_assert(list_empty(&ce->e_lru_list));
-	__mb_cache_entry_forget(ce, GFP_KERNEL);
+	entry = NULL;
+out:
+	hlist_bl_unlock(head);
+	if (old_entry)
+		mb_cache_entry_put(cache, old_entry);
+
+	return entry;
 }
 
 /*
- * mb_cache_shrink_scan()  memory pressure callback
- *
- * This function is called by the kernel memory management when memory
- * gets low.
+ * mb_cache_entry_find_first - find the first entry in cache with given key
+ * @cache: cache where we should search
+ * @key: key to look for
  *
- * @shrink: (ignored)
- * @sc: shrink_control passed from reclaim
- *
- * Returns the number of objects freed.
+ * Search in @cache for entry with key @key. Grabs reference to the first
+ * entry found and returns the entry.
  */
-static unsigned long
-mb_cache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
+struct mb_cache_entry *mb_cache_entry_find_first(struct mb_cache *cache,
+						 u32 key)
 {
-	LIST_HEAD(free_list);
-	struct mb_cache_entry *entry, *tmp;
-	int nr_to_scan = sc->nr_to_scan;
-	gfp_t gfp_mask = sc->gfp_mask;
-	unsigned long freed = 0;
-
-	mb_debug("trying to free %d entries", nr_to_scan);
-	spin_lock(&mb_cache_spinlock);
-	while ((nr_to_scan-- > 0) && !list_empty(&mb_cache_lru_list)) {
-		struct mb_cache_entry *ce =
-			list_entry(mb_cache_lru_list.next,
-				struct mb_cache_entry, e_lru_list);
-		list_del_init(&ce->e_lru_list);
-		if (ce->e_used || ce->e_queued || atomic_read(&ce->e_refcnt))
-			continue;
-		spin_unlock(&mb_cache_spinlock);
-		/* Prevent any find or get operation on the entry */
-		hlist_bl_lock(ce->e_block_hash_p);
-		hlist_bl_lock(ce->e_index_hash_p);
-		/* Ignore if it is touched by a find/get */
-		if (ce->e_used || ce->e_queued || atomic_read(&ce->e_refcnt) ||
-			!list_empty(&ce->e_lru_list)) {
-			hlist_bl_unlock(ce->e_index_hash_p);
-			hlist_bl_unlock(ce->e_block_hash_p);
-			spin_lock(&mb_cache_spinlock);
-			continue;
-		}
-		__mb_cache_entry_unhash_unlock(ce);
-		list_add_tail(&ce->e_lru_list, &free_list);
-		spin_lock(&mb_cache_spinlock);
-	}
-	spin_unlock(&mb_cache_spinlock);
-
-	list_for_each_entry_safe(entry, tmp, &free_list, e_lru_list) {
-		__mb_cache_entry_forget(entry, gfp_mask);
-		freed++;
-	}
-	return freed;
+	return __entry_find(cache, NULL, key);
 }
+EXPORT_SYMBOL(mb_cache_entry_find_first);
 
-static unsigned long
-mb_cache_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+/*
+ * mb_cache_entry_find_next - find next entry in cache with the same
+ * @cache: cache where we should search
+ * @entry: entry to start search from
+ *
+ * Finds next entry in the hash chain which has the same key as @entry.
+ * If @entry is unhashed (which can happen when deletion of entry races
+ * with the search), finds the first entry in the hash chain. The function
+ * drops reference to @entry and returns with a reference to the found entry.
+ */
+struct mb_cache_entry *mb_cache_entry_find_next(struct mb_cache *cache,
+						struct mb_cache_entry *entry)
 {
-	struct mb_cache *cache;
-	unsigned long count = 0;
-
-	spin_lock(&mb_cache_spinlock);
-	list_for_each_entry(cache, &mb_cache_list, c_cache_list) {
-		mb_debug("cache %s (%d)", cache->c_name,
-			  atomic_read(&cache->c_entry_count));
-		count += atomic_read(&cache->c_entry_count);
-	}
-	spin_unlock(&mb_cache_spinlock);
-
-	return vfs_pressure_ratio(count);
+	return __entry_find(cache, entry, entry->e_key);
 }
-
-static struct shrinker mb_cache_shrinker = {
-	.count_objects = mb_cache_shrink_count,
-	.scan_objects = mb_cache_shrink_scan,
-	.seeks = DEFAULT_SEEKS,
-};
+EXPORT_SYMBOL(mb_cache_entry_find_next);
 
 /*
- * mb_cache_create()  create a new cache
- *
- * All entries in one cache are equal size. Cache entries may be from
- * multiple devices. If this is the first mbcache created, registers
- * the cache with kernel memory management. Returns NULL if no more
- * memory was available.
- *
- * @name: name of the cache (informal)
- * @bucket_bits: log2(number of hash buckets)
+ * mb_cache_entry_get - get a cache entry by block number (and key)
+ * @cache - cache we work with
+ * @key - key of block number @block
+ * @block - block number
  */
-struct mb_cache *
-mb_cache_create(const char *name, int bucket_bits)
+struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key,
+					  sector_t block)
 {
-	int n, bucket_count = 1 << bucket_bits;
-	struct mb_cache *cache = NULL;
-
-	if (!mb_cache_bg_lock) {
-		mb_cache_bg_lock = kmalloc(sizeof(struct blockgroup_lock),
-			GFP_KERNEL);
-		if (!mb_cache_bg_lock)
-			return NULL;
-		bgl_lock_init(mb_cache_bg_lock);
-	}
-
-	cache = kmalloc(sizeof(struct mb_cache), GFP_KERNEL);
-	if (!cache)
-		return NULL;
-	cache->c_name = name;
-	atomic_set(&cache->c_entry_count, 0);
-	cache->c_bucket_bits = bucket_bits;
-	cache->c_block_hash = kmalloc(bucket_count *
-		sizeof(struct hlist_bl_head), GFP_KERNEL);
-	if (!cache->c_block_hash)
-		goto fail;
-	for (n=0; n<bucket_count; n++)
-		INIT_HLIST_BL_HEAD(&cache->c_block_hash[n]);
-	cache->c_index_hash = kmalloc(bucket_count *
-		sizeof(struct hlist_bl_head), GFP_KERNEL);
-	if (!cache->c_index_hash)
-		goto fail;
-	for (n=0; n<bucket_count; n++)
-		INIT_HLIST_BL_HEAD(&cache->c_index_hash[n]);
-	if (!mb_cache_kmem_cache) {
-		mb_cache_kmem_cache = kmem_cache_create(name,
-			sizeof(struct mb_cache_entry), 0,
-			SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL);
-		if (!mb_cache_kmem_cache)
-			goto fail2;
+	struct hlist_bl_node *node;
+	struct hlist_bl_head *head;
+	struct mb_cache_entry *entry;
+
+	head = mb_cache_entry_head(cache, key);
+	hlist_bl_lock(head);
+	hlist_bl_for_each_entry(entry, node, head, e_hash_list) {
+		if (entry->e_key == key && entry->e_block == block) {
+			atomic_inc(&entry->e_refcnt);
+			goto out;
+		}
 	}
-	cache->c_entry_cache = mb_cache_kmem_cache;
-
-	/*
-	 * Set an upper limit on the number of cache entries so that the hash
-	 * chains won't grow too long.
-	 */
-	cache->c_max_entries = bucket_count << 4;
-
-	spin_lock(&mb_cache_spinlock);
-	list_add(&cache->c_cache_list, &mb_cache_list);
-	spin_unlock(&mb_cache_spinlock);
-	return cache;
-
-fail2:
-	kfree(cache->c_index_hash);
-
-fail:
-	kfree(cache->c_block_hash);
-	kfree(cache);
-	return NULL;
+	entry = NULL;
+out:
+	hlist_bl_unlock(head);
+	return entry;
 }
+EXPORT_SYMBOL(mb_cache_entry_get);
 
-
-/*
- * mb_cache_shrink()
- *
- * Removes all cache entries of a device from the cache. All cache entries
- * currently in use cannot be freed, and thus remain in the cache. All others
- * are freed.
+/* mb_cache_entry_delete_block - remove information about block from cache
+ * @cache - cache we work with
+ * @key - key of block @block
+ * @block - block number
  *
- * @bdev: which device's cache entries to shrink
+ * Remove entry from cache @cache with key @key with data stored in @block.
  */
-void
-mb_cache_shrink(struct block_device *bdev)
+void mb_cache_entry_delete_block(struct mb_cache *cache, u32 key,
+				 sector_t block)
 {
-	LIST_HEAD(free_list);
-	struct list_head *l;
-	struct mb_cache_entry *ce, *tmp;
-
-	l = &mb_cache_lru_list;
-	spin_lock(&mb_cache_spinlock);
-	while (!list_is_last(l, &mb_cache_lru_list)) {
-		l = l->next;
-		ce = list_entry(l, struct mb_cache_entry, e_lru_list);
-		if (ce->e_bdev == bdev) {
-			list_del_init(&ce->e_lru_list);
-			if (ce->e_used || ce->e_queued ||
-				atomic_read(&ce->e_refcnt))
-				continue;
-			spin_unlock(&mb_cache_spinlock);
-			/*
-			 * Prevent any find or get operation on the entry.
-			 */
-			hlist_bl_lock(ce->e_block_hash_p);
-			hlist_bl_lock(ce->e_index_hash_p);
-			/* Ignore if it is touched by a find/get */
-			if (ce->e_used || ce->e_queued ||
-				atomic_read(&ce->e_refcnt) ||
-				!list_empty(&ce->e_lru_list)) {
-				hlist_bl_unlock(ce->e_index_hash_p);
-				hlist_bl_unlock(ce->e_block_hash_p);
-				l = &mb_cache_lru_list;
-				spin_lock(&mb_cache_spinlock);
-				continue;
+	struct hlist_bl_node *node;
+	struct hlist_bl_head *head;
+	struct mb_cache_entry *entry;
+
+	head = mb_cache_entry_head(cache, key);
+	hlist_bl_lock(head);
+	hlist_bl_for_each_entry(entry, node, head, e_hash_list) {
+		if (entry->e_key == key && entry->e_block == block) {
+			/* We keep hash list reference to keep entry alive */
+			hlist_bl_del_init(&entry->e_hash_list);
+			hlist_bl_unlock(head);
+			spin_lock(&cache->c_list_lock);
+			if (!list_empty(&entry->e_list)) {
+				list_del_init(&entry->e_list);
+				cache->c_entry_count--;
+				atomic_dec(&entry->e_refcnt);
 			}
-			__mb_cache_entry_unhash_unlock(ce);
-			mb_assert(!(ce->e_used || ce->e_queued ||
-				atomic_read(&ce->e_refcnt)));
-			list_add_tail(&ce->e_lru_list, &free_list);
-			l = &mb_cache_lru_list;
-			spin_lock(&mb_cache_spinlock);
+			spin_unlock(&cache->c_list_lock);
+			mb_cache_entry_put(cache, entry);
+			return;
 		}
 	}
-	spin_unlock(&mb_cache_spinlock);
-
-	list_for_each_entry_safe(ce, tmp, &free_list, e_lru_list) {
-		__mb_cache_entry_forget(ce, GFP_KERNEL);
-	}
+	hlist_bl_unlock(head);
 }
+EXPORT_SYMBOL(mb_cache_entry_delete_block);
 
-
-/*
- * mb_cache_destroy()
+/* mb_cache_entry_touch - cache entry got used
+ * @cache - cache the entry belongs to
+ * @entry - entry that got used
  *
- * Shrinks the cache to its minimum possible size (hopefully 0 entries),
- * and then destroys it. If this was the last mbcache, un-registers the
- * mbcache from kernel memory management.
+ * Marks entry as used to give hit higher chances of surviving in cache.
  */
-void
-mb_cache_destroy(struct mb_cache *cache)
+void mb_cache_entry_touch(struct mb_cache *cache,
+			  struct mb_cache_entry *entry)
 {
-	LIST_HEAD(free_list);
-	struct mb_cache_entry *ce, *tmp;
-
-	spin_lock(&mb_cache_spinlock);
-	list_for_each_entry_safe(ce, tmp, &mb_cache_lru_list, e_lru_list) {
-		if (ce->e_cache == cache)
-			list_move_tail(&ce->e_lru_list, &free_list);
-	}
-	list_del(&cache->c_cache_list);
-	spin_unlock(&mb_cache_spinlock);
-
-	list_for_each_entry_safe(ce, tmp, &free_list, e_lru_list) {
-		list_del_init(&ce->e_lru_list);
-		/*
-		 * Prevent any find or get operation on the entry.
-		 */
-		hlist_bl_lock(ce->e_block_hash_p);
-		hlist_bl_lock(ce->e_index_hash_p);
-		mb_assert(!(ce->e_used || ce->e_queued ||
-			atomic_read(&ce->e_refcnt)));
-		__mb_cache_entry_unhash_unlock(ce);
-		__mb_cache_entry_forget(ce, GFP_KERNEL);
-	}
-
-	if (atomic_read(&cache->c_entry_count) > 0) {
-		mb_error("cache %s: %d orphaned entries",
-			  cache->c_name,
-			  atomic_read(&cache->c_entry_count));
-	}
-
-	if (list_empty(&mb_cache_list)) {
-		kmem_cache_destroy(mb_cache_kmem_cache);
-		mb_cache_kmem_cache = NULL;
-	}
-	kfree(cache->c_index_hash);
-	kfree(cache->c_block_hash);
-	kfree(cache);
+	entry->e_referenced = 1;
 }
+EXPORT_SYMBOL(mb_cache_entry_touch);
 
-/*
- * mb_cache_entry_alloc()
- *
- * Allocates a new cache entry. The new entry will not be valid initially,
- * and thus cannot be looked up yet. It should be filled with data, and
- * then inserted into the cache using mb_cache_entry_insert(). Returns NULL
- * if no more memory was available.
- */
-struct mb_cache_entry *
-mb_cache_entry_alloc(struct mb_cache *cache, gfp_t gfp_flags)
+static unsigned long mb_cache_count(struct shrinker *shrink,
+				    struct shrink_control *sc)
 {
-	struct mb_cache_entry *ce;
-
-	if (atomic_read(&cache->c_entry_count) >= cache->c_max_entries) {
-		struct list_head *l;
-
-		l = &mb_cache_lru_list;
-		spin_lock(&mb_cache_spinlock);
-		while (!list_is_last(l, &mb_cache_lru_list)) {
-			l = l->next;
-			ce = list_entry(l, struct mb_cache_entry, e_lru_list);
-			if (ce->e_cache == cache) {
-				list_del_init(&ce->e_lru_list);
-				if (ce->e_used || ce->e_queued ||
-					atomic_read(&ce->e_refcnt))
-					continue;
-				spin_unlock(&mb_cache_spinlock);
-				/*
-				 * Prevent any find or get operation on the
-				 * entry.
-				 */
-				hlist_bl_lock(ce->e_block_hash_p);
-				hlist_bl_lock(ce->e_index_hash_p);
-				/* Ignore if it is touched by a find/get */
-				if (ce->e_used || ce->e_queued ||
-					atomic_read(&ce->e_refcnt) ||
-					!list_empty(&ce->e_lru_list)) {
-					hlist_bl_unlock(ce->e_index_hash_p);
-					hlist_bl_unlock(ce->e_block_hash_p);
-					l = &mb_cache_lru_list;
-					spin_lock(&mb_cache_spinlock);
-					continue;
-				}
-				mb_assert(list_empty(&ce->e_lru_list));
-				mb_assert(!(ce->e_used || ce->e_queued ||
-					atomic_read(&ce->e_refcnt)));
-				__mb_cache_entry_unhash_unlock(ce);
-				goto found;
-			}
-		}
-		spin_unlock(&mb_cache_spinlock);
-	}
+	struct mb_cache *cache = container_of(shrink, struct mb_cache,
+					      c_shrink);
 
-	ce = kmem_cache_alloc(cache->c_entry_cache, gfp_flags);
-	if (!ce)
-		return NULL;
-	atomic_inc(&cache->c_entry_count);
-	INIT_LIST_HEAD(&ce->e_lru_list);
-	INIT_HLIST_BL_NODE(&ce->e_block_list);
-	INIT_HLIST_BL_NODE(&ce->e_index.o_list);
-	ce->e_cache = cache;
-	ce->e_queued = 0;
-	atomic_set(&ce->e_refcnt, 0);
-found:
-	ce->e_block_hash_p = &cache->c_block_hash[0];
-	ce->e_index_hash_p = &cache->c_index_hash[0];
-	ce->e_used = 1 + MB_CACHE_WRITER;
-	return ce;
+	return cache->c_entry_count;
 }
 
-
-/*
- * mb_cache_entry_insert()
- *
- * Inserts an entry that was allocated using mb_cache_entry_alloc() into
- * the cache. After this, the cache entry can be looked up, but is not yet
- * in the lru list as the caller still holds a handle to it. Returns 0 on
- * success, or -EBUSY if a cache entry for that device + inode exists
- * already (this may happen after a failed lookup, but when another process
- * has inserted the same cache entry in the meantime).
- *
- * @bdev: device the cache entry belongs to
- * @block: block number
- * @key: lookup key
- */
-int
-mb_cache_entry_insert(struct mb_cache_entry *ce, struct block_device *bdev,
-		      sector_t block, unsigned int key)
+/* Shrink number of entries in cache */
+static unsigned long mb_cache_shrink(struct mb_cache *cache,
+				     unsigned int nr_to_scan)
 {
-	struct mb_cache *cache = ce->e_cache;
-	unsigned int bucket;
-	struct hlist_bl_node *l;
-	struct hlist_bl_head *block_hash_p;
-	struct hlist_bl_head *index_hash_p;
-	struct mb_cache_entry *lce;
-
-	mb_assert(ce);
-	bucket = hash_long((unsigned long)bdev + (block & 0xffffffff), 
-			   cache->c_bucket_bits);
-	block_hash_p = &cache->c_block_hash[bucket];
-	hlist_bl_lock(block_hash_p);
-	hlist_bl_for_each_entry(lce, l, block_hash_p, e_block_list) {
-		if (lce->e_bdev == bdev && lce->e_block == block) {
-			hlist_bl_unlock(block_hash_p);
-			return -EBUSY;
+	struct mb_cache_entry *entry;
+	struct hlist_bl_head *head;
+	unsigned int shrunk = 0;
+
+	spin_lock(&cache->c_list_lock);
+	while (nr_to_scan-- && !list_empty(&cache->c_list)) {
+		entry = list_first_entry(&cache->c_list,
+					 struct mb_cache_entry, e_list);
+		if (entry->e_referenced) {
+			entry->e_referenced = 0;
+			list_move_tail(&cache->c_list, &entry->e_list);
+			continue;
 		}
+		list_del_init(&entry->e_list);
+		cache->c_entry_count--;
+		/*
+		 * We keep LRU list reference so that entry doesn't go away
+		 * from under us.
+		 */
+		spin_unlock(&cache->c_list_lock);
+		head = mb_cache_entry_head(cache, entry->e_key);
+		hlist_bl_lock(head);
+		if (!hlist_bl_unhashed(&entry->e_hash_list)) {
+			hlist_bl_del_init(&entry->e_hash_list);
+			atomic_dec(&entry->e_refcnt);
+		}
+		hlist_bl_unlock(head);
+		if (mb_cache_entry_put(cache, entry))
+			shrunk++;
+		cond_resched();
+		spin_lock(&cache->c_list_lock);
 	}
-	mb_assert(!__mb_cache_entry_is_block_hashed(ce));
-	__mb_cache_entry_unhash_block(ce);
-	__mb_cache_entry_unhash_index(ce);
-	ce->e_bdev = bdev;
-	ce->e_block = block;
-	ce->e_block_hash_p = block_hash_p;
-	ce->e_index.o_key = key;
-	hlist_bl_add_head(&ce->e_block_list, block_hash_p);
-	hlist_bl_unlock(block_hash_p);
-	bucket = hash_long(key, cache->c_bucket_bits);
-	index_hash_p = &cache->c_index_hash[bucket];
-	hlist_bl_lock(index_hash_p);
-	ce->e_index_hash_p = index_hash_p;
-	hlist_bl_add_head(&ce->e_index.o_list, index_hash_p);
-	hlist_bl_unlock(index_hash_p);
-	return 0;
-}
+	spin_unlock(&cache->c_list_lock);
 
+	return shrunk;
+}
 
-/*
- * mb_cache_entry_release()
- *
- * Release a handle to a cache entry. When the last handle to a cache entry
- * is released it is either freed (if it is invalid) or otherwise inserted
- * in to the lru list.
- */
-void
-mb_cache_entry_release(struct mb_cache_entry *ce)
+static unsigned long mb_cache_scan(struct shrinker *shrink,
+				   struct shrink_control *sc)
 {
-	__mb_cache_entry_release(ce);
+	int nr_to_scan = sc->nr_to_scan;
+	struct mb_cache *cache = container_of(shrink, struct mb_cache,
+					      c_shrink);
+	return mb_cache_shrink(cache, nr_to_scan);
 }
 
+/* We shrink 1/X of the cache when we have too many entries in it */
+#define SHRINK_DIVISOR 16
 
-/*
- * mb_cache_entry_free()
- *
- */
-void
-mb_cache_entry_free(struct mb_cache_entry *ce)
+static void mb_cache_shrink_worker(struct work_struct *work)
 {
-	mb_assert(ce);
-	mb_assert(list_empty(&ce->e_lru_list));
-	hlist_bl_lock(ce->e_index_hash_p);
-	__mb_cache_entry_unhash_index(ce);
-	hlist_bl_unlock(ce->e_index_hash_p);
-	hlist_bl_lock(ce->e_block_hash_p);
-	__mb_cache_entry_unhash_block(ce);
-	hlist_bl_unlock(ce->e_block_hash_p);
-	__mb_cache_entry_release(ce);
+	struct mb_cache *cache = container_of(work, struct mb_cache,
+					      c_shrink_work);
+	mb_cache_shrink(cache, cache->c_max_entries / SHRINK_DIVISOR);
 }
 
-
 /*
- * mb_cache_entry_get()
+ * mb_cache_create - create cache
+ * @bucket_bits: log2 of the hash table size
  *
- * Get a cache entry  by device / block number. (There can only be one entry
- * in the cache per device and block.) Returns NULL if no such cache entry
- * exists. The returned cache entry is locked for exclusive access ("single
- * writer").
+ * Create cache for keys with 2^bucket_bits hash entries.
  */
-struct mb_cache_entry *
-mb_cache_entry_get(struct mb_cache *cache, struct block_device *bdev,
-		   sector_t block)
+struct mb_cache *mb_cache_create(int bucket_bits)
 {
-	unsigned int bucket;
-	struct hlist_bl_node *l;
-	struct mb_cache_entry *ce;
-	struct hlist_bl_head *block_hash_p;
-
-	bucket = hash_long((unsigned long)bdev + (block & 0xffffffff),
-			   cache->c_bucket_bits);
-	block_hash_p = &cache->c_block_hash[bucket];
-	/* First serialize access to the block corresponding hash chain. */
-	hlist_bl_lock(block_hash_p);
-	hlist_bl_for_each_entry(ce, l, block_hash_p, e_block_list) {
-		mb_assert(ce->e_block_hash_p == block_hash_p);
-		if (ce->e_bdev == bdev && ce->e_block == block) {
-			/*
-			 * Prevent a free from removing the entry.
-			 */
-			atomic_inc(&ce->e_refcnt);
-			hlist_bl_unlock(block_hash_p);
-			__spin_lock_mb_cache_entry(ce);
-			atomic_dec(&ce->e_refcnt);
-			if (ce->e_used > 0) {
-				DEFINE_WAIT(wait);
-				while (ce->e_used > 0) {
-					ce->e_queued++;
-					prepare_to_wait(&mb_cache_queue, &wait,
-							TASK_UNINTERRUPTIBLE);
-					__spin_unlock_mb_cache_entry(ce);
-					schedule();
-					__spin_lock_mb_cache_entry(ce);
-					ce->e_queued--;
-				}
-				finish_wait(&mb_cache_queue, &wait);
-			}
-			ce->e_used += 1 + MB_CACHE_WRITER;
-			__spin_unlock_mb_cache_entry(ce);
+	struct mb_cache *cache;
+	int bucket_count = 1 << bucket_bits;
+	int i;
 
-			if (!list_empty(&ce->e_lru_list)) {
-				spin_lock(&mb_cache_spinlock);
-				list_del_init(&ce->e_lru_list);
-				spin_unlock(&mb_cache_spinlock);
-			}
-			if (!__mb_cache_entry_is_block_hashed(ce)) {
-				__mb_cache_entry_release(ce);
-				return NULL;
-			}
-			return ce;
-		}
+	if (!try_module_get(THIS_MODULE))
+		return NULL;
+
+	cache = kzalloc(sizeof(struct mb_cache), GFP_KERNEL);
+	if (!cache)
+		goto err_out;
+	cache->c_bucket_bits = bucket_bits;
+	cache->c_max_entries = bucket_count << 4;
+	INIT_LIST_HEAD(&cache->c_list);
+	spin_lock_init(&cache->c_list_lock);
+	cache->c_hash = kmalloc(bucket_count * sizeof(struct hlist_bl_head),
+				GFP_KERNEL);
+	if (!cache->c_hash) {
+		kfree(cache);
+		goto err_out;
 	}
-	hlist_bl_unlock(block_hash_p);
-	return NULL;
-}
+	for (i = 0; i < bucket_count; i++)
+		INIT_HLIST_BL_HEAD(&cache->c_hash[i]);
 
-#if !defined(MB_CACHE_INDEXES_COUNT) || (MB_CACHE_INDEXES_COUNT > 0)
+	cache->c_shrink.count_objects = mb_cache_count;
+	cache->c_shrink.scan_objects = mb_cache_scan;
+	cache->c_shrink.seeks = DEFAULT_SEEKS;
+	register_shrinker(&cache->c_shrink);
 
-static struct mb_cache_entry *
-__mb_cache_entry_find(struct hlist_bl_node *l, struct hlist_bl_head *head,
-		      struct block_device *bdev, unsigned int key)
-{
+	INIT_WORK(&cache->c_shrink_work, mb_cache_shrink_worker);
 
-	/* The index hash chain is alredy acquire by caller. */
-	while (l != NULL) {
-		struct mb_cache_entry *ce =
-			hlist_bl_entry(l, struct mb_cache_entry,
-				e_index.o_list);
-		mb_assert(ce->e_index_hash_p == head);
-		if (ce->e_bdev == bdev && ce->e_index.o_key == key) {
-			/*
-			 * Prevent a free from removing the entry.
-			 */
-			atomic_inc(&ce->e_refcnt);
-			hlist_bl_unlock(head);
-			__spin_lock_mb_cache_entry(ce);
-			atomic_dec(&ce->e_refcnt);
-			ce->e_used++;
-			/* Incrementing before holding the lock gives readers
-			   priority over writers. */
-			if (ce->e_used >= MB_CACHE_WRITER) {
-				DEFINE_WAIT(wait);
-
-				while (ce->e_used >= MB_CACHE_WRITER) {
-					ce->e_queued++;
-					prepare_to_wait(&mb_cache_queue, &wait,
-							TASK_UNINTERRUPTIBLE);
-					__spin_unlock_mb_cache_entry(ce);
-					schedule();
-					__spin_lock_mb_cache_entry(ce);
-					ce->e_queued--;
-				}
-				finish_wait(&mb_cache_queue, &wait);
-			}
-			__spin_unlock_mb_cache_entry(ce);
-			if (!list_empty(&ce->e_lru_list)) {
-				spin_lock(&mb_cache_spinlock);
-				list_del_init(&ce->e_lru_list);
-				spin_unlock(&mb_cache_spinlock);
-			}
-			if (!__mb_cache_entry_is_block_hashed(ce)) {
-				__mb_cache_entry_release(ce);
-				return ERR_PTR(-EAGAIN);
-			}
-			return ce;
-		}
-		l = l->next;
-	}
-	hlist_bl_unlock(head);
+	return cache;
+
+err_out:
+	module_put(THIS_MODULE);
 	return NULL;
 }
-
+EXPORT_SYMBOL(mb_cache_create);
 
 /*
- * mb_cache_entry_find_first()
- *
- * Find the first cache entry on a given device with a certain key in
- * an additional index. Additional matches can be found with
- * mb_cache_entry_find_next(). Returns NULL if no match was found. The
- * returned cache entry is locked for shared access ("multiple readers").
+ * mb_cache_destroy - destroy cache
+ * @cache: the cache to destroy
  *
- * @cache: the cache to search
- * @bdev: the device the cache entry should belong to
- * @key: the key in the index
+ * Free all entries in cache and cache itself. Caller must make sure nobody
+ * (except shrinker) can reach @cache when calling this.
  */
-struct mb_cache_entry *
-mb_cache_entry_find_first(struct mb_cache *cache, struct block_device *bdev,
-			  unsigned int key)
+void mb_cache_destroy(struct mb_cache *cache)
 {
-	unsigned int bucket = hash_long(key, cache->c_bucket_bits);
-	struct hlist_bl_node *l;
-	struct mb_cache_entry *ce = NULL;
-	struct hlist_bl_head *index_hash_p;
-
-	index_hash_p = &cache->c_index_hash[bucket];
-	hlist_bl_lock(index_hash_p);
-	if (!hlist_bl_empty(index_hash_p)) {
-		l = hlist_bl_first(index_hash_p);
-		ce = __mb_cache_entry_find(l, index_hash_p, bdev, key);
-	} else
-		hlist_bl_unlock(index_hash_p);
-	return ce;
-}
+	struct mb_cache_entry *entry, *next;
 
+	unregister_shrinker(&cache->c_shrink);
 
-/*
- * mb_cache_entry_find_next()
- *
- * Find the next cache entry on a given device with a certain key in an
- * additional index. Returns NULL if no match could be found. The previous
- * entry is atomatically released, so that mb_cache_entry_find_next() can
- * be called like this:
- *
- * entry = mb_cache_entry_find_first();
- * while (entry) {
- * 	...
- *	entry = mb_cache_entry_find_next(entry, ...);
- * }
- *
- * @prev: The previous match
- * @bdev: the device the cache entry should belong to
- * @key: the key in the index
- */
-struct mb_cache_entry *
-mb_cache_entry_find_next(struct mb_cache_entry *prev,
-			 struct block_device *bdev, unsigned int key)
-{
-	struct mb_cache *cache = prev->e_cache;
-	unsigned int bucket = hash_long(key, cache->c_bucket_bits);
-	struct hlist_bl_node *l;
-	struct mb_cache_entry *ce;
-	struct hlist_bl_head *index_hash_p;
-
-	index_hash_p = &cache->c_index_hash[bucket];
-	mb_assert(prev->e_index_hash_p == index_hash_p);
-	hlist_bl_lock(index_hash_p);
-	mb_assert(!hlist_bl_empty(index_hash_p));
-	l = prev->e_index.o_list.next;
-	ce = __mb_cache_entry_find(l, index_hash_p, bdev, key);
-	__mb_cache_entry_release(prev);
-	return ce;
+	/*
+	 * We don't bother with any locking. Cache must not be used at this
+	 * point.
+	 */
+	list_for_each_entry_safe(entry, next, &cache->c_list, e_list) {
+		if (!hlist_bl_unhashed(&entry->e_hash_list)) {
+			hlist_bl_del_init(&entry->e_hash_list);
+			atomic_dec(&entry->e_refcnt);
+		} else
+			WARN_ON(1);
+		list_del(&entry->e_list);
+		WARN_ON(atomic_read(&entry->e_refcnt) != 1);
+		mb_cache_entry_put(cache, entry);
+	}
+	kfree(cache->c_hash);
+	kfree(cache);
+	module_put(THIS_MODULE);
 }
+EXPORT_SYMBOL(mb_cache_destroy);
 
-#endif  /* !defined(MB_CACHE_INDEXES_COUNT) || (MB_CACHE_INDEXES_COUNT > 0) */
-
-static int __init init_mbcache(void)
+static int __init mbcache_init(void)
 {
-	register_shrinker(&mb_cache_shrinker);
+	mb_entry_cache = kmem_cache_create("mbcache",
+				sizeof(struct mb_cache_entry), 0,
+				SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL);
+	BUG_ON(!mb_entry_cache);
 	return 0;
 }
 
-static void __exit exit_mbcache(void)
+static void __exit mbcache_exit(void)
 {
-	unregister_shrinker(&mb_cache_shrinker);
+	kmem_cache_destroy(mb_entry_cache);
 }
 
-module_init(init_mbcache)
-module_exit(exit_mbcache)
+module_init(mbcache_init)
+module_exit(mbcache_exit)
 
+MODULE_AUTHOR("Jan Kara <jack@suse.cz>");
+MODULE_DESCRIPTION("Meta block cache (for extended attributes)");
+MODULE_LICENSE("GPL");
diff --git a/fs/minix/dir.c b/fs/minix/dir.c
index d19ac258105a..33957c07cd11 100644
--- a/fs/minix/dir.c
+++ b/fs/minix/dir.c
@@ -28,7 +28,7 @@ const struct file_operations minix_dir_operations = {
 static inline void dir_put_page(struct page *page)
 {
 	kunmap(page);
-	page_cache_release(page);
+	put_page(page);
 }
 
 /*
@@ -38,10 +38,10 @@ static inline void dir_put_page(struct page *page)
 static unsigned
 minix_last_byte(struct inode *inode, unsigned long page_nr)
 {
-	unsigned last_byte = PAGE_CACHE_SIZE;
+	unsigned last_byte = PAGE_SIZE;
 
-	if (page_nr == (inode->i_size >> PAGE_CACHE_SHIFT))
-		last_byte = inode->i_size & (PAGE_CACHE_SIZE - 1);
+	if (page_nr == (inode->i_size >> PAGE_SHIFT))
+		last_byte = inode->i_size & (PAGE_SIZE - 1);
 	return last_byte;
 }
 
@@ -92,8 +92,8 @@ static int minix_readdir(struct file *file, struct dir_context *ctx)
 	if (pos >= inode->i_size)
 		return 0;
 
-	offset = pos & ~PAGE_CACHE_MASK;
-	n = pos >> PAGE_CACHE_SHIFT;
+	offset = pos & ~PAGE_MASK;
+	n = pos >> PAGE_SHIFT;
 
 	for ( ; n < npages; n++, offset = 0) {
 		char *p, *kaddr, *limit;
@@ -229,7 +229,7 @@ int minix_add_link(struct dentry *dentry, struct inode *inode)
 		lock_page(page);
 		kaddr = (char*)page_address(page);
 		dir_end = kaddr + minix_last_byte(dir, n);
-		limit = kaddr + PAGE_CACHE_SIZE - sbi->s_dirsize;
+		limit = kaddr + PAGE_SIZE - sbi->s_dirsize;
 		for (p = kaddr; p <= limit; p = minix_next_entry(p, sbi)) {
 			de = (minix_dirent *)p;
 			de3 = (minix3_dirent *)p;
@@ -327,7 +327,7 @@ int minix_make_empty(struct inode *inode, struct inode *dir)
 	}
 
 	kaddr = kmap_atomic(page);
-	memset(kaddr, 0, PAGE_CACHE_SIZE);
+	memset(kaddr, 0, PAGE_SIZE);
 
 	if (sbi->s_version == MINIX_V3) {
 		minix3_dirent *de3 = (minix3_dirent *)kaddr;
@@ -350,7 +350,7 @@ int minix_make_empty(struct inode *inode, struct inode *dir)
 
 	err = dir_commit_chunk(page, 0, 2 * sbi->s_dirsize);
 fail:
-	page_cache_release(page);
+	put_page(page);
 	return err;
 }
 
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index 086cd0a61e80..f975d667c539 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -91,7 +91,7 @@ static int __init init_inodecache(void)
 	minix_inode_cachep = kmem_cache_create("minix_inode_cache",
 					     sizeof(struct minix_inode_info),
 					     0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD),
+						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
 					     init_once);
 	if (minix_inode_cachep == NULL)
 		return -ENOMEM;
@@ -435,8 +435,7 @@ static const struct address_space_operations minix_aops = {
 
 static const struct inode_operations minix_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 	.getattr	= minix_getattr,
 };
 
@@ -452,6 +451,7 @@ void minix_set_inode(struct inode *inode, dev_t rdev)
 		inode->i_mapping->a_ops = &minix_aops;
 	} else if (S_ISLNK(inode->i_mode)) {
 		inode->i_op = &minix_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &minix_aops;
 	} else
 		init_special_inode(inode, inode->i_mode, rdev);
diff --git a/fs/minix/itree_v1.c b/fs/minix/itree_v1.c
index 282e15ad8cd8..46ca39d6c735 100644
--- a/fs/minix/itree_v1.c
+++ b/fs/minix/itree_v1.c
@@ -24,16 +24,15 @@ static inline block_t *i_data(struct inode *inode)
 static int block_to_path(struct inode * inode, long block, int offsets[DEPTH])
 {
 	int n = 0;
-	char b[BDEVNAME_SIZE];
 
 	if (block < 0) {
-		printk("MINIX-fs: block_to_path: block %ld < 0 on dev %s\n",
-			block, bdevname(inode->i_sb->s_bdev, b));
+		printk("MINIX-fs: block_to_path: block %ld < 0 on dev %pg\n",
+			block, inode->i_sb->s_bdev);
 	} else if (block >= (minix_sb(inode->i_sb)->s_max_size/BLOCK_SIZE)) {
 		if (printk_ratelimit())
 			printk("MINIX-fs: block_to_path: "
-			       "block %ld too big on dev %s\n",
-				block, bdevname(inode->i_sb->s_bdev, b));
+			       "block %ld too big on dev %pg\n",
+				block, inode->i_sb->s_bdev);
 	} else if (block < 7) {
 		offsets[n++] = block;
 	} else if ((block -= 7) < 512) {
diff --git a/fs/minix/itree_v2.c b/fs/minix/itree_v2.c
index 78e2d93e5c83..1ee101352586 100644
--- a/fs/minix/itree_v2.c
+++ b/fs/minix/itree_v2.c
@@ -26,18 +26,17 @@ static inline block_t *i_data(struct inode *inode)
 static int block_to_path(struct inode * inode, long block, int offsets[DEPTH])
 {
 	int n = 0;
-	char b[BDEVNAME_SIZE];
 	struct super_block *sb = inode->i_sb;
 
 	if (block < 0) {
-		printk("MINIX-fs: block_to_path: block %ld < 0 on dev %s\n",
-			block, bdevname(sb->s_bdev, b));
+		printk("MINIX-fs: block_to_path: block %ld < 0 on dev %pg\n",
+			block, sb->s_bdev);
 	} else if ((u64)block * (u64)sb->s_blocksize >=
 			minix_sb(sb)->s_max_size) {
 		if (printk_ratelimit())
 			printk("MINIX-fs: block_to_path: "
-			       "block %ld too big on dev %s\n",
-				block, bdevname(sb->s_bdev, b));
+			       "block %ld too big on dev %pg\n",
+				block, sb->s_bdev);
 	} else if (block < DIRCOUNT) {
 		offsets[n++] = block;
 	} else if ((block -= DIRCOUNT) < INDIRCOUNT(sb)) {
diff --git a/fs/minix/namei.c b/fs/minix/namei.c
index a795a11e50c7..2887d1d95ce2 100644
--- a/fs/minix/namei.c
+++ b/fs/minix/namei.c
@@ -243,11 +243,11 @@ static int minix_rename(struct inode * old_dir, struct dentry *old_dentry,
 out_dir:
 	if (dir_de) {
 		kunmap(dir_page);
-		page_cache_release(dir_page);
+		put_page(dir_page);
 	}
 out_old:
 	kunmap(old_page);
-	page_cache_release(old_page);
+	put_page(old_page);
 out:
 	return err;
 }
diff --git a/fs/mpage.c b/fs/mpage.c
index 09abba7653aa..eedc644b78d7 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -24,6 +24,7 @@
 #include <linux/highmem.h>
 #include <linux/prefetch.h>
 #include <linux/mpage.h>
+#include <linux/mm_inline.h>
 #include <linux/writeback.h>
 #include <linux/backing-dev.h>
 #include <linux/pagevec.h>
@@ -106,7 +107,7 @@ map_buffer_to_page(struct page *page, struct buffer_head *bh, int page_block)
 		 * don't make any buffers if there is only one buffer on
 		 * the page and the page just needs to be set up to date
 		 */
-		if (inode->i_blkbits == PAGE_CACHE_SHIFT && 
+		if (inode->i_blkbits == PAGE_SHIFT &&
 		    buffer_uptodate(bh)) {
 			SetPageUptodate(page);    
 			return;
@@ -144,7 +145,7 @@ do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages,
 {
 	struct inode *inode = page->mapping->host;
 	const unsigned blkbits = inode->i_blkbits;
-	const unsigned blocks_per_page = PAGE_CACHE_SIZE >> blkbits;
+	const unsigned blocks_per_page = PAGE_SIZE >> blkbits;
 	const unsigned blocksize = 1 << blkbits;
 	sector_t block_in_file;
 	sector_t last_block;
@@ -161,7 +162,7 @@ do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages,
 	if (page_has_buffers(page))
 		goto confused;
 
-	block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits);
+	block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits);
 	last_block = block_in_file + nr_pages * blocks_per_page;
 	last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits;
 	if (last_block > last_block_in_file)
@@ -248,7 +249,7 @@ do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages,
 	}
 
 	if (first_hole != blocks_per_page) {
-		zero_user_segment(page, first_hole << blkbits, PAGE_CACHE_SIZE);
+		zero_user_segment(page, first_hole << blkbits, PAGE_SIZE);
 		if (first_hole == 0) {
 			SetPageUptodate(page);
 			unlock_page(page);
@@ -330,7 +331,7 @@ confused:
  *
  * then this code just gives up and calls the buffer_head-based read function.
  * It does handle a page which has holes at the end - that is a common case:
- * the end-of-file on blocksize < PAGE_CACHE_SIZE setups.
+ * the end-of-file on blocksize < PAGE_SIZE setups.
  *
  * BH_Boundary explanation:
  *
@@ -361,12 +362,12 @@ 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 = GFP_KERNEL & mapping_gfp_mask(mapping);
+	gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL);
 
 	map_bh.b_state = 0;
 	map_bh.b_size = 0;
 	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
-		struct page *page = list_entry(pages->prev, struct page, lru);
+		struct page *page = lru_to_page(pages);
 
 		prefetchw(&page->flags);
 		list_del(&page->lru);
@@ -379,7 +380,7 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages,
 					&first_logical_block,
 					get_block, gfp);
 		}
-		page_cache_release(page);
+		put_page(page);
 	}
 	BUG_ON(!list_empty(pages));
 	if (bio)
@@ -397,7 +398,7 @@ int mpage_readpage(struct page *page, get_block_t get_block)
 	sector_t last_block_in_bio = 0;
 	struct buffer_head map_bh;
 	unsigned long first_logical_block = 0;
-	gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(page->mapping);
+	gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL);
 
 	map_bh.b_state = 0;
 	map_bh.b_size = 0;
@@ -471,7 +472,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
 	struct inode *inode = page->mapping->host;
 	const unsigned blkbits = inode->i_blkbits;
 	unsigned long end_index;
-	const unsigned blocks_per_page = PAGE_CACHE_SIZE >> blkbits;
+	const unsigned blocks_per_page = PAGE_SIZE >> blkbits;
 	sector_t last_block;
 	sector_t block_in_file;
 	sector_t blocks[MAX_BUF_PER_PAGE];
@@ -541,7 +542,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
 	 * The page has no buffers: map it to disk
 	 */
 	BUG_ON(!PageUptodate(page));
-	block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits);
+	block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits);
 	last_block = (i_size - 1) >> blkbits;
 	map_bh.b_page = page;
 	for (page_block = 0; page_block < blocks_per_page; ) {
@@ -573,7 +574,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
 	first_unmapped = page_block;
 
 page_is_mapped:
-	end_index = i_size >> PAGE_CACHE_SHIFT;
+	end_index = i_size >> PAGE_SHIFT;
 	if (page->index >= end_index) {
 		/*
 		 * The page straddles i_size.  It must be zeroed out on each
@@ -583,11 +584,11 @@ page_is_mapped:
 		 * is zeroed when mapped, and writes to that region are not
 		 * written out to the file."
 		 */
-		unsigned offset = i_size & (PAGE_CACHE_SIZE - 1);
+		unsigned offset = i_size & (PAGE_SIZE - 1);
 
 		if (page->index > end_index || !offset)
 			goto confused;
-		zero_user_segment(page, offset, PAGE_CACHE_SIZE);
+		zero_user_segment(page, offset, PAGE_SIZE);
 	}
 
 	/*
diff --git a/fs/namei.c b/fs/namei.c
index 6f567347f14f..1d9ca2d5dff6 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -505,13 +505,13 @@ struct nameidata {
 	int		total_link_count;
 	struct saved {
 		struct path link;
-		void *cookie;
+		struct delayed_call done;
 		const char *name;
-		struct inode *inode;
 		unsigned seq;
 	} *stack, internal[EMBEDDED_LEVELS];
 	struct filename	*name;
 	struct nameidata *saved;
+	struct inode	*link_inode;
 	unsigned	root_seq;
 	int		dfd;
 };
@@ -534,10 +534,8 @@ static void restore_nameidata(void)
 	current->nameidata = old;
 	if (old)
 		old->total_link_count = now->total_link_count;
-	if (now->stack != now->internal) {
+	if (now->stack != now->internal)
 		kfree(now->stack);
-		now->stack = now->internal;
-	}
 }
 
 static int __nd_alloc_stack(struct nameidata *nd)
@@ -592,11 +590,8 @@ static void drop_links(struct nameidata *nd)
 	int i = nd->depth;
 	while (i--) {
 		struct saved *last = nd->stack + i;
-		struct inode *inode = last->inode;
-		if (last->cookie && inode->i_op->put_link) {
-			inode->i_op->put_link(inode, last->cookie);
-			last->cookie = NULL;
-		}
+		do_delayed_call(&last->done);
+		clear_delayed_call(&last->done);
 	}
 }
 
@@ -657,7 +652,7 @@ static bool legitimize_links(struct nameidata *nd)
  * Path walking has 2 modes, rcu-walk and ref-walk (see
  * Documentation/filesystems/path-lookup.txt).  In situations when we can't
  * continue in RCU mode, we attempt to drop out of rcu-walk mode and grab
- * normal reference counts on dentries and vfsmounts to transition to rcu-walk
+ * normal reference counts on dentries and vfsmounts to transition to ref-walk
  * mode.  Refcounts are grabbed at the last known good point before rcu-walk
  * got stuck, so ref-walk may continue from there. If this is not successful
  * (eg. a seqcount has changed), then failure is returned and it's up to caller
@@ -807,19 +802,19 @@ static int complete_walk(struct nameidata *nd)
 
 static void set_root(struct nameidata *nd)
 {
-	get_fs_root(current->fs, &nd->root);
-}
-
-static void set_root_rcu(struct nameidata *nd)
-{
 	struct fs_struct *fs = current->fs;
-	unsigned seq;
 
-	do {
-		seq = read_seqcount_begin(&fs->seq);
-		nd->root = fs->root;
-		nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq);
-	} while (read_seqcount_retry(&fs->seq, seq));
+	if (nd->flags & LOOKUP_RCU) {
+		unsigned seq;
+
+		do {
+			seq = read_seqcount_begin(&fs->seq);
+			nd->root = fs->root;
+			nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq);
+		} while (read_seqcount_retry(&fs->seq, seq));
+	} else {
+		get_fs_root(fs, &nd->root);
+	}
 }
 
 static void path_put_conditional(struct path *path, struct nameidata *nd)
@@ -841,8 +836,28 @@ static inline void path_to_nameidata(const struct path *path,
 	nd->path.dentry = path->dentry;
 }
 
+static int nd_jump_root(struct nameidata *nd)
+{
+	if (nd->flags & LOOKUP_RCU) {
+		struct dentry *d;
+		nd->path = nd->root;
+		d = nd->path.dentry;
+		nd->inode = d->d_inode;
+		nd->seq = nd->root_seq;
+		if (unlikely(read_seqcount_retry(&d->d_seq, nd->seq)))
+			return -ECHILD;
+	} else {
+		path_put(&nd->path);
+		nd->path = nd->root;
+		path_get(&nd->path);
+		nd->inode = nd->path.dentry->d_inode;
+	}
+	nd->flags |= LOOKUP_JUMPED;
+	return 0;
+}
+
 /*
- * Helper to directly jump to a known parsed path from ->follow_link,
+ * Helper to directly jump to a known parsed path from ->get_link,
  * caller must have taken a reference to path beforehand.
  */
 void nd_jump_link(struct path *path)
@@ -858,9 +873,7 @@ void nd_jump_link(struct path *path)
 static inline void put_link(struct nameidata *nd)
 {
 	struct saved *last = nd->stack + --nd->depth;
-	struct inode *inode = last->inode;
-	if (last->cookie && inode->i_op->put_link)
-		inode->i_op->put_link(inode, last->cookie);
+	do_delayed_call(&last->done);
 	if (!(nd->flags & LOOKUP_RCU))
 		path_put(&last->link);
 }
@@ -892,7 +905,7 @@ static inline int may_follow_link(struct nameidata *nd)
 		return 0;
 
 	/* Allowed if owner and follower match. */
-	inode = nd->stack[0].inode;
+	inode = nd->link_inode;
 	if (uid_eq(current_cred()->fsuid, inode->i_uid))
 		return 0;
 
@@ -983,7 +996,7 @@ const char *get_link(struct nameidata *nd)
 {
 	struct saved *last = nd->stack + nd->depth - 1;
 	struct dentry *dentry = last->link.dentry;
-	struct inode *inode = last->inode;
+	struct inode *inode = nd->link_inode;
 	int error;
 	const char *res;
 
@@ -1004,36 +1017,27 @@ const char *get_link(struct nameidata *nd)
 	nd->last_type = LAST_BIND;
 	res = inode->i_link;
 	if (!res) {
+		const char * (*get)(struct dentry *, struct inode *,
+				struct delayed_call *);
+		get = inode->i_op->get_link;
 		if (nd->flags & LOOKUP_RCU) {
-			if (unlikely(unlazy_walk(nd, NULL, 0)))
-				return ERR_PTR(-ECHILD);
+			res = get(NULL, inode, &last->done);
+			if (res == ERR_PTR(-ECHILD)) {
+				if (unlikely(unlazy_walk(nd, NULL, 0)))
+					return ERR_PTR(-ECHILD);
+				res = get(dentry, inode, &last->done);
+			}
+		} else {
+			res = get(dentry, inode, &last->done);
 		}
-		res = inode->i_op->follow_link(dentry, &last->cookie);
-		if (IS_ERR_OR_NULL(res)) {
-			last->cookie = NULL;
+		if (IS_ERR_OR_NULL(res))
 			return res;
-		}
 	}
 	if (*res == '/') {
-		if (nd->flags & LOOKUP_RCU) {
-			struct dentry *d;
-			if (!nd->root.mnt)
-				set_root_rcu(nd);
-			nd->path = nd->root;
-			d = nd->path.dentry;
-			nd->inode = d->d_inode;
-			nd->seq = nd->root_seq;
-			if (unlikely(read_seqcount_retry(&d->d_seq, nd->seq)))
-				return ERR_PTR(-ECHILD);
-		} else {
-			if (!nd->root.mnt)
-				set_root(nd);
-			path_put(&nd->path);
-			nd->path = nd->root;
-			path_get(&nd->root);
-			nd->inode = nd->path.dentry->d_inode;
-		}
-		nd->flags |= LOOKUP_JUMPED;
+		if (!nd->root.mnt)
+			set_root(nd);
+		if (unlikely(nd_jump_root(nd)))
+			return ERR_PTR(-ECHILD);
 		while (unlikely(*++res == '/'))
 			;
 	}
@@ -1216,8 +1220,8 @@ static int follow_managed(struct path *path, struct nameidata *nd)
 
 	if (need_mntput && path->mnt == mnt)
 		mntput(path->mnt);
-	if (ret == -EISDIR)
-		ret = 0;
+	if (ret == -EISDIR || !ret)
+		ret = 1;
 	if (need_mntput)
 		nd->flags |= LOOKUP_JUMPED;
 	if (unlikely(ret < 0))
@@ -1294,8 +1298,6 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
 static int follow_dotdot_rcu(struct nameidata *nd)
 {
 	struct inode *inode = nd->inode;
-	if (!nd->root.mnt)
-		set_root_rcu(nd);
 
 	while (1) {
 		if (path_equal(&nd->path, &nd->root))
@@ -1415,9 +1417,6 @@ static void follow_mount(struct path *path)
 
 static int follow_dotdot(struct nameidata *nd)
 {
-	if (!nd->root.mnt)
-		set_root(nd);
-
 	while(1) {
 		struct dentry *old = nd->path.dentry;
 
@@ -1445,40 +1444,26 @@ static int follow_dotdot(struct nameidata *nd)
  * This looks up the name in dcache, possibly revalidates the old dentry and
  * allocates a new one if not found or not valid.  In the need_lookup argument
  * returns whether i_op->lookup is necessary.
- *
- * dir->d_inode->i_mutex must be held
  */
-static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir,
-				    unsigned int flags, bool *need_lookup)
+static struct dentry *lookup_dcache(const struct qstr *name,
+				    struct dentry *dir,
+				    unsigned int flags)
 {
 	struct dentry *dentry;
 	int error;
 
-	*need_lookup = false;
 	dentry = d_lookup(dir, name);
 	if (dentry) {
 		if (dentry->d_flags & DCACHE_OP_REVALIDATE) {
 			error = d_revalidate(dentry, flags);
 			if (unlikely(error <= 0)) {
-				if (error < 0) {
-					dput(dentry);
-					return ERR_PTR(error);
-				} else {
+				if (!error)
 					d_invalidate(dentry);
-					dput(dentry);
-					dentry = NULL;
-				}
+				dput(dentry);
+				return ERR_PTR(error);
 			}
 		}
 	}
-
-	if (!dentry) {
-		dentry = d_alloc(dir, name);
-		if (unlikely(!dentry))
-			return ERR_PTR(-ENOMEM);
-
-		*need_lookup = true;
-	}
 	return dentry;
 }
 
@@ -1507,45 +1492,44 @@ static struct dentry *lookup_real(struct inode *dir, struct dentry *dentry,
 	return dentry;
 }
 
-static struct dentry *__lookup_hash(struct qstr *name,
+static struct dentry *__lookup_hash(const struct qstr *name,
 		struct dentry *base, unsigned int flags)
 {
-	bool need_lookup;
-	struct dentry *dentry;
+	struct dentry *dentry = lookup_dcache(name, base, flags);
 
-	dentry = lookup_dcache(name, base, flags, &need_lookup);
-	if (!need_lookup)
+	if (dentry)
 		return dentry;
 
+	dentry = d_alloc(base, name);
+	if (unlikely(!dentry))
+		return ERR_PTR(-ENOMEM);
+
 	return lookup_real(base->d_inode, dentry, flags);
 }
 
-/*
- *  It's more convoluted than I'd like it to be, but... it's still fairly
- *  small and for now I'd prefer to have fast path as straight as possible.
- *  It _is_ time-critical.
- */
 static int lookup_fast(struct nameidata *nd,
 		       struct path *path, struct inode **inode,
 		       unsigned *seqp)
 {
 	struct vfsmount *mnt = nd->path.mnt;
 	struct dentry *dentry, *parent = nd->path.dentry;
-	int need_reval = 1;
 	int status = 1;
 	int err;
 
 	/*
 	 * Rename seqlock is not required here because in the off chance
-	 * of a false negative due to a concurrent rename, we're going to
-	 * do the non-racy lookup, below.
+	 * of a false negative due to a concurrent rename, the caller is
+	 * going to fall back to non-racy lookup.
 	 */
 	if (nd->flags & LOOKUP_RCU) {
 		unsigned seq;
 		bool negative;
 		dentry = __d_lookup_rcu(parent, &nd->last, &seq);
-		if (!dentry)
-			goto unlazy;
+		if (unlikely(!dentry)) {
+			if (unlazy_walk(nd, NULL, 0))
+				return -ECHILD;
+			return 0;
+		}
 
 		/*
 		 * This sequence count validates that the inode matches
@@ -1553,7 +1537,7 @@ static int lookup_fast(struct nameidata *nd,
 		 */
 		*inode = d_backing_inode(dentry);
 		negative = d_is_negative(dentry);
-		if (read_seqcount_retry(&dentry->d_seq, seq))
+		if (unlikely(read_seqcount_retry(&dentry->d_seq, seq)))
 			return -ECHILD;
 
 		/*
@@ -1563,81 +1547,89 @@ static int lookup_fast(struct nameidata *nd,
 		 * The memory barrier in read_seqcount_begin of child is
 		 *  enough, we can use __read_seqcount_retry here.
 		 */
-		if (__read_seqcount_retry(&parent->d_seq, nd->seq))
+		if (unlikely(__read_seqcount_retry(&parent->d_seq, nd->seq)))
 			return -ECHILD;
 
 		*seqp = seq;
-		if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) {
+		if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE))
 			status = d_revalidate(dentry, nd->flags);
-			if (unlikely(status <= 0)) {
-				if (status != -ECHILD)
-					need_reval = 0;
-				goto unlazy;
-			}
+		if (unlikely(status <= 0)) {
+			if (unlazy_walk(nd, dentry, seq))
+				return -ECHILD;
+			if (status == -ECHILD)
+				status = d_revalidate(dentry, nd->flags);
+		} else {
+			/*
+			 * Note: do negative dentry check after revalidation in
+			 * case that drops it.
+			 */
+			if (unlikely(negative))
+				return -ENOENT;
+			path->mnt = mnt;
+			path->dentry = dentry;
+			if (likely(__follow_mount_rcu(nd, path, inode, seqp)))
+				return 1;
+			if (unlazy_walk(nd, dentry, seq))
+				return -ECHILD;
 		}
-		/*
-		 * Note: do negative dentry check after revalidation in
-		 * case that drops it.
-		 */
-		if (negative)
-			return -ENOENT;
-		path->mnt = mnt;
-		path->dentry = dentry;
-		if (likely(__follow_mount_rcu(nd, path, inode, seqp)))
-			return 0;
-unlazy:
-		if (unlazy_walk(nd, dentry, seq))
-			return -ECHILD;
 	} else {
 		dentry = __d_lookup(parent, &nd->last);
+		if (unlikely(!dentry))
+			return 0;
+		if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE))
+			status = d_revalidate(dentry, nd->flags);
 	}
-
-	if (unlikely(!dentry))
-		goto need_lookup;
-
-	if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE) && need_reval)
-		status = d_revalidate(dentry, nd->flags);
 	if (unlikely(status <= 0)) {
-		if (status < 0) {
-			dput(dentry);
-			return status;
-		}
-		d_invalidate(dentry);
+		if (!status)
+			d_invalidate(dentry);
 		dput(dentry);
-		goto need_lookup;
+		return status;
 	}
-
 	if (unlikely(d_is_negative(dentry))) {
 		dput(dentry);
 		return -ENOENT;
 	}
+
 	path->mnt = mnt;
 	path->dentry = dentry;
 	err = follow_managed(path, nd);
-	if (likely(!err))
+	if (likely(err > 0))
 		*inode = d_backing_inode(path->dentry);
 	return err;
-
-need_lookup:
-	return 1;
 }
 
 /* Fast lookup failed, do it the slow way */
-static int lookup_slow(struct nameidata *nd, struct path *path)
+static struct dentry *lookup_slow(const struct qstr *name,
+				  struct dentry *dir,
+				  unsigned int flags)
 {
-	struct dentry *dentry, *parent;
-
-	parent = nd->path.dentry;
-	BUG_ON(nd->inode != parent->d_inode);
-
-	mutex_lock(&parent->d_inode->i_mutex);
-	dentry = __lookup_hash(&nd->last, parent, nd->flags);
-	mutex_unlock(&parent->d_inode->i_mutex);
-	if (IS_ERR(dentry))
-		return PTR_ERR(dentry);
-	path->mnt = nd->path.mnt;
-	path->dentry = dentry;
-	return follow_managed(path, nd);
+	struct dentry *dentry;
+	inode_lock(dir->d_inode);
+	dentry = d_lookup(dir, name);
+	if (unlikely(dentry)) {
+		if ((dentry->d_flags & DCACHE_OP_REVALIDATE) &&
+		    !(flags & LOOKUP_NO_REVAL)) {
+			int error = d_revalidate(dentry, flags);
+			if (unlikely(error <= 0)) {
+				if (!error)
+					d_invalidate(dentry);
+				dput(dentry);
+				dentry = ERR_PTR(error);
+			}
+		}
+		if (dentry) {
+			inode_unlock(dir->d_inode);
+			return dentry;
+		}
+	}
+	dentry = d_alloc(dir, name);
+	if (unlikely(!dentry)) {
+		inode_unlock(dir->d_inode);
+		return ERR_PTR(-ENOMEM);
+	}
+	dentry = lookup_real(dir->d_inode, dentry, flags);
+	inode_unlock(dir->d_inode);
+	return dentry;
 }
 
 static inline int may_lookup(struct nameidata *nd)
@@ -1655,6 +1647,8 @@ static inline int may_lookup(struct nameidata *nd)
 static inline int handle_dots(struct nameidata *nd, int type)
 {
 	if (type == LAST_DOTDOT) {
+		if (!nd->root.mnt)
+			set_root(nd);
 		if (nd->flags & LOOKUP_RCU) {
 			return follow_dotdot_rcu(nd);
 		} else
@@ -1691,8 +1685,8 @@ static int pick_link(struct nameidata *nd, struct path *link,
 
 	last = nd->stack + nd->depth++;
 	last->link = *link;
-	last->cookie = NULL;
-	last->inode = inode;
+	clear_delayed_call(&last->done);
+	nd->link_inode = inode;
 	last->seq = seq;
 	return 1;
 }
@@ -1711,6 +1705,11 @@ static inline int should_follow_link(struct nameidata *nd, struct path *link,
 		return 0;
 	if (!follow)
 		return 0;
+	/* make sure that d_is_symlink above matches inode */
+	if (nd->flags & LOOKUP_RCU) {
+		if (read_seqcount_retry(&link->dentry->d_seq, seq))
+			return -ECHILD;
+	}
 	return pick_link(nd, link, inode, seq);
 }
 
@@ -1734,19 +1733,26 @@ static int walk_component(struct nameidata *nd, int flags)
 		return err;
 	}
 	err = lookup_fast(nd, &path, &inode, &seq);
-	if (unlikely(err)) {
+	if (unlikely(err <= 0)) {
 		if (err < 0)
 			return err;
-
-		err = lookup_slow(nd, &path);
-		if (err < 0)
+		path.dentry = lookup_slow(&nd->last, nd->path.dentry,
+					  nd->flags);
+		if (IS_ERR(path.dentry))
+			return PTR_ERR(path.dentry);
+
+		path.mnt = nd->path.mnt;
+		err = follow_managed(&path, nd);
+		if (unlikely(err < 0))
 			return err;
 
-		inode = d_backing_inode(path.dentry);
+		if (unlikely(d_is_negative(path.dentry))) {
+			path_to_nameidata(&path, nd);
+			return -ENOENT;
+		}
+
 		seq = 0;	/* we are already out of RCU mode */
-		err = -ENOENT;
-		if (d_is_negative(path.dentry))
-			goto out_path_put;
+		inode = d_backing_inode(path.dentry);
 	}
 
 	if (flags & WALK_PUT)
@@ -1758,10 +1764,6 @@ static int walk_component(struct nameidata *nd, int flags)
 	nd->inode = inode;
 	nd->seq = seq;
 	return 0;
-
-out_path_put:
-	path_to_nameidata(&path, nd);
-	return err;
 }
 
 /*
@@ -1996,7 +1998,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 	nd->last_type = LAST_ROOT; /* if there are only slashes... */
 	nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT;
 	nd->depth = 0;
-	nd->total_link_count = 0;
 	if (flags & LOOKUP_ROOT) {
 		struct dentry *root = nd->root.dentry;
 		struct inode *inode = root->d_inode;
@@ -2021,18 +2022,19 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 	}
 
 	nd->root.mnt = NULL;
+	nd->path.mnt = NULL;
+	nd->path.dentry = NULL;
 
 	nd->m_seq = read_seqbegin(&mount_lock);
 	if (*s == '/') {
-		if (flags & LOOKUP_RCU) {
+		if (flags & LOOKUP_RCU)
 			rcu_read_lock();
-			set_root_rcu(nd);
-			nd->seq = nd->root_seq;
-		} else {
-			set_root(nd);
-			path_get(&nd->root);
-		}
-		nd->path = nd->root;
+		set_root(nd);
+		if (likely(!nd_jump_root(nd)))
+			return s;
+		nd->root.mnt = NULL;
+		rcu_read_unlock();
+		return ERR_PTR(-ECHILD);
 	} else if (nd->dfd == AT_FDCWD) {
 		if (flags & LOOKUP_RCU) {
 			struct fs_struct *fs = current->fs;
@@ -2043,11 +2045,14 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 			do {
 				seq = read_seqcount_begin(&fs->seq);
 				nd->path = fs->pwd;
+				nd->inode = nd->path.dentry->d_inode;
 				nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
 			} while (read_seqcount_retry(&fs->seq, seq));
 		} else {
 			get_fs_pwd(current->fs, &nd->path);
+			nd->inode = nd->path.dentry->d_inode;
 		}
+		return s;
 	} else {
 		/* Caller must check execute permissions on the starting path component */
 		struct fd f = fdget_raw(nd->dfd);
@@ -2077,16 +2082,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 		fdput(f);
 		return s;
 	}
-
-	nd->inode = nd->path.dentry->d_inode;
-	if (!(flags & LOOKUP_RCU))
-		return s;
-	if (likely(!read_seqcount_retry(&nd->path.dentry->d_seq, nd->seq)))
-		return s;
-	if (!(nd->flags & LOOKUP_ROOT))
-		nd->root.mnt = NULL;
-	rcu_read_unlock();
-	return ERR_PTR(-ECHILD);
 }
 
 static const char *trailing_symlink(struct nameidata *nd)
@@ -2235,10 +2230,10 @@ struct dentry *kern_path_locked(const char *name, struct path *path)
 		putname(filename);
 		return ERR_PTR(-EINVAL);
 	}
-	mutex_lock_nested(&path->dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+	inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT);
 	d = __lookup_hash(&last, path->dentry, 0);
 	if (IS_ERR(d)) {
-		mutex_unlock(&path->dentry->d_inode->i_mutex);
+		inode_unlock(path->dentry->d_inode);
 		path_put(path);
 	}
 	putname(filename);
@@ -2279,6 +2274,8 @@ EXPORT_SYMBOL(vfs_path_lookup);
  *
  * Note that this routine is purely a helper for filesystem usage and should
  * not be called by generic code.
+ *
+ * The caller must hold base->i_mutex.
  */
 struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
 {
@@ -2286,7 +2283,7 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
 	unsigned int c;
 	int err;
 
-	WARN_ON_ONCE(!mutex_is_locked(&base->d_inode->i_mutex));
+	WARN_ON_ONCE(!inode_is_locked(base->d_inode));
 
 	this.name = name;
 	this.len = len;
@@ -2322,6 +2319,63 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
 }
 EXPORT_SYMBOL(lookup_one_len);
 
+/**
+ * lookup_one_len_unlocked - filesystem helper to lookup single pathname component
+ * @name:	pathname component to lookup
+ * @base:	base directory to lookup from
+ * @len:	maximum length @len should be interpreted to
+ *
+ * Note that this routine is purely a helper for filesystem usage and should
+ * not be called by generic code.
+ *
+ * Unlike lookup_one_len, it should be called without the parent
+ * i_mutex held, and will take the i_mutex itself if necessary.
+ */
+struct dentry *lookup_one_len_unlocked(const char *name,
+				       struct dentry *base, int len)
+{
+	struct qstr this;
+	unsigned int c;
+	int err;
+	struct dentry *ret;
+
+	this.name = name;
+	this.len = len;
+	this.hash = full_name_hash(name, len);
+	if (!len)
+		return ERR_PTR(-EACCES);
+
+	if (unlikely(name[0] == '.')) {
+		if (len < 2 || (len == 2 && name[1] == '.'))
+			return ERR_PTR(-EACCES);
+	}
+
+	while (len--) {
+		c = *(const unsigned char *)name++;
+		if (c == '/' || c == '\0')
+			return ERR_PTR(-EACCES);
+	}
+	/*
+	 * See if the low-level filesystem might want
+	 * to use its own hash..
+	 */
+	if (base->d_flags & DCACHE_OP_HASH) {
+		int err = base->d_op->d_hash(base, &this);
+		if (err < 0)
+			return ERR_PTR(err);
+	}
+
+	err = inode_permission(base->d_inode, MAY_EXEC);
+	if (err)
+		return ERR_PTR(err);
+
+	ret = lookup_dcache(&this, base, 0);
+	if (!ret)
+		ret = lookup_slow(&this, base, 0);
+	return ret;
+}
+EXPORT_SYMBOL(lookup_one_len_unlocked);
+
 int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
 		 struct path *path, int *empty)
 {
@@ -2395,31 +2449,21 @@ mountpoint_last(struct nameidata *nd, struct path *path)
 		if (error)
 			return error;
 		dentry = dget(nd->path.dentry);
-		goto done;
-	}
-
-	mutex_lock(&dir->d_inode->i_mutex);
-	dentry = d_lookup(dir, &nd->last);
-	if (!dentry) {
-		/*
-		 * No cached dentry. Mounted dentries are pinned in the cache,
-		 * so that means that this dentry is probably a symlink or the
-		 * path doesn't actually point to a mounted dentry.
-		 */
-		dentry = d_alloc(dir, &nd->last);
+	} else {
+		dentry = d_lookup(dir, &nd->last);
 		if (!dentry) {
-			mutex_unlock(&dir->d_inode->i_mutex);
-			return -ENOMEM;
-		}
-		dentry = lookup_real(dir->d_inode, dentry, nd->flags);
-		if (IS_ERR(dentry)) {
-			mutex_unlock(&dir->d_inode->i_mutex);
-			return PTR_ERR(dentry);
+			/*
+			 * No cached dentry. Mounted dentries are pinned in the
+			 * cache, so that means that this dentry is probably
+			 * a symlink or the path doesn't actually point
+			 * to a mounted dentry.
+			 */
+			dentry = lookup_slow(&nd->last, dir,
+					     nd->flags | LOOKUP_NO_REVAL);
+			if (IS_ERR(dentry))
+				return PTR_ERR(dentry);
 		}
 	}
-	mutex_unlock(&dir->d_inode->i_mutex);
-
-done:
 	if (d_is_negative(dentry)) {
 		dput(dentry);
 		return -ENOENT;
@@ -2607,7 +2651,7 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2)
 	struct dentry *p;
 
 	if (p1 == p2) {
-		mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
+		inode_lock_nested(p1->d_inode, I_MUTEX_PARENT);
 		return NULL;
 	}
 
@@ -2615,29 +2659,29 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2)
 
 	p = d_ancestor(p2, p1);
 	if (p) {
-		mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_PARENT);
-		mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_CHILD);
+		inode_lock_nested(p2->d_inode, I_MUTEX_PARENT);
+		inode_lock_nested(p1->d_inode, I_MUTEX_CHILD);
 		return p;
 	}
 
 	p = d_ancestor(p1, p2);
 	if (p) {
-		mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
-		mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD);
+		inode_lock_nested(p1->d_inode, I_MUTEX_PARENT);
+		inode_lock_nested(p2->d_inode, I_MUTEX_CHILD);
 		return p;
 	}
 
-	mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
-	mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_PARENT2);
+	inode_lock_nested(p1->d_inode, I_MUTEX_PARENT);
+	inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2);
 	return NULL;
 }
 EXPORT_SYMBOL(lock_rename);
 
 void unlock_rename(struct dentry *p1, struct dentry *p2)
 {
-	mutex_unlock(&p1->d_inode->i_mutex);
+	inode_unlock(p1->d_inode);
 	if (p1 != p2) {
-		mutex_unlock(&p2->d_inode->i_mutex);
+		inode_unlock(p2->d_inode);
 		mutex_unlock(&p1->d_inode->i_sb->s_vfs_rename_mutex);
 	}
 }
@@ -2670,10 +2714,6 @@ static int may_open(struct path *path, int acc_mode, int flag)
 	struct inode *inode = dentry->d_inode;
 	int error;
 
-	/* O_PATH? */
-	if (!acc_mode)
-		return 0;
-
 	if (!inode)
 		return -ENOENT;
 
@@ -2695,7 +2735,7 @@ static int may_open(struct path *path, int acc_mode, int flag)
 		break;
 	}
 
-	error = inode_permission(inode, acc_mode);
+	error = inode_permission(inode, MAY_OPEN | acc_mode);
 	if (error)
 		return error;
 
@@ -2887,7 +2927,7 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry,
 	if (*opened & FILE_CREATED) {
 		WARN_ON(!(open_flag & O_CREAT));
 		fsnotify_create(dir, dentry);
-		acc_mode = MAY_OPEN;
+		acc_mode = 0;
 	}
 	error = may_open(&file->f_path, acc_mode, open_flag);
 	if (error)
@@ -2952,16 +2992,22 @@ static int lookup_open(struct nameidata *nd, struct path *path,
 	struct inode *dir_inode = dir->d_inode;
 	struct dentry *dentry;
 	int error;
-	bool need_lookup;
+	bool need_lookup = false;
 
 	*opened &= ~FILE_CREATED;
-	dentry = lookup_dcache(&nd->last, dir, nd->flags, &need_lookup);
+	dentry = lookup_dcache(&nd->last, dir, nd->flags);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
-	/* Cached positive dentry: will open in f_op->open */
-	if (!need_lookup && dentry->d_inode)
+	if (!dentry) {
+		dentry = d_alloc(dir, &nd->last);
+		if (unlikely(!dentry))
+			return -ENOMEM;
+		need_lookup = true;
+	} else if (dentry->d_inode) {
+		/* Cached positive dentry: will open in f_op->open */
 		goto out_no_open;
+	}
 
 	if ((nd->flags & LOOKUP_OPEN) && dir_inode->i_op->atomic_open) {
 		return atomic_open(nd, dentry, path, file, op, got_write,
@@ -3045,13 +3091,14 @@ static int do_last(struct nameidata *nd,
 			nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
 		/* we _can_ be in RCU mode here */
 		error = lookup_fast(nd, &path, &inode, &seq);
-		if (likely(!error))
+		if (likely(error > 0))
 			goto finish_lookup;
 
 		if (error < 0)
 			return error;
 
 		BUG_ON(nd->inode != dir->d_inode);
+		BUG_ON(nd->flags & LOOKUP_RCU);
 	} else {
 		/* create side of things */
 		/*
@@ -3080,9 +3127,9 @@ retry_lookup:
 		 * dropping this one anyway.
 		 */
 	}
-	mutex_lock(&dir->d_inode->i_mutex);
+	inode_lock(dir->d_inode);
 	error = lookup_open(nd, &path, file, op, got_write, opened);
-	mutex_unlock(&dir->d_inode->i_mutex);
+	inode_unlock(dir->d_inode);
 
 	if (error <= 0) {
 		if (error)
@@ -3100,18 +3147,12 @@ retry_lookup:
 		/* Don't check for write permission, don't truncate */
 		open_flag &= ~O_TRUNC;
 		will_truncate = false;
-		acc_mode = MAY_OPEN;
+		acc_mode = 0;
 		path_to_nameidata(&path, nd);
 		goto finish_open_created;
 	}
 
 	/*
-	 * create/update audit record if it already exists.
-	 */
-	if (d_is_positive(path.dentry))
-		audit_inode(nd->name, path.dentry, 0);
-
-	/*
 	 * If atomic_open() acquired write access it is dropped now due to
 	 * possible mount and symlink following (this might be optimized away if
 	 * necessary...)
@@ -3121,6 +3162,16 @@ retry_lookup:
 		got_write = false;
 	}
 
+	if (unlikely(d_is_negative(path.dentry))) {
+		path_to_nameidata(&path, nd);
+		return -ENOENT;
+	}
+
+	/*
+	 * create/update audit record if it already exists.
+	 */
+	audit_inode(nd->name, path.dentry, 0);
+
 	if (unlikely((open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT))) {
 		path_to_nameidata(&path, nd);
 		return -EEXIST;
@@ -3130,13 +3181,8 @@ retry_lookup:
 	if (unlikely(error < 0))
 		return error;
 
-	BUG_ON(nd->flags & LOOKUP_RCU);
-	inode = d_backing_inode(path.dentry);
 	seq = 0;	/* out of RCU mode, so the value doesn't matter */
-	if (unlikely(d_is_negative(path.dentry))) {
-		path_to_nameidata(&path, nd);
-		return -ENOENT;
-	}
+	inode = d_backing_inode(path.dentry);
 finish_lookup:
 	if (nd->depth)
 		put_link(nd);
@@ -3145,11 +3191,6 @@ finish_lookup:
 	if (unlikely(error))
 		return error;
 
-	if (unlikely(d_is_symlink(path.dentry)) && !(open_flag & O_PATH)) {
-		path_to_nameidata(&path, nd);
-		return -ELOOP;
-	}
-
 	if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path.mnt) {
 		path_to_nameidata(&path, nd);
 	} else {
@@ -3168,6 +3209,10 @@ finish_open:
 		return error;
 	}
 	audit_inode(nd->name, nd->path.dentry, 0);
+	if (unlikely(d_is_symlink(nd->path.dentry)) && !(open_flag & O_PATH)) {
+		error = -ELOOP;
+		goto out;
+	}
 	error = -EISDIR;
 	if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry))
 		goto out;
@@ -3184,10 +3229,11 @@ finish_open:
 		got_write = true;
 	}
 finish_open_created:
-	error = may_open(&nd->path, acc_mode, open_flag);
-	if (error)
-		goto out;
-
+	if (likely(!(open_flag & O_PATH))) {
+		error = may_open(&nd->path, acc_mode, open_flag);
+		if (error)
+			goto out;
+	}
 	BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
 	error = vfs_open(&nd->path, file, current_cred());
 	if (!error) {
@@ -3211,6 +3257,10 @@ opened:
 			goto exit_fput;
 	}
 out:
+	if (unlikely(error > 0)) {
+		WARN_ON(1);
+		error = -EINVAL;
+	}
 	if (got_write)
 		mnt_drop_write(nd->path.mnt);
 	path_put(&save_parent);
@@ -3274,7 +3324,7 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags,
 		goto out2;
 	audit_inode(nd->name, child, 0);
 	/* Don't check for other permissions, the inode was just created */
-	error = may_open(&path, MAY_OPEN, op->open_flag);
+	error = may_open(&path, 0, op->open_flag);
 	if (error)
 		goto out2;
 	file->f_path.mnt = path.mnt;
@@ -3427,7 +3477,7 @@ static struct dentry *filename_create(int dfd, struct filename *name,
 	 * Do the final lookup.
 	 */
 	lookup_flags |= LOOKUP_CREATE | LOOKUP_EXCL;
-	mutex_lock_nested(&path->dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+	inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT);
 	dentry = __lookup_hash(&last, path->dentry, lookup_flags);
 	if (IS_ERR(dentry))
 		goto unlock;
@@ -3456,7 +3506,7 @@ fail:
 	dput(dentry);
 	dentry = ERR_PTR(error);
 unlock:
-	mutex_unlock(&path->dentry->d_inode->i_mutex);
+	inode_unlock(path->dentry->d_inode);
 	if (!err2)
 		mnt_drop_write(path->mnt);
 out:
@@ -3476,7 +3526,7 @@ EXPORT_SYMBOL(kern_path_create);
 void done_path_create(struct path *path, struct dentry *dentry)
 {
 	dput(dentry);
-	mutex_unlock(&path->dentry->d_inode->i_mutex);
+	inode_unlock(path->dentry->d_inode);
 	mnt_drop_write(path->mnt);
 	path_put(path);
 }
@@ -3637,31 +3687,6 @@ SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode)
 	return sys_mkdirat(AT_FDCWD, pathname, mode);
 }
 
-/*
- * The dentry_unhash() helper will try to drop the dentry early: we
- * should have a usage count of 1 if we're the only user of this
- * dentry, and if that is true (possibly after pruning the dcache),
- * then we drop the dentry now.
- *
- * A low-level filesystem can, if it choses, legally
- * do a
- *
- *	if (!d_unhashed(dentry))
- *		return -EBUSY;
- *
- * if it cannot handle the case of removing a directory
- * that is still in use by something else..
- */
-void dentry_unhash(struct dentry *dentry)
-{
-	shrink_dcache_parent(dentry);
-	spin_lock(&dentry->d_lock);
-	if (dentry->d_lockref.count == 1)
-		__d_drop(dentry);
-	spin_unlock(&dentry->d_lock);
-}
-EXPORT_SYMBOL(dentry_unhash);
-
 int vfs_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	int error = may_delete(dir, dentry, 1);
@@ -3673,7 +3698,7 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry)
 		return -EPERM;
 
 	dget(dentry);
-	mutex_lock(&dentry->d_inode->i_mutex);
+	inode_lock(dentry->d_inode);
 
 	error = -EBUSY;
 	if (is_local_mountpoint(dentry))
@@ -3693,7 +3718,7 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry)
 	detach_mounts(dentry);
 
 out:
-	mutex_unlock(&dentry->d_inode->i_mutex);
+	inode_unlock(dentry->d_inode);
 	dput(dentry);
 	if (!error)
 		d_delete(dentry);
@@ -3732,7 +3757,7 @@ retry:
 	if (error)
 		goto exit1;
 
-	mutex_lock_nested(&path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+	inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT);
 	dentry = __lookup_hash(&last, path.dentry, lookup_flags);
 	error = PTR_ERR(dentry);
 	if (IS_ERR(dentry))
@@ -3748,7 +3773,7 @@ retry:
 exit3:
 	dput(dentry);
 exit2:
-	mutex_unlock(&path.dentry->d_inode->i_mutex);
+	inode_unlock(path.dentry->d_inode);
 	mnt_drop_write(path.mnt);
 exit1:
 	path_put(&path);
@@ -3794,7 +3819,7 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegate
 	if (!dir->i_op->unlink)
 		return -EPERM;
 
-	mutex_lock(&target->i_mutex);
+	inode_lock(target);
 	if (is_local_mountpoint(dentry))
 		error = -EBUSY;
 	else {
@@ -3811,7 +3836,7 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegate
 		}
 	}
 out:
-	mutex_unlock(&target->i_mutex);
+	inode_unlock(target);
 
 	/* We don't d_delete() NFS sillyrenamed files--they still exist. */
 	if (!error && !(dentry->d_flags & DCACHE_NFSFS_RENAMED)) {
@@ -3854,7 +3879,7 @@ retry:
 	if (error)
 		goto exit1;
 retry_deleg:
-	mutex_lock_nested(&path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+	inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT);
 	dentry = __lookup_hash(&last, path.dentry, lookup_flags);
 	error = PTR_ERR(dentry);
 	if (!IS_ERR(dentry)) {
@@ -3872,7 +3897,7 @@ retry_deleg:
 exit2:
 		dput(dentry);
 	}
-	mutex_unlock(&path.dentry->d_inode->i_mutex);
+	inode_unlock(path.dentry->d_inode);
 	if (inode)
 		iput(inode);	/* truncate the inode here */
 	inode = NULL;
@@ -4024,7 +4049,7 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de
 	if (error)
 		return error;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	/* Make sure we don't allow creating hardlink to an unlinked file */
 	if (inode->i_nlink == 0 && !(inode->i_state & I_LINKABLE))
 		error =  -ENOENT;
@@ -4041,7 +4066,7 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de
 		inode->i_state &= ~I_LINKABLE;
 		spin_unlock(&inode->i_lock);
 	}
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	if (!error)
 		fsnotify_link(dir, inode, new_dentry);
 	return error;
@@ -4241,7 +4266,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (!is_dir || (flags & RENAME_EXCHANGE))
 		lock_two_nondirectories(source, target);
 	else if (target)
-		mutex_lock(&target->i_mutex);
+		inode_lock(target);
 
 	error = -EBUSY;
 	if (is_local_mountpoint(old_dentry) || is_local_mountpoint(new_dentry))
@@ -4294,7 +4319,7 @@ out:
 	if (!is_dir || (flags & RENAME_EXCHANGE))
 		unlock_two_nondirectories(source, target);
 	else if (target)
-		mutex_unlock(&target->i_mutex);
+		inode_unlock(target);
 	dput(new_dentry);
 	if (!error) {
 		fsnotify_move(old_dir, new_dir, old_name, is_dir,
@@ -4496,72 +4521,73 @@ EXPORT_SYMBOL(readlink_copy);
 
 /*
  * A helper for ->readlink().  This should be used *ONLY* for symlinks that
- * have ->follow_link() touching nd only in nd_set_link().  Using (or not
- * using) it for any given inode is up to filesystem.
+ * have ->get_link() not calling nd_jump_link().  Using (or not using) it
+ * for any given inode is up to filesystem.
  */
 int generic_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 {
-	void *cookie;
+	DEFINE_DELAYED_CALL(done);
 	struct inode *inode = d_inode(dentry);
 	const char *link = inode->i_link;
 	int res;
 
 	if (!link) {
-		link = inode->i_op->follow_link(dentry, &cookie);
+		link = inode->i_op->get_link(dentry, inode, &done);
 		if (IS_ERR(link))
 			return PTR_ERR(link);
 	}
 	res = readlink_copy(buffer, buflen, link);
-	if (inode->i_op->put_link)
-		inode->i_op->put_link(inode, cookie);
+	do_delayed_call(&done);
 	return res;
 }
 EXPORT_SYMBOL(generic_readlink);
 
 /* get the link contents into pagecache */
-static char *page_getlink(struct dentry * dentry, struct page **ppage)
+const char *page_get_link(struct dentry *dentry, struct inode *inode,
+			  struct delayed_call *callback)
 {
 	char *kaddr;
 	struct page *page;
-	struct address_space *mapping = dentry->d_inode->i_mapping;
-	page = read_mapping_page(mapping, 0, NULL);
-	if (IS_ERR(page))
-		return (char*)page;
-	*ppage = page;
-	kaddr = kmap(page);
-	nd_terminate_link(kaddr, dentry->d_inode->i_size, PAGE_SIZE - 1);
+	struct address_space *mapping = inode->i_mapping;
+
+	if (!dentry) {
+		page = find_get_page(mapping, 0);
+		if (!page)
+			return ERR_PTR(-ECHILD);
+		if (!PageUptodate(page)) {
+			put_page(page);
+			return ERR_PTR(-ECHILD);
+		}
+	} else {
+		page = read_mapping_page(mapping, 0, NULL);
+		if (IS_ERR(page))
+			return (char*)page;
+	}
+	set_delayed_call(callback, page_put_link, page);
+	BUG_ON(mapping_gfp_mask(mapping) & __GFP_HIGHMEM);
+	kaddr = page_address(page);
+	nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1);
 	return kaddr;
 }
 
-int page_readlink(struct dentry *dentry, char __user *buffer, int buflen)
-{
-	struct page *page = NULL;
-	int res = readlink_copy(buffer, buflen, page_getlink(dentry, &page));
-	if (page) {
-		kunmap(page);
-		page_cache_release(page);
-	}
-	return res;
-}
-EXPORT_SYMBOL(page_readlink);
+EXPORT_SYMBOL(page_get_link);
 
-const char *page_follow_link_light(struct dentry *dentry, void **cookie)
+void page_put_link(void *arg)
 {
-	struct page *page = NULL;
-	char *res = page_getlink(dentry, &page);
-	if (!IS_ERR(res))
-		*cookie = page;
-	return res;
+	put_page(arg);
 }
-EXPORT_SYMBOL(page_follow_link_light);
+EXPORT_SYMBOL(page_put_link);
 
-void page_put_link(struct inode *unused, void *cookie)
+int page_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 {
-	struct page *page = cookie;
-	kunmap(page);
-	page_cache_release(page);
+	DEFINE_DELAYED_CALL(done);
+	int res = readlink_copy(buffer, buflen,
+				page_get_link(dentry, d_inode(dentry),
+					      &done));
+	do_delayed_call(&done);
+	return res;
 }
-EXPORT_SYMBOL(page_put_link);
+EXPORT_SYMBOL(page_readlink);
 
 /*
  * The nofs argument instructs pagecache_write_begin to pass AOP_FLAG_NOFS
@@ -4572,7 +4598,6 @@ int __page_symlink(struct inode *inode, const char *symname, int len, int nofs)
 	struct page *page;
 	void *fsdata;
 	int err;
-	char *kaddr;
 	unsigned int flags = AOP_FLAG_UNINTERRUPTIBLE;
 	if (nofs)
 		flags |= AOP_FLAG_NOFS;
@@ -4583,9 +4608,7 @@ retry:
 	if (err)
 		goto fail;
 
-	kaddr = kmap_atomic(page);
-	memcpy(kaddr, symname, len-1);
-	kunmap_atomic(kaddr);
+	memcpy(page_address(page), symname, len-1);
 
 	err = pagecache_write_end(NULL, mapping, 0, len-1, len-1,
 							page, fsdata);
@@ -4604,13 +4627,12 @@ EXPORT_SYMBOL(__page_symlink);
 int page_symlink(struct inode *inode, const char *symname, int len)
 {
 	return __page_symlink(inode, symname, len,
-			!(mapping_gfp_mask(inode->i_mapping) & __GFP_FS));
+			!mapping_gfp_constraint(inode->i_mapping, __GFP_FS));
 }
 EXPORT_SYMBOL(page_symlink);
 
 const struct inode_operations page_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 };
 EXPORT_SYMBOL(page_symlink_inode_operations);
diff --git a/fs/namespace.c b/fs/namespace.c
index 0570729c87fd..4fb1691b4355 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1584,6 +1584,14 @@ static inline bool may_mount(void)
 	return ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN);
 }
 
+static inline bool may_mandlock(void)
+{
+#ifndef	CONFIG_MANDATORY_FILE_LOCKING
+	return false;
+#endif
+	return capable(CAP_SYS_ADMIN);
+}
+
 /*
  * Now umount can handle mount points as well as block devices.
  * This is important for filesystems which use unnamed block devices.
@@ -1953,9 +1961,9 @@ static struct mountpoint *lock_mount(struct path *path)
 	struct vfsmount *mnt;
 	struct dentry *dentry = path->dentry;
 retry:
-	mutex_lock(&dentry->d_inode->i_mutex);
+	inode_lock(dentry->d_inode);
 	if (unlikely(cant_mount(dentry))) {
-		mutex_unlock(&dentry->d_inode->i_mutex);
+		inode_unlock(dentry->d_inode);
 		return ERR_PTR(-ENOENT);
 	}
 	namespace_lock();
@@ -1966,13 +1974,13 @@ retry:
 			mp = new_mountpoint(dentry);
 		if (IS_ERR(mp)) {
 			namespace_unlock();
-			mutex_unlock(&dentry->d_inode->i_mutex);
+			inode_unlock(dentry->d_inode);
 			return mp;
 		}
 		return mp;
 	}
 	namespace_unlock();
-	mutex_unlock(&path->dentry->d_inode->i_mutex);
+	inode_unlock(path->dentry->d_inode);
 	path_put(path);
 	path->mnt = mnt;
 	dentry = path->dentry = dget(mnt->mnt_root);
@@ -1984,7 +1992,7 @@ static void unlock_mount(struct mountpoint *where)
 	struct dentry *dentry = where->m_dentry;
 	put_mountpoint(where);
 	namespace_unlock();
-	mutex_unlock(&dentry->d_inode->i_mutex);
+	inode_unlock(dentry->d_inode);
 }
 
 static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp)
@@ -2601,18 +2609,18 @@ static long exact_copy_from_user(void *to, const void __user * from,
 	return n;
 }
 
-int copy_mount_options(const void __user * data, unsigned long *where)
+void *copy_mount_options(const void __user * data)
 {
 	int i;
-	unsigned long page;
 	unsigned long size;
+	char *copy;
 
-	*where = 0;
 	if (!data)
-		return 0;
+		return NULL;
 
-	if (!(page = __get_free_page(GFP_KERNEL)))
-		return -ENOMEM;
+	copy = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!copy)
+		return ERR_PTR(-ENOMEM);
 
 	/* We only care that *some* data at the address the user
 	 * gave us is valid.  Just in case, we'll zero
@@ -2623,15 +2631,14 @@ int copy_mount_options(const void __user * data, unsigned long *where)
 	if (size > PAGE_SIZE)
 		size = PAGE_SIZE;
 
-	i = size - exact_copy_from_user((void *)page, data, size);
+	i = size - exact_copy_from_user(copy, data, size);
 	if (!i) {
-		free_page(page);
-		return -EFAULT;
+		kfree(copy);
+		return ERR_PTR(-EFAULT);
 	}
 	if (i != PAGE_SIZE)
-		memset((char *)page + i, 0, PAGE_SIZE - i);
-	*where = page;
-	return 0;
+		memset(copy + i, 0, PAGE_SIZE - i);
+	return copy;
 }
 
 char *copy_mount_string(const void __user *data)
@@ -2677,6 +2684,8 @@ long do_mount(const char *dev_name, const char __user *dir_name,
 				   type_page, flags, data_page);
 	if (!retval && !may_mount())
 		retval = -EPERM;
+	if (!retval && (flags & MS_MANDLOCK) && !may_mandlock())
+		retval = -EPERM;
 	if (retval)
 		goto dput_out;
 
@@ -2896,7 +2905,7 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
 	int ret;
 	char *kernel_type;
 	char *kernel_dev;
-	unsigned long data_page;
+	void *options;
 
 	kernel_type = copy_mount_string(type);
 	ret = PTR_ERR(kernel_type);
@@ -2908,14 +2917,14 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
 	if (IS_ERR(kernel_dev))
 		goto out_dev;
 
-	ret = copy_mount_options(data, &data_page);
-	if (ret < 0)
+	options = copy_mount_options(data);
+	ret = PTR_ERR(options);
+	if (IS_ERR(options))
 		goto out_data;
 
-	ret = do_mount(kernel_dev, dir_name, kernel_type, flags,
-		(void *) data_page);
+	ret = do_mount(kernel_dev, dir_name, kernel_type, flags, options);
 
-	free_page(data_page);
+	kfree(options);
 out_data:
 	kfree(kernel_dev);
 out_dev:
@@ -2939,9 +2948,9 @@ bool is_path_reachable(struct mount *mnt, struct dentry *dentry,
 	return &mnt->mnt == root->mnt && is_subdir(dentry, root->dentry);
 }
 
-int path_is_under(struct path *path1, struct path *path2)
+bool path_is_under(struct path *path1, struct path *path2)
 {
-	int res;
+	bool res;
 	read_seqlock_excl(&mount_lock);
 	res = is_path_reachable(real_mount(path1->mnt), path1->dentry, path2);
 	read_sequnlock_excl(&mount_lock);
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index 356816e7bc90..bfdad003ee56 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -369,7 +369,7 @@ ncp_lookup_validate(struct dentry *dentry, unsigned int flags)
 	if (!res) {
 		struct inode *inode = d_inode(dentry);
 
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		if (finfo.i.dirEntNum == NCP_FINFO(inode)->dirEntNum) {
 			ncp_new_dentry(dentry);
 			val=1;
@@ -377,7 +377,7 @@ ncp_lookup_validate(struct dentry *dentry, unsigned int flags)
 			ncp_dbg(2, "found, but dirEntNum changed\n");
 
 		ncp_update_inode2(inode, &finfo);
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 	}
 
 finished:
@@ -510,7 +510,7 @@ static int ncp_readdir(struct file *file, struct dir_context *ctx)
 			kunmap(ctl.page);
 			SetPageUptodate(ctl.page);
 			unlock_page(ctl.page);
-			page_cache_release(ctl.page);
+			put_page(ctl.page);
 			ctl.page = NULL;
 		}
 		ctl.idx  = 0;
@@ -520,7 +520,7 @@ invalid_cache:
 	if (ctl.page) {
 		kunmap(ctl.page);
 		unlock_page(ctl.page);
-		page_cache_release(ctl.page);
+		put_page(ctl.page);
 		ctl.page = NULL;
 	}
 	ctl.cache = cache;
@@ -554,14 +554,14 @@ finished:
 		kunmap(ctl.page);
 		SetPageUptodate(ctl.page);
 		unlock_page(ctl.page);
-		page_cache_release(ctl.page);
+		put_page(ctl.page);
 	}
 	if (page) {
 		cache->head = ctl.head;
 		kunmap(page);
 		SetPageUptodate(page);
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 	}
 out:
 	return result;
@@ -633,15 +633,15 @@ ncp_fill_cache(struct file *file, struct dir_context *ctx,
 				d_rehash(newdent);
 		} else {
 			spin_lock(&dentry->d_lock);
-			NCP_FINFO(inode)->flags &= ~NCPI_DIR_CACHE;
+			NCP_FINFO(dir)->flags &= ~NCPI_DIR_CACHE;
 			spin_unlock(&dentry->d_lock);
 		}
 	} else {
 		struct inode *inode = d_inode(newdent);
 
-		mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
+		inode_lock_nested(inode, I_MUTEX_CHILD);
 		ncp_update_inode2(inode, entry);
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 	}
 
 	if (ctl.idx >= NCP_DIRCACHE_SIZE) {
@@ -649,7 +649,7 @@ ncp_fill_cache(struct file *file, struct dir_context *ctx,
 			kunmap(ctl.page);
 			SetPageUptodate(ctl.page);
 			unlock_page(ctl.page);
-			page_cache_release(ctl.page);
+			put_page(ctl.page);
 		}
 		ctl.cache = NULL;
 		ctl.idx  -= NCP_DIRCACHE_SIZE;
@@ -1165,8 +1165,6 @@ out:
 static int ncp_mknod(struct inode * dir, struct dentry *dentry,
 		     umode_t mode, dev_t rdev)
 {
-	if (!new_valid_dev(rdev))
-		return -EINVAL;
 	if (ncp_is_nfs_extras(NCP_SERVER(dir), NCP_FINFO(dir)->volNumber)) {
 		ncp_dbg(1, "mode = 0%ho\n", mode);
 		return ncp_create_new(dir, dentry, mode, rdev, 0);
diff --git a/fs/ncpfs/file.c b/fs/ncpfs/file.c
index 011324ce9df2..dd38ca1f2ecb 100644
--- a/fs/ncpfs/file.c
+++ b/fs/ncpfs/file.c
@@ -224,10 +224,10 @@ ncp_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	iocb->ki_pos = pos;
 
 	if (pos > i_size_read(inode)) {
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		if (pos > i_size_read(inode))
 			i_size_write(inode, pos);
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 	}
 	ncp_dbg(1, "exit %pD2\n", file);
 outrel:
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index 9605a2f63549..1af15fcbe57b 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -82,7 +82,7 @@ static int init_inodecache(void)
 	ncp_inode_cachep = kmem_cache_create("ncp_inode_cache",
 					     sizeof(struct ncp_inode_info),
 					     0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD),
+						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
 					     init_once);
 	if (ncp_inode_cachep == NULL)
 		return -ENOMEM;
@@ -244,8 +244,7 @@ static void ncp_set_attr(struct inode *inode, struct ncp_entry_info *nwinfo)
 #if defined(CONFIG_NCPFS_EXTRAS) || defined(CONFIG_NCPFS_NFS_NS)
 static const struct inode_operations ncp_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 	.setattr	= ncp_notify_change,
 };
 #endif
@@ -283,6 +282,7 @@ ncp_iget(struct super_block *sb, struct ncp_entry_info *info)
 #if defined(CONFIG_NCPFS_EXTRAS) || defined(CONFIG_NCPFS_NFS_NS)
 		} else if (S_ISLNK(inode->i_mode)) {
 			inode->i_op = &ncp_symlink_inode_operations;
+			inode_nohighmem(inode);
 			inode->i_data.a_ops = &ncp_symlink_aops;
 #endif
 		} else {
diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c
index 79b113048eac..0a3f9b594602 100644
--- a/fs/ncpfs/ioctl.c
+++ b/fs/ncpfs/ioctl.c
@@ -525,6 +525,8 @@ static long __ncp_ioctl(struct inode *inode, unsigned int cmd, unsigned long arg
 			switch (rqdata.cmd) {
 				case NCP_LOCK_EX:
 				case NCP_LOCK_SH:
+						if (rqdata.timeout < 0)
+							return -EINVAL;
 						if (rqdata.timeout == 0)
 							rqdata.timeout = NCP_LOCK_DEFAULT_TIMEOUT;
 						else if (rqdata.timeout > NCP_LOCK_MAX_TIMEOUT)
diff --git a/fs/ncpfs/ncplib_kernel.h b/fs/ncpfs/ncplib_kernel.h
index 5233fbc1747a..17cfb743b5bf 100644
--- a/fs/ncpfs/ncplib_kernel.h
+++ b/fs/ncpfs/ncplib_kernel.h
@@ -191,7 +191,7 @@ struct ncp_cache_head {
 	int		eof;
 };
 
-#define NCP_DIRCACHE_SIZE	((int)(PAGE_CACHE_SIZE/sizeof(struct dentry *)))
+#define NCP_DIRCACHE_SIZE	((int)(PAGE_SIZE/sizeof(struct dentry *)))
 union ncp_dir_cache {
 	struct ncp_cache_head	head;
 	struct dentry		*dentry[NCP_DIRCACHE_SIZE];
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 9cd4eb3a1e22..17a42e4eb872 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -229,9 +229,9 @@ bl_read_pagelist(struct nfs_pgio_header *header)
 	struct parallel_io *par;
 	loff_t f_offset = header->args.offset;
 	size_t bytes_left = header->args.count;
-	unsigned int pg_offset, pg_len;
+	unsigned int pg_offset = header->args.pgbase, pg_len;
 	struct page **pages = header->args.pages;
-	int pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT;
+	int pg_index = header->args.pgbase >> PAGE_SHIFT;
 	const bool is_dio = (header->dreq != NULL);
 	struct blk_plug plug;
 	int i;
@@ -262,20 +262,16 @@ bl_read_pagelist(struct nfs_pgio_header *header)
 			extent_length = be.be_length - (isect - be.be_f_offset);
 		}
 
-		pg_offset = f_offset & ~PAGE_CACHE_MASK;
 		if (is_dio) {
-			if (pg_offset + bytes_left > PAGE_CACHE_SIZE)
-				pg_len = PAGE_CACHE_SIZE - pg_offset;
+			if (pg_offset + bytes_left > PAGE_SIZE)
+				pg_len = PAGE_SIZE - pg_offset;
 			else
 				pg_len = bytes_left;
 		} else {
 			BUG_ON(pg_offset != 0);
-			pg_len = PAGE_CACHE_SIZE;
+			pg_len = PAGE_SIZE;
 		}
 
-		isect += (pg_offset >> SECTOR_SHIFT);
-		extent_length -= (pg_offset >> SECTOR_SHIFT);
-
 		if (is_hole(&be)) {
 			bio = bl_submit_bio(READ, bio);
 			/* Fill hole w/ zeroes w/o accessing device */
@@ -301,6 +297,7 @@ bl_read_pagelist(struct nfs_pgio_header *header)
 		extent_length -= (pg_len >> SECTOR_SHIFT);
 		f_offset += pg_len;
 		bytes_left -= pg_len;
+		pg_offset = 0;
 	}
 	if ((isect << SECTOR_SHIFT) >= header->inode->i_size) {
 		header->res.eof = 1;
@@ -342,9 +339,9 @@ static void bl_write_cleanup(struct work_struct *work)
 
 	if (likely(!hdr->pnfs_error)) {
 		struct pnfs_block_layout *bl = BLK_LSEG2EXT(hdr->lseg);
-		u64 start = hdr->args.offset & (loff_t)PAGE_CACHE_MASK;
+		u64 start = hdr->args.offset & (loff_t)PAGE_MASK;
 		u64 end = (hdr->args.offset + hdr->args.count +
-			PAGE_CACHE_SIZE - 1) & (loff_t)PAGE_CACHE_MASK;
+			PAGE_SIZE - 1) & (loff_t)PAGE_MASK;
 
 		ext_tree_mark_written(bl, start >> SECTOR_SHIFT,
 					(end - start) >> SECTOR_SHIFT);
@@ -376,7 +373,7 @@ bl_write_pagelist(struct nfs_pgio_header *header, int sync)
 	loff_t offset = header->args.offset;
 	size_t count = header->args.count;
 	struct page **pages = header->args.pages;
-	int pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT;
+	int pg_index = header->args.pgbase >> PAGE_SHIFT;
 	unsigned int pg_len;
 	struct blk_plug plug;
 	int i;
@@ -395,7 +392,7 @@ bl_write_pagelist(struct nfs_pgio_header *header, int sync)
 	blk_start_plug(&plug);
 
 	/* we always write out the whole page */
-	offset = offset & (loff_t)PAGE_CACHE_MASK;
+	offset = offset & (loff_t)PAGE_MASK;
 	isect = offset >> SECTOR_SHIFT;
 
 	for (i = pg_index; i < header->page_array.npages; i++) {
@@ -411,7 +408,7 @@ bl_write_pagelist(struct nfs_pgio_header *header, int sync)
 			extent_length = be.be_length - (isect - be.be_f_offset);
 		}
 
-		pg_len = PAGE_CACHE_SIZE;
+		pg_len = PAGE_SIZE;
 		bio = do_add_page_to_bio(bio, header->page_array.npages - i,
 					 WRITE, isect, pages[i], &map, &be,
 					 bl_end_io_write, par,
@@ -449,8 +446,8 @@ static void bl_free_layout_hdr(struct pnfs_layout_hdr *lo)
 	kfree(bl);
 }
 
-static struct pnfs_layout_hdr *bl_alloc_layout_hdr(struct inode *inode,
-						   gfp_t gfp_flags)
+static struct pnfs_layout_hdr *__bl_alloc_layout_hdr(struct inode *inode,
+		gfp_t gfp_flags, bool is_scsi_layout)
 {
 	struct pnfs_block_layout *bl;
 
@@ -463,9 +460,22 @@ static struct pnfs_layout_hdr *bl_alloc_layout_hdr(struct inode *inode,
 	bl->bl_ext_ro = RB_ROOT;
 	spin_lock_init(&bl->bl_ext_lock);
 
+	bl->bl_scsi_layout = is_scsi_layout;
 	return &bl->bl_layout;
 }
 
+static struct pnfs_layout_hdr *bl_alloc_layout_hdr(struct inode *inode,
+						   gfp_t gfp_flags)
+{
+	return __bl_alloc_layout_hdr(inode, gfp_flags, false);
+}
+
+static struct pnfs_layout_hdr *sl_alloc_layout_hdr(struct inode *inode,
+						   gfp_t gfp_flags)
+{
+	return __bl_alloc_layout_hdr(inode, gfp_flags, true);
+}
+
 static void bl_free_lseg(struct pnfs_layout_segment *lseg)
 {
 	dprintk("%s enter\n", __func__);
@@ -746,7 +756,7 @@ bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh)
 
 static bool
 is_aligned_req(struct nfs_pageio_descriptor *pgio,
-		struct nfs_page *req, unsigned int alignment)
+		struct nfs_page *req, unsigned int alignment, bool is_write)
 {
 	/*
 	 * Always accept buffered writes, higher layers take care of the
@@ -761,7 +771,8 @@ is_aligned_req(struct nfs_pageio_descriptor *pgio,
 	if (IS_ALIGNED(req->wb_bytes, alignment))
 		return true;
 
-	if (req_offset(req) + req->wb_bytes == i_size_read(pgio->pg_inode)) {
+	if (is_write &&
+	    (req_offset(req) + req->wb_bytes == i_size_read(pgio->pg_inode))) {
 		/*
 		 * If the write goes up to the inode size, just write
 		 * the full page.  Data past the inode size is
@@ -778,7 +789,7 @@ is_aligned_req(struct nfs_pageio_descriptor *pgio,
 static void
 bl_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 {
-	if (!is_aligned_req(pgio, req, SECTOR_SIZE)) {
+	if (!is_aligned_req(pgio, req, SECTOR_SIZE, false)) {
 		nfs_pageio_reset_read_mds(pgio);
 		return;
 	}
@@ -794,7 +805,7 @@ static size_t
 bl_pg_test_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 		struct nfs_page *req)
 {
-	if (!is_aligned_req(pgio, req, SECTOR_SIZE))
+	if (!is_aligned_req(pgio, req, SECTOR_SIZE, false))
 		return 0;
 	return pnfs_generic_pg_test(pgio, prev, req);
 }
@@ -809,7 +820,7 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx)
 	pgoff_t end;
 
 	/* Optimize common case that writes from 0 to end of file */
-	end = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE);
+	end = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
 	if (end != inode->i_mapping->nrpages) {
 		rcu_read_lock();
 		end = page_cache_next_hole(mapping, idx + 1, ULONG_MAX);
@@ -817,9 +828,9 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx)
 	}
 
 	if (!end)
-		return i_size_read(inode) - (idx << PAGE_CACHE_SHIFT);
+		return i_size_read(inode) - (idx << PAGE_SHIFT);
 	else
-		return (end - idx) << PAGE_CACHE_SHIFT;
+		return (end - idx) << PAGE_SHIFT;
 }
 
 static void
@@ -827,7 +838,7 @@ bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 {
 	u64 wb_size;
 
-	if (!is_aligned_req(pgio, req, PAGE_SIZE)) {
+	if (!is_aligned_req(pgio, req, PAGE_SIZE, true)) {
 		nfs_pageio_reset_write_mds(pgio);
 		return;
 	}
@@ -849,7 +860,7 @@ static size_t
 bl_pg_test_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 		 struct nfs_page *req)
 {
-	if (!is_aligned_req(pgio, req, PAGE_SIZE))
+	if (!is_aligned_req(pgio, req, PAGE_SIZE, true))
 		return 0;
 	return pnfs_generic_pg_test(pgio, prev, req);
 }
@@ -891,22 +902,53 @@ static struct pnfs_layoutdriver_type blocklayout_type = {
 	.sync				= pnfs_generic_sync,
 };
 
+static struct pnfs_layoutdriver_type scsilayout_type = {
+	.id				= LAYOUT_SCSI,
+	.name				= "LAYOUT_SCSI",
+	.owner				= THIS_MODULE,
+	.flags				= PNFS_LAYOUTRET_ON_SETATTR |
+					  PNFS_READ_WHOLE_PAGE,
+	.read_pagelist			= bl_read_pagelist,
+	.write_pagelist			= bl_write_pagelist,
+	.alloc_layout_hdr		= sl_alloc_layout_hdr,
+	.free_layout_hdr		= bl_free_layout_hdr,
+	.alloc_lseg			= bl_alloc_lseg,
+	.free_lseg			= bl_free_lseg,
+	.return_range			= bl_return_range,
+	.prepare_layoutcommit		= bl_prepare_layoutcommit,
+	.cleanup_layoutcommit		= bl_cleanup_layoutcommit,
+	.set_layoutdriver		= bl_set_layoutdriver,
+	.alloc_deviceid_node		= bl_alloc_deviceid_node,
+	.free_deviceid_node		= bl_free_deviceid_node,
+	.pg_read_ops			= &bl_pg_read_ops,
+	.pg_write_ops			= &bl_pg_write_ops,
+	.sync				= pnfs_generic_sync,
+};
+
+
 static int __init nfs4blocklayout_init(void)
 {
 	int ret;
 
 	dprintk("%s: NFSv4 Block Layout Driver Registering...\n", __func__);
 
-	ret = pnfs_register_layoutdriver(&blocklayout_type);
+	ret = bl_init_pipefs();
 	if (ret)
 		goto out;
-	ret = bl_init_pipefs();
+
+	ret = pnfs_register_layoutdriver(&blocklayout_type);
 	if (ret)
-		goto out_unregister;
+		goto out_cleanup_pipe;
+
+	ret = pnfs_register_layoutdriver(&scsilayout_type);
+	if (ret)
+		goto out_unregister_block;
 	return 0;
 
-out_unregister:
+out_unregister_block:
 	pnfs_unregister_layoutdriver(&blocklayout_type);
+out_cleanup_pipe:
+	bl_cleanup_pipefs();
 out:
 	return ret;
 }
@@ -916,8 +958,9 @@ static void __exit nfs4blocklayout_exit(void)
 	dprintk("%s: NFSv4 Block Layout Driver Unregistering...\n",
 	       __func__);
 
-	bl_cleanup_pipefs();
+	pnfs_unregister_layoutdriver(&scsilayout_type);
 	pnfs_unregister_layoutdriver(&blocklayout_type);
+	bl_cleanup_pipefs();
 }
 
 MODULE_ALIAS("nfs-layouttype4-3");
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index c556640dcf3b..18e6fd0b9506 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -40,8 +40,8 @@
 #include "../pnfs.h"
 #include "../netns.h"
 
-#define PAGE_CACHE_SECTORS (PAGE_CACHE_SIZE >> SECTOR_SHIFT)
-#define PAGE_CACHE_SECTOR_SHIFT (PAGE_CACHE_SHIFT - SECTOR_SHIFT)
+#define PAGE_CACHE_SECTORS (PAGE_SIZE >> SECTOR_SHIFT)
+#define PAGE_CACHE_SECTOR_SHIFT (PAGE_SHIFT - SECTOR_SHIFT)
 #define SECTOR_SIZE (1 << SECTOR_SHIFT)
 
 struct pnfs_block_dev;
@@ -55,7 +55,6 @@ struct pnfs_block_dev;
  */
 #define PNFS_BLOCK_UUID_LEN	128
 
-
 struct pnfs_block_volume {
 	enum pnfs_block_volume_type	type;
 	union {
@@ -82,6 +81,13 @@ struct pnfs_block_volume {
 			u32		volumes_count;
 			u32		volumes[PNFS_BLOCK_MAX_DEVICES];
 		} stripe;
+		struct {
+			enum scsi_code_set		code_set;
+			enum scsi_designator_type	designator_type;
+			int				designator_len;
+			u8				designator[256];
+			u64				pr_key;
+		} scsi;
 	};
 };
 
@@ -106,6 +112,9 @@ struct pnfs_block_dev {
 	struct block_device		*bdev;
 	u64				disk_offset;
 
+	u64				pr_key;
+	bool				pr_registered;
+
 	bool (*map)(struct pnfs_block_dev *dev, u64 offset,
 			struct pnfs_block_dev_map *map);
 };
@@ -131,6 +140,7 @@ struct pnfs_block_layout {
 	struct rb_root		bl_ext_rw;
 	struct rb_root		bl_ext_ro;
 	spinlock_t		bl_ext_lock;   /* Protects list manipulation */
+	bool			bl_scsi_layout;
 };
 
 static inline struct pnfs_block_layout *
@@ -182,6 +192,6 @@ void ext_tree_mark_committed(struct nfs4_layoutcommit_args *arg, int status);
 dev_t bl_resolve_deviceid(struct nfs_server *server,
 		struct pnfs_block_volume *b, gfp_t gfp_mask);
 int __init bl_init_pipefs(void);
-void __exit bl_cleanup_pipefs(void);
+void bl_cleanup_pipefs(void);
 
 #endif /* FS_NFS_NFS4BLOCKLAYOUT_H */
diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c
index a861bbdfe577..e5b89675263e 100644
--- a/fs/nfs/blocklayout/dev.c
+++ b/fs/nfs/blocklayout/dev.c
@@ -1,11 +1,12 @@
 /*
- * Copyright (c) 2014 Christoph Hellwig.
+ * Copyright (c) 2014-2016 Christoph Hellwig.
  */
 #include <linux/sunrpc/svc.h>
 #include <linux/blkdev.h>
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
 #include <linux/nfs_xdr.h>
+#include <linux/pr.h>
 
 #include "blocklayout.h"
 
@@ -21,6 +22,17 @@ bl_free_device(struct pnfs_block_dev *dev)
 			bl_free_device(&dev->children[i]);
 		kfree(dev->children);
 	} else {
+		if (dev->pr_registered) {
+			const struct pr_ops *ops =
+				dev->bdev->bd_disk->fops->pr_ops;
+			int error;
+
+			error = ops->pr_register(dev->bdev, dev->pr_key, 0,
+				false);
+			if (error)
+				pr_err("failed to unregister PR key.\n");
+		}
+
 		if (dev->bdev)
 			blkdev_put(dev->bdev, FMODE_READ | FMODE_WRITE);
 	}
@@ -113,6 +125,24 @@ nfs4_block_decode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b)
 		for (i = 0; i < b->stripe.volumes_count; i++)
 			b->stripe.volumes[i] = be32_to_cpup(p++);
 		break;
+	case PNFS_BLOCK_VOLUME_SCSI:
+		p = xdr_inline_decode(xdr, 4 + 4 + 4);
+		if (!p)
+			return -EIO;
+		b->scsi.code_set = be32_to_cpup(p++);
+		b->scsi.designator_type = be32_to_cpup(p++);
+		b->scsi.designator_len = be32_to_cpup(p++);
+		p = xdr_inline_decode(xdr, b->scsi.designator_len);
+		if (!p)
+			return -EIO;
+		if (b->scsi.designator_len > 256)
+			return -EIO;
+		memcpy(&b->scsi.designator, p, b->scsi.designator_len);
+		p = xdr_inline_decode(xdr, 8);
+		if (!p)
+			return -EIO;
+		p = xdr_decode_hyper(p, &b->scsi.pr_key);
+		break;
 	default:
 		dprintk("unknown volume type!\n");
 		return -EIO;
@@ -216,6 +246,116 @@ bl_parse_simple(struct nfs_server *server, struct pnfs_block_dev *d,
 	return 0;
 }
 
+static bool
+bl_validate_designator(struct pnfs_block_volume *v)
+{
+	switch (v->scsi.designator_type) {
+	case PS_DESIGNATOR_EUI64:
+		if (v->scsi.code_set != PS_CODE_SET_BINARY)
+			return false;
+
+		if (v->scsi.designator_len != 8 &&
+		    v->scsi.designator_len != 10 &&
+		    v->scsi.designator_len != 16)
+			return false;
+
+		return true;
+	case PS_DESIGNATOR_NAA:
+		if (v->scsi.code_set != PS_CODE_SET_BINARY)
+			return false;
+
+		if (v->scsi.designator_len != 8 &&
+		    v->scsi.designator_len != 16)
+			return false;
+
+		return true;
+	case PS_DESIGNATOR_T10:
+	case PS_DESIGNATOR_NAME:
+		pr_err("pNFS: unsupported designator "
+			"(code set %d, type %d, len %d.\n",
+			v->scsi.code_set,
+			v->scsi.designator_type,
+			v->scsi.designator_len);
+		return false;
+	default:
+		pr_err("pNFS: invalid designator "
+			"(code set %d, type %d, len %d.\n",
+			v->scsi.code_set,
+			v->scsi.designator_type,
+			v->scsi.designator_len);
+		return false;
+	}
+}
+
+static int
+bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d,
+		struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
+{
+	struct pnfs_block_volume *v = &volumes[idx];
+	const struct pr_ops *ops;
+	const char *devname;
+	int error;
+
+	if (!bl_validate_designator(v))
+		return -EINVAL;
+
+	switch (v->scsi.designator_len) {
+	case 8:
+		devname = kasprintf(GFP_KERNEL, "/dev/disk/by-id/wwn-0x%8phN",
+				v->scsi.designator);
+		break;
+	case 12:
+		devname = kasprintf(GFP_KERNEL, "/dev/disk/by-id/wwn-0x%12phN",
+				v->scsi.designator);
+		break;
+	case 16:
+		devname = kasprintf(GFP_KERNEL, "/dev/disk/by-id/wwn-0x%16phN",
+				v->scsi.designator);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	d->bdev = blkdev_get_by_path(devname, FMODE_READ, NULL);
+	if (IS_ERR(d->bdev)) {
+		pr_warn("pNFS: failed to open device %s (%ld)\n",
+			devname, PTR_ERR(d->bdev));
+		kfree(devname);
+		return PTR_ERR(d->bdev);
+	}
+
+	kfree(devname);
+
+	d->len = i_size_read(d->bdev->bd_inode);
+	d->map = bl_map_simple;
+	d->pr_key = v->scsi.pr_key;
+
+	pr_info("pNFS: using block device %s (reservation key 0x%llx)\n",
+		d->bdev->bd_disk->disk_name, d->pr_key);
+
+	ops = d->bdev->bd_disk->fops->pr_ops;
+	if (!ops) {
+		pr_err("pNFS: block device %s does not support reservations.",
+				d->bdev->bd_disk->disk_name);
+		error = -EINVAL;
+		goto out_blkdev_put;
+	}
+
+	error = ops->pr_register(d->bdev, 0, d->pr_key, true);
+	if (error) {
+		pr_err("pNFS: failed to register key for block device %s.",
+				d->bdev->bd_disk->disk_name);
+		goto out_blkdev_put;
+	}
+
+	d->pr_registered = true;
+	return 0;
+
+out_blkdev_put:
+	blkdev_put(d->bdev, FMODE_READ);
+	return error;
+}
+
 static int
 bl_parse_slice(struct nfs_server *server, struct pnfs_block_dev *d,
 		struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
@@ -303,6 +443,8 @@ bl_parse_deviceid(struct nfs_server *server, struct pnfs_block_dev *d,
 		return bl_parse_concat(server, d, volumes, idx, gfp_mask);
 	case PNFS_BLOCK_VOLUME_STRIPE:
 		return bl_parse_stripe(server, d, volumes, idx, gfp_mask);
+	case PNFS_BLOCK_VOLUME_SCSI:
+		return bl_parse_scsi(server, d, volumes, idx, gfp_mask);
 	default:
 		dprintk("unsupported volume type: %d\n", volumes[idx].type);
 		return -EIO;
diff --git a/fs/nfs/blocklayout/extent_tree.c b/fs/nfs/blocklayout/extent_tree.c
index c59a59c37f3d..720b3ff55fa9 100644
--- a/fs/nfs/blocklayout/extent_tree.c
+++ b/fs/nfs/blocklayout/extent_tree.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2014 Christoph Hellwig.
+ * Copyright (c) 2014-2016 Christoph Hellwig.
  */
 
 #include <linux/vmalloc.h>
@@ -462,10 +462,12 @@ out:
 	return err;
 }
 
-static size_t ext_tree_layoutupdate_size(size_t count)
+static size_t ext_tree_layoutupdate_size(struct pnfs_block_layout *bl, size_t count)
 {
-	return sizeof(__be32) /* number of entries */ +
-		PNFS_BLOCK_EXTENT_SIZE * count;
+	if (bl->bl_scsi_layout)
+		return sizeof(__be32) + PNFS_SCSI_RANGE_SIZE * count;
+	else
+		return sizeof(__be32) + PNFS_BLOCK_EXTENT_SIZE * count;
 }
 
 static void ext_tree_free_commitdata(struct nfs4_layoutcommit_args *arg,
@@ -476,12 +478,30 @@ static void ext_tree_free_commitdata(struct nfs4_layoutcommit_args *arg,
 
 		for (i = 0; i < nr_pages; i++)
 			put_page(arg->layoutupdate_pages[i]);
+		vfree(arg->start_p);
 		kfree(arg->layoutupdate_pages);
 	} else {
 		put_page(arg->layoutupdate_page);
 	}
 }
 
+static __be32 *encode_block_extent(struct pnfs_block_extent *be, __be32 *p)
+{
+	p = xdr_encode_opaque_fixed(p, be->be_device->deviceid.data,
+			NFS4_DEVICEID4_SIZE);
+	p = xdr_encode_hyper(p, be->be_f_offset << SECTOR_SHIFT);
+	p = xdr_encode_hyper(p, be->be_length << SECTOR_SHIFT);
+	p = xdr_encode_hyper(p, 0LL);
+	*p++ = cpu_to_be32(PNFS_BLOCK_READWRITE_DATA);
+	return p;
+}
+
+static __be32 *encode_scsi_range(struct pnfs_block_extent *be, __be32 *p)
+{
+	p = xdr_encode_hyper(p, be->be_f_offset << SECTOR_SHIFT);
+	return xdr_encode_hyper(p, be->be_length << SECTOR_SHIFT);
+}
+
 static int ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
 		size_t buffer_size, size_t *count)
 {
@@ -495,19 +515,16 @@ static int ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
 			continue;
 
 		(*count)++;
-		if (ext_tree_layoutupdate_size(*count) > buffer_size) {
+		if (ext_tree_layoutupdate_size(bl, *count) > buffer_size) {
 			/* keep counting.. */
 			ret = -ENOSPC;
 			continue;
 		}
 
-		p = xdr_encode_opaque_fixed(p, be->be_device->deviceid.data,
-				NFS4_DEVICEID4_SIZE);
-		p = xdr_encode_hyper(p, be->be_f_offset << SECTOR_SHIFT);
-		p = xdr_encode_hyper(p, be->be_length << SECTOR_SHIFT);
-		p = xdr_encode_hyper(p, 0LL);
-		*p++ = cpu_to_be32(PNFS_BLOCK_READWRITE_DATA);
-
+		if (bl->bl_scsi_layout)
+			p = encode_scsi_range(be, p);
+		else
+			p = encode_block_extent(be, p);
 		be->be_tag = EXTENT_COMMITTING;
 	}
 	spin_unlock(&bl->bl_ext_lock);
@@ -536,7 +553,7 @@ retry:
 	if (unlikely(ret)) {
 		ext_tree_free_commitdata(arg, buffer_size);
 
-		buffer_size = ext_tree_layoutupdate_size(count);
+		buffer_size = ext_tree_layoutupdate_size(bl, count);
 		count = 0;
 
 		arg->layoutupdate_pages =
@@ -555,14 +572,19 @@ retry:
 	}
 
 	*start_p = cpu_to_be32(count);
-	arg->layoutupdate_len = ext_tree_layoutupdate_size(count);
+	arg->layoutupdate_len = ext_tree_layoutupdate_size(bl, count);
 
 	if (unlikely(arg->layoutupdate_pages != &arg->layoutupdate_page)) {
 		void *p = start_p, *end = p + arg->layoutupdate_len;
+		struct page *page = NULL;
 		int i = 0;
 
-		for ( ; p < end; p += PAGE_SIZE)
-			arg->layoutupdate_pages[i++] = vmalloc_to_page(p);
+		arg->start_p = start_p;
+		for ( ; p < end; p += PAGE_SIZE) {
+			page = vmalloc_to_page(p);
+			arg->layoutupdate_pages[i++] = page;
+			get_page(page);
+		}
 	}
 
 	dprintk("%s found %zu ranges\n", __func__, count);
diff --git a/fs/nfs/blocklayout/rpc_pipefs.c b/fs/nfs/blocklayout/rpc_pipefs.c
index dbe5839cdeba..9fb067a6f7e0 100644
--- a/fs/nfs/blocklayout/rpc_pipefs.c
+++ b/fs/nfs/blocklayout/rpc_pipefs.c
@@ -281,7 +281,7 @@ out:
 	return ret;
 }
 
-void __exit bl_cleanup_pipefs(void)
+void bl_cleanup_pipefs(void)
 {
 	rpc_pipefs_notifier_unregister(&nfs4blocklayout_block);
 	unregister_pernet_subsys(&nfs4blocklayout_net_ops);
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 75f7c0a7538a..a7f2e6e33305 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -99,17 +99,6 @@ nfs4_callback_up(struct svc_serv *serv)
 }
 
 #if defined(CONFIG_NFS_V4_1)
-static int nfs41_callback_up_net(struct svc_serv *serv, struct net *net)
-{
-	/*
-	 * Create an svc_sock for the back channel service that shares the
-	 * fore channel connection.
-	 * Returns the input port (0) and sets the svc_serv bc_xprt on success
-	 */
-	return svc_create_xprt(serv, "tcp-bc", net, PF_INET, 0,
-			      SVC_SOCK_ANONYMOUS);
-}
-
 /*
  * The callback service for NFSv4.1 callbacks
  */
@@ -184,11 +173,6 @@ static inline void nfs_callback_bc_serv(u32 minorversion, struct rpc_xprt *xprt,
 		xprt->bc_serv = serv;
 }
 #else
-static int nfs41_callback_up_net(struct svc_serv *serv, struct net *net)
-{
-	return 0;
-}
-
 static void nfs_minorversion_callback_svc_setup(struct svc_serv *serv,
 		struct svc_rqst **rqstpp, int (**callback_svc)(void *vrqstp))
 {
@@ -259,7 +243,8 @@ static void nfs_callback_down_net(u32 minorversion, struct svc_serv *serv, struc
 	svc_shutdown_net(serv, net);
 }
 
-static int nfs_callback_up_net(int minorversion, struct svc_serv *serv, struct net *net)
+static int nfs_callback_up_net(int minorversion, struct svc_serv *serv,
+			       struct net *net, struct rpc_xprt *xprt)
 {
 	struct nfs_net *nn = net_generic(net, nfs_net_id);
 	int ret;
@@ -275,20 +260,11 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv, struct n
 		goto err_bind;
 	}
 
-	switch (minorversion) {
-		case 0:
-			ret = nfs4_callback_up_net(serv, net);
-			break;
-		case 1:
-		case 2:
-			ret = nfs41_callback_up_net(serv, net);
-			break;
-		default:
-			printk(KERN_ERR "NFS: unknown callback version: %d\n",
-					minorversion);
-			ret = -EINVAL;
-			break;
-	}
+	ret = -EPROTONOSUPPORT;
+	if (minorversion == 0)
+		ret = nfs4_callback_up_net(serv, net);
+	else if (xprt->ops->bc_up)
+		ret = xprt->ops->bc_up(serv, net);
 
 	if (ret < 0) {
 		printk(KERN_ERR "NFS: callback service start failed\n");
@@ -364,7 +340,7 @@ int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt)
 		goto err_create;
 	}
 
-	ret = nfs_callback_up_net(minorversion, serv, net);
+	ret = nfs_callback_up_net(minorversion, serv, net, xprt);
 	if (ret < 0)
 		goto err_net;
 
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index 84326e9fb47a..5fe1cecbf9f0 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -37,10 +37,11 @@ enum nfs4_callback_opnum {
 	OP_CB_ILLEGAL = 10044,
 };
 
+struct nfs4_slot;
 struct cb_process_state {
 	__be32			drc_status;
 	struct nfs_client	*clp;
-	u32			slotid;
+	struct nfs4_slot	*slot;
 	u32			minorversion;
 	struct net		*net;
 };
@@ -61,7 +62,6 @@ struct cb_compound_hdr_res {
 };
 
 struct cb_getattrargs {
-	struct sockaddr *addr;
 	struct nfs_fh fh;
 	uint32_t bitmap[2];
 };
@@ -76,7 +76,6 @@ struct cb_getattrres {
 };
 
 struct cb_recallargs {
-	struct sockaddr *addr;
 	struct nfs_fh fh;
 	nfs4_stateid stateid;
 	uint32_t truncate;
@@ -119,9 +118,6 @@ extern __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
 				       struct cb_sequenceres *res,
 				       struct cb_process_state *cps);
 
-extern int nfs41_validate_delegation_stateid(struct nfs_delegation *delegation,
-					     const nfs4_stateid *stateid);
-
 #define RCA4_TYPE_MASK_RDATA_DLG	0
 #define RCA4_TYPE_MASK_WDATA_DLG	1
 #define RCA4_TYPE_MASK_DIR_DLG         2
@@ -134,7 +130,6 @@ extern int nfs41_validate_delegation_stateid(struct nfs_delegation *delegation,
 #define RCA4_TYPE_MASK_ALL 0xf31f
 
 struct cb_recallanyargs {
-	struct sockaddr	*craa_addr;
 	uint32_t	craa_objs_to_keep;
 	uint32_t	craa_type_mask;
 };
@@ -144,7 +139,6 @@ extern __be32 nfs4_callback_recallany(struct cb_recallanyargs *args,
 					struct cb_process_state *cps);
 
 struct cb_recallslotargs {
-	struct sockaddr	*crsa_addr;
 	uint32_t	crsa_target_highest_slotid;
 };
 extern __be32 nfs4_callback_recallslot(struct cb_recallslotargs *args,
@@ -152,7 +146,6 @@ extern __be32 nfs4_callback_recallslot(struct cb_recallslotargs *args,
 					 struct cb_process_state *cps);
 
 struct cb_layoutrecallargs {
-	struct sockaddr		*cbl_addr;
 	uint32_t		cbl_recall_type;
 	uint32_t		cbl_layout_type;
 	uint32_t		cbl_layoutchanged;
@@ -196,9 +189,6 @@ extern __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy,
 #if IS_ENABLED(CONFIG_NFS_V4)
 extern int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt);
 extern void nfs_callback_down(int minorversion, struct net *net);
-extern int nfs4_validate_delegation_stateid(struct nfs_delegation *delegation,
-					    const nfs4_stateid *stateid);
-extern int nfs4_set_callback_sessionid(struct nfs_client *clp);
 #endif /* CONFIG_NFS_V4 */
 /*
  * nfs41: Callbacks are expected to not cause substantial latency,
@@ -209,6 +199,5 @@ extern int nfs4_set_callback_sessionid(struct nfs_client *clp);
 #define NFS41_BC_MAX_CALLBACKS 1
 
 extern unsigned int nfs_callback_set_tcpport;
-extern unsigned short nfs_callback_tcpport;
 
 #endif /* __LINUX_FS_NFS_CALLBACK_H */
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index b85cf7a30232..618ced381a14 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -17,9 +17,7 @@
 #include "nfs4session.h"
 #include "nfs4trace.h"
 
-#ifdef NFS_DEBUG
 #define NFSDBG_FACILITY NFSDBG_CALLBACK
-#endif
 
 __be32 nfs4_callback_getattr(struct cb_getattrargs *args,
 			     struct cb_getattrres *res,
@@ -85,8 +83,11 @@ __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy,
 
 	res = htonl(NFS4ERR_BADHANDLE);
 	inode = nfs_delegation_find_inode(cps->clp, &args->fh);
-	if (inode == NULL)
+	if (inode == NULL) {
+		trace_nfs4_cb_recall(cps->clp, &args->fh, NULL,
+				&args->stateid, -ntohl(res));
 		goto out;
+	}
 	/* Set up a helper thread to actually return the delegation */
 	switch (nfs_async_inode_return_delegation(inode, &args->stateid)) {
 	case 0:
@@ -98,7 +99,8 @@ __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy,
 	default:
 		res = htonl(NFS4ERR_RESOURCE);
 	}
-	trace_nfs4_recall_delegation(inode, -ntohl(res));
+	trace_nfs4_cb_recall(cps->clp, &args->fh, inode,
+			&args->stateid, -ntohl(res));
 	iput(inode);
 out:
 	dprintk("%s: exit with status = %d\n", __func__, ntohl(res));
@@ -162,6 +164,22 @@ static struct pnfs_layout_hdr * get_layout_by_fh(struct nfs_client *clp,
 	return lo;
 }
 
+/*
+ * Enforce RFC5661 section 12.5.5.2.1. (Layout Recall and Return Sequencing)
+ */
+static bool pnfs_check_stateid_sequence(struct pnfs_layout_hdr *lo,
+					const nfs4_stateid *new)
+{
+	u32 oldseq, newseq;
+
+	oldseq = be32_to_cpu(lo->plh_stateid.seqid);
+	newseq = be32_to_cpu(new->seqid);
+
+	if (newseq > oldseq + 1)
+		return false;
+	return true;
+}
+
 static u32 initiate_file_draining(struct nfs_client *clp,
 				  struct cb_layoutrecallargs *args)
 {
@@ -171,34 +189,52 @@ static u32 initiate_file_draining(struct nfs_client *clp,
 	LIST_HEAD(free_me_list);
 
 	lo = get_layout_by_fh(clp, &args->cbl_fh, &args->cbl_stateid);
-	if (!lo)
+	if (!lo) {
+		trace_nfs4_cb_layoutrecall_file(clp, &args->cbl_fh, NULL,
+				&args->cbl_stateid, -rv);
 		goto out;
+	}
 
 	ino = lo->plh_inode;
 
 	spin_lock(&ino->i_lock);
+	if (!pnfs_check_stateid_sequence(lo, &args->cbl_stateid)) {
+		rv = NFS4ERR_DELAY;
+		goto unlock;
+	}
 	pnfs_set_layout_stateid(lo, &args->cbl_stateid, true);
 	spin_unlock(&ino->i_lock);
 
 	pnfs_layoutcommit_inode(ino, false);
 
 	spin_lock(&ino->i_lock);
-	if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) ||
-	    pnfs_mark_matching_lsegs_invalid(lo, &free_me_list,
-					&args->cbl_range)) {
+	/*
+	 * Enforce RFC5661 Section 12.5.5.2.1.5 (Bulk Recall and Return)
+	 */
+	if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) {
 		rv = NFS4ERR_DELAY;
 		goto unlock;
 	}
 
+	if (pnfs_mark_matching_lsegs_return(lo, &free_me_list,
+					&args->cbl_range)) {
+		rv = NFS4_OK;
+		goto unlock;
+	}
+
 	if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) {
 		NFS_SERVER(ino)->pnfs_curr_ld->return_range(lo,
 			&args->cbl_range);
 	}
+	pnfs_mark_layout_returned_if_empty(lo);
 unlock:
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&free_me_list);
+	/* Free all lsegs that are attached to commit buckets */
+	nfs_commit_inode(ino, 0);
 	pnfs_put_layout_hdr(lo);
-	trace_nfs4_cb_layoutrecall_inode(clp, &args->cbl_fh, ino, -rv);
+	trace_nfs4_cb_layoutrecall_file(clp, &args->cbl_fh, ino,
+			&args->cbl_stateid, -rv);
 	iput(ino);
 out:
 	return rv;
@@ -318,47 +354,38 @@ out:
  * a single outstanding callback request at a time.
  */
 static __be32
-validate_seqid(struct nfs4_slot_table *tbl, struct cb_sequenceargs * args)
+validate_seqid(const struct nfs4_slot_table *tbl, const struct nfs4_slot *slot,
+		const struct cb_sequenceargs * args)
 {
-	struct nfs4_slot *slot;
-
-	dprintk("%s enter. slotid %u seqid %u\n",
-		__func__, args->csa_slotid, args->csa_sequenceid);
+	dprintk("%s enter. slotid %u seqid %u, slot table seqid: %u\n",
+		__func__, args->csa_slotid, args->csa_sequenceid, slot->seq_nr);
 
-	if (args->csa_slotid >= NFS41_BC_MAX_CALLBACKS)
+	if (args->csa_slotid > tbl->server_highest_slotid)
 		return htonl(NFS4ERR_BADSLOT);
 
-	slot = tbl->slots + args->csa_slotid;
-	dprintk("%s slot table seqid: %u\n", __func__, slot->seq_nr);
-
-	/* Normal */
-	if (likely(args->csa_sequenceid == slot->seq_nr + 1))
-		goto out_ok;
-
 	/* Replay */
 	if (args->csa_sequenceid == slot->seq_nr) {
 		dprintk("%s seqid %u is a replay\n",
 			__func__, args->csa_sequenceid);
+		if (nfs4_test_locked_slot(tbl, slot->slot_nr))
+			return htonl(NFS4ERR_DELAY);
 		/* Signal process_op to set this error on next op */
 		if (args->csa_cachethis == 0)
 			return htonl(NFS4ERR_RETRY_UNCACHED_REP);
 
-		/* The ca_maxresponsesize_cached is 0 with no DRC */
-		else if (args->csa_cachethis == 1)
-			return htonl(NFS4ERR_REP_TOO_BIG_TO_CACHE);
+		/* Liar! We never allowed you to set csa_cachethis != 0 */
+		return htonl(NFS4ERR_SEQ_FALSE_RETRY);
 	}
 
 	/* Wraparound */
-	if (args->csa_sequenceid == 1 && (slot->seq_nr + 1) == 0) {
-		slot->seq_nr = 1;
-		goto out_ok;
-	}
+	if (unlikely(slot->seq_nr == 0xFFFFFFFFU)) {
+		if (args->csa_sequenceid == 1)
+			return htonl(NFS4_OK);
+	} else if (likely(args->csa_sequenceid == slot->seq_nr + 1))
+		return htonl(NFS4_OK);
 
 	/* Misordered request */
 	return htonl(NFS4ERR_SEQ_MISORDERED);
-out_ok:
-	tbl->highest_used_slotid = args->csa_slotid;
-	return htonl(NFS4_OK);
 }
 
 /*
@@ -437,6 +464,12 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
 	tbl = &clp->cl_session->bc_slot_table;
 	slot = tbl->slots + args->csa_slotid;
 
+	/* Set up res before grabbing the spinlock */
+	memcpy(&res->csr_sessionid, &args->csa_sessionid,
+	       sizeof(res->csr_sessionid));
+	res->csr_sequenceid = args->csa_sequenceid;
+	res->csr_slotid = args->csa_slotid;
+
 	spin_lock(&tbl->slot_tbl_lock);
 	/* state manager is resetting the session */
 	if (test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state)) {
@@ -449,18 +482,26 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
 		goto out_unlock;
 	}
 
-	memcpy(&res->csr_sessionid, &args->csa_sessionid,
-	       sizeof(res->csr_sessionid));
-	res->csr_sequenceid = args->csa_sequenceid;
-	res->csr_slotid = args->csa_slotid;
-	res->csr_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
-	res->csr_target_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
+	status = htonl(NFS4ERR_BADSLOT);
+	slot = nfs4_lookup_slot(tbl, args->csa_slotid);
+	if (IS_ERR(slot))
+		goto out_unlock;
+
+	res->csr_highestslotid = tbl->server_highest_slotid;
+	res->csr_target_highestslotid = tbl->target_highest_slotid;
 
-	status = validate_seqid(tbl, args);
+	status = validate_seqid(tbl, slot, args);
 	if (status)
 		goto out_unlock;
+	if (!nfs4_try_to_lock_slot(tbl, slot)) {
+		status = htonl(NFS4ERR_DELAY);
+		goto out_unlock;
+	}
+	cps->slot = slot;
 
-	cps->slotid = args->csa_slotid;
+	/* The ca_maxresponsesize_cached is 0 with no DRC */
+	if (args->csa_cachethis != 0)
+		return htonl(NFS4ERR_REP_TOO_BIG_TO_CACHE);
 
 	/*
 	 * Check for pending referring calls.  If a match is found, a
@@ -477,7 +518,7 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
 	 * If CB_SEQUENCE returns an error, then the state of the slot
 	 * (sequence ID, cached reply) MUST NOT change.
 	 */
-	slot->seq_nr++;
+	slot->seq_nr = args->csa_sequenceid;
 out_unlock:
 	spin_unlock(&tbl->slot_tbl_lock);
 
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 6b1697a01dde..976c90608e56 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -18,19 +18,21 @@
 #include "internal.h"
 #include "nfs4session.h"
 
-#define CB_OP_TAGLEN_MAXSZ	(512)
-#define CB_OP_HDR_RES_MAXSZ	(2 + CB_OP_TAGLEN_MAXSZ)
-#define CB_OP_GETATTR_BITMAP_MAXSZ	(4)
-#define CB_OP_GETATTR_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ + \
-				CB_OP_GETATTR_BITMAP_MAXSZ + \
-				2 + 2 + 3 + 3)
-#define CB_OP_RECALL_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ)
+#define CB_OP_TAGLEN_MAXSZ		(512)
+#define CB_OP_HDR_RES_MAXSZ		(2 * 4) // opcode, status
+#define CB_OP_GETATTR_BITMAP_MAXSZ	(4 * 4) // bitmap length, 3 bitmaps
+#define CB_OP_GETATTR_RES_MAXSZ		(CB_OP_HDR_RES_MAXSZ + \
+					 CB_OP_GETATTR_BITMAP_MAXSZ + \
+					 /* change, size, ctime, mtime */\
+					 (2 + 2 + 3 + 3) * 4)
+#define CB_OP_RECALL_RES_MAXSZ		(CB_OP_HDR_RES_MAXSZ)
 
 #if defined(CONFIG_NFS_V4_1)
 #define CB_OP_LAYOUTRECALL_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ)
 #define CB_OP_DEVICENOTIFY_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ)
 #define CB_OP_SEQUENCE_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ + \
-					4 + 1 + 3)
+					 NFS4_MAX_SESSIONID_LEN + \
+					 (1 + 3) * 4) // seqid, 3 slotids
 #define CB_OP_RECALLANY_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ)
 #define CB_OP_RECALLSLOT_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ)
 #endif /* CONFIG_NFS_V4_1 */
@@ -157,7 +159,7 @@ static __be32 decode_compound_hdr_arg(struct xdr_stream *xdr, struct cb_compound
 	if (unlikely(status != 0))
 		return status;
 	/* We do not like overly long tags! */
-	if (hdr->taglen > CB_OP_TAGLEN_MAXSZ - 12) {
+	if (hdr->taglen > CB_OP_TAGLEN_MAXSZ) {
 		printk("NFS: NFSv4 CALLBACK %s: client sent tag of length %u\n",
 				__func__, hdr->taglen);
 		return htonl(NFS4ERR_RESOURCE);
@@ -198,7 +200,6 @@ static __be32 decode_getattr_args(struct svc_rqst *rqstp, struct xdr_stream *xdr
 	status = decode_fh(xdr, &args->fh);
 	if (unlikely(status != 0))
 		goto out;
-	args->addr = svc_addr(rqstp);
 	status = decode_bitmap(xdr, args->bitmap);
 out:
 	dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
@@ -210,7 +211,6 @@ static __be32 decode_recall_args(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 	__be32 *p;
 	__be32 status;
 
-	args->addr = svc_addr(rqstp);
 	status = decode_stateid(xdr, &args->stateid);
 	if (unlikely(status != 0))
 		goto out;
@@ -236,7 +236,6 @@ static __be32 decode_layoutrecall_args(struct svc_rqst *rqstp,
 	__be32 status = 0;
 	uint32_t iomode;
 
-	args->cbl_addr = svc_addr(rqstp);
 	p = read_buf(xdr, 4 * sizeof(uint32_t));
 	if (unlikely(p == NULL)) {
 		status = htonl(NFS4ERR_BADXDR);
@@ -383,13 +382,12 @@ static __be32 decode_sessionid(struct xdr_stream *xdr,
 				 struct nfs4_sessionid *sid)
 {
 	__be32 *p;
-	int len = NFS4_MAX_SESSIONID_LEN;
 
-	p = read_buf(xdr, len);
+	p = read_buf(xdr, NFS4_MAX_SESSIONID_LEN);
 	if (unlikely(p == NULL))
 		return htonl(NFS4ERR_RESOURCE);
 
-	memcpy(sid->data, p, len);
+	memcpy(sid->data, p, NFS4_MAX_SESSIONID_LEN);
 	return 0;
 }
 
@@ -500,7 +498,6 @@ static __be32 decode_recallany_args(struct svc_rqst *rqstp,
 	uint32_t bitmap[2];
 	__be32 *p, status;
 
-	args->craa_addr = svc_addr(rqstp);
 	p = read_buf(xdr, 4);
 	if (unlikely(p == NULL))
 		return htonl(NFS4ERR_BADXDR);
@@ -519,7 +516,6 @@ static __be32 decode_recallslot_args(struct svc_rqst *rqstp,
 {
 	__be32 *p;
 
-	args->crsa_addr = svc_addr(rqstp);
 	p = read_buf(xdr, 4);
 	if (unlikely(p == NULL))
 		return htonl(NFS4ERR_BADXDR);
@@ -684,13 +680,12 @@ static __be32 encode_sessionid(struct xdr_stream *xdr,
 				 const struct nfs4_sessionid *sid)
 {
 	__be32 *p;
-	int len = NFS4_MAX_SESSIONID_LEN;
 
-	p = xdr_reserve_space(xdr, len);
+	p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN);
 	if (unlikely(p == NULL))
 		return htonl(NFS4ERR_RESOURCE);
 
-	memcpy(p, sid, len);
+	memcpy(p, sid, NFS4_MAX_SESSIONID_LEN);
 	return 0;
 }
 
@@ -704,7 +699,9 @@ static __be32 encode_cb_sequence_res(struct svc_rqst *rqstp,
 	if (unlikely(status != 0))
 		goto out;
 
-	encode_sessionid(xdr, &res->csr_sessionid);
+	status = encode_sessionid(xdr, &res->csr_sessionid);
+	if (status)
+		goto out;
 
 	p = xdr_reserve_space(xdr, 4 * sizeof(uint32_t));
 	if (unlikely(p == NULL))
@@ -755,7 +752,8 @@ preprocess_nfs41_op(int nop, unsigned int op_nr, struct callback_op **op)
 	return htonl(NFS_OK);
 }
 
-static void nfs4_callback_free_slot(struct nfs4_session *session)
+static void nfs4_callback_free_slot(struct nfs4_session *session,
+		struct nfs4_slot *slot)
 {
 	struct nfs4_slot_table *tbl = &session->bc_slot_table;
 
@@ -764,15 +762,17 @@ static void nfs4_callback_free_slot(struct nfs4_session *session)
 	 * Let the state manager know callback processing done.
 	 * A single slot, so highest used slotid is either 0 or -1
 	 */
-	tbl->highest_used_slotid = NFS4_NO_SLOT;
+	nfs4_free_slot(tbl, slot);
 	nfs4_slot_tbl_drain_complete(tbl);
 	spin_unlock(&tbl->slot_tbl_lock);
 }
 
 static void nfs4_cb_free_slot(struct cb_process_state *cps)
 {
-	if (cps->slotid != NFS4_NO_SLOT)
-		nfs4_callback_free_slot(cps->clp->cl_session);
+	if (cps->slot) {
+		nfs4_callback_free_slot(cps->clp->cl_session, cps->slot);
+		cps->slot = NULL;
+	}
 }
 
 #else /* CONFIG_NFS_V4_1 */
@@ -896,7 +896,6 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 	struct cb_process_state cps = {
 		.drc_status = 0,
 		.clp = NULL,
-		.slotid = NFS4_NO_SLOT,
 		.net = SVC_NET(rqstp),
 	};
 	unsigned int nops = 0;
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 57c5a02f6213..0c96528db94a 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -736,7 +736,7 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 		server->rsize = max_rpc_payload;
 	if (server->rsize > NFS_MAX_FILE_IO_SIZE)
 		server->rsize = NFS_MAX_FILE_IO_SIZE;
-	server->rpages = (server->rsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	server->rpages = (server->rsize + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
 	server->backing_dev_info.name = "nfs";
 	server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD;
@@ -745,13 +745,13 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 		server->wsize = max_rpc_payload;
 	if (server->wsize > NFS_MAX_FILE_IO_SIZE)
 		server->wsize = NFS_MAX_FILE_IO_SIZE;
-	server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	server->wpages = (server->wsize + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
 	server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL);
 
 	server->dtsize = nfs_block_size(fsinfo->dtpref, NULL);
-	if (server->dtsize > PAGE_CACHE_SIZE * NFS_MAX_READDIR_PAGES)
-		server->dtsize = PAGE_CACHE_SIZE * NFS_MAX_READDIR_PAGES;
+	if (server->dtsize > PAGE_SIZE * NFS_MAX_READDIR_PAGES)
+		server->dtsize = PAGE_SIZE * NFS_MAX_READDIR_PAGES;
 	if (server->dtsize > server->rsize)
 		server->dtsize = server->rsize;
 
@@ -764,6 +764,7 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 
 	server->time_delta = fsinfo->time_delta;
 
+	server->clone_blksize = fsinfo->clone_blksize;
 	/* We're airborne Set socket buffersize */
 	rpc_setbufsize(server->client, server->wsize + 100, server->rsize + 100);
 }
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index be806ead7f4d..5166adcfc0fb 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -721,14 +721,12 @@ int nfs_async_inode_return_delegation(struct inode *inode,
 	struct nfs_client *clp = server->nfs_client;
 	struct nfs_delegation *delegation;
 
-	filemap_flush(inode->i_mapping);
-
 	rcu_read_lock();
 	delegation = rcu_dereference(NFS_I(inode)->delegation);
 	if (delegation == NULL)
 		goto out_enoent;
-
-	if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid))
+	if (stateid != NULL &&
+	    !clp->cl_mvops->match_stateid(&delegation->stateid, stateid))
 		goto out_enoent;
 	nfs_mark_return_delegation(server, delegation);
 	rcu_read_unlock();
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 3d8e4ffa0a33..33eb81738d03 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -377,7 +377,7 @@ int nfs_readdir_xdr_filler(struct page **pages, nfs_readdir_descriptor_t *desc,
  again:
 	timestamp = jiffies;
 	gencount = nfs_inc_attr_generation_counter();
-	error = NFS_PROTO(inode)->readdir(file->f_path.dentry, cred, entry->cookie, pages,
+	error = NFS_PROTO(inode)->readdir(file_dentry(file), cred, entry->cookie, pages,
 					  NFS_SERVER(inode)->dtsize, desc->plus);
 	if (error < 0) {
 		/* We requested READDIRPLUS, but the server doesn't grok it */
@@ -560,7 +560,7 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
 		count++;
 
 		if (desc->plus != 0)
-			nfs_prime_dcache(desc->file->f_path.dentry, entry);
+			nfs_prime_dcache(file_dentry(desc->file), entry);
 
 		status = nfs_readdir_add_to_array(entry, page);
 		if (status != 0)
@@ -707,7 +707,7 @@ void cache_page_release(nfs_readdir_descriptor_t *desc)
 {
 	if (!desc->page->mapping)
 		nfs_readdir_clear_array(desc->page);
-	page_cache_release(desc->page);
+	put_page(desc->page);
 	desc->page = NULL;
 }
 
@@ -864,7 +864,7 @@ static bool nfs_dir_mapping_need_revalidate(struct inode *dir)
  */
 static int nfs_readdir(struct file *file, struct dir_context *ctx)
 {
-	struct dentry	*dentry = file->f_path.dentry;
+	struct dentry	*dentry = file_dentry(file);
 	struct inode	*inode = d_inode(dentry);
 	nfs_readdir_descriptor_t my_desc,
 			*desc = &my_desc;
@@ -940,7 +940,7 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence)
 	dfprintk(FILE, "NFS: llseek dir(%pD2, %lld, %d)\n",
 			filp, offset, whence);
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	switch (whence) {
 		case 1:
 			offset += filp->f_pos;
@@ -957,7 +957,7 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence)
 		dir_ctx->duped = 0;
 	}
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return offset;
 }
 
@@ -972,9 +972,9 @@ static int nfs_fsync_dir(struct file *filp, loff_t start, loff_t end,
 
 	dfprintk(FILE, "NFS: fsync dir(%pD2) datasync %d\n", filp, datasync);
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	nfs_inc_stats(inode, NFSIOS_VFSFSYNC);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return 0;
 }
 
@@ -1360,19 +1360,15 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in
 	dfprintk(VFS, "NFS: lookup(%pd2)\n", dentry);
 	nfs_inc_stats(dir, NFSIOS_VFSLOOKUP);
 
-	res = ERR_PTR(-ENAMETOOLONG);
-	if (dentry->d_name.len > NFS_SERVER(dir)->namelen)
-		goto out;
+	if (unlikely(dentry->d_name.len > NFS_SERVER(dir)->namelen))
+		return ERR_PTR(-ENAMETOOLONG);
 
 	/*
 	 * If we're doing an exclusive create, optimize away the lookup
 	 * but don't hash the dentry.
 	 */
-	if (nfs_is_exclusive_create(dir, flags)) {
-		d_instantiate(dentry, NULL);
-		res = NULL;
-		goto out;
-	}
+	if (nfs_is_exclusive_create(dir, flags))
+		return NULL;
 
 	res = ERR_PTR(-ENOMEM);
 	fhandle = nfs_alloc_fhandle();
@@ -1714,9 +1710,6 @@ nfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev)
 	dfprintk(VFS, "NFS: mknod(%s/%lu), %pd\n",
 			dir->i_sb->s_id, dir->i_ino, dentry);
 
-	if (!new_valid_dev(rdev))
-		return -EINVAL;
-
 	attr.ia_mode = mode;
 	attr.ia_valid = ATTR_MODE;
 
@@ -1897,15 +1890,14 @@ int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
 	attr.ia_mode = S_IFLNK | S_IRWXUGO;
 	attr.ia_valid = ATTR_MODE;
 
-	page = alloc_page(GFP_HIGHUSER);
+	page = alloc_page(GFP_USER);
 	if (!page)
 		return -ENOMEM;
 
-	kaddr = kmap_atomic(page);
+	kaddr = page_address(page);
 	memcpy(kaddr, symname, pathlen);
 	if (pathlen < PAGE_SIZE)
 		memset(kaddr + pathlen, 0, PAGE_SIZE - pathlen);
-	kunmap_atomic(kaddr);
 
 	trace_nfs_symlink_enter(dir, dentry);
 	error = NFS_PROTO(dir)->symlink(dir, dentry, page, pathlen, &attr);
@@ -1931,7 +1923,7 @@ int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
 		 * add_to_page_cache_lru() grabs an extra page refcount.
 		 * Drop it here to avoid leaking this page later.
 		 */
-		page_cache_release(page);
+		put_page(page);
 	} else
 		__free_page(page);
 
@@ -2435,6 +2427,20 @@ int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags)
 }
 EXPORT_SYMBOL_GPL(nfs_may_open);
 
+static int nfs_execute_ok(struct inode *inode, int mask)
+{
+	struct nfs_server *server = NFS_SERVER(inode);
+	int ret;
+
+	if (mask & MAY_NOT_BLOCK)
+		ret = nfs_revalidate_inode_rcu(server, inode);
+	else
+		ret = nfs_revalidate_inode(server, inode);
+	if (ret == 0 && !execute_ok(inode))
+		ret = -EACCES;
+	return ret;
+}
+
 int nfs_permission(struct inode *inode, int mask)
 {
 	struct rpc_cred *cred;
@@ -2452,6 +2458,9 @@ int nfs_permission(struct inode *inode, int mask)
 		case S_IFLNK:
 			goto out;
 		case S_IFREG:
+			if ((mask & MAY_OPEN) &&
+			   nfs_server_capable(inode, NFS_CAP_ATOMIC_OPEN))
+				return 0;
 			break;
 		case S_IFDIR:
 			/*
@@ -2484,8 +2493,8 @@ force_lookup:
 			res = PTR_ERR(cred);
 	}
 out:
-	if (!res && (mask & MAY_EXEC) && !execute_ok(inode))
-		res = -EACCES;
+	if (!res && (mask & MAY_EXEC))
+		res = nfs_execute_ok(inode, mask);
 
 	dfprintk(VFS, "NFS: permission(%s/%lu), mask=0x%x, res=%d\n",
 		inode->i_sb->s_id, inode->i_ino, mask, res);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 4b1d08f56aba..c93826e4a8c6 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -117,12 +117,6 @@ static inline int put_dreq(struct nfs_direct_req *dreq)
 	return atomic_dec_and_test(&dreq->io_count);
 }
 
-void nfs_direct_set_resched_writes(struct nfs_direct_req *dreq)
-{
-	dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
-}
-EXPORT_SYMBOL_GPL(nfs_direct_set_resched_writes);
-
 static void
 nfs_direct_good_bytes(struct nfs_direct_req *dreq, struct nfs_pgio_header *hdr)
 {
@@ -275,7 +269,7 @@ static void nfs_direct_release_pages(struct page **pages, unsigned int npages)
 {
 	unsigned int i;
 	for (i = 0; i < npages; i++)
-		page_cache_release(pages[i]);
+		put_page(pages[i]);
 }
 
 void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo,
@@ -586,7 +580,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
 	if (!count)
 		goto out;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	result = nfs_sync_mapping(mapping);
 	if (result)
 		goto out_unlock;
@@ -614,7 +608,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
 	NFS_I(inode)->read_io += count;
 	result = nfs_direct_read_schedule_iovec(dreq, iter, pos);
 
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	if (!result) {
 		result = nfs_direct_wait(dreq);
@@ -628,7 +622,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
 out_release:
 	nfs_direct_req_release(dreq);
 out_unlock:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 out:
 	return result;
 }
@@ -670,6 +664,10 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 
 	req = nfs_list_entry(reqs.next);
 	nfs_direct_setup_mirroring(dreq, &desc, req);
+	if (desc.pg_error < 0) {
+		list_splice_init(&reqs, &failed);
+		goto out_failed;
+	}
 
 	list_for_each_entry_safe(req, tmp, &reqs, wb_list) {
 		if (!nfs_pageio_add_request(&desc, req)) {
@@ -677,13 +675,17 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 			nfs_list_add_request(req, &failed);
 			spin_lock(cinfo.lock);
 			dreq->flags = 0;
-			dreq->error = -EIO;
+			if (desc.pg_error < 0)
+				dreq->error = desc.pg_error;
+			else
+				dreq->error = -EIO;
 			spin_unlock(cinfo.lock);
 		}
 		nfs_release_request(req);
 	}
 	nfs_pageio_complete(&desc);
 
+out_failed:
 	while (!list_empty(&failed)) {
 		req = nfs_list_entry(failed.next);
 		nfs_list_remove_request(req);
@@ -727,14 +729,20 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data)
 		nfs_direct_write_complete(dreq, data->inode);
 }
 
-static void nfs_direct_error_cleanup(struct nfs_inode *nfsi)
+static void nfs_direct_resched_write(struct nfs_commit_info *cinfo,
+		struct nfs_page *req)
 {
-	/* There is no lock to clear */
+	struct nfs_direct_req *dreq = cinfo->dreq;
+
+	spin_lock(&dreq->lock);
+	dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
+	spin_unlock(&dreq->lock);
+	nfs_mark_request_commit(req, NULL, cinfo, 0);
 }
 
 static const struct nfs_commit_completion_ops nfs_direct_commit_completion_ops = {
 	.completion = nfs_direct_commit_complete,
-	.error_cleanup = nfs_direct_error_cleanup,
+	.resched_write = nfs_direct_resched_write,
 };
 
 static void nfs_direct_commit_schedule(struct nfs_direct_req *dreq)
@@ -839,10 +847,25 @@ static void nfs_write_sync_pgio_error(struct list_head *head)
 	}
 }
 
+static void nfs_direct_write_reschedule_io(struct nfs_pgio_header *hdr)
+{
+	struct nfs_direct_req *dreq = hdr->dreq;
+
+	spin_lock(&dreq->lock);
+	if (dreq->error == 0) {
+		dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
+		/* fake unstable write to let common nfs resend pages */
+		hdr->verf.committed = NFS_UNSTABLE;
+		hdr->good_bytes = hdr->args.count;
+	}
+	spin_unlock(&dreq->lock);
+}
+
 static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = {
 	.error_cleanup = nfs_write_sync_pgio_error,
 	.init_hdr = nfs_direct_pgio_init,
 	.completion = nfs_direct_write_completion,
+	.reschedule_io = nfs_direct_write_reschedule_io,
 };
 
 
@@ -900,6 +923,11 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 			}
 
 			nfs_direct_setup_mirroring(dreq, &desc, req);
+			if (desc.pg_error < 0) {
+				nfs_free_request(req);
+				result = desc.pg_error;
+				break;
+			}
 
 			nfs_lock_request(req);
 			req->wb_index = pos >> PAGE_SHIFT;
@@ -975,9 +1003,9 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
 		      iov_iter_count(iter));
 
 	pos = iocb->ki_pos;
-	end = (pos + iov_iter_count(iter) - 1) >> PAGE_CACHE_SHIFT;
+	end = (pos + iov_iter_count(iter) - 1) >> PAGE_SHIFT;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	result = nfs_sync_mapping(mapping);
 	if (result)
@@ -985,7 +1013,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
 
 	if (mapping->nrpages) {
 		result = invalidate_inode_pages2_range(mapping,
-					pos >> PAGE_CACHE_SHIFT, end);
+					pos >> PAGE_SHIFT, end);
 		if (result)
 			goto out_unlock;
 	}
@@ -1014,10 +1042,10 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
 
 	if (mapping->nrpages) {
 		invalidate_inode_pages2_range(mapping,
-					      pos >> PAGE_CACHE_SHIFT, end);
+					      pos >> PAGE_SHIFT, end);
 	}
 
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	if (!result) {
 		result = nfs_direct_wait(dreq);
@@ -1038,7 +1066,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
 out_release:
 	nfs_direct_req_release(dreq);
 out_unlock:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return result;
 }
 
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 37f639d50af5..be01095b97ae 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -233,7 +233,7 @@ EXPORT_SYMBOL_GPL(nfs_file_mmap);
  * nfs_file_write() that a write error occurred, and hence cause it to
  * fall back to doing a synchronous write.
  */
-int
+static int
 nfs_file_fsync_commit(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
@@ -263,9 +263,8 @@ nfs_file_fsync_commit(struct file *file, loff_t start, loff_t end, int datasync)
 out:
 	return ret;
 }
-EXPORT_SYMBOL_GPL(nfs_file_fsync_commit);
 
-static int
+int
 nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	int ret;
@@ -273,14 +272,16 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 
 	trace_nfs_fsync_enter(inode);
 
-	nfs_inode_dio_wait(inode);
+	inode_dio_wait(inode);
 	do {
 		ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
 		if (ret != 0)
 			break;
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		ret = nfs_file_fsync_commit(file, start, end, datasync);
-		mutex_unlock(&inode->i_mutex);
+		if (!ret)
+			ret = pnfs_sync_inode(inode, !!datasync);
+		inode_unlock(inode);
 		/*
 		 * If nfs_file_fsync_commit detected a server reboot, then
 		 * resend all dirty pages that might have been covered by
@@ -293,6 +294,7 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	trace_nfs_fsync_exit(inode, ret);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(nfs_file_fsync);
 
 /*
  * Decide whether a read/modify/write cycle may be more efficient
@@ -318,7 +320,7 @@ static int nfs_want_read_modify_write(struct file *file, struct page *page,
 			loff_t pos, unsigned len)
 {
 	unsigned int pglen = nfs_page_length(page);
-	unsigned int offset = pos & (PAGE_CACHE_SIZE - 1);
+	unsigned int offset = pos & (PAGE_SIZE - 1);
 	unsigned int end = offset + len;
 
 	if (pnfs_ld_read_whole_page(file->f_mapping->host)) {
@@ -349,7 +351,7 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping,
 			struct page **pagep, void **fsdata)
 {
 	int ret;
-	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+	pgoff_t index = pos >> PAGE_SHIFT;
 	struct page *page;
 	int once_thru = 0;
 
@@ -368,7 +370,7 @@ start:
 	/*
 	 * Wait for O_DIRECT to complete
 	 */
-	nfs_inode_dio_wait(mapping->host);
+	inode_dio_wait(mapping->host);
 
 	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
@@ -378,12 +380,12 @@ start:
 	ret = nfs_flush_incompatible(file, page);
 	if (ret) {
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 	} else if (!once_thru &&
 		   nfs_want_read_modify_write(file, page, pos, len)) {
 		once_thru = 1;
 		ret = nfs_readpage(file, page);
-		page_cache_release(page);
+		put_page(page);
 		if (!ret)
 			goto start;
 	}
@@ -394,7 +396,7 @@ static int nfs_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
 			struct page *page, void *fsdata)
 {
-	unsigned offset = pos & (PAGE_CACHE_SIZE - 1);
+	unsigned offset = pos & (PAGE_SIZE - 1);
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
 	int status;
 
@@ -411,20 +413,20 @@ static int nfs_write_end(struct file *file, struct address_space *mapping,
 
 		if (pglen == 0) {
 			zero_user_segments(page, 0, offset,
-					end, PAGE_CACHE_SIZE);
+					end, PAGE_SIZE);
 			SetPageUptodate(page);
 		} else if (end >= pglen) {
-			zero_user_segment(page, end, PAGE_CACHE_SIZE);
+			zero_user_segment(page, end, PAGE_SIZE);
 			if (offset == 0)
 				SetPageUptodate(page);
 		} else
-			zero_user_segment(page, pglen, PAGE_CACHE_SIZE);
+			zero_user_segment(page, pglen, PAGE_SIZE);
 	}
 
 	status = nfs_updatepage(file, page, offset, copied);
 
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 
 	if (status < 0)
 		return status;
@@ -452,7 +454,7 @@ static void nfs_invalidate_page(struct page *page, unsigned int offset,
 	dfprintk(PAGECACHE, "NFS: invalidate_page(%p, %u, %u)\n",
 		 page, offset, length);
 
-	if (offset != 0 || length < PAGE_CACHE_SIZE)
+	if (offset != 0 || length < PAGE_SIZE)
 		return;
 	/* Cancel any unstarted writes on this page */
 	nfs_wb_page_cancel(page_file_mapping(page)->host, page);
@@ -473,8 +475,8 @@ static int nfs_release_page(struct page *page, gfp_t gfp)
 	dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page);
 
 	/* Always try to initiate a 'commit' if relevant, but only
-	 * wait for it if __GFP_WAIT is set.  Even then, only wait 1
-	 * second and only if the 'bdi' is not congested.
+	 * wait for it if the caller allows blocking.  Even then,
+	 * only wait 1 second and only if the 'bdi' is not congested.
 	 * Waiting indefinitely can cause deadlocks when the NFS
 	 * server is on this machine, when a new TCP connection is
 	 * needed and in other rare cases.  There is no particular
@@ -484,7 +486,7 @@ static int nfs_release_page(struct page *page, gfp_t gfp)
 	if (mapping) {
 		struct nfs_server *nfss = NFS_SERVER(mapping->host);
 		nfs_commit_inode(mapping->host, 0);
-		if ((gfp & __GFP_WAIT) &&
+		if (gfpflags_allow_blocking(gfp) &&
 		    !bdi_write_congested(&nfss->backing_dev_info)) {
 			wait_on_page_bit_killable_timeout(page, PG_private,
 							  HZ);
@@ -514,7 +516,7 @@ static void nfs_check_dirty_writeback(struct page *page,
 	 * so it will not block due to pages that will shortly be freeable.
 	 */
 	nfsi = NFS_I(mapping->host);
-	if (test_bit(NFS_INO_COMMIT, &nfsi->flags)) {
+	if (atomic_read(&nfsi->commit_info.rpcs_out)) {
 		*writeback = true;
 		return;
 	}
@@ -545,7 +547,7 @@ static int nfs_launder_page(struct page *page)
 		inode->i_ino, (long long)page_offset(page));
 
 	nfs_fscache_wait_on_page_write(nfsi, page);
-	return nfs_wb_page(inode, page);
+	return nfs_wb_launder_page(inode, page);
 }
 
 static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,
@@ -756,7 +758,7 @@ do_unlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 
 	l_ctx = nfs_get_lock_context(nfs_file_open_context(filp));
 	if (!IS_ERR(l_ctx)) {
-		status = nfs_iocounter_wait(&l_ctx->io_count);
+		status = nfs_iocounter_wait(l_ctx);
 		nfs_put_lock_context(l_ctx);
 		if (status < 0)
 			return status;
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 02ec07973bc4..3384dc8e6683 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -202,6 +202,7 @@ static int filelayout_async_handle_error(struct rpc_task *task,
 			task->tk_status);
 		nfs4_mark_deviceid_unavailable(devid);
 		pnfs_error_mark_layout_for_return(inode, lseg);
+		pnfs_set_lo_fail(lseg);
 		rpc_wake_up(&tbl->slot_tbl_waitq);
 		/* fall through */
 	default:
@@ -883,13 +884,19 @@ static void
 filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 			struct nfs_page *req)
 {
-	if (!pgio->pg_lseg)
+	if (!pgio->pg_lseg) {
 		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 					   req->wb_context,
 					   0,
 					   NFS4_MAX_UINT64,
 					   IOMODE_READ,
 					   GFP_KERNEL);
+		if (IS_ERR(pgio->pg_lseg)) {
+			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
+			pgio->pg_lseg = NULL;
+			return;
+		}
+	}
 	/* If no lseg, fall back to read through mds */
 	if (pgio->pg_lseg == NULL)
 		nfs_pageio_reset_read_mds(pgio);
@@ -902,13 +909,20 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 	struct nfs_commit_info cinfo;
 	int status;
 
-	if (!pgio->pg_lseg)
+	if (!pgio->pg_lseg) {
 		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 					   req->wb_context,
 					   0,
 					   NFS4_MAX_UINT64,
 					   IOMODE_RW,
 					   GFP_NOFS);
+		if (IS_ERR(pgio->pg_lseg)) {
+			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
+			pgio->pg_lseg = NULL;
+			return;
+		}
+	}
+
 	/* If no lseg, fall back to write through mds */
 	if (pgio->pg_lseg == NULL)
 		goto out_mds;
@@ -957,7 +971,7 @@ filelayout_mark_request_commit(struct nfs_page *req,
 	u32 i, j;
 
 	if (fl->commit_through_mds) {
-		nfs_request_add_commit_list(req, &cinfo->mds->list, cinfo);
+		nfs_request_add_commit_list(req, cinfo);
 	} else {
 		/* Note that we are calling nfs4_fl_calc_j_index on each page
 		 * that ends up being committed to a data server.  An attractive
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index fbc5a56de875..0cb1abd535e3 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -145,7 +145,7 @@ static bool ff_mirror_match_fh(const struct nfs4_ff_layout_mirror *m1,
 		return false;
 	for (i = 0; i < m1->fh_versions_cnt; i++) {
 		bool found_fh = false;
-		for (j = 0; j < m2->fh_versions_cnt; i++) {
+		for (j = 0; j < m2->fh_versions_cnt; j++) {
 			if (nfs_compare_fh(&m1->fh_versions[i],
 					&m2->fh_versions[j]) == 0) {
 				found_fh = true;
@@ -339,6 +339,19 @@ static void ff_layout_sort_mirrors(struct nfs4_ff_layout_segment *fls)
 	}
 }
 
+static void ff_layout_mark_devices_valid(struct nfs4_ff_layout_segment *fls)
+{
+	struct nfs4_deviceid_node *node;
+	int i;
+
+	if (!(fls->flags & FF_FLAGS_NO_IO_THRU_MDS))
+		return;
+	for (i = 0; i < fls->mirror_array_cnt; i++) {
+		node = &fls->mirror_array[i]->mirror_ds->id_node;
+		clear_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags);
+	}
+}
+
 static struct pnfs_layout_segment *
 ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
 		     struct nfs4_layoutget_res *lgr,
@@ -492,13 +505,22 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
 	}
 
 	p = xdr_inline_decode(&stream, 4);
-	if (p)
-		fls->flags = be32_to_cpup(p);
+	if (!p)
+		goto out_sort_mirrors;
+	fls->flags = be32_to_cpup(p);
+
+	p = xdr_inline_decode(&stream, 4);
+	if (!p)
+		goto out_sort_mirrors;
+	for (i=0; i < fls->mirror_array_cnt; i++)
+		fls->mirror_array[i]->report_interval = be32_to_cpup(p);
 
+out_sort_mirrors:
 	ff_layout_sort_mirrors(fls);
 	rc = ff_layout_check_layout(lgr);
 	if (rc)
 		goto out_err_free;
+	ff_layout_mark_devices_valid(fls);
 
 	ret = &fls->generic_hdr;
 	dprintk("<-- %s (success)\n", __func__);
@@ -589,7 +611,9 @@ nfs4_ff_layoutstat_start_io(struct nfs4_ff_layout_mirror *mirror,
 		mirror->start_time = now;
 	if (ktime_equal(mirror->last_report_time, notime))
 		mirror->last_report_time = now;
-	if (layoutstats_timer != 0)
+	if (mirror->report_interval != 0)
+		report_interval = (s64)mirror->report_interval * 1000LL;
+	else if (layoutstats_timer != 0)
 		report_interval = (s64)layoutstats_timer * 1000LL;
 	if (ktime_to_ms(ktime_sub(now, mirror->last_report_time)) >=
 			report_interval) {
@@ -741,17 +765,17 @@ ff_layout_alloc_commit_info(struct pnfs_layout_segment *lseg,
 }
 
 static struct nfs4_pnfs_ds *
-ff_layout_choose_best_ds_for_read(struct nfs_pageio_descriptor *pgio,
+ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg,
+				  int start_idx,
 				  int *best_idx)
 {
-	struct nfs4_ff_layout_segment *fls;
+	struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
 	struct nfs4_pnfs_ds *ds;
 	int idx;
 
-	fls = FF_LAYOUT_LSEG(pgio->pg_lseg);
 	/* mirrors are sorted by efficiency */
-	for (idx = 0; idx < fls->mirror_array_cnt; idx++) {
-		ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, idx, false);
+	for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) {
+		ds = nfs4_ff_layout_prepare_ds(lseg, idx, false);
 		if (ds) {
 			*best_idx = idx;
 			return ds;
@@ -771,18 +795,24 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 	int ds_idx;
 
 	/* Use full layout for now */
-	if (!pgio->pg_lseg)
+	if (!pgio->pg_lseg) {
 		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 						   req->wb_context,
 						   0,
 						   NFS4_MAX_UINT64,
 						   IOMODE_READ,
 						   GFP_KERNEL);
+		if (IS_ERR(pgio->pg_lseg)) {
+			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
+			pgio->pg_lseg = NULL;
+			return;
+		}
+	}
 	/* If no lseg, fall back to read through mds */
 	if (pgio->pg_lseg == NULL)
 		goto out_mds;
 
-	ds = ff_layout_choose_best_ds_for_read(pgio, &ds_idx);
+	ds = ff_layout_choose_best_ds_for_read(pgio->pg_lseg, 0, &ds_idx);
 	if (!ds)
 		goto out_mds;
 	mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx);
@@ -811,13 +841,19 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 	int i;
 	int status;
 
-	if (!pgio->pg_lseg)
+	if (!pgio->pg_lseg) {
 		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 						   req->wb_context,
 						   0,
 						   NFS4_MAX_UINT64,
 						   IOMODE_RW,
 						   GFP_NOFS);
+		if (IS_ERR(pgio->pg_lseg)) {
+			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
+			pgio->pg_lseg = NULL;
+			return;
+		}
+	}
 	/* If no lseg, fall back to write through mds */
 	if (pgio->pg_lseg == NULL)
 		goto out_mds;
@@ -853,18 +889,25 @@ static unsigned int
 ff_layout_pg_get_mirror_count_write(struct nfs_pageio_descriptor *pgio,
 				    struct nfs_page *req)
 {
-	if (!pgio->pg_lseg)
+	if (!pgio->pg_lseg) {
 		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 						   req->wb_context,
 						   0,
 						   NFS4_MAX_UINT64,
 						   IOMODE_RW,
 						   GFP_NOFS);
+		if (IS_ERR(pgio->pg_lseg)) {
+			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
+			pgio->pg_lseg = NULL;
+			goto out;
+		}
+	}
 	if (pgio->pg_lseg)
 		return FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg);
 
 	/* no lseg means that pnfs is not in use, so no mirroring here */
 	nfs_pageio_reset_write_mds(pgio);
+out:
 	return 1;
 }
 
@@ -898,18 +941,7 @@ static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs)
 			hdr->args.count,
 			(unsigned long long)hdr->args.offset);
 
-		if (!hdr->dreq) {
-			struct nfs_open_context *ctx;
-
-			ctx = nfs_list_entry(hdr->pages.next)->wb_context;
-			set_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags);
-			hdr->completion_ops->error_cleanup(&hdr->pages);
-		} else {
-			nfs_direct_set_resched_writes(hdr->dreq);
-			/* fake unstable write to let common nfs resend pages */
-			hdr->verf.committed = NFS_UNSTABLE;
-			hdr->good_bytes = hdr->args.count;
-		}
+		hdr->completion_ops->reschedule_io(hdr);
 		return;
 	}
 
@@ -1035,7 +1067,8 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
 		rpc_wake_up(&tbl->slot_tbl_waitq);
 		/* fall through */
 	default:
-		if (ff_layout_has_available_ds(lseg))
+		if (ff_layout_no_fallback_to_mds(lseg) ||
+		    ff_layout_has_available_ds(lseg))
 			return -NFS4ERR_RESET_TO_PNFS;
 reset:
 		dprintk("%s Retry through MDS. Error %d\n", __func__,
@@ -1086,7 +1119,7 @@ static int ff_layout_async_handle_error_v3(struct rpc_task *task,
 	return -NFS4ERR_RESET_TO_PNFS;
 out_retry:
 	task->tk_status = 0;
-	rpc_restart_call(task);
+	rpc_restart_call_prepare(task);
 	rpc_delay(task, NFS_JUKEBOX_RETRY_TIME);
 	return -EAGAIN;
 }
@@ -1144,6 +1177,14 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg,
 		}
 	}
 
+	switch (status) {
+	case NFS4ERR_DELAY:
+	case NFS4ERR_GRACE:
+		return;
+	default:
+		break;
+	}
+
 	mirror = FF_LAYOUT_COMP(lseg, idx);
 	err = ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout),
 				       mirror, offset, length, status, opnum,
@@ -1153,7 +1194,6 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg,
 }
 
 /* NFS_PROTO call done callback routines */
-
 static int ff_layout_read_done_cb(struct rpc_task *task,
 				struct nfs_pgio_header *hdr)
 {
@@ -1171,7 +1211,11 @@ static int ff_layout_read_done_cb(struct rpc_task *task,
 
 	switch (err) {
 	case -NFS4ERR_RESET_TO_PNFS:
-		set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
+		if (ff_layout_choose_best_ds_for_read(hdr->lseg,
+					hdr->pgio_mirror_idx + 1,
+					&hdr->pgio_mirror_idx))
+			goto out_eagain;
+		set_bit(NFS_LAYOUT_RETURN_REQUESTED,
 			&hdr->lseg->pls_layout->plh_flags);
 		pnfs_read_resend_pnfs(hdr);
 		return task->tk_status;
@@ -1179,11 +1223,13 @@ static int ff_layout_read_done_cb(struct rpc_task *task,
 		ff_layout_reset_read(hdr);
 		return task->tk_status;
 	case -EAGAIN:
-		rpc_restart_call_prepare(task);
-		return -EAGAIN;
+		goto out_eagain;
 	}
 
 	return 0;
+out_eagain:
+	rpc_restart_call_prepare(task);
+	return -EAGAIN;
 }
 
 static bool
@@ -1222,14 +1268,31 @@ ff_layout_reset_to_mds(struct pnfs_layout_segment *lseg, int idx)
 	return ff_layout_test_devid_unavailable(node);
 }
 
-static int ff_layout_read_prepare_common(struct rpc_task *task,
-					 struct nfs_pgio_header *hdr)
+static void ff_layout_read_record_layoutstats_start(struct rpc_task *task,
+		struct nfs_pgio_header *hdr)
 {
+	if (test_and_set_bit(NFS_IOHDR_STAT, &hdr->flags))
+		return;
 	nfs4_ff_layout_stat_io_start_read(hdr->inode,
 			FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx),
 			hdr->args.count,
 			task->tk_start);
+}
+
+static void ff_layout_read_record_layoutstats_done(struct rpc_task *task,
+		struct nfs_pgio_header *hdr)
+{
+	if (!test_and_clear_bit(NFS_IOHDR_STAT, &hdr->flags))
+		return;
+	nfs4_ff_layout_stat_io_end_read(task,
+			FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx),
+			hdr->args.count,
+			hdr->res.count);
+}
 
+static int ff_layout_read_prepare_common(struct rpc_task *task,
+					 struct nfs_pgio_header *hdr)
+{
 	if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) {
 		rpc_exit(task, -EIO);
 		return -EIO;
@@ -1245,6 +1308,7 @@ static int ff_layout_read_prepare_common(struct rpc_task *task,
 	}
 	hdr->pgio_done_cb = ff_layout_read_done_cb;
 
+	ff_layout_read_record_layoutstats_start(task, hdr);
 	return 0;
 }
 
@@ -1303,10 +1367,6 @@ static void ff_layout_read_call_done(struct rpc_task *task, void *data)
 
 	dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status);
 
-	nfs4_ff_layout_stat_io_end_read(task,
-			FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx),
-			hdr->args.count, hdr->res.count);
-
 	if (test_bit(NFS_IOHDR_REDO, &hdr->flags) &&
 	    task->tk_status == 0) {
 		nfs4_sequence_done(task, &hdr->res.seq_res);
@@ -1321,10 +1381,20 @@ static void ff_layout_read_count_stats(struct rpc_task *task, void *data)
 {
 	struct nfs_pgio_header *hdr = data;
 
+	ff_layout_read_record_layoutstats_done(task, hdr);
 	rpc_count_iostats_metrics(task,
 	    &NFS_CLIENT(hdr->inode)->cl_metrics[NFSPROC4_CLNT_READ]);
 }
 
+static void ff_layout_read_release(void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	ff_layout_read_record_layoutstats_done(&hdr->task, hdr);
+	pnfs_generic_rw_release(data);
+}
+
+
 static int ff_layout_write_done_cb(struct rpc_task *task,
 				struct nfs_pgio_header *hdr)
 {
@@ -1342,15 +1412,12 @@ static int ff_layout_write_done_cb(struct rpc_task *task,
 
 	switch (err) {
 	case -NFS4ERR_RESET_TO_PNFS:
-		pnfs_set_retry_layoutget(hdr->lseg->pls_layout);
 		ff_layout_reset_write(hdr, true);
 		return task->tk_status;
 	case -NFS4ERR_RESET_TO_MDS:
-		pnfs_clear_retry_layoutget(hdr->lseg->pls_layout);
 		ff_layout_reset_write(hdr, false);
 		return task->tk_status;
 	case -EAGAIN:
-		rpc_restart_call_prepare(task);
 		return -EAGAIN;
 	}
 
@@ -1382,11 +1449,9 @@ static int ff_layout_commit_done_cb(struct rpc_task *task,
 
 	switch (err) {
 	case -NFS4ERR_RESET_TO_PNFS:
-		pnfs_set_retry_layoutget(data->lseg->pls_layout);
 		pnfs_generic_prepare_to_resend_writes(data);
 		return -EAGAIN;
 	case -NFS4ERR_RESET_TO_MDS:
-		pnfs_clear_retry_layoutget(data->lseg->pls_layout);
 		pnfs_generic_prepare_to_resend_writes(data);
 		return -EAGAIN;
 	case -EAGAIN:
@@ -1401,14 +1466,31 @@ static int ff_layout_commit_done_cb(struct rpc_task *task,
 	return 0;
 }
 
-static int ff_layout_write_prepare_common(struct rpc_task *task,
-					  struct nfs_pgio_header *hdr)
+static void ff_layout_write_record_layoutstats_start(struct rpc_task *task,
+		struct nfs_pgio_header *hdr)
 {
+	if (test_and_set_bit(NFS_IOHDR_STAT, &hdr->flags))
+		return;
 	nfs4_ff_layout_stat_io_start_write(hdr->inode,
 			FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx),
 			hdr->args.count,
 			task->tk_start);
+}
+
+static void ff_layout_write_record_layoutstats_done(struct rpc_task *task,
+		struct nfs_pgio_header *hdr)
+{
+	if (!test_and_clear_bit(NFS_IOHDR_STAT, &hdr->flags))
+		return;
+	nfs4_ff_layout_stat_io_end_write(task,
+			FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx),
+			hdr->args.count, hdr->res.count,
+			hdr->res.verf->committed);
+}
 
+static int ff_layout_write_prepare_common(struct rpc_task *task,
+					  struct nfs_pgio_header *hdr)
+{
 	if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) {
 		rpc_exit(task, -EIO);
 		return -EIO;
@@ -1425,6 +1507,7 @@ static int ff_layout_write_prepare_common(struct rpc_task *task,
 		return -EAGAIN;
 	}
 
+	ff_layout_write_record_layoutstats_start(task, hdr);
 	return 0;
 }
 
@@ -1460,11 +1543,6 @@ static void ff_layout_write_call_done(struct rpc_task *task, void *data)
 {
 	struct nfs_pgio_header *hdr = data;
 
-	nfs4_ff_layout_stat_io_end_write(task,
-			FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx),
-			hdr->args.count, hdr->res.count,
-			hdr->res.verf->committed);
-
 	if (test_bit(NFS_IOHDR_REDO, &hdr->flags) &&
 	    task->tk_status == 0) {
 		nfs4_sequence_done(task, &hdr->res.seq_res);
@@ -1479,18 +1557,53 @@ static void ff_layout_write_count_stats(struct rpc_task *task, void *data)
 {
 	struct nfs_pgio_header *hdr = data;
 
+	ff_layout_write_record_layoutstats_done(task, hdr);
 	rpc_count_iostats_metrics(task,
 	    &NFS_CLIENT(hdr->inode)->cl_metrics[NFSPROC4_CLNT_WRITE]);
 }
 
-static void ff_layout_commit_prepare_common(struct rpc_task *task,
+static void ff_layout_write_release(void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	ff_layout_write_record_layoutstats_done(&hdr->task, hdr);
+	pnfs_generic_rw_release(data);
+}
+
+static void ff_layout_commit_record_layoutstats_start(struct rpc_task *task,
 		struct nfs_commit_data *cdata)
 {
+	if (test_and_set_bit(NFS_IOHDR_STAT, &cdata->flags))
+		return;
 	nfs4_ff_layout_stat_io_start_write(cdata->inode,
 			FF_LAYOUT_COMP(cdata->lseg, cdata->ds_commit_index),
 			0, task->tk_start);
 }
 
+static void ff_layout_commit_record_layoutstats_done(struct rpc_task *task,
+		struct nfs_commit_data *cdata)
+{
+	struct nfs_page *req;
+	__u64 count = 0;
+
+	if (!test_and_clear_bit(NFS_IOHDR_STAT, &cdata->flags))
+		return;
+
+	if (task->tk_status == 0) {
+		list_for_each_entry(req, &cdata->pages, wb_list)
+			count += req->wb_bytes;
+	}
+	nfs4_ff_layout_stat_io_end_write(task,
+			FF_LAYOUT_COMP(cdata->lseg, cdata->ds_commit_index),
+			count, count, NFS_FILE_SYNC);
+}
+
+static void ff_layout_commit_prepare_common(struct rpc_task *task,
+		struct nfs_commit_data *cdata)
+{
+	ff_layout_commit_record_layoutstats_start(task, cdata);
+}
+
 static void ff_layout_commit_prepare_v3(struct rpc_task *task, void *data)
 {
 	ff_layout_commit_prepare_common(task, data);
@@ -1511,19 +1624,6 @@ static void ff_layout_commit_prepare_v4(struct rpc_task *task, void *data)
 
 static void ff_layout_commit_done(struct rpc_task *task, void *data)
 {
-	struct nfs_commit_data *cdata = data;
-	struct nfs_page *req;
-	__u64 count = 0;
-
-	if (task->tk_status == 0) {
-		list_for_each_entry(req, &cdata->pages, wb_list)
-			count += req->wb_bytes;
-	}
-
-	nfs4_ff_layout_stat_io_end_write(task,
-			FF_LAYOUT_COMP(cdata->lseg, cdata->ds_commit_index),
-			count, count, NFS_FILE_SYNC);
-
 	pnfs_generic_write_commit_done(task, data);
 }
 
@@ -1531,50 +1631,59 @@ static void ff_layout_commit_count_stats(struct rpc_task *task, void *data)
 {
 	struct nfs_commit_data *cdata = data;
 
+	ff_layout_commit_record_layoutstats_done(task, cdata);
 	rpc_count_iostats_metrics(task,
 	    &NFS_CLIENT(cdata->inode)->cl_metrics[NFSPROC4_CLNT_COMMIT]);
 }
 
+static void ff_layout_commit_release(void *data)
+{
+	struct nfs_commit_data *cdata = data;
+
+	ff_layout_commit_record_layoutstats_done(&cdata->task, cdata);
+	pnfs_generic_commit_release(data);
+}
+
 static const struct rpc_call_ops ff_layout_read_call_ops_v3 = {
 	.rpc_call_prepare = ff_layout_read_prepare_v3,
 	.rpc_call_done = ff_layout_read_call_done,
 	.rpc_count_stats = ff_layout_read_count_stats,
-	.rpc_release = pnfs_generic_rw_release,
+	.rpc_release = ff_layout_read_release,
 };
 
 static const struct rpc_call_ops ff_layout_read_call_ops_v4 = {
 	.rpc_call_prepare = ff_layout_read_prepare_v4,
 	.rpc_call_done = ff_layout_read_call_done,
 	.rpc_count_stats = ff_layout_read_count_stats,
-	.rpc_release = pnfs_generic_rw_release,
+	.rpc_release = ff_layout_read_release,
 };
 
 static const struct rpc_call_ops ff_layout_write_call_ops_v3 = {
 	.rpc_call_prepare = ff_layout_write_prepare_v3,
 	.rpc_call_done = ff_layout_write_call_done,
 	.rpc_count_stats = ff_layout_write_count_stats,
-	.rpc_release = pnfs_generic_rw_release,
+	.rpc_release = ff_layout_write_release,
 };
 
 static const struct rpc_call_ops ff_layout_write_call_ops_v4 = {
 	.rpc_call_prepare = ff_layout_write_prepare_v4,
 	.rpc_call_done = ff_layout_write_call_done,
 	.rpc_count_stats = ff_layout_write_count_stats,
-	.rpc_release = pnfs_generic_rw_release,
+	.rpc_release = ff_layout_write_release,
 };
 
 static const struct rpc_call_ops ff_layout_commit_call_ops_v3 = {
 	.rpc_call_prepare = ff_layout_commit_prepare_v3,
 	.rpc_call_done = ff_layout_commit_done,
 	.rpc_count_stats = ff_layout_commit_count_stats,
-	.rpc_release = pnfs_generic_commit_release,
+	.rpc_release = ff_layout_commit_release,
 };
 
 static const struct rpc_call_ops ff_layout_commit_call_ops_v4 = {
 	.rpc_call_prepare = ff_layout_commit_prepare_v4,
 	.rpc_call_done = ff_layout_commit_done,
 	.rpc_count_stats = ff_layout_commit_count_stats,
-	.rpc_release = pnfs_generic_commit_release,
+	.rpc_release = ff_layout_commit_release,
 };
 
 static enum pnfs_try_status
@@ -1839,11 +1948,9 @@ ff_layout_encode_layoutreturn(struct pnfs_layout_hdr *lo,
 	start = xdr_reserve_space(xdr, 4);
 	BUG_ON(!start);
 
-	if (ff_layout_encode_ioerr(flo, xdr, args))
-		goto out;
-
+	ff_layout_encode_ioerr(flo, xdr, args);
 	ff_layout_encode_iostats(flo, xdr, args);
-out:
+
 	*start = cpu_to_be32((xdr->p - start - 1) * 4);
 	dprintk("%s: Return\n", __func__);
 }
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h
index 68cc0d9828f9..dd353bb7dc0a 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.h
+++ b/fs/nfs/flexfilelayout/flexfilelayout.h
@@ -10,6 +10,7 @@
 #define FS_NFS_NFS4FLEXFILELAYOUT_H
 
 #define FF_FLAGS_NO_LAYOUTCOMMIT 1
+#define FF_FLAGS_NO_IO_THRU_MDS 2
 
 #include "../pnfs.h"
 
@@ -84,6 +85,7 @@ struct nfs4_ff_layout_mirror {
 	struct nfs4_ff_layoutstat	write_stat;
 	ktime_t				start_time;
 	ktime_t				last_report_time;
+	u32				report_interval;
 };
 
 struct nfs4_ff_layout_segment {
@@ -146,6 +148,12 @@ FF_LAYOUT_MIRROR_COUNT(struct pnfs_layout_segment *lseg)
 }
 
 static inline bool
+ff_layout_no_fallback_to_mds(struct pnfs_layout_segment *lseg)
+{
+	return FF_LAYOUT_LSEG(lseg)->flags & FF_FLAGS_NO_IO_THRU_MDS;
+}
+
+static inline bool
 ff_layout_test_devid_unavailable(struct nfs4_deviceid_node *node)
 {
 	return nfs4_test_deviceid_unavailable(node);
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index e125e55de86d..add0e5a70bd6 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -218,63 +218,55 @@ static void extend_ds_error(struct nfs4_ff_layout_ds_err *err,
 	err->length = end - err->offset;
 }
 
-static bool ds_error_can_merge(struct nfs4_ff_layout_ds_err *err,  u64 offset,
-			       u64 length, int status, enum nfs_opnum4 opnum,
-			       nfs4_stateid *stateid,
-			       struct nfs4_deviceid *deviceid)
+static int
+ff_ds_error_match(const struct nfs4_ff_layout_ds_err *e1,
+		const struct nfs4_ff_layout_ds_err *e2)
 {
-	return err->status == status && err->opnum == opnum &&
-	       nfs4_stateid_match(&err->stateid, stateid) &&
-	       !memcmp(&err->deviceid, deviceid, sizeof(*deviceid)) &&
-	       end_offset(err->offset, err->length) >= offset &&
-	       err->offset <= end_offset(offset, length);
-}
-
-static bool merge_ds_error(struct nfs4_ff_layout_ds_err *old,
-			   struct nfs4_ff_layout_ds_err *new)
-{
-	if (!ds_error_can_merge(old, new->offset, new->length, new->status,
-				new->opnum, &new->stateid, &new->deviceid))
-		return false;
-
-	extend_ds_error(old, new->offset, new->length);
-	return true;
+	int ret;
+
+	if (e1->opnum != e2->opnum)
+		return e1->opnum < e2->opnum ? -1 : 1;
+	if (e1->status != e2->status)
+		return e1->status < e2->status ? -1 : 1;
+	ret = memcmp(&e1->stateid, &e2->stateid, sizeof(e1->stateid));
+	if (ret != 0)
+		return ret;
+	ret = memcmp(&e1->deviceid, &e2->deviceid, sizeof(e1->deviceid));
+	if (ret != 0)
+		return ret;
+	if (end_offset(e1->offset, e1->length) < e2->offset)
+		return -1;
+	if (e1->offset > end_offset(e2->offset, e2->length))
+		return 1;
+	/* If ranges overlap or are contiguous, they are the same */
+	return 0;
 }
 
-static bool
+static void
 ff_layout_add_ds_error_locked(struct nfs4_flexfile_layout *flo,
 			      struct nfs4_ff_layout_ds_err *dserr)
 {
-	struct nfs4_ff_layout_ds_err *err;
-
-	list_for_each_entry(err, &flo->error_list, list) {
-		if (merge_ds_error(err, dserr)) {
-			return true;
-		}
-	}
-
-	list_add(&dserr->list, &flo->error_list);
-	return false;
-}
-
-static bool
-ff_layout_update_ds_error(struct nfs4_flexfile_layout *flo, u64 offset,
-			  u64 length, int status, enum nfs_opnum4 opnum,
-			  nfs4_stateid *stateid, struct nfs4_deviceid *deviceid)
-{
-	bool found = false;
-	struct nfs4_ff_layout_ds_err *err;
-
-	list_for_each_entry(err, &flo->error_list, list) {
-		if (ds_error_can_merge(err, offset, length, status, opnum,
-				       stateid, deviceid)) {
-			found = true;
-			extend_ds_error(err, offset, length);
+	struct nfs4_ff_layout_ds_err *err, *tmp;
+	struct list_head *head = &flo->error_list;
+	int match;
+
+	/* Do insertion sort w/ merges */
+	list_for_each_entry_safe(err, tmp, &flo->error_list, list) {
+		match = ff_ds_error_match(err, dserr);
+		if (match < 0)
+			continue;
+		if (match > 0) {
+			/* Add entry "dserr" _before_ entry "err" */
+			head = &err->list;
 			break;
 		}
+		/* Entries match, so merge "err" into "dserr" */
+		extend_ds_error(dserr, err->offset, err->length);
+		list_del(&err->list);
+		kfree(err);
 	}
 
-	return found;
+	list_add_tail(&dserr->list, head);
 }
 
 int ff_layout_track_ds_error(struct nfs4_flexfile_layout *flo,
@@ -283,7 +275,6 @@ int ff_layout_track_ds_error(struct nfs4_flexfile_layout *flo,
 			     gfp_t gfp_flags)
 {
 	struct nfs4_ff_layout_ds_err *dserr;
-	bool needfree;
 
 	if (status == 0)
 		return 0;
@@ -291,14 +282,6 @@ int ff_layout_track_ds_error(struct nfs4_flexfile_layout *flo,
 	if (mirror->mirror_ds == NULL)
 		return -EINVAL;
 
-	spin_lock(&flo->generic_hdr.plh_inode->i_lock);
-	if (ff_layout_update_ds_error(flo, offset, length, status, opnum,
-				      &mirror->stateid,
-				      &mirror->mirror_ds->id_node.deviceid)) {
-		spin_unlock(&flo->generic_hdr.plh_inode->i_lock);
-		return 0;
-	}
-	spin_unlock(&flo->generic_hdr.plh_inode->i_lock);
 	dserr = kmalloc(sizeof(*dserr), gfp_flags);
 	if (!dserr)
 		return -ENOMEM;
@@ -313,10 +296,8 @@ int ff_layout_track_ds_error(struct nfs4_flexfile_layout *flo,
 	       NFS4_DEVICEID4_SIZE);
 
 	spin_lock(&flo->generic_hdr.plh_inode->i_lock);
-	needfree = ff_layout_add_ds_error_locked(flo, dserr);
+	ff_layout_add_ds_error_locked(flo, dserr);
 	spin_unlock(&flo->generic_hdr.plh_inode->i_lock);
-	if (needfree)
-		kfree(dserr);
 
 	return 0;
 }
@@ -429,22 +410,16 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
 					 mirror, lseg->pls_range.offset,
 					 lseg->pls_range.length, NFS4ERR_NXIO,
 					 OP_ILLEGAL, GFP_NOIO);
-		if (fail_return) {
-			pnfs_error_mark_layout_for_return(ino, lseg);
-			if (ff_layout_has_available_ds(lseg))
-				pnfs_set_retry_layoutget(lseg->pls_layout);
-			else
-				pnfs_clear_retry_layoutget(lseg->pls_layout);
-
-		} else {
+		if (!fail_return) {
 			if (ff_layout_has_available_ds(lseg))
-				set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
+				set_bit(NFS_LAYOUT_RETURN_REQUESTED,
 					&lseg->pls_layout->plh_flags);
-			else {
+			else
 				pnfs_error_mark_layout_for_return(ino, lseg);
-				pnfs_clear_retry_layoutget(lseg->pls_layout);
-			}
-		}
+		} else
+			pnfs_error_mark_layout_for_return(ino, lseg);
+		ds = NULL;
+		goto out;
 	}
 out_update_creds:
 	if (ff_layout_update_mirror_cred(mirror, ds))
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 326d9e10d833..738c84a42eb0 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -71,19 +71,25 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr)
 	return nfs_fileid_to_ino_t(fattr->fileid);
 }
 
-/**
- * nfs_wait_bit_killable - helper for functions that are sleeping on bit locks
- * @word: long word containing the bit lock
- */
-int nfs_wait_bit_killable(struct wait_bit_key *key)
+static int nfs_wait_killable(int mode)
 {
-	if (fatal_signal_pending(current))
-		return -ERESTARTSYS;
 	freezable_schedule_unsafe();
+	if (signal_pending_state(mode, current))
+		return -ERESTARTSYS;
 	return 0;
 }
+
+int nfs_wait_bit_killable(struct wait_bit_key *key, int mode)
+{
+	return nfs_wait_killable(mode);
+}
 EXPORT_SYMBOL_GPL(nfs_wait_bit_killable);
 
+int nfs_wait_atomic_killable(atomic_t *p)
+{
+	return nfs_wait_killable(TASK_KILLABLE);
+}
+
 /**
  * nfs_compat_user_ino64 - returns the user-visible inode number
  * @fileid: 64-bit fileid
@@ -135,7 +141,7 @@ void nfs_evict_inode(struct inode *inode)
 
 int nfs_sync_inode(struct inode *inode)
 {
-	nfs_inode_dio_wait(inode);
+	inode_dio_wait(inode);
 	return nfs_wb_all(inode);
 }
 EXPORT_SYMBOL_GPL(nfs_sync_inode);
@@ -408,9 +414,10 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
 				inode->i_fop = NULL;
 				inode->i_flags |= S_AUTOMOUNT;
 			}
-		} else if (S_ISLNK(inode->i_mode))
+		} else if (S_ISLNK(inode->i_mode)) {
 			inode->i_op = &nfs_symlink_inode_operations;
-		else
+			inode_nohighmem(inode);
+		} else
 			init_special_inode(inode, inode->i_mode, fattr->rdev);
 
 		memset(&inode->i_atime, 0, sizeof(inode->i_atime));
@@ -618,7 +625,10 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr,
 		nfs_inc_stats(inode, NFSIOS_SETATTRTRUNC);
 		nfs_vmtruncate(inode, attr->ia_size);
 	}
-	nfs_update_inode(inode, fattr);
+	if (fattr->valid)
+		nfs_update_inode(inode, fattr);
+	else
+		NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATTR;
 	spin_unlock(&inode->i_lock);
 }
 EXPORT_SYMBOL_GPL(nfs_setattr_update_inode);
@@ -651,9 +661,9 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 	trace_nfs_getattr_enter(inode);
 	/* Flush out writes to the server in order to update c/mtime.  */
 	if (S_ISREG(inode->i_mode)) {
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		err = nfs_sync_inode(inode);
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 		if (err)
 			goto out;
 	}
@@ -696,7 +706,7 @@ static void nfs_init_lock_context(struct nfs_lock_context *l_ctx)
 	l_ctx->lockowner.l_owner = current->files;
 	l_ctx->lockowner.l_pid = current->tgid;
 	INIT_LIST_HEAD(&l_ctx->list);
-	nfs_iocounter_init(&l_ctx->io_count);
+	atomic_set(&l_ctx->io_count, 0);
 }
 
 static struct nfs_lock_context *__nfs_find_lock_context(struct nfs_open_context *ctx)
@@ -909,6 +919,12 @@ void nfs_file_clear_open_context(struct file *filp)
 	if (ctx) {
 		struct inode *inode = d_inode(ctx->dentry);
 
+		/*
+		 * We fatal error on write before. Try to writeback
+		 * every page again.
+		 */
+		if (ctx->error < 0)
+			invalidate_inode_pages2(inode->i_mapping);
 		filp->private_data = NULL;
 		spin_lock(&inode->i_lock);
 		list_move_tail(&ctx->list, &NFS_I(inode)->open_files);
@@ -924,7 +940,7 @@ int nfs_open(struct inode *inode, struct file *filp)
 {
 	struct nfs_open_context *ctx;
 
-	ctx = alloc_nfs_open_context(filp->f_path.dentry, filp->f_mode);
+	ctx = alloc_nfs_open_context(file_dentry(filp), filp->f_mode);
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 	nfs_file_set_open_context(filp, ctx);
@@ -1083,6 +1099,27 @@ static bool nfs_mapping_need_revalidate_inode(struct inode *inode)
 		|| NFS_STALE(inode);
 }
 
+int nfs_revalidate_mapping_rcu(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+	unsigned long *bitlock = &nfsi->flags;
+	int ret = 0;
+
+	if (IS_SWAPFILE(inode))
+		goto out;
+	if (nfs_mapping_need_revalidate_inode(inode)) {
+		ret = -ECHILD;
+		goto out;
+	}
+	spin_lock(&inode->i_lock);
+	if (test_bit(NFS_INO_INVALIDATING, bitlock) ||
+	    (nfsi->cache_validity & NFS_INO_INVALID_DATA))
+		ret = -ECHILD;
+	spin_unlock(&inode->i_lock);
+out:
+	return ret;
+}
+
 /**
  * __nfs_revalidate_mapping - Revalidate the pagecache
  * @inode - pointer to host inode
@@ -1141,9 +1178,9 @@ static int __nfs_revalidate_mapping(struct inode *inode,
 	spin_unlock(&inode->i_lock);
 	trace_nfs_invalidate_mapping_enter(inode);
 	if (may_lock) {
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		ret = nfs_invalidate_mapping(inode, mapping);
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 	} else
 		ret = nfs_invalidate_mapping(inode, mapping);
 	trace_nfs_invalidate_mapping_exit(inode, ret);
@@ -1638,6 +1675,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	unsigned long invalid = 0;
 	unsigned long now = jiffies;
 	unsigned long save_cache_validity;
+	bool cache_revalidated = true;
 
 	dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%x)\n",
 			__func__, inode->i_sb->s_id, inode->i_ino,
@@ -1699,22 +1737,28 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 				nfs_force_lookup_revalidate(inode);
 			inode->i_version = fattr->change_attr;
 		}
-	} else
+	} else {
 		nfsi->cache_validity |= save_cache_validity;
+		cache_revalidated = false;
+	}
 
 	if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
 		memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
-	} else if (server->caps & NFS_CAP_MTIME)
+	} else if (server->caps & NFS_CAP_MTIME) {
 		nfsi->cache_validity |= save_cache_validity &
 				(NFS_INO_INVALID_ATTR
 				| NFS_INO_REVAL_FORCED);
+		cache_revalidated = false;
+	}
 
 	if (fattr->valid & NFS_ATTR_FATTR_CTIME) {
 		memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
-	} else if (server->caps & NFS_CAP_CTIME)
+	} else if (server->caps & NFS_CAP_CTIME) {
 		nfsi->cache_validity |= save_cache_validity &
 				(NFS_INO_INVALID_ATTR
 				| NFS_INO_REVAL_FORCED);
+		cache_revalidated = false;
+	}
 
 	/* Check if our cached file size is stale */
 	if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
@@ -1734,19 +1778,23 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 					(long long)cur_isize,
 					(long long)new_isize);
 		}
-	} else
+	} else {
 		nfsi->cache_validity |= save_cache_validity &
 				(NFS_INO_INVALID_ATTR
 				| NFS_INO_REVAL_PAGECACHE
 				| NFS_INO_REVAL_FORCED);
+		cache_revalidated = false;
+	}
 
 
 	if (fattr->valid & NFS_ATTR_FATTR_ATIME)
 		memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime));
-	else if (server->caps & NFS_CAP_ATIME)
+	else if (server->caps & NFS_CAP_ATIME) {
 		nfsi->cache_validity |= save_cache_validity &
 				(NFS_INO_INVALID_ATIME
 				| NFS_INO_REVAL_FORCED);
+		cache_revalidated = false;
+	}
 
 	if (fattr->valid & NFS_ATTR_FATTR_MODE) {
 		if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) {
@@ -1755,36 +1803,42 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			inode->i_mode = newmode;
 			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
 		}
-	} else if (server->caps & NFS_CAP_MODE)
+	} else if (server->caps & NFS_CAP_MODE) {
 		nfsi->cache_validity |= save_cache_validity &
 				(NFS_INO_INVALID_ATTR
 				| NFS_INO_INVALID_ACCESS
 				| NFS_INO_INVALID_ACL
 				| NFS_INO_REVAL_FORCED);
+		cache_revalidated = false;
+	}
 
 	if (fattr->valid & NFS_ATTR_FATTR_OWNER) {
 		if (!uid_eq(inode->i_uid, fattr->uid)) {
 			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
 			inode->i_uid = fattr->uid;
 		}
-	} else if (server->caps & NFS_CAP_OWNER)
+	} else if (server->caps & NFS_CAP_OWNER) {
 		nfsi->cache_validity |= save_cache_validity &
 				(NFS_INO_INVALID_ATTR
 				| NFS_INO_INVALID_ACCESS
 				| NFS_INO_INVALID_ACL
 				| NFS_INO_REVAL_FORCED);
+		cache_revalidated = false;
+	}
 
 	if (fattr->valid & NFS_ATTR_FATTR_GROUP) {
 		if (!gid_eq(inode->i_gid, fattr->gid)) {
 			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
 			inode->i_gid = fattr->gid;
 		}
-	} else if (server->caps & NFS_CAP_OWNER_GROUP)
+	} else if (server->caps & NFS_CAP_OWNER_GROUP) {
 		nfsi->cache_validity |= save_cache_validity &
 				(NFS_INO_INVALID_ATTR
 				| NFS_INO_INVALID_ACCESS
 				| NFS_INO_INVALID_ACL
 				| NFS_INO_REVAL_FORCED);
+		cache_revalidated = false;
+	}
 
 	if (fattr->valid & NFS_ATTR_FATTR_NLINK) {
 		if (inode->i_nlink != fattr->nlink) {
@@ -1793,19 +1847,22 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 				invalid |= NFS_INO_INVALID_DATA;
 			set_nlink(inode, fattr->nlink);
 		}
-	} else if (server->caps & NFS_CAP_NLINK)
+	} else if (server->caps & NFS_CAP_NLINK) {
 		nfsi->cache_validity |= save_cache_validity &
 				(NFS_INO_INVALID_ATTR
 				| NFS_INO_REVAL_FORCED);
+		cache_revalidated = false;
+	}
 
 	if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
 		/*
 		 * report the blocks in 512byte units
 		 */
 		inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used);
- 	}
-	if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
+	} else if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
 		inode->i_blocks = fattr->du.nfs2.blocks;
+	else
+		cache_revalidated = false;
 
 	/* Update attrtimeo value if we're out of the unstable period */
 	if (invalid & NFS_INO_INVALID_ATTR) {
@@ -1815,16 +1872,24 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		/* Set barrier to be more recent than all outstanding updates */
 		nfsi->attr_gencount = nfs_inc_attr_generation_counter();
 	} else {
-		if (!time_in_range_open(now, nfsi->attrtimeo_timestamp, nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) {
-			if ((nfsi->attrtimeo <<= 1) > NFS_MAXATTRTIMEO(inode))
-				nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode);
+		if (cache_revalidated) {
+			if (!time_in_range_open(now, nfsi->attrtimeo_timestamp,
+				nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) {
+				nfsi->attrtimeo <<= 1;
+				if (nfsi->attrtimeo > NFS_MAXATTRTIMEO(inode))
+					nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode);
+			}
 			nfsi->attrtimeo_timestamp = now;
 		}
 		/* Set the barrier to be more recent than this fattr */
 		if ((long)fattr->gencount - (long)nfsi->attr_gencount > 0)
 			nfsi->attr_gencount = fattr->gencount;
 	}
-	invalid &= ~NFS_INO_INVALID_ATTR;
+
+	/* Don't declare attrcache up to date if there were no attrs! */
+	if (cache_revalidated)
+		invalid &= ~NFS_INO_INVALID_ATTR;
+
 	/* Don't invalidate the data if we were to blame */
 	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)
 				|| S_ISLNK(inode->i_mode)))
@@ -1904,7 +1969,7 @@ static int __init nfs_init_inodecache(void)
 	nfs_inode_cachep = kmem_cache_create("nfs_inode_cache",
 					     sizeof(struct nfs_inode),
 					     0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD),
+						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
 					     init_once);
 	if (nfs_inode_cachep == NULL)
 		return -ENOMEM;
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 56cfde26fb9c..f1d1d2c472e9 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -238,7 +238,7 @@ extern void nfs_pgheader_init(struct nfs_pageio_descriptor *desc,
 			      struct nfs_pgio_header *hdr,
 			      void (*release)(struct nfs_pgio_header *hdr));
 void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos);
-int nfs_iocounter_wait(struct nfs_io_counter *c);
+int nfs_iocounter_wait(struct nfs_lock_context *l_ctx);
 
 extern const struct nfs_pageio_ops nfs_pgio_rw_ops;
 struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *);
@@ -252,18 +252,18 @@ void nfs_free_request(struct nfs_page *req);
 struct nfs_pgio_mirror *
 nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc);
 
-static inline void nfs_iocounter_init(struct nfs_io_counter *c)
-{
-	c->flags = 0;
-	atomic_set(&c->io_count, 0);
-}
-
 static inline bool nfs_pgio_has_mirroring(struct nfs_pageio_descriptor *desc)
 {
 	WARN_ON_ONCE(desc->pg_mirror_count < 1);
 	return desc->pg_mirror_count > 1;
 }
 
+static inline bool nfs_match_open_context(const struct nfs_open_context *ctx1,
+		const struct nfs_open_context *ctx2)
+{
+	return ctx1->cred == ctx2->cred && ctx1->state == ctx2->state;
+}
+
 /* nfs2xdr.c */
 extern struct rpc_procinfo nfs_procedures[];
 extern int nfs2_decode_dirent(struct xdr_stream *,
@@ -358,7 +358,7 @@ int nfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
 int nfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
 
 /* file.c */
-int nfs_file_fsync_commit(struct file *, loff_t, loff_t, int);
+int nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync);
 loff_t nfs_file_llseek(struct file *, loff_t, int);
 ssize_t nfs_file_read(struct kiocb *, struct iov_iter *);
 ssize_t nfs_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *,
@@ -379,7 +379,8 @@ extern int nfs_drop_inode(struct inode *);
 extern void nfs_clear_inode(struct inode *);
 extern void nfs_evict_inode(struct inode *);
 void nfs_zap_acl_cache(struct inode *inode);
-extern int nfs_wait_bit_killable(struct wait_bit_key *key);
+extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode);
+extern int nfs_wait_atomic_killable(atomic_t *p);
 
 /* super.c */
 extern const struct super_operations nfs_sops;
@@ -483,7 +484,7 @@ void nfs_retry_commit(struct list_head *page_list,
 		      struct nfs_commit_info *cinfo,
 		      u32 ds_commit_idx);
 void nfs_commitdata_release(struct nfs_commit_data *data);
-void nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst,
+void nfs_request_add_commit_list(struct nfs_page *req,
 				 struct nfs_commit_info *cinfo);
 void nfs_request_add_commit_list_locked(struct nfs_page *req,
 		struct list_head *dst,
@@ -514,12 +515,7 @@ extern int nfs_sillyrename(struct inode *dir, struct dentry *dentry);
 /* direct.c */
 void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo,
 			      struct nfs_direct_req *dreq);
-static inline void nfs_inode_dio_wait(struct inode *inode)
-{
-	inode_dio_wait(inode);
-}
 extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq);
-extern void nfs_direct_set_resched_writes(struct nfs_direct_req *dreq);
 
 /* nfs4proc.c */
 extern void __nfs4_read_done_cb(struct nfs_pgio_header *);
@@ -642,11 +638,11 @@ unsigned int nfs_page_length(struct page *page)
 
 	if (i_size > 0) {
 		pgoff_t page_index = page_file_index(page);
-		pgoff_t end_index = (i_size - 1) >> PAGE_CACHE_SHIFT;
+		pgoff_t end_index = (i_size - 1) >> PAGE_SHIFT;
 		if (page_index < end_index)
-			return PAGE_CACHE_SIZE;
+			return PAGE_SIZE;
 		if (page_index == end_index)
-			return ((i_size - 1) & ~PAGE_CACHE_MASK) + 1;
+			return ((i_size - 1) & ~PAGE_MASK) + 1;
 	}
 	return 0;
 }
@@ -696,9 +692,32 @@ static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh)
 {
 	return ~crc32_le(0xFFFFFFFF, &fh->data[0], fh->size);
 }
+static inline u32 nfs_stateid_hash(const nfs4_stateid *stateid)
+{
+	return ~crc32_le(0xFFFFFFFF, &stateid->other[0],
+				NFS4_STATEID_OTHER_SIZE);
+}
 #else
 static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh)
 {
 	return 0;
 }
+static inline u32 nfs_stateid_hash(nfs4_stateid *stateid)
+{
+	return 0;
+}
 #endif
+
+static inline bool nfs_error_is_fatal(int err)
+{
+	switch (err) {
+	case -ERESTARTSYS:
+	case -EIO:
+	case -ENOSPC:
+	case -EROFS:
+	case -E2BIG:
+		return true;
+	default:
+		return false;
+	}
+}
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index 99a45283b9ee..09b190015df4 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -16,9 +16,7 @@
 #include <linux/nfs_fs.h>
 #include "internal.h"
 
-#ifdef NFS_DEBUG
-# define NFSDBG_FACILITY	NFSDBG_MOUNT
-#endif
+#define NFSDBG_FACILITY	NFSDBG_MOUNT
 
 /*
  * Defined by RFC 1094, section A.3; and RFC 1813, section 5.1.4
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 1ebe2fc7cda2..17c0fa1eccfa 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -284,12 +284,12 @@ nfs3_listxattr(struct dentry *dentry, char *data, size_t size)
 	int error;
 
 	error = nfs3_list_one_acl(inode, ACL_TYPE_ACCESS,
-			POSIX_ACL_XATTR_ACCESS, data, size, &result);
+			XATTR_NAME_POSIX_ACL_ACCESS, data, size, &result);
 	if (error)
 		return error;
 
 	error = nfs3_list_one_acl(inode, ACL_TYPE_DEFAULT,
-			POSIX_ACL_XATTR_DEFAULT, data, size, &result);
+			XATTR_NAME_POSIX_ACL_DEFAULT, data, size, &result);
 	if (error)
 		return error;
 	return result;
diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
index 814c1255f1d2..b587ccd31083 100644
--- a/fs/nfs/nfs42.h
+++ b/fs/nfs/nfs42.h
@@ -17,5 +17,6 @@ int nfs42_proc_deallocate(struct file *, loff_t, loff_t);
 loff_t nfs42_proc_llseek(struct file *, loff_t, int);
 int nfs42_proc_layoutstats_generic(struct nfs_server *,
 				   struct nfs42_layoutstat_data *);
+int nfs42_proc_clone(struct file *, struct file *, loff_t, loff_t, loff_t);
 
 #endif /* __LINUX_FS_NFS_NFS4_2_H */
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 0f020e4d8421..dff83460e5a6 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -14,31 +14,10 @@
 #include "pnfs.h"
 #include "internal.h"
 
-#define NFSDBG_FACILITY NFSDBG_PNFS
-
-static int nfs42_set_rw_stateid(nfs4_stateid *dst, struct file *file,
-				fmode_t fmode)
-{
-	struct nfs_open_context *open;
-	struct nfs_lock_context *lock;
-	int ret;
-
-	open = get_nfs_open_context(nfs_file_open_context(file));
-	lock = nfs_get_lock_context(open);
-	if (IS_ERR(lock)) {
-		put_nfs_open_context(open);
-		return PTR_ERR(lock);
-	}
-
-	ret = nfs4_set_rw_stateid(dst, open, lock, fmode);
-
-	nfs_put_lock_context(lock);
-	put_nfs_open_context(open);
-	return ret;
-}
+#define NFSDBG_FACILITY NFSDBG_PROC
 
 static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
-				 loff_t offset, loff_t len)
+		struct nfs_lock_context *lock, loff_t offset, loff_t len)
 {
 	struct inode *inode = file_inode(filep);
 	struct nfs_server *server = NFS_SERVER(inode);
@@ -56,7 +35,8 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 	msg->rpc_argp = &args;
 	msg->rpc_resp = &res;
 
-	status = nfs42_set_rw_stateid(&args.falloc_stateid, filep, FMODE_WRITE);
+	status = nfs4_set_rw_stateid(&args.falloc_stateid, lock->open_context,
+			lock, FMODE_WRITE);
 	if (status)
 		return status;
 
@@ -78,15 +58,26 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 {
 	struct nfs_server *server = NFS_SERVER(file_inode(filep));
 	struct nfs4_exception exception = { };
+	struct nfs_lock_context *lock;
 	int err;
 
+	lock = nfs_get_lock_context(nfs_file_open_context(filep));
+	if (IS_ERR(lock))
+		return PTR_ERR(lock);
+
+	exception.inode = file_inode(filep);
+	exception.state = lock->open_context->state;
+
 	do {
-		err = _nfs42_proc_fallocate(msg, filep, offset, len);
-		if (err == -ENOTSUPP)
-			return -EOPNOTSUPP;
+		err = _nfs42_proc_fallocate(msg, filep, lock, offset, len);
+		if (err == -ENOTSUPP) {
+			err = -EOPNOTSUPP;
+			break;
+		}
 		err = nfs4_handle_exception(server, err, &exception);
 	} while (exception.retry);
 
+	nfs_put_lock_context(lock);
 	return err;
 }
 
@@ -101,13 +92,13 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len)
 	if (!nfs_server_capable(inode, NFS_CAP_ALLOCATE))
 		return -EOPNOTSUPP;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	err = nfs42_proc_fallocate(&msg, filep, offset, len);
 	if (err == -EOPNOTSUPP)
 		NFS_SERVER(inode)->caps &= ~NFS_CAP_ALLOCATE;
 
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return err;
 }
 
@@ -123,7 +114,7 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len)
 		return -EOPNOTSUPP;
 
 	nfs_wb_all(inode);
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	err = nfs42_proc_fallocate(&msg, filep, offset, len);
 	if (err == 0)
@@ -131,11 +122,12 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len)
 	if (err == -EOPNOTSUPP)
 		NFS_SERVER(inode)->caps &= ~NFS_CAP_DEALLOCATE;
 
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return err;
 }
 
-static loff_t _nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
+static loff_t _nfs42_proc_llseek(struct file *filep,
+		struct nfs_lock_context *lock, loff_t offset, int whence)
 {
 	struct inode *inode = file_inode(filep);
 	struct nfs42_seek_args args = {
@@ -156,7 +148,8 @@ static loff_t _nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
 	if (!nfs_server_capable(inode, NFS_CAP_SEEK))
 		return -ENOTSUPP;
 
-	status = nfs42_set_rw_stateid(&args.sa_stateid, filep, FMODE_READ);
+	status = nfs4_set_rw_stateid(&args.sa_stateid, lock->open_context,
+			lock, FMODE_READ);
 	if (status)
 		return status;
 
@@ -175,17 +168,28 @@ loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
 {
 	struct nfs_server *server = NFS_SERVER(file_inode(filep));
 	struct nfs4_exception exception = { };
+	struct nfs_lock_context *lock;
 	loff_t err;
 
+	lock = nfs_get_lock_context(nfs_file_open_context(filep));
+	if (IS_ERR(lock))
+		return PTR_ERR(lock);
+
+	exception.inode = file_inode(filep);
+	exception.state = lock->open_context->state;
+
 	do {
-		err = _nfs42_proc_llseek(filep, offset, whence);
+		err = _nfs42_proc_llseek(filep, lock, offset, whence);
 		if (err >= 0)
 			break;
-		if (err == -ENOTSUPP)
-			return -EOPNOTSUPP;
+		if (err == -ENOTSUPP) {
+			err = -EOPNOTSUPP;
+			break;
+		}
 		err = nfs4_handle_exception(server, err, &exception);
 	} while (exception.retry);
 
+	nfs_put_lock_context(lock);
 	return err;
 }
 
@@ -204,6 +208,8 @@ static void
 nfs42_layoutstat_done(struct rpc_task *task, void *calldata)
 {
 	struct nfs42_layoutstat_data *data = calldata;
+	struct inode *inode = data->inode;
+	struct pnfs_layout_hdr *lo;
 
 	if (!nfs4_sequence_done(task, &data->res.seq_res))
 		return;
@@ -211,12 +217,35 @@ nfs42_layoutstat_done(struct rpc_task *task, void *calldata)
 	switch (task->tk_status) {
 	case 0:
 		break;
+	case -NFS4ERR_EXPIRED:
+	case -NFS4ERR_STALE_STATEID:
+	case -NFS4ERR_OLD_STATEID:
+	case -NFS4ERR_BAD_STATEID:
+		spin_lock(&inode->i_lock);
+		lo = NFS_I(inode)->layout;
+		if (lo && nfs4_stateid_match(&data->args.stateid,
+					     &lo->plh_stateid)) {
+			LIST_HEAD(head);
+
+			/*
+			 * Mark the bad layout state as invalid, then retry
+			 * with the current stateid.
+			 */
+			set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
+			pnfs_mark_matching_lsegs_invalid(lo, &head, NULL);
+			spin_unlock(&inode->i_lock);
+			pnfs_free_lseg_list(&head);
+		} else
+			spin_unlock(&inode->i_lock);
+		break;
 	case -ENOTSUPP:
 	case -EOPNOTSUPP:
-		NFS_SERVER(data->inode)->caps &= ~NFS_CAP_LAYOUTSTATS;
+		NFS_SERVER(inode)->caps &= ~NFS_CAP_LAYOUTSTATS;
 	default:
-		dprintk("%s server returns %d\n", __func__, task->tk_status);
+		break;
 	}
+
+	dprintk("%s server returns %d\n", __func__, task->tk_status);
 }
 
 static void
@@ -271,3 +300,104 @@ int nfs42_proc_layoutstats_generic(struct nfs_server *server,
 		return PTR_ERR(task);
 	return 0;
 }
+
+static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f,
+		struct file *dst_f, struct nfs_lock_context *src_lock,
+		struct nfs_lock_context *dst_lock, loff_t src_offset,
+		loff_t dst_offset, loff_t count)
+{
+	struct inode *src_inode = file_inode(src_f);
+	struct inode *dst_inode = file_inode(dst_f);
+	struct nfs_server *server = NFS_SERVER(dst_inode);
+	struct nfs42_clone_args args = {
+		.src_fh = NFS_FH(src_inode),
+		.dst_fh = NFS_FH(dst_inode),
+		.src_offset = src_offset,
+		.dst_offset = dst_offset,
+		.count = count,
+		.dst_bitmask = server->cache_consistency_bitmask,
+	};
+	struct nfs42_clone_res res = {
+		.server	= server,
+	};
+	int status;
+
+	msg->rpc_argp = &args;
+	msg->rpc_resp = &res;
+
+	status = nfs4_set_rw_stateid(&args.src_stateid, src_lock->open_context,
+			src_lock, FMODE_READ);
+	if (status)
+		return status;
+
+	status = nfs4_set_rw_stateid(&args.dst_stateid, dst_lock->open_context,
+			dst_lock, FMODE_WRITE);
+	if (status)
+		return status;
+
+	res.dst_fattr = nfs_alloc_fattr();
+	if (!res.dst_fattr)
+		return -ENOMEM;
+
+	status = nfs4_call_sync(server->client, server, msg,
+				&args.seq_args, &res.seq_res, 0);
+	if (status == 0)
+		status = nfs_post_op_update_inode(dst_inode, res.dst_fattr);
+
+	kfree(res.dst_fattr);
+	return status;
+}
+
+int nfs42_proc_clone(struct file *src_f, struct file *dst_f,
+		     loff_t src_offset, loff_t dst_offset, loff_t count)
+{
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLONE],
+	};
+	struct inode *inode = file_inode(src_f);
+	struct nfs_server *server = NFS_SERVER(file_inode(src_f));
+	struct nfs_lock_context *src_lock;
+	struct nfs_lock_context *dst_lock;
+	struct nfs4_exception src_exception = { };
+	struct nfs4_exception dst_exception = { };
+	int err, err2;
+
+	if (!nfs_server_capable(inode, NFS_CAP_CLONE))
+		return -EOPNOTSUPP;
+
+	src_lock = nfs_get_lock_context(nfs_file_open_context(src_f));
+	if (IS_ERR(src_lock))
+		return PTR_ERR(src_lock);
+
+	src_exception.inode = file_inode(src_f);
+	src_exception.state = src_lock->open_context->state;
+
+	dst_lock = nfs_get_lock_context(nfs_file_open_context(dst_f));
+	if (IS_ERR(dst_lock)) {
+		err = PTR_ERR(dst_lock);
+		goto out_put_src_lock;
+	}
+
+	dst_exception.inode = file_inode(dst_f);
+	dst_exception.state = dst_lock->open_context->state;
+
+	do {
+		err = _nfs42_proc_clone(&msg, src_f, dst_f, src_lock, dst_lock,
+					src_offset, dst_offset, count);
+		if (err == -ENOTSUPP || err == -EOPNOTSUPP) {
+			NFS_SERVER(inode)->caps &= ~NFS_CAP_CLONE;
+			err = -EOPNOTSUPP;
+			break;
+		}
+
+		err2 = nfs4_handle_exception(server, err, &src_exception);
+		err = nfs4_handle_exception(server, err, &dst_exception);
+		if (!err)
+			err = err2;
+	} while (src_exception.retry || dst_exception.retry);
+
+	nfs_put_lock_context(dst_lock);
+out_put_src_lock:
+	nfs_put_lock_context(src_lock);
+	return err;
+}
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index 0eb29e14070d..0ca482a51e53 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -34,6 +34,12 @@
 					1 /* opaque devaddr4 length */ + \
 					XDR_QUADLEN(PNFS_LAYOUTSTATS_MAXSIZE))
 #define decode_layoutstats_maxsz	(op_decode_hdr_maxsz)
+#define encode_clone_maxsz		(encode_stateid_maxsz + \
+					encode_stateid_maxsz + \
+					2 /* src offset */ + \
+					2 /* dst offset */ + \
+					2 /* count */)
+#define decode_clone_maxsz		(op_decode_hdr_maxsz)
 
 #define NFS4_enc_allocate_sz		(compound_encode_hdr_maxsz + \
 					 encode_putfh_maxsz + \
@@ -65,7 +71,20 @@
 					 decode_sequence_maxsz + \
 					 decode_putfh_maxsz + \
 					 PNFS_LAYOUTSTATS_MAXDEV * decode_layoutstats_maxsz)
-
+#define NFS4_enc_clone_sz		(compound_encode_hdr_maxsz + \
+					 encode_sequence_maxsz + \
+					 encode_putfh_maxsz + \
+					 encode_savefh_maxsz + \
+					 encode_putfh_maxsz + \
+					 encode_clone_maxsz + \
+					 encode_getattr_maxsz)
+#define NFS4_dec_clone_sz		(compound_decode_hdr_maxsz + \
+					 decode_sequence_maxsz + \
+					 decode_putfh_maxsz + \
+					 decode_savefh_maxsz + \
+					 decode_putfh_maxsz + \
+					 decode_clone_maxsz + \
+					 decode_getattr_maxsz)
 
 static void encode_fallocate(struct xdr_stream *xdr,
 			     struct nfs42_falloc_args *args)
@@ -128,6 +147,21 @@ static void encode_layoutstats(struct xdr_stream *xdr,
 		encode_uint32(xdr, 0);
 }
 
+static void encode_clone(struct xdr_stream *xdr,
+			 struct nfs42_clone_args *args,
+			 struct compound_hdr *hdr)
+{
+	__be32 *p;
+
+	encode_op_hdr(xdr, OP_CLONE, decode_clone_maxsz, hdr);
+	encode_nfs4_stateid(xdr, &args->src_stateid);
+	encode_nfs4_stateid(xdr, &args->dst_stateid);
+	p = reserve_space(xdr, 3*8);
+	p = xdr_encode_hyper(p, args->src_offset);
+	p = xdr_encode_hyper(p, args->dst_offset);
+	xdr_encode_hyper(p, args->count);
+}
+
 /*
  * Encode ALLOCATE request
  */
@@ -206,6 +240,27 @@ static void nfs4_xdr_enc_layoutstats(struct rpc_rqst *req,
 	encode_nops(&hdr);
 }
 
+/*
+ * Encode CLONE request
+ */
+static void nfs4_xdr_enc_clone(struct rpc_rqst *req,
+			       struct xdr_stream *xdr,
+			       struct nfs42_clone_args *args)
+{
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, args->src_fh, &hdr);
+	encode_savefh(xdr, &hdr);
+	encode_putfh(xdr, args->dst_fh, &hdr);
+	encode_clone(xdr, args, &hdr);
+	encode_getfattr(xdr, args->dst_bitmask, &hdr);
+	encode_nops(&hdr);
+}
+
 static int decode_allocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res)
 {
 	return decode_op_hdr(xdr, OP_ALLOCATE);
@@ -243,6 +298,11 @@ static int decode_layoutstats(struct xdr_stream *xdr)
 	return decode_op_hdr(xdr, OP_LAYOUTSTATS);
 }
 
+static int decode_clone(struct xdr_stream *xdr)
+{
+	return decode_op_hdr(xdr, OP_CLONE);
+}
+
 /*
  * Decode ALLOCATE request
  */
@@ -351,4 +411,39 @@ out:
 	return status;
 }
 
+/*
+ * Decode CLONE request
+ */
+static int nfs4_xdr_dec_clone(struct rpc_rqst *rqstp,
+			      struct xdr_stream *xdr,
+			      struct nfs42_clone_res *res)
+{
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_savefh(xdr);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_clone(xdr);
+	if (status)
+		goto out;
+	status = decode_getfattr(xdr, res->dst_fattr, res->server);
+
+out:
+	res->rpc_status = status;
+	return status;
+}
+
 #endif /* __LINUX_FS_NFS_NFS4_2XDR_H */
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 50cfc4ca7a02..4afdee420d25 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -183,10 +183,12 @@ struct nfs4_state {
 
 
 struct nfs4_exception {
-	long timeout;
-	int retry;
 	struct nfs4_state *state;
 	struct inode *inode;
+	long timeout;
+	unsigned char delay : 1,
+		      recovering : 1,
+		      retry : 1;
 };
 
 struct nfs4_state_recovery_ops {
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 223bedda64ae..10410e8b5853 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -33,7 +33,7 @@ static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion)
 		return ret;
 	idr_preload(GFP_KERNEL);
 	spin_lock(&nn->nfs_client_lock);
-	ret = idr_alloc(&nn->cb_ident_idr, clp, 0, 0, GFP_NOWAIT);
+	ret = idr_alloc(&nn->cb_ident_idr, clp, 1, 0, GFP_NOWAIT);
 	if (ret >= 0)
 		clp->cl_cb_ident = ret;
 	spin_unlock(&nn->nfs_client_lock);
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index b0dbe0abed53..d0390516467c 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -4,8 +4,10 @@
  *  Copyright (C) 1992  Rick Sladkey
  */
 #include <linux/fs.h>
+#include <linux/file.h>
 #include <linux/falloc.h>
 #include <linux/nfs_fs.h>
+#include <uapi/linux/btrfs.h>	/* BTRFS_IOC_CLONE/BTRFS_IOC_CLONE_RANGE */
 #include "delegation.h"
 #include "internal.h"
 #include "iostat.h"
@@ -24,7 +26,7 @@ static int
 nfs4_file_open(struct inode *inode, struct file *filp)
 {
 	struct nfs_open_context *ctx;
-	struct dentry *dentry = filp->f_path.dentry;
+	struct dentry *dentry = file_dentry(filp);
 	struct dentry *parent = NULL;
 	struct inode *dir;
 	unsigned openflags = filp->f_flags;
@@ -55,7 +57,7 @@ nfs4_file_open(struct inode *inode, struct file *filp)
 	parent = dget_parent(dentry);
 	dir = d_inode(parent);
 
-	ctx = alloc_nfs_open_context(filp->f_path.dentry, filp->f_mode);
+	ctx = alloc_nfs_open_context(file_dentry(filp), filp->f_mode);
 	err = PTR_ERR(ctx);
 	if (IS_ERR(ctx))
 		goto out;
@@ -126,37 +128,6 @@ nfs4_file_flush(struct file *file, fl_owner_t id)
 	return vfs_fsync(file, 0);
 }
 
-static int
-nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
-{
-	int ret;
-	struct inode *inode = file_inode(file);
-
-	trace_nfs_fsync_enter(inode);
-
-	nfs_inode_dio_wait(inode);
-	do {
-		ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
-		if (ret != 0)
-			break;
-		mutex_lock(&inode->i_mutex);
-		ret = nfs_file_fsync_commit(file, start, end, datasync);
-		if (!ret)
-			ret = pnfs_sync_inode(inode, !!datasync);
-		mutex_unlock(&inode->i_mutex);
-		/*
-		 * If nfs_file_fsync_commit detected a server reboot, then
-		 * resend all dirty pages that might have been covered by
-		 * the NFS_CONTEXT_RESEND_WRITES flag
-		 */
-		start = 0;
-		end = LLONG_MAX;
-	} while (ret == -EAGAIN);
-
-	trace_nfs_fsync_exit(inode, ret);
-	return ret;
-}
-
 #ifdef CONFIG_NFS_V4_2
 static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence)
 {
@@ -192,28 +163,90 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t
 		return nfs42_proc_deallocate(filep, offset, len);
 	return nfs42_proc_allocate(filep, offset, len);
 }
+
+static int nfs42_clone_file_range(struct file *src_file, loff_t src_off,
+		struct file *dst_file, loff_t dst_off, u64 count)
+{
+	struct inode *dst_inode = file_inode(dst_file);
+	struct nfs_server *server = NFS_SERVER(dst_inode);
+	struct inode *src_inode = file_inode(src_file);
+	unsigned int bs = server->clone_blksize;
+	bool same_inode = false;
+	int ret;
+
+	/* check alignment w.r.t. clone_blksize */
+	ret = -EINVAL;
+	if (bs) {
+		if (!IS_ALIGNED(src_off, bs) || !IS_ALIGNED(dst_off, bs))
+			goto out;
+		if (!IS_ALIGNED(count, bs) && i_size_read(src_inode) != (src_off + count))
+			goto out;
+	}
+
+	if (src_inode == dst_inode)
+		same_inode = true;
+
+	/* XXX: do we lock at all? what if server needs CB_RECALL_LAYOUT? */
+	if (same_inode) {
+		inode_lock(src_inode);
+	} else if (dst_inode < src_inode) {
+		inode_lock_nested(dst_inode, I_MUTEX_PARENT);
+		inode_lock_nested(src_inode, I_MUTEX_CHILD);
+	} else {
+		inode_lock_nested(src_inode, I_MUTEX_PARENT);
+		inode_lock_nested(dst_inode, I_MUTEX_CHILD);
+	}
+
+	/* flush all pending writes on both src and dst so that server
+	 * has the latest data */
+	ret = nfs_sync_inode(src_inode);
+	if (ret)
+		goto out_unlock;
+	ret = nfs_sync_inode(dst_inode);
+	if (ret)
+		goto out_unlock;
+
+	ret = nfs42_proc_clone(src_file, dst_file, src_off, dst_off, count);
+
+	/* truncate inode page cache of the dst range so that future reads can fetch
+	 * new data from server */
+	if (!ret)
+		truncate_inode_pages_range(&dst_inode->i_data, dst_off, dst_off + count - 1);
+
+out_unlock:
+	if (same_inode) {
+		inode_unlock(src_inode);
+	} else if (dst_inode < src_inode) {
+		inode_unlock(src_inode);
+		inode_unlock(dst_inode);
+	} else {
+		inode_unlock(dst_inode);
+		inode_unlock(src_inode);
+	}
+out:
+	return ret;
+}
 #endif /* CONFIG_NFS_V4_2 */
 
 const struct file_operations nfs4_file_operations = {
-#ifdef CONFIG_NFS_V4_2
-	.llseek		= nfs4_file_llseek,
-#else
-	.llseek		= nfs_file_llseek,
-#endif
 	.read_iter	= nfs_file_read,
 	.write_iter	= nfs_file_write,
 	.mmap		= nfs_file_mmap,
 	.open		= nfs4_file_open,
 	.flush		= nfs4_file_flush,
 	.release	= nfs_file_release,
-	.fsync		= nfs4_file_fsync,
+	.fsync		= nfs_file_fsync,
 	.lock		= nfs_lock,
 	.flock		= nfs_flock,
 	.splice_read	= nfs_file_splice_read,
 	.splice_write	= iter_file_splice_write,
-#ifdef CONFIG_NFS_V4_2
-	.fallocate	= nfs42_fallocate,
-#endif /* CONFIG_NFS_V4_2 */
 	.check_flags	= nfs_check_flags,
 	.setlease	= simple_nosetlease,
+#ifdef CONFIG_NFS_V4_2
+	.llseek		= nfs4_file_llseek,
+	.fallocate	= nfs42_fallocate,
+	.clone_file_range = nfs42_clone_file_range,
+#else
+	.llseek		= nfs_file_llseek,
+#endif
 };
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 0e5ff69455c7..327b8c34d360 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -78,7 +78,6 @@ struct nfs4_opendata;
 static int _nfs4_proc_open(struct nfs4_opendata *data);
 static int _nfs4_recover_proc_open(struct nfs4_opendata *data);
 static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *);
-static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *, struct nfs4_state *, long *);
 static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr);
 static int nfs4_proc_getattr(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *label);
 static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label);
@@ -209,6 +208,9 @@ static const u32 nfs4_pnfs_open_bitmap[3] = {
 	| FATTR4_WORD1_TIME_METADATA
 	| FATTR4_WORD1_TIME_MODIFY,
 	FATTR4_WORD2_MDSTHRESHOLD
+#ifdef CONFIG_NFS_V4_SECURITY_LABEL
+	| FATTR4_WORD2_SECURITY_LABEL
+#endif
 };
 
 static const u32 nfs4_open_noattr_bitmap[3] = {
@@ -239,6 +241,7 @@ const u32 nfs4_fsinfo_bitmap[3] = { FATTR4_WORD0_MAXFILESIZE
 			FATTR4_WORD1_TIME_DELTA
 			| FATTR4_WORD1_FS_LAYOUT_TYPES,
 			FATTR4_WORD2_LAYOUT_BLKSIZE
+			| FATTR4_WORD2_CLONE_BLKSIZE
 };
 
 const u32 nfs4_fs_locations_bitmap[3] = {
@@ -344,13 +347,16 @@ static int nfs4_delay(struct rpc_clnt *clnt, long *timeout)
 /* This is the error handling routine for processes that are allowed
  * to sleep.
  */
-int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_exception *exception)
+static int nfs4_do_handle_exception(struct nfs_server *server,
+		int errorcode, struct nfs4_exception *exception)
 {
 	struct nfs_client *clp = server->nfs_client;
 	struct nfs4_state *state = exception->state;
 	struct inode *inode = exception->inode;
 	int ret = errorcode;
 
+	exception->delay = 0;
+	exception->recovering = 0;
 	exception->retry = 0;
 	switch(errorcode) {
 		case 0:
@@ -359,11 +365,9 @@ int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_
 		case -NFS4ERR_DELEG_REVOKED:
 		case -NFS4ERR_ADMIN_REVOKED:
 		case -NFS4ERR_BAD_STATEID:
-			if (inode && nfs4_have_delegation(inode, FMODE_READ)) {
-				nfs4_inode_return_delegation(inode);
-				exception->retry = 1;
-				return 0;
-			}
+			if (inode && nfs_async_inode_return_delegation(inode,
+						NULL) == 0)
+				goto wait_on_recovery;
 			if (state == NULL)
 				break;
 			ret = nfs4_schedule_stateid_recovery(server, state);
@@ -409,11 +413,12 @@ int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_
 				ret = -EBUSY;
 				break;
 			}
-		case -NFS4ERR_GRACE:
 		case -NFS4ERR_DELAY:
-			ret = nfs4_delay(server->client, &exception->timeout);
-			if (ret != 0)
-				break;
+			nfs_inc_server_stats(server, NFSIOS_DELAY);
+		case -NFS4ERR_GRACE:
+			exception->delay = 1;
+			return 0;
+
 		case -NFS4ERR_RETRY_UNCACHED_REP:
 		case -NFS4ERR_OLD_STATEID:
 			exception->retry = 1;
@@ -434,14 +439,85 @@ int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_
 	/* We failed to handle the error */
 	return nfs4_map_errors(ret);
 wait_on_recovery:
-	ret = nfs4_wait_clnt_recover(clp);
+	exception->recovering = 1;
+	return 0;
+}
+
+/* This is the error handling routine for processes that are allowed
+ * to sleep.
+ */
+int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_exception *exception)
+{
+	struct nfs_client *clp = server->nfs_client;
+	int ret;
+
+	ret = nfs4_do_handle_exception(server, errorcode, exception);
+	if (exception->delay) {
+		ret = nfs4_delay(server->client, &exception->timeout);
+		goto out_retry;
+	}
+	if (exception->recovering) {
+		ret = nfs4_wait_clnt_recover(clp);
+		if (test_bit(NFS_MIG_FAILED, &server->mig_status))
+			return -EIO;
+		goto out_retry;
+	}
+	return ret;
+out_retry:
+	if (ret == 0)
+		exception->retry = 1;
+	return ret;
+}
+
+static int
+nfs4_async_handle_exception(struct rpc_task *task, struct nfs_server *server,
+		int errorcode, struct nfs4_exception *exception)
+{
+	struct nfs_client *clp = server->nfs_client;
+	int ret;
+
+	ret = nfs4_do_handle_exception(server, errorcode, exception);
+	if (exception->delay) {
+		rpc_delay(task, nfs4_update_delay(&exception->timeout));
+		goto out_retry;
+	}
+	if (exception->recovering) {
+		rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL);
+		if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0)
+			rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task);
+		goto out_retry;
+	}
 	if (test_bit(NFS_MIG_FAILED, &server->mig_status))
-		return -EIO;
+		ret = -EIO;
+	return ret;
+out_retry:
 	if (ret == 0)
 		exception->retry = 1;
 	return ret;
 }
 
+static int
+nfs4_async_handle_error(struct rpc_task *task, struct nfs_server *server,
+			struct nfs4_state *state, long *timeout)
+{
+	struct nfs4_exception exception = {
+		.state = state,
+	};
+
+	if (task->tk_status >= 0)
+		return 0;
+	if (timeout)
+		exception.timeout = *timeout;
+	task->tk_status = nfs4_async_handle_exception(task, server,
+			task->tk_status,
+			&exception);
+	if (exception.delay && timeout)
+		*timeout = exception.timeout;
+	if (exception.retry)
+		return -EAGAIN;
+	return 0;
+}
+
 /*
  * Return 'true' if 'clp' is using an rpc_client that is integrity protected
  * or 'false' otherwise.
@@ -1312,6 +1388,7 @@ static void __update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_s
 	 * Protect the call to nfs4_state_set_mode_locked and
 	 * serialise the stateid update
 	 */
+	spin_lock(&state->owner->so_lock);
 	write_seqlock(&state->seqlock);
 	if (deleg_stateid != NULL) {
 		nfs4_stateid_copy(&state->stateid, deleg_stateid);
@@ -1320,7 +1397,6 @@ static void __update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_s
 	if (open_stateid != NULL)
 		nfs_set_open_stateid_locked(state, open_stateid, fmode);
 	write_sequnlock(&state->seqlock);
-	spin_lock(&state->owner->so_lock);
 	update_open_stateflags(state, fmode);
 	spin_unlock(&state->owner->so_lock);
 }
@@ -1525,6 +1601,7 @@ _nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data)
 
 	if (!data->rpc_done) {
 		state = nfs4_try_open_cached(data);
+		trace_nfs4_cached_open(data->state);
 		goto out;
 	}
 
@@ -1942,6 +2019,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
 	}
 	return;
 unlock_no_action:
+	trace_nfs4_cached_open(data->state);
 	rcu_read_unlock();
 out_no_action:
 	task->tk_action = NULL;
@@ -2383,14 +2461,15 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 
 	dentry = opendata->dentry;
 	if (d_really_is_negative(dentry)) {
-		/* FIXME: Is this d_drop() ever needed? */
+		struct dentry *alias;
 		d_drop(dentry);
-		dentry = d_add_unique(dentry, igrab(state->inode));
-		if (dentry == NULL) {
-			dentry = opendata->dentry;
-		} else if (dentry != ctx->dentry) {
+		alias = d_exact_alias(dentry, state->inode);
+		if (!alias)
+			alias = d_splice_alias(igrab(state->inode), dentry);
+		/* d_splice_alias() can't fail here - it's a non-directory */
+		if (alias) {
 			dput(ctx->dentry);
-			ctx->dentry = dget(dentry);
+			ctx->dentry = dentry = alias;
 		}
 		nfs_set_verifier(dentry,
 				nfs_save_change_attribute(d_inode(opendata->dir)));
@@ -2630,6 +2709,7 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
 	status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
 	if (status == 0 && state != NULL)
 		renew_lease(server, timestamp);
+	trace_nfs4_setattr(inode, &arg.stateid, status);
 	return status;
 }
 
@@ -2646,7 +2726,6 @@ static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
 	int err;
 	do {
 		err = _nfs4_do_setattr(inode, cred, fattr, sattr, state, ilabel, olabel);
-		trace_nfs4_setattr(inode, err);
 		switch (err) {
 		case -NFS4ERR_OPENMODE:
 			if (!(sattr->ia_valid & ATTR_SIZE)) {
@@ -4530,7 +4609,7 @@ static inline int nfs4_server_supports_acls(struct nfs_server *server)
 #define NFS4ACL_MAXPAGES DIV_ROUND_UP(XATTR_SIZE_MAX, PAGE_SIZE)
 
 static int buf_to_pages_noslab(const void *buf, size_t buflen,
-		struct page **pages, unsigned int *pgbase)
+		struct page **pages)
 {
 	struct page *newpage, **spages;
 	int rc = 0;
@@ -4674,7 +4753,6 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 		goto out_free;
 
 	args.acl_len = npages * PAGE_SIZE;
-	args.acl_pgbase = 0;
 
 	dprintk("%s  buf %p buflen %zu npages %d args.acl_len %zu\n",
 		__func__, buf, buflen, npages, args.acl_len);
@@ -4766,7 +4844,7 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
 		return -EOPNOTSUPP;
 	if (npages > ARRAY_SIZE(pages))
 		return -ERANGE;
-	i = buf_to_pages_noslab(buf, buflen, arg.acl_pages, &arg.acl_pgbase);
+	i = buf_to_pages_noslab(buf, buflen, arg.acl_pages);
 	if (i < 0)
 		return i;
 	nfs4_inode_return_delegation(inode);
@@ -4955,79 +5033,6 @@ out:
 #endif	/* CONFIG_NFS_V4_SECURITY_LABEL */
 
 
-static int
-nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
-			struct nfs4_state *state, long *timeout)
-{
-	struct nfs_client *clp = server->nfs_client;
-
-	if (task->tk_status >= 0)
-		return 0;
-	switch(task->tk_status) {
-		case -NFS4ERR_DELEG_REVOKED:
-		case -NFS4ERR_ADMIN_REVOKED:
-		case -NFS4ERR_BAD_STATEID:
-		case -NFS4ERR_OPENMODE:
-			if (state == NULL)
-				break;
-			if (nfs4_schedule_stateid_recovery(server, state) < 0)
-				goto recovery_failed;
-			goto wait_on_recovery;
-		case -NFS4ERR_EXPIRED:
-			if (state != NULL) {
-				if (nfs4_schedule_stateid_recovery(server, state) < 0)
-					goto recovery_failed;
-			}
-		case -NFS4ERR_STALE_STATEID:
-		case -NFS4ERR_STALE_CLIENTID:
-			nfs4_schedule_lease_recovery(clp);
-			goto wait_on_recovery;
-		case -NFS4ERR_MOVED:
-			if (nfs4_schedule_migration_recovery(server) < 0)
-				goto recovery_failed;
-			goto wait_on_recovery;
-		case -NFS4ERR_LEASE_MOVED:
-			nfs4_schedule_lease_moved_recovery(clp);
-			goto wait_on_recovery;
-#if defined(CONFIG_NFS_V4_1)
-		case -NFS4ERR_BADSESSION:
-		case -NFS4ERR_BADSLOT:
-		case -NFS4ERR_BAD_HIGH_SLOT:
-		case -NFS4ERR_DEADSESSION:
-		case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
-		case -NFS4ERR_SEQ_FALSE_RETRY:
-		case -NFS4ERR_SEQ_MISORDERED:
-			dprintk("%s ERROR %d, Reset session\n", __func__,
-				task->tk_status);
-			nfs4_schedule_session_recovery(clp->cl_session, task->tk_status);
-			goto wait_on_recovery;
-#endif /* CONFIG_NFS_V4_1 */
-		case -NFS4ERR_DELAY:
-			nfs_inc_server_stats(server, NFSIOS_DELAY);
-			rpc_delay(task, nfs4_update_delay(timeout));
-			goto restart_call;
-		case -NFS4ERR_GRACE:
-			rpc_delay(task, NFS4_POLL_RETRY_MAX);
-		case -NFS4ERR_RETRY_UNCACHED_REP:
-		case -NFS4ERR_OLD_STATEID:
-			goto restart_call;
-	}
-	task->tk_status = nfs4_map_errors(task->tk_status);
-	return 0;
-recovery_failed:
-	task->tk_status = -EIO;
-	return 0;
-wait_on_recovery:
-	rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL);
-	if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0)
-		rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task);
-	if (test_bit(NFS_MIG_FAILED, &server->mig_status))
-		goto recovery_failed;
-restart_call:
-	task->tk_status = 0;
-	return -EAGAIN;
-}
-
 static void nfs4_init_boot_verifier(const struct nfs_client *clp,
 				    nfs4_verifier *bootverf)
 {
@@ -5049,7 +5054,6 @@ static void nfs4_init_boot_verifier(const struct nfs_client *clp,
 static int
 nfs4_init_nonuniform_client_string(struct nfs_client *clp)
 {
-	int result;
 	size_t len;
 	char *str;
 
@@ -5077,7 +5081,7 @@ nfs4_init_nonuniform_client_string(struct nfs_client *clp)
 		return -ENOMEM;
 
 	rcu_read_lock();
-	result = scnprintf(str, len, "Linux NFSv4.0 %s/%s %s",
+	scnprintf(str, len, "Linux NFSv4.0 %s/%s %s",
 			clp->cl_ipaddr,
 			rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR),
 			rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_PROTO));
@@ -5090,7 +5094,6 @@ nfs4_init_nonuniform_client_string(struct nfs_client *clp)
 static int
 nfs4_init_uniquifier_client_string(struct nfs_client *clp)
 {
-	int result;
 	size_t len;
 	char *str;
 
@@ -5110,7 +5113,7 @@ nfs4_init_uniquifier_client_string(struct nfs_client *clp)
 	if (!str)
 		return -ENOMEM;
 
-	result = scnprintf(str, len, "Linux NFSv%u.%u %s/%s",
+	scnprintf(str, len, "Linux NFSv%u.%u %s/%s",
 			clp->rpc_ops->version, clp->cl_minorversion,
 			nfs4_client_id_uniquifier,
 			clp->cl_rpcclient->cl_nodename);
@@ -5121,7 +5124,6 @@ nfs4_init_uniquifier_client_string(struct nfs_client *clp)
 static int
 nfs4_init_uniform_client_string(struct nfs_client *clp)
 {
-	int result;
 	size_t len;
 	char *str;
 
@@ -5146,7 +5148,7 @@ nfs4_init_uniform_client_string(struct nfs_client *clp)
 	if (!str)
 		return -ENOMEM;
 
-	result = scnprintf(str, len, "Linux NFSv%u.%u %s",
+	scnprintf(str, len, "Linux NFSv%u.%u %s",
 			clp->rpc_ops->version, clp->cl_minorversion,
 			clp->cl_rpcclient->cl_nodename);
 	clp->cl_owner_id = str;
@@ -5385,6 +5387,11 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co
 	if (data == NULL)
 		return -ENOMEM;
 	nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1);
+
+	nfs4_state_protect(server->nfs_client,
+			NFS_SP4_MACH_CRED_CLEANUP,
+			&task_setup_data.rpc_client, &msg);
+
 	data->args.fhandle = &data->fh;
 	data->args.stateid = &data->stateid;
 	data->args.bitmask = server->cache_consistency_bitmask;
@@ -5427,7 +5434,7 @@ int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4
 	int err;
 	do {
 		err = _nfs4_proc_delegreturn(inode, cred, stateid, issync);
-		trace_nfs4_delegreturn(inode, err);
+		trace_nfs4_delegreturn(inode, stateid, err);
 		switch (err) {
 			case -NFS4ERR_STALE_STATEID:
 			case -NFS4ERR_EXPIRED:
@@ -5522,7 +5529,7 @@ struct nfs4_unlockdata {
 	struct nfs4_lock_state *lsp;
 	struct nfs_open_context *ctx;
 	struct file_lock fl;
-	const struct nfs_server *server;
+	struct nfs_server *server;
 	unsigned long timestamp;
 };
 
@@ -5937,6 +5944,7 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
 		data->cancelled = 1;
 	rpc_put_task(task);
 	dprintk("%s: done, ret = %d!\n", __func__, ret);
+	trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret);
 	return ret;
 }
 
@@ -5953,7 +5961,6 @@ static int nfs4_lock_reclaim(struct nfs4_state *state, struct file_lock *request
 		if (test_bit(NFS_DELEGATED_STATE, &state->flags) != 0)
 			return 0;
 		err = _nfs4_do_setlk(state, F_SETLK, request, NFS_LOCK_RECLAIM);
-		trace_nfs4_lock_reclaim(request, state, F_SETLK, err);
 		if (err != -NFS4ERR_DELAY)
 			break;
 		nfs4_handle_exception(server, err, &exception);
@@ -5980,7 +5987,6 @@ static int nfs4_lock_expired(struct nfs4_state *state, struct file_lock *request
 		if (test_bit(NFS_DELEGATED_STATE, &state->flags) != 0)
 			return 0;
 		err = _nfs4_do_setlk(state, F_SETLK, request, NFS_LOCK_EXPIRED);
-		trace_nfs4_lock_expired(request, state, F_SETLK, err);
 		switch (err) {
 		default:
 			goto out;
@@ -6088,7 +6094,6 @@ static int nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock *
 
 	do {
 		err = _nfs4_proc_setlk(state, cmd, request);
-		trace_nfs4_set_lock(request, state, cmd, err);
 		if (err == -NFS4ERR_DENIED)
 			err = -EAGAIN;
 		err = nfs4_handle_exception(NFS_SERVER(state->inode),
@@ -6249,48 +6254,32 @@ nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_state *lsp)
 
 #define XATTR_NAME_NFSV4_ACL "system.nfs4_acl"
 
-static int nfs4_xattr_set_nfs4_acl(struct dentry *dentry, const char *key,
+static int nfs4_xattr_set_nfs4_acl(const struct xattr_handler *handler,
+				   struct dentry *dentry, const char *key,
 				   const void *buf, size_t buflen,
-				   int flags, int type)
+				   int flags)
 {
-	if (strcmp(key, "") != 0)
-		return -EINVAL;
-
 	return nfs4_proc_set_acl(d_inode(dentry), buf, buflen);
 }
 
-static int nfs4_xattr_get_nfs4_acl(struct dentry *dentry, const char *key,
-				   void *buf, size_t buflen, int type)
+static int nfs4_xattr_get_nfs4_acl(const struct xattr_handler *handler,
+				   struct dentry *dentry, const char *key,
+				   void *buf, size_t buflen)
 {
-	if (strcmp(key, "") != 0)
-		return -EINVAL;
-
 	return nfs4_proc_get_acl(d_inode(dentry), buf, buflen);
 }
 
-static size_t nfs4_xattr_list_nfs4_acl(struct dentry *dentry, char *list,
-				       size_t list_len, const char *name,
-				       size_t name_len, int type)
+static bool nfs4_xattr_list_nfs4_acl(struct dentry *dentry)
 {
-	size_t len = sizeof(XATTR_NAME_NFSV4_ACL);
-
-	if (!nfs4_server_supports_acls(NFS_SERVER(d_inode(dentry))))
-		return 0;
-
-	if (list && len <= list_len)
-		memcpy(list, XATTR_NAME_NFSV4_ACL, len);
-	return len;
+	return nfs4_server_supports_acls(NFS_SERVER(d_inode(dentry)));
 }
 
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
-static inline int nfs4_server_supports_labels(struct nfs_server *server)
-{
-	return server->caps & NFS_CAP_SECURITY_LABEL;
-}
 
-static int nfs4_xattr_set_nfs4_label(struct dentry *dentry, const char *key,
-				   const void *buf, size_t buflen,
-				   int flags, int type)
+static int nfs4_xattr_set_nfs4_label(const struct xattr_handler *handler,
+				     struct dentry *dentry, const char *key,
+				     const void *buf, size_t buflen,
+				     int flags)
 {
 	if (security_ismaclabel(key))
 		return nfs4_set_security_label(dentry, buf, buflen);
@@ -6298,36 +6287,43 @@ static int nfs4_xattr_set_nfs4_label(struct dentry *dentry, const char *key,
 	return -EOPNOTSUPP;
 }
 
-static int nfs4_xattr_get_nfs4_label(struct dentry *dentry, const char *key,
-				   void *buf, size_t buflen, int type)
+static int nfs4_xattr_get_nfs4_label(const struct xattr_handler *handler,
+				     struct dentry *dentry, const char *key,
+				     void *buf, size_t buflen)
 {
 	if (security_ismaclabel(key))
 		return nfs4_get_security_label(d_inode(dentry), buf, buflen);
 	return -EOPNOTSUPP;
 }
 
-static size_t nfs4_xattr_list_nfs4_label(struct dentry *dentry, char *list,
-				       size_t list_len, const char *name,
-				       size_t name_len, int type)
+static ssize_t
+nfs4_listxattr_nfs4_label(struct inode *inode, char *list, size_t list_len)
 {
-	size_t len = 0;
+	int len = 0;
 
-	if (nfs_server_capable(d_inode(dentry), NFS_CAP_SECURITY_LABEL)) {
-		len = security_inode_listsecurity(d_inode(dentry), NULL, 0);
-		if (list && len <= list_len)
-			security_inode_listsecurity(d_inode(dentry), list, len);
+	if (nfs_server_capable(inode, NFS_CAP_SECURITY_LABEL)) {
+		len = security_inode_listsecurity(inode, list, list_len);
+		if (list_len && len > list_len)
+			return -ERANGE;
 	}
 	return len;
 }
 
 static const struct xattr_handler nfs4_xattr_nfs4_label_handler = {
 	.prefix = XATTR_SECURITY_PREFIX,
-	.list	= nfs4_xattr_list_nfs4_label,
 	.get	= nfs4_xattr_get_nfs4_label,
 	.set	= nfs4_xattr_set_nfs4_label,
 };
-#endif
 
+#else
+
+static ssize_t
+nfs4_listxattr_nfs4_label(struct inode *inode, char *list, size_t list_len)
+{
+	return 0;
+}
+
+#endif
 
 /*
  * nfs_fhget will use either the mounted_on_fileid or the fileid
@@ -6787,13 +6783,26 @@ nfs41_same_server_scope(struct nfs41_server_scope *a,
 	return false;
 }
 
+static void
+nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata)
+{
+}
+
+static const struct rpc_call_ops nfs4_bind_one_conn_to_session_ops = {
+	.rpc_call_done =  &nfs4_bind_one_conn_to_session_done,
+};
+
 /*
- * nfs4_proc_bind_conn_to_session()
+ * nfs4_proc_bind_one_conn_to_session()
  *
  * The 4.1 client currently uses the same TCP connection for the
  * fore and backchannel.
  */
-int nfs4_proc_bind_conn_to_session(struct nfs_client *clp, struct rpc_cred *cred)
+static
+int nfs4_proc_bind_one_conn_to_session(struct rpc_clnt *clnt,
+		struct rpc_xprt *xprt,
+		struct nfs_client *clp,
+		struct rpc_cred *cred)
 {
 	int status;
 	struct nfs41_bind_conn_to_session_args args = {
@@ -6808,6 +6817,14 @@ int nfs4_proc_bind_conn_to_session(struct nfs_client *clp, struct rpc_cred *cred
 		.rpc_resp = &res,
 		.rpc_cred = cred,
 	};
+	struct rpc_task_setup task_setup_data = {
+		.rpc_client = clnt,
+		.rpc_xprt = xprt,
+		.callback_ops = &nfs4_bind_one_conn_to_session_ops,
+		.rpc_message = &msg,
+		.flags = RPC_TASK_TIMEOUT,
+	};
+	struct rpc_task *task;
 
 	dprintk("--> %s\n", __func__);
 
@@ -6815,7 +6832,16 @@ int nfs4_proc_bind_conn_to_session(struct nfs_client *clp, struct rpc_cred *cred
 	if (!(clp->cl_session->flags & SESSION4_BACK_CHAN))
 		args.dir = NFS4_CDFC4_FORE;
 
-	status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
+	/* Do not set the backchannel flag unless this is clnt->cl_xprt */
+	if (xprt != rcu_access_pointer(clnt->cl_xprt))
+		args.dir = NFS4_CDFC4_FORE;
+
+	task = rpc_run_task(&task_setup_data);
+	if (!IS_ERR(task)) {
+		status = task->tk_status;
+		rpc_put_task(task);
+	} else
+		status = PTR_ERR(task);
 	trace_nfs4_bind_conn_to_session(clp, status);
 	if (status == 0) {
 		if (memcmp(res.sessionid.data,
@@ -6842,6 +6868,31 @@ out:
 	return status;
 }
 
+struct rpc_bind_conn_calldata {
+	struct nfs_client *clp;
+	struct rpc_cred *cred;
+};
+
+static int
+nfs4_proc_bind_conn_to_session_callback(struct rpc_clnt *clnt,
+		struct rpc_xprt *xprt,
+		void *calldata)
+{
+	struct rpc_bind_conn_calldata *p = calldata;
+
+	return nfs4_proc_bind_one_conn_to_session(clnt, xprt, p->clp, p->cred);
+}
+
+int nfs4_proc_bind_conn_to_session(struct nfs_client *clp, struct rpc_cred *cred)
+{
+	struct rpc_bind_conn_calldata data = {
+		.clp = clp,
+		.cred = cred,
+	};
+	return rpc_clnt_iterate_for_each_xprt(clp->cl_rpcclient,
+			nfs4_proc_bind_conn_to_session_callback, &data);
+}
+
 /*
  * Minimum set of SP4_MACH_CRED operations from RFC 5661 in the enforce map
  * and operations we'd like to see to enable certain features in the allow map
@@ -6857,10 +6908,13 @@ static const struct nfs41_state_protection nfs4_sp4_mach_cred_request = {
 	},
 	.allow.u.words = {
 		[0] = 1 << (OP_CLOSE) |
+		      1 << (OP_OPEN_DOWNGRADE) |
 		      1 << (OP_LOCKU) |
+		      1 << (OP_DELEGRETURN) |
 		      1 << (OP_COMMIT),
 		[1] = 1 << (OP_SECINFO - 32) |
 		      1 << (OP_SECINFO_NO_NAME - 32) |
+		      1 << (OP_LAYOUTRETURN - 32) |
 		      1 << (OP_TEST_STATEID - 32) |
 		      1 << (OP_FREE_STATEID - 32) |
 		      1 << (OP_WRITE - 32)
@@ -6925,11 +6979,19 @@ static int nfs4_sp4_select_mode(struct nfs_client *clp,
 		}
 
 		if (test_bit(OP_CLOSE, sp->allow.u.longs) &&
+		    test_bit(OP_OPEN_DOWNGRADE, sp->allow.u.longs) &&
+		    test_bit(OP_DELEGRETURN, sp->allow.u.longs) &&
 		    test_bit(OP_LOCKU, sp->allow.u.longs)) {
 			dfprintk(MOUNT, "  cleanup mode enabled\n");
 			set_bit(NFS_SP4_MACH_CRED_CLEANUP, &clp->cl_sp4_flags);
 		}
 
+		if (test_bit(OP_LAYOUTRETURN, sp->allow.u.longs)) {
+			dfprintk(MOUNT, "  pnfs cleanup mode enabled\n");
+			set_bit(NFS_SP4_MACH_CRED_PNFS_CLEANUP,
+				&clp->cl_sp4_flags);
+		}
+
 		if (test_bit(OP_SECINFO, sp->allow.u.longs) &&
 		    test_bit(OP_SECINFO_NO_NAME, sp->allow.u.longs)) {
 			dfprintk(MOUNT, "  secinfo mode enabled\n");
@@ -7313,7 +7375,7 @@ static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args)
 	args->bc_attrs.max_resp_sz = PAGE_SIZE;
 	args->bc_attrs.max_resp_sz_cached = 0;
 	args->bc_attrs.max_ops = NFS4_MAX_BACK_CHANNEL_OPS;
-	args->bc_attrs.max_reqs = 1;
+	args->bc_attrs.max_reqs = NFS41_BC_MAX_CALLBACKS;
 
 	dprintk("%s: Back Channel : max_rqst_sz=%u max_resp_sz=%u "
 		"max_resp_sz_cached=%u max_ops=%u max_reqs=%u\n",
@@ -7758,6 +7820,7 @@ nfs4_layoutget_prepare(struct rpc_task *task, void *calldata)
 	struct nfs4_layoutget *lgp = calldata;
 	struct nfs_server *server = NFS_SERVER(lgp->args.inode);
 	struct nfs4_session *session = nfs4_get_session(server);
+	int ret;
 
 	dprintk("--> %s\n", __func__);
 	/* Note the is a race here, where a CB_LAYOUTRECALL can come in
@@ -7768,12 +7831,12 @@ nfs4_layoutget_prepare(struct rpc_task *task, void *calldata)
 	if (nfs41_setup_sequence(session, &lgp->args.seq_args,
 				&lgp->res.seq_res, task))
 		return;
-	if (pnfs_choose_layoutget_stateid(&lgp->args.stateid,
+	ret = pnfs_choose_layoutget_stateid(&lgp->args.stateid,
 					  NFS_I(lgp->args.inode)->layout,
 					  &lgp->args.range,
-					  lgp->args.ctx->state)) {
-		rpc_exit(task, NFS4_OK);
-	}
+					  lgp->args.ctx->state);
+	if (ret < 0)
+		rpc_exit(task, ret);
 }
 
 static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
@@ -7793,6 +7856,15 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 	switch (task->tk_status) {
 	case 0:
 		goto out;
+
+	/*
+	 * NFS4ERR_LAYOUTUNAVAILABLE means we are not supposed to use pnfs
+	 * on the file. set tk_status to -ENODATA to tell upper layer to
+	 * retry go inband.
+	 */
+	case -NFS4ERR_LAYOUTUNAVAILABLE:
+		task->tk_status = -ENODATA;
+		goto out;
 	/*
 	 * NFS4ERR_BADLAYOUT means the MDS cannot return a layout of
 	 * length lgp->args.minlength != 0 (see RFC5661 section 18.43.3).
@@ -7861,7 +7933,7 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 			spin_unlock(&inode->i_lock);
 		goto out_restart;
 	}
-	if (nfs4_async_handle_error(task, server, state, NULL) == -EAGAIN)
+	if (nfs4_async_handle_error(task, server, state, &lgp->timeout) == -EAGAIN)
 		goto out_restart;
 out:
 	dprintk("<-- %s\n", __func__);
@@ -7989,6 +8061,7 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
 	trace_nfs4_layoutget(lgp->args.ctx,
 			&lgp->args.range,
 			&lgp->res.range,
+			&lgp->res.stateid,
 			status);
 	/* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */
 	if (status == 0 && lgp->res.layoutp->len)
@@ -8045,11 +8118,11 @@ static void nfs4_layoutreturn_release(void *calldata)
 
 	dprintk("--> %s\n", __func__);
 	spin_lock(&lo->plh_inode->i_lock);
+	pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range);
+	pnfs_mark_layout_returned_if_empty(lo);
 	if (lrp->res.lrs_present)
 		pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
-	pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range);
 	pnfs_clear_layoutreturn_waitbit(lo);
-	lo->plh_block_lgets--;
 	spin_unlock(&lo->plh_inode->i_lock);
 	pnfs_free_lseg_list(&freeme);
 	pnfs_put_layout_hdr(lrp->args.layout);
@@ -8081,6 +8154,10 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync)
 	};
 	int status = 0;
 
+	nfs4_state_protect(NFS_SERVER(lrp->args.inode)->nfs_client,
+			NFS_SP4_MACH_CRED_PNFS_CLEANUP,
+			&task_setup_data.rpc_client, &msg);
+
 	dprintk("--> %s\n", __func__);
 	if (!sync) {
 		lrp->inode = nfs_igrab_and_active(lrp->args.inode);
@@ -8096,7 +8173,7 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync)
 		return PTR_ERR(task);
 	if (sync)
 		status = task->tk_status;
-	trace_nfs4_layoutreturn(lrp->args.inode, status);
+	trace_nfs4_layoutreturn(lrp->args.inode, &lrp->args.stateid, status);
 	dprintk("<-- %s status=%d\n", __func__, status);
 	rpc_put_task(task);
 	return status;
@@ -8244,7 +8321,7 @@ nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data, bool sync)
 		return PTR_ERR(task);
 	if (sync)
 		status = task->tk_status;
-	trace_nfs4_layoutcommit(data->args.inode, status);
+	trace_nfs4_layoutcommit(data->args.inode, &data->args.stateid, status);
 	dprintk("%s: status %d\n", __func__, status);
 	rpc_put_task(task);
 	return status;
@@ -8718,7 +8795,8 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
 		| NFS_CAP_ALLOCATE
 		| NFS_CAP_DEALLOCATE
 		| NFS_CAP_SEEK
-		| NFS_CAP_LAYOUTSTATS,
+		| NFS_CAP_LAYOUTSTATS
+		| NFS_CAP_CLONE,
 	.init_client = nfs41_init_client,
 	.shutdown_client = nfs41_shutdown_client,
 	.match_stateid = nfs41_match_stateid,
@@ -8743,6 +8821,24 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = {
 #endif
 };
 
+ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size)
+{
+	ssize_t error, error2;
+
+	error = generic_listxattr(dentry, list, size);
+	if (error < 0)
+		return error;
+	if (list) {
+		list += error;
+		size -= error;
+	}
+
+	error2 = nfs4_listxattr_nfs4_label(d_inode(dentry), list, size);
+	if (error2 < 0)
+		return error2;
+	return error + error2;
+}
+
 static const struct inode_operations nfs4_dir_inode_operations = {
 	.create		= nfs_create,
 	.lookup		= nfs_lookup,
@@ -8759,7 +8855,7 @@ static const struct inode_operations nfs4_dir_inode_operations = {
 	.setattr	= nfs_setattr,
 	.getxattr	= generic_getxattr,
 	.setxattr	= generic_setxattr,
-	.listxattr	= generic_listxattr,
+	.listxattr	= nfs4_listxattr,
 	.removexattr	= generic_removexattr,
 };
 
@@ -8769,7 +8865,7 @@ static const struct inode_operations nfs4_file_inode_operations = {
 	.setattr	= nfs_setattr,
 	.getxattr	= generic_getxattr,
 	.setxattr	= generic_setxattr,
-	.listxattr	= generic_listxattr,
+	.listxattr	= nfs4_listxattr,
 	.removexattr	= generic_removexattr,
 };
 
@@ -8828,7 +8924,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 };
 
 static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = {
-	.prefix	= XATTR_NAME_NFSV4_ACL,
+	.name	= XATTR_NAME_NFSV4_ACL,
 	.list	= nfs4_xattr_list_nfs4_acl,
 	.get	= nfs4_xattr_get_nfs4_acl,
 	.set	= nfs4_xattr_set_nfs4_acl,
diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c
index e23366effcfb..332d06e64fa9 100644
--- a/fs/nfs/nfs4session.c
+++ b/fs/nfs/nfs4session.c
@@ -135,6 +135,43 @@ static struct nfs4_slot *nfs4_find_or_create_slot(struct nfs4_slot_table  *tbl,
 	return ERR_PTR(-ENOMEM);
 }
 
+static void nfs4_lock_slot(struct nfs4_slot_table *tbl,
+		struct nfs4_slot *slot)
+{
+	u32 slotid = slot->slot_nr;
+
+	__set_bit(slotid, tbl->used_slots);
+	if (slotid > tbl->highest_used_slotid ||
+	    tbl->highest_used_slotid == NFS4_NO_SLOT)
+		tbl->highest_used_slotid = slotid;
+	slot->generation = tbl->generation;
+}
+
+/*
+ * nfs4_try_to_lock_slot - Given a slot try to allocate it
+ *
+ * Note: must be called with the slot_tbl_lock held.
+ */
+bool nfs4_try_to_lock_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot)
+{
+	if (nfs4_test_locked_slot(tbl, slot->slot_nr))
+		return false;
+	nfs4_lock_slot(tbl, slot);
+	return true;
+}
+
+/*
+ * nfs4_lookup_slot - Find a slot but don't allocate it
+ *
+ * Note: must be called with the slot_tbl_lock held.
+ */
+struct nfs4_slot *nfs4_lookup_slot(struct nfs4_slot_table *tbl, u32 slotid)
+{
+	if (slotid <= tbl->max_slotid)
+		return nfs4_find_or_create_slot(tbl, slotid, 1, GFP_NOWAIT);
+	return ERR_PTR(-E2BIG);
+}
+
 /*
  * nfs4_alloc_slot - efficiently look for a free slot
  *
@@ -153,18 +190,11 @@ struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl)
 		__func__, tbl->used_slots[0], tbl->highest_used_slotid,
 		tbl->max_slotid + 1);
 	slotid = find_first_zero_bit(tbl->used_slots, tbl->max_slotid + 1);
-	if (slotid > tbl->max_slotid)
-		goto out;
-	ret = nfs4_find_or_create_slot(tbl, slotid, 1, GFP_NOWAIT);
-	if (IS_ERR(ret))
-		goto out;
-	__set_bit(slotid, tbl->used_slots);
-	if (slotid > tbl->highest_used_slotid ||
-			tbl->highest_used_slotid == NFS4_NO_SLOT)
-		tbl->highest_used_slotid = slotid;
-	ret->generation = tbl->generation;
-
-out:
+	if (slotid <= tbl->max_slotid) {
+		ret = nfs4_find_or_create_slot(tbl, slotid, 1, GFP_NOWAIT);
+		if (!IS_ERR(ret))
+			nfs4_lock_slot(tbl, ret);
+	}
 	dprintk("<-- %s used_slots=%04lx highest_used=%u slotid=%u\n",
 		__func__, tbl->used_slots[0], tbl->highest_used_slotid,
 		!IS_ERR(ret) ? ret->slot_nr : NFS4_NO_SLOT);
diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h
index e3ea2c5324d6..5b51298d1d03 100644
--- a/fs/nfs/nfs4session.h
+++ b/fs/nfs/nfs4session.h
@@ -77,6 +77,8 @@ extern int nfs4_setup_slot_table(struct nfs4_slot_table *tbl,
 		unsigned int max_reqs, const char *queue);
 extern void nfs4_shutdown_slot_table(struct nfs4_slot_table *tbl);
 extern struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl);
+extern struct nfs4_slot *nfs4_lookup_slot(struct nfs4_slot_table *tbl, u32 slotid);
+extern bool nfs4_try_to_lock_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot);
 extern void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot);
 extern void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl);
 bool nfs41_wake_and_assign_slot(struct nfs4_slot_table *tbl,
@@ -88,6 +90,12 @@ static inline bool nfs4_slot_tbl_draining(struct nfs4_slot_table *tbl)
 	return !!test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state);
 }
 
+static inline bool nfs4_test_locked_slot(const struct nfs4_slot_table *tbl,
+		u32 slotid)
+{
+	return !!test_bit(slotid, tbl->used_slots);
+}
+
 #if defined(CONFIG_NFS_V4_1)
 extern void nfs41_set_target_slotid(struct nfs4_slot_table *tbl,
 		u32 target_highest_slotid);
diff --git a/fs/nfs/nfs4sysctl.c b/fs/nfs/nfs4sysctl.c
index 0fbd3ab1be22..8693d77c45ea 100644
--- a/fs/nfs/nfs4sysctl.c
+++ b/fs/nfs/nfs4sysctl.c
@@ -12,7 +12,7 @@
 #include "nfs4idmap.h"
 #include "callback.h"
 
-static const int nfs_set_port_min = 0;
+static const int nfs_set_port_min;
 static const int nfs_set_port_max = 65535;
 static struct ctl_table_header *nfs4_callback_sysctl_table;
 
diff --git a/fs/nfs/nfs4trace.c b/fs/nfs/nfs4trace.c
index d774335cc8bc..2850bce19244 100644
--- a/fs/nfs/nfs4trace.c
+++ b/fs/nfs/nfs4trace.c
@@ -6,6 +6,7 @@
 #include "internal.h"
 #include "nfs4session.h"
 #include "callback.h"
+#include "pnfs.h"
 
 #define CREATE_TRACE_POINTS
 #include "nfs4trace.h"
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index 671cf68fe56b..2c8d05dae5b1 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -321,6 +321,7 @@ TRACE_EVENT(nfs4_sequence_done,
 			__entry->highest_slotid = res->sr_highest_slotid;
 			__entry->target_highest_slotid =
 					res->sr_target_highest_slotid;
+			__entry->status_flags = res->sr_status_flags;
 			__entry->error = res->sr_status;
 		),
 		TP_printk(
@@ -399,6 +400,10 @@ DECLARE_EVENT_CLASS(nfs4_open_event,
 			__field(u64, fileid)
 			__field(u64, dir)
 			__string(name, ctx->dentry->d_name.name)
+			__field(int, stateid_seq)
+			__field(u32, stateid_hash)
+			__field(int, openstateid_seq)
+			__field(u32, openstateid_hash)
 		),
 
 		TP_fast_assign(
@@ -409,8 +414,22 @@ DECLARE_EVENT_CLASS(nfs4_open_event,
 			__entry->flags = flags;
 			__entry->fmode = (__force unsigned int)ctx->mode;
 			__entry->dev = ctx->dentry->d_sb->s_dev;
-			if (!IS_ERR_OR_NULL(state))
+			if (!IS_ERR_OR_NULL(state)) {
 				inode = state->inode;
+				__entry->stateid_seq =
+					be32_to_cpu(state->stateid.seqid);
+				__entry->stateid_hash =
+					nfs_stateid_hash(&state->stateid);
+				__entry->openstateid_seq =
+					be32_to_cpu(state->open_stateid.seqid);
+				__entry->openstateid_hash =
+					nfs_stateid_hash(&state->open_stateid);
+			} else {
+				__entry->stateid_seq = 0;
+				__entry->stateid_hash = 0;
+				__entry->openstateid_seq = 0;
+				__entry->openstateid_hash = 0;
+			}
 			if (inode != NULL) {
 				__entry->fileid = NFS_FILEID(inode);
 				__entry->fhandle = nfs_fhandle_hash(NFS_FH(inode));
@@ -425,7 +444,8 @@ DECLARE_EVENT_CLASS(nfs4_open_event,
 		TP_printk(
 			"error=%d (%s) flags=%d (%s) fmode=%s "
 			"fileid=%02x:%02x:%llu fhandle=0x%08x "
-			"name=%02x:%02x:%llu/%s",
+			"name=%02x:%02x:%llu/%s stateid=%d:0x%08x "
+			"openstateid=%d:0x%08x",
 			 __entry->error,
 			 show_nfsv4_errors(__entry->error),
 			 __entry->flags,
@@ -436,7 +456,9 @@ DECLARE_EVENT_CLASS(nfs4_open_event,
 			 __entry->fhandle,
 			 MAJOR(__entry->dev), MINOR(__entry->dev),
 			 (unsigned long long)__entry->dir,
-			 __get_str(name)
+			 __get_str(name),
+			 __entry->stateid_seq, __entry->stateid_hash,
+			 __entry->openstateid_seq, __entry->openstateid_hash
 		)
 );
 
@@ -452,6 +474,45 @@ DEFINE_NFS4_OPEN_EVENT(nfs4_open_reclaim);
 DEFINE_NFS4_OPEN_EVENT(nfs4_open_expired);
 DEFINE_NFS4_OPEN_EVENT(nfs4_open_file);
 
+TRACE_EVENT(nfs4_cached_open,
+		TP_PROTO(
+			const struct nfs4_state *state
+		),
+		TP_ARGS(state),
+		TP_STRUCT__entry(
+			__field(dev_t, dev)
+			__field(u32, fhandle)
+			__field(u64, fileid)
+			__field(unsigned int, fmode)
+			__field(int, stateid_seq)
+			__field(u32, stateid_hash)
+		),
+
+		TP_fast_assign(
+			const struct inode *inode = state->inode;
+
+			__entry->dev = inode->i_sb->s_dev;
+			__entry->fileid = NFS_FILEID(inode);
+			__entry->fhandle = nfs_fhandle_hash(NFS_FH(inode));
+			__entry->fmode = (__force unsigned int)state->state;
+			__entry->stateid_seq =
+				be32_to_cpu(state->stateid.seqid);
+			__entry->stateid_hash =
+				nfs_stateid_hash(&state->stateid);
+		),
+
+		TP_printk(
+			"fmode=%s fileid=%02x:%02x:%llu "
+			"fhandle=0x%08x stateid=%d:0x%08x",
+			__entry->fmode ?  show_fmode_flags(__entry->fmode) :
+					  "closed",
+			MAJOR(__entry->dev), MINOR(__entry->dev),
+			(unsigned long long)__entry->fileid,
+			__entry->fhandle,
+			__entry->stateid_seq, __entry->stateid_hash
+		)
+);
+
 TRACE_EVENT(nfs4_close,
 		TP_PROTO(
 			const struct nfs4_state *state,
@@ -468,6 +529,8 @@ TRACE_EVENT(nfs4_close,
 			__field(u64, fileid)
 			__field(unsigned int, fmode)
 			__field(int, error)
+			__field(int, stateid_seq)
+			__field(u32, stateid_hash)
 		),
 
 		TP_fast_assign(
@@ -478,18 +541,23 @@ TRACE_EVENT(nfs4_close,
 			__entry->fhandle = nfs_fhandle_hash(NFS_FH(inode));
 			__entry->fmode = (__force unsigned int)state->state;
 			__entry->error = error;
+			__entry->stateid_seq =
+				be32_to_cpu(args->stateid.seqid);
+			__entry->stateid_hash =
+				nfs_stateid_hash(&args->stateid);
 		),
 
 		TP_printk(
 			"error=%d (%s) fmode=%s fileid=%02x:%02x:%llu "
-			"fhandle=0x%08x",
+			"fhandle=0x%08x openstateid=%d:0x%08x",
 			__entry->error,
 			show_nfsv4_errors(__entry->error),
 			__entry->fmode ?  show_fmode_flags(__entry->fmode) :
 					  "closed",
 			MAJOR(__entry->dev), MINOR(__entry->dev),
 			(unsigned long long)__entry->fileid,
-			__entry->fhandle
+			__entry->fhandle,
+			__entry->stateid_seq, __entry->stateid_hash
 		)
 );
 
@@ -523,6 +591,8 @@ DECLARE_EVENT_CLASS(nfs4_lock_event,
 			__field(dev_t, dev)
 			__field(u32, fhandle)
 			__field(u64, fileid)
+			__field(int, stateid_seq)
+			__field(u32, stateid_hash)
 		),
 
 		TP_fast_assign(
@@ -536,11 +606,16 @@ DECLARE_EVENT_CLASS(nfs4_lock_event,
 			__entry->dev = inode->i_sb->s_dev;
 			__entry->fileid = NFS_FILEID(inode);
 			__entry->fhandle = nfs_fhandle_hash(NFS_FH(inode));
+			__entry->stateid_seq =
+				be32_to_cpu(state->stateid.seqid);
+			__entry->stateid_hash =
+				nfs_stateid_hash(&state->stateid);
 		),
 
 		TP_printk(
 			"error=%d (%s) cmd=%s:%s range=%lld:%lld "
-			"fileid=%02x:%02x:%llu fhandle=0x%08x",
+			"fileid=%02x:%02x:%llu fhandle=0x%08x "
+			"stateid=%d:0x%08x",
 			__entry->error,
 			show_nfsv4_errors(__entry->error),
 			show_lock_cmd(__entry->cmd),
@@ -549,7 +624,8 @@ DECLARE_EVENT_CLASS(nfs4_lock_event,
 			(long long)__entry->end,
 			MAJOR(__entry->dev), MINOR(__entry->dev),
 			(unsigned long long)__entry->fileid,
-			__entry->fhandle
+			__entry->fhandle,
+			__entry->stateid_seq, __entry->stateid_hash
 		)
 );
 
@@ -563,11 +639,73 @@ DECLARE_EVENT_CLASS(nfs4_lock_event,
 			), \
 			TP_ARGS(request, state, cmd, error))
 DEFINE_NFS4_LOCK_EVENT(nfs4_get_lock);
-DEFINE_NFS4_LOCK_EVENT(nfs4_set_lock);
-DEFINE_NFS4_LOCK_EVENT(nfs4_lock_reclaim);
-DEFINE_NFS4_LOCK_EVENT(nfs4_lock_expired);
 DEFINE_NFS4_LOCK_EVENT(nfs4_unlock);
 
+TRACE_EVENT(nfs4_set_lock,
+		TP_PROTO(
+			const struct file_lock *request,
+			const struct nfs4_state *state,
+			const nfs4_stateid *lockstateid,
+			int cmd,
+			int error
+		),
+
+		TP_ARGS(request, state, lockstateid, cmd, error),
+
+		TP_STRUCT__entry(
+			__field(int, error)
+			__field(int, cmd)
+			__field(char, type)
+			__field(loff_t, start)
+			__field(loff_t, end)
+			__field(dev_t, dev)
+			__field(u32, fhandle)
+			__field(u64, fileid)
+			__field(int, stateid_seq)
+			__field(u32, stateid_hash)
+			__field(int, lockstateid_seq)
+			__field(u32, lockstateid_hash)
+		),
+
+		TP_fast_assign(
+			const struct inode *inode = state->inode;
+
+			__entry->error = error;
+			__entry->cmd = cmd;
+			__entry->type = request->fl_type;
+			__entry->start = request->fl_start;
+			__entry->end = request->fl_end;
+			__entry->dev = inode->i_sb->s_dev;
+			__entry->fileid = NFS_FILEID(inode);
+			__entry->fhandle = nfs_fhandle_hash(NFS_FH(inode));
+			__entry->stateid_seq =
+				be32_to_cpu(state->stateid.seqid);
+			__entry->stateid_hash =
+				nfs_stateid_hash(&state->stateid);
+			__entry->lockstateid_seq =
+				be32_to_cpu(lockstateid->seqid);
+			__entry->lockstateid_hash =
+				nfs_stateid_hash(lockstateid);
+		),
+
+		TP_printk(
+			"error=%d (%s) cmd=%s:%s range=%lld:%lld "
+			"fileid=%02x:%02x:%llu fhandle=0x%08x "
+			"stateid=%d:0x%08x lockstateid=%d:0x%08x",
+			__entry->error,
+			show_nfsv4_errors(__entry->error),
+			show_lock_cmd(__entry->cmd),
+			show_lock_type(__entry->type),
+			(long long)__entry->start,
+			(long long)__entry->end,
+			MAJOR(__entry->dev), MINOR(__entry->dev),
+			(unsigned long long)__entry->fileid,
+			__entry->fhandle,
+			__entry->stateid_seq, __entry->stateid_hash,
+			__entry->lockstateid_seq, __entry->lockstateid_hash
+		)
+);
+
 DECLARE_EVENT_CLASS(nfs4_set_delegation_event,
 		TP_PROTO(
 			const struct inode *inode,
@@ -621,20 +759,28 @@ TRACE_EVENT(nfs4_delegreturn_exit,
 			__field(dev_t, dev)
 			__field(u32, fhandle)
 			__field(int, error)
+			__field(int, stateid_seq)
+			__field(u32, stateid_hash)
 		),
 
 		TP_fast_assign(
 			__entry->dev = res->server->s_dev;
 			__entry->fhandle = nfs_fhandle_hash(args->fhandle);
 			__entry->error = error;
+			__entry->stateid_seq =
+				be32_to_cpu(args->stateid->seqid);
+			__entry->stateid_hash =
+				nfs_stateid_hash(args->stateid);
 		),
 
 		TP_printk(
-			"error=%d (%s) dev=%02x:%02x fhandle=0x%08x",
+			"error=%d (%s) dev=%02x:%02x fhandle=0x%08x "
+			"stateid=%d:0x%08x",
 			__entry->error,
 			show_nfsv4_errors(__entry->error),
 			MAJOR(__entry->dev), MINOR(__entry->dev),
-			__entry->fhandle
+			__entry->fhandle,
+			__entry->stateid_seq, __entry->stateid_hash
 		)
 );
 
@@ -653,6 +799,8 @@ DECLARE_EVENT_CLASS(nfs4_test_stateid_event,
 			__field(dev_t, dev)
 			__field(u32, fhandle)
 			__field(u64, fileid)
+			__field(int, stateid_seq)
+			__field(u32, stateid_hash)
 		),
 
 		TP_fast_assign(
@@ -662,15 +810,21 @@ DECLARE_EVENT_CLASS(nfs4_test_stateid_event,
 			__entry->dev = inode->i_sb->s_dev;
 			__entry->fileid = NFS_FILEID(inode);
 			__entry->fhandle = nfs_fhandle_hash(NFS_FH(inode));
+			__entry->stateid_seq =
+				be32_to_cpu(state->stateid.seqid);
+			__entry->stateid_hash =
+				nfs_stateid_hash(&state->stateid);
 		),
 
 		TP_printk(
-			"error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x",
+			"error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
+			"stateid=%d:0x%08x",
 			__entry->error,
 			show_nfsv4_errors(__entry->error),
 			MAJOR(__entry->dev), MINOR(__entry->dev),
 			(unsigned long long)__entry->fileid,
-			__entry->fhandle
+			__entry->fhandle,
+			__entry->stateid_seq, __entry->stateid_hash
 		)
 );
 
@@ -820,7 +974,6 @@ DECLARE_EVENT_CLASS(nfs4_inode_event,
 			), \
 			TP_ARGS(inode, error))
 
-DEFINE_NFS4_INODE_EVENT(nfs4_setattr);
 DEFINE_NFS4_INODE_EVENT(nfs4_access);
 DEFINE_NFS4_INODE_EVENT(nfs4_readlink);
 DEFINE_NFS4_INODE_EVENT(nfs4_readdir);
@@ -830,8 +983,59 @@ DEFINE_NFS4_INODE_EVENT(nfs4_set_acl);
 DEFINE_NFS4_INODE_EVENT(nfs4_get_security_label);
 DEFINE_NFS4_INODE_EVENT(nfs4_set_security_label);
 #endif /* CONFIG_NFS_V4_SECURITY_LABEL */
-DEFINE_NFS4_INODE_EVENT(nfs4_recall_delegation);
-DEFINE_NFS4_INODE_EVENT(nfs4_delegreturn);
+
+DECLARE_EVENT_CLASS(nfs4_inode_stateid_event,
+		TP_PROTO(
+			const struct inode *inode,
+			const nfs4_stateid *stateid,
+			int error
+		),
+
+		TP_ARGS(inode, stateid, error),
+
+		TP_STRUCT__entry(
+			__field(dev_t, dev)
+			__field(u32, fhandle)
+			__field(u64, fileid)
+			__field(int, error)
+			__field(int, stateid_seq)
+			__field(u32, stateid_hash)
+		),
+
+		TP_fast_assign(
+			__entry->dev = inode->i_sb->s_dev;
+			__entry->fileid = NFS_FILEID(inode);
+			__entry->fhandle = nfs_fhandle_hash(NFS_FH(inode));
+			__entry->error = error;
+			__entry->stateid_seq =
+				be32_to_cpu(stateid->seqid);
+			__entry->stateid_hash =
+				nfs_stateid_hash(stateid);
+		),
+
+		TP_printk(
+			"error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
+			"stateid=%d:0x%08x",
+			__entry->error,
+			show_nfsv4_errors(__entry->error),
+			MAJOR(__entry->dev), MINOR(__entry->dev),
+			(unsigned long long)__entry->fileid,
+			__entry->fhandle,
+			__entry->stateid_seq, __entry->stateid_hash
+		)
+);
+
+#define DEFINE_NFS4_INODE_STATEID_EVENT(name) \
+	DEFINE_EVENT(nfs4_inode_stateid_event, name, \
+			TP_PROTO( \
+				const struct inode *inode, \
+				const nfs4_stateid *stateid, \
+				int error \
+			), \
+			TP_ARGS(inode, stateid, error))
+
+DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_setattr);
+DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_delegreturn);
 
 DECLARE_EVENT_CLASS(nfs4_getattr_event,
 		TP_PROTO(
@@ -941,8 +1145,74 @@ DECLARE_EVENT_CLASS(nfs4_inode_callback_event,
 			), \
 			TP_ARGS(clp, fhandle, inode, error))
 DEFINE_NFS4_INODE_CALLBACK_EVENT(nfs4_cb_getattr);
-DEFINE_NFS4_INODE_CALLBACK_EVENT(nfs4_cb_layoutrecall_inode);
 
+DECLARE_EVENT_CLASS(nfs4_inode_stateid_callback_event,
+		TP_PROTO(
+			const struct nfs_client *clp,
+			const struct nfs_fh *fhandle,
+			const struct inode *inode,
+			const nfs4_stateid *stateid,
+			int error
+		),
+
+		TP_ARGS(clp, fhandle, inode, stateid, error),
+
+		TP_STRUCT__entry(
+			__field(int, error)
+			__field(dev_t, dev)
+			__field(u32, fhandle)
+			__field(u64, fileid)
+			__string(dstaddr, clp ?
+				rpc_peeraddr2str(clp->cl_rpcclient,
+					RPC_DISPLAY_ADDR) : "unknown")
+			__field(int, stateid_seq)
+			__field(u32, stateid_hash)
+		),
+
+		TP_fast_assign(
+			__entry->error = error;
+			__entry->fhandle = nfs_fhandle_hash(fhandle);
+			if (inode != NULL) {
+				__entry->fileid = NFS_FILEID(inode);
+				__entry->dev = inode->i_sb->s_dev;
+			} else {
+				__entry->fileid = 0;
+				__entry->dev = 0;
+			}
+			__assign_str(dstaddr, clp ?
+				rpc_peeraddr2str(clp->cl_rpcclient,
+					RPC_DISPLAY_ADDR) : "unknown")
+			__entry->stateid_seq =
+				be32_to_cpu(stateid->seqid);
+			__entry->stateid_hash =
+				nfs_stateid_hash(stateid);
+		),
+
+		TP_printk(
+			"error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
+			"stateid=%d:0x%08x dstaddr=%s",
+			__entry->error,
+			show_nfsv4_errors(__entry->error),
+			MAJOR(__entry->dev), MINOR(__entry->dev),
+			(unsigned long long)__entry->fileid,
+			__entry->fhandle,
+			__entry->stateid_seq, __entry->stateid_hash,
+			__get_str(dstaddr)
+		)
+);
+
+#define DEFINE_NFS4_INODE_STATEID_CALLBACK_EVENT(name) \
+	DEFINE_EVENT(nfs4_inode_stateid_callback_event, name, \
+			TP_PROTO( \
+				const struct nfs_client *clp, \
+				const struct nfs_fh *fhandle, \
+				const struct inode *inode, \
+				const nfs4_stateid *stateid, \
+				int error \
+			), \
+			TP_ARGS(clp, fhandle, inode, stateid, error))
+DEFINE_NFS4_INODE_STATEID_CALLBACK_EVENT(nfs4_cb_recall);
+DEFINE_NFS4_INODE_STATEID_CALLBACK_EVENT(nfs4_cb_layoutrecall_file);
 
 DECLARE_EVENT_CLASS(nfs4_idmap_event,
 		TP_PROTO(
@@ -1005,28 +1275,37 @@ DECLARE_EVENT_CLASS(nfs4_read_event,
 			__field(loff_t, offset)
 			__field(size_t, count)
 			__field(int, error)
+			__field(int, stateid_seq)
+			__field(u32, stateid_hash)
 		),
 
 		TP_fast_assign(
 			const struct inode *inode = hdr->inode;
+			const struct nfs4_state *state =
+				hdr->args.context->state;
 			__entry->dev = inode->i_sb->s_dev;
 			__entry->fileid = NFS_FILEID(inode);
 			__entry->fhandle = nfs_fhandle_hash(NFS_FH(inode));
 			__entry->offset = hdr->args.offset;
 			__entry->count = hdr->args.count;
 			__entry->error = error;
+			__entry->stateid_seq =
+				be32_to_cpu(state->stateid.seqid);
+			__entry->stateid_hash =
+				nfs_stateid_hash(&state->stateid);
 		),
 
 		TP_printk(
 			"error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
-			"offset=%lld count=%zu",
+			"offset=%lld count=%zu stateid=%d:0x%08x",
 			__entry->error,
 			show_nfsv4_errors(__entry->error),
 			MAJOR(__entry->dev), MINOR(__entry->dev),
 			(unsigned long long)__entry->fileid,
 			__entry->fhandle,
 			(long long)__entry->offset,
-			__entry->count
+			__entry->count,
+			__entry->stateid_seq, __entry->stateid_hash
 		)
 );
 #define DEFINE_NFS4_READ_EVENT(name) \
@@ -1056,28 +1335,37 @@ DECLARE_EVENT_CLASS(nfs4_write_event,
 			__field(loff_t, offset)
 			__field(size_t, count)
 			__field(int, error)
+			__field(int, stateid_seq)
+			__field(u32, stateid_hash)
 		),
 
 		TP_fast_assign(
 			const struct inode *inode = hdr->inode;
+			const struct nfs4_state *state =
+				hdr->args.context->state;
 			__entry->dev = inode->i_sb->s_dev;
 			__entry->fileid = NFS_FILEID(inode);
 			__entry->fhandle = nfs_fhandle_hash(NFS_FH(inode));
 			__entry->offset = hdr->args.offset;
 			__entry->count = hdr->args.count;
 			__entry->error = error;
+			__entry->stateid_seq =
+				be32_to_cpu(state->stateid.seqid);
+			__entry->stateid_hash =
+				nfs_stateid_hash(&state->stateid);
 		),
 
 		TP_printk(
 			"error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
-			"offset=%lld count=%zu",
+			"offset=%lld count=%zu stateid=%d:0x%08x",
 			__entry->error,
 			show_nfsv4_errors(__entry->error),
 			MAJOR(__entry->dev), MINOR(__entry->dev),
 			(unsigned long long)__entry->fileid,
 			__entry->fhandle,
 			(long long)__entry->offset,
-			__entry->count
+			__entry->count,
+			__entry->stateid_seq, __entry->stateid_hash
 		)
 );
 
@@ -1154,10 +1442,11 @@ TRACE_EVENT(nfs4_layoutget,
 			const struct nfs_open_context *ctx,
 			const struct pnfs_layout_range *args,
 			const struct pnfs_layout_range *res,
+			const nfs4_stateid *layout_stateid,
 			int error
 		),
 
-		TP_ARGS(ctx, args, res, error),
+		TP_ARGS(ctx, args, res, layout_stateid, error),
 
 		TP_STRUCT__entry(
 			__field(dev_t, dev)
@@ -1167,10 +1456,15 @@ TRACE_EVENT(nfs4_layoutget,
 			__field(u64, offset)
 			__field(u64, count)
 			__field(int, error)
+			__field(int, stateid_seq)
+			__field(u32, stateid_hash)
+			__field(int, layoutstateid_seq)
+			__field(u32, layoutstateid_hash)
 		),
 
 		TP_fast_assign(
 			const struct inode *inode = d_inode(ctx->dentry);
+			const struct nfs4_state *state = ctx->state;
 			__entry->dev = inode->i_sb->s_dev;
 			__entry->fileid = NFS_FILEID(inode);
 			__entry->fhandle = nfs_fhandle_hash(NFS_FH(inode));
@@ -1178,11 +1472,25 @@ TRACE_EVENT(nfs4_layoutget,
 			__entry->offset = args->offset;
 			__entry->count = args->length;
 			__entry->error = error;
+			__entry->stateid_seq =
+				be32_to_cpu(state->stateid.seqid);
+			__entry->stateid_hash =
+				nfs_stateid_hash(&state->stateid);
+			if (!error) {
+				__entry->layoutstateid_seq =
+				be32_to_cpu(layout_stateid->seqid);
+				__entry->layoutstateid_hash =
+				nfs_stateid_hash(layout_stateid);
+			} else {
+				__entry->layoutstateid_seq = 0;
+				__entry->layoutstateid_hash = 0;
+			}
 		),
 
 		TP_printk(
 			"error=%d (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
-			"iomode=%s offset=%llu count=%llu",
+			"iomode=%s offset=%llu count=%llu stateid=%d:0x%08x "
+			"layoutstateid=%d:0x%08x",
 			__entry->error,
 			show_nfsv4_errors(__entry->error),
 			MAJOR(__entry->dev), MINOR(__entry->dev),
@@ -1190,14 +1498,83 @@ TRACE_EVENT(nfs4_layoutget,
 			__entry->fhandle,
 			show_pnfs_iomode(__entry->iomode),
 			(unsigned long long)__entry->offset,
-			(unsigned long long)__entry->count
+			(unsigned long long)__entry->count,
+			__entry->stateid_seq, __entry->stateid_hash,
+			__entry->layoutstateid_seq, __entry->layoutstateid_hash
 		)
 );
 
-DEFINE_NFS4_INODE_EVENT(nfs4_layoutcommit);
-DEFINE_NFS4_INODE_EVENT(nfs4_layoutreturn);
+DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_layoutcommit);
+DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_layoutreturn);
 DEFINE_NFS4_INODE_EVENT(nfs4_layoutreturn_on_close);
 
+#define show_pnfs_update_layout_reason(reason)				\
+	__print_symbolic(reason,					\
+		{ PNFS_UPDATE_LAYOUT_UNKNOWN, "unknown" },		\
+		{ PNFS_UPDATE_LAYOUT_NO_PNFS, "no pnfs" },		\
+		{ PNFS_UPDATE_LAYOUT_RD_ZEROLEN, "read+zerolen" },	\
+		{ PNFS_UPDATE_LAYOUT_MDSTHRESH, "mdsthresh" },		\
+		{ PNFS_UPDATE_LAYOUT_NOMEM, "nomem" },			\
+		{ PNFS_UPDATE_LAYOUT_BULK_RECALL, "bulk recall" },	\
+		{ PNFS_UPDATE_LAYOUT_IO_TEST_FAIL, "io test fail" },	\
+		{ PNFS_UPDATE_LAYOUT_FOUND_CACHED, "found cached" },	\
+		{ PNFS_UPDATE_LAYOUT_RETURN, "layoutreturn" },		\
+		{ PNFS_UPDATE_LAYOUT_BLOCKED, "layouts blocked" },	\
+		{ PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET, "sent layoutget" })
+
+TRACE_EVENT(pnfs_update_layout,
+		TP_PROTO(struct inode *inode,
+			loff_t pos,
+			u64 count,
+			enum pnfs_iomode iomode,
+			struct pnfs_layout_hdr *lo,
+			enum pnfs_update_layout_reason reason
+		),
+		TP_ARGS(inode, pos, count, iomode, lo, reason),
+		TP_STRUCT__entry(
+			__field(dev_t, dev)
+			__field(u64, fileid)
+			__field(u32, fhandle)
+			__field(loff_t, pos)
+			__field(u64, count)
+			__field(enum pnfs_iomode, iomode)
+			__field(int, layoutstateid_seq)
+			__field(u32, layoutstateid_hash)
+			__field(enum pnfs_update_layout_reason, reason)
+		),
+		TP_fast_assign(
+			__entry->dev = inode->i_sb->s_dev;
+			__entry->fileid = NFS_FILEID(inode);
+			__entry->fhandle = nfs_fhandle_hash(NFS_FH(inode));
+			__entry->pos = pos;
+			__entry->count = count;
+			__entry->iomode = iomode;
+			__entry->reason = reason;
+			if (lo != NULL) {
+				__entry->layoutstateid_seq =
+				be32_to_cpu(lo->plh_stateid.seqid);
+				__entry->layoutstateid_hash =
+				nfs_stateid_hash(&lo->plh_stateid);
+			} else {
+				__entry->layoutstateid_seq = 0;
+				__entry->layoutstateid_hash = 0;
+			}
+		),
+		TP_printk(
+			"fileid=%02x:%02x:%llu fhandle=0x%08x "
+			"iomode=%s pos=%llu count=%llu "
+			"layoutstateid=%d:0x%08x (%s)",
+			MAJOR(__entry->dev), MINOR(__entry->dev),
+			(unsigned long long)__entry->fileid,
+			__entry->fhandle,
+			show_pnfs_iomode(__entry->iomode),
+			(unsigned long long)__entry->pos,
+			(unsigned long long)__entry->count,
+			__entry->layoutstateid_seq, __entry->layoutstateid_hash,
+			show_pnfs_update_layout_reason(__entry->reason)
+		)
+);
+
 #endif /* CONFIG_NFS_V4_1 */
 
 #endif /* _TRACE_NFS4_H */
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 788adf3897c7..88474a4fc669 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1659,7 +1659,7 @@ encode_setacl(struct xdr_stream *xdr, struct nfs_setaclargs *arg, struct compoun
 	*p = cpu_to_be32(FATTR4_WORD0_ACL);
 	p = reserve_space(xdr, 4);
 	*p = cpu_to_be32(arg->acl_len);
-	xdr_write_pages(xdr, arg->acl_pages, arg->acl_pgbase, arg->acl_len);
+	xdr_write_pages(xdr, arg->acl_pages, 0, arg->acl_len);
 }
 
 static void
@@ -2491,7 +2491,7 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr,
 	encode_getattr_two(xdr, FATTR4_WORD0_ACL, 0, &hdr);
 
 	xdr_inline_pages(&req->rq_rcv_buf, replen << 2,
-		args->acl_pages, args->acl_pgbase, args->acl_len);
+		args->acl_pages, 0, args->acl_len);
 
 	encode_nops(&hdr);
 }
@@ -3615,6 +3615,7 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st
 	status = 0;
 	if (unlikely(!(bitmap[0] & FATTR4_WORD0_FS_LOCATIONS)))
 		goto out;
+	bitmap[0] &= ~FATTR4_WORD0_FS_LOCATIONS;
 	status = -EIO;
 	/* Ignore borken servers that return unrequested attrs */
 	if (unlikely(res == NULL))
@@ -4375,6 +4376,11 @@ static int decode_statfs(struct xdr_stream *xdr, struct nfs_fsstat *fsstat)
 		goto xdr_error;
 	if ((status = decode_attr_files_total(xdr, bitmap, &fsstat->tfiles)) != 0)
 		goto xdr_error;
+
+	status = -EIO;
+	if (unlikely(bitmap[0]))
+		goto xdr_error;
+
 	if ((status = decode_attr_space_avail(xdr, bitmap, &fsstat->abytes)) != 0)
 		goto xdr_error;
 	if ((status = decode_attr_space_free(xdr, bitmap, &fsstat->fbytes)) != 0)
@@ -4574,6 +4580,10 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
 		goto xdr_error;
 	fattr->valid |= status;
 
+	status = -EIO;
+	if (unlikely(bitmap[0]))
+		goto xdr_error;
+
 	status = decode_attr_mode(xdr, bitmap, &fmode);
 	if (status < 0)
 		goto xdr_error;
@@ -4627,6 +4637,10 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
 		goto xdr_error;
 	fattr->valid |= status;
 
+	status = -EIO;
+	if (unlikely(bitmap[1]))
+		goto xdr_error;
+
 	status = decode_attr_mdsthreshold(xdr, bitmap, fattr->mdsthreshold);
 	if (status < 0)
 		goto xdr_error;
@@ -4764,6 +4778,28 @@ static int decode_attr_layout_blksize(struct xdr_stream *xdr, uint32_t *bitmap,
 	return 0;
 }
 
+/*
+ * The granularity of a CLONE operation.
+ */
+static int decode_attr_clone_blksize(struct xdr_stream *xdr, uint32_t *bitmap,
+				     uint32_t *res)
+{
+	__be32 *p;
+
+	dprintk("%s: bitmap is %x\n", __func__, bitmap[2]);
+	*res = 0;
+	if (bitmap[2] & FATTR4_WORD2_CLONE_BLKSIZE) {
+		p = xdr_inline_decode(xdr, 4);
+		if (unlikely(!p)) {
+			print_overflow_msg(__func__, xdr);
+			return -EIO;
+		}
+		*res = be32_to_cpup(p);
+		bitmap[2] &= ~FATTR4_WORD2_CLONE_BLKSIZE;
+	}
+	return 0;
+}
+
 static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
 {
 	unsigned int savep;
@@ -4789,15 +4825,28 @@ static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
 	if ((status = decode_attr_maxwrite(xdr, bitmap, &fsinfo->wtmax)) != 0)
 		goto xdr_error;
 	fsinfo->wtpref = fsinfo->wtmax;
+
+	status = -EIO;
+	if (unlikely(bitmap[0]))
+		goto xdr_error;
+
 	status = decode_attr_time_delta(xdr, bitmap, &fsinfo->time_delta);
 	if (status != 0)
 		goto xdr_error;
 	status = decode_attr_pnfstype(xdr, bitmap, &fsinfo->layouttype);
 	if (status != 0)
 		goto xdr_error;
+
+	status = -EIO;
+	if (unlikely(bitmap[1]))
+		goto xdr_error;
+
 	status = decode_attr_layout_blksize(xdr, bitmap, &fsinfo->blksize);
 	if (status)
 		goto xdr_error;
+	status = decode_attr_clone_blksize(xdr, bitmap, &fsinfo->clone_blksize);
+	if (status)
+		goto xdr_error;
 
 	status = verify_attr_len(xdr, savep, attrlen);
 xdr_error:
@@ -4952,7 +5001,7 @@ static int decode_space_limit(struct xdr_stream *xdr,
 		blocksize = be32_to_cpup(p);
 		maxsize = (uint64_t)nblocks * (uint64_t)blocksize;
 	}
-	maxsize >>= PAGE_CACHE_SHIFT;
+	maxsize >>= PAGE_SHIFT;
 	*pagemod_limit = min_t(u64, maxsize, ULONG_MAX);
 	return 0;
 out_overflow:
@@ -7465,6 +7514,7 @@ struct rpc_procinfo	nfs4_procedures[] = {
 	PROC(ALLOCATE,		enc_allocate,		dec_allocate),
 	PROC(DEALLOCATE,	enc_deallocate,		dec_deallocate),
 	PROC(LAYOUTSTATS,	enc_layoutstats,	dec_layoutstats),
+	PROC(CLONE,		enc_clone,		dec_clone),
 #endif /* CONFIG_NFS_V4_2 */
 };
 
diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c
index 9bc9f04fb7f6..89a15dbe5efc 100644
--- a/fs/nfs/nfsroot.c
+++ b/fs/nfs/nfsroot.c
@@ -90,7 +90,7 @@
 #define NFS_DEF_OPTIONS		"vers=2,udp,rsize=4096,wsize=4096"
 
 /* Parameters passed from the kernel command line */
-static char nfs_root_parms[256] __initdata = "";
+static char nfs_root_parms[NFS_MAXPATHLEN + 1] __initdata = "";
 
 /* Text-based mount options passed to super.c */
 static char nfs_root_options[256] __initdata = NFS_DEF_OPTIONS;
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 59f838cdc009..9f80a086b612 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -39,7 +39,6 @@
 			{ 1 << NFS_INO_INVALIDATING, "INVALIDATING" }, \
 			{ 1 << NFS_INO_FLUSHING, "FLUSHING" }, \
 			{ 1 << NFS_INO_FSCACHE, "FSCACHE" }, \
-			{ 1 << NFS_INO_COMMIT, "COMMIT" }, \
 			{ 1 << NFS_INO_LAYOUTCOMMIT, "NEED_LAYOUTCOMMIT" }, \
 			{ 1 << NFS_INO_LAYOUTCOMMITTING, "LAYOUTCOMMIT" })
 
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index 5c0c6b58157f..049c1b1f2932 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;
 }
@@ -489,7 +486,7 @@ static void __r4w_put_page(void *priv, struct page *page)
 	dprintk("%s: index=0x%lx\n", __func__,
 		(page == ZERO_PAGE(0)) ? -1UL : page->index);
 	if (ZERO_PAGE(0) != page)
-		page_cache_release(page);
+		put_page(page);
 	return;
 }
 
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index fe3ddd20ff89..1f6db4231057 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -101,53 +101,18 @@ nfs_page_free(struct nfs_page *p)
 	kmem_cache_free(nfs_page_cachep, p);
 }
 
-static void
-nfs_iocounter_inc(struct nfs_io_counter *c)
-{
-	atomic_inc(&c->io_count);
-}
-
-static void
-nfs_iocounter_dec(struct nfs_io_counter *c)
-{
-	if (atomic_dec_and_test(&c->io_count)) {
-		clear_bit(NFS_IO_INPROGRESS, &c->flags);
-		smp_mb__after_atomic();
-		wake_up_bit(&c->flags, NFS_IO_INPROGRESS);
-	}
-}
-
-static int
-__nfs_iocounter_wait(struct nfs_io_counter *c)
-{
-	wait_queue_head_t *wq = bit_waitqueue(&c->flags, NFS_IO_INPROGRESS);
-	DEFINE_WAIT_BIT(q, &c->flags, NFS_IO_INPROGRESS);
-	int ret = 0;
-
-	do {
-		prepare_to_wait(wq, &q.wait, TASK_KILLABLE);
-		set_bit(NFS_IO_INPROGRESS, &c->flags);
-		if (atomic_read(&c->io_count) == 0)
-			break;
-		ret = nfs_wait_bit_killable(&q.key);
-	} while (atomic_read(&c->io_count) != 0 && !ret);
-	finish_wait(wq, &q.wait);
-	return ret;
-}
-
 /**
  * nfs_iocounter_wait - wait for i/o to complete
- * @c: nfs_io_counter to use
+ * @l_ctx: nfs_lock_context with io_counter to use
  *
  * returns -ERESTARTSYS if interrupted by a fatal signal.
  * Otherwise returns 0 once the io_count hits 0.
  */
 int
-nfs_iocounter_wait(struct nfs_io_counter *c)
+nfs_iocounter_wait(struct nfs_lock_context *l_ctx)
 {
-	if (atomic_read(&c->io_count) == 0)
-		return 0;
-	return __nfs_iocounter_wait(c);
+	return wait_on_atomic_t(&l_ctx->io_count, nfs_wait_atomic_killable,
+			TASK_KILLABLE);
 }
 
 /*
@@ -370,14 +335,14 @@ nfs_create_request(struct nfs_open_context *ctx, struct page *page,
 		return ERR_CAST(l_ctx);
 	}
 	req->wb_lock_context = l_ctx;
-	nfs_iocounter_inc(&l_ctx->io_count);
+	atomic_inc(&l_ctx->io_count);
 
 	/* Initialize the request struct. Initially, we assume a
 	 * long write-back delay. This will be adjusted in
 	 * update_nfs_request below if the region is not locked. */
 	req->wb_page    = page;
 	req->wb_index	= page_file_index(page);
-	page_cache_get(page);
+	get_page(page);
 	req->wb_offset  = offset;
 	req->wb_pgbase	= offset;
 	req->wb_bytes   = count;
@@ -427,11 +392,12 @@ static void nfs_clear_request(struct nfs_page *req)
 	struct nfs_lock_context *l_ctx = req->wb_lock_context;
 
 	if (page != NULL) {
-		page_cache_release(page);
+		put_page(page);
 		req->wb_page = NULL;
 	}
 	if (l_ctx != NULL) {
-		nfs_iocounter_dec(&l_ctx->io_count);
+		if (atomic_dec_and_test(&l_ctx->io_count))
+			wake_up_atomic_t(&l_ctx->io_count);
 		nfs_put_lock_context(l_ctx);
 		req->wb_lock_context = NULL;
 	}
@@ -664,22 +630,11 @@ EXPORT_SYMBOL_GPL(nfs_initiate_pgio);
  * @desc: IO descriptor
  * @hdr: pageio header
  */
-static int nfs_pgio_error(struct nfs_pageio_descriptor *desc,
-			  struct nfs_pgio_header *hdr)
+static void nfs_pgio_error(struct nfs_pgio_header *hdr)
 {
-	struct nfs_pgio_mirror *mirror;
-	u32 midx;
-
 	set_bit(NFS_IOHDR_REDO, &hdr->flags);
 	nfs_pgio_data_destroy(hdr);
 	hdr->completion_ops->completion(hdr);
-	/* TODO: Make sure it's right to clean up all mirrors here
-	 *       and not just hdr->pgio_mirror_idx */
-	for (midx = 0; midx < desc->pg_mirror_count; midx++) {
-		mirror = &desc->pg_mirrors[midx];
-		desc->pg_completion_ops->error_cleanup(&mirror->pg_list);
-	}
-	return -ENOMEM;
 }
 
 /**
@@ -800,8 +755,11 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc,
 	unsigned int pagecount, pageused;
 
 	pagecount = nfs_page_array_len(mirror->pg_base, mirror->pg_count);
-	if (!nfs_pgarray_set(&hdr->page_array, pagecount))
-		return nfs_pgio_error(desc, hdr);
+	if (!nfs_pgarray_set(&hdr->page_array, pagecount)) {
+		nfs_pgio_error(hdr);
+		desc->pg_error = -ENOMEM;
+		return desc->pg_error;
+	}
 
 	nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq);
 	pages = hdr->page_array.pagevec;
@@ -819,8 +777,11 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc,
 			*pages++ = last_page = req->wb_page;
 		}
 	}
-	if (WARN_ON_ONCE(pageused != pagecount))
-		return nfs_pgio_error(desc, hdr);
+	if (WARN_ON_ONCE(pageused != pagecount)) {
+		nfs_pgio_error(hdr);
+		desc->pg_error = -EINVAL;
+		return desc->pg_error;
+	}
 
 	if ((desc->pg_ioflags & FLUSH_COND_STABLE) &&
 	    (desc->pg_moreio || nfs_reqs_to_commit(&cinfo)))
@@ -835,18 +796,13 @@ EXPORT_SYMBOL_GPL(nfs_generic_pgio);
 
 static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc)
 {
-	struct nfs_pgio_mirror *mirror;
 	struct nfs_pgio_header *hdr;
 	int ret;
 
-	mirror = nfs_pgio_current_mirror(desc);
-
 	hdr = nfs_pgio_header_alloc(desc->pg_rw_ops);
 	if (!hdr) {
-		/* TODO: make sure this is right with mirroring - or
-		 *       should it back out all mirrors? */
-		desc->pg_completion_ops->error_cleanup(&mirror->pg_list);
-		return -ENOMEM;
+		desc->pg_error = -ENOMEM;
+		return desc->pg_error;
 	}
 	nfs_pgheader_init(desc, hdr, nfs_pgio_header_free);
 	ret = nfs_generic_pgio(desc, hdr);
@@ -874,6 +830,9 @@ static int nfs_pageio_setup_mirroring(struct nfs_pageio_descriptor *pgio,
 
 	mirror_count = pgio->pg_ops->pg_get_mirror_count(pgio, req);
 
+	if (pgio->pg_error < 0)
+		return pgio->pg_error;
+
 	if (!mirror_count || mirror_count > NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX)
 		return -EINVAL;
 
@@ -903,12 +862,6 @@ static void nfs_pageio_cleanup_mirroring(struct nfs_pageio_descriptor *pgio)
 	pgio->pg_mirrors_dynamic = NULL;
 }
 
-static bool nfs_match_open_context(const struct nfs_open_context *ctx1,
-		const struct nfs_open_context *ctx2)
-{
-	return ctx1->cred == ctx2->cred && ctx1->state == ctx2->state;
-}
-
 static bool nfs_match_lock_context(const struct nfs_lock_context *l1,
 		const struct nfs_lock_context *l2)
 {
@@ -951,7 +904,7 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev,
 				return false;
 		} else {
 			if (req->wb_pgbase != 0 ||
-			    prev->wb_pgbase + prev->wb_bytes != PAGE_CACHE_SIZE)
+			    prev->wb_pgbase + prev->wb_bytes != PAGE_SIZE)
 				return false;
 		}
 	}
@@ -982,6 +935,8 @@ static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc,
 	} else {
 		if (desc->pg_ops->pg_init)
 			desc->pg_ops->pg_init(desc, req);
+		if (desc->pg_error < 0)
+			return 0;
 		mirror->pg_base = req->wb_pgbase;
 	}
 	if (!nfs_can_coalesce_requests(prev, req, desc))
@@ -1147,6 +1102,8 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
 	bytes = req->wb_bytes;
 
 	nfs_pageio_setup_mirroring(desc, req);
+	if (desc->pg_error < 0)
+		goto out_failed;
 
 	for (midx = 0; midx < desc->pg_mirror_count; midx++) {
 		if (midx) {
@@ -1163,7 +1120,8 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
 
 			if (IS_ERR(dupreq)) {
 				nfs_page_group_unlock(req);
-				return 0;
+				desc->pg_error = PTR_ERR(dupreq);
+				goto out_failed;
 			}
 
 			nfs_lock_request(dupreq);
@@ -1176,10 +1134,32 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
 		if (nfs_pgio_has_mirroring(desc))
 			desc->pg_mirror_idx = midx;
 		if (!nfs_pageio_add_request_mirror(desc, dupreq))
-			return 0;
+			goto out_failed;
 	}
 
 	return 1;
+
+out_failed:
+	/*
+	 * We might have failed before sending any reqs over wire.
+	 * Clean up rest of the reqs in mirror pg_list.
+	 */
+	if (desc->pg_error) {
+		struct nfs_pgio_mirror *mirror;
+		void (*func)(struct list_head *);
+
+		/* remember fatal errors */
+		if (nfs_error_is_fatal(desc->pg_error))
+			mapping_set_error(desc->pg_inode->i_mapping,
+					  desc->pg_error);
+
+		func = desc->pg_completion_ops->error_cleanup;
+		for (midx = 0; midx < desc->pg_mirror_count; midx++) {
+			mirror = &desc->pg_mirrors[midx];
+			func(&mirror->pg_list);
+		}
+	}
+	return 0;
 }
 
 /*
@@ -1232,7 +1212,7 @@ int nfs_pageio_resend(struct nfs_pageio_descriptor *desc,
 	nfs_pageio_complete(desc);
 	if (!list_empty(&failed)) {
 		list_move(&failed, &hdr->pages);
-		return -EIO;
+		return desc->pg_error < 0 ? desc->pg_error : -EIO;
 	}
 	return 0;
 }
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 8abe27165ad0..89a5ef4df08a 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -52,9 +52,7 @@ static DEFINE_SPINLOCK(pnfs_spinlock);
  */
 static LIST_HEAD(pnfs_modules_tbl);
 
-static int
-pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid,
-		       enum pnfs_iomode iomode, bool sync);
+static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo);
 
 /* Return the registered pnfs layout driver module matching given id */
 static struct pnfs_layoutdriver_type *
@@ -243,6 +241,8 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo)
 {
 	struct inode *inode = lo->plh_inode;
 
+	pnfs_layoutreturn_before_put_layout_hdr(lo);
+
 	if (atomic_dec_and_lock(&lo->plh_refcount, &inode->i_lock)) {
 		if (!list_empty(&lo->plh_segs))
 			WARN_ONCE(1, "NFS: BUG unfreed layout segments.\n");
@@ -252,6 +252,27 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo)
 	}
 }
 
+/*
+ * Mark a pnfs_layout_hdr and all associated layout segments as invalid
+ *
+ * In order to continue using the pnfs_layout_hdr, a full recovery
+ * is required.
+ * Note that caller must hold inode->i_lock.
+ */
+static int
+pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo,
+		struct list_head *lseg_list)
+{
+	struct pnfs_layout_range range = {
+		.iomode = IOMODE_ANY,
+		.offset = 0,
+		.length = NFS4_MAX_UINT64,
+	};
+
+	set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
+	return pnfs_mark_matching_lsegs_invalid(lo, lseg_list, &range);
+}
+
 static int
 pnfs_iomode_to_fail_bit(u32 iomode)
 {
@@ -345,58 +366,6 @@ pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo,
 	rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq);
 }
 
-/* Return true if layoutreturn is needed */
-static bool
-pnfs_layout_need_return(struct pnfs_layout_hdr *lo,
-			struct pnfs_layout_segment *lseg)
-{
-	struct pnfs_layout_segment *s;
-
-	if (!test_and_clear_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags))
-		return false;
-
-	list_for_each_entry(s, &lo->plh_segs, pls_list)
-		if (s != lseg && test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags))
-			return false;
-
-	return true;
-}
-
-static bool
-pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo)
-{
-	if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
-		return false;
-	lo->plh_return_iomode = 0;
-	pnfs_get_layout_hdr(lo);
-	clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags);
-	return true;
-}
-
-static void pnfs_layoutreturn_before_put_lseg(struct pnfs_layout_segment *lseg,
-		struct pnfs_layout_hdr *lo, struct inode *inode)
-{
-	lo = lseg->pls_layout;
-	inode = lo->plh_inode;
-
-	spin_lock(&inode->i_lock);
-	if (pnfs_layout_need_return(lo, lseg)) {
-		nfs4_stateid stateid;
-		enum pnfs_iomode iomode;
-		bool send;
-
-		stateid = lo->plh_stateid;
-		iomode = lo->plh_return_iomode;
-		send = pnfs_prepare_layoutreturn(lo);
-		spin_unlock(&inode->i_lock);
-		if (send) {
-			/* Send an async layoutreturn so we dont deadlock */
-			pnfs_send_layoutreturn(lo, stateid, iomode, false);
-		}
-	} else
-		spin_unlock(&inode->i_lock);
-}
-
 void
 pnfs_put_lseg(struct pnfs_layout_segment *lseg)
 {
@@ -410,15 +379,8 @@ pnfs_put_lseg(struct pnfs_layout_segment *lseg)
 		atomic_read(&lseg->pls_refcount),
 		test_bit(NFS_LSEG_VALID, &lseg->pls_flags));
 
-	/* Handle the case where refcount != 1 */
-	if (atomic_add_unless(&lseg->pls_refcount, -1, 1))
-		return;
-
 	lo = lseg->pls_layout;
 	inode = lo->plh_inode;
-	/* Do we need a layoutreturn? */
-	if (test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags))
-		pnfs_layoutreturn_before_put_lseg(lseg, lo, inode);
 
 	if (atomic_dec_and_lock(&lseg->pls_refcount, &inode->i_lock)) {
 		if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags)) {
@@ -566,10 +528,10 @@ static int mark_lseg_invalid(struct pnfs_layout_segment *lseg,
 int
 pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
 			    struct list_head *tmp_list,
-			    struct pnfs_layout_range *recall_range)
+			    const struct pnfs_layout_range *recall_range)
 {
 	struct pnfs_layout_segment *lseg, *next;
-	int invalid = 0, removed = 0;
+	int remaining = 0;
 
 	dprintk("%s:Begin lo %p\n", __func__, lo);
 
@@ -582,11 +544,11 @@ pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
 				"offset %llu length %llu\n", __func__,
 				lseg, lseg->pls_range.iomode, lseg->pls_range.offset,
 				lseg->pls_range.length);
-			invalid++;
-			removed += mark_lseg_invalid(lseg, tmp_list);
+			if (!mark_lseg_invalid(lseg, tmp_list))
+				remaining++;
 		}
-	dprintk("%s:Return %i\n", __func__, invalid - removed);
-	return invalid - removed;
+	dprintk("%s:Return %i\n", __func__, remaining);
+	return remaining;
 }
 
 /* note free_me must contain lsegs from a single layout_hdr */
@@ -613,12 +575,10 @@ pnfs_destroy_layout(struct nfs_inode *nfsi)
 	spin_lock(&nfsi->vfs_inode.i_lock);
 	lo = nfsi->layout;
 	if (lo) {
-		lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */
-		pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
 		pnfs_get_layout_hdr(lo);
+		pnfs_mark_layout_stateid_invalid(lo, &tmp_list);
 		pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RO_FAILED);
 		pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RW_FAILED);
-		pnfs_clear_retry_layoutget(lo);
 		spin_unlock(&nfsi->vfs_inode.i_lock);
 		pnfs_free_lseg_list(&tmp_list);
 		pnfs_put_layout_hdr(lo);
@@ -677,11 +637,6 @@ pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list,
 {
 	struct pnfs_layout_hdr *lo;
 	struct inode *inode;
-	struct pnfs_layout_range range = {
-		.iomode = IOMODE_ANY,
-		.offset = 0,
-		.length = NFS4_MAX_UINT64,
-	};
 	LIST_HEAD(lseg_list);
 	int ret = 0;
 
@@ -696,13 +651,15 @@ pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list,
 
 		spin_lock(&inode->i_lock);
 		list_del_init(&lo->plh_bulk_destroy);
-		lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */
-		if (is_bulk_recall)
-			set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
-		if (pnfs_mark_matching_lsegs_invalid(lo, &lseg_list, &range))
+		if (pnfs_mark_layout_stateid_invalid(lo, &lseg_list)) {
+			if (is_bulk_recall)
+				set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
 			ret = -EAGAIN;
+		}
 		spin_unlock(&inode->i_lock);
 		pnfs_free_lseg_list(&lseg_list);
+		/* Free all lsegs that are attached to commit buckets */
+		nfs_commit_inode(inode, 0);
 		pnfs_put_layout_hdr(lo);
 		iput(inode);
 	}
@@ -826,7 +783,7 @@ pnfs_layoutgets_blocked(const struct pnfs_layout_hdr *lo)
 
 int
 pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo,
-			      struct pnfs_layout_range *range,
+			      const struct pnfs_layout_range *range,
 			      struct nfs4_state *open_state)
 {
 	int status = 0;
@@ -861,7 +818,7 @@ pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo,
 static struct pnfs_layout_segment *
 send_layoutget(struct pnfs_layout_hdr *lo,
 	   struct nfs_open_context *ctx,
-	   struct pnfs_layout_range *range,
+	   const struct pnfs_layout_range *range,
 	   gfp_t gfp_flags)
 {
 	struct inode *ino = lo->plh_inode;
@@ -872,44 +829,41 @@ send_layoutget(struct pnfs_layout_hdr *lo,
 
 	dprintk("--> %s\n", __func__);
 
-	lgp = kzalloc(sizeof(*lgp), gfp_flags);
-	if (lgp == NULL)
-		return NULL;
-
-	i_size = i_size_read(ino);
-
-	lgp->args.minlength = PAGE_CACHE_SIZE;
-	if (lgp->args.minlength > range->length)
-		lgp->args.minlength = range->length;
-	if (range->iomode == IOMODE_READ) {
-		if (range->offset >= i_size)
-			lgp->args.minlength = 0;
-		else if (i_size - range->offset < lgp->args.minlength)
-			lgp->args.minlength = i_size - range->offset;
-	}
-	lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE;
-	lgp->args.range = *range;
-	lgp->args.type = server->pnfs_curr_ld->id;
-	lgp->args.inode = ino;
-	lgp->args.ctx = get_nfs_open_context(ctx);
-	lgp->gfp_flags = gfp_flags;
-	lgp->cred = lo->plh_lc_cred;
-
-	/* Synchronously retrieve layout information from server and
-	 * store in lseg.
+	/*
+	 * Synchronously retrieve layout information from server and
+	 * store in lseg. If we race with a concurrent seqid morphing
+	 * op, then re-send the LAYOUTGET.
 	 */
-	lseg = nfs4_proc_layoutget(lgp, gfp_flags);
-	if (IS_ERR(lseg)) {
-		switch (PTR_ERR(lseg)) {
-		case -ENOMEM:
-		case -ERESTARTSYS:
-			break;
-		default:
-			/* remember that LAYOUTGET failed and suspend trying */
-			pnfs_layout_io_set_failed(lo, range->iomode);
+	do {
+		lgp = kzalloc(sizeof(*lgp), gfp_flags);
+		if (lgp == NULL)
+			return NULL;
+
+		i_size = i_size_read(ino);
+
+		lgp->args.minlength = PAGE_SIZE;
+		if (lgp->args.minlength > range->length)
+			lgp->args.minlength = range->length;
+		if (range->iomode == IOMODE_READ) {
+			if (range->offset >= i_size)
+				lgp->args.minlength = 0;
+			else if (i_size - range->offset < lgp->args.minlength)
+				lgp->args.minlength = i_size - range->offset;
 		}
-		return NULL;
-	} else
+		lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE;
+		pnfs_copy_range(&lgp->args.range, range);
+		lgp->args.type = server->pnfs_curr_ld->id;
+		lgp->args.inode = ino;
+		lgp->args.ctx = get_nfs_open_context(ctx);
+		lgp->gfp_flags = gfp_flags;
+		lgp->cred = lo->plh_lc_cred;
+
+		lseg = nfs4_proc_layoutget(lgp, gfp_flags);
+	} while (lseg == ERR_PTR(-EAGAIN));
+
+	if (IS_ERR(lseg) && !nfs_error_is_fatal(PTR_ERR(lseg)))
+		lseg = NULL;
+	else
 		pnfs_layout_clear_fail_bit(lo,
 				pnfs_iomode_to_fail_bit(range->iomode));
 
@@ -939,8 +893,19 @@ void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo)
 	rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq);
 }
 
+static bool
+pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo)
+{
+	if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
+		return false;
+	lo->plh_return_iomode = 0;
+	pnfs_get_layout_hdr(lo);
+	clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
+	return true;
+}
+
 static int
-pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid,
+pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, const nfs4_stateid *stateid,
 		       enum pnfs_iomode iomode, bool sync)
 {
 	struct inode *ino = lo->plh_inode;
@@ -957,7 +922,7 @@ pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid,
 		goto out;
 	}
 
-	lrp->args.stateid = stateid;
+	nfs4_stateid_copy(&lrp->args.stateid, stateid);
 	lrp->args.layout_type = NFS_SERVER(ino)->pnfs_curr_ld->id;
 	lrp->args.inode = ino;
 	lrp->args.range.iomode = iomode;
@@ -973,6 +938,48 @@ out:
 	return status;
 }
 
+/* Return true if layoutreturn is needed */
+static bool
+pnfs_layout_need_return(struct pnfs_layout_hdr *lo)
+{
+	struct pnfs_layout_segment *s;
+
+	if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags))
+		return false;
+
+	/* Defer layoutreturn until all lsegs are done */
+	list_for_each_entry(s, &lo->plh_segs, pls_list) {
+		if (test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags))
+			return false;
+	}
+
+	return true;
+}
+
+static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo)
+{
+	struct inode *inode= lo->plh_inode;
+
+	if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags))
+		return;
+	spin_lock(&inode->i_lock);
+	if (pnfs_layout_need_return(lo)) {
+		nfs4_stateid stateid;
+		enum pnfs_iomode iomode;
+		bool send;
+
+		nfs4_stateid_copy(&stateid, &lo->plh_stateid);
+		iomode = lo->plh_return_iomode;
+		send = pnfs_prepare_layoutreturn(lo);
+		spin_unlock(&inode->i_lock);
+		if (send) {
+			/* Send an async layoutreturn so we dont deadlock */
+			pnfs_send_layoutreturn(lo, &stateid, iomode, false);
+		}
+	} else
+		spin_unlock(&inode->i_lock);
+}
+
 /*
  * Initiates a LAYOUTRETURN(FILE), and removes the pnfs_layout_hdr
  * when the layout segment list is empty.
@@ -1000,7 +1007,7 @@ _pnfs_return_layout(struct inode *ino)
 		dprintk("NFS: %s no layout to return\n", __func__);
 		goto out;
 	}
-	stateid = nfsi->layout->plh_stateid;
+	nfs4_stateid_copy(&stateid, &nfsi->layout->plh_stateid);
 	/* Reference matched in nfs4_layoutreturn_release */
 	pnfs_get_layout_hdr(lo);
 	empty = list_empty(&lo->plh_segs);
@@ -1028,7 +1035,7 @@ _pnfs_return_layout(struct inode *ino)
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&tmp_list);
 	if (send)
-		status = pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true);
+		status = pnfs_send_layoutreturn(lo, &stateid, IOMODE_ANY, true);
 out_put_layout_hdr:
 	pnfs_put_layout_hdr(lo);
 out:
@@ -1091,13 +1098,12 @@ bool pnfs_roc(struct inode *ino)
 			goto out_noroc;
 	}
 
-	stateid = lo->plh_stateid;
+	nfs4_stateid_copy(&stateid, &lo->plh_stateid);
 	/* always send layoutreturn if being marked so */
-	if (test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
+	if (test_and_clear_bit(NFS_LAYOUT_RETURN_REQUESTED,
 				   &lo->plh_flags))
 		layoutreturn = pnfs_prepare_layoutreturn(lo);
 
-	pnfs_clear_retry_layoutget(lo);
 	list_for_each_entry_safe(lseg, tmp, &lo->plh_segs, pls_list)
 		/* If we are sending layoutreturn, invalidate all valid lsegs */
 		if (layoutreturn || test_bit(NFS_LSEG_ROC, &lseg->pls_flags)) {
@@ -1119,7 +1125,7 @@ out_noroc:
 	pnfs_free_lseg_list(&tmp_list);
 	pnfs_layoutcommit_inode(ino, true);
 	if (layoutreturn)
-		pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true);
+		pnfs_send_layoutreturn(lo, &stateid, IOMODE_ANY, true);
 	return roc;
 }
 
@@ -1144,6 +1150,7 @@ void pnfs_roc_set_barrier(struct inode *ino, u32 barrier)
 
 	spin_lock(&ino->i_lock);
 	lo = NFS_I(ino)->layout;
+	pnfs_mark_layout_returned_if_empty(lo);
 	if (pnfs_seqid_is_newer(barrier, lo->plh_barrier))
 		lo->plh_barrier = barrier;
 	spin_unlock(&ino->i_lock);
@@ -1460,25 +1467,15 @@ static bool pnfs_within_mdsthreshold(struct nfs_open_context *ctx,
 	return ret;
 }
 
-/* stop waiting if someone clears NFS_LAYOUT_RETRY_LAYOUTGET bit. */
-static int pnfs_layoutget_retry_bit_wait(struct wait_bit_key *key)
-{
-	if (!test_bit(NFS_LAYOUT_RETRY_LAYOUTGET, key->flags))
-		return 1;
-	return nfs_wait_bit_killable(key);
-}
-
 static bool pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo)
 {
-	if (!pnfs_should_retry_layoutget(lo))
-		return false;
 	/*
 	 * send layoutcommit as it can hold up layoutreturn due to lseg
 	 * reference
 	 */
 	pnfs_layoutcommit_inode(lo->plh_inode, false);
 	return !wait_on_bit_action(&lo->plh_flags, NFS_LAYOUT_RETURN,
-				   pnfs_layoutget_retry_bit_wait,
+				   nfs_wait_bit_killable,
 				   TASK_UNINTERRUPTIBLE);
 }
 
@@ -1515,14 +1512,23 @@ pnfs_update_layout(struct inode *ino,
 	struct pnfs_layout_segment *lseg = NULL;
 	bool first;
 
-	if (!pnfs_enabled_sb(NFS_SERVER(ino)))
+	if (!pnfs_enabled_sb(NFS_SERVER(ino))) {
+		trace_pnfs_update_layout(ino, pos, count, iomode, NULL,
+				 PNFS_UPDATE_LAYOUT_NO_PNFS);
 		goto out;
+	}
 
-	if (iomode == IOMODE_READ && i_size_read(ino) == 0)
+	if (iomode == IOMODE_READ && i_size_read(ino) == 0) {
+		trace_pnfs_update_layout(ino, pos, count, iomode, NULL,
+				 PNFS_UPDATE_LAYOUT_RD_ZEROLEN);
 		goto out;
+	}
 
-	if (pnfs_within_mdsthreshold(ctx, ino, iomode))
+	if (pnfs_within_mdsthreshold(ctx, ino, iomode)) {
+		trace_pnfs_update_layout(ino, pos, count, iomode, NULL,
+				 PNFS_UPDATE_LAYOUT_MDSTHRESH);
 		goto out;
+	}
 
 lookup_again:
 	first = false;
@@ -1530,19 +1536,25 @@ lookup_again:
 	lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags);
 	if (lo == NULL) {
 		spin_unlock(&ino->i_lock);
+		trace_pnfs_update_layout(ino, pos, count, iomode, NULL,
+				 PNFS_UPDATE_LAYOUT_NOMEM);
 		goto out;
 	}
 
 	/* Do we even need to bother with this? */
 	if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) {
+		trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+				 PNFS_UPDATE_LAYOUT_BULK_RECALL);
 		dprintk("%s matches recall, use MDS\n", __func__);
 		goto out_unlock;
 	}
 
 	/* if LAYOUTGET already failed once we don't try again */
-	if (pnfs_layout_io_test_failed(lo, iomode) &&
-	    !pnfs_should_retry_layoutget(lo))
+	if (pnfs_layout_io_test_failed(lo, iomode)) {
+		trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+				 PNFS_UPDATE_LAYOUT_IO_TEST_FAIL);
 		goto out_unlock;
+	}
 
 	first = list_empty(&lo->plh_segs);
 	if (first) {
@@ -1562,8 +1574,11 @@ lookup_again:
 		 * already exists
 		 */
 		lseg = pnfs_find_lseg(lo, &arg);
-		if (lseg)
+		if (lseg) {
+			trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+					PNFS_UPDATE_LAYOUT_FOUND_CACHED);
 			goto out_unlock;
+		}
 	}
 
 	/*
@@ -1580,11 +1595,16 @@ lookup_again:
 			dprintk("%s retrying\n", __func__);
 			goto lookup_again;
 		}
+		trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+				PNFS_UPDATE_LAYOUT_RETURN);
 		goto out_put_layout_hdr;
 	}
 
-	if (pnfs_layoutgets_blocked(lo))
+	if (pnfs_layoutgets_blocked(lo)) {
+		trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+				PNFS_UPDATE_LAYOUT_BLOCKED);
 		goto out_unlock;
+	}
 	atomic_inc(&lo->plh_outstanding);
 	spin_unlock(&ino->i_lock);
 
@@ -1598,17 +1618,18 @@ lookup_again:
 		spin_unlock(&clp->cl_lock);
 	}
 
-	pg_offset = arg.offset & ~PAGE_CACHE_MASK;
+	pg_offset = arg.offset & ~PAGE_MASK;
 	if (pg_offset) {
 		arg.offset -= pg_offset;
 		arg.length += pg_offset;
 	}
 	if (arg.length != NFS4_MAX_UINT64)
-		arg.length = PAGE_CACHE_ALIGN(arg.length);
+		arg.length = PAGE_ALIGN(arg.length);
 
 	lseg = send_layoutget(lo, ctx, &arg, gfp_flags);
-	pnfs_clear_retry_layoutget(lo);
 	atomic_dec(&lo->plh_outstanding);
+	trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+				 PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET);
 out_put_layout_hdr:
 	if (first)
 		pnfs_clear_first_layoutget(lo);
@@ -1618,7 +1639,7 @@ out:
 			"(%s, offset: %llu, length: %llu)\n",
 			__func__, ino->i_sb->s_id,
 			(unsigned long long)NFS_FILEID(ino),
-			lseg == NULL ? "not found" : "found",
+			IS_ERR_OR_NULL(lseg) ? "not found" : "found",
 			iomode==IOMODE_RW ?  "read/write" : "read-only",
 			(unsigned long long)pos,
 			(unsigned long long)count);
@@ -1687,6 +1708,7 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
 		/* existing state ID, make sure the sequence number matches. */
 		if (pnfs_layout_stateid_blocked(lo, &res->stateid)) {
 			dprintk("%s forget reply due to sequence\n", __func__);
+			status = -EAGAIN;
 			goto out_forget_reply;
 		}
 		pnfs_set_layout_stateid(lo, &res->stateid, false);
@@ -1724,16 +1746,40 @@ out_forget_reply:
 }
 
 static void
+pnfs_set_plh_return_iomode(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode)
+{
+	if (lo->plh_return_iomode == iomode)
+		return;
+	if (lo->plh_return_iomode != 0)
+		iomode = IOMODE_ANY;
+	lo->plh_return_iomode = iomode;
+	set_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
+}
+
+/**
+ * pnfs_mark_matching_lsegs_return - Free or return matching layout segments
+ * @lo: pointer to layout header
+ * @tmp_list: list header to be used with pnfs_free_lseg_list()
+ * @return_range: describe layout segment ranges to be returned
+ *
+ * This function is mainly intended for use by layoutrecall. It attempts
+ * to free the layout segment immediately, or else to mark it for return
+ * as soon as its reference count drops to zero.
+ */
+int
 pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
 				struct list_head *tmp_list,
-				struct pnfs_layout_range *return_range)
+				const struct pnfs_layout_range *return_range)
 {
 	struct pnfs_layout_segment *lseg, *next;
+	int remaining = 0;
 
 	dprintk("%s:Begin lo %p\n", __func__, lo);
 
 	if (list_empty(&lo->plh_segs))
-		return;
+		return 0;
+
+	assert_spin_locked(&lo->plh_inode->i_lock);
 
 	list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
 		if (should_free_lseg(&lseg->pls_range, return_range)) {
@@ -1742,39 +1788,47 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
 				lseg, lseg->pls_range.iomode,
 				lseg->pls_range.offset,
 				lseg->pls_range.length);
+			if (mark_lseg_invalid(lseg, tmp_list))
+				continue;
+			remaining++;
 			set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags);
-			mark_lseg_invalid(lseg, tmp_list);
-			set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
-					&lo->plh_flags);
+			pnfs_set_plh_return_iomode(lo, return_range->iomode);
 		}
+	return remaining;
 }
 
 void pnfs_error_mark_layout_for_return(struct inode *inode,
 				       struct pnfs_layout_segment *lseg)
 {
 	struct pnfs_layout_hdr *lo = NFS_I(inode)->layout;
-	int iomode = pnfs_iomode_to_fail_bit(lseg->pls_range.iomode);
 	struct pnfs_layout_range range = {
 		.iomode = lseg->pls_range.iomode,
 		.offset = 0,
 		.length = NFS4_MAX_UINT64,
 	};
 	LIST_HEAD(free_me);
+	bool return_now = false;
 
 	spin_lock(&inode->i_lock);
-	/* set failure bit so that pnfs path will be retried later */
-	pnfs_layout_set_fail_bit(lo, iomode);
-	if (lo->plh_return_iomode == 0)
-		lo->plh_return_iomode = range.iomode;
-	else if (lo->plh_return_iomode != range.iomode)
-		lo->plh_return_iomode = IOMODE_ANY;
+	pnfs_set_plh_return_iomode(lo, range.iomode);
 	/*
 	 * mark all matching lsegs so that we are sure to have no live
 	 * segments at hand when sending layoutreturn. See pnfs_put_lseg()
 	 * for how it works.
 	 */
-	pnfs_mark_matching_lsegs_return(lo, &free_me, &range);
-	spin_unlock(&inode->i_lock);
+	if (!pnfs_mark_matching_lsegs_return(lo, &free_me, &range)) {
+		nfs4_stateid stateid;
+		enum pnfs_iomode iomode = lo->plh_return_iomode;
+
+		nfs4_stateid_copy(&stateid, &lo->plh_stateid);
+		return_now = pnfs_prepare_layoutreturn(lo);
+		spin_unlock(&inode->i_lock);
+		if (return_now)
+			pnfs_send_layoutreturn(lo, &stateid, iomode, false);
+	} else {
+		spin_unlock(&inode->i_lock);
+		nfs_commit_inode(inode, 0);
+	}
 	pnfs_free_lseg_list(&free_me);
 }
 EXPORT_SYMBOL_GPL(pnfs_error_mark_layout_for_return);
@@ -1796,6 +1850,11 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r
 						   rd_size,
 						   IOMODE_READ,
 						   GFP_KERNEL);
+		if (IS_ERR(pgio->pg_lseg)) {
+			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
+			pgio->pg_lseg = NULL;
+			return;
+		}
 	}
 	/* If no lseg, fall back to read through mds */
 	if (pgio->pg_lseg == NULL)
@@ -1808,13 +1867,19 @@ void
 pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
 			   struct nfs_page *req, u64 wb_size)
 {
-	if (pgio->pg_lseg == NULL)
+	if (pgio->pg_lseg == NULL) {
 		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 						   req->wb_context,
 						   req_offset(req),
 						   wb_size,
 						   IOMODE_RW,
 						   GFP_NOFS);
+		if (IS_ERR(pgio->pg_lseg)) {
+			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
+			pgio->pg_lseg = NULL;
+			return;
+		}
+	}
 	/* If no lseg, fall back to write through mds */
 	if (pgio->pg_lseg == NULL)
 		nfs_pageio_reset_write_mds(pgio);
@@ -1912,12 +1977,13 @@ static void pnfs_ld_handle_write_error(struct nfs_pgio_header *hdr)
  */
 void pnfs_ld_write_done(struct nfs_pgio_header *hdr)
 {
-	trace_nfs4_pnfs_write(hdr, hdr->pnfs_error);
-	if (!hdr->pnfs_error) {
+	if (likely(!hdr->pnfs_error)) {
 		pnfs_set_layoutcommit(hdr->inode, hdr->lseg,
 				hdr->mds_offset + hdr->res.count);
 		hdr->mds_ops->rpc_call_done(&hdr->task, hdr);
-	} else
+	}
+	trace_nfs4_pnfs_write(hdr, hdr->pnfs_error);
+	if (unlikely(hdr->pnfs_error))
 		pnfs_ld_handle_write_error(hdr);
 	hdr->mds_ops->rpc_release(hdr);
 }
@@ -1981,15 +2047,13 @@ static void pnfs_writehdr_free(struct nfs_pgio_header *hdr)
 int
 pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
 {
-	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
-
 	struct nfs_pgio_header *hdr;
 	int ret;
 
 	hdr = nfs_pgio_header_alloc(desc->pg_rw_ops);
 	if (!hdr) {
-		desc->pg_completion_ops->error_cleanup(&mirror->pg_list);
-		return -ENOMEM;
+		desc->pg_error = -ENOMEM;
+		return desc->pg_error;
 	}
 	nfs_pgheader_init(desc, hdr, pnfs_writehdr_free);
 
@@ -2028,11 +2092,12 @@ static void pnfs_ld_handle_read_error(struct nfs_pgio_header *hdr)
  */
 void pnfs_ld_read_done(struct nfs_pgio_header *hdr)
 {
-	trace_nfs4_pnfs_read(hdr, hdr->pnfs_error);
 	if (likely(!hdr->pnfs_error)) {
 		__nfs4_read_done_cb(hdr);
 		hdr->mds_ops->rpc_call_done(&hdr->task, hdr);
-	} else
+	}
+	trace_nfs4_pnfs_read(hdr, hdr->pnfs_error);
+	if (unlikely(hdr->pnfs_error))
 		pnfs_ld_handle_read_error(hdr);
 	hdr->mds_ops->rpc_release(hdr);
 }
@@ -2111,15 +2176,13 @@ static void pnfs_readhdr_free(struct nfs_pgio_header *hdr)
 int
 pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
 {
-	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
-
 	struct nfs_pgio_header *hdr;
 	int ret;
 
 	hdr = nfs_pgio_header_alloc(desc->pg_rw_ops);
 	if (!hdr) {
-		desc->pg_completion_ops->error_cleanup(&mirror->pg_list);
-		return -ENOMEM;
+		desc->pg_error = -ENOMEM;
+		return desc->pg_error;
 	}
 	nfs_pgheader_init(desc, hdr, pnfs_readhdr_free);
 	hdr->lseg = pnfs_get_lseg(desc->pg_lseg);
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index d1990e90e7a0..1ac1db5f6dad 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -94,11 +94,10 @@ enum {
 	NFS_LAYOUT_RO_FAILED = 0,	/* get ro layout failed stop trying */
 	NFS_LAYOUT_RW_FAILED,		/* get rw layout failed stop trying */
 	NFS_LAYOUT_BULK_RECALL,		/* bulk recall affecting layout */
-	NFS_LAYOUT_RETURN,		/* Return this layout ASAP */
-	NFS_LAYOUT_RETURN_BEFORE_CLOSE,	/* Return this layout before close */
+	NFS_LAYOUT_RETURN,		/* layoutreturn in progress */
+	NFS_LAYOUT_RETURN_REQUESTED,	/* Return this layout ASAP */
 	NFS_LAYOUT_INVALID_STID,	/* layout stateid id is invalid */
 	NFS_LAYOUT_FIRST_LAYOUTGET,	/* Serialize first layoutget */
-	NFS_LAYOUT_RETRY_LAYOUTGET,	/* Retry layoutget */
 };
 
 enum layoutdriver_policy_flags {
@@ -261,11 +260,14 @@ void pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo,
 			     bool update_barrier);
 int pnfs_choose_layoutget_stateid(nfs4_stateid *dst,
 				  struct pnfs_layout_hdr *lo,
-				  struct pnfs_layout_range *range,
+				  const struct pnfs_layout_range *range,
 				  struct nfs4_state *open_state);
 int pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
 				struct list_head *tmp_list,
-				struct pnfs_layout_range *recall_range);
+				const struct pnfs_layout_range *recall_range);
+int pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
+				struct list_head *tmp_list,
+				const struct pnfs_layout_range *recall_range);
 bool pnfs_roc(struct inode *ino);
 void pnfs_roc_release(struct inode *ino);
 void pnfs_roc_set_barrier(struct inode *ino, u32 barrier);
@@ -379,26 +381,6 @@ nfs4_get_deviceid(struct nfs4_deviceid_node *d)
 	return d;
 }
 
-static inline void pnfs_set_retry_layoutget(struct pnfs_layout_hdr *lo)
-{
-	if (!test_and_set_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags))
-		atomic_inc(&lo->plh_refcount);
-}
-
-static inline void pnfs_clear_retry_layoutget(struct pnfs_layout_hdr *lo)
-{
-	if (test_and_clear_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags)) {
-		atomic_dec(&lo->plh_refcount);
-		/* wake up waiters for LAYOUTRETURN as that is not needed */
-		wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN);
-	}
-}
-
-static inline bool pnfs_should_retry_layoutget(struct pnfs_layout_hdr *lo)
-{
-	return test_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags);
-}
-
 static inline struct pnfs_layout_segment *
 pnfs_get_lseg(struct pnfs_layout_segment *lseg)
 {
@@ -409,6 +391,12 @@ pnfs_get_lseg(struct pnfs_layout_segment *lseg)
 	return lseg;
 }
 
+static inline bool
+pnfs_is_valid_lseg(struct pnfs_layout_segment *lseg)
+{
+	return test_bit(NFS_LSEG_VALID, &lseg->pls_flags) != 0;
+}
+
 /* Return true if a layout driver is being used for this mountpoint */
 static inline int pnfs_enabled_sb(struct nfs_server *nfss)
 {
@@ -556,6 +544,26 @@ pnfs_calc_offset_length(u64 offset, u64 end)
 	return 1 + end - offset;
 }
 
+/**
+ * pnfs_mark_layout_returned_if_empty - marks the layout as returned
+ * @lo: layout header
+ *
+ * Note: Caller must hold inode->i_lock
+ */
+static inline void
+pnfs_mark_layout_returned_if_empty(struct pnfs_layout_hdr *lo)
+{
+	if (list_empty(&lo->plh_segs))
+		set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
+}
+
+static inline void
+pnfs_copy_range(struct pnfs_layout_range *dst,
+		const struct pnfs_layout_range *src)
+{
+	memcpy(dst, src, sizeof(*dst));
+}
+
 extern unsigned int layoutstats_timer;
 
 #ifdef NFS_DEBUG
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index 24655b807d44..4aaed890048f 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -266,17 +266,14 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
 		} else {
 			nfs_retry_commit(mds_pages, NULL, cinfo, 0);
 			pnfs_generic_retry_commit(cinfo, 0);
-			cinfo->completion_ops->error_cleanup(NFS_I(inode));
 			return -ENOMEM;
 		}
 	}
 
 	nreq += pnfs_generic_alloc_ds_commits(cinfo, &list);
 
-	if (nreq == 0) {
-		cinfo->completion_ops->error_cleanup(NFS_I(inode));
+	if (nreq == 0)
 		goto out;
-	}
 
 	atomic_add(nreq, &cinfo->mds->rpcs_out);
 
@@ -609,12 +606,22 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv,
 		dprintk("%s: DS %s: trying address %s\n",
 			__func__, ds->ds_remotestr, da->da_remotestr);
 
-		clp = get_v3_ds_connect(mds_srv->nfs_client,
+		if (!IS_ERR(clp)) {
+			struct xprt_create xprt_args = {
+				.ident = XPRT_TRANSPORT_TCP,
+				.net = clp->cl_net,
+				.dstaddr = (struct sockaddr *)&da->da_addr,
+				.addrlen = da->da_addrlen,
+				.servername = clp->cl_hostname,
+			};
+			/* Add this address as an alias */
+			rpc_clnt_add_xprt(clp->cl_rpcclient, &xprt_args,
+					rpc_clnt_test_and_add_xprt, NULL);
+		} else
+			clp = get_v3_ds_connect(mds_srv->nfs_client,
 					(struct sockaddr *)&da->da_addr,
 					da->da_addrlen, IPPROTO_TCP,
 					timeo, retrans, au_flavor);
-		if (!IS_ERR(clp))
-			break;
 	}
 
 	if (IS_ERR(clp)) {
@@ -871,6 +878,11 @@ pnfs_layout_mark_request_commit(struct nfs_page *req,
 	buckets = cinfo->ds->buckets;
 	list = &buckets[ds_commit_idx].written;
 	if (list_empty(list)) {
+		if (!pnfs_is_valid_lseg(lseg)) {
+			spin_unlock(cinfo->lock);
+			cinfo->completion_ops->resched_write(cinfo, req);
+			return;
+		}
 		/* Non-empty buckets hold a reference on the lseg.  That ref
 		 * is normally transferred to the COMMIT call and released
 		 * there.  It could also be released if the last req is pulled
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 01b8cc8e8cfc..6776d7a7839e 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -46,7 +46,7 @@ static void nfs_readhdr_free(struct nfs_pgio_header *rhdr)
 static
 int nfs_return_empty_page(struct page *page)
 {
-	zero_user(page, 0, PAGE_CACHE_SIZE);
+	zero_user(page, 0, PAGE_SIZE);
 	SetPageUptodate(page);
 	unlock_page(page);
 	return 0;
@@ -85,6 +85,23 @@ void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio)
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds);
 
+static void nfs_readpage_release(struct nfs_page *req)
+{
+	struct inode *inode = d_inode(req->wb_context->dentry);
+
+	dprintk("NFS: read done (%s/%llu %d@%lld)\n", inode->i_sb->s_id,
+		(unsigned long long)NFS_FILEID(inode), req->wb_bytes,
+		(long long)req_offset(req));
+
+	if (nfs_page_group_sync_on_bit(req, PG_UNLOCKPAGE)) {
+		if (PageUptodate(req->wb_page))
+			nfs_readpage_to_fscache(inode, req->wb_page, 0);
+
+		unlock_page(req->wb_page);
+	}
+	nfs_release_request(req);
+}
+
 int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 		       struct page *page)
 {
@@ -101,12 +118,15 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 		unlock_page(page);
 		return PTR_ERR(new);
 	}
-	if (len < PAGE_CACHE_SIZE)
-		zero_user_segment(page, len, PAGE_CACHE_SIZE);
+	if (len < PAGE_SIZE)
+		zero_user_segment(page, len, PAGE_SIZE);
 
 	nfs_pageio_init_read(&pgio, inode, false,
 			     &nfs_async_read_completion_ops);
-	nfs_pageio_add_request(&pgio, new);
+	if (!nfs_pageio_add_request(&pgio, new)) {
+		nfs_list_remove_request(new);
+		nfs_readpage_release(new);
+	}
 	nfs_pageio_complete(&pgio);
 
 	/* It doesn't make sense to do mirrored reads! */
@@ -115,24 +135,7 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 	pgm = &pgio.pg_mirrors[0];
 	NFS_I(inode)->read_io += pgm->pg_bytes_written;
 
-	return 0;
-}
-
-static void nfs_readpage_release(struct nfs_page *req)
-{
-	struct inode *inode = d_inode(req->wb_context->dentry);
-
-	dprintk("NFS: read done (%s/%llu %d@%lld)\n", inode->i_sb->s_id,
-		(unsigned long long)NFS_FILEID(inode), req->wb_bytes,
-		(long long)req_offset(req));
-
-	if (nfs_page_group_sync_on_bit(req, PG_UNLOCKPAGE)) {
-		if (PageUptodate(req->wb_page))
-			nfs_readpage_to_fscache(inode, req->wb_page, 0);
-
-		unlock_page(req->wb_page);
-	}
-	nfs_release_request(req);
+	return pgio.pg_error < 0 ? pgio.pg_error : 0;
 }
 
 static void nfs_page_group_set_uptodate(struct nfs_page *req)
@@ -246,6 +249,13 @@ static void nfs_readpage_retry(struct rpc_task *task,
 		nfs_set_pgio_error(hdr, -EIO, argp->offset);
 		return;
 	}
+
+	/* For non rpc-based layout drivers, retry-through-MDS */
+	if (!task->tk_ops) {
+		hdr->pnfs_error = -EAGAIN;
+		return;
+	}
+
 	/* Yes, so retry the read at the end of the hdr */
 	hdr->mds_offset += resp->count;
 	argp->offset += resp->count;
@@ -268,7 +278,7 @@ static void nfs_readpage_result(struct rpc_task *task,
 			hdr->good_bytes = bound - hdr->io_start;
 		}
 		spin_unlock(&hdr->lock);
-	} else if (hdr->res.count != hdr->args.count)
+	} else if (hdr->res.count < hdr->args.count)
 		nfs_readpage_retry(task, hdr);
 }
 
@@ -285,7 +295,7 @@ int nfs_readpage(struct file *file, struct page *page)
 	int		error;
 
 	dprintk("NFS: nfs_readpage (%p %ld@%lu)\n",
-		page, PAGE_CACHE_SIZE, page_file_index(page));
+		page, PAGE_SIZE, page_file_index(page));
 	nfs_inc_stats(inode, NFSIOS_VFSREADPAGE);
 	nfs_add_stats(inode, NFSIOS_READPAGES, 1);
 
@@ -351,9 +361,11 @@ readpage_async_filler(void *data, struct page *page)
 	if (IS_ERR(new))
 		goto out_error;
 
-	if (len < PAGE_CACHE_SIZE)
-		zero_user_segment(page, len, PAGE_CACHE_SIZE);
+	if (len < PAGE_SIZE)
+		zero_user_segment(page, len, PAGE_SIZE);
 	if (!nfs_pageio_add_request(desc->pgio, new)) {
+		nfs_list_remove_request(new);
+		nfs_readpage_release(new);
 		error = desc->pgio->pg_error;
 		goto out_unlock;
 	}
@@ -412,8 +424,8 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 
 	pgm = &pgio.pg_mirrors[0];
 	NFS_I(inode)->read_io += pgm->pg_bytes_written;
-	npages = (pgm->pg_bytes_written + PAGE_CACHE_SIZE - 1) >>
-		 PAGE_CACHE_SHIFT;
+	npages = (pgm->pg_bytes_written + PAGE_SIZE - 1) >>
+		 PAGE_SHIFT;
 	nfs_add_stats(inode, NFSIOS_READPAGES, npages);
 read_complete:
 	put_nfs_open_context(desc.ctx);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 383a027de452..f1268280244e 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2816,7 +2816,6 @@ out_invalid_transport_udp:
  * NFS client for backwards compatibility
  */
 unsigned int nfs_callback_set_tcpport;
-unsigned short nfs_callback_tcpport;
 /* Default cache timeout is 10 minutes */
 unsigned int nfs_idmap_cache_timeout = 600;
 /* Turn off NFSv4 uid/gid mapping when using AUTH_SYS */
@@ -2827,7 +2826,6 @@ char nfs4_client_id_uniquifier[NFS4_CLIENT_ID_UNIQ_LEN] = "";
 bool recover_lost_locks = false;
 
 EXPORT_SYMBOL_GPL(nfs_callback_set_tcpport);
-EXPORT_SYMBOL_GPL(nfs_callback_tcpport);
 EXPORT_SYMBOL_GPL(nfs_idmap_cache_timeout);
 EXPORT_SYMBOL_GPL(nfs4_disable_idmapping);
 EXPORT_SYMBOL_GPL(max_session_slots);
diff --git a/fs/nfs/symlink.c b/fs/nfs/symlink.c
index b6de433da5db..4fe3eead3868 100644
--- a/fs/nfs/symlink.c
+++ b/fs/nfs/symlink.c
@@ -42,21 +42,35 @@ error:
 	return -EIO;
 }
 
-static const char *nfs_follow_link(struct dentry *dentry, void **cookie)
+static const char *nfs_get_link(struct dentry *dentry,
+				struct inode *inode,
+				struct delayed_call *done)
 {
-	struct inode *inode = d_inode(dentry);
 	struct page *page;
 	void *err;
 
-	err = ERR_PTR(nfs_revalidate_mapping(inode, inode->i_mapping));
-	if (err)
-		return err;
-	page = read_cache_page(&inode->i_data, 0,
-				(filler_t *)nfs_symlink_filler, inode);
-	if (IS_ERR(page))
-		return ERR_CAST(page);
-	*cookie = page;
-	return kmap(page);
+	if (!dentry) {
+		err = ERR_PTR(nfs_revalidate_mapping_rcu(inode));
+		if (err)
+			return err;
+		page = find_get_page(inode->i_mapping, 0);
+		if (!page)
+			return ERR_PTR(-ECHILD);
+		if (!PageUptodate(page)) {
+			put_page(page);
+			return ERR_PTR(-ECHILD);
+		}
+	} else {
+		err = ERR_PTR(nfs_revalidate_mapping(inode, inode->i_mapping));
+		if (err)
+			return err;
+		page = read_cache_page(&inode->i_data, 0,
+					(filler_t *)nfs_symlink_filler, inode);
+		if (IS_ERR(page))
+			return ERR_CAST(page);
+	}
+	set_delayed_call(done, page_put_link, page);
+	return page_address(page);
 }
 
 /*
@@ -64,8 +78,7 @@ static const char *nfs_follow_link(struct dentry *dentry, void **cookie)
  */
 const struct inode_operations nfs_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= nfs_follow_link,
-	.put_link	= page_put_link,
+	.get_link	= nfs_get_link,
 	.getattr	= nfs_getattr,
 	.setattr	= nfs_setattr,
 };
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 75ab7622e0cc..5f4fd53e5764 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -21,6 +21,8 @@
 #include <linux/nfs_page.h>
 #include <linux/backing-dev.h>
 #include <linux/export.h>
+#include <linux/freezer.h>
+#include <linux/wait.h>
 
 #include <asm/uaccess.h>
 
@@ -148,7 +150,7 @@ static void nfs_grow_file(struct page *page, unsigned int offset, unsigned int c
 
 	spin_lock(&inode->i_lock);
 	i_size = i_size_read(inode);
-	end_index = (i_size - 1) >> PAGE_CACHE_SHIFT;
+	end_index = (i_size - 1) >> PAGE_SHIFT;
 	if (i_size > 0 && page_file_index(page) < end_index)
 		goto out;
 	end = page_file_offset(page) + ((loff_t)offset+count);
@@ -244,11 +246,9 @@ static int wb_priority(struct writeback_control *wbc)
 {
 	int ret = 0;
 	if (wbc->for_reclaim)
-		return FLUSH_HIGHPRI | FLUSH_STABLE;
+		return FLUSH_HIGHPRI | FLUSH_COND_STABLE;
 	if (wbc->sync_mode == WB_SYNC_ALL)
 		ret = FLUSH_COND_STABLE;
-	if (wbc->for_kupdate || wbc->for_background)
-		ret |= FLUSH_LOWPRI;
 	return ret;
 }
 
@@ -545,12 +545,22 @@ try_again:
 	return head;
 }
 
+static void nfs_write_error_remove_page(struct nfs_page *req)
+{
+	nfs_unlock_request(req);
+	nfs_end_page_writeback(req);
+	nfs_release_request(req);
+	generic_error_remove_page(page_file_mapping(req->wb_page),
+				  req->wb_page);
+}
+
 /*
  * Find an associated nfs write request, and prepare to flush it out
  * May return an error if the user signalled nfs_wait_on_request().
  */
 static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
-				struct page *page, bool nonblock)
+				struct page *page, bool nonblock,
+				bool launder)
 {
 	struct nfs_page *req;
 	int ret = 0;
@@ -567,8 +577,21 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
 
 	ret = 0;
 	if (!nfs_pageio_add_request(pgio, req)) {
-		nfs_redirty_request(req);
 		ret = pgio->pg_error;
+		/*
+		 * Remove the problematic req upon fatal errors
+		 * in launder case, while other dirty pages can
+		 * still be around until they get flushed.
+		 */
+		if (nfs_error_is_fatal(ret)) {
+			nfs_context_set_write_error(req->wb_context, ret);
+			if (launder) {
+				nfs_write_error_remove_page(req);
+				goto out;
+			}
+		}
+		nfs_redirty_request(req);
+		ret = -EAGAIN;
 	} else
 		nfs_add_stats(page_file_mapping(page)->host,
 				NFSIOS_WRITEPAGES, 1);
@@ -576,12 +599,14 @@ out:
 	return ret;
 }
 
-static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio)
+static int nfs_do_writepage(struct page *page, struct writeback_control *wbc,
+			    struct nfs_pageio_descriptor *pgio, bool launder)
 {
 	int ret;
 
 	nfs_pageio_cond_complete(pgio, page_file_index(page));
-	ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE);
+	ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE,
+				   launder);
 	if (ret == -EAGAIN) {
 		redirty_page_for_writepage(wbc, page);
 		ret = 0;
@@ -592,7 +617,9 @@ static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, st
 /*
  * Write an mmapped page to the server.
  */
-static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc)
+static int nfs_writepage_locked(struct page *page,
+				struct writeback_control *wbc,
+				bool launder)
 {
 	struct nfs_pageio_descriptor pgio;
 	struct inode *inode = page_file_mapping(page)->host;
@@ -601,7 +628,7 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc
 	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
 	nfs_pageio_init_write(&pgio, inode, wb_priority(wbc),
 				false, &nfs_async_write_completion_ops);
-	err = nfs_do_writepage(page, wbc, &pgio);
+	err = nfs_do_writepage(page, wbc, &pgio, launder);
 	nfs_pageio_complete(&pgio);
 	if (err < 0)
 		return err;
@@ -614,7 +641,7 @@ int nfs_writepage(struct page *page, struct writeback_control *wbc)
 {
 	int ret;
 
-	ret = nfs_writepage_locked(page, wbc);
+	ret = nfs_writepage_locked(page, wbc, false);
 	unlock_page(page);
 	return ret;
 }
@@ -623,7 +650,7 @@ static int nfs_writepages_callback(struct page *page, struct writeback_control *
 {
 	int ret;
 
-	ret = nfs_do_writepage(page, wbc, data);
+	ret = nfs_do_writepage(page, wbc, data, false);
 	unlock_page(page);
 	return ret;
 }
@@ -803,11 +830,10 @@ EXPORT_SYMBOL_GPL(nfs_request_add_commit_list_locked);
  * holding the nfs_page lock.
  */
 void
-nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst,
-			    struct nfs_commit_info *cinfo)
+nfs_request_add_commit_list(struct nfs_page *req, struct nfs_commit_info *cinfo)
 {
 	spin_lock(cinfo->lock);
-	nfs_request_add_commit_list_locked(req, dst, cinfo);
+	nfs_request_add_commit_list_locked(req, &cinfo->mds->list, cinfo);
 	spin_unlock(cinfo->lock);
 	nfs_mark_page_unstable(req->wb_page, cinfo);
 }
@@ -865,7 +891,7 @@ nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
 {
 	if (pnfs_mark_request_commit(req, lseg, cinfo, ds_commit_idx))
 		return;
-	nfs_request_add_commit_list(req, &cinfo->mds->list, cinfo);
+	nfs_request_add_commit_list(req, cinfo);
 }
 
 static void
@@ -1128,7 +1154,8 @@ int nfs_flush_incompatible(struct file *file, struct page *page)
 		if (req == NULL)
 			return 0;
 		l_ctx = req->wb_lock_context;
-		do_flush = req->wb_page != page || req->wb_context != ctx;
+		do_flush = req->wb_page != page ||
+			!nfs_match_open_context(req->wb_context, ctx);
 		/* for now, flush if more than 1 request in page_group */
 		do_flush |= req->wb_this_page != req;
 		if (l_ctx && flctx &&
@@ -1326,9 +1353,15 @@ static void nfs_async_write_error(struct list_head *head)
 	}
 }
 
+static void nfs_async_write_reschedule_io(struct nfs_pgio_header *hdr)
+{
+	nfs_async_write_error(&hdr->pages);
+}
+
 static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops = {
 	.error_cleanup = nfs_async_write_error,
 	.completion = nfs_write_completion,
+	.reschedule_io = nfs_async_write_reschedule_io,
 };
 
 void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
@@ -1505,6 +1538,13 @@ static void nfs_writeback_result(struct rpc_task *task,
 			task->tk_status = -EIO;
 			return;
 		}
+
+		/* For non rpc-based layout drivers, retry-through-MDS */
+		if (!task->tk_ops) {
+			hdr->pnfs_error = -EAGAIN;
+			return;
+		}
+
 		/* Was this an NFSv2 write or an NFSv3 stable write? */
 		if (resp->verf->committed != NFS_UNSTABLE) {
 			/* Resend from where the server left off */
@@ -1522,27 +1562,21 @@ static void nfs_writeback_result(struct rpc_task *task,
 	}
 }
 
-
-static int nfs_commit_set_lock(struct nfs_inode *nfsi, int may_wait)
+static int wait_on_commit(struct nfs_mds_commit_info *cinfo)
 {
-	int ret;
+	return wait_on_atomic_t(&cinfo->rpcs_out,
+			nfs_wait_atomic_killable, TASK_KILLABLE);
+}
 
-	if (!test_and_set_bit(NFS_INO_COMMIT, &nfsi->flags))
-		return 1;
-	if (!may_wait)
-		return 0;
-	ret = out_of_line_wait_on_bit_lock(&nfsi->flags,
-				NFS_INO_COMMIT,
-				nfs_wait_bit_killable,
-				TASK_KILLABLE);
-	return (ret < 0) ? ret : 1;
+static void nfs_commit_begin(struct nfs_mds_commit_info *cinfo)
+{
+	atomic_inc(&cinfo->rpcs_out);
 }
 
-static void nfs_commit_clear_lock(struct nfs_inode *nfsi)
+static void nfs_commit_end(struct nfs_mds_commit_info *cinfo)
 {
-	clear_bit(NFS_INO_COMMIT, &nfsi->flags);
-	smp_mb__after_atomic();
-	wake_up_bit(&nfsi->flags, NFS_INO_COMMIT);
+	if (atomic_dec_and_test(&cinfo->rpcs_out))
+		wake_up_atomic_t(&cinfo->rpcs_out);
 }
 
 void nfs_commitdata_release(struct nfs_commit_data *data)
@@ -1659,6 +1693,13 @@ void nfs_retry_commit(struct list_head *page_list,
 }
 EXPORT_SYMBOL_GPL(nfs_retry_commit);
 
+static void
+nfs_commit_resched_write(struct nfs_commit_info *cinfo,
+		struct nfs_page *req)
+{
+	__set_page_dirty_nobuffers(req->wb_page);
+}
+
 /*
  * Commit dirty pages
  */
@@ -1680,7 +1721,6 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how,
 				   data->mds_ops, how, 0);
  out_bad:
 	nfs_retry_commit(head, NULL, cinfo, 0);
-	cinfo->completion_ops->error_cleanup(NFS_I(inode));
 	return -ENOMEM;
 }
 
@@ -1742,8 +1782,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 		clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
 
 	nfs_init_cinfo(&cinfo, data->inode, data->dreq);
-	if (atomic_dec_and_test(&cinfo.mds->rpcs_out))
-		nfs_commit_clear_lock(NFS_I(data->inode));
+	nfs_commit_end(cinfo.mds);
 }
 
 static void nfs_commit_release(void *calldata)
@@ -1762,7 +1801,7 @@ static const struct rpc_call_ops nfs_commit_ops = {
 
 static const struct nfs_commit_completion_ops nfs_commit_completion_ops = {
 	.completion = nfs_commit_release_pages,
-	.error_cleanup = nfs_commit_clear_lock,
+	.resched_write = nfs_commit_resched_write,
 };
 
 int nfs_generic_commit_list(struct inode *inode, struct list_head *head,
@@ -1781,30 +1820,25 @@ int nfs_commit_inode(struct inode *inode, int how)
 	LIST_HEAD(head);
 	struct nfs_commit_info cinfo;
 	int may_wait = how & FLUSH_SYNC;
+	int error = 0;
 	int res;
 
-	res = nfs_commit_set_lock(NFS_I(inode), may_wait);
-	if (res <= 0)
-		goto out_mark_dirty;
 	nfs_init_cinfo_from_inode(&cinfo, inode);
+	nfs_commit_begin(cinfo.mds);
 	res = nfs_scan_commit(inode, &head, &cinfo);
-	if (res) {
-		int error;
-
+	if (res)
 		error = nfs_generic_commit_list(inode, &head, how, &cinfo);
-		if (error < 0)
-			return error;
-		if (!may_wait)
-			goto out_mark_dirty;
-		error = wait_on_bit_action(&NFS_I(inode)->flags,
-				NFS_INO_COMMIT,
-				nfs_wait_bit_killable,
-				TASK_KILLABLE);
-		if (error < 0)
-			return error;
-	} else
-		nfs_commit_clear_lock(NFS_I(inode));
+	nfs_commit_end(cinfo.mds);
+	if (error < 0)
+		goto out_error;
+	if (!may_wait)
+		goto out_mark_dirty;
+	error = wait_on_commit(cinfo.mds);
+	if (error < 0)
+		return error;
 	return res;
+out_error:
+	res = error;
 	/* Note: If we exit without ensuring that the commit is complete,
 	 * we must mark the inode as dirty. Otherwise, future calls to
 	 * sync_inode() with the WB_SYNC_ALL flag set will fail to ensure
@@ -1814,6 +1848,7 @@ out_mark_dirty:
 	__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
 	return res;
 }
+EXPORT_SYMBOL_GPL(nfs_commit_inode);
 
 int nfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 {
@@ -1904,10 +1939,10 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page)
 /*
  * Write back all requests on one page - we do this before reading it.
  */
-int nfs_wb_page(struct inode *inode, struct page *page)
+int nfs_wb_single_page(struct inode *inode, struct page *page, bool launder)
 {
 	loff_t range_start = page_file_offset(page);
-	loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1);
+	loff_t range_end = range_start + (loff_t)(PAGE_SIZE - 1);
 	struct writeback_control wbc = {
 		.sync_mode = WB_SYNC_ALL,
 		.nr_to_write = 0,
@@ -1921,7 +1956,7 @@ int nfs_wb_page(struct inode *inode, struct page *page)
 	for (;;) {
 		wait_on_page_writeback(page);
 		if (clear_page_dirty_for_io(page)) {
-			ret = nfs_writepage_locked(page, &wbc);
+			ret = nfs_writepage_locked(page, &wbc, launder);
 			if (ret < 0)
 				goto out_error;
 			continue;
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index a0b77fc1bd39..c9f583d7bac8 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -84,12 +84,30 @@ config NFSD_V4
 	  If unsure, say N.
 
 config NFSD_PNFS
-	bool "NFSv4.1 server support for Parallel NFS (pNFS)"
-	depends on NFSD_V4
+	bool
+
+config NFSD_BLOCKLAYOUT
+	bool "NFSv4.1 server support for pNFS block layouts"
+	depends on NFSD_V4 && BLOCK
+	select NFSD_PNFS
+	help
+	  This option enables support for the exporting pNFS block layouts
+	  in the kernel's NFS server. The pNFS block layout enables NFS
+	  clients to directly perform I/O to block devices accesible to both
+	  the server and the clients.  See RFC 5663 for more details.
+
+	  If unsure, say N.
+
+config NFSD_SCSILAYOUT
+	bool "NFSv4.1 server support for pNFS SCSI layouts"
+	depends on NFSD_V4 && BLOCK
+	select NFSD_PNFS
 	help
-	  This option enables support for the parallel NFS features of the
-	  minor version 1 of the NFSv4 protocol (RFC5661) in the kernel's NFS
-	  server.
+	  This option enables support for the exporting pNFS SCSI layouts
+	  in the kernel's NFS server. The pNFS SCSI layout enables NFS
+	  clients to directly perform I/O to SCSI devices accesible to both
+	  the server and the clients.  See draft-ietf-nfsv4-scsi-layout for
+	  more details.
 
 	  If unsure, say N.
 
diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile
index 9a6028e120c6..3ae5f3c77e28 100644
--- a/fs/nfsd/Makefile
+++ b/fs/nfsd/Makefile
@@ -17,4 +17,6 @@ nfsd-$(CONFIG_NFSD_V3)	+= nfs3proc.o nfs3xdr.o
 nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o
 nfsd-$(CONFIG_NFSD_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \
 			   nfs4acl.o nfs4callback.o nfs4recover.o
-nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o blocklayout.o blocklayoutxdr.o
+nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o
+nfsd-$(CONFIG_NFSD_BLOCKLAYOUT) += blocklayout.o blocklayoutxdr.o
+nfsd-$(CONFIG_NFSD_SCSILAYOUT) += blocklayout.o blocklayoutxdr.o
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index c29d9421bd5e..e55b5242614d 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -1,11 +1,14 @@
 /*
- * Copyright (c) 2014 Christoph Hellwig.
+ * Copyright (c) 2014-2016 Christoph Hellwig.
  */
 #include <linux/exportfs.h>
 #include <linux/genhd.h>
 #include <linux/slab.h>
+#include <linux/pr.h>
 
 #include <linux/nfsd/debug.h>
+#include <scsi/scsi_proto.h>
+#include <scsi/scsi_common.h>
 
 #include "blocklayoutxdr.h"
 #include "pnfs.h"
@@ -13,37 +16,6 @@
 #define NFSDDBG_FACILITY	NFSDDBG_PNFS
 
 
-static int
-nfsd4_block_get_device_info_simple(struct super_block *sb,
-		struct nfsd4_getdeviceinfo *gdp)
-{
-	struct pnfs_block_deviceaddr *dev;
-	struct pnfs_block_volume *b;
-
-	dev = kzalloc(sizeof(struct pnfs_block_deviceaddr) +
-		      sizeof(struct pnfs_block_volume), GFP_KERNEL);
-	if (!dev)
-		return -ENOMEM;
-	gdp->gd_device = dev;
-
-	dev->nr_volumes = 1;
-	b = &dev->volumes[0];
-
-	b->type = PNFS_BLOCK_VOLUME_SIMPLE;
-	b->simple.sig_len = PNFS_BLOCK_UUID_LEN;
-	return sb->s_export_op->get_uuid(sb, b->simple.sig, &b->simple.sig_len,
-			&b->simple.offset);
-}
-
-static __be32
-nfsd4_block_proc_getdeviceinfo(struct super_block *sb,
-		struct nfsd4_getdeviceinfo *gdp)
-{
-	if (sb->s_bdev != sb->s_bdev->bd_contains)
-		return nfserr_inval;
-	return nfserrno(nfsd4_block_get_device_info_simple(sb, gdp));
-}
-
 static __be32
 nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
 		struct nfsd4_layoutget *args)
@@ -141,20 +113,13 @@ out_layoutunavailable:
 }
 
 static __be32
-nfsd4_block_proc_layoutcommit(struct inode *inode,
-		struct nfsd4_layoutcommit *lcp)
+nfsd4_block_commit_blocks(struct inode *inode, struct nfsd4_layoutcommit *lcp,
+		struct iomap *iomaps, int nr_iomaps)
 {
 	loff_t new_size = lcp->lc_last_wr + 1;
 	struct iattr iattr = { .ia_valid = 0 };
-	struct iomap *iomaps;
-	int nr_iomaps;
 	int error;
 
-	nr_iomaps = nfsd4_block_decode_layoutupdate(lcp->lc_up_layout,
-			lcp->lc_up_len, &iomaps, 1 << inode->i_blkbits);
-	if (nr_iomaps < 0)
-		return nfserrno(nr_iomaps);
-
 	if (lcp->lc_mtime.tv_nsec == UTIME_NOW ||
 	    timespec_compare(&lcp->lc_mtime, &inode->i_mtime) < 0)
 		lcp->lc_mtime = current_fs_time(inode->i_sb);
@@ -172,6 +137,54 @@ nfsd4_block_proc_layoutcommit(struct inode *inode,
 	return nfserrno(error);
 }
 
+#ifdef CONFIG_NFSD_BLOCKLAYOUT
+static int
+nfsd4_block_get_device_info_simple(struct super_block *sb,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	struct pnfs_block_deviceaddr *dev;
+	struct pnfs_block_volume *b;
+
+	dev = kzalloc(sizeof(struct pnfs_block_deviceaddr) +
+		      sizeof(struct pnfs_block_volume), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+	gdp->gd_device = dev;
+
+	dev->nr_volumes = 1;
+	b = &dev->volumes[0];
+
+	b->type = PNFS_BLOCK_VOLUME_SIMPLE;
+	b->simple.sig_len = PNFS_BLOCK_UUID_LEN;
+	return sb->s_export_op->get_uuid(sb, b->simple.sig, &b->simple.sig_len,
+			&b->simple.offset);
+}
+
+static __be32
+nfsd4_block_proc_getdeviceinfo(struct super_block *sb,
+		struct nfs4_client *clp,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	if (sb->s_bdev != sb->s_bdev->bd_contains)
+		return nfserr_inval;
+	return nfserrno(nfsd4_block_get_device_info_simple(sb, gdp));
+}
+
+static __be32
+nfsd4_block_proc_layoutcommit(struct inode *inode,
+		struct nfsd4_layoutcommit *lcp)
+{
+	struct iomap *iomaps;
+	int nr_iomaps;
+
+	nr_iomaps = nfsd4_block_decode_layoutupdate(lcp->lc_up_layout,
+			lcp->lc_up_len, &iomaps, 1 << inode->i_blkbits);
+	if (nr_iomaps < 0)
+		return nfserrno(nr_iomaps);
+
+	return nfsd4_block_commit_blocks(inode, lcp, iomaps, nr_iomaps);
+}
+
 const struct nfsd4_layout_ops bl_layout_ops = {
 	/*
 	 * Pretend that we send notification to the client.  This is a blatant
@@ -190,3 +203,206 @@ const struct nfsd4_layout_ops bl_layout_ops = {
 	.encode_layoutget	= nfsd4_block_encode_layoutget,
 	.proc_layoutcommit	= nfsd4_block_proc_layoutcommit,
 };
+#endif /* CONFIG_NFSD_BLOCKLAYOUT */
+
+#ifdef CONFIG_NFSD_SCSILAYOUT
+static int nfsd4_scsi_identify_device(struct block_device *bdev,
+		struct pnfs_block_volume *b)
+{
+	struct request_queue *q = bdev->bd_disk->queue;
+	struct request *rq;
+	size_t bufflen = 252, len, id_len;
+	u8 *buf, *d, type, assoc;
+	int error;
+
+	buf = kzalloc(bufflen, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	rq = blk_get_request(q, READ, GFP_KERNEL);
+	if (IS_ERR(rq)) {
+		error = -ENOMEM;
+		goto out_free_buf;
+	}
+	blk_rq_set_block_pc(rq);
+
+	error = blk_rq_map_kern(q, rq, buf, bufflen, GFP_KERNEL);
+	if (error)
+		goto out_put_request;
+
+	rq->cmd[0] = INQUIRY;
+	rq->cmd[1] = 1;
+	rq->cmd[2] = 0x83;
+	rq->cmd[3] = bufflen >> 8;
+	rq->cmd[4] = bufflen & 0xff;
+	rq->cmd_len = COMMAND_SIZE(INQUIRY);
+
+	error = blk_execute_rq(rq->q, NULL, rq, 1);
+	if (error) {
+		pr_err("pNFS: INQUIRY 0x83 failed with: %x\n",
+			rq->errors);
+		goto out_put_request;
+	}
+
+	len = (buf[2] << 8) + buf[3] + 4;
+	if (len > bufflen) {
+		pr_err("pNFS: INQUIRY 0x83 response invalid (len = %zd)\n",
+			len);
+		goto out_put_request;
+	}
+
+	d = buf + 4;
+	for (d = buf + 4; d < buf + len; d += id_len + 4) {
+		id_len = d[3];
+		type = d[1] & 0xf;
+		assoc = (d[1] >> 4) & 0x3;
+
+		/*
+		 * We only care about a EUI-64 and NAA designator types
+		 * with LU association.
+		 */
+		if (assoc != 0x00)
+			continue;
+		if (type != 0x02 && type != 0x03)
+			continue;
+		if (id_len != 8 && id_len != 12 && id_len != 16)
+			continue;
+
+		b->scsi.code_set = PS_CODE_SET_BINARY;
+		b->scsi.designator_type = type == 0x02 ?
+			PS_DESIGNATOR_EUI64 : PS_DESIGNATOR_NAA;
+		b->scsi.designator_len = id_len;
+		memcpy(b->scsi.designator, d + 4, id_len);
+
+		/*
+		 * If we found a 8 or 12 byte descriptor continue on to
+		 * see if a 16 byte one is available.  If we find a
+		 * 16 byte descriptor we're done.
+		 */
+		if (id_len == 16)
+			break;
+	}
+
+out_put_request:
+	blk_put_request(rq);
+out_free_buf:
+	kfree(buf);
+	return error;
+}
+
+#define NFSD_MDS_PR_KEY		0x0100000000000000
+
+/*
+ * We use the client ID as a unique key for the reservations.
+ * This allows us to easily fence a client when recalls fail.
+ */
+static u64 nfsd4_scsi_pr_key(struct nfs4_client *clp)
+{
+	return ((u64)clp->cl_clientid.cl_boot << 32) | clp->cl_clientid.cl_id;
+}
+
+static int
+nfsd4_block_get_device_info_scsi(struct super_block *sb,
+		struct nfs4_client *clp,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	struct pnfs_block_deviceaddr *dev;
+	struct pnfs_block_volume *b;
+	const struct pr_ops *ops;
+	int error;
+
+	dev = kzalloc(sizeof(struct pnfs_block_deviceaddr) +
+		      sizeof(struct pnfs_block_volume), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+	gdp->gd_device = dev;
+
+	dev->nr_volumes = 1;
+	b = &dev->volumes[0];
+
+	b->type = PNFS_BLOCK_VOLUME_SCSI;
+	b->scsi.pr_key = nfsd4_scsi_pr_key(clp);
+
+	error = nfsd4_scsi_identify_device(sb->s_bdev, b);
+	if (error)
+		return error;
+
+	ops = sb->s_bdev->bd_disk->fops->pr_ops;
+	if (!ops) {
+		pr_err("pNFS: device %s does not support PRs.\n",
+			sb->s_id);
+		return -EINVAL;
+	}
+
+	error = ops->pr_register(sb->s_bdev, 0, NFSD_MDS_PR_KEY, true);
+	if (error) {
+		pr_err("pNFS: failed to register key for device %s.\n",
+			sb->s_id);
+		return -EINVAL;
+	}
+
+	error = ops->pr_reserve(sb->s_bdev, NFSD_MDS_PR_KEY,
+			PR_EXCLUSIVE_ACCESS_REG_ONLY, 0);
+	if (error) {
+		pr_err("pNFS: failed to reserve device %s.\n",
+			sb->s_id);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static __be32
+nfsd4_scsi_proc_getdeviceinfo(struct super_block *sb,
+		struct nfs4_client *clp,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	if (sb->s_bdev != sb->s_bdev->bd_contains)
+		return nfserr_inval;
+	return nfserrno(nfsd4_block_get_device_info_scsi(sb, clp, gdp));
+}
+static __be32
+nfsd4_scsi_proc_layoutcommit(struct inode *inode,
+		struct nfsd4_layoutcommit *lcp)
+{
+	struct iomap *iomaps;
+	int nr_iomaps;
+
+	nr_iomaps = nfsd4_scsi_decode_layoutupdate(lcp->lc_up_layout,
+			lcp->lc_up_len, &iomaps, 1 << inode->i_blkbits);
+	if (nr_iomaps < 0)
+		return nfserrno(nr_iomaps);
+
+	return nfsd4_block_commit_blocks(inode, lcp, iomaps, nr_iomaps);
+}
+
+static void
+nfsd4_scsi_fence_client(struct nfs4_layout_stateid *ls)
+{
+	struct nfs4_client *clp = ls->ls_stid.sc_client;
+	struct block_device *bdev = ls->ls_file->f_path.mnt->mnt_sb->s_bdev;
+
+	bdev->bd_disk->fops->pr_ops->pr_preempt(bdev, NFSD_MDS_PR_KEY,
+			nfsd4_scsi_pr_key(clp), 0, true);
+}
+
+const struct nfsd4_layout_ops scsi_layout_ops = {
+	/*
+	 * Pretend that we send notification to the client.  This is a blatant
+	 * lie to force recent Linux clients to cache our device IDs.
+	 * We rarely ever change the device ID, so the harm of leaking deviceids
+	 * for a while isn't too bad.  Unfortunately RFC5661 is a complete mess
+	 * in this regard, but I filed errata 4119 for this a while ago, and
+	 * hopefully the Linux client will eventually start caching deviceids
+	 * without this again.
+	 */
+	.notify_types		=
+			NOTIFY_DEVICEID4_DELETE | NOTIFY_DEVICEID4_CHANGE,
+	.proc_getdeviceinfo	= nfsd4_scsi_proc_getdeviceinfo,
+	.encode_getdeviceinfo	= nfsd4_block_encode_getdeviceinfo,
+	.proc_layoutget		= nfsd4_block_proc_layoutget,
+	.encode_layoutget	= nfsd4_block_encode_layoutget,
+	.proc_layoutcommit	= nfsd4_scsi_proc_layoutcommit,
+	.fence_client		= nfsd4_scsi_fence_client,
+};
+#endif /* CONFIG_NFSD_SCSILAYOUT */
diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c
index 6d834dc9bbc8..6c3b316f932e 100644
--- a/fs/nfsd/blocklayoutxdr.c
+++ b/fs/nfsd/blocklayoutxdr.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2014 Christoph Hellwig.
+ * Copyright (c) 2014-2016 Christoph Hellwig.
  */
 #include <linux/sunrpc/svc.h>
 #include <linux/exportfs.h>
@@ -53,6 +53,18 @@ nfsd4_block_encode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b)
 		p = xdr_encode_hyper(p, b->simple.offset);
 		p = xdr_encode_opaque(p, b->simple.sig, b->simple.sig_len);
 		break;
+	case PNFS_BLOCK_VOLUME_SCSI:
+		len = 4 + 4 + 4 + 4 + b->scsi.designator_len + 8;
+		p = xdr_reserve_space(xdr, len);
+		if (!p)
+			return -ETOOSMALL;
+
+		*p++ = cpu_to_be32(b->type);
+		*p++ = cpu_to_be32(b->scsi.code_set);
+		*p++ = cpu_to_be32(b->scsi.designator_type);
+		p = xdr_encode_opaque(p, b->scsi.designator, b->scsi.designator_len);
+		p = xdr_encode_hyper(p, b->scsi.pr_key);
+		break;
 	default:
 		return -ENOTSUPP;
 	}
@@ -93,18 +105,22 @@ nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,
 		u32 block_size)
 {
 	struct iomap *iomaps;
-	u32 nr_iomaps, expected, i;
+	u32 nr_iomaps, i;
 
 	if (len < sizeof(u32)) {
 		dprintk("%s: extent array too small: %u\n", __func__, len);
 		return -EINVAL;
 	}
+	len -= sizeof(u32);
+	if (len % PNFS_BLOCK_EXTENT_SIZE) {
+		dprintk("%s: extent array invalid: %u\n", __func__, len);
+		return -EINVAL;
+	}
 
 	nr_iomaps = be32_to_cpup(p++);
-	expected = sizeof(__be32) + nr_iomaps * PNFS_BLOCK_EXTENT_SIZE;
-	if (len != expected) {
+	if (nr_iomaps != len / PNFS_BLOCK_EXTENT_SIZE) {
 		dprintk("%s: extent array size mismatch: %u/%u\n",
-			__func__, len, expected);
+			__func__, len, nr_iomaps);
 		return -EINVAL;
 	}
 
@@ -155,3 +171,54 @@ fail:
 	kfree(iomaps);
 	return -EINVAL;
 }
+
+int
+nfsd4_scsi_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,
+		u32 block_size)
+{
+	struct iomap *iomaps;
+	u32 nr_iomaps, expected, i;
+
+	if (len < sizeof(u32)) {
+		dprintk("%s: extent array too small: %u\n", __func__, len);
+		return -EINVAL;
+	}
+
+	nr_iomaps = be32_to_cpup(p++);
+	expected = sizeof(__be32) + nr_iomaps * PNFS_SCSI_RANGE_SIZE;
+	if (len != expected) {
+		dprintk("%s: extent array size mismatch: %u/%u\n",
+			__func__, len, expected);
+		return -EINVAL;
+	}
+
+	iomaps = kcalloc(nr_iomaps, sizeof(*iomaps), GFP_KERNEL);
+	if (!iomaps) {
+		dprintk("%s: failed to allocate extent array\n", __func__);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < nr_iomaps; i++) {
+		u64 val;
+
+		p = xdr_decode_hyper(p, &val);
+		if (val & (block_size - 1)) {
+			dprintk("%s: unaligned offset 0x%llx\n", __func__, val);
+			goto fail;
+		}
+		iomaps[i].offset = val;
+
+		p = xdr_decode_hyper(p, &val);
+		if (val & (block_size - 1)) {
+			dprintk("%s: unaligned length 0x%llx\n", __func__, val);
+			goto fail;
+		}
+		iomaps[i].length = val;
+	}
+
+	*iomapp = iomaps;
+	return nr_iomaps;
+fail:
+	kfree(iomaps);
+	return -EINVAL;
+}
diff --git a/fs/nfsd/blocklayoutxdr.h b/fs/nfsd/blocklayoutxdr.h
index 6de925fe8499..397bc7563a49 100644
--- a/fs/nfsd/blocklayoutxdr.h
+++ b/fs/nfsd/blocklayoutxdr.h
@@ -15,6 +15,11 @@ struct pnfs_block_extent {
 	enum pnfs_block_extent_state	es;
 };
 
+struct pnfs_block_range {
+	u64				foff;
+	u64				len;
+};
+
 /*
  * Random upper cap for the uuid length to avoid unbounded allocation.
  * Not actually limited by the protocol.
@@ -29,6 +34,13 @@ struct pnfs_block_volume {
 			u32		sig_len;
 			u8		sig[PNFS_BLOCK_UUID_LEN];
 		} simple;
+		struct {
+			enum scsi_code_set		code_set;
+			enum scsi_designator_type	designator_type;
+			int				designator_len;
+			u8				designator[256];
+			u64				pr_key;
+		} scsi;
 	};
 };
 
@@ -43,5 +55,7 @@ __be32 nfsd4_block_encode_layoutget(struct xdr_stream *xdr,
 		struct nfsd4_layoutget *lgp);
 int nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,
 		u32 block_size);
+int nfsd4_scsi_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,
+		u32 block_size);
 
 #endif /* _NFSD_BLOCKLAYOUTXDR_H */
diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c
index 77e7a5cca888..1a03bc3059e8 100644
--- a/fs/nfsd/lockd.c
+++ b/fs/nfsd/lockd.c
@@ -58,7 +58,7 @@ nlm_fclose(struct file *filp)
 	fput(filp);
 }
 
-static struct nlmsvc_binding	nfsd_nlm_ops = {
+static const struct nlmsvc_binding nfsd_nlm_ops = {
 	.fopen		= nlm_fopen,		/* open file for locking */
 	.fclose		= nlm_fclose,		/* close file */
 };
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index d8b16c2568f3..5fbf3bbd00d0 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -92,7 +92,7 @@ struct nfsd_net {
 
 	struct file *rec_file;
 	bool in_grace;
-	struct nfsd4_client_tracking_ops *client_tracking_ops;
+	const struct nfsd4_client_tracking_ops *client_tracking_ops;
 
 	time_t nfsd4_lease;
 	time_t nfsd4_grace;
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 7b755b7f785c..51c3b06e8036 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -147,6 +147,7 @@ nfsd3_proc_read(struct svc_rqst *rqstp, struct nfsd3_readargs *argp,
 {
 	__be32	nfserr;
 	u32	max_blocksize = svc_max_payload(rqstp);
+	unsigned long cnt = min(argp->count, max_blocksize);
 
 	dprintk("nfsd: READ(3) %s %lu bytes at %Lu\n",
 				SVCFH_fmt(&argp->fh),
@@ -157,7 +158,7 @@ nfsd3_proc_read(struct svc_rqst *rqstp, struct nfsd3_readargs *argp,
 	 * 1 (status) + 22 (post_op_attr) + 1 (count) + 1 (eof)
 	 * + 1 (xdr opaque byte count) = 26
 	 */
-	resp->count = min(argp->count, max_blocksize);
+	resp->count = cnt;
 	svc_reserve_auth(rqstp, ((1 + NFS3_POST_OP_ATTR_WORDS + 3)<<2) + resp->count +4);
 
 	fh_copy(&resp->fh, &argp->fh);
@@ -167,8 +168,8 @@ nfsd3_proc_read(struct svc_rqst *rqstp, struct nfsd3_readargs *argp,
 				  &resp->count);
 	if (nfserr == 0) {
 		struct inode	*inode = d_inode(resp->fh.fh_dentry);
-
-		resp->eof = (argp->offset + resp->count) >= inode->i_size;
+		resp->eof = nfsd_eof_on_read(cnt, resp->count, argp->offset,
+							inode->i_size);
 	}
 
 	RETURN_STATUS(nfserr);
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index f6e7cbabac5a..2246454dec76 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -262,11 +262,11 @@ void fill_post_wcc(struct svc_fh *fhp)
 	err = fh_getattr(fhp, &fhp->fh_post_attr);
 	fhp->fh_post_change = d_inode(fhp->fh_dentry)->i_version;
 	if (err) {
-		fhp->fh_post_saved = 0;
+		fhp->fh_post_saved = false;
 		/* Grab the ctime anyway - set_change_info might use it */
 		fhp->fh_post_attr.ctime = d_inode(fhp->fh_dentry)->i_ctime;
 	} else
-		fhp->fh_post_saved = 1;
+		fhp->fh_post_saved = true;
 }
 
 /*
@@ -823,7 +823,7 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp,
 		} else
 			dchild = dget(dparent);
 	} else
-		dchild = lookup_one_len(name, dparent, namlen);
+		dchild = lookup_one_len_unlocked(name, dparent, namlen);
 	if (IS_ERR(dchild))
 		return rv;
 	if (d_mountpoint(dchild))
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index e7f50c4081d6..7389cb1d7409 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -792,12 +792,16 @@ static void warn_no_callback_path(struct nfs4_client *clp, int reason)
 
 static void nfsd4_mark_cb_down(struct nfs4_client *clp, int reason)
 {
+	if (test_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags))
+		return;
 	clp->cl_cb_state = NFSD4_CB_DOWN;
 	warn_no_callback_path(clp, reason);
 }
 
 static void nfsd4_mark_cb_fault(struct nfs4_client *clp, int reason)
 {
+	if (test_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags))
+		return;
 	clp->cl_cb_state = NFSD4_CB_FAULT;
 	warn_no_callback_path(clp, reason);
 }
@@ -1143,7 +1147,7 @@ nfsd4_run_cb_work(struct work_struct *work)
 }
 
 void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
-		struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op)
+		const struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op)
 {
 	cb->cb_clp = clp;
 	cb->cb_msg.rpc_proc = &nfs4_cb_procedures[op];
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index ebf90e487c75..825c7bc8d789 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -1,6 +1,7 @@
 /*
  * Copyright (c) 2014 Christoph Hellwig.
  */
+#include <linux/blkdev.h>
 #include <linux/kmod.h>
 #include <linux/file.h>
 #include <linux/jhash.h>
@@ -22,11 +23,16 @@ struct nfs4_layout {
 static struct kmem_cache *nfs4_layout_cache;
 static struct kmem_cache *nfs4_layout_stateid_cache;
 
-static struct nfsd4_callback_ops nfsd4_cb_layout_ops;
+static const struct nfsd4_callback_ops nfsd4_cb_layout_ops;
 static const struct lock_manager_operations nfsd4_layouts_lm_ops;
 
 const struct nfsd4_layout_ops *nfsd4_layout_ops[LAYOUT_TYPE_MAX] =  {
+#ifdef CONFIG_NFSD_BLOCKLAYOUT
 	[LAYOUT_BLOCK_VOLUME]	= &bl_layout_ops,
+#endif
+#ifdef CONFIG_NFSD_SCSILAYOUT
+	[LAYOUT_SCSI]		= &scsi_layout_ops,
+#endif
 };
 
 /* pNFS device ID to export fsid mapping */
@@ -121,10 +127,24 @@ void nfsd4_setup_layout_type(struct svc_export *exp)
 	if (!(exp->ex_flags & NFSEXP_PNFS))
 		return;
 
+	/*
+	 * Check if the file system supports exporting a block-like layout.
+	 * If the block device supports reservations prefer the SCSI layout,
+	 * otherwise advertise the block layout.
+	 */
+#ifdef CONFIG_NFSD_BLOCKLAYOUT
 	if (sb->s_export_op->get_uuid &&
 	    sb->s_export_op->map_blocks &&
 	    sb->s_export_op->commit_blocks)
 		exp->ex_layout_type = LAYOUT_BLOCK_VOLUME;
+#endif
+#ifdef CONFIG_NFSD_SCSILAYOUT
+	/* overwrite block layout selection if needed */
+	if (sb->s_export_op->map_blocks &&
+	    sb->s_export_op->commit_blocks &&
+	    sb->s_bdev && sb->s_bdev->bd_disk->fops->pr_ops)
+		exp->ex_layout_type = LAYOUT_SCSI;
+#endif
 }
 
 static void
@@ -201,6 +221,7 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate,
 	INIT_LIST_HEAD(&ls->ls_perfile);
 	spin_lock_init(&ls->ls_lock);
 	INIT_LIST_HEAD(&ls->ls_layouts);
+	mutex_init(&ls->ls_mutex);
 	ls->ls_layout_type = layout_type;
 	nfsd4_init_cb(&ls->ls_recall, clp, &nfsd4_cb_layout_ops,
 			NFSPROC4_CLNT_CB_LAYOUT);
@@ -262,19 +283,23 @@ nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp,
 		status = nfserr_jukebox;
 		if (!ls)
 			goto out;
+		mutex_lock(&ls->ls_mutex);
 	} else {
 		ls = container_of(stid, struct nfs4_layout_stateid, ls_stid);
 
 		status = nfserr_bad_stateid;
+		mutex_lock(&ls->ls_mutex);
 		if (stateid->si_generation > stid->sc_stateid.si_generation)
-			goto out_put_stid;
+			goto out_unlock_stid;
 		if (layout_type != ls->ls_layout_type)
-			goto out_put_stid;
+			goto out_unlock_stid;
 	}
 
 	*lsp = ls;
 	return 0;
 
+out_unlock_stid:
+	mutex_unlock(&ls->ls_mutex);
 out_put_stid:
 	nfs4_put_stid(stid);
 out:
@@ -296,8 +321,6 @@ nfsd4_recall_file_layout(struct nfs4_layout_stateid *ls)
 	trace_layout_recall(&ls->ls_stid.sc_stateid);
 
 	atomic_inc(&ls->ls_stid.sc_count);
-	update_stateid(&ls->ls_stid.sc_stateid);
-	memcpy(&ls->ls_recall_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t));
 	nfsd4_run_cb(&ls->ls_recall);
 
 out_unlock:
@@ -406,8 +429,7 @@ nfsd4_insert_layout(struct nfsd4_layoutget *lgp, struct nfs4_layout_stateid *ls)
 	list_add_tail(&new->lo_perstate, &ls->ls_layouts);
 	new = NULL;
 done:
-	update_stateid(&ls->ls_stid.sc_stateid);
-	memcpy(&lgp->lg_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t));
+	nfs4_inc_and_copy_stateid(&lgp->lg_sid, &ls->ls_stid);
 	spin_unlock(&ls->ls_lock);
 out:
 	spin_unlock(&fp->fi_lock);
@@ -481,11 +503,8 @@ nfsd4_return_file_layouts(struct svc_rqst *rqstp,
 		}
 	}
 	if (!list_empty(&ls->ls_layouts)) {
-		if (found) {
-			update_stateid(&ls->ls_stid.sc_stateid);
-			memcpy(&lrp->lr_sid, &ls->ls_stid.sc_stateid,
-				sizeof(stateid_t));
-		}
+		if (found)
+			nfs4_inc_and_copy_stateid(&lrp->lr_sid, &ls->ls_stid);
 		lrp->lrs_present = 1;
 	} else {
 		trace_layoutstate_unhash(&ls->ls_stid.sc_stateid);
@@ -494,6 +513,7 @@ nfsd4_return_file_layouts(struct svc_rqst *rqstp,
 	}
 	spin_unlock(&ls->ls_lock);
 
+	mutex_unlock(&ls->ls_mutex);
 	nfs4_put_stid(&ls->ls_stid);
 	nfsd4_free_layouts(&reaplist);
 	return nfs_ok;
@@ -590,8 +610,6 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls)
 
 	rpc_ntop((struct sockaddr *)&clp->cl_addr, addr_str, sizeof(addr_str));
 
-	trace_layout_recall_fail(&ls->ls_stid.sc_stateid);
-
 	printk(KERN_WARNING
 		"nfsd: client %s failed to respond to layout recall. "
 		"  Fencing..\n", addr_str);
@@ -608,34 +626,67 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls)
 	}
 }
 
+static void
+nfsd4_cb_layout_prepare(struct nfsd4_callback *cb)
+{
+	struct nfs4_layout_stateid *ls =
+		container_of(cb, struct nfs4_layout_stateid, ls_recall);
+
+	mutex_lock(&ls->ls_mutex);
+	nfs4_inc_and_copy_stateid(&ls->ls_recall_sid, &ls->ls_stid);
+	mutex_unlock(&ls->ls_mutex);
+}
+
 static int
 nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task)
 {
 	struct nfs4_layout_stateid *ls =
 		container_of(cb, struct nfs4_layout_stateid, ls_recall);
+	struct nfsd_net *nn;
+	ktime_t now, cutoff;
+	const struct nfsd4_layout_ops *ops;
 	LIST_HEAD(reaplist);
 
+
 	switch (task->tk_status) {
 	case 0:
-		return 1;
+	case -NFS4ERR_DELAY:
+		/*
+		 * Anything left? If not, then call it done. Note that we don't
+		 * take the spinlock since this is an optimization and nothing
+		 * should get added until the cb counter goes to zero.
+		 */
+		if (list_empty(&ls->ls_layouts))
+			return 1;
+
+		/* Poll the client until it's done with the layout */
+		now = ktime_get();
+		nn = net_generic(ls->ls_stid.sc_client->net, nfsd_net_id);
+
+		/* Client gets 2 lease periods to return it */
+		cutoff = ktime_add_ns(task->tk_start,
+					 nn->nfsd4_lease * NSEC_PER_SEC * 2);
+
+		if (ktime_before(now, cutoff)) {
+			rpc_delay(task, HZ/100); /* 10 mili-seconds */
+			return 0;
+		}
+		/* Fallthrough */
 	case -NFS4ERR_NOMATCHING_LAYOUT:
 		trace_layout_recall_done(&ls->ls_stid.sc_stateid);
 		task->tk_status = 0;
 		return 1;
-	case -NFS4ERR_DELAY:
-		/* Poll the client until it's done with the layout */
-		/* FIXME: cap number of retries.
-		 * The pnfs standard states that we need to only expire
-		 * the client after at-least "lease time" .eg lease-time * 2
-		 * when failing to communicate a recall
-		 */
-		rpc_delay(task, HZ/100); /* 10 mili-seconds */
-		return 0;
 	default:
 		/*
 		 * Unknown error or non-responding client, we'll need to fence.
 		 */
-		nfsd4_cb_layout_fail(ls);
+		trace_layout_recall_fail(&ls->ls_stid.sc_stateid);
+
+		ops = nfsd4_layout_ops[ls->ls_layout_type];
+		if (ops->fence_client)
+			ops->fence_client(ls);
+		else
+			nfsd4_cb_layout_fail(ls);
 		return -1;
 	}
 }
@@ -654,7 +705,8 @@ nfsd4_cb_layout_release(struct nfsd4_callback *cb)
 	nfs4_put_stid(&ls->ls_stid);
 }
 
-static struct nfsd4_callback_ops nfsd4_cb_layout_ops = {
+static const struct nfsd4_callback_ops nfsd4_cb_layout_ops = {
+	.prepare	= nfsd4_cb_layout_prepare,
 	.done		= nfsd4_cb_layout_done,
 	.release	= nfsd4_cb_layout_release,
 };
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 4ce6b97b31ad..de1ff1d98bb1 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -55,10 +55,10 @@ nfsd4_security_inode_setsecctx(struct svc_fh *resfh, struct xdr_netobj *label, u
 	struct inode *inode = d_inode(resfh->fh_dentry);
 	int status;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	status = security_inode_setsecctx(resfh->fh_dentry,
 		label->data, label->len);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	if (status)
 		/*
@@ -774,8 +774,9 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
 
 	/* check stateid */
-	status = nfs4_preprocess_stateid_op(rqstp, cstate, &read->rd_stateid,
-			RD_STATE, &read->rd_filp, &read->rd_tmp_file);
+	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
+					&read->rd_stateid, RD_STATE,
+					&read->rd_filp, &read->rd_tmp_file);
 	if (status) {
 		dprintk("NFSD: nfsd4_read: couldn't process stateid!\n");
 		goto out;
@@ -863,12 +864,10 @@ static __be32
 nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	      struct nfsd4_secinfo *secinfo)
 {
-	struct svc_fh resfh;
 	struct svc_export *exp;
 	struct dentry *dentry;
 	__be32 err;
 
-	fh_init(&resfh, NFS4_FHSIZE);
 	err = fh_verify(rqstp, &cstate->current_fh, S_IFDIR, NFSD_MAY_EXEC);
 	if (err)
 		return err;
@@ -877,6 +876,7 @@ nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 				    &exp, &dentry);
 	if (err)
 		return err;
+	fh_unlock(&cstate->current_fh);
 	if (d_really_is_negative(dentry)) {
 		exp_put(exp);
 		err = nfserr_noent;
@@ -921,7 +921,8 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	if (setattr->sa_iattr.ia_valid & ATTR_SIZE) {
 		status = nfs4_preprocess_stateid_op(rqstp, cstate,
-			&setattr->sa_stateid, WR_STATE, NULL, NULL);
+				&cstate->current_fh, &setattr->sa_stateid,
+				WR_STATE, NULL, NULL);
 		if (status) {
 			dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n");
 			return status;
@@ -985,8 +986,8 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (write->wr_offset >= OFFSET_MAX)
 		return nfserr_inval;
 
-	status = nfs4_preprocess_stateid_op(rqstp, cstate, stateid, WR_STATE,
-			&filp, NULL);
+	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
+						stateid, WR_STATE, &filp, NULL);
 	if (status) {
 		dprintk("NFSD: nfsd4_write: couldn't process stateid!\n");
 		return status;
@@ -1010,13 +1011,54 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 }
 
 static __be32
+nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+		struct nfsd4_clone *clone)
+{
+	struct file *src, *dst;
+	__be32 status;
+
+	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->save_fh,
+					    &clone->cl_src_stateid, RD_STATE,
+					    &src, NULL);
+	if (status) {
+		dprintk("NFSD: %s: couldn't process src stateid!\n", __func__);
+		goto out;
+	}
+
+	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
+					    &clone->cl_dst_stateid, WR_STATE,
+					    &dst, NULL);
+	if (status) {
+		dprintk("NFSD: %s: couldn't process dst stateid!\n", __func__);
+		goto out_put_src;
+	}
+
+	/* fix up for NFS-specific error code */
+	if (!S_ISREG(file_inode(src)->i_mode) ||
+	    !S_ISREG(file_inode(dst)->i_mode)) {
+		status = nfserr_wrong_type;
+		goto out_put_dst;
+	}
+
+	status = nfsd4_clone_file_range(src, clone->cl_src_pos,
+			dst, clone->cl_dst_pos, clone->cl_count);
+
+out_put_dst:
+	fput(dst);
+out_put_src:
+	fput(src);
+out:
+	return status;
+}
+
+static __be32
 nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		struct nfsd4_fallocate *fallocate, int flags)
 {
 	__be32 status = nfserr_notsupp;
 	struct file *file;
 
-	status = nfs4_preprocess_stateid_op(rqstp, cstate,
+	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
 					    &fallocate->falloc_stateid,
 					    WR_STATE, &file, NULL);
 	if (status != nfs_ok) {
@@ -1055,7 +1097,7 @@ nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	__be32 status;
 	struct file *file;
 
-	status = nfs4_preprocess_stateid_op(rqstp, cstate,
+	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
 					    &seek->seek_stateid,
 					    RD_STATE, &file, NULL);
 	if (status) {
@@ -1226,8 +1268,10 @@ nfsd4_getdeviceinfo(struct svc_rqst *rqstp,
 		goto out;
 
 	nfserr = nfs_ok;
-	if (gdp->gd_maxcount != 0)
-		nfserr = ops->proc_getdeviceinfo(exp->ex_path.mnt->mnt_sb, gdp);
+	if (gdp->gd_maxcount != 0) {
+		nfserr = ops->proc_getdeviceinfo(exp->ex_path.mnt->mnt_sb,
+					cstate->session->se_client, gdp);
+	}
 
 	gdp->gd_notify_types &= ops->notify_types;
 out:
@@ -1309,6 +1353,7 @@ nfsd4_layoutget(struct svc_rqst *rqstp,
 	nfserr = nfsd4_insert_layout(lgp, ls);
 
 out_put_stid:
+	mutex_unlock(&ls->ls_mutex);
 	nfs4_put_stid(&ls->ls_stid);
 out:
 	return nfserr;
@@ -1362,6 +1407,9 @@ nfsd4_layoutcommit(struct svc_rqst *rqstp,
 		goto out;
 	}
 
+	/* LAYOUTCOMMIT does not require any serialization */
+	mutex_unlock(&ls->ls_mutex);
+
 	if (new_size > i_size_read(inode)) {
 		lcp->lc_size_chg = 1;
 		lcp->lc_newsize = new_size;
@@ -2275,6 +2323,12 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_name = "OP_DEALLOCATE",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
 	},
+	[OP_CLONE] = {
+		.op_func = (nfsd4op_func)nfsd4_clone,
+		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
+		.op_name = "OP_CLONE",
+		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
+	},
 	[OP_SEEK] = {
 		.op_func = (nfsd4op_func)nfsd4_seek,
 		.op_name = "OP_SEEK",
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index e3d47091b191..66eaeb1e8c2c 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -32,10 +32,10 @@
 *
 */
 
+#include <crypto/hash.h>
 #include <linux/file.h>
 #include <linux/slab.h>
 #include <linux/namei.h>
-#include <linux/crypto.h>
 #include <linux/sched.h>
 #include <linux/fs.h>
 #include <linux/module.h>
@@ -104,29 +104,35 @@ static int
 nfs4_make_rec_clidname(char *dname, const struct xdr_netobj *clname)
 {
 	struct xdr_netobj cksum;
-	struct hash_desc desc;
-	struct scatterlist sg;
+	struct crypto_shash *tfm;
 	int status;
 
 	dprintk("NFSD: nfs4_make_rec_clidname for %.*s\n",
 			clname->len, clname->data);
-	desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
-	desc.tfm = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR(desc.tfm)) {
-		status = PTR_ERR(desc.tfm);
+	tfm = crypto_alloc_shash("md5", 0, 0);
+	if (IS_ERR(tfm)) {
+		status = PTR_ERR(tfm);
 		goto out_no_tfm;
 	}
 
-	cksum.len = crypto_hash_digestsize(desc.tfm);
+	cksum.len = crypto_shash_digestsize(tfm);
 	cksum.data = kmalloc(cksum.len, GFP_KERNEL);
 	if (cksum.data == NULL) {
 		status = -ENOMEM;
  		goto out;
 	}
 
-	sg_init_one(&sg, clname->data, clname->len);
+	{
+		SHASH_DESC_ON_STACK(desc, tfm);
+
+		desc->tfm = tfm;
+		desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+
+		status = crypto_shash_digest(desc, clname->data, clname->len,
+					     cksum.data);
+		shash_desc_zero(desc);
+	}
 
-	status = crypto_hash_digest(&desc, &sg, sg.length, cksum.data);
 	if (status)
 		goto out;
 
@@ -135,7 +141,7 @@ nfs4_make_rec_clidname(char *dname, const struct xdr_netobj *clname)
 	status = 0;
 out:
 	kfree(cksum.data);
-	crypto_free_hash(desc.tfm);
+	crypto_free_shash(tfm);
 out_no_tfm:
 	return status;
 }
@@ -192,7 +198,7 @@ nfsd4_create_clid_dir(struct nfs4_client *clp)
 
 	dir = nn->rec_file->f_path.dentry;
 	/* lock the parent */
-	mutex_lock(&d_inode(dir)->i_mutex);
+	inode_lock(d_inode(dir));
 
 	dentry = lookup_one_len(dname, dir, HEXDIR_LEN-1);
 	if (IS_ERR(dentry)) {
@@ -213,7 +219,7 @@ nfsd4_create_clid_dir(struct nfs4_client *clp)
 out_put:
 	dput(dentry);
 out_unlock:
-	mutex_unlock(&d_inode(dir)->i_mutex);
+	inode_unlock(d_inode(dir));
 	if (status == 0) {
 		if (nn->in_grace) {
 			crp = nfs4_client_to_reclaim(dname, nn);
@@ -286,7 +292,7 @@ nfsd4_list_rec_dir(recdir_func *f, struct nfsd_net *nn)
 	}
 
 	status = iterate_dir(nn->rec_file, &ctx.ctx);
-	mutex_lock_nested(&d_inode(dir)->i_mutex, I_MUTEX_PARENT);
+	inode_lock_nested(d_inode(dir), I_MUTEX_PARENT);
 
 	list_for_each_entry_safe(entry, tmp, &ctx.names, list) {
 		if (!status) {
@@ -302,7 +308,7 @@ nfsd4_list_rec_dir(recdir_func *f, struct nfsd_net *nn)
 		list_del(&entry->list);
 		kfree(entry);
 	}
-	mutex_unlock(&d_inode(dir)->i_mutex);
+	inode_unlock(d_inode(dir));
 	nfs4_reset_creds(original_cred);
 
 	list_for_each_entry_safe(entry, tmp, &ctx.names, list) {
@@ -322,7 +328,7 @@ nfsd4_unlink_clid_dir(char *name, int namlen, struct nfsd_net *nn)
 	dprintk("NFSD: nfsd4_unlink_clid_dir. name %.*s\n", namlen, name);
 
 	dir = nn->rec_file->f_path.dentry;
-	mutex_lock_nested(&d_inode(dir)->i_mutex, I_MUTEX_PARENT);
+	inode_lock_nested(d_inode(dir), I_MUTEX_PARENT);
 	dentry = lookup_one_len(name, dir, namlen);
 	if (IS_ERR(dentry)) {
 		status = PTR_ERR(dentry);
@@ -335,7 +341,7 @@ nfsd4_unlink_clid_dir(char *name, int namlen, struct nfsd_net *nn)
 out:
 	dput(dentry);
 out_unlock:
-	mutex_unlock(&d_inode(dir)->i_mutex);
+	inode_unlock(d_inode(dir));
 	return status;
 }
 
@@ -631,7 +637,7 @@ nfsd4_check_legacy_client(struct nfs4_client *clp)
 	return -ENOENT;
 }
 
-static struct nfsd4_client_tracking_ops nfsd4_legacy_tracking_ops = {
+static const struct nfsd4_client_tracking_ops nfsd4_legacy_tracking_ops = {
 	.init		= nfsd4_legacy_tracking_init,
 	.exit		= nfsd4_legacy_tracking_exit,
 	.create		= nfsd4_create_clid_dir,
@@ -1050,7 +1056,7 @@ out_err:
 		printk(KERN_ERR "NFSD: Unable to end grace period: %d\n", ret);
 }
 
-static struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops = {
+static const struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops = {
 	.init		= nfsd4_init_cld_pipe,
 	.exit		= nfsd4_remove_cld_pipe,
 	.create		= nfsd4_cld_create,
@@ -1260,6 +1266,7 @@ nfsd4_umh_cltrack_init(struct net *net)
 	/* XXX: The usermode helper s not working in container yet. */
 	if (net != &init_net) {
 		pr_warn("NFSD: attempt to initialize umh client tracking in a container ignored.\n");
+		kfree(grace_start);
 		return -EINVAL;
 	}
 
@@ -1394,7 +1401,7 @@ nfsd4_umh_cltrack_grace_done(struct nfsd_net *nn)
 	kfree(legacy);
 }
 
-static struct nfsd4_client_tracking_ops nfsd4_umh_tracking_ops = {
+static const struct nfsd4_client_tracking_ops nfsd4_umh_tracking_ops = {
 	.init		= nfsd4_umh_cltrack_init,
 	.exit		= NULL,
 	.create		= nfsd4_umh_cltrack_create,
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 0f1d5691b795..0462eeddfff9 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -98,7 +98,7 @@ static struct kmem_cache *odstate_slab;
 
 static void free_session(struct nfsd4_session *);
 
-static struct nfsd4_callback_ops nfsd4_cb_recall_ops;
+static const struct nfsd4_callback_ops nfsd4_cb_recall_ops;
 
 static bool is_session_dead(struct nfsd4_session *ses)
 {
@@ -575,6 +575,7 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl,
 	stid->sc_stateid.si_opaque.so_clid = cl->cl_clientid;
 	/* Will be incremented before return to client: */
 	atomic_set(&stid->sc_count, 1);
+	spin_lock_init(&stid->sc_lock);
 
 	/*
 	 * It shouldn't be a problem to reuse an opaque stateid value.
@@ -745,6 +746,18 @@ nfs4_put_stid(struct nfs4_stid *s)
 		put_nfs4_file(fp);
 }
 
+void
+nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid)
+{
+	stateid_t *src = &stid->sc_stateid;
+
+	spin_lock(&stid->sc_lock);
+	if (unlikely(++src->si_generation == 0))
+		src->si_generation = 1;
+	memcpy(dst, src, sizeof(*dst));
+	spin_unlock(&stid->sc_lock);
+}
+
 static void nfs4_put_deleg_lease(struct nfs4_file *fp)
 {
 	struct file *filp = NULL;
@@ -765,16 +778,68 @@ void nfs4_unhash_stid(struct nfs4_stid *s)
 	s->sc_type = 0;
 }
 
-static void
+/**
+ * nfs4_get_existing_delegation - Discover if this delegation already exists
+ * @clp:     a pointer to the nfs4_client we're granting a delegation to
+ * @fp:      a pointer to the nfs4_file we're granting a delegation on
+ *
+ * Return:
+ *      On success: NULL if an existing delegation was not found.
+ *
+ *      On error: -EAGAIN if one was previously granted to this nfs4_client
+ *                 for this nfs4_file.
+ *
+ */
+
+static int
+nfs4_get_existing_delegation(struct nfs4_client *clp, struct nfs4_file *fp)
+{
+	struct nfs4_delegation *searchdp = NULL;
+	struct nfs4_client *searchclp = NULL;
+
+	lockdep_assert_held(&state_lock);
+	lockdep_assert_held(&fp->fi_lock);
+
+	list_for_each_entry(searchdp, &fp->fi_delegations, dl_perfile) {
+		searchclp = searchdp->dl_stid.sc_client;
+		if (clp == searchclp) {
+			return -EAGAIN;
+		}
+	}
+	return 0;
+}
+
+/**
+ * hash_delegation_locked - Add a delegation to the appropriate lists
+ * @dp:     a pointer to the nfs4_delegation we are adding.
+ * @fp:     a pointer to the nfs4_file we're granting a delegation on
+ *
+ * Return:
+ *      On success: NULL if the delegation was successfully hashed.
+ *
+ *      On error: -EAGAIN if one was previously granted to this
+ *                 nfs4_client for this nfs4_file. Delegation is not hashed.
+ *
+ */
+
+static int
 hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp)
 {
+	int status;
+	struct nfs4_client *clp = dp->dl_stid.sc_client;
+
 	lockdep_assert_held(&state_lock);
 	lockdep_assert_held(&fp->fi_lock);
 
+	status = nfs4_get_existing_delegation(clp, fp);
+	if (status)
+		return status;
+	++fp->fi_delegees;
 	atomic_inc(&dp->dl_stid.sc_count);
 	dp->dl_stid.sc_type = NFS4_DELEG_STID;
 	list_add(&dp->dl_perfile, &fp->fi_delegations);
-	list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations);
+	list_add(&dp->dl_perclnt, &clp->cl_delegations);
+	return 0;
 }
 
 static bool
@@ -1792,15 +1857,28 @@ static void copy_clid(struct nfs4_client *target, struct nfs4_client *source)
 	target->cl_clientid.cl_id = source->cl_clientid.cl_id; 
 }
 
-static int copy_cred(struct svc_cred *target, struct svc_cred *source)
+int strdup_if_nonnull(char **target, char *source)
 {
-	if (source->cr_principal) {
-		target->cr_principal =
-				kstrdup(source->cr_principal, GFP_KERNEL);
-		if (target->cr_principal == NULL)
+	if (source) {
+		*target = kstrdup(source, GFP_KERNEL);
+		if (!*target)
 			return -ENOMEM;
 	} else
-		target->cr_principal = NULL;
+		*target = NULL;
+	return 0;
+}
+
+static int copy_cred(struct svc_cred *target, struct svc_cred *source)
+{
+	int ret;
+
+	ret = strdup_if_nonnull(&target->cr_principal, source->cr_principal);
+	if (ret)
+		return ret;
+	ret = strdup_if_nonnull(&target->cr_raw_principal,
+					source->cr_raw_principal);
+	if (ret)
+		return ret;
 	target->cr_flavor = source->cr_flavor;
 	target->cr_uid = source->cr_uid;
 	target->cr_gid = source->cr_gid;
@@ -1904,6 +1982,9 @@ static bool mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp)
 		return false;
 	if (!svc_rqst_integrity_protected(rqstp))
 		return false;
+	if (cl->cl_cred.cr_raw_principal)
+		return 0 == strcmp(cl->cl_cred.cr_raw_principal,
+						cr->cr_raw_principal);
 	if (!cr->cr_principal)
 		return false;
 	return 0 == strcmp(cl->cl_cred.cr_principal, cr->cr_principal);
@@ -2175,7 +2256,8 @@ nfsd4_store_cache_entry(struct nfsd4_compoundres *resp)
 	base = resp->cstate.data_offset;
 	slot->sl_datalen = buf->len - base;
 	if (read_bytes_from_xdr_buf(buf, base, slot->sl_data, slot->sl_datalen))
-		WARN("%s: sessions DRC could not cache compound\n", __func__);
+		WARN(1, "%s: sessions DRC could not cache compound\n",
+		     __func__);
 	return;
 }
 
@@ -2256,15 +2338,20 @@ nfsd4_set_ex_flags(struct nfs4_client *new, struct nfsd4_exchange_id *clid)
 	clid->flags = new->cl_exchange_flags;
 }
 
+static bool client_has_openowners(struct nfs4_client *clp)
+{
+	struct nfs4_openowner *oo;
+
+	list_for_each_entry(oo, &clp->cl_openowners, oo_perclient) {
+		if (!list_empty(&oo->oo_owner.so_stateids))
+			return true;
+	}
+	return false;
+}
+
 static bool client_has_state(struct nfs4_client *clp)
 {
-	/*
-	 * Note clp->cl_openowners check isn't quite right: there's no
-	 * need to count owners without stateid's.
-	 *
-	 * Also note we should probably be using this in 4.0 case too.
-	 */
-	return !list_empty(&clp->cl_openowners)
+	return client_has_openowners(clp)
 #ifdef CONFIG_NFSD_PNFS
 		|| !list_empty(&clp->cl_lo_states)
 #endif
@@ -2295,22 +2382,36 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
 	if (exid->flags & ~EXCHGID4_FLAG_MASK_A)
 		return nfserr_inval;
 
+	new = create_client(exid->clname, rqstp, &verf);
+	if (new == NULL)
+		return nfserr_jukebox;
+
 	switch (exid->spa_how) {
 	case SP4_MACH_CRED:
-		if (!svc_rqst_integrity_protected(rqstp))
-			return nfserr_inval;
+		if (!svc_rqst_integrity_protected(rqstp)) {
+			status = nfserr_inval;
+			goto out_nolock;
+		}
+		/*
+		 * Sometimes userspace doesn't give us a principal.
+		 * Which is a bug, really.  Anyway, we can't enforce
+		 * MACH_CRED in that case, better to give up now:
+		 */
+		if (!new->cl_cred.cr_principal &&
+					!new->cl_cred.cr_raw_principal) {
+			status = nfserr_serverfault;
+			goto out_nolock;
+		}
+		new->cl_mach_cred = true;
 	case SP4_NONE:
 		break;
 	default:				/* checked by xdr code */
 		WARN_ON_ONCE(1);
 	case SP4_SSV:
-		return nfserr_encr_alg_unsupp;
+		status = nfserr_encr_alg_unsupp;
+		goto out_nolock;
 	}
 
-	new = create_client(exid->clname, rqstp, &verf);
-	if (new == NULL)
-		return nfserr_jukebox;
-
 	/* Cases below refer to rfc 5661 section 18.35.4: */
 	spin_lock(&nn->client_lock);
 	conf = find_confirmed_client_by_name(&exid->clname, nn);
@@ -2372,7 +2473,6 @@ out_new:
 			goto out;
 	}
 	new->cl_minorversion = cstate->minorversion;
-	new->cl_mach_cred = (exid->spa_how == SP4_MACH_CRED);
 
 	gen_clid(new, nn);
 	add_to_unconfirmed(new);
@@ -2390,6 +2490,7 @@ out_copy:
 
 out:
 	spin_unlock(&nn->client_lock);
+out_nolock:
 	if (new)
 		expire_client(new);
 	if (unconf)
@@ -2486,21 +2587,26 @@ static __be32 check_forechannel_attrs(struct nfsd4_channel_attrs *ca, struct nfs
 	return nfs_ok;
 }
 
+/*
+ * Server's NFSv4.1 backchannel support is AUTH_SYS-only for now.
+ * These are based on similar macros in linux/sunrpc/msg_prot.h .
+ */
+#define RPC_MAX_HEADER_WITH_AUTH_SYS \
+	(RPC_CALLHDRSIZE + 2 * (2 + UNX_CALLSLACK))
+
+#define RPC_MAX_REPHEADER_WITH_AUTH_SYS \
+	(RPC_REPHDRSIZE + (2 + NUL_REPLYSLACK))
+
 #define NFSD_CB_MAX_REQ_SZ	((NFS4_enc_cb_recall_sz + \
-				 RPC_MAX_HEADER_WITH_AUTH) * sizeof(__be32))
+				 RPC_MAX_HEADER_WITH_AUTH_SYS) * sizeof(__be32))
 #define NFSD_CB_MAX_RESP_SZ	((NFS4_dec_cb_recall_sz + \
-				 RPC_MAX_REPHEADER_WITH_AUTH) * sizeof(__be32))
+				 RPC_MAX_REPHEADER_WITH_AUTH_SYS) * \
+				 sizeof(__be32))
 
 static __be32 check_backchannel_attrs(struct nfsd4_channel_attrs *ca)
 {
 	ca->headerpadsz = 0;
 
-	/*
-	 * These RPC_MAX_HEADER macros are overkill, especially since we
-	 * don't even do gss on the backchannel yet.  But this is still
-	 * less than 1k.  Tighten up this estimate in the unlikely event
-	 * it turns out to be a problem for some client:
-	 */
 	if (ca->maxreq_sz < NFSD_CB_MAX_REQ_SZ)
 		return nfserr_toosmall;
 	if (ca->maxresp_sz < NFSD_CB_MAX_RESP_SZ)
@@ -2610,10 +2716,9 @@ nfsd4_create_session(struct svc_rqst *rqstp,
 		goto out_free_conn;
 	}
 	status = nfs_ok;
-	/*
-	 * We do not support RDMA or persistent sessions
-	 */
+	/* Persistent sessions are not supported */
 	cr_ses->flags &= ~SESSION4_PERSIST;
+	/* Upshifting from TCP to RDMA is not supported */
 	cr_ses->flags &= ~SESSION4_RDMA;
 
 	init_session(rqstp, new, conf, cr_ses);
@@ -3049,7 +3154,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	/* Cases below refer to rfc 3530 section 14.2.33: */
 	spin_lock(&nn->client_lock);
 	conf = find_confirmed_client_by_name(&clname, nn);
-	if (conf) {
+	if (conf && client_has_state(conf)) {
 		/* case 0: */
 		status = nfserr_clid_inuse;
 		if (clp_used_exchangeid(conf))
@@ -3136,6 +3241,11 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
 	} else { /* case 3: normal case; new or rebooted client */
 		old = find_confirmed_client_by_name(&unconf->cl_name, nn);
 		if (old) {
+			status = nfserr_clid_inuse;
+			if (client_has_state(old)
+					&& !same_creds(&unconf->cl_cred,
+							&old->cl_cred))
+				goto out;
 			status = mark_client_expired_locked(old);
 			if (status) {
 				old = NULL;
@@ -3317,6 +3427,27 @@ static const struct nfs4_stateowner_operations openowner_ops = {
 	.so_free =	nfs4_free_openowner,
 };
 
+static struct nfs4_ol_stateid *
+nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open)
+{
+	struct nfs4_ol_stateid *local, *ret = NULL;
+	struct nfs4_openowner *oo = open->op_openowner;
+
+	lockdep_assert_held(&fp->fi_lock);
+
+	list_for_each_entry(local, &fp->fi_stateids, st_perfile) {
+		/* ignore lock owners */
+		if (local->st_stateowner->so_is_open_owner == 0)
+			continue;
+		if (local->st_stateowner == &oo->oo_owner) {
+			ret = local;
+			atomic_inc(&ret->st_stid.sc_count);
+			break;
+		}
+	}
+	return ret;
+}
+
 static struct nfs4_openowner *
 alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
 			   struct nfsd4_compound_state *cstate)
@@ -3348,9 +3479,20 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
 	return ret;
 }
 
-static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, struct nfsd4_open *open) {
+static struct nfs4_ol_stateid *
+init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
+		struct nfsd4_open *open)
+{
+
 	struct nfs4_openowner *oo = open->op_openowner;
+	struct nfs4_ol_stateid *retstp = NULL;
 
+	spin_lock(&oo->oo_owner.so_client->cl_lock);
+	spin_lock(&fp->fi_lock);
+
+	retstp = nfsd4_find_existing_open(fp, open);
+	if (retstp)
+		goto out_unlock;
 	atomic_inc(&stp->st_stid.sc_count);
 	stp->st_stid.sc_type = NFS4_OPEN_STID;
 	INIT_LIST_HEAD(&stp->st_locks);
@@ -3360,12 +3502,14 @@ static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
 	stp->st_access_bmap = 0;
 	stp->st_deny_bmap = 0;
 	stp->st_openstp = NULL;
-	spin_lock(&oo->oo_owner.so_client->cl_lock);
+	init_rwsem(&stp->st_rwsem);
 	list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids);
-	spin_lock(&fp->fi_lock);
 	list_add(&stp->st_perfile, &fp->fi_stateids);
+
+out_unlock:
 	spin_unlock(&fp->fi_lock);
 	spin_unlock(&oo->oo_owner.so_client->cl_lock);
+	return retstp;
 }
 
 /*
@@ -3539,7 +3683,7 @@ static void nfsd4_cb_recall_release(struct nfsd4_callback *cb)
 	nfs4_put_stid(&dp->dl_stid);
 }
 
-static struct nfsd4_callback_ops nfsd4_cb_recall_ops = {
+static const struct nfsd4_callback_ops nfsd4_cb_recall_ops = {
 	.prepare	= nfsd4_cb_recall_prepare,
 	.done		= nfsd4_cb_recall_done,
 	.release	= nfsd4_cb_recall_release,
@@ -3776,27 +3920,6 @@ out:
 	return nfs_ok;
 }
 
-static struct nfs4_ol_stateid *
-nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open)
-{
-	struct nfs4_ol_stateid *local, *ret = NULL;
-	struct nfs4_openowner *oo = open->op_openowner;
-
-	spin_lock(&fp->fi_lock);
-	list_for_each_entry(local, &fp->fi_stateids, st_perfile) {
-		/* ignore lock owners */
-		if (local->st_stateowner->so_is_open_owner == 0)
-			continue;
-		if (local->st_stateowner == &oo->oo_owner) {
-			ret = local;
-			atomic_inc(&ret->st_stid.sc_count);
-			break;
-		}
-	}
-	spin_unlock(&fp->fi_lock);
-	return ret;
-}
-
 static inline int nfs4_access_to_access(u32 nfs4_access)
 {
 	int flags = 0;
@@ -3945,6 +4068,18 @@ static struct file_lock *nfs4_alloc_init_lease(struct nfs4_file *fp, int flag)
 	return fl;
 }
 
+/**
+ * nfs4_setlease - Obtain a delegation by requesting lease from vfs layer
+ * @dp:   a pointer to the nfs4_delegation we're adding.
+ *
+ * Return:
+ *      On success: Return code will be 0 on success.
+ *
+ *      On error: -EAGAIN if there was an existing delegation.
+ *                 nonzero if there is an error in other cases.
+ *
+ */
+
 static int nfs4_setlease(struct nfs4_delegation *dp)
 {
 	struct nfs4_file *fp = dp->dl_stid.sc_file;
@@ -3976,16 +4111,19 @@ static int nfs4_setlease(struct nfs4_delegation *dp)
 		goto out_unlock;
 	/* Race breaker */
 	if (fp->fi_deleg_file) {
-		status = 0;
-		++fp->fi_delegees;
-		hash_delegation_locked(dp, fp);
+		status = hash_delegation_locked(dp, fp);
 		goto out_unlock;
 	}
 	fp->fi_deleg_file = filp;
-	fp->fi_delegees = 1;
-	hash_delegation_locked(dp, fp);
+	fp->fi_delegees = 0;
+	status = hash_delegation_locked(dp, fp);
 	spin_unlock(&fp->fi_lock);
 	spin_unlock(&state_lock);
+	if (status) {
+		/* Should never happen, this is a new fi_deleg_file  */
+		WARN_ON_ONCE(1);
+		goto out_fput;
+	}
 	return 0;
 out_unlock:
 	spin_unlock(&fp->fi_lock);
@@ -4005,6 +4143,15 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
 	if (fp->fi_had_conflict)
 		return ERR_PTR(-EAGAIN);
 
+	spin_lock(&state_lock);
+	spin_lock(&fp->fi_lock);
+	status = nfs4_get_existing_delegation(clp, fp);
+	spin_unlock(&fp->fi_lock);
+	spin_unlock(&state_lock);
+
+	if (status)
+		return ERR_PTR(status);
+
 	dp = alloc_init_deleg(clp, fh, odstate);
 	if (!dp)
 		return ERR_PTR(-ENOMEM);
@@ -4023,9 +4170,7 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
 		status = -EAGAIN;
 		goto out_unlock;
 	}
-	++fp->fi_delegees;
-	hash_delegation_locked(dp, fp);
-	status = 0;
+	status = hash_delegation_locked(dp, fp);
 out_unlock:
 	spin_unlock(&fp->fi_lock);
 	spin_unlock(&state_lock);
@@ -4160,6 +4305,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 	struct nfs4_client *cl = open->op_openowner->oo_owner.so_client;
 	struct nfs4_file *fp = NULL;
 	struct nfs4_ol_stateid *stp = NULL;
+	struct nfs4_ol_stateid *swapstp = NULL;
 	struct nfs4_delegation *dp = NULL;
 	__be32 status;
 
@@ -4173,7 +4319,9 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 		status = nfs4_check_deleg(cl, open, &dp);
 		if (status)
 			goto out;
+		spin_lock(&fp->fi_lock);
 		stp = nfsd4_find_existing_open(fp, open);
+		spin_unlock(&fp->fi_lock);
 	} else {
 		open->op_file = NULL;
 		status = nfserr_bad_stateid;
@@ -4187,15 +4335,32 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 	 */
 	if (stp) {
 		/* Stateid was found, this is an OPEN upgrade */
+		down_read(&stp->st_rwsem);
 		status = nfs4_upgrade_open(rqstp, fp, current_fh, stp, open);
-		if (status)
+		if (status) {
+			up_read(&stp->st_rwsem);
 			goto out;
+		}
 	} else {
 		stp = open->op_stp;
 		open->op_stp = NULL;
-		init_open_stateid(stp, fp, open);
+		swapstp = init_open_stateid(stp, fp, open);
+		if (swapstp) {
+			nfs4_put_stid(&stp->st_stid);
+			stp = swapstp;
+			down_read(&stp->st_rwsem);
+			status = nfs4_upgrade_open(rqstp, fp, current_fh,
+						stp, open);
+			if (status) {
+				up_read(&stp->st_rwsem);
+				goto out;
+			}
+			goto upgrade_out;
+		}
+		down_read(&stp->st_rwsem);
 		status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open);
 		if (status) {
+			up_read(&stp->st_rwsem);
 			release_open_stateid(stp);
 			goto out;
 		}
@@ -4205,8 +4370,9 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 		if (stp->st_clnt_odstate == open->op_odstate)
 			open->op_odstate = NULL;
 	}
-	update_stateid(&stp->st_stid.sc_stateid);
-	memcpy(&open->op_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
+upgrade_out:
+	nfs4_inc_and_copy_stateid(&open->op_stateid, &stp->st_stid);
+	up_read(&stp->st_rwsem);
 
 	if (nfsd4_has_session(&resp->cstate)) {
 		if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) {
@@ -4410,8 +4576,7 @@ static void
 laundromat_main(struct work_struct *laundry)
 {
 	time_t t;
-	struct delayed_work *dwork = container_of(laundry, struct delayed_work,
-						  work);
+	struct delayed_work *dwork = to_delayed_work(laundry);
 	struct nfsd_net *nn = container_of(dwork, struct nfsd_net,
 					   laundromat_work);
 
@@ -4666,10 +4831,9 @@ nfs4_check_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfs4_stid *s,
  */
 __be32
 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
-		struct nfsd4_compound_state *cstate, stateid_t *stateid,
-		int flags, struct file **filpp, bool *tmp_file)
+		struct nfsd4_compound_state *cstate, struct svc_fh *fhp,
+		stateid_t *stateid, int flags, struct file **filpp, bool *tmp_file)
 {
-	struct svc_fh *fhp = &cstate->current_fh;
 	struct inode *ino = d_inode(fhp->fh_dentry);
 	struct net *net = SVC_NET(rqstp);
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
@@ -4819,10 +4983,13 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_
 		 * revoked delegations are kept only for free_stateid.
 		 */
 		return nfserr_bad_stateid;
+	down_write(&stp->st_rwsem);
 	status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate));
-	if (status)
-		return status;
-	return nfs4_check_fh(current_fh, &stp->st_stid);
+	if (status == nfs_ok)
+		status = nfs4_check_fh(current_fh, &stp->st_stid);
+	if (status != nfs_ok)
+		up_write(&stp->st_rwsem);
+	return status;
 }
 
 /* 
@@ -4869,6 +5036,7 @@ static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cs
 		return status;
 	oo = openowner(stp->st_stateowner);
 	if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) {
+		up_write(&stp->st_rwsem);
 		nfs4_put_stid(&stp->st_stid);
 		return nfserr_bad_stateid;
 	}
@@ -4899,11 +5067,13 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		goto out;
 	oo = openowner(stp->st_stateowner);
 	status = nfserr_bad_stateid;
-	if (oo->oo_flags & NFS4_OO_CONFIRMED)
+	if (oo->oo_flags & NFS4_OO_CONFIRMED) {
+		up_write(&stp->st_rwsem);
 		goto put_stateid;
+	}
 	oo->oo_flags |= NFS4_OO_CONFIRMED;
-	update_stateid(&stp->st_stid.sc_stateid);
-	memcpy(&oc->oc_resp_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
+	nfs4_inc_and_copy_stateid(&oc->oc_resp_stateid, &stp->st_stid);
+	up_write(&stp->st_rwsem);
 	dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n",
 		__func__, oc->oc_seqid, STATEID_VAL(&stp->st_stid.sc_stateid));
 
@@ -4975,13 +5145,11 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp,
 		goto put_stateid;
 	}
 	nfs4_stateid_downgrade(stp, od->od_share_access);
-
 	reset_union_bmap_deny(od->od_share_deny, stp);
-
-	update_stateid(&stp->st_stid.sc_stateid);
-	memcpy(&od->od_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
+	nfs4_inc_and_copy_stateid(&od->od_stateid, &stp->st_stid);
 	status = nfs_ok;
 put_stateid:
+	up_write(&stp->st_rwsem);
 	nfs4_put_stid(&stp->st_stid);
 out:
 	nfsd4_bump_seqid(cstate, status);
@@ -5033,8 +5201,8 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	nfsd4_bump_seqid(cstate, status);
 	if (status)
 		goto out; 
-	update_stateid(&stp->st_stid.sc_stateid);
-	memcpy(&close->cl_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
+	nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid);
+	up_write(&stp->st_rwsem);
 
 	nfsd4_close_open_stateid(stp);
 
@@ -5260,6 +5428,7 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo,
 	stp->st_access_bmap = 0;
 	stp->st_deny_bmap = open_stp->st_deny_bmap;
 	stp->st_openstp = open_stp;
+	init_rwsem(&stp->st_rwsem);
 	list_add(&stp->st_locks, &open_stp->st_locks);
 	list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids);
 	spin_lock(&fp->fi_lock);
@@ -5428,6 +5597,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 					&open_stp, nn);
 		if (status)
 			goto out;
+		up_write(&open_stp->st_rwsem);
 		open_sop = openowner(open_stp->st_stateowner);
 		status = nfserr_bad_stateid;
 		if (!same_clid(&open_sop->oo_owner.so_client->cl_clientid,
@@ -5435,6 +5605,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 			goto out;
 		status = lookup_or_create_lock_state(cstate, open_stp, lock,
 							&lock_stp, &new);
+		if (status == nfs_ok)
+			down_write(&lock_stp->st_rwsem);
 	} else {
 		status = nfs4_preprocess_seqid_op(cstate,
 				       lock->lk_old_lock_seqid,
@@ -5512,9 +5684,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	err = vfs_lock_file(filp, F_SETLK, file_lock, conflock);
 	switch (-err) {
 	case 0: /* success! */
-		update_stateid(&lock_stp->st_stid.sc_stateid);
-		memcpy(&lock->lk_resp_stateid, &lock_stp->st_stid.sc_stateid, 
-				sizeof(stateid_t));
+		nfs4_inc_and_copy_stateid(&lock->lk_resp_stateid, &lock_stp->st_stid);
 		status = 0;
 		break;
 	case (EAGAIN):		/* conflock holds conflicting lock */
@@ -5540,6 +5710,8 @@ out:
 		    seqid_mutating_err(ntohl(status)))
 			lock_sop->lo_owner.so_seqid++;
 
+		up_write(&lock_stp->st_rwsem);
+
 		/*
 		 * If this is a new, never-before-used stateid, and we are
 		 * returning an error, then just go ahead and release it.
@@ -5704,11 +5876,11 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		dprintk("NFSD: nfs4_locku: vfs_lock_file failed!\n");
 		goto out_nfserr;
 	}
-	update_stateid(&stp->st_stid.sc_stateid);
-	memcpy(&locku->lu_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
+	nfs4_inc_and_copy_stateid(&locku->lu_stateid, &stp->st_stid);
 fput:
 	fput(filp);
 put_stateid:
+	up_write(&stp->st_rwsem);
 	nfs4_put_stid(&stp->st_stid);
 out:
 	nfsd4_bump_seqid(cstate, status);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 51c9e9ca39a4..9df898ba648f 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1072,8 +1072,9 @@ nfsd4_decode_rename(struct nfsd4_compoundargs *argp, struct nfsd4_rename *rename
 
 	READ_BUF(4);
 	rename->rn_snamelen = be32_to_cpup(p++);
-	READ_BUF(rename->rn_snamelen + 4);
+	READ_BUF(rename->rn_snamelen);
 	SAVEMEM(rename->rn_sname, rename->rn_snamelen);
+	READ_BUF(4);
 	rename->rn_tnamelen = be32_to_cpup(p++);
 	READ_BUF(rename->rn_tnamelen);
 	SAVEMEM(rename->rn_tname, rename->rn_tnamelen);
@@ -1155,13 +1156,14 @@ nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclient
 	READ_BUF(8);
 	setclientid->se_callback_prog = be32_to_cpup(p++);
 	setclientid->se_callback_netid_len = be32_to_cpup(p++);
-
-	READ_BUF(setclientid->se_callback_netid_len + 4);
+	READ_BUF(setclientid->se_callback_netid_len);
 	SAVEMEM(setclientid->se_callback_netid_val, setclientid->se_callback_netid_len);
+	READ_BUF(4);
 	setclientid->se_callback_addr_len = be32_to_cpup(p++);
 
-	READ_BUF(setclientid->se_callback_addr_len + 4);
+	READ_BUF(setclientid->se_callback_addr_len);
 	SAVEMEM(setclientid->se_callback_addr_val, setclientid->se_callback_addr_len);
+	READ_BUF(4);
 	setclientid->se_callback_ident = be32_to_cpup(p++);
 
 	DECODE_TAIL;
@@ -1675,6 +1677,25 @@ nfsd4_decode_fallocate(struct nfsd4_compoundargs *argp,
 }
 
 static __be32
+nfsd4_decode_clone(struct nfsd4_compoundargs *argp, struct nfsd4_clone *clone)
+{
+	DECODE_HEAD;
+
+	status = nfsd4_decode_stateid(argp, &clone->cl_src_stateid);
+	if (status)
+		return status;
+	status = nfsd4_decode_stateid(argp, &clone->cl_dst_stateid);
+	if (status)
+		return status;
+
+	READ_BUF(8 + 8 + 8);
+	p = xdr_decode_hyper(p, &clone->cl_src_pos);
+	p = xdr_decode_hyper(p, &clone->cl_dst_pos);
+	p = xdr_decode_hyper(p, &clone->cl_count);
+	DECODE_TAIL;
+}
+
+static __be32
 nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek)
 {
 	DECODE_HEAD;
@@ -1785,6 +1806,7 @@ static nfsd4_dec nfsd4_dec_ops[] = {
 	[OP_READ_PLUS]		= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_SEEK]		= (nfsd4_dec)nfsd4_decode_seek,
 	[OP_WRITE_SAME]		= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_CLONE]		= (nfsd4_dec)nfsd4_decode_clone,
 };
 
 static inline bool
@@ -1815,8 +1837,9 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
 
 	READ_BUF(4);
 	argp->taglen = be32_to_cpup(p++);
-	READ_BUF(argp->taglen + 8);
+	READ_BUF(argp->taglen);
 	SAVEMEM(argp->tag, argp->taglen);
+	READ_BUF(8);
 	argp->minorversion = be32_to_cpup(p++);
 	argp->opcnt = be32_to_cpup(p++);
 	max_reply += 4 + (XDR_QUADLEN(argp->taglen) << 2);
@@ -2838,14 +2861,14 @@ nfsd4_encode_dirent_fattr(struct xdr_stream *xdr, struct nfsd4_readdir *cd,
 	__be32 nfserr;
 	int ignore_crossmnt = 0;
 
-	dentry = lookup_one_len(name, cd->rd_fhp->fh_dentry, namlen);
+	dentry = lookup_one_len_unlocked(name, cd->rd_fhp->fh_dentry, namlen);
 	if (IS_ERR(dentry))
 		return nfserrno(PTR_ERR(dentry));
 	if (d_really_is_negative(dentry)) {
 		/*
-		 * nfsd_buffered_readdir drops the i_mutex between
-		 * readdir and calling this callback, leaving a window
-		 * where this directory entry could have gone away.
+		 * we're not holding the i_mutex here, so there's
+		 * a window where this directory entry could have gone
+		 * away.
 		 */
 		dput(dentry);
 		return nfserr_noent;
@@ -3040,7 +3063,7 @@ static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp,
 		p = xdr_encode_opaque_fixed(p, bcts->sessionid.data,
 						NFS4_MAX_SESSIONID_LEN);
 		*p++ = cpu_to_be32(bcts->dir);
-		/* Sorry, we do not yet support RDMA over 4.1: */
+		/* Upshifting from TCP to RDMA is not supported */
 		*p++ = cpu_to_be32(0);
 	}
 	return nfserr;
@@ -3342,6 +3365,7 @@ static __be32 nfsd4_encode_splice_read(
 	struct xdr_stream *xdr = &resp->xdr;
 	struct xdr_buf *buf = xdr->buf;
 	u32 eof;
+	long len;
 	int space_left;
 	__be32 nfserr;
 	__be32 *p = xdr->p - 2;
@@ -3350,6 +3374,7 @@ static __be32 nfsd4_encode_splice_read(
 	if (xdr->end - xdr->p < 1)
 		return nfserr_resource;
 
+	len = maxcount;
 	nfserr = nfsd_splice_read(read->rd_rqstp, file,
 				  read->rd_offset, &maxcount);
 	if (nfserr) {
@@ -3362,8 +3387,8 @@ static __be32 nfsd4_encode_splice_read(
 		return nfserr;
 	}
 
-	eof = (read->rd_offset + maxcount >=
-	       d_inode(read->rd_fhp->fh_dentry)->i_size);
+	eof = nfsd_eof_on_read(len, maxcount, read->rd_offset,
+				d_inode(read->rd_fhp->fh_dentry)->i_size);
 
 	*(p++) = htonl(eof);
 	*(p++) = htonl(maxcount);
@@ -3433,14 +3458,15 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
 	}
 	read->rd_vlen = v;
 
+	len = maxcount;
 	nfserr = nfsd_readv(file, read->rd_offset, resp->rqstp->rq_vec,
 			read->rd_vlen, &maxcount);
 	if (nfserr)
 		return nfserr;
 	xdr_truncate_encode(xdr, starting_len + 8 + ((maxcount+3)&~3));
 
-	eof = (read->rd_offset + maxcount >=
-	       d_inode(read->rd_fhp->fh_dentry)->i_size);
+	eof = nfsd_eof_on_read(len, maxcount, read->rd_offset,
+				d_inode(read->rd_fhp->fh_dentry)->i_size);
 
 	tmp = htonl(eof);
 	write_bytes_to_xdr_buf(xdr->buf, starting_len    , &tmp, 4);
@@ -4292,6 +4318,7 @@ static nfsd4_enc nfsd4_enc_ops[] = {
 	[OP_READ_PLUS]		= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_SEEK]		= (nfsd4_enc)nfsd4_encode_seek,
 	[OP_WRITE_SAME]		= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_CLONE]		= (nfsd4_enc)nfsd4_encode_noop,
 };
 
 /*
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 46ec934f5dee..54cde9a5864e 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -63,7 +63,6 @@ static unsigned int		longest_chain;
 static unsigned int		longest_chain_cachesize;
 
 static int	nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec);
-static void	cache_cleaner_func(struct work_struct *unused);
 static unsigned long nfsd_reply_cache_count(struct shrinker *shrink,
 					    struct shrink_control *sc);
 static unsigned long nfsd_reply_cache_scan(struct shrinker *shrink,
@@ -76,13 +75,6 @@ static struct shrinker nfsd_reply_cache_shrinker = {
 };
 
 /*
- * locking for the reply cache:
- * A cache entry is "single use" if c_state == RC_INPROG
- * Otherwise, it when accessing _prev or _next, the lock must be held.
- */
-static DECLARE_DELAYED_WORK(cache_cleaner, cache_cleaner_func);
-
-/*
  * Put a cap on the size of the DRC based on the amount of available
  * low memory in the machine.
  *
@@ -203,7 +195,6 @@ void nfsd_reply_cache_shutdown(void)
 	unsigned int i;
 
 	unregister_shrinker(&nfsd_reply_cache_shrinker);
-	cancel_delayed_work_sync(&cache_cleaner);
 
 	for (i = 0; i < drc_hashsize; i++) {
 		struct list_head *head = &drc_hashtbl[i].lru_head;
@@ -217,10 +208,8 @@ void nfsd_reply_cache_shutdown(void)
 	drc_hashtbl = NULL;
 	drc_hashsize = 0;
 
-	if (drc_slab) {
-		kmem_cache_destroy(drc_slab);
-		drc_slab = NULL;
-	}
+	kmem_cache_destroy(drc_slab);
+	drc_slab = NULL;
 }
 
 /*
@@ -232,7 +221,6 @@ lru_put_end(struct nfsd_drc_bucket *b, struct svc_cacherep *rp)
 {
 	rp->c_timestamp = jiffies;
 	list_move_tail(&rp->c_lru, &b->lru_head);
-	schedule_delayed_work(&cache_cleaner, RC_EXPIRE);
 }
 
 static long
@@ -266,7 +254,6 @@ prune_cache_entries(void)
 {
 	unsigned int i;
 	long freed = 0;
-	bool cancel = true;
 
 	for (i = 0; i < drc_hashsize; i++) {
 		struct nfsd_drc_bucket *b = &drc_hashtbl[i];
@@ -275,26 +262,11 @@ prune_cache_entries(void)
 			continue;
 		spin_lock(&b->cache_lock);
 		freed += prune_bucket(b);
-		if (!list_empty(&b->lru_head))
-			cancel = false;
 		spin_unlock(&b->cache_lock);
 	}
-
-	/*
-	 * Conditionally rearm the job to run in RC_EXPIRE since we just
-	 * ran the pruner.
-	 */
-	if (!cancel)
-		mod_delayed_work(system_wq, &cache_cleaner, RC_EXPIRE);
 	return freed;
 }
 
-static void
-cache_cleaner_func(struct work_struct *unused)
-{
-	prune_cache_entries();
-}
-
 static unsigned long
 nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc)
 {
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 350041a40fe5..c1681ce894c5 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -631,10 +631,7 @@ fh_put(struct svc_fh *fhp)
 		fh_unlock(fhp);
 		fhp->fh_dentry = NULL;
 		dput(dentry);
-#ifdef CONFIG_NFSD_V3
-		fhp->fh_pre_saved = 0;
-		fhp->fh_post_saved = 0;
-#endif
+		fh_clear_wcc(fhp);
 	}
 	fh_drop_write(fhp);
 	if (exp) {
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index 1e90dad4926b..f84fe6bf9aee 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -7,6 +7,7 @@
 #ifndef _LINUX_NFSD_NFSFH_H
 #define _LINUX_NFSD_NFSFH_H
 
+#include <linux/crc32.h>
 #include <linux/sunrpc/svc.h>
 #include <uapi/linux/nfsd/nfsfh.h>
 
@@ -26,16 +27,16 @@ static inline ino_t u32_to_ino_t(__u32 uino)
  */
 typedef struct svc_fh {
 	struct knfsd_fh		fh_handle;	/* FH data */
+	int			fh_maxsize;	/* max size for fh_handle */
 	struct dentry *		fh_dentry;	/* validated dentry */
 	struct svc_export *	fh_export;	/* export pointer */
-	int			fh_maxsize;	/* max size for fh_handle */
 
-	unsigned char		fh_locked;	/* inode locked by us */
-	unsigned char		fh_want_write;	/* remount protection taken */
+	bool			fh_locked;	/* inode locked by us */
+	bool			fh_want_write;	/* remount protection taken */
 
 #ifdef CONFIG_NFSD_V3
-	unsigned char		fh_post_saved;	/* post-op attrs saved */
-	unsigned char		fh_pre_saved;	/* pre-op attrs saved */
+	bool			fh_post_saved;	/* post-op attrs saved */
+	bool			fh_pre_saved;	/* pre-op attrs saved */
 
 	/* Pre-op attributes saved during fh_lock */
 	__u64			fh_pre_size;	/* size before operation */
@@ -205,6 +206,28 @@ static inline bool fh_fsid_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2)
 	return true;
 }
 
+#ifdef CONFIG_CRC32
+/**
+ * knfsd_fh_hash - calculate the crc32 hash for the filehandle
+ * @fh - pointer to filehandle
+ *
+ * returns a crc32 hash for the filehandle that is compatible with
+ * the one displayed by "wireshark".
+ */
+
+static inline u32
+knfsd_fh_hash(struct knfsd_fh *fh)
+{
+	return ~crc32_le(0xFFFFFFFF, (unsigned char *)&fh->fh_base, fh->fh_size);
+}
+#else
+static inline u32
+knfsd_fh_hash(struct knfsd_fh *fh)
+{
+	return 0;
+}
+#endif
+
 #ifdef CONFIG_NFSD_V3
 /*
  * The wcc data stored in current_fh should be cleared
@@ -213,8 +236,8 @@ static inline bool fh_fsid_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2)
 static inline void
 fh_clear_wcc(struct svc_fh *fhp)
 {
-	fhp->fh_post_saved = 0;
-	fhp->fh_pre_saved = 0;
+	fhp->fh_post_saved = false;
+	fhp->fh_pre_saved = false;
 }
 
 /*
@@ -231,7 +254,7 @@ fill_pre_wcc(struct svc_fh *fhp)
 		fhp->fh_pre_ctime = inode->i_ctime;
 		fhp->fh_pre_size  = inode->i_size;
 		fhp->fh_pre_change = inode->i_version;
-		fhp->fh_pre_saved = 1;
+		fhp->fh_pre_saved = true;
 	}
 }
 
@@ -265,9 +288,9 @@ fh_lock_nested(struct svc_fh *fhp, unsigned int subclass)
 	}
 
 	inode = d_inode(dentry);
-	mutex_lock_nested(&inode->i_mutex, subclass);
+	inode_lock_nested(inode, subclass);
 	fill_pre_wcc(fhp);
-	fhp->fh_locked = 1;
+	fhp->fh_locked = true;
 }
 
 static inline void
@@ -284,8 +307,8 @@ fh_unlock(struct svc_fh *fhp)
 {
 	if (fhp->fh_locked) {
 		fill_post_wcc(fhp);
-		mutex_unlock(&d_inode(fhp->fh_dentry)->i_mutex);
-		fhp->fh_locked = 0;
+		inode_unlock(d_inode(fhp->fh_dentry));
+		fhp->fh_locked = false;
 	}
 }
 
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index ad4e2377dd63..45007acaf364 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -14,9 +14,13 @@
 
 #include <linux/sunrpc/stats.h>
 #include <linux/sunrpc/svcsock.h>
+#include <linux/sunrpc/svc_xprt.h>
 #include <linux/lockd/bind.h>
 #include <linux/nfsacl.h>
 #include <linux/seq_file.h>
+#include <linux/inetdevice.h>
+#include <net/addrconf.h>
+#include <net/ipv6.h>
 #include <net/net_namespace.h>
 #include "nfsd.h"
 #include "cache.h"
@@ -306,22 +310,81 @@ static void nfsd_shutdown_net(struct net *net)
 	nfsd_shutdown_generic();
 }
 
+static int nfsd_inetaddr_event(struct notifier_block *this, unsigned long event,
+	void *ptr)
+{
+	struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
+	struct net_device *dev = ifa->ifa_dev->dev;
+	struct net *net = dev_net(dev);
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct sockaddr_in sin;
+
+	if (event != NETDEV_DOWN)
+		goto out;
+
+	if (nn->nfsd_serv) {
+		dprintk("nfsd_inetaddr_event: removed %pI4\n", &ifa->ifa_local);
+		sin.sin_family = AF_INET;
+		sin.sin_addr.s_addr = ifa->ifa_local;
+		svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin);
+	}
+
+out:
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block nfsd_inetaddr_notifier = {
+	.notifier_call = nfsd_inetaddr_event,
+};
+
+#if IS_ENABLED(CONFIG_IPV6)
+static int nfsd_inet6addr_event(struct notifier_block *this,
+	unsigned long event, void *ptr)
+{
+	struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr;
+	struct net_device *dev = ifa->idev->dev;
+	struct net *net = dev_net(dev);
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct sockaddr_in6 sin6;
+
+	if (event != NETDEV_DOWN)
+		goto out;
+
+	if (nn->nfsd_serv) {
+		dprintk("nfsd_inet6addr_event: removed %pI6\n", &ifa->addr);
+		sin6.sin6_family = AF_INET6;
+		sin6.sin6_addr = ifa->addr;
+		svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin6);
+	}
+
+out:
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block nfsd_inet6addr_notifier = {
+	.notifier_call = nfsd_inet6addr_event,
+};
+#endif
+
 static void nfsd_last_thread(struct svc_serv *serv, struct net *net)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
+	unregister_inetaddr_notifier(&nfsd_inetaddr_notifier);
+#if IS_ENABLED(CONFIG_IPV6)
+	unregister_inet6addr_notifier(&nfsd_inet6addr_notifier);
+#endif
 	/*
 	 * write_ports can create the server without actually starting
 	 * any threads--if we get shut down before any threads are
 	 * started, then nfsd_last_thread will be run before any of this
-	 * other initialization has been done.
+	 * other initialization has been done except the rpcb information.
 	 */
+	svc_rpcb_cleanup(serv, net);
 	if (!nn->nfsd_net_up)
 		return;
-	nfsd_shutdown_net(net);
-
-	svc_rpcb_cleanup(serv, net);
 
+	nfsd_shutdown_net(net);
 	printk(KERN_WARNING "nfsd: last server has exited, flushing export "
 			    "cache\n");
 	nfsd_export_flush(net);
@@ -425,6 +488,10 @@ int nfsd_create_serv(struct net *net)
 	}
 
 	set_max_drc();
+	register_inetaddr_notifier(&nfsd_inetaddr_notifier);
+#if IS_ENABLED(CONFIG_IPV6)
+	register_inet6addr_notifier(&nfsd_inet6addr_notifier);
+#endif
 	do_gettimeofday(&nn->nfssvc_boot);		/* record boot time */
 	return 0;
 }
diff --git a/fs/nfsd/pnfs.h b/fs/nfsd/pnfs.h
index d4c4453674c6..7d073b9b1553 100644
--- a/fs/nfsd/pnfs.h
+++ b/fs/nfsd/pnfs.h
@@ -21,6 +21,7 @@ struct nfsd4_layout_ops {
 	u32		notify_types;
 
 	__be32 (*proc_getdeviceinfo)(struct super_block *sb,
+			struct nfs4_client *clp,
 			struct nfsd4_getdeviceinfo *gdevp);
 	__be32 (*encode_getdeviceinfo)(struct xdr_stream *xdr,
 			struct nfsd4_getdeviceinfo *gdevp);
@@ -32,10 +33,17 @@ struct nfsd4_layout_ops {
 
 	__be32 (*proc_layoutcommit)(struct inode *inode,
 			struct nfsd4_layoutcommit *lcp);
+
+	void (*fence_client)(struct nfs4_layout_stateid *ls);
 };
 
 extern const struct nfsd4_layout_ops *nfsd4_layout_ops[];
+#ifdef CONFIG_NFSD_BLOCKLAYOUT
 extern const struct nfsd4_layout_ops bl_layout_ops;
+#endif
+#ifdef CONFIG_NFSD_SCSILAYOUT
+extern const struct nfsd4_layout_ops scsi_layout_ops;
+#endif
 
 __be32 nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *cstate, stateid_t *stateid,
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 583ffc13cae2..c050c53036a6 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -65,7 +65,7 @@ struct nfsd4_callback {
 	struct nfs4_client *cb_clp;
 	u32 cb_minorversion;
 	struct rpc_message cb_msg;
-	struct nfsd4_callback_ops *cb_ops;
+	const struct nfsd4_callback_ops *cb_ops;
 	struct work_struct cb_work;
 	int cb_seq_status;
 	int cb_status;
@@ -84,7 +84,7 @@ struct nfsd4_callback_ops {
  * fields that are of general use to any stateid.
  */
 struct nfs4_stid {
-	atomic_t sc_count;
+	atomic_t		sc_count;
 #define NFS4_OPEN_STID 1
 #define NFS4_LOCK_STID 2
 #define NFS4_DELEG_STID 4
@@ -94,11 +94,12 @@ struct nfs4_stid {
 #define NFS4_REVOKED_DELEG_STID 16
 #define NFS4_CLOSED_DELEG_STID 32
 #define NFS4_LAYOUT_STID 64
-	unsigned char sc_type;
-	stateid_t sc_stateid;
-	struct nfs4_client *sc_client;
-	struct nfs4_file *sc_file;
-	void (*sc_free)(struct nfs4_stid *);
+	unsigned char		sc_type;
+	stateid_t		sc_stateid;
+	spinlock_t		sc_lock;
+	struct nfs4_client	*sc_client;
+	struct nfs4_file	*sc_file;
+	void			(*sc_free)(struct nfs4_stid *);
 };
 
 /*
@@ -364,15 +365,6 @@ struct nfs4_client_reclaim {
 	char			cr_recdir[HEXDIR_LEN]; /* recover dir */
 };
 
-static inline void
-update_stateid(stateid_t *stateid)
-{
-	stateid->si_generation++;
-	/* Wraparound recommendation from 3530bis-13 9.1.3.2: */
-	if (stateid->si_generation == 0)
-		stateid->si_generation = 1;
-}
-
 /* A reasonable value for REPLAY_ISIZE was estimated as follows:  
  * The OPEN response, typically the largest, requires 
  *   4(status) + 8(stateid) + 20(changeinfo) + 4(rflags) +  8(verifier) + 
@@ -534,15 +526,16 @@ struct nfs4_file {
  * Better suggestions welcome.
  */
 struct nfs4_ol_stateid {
-	struct nfs4_stid    st_stid; /* must be first field */
-	struct list_head              st_perfile;
-	struct list_head              st_perstateowner;
-	struct list_head              st_locks;
-	struct nfs4_stateowner      * st_stateowner;
-	struct nfs4_clnt_odstate    * st_clnt_odstate;
-	unsigned char                 st_access_bmap;
-	unsigned char                 st_deny_bmap;
-	struct nfs4_ol_stateid         * st_openstp;
+	struct nfs4_stid		st_stid;
+	struct list_head		st_perfile;
+	struct list_head		st_perstateowner;
+	struct list_head		st_locks;
+	struct nfs4_stateowner		*st_stateowner;
+	struct nfs4_clnt_odstate	*st_clnt_odstate;
+	unsigned char			st_access_bmap;
+	unsigned char			st_deny_bmap;
+	struct nfs4_ol_stateid		*st_openstp;
+	struct rw_semaphore		st_rwsem;
 };
 
 static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s)
@@ -561,6 +554,7 @@ struct nfs4_layout_stateid {
 	struct nfsd4_callback		ls_recall;
 	stateid_t			ls_recall_sid;
 	bool				ls_recalled;
+	struct mutex			ls_mutex;
 };
 
 static inline struct nfs4_layout_stateid *layoutstateid(struct nfs4_stid *s)
@@ -584,8 +578,8 @@ struct nfsd4_compound_state;
 struct nfsd_net;
 
 extern __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
-		struct nfsd4_compound_state *cstate, stateid_t *stateid,
-		int flags, struct file **filp, bool *tmp_file);
+		struct nfsd4_compound_state *cstate, struct svc_fh *fhp,
+		stateid_t *stateid, int flags, struct file **filp, bool *tmp_file);
 __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
 		     stateid_t *stateid, unsigned char typemask,
 		     struct nfs4_stid **s, struct nfsd_net *nn);
@@ -593,6 +587,7 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl,
 		struct kmem_cache *slab);
 void nfs4_unhash_stid(struct nfs4_stid *s);
 void nfs4_put_stid(struct nfs4_stid *s);
+void nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid);
 void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *, struct nfsd_net *);
 extern void nfs4_release_reclaim(struct nfsd_net *);
 extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(const char *recdir,
@@ -604,7 +599,7 @@ extern void nfsd4_probe_callback(struct nfs4_client *clp);
 extern void nfsd4_probe_callback_sync(struct nfs4_client *clp);
 extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *);
 extern void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
-		struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op);
+		const struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op);
 extern void nfsd4_run_cb(struct nfsd4_callback *cb);
 extern int nfsd4_create_callback_queue(void);
 extern void nfsd4_destroy_callback_queue(void);
diff --git a/fs/nfsd/trace.c b/fs/nfsd/trace.c
index 82f89070594c..90967466a1e5 100644
--- a/fs/nfsd/trace.c
+++ b/fs/nfsd/trace.c
@@ -1,5 +1,3 @@
 
-#include "state.h"
-
 #define CREATE_TRACE_POINTS
 #include "trace.h"
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index c668520c344b..3287041905da 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -8,6 +8,49 @@
 #define _NFSD_TRACE_H
 
 #include <linux/tracepoint.h>
+#include "nfsfh.h"
+
+DECLARE_EVENT_CLASS(nfsd_io_class,
+	TP_PROTO(struct svc_rqst *rqstp,
+		 struct svc_fh	*fhp,
+		 loff_t		offset,
+		 int		len),
+	TP_ARGS(rqstp, fhp, offset, len),
+	TP_STRUCT__entry(
+		__field(__be32, xid)
+		__field_struct(struct knfsd_fh, fh)
+		__field(loff_t, offset)
+		__field(int, len)
+	),
+	TP_fast_assign(
+		__entry->xid = rqstp->rq_xid,
+		fh_copy_shallow(&__entry->fh, &fhp->fh_handle);
+		__entry->offset = offset;
+		__entry->len = len;
+	),
+	TP_printk("xid=0x%x fh=0x%x offset=%lld len=%d",
+		  __be32_to_cpu(__entry->xid), knfsd_fh_hash(&__entry->fh),
+		  __entry->offset, __entry->len)
+)
+
+#define DEFINE_NFSD_IO_EVENT(name)		\
+DEFINE_EVENT(nfsd_io_class, name,		\
+	TP_PROTO(struct svc_rqst *rqstp,	\
+		 struct svc_fh	*fhp,		\
+		 loff_t		offset,		\
+		 int		len),		\
+	TP_ARGS(rqstp, fhp, offset, len))
+
+DEFINE_NFSD_IO_EVENT(read_start);
+DEFINE_NFSD_IO_EVENT(read_opened);
+DEFINE_NFSD_IO_EVENT(read_io_done);
+DEFINE_NFSD_IO_EVENT(read_done);
+DEFINE_NFSD_IO_EVENT(write_start);
+DEFINE_NFSD_IO_EVENT(write_opened);
+DEFINE_NFSD_IO_EVENT(write_io_done);
+DEFINE_NFSD_IO_EVENT(write_done);
+
+#include "state.h"
 
 DECLARE_EVENT_CLASS(nfsd_stateid_class,
 	TP_PROTO(stateid_t *stp),
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 45c04979e7b3..d40010e4f1a9 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -36,12 +36,14 @@
 #endif /* CONFIG_NFSD_V3 */
 
 #ifdef CONFIG_NFSD_V4
+#include "../internal.h"
 #include "acl.h"
 #include "idmap.h"
 #endif /* CONFIG_NFSD_V4 */
 
 #include "nfsd.h"
 #include "vfs.h"
+#include "trace.h"
 
 #define NFSDDBG_FACILITY		NFSDDBG_FILEOP
 
@@ -217,10 +219,16 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		host_err = PTR_ERR(dentry);
 		if (IS_ERR(dentry))
 			goto out_nfserr;
-		/*
-		 * check if we have crossed a mount point ...
-		 */
 		if (nfsd_mountpoint(dentry, exp)) {
+			/*
+			 * We don't need the i_mutex after all.  It's
+			 * still possible we could open this (regular
+			 * files can be mountpoints too), but the
+			 * i_mutex is just there to prevent renames of
+			 * something that we might be about to delegate,
+			 * and a mountpoint won't be renamed:
+			 */
+			fh_unlock(fhp);
 			if ((host_err = nfsd_cross_mnt(rqstp, &dentry, &exp))) {
 				dput(dentry);
 				goto out_nfserr;
@@ -485,9 +493,9 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp,
 
 	dentry = fhp->fh_dentry;
 
-	mutex_lock(&d_inode(dentry)->i_mutex);
+	inode_lock(d_inode(dentry));
 	host_error = security_inode_setsecctx(dentry, label->data, label->len);
-	mutex_unlock(&d_inode(dentry)->i_mutex);
+	inode_unlock(d_inode(dentry));
 	return nfserrno(host_error);
 }
 #else
@@ -498,6 +506,13 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp,
 }
 #endif
 
+__be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst,
+		u64 dst_pos, u64 count)
+{
+	return nfserrno(vfs_clone_file_range(src, src_pos, dst, dst_pos,
+			count));
+}
+
 __be32 nfsd4_vfs_fallocate(struct svc_rqst *rqstp, struct svc_fh *fhp,
 			   struct file *file, loff_t offset, loff_t len,
 			   int flags)
@@ -855,7 +870,7 @@ __be32 nfsd_readv(struct file *file, loff_t offset, struct kvec *vec, int vlen,
 
 	oldfs = get_fs();
 	set_fs(KERNEL_DS);
-	host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset);
+	host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset, 0);
 	set_fs(oldfs);
 	return nfsd_finish_read(file, count, host_err);
 }
@@ -942,7 +957,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 
 	/* Write the data. */
 	oldfs = get_fs(); set_fs(KERNEL_DS);
-	host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos);
+	host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos, 0);
 	set_fs(oldfs);
 	if (host_err < 0)
 		goto out_nfserr;
@@ -983,16 +998,23 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	struct raparms	*ra;
 	__be32 err;
 
+	trace_read_start(rqstp, fhp, offset, vlen);
 	err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, &file);
 	if (err)
 		return err;
 
 	ra = nfsd_init_raparms(file);
+
+	trace_read_opened(rqstp, fhp, offset, vlen);
 	err = nfsd_vfs_read(rqstp, file, offset, vec, vlen, count);
+	trace_read_io_done(rqstp, fhp, offset, vlen);
+
 	if (ra)
 		nfsd_put_raparams(file, ra);
 	fput(file);
 
+	trace_read_done(rqstp, fhp, offset, vlen);
+
 	return err;
 }
 
@@ -1008,24 +1030,31 @@ nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 {
 	__be32			err = 0;
 
+	trace_write_start(rqstp, fhp, offset, vlen);
+
 	if (file) {
 		err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
 				NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE);
 		if (err)
 			goto out;
+		trace_write_opened(rqstp, fhp, offset, vlen);
 		err = nfsd_vfs_write(rqstp, fhp, file, offset, vec, vlen, cnt,
 				stablep);
+		trace_write_io_done(rqstp, fhp, offset, vlen);
 	} else {
 		err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_WRITE, &file);
 		if (err)
 			goto out;
 
+		trace_write_opened(rqstp, fhp, offset, vlen);
 		if (cnt)
 			err = nfsd_vfs_write(rqstp, fhp, file, offset, vec, vlen,
 					     cnt, stablep);
+		trace_write_io_done(rqstp, fhp, offset, vlen);
 		fput(file);
 	}
 out:
+	trace_write_done(rqstp, fhp, offset, vlen);
 	return err;
 }
 
@@ -1631,7 +1660,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 	/* cannot use fh_lock as we need deadlock protective ordering
 	 * so do it by hand */
 	trap = lock_rename(tdentry, fdentry);
-	ffhp->fh_locked = tfhp->fh_locked = 1;
+	ffhp->fh_locked = tfhp->fh_locked = true;
 	fill_pre_wcc(ffhp);
 	fill_pre_wcc(tfhp);
 
@@ -1681,7 +1710,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 	fill_post_wcc(ffhp);
 	fill_post_wcc(tfhp);
 	unlock_rename(tdentry, fdentry);
-	ffhp->fh_locked = tfhp->fh_locked = 0;
+	ffhp->fh_locked = tfhp->fh_locked = false;
 	fh_drop_write(ffhp);
 
 out:
@@ -1809,7 +1838,6 @@ static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func,
 	offset = *offsetp;
 
 	while (1) {
-		struct inode *dir_inode = file_inode(file);
 		unsigned int reclen;
 
 		cdp->err = nfserr_eof; /* will be cleared on successful read */
@@ -1828,15 +1856,6 @@ static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func,
 		if (!size)
 			break;
 
-		/*
-		 * Various filldir functions may end up calling back into
-		 * lookup_one_len() and the file system's ->lookup() method.
-		 * These expect i_mutex to be held, as it would within readdir.
-		 */
-		host_err = mutex_lock_killable(&dir_inode->i_mutex);
-		if (host_err)
-			break;
-
 		de = (struct buffered_dirent *)buf.dirent;
 		while (size > 0) {
 			offset = de->offset;
@@ -1853,7 +1872,6 @@ static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func,
 			size -= reclen;
 			de = (struct buffered_dirent *)((char *)de + reclen);
 		}
-		mutex_unlock(&dir_inode->i_mutex);
 		if (size > 0) /* We bailed out early */
 			break;
 
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index fee2451ae248..2d573ec057f8 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -56,6 +56,8 @@ __be32          nfsd4_set_nfs4_label(struct svc_rqst *, struct svc_fh *,
 		    struct xdr_netobj *);
 __be32		nfsd4_vfs_fallocate(struct svc_rqst *, struct svc_fh *,
 				    struct file *, loff_t, loff_t, int);
+__be32		nfsd4_clone_file_range(struct file *, u64, struct file *,
+			u64, u64);
 #endif /* CONFIG_NFSD_V4 */
 __be32		nfsd_create(struct svc_rqst *, struct svc_fh *,
 				char *name, int len, struct iattr *attrs,
@@ -112,14 +114,14 @@ static inline int fh_want_write(struct svc_fh *fh)
 	int ret = mnt_want_write(fh->fh_export->ex_path.mnt);
 
 	if (!ret)
-		fh->fh_want_write = 1;
+		fh->fh_want_write = true;
 	return ret;
 }
 
 static inline void fh_drop_write(struct svc_fh *fh)
 {
 	if (fh->fh_want_write) {
-		fh->fh_want_write = 0;
+		fh->fh_want_write = false;
 		mnt_drop_write(fh->fh_export->ex_path.mnt);
 	}
 }
@@ -137,4 +139,23 @@ static inline int nfsd_create_is_exclusive(int createmode)
 	       || createmode == NFS4_CREATE_EXCLUSIVE4_1;
 }
 
+static inline bool nfsd_eof_on_read(long requested, long read,
+				loff_t offset, loff_t size)
+{
+	/* We assume a short read means eof: */
+	if (requested > read)
+		return true;
+	/*
+	 * A non-short read might also reach end of file.  The spec
+	 * still requires us to set eof in that case.
+	 *
+	 * Further operations may have modified the file size since
+	 * the read, so the following check is not atomic with the read.
+	 * We've only seen that cause a problem for a client in the case
+	 * where the read returned a count of 0 without setting eof.
+	 * That case was fixed by the addition of the above check.
+	 */
+	return (offset + read >= size);
+}
+
 #endif /* LINUX_NFSD_VFS_H */
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 9f991007a578..d9554813e58a 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -491,6 +491,15 @@ struct nfsd4_fallocate {
 	u64		falloc_length;
 };
 
+struct nfsd4_clone {
+	/* request */
+	stateid_t	cl_src_stateid;
+	stateid_t	cl_dst_stateid;
+	u64		cl_src_pos;
+	u64		cl_dst_pos;
+	u64		cl_count;
+};
+
 struct nfsd4_seek {
 	/* request */
 	stateid_t	seek_stateid;
@@ -555,6 +564,7 @@ struct nfsd4_op {
 		/* NFSv4.2 */
 		struct nfsd4_fallocate		allocate;
 		struct nfsd4_fallocate		deallocate;
+		struct nfsd4_clone		clone;
 		struct nfsd4_seek		seek;
 	} u;
 	struct nfs4_replay *			replay;
@@ -632,7 +642,7 @@ static inline void
 set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp)
 {
 	BUG_ON(!fhp->fh_pre_saved);
-	cinfo->atomic = fhp->fh_post_saved;
+	cinfo->atomic = (u32)fhp->fh_post_saved;
 	cinfo->change_supported = IS_I_VERSION(d_inode(fhp->fh_dentry));
 
 	cinfo->before_change = fhp->fh_pre_change;
diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c
index 8df0f3b7839b..2ccbf5531554 100644
--- a/fs/nilfs2/alloc.c
+++ b/fs/nilfs2/alloc.c
@@ -133,38 +133,38 @@ nilfs_palloc_bitmap_blkoff(const struct inode *inode, unsigned long group)
 
 /**
  * nilfs_palloc_group_desc_nfrees - get the number of free entries in a group
- * @inode: inode of metadata file using this allocator
- * @group: group number
  * @desc: pointer to descriptor structure for the group
+ * @lock: spin lock protecting @desc
  */
 static unsigned long
-nilfs_palloc_group_desc_nfrees(struct inode *inode, unsigned long group,
-			       const struct nilfs_palloc_group_desc *desc)
+nilfs_palloc_group_desc_nfrees(const struct nilfs_palloc_group_desc *desc,
+			       spinlock_t *lock)
 {
 	unsigned long nfree;
 
-	spin_lock(nilfs_mdt_bgl_lock(inode, group));
+	spin_lock(lock);
 	nfree = le32_to_cpu(desc->pg_nfrees);
-	spin_unlock(nilfs_mdt_bgl_lock(inode, group));
+	spin_unlock(lock);
 	return nfree;
 }
 
 /**
  * nilfs_palloc_group_desc_add_entries - adjust count of free entries
- * @inode: inode of metadata file using this allocator
- * @group: group number
  * @desc: pointer to descriptor structure for the group
+ * @lock: spin lock protecting @desc
  * @n: delta to be added
  */
-static void
-nilfs_palloc_group_desc_add_entries(struct inode *inode,
-				    unsigned long group,
-				    struct nilfs_palloc_group_desc *desc,
-				    u32 n)
+static u32
+nilfs_palloc_group_desc_add_entries(struct nilfs_palloc_group_desc *desc,
+				    spinlock_t *lock, u32 n)
 {
-	spin_lock(nilfs_mdt_bgl_lock(inode, group));
+	u32 nfree;
+
+	spin_lock(lock);
 	le32_add_cpu(&desc->pg_nfrees, n);
-	spin_unlock(nilfs_mdt_bgl_lock(inode, group));
+	nfree = le32_to_cpu(desc->pg_nfrees);
+	spin_unlock(lock);
+	return nfree;
 }
 
 /**
@@ -240,6 +240,26 @@ static int nilfs_palloc_get_block(struct inode *inode, unsigned long blkoff,
 }
 
 /**
+ * nilfs_palloc_delete_block - delete a block on the persistent allocator file
+ * @inode: inode of metadata file using this allocator
+ * @blkoff: block offset
+ * @prev: nilfs_bh_assoc struct of the last used buffer
+ * @lock: spin lock protecting @prev
+ */
+static int nilfs_palloc_delete_block(struct inode *inode, unsigned long blkoff,
+				     struct nilfs_bh_assoc *prev,
+				     spinlock_t *lock)
+{
+	spin_lock(lock);
+	if (prev->bh && blkoff == prev->blkoff) {
+		brelse(prev->bh);
+		prev->bh = NULL;
+	}
+	spin_unlock(lock);
+	return nilfs_mdt_delete_block(inode, blkoff);
+}
+
+/**
  * nilfs_palloc_get_desc_block - get buffer head of a group descriptor block
  * @inode: inode of metadata file using this allocator
  * @group: group number
@@ -278,6 +298,22 @@ static int nilfs_palloc_get_bitmap_block(struct inode *inode,
 }
 
 /**
+ * nilfs_palloc_delete_bitmap_block - delete a bitmap block
+ * @inode: inode of metadata file using this allocator
+ * @group: group number
+ */
+static int nilfs_palloc_delete_bitmap_block(struct inode *inode,
+					    unsigned long group)
+{
+	struct nilfs_palloc_cache *cache = NILFS_MDT(inode)->mi_palloc_cache;
+
+	return nilfs_palloc_delete_block(inode,
+					 nilfs_palloc_bitmap_blkoff(inode,
+								    group),
+					 &cache->prev_bitmap, &cache->lock);
+}
+
+/**
  * nilfs_palloc_get_entry_block - get buffer head of an entry block
  * @inode: inode of metadata file using this allocator
  * @nr: serial number of the entry (e.g. inode number)
@@ -296,6 +332,20 @@ int nilfs_palloc_get_entry_block(struct inode *inode, __u64 nr,
 }
 
 /**
+ * nilfs_palloc_delete_entry_block - delete an entry block
+ * @inode: inode of metadata file using this allocator
+ * @nr: serial number of the entry
+ */
+static int nilfs_palloc_delete_entry_block(struct inode *inode, __u64 nr)
+{
+	struct nilfs_palloc_cache *cache = NILFS_MDT(inode)->mi_palloc_cache;
+
+	return nilfs_palloc_delete_block(inode,
+					 nilfs_palloc_entry_blkoff(inode, nr),
+					 &cache->prev_entry, &cache->lock);
+}
+
+/**
  * nilfs_palloc_block_get_group_desc - get kernel address of a group descriptor
  * @inode: inode of metadata file using this allocator
  * @group: group number
@@ -332,51 +382,40 @@ void *nilfs_palloc_block_get_entry(const struct inode *inode, __u64 nr,
 
 /**
  * nilfs_palloc_find_available_slot - find available slot in a group
- * @inode: inode of metadata file using this allocator
- * @group: group number
- * @target: offset number of an entry in the group (start point)
  * @bitmap: bitmap of the group
+ * @target: offset number of an entry in the group (start point)
  * @bsize: size in bits
+ * @lock: spin lock protecting @bitmap
  */
-static int nilfs_palloc_find_available_slot(struct inode *inode,
-					    unsigned long group,
+static int nilfs_palloc_find_available_slot(unsigned char *bitmap,
 					    unsigned long target,
-					    unsigned char *bitmap,
-					    int bsize)
-{
-	int curr, pos, end, i;
-
-	if (target > 0) {
-		end = (target + BITS_PER_LONG - 1) & ~(BITS_PER_LONG - 1);
-		if (end > bsize)
-			end = bsize;
-		pos = nilfs_find_next_zero_bit(bitmap, end, target);
-		if (pos < end &&
-		    !nilfs_set_bit_atomic(
-			    nilfs_mdt_bgl_lock(inode, group), pos, bitmap))
-			return pos;
-	} else
-		end = 0;
-
-	for (i = 0, curr = end;
-	     i < bsize;
-	     i += BITS_PER_LONG, curr += BITS_PER_LONG) {
-		/* wrap around */
-		if (curr >= bsize)
-			curr = 0;
-		while (*((unsigned long *)bitmap + curr / BITS_PER_LONG)
-		       != ~0UL) {
-			end = curr + BITS_PER_LONG;
-			if (end > bsize)
-				end = bsize;
-			pos = nilfs_find_next_zero_bit(bitmap, end, curr);
-			if ((pos < end) &&
-			    !nilfs_set_bit_atomic(
-				    nilfs_mdt_bgl_lock(inode, group), pos,
-				    bitmap))
+					    unsigned bsize,
+					    spinlock_t *lock)
+{
+	int pos, end = bsize;
+
+	if (likely(target < bsize)) {
+		pos = target;
+		do {
+			pos = nilfs_find_next_zero_bit(bitmap, end, pos);
+			if (pos >= end)
+				break;
+			if (!nilfs_set_bit_atomic(lock, pos, bitmap))
 				return pos;
-		}
+		} while (++pos < end);
+
+		end = target;
+	}
+
+	/* wrap around */
+	for (pos = 0; pos < end; pos++) {
+		pos = nilfs_find_next_zero_bit(bitmap, end, pos);
+		if (pos >= end)
+			break;
+		if (!nilfs_set_bit_atomic(lock, pos, bitmap))
+			return pos;
 	}
+
 	return -ENOSPC;
 }
 
@@ -475,15 +514,15 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
 	void *desc_kaddr, *bitmap_kaddr;
 	unsigned long group, maxgroup, ngroups;
 	unsigned long group_offset, maxgroup_offset;
-	unsigned long n, entries_per_group, groups_per_desc_block;
+	unsigned long n, entries_per_group;
 	unsigned long i, j;
+	spinlock_t *lock;
 	int pos, ret;
 
 	ngroups = nilfs_palloc_groups_count(inode);
 	maxgroup = ngroups - 1;
 	group = nilfs_palloc_group(inode, req->pr_entry_nr, &group_offset);
 	entries_per_group = nilfs_palloc_entries_per_group(inode);
-	groups_per_desc_block = nilfs_palloc_groups_per_desc_block(inode);
 
 	for (i = 0; i < ngroups; i += n) {
 		if (group >= ngroups) {
@@ -501,8 +540,8 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
 		n = nilfs_palloc_rest_groups_in_desc_block(inode, group,
 							   maxgroup);
 		for (j = 0; j < n; j++, desc++, group++) {
-			if (nilfs_palloc_group_desc_nfrees(inode, group, desc)
-			    > 0) {
+			lock = nilfs_mdt_bgl_lock(inode, group);
+			if (nilfs_palloc_group_desc_nfrees(desc, lock) > 0) {
 				ret = nilfs_palloc_get_bitmap_block(
 					inode, group, 1, &bitmap_bh);
 				if (ret < 0)
@@ -510,12 +549,12 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
 				bitmap_kaddr = kmap(bitmap_bh->b_page);
 				bitmap = bitmap_kaddr + bh_offset(bitmap_bh);
 				pos = nilfs_palloc_find_available_slot(
-					inode, group, group_offset, bitmap,
-					entries_per_group);
+					bitmap, group_offset,
+					entries_per_group, lock);
 				if (pos >= 0) {
 					/* found a free entry */
 					nilfs_palloc_group_desc_add_entries(
-						inode, group, desc, -1);
+						desc, lock, -1);
 					req->pr_entry_nr =
 						entries_per_group * group + pos;
 					kunmap(desc_bh->b_page);
@@ -573,6 +612,7 @@ void nilfs_palloc_commit_free_entry(struct inode *inode,
 	unsigned long group, group_offset;
 	unsigned char *bitmap;
 	void *desc_kaddr, *bitmap_kaddr;
+	spinlock_t *lock;
 
 	group = nilfs_palloc_group(inode, req->pr_entry_nr, &group_offset);
 	desc_kaddr = kmap(req->pr_desc_bh->b_page);
@@ -580,13 +620,15 @@ void nilfs_palloc_commit_free_entry(struct inode *inode,
 						 req->pr_desc_bh, desc_kaddr);
 	bitmap_kaddr = kmap(req->pr_bitmap_bh->b_page);
 	bitmap = bitmap_kaddr + bh_offset(req->pr_bitmap_bh);
+	lock = nilfs_mdt_bgl_lock(inode, group);
 
-	if (!nilfs_clear_bit_atomic(nilfs_mdt_bgl_lock(inode, group),
-				    group_offset, bitmap))
-		printk(KERN_WARNING "%s: entry number %llu already freed\n",
-		       __func__, (unsigned long long)req->pr_entry_nr);
+	if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap))
+		nilfs_warning(inode->i_sb, __func__,
+			      "entry number %llu already freed: ino=%lu\n",
+			      (unsigned long long)req->pr_entry_nr,
+			      (unsigned long)inode->i_ino);
 	else
-		nilfs_palloc_group_desc_add_entries(inode, group, desc, 1);
+		nilfs_palloc_group_desc_add_entries(desc, lock, 1);
 
 	kunmap(req->pr_bitmap_bh->b_page);
 	kunmap(req->pr_desc_bh->b_page);
@@ -611,6 +653,7 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode,
 	void *desc_kaddr, *bitmap_kaddr;
 	unsigned char *bitmap;
 	unsigned long group, group_offset;
+	spinlock_t *lock;
 
 	group = nilfs_palloc_group(inode, req->pr_entry_nr, &group_offset);
 	desc_kaddr = kmap(req->pr_desc_bh->b_page);
@@ -618,12 +661,15 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode,
 						 req->pr_desc_bh, desc_kaddr);
 	bitmap_kaddr = kmap(req->pr_bitmap_bh->b_page);
 	bitmap = bitmap_kaddr + bh_offset(req->pr_bitmap_bh);
-	if (!nilfs_clear_bit_atomic(nilfs_mdt_bgl_lock(inode, group),
-				    group_offset, bitmap))
-		printk(KERN_WARNING "%s: entry number %llu already freed\n",
-		       __func__, (unsigned long long)req->pr_entry_nr);
+	lock = nilfs_mdt_bgl_lock(inode, group);
+
+	if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap))
+		nilfs_warning(inode->i_sb, __func__,
+			      "entry number %llu already freed: ino=%lu\n",
+			      (unsigned long long)req->pr_entry_nr,
+			      (unsigned long)inode->i_ino);
 	else
-		nilfs_palloc_group_desc_add_entries(inode, group, desc, 1);
+		nilfs_palloc_group_desc_add_entries(desc, lock, 1);
 
 	kunmap(req->pr_bitmap_bh->b_page);
 	kunmap(req->pr_desc_bh->b_page);
@@ -680,22 +726,6 @@ void nilfs_palloc_abort_free_entry(struct inode *inode,
 }
 
 /**
- * nilfs_palloc_group_is_in - judge if an entry is in a group
- * @inode: inode of metadata file using this allocator
- * @group: group number
- * @nr: serial number of the entry (e.g. inode number)
- */
-static int
-nilfs_palloc_group_is_in(struct inode *inode, unsigned long group, __u64 nr)
-{
-	__u64 first, last;
-
-	first = group * nilfs_palloc_entries_per_group(inode);
-	last = first + nilfs_palloc_entries_per_group(inode) - 1;
-	return (nr >= first) && (nr <= last);
-}
-
-/**
  * nilfs_palloc_freev - deallocate a set of persistent objects
  * @inode: inode of metadata file using this allocator
  * @entry_nrs: array of entry numbers to be deallocated
@@ -708,9 +738,18 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
 	unsigned char *bitmap;
 	void *desc_kaddr, *bitmap_kaddr;
 	unsigned long group, group_offset;
-	int i, j, n, ret;
+	__u64 group_min_nr, last_nrs[8];
+	const unsigned long epg = nilfs_palloc_entries_per_group(inode);
+	const unsigned epb = NILFS_MDT(inode)->mi_entries_per_block;
+	unsigned entry_start, end, pos;
+	spinlock_t *lock;
+	int i, j, k, ret;
+	u32 nfree;
 
 	for (i = 0; i < nitems; i = j) {
+		int change_group = false;
+		int nempties = 0, n = 0;
+
 		group = nilfs_palloc_group(inode, entry_nrs[i], &group_offset);
 		ret = nilfs_palloc_get_desc_block(inode, group, 0, &desc_bh);
 		if (ret < 0)
@@ -721,38 +760,89 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
 			brelse(desc_bh);
 			return ret;
 		}
-		desc_kaddr = kmap(desc_bh->b_page);
-		desc = nilfs_palloc_block_get_group_desc(
-			inode, group, desc_bh, desc_kaddr);
+
+		/* Get the first entry number of the group */
+		group_min_nr = (__u64)group * epg;
+
 		bitmap_kaddr = kmap(bitmap_bh->b_page);
 		bitmap = bitmap_kaddr + bh_offset(bitmap_bh);
-		for (j = i, n = 0;
-		     (j < nitems) && nilfs_palloc_group_is_in(inode, group,
-							      entry_nrs[j]);
-		     j++) {
-			nilfs_palloc_group(inode, entry_nrs[j], &group_offset);
-			if (!nilfs_clear_bit_atomic(
-				    nilfs_mdt_bgl_lock(inode, group),
-				    group_offset, bitmap)) {
-				printk(KERN_WARNING
-				       "%s: entry number %llu already freed\n",
-				       __func__,
-				       (unsigned long long)entry_nrs[j]);
+		lock = nilfs_mdt_bgl_lock(inode, group);
+
+		j = i;
+		entry_start = rounddown(group_offset, epb);
+		do {
+			if (!nilfs_clear_bit_atomic(lock, group_offset,
+						    bitmap)) {
+				nilfs_warning(inode->i_sb, __func__,
+					      "entry number %llu already freed: ino=%lu\n",
+					      (unsigned long long)entry_nrs[j],
+					      (unsigned long)inode->i_ino);
 			} else {
 				n++;
 			}
-		}
-		nilfs_palloc_group_desc_add_entries(inode, group, desc, n);
+
+			j++;
+			if (j >= nitems || entry_nrs[j] < group_min_nr ||
+			    entry_nrs[j] >= group_min_nr + epg) {
+				change_group = true;
+			} else {
+				group_offset = entry_nrs[j] - group_min_nr;
+				if (group_offset >= entry_start &&
+				    group_offset < entry_start + epb) {
+					/* This entry is in the same block */
+					continue;
+				}
+			}
+
+			/* Test if the entry block is empty or not */
+			end = entry_start + epb;
+			pos = nilfs_find_next_bit(bitmap, end, entry_start);
+			if (pos >= end) {
+				last_nrs[nempties++] = entry_nrs[j - 1];
+				if (nempties >= ARRAY_SIZE(last_nrs))
+					break;
+			}
+
+			if (change_group)
+				break;
+
+			/* Go on to the next entry block */
+			entry_start = rounddown(group_offset, epb);
+		} while (true);
 
 		kunmap(bitmap_bh->b_page);
-		kunmap(desc_bh->b_page);
+		mark_buffer_dirty(bitmap_bh);
+		brelse(bitmap_bh);
 
+		for (k = 0; k < nempties; k++) {
+			ret = nilfs_palloc_delete_entry_block(inode,
+							      last_nrs[k]);
+			if (ret && ret != -ENOENT) {
+				nilfs_warning(inode->i_sb, __func__,
+					      "failed to delete block of entry %llu: ino=%lu, err=%d\n",
+					      (unsigned long long)last_nrs[k],
+					      (unsigned long)inode->i_ino, ret);
+			}
+		}
+
+		desc_kaddr = kmap_atomic(desc_bh->b_page);
+		desc = nilfs_palloc_block_get_group_desc(
+			inode, group, desc_bh, desc_kaddr);
+		nfree = nilfs_palloc_group_desc_add_entries(desc, lock, n);
+		kunmap_atomic(desc_kaddr);
 		mark_buffer_dirty(desc_bh);
-		mark_buffer_dirty(bitmap_bh);
 		nilfs_mdt_mark_dirty(inode);
-
-		brelse(bitmap_bh);
 		brelse(desc_bh);
+
+		if (nfree == nilfs_palloc_entries_per_group(inode)) {
+			ret = nilfs_palloc_delete_bitmap_block(inode, group);
+			if (ret && ret != -ENOENT) {
+				nilfs_warning(inode->i_sb, __func__,
+					      "failed to delete bitmap block of group %lu: ino=%lu, err=%d\n",
+					      group,
+					      (unsigned long)inode->i_ino, ret);
+			}
+		}
 	}
 	return 0;
 }
diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h
index 4bd6451b5703..6e6f49aa53df 100644
--- a/fs/nilfs2/alloc.h
+++ b/fs/nilfs2/alloc.h
@@ -77,6 +77,7 @@ int nilfs_palloc_freev(struct inode *, __u64 *, size_t);
 #define nilfs_set_bit_atomic		ext2_set_bit_atomic
 #define nilfs_clear_bit_atomic		ext2_clear_bit_atomic
 #define nilfs_find_next_zero_bit	find_next_zero_bit_le
+#define nilfs_find_next_bit		find_next_bit_le
 
 /**
  * struct nilfs_bh_assoc - block offset and buffer head association
diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c
index 27f75bcbeb30..a9fb3636c142 100644
--- a/fs/nilfs2/bmap.c
+++ b/fs/nilfs2/bmap.c
@@ -458,7 +458,7 @@ __u64 nilfs_bmap_data_get_key(const struct nilfs_bmap *bmap,
 	struct buffer_head *pbh;
 	__u64 key;
 
-	key = page_index(bh->b_page) << (PAGE_CACHE_SHIFT -
+	key = page_index(bh->b_page) << (PAGE_SHIFT -
 					 bmap->b_inode->i_blkbits);
 	for (pbh = page_buffers(bh->b_page); pbh != bh; pbh = pbh->b_this_page)
 		key++;
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index a35ae35e6932..e0c9daf9aa22 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -62,7 +62,7 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr)
 	set_buffer_uptodate(bh);
 
 	unlock_page(bh->b_page);
-	page_cache_release(bh->b_page);
+	put_page(bh->b_page);
 	return bh;
 }
 
@@ -128,7 +128,7 @@ found:
 
 out_locked:
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 	return err;
 }
 
@@ -146,7 +146,7 @@ void nilfs_btnode_delete(struct buffer_head *bh)
 	pgoff_t index = page_index(page);
 	int still_dirty;
 
-	page_cache_get(page);
+	get_page(page);
 	lock_page(page);
 	wait_on_page_writeback(page);
 
@@ -154,7 +154,7 @@ void nilfs_btnode_delete(struct buffer_head *bh)
 	still_dirty = PageDirty(page);
 	mapping = page->mapping;
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 
 	if (!still_dirty && mapping)
 		invalidate_inode_pages2_range(mapping, index, index);
@@ -181,7 +181,7 @@ int nilfs_btnode_prepare_change_key(struct address_space *btnc,
 	obh = ctxt->bh;
 	ctxt->newbh = NULL;
 
-	if (inode->i_blkbits == PAGE_CACHE_SHIFT) {
+	if (inode->i_blkbits == PAGE_SHIFT) {
 		lock_page(obh->b_page);
 		/*
 		 * We cannot call radix_tree_preload for the kernels older
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index 919fd5bb14a8..3a3821b00486 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -919,8 +919,6 @@ static void nilfs_btree_split(struct nilfs_bmap *btree,
 			      int level, __u64 *keyp, __u64 *ptrp)
 {
 	struct nilfs_btree_node *node, *right;
-	__u64 newkey;
-	__u64 newptr;
 	int nchildren, n, move, ncblk;
 
 	node = nilfs_btree_get_nonroot_node(path, level);
@@ -942,9 +940,6 @@ static void nilfs_btree_split(struct nilfs_bmap *btree,
 	if (!buffer_dirty(path[level].bp_sib_bh))
 		mark_buffer_dirty(path[level].bp_sib_bh);
 
-	newkey = nilfs_btree_node_get_key(right, 0);
-	newptr = path[level].bp_newreq.bpr_ptr;
-
 	if (move) {
 		path[level].bp_index -= nilfs_btree_node_get_nchildren(node);
 		nilfs_btree_node_insert(right, path[level].bp_index,
@@ -1856,7 +1851,7 @@ int nilfs_btree_convert_and_insert(struct nilfs_bmap *btree,
 				   __u64 key, __u64 ptr,
 				   const __u64 *keys, const __u64 *ptrs, int n)
 {
-	struct buffer_head *bh;
+	struct buffer_head *bh = NULL;
 	union nilfs_bmap_ptr_req dreq, nreq, *di, *ni;
 	struct nilfs_bmap_stats stats;
 	int ret;
diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c
index 0d5fada91191..7dc23f100e57 100644
--- a/fs/nilfs2/dat.c
+++ b/fs/nilfs2/dat.c
@@ -155,7 +155,6 @@ void nilfs_dat_commit_start(struct inode *dat, struct nilfs_palloc_req *req,
 int nilfs_dat_prepare_end(struct inode *dat, struct nilfs_palloc_req *req)
 {
 	struct nilfs_dat_entry *entry;
-	__u64 start;
 	sector_t blocknr;
 	void *kaddr;
 	int ret;
@@ -169,7 +168,6 @@ int nilfs_dat_prepare_end(struct inode *dat, struct nilfs_palloc_req *req)
 	kaddr = kmap_atomic(req->pr_entry_bh->b_page);
 	entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr,
 					     req->pr_entry_bh, kaddr);
-	start = le64_to_cpu(entry->de_start);
 	blocknr = le64_to_cpu(entry->de_blocknr);
 	kunmap_atomic(kaddr);
 
diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c
index 6b8b92b19cec..e08f064e4bd7 100644
--- a/fs/nilfs2/dir.c
+++ b/fs/nilfs2/dir.c
@@ -58,7 +58,7 @@ static inline unsigned nilfs_chunk_size(struct inode *inode)
 static inline void nilfs_put_page(struct page *page)
 {
 	kunmap(page);
-	page_cache_release(page);
+	put_page(page);
 }
 
 /*
@@ -69,9 +69,9 @@ static unsigned nilfs_last_byte(struct inode *inode, unsigned long page_nr)
 {
 	unsigned last_byte = inode->i_size;
 
-	last_byte -= page_nr << PAGE_CACHE_SHIFT;
-	if (last_byte > PAGE_CACHE_SIZE)
-		last_byte = PAGE_CACHE_SIZE;
+	last_byte -= page_nr << PAGE_SHIFT;
+	if (last_byte > PAGE_SIZE)
+		last_byte = PAGE_SIZE;
 	return last_byte;
 }
 
@@ -109,12 +109,12 @@ static void nilfs_check_page(struct page *page)
 	unsigned chunk_size = nilfs_chunk_size(dir);
 	char *kaddr = page_address(page);
 	unsigned offs, rec_len;
-	unsigned limit = PAGE_CACHE_SIZE;
+	unsigned limit = PAGE_SIZE;
 	struct nilfs_dir_entry *p;
 	char *error;
 
-	if ((dir->i_size >> PAGE_CACHE_SHIFT) == page->index) {
-		limit = dir->i_size & ~PAGE_CACHE_MASK;
+	if ((dir->i_size >> PAGE_SHIFT) == page->index) {
+		limit = dir->i_size & ~PAGE_MASK;
 		if (limit & (chunk_size - 1))
 			goto Ebadsize;
 		if (!limit)
@@ -161,7 +161,7 @@ Espan:
 bad_entry:
 	nilfs_error(sb, "nilfs_check_page", "bad entry in directory #%lu: %s - "
 		    "offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
-		    dir->i_ino, error, (page->index<<PAGE_CACHE_SHIFT)+offs,
+		    dir->i_ino, error, (page->index<<PAGE_SHIFT)+offs,
 		    (unsigned long) le64_to_cpu(p->inode),
 		    rec_len, p->name_len);
 	goto fail;
@@ -170,7 +170,7 @@ Eend:
 	nilfs_error(sb, "nilfs_check_page",
 		    "entry in directory #%lu spans the page boundary"
 		    "offset=%lu, inode=%lu",
-		    dir->i_ino, (page->index<<PAGE_CACHE_SHIFT)+offs,
+		    dir->i_ino, (page->index<<PAGE_SHIFT)+offs,
 		    (unsigned long) le64_to_cpu(p->inode));
 fail:
 	SetPageChecked(page);
@@ -256,8 +256,8 @@ static int nilfs_readdir(struct file *file, struct dir_context *ctx)
 	loff_t pos = ctx->pos;
 	struct inode *inode = file_inode(file);
 	struct super_block *sb = inode->i_sb;
-	unsigned int offset = pos & ~PAGE_CACHE_MASK;
-	unsigned long n = pos >> PAGE_CACHE_SHIFT;
+	unsigned int offset = pos & ~PAGE_MASK;
+	unsigned long n = pos >> PAGE_SHIFT;
 	unsigned long npages = dir_pages(inode);
 /*	unsigned chunk_mask = ~(nilfs_chunk_size(inode)-1); */
 
@@ -272,7 +272,7 @@ static int nilfs_readdir(struct file *file, struct dir_context *ctx)
 		if (IS_ERR(page)) {
 			nilfs_error(sb, __func__, "bad page in #%lu",
 				    inode->i_ino);
-			ctx->pos += PAGE_CACHE_SIZE - offset;
+			ctx->pos += PAGE_SIZE - offset;
 			return -EIO;
 		}
 		kaddr = page_address(page);
@@ -361,7 +361,7 @@ nilfs_find_entry(struct inode *dir, const struct qstr *qstr,
 		if (++n >= npages)
 			n = 0;
 		/* next page is past the blocks we've got */
-		if (unlikely(n > (dir->i_blocks >> (PAGE_CACHE_SHIFT - 9)))) {
+		if (unlikely(n > (dir->i_blocks >> (PAGE_SHIFT - 9)))) {
 			nilfs_error(dir->i_sb, __func__,
 			       "dir %lu size %lld exceeds block count %llu",
 			       dir->i_ino, dir->i_size,
@@ -401,7 +401,7 @@ ino_t nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr)
 	if (de) {
 		res = le64_to_cpu(de->inode);
 		kunmap(page);
-		page_cache_release(page);
+		put_page(page);
 	}
 	return res;
 }
@@ -460,7 +460,7 @@ int nilfs_add_link(struct dentry *dentry, struct inode *inode)
 		kaddr = page_address(page);
 		dir_end = kaddr + nilfs_last_byte(dir, n);
 		de = (struct nilfs_dir_entry *)kaddr;
-		kaddr += PAGE_CACHE_SIZE - reclen;
+		kaddr += PAGE_SIZE - reclen;
 		while ((char *)de <= kaddr) {
 			if ((char *)de == dir_end) {
 				/* We hit i_size */
@@ -603,7 +603,7 @@ int nilfs_make_empty(struct inode *inode, struct inode *parent)
 	kunmap_atomic(kaddr);
 	nilfs_commit_chunk(page, mapping, 0, chunk_size);
 fail:
-	page_cache_release(page);
+	put_page(page);
 	return err;
 }
 
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index 54575e3cc1a2..088ba001c6ef 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -109,7 +109,7 @@ static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 		goto out;
 
 	file_update_time(vma->vm_file);
-	ret = __block_page_mkwrite(vma, vmf, nilfs_get_block);
+	ret = block_page_mkwrite(vma, vmf, nilfs_get_block);
 	if (ret) {
 		nilfs_transaction_abort(inode->i_sb);
 		goto out;
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index 748ca238915a..0224b7826ace 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -115,7 +115,7 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff,
 
  failed:
 	unlock_page(bh->b_page);
-	page_cache_release(bh->b_page);
+	put_page(bh->b_page);
 	return err;
 }
 
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 4a73d6dffabf..534631358b13 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -249,7 +249,7 @@ static int nilfs_set_page_dirty(struct page *page)
 		if (nr_dirty)
 			nilfs_set_file_dirty(inode, nr_dirty);
 	} else if (ret) {
-		unsigned nr_dirty = 1 << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+		unsigned nr_dirty = 1 << (PAGE_SHIFT - inode->i_blkbits);
 
 		nilfs_set_file_dirty(inode, nr_dirty);
 	}
@@ -291,7 +291,7 @@ static int nilfs_write_end(struct file *file, struct address_space *mapping,
 			   struct page *page, void *fsdata)
 {
 	struct inode *inode = mapping->host;
-	unsigned start = pos & (PAGE_CACHE_SIZE - 1);
+	unsigned start = pos & (PAGE_SIZE - 1);
 	unsigned nr_dirty;
 	int err;
 
@@ -356,7 +356,7 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
 		goto failed;
 
 	mapping_set_gfp_mask(inode->i_mapping,
-			     mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS);
+			   mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS));
 
 	root = NILFS_I(dir)->i_root;
 	ii = NILFS_I(inode);
@@ -510,6 +510,7 @@ static int __nilfs_read_inode(struct super_block *sb,
 		inode->i_mapping->a_ops = &nilfs_aops;
 	} else if (S_ISLNK(inode->i_mode)) {
 		inode->i_op = &nilfs_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &nilfs_aops;
 	} else {
 		inode->i_op = &nilfs_special_inode_operations;
@@ -522,7 +523,7 @@ static int __nilfs_read_inode(struct super_block *sb,
 	up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
 	nilfs_set_inode_flags(inode);
 	mapping_set_gfp_mask(inode->i_mapping,
-			     mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS);
+			   mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS));
 	return 0;
 
  failed_unmap:
@@ -1002,7 +1003,7 @@ int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	if (ret)
 		return ret;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	isize = i_size_read(inode);
 
@@ -1112,6 +1113,6 @@ int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	if (ret == 1)
 		ret = 0;
 
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return ret;
 }
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index aba43811d6ef..e8fe24882b5b 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -158,7 +158,7 @@ static int nilfs_ioctl_setflags(struct inode *inode, struct file *filp,
 
 	flags = nilfs_mask_flags(inode->i_mode, flags);
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	oldflags = NILFS_I(inode)->i_flags;
 
@@ -186,7 +186,7 @@ static int nilfs_ioctl_setflags(struct inode *inode, struct file *filp,
 	nilfs_mark_inode_dirty(inode);
 	ret = nilfs_transaction_commit(inode->i_sb);
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	mnt_drop_write_file(filp);
 	return ret;
 }
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index dee34d990281..f6982b9153d5 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -33,6 +33,7 @@
 #include "page.h"
 #include "mdt.h"
 
+#include <trace/events/nilfs2.h>
 
 #define NILFS_MDT_MAX_RA_BLOCKS		(16 - 1)
 
@@ -68,6 +69,9 @@ nilfs_mdt_insert_new_block(struct inode *inode, unsigned long block,
 	set_buffer_uptodate(bh);
 	mark_buffer_dirty(bh);
 	nilfs_mdt_mark_dirty(inode);
+
+	trace_nilfs2_mdt_insert_new_block(inode, inode->i_ino, block);
+
 	return 0;
 }
 
@@ -106,7 +110,7 @@ static int nilfs_mdt_create_block(struct inode *inode, unsigned long block,
 
  failed_bh:
 	unlock_page(bh->b_page);
-	page_cache_release(bh->b_page);
+	put_page(bh->b_page);
 	brelse(bh);
 
  failed_unlock:
@@ -158,13 +162,15 @@ nilfs_mdt_submit_block(struct inode *inode, unsigned long blkoff,
 	get_bh(bh);
 	submit_bh(mode, bh);
 	ret = 0;
+
+	trace_nilfs2_mdt_submit_block(inode, inode->i_ino, blkoff, mode);
  out:
 	get_bh(bh);
 	*out_bh = bh;
 
  failed_bh:
 	unlock_page(bh->b_page);
-	page_cache_release(bh->b_page);
+	put_page(bh->b_page);
 	brelse(bh);
  failed:
 	return ret;
@@ -357,7 +363,7 @@ int nilfs_mdt_delete_block(struct inode *inode, unsigned long block)
 int nilfs_mdt_forget_block(struct inode *inode, unsigned long block)
 {
 	pgoff_t index = (pgoff_t)block >>
-		(PAGE_CACHE_SHIFT - inode->i_blkbits);
+		(PAGE_SHIFT - inode->i_blkbits);
 	struct page *page;
 	unsigned long first_block;
 	int ret = 0;
@@ -370,7 +376,7 @@ int nilfs_mdt_forget_block(struct inode *inode, unsigned long block)
 	wait_on_page_writeback(page);
 
 	first_block = (unsigned long)index <<
-		(PAGE_CACHE_SHIFT - inode->i_blkbits);
+		(PAGE_SHIFT - inode->i_blkbits);
 	if (page_has_buffers(page)) {
 		struct buffer_head *bh;
 
@@ -379,7 +385,7 @@ int nilfs_mdt_forget_block(struct inode *inode, unsigned long block)
 	}
 	still_dirty = PageDirty(page);
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 
 	if (still_dirty ||
 	    invalidate_inode_pages2_range(inode->i_mapping, index, index) != 0)
@@ -572,7 +578,7 @@ int nilfs_mdt_freeze_buffer(struct inode *inode, struct buffer_head *bh)
 	}
 
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 	return 0;
 }
 
@@ -591,7 +597,7 @@ nilfs_mdt_get_frozen_buffer(struct inode *inode, struct buffer_head *bh)
 			bh_frozen = nilfs_page_get_nth_block(page, n);
 		}
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 	}
 	return bh_frozen;
 }
diff --git a/fs/nilfs2/mdt.h b/fs/nilfs2/mdt.h
index fe529a87a208..03246cac3338 100644
--- a/fs/nilfs2/mdt.h
+++ b/fs/nilfs2/mdt.h
@@ -72,7 +72,7 @@ static inline struct nilfs_mdt_info *NILFS_MDT(const struct inode *inode)
 }
 
 /* Default GFP flags using highmem */
-#define NILFS_MDT_GFP      (__GFP_WAIT | __GFP_IO | __GFP_HIGHMEM)
+#define NILFS_MDT_GFP      (__GFP_RECLAIM | __GFP_IO | __GFP_HIGHMEM)
 
 int nilfs_mdt_get_block(struct inode *, unsigned long, int,
 			void (*init_block)(struct inode *,
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 37dd6b05b1b5..151bc19d47c0 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -120,9 +120,6 @@ nilfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev)
 	struct nilfs_transaction_info ti;
 	int err;
 
-	if (!new_valid_dev(rdev))
-		return -EINVAL;
-
 	err = nilfs_transaction_begin(dir->i_sb, &ti, 1);
 	if (err)
 		return err;
@@ -164,6 +161,7 @@ static int nilfs_symlink(struct inode *dir, struct dentry *dentry,
 
 	/* slow symlink */
 	inode->i_op = &nilfs_symlink_inode_operations;
+	inode_nohighmem(inode);
 	inode->i_mapping->a_ops = &nilfs_aops;
 	err = page_symlink(inode, symname, l);
 	if (err)
@@ -433,11 +431,11 @@ static int nilfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 out_dir:
 	if (dir_de) {
 		kunmap(dir_page);
-		page_cache_release(dir_page);
+		put_page(dir_page);
 	}
 out_old:
 	kunmap(old_page);
-	page_cache_release(old_page);
+	put_page(old_page);
 out:
 	nilfs_transaction_abort(old_dir->i_sb);
 	return err;
@@ -571,8 +569,7 @@ const struct inode_operations nilfs_special_inode_operations = {
 
 const struct inode_operations nilfs_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 	.permission     = nilfs_permission,
 };
 
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index 45d650addd56..489391561cda 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -50,7 +50,7 @@ __nilfs_get_page_block(struct page *page, unsigned long block, pgoff_t index,
 	if (!page_has_buffers(page))
 		create_empty_buffers(page, 1 << blkbits, b_state);
 
-	first_block = (unsigned long)index << (PAGE_CACHE_SHIFT - blkbits);
+	first_block = (unsigned long)index << (PAGE_SHIFT - blkbits);
 	bh = nilfs_page_get_nth_block(page, block - first_block);
 
 	touch_buffer(bh);
@@ -64,7 +64,7 @@ struct buffer_head *nilfs_grab_buffer(struct inode *inode,
 				      unsigned long b_state)
 {
 	int blkbits = inode->i_blkbits;
-	pgoff_t index = blkoff >> (PAGE_CACHE_SHIFT - blkbits);
+	pgoff_t index = blkoff >> (PAGE_SHIFT - blkbits);
 	struct page *page;
 	struct buffer_head *bh;
 
@@ -75,7 +75,7 @@ struct buffer_head *nilfs_grab_buffer(struct inode *inode,
 	bh = __nilfs_get_page_block(page, blkoff, index, blkbits, b_state);
 	if (unlikely(!bh)) {
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 		return NULL;
 	}
 	return bh;
@@ -180,7 +180,7 @@ void nilfs_page_bug(struct page *page)
 
 	printk(KERN_CRIT "NILFS_PAGE_BUG(%p): cnt=%d index#=%llu flags=0x%lx "
 	       "mapping=%p ino=%lu\n",
-	       page, atomic_read(&page->_count),
+	       page, page_ref_count(page),
 	       (unsigned long long)page->index, page->flags, m, ino);
 
 	if (page_has_buffers(page)) {
@@ -288,7 +288,7 @@ repeat:
 		__set_page_dirty_nobuffers(dpage);
 
 		unlock_page(dpage);
-		page_cache_release(dpage);
+		put_page(dpage);
 		unlock_page(page);
 	}
 	pagevec_release(&pvec);
@@ -333,7 +333,7 @@ repeat:
 			WARN_ON(PageDirty(dpage));
 			nilfs_copy_page(dpage, page, 0);
 			unlock_page(dpage);
-			page_cache_release(dpage);
+			put_page(dpage);
 		} else {
 			struct page *page2;
 
@@ -350,7 +350,7 @@ repeat:
 			if (unlikely(err < 0)) {
 				WARN_ON(err == -EEXIST);
 				page->mapping = NULL;
-				page_cache_release(page); /* for cache */
+				put_page(page); /* for cache */
 			} else {
 				page->mapping = dmap;
 				dmap->nrpages++;
@@ -523,8 +523,8 @@ unsigned long nilfs_find_uncommitted_extent(struct inode *inode,
 	if (inode->i_mapping->nrpages == 0)
 		return 0;
 
-	index = start_blk >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
-	nblocks_in_page = 1U << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+	index = start_blk >> (PAGE_SHIFT - inode->i_blkbits);
+	nblocks_in_page = 1U << (PAGE_SHIFT - inode->i_blkbits);
 
 	pagevec_init(&pvec, 0);
 
@@ -537,7 +537,7 @@ repeat:
 	if (length > 0 && pvec.pages[0]->index > index)
 		goto out;
 
-	b = pvec.pages[0]->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+	b = pvec.pages[0]->index << (PAGE_SHIFT - inode->i_blkbits);
 	i = 0;
 	do {
 		page = pvec.pages[i];
diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
index ff00a0b7acb9..5afa77fadc11 100644
--- a/fs/nilfs2/recovery.c
+++ b/fs/nilfs2/recovery.c
@@ -544,14 +544,14 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
 				blocksize, page, NULL);
 
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 
 		(*nr_salvaged_blocks)++;
 		goto next;
 
  failed_page:
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 
  failed_inode:
 		printk(KERN_WARNING
@@ -582,7 +582,7 @@ static int nilfs_do_roll_forward(struct the_nilfs *nilfs,
 				 struct nilfs_recovery_info *ri)
 {
 	struct buffer_head *bh_sum = NULL;
-	struct nilfs_segment_summary *sum;
+	struct nilfs_segment_summary *sum = NULL;
 	sector_t pseg_start;
 	sector_t seg_start, seg_end;  /* Starting/ending DBN of full segment */
 	unsigned long nsalvaged_blocks = 0;
@@ -814,7 +814,7 @@ int nilfs_search_super_root(struct the_nilfs *nilfs,
 			    struct nilfs_recovery_info *ri)
 {
 	struct buffer_head *bh_sum = NULL;
-	struct nilfs_segment_summary *sum;
+	struct nilfs_segment_summary *sum = NULL;
 	sector_t pseg_start, pseg_end, sr_pseg_start = 0;
 	sector_t seg_start, seg_end; /* range of full segment (block number) */
 	sector_t b, end;
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index c6abbad9b8e3..4317f72568e6 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -77,6 +77,36 @@ enum {
 	NILFS_ST_DONE,
 };
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/nilfs2.h>
+
+/*
+ * nilfs_sc_cstage_inc(), nilfs_sc_cstage_set(), nilfs_sc_cstage_get() are
+ * wrapper functions of stage count (nilfs_sc_info->sc_stage.scnt). Users of
+ * the variable must use them because transition of stage count must involve
+ * trace events (trace_nilfs2_collection_stage_transition).
+ *
+ * nilfs_sc_cstage_get() isn't required for the above purpose because it doesn't
+ * produce tracepoint events. It is provided just for making the intention
+ * clear.
+ */
+static inline void nilfs_sc_cstage_inc(struct nilfs_sc_info *sci)
+{
+	sci->sc_stage.scnt++;
+	trace_nilfs2_collection_stage_transition(sci);
+}
+
+static inline void nilfs_sc_cstage_set(struct nilfs_sc_info *sci, int next_scnt)
+{
+	sci->sc_stage.scnt = next_scnt;
+	trace_nilfs2_collection_stage_transition(sci);
+}
+
+static inline int nilfs_sc_cstage_get(struct nilfs_sc_info *sci)
+{
+	return sci->sc_stage.scnt;
+}
+
 /* State flags of collection */
 #define NILFS_CF_NODE		0x0001	/* Collecting node blocks */
 #define NILFS_CF_IFILE_STARTED	0x0002	/* IFILE stage has started */
@@ -184,11 +214,18 @@ int nilfs_transaction_begin(struct super_block *sb,
 {
 	struct the_nilfs *nilfs;
 	int ret = nilfs_prepare_segment_lock(ti);
+	struct nilfs_transaction_info *trace_ti;
 
 	if (unlikely(ret < 0))
 		return ret;
-	if (ret > 0)
+	if (ret > 0) {
+		trace_ti = current->journal_info;
+
+		trace_nilfs2_transaction_transition(sb, trace_ti,
+				    trace_ti->ti_count, trace_ti->ti_flags,
+				    TRACE_NILFS2_TRANSACTION_BEGIN);
 		return 0;
+	}
 
 	sb_start_intwrite(sb);
 
@@ -199,6 +236,11 @@ int nilfs_transaction_begin(struct super_block *sb,
 		ret = -ENOSPC;
 		goto failed;
 	}
+
+	trace_ti = current->journal_info;
+	trace_nilfs2_transaction_transition(sb, trace_ti, trace_ti->ti_count,
+					    trace_ti->ti_flags,
+					    TRACE_NILFS2_TRANSACTION_BEGIN);
 	return 0;
 
  failed:
@@ -231,6 +273,8 @@ int nilfs_transaction_commit(struct super_block *sb)
 	ti->ti_flags |= NILFS_TI_COMMIT;
 	if (ti->ti_count > 0) {
 		ti->ti_count--;
+		trace_nilfs2_transaction_transition(sb, ti, ti->ti_count,
+			    ti->ti_flags, TRACE_NILFS2_TRANSACTION_COMMIT);
 		return 0;
 	}
 	if (nilfs->ns_writer) {
@@ -242,6 +286,9 @@ int nilfs_transaction_commit(struct super_block *sb)
 			nilfs_segctor_do_flush(sci, 0);
 	}
 	up_read(&nilfs->ns_segctor_sem);
+	trace_nilfs2_transaction_transition(sb, ti, ti->ti_count,
+			    ti->ti_flags, TRACE_NILFS2_TRANSACTION_COMMIT);
+
 	current->journal_info = ti->ti_save;
 
 	if (ti->ti_flags & NILFS_TI_SYNC)
@@ -260,10 +307,15 @@ void nilfs_transaction_abort(struct super_block *sb)
 	BUG_ON(ti == NULL || ti->ti_magic != NILFS_TI_MAGIC);
 	if (ti->ti_count > 0) {
 		ti->ti_count--;
+		trace_nilfs2_transaction_transition(sb, ti, ti->ti_count,
+			    ti->ti_flags, TRACE_NILFS2_TRANSACTION_ABORT);
 		return;
 	}
 	up_read(&nilfs->ns_segctor_sem);
 
+	trace_nilfs2_transaction_transition(sb, ti, ti->ti_count,
+		    ti->ti_flags, TRACE_NILFS2_TRANSACTION_ABORT);
+
 	current->journal_info = ti->ti_save;
 	if (ti->ti_flags & NILFS_TI_DYNAMIC_ALLOC)
 		kmem_cache_free(nilfs_transaction_cachep, ti);
@@ -309,6 +361,9 @@ static void nilfs_transaction_lock(struct super_block *sb,
 	current->journal_info = ti;
 
 	for (;;) {
+		trace_nilfs2_transaction_transition(sb, ti, ti->ti_count,
+			    ti->ti_flags, TRACE_NILFS2_TRANSACTION_TRYLOCK);
+
 		down_write(&nilfs->ns_segctor_sem);
 		if (!test_bit(NILFS_SC_PRIOR_FLUSH, &sci->sc_flags))
 			break;
@@ -320,6 +375,9 @@ static void nilfs_transaction_lock(struct super_block *sb,
 	}
 	if (gcflag)
 		ti->ti_flags |= NILFS_TI_GC;
+
+	trace_nilfs2_transaction_transition(sb, ti, ti->ti_count,
+			    ti->ti_flags, TRACE_NILFS2_TRANSACTION_LOCK);
 }
 
 static void nilfs_transaction_unlock(struct super_block *sb)
@@ -332,6 +390,9 @@ static void nilfs_transaction_unlock(struct super_block *sb)
 
 	up_write(&nilfs->ns_segctor_sem);
 	current->journal_info = ti->ti_save;
+
+	trace_nilfs2_transaction_transition(sb, ti, ti->ti_count,
+			    ti->ti_flags, TRACE_NILFS2_TRANSACTION_UNLOCK);
 }
 
 static void *nilfs_segctor_map_segsum_entry(struct nilfs_sc_info *sci,
@@ -1062,7 +1123,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 	size_t ndone;
 	int err = 0;
 
-	switch (sci->sc_stage.scnt) {
+	switch (nilfs_sc_cstage_get(sci)) {
 	case NILFS_ST_INIT:
 		/* Pre-processes */
 		sci->sc_stage.flags = 0;
@@ -1071,7 +1132,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 			sci->sc_nblk_inc = 0;
 			sci->sc_curseg->sb_sum.flags = NILFS_SS_LOGBGN;
 			if (mode == SC_LSEG_DSYNC) {
-				sci->sc_stage.scnt = NILFS_ST_DSYNC;
+				nilfs_sc_cstage_set(sci, NILFS_ST_DSYNC);
 				goto dsync_mode;
 			}
 		}
@@ -1079,10 +1140,10 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 		sci->sc_stage.dirty_file_ptr = NULL;
 		sci->sc_stage.gc_inode_ptr = NULL;
 		if (mode == SC_FLUSH_DAT) {
-			sci->sc_stage.scnt = NILFS_ST_DAT;
+			nilfs_sc_cstage_set(sci, NILFS_ST_DAT);
 			goto dat_stage;
 		}
-		sci->sc_stage.scnt++;  /* Fall through */
+		nilfs_sc_cstage_inc(sci);  /* Fall through */
 	case NILFS_ST_GC:
 		if (nilfs_doing_gc()) {
 			head = &sci->sc_gc_inodes;
@@ -1103,7 +1164,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 			}
 			sci->sc_stage.gc_inode_ptr = NULL;
 		}
-		sci->sc_stage.scnt++;  /* Fall through */
+		nilfs_sc_cstage_inc(sci);  /* Fall through */
 	case NILFS_ST_FILE:
 		head = &sci->sc_dirty_files;
 		ii = list_prepare_entry(sci->sc_stage.dirty_file_ptr, head,
@@ -1125,10 +1186,10 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 		}
 		sci->sc_stage.dirty_file_ptr = NULL;
 		if (mode == SC_FLUSH_FILE) {
-			sci->sc_stage.scnt = NILFS_ST_DONE;
+			nilfs_sc_cstage_set(sci, NILFS_ST_DONE);
 			return 0;
 		}
-		sci->sc_stage.scnt++;
+		nilfs_sc_cstage_inc(sci);
 		sci->sc_stage.flags |= NILFS_CF_IFILE_STARTED;
 		/* Fall through */
 	case NILFS_ST_IFILE:
@@ -1136,7 +1197,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 					      &nilfs_sc_file_ops);
 		if (unlikely(err))
 			break;
-		sci->sc_stage.scnt++;
+		nilfs_sc_cstage_inc(sci);
 		/* Creating a checkpoint */
 		err = nilfs_segctor_create_checkpoint(sci);
 		if (unlikely(err))
@@ -1147,7 +1208,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 					      &nilfs_sc_file_ops);
 		if (unlikely(err))
 			break;
-		sci->sc_stage.scnt++;  /* Fall through */
+		nilfs_sc_cstage_inc(sci);  /* Fall through */
 	case NILFS_ST_SUFILE:
 		err = nilfs_sufile_freev(nilfs->ns_sufile, sci->sc_freesegs,
 					 sci->sc_nfreesegs, &ndone);
@@ -1163,7 +1224,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 					      &nilfs_sc_file_ops);
 		if (unlikely(err))
 			break;
-		sci->sc_stage.scnt++;  /* Fall through */
+		nilfs_sc_cstage_inc(sci);  /* Fall through */
 	case NILFS_ST_DAT:
  dat_stage:
 		err = nilfs_segctor_scan_file(sci, nilfs->ns_dat,
@@ -1171,10 +1232,10 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 		if (unlikely(err))
 			break;
 		if (mode == SC_FLUSH_DAT) {
-			sci->sc_stage.scnt = NILFS_ST_DONE;
+			nilfs_sc_cstage_set(sci, NILFS_ST_DONE);
 			return 0;
 		}
-		sci->sc_stage.scnt++;  /* Fall through */
+		nilfs_sc_cstage_inc(sci);  /* Fall through */
 	case NILFS_ST_SR:
 		if (mode == SC_LSEG_SR) {
 			/* Appending a super root */
@@ -1184,7 +1245,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 		}
 		/* End of a logical segment */
 		sci->sc_curseg->sb_sum.flags |= NILFS_SS_LOGEND;
-		sci->sc_stage.scnt = NILFS_ST_DONE;
+		nilfs_sc_cstage_set(sci, NILFS_ST_DONE);
 		return 0;
 	case NILFS_ST_DSYNC:
  dsync_mode:
@@ -1197,7 +1258,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 		if (unlikely(err))
 			break;
 		sci->sc_curseg->sb_sum.flags |= NILFS_SS_LOGEND;
-		sci->sc_stage.scnt = NILFS_ST_DONE;
+		nilfs_sc_cstage_set(sci, NILFS_ST_DONE);
 		return 0;
 	case NILFS_ST_DONE:
 		return 0;
@@ -1442,7 +1503,8 @@ static int nilfs_segctor_collect(struct nilfs_sc_info *sci,
 			goto failed;
 
 		/* The current segment is filled up */
-		if (mode != SC_LSEG_SR || sci->sc_stage.scnt < NILFS_ST_CPFILE)
+		if (mode != SC_LSEG_SR ||
+		    nilfs_sc_cstage_get(sci) < NILFS_ST_CPFILE)
 			break;
 
 		nilfs_clear_logs(&sci->sc_segbufs);
@@ -1946,7 +2008,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode)
 	struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
 	int err;
 
-	sci->sc_stage.scnt = NILFS_ST_INIT;
+	nilfs_sc_cstage_set(sci, NILFS_ST_INIT);
 	sci->sc_cno = nilfs->ns_cno;
 
 	err = nilfs_segctor_collect_dirty_files(sci, nilfs);
@@ -1974,7 +2036,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode)
 			goto failed;
 
 		/* Avoid empty segment */
-		if (sci->sc_stage.scnt == NILFS_ST_DONE &&
+		if (nilfs_sc_cstage_get(sci) == NILFS_ST_DONE &&
 		    nilfs_segbuf_empty(sci->sc_curseg)) {
 			nilfs_segctor_abort_construction(sci, nilfs, 1);
 			goto out;
@@ -1988,7 +2050,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode)
 			nilfs_segctor_fill_in_file_bmap(sci);
 
 		if (mode == SC_LSEG_SR &&
-		    sci->sc_stage.scnt >= NILFS_ST_CPFILE) {
+		    nilfs_sc_cstage_get(sci) >= NILFS_ST_CPFILE) {
 			err = nilfs_segctor_fill_in_checkpoint(sci);
 			if (unlikely(err))
 				goto failed_to_write;
@@ -2007,8 +2069,8 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode)
 		if (unlikely(err))
 			goto failed_to_write;
 
-		if (sci->sc_stage.scnt == NILFS_ST_DONE ||
-		    nilfs->ns_blocksize_bits != PAGE_CACHE_SHIFT) {
+		if (nilfs_sc_cstage_get(sci) == NILFS_ST_DONE ||
+		    nilfs->ns_blocksize_bits != PAGE_SHIFT) {
 			/*
 			 * At this point, we avoid double buffering
 			 * for blocksize < pagesize because page dirty
@@ -2020,7 +2082,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode)
 			if (err)
 				goto failed_to_write;
 		}
-	} while (sci->sc_stage.scnt != NILFS_ST_DONE);
+	} while (nilfs_sc_cstage_get(sci) != NILFS_ST_DONE);
 
  out:
 	nilfs_segctor_drop_written_files(sci, nilfs);
@@ -2430,7 +2492,6 @@ static void nilfs_segctor_thread_construct(struct nilfs_sc_info *sci, int mode)
 static void nilfs_segctor_do_immediate_flush(struct nilfs_sc_info *sci)
 {
 	int mode = 0;
-	int err;
 
 	spin_lock(&sci->sc_state_lock);
 	mode = (sci->sc_flush_request & FLUSH_DAT_BIT) ?
@@ -2438,7 +2499,7 @@ static void nilfs_segctor_do_immediate_flush(struct nilfs_sc_info *sci)
 	spin_unlock(&sci->sc_state_lock);
 
 	if (mode) {
-		err = nilfs_segctor_do_construct(sci, mode);
+		nilfs_segctor_do_construct(sci, mode);
 
 		spin_lock(&sci->sc_state_lock);
 		sci->sc_flush_request &= (mode == SC_FLUSH_FILE) ?
diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h
index a48d6de1e02c..0408b9b2814b 100644
--- a/fs/nilfs2/segment.h
+++ b/fs/nilfs2/segment.h
@@ -67,7 +67,8 @@ struct nilfs_recovery_info {
 
 /**
  * struct nilfs_cstage - Context of collection stage
- * @scnt: Stage count
+ * @scnt: Stage count, must be accessed via wrappers:
+ *        nilfs_sc_cstage_inc(), nilfs_sc_cstage_set(), nilfs_sc_cstage_get()
  * @flags: State flags
  * @dirty_file_ptr: Pointer on dirty_files list, or inode of a target file
  * @gc_inode_ptr: Pointer on the list of gc-inodes
diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c
index 2a869c35c362..52821ffc11f4 100644
--- a/fs/nilfs2/sufile.c
+++ b/fs/nilfs2/sufile.c
@@ -30,6 +30,8 @@
 #include "mdt.h"
 #include "sufile.h"
 
+#include <trace/events/nilfs2.h>
+
 /**
  * struct nilfs_sufile_info - on-memory private data of sufile
  * @mi: on-memory private data of metadata file
@@ -317,7 +319,7 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump)
 	size_t susz = NILFS_MDT(sufile)->mi_entry_size;
 	__u64 segnum, maxsegnum, last_alloc;
 	void *kaddr;
-	unsigned long nsegments, ncleansegs, nsus, cnt;
+	unsigned long nsegments, nsus, cnt;
 	int ret, j;
 
 	down_write(&NILFS_MDT(sufile)->mi_sem);
@@ -327,7 +329,6 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump)
 		goto out_sem;
 	kaddr = kmap_atomic(header_bh->b_page);
 	header = kaddr + bh_offset(header_bh);
-	ncleansegs = le64_to_cpu(header->sh_ncleansegs);
 	last_alloc = le64_to_cpu(header->sh_last_alloc);
 	kunmap_atomic(kaddr);
 
@@ -358,6 +359,7 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump)
 				break; /* never happens */
 			}
 		}
+		trace_nilfs2_segment_usage_check(sufile, segnum, cnt);
 		ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 1,
 							   &su_bh);
 		if (ret < 0)
@@ -388,6 +390,9 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump)
 			nilfs_mdt_mark_dirty(sufile);
 			brelse(su_bh);
 			*segnump = segnum;
+
+			trace_nilfs2_segment_usage_allocated(sufile, segnum);
+
 			goto out_header;
 		}
 
@@ -490,6 +495,8 @@ void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum,
 	NILFS_SUI(sufile)->ncleansegs++;
 
 	nilfs_mdt_mark_dirty(sufile);
+
+	trace_nilfs2_segment_usage_freed(sufile, segnum);
 }
 
 /**
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index f47585bfeb01..7f5d3d9f1c37 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -361,7 +361,7 @@ static int nilfs_move_2nd_super(struct super_block *sb, loff_t sb2off)
 	struct nilfs_super_block *nsbp;
 	sector_t blocknr, newblocknr;
 	unsigned long offset;
-	int sb2i = -1;  /* array index of the secondary superblock */
+	int sb2i;  /* array index of the secondary superblock */
 	int ret = 0;
 
 	/* nilfs->ns_sem must be locked by the caller. */
@@ -372,6 +372,9 @@ static int nilfs_move_2nd_super(struct super_block *sb, loff_t sb2off)
 	} else if (nilfs->ns_sbh[0]->b_blocknr > nilfs->ns_first_data_block) {
 		sb2i = 0;
 		blocknr = nilfs->ns_sbh[0]->b_blocknr;
+	} else {
+		sb2i = -1;
+		blocknr = 0;
 	}
 	if (sb2i >= 0 && (u64)blocknr << nilfs->ns_blocksize_bits == sb2off)
 		goto out;  /* super block location is unchanged */
@@ -1313,13 +1316,11 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
 	}
 
 	if (!s->s_root) {
-		char b[BDEVNAME_SIZE];
-
-		s_new = true;
+ 		s_new = true;
 
 		/* New superblock instance created */
 		s->s_mode = mode;
-		strlcpy(s->s_id, bdevname(sd.bdev, b), sizeof(s->s_id));
+		snprintf(s->s_id, sizeof(s->s_id), "%pg", sd.bdev);
 		sb_set_blocksize(s, block_size(sd.bdev));
 
 		err = nilfs_fill_super(s, data, flags & MS_SILENT ? 1 : 0);
@@ -1405,21 +1406,18 @@ static void nilfs_destroy_cachep(void)
 	 */
 	rcu_barrier();
 
-	if (nilfs_inode_cachep)
-		kmem_cache_destroy(nilfs_inode_cachep);
-	if (nilfs_transaction_cachep)
-		kmem_cache_destroy(nilfs_transaction_cachep);
-	if (nilfs_segbuf_cachep)
-		kmem_cache_destroy(nilfs_segbuf_cachep);
-	if (nilfs_btree_path_cache)
-		kmem_cache_destroy(nilfs_btree_path_cache);
+	kmem_cache_destroy(nilfs_inode_cachep);
+	kmem_cache_destroy(nilfs_transaction_cachep);
+	kmem_cache_destroy(nilfs_segbuf_cachep);
+	kmem_cache_destroy(nilfs_btree_path_cache);
 }
 
 static int __init nilfs_init_cachep(void)
 {
 	nilfs_inode_cachep = kmem_cache_create("nilfs2_inode_cache",
 			sizeof(struct nilfs_inode_info), 0,
-			SLAB_RECLAIM_ACCOUNT, nilfs_inode_init_once);
+			SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT,
+			nilfs_inode_init_once);
 	if (!nilfs_inode_cachep)
 		goto fail;
 
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
index e785fd954c30..741077deef3b 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -199,8 +199,7 @@ void fsnotify_unmount_inodes(struct super_block *sb)
 				break;
 			}
 			spin_unlock(&next_i->i_lock);
-			next_i = list_entry(next_i->i_sb_list.next,
-						struct inode, i_sb_list);
+			next_i = list_next_entry(next_i, i_sb_list);
 		}
 
 		/*
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index fc0df4442f7b..7115c5d7d373 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -91,10 +91,14 @@
 #include <linux/fsnotify_backend.h>
 #include "fsnotify.h"
 
+#define FSNOTIFY_REAPER_DELAY	(1)	/* 1 jiffy */
+
 struct srcu_struct fsnotify_mark_srcu;
 static DEFINE_SPINLOCK(destroy_lock);
 static LIST_HEAD(destroy_list);
-static DECLARE_WAIT_QUEUE_HEAD(destroy_waitq);
+
+static void fsnotify_mark_destroy(struct work_struct *work);
+static DECLARE_DELAYED_WORK(reaper_work, fsnotify_mark_destroy);
 
 void fsnotify_get_mark(struct fsnotify_mark *mark)
 {
@@ -189,7 +193,8 @@ void fsnotify_free_mark(struct fsnotify_mark *mark)
 	spin_lock(&destroy_lock);
 	list_add(&mark->g_list, &destroy_list);
 	spin_unlock(&destroy_lock);
-	wake_up(&destroy_waitq);
+	queue_delayed_work(system_unbound_wq, &reaper_work,
+				FSNOTIFY_REAPER_DELAY);
 
 	/*
 	 * Some groups like to know that marks are being freed.  This is a
@@ -388,7 +393,8 @@ err:
 	spin_lock(&destroy_lock);
 	list_add(&mark->g_list, &destroy_list);
 	spin_unlock(&destroy_lock);
-	wake_up(&destroy_waitq);
+	queue_delayed_work(system_unbound_wq, &reaper_work,
+				FSNOTIFY_REAPER_DELAY);
 
 	return ret;
 }
@@ -493,39 +499,20 @@ void fsnotify_init_mark(struct fsnotify_mark *mark,
 	mark->free_mark = free_mark;
 }
 
-static int fsnotify_mark_destroy(void *ignored)
+static void fsnotify_mark_destroy(struct work_struct *work)
 {
 	struct fsnotify_mark *mark, *next;
 	struct list_head private_destroy_list;
 
-	for (;;) {
-		spin_lock(&destroy_lock);
-		/* exchange the list head */
-		list_replace_init(&destroy_list, &private_destroy_list);
-		spin_unlock(&destroy_lock);
-
-		synchronize_srcu(&fsnotify_mark_srcu);
+	spin_lock(&destroy_lock);
+	/* exchange the list head */
+	list_replace_init(&destroy_list, &private_destroy_list);
+	spin_unlock(&destroy_lock);
 
-		list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) {
-			list_del_init(&mark->g_list);
-			fsnotify_put_mark(mark);
-		}
+	synchronize_srcu(&fsnotify_mark_srcu);
 
-		wait_event_interruptible(destroy_waitq, !list_empty(&destroy_list));
+	list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) {
+		list_del_init(&mark->g_list);
+		fsnotify_put_mark(mark);
 	}
-
-	return 0;
-}
-
-static int __init fsnotify_mark_init(void)
-{
-	struct task_struct *thread;
-
-	thread = kthread_run(fsnotify_mark_destroy, NULL,
-			     "fsnotify_mark");
-	if (IS_ERR(thread))
-		panic("unable to start fsnotify mark destruction thread.");
-
-	return 0;
 }
-device_initcall(fsnotify_mark_init);
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index 7521e11db728..97768a1379f2 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -74,7 +74,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
 
 		set_buffer_uptodate(bh);
 
-		file_ofs = ((s64)page->index << PAGE_CACHE_SHIFT) +
+		file_ofs = ((s64)page->index << PAGE_SHIFT) +
 				bh_offset(bh);
 		read_lock_irqsave(&ni->size_lock, flags);
 		init_size = ni->initialized_size;
@@ -142,7 +142,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
 		u32 rec_size;
 
 		rec_size = ni->itype.index.block_size;
-		recs = PAGE_CACHE_SIZE / rec_size;
+		recs = PAGE_SIZE / rec_size;
 		/* Should have been verified before we got here... */
 		BUG_ON(!recs);
 		local_irq_save(flags);
@@ -229,7 +229,7 @@ static int ntfs_read_block(struct page *page)
 	 * fully truncated, truncate will throw it away as soon as we unlock
 	 * it so no need to worry what we do with it.
 	 */
-	iblock = (s64)page->index << (PAGE_CACHE_SHIFT - blocksize_bits);
+	iblock = (s64)page->index << (PAGE_SHIFT - blocksize_bits);
 	read_lock_irqsave(&ni->size_lock, flags);
 	lblock = (ni->allocated_size + blocksize - 1) >> blocksize_bits;
 	init_size = ni->initialized_size;
@@ -412,9 +412,9 @@ retry_readpage:
 	vi = page->mapping->host;
 	i_size = i_size_read(vi);
 	/* Is the page fully outside i_size? (truncate in progress) */
-	if (unlikely(page->index >= (i_size + PAGE_CACHE_SIZE - 1) >>
-			PAGE_CACHE_SHIFT)) {
-		zero_user(page, 0, PAGE_CACHE_SIZE);
+	if (unlikely(page->index >= (i_size + PAGE_SIZE - 1) >>
+			PAGE_SHIFT)) {
+		zero_user(page, 0, PAGE_SIZE);
 		ntfs_debug("Read outside i_size - truncated?");
 		goto done;
 	}
@@ -463,7 +463,7 @@ retry_readpage:
 	 * ok to ignore the compressed flag here.
 	 */
 	if (unlikely(page->index > 0)) {
-		zero_user(page, 0, PAGE_CACHE_SIZE);
+		zero_user(page, 0, PAGE_SIZE);
 		goto done;
 	}
 	if (!NInoAttr(ni))
@@ -509,7 +509,7 @@ retry_readpage:
 			le16_to_cpu(ctx->attr->data.resident.value_offset),
 			attr_len);
 	/* Zero the remainder of the page. */
-	memset(addr + attr_len, 0, PAGE_CACHE_SIZE - attr_len);
+	memset(addr + attr_len, 0, PAGE_SIZE - attr_len);
 	flush_dcache_page(page);
 	kunmap_atomic(addr);
 put_unm_err_out:
@@ -599,7 +599,7 @@ static int ntfs_write_block(struct page *page, struct writeback_control *wbc)
 	/* NOTE: Different naming scheme to ntfs_read_block()! */
 
 	/* The first block in the page. */
-	block = (s64)page->index << (PAGE_CACHE_SHIFT - blocksize_bits);
+	block = (s64)page->index << (PAGE_SHIFT - blocksize_bits);
 
 	read_lock_irqsave(&ni->size_lock, flags);
 	i_size = i_size_read(vi);
@@ -674,7 +674,7 @@ static int ntfs_write_block(struct page *page, struct writeback_control *wbc)
 				// in the inode.
 				// Again, for each page do:
 				//	__set_page_dirty_buffers();
-				// page_cache_release()
+				// put_page()
 				// We don't need to wait on the writes.
 				// Update iblock.
 			}
@@ -925,7 +925,7 @@ static int ntfs_write_mst_block(struct page *page,
 	ntfs_volume *vol = ni->vol;
 	u8 *kaddr;
 	unsigned int rec_size = ni->itype.index.block_size;
-	ntfs_inode *locked_nis[PAGE_CACHE_SIZE / rec_size];
+	ntfs_inode *locked_nis[PAGE_SIZE / rec_size];
 	struct buffer_head *bh, *head, *tbh, *rec_start_bh;
 	struct buffer_head *bhs[MAX_BUF_PER_PAGE];
 	runlist_element *rl;
@@ -949,7 +949,7 @@ static int ntfs_write_mst_block(struct page *page,
 			(NInoAttr(ni) && ni->type == AT_INDEX_ALLOCATION)));
 	bh_size = vol->sb->s_blocksize;
 	bh_size_bits = vol->sb->s_blocksize_bits;
-	max_bhs = PAGE_CACHE_SIZE / bh_size;
+	max_bhs = PAGE_SIZE / bh_size;
 	BUG_ON(!max_bhs);
 	BUG_ON(max_bhs > MAX_BUF_PER_PAGE);
 
@@ -961,13 +961,13 @@ static int ntfs_write_mst_block(struct page *page,
 	BUG_ON(!bh);
 
 	rec_size_bits = ni->itype.index.block_size_bits;
-	BUG_ON(!(PAGE_CACHE_SIZE >> rec_size_bits));
+	BUG_ON(!(PAGE_SIZE >> rec_size_bits));
 	bhs_per_rec = rec_size >> bh_size_bits;
 	BUG_ON(!bhs_per_rec);
 
 	/* The first block in the page. */
 	rec_block = block = (sector_t)page->index <<
-			(PAGE_CACHE_SHIFT - bh_size_bits);
+			(PAGE_SHIFT - bh_size_bits);
 
 	/* The first out of bounds block for the data size. */
 	dblock = (i_size_read(vi) + bh_size - 1) >> bh_size_bits;
@@ -1133,7 +1133,7 @@ lock_retry_remap:
 			unsigned long mft_no;
 
 			/* Get the mft record number. */
-			mft_no = (((s64)page->index << PAGE_CACHE_SHIFT) + ofs)
+			mft_no = (((s64)page->index << PAGE_SHIFT) + ofs)
 					>> rec_size_bits;
 			/* Check whether to write this mft record. */
 			tni = NULL;
@@ -1249,7 +1249,7 @@ do_mirror:
 				continue;
 			ofs = bh_offset(tbh);
 			/* Get the mft record number. */
-			mft_no = (((s64)page->index << PAGE_CACHE_SHIFT) + ofs)
+			mft_no = (((s64)page->index << PAGE_SHIFT) + ofs)
 					>> rec_size_bits;
 			if (mft_no < vol->mftmirr_size)
 				ntfs_sync_mft_mirror(vol, mft_no,
@@ -1300,7 +1300,7 @@ done:
 		 * Set page error if there is only one ntfs record in the page.
 		 * Otherwise we would loose per-record granularity.
 		 */
-		if (ni->itype.index.block_size == PAGE_CACHE_SIZE)
+		if (ni->itype.index.block_size == PAGE_SIZE)
 			SetPageError(page);
 		NVolSetErrors(vol);
 	}
@@ -1308,7 +1308,7 @@ done:
 		ntfs_debug("Page still contains one or more dirty ntfs "
 				"records.  Redirtying the page starting at "
 				"record 0x%lx.", page->index <<
-				(PAGE_CACHE_SHIFT - rec_size_bits));
+				(PAGE_SHIFT - rec_size_bits));
 		redirty_page_for_writepage(wbc, page);
 		unlock_page(page);
 	} else {
@@ -1365,13 +1365,13 @@ retry_writepage:
 	BUG_ON(!PageLocked(page));
 	i_size = i_size_read(vi);
 	/* Is the page fully outside i_size? (truncate in progress) */
-	if (unlikely(page->index >= (i_size + PAGE_CACHE_SIZE - 1) >>
-			PAGE_CACHE_SHIFT)) {
+	if (unlikely(page->index >= (i_size + PAGE_SIZE - 1) >>
+			PAGE_SHIFT)) {
 		/*
 		 * The page may have dirty, unmapped buffers.  Make them
 		 * freeable here, so the page does not leak.
 		 */
-		block_invalidatepage(page, 0, PAGE_CACHE_SIZE);
+		block_invalidatepage(page, 0, PAGE_SIZE);
 		unlock_page(page);
 		ntfs_debug("Write outside i_size - truncated?");
 		return 0;
@@ -1414,10 +1414,10 @@ retry_writepage:
 	/* NInoNonResident() == NInoIndexAllocPresent() */
 	if (NInoNonResident(ni)) {
 		/* We have to zero every time due to mmap-at-end-of-file. */
-		if (page->index >= (i_size >> PAGE_CACHE_SHIFT)) {
+		if (page->index >= (i_size >> PAGE_SHIFT)) {
 			/* The page straddles i_size. */
-			unsigned int ofs = i_size & ~PAGE_CACHE_MASK;
-			zero_user_segment(page, ofs, PAGE_CACHE_SIZE);
+			unsigned int ofs = i_size & ~PAGE_MASK;
+			zero_user_segment(page, ofs, PAGE_SIZE);
 		}
 		/* Handle mst protected attributes. */
 		if (NInoMstProtected(ni))
@@ -1500,7 +1500,7 @@ retry_writepage:
 			le16_to_cpu(ctx->attr->data.resident.value_offset),
 			addr, attr_len);
 	/* Zero out of bounds area in the page cache page. */
-	memset(addr + attr_len, 0, PAGE_CACHE_SIZE - attr_len);
+	memset(addr + attr_len, 0, PAGE_SIZE - attr_len);
 	kunmap_atomic(addr);
 	flush_dcache_page(page);
 	flush_dcache_mft_record_page(ctx->ntfs_ino);
diff --git a/fs/ntfs/aops.h b/fs/ntfs/aops.h
index caecc58f529c..820d6eabf60f 100644
--- a/fs/ntfs/aops.h
+++ b/fs/ntfs/aops.h
@@ -40,7 +40,7 @@
 static inline void ntfs_unmap_page(struct page *page)
 {
 	kunmap(page);
-	page_cache_release(page);
+	put_page(page);
 }
 
 /**
@@ -49,7 +49,7 @@ static inline void ntfs_unmap_page(struct page *page)
  * @index:	index into the page cache for @mapping of the page to map
  *
  * Read a page from the page cache of the address space @mapping at position
- * @index, where @index is in units of PAGE_CACHE_SIZE, and not in bytes.
+ * @index, where @index is in units of PAGE_SIZE, and not in bytes.
  *
  * If the page is not in memory it is loaded from disk first using the readpage
  * method defined in the address space operations of @mapping and the page is
diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c
index 250ed5b20c8f..44a39a099b54 100644
--- a/fs/ntfs/attrib.c
+++ b/fs/ntfs/attrib.c
@@ -152,7 +152,7 @@ int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn, ntfs_attr_search_ctx *ctx)
 			if (old_ctx.base_ntfs_ino && old_ctx.ntfs_ino !=
 					old_ctx.base_ntfs_ino) {
 				put_this_page = old_ctx.ntfs_ino->page;
-				page_cache_get(put_this_page);
+				get_page(put_this_page);
 			}
 			/*
 			 * Reinitialize the search context so we can lookup the
@@ -275,7 +275,7 @@ retry_map:
 		 * the pieces anyway.
 		 */
 		if (put_this_page)
-			page_cache_release(put_this_page);
+			put_page(put_this_page);
 	}
 	return err;
 }
@@ -1660,7 +1660,7 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size)
 		memcpy(kaddr, (u8*)a +
 				le16_to_cpu(a->data.resident.value_offset),
 				attr_size);
-		memset(kaddr + attr_size, 0, PAGE_CACHE_SIZE - attr_size);
+		memset(kaddr + attr_size, 0, PAGE_SIZE - attr_size);
 		kunmap_atomic(kaddr);
 		flush_dcache_page(page);
 		SetPageUptodate(page);
@@ -1748,7 +1748,7 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size)
 	if (page) {
 		set_page_dirty(page);
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 	}
 	ntfs_debug("Done.");
 	return 0;
@@ -1835,7 +1835,7 @@ rl_err_out:
 		ntfs_free(rl);
 page_err_out:
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 	}
 	if (err == -EINVAL)
 		err = -EIO;
@@ -2513,17 +2513,17 @@ int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val)
 	BUG_ON(NInoEncrypted(ni));
 	mapping = VFS_I(ni)->i_mapping;
 	/* Work out the starting index and page offset. */
-	idx = ofs >> PAGE_CACHE_SHIFT;
-	start_ofs = ofs & ~PAGE_CACHE_MASK;
+	idx = ofs >> PAGE_SHIFT;
+	start_ofs = ofs & ~PAGE_MASK;
 	/* Work out the ending index and page offset. */
 	end = ofs + cnt;
-	end_ofs = end & ~PAGE_CACHE_MASK;
+	end_ofs = end & ~PAGE_MASK;
 	/* If the end is outside the inode size return -ESPIPE. */
 	if (unlikely(end > i_size_read(VFS_I(ni)))) {
 		ntfs_error(vol->sb, "Request exceeds end of attribute.");
 		return -ESPIPE;
 	}
-	end >>= PAGE_CACHE_SHIFT;
+	end >>= PAGE_SHIFT;
 	/* If there is a first partial page, need to do it the slow way. */
 	if (start_ofs) {
 		page = read_mapping_page(mapping, idx, NULL);
@@ -2536,7 +2536,7 @@ int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val)
 		 * If the last page is the same as the first page, need to
 		 * limit the write to the end offset.
 		 */
-		size = PAGE_CACHE_SIZE;
+		size = PAGE_SIZE;
 		if (idx == end)
 			size = end_ofs;
 		kaddr = kmap_atomic(page);
@@ -2544,7 +2544,7 @@ int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val)
 		flush_dcache_page(page);
 		kunmap_atomic(kaddr);
 		set_page_dirty(page);
-		page_cache_release(page);
+		put_page(page);
 		balance_dirty_pages_ratelimited(mapping);
 		cond_resched();
 		if (idx == end)
@@ -2561,7 +2561,7 @@ int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val)
 			return -ENOMEM;
 		}
 		kaddr = kmap_atomic(page);
-		memset(kaddr, val, PAGE_CACHE_SIZE);
+		memset(kaddr, val, PAGE_SIZE);
 		flush_dcache_page(page);
 		kunmap_atomic(kaddr);
 		/*
@@ -2585,7 +2585,7 @@ int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val)
 		set_page_dirty(page);
 		/* Finally unlock and release the page. */
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 		balance_dirty_pages_ratelimited(mapping);
 		cond_resched();
 	}
@@ -2602,7 +2602,7 @@ int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val)
 		flush_dcache_page(page);
 		kunmap_atomic(kaddr);
 		set_page_dirty(page);
-		page_cache_release(page);
+		put_page(page);
 		balance_dirty_pages_ratelimited(mapping);
 		cond_resched();
 	}
diff --git a/fs/ntfs/bitmap.c b/fs/ntfs/bitmap.c
index 0809cf876098..ec130c588d2b 100644
--- a/fs/ntfs/bitmap.c
+++ b/fs/ntfs/bitmap.c
@@ -67,8 +67,8 @@ int __ntfs_bitmap_set_bits_in_run(struct inode *vi, const s64 start_bit,
 	 * Calculate the indices for the pages containing the first and last
 	 * bits, i.e. @start_bit and @start_bit + @cnt - 1, respectively.
 	 */
-	index = start_bit >> (3 + PAGE_CACHE_SHIFT);
-	end_index = (start_bit + cnt - 1) >> (3 + PAGE_CACHE_SHIFT);
+	index = start_bit >> (3 + PAGE_SHIFT);
+	end_index = (start_bit + cnt - 1) >> (3 + PAGE_SHIFT);
 
 	/* Get the page containing the first bit (@start_bit). */
 	mapping = vi->i_mapping;
@@ -82,7 +82,7 @@ int __ntfs_bitmap_set_bits_in_run(struct inode *vi, const s64 start_bit,
 	kaddr = page_address(page);
 
 	/* Set @pos to the position of the byte containing @start_bit. */
-	pos = (start_bit >> 3) & ~PAGE_CACHE_MASK;
+	pos = (start_bit >> 3) & ~PAGE_MASK;
 
 	/* Calculate the position of @start_bit in the first byte. */
 	bit = start_bit & 7;
@@ -108,7 +108,7 @@ int __ntfs_bitmap_set_bits_in_run(struct inode *vi, const s64 start_bit,
 	 * Depending on @value, modify all remaining whole bytes in the page up
 	 * to @cnt.
 	 */
-	len = min_t(s64, cnt >> 3, PAGE_CACHE_SIZE - pos);
+	len = min_t(s64, cnt >> 3, PAGE_SIZE - pos);
 	memset(kaddr + pos, value ? 0xff : 0, len);
 	cnt -= len << 3;
 
@@ -132,7 +132,7 @@ int __ntfs_bitmap_set_bits_in_run(struct inode *vi, const s64 start_bit,
 		 * Depending on @value, modify all remaining whole bytes in the
 		 * page up to @cnt.
 		 */
-		len = min_t(s64, cnt >> 3, PAGE_CACHE_SIZE);
+		len = min_t(s64, cnt >> 3, PAGE_SIZE);
 		memset(kaddr, value ? 0xff : 0, len);
 		cnt -= len << 3;
 	}
diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c
index f82498c35e78..f2b5e746f49b 100644
--- a/fs/ntfs/compress.c
+++ b/fs/ntfs/compress.c
@@ -104,16 +104,12 @@ static void zero_partial_compressed_page(struct page *page,
 	unsigned int kp_ofs;
 
 	ntfs_debug("Zeroing page region outside initialized size.");
-	if (((s64)page->index << PAGE_CACHE_SHIFT) >= initialized_size) {
-		/*
-		 * FIXME: Using clear_page() will become wrong when we get
-		 * PAGE_CACHE_SIZE != PAGE_SIZE but for now there is no problem.
-		 */
+	if (((s64)page->index << PAGE_SHIFT) >= initialized_size) {
 		clear_page(kp);
 		return;
 	}
-	kp_ofs = initialized_size & ~PAGE_CACHE_MASK;
-	memset(kp + kp_ofs, 0, PAGE_CACHE_SIZE - kp_ofs);
+	kp_ofs = initialized_size & ~PAGE_MASK;
+	memset(kp + kp_ofs, 0, PAGE_SIZE - kp_ofs);
 	return;
 }
 
@@ -123,7 +119,7 @@ static void zero_partial_compressed_page(struct page *page,
 static inline void handle_bounds_compressed_page(struct page *page,
 		const loff_t i_size, const s64 initialized_size)
 {
-	if ((page->index >= (initialized_size >> PAGE_CACHE_SHIFT)) &&
+	if ((page->index >= (initialized_size >> PAGE_SHIFT)) &&
 			(initialized_size < i_size))
 		zero_partial_compressed_page(page, initialized_size);
 	return;
@@ -160,7 +156,7 @@ static inline void handle_bounds_compressed_page(struct page *page,
  * @xpage_done indicates whether the target page (@dest_pages[@xpage]) was
  * completed during the decompression of the compression block (@cb_start).
  *
- * Warning: This function *REQUIRES* PAGE_CACHE_SIZE >= 4096 or it will blow up
+ * Warning: This function *REQUIRES* PAGE_SIZE >= 4096 or it will blow up
  * unpredicatbly! You have been warned!
  *
  * Note to hackers: This function may not sleep until it has finished accessing
@@ -241,7 +237,7 @@ return_error:
 				if (di == xpage)
 					*xpage_done = 1;
 				else
-					page_cache_release(dp);
+					put_page(dp);
 				dest_pages[di] = NULL;
 			}
 		}
@@ -274,7 +270,7 @@ return_error:
 		cb = cb_sb_end;
 
 		/* Advance destination position to next sub-block. */
-		*dest_ofs = (*dest_ofs + NTFS_SB_SIZE) & ~PAGE_CACHE_MASK;
+		*dest_ofs = (*dest_ofs + NTFS_SB_SIZE) & ~PAGE_MASK;
 		if (!*dest_ofs && (++*dest_index > dest_max_index))
 			goto return_overflow;
 		goto do_next_sb;
@@ -301,7 +297,7 @@ return_error:
 
 		/* Advance destination position to next sub-block. */
 		*dest_ofs += NTFS_SB_SIZE;
-		if (!(*dest_ofs &= ~PAGE_CACHE_MASK)) {
+		if (!(*dest_ofs &= ~PAGE_MASK)) {
 finalize_page:
 			/*
 			 * First stage: add current page index to array of
@@ -335,7 +331,7 @@ do_next_tag:
 			*dest_ofs += nr_bytes;
 		}
 		/* We have finished the current sub-block. */
-		if (!(*dest_ofs &= ~PAGE_CACHE_MASK))
+		if (!(*dest_ofs &= ~PAGE_MASK))
 			goto finalize_page;
 		goto do_next_sb;
 	}
@@ -462,7 +458,7 @@ return_overflow:
  * have been written to so that we would lose data if we were to just overwrite
  * them with the out-of-date uncompressed data.
  *
- * FIXME: For PAGE_CACHE_SIZE > cb_size we are not doing the Right Thing(TM) at
+ * FIXME: For PAGE_SIZE > cb_size we are not doing the Right Thing(TM) at
  * the end of the file I think. We need to detect this case and zero the out
  * of bounds remainder of the page in question and mark it as handled. At the
  * moment we would just return -EIO on such a page. This bug will only become
@@ -470,7 +466,7 @@ return_overflow:
  * clusters so is probably not going to be seen by anyone. Still this should
  * be fixed. (AIA)
  *
- * FIXME: Again for PAGE_CACHE_SIZE > cb_size we are screwing up both in
+ * FIXME: Again for PAGE_SIZE > cb_size we are screwing up both in
  * handling sparse and compressed cbs. (AIA)
  *
  * FIXME: At the moment we don't do any zeroing out in the case that
@@ -497,14 +493,14 @@ int ntfs_read_compressed_block(struct page *page)
 	u64 cb_size_mask = cb_size - 1UL;
 	VCN vcn;
 	LCN lcn;
-	/* The first wanted vcn (minimum alignment is PAGE_CACHE_SIZE). */
-	VCN start_vcn = (((s64)index << PAGE_CACHE_SHIFT) & ~cb_size_mask) >>
+	/* The first wanted vcn (minimum alignment is PAGE_SIZE). */
+	VCN start_vcn = (((s64)index << PAGE_SHIFT) & ~cb_size_mask) >>
 			vol->cluster_size_bits;
 	/*
 	 * The first vcn after the last wanted vcn (minimum alignment is again
-	 * PAGE_CACHE_SIZE.
+	 * PAGE_SIZE.
 	 */
-	VCN end_vcn = ((((s64)(index + 1UL) << PAGE_CACHE_SHIFT) + cb_size - 1)
+	VCN end_vcn = ((((s64)(index + 1UL) << PAGE_SHIFT) + cb_size - 1)
 			& ~cb_size_mask) >> vol->cluster_size_bits;
 	/* Number of compression blocks (cbs) in the wanted vcn range. */
 	unsigned int nr_cbs = (end_vcn - start_vcn) << vol->cluster_size_bits
@@ -515,7 +511,7 @@ int ntfs_read_compressed_block(struct page *page)
 	 * guarantees of start_vcn and end_vcn, no need to round up here.
 	 */
 	unsigned int nr_pages = (end_vcn - start_vcn) <<
-			vol->cluster_size_bits >> PAGE_CACHE_SHIFT;
+			vol->cluster_size_bits >> PAGE_SHIFT;
 	unsigned int xpage, max_page, cur_page, cur_ofs, i;
 	unsigned int cb_clusters, cb_max_ofs;
 	int block, max_block, cb_max_page, bhs_size, nr_bhs, err = 0;
@@ -549,7 +545,7 @@ int ntfs_read_compressed_block(struct page *page)
 	 * We have already been given one page, this is the one we must do.
 	 * Once again, the alignment guarantees keep it simple.
 	 */
-	offset = start_vcn << vol->cluster_size_bits >> PAGE_CACHE_SHIFT;
+	offset = start_vcn << vol->cluster_size_bits >> PAGE_SHIFT;
 	xpage = index - offset;
 	pages[xpage] = page;
 	/*
@@ -560,13 +556,13 @@ int ntfs_read_compressed_block(struct page *page)
 	i_size = i_size_read(VFS_I(ni));
 	initialized_size = ni->initialized_size;
 	read_unlock_irqrestore(&ni->size_lock, flags);
-	max_page = ((i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT) -
+	max_page = ((i_size + PAGE_SIZE - 1) >> PAGE_SHIFT) -
 			offset;
 	/* Is the page fully outside i_size? (truncate in progress) */
 	if (xpage >= max_page) {
 		kfree(bhs);
 		kfree(pages);
-		zero_user(page, 0, PAGE_CACHE_SIZE);
+		zero_user(page, 0, PAGE_SIZE);
 		ntfs_debug("Compressed read outside i_size - truncated?");
 		SetPageUptodate(page);
 		unlock_page(page);
@@ -591,7 +587,7 @@ int ntfs_read_compressed_block(struct page *page)
 				continue;
 			}
 			unlock_page(page);
-			page_cache_release(page);
+			put_page(page);
 			pages[i] = NULL;
 		}
 	}
@@ -735,9 +731,9 @@ lock_retry_remap:
 	ntfs_debug("Successfully read the compression block.");
 
 	/* The last page and maximum offset within it for the current cb. */
-	cb_max_page = (cur_page << PAGE_CACHE_SHIFT) + cur_ofs + cb_size;
-	cb_max_ofs = cb_max_page & ~PAGE_CACHE_MASK;
-	cb_max_page >>= PAGE_CACHE_SHIFT;
+	cb_max_page = (cur_page << PAGE_SHIFT) + cur_ofs + cb_size;
+	cb_max_ofs = cb_max_page & ~PAGE_MASK;
+	cb_max_page >>= PAGE_SHIFT;
 
 	/* Catch end of file inside a compression block. */
 	if (cb_max_page > max_page)
@@ -753,16 +749,11 @@ lock_retry_remap:
 		for (; cur_page < cb_max_page; cur_page++) {
 			page = pages[cur_page];
 			if (page) {
-				/*
-				 * FIXME: Using clear_page() will become wrong
-				 * when we get PAGE_CACHE_SIZE != PAGE_SIZE but
-				 * for now there is no problem.
-				 */
 				if (likely(!cur_ofs))
 					clear_page(page_address(page));
 				else
 					memset(page_address(page) + cur_ofs, 0,
-							PAGE_CACHE_SIZE -
+							PAGE_SIZE -
 							cur_ofs);
 				flush_dcache_page(page);
 				kunmap(page);
@@ -771,10 +762,10 @@ lock_retry_remap:
 				if (cur_page == xpage)
 					xpage_done = 1;
 				else
-					page_cache_release(page);
+					put_page(page);
 				pages[cur_page] = NULL;
 			}
-			cb_pos += PAGE_CACHE_SIZE - cur_ofs;
+			cb_pos += PAGE_SIZE - cur_ofs;
 			cur_ofs = 0;
 			if (cb_pos >= cb_end)
 				break;
@@ -807,7 +798,7 @@ lock_retry_remap:
 		 * synchronous io for the majority of pages.
 		 * Or if we choose not to do the read-ahead/-behind stuff, we
 		 * could just return block_read_full_page(pages[xpage]) as long
-		 * as PAGE_CACHE_SIZE <= cb_size.
+		 * as PAGE_SIZE <= cb_size.
 		 */
 		if (cb_max_ofs)
 			cb_max_page--;
@@ -816,8 +807,8 @@ lock_retry_remap:
 			page = pages[cur_page];
 			if (page)
 				memcpy(page_address(page) + cur_ofs, cb_pos,
-						PAGE_CACHE_SIZE - cur_ofs);
-			cb_pos += PAGE_CACHE_SIZE - cur_ofs;
+						PAGE_SIZE - cur_ofs);
+			cb_pos += PAGE_SIZE - cur_ofs;
 			cur_ofs = 0;
 			if (cb_pos >= cb_end)
 				break;
@@ -850,10 +841,10 @@ lock_retry_remap:
 				if (cur2_page == xpage)
 					xpage_done = 1;
 				else
-					page_cache_release(page);
+					put_page(page);
 				pages[cur2_page] = NULL;
 			}
-			cb_pos2 += PAGE_CACHE_SIZE - cur_ofs2;
+			cb_pos2 += PAGE_SIZE - cur_ofs2;
 			cur_ofs2 = 0;
 			if (cb_pos2 >= cb_end)
 				break;
@@ -884,7 +875,7 @@ lock_retry_remap:
 					kunmap(page);
 					unlock_page(page);
 					if (prev_cur_page != xpage)
-						page_cache_release(page);
+						put_page(page);
 					pages[prev_cur_page] = NULL;
 				}
 			}
@@ -914,7 +905,7 @@ lock_retry_remap:
 			kunmap(page);
 			unlock_page(page);
 			if (cur_page != xpage)
-				page_cache_release(page);
+				put_page(page);
 			pages[cur_page] = NULL;
 		}
 	}
@@ -961,7 +952,7 @@ err_out:
 			kunmap(page);
 			unlock_page(page);
 			if (i != xpage)
-				page_cache_release(page);
+				put_page(page);
 		}
 	}
 	kfree(pages);
diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c
index 9e38dafa3bc7..a18613579001 100644
--- a/fs/ntfs/dir.c
+++ b/fs/ntfs/dir.c
@@ -315,11 +315,11 @@ found_it:
 descend_into_child_node:
 	/*
 	 * Convert vcn to index into the index allocation attribute in units
-	 * of PAGE_CACHE_SIZE and map the page cache page, reading it from
+	 * of PAGE_SIZE and map the page cache page, reading it from
 	 * disk if necessary.
 	 */
 	page = ntfs_map_page(ia_mapping, vcn <<
-			dir_ni->itype.index.vcn_size_bits >> PAGE_CACHE_SHIFT);
+			dir_ni->itype.index.vcn_size_bits >> PAGE_SHIFT);
 	if (IS_ERR(page)) {
 		ntfs_error(sb, "Failed to map directory index page, error %ld.",
 				-PTR_ERR(page));
@@ -331,9 +331,9 @@ descend_into_child_node:
 fast_descend_into_child_node:
 	/* Get to the index allocation block. */
 	ia = (INDEX_ALLOCATION*)(kaddr + ((vcn <<
-			dir_ni->itype.index.vcn_size_bits) & ~PAGE_CACHE_MASK));
+			dir_ni->itype.index.vcn_size_bits) & ~PAGE_MASK));
 	/* Bounds checks. */
-	if ((u8*)ia < kaddr || (u8*)ia > kaddr + PAGE_CACHE_SIZE) {
+	if ((u8*)ia < kaddr || (u8*)ia > kaddr + PAGE_SIZE) {
 		ntfs_error(sb, "Out of bounds check failed. Corrupt directory "
 				"inode 0x%lx or driver bug.", dir_ni->mft_no);
 		goto unm_err_out;
@@ -366,7 +366,7 @@ fast_descend_into_child_node:
 		goto unm_err_out;
 	}
 	index_end = (u8*)ia + dir_ni->itype.index.block_size;
-	if (index_end > kaddr + PAGE_CACHE_SIZE) {
+	if (index_end > kaddr + PAGE_SIZE) {
 		ntfs_error(sb, "Index buffer (VCN 0x%llx) of directory inode "
 				"0x%lx crosses page boundary. Impossible! "
 				"Cannot access! This is probably a bug in the "
@@ -559,9 +559,9 @@ found_it2:
 			/* If vcn is in the same page cache page as old_vcn we
 			 * recycle the mapped page. */
 			if (old_vcn << vol->cluster_size_bits >>
-					PAGE_CACHE_SHIFT == vcn <<
+					PAGE_SHIFT == vcn <<
 					vol->cluster_size_bits >>
-					PAGE_CACHE_SHIFT)
+					PAGE_SHIFT)
 				goto fast_descend_into_child_node;
 			unlock_page(page);
 			ntfs_unmap_page(page);
@@ -793,11 +793,11 @@ found_it:
 descend_into_child_node:
 	/*
 	 * Convert vcn to index into the index allocation attribute in units
-	 * of PAGE_CACHE_SIZE and map the page cache page, reading it from
+	 * of PAGE_SIZE and map the page cache page, reading it from
 	 * disk if necessary.
 	 */
 	page = ntfs_map_page(ia_mapping, vcn <<
-			dir_ni->itype.index.vcn_size_bits >> PAGE_CACHE_SHIFT);
+			dir_ni->itype.index.vcn_size_bits >> PAGE_SHIFT);
 	if (IS_ERR(page)) {
 		ntfs_error(sb, "Failed to map directory index page, error %ld.",
 				-PTR_ERR(page));
@@ -809,9 +809,9 @@ descend_into_child_node:
 fast_descend_into_child_node:
 	/* Get to the index allocation block. */
 	ia = (INDEX_ALLOCATION*)(kaddr + ((vcn <<
-			dir_ni->itype.index.vcn_size_bits) & ~PAGE_CACHE_MASK));
+			dir_ni->itype.index.vcn_size_bits) & ~PAGE_MASK));
 	/* Bounds checks. */
-	if ((u8*)ia < kaddr || (u8*)ia > kaddr + PAGE_CACHE_SIZE) {
+	if ((u8*)ia < kaddr || (u8*)ia > kaddr + PAGE_SIZE) {
 		ntfs_error(sb, "Out of bounds check failed. Corrupt directory "
 				"inode 0x%lx or driver bug.", dir_ni->mft_no);
 		goto unm_err_out;
@@ -844,7 +844,7 @@ fast_descend_into_child_node:
 		goto unm_err_out;
 	}
 	index_end = (u8*)ia + dir_ni->itype.index.block_size;
-	if (index_end > kaddr + PAGE_CACHE_SIZE) {
+	if (index_end > kaddr + PAGE_SIZE) {
 		ntfs_error(sb, "Index buffer (VCN 0x%llx) of directory inode "
 				"0x%lx crosses page boundary. Impossible! "
 				"Cannot access! This is probably a bug in the "
@@ -968,9 +968,9 @@ found_it2:
 			/* If vcn is in the same page cache page as old_vcn we
 			 * recycle the mapped page. */
 			if (old_vcn << vol->cluster_size_bits >>
-					PAGE_CACHE_SHIFT == vcn <<
+					PAGE_SHIFT == vcn <<
 					vol->cluster_size_bits >>
-					PAGE_CACHE_SHIFT)
+					PAGE_SHIFT)
 				goto fast_descend_into_child_node;
 			unlock_page(page);
 			ntfs_unmap_page(page);
@@ -1246,15 +1246,15 @@ skip_index_root:
 		goto iput_err_out;
 	}
 	/* Get the starting bit position in the current bitmap page. */
-	cur_bmp_pos = bmp_pos & ((PAGE_CACHE_SIZE * 8) - 1);
-	bmp_pos &= ~(u64)((PAGE_CACHE_SIZE * 8) - 1);
+	cur_bmp_pos = bmp_pos & ((PAGE_SIZE * 8) - 1);
+	bmp_pos &= ~(u64)((PAGE_SIZE * 8) - 1);
 get_next_bmp_page:
 	ntfs_debug("Reading bitmap with page index 0x%llx, bit ofs 0x%llx",
-			(unsigned long long)bmp_pos >> (3 + PAGE_CACHE_SHIFT),
+			(unsigned long long)bmp_pos >> (3 + PAGE_SHIFT),
 			(unsigned long long)bmp_pos &
-			(unsigned long long)((PAGE_CACHE_SIZE * 8) - 1));
+			(unsigned long long)((PAGE_SIZE * 8) - 1));
 	bmp_page = ntfs_map_page(bmp_mapping,
-			bmp_pos >> (3 + PAGE_CACHE_SHIFT));
+			bmp_pos >> (3 + PAGE_SHIFT));
 	if (IS_ERR(bmp_page)) {
 		ntfs_error(sb, "Reading index bitmap failed.");
 		err = PTR_ERR(bmp_page);
@@ -1270,9 +1270,9 @@ find_next_index_buffer:
 		 * If we have reached the end of the bitmap page, get the next
 		 * page, and put away the old one.
 		 */
-		if (unlikely((cur_bmp_pos >> 3) >= PAGE_CACHE_SIZE)) {
+		if (unlikely((cur_bmp_pos >> 3) >= PAGE_SIZE)) {
 			ntfs_unmap_page(bmp_page);
-			bmp_pos += PAGE_CACHE_SIZE * 8;
+			bmp_pos += PAGE_SIZE * 8;
 			cur_bmp_pos = 0;
 			goto get_next_bmp_page;
 		}
@@ -1285,8 +1285,8 @@ find_next_index_buffer:
 	ntfs_debug("Handling index buffer 0x%llx.",
 			(unsigned long long)bmp_pos + cur_bmp_pos);
 	/* If the current index buffer is in the same page we reuse the page. */
-	if ((prev_ia_pos & (s64)PAGE_CACHE_MASK) !=
-			(ia_pos & (s64)PAGE_CACHE_MASK)) {
+	if ((prev_ia_pos & (s64)PAGE_MASK) !=
+			(ia_pos & (s64)PAGE_MASK)) {
 		prev_ia_pos = ia_pos;
 		if (likely(ia_page != NULL)) {
 			unlock_page(ia_page);
@@ -1296,7 +1296,7 @@ find_next_index_buffer:
 		 * Map the page cache page containing the current ia_pos,
 		 * reading it from disk if necessary.
 		 */
-		ia_page = ntfs_map_page(ia_mapping, ia_pos >> PAGE_CACHE_SHIFT);
+		ia_page = ntfs_map_page(ia_mapping, ia_pos >> PAGE_SHIFT);
 		if (IS_ERR(ia_page)) {
 			ntfs_error(sb, "Reading index allocation data failed.");
 			err = PTR_ERR(ia_page);
@@ -1307,10 +1307,10 @@ find_next_index_buffer:
 		kaddr = (u8*)page_address(ia_page);
 	}
 	/* Get the current index buffer. */
-	ia = (INDEX_ALLOCATION*)(kaddr + (ia_pos & ~PAGE_CACHE_MASK &
-			~(s64)(ndir->itype.index.block_size - 1)));
+	ia = (INDEX_ALLOCATION*)(kaddr + (ia_pos & ~PAGE_MASK &
+					  ~(s64)(ndir->itype.index.block_size - 1)));
 	/* Bounds checks. */
-	if (unlikely((u8*)ia < kaddr || (u8*)ia > kaddr + PAGE_CACHE_SIZE)) {
+	if (unlikely((u8*)ia < kaddr || (u8*)ia > kaddr + PAGE_SIZE)) {
 		ntfs_error(sb, "Out of bounds check failed. Corrupt directory "
 				"inode 0x%lx or driver bug.", vdir->i_ino);
 		goto err_out;
@@ -1348,7 +1348,7 @@ find_next_index_buffer:
 		goto err_out;
 	}
 	index_end = (u8*)ia + ndir->itype.index.block_size;
-	if (unlikely(index_end > kaddr + PAGE_CACHE_SIZE)) {
+	if (unlikely(index_end > kaddr + PAGE_SIZE)) {
 		ntfs_error(sb, "Index buffer (VCN 0x%llx) of directory inode "
 				"0x%lx crosses page boundary. Impossible! "
 				"Cannot access! This is probably a bug in the "
@@ -1509,7 +1509,7 @@ static int ntfs_dir_fsync(struct file *filp, loff_t start, loff_t end,
 	err = filemap_write_and_wait_range(vi->i_mapping, start, end);
 	if (err)
 		return err;
-	mutex_lock(&vi->i_mutex);
+	inode_lock(vi);
 
 	BUG_ON(!S_ISDIR(vi->i_mode));
 	/* If the bitmap attribute inode is in memory sync it, too. */
@@ -1532,7 +1532,7 @@ static int ntfs_dir_fsync(struct file *filp, loff_t start, loff_t end,
 	else
 		ntfs_warning(vi->i_sb, "Failed to f%ssync inode 0x%lx.  Error "
 				"%u.", datasync ? "data" : "", vi->i_ino, -ret);
-	mutex_unlock(&vi->i_mutex);
+	inode_unlock(vi);
 	return ret;
 }
 
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index 262561fea923..91117ada8528 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -220,8 +220,8 @@ do_non_resident_extend:
 		m = NULL;
 	}
 	mapping = vi->i_mapping;
-	index = old_init_size >> PAGE_CACHE_SHIFT;
-	end_index = (new_init_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	index = old_init_size >> PAGE_SHIFT;
+	end_index = (new_init_size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	do {
 		/*
 		 * Read the page.  If the page is not present, this will zero
@@ -233,7 +233,7 @@ do_non_resident_extend:
 			goto init_err_out;
 		}
 		if (unlikely(PageError(page))) {
-			page_cache_release(page);
+			put_page(page);
 			err = -EIO;
 			goto init_err_out;
 		}
@@ -242,13 +242,13 @@ do_non_resident_extend:
 		 * enough to make ntfs_writepage() work.
 		 */
 		write_lock_irqsave(&ni->size_lock, flags);
-		ni->initialized_size = (s64)(index + 1) << PAGE_CACHE_SHIFT;
+		ni->initialized_size = (s64)(index + 1) << PAGE_SHIFT;
 		if (ni->initialized_size > new_init_size)
 			ni->initialized_size = new_init_size;
 		write_unlock_irqrestore(&ni->size_lock, flags);
 		/* Set the page dirty so it gets written out. */
 		set_page_dirty(page);
-		page_cache_release(page);
+		put_page(page);
 		/*
 		 * Play nice with the vm and the rest of the system.  This is
 		 * very much needed as we can potentially be modifying the
@@ -525,8 +525,8 @@ static inline int __ntfs_grab_cache_pages(struct address_space *mapping,
 				}
 			}
 			err = add_to_page_cache_lru(*cached_page, mapping,
-					index,
-					GFP_KERNEL & mapping_gfp_mask(mapping));
+				   index,
+				   mapping_gfp_constraint(mapping, GFP_KERNEL));
 			if (unlikely(err)) {
 				if (err == -EEXIST)
 					continue;
@@ -543,7 +543,7 @@ out:
 err_out:
 	while (nr > 0) {
 		unlock_page(pages[--nr]);
-		page_cache_release(pages[nr]);
+		put_page(pages[nr]);
 	}
 	goto out;
 }
@@ -573,7 +573,7 @@ static inline int ntfs_submit_bh_for_read(struct buffer_head *bh)
  * only partially being written to.
  *
  * If @nr_pages is greater than one, we are guaranteed that the cluster size is
- * greater than PAGE_CACHE_SIZE, that all pages in @pages are entirely inside
+ * greater than PAGE_SIZE, that all pages in @pages are entirely inside
  * the same cluster and that they are the entirety of that cluster, and that
  * the cluster is sparse, i.e. we need to allocate a cluster to fill the hole.
  *
@@ -653,7 +653,7 @@ static int ntfs_prepare_pages_for_non_resident_write(struct page **pages,
 	u = 0;
 do_next_page:
 	page = pages[u];
-	bh_pos = (s64)page->index << PAGE_CACHE_SHIFT;
+	bh_pos = (s64)page->index << PAGE_SHIFT;
 	bh = head = page_buffers(page);
 	do {
 		VCN cdelta;
@@ -810,11 +810,11 @@ map_buffer_cached:
 					
 				kaddr = kmap_atomic(page);
 				if (bh_pos < pos) {
-					pofs = bh_pos & ~PAGE_CACHE_MASK;
+					pofs = bh_pos & ~PAGE_MASK;
 					memset(kaddr + pofs, 0, pos - bh_pos);
 				}
 				if (bh_end > end) {
-					pofs = end & ~PAGE_CACHE_MASK;
+					pofs = end & ~PAGE_MASK;
 					memset(kaddr + pofs, 0, bh_end - end);
 				}
 				kunmap_atomic(kaddr);
@@ -942,7 +942,7 @@ rl_not_mapped_enoent:
 		 * unmapped.  This can only happen when the cluster size is
 		 * less than the page cache size.
 		 */
-		if (unlikely(vol->cluster_size < PAGE_CACHE_SIZE)) {
+		if (unlikely(vol->cluster_size < PAGE_SIZE)) {
 			bh_cend = (bh_end + vol->cluster_size - 1) >>
 					vol->cluster_size_bits;
 			if ((bh_cend <= cpos || bh_cpos >= cend)) {
@@ -1208,7 +1208,7 @@ rl_not_mapped_enoent:
 		wait_on_buffer(bh);
 		if (likely(buffer_uptodate(bh))) {
 			page = bh->b_page;
-			bh_pos = ((s64)page->index << PAGE_CACHE_SHIFT) +
+			bh_pos = ((s64)page->index << PAGE_SHIFT) +
 					bh_offset(bh);
 			/*
 			 * If the buffer overflows the initialized size, need
@@ -1350,7 +1350,7 @@ rl_not_mapped_enoent:
 		bh = head = page_buffers(page);
 		do {
 			if (u == nr_pages &&
-					((s64)page->index << PAGE_CACHE_SHIFT) +
+					((s64)page->index << PAGE_SHIFT) +
 					bh_offset(bh) >= end)
 				break;
 			if (!buffer_new(bh))
@@ -1422,7 +1422,7 @@ static inline int ntfs_commit_pages_after_non_resident_write(
 		bool partial;
 
 		page = pages[u];
-		bh_pos = (s64)page->index << PAGE_CACHE_SHIFT;
+		bh_pos = (s64)page->index << PAGE_SHIFT;
 		bh = head = page_buffers(page);
 		partial = false;
 		do {
@@ -1639,7 +1639,7 @@ static int ntfs_commit_pages_after_write(struct page **pages,
 		if (end < attr_len)
 			memcpy(kaddr + end, kattr + end, attr_len - end);
 		/* Zero the region outside the end of the attribute value. */
-		memset(kaddr + attr_len, 0, PAGE_CACHE_SIZE - attr_len);
+		memset(kaddr + attr_len, 0, PAGE_SIZE - attr_len);
 		flush_dcache_page(page);
 		SetPageUptodate(page);
 	}
@@ -1706,7 +1706,7 @@ static size_t ntfs_copy_from_user_iter(struct page **pages, unsigned nr_pages,
 	unsigned len, copied;
 
 	do {
-		len = PAGE_CACHE_SIZE - ofs;
+		len = PAGE_SIZE - ofs;
 		if (len > bytes)
 			len = bytes;
 		copied = iov_iter_copy_from_user_atomic(*pages, &data, ofs,
@@ -1724,14 +1724,14 @@ out:
 	return total;
 err:
 	/* Zero the rest of the target like __copy_from_user(). */
-	len = PAGE_CACHE_SIZE - copied;
+	len = PAGE_SIZE - copied;
 	do {
 		if (len > bytes)
 			len = bytes;
 		zero_user(*pages, copied, len);
 		bytes -= len;
 		copied = 0;
-		len = PAGE_CACHE_SIZE;
+		len = PAGE_SIZE;
 	} while (++pages < last_page);
 	goto out;
 }
@@ -1787,8 +1787,8 @@ static ssize_t ntfs_perform_write(struct file *file, struct iov_iter *i,
 	 * attributes.
 	 */
 	nr_pages = 1;
-	if (vol->cluster_size > PAGE_CACHE_SIZE && NInoNonResident(ni))
-		nr_pages = vol->cluster_size >> PAGE_CACHE_SHIFT;
+	if (vol->cluster_size > PAGE_SIZE && NInoNonResident(ni))
+		nr_pages = vol->cluster_size >> PAGE_SHIFT;
 	last_vcn = -1;
 	do {
 		VCN vcn;
@@ -1796,9 +1796,9 @@ static ssize_t ntfs_perform_write(struct file *file, struct iov_iter *i,
 		unsigned ofs, do_pages, u;
 		size_t copied;
 
-		start_idx = idx = pos >> PAGE_CACHE_SHIFT;
-		ofs = pos & ~PAGE_CACHE_MASK;
-		bytes = PAGE_CACHE_SIZE - ofs;
+		start_idx = idx = pos >> PAGE_SHIFT;
+		ofs = pos & ~PAGE_MASK;
+		bytes = PAGE_SIZE - ofs;
 		do_pages = 1;
 		if (nr_pages > 1) {
 			vcn = pos >> vol->cluster_size_bits;
@@ -1832,7 +1832,7 @@ static ssize_t ntfs_perform_write(struct file *file, struct iov_iter *i,
 				if (lcn == LCN_HOLE) {
 					start_idx = (pos & ~(s64)
 							vol->cluster_size_mask)
-							>> PAGE_CACHE_SHIFT;
+							>> PAGE_SHIFT;
 					bytes = vol->cluster_size - (pos &
 							vol->cluster_size_mask);
 					do_pages = nr_pages;
@@ -1871,12 +1871,12 @@ again:
 			if (unlikely(status)) {
 				do {
 					unlock_page(pages[--do_pages]);
-					page_cache_release(pages[do_pages]);
+					put_page(pages[do_pages]);
 				} while (do_pages);
 				break;
 			}
 		}
-		u = (pos >> PAGE_CACHE_SHIFT) - pages[0]->index;
+		u = (pos >> PAGE_SHIFT) - pages[0]->index;
 		copied = ntfs_copy_from_user_iter(pages + u, do_pages - u, ofs,
 					i, bytes);
 		ntfs_flush_dcache_pages(pages + u, do_pages - u);
@@ -1889,7 +1889,7 @@ again:
 		}
 		do {
 			unlock_page(pages[--do_pages]);
-			page_cache_release(pages[do_pages]);
+			put_page(pages[do_pages]);
 		} while (do_pages);
 		if (unlikely(status < 0))
 			break;
@@ -1921,7 +1921,7 @@ again:
 		}
 	} while (iov_iter_count(i));
 	if (cached_page)
-		page_cache_release(cached_page);
+		put_page(cached_page);
 	ntfs_debug("Done.  Returning %s (written 0x%lx, status %li).",
 			written ? "written" : "status", (unsigned long)written,
 			(long)status);
@@ -1944,14 +1944,14 @@ static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	ssize_t written = 0;
 	ssize_t err;
 
-	mutex_lock(&vi->i_mutex);
+	inode_lock(vi);
 	/* We can write back this queue in page reclaim. */
 	current->backing_dev_info = inode_to_bdi(vi);
 	err = ntfs_prepare_file_for_write(iocb, from);
 	if (iov_iter_count(from) && !err)
 		written = ntfs_perform_write(file, from, iocb->ki_pos);
 	current->backing_dev_info = NULL;
-	mutex_unlock(&vi->i_mutex);
+	inode_unlock(vi);
 	if (likely(written > 0)) {
 		err = generic_write_sync(file, iocb->ki_pos, written);
 		if (err < 0)
@@ -1996,7 +1996,7 @@ static int ntfs_file_fsync(struct file *filp, loff_t start, loff_t end,
 	err = filemap_write_and_wait_range(vi->i_mapping, start, end);
 	if (err)
 		return err;
-	mutex_lock(&vi->i_mutex);
+	inode_lock(vi);
 
 	BUG_ON(S_ISDIR(vi->i_mode));
 	if (!datasync || !NInoNonResident(NTFS_I(vi)))
@@ -2015,7 +2015,7 @@ static int ntfs_file_fsync(struct file *filp, loff_t start, loff_t end,
 	else
 		ntfs_warning(vi->i_sb, "Failed to f%ssync inode 0x%lx.  Error "
 				"%u.", datasync ? "data" : "", vi->i_ino, -ret);
-	mutex_unlock(&vi->i_mutex);
+	inode_unlock(vi);
 	return ret;
 }
 
diff --git a/fs/ntfs/index.c b/fs/ntfs/index.c
index 096c135691ae..0d645f357930 100644
--- a/fs/ntfs/index.c
+++ b/fs/ntfs/index.c
@@ -272,11 +272,11 @@ done:
 descend_into_child_node:
 	/*
 	 * Convert vcn to index into the index allocation attribute in units
-	 * of PAGE_CACHE_SIZE and map the page cache page, reading it from
+	 * of PAGE_SIZE and map the page cache page, reading it from
 	 * disk if necessary.
 	 */
 	page = ntfs_map_page(ia_mapping, vcn <<
-			idx_ni->itype.index.vcn_size_bits >> PAGE_CACHE_SHIFT);
+			idx_ni->itype.index.vcn_size_bits >> PAGE_SHIFT);
 	if (IS_ERR(page)) {
 		ntfs_error(sb, "Failed to map index page, error %ld.",
 				-PTR_ERR(page));
@@ -288,9 +288,9 @@ descend_into_child_node:
 fast_descend_into_child_node:
 	/* Get to the index allocation block. */
 	ia = (INDEX_ALLOCATION*)(kaddr + ((vcn <<
-			idx_ni->itype.index.vcn_size_bits) & ~PAGE_CACHE_MASK));
+			idx_ni->itype.index.vcn_size_bits) & ~PAGE_MASK));
 	/* Bounds checks. */
-	if ((u8*)ia < kaddr || (u8*)ia > kaddr + PAGE_CACHE_SIZE) {
+	if ((u8*)ia < kaddr || (u8*)ia > kaddr + PAGE_SIZE) {
 		ntfs_error(sb, "Out of bounds check failed.  Corrupt inode "
 				"0x%lx or driver bug.", idx_ni->mft_no);
 		goto unm_err_out;
@@ -323,7 +323,7 @@ fast_descend_into_child_node:
 		goto unm_err_out;
 	}
 	index_end = (u8*)ia + idx_ni->itype.index.block_size;
-	if (index_end > kaddr + PAGE_CACHE_SIZE) {
+	if (index_end > kaddr + PAGE_SIZE) {
 		ntfs_error(sb, "Index buffer (VCN 0x%llx) of inode 0x%lx "
 				"crosses page boundary.  Impossible!  Cannot "
 				"access!  This is probably a bug in the "
@@ -427,9 +427,9 @@ ia_done:
 		 * the mapped page.
 		 */
 		if (old_vcn << vol->cluster_size_bits >>
-				PAGE_CACHE_SHIFT == vcn <<
+				PAGE_SHIFT == vcn <<
 				vol->cluster_size_bits >>
-				PAGE_CACHE_SHIFT)
+				PAGE_SHIFT)
 			goto fast_descend_into_child_node;
 		unlock_page(page);
 		ntfs_unmap_page(page);
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
index d284f07eda77..f40972d6df90 100644
--- a/fs/ntfs/inode.c
+++ b/fs/ntfs/inode.c
@@ -868,12 +868,12 @@ skip_attr_list_load:
 					ni->itype.index.block_size);
 			goto unm_err_out;
 		}
-		if (ni->itype.index.block_size > PAGE_CACHE_SIZE) {
+		if (ni->itype.index.block_size > PAGE_SIZE) {
 			ntfs_error(vi->i_sb, "Index block size (%u) > "
-					"PAGE_CACHE_SIZE (%ld) is not "
+					"PAGE_SIZE (%ld) is not "
 					"supported.  Sorry.",
 					ni->itype.index.block_size,
-					PAGE_CACHE_SIZE);
+					PAGE_SIZE);
 			err = -EOPNOTSUPP;
 			goto unm_err_out;
 		}
@@ -1585,10 +1585,10 @@ static int ntfs_read_locked_index_inode(struct inode *base_vi, struct inode *vi)
 				"two.", ni->itype.index.block_size);
 		goto unm_err_out;
 	}
-	if (ni->itype.index.block_size > PAGE_CACHE_SIZE) {
-		ntfs_error(vi->i_sb, "Index block size (%u) > PAGE_CACHE_SIZE "
+	if (ni->itype.index.block_size > PAGE_SIZE) {
+		ntfs_error(vi->i_sb, "Index block size (%u) > PAGE_SIZE "
 				"(%ld) is not supported.  Sorry.",
-				ni->itype.index.block_size, PAGE_CACHE_SIZE);
+				ni->itype.index.block_size, PAGE_SIZE);
 		err = -EOPNOTSUPP;
 		goto unm_err_out;
 	}
diff --git a/fs/ntfs/lcnalloc.c b/fs/ntfs/lcnalloc.c
index 1711b710b641..27a24a42f712 100644
--- a/fs/ntfs/lcnalloc.c
+++ b/fs/ntfs/lcnalloc.c
@@ -283,15 +283,15 @@ runlist_element *ntfs_cluster_alloc(ntfs_volume *vol, const VCN start_vcn,
 			ntfs_unmap_page(page);
 		}
 		page = ntfs_map_page(mapping, last_read_pos >>
-				PAGE_CACHE_SHIFT);
+				PAGE_SHIFT);
 		if (IS_ERR(page)) {
 			err = PTR_ERR(page);
 			ntfs_error(vol->sb, "Failed to map page.");
 			goto out;
 		}
-		buf_size = last_read_pos & ~PAGE_CACHE_MASK;
+		buf_size = last_read_pos & ~PAGE_MASK;
 		buf = page_address(page) + buf_size;
-		buf_size = PAGE_CACHE_SIZE - buf_size;
+		buf_size = PAGE_SIZE - buf_size;
 		if (unlikely(last_read_pos + buf_size > i_size))
 			buf_size = i_size - last_read_pos;
 		buf_size <<= 3;
diff --git a/fs/ntfs/logfile.c b/fs/ntfs/logfile.c
index c71de292c5ad..9d71213ca81e 100644
--- a/fs/ntfs/logfile.c
+++ b/fs/ntfs/logfile.c
@@ -381,7 +381,7 @@ static int ntfs_check_and_load_restart_page(struct inode *vi,
 	 * completely inside @rp, just copy it from there.  Otherwise map all
 	 * the required pages and copy the data from them.
 	 */
-	size = PAGE_CACHE_SIZE - (pos & ~PAGE_CACHE_MASK);
+	size = PAGE_SIZE - (pos & ~PAGE_MASK);
 	if (size >= le32_to_cpu(rp->system_page_size)) {
 		memcpy(trp, rp, le32_to_cpu(rp->system_page_size));
 	} else {
@@ -394,8 +394,8 @@ static int ntfs_check_and_load_restart_page(struct inode *vi,
 		/* Copy the remaining data one page at a time. */
 		have_read = size;
 		to_read = le32_to_cpu(rp->system_page_size) - size;
-		idx = (pos + size) >> PAGE_CACHE_SHIFT;
-		BUG_ON((pos + size) & ~PAGE_CACHE_MASK);
+		idx = (pos + size) >> PAGE_SHIFT;
+		BUG_ON((pos + size) & ~PAGE_MASK);
 		do {
 			page = ntfs_map_page(vi->i_mapping, idx);
 			if (IS_ERR(page)) {
@@ -406,7 +406,7 @@ static int ntfs_check_and_load_restart_page(struct inode *vi,
 					err = -EIO;
 				goto err_out;
 			}
-			size = min_t(int, to_read, PAGE_CACHE_SIZE);
+			size = min_t(int, to_read, PAGE_SIZE);
 			memcpy((u8*)trp + have_read, page_address(page), size);
 			ntfs_unmap_page(page);
 			have_read += size;
@@ -509,11 +509,11 @@ bool ntfs_check_logfile(struct inode *log_vi, RESTART_PAGE_HEADER **rp)
 	 * log page size if the page cache size is between the default log page
 	 * size and twice that.
 	 */
-	if (PAGE_CACHE_SIZE >= DefaultLogPageSize && PAGE_CACHE_SIZE <=
+	if (PAGE_SIZE >= DefaultLogPageSize && PAGE_SIZE <=
 			DefaultLogPageSize * 2)
 		log_page_size = DefaultLogPageSize;
 	else
-		log_page_size = PAGE_CACHE_SIZE;
+		log_page_size = PAGE_SIZE;
 	log_page_mask = log_page_size - 1;
 	/*
 	 * Use ntfs_ffs() instead of ffs() to enable the compiler to
@@ -539,7 +539,7 @@ bool ntfs_check_logfile(struct inode *log_vi, RESTART_PAGE_HEADER **rp)
 	 * to be empty.
 	 */
 	for (pos = 0; pos < size; pos <<= 1) {
-		pgoff_t idx = pos >> PAGE_CACHE_SHIFT;
+		pgoff_t idx = pos >> PAGE_SHIFT;
 		if (!page || page->index != idx) {
 			if (page)
 				ntfs_unmap_page(page);
@@ -550,7 +550,7 @@ bool ntfs_check_logfile(struct inode *log_vi, RESTART_PAGE_HEADER **rp)
 				goto err_out;
 			}
 		}
-		kaddr = (u8*)page_address(page) + (pos & ~PAGE_CACHE_MASK);
+		kaddr = (u8*)page_address(page) + (pos & ~PAGE_MASK);
 		/*
 		 * A non-empty block means the logfile is not empty while an
 		 * empty block after a non-empty block has been encountered
diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c
index 3014a36a255b..37b2501caaa4 100644
--- a/fs/ntfs/mft.c
+++ b/fs/ntfs/mft.c
@@ -61,16 +61,16 @@ static inline MFT_RECORD *map_mft_record_page(ntfs_inode *ni)
 	 * here if the volume was that big...
 	 */
 	index = (u64)ni->mft_no << vol->mft_record_size_bits >>
-			PAGE_CACHE_SHIFT;
-	ofs = (ni->mft_no << vol->mft_record_size_bits) & ~PAGE_CACHE_MASK;
+			PAGE_SHIFT;
+	ofs = (ni->mft_no << vol->mft_record_size_bits) & ~PAGE_MASK;
 
 	i_size = i_size_read(mft_vi);
 	/* The maximum valid index into the page cache for $MFT's data. */
-	end_index = i_size >> PAGE_CACHE_SHIFT;
+	end_index = i_size >> PAGE_SHIFT;
 
 	/* If the wanted index is out of bounds the mft record doesn't exist. */
 	if (unlikely(index >= end_index)) {
-		if (index > end_index || (i_size & ~PAGE_CACHE_MASK) < ofs +
+		if (index > end_index || (i_size & ~PAGE_MASK) < ofs +
 				vol->mft_record_size) {
 			page = ERR_PTR(-ENOENT);
 			ntfs_error(vol->sb, "Attempt to read mft record 0x%lx, "
@@ -487,7 +487,7 @@ int ntfs_sync_mft_mirror(ntfs_volume *vol, const unsigned long mft_no,
 	}
 	/* Get the page containing the mirror copy of the mft record @m. */
 	page = ntfs_map_page(vol->mftmirr_ino->i_mapping, mft_no >>
-			(PAGE_CACHE_SHIFT - vol->mft_record_size_bits));
+			(PAGE_SHIFT - vol->mft_record_size_bits));
 	if (IS_ERR(page)) {
 		ntfs_error(vol->sb, "Failed to map mft mirror page.");
 		err = PTR_ERR(page);
@@ -497,7 +497,7 @@ int ntfs_sync_mft_mirror(ntfs_volume *vol, const unsigned long mft_no,
 	BUG_ON(!PageUptodate(page));
 	ClearPageUptodate(page);
 	/* Offset of the mft mirror record inside the page. */
-	page_ofs = (mft_no << vol->mft_record_size_bits) & ~PAGE_CACHE_MASK;
+	page_ofs = (mft_no << vol->mft_record_size_bits) & ~PAGE_MASK;
 	/* The address in the page of the mirror copy of the mft record @m. */
 	kmirr = page_address(page) + page_ofs;
 	/* Copy the mst protected mft record to the mirror. */
@@ -1178,8 +1178,8 @@ static int ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(ntfs_volume *vol,
 	for (; pass <= 2;) {
 		/* Cap size to pass_end. */
 		ofs = data_pos >> 3;
-		page_ofs = ofs & ~PAGE_CACHE_MASK;
-		size = PAGE_CACHE_SIZE - page_ofs;
+		page_ofs = ofs & ~PAGE_MASK;
+		size = PAGE_SIZE - page_ofs;
 		ll = ((pass_end + 7) >> 3) - ofs;
 		if (size > ll)
 			size = ll;
@@ -1190,7 +1190,7 @@ static int ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(ntfs_volume *vol,
 		 */
 		if (size) {
 			page = ntfs_map_page(mftbmp_mapping,
-					ofs >> PAGE_CACHE_SHIFT);
+					ofs >> PAGE_SHIFT);
 			if (IS_ERR(page)) {
 				ntfs_error(vol->sb, "Failed to read mft "
 						"bitmap, aborting.");
@@ -1328,13 +1328,13 @@ static int ntfs_mft_bitmap_extend_allocation_nolock(ntfs_volume *vol)
 	 */
 	ll = lcn >> 3;
 	page = ntfs_map_page(vol->lcnbmp_ino->i_mapping,
-			ll >> PAGE_CACHE_SHIFT);
+			ll >> PAGE_SHIFT);
 	if (IS_ERR(page)) {
 		up_write(&mftbmp_ni->runlist.lock);
 		ntfs_error(vol->sb, "Failed to read from lcn bitmap.");
 		return PTR_ERR(page);
 	}
-	b = (u8*)page_address(page) + (ll & ~PAGE_CACHE_MASK);
+	b = (u8*)page_address(page) + (ll & ~PAGE_MASK);
 	tb = 1 << (lcn & 7ull);
 	down_write(&vol->lcnbmp_lock);
 	if (*b != 0xff && !(*b & tb)) {
@@ -2103,14 +2103,14 @@ static int ntfs_mft_record_format(const ntfs_volume *vol, const s64 mft_no)
 	 * The index into the page cache and the offset within the page cache
 	 * page of the wanted mft record.
 	 */
-	index = mft_no << vol->mft_record_size_bits >> PAGE_CACHE_SHIFT;
-	ofs = (mft_no << vol->mft_record_size_bits) & ~PAGE_CACHE_MASK;
+	index = mft_no << vol->mft_record_size_bits >> PAGE_SHIFT;
+	ofs = (mft_no << vol->mft_record_size_bits) & ~PAGE_MASK;
 	/* The maximum valid index into the page cache for $MFT's data. */
 	i_size = i_size_read(mft_vi);
-	end_index = i_size >> PAGE_CACHE_SHIFT;
+	end_index = i_size >> PAGE_SHIFT;
 	if (unlikely(index >= end_index)) {
 		if (unlikely(index > end_index || ofs + vol->mft_record_size >=
-				(i_size & ~PAGE_CACHE_MASK))) {
+				(i_size & ~PAGE_MASK))) {
 			ntfs_error(vol->sb, "Tried to format non-existing mft "
 					"record 0x%llx.", (long long)mft_no);
 			return -ENOENT;
@@ -2515,8 +2515,8 @@ mft_rec_already_initialized:
 	 * We now have allocated and initialized the mft record.  Calculate the
 	 * index of and the offset within the page cache page the record is in.
 	 */
-	index = bit << vol->mft_record_size_bits >> PAGE_CACHE_SHIFT;
-	ofs = (bit << vol->mft_record_size_bits) & ~PAGE_CACHE_MASK;
+	index = bit << vol->mft_record_size_bits >> PAGE_SHIFT;
+	ofs = (bit << vol->mft_record_size_bits) & ~PAGE_MASK;
 	/* Read, map, and pin the page containing the mft record. */
 	page = ntfs_map_page(vol->mft_ino->i_mapping, index);
 	if (IS_ERR(page)) {
diff --git a/fs/ntfs/ntfs.h b/fs/ntfs/ntfs.h
index c581e26a350d..12de47b96ca9 100644
--- a/fs/ntfs/ntfs.h
+++ b/fs/ntfs/ntfs.h
@@ -43,7 +43,7 @@ typedef enum {
 	NTFS_MAX_NAME_LEN	= 255,
 	NTFS_MAX_ATTR_NAME_LEN	= 255,
 	NTFS_MAX_CLUSTER_SIZE	= 64 * 1024,	/* 64kiB */
-	NTFS_MAX_PAGES_PER_CLUSTER = NTFS_MAX_CLUSTER_SIZE / PAGE_CACHE_SIZE,
+	NTFS_MAX_PAGES_PER_CLUSTER = NTFS_MAX_CLUSTER_SIZE / PAGE_SIZE,
 } NTFS_CONSTANTS;
 
 /* Global variables. */
diff --git a/fs/ntfs/quota.c b/fs/ntfs/quota.c
index d80e3315cab0..9793e68ba1dd 100644
--- a/fs/ntfs/quota.c
+++ b/fs/ntfs/quota.c
@@ -48,7 +48,7 @@ bool ntfs_mark_quotas_out_of_date(ntfs_volume *vol)
 		ntfs_error(vol->sb, "Quota inodes are not open.");
 		return false;
 	}
-	mutex_lock(&vol->quota_q_ino->i_mutex);
+	inode_lock(vol->quota_q_ino);
 	ictx = ntfs_index_ctx_get(NTFS_I(vol->quota_q_ino));
 	if (!ictx) {
 		ntfs_error(vol->sb, "Failed to get index context.");
@@ -98,7 +98,7 @@ bool ntfs_mark_quotas_out_of_date(ntfs_volume *vol)
 	ntfs_index_entry_mark_dirty(ictx);
 set_done:
 	ntfs_index_ctx_put(ictx);
-	mutex_unlock(&vol->quota_q_ino->i_mutex);
+	inode_unlock(vol->quota_q_ino);
 	/*
 	 * We set the flag so we do not try to mark the quotas out of date
 	 * again on remount.
@@ -110,7 +110,7 @@ done:
 err_out:
 	if (ictx)
 		ntfs_index_ctx_put(ictx);
-	mutex_unlock(&vol->quota_q_ino->i_mutex);
+	inode_unlock(vol->quota_q_ino);
 	return false;
 }
 
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index d1a853585b53..ecb49870a680 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -823,14 +823,14 @@ static bool parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b)
 	ntfs_debug("vol->mft_record_size_bits = %i (0x%x)",
 			vol->mft_record_size_bits, vol->mft_record_size_bits);
 	/*
-	 * We cannot support mft record sizes above the PAGE_CACHE_SIZE since
+	 * We cannot support mft record sizes above the PAGE_SIZE since
 	 * we store $MFT/$DATA, the table of mft records in the page cache.
 	 */
-	if (vol->mft_record_size > PAGE_CACHE_SIZE) {
+	if (vol->mft_record_size > PAGE_SIZE) {
 		ntfs_error(vol->sb, "Mft record size (%i) exceeds the "
-				"PAGE_CACHE_SIZE on your system (%lu).  "
+				"PAGE_SIZE on your system (%lu).  "
 				"This is not supported.  Sorry.",
-				vol->mft_record_size, PAGE_CACHE_SIZE);
+				vol->mft_record_size, PAGE_SIZE);
 		return false;
 	}
 	/* We cannot support mft record sizes below the sector size. */
@@ -1096,7 +1096,7 @@ static bool check_mft_mirror(ntfs_volume *vol)
 
 	ntfs_debug("Entering.");
 	/* Compare contents of $MFT and $MFTMirr. */
-	mrecs_per_page = PAGE_CACHE_SIZE / vol->mft_record_size;
+	mrecs_per_page = PAGE_SIZE / vol->mft_record_size;
 	BUG_ON(!mrecs_per_page);
 	BUG_ON(!vol->mftmirr_size);
 	mft_page = mirr_page = NULL;
@@ -1284,10 +1284,10 @@ static int check_windows_hibernation_status(ntfs_volume *vol)
 	 * Find the inode number for the hibernation file by looking up the
 	 * filename hiberfil.sys in the root directory.
 	 */
-	mutex_lock(&vol->root_ino->i_mutex);
+	inode_lock(vol->root_ino);
 	mref = ntfs_lookup_inode_by_name(NTFS_I(vol->root_ino), hiberfil, 12,
 			&name);
-	mutex_unlock(&vol->root_ino->i_mutex);
+	inode_unlock(vol->root_ino);
 	if (IS_ERR_MREF(mref)) {
 		ret = MREF_ERR(mref);
 		/* If the file does not exist, Windows is not hibernated. */
@@ -1377,10 +1377,10 @@ static bool load_and_init_quota(ntfs_volume *vol)
 	 * Find the inode number for the quota file by looking up the filename
 	 * $Quota in the extended system files directory $Extend.
 	 */
-	mutex_lock(&vol->extend_ino->i_mutex);
+	inode_lock(vol->extend_ino);
 	mref = ntfs_lookup_inode_by_name(NTFS_I(vol->extend_ino), Quota, 6,
 			&name);
-	mutex_unlock(&vol->extend_ino->i_mutex);
+	inode_unlock(vol->extend_ino);
 	if (IS_ERR_MREF(mref)) {
 		/*
 		 * If the file does not exist, quotas are disabled and have
@@ -1460,10 +1460,10 @@ static bool load_and_init_usnjrnl(ntfs_volume *vol)
 	 * Find the inode number for the transaction log file by looking up the
 	 * filename $UsnJrnl in the extended system files directory $Extend.
 	 */
-	mutex_lock(&vol->extend_ino->i_mutex);
+	inode_lock(vol->extend_ino);
 	mref = ntfs_lookup_inode_by_name(NTFS_I(vol->extend_ino), UsnJrnl, 8,
 			&name);
-	mutex_unlock(&vol->extend_ino->i_mutex);
+	inode_unlock(vol->extend_ino);
 	if (IS_ERR_MREF(mref)) {
 		/*
 		 * If the file does not exist, transaction logging is disabled,
@@ -1615,20 +1615,20 @@ static bool load_and_init_attrdef(ntfs_volume *vol)
 	if (!vol->attrdef)
 		goto iput_failed;
 	index = 0;
-	max_index = i_size >> PAGE_CACHE_SHIFT;
-	size = PAGE_CACHE_SIZE;
+	max_index = i_size >> PAGE_SHIFT;
+	size = PAGE_SIZE;
 	while (index < max_index) {
 		/* Read the attrdef table and copy it into the linear buffer. */
 read_partial_attrdef_page:
 		page = ntfs_map_page(ino->i_mapping, index);
 		if (IS_ERR(page))
 			goto free_iput_failed;
-		memcpy((u8*)vol->attrdef + (index++ << PAGE_CACHE_SHIFT),
+		memcpy((u8*)vol->attrdef + (index++ << PAGE_SHIFT),
 				page_address(page), size);
 		ntfs_unmap_page(page);
 	};
-	if (size == PAGE_CACHE_SIZE) {
-		size = i_size & ~PAGE_CACHE_MASK;
+	if (size == PAGE_SIZE) {
+		size = i_size & ~PAGE_MASK;
 		if (size)
 			goto read_partial_attrdef_page;
 	}
@@ -1684,20 +1684,20 @@ static bool load_and_init_upcase(ntfs_volume *vol)
 	if (!vol->upcase)
 		goto iput_upcase_failed;
 	index = 0;
-	max_index = i_size >> PAGE_CACHE_SHIFT;
-	size = PAGE_CACHE_SIZE;
+	max_index = i_size >> PAGE_SHIFT;
+	size = PAGE_SIZE;
 	while (index < max_index) {
 		/* Read the upcase table and copy it into the linear buffer. */
 read_partial_upcase_page:
 		page = ntfs_map_page(ino->i_mapping, index);
 		if (IS_ERR(page))
 			goto iput_upcase_failed;
-		memcpy((char*)vol->upcase + (index++ << PAGE_CACHE_SHIFT),
+		memcpy((char*)vol->upcase + (index++ << PAGE_SHIFT),
 				page_address(page), size);
 		ntfs_unmap_page(page);
 	};
-	if (size == PAGE_CACHE_SIZE) {
-		size = i_size & ~PAGE_CACHE_MASK;
+	if (size == PAGE_SIZE) {
+		size = i_size & ~PAGE_MASK;
 		if (size)
 			goto read_partial_upcase_page;
 	}
@@ -2471,14 +2471,14 @@ static s64 get_nr_free_clusters(ntfs_volume *vol)
 	down_read(&vol->lcnbmp_lock);
 	/*
 	 * Convert the number of bits into bytes rounded up, then convert into
-	 * multiples of PAGE_CACHE_SIZE, rounding up so that if we have one
+	 * multiples of PAGE_SIZE, rounding up so that if we have one
 	 * full and one partial page max_index = 2.
 	 */
-	max_index = (((vol->nr_clusters + 7) >> 3) + PAGE_CACHE_SIZE - 1) >>
-			PAGE_CACHE_SHIFT;
-	/* Use multiples of 4 bytes, thus max_size is PAGE_CACHE_SIZE / 4. */
+	max_index = (((vol->nr_clusters + 7) >> 3) + PAGE_SIZE - 1) >>
+			PAGE_SHIFT;
+	/* Use multiples of 4 bytes, thus max_size is PAGE_SIZE / 4. */
 	ntfs_debug("Reading $Bitmap, max_index = 0x%lx, max_size = 0x%lx.",
-			max_index, PAGE_CACHE_SIZE / 4);
+			max_index, PAGE_SIZE / 4);
 	for (index = 0; index < max_index; index++) {
 		unsigned long *kaddr;
 
@@ -2491,7 +2491,7 @@ static s64 get_nr_free_clusters(ntfs_volume *vol)
 		if (IS_ERR(page)) {
 			ntfs_debug("read_mapping_page() error. Skipping "
 					"page (index 0x%lx).", index);
-			nr_free -= PAGE_CACHE_SIZE * 8;
+			nr_free -= PAGE_SIZE * 8;
 			continue;
 		}
 		kaddr = kmap_atomic(page);
@@ -2503,9 +2503,9 @@ static s64 get_nr_free_clusters(ntfs_volume *vol)
 		 * ntfs_readpage().
 		 */
 		nr_free -= bitmap_weight(kaddr,
-					PAGE_CACHE_SIZE * BITS_PER_BYTE);
+					PAGE_SIZE * BITS_PER_BYTE);
 		kunmap_atomic(kaddr);
-		page_cache_release(page);
+		put_page(page);
 	}
 	ntfs_debug("Finished reading $Bitmap, last index = 0x%lx.", index - 1);
 	/*
@@ -2547,9 +2547,9 @@ static unsigned long __get_nr_free_mft_records(ntfs_volume *vol,
 	pgoff_t index;
 
 	ntfs_debug("Entering.");
-	/* Use multiples of 4 bytes, thus max_size is PAGE_CACHE_SIZE / 4. */
+	/* Use multiples of 4 bytes, thus max_size is PAGE_SIZE / 4. */
 	ntfs_debug("Reading $MFT/$BITMAP, max_index = 0x%lx, max_size = "
-			"0x%lx.", max_index, PAGE_CACHE_SIZE / 4);
+			"0x%lx.", max_index, PAGE_SIZE / 4);
 	for (index = 0; index < max_index; index++) {
 		unsigned long *kaddr;
 
@@ -2562,7 +2562,7 @@ static unsigned long __get_nr_free_mft_records(ntfs_volume *vol,
 		if (IS_ERR(page)) {
 			ntfs_debug("read_mapping_page() error. Skipping "
 					"page (index 0x%lx).", index);
-			nr_free -= PAGE_CACHE_SIZE * 8;
+			nr_free -= PAGE_SIZE * 8;
 			continue;
 		}
 		kaddr = kmap_atomic(page);
@@ -2574,9 +2574,9 @@ static unsigned long __get_nr_free_mft_records(ntfs_volume *vol,
 		 * ntfs_readpage().
 		 */
 		nr_free -= bitmap_weight(kaddr,
-					PAGE_CACHE_SIZE * BITS_PER_BYTE);
+					PAGE_SIZE * BITS_PER_BYTE);
 		kunmap_atomic(kaddr);
-		page_cache_release(page);
+		put_page(page);
 	}
 	ntfs_debug("Finished reading $MFT/$BITMAP, last index = 0x%lx.",
 			index - 1);
@@ -2618,17 +2618,17 @@ static int ntfs_statfs(struct dentry *dentry, struct kstatfs *sfs)
 	/* Type of filesystem. */
 	sfs->f_type   = NTFS_SB_MAGIC;
 	/* Optimal transfer block size. */
-	sfs->f_bsize  = PAGE_CACHE_SIZE;
+	sfs->f_bsize  = PAGE_SIZE;
 	/*
 	 * Total data blocks in filesystem in units of f_bsize and since
 	 * inodes are also stored in data blocs ($MFT is a file) this is just
 	 * the total clusters.
 	 */
 	sfs->f_blocks = vol->nr_clusters << vol->cluster_size_bits >>
-				PAGE_CACHE_SHIFT;
+				PAGE_SHIFT;
 	/* Free data blocks in filesystem in units of f_bsize. */
 	size	      = get_nr_free_clusters(vol) << vol->cluster_size_bits >>
-				PAGE_CACHE_SHIFT;
+				PAGE_SHIFT;
 	if (size < 0LL)
 		size = 0LL;
 	/* Free blocks avail to non-superuser, same as above on NTFS. */
@@ -2639,11 +2639,11 @@ static int ntfs_statfs(struct dentry *dentry, struct kstatfs *sfs)
 	size = i_size_read(vol->mft_ino) >> vol->mft_record_size_bits;
 	/*
 	 * Convert the maximum number of set bits into bytes rounded up, then
-	 * convert into multiples of PAGE_CACHE_SIZE, rounding up so that if we
+	 * convert into multiples of PAGE_SIZE, rounding up so that if we
 	 * have one full and one partial page max_index = 2.
 	 */
 	max_index = ((((mft_ni->initialized_size >> vol->mft_record_size_bits)
-			+ 7) >> 3) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+			+ 7) >> 3) + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	read_unlock_irqrestore(&mft_ni->size_lock, flags);
 	/* Number of inodes in filesystem (at this point in time). */
 	sfs->f_files = size;
@@ -2765,15 +2765,15 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent)
 	if (!parse_options(vol, (char*)opt))
 		goto err_out_now;
 
-	/* We support sector sizes up to the PAGE_CACHE_SIZE. */
-	if (bdev_logical_block_size(sb->s_bdev) > PAGE_CACHE_SIZE) {
+	/* We support sector sizes up to the PAGE_SIZE. */
+	if (bdev_logical_block_size(sb->s_bdev) > PAGE_SIZE) {
 		if (!silent)
 			ntfs_error(sb, "Device has unsupported sector size "
 					"(%i).  The maximum supported sector "
 					"size on this architecture is %lu "
 					"bytes.",
 					bdev_logical_block_size(sb->s_bdev),
-					PAGE_CACHE_SIZE);
+					PAGE_SIZE);
 		goto err_out_now;
 	}
 	/*
@@ -3139,8 +3139,8 @@ static int __init init_ntfs_fs(void)
 
 	ntfs_big_inode_cache = kmem_cache_create(ntfs_big_inode_cache_name,
 			sizeof(big_ntfs_inode), 0,
-			SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD,
-			ntfs_big_inode_init_once);
+			SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|
+			SLAB_ACCOUNT, ntfs_big_inode_init_once);
 	if (!ntfs_big_inode_cache) {
 		pr_crit("Failed to create %s!\n", ntfs_big_inode_cache_name);
 		goto big_inode_err_out;
diff --git a/fs/ocfs2/Makefile b/fs/ocfs2/Makefile
index ce210d4951a1..e27e6527912b 100644
--- a/fs/ocfs2/Makefile
+++ b/fs/ocfs2/Makefile
@@ -41,7 +41,8 @@ ocfs2-objs := \
 	quota_local.o		\
 	quota_global.o		\
 	xattr.o			\
-	acl.o
+	acl.o	\
+	filecheck.o
 
 ocfs2_stackglue-objs := stackglue.o
 ocfs2_stack_o2cb-objs := stack_o2cb.o
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 86181d6526dc..e361d1a0ca09 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -164,7 +164,7 @@ static int ocfs2_dinode_insert_check(struct ocfs2_extent_tree *et,
 				     struct ocfs2_extent_rec *rec);
 static int ocfs2_dinode_sanity_check(struct ocfs2_extent_tree *et);
 static void ocfs2_dinode_fill_root_el(struct ocfs2_extent_tree *et);
-static struct ocfs2_extent_tree_operations ocfs2_dinode_et_ops = {
+static const struct ocfs2_extent_tree_operations ocfs2_dinode_et_ops = {
 	.eo_set_last_eb_blk	= ocfs2_dinode_set_last_eb_blk,
 	.eo_get_last_eb_blk	= ocfs2_dinode_get_last_eb_blk,
 	.eo_update_clusters	= ocfs2_dinode_update_clusters,
@@ -286,7 +286,7 @@ static void ocfs2_xattr_value_update_clusters(struct ocfs2_extent_tree *et,
 	le32_add_cpu(&vb->vb_xv->xr_clusters, clusters);
 }
 
-static struct ocfs2_extent_tree_operations ocfs2_xattr_value_et_ops = {
+static const struct ocfs2_extent_tree_operations ocfs2_xattr_value_et_ops = {
 	.eo_set_last_eb_blk	= ocfs2_xattr_value_set_last_eb_blk,
 	.eo_get_last_eb_blk	= ocfs2_xattr_value_get_last_eb_blk,
 	.eo_update_clusters	= ocfs2_xattr_value_update_clusters,
@@ -332,7 +332,7 @@ static void ocfs2_xattr_tree_update_clusters(struct ocfs2_extent_tree *et,
 	le32_add_cpu(&xb->xb_attrs.xb_root.xt_clusters, clusters);
 }
 
-static struct ocfs2_extent_tree_operations ocfs2_xattr_tree_et_ops = {
+static const struct ocfs2_extent_tree_operations ocfs2_xattr_tree_et_ops = {
 	.eo_set_last_eb_blk	= ocfs2_xattr_tree_set_last_eb_blk,
 	.eo_get_last_eb_blk	= ocfs2_xattr_tree_get_last_eb_blk,
 	.eo_update_clusters	= ocfs2_xattr_tree_update_clusters,
@@ -379,7 +379,7 @@ static void ocfs2_dx_root_fill_root_el(struct ocfs2_extent_tree *et)
 	et->et_root_el = &dx_root->dr_list;
 }
 
-static struct ocfs2_extent_tree_operations ocfs2_dx_root_et_ops = {
+static const struct ocfs2_extent_tree_operations ocfs2_dx_root_et_ops = {
 	.eo_set_last_eb_blk	= ocfs2_dx_root_set_last_eb_blk,
 	.eo_get_last_eb_blk	= ocfs2_dx_root_get_last_eb_blk,
 	.eo_update_clusters	= ocfs2_dx_root_update_clusters,
@@ -425,7 +425,7 @@ ocfs2_refcount_tree_extent_contig(struct ocfs2_extent_tree *et,
 	return CONTIG_NONE;
 }
 
-static struct ocfs2_extent_tree_operations ocfs2_refcount_tree_et_ops = {
+static const struct ocfs2_extent_tree_operations ocfs2_refcount_tree_et_ops = {
 	.eo_set_last_eb_blk	= ocfs2_refcount_tree_set_last_eb_blk,
 	.eo_get_last_eb_blk	= ocfs2_refcount_tree_get_last_eb_blk,
 	.eo_update_clusters	= ocfs2_refcount_tree_update_clusters,
@@ -438,7 +438,7 @@ static void __ocfs2_init_extent_tree(struct ocfs2_extent_tree *et,
 				     struct buffer_head *bh,
 				     ocfs2_journal_access_func access,
 				     void *obj,
-				     struct ocfs2_extent_tree_operations *ops)
+				     const struct ocfs2_extent_tree_operations *ops)
 {
 	et->et_ops = ops;
 	et->et_root_bh = bh;
@@ -2516,21 +2516,6 @@ static int ocfs2_update_edge_lengths(handle_t *handle,
 	struct ocfs2_extent_block *eb;
 	u32 range;
 
-	/*
-	 * In normal tree rotation process, we will never touch the
-	 * tree branch above subtree_index and ocfs2_extend_rotate_transaction
-	 * doesn't reserve the credits for them either.
-	 *
-	 * But we do have a special case here which will update the rightmost
-	 * records for all the bh in the path.
-	 * So we have to allocate extra credits and access them.
-	 */
-	ret = ocfs2_extend_trans(handle, subtree_index);
-	if (ret) {
-		mlog_errno(ret);
-		goto out;
-	}
-
 	ret = ocfs2_journal_access_path(et->et_ci, handle, path);
 	if (ret) {
 		mlog_errno(ret);
@@ -2956,7 +2941,7 @@ static int __ocfs2_rotate_tree_left(handle_t *handle,
 		     right_path->p_node[subtree_root].bh->b_blocknr,
 		     right_path->p_tree_depth);
 
-		ret = ocfs2_extend_rotate_transaction(handle, subtree_root,
+		ret = ocfs2_extend_rotate_transaction(handle, 0,
 						      orig_credits, left_path);
 		if (ret) {
 			mlog_errno(ret);
@@ -3029,21 +3014,9 @@ static int ocfs2_remove_rightmost_path(handle_t *handle,
 	struct ocfs2_extent_block *eb;
 	struct ocfs2_extent_list *el;
 
-
 	ret = ocfs2_et_sanity_check(et);
 	if (ret)
 		goto out;
-	/*
-	 * There's two ways we handle this depending on
-	 * whether path is the only existing one.
-	 */
-	ret = ocfs2_extend_rotate_transaction(handle, 0,
-					      handle->h_buffer_credits,
-					      path);
-	if (ret) {
-		mlog_errno(ret);
-		goto out;
-	}
 
 	ret = ocfs2_journal_access_path(et->et_ci, handle, path);
 	if (ret) {
@@ -3641,6 +3614,14 @@ static int ocfs2_merge_rec_left(struct ocfs2_path *right_path,
 		 */
 		if (le16_to_cpu(right_rec->e_leaf_clusters) == 0 &&
 		    le16_to_cpu(el->l_next_free_rec) == 1) {
+			/* extend credit for ocfs2_remove_rightmost_path */
+			ret = ocfs2_extend_rotate_transaction(handle, 0,
+					handle->h_buffer_credits,
+					right_path);
+			if (ret) {
+				mlog_errno(ret);
+				goto out;
+			}
 
 			ret = ocfs2_remove_rightmost_path(handle, et,
 							  right_path,
@@ -3679,6 +3660,14 @@ static int ocfs2_try_to_merge_extent(handle_t *handle,
 	BUG_ON(ctxt->c_contig_type == CONTIG_NONE);
 
 	if (ctxt->c_split_covers_rec && ctxt->c_has_empty_extent) {
+		/* extend credit for ocfs2_remove_rightmost_path */
+		ret = ocfs2_extend_rotate_transaction(handle, 0,
+				handle->h_buffer_credits,
+				path);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
 		/*
 		 * The merge code will need to create an empty
 		 * extent to take the place of the newly
@@ -3727,6 +3716,15 @@ static int ocfs2_try_to_merge_extent(handle_t *handle,
 		 */
 		BUG_ON(!ocfs2_is_empty_extent(&el->l_recs[0]));
 
+		/* extend credit for ocfs2_remove_rightmost_path */
+		ret = ocfs2_extend_rotate_transaction(handle, 0,
+					handle->h_buffer_credits,
+					path);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
 		/* The merge left us with an empty extent, remove it. */
 		ret = ocfs2_rotate_tree_left(handle, et, path, dealloc);
 		if (ret) {
@@ -3748,6 +3746,15 @@ static int ocfs2_try_to_merge_extent(handle_t *handle,
 			goto out;
 		}
 
+		/* extend credit for ocfs2_remove_rightmost_path */
+		ret = ocfs2_extend_rotate_transaction(handle, 0,
+				handle->h_buffer_credits,
+				path);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
 		ret = ocfs2_rotate_tree_left(handle, et, path, dealloc);
 		/*
 		 * Error from this last rotate is not critical, so
@@ -3783,6 +3790,16 @@ static int ocfs2_try_to_merge_extent(handle_t *handle,
 		}
 
 		if (ctxt->c_split_covers_rec) {
+			/* extend credit for ocfs2_remove_rightmost_path */
+			ret = ocfs2_extend_rotate_transaction(handle, 0,
+					handle->h_buffer_credits,
+					path);
+			if (ret) {
+				mlog_errno(ret);
+				ret = 0;
+				goto out;
+			}
+
 			/*
 			 * The merge may have left an empty extent in
 			 * our leaf. Try to rotate it away.
@@ -5342,6 +5359,15 @@ static int ocfs2_truncate_rec(handle_t *handle,
 	struct ocfs2_extent_block *eb;
 
 	if (ocfs2_is_empty_extent(&el->l_recs[0]) && index > 0) {
+		/* extend credit for ocfs2_remove_rightmost_path */
+		ret = ocfs2_extend_rotate_transaction(handle, 0,
+				handle->h_buffer_credits,
+				path);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
 		ret = ocfs2_rotate_tree_left(handle, et, path, dealloc);
 		if (ret) {
 			mlog_errno(ret);
@@ -5719,7 +5745,7 @@ int ocfs2_remove_btree_range(struct inode *inode,
 		goto bail;
 	}
 
-	mutex_lock(&tl_inode->i_mutex);
+	inode_lock(tl_inode);
 
 	if (ocfs2_truncate_log_needs_flush(osb)) {
 		ret = __ocfs2_flush_truncate_log(osb);
@@ -5776,7 +5802,7 @@ int ocfs2_remove_btree_range(struct inode *inode,
 out_commit:
 	ocfs2_commit_trans(osb, handle);
 out:
-	mutex_unlock(&tl_inode->i_mutex);
+	inode_unlock(tl_inode);
 bail:
 	if (meta_ac)
 		ocfs2_free_alloc_context(meta_ac);
@@ -5832,7 +5858,7 @@ int ocfs2_truncate_log_append(struct ocfs2_super *osb,
 	struct ocfs2_dinode *di;
 	struct ocfs2_truncate_log *tl;
 
-	BUG_ON(mutex_trylock(&tl_inode->i_mutex));
+	BUG_ON(inode_trylock(tl_inode));
 
 	start_cluster = ocfs2_blocks_to_clusters(osb->sb, start_blk);
 
@@ -5928,16 +5954,6 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
 
 		ocfs2_journal_dirty(handle, tl_bh);
 
-		/* TODO: Perhaps we can calculate the bulk of the
-		 * credits up front rather than extending like
-		 * this. */
-		status = ocfs2_extend_trans(handle,
-					    OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
-		if (status < 0) {
-			mlog_errno(status);
-			goto bail;
-		}
-
 		rec = tl->tl_recs[i];
 		start_blk = ocfs2_clusters_to_blocks(data_alloc_inode->i_sb,
 						    le32_to_cpu(rec.t_start));
@@ -5958,6 +5974,13 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
 				goto bail;
 			}
 		}
+
+		status = ocfs2_extend_trans(handle,
+				OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
+		if (status < 0) {
+			mlog_errno(status);
+			goto bail;
+		}
 		i--;
 	}
 
@@ -5980,7 +6003,7 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb)
 	struct ocfs2_dinode *di;
 	struct ocfs2_truncate_log *tl;
 
-	BUG_ON(mutex_trylock(&tl_inode->i_mutex));
+	BUG_ON(inode_trylock(tl_inode));
 
 	di = (struct ocfs2_dinode *) tl_bh->b_data;
 
@@ -6008,7 +6031,7 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb)
 		goto out;
 	}
 
-	mutex_lock(&data_alloc_inode->i_mutex);
+	inode_lock(data_alloc_inode);
 
 	status = ocfs2_inode_lock(data_alloc_inode, &data_alloc_bh, 1);
 	if (status < 0) {
@@ -6016,7 +6039,7 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb)
 		goto out_mutex;
 	}
 
-	handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_UPDATE);
+	handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
 	if (IS_ERR(handle)) {
 		status = PTR_ERR(handle);
 		mlog_errno(status);
@@ -6035,7 +6058,7 @@ out_unlock:
 	ocfs2_inode_unlock(data_alloc_inode, 1);
 
 out_mutex:
-	mutex_unlock(&data_alloc_inode->i_mutex);
+	inode_unlock(data_alloc_inode);
 	iput(data_alloc_inode);
 
 out:
@@ -6047,9 +6070,9 @@ int ocfs2_flush_truncate_log(struct ocfs2_super *osb)
 	int status;
 	struct inode *tl_inode = osb->osb_tl_inode;
 
-	mutex_lock(&tl_inode->i_mutex);
+	inode_lock(tl_inode);
 	status = __ocfs2_flush_truncate_log(osb);
-	mutex_unlock(&tl_inode->i_mutex);
+	inode_unlock(tl_inode);
 
 	return status;
 }
@@ -6079,7 +6102,7 @@ void ocfs2_schedule_truncate_log_flush(struct ocfs2_super *osb,
 		if (cancel)
 			cancel_delayed_work(&osb->osb_truncate_log_wq);
 
-		queue_delayed_work(ocfs2_wq, &osb->osb_truncate_log_wq,
+		queue_delayed_work(osb->ocfs2_wq, &osb->osb_truncate_log_wq,
 				   OCFS2_TRUNCATE_LOG_FLUSH_INTERVAL);
 	}
 }
@@ -6174,8 +6197,7 @@ int ocfs2_begin_truncate_log_recovery(struct ocfs2_super *osb,
 	}
 
 bail:
-	if (tl_inode)
-		iput(tl_inode);
+	iput(tl_inode);
 	brelse(tl_bh);
 
 	if (status < 0) {
@@ -6209,7 +6231,7 @@ int ocfs2_complete_truncate_log_recovery(struct ocfs2_super *osb,
 		(unsigned long long)le64_to_cpu(tl_copy->i_blkno),
 		num_recs);
 
-	mutex_lock(&tl_inode->i_mutex);
+	inode_lock(tl_inode);
 	for(i = 0; i < num_recs; i++) {
 		if (ocfs2_truncate_log_needs_flush(osb)) {
 			status = __ocfs2_flush_truncate_log(osb);
@@ -6240,7 +6262,7 @@ int ocfs2_complete_truncate_log_recovery(struct ocfs2_super *osb,
 	}
 
 bail_up:
-	mutex_unlock(&tl_inode->i_mutex);
+	inode_unlock(tl_inode);
 
 	return status;
 }
@@ -6254,7 +6276,7 @@ void ocfs2_truncate_log_shutdown(struct ocfs2_super *osb)
 
 	if (tl_inode) {
 		cancel_delayed_work(&osb->osb_truncate_log_wq);
-		flush_workqueue(ocfs2_wq);
+		flush_workqueue(osb->ocfs2_wq);
 
 		status = ocfs2_flush_truncate_log(osb);
 		if (status < 0)
@@ -6347,7 +6369,7 @@ static int ocfs2_free_cached_blocks(struct ocfs2_super *osb,
 		goto out;
 	}
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	ret = ocfs2_inode_lock(inode, &di_bh, 1);
 	if (ret) {
@@ -6396,7 +6418,7 @@ out_unlock:
 	ocfs2_inode_unlock(inode, 1);
 	brelse(di_bh);
 out_mutex:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	iput(inode);
 out:
 	while(head) {
@@ -6440,7 +6462,7 @@ static int ocfs2_free_cached_clusters(struct ocfs2_super *osb,
 	handle_t *handle;
 	int ret = 0;
 
-	mutex_lock(&tl_inode->i_mutex);
+	inode_lock(tl_inode);
 
 	while (head) {
 		if (ocfs2_truncate_log_needs_flush(osb)) {
@@ -6472,7 +6494,7 @@ static int ocfs2_free_cached_clusters(struct ocfs2_super *osb,
 		}
 	}
 
-	mutex_unlock(&tl_inode->i_mutex);
+	inode_unlock(tl_inode);
 
 	while (head) {
 		/* Premature exit may have left some dangling items. */
@@ -6649,7 +6671,7 @@ static void ocfs2_zero_cluster_pages(struct inode *inode, loff_t start,
 {
 	int i;
 	struct page *page;
-	unsigned int from, to = PAGE_CACHE_SIZE;
+	unsigned int from, to = PAGE_SIZE;
 	struct super_block *sb = inode->i_sb;
 
 	BUG_ON(!ocfs2_sparse_alloc(OCFS2_SB(sb)));
@@ -6657,21 +6679,21 @@ static void ocfs2_zero_cluster_pages(struct inode *inode, loff_t start,
 	if (numpages == 0)
 		goto out;
 
-	to = PAGE_CACHE_SIZE;
+	to = PAGE_SIZE;
 	for(i = 0; i < numpages; i++) {
 		page = pages[i];
 
-		from = start & (PAGE_CACHE_SIZE - 1);
-		if ((end >> PAGE_CACHE_SHIFT) == page->index)
-			to = end & (PAGE_CACHE_SIZE - 1);
+		from = start & (PAGE_SIZE - 1);
+		if ((end >> PAGE_SHIFT) == page->index)
+			to = end & (PAGE_SIZE - 1);
 
-		BUG_ON(from > PAGE_CACHE_SIZE);
-		BUG_ON(to > PAGE_CACHE_SIZE);
+		BUG_ON(from > PAGE_SIZE);
+		BUG_ON(to > PAGE_SIZE);
 
 		ocfs2_map_and_dirty_page(inode, handle, from, to, page, 1,
 					 &phys);
 
-		start = (page->index + 1) << PAGE_CACHE_SHIFT;
+		start = (page->index + 1) << PAGE_SHIFT;
 	}
 out:
 	if (pages)
@@ -6690,7 +6712,7 @@ int ocfs2_grab_pages(struct inode *inode, loff_t start, loff_t end,
 
 	numpages = 0;
 	last_page_bytes = PAGE_ALIGN(end);
-	index = start >> PAGE_CACHE_SHIFT;
+	index = start >> PAGE_SHIFT;
 	do {
 		pages[numpages] = find_or_create_page(mapping, index, GFP_NOFS);
 		if (!pages[numpages]) {
@@ -6701,7 +6723,7 @@ int ocfs2_grab_pages(struct inode *inode, loff_t start, loff_t end,
 
 		numpages++;
 		index++;
-	} while (index < (last_page_bytes >> PAGE_CACHE_SHIFT));
+	} while (index < (last_page_bytes >> PAGE_SHIFT));
 
 out:
 	if (ret != 0) {
@@ -6928,8 +6950,8 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
 		 * to do that now.
 		 */
 		if (!ocfs2_sparse_alloc(osb) &&
-		    PAGE_CACHE_SIZE < osb->s_clustersize)
-			end = PAGE_CACHE_SIZE;
+		    PAGE_SIZE < osb->s_clustersize)
+			end = PAGE_SIZE;
 
 		ret = ocfs2_grab_eof_pages(inode, 0, end, pages, &num_pages);
 		if (ret) {
@@ -6949,8 +6971,8 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
 			goto out_unlock;
 		}
 
-		page_end = PAGE_CACHE_SIZE;
-		if (PAGE_CACHE_SIZE > osb->s_clustersize)
+		page_end = PAGE_SIZE;
+		if (PAGE_SIZE > osb->s_clustersize)
 			page_end = osb->s_clustersize;
 
 		for (i = 0; i < num_pages; i++)
@@ -7356,7 +7378,7 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range)
 		goto out;
 	}
 
-	mutex_lock(&main_bm_inode->i_mutex);
+	inode_lock(main_bm_inode);
 
 	ret = ocfs2_inode_lock(main_bm_inode, &main_bm_bh, 0);
 	if (ret < 0) {
@@ -7423,7 +7445,7 @@ out_unlock:
 	ocfs2_inode_unlock(main_bm_inode, 0);
 	brelse(main_bm_bh);
 out_mutex:
-	mutex_unlock(&main_bm_inode->i_mutex);
+	inode_unlock(main_bm_inode);
 	iput(main_bm_inode);
 out:
 	return ret;
diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h
index fb09b97db162..f3dc1b0dfffc 100644
--- a/fs/ocfs2/alloc.h
+++ b/fs/ocfs2/alloc.h
@@ -54,7 +54,7 @@
  */
 struct ocfs2_extent_tree_operations;
 struct ocfs2_extent_tree {
-	struct ocfs2_extent_tree_operations	*et_ops;
+	const struct ocfs2_extent_tree_operations *et_ops;
 	struct buffer_head			*et_root_bh;
 	struct ocfs2_extent_list		*et_root_el;
 	struct ocfs2_caching_info		*et_ci;
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 7f604727f487..ad1577348a92 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -234,7 +234,7 @@ int ocfs2_read_inline_data(struct inode *inode, struct page *page,
 
 	size = i_size_read(inode);
 
-	if (size > PAGE_CACHE_SIZE ||
+	if (size > PAGE_SIZE ||
 	    size > ocfs2_max_inline_data_with_xattr(inode->i_sb, di)) {
 		ocfs2_error(inode->i_sb,
 			    "Inode %llu has with inline data has bad size: %Lu\n",
@@ -247,7 +247,7 @@ int ocfs2_read_inline_data(struct inode *inode, struct page *page,
 	if (size)
 		memcpy(kaddr, di->id2.i_data.id_data, size);
 	/* Clear the remaining part of the page */
-	memset(kaddr + size, 0, PAGE_CACHE_SIZE - size);
+	memset(kaddr + size, 0, PAGE_SIZE - size);
 	flush_dcache_page(page);
 	kunmap_atomic(kaddr);
 
@@ -282,7 +282,7 @@ static int ocfs2_readpage(struct file *file, struct page *page)
 {
 	struct inode *inode = page->mapping->host;
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
-	loff_t start = (loff_t)page->index << PAGE_CACHE_SHIFT;
+	loff_t start = (loff_t)page->index << PAGE_SHIFT;
 	int ret, unlock = 1;
 
 	trace_ocfs2_readpage((unsigned long long)oi->ip_blkno,
@@ -385,7 +385,7 @@ static int ocfs2_readpages(struct file *filp, struct address_space *mapping,
 	 * drop out in that case as it's not worth handling here.
 	 */
 	last = list_entry(pages->prev, struct page, lru);
-	start = (loff_t)last->index << PAGE_CACHE_SHIFT;
+	start = (loff_t)last->index << PAGE_SHIFT;
 	if (start >= i_size_read(inode))
 		goto out_unlock;
 
@@ -499,153 +499,6 @@ bail:
 	return status;
 }
 
-/*
- * TODO: Make this into a generic get_blocks function.
- *
- * From do_direct_io in direct-io.c:
- *  "So what we do is to permit the ->get_blocks function to populate
- *   bh.b_size with the size of IO which is permitted at this offset and
- *   this i_blkbits."
- *
- * This function is called directly from get_more_blocks in direct-io.c.
- *
- * called like this: dio->get_blocks(dio->inode, fs_startblk,
- * 					fs_count, map_bh, dio->rw == WRITE);
- */
-static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
-				     struct buffer_head *bh_result, int create)
-{
-	int ret;
-	u32 cpos = 0;
-	int alloc_locked = 0;
-	u64 p_blkno, inode_blocks, contig_blocks;
-	unsigned int ext_flags;
-	unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits;
-	unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
-	unsigned long len = bh_result->b_size;
-	unsigned int clusters_to_alloc = 0, contig_clusters = 0;
-
-	cpos = ocfs2_blocks_to_clusters(inode->i_sb, iblock);
-
-	/* This function won't even be called if the request isn't all
-	 * nicely aligned and of the right size, so there's no need
-	 * for us to check any of that. */
-
-	inode_blocks = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
-
-	down_read(&OCFS2_I(inode)->ip_alloc_sem);
-
-	/* This figures out the size of the next contiguous block, and
-	 * our logical offset */
-	ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
-					  &contig_blocks, &ext_flags);
-	up_read(&OCFS2_I(inode)->ip_alloc_sem);
-
-	if (ret) {
-		mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
-		     (unsigned long long)iblock);
-		ret = -EIO;
-		goto bail;
-	}
-
-	/* We should already CoW the refcounted extent in case of create. */
-	BUG_ON(create && (ext_flags & OCFS2_EXT_REFCOUNTED));
-
-	/* allocate blocks if no p_blkno is found, and create == 1 */
-	if (!p_blkno && create) {
-		ret = ocfs2_inode_lock(inode, NULL, 1);
-		if (ret < 0) {
-			mlog_errno(ret);
-			goto bail;
-		}
-
-		alloc_locked = 1;
-
-		down_write(&OCFS2_I(inode)->ip_alloc_sem);
-
-		/* fill hole, allocate blocks can't be larger than the size
-		 * of the hole */
-		clusters_to_alloc = ocfs2_clusters_for_bytes(inode->i_sb, len);
-		contig_clusters = ocfs2_clusters_for_blocks(inode->i_sb,
-				contig_blocks);
-		if (clusters_to_alloc > contig_clusters)
-			clusters_to_alloc = contig_clusters;
-
-		/* allocate extent and insert them into the extent tree */
-		ret = ocfs2_extend_allocation(inode, cpos,
-				clusters_to_alloc, 0);
-		if (ret < 0) {
-			up_write(&OCFS2_I(inode)->ip_alloc_sem);
-			mlog_errno(ret);
-			goto bail;
-		}
-
-		ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
-				&contig_blocks, &ext_flags);
-		if (ret < 0) {
-			up_write(&OCFS2_I(inode)->ip_alloc_sem);
-			mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
-					(unsigned long long)iblock);
-			ret = -EIO;
-			goto bail;
-		}
-		set_buffer_new(bh_result);
-		up_write(&OCFS2_I(inode)->ip_alloc_sem);
-	}
-
-	/*
-	 * get_more_blocks() expects us to describe a hole by clearing
-	 * the mapped bit on bh_result().
-	 *
-	 * Consider an unwritten extent as a hole.
-	 */
-	if (p_blkno && !(ext_flags & OCFS2_EXT_UNWRITTEN))
-		map_bh(bh_result, inode->i_sb, p_blkno);
-	else
-		clear_buffer_mapped(bh_result);
-
-	/* make sure we don't map more than max_blocks blocks here as
-	   that's all the kernel will handle at this point. */
-	if (max_blocks < contig_blocks)
-		contig_blocks = max_blocks;
-	bh_result->b_size = contig_blocks << blocksize_bits;
-bail:
-	if (alloc_locked)
-		ocfs2_inode_unlock(inode, 1);
-	return ret;
-}
-
-/*
- * ocfs2_dio_end_io is called by the dio core when a dio is finished.  We're
- * particularly interested in the aio/dio case.  We use the rw_lock DLM lock
- * to protect io on one node from truncation on another.
- */
-static void ocfs2_dio_end_io(struct kiocb *iocb,
-			     loff_t offset,
-			     ssize_t bytes,
-			     void *private)
-{
-	struct inode *inode = file_inode(iocb->ki_filp);
-	int level;
-
-	/* this io's submitter should not have unlocked this before we could */
-	BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
-
-	if (ocfs2_iocb_is_unaligned_aio(iocb)) {
-		ocfs2_iocb_clear_unaligned_aio(iocb);
-
-		mutex_unlock(&OCFS2_I(inode)->ip_unaligned_aio);
-	}
-
-	/* Let rw unlock to be done later to protect append direct io write */
-	if (offset + bytes <= i_size_read(inode)) {
-		ocfs2_iocb_clear_rw_locked(iocb);
-
-		level = ocfs2_iocb_rw_locked_level(iocb);
-		ocfs2_rw_unlock(inode, level);
-	}
-}
-
 static int ocfs2_releasepage(struct page *page, gfp_t wait)
 {
 	if (!page_has_buffers(page))
@@ -653,373 +506,17 @@ static int ocfs2_releasepage(struct page *page, gfp_t wait)
 	return try_to_free_buffers(page);
 }
 
-static int ocfs2_is_overwrite(struct ocfs2_super *osb,
-		struct inode *inode, loff_t offset)
-{
-	int ret = 0;
-	u32 v_cpos = 0;
-	u32 p_cpos = 0;
-	unsigned int num_clusters = 0;
-	unsigned int ext_flags = 0;
-
-	v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset);
-	ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos,
-			&num_clusters, &ext_flags);
-	if (ret < 0) {
-		mlog_errno(ret);
-		return ret;
-	}
-
-	if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN))
-		return 1;
-
-	return 0;
-}
-
-static int ocfs2_direct_IO_zero_extend(struct ocfs2_super *osb,
-		struct inode *inode, loff_t offset,
-		u64 zero_len, int cluster_align)
-{
-	u32 p_cpos = 0;
-	u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, i_size_read(inode));
-	unsigned int num_clusters = 0;
-	unsigned int ext_flags = 0;
-	int ret = 0;
-
-	if (offset <= i_size_read(inode) || cluster_align)
-		return 0;
-
-	ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos, &num_clusters,
-			&ext_flags);
-	if (ret < 0) {
-		mlog_errno(ret);
-		return ret;
-	}
-
-	if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) {
-		u64 s = i_size_read(inode);
-		sector_t sector = ((u64)p_cpos << (osb->s_clustersize_bits - 9)) +
-			(do_div(s, osb->s_clustersize) >> 9);
-
-		ret = blkdev_issue_zeroout(osb->sb->s_bdev, sector,
-				zero_len >> 9, GFP_NOFS, false);
-		if (ret < 0)
-			mlog_errno(ret);
-	}
-
-	return ret;
-}
-
-static int ocfs2_direct_IO_extend_no_holes(struct ocfs2_super *osb,
-		struct inode *inode, loff_t offset)
-{
-	u64 zero_start, zero_len, total_zero_len;
-	u32 p_cpos = 0, clusters_to_add;
-	u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, i_size_read(inode));
-	unsigned int num_clusters = 0;
-	unsigned int ext_flags = 0;
-	u32 size_div, offset_div;
-	int ret = 0;
-
-	{
-		u64 o = offset;
-		u64 s = i_size_read(inode);
-
-		offset_div = do_div(o, osb->s_clustersize);
-		size_div = do_div(s, osb->s_clustersize);
-	}
-
-	if (offset <= i_size_read(inode))
-		return 0;
-
-	clusters_to_add = ocfs2_bytes_to_clusters(inode->i_sb, offset) -
-		ocfs2_bytes_to_clusters(inode->i_sb, i_size_read(inode));
-	total_zero_len = offset - i_size_read(inode);
-	if (clusters_to_add)
-		total_zero_len -= offset_div;
-
-	/* Allocate clusters to fill out holes, and this is only needed
-	 * when we add more than one clusters. Otherwise the cluster will
-	 * be allocated during direct IO */
-	if (clusters_to_add > 1) {
-		ret = ocfs2_extend_allocation(inode,
-				OCFS2_I(inode)->ip_clusters,
-				clusters_to_add - 1, 0);
-		if (ret) {
-			mlog_errno(ret);
-			goto out;
-		}
-	}
-
-	while (total_zero_len) {
-		ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos, &num_clusters,
-				&ext_flags);
-		if (ret < 0) {
-			mlog_errno(ret);
-			goto out;
-		}
-
-		zero_start = ocfs2_clusters_to_bytes(osb->sb, p_cpos) +
-			size_div;
-		zero_len = ocfs2_clusters_to_bytes(osb->sb, num_clusters) -
-			size_div;
-		zero_len = min(total_zero_len, zero_len);
-
-		if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) {
-			ret = blkdev_issue_zeroout(osb->sb->s_bdev,
-					zero_start >> 9, zero_len >> 9,
-					GFP_NOFS, false);
-			if (ret < 0) {
-				mlog_errno(ret);
-				goto out;
-			}
-		}
-
-		total_zero_len -= zero_len;
-		v_cpos += ocfs2_bytes_to_clusters(osb->sb, zero_len + size_div);
-
-		/* Only at first iteration can be cluster not aligned.
-		 * So set size_div to 0 for the rest */
-		size_div = 0;
-	}
-
-out:
-	return ret;
-}
-
-static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
-		struct iov_iter *iter,
-		loff_t offset)
-{
-	ssize_t ret = 0;
-	ssize_t written = 0;
-	bool orphaned = false;
-	int is_overwrite = 0;
-	struct file *file = iocb->ki_filp;
-	struct inode *inode = file_inode(file)->i_mapping->host;
-	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
-	struct buffer_head *di_bh = NULL;
-	size_t count = iter->count;
-	journal_t *journal = osb->journal->j_journal;
-	u64 zero_len_head, zero_len_tail;
-	int cluster_align_head, cluster_align_tail;
-	loff_t final_size = offset + count;
-	int append_write = offset >= i_size_read(inode) ? 1 : 0;
-	unsigned int num_clusters = 0;
-	unsigned int ext_flags = 0;
-
-	{
-		u64 o = offset;
-		u64 s = i_size_read(inode);
-
-		zero_len_head = do_div(o, 1 << osb->s_clustersize_bits);
-		cluster_align_head = !zero_len_head;
-
-		zero_len_tail = osb->s_clustersize -
-			do_div(s, osb->s_clustersize);
-		if ((offset - i_size_read(inode)) < zero_len_tail)
-			zero_len_tail = offset - i_size_read(inode);
-		cluster_align_tail = !zero_len_tail;
-	}
-
-	/*
-	 * when final_size > inode->i_size, inode->i_size will be
-	 * updated after direct write, so add the inode to orphan
-	 * dir first.
-	 */
-	if (final_size > i_size_read(inode)) {
-		ret = ocfs2_add_inode_to_orphan(osb, inode);
-		if (ret < 0) {
-			mlog_errno(ret);
-			goto out;
-		}
-		orphaned = true;
-	}
-
-	if (append_write) {
-		ret = ocfs2_inode_lock(inode, NULL, 1);
-		if (ret < 0) {
-			mlog_errno(ret);
-			goto clean_orphan;
-		}
-
-		/* zeroing out the previously allocated cluster tail
-		 * that but not zeroed */
-		if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) {
-			down_read(&OCFS2_I(inode)->ip_alloc_sem);
-			ret = ocfs2_direct_IO_zero_extend(osb, inode, offset,
-					zero_len_tail, cluster_align_tail);
-			up_read(&OCFS2_I(inode)->ip_alloc_sem);
-		} else {
-			down_write(&OCFS2_I(inode)->ip_alloc_sem);
-			ret = ocfs2_direct_IO_extend_no_holes(osb, inode,
-					offset);
-			up_write(&OCFS2_I(inode)->ip_alloc_sem);
-		}
-		if (ret < 0) {
-			mlog_errno(ret);
-			ocfs2_inode_unlock(inode, 1);
-			goto clean_orphan;
-		}
-
-		is_overwrite = ocfs2_is_overwrite(osb, inode, offset);
-		if (is_overwrite < 0) {
-			mlog_errno(is_overwrite);
-			ret = is_overwrite;
-			ocfs2_inode_unlock(inode, 1);
-			goto clean_orphan;
-		}
-
-		ocfs2_inode_unlock(inode, 1);
-	}
-
-	written = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
-				       offset, ocfs2_direct_IO_get_blocks,
-				       ocfs2_dio_end_io, NULL, 0);
-	/* overwrite aio may return -EIOCBQUEUED, and it is not an error */
-	if ((written < 0) && (written != -EIOCBQUEUED)) {
-		loff_t i_size = i_size_read(inode);
-
-		if (offset + count > i_size) {
-			ret = ocfs2_inode_lock(inode, &di_bh, 1);
-			if (ret < 0) {
-				mlog_errno(ret);
-				goto clean_orphan;
-			}
-
-			if (i_size == i_size_read(inode)) {
-				ret = ocfs2_truncate_file(inode, di_bh,
-						i_size);
-				if (ret < 0) {
-					if (ret != -ENOSPC)
-						mlog_errno(ret);
-
-					ocfs2_inode_unlock(inode, 1);
-					brelse(di_bh);
-					di_bh = NULL;
-					goto clean_orphan;
-				}
-			}
-
-			ocfs2_inode_unlock(inode, 1);
-			brelse(di_bh);
-			di_bh = NULL;
-
-			ret = jbd2_journal_force_commit(journal);
-			if (ret < 0)
-				mlog_errno(ret);
-		}
-	} else if (written > 0 && append_write && !is_overwrite &&
-			!cluster_align_head) {
-		/* zeroing out the allocated cluster head */
-		u32 p_cpos = 0;
-		u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset);
-
-		ret = ocfs2_inode_lock(inode, NULL, 0);
-		if (ret < 0) {
-			mlog_errno(ret);
-			goto clean_orphan;
-		}
-
-		ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos,
-				&num_clusters, &ext_flags);
-		if (ret < 0) {
-			mlog_errno(ret);
-			ocfs2_inode_unlock(inode, 0);
-			goto clean_orphan;
-		}
-
-		BUG_ON(!p_cpos || (ext_flags & OCFS2_EXT_UNWRITTEN));
-
-		ret = blkdev_issue_zeroout(osb->sb->s_bdev,
-				(u64)p_cpos << (osb->s_clustersize_bits - 9),
-				zero_len_head >> 9, GFP_NOFS, false);
-		if (ret < 0)
-			mlog_errno(ret);
-
-		ocfs2_inode_unlock(inode, 0);
-	}
-
-clean_orphan:
-	if (orphaned) {
-		int tmp_ret;
-		int update_isize = written > 0 ? 1 : 0;
-		loff_t end = update_isize ? offset + written : 0;
-
-		tmp_ret = ocfs2_inode_lock(inode, &di_bh, 1);
-		if (tmp_ret < 0) {
-			ret = tmp_ret;
-			mlog_errno(ret);
-			goto out;
-		}
-
-		tmp_ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh,
-				update_isize, end);
-		if (tmp_ret < 0) {
-			ret = tmp_ret;
-			mlog_errno(ret);
-			brelse(di_bh);
-			goto out;
-		}
-
-		ocfs2_inode_unlock(inode, 1);
-		brelse(di_bh);
-
-		tmp_ret = jbd2_journal_force_commit(journal);
-		if (tmp_ret < 0) {
-			ret = tmp_ret;
-			mlog_errno(tmp_ret);
-		}
-	}
-
-out:
-	if (ret >= 0)
-		ret = written;
-	return ret;
-}
-
-static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
-			       loff_t offset)
-{
-	struct file *file = iocb->ki_filp;
-	struct inode *inode = file_inode(file)->i_mapping->host;
-	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
-	int full_coherency = !(osb->s_mount_opt &
-			OCFS2_MOUNT_COHERENCY_BUFFERED);
-
-	/*
-	 * Fallback to buffered I/O if we see an inode without
-	 * extents.
-	 */
-	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
-		return 0;
-
-	/* Fallback to buffered I/O if we are appending and
-	 * concurrent O_DIRECT writes are allowed.
-	 */
-	if (i_size_read(inode) <= offset && !full_coherency)
-		return 0;
-
-	if (iov_iter_rw(iter) == READ)
-		return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
-					    iter, offset,
-					    ocfs2_direct_IO_get_blocks,
-					    ocfs2_dio_end_io, NULL, 0);
-	else
-		return ocfs2_direct_IO_write(iocb, iter, offset);
-}
-
 static void ocfs2_figure_cluster_boundaries(struct ocfs2_super *osb,
 					    u32 cpos,
 					    unsigned int *start,
 					    unsigned int *end)
 {
-	unsigned int cluster_start = 0, cluster_end = PAGE_CACHE_SIZE;
+	unsigned int cluster_start = 0, cluster_end = PAGE_SIZE;
 
-	if (unlikely(PAGE_CACHE_SHIFT > osb->s_clustersize_bits)) {
+	if (unlikely(PAGE_SHIFT > osb->s_clustersize_bits)) {
 		unsigned int cpp;
 
-		cpp = 1 << (PAGE_CACHE_SHIFT - osb->s_clustersize_bits);
+		cpp = 1 << (PAGE_SHIFT - osb->s_clustersize_bits);
 
 		cluster_start = cpos % cpp;
 		cluster_start = cluster_start << osb->s_clustersize_bits;
@@ -1187,13 +684,20 @@ next_bh:
 	return ret;
 }
 
-#if (PAGE_CACHE_SIZE >= OCFS2_MAX_CLUSTERSIZE)
+#if (PAGE_SIZE >= OCFS2_MAX_CLUSTERSIZE)
 #define OCFS2_MAX_CTXT_PAGES	1
 #else
-#define OCFS2_MAX_CTXT_PAGES	(OCFS2_MAX_CLUSTERSIZE / PAGE_CACHE_SIZE)
+#define OCFS2_MAX_CTXT_PAGES	(OCFS2_MAX_CLUSTERSIZE / PAGE_SIZE)
 #endif
 
-#define OCFS2_MAX_CLUSTERS_PER_PAGE	(PAGE_CACHE_SIZE / OCFS2_MIN_CLUSTERSIZE)
+#define OCFS2_MAX_CLUSTERS_PER_PAGE	(PAGE_SIZE / OCFS2_MIN_CLUSTERSIZE)
+
+struct ocfs2_unwritten_extent {
+	struct list_head	ue_node;
+	struct list_head	ue_ip_node;
+	u32			ue_cpos;
+	u32			ue_phys;
+};
 
 /*
  * Describe the state of a single cluster to be written to.
@@ -1206,7 +710,7 @@ struct ocfs2_write_cluster_desc {
 	 * filled.
 	 */
 	unsigned	c_new;
-	unsigned	c_unwritten;
+	unsigned	c_clear_unwritten;
 	unsigned	c_needs_zero;
 };
 
@@ -1218,6 +722,9 @@ struct ocfs2_write_ctxt {
 	/* First cluster allocated in a nonsparse extend */
 	u32				w_first_new_cpos;
 
+	/* Type of caller. Must be one of buffer, mmap, direct.  */
+	ocfs2_write_type_t		w_type;
+
 	struct ocfs2_write_cluster_desc	w_desc[OCFS2_MAX_CLUSTERS_PER_PAGE];
 
 	/*
@@ -1266,6 +773,8 @@ struct ocfs2_write_ctxt {
 	struct buffer_head		*w_di_bh;
 
 	struct ocfs2_cached_dealloc_ctxt w_dealloc;
+
+	struct list_head		w_unwritten_list;
 };
 
 void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages)
@@ -1276,7 +785,7 @@ void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages)
 		if (pages[i]) {
 			unlock_page(pages[i]);
 			mark_page_accessed(pages[i]);
-			page_cache_release(pages[i]);
+			put_page(pages[i]);
 		}
 	}
 }
@@ -1299,13 +808,30 @@ static void ocfs2_unlock_pages(struct ocfs2_write_ctxt *wc)
 			}
 		}
 		mark_page_accessed(wc->w_target_page);
-		page_cache_release(wc->w_target_page);
+		put_page(wc->w_target_page);
 	}
 	ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages);
 }
 
-static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
+static void ocfs2_free_unwritten_list(struct inode *inode,
+				 struct list_head *head)
 {
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+	struct ocfs2_unwritten_extent *ue = NULL, *tmp = NULL;
+
+	list_for_each_entry_safe(ue, tmp, head, ue_node) {
+		list_del(&ue->ue_node);
+		spin_lock(&oi->ip_lock);
+		list_del(&ue->ue_ip_node);
+		spin_unlock(&oi->ip_lock);
+		kfree(ue);
+	}
+}
+
+static void ocfs2_free_write_ctxt(struct inode *inode,
+				  struct ocfs2_write_ctxt *wc)
+{
+	ocfs2_free_unwritten_list(inode, &wc->w_unwritten_list);
 	ocfs2_unlock_pages(wc);
 	brelse(wc->w_di_bh);
 	kfree(wc);
@@ -1313,7 +839,8 @@ static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
 
 static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp,
 				  struct ocfs2_super *osb, loff_t pos,
-				  unsigned len, struct buffer_head *di_bh)
+				  unsigned len, ocfs2_write_type_t type,
+				  struct buffer_head *di_bh)
 {
 	u32 cend;
 	struct ocfs2_write_ctxt *wc;
@@ -1328,13 +855,15 @@ static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp,
 	wc->w_clen = cend - wc->w_cpos + 1;
 	get_bh(di_bh);
 	wc->w_di_bh = di_bh;
+	wc->w_type = type;
 
-	if (unlikely(PAGE_CACHE_SHIFT > osb->s_clustersize_bits))
+	if (unlikely(PAGE_SHIFT > osb->s_clustersize_bits))
 		wc->w_large_pages = 1;
 	else
 		wc->w_large_pages = 0;
 
 	ocfs2_init_dealloc_ctxt(&wc->w_dealloc);
+	INIT_LIST_HEAD(&wc->w_unwritten_list);
 
 	*wcp = wc;
 
@@ -1391,16 +920,17 @@ static void ocfs2_write_failure(struct inode *inode,
 				loff_t user_pos, unsigned user_len)
 {
 	int i;
-	unsigned from = user_pos & (PAGE_CACHE_SIZE - 1),
+	unsigned from = user_pos & (PAGE_SIZE - 1),
 		to = user_pos + user_len;
 	struct page *tmppage;
 
-	ocfs2_zero_new_buffers(wc->w_target_page, from, to);
+	if (wc->w_target_page)
+		ocfs2_zero_new_buffers(wc->w_target_page, from, to);
 
 	for(i = 0; i < wc->w_num_pages; i++) {
 		tmppage = wc->w_pages[i];
 
-		if (page_has_buffers(tmppage)) {
+		if (tmppage && page_has_buffers(tmppage)) {
 			if (ocfs2_should_order_data(inode))
 				ocfs2_jbd2_file_inode(wc->w_handle, inode);
 
@@ -1430,7 +960,7 @@ static int ocfs2_prepare_page_for_write(struct inode *inode, u64 *p_blkno,
 			(page_offset(page) <= user_pos));
 
 	if (page == wc->w_target_page) {
-		map_from = user_pos & (PAGE_CACHE_SIZE - 1);
+		map_from = user_pos & (PAGE_SIZE - 1);
 		map_to = map_from + user_len;
 
 		if (new)
@@ -1504,7 +1034,7 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping,
 	struct inode *inode = mapping->host;
 	loff_t last_byte;
 
-	target_index = user_pos >> PAGE_CACHE_SHIFT;
+	target_index = user_pos >> PAGE_SHIFT;
 
 	/*
 	 * Figure out how many pages we'll be manipulating here. For
@@ -1523,18 +1053,20 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping,
 		 */
 		last_byte = max(user_pos + user_len, i_size_read(inode));
 		BUG_ON(last_byte < 1);
-		end_index = ((last_byte - 1) >> PAGE_CACHE_SHIFT) + 1;
+		end_index = ((last_byte - 1) >> PAGE_SHIFT) + 1;
 		if ((start + wc->w_num_pages) > end_index)
 			wc->w_num_pages = end_index - start;
 	} else {
 		wc->w_num_pages = 1;
 		start = target_index;
 	}
+	end_index = (user_pos + user_len - 1) >> PAGE_SHIFT;
 
 	for(i = 0; i < wc->w_num_pages; i++) {
 		index = start + i;
 
-		if (index == target_index && mmap_page) {
+		if (index >= target_index && index <= end_index &&
+		    wc->w_type == OCFS2_WRITE_MMAP) {
 			/*
 			 * ocfs2_pagemkwrite() is a little different
 			 * and wants us to directly use the page
@@ -1550,9 +1082,14 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping,
 				goto out;
 			}
 
-			page_cache_get(mmap_page);
+			get_page(mmap_page);
 			wc->w_pages[i] = mmap_page;
 			wc->w_target_locked = true;
+		} else if (index >= target_index && index <= end_index &&
+			   wc->w_type == OCFS2_WRITE_DIRECT) {
+			/* Direct write has no mapping page. */
+			wc->w_pages[i] = NULL;
+			continue;
 		} else {
 			wc->w_pages[i] = find_or_create_page(mapping, index,
 							     GFP_NOFS);
@@ -1577,19 +1114,20 @@ out:
  * Prepare a single cluster for write one cluster into the file.
  */
 static int ocfs2_write_cluster(struct address_space *mapping,
-			       u32 phys, unsigned int unwritten,
+			       u32 *phys, unsigned int new,
+			       unsigned int clear_unwritten,
 			       unsigned int should_zero,
 			       struct ocfs2_alloc_context *data_ac,
 			       struct ocfs2_alloc_context *meta_ac,
 			       struct ocfs2_write_ctxt *wc, u32 cpos,
 			       loff_t user_pos, unsigned user_len)
 {
-	int ret, i, new;
-	u64 v_blkno, p_blkno;
+	int ret, i;
+	u64 p_blkno;
 	struct inode *inode = mapping->host;
 	struct ocfs2_extent_tree et;
+	int bpc = ocfs2_clusters_to_blocks(inode->i_sb, 1);
 
-	new = phys == 0 ? 1 : 0;
 	if (new) {
 		u32 tmp_pos;
 
@@ -1599,9 +1137,9 @@ static int ocfs2_write_cluster(struct address_space *mapping,
 		 */
 		tmp_pos = cpos;
 		ret = ocfs2_add_inode_data(OCFS2_SB(inode->i_sb), inode,
-					   &tmp_pos, 1, 0, wc->w_di_bh,
-					   wc->w_handle, data_ac,
-					   meta_ac, NULL);
+					   &tmp_pos, 1, !clear_unwritten,
+					   wc->w_di_bh, wc->w_handle,
+					   data_ac, meta_ac, NULL);
 		/*
 		 * This shouldn't happen because we must have already
 		 * calculated the correct meta data allocation required. The
@@ -1618,11 +1156,11 @@ static int ocfs2_write_cluster(struct address_space *mapping,
 			mlog_errno(ret);
 			goto out;
 		}
-	} else if (unwritten) {
+	} else if (clear_unwritten) {
 		ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode),
 					      wc->w_di_bh);
 		ret = ocfs2_mark_extent_written(inode, &et,
-						wc->w_handle, cpos, 1, phys,
+						wc->w_handle, cpos, 1, *phys,
 						meta_ac, &wc->w_dealloc);
 		if (ret < 0) {
 			mlog_errno(ret);
@@ -1630,30 +1168,33 @@ static int ocfs2_write_cluster(struct address_space *mapping,
 		}
 	}
 
-	if (should_zero)
-		v_blkno = ocfs2_clusters_to_blocks(inode->i_sb, cpos);
-	else
-		v_blkno = user_pos >> inode->i_sb->s_blocksize_bits;
-
 	/*
 	 * The only reason this should fail is due to an inability to
 	 * find the extent added.
 	 */
-	ret = ocfs2_extent_map_get_blocks(inode, v_blkno, &p_blkno, NULL,
-					  NULL);
+	ret = ocfs2_get_clusters(inode, cpos, phys, NULL, NULL);
 	if (ret < 0) {
 		mlog(ML_ERROR, "Get physical blkno failed for inode %llu, "
-			    "at logical block %llu",
-			    (unsigned long long)OCFS2_I(inode)->ip_blkno,
-			    (unsigned long long)v_blkno);
+			    "at logical cluster %u",
+			    (unsigned long long)OCFS2_I(inode)->ip_blkno, cpos);
 		goto out;
 	}
 
-	BUG_ON(p_blkno == 0);
+	BUG_ON(*phys == 0);
+
+	p_blkno = ocfs2_clusters_to_blocks(inode->i_sb, *phys);
+	if (!should_zero)
+		p_blkno += (user_pos >> inode->i_sb->s_blocksize_bits) & (u64)(bpc - 1);
 
 	for(i = 0; i < wc->w_num_pages; i++) {
 		int tmpret;
 
+		/* This is the direct io target page. */
+		if (wc->w_pages[i] == NULL) {
+			p_blkno++;
+			continue;
+		}
+
 		tmpret = ocfs2_prepare_page_for_write(inode, &p_blkno, wc,
 						      wc->w_pages[i], cpos,
 						      user_pos, user_len,
@@ -1700,8 +1241,9 @@ static int ocfs2_write_cluster_by_desc(struct address_space *mapping,
 		if ((cluster_off + local_len) > osb->s_clustersize)
 			local_len = osb->s_clustersize - cluster_off;
 
-		ret = ocfs2_write_cluster(mapping, desc->c_phys,
-					  desc->c_unwritten,
+		ret = ocfs2_write_cluster(mapping, &desc->c_phys,
+					  desc->c_new,
+					  desc->c_clear_unwritten,
 					  desc->c_needs_zero,
 					  data_ac, meta_ac,
 					  wc, desc->c_cpos, pos, local_len);
@@ -1730,7 +1272,7 @@ static void ocfs2_set_target_boundaries(struct ocfs2_super *osb,
 {
 	struct ocfs2_write_cluster_desc *desc;
 
-	wc->w_target_from = pos & (PAGE_CACHE_SIZE - 1);
+	wc->w_target_from = pos & (PAGE_SIZE - 1);
 	wc->w_target_to = wc->w_target_from + len;
 
 	if (alloc == 0)
@@ -1767,8 +1309,68 @@ static void ocfs2_set_target_boundaries(struct ocfs2_super *osb,
 							&wc->w_target_to);
 	} else {
 		wc->w_target_from = 0;
-		wc->w_target_to = PAGE_CACHE_SIZE;
+		wc->w_target_to = PAGE_SIZE;
+	}
+}
+
+/*
+ * Check if this extent is marked UNWRITTEN by direct io. If so, we need not to
+ * do the zero work. And should not to clear UNWRITTEN since it will be cleared
+ * by the direct io procedure.
+ * If this is a new extent that allocated by direct io, we should mark it in
+ * the ip_unwritten_list.
+ */
+static int ocfs2_unwritten_check(struct inode *inode,
+				 struct ocfs2_write_ctxt *wc,
+				 struct ocfs2_write_cluster_desc *desc)
+{
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+	struct ocfs2_unwritten_extent *ue = NULL, *new = NULL;
+	int ret = 0;
+
+	if (!desc->c_needs_zero)
+		return 0;
+
+retry:
+	spin_lock(&oi->ip_lock);
+	/* Needs not to zero no metter buffer or direct. The one who is zero
+	 * the cluster is doing zero. And he will clear unwritten after all
+	 * cluster io finished. */
+	list_for_each_entry(ue, &oi->ip_unwritten_list, ue_ip_node) {
+		if (desc->c_cpos == ue->ue_cpos) {
+			BUG_ON(desc->c_new);
+			desc->c_needs_zero = 0;
+			desc->c_clear_unwritten = 0;
+			goto unlock;
+		}
 	}
+
+	if (wc->w_type != OCFS2_WRITE_DIRECT)
+		goto unlock;
+
+	if (new == NULL) {
+		spin_unlock(&oi->ip_lock);
+		new = kmalloc(sizeof(struct ocfs2_unwritten_extent),
+			     GFP_NOFS);
+		if (new == NULL) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		goto retry;
+	}
+	/* This direct write will doing zero. */
+	new->ue_cpos = desc->c_cpos;
+	new->ue_phys = desc->c_phys;
+	desc->c_clear_unwritten = 0;
+	list_add_tail(&new->ue_ip_node, &oi->ip_unwritten_list);
+	list_add_tail(&new->ue_node, &wc->w_unwritten_list);
+	new = NULL;
+unlock:
+	spin_unlock(&oi->ip_lock);
+out:
+	if (new)
+		kfree(new);
+	return ret;
 }
 
 /*
@@ -1846,14 +1448,21 @@ static int ocfs2_populate_write_desc(struct inode *inode,
 		if (phys == 0) {
 			desc->c_new = 1;
 			desc->c_needs_zero = 1;
+			desc->c_clear_unwritten = 1;
 			*clusters_to_alloc = *clusters_to_alloc + 1;
 		}
 
 		if (ext_flags & OCFS2_EXT_UNWRITTEN) {
-			desc->c_unwritten = 1;
+			desc->c_clear_unwritten = 1;
 			desc->c_needs_zero = 1;
 		}
 
+		ret = ocfs2_unwritten_check(inode, wc, desc);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
 		num_clusters--;
 	}
 
@@ -2016,8 +1625,10 @@ static int ocfs2_expand_nonsparse_inode(struct inode *inode,
 	if (ret)
 		mlog_errno(ret);
 
-	wc->w_first_new_cpos =
-		ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode));
+	/* There is no wc if this is call from direct. */
+	if (wc)
+		wc->w_first_new_cpos =
+			ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode));
 
 	return ret;
 }
@@ -2046,9 +1657,9 @@ static int ocfs2_try_to_free_truncate_log(struct ocfs2_super *osb,
 	int ret = 0;
 	unsigned int truncated_clusters;
 
-	mutex_lock(&osb->osb_tl_inode->i_mutex);
+	inode_lock(osb->osb_tl_inode);
 	truncated_clusters = osb->truncated_clusters;
-	mutex_unlock(&osb->osb_tl_inode->i_mutex);
+	inode_unlock(osb->osb_tl_inode);
 
 	/*
 	 * Check whether we can succeed in allocating if we free
@@ -2071,9 +1682,8 @@ out:
 	return ret;
 }
 
-int ocfs2_write_begin_nolock(struct file *filp,
-			     struct address_space *mapping,
-			     loff_t pos, unsigned len, unsigned flags,
+int ocfs2_write_begin_nolock(struct address_space *mapping,
+			     loff_t pos, unsigned len, ocfs2_write_type_t type,
 			     struct page **pagep, void **fsdata,
 			     struct buffer_head *di_bh, struct page *mmap_page)
 {
@@ -2090,7 +1700,7 @@ int ocfs2_write_begin_nolock(struct file *filp,
 	int try_free = 1, ret1;
 
 try_again:
-	ret = ocfs2_alloc_write_ctxt(&wc, osb, pos, len, di_bh);
+	ret = ocfs2_alloc_write_ctxt(&wc, osb, pos, len, type, di_bh);
 	if (ret) {
 		mlog_errno(ret);
 		return ret;
@@ -2109,14 +1719,17 @@ try_again:
 		}
 	}
 
-	if (ocfs2_sparse_alloc(osb))
-		ret = ocfs2_zero_tail(inode, di_bh, pos);
-	else
-		ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos, len,
-						   wc);
-	if (ret) {
-		mlog_errno(ret);
-		goto out;
+	/* Direct io change i_size late, should not zero tail here. */
+	if (type != OCFS2_WRITE_DIRECT) {
+		if (ocfs2_sparse_alloc(osb))
+			ret = ocfs2_zero_tail(inode, di_bh, pos);
+		else
+			ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos,
+							   len, wc);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
 	}
 
 	ret = ocfs2_check_range_for_refcount(inode, pos, len);
@@ -2147,7 +1760,7 @@ try_again:
 			(unsigned long long)OCFS2_I(inode)->ip_blkno,
 			(long long)i_size_read(inode),
 			le32_to_cpu(di->i_clusters),
-			pos, len, flags, mmap_page,
+			pos, len, type, mmap_page,
 			clusters_to_alloc, extents_to_split);
 
 	/*
@@ -2177,17 +1790,17 @@ try_again:
 
 		credits = ocfs2_calc_extend_credits(inode->i_sb,
 						    &di->id2.i_list);
-
-	}
+	} else if (type == OCFS2_WRITE_DIRECT)
+		/* direct write needs not to start trans if no extents alloc. */
+		goto success;
 
 	/*
 	 * We have to zero sparse allocated clusters, unwritten extent clusters,
 	 * and non-sparse clusters we just extended.  For non-sparse writes,
 	 * we know zeros will only be needed in the first and/or last cluster.
 	 */
-	if (clusters_to_alloc || extents_to_split ||
-	    (wc->w_clen && (wc->w_desc[0].c_needs_zero ||
-			    wc->w_desc[wc->w_clen - 1].c_needs_zero)))
+	if (wc->w_clen && (wc->w_desc[0].c_needs_zero ||
+			   wc->w_desc[wc->w_clen - 1].c_needs_zero))
 		cluster_of_pages = 1;
 	else
 		cluster_of_pages = 0;
@@ -2254,7 +1867,8 @@ try_again:
 		ocfs2_free_alloc_context(meta_ac);
 
 success:
-	*pagep = wc->w_target_page;
+	if (pagep)
+		*pagep = wc->w_target_page;
 	*fsdata = wc;
 	return 0;
 out_quota:
@@ -2265,7 +1879,7 @@ out_commit:
 	ocfs2_commit_trans(osb, handle);
 
 out:
-	ocfs2_free_write_ctxt(wc);
+	ocfs2_free_write_ctxt(inode, wc);
 
 	if (data_ac) {
 		ocfs2_free_alloc_context(data_ac);
@@ -2317,8 +1931,8 @@ static int ocfs2_write_begin(struct file *file, struct address_space *mapping,
 	 */
 	down_write(&OCFS2_I(inode)->ip_alloc_sem);
 
-	ret = ocfs2_write_begin_nolock(file, mapping, pos, len, flags, pagep,
-				       fsdata, di_bh, NULL);
+	ret = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_BUFFER,
+				       pagep, fsdata, di_bh, NULL);
 	if (ret) {
 		mlog_errno(ret);
 		goto out_fail;
@@ -2367,7 +1981,7 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 			   struct page *page, void *fsdata)
 {
 	int i, ret;
-	unsigned from, to, start = pos & (PAGE_CACHE_SIZE - 1);
+	unsigned from, to, start = pos & (PAGE_SIZE - 1);
 	struct inode *inode = mapping->host;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	struct ocfs2_write_ctxt *wc = fsdata;
@@ -2375,12 +1989,16 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 	handle_t *handle = wc->w_handle;
 	struct page *tmppage;
 
-	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
-			OCFS2_JOURNAL_ACCESS_WRITE);
-	if (ret) {
-		copied = ret;
-		mlog_errno(ret);
-		goto out;
+	BUG_ON(!list_empty(&wc->w_unwritten_list));
+
+	if (handle) {
+		ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode),
+				wc->w_di_bh, OCFS2_JOURNAL_ACCESS_WRITE);
+		if (ret) {
+			copied = ret;
+			mlog_errno(ret);
+			goto out;
+		}
 	}
 
 	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
@@ -2388,24 +2006,29 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 		goto out_write_size;
 	}
 
-	if (unlikely(copied < len)) {
+	if (unlikely(copied < len) && wc->w_target_page) {
 		if (!PageUptodate(wc->w_target_page))
 			copied = 0;
 
 		ocfs2_zero_new_buffers(wc->w_target_page, start+copied,
 				       start+len);
 	}
-	flush_dcache_page(wc->w_target_page);
+	if (wc->w_target_page)
+		flush_dcache_page(wc->w_target_page);
 
 	for(i = 0; i < wc->w_num_pages; i++) {
 		tmppage = wc->w_pages[i];
 
+		/* This is the direct io target page. */
+		if (tmppage == NULL)
+			continue;
+
 		if (tmppage == wc->w_target_page) {
 			from = wc->w_target_from;
 			to = wc->w_target_to;
 
-			BUG_ON(from > PAGE_CACHE_SIZE ||
-			       to > PAGE_CACHE_SIZE ||
+			BUG_ON(from > PAGE_SIZE ||
+			       to > PAGE_SIZE ||
 			       to < from);
 		} else {
 			/*
@@ -2414,29 +2037,33 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 			 * to flush their entire range.
 			 */
 			from = 0;
-			to = PAGE_CACHE_SIZE;
+			to = PAGE_SIZE;
 		}
 
 		if (page_has_buffers(tmppage)) {
-			if (ocfs2_should_order_data(inode))
-				ocfs2_jbd2_file_inode(wc->w_handle, inode);
+			if (handle && ocfs2_should_order_data(inode))
+				ocfs2_jbd2_file_inode(handle, inode);
 			block_commit_write(tmppage, from, to);
 		}
 	}
 
 out_write_size:
-	pos += copied;
-	if (pos > i_size_read(inode)) {
-		i_size_write(inode, pos);
-		mark_inode_dirty(inode);
-	}
-	inode->i_blocks = ocfs2_inode_sector_count(inode);
-	di->i_size = cpu_to_le64((u64)i_size_read(inode));
-	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-	di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
-	di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
-	ocfs2_update_inode_fsync_trans(handle, inode, 1);
-	ocfs2_journal_dirty(handle, wc->w_di_bh);
+	/* Direct io do not update i_size here. */
+	if (wc->w_type != OCFS2_WRITE_DIRECT) {
+		pos += copied;
+		if (pos > i_size_read(inode)) {
+			i_size_write(inode, pos);
+			mark_inode_dirty(inode);
+		}
+		inode->i_blocks = ocfs2_inode_sector_count(inode);
+		di->i_size = cpu_to_le64((u64)i_size_read(inode));
+		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+		di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
+		di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
+		ocfs2_update_inode_fsync_trans(handle, inode, 1);
+	}
+	if (handle)
+		ocfs2_journal_dirty(handle, wc->w_di_bh);
 
 out:
 	/* unlock pages before dealloc since it needs acquiring j_trans_barrier
@@ -2446,7 +2073,8 @@ out:
 	 */
 	ocfs2_unlock_pages(wc);
 
-	ocfs2_commit_trans(osb, handle);
+	if (handle)
+		ocfs2_commit_trans(osb, handle);
 
 	ocfs2_run_deallocs(osb, &wc->w_dealloc);
 
@@ -2471,6 +2099,360 @@ static int ocfs2_write_end(struct file *file, struct address_space *mapping,
 	return ret;
 }
 
+struct ocfs2_dio_write_ctxt {
+	struct list_head	dw_zero_list;
+	unsigned		dw_zero_count;
+	int			dw_orphaned;
+	pid_t			dw_writer_pid;
+};
+
+static struct ocfs2_dio_write_ctxt *
+ocfs2_dio_alloc_write_ctx(struct buffer_head *bh, int *alloc)
+{
+	struct ocfs2_dio_write_ctxt *dwc = NULL;
+
+	if (bh->b_private)
+		return bh->b_private;
+
+	dwc = kmalloc(sizeof(struct ocfs2_dio_write_ctxt), GFP_NOFS);
+	if (dwc == NULL)
+		return NULL;
+	INIT_LIST_HEAD(&dwc->dw_zero_list);
+	dwc->dw_zero_count = 0;
+	dwc->dw_orphaned = 0;
+	dwc->dw_writer_pid = task_pid_nr(current);
+	bh->b_private = dwc;
+	*alloc = 1;
+
+	return dwc;
+}
+
+static void ocfs2_dio_free_write_ctx(struct inode *inode,
+				     struct ocfs2_dio_write_ctxt *dwc)
+{
+	ocfs2_free_unwritten_list(inode, &dwc->dw_zero_list);
+	kfree(dwc);
+}
+
+/*
+ * TODO: Make this into a generic get_blocks function.
+ *
+ * From do_direct_io in direct-io.c:
+ *  "So what we do is to permit the ->get_blocks function to populate
+ *   bh.b_size with the size of IO which is permitted at this offset and
+ *   this i_blkbits."
+ *
+ * This function is called directly from get_more_blocks in direct-io.c.
+ *
+ * called like this: dio->get_blocks(dio->inode, fs_startblk,
+ * 					fs_count, map_bh, dio->rw == WRITE);
+ */
+static int ocfs2_dio_get_block(struct inode *inode, sector_t iblock,
+			       struct buffer_head *bh_result, int create)
+{
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+	struct ocfs2_write_ctxt *wc;
+	struct ocfs2_write_cluster_desc *desc = NULL;
+	struct ocfs2_dio_write_ctxt *dwc = NULL;
+	struct buffer_head *di_bh = NULL;
+	u64 p_blkno;
+	loff_t pos = iblock << inode->i_sb->s_blocksize_bits;
+	unsigned len, total_len = bh_result->b_size;
+	int ret = 0, first_get_block = 0;
+
+	len = osb->s_clustersize - (pos & (osb->s_clustersize - 1));
+	len = min(total_len, len);
+
+	mlog(0, "get block of %lu at %llu:%u req %u\n",
+			inode->i_ino, pos, len, total_len);
+
+	/*
+	 * Because we need to change file size in ocfs2_dio_end_io_write(), or
+	 * we may need to add it to orphan dir. So can not fall to fast path
+	 * while file size will be changed.
+	 */
+	if (pos + total_len <= i_size_read(inode)) {
+		down_read(&oi->ip_alloc_sem);
+		/* This is the fast path for re-write. */
+		ret = ocfs2_get_block(inode, iblock, bh_result, create);
+
+		up_read(&oi->ip_alloc_sem);
+
+		if (buffer_mapped(bh_result) &&
+		    !buffer_new(bh_result) &&
+		    ret == 0)
+			goto out;
+
+		/* Clear state set by ocfs2_get_block. */
+		bh_result->b_state = 0;
+	}
+
+	dwc = ocfs2_dio_alloc_write_ctx(bh_result, &first_get_block);
+	if (unlikely(dwc == NULL)) {
+		ret = -ENOMEM;
+		mlog_errno(ret);
+		goto out;
+	}
+
+	if (ocfs2_clusters_for_bytes(inode->i_sb, pos + total_len) >
+	    ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode)) &&
+	    !dwc->dw_orphaned) {
+		/*
+		 * when we are going to alloc extents beyond file size, add the
+		 * inode to orphan dir, so we can recall those spaces when
+		 * system crashed during write.
+		 */
+		ret = ocfs2_add_inode_to_orphan(osb, inode);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto out;
+		}
+		dwc->dw_orphaned = 1;
+	}
+
+	ret = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	down_write(&oi->ip_alloc_sem);
+
+	if (first_get_block) {
+		if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
+			ret = ocfs2_zero_tail(inode, di_bh, pos);
+		else
+			ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos,
+							   total_len, NULL);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto unlock;
+		}
+	}
+
+	ret = ocfs2_write_begin_nolock(inode->i_mapping, pos, len,
+				       OCFS2_WRITE_DIRECT, NULL,
+				       (void **)&wc, di_bh, NULL);
+	if (ret) {
+		mlog_errno(ret);
+		goto unlock;
+	}
+
+	desc = &wc->w_desc[0];
+
+	p_blkno = ocfs2_clusters_to_blocks(inode->i_sb, desc->c_phys);
+	BUG_ON(p_blkno == 0);
+	p_blkno += iblock & (u64)(ocfs2_clusters_to_blocks(inode->i_sb, 1) - 1);
+
+	map_bh(bh_result, inode->i_sb, p_blkno);
+	bh_result->b_size = len;
+	if (desc->c_needs_zero)
+		set_buffer_new(bh_result);
+
+	/* May sleep in end_io. It should not happen in a irq context. So defer
+	 * it to dio work queue. */
+	set_buffer_defer_completion(bh_result);
+
+	if (!list_empty(&wc->w_unwritten_list)) {
+		struct ocfs2_unwritten_extent *ue = NULL;
+
+		ue = list_first_entry(&wc->w_unwritten_list,
+				      struct ocfs2_unwritten_extent,
+				      ue_node);
+		BUG_ON(ue->ue_cpos != desc->c_cpos);
+		/* The physical address may be 0, fill it. */
+		ue->ue_phys = desc->c_phys;
+
+		list_splice_tail_init(&wc->w_unwritten_list, &dwc->dw_zero_list);
+		dwc->dw_zero_count++;
+	}
+
+	ret = ocfs2_write_end_nolock(inode->i_mapping, pos, len, len, NULL, wc);
+	BUG_ON(ret != len);
+	ret = 0;
+unlock:
+	up_write(&oi->ip_alloc_sem);
+	ocfs2_inode_unlock(inode, 1);
+	brelse(di_bh);
+out:
+	if (ret < 0)
+		ret = -EIO;
+	return ret;
+}
+
+static void ocfs2_dio_end_io_write(struct inode *inode,
+				   struct ocfs2_dio_write_ctxt *dwc,
+				   loff_t offset,
+				   ssize_t bytes)
+{
+	struct ocfs2_cached_dealloc_ctxt dealloc;
+	struct ocfs2_extent_tree et;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+	struct ocfs2_unwritten_extent *ue = NULL;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_dinode *di;
+	struct ocfs2_alloc_context *data_ac = NULL;
+	struct ocfs2_alloc_context *meta_ac = NULL;
+	handle_t *handle = NULL;
+	loff_t end = offset + bytes;
+	int ret = 0, credits = 0, locked = 0;
+
+	ocfs2_init_dealloc_ctxt(&dealloc);
+
+	/* We do clear unwritten, delete orphan, change i_size here. If neither
+	 * of these happen, we can skip all this. */
+	if (list_empty(&dwc->dw_zero_list) &&
+	    end <= i_size_read(inode) &&
+	    !dwc->dw_orphaned)
+		goto out;
+
+	/* ocfs2_file_write_iter will get i_mutex, so we need not lock if we
+	 * are in that context. */
+	if (dwc->dw_writer_pid != task_pid_nr(current)) {
+		mutex_lock(&inode->i_mutex);
+		locked = 1;
+	}
+
+	ret = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (ret < 0) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	down_write(&oi->ip_alloc_sem);
+
+	/* Delete orphan before acquire i_mutex. */
+	if (dwc->dw_orphaned) {
+		BUG_ON(dwc->dw_writer_pid != task_pid_nr(current));
+
+		end = end > i_size_read(inode) ? end : 0;
+
+		ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh,
+				!!end, end);
+		if (ret < 0)
+			mlog_errno(ret);
+	}
+
+	di = (struct ocfs2_dinode *)di_bh;
+
+	ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), di_bh);
+
+	ret = ocfs2_lock_allocators(inode, &et, 0, dwc->dw_zero_count*2,
+				    &data_ac, &meta_ac);
+	if (ret) {
+		mlog_errno(ret);
+		goto unlock;
+	}
+
+	credits = ocfs2_calc_extend_credits(inode->i_sb, &di->id2.i_list);
+
+	handle = ocfs2_start_trans(osb, credits);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		mlog_errno(ret);
+		goto unlock;
+	}
+	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		mlog_errno(ret);
+		goto commit;
+	}
+
+	list_for_each_entry(ue, &dwc->dw_zero_list, ue_node) {
+		ret = ocfs2_mark_extent_written(inode, &et, handle,
+						ue->ue_cpos, 1,
+						ue->ue_phys,
+						meta_ac, &dealloc);
+		if (ret < 0) {
+			mlog_errno(ret);
+			break;
+		}
+	}
+
+	if (end > i_size_read(inode)) {
+		ret = ocfs2_set_inode_size(handle, inode, di_bh, end);
+		if (ret < 0)
+			mlog_errno(ret);
+	}
+commit:
+	ocfs2_commit_trans(osb, handle);
+unlock:
+	up_write(&oi->ip_alloc_sem);
+	ocfs2_inode_unlock(inode, 1);
+	brelse(di_bh);
+out:
+	if (data_ac)
+		ocfs2_free_alloc_context(data_ac);
+	if (meta_ac)
+		ocfs2_free_alloc_context(meta_ac);
+	ocfs2_run_deallocs(osb, &dealloc);
+	if (locked)
+		mutex_unlock(&inode->i_mutex);
+	ocfs2_dio_free_write_ctx(inode, dwc);
+}
+
+/*
+ * ocfs2_dio_end_io is called by the dio core when a dio is finished.  We're
+ * particularly interested in the aio/dio case.  We use the rw_lock DLM lock
+ * to protect io on one node from truncation on another.
+ */
+static int ocfs2_dio_end_io(struct kiocb *iocb,
+			    loff_t offset,
+			    ssize_t bytes,
+			    void *private)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	int level;
+
+	if (bytes <= 0)
+		return 0;
+
+	/* this io's submitter should not have unlocked this before we could */
+	BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
+
+	if (private)
+		ocfs2_dio_end_io_write(inode, private, offset, bytes);
+
+	ocfs2_iocb_clear_rw_locked(iocb);
+
+	level = ocfs2_iocb_rw_locked_level(iocb);
+	ocfs2_rw_unlock(inode, level);
+	return 0;
+}
+
+static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+			       loff_t offset)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file)->i_mapping->host;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	loff_t end = offset + iter->count;
+	get_block_t *get_block;
+
+	/*
+	 * Fallback to buffered I/O if we see an inode without
+	 * extents.
+	 */
+	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
+		return 0;
+
+	/* Fallback to buffered I/O if we do not support append dio. */
+	if (end > i_size_read(inode) && !ocfs2_supports_append_dio(osb))
+		return 0;
+
+	if (iov_iter_rw(iter) == READ)
+		get_block = ocfs2_get_block;
+	else
+		get_block = ocfs2_dio_get_block;
+
+	return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
+				    iter, offset, get_block,
+				    ocfs2_dio_end_io, NULL, 0);
+}
+
 const struct address_space_operations ocfs2_aops = {
 	.readpage		= ocfs2_readpage,
 	.readpages		= ocfs2_readpages,
diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index 24e496d6bdcd..b1c9f28a57b1 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -47,9 +47,14 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 			   loff_t pos, unsigned len, unsigned copied,
 			   struct page *page, void *fsdata);
 
-int ocfs2_write_begin_nolock(struct file *filp,
-			     struct address_space *mapping,
-			     loff_t pos, unsigned len, unsigned flags,
+typedef enum {
+	OCFS2_WRITE_BUFFER = 0,
+	OCFS2_WRITE_DIRECT,
+	OCFS2_WRITE_MMAP,
+} ocfs2_write_type_t;
+
+int ocfs2_write_begin_nolock(struct address_space *mapping,
+			     loff_t pos, unsigned len, ocfs2_write_type_t type,
 			     struct page **pagep, void **fsdata,
 			     struct buffer_head *di_bh, struct page *mmap_page);
 
@@ -79,7 +84,6 @@ static inline void ocfs2_iocb_set_rw_locked(struct kiocb *iocb, int level)
 enum ocfs2_iocb_lock_bits {
 	OCFS2_IOCB_RW_LOCK = 0,
 	OCFS2_IOCB_RW_LOCK_LEVEL,
-	OCFS2_IOCB_UNALIGNED_IO,
 	OCFS2_IOCB_NUM_LOCKS
 };
 
@@ -88,11 +92,4 @@ enum ocfs2_iocb_lock_bits {
 #define ocfs2_iocb_rw_locked_level(iocb) \
 	test_bit(OCFS2_IOCB_RW_LOCK_LEVEL, (unsigned long *)&iocb->private)
 
-#define ocfs2_iocb_set_unaligned_aio(iocb) \
-	set_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private)
-#define ocfs2_iocb_clear_unaligned_aio(iocb) \
-	clear_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private)
-#define ocfs2_iocb_is_unaligned_aio(iocb) \
-	test_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private)
-
 #endif /* OCFS2_FILE_H */
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index ddddef0021a0..1934abb6b680 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -287,7 +287,6 @@ struct o2hb_bio_wait_ctxt {
 static void o2hb_write_timeout(struct work_struct *work)
 {
 	int failed, quorum;
-	unsigned long flags;
 	struct o2hb_region *reg =
 		container_of(work, struct o2hb_region,
 			     hr_write_timeout_work.work);
@@ -297,14 +296,14 @@ static void o2hb_write_timeout(struct work_struct *work)
 	     jiffies_to_msecs(jiffies - reg->hr_last_timeout_start));
 
 	if (o2hb_global_heartbeat_active()) {
-		spin_lock_irqsave(&o2hb_live_lock, flags);
+		spin_lock(&o2hb_live_lock);
 		if (test_bit(reg->hr_region_num, o2hb_quorum_region_bitmap))
 			set_bit(reg->hr_region_num, o2hb_failed_region_bitmap);
 		failed = bitmap_weight(o2hb_failed_region_bitmap,
 					O2NM_MAX_REGIONS);
 		quorum = bitmap_weight(o2hb_quorum_region_bitmap,
 					O2NM_MAX_REGIONS);
-		spin_unlock_irqrestore(&o2hb_live_lock, flags);
+		spin_unlock(&o2hb_live_lock);
 
 		mlog(ML_HEARTBEAT, "Number of regions %d, failed regions %d\n",
 		     quorum, failed);
@@ -418,13 +417,13 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg,
 	bio->bi_private = wc;
 	bio->bi_end_io = o2hb_bio_end_io;
 
-	vec_start = (cs << bits) % PAGE_CACHE_SIZE;
+	vec_start = (cs << bits) % PAGE_SIZE;
 	while(cs < max_slots) {
 		current_page = cs / spp;
 		page = reg->hr_slot_data[current_page];
 
-		vec_len = min(PAGE_CACHE_SIZE - vec_start,
-			      (max_slots-cs) * (PAGE_CACHE_SIZE/spp) );
+		vec_len = min(PAGE_SIZE - vec_start,
+			      (max_slots-cs) * (PAGE_SIZE/spp) );
 
 		mlog(ML_HB_BIO, "page %d, vec_len = %u, vec_start = %u\n",
 		     current_page, vec_len, vec_start);
@@ -432,7 +431,7 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg,
 		len = bio_add_page(bio, page, vec_len, vec_start);
 		if (len != vec_len) break;
 
-		cs += vec_len / (PAGE_CACHE_SIZE/spp);
+		cs += vec_len / (PAGE_SIZE/spp);
 		vec_start = 0;
 	}
 
@@ -1254,15 +1253,15 @@ static const struct file_operations o2hb_debug_fops = {
 
 void o2hb_exit(void)
 {
-	kfree(o2hb_db_livenodes);
-	kfree(o2hb_db_liveregions);
-	kfree(o2hb_db_quorumregions);
-	kfree(o2hb_db_failedregions);
 	debugfs_remove(o2hb_debug_failedregions);
 	debugfs_remove(o2hb_debug_quorumregions);
 	debugfs_remove(o2hb_debug_liveregions);
 	debugfs_remove(o2hb_debug_livenodes);
 	debugfs_remove(o2hb_debug_dir);
+	kfree(o2hb_db_livenodes);
+	kfree(o2hb_db_liveregions);
+	kfree(o2hb_db_quorumregions);
+	kfree(o2hb_db_failedregions);
 }
 
 static struct dentry *o2hb_debug_create(const char *name, struct dentry *dir,
@@ -1438,13 +1437,15 @@ static void o2hb_region_release(struct config_item *item)
 
 	kfree(reg->hr_slots);
 
-	kfree(reg->hr_db_regnum);
-	kfree(reg->hr_db_livenodes);
 	debugfs_remove(reg->hr_debug_livenodes);
 	debugfs_remove(reg->hr_debug_regnum);
 	debugfs_remove(reg->hr_debug_elapsed_time);
 	debugfs_remove(reg->hr_debug_pinned);
 	debugfs_remove(reg->hr_debug_dir);
+	kfree(reg->hr_db_livenodes);
+	kfree(reg->hr_db_regnum);
+	kfree(reg->hr_db_elapsed_time);
+	kfree(reg->hr_db_pinned);
 
 	spin_lock(&o2hb_live_lock);
 	list_del(&reg->hr_all_item);
@@ -1480,16 +1481,17 @@ static int o2hb_read_block_input(struct o2hb_region *reg,
 	return 0;
 }
 
-static ssize_t o2hb_region_block_bytes_read(struct o2hb_region *reg,
+static ssize_t o2hb_region_block_bytes_show(struct config_item *item,
 					    char *page)
 {
-	return sprintf(page, "%u\n", reg->hr_block_bytes);
+	return sprintf(page, "%u\n", to_o2hb_region(item)->hr_block_bytes);
 }
 
-static ssize_t o2hb_region_block_bytes_write(struct o2hb_region *reg,
+static ssize_t o2hb_region_block_bytes_store(struct config_item *item,
 					     const char *page,
 					     size_t count)
 {
+	struct o2hb_region *reg = to_o2hb_region(item);
 	int status;
 	unsigned long block_bytes;
 	unsigned int block_bits;
@@ -1508,16 +1510,17 @@ static ssize_t o2hb_region_block_bytes_write(struct o2hb_region *reg,
 	return count;
 }
 
-static ssize_t o2hb_region_start_block_read(struct o2hb_region *reg,
+static ssize_t o2hb_region_start_block_show(struct config_item *item,
 					    char *page)
 {
-	return sprintf(page, "%llu\n", reg->hr_start_block);
+	return sprintf(page, "%llu\n", to_o2hb_region(item)->hr_start_block);
 }
 
-static ssize_t o2hb_region_start_block_write(struct o2hb_region *reg,
+static ssize_t o2hb_region_start_block_store(struct config_item *item,
 					     const char *page,
 					     size_t count)
 {
+	struct o2hb_region *reg = to_o2hb_region(item);
 	unsigned long long tmp;
 	char *p = (char *)page;
 
@@ -1533,16 +1536,16 @@ static ssize_t o2hb_region_start_block_write(struct o2hb_region *reg,
 	return count;
 }
 
-static ssize_t o2hb_region_blocks_read(struct o2hb_region *reg,
-				       char *page)
+static ssize_t o2hb_region_blocks_show(struct config_item *item, char *page)
 {
-	return sprintf(page, "%d\n", reg->hr_blocks);
+	return sprintf(page, "%d\n", to_o2hb_region(item)->hr_blocks);
 }
 
-static ssize_t o2hb_region_blocks_write(struct o2hb_region *reg,
+static ssize_t o2hb_region_blocks_store(struct config_item *item,
 					const char *page,
 					size_t count)
 {
+	struct o2hb_region *reg = to_o2hb_region(item);
 	unsigned long tmp;
 	char *p = (char *)page;
 
@@ -1561,20 +1564,19 @@ static ssize_t o2hb_region_blocks_write(struct o2hb_region *reg,
 	return count;
 }
 
-static ssize_t o2hb_region_dev_read(struct o2hb_region *reg,
-				    char *page)
+static ssize_t o2hb_region_dev_show(struct config_item *item, char *page)
 {
 	unsigned int ret = 0;
 
-	if (reg->hr_bdev)
-		ret = sprintf(page, "%s\n", reg->hr_dev_name);
+	if (to_o2hb_region(item)->hr_bdev)
+		ret = sprintf(page, "%s\n", to_o2hb_region(item)->hr_dev_name);
 
 	return ret;
 }
 
 static void o2hb_init_region_params(struct o2hb_region *reg)
 {
-	reg->hr_slots_per_page = PAGE_CACHE_SIZE >> reg->hr_block_bits;
+	reg->hr_slots_per_page = PAGE_SIZE >> reg->hr_block_bits;
 	reg->hr_timeout_ms = O2HB_REGION_TIMEOUT_MS;
 
 	mlog(ML_HEARTBEAT, "hr_start_block = %llu, hr_blocks = %u\n",
@@ -1677,10 +1679,11 @@ out:
 }
 
 /* this is acting as commit; we set up all of hr_bdev and hr_task or nothing */
-static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
+static ssize_t o2hb_region_dev_store(struct config_item *item,
 				     const char *page,
 				     size_t count)
 {
+	struct o2hb_region *reg = to_o2hb_region(item);
 	struct task_struct *hb_task;
 	long fd;
 	int sectsize;
@@ -1778,8 +1781,8 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
 	}
 	++live_threshold;
 	atomic_set(&reg->hr_steady_iterations, live_threshold);
-	/* unsteady_iterations is double the steady_iterations */
-	atomic_set(&reg->hr_unsteady_iterations, (live_threshold << 1));
+	/* unsteady_iterations is triple the steady_iterations */
+	atomic_set(&reg->hr_unsteady_iterations, (live_threshold * 3));
 
 	hb_task = kthread_run(o2hb_thread, reg, "o2hb-%s",
 			      reg->hr_item.ci_name);
@@ -1841,9 +1844,9 @@ out:
 	return ret;
 }
 
-static ssize_t o2hb_region_pid_read(struct o2hb_region *reg,
-                                      char *page)
+static ssize_t o2hb_region_pid_show(struct config_item *item, char *page)
 {
+	struct o2hb_region *reg = to_o2hb_region(item);
 	pid_t pid = 0;
 
 	spin_lock(&o2hb_live_lock);
@@ -1857,92 +1860,23 @@ static ssize_t o2hb_region_pid_read(struct o2hb_region *reg,
 	return sprintf(page, "%u\n", pid);
 }
 
-struct o2hb_region_attribute {
-	struct configfs_attribute attr;
-	ssize_t (*show)(struct o2hb_region *, char *);
-	ssize_t (*store)(struct o2hb_region *, const char *, size_t);
-};
-
-static struct o2hb_region_attribute o2hb_region_attr_block_bytes = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "block_bytes",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2hb_region_block_bytes_read,
-	.store	= o2hb_region_block_bytes_write,
-};
-
-static struct o2hb_region_attribute o2hb_region_attr_start_block = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "start_block",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2hb_region_start_block_read,
-	.store	= o2hb_region_start_block_write,
-};
-
-static struct o2hb_region_attribute o2hb_region_attr_blocks = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "blocks",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2hb_region_blocks_read,
-	.store	= o2hb_region_blocks_write,
-};
-
-static struct o2hb_region_attribute o2hb_region_attr_dev = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "dev",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2hb_region_dev_read,
-	.store	= o2hb_region_dev_write,
-};
-
-static struct o2hb_region_attribute o2hb_region_attr_pid = {
-       .attr   = { .ca_owner = THIS_MODULE,
-                   .ca_name = "pid",
-                   .ca_mode = S_IRUGO | S_IRUSR },
-       .show   = o2hb_region_pid_read,
-};
+CONFIGFS_ATTR(o2hb_region_, block_bytes);
+CONFIGFS_ATTR(o2hb_region_, start_block);
+CONFIGFS_ATTR(o2hb_region_, blocks);
+CONFIGFS_ATTR(o2hb_region_, dev);
+CONFIGFS_ATTR_RO(o2hb_region_, pid);
 
 static struct configfs_attribute *o2hb_region_attrs[] = {
-	&o2hb_region_attr_block_bytes.attr,
-	&o2hb_region_attr_start_block.attr,
-	&o2hb_region_attr_blocks.attr,
-	&o2hb_region_attr_dev.attr,
-	&o2hb_region_attr_pid.attr,
+	&o2hb_region_attr_block_bytes,
+	&o2hb_region_attr_start_block,
+	&o2hb_region_attr_blocks,
+	&o2hb_region_attr_dev,
+	&o2hb_region_attr_pid,
 	NULL,
 };
 
-static ssize_t o2hb_region_show(struct config_item *item,
-				struct configfs_attribute *attr,
-				char *page)
-{
-	struct o2hb_region *reg = to_o2hb_region(item);
-	struct o2hb_region_attribute *o2hb_region_attr =
-		container_of(attr, struct o2hb_region_attribute, attr);
-	ssize_t ret = 0;
-
-	if (o2hb_region_attr->show)
-		ret = o2hb_region_attr->show(reg, page);
-	return ret;
-}
-
-static ssize_t o2hb_region_store(struct config_item *item,
-				 struct configfs_attribute *attr,
-				 const char *page, size_t count)
-{
-	struct o2hb_region *reg = to_o2hb_region(item);
-	struct o2hb_region_attribute *o2hb_region_attr =
-		container_of(attr, struct o2hb_region_attribute, attr);
-	ssize_t ret = -EINVAL;
-
-	if (o2hb_region_attr->store)
-		ret = o2hb_region_attr->store(reg, page, count);
-	return ret;
-}
-
 static struct configfs_item_operations o2hb_region_item_ops = {
 	.release		= o2hb_region_release,
-	.show_attribute		= o2hb_region_show,
-	.store_attribute	= o2hb_region_store,
 };
 
 static struct config_item_type o2hb_region_type = {
@@ -2137,49 +2071,14 @@ unlock:
 	spin_unlock(&o2hb_live_lock);
 }
 
-struct o2hb_heartbeat_group_attribute {
-	struct configfs_attribute attr;
-	ssize_t (*show)(struct o2hb_heartbeat_group *, char *);
-	ssize_t (*store)(struct o2hb_heartbeat_group *, const char *, size_t);
-};
-
-static ssize_t o2hb_heartbeat_group_show(struct config_item *item,
-					 struct configfs_attribute *attr,
-					 char *page)
-{
-	struct o2hb_heartbeat_group *reg = to_o2hb_heartbeat_group(to_config_group(item));
-	struct o2hb_heartbeat_group_attribute *o2hb_heartbeat_group_attr =
-		container_of(attr, struct o2hb_heartbeat_group_attribute, attr);
-	ssize_t ret = 0;
-
-	if (o2hb_heartbeat_group_attr->show)
-		ret = o2hb_heartbeat_group_attr->show(reg, page);
-	return ret;
-}
-
-static ssize_t o2hb_heartbeat_group_store(struct config_item *item,
-					  struct configfs_attribute *attr,
-					  const char *page, size_t count)
-{
-	struct o2hb_heartbeat_group *reg = to_o2hb_heartbeat_group(to_config_group(item));
-	struct o2hb_heartbeat_group_attribute *o2hb_heartbeat_group_attr =
-		container_of(attr, struct o2hb_heartbeat_group_attribute, attr);
-	ssize_t ret = -EINVAL;
-
-	if (o2hb_heartbeat_group_attr->store)
-		ret = o2hb_heartbeat_group_attr->store(reg, page, count);
-	return ret;
-}
-
-static ssize_t o2hb_heartbeat_group_threshold_show(struct o2hb_heartbeat_group *group,
-						     char *page)
+static ssize_t o2hb_heartbeat_group_threshold_show(struct config_item *item,
+		char *page)
 {
 	return sprintf(page, "%u\n", o2hb_dead_threshold);
 }
 
-static ssize_t o2hb_heartbeat_group_threshold_store(struct o2hb_heartbeat_group *group,
-						    const char *page,
-						    size_t count)
+static ssize_t o2hb_heartbeat_group_threshold_store(struct config_item *item,
+		const char *page, size_t count)
 {
 	unsigned long tmp;
 	char *p = (char *)page;
@@ -2194,17 +2093,15 @@ static ssize_t o2hb_heartbeat_group_threshold_store(struct o2hb_heartbeat_group
 	return count;
 }
 
-static
-ssize_t o2hb_heartbeat_group_mode_show(struct o2hb_heartbeat_group *group,
-				       char *page)
+static ssize_t o2hb_heartbeat_group_mode_show(struct config_item *item,
+		char *page)
 {
 	return sprintf(page, "%s\n",
 		       o2hb_heartbeat_mode_desc[o2hb_heartbeat_mode]);
 }
 
-static
-ssize_t o2hb_heartbeat_group_mode_store(struct o2hb_heartbeat_group *group,
-					const char *page, size_t count)
+static ssize_t o2hb_heartbeat_group_mode_store(struct config_item *item,
+		const char *page, size_t count)
 {
 	unsigned int i;
 	int ret;
@@ -2229,33 +2126,15 @@ ssize_t o2hb_heartbeat_group_mode_store(struct o2hb_heartbeat_group *group,
 
 }
 
-static struct o2hb_heartbeat_group_attribute o2hb_heartbeat_group_attr_threshold = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "dead_threshold",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2hb_heartbeat_group_threshold_show,
-	.store	= o2hb_heartbeat_group_threshold_store,
-};
-
-static struct o2hb_heartbeat_group_attribute o2hb_heartbeat_group_attr_mode = {
-	.attr   = { .ca_owner = THIS_MODULE,
-		.ca_name = "mode",
-		.ca_mode = S_IRUGO | S_IWUSR },
-	.show   = o2hb_heartbeat_group_mode_show,
-	.store  = o2hb_heartbeat_group_mode_store,
-};
+CONFIGFS_ATTR(o2hb_heartbeat_group_, threshold);
+CONFIGFS_ATTR(o2hb_heartbeat_group_, mode);
 
 static struct configfs_attribute *o2hb_heartbeat_group_attrs[] = {
-	&o2hb_heartbeat_group_attr_threshold.attr,
-	&o2hb_heartbeat_group_attr_mode.attr,
+	&o2hb_heartbeat_group_attr_threshold,
+	&o2hb_heartbeat_group_attr_mode,
 	NULL,
 };
 
-static struct configfs_item_operations o2hb_heartbeat_group_item_ops = {
-	.show_attribute		= o2hb_heartbeat_group_show,
-	.store_attribute	= o2hb_heartbeat_group_store,
-};
-
 static struct configfs_group_operations o2hb_heartbeat_group_group_ops = {
 	.make_item	= o2hb_heartbeat_group_make_item,
 	.drop_item	= o2hb_heartbeat_group_drop_item,
@@ -2263,7 +2142,6 @@ static struct configfs_group_operations o2hb_heartbeat_group_group_ops = {
 
 static struct config_item_type o2hb_heartbeat_group_type = {
 	.ct_group_ops	= &o2hb_heartbeat_group_group_ops,
-	.ct_item_ops	= &o2hb_heartbeat_group_item_ops,
 	.ct_attrs	= o2hb_heartbeat_group_attrs,
 	.ct_owner	= THIS_MODULE,
 };
@@ -2546,11 +2424,10 @@ EXPORT_SYMBOL_GPL(o2hb_check_node_heartbeating);
 int o2hb_check_node_heartbeating_no_sem(u8 node_num)
 {
 	unsigned long testing_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
-	unsigned long flags;
 
-	spin_lock_irqsave(&o2hb_live_lock, flags);
+	spin_lock(&o2hb_live_lock);
 	o2hb_fill_node_map_from_callback(testing_map, sizeof(testing_map));
-	spin_unlock_irqrestore(&o2hb_live_lock, flags);
+	spin_unlock(&o2hb_live_lock);
 	if (!test_bit(node_num, testing_map)) {
 		mlog(ML_HEARTBEAT,
 		     "node (%u) does not have heartbeating enabled.\n",
diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c
index 441c84e169e6..b17d180bdc16 100644
--- a/fs/ocfs2/cluster/nodemanager.c
+++ b/fs/ocfs2/cluster/nodemanager.c
@@ -172,9 +172,9 @@ static void o2nm_node_release(struct config_item *item)
 	kfree(node);
 }
 
-static ssize_t o2nm_node_num_read(struct o2nm_node *node, char *page)
+static ssize_t o2nm_node_num_show(struct config_item *item, char *page)
 {
-	return sprintf(page, "%d\n", node->nd_num);
+	return sprintf(page, "%d\n", to_o2nm_node(item)->nd_num);
 }
 
 static struct o2nm_cluster *to_o2nm_cluster_from_node(struct o2nm_node *node)
@@ -188,15 +188,16 @@ enum {
 	O2NM_NODE_ATTR_NUM = 0,
 	O2NM_NODE_ATTR_PORT,
 	O2NM_NODE_ATTR_ADDRESS,
-	O2NM_NODE_ATTR_LOCAL,
 };
 
-static ssize_t o2nm_node_num_write(struct o2nm_node *node, const char *page,
+static ssize_t o2nm_node_num_store(struct config_item *item, const char *page,
 				   size_t count)
 {
+	struct o2nm_node *node = to_o2nm_node(item);
 	struct o2nm_cluster *cluster = to_o2nm_cluster_from_node(node);
 	unsigned long tmp;
 	char *p = (char *)page;
+	int ret = 0;
 
 	tmp = simple_strtoul(p, &p, 0);
 	if (!p || (*p && (*p != '\n')))
@@ -215,26 +216,30 @@ static ssize_t o2nm_node_num_write(struct o2nm_node *node, const char *page,
 
 	write_lock(&cluster->cl_nodes_lock);
 	if (cluster->cl_nodes[tmp])
-		p = NULL;
+		ret = -EEXIST;
+	else if (test_and_set_bit(O2NM_NODE_ATTR_NUM,
+			&node->nd_set_attributes))
+		ret = -EBUSY;
 	else  {
 		cluster->cl_nodes[tmp] = node;
 		node->nd_num = tmp;
 		set_bit(tmp, cluster->cl_nodes_bitmap);
 	}
 	write_unlock(&cluster->cl_nodes_lock);
-	if (p == NULL)
-		return -EEXIST;
+	if (ret)
+		return ret;
 
 	return count;
 }
-static ssize_t o2nm_node_ipv4_port_read(struct o2nm_node *node, char *page)
+static ssize_t o2nm_node_ipv4_port_show(struct config_item *item, char *page)
 {
-	return sprintf(page, "%u\n", ntohs(node->nd_ipv4_port));
+	return sprintf(page, "%u\n", ntohs(to_o2nm_node(item)->nd_ipv4_port));
 }
 
-static ssize_t o2nm_node_ipv4_port_write(struct o2nm_node *node,
+static ssize_t o2nm_node_ipv4_port_store(struct config_item *item,
 					 const char *page, size_t count)
 {
+	struct o2nm_node *node = to_o2nm_node(item);
 	unsigned long tmp;
 	char *p = (char *)page;
 
@@ -247,20 +252,23 @@ static ssize_t o2nm_node_ipv4_port_write(struct o2nm_node *node,
 	if (tmp >= (u16)-1)
 		return -ERANGE;
 
+	if (test_and_set_bit(O2NM_NODE_ATTR_PORT, &node->nd_set_attributes))
+		return -EBUSY;
 	node->nd_ipv4_port = htons(tmp);
 
 	return count;
 }
 
-static ssize_t o2nm_node_ipv4_address_read(struct o2nm_node *node, char *page)
+static ssize_t o2nm_node_ipv4_address_show(struct config_item *item, char *page)
 {
-	return sprintf(page, "%pI4\n", &node->nd_ipv4_address);
+	return sprintf(page, "%pI4\n", &to_o2nm_node(item)->nd_ipv4_address);
 }
 
-static ssize_t o2nm_node_ipv4_address_write(struct o2nm_node *node,
+static ssize_t o2nm_node_ipv4_address_store(struct config_item *item,
 					    const char *page,
 					    size_t count)
 {
+	struct o2nm_node *node = to_o2nm_node(item);
 	struct o2nm_cluster *cluster = to_o2nm_cluster_from_node(node);
 	int ret, i;
 	struct rb_node **p, *parent;
@@ -282,6 +290,9 @@ static ssize_t o2nm_node_ipv4_address_write(struct o2nm_node *node,
 	write_lock(&cluster->cl_nodes_lock);
 	if (o2nm_node_ip_tree_lookup(cluster, ipv4_addr, &p, &parent))
 		ret = -EEXIST;
+	else if (test_and_set_bit(O2NM_NODE_ATTR_ADDRESS,
+			&node->nd_set_attributes))
+		ret = -EBUSY;
 	else {
 		rb_link_node(&node->nd_ip_node, parent, p);
 		rb_insert_color(&node->nd_ip_node, &cluster->cl_node_ip_tree);
@@ -295,14 +306,15 @@ static ssize_t o2nm_node_ipv4_address_write(struct o2nm_node *node,
 	return count;
 }
 
-static ssize_t o2nm_node_local_read(struct o2nm_node *node, char *page)
+static ssize_t o2nm_node_local_show(struct config_item *item, char *page)
 {
-	return sprintf(page, "%d\n", node->nd_local);
+	return sprintf(page, "%d\n", to_o2nm_node(item)->nd_local);
 }
 
-static ssize_t o2nm_node_local_write(struct o2nm_node *node, const char *page,
+static ssize_t o2nm_node_local_store(struct config_item *item, const char *page,
 				     size_t count)
 {
+	struct o2nm_node *node = to_o2nm_node(item);
 	struct o2nm_cluster *cluster = to_o2nm_cluster_from_node(node);
 	unsigned long tmp;
 	char *p = (char *)page;
@@ -349,108 +361,21 @@ static ssize_t o2nm_node_local_write(struct o2nm_node *node, const char *page,
 	return count;
 }
 
-struct o2nm_node_attribute {
-	struct configfs_attribute attr;
-	ssize_t (*show)(struct o2nm_node *, char *);
-	ssize_t (*store)(struct o2nm_node *, const char *, size_t);
-};
-
-static struct o2nm_node_attribute o2nm_node_attr_num = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "num",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2nm_node_num_read,
-	.store	= o2nm_node_num_write,
-};
-
-static struct o2nm_node_attribute o2nm_node_attr_ipv4_port = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "ipv4_port",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2nm_node_ipv4_port_read,
-	.store	= o2nm_node_ipv4_port_write,
-};
-
-static struct o2nm_node_attribute o2nm_node_attr_ipv4_address = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "ipv4_address",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2nm_node_ipv4_address_read,
-	.store	= o2nm_node_ipv4_address_write,
-};
-
-static struct o2nm_node_attribute o2nm_node_attr_local = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "local",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2nm_node_local_read,
-	.store	= o2nm_node_local_write,
-};
+CONFIGFS_ATTR(o2nm_node_, num);
+CONFIGFS_ATTR(o2nm_node_, ipv4_port);
+CONFIGFS_ATTR(o2nm_node_, ipv4_address);
+CONFIGFS_ATTR(o2nm_node_, local);
 
 static struct configfs_attribute *o2nm_node_attrs[] = {
-	[O2NM_NODE_ATTR_NUM] = &o2nm_node_attr_num.attr,
-	[O2NM_NODE_ATTR_PORT] = &o2nm_node_attr_ipv4_port.attr,
-	[O2NM_NODE_ATTR_ADDRESS] = &o2nm_node_attr_ipv4_address.attr,
-	[O2NM_NODE_ATTR_LOCAL] = &o2nm_node_attr_local.attr,
+	&o2nm_node_attr_num,
+	&o2nm_node_attr_ipv4_port,
+	&o2nm_node_attr_ipv4_address,
+	&o2nm_node_attr_local,
 	NULL,
 };
 
-static int o2nm_attr_index(struct configfs_attribute *attr)
-{
-	int i;
-	for (i = 0; i < ARRAY_SIZE(o2nm_node_attrs); i++) {
-		if (attr == o2nm_node_attrs[i])
-			return i;
-	}
-	BUG();
-	return 0;
-}
-
-static ssize_t o2nm_node_show(struct config_item *item,
-			      struct configfs_attribute *attr,
-			      char *page)
-{
-	struct o2nm_node *node = to_o2nm_node(item);
-	struct o2nm_node_attribute *o2nm_node_attr =
-		container_of(attr, struct o2nm_node_attribute, attr);
-	ssize_t ret = 0;
-
-	if (o2nm_node_attr->show)
-		ret = o2nm_node_attr->show(node, page);
-	return ret;
-}
-
-static ssize_t o2nm_node_store(struct config_item *item,
-			       struct configfs_attribute *attr,
-			       const char *page, size_t count)
-{
-	struct o2nm_node *node = to_o2nm_node(item);
-	struct o2nm_node_attribute *o2nm_node_attr =
-		container_of(attr, struct o2nm_node_attribute, attr);
-	ssize_t ret;
-	int attr_index = o2nm_attr_index(attr);
-
-	if (o2nm_node_attr->store == NULL) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (test_bit(attr_index, &node->nd_set_attributes))
-		return -EBUSY;
-
-	ret = o2nm_node_attr->store(node, page, count);
-	if (ret < count)
-		goto out;
-
-	set_bit(attr_index, &node->nd_set_attributes);
-out:
-	return ret;
-}
-
 static struct configfs_item_operations o2nm_node_item_ops = {
 	.release		= o2nm_node_release,
-	.show_attribute		= o2nm_node_show,
-	.store_attribute	= o2nm_node_store,
 };
 
 static struct config_item_type o2nm_node_type = {
@@ -475,12 +400,6 @@ static struct o2nm_node_group *to_o2nm_node_group(struct config_group *group)
 }
 #endif
 
-struct o2nm_cluster_attribute {
-	struct configfs_attribute attr;
-	ssize_t (*show)(struct o2nm_cluster *, char *);
-	ssize_t (*store)(struct o2nm_cluster *, const char *, size_t);
-};
-
 static ssize_t o2nm_cluster_attr_write(const char *page, ssize_t count,
                                        unsigned int *val)
 {
@@ -501,15 +420,16 @@ static ssize_t o2nm_cluster_attr_write(const char *page, ssize_t count,
 	return count;
 }
 
-static ssize_t o2nm_cluster_attr_idle_timeout_ms_read(
-	struct o2nm_cluster *cluster, char *page)
+static ssize_t o2nm_cluster_idle_timeout_ms_show(struct config_item *item,
+	char *page)
 {
-	return sprintf(page, "%u\n", cluster->cl_idle_timeout_ms);
+	return sprintf(page, "%u\n", to_o2nm_cluster(item)->cl_idle_timeout_ms);
 }
 
-static ssize_t o2nm_cluster_attr_idle_timeout_ms_write(
-	struct o2nm_cluster *cluster, const char *page, size_t count)
+static ssize_t o2nm_cluster_idle_timeout_ms_store(struct config_item *item,
+	const char *page, size_t count)
 {
+	struct o2nm_cluster *cluster = to_o2nm_cluster(item);
 	ssize_t ret;
 	unsigned int val;
 
@@ -536,15 +456,17 @@ static ssize_t o2nm_cluster_attr_idle_timeout_ms_write(
 	return ret;
 }
 
-static ssize_t o2nm_cluster_attr_keepalive_delay_ms_read(
-	struct o2nm_cluster *cluster, char *page)
+static ssize_t o2nm_cluster_keepalive_delay_ms_show(
+	struct config_item *item, char *page)
 {
-	return sprintf(page, "%u\n", cluster->cl_keepalive_delay_ms);
+	return sprintf(page, "%u\n",
+			to_o2nm_cluster(item)->cl_keepalive_delay_ms);
 }
 
-static ssize_t o2nm_cluster_attr_keepalive_delay_ms_write(
-	struct o2nm_cluster *cluster, const char *page, size_t count)
+static ssize_t o2nm_cluster_keepalive_delay_ms_store(
+	struct config_item *item, const char *page, size_t count)
 {
+	struct o2nm_cluster *cluster = to_o2nm_cluster(item);
 	ssize_t ret;
 	unsigned int val;
 
@@ -571,22 +493,24 @@ static ssize_t o2nm_cluster_attr_keepalive_delay_ms_write(
 	return ret;
 }
 
-static ssize_t o2nm_cluster_attr_reconnect_delay_ms_read(
-	struct o2nm_cluster *cluster, char *page)
+static ssize_t o2nm_cluster_reconnect_delay_ms_show(
+	struct config_item *item, char *page)
 {
-	return sprintf(page, "%u\n", cluster->cl_reconnect_delay_ms);
+	return sprintf(page, "%u\n",
+			to_o2nm_cluster(item)->cl_reconnect_delay_ms);
 }
 
-static ssize_t o2nm_cluster_attr_reconnect_delay_ms_write(
-	struct o2nm_cluster *cluster, const char *page, size_t count)
+static ssize_t o2nm_cluster_reconnect_delay_ms_store(
+	struct config_item *item, const char *page, size_t count)
 {
 	return o2nm_cluster_attr_write(page, count,
-	                               &cluster->cl_reconnect_delay_ms);
+                               &to_o2nm_cluster(item)->cl_reconnect_delay_ms);
 }
 
-static ssize_t o2nm_cluster_attr_fence_method_read(
-	struct o2nm_cluster *cluster, char *page)
+static ssize_t o2nm_cluster_fence_method_show(
+	struct config_item *item, char *page)
 {
+	struct o2nm_cluster *cluster = to_o2nm_cluster(item);
 	ssize_t ret = 0;
 
 	if (cluster)
@@ -595,8 +519,8 @@ static ssize_t o2nm_cluster_attr_fence_method_read(
 	return ret;
 }
 
-static ssize_t o2nm_cluster_attr_fence_method_write(
-	struct o2nm_cluster *cluster, const char *page, size_t count)
+static ssize_t o2nm_cluster_fence_method_store(
+	struct config_item *item, const char *page, size_t count)
 {
 	unsigned int i;
 
@@ -608,10 +532,10 @@ static ssize_t o2nm_cluster_attr_fence_method_write(
 			continue;
 		if (strncasecmp(page, o2nm_fence_method_desc[i], count - 1))
 			continue;
-		if (cluster->cl_fence_method != i) {
+		if (to_o2nm_cluster(item)->cl_fence_method != i) {
 			printk(KERN_INFO "ocfs2: Changing fence method to %s\n",
 			       o2nm_fence_method_desc[i]);
-			cluster->cl_fence_method = i;
+			to_o2nm_cluster(item)->cl_fence_method = i;
 		}
 		return count;
 	}
@@ -620,79 +544,18 @@ bail:
 	return -EINVAL;
 }
 
-static struct o2nm_cluster_attribute o2nm_cluster_attr_idle_timeout_ms = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "idle_timeout_ms",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2nm_cluster_attr_idle_timeout_ms_read,
-	.store	= o2nm_cluster_attr_idle_timeout_ms_write,
-};
-
-static struct o2nm_cluster_attribute o2nm_cluster_attr_keepalive_delay_ms = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "keepalive_delay_ms",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2nm_cluster_attr_keepalive_delay_ms_read,
-	.store	= o2nm_cluster_attr_keepalive_delay_ms_write,
-};
-
-static struct o2nm_cluster_attribute o2nm_cluster_attr_reconnect_delay_ms = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "reconnect_delay_ms",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2nm_cluster_attr_reconnect_delay_ms_read,
-	.store	= o2nm_cluster_attr_reconnect_delay_ms_write,
-};
-
-static struct o2nm_cluster_attribute o2nm_cluster_attr_fence_method = {
-	.attr	= { .ca_owner = THIS_MODULE,
-		    .ca_name = "fence_method",
-		    .ca_mode = S_IRUGO | S_IWUSR },
-	.show	= o2nm_cluster_attr_fence_method_read,
-	.store	= o2nm_cluster_attr_fence_method_write,
-};
+CONFIGFS_ATTR(o2nm_cluster_, idle_timeout_ms);
+CONFIGFS_ATTR(o2nm_cluster_, keepalive_delay_ms);
+CONFIGFS_ATTR(o2nm_cluster_, reconnect_delay_ms);
+CONFIGFS_ATTR(o2nm_cluster_, fence_method);
 
 static struct configfs_attribute *o2nm_cluster_attrs[] = {
-	&o2nm_cluster_attr_idle_timeout_ms.attr,
-	&o2nm_cluster_attr_keepalive_delay_ms.attr,
-	&o2nm_cluster_attr_reconnect_delay_ms.attr,
-	&o2nm_cluster_attr_fence_method.attr,
+	&o2nm_cluster_attr_idle_timeout_ms,
+	&o2nm_cluster_attr_keepalive_delay_ms,
+	&o2nm_cluster_attr_reconnect_delay_ms,
+	&o2nm_cluster_attr_fence_method,
 	NULL,
 };
-static ssize_t o2nm_cluster_show(struct config_item *item,
-                                 struct configfs_attribute *attr,
-                                 char *page)
-{
-	struct o2nm_cluster *cluster = to_o2nm_cluster(item);
-	struct o2nm_cluster_attribute *o2nm_cluster_attr =
-		container_of(attr, struct o2nm_cluster_attribute, attr);
-	ssize_t ret = 0;
-
-	if (o2nm_cluster_attr->show)
-		ret = o2nm_cluster_attr->show(cluster, page);
-	return ret;
-}
-
-static ssize_t o2nm_cluster_store(struct config_item *item,
-                                  struct configfs_attribute *attr,
-                                  const char *page, size_t count)
-{
-	struct o2nm_cluster *cluster = to_o2nm_cluster(item);
-	struct o2nm_cluster_attribute *o2nm_cluster_attr =
-		container_of(attr, struct o2nm_cluster_attribute, attr);
-	ssize_t ret;
-
-	if (o2nm_cluster_attr->store == NULL) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	ret = o2nm_cluster_attr->store(cluster, page, count);
-	if (ret < count)
-		goto out;
-out:
-	return ret;
-}
 
 static struct config_item *o2nm_node_group_make_item(struct config_group *group,
 						     const char *name)
@@ -767,14 +630,11 @@ static void o2nm_cluster_release(struct config_item *item)
 {
 	struct o2nm_cluster *cluster = to_o2nm_cluster(item);
 
-	kfree(cluster->cl_group.default_groups);
 	kfree(cluster);
 }
 
 static struct configfs_item_operations o2nm_cluster_item_ops = {
 	.release	= o2nm_cluster_release,
-	.show_attribute		= o2nm_cluster_show,
-	.store_attribute	= o2nm_cluster_store,
 };
 
 static struct config_item_type o2nm_cluster_type = {
@@ -805,7 +665,6 @@ static struct config_group *o2nm_cluster_group_make_group(struct config_group *g
 	struct o2nm_cluster *cluster = NULL;
 	struct o2nm_node_group *ns = NULL;
 	struct config_group *o2hb_group = NULL, *ret = NULL;
-	void *defs = NULL;
 
 	/* this runs under the parent dir's i_mutex; there can be only
 	 * one caller in here at a time */
@@ -814,20 +673,18 @@ static struct config_group *o2nm_cluster_group_make_group(struct config_group *g
 
 	cluster = kzalloc(sizeof(struct o2nm_cluster), GFP_KERNEL);
 	ns = kzalloc(sizeof(struct o2nm_node_group), GFP_KERNEL);
-	defs = kcalloc(3, sizeof(struct config_group *), GFP_KERNEL);
 	o2hb_group = o2hb_alloc_hb_set();
-	if (cluster == NULL || ns == NULL || o2hb_group == NULL || defs == NULL)
+	if (cluster == NULL || ns == NULL || o2hb_group == NULL)
 		goto out;
 
 	config_group_init_type_name(&cluster->cl_group, name,
 				    &o2nm_cluster_type);
+	configfs_add_default_group(&ns->ns_group, &cluster->cl_group);
+
 	config_group_init_type_name(&ns->ns_group, "node",
 				    &o2nm_node_group_type);
+	configfs_add_default_group(o2hb_group, &cluster->cl_group);
 
-	cluster->cl_group.default_groups = defs;
-	cluster->cl_group.default_groups[0] = &ns->ns_group;
-	cluster->cl_group.default_groups[1] = o2hb_group;
-	cluster->cl_group.default_groups[2] = NULL;
 	rwlock_init(&cluster->cl_nodes_lock);
 	cluster->cl_node_ip_tree = RB_ROOT;
 	cluster->cl_reconnect_delay_ms = O2NET_RECONNECT_DELAY_MS_DEFAULT;
@@ -843,7 +700,6 @@ out:
 		kfree(cluster);
 		kfree(ns);
 		o2hb_free_hb_set(o2hb_group);
-		kfree(defs);
 		ret = ERR_PTR(-ENOMEM);
 	}
 
@@ -853,18 +709,11 @@ out:
 static void o2nm_cluster_group_drop_item(struct config_group *group, struct config_item *item)
 {
 	struct o2nm_cluster *cluster = to_o2nm_cluster(item);
-	int i;
-	struct config_item *killme;
 
 	BUG_ON(o2nm_single_cluster != cluster);
 	o2nm_single_cluster = NULL;
 
-	for (i = 0; cluster->cl_group.default_groups[i]; i++) {
-		killme = &cluster->cl_group.default_groups[i]->cg_item;
-		cluster->cl_group.default_groups[i] = NULL;
-		config_item_put(killme);
-	}
-
+	configfs_remove_default_groups(&cluster->cl_group);
 	config_item_put(item);
 }
 
@@ -896,7 +745,7 @@ int o2nm_depend_item(struct config_item *item)
 
 void o2nm_undepend_item(struct config_item *item)
 {
-	configfs_undepend_item(&o2nm_cluster_group.cs_subsys, item);
+	configfs_undepend_item(item);
 }
 
 int o2nm_depend_this_node(void)
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index ffecf89c8c1c..e1adf285fc31 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -4361,7 +4361,7 @@ static int ocfs2_dx_dir_remove_index(struct inode *dir,
 		mlog_errno(ret);
 		goto out;
 	}
-	mutex_lock(&dx_alloc_inode->i_mutex);
+	inode_lock(dx_alloc_inode);
 
 	ret = ocfs2_inode_lock(dx_alloc_inode, &dx_alloc_bh, 1);
 	if (ret) {
@@ -4410,7 +4410,7 @@ out_unlock:
 	ocfs2_inode_unlock(dx_alloc_inode, 1);
 
 out_mutex:
-	mutex_unlock(&dx_alloc_inode->i_mutex);
+	inode_unlock(dx_alloc_inode);
 	brelse(dx_alloc_bh);
 out:
 	iput(dx_alloc_inode);
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index e88ccf8c83ff..004f2cbe8f71 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -282,6 +282,7 @@ static inline void __dlm_set_joining_node(struct dlm_ctxt *dlm,
 #define DLM_LOCK_RES_DROPPING_REF         0x00000040
 #define DLM_LOCK_RES_BLOCK_DIRTY          0x00001000
 #define DLM_LOCK_RES_SETREF_INPROG        0x00002000
+#define DLM_LOCK_RES_RECOVERY_WAITING     0x00004000
 
 /* max milliseconds to wait to sync up a network failure with a node death */
 #define DLM_NODE_DEATH_WAIT_MAX (5 * 1000)
@@ -376,17 +377,6 @@ struct dlm_lock
 		 lksb_kernel_allocated:1;
 };
 
-
-#define DLM_LKSB_UNUSED1           0x01
-#define DLM_LKSB_PUT_LVB           0x02
-#define DLM_LKSB_GET_LVB           0x04
-#define DLM_LKSB_UNUSED2           0x08
-#define DLM_LKSB_UNUSED3           0x10
-#define DLM_LKSB_UNUSED4           0x20
-#define DLM_LKSB_UNUSED5           0x40
-#define DLM_LKSB_UNUSED6           0x80
-
-
 enum dlm_lockres_list {
 	DLM_GRANTED_LIST = 0,
 	DLM_CONVERTING_LIST = 1,
@@ -462,6 +452,7 @@ enum {
 	DLM_QUERY_REGION		= 519,
 	DLM_QUERY_NODEINFO		= 520,
 	DLM_BEGIN_EXIT_DOMAIN_MSG	= 521,
+	DLM_DEREF_LOCKRES_DONE		= 522,
 };
 
 struct dlm_reco_node_data
@@ -556,7 +547,7 @@ struct dlm_master_requery
  * };
  *
  * from ../cluster/tcp.h
- *    NET_MAX_PAYLOAD_BYTES  (4096 - sizeof(net_msg))
+ *    O2NET_MAX_PAYLOAD_BYTES  (4096 - sizeof(net_msg))
  *    (roughly 4080 bytes)
  * and sizeof(dlm_migratable_lockres) = 112 bytes
  * and sizeof(dlm_migratable_lock) = 16 bytes
@@ -597,7 +588,7 @@ struct dlm_migratable_lockres
 
 /* from above, 128 bytes
  * for some undetermined future use */
-#define DLM_MIG_LOCKRES_RESERVED   (NET_MAX_PAYLOAD_BYTES - \
+#define DLM_MIG_LOCKRES_RESERVED   (O2NET_MAX_PAYLOAD_BYTES - \
 				    DLM_MIG_LOCKRES_MAX_LEN)
 
 struct dlm_create_lock
@@ -793,6 +784,20 @@ struct dlm_deref_lockres
 	u8 name[O2NM_MAX_NAME_LEN];
 };
 
+enum {
+	DLM_DEREF_RESPONSE_DONE = 0,
+	DLM_DEREF_RESPONSE_INPROG = 1,
+};
+
+struct dlm_deref_lockres_done {
+	u32 pad1;
+	u16 pad2;
+	u8 node_idx;
+	u8 namelen;
+
+	u8 name[O2NM_MAX_NAME_LEN];
+};
+
 static inline enum dlm_status
 __dlm_lockres_state_to_status(struct dlm_lock_resource *res)
 {
@@ -800,7 +805,8 @@ __dlm_lockres_state_to_status(struct dlm_lock_resource *res)
 
 	assert_spin_locked(&res->spinlock);
 
-	if (res->state & DLM_LOCK_RES_RECOVERING)
+	if (res->state & (DLM_LOCK_RES_RECOVERING|
+			DLM_LOCK_RES_RECOVERY_WAITING))
 		status = DLM_RECOVERING;
 	else if (res->state & DLM_LOCK_RES_MIGRATING)
 		status = DLM_MIGRATING;
@@ -979,6 +985,8 @@ int dlm_assert_master_handler(struct o2net_msg *msg, u32 len, void *data,
 void dlm_assert_master_post_handler(int status, void *data, void *ret_data);
 int dlm_deref_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
 			      void **ret_data);
+int dlm_deref_lockres_done_handler(struct o2net_msg *msg, u32 len, void *data,
+			      void **ret_data);
 int dlm_migrate_request_handler(struct o2net_msg *msg, u32 len, void *data,
 				void **ret_data);
 int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
@@ -1020,6 +1028,7 @@ static inline void __dlm_wait_on_lockres(struct dlm_lock_resource *res)
 {
 	__dlm_wait_on_lockres_flags(res, (DLM_LOCK_RES_IN_PROGRESS|
 				    	  DLM_LOCK_RES_RECOVERING|
+					  DLM_LOCK_RES_RECOVERY_WAITING|
 					  DLM_LOCK_RES_MIGRATING));
 }
 
diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c
index e36d63ff1783..cdeafb4e7ed6 100644
--- a/fs/ocfs2/dlm/dlmconvert.c
+++ b/fs/ocfs2/dlm/dlmconvert.c
@@ -212,6 +212,12 @@ grant:
 	if (lock->lksb->flags & DLM_LKSB_PUT_LVB)
 		memcpy(res->lvb, lock->lksb->lvb, DLM_LVB_LEN);
 
+	/*
+	 * Move the lock to the tail because it may be the only lock which has
+	 * an invalid lvb.
+	 */
+	list_move_tail(&lock->list, &res->granted);
+
 	status = DLM_NORMAL;
 	*call_ast = 1;
 	goto unlock_exit;
@@ -262,6 +268,7 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
 				  struct dlm_lock *lock, int flags, int type)
 {
 	enum dlm_status status;
+	u8 old_owner = res->owner;
 
 	mlog(0, "type=%d, convert_type=%d, busy=%d\n", lock->ml.type,
 	     lock->ml.convert_type, res->state & DLM_LOCK_RES_IN_PROGRESS);
@@ -287,6 +294,19 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
 		status = DLM_DENIED;
 		goto bail;
 	}
+
+	if (lock->ml.type == type && lock->ml.convert_type == LKM_IVMODE) {
+		mlog(0, "last convert request returned DLM_RECOVERING, but "
+		     "owner has already queued and sent ast to me. res %.*s, "
+		     "(cookie=%u:%llu, type=%d, conv=%d)\n",
+		     res->lockname.len, res->lockname.name,
+		     dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
+		     dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)),
+		     lock->ml.type, lock->ml.convert_type);
+		status = DLM_NORMAL;
+		goto bail;
+	}
+
 	res->state |= DLM_LOCK_RES_IN_PROGRESS;
 	/* move lock to local convert queue */
 	/* do not alter lock refcount.  switching lists. */
@@ -316,11 +336,19 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
 	spin_lock(&res->spinlock);
 	res->state &= ~DLM_LOCK_RES_IN_PROGRESS;
 	lock->convert_pending = 0;
-	/* if it failed, move it back to granted queue */
+	/* if it failed, move it back to granted queue.
+	 * if master returns DLM_NORMAL and then down before sending ast,
+	 * it may have already been moved to granted queue, reset to
+	 * DLM_RECOVERING and retry convert */
 	if (status != DLM_NORMAL) {
 		if (status != DLM_NOTQUEUED)
 			dlm_error(status);
 		dlm_revert_pending_convert(res, lock);
+	} else if ((res->state & DLM_LOCK_RES_RECOVERING) ||
+			(old_owner != res->owner)) {
+		mlog(0, "res %.*s is in recovering or has been recovered.\n",
+				res->lockname.len, res->lockname.name);
+		status = DLM_RECOVERING;
 	}
 bail:
 	spin_unlock(&res->spinlock);
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 2ee7fe747cea..12e064b8be9a 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -132,10 +132,13 @@ static DECLARE_WAIT_QUEUE_HEAD(dlm_domain_events);
  *	- Message DLM_QUERY_NODEINFO added to allow online node removes
  * New in version 1.2:
  * 	- Message DLM_BEGIN_EXIT_DOMAIN_MSG added to mark start of exit domain
+ * New in version 1.3:
+ *	- Message DLM_DEREF_LOCKRES_DONE added to inform non-master that the
+ *	  refmap is cleared
  */
 static const struct dlm_protocol_version dlm_protocol = {
 	.pv_major = 1,
-	.pv_minor = 2,
+	.pv_minor = 3,
 };
 
 #define DLM_DOMAIN_BACKOFF_MS 200
@@ -1396,7 +1399,7 @@ static int dlm_send_join_cancels(struct dlm_ctxt *dlm,
 				 unsigned int map_size)
 {
 	int status, tmpstat;
-	unsigned int node;
+	int node;
 
 	if (map_size != (BITS_TO_LONGS(O2NM_MAX_NODES) *
 			 sizeof(unsigned long))) {
@@ -1853,7 +1856,13 @@ static int dlm_register_domain_handlers(struct dlm_ctxt *dlm)
 					sizeof(struct dlm_exit_domain),
 					dlm_begin_exit_domain_handler,
 					dlm, NULL, &dlm->dlm_domain_handlers);
+	if (status)
+		goto bail;
 
+	status = o2net_register_handler(DLM_DEREF_LOCKRES_DONE, dlm->key,
+					sizeof(struct dlm_deref_lockres_done),
+					dlm_deref_lockres_done_handler,
+					dlm, NULL, &dlm->dlm_domain_handlers);
 bail:
 	if (status)
 		dlm_unregister_domain_handlers(dlm);
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index ce38b4ccc9ab..9aed6e202201 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -2278,7 +2278,7 @@ int dlm_drop_lockres_ref(struct dlm_ctxt *dlm, struct dlm_lock_resource *res)
 		dlm_print_one_lock_resource(res);
 		BUG();
 	}
-	return ret;
+	return ret ? ret : r;
 }
 
 int dlm_deref_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
@@ -2345,7 +2345,7 @@ int dlm_deref_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
 		     	res->lockname.len, res->lockname.name, node);
 			dlm_print_one_lock_resource(res);
 		}
-		ret = 0;
+		ret = DLM_DEREF_RESPONSE_DONE;
 		goto done;
 	}
 
@@ -2365,7 +2365,7 @@ int dlm_deref_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
 	spin_unlock(&dlm->work_lock);
 
 	queue_work(dlm->dlm_worker, &dlm->dispatched_work);
-	return 0;
+	return DLM_DEREF_RESPONSE_INPROG;
 
 done:
 	if (res)
@@ -2375,6 +2375,122 @@ done:
 	return ret;
 }
 
+int dlm_deref_lockres_done_handler(struct o2net_msg *msg, u32 len, void *data,
+			      void **ret_data)
+{
+	struct dlm_ctxt *dlm = data;
+	struct dlm_deref_lockres_done *deref
+			= (struct dlm_deref_lockres_done *)msg->buf;
+	struct dlm_lock_resource *res = NULL;
+	char *name;
+	unsigned int namelen;
+	int ret = -EINVAL;
+	u8 node;
+	unsigned int hash;
+
+	if (!dlm_grab(dlm))
+		return 0;
+
+	name = deref->name;
+	namelen = deref->namelen;
+	node = deref->node_idx;
+
+	if (namelen > DLM_LOCKID_NAME_MAX) {
+		mlog(ML_ERROR, "Invalid name length!");
+		goto done;
+	}
+	if (deref->node_idx >= O2NM_MAX_NODES) {
+		mlog(ML_ERROR, "Invalid node number: %u\n", node);
+		goto done;
+	}
+
+	hash = dlm_lockid_hash(name, namelen);
+
+	spin_lock(&dlm->spinlock);
+	res = __dlm_lookup_lockres_full(dlm, name, namelen, hash);
+	if (!res) {
+		spin_unlock(&dlm->spinlock);
+		mlog(ML_ERROR, "%s:%.*s: bad lockres name\n",
+		     dlm->name, namelen, name);
+		goto done;
+	}
+
+	spin_lock(&res->spinlock);
+	BUG_ON(!(res->state & DLM_LOCK_RES_DROPPING_REF));
+	if (!list_empty(&res->purge)) {
+		mlog(0, "%s: Removing res %.*s from purgelist\n",
+			dlm->name, res->lockname.len, res->lockname.name);
+		list_del_init(&res->purge);
+		dlm_lockres_put(res);
+		dlm->purge_count--;
+	}
+
+	if (!__dlm_lockres_unused(res)) {
+		mlog(ML_ERROR, "%s: res %.*s in use after deref\n",
+			dlm->name, res->lockname.len, res->lockname.name);
+		__dlm_print_one_lock_resource(res);
+		BUG();
+	}
+
+	__dlm_unhash_lockres(dlm, res);
+
+	spin_lock(&dlm->track_lock);
+	if (!list_empty(&res->tracking))
+		list_del_init(&res->tracking);
+	else {
+		mlog(ML_ERROR, "%s: Resource %.*s not on the Tracking list\n",
+		     dlm->name, res->lockname.len, res->lockname.name);
+		__dlm_print_one_lock_resource(res);
+	}
+	spin_unlock(&dlm->track_lock);
+
+	/* lockres is not in the hash now. drop the flag and wake up
+	 * any processes waiting in dlm_get_lock_resource.
+	 */
+	res->state &= ~DLM_LOCK_RES_DROPPING_REF;
+	spin_unlock(&res->spinlock);
+	wake_up(&res->wq);
+
+	dlm_lockres_put(res);
+
+	spin_unlock(&dlm->spinlock);
+
+done:
+	dlm_put(dlm);
+	return ret;
+}
+
+static void dlm_drop_lockres_ref_done(struct dlm_ctxt *dlm,
+		struct dlm_lock_resource *res, u8 node)
+{
+	struct dlm_deref_lockres_done deref;
+	int ret = 0, r;
+	const char *lockname;
+	unsigned int namelen;
+
+	lockname = res->lockname.name;
+	namelen = res->lockname.len;
+	BUG_ON(namelen > O2NM_MAX_NAME_LEN);
+
+	memset(&deref, 0, sizeof(deref));
+	deref.node_idx = dlm->node_num;
+	deref.namelen = namelen;
+	memcpy(deref.name, lockname, namelen);
+
+	ret = o2net_send_message(DLM_DEREF_LOCKRES_DONE, dlm->key,
+				 &deref, sizeof(deref), node, &r);
+	if (ret < 0) {
+		mlog(ML_ERROR, "%s: res %.*s, error %d send DEREF DONE "
+				" to node %u\n", dlm->name, namelen,
+				lockname, ret, node);
+	} else if (r < 0) {
+		/* ignore the error */
+		mlog(ML_ERROR, "%s: res %.*s, DEREF to node %u got %d\n",
+		     dlm->name, namelen, lockname, node, r);
+		dlm_print_one_lock_resource(res);
+	}
+}
+
 static void dlm_deref_lockres_worker(struct dlm_work_item *item, void *data)
 {
 	struct dlm_ctxt *dlm;
@@ -2388,13 +2504,15 @@ static void dlm_deref_lockres_worker(struct dlm_work_item *item, void *data)
 
 	spin_lock(&res->spinlock);
 	BUG_ON(res->state & DLM_LOCK_RES_DROPPING_REF);
+	__dlm_wait_on_lockres_flags(res, DLM_LOCK_RES_SETREF_INPROG);
 	if (test_bit(node, res->refmap)) {
-		__dlm_wait_on_lockres_flags(res, DLM_LOCK_RES_SETREF_INPROG);
 		dlm_lockres_clear_refmap_bit(dlm, res, node);
 		cleared = 1;
 	}
 	spin_unlock(&res->spinlock);
 
+	dlm_drop_lockres_ref_done(dlm, res, node);
+
 	if (cleared) {
 		mlog(0, "%s:%.*s node %u ref dropped in dispatch\n",
 		     dlm->name, res->lockname.len, res->lockname.name, node);
@@ -2432,7 +2550,8 @@ static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm,
 		return 0;
 
 	/* delay migration when the lockres is in RECOCERING state */
-	if (res->state & DLM_LOCK_RES_RECOVERING)
+	if (res->state & (DLM_LOCK_RES_RECOVERING|
+			DLM_LOCK_RES_RECOVERY_WAITING))
 		return 0;
 
 	if (res->owner != dlm->node_num)
@@ -2519,6 +2638,11 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm,
 	spin_lock(&dlm->master_lock);
 	ret = dlm_add_migration_mle(dlm, res, mle, &oldmle, name,
 				    namelen, target, dlm->node_num);
+	/* get an extra reference on the mle.
+	 * otherwise the assert_master from the new
+	 * master will destroy this.
+	 */
+	dlm_get_mle_inuse(mle);
 	spin_unlock(&dlm->master_lock);
 	spin_unlock(&dlm->spinlock);
 
@@ -2544,7 +2668,7 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm,
 	}
 
 fail:
-	if (oldmle) {
+	if (ret != -EEXIST && oldmle) {
 		/* master is known, detach if not already detached */
 		dlm_mle_detach_hb_events(dlm, oldmle);
 		dlm_put_mle(oldmle);
@@ -2554,6 +2678,7 @@ fail:
 		if (mle_added) {
 			dlm_mle_detach_hb_events(dlm, mle);
 			dlm_put_mle(mle);
+			dlm_put_mle_inuse(mle);
 		} else if (mle) {
 			kmem_cache_free(dlm_mle_cache, mle);
 			mle = NULL;
@@ -2571,17 +2696,6 @@ fail:
 	 * ensure that all assert_master work is flushed. */
 	flush_workqueue(dlm->dlm_worker);
 
-	/* get an extra reference on the mle.
-	 * otherwise the assert_master from the new
-	 * master will destroy this.
-	 * also, make sure that all callers of dlm_get_mle
-	 * take both dlm->spinlock and dlm->master_lock */
-	spin_lock(&dlm->spinlock);
-	spin_lock(&dlm->master_lock);
-	dlm_get_mle_inuse(mle);
-	spin_unlock(&dlm->master_lock);
-	spin_unlock(&dlm->spinlock);
-
 	/* notify new node and send all lock state */
 	/* call send_one_lockres with migration flag.
 	 * this serves as notice to the target node that a
@@ -2843,6 +2957,8 @@ again:
 	res->state &= ~DLM_LOCK_RES_BLOCK_DIRTY;
 	if (!ret)
 		BUG_ON(!(res->state & DLM_LOCK_RES_MIGRATING));
+	else
+		res->migration_pending = 0;
 	spin_unlock(&res->spinlock);
 
 	/*
@@ -3048,7 +3164,7 @@ int dlm_migrate_request_handler(struct o2net_msg *msg, u32 len, void *data,
 	int ret = 0;
 
 	if (!dlm_grab(dlm))
-		return -EINVAL;
+		return 0;
 
 	name = migrate->name;
 	namelen = migrate->namelen;
@@ -3139,7 +3255,8 @@ static int dlm_add_migration_mle(struct dlm_ctxt *dlm,
 				mlog(0, "tried to migrate %.*s, but some "
 				     "process beat me to it\n",
 				     namelen, name);
-				ret = -EEXIST;
+				spin_unlock(&tmp->spinlock);
+				return -EEXIST;
 			} else {
 				/* bad.  2 NODES are trying to migrate! */
 				mlog(ML_ERROR, "migration error  mle: "
@@ -3310,6 +3427,15 @@ top:
 			    mle->new_master != dead_node)
 				continue;
 
+			if (mle->new_master == dead_node && mle->inuse) {
+				mlog(ML_NOTICE, "%s: target %u died during "
+						"migration from %u, the MLE is "
+						"still keep used, ignore it!\n",
+						dlm->name, dead_node,
+						mle->master);
+				continue;
+			}
+
 			/* If we have reached this point, this mle needs to be
 			 * removed from the list and freed. */
 			dlm_clean_migration_mle(dlm, mle);
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 9e4f862d20fe..f6b313898763 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1373,6 +1373,7 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
 	char *buf = NULL;
 	struct dlm_work_item *item = NULL;
 	struct dlm_lock_resource *res = NULL;
+	unsigned int hash;
 
 	if (!dlm_grab(dlm))
 		return -EINVAL;
@@ -1400,11 +1401,26 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
 	/* lookup the lock to see if we have a secondary queue for this
 	 * already...  just add the locks in and this will have its owner
 	 * and RECOVERY flag changed when it completes. */
-	res = dlm_lookup_lockres(dlm, mres->lockname, mres->lockname_len);
+	hash = dlm_lockid_hash(mres->lockname, mres->lockname_len);
+	spin_lock(&dlm->spinlock);
+	res = __dlm_lookup_lockres_full(dlm, mres->lockname, mres->lockname_len,
+			hash);
 	if (res) {
 	 	/* this will get a ref on res */
 		/* mark it as recovering/migrating and hash it */
 		spin_lock(&res->spinlock);
+		if (res->state & DLM_LOCK_RES_DROPPING_REF) {
+			mlog(0, "%s: node is attempting to migrate "
+				"lockres %.*s, but marked as dropping "
+				" ref!\n", dlm->name,
+				mres->lockname_len, mres->lockname);
+			ret = -EINVAL;
+			spin_unlock(&res->spinlock);
+			spin_unlock(&dlm->spinlock);
+			dlm_lockres_put(res);
+			goto leave;
+		}
+
 		if (mres->flags & DLM_MRES_RECOVERY) {
 			res->state |= DLM_LOCK_RES_RECOVERING;
 		} else {
@@ -1421,13 +1437,16 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
 				     mres->lockname_len, mres->lockname);
 				ret = -EFAULT;
 				spin_unlock(&res->spinlock);
+				spin_unlock(&dlm->spinlock);
 				dlm_lockres_put(res);
 				goto leave;
 			}
 			res->state |= DLM_LOCK_RES_MIGRATING;
 		}
 		spin_unlock(&res->spinlock);
+		spin_unlock(&dlm->spinlock);
 	} else {
+		spin_unlock(&dlm->spinlock);
 		/* need to allocate, just like if it was
 		 * mastered here normally  */
 		res = dlm_new_lockres(dlm, mres->lockname, mres->lockname_len);
@@ -2064,7 +2083,6 @@ void dlm_move_lockres_to_recovery_list(struct dlm_ctxt *dlm,
 			dlm_lock_get(lock);
 			if (lock->convert_pending) {
 				/* move converting lock back to granted */
-				BUG_ON(i != DLM_CONVERTING_LIST);
 				mlog(0, "node died with convert pending "
 				     "on %.*s. move back to granted list.\n",
 				     res->lockname.len, res->lockname.name);
@@ -2156,6 +2174,13 @@ static void dlm_finish_local_lockres_recovery(struct dlm_ctxt *dlm,
 	for (i = 0; i < DLM_HASH_BUCKETS; i++) {
 		bucket = dlm_lockres_hash(dlm, i);
 		hlist_for_each_entry(res, bucket, hash_node) {
+			if (res->state & DLM_LOCK_RES_RECOVERY_WAITING) {
+				spin_lock(&res->spinlock);
+				res->state &= ~DLM_LOCK_RES_RECOVERY_WAITING;
+				spin_unlock(&res->spinlock);
+				wake_up(&res->wq);
+			}
+
 			if (!(res->state & DLM_LOCK_RES_RECOVERING))
 				continue;
 
@@ -2293,6 +2318,7 @@ static void dlm_free_dead_locks(struct dlm_ctxt *dlm,
 			     res->lockname.len, res->lockname.name, freed, dead_node);
 			__dlm_print_one_lock_resource(res);
 		}
+		res->state |= DLM_LOCK_RES_RECOVERY_WAITING;
 		dlm_lockres_clear_refmap_bit(dlm, res, dead_node);
 	} else if (test_bit(dead_node, res->refmap)) {
 		mlog(0, "%s:%.*s: dead node %u had a ref, but had "
@@ -2360,6 +2386,8 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
 						break;
 					}
 				}
+				dlm_lockres_clear_refmap_bit(dlm, res,
+						dead_node);
 				spin_unlock(&res->spinlock);
 				continue;
 			}
@@ -2368,14 +2396,16 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
 			dlm_revalidate_lvb(dlm, res, dead_node);
 			if (res->owner == dead_node) {
 				if (res->state & DLM_LOCK_RES_DROPPING_REF) {
-					mlog(ML_NOTICE, "%s: res %.*s, Skip "
-					     "recovery as it is being freed\n",
-					     dlm->name, res->lockname.len,
-					     res->lockname.name);
-				} else
-					dlm_move_lockres_to_recovery_list(dlm,
-									  res);
-
+					mlog(0, "%s:%.*s: owned by "
+						"dead node %u, this node was "
+						"dropping its ref when it died. "
+						"continue, dropping the flag.\n",
+						dlm->name, res->lockname.len,
+						res->lockname.name, dead_node);
+				}
+				res->state &= ~DLM_LOCK_RES_DROPPING_REF;
+				dlm_move_lockres_to_recovery_list(dlm,
+						res);
 			} else if (res->owner == dlm->node_num) {
 				dlm_free_dead_locks(dlm, res, dead_node);
 				__dlm_lockres_calc_usage(dlm, res);
@@ -2450,11 +2480,7 @@ static void __dlm_hb_node_down(struct dlm_ctxt *dlm, int idx)
 	 * perhaps later we can genericize this for other waiters. */
 	wake_up(&dlm->migration_wq);
 
-	if (test_bit(idx, dlm->recovery_map))
-		mlog(0, "domain %s, node %u already added "
-		     "to recovery map!\n", dlm->name, idx);
-	else
-		set_bit(idx, dlm->recovery_map);
+	set_bit(idx, dlm->recovery_map);
 }
 
 void dlm_hb_node_down_cb(struct o2nm_node *node, int idx, void *data)
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index c5f6c241ecd7..68d239ba0c63 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -106,7 +106,8 @@ int __dlm_lockres_unused(struct dlm_lock_resource *res)
 	if (!list_empty(&res->dirty) || res->state & DLM_LOCK_RES_DIRTY)
 		return 0;
 
-	if (res->state & DLM_LOCK_RES_RECOVERING)
+	if (res->state & (DLM_LOCK_RES_RECOVERING|
+			DLM_LOCK_RES_RECOVERY_WAITING))
 		return 0;
 
 	/* Another node has this resource with this node as the master */
@@ -202,6 +203,13 @@ static void dlm_purge_lockres(struct dlm_ctxt *dlm,
 		dlm->purge_count--;
 	}
 
+	if (!master && ret != 0) {
+		mlog(0, "%s: deref %.*s in progress or master goes down\n",
+			dlm->name, res->lockname.len, res->lockname.name);
+		spin_unlock(&res->spinlock);
+		return;
+	}
+
 	if (!__dlm_lockres_unused(res)) {
 		mlog(ML_ERROR, "%s: res %.*s in use after deref\n",
 		     dlm->name, res->lockname.len, res->lockname.name);
@@ -700,7 +708,8 @@ static int dlm_thread(void *data)
 			 * dirty for a short while. */
 			BUG_ON(res->state & DLM_LOCK_RES_MIGRATING);
 			if (res->state & (DLM_LOCK_RES_IN_PROGRESS |
-					  DLM_LOCK_RES_RECOVERING)) {
+					  DLM_LOCK_RES_RECOVERING |
+					  DLM_LOCK_RES_RECOVERY_WAITING)) {
 				/* move it to the tail and keep going */
 				res->state &= ~DLM_LOCK_RES_DIRTY;
 				spin_unlock(&res->spinlock);
diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c
index 2e3c9dbab68c..1082b2c3014b 100644
--- a/fs/ocfs2/dlm/dlmunlock.c
+++ b/fs/ocfs2/dlm/dlmunlock.c
@@ -421,7 +421,7 @@ int dlm_unlock_lock_handler(struct o2net_msg *msg, u32 len, void *data,
 	}
 
 	if (!dlm_grab(dlm))
-		return DLM_REJECTED;
+		return DLM_FORWARD;
 
 	mlog_bug_on_msg(!dlm_domain_fully_joined(dlm),
 			"Domain %s not fully joined!\n", dlm->name);
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index b5cf27dcb18a..47b3b2d4e775 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -571,8 +571,8 @@ static int dlmfs_fill_super(struct super_block * sb,
 			    int silent)
 {
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
-	sb->s_blocksize = PAGE_CACHE_SIZE;
-	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
+	sb->s_blocksize = PAGE_SIZE;
+	sb->s_blocksize_bits = PAGE_SHIFT;
 	sb->s_magic = DLMFS_MAGIC;
 	sb->s_op = &dlmfs_ops;
 	sb->s_root = d_make_root(dlmfs_get_root_inode(sb));
@@ -638,7 +638,7 @@ static int __init init_dlmfs_fs(void)
 	dlmfs_inode_cache = kmem_cache_create("dlmfs_inode_cache",
 				sizeof(struct dlmfs_inode_private),
 				0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
-					SLAB_MEM_SPREAD),
+					SLAB_MEM_SPREAD|SLAB_ACCOUNT),
 				dlmfs_init_once);
 	if (!dlmfs_inode_cache) {
 		status = -ENOMEM;
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 20276e340339..474e57f834e6 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -1390,6 +1390,7 @@ static int __ocfs2_cluster_lock(struct ocfs2_super *osb,
 	unsigned int gen;
 	int noqueue_attempted = 0;
 	int dlm_locked = 0;
+	int kick_dc = 0;
 
 	if (!(lockres->l_flags & OCFS2_LOCK_INITIALIZED)) {
 		mlog_errno(-EINVAL);
@@ -1524,7 +1525,12 @@ update_holders:
 unlock:
 	lockres_clear_flags(lockres, OCFS2_LOCK_UPCONVERT_FINISHING);
 
+	/* ocfs2_unblock_lock reques on seeing OCFS2_LOCK_UPCONVERT_FINISHING */
+	kick_dc = (lockres->l_flags & OCFS2_LOCK_BLOCKED);
+
 	spin_unlock_irqrestore(&lockres->l_lock, flags);
+	if (kick_dc)
+		ocfs2_wake_downconvert_thread(osb);
 out:
 	/*
 	 * This is helping work around a lock inversion between the page lock
@@ -2432,12 +2438,6 @@ bail:
  * done this we have to return AOP_TRUNCATED_PAGE so the aop method
  * that called us can bubble that back up into the VFS who will then
  * immediately retry the aop call.
- *
- * We do a blocking lock and immediate unlock before returning, though, so that
- * the lock has a great chance of being cached on this node by the time the VFS
- * calls back to retry the aop.    This has a potential to livelock as nodes
- * ping locks back and forth, but that's a risk we're willing to take to avoid
- * the lock inversion simply.
  */
 int ocfs2_inode_lock_with_page(struct inode *inode,
 			      struct buffer_head **ret_bh,
@@ -2449,8 +2449,6 @@ int ocfs2_inode_lock_with_page(struct inode *inode,
 	ret = ocfs2_inode_lock_full(inode, ret_bh, ex, OCFS2_LOCK_NONBLOCK);
 	if (ret == -EAGAIN) {
 		unlock_page(page);
-		if (ocfs2_inode_lock(inode, ret_bh, ex) == 0)
-			ocfs2_inode_unlock(inode, ex);
 		ret = AOP_TRUNCATED_PAGE;
 	}
 
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 0e5b4515f92e..5308841756be 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -770,14 +770,14 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
 {
 	struct address_space *mapping = inode->i_mapping;
 	struct page *page;
-	unsigned long index = abs_from >> PAGE_CACHE_SHIFT;
+	unsigned long index = abs_from >> PAGE_SHIFT;
 	handle_t *handle;
 	int ret = 0;
 	unsigned zero_from, zero_to, block_start, block_end;
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
 
 	BUG_ON(abs_from >= abs_to);
-	BUG_ON(abs_to > (((u64)index + 1) << PAGE_CACHE_SHIFT));
+	BUG_ON(abs_to > (((u64)index + 1) << PAGE_SHIFT));
 	BUG_ON(abs_from & (inode->i_blkbits - 1));
 
 	handle = ocfs2_zero_start_ordered_transaction(inode, di_bh);
@@ -794,10 +794,10 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
 	}
 
 	/* Get the offsets within the page that we want to zero */
-	zero_from = abs_from & (PAGE_CACHE_SIZE - 1);
-	zero_to = abs_to & (PAGE_CACHE_SIZE - 1);
+	zero_from = abs_from & (PAGE_SIZE - 1);
+	zero_to = abs_to & (PAGE_SIZE - 1);
 	if (!zero_to)
-		zero_to = PAGE_CACHE_SIZE;
+		zero_to = PAGE_SIZE;
 
 	trace_ocfs2_write_zero_page(
 			(unsigned long long)OCFS2_I(inode)->ip_blkno,
@@ -851,7 +851,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
 
 out_unlock:
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 out_commit_trans:
 	if (handle)
 		ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
@@ -959,7 +959,7 @@ static int ocfs2_zero_extend_range(struct inode *inode, u64 range_start,
 	BUG_ON(range_start >= range_end);
 
 	while (zero_pos < range_end) {
-		next_pos = (zero_pos & PAGE_CACHE_MASK) + PAGE_CACHE_SIZE;
+		next_pos = (zero_pos & PAGE_MASK) + PAGE_SIZE;
 		if (next_pos > range_end)
 			next_pos = range_end;
 		rc = ocfs2_write_zero_page(inode, zero_pos, next_pos, di_bh);
@@ -1302,6 +1302,14 @@ int ocfs2_getattr(struct vfsmount *mnt,
 	}
 
 	generic_fillattr(inode, stat);
+	/*
+	 * If there is inline data in the inode, the inode will normally not
+	 * have data blocks allocated (it may have an external xattr block).
+	 * Report at least one sector for such files, so tools like tar, rsync,
+	 * others don't incorrectly think the file is completely sparse.
+	 */
+	if (unlikely(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL))
+		stat->blocks += (stat->size + 511)>>9;
 
 	/* We set the blksize from the cluster size for performance */
 	stat->blksize = osb->s_clustersize;
@@ -1373,44 +1381,6 @@ out:
 	return ret;
 }
 
-/*
- * Will look for holes and unwritten extents in the range starting at
- * pos for count bytes (inclusive).
- */
-static int ocfs2_check_range_for_holes(struct inode *inode, loff_t pos,
-				       size_t count)
-{
-	int ret = 0;
-	unsigned int extent_flags;
-	u32 cpos, clusters, extent_len, phys_cpos;
-	struct super_block *sb = inode->i_sb;
-
-	cpos = pos >> OCFS2_SB(sb)->s_clustersize_bits;
-	clusters = ocfs2_clusters_for_bytes(sb, pos + count) - cpos;
-
-	while (clusters) {
-		ret = ocfs2_get_clusters(inode, cpos, &phys_cpos, &extent_len,
-					 &extent_flags);
-		if (ret < 0) {
-			mlog_errno(ret);
-			goto out;
-		}
-
-		if (phys_cpos == 0 || (extent_flags & OCFS2_EXT_UNWRITTEN)) {
-			ret = 1;
-			break;
-		}
-
-		if (extent_len > clusters)
-			extent_len = clusters;
-
-		clusters -= extent_len;
-		cpos += extent_len;
-	}
-out:
-	return ret;
-}
-
 static int ocfs2_write_remove_suid(struct inode *inode)
 {
 	int ret;
@@ -1864,7 +1834,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode,
 	if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb))
 		return -EROFS;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	/*
 	 * This prevents concurrent writes on other nodes
@@ -1983,7 +1953,7 @@ out_rw_unlock:
 	ocfs2_rw_unlock(inode, 1);
 
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return ret;
 }
 
@@ -2121,18 +2091,12 @@ out:
 
 static int ocfs2_prepare_inode_for_write(struct file *file,
 					 loff_t pos,
-					 size_t count,
-					 int appending,
-					 int *direct_io,
-					 int *has_refcount)
+					 size_t count)
 {
 	int ret = 0, meta_level = 0;
 	struct dentry *dentry = file->f_path.dentry;
 	struct inode *inode = d_inode(dentry);
 	loff_t end;
-	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
-	int full_coherency = !(osb->s_mount_opt &
-		OCFS2_MOUNT_COHERENCY_BUFFERED);
 
 	/*
 	 * We start with a read level meta lock and only jump to an ex
@@ -2181,10 +2145,6 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 							       pos,
 							       count,
 							       &meta_level);
-			if (has_refcount)
-				*has_refcount = 1;
-			if (direct_io)
-				*direct_io = 0;
 		}
 
 		if (ret < 0) {
@@ -2192,67 +2152,12 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 			goto out_unlock;
 		}
 
-		/*
-		 * Skip the O_DIRECT checks if we don't need
-		 * them.
-		 */
-		if (!direct_io || !(*direct_io))
-			break;
-
-		/*
-		 * There's no sane way to do direct writes to an inode
-		 * with inline data.
-		 */
-		if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
-			*direct_io = 0;
-			break;
-		}
-
-		/*
-		 * Allowing concurrent direct writes means
-		 * i_size changes wouldn't be synchronized, so
-		 * one node could wind up truncating another
-		 * nodes writes.
-		 */
-		if (end > i_size_read(inode) && !full_coherency) {
-			*direct_io = 0;
-			break;
-		}
-
-		/*
-		 * Fallback to old way if the feature bit is not set.
-		 */
-		if (end > i_size_read(inode) &&
-				!ocfs2_supports_append_dio(osb)) {
-			*direct_io = 0;
-			break;
-		}
-
-		/*
-		 * We don't fill holes during direct io, so
-		 * check for them here. If any are found, the
-		 * caller will have to retake some cluster
-		 * locks and initiate the io as buffered.
-		 */
-		ret = ocfs2_check_range_for_holes(inode, pos, count);
-		if (ret == 1) {
-			/*
-			 * Fallback to old way if the feature bit is not set.
-			 * Otherwise try dio first and then complete the rest
-			 * request through buffer io.
-			 */
-			if (!ocfs2_supports_append_dio(osb))
-				*direct_io = 0;
-			ret = 0;
-		} else if (ret < 0)
-			mlog_errno(ret);
 		break;
 	}
 
 out_unlock:
 	trace_ocfs2_prepare_inode_for_write(OCFS2_I(inode)->ip_blkno,
-					    pos, appending, count,
-					    direct_io, has_refcount);
+					    pos, count);
 
 	if (meta_level >= 0)
 		ocfs2_inode_unlock(inode, meta_level);
@@ -2264,18 +2169,16 @@ out:
 static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 				    struct iov_iter *from)
 {
-	int direct_io, appending, rw_level;
-	int can_do_direct, has_refcount = 0;
+	int direct_io, rw_level;
 	ssize_t written = 0;
 	ssize_t ret;
-	size_t count = iov_iter_count(from), orig_count;
+	size_t count = iov_iter_count(from);
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	int full_coherency = !(osb->s_mount_opt &
 			       OCFS2_MOUNT_COHERENCY_BUFFERED);
-	int unaligned_dio = 0;
-	int dropped_dio = 0;
+	void *saved_ki_complete = NULL;
 	int append_write = ((iocb->ki_pos + count) >=
 			i_size_read(inode) ? 1 : 0);
 
@@ -2288,12 +2191,10 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 	if (count == 0)
 		return 0;
 
-	appending = iocb->ki_flags & IOCB_APPEND ? 1 : 0;
 	direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
-relock:
 	/*
 	 * Concurrent O_DIRECT writes are allowed with
 	 * mount_option "coherency=buffered".
@@ -2326,7 +2227,6 @@ relock:
 		ocfs2_inode_unlock(inode, 1);
 	}
 
-	orig_count = iov_iter_count(from);
 	ret = generic_write_checks(iocb, from);
 	if (ret <= 0) {
 		if (ret)
@@ -2335,41 +2235,18 @@ relock:
 	}
 	count = ret;
 
-	can_do_direct = direct_io;
-	ret = ocfs2_prepare_inode_for_write(file, iocb->ki_pos, count, appending,
-					    &can_do_direct, &has_refcount);
+	ret = ocfs2_prepare_inode_for_write(file, iocb->ki_pos, count);
 	if (ret < 0) {
 		mlog_errno(ret);
 		goto out;
 	}
 
-	if (direct_io && !is_sync_kiocb(iocb))
-		unaligned_dio = ocfs2_is_io_unaligned(inode, count, iocb->ki_pos);
-
-	/*
-	 * We can't complete the direct I/O as requested, fall back to
-	 * buffered I/O.
-	 */
-	if (direct_io && !can_do_direct) {
-		ocfs2_rw_unlock(inode, rw_level);
-
-		rw_level = -1;
-
-		direct_io = 0;
-		iocb->ki_flags &= ~IOCB_DIRECT;
-		iov_iter_reexpand(from, orig_count);
-		dropped_dio = 1;
-		goto relock;
-	}
-
-	if (unaligned_dio) {
+	if (direct_io && !is_sync_kiocb(iocb) &&
+	    ocfs2_is_io_unaligned(inode, count, iocb->ki_pos)) {
 		/*
-		 * Wait on previous unaligned aio to complete before
-		 * proceeding.
+		 * Make it a sync io if it's an unaligned aio.
 		 */
-		mutex_lock(&OCFS2_I(inode)->ip_unaligned_aio);
-		/* Mark the iocb as needing an unlock in ocfs2_dio_end_io */
-		ocfs2_iocb_set_unaligned_aio(iocb);
+		saved_ki_complete = xchg(&iocb->ki_complete, NULL);
 	}
 
 	/* communicate with ocfs2_dio_end_io */
@@ -2390,14 +2267,13 @@ relock:
 	 */
 	if ((written == -EIOCBQUEUED) || (!ocfs2_iocb_is_rw_locked(iocb))) {
 		rw_level = -1;
-		unaligned_dio = 0;
 	}
 
 	if (unlikely(written <= 0))
-		goto no_sync;
+		goto out;
 
 	if (((file->f_flags & O_DSYNC) && !direct_io) ||
-	    IS_SYNC(inode) || dropped_dio) {
+	    IS_SYNC(inode)) {
 		ret = filemap_fdatawrite_range(file->f_mapping,
 					       iocb->ki_pos - written,
 					       iocb->ki_pos - 1);
@@ -2416,18 +2292,15 @@ relock:
 						      iocb->ki_pos - 1);
 	}
 
-no_sync:
-	if (unaligned_dio && ocfs2_iocb_is_unaligned_aio(iocb)) {
-		ocfs2_iocb_clear_unaligned_aio(iocb);
-		mutex_unlock(&OCFS2_I(inode)->ip_unaligned_aio);
-	}
-
 out:
+	if (saved_ki_complete)
+		xchg(&iocb->ki_complete, saved_ki_complete);
+
 	if (rw_level != -1)
 		ocfs2_rw_unlock(inode, rw_level);
 
 out_mutex:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	if (written)
 		ret = written;
@@ -2539,7 +2412,7 @@ static loff_t ocfs2_file_llseek(struct file *file, loff_t offset, int whence)
 	struct inode *inode = file->f_mapping->host;
 	int ret = 0;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	switch (whence) {
 	case SEEK_SET:
@@ -2577,7 +2450,7 @@ static loff_t ocfs2_file_llseek(struct file *file, loff_t offset, int whence)
 	offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
 
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	if (ret)
 		return ret;
 	return offset;
diff --git a/fs/ocfs2/filecheck.c b/fs/ocfs2/filecheck.c
new file mode 100644
index 000000000000..2cabbcf2f28e
--- /dev/null
+++ b/fs/ocfs2/filecheck.c
@@ -0,0 +1,606 @@
+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * filecheck.c
+ *
+ * Code which implements online file check.
+ *
+ * Copyright (C) 2016 SuSE.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License as published by the Free Software Foundation, version 2.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/kmod.h>
+#include <linux/fs.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+#include <linux/sysctl.h>
+#include <cluster/masklog.h>
+
+#include "ocfs2.h"
+#include "ocfs2_fs.h"
+#include "stackglue.h"
+#include "inode.h"
+
+#include "filecheck.h"
+
+
+/* File check error strings,
+ * must correspond with error number in header file.
+ */
+static const char * const ocfs2_filecheck_errs[] = {
+	"SUCCESS",
+	"FAILED",
+	"INPROGRESS",
+	"READONLY",
+	"INJBD",
+	"INVALIDINO",
+	"BLOCKECC",
+	"BLOCKNO",
+	"VALIDFLAG",
+	"GENERATION",
+	"UNSUPPORTED"
+};
+
+static DEFINE_SPINLOCK(ocfs2_filecheck_sysfs_lock);
+static LIST_HEAD(ocfs2_filecheck_sysfs_list);
+
+struct ocfs2_filecheck {
+	struct list_head fc_head;	/* File check entry list head */
+	spinlock_t fc_lock;
+	unsigned int fc_max;	/* Maximum number of entry in list */
+	unsigned int fc_size;	/* Current entry count in list */
+	unsigned int fc_done;	/* Finished entry count in list */
+};
+
+struct ocfs2_filecheck_sysfs_entry {	/* sysfs entry per mounting */
+	struct list_head fs_list;
+	atomic_t fs_count;
+	struct super_block *fs_sb;
+	struct kset *fs_devicekset;
+	struct kset *fs_fcheckkset;
+	struct ocfs2_filecheck *fs_fcheck;
+};
+
+#define OCFS2_FILECHECK_MAXSIZE		100
+#define OCFS2_FILECHECK_MINSIZE		10
+
+/* File check operation type */
+enum {
+	OCFS2_FILECHECK_TYPE_CHK = 0,	/* Check a file(inode) */
+	OCFS2_FILECHECK_TYPE_FIX,	/* Fix a file(inode) */
+	OCFS2_FILECHECK_TYPE_SET = 100	/* Set entry list maximum size */
+};
+
+struct ocfs2_filecheck_entry {
+	struct list_head fe_list;
+	unsigned long fe_ino;
+	unsigned int fe_type;
+	unsigned int fe_done:1;
+	unsigned int fe_status:31;
+};
+
+struct ocfs2_filecheck_args {
+	unsigned int fa_type;
+	union {
+		unsigned long fa_ino;
+		unsigned int fa_len;
+	};
+};
+
+static const char *
+ocfs2_filecheck_error(int errno)
+{
+	if (!errno)
+		return ocfs2_filecheck_errs[errno];
+
+	BUG_ON(errno < OCFS2_FILECHECK_ERR_START ||
+	       errno > OCFS2_FILECHECK_ERR_END);
+	return ocfs2_filecheck_errs[errno - OCFS2_FILECHECK_ERR_START + 1];
+}
+
+static ssize_t ocfs2_filecheck_show(struct kobject *kobj,
+				    struct kobj_attribute *attr,
+				    char *buf);
+static ssize_t ocfs2_filecheck_store(struct kobject *kobj,
+				     struct kobj_attribute *attr,
+				     const char *buf, size_t count);
+static struct kobj_attribute ocfs2_attr_filecheck_chk =
+					__ATTR(check, S_IRUSR | S_IWUSR,
+					ocfs2_filecheck_show,
+					ocfs2_filecheck_store);
+static struct kobj_attribute ocfs2_attr_filecheck_fix =
+					__ATTR(fix, S_IRUSR | S_IWUSR,
+					ocfs2_filecheck_show,
+					ocfs2_filecheck_store);
+static struct kobj_attribute ocfs2_attr_filecheck_set =
+					__ATTR(set, S_IRUSR | S_IWUSR,
+					ocfs2_filecheck_show,
+					ocfs2_filecheck_store);
+
+static int ocfs2_filecheck_sysfs_wait(atomic_t *p)
+{
+	schedule();
+	return 0;
+}
+
+static void
+ocfs2_filecheck_sysfs_free(struct ocfs2_filecheck_sysfs_entry *entry)
+{
+	struct ocfs2_filecheck_entry *p;
+
+	if (!atomic_dec_and_test(&entry->fs_count))
+		wait_on_atomic_t(&entry->fs_count, ocfs2_filecheck_sysfs_wait,
+				 TASK_UNINTERRUPTIBLE);
+
+	spin_lock(&entry->fs_fcheck->fc_lock);
+	while (!list_empty(&entry->fs_fcheck->fc_head)) {
+		p = list_first_entry(&entry->fs_fcheck->fc_head,
+				     struct ocfs2_filecheck_entry, fe_list);
+		list_del(&p->fe_list);
+		BUG_ON(!p->fe_done); /* To free a undone file check entry */
+		kfree(p);
+	}
+	spin_unlock(&entry->fs_fcheck->fc_lock);
+
+	kset_unregister(entry->fs_fcheckkset);
+	kset_unregister(entry->fs_devicekset);
+	kfree(entry->fs_fcheck);
+	kfree(entry);
+}
+
+static void
+ocfs2_filecheck_sysfs_add(struct ocfs2_filecheck_sysfs_entry *entry)
+{
+	spin_lock(&ocfs2_filecheck_sysfs_lock);
+	list_add_tail(&entry->fs_list, &ocfs2_filecheck_sysfs_list);
+	spin_unlock(&ocfs2_filecheck_sysfs_lock);
+}
+
+static int ocfs2_filecheck_sysfs_del(const char *devname)
+{
+	struct ocfs2_filecheck_sysfs_entry *p;
+
+	spin_lock(&ocfs2_filecheck_sysfs_lock);
+	list_for_each_entry(p, &ocfs2_filecheck_sysfs_list, fs_list) {
+		if (!strcmp(p->fs_sb->s_id, devname)) {
+			list_del(&p->fs_list);
+			spin_unlock(&ocfs2_filecheck_sysfs_lock);
+			ocfs2_filecheck_sysfs_free(p);
+			return 0;
+		}
+	}
+	spin_unlock(&ocfs2_filecheck_sysfs_lock);
+	return 1;
+}
+
+static void
+ocfs2_filecheck_sysfs_put(struct ocfs2_filecheck_sysfs_entry *entry)
+{
+	if (atomic_dec_and_test(&entry->fs_count))
+		wake_up_atomic_t(&entry->fs_count);
+}
+
+static struct ocfs2_filecheck_sysfs_entry *
+ocfs2_filecheck_sysfs_get(const char *devname)
+{
+	struct ocfs2_filecheck_sysfs_entry *p = NULL;
+
+	spin_lock(&ocfs2_filecheck_sysfs_lock);
+	list_for_each_entry(p, &ocfs2_filecheck_sysfs_list, fs_list) {
+		if (!strcmp(p->fs_sb->s_id, devname)) {
+			atomic_inc(&p->fs_count);
+			spin_unlock(&ocfs2_filecheck_sysfs_lock);
+			return p;
+		}
+	}
+	spin_unlock(&ocfs2_filecheck_sysfs_lock);
+	return NULL;
+}
+
+int ocfs2_filecheck_create_sysfs(struct super_block *sb)
+{
+	int ret = 0;
+	struct kset *device_kset = NULL;
+	struct kset *fcheck_kset = NULL;
+	struct ocfs2_filecheck *fcheck = NULL;
+	struct ocfs2_filecheck_sysfs_entry *entry = NULL;
+	struct attribute **attrs = NULL;
+	struct attribute_group attrgp;
+
+	if (!ocfs2_kset)
+		return -ENOMEM;
+
+	attrs = kmalloc(sizeof(struct attribute *) * 4, GFP_NOFS);
+	if (!attrs) {
+		ret = -ENOMEM;
+		goto error;
+	} else {
+		attrs[0] = &ocfs2_attr_filecheck_chk.attr;
+		attrs[1] = &ocfs2_attr_filecheck_fix.attr;
+		attrs[2] = &ocfs2_attr_filecheck_set.attr;
+		attrs[3] = NULL;
+		memset(&attrgp, 0, sizeof(attrgp));
+		attrgp.attrs = attrs;
+	}
+
+	fcheck = kmalloc(sizeof(struct ocfs2_filecheck), GFP_NOFS);
+	if (!fcheck) {
+		ret = -ENOMEM;
+		goto error;
+	} else {
+		INIT_LIST_HEAD(&fcheck->fc_head);
+		spin_lock_init(&fcheck->fc_lock);
+		fcheck->fc_max = OCFS2_FILECHECK_MINSIZE;
+		fcheck->fc_size = 0;
+		fcheck->fc_done = 0;
+	}
+
+	if (strlen(sb->s_id) <= 0) {
+		mlog(ML_ERROR,
+		"Cannot get device basename when create filecheck sysfs\n");
+		ret = -ENODEV;
+		goto error;
+	}
+
+	device_kset = kset_create_and_add(sb->s_id, NULL, &ocfs2_kset->kobj);
+	if (!device_kset) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	fcheck_kset = kset_create_and_add("filecheck", NULL,
+					  &device_kset->kobj);
+	if (!fcheck_kset) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	ret = sysfs_create_group(&fcheck_kset->kobj, &attrgp);
+	if (ret)
+		goto error;
+
+	entry = kmalloc(sizeof(struct ocfs2_filecheck_sysfs_entry), GFP_NOFS);
+	if (!entry) {
+		ret = -ENOMEM;
+		goto error;
+	} else {
+		atomic_set(&entry->fs_count, 1);
+		entry->fs_sb = sb;
+		entry->fs_devicekset = device_kset;
+		entry->fs_fcheckkset = fcheck_kset;
+		entry->fs_fcheck = fcheck;
+		ocfs2_filecheck_sysfs_add(entry);
+	}
+
+	kfree(attrs);
+	return 0;
+
+error:
+	kfree(attrs);
+	kfree(entry);
+	kfree(fcheck);
+	kset_unregister(fcheck_kset);
+	kset_unregister(device_kset);
+	return ret;
+}
+
+int ocfs2_filecheck_remove_sysfs(struct super_block *sb)
+{
+	return ocfs2_filecheck_sysfs_del(sb->s_id);
+}
+
+static int
+ocfs2_filecheck_erase_entries(struct ocfs2_filecheck_sysfs_entry *ent,
+			      unsigned int count);
+static int
+ocfs2_filecheck_adjust_max(struct ocfs2_filecheck_sysfs_entry *ent,
+			   unsigned int len)
+{
+	int ret;
+
+	if ((len < OCFS2_FILECHECK_MINSIZE) || (len > OCFS2_FILECHECK_MAXSIZE))
+		return -EINVAL;
+
+	spin_lock(&ent->fs_fcheck->fc_lock);
+	if (len < (ent->fs_fcheck->fc_size - ent->fs_fcheck->fc_done)) {
+		mlog(ML_ERROR,
+		"Cannot set online file check maximum entry number "
+		"to %u due to too many pending entries(%u)\n",
+		len, ent->fs_fcheck->fc_size - ent->fs_fcheck->fc_done);
+		ret = -EBUSY;
+	} else {
+		if (len < ent->fs_fcheck->fc_size)
+			BUG_ON(!ocfs2_filecheck_erase_entries(ent,
+				ent->fs_fcheck->fc_size - len));
+
+		ent->fs_fcheck->fc_max = len;
+		ret = 0;
+	}
+	spin_unlock(&ent->fs_fcheck->fc_lock);
+
+	return ret;
+}
+
+#define OCFS2_FILECHECK_ARGS_LEN	24
+static int
+ocfs2_filecheck_args_get_long(const char *buf, size_t count,
+			      unsigned long *val)
+{
+	char buffer[OCFS2_FILECHECK_ARGS_LEN];
+
+	memcpy(buffer, buf, count);
+	buffer[count] = '\0';
+
+	if (kstrtoul(buffer, 0, val))
+		return 1;
+
+	return 0;
+}
+
+static int
+ocfs2_filecheck_type_parse(const char *name, unsigned int *type)
+{
+	if (!strncmp(name, "fix", 4))
+		*type = OCFS2_FILECHECK_TYPE_FIX;
+	else if (!strncmp(name, "check", 6))
+		*type = OCFS2_FILECHECK_TYPE_CHK;
+	else if (!strncmp(name, "set", 4))
+		*type = OCFS2_FILECHECK_TYPE_SET;
+	else
+		return 1;
+
+	return 0;
+}
+
+static int
+ocfs2_filecheck_args_parse(const char *name, const char *buf, size_t count,
+			   struct ocfs2_filecheck_args *args)
+{
+	unsigned long val = 0;
+	unsigned int type;
+
+	/* too short/long args length */
+	if ((count < 1) || (count >= OCFS2_FILECHECK_ARGS_LEN))
+		return 1;
+
+	if (ocfs2_filecheck_type_parse(name, &type))
+		return 1;
+	if (ocfs2_filecheck_args_get_long(buf, count, &val))
+		return 1;
+
+	if (val <= 0)
+		return 1;
+
+	args->fa_type = type;
+	if (type == OCFS2_FILECHECK_TYPE_SET)
+		args->fa_len = (unsigned int)val;
+	else
+		args->fa_ino = val;
+
+	return 0;
+}
+
+static ssize_t ocfs2_filecheck_show(struct kobject *kobj,
+				    struct kobj_attribute *attr,
+				    char *buf)
+{
+
+	ssize_t ret = 0, total = 0, remain = PAGE_SIZE;
+	unsigned int type;
+	struct ocfs2_filecheck_entry *p;
+	struct ocfs2_filecheck_sysfs_entry *ent;
+
+	if (ocfs2_filecheck_type_parse(attr->attr.name, &type))
+		return -EINVAL;
+
+	ent = ocfs2_filecheck_sysfs_get(kobj->parent->name);
+	if (!ent) {
+		mlog(ML_ERROR,
+		"Cannot get the corresponding entry via device basename %s\n",
+		kobj->name);
+		return -ENODEV;
+	}
+
+	if (type == OCFS2_FILECHECK_TYPE_SET) {
+		spin_lock(&ent->fs_fcheck->fc_lock);
+		total = snprintf(buf, remain, "%u\n", ent->fs_fcheck->fc_max);
+		spin_unlock(&ent->fs_fcheck->fc_lock);
+		goto exit;
+	}
+
+	ret = snprintf(buf, remain, "INO\t\tDONE\tERROR\n");
+	total += ret;
+	remain -= ret;
+	spin_lock(&ent->fs_fcheck->fc_lock);
+	list_for_each_entry(p, &ent->fs_fcheck->fc_head, fe_list) {
+		if (p->fe_type != type)
+			continue;
+
+		ret = snprintf(buf + total, remain, "%lu\t\t%u\t%s\n",
+			       p->fe_ino, p->fe_done,
+			       ocfs2_filecheck_error(p->fe_status));
+		if (ret < 0) {
+			total = ret;
+			break;
+		}
+		if (ret == remain) {
+			/* snprintf() didn't fit */
+			total = -E2BIG;
+			break;
+		}
+		total += ret;
+		remain -= ret;
+	}
+	spin_unlock(&ent->fs_fcheck->fc_lock);
+
+exit:
+	ocfs2_filecheck_sysfs_put(ent);
+	return total;
+}
+
+static int
+ocfs2_filecheck_erase_entry(struct ocfs2_filecheck_sysfs_entry *ent)
+{
+	struct ocfs2_filecheck_entry *p;
+
+	list_for_each_entry(p, &ent->fs_fcheck->fc_head, fe_list) {
+		if (p->fe_done) {
+			list_del(&p->fe_list);
+			kfree(p);
+			ent->fs_fcheck->fc_size--;
+			ent->fs_fcheck->fc_done--;
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+static int
+ocfs2_filecheck_erase_entries(struct ocfs2_filecheck_sysfs_entry *ent,
+			      unsigned int count)
+{
+	unsigned int i = 0;
+	unsigned int ret = 0;
+
+	while (i++ < count) {
+		if (ocfs2_filecheck_erase_entry(ent))
+			ret++;
+		else
+			break;
+	}
+
+	return (ret == count ? 1 : 0);
+}
+
+static void
+ocfs2_filecheck_done_entry(struct ocfs2_filecheck_sysfs_entry *ent,
+			   struct ocfs2_filecheck_entry *entry)
+{
+	entry->fe_done = 1;
+	spin_lock(&ent->fs_fcheck->fc_lock);
+	ent->fs_fcheck->fc_done++;
+	spin_unlock(&ent->fs_fcheck->fc_lock);
+}
+
+static unsigned int
+ocfs2_filecheck_handle(struct super_block *sb,
+		       unsigned long ino, unsigned int flags)
+{
+	unsigned int ret = OCFS2_FILECHECK_ERR_SUCCESS;
+	struct inode *inode = NULL;
+	int rc;
+
+	inode = ocfs2_iget(OCFS2_SB(sb), ino, flags, 0);
+	if (IS_ERR(inode)) {
+		rc = (int)(-(long)inode);
+		if (rc >= OCFS2_FILECHECK_ERR_START &&
+		    rc < OCFS2_FILECHECK_ERR_END)
+			ret = rc;
+		else
+			ret = OCFS2_FILECHECK_ERR_FAILED;
+	} else
+		iput(inode);
+
+	return ret;
+}
+
+static void
+ocfs2_filecheck_handle_entry(struct ocfs2_filecheck_sysfs_entry *ent,
+			     struct ocfs2_filecheck_entry *entry)
+{
+	if (entry->fe_type == OCFS2_FILECHECK_TYPE_CHK)
+		entry->fe_status = ocfs2_filecheck_handle(ent->fs_sb,
+				entry->fe_ino, OCFS2_FI_FLAG_FILECHECK_CHK);
+	else if (entry->fe_type == OCFS2_FILECHECK_TYPE_FIX)
+		entry->fe_status = ocfs2_filecheck_handle(ent->fs_sb,
+				entry->fe_ino, OCFS2_FI_FLAG_FILECHECK_FIX);
+	else
+		entry->fe_status = OCFS2_FILECHECK_ERR_UNSUPPORTED;
+
+	ocfs2_filecheck_done_entry(ent, entry);
+}
+
+static ssize_t ocfs2_filecheck_store(struct kobject *kobj,
+				     struct kobj_attribute *attr,
+				     const char *buf, size_t count)
+{
+	struct ocfs2_filecheck_args args;
+	struct ocfs2_filecheck_entry *entry;
+	struct ocfs2_filecheck_sysfs_entry *ent;
+	ssize_t ret = 0;
+
+	if (count == 0)
+		return count;
+
+	if (ocfs2_filecheck_args_parse(attr->attr.name, buf, count, &args)) {
+		mlog(ML_ERROR, "Invalid arguments for online file check\n");
+		return -EINVAL;
+	}
+
+	ent = ocfs2_filecheck_sysfs_get(kobj->parent->name);
+	if (!ent) {
+		mlog(ML_ERROR,
+		"Cannot get the corresponding entry via device basename %s\n",
+		kobj->parent->name);
+		return -ENODEV;
+	}
+
+	if (args.fa_type == OCFS2_FILECHECK_TYPE_SET) {
+		ret = ocfs2_filecheck_adjust_max(ent, args.fa_len);
+		goto exit;
+	}
+
+	entry = kmalloc(sizeof(struct ocfs2_filecheck_entry), GFP_NOFS);
+	if (!entry) {
+		ret = -ENOMEM;
+		goto exit;
+	}
+
+	spin_lock(&ent->fs_fcheck->fc_lock);
+	if ((ent->fs_fcheck->fc_size >= ent->fs_fcheck->fc_max) &&
+	    (ent->fs_fcheck->fc_done == 0)) {
+		mlog(ML_ERROR,
+		"Cannot do more file check "
+		"since file check queue(%u) is full now\n",
+		ent->fs_fcheck->fc_max);
+		ret = -EBUSY;
+		kfree(entry);
+	} else {
+		if ((ent->fs_fcheck->fc_size >= ent->fs_fcheck->fc_max) &&
+		    (ent->fs_fcheck->fc_done > 0)) {
+			/* Delete the oldest entry which was done,
+			 * make sure the entry size in list does
+			 * not exceed maximum value
+			 */
+			BUG_ON(!ocfs2_filecheck_erase_entry(ent));
+		}
+
+		entry->fe_ino = args.fa_ino;
+		entry->fe_type = args.fa_type;
+		entry->fe_done = 0;
+		entry->fe_status = OCFS2_FILECHECK_ERR_INPROGRESS;
+		list_add_tail(&entry->fe_list, &ent->fs_fcheck->fc_head);
+		ent->fs_fcheck->fc_size++;
+	}
+	spin_unlock(&ent->fs_fcheck->fc_lock);
+
+	if (!ret)
+		ocfs2_filecheck_handle_entry(ent, entry);
+
+exit:
+	ocfs2_filecheck_sysfs_put(ent);
+	return (!ret ? count : ret);
+}
diff --git a/fs/ocfs2/filecheck.h b/fs/ocfs2/filecheck.h
new file mode 100644
index 000000000000..e5cd002a2c09
--- /dev/null
+++ b/fs/ocfs2/filecheck.h
@@ -0,0 +1,49 @@
+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * filecheck.h
+ *
+ * Online file check.
+ *
+ * Copyright (C) 2016 SuSE.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License as published by the Free Software Foundation, version 2.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+
+#ifndef FILECHECK_H
+#define FILECHECK_H
+
+#include <linux/types.h>
+#include <linux/list.h>
+
+
+/* File check errno */
+enum {
+	OCFS2_FILECHECK_ERR_SUCCESS = 0,	/* Success */
+	OCFS2_FILECHECK_ERR_FAILED = 1000,	/* Other failure */
+	OCFS2_FILECHECK_ERR_INPROGRESS,		/* In progress */
+	OCFS2_FILECHECK_ERR_READONLY,		/* Read only */
+	OCFS2_FILECHECK_ERR_INJBD,		/* Buffer in jbd */
+	OCFS2_FILECHECK_ERR_INVALIDINO,		/* Invalid ino */
+	OCFS2_FILECHECK_ERR_BLOCKECC,		/* Block ecc */
+	OCFS2_FILECHECK_ERR_BLOCKNO,		/* Block number */
+	OCFS2_FILECHECK_ERR_VALIDFLAG,		/* Inode valid flag */
+	OCFS2_FILECHECK_ERR_GENERATION,		/* Inode generation */
+	OCFS2_FILECHECK_ERR_UNSUPPORTED		/* Unsupported */
+};
+
+#define OCFS2_FILECHECK_ERR_START	OCFS2_FILECHECK_ERR_FAILED
+#define OCFS2_FILECHECK_ERR_END		OCFS2_FILECHECK_ERR_UNSUPPORTED
+
+int ocfs2_filecheck_create_sysfs(struct super_block *sb);
+int ocfs2_filecheck_remove_sysfs(struct super_block *sb);
+
+#endif  /* FILECHECK_H */
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 8f87e05ee25d..12f4a9e9800f 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -53,6 +53,7 @@
 #include "xattr.h"
 #include "refcounttree.h"
 #include "ocfs2_trace.h"
+#include "filecheck.h"
 
 #include "buffer_head_io.h"
 
@@ -74,6 +75,14 @@ static int ocfs2_truncate_for_delete(struct ocfs2_super *osb,
 				    struct inode *inode,
 				    struct buffer_head *fe_bh);
 
+static int ocfs2_filecheck_read_inode_block_full(struct inode *inode,
+						 struct buffer_head **bh,
+						 int flags, int type);
+static int ocfs2_filecheck_validate_inode_block(struct super_block *sb,
+						struct buffer_head *bh);
+static int ocfs2_filecheck_repair_inode_block(struct super_block *sb,
+					      struct buffer_head *bh);
+
 void ocfs2_set_inode_flags(struct inode *inode)
 {
 	unsigned int flags = OCFS2_I(inode)->ip_attr;
@@ -127,6 +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;
 	struct inode *inode = NULL;
 	struct super_block *sb = osb->sb;
 	struct ocfs2_find_inode_args args;
@@ -161,12 +171,17 @@ struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags,
 	}
 	trace_ocfs2_iget5_locked(inode->i_state);
 	if (inode->i_state & I_NEW) {
-		ocfs2_read_locked_inode(inode, &args);
+		rc = ocfs2_read_locked_inode(inode, &args);
 		unlock_new_inode(inode);
 	}
 	if (is_bad_inode(inode)) {
 		iput(inode);
-		inode = ERR_PTR(-ESTALE);
+		if ((flags & OCFS2_FI_FLAG_FILECHECK_CHK) ||
+		    (flags & OCFS2_FI_FLAG_FILECHECK_FIX))
+			/* Return OCFS2_FILECHECK_ERR_XXX related errno */
+			inode = ERR_PTR(rc);
+		else
+			inode = ERR_PTR(-ESTALE);
 		goto bail;
 	}
 
@@ -361,6 +376,7 @@ void ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe,
 		    break;
 	    case S_IFLNK:
 		    inode->i_op = &ocfs2_symlink_inode_operations;
+		    inode_nohighmem(inode);
 		    i_size_write(inode, le64_to_cpu(fe->i_size));
 		    break;
 	    default:
@@ -409,7 +425,7 @@ static int ocfs2_read_locked_inode(struct inode *inode,
 	struct ocfs2_super *osb;
 	struct ocfs2_dinode *fe;
 	struct buffer_head *bh = NULL;
-	int status, can_lock;
+	int status, can_lock, lock_level = 0;
 	u32 generation = 0;
 
 	status = -EINVAL;
@@ -477,7 +493,7 @@ static int ocfs2_read_locked_inode(struct inode *inode,
 			mlog_errno(status);
 			return status;
 		}
-		status = ocfs2_inode_lock(inode, NULL, 0);
+		status = ocfs2_inode_lock(inode, NULL, lock_level);
 		if (status) {
 			make_bad_inode(inode);
 			mlog_errno(status);
@@ -494,16 +510,32 @@ static int ocfs2_read_locked_inode(struct inode *inode,
 	}
 
 	if (can_lock) {
-		status = ocfs2_read_inode_block_full(inode, &bh,
-						     OCFS2_BH_IGNORE_CACHE);
+		if (args->fi_flags & OCFS2_FI_FLAG_FILECHECK_CHK)
+			status = ocfs2_filecheck_read_inode_block_full(inode,
+						&bh, OCFS2_BH_IGNORE_CACHE, 0);
+		else if (args->fi_flags & OCFS2_FI_FLAG_FILECHECK_FIX)
+			status = ocfs2_filecheck_read_inode_block_full(inode,
+						&bh, OCFS2_BH_IGNORE_CACHE, 1);
+		else
+			status = ocfs2_read_inode_block_full(inode,
+						&bh, OCFS2_BH_IGNORE_CACHE);
 	} else {
 		status = ocfs2_read_blocks_sync(osb, args->fi_blkno, 1, &bh);
 		/*
 		 * If buffer is in jbd, then its checksum may not have been
 		 * computed as yet.
 		 */
-		if (!status && !buffer_jbd(bh))
-			status = ocfs2_validate_inode_block(osb->sb, bh);
+		if (!status && !buffer_jbd(bh)) {
+			if (args->fi_flags & OCFS2_FI_FLAG_FILECHECK_CHK)
+				status = ocfs2_filecheck_validate_inode_block(
+								osb->sb, bh);
+			else if (args->fi_flags & OCFS2_FI_FLAG_FILECHECK_FIX)
+				status = ocfs2_filecheck_repair_inode_block(
+								osb->sb, bh);
+			else
+				status = ocfs2_validate_inode_block(
+								osb->sb, bh);
+		}
 	}
 	if (status < 0) {
 		mlog_errno(status);
@@ -531,11 +563,24 @@ static int ocfs2_read_locked_inode(struct inode *inode,
 
 	BUG_ON(args->fi_blkno != le64_to_cpu(fe->i_blkno));
 
+	if (buffer_dirty(bh) && !buffer_jbd(bh)) {
+		if (can_lock) {
+			ocfs2_inode_unlock(inode, lock_level);
+			lock_level = 1;
+			ocfs2_inode_lock(inode, NULL, lock_level);
+		}
+		status = ocfs2_write_block(osb, bh, INODE_CACHE(inode));
+		if (status < 0) {
+			mlog_errno(status);
+			goto bail;
+		}
+	}
+
 	status = 0;
 
 bail:
 	if (can_lock)
-		ocfs2_inode_unlock(inode, 0);
+		ocfs2_inode_unlock(inode, lock_level);
 
 	if (status < 0)
 		make_bad_inode(inode);
@@ -629,10 +674,10 @@ static int ocfs2_remove_inode(struct inode *inode,
 		goto bail;
 	}
 
-	mutex_lock(&inode_alloc_inode->i_mutex);
+	inode_lock(inode_alloc_inode);
 	status = ocfs2_inode_lock(inode_alloc_inode, &inode_alloc_bh, 1);
 	if (status < 0) {
-		mutex_unlock(&inode_alloc_inode->i_mutex);
+		inode_unlock(inode_alloc_inode);
 
 		mlog_errno(status);
 		goto bail;
@@ -679,7 +724,7 @@ bail_commit:
 	ocfs2_commit_trans(osb, handle);
 bail_unlock:
 	ocfs2_inode_unlock(inode_alloc_inode, 1);
-	mutex_unlock(&inode_alloc_inode->i_mutex);
+	inode_unlock(inode_alloc_inode);
 	brelse(inode_alloc_bh);
 bail:
 	iput(inode_alloc_inode);
@@ -750,10 +795,10 @@ static int ocfs2_wipe_inode(struct inode *inode,
 		/* Lock the orphan dir. The lock will be held for the entire
 		 * delete_inode operation. We do this now to avoid races with
 		 * recovery completion on other nodes. */
-		mutex_lock(&orphan_dir_inode->i_mutex);
+		inode_lock(orphan_dir_inode);
 		status = ocfs2_inode_lock(orphan_dir_inode, &orphan_dir_bh, 1);
 		if (status < 0) {
-			mutex_unlock(&orphan_dir_inode->i_mutex);
+			inode_unlock(orphan_dir_inode);
 
 			mlog_errno(status);
 			goto bail;
@@ -802,7 +847,7 @@ bail_unlock_dir:
 		return status;
 
 	ocfs2_inode_unlock(orphan_dir_inode, 1);
-	mutex_unlock(&orphan_dir_inode->i_mutex);
+	inode_unlock(orphan_dir_inode);
 	brelse(orphan_dir_bh);
 bail:
 	iput(orphan_dir_inode);
@@ -1125,6 +1170,9 @@ static void ocfs2_clear_inode(struct inode *inode)
 	mlog_bug_on_msg(!list_empty(&oi->ip_io_markers),
 			"Clear inode of %llu, inode has io markers\n",
 			(unsigned long long)oi->ip_blkno);
+	mlog_bug_on_msg(!list_empty(&oi->ip_unwritten_list),
+			"Clear inode of %llu, inode has unwritten extents\n",
+			(unsigned long long)oi->ip_blkno);
 
 	ocfs2_extent_map_trunc(inode, 0);
 
@@ -1396,6 +1444,169 @@ bail:
 	return rc;
 }
 
+static int ocfs2_filecheck_validate_inode_block(struct super_block *sb,
+						struct buffer_head *bh)
+{
+	int rc = 0;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data;
+
+	trace_ocfs2_filecheck_validate_inode_block(
+		(unsigned long long)bh->b_blocknr);
+
+	BUG_ON(!buffer_uptodate(bh));
+
+	/*
+	 * Call ocfs2_validate_meta_ecc() first since it has ecc repair
+	 * function, but we should not return error immediately when ecc
+	 * validation fails, because the reason is quite likely the invalid
+	 * inode number inputed.
+	 */
+	rc = ocfs2_validate_meta_ecc(sb, bh->b_data, &di->i_check);
+	if (rc) {
+		mlog(ML_ERROR,
+		     "Filecheck: checksum failed for dinode %llu\n",
+		     (unsigned long long)bh->b_blocknr);
+		rc = -OCFS2_FILECHECK_ERR_BLOCKECC;
+	}
+
+	if (!OCFS2_IS_VALID_DINODE(di)) {
+		mlog(ML_ERROR,
+		     "Filecheck: invalid dinode #%llu: signature = %.*s\n",
+		     (unsigned long long)bh->b_blocknr, 7, di->i_signature);
+		rc = -OCFS2_FILECHECK_ERR_INVALIDINO;
+		goto bail;
+	} else if (rc)
+		goto bail;
+
+	if (le64_to_cpu(di->i_blkno) != bh->b_blocknr) {
+		mlog(ML_ERROR,
+		     "Filecheck: invalid dinode #%llu: i_blkno is %llu\n",
+		     (unsigned long long)bh->b_blocknr,
+		     (unsigned long long)le64_to_cpu(di->i_blkno));
+		rc = -OCFS2_FILECHECK_ERR_BLOCKNO;
+		goto bail;
+	}
+
+	if (!(di->i_flags & cpu_to_le32(OCFS2_VALID_FL))) {
+		mlog(ML_ERROR,
+		     "Filecheck: invalid dinode #%llu: OCFS2_VALID_FL "
+		     "not set\n",
+		     (unsigned long long)bh->b_blocknr);
+		rc = -OCFS2_FILECHECK_ERR_VALIDFLAG;
+		goto bail;
+	}
+
+	if (le32_to_cpu(di->i_fs_generation) !=
+	    OCFS2_SB(sb)->fs_generation) {
+		mlog(ML_ERROR,
+		     "Filecheck: invalid dinode #%llu: fs_generation is %u\n",
+		     (unsigned long long)bh->b_blocknr,
+		     le32_to_cpu(di->i_fs_generation));
+		rc = -OCFS2_FILECHECK_ERR_GENERATION;
+		goto bail;
+	}
+
+bail:
+	return rc;
+}
+
+static int ocfs2_filecheck_repair_inode_block(struct super_block *sb,
+					      struct buffer_head *bh)
+{
+	int changed = 0;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data;
+
+	if (!ocfs2_filecheck_validate_inode_block(sb, bh))
+		return 0;
+
+	trace_ocfs2_filecheck_repair_inode_block(
+		(unsigned long long)bh->b_blocknr);
+
+	if (ocfs2_is_hard_readonly(OCFS2_SB(sb)) ||
+	    ocfs2_is_soft_readonly(OCFS2_SB(sb))) {
+		mlog(ML_ERROR,
+		     "Filecheck: cannot repair dinode #%llu "
+		     "on readonly filesystem\n",
+		     (unsigned long long)bh->b_blocknr);
+		return -OCFS2_FILECHECK_ERR_READONLY;
+	}
+
+	if (buffer_jbd(bh)) {
+		mlog(ML_ERROR,
+		     "Filecheck: cannot repair dinode #%llu, "
+		     "its buffer is in jbd\n",
+		     (unsigned long long)bh->b_blocknr);
+		return -OCFS2_FILECHECK_ERR_INJBD;
+	}
+
+	if (!OCFS2_IS_VALID_DINODE(di)) {
+		/* Cannot fix invalid inode block */
+		return -OCFS2_FILECHECK_ERR_INVALIDINO;
+	}
+
+	if (!(di->i_flags & cpu_to_le32(OCFS2_VALID_FL))) {
+		/* Cannot just add VALID_FL flag back as a fix,
+		 * need more things to check here.
+		 */
+		return -OCFS2_FILECHECK_ERR_VALIDFLAG;
+	}
+
+	if (le64_to_cpu(di->i_blkno) != bh->b_blocknr) {
+		di->i_blkno = cpu_to_le64(bh->b_blocknr);
+		changed = 1;
+		mlog(ML_ERROR,
+		     "Filecheck: reset dinode #%llu: i_blkno to %llu\n",
+		     (unsigned long long)bh->b_blocknr,
+		     (unsigned long long)le64_to_cpu(di->i_blkno));
+	}
+
+	if (le32_to_cpu(di->i_fs_generation) !=
+	    OCFS2_SB(sb)->fs_generation) {
+		di->i_fs_generation = cpu_to_le32(OCFS2_SB(sb)->fs_generation);
+		changed = 1;
+		mlog(ML_ERROR,
+		     "Filecheck: reset dinode #%llu: fs_generation to %u\n",
+		     (unsigned long long)bh->b_blocknr,
+		     le32_to_cpu(di->i_fs_generation));
+	}
+
+	if (changed || ocfs2_validate_meta_ecc(sb, bh->b_data, &di->i_check)) {
+		ocfs2_compute_meta_ecc(sb, bh->b_data, &di->i_check);
+		mark_buffer_dirty(bh);
+		mlog(ML_ERROR,
+		     "Filecheck: reset dinode #%llu: compute meta ecc\n",
+		     (unsigned long long)bh->b_blocknr);
+	}
+
+	return 0;
+}
+
+static int
+ocfs2_filecheck_read_inode_block_full(struct inode *inode,
+				      struct buffer_head **bh,
+				      int flags, int type)
+{
+	int rc;
+	struct buffer_head *tmp = *bh;
+
+	if (!type) /* Check inode block */
+		rc = ocfs2_read_blocks(INODE_CACHE(inode),
+				OCFS2_I(inode)->ip_blkno,
+				1, &tmp, flags,
+				ocfs2_filecheck_validate_inode_block);
+	else /* Repair inode block */
+		rc = ocfs2_read_blocks(INODE_CACHE(inode),
+				OCFS2_I(inode)->ip_blkno,
+				1, &tmp, flags,
+				ocfs2_filecheck_repair_inode_block);
+
+	/* If ocfs2_read_blocks() got us a new bh, pass it up. */
+	if (!rc && !*bh)
+		*bh = tmp;
+
+	return rc;
+}
+
 int ocfs2_read_inode_block_full(struct inode *inode, struct buffer_head **bh,
 				int flags)
 {
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index aac8b86f312e..d8f3fc8d2551 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -43,9 +43,6 @@ struct ocfs2_inode_info
 	/* protects extended attribute changes on this inode */
 	struct rw_semaphore		ip_xattr_sem;
 
-	/* Number of outstanding AIO's which are not page aligned */
-	struct mutex			ip_unaligned_aio;
-
 	/* These fields are protected by ip_lock */
 	spinlock_t			ip_lock;
 	u32				ip_open_count;
@@ -57,6 +54,9 @@ struct ocfs2_inode_info
 	u32				ip_flags; /* see below */
 	u32				ip_attr; /* inode attributes */
 
+	/* Record unwritten extents during direct io. */
+	struct list_head		ip_unwritten_list;
+
 	/* protected by recovery_lock. */
 	struct inode			*ip_next_orphan;
 
@@ -139,6 +139,9 @@ int ocfs2_drop_inode(struct inode *inode);
 /* Flags for ocfs2_iget() */
 #define OCFS2_FI_FLAG_SYSFILE		0x1
 #define OCFS2_FI_FLAG_ORPHAN_RECOVERY	0x2
+#define OCFS2_FI_FLAG_FILECHECK_CHK	0x4
+#define OCFS2_FI_FLAG_FILECHECK_FIX	0x8
+
 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);
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index 3cb097ccce60..4506ec5ec2ea 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -86,7 +86,7 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags,
 	unsigned oldflags;
 	int status;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	status = ocfs2_inode_lock(inode, &bh, 1);
 	if (status < 0) {
@@ -135,7 +135,7 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags,
 bail_unlock:
 	ocfs2_inode_unlock(inode, 1);
 bail:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	brelse(bh);
 
@@ -287,7 +287,7 @@ static int ocfs2_info_scan_inode_alloc(struct ocfs2_super *osb,
 	struct ocfs2_dinode *dinode_alloc = NULL;
 
 	if (inode_alloc)
-		mutex_lock(&inode_alloc->i_mutex);
+		inode_lock(inode_alloc);
 
 	if (o2info_coherent(&fi->ifi_req)) {
 		status = ocfs2_inode_lock(inode_alloc, &bh, 0);
@@ -317,7 +317,7 @@ bail:
 		ocfs2_inode_unlock(inode_alloc, 0);
 
 	if (inode_alloc)
-		mutex_unlock(&inode_alloc->i_mutex);
+		inode_unlock(inode_alloc);
 
 	brelse(bh);
 
@@ -547,7 +547,7 @@ static int ocfs2_info_freefrag_scan_bitmap(struct ocfs2_super *osb,
 	struct ocfs2_dinode *gb_dinode = NULL;
 
 	if (gb_inode)
-		mutex_lock(&gb_inode->i_mutex);
+		inode_lock(gb_inode);
 
 	if (o2info_coherent(&ffg->iff_req)) {
 		status = ocfs2_inode_lock(gb_inode, &bh, 0);
@@ -604,11 +604,9 @@ bail:
 		ocfs2_inode_unlock(gb_inode, 0);
 
 	if (gb_inode)
-		mutex_unlock(&gb_inode->i_mutex);
-
-	if (gb_inode)
-		iput(gb_inode);
+		inode_unlock(gb_inode);
 
+	iput(gb_inode);
 	brelse(bh);
 
 	return status;
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 13534f4fe5b5..e607419cdfa4 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -231,7 +231,7 @@ void ocfs2_recovery_exit(struct ocfs2_super *osb)
 	/* At this point, we know that no more recovery threads can be
 	 * launched, so wait for any recovery completion work to
 	 * complete. */
-	flush_workqueue(ocfs2_wq);
+	flush_workqueue(osb->ocfs2_wq);
 
 	/*
 	 * Now that recovery is shut down, and the osb is about to be
@@ -1042,8 +1042,7 @@ void ocfs2_journal_shutdown(struct ocfs2_super *osb)
 
 //	up_write(&journal->j_trans_barrier);
 done:
-	if (inode)
-		iput(inode);
+	iput(inode);
 }
 
 static void ocfs2_clear_journal_error(struct super_block *sb,
@@ -1327,7 +1326,7 @@ static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
 
 	spin_lock(&journal->j_lock);
 	list_add_tail(&item->lri_list, &journal->j_la_cleanups);
-	queue_work(ocfs2_wq, &journal->j_recovery_work);
+	queue_work(journal->j_osb->ocfs2_wq, &journal->j_recovery_work);
 	spin_unlock(&journal->j_lock);
 }
 
@@ -1687,9 +1686,7 @@ done:
 	if (got_lock)
 		ocfs2_inode_unlock(inode, 1);
 
-	if (inode)
-		iput(inode);
-
+	iput(inode);
 	brelse(bh);
 
 	return status;
@@ -1796,8 +1793,7 @@ static int ocfs2_trylock_journal(struct ocfs2_super *osb,
 
 	ocfs2_inode_unlock(inode, 1);
 bail:
-	if (inode)
-		iput(inode);
+	iput(inode);
 
 	return status;
 }
@@ -1972,7 +1968,7 @@ static void ocfs2_orphan_scan_work(struct work_struct *work)
 	mutex_lock(&os->os_lock);
 	ocfs2_queue_orphan_scan(osb);
 	if (atomic_read(&os->os_state) == ORPHAN_SCAN_ACTIVE)
-		queue_delayed_work(ocfs2_wq, &os->os_orphan_scan_work,
+		queue_delayed_work(osb->ocfs2_wq, &os->os_orphan_scan_work,
 				      ocfs2_orphan_scan_timeout());
 	mutex_unlock(&os->os_lock);
 }
@@ -2012,7 +2008,7 @@ void ocfs2_orphan_scan_start(struct ocfs2_super *osb)
 		atomic_set(&os->os_state, ORPHAN_SCAN_INACTIVE);
 	else {
 		atomic_set(&os->os_state, ORPHAN_SCAN_ACTIVE);
-		queue_delayed_work(ocfs2_wq, &os->os_orphan_scan_work,
+		queue_delayed_work(osb->ocfs2_wq, &os->os_orphan_scan_work,
 				   ocfs2_orphan_scan_timeout());
 	}
 }
@@ -2092,7 +2088,7 @@ static int ocfs2_queue_orphans(struct ocfs2_super *osb,
 		return status;
 	}
 
-	mutex_lock(&orphan_dir_inode->i_mutex);
+	inode_lock(orphan_dir_inode);
 	status = ocfs2_inode_lock(orphan_dir_inode, NULL, 0);
 	if (status < 0) {
 		mlog_errno(status);
@@ -2110,7 +2106,7 @@ static int ocfs2_queue_orphans(struct ocfs2_super *osb,
 out_cluster:
 	ocfs2_inode_unlock(orphan_dir_inode, 0);
 out:
-	mutex_unlock(&orphan_dir_inode->i_mutex);
+	inode_unlock(orphan_dir_inode);
 	iput(orphan_dir_inode);
 	return status;
 }
@@ -2200,7 +2196,7 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
 		oi->ip_next_orphan = NULL;
 
 		if (oi->ip_flags & OCFS2_INODE_DIO_ORPHAN_ENTRY) {
-			mutex_lock(&inode->i_mutex);
+			inode_lock(inode);
 			ret = ocfs2_rw_lock(inode, 1);
 			if (ret < 0) {
 				mlog_errno(ret);
@@ -2239,7 +2235,7 @@ unlock_inode:
 unlock_rw:
 			ocfs2_rw_unlock(inode, 1);
 unlock_mutex:
-			mutex_unlock(&inode->i_mutex);
+			inode_unlock(inode);
 
 			/* clear dio flag in ocfs2_inode_info */
 			oi->ip_flags &= ~OCFS2_INODE_DIO_ORPHAN_ENTRY;
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index 0a4457fb0711..fe0d1f9571bb 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -358,8 +358,7 @@ int ocfs2_load_local_alloc(struct ocfs2_super *osb)
 bail:
 	if (status < 0)
 		brelse(alloc_bh);
-	if (inode)
-		iput(inode);
+	iput(inode);
 
 	trace_ocfs2_load_local_alloc(osb->local_alloc_bits);
 
@@ -387,7 +386,7 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb)
 	struct ocfs2_dinode *alloc = NULL;
 
 	cancel_delayed_work(&osb->la_enable_wq);
-	flush_workqueue(ocfs2_wq);
+	flush_workqueue(osb->ocfs2_wq);
 
 	if (osb->local_alloc_state == OCFS2_LA_UNUSED)
 		goto out;
@@ -415,7 +414,7 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb)
 		goto out;
 	}
 
-	mutex_lock(&main_bm_inode->i_mutex);
+	inode_lock(main_bm_inode);
 
 	status = ocfs2_inode_lock(main_bm_inode, &main_bm_bh, 1);
 	if (status < 0) {
@@ -469,12 +468,11 @@ out_unlock:
 	ocfs2_inode_unlock(main_bm_inode, 1);
 
 out_mutex:
-	mutex_unlock(&main_bm_inode->i_mutex);
+	inode_unlock(main_bm_inode);
 	iput(main_bm_inode);
 
 out:
-	if (local_alloc_inode)
-		iput(local_alloc_inode);
+	iput(local_alloc_inode);
 
 	kfree(alloc_copy);
 }
@@ -508,7 +506,7 @@ int ocfs2_begin_local_alloc_recovery(struct ocfs2_super *osb,
 		goto bail;
 	}
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	status = ocfs2_read_inode_block_full(inode, &alloc_bh,
 					     OCFS2_BH_IGNORE_CACHE);
@@ -541,7 +539,7 @@ bail:
 	brelse(alloc_bh);
 
 	if (inode) {
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 		iput(inode);
 	}
 
@@ -573,7 +571,7 @@ int ocfs2_complete_local_alloc_recovery(struct ocfs2_super *osb,
 		goto out;
 	}
 
-	mutex_lock(&main_bm_inode->i_mutex);
+	inode_lock(main_bm_inode);
 
 	status = ocfs2_inode_lock(main_bm_inode, &main_bm_bh, 1);
 	if (status < 0) {
@@ -603,7 +601,7 @@ out_unlock:
 	ocfs2_inode_unlock(main_bm_inode, 1);
 
 out_mutex:
-	mutex_unlock(&main_bm_inode->i_mutex);
+	inode_unlock(main_bm_inode);
 
 	brelse(main_bm_bh);
 
@@ -645,7 +643,7 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
 		goto bail;
 	}
 
-	mutex_lock(&local_alloc_inode->i_mutex);
+	inode_lock(local_alloc_inode);
 
 	/*
 	 * We must double check state and allocator bits because
@@ -711,7 +709,7 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
 	status = 0;
 bail:
 	if (status < 0 && local_alloc_inode) {
-		mutex_unlock(&local_alloc_inode->i_mutex);
+		inode_unlock(local_alloc_inode);
 		iput(local_alloc_inode);
 	}
 
@@ -1087,7 +1085,7 @@ static int ocfs2_recalc_la_window(struct ocfs2_super *osb,
 		} else {
 			osb->local_alloc_state = OCFS2_LA_DISABLED;
 		}
-		queue_delayed_work(ocfs2_wq, &osb->la_enable_wq,
+		queue_delayed_work(osb->ocfs2_wq, &osb->la_enable_wq,
 				   OCFS2_LA_ENABLE_INTERVAL);
 		goto out_unlock;
 	}
@@ -1327,9 +1325,7 @@ bail:
 
 	brelse(main_bm_bh);
 
-	if (main_bm_inode)
-		iput(main_bm_inode);
-
+	iput(main_bm_inode);
 	kfree(alloc_copy);
 
 	if (ac)
diff --git a/fs/ocfs2/locks.c b/fs/ocfs2/locks.c
index 652ece4a9d9e..d56f0079b858 100644
--- a/fs/ocfs2/locks.c
+++ b/fs/ocfs2/locks.c
@@ -67,7 +67,10 @@ static int ocfs2_do_flock(struct file *file, struct inode *inode,
 		 */
 
 		locks_lock_file_wait(file,
-				     &(struct file_lock){.fl_type = F_UNLCK});
+				&(struct file_lock) {
+					.fl_type = F_UNLCK,
+					.fl_flags = FL_FLOCK
+				});
 
 		ocfs2_file_unlock(file);
 	}
diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c
index 9581d190f6e1..71545ad4628c 100644
--- a/fs/ocfs2/mmap.c
+++ b/fs/ocfs2/mmap.c
@@ -65,13 +65,13 @@ static int __ocfs2_page_mkwrite(struct file *file, struct buffer_head *di_bh,
 	struct inode *inode = file_inode(file);
 	struct address_space *mapping = inode->i_mapping;
 	loff_t pos = page_offset(page);
-	unsigned int len = PAGE_CACHE_SIZE;
+	unsigned int len = PAGE_SIZE;
 	pgoff_t last_index;
 	struct page *locked_page = NULL;
 	void *fsdata;
 	loff_t size = i_size_read(inode);
 
-	last_index = (size - 1) >> PAGE_CACHE_SHIFT;
+	last_index = (size - 1) >> PAGE_SHIFT;
 
 	/*
 	 * There are cases that lead to the page no longer bebongs to the
@@ -102,10 +102,10 @@ static int __ocfs2_page_mkwrite(struct file *file, struct buffer_head *di_bh,
 	 * because the "write" would invalidate their data.
 	 */
 	if (page->index == last_index)
-		len = ((size - 1) & ~PAGE_CACHE_MASK) + 1;
+		len = ((size - 1) & ~PAGE_MASK) + 1;
 
-	ret = ocfs2_write_begin_nolock(file, mapping, pos, len, 0, &locked_page,
-				       &fsdata, di_bh, page);
+	ret = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_MMAP,
+				       &locked_page, &fsdata, di_bh, page);
 	if (ret) {
 		if (ret != -ENOSPC)
 			mlog_errno(ret);
@@ -147,6 +147,10 @@ static int ocfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	ret = ocfs2_inode_lock(inode, &di_bh, 1);
 	if (ret < 0) {
 		mlog_errno(ret);
+		if (ret == -ENOMEM)
+			ret = VM_FAULT_OOM;
+		else
+			ret = VM_FAULT_SIGBUS;
 		goto out;
 	}
 
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 124471d26a73..e3d05d9901a3 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -276,7 +276,7 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context,
 	 *	context->data_ac->ac_resv = &OCFS2_I(inode)->ip_la_data_resv;
 	 */
 
-	mutex_lock(&tl_inode->i_mutex);
+	inode_lock(tl_inode);
 
 	if (ocfs2_truncate_log_needs_flush(osb)) {
 		ret = __ocfs2_flush_truncate_log(osb);
@@ -338,7 +338,7 @@ out_commit:
 	ocfs2_commit_trans(osb, handle);
 
 out_unlock_mutex:
-	mutex_unlock(&tl_inode->i_mutex);
+	inode_unlock(tl_inode);
 
 	if (context->data_ac) {
 		ocfs2_free_alloc_context(context->data_ac);
@@ -632,7 +632,7 @@ static int ocfs2_move_extent(struct ocfs2_move_extents_context *context,
 		goto out;
 	}
 
-	mutex_lock(&gb_inode->i_mutex);
+	inode_lock(gb_inode);
 
 	ret = ocfs2_inode_lock(gb_inode, &gb_bh, 1);
 	if (ret) {
@@ -640,7 +640,7 @@ static int ocfs2_move_extent(struct ocfs2_move_extents_context *context,
 		goto out_unlock_gb_mutex;
 	}
 
-	mutex_lock(&tl_inode->i_mutex);
+	inode_lock(tl_inode);
 
 	handle = ocfs2_start_trans(osb, credits);
 	if (IS_ERR(handle)) {
@@ -708,11 +708,11 @@ out_commit:
 	brelse(gd_bh);
 
 out_unlock_tl_inode:
-	mutex_unlock(&tl_inode->i_mutex);
+	inode_unlock(tl_inode);
 
 	ocfs2_inode_unlock(gb_inode, 1);
 out_unlock_gb_mutex:
-	mutex_unlock(&gb_inode->i_mutex);
+	inode_unlock(gb_inode);
 	brelse(gb_bh);
 	iput(gb_inode);
 
@@ -905,7 +905,7 @@ static int ocfs2_move_extents(struct ocfs2_move_extents_context *context)
 	if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb))
 		return -EROFS;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	/*
 	 * This prevents concurrent writes from other nodes
@@ -969,7 +969,7 @@ out_inode_unlock:
 out_rw_unlock:
 	ocfs2_rw_unlock(inode, 1);
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	return status;
 }
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 3b48ac25d8a7..6b3e87189a64 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -367,7 +367,7 @@ 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;
@@ -1045,7 +1045,7 @@ leave:
 	if (orphan_dir) {
 		/* This was locked for us in ocfs2_prepare_orphan_dir() */
 		ocfs2_inode_unlock(orphan_dir, 1);
-		mutex_unlock(&orphan_dir->i_mutex);
+		inode_unlock(orphan_dir);
 		iput(orphan_dir);
 	}
 
@@ -1664,7 +1664,7 @@ bail:
 	if (orphan_dir) {
 		/* This was locked for us in ocfs2_prepare_orphan_dir() */
 		ocfs2_inode_unlock(orphan_dir, 1);
-		mutex_unlock(&orphan_dir->i_mutex);
+		inode_unlock(orphan_dir);
 		iput(orphan_dir);
 	}
 
@@ -1683,8 +1683,7 @@ bail:
 	if (new_inode)
 		sync_mapping_buffers(old_inode->i_mapping);
 
-	if (new_inode)
-		iput(new_inode);
+	iput(new_inode);
 
 	ocfs2_free_dir_lookup_result(&target_lookup_res);
 	ocfs2_free_dir_lookup_result(&old_entry_lookup);
@@ -1958,6 +1957,7 @@ static int ocfs2_symlink(struct inode *dir,
 	inode->i_rdev = 0;
 	newsize = l - 1;
 	inode->i_op = &ocfs2_symlink_inode_operations;
+	inode_nohighmem(inode);
 	if (l > ocfs2_fast_symlink_chars(sb)) {
 		u32 offset = 0;
 
@@ -2121,11 +2121,11 @@ static int ocfs2_lookup_lock_orphan_dir(struct ocfs2_super *osb,
 		return ret;
 	}
 
-	mutex_lock(&orphan_dir_inode->i_mutex);
+	inode_lock(orphan_dir_inode);
 
 	ret = ocfs2_inode_lock(orphan_dir_inode, &orphan_dir_bh, 1);
 	if (ret < 0) {
-		mutex_unlock(&orphan_dir_inode->i_mutex);
+		inode_unlock(orphan_dir_inode);
 		iput(orphan_dir_inode);
 
 		mlog_errno(ret);
@@ -2226,7 +2226,7 @@ out:
 
 	if (ret) {
 		ocfs2_inode_unlock(orphan_dir_inode, 1);
-		mutex_unlock(&orphan_dir_inode->i_mutex);
+		inode_unlock(orphan_dir_inode);
 		iput(orphan_dir_inode);
 	}
 
@@ -2372,6 +2372,15 @@ int ocfs2_orphan_del(struct ocfs2_super *osb,
 	     (unsigned long long)OCFS2_I(orphan_dir_inode)->ip_blkno,
 	     name, strlen(name));
 
+	status = ocfs2_journal_access_di(handle,
+					 INODE_CACHE(orphan_dir_inode),
+					 orphan_dir_bh,
+					 OCFS2_JOURNAL_ACCESS_WRITE);
+	if (status < 0) {
+		mlog_errno(status);
+		goto leave;
+	}
+
 	/* find it's spot in the orphan directory */
 	status = ocfs2_find_entry(name, strlen(name), orphan_dir_inode,
 				  &lookup);
@@ -2387,15 +2396,6 @@ int ocfs2_orphan_del(struct ocfs2_super *osb,
 		goto leave;
 	}
 
-	status = ocfs2_journal_access_di(handle,
-					 INODE_CACHE(orphan_dir_inode),
-					 orphan_dir_bh,
-					 OCFS2_JOURNAL_ACCESS_WRITE);
-	if (status < 0) {
-		mlog_errno(status);
-		goto leave;
-	}
-
 	/* do the i_nlink dance! :) */
 	orphan_fe = (struct ocfs2_dinode *) orphan_dir_bh->b_data;
 	if (S_ISDIR(inode->i_mode))
@@ -2495,7 +2495,7 @@ out:
 			ocfs2_free_alloc_context(inode_ac);
 
 		/* Unroll orphan dir locking */
-		mutex_unlock(&orphan_dir->i_mutex);
+		inode_unlock(orphan_dir);
 		ocfs2_inode_unlock(orphan_dir, 1);
 		iput(orphan_dir);
 	}
@@ -2602,7 +2602,7 @@ leave:
 	if (orphan_dir) {
 		/* This was locked for us in ocfs2_prepare_orphan_dir() */
 		ocfs2_inode_unlock(orphan_dir, 1);
-		mutex_unlock(&orphan_dir->i_mutex);
+		inode_unlock(orphan_dir);
 		iput(orphan_dir);
 	}
 
@@ -2689,7 +2689,7 @@ int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
 
 bail_unlock_orphan:
 	ocfs2_inode_unlock(orphan_dir_inode, 1);
-	mutex_unlock(&orphan_dir_inode->i_mutex);
+	inode_unlock(orphan_dir_inode);
 	iput(orphan_dir_inode);
 
 	ocfs2_free_dir_lookup_result(&orphan_insert);
@@ -2721,10 +2721,10 @@ int ocfs2_del_inode_from_orphan(struct ocfs2_super *osb,
 		goto bail;
 	}
 
-	mutex_lock(&orphan_dir_inode->i_mutex);
+	inode_lock(orphan_dir_inode);
 	status = ocfs2_inode_lock(orphan_dir_inode, &orphan_dir_bh, 1);
 	if (status < 0) {
-		mutex_unlock(&orphan_dir_inode->i_mutex);
+		inode_unlock(orphan_dir_inode);
 		iput(orphan_dir_inode);
 		mlog_errno(status);
 		goto bail;
@@ -2770,7 +2770,7 @@ bail_commit:
 
 bail_unlock_orphan:
 	ocfs2_inode_unlock(orphan_dir_inode, 1);
-	mutex_unlock(&orphan_dir_inode->i_mutex);
+	inode_unlock(orphan_dir_inode);
 	brelse(orphan_dir_bh);
 	iput(orphan_dir_inode);
 
@@ -2834,12 +2834,12 @@ int ocfs2_mv_orphaned_inode_to_new(struct inode *dir,
 		goto leave;
 	}
 
-	mutex_lock(&orphan_dir_inode->i_mutex);
+	inode_lock(orphan_dir_inode);
 
 	status = ocfs2_inode_lock(orphan_dir_inode, &orphan_dir_bh, 1);
 	if (status < 0) {
 		mlog_errno(status);
-		mutex_unlock(&orphan_dir_inode->i_mutex);
+		inode_unlock(orphan_dir_inode);
 		iput(orphan_dir_inode);
 		goto leave;
 	}
@@ -2901,7 +2901,7 @@ out_commit:
 	ocfs2_commit_trans(osb, handle);
 orphan_unlock:
 	ocfs2_inode_unlock(orphan_dir_inode, 1);
-	mutex_unlock(&orphan_dir_inode->i_mutex);
+	inode_unlock(orphan_dir_inode);
 	iput(orphan_dir_inode);
 leave:
 
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 7a0126267847..e63af7ddfe68 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -464,6 +464,14 @@ struct ocfs2_super
 	struct ocfs2_refcount_tree *osb_ref_tree_lru;
 
 	struct mutex system_file_mutex;
+
+	/*
+	 * OCFS2 needs to schedule several different types of work which
+	 * require cluster locking, disk I/O, recovery waits, etc. Since these
+	 * types of work tend to be heavy we avoid using the kernel events
+	 * workqueue and schedule on our own.
+	 */
+	struct workqueue_struct *ocfs2_wq;
 };
 
 #define OCFS2_SB(sb)	    ((struct ocfs2_super *)(sb)->s_fs_info)
@@ -814,10 +822,10 @@ static inline unsigned int ocfs2_page_index_to_clusters(struct super_block *sb,
 	u32 clusters = pg_index;
 	unsigned int cbits = OCFS2_SB(sb)->s_clustersize_bits;
 
-	if (unlikely(PAGE_CACHE_SHIFT > cbits))
-		clusters = pg_index << (PAGE_CACHE_SHIFT - cbits);
-	else if (PAGE_CACHE_SHIFT < cbits)
-		clusters = pg_index >> (cbits - PAGE_CACHE_SHIFT);
+	if (unlikely(PAGE_SHIFT > cbits))
+		clusters = pg_index << (PAGE_SHIFT - cbits);
+	else if (PAGE_SHIFT < cbits)
+		clusters = pg_index >> (cbits - PAGE_SHIFT);
 
 	return clusters;
 }
@@ -831,10 +839,10 @@ static inline pgoff_t ocfs2_align_clusters_to_page_index(struct super_block *sb,
 	unsigned int cbits = OCFS2_SB(sb)->s_clustersize_bits;
         pgoff_t index = clusters;
 
-	if (PAGE_CACHE_SHIFT > cbits) {
-		index = (pgoff_t)clusters >> (PAGE_CACHE_SHIFT - cbits);
-	} else if (PAGE_CACHE_SHIFT < cbits) {
-		index = (pgoff_t)clusters << (cbits - PAGE_CACHE_SHIFT);
+	if (PAGE_SHIFT > cbits) {
+		index = (pgoff_t)clusters >> (PAGE_SHIFT - cbits);
+	} else if (PAGE_SHIFT < cbits) {
+		index = (pgoff_t)clusters << (cbits - PAGE_SHIFT);
 	}
 
 	return index;
@@ -845,8 +853,8 @@ static inline unsigned int ocfs2_pages_per_cluster(struct super_block *sb)
 	unsigned int cbits = OCFS2_SB(sb)->s_clustersize_bits;
 	unsigned int pages_per_cluster = 1;
 
-	if (PAGE_CACHE_SHIFT < cbits)
-		pages_per_cluster = 1 << (cbits - PAGE_CACHE_SHIFT);
+	if (PAGE_SHIFT < cbits)
+		pages_per_cluster = 1 << (cbits - PAGE_SHIFT);
 
 	return pages_per_cluster;
 }
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index 6cb019b7c6a8..f8f5fc5e6c05 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -1450,28 +1450,20 @@ DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_remove_inode_range);
 
 TRACE_EVENT(ocfs2_prepare_inode_for_write,
 	TP_PROTO(unsigned long long ino, unsigned long long saved_pos,
-		 int appending, unsigned long count,
-		 int *direct_io, int *has_refcount),
-	TP_ARGS(ino, saved_pos, appending, count, direct_io, has_refcount),
+		 unsigned long count),
+	TP_ARGS(ino, saved_pos, count),
 	TP_STRUCT__entry(
 		__field(unsigned long long, ino)
 		__field(unsigned long long, saved_pos)
-		__field(int, appending)
 		__field(unsigned long, count)
-		__field(int, direct_io)
-		__field(int, has_refcount)
 	),
 	TP_fast_assign(
 		__entry->ino = ino;
 		__entry->saved_pos = saved_pos;
-		__entry->appending = appending;
 		__entry->count = count;
-		__entry->direct_io = direct_io ? *direct_io : -1;
-		__entry->has_refcount = has_refcount ? *has_refcount : -1;
 	),
-	TP_printk("%llu %llu %d %lu %d %d", __entry->ino,
-		  __entry->saved_pos, __entry->appending, __entry->count,
-		  __entry->direct_io, __entry->has_refcount)
+	TP_printk("%llu %llu %lu", __entry->ino,
+		  __entry->saved_pos, __entry->count)
 );
 
 DEFINE_OCFS2_INT_EVENT(generic_file_aio_read_ret);
@@ -1540,6 +1532,8 @@ DEFINE_OCFS2_ULL_INT_EVENT(ocfs2_read_locked_inode);
 DEFINE_OCFS2_INT_INT_EVENT(ocfs2_check_orphan_recovery_state);
 
 DEFINE_OCFS2_ULL_EVENT(ocfs2_validate_inode_block);
+DEFINE_OCFS2_ULL_EVENT(ocfs2_filecheck_validate_inode_block);
+DEFINE_OCFS2_ULL_EVENT(ocfs2_filecheck_repair_inode_block);
 
 TRACE_EVENT(ocfs2_inode_is_valid_to_delete,
 	TP_PROTO(void *task, void *dc_task, unsigned long long ino,
@@ -2035,6 +2029,8 @@ DEFINE_OCFS2_UINT_INT_EVENT(ocfs2_release_dquot);
 
 DEFINE_OCFS2_UINT_INT_EVENT(ocfs2_acquire_dquot);
 
+DEFINE_OCFS2_UINT_INT_EVENT(ocfs2_get_next_id);
+
 DEFINE_OCFS2_UINT_INT_EVENT(ocfs2_mark_dquot_dirty);
 
 /* End of trace events for fs/ocfs2/quota_global.c. */
diff --git a/fs/ocfs2/quota.h b/fs/ocfs2/quota.h
index b6d51333ad02..d153e6e31529 100644
--- a/fs/ocfs2/quota.h
+++ b/fs/ocfs2/quota.h
@@ -82,7 +82,7 @@ struct ocfs2_quota_chunk {
 extern struct kmem_cache *ocfs2_dquot_cachep;
 extern struct kmem_cache *ocfs2_qf_chunk_cachep;
 
-extern struct qtree_fmt_operations ocfs2_global_ops;
+extern const struct qtree_fmt_operations ocfs2_global_ops;
 
 struct ocfs2_quota_recovery *ocfs2_begin_quota_recovery(
 				struct ocfs2_super *osb, int slot_num);
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index c93d67220887..ab6a6cdcf91c 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -123,7 +123,7 @@ static int ocfs2_global_is_id(void *dp, struct dquot *dquot)
 		      dquot->dq_id);
 }
 
-struct qtree_fmt_operations ocfs2_global_ops = {
+const struct qtree_fmt_operations ocfs2_global_ops = {
 	.mem2disk_dqblk = ocfs2_global_mem2diskdqb,
 	.disk2mem_dqblk = ocfs2_global_disk2memdqb,
 	.is_id = ocfs2_global_is_id,
@@ -308,7 +308,7 @@ int ocfs2_lock_global_qf(struct ocfs2_mem_dqinfo *oinfo, int ex)
 		WARN_ON(bh != oinfo->dqi_gqi_bh);
 	spin_unlock(&dq_data_lock);
 	if (ex) {
-		mutex_lock(&oinfo->dqi_gqinode->i_mutex);
+		inode_lock(oinfo->dqi_gqinode);
 		down_write(&OCFS2_I(oinfo->dqi_gqinode)->ip_alloc_sem);
 	} else {
 		down_read(&OCFS2_I(oinfo->dqi_gqinode)->ip_alloc_sem);
@@ -320,7 +320,7 @@ void ocfs2_unlock_global_qf(struct ocfs2_mem_dqinfo *oinfo, int ex)
 {
 	if (ex) {
 		up_write(&OCFS2_I(oinfo->dqi_gqinode)->ip_alloc_sem);
-		mutex_unlock(&oinfo->dqi_gqinode->i_mutex);
+		inode_unlock(oinfo->dqi_gqinode);
 	} else {
 		up_read(&OCFS2_I(oinfo->dqi_gqinode)->ip_alloc_sem);
 	}
@@ -726,7 +726,7 @@ static int ocfs2_release_dquot(struct dquot *dquot)
 		dqgrab(dquot);
 		/* First entry on list -> queue work */
 		if (llist_add(&OCFS2_DQUOT(dquot)->list, &osb->dquot_drop_list))
-			queue_work(ocfs2_wq, &osb->dquot_drop_work);
+			queue_work(osb->ocfs2_wq, &osb->dquot_drop_work);
 		goto out;
 	}
 	status = ocfs2_lock_global_qf(oinfo, 1);
@@ -860,6 +860,37 @@ out:
 	return status;
 }
 
+static int ocfs2_get_next_id(struct super_block *sb, struct kqid *qid)
+{
+	int type = qid->type;
+	struct ocfs2_mem_dqinfo *info = sb_dqinfo(sb, type)->dqi_priv;
+	int status = 0;
+
+	trace_ocfs2_get_next_id(from_kqid(&init_user_ns, *qid), type);
+	if (!sb_has_quota_loaded(sb, type)) {
+		status = -ESRCH;
+		goto out;
+	}
+	status = ocfs2_lock_global_qf(info, 0);
+	if (status < 0)
+		goto out;
+	status = ocfs2_qinfo_lock(info, 0);
+	if (status < 0)
+		goto out_global;
+	status = qtree_get_next_id(&info->dqi_gi, qid);
+	ocfs2_qinfo_unlock(info, 0);
+out_global:
+	ocfs2_unlock_global_qf(info, 0);
+out:
+	/*
+	 * Avoid logging ENOENT since it just means there isn't next ID and
+	 * ESRCH which means quota isn't enabled for the filesystem.
+	 */
+	if (status && status != -ENOENT && status != -ESRCH)
+		mlog_errno(status);
+	return status;
+}
+
 static int ocfs2_mark_dquot_dirty(struct dquot *dquot)
 {
 	unsigned long mask = (1 << (DQ_LASTSET_B + QIF_ILIMITS_B)) |
@@ -968,4 +999,5 @@ const struct dquot_operations ocfs2_quota_operations = {
 	.write_info	= ocfs2_write_info,
 	.alloc_dquot	= ocfs2_alloc_dquot,
 	.destroy_dquot	= ocfs2_destroy_dquot,
+	.get_next_id	= ocfs2_get_next_id,
 };
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 252119860e6c..744d5d90c363 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -807,7 +807,7 @@ int ocfs2_remove_refcount_tree(struct inode *inode, struct buffer_head *di_bh)
 			mlog_errno(ret);
 			goto out;
 		}
-		mutex_lock(&alloc_inode->i_mutex);
+		inode_lock(alloc_inode);
 
 		ret = ocfs2_inode_lock(alloc_inode, &alloc_bh, 1);
 		if (ret) {
@@ -867,7 +867,7 @@ out_unlock:
 	}
 out_mutex:
 	if (alloc_inode) {
-		mutex_unlock(&alloc_inode->i_mutex);
+		inode_unlock(alloc_inode);
 		iput(alloc_inode);
 	}
 out:
@@ -2937,16 +2937,16 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle,
 		end = i_size_read(inode);
 
 	while (offset < end) {
-		page_index = offset >> PAGE_CACHE_SHIFT;
-		map_end = ((loff_t)page_index + 1) << PAGE_CACHE_SHIFT;
+		page_index = offset >> PAGE_SHIFT;
+		map_end = ((loff_t)page_index + 1) << PAGE_SHIFT;
 		if (map_end > end)
 			map_end = end;
 
 		/* from, to is the offset within the page. */
-		from = offset & (PAGE_CACHE_SIZE - 1);
-		to = PAGE_CACHE_SIZE;
-		if (map_end & (PAGE_CACHE_SIZE - 1))
-			to = map_end & (PAGE_CACHE_SIZE - 1);
+		from = offset & (PAGE_SIZE - 1);
+		to = PAGE_SIZE;
+		if (map_end & (PAGE_SIZE - 1))
+			to = map_end & (PAGE_SIZE - 1);
 
 		page = find_or_create_page(mapping, page_index, GFP_NOFS);
 		if (!page) {
@@ -2956,10 +2956,10 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle,
 		}
 
 		/*
-		 * In case PAGE_CACHE_SIZE <= CLUSTER_SIZE, This page
+		 * In case PAGE_SIZE <= CLUSTER_SIZE, This page
 		 * can't be dirtied before we CoW it out.
 		 */
-		if (PAGE_CACHE_SIZE <= OCFS2_SB(sb)->s_clustersize)
+		if (PAGE_SIZE <= OCFS2_SB(sb)->s_clustersize)
 			BUG_ON(PageDirty(page));
 
 		if (!PageUptodate(page)) {
@@ -2987,7 +2987,7 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle,
 		mark_page_accessed(page);
 unlock:
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 		page = NULL;
 		offset = map_end;
 		if (ret)
@@ -3165,8 +3165,8 @@ int ocfs2_cow_sync_writeback(struct super_block *sb,
 	}
 
 	while (offset < end) {
-		page_index = offset >> PAGE_CACHE_SHIFT;
-		map_end = ((loff_t)page_index + 1) << PAGE_CACHE_SHIFT;
+		page_index = offset >> PAGE_SHIFT;
+		map_end = ((loff_t)page_index + 1) << PAGE_SHIFT;
 		if (map_end > end)
 			map_end = end;
 
@@ -3182,7 +3182,7 @@ int ocfs2_cow_sync_writeback(struct super_block *sb,
 			mark_page_accessed(page);
 
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 		page = NULL;
 		offset = map_end;
 		if (ret)
@@ -4197,7 +4197,7 @@ static int __ocfs2_reflink(struct dentry *old_dentry,
 		goto out;
 	}
 
-	mutex_lock_nested(&new_inode->i_mutex, I_MUTEX_CHILD);
+	inode_lock_nested(new_inode, I_MUTEX_CHILD);
 	ret = ocfs2_inode_lock_nested(new_inode, &new_bh, 1,
 				      OI_LS_REFLINK_TARGET);
 	if (ret) {
@@ -4231,7 +4231,7 @@ inode_unlock:
 	ocfs2_inode_unlock(new_inode, 1);
 	brelse(new_bh);
 out_unlock:
-	mutex_unlock(&new_inode->i_mutex);
+	inode_unlock(new_inode);
 out:
 	if (!ret) {
 		ret = filemap_fdatawait(inode->i_mapping);
@@ -4402,11 +4402,11 @@ static int ocfs2_vfs_reflink(struct dentry *old_dentry, struct inode *dir,
 			return error;
 	}
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	error = dquot_initialize(dir);
 	if (!error)
 		error = ocfs2_reflink(old_dentry, dir, new_dentry, preserve);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	if (!error)
 		fsnotify_create(dir, new_dentry);
 	return error;
diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c
index d5da6f624142..18451e0fab81 100644
--- a/fs/ocfs2/resize.c
+++ b/fs/ocfs2/resize.c
@@ -54,11 +54,12 @@
 static u16 ocfs2_calc_new_backup_super(struct inode *inode,
 				       struct ocfs2_group_desc *gd,
 				       u16 cl_cpg,
+				       u16 old_bg_clusters,
 				       int set)
 {
 	int i;
 	u16 backups = 0;
-	u32 cluster;
+	u32 cluster, lgd_cluster;
 	u64 blkno, gd_blkno, lgd_blkno = le64_to_cpu(gd->bg_blkno);
 
 	for (i = 0; i < OCFS2_MAX_BACKUP_SUPERBLOCKS; i++) {
@@ -71,6 +72,12 @@ static u16 ocfs2_calc_new_backup_super(struct inode *inode,
 		else if (gd_blkno > lgd_blkno)
 			break;
 
+		/* check if already done backup super */
+		lgd_cluster = ocfs2_blocks_to_clusters(inode->i_sb, lgd_blkno);
+		lgd_cluster += old_bg_clusters;
+		if (lgd_cluster >= cluster)
+			continue;
+
 		if (set)
 			ocfs2_set_bit(cluster % cl_cpg,
 				      (unsigned long *)gd->bg_bitmap);
@@ -99,6 +106,7 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle,
 	u16 chain, num_bits, backups = 0;
 	u16 cl_bpc = le16_to_cpu(cl->cl_bpc);
 	u16 cl_cpg = le16_to_cpu(cl->cl_cpg);
+	u16 old_bg_clusters;
 
 	trace_ocfs2_update_last_group_and_inode(new_clusters,
 						first_new_cluster);
@@ -112,6 +120,7 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle,
 
 	group = (struct ocfs2_group_desc *)group_bh->b_data;
 
+	old_bg_clusters = le16_to_cpu(group->bg_bits) / cl_bpc;
 	/* update the group first. */
 	num_bits = new_clusters * cl_bpc;
 	le16_add_cpu(&group->bg_bits, num_bits);
@@ -125,7 +134,7 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle,
 				     OCFS2_FEATURE_COMPAT_BACKUP_SB)) {
 		backups = ocfs2_calc_new_backup_super(bm_inode,
 						     group,
-						     cl_cpg, 1);
+						     cl_cpg, old_bg_clusters, 1);
 		le16_add_cpu(&group->bg_free_bits_count, -1 * backups);
 	}
 
@@ -163,7 +172,7 @@ out_rollback:
 	if (ret < 0) {
 		ocfs2_calc_new_backup_super(bm_inode,
 					    group,
-					    cl_cpg, 0);
+					    cl_cpg, old_bg_clusters, 0);
 		le16_add_cpu(&group->bg_free_bits_count, backups);
 		le16_add_cpu(&group->bg_bits, -1 * num_bits);
 		le16_add_cpu(&group->bg_free_bits_count, -1 * num_bits);
@@ -187,7 +196,7 @@ static int update_backups(struct inode * inode, u32 clusters, char *data)
 	for (i = 0; i < OCFS2_MAX_BACKUP_SUPERBLOCKS; i++) {
 		blkno = ocfs2_backup_super_blkno(inode->i_sb, i);
 		cluster = ocfs2_blocks_to_clusters(inode->i_sb, blkno);
-		if (cluster > clusters)
+		if (cluster >= clusters)
 			break;
 
 		ret = ocfs2_read_blocks_sync(osb, blkno, 1, &backup);
@@ -292,7 +301,7 @@ int ocfs2_group_extend(struct inode * inode, int new_clusters)
 		goto out;
 	}
 
-	mutex_lock(&main_bm_inode->i_mutex);
+	inode_lock(main_bm_inode);
 
 	ret = ocfs2_inode_lock(main_bm_inode, &main_bm_bh, 1);
 	if (ret < 0) {
@@ -366,7 +375,7 @@ out_unlock:
 	ocfs2_inode_unlock(main_bm_inode, 1);
 
 out_mutex:
-	mutex_unlock(&main_bm_inode->i_mutex);
+	inode_unlock(main_bm_inode);
 	iput(main_bm_inode);
 
 out:
@@ -477,7 +486,7 @@ int ocfs2_group_add(struct inode *inode, struct ocfs2_new_group_input *input)
 		goto out;
 	}
 
-	mutex_lock(&main_bm_inode->i_mutex);
+	inode_lock(main_bm_inode);
 
 	ret = ocfs2_inode_lock(main_bm_inode, &main_bm_bh, 1);
 	if (ret < 0) {
@@ -581,7 +590,7 @@ out_unlock:
 	ocfs2_inode_unlock(main_bm_inode, 1);
 
 out_mutex:
-	mutex_unlock(&main_bm_inode->i_mutex);
+	inode_unlock(main_bm_inode);
 	iput(main_bm_inode);
 
 out:
diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c
index e78a203d44c8..1e09592148ad 100644
--- a/fs/ocfs2/slot_map.c
+++ b/fs/ocfs2/slot_map.c
@@ -322,8 +322,7 @@ static void __ocfs2_free_slot_info(struct ocfs2_slot_info *si)
 	if (si == NULL)
 		return;
 
-	if (si->si_inode)
-		iput(si->si_inode);
+	iput(si->si_inode);
 	if (si->si_bh) {
 		for (i = 0; i < si->si_blocks; i++) {
 			if (si->si_bh[i]) {
@@ -503,8 +502,17 @@ int ocfs2_find_slot(struct ocfs2_super *osb)
 	trace_ocfs2_find_slot(osb->slot_num);
 
 	status = ocfs2_update_disk_slot(osb, si, osb->slot_num);
-	if (status < 0)
+	if (status < 0) {
 		mlog_errno(status);
+		/*
+		 * if write block failed, invalidate slot to avoid overwrite
+		 * slot during dismount in case another node rightly has mounted
+		 */
+		spin_lock(&osb->osb_lock);
+		ocfs2_invalidate_slot(si, osb->slot_num);
+		osb->slot_num = OCFS2_INVALID_SLOT;
+		spin_unlock(&osb->osb_lock);
+	}
 
 bail:
 	return status;
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 5d965e83bd43..13219ed73e1d 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -629,7 +629,8 @@ static struct attribute_group ocfs2_attr_group = {
 	.attrs = ocfs2_attrs,
 };
 
-static struct kset *ocfs2_kset;
+struct kset *ocfs2_kset;
+EXPORT_SYMBOL_GPL(ocfs2_kset);
 
 static void ocfs2_sysfs_exit(void)
 {
diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h
index 66334a30cea8..f2dce10fae54 100644
--- a/fs/ocfs2/stackglue.h
+++ b/fs/ocfs2/stackglue.h
@@ -298,4 +298,6 @@ void ocfs2_stack_glue_set_max_proto_version(struct ocfs2_protocol_version *max_p
 int ocfs2_stack_glue_register(struct ocfs2_stack_plugin *plugin);
 void ocfs2_stack_glue_unregister(struct ocfs2_stack_plugin *plugin);
 
+extern struct kset *ocfs2_kset;
+
 #endif  /* STACKGLUE_H */
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index fc6d25f6d444..2f19aeec5482 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -141,7 +141,7 @@ void ocfs2_free_ac_resource(struct ocfs2_alloc_context *ac)
 		if (ac->ac_which != OCFS2_AC_USE_LOCAL)
 			ocfs2_inode_unlock(inode, 1);
 
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 
 		iput(inode);
 		ac->ac_inode = NULL;
@@ -797,11 +797,11 @@ static int ocfs2_reserve_suballoc_bits(struct ocfs2_super *osb,
 		return -EINVAL;
 	}
 
-	mutex_lock(&alloc_inode->i_mutex);
+	inode_lock(alloc_inode);
 
 	status = ocfs2_inode_lock(alloc_inode, &bh, 1);
 	if (status < 0) {
-		mutex_unlock(&alloc_inode->i_mutex);
+		inode_unlock(alloc_inode);
 		iput(alloc_inode);
 
 		mlog_errno(status);
@@ -2875,10 +2875,10 @@ int ocfs2_test_inode_bit(struct ocfs2_super *osb, u64 blkno, int *res)
 		goto bail;
 	}
 
-	mutex_lock(&inode_alloc_inode->i_mutex);
+	inode_lock(inode_alloc_inode);
 	status = ocfs2_inode_lock(inode_alloc_inode, &alloc_bh, 0);
 	if (status < 0) {
-		mutex_unlock(&inode_alloc_inode->i_mutex);
+		inode_unlock(inode_alloc_inode);
 		iput(inode_alloc_inode);
 		mlog(ML_ERROR, "lock on alloc inode on slot %u failed %d\n",
 		     (u32)suballoc_slot, status);
@@ -2891,7 +2891,7 @@ int ocfs2_test_inode_bit(struct ocfs2_super *osb, u64 blkno, int *res)
 		mlog(ML_ERROR, "test suballoc bit failed %d\n", status);
 
 	ocfs2_inode_unlock(inode_alloc_inode, 0);
-	mutex_unlock(&inode_alloc_inode->i_mutex);
+	inode_unlock(inode_alloc_inode);
 
 	iput(inode_alloc_inode);
 	brelse(alloc_bh);
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 2de4c8a9340c..d7cae3327de5 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -74,17 +74,12 @@
 #include "suballoc.h"
 
 #include "buffer_head_io.h"
+#include "filecheck.h"
 
 static struct kmem_cache *ocfs2_inode_cachep;
 struct kmem_cache *ocfs2_dquot_cachep;
 struct kmem_cache *ocfs2_qf_chunk_cachep;
 
-/* OCFS2 needs to schedule several different types of work which
- * require cluster locking, disk I/O, recovery waits, etc. Since these
- * types of work tend to be heavy we avoid using the kernel events
- * workqueue and schedule on our own. */
-struct workqueue_struct *ocfs2_wq = NULL;
-
 static struct dentry *ocfs2_debugfs_root;
 
 MODULE_AUTHOR("Oracle");
@@ -236,6 +231,7 @@ static int ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len)
 	struct ocfs2_recovery_map *rm = osb->recovery_map;
 	struct ocfs2_orphan_scan *os = &osb->osb_orphan_scan;
 	int i, out = 0;
+	unsigned long flags;
 
 	out += snprintf(buf + out, len - out,
 			"%10s => Id: %-s  Uuid: %-s  Gen: 0x%X  Label: %-s\n",
@@ -271,14 +267,14 @@ static int ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len)
 				cconn->cc_version.pv_minor);
 	}
 
-	spin_lock(&osb->dc_task_lock);
+	spin_lock_irqsave(&osb->dc_task_lock, flags);
 	out += snprintf(buf + out, len - out,
 			"%10s => Pid: %d  Count: %lu  WakeSeq: %lu  "
 			"WorkSeq: %lu\n", "DownCnvt",
 			(osb->dc_task ?  task_pid_nr(osb->dc_task) : -1),
 			osb->blocked_lock_count, osb->dc_wake_sequence,
 			osb->dc_work_sequence);
-	spin_unlock(&osb->dc_task_lock);
+	spin_unlock_irqrestore(&osb->dc_task_lock, flags);
 
 	spin_lock(&osb->osb_lock);
 	out += snprintf(buf + out, len - out, "%10s => Pid: %d  Nodes:",
@@ -609,8 +605,8 @@ static unsigned long long ocfs2_max_file_offset(unsigned int bbits,
 	/*
 	 * We might be limited by page cache size.
 	 */
-	if (bytes > PAGE_CACHE_SIZE) {
-		bytes = PAGE_CACHE_SIZE;
+	if (bytes > PAGE_SIZE) {
+		bytes = PAGE_SIZE;
 		trim = 1;
 		/*
 		 * Shift by 31 here so that we don't get larger than
@@ -1204,6 +1200,9 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 	/* Start this when the mount is almost sure of being successful */
 	ocfs2_orphan_scan_start(osb);
 
+	/* Create filecheck sysfile /sys/fs/ocfs2/<devname>/filecheck */
+	ocfs2_filecheck_create_sysfs(sb);
+
 	return status;
 
 read_super_error:
@@ -1280,6 +1279,8 @@ static int ocfs2_parse_options(struct super_block *sb,
 	int status, user_stack = 0;
 	char *p;
 	u32 tmp;
+	int token, option;
+	substring_t args[MAX_OPT_ARGS];
 
 	trace_ocfs2_parse_options(is_remount, options ? options : "(none)");
 
@@ -1298,9 +1299,6 @@ static int ocfs2_parse_options(struct super_block *sb,
 	}
 
 	while ((p = strsep(&options, ",")) != NULL) {
-		int token, option;
-		substring_t args[MAX_OPT_ARGS];
-
 		if (!*p)
 			continue;
 
@@ -1367,7 +1365,6 @@ static int ocfs2_parse_options(struct super_block *sb,
 				mopt->atime_quantum = option;
 			break;
 		case Opt_slot:
-			option = 0;
 			if (match_int(&args[0], &option)) {
 				status = 0;
 				goto bail;
@@ -1376,7 +1373,6 @@ static int ocfs2_parse_options(struct super_block *sb,
 				mopt->slot = (s16)option;
 			break;
 		case Opt_commit:
-			option = 0;
 			if (match_int(&args[0], &option)) {
 				status = 0;
 				goto bail;
@@ -1388,7 +1384,6 @@ static int ocfs2_parse_options(struct super_block *sb,
 			mopt->commit_interval = HZ * option;
 			break;
 		case Opt_localalloc:
-			option = 0;
 			if (match_int(&args[0], &option)) {
 				status = 0;
 				goto bail;
@@ -1612,33 +1607,25 @@ static int __init ocfs2_init(void)
 	if (status < 0)
 		goto out2;
 
-	ocfs2_wq = create_singlethread_workqueue("ocfs2_wq");
-	if (!ocfs2_wq) {
-		status = -ENOMEM;
-		goto out3;
-	}
-
 	ocfs2_debugfs_root = debugfs_create_dir("ocfs2", NULL);
 	if (!ocfs2_debugfs_root) {
 		status = -ENOMEM;
 		mlog(ML_ERROR, "Unable to create ocfs2 debugfs root.\n");
-		goto out4;
+		goto out3;
 	}
 
 	ocfs2_set_locking_protocol();
 
 	status = register_quota_format(&ocfs2_quota_format);
 	if (status < 0)
-		goto out4;
+		goto out3;
 	status = register_filesystem(&ocfs2_fs_type);
 	if (!status)
 		return 0;
 
 	unregister_quota_format(&ocfs2_quota_format);
-out4:
-	destroy_workqueue(ocfs2_wq);
-	debugfs_remove(ocfs2_debugfs_root);
 out3:
+	debugfs_remove(ocfs2_debugfs_root);
 	ocfs2_free_mem_caches();
 out2:
 	exit_ocfs2_uptodate_cache();
@@ -1649,11 +1636,6 @@ out1:
 
 static void __exit ocfs2_exit(void)
 {
-	if (ocfs2_wq) {
-		flush_workqueue(ocfs2_wq);
-		destroy_workqueue(ocfs2_wq);
-	}
-
 	unregister_quota_format(&ocfs2_quota_format);
 
 	debugfs_remove(ocfs2_debugfs_root);
@@ -1671,6 +1653,7 @@ static void ocfs2_put_super(struct super_block *sb)
 
 	ocfs2_sync_blockdev(sb);
 	ocfs2_dismount_volume(sb, 0);
+	ocfs2_filecheck_remove_sysfs(sb);
 }
 
 static int ocfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
@@ -1726,8 +1709,7 @@ static int ocfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
 	ocfs2_inode_unlock(inode, 0);
 	status = 0;
 bail:
-	if (inode)
-		iput(inode);
+	iput(inode);
 
 	if (status)
 		mlog_errno(status);
@@ -1744,8 +1726,8 @@ static void ocfs2_inode_init_once(void *data)
 	spin_lock_init(&oi->ip_lock);
 	ocfs2_extent_map_init(&oi->vfs_inode);
 	INIT_LIST_HEAD(&oi->ip_io_markers);
+	INIT_LIST_HEAD(&oi->ip_unwritten_list);
 	oi->ip_dir_start_lookup = 0;
-	mutex_init(&oi->ip_unaligned_aio);
 	init_rwsem(&oi->ip_alloc_sem);
 	init_rwsem(&oi->ip_xattr_sem);
 	mutex_init(&oi->ip_io_mutex);
@@ -1771,7 +1753,7 @@ static int ocfs2_initialize_mem_caches(void)
 				       sizeof(struct ocfs2_inode_info),
 				       0,
 				       (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD),
+						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
 				       ocfs2_inode_init_once);
 	ocfs2_dquot_cachep = kmem_cache_create("ocfs2_dquot_cache",
 					sizeof(struct ocfs2_dquot),
@@ -2348,6 +2330,12 @@ static int ocfs2_initialize_super(struct super_block *sb,
 	}
 	cleancache_init_shared_fs(sb);
 
+	osb->ocfs2_wq = create_singlethread_workqueue("ocfs2_wq");
+	if (!osb->ocfs2_wq) {
+		status = -ENOMEM;
+		mlog_errno(status);
+	}
+
 bail:
 	return status;
 }
@@ -2535,6 +2523,12 @@ static void ocfs2_delete_osb(struct ocfs2_super *osb)
 {
 	/* This function assumes that the caller has the main osb resource */
 
+	/* ocfs2_initializer_super have already created this workqueue */
+	if (osb->ocfs2_wq) {
+		flush_workqueue(osb->ocfs2_wq);
+		destroy_workqueue(osb->ocfs2_wq);
+	}
+
 	ocfs2_free_slot_info(osb);
 
 	kfree(osb->osb_orphan_wipes);
diff --git a/fs/ocfs2/super.h b/fs/ocfs2/super.h
index b477d0b1c7b6..b023e4f3d740 100644
--- a/fs/ocfs2/super.h
+++ b/fs/ocfs2/super.h
@@ -26,8 +26,6 @@
 #ifndef OCFS2_SUPER_H
 #define OCFS2_SUPER_H
 
-extern struct workqueue_struct *ocfs2_wq;
-
 int ocfs2_publish_get_mount_state(struct ocfs2_super *osb,
 				  int node_num);
 
diff --git a/fs/ocfs2/symlink.c b/fs/ocfs2/symlink.c
index 66edce7ecfd7..6c2a3e3c521c 100644
--- a/fs/ocfs2/symlink.c
+++ b/fs/ocfs2/symlink.c
@@ -88,8 +88,7 @@ const struct address_space_operations ocfs2_fast_symlink_aops = {
 
 const struct inode_operations ocfs2_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 	.getattr	= ocfs2_getattr,
 	.setattr	= ocfs2_setattr,
 	.setxattr	= generic_setxattr,
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index ebfdea78659b..7d3d979f57d9 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -544,8 +544,7 @@ static inline const char *ocfs2_xattr_prefix(int name_index)
 
 	if (name_index > 0 && name_index < OCFS2_XATTR_MAX)
 		handler = ocfs2_xattr_handler_map[name_index];
-
-	return handler ? handler->prefix : NULL;
+	return handler ? xattr_prefix(handler) : NULL;
 }
 
 static u32 ocfs2_xattr_name_hash(struct inode *inode,
@@ -884,14 +883,39 @@ static int ocfs2_xattr_value_truncate(struct inode *inode,
 	return ret;
 }
 
-static int ocfs2_xattr_list_entry(char *buffer, size_t size,
-				  size_t *result, const char *prefix,
+static int ocfs2_xattr_list_entry(struct super_block *sb,
+				  char *buffer, size_t size,
+				  size_t *result, int type,
 				  const char *name, int name_len)
 {
 	char *p = buffer + *result;
-	int prefix_len = strlen(prefix);
-	int total_len = prefix_len + name_len + 1;
+	const char *prefix;
+	int prefix_len;
+	int total_len;
 
+	switch(type) {
+	case OCFS2_XATTR_INDEX_USER:
+		if (OCFS2_SB(sb)->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR)
+			return 0;
+		break;
+
+	case OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS:
+	case OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT:
+		if (!(sb->s_flags & MS_POSIXACL))
+			return 0;
+		break;
+
+	case OCFS2_XATTR_INDEX_TRUSTED:
+		if (!capable(CAP_SYS_ADMIN))
+			return 0;
+		break;
+	}
+
+	prefix = ocfs2_xattr_prefix(type);
+	if (!prefix)
+		return 0;
+	prefix_len = strlen(prefix);
+	total_len = prefix_len + name_len + 1;
 	*result += total_len;
 
 	/* we are just looking for how big our buffer needs to be */
@@ -914,23 +938,20 @@ static int ocfs2_xattr_list_entries(struct inode *inode,
 {
 	size_t result = 0;
 	int i, type, ret;
-	const char *prefix, *name;
+	const char *name;
 
 	for (i = 0 ; i < le16_to_cpu(header->xh_count); i++) {
 		struct ocfs2_xattr_entry *entry = &header->xh_entries[i];
 		type = ocfs2_xattr_get_type(entry);
-		prefix = ocfs2_xattr_prefix(type);
-
-		if (prefix) {
-			name = (const char *)header +
-				le16_to_cpu(entry->xe_name_offset);
+		name = (const char *)header +
+			le16_to_cpu(entry->xe_name_offset);
 
-			ret = ocfs2_xattr_list_entry(buffer, buffer_size,
-						     &result, prefix, name,
-						     entry->xe_name_len);
-			if (ret)
-				return ret;
-		}
+		ret = ocfs2_xattr_list_entry(inode->i_sb,
+					     buffer, buffer_size,
+					     &result, type, name,
+					     entry->xe_name_len);
+		if (ret)
+			return ret;
 	}
 
 	return result;
@@ -2503,7 +2524,7 @@ static int ocfs2_xattr_free_block(struct inode *inode,
 		mlog_errno(ret);
 		goto out;
 	}
-	mutex_lock(&xb_alloc_inode->i_mutex);
+	inode_lock(xb_alloc_inode);
 
 	ret = ocfs2_inode_lock(xb_alloc_inode, &xb_alloc_bh, 1);
 	if (ret < 0) {
@@ -2528,7 +2549,7 @@ out_unlock:
 	ocfs2_inode_unlock(xb_alloc_inode, 1);
 	brelse(xb_alloc_bh);
 out_mutex:
-	mutex_unlock(&xb_alloc_inode->i_mutex);
+	inode_unlock(xb_alloc_inode);
 	iput(xb_alloc_inode);
 out:
 	brelse(blk_bh);
@@ -3598,17 +3619,17 @@ int ocfs2_xattr_set(struct inode *inode,
 		}
 	}
 
-	mutex_lock(&tl_inode->i_mutex);
+	inode_lock(tl_inode);
 
 	if (ocfs2_truncate_log_needs_flush(osb)) {
 		ret = __ocfs2_flush_truncate_log(osb);
 		if (ret < 0) {
-			mutex_unlock(&tl_inode->i_mutex);
+			inode_unlock(tl_inode);
 			mlog_errno(ret);
 			goto cleanup;
 		}
 	}
-	mutex_unlock(&tl_inode->i_mutex);
+	inode_unlock(tl_inode);
 
 	ret = ocfs2_init_xattr_set_ctxt(inode, di, &xi, &xis,
 					&xbs, &ctxt, ref_meta, &credits);
@@ -4033,32 +4054,30 @@ static int ocfs2_list_xattr_bucket(struct inode *inode,
 	int ret = 0, type;
 	struct ocfs2_xattr_tree_list *xl = (struct ocfs2_xattr_tree_list *)para;
 	int i, block_off, new_offset;
-	const char *prefix, *name;
+	const char *name;
 
 	for (i = 0 ; i < le16_to_cpu(bucket_xh(bucket)->xh_count); i++) {
 		struct ocfs2_xattr_entry *entry = &bucket_xh(bucket)->xh_entries[i];
 		type = ocfs2_xattr_get_type(entry);
-		prefix = ocfs2_xattr_prefix(type);
 
-		if (prefix) {
-			ret = ocfs2_xattr_bucket_get_name_value(inode->i_sb,
-								bucket_xh(bucket),
-								i,
-								&block_off,
-								&new_offset);
-			if (ret)
-				break;
+		ret = ocfs2_xattr_bucket_get_name_value(inode->i_sb,
+							bucket_xh(bucket),
+							i,
+							&block_off,
+							&new_offset);
+		if (ret)
+			break;
 
-			name = (const char *)bucket_block(bucket, block_off) +
-				new_offset;
-			ret = ocfs2_xattr_list_entry(xl->buffer,
-						     xl->buffer_size,
-						     &xl->result,
-						     prefix, name,
-						     entry->xe_name_len);
-			if (ret)
-				break;
-		}
+		name = (const char *)bucket_block(bucket, block_off) +
+			new_offset;
+		ret = ocfs2_xattr_list_entry(inode->i_sb,
+					     xl->buffer,
+					     xl->buffer_size,
+					     &xl->result,
+					     type, name,
+					     entry->xe_name_len);
+		if (ret)
+			break;
 	}
 
 	return ret;
@@ -5441,7 +5460,7 @@ static int ocfs2_rm_xattr_cluster(struct inode *inode,
 		return ret;
 	}
 
-	mutex_lock(&tl_inode->i_mutex);
+	inode_lock(tl_inode);
 
 	if (ocfs2_truncate_log_needs_flush(osb)) {
 		ret = __ocfs2_flush_truncate_log(osb);
@@ -5485,7 +5504,7 @@ out_commit:
 out:
 	ocfs2_schedule_truncate_log_flush(osb, 1);
 
-	mutex_unlock(&tl_inode->i_mutex);
+	inode_unlock(tl_inode);
 
 	if (meta_ac)
 		ocfs2_free_alloc_context(meta_ac);
@@ -7226,39 +7245,22 @@ int ocfs2_init_security_and_acl(struct inode *dir,
 leave:
 	return ret;
 }
+
 /*
  * 'security' attributes support
  */
-static size_t ocfs2_xattr_security_list(struct dentry *dentry, char *list,
-					size_t list_size, const char *name,
-					size_t name_len, int type)
-{
-	const size_t prefix_len = XATTR_SECURITY_PREFIX_LEN;
-	const size_t total_len = prefix_len + name_len + 1;
-
-	if (list && total_len <= list_size) {
-		memcpy(list, XATTR_SECURITY_PREFIX, prefix_len);
-		memcpy(list + prefix_len, name, name_len);
-		list[prefix_len + name_len] = '\0';
-	}
-	return total_len;
-}
-
-static int ocfs2_xattr_security_get(struct dentry *dentry, const char *name,
-				    void *buffer, size_t size, int type)
+static int ocfs2_xattr_security_get(const struct xattr_handler *handler,
+				    struct dentry *dentry, const char *name,
+				    void *buffer, size_t size)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	return ocfs2_xattr_get(d_inode(dentry), OCFS2_XATTR_INDEX_SECURITY,
 			       name, buffer, size);
 }
 
-static int ocfs2_xattr_security_set(struct dentry *dentry, const char *name,
-		const void *value, size_t size, int flags, int type)
+static int ocfs2_xattr_security_set(const struct xattr_handler *handler,
+				    struct dentry *dentry, const char *name,
+				    const void *value, size_t size, int flags)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
-
 	return ocfs2_xattr_set(d_inode(dentry), OCFS2_XATTR_INDEX_SECURITY,
 			       name, value, size, flags);
 }
@@ -7311,7 +7313,6 @@ int ocfs2_init_security_set(handle_t *handle,
 
 const struct xattr_handler ocfs2_xattr_security_handler = {
 	.prefix	= XATTR_SECURITY_PREFIX,
-	.list	= ocfs2_xattr_security_list,
 	.get	= ocfs2_xattr_security_get,
 	.set	= ocfs2_xattr_security_set,
 };
@@ -7319,46 +7320,24 @@ const struct xattr_handler ocfs2_xattr_security_handler = {
 /*
  * 'trusted' attributes support
  */
-static size_t ocfs2_xattr_trusted_list(struct dentry *dentry, char *list,
-				       size_t list_size, const char *name,
-				       size_t name_len, int type)
-{
-	const size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN;
-	const size_t total_len = prefix_len + name_len + 1;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return 0;
-
-	if (list && total_len <= list_size) {
-		memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len);
-		memcpy(list + prefix_len, name, name_len);
-		list[prefix_len + name_len] = '\0';
-	}
-	return total_len;
-}
-
-static int ocfs2_xattr_trusted_get(struct dentry *dentry, const char *name,
-		void *buffer, size_t size, int type)
+static int ocfs2_xattr_trusted_get(const struct xattr_handler *handler,
+				   struct dentry *dentry, const char *name,
+				   void *buffer, size_t size)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	return ocfs2_xattr_get(d_inode(dentry), OCFS2_XATTR_INDEX_TRUSTED,
 			       name, buffer, size);
 }
 
-static int ocfs2_xattr_trusted_set(struct dentry *dentry, const char *name,
-		const void *value, size_t size, int flags, int type)
+static int ocfs2_xattr_trusted_set(const struct xattr_handler *handler,
+				   struct dentry *dentry, const char *name,
+				   const void *value, size_t size, int flags)
 {
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
-
 	return ocfs2_xattr_set(d_inode(dentry), OCFS2_XATTR_INDEX_TRUSTED,
 			       name, value, size, flags);
 }
 
 const struct xattr_handler ocfs2_xattr_trusted_handler = {
 	.prefix	= XATTR_TRUSTED_PREFIX,
-	.list	= ocfs2_xattr_trusted_list,
 	.get	= ocfs2_xattr_trusted_get,
 	.set	= ocfs2_xattr_trusted_set,
 };
@@ -7366,45 +7345,24 @@ const struct xattr_handler ocfs2_xattr_trusted_handler = {
 /*
  * 'user' attributes support
  */
-static size_t ocfs2_xattr_user_list(struct dentry *dentry, char *list,
-				    size_t list_size, const char *name,
-				    size_t name_len, int type)
-{
-	const size_t prefix_len = XATTR_USER_PREFIX_LEN;
-	const size_t total_len = prefix_len + name_len + 1;
-	struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb);
-
-	if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR)
-		return 0;
-
-	if (list && total_len <= list_size) {
-		memcpy(list, XATTR_USER_PREFIX, prefix_len);
-		memcpy(list + prefix_len, name, name_len);
-		list[prefix_len + name_len] = '\0';
-	}
-	return total_len;
-}
-
-static int ocfs2_xattr_user_get(struct dentry *dentry, const char *name,
-		void *buffer, size_t size, int type)
+static int ocfs2_xattr_user_get(const struct xattr_handler *handler,
+				struct dentry *dentry, const char *name,
+				void *buffer, size_t size)
 {
 	struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb);
 
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR)
 		return -EOPNOTSUPP;
 	return ocfs2_xattr_get(d_inode(dentry), OCFS2_XATTR_INDEX_USER, name,
 			       buffer, size);
 }
 
-static int ocfs2_xattr_user_set(struct dentry *dentry, const char *name,
-		const void *value, size_t size, int flags, int type)
+static int ocfs2_xattr_user_set(const struct xattr_handler *handler,
+				struct dentry *dentry, const char *name,
+				const void *value, size_t size, int flags)
 {
 	struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb);
 
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
 	if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR)
 		return -EOPNOTSUPP;
 
@@ -7414,7 +7372,6 @@ static int ocfs2_xattr_user_set(struct dentry *dentry, const char *name,
 
 const struct xattr_handler ocfs2_xattr_user_handler = {
 	.prefix	= XATTR_USER_PREFIX,
-	.list	= ocfs2_xattr_user_list,
 	.get	= ocfs2_xattr_user_get,
 	.set	= ocfs2_xattr_user_set,
 };
diff --git a/fs/open.c b/fs/open.c
index b6f1e96a7c0b..17cb6b1dab75 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -58,10 +58,10 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
 	if (ret)
 		newattrs.ia_valid |= ret | ATTR_FORCE;
 
-	mutex_lock(&dentry->d_inode->i_mutex);
+	inode_lock(dentry->d_inode);
 	/* Note any delegations or leases have already been broken: */
 	ret = notify_change(dentry, &newattrs, NULL);
-	mutex_unlock(&dentry->d_inode->i_mutex);
+	inode_unlock(dentry->d_inode);
 	return ret;
 }
 
@@ -510,7 +510,7 @@ static int chmod_common(struct path *path, umode_t mode)
 	if (error)
 		return error;
 retry_deleg:
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	error = security_path_chmod(path, mode);
 	if (error)
 		goto out_unlock;
@@ -518,7 +518,7 @@ retry_deleg:
 	newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
 	error = notify_change(path->dentry, &newattrs, &delegated_inode);
 out_unlock:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	if (delegated_inode) {
 		error = break_deleg_wait(&delegated_inode);
 		if (!error)
@@ -593,11 +593,11 @@ retry_deleg:
 	if (!S_ISDIR(inode->i_mode))
 		newattrs.ia_valid |=
 			ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	error = security_path_chown(path, uid, gid);
 	if (!error)
 		error = notify_change(path->dentry, &newattrs, &delegated_inode);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	if (delegated_inode) {
 		error = break_deleg_wait(&delegated_inode);
 		if (!error)
@@ -887,7 +887,7 @@ EXPORT_SYMBOL(dentry_open);
 static inline int build_open_flags(int flags, umode_t mode, struct open_flags *op)
 {
 	int lookup_flags = 0;
-	int acc_mode;
+	int acc_mode = ACC_MODE(flags);
 
 	if (flags & (O_CREAT | __O_TMPFILE))
 		op->mode = (mode & S_IALLUGO) | S_IFREG;
@@ -909,7 +909,6 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
 	if (flags & __O_TMPFILE) {
 		if ((flags & O_TMPFILE_MASK) != O_TMPFILE)
 			return -EINVAL;
-		acc_mode = MAY_OPEN | ACC_MODE(flags);
 		if (!(acc_mode & MAY_WRITE))
 			return -EINVAL;
 	} else if (flags & O_PATH) {
@@ -919,8 +918,6 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
 		 */
 		flags &= O_DIRECTORY | O_NOFOLLOW | O_PATH;
 		acc_mode = 0;
-	} else {
-		acc_mode = MAY_OPEN | ACC_MODE(flags);
 	}
 
 	op->open_flag = flags;
@@ -995,14 +992,12 @@ struct file *filp_open(const char *filename, int flags, umode_t mode)
 EXPORT_SYMBOL(filp_open);
 
 struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt,
-			    const char *filename, int flags)
+			    const char *filename, int flags, umode_t mode)
 {
 	struct open_flags op;
-	int err = build_open_flags(flags, 0, &op);
+	int err = build_open_flags(flags, mode, &op);
 	if (err)
 		return ERR_PTR(err);
-	if (flags & O_CREAT)
-		return ERR_PTR(-EINVAL);
 	return do_file_open_root(dentry, mnt, filename, &op);
 }
 EXPORT_SYMBOL(file_open_root);
diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c
index 15e4500cda3e..b61b883c8ff8 100644
--- a/fs/openpromfs/inode.c
+++ b/fs/openpromfs/inode.c
@@ -443,7 +443,7 @@ static int __init init_openprom_fs(void)
 					    sizeof(struct op_inode_info),
 					    0,
 					    (SLAB_RECLAIM_ACCOUNT |
-					     SLAB_MEM_SPREAD),
+					     SLAB_MEM_SPREAD | SLAB_ACCOUNT),
 					    op_inode_init_once);
 	if (!op_inode_cachep)
 		return -ENOMEM;
diff --git a/fs/orangefs/Kconfig b/fs/orangefs/Kconfig
new file mode 100644
index 000000000000..1554c02489de
--- /dev/null
+++ b/fs/orangefs/Kconfig
@@ -0,0 +1,6 @@
+config ORANGEFS_FS
+	tristate "ORANGEFS (Powered by PVFS) support"
+	select FS_POSIX_ACL
+	help
+	   Orange is a parallel file system designed for use on high end
+	   computing (HEC) systems.
diff --git a/fs/orangefs/Makefile b/fs/orangefs/Makefile
new file mode 100644
index 000000000000..a9d6a968fe6d
--- /dev/null
+++ b/fs/orangefs/Makefile
@@ -0,0 +1,10 @@
+#
+# Makefile for the ORANGEFS filesystem.
+#
+
+obj-$(CONFIG_ORANGEFS_FS) += orangefs.o
+
+orangefs-objs := acl.o file.o orangefs-cache.o orangefs-utils.o xattr.o \
+		 dcache.o inode.o orangefs-sysfs.o orangefs-mod.o super.o \
+		 devorangefs-req.o namei.o symlink.o dir.o orangefs-bufmap.o \
+		 orangefs-debugfs.o waitqueue.o
diff --git a/fs/orangefs/acl.c b/fs/orangefs/acl.c
new file mode 100644
index 000000000000..03f89dbb2512
--- /dev/null
+++ b/fs/orangefs/acl.c
@@ -0,0 +1,175 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-bufmap.h"
+#include <linux/posix_acl_xattr.h>
+#include <linux/fs_struct.h>
+
+struct posix_acl *orangefs_get_acl(struct inode *inode, int type)
+{
+	struct posix_acl *acl;
+	int ret;
+	char *key = NULL, *value = NULL;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		key = ORANGEFS_XATTR_NAME_ACL_ACCESS;
+		break;
+	case ACL_TYPE_DEFAULT:
+		key = ORANGEFS_XATTR_NAME_ACL_DEFAULT;
+		break;
+	default:
+		gossip_err("orangefs_get_acl: bogus value of type %d\n", type);
+		return ERR_PTR(-EINVAL);
+	}
+	/*
+	 * Rather than incurring a network call just to determine the exact
+	 * length of the attribute, I just allocate a max length to save on
+	 * the network call. Conceivably, we could pass NULL to
+	 * orangefs_inode_getxattr() to probe the length of the value, but
+	 * I don't do that for now.
+	 */
+	value = kmalloc(ORANGEFS_MAX_XATTR_VALUELEN, GFP_KERNEL);
+	if (value == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	gossip_debug(GOSSIP_ACL_DEBUG,
+		     "inode %pU, key %s, type %d\n",
+		     get_khandle_from_ino(inode),
+		     key,
+		     type);
+	ret = orangefs_inode_getxattr(inode,
+				   "",
+				   key,
+				   value,
+				   ORANGEFS_MAX_XATTR_VALUELEN);
+	/* if the key exists, convert it to an in-memory rep */
+	if (ret > 0) {
+		acl = posix_acl_from_xattr(&init_user_ns, value, ret);
+	} else if (ret == -ENODATA || ret == -ENOSYS) {
+		acl = NULL;
+	} else {
+		gossip_err("inode %pU retrieving acl's failed with error %d\n",
+			   get_khandle_from_ino(inode),
+			   ret);
+		acl = ERR_PTR(ret);
+	}
+	/* kfree(NULL) is safe, so don't worry if value ever got used */
+	kfree(value);
+	return acl;
+}
+
+int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	int error = 0;
+	void *value = NULL;
+	size_t size = 0;
+	const char *name = NULL;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name = ORANGEFS_XATTR_NAME_ACL_ACCESS;
+		if (acl) {
+			umode_t mode = inode->i_mode;
+			/*
+			 * can we represent this with the traditional file
+			 * mode permission bits?
+			 */
+			error = posix_acl_equiv_mode(acl, &mode);
+			if (error < 0) {
+				gossip_err("%s: posix_acl_equiv_mode err: %d\n",
+					   __func__,
+					   error);
+				return error;
+			}
+
+			if (inode->i_mode != mode)
+				SetModeFlag(orangefs_inode);
+			inode->i_mode = mode;
+			mark_inode_dirty_sync(inode);
+			if (error == 0)
+				acl = NULL;
+		}
+		break;
+	case ACL_TYPE_DEFAULT:
+		name = ORANGEFS_XATTR_NAME_ACL_DEFAULT;
+		break;
+	default:
+		gossip_err("%s: invalid type %d!\n", __func__, type);
+		return -EINVAL;
+	}
+
+	gossip_debug(GOSSIP_ACL_DEBUG,
+		     "%s: inode %pU, key %s type %d\n",
+		     __func__, get_khandle_from_ino(inode),
+		     name,
+		     type);
+
+	if (acl) {
+		size = posix_acl_xattr_size(acl->a_count);
+		value = kmalloc(size, GFP_KERNEL);
+		if (!value)
+			return -ENOMEM;
+
+		error = posix_acl_to_xattr(&init_user_ns, acl, value, size);
+		if (error < 0)
+			goto out;
+	}
+
+	gossip_debug(GOSSIP_ACL_DEBUG,
+		     "%s: name %s, value %p, size %zd, acl %p\n",
+		     __func__, name, value, size, acl);
+	/*
+	 * Go ahead and set the extended attribute now. NOTE: Suppose acl
+	 * was NULL, then value will be NULL and size will be 0 and that
+	 * will xlate to a removexattr. However, we don't want removexattr
+	 * complain if attributes does not exist.
+	 */
+	error = orangefs_inode_setxattr(inode, "", name, value, size, 0);
+
+out:
+	kfree(value);
+	if (!error)
+		set_cached_acl(inode, type, acl);
+	return error;
+}
+
+int orangefs_init_acl(struct inode *inode, struct inode *dir)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	struct posix_acl *default_acl, *acl;
+	umode_t mode = inode->i_mode;
+	int error = 0;
+
+	ClearModeFlag(orangefs_inode);
+
+	error = posix_acl_create(dir, &mode, &default_acl, &acl);
+	if (error)
+		return error;
+
+	if (default_acl) {
+		error = orangefs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
+		posix_acl_release(default_acl);
+	}
+
+	if (acl) {
+		if (!error)
+			error = orangefs_set_acl(inode, acl, ACL_TYPE_ACCESS);
+		posix_acl_release(acl);
+	}
+
+	/* If mode of the inode was changed, then do a forcible ->setattr */
+	if (mode != inode->i_mode) {
+		SetModeFlag(orangefs_inode);
+		inode->i_mode = mode;
+		orangefs_flush_inode(inode);
+	}
+
+	return error;
+}
diff --git a/fs/orangefs/dcache.c b/fs/orangefs/dcache.c
new file mode 100644
index 000000000000..5dfc4f3cfe68
--- /dev/null
+++ b/fs/orangefs/dcache.c
@@ -0,0 +1,138 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+/*
+ *  Implementation of dentry (directory cache) functions.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+
+/* Returns 1 if dentry can still be trusted, else 0. */
+static int orangefs_revalidate_lookup(struct dentry *dentry)
+{
+	struct dentry *parent_dentry = dget_parent(dentry);
+	struct inode *parent_inode = parent_dentry->d_inode;
+	struct orangefs_inode_s *parent = ORANGEFS_I(parent_inode);
+	struct inode *inode = dentry->d_inode;
+	struct orangefs_kernel_op_s *new_op;
+	int ret = 0;
+	int err = 0;
+
+	gossip_debug(GOSSIP_DCACHE_DEBUG, "%s: attempting lookup.\n", __func__);
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_LOOKUP);
+	if (!new_op)
+		goto out_put_parent;
+
+	new_op->upcall.req.lookup.sym_follow = ORANGEFS_LOOKUP_LINK_NO_FOLLOW;
+	new_op->upcall.req.lookup.parent_refn = parent->refn;
+	strncpy(new_op->upcall.req.lookup.d_name,
+		dentry->d_name.name,
+		ORANGEFS_NAME_MAX);
+
+	gossip_debug(GOSSIP_DCACHE_DEBUG,
+		     "%s:%s:%d interrupt flag [%d]\n",
+		     __FILE__,
+		     __func__,
+		     __LINE__,
+		     get_interruptible_flag(parent_inode));
+
+	err = service_operation(new_op, "orangefs_lookup",
+			get_interruptible_flag(parent_inode));
+
+	/* Positive dentry: reject if error or not the same inode. */
+	if (inode) {
+		if (err) {
+			gossip_debug(GOSSIP_DCACHE_DEBUG,
+			    "%s:%s:%d lookup failure.\n",
+			    __FILE__, __func__, __LINE__);
+			goto out_drop;
+		}
+		if (!match_handle(new_op->downcall.resp.lookup.refn.khandle,
+		    inode)) {
+			gossip_debug(GOSSIP_DCACHE_DEBUG,
+			    "%s:%s:%d no match.\n",
+			    __FILE__, __func__, __LINE__);
+			goto out_drop;
+		}
+
+	/* Negative dentry: reject if success or error other than ENOENT. */
+	} else {
+		gossip_debug(GOSSIP_DCACHE_DEBUG, "%s: negative dentry.\n",
+		    __func__);
+		if (!err || err != -ENOENT) {
+			if (new_op->downcall.status != 0)
+				gossip_debug(GOSSIP_DCACHE_DEBUG,
+				    "%s:%s:%d lookup failure.\n",
+				    __FILE__, __func__, __LINE__);
+			goto out_drop;
+		}
+	}
+
+	ret = 1;
+out_release_op:
+	op_release(new_op);
+out_put_parent:
+	dput(parent_dentry);
+	return ret;
+out_drop:
+	gossip_debug(GOSSIP_DCACHE_DEBUG, "%s:%s:%d revalidate failed\n",
+	    __FILE__, __func__, __LINE__);
+	goto out_release_op;
+}
+
+/*
+ * Verify that dentry is valid.
+ *
+ * Should return 1 if dentry can still be trusted, else 0.
+ */
+static int orangefs_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	int ret;
+
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	gossip_debug(GOSSIP_DCACHE_DEBUG, "%s: called on dentry %p.\n",
+		     __func__, dentry);
+
+	/* skip root handle lookups. */
+	if (dentry->d_inode && is_root_handle(dentry->d_inode))
+		return 1;
+
+	/*
+	 * If this passes, the positive dentry still exists or the negative
+	 * dentry still does not exist.
+	 */
+	if (!orangefs_revalidate_lookup(dentry))
+		return 0;
+
+	/* We do not need to continue with negative dentries. */
+	if (!dentry->d_inode)
+		goto out;
+
+	/* Now we must perform a getattr to validate the inode contents. */
+
+	ret = orangefs_inode_check_changed(dentry->d_inode);
+	if (ret < 0) {
+		gossip_debug(GOSSIP_DCACHE_DEBUG, "%s:%s:%d getattr failure.\n",
+		    __FILE__, __func__, __LINE__);
+		return 0;
+	}
+	if (ret == 0)
+		return 0;
+
+out:
+	gossip_debug(GOSSIP_DCACHE_DEBUG,
+	    "%s: negative dentry or positive dentry and inode valid.\n",
+	    __func__);
+	return 1;
+}
+
+const struct dentry_operations orangefs_dentry_operations = {
+	.d_revalidate = orangefs_d_revalidate,
+};
diff --git a/fs/orangefs/devorangefs-req.c b/fs/orangefs/devorangefs-req.c
new file mode 100644
index 000000000000..db170beba797
--- /dev/null
+++ b/fs/orangefs/devorangefs-req.c
@@ -0,0 +1,943 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * Changes by Acxiom Corporation to add protocol version to kernel
+ * communication, Copyright Acxiom Corporation, 2005.
+ *
+ * See COPYING in top-level directory.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-dev-proto.h"
+#include "orangefs-bufmap.h"
+
+#include <linux/debugfs.h>
+#include <linux/slab.h>
+
+/* this file implements the /dev/pvfs2-req device node */
+
+static int open_access_count;
+
+#define DUMP_DEVICE_ERROR()                                                   \
+do {                                                                          \
+	gossip_err("*****************************************************\n");\
+	gossip_err("ORANGEFS Device Error:  You cannot open the device file ");  \
+	gossip_err("\n/dev/%s more than once.  Please make sure that\nthere " \
+		   "are no ", ORANGEFS_REQDEVICE_NAME);                          \
+	gossip_err("instances of a program using this device\ncurrently "     \
+		   "running. (You must verify this!)\n");                     \
+	gossip_err("For example, you can use the lsof program as follows:\n");\
+	gossip_err("'lsof | grep %s' (run this as root)\n",                   \
+		   ORANGEFS_REQDEVICE_NAME);                                     \
+	gossip_err("  open_access_count = %d\n", open_access_count);          \
+	gossip_err("*****************************************************\n");\
+} while (0)
+
+static int hash_func(__u64 tag, int table_size)
+{
+	return do_div(tag, (unsigned int)table_size);
+}
+
+static void orangefs_devreq_add_op(struct orangefs_kernel_op_s *op)
+{
+	int index = hash_func(op->tag, hash_table_size);
+
+	list_add_tail(&op->list, &htable_ops_in_progress[index]);
+}
+
+/*
+ * find the op with this tag and remove it from the in progress
+ * hash table.
+ */
+static struct orangefs_kernel_op_s *orangefs_devreq_remove_op(__u64 tag)
+{
+	struct orangefs_kernel_op_s *op, *next;
+	int index;
+
+	index = hash_func(tag, hash_table_size);
+
+	spin_lock(&htable_ops_in_progress_lock);
+	list_for_each_entry_safe(op,
+				 next,
+				 &htable_ops_in_progress[index],
+				 list) {
+		if (op->tag == tag && !op_state_purged(op) &&
+		    !op_state_given_up(op)) {
+			list_del_init(&op->list);
+			spin_unlock(&htable_ops_in_progress_lock);
+			return op;
+		}
+	}
+
+	spin_unlock(&htable_ops_in_progress_lock);
+	return NULL;
+}
+
+/* Returns whether any FS are still pending remounted */
+static int mark_all_pending_mounts(void)
+{
+	int unmounted = 1;
+	struct orangefs_sb_info_s *orangefs_sb = NULL;
+
+	spin_lock(&orangefs_superblocks_lock);
+	list_for_each_entry(orangefs_sb, &orangefs_superblocks, list) {
+		/* All of these file system require a remount */
+		orangefs_sb->mount_pending = 1;
+		unmounted = 0;
+	}
+	spin_unlock(&orangefs_superblocks_lock);
+	return unmounted;
+}
+
+/*
+ * Determine if a given file system needs to be remounted or not
+ *  Returns -1 on error
+ *           0 if already mounted
+ *           1 if needs remount
+ */
+static int fs_mount_pending(__s32 fsid)
+{
+	int mount_pending = -1;
+	struct orangefs_sb_info_s *orangefs_sb = NULL;
+
+	spin_lock(&orangefs_superblocks_lock);
+	list_for_each_entry(orangefs_sb, &orangefs_superblocks, list) {
+		if (orangefs_sb->fs_id == fsid) {
+			mount_pending = orangefs_sb->mount_pending;
+			break;
+		}
+	}
+	spin_unlock(&orangefs_superblocks_lock);
+	return mount_pending;
+}
+
+static int orangefs_devreq_open(struct inode *inode, struct file *file)
+{
+	int ret = -EINVAL;
+
+	if (!(file->f_flags & O_NONBLOCK)) {
+		gossip_err("%s: device cannot be opened in blocking mode\n",
+			   __func__);
+		goto out;
+	}
+	ret = -EACCES;
+	gossip_debug(GOSSIP_DEV_DEBUG, "client-core: opening device\n");
+	mutex_lock(&devreq_mutex);
+
+	if (open_access_count == 0) {
+		open_access_count = 1;
+		ret = 0;
+	} else {
+		DUMP_DEVICE_ERROR();
+	}
+	mutex_unlock(&devreq_mutex);
+
+out:
+
+	gossip_debug(GOSSIP_DEV_DEBUG,
+		     "pvfs2-client-core: open device complete (ret = %d)\n",
+		     ret);
+	return ret;
+}
+
+/* Function for read() callers into the device */
+static ssize_t orangefs_devreq_read(struct file *file,
+				 char __user *buf,
+				 size_t count, loff_t *offset)
+{
+	struct orangefs_kernel_op_s *op, *temp;
+	__s32 proto_ver = ORANGEFS_KERNEL_PROTO_VERSION;
+	static __s32 magic = ORANGEFS_DEVREQ_MAGIC;
+	struct orangefs_kernel_op_s *cur_op = NULL;
+	unsigned long ret;
+
+	/* We do not support blocking IO. */
+	if (!(file->f_flags & O_NONBLOCK)) {
+		gossip_err("%s: blocking read from client-core.\n",
+			   __func__);
+		return -EINVAL;
+	}
+
+	/*
+	 * The client will do an ioctl to find MAX_DEV_REQ_UPSIZE, then
+	 * always read with that size buffer.
+	 */
+	if (count != MAX_DEV_REQ_UPSIZE) {
+		gossip_err("orangefs: client-core tried to read wrong size\n");
+		return -EINVAL;
+	}
+
+restart:
+	/* Get next op (if any) from top of list. */
+	spin_lock(&orangefs_request_list_lock);
+	list_for_each_entry_safe(op, temp, &orangefs_request_list, list) {
+		__s32 fsid;
+		/* This lock is held past the end of the loop when we break. */
+		spin_lock(&op->lock);
+		if (unlikely(op_state_purged(op) || op_state_given_up(op))) {
+			spin_unlock(&op->lock);
+			continue;
+		}
+
+		fsid = fsid_of_op(op);
+		if (fsid != ORANGEFS_FS_ID_NULL) {
+			int ret;
+			/* Skip ops whose filesystem needs to be mounted. */
+			ret = fs_mount_pending(fsid);
+			if (ret == 1) {
+				gossip_debug(GOSSIP_DEV_DEBUG,
+				    "%s: mount pending, skipping op tag "
+				    "%llu %s\n",
+				    __func__,
+				    llu(op->tag),
+				    get_opname_string(op));
+				spin_unlock(&op->lock);
+				continue;
+			/*
+			 * Skip ops whose filesystem we don't know about unless
+			 * it is being mounted.
+			 */
+			/* XXX: is there a better way to detect this? */
+			} else if (ret == -1 &&
+				   !(op->upcall.type ==
+					ORANGEFS_VFS_OP_FS_MOUNT ||
+				     op->upcall.type ==
+					ORANGEFS_VFS_OP_GETATTR)) {
+				gossip_debug(GOSSIP_DEV_DEBUG,
+				    "orangefs: skipping op tag %llu %s\n",
+				    llu(op->tag), get_opname_string(op));
+				gossip_err(
+				    "orangefs: ERROR: fs_mount_pending %d\n",
+				    fsid);
+				spin_unlock(&op->lock);
+				continue;
+			}
+		}
+		/*
+		 * Either this op does not pertain to a filesystem, is mounting
+		 * a filesystem, or pertains to a mounted filesystem. Let it
+		 * through.
+		 */
+		cur_op = op;
+		break;
+	}
+
+	/*
+	 * At this point we either have a valid op and can continue or have not
+	 * found an op and must ask the client to try again later.
+	 */
+	if (!cur_op) {
+		spin_unlock(&orangefs_request_list_lock);
+		return -EAGAIN;
+	}
+
+	gossip_debug(GOSSIP_DEV_DEBUG, "%s: reading op tag %llu %s\n",
+		     __func__,
+		     llu(cur_op->tag),
+		     get_opname_string(cur_op));
+
+	/*
+	 * Such an op should never be on the list in the first place. If so, we
+	 * will abort.
+	 */
+	if (op_state_in_progress(cur_op) || op_state_serviced(cur_op)) {
+		gossip_err("orangefs: ERROR: Current op already queued.\n");
+		list_del_init(&cur_op->list);
+		spin_unlock(&cur_op->lock);
+		spin_unlock(&orangefs_request_list_lock);
+		return -EAGAIN;
+	}
+
+	list_del_init(&cur_op->list);
+	spin_unlock(&orangefs_request_list_lock);
+
+	spin_unlock(&cur_op->lock);
+
+	/* Push the upcall out. */
+	ret = copy_to_user(buf, &proto_ver, sizeof(__s32));
+	if (ret != 0)
+		goto error;
+	ret = copy_to_user(buf+sizeof(__s32), &magic, sizeof(__s32));
+	if (ret != 0)
+		goto error;
+	ret = copy_to_user(buf+2 * sizeof(__s32), &cur_op->tag, sizeof(__u64));
+	if (ret != 0)
+		goto error;
+	ret = copy_to_user(buf+2*sizeof(__s32)+sizeof(__u64), &cur_op->upcall,
+			   sizeof(struct orangefs_upcall_s));
+	if (ret != 0)
+		goto error;
+
+	spin_lock(&htable_ops_in_progress_lock);
+	spin_lock(&cur_op->lock);
+	if (unlikely(op_state_given_up(cur_op))) {
+		spin_unlock(&cur_op->lock);
+		spin_unlock(&htable_ops_in_progress_lock);
+		complete(&cur_op->waitq);
+		goto restart;
+	}
+
+	/*
+	 * Set the operation to be in progress and move it between lists since
+	 * it has been sent to the client.
+	 */
+	set_op_state_inprogress(cur_op);
+	gossip_debug(GOSSIP_DEV_DEBUG,
+		     "%s: 1 op:%s: op_state:%d: process:%s:\n",
+		     __func__,
+		     get_opname_string(cur_op),
+		     cur_op->op_state,
+		     current->comm);
+	orangefs_devreq_add_op(cur_op);
+	spin_unlock(&cur_op->lock);
+	spin_unlock(&htable_ops_in_progress_lock);
+
+	/* The client only asks to read one size buffer. */
+	return MAX_DEV_REQ_UPSIZE;
+error:
+	/*
+	 * We were unable to copy the op data to the client. Put the op back in
+	 * list. If client has crashed, the op will be purged later when the
+	 * device is released.
+	 */
+	gossip_err("orangefs: Failed to copy data to user space\n");
+	spin_lock(&orangefs_request_list_lock);
+	spin_lock(&cur_op->lock);
+	if (likely(!op_state_given_up(cur_op))) {
+		set_op_state_waiting(cur_op);
+		gossip_debug(GOSSIP_DEV_DEBUG,
+			     "%s: 2 op:%s: op_state:%d: process:%s:\n",
+			     __func__,
+			     get_opname_string(cur_op),
+			     cur_op->op_state,
+			     current->comm);
+		list_add(&cur_op->list, &orangefs_request_list);
+		spin_unlock(&cur_op->lock);
+	} else {
+		spin_unlock(&cur_op->lock);
+		complete(&cur_op->waitq);
+	}
+	spin_unlock(&orangefs_request_list_lock);
+	return -EFAULT;
+}
+
+/*
+ * Function for writev() callers into the device.
+ *
+ * Userspace should have written:
+ *  - __u32 version
+ *  - __u32 magic
+ *  - __u64 tag
+ *  - struct orangefs_downcall_s
+ *  - trailer buffer (in the case of READDIR operations)
+ */
+static ssize_t orangefs_devreq_write_iter(struct kiocb *iocb,
+				      struct iov_iter *iter)
+{
+	ssize_t ret;
+	struct orangefs_kernel_op_s *op = NULL;
+	struct {
+		__u32 version;
+		__u32 magic;
+		__u64 tag;
+	} head;
+	int total = ret = iov_iter_count(iter);
+	int n;
+	int downcall_size = sizeof(struct orangefs_downcall_s);
+	int head_size = sizeof(head);
+
+	gossip_debug(GOSSIP_DEV_DEBUG, "%s: total:%d: ret:%zd:\n",
+		     __func__,
+		     total,
+		     ret);
+
+        if (total < MAX_DEV_REQ_DOWNSIZE) {
+		gossip_err("%s: total:%d: must be at least:%u:\n",
+			   __func__,
+			   total,
+			   (unsigned int) MAX_DEV_REQ_DOWNSIZE);
+		return -EFAULT;
+	}
+     
+	n = copy_from_iter(&head, head_size, iter);
+	if (n < head_size) {
+		gossip_err("%s: failed to copy head.\n", __func__);
+		return -EFAULT;
+	}
+
+	if (head.version < ORANGEFS_MINIMUM_USERSPACE_VERSION) {
+		gossip_err("%s: userspace claims version"
+			   "%d, minimum version required: %d.\n",
+			   __func__,
+			   head.version,
+			   ORANGEFS_MINIMUM_USERSPACE_VERSION);
+		return -EPROTO;
+	}
+
+	if (head.magic != ORANGEFS_DEVREQ_MAGIC) {
+		gossip_err("Error: Device magic number does not match.\n");
+		return -EPROTO;
+	}
+
+	/* remove the op from the in progress hash table */
+	op = orangefs_devreq_remove_op(head.tag);
+	if (!op) {
+		gossip_err("WARNING: No one's waiting for tag %llu\n",
+			   llu(head.tag));
+		return ret;
+	}
+
+	n = copy_from_iter(&op->downcall, downcall_size, iter);
+	if (n != downcall_size) {
+		gossip_err("%s: failed to copy downcall.\n", __func__);
+		goto Efault;
+	}
+
+	if (op->downcall.status)
+		goto wakeup;
+
+	/*
+	 * We've successfully peeled off the head and the downcall. 
+	 * Something has gone awry if total doesn't equal the
+	 * sum of head_size, downcall_size and trailer_size.
+	 */
+	if ((head_size + downcall_size + op->downcall.trailer_size) != total) {
+		gossip_err("%s: funky write, head_size:%d"
+			   ": downcall_size:%d: trailer_size:%lld"
+			   ": total size:%d:\n",
+			   __func__,
+			   head_size,
+			   downcall_size,
+			   op->downcall.trailer_size,
+			   total);
+		goto Efault;
+	}
+
+	/* Only READDIR operations should have trailers. */
+	if ((op->downcall.type != ORANGEFS_VFS_OP_READDIR) &&
+	    (op->downcall.trailer_size != 0)) {
+		gossip_err("%s: %x operation with trailer.",
+			   __func__,
+			   op->downcall.type);
+		goto Efault;
+	}
+
+	/* READDIR operations should always have trailers. */
+	if ((op->downcall.type == ORANGEFS_VFS_OP_READDIR) &&
+	    (op->downcall.trailer_size == 0)) {
+		gossip_err("%s: %x operation with no trailer.",
+			   __func__,
+			   op->downcall.type);
+		goto Efault;
+	}
+
+	if (op->downcall.type != ORANGEFS_VFS_OP_READDIR)
+		goto wakeup;
+
+	op->downcall.trailer_buf =
+		vmalloc(op->downcall.trailer_size);
+	if (op->downcall.trailer_buf == NULL) {
+		gossip_err("%s: failed trailer vmalloc.\n",
+			   __func__);
+		goto Enomem;
+	}
+	memset(op->downcall.trailer_buf, 0, op->downcall.trailer_size);
+	n = copy_from_iter(op->downcall.trailer_buf,
+			   op->downcall.trailer_size,
+			   iter);
+	if (n != op->downcall.trailer_size) {
+		gossip_err("%s: failed to copy trailer.\n", __func__);
+		vfree(op->downcall.trailer_buf);
+		goto Efault;
+	}
+
+wakeup:
+	/*
+	 * Return to vfs waitqueue, and back to service_operation
+	 * through wait_for_matching_downcall. 
+	 */
+	spin_lock(&op->lock);
+	if (unlikely(op_is_cancel(op))) {
+		spin_unlock(&op->lock);
+		put_cancel(op);
+	} else if (unlikely(op_state_given_up(op))) {
+		spin_unlock(&op->lock);
+		complete(&op->waitq);
+	} else {
+		set_op_state_serviced(op);
+		gossip_debug(GOSSIP_DEV_DEBUG,
+			     "%s: op:%s: op_state:%d: process:%s:\n",
+			     __func__,
+			     get_opname_string(op),
+			     op->op_state,
+			     current->comm);
+		spin_unlock(&op->lock);
+	}
+	return ret;
+
+Efault:
+	op->downcall.status = -(ORANGEFS_ERROR_BIT | 9);
+	ret = -EFAULT;
+	goto wakeup;
+
+Enomem:
+	op->downcall.status = -(ORANGEFS_ERROR_BIT | 8);
+	ret = -ENOMEM;
+	goto wakeup;
+}
+
+/*
+ * NOTE: gets called when the last reference to this device is dropped.
+ * Using the open_access_count variable, we enforce a reference count
+ * on this file so that it can be opened by only one process at a time.
+ * the devreq_mutex is used to make sure all i/o has completed
+ * before we call orangefs_bufmap_finalize, and similar such tricky
+ * situations
+ */
+static int orangefs_devreq_release(struct inode *inode, struct file *file)
+{
+	int unmounted = 0;
+
+	gossip_debug(GOSSIP_DEV_DEBUG,
+		     "%s:pvfs2-client-core: exiting, closing device\n",
+		     __func__);
+
+	mutex_lock(&devreq_mutex);
+	orangefs_bufmap_finalize();
+
+	open_access_count = -1;
+
+	unmounted = mark_all_pending_mounts();
+	gossip_debug(GOSSIP_DEV_DEBUG, "ORANGEFS Device Close: Filesystem(s) %s\n",
+		     (unmounted ? "UNMOUNTED" : "MOUNTED"));
+
+	purge_waiting_ops();
+	purge_inprogress_ops();
+
+	orangefs_bufmap_run_down();
+
+	gossip_debug(GOSSIP_DEV_DEBUG,
+		     "pvfs2-client-core: device close complete\n");
+	open_access_count = 0;
+	mutex_unlock(&devreq_mutex);
+	return 0;
+}
+
+int is_daemon_in_service(void)
+{
+	int in_service;
+
+	/*
+	 * What this function does is checks if client-core is alive
+	 * based on the access count we maintain on the device.
+	 */
+	mutex_lock(&devreq_mutex);
+	in_service = open_access_count == 1 ? 0 : -EIO;
+	mutex_unlock(&devreq_mutex);
+	return in_service;
+}
+
+bool __is_daemon_in_service(void)
+{
+	return open_access_count == 1;
+}
+
+static inline long check_ioctl_command(unsigned int command)
+{
+	/* Check for valid ioctl codes */
+	if (_IOC_TYPE(command) != ORANGEFS_DEV_MAGIC) {
+		gossip_err("device ioctl magic numbers don't match! Did you rebuild pvfs2-client-core/libpvfs2? [cmd %x, magic %x != %x]\n",
+			command,
+			_IOC_TYPE(command),
+			ORANGEFS_DEV_MAGIC);
+		return -EINVAL;
+	}
+	/* and valid ioctl commands */
+	if (_IOC_NR(command) >= ORANGEFS_DEV_MAXNR || _IOC_NR(command) <= 0) {
+		gossip_err("Invalid ioctl command number [%d >= %d]\n",
+			   _IOC_NR(command), ORANGEFS_DEV_MAXNR);
+		return -ENOIOCTLCMD;
+	}
+	return 0;
+}
+
+static long dispatch_ioctl_command(unsigned int command, unsigned long arg)
+{
+	static __s32 magic = ORANGEFS_DEVREQ_MAGIC;
+	static __s32 max_up_size = MAX_DEV_REQ_UPSIZE;
+	static __s32 max_down_size = MAX_DEV_REQ_DOWNSIZE;
+	struct ORANGEFS_dev_map_desc user_desc;
+	int ret = 0;
+	struct dev_mask_info_s mask_info = { 0 };
+	struct dev_mask2_info_s mask2_info = { 0, 0 };
+	int upstream_kmod = 1;
+	struct orangefs_sb_info_s *orangefs_sb;
+
+	/* mtmoore: add locking here */
+
+	switch (command) {
+	case ORANGEFS_DEV_GET_MAGIC:
+		return ((put_user(magic, (__s32 __user *) arg) == -EFAULT) ?
+			-EIO :
+			0);
+	case ORANGEFS_DEV_GET_MAX_UPSIZE:
+		return ((put_user(max_up_size,
+				  (__s32 __user *) arg) == -EFAULT) ?
+					-EIO :
+					0);
+	case ORANGEFS_DEV_GET_MAX_DOWNSIZE:
+		return ((put_user(max_down_size,
+				  (__s32 __user *) arg) == -EFAULT) ?
+					-EIO :
+					0);
+	case ORANGEFS_DEV_MAP:
+		ret = copy_from_user(&user_desc,
+				     (struct ORANGEFS_dev_map_desc __user *)
+				     arg,
+				     sizeof(struct ORANGEFS_dev_map_desc));
+		/* WTF -EIO and not -EFAULT? */
+		return ret ? -EIO : orangefs_bufmap_initialize(&user_desc);
+	case ORANGEFS_DEV_REMOUNT_ALL:
+		gossip_debug(GOSSIP_DEV_DEBUG,
+			     "%s: got ORANGEFS_DEV_REMOUNT_ALL\n",
+			     __func__);
+
+		/*
+		 * remount all mounted orangefs volumes to regain the lost
+		 * dynamic mount tables (if any) -- NOTE: this is done
+		 * without keeping the superblock list locked due to the
+		 * upcall/downcall waiting.  also, the request mutex is
+		 * used to ensure that no operations will be serviced until
+		 * all of the remounts are serviced (to avoid ops between
+		 * mounts to fail)
+		 */
+		ret = mutex_lock_interruptible(&request_mutex);
+		if (ret < 0)
+			return ret;
+		gossip_debug(GOSSIP_DEV_DEBUG,
+			     "%s: priority remount in progress\n",
+			     __func__);
+		spin_lock(&orangefs_superblocks_lock);
+		list_for_each_entry(orangefs_sb, &orangefs_superblocks, list) {
+			/*
+			 * We have to drop the spinlock, so entries can be
+			 * removed.  They can't be freed, though, so we just
+			 * keep the forward pointers and zero the back ones -
+			 * that way we can get to the rest of the list.
+			 */
+			if (!orangefs_sb->list.prev)
+				continue;
+			gossip_debug(GOSSIP_DEV_DEBUG,
+				     "%s: Remounting SB %p\n",
+				     __func__,
+				     orangefs_sb);
+
+			spin_unlock(&orangefs_superblocks_lock);
+			ret = orangefs_remount(orangefs_sb);
+			spin_lock(&orangefs_superblocks_lock);
+			if (ret) {
+				gossip_debug(GOSSIP_DEV_DEBUG,
+					     "SB %p remount failed\n",
+					     orangefs_sb);
+				break;
+			}
+		}
+		spin_unlock(&orangefs_superblocks_lock);
+		gossip_debug(GOSSIP_DEV_DEBUG,
+			     "%s: priority remount complete\n",
+			     __func__);
+		mutex_unlock(&request_mutex);
+		return ret;
+
+	case ORANGEFS_DEV_UPSTREAM:
+		ret = copy_to_user((void __user *)arg,
+				    &upstream_kmod,
+				    sizeof(upstream_kmod));
+
+		if (ret != 0)
+			return -EIO;
+		else
+			return ret;
+
+	case ORANGEFS_DEV_CLIENT_MASK:
+		ret = copy_from_user(&mask2_info,
+				     (void __user *)arg,
+				     sizeof(struct dev_mask2_info_s));
+
+		if (ret != 0)
+			return -EIO;
+
+		client_debug_mask.mask1 = mask2_info.mask1_value;
+		client_debug_mask.mask2 = mask2_info.mask2_value;
+
+		pr_info("%s: client debug mask has been been received "
+			":%llx: :%llx:\n",
+			__func__,
+			(unsigned long long)client_debug_mask.mask1,
+			(unsigned long long)client_debug_mask.mask2);
+
+		return ret;
+
+	case ORANGEFS_DEV_CLIENT_STRING:
+		ret = copy_from_user(&client_debug_array_string,
+				     (void __user *)arg,
+				     ORANGEFS_MAX_DEBUG_STRING_LEN);
+		/*
+		 * The real client-core makes an effort to ensure
+		 * that actual strings that aren't too long to fit in
+		 * this buffer is what we get here. We're going to use
+		 * string functions on the stuff we got, so we'll make
+		 * this extra effort to try and keep from
+		 * flowing out of this buffer when we use the string
+		 * functions, even if somehow the stuff we end up
+		 * with here is garbage.
+		 */
+		client_debug_array_string[ORANGEFS_MAX_DEBUG_STRING_LEN - 1] =
+			'\0';
+		
+		if (ret != 0) {
+			pr_info("%s: CLIENT_STRING: copy_from_user failed\n",
+				__func__);
+			return -EIO;
+		}
+
+		pr_info("%s: client debug array string has been received.\n",
+			__func__);
+
+		if (!help_string_initialized) {
+
+			/* Free the "we don't know yet" default string... */
+			kfree(debug_help_string);
+
+			/* build a proper debug help string */
+			if (orangefs_prepare_debugfs_help_string(0)) {
+				gossip_err("%s: no debug help string \n",
+					   __func__);
+				return -EIO;
+			}
+
+			/* Replace the boilerplate boot-time debug-help file. */
+			debugfs_remove(help_file_dentry);
+
+			help_file_dentry =
+				debugfs_create_file(
+					ORANGEFS_KMOD_DEBUG_HELP_FILE,
+					0444,
+					debug_dir,
+					debug_help_string,
+					&debug_help_fops);
+
+			if (!help_file_dentry) {
+				gossip_err("%s: debugfs_create_file failed for"
+					   " :%s:!\n",
+					   __func__,
+					   ORANGEFS_KMOD_DEBUG_HELP_FILE);
+				return -EIO;
+			}
+		}
+
+		debug_mask_to_string(&client_debug_mask, 1);
+
+		debugfs_remove(client_debug_dentry);
+
+		orangefs_client_debug_init();
+
+		help_string_initialized++;
+
+		return ret;
+
+	case ORANGEFS_DEV_DEBUG:
+		ret = copy_from_user(&mask_info,
+				     (void __user *)arg,
+				     sizeof(mask_info));
+
+		if (ret != 0)
+			return -EIO;
+
+		if (mask_info.mask_type == KERNEL_MASK) {
+			if ((mask_info.mask_value == 0)
+			    && (kernel_mask_set_mod_init)) {
+				/*
+				 * the kernel debug mask was set when the
+				 * kernel module was loaded; don't override
+				 * it if the client-core was started without
+				 * a value for ORANGEFS_KMODMASK.
+				 */
+				return 0;
+			}
+			debug_mask_to_string(&mask_info.mask_value,
+					     mask_info.mask_type);
+			gossip_debug_mask = mask_info.mask_value;
+			pr_info("%s: kernel debug mask has been modified to "
+				":%s: :%llx:\n",
+				__func__,
+				kernel_debug_string,
+				(unsigned long long)gossip_debug_mask);
+		} else if (mask_info.mask_type == CLIENT_MASK) {
+			debug_mask_to_string(&mask_info.mask_value,
+					     mask_info.mask_type);
+			pr_info("%s: client debug mask has been modified to"
+				":%s: :%llx:\n",
+				__func__,
+				client_debug_string,
+				llu(mask_info.mask_value));
+		} else {
+			gossip_lerr("Invalid mask type....\n");
+			return -EINVAL;
+		}
+
+		return ret;
+
+	default:
+		return -ENOIOCTLCMD;
+	}
+	return -ENOIOCTLCMD;
+}
+
+static long orangefs_devreq_ioctl(struct file *file,
+			       unsigned int command, unsigned long arg)
+{
+	long ret;
+
+	/* Check for properly constructed commands */
+	ret = check_ioctl_command(command);
+	if (ret < 0)
+		return (int)ret;
+
+	return (int)dispatch_ioctl_command(command, arg);
+}
+
+#ifdef CONFIG_COMPAT		/* CONFIG_COMPAT is in .config */
+
+/*  Compat structure for the ORANGEFS_DEV_MAP ioctl */
+struct ORANGEFS_dev_map_desc32 {
+	compat_uptr_t ptr;
+	__s32 total_size;
+	__s32 size;
+	__s32 count;
+};
+
+static unsigned long translate_dev_map26(unsigned long args, long *error)
+{
+	struct ORANGEFS_dev_map_desc32 __user *p32 = (void __user *)args;
+	/*
+	 * Depending on the architecture, allocate some space on the
+	 * user-call-stack based on our expected layout.
+	 */
+	struct ORANGEFS_dev_map_desc __user *p =
+	    compat_alloc_user_space(sizeof(*p));
+	compat_uptr_t addr;
+
+	*error = 0;
+	/* get the ptr from the 32 bit user-space */
+	if (get_user(addr, &p32->ptr))
+		goto err;
+	/* try to put that into a 64-bit layout */
+	if (put_user(compat_ptr(addr), &p->ptr))
+		goto err;
+	/* copy the remaining fields */
+	if (copy_in_user(&p->total_size, &p32->total_size, sizeof(__s32)))
+		goto err;
+	if (copy_in_user(&p->size, &p32->size, sizeof(__s32)))
+		goto err;
+	if (copy_in_user(&p->count, &p32->count, sizeof(__s32)))
+		goto err;
+	return (unsigned long)p;
+err:
+	*error = -EFAULT;
+	return 0;
+}
+
+/*
+ * 32 bit user-space apps' ioctl handlers when kernel modules
+ * is compiled as a 64 bit one
+ */
+static long orangefs_devreq_compat_ioctl(struct file *filp, unsigned int cmd,
+				      unsigned long args)
+{
+	long ret;
+	unsigned long arg = args;
+
+	/* Check for properly constructed commands */
+	ret = check_ioctl_command(cmd);
+	if (ret < 0)
+		return ret;
+	if (cmd == ORANGEFS_DEV_MAP) {
+		/*
+		 * convert the arguments to what we expect internally
+		 * in kernel space
+		 */
+		arg = translate_dev_map26(args, &ret);
+		if (ret < 0) {
+			gossip_err("Could not translate dev map\n");
+			return ret;
+		}
+	}
+	/* no other ioctl requires translation */
+	return dispatch_ioctl_command(cmd, arg);
+}
+
+#endif /* CONFIG_COMPAT is in .config */
+
+/* the assigned character device major number */
+static int orangefs_dev_major;
+
+/*
+ * Initialize orangefs device specific state:
+ * Must be called at module load time only
+ */
+int orangefs_dev_init(void)
+{
+	/* register orangefs-req device  */
+	orangefs_dev_major = register_chrdev(0,
+					  ORANGEFS_REQDEVICE_NAME,
+					  &orangefs_devreq_file_operations);
+	if (orangefs_dev_major < 0) {
+		gossip_debug(GOSSIP_DEV_DEBUG,
+			     "Failed to register /dev/%s (error %d)\n",
+			     ORANGEFS_REQDEVICE_NAME, orangefs_dev_major);
+		return orangefs_dev_major;
+	}
+
+	gossip_debug(GOSSIP_DEV_DEBUG,
+		     "*** /dev/%s character device registered ***\n",
+		     ORANGEFS_REQDEVICE_NAME);
+	gossip_debug(GOSSIP_DEV_DEBUG, "'mknod /dev/%s c %d 0'.\n",
+		     ORANGEFS_REQDEVICE_NAME, orangefs_dev_major);
+	return 0;
+}
+
+void orangefs_dev_cleanup(void)
+{
+	unregister_chrdev(orangefs_dev_major, ORANGEFS_REQDEVICE_NAME);
+	gossip_debug(GOSSIP_DEV_DEBUG,
+		     "*** /dev/%s character device unregistered ***\n",
+		     ORANGEFS_REQDEVICE_NAME);
+}
+
+static unsigned int orangefs_devreq_poll(struct file *file,
+				      struct poll_table_struct *poll_table)
+{
+	int poll_revent_mask = 0;
+
+	poll_wait(file, &orangefs_request_list_waitq, poll_table);
+
+	if (!list_empty(&orangefs_request_list))
+		poll_revent_mask |= POLL_IN;
+	return poll_revent_mask;
+}
+
+const struct file_operations orangefs_devreq_file_operations = {
+	.owner = THIS_MODULE,
+	.read = orangefs_devreq_read,
+	.write_iter = orangefs_devreq_write_iter,
+	.open = orangefs_devreq_open,
+	.release = orangefs_devreq_release,
+	.unlocked_ioctl = orangefs_devreq_ioctl,
+
+#ifdef CONFIG_COMPAT		/* CONFIG_COMPAT is in .config */
+	.compat_ioctl = orangefs_devreq_compat_ioctl,
+#endif
+	.poll = orangefs_devreq_poll
+};
diff --git a/fs/orangefs/dir.c b/fs/orangefs/dir.c
new file mode 100644
index 000000000000..324f0af40d7b
--- /dev/null
+++ b/fs/orangefs/dir.c
@@ -0,0 +1,396 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-bufmap.h"
+
+/*
+ * decode routine used by kmod to deal with the blob sent from
+ * userspace for readdirs. The blob contains zero or more of these
+ * sub-blobs:
+ *   __u32 - represents length of the character string that follows.
+ *   string - between 1 and ORANGEFS_NAME_MAX bytes long.
+ *   padding - (if needed) to cause the __u32 plus the string to be
+ *             eight byte aligned.
+ *   khandle - sizeof(khandle) bytes.
+ */
+static long decode_dirents(char *ptr, size_t size,
+                           struct orangefs_readdir_response_s *readdir)
+{
+	int i;
+	struct orangefs_readdir_response_s *rd =
+		(struct orangefs_readdir_response_s *) ptr;
+	char *buf = ptr;
+	int khandle_size = sizeof(struct orangefs_khandle);
+	size_t offset = offsetof(struct orangefs_readdir_response_s,
+				dirent_array);
+	/* 8 reflects eight byte alignment */
+	int smallest_blob = khandle_size + 8;
+	__u32 len;
+	int aligned_len;
+	int sizeof_u32 = sizeof(__u32);
+	long ret;
+
+	gossip_debug(GOSSIP_DIR_DEBUG, "%s: size:%zu:\n", __func__, size);
+
+	/* size is = offset on empty dirs, > offset on non-empty dirs... */
+	if (size < offset) {
+		gossip_err("%s: size:%zu: offset:%zu:\n",
+			   __func__,
+			   size,
+			   offset);
+		ret = -EINVAL;
+		goto out;
+	}
+
+        if ((size == offset) && (readdir->orangefs_dirent_outcount != 0)) {
+		gossip_err("%s: size:%zu: dirent_outcount:%d:\n",
+			   __func__,
+			   size,
+			   readdir->orangefs_dirent_outcount);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	readdir->token = rd->token;
+	readdir->orangefs_dirent_outcount = rd->orangefs_dirent_outcount;
+	readdir->dirent_array = kcalloc(readdir->orangefs_dirent_outcount,
+					sizeof(*readdir->dirent_array),
+					GFP_KERNEL);
+	if (readdir->dirent_array == NULL) {
+		gossip_err("%s: kcalloc failed.\n", __func__);
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	buf += offset;
+	size -= offset;
+
+	for (i = 0; i < readdir->orangefs_dirent_outcount; i++) {
+		if (size < smallest_blob) {
+			gossip_err("%s: size:%zu: smallest_blob:%d:\n",
+				   __func__,
+				   size,
+				   smallest_blob);
+			ret = -EINVAL;
+			goto free;
+		}
+
+		len = *(__u32 *)buf;
+		if ((len < 1) || (len > ORANGEFS_NAME_MAX)) {
+			gossip_err("%s: len:%d:\n", __func__, len);
+			ret = -EINVAL;
+			goto free;
+		}
+
+		gossip_debug(GOSSIP_DIR_DEBUG,
+			     "%s: size:%zu: len:%d:\n",
+			     __func__,
+			     size,
+			     len);
+
+		readdir->dirent_array[i].d_name = buf + sizeof_u32;
+		readdir->dirent_array[i].d_length = len;
+
+		/*
+		 * Calculate "aligned" length of this string and its
+		 * associated __u32 descriptor.
+		 */
+		aligned_len = ((sizeof_u32 + len + 1) + 7) & ~7;
+		gossip_debug(GOSSIP_DIR_DEBUG,
+			     "%s: aligned_len:%d:\n",
+			     __func__,
+			     aligned_len);
+
+		/*
+		 * The end of the blob should coincide with the end
+		 * of the last sub-blob.
+		 */
+		if (size < aligned_len + khandle_size) {
+			gossip_err("%s: ran off the end of the blob.\n",
+				   __func__);
+			ret = -EINVAL;
+			goto free;
+		}
+		size -= aligned_len + khandle_size;
+
+		buf += aligned_len;
+
+		readdir->dirent_array[i].khandle =
+			*(struct orangefs_khandle *) buf;
+		buf += khandle_size;
+	}
+	ret = buf - ptr;
+	gossip_debug(GOSSIP_DIR_DEBUG, "%s: returning:%ld:\n", __func__, ret);
+	goto out;
+
+free:
+	kfree(readdir->dirent_array);
+	readdir->dirent_array = NULL;
+
+out:
+	return ret;
+}
+
+/*
+ * Read directory entries from an instance of an open directory.
+ */
+static int orangefs_readdir(struct file *file, struct dir_context *ctx)
+{
+	int ret = 0;
+	int buffer_index;
+	/*
+	 * ptoken supports Orangefs' distributed directory logic, added
+	 * in 2.9.2.
+	 */
+	__u64 *ptoken = file->private_data;
+	__u64 pos = 0;
+	ino_t ino = 0;
+	struct dentry *dentry = file->f_path.dentry;
+	struct orangefs_kernel_op_s *new_op = NULL;
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(dentry->d_inode);
+	struct orangefs_readdir_response_s readdir_response;
+	void *dents_buf;
+	int i = 0;
+	int len = 0;
+	ino_t current_ino = 0;
+	char *current_entry = NULL;
+	long bytes_decoded;
+
+	gossip_debug(GOSSIP_DIR_DEBUG,
+		     "%s: ctx->pos:%lld, ptoken = %llu\n",
+		     __func__,
+		     lld(ctx->pos),
+		     llu(*ptoken));
+
+	pos = (__u64) ctx->pos;
+
+	/* are we done? */
+	if (pos == ORANGEFS_READDIR_END) {
+		gossip_debug(GOSSIP_DIR_DEBUG,
+			     "Skipping to termination path\n");
+		return 0;
+	}
+
+	gossip_debug(GOSSIP_DIR_DEBUG,
+		     "orangefs_readdir called on %s (pos=%llu)\n",
+		     dentry->d_name.name, llu(pos));
+
+	memset(&readdir_response, 0, sizeof(readdir_response));
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_READDIR);
+	if (!new_op)
+		return -ENOMEM;
+
+	/*
+	 * Only the indices are shared. No memory is actually shared, but the
+	 * mechanism is used.
+	 */
+	new_op->uses_shared_memory = 1;
+	new_op->upcall.req.readdir.refn = orangefs_inode->refn;
+	new_op->upcall.req.readdir.max_dirent_count =
+	    ORANGEFS_MAX_DIRENT_COUNT_READDIR;
+
+	gossip_debug(GOSSIP_DIR_DEBUG,
+		     "%s: upcall.req.readdir.refn.khandle: %pU\n",
+		     __func__,
+		     &new_op->upcall.req.readdir.refn.khandle);
+
+	new_op->upcall.req.readdir.token = *ptoken;
+
+get_new_buffer_index:
+	buffer_index = orangefs_readdir_index_get();
+	if (buffer_index < 0) {
+		ret = buffer_index;
+		gossip_lerr("orangefs_readdir: orangefs_readdir_index_get() failure (%d)\n",
+			    ret);
+		goto out_free_op;
+	}
+	new_op->upcall.req.readdir.buf_index = buffer_index;
+
+	ret = service_operation(new_op,
+				"orangefs_readdir",
+				get_interruptible_flag(dentry->d_inode));
+
+	gossip_debug(GOSSIP_DIR_DEBUG,
+		     "Readdir downcall status is %d.  ret:%d\n",
+		     new_op->downcall.status,
+		     ret);
+
+	orangefs_readdir_index_put(buffer_index);
+
+	if (ret == -EAGAIN && op_state_purged(new_op)) {
+		/* Client-core indices are invalid after it restarted. */
+		gossip_debug(GOSSIP_DIR_DEBUG,
+			"%s: Getting new buffer_index for retry of readdir..\n",
+			 __func__);
+		goto get_new_buffer_index;
+	}
+
+	if (ret == -EIO && op_state_purged(new_op)) {
+		gossip_err("%s: Client is down. Aborting readdir call.\n",
+			__func__);
+		goto out_free_op;
+	}
+
+	if (ret < 0 || new_op->downcall.status != 0) {
+		gossip_debug(GOSSIP_DIR_DEBUG,
+			     "Readdir request failed.  Status:%d\n",
+			     new_op->downcall.status);
+		if (ret >= 0)
+			ret = new_op->downcall.status;
+		goto out_free_op;
+	}
+
+	dents_buf = new_op->downcall.trailer_buf;
+	if (dents_buf == NULL) {
+		gossip_err("Invalid NULL buffer in readdir response\n");
+		ret = -ENOMEM;
+		goto out_free_op;
+	}
+
+	bytes_decoded = decode_dirents(dents_buf, new_op->downcall.trailer_size,
+					&readdir_response);
+	if (bytes_decoded < 0) {
+		ret = bytes_decoded;
+		gossip_err("Could not decode readdir from buffer %d\n", ret);
+		goto out_vfree;
+	}
+
+	if (bytes_decoded != new_op->downcall.trailer_size) {
+		gossip_err("orangefs_readdir: # bytes decoded (%ld) "
+			   "!= trailer size (%ld)\n",
+			   bytes_decoded,
+			   (long)new_op->downcall.trailer_size);
+		ret = -EINVAL;
+		goto out_destroy_handle;
+	}
+
+	/*
+	 *  orangefs doesn't actually store dot and dot-dot, but
+	 *  we need to have them represented.
+	 */
+	if (pos == 0) {
+		ino = get_ino_from_khandle(dentry->d_inode);
+		gossip_debug(GOSSIP_DIR_DEBUG,
+			     "%s: calling dir_emit of \".\" with pos = %llu\n",
+			     __func__,
+			     llu(pos));
+		ret = dir_emit(ctx, ".", 1, ino, DT_DIR);
+		pos += 1;
+	}
+
+	if (pos == 1) {
+		ino = get_parent_ino_from_dentry(dentry);
+		gossip_debug(GOSSIP_DIR_DEBUG,
+			     "%s: calling dir_emit of \"..\" with pos = %llu\n",
+			     __func__,
+			     llu(pos));
+		ret = dir_emit(ctx, "..", 2, ino, DT_DIR);
+		pos += 1;
+	}
+
+	/*
+	 * we stored ORANGEFS_ITERATE_NEXT in ctx->pos last time around
+	 * to prevent "finding" dot and dot-dot on any iteration
+	 * other than the first.
+	 */
+	if (ctx->pos == ORANGEFS_ITERATE_NEXT)
+		ctx->pos = 0;
+
+	gossip_debug(GOSSIP_DIR_DEBUG,
+		     "%s: dirent_outcount:%d:\n",
+		     __func__,
+		     readdir_response.orangefs_dirent_outcount);
+	for (i = ctx->pos;
+	     i < readdir_response.orangefs_dirent_outcount;
+	     i++) {
+		len = readdir_response.dirent_array[i].d_length;
+		current_entry = readdir_response.dirent_array[i].d_name;
+		current_ino = orangefs_khandle_to_ino(
+			&readdir_response.dirent_array[i].khandle);
+
+		gossip_debug(GOSSIP_DIR_DEBUG,
+			     "calling dir_emit for %s with len %d"
+			     ", ctx->pos %ld\n",
+			     current_entry,
+			     len,
+			     (unsigned long)ctx->pos);
+		/*
+		 * type is unknown. We don't return object type
+		 * in the dirent_array. This leaves getdents
+		 * clueless about type.
+		 */
+		ret =
+		    dir_emit(ctx, current_entry, len, current_ino, DT_UNKNOWN);
+		if (!ret)
+			break;
+		ctx->pos++;
+		gossip_debug(GOSSIP_DIR_DEBUG,
+			      "%s: ctx->pos:%lld\n",
+			      __func__,
+			      lld(ctx->pos));
+
+	}
+
+	/*
+	 * we ran all the way through the last batch, set up for
+	 * getting another batch...
+	 */
+	if (ret) {
+		*ptoken = readdir_response.token;
+		ctx->pos = ORANGEFS_ITERATE_NEXT;
+	}
+
+	/*
+	 * Did we hit the end of the directory?
+	 */
+	if (readdir_response.token == ORANGEFS_READDIR_END) {
+		gossip_debug(GOSSIP_DIR_DEBUG,
+		"End of dir detected; setting ctx->pos to ORANGEFS_READDIR_END.\n");
+		ctx->pos = ORANGEFS_READDIR_END;
+	}
+
+out_destroy_handle:
+	/* kfree(NULL) is safe */
+	kfree(readdir_response.dirent_array);
+out_vfree:
+	gossip_debug(GOSSIP_DIR_DEBUG, "vfree %p\n", dents_buf);
+	vfree(dents_buf);
+out_free_op:
+	op_release(new_op);
+	gossip_debug(GOSSIP_DIR_DEBUG, "orangefs_readdir returning %d\n", ret);
+	return ret;
+}
+
+static int orangefs_dir_open(struct inode *inode, struct file *file)
+{
+	__u64 *ptoken;
+
+	file->private_data = kmalloc(sizeof(__u64), GFP_KERNEL);
+	if (!file->private_data)
+		return -ENOMEM;
+
+	ptoken = file->private_data;
+	*ptoken = ORANGEFS_READDIR_START;
+	return 0;
+}
+
+static int orangefs_dir_release(struct inode *inode, struct file *file)
+{
+	orangefs_flush_inode(inode);
+	kfree(file->private_data);
+	return 0;
+}
+
+/** ORANGEFS implementation of VFS directory operations */
+const struct file_operations orangefs_dir_operations = {
+	.read = generic_read_dir,
+	.iterate = orangefs_readdir,
+	.open = orangefs_dir_open,
+	.release = orangefs_dir_release,
+};
diff --git a/fs/orangefs/downcall.h b/fs/orangefs/downcall.h
new file mode 100644
index 000000000000..66b99210f1f9
--- /dev/null
+++ b/fs/orangefs/downcall.h
@@ -0,0 +1,133 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+/*
+ *  Definitions of downcalls used in Linux kernel module.
+ */
+
+#ifndef __DOWNCALL_H
+#define __DOWNCALL_H
+
+/*
+ * Sanitized the device-client core interaction
+ * for clean 32-64 bit usage
+ */
+struct orangefs_io_response {
+	__s64 amt_complete;
+};
+
+struct orangefs_lookup_response {
+	struct orangefs_object_kref refn;
+};
+
+struct orangefs_create_response {
+	struct orangefs_object_kref refn;
+};
+
+struct orangefs_symlink_response {
+	struct orangefs_object_kref refn;
+};
+
+struct orangefs_getattr_response {
+	struct ORANGEFS_sys_attr_s attributes;
+	char link_target[ORANGEFS_NAME_MAX];
+};
+
+struct orangefs_mkdir_response {
+	struct orangefs_object_kref refn;
+};
+
+/*
+ * duplication of some system interface structures so that I don't have
+ * to allocate extra memory
+ */
+struct orangefs_dirent {
+	char *d_name;
+	int d_length;
+	struct orangefs_khandle khandle;
+};
+
+struct orangefs_statfs_response {
+	__s64 block_size;
+	__s64 blocks_total;
+	__s64 blocks_avail;
+	__s64 files_total;
+	__s64 files_avail;
+};
+
+struct orangefs_fs_mount_response {
+	__s32 fs_id;
+	__s32 id;
+	struct orangefs_khandle root_khandle;
+};
+
+/* the getxattr response is the attribute value */
+struct orangefs_getxattr_response {
+	__s32 val_sz;
+	__s32 __pad1;
+	char val[ORANGEFS_MAX_XATTR_VALUELEN];
+};
+
+/* the listxattr response is an array of attribute names */
+struct orangefs_listxattr_response {
+	__s32 returned_count;
+	__s32 __pad1;
+	__u64 token;
+	char key[ORANGEFS_MAX_XATTR_LISTLEN * ORANGEFS_MAX_XATTR_NAMELEN];
+	__s32 keylen;
+	__s32 __pad2;
+	__s32 lengths[ORANGEFS_MAX_XATTR_LISTLEN];
+};
+
+struct orangefs_param_response {
+	__s64 value;
+};
+
+#define PERF_COUNT_BUF_SIZE 4096
+struct orangefs_perf_count_response {
+	char buffer[PERF_COUNT_BUF_SIZE];
+};
+
+#define FS_KEY_BUF_SIZE 4096
+struct orangefs_fs_key_response {
+	__s32 fs_keylen;
+	__s32 __pad1;
+	char fs_key[FS_KEY_BUF_SIZE];
+};
+
+struct orangefs_downcall_s {
+	__s32 type;
+	__s32 status;
+	/* currently trailer is used only by readdir */
+	__s64 trailer_size;
+	char *trailer_buf;
+
+	union {
+		struct orangefs_io_response io;
+		struct orangefs_lookup_response lookup;
+		struct orangefs_create_response create;
+		struct orangefs_symlink_response sym;
+		struct orangefs_getattr_response getattr;
+		struct orangefs_mkdir_response mkdir;
+		struct orangefs_statfs_response statfs;
+		struct orangefs_fs_mount_response fs_mount;
+		struct orangefs_getxattr_response getxattr;
+		struct orangefs_listxattr_response listxattr;
+		struct orangefs_param_response param;
+		struct orangefs_perf_count_response perf_count;
+		struct orangefs_fs_key_response fs_key;
+	} resp;
+};
+
+struct orangefs_readdir_response_s {
+	__u64 token;
+	__u64 directory_version;
+	__u32 __pad2;
+	__u32 orangefs_dirent_outcount;
+	struct orangefs_dirent *dirent_array;
+};
+
+#endif /* __DOWNCALL_H */
diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c
new file mode 100644
index 000000000000..ae92795ed965
--- /dev/null
+++ b/fs/orangefs/file.c
@@ -0,0 +1,717 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+/*
+ *  Linux VFS file operations.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-bufmap.h"
+#include <linux/fs.h>
+#include <linux/pagemap.h>
+
+/*
+ * Copy to client-core's address space from the buffers specified
+ * by the iovec upto total_size bytes.
+ * NOTE: the iovector can either contain addresses which
+ *       can futher be kernel-space or user-space addresses.
+ *       or it can pointers to struct page's
+ */
+static int precopy_buffers(int buffer_index,
+			   struct iov_iter *iter,
+			   size_t total_size)
+{
+	int ret = 0;
+	/*
+	 * copy data from application/kernel by pulling it out
+	 * of the iovec.
+	 */
+
+
+	if (total_size) {
+		ret = orangefs_bufmap_copy_from_iovec(iter,
+						      buffer_index,
+						      total_size);
+		if (ret < 0)
+		gossip_err("%s: Failed to copy-in buffers. Please make sure that the pvfs2-client is running. %ld\n",
+			   __func__,
+			   (long)ret);
+	}
+
+	if (ret < 0)
+		gossip_err("%s: Failed to copy-in buffers. Please make sure that the pvfs2-client is running. %ld\n",
+			__func__,
+			(long)ret);
+	return ret;
+}
+
+/*
+ * Copy from client-core's address space to the buffers specified
+ * by the iovec upto total_size bytes.
+ * NOTE: the iovector can either contain addresses which
+ *       can futher be kernel-space or user-space addresses.
+ *       or it can pointers to struct page's
+ */
+static int postcopy_buffers(int buffer_index,
+			    struct iov_iter *iter,
+			    size_t total_size)
+{
+	int ret = 0;
+	/*
+	 * copy data to application/kernel by pushing it out to
+	 * the iovec. NOTE; target buffers can be addresses or
+	 * struct page pointers.
+	 */
+	if (total_size) {
+		ret = orangefs_bufmap_copy_to_iovec(iter,
+						    buffer_index,
+						    total_size);
+		if (ret < 0)
+			gossip_err("%s: Failed to copy-out buffers. Please make sure that the pvfs2-client is running (%ld)\n",
+				__func__,
+				(long)ret);
+	}
+	return ret;
+}
+
+/*
+ * Post and wait for the I/O upcall to finish
+ */
+static ssize_t wait_for_direct_io(enum ORANGEFS_io_type type, struct inode *inode,
+		loff_t *offset, struct iov_iter *iter,
+		size_t total_size, loff_t readahead_size)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	struct orangefs_khandle *handle = &orangefs_inode->refn.khandle;
+	struct orangefs_kernel_op_s *new_op = NULL;
+	struct iov_iter saved = *iter;
+	int buffer_index = -1;
+	ssize_t ret;
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_FILE_IO);
+	if (!new_op)
+		return -ENOMEM;
+
+	/* synchronous I/O */
+	new_op->upcall.req.io.readahead_size = readahead_size;
+	new_op->upcall.req.io.io_type = type;
+	new_op->upcall.req.io.refn = orangefs_inode->refn;
+
+populate_shared_memory:
+	/* get a shared buffer index */
+	buffer_index = orangefs_bufmap_get();
+	if (buffer_index < 0) {
+		ret = buffer_index;
+		gossip_debug(GOSSIP_FILE_DEBUG,
+			     "%s: orangefs_bufmap_get failure (%zd)\n",
+			     __func__, ret);
+		goto out;
+	}
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		     "%s(%pU): GET op %p -> buffer_index %d\n",
+		     __func__,
+		     handle,
+		     new_op,
+		     buffer_index);
+
+	new_op->uses_shared_memory = 1;
+	new_op->upcall.req.io.buf_index = buffer_index;
+	new_op->upcall.req.io.count = total_size;
+	new_op->upcall.req.io.offset = *offset;
+
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		     "%s(%pU): offset: %llu total_size: %zd\n",
+		     __func__,
+		     handle,
+		     llu(*offset),
+		     total_size);
+	/*
+	 * Stage 1: copy the buffers into client-core's address space
+	 * precopy_buffers only pertains to writes.
+	 */
+	if (type == ORANGEFS_IO_WRITE) {
+		ret = precopy_buffers(buffer_index,
+				      iter,
+				      total_size);
+		if (ret < 0)
+			goto out;
+	}
+
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		     "%s(%pU): Calling post_io_request with tag (%llu)\n",
+		     __func__,
+		     handle,
+		     llu(new_op->tag));
+
+	/* Stage 2: Service the I/O operation */
+	ret = service_operation(new_op,
+				type == ORANGEFS_IO_WRITE ?
+					"file_write" :
+					"file_read",
+				get_interruptible_flag(inode));
+
+	/*
+	 * If service_operation() returns -EAGAIN #and# the operation was
+	 * purged from orangefs_request_list or htable_ops_in_progress, then
+	 * we know that the client was restarted, causing the shared memory
+	 * area to be wiped clean.  To restart a  write operation in this
+	 * case, we must re-copy the data from the user's iovec to a NEW
+	 * shared memory location. To restart a read operation, we must get
+	 * a new shared memory location.
+	 */
+	if (ret == -EAGAIN && op_state_purged(new_op)) {
+		orangefs_bufmap_put(buffer_index);
+		buffer_index = -1;
+		if (type == ORANGEFS_IO_WRITE)
+			*iter = saved;
+		gossip_debug(GOSSIP_FILE_DEBUG,
+			     "%s:going to repopulate_shared_memory.\n",
+			     __func__);
+		goto populate_shared_memory;
+	}
+
+	if (ret < 0) {
+		if (ret == -EINTR) {
+			/*
+			 * We can't return EINTR if any data was written,
+			 * it's not POSIX. It is minimally acceptable
+			 * to give a partial write, the way NFS does.
+			 *
+			 * It would be optimal to return all or nothing,
+			 * but if a userspace write is bigger than
+			 * an IO buffer, and the interrupt occurs
+			 * between buffer writes, that would not be
+			 * possible.
+			 */
+			switch (new_op->op_state - OP_VFS_STATE_GIVEN_UP) {
+			/*
+			 * If the op was waiting when the interrupt
+			 * occurred, then the client-core did not
+			 * trigger the write.
+			 */
+			case OP_VFS_STATE_WAITING:
+				if (*offset == 0)
+					ret = -EINTR;
+				else
+					ret = 0;
+				break;
+			/* 
+			 * If the op was in progress when the interrupt
+			 * occurred, then the client-core was able to
+			 * trigger the write.
+			 */
+			case OP_VFS_STATE_INPROGR:
+				ret = total_size;
+				break;
+			default:
+				gossip_err("%s: unexpected op state :%d:.\n",
+					   __func__,
+					   new_op->op_state);
+				ret = 0;
+				break;
+			}
+			gossip_debug(GOSSIP_FILE_DEBUG,
+				     "%s: got EINTR, state:%d: %p\n",
+				     __func__,
+				     new_op->op_state,
+				     new_op);
+		} else {
+			gossip_err("%s: error in %s handle %pU, returning %zd\n",
+				__func__,
+				type == ORANGEFS_IO_READ ?
+					"read from" : "write to",
+				handle, ret);
+		}
+		if (orangefs_cancel_op_in_progress(new_op))
+			return ret;
+
+		goto out;
+	}
+
+	/*
+	 * Stage 3: Post copy buffers from client-core's address space
+	 * postcopy_buffers only pertains to reads.
+	 */
+	if (type == ORANGEFS_IO_READ) {
+		ret = postcopy_buffers(buffer_index,
+				       iter,
+				       new_op->downcall.resp.io.amt_complete);
+		if (ret < 0)
+			goto out;
+	}
+	gossip_debug(GOSSIP_FILE_DEBUG,
+	    "%s(%pU): Amount %s, returned by the sys-io call:%d\n",
+	    __func__,
+	    handle,
+	    type == ORANGEFS_IO_READ ?  "read" : "written",
+	    (int)new_op->downcall.resp.io.amt_complete);
+
+	ret = new_op->downcall.resp.io.amt_complete;
+
+out:
+	if (buffer_index >= 0) {
+		orangefs_bufmap_put(buffer_index);
+		gossip_debug(GOSSIP_FILE_DEBUG,
+			     "%s(%pU): PUT buffer_index %d\n",
+			     __func__, handle, buffer_index);
+		buffer_index = -1;
+	}
+	op_release(new_op);
+	return ret;
+}
+
+/*
+ * Common entry point for read/write/readv/writev
+ * This function will dispatch it to either the direct I/O
+ * or buffered I/O path depending on the mount options and/or
+ * augmented/extended metadata attached to the file.
+ * Note: File extended attributes override any mount options.
+ */
+static ssize_t do_readv_writev(enum ORANGEFS_io_type type, struct file *file,
+		loff_t *offset, struct iov_iter *iter)
+{
+	struct inode *inode = file->f_mapping->host;
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	struct orangefs_khandle *handle = &orangefs_inode->refn.khandle;
+	size_t count = iov_iter_count(iter);
+	ssize_t total_count = 0;
+	ssize_t ret = -EINVAL;
+
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		"%s-BEGIN(%pU): count(%d) after estimate_max_iovecs.\n",
+		__func__,
+		handle,
+		(int)count);
+
+	if (type == ORANGEFS_IO_WRITE) {
+		gossip_debug(GOSSIP_FILE_DEBUG,
+			     "%s(%pU): proceeding with offset : %llu, "
+			     "size %d\n",
+			     __func__,
+			     handle,
+			     llu(*offset),
+			     (int)count);
+	}
+
+	if (count == 0) {
+		ret = 0;
+		goto out;
+	}
+
+	while (iov_iter_count(iter)) {
+		size_t each_count = iov_iter_count(iter);
+		size_t amt_complete;
+
+		/* how much to transfer in this loop iteration */
+		if (each_count > orangefs_bufmap_size_query())
+			each_count = orangefs_bufmap_size_query();
+
+		gossip_debug(GOSSIP_FILE_DEBUG,
+			     "%s(%pU): size of each_count(%d)\n",
+			     __func__,
+			     handle,
+			     (int)each_count);
+		gossip_debug(GOSSIP_FILE_DEBUG,
+			     "%s(%pU): BEFORE wait_for_io: offset is %d\n",
+			     __func__,
+			     handle,
+			     (int)*offset);
+
+		ret = wait_for_direct_io(type, inode, offset, iter,
+				each_count, 0);
+		gossip_debug(GOSSIP_FILE_DEBUG,
+			     "%s(%pU): return from wait_for_io:%d\n",
+			     __func__,
+			     handle,
+			     (int)ret);
+
+		if (ret < 0)
+			goto out;
+
+		*offset += ret;
+		total_count += ret;
+		amt_complete = ret;
+
+		gossip_debug(GOSSIP_FILE_DEBUG,
+			     "%s(%pU): AFTER wait_for_io: offset is %d\n",
+			     __func__,
+			     handle,
+			     (int)*offset);
+
+		/*
+		 * if we got a short I/O operations,
+		 * fall out and return what we got so far
+		 */
+		if (amt_complete < each_count)
+			break;
+	} /*end while */
+
+out:
+	if (total_count > 0)
+		ret = total_count;
+	if (ret > 0) {
+		if (type == ORANGEFS_IO_READ) {
+			file_accessed(file);
+		} else {
+			SetMtimeFlag(orangefs_inode);
+			inode->i_mtime = CURRENT_TIME;
+			mark_inode_dirty_sync(inode);
+		}
+	}
+
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		     "%s(%pU): Value(%d) returned.\n",
+		     __func__,
+		     handle,
+		     (int)ret);
+
+	return ret;
+}
+
+/*
+ * Read data from a specified offset in a file (referenced by inode).
+ * Data may be placed either in a user or kernel buffer.
+ */
+ssize_t orangefs_inode_read(struct inode *inode,
+			    struct iov_iter *iter,
+			    loff_t *offset,
+			    loff_t readahead_size)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	size_t count = iov_iter_count(iter);
+	size_t bufmap_size;
+	ssize_t ret = -EINVAL;
+
+	g_orangefs_stats.reads++;
+
+	bufmap_size = orangefs_bufmap_size_query();
+	if (count > bufmap_size) {
+		gossip_debug(GOSSIP_FILE_DEBUG,
+			     "%s: count is too large (%zd/%zd)!\n",
+			     __func__, count, bufmap_size);
+		return -EINVAL;
+	}
+
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		     "%s(%pU) %zd@%llu\n",
+		     __func__,
+		     &orangefs_inode->refn.khandle,
+		     count,
+		     llu(*offset));
+
+	ret = wait_for_direct_io(ORANGEFS_IO_READ, inode, offset, iter,
+			count, readahead_size);
+	if (ret > 0)
+		*offset += ret;
+
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		     "%s(%pU): Value(%zd) returned.\n",
+		     __func__,
+		     &orangefs_inode->refn.khandle,
+		     ret);
+
+	return ret;
+}
+
+static ssize_t orangefs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct file *file = iocb->ki_filp;
+	loff_t pos = *(&iocb->ki_pos);
+	ssize_t rc = 0;
+
+	BUG_ON(iocb->private);
+
+	gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_file_read_iter\n");
+
+	g_orangefs_stats.reads++;
+
+	rc = do_readv_writev(ORANGEFS_IO_READ, file, &pos, iter);
+	iocb->ki_pos = pos;
+
+	return rc;
+}
+
+static ssize_t orangefs_file_write_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct file *file = iocb->ki_filp;
+	loff_t pos;
+	ssize_t rc;
+
+	BUG_ON(iocb->private);
+
+	gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_file_write_iter\n");
+
+	mutex_lock(&file->f_mapping->host->i_mutex);
+
+	/* Make sure generic_write_checks sees an up to date inode size. */
+	if (file->f_flags & O_APPEND) {
+		rc = orangefs_inode_getattr(file->f_mapping->host, 0, 1);
+		if (rc == -ESTALE)
+			rc = -EIO;
+		if (rc) {
+			gossip_err("%s: orangefs_inode_getattr failed, "
+			    "rc:%zd:.\n", __func__, rc);
+			goto out;
+		}
+	}
+
+	if (file->f_pos > i_size_read(file->f_mapping->host))
+		orangefs_i_size_write(file->f_mapping->host, file->f_pos);
+
+	rc = generic_write_checks(iocb, iter);
+
+	if (rc <= 0) {
+		gossip_err("%s: generic_write_checks failed, rc:%zd:.\n",
+			   __func__, rc);
+		goto out;
+	}
+
+	/*
+	 * if we are appending, generic_write_checks would have updated
+	 * pos to the end of the file, so we will wait till now to set
+	 * pos...
+	 */
+	pos = *(&iocb->ki_pos);
+
+	rc = do_readv_writev(ORANGEFS_IO_WRITE,
+			     file,
+			     &pos,
+			     iter);
+	if (rc < 0) {
+		gossip_err("%s: do_readv_writev failed, rc:%zd:.\n",
+			   __func__, rc);
+		goto out;
+	}
+
+	iocb->ki_pos = pos;
+	g_orangefs_stats.writes++;
+
+out:
+
+	mutex_unlock(&file->f_mapping->host->i_mutex);
+	return rc;
+}
+
+/*
+ * Perform a miscellaneous operation on a file.
+ */
+static long orangefs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	int ret = -ENOTTY;
+	__u64 val = 0;
+	unsigned long uval;
+
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		     "orangefs_ioctl: called with cmd %d\n",
+		     cmd);
+
+	/*
+	 * we understand some general ioctls on files, such as the immutable
+	 * and append flags
+	 */
+	if (cmd == FS_IOC_GETFLAGS) {
+		val = 0;
+		ret = orangefs_inode_getxattr(file_inode(file),
+					      ORANGEFS_XATTR_NAME_DEFAULT_PREFIX,
+					      "user.pvfs2.meta_hint",
+					      &val, sizeof(val));
+		if (ret < 0 && ret != -ENODATA)
+			return ret;
+		else if (ret == -ENODATA)
+			val = 0;
+		uval = val;
+		gossip_debug(GOSSIP_FILE_DEBUG,
+			     "orangefs_ioctl: FS_IOC_GETFLAGS: %llu\n",
+			     (unsigned long long)uval);
+		return put_user(uval, (int __user *)arg);
+	} else if (cmd == FS_IOC_SETFLAGS) {
+		ret = 0;
+		if (get_user(uval, (int __user *)arg))
+			return -EFAULT;
+		/*
+		 * ORANGEFS_MIRROR_FL is set internally when the mirroring mode
+		 * is turned on for a file. The user is not allowed to turn
+		 * on this bit, but the bit is present if the user first gets
+		 * the flags and then updates the flags with some new
+		 * settings. So, we ignore it in the following edit. bligon.
+		 */
+		if ((uval & ~ORANGEFS_MIRROR_FL) &
+		    (~(FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NOATIME_FL))) {
+			gossip_err("orangefs_ioctl: the FS_IOC_SETFLAGS only supports setting one of FS_IMMUTABLE_FL|FS_APPEND_FL|FS_NOATIME_FL\n");
+			return -EINVAL;
+		}
+		val = uval;
+		gossip_debug(GOSSIP_FILE_DEBUG,
+			     "orangefs_ioctl: FS_IOC_SETFLAGS: %llu\n",
+			     (unsigned long long)val);
+		ret = orangefs_inode_setxattr(file_inode(file),
+					      ORANGEFS_XATTR_NAME_DEFAULT_PREFIX,
+					      "user.pvfs2.meta_hint",
+					      &val, sizeof(val), 0);
+	}
+
+	return ret;
+}
+
+/*
+ * Memory map a region of a file.
+ */
+static int orangefs_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		     "orangefs_file_mmap: called on %s\n",
+		     (file ?
+			(char *)file->f_path.dentry->d_name.name :
+			(char *)"Unknown"));
+
+	/* set the sequential readahead hint */
+	vma->vm_flags |= VM_SEQ_READ;
+	vma->vm_flags &= ~VM_RAND_READ;
+
+	/* Use readonly mmap since we cannot support writable maps. */
+	return generic_file_readonly_mmap(file, vma);
+}
+
+#define mapping_nrpages(idata) ((idata)->nrpages)
+
+/*
+ * Called to notify the module that there are no more references to
+ * this file (i.e. no processes have it open).
+ *
+ * \note Not called when each file is closed.
+ */
+static int orangefs_file_release(struct inode *inode, struct file *file)
+{
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		     "orangefs_file_release: called on %s\n",
+		     file->f_path.dentry->d_name.name);
+
+	orangefs_flush_inode(inode);
+
+	/*
+	 * remove all associated inode pages from the page cache and mmap
+	 * readahead cache (if any); this forces an expensive refresh of
+	 * data for the next caller of mmap (or 'get_block' accesses)
+	 */
+	if (file->f_path.dentry->d_inode &&
+	    file->f_path.dentry->d_inode->i_mapping &&
+	    mapping_nrpages(&file->f_path.dentry->d_inode->i_data))
+		truncate_inode_pages(file->f_path.dentry->d_inode->i_mapping,
+				     0);
+	return 0;
+}
+
+/*
+ * Push all data for a specific file onto permanent storage.
+ */
+static int orangefs_fsync(struct file *file,
+		       loff_t start,
+		       loff_t end,
+		       int datasync)
+{
+	int ret = -EINVAL;
+	struct orangefs_inode_s *orangefs_inode =
+		ORANGEFS_I(file->f_path.dentry->d_inode);
+	struct orangefs_kernel_op_s *new_op = NULL;
+
+	/* required call */
+	filemap_write_and_wait_range(file->f_mapping, start, end);
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_FSYNC);
+	if (!new_op)
+		return -ENOMEM;
+	new_op->upcall.req.fsync.refn = orangefs_inode->refn;
+
+	ret = service_operation(new_op,
+			"orangefs_fsync",
+			get_interruptible_flag(file->f_path.dentry->d_inode));
+
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		     "orangefs_fsync got return value of %d\n",
+		     ret);
+
+	op_release(new_op);
+
+	orangefs_flush_inode(file->f_path.dentry->d_inode);
+	return ret;
+}
+
+/*
+ * Change the file pointer position for an instance of an open file.
+ *
+ * \note If .llseek is overriden, we must acquire lock as described in
+ *       Documentation/filesystems/Locking.
+ *
+ * Future upgrade could support SEEK_DATA and SEEK_HOLE but would
+ * require much changes to the FS
+ */
+static loff_t orangefs_file_llseek(struct file *file, loff_t offset, int origin)
+{
+	int ret = -EINVAL;
+	struct inode *inode = file_inode(file);
+
+	if (origin == SEEK_END) {
+		/*
+		 * revalidate the inode's file size.
+		 * NOTE: We are only interested in file size here,
+		 * so we set mask accordingly.
+		 */
+		ret = orangefs_inode_getattr(file->f_mapping->host, 0, 1);
+		if (ret == -ESTALE)
+			ret = -EIO;
+		if (ret) {
+			gossip_debug(GOSSIP_FILE_DEBUG,
+				     "%s:%s:%d calling make bad inode\n",
+				     __FILE__,
+				     __func__,
+				     __LINE__);
+			return ret;
+		}
+	}
+
+	gossip_debug(GOSSIP_FILE_DEBUG,
+		     "orangefs_file_llseek: offset is %ld | origin is %d"
+		     " | inode size is %lu\n",
+		     (long)offset,
+		     origin,
+		     (unsigned long)i_size_read(inode));
+
+	return generic_file_llseek(file, offset, origin);
+}
+
+/*
+ * Support local locks (locks that only this kernel knows about)
+ * if Orangefs was mounted -o local_lock.
+ */
+static int orangefs_lock(struct file *filp, int cmd, struct file_lock *fl)
+{
+	int rc = -EINVAL;
+
+	if (ORANGEFS_SB(filp->f_inode->i_sb)->flags & ORANGEFS_OPT_LOCAL_LOCK) {
+		if (cmd == F_GETLK) {
+			rc = 0;
+			posix_test_lock(filp, fl);
+		} else {
+			rc = posix_lock_file(filp, fl, NULL);
+		}
+	}
+
+	return rc;
+}
+
+/** ORANGEFS implementation of VFS file operations */
+const struct file_operations orangefs_file_operations = {
+	.llseek		= orangefs_file_llseek,
+	.read_iter	= orangefs_file_read_iter,
+	.write_iter	= orangefs_file_write_iter,
+	.lock		= orangefs_lock,
+	.unlocked_ioctl	= orangefs_ioctl,
+	.mmap		= orangefs_file_mmap,
+	.open		= generic_file_open,
+	.release	= orangefs_file_release,
+	.fsync		= orangefs_fsync,
+};
diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c
new file mode 100644
index 000000000000..85640e955cde
--- /dev/null
+++ b/fs/orangefs/inode.c
@@ -0,0 +1,461 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+/*
+ *  Linux VFS inode operations.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-bufmap.h"
+
+static int read_one_page(struct page *page)
+{
+	int ret;
+	int max_block;
+	ssize_t bytes_read = 0;
+	struct inode *inode = page->mapping->host;
+	const __u32 blocksize = PAGE_SIZE;	/* inode->i_blksize */
+	const __u32 blockbits = PAGE_SHIFT;	/* inode->i_blkbits */
+	struct iov_iter to;
+	struct bio_vec bv = {.bv_page = page, .bv_len = PAGE_SIZE};
+
+	iov_iter_bvec(&to, ITER_BVEC | READ, &bv, 1, PAGE_SIZE);
+
+	gossip_debug(GOSSIP_INODE_DEBUG,
+		    "orangefs_readpage called with page %p\n",
+		     page);
+
+	max_block = ((inode->i_size / blocksize) + 1);
+
+	if (page->index < max_block) {
+		loff_t blockptr_offset = (((loff_t) page->index) << blockbits);
+
+		bytes_read = orangefs_inode_read(inode,
+						 &to,
+						 &blockptr_offset,
+						 inode->i_size);
+	}
+	/* this will only zero remaining unread portions of the page data */
+	iov_iter_zero(~0U, &to);
+	/* takes care of potential aliasing */
+	flush_dcache_page(page);
+	if (bytes_read < 0) {
+		ret = bytes_read;
+		SetPageError(page);
+	} else {
+		SetPageUptodate(page);
+		if (PageError(page))
+			ClearPageError(page);
+		ret = 0;
+	}
+	/* unlock the page after the ->readpage() routine completes */
+	unlock_page(page);
+	return ret;
+}
+
+static int orangefs_readpage(struct file *file, struct page *page)
+{
+	return read_one_page(page);
+}
+
+static int orangefs_readpages(struct file *file,
+			   struct address_space *mapping,
+			   struct list_head *pages,
+			   unsigned nr_pages)
+{
+	int page_idx;
+	int ret;
+
+	gossip_debug(GOSSIP_INODE_DEBUG, "orangefs_readpages called\n");
+
+	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
+		struct page *page;
+
+		page = list_entry(pages->prev, struct page, lru);
+		list_del(&page->lru);
+		if (!add_to_page_cache(page,
+				       mapping,
+				       page->index,
+				       GFP_KERNEL)) {
+			ret = read_one_page(page);
+			gossip_debug(GOSSIP_INODE_DEBUG,
+				"failure adding page to cache, read_one_page returned: %d\n",
+				ret);
+	      } else {
+			put_page(page);
+	      }
+	}
+	BUG_ON(!list_empty(pages));
+	return 0;
+}
+
+static void orangefs_invalidatepage(struct page *page,
+				 unsigned int offset,
+				 unsigned int length)
+{
+	gossip_debug(GOSSIP_INODE_DEBUG,
+		     "orangefs_invalidatepage called on page %p "
+		     "(offset is %u)\n",
+		     page,
+		     offset);
+
+	ClearPageUptodate(page);
+	ClearPageMappedToDisk(page);
+	return;
+
+}
+
+static int orangefs_releasepage(struct page *page, gfp_t foo)
+{
+	gossip_debug(GOSSIP_INODE_DEBUG,
+		     "orangefs_releasepage called on page %p\n",
+		     page);
+	return 0;
+}
+
+/*
+ * Having a direct_IO entry point in the address_space_operations
+ * struct causes the kernel to allows us to use O_DIRECT on
+ * open. Nothing will ever call this thing, but in the future we
+ * will need to be able to use O_DIRECT on open in order to support
+ * AIO. Modeled after NFS, they do this too.
+ */
+/*
+ * static ssize_t orangefs_direct_IO(int rw,
+ *			struct kiocb *iocb,
+ *			struct iov_iter *iter,
+ *			loff_t offset)
+ *{
+ *	gossip_debug(GOSSIP_INODE_DEBUG,
+ *		     "orangefs_direct_IO: %s\n",
+ *		     iocb->ki_filp->f_path.dentry->d_name.name);
+ *
+ *	return -EINVAL;
+ *}
+ */
+
+struct backing_dev_info orangefs_backing_dev_info = {
+	.name = "orangefs",
+	.ra_pages = 0,
+	.capabilities = BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
+};
+
+/** ORANGEFS2 implementation of address space operations */
+const struct address_space_operations orangefs_address_operations = {
+	.readpage = orangefs_readpage,
+	.readpages = orangefs_readpages,
+	.invalidatepage = orangefs_invalidatepage,
+	.releasepage = orangefs_releasepage,
+/*	.direct_IO = orangefs_direct_IO */
+};
+
+static int orangefs_setattr_size(struct inode *inode, struct iattr *iattr)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	struct orangefs_kernel_op_s *new_op;
+	loff_t orig_size;
+	int ret = -EINVAL;
+
+	gossip_debug(GOSSIP_INODE_DEBUG,
+		     "%s: %pU: Handle is %pU | fs_id %d | size is %llu\n",
+		     __func__,
+		     get_khandle_from_ino(inode),
+		     &orangefs_inode->refn.khandle,
+		     orangefs_inode->refn.fs_id,
+		     iattr->ia_size);
+
+	/* Ensure that we have a up to date size, so we know if it changed. */
+	ret = orangefs_inode_getattr(inode, 0, 1);
+	if (ret == -ESTALE)
+		ret = -EIO;
+	if (ret) {
+		gossip_err("%s: orangefs_inode_getattr failed, ret:%d:.\n",
+		    __func__, ret);
+		return ret;
+	}
+	orig_size = i_size_read(inode);
+
+	truncate_setsize(inode, iattr->ia_size);
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_TRUNCATE);
+	if (!new_op)
+		return -ENOMEM;
+
+	new_op->upcall.req.truncate.refn = orangefs_inode->refn;
+	new_op->upcall.req.truncate.size = (__s64) iattr->ia_size;
+
+	ret = service_operation(new_op, __func__,
+				get_interruptible_flag(inode));
+
+	/*
+	 * the truncate has no downcall members to retrieve, but
+	 * the status value tells us if it went through ok or not
+	 */
+	gossip_debug(GOSSIP_INODE_DEBUG,
+		     "orangefs: orangefs_truncate got return value of %d\n",
+		     ret);
+
+	op_release(new_op);
+
+	if (ret != 0)
+		return ret;
+
+	if (orig_size != i_size_read(inode))
+		iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME;
+
+	return ret;
+}
+
+/*
+ * Change attributes of an object referenced by dentry.
+ */
+int orangefs_setattr(struct dentry *dentry, struct iattr *iattr)
+{
+	int ret = -EINVAL;
+	struct inode *inode = dentry->d_inode;
+
+	gossip_debug(GOSSIP_INODE_DEBUG,
+		     "orangefs_setattr: called on %s\n",
+		     dentry->d_name.name);
+
+	ret = inode_change_ok(inode, iattr);
+	if (ret)
+		goto out;
+
+	if ((iattr->ia_valid & ATTR_SIZE) &&
+	    iattr->ia_size != i_size_read(inode)) {
+		ret = orangefs_setattr_size(inode, iattr);
+		if (ret)
+			goto out;
+	}
+
+	setattr_copy(inode, iattr);
+	mark_inode_dirty(inode);
+
+	ret = orangefs_inode_setattr(inode, iattr);
+	gossip_debug(GOSSIP_INODE_DEBUG,
+		     "orangefs_setattr: inode_setattr returned %d\n",
+		     ret);
+
+	if (!ret && (iattr->ia_valid & ATTR_MODE))
+		/* change mod on a file that has ACLs */
+		ret = posix_acl_chmod(inode, inode->i_mode);
+
+out:
+	gossip_debug(GOSSIP_INODE_DEBUG, "orangefs_setattr: returning %d\n", ret);
+	return ret;
+}
+
+/*
+ * Obtain attributes of an object given a dentry
+ */
+int orangefs_getattr(struct vfsmount *mnt,
+		  struct dentry *dentry,
+		  struct kstat *kstat)
+{
+	int ret = -ENOENT;
+	struct inode *inode = dentry->d_inode;
+	struct orangefs_inode_s *orangefs_inode = NULL;
+
+	gossip_debug(GOSSIP_INODE_DEBUG,
+		     "orangefs_getattr: called on %s\n",
+		     dentry->d_name.name);
+
+	ret = orangefs_inode_getattr(inode, 0, 1);
+	if (ret == 0) {
+		generic_fillattr(inode, kstat);
+
+		/* override block size reported to stat */
+		orangefs_inode = ORANGEFS_I(inode);
+		kstat->blksize = orangefs_inode->blksize;
+	}
+	return ret;
+}
+
+int orangefs_permission(struct inode *inode, int mask)
+{
+	int ret;
+
+	if (mask & MAY_NOT_BLOCK)
+		return -ECHILD;
+
+	gossip_debug(GOSSIP_INODE_DEBUG, "%s: refreshing\n", __func__);
+
+	/* Make sure the permission (and other common attrs) are up to date. */
+	ret = orangefs_inode_getattr(inode, 0, 0);
+	if (ret < 0)
+		return ret;
+
+	return generic_permission(inode, mask);
+}
+
+/* ORANGEDS2 implementation of VFS inode operations for files */
+struct inode_operations orangefs_file_inode_operations = {
+	.get_acl = orangefs_get_acl,
+	.set_acl = orangefs_set_acl,
+	.setattr = orangefs_setattr,
+	.getattr = orangefs_getattr,
+	.setxattr = generic_setxattr,
+	.getxattr = generic_getxattr,
+	.listxattr = orangefs_listxattr,
+	.removexattr = generic_removexattr,
+	.permission = orangefs_permission,
+};
+
+static int orangefs_init_iops(struct inode *inode)
+{
+	inode->i_mapping->a_ops = &orangefs_address_operations;
+
+	switch (inode->i_mode & S_IFMT) {
+	case S_IFREG:
+		inode->i_op = &orangefs_file_inode_operations;
+		inode->i_fop = &orangefs_file_operations;
+		inode->i_blkbits = PAGE_SHIFT;
+		break;
+	case S_IFLNK:
+		inode->i_op = &orangefs_symlink_inode_operations;
+		break;
+	case S_IFDIR:
+		inode->i_op = &orangefs_dir_inode_operations;
+		inode->i_fop = &orangefs_dir_operations;
+		break;
+	default:
+		gossip_debug(GOSSIP_INODE_DEBUG,
+			     "%s: unsupported mode\n",
+			     __func__);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/*
+ * Given a ORANGEFS object identifier (fsid, handle), convert it into a ino_t type
+ * that will be used as a hash-index from where the handle will
+ * be searched for in the VFS hash table of inodes.
+ */
+static inline ino_t orangefs_handle_hash(struct orangefs_object_kref *ref)
+{
+	if (!ref)
+		return 0;
+	return orangefs_khandle_to_ino(&(ref->khandle));
+}
+
+/*
+ * Called to set up an inode from iget5_locked.
+ */
+static int orangefs_set_inode(struct inode *inode, void *data)
+{
+	struct orangefs_object_kref *ref = (struct orangefs_object_kref *) data;
+	ORANGEFS_I(inode)->refn.fs_id = ref->fs_id;
+	ORANGEFS_I(inode)->refn.khandle = ref->khandle;
+	return 0;
+}
+
+/*
+ * Called to determine if handles match.
+ */
+static int orangefs_test_inode(struct inode *inode, void *data)
+{
+	struct orangefs_object_kref *ref = (struct orangefs_object_kref *) data;
+	struct orangefs_inode_s *orangefs_inode = NULL;
+
+	orangefs_inode = ORANGEFS_I(inode);
+	return (!ORANGEFS_khandle_cmp(&(orangefs_inode->refn.khandle), &(ref->khandle))
+		&& orangefs_inode->refn.fs_id == ref->fs_id);
+}
+
+/*
+ * Front-end to lookup the inode-cache maintained by the VFS using the ORANGEFS
+ * file handle.
+ *
+ * @sb: the file system super block instance.
+ * @ref: The ORANGEFS object for which we are trying to locate an inode structure.
+ */
+struct inode *orangefs_iget(struct super_block *sb, struct orangefs_object_kref *ref)
+{
+	struct inode *inode = NULL;
+	unsigned long hash;
+	int error;
+
+	hash = orangefs_handle_hash(ref);
+	inode = iget5_locked(sb, hash, orangefs_test_inode, orangefs_set_inode, ref);
+	if (!inode || !(inode->i_state & I_NEW))
+		return inode;
+
+	error = orangefs_inode_getattr(inode, 1, 0);
+	if (error) {
+		iget_failed(inode);
+		return ERR_PTR(error);
+	}
+
+	inode->i_ino = hash;	/* needed for stat etc */
+	orangefs_init_iops(inode);
+	unlock_new_inode(inode);
+
+	gossip_debug(GOSSIP_INODE_DEBUG,
+		     "iget handle %pU, fsid %d hash %ld i_ino %lu\n",
+		     &ref->khandle,
+		     ref->fs_id,
+		     hash,
+		     inode->i_ino);
+
+	return inode;
+}
+
+/*
+ * Allocate an inode for a newly created file and insert it into the inode hash.
+ */
+struct inode *orangefs_new_inode(struct super_block *sb, struct inode *dir,
+		int mode, dev_t dev, struct orangefs_object_kref *ref)
+{
+	unsigned long hash = orangefs_handle_hash(ref);
+	struct inode *inode;
+	int error;
+
+	gossip_debug(GOSSIP_INODE_DEBUG,
+		     "%s:(sb is %p | MAJOR(dev)=%u | MINOR(dev)=%u mode=%o)\n",
+		     __func__,
+		     sb,
+		     MAJOR(dev),
+		     MINOR(dev),
+		     mode);
+
+	inode = new_inode(sb);
+	if (!inode)
+		return NULL;
+
+	orangefs_set_inode(inode, ref);
+	inode->i_ino = hash;	/* needed for stat etc */
+
+	error = orangefs_inode_getattr(inode, 1, 0);
+	if (error)
+		goto out_iput;
+
+	orangefs_init_iops(inode);
+
+	inode->i_mode = mode;
+	inode->i_uid = current_fsuid();
+	inode->i_gid = current_fsgid();
+	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+	inode->i_size = PAGE_SIZE;
+	inode->i_rdev = dev;
+
+	error = insert_inode_locked4(inode, hash, orangefs_test_inode, ref);
+	if (error < 0)
+		goto out_iput;
+
+	gossip_debug(GOSSIP_INODE_DEBUG,
+		     "Initializing ACL's for inode %pU\n",
+		     get_khandle_from_ino(inode));
+	orangefs_init_acl(inode, dir);
+	return inode;
+
+out_iput:
+	iput(inode);
+	return ERR_PTR(error);
+}
diff --git a/fs/orangefs/namei.c b/fs/orangefs/namei.c
new file mode 100644
index 000000000000..5a60c508af4e
--- /dev/null
+++ b/fs/orangefs/namei.c
@@ -0,0 +1,462 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+/*
+ *  Linux VFS namei operations.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+
+/*
+ * Get a newly allocated inode to go with a negative dentry.
+ */
+static int orangefs_create(struct inode *dir,
+			struct dentry *dentry,
+			umode_t mode,
+			bool exclusive)
+{
+	struct orangefs_inode_s *parent = ORANGEFS_I(dir);
+	struct orangefs_kernel_op_s *new_op;
+	struct inode *inode;
+	int ret;
+
+	gossip_debug(GOSSIP_NAME_DEBUG, "%s: %s\n",
+		     __func__,
+		     dentry->d_name.name);
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_CREATE);
+	if (!new_op)
+		return -ENOMEM;
+
+	new_op->upcall.req.create.parent_refn = parent->refn;
+
+	fill_default_sys_attrs(new_op->upcall.req.create.attributes,
+			       ORANGEFS_TYPE_METAFILE, mode);
+
+	strncpy(new_op->upcall.req.create.d_name,
+		dentry->d_name.name, ORANGEFS_NAME_MAX);
+
+	ret = service_operation(new_op, __func__, get_interruptible_flag(dir));
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "%s: %s: handle:%pU: fsid:%d: new_op:%p: ret:%d:\n",
+		     __func__,
+		     dentry->d_name.name,
+		     &new_op->downcall.resp.create.refn.khandle,
+		     new_op->downcall.resp.create.refn.fs_id,
+		     new_op,
+		     ret);
+
+	if (ret < 0)
+		goto out;
+
+	inode = orangefs_new_inode(dir->i_sb, dir, S_IFREG | mode, 0,
+				&new_op->downcall.resp.create.refn);
+	if (IS_ERR(inode)) {
+		gossip_err("%s: Failed to allocate inode for file :%s:\n",
+			   __func__,
+			   dentry->d_name.name);
+		ret = PTR_ERR(inode);
+		goto out;
+	}
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "%s: Assigned inode :%pU: for file :%s:\n",
+		     __func__,
+		     get_khandle_from_ino(inode),
+		     dentry->d_name.name);
+
+	d_instantiate(dentry, inode);
+	unlock_new_inode(inode);
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "%s: dentry instantiated for %s\n",
+		     __func__,
+		     dentry->d_name.name);
+
+	SetMtimeFlag(parent);
+	dir->i_mtime = dir->i_ctime = current_fs_time(dir->i_sb);
+	mark_inode_dirty_sync(dir);
+	ret = 0;
+out:
+	op_release(new_op);
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "%s: %s: returning %d\n",
+		     __func__,
+		     dentry->d_name.name,
+		     ret);
+	return ret;
+}
+
+/*
+ * Attempt to resolve an object name (dentry->d_name), parent handle, and
+ * fsid into a handle for the object.
+ */
+static struct dentry *orangefs_lookup(struct inode *dir, struct dentry *dentry,
+				   unsigned int flags)
+{
+	struct orangefs_inode_s *parent = ORANGEFS_I(dir);
+	struct orangefs_kernel_op_s *new_op;
+	struct inode *inode;
+	struct dentry *res;
+	int ret = -EINVAL;
+
+	/*
+	 * in theory we could skip a lookup here (if the intent is to
+	 * create) in order to avoid a potentially failed lookup, but
+	 * leaving it in can skip a valid lookup and try to create a file
+	 * that already exists (e.g. the vfs already handles checking for
+	 * -EEXIST on O_EXCL opens, which is broken if we skip this lookup
+	 * in the create path)
+	 */
+	gossip_debug(GOSSIP_NAME_DEBUG, "%s called on %s\n",
+		     __func__, dentry->d_name.name);
+
+	if (dentry->d_name.len > (ORANGEFS_NAME_MAX - 1))
+		return ERR_PTR(-ENAMETOOLONG);
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_LOOKUP);
+	if (!new_op)
+		return ERR_PTR(-ENOMEM);
+
+	new_op->upcall.req.lookup.sym_follow = ORANGEFS_LOOKUP_LINK_NO_FOLLOW;
+
+	gossip_debug(GOSSIP_NAME_DEBUG, "%s:%s:%d using parent %pU\n",
+		     __FILE__,
+		     __func__,
+		     __LINE__,
+		     &parent->refn.khandle);
+	new_op->upcall.req.lookup.parent_refn = parent->refn;
+
+	strncpy(new_op->upcall.req.lookup.d_name, dentry->d_name.name,
+		ORANGEFS_NAME_MAX);
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "%s: doing lookup on %s under %pU,%d\n",
+		     __func__,
+		     new_op->upcall.req.lookup.d_name,
+		     &new_op->upcall.req.lookup.parent_refn.khandle,
+		     new_op->upcall.req.lookup.parent_refn.fs_id);
+
+	ret = service_operation(new_op, __func__, get_interruptible_flag(dir));
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "Lookup Got %pU, fsid %d (ret=%d)\n",
+		     &new_op->downcall.resp.lookup.refn.khandle,
+		     new_op->downcall.resp.lookup.refn.fs_id,
+		     ret);
+
+	if (ret < 0) {
+		if (ret == -ENOENT) {
+			/*
+			 * if no inode was found, add a negative dentry to
+			 * dcache anyway; if we don't, we don't hold expected
+			 * lookup semantics and we most noticeably break
+			 * during directory renames.
+			 *
+			 * however, if the operation failed or exited, do not
+			 * add the dentry (e.g. in the case that a touch is
+			 * issued on a file that already exists that was
+			 * interrupted during this lookup -- no need to add
+			 * another negative dentry for an existing file)
+			 */
+
+			gossip_debug(GOSSIP_NAME_DEBUG,
+				     "orangefs_lookup: Adding *negative* dentry "
+				     "%p for %s\n",
+				     dentry,
+				     dentry->d_name.name);
+
+			d_add(dentry, NULL);
+			res = NULL;
+			goto out;
+		}
+
+		/* must be a non-recoverable error */
+		res = ERR_PTR(ret);
+		goto out;
+	}
+
+	inode = orangefs_iget(dir->i_sb, &new_op->downcall.resp.lookup.refn);
+	if (IS_ERR(inode)) {
+		gossip_debug(GOSSIP_NAME_DEBUG,
+			"error %ld from iget\n", PTR_ERR(inode));
+		res = ERR_CAST(inode);
+		goto out;
+	}
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "%s:%s:%d "
+		     "Found good inode [%lu] with count [%d]\n",
+		     __FILE__,
+		     __func__,
+		     __LINE__,
+		     inode->i_ino,
+		     (int)atomic_read(&inode->i_count));
+
+	/* update dentry/inode pair into dcache */
+	res = d_splice_alias(inode, dentry);
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "Lookup success (inode ct = %d)\n",
+		     (int)atomic_read(&inode->i_count));
+out:
+	op_release(new_op);
+	return res;
+}
+
+/* return 0 on success; non-zero otherwise */
+static int orangefs_unlink(struct inode *dir, struct dentry *dentry)
+{
+	struct inode *inode = dentry->d_inode;
+	struct orangefs_inode_s *parent = ORANGEFS_I(dir);
+	struct orangefs_kernel_op_s *new_op;
+	int ret;
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "%s: called on %s\n"
+		     "  (inode %pU): Parent is %pU | fs_id %d\n",
+		     __func__,
+		     dentry->d_name.name,
+		     get_khandle_from_ino(inode),
+		     &parent->refn.khandle,
+		     parent->refn.fs_id);
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_REMOVE);
+	if (!new_op)
+		return -ENOMEM;
+
+	new_op->upcall.req.remove.parent_refn = parent->refn;
+	strncpy(new_op->upcall.req.remove.d_name, dentry->d_name.name,
+		ORANGEFS_NAME_MAX);
+
+	ret = service_operation(new_op, "orangefs_unlink",
+				get_interruptible_flag(inode));
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "%s: service_operation returned:%d:\n",
+		     __func__,
+		     ret);
+
+	op_release(new_op);
+
+	if (!ret) {
+		drop_nlink(inode);
+
+		SetMtimeFlag(parent);
+		dir->i_mtime = dir->i_ctime = current_fs_time(dir->i_sb);
+		mark_inode_dirty_sync(dir);
+	}
+	return ret;
+}
+
+static int orangefs_symlink(struct inode *dir,
+			 struct dentry *dentry,
+			 const char *symname)
+{
+	struct orangefs_inode_s *parent = ORANGEFS_I(dir);
+	struct orangefs_kernel_op_s *new_op;
+	struct inode *inode;
+	int mode = 755;
+	int ret;
+
+	gossip_debug(GOSSIP_NAME_DEBUG, "%s: called\n", __func__);
+
+	if (!symname)
+		return -EINVAL;
+
+	if (strlen(symname)+1 > ORANGEFS_NAME_MAX)
+		return -ENAMETOOLONG;
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_SYMLINK);
+	if (!new_op)
+		return -ENOMEM;
+
+	new_op->upcall.req.sym.parent_refn = parent->refn;
+
+	fill_default_sys_attrs(new_op->upcall.req.sym.attributes,
+			       ORANGEFS_TYPE_SYMLINK,
+			       mode);
+
+	strncpy(new_op->upcall.req.sym.entry_name,
+		dentry->d_name.name,
+		ORANGEFS_NAME_MAX);
+	strncpy(new_op->upcall.req.sym.target, symname, ORANGEFS_NAME_MAX);
+
+	ret = service_operation(new_op, __func__, get_interruptible_flag(dir));
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "Symlink Got ORANGEFS handle %pU on fsid %d (ret=%d)\n",
+		     &new_op->downcall.resp.sym.refn.khandle,
+		     new_op->downcall.resp.sym.refn.fs_id, ret);
+
+	if (ret < 0) {
+		gossip_debug(GOSSIP_NAME_DEBUG,
+			    "%s: failed with error code %d\n",
+			    __func__, ret);
+		goto out;
+	}
+
+	inode = orangefs_new_inode(dir->i_sb, dir, S_IFLNK | mode, 0,
+				&new_op->downcall.resp.sym.refn);
+	if (IS_ERR(inode)) {
+		gossip_err
+		    ("*** Failed to allocate orangefs symlink inode\n");
+		ret = PTR_ERR(inode);
+		goto out;
+	}
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "Assigned symlink inode new number of %pU\n",
+		     get_khandle_from_ino(inode));
+
+	d_instantiate(dentry, inode);
+	unlock_new_inode(inode);
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "Inode (Symlink) %pU -> %s\n",
+		     get_khandle_from_ino(inode),
+		     dentry->d_name.name);
+
+	SetMtimeFlag(parent);
+	dir->i_mtime = dir->i_ctime = current_fs_time(dir->i_sb);
+	mark_inode_dirty_sync(dir);
+	ret = 0;
+out:
+	op_release(new_op);
+	return ret;
+}
+
+static int orangefs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+	struct orangefs_inode_s *parent = ORANGEFS_I(dir);
+	struct orangefs_kernel_op_s *new_op;
+	struct inode *inode;
+	int ret;
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_MKDIR);
+	if (!new_op)
+		return -ENOMEM;
+
+	new_op->upcall.req.mkdir.parent_refn = parent->refn;
+
+	fill_default_sys_attrs(new_op->upcall.req.mkdir.attributes,
+			      ORANGEFS_TYPE_DIRECTORY, mode);
+
+	strncpy(new_op->upcall.req.mkdir.d_name,
+		dentry->d_name.name, ORANGEFS_NAME_MAX);
+
+	ret = service_operation(new_op, __func__, get_interruptible_flag(dir));
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "Mkdir Got ORANGEFS handle %pU on fsid %d\n",
+		     &new_op->downcall.resp.mkdir.refn.khandle,
+		     new_op->downcall.resp.mkdir.refn.fs_id);
+
+	if (ret < 0) {
+		gossip_debug(GOSSIP_NAME_DEBUG,
+			     "%s: failed with error code %d\n",
+			     __func__, ret);
+		goto out;
+	}
+
+	inode = orangefs_new_inode(dir->i_sb, dir, S_IFDIR | mode, 0,
+				&new_op->downcall.resp.mkdir.refn);
+	if (IS_ERR(inode)) {
+		gossip_err("*** Failed to allocate orangefs dir inode\n");
+		ret = PTR_ERR(inode);
+		goto out;
+	}
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "Assigned dir inode new number of %pU\n",
+		     get_khandle_from_ino(inode));
+
+	d_instantiate(dentry, inode);
+	unlock_new_inode(inode);
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "Inode (Directory) %pU -> %s\n",
+		     get_khandle_from_ino(inode),
+		     dentry->d_name.name);
+
+	/*
+	 * NOTE: we have no good way to keep nlink consistent for directories
+	 * across clients; keep constant at 1.
+	 */
+	SetMtimeFlag(parent);
+	dir->i_mtime = dir->i_ctime = current_fs_time(dir->i_sb);
+	mark_inode_dirty_sync(dir);
+out:
+	op_release(new_op);
+	return ret;
+}
+
+static int orangefs_rename(struct inode *old_dir,
+			struct dentry *old_dentry,
+			struct inode *new_dir,
+			struct dentry *new_dentry)
+{
+	struct orangefs_kernel_op_s *new_op;
+	int ret;
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "orangefs_rename: called (%s/%s => %s/%s) ct=%d\n",
+		     old_dentry->d_parent->d_name.name,
+		     old_dentry->d_name.name,
+		     new_dentry->d_parent->d_name.name,
+		     new_dentry->d_name.name,
+		     d_count(new_dentry));
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_RENAME);
+	if (!new_op)
+		return -EINVAL;
+
+	new_op->upcall.req.rename.old_parent_refn = ORANGEFS_I(old_dir)->refn;
+	new_op->upcall.req.rename.new_parent_refn = ORANGEFS_I(new_dir)->refn;
+
+	strncpy(new_op->upcall.req.rename.d_old_name,
+		old_dentry->d_name.name,
+		ORANGEFS_NAME_MAX);
+	strncpy(new_op->upcall.req.rename.d_new_name,
+		new_dentry->d_name.name,
+		ORANGEFS_NAME_MAX);
+
+	ret = service_operation(new_op,
+				"orangefs_rename",
+				get_interruptible_flag(old_dentry->d_inode));
+
+	gossip_debug(GOSSIP_NAME_DEBUG,
+		     "orangefs_rename: got downcall status %d\n",
+		     ret);
+
+	if (new_dentry->d_inode)
+		new_dentry->d_inode->i_ctime = CURRENT_TIME;
+
+	op_release(new_op);
+	return ret;
+}
+
+/* ORANGEFS implementation of VFS inode operations for directories */
+struct inode_operations orangefs_dir_inode_operations = {
+	.lookup = orangefs_lookup,
+	.get_acl = orangefs_get_acl,
+	.set_acl = orangefs_set_acl,
+	.create = orangefs_create,
+	.unlink = orangefs_unlink,
+	.symlink = orangefs_symlink,
+	.mkdir = orangefs_mkdir,
+	.rmdir = orangefs_unlink,
+	.rename = orangefs_rename,
+	.setattr = orangefs_setattr,
+	.getattr = orangefs_getattr,
+	.setxattr = generic_setxattr,
+	.getxattr = generic_getxattr,
+	.removexattr = generic_removexattr,
+	.listxattr = orangefs_listxattr,
+	.permission = orangefs_permission,
+};
diff --git a/fs/orangefs/orangefs-bufmap.c b/fs/orangefs/orangefs-bufmap.c
new file mode 100644
index 000000000000..75375e90a63f
--- /dev/null
+++ b/fs/orangefs/orangefs-bufmap.c
@@ -0,0 +1,556 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-bufmap.h"
+
+struct slot_map {
+	int c;
+	wait_queue_head_t q;
+	int count;
+	unsigned long *map;
+};
+
+static struct slot_map rw_map = {
+	.c = -1,
+	.q = __WAIT_QUEUE_HEAD_INITIALIZER(rw_map.q)
+};
+static struct slot_map readdir_map = {
+	.c = -1,
+	.q = __WAIT_QUEUE_HEAD_INITIALIZER(readdir_map.q)
+};
+
+
+static void install(struct slot_map *m, int count, unsigned long *map)
+{
+	spin_lock(&m->q.lock);
+	m->c = m->count = count;
+	m->map = map;
+	wake_up_all_locked(&m->q);
+	spin_unlock(&m->q.lock);
+}
+
+static void mark_killed(struct slot_map *m)
+{
+	spin_lock(&m->q.lock);
+	m->c -= m->count + 1;
+	spin_unlock(&m->q.lock);
+}
+
+static void run_down(struct slot_map *m)
+{
+	DEFINE_WAIT(wait);
+	spin_lock(&m->q.lock);
+	if (m->c != -1) {
+		for (;;) {
+			if (likely(list_empty(&wait.task_list)))
+				__add_wait_queue_tail(&m->q, &wait);
+			set_current_state(TASK_UNINTERRUPTIBLE);
+
+			if (m->c == -1)
+				break;
+
+			spin_unlock(&m->q.lock);
+			schedule();
+			spin_lock(&m->q.lock);
+		}
+		__remove_wait_queue(&m->q, &wait);
+		__set_current_state(TASK_RUNNING);
+	}
+	m->map = NULL;
+	spin_unlock(&m->q.lock);
+}
+
+static void put(struct slot_map *m, int slot)
+{
+	int v;
+	spin_lock(&m->q.lock);
+	__clear_bit(slot, m->map);
+	v = ++m->c;
+	if (unlikely(v == 1))	/* no free slots -> one free slot */
+		wake_up_locked(&m->q);
+	else if (unlikely(v == -1))	/* finished dying */
+		wake_up_all_locked(&m->q);
+	spin_unlock(&m->q.lock);
+}
+
+static int wait_for_free(struct slot_map *m)
+{
+	long left = slot_timeout_secs * HZ;
+	DEFINE_WAIT(wait);
+
+	do {
+		long n = left, t;
+		if (likely(list_empty(&wait.task_list)))
+			__add_wait_queue_tail_exclusive(&m->q, &wait);
+		set_current_state(TASK_INTERRUPTIBLE);
+
+		if (m->c > 0)
+			break;
+
+		if (m->c < 0) {
+			/* we are waiting for map to be installed */
+			/* it would better be there soon, or we go away */
+			if (n > ORANGEFS_BUFMAP_WAIT_TIMEOUT_SECS * HZ)
+				n = ORANGEFS_BUFMAP_WAIT_TIMEOUT_SECS * HZ;
+		}
+		spin_unlock(&m->q.lock);
+		t = schedule_timeout(n);
+		spin_lock(&m->q.lock);
+		if (unlikely(!t) && n != left && m->c < 0)
+			left = t;
+		else
+			left = t + (left - n);
+		if (unlikely(signal_pending(current)))
+			left = -EINTR;
+	} while (left > 0);
+
+	if (!list_empty(&wait.task_list))
+		list_del(&wait.task_list);
+	else if (left <= 0 && waitqueue_active(&m->q))
+		__wake_up_locked_key(&m->q, TASK_INTERRUPTIBLE, NULL);
+	__set_current_state(TASK_RUNNING);
+
+	if (likely(left > 0))
+		return 0;
+
+	return left < 0 ? -EINTR : -ETIMEDOUT;
+}
+
+static int get(struct slot_map *m)
+{
+	int res = 0;
+	spin_lock(&m->q.lock);
+	if (unlikely(m->c <= 0))
+		res = wait_for_free(m);
+	if (likely(!res)) {
+		m->c--;
+		res = find_first_zero_bit(m->map, m->count);
+		__set_bit(res, m->map);
+	}
+	spin_unlock(&m->q.lock);
+	return res;
+}
+
+/* used to describe mapped buffers */
+struct orangefs_bufmap_desc {
+	void *uaddr;			/* user space address pointer */
+	struct page **page_array;	/* array of mapped pages */
+	int array_count;		/* size of above arrays */
+	struct list_head list_link;
+};
+
+static struct orangefs_bufmap {
+	int desc_size;
+	int desc_shift;
+	int desc_count;
+	int total_size;
+	int page_count;
+
+	struct page **page_array;
+	struct orangefs_bufmap_desc *desc_array;
+
+	/* array to track usage of buffer descriptors */
+	unsigned long *buffer_index_array;
+
+	/* array to track usage of buffer descriptors for readdir */
+#define N DIV_ROUND_UP(ORANGEFS_READDIR_DEFAULT_DESC_COUNT, BITS_PER_LONG)
+	unsigned long readdir_index_array[N];
+#undef N
+} *__orangefs_bufmap;
+
+static DEFINE_SPINLOCK(orangefs_bufmap_lock);
+
+static void
+orangefs_bufmap_unmap(struct orangefs_bufmap *bufmap)
+{
+	int i;
+
+	for (i = 0; i < bufmap->page_count; i++)
+		put_page(bufmap->page_array[i]);
+}
+
+static void
+orangefs_bufmap_free(struct orangefs_bufmap *bufmap)
+{
+	kfree(bufmap->page_array);
+	kfree(bufmap->desc_array);
+	kfree(bufmap->buffer_index_array);
+	kfree(bufmap);
+}
+
+/*
+ * XXX: Can the size and shift change while the caller gives up the 
+ * XXX: lock between calling this and doing something useful?
+ */
+
+int orangefs_bufmap_size_query(void)
+{
+	struct orangefs_bufmap *bufmap;
+	int size = 0;
+	spin_lock(&orangefs_bufmap_lock);
+	bufmap = __orangefs_bufmap;
+	if (bufmap)
+		size = bufmap->desc_size;
+	spin_unlock(&orangefs_bufmap_lock);
+	return size;
+}
+
+int orangefs_bufmap_shift_query(void)
+{
+	struct orangefs_bufmap *bufmap;
+	int shift = 0;
+	spin_lock(&orangefs_bufmap_lock);
+	bufmap = __orangefs_bufmap;
+	if (bufmap)
+		shift = bufmap->desc_shift;
+	spin_unlock(&orangefs_bufmap_lock);
+	return shift;
+}
+
+static DECLARE_WAIT_QUEUE_HEAD(bufmap_waitq);
+static DECLARE_WAIT_QUEUE_HEAD(readdir_waitq);
+
+/*
+ * orangefs_get_bufmap_init
+ *
+ * If bufmap_init is 1, then the shared memory system, including the
+ * buffer_index_array, is available.  Otherwise, it is not.
+ *
+ * returns the value of bufmap_init
+ */
+int orangefs_get_bufmap_init(void)
+{
+	return __orangefs_bufmap ? 1 : 0;
+}
+
+
+static struct orangefs_bufmap *
+orangefs_bufmap_alloc(struct ORANGEFS_dev_map_desc *user_desc)
+{
+	struct orangefs_bufmap *bufmap;
+
+	bufmap = kzalloc(sizeof(*bufmap), GFP_KERNEL);
+	if (!bufmap)
+		goto out;
+
+	bufmap->total_size = user_desc->total_size;
+	bufmap->desc_count = user_desc->count;
+	bufmap->desc_size = user_desc->size;
+	bufmap->desc_shift = ilog2(bufmap->desc_size);
+
+	bufmap->buffer_index_array =
+		kzalloc(DIV_ROUND_UP(bufmap->desc_count, BITS_PER_LONG), GFP_KERNEL);
+	if (!bufmap->buffer_index_array) {
+		gossip_err("orangefs: could not allocate %d buffer indices\n",
+				bufmap->desc_count);
+		goto out_free_bufmap;
+	}
+
+	bufmap->desc_array =
+		kcalloc(bufmap->desc_count, sizeof(struct orangefs_bufmap_desc),
+			GFP_KERNEL);
+	if (!bufmap->desc_array) {
+		gossip_err("orangefs: could not allocate %d descriptors\n",
+				bufmap->desc_count);
+		goto out_free_index_array;
+	}
+
+	bufmap->page_count = bufmap->total_size / PAGE_SIZE;
+
+	/* allocate storage to track our page mappings */
+	bufmap->page_array =
+		kcalloc(bufmap->page_count, sizeof(struct page *), GFP_KERNEL);
+	if (!bufmap->page_array)
+		goto out_free_desc_array;
+
+	return bufmap;
+
+out_free_desc_array:
+	kfree(bufmap->desc_array);
+out_free_index_array:
+	kfree(bufmap->buffer_index_array);
+out_free_bufmap:
+	kfree(bufmap);
+out:
+	return NULL;
+}
+
+static int
+orangefs_bufmap_map(struct orangefs_bufmap *bufmap,
+		struct ORANGEFS_dev_map_desc *user_desc)
+{
+	int pages_per_desc = bufmap->desc_size / PAGE_SIZE;
+	int offset = 0, ret, i;
+
+	/* map the pages */
+	ret = get_user_pages_fast((unsigned long)user_desc->ptr,
+			     bufmap->page_count, 1, bufmap->page_array);
+
+	if (ret < 0)
+		return ret;
+
+	if (ret != bufmap->page_count) {
+		gossip_err("orangefs error: asked for %d pages, only got %d.\n",
+				bufmap->page_count, ret);
+
+		for (i = 0; i < ret; i++) {
+			SetPageError(bufmap->page_array[i]);
+			put_page(bufmap->page_array[i]);
+		}
+		return -ENOMEM;
+	}
+
+	/*
+	 * ideally we want to get kernel space pointers for each page, but
+	 * we can't kmap that many pages at once if highmem is being used.
+	 * so instead, we just kmap/kunmap the page address each time the
+	 * kaddr is needed.
+	 */
+	for (i = 0; i < bufmap->page_count; i++)
+		flush_dcache_page(bufmap->page_array[i]);
+
+	/* build a list of available descriptors */
+	for (offset = 0, i = 0; i < bufmap->desc_count; i++) {
+		bufmap->desc_array[i].page_array = &bufmap->page_array[offset];
+		bufmap->desc_array[i].array_count = pages_per_desc;
+		bufmap->desc_array[i].uaddr =
+		    (user_desc->ptr + (i * pages_per_desc * PAGE_SIZE));
+		offset += pages_per_desc;
+	}
+
+	return 0;
+}
+
+/*
+ * orangefs_bufmap_initialize()
+ *
+ * initializes the mapped buffer interface
+ *
+ * returns 0 on success, -errno on failure
+ */
+int orangefs_bufmap_initialize(struct ORANGEFS_dev_map_desc *user_desc)
+{
+	struct orangefs_bufmap *bufmap;
+	int ret = -EINVAL;
+
+	gossip_debug(GOSSIP_BUFMAP_DEBUG,
+		     "orangefs_bufmap_initialize: called (ptr ("
+		     "%p) sz (%d) cnt(%d).\n",
+		     user_desc->ptr,
+		     user_desc->size,
+		     user_desc->count);
+
+	/*
+	 * sanity check alignment and size of buffer that caller wants to
+	 * work with
+	 */
+	if (PAGE_ALIGN((unsigned long)user_desc->ptr) !=
+	    (unsigned long)user_desc->ptr) {
+		gossip_err("orangefs error: memory alignment (front). %p\n",
+			   user_desc->ptr);
+		goto out;
+	}
+
+	if (PAGE_ALIGN(((unsigned long)user_desc->ptr + user_desc->total_size))
+	    != (unsigned long)(user_desc->ptr + user_desc->total_size)) {
+		gossip_err("orangefs error: memory alignment (back).(%p + %d)\n",
+			   user_desc->ptr,
+			   user_desc->total_size);
+		goto out;
+	}
+
+	if (user_desc->total_size != (user_desc->size * user_desc->count)) {
+		gossip_err("orangefs error: user provided an oddly sized buffer: (%d, %d, %d)\n",
+			   user_desc->total_size,
+			   user_desc->size,
+			   user_desc->count);
+		goto out;
+	}
+
+	if ((user_desc->size % PAGE_SIZE) != 0) {
+		gossip_err("orangefs error: bufmap size not page size divisible (%d).\n",
+			   user_desc->size);
+		goto out;
+	}
+
+	ret = -ENOMEM;
+	bufmap = orangefs_bufmap_alloc(user_desc);
+	if (!bufmap)
+		goto out;
+
+	ret = orangefs_bufmap_map(bufmap, user_desc);
+	if (ret)
+		goto out_free_bufmap;
+
+
+	spin_lock(&orangefs_bufmap_lock);
+	if (__orangefs_bufmap) {
+		spin_unlock(&orangefs_bufmap_lock);
+		gossip_err("orangefs: error: bufmap already initialized.\n");
+		ret = -EINVAL;
+		goto out_unmap_bufmap;
+	}
+	__orangefs_bufmap = bufmap;
+	install(&rw_map,
+		bufmap->desc_count,
+		bufmap->buffer_index_array);
+	install(&readdir_map,
+		ORANGEFS_READDIR_DEFAULT_DESC_COUNT,
+		bufmap->readdir_index_array);
+	spin_unlock(&orangefs_bufmap_lock);
+
+	gossip_debug(GOSSIP_BUFMAP_DEBUG,
+		     "orangefs_bufmap_initialize: exiting normally\n");
+	return 0;
+
+out_unmap_bufmap:
+	orangefs_bufmap_unmap(bufmap);
+out_free_bufmap:
+	orangefs_bufmap_free(bufmap);
+out:
+	return ret;
+}
+
+/*
+ * orangefs_bufmap_finalize()
+ *
+ * shuts down the mapped buffer interface and releases any resources
+ * associated with it
+ *
+ * no return value
+ */
+void orangefs_bufmap_finalize(void)
+{
+	struct orangefs_bufmap *bufmap = __orangefs_bufmap;
+	if (!bufmap)
+		return;
+	gossip_debug(GOSSIP_BUFMAP_DEBUG, "orangefs_bufmap_finalize: called\n");
+	mark_killed(&rw_map);
+	mark_killed(&readdir_map);
+	gossip_debug(GOSSIP_BUFMAP_DEBUG,
+		     "orangefs_bufmap_finalize: exiting normally\n");
+}
+
+void orangefs_bufmap_run_down(void)
+{
+	struct orangefs_bufmap *bufmap = __orangefs_bufmap;
+	if (!bufmap)
+		return;
+	run_down(&rw_map);
+	run_down(&readdir_map);
+	spin_lock(&orangefs_bufmap_lock);
+	__orangefs_bufmap = NULL;
+	spin_unlock(&orangefs_bufmap_lock);
+	orangefs_bufmap_unmap(bufmap);
+	orangefs_bufmap_free(bufmap);
+}
+
+/*
+ * orangefs_bufmap_get()
+ *
+ * gets a free mapped buffer descriptor, will sleep until one becomes
+ * available if necessary
+ *
+ * returns slot on success, -errno on failure
+ */
+int orangefs_bufmap_get(void)
+{
+	return get(&rw_map);
+}
+
+/*
+ * orangefs_bufmap_put()
+ *
+ * returns a mapped buffer descriptor to the collection
+ *
+ * no return value
+ */
+void orangefs_bufmap_put(int buffer_index)
+{
+	put(&rw_map, buffer_index);
+}
+
+/*
+ * orangefs_readdir_index_get()
+ *
+ * gets a free descriptor, will sleep until one becomes
+ * available if necessary.
+ * Although the readdir buffers are not mapped into kernel space
+ * we could do that at a later point of time. Regardless, these
+ * indices are used by the client-core.
+ *
+ * returns slot on success, -errno on failure
+ */
+int orangefs_readdir_index_get(void)
+{
+	return get(&readdir_map);
+}
+
+void orangefs_readdir_index_put(int buffer_index)
+{
+	put(&readdir_map, buffer_index);
+}
+
+/*
+ * we've been handed an iovec, we need to copy it to 
+ * the shared memory descriptor at "buffer_index".
+ */
+int orangefs_bufmap_copy_from_iovec(struct iov_iter *iter,
+				int buffer_index,
+				size_t size)
+{
+	struct orangefs_bufmap_desc *to;
+	int i;
+
+	gossip_debug(GOSSIP_BUFMAP_DEBUG,
+		     "%s: buffer_index:%d: size:%zu:\n",
+		     __func__, buffer_index, size);
+
+	to = &__orangefs_bufmap->desc_array[buffer_index];
+	for (i = 0; size; i++) {
+		struct page *page = to->page_array[i];
+		size_t n = size;
+		if (n > PAGE_SIZE)
+			n = PAGE_SIZE;
+		n = copy_page_from_iter(page, 0, n, iter);
+		if (!n)
+			return -EFAULT;
+		size -= n;
+	}
+	return 0;
+
+}
+
+/*
+ * we've been handed an iovec, we need to fill it from
+ * the shared memory descriptor at "buffer_index".
+ */
+int orangefs_bufmap_copy_to_iovec(struct iov_iter *iter,
+				    int buffer_index,
+				    size_t size)
+{
+	struct orangefs_bufmap_desc *from;
+	int i;
+
+	from = &__orangefs_bufmap->desc_array[buffer_index];
+	gossip_debug(GOSSIP_BUFMAP_DEBUG,
+		     "%s: buffer_index:%d: size:%zu:\n",
+		     __func__, buffer_index, size);
+
+
+	for (i = 0; size; i++) {
+		struct page *page = from->page_array[i];
+		size_t n = size;
+		if (n > PAGE_SIZE)
+			n = PAGE_SIZE;
+		n = copy_page_to_iter(page, 0, n, iter);
+		if (!n)
+			return -EFAULT;
+		size -= n;
+	}
+	return 0;
+}
diff --git a/fs/orangefs/orangefs-bufmap.h b/fs/orangefs/orangefs-bufmap.h
new file mode 100644
index 000000000000..71f64f4057b5
--- /dev/null
+++ b/fs/orangefs/orangefs-bufmap.h
@@ -0,0 +1,36 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+#ifndef __ORANGEFS_BUFMAP_H
+#define __ORANGEFS_BUFMAP_H
+
+int orangefs_bufmap_size_query(void);
+
+int orangefs_bufmap_shift_query(void);
+
+int orangefs_bufmap_initialize(struct ORANGEFS_dev_map_desc *user_desc);
+
+void orangefs_bufmap_finalize(void);
+
+void orangefs_bufmap_run_down(void);
+
+int orangefs_bufmap_get(void);
+
+void orangefs_bufmap_put(int buffer_index);
+
+int orangefs_readdir_index_get(void);
+
+void orangefs_readdir_index_put(int buffer_index);
+
+int orangefs_bufmap_copy_from_iovec(struct iov_iter *iter,
+				int buffer_index,
+				size_t size);
+
+int orangefs_bufmap_copy_to_iovec(struct iov_iter *iter,
+			      int buffer_index,
+			      size_t size);
+
+#endif /* __ORANGEFS_BUFMAP_H */
diff --git a/fs/orangefs/orangefs-cache.c b/fs/orangefs/orangefs-cache.c
new file mode 100644
index 000000000000..900a2e38e11b
--- /dev/null
+++ b/fs/orangefs/orangefs-cache.c
@@ -0,0 +1,161 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+
+/* tags assigned to kernel upcall operations */
+static __u64 next_tag_value;
+static DEFINE_SPINLOCK(next_tag_value_lock);
+
+/* the orangefs memory caches */
+
+/* a cache for orangefs upcall/downcall operations */
+static struct kmem_cache *op_cache;
+
+int op_cache_initialize(void)
+{
+	op_cache = kmem_cache_create("orangefs_op_cache",
+				     sizeof(struct orangefs_kernel_op_s),
+				     0,
+				     ORANGEFS_CACHE_CREATE_FLAGS,
+				     NULL);
+
+	if (!op_cache) {
+		gossip_err("Cannot create orangefs_op_cache\n");
+		return -ENOMEM;
+	}
+
+	/* initialize our atomic tag counter */
+	spin_lock(&next_tag_value_lock);
+	next_tag_value = 100;
+	spin_unlock(&next_tag_value_lock);
+	return 0;
+}
+
+int op_cache_finalize(void)
+{
+	kmem_cache_destroy(op_cache);
+	return 0;
+}
+
+char *get_opname_string(struct orangefs_kernel_op_s *new_op)
+{
+	if (new_op) {
+		__s32 type = new_op->upcall.type;
+
+		if (type == ORANGEFS_VFS_OP_FILE_IO)
+			return "OP_FILE_IO";
+		else if (type == ORANGEFS_VFS_OP_LOOKUP)
+			return "OP_LOOKUP";
+		else if (type == ORANGEFS_VFS_OP_CREATE)
+			return "OP_CREATE";
+		else if (type == ORANGEFS_VFS_OP_GETATTR)
+			return "OP_GETATTR";
+		else if (type == ORANGEFS_VFS_OP_REMOVE)
+			return "OP_REMOVE";
+		else if (type == ORANGEFS_VFS_OP_MKDIR)
+			return "OP_MKDIR";
+		else if (type == ORANGEFS_VFS_OP_READDIR)
+			return "OP_READDIR";
+		else if (type == ORANGEFS_VFS_OP_READDIRPLUS)
+			return "OP_READDIRPLUS";
+		else if (type == ORANGEFS_VFS_OP_SETATTR)
+			return "OP_SETATTR";
+		else if (type == ORANGEFS_VFS_OP_SYMLINK)
+			return "OP_SYMLINK";
+		else if (type == ORANGEFS_VFS_OP_RENAME)
+			return "OP_RENAME";
+		else if (type == ORANGEFS_VFS_OP_STATFS)
+			return "OP_STATFS";
+		else if (type == ORANGEFS_VFS_OP_TRUNCATE)
+			return "OP_TRUNCATE";
+		else if (type == ORANGEFS_VFS_OP_MMAP_RA_FLUSH)
+			return "OP_MMAP_RA_FLUSH";
+		else if (type == ORANGEFS_VFS_OP_FS_MOUNT)
+			return "OP_FS_MOUNT";
+		else if (type == ORANGEFS_VFS_OP_FS_UMOUNT)
+			return "OP_FS_UMOUNT";
+		else if (type == ORANGEFS_VFS_OP_GETXATTR)
+			return "OP_GETXATTR";
+		else if (type == ORANGEFS_VFS_OP_SETXATTR)
+			return "OP_SETXATTR";
+		else if (type == ORANGEFS_VFS_OP_LISTXATTR)
+			return "OP_LISTXATTR";
+		else if (type == ORANGEFS_VFS_OP_REMOVEXATTR)
+			return "OP_REMOVEXATTR";
+		else if (type == ORANGEFS_VFS_OP_PARAM)
+			return "OP_PARAM";
+		else if (type == ORANGEFS_VFS_OP_PERF_COUNT)
+			return "OP_PERF_COUNT";
+		else if (type == ORANGEFS_VFS_OP_CANCEL)
+			return "OP_CANCEL";
+		else if (type == ORANGEFS_VFS_OP_FSYNC)
+			return "OP_FSYNC";
+		else if (type == ORANGEFS_VFS_OP_FSKEY)
+			return "OP_FSKEY";
+	}
+	return "OP_UNKNOWN?";
+}
+
+void orangefs_new_tag(struct orangefs_kernel_op_s *op)
+{
+	spin_lock(&next_tag_value_lock);
+	op->tag = next_tag_value++;
+	if (next_tag_value == 0)
+		next_tag_value = 100;
+	spin_unlock(&next_tag_value_lock);
+}
+
+struct orangefs_kernel_op_s *op_alloc(__s32 type)
+{
+	struct orangefs_kernel_op_s *new_op = NULL;
+
+	new_op = kmem_cache_zalloc(op_cache, GFP_KERNEL);
+	if (new_op) {
+		INIT_LIST_HEAD(&new_op->list);
+		spin_lock_init(&new_op->lock);
+		init_completion(&new_op->waitq);
+
+		new_op->upcall.type = ORANGEFS_VFS_OP_INVALID;
+		new_op->downcall.type = ORANGEFS_VFS_OP_INVALID;
+		new_op->downcall.status = -1;
+
+		new_op->op_state = OP_VFS_STATE_UNKNOWN;
+
+		/* initialize the op specific tag and upcall credentials */
+		orangefs_new_tag(new_op);
+		new_op->upcall.type = type;
+		new_op->attempts = 0;
+		gossip_debug(GOSSIP_CACHE_DEBUG,
+			     "Alloced OP (%p: %llu %s)\n",
+			     new_op,
+			     llu(new_op->tag),
+			     get_opname_string(new_op));
+
+		new_op->upcall.uid = from_kuid(current_user_ns(),
+					       current_fsuid());
+
+		new_op->upcall.gid = from_kgid(current_user_ns(),
+					       current_fsgid());
+	} else {
+		gossip_err("op_alloc: kmem_cache_zalloc failed!\n");
+	}
+	return new_op;
+}
+
+void op_release(struct orangefs_kernel_op_s *orangefs_op)
+{
+	if (orangefs_op) {
+		gossip_debug(GOSSIP_CACHE_DEBUG,
+			     "Releasing OP (%p: %llu)\n",
+			     orangefs_op,
+			     llu(orangefs_op->tag));
+		kmem_cache_free(op_cache, orangefs_op);
+	} else {
+		gossip_err("NULL pointer in op_release\n");
+	}
+}
diff --git a/fs/orangefs/orangefs-debug.h b/fs/orangefs/orangefs-debug.h
new file mode 100644
index 000000000000..387db17cde2b
--- /dev/null
+++ b/fs/orangefs/orangefs-debug.h
@@ -0,0 +1,92 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+/* This file just defines debugging masks to be used with the gossip
+ * logging utility.  All debugging masks for ORANGEFS are kept here to make
+ * sure we don't have collisions.
+ */
+
+#ifndef __ORANGEFS_DEBUG_H
+#define __ORANGEFS_DEBUG_H
+
+#ifdef __KERNEL__
+#include <linux/types.h>
+#else
+#include <stdint.h>
+#endif
+
+#define	GOSSIP_NO_DEBUG			(__u64)0
+
+#define GOSSIP_SUPER_DEBUG		((__u64)1 << 0)
+#define GOSSIP_INODE_DEBUG		((__u64)1 << 1)
+#define GOSSIP_FILE_DEBUG		((__u64)1 << 2)
+#define GOSSIP_DIR_DEBUG		((__u64)1 << 3)
+#define GOSSIP_UTILS_DEBUG		((__u64)1 << 4)
+#define GOSSIP_WAIT_DEBUG		((__u64)1 << 5)
+#define GOSSIP_ACL_DEBUG		((__u64)1 << 6)
+#define GOSSIP_DCACHE_DEBUG		((__u64)1 << 7)
+#define GOSSIP_DEV_DEBUG		((__u64)1 << 8)
+#define GOSSIP_NAME_DEBUG		((__u64)1 << 9)
+#define GOSSIP_BUFMAP_DEBUG		((__u64)1 << 10)
+#define GOSSIP_CACHE_DEBUG		((__u64)1 << 11)
+#define GOSSIP_DEBUGFS_DEBUG		((__u64)1 << 12)
+#define GOSSIP_XATTR_DEBUG		((__u64)1 << 13)
+#define GOSSIP_INIT_DEBUG		((__u64)1 << 14)
+#define GOSSIP_SYSFS_DEBUG		((__u64)1 << 15)
+
+#define GOSSIP_MAX_NR                 16
+#define GOSSIP_MAX_DEBUG              (((__u64)1 << GOSSIP_MAX_NR) - 1)
+
+/*function prototypes*/
+__u64 ORANGEFS_kmod_eventlog_to_mask(const char *event_logging);
+__u64 ORANGEFS_debug_eventlog_to_mask(const char *event_logging);
+char *ORANGEFS_debug_mask_to_eventlog(__u64 mask);
+char *ORANGEFS_kmod_mask_to_eventlog(__u64 mask);
+
+/* a private internal type */
+struct __keyword_mask_s {
+	const char *keyword;
+	__u64 mask_val;
+};
+
+/*
+ * Map all kmod keywords to kmod debug masks here. Keep this
+ * structure "packed":
+ *
+ *   "all" is always last...
+ *
+ *   keyword     mask_val     index
+ *     foo          1           0
+ *     bar          2           1
+ *     baz          4           2
+ *     qux          8           3
+ *      .           .           .
+ */
+static struct __keyword_mask_s s_kmod_keyword_mask_map[] = {
+	{"super", GOSSIP_SUPER_DEBUG},
+	{"inode", GOSSIP_INODE_DEBUG},
+	{"file", GOSSIP_FILE_DEBUG},
+	{"dir", GOSSIP_DIR_DEBUG},
+	{"utils", GOSSIP_UTILS_DEBUG},
+	{"wait", GOSSIP_WAIT_DEBUG},
+	{"acl", GOSSIP_ACL_DEBUG},
+	{"dcache", GOSSIP_DCACHE_DEBUG},
+	{"dev", GOSSIP_DEV_DEBUG},
+	{"name", GOSSIP_NAME_DEBUG},
+	{"bufmap", GOSSIP_BUFMAP_DEBUG},
+	{"cache", GOSSIP_CACHE_DEBUG},
+	{"debugfs", GOSSIP_DEBUGFS_DEBUG},
+	{"xattr", GOSSIP_XATTR_DEBUG},
+	{"init", GOSSIP_INIT_DEBUG},
+	{"sysfs", GOSSIP_SYSFS_DEBUG},
+	{"none", GOSSIP_NO_DEBUG},
+	{"all", GOSSIP_MAX_DEBUG}
+};
+
+static const int num_kmod_keyword_mask_map = (int)
+	(sizeof(s_kmod_keyword_mask_map) / sizeof(struct __keyword_mask_s));
+
+#endif /* __ORANGEFS_DEBUG_H */
diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c
new file mode 100644
index 000000000000..1714a737d556
--- /dev/null
+++ b/fs/orangefs/orangefs-debugfs.c
@@ -0,0 +1,454 @@
+/*
+ * What:		/sys/kernel/debug/orangefs/debug-help
+ * Date:		June 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ * 			List of client and kernel debug keywords.
+ *
+ *
+ * What:		/sys/kernel/debug/orangefs/client-debug
+ * Date:		June 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ * 			Debug setting for "the client", the userspace
+ * 			helper for the kernel module.
+ *
+ *
+ * What:		/sys/kernel/debug/orangefs/kernel-debug
+ * Date:		June 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ * 			Debug setting for the orangefs kernel module.
+ *
+ * 			Any of the keywords, or comma-separated lists
+ * 			of keywords, from debug-help can be catted to
+ * 			client-debug or kernel-debug.
+ *
+ * 			"none", "all" and "verbose" are special keywords
+ * 			for client-debug. Setting client-debug to "all"
+ * 			is kind of like trying to drink water from a
+ * 			fire hose, "verbose" triggers most of the same
+ * 			output except for the constant flow of output
+ * 			from the main wait loop.
+ *
+ * 			"none" and "all" are similar settings for kernel-debug
+ * 			no need for a "verbose".
+ */
+#include <linux/debugfs.h>
+#include <linux/slab.h>
+
+#include <linux/uaccess.h>
+
+#include "orangefs-debugfs.h"
+#include "protocol.h"
+#include "orangefs-kernel.h"
+
+static int orangefs_debug_disabled = 1;
+
+static int orangefs_debug_help_open(struct inode *, struct file *);
+
+const struct file_operations debug_help_fops = {
+	.open           = orangefs_debug_help_open,
+	.read           = seq_read,
+	.release        = seq_release,
+	.llseek         = seq_lseek,
+};
+
+static void *help_start(struct seq_file *, loff_t *);
+static void *help_next(struct seq_file *, void *, loff_t *);
+static void help_stop(struct seq_file *, void *);
+static int help_show(struct seq_file *, void *);
+
+static const struct seq_operations help_debug_ops = {
+	.start	= help_start,
+	.next	= help_next,
+	.stop	= help_stop,
+	.show	= help_show,
+};
+
+/*
+ * Used to protect data in ORANGEFS_KMOD_DEBUG_FILE and
+ * ORANGEFS_KMOD_DEBUG_FILE.
+ */
+static DEFINE_MUTEX(orangefs_debug_lock);
+
+int orangefs_debug_open(struct inode *, struct file *);
+
+static ssize_t orangefs_debug_read(struct file *,
+				 char __user *,
+				 size_t,
+				 loff_t *);
+
+static ssize_t orangefs_debug_write(struct file *,
+				  const char __user *,
+				  size_t,
+				  loff_t *);
+
+static const struct file_operations kernel_debug_fops = {
+	.open           = orangefs_debug_open,
+	.read           = orangefs_debug_read,
+	.write		= orangefs_debug_write,
+	.llseek         = generic_file_llseek,
+};
+
+/*
+ * initialize kmod debug operations, create orangefs debugfs dir and
+ * ORANGEFS_KMOD_DEBUG_HELP_FILE.
+ */
+int orangefs_debugfs_init(void)
+{
+
+	int rc = -ENOMEM;
+
+	debug_dir = debugfs_create_dir("orangefs", NULL);
+	if (!debug_dir) {
+		pr_info("%s: debugfs_create_dir failed.\n", __func__);
+		goto out;
+	}
+
+	help_file_dentry = debugfs_create_file(ORANGEFS_KMOD_DEBUG_HELP_FILE,
+				  0444,
+				  debug_dir,
+				  debug_help_string,
+				  &debug_help_fops);
+	if (!help_file_dentry) {
+		pr_info("%s: debugfs_create_file failed.\n", __func__);
+		goto out;
+	}
+
+	orangefs_debug_disabled = 0;
+	rc = 0;
+
+out:
+
+	return rc;
+}
+
+void orangefs_debugfs_cleanup(void)
+{
+	debugfs_remove_recursive(debug_dir);
+}
+
+/* open ORANGEFS_KMOD_DEBUG_HELP_FILE */
+static int orangefs_debug_help_open(struct inode *inode, struct file *file)
+{
+	int rc = -ENODEV;
+	int ret;
+
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG,
+		     "orangefs_debug_help_open: start\n");
+
+	if (orangefs_debug_disabled)
+		goto out;
+
+	ret = seq_open(file, &help_debug_ops);
+	if (ret)
+		goto out;
+
+	((struct seq_file *)(file->private_data))->private = inode->i_private;
+
+	rc = 0;
+
+out:
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG,
+		     "orangefs_debug_help_open: rc:%d:\n",
+		     rc);
+	return rc;
+}
+
+/*
+ * I think start always gets called again after stop. Start
+ * needs to return NULL when it is done. The whole "payload"
+ * in this case is a single (long) string, so by the second
+ * time we get to start (pos = 1), we're done.
+ */
+static void *help_start(struct seq_file *m, loff_t *pos)
+{
+	void *payload = NULL;
+
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "help_start: start\n");
+
+	if (*pos == 0)
+		payload = m->private;
+
+	return payload;
+}
+
+static void *help_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "help_next: start\n");
+
+	return NULL;
+}
+
+static void help_stop(struct seq_file *m, void *p)
+{
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "help_stop: start\n");
+}
+
+static int help_show(struct seq_file *m, void *v)
+{
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "help_show: start\n");
+
+	seq_puts(m, v);
+
+	return 0;
+}
+
+/*
+ * initialize the kernel-debug file.
+ */
+int orangefs_kernel_debug_init(void)
+{
+	int rc = -ENOMEM;
+	struct dentry *ret;
+	char *k_buffer = NULL;
+
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "%s: start\n", __func__);
+
+	k_buffer = kzalloc(ORANGEFS_MAX_DEBUG_STRING_LEN, GFP_KERNEL);
+	if (!k_buffer)
+		goto out;
+
+	if (strlen(kernel_debug_string) + 1 < ORANGEFS_MAX_DEBUG_STRING_LEN) {
+		strcpy(k_buffer, kernel_debug_string);
+		strcat(k_buffer, "\n");
+	} else {
+		strcpy(k_buffer, "none\n");
+		pr_info("%s: overflow 1!\n", __func__);
+	}
+
+	ret = debugfs_create_file(ORANGEFS_KMOD_DEBUG_FILE,
+				  0444,
+				  debug_dir,
+				  k_buffer,
+				  &kernel_debug_fops);
+	if (!ret) {
+		pr_info("%s: failed to create %s.\n",
+			__func__,
+			ORANGEFS_KMOD_DEBUG_FILE);
+		goto out;
+	}
+
+	rc = 0;
+
+out:
+
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "%s: rc:%d:\n", __func__, rc);
+	return rc;
+}
+
+/*
+ * initialize the client-debug file.
+ */
+int orangefs_client_debug_init(void)
+{
+
+	int rc = -ENOMEM;
+	char *c_buffer = NULL;
+
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "%s: start\n", __func__);
+
+	c_buffer = kzalloc(ORANGEFS_MAX_DEBUG_STRING_LEN, GFP_KERNEL);
+	if (!c_buffer)
+		goto out;
+
+	if (strlen(client_debug_string) + 1 < ORANGEFS_MAX_DEBUG_STRING_LEN) {
+		strcpy(c_buffer, client_debug_string);
+		strcat(c_buffer, "\n");
+	} else {
+		strcpy(c_buffer, "none\n");
+		pr_info("%s: overflow! 2\n", __func__);
+	}
+
+	client_debug_dentry = debugfs_create_file(ORANGEFS_CLIENT_DEBUG_FILE,
+						  0444,
+						  debug_dir,
+						  c_buffer,
+						  &kernel_debug_fops);
+	if (!client_debug_dentry) {
+		pr_info("%s: failed to create updated %s.\n",
+			__func__,
+			ORANGEFS_CLIENT_DEBUG_FILE);
+		goto out;
+	}
+
+	rc = 0;
+
+out:
+
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "%s: rc:%d:\n", __func__, rc);
+	return rc;
+}
+
+/* open ORANGEFS_KMOD_DEBUG_FILE or ORANGEFS_CLIENT_DEBUG_FILE.*/
+int orangefs_debug_open(struct inode *inode, struct file *file)
+{
+	int rc = -ENODEV;
+
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG,
+		     "%s: orangefs_debug_disabled: %d\n",
+		     __func__,
+		     orangefs_debug_disabled);
+
+	if (orangefs_debug_disabled)
+		goto out;
+
+	rc = 0;
+	mutex_lock(&orangefs_debug_lock);
+	file->private_data = inode->i_private;
+	mutex_unlock(&orangefs_debug_lock);
+
+out:
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG,
+		     "orangefs_debug_open: rc: %d\n",
+		     rc);
+	return rc;
+}
+
+static ssize_t orangefs_debug_read(struct file *file,
+				 char __user *ubuf,
+				 size_t count,
+				 loff_t *ppos)
+{
+	char *buf;
+	int sprintf_ret;
+	ssize_t read_ret = -ENOMEM;
+
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "orangefs_debug_read: start\n");
+
+	buf = kmalloc(ORANGEFS_MAX_DEBUG_STRING_LEN, GFP_KERNEL);
+	if (!buf)
+		goto out;
+
+	mutex_lock(&orangefs_debug_lock);
+	sprintf_ret = sprintf(buf, "%s", (char *)file->private_data);
+	mutex_unlock(&orangefs_debug_lock);
+
+	read_ret = simple_read_from_buffer(ubuf, count, ppos, buf, sprintf_ret);
+
+	kfree(buf);
+
+out:
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG,
+		     "orangefs_debug_read: ret: %zu\n",
+		     read_ret);
+
+	return read_ret;
+}
+
+static ssize_t orangefs_debug_write(struct file *file,
+				  const char __user *ubuf,
+				  size_t count,
+				  loff_t *ppos)
+{
+	char *buf;
+	int rc = -EFAULT;
+	size_t silly = 0;
+	char *debug_string;
+	struct orangefs_kernel_op_s *new_op = NULL;
+	struct client_debug_mask c_mask = { NULL, 0, 0 };
+
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG,
+		"orangefs_debug_write: %s\n",
+		file->f_path.dentry->d_name.name);
+
+	/*
+	 * Thwart users who try to jamb a ridiculous number
+	 * of bytes into the debug file...
+	 */
+	if (count > ORANGEFS_MAX_DEBUG_STRING_LEN + 1) {
+		silly = count;
+		count = ORANGEFS_MAX_DEBUG_STRING_LEN + 1;
+	}
+
+	buf = kzalloc(ORANGEFS_MAX_DEBUG_STRING_LEN, GFP_KERNEL);
+	if (!buf)
+		goto out;
+
+	if (copy_from_user(buf, ubuf, count - 1)) {
+		gossip_debug(GOSSIP_DEBUGFS_DEBUG,
+			     "%s: copy_from_user failed!\n",
+			     __func__);
+		goto out;
+	}
+
+	/*
+	 * Map the keyword string from userspace into a valid debug mask.
+	 * The mapping process involves mapping the human-inputted string
+	 * into a valid mask, and then rebuilding the string from the
+	 * verified valid mask.
+	 *
+	 * A service operation is required to set a new client-side
+	 * debug mask.
+	 */
+	if (!strcmp(file->f_path.dentry->d_name.name,
+		    ORANGEFS_KMOD_DEBUG_FILE)) {
+		debug_string_to_mask(buf, &gossip_debug_mask, 0);
+		debug_mask_to_string(&gossip_debug_mask, 0);
+		debug_string = kernel_debug_string;
+		gossip_debug(GOSSIP_DEBUGFS_DEBUG,
+			     "New kernel debug string is %s\n",
+			     kernel_debug_string);
+	} else {
+		/* Can't reset client debug mask if client is not running. */
+		if (is_daemon_in_service()) {
+			pr_info("%s: Client not running :%d:\n",
+				__func__,
+				is_daemon_in_service());
+			goto out;
+		}
+
+		debug_string_to_mask(buf, &c_mask, 1);
+		debug_mask_to_string(&c_mask, 1);
+		debug_string = client_debug_string;
+
+		new_op = op_alloc(ORANGEFS_VFS_OP_PARAM);
+		if (!new_op) {
+			pr_info("%s: op_alloc failed!\n", __func__);
+			goto out;
+		}
+
+		new_op->upcall.req.param.op =
+			ORANGEFS_PARAM_REQUEST_OP_TWO_MASK_VALUES;
+		new_op->upcall.req.param.type = ORANGEFS_PARAM_REQUEST_SET;
+		memset(new_op->upcall.req.param.s_value,
+		       0,
+		       ORANGEFS_MAX_DEBUG_STRING_LEN);
+		sprintf(new_op->upcall.req.param.s_value,
+			"%llx %llx\n",
+			c_mask.mask1,
+			c_mask.mask2);
+
+		/* service_operation returns 0 on success... */
+		rc = service_operation(new_op,
+				       "orangefs_param",
+					ORANGEFS_OP_INTERRUPTIBLE);
+
+		if (rc)
+			gossip_debug(GOSSIP_DEBUGFS_DEBUG,
+				     "%s: service_operation failed! rc:%d:\n",
+				     __func__,
+				     rc);
+
+		op_release(new_op);
+	}
+
+	mutex_lock(&orangefs_debug_lock);
+	memset(file->f_inode->i_private, 0, ORANGEFS_MAX_DEBUG_STRING_LEN);
+	sprintf((char *)file->f_inode->i_private, "%s\n", debug_string);
+	mutex_unlock(&orangefs_debug_lock);
+
+	*ppos += count;
+	if (silly)
+		rc = silly;
+	else
+		rc = count;
+
+out:
+	gossip_debug(GOSSIP_DEBUGFS_DEBUG,
+		     "orangefs_debug_write: rc: %d\n",
+		     rc);
+	kfree(buf);
+	return rc;
+}
diff --git a/fs/orangefs/orangefs-debugfs.h b/fs/orangefs/orangefs-debugfs.h
new file mode 100644
index 000000000000..e4828c0e3ef9
--- /dev/null
+++ b/fs/orangefs/orangefs-debugfs.h
@@ -0,0 +1,3 @@
+int orangefs_debugfs_init(void);
+int orangefs_kernel_debug_init(void);
+void orangefs_debugfs_cleanup(void);
diff --git a/fs/orangefs/orangefs-dev-proto.h b/fs/orangefs/orangefs-dev-proto.h
new file mode 100644
index 000000000000..9eac9d9a3f3a
--- /dev/null
+++ b/fs/orangefs/orangefs-dev-proto.h
@@ -0,0 +1,62 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+#ifndef _ORANGEFS_DEV_PROTO_H
+#define _ORANGEFS_DEV_PROTO_H
+
+/*
+ * types and constants shared between user space and kernel space for
+ * device interaction using a common protocol
+ */
+
+/*
+ * valid orangefs kernel operation types
+ */
+#define ORANGEFS_VFS_OP_INVALID           0xFF000000
+#define ORANGEFS_VFS_OP_FILE_IO        0xFF000001
+#define ORANGEFS_VFS_OP_LOOKUP         0xFF000002
+#define ORANGEFS_VFS_OP_CREATE         0xFF000003
+#define ORANGEFS_VFS_OP_GETATTR        0xFF000004
+#define ORANGEFS_VFS_OP_REMOVE         0xFF000005
+#define ORANGEFS_VFS_OP_MKDIR          0xFF000006
+#define ORANGEFS_VFS_OP_READDIR        0xFF000007
+#define ORANGEFS_VFS_OP_SETATTR        0xFF000008
+#define ORANGEFS_VFS_OP_SYMLINK        0xFF000009
+#define ORANGEFS_VFS_OP_RENAME         0xFF00000A
+#define ORANGEFS_VFS_OP_STATFS         0xFF00000B
+#define ORANGEFS_VFS_OP_TRUNCATE       0xFF00000C
+#define ORANGEFS_VFS_OP_MMAP_RA_FLUSH  0xFF00000D
+#define ORANGEFS_VFS_OP_FS_MOUNT       0xFF00000E
+#define ORANGEFS_VFS_OP_FS_UMOUNT      0xFF00000F
+#define ORANGEFS_VFS_OP_GETXATTR       0xFF000010
+#define ORANGEFS_VFS_OP_SETXATTR          0xFF000011
+#define ORANGEFS_VFS_OP_LISTXATTR         0xFF000012
+#define ORANGEFS_VFS_OP_REMOVEXATTR       0xFF000013
+#define ORANGEFS_VFS_OP_PARAM          0xFF000014
+#define ORANGEFS_VFS_OP_PERF_COUNT     0xFF000015
+#define ORANGEFS_VFS_OP_CANCEL            0xFF00EE00
+#define ORANGEFS_VFS_OP_FSYNC          0xFF00EE01
+#define ORANGEFS_VFS_OP_FSKEY             0xFF00EE02
+#define ORANGEFS_VFS_OP_READDIRPLUS       0xFF00EE03
+
+/*
+ * Misc constants. Please retain them as multiples of 8!
+ * Otherwise 32-64 bit interactions will be messed up :)
+ */
+#define ORANGEFS_MAX_DEBUG_STRING_LEN	0x00000400
+#define ORANGEFS_MAX_DEBUG_ARRAY_LEN	0x00000800
+
+/*
+ * The maximum number of directory entries in a single request is 96.
+ * XXX: Why can this not be higher. The client-side code can handle up to 512.
+ * XXX: What happens if we expect more than the client can return?
+ */
+#define ORANGEFS_MAX_DIRENT_COUNT_READDIR 96
+
+#include "upcall.h"
+#include "downcall.h"
+
+#endif
diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h
new file mode 100644
index 000000000000..a9925e296ceb
--- /dev/null
+++ b/fs/orangefs/orangefs-kernel.h
@@ -0,0 +1,623 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+/*
+ *  The ORANGEFS Linux kernel support allows ORANGEFS volumes to be mounted and
+ *  accessed through the Linux VFS (i.e. using standard I/O system calls).
+ *  This support is only needed on clients that wish to mount the file system.
+ *
+ */
+
+/*
+ *  Declarations and macros for the ORANGEFS Linux kernel support.
+ */
+
+#ifndef __ORANGEFSKERNEL_H
+#define __ORANGEFSKERNEL_H
+
+#include <linux/kernel.h>
+#include <linux/moduleparam.h>
+#include <linux/statfs.h>
+#include <linux/backing-dev.h>
+#include <linux/device.h>
+#include <linux/mpage.h>
+#include <linux/namei.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/vmalloc.h>
+
+#include <linux/aio.h>
+#include <linux/posix_acl.h>
+#include <linux/posix_acl_xattr.h>
+#include <linux/compat.h>
+#include <linux/mount.h>
+#include <linux/uaccess.h>
+#include <linux/atomic.h>
+#include <linux/uio.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/wait.h>
+#include <linux/dcache.h>
+#include <linux/pagemap.h>
+#include <linux/poll.h>
+#include <linux/rwsem.h>
+#include <linux/xattr.h>
+#include <linux/exportfs.h>
+
+#include <asm/unaligned.h>
+
+#include "orangefs-dev-proto.h"
+
+#ifdef ORANGEFS_KERNEL_DEBUG
+#define ORANGEFS_DEFAULT_OP_TIMEOUT_SECS       10
+#else
+#define ORANGEFS_DEFAULT_OP_TIMEOUT_SECS       20
+#endif
+
+#define ORANGEFS_BUFMAP_WAIT_TIMEOUT_SECS   30
+
+#define ORANGEFS_DEFAULT_SLOT_TIMEOUT_SECS     900	/* 15 minutes */
+
+#define ORANGEFS_REQDEVICE_NAME          "pvfs2-req"
+
+#define ORANGEFS_DEVREQ_MAGIC             0x20030529
+#define ORANGEFS_LINK_MAX                 0x000000FF
+#define ORANGEFS_PURGE_RETRY_COUNT     0x00000005
+#define ORANGEFS_MAX_NUM_OPTIONS          0x00000004
+#define ORANGEFS_MAX_MOUNT_OPT_LEN        0x00000080
+#define ORANGEFS_MAX_FSKEY_LEN            64
+
+#define MAX_DEV_REQ_UPSIZE (2 * sizeof(__s32) +   \
+sizeof(__u64) + sizeof(struct orangefs_upcall_s))
+#define MAX_DEV_REQ_DOWNSIZE (2 * sizeof(__s32) + \
+sizeof(__u64) + sizeof(struct orangefs_downcall_s))
+
+/*
+ * valid orangefs kernel operation states
+ *
+ * unknown  - op was just initialized
+ * waiting  - op is on request_list (upward bound)
+ * inprogr  - op is in progress (waiting for downcall)
+ * serviced - op has matching downcall; ok
+ * purged   - op has to start a timer since client-core
+ *            exited uncleanly before servicing op
+ * given up - submitter has given up waiting for it
+ */
+enum orangefs_vfs_op_states {
+	OP_VFS_STATE_UNKNOWN = 0,
+	OP_VFS_STATE_WAITING = 1,
+	OP_VFS_STATE_INPROGR = 2,
+	OP_VFS_STATE_SERVICED = 4,
+	OP_VFS_STATE_PURGED = 8,
+	OP_VFS_STATE_GIVEN_UP = 16,
+};
+
+/*
+ * An array of client_debug_mask will be built to hold debug keyword/mask
+ * values fetched from userspace.
+ */
+struct client_debug_mask {
+	char *keyword;
+	__u64 mask1;
+	__u64 mask2;
+};
+
+/*
+ * orangefs kernel memory related flags
+ */
+
+#if ((defined ORANGEFS_KERNEL_DEBUG) && (defined CONFIG_DEBUG_SLAB))
+#define ORANGEFS_CACHE_CREATE_FLAGS SLAB_RED_ZONE
+#else
+#define ORANGEFS_CACHE_CREATE_FLAGS 0
+#endif /* ((defined ORANGEFS_KERNEL_DEBUG) && (defined CONFIG_DEBUG_SLAB)) */
+
+/* orangefs xattr and acl related defines */
+#define ORANGEFS_XATTR_INDEX_POSIX_ACL_ACCESS  1
+#define ORANGEFS_XATTR_INDEX_POSIX_ACL_DEFAULT 2
+#define ORANGEFS_XATTR_INDEX_TRUSTED           3
+#define ORANGEFS_XATTR_INDEX_DEFAULT           4
+
+#define ORANGEFS_XATTR_NAME_ACL_ACCESS XATTR_NAME_POSIX_ACL_ACCESS
+#define ORANGEFS_XATTR_NAME_ACL_DEFAULT XATTR_NAME_POSIX_ACL_DEFAULT
+#define ORANGEFS_XATTR_NAME_TRUSTED_PREFIX "trusted."
+#define ORANGEFS_XATTR_NAME_DEFAULT_PREFIX ""
+
+/* these functions are defined in orangefs-utils.c */
+int orangefs_prepare_cdm_array(char *debug_array_string);
+int orangefs_prepare_debugfs_help_string(int);
+
+/* defined in orangefs-debugfs.c */
+int orangefs_client_debug_init(void);
+
+void debug_string_to_mask(char *, void *, int);
+void do_c_mask(int, char *, struct client_debug_mask **);
+void do_k_mask(int, char *, __u64 **);
+
+void debug_mask_to_string(void *, int);
+void do_k_string(void *, int);
+void do_c_string(void *, int);
+int check_amalgam_keyword(void *, int);
+int keyword_is_amalgam(char *);
+
+/*these variables are defined in orangefs-mod.c */
+extern char kernel_debug_string[ORANGEFS_MAX_DEBUG_STRING_LEN];
+extern char client_debug_string[ORANGEFS_MAX_DEBUG_STRING_LEN];
+extern char client_debug_array_string[ORANGEFS_MAX_DEBUG_STRING_LEN];
+extern unsigned int kernel_mask_set_mod_init;
+
+extern int orangefs_init_acl(struct inode *inode, struct inode *dir);
+extern const struct xattr_handler *orangefs_xattr_handlers[];
+
+extern struct posix_acl *orangefs_get_acl(struct inode *inode, int type);
+extern int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+
+/*
+ * Redefine xtvec structure so that we could move helper functions out of
+ * the define
+ */
+struct xtvec {
+	__kernel_off_t xtv_off;		/* must be off_t */
+	__kernel_size_t xtv_len;	/* must be size_t */
+};
+
+/*
+ * orangefs data structures
+ */
+struct orangefs_kernel_op_s {
+	enum orangefs_vfs_op_states op_state;
+	__u64 tag;
+
+	/*
+	 * Set uses_shared_memory to non zero if this operation uses
+	 * shared memory. If true, then a retry on the op must also
+	 * get a new shared memory buffer and re-populate it.
+	 * Cancels don't care - it only matters for service_operation()
+	 * retry logics and cancels don't go through it anymore. It
+	 * safely stays non-zero when we use it as slot_to_free.
+	 */
+	union {
+		int uses_shared_memory;
+		int slot_to_free;
+	};
+
+	struct orangefs_upcall_s upcall;
+	struct orangefs_downcall_s downcall;
+
+	struct completion waitq;
+	spinlock_t lock;
+
+	int attempts;
+
+	struct list_head list;
+};
+
+#define set_op_state_waiting(op)     ((op)->op_state = OP_VFS_STATE_WAITING)
+#define set_op_state_inprogress(op)  ((op)->op_state = OP_VFS_STATE_INPROGR)
+#define set_op_state_given_up(op)  ((op)->op_state = OP_VFS_STATE_GIVEN_UP)
+static inline void set_op_state_serviced(struct orangefs_kernel_op_s *op)
+{
+	op->op_state = OP_VFS_STATE_SERVICED;
+	complete(&op->waitq);
+}
+
+#define op_state_waiting(op)     ((op)->op_state & OP_VFS_STATE_WAITING)
+#define op_state_in_progress(op) ((op)->op_state & OP_VFS_STATE_INPROGR)
+#define op_state_serviced(op)    ((op)->op_state & OP_VFS_STATE_SERVICED)
+#define op_state_purged(op)      ((op)->op_state & OP_VFS_STATE_PURGED)
+#define op_state_given_up(op)    ((op)->op_state & OP_VFS_STATE_GIVEN_UP)
+#define op_is_cancel(op)         ((op)->upcall.type == ORANGEFS_VFS_OP_CANCEL)
+
+void op_release(struct orangefs_kernel_op_s *op);
+
+extern void orangefs_bufmap_put(int);
+static inline void put_cancel(struct orangefs_kernel_op_s *op)
+{
+	orangefs_bufmap_put(op->slot_to_free);
+	op_release(op);
+}
+
+static inline void set_op_state_purged(struct orangefs_kernel_op_s *op)
+{
+	spin_lock(&op->lock);
+	if (unlikely(op_is_cancel(op))) {
+		list_del_init(&op->list);
+		spin_unlock(&op->lock);
+		put_cancel(op);
+	} else {
+		op->op_state |= OP_VFS_STATE_PURGED;
+		complete(&op->waitq);
+		spin_unlock(&op->lock);
+	}
+}
+
+/* per inode private orangefs info */
+struct orangefs_inode_s {
+	struct orangefs_object_kref refn;
+	char link_target[ORANGEFS_NAME_MAX];
+	__s64 blksize;
+	/*
+	 * Reading/Writing Extended attributes need to acquire the appropriate
+	 * reader/writer semaphore on the orangefs_inode_s structure.
+	 */
+	struct rw_semaphore xattr_sem;
+
+	struct inode vfs_inode;
+	sector_t last_failed_block_index_read;
+
+	/*
+	 * State of in-memory attributes not yet flushed to disk associated
+	 * with this object
+	 */
+	unsigned long pinode_flags;
+};
+
+#define P_ATIME_FLAG 0
+#define P_MTIME_FLAG 1
+#define P_CTIME_FLAG 2
+#define P_MODE_FLAG  3
+
+#define ClearAtimeFlag(pinode) clear_bit(P_ATIME_FLAG, &(pinode)->pinode_flags)
+#define SetAtimeFlag(pinode)   set_bit(P_ATIME_FLAG, &(pinode)->pinode_flags)
+#define AtimeFlag(pinode)      test_bit(P_ATIME_FLAG, &(pinode)->pinode_flags)
+
+#define ClearMtimeFlag(pinode) clear_bit(P_MTIME_FLAG, &(pinode)->pinode_flags)
+#define SetMtimeFlag(pinode)   set_bit(P_MTIME_FLAG, &(pinode)->pinode_flags)
+#define MtimeFlag(pinode)      test_bit(P_MTIME_FLAG, &(pinode)->pinode_flags)
+
+#define ClearCtimeFlag(pinode) clear_bit(P_CTIME_FLAG, &(pinode)->pinode_flags)
+#define SetCtimeFlag(pinode)   set_bit(P_CTIME_FLAG, &(pinode)->pinode_flags)
+#define CtimeFlag(pinode)      test_bit(P_CTIME_FLAG, &(pinode)->pinode_flags)
+
+#define ClearModeFlag(pinode) clear_bit(P_MODE_FLAG, &(pinode)->pinode_flags)
+#define SetModeFlag(pinode)   set_bit(P_MODE_FLAG, &(pinode)->pinode_flags)
+#define ModeFlag(pinode)      test_bit(P_MODE_FLAG, &(pinode)->pinode_flags)
+
+/* per superblock private orangefs info */
+struct orangefs_sb_info_s {
+	struct orangefs_khandle root_khandle;
+	__s32 fs_id;
+	int id;
+	int flags;
+#define ORANGEFS_OPT_INTR	0x01
+#define ORANGEFS_OPT_LOCAL_LOCK	0x02
+	char devname[ORANGEFS_MAX_SERVER_ADDR_LEN];
+	struct super_block *sb;
+	int mount_pending;
+	struct list_head list;
+};
+
+/*
+ * structure that holds the state of any async I/O operation issued
+ * through the VFS. Needed especially to handle cancellation requests
+ * or even completion notification so that the VFS client-side daemon
+ * can free up its vfs_request slots.
+ */
+struct orangefs_kiocb_s {
+	/* the pointer to the task that initiated the AIO */
+	struct task_struct *tsk;
+
+	/* pointer to the kiocb that kicked this operation */
+	struct kiocb *kiocb;
+
+	/* buffer index that was used for the I/O */
+	struct orangefs_bufmap *bufmap;
+	int buffer_index;
+
+	/* orangefs kernel operation type */
+	struct orangefs_kernel_op_s *op;
+
+	/* The user space buffers from/to which I/O is being staged */
+	struct iovec *iov;
+
+	/* number of elements in the iovector */
+	unsigned long nr_segs;
+
+	/* set to indicate the type of the operation */
+	int rw;
+
+	/* file offset */
+	loff_t offset;
+
+	/* and the count in bytes */
+	size_t bytes_to_be_copied;
+
+	ssize_t bytes_copied;
+	int needs_cleanup;
+};
+
+struct orangefs_stats {
+	unsigned long cache_hits;
+	unsigned long cache_misses;
+	unsigned long reads;
+	unsigned long writes;
+};
+
+extern struct orangefs_stats g_orangefs_stats;
+
+/*
+ * NOTE: See Documentation/filesystems/porting for information
+ * on implementing FOO_I and properly accessing fs private data
+ */
+static inline struct orangefs_inode_s *ORANGEFS_I(struct inode *inode)
+{
+	return container_of(inode, struct orangefs_inode_s, vfs_inode);
+}
+
+static inline struct orangefs_sb_info_s *ORANGEFS_SB(struct super_block *sb)
+{
+	return (struct orangefs_sb_info_s *) sb->s_fs_info;
+}
+
+/* ino_t descends from "unsigned long", 8 bytes, 64 bits. */
+static inline ino_t orangefs_khandle_to_ino(struct orangefs_khandle *khandle)
+{
+	union {
+		unsigned char u[8];
+		__u64 ino;
+	} ihandle;
+
+	ihandle.u[0] = khandle->u[0] ^ khandle->u[4];
+	ihandle.u[1] = khandle->u[1] ^ khandle->u[5];
+	ihandle.u[2] = khandle->u[2] ^ khandle->u[6];
+	ihandle.u[3] = khandle->u[3] ^ khandle->u[7];
+	ihandle.u[4] = khandle->u[12] ^ khandle->u[8];
+	ihandle.u[5] = khandle->u[13] ^ khandle->u[9];
+	ihandle.u[6] = khandle->u[14] ^ khandle->u[10];
+	ihandle.u[7] = khandle->u[15] ^ khandle->u[11];
+
+	return ihandle.ino;
+}
+
+static inline struct orangefs_khandle *get_khandle_from_ino(struct inode *inode)
+{
+	return &(ORANGEFS_I(inode)->refn.khandle);
+}
+
+static inline __s32 get_fsid_from_ino(struct inode *inode)
+{
+	return ORANGEFS_I(inode)->refn.fs_id;
+}
+
+static inline ino_t get_ino_from_khandle(struct inode *inode)
+{
+	struct orangefs_khandle *khandle;
+	ino_t ino;
+
+	khandle = get_khandle_from_ino(inode);
+	ino = orangefs_khandle_to_ino(khandle);
+	return ino;
+}
+
+static inline ino_t get_parent_ino_from_dentry(struct dentry *dentry)
+{
+	return get_ino_from_khandle(dentry->d_parent->d_inode);
+}
+
+static inline int is_root_handle(struct inode *inode)
+{
+	gossip_debug(GOSSIP_DCACHE_DEBUG,
+		     "%s: root handle: %pU, this handle: %pU:\n",
+		     __func__,
+		     &ORANGEFS_SB(inode->i_sb)->root_khandle,
+		     get_khandle_from_ino(inode));
+
+	if (ORANGEFS_khandle_cmp(&(ORANGEFS_SB(inode->i_sb)->root_khandle),
+			     get_khandle_from_ino(inode)))
+		return 0;
+	else
+		return 1;
+}
+
+static inline int match_handle(struct orangefs_khandle resp_handle,
+			       struct inode *inode)
+{
+	gossip_debug(GOSSIP_DCACHE_DEBUG,
+		     "%s: one handle: %pU, another handle:%pU:\n",
+		     __func__,
+		     &resp_handle,
+		     get_khandle_from_ino(inode));
+
+	if (ORANGEFS_khandle_cmp(&resp_handle, get_khandle_from_ino(inode)))
+		return 0;
+	else
+		return 1;
+}
+
+/*
+ * defined in orangefs-cache.c
+ */
+int op_cache_initialize(void);
+int op_cache_finalize(void);
+struct orangefs_kernel_op_s *op_alloc(__s32 type);
+void orangefs_new_tag(struct orangefs_kernel_op_s *op);
+char *get_opname_string(struct orangefs_kernel_op_s *new_op);
+
+int orangefs_inode_cache_initialize(void);
+int orangefs_inode_cache_finalize(void);
+
+/*
+ * defined in orangefs-mod.c
+ */
+void purge_inprogress_ops(void);
+
+/*
+ * defined in waitqueue.c
+ */
+void purge_waiting_ops(void);
+
+/*
+ * defined in super.c
+ */
+struct dentry *orangefs_mount(struct file_system_type *fst,
+			   int flags,
+			   const char *devname,
+			   void *data);
+
+void orangefs_kill_sb(struct super_block *sb);
+int orangefs_remount(struct orangefs_sb_info_s *);
+
+int fsid_key_table_initialize(void);
+void fsid_key_table_finalize(void);
+
+/*
+ * defined in inode.c
+ */
+__u32 convert_to_orangefs_mask(unsigned long lite_mask);
+struct inode *orangefs_new_inode(struct super_block *sb,
+			      struct inode *dir,
+			      int mode,
+			      dev_t dev,
+			      struct orangefs_object_kref *ref);
+
+int orangefs_setattr(struct dentry *dentry, struct iattr *iattr);
+
+int orangefs_getattr(struct vfsmount *mnt,
+		  struct dentry *dentry,
+		  struct kstat *kstat);
+
+int orangefs_permission(struct inode *inode, int mask);
+
+/*
+ * defined in xattr.c
+ */
+int orangefs_setxattr(struct dentry *dentry,
+		   const char *name,
+		   const void *value,
+		   size_t size,
+		   int flags);
+
+ssize_t orangefs_getxattr(struct dentry *dentry,
+		       const char *name,
+		       void *buffer,
+		       size_t size);
+
+ssize_t orangefs_listxattr(struct dentry *dentry, char *buffer, size_t size);
+
+/*
+ * defined in namei.c
+ */
+struct inode *orangefs_iget(struct super_block *sb,
+			 struct orangefs_object_kref *ref);
+
+ssize_t orangefs_inode_read(struct inode *inode,
+			    struct iov_iter *iter,
+			    loff_t *offset,
+			    loff_t readahead_size);
+
+/*
+ * defined in devorangefs-req.c
+ */
+int orangefs_dev_init(void);
+void orangefs_dev_cleanup(void);
+int is_daemon_in_service(void);
+bool __is_daemon_in_service(void);
+
+/*
+ * defined in orangefs-utils.c
+ */
+__s32 fsid_of_op(struct orangefs_kernel_op_s *op);
+
+int orangefs_flush_inode(struct inode *inode);
+
+ssize_t orangefs_inode_getxattr(struct inode *inode,
+			     const char *prefix,
+			     const char *name,
+			     void *buffer,
+			     size_t size);
+
+int orangefs_inode_setxattr(struct inode *inode,
+			 const char *prefix,
+			 const char *name,
+			 const void *value,
+			 size_t size,
+			 int flags);
+
+int orangefs_inode_getattr(struct inode *inode, int new, int size);
+
+int orangefs_inode_check_changed(struct inode *inode);
+
+int orangefs_inode_setattr(struct inode *inode, struct iattr *iattr);
+
+void orangefs_make_bad_inode(struct inode *inode);
+
+int orangefs_unmount_sb(struct super_block *sb);
+
+bool orangefs_cancel_op_in_progress(struct orangefs_kernel_op_s *op);
+
+int orangefs_normalize_to_errno(__s32 error_code);
+
+extern struct mutex devreq_mutex;
+extern struct mutex request_mutex;
+extern int debug;
+extern int op_timeout_secs;
+extern int slot_timeout_secs;
+extern struct list_head orangefs_superblocks;
+extern spinlock_t orangefs_superblocks_lock;
+extern struct list_head orangefs_request_list;
+extern spinlock_t orangefs_request_list_lock;
+extern wait_queue_head_t orangefs_request_list_waitq;
+extern struct list_head *htable_ops_in_progress;
+extern spinlock_t htable_ops_in_progress_lock;
+extern int hash_table_size;
+
+extern const struct address_space_operations orangefs_address_operations;
+extern struct backing_dev_info orangefs_backing_dev_info;
+extern struct inode_operations orangefs_file_inode_operations;
+extern const struct file_operations orangefs_file_operations;
+extern struct inode_operations orangefs_symlink_inode_operations;
+extern struct inode_operations orangefs_dir_inode_operations;
+extern const struct file_operations orangefs_dir_operations;
+extern const struct dentry_operations orangefs_dentry_operations;
+extern const struct file_operations orangefs_devreq_file_operations;
+
+extern wait_queue_head_t orangefs_bufmap_init_waitq;
+
+/*
+ * misc convenience macros
+ */
+
+#define ORANGEFS_OP_INTERRUPTIBLE 1   /* service_operation() is interruptible */
+#define ORANGEFS_OP_PRIORITY      2   /* service_operation() is high priority */
+#define ORANGEFS_OP_CANCELLATION  4   /* this is a cancellation */
+#define ORANGEFS_OP_NO_MUTEX      8   /* don't acquire request_mutex */
+#define ORANGEFS_OP_ASYNC         16  /* Queue it, but don't wait */
+
+int service_operation(struct orangefs_kernel_op_s *op,
+		      const char *op_name,
+		      int flags);
+
+#define get_interruptible_flag(inode) \
+	((ORANGEFS_SB(inode->i_sb)->flags & ORANGEFS_OPT_INTR) ? \
+		ORANGEFS_OP_INTERRUPTIBLE : 0)
+
+#define fill_default_sys_attrs(sys_attr, type, mode)			\
+do {									\
+	sys_attr.owner = from_kuid(current_user_ns(), current_fsuid()); \
+	sys_attr.group = from_kgid(current_user_ns(), current_fsgid()); \
+	sys_attr.perms = ORANGEFS_util_translate_mode(mode);		\
+	sys_attr.mtime = 0;						\
+	sys_attr.atime = 0;						\
+	sys_attr.ctime = 0;						\
+	sys_attr.mask = ORANGEFS_ATTR_SYS_ALL_SETABLE;			\
+} while (0)
+
+static inline void orangefs_i_size_write(struct inode *inode, loff_t i_size)
+{
+#if BITS_PER_LONG == 32 && defined(CONFIG_SMP)
+	mutex_lock(&inode->i_mutex);
+#endif
+	i_size_write(inode, i_size);
+#if BITS_PER_LONG == 32 && defined(CONFIG_SMP)
+	mutex_unlock(&inode->i_mutex);
+#endif
+}
+
+#endif /* __ORANGEFSKERNEL_H */
diff --git a/fs/orangefs/orangefs-mod.c b/fs/orangefs/orangefs-mod.c
new file mode 100644
index 000000000000..6f072a8c0de1
--- /dev/null
+++ b/fs/orangefs/orangefs-mod.c
@@ -0,0 +1,293 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * Changes by Acxiom Corporation to add proc file handler for pvfs2 client
+ * parameters, Copyright Acxiom Corporation, 2005.
+ *
+ * See COPYING in top-level directory.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-debugfs.h"
+#include "orangefs-sysfs.h"
+
+/* ORANGEFS_VERSION is a ./configure define */
+#ifndef ORANGEFS_VERSION
+#define ORANGEFS_VERSION "upstream"
+#endif
+
+/*
+ * global variables declared here
+ */
+
+/* array of client debug keyword/mask values */
+struct client_debug_mask *cdm_array;
+int cdm_element_count;
+
+char kernel_debug_string[ORANGEFS_MAX_DEBUG_STRING_LEN] = "none";
+char client_debug_string[ORANGEFS_MAX_DEBUG_STRING_LEN];
+char client_debug_array_string[ORANGEFS_MAX_DEBUG_STRING_LEN];
+
+char *debug_help_string;
+int help_string_initialized;
+struct dentry *help_file_dentry;
+struct dentry *client_debug_dentry;
+struct dentry *debug_dir;
+int client_verbose_index;
+int client_all_index;
+struct orangefs_stats g_orangefs_stats;
+
+/* the size of the hash tables for ops in progress */
+int hash_table_size = 509;
+
+static ulong module_parm_debug_mask;
+__u64 gossip_debug_mask;
+struct client_debug_mask client_debug_mask = { NULL, 0, 0 };
+unsigned int kernel_mask_set_mod_init; /* implicitly false */
+int op_timeout_secs = ORANGEFS_DEFAULT_OP_TIMEOUT_SECS;
+int slot_timeout_secs = ORANGEFS_DEFAULT_SLOT_TIMEOUT_SECS;
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("ORANGEFS Development Team");
+MODULE_DESCRIPTION("The Linux Kernel VFS interface to ORANGEFS");
+MODULE_PARM_DESC(module_parm_debug_mask, "debugging level (see orangefs-debug.h for values)");
+MODULE_PARM_DESC(op_timeout_secs, "Operation timeout in seconds");
+MODULE_PARM_DESC(slot_timeout_secs, "Slot timeout in seconds");
+MODULE_PARM_DESC(hash_table_size,
+		 "size of hash table for operations in progress");
+
+static struct file_system_type orangefs_fs_type = {
+	.name = "pvfs2",
+	.mount = orangefs_mount,
+	.kill_sb = orangefs_kill_sb,
+	.owner = THIS_MODULE,
+};
+
+module_param(hash_table_size, int, 0);
+module_param(module_parm_debug_mask, ulong, 0644);
+module_param(op_timeout_secs, int, 0);
+module_param(slot_timeout_secs, int, 0);
+
+/* synchronizes the request device file */
+DEFINE_MUTEX(devreq_mutex);
+
+/*
+ * Blocks non-priority requests from being queued for servicing.  This
+ * could be used for protecting the request list data structure, but
+ * for now it's only being used to stall the op addition to the request
+ * list
+ */
+DEFINE_MUTEX(request_mutex);
+
+/* hash table for storing operations waiting for matching downcall */
+struct list_head *htable_ops_in_progress;
+DEFINE_SPINLOCK(htable_ops_in_progress_lock);
+
+/* list for queueing upcall operations */
+LIST_HEAD(orangefs_request_list);
+
+/* used to protect the above orangefs_request_list */
+DEFINE_SPINLOCK(orangefs_request_list_lock);
+
+/* used for incoming request notification */
+DECLARE_WAIT_QUEUE_HEAD(orangefs_request_list_waitq);
+
+static int __init orangefs_init(void)
+{
+	int ret = -1;
+	__u32 i = 0;
+
+	/* convert input debug mask to a 64-bit unsigned integer */
+	gossip_debug_mask = (unsigned long long) module_parm_debug_mask;
+
+	/*
+	 * set the kernel's gossip debug string; invalid mask values will
+	 * be ignored.
+	 */
+	debug_mask_to_string(&gossip_debug_mask, 0);
+
+	/* remove any invalid values from the mask */
+	debug_string_to_mask(kernel_debug_string, &gossip_debug_mask, 0);
+
+	/*
+	 * if the mask has a non-zero value, then indicate that the mask
+	 * was set when the kernel module was loaded.  The orangefs dev ioctl
+	 * command will look at this boolean to determine if the kernel's
+	 * debug mask should be overwritten when the client-core is started.
+	 */
+	if (gossip_debug_mask != 0)
+		kernel_mask_set_mod_init = true;
+
+	pr_info("%s: called with debug mask: :%s: :%llx:\n",
+		__func__,
+		kernel_debug_string,
+		(unsigned long long)gossip_debug_mask);
+
+	ret = bdi_init(&orangefs_backing_dev_info);
+
+	if (ret)
+		return ret;
+
+	if (op_timeout_secs < 0)
+		op_timeout_secs = 0;
+
+	if (slot_timeout_secs < 0)
+		slot_timeout_secs = 0;
+
+	/* initialize global book keeping data structures */
+	ret = op_cache_initialize();
+	if (ret < 0)
+		goto err;
+
+	ret = orangefs_inode_cache_initialize();
+	if (ret < 0)
+		goto cleanup_op;
+
+	htable_ops_in_progress =
+	    kcalloc(hash_table_size, sizeof(struct list_head), GFP_KERNEL);
+	if (!htable_ops_in_progress) {
+		gossip_err("Failed to initialize op hashtable");
+		ret = -ENOMEM;
+		goto cleanup_inode;
+	}
+
+	/* initialize a doubly linked at each hash table index */
+	for (i = 0; i < hash_table_size; i++)
+		INIT_LIST_HEAD(&htable_ops_in_progress[i]);
+
+	ret = fsid_key_table_initialize();
+	if (ret < 0)
+		goto cleanup_progress_table;
+
+	/*
+	 * Build the contents of /sys/kernel/debug/orangefs/debug-help
+	 * from the keywords in the kernel keyword/mask array.
+	 *
+	 * The keywords in the client keyword/mask array are
+	 * unknown at boot time.
+	 *
+	 * orangefs_prepare_debugfs_help_string will be used again
+	 * later to rebuild the debug-help file after the client starts
+	 * and passes along the needed info. The argument signifies
+	 * which time orangefs_prepare_debugfs_help_string is being
+	 * called.
+	 */
+	ret = orangefs_prepare_debugfs_help_string(1);
+	if (ret)
+		goto cleanup_key_table;
+
+	ret = orangefs_debugfs_init();
+	if (ret)
+		goto debugfs_init_failed;
+
+	ret = orangefs_kernel_debug_init();
+	if (ret)
+		goto kernel_debug_init_failed;
+
+	ret = orangefs_sysfs_init();
+	if (ret)
+		goto sysfs_init_failed;
+
+	/* Initialize the orangefsdev subsystem. */
+	ret = orangefs_dev_init();
+	if (ret < 0) {
+		gossip_err("%s: could not initialize device subsystem %d!\n",
+			   __func__,
+			   ret);
+		goto cleanup_device;
+	}
+
+	ret = register_filesystem(&orangefs_fs_type);
+	if (ret == 0) {
+		pr_info("orangefs: module version %s loaded\n", ORANGEFS_VERSION);
+		ret = 0;
+		goto out;
+	}
+
+	orangefs_sysfs_exit();
+
+cleanup_device:
+	orangefs_dev_cleanup();
+
+sysfs_init_failed:
+
+kernel_debug_init_failed:
+
+debugfs_init_failed:
+	orangefs_debugfs_cleanup();
+
+cleanup_key_table:
+	fsid_key_table_finalize();
+
+cleanup_progress_table:
+	kfree(htable_ops_in_progress);
+
+cleanup_inode:
+	orangefs_inode_cache_finalize();
+
+cleanup_op:
+	op_cache_finalize();
+
+err:
+	bdi_destroy(&orangefs_backing_dev_info);
+
+out:
+	return ret;
+}
+
+static void __exit orangefs_exit(void)
+{
+	int i = 0;
+	gossip_debug(GOSSIP_INIT_DEBUG, "orangefs: orangefs_exit called\n");
+
+	unregister_filesystem(&orangefs_fs_type);
+	orangefs_debugfs_cleanup();
+	orangefs_sysfs_exit();
+	fsid_key_table_finalize();
+	orangefs_dev_cleanup();
+	BUG_ON(!list_empty(&orangefs_request_list));
+	for (i = 0; i < hash_table_size; i++)
+		BUG_ON(!list_empty(&htable_ops_in_progress[i]));
+
+	orangefs_inode_cache_finalize();
+	op_cache_finalize();
+
+	kfree(htable_ops_in_progress);
+
+	bdi_destroy(&orangefs_backing_dev_info);
+
+	pr_info("orangefs: module version %s unloaded\n", ORANGEFS_VERSION);
+}
+
+/*
+ * What we do in this function is to walk the list of operations
+ * that are in progress in the hash table and mark them as purged as well.
+ */
+void purge_inprogress_ops(void)
+{
+	int i;
+
+	for (i = 0; i < hash_table_size; i++) {
+		struct orangefs_kernel_op_s *op;
+		struct orangefs_kernel_op_s *next;
+
+		spin_lock(&htable_ops_in_progress_lock);
+		list_for_each_entry_safe(op,
+					 next,
+					 &htable_ops_in_progress[i],
+					 list) {
+			set_op_state_purged(op);
+			gossip_debug(GOSSIP_DEV_DEBUG,
+				     "%s: op:%s: op_state:%d: process:%s:\n",
+				     __func__,
+				     get_opname_string(op),
+				     op->op_state,
+				     current->comm);
+		}
+		spin_unlock(&htable_ops_in_progress_lock);
+	}
+}
+
+module_init(orangefs_init);
+module_exit(orangefs_exit);
diff --git a/fs/orangefs/orangefs-sysfs.c b/fs/orangefs/orangefs-sysfs.c
new file mode 100644
index 000000000000..5c03113e3ad2
--- /dev/null
+++ b/fs/orangefs/orangefs-sysfs.c
@@ -0,0 +1,1772 @@
+/*
+ * Documentation/ABI/stable/orangefs-sysfs:
+ *
+ * What:		/sys/fs/orangefs/perf_counter_reset
+ * Date:		June 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ * 			echo a 0 or a 1 into perf_counter_reset to
+ * 			reset all the counters in
+ * 			/sys/fs/orangefs/perf_counters
+ * 			except ones with PINT_PERF_PRESERVE set.
+ *
+ *
+ * What:		/sys/fs/orangefs/perf_counters/...
+ * Date:		Jun 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ * 			Counters and settings for various caches.
+ * 			Read only.
+ *
+ *
+ * What:		/sys/fs/orangefs/perf_time_interval_secs
+ * Date:		Jun 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ *			Length of perf counter intervals in
+ *			seconds.
+ *
+ *
+ * What:		/sys/fs/orangefs/perf_history_size
+ * Date:		Jun 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ * 			The perf_counters cache statistics have N, or
+ * 			perf_history_size, samples. The default is
+ * 			one.
+ *
+ *			Every perf_time_interval_secs the (first)
+ *			samples are reset.
+ *
+ *			If N is greater than one, the "current" set
+ *			of samples is reset, and the samples from the
+ *			other N-1 intervals remain available.
+ *
+ *
+ * What:		/sys/fs/orangefs/op_timeout_secs
+ * Date:		Jun 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ *			Service operation timeout in seconds.
+ *
+ *
+ * What:		/sys/fs/orangefs/slot_timeout_secs
+ * Date:		Jun 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ *			"Slot" timeout in seconds. A "slot"
+ *			is an indexed buffer in the shared
+ *			memory segment used for communication
+ *			between the kernel module and userspace.
+ *			Slots are requested and waited for,
+ *			the wait times out after slot_timeout_secs.
+ *
+ *
+ * What:		/sys/fs/orangefs/acache/...
+ * Date:		Jun 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ * 			Attribute cache configurable settings.
+ *
+ *
+ * What:		/sys/fs/orangefs/ncache/...
+ * Date:		Jun 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ * 			Name cache configurable settings.
+ *
+ *
+ * What:		/sys/fs/orangefs/capcache/...
+ * Date:		Jun 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ * 			Capability cache configurable settings.
+ *
+ *
+ * What:		/sys/fs/orangefs/ccache/...
+ * Date:		Jun 2015
+ * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Description:
+ * 			Credential cache configurable settings.
+ *
+ */
+
+#include <linux/fs.h>
+#include <linux/kobject.h>
+#include <linux/string.h>
+#include <linux/sysfs.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-sysfs.h"
+
+#define ORANGEFS_KOBJ_ID "orangefs"
+#define ACACHE_KOBJ_ID "acache"
+#define CAPCACHE_KOBJ_ID "capcache"
+#define CCACHE_KOBJ_ID "ccache"
+#define NCACHE_KOBJ_ID "ncache"
+#define PC_KOBJ_ID "pc"
+#define STATS_KOBJ_ID "stats"
+
+struct orangefs_obj {
+	struct kobject kobj;
+	int op_timeout_secs;
+	int perf_counter_reset;
+	int perf_history_size;
+	int perf_time_interval_secs;
+	int slot_timeout_secs;
+};
+
+struct acache_orangefs_obj {
+	struct kobject kobj;
+	int hard_limit;
+	int reclaim_percentage;
+	int soft_limit;
+	int timeout_msecs;
+};
+
+struct capcache_orangefs_obj {
+	struct kobject kobj;
+	int hard_limit;
+	int reclaim_percentage;
+	int soft_limit;
+	int timeout_secs;
+};
+
+struct ccache_orangefs_obj {
+	struct kobject kobj;
+	int hard_limit;
+	int reclaim_percentage;
+	int soft_limit;
+	int timeout_secs;
+};
+
+struct ncache_orangefs_obj {
+	struct kobject kobj;
+	int hard_limit;
+	int reclaim_percentage;
+	int soft_limit;
+	int timeout_msecs;
+};
+
+struct pc_orangefs_obj {
+	struct kobject kobj;
+	char *acache;
+	char *capcache;
+	char *ncache;
+};
+
+struct stats_orangefs_obj {
+	struct kobject kobj;
+	int reads;
+	int writes;
+};
+
+struct orangefs_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct orangefs_obj *orangefs_obj,
+			struct orangefs_attribute *attr,
+			char *buf);
+	ssize_t (*store)(struct orangefs_obj *orangefs_obj,
+			 struct orangefs_attribute *attr,
+			 const char *buf,
+			 size_t count);
+};
+
+struct acache_orangefs_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct acache_orangefs_obj *acache_orangefs_obj,
+			struct acache_orangefs_attribute *attr,
+			char *buf);
+	ssize_t (*store)(struct acache_orangefs_obj *acache_orangefs_obj,
+			 struct acache_orangefs_attribute *attr,
+			 const char *buf,
+			 size_t count);
+};
+
+struct capcache_orangefs_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct capcache_orangefs_obj *capcache_orangefs_obj,
+			struct capcache_orangefs_attribute *attr,
+			char *buf);
+	ssize_t (*store)(struct capcache_orangefs_obj *capcache_orangefs_obj,
+			 struct capcache_orangefs_attribute *attr,
+			 const char *buf,
+			 size_t count);
+};
+
+struct ccache_orangefs_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct ccache_orangefs_obj *ccache_orangefs_obj,
+			struct ccache_orangefs_attribute *attr,
+			char *buf);
+	ssize_t (*store)(struct ccache_orangefs_obj *ccache_orangefs_obj,
+			 struct ccache_orangefs_attribute *attr,
+			 const char *buf,
+			 size_t count);
+};
+
+struct ncache_orangefs_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct ncache_orangefs_obj *ncache_orangefs_obj,
+			struct ncache_orangefs_attribute *attr,
+			char *buf);
+	ssize_t (*store)(struct ncache_orangefs_obj *ncache_orangefs_obj,
+			 struct ncache_orangefs_attribute *attr,
+			 const char *buf,
+			 size_t count);
+};
+
+struct pc_orangefs_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct pc_orangefs_obj *pc_orangefs_obj,
+			struct pc_orangefs_attribute *attr,
+			char *buf);
+	ssize_t (*store)(struct pc_orangefs_obj *pc_orangefs_obj,
+			 struct pc_orangefs_attribute *attr,
+			 const char *buf,
+			 size_t count);
+};
+
+struct stats_orangefs_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct stats_orangefs_obj *stats_orangefs_obj,
+			struct stats_orangefs_attribute *attr,
+			char *buf);
+	ssize_t (*store)(struct stats_orangefs_obj *stats_orangefs_obj,
+			 struct stats_orangefs_attribute *attr,
+			 const char *buf,
+			 size_t count);
+};
+
+static ssize_t orangefs_attr_show(struct kobject *kobj,
+				  struct attribute *attr,
+				  char *buf)
+{
+	struct orangefs_attribute *attribute;
+	struct orangefs_obj *orangefs_obj;
+	int rc;
+
+	attribute = container_of(attr, struct orangefs_attribute, attr);
+	orangefs_obj = container_of(kobj, struct orangefs_obj, kobj);
+
+	if (!attribute->show) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->show(orangefs_obj, attribute, buf);
+
+out:
+	return rc;
+}
+
+static ssize_t orangefs_attr_store(struct kobject *kobj,
+				   struct attribute *attr,
+				   const char *buf,
+				   size_t len)
+{
+	struct orangefs_attribute *attribute;
+	struct orangefs_obj *orangefs_obj;
+	int rc;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG,
+		     "orangefs_attr_store: start\n");
+
+	attribute = container_of(attr, struct orangefs_attribute, attr);
+	orangefs_obj = container_of(kobj, struct orangefs_obj, kobj);
+
+	if (!attribute->store) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->store(orangefs_obj, attribute, buf, len);
+
+out:
+	return rc;
+}
+
+static const struct sysfs_ops orangefs_sysfs_ops = {
+	.show = orangefs_attr_show,
+	.store = orangefs_attr_store,
+};
+
+static ssize_t acache_orangefs_attr_show(struct kobject *kobj,
+					 struct attribute *attr,
+					 char *buf)
+{
+	struct acache_orangefs_attribute *attribute;
+	struct acache_orangefs_obj *acache_orangefs_obj;
+	int rc;
+
+	attribute = container_of(attr, struct acache_orangefs_attribute, attr);
+	acache_orangefs_obj =
+		container_of(kobj, struct acache_orangefs_obj, kobj);
+
+	if (!attribute->show) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->show(acache_orangefs_obj, attribute, buf);
+
+out:
+	return rc;
+}
+
+static ssize_t acache_orangefs_attr_store(struct kobject *kobj,
+					  struct attribute *attr,
+					  const char *buf,
+					  size_t len)
+{
+	struct acache_orangefs_attribute *attribute;
+	struct acache_orangefs_obj *acache_orangefs_obj;
+	int rc;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG,
+		     "acache_orangefs_attr_store: start\n");
+
+	attribute = container_of(attr, struct acache_orangefs_attribute, attr);
+	acache_orangefs_obj =
+		container_of(kobj, struct acache_orangefs_obj, kobj);
+
+	if (!attribute->store) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->store(acache_orangefs_obj, attribute, buf, len);
+
+out:
+	return rc;
+}
+
+static const struct sysfs_ops acache_orangefs_sysfs_ops = {
+	.show = acache_orangefs_attr_show,
+	.store = acache_orangefs_attr_store,
+};
+
+static ssize_t capcache_orangefs_attr_show(struct kobject *kobj,
+					   struct attribute *attr,
+					   char *buf)
+{
+	struct capcache_orangefs_attribute *attribute;
+	struct capcache_orangefs_obj *capcache_orangefs_obj;
+	int rc;
+
+	attribute =
+		container_of(attr, struct capcache_orangefs_attribute, attr);
+	capcache_orangefs_obj =
+		container_of(kobj, struct capcache_orangefs_obj, kobj);
+
+	if (!attribute->show) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->show(capcache_orangefs_obj, attribute, buf);
+
+out:
+	return rc;
+}
+
+static ssize_t capcache_orangefs_attr_store(struct kobject *kobj,
+					    struct attribute *attr,
+					    const char *buf,
+					    size_t len)
+{
+	struct capcache_orangefs_attribute *attribute;
+	struct capcache_orangefs_obj *capcache_orangefs_obj;
+	int rc;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG,
+		     "capcache_orangefs_attr_store: start\n");
+
+	attribute =
+		container_of(attr, struct capcache_orangefs_attribute, attr);
+	capcache_orangefs_obj =
+		container_of(kobj, struct capcache_orangefs_obj, kobj);
+
+	if (!attribute->store) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->store(capcache_orangefs_obj, attribute, buf, len);
+
+out:
+	return rc;
+}
+
+static const struct sysfs_ops capcache_orangefs_sysfs_ops = {
+	.show = capcache_orangefs_attr_show,
+	.store = capcache_orangefs_attr_store,
+};
+
+static ssize_t ccache_orangefs_attr_show(struct kobject *kobj,
+					 struct attribute *attr,
+					 char *buf)
+{
+	struct ccache_orangefs_attribute *attribute;
+	struct ccache_orangefs_obj *ccache_orangefs_obj;
+	int rc;
+
+	attribute =
+		container_of(attr, struct ccache_orangefs_attribute, attr);
+	ccache_orangefs_obj =
+		container_of(kobj, struct ccache_orangefs_obj, kobj);
+
+	if (!attribute->show) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->show(ccache_orangefs_obj, attribute, buf);
+
+out:
+	return rc;
+}
+
+static ssize_t ccache_orangefs_attr_store(struct kobject *kobj,
+					  struct attribute *attr,
+					  const char *buf,
+					  size_t len)
+{
+	struct ccache_orangefs_attribute *attribute;
+	struct ccache_orangefs_obj *ccache_orangefs_obj;
+	int rc;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG,
+		     "ccache_orangefs_attr_store: start\n");
+
+	attribute =
+		container_of(attr, struct ccache_orangefs_attribute, attr);
+	ccache_orangefs_obj =
+		container_of(kobj, struct ccache_orangefs_obj, kobj);
+
+	if (!attribute->store) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->store(ccache_orangefs_obj, attribute, buf, len);
+
+out:
+	return rc;
+}
+
+static const struct sysfs_ops ccache_orangefs_sysfs_ops = {
+	.show = ccache_orangefs_attr_show,
+	.store = ccache_orangefs_attr_store,
+};
+
+static ssize_t ncache_orangefs_attr_show(struct kobject *kobj,
+					 struct attribute *attr,
+					 char *buf)
+{
+	struct ncache_orangefs_attribute *attribute;
+	struct ncache_orangefs_obj *ncache_orangefs_obj;
+	int rc;
+
+	attribute = container_of(attr, struct ncache_orangefs_attribute, attr);
+	ncache_orangefs_obj =
+		container_of(kobj, struct ncache_orangefs_obj, kobj);
+
+	if (!attribute->show) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->show(ncache_orangefs_obj, attribute, buf);
+
+out:
+	return rc;
+}
+
+static ssize_t ncache_orangefs_attr_store(struct kobject *kobj,
+					  struct attribute *attr,
+					  const char *buf,
+					  size_t len)
+{
+	struct ncache_orangefs_attribute *attribute;
+	struct ncache_orangefs_obj *ncache_orangefs_obj;
+	int rc;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG,
+		     "ncache_orangefs_attr_store: start\n");
+
+	attribute = container_of(attr, struct ncache_orangefs_attribute, attr);
+	ncache_orangefs_obj =
+		container_of(kobj, struct ncache_orangefs_obj, kobj);
+
+	if (!attribute->store) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->store(ncache_orangefs_obj, attribute, buf, len);
+
+out:
+	return rc;
+}
+
+static const struct sysfs_ops ncache_orangefs_sysfs_ops = {
+	.show = ncache_orangefs_attr_show,
+	.store = ncache_orangefs_attr_store,
+};
+
+static ssize_t pc_orangefs_attr_show(struct kobject *kobj,
+				     struct attribute *attr,
+				     char *buf)
+{
+	struct pc_orangefs_attribute *attribute;
+	struct pc_orangefs_obj *pc_orangefs_obj;
+	int rc;
+
+	attribute = container_of(attr, struct pc_orangefs_attribute, attr);
+	pc_orangefs_obj =
+		container_of(kobj, struct pc_orangefs_obj, kobj);
+
+	if (!attribute->show) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->show(pc_orangefs_obj, attribute, buf);
+
+out:
+	return rc;
+}
+
+static const struct sysfs_ops pc_orangefs_sysfs_ops = {
+	.show = pc_orangefs_attr_show,
+};
+
+static ssize_t stats_orangefs_attr_show(struct kobject *kobj,
+					struct attribute *attr,
+					char *buf)
+{
+	struct stats_orangefs_attribute *attribute;
+	struct stats_orangefs_obj *stats_orangefs_obj;
+	int rc;
+
+	attribute = container_of(attr, struct stats_orangefs_attribute, attr);
+	stats_orangefs_obj =
+		container_of(kobj, struct stats_orangefs_obj, kobj);
+
+	if (!attribute->show) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = attribute->show(stats_orangefs_obj, attribute, buf);
+
+out:
+	return rc;
+}
+
+static const struct sysfs_ops stats_orangefs_sysfs_ops = {
+	.show = stats_orangefs_attr_show,
+};
+
+static void orangefs_release(struct kobject *kobj)
+{
+	struct orangefs_obj *orangefs_obj;
+
+	orangefs_obj = container_of(kobj, struct orangefs_obj, kobj);
+	kfree(orangefs_obj);
+}
+
+static void acache_orangefs_release(struct kobject *kobj)
+{
+	struct acache_orangefs_obj *acache_orangefs_obj;
+
+	acache_orangefs_obj =
+		container_of(kobj, struct acache_orangefs_obj, kobj);
+	kfree(acache_orangefs_obj);
+}
+
+static void capcache_orangefs_release(struct kobject *kobj)
+{
+	struct capcache_orangefs_obj *capcache_orangefs_obj;
+
+	capcache_orangefs_obj =
+		container_of(kobj, struct capcache_orangefs_obj, kobj);
+	kfree(capcache_orangefs_obj);
+}
+
+static void ccache_orangefs_release(struct kobject *kobj)
+{
+	struct ccache_orangefs_obj *ccache_orangefs_obj;
+
+	ccache_orangefs_obj =
+		container_of(kobj, struct ccache_orangefs_obj, kobj);
+	kfree(ccache_orangefs_obj);
+}
+
+static void ncache_orangefs_release(struct kobject *kobj)
+{
+	struct ncache_orangefs_obj *ncache_orangefs_obj;
+
+	ncache_orangefs_obj =
+		container_of(kobj, struct ncache_orangefs_obj, kobj);
+	kfree(ncache_orangefs_obj);
+}
+
+static void pc_orangefs_release(struct kobject *kobj)
+{
+	struct pc_orangefs_obj *pc_orangefs_obj;
+
+	pc_orangefs_obj =
+		container_of(kobj, struct pc_orangefs_obj, kobj);
+	kfree(pc_orangefs_obj);
+}
+
+static void stats_orangefs_release(struct kobject *kobj)
+{
+	struct stats_orangefs_obj *stats_orangefs_obj;
+
+	stats_orangefs_obj =
+		container_of(kobj, struct stats_orangefs_obj, kobj);
+	kfree(stats_orangefs_obj);
+}
+
+static ssize_t sysfs_int_show(char *kobj_id, char *buf, void *attr)
+{
+	int rc = -EIO;
+	struct orangefs_attribute *orangefs_attr;
+	struct stats_orangefs_attribute *stats_orangefs_attr;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG, "sysfs_int_show: id:%s:\n", kobj_id);
+
+	if (!strcmp(kobj_id, ORANGEFS_KOBJ_ID)) {
+		orangefs_attr = (struct orangefs_attribute *)attr;
+
+		if (!strcmp(orangefs_attr->attr.name, "op_timeout_secs")) {
+			rc = scnprintf(buf,
+				       PAGE_SIZE,
+				       "%d\n",
+				       op_timeout_secs);
+			goto out;
+		} else if (!strcmp(orangefs_attr->attr.name,
+				   "slot_timeout_secs")) {
+			rc = scnprintf(buf,
+				       PAGE_SIZE,
+				       "%d\n",
+				       slot_timeout_secs);
+			goto out;
+		} else {
+			goto out;
+		}
+
+	} else if (!strcmp(kobj_id, STATS_KOBJ_ID)) {
+		stats_orangefs_attr = (struct stats_orangefs_attribute *)attr;
+
+		if (!strcmp(stats_orangefs_attr->attr.name, "reads")) {
+			rc = scnprintf(buf,
+				       PAGE_SIZE,
+				       "%lu\n",
+				       g_orangefs_stats.reads);
+			goto out;
+		} else if (!strcmp(stats_orangefs_attr->attr.name, "writes")) {
+			rc = scnprintf(buf,
+				       PAGE_SIZE,
+				       "%lu\n",
+				       g_orangefs_stats.writes);
+			goto out;
+		} else {
+			goto out;
+		}
+	}
+
+out:
+
+	return rc;
+}
+
+static ssize_t int_orangefs_show(struct orangefs_obj *orangefs_obj,
+				 struct orangefs_attribute *attr,
+				 char *buf)
+{
+	int rc;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG,
+		     "int_orangefs_show:start attr->attr.name:%s:\n",
+		     attr->attr.name);
+
+	rc = sysfs_int_show(ORANGEFS_KOBJ_ID, buf, (void *) attr);
+
+	return rc;
+}
+
+static ssize_t int_stats_show(struct stats_orangefs_obj *stats_orangefs_obj,
+			struct stats_orangefs_attribute *attr,
+			char *buf)
+{
+	int rc;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG,
+		     "int_stats_show:start attr->attr.name:%s:\n",
+		     attr->attr.name);
+
+	rc = sysfs_int_show(STATS_KOBJ_ID, buf, (void *) attr);
+
+	return rc;
+}
+
+static ssize_t int_store(struct orangefs_obj *orangefs_obj,
+			 struct orangefs_attribute *attr,
+			 const char *buf,
+			 size_t count)
+{
+	int rc = 0;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG,
+		     "int_store: start attr->attr.name:%s: buf:%s:\n",
+		     attr->attr.name, buf);
+
+	if (!strcmp(attr->attr.name, "op_timeout_secs")) {
+		rc = kstrtoint(buf, 0, &op_timeout_secs);
+		goto out;
+	} else if (!strcmp(attr->attr.name, "slot_timeout_secs")) {
+		rc = kstrtoint(buf, 0, &slot_timeout_secs);
+		goto out;
+	} else {
+		goto out;
+	}
+
+out:
+	if (rc)
+		rc = -EINVAL;
+	else
+		rc = count;
+
+	return rc;
+}
+
+/*
+ * obtain attribute values from userspace with a service operation.
+ */
+static int sysfs_service_op_show(char *kobj_id, char *buf, void *attr)
+{
+	struct orangefs_kernel_op_s *new_op = NULL;
+	int rc = 0;
+	char *ser_op_type = NULL;
+	struct orangefs_attribute *orangefs_attr;
+	struct acache_orangefs_attribute *acache_attr;
+	struct capcache_orangefs_attribute *capcache_attr;
+	struct ccache_orangefs_attribute *ccache_attr;
+	struct ncache_orangefs_attribute *ncache_attr;
+	struct pc_orangefs_attribute *pc_attr;
+	__u32 op_alloc_type;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG,
+		     "sysfs_service_op_show: id:%s:\n",
+		     kobj_id);
+
+	if (strcmp(kobj_id, PC_KOBJ_ID))
+		op_alloc_type = ORANGEFS_VFS_OP_PARAM;
+	else
+		op_alloc_type = ORANGEFS_VFS_OP_PERF_COUNT;
+
+	new_op = op_alloc(op_alloc_type);
+	if (!new_op)
+		return -ENOMEM;
+
+	/* Can't do a service_operation if the client is not running... */
+	rc = is_daemon_in_service();
+	if (rc) {
+		pr_info("%s: Client not running :%d:\n",
+			__func__,
+			is_daemon_in_service());
+		goto out;
+	}
+
+	if (strcmp(kobj_id, PC_KOBJ_ID))
+		new_op->upcall.req.param.type = ORANGEFS_PARAM_REQUEST_GET;
+
+	if (!strcmp(kobj_id, ORANGEFS_KOBJ_ID)) {
+		orangefs_attr = (struct orangefs_attribute *)attr;
+
+		if (!strcmp(orangefs_attr->attr.name, "perf_history_size"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_PERF_HISTORY_SIZE;
+		else if (!strcmp(orangefs_attr->attr.name,
+				 "perf_time_interval_secs"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_PERF_TIME_INTERVAL_SECS;
+		else if (!strcmp(orangefs_attr->attr.name,
+				 "perf_counter_reset"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_PERF_RESET;
+
+	} else if (!strcmp(kobj_id, ACACHE_KOBJ_ID)) {
+		acache_attr = (struct acache_orangefs_attribute *)attr;
+
+		if (!strcmp(acache_attr->attr.name, "timeout_msecs"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_ACACHE_TIMEOUT_MSECS;
+
+		if (!strcmp(acache_attr->attr.name, "hard_limit"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_ACACHE_HARD_LIMIT;
+
+		if (!strcmp(acache_attr->attr.name, "soft_limit"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_ACACHE_SOFT_LIMIT;
+
+		if (!strcmp(acache_attr->attr.name, "reclaim_percentage"))
+			new_op->upcall.req.param.op =
+			  ORANGEFS_PARAM_REQUEST_OP_ACACHE_RECLAIM_PERCENTAGE;
+
+	} else if (!strcmp(kobj_id, CAPCACHE_KOBJ_ID)) {
+		capcache_attr = (struct capcache_orangefs_attribute *)attr;
+
+		if (!strcmp(capcache_attr->attr.name, "timeout_secs"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_TIMEOUT_SECS;
+
+		if (!strcmp(capcache_attr->attr.name, "hard_limit"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_HARD_LIMIT;
+
+		if (!strcmp(capcache_attr->attr.name, "soft_limit"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_SOFT_LIMIT;
+
+		if (!strcmp(capcache_attr->attr.name, "reclaim_percentage"))
+			new_op->upcall.req.param.op =
+			  ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_RECLAIM_PERCENTAGE;
+
+	} else if (!strcmp(kobj_id, CCACHE_KOBJ_ID)) {
+		ccache_attr = (struct ccache_orangefs_attribute *)attr;
+
+		if (!strcmp(ccache_attr->attr.name, "timeout_secs"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_CCACHE_TIMEOUT_SECS;
+
+		if (!strcmp(ccache_attr->attr.name, "hard_limit"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_CCACHE_HARD_LIMIT;
+
+		if (!strcmp(ccache_attr->attr.name, "soft_limit"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_CCACHE_SOFT_LIMIT;
+
+		if (!strcmp(ccache_attr->attr.name, "reclaim_percentage"))
+			new_op->upcall.req.param.op =
+			  ORANGEFS_PARAM_REQUEST_OP_CCACHE_RECLAIM_PERCENTAGE;
+
+	} else if (!strcmp(kobj_id, NCACHE_KOBJ_ID)) {
+		ncache_attr = (struct ncache_orangefs_attribute *)attr;
+
+		if (!strcmp(ncache_attr->attr.name, "timeout_msecs"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_NCACHE_TIMEOUT_MSECS;
+
+		if (!strcmp(ncache_attr->attr.name, "hard_limit"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_NCACHE_HARD_LIMIT;
+
+		if (!strcmp(ncache_attr->attr.name, "soft_limit"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_NCACHE_SOFT_LIMIT;
+
+		if (!strcmp(ncache_attr->attr.name, "reclaim_percentage"))
+			new_op->upcall.req.param.op =
+			  ORANGEFS_PARAM_REQUEST_OP_NCACHE_RECLAIM_PERCENTAGE;
+
+	} else if (!strcmp(kobj_id, PC_KOBJ_ID)) {
+		pc_attr = (struct pc_orangefs_attribute *)attr;
+
+		if (!strcmp(pc_attr->attr.name, ACACHE_KOBJ_ID))
+			new_op->upcall.req.perf_count.type =
+				ORANGEFS_PERF_COUNT_REQUEST_ACACHE;
+
+		if (!strcmp(pc_attr->attr.name, CAPCACHE_KOBJ_ID))
+			new_op->upcall.req.perf_count.type =
+				ORANGEFS_PERF_COUNT_REQUEST_CAPCACHE;
+
+		if (!strcmp(pc_attr->attr.name, NCACHE_KOBJ_ID))
+			new_op->upcall.req.perf_count.type =
+				ORANGEFS_PERF_COUNT_REQUEST_NCACHE;
+
+	} else {
+		gossip_err("sysfs_service_op_show: unknown kobj_id:%s:\n",
+			   kobj_id);
+		rc = -EINVAL;
+		goto out;
+	}
+
+
+	if (strcmp(kobj_id, PC_KOBJ_ID))
+		ser_op_type = "orangefs_param";
+	else
+		ser_op_type = "orangefs_perf_count";
+
+	/*
+	 * The service_operation will return an errno return code on
+	 * error, and zero on success.
+	 */
+	rc = service_operation(new_op, ser_op_type, ORANGEFS_OP_INTERRUPTIBLE);
+
+out:
+	if (!rc) {
+		if (strcmp(kobj_id, PC_KOBJ_ID)) {
+			rc = scnprintf(buf,
+				       PAGE_SIZE,
+				       "%d\n",
+				       (int)new_op->downcall.resp.param.value);
+		} else {
+			rc = scnprintf(
+				buf,
+				PAGE_SIZE,
+				"%s",
+				new_op->downcall.resp.perf_count.buffer);
+		}
+	}
+
+	op_release(new_op);
+
+	return rc;
+
+}
+
+static ssize_t service_orangefs_show(struct orangefs_obj *orangefs_obj,
+				     struct orangefs_attribute *attr,
+				     char *buf)
+{
+	int rc = 0;
+
+	rc = sysfs_service_op_show(ORANGEFS_KOBJ_ID, buf, (void *)attr);
+
+	return rc;
+}
+
+static ssize_t
+	service_acache_show(struct acache_orangefs_obj *acache_orangefs_obj,
+			    struct acache_orangefs_attribute *attr,
+			    char *buf)
+{
+	int rc = 0;
+
+	rc = sysfs_service_op_show(ACACHE_KOBJ_ID, buf, (void *)attr);
+
+	return rc;
+}
+
+static ssize_t service_capcache_show(struct capcache_orangefs_obj
+					*capcache_orangefs_obj,
+				     struct capcache_orangefs_attribute *attr,
+				     char *buf)
+{
+	int rc = 0;
+
+	rc = sysfs_service_op_show(CAPCACHE_KOBJ_ID, buf, (void *)attr);
+
+	return rc;
+}
+
+static ssize_t service_ccache_show(struct ccache_orangefs_obj
+					*ccache_orangefs_obj,
+				   struct ccache_orangefs_attribute *attr,
+				   char *buf)
+{
+	int rc = 0;
+
+	rc = sysfs_service_op_show(CCACHE_KOBJ_ID, buf, (void *)attr);
+
+	return rc;
+}
+
+static ssize_t
+	service_ncache_show(struct ncache_orangefs_obj *ncache_orangefs_obj,
+			    struct ncache_orangefs_attribute *attr,
+			    char *buf)
+{
+	int rc = 0;
+
+	rc = sysfs_service_op_show(NCACHE_KOBJ_ID, buf, (void *)attr);
+
+	return rc;
+}
+
+static ssize_t
+	service_pc_show(struct pc_orangefs_obj *pc_orangefs_obj,
+			    struct pc_orangefs_attribute *attr,
+			    char *buf)
+{
+	int rc = 0;
+
+	rc = sysfs_service_op_show(PC_KOBJ_ID, buf, (void *)attr);
+
+	return rc;
+}
+
+/*
+ * pass attribute values back to userspace with a service operation.
+ *
+ * We have to do a memory allocation, an sscanf and a service operation.
+ * And we have to evaluate what the user entered, to make sure the
+ * value is within the range supported by the attribute. So, there's
+ * a lot of return code checking and mapping going on here.
+ *
+ * We want to return 1 if we think everything went OK, and
+ * EINVAL if not.
+ */
+static int sysfs_service_op_store(char *kobj_id, const char *buf, void *attr)
+{
+	struct orangefs_kernel_op_s *new_op = NULL;
+	int val = 0;
+	int rc = 0;
+	struct orangefs_attribute *orangefs_attr;
+	struct acache_orangefs_attribute *acache_attr;
+	struct capcache_orangefs_attribute *capcache_attr;
+	struct ccache_orangefs_attribute *ccache_attr;
+	struct ncache_orangefs_attribute *ncache_attr;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG,
+		     "sysfs_service_op_store: id:%s:\n",
+		     kobj_id);
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_PARAM);
+	if (!new_op)
+		return -EINVAL; /* sic */
+
+	/* Can't do a service_operation if the client is not running... */
+	rc = is_daemon_in_service();
+	if (rc) {
+		pr_info("%s: Client not running :%d:\n",
+			__func__,
+			is_daemon_in_service());
+		goto out;
+	}
+
+	/*
+	 * The value we want to send back to userspace is in buf.
+	 */
+	rc = kstrtoint(buf, 0, &val);
+	if (rc)
+		goto out;
+
+	if (!strcmp(kobj_id, ORANGEFS_KOBJ_ID)) {
+		orangefs_attr = (struct orangefs_attribute *)attr;
+
+		if (!strcmp(orangefs_attr->attr.name, "perf_history_size")) {
+			if (val > 0) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_PERF_HISTORY_SIZE;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(orangefs_attr->attr.name,
+				   "perf_time_interval_secs")) {
+			if (val > 0) {
+				new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_PERF_TIME_INTERVAL_SECS;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(orangefs_attr->attr.name,
+				   "perf_counter_reset")) {
+			if ((val == 0) || (val == 1)) {
+				new_op->upcall.req.param.op =
+					ORANGEFS_PARAM_REQUEST_OP_PERF_RESET;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		}
+
+	} else if (!strcmp(kobj_id, ACACHE_KOBJ_ID)) {
+		acache_attr = (struct acache_orangefs_attribute *)attr;
+
+		if (!strcmp(acache_attr->attr.name, "hard_limit")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_ACACHE_HARD_LIMIT;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(acache_attr->attr.name, "soft_limit")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_ACACHE_SOFT_LIMIT;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(acache_attr->attr.name,
+				   "reclaim_percentage")) {
+			if ((val > -1) && (val < 101)) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_ACACHE_RECLAIM_PERCENTAGE;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(acache_attr->attr.name, "timeout_msecs")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_ACACHE_TIMEOUT_MSECS;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		}
+
+	} else if (!strcmp(kobj_id, CAPCACHE_KOBJ_ID)) {
+		capcache_attr = (struct capcache_orangefs_attribute *)attr;
+
+		if (!strcmp(capcache_attr->attr.name, "hard_limit")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_HARD_LIMIT;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(capcache_attr->attr.name, "soft_limit")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_SOFT_LIMIT;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(capcache_attr->attr.name,
+				   "reclaim_percentage")) {
+			if ((val > -1) && (val < 101)) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_RECLAIM_PERCENTAGE;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(capcache_attr->attr.name, "timeout_secs")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_TIMEOUT_SECS;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		}
+
+	} else if (!strcmp(kobj_id, CCACHE_KOBJ_ID)) {
+		ccache_attr = (struct ccache_orangefs_attribute *)attr;
+
+		if (!strcmp(ccache_attr->attr.name, "hard_limit")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_CCACHE_HARD_LIMIT;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(ccache_attr->attr.name, "soft_limit")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_CCACHE_SOFT_LIMIT;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(ccache_attr->attr.name,
+				   "reclaim_percentage")) {
+			if ((val > -1) && (val < 101)) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_CCACHE_RECLAIM_PERCENTAGE;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(ccache_attr->attr.name, "timeout_secs")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_CCACHE_TIMEOUT_SECS;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		}
+
+	} else if (!strcmp(kobj_id, NCACHE_KOBJ_ID)) {
+		ncache_attr = (struct ncache_orangefs_attribute *)attr;
+
+		if (!strcmp(ncache_attr->attr.name, "hard_limit")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_NCACHE_HARD_LIMIT;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(ncache_attr->attr.name, "soft_limit")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_NCACHE_SOFT_LIMIT;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(ncache_attr->attr.name,
+				   "reclaim_percentage")) {
+			if ((val > -1) && (val < 101)) {
+				new_op->upcall.req.param.op =
+					ORANGEFS_PARAM_REQUEST_OP_NCACHE_RECLAIM_PERCENTAGE;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		} else if (!strcmp(ncache_attr->attr.name, "timeout_msecs")) {
+			if (val > -1) {
+				new_op->upcall.req.param.op =
+				  ORANGEFS_PARAM_REQUEST_OP_NCACHE_TIMEOUT_MSECS;
+			} else {
+				rc = 0;
+				goto out;
+			}
+		}
+
+	} else {
+		gossip_err("sysfs_service_op_store: unknown kobj_id:%s:\n",
+			   kobj_id);
+		rc = -EINVAL;
+		goto out;
+	}
+
+	new_op->upcall.req.param.type = ORANGEFS_PARAM_REQUEST_SET;
+
+	new_op->upcall.req.param.value = val;
+
+	/*
+	 * The service_operation will return a errno return code on
+	 * error, and zero on success.
+	 */
+	rc = service_operation(new_op, "orangefs_param", ORANGEFS_OP_INTERRUPTIBLE);
+
+	if (rc < 0) {
+		gossip_err("sysfs_service_op_store: service op returned:%d:\n",
+			rc);
+		rc = 0;
+	} else {
+		rc = 1;
+	}
+
+out:
+	op_release(new_op);
+
+	if (rc == -ENOMEM || rc == 0)
+		rc = -EINVAL;
+
+	return rc;
+}
+
+static ssize_t
+	service_orangefs_store(struct orangefs_obj *orangefs_obj,
+			       struct orangefs_attribute *attr,
+			       const char *buf,
+			       size_t count)
+{
+	int rc = 0;
+
+	rc = sysfs_service_op_store(ORANGEFS_KOBJ_ID, buf, (void *) attr);
+
+	/* rc should have an errno value if the service_op went bad. */
+	if (rc == 1)
+		rc = count;
+
+	return rc;
+}
+
+static ssize_t
+	service_acache_store(struct acache_orangefs_obj *acache_orangefs_obj,
+			     struct acache_orangefs_attribute *attr,
+			     const char *buf,
+			     size_t count)
+{
+	int rc = 0;
+
+	rc = sysfs_service_op_store(ACACHE_KOBJ_ID, buf, (void *) attr);
+
+	/* rc should have an errno value if the service_op went bad. */
+	if (rc == 1)
+		rc = count;
+
+	return rc;
+}
+
+static ssize_t
+	service_capcache_store(struct capcache_orangefs_obj
+				*capcache_orangefs_obj,
+			       struct capcache_orangefs_attribute *attr,
+			       const char *buf,
+			       size_t count)
+{
+	int rc = 0;
+
+	rc = sysfs_service_op_store(CAPCACHE_KOBJ_ID, buf, (void *) attr);
+
+	/* rc should have an errno value if the service_op went bad. */
+	if (rc == 1)
+		rc = count;
+
+	return rc;
+}
+
+static ssize_t service_ccache_store(struct ccache_orangefs_obj
+					*ccache_orangefs_obj,
+				    struct ccache_orangefs_attribute *attr,
+				    const char *buf,
+				    size_t count)
+{
+	int rc = 0;
+
+	rc = sysfs_service_op_store(CCACHE_KOBJ_ID, buf, (void *) attr);
+
+	/* rc should have an errno value if the service_op went bad. */
+	if (rc == 1)
+		rc = count;
+
+	return rc;
+}
+
+static ssize_t
+	service_ncache_store(struct ncache_orangefs_obj *ncache_orangefs_obj,
+			     struct ncache_orangefs_attribute *attr,
+			     const char *buf,
+			     size_t count)
+{
+	int rc = 0;
+
+	rc = sysfs_service_op_store(NCACHE_KOBJ_ID, buf, (void *) attr);
+
+	/* rc should have an errno value if the service_op went bad. */
+	if (rc == 1)
+		rc = count;
+
+	return rc;
+}
+
+static struct orangefs_attribute op_timeout_secs_attribute =
+	__ATTR(op_timeout_secs, 0664, int_orangefs_show, int_store);
+
+static struct orangefs_attribute slot_timeout_secs_attribute =
+	__ATTR(slot_timeout_secs, 0664, int_orangefs_show, int_store);
+
+static struct orangefs_attribute perf_counter_reset_attribute =
+	__ATTR(perf_counter_reset,
+	       0664,
+	       service_orangefs_show,
+	       service_orangefs_store);
+
+static struct orangefs_attribute perf_history_size_attribute =
+	__ATTR(perf_history_size,
+	       0664,
+	       service_orangefs_show,
+	       service_orangefs_store);
+
+static struct orangefs_attribute perf_time_interval_secs_attribute =
+	__ATTR(perf_time_interval_secs,
+	       0664,
+	       service_orangefs_show,
+	       service_orangefs_store);
+
+static struct attribute *orangefs_default_attrs[] = {
+	&op_timeout_secs_attribute.attr,
+	&slot_timeout_secs_attribute.attr,
+	&perf_counter_reset_attribute.attr,
+	&perf_history_size_attribute.attr,
+	&perf_time_interval_secs_attribute.attr,
+	NULL,
+};
+
+static struct kobj_type orangefs_ktype = {
+	.sysfs_ops = &orangefs_sysfs_ops,
+	.release = orangefs_release,
+	.default_attrs = orangefs_default_attrs,
+};
+
+static struct acache_orangefs_attribute acache_hard_limit_attribute =
+	__ATTR(hard_limit,
+	       0664,
+	       service_acache_show,
+	       service_acache_store);
+
+static struct acache_orangefs_attribute acache_reclaim_percent_attribute =
+	__ATTR(reclaim_percentage,
+	       0664,
+	       service_acache_show,
+	       service_acache_store);
+
+static struct acache_orangefs_attribute acache_soft_limit_attribute =
+	__ATTR(soft_limit,
+	       0664,
+	       service_acache_show,
+	       service_acache_store);
+
+static struct acache_orangefs_attribute acache_timeout_msecs_attribute =
+	__ATTR(timeout_msecs,
+	       0664,
+	       service_acache_show,
+	       service_acache_store);
+
+static struct attribute *acache_orangefs_default_attrs[] = {
+	&acache_hard_limit_attribute.attr,
+	&acache_reclaim_percent_attribute.attr,
+	&acache_soft_limit_attribute.attr,
+	&acache_timeout_msecs_attribute.attr,
+	NULL,
+};
+
+static struct kobj_type acache_orangefs_ktype = {
+	.sysfs_ops = &acache_orangefs_sysfs_ops,
+	.release = acache_orangefs_release,
+	.default_attrs = acache_orangefs_default_attrs,
+};
+
+static struct capcache_orangefs_attribute capcache_hard_limit_attribute =
+	__ATTR(hard_limit,
+	       0664,
+	       service_capcache_show,
+	       service_capcache_store);
+
+static struct capcache_orangefs_attribute capcache_reclaim_percent_attribute =
+	__ATTR(reclaim_percentage,
+	       0664,
+	       service_capcache_show,
+	       service_capcache_store);
+
+static struct capcache_orangefs_attribute capcache_soft_limit_attribute =
+	__ATTR(soft_limit,
+	       0664,
+	       service_capcache_show,
+	       service_capcache_store);
+
+static struct capcache_orangefs_attribute capcache_timeout_secs_attribute =
+	__ATTR(timeout_secs,
+	       0664,
+	       service_capcache_show,
+	       service_capcache_store);
+
+static struct attribute *capcache_orangefs_default_attrs[] = {
+	&capcache_hard_limit_attribute.attr,
+	&capcache_reclaim_percent_attribute.attr,
+	&capcache_soft_limit_attribute.attr,
+	&capcache_timeout_secs_attribute.attr,
+	NULL,
+};
+
+static struct kobj_type capcache_orangefs_ktype = {
+	.sysfs_ops = &capcache_orangefs_sysfs_ops,
+	.release = capcache_orangefs_release,
+	.default_attrs = capcache_orangefs_default_attrs,
+};
+
+static struct ccache_orangefs_attribute ccache_hard_limit_attribute =
+	__ATTR(hard_limit,
+	       0664,
+	       service_ccache_show,
+	       service_ccache_store);
+
+static struct ccache_orangefs_attribute ccache_reclaim_percent_attribute =
+	__ATTR(reclaim_percentage,
+	       0664,
+	       service_ccache_show,
+	       service_ccache_store);
+
+static struct ccache_orangefs_attribute ccache_soft_limit_attribute =
+	__ATTR(soft_limit,
+	       0664,
+	       service_ccache_show,
+	       service_ccache_store);
+
+static struct ccache_orangefs_attribute ccache_timeout_secs_attribute =
+	__ATTR(timeout_secs,
+	       0664,
+	       service_ccache_show,
+	       service_ccache_store);
+
+static struct attribute *ccache_orangefs_default_attrs[] = {
+	&ccache_hard_limit_attribute.attr,
+	&ccache_reclaim_percent_attribute.attr,
+	&ccache_soft_limit_attribute.attr,
+	&ccache_timeout_secs_attribute.attr,
+	NULL,
+};
+
+static struct kobj_type ccache_orangefs_ktype = {
+	.sysfs_ops = &ccache_orangefs_sysfs_ops,
+	.release = ccache_orangefs_release,
+	.default_attrs = ccache_orangefs_default_attrs,
+};
+
+static struct ncache_orangefs_attribute ncache_hard_limit_attribute =
+	__ATTR(hard_limit,
+	       0664,
+	       service_ncache_show,
+	       service_ncache_store);
+
+static struct ncache_orangefs_attribute ncache_reclaim_percent_attribute =
+	__ATTR(reclaim_percentage,
+	       0664,
+	       service_ncache_show,
+	       service_ncache_store);
+
+static struct ncache_orangefs_attribute ncache_soft_limit_attribute =
+	__ATTR(soft_limit,
+	       0664,
+	       service_ncache_show,
+	       service_ncache_store);
+
+static struct ncache_orangefs_attribute ncache_timeout_msecs_attribute =
+	__ATTR(timeout_msecs,
+	       0664,
+	       service_ncache_show,
+	       service_ncache_store);
+
+static struct attribute *ncache_orangefs_default_attrs[] = {
+	&ncache_hard_limit_attribute.attr,
+	&ncache_reclaim_percent_attribute.attr,
+	&ncache_soft_limit_attribute.attr,
+	&ncache_timeout_msecs_attribute.attr,
+	NULL,
+};
+
+static struct kobj_type ncache_orangefs_ktype = {
+	.sysfs_ops = &ncache_orangefs_sysfs_ops,
+	.release = ncache_orangefs_release,
+	.default_attrs = ncache_orangefs_default_attrs,
+};
+
+static struct pc_orangefs_attribute pc_acache_attribute =
+	__ATTR(acache,
+	       0664,
+	       service_pc_show,
+	       NULL);
+
+static struct pc_orangefs_attribute pc_capcache_attribute =
+	__ATTR(capcache,
+	       0664,
+	       service_pc_show,
+	       NULL);
+
+static struct pc_orangefs_attribute pc_ncache_attribute =
+	__ATTR(ncache,
+	       0664,
+	       service_pc_show,
+	       NULL);
+
+static struct attribute *pc_orangefs_default_attrs[] = {
+	&pc_acache_attribute.attr,
+	&pc_capcache_attribute.attr,
+	&pc_ncache_attribute.attr,
+	NULL,
+};
+
+static struct kobj_type pc_orangefs_ktype = {
+	.sysfs_ops = &pc_orangefs_sysfs_ops,
+	.release = pc_orangefs_release,
+	.default_attrs = pc_orangefs_default_attrs,
+};
+
+static struct stats_orangefs_attribute stats_reads_attribute =
+	__ATTR(reads,
+	       0664,
+	       int_stats_show,
+	       NULL);
+
+static struct stats_orangefs_attribute stats_writes_attribute =
+	__ATTR(writes,
+	       0664,
+	       int_stats_show,
+	       NULL);
+
+static struct attribute *stats_orangefs_default_attrs[] = {
+	&stats_reads_attribute.attr,
+	&stats_writes_attribute.attr,
+	NULL,
+};
+
+static struct kobj_type stats_orangefs_ktype = {
+	.sysfs_ops = &stats_orangefs_sysfs_ops,
+	.release = stats_orangefs_release,
+	.default_attrs = stats_orangefs_default_attrs,
+};
+
+static struct orangefs_obj *orangefs_obj;
+static struct acache_orangefs_obj *acache_orangefs_obj;
+static struct capcache_orangefs_obj *capcache_orangefs_obj;
+static struct ccache_orangefs_obj *ccache_orangefs_obj;
+static struct ncache_orangefs_obj *ncache_orangefs_obj;
+static struct pc_orangefs_obj *pc_orangefs_obj;
+static struct stats_orangefs_obj *stats_orangefs_obj;
+
+int orangefs_sysfs_init(void)
+{
+	int rc = -EINVAL;
+
+	gossip_debug(GOSSIP_SYSFS_DEBUG, "orangefs_sysfs_init: start\n");
+
+	/* create /sys/fs/orangefs. */
+	orangefs_obj = kzalloc(sizeof(*orangefs_obj), GFP_KERNEL);
+	if (!orangefs_obj)
+		goto out;
+
+	rc = kobject_init_and_add(&orangefs_obj->kobj,
+				  &orangefs_ktype,
+				  fs_kobj,
+				  ORANGEFS_KOBJ_ID);
+
+	if (rc)
+		goto ofs_obj_bail;
+
+	kobject_uevent(&orangefs_obj->kobj, KOBJ_ADD);
+
+	/* create /sys/fs/orangefs/acache. */
+	acache_orangefs_obj = kzalloc(sizeof(*acache_orangefs_obj), GFP_KERNEL);
+	if (!acache_orangefs_obj) {
+		rc = -EINVAL;
+		goto ofs_obj_bail;
+	}
+
+	rc = kobject_init_and_add(&acache_orangefs_obj->kobj,
+				  &acache_orangefs_ktype,
+				  &orangefs_obj->kobj,
+				  ACACHE_KOBJ_ID);
+
+	if (rc)
+		goto acache_obj_bail;
+
+	kobject_uevent(&acache_orangefs_obj->kobj, KOBJ_ADD);
+
+	/* create /sys/fs/orangefs/capcache. */
+	capcache_orangefs_obj =
+		kzalloc(sizeof(*capcache_orangefs_obj), GFP_KERNEL);
+	if (!capcache_orangefs_obj) {
+		rc = -EINVAL;
+		goto acache_obj_bail;
+	}
+
+	rc = kobject_init_and_add(&capcache_orangefs_obj->kobj,
+				  &capcache_orangefs_ktype,
+				  &orangefs_obj->kobj,
+				  CAPCACHE_KOBJ_ID);
+	if (rc)
+		goto capcache_obj_bail;
+
+	kobject_uevent(&capcache_orangefs_obj->kobj, KOBJ_ADD);
+
+	/* create /sys/fs/orangefs/ccache. */
+	ccache_orangefs_obj =
+		kzalloc(sizeof(*ccache_orangefs_obj), GFP_KERNEL);
+	if (!ccache_orangefs_obj) {
+		rc = -EINVAL;
+		goto capcache_obj_bail;
+	}
+
+	rc = kobject_init_and_add(&ccache_orangefs_obj->kobj,
+				  &ccache_orangefs_ktype,
+				  &orangefs_obj->kobj,
+				  CCACHE_KOBJ_ID);
+	if (rc)
+		goto ccache_obj_bail;
+
+	kobject_uevent(&ccache_orangefs_obj->kobj, KOBJ_ADD);
+
+	/* create /sys/fs/orangefs/ncache. */
+	ncache_orangefs_obj = kzalloc(sizeof(*ncache_orangefs_obj), GFP_KERNEL);
+	if (!ncache_orangefs_obj) {
+		rc = -EINVAL;
+		goto ccache_obj_bail;
+	}
+
+	rc = kobject_init_and_add(&ncache_orangefs_obj->kobj,
+				  &ncache_orangefs_ktype,
+				  &orangefs_obj->kobj,
+				  NCACHE_KOBJ_ID);
+
+	if (rc)
+		goto ncache_obj_bail;
+
+	kobject_uevent(&ncache_orangefs_obj->kobj, KOBJ_ADD);
+
+	/* create /sys/fs/orangefs/perf_counters. */
+	pc_orangefs_obj = kzalloc(sizeof(*pc_orangefs_obj), GFP_KERNEL);
+	if (!pc_orangefs_obj) {
+		rc = -EINVAL;
+		goto ncache_obj_bail;
+	}
+
+	rc = kobject_init_and_add(&pc_orangefs_obj->kobj,
+				  &pc_orangefs_ktype,
+				  &orangefs_obj->kobj,
+				  "perf_counters");
+
+	if (rc)
+		goto pc_obj_bail;
+
+	kobject_uevent(&pc_orangefs_obj->kobj, KOBJ_ADD);
+
+	/* create /sys/fs/orangefs/stats. */
+	stats_orangefs_obj = kzalloc(sizeof(*stats_orangefs_obj), GFP_KERNEL);
+	if (!stats_orangefs_obj) {
+		rc = -EINVAL;
+		goto pc_obj_bail;
+	}
+
+	rc = kobject_init_and_add(&stats_orangefs_obj->kobj,
+				  &stats_orangefs_ktype,
+				  &orangefs_obj->kobj,
+				  STATS_KOBJ_ID);
+
+	if (rc)
+		goto stats_obj_bail;
+
+	kobject_uevent(&stats_orangefs_obj->kobj, KOBJ_ADD);
+	goto out;
+
+stats_obj_bail:
+		kobject_put(&stats_orangefs_obj->kobj);
+
+pc_obj_bail:
+		kobject_put(&pc_orangefs_obj->kobj);
+
+ncache_obj_bail:
+		kobject_put(&ncache_orangefs_obj->kobj);
+
+ccache_obj_bail:
+		kobject_put(&ccache_orangefs_obj->kobj);
+
+capcache_obj_bail:
+		kobject_put(&capcache_orangefs_obj->kobj);
+
+acache_obj_bail:
+		kobject_put(&acache_orangefs_obj->kobj);
+
+ofs_obj_bail:
+		kobject_put(&orangefs_obj->kobj);
+out:
+	return rc;
+}
+
+void orangefs_sysfs_exit(void)
+{
+	gossip_debug(GOSSIP_SYSFS_DEBUG, "orangefs_sysfs_exit: start\n");
+
+	kobject_put(&acache_orangefs_obj->kobj);
+	kobject_put(&capcache_orangefs_obj->kobj);
+	kobject_put(&ccache_orangefs_obj->kobj);
+	kobject_put(&ncache_orangefs_obj->kobj);
+	kobject_put(&pc_orangefs_obj->kobj);
+	kobject_put(&stats_orangefs_obj->kobj);
+
+	kobject_put(&orangefs_obj->kobj);
+}
diff --git a/fs/orangefs/orangefs-sysfs.h b/fs/orangefs/orangefs-sysfs.h
new file mode 100644
index 000000000000..f0b76382db02
--- /dev/null
+++ b/fs/orangefs/orangefs-sysfs.h
@@ -0,0 +1,2 @@
+extern int orangefs_sysfs_init(void);
+extern void orangefs_sysfs_exit(void);
diff --git a/fs/orangefs/orangefs-utils.c b/fs/orangefs/orangefs-utils.c
new file mode 100644
index 000000000000..2d129b5886ee
--- /dev/null
+++ b/fs/orangefs/orangefs-utils.c
@@ -0,0 +1,1052 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-dev-proto.h"
+#include "orangefs-bufmap.h"
+
+__s32 fsid_of_op(struct orangefs_kernel_op_s *op)
+{
+	__s32 fsid = ORANGEFS_FS_ID_NULL;
+
+	if (op) {
+		switch (op->upcall.type) {
+		case ORANGEFS_VFS_OP_FILE_IO:
+			fsid = op->upcall.req.io.refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_LOOKUP:
+			fsid = op->upcall.req.lookup.parent_refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_CREATE:
+			fsid = op->upcall.req.create.parent_refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_GETATTR:
+			fsid = op->upcall.req.getattr.refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_REMOVE:
+			fsid = op->upcall.req.remove.parent_refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_MKDIR:
+			fsid = op->upcall.req.mkdir.parent_refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_READDIR:
+			fsid = op->upcall.req.readdir.refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_SETATTR:
+			fsid = op->upcall.req.setattr.refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_SYMLINK:
+			fsid = op->upcall.req.sym.parent_refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_RENAME:
+			fsid = op->upcall.req.rename.old_parent_refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_STATFS:
+			fsid = op->upcall.req.statfs.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_TRUNCATE:
+			fsid = op->upcall.req.truncate.refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_MMAP_RA_FLUSH:
+			fsid = op->upcall.req.ra_cache_flush.refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_FS_UMOUNT:
+			fsid = op->upcall.req.fs_umount.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_GETXATTR:
+			fsid = op->upcall.req.getxattr.refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_SETXATTR:
+			fsid = op->upcall.req.setxattr.refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_LISTXATTR:
+			fsid = op->upcall.req.listxattr.refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_REMOVEXATTR:
+			fsid = op->upcall.req.removexattr.refn.fs_id;
+			break;
+		case ORANGEFS_VFS_OP_FSYNC:
+			fsid = op->upcall.req.fsync.refn.fs_id;
+			break;
+		default:
+			break;
+		}
+	}
+	return fsid;
+}
+
+static int orangefs_inode_flags(struct ORANGEFS_sys_attr_s *attrs)
+{
+	int flags = 0;
+	if (attrs->flags & ORANGEFS_IMMUTABLE_FL)
+		flags |= S_IMMUTABLE;
+	else
+		flags &= ~S_IMMUTABLE;
+	if (attrs->flags & ORANGEFS_APPEND_FL)
+		flags |= S_APPEND;
+	else
+		flags &= ~S_APPEND;
+	if (attrs->flags & ORANGEFS_NOATIME_FL)
+		flags |= S_NOATIME;
+	else
+		flags &= ~S_NOATIME;
+	return flags;
+}
+
+static int orangefs_inode_perms(struct ORANGEFS_sys_attr_s *attrs)
+{
+	int perm_mode = 0;
+
+	if (attrs->perms & ORANGEFS_O_EXECUTE)
+		perm_mode |= S_IXOTH;
+	if (attrs->perms & ORANGEFS_O_WRITE)
+		perm_mode |= S_IWOTH;
+	if (attrs->perms & ORANGEFS_O_READ)
+		perm_mode |= S_IROTH;
+
+	if (attrs->perms & ORANGEFS_G_EXECUTE)
+		perm_mode |= S_IXGRP;
+	if (attrs->perms & ORANGEFS_G_WRITE)
+		perm_mode |= S_IWGRP;
+	if (attrs->perms & ORANGEFS_G_READ)
+		perm_mode |= S_IRGRP;
+
+	if (attrs->perms & ORANGEFS_U_EXECUTE)
+		perm_mode |= S_IXUSR;
+	if (attrs->perms & ORANGEFS_U_WRITE)
+		perm_mode |= S_IWUSR;
+	if (attrs->perms & ORANGEFS_U_READ)
+		perm_mode |= S_IRUSR;
+
+	if (attrs->perms & ORANGEFS_G_SGID)
+		perm_mode |= S_ISGID;
+	if (attrs->perms & ORANGEFS_U_SUID)
+		perm_mode |= S_ISUID;
+
+	return perm_mode;
+}
+
+/*
+ * NOTE: in kernel land, we never use the sys_attr->link_target for
+ * anything, so don't bother copying it into the sys_attr object here.
+ */
+static inline int copy_attributes_from_inode(struct inode *inode,
+					     struct ORANGEFS_sys_attr_s *attrs,
+					     struct iattr *iattr)
+{
+	umode_t tmp_mode;
+
+	if (!iattr || !inode || !attrs) {
+		gossip_err("NULL iattr (%p), inode (%p), attrs (%p) "
+			   "in copy_attributes_from_inode!\n",
+			   iattr,
+			   inode,
+			   attrs);
+		return -EINVAL;
+	}
+	/*
+	 * We need to be careful to only copy the attributes out of the
+	 * iattr object that we know are valid.
+	 */
+	attrs->mask = 0;
+	if (iattr->ia_valid & ATTR_UID) {
+		attrs->owner = from_kuid(current_user_ns(), iattr->ia_uid);
+		attrs->mask |= ORANGEFS_ATTR_SYS_UID;
+		gossip_debug(GOSSIP_UTILS_DEBUG, "(UID) %d\n", attrs->owner);
+	}
+	if (iattr->ia_valid & ATTR_GID) {
+		attrs->group = from_kgid(current_user_ns(), iattr->ia_gid);
+		attrs->mask |= ORANGEFS_ATTR_SYS_GID;
+		gossip_debug(GOSSIP_UTILS_DEBUG, "(GID) %d\n", attrs->group);
+	}
+
+	if (iattr->ia_valid & ATTR_ATIME) {
+		attrs->mask |= ORANGEFS_ATTR_SYS_ATIME;
+		if (iattr->ia_valid & ATTR_ATIME_SET) {
+			attrs->atime = (time64_t)iattr->ia_atime.tv_sec;
+			attrs->mask |= ORANGEFS_ATTR_SYS_ATIME_SET;
+		}
+	}
+	if (iattr->ia_valid & ATTR_MTIME) {
+		attrs->mask |= ORANGEFS_ATTR_SYS_MTIME;
+		if (iattr->ia_valid & ATTR_MTIME_SET) {
+			attrs->mtime = (time64_t)iattr->ia_mtime.tv_sec;
+			attrs->mask |= ORANGEFS_ATTR_SYS_MTIME_SET;
+		}
+	}
+	if (iattr->ia_valid & ATTR_CTIME)
+		attrs->mask |= ORANGEFS_ATTR_SYS_CTIME;
+
+	/*
+	 * ORANGEFS cannot set size with a setattr operation.  Probably not likely
+	 * to be requested through the VFS, but just in case, don't worry about
+	 * ATTR_SIZE
+	 */
+
+	if (iattr->ia_valid & ATTR_MODE) {
+		tmp_mode = iattr->ia_mode;
+		if (tmp_mode & (S_ISVTX)) {
+			if (is_root_handle(inode)) {
+				/*
+				 * allow sticky bit to be set on root (since
+				 * it shows up that way by default anyhow),
+				 * but don't show it to the server
+				 */
+				tmp_mode -= S_ISVTX;
+			} else {
+				gossip_debug(GOSSIP_UTILS_DEBUG,
+					     "User attempted to set sticky bit on non-root directory; returning EINVAL.\n");
+				return -EINVAL;
+			}
+		}
+
+		if (tmp_mode & (S_ISUID)) {
+			gossip_debug(GOSSIP_UTILS_DEBUG,
+				     "Attempting to set setuid bit (not supported); returning EINVAL.\n");
+			return -EINVAL;
+		}
+
+		attrs->perms = ORANGEFS_util_translate_mode(tmp_mode);
+		attrs->mask |= ORANGEFS_ATTR_SYS_PERM;
+	}
+
+	return 0;
+}
+
+static int orangefs_inode_type(enum orangefs_ds_type objtype)
+{
+	if (objtype == ORANGEFS_TYPE_METAFILE)
+		return S_IFREG;
+	else if (objtype == ORANGEFS_TYPE_DIRECTORY)
+		return S_IFDIR;
+	else if (objtype == ORANGEFS_TYPE_SYMLINK)
+		return S_IFLNK;
+	else
+		return -1;
+}
+
+static int orangefs_inode_is_stale(struct inode *inode, int new,
+    struct ORANGEFS_sys_attr_s *attrs, char *link_target)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	int type = orangefs_inode_type(attrs->objtype);
+	if (!new) {
+		/*
+		 * If the inode type or symlink target have changed then this
+		 * inode is stale.
+		 */
+		if (type == -1 || !(inode->i_mode & type)) {
+			orangefs_make_bad_inode(inode);
+			return 1;
+		}
+		if (type == S_IFLNK && strncmp(orangefs_inode->link_target,
+		    link_target, ORANGEFS_NAME_MAX)) {
+			orangefs_make_bad_inode(inode);
+			return 1;
+		}
+	}
+	return 0;
+}
+
+int orangefs_inode_getattr(struct inode *inode, int new, int size)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	struct orangefs_kernel_op_s *new_op;
+	loff_t inode_size, rounded_up_size;
+	int ret, type;
+
+	gossip_debug(GOSSIP_UTILS_DEBUG, "%s: called on inode %pU\n", __func__,
+	    get_khandle_from_ino(inode));
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_GETATTR);
+	if (!new_op)
+		return -ENOMEM;
+	new_op->upcall.req.getattr.refn = orangefs_inode->refn;
+	new_op->upcall.req.getattr.mask = size ?
+	    ORANGEFS_ATTR_SYS_ALL_NOHINT : ORANGEFS_ATTR_SYS_ALL_NOHINT_NOSIZE;
+
+	ret = service_operation(new_op, __func__,
+	    get_interruptible_flag(inode));
+	if (ret != 0)
+		goto out;
+
+	type = orangefs_inode_type(new_op->
+	    downcall.resp.getattr.attributes.objtype);
+	ret = orangefs_inode_is_stale(inode, new,
+	    &new_op->downcall.resp.getattr.attributes,
+	    new_op->downcall.resp.getattr.link_target);
+	if (ret) {
+		ret = -ESTALE;
+		goto out;
+	}
+
+	switch (type) {
+	case S_IFREG:
+		inode->i_flags = orangefs_inode_flags(&new_op->
+		    downcall.resp.getattr.attributes);
+		if (size) {
+			inode_size = (loff_t)new_op->
+			    downcall.resp.getattr.attributes.size;
+			rounded_up_size =
+			    (inode_size + (4096 - (inode_size % 4096)));
+			inode->i_size = inode_size;
+			orangefs_inode->blksize =
+			    new_op->downcall.resp.getattr.attributes.blksize;
+			spin_lock(&inode->i_lock);
+			inode->i_bytes = inode_size;
+			inode->i_blocks =
+			    (unsigned long)(rounded_up_size / 512);
+			spin_unlock(&inode->i_lock);
+		}
+		break;
+	case S_IFDIR:
+		inode->i_size = PAGE_SIZE;
+		orangefs_inode->blksize = (1 << inode->i_blkbits);
+		spin_lock(&inode->i_lock);
+		inode_set_bytes(inode, inode->i_size);
+		spin_unlock(&inode->i_lock);
+		set_nlink(inode, 1);
+		break;
+	case S_IFLNK:
+		if (new) {
+			inode->i_size = (loff_t)strlen(new_op->
+			    downcall.resp.getattr.link_target);
+			orangefs_inode->blksize = (1 << inode->i_blkbits);
+			ret = strscpy(orangefs_inode->link_target,
+			    new_op->downcall.resp.getattr.link_target,
+			    ORANGEFS_NAME_MAX);
+			if (ret == -E2BIG) {
+				ret = -EIO;
+				goto out;
+			}
+			inode->i_link = orangefs_inode->link_target;
+		}
+		break;
+	}
+
+	inode->i_uid = make_kuid(&init_user_ns, new_op->
+	    downcall.resp.getattr.attributes.owner);
+	inode->i_gid = make_kgid(&init_user_ns, new_op->
+	    downcall.resp.getattr.attributes.group);
+	inode->i_atime.tv_sec = (time64_t)new_op->
+	    downcall.resp.getattr.attributes.atime;
+	inode->i_mtime.tv_sec = (time64_t)new_op->
+	    downcall.resp.getattr.attributes.mtime;
+	inode->i_ctime.tv_sec = (time64_t)new_op->
+	    downcall.resp.getattr.attributes.ctime;
+	inode->i_atime.tv_nsec = 0;
+	inode->i_mtime.tv_nsec = 0;
+	inode->i_ctime.tv_nsec = 0;
+
+	/* special case: mark the root inode as sticky */
+	inode->i_mode = type | (is_root_handle(inode) ? S_ISVTX : 0) |
+	    orangefs_inode_perms(&new_op->downcall.resp.getattr.attributes);
+
+	ret = 0;
+out:
+	op_release(new_op);
+	return ret;
+}
+
+int orangefs_inode_check_changed(struct inode *inode)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	struct orangefs_kernel_op_s *new_op;
+	int ret;
+
+	gossip_debug(GOSSIP_UTILS_DEBUG, "%s: called on inode %pU\n", __func__,
+	    get_khandle_from_ino(inode));
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_GETATTR);
+	if (!new_op)
+		return -ENOMEM;
+	new_op->upcall.req.getattr.refn = orangefs_inode->refn;
+	new_op->upcall.req.getattr.mask = ORANGEFS_ATTR_SYS_TYPE |
+	    ORANGEFS_ATTR_SYS_LNK_TARGET;
+
+	ret = service_operation(new_op, __func__,
+	    get_interruptible_flag(inode));
+	if (ret != 0)
+		goto out;
+
+	ret = orangefs_inode_is_stale(inode, 0,
+	    &new_op->downcall.resp.getattr.attributes,
+	    new_op->downcall.resp.getattr.link_target);
+out:
+	op_release(new_op);
+	return ret;
+}
+
+/*
+ * issues a orangefs setattr request to make sure the new attribute values
+ * take effect if successful.  returns 0 on success; -errno otherwise
+ */
+int orangefs_inode_setattr(struct inode *inode, struct iattr *iattr)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	struct orangefs_kernel_op_s *new_op;
+	int ret;
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_SETATTR);
+	if (!new_op)
+		return -ENOMEM;
+
+	new_op->upcall.req.setattr.refn = orangefs_inode->refn;
+	ret = copy_attributes_from_inode(inode,
+		       &new_op->upcall.req.setattr.attributes,
+		       iattr);
+	if (ret >= 0) {
+		ret = service_operation(new_op, __func__,
+				get_interruptible_flag(inode));
+
+		gossip_debug(GOSSIP_UTILS_DEBUG,
+			     "orangefs_inode_setattr: returning %d\n",
+			     ret);
+	}
+
+	op_release(new_op);
+
+	/*
+	 * successful setattr should clear the atime, mtime and
+	 * ctime flags.
+	 */
+	if (ret == 0) {
+		ClearAtimeFlag(orangefs_inode);
+		ClearMtimeFlag(orangefs_inode);
+		ClearCtimeFlag(orangefs_inode);
+		ClearModeFlag(orangefs_inode);
+	}
+
+	return ret;
+}
+
+int orangefs_flush_inode(struct inode *inode)
+{
+	/*
+	 * If it is a dirty inode, this function gets called.
+	 * Gather all the information that needs to be setattr'ed
+	 * Right now, this will only be used for mode, atime, mtime
+	 * and/or ctime.
+	 */
+	struct iattr wbattr;
+	int ret;
+	int mtime_flag;
+	int ctime_flag;
+	int atime_flag;
+	int mode_flag;
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+
+	memset(&wbattr, 0, sizeof(wbattr));
+
+	/*
+	 * check inode flags up front, and clear them if they are set.  This
+	 * will prevent multiple processes from all trying to flush the same
+	 * inode if they call close() simultaneously
+	 */
+	mtime_flag = MtimeFlag(orangefs_inode);
+	ClearMtimeFlag(orangefs_inode);
+	ctime_flag = CtimeFlag(orangefs_inode);
+	ClearCtimeFlag(orangefs_inode);
+	atime_flag = AtimeFlag(orangefs_inode);
+	ClearAtimeFlag(orangefs_inode);
+	mode_flag = ModeFlag(orangefs_inode);
+	ClearModeFlag(orangefs_inode);
+
+	/*  -- Lazy atime,mtime and ctime update --
+	 * Note: all times are dictated by server in the new scheme
+	 * and not by the clients
+	 *
+	 * Also mode updates are being handled now..
+	 */
+
+	if (mtime_flag)
+		wbattr.ia_valid |= ATTR_MTIME;
+	if (ctime_flag)
+		wbattr.ia_valid |= ATTR_CTIME;
+	if (atime_flag)
+		wbattr.ia_valid |= ATTR_ATIME;
+
+	if (mode_flag) {
+		wbattr.ia_mode = inode->i_mode;
+		wbattr.ia_valid |= ATTR_MODE;
+	}
+
+	gossip_debug(GOSSIP_UTILS_DEBUG,
+		     "*********** orangefs_flush_inode: %pU "
+		     "(ia_valid %d)\n",
+		     get_khandle_from_ino(inode),
+		     wbattr.ia_valid);
+	if (wbattr.ia_valid == 0) {
+		gossip_debug(GOSSIP_UTILS_DEBUG,
+			     "orangefs_flush_inode skipping setattr()\n");
+		return 0;
+	}
+
+	gossip_debug(GOSSIP_UTILS_DEBUG,
+		     "orangefs_flush_inode (%pU) writing mode %o\n",
+		     get_khandle_from_ino(inode),
+		     inode->i_mode);
+
+	ret = orangefs_inode_setattr(inode, &wbattr);
+
+	return ret;
+}
+
+int orangefs_unmount_sb(struct super_block *sb)
+{
+	int ret = -EINVAL;
+	struct orangefs_kernel_op_s *new_op = NULL;
+
+	gossip_debug(GOSSIP_UTILS_DEBUG,
+		     "orangefs_unmount_sb called on sb %p\n",
+		     sb);
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_FS_UMOUNT);
+	if (!new_op)
+		return -ENOMEM;
+	new_op->upcall.req.fs_umount.id = ORANGEFS_SB(sb)->id;
+	new_op->upcall.req.fs_umount.fs_id = ORANGEFS_SB(sb)->fs_id;
+	strncpy(new_op->upcall.req.fs_umount.orangefs_config_server,
+		ORANGEFS_SB(sb)->devname,
+		ORANGEFS_MAX_SERVER_ADDR_LEN);
+
+	gossip_debug(GOSSIP_UTILS_DEBUG,
+		     "Attempting ORANGEFS Unmount via host %s\n",
+		     new_op->upcall.req.fs_umount.orangefs_config_server);
+
+	ret = service_operation(new_op, "orangefs_fs_umount", 0);
+
+	gossip_debug(GOSSIP_UTILS_DEBUG,
+		     "orangefs_unmount: got return value of %d\n", ret);
+	if (ret)
+		sb = ERR_PTR(ret);
+	else
+		ORANGEFS_SB(sb)->mount_pending = 1;
+
+	op_release(new_op);
+	return ret;
+}
+
+void orangefs_make_bad_inode(struct inode *inode)
+{
+	if (is_root_handle(inode)) {
+		/*
+		 * if this occurs, the pvfs2-client-core was killed but we
+		 * can't afford to lose the inode operations and such
+		 * associated with the root handle in any case.
+		 */
+		gossip_debug(GOSSIP_UTILS_DEBUG,
+			     "*** NOT making bad root inode %pU\n",
+			     get_khandle_from_ino(inode));
+	} else {
+		gossip_debug(GOSSIP_UTILS_DEBUG,
+			     "*** making bad inode %pU\n",
+			     get_khandle_from_ino(inode));
+		make_bad_inode(inode);
+	}
+}
+
+/*
+ * The following is a very dirty hack that is now a permanent part of the
+ * ORANGEFS protocol. See protocol.h for more error definitions.
+ */
+
+/* The order matches include/orangefs-types.h in the OrangeFS source. */
+static int PINT_errno_mapping[] = {
+	0, EPERM, ENOENT, EINTR, EIO, ENXIO, EBADF, EAGAIN, ENOMEM,
+	EFAULT, EBUSY, EEXIST, ENODEV, ENOTDIR, EISDIR, EINVAL, EMFILE,
+	EFBIG, ENOSPC, EROFS, EMLINK, EPIPE, EDEADLK, ENAMETOOLONG,
+	ENOLCK, ENOSYS, ENOTEMPTY, ELOOP, EWOULDBLOCK, ENOMSG, EUNATCH,
+	EBADR, EDEADLOCK, ENODATA, ETIME, ENONET, EREMOTE, ECOMM,
+	EPROTO, EBADMSG, EOVERFLOW, ERESTART, EMSGSIZE, EPROTOTYPE,
+	ENOPROTOOPT, EPROTONOSUPPORT, EOPNOTSUPP, EADDRINUSE,
+	EADDRNOTAVAIL, ENETDOWN, ENETUNREACH, ENETRESET, ENOBUFS,
+	ETIMEDOUT, ECONNREFUSED, EHOSTDOWN, EHOSTUNREACH, EALREADY,
+	EACCES, ECONNRESET, ERANGE
+};
+
+int orangefs_normalize_to_errno(__s32 error_code)
+{
+	__u32 i;
+
+	/* Success */
+	if (error_code == 0) {
+		return 0;
+	/*
+	 * This shouldn't ever happen. If it does it should be fixed on the
+	 * server.
+	 */
+	} else if (error_code > 0) {
+		gossip_err("orangefs: error status receieved.\n");
+		gossip_err("orangefs: assuming error code is inverted.\n");
+		error_code = -error_code;
+	}
+
+	/*
+	 * XXX: This is very bad since error codes from ORANGEFS may not be
+	 * suitable for return into userspace.
+	 */
+
+	/*
+	 * Convert ORANGEFS error values into errno values suitable for return
+	 * from the kernel.
+	 */
+	if ((-error_code) & ORANGEFS_NON_ERRNO_ERROR_BIT) {
+		if (((-error_code) &
+		    (ORANGEFS_ERROR_NUMBER_BITS|ORANGEFS_NON_ERRNO_ERROR_BIT|
+		    ORANGEFS_ERROR_BIT)) == ORANGEFS_ECANCEL) {
+			/*
+			 * cancellation error codes generally correspond to
+			 * a timeout from the client's perspective
+			 */
+			error_code = -ETIMEDOUT;
+		} else {
+			/* assume a default error code */
+			gossip_err("orangefs: warning: got error code without errno equivalent: %d.\n", error_code);
+			error_code = -EINVAL;
+		}
+
+	/* Convert ORANGEFS encoded errno values into regular errno values. */
+	} else if ((-error_code) & ORANGEFS_ERROR_BIT) {
+		i = (-error_code) & ~(ORANGEFS_ERROR_BIT|ORANGEFS_ERROR_CLASS_BITS);
+		if (i < sizeof(PINT_errno_mapping)/sizeof(*PINT_errno_mapping))
+			error_code = -PINT_errno_mapping[i];
+		else
+			error_code = -EINVAL;
+
+	/*
+	 * Only ORANGEFS protocol error codes should ever come here. Otherwise
+	 * there is a bug somewhere.
+	 */
+	} else {
+		gossip_err("orangefs: orangefs_normalize_to_errno: got error code which is not from ORANGEFS.\n");
+	}
+	return error_code;
+}
+
+#define NUM_MODES 11
+__s32 ORANGEFS_util_translate_mode(int mode)
+{
+	int ret = 0;
+	int i = 0;
+	static int modes[NUM_MODES] = {
+		S_IXOTH, S_IWOTH, S_IROTH,
+		S_IXGRP, S_IWGRP, S_IRGRP,
+		S_IXUSR, S_IWUSR, S_IRUSR,
+		S_ISGID, S_ISUID
+	};
+	static int orangefs_modes[NUM_MODES] = {
+		ORANGEFS_O_EXECUTE, ORANGEFS_O_WRITE, ORANGEFS_O_READ,
+		ORANGEFS_G_EXECUTE, ORANGEFS_G_WRITE, ORANGEFS_G_READ,
+		ORANGEFS_U_EXECUTE, ORANGEFS_U_WRITE, ORANGEFS_U_READ,
+		ORANGEFS_G_SGID, ORANGEFS_U_SUID
+	};
+
+	for (i = 0; i < NUM_MODES; i++)
+		if (mode & modes[i])
+			ret |= orangefs_modes[i];
+
+	return ret;
+}
+#undef NUM_MODES
+
+/*
+ * After obtaining a string representation of the client's debug
+ * keywords and their associated masks, this function is called to build an
+ * array of these values.
+ */
+int orangefs_prepare_cdm_array(char *debug_array_string)
+{
+	int i;
+	int rc = -EINVAL;
+	char *cds_head = NULL;
+	char *cds_delimiter = NULL;
+	int keyword_len = 0;
+
+	gossip_debug(GOSSIP_UTILS_DEBUG, "%s: start\n", __func__);
+
+	/*
+	 * figure out how many elements the cdm_array needs.
+	 */
+	for (i = 0; i < strlen(debug_array_string); i++)
+		if (debug_array_string[i] == '\n')
+			cdm_element_count++;
+
+	if (!cdm_element_count) {
+		pr_info("No elements in client debug array string!\n");
+		goto out;
+	}
+
+	cdm_array =
+		kzalloc(cdm_element_count * sizeof(struct client_debug_mask),
+			GFP_KERNEL);
+	if (!cdm_array) {
+		pr_info("malloc failed for cdm_array!\n");
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	cds_head = debug_array_string;
+
+	for (i = 0; i < cdm_element_count; i++) {
+		cds_delimiter = strchr(cds_head, '\n');
+		*cds_delimiter = '\0';
+
+		keyword_len = strcspn(cds_head, " ");
+
+		cdm_array[i].keyword = kzalloc(keyword_len + 1, GFP_KERNEL);
+		if (!cdm_array[i].keyword) {
+			rc = -ENOMEM;
+			goto out;
+		}
+
+		sscanf(cds_head,
+		       "%s %llx %llx",
+		       cdm_array[i].keyword,
+		       (unsigned long long *)&(cdm_array[i].mask1),
+		       (unsigned long long *)&(cdm_array[i].mask2));
+
+		if (!strcmp(cdm_array[i].keyword, ORANGEFS_VERBOSE))
+			client_verbose_index = i;
+
+		if (!strcmp(cdm_array[i].keyword, ORANGEFS_ALL))
+			client_all_index = i;
+
+		cds_head = cds_delimiter + 1;
+	}
+
+	rc = cdm_element_count;
+
+	gossip_debug(GOSSIP_UTILS_DEBUG, "%s: rc:%d:\n", __func__, rc);
+
+out:
+
+	return rc;
+
+}
+
+/*
+ * /sys/kernel/debug/orangefs/debug-help can be catted to
+ * see all the available kernel and client debug keywords.
+ *
+ * When the kernel boots, we have no idea what keywords the
+ * client supports, nor their associated masks.
+ *
+ * We pass through this function once at boot and stamp a
+ * boilerplate "we don't know" message for the client in the
+ * debug-help file. We pass through here again when the client
+ * starts and then we can fill out the debug-help file fully.
+ *
+ * The client might be restarted any number of times between
+ * reboots, we only build the debug-help file the first time.
+ */
+int orangefs_prepare_debugfs_help_string(int at_boot)
+{
+	int rc = -EINVAL;
+	int i;
+	int byte_count = 0;
+	char *client_title = "Client Debug Keywords:\n";
+	char *kernel_title = "Kernel Debug Keywords:\n";
+
+	gossip_debug(GOSSIP_UTILS_DEBUG, "%s: start\n", __func__);
+
+	if (at_boot) {
+		byte_count += strlen(HELP_STRING_UNINITIALIZED);
+		client_title = HELP_STRING_UNINITIALIZED;
+	} else {
+		/*
+		 * fill the client keyword/mask array and remember
+		 * how many elements there were.
+		 */
+		cdm_element_count =
+			orangefs_prepare_cdm_array(client_debug_array_string);
+		if (cdm_element_count <= 0)
+			goto out;
+
+		/* Count the bytes destined for debug_help_string. */
+		byte_count += strlen(client_title);
+
+		for (i = 0; i < cdm_element_count; i++) {
+			byte_count += strlen(cdm_array[i].keyword + 2);
+			if (byte_count >= DEBUG_HELP_STRING_SIZE) {
+				pr_info("%s: overflow 1!\n", __func__);
+				goto out;
+			}
+		}
+
+		gossip_debug(GOSSIP_UTILS_DEBUG,
+			     "%s: cdm_element_count:%d:\n",
+			     __func__,
+			     cdm_element_count);
+	}
+
+	byte_count += strlen(kernel_title);
+	for (i = 0; i < num_kmod_keyword_mask_map; i++) {
+		byte_count +=
+			strlen(s_kmod_keyword_mask_map[i].keyword + 2);
+		if (byte_count >= DEBUG_HELP_STRING_SIZE) {
+			pr_info("%s: overflow 2!\n", __func__);
+			goto out;
+		}
+	}
+
+	/* build debug_help_string. */
+	debug_help_string = kzalloc(DEBUG_HELP_STRING_SIZE, GFP_KERNEL);
+	if (!debug_help_string) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	strcat(debug_help_string, client_title);
+
+	if (!at_boot) {
+		for (i = 0; i < cdm_element_count; i++) {
+			strcat(debug_help_string, "\t");
+			strcat(debug_help_string, cdm_array[i].keyword);
+			strcat(debug_help_string, "\n");
+		}
+	}
+
+	strcat(debug_help_string, "\n");
+	strcat(debug_help_string, kernel_title);
+
+	for (i = 0; i < num_kmod_keyword_mask_map; i++) {
+		strcat(debug_help_string, "\t");
+		strcat(debug_help_string, s_kmod_keyword_mask_map[i].keyword);
+		strcat(debug_help_string, "\n");
+	}
+
+	rc = 0;
+
+out:
+
+	return rc;
+
+}
+
+/*
+ * kernel = type 0
+ * client = type 1
+ */
+void debug_mask_to_string(void *mask, int type)
+{
+	int i;
+	int len = 0;
+	char *debug_string;
+	int element_count = 0;
+
+	gossip_debug(GOSSIP_UTILS_DEBUG, "%s: start\n", __func__);
+
+	if (type) {
+		debug_string = client_debug_string;
+		element_count = cdm_element_count;
+	} else {
+		debug_string = kernel_debug_string;
+		element_count = num_kmod_keyword_mask_map;
+	}
+
+	memset(debug_string, 0, ORANGEFS_MAX_DEBUG_STRING_LEN);
+
+	/*
+	 * Some keywords, like "all" or "verbose", are amalgams of
+	 * numerous other keywords. Make a special check for those
+	 * before grinding through the whole mask only to find out
+	 * later...
+	 */
+	if (check_amalgam_keyword(mask, type))
+		goto out;
+
+	/* Build the debug string. */
+	for (i = 0; i < element_count; i++)
+		if (type)
+			do_c_string(mask, i);
+		else
+			do_k_string(mask, i);
+
+	len = strlen(debug_string);
+
+	if ((len) && (type))
+		client_debug_string[len - 1] = '\0';
+	else if (len)
+		kernel_debug_string[len - 1] = '\0';
+	else if (type)
+		strcpy(client_debug_string, "none");
+	else
+		strcpy(kernel_debug_string, "none");
+
+out:
+gossip_debug(GOSSIP_UTILS_DEBUG, "%s: string:%s:\n", __func__, debug_string);
+
+	return;
+
+}
+
+void do_k_string(void *k_mask, int index)
+{
+	__u64 *mask = (__u64 *) k_mask;
+
+	if (keyword_is_amalgam((char *) s_kmod_keyword_mask_map[index].keyword))
+		goto out;
+
+	if (*mask & s_kmod_keyword_mask_map[index].mask_val) {
+		if ((strlen(kernel_debug_string) +
+		     strlen(s_kmod_keyword_mask_map[index].keyword))
+			< ORANGEFS_MAX_DEBUG_STRING_LEN - 1) {
+				strcat(kernel_debug_string,
+				       s_kmod_keyword_mask_map[index].keyword);
+				strcat(kernel_debug_string, ",");
+			} else {
+				gossip_err("%s: overflow!\n", __func__);
+				strcpy(kernel_debug_string, ORANGEFS_ALL);
+				goto out;
+			}
+	}
+
+out:
+
+	return;
+}
+
+void do_c_string(void *c_mask, int index)
+{
+	struct client_debug_mask *mask = (struct client_debug_mask *) c_mask;
+
+	if (keyword_is_amalgam(cdm_array[index].keyword))
+		goto out;
+
+	if ((mask->mask1 & cdm_array[index].mask1) ||
+	    (mask->mask2 & cdm_array[index].mask2)) {
+		if ((strlen(client_debug_string) +
+		     strlen(cdm_array[index].keyword) + 1)
+			< ORANGEFS_MAX_DEBUG_STRING_LEN - 2) {
+				strcat(client_debug_string,
+				       cdm_array[index].keyword);
+				strcat(client_debug_string, ",");
+			} else {
+				gossip_err("%s: overflow!\n", __func__);
+				strcpy(client_debug_string, ORANGEFS_ALL);
+				goto out;
+			}
+	}
+out:
+	return;
+}
+
+int keyword_is_amalgam(char *keyword)
+{
+	int rc = 0;
+
+	if ((!strcmp(keyword, ORANGEFS_ALL)) || (!strcmp(keyword, ORANGEFS_VERBOSE)))
+		rc = 1;
+
+	return rc;
+}
+
+/*
+ * kernel = type 0
+ * client = type 1
+ *
+ * return 1 if we found an amalgam.
+ */
+int check_amalgam_keyword(void *mask, int type)
+{
+	__u64 *k_mask;
+	struct client_debug_mask *c_mask;
+	int k_all_index = num_kmod_keyword_mask_map - 1;
+	int rc = 0;
+
+	if (type) {
+		c_mask = (struct client_debug_mask *) mask;
+
+		if ((c_mask->mask1 == cdm_array[client_all_index].mask1) &&
+		    (c_mask->mask2 == cdm_array[client_all_index].mask2)) {
+			strcpy(client_debug_string, ORANGEFS_ALL);
+			rc = 1;
+			goto out;
+		}
+
+		if ((c_mask->mask1 == cdm_array[client_verbose_index].mask1) &&
+		    (c_mask->mask2 == cdm_array[client_verbose_index].mask2)) {
+			strcpy(client_debug_string, ORANGEFS_VERBOSE);
+			rc = 1;
+			goto out;
+		}
+
+	} else {
+		k_mask = (__u64 *) mask;
+
+		if (*k_mask >= s_kmod_keyword_mask_map[k_all_index].mask_val) {
+			strcpy(kernel_debug_string, ORANGEFS_ALL);
+			rc = 1;
+			goto out;
+		}
+	}
+
+out:
+
+	return rc;
+}
+
+/*
+ * kernel = type 0
+ * client = type 1
+ */
+void debug_string_to_mask(char *debug_string, void *mask, int type)
+{
+	char *unchecked_keyword;
+	int i;
+	char *strsep_fodder = kstrdup(debug_string, GFP_KERNEL);
+	char *original_pointer;
+	int element_count = 0;
+	struct client_debug_mask *c_mask;
+	__u64 *k_mask;
+
+	gossip_debug(GOSSIP_UTILS_DEBUG, "%s: start\n", __func__);
+
+	if (type) {
+		c_mask = (struct client_debug_mask *)mask;
+		element_count = cdm_element_count;
+	} else {
+		k_mask = (__u64 *)mask;
+		*k_mask = 0;
+		element_count = num_kmod_keyword_mask_map;
+	}
+
+	original_pointer = strsep_fodder;
+	while ((unchecked_keyword = strsep(&strsep_fodder, ",")))
+		if (strlen(unchecked_keyword)) {
+			for (i = 0; i < element_count; i++)
+				if (type)
+					do_c_mask(i,
+						  unchecked_keyword,
+						  &c_mask);
+				else
+					do_k_mask(i,
+						  unchecked_keyword,
+						  &k_mask);
+		}
+
+	kfree(original_pointer);
+}
+
+void do_c_mask(int i,
+	       char *unchecked_keyword,
+	       struct client_debug_mask **sane_mask)
+{
+
+	if (!strcmp(cdm_array[i].keyword, unchecked_keyword)) {
+		(**sane_mask).mask1 = (**sane_mask).mask1 | cdm_array[i].mask1;
+		(**sane_mask).mask2 = (**sane_mask).mask2 | cdm_array[i].mask2;
+	}
+}
+
+void do_k_mask(int i, char *unchecked_keyword, __u64 **sane_mask)
+{
+
+	if (!strcmp(s_kmod_keyword_mask_map[i].keyword, unchecked_keyword))
+		**sane_mask = (**sane_mask) |
+				s_kmod_keyword_mask_map[i].mask_val;
+}
diff --git a/fs/orangefs/protocol.h b/fs/orangefs/protocol.h
new file mode 100644
index 000000000000..1efc6f8a5224
--- /dev/null
+++ b/fs/orangefs/protocol.h
@@ -0,0 +1,455 @@
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/spinlock_types.h>
+#include <linux/slab.h>
+#include <linux/ioctl.h>
+
+extern struct client_debug_mask *cdm_array;
+extern char *debug_help_string;
+extern int help_string_initialized;
+extern struct dentry *debug_dir;
+extern struct dentry *help_file_dentry;
+extern struct dentry *client_debug_dentry;
+extern const struct file_operations debug_help_fops;
+extern int client_all_index;
+extern int client_verbose_index;
+extern int cdm_element_count;
+#define DEBUG_HELP_STRING_SIZE 4096
+#define HELP_STRING_UNINITIALIZED \
+	"Client Debug Keywords are unknown until the first time\n" \
+	"the client is started after boot.\n"
+#define ORANGEFS_KMOD_DEBUG_HELP_FILE "debug-help"
+#define ORANGEFS_KMOD_DEBUG_FILE "kernel-debug"
+#define ORANGEFS_CLIENT_DEBUG_FILE "client-debug"
+#define ORANGEFS_VERBOSE "verbose"
+#define ORANGEFS_ALL "all"
+
+/* pvfs2-config.h ***********************************************************/
+#define ORANGEFS_VERSION_MAJOR 2
+#define ORANGEFS_VERSION_MINOR 9
+#define ORANGEFS_VERSION_SUB 0
+
+/* khandle stuff  ***********************************************************/
+
+/*
+ * The 2.9 core will put 64 bit handles in here like this:
+ *    1234 0000 0000 5678
+ * The 3.0 and beyond cores will put 128 bit handles in here like this:
+ *    1234 5678 90AB CDEF
+ * The kernel module will always use the first four bytes and
+ * the last four bytes as an inum.
+ */
+struct orangefs_khandle {
+	unsigned char u[16];
+}  __aligned(8);
+
+/*
+ * kernel version of an object ref.
+ */
+struct orangefs_object_kref {
+	struct orangefs_khandle khandle;
+	__s32 fs_id;
+	__s32 __pad1;
+};
+
+/*
+ * compare 2 khandles assumes little endian thus from large address to
+ * small address
+ */
+static inline int ORANGEFS_khandle_cmp(const struct orangefs_khandle *kh1,
+				   const struct orangefs_khandle *kh2)
+{
+	int i;
+
+	for (i = 15; i >= 0; i--) {
+		if (kh1->u[i] > kh2->u[i])
+			return 1;
+		if (kh1->u[i] < kh2->u[i])
+			return -1;
+	}
+
+	return 0;
+}
+
+static inline void ORANGEFS_khandle_to(const struct orangefs_khandle *kh,
+				   void *p, int size)
+{
+
+	memcpy(p, kh->u, 16);
+	memset(p + 16, 0, size - 16);
+
+}
+
+static inline void ORANGEFS_khandle_from(struct orangefs_khandle *kh,
+				     void *p, int size)
+{
+	memset(kh, 0, 16);
+	memcpy(kh->u, p, 16);
+
+}
+
+/* pvfs2-types.h ************************************************************/
+typedef __u32 ORANGEFS_uid;
+typedef __u32 ORANGEFS_gid;
+typedef __s32 ORANGEFS_fs_id;
+typedef __u32 ORANGEFS_permissions;
+typedef __u64 ORANGEFS_time;
+typedef __s64 ORANGEFS_size;
+typedef __u64 ORANGEFS_flags;
+typedef __u64 ORANGEFS_ds_position;
+typedef __s32 ORANGEFS_error;
+typedef __s64 ORANGEFS_offset;
+
+#define ORANGEFS_SUPER_MAGIC 0x20030528
+
+/*
+ * ORANGEFS error codes are a signed 32-bit integer. Error codes are negative, but
+ * the sign is stripped before decoding.
+ */
+
+/* Bit 31 is not used since it is the sign. */
+
+/*
+ * Bit 30 specifies that this is a ORANGEFS error. A ORANGEFS error is either an
+ * encoded errno value or a ORANGEFS protocol error.
+ */
+#define ORANGEFS_ERROR_BIT (1 << 30)
+
+/*
+ * Bit 29 specifies that this is a ORANGEFS protocol error and not an encoded
+ * errno value.
+ */
+#define ORANGEFS_NON_ERRNO_ERROR_BIT (1 << 29)
+
+/*
+ * Bits 9, 8, and 7 specify the error class, which encodes the section of
+ * server code the error originated in for logging purposes. It is not used
+ * in the kernel except to be masked out.
+ */
+#define ORANGEFS_ERROR_CLASS_BITS 0x380
+
+/* Bits 6 - 0 are reserved for the actual error code. */
+#define ORANGEFS_ERROR_NUMBER_BITS 0x7f
+
+/* Encoded errno values decoded by PINT_errno_mapping in orangefs-utils.c. */
+
+/* Our own ORANGEFS protocol error codes. */
+#define ORANGEFS_ECANCEL    (1|ORANGEFS_NON_ERRNO_ERROR_BIT|ORANGEFS_ERROR_BIT)
+#define ORANGEFS_EDEVINIT   (2|ORANGEFS_NON_ERRNO_ERROR_BIT|ORANGEFS_ERROR_BIT)
+#define ORANGEFS_EDETAIL    (3|ORANGEFS_NON_ERRNO_ERROR_BIT|ORANGEFS_ERROR_BIT)
+#define ORANGEFS_EHOSTNTFD  (4|ORANGEFS_NON_ERRNO_ERROR_BIT|ORANGEFS_ERROR_BIT)
+#define ORANGEFS_EADDRNTFD  (5|ORANGEFS_NON_ERRNO_ERROR_BIT|ORANGEFS_ERROR_BIT)
+#define ORANGEFS_ENORECVR   (6|ORANGEFS_NON_ERRNO_ERROR_BIT|ORANGEFS_ERROR_BIT)
+#define ORANGEFS_ETRYAGAIN  (7|ORANGEFS_NON_ERRNO_ERROR_BIT|ORANGEFS_ERROR_BIT)
+#define ORANGEFS_ENOTPVFS   (8|ORANGEFS_NON_ERRNO_ERROR_BIT|ORANGEFS_ERROR_BIT)
+#define ORANGEFS_ESECURITY  (9|ORANGEFS_NON_ERRNO_ERROR_BIT|ORANGEFS_ERROR_BIT)
+
+/* permission bits */
+#define ORANGEFS_O_EXECUTE (1 << 0)
+#define ORANGEFS_O_WRITE   (1 << 1)
+#define ORANGEFS_O_READ    (1 << 2)
+#define ORANGEFS_G_EXECUTE (1 << 3)
+#define ORANGEFS_G_WRITE   (1 << 4)
+#define ORANGEFS_G_READ    (1 << 5)
+#define ORANGEFS_U_EXECUTE (1 << 6)
+#define ORANGEFS_U_WRITE   (1 << 7)
+#define ORANGEFS_U_READ    (1 << 8)
+/* no ORANGEFS_U_VTX (sticky bit) */
+#define ORANGEFS_G_SGID    (1 << 10)
+#define ORANGEFS_U_SUID    (1 << 11)
+
+/* definition taken from stdint.h */
+#define INT32_MAX (2147483647)
+#define ORANGEFS_ITERATE_START    (INT32_MAX - 1)
+#define ORANGEFS_ITERATE_END      (INT32_MAX - 2)
+#define ORANGEFS_ITERATE_NEXT     (INT32_MAX - 3)
+#define ORANGEFS_READDIR_START ORANGEFS_ITERATE_START
+#define ORANGEFS_READDIR_END   ORANGEFS_ITERATE_END
+#define ORANGEFS_IMMUTABLE_FL FS_IMMUTABLE_FL
+#define ORANGEFS_APPEND_FL    FS_APPEND_FL
+#define ORANGEFS_NOATIME_FL   FS_NOATIME_FL
+#define ORANGEFS_MIRROR_FL    0x01000000ULL
+#define ORANGEFS_O_EXECUTE (1 << 0)
+#define ORANGEFS_FS_ID_NULL       ((__s32)0)
+#define ORANGEFS_ATTR_SYS_UID                   (1 << 0)
+#define ORANGEFS_ATTR_SYS_GID                   (1 << 1)
+#define ORANGEFS_ATTR_SYS_PERM                  (1 << 2)
+#define ORANGEFS_ATTR_SYS_ATIME                 (1 << 3)
+#define ORANGEFS_ATTR_SYS_CTIME                 (1 << 4)
+#define ORANGEFS_ATTR_SYS_MTIME                 (1 << 5)
+#define ORANGEFS_ATTR_SYS_TYPE                  (1 << 6)
+#define ORANGEFS_ATTR_SYS_ATIME_SET             (1 << 7)
+#define ORANGEFS_ATTR_SYS_MTIME_SET             (1 << 8)
+#define ORANGEFS_ATTR_SYS_SIZE                  (1 << 20)
+#define ORANGEFS_ATTR_SYS_LNK_TARGET            (1 << 24)
+#define ORANGEFS_ATTR_SYS_DFILE_COUNT           (1 << 25)
+#define ORANGEFS_ATTR_SYS_DIRENT_COUNT          (1 << 26)
+#define ORANGEFS_ATTR_SYS_BLKSIZE               (1 << 28)
+#define ORANGEFS_ATTR_SYS_MIRROR_COPIES_COUNT   (1 << 29)
+#define ORANGEFS_ATTR_SYS_COMMON_ALL	\
+	(ORANGEFS_ATTR_SYS_UID	|	\
+	 ORANGEFS_ATTR_SYS_GID	|	\
+	 ORANGEFS_ATTR_SYS_PERM	|	\
+	 ORANGEFS_ATTR_SYS_ATIME	|	\
+	 ORANGEFS_ATTR_SYS_CTIME	|	\
+	 ORANGEFS_ATTR_SYS_MTIME	|	\
+	 ORANGEFS_ATTR_SYS_TYPE)
+
+#define ORANGEFS_ATTR_SYS_ALL_SETABLE		\
+(ORANGEFS_ATTR_SYS_COMMON_ALL-ORANGEFS_ATTR_SYS_TYPE)
+
+#define ORANGEFS_ATTR_SYS_ALL_NOHINT			\
+	(ORANGEFS_ATTR_SYS_COMMON_ALL		|	\
+	 ORANGEFS_ATTR_SYS_SIZE			|	\
+	 ORANGEFS_ATTR_SYS_LNK_TARGET		|	\
+	 ORANGEFS_ATTR_SYS_DFILE_COUNT		|	\
+	 ORANGEFS_ATTR_SYS_MIRROR_COPIES_COUNT	|	\
+	 ORANGEFS_ATTR_SYS_DIRENT_COUNT		|	\
+	 ORANGEFS_ATTR_SYS_BLKSIZE)
+
+#define ORANGEFS_ATTR_SYS_ALL_NOHINT_NOSIZE		\
+	(ORANGEFS_ATTR_SYS_COMMON_ALL		|	\
+	 ORANGEFS_ATTR_SYS_LNK_TARGET		|	\
+	 ORANGEFS_ATTR_SYS_DFILE_COUNT		|	\
+	 ORANGEFS_ATTR_SYS_MIRROR_COPIES_COUNT	|	\
+	 ORANGEFS_ATTR_SYS_DIRENT_COUNT		|	\
+	 ORANGEFS_ATTR_SYS_BLKSIZE)
+
+#define ORANGEFS_XATTR_REPLACE 0x2
+#define ORANGEFS_XATTR_CREATE  0x1
+#define ORANGEFS_MAX_SERVER_ADDR_LEN 256
+#define ORANGEFS_NAME_MAX                256
+/*
+ * max extended attribute name len as imposed by the VFS and exploited for the
+ * upcall request types.
+ * NOTE: Please retain them as multiples of 8 even if you wish to change them
+ * This is *NECESSARY* for supporting 32 bit user-space binaries on a 64-bit
+ * kernel. Due to implementation within DBPF, this really needs to be
+ * ORANGEFS_NAME_MAX, which it was the same value as, but no reason to let it
+ * break if that changes in the future.
+ */
+#define ORANGEFS_MAX_XATTR_NAMELEN   ORANGEFS_NAME_MAX	/* Not the same as
+						 * XATTR_NAME_MAX defined
+						 * by <linux/xattr.h>
+						 */
+#define ORANGEFS_MAX_XATTR_VALUELEN  8192	/* Not the same as XATTR_SIZE_MAX
+					 * defined by <linux/xattr.h>
+					 */
+#define ORANGEFS_MAX_XATTR_LISTLEN   16	/* Not the same as XATTR_LIST_MAX
+					 * defined by <linux/xattr.h>
+					 */
+/*
+ * ORANGEFS I/O operation types, used in both system and server interfaces.
+ */
+enum ORANGEFS_io_type {
+	ORANGEFS_IO_READ = 1,
+	ORANGEFS_IO_WRITE = 2
+};
+
+/*
+ * If this enum is modified the server parameters related to the precreate pool
+ * batch and low threshold sizes may need to be modified  to reflect this
+ * change.
+ */
+enum orangefs_ds_type {
+	ORANGEFS_TYPE_NONE = 0,
+	ORANGEFS_TYPE_METAFILE = (1 << 0),
+	ORANGEFS_TYPE_DATAFILE = (1 << 1),
+	ORANGEFS_TYPE_DIRECTORY = (1 << 2),
+	ORANGEFS_TYPE_SYMLINK = (1 << 3),
+	ORANGEFS_TYPE_DIRDATA = (1 << 4),
+	ORANGEFS_TYPE_INTERNAL = (1 << 5)	/* for the server's private use */
+};
+
+/*
+ * ORANGEFS_certificate simply stores a buffer with the buffer size.
+ * The buffer can be converted to an OpenSSL X509 struct for use.
+ */
+struct ORANGEFS_certificate {
+	__u32 buf_size;
+	unsigned char *buf;
+};
+
+/*
+ * A credential identifies a user and is signed by the client/user
+ * private key.
+ */
+struct ORANGEFS_credential {
+	__u32 userid;	/* user id */
+	__u32 num_groups;	/* length of group_array */
+	__u32 *group_array;	/* groups for which the user is a member */
+	char *issuer;		/* alias of the issuing server */
+	__u64 timeout;	/* seconds after epoch to time out */
+	__u32 sig_size;	/* length of the signature in bytes */
+	unsigned char *signature;	/* digital signature */
+	struct ORANGEFS_certificate certificate;	/* user certificate buffer */
+};
+#define extra_size_ORANGEFS_credential (ORANGEFS_REQ_LIMIT_GROUPS	*	\
+				    sizeof(__u32)		+	\
+				    ORANGEFS_REQ_LIMIT_ISSUER	+	\
+				    ORANGEFS_REQ_LIMIT_SIGNATURE	+	\
+				    extra_size_ORANGEFS_certificate)
+
+/* This structure is used by the VFS-client interaction alone */
+struct ORANGEFS_keyval_pair {
+	char key[ORANGEFS_MAX_XATTR_NAMELEN];
+	__s32 key_sz;	/* __s32 for portable, fixed-size structures */
+	__s32 val_sz;
+	char val[ORANGEFS_MAX_XATTR_VALUELEN];
+};
+
+/* pvfs2-sysint.h ***********************************************************/
+/* Describes attributes for a file, directory, or symlink. */
+struct ORANGEFS_sys_attr_s {
+	__u32 owner;
+	__u32 group;
+	__u32 perms;
+	__u64 atime;
+	__u64 mtime;
+	__u64 ctime;
+	__s64 size;
+
+	/* NOTE: caller must free if valid */
+	char *link_target;
+
+	/* Changed to __s32 so that size of structure does not change */
+	__s32 dfile_count;
+
+	/* Changed to __s32 so that size of structure does not change */
+	__s32 distr_dir_servers_initial;
+
+	/* Changed to __s32 so that size of structure does not change */
+	__s32 distr_dir_servers_max;
+
+	/* Changed to __s32 so that size of structure does not change */
+	__s32 distr_dir_split_size;
+
+	__u32 mirror_copies_count;
+
+	/* NOTE: caller must free if valid */
+	char *dist_name;
+
+	/* NOTE: caller must free if valid */
+	char *dist_params;
+
+	__s64 dirent_count;
+	enum orangefs_ds_type objtype;
+	__u64 flags;
+	__u32 mask;
+	__s64 blksize;
+};
+
+#define ORANGEFS_LOOKUP_LINK_NO_FOLLOW 0
+
+/* pint-dev.h ***************************************************************/
+
+/* parameter structure used in ORANGEFS_DEV_DEBUG ioctl command */
+struct dev_mask_info_s {
+	enum {
+		KERNEL_MASK,
+		CLIENT_MASK,
+	} mask_type;
+	__u64 mask_value;
+};
+
+struct dev_mask2_info_s {
+	__u64 mask1_value;
+	__u64 mask2_value;
+};
+
+/* pvfs2-util.h *************************************************************/
+__s32 ORANGEFS_util_translate_mode(int mode);
+
+/* pvfs2-debug.h ************************************************************/
+#include "orangefs-debug.h"
+
+/* pvfs2-internal.h *********************************************************/
+#define llu(x) (unsigned long long)(x)
+#define lld(x) (long long)(x)
+
+/* pint-dev-shared.h ********************************************************/
+#define ORANGEFS_DEV_MAGIC 'k'
+
+#define ORANGEFS_READDIR_DEFAULT_DESC_COUNT  5
+
+#define DEV_GET_MAGIC           0x1
+#define DEV_GET_MAX_UPSIZE      0x2
+#define DEV_GET_MAX_DOWNSIZE    0x3
+#define DEV_MAP                 0x4
+#define DEV_REMOUNT_ALL         0x5
+#define DEV_DEBUG               0x6
+#define DEV_UPSTREAM            0x7
+#define DEV_CLIENT_MASK         0x8
+#define DEV_CLIENT_STRING       0x9
+#define DEV_MAX_NR              0xa
+
+/* supported ioctls, codes are with respect to user-space */
+enum {
+	ORANGEFS_DEV_GET_MAGIC = _IOW(ORANGEFS_DEV_MAGIC, DEV_GET_MAGIC, __s32),
+	ORANGEFS_DEV_GET_MAX_UPSIZE =
+	    _IOW(ORANGEFS_DEV_MAGIC, DEV_GET_MAX_UPSIZE, __s32),
+	ORANGEFS_DEV_GET_MAX_DOWNSIZE =
+	    _IOW(ORANGEFS_DEV_MAGIC, DEV_GET_MAX_DOWNSIZE, __s32),
+	ORANGEFS_DEV_MAP = _IO(ORANGEFS_DEV_MAGIC, DEV_MAP),
+	ORANGEFS_DEV_REMOUNT_ALL = _IO(ORANGEFS_DEV_MAGIC, DEV_REMOUNT_ALL),
+	ORANGEFS_DEV_DEBUG = _IOR(ORANGEFS_DEV_MAGIC, DEV_DEBUG, __s32),
+	ORANGEFS_DEV_UPSTREAM = _IOW(ORANGEFS_DEV_MAGIC, DEV_UPSTREAM, int),
+	ORANGEFS_DEV_CLIENT_MASK = _IOW(ORANGEFS_DEV_MAGIC,
+				    DEV_CLIENT_MASK,
+				    struct dev_mask2_info_s),
+	ORANGEFS_DEV_CLIENT_STRING = _IOW(ORANGEFS_DEV_MAGIC,
+				      DEV_CLIENT_STRING,
+				      char *),
+	ORANGEFS_DEV_MAXNR = DEV_MAX_NR,
+};
+
+/*
+ * version number for use in communicating between kernel space and user
+ * space. Zero signifies the upstream version of the kernel module.
+ */
+#define ORANGEFS_KERNEL_PROTO_VERSION 0
+#define ORANGEFS_MINIMUM_USERSPACE_VERSION 20903
+
+/*
+ * describes memory regions to map in the ORANGEFS_DEV_MAP ioctl.
+ * NOTE: See devorangefs-req.c for 32 bit compat structure.
+ * Since this structure has a variable-sized layout that is different
+ * on 32 and 64 bit platforms, we need to normalize to a 64 bit layout
+ * on such systems before servicing ioctl calls from user-space binaries
+ * that may be 32 bit!
+ */
+struct ORANGEFS_dev_map_desc {
+	void *ptr;
+	__s32 total_size;
+	__s32 size;
+	__s32 count;
+};
+
+/* gossip.h *****************************************************************/
+
+#ifdef GOSSIP_DISABLE_DEBUG
+#define gossip_debug(mask, fmt, ...)					\
+do {									\
+	if (0)								\
+		printk(KERN_DEBUG fmt, ##__VA_ARGS__);			\
+} while (0)
+#else
+extern __u64 gossip_debug_mask;
+extern struct client_debug_mask client_debug_mask;
+
+/* try to avoid function call overhead by checking masks in macro */
+#define gossip_debug(mask, fmt, ...)					\
+do {									\
+	if (gossip_debug_mask & (mask))					\
+		printk(KERN_DEBUG fmt, ##__VA_ARGS__);			\
+} while (0)
+#endif /* GOSSIP_DISABLE_DEBUG */
+
+/* do file and line number printouts w/ the GNU preprocessor */
+#define gossip_ldebug(mask, fmt, ...)					\
+	gossip_debug(mask, "%s: " fmt, __func__, ##__VA_ARGS__)
+
+#define gossip_err pr_err
+#define gossip_lerr(fmt, ...)						\
+	gossip_err("%s line %d: " fmt,					\
+		   __FILE__, __LINE__, ##__VA_ARGS__)
diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c
new file mode 100644
index 000000000000..b9da9a0281c9
--- /dev/null
+++ b/fs/orangefs/super.c
@@ -0,0 +1,559 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-bufmap.h"
+
+#include <linux/parser.h>
+
+/* a cache for orangefs-inode objects (i.e. orangefs inode private data) */
+static struct kmem_cache *orangefs_inode_cache;
+
+/* list for storing orangefs specific superblocks in use */
+LIST_HEAD(orangefs_superblocks);
+
+DEFINE_SPINLOCK(orangefs_superblocks_lock);
+
+enum {
+	Opt_intr,
+	Opt_acl,
+	Opt_local_lock,
+
+	Opt_err
+};
+
+static const match_table_t tokens = {
+	{ Opt_acl,		"acl" },
+	{ Opt_intr,		"intr" },
+	{ Opt_local_lock,	"local_lock" },
+	{ Opt_err,	NULL }
+};
+
+
+static int parse_mount_options(struct super_block *sb, char *options,
+		int silent)
+{
+	struct orangefs_sb_info_s *orangefs_sb = ORANGEFS_SB(sb);
+	substring_t args[MAX_OPT_ARGS];
+	char *p;
+
+	/*
+	 * Force any potential flags that might be set from the mount
+	 * to zero, ie, initialize to unset.
+	 */
+	sb->s_flags &= ~MS_POSIXACL;
+	orangefs_sb->flags &= ~ORANGEFS_OPT_INTR;
+	orangefs_sb->flags &= ~ORANGEFS_OPT_LOCAL_LOCK;
+
+	while ((p = strsep(&options, ",")) != NULL) {
+		int token;
+
+		if (!*p)
+			continue;
+
+		token = match_token(p, tokens, args);
+		switch (token) {
+		case Opt_acl:
+			sb->s_flags |= MS_POSIXACL;
+			break;
+		case Opt_intr:
+			orangefs_sb->flags |= ORANGEFS_OPT_INTR;
+			break;
+		case Opt_local_lock:
+			orangefs_sb->flags |= ORANGEFS_OPT_LOCAL_LOCK;
+			break;
+		default:
+			goto fail;
+		}
+	}
+
+	return 0;
+fail:
+	if (!silent)
+		gossip_err("Error: mount option [%s] is not supported.\n", p);
+	return -EINVAL;
+}
+
+static void orangefs_inode_cache_ctor(void *req)
+{
+	struct orangefs_inode_s *orangefs_inode = req;
+
+	inode_init_once(&orangefs_inode->vfs_inode);
+	init_rwsem(&orangefs_inode->xattr_sem);
+
+	orangefs_inode->vfs_inode.i_version = 1;
+}
+
+static struct inode *orangefs_alloc_inode(struct super_block *sb)
+{
+	struct orangefs_inode_s *orangefs_inode;
+
+	orangefs_inode = kmem_cache_alloc(orangefs_inode_cache, GFP_KERNEL);
+	if (orangefs_inode == NULL) {
+		gossip_err("Failed to allocate orangefs_inode\n");
+		return NULL;
+	}
+
+	/*
+	 * We want to clear everything except for rw_semaphore and the
+	 * vfs_inode.
+	 */
+	memset(&orangefs_inode->refn.khandle, 0, 16);
+	orangefs_inode->refn.fs_id = ORANGEFS_FS_ID_NULL;
+	orangefs_inode->last_failed_block_index_read = 0;
+	memset(orangefs_inode->link_target, 0, sizeof(orangefs_inode->link_target));
+	orangefs_inode->pinode_flags = 0;
+
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "orangefs_alloc_inode: allocated %p\n",
+		     &orangefs_inode->vfs_inode);
+	return &orangefs_inode->vfs_inode;
+}
+
+static void orangefs_destroy_inode(struct inode *inode)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+			"%s: deallocated %p destroying inode %pU\n",
+			__func__, orangefs_inode, get_khandle_from_ino(inode));
+
+	kmem_cache_free(orangefs_inode_cache, orangefs_inode);
+}
+
+/*
+ * NOTE: information filled in here is typically reflected in the
+ * output of the system command 'df'
+*/
+static int orangefs_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+	int ret = -ENOMEM;
+	struct orangefs_kernel_op_s *new_op = NULL;
+	int flags = 0;
+	struct super_block *sb = NULL;
+
+	sb = dentry->d_sb;
+
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "orangefs_statfs: called on sb %p (fs_id is %d)\n",
+		     sb,
+		     (int)(ORANGEFS_SB(sb)->fs_id));
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_STATFS);
+	if (!new_op)
+		return ret;
+	new_op->upcall.req.statfs.fs_id = ORANGEFS_SB(sb)->fs_id;
+
+	if (ORANGEFS_SB(sb)->flags & ORANGEFS_OPT_INTR)
+		flags = ORANGEFS_OP_INTERRUPTIBLE;
+
+	ret = service_operation(new_op, "orangefs_statfs", flags);
+
+	if (new_op->downcall.status < 0)
+		goto out_op_release;
+
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "%s: got %ld blocks available | "
+		     "%ld blocks total | %ld block size | "
+		     "%ld files total | %ld files avail\n",
+		     __func__,
+		     (long)new_op->downcall.resp.statfs.blocks_avail,
+		     (long)new_op->downcall.resp.statfs.blocks_total,
+		     (long)new_op->downcall.resp.statfs.block_size,
+		     (long)new_op->downcall.resp.statfs.files_total,
+		     (long)new_op->downcall.resp.statfs.files_avail);
+
+	buf->f_type = sb->s_magic;
+	memcpy(&buf->f_fsid, &ORANGEFS_SB(sb)->fs_id, sizeof(buf->f_fsid));
+	buf->f_bsize = new_op->downcall.resp.statfs.block_size;
+	buf->f_namelen = ORANGEFS_NAME_MAX;
+
+	buf->f_blocks = (sector_t) new_op->downcall.resp.statfs.blocks_total;
+	buf->f_bfree = (sector_t) new_op->downcall.resp.statfs.blocks_avail;
+	buf->f_bavail = (sector_t) new_op->downcall.resp.statfs.blocks_avail;
+	buf->f_files = (sector_t) new_op->downcall.resp.statfs.files_total;
+	buf->f_ffree = (sector_t) new_op->downcall.resp.statfs.files_avail;
+	buf->f_frsize = sb->s_blocksize;
+
+out_op_release:
+	op_release(new_op);
+	gossip_debug(GOSSIP_SUPER_DEBUG, "orangefs_statfs: returning %d\n", ret);
+	return ret;
+}
+
+/*
+ * Remount as initiated by VFS layer.  We just need to reparse the mount
+ * options, no need to signal pvfs2-client-core about it.
+ */
+static int orangefs_remount_fs(struct super_block *sb, int *flags, char *data)
+{
+	gossip_debug(GOSSIP_SUPER_DEBUG, "orangefs_remount_fs: called\n");
+	return parse_mount_options(sb, data, 1);
+}
+
+/*
+ * Remount as initiated by pvfs2-client-core on restart.  This is used to
+ * repopulate mount information left from previous pvfs2-client-core.
+ *
+ * the idea here is that given a valid superblock, we're
+ * re-initializing the user space client with the initial mount
+ * information specified when the super block was first initialized.
+ * this is very different than the first initialization/creation of a
+ * superblock.  we use the special service_priority_operation to make
+ * sure that the mount gets ahead of any other pending operation that
+ * is waiting for servicing.  this means that the pvfs2-client won't
+ * fail to start several times for all other pending operations before
+ * the client regains all of the mount information from us.
+ * NOTE: this function assumes that the request_mutex is already acquired!
+ */
+int orangefs_remount(struct orangefs_sb_info_s *orangefs_sb)
+{
+	struct orangefs_kernel_op_s *new_op;
+	int ret = -EINVAL;
+
+	gossip_debug(GOSSIP_SUPER_DEBUG, "orangefs_remount: called\n");
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_FS_MOUNT);
+	if (!new_op)
+		return -ENOMEM;
+	strncpy(new_op->upcall.req.fs_mount.orangefs_config_server,
+		orangefs_sb->devname,
+		ORANGEFS_MAX_SERVER_ADDR_LEN);
+
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "Attempting ORANGEFS Remount via host %s\n",
+		     new_op->upcall.req.fs_mount.orangefs_config_server);
+
+	/*
+	 * we assume that the calling function has already acquired the
+	 * request_mutex to prevent other operations from bypassing
+	 * this one
+	 */
+	ret = service_operation(new_op, "orangefs_remount",
+		ORANGEFS_OP_PRIORITY | ORANGEFS_OP_NO_MUTEX);
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "orangefs_remount: mount got return value of %d\n",
+		     ret);
+	if (ret == 0) {
+		/*
+		 * store the id assigned to this sb -- it's just a
+		 * short-lived mapping that the system interface uses
+		 * to map this superblock to a particular mount entry
+		 */
+		orangefs_sb->id = new_op->downcall.resp.fs_mount.id;
+		orangefs_sb->mount_pending = 0;
+	}
+
+	op_release(new_op);
+	return ret;
+}
+
+int fsid_key_table_initialize(void)
+{
+	return 0;
+}
+
+void fsid_key_table_finalize(void)
+{
+}
+
+/* Called whenever the VFS dirties the inode in response to atime updates */
+static void orangefs_dirty_inode(struct inode *inode, int flags)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "orangefs_dirty_inode: %pU\n",
+		     get_khandle_from_ino(inode));
+	SetAtimeFlag(orangefs_inode);
+}
+
+static const struct super_operations orangefs_s_ops = {
+	.alloc_inode = orangefs_alloc_inode,
+	.destroy_inode = orangefs_destroy_inode,
+	.dirty_inode = orangefs_dirty_inode,
+	.drop_inode = generic_delete_inode,
+	.statfs = orangefs_statfs,
+	.remount_fs = orangefs_remount_fs,
+	.show_options = generic_show_options,
+};
+
+static struct dentry *orangefs_fh_to_dentry(struct super_block *sb,
+				  struct fid *fid,
+				  int fh_len,
+				  int fh_type)
+{
+	struct orangefs_object_kref refn;
+
+	if (fh_len < 5 || fh_type > 2)
+		return NULL;
+
+	ORANGEFS_khandle_from(&(refn.khandle), fid->raw, 16);
+	refn.fs_id = (u32) fid->raw[4];
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "fh_to_dentry: handle %pU, fs_id %d\n",
+		     &refn.khandle,
+		     refn.fs_id);
+
+	return d_obtain_alias(orangefs_iget(sb, &refn));
+}
+
+static int orangefs_encode_fh(struct inode *inode,
+		    __u32 *fh,
+		    int *max_len,
+		    struct inode *parent)
+{
+	int len = parent ? 10 : 5;
+	int type = 1;
+	struct orangefs_object_kref refn;
+
+	if (*max_len < len) {
+		gossip_lerr("fh buffer is too small for encoding\n");
+		*max_len = len;
+		type = 255;
+		goto out;
+	}
+
+	refn = ORANGEFS_I(inode)->refn;
+	ORANGEFS_khandle_to(&refn.khandle, fh, 16);
+	fh[4] = refn.fs_id;
+
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "Encoding fh: handle %pU, fsid %u\n",
+		     &refn.khandle,
+		     refn.fs_id);
+
+
+	if (parent) {
+		refn = ORANGEFS_I(parent)->refn;
+		ORANGEFS_khandle_to(&refn.khandle, (char *) fh + 20, 16);
+		fh[9] = refn.fs_id;
+
+		type = 2;
+		gossip_debug(GOSSIP_SUPER_DEBUG,
+			     "Encoding parent: handle %pU, fsid %u\n",
+			     &refn.khandle,
+			     refn.fs_id);
+	}
+	*max_len = len;
+
+out:
+	return type;
+}
+
+static const struct export_operations orangefs_export_ops = {
+	.encode_fh = orangefs_encode_fh,
+	.fh_to_dentry = orangefs_fh_to_dentry,
+};
+
+static int orangefs_fill_sb(struct super_block *sb,
+		struct orangefs_fs_mount_response *fs_mount,
+		void *data, int silent)
+{
+	int ret = -EINVAL;
+	struct inode *root = NULL;
+	struct dentry *root_dentry = NULL;
+	struct orangefs_object_kref root_object;
+
+	/* alloc and init our private orangefs sb info */
+	sb->s_fs_info = kzalloc(sizeof(struct orangefs_sb_info_s), GFP_KERNEL);
+	if (!ORANGEFS_SB(sb))
+		return -ENOMEM;
+	ORANGEFS_SB(sb)->sb = sb;
+
+	ORANGEFS_SB(sb)->root_khandle = fs_mount->root_khandle;
+	ORANGEFS_SB(sb)->fs_id = fs_mount->fs_id;
+	ORANGEFS_SB(sb)->id = fs_mount->id;
+
+	if (data) {
+		ret = parse_mount_options(sb, data, silent);
+		if (ret)
+			return ret;
+	}
+
+	/* Hang the xattr handlers off the superblock */
+	sb->s_xattr = orangefs_xattr_handlers;
+	sb->s_magic = ORANGEFS_SUPER_MAGIC;
+	sb->s_op = &orangefs_s_ops;
+	sb->s_d_op = &orangefs_dentry_operations;
+
+	sb->s_blocksize = orangefs_bufmap_size_query();
+	sb->s_blocksize_bits = orangefs_bufmap_shift_query();
+	sb->s_maxbytes = MAX_LFS_FILESIZE;
+
+	root_object.khandle = ORANGEFS_SB(sb)->root_khandle;
+	root_object.fs_id = ORANGEFS_SB(sb)->fs_id;
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "get inode %pU, fsid %d\n",
+		     &root_object.khandle,
+		     root_object.fs_id);
+
+	root = orangefs_iget(sb, &root_object);
+	if (IS_ERR(root))
+		return PTR_ERR(root);
+
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "Allocated root inode [%p] with mode %x\n",
+		     root,
+		     root->i_mode);
+
+	/* allocates and places root dentry in dcache */
+	root_dentry = d_make_root(root);
+	if (!root_dentry)
+		return -ENOMEM;
+
+	sb->s_export_op = &orangefs_export_ops;
+	sb->s_root = root_dentry;
+	return 0;
+}
+
+struct dentry *orangefs_mount(struct file_system_type *fst,
+			   int flags,
+			   const char *devname,
+			   void *data)
+{
+	int ret = -EINVAL;
+	struct super_block *sb = ERR_PTR(-EINVAL);
+	struct orangefs_kernel_op_s *new_op;
+	struct dentry *d = ERR_PTR(-EINVAL);
+
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "orangefs_mount: called with devname %s\n",
+		     devname);
+
+	if (!devname) {
+		gossip_err("ERROR: device name not specified.\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_FS_MOUNT);
+	if (!new_op)
+		return ERR_PTR(-ENOMEM);
+
+	strncpy(new_op->upcall.req.fs_mount.orangefs_config_server,
+		devname,
+		ORANGEFS_MAX_SERVER_ADDR_LEN);
+
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "Attempting ORANGEFS Mount via host %s\n",
+		     new_op->upcall.req.fs_mount.orangefs_config_server);
+
+	ret = service_operation(new_op, "orangefs_mount", 0);
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "orangefs_mount: mount got return value of %d\n", ret);
+	if (ret)
+		goto free_op;
+
+	if (new_op->downcall.resp.fs_mount.fs_id == ORANGEFS_FS_ID_NULL) {
+		gossip_err("ERROR: Retrieved null fs_id\n");
+		ret = -EINVAL;
+		goto free_op;
+	}
+
+	sb = sget(fst, NULL, set_anon_super, flags, NULL);
+
+	if (IS_ERR(sb)) {
+		d = ERR_CAST(sb);
+		goto free_op;
+	}
+
+	ret = orangefs_fill_sb(sb,
+	      &new_op->downcall.resp.fs_mount, data,
+	      flags & MS_SILENT ? 1 : 0);
+
+	if (ret) {
+		d = ERR_PTR(ret);
+		goto free_op;
+	}
+
+	/*
+	 * on successful mount, store the devname and data
+	 * used
+	 */
+	strncpy(ORANGEFS_SB(sb)->devname,
+		devname,
+		ORANGEFS_MAX_SERVER_ADDR_LEN);
+
+	/* mount_pending must be cleared */
+	ORANGEFS_SB(sb)->mount_pending = 0;
+
+	/*
+	 * finally, add this sb to our list of known orangefs
+	 * sb's
+	 */
+	gossip_debug(GOSSIP_SUPER_DEBUG,
+		     "Adding SB %p to orangefs superblocks\n",
+		     ORANGEFS_SB(sb));
+	spin_lock(&orangefs_superblocks_lock);
+	list_add_tail(&ORANGEFS_SB(sb)->list, &orangefs_superblocks);
+	spin_unlock(&orangefs_superblocks_lock);
+	op_release(new_op);
+	return dget(sb->s_root);
+
+free_op:
+	gossip_err("orangefs_mount: mount request failed with %d\n", ret);
+	if (ret == -EINVAL) {
+		gossip_err("Ensure that all orangefs-servers have the same FS configuration files\n");
+		gossip_err("Look at pvfs2-client-core log file (typically /tmp/pvfs2-client.log) for more details\n");
+	}
+
+	op_release(new_op);
+
+	return d;
+}
+
+void orangefs_kill_sb(struct super_block *sb)
+{
+	gossip_debug(GOSSIP_SUPER_DEBUG, "orangefs_kill_sb: called\n");
+
+	/* provided sb cleanup */
+	kill_anon_super(sb);
+
+	/*
+	 * issue the unmount to userspace to tell it to remove the
+	 * dynamic mount info it has for this superblock
+	 */
+	 orangefs_unmount_sb(sb);
+
+	/* remove the sb from our list of orangefs specific sb's */
+
+	spin_lock(&orangefs_superblocks_lock);
+	__list_del_entry(&ORANGEFS_SB(sb)->list);	/* not list_del_init */
+	ORANGEFS_SB(sb)->list.prev = NULL;
+	spin_unlock(&orangefs_superblocks_lock);
+
+	/*
+	 * make sure that ORANGEFS_DEV_REMOUNT_ALL loop that might've seen us
+	 * gets completed before we free the dang thing.
+	 */
+	mutex_lock(&request_mutex);
+	mutex_unlock(&request_mutex);
+
+	/* free the orangefs superblock private data */
+	kfree(ORANGEFS_SB(sb));
+}
+
+int orangefs_inode_cache_initialize(void)
+{
+	orangefs_inode_cache = kmem_cache_create("orangefs_inode_cache",
+					      sizeof(struct orangefs_inode_s),
+					      0,
+					      ORANGEFS_CACHE_CREATE_FLAGS,
+					      orangefs_inode_cache_ctor);
+
+	if (!orangefs_inode_cache) {
+		gossip_err("Cannot create orangefs_inode_cache\n");
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+int orangefs_inode_cache_finalize(void)
+{
+	kmem_cache_destroy(orangefs_inode_cache);
+	return 0;
+}
diff --git a/fs/orangefs/symlink.c b/fs/orangefs/symlink.c
new file mode 100644
index 000000000000..6418dd638680
--- /dev/null
+++ b/fs/orangefs/symlink.c
@@ -0,0 +1,19 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-bufmap.h"
+
+struct inode_operations orangefs_symlink_inode_operations = {
+	.readlink = generic_readlink,
+	.get_link = simple_get_link,
+	.setattr = orangefs_setattr,
+	.getattr = orangefs_getattr,
+	.listxattr = orangefs_listxattr,
+	.setxattr = generic_setxattr,
+	.permission = orangefs_permission,
+};
diff --git a/fs/orangefs/upcall.h b/fs/orangefs/upcall.h
new file mode 100644
index 000000000000..001b20239407
--- /dev/null
+++ b/fs/orangefs/upcall.h
@@ -0,0 +1,246 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+#ifndef __UPCALL_H
+#define __UPCALL_H
+
+/*
+ * Sanitized this header file to fix
+ * 32-64 bit interaction issues between
+ * client-core and device
+ */
+struct orangefs_io_request_s {
+	__s32 __pad1;
+	__s32 buf_index;
+	__s32 count;
+	__s32 __pad2;
+	__s64 offset;
+	struct orangefs_object_kref refn;
+	enum ORANGEFS_io_type io_type;
+	__s32 readahead_size;
+};
+
+struct orangefs_lookup_request_s {
+	__s32 sym_follow;
+	__s32 __pad1;
+	struct orangefs_object_kref parent_refn;
+	char d_name[ORANGEFS_NAME_MAX];
+};
+
+struct orangefs_create_request_s {
+	struct orangefs_object_kref parent_refn;
+	struct ORANGEFS_sys_attr_s attributes;
+	char d_name[ORANGEFS_NAME_MAX];
+};
+
+struct orangefs_symlink_request_s {
+	struct orangefs_object_kref parent_refn;
+	struct ORANGEFS_sys_attr_s attributes;
+	char entry_name[ORANGEFS_NAME_MAX];
+	char target[ORANGEFS_NAME_MAX];
+};
+
+struct orangefs_getattr_request_s {
+	struct orangefs_object_kref refn;
+	__u32 mask;
+	__u32 __pad1;
+};
+
+struct orangefs_setattr_request_s {
+	struct orangefs_object_kref refn;
+	struct ORANGEFS_sys_attr_s attributes;
+};
+
+struct orangefs_remove_request_s {
+	struct orangefs_object_kref parent_refn;
+	char d_name[ORANGEFS_NAME_MAX];
+};
+
+struct orangefs_mkdir_request_s {
+	struct orangefs_object_kref parent_refn;
+	struct ORANGEFS_sys_attr_s attributes;
+	char d_name[ORANGEFS_NAME_MAX];
+};
+
+struct orangefs_readdir_request_s {
+	struct orangefs_object_kref refn;
+	__u64 token;
+	__s32 max_dirent_count;
+	__s32 buf_index;
+};
+
+struct orangefs_readdirplus_request_s {
+	struct orangefs_object_kref refn;
+	__u64 token;
+	__s32 max_dirent_count;
+	__u32 mask;
+	__s32 buf_index;
+	__s32 __pad1;
+};
+
+struct orangefs_rename_request_s {
+	struct orangefs_object_kref old_parent_refn;
+	struct orangefs_object_kref new_parent_refn;
+	char d_old_name[ORANGEFS_NAME_MAX];
+	char d_new_name[ORANGEFS_NAME_MAX];
+};
+
+struct orangefs_statfs_request_s {
+	__s32 fs_id;
+	__s32 __pad1;
+};
+
+struct orangefs_truncate_request_s {
+	struct orangefs_object_kref refn;
+	__s64 size;
+};
+
+struct orangefs_mmap_ra_cache_flush_request_s {
+	struct orangefs_object_kref refn;
+};
+
+struct orangefs_fs_mount_request_s {
+	char orangefs_config_server[ORANGEFS_MAX_SERVER_ADDR_LEN];
+};
+
+struct orangefs_fs_umount_request_s {
+	__s32 id;
+	__s32 fs_id;
+	char orangefs_config_server[ORANGEFS_MAX_SERVER_ADDR_LEN];
+};
+
+struct orangefs_getxattr_request_s {
+	struct orangefs_object_kref refn;
+	__s32 key_sz;
+	__s32 __pad1;
+	char key[ORANGEFS_MAX_XATTR_NAMELEN];
+};
+
+struct orangefs_setxattr_request_s {
+	struct orangefs_object_kref refn;
+	struct ORANGEFS_keyval_pair keyval;
+	__s32 flags;
+	__s32 __pad1;
+};
+
+struct orangefs_listxattr_request_s {
+	struct orangefs_object_kref refn;
+	__s32 requested_count;
+	__s32 __pad1;
+	__u64 token;
+};
+
+struct orangefs_removexattr_request_s {
+	struct orangefs_object_kref refn;
+	__s32 key_sz;
+	__s32 __pad1;
+	char key[ORANGEFS_MAX_XATTR_NAMELEN];
+};
+
+struct orangefs_op_cancel_s {
+	__u64 op_tag;
+};
+
+struct orangefs_fsync_request_s {
+	struct orangefs_object_kref refn;
+};
+
+enum orangefs_param_request_type {
+	ORANGEFS_PARAM_REQUEST_SET = 1,
+	ORANGEFS_PARAM_REQUEST_GET = 2
+};
+
+enum orangefs_param_request_op {
+	ORANGEFS_PARAM_REQUEST_OP_ACACHE_TIMEOUT_MSECS = 1,
+	ORANGEFS_PARAM_REQUEST_OP_ACACHE_HARD_LIMIT = 2,
+	ORANGEFS_PARAM_REQUEST_OP_ACACHE_SOFT_LIMIT = 3,
+	ORANGEFS_PARAM_REQUEST_OP_ACACHE_RECLAIM_PERCENTAGE = 4,
+	ORANGEFS_PARAM_REQUEST_OP_PERF_TIME_INTERVAL_SECS = 5,
+	ORANGEFS_PARAM_REQUEST_OP_PERF_HISTORY_SIZE = 6,
+	ORANGEFS_PARAM_REQUEST_OP_PERF_RESET = 7,
+	ORANGEFS_PARAM_REQUEST_OP_NCACHE_TIMEOUT_MSECS = 8,
+	ORANGEFS_PARAM_REQUEST_OP_NCACHE_HARD_LIMIT = 9,
+	ORANGEFS_PARAM_REQUEST_OP_NCACHE_SOFT_LIMIT = 10,
+	ORANGEFS_PARAM_REQUEST_OP_NCACHE_RECLAIM_PERCENTAGE = 11,
+	ORANGEFS_PARAM_REQUEST_OP_STATIC_ACACHE_TIMEOUT_MSECS = 12,
+	ORANGEFS_PARAM_REQUEST_OP_STATIC_ACACHE_HARD_LIMIT = 13,
+	ORANGEFS_PARAM_REQUEST_OP_STATIC_ACACHE_SOFT_LIMIT = 14,
+	ORANGEFS_PARAM_REQUEST_OP_STATIC_ACACHE_RECLAIM_PERCENTAGE = 15,
+	ORANGEFS_PARAM_REQUEST_OP_CLIENT_DEBUG = 16,
+	ORANGEFS_PARAM_REQUEST_OP_CCACHE_TIMEOUT_SECS = 17,
+	ORANGEFS_PARAM_REQUEST_OP_CCACHE_HARD_LIMIT = 18,
+	ORANGEFS_PARAM_REQUEST_OP_CCACHE_SOFT_LIMIT = 19,
+	ORANGEFS_PARAM_REQUEST_OP_CCACHE_RECLAIM_PERCENTAGE = 20,
+	ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_TIMEOUT_SECS = 21,
+	ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_HARD_LIMIT = 22,
+	ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_SOFT_LIMIT = 23,
+	ORANGEFS_PARAM_REQUEST_OP_CAPCACHE_RECLAIM_PERCENTAGE = 24,
+	ORANGEFS_PARAM_REQUEST_OP_TWO_MASK_VALUES = 25,
+};
+
+struct orangefs_param_request_s {
+	enum orangefs_param_request_type type;
+	enum orangefs_param_request_op op;
+	__s64 value;
+	char s_value[ORANGEFS_MAX_DEBUG_STRING_LEN];
+};
+
+enum orangefs_perf_count_request_type {
+	ORANGEFS_PERF_COUNT_REQUEST_ACACHE = 1,
+	ORANGEFS_PERF_COUNT_REQUEST_NCACHE = 2,
+	ORANGEFS_PERF_COUNT_REQUEST_CAPCACHE = 3,
+};
+
+struct orangefs_perf_count_request_s {
+	enum orangefs_perf_count_request_type type;
+	__s32 __pad1;
+};
+
+struct orangefs_fs_key_request_s {
+	__s32 fsid;
+	__s32 __pad1;
+};
+
+struct orangefs_upcall_s {
+	__s32 type;
+	__u32 uid;
+	__u32 gid;
+	int pid;
+	int tgid;
+	/* Trailers unused but must be retained for protocol compatibility. */
+	__s64 trailer_size;
+	char *trailer_buf;
+
+	union {
+		struct orangefs_io_request_s io;
+		struct orangefs_lookup_request_s lookup;
+		struct orangefs_create_request_s create;
+		struct orangefs_symlink_request_s sym;
+		struct orangefs_getattr_request_s getattr;
+		struct orangefs_setattr_request_s setattr;
+		struct orangefs_remove_request_s remove;
+		struct orangefs_mkdir_request_s mkdir;
+		struct orangefs_readdir_request_s readdir;
+		struct orangefs_readdirplus_request_s readdirplus;
+		struct orangefs_rename_request_s rename;
+		struct orangefs_statfs_request_s statfs;
+		struct orangefs_truncate_request_s truncate;
+		struct orangefs_mmap_ra_cache_flush_request_s ra_cache_flush;
+		struct orangefs_fs_mount_request_s fs_mount;
+		struct orangefs_fs_umount_request_s fs_umount;
+		struct orangefs_getxattr_request_s getxattr;
+		struct orangefs_setxattr_request_s setxattr;
+		struct orangefs_listxattr_request_s listxattr;
+		struct orangefs_removexattr_request_s removexattr;
+		struct orangefs_op_cancel_s cancel;
+		struct orangefs_fsync_request_s fsync;
+		struct orangefs_param_request_s param;
+		struct orangefs_perf_count_request_s perf_count;
+		struct orangefs_fs_key_request_s fs_key;
+	} req;
+};
+
+#endif /* __UPCALL_H */
diff --git a/fs/orangefs/waitqueue.c b/fs/orangefs/waitqueue.c
new file mode 100644
index 000000000000..31635bc303fe
--- /dev/null
+++ b/fs/orangefs/waitqueue.c
@@ -0,0 +1,357 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ * (C) 2011 Omnibond Systems
+ *
+ * Changes by Acxiom Corporation to implement generic service_operation()
+ * function, Copyright Acxiom Corporation, 2005.
+ *
+ * See COPYING in top-level directory.
+ */
+
+/*
+ *  In-kernel waitqueue operations.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-bufmap.h"
+
+static int wait_for_matching_downcall(struct orangefs_kernel_op_s *, long, bool);
+static void orangefs_clean_up_interrupted_operation(struct orangefs_kernel_op_s *);
+
+/*
+ * What we do in this function is to walk the list of operations that are
+ * present in the request queue and mark them as purged.
+ * NOTE: This is called from the device close after client-core has
+ * guaranteed that no new operations could appear on the list since the
+ * client-core is anyway going to exit.
+ */
+void purge_waiting_ops(void)
+{
+	struct orangefs_kernel_op_s *op;
+
+	spin_lock(&orangefs_request_list_lock);
+	list_for_each_entry(op, &orangefs_request_list, list) {
+		gossip_debug(GOSSIP_WAIT_DEBUG,
+			     "pvfs2-client-core: purging op tag %llu %s\n",
+			     llu(op->tag),
+			     get_opname_string(op));
+		set_op_state_purged(op);
+		gossip_debug(GOSSIP_DEV_DEBUG,
+			     "%s: op:%s: op_state:%d: process:%s:\n",
+			     __func__,
+			     get_opname_string(op),
+			     op->op_state,
+			     current->comm);
+	}
+	spin_unlock(&orangefs_request_list_lock);
+}
+
+/*
+ * submits a ORANGEFS operation and waits for it to complete
+ *
+ * Note op->downcall.status will contain the status of the operation (in
+ * errno format), whether provided by pvfs2-client or a result of failure to
+ * service the operation.  If the caller wishes to distinguish, then
+ * op->state can be checked to see if it was serviced or not.
+ *
+ * Returns contents of op->downcall.status for convenience
+ */
+int service_operation(struct orangefs_kernel_op_s *op,
+		      const char *op_name,
+		      int flags)
+{
+	long timeout = MAX_SCHEDULE_TIMEOUT;
+	int ret = 0;
+
+	DEFINE_WAIT(wait_entry);
+
+	op->upcall.tgid = current->tgid;
+	op->upcall.pid = current->pid;
+
+retry_servicing:
+	op->downcall.status = 0;
+	gossip_debug(GOSSIP_WAIT_DEBUG,
+		     "%s: %s op:%p: process:%s: pid:%d:\n",
+		     __func__,
+		     op_name,
+		     op,
+		     current->comm,
+		     current->pid);
+
+	/*
+	 * If ORANGEFS_OP_NO_MUTEX was set in flags, we need to avoid
+	 * acquiring the request_mutex because we're servicing a
+	 * high priority remount operation and the request_mutex is
+	 * already taken.
+	 */
+	if (!(flags & ORANGEFS_OP_NO_MUTEX)) {
+		if (flags & ORANGEFS_OP_INTERRUPTIBLE)
+			ret = mutex_lock_interruptible(&request_mutex);
+		else
+			ret = mutex_lock_killable(&request_mutex);
+		/*
+		 * check to see if we were interrupted while waiting for
+		 * mutex
+		 */
+		if (ret < 0) {
+			op->downcall.status = ret;
+			gossip_debug(GOSSIP_WAIT_DEBUG,
+				     "%s: service_operation interrupted.\n",
+				     __func__);
+			return ret;
+		}
+	}
+
+	/* queue up the operation */
+	spin_lock(&orangefs_request_list_lock);
+	spin_lock(&op->lock);
+	set_op_state_waiting(op);
+	gossip_debug(GOSSIP_DEV_DEBUG,
+		     "%s: op:%s: op_state:%d: process:%s:\n",
+		     __func__,
+		     get_opname_string(op),
+		     op->op_state,
+		     current->comm);
+	/* add high priority remount op to the front of the line. */
+	if (flags & ORANGEFS_OP_PRIORITY)
+		list_add(&op->list, &orangefs_request_list);
+	else
+		list_add_tail(&op->list, &orangefs_request_list);
+	spin_unlock(&op->lock);
+	wake_up_interruptible(&orangefs_request_list_waitq);
+	if (!__is_daemon_in_service()) {
+		gossip_debug(GOSSIP_WAIT_DEBUG,
+			     "%s:client core is NOT in service.\n",
+			     __func__);
+		timeout = op_timeout_secs * HZ;
+	}
+	spin_unlock(&orangefs_request_list_lock);
+
+	if (!(flags & ORANGEFS_OP_NO_MUTEX))
+		mutex_unlock(&request_mutex);
+
+	ret = wait_for_matching_downcall(op, timeout,
+					 flags & ORANGEFS_OP_INTERRUPTIBLE);
+
+	gossip_debug(GOSSIP_WAIT_DEBUG,
+		     "%s: wait_for_matching_downcall returned %d for %p\n",
+		     __func__,
+		     ret,
+		     op);
+
+	/* got matching downcall; make sure status is in errno format */
+	if (!ret) {
+		spin_unlock(&op->lock);
+		op->downcall.status =
+		    orangefs_normalize_to_errno(op->downcall.status);
+		ret = op->downcall.status;
+		goto out;
+	}
+
+	/* failed to get matching downcall */
+	if (ret == -ETIMEDOUT) {
+		gossip_err("%s: %s -- wait timed out; aborting attempt.\n",
+			   __func__,
+			   op_name);
+	}
+
+	/*
+	 * remove a waiting op from the request list or
+	 * remove an in-progress op from the in-progress list.
+	 */
+	orangefs_clean_up_interrupted_operation(op);
+
+	op->downcall.status = ret;
+	/* retry if operation has not been serviced and if requested */
+	if (ret == -EAGAIN) {
+		op->attempts++;
+		timeout = op_timeout_secs * HZ;
+		gossip_debug(GOSSIP_WAIT_DEBUG,
+			     "orangefs: tag %llu (%s)"
+			     " -- operation to be retried (%d attempt)\n",
+			     llu(op->tag),
+			     op_name,
+			     op->attempts);
+
+		/*
+		 * io ops (ops that use the shared memory buffer) have
+		 * to be returned to their caller for a retry. Other ops
+		 * can just be recycled here.
+		 */
+		if (!op->uses_shared_memory)
+			goto retry_servicing;
+	}
+
+out:
+	gossip_debug(GOSSIP_WAIT_DEBUG,
+		     "%s: %s returning: %d for %p.\n",
+		     __func__,
+		     op_name,
+		     ret,
+		     op);
+	return ret;
+}
+
+/* This can get called on an I/O op if it had a bad service_operation. */
+bool orangefs_cancel_op_in_progress(struct orangefs_kernel_op_s *op)
+{
+	u64 tag = op->tag;
+	if (!op_state_in_progress(op))
+		return false;
+
+	op->slot_to_free = op->upcall.req.io.buf_index;
+	memset(&op->upcall, 0, sizeof(op->upcall));
+	memset(&op->downcall, 0, sizeof(op->downcall));
+	op->upcall.type = ORANGEFS_VFS_OP_CANCEL;
+	op->upcall.req.cancel.op_tag = tag;
+	op->downcall.type = ORANGEFS_VFS_OP_INVALID;
+	op->downcall.status = -1;
+	orangefs_new_tag(op);
+
+	spin_lock(&orangefs_request_list_lock);
+	/* orangefs_request_list_lock is enough of a barrier here */
+	if (!__is_daemon_in_service()) {
+		spin_unlock(&orangefs_request_list_lock);
+		return false;
+	}
+	spin_lock(&op->lock);
+	set_op_state_waiting(op);
+	gossip_debug(GOSSIP_DEV_DEBUG,
+		     "%s: op:%s: op_state:%d: process:%s:\n",
+		     __func__,
+		     get_opname_string(op),
+		     op->op_state,
+		     current->comm);
+	list_add(&op->list, &orangefs_request_list);
+	spin_unlock(&op->lock);
+	spin_unlock(&orangefs_request_list_lock);
+
+	gossip_debug(GOSSIP_WAIT_DEBUG,
+		     "Attempting ORANGEFS operation cancellation of tag %llu\n",
+		     llu(tag));
+	return true;
+}
+
+/*
+ * Change an op to the "given up" state and remove it from its list.
+ */
+static void
+	orangefs_clean_up_interrupted_operation(struct orangefs_kernel_op_s *op)
+{
+	/*
+	 * handle interrupted cases depending on what state we were in when
+	 * the interruption is detected.
+	 *
+	 * Called with op->lock held.
+	 */
+
+	/*
+	 * List manipulation code elsewhere will ignore ops that
+	 * have been given up upon.
+	 */
+	op->op_state |= OP_VFS_STATE_GIVEN_UP;
+
+	if (list_empty(&op->list)) {
+		/* caught copying to/from daemon */
+		BUG_ON(op_state_serviced(op));
+		spin_unlock(&op->lock);
+		wait_for_completion(&op->waitq);
+	} else if (op_state_waiting(op)) {
+		/*
+		 * upcall hasn't been read; remove op from upcall request
+		 * list.
+		 */
+		spin_unlock(&op->lock);
+		spin_lock(&orangefs_request_list_lock);
+		list_del_init(&op->list);
+		spin_unlock(&orangefs_request_list_lock);
+		gossip_debug(GOSSIP_WAIT_DEBUG,
+			     "Interrupted: Removed op %p from request_list\n",
+			     op);
+	} else if (op_state_in_progress(op)) {
+		/* op must be removed from the in progress htable */
+		spin_unlock(&op->lock);
+		spin_lock(&htable_ops_in_progress_lock);
+		list_del_init(&op->list);
+		spin_unlock(&htable_ops_in_progress_lock);
+		gossip_debug(GOSSIP_WAIT_DEBUG,
+			     "Interrupted: Removed op %p"
+			     " from htable_ops_in_progress\n",
+			     op);
+	} else {
+		spin_unlock(&op->lock);
+		gossip_err("interrupted operation is in a weird state 0x%x\n",
+			   op->op_state);
+	}
+	reinit_completion(&op->waitq);
+}
+
+/*
+ * Sleeps on waitqueue waiting for matching downcall.
+ * If client-core finishes servicing, then we are good to go.
+ * else if client-core exits, we get woken up here, and retry with a timeout
+ *
+ * When this call returns to the caller, the specified op will no
+ * longer be in either the in_progress hash table or on the request list.
+ *
+ * Returns 0 on success and -errno on failure
+ * Errors are:
+ * EAGAIN in case we want the caller to requeue and try again..
+ * EINTR/EIO/ETIMEDOUT indicating we are done trying to service this
+ * operation since client-core seems to be exiting too often
+ * or if we were interrupted.
+ *
+ * Returns with op->lock taken.
+ */
+static int wait_for_matching_downcall(struct orangefs_kernel_op_s *op,
+				      long timeout,
+				      bool interruptible)
+{
+	long n;
+
+	/*
+	 * There's a "schedule_timeout" inside of these wait
+	 * primitives, during which the op is out of the hands of the
+	 * user process that needs something done and is being
+	 * manipulated by the client-core process.
+	 */
+	if (interruptible)
+		n = wait_for_completion_interruptible_timeout(&op->waitq,
+							      timeout);
+	else
+		n = wait_for_completion_killable_timeout(&op->waitq, timeout);
+
+	spin_lock(&op->lock);
+
+	if (op_state_serviced(op))
+		return 0;
+
+	if (unlikely(n < 0)) {
+		gossip_debug(GOSSIP_WAIT_DEBUG,
+			     "%s: operation interrupted, tag %llu, %p\n",
+			     __func__,
+			     llu(op->tag),
+			     op);
+		return -EINTR;
+	}
+	if (op_state_purged(op)) {
+		gossip_debug(GOSSIP_WAIT_DEBUG,
+			     "%s: operation purged, tag %llu, %p, %d\n",
+			     __func__,
+			     llu(op->tag),
+			     op,
+			     op->attempts);
+		return (op->attempts < ORANGEFS_PURGE_RETRY_COUNT) ?
+			 -EAGAIN :
+			 -EIO;
+	}
+	/* must have timed out, then... */
+	gossip_debug(GOSSIP_WAIT_DEBUG,
+		     "%s: operation timed out, tag %llu, %p, %d)\n",
+		     __func__,
+		     llu(op->tag),
+		     op,
+		     op->attempts);
+	return -ETIMEDOUT;
+}
diff --git a/fs/orangefs/xattr.c b/fs/orangefs/xattr.c
new file mode 100644
index 000000000000..63a6280d8c3a
--- /dev/null
+++ b/fs/orangefs/xattr.c
@@ -0,0 +1,530 @@
+/*
+ * (C) 2001 Clemson University and The University of Chicago
+ *
+ * See COPYING in top-level directory.
+ */
+
+/*
+ *  Linux VFS extended attribute operations.
+ */
+
+#include "protocol.h"
+#include "orangefs-kernel.h"
+#include "orangefs-bufmap.h"
+#include <linux/posix_acl_xattr.h>
+#include <linux/xattr.h>
+
+
+#define SYSTEM_ORANGEFS_KEY "system.pvfs2."
+#define SYSTEM_ORANGEFS_KEY_LEN 13
+
+/*
+ * this function returns
+ *   0 if the key corresponding to name is not meant to be printed as part
+ *     of a listxattr.
+ *   1 if the key corresponding to name is meant to be returned as part of
+ *     a listxattr.
+ * The ones that start SYSTEM_ORANGEFS_KEY are the ones to avoid printing.
+ */
+static int is_reserved_key(const char *key, size_t size)
+{
+
+	if (size < SYSTEM_ORANGEFS_KEY_LEN)
+		return 1;
+
+	return strncmp(key, SYSTEM_ORANGEFS_KEY, SYSTEM_ORANGEFS_KEY_LEN) ?  1 : 0;
+}
+
+static inline int convert_to_internal_xattr_flags(int setxattr_flags)
+{
+	int internal_flag = 0;
+
+	if (setxattr_flags & XATTR_REPLACE) {
+		/* Attribute must exist! */
+		internal_flag = ORANGEFS_XATTR_REPLACE;
+	} else if (setxattr_flags & XATTR_CREATE) {
+		/* Attribute must not exist */
+		internal_flag = ORANGEFS_XATTR_CREATE;
+	}
+	return internal_flag;
+}
+
+
+/*
+ * Tries to get a specified key's attributes of a given
+ * file into a user-specified buffer. Note that the getxattr
+ * interface allows for the users to probe the size of an
+ * extended attribute by passing in a value of 0 to size.
+ * Thus our return value is always the size of the attribute
+ * unless the key does not exist for the file and/or if
+ * there were errors in fetching the attribute value.
+ */
+ssize_t orangefs_inode_getxattr(struct inode *inode, const char *prefix,
+		const char *name, void *buffer, size_t size)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	struct orangefs_kernel_op_s *new_op = NULL;
+	ssize_t ret = -ENOMEM;
+	ssize_t length = 0;
+	int fsuid;
+	int fsgid;
+
+	gossip_debug(GOSSIP_XATTR_DEBUG,
+		     "%s: prefix %s name %s, buffer_size %zd\n",
+		     __func__, prefix, name, size);
+
+	if ((strlen(name) + strlen(prefix)) >= ORANGEFS_MAX_XATTR_NAMELEN) {
+		gossip_err("Invalid key length (%d)\n",
+			   (int)(strlen(name) + strlen(prefix)));
+		return -EINVAL;
+	}
+
+	fsuid = from_kuid(current_user_ns(), current_fsuid());
+	fsgid = from_kgid(current_user_ns(), current_fsgid());
+
+	gossip_debug(GOSSIP_XATTR_DEBUG,
+		     "getxattr on inode %pU, name %s "
+		     "(uid %o, gid %o)\n",
+		     get_khandle_from_ino(inode),
+		     name,
+		     fsuid,
+		     fsgid);
+
+	down_read(&orangefs_inode->xattr_sem);
+
+	new_op = op_alloc(ORANGEFS_VFS_OP_GETXATTR);
+	if (!new_op)
+		goto out_unlock;
+
+	new_op->upcall.req.getxattr.refn = orangefs_inode->refn;
+	ret = snprintf((char *)new_op->upcall.req.getxattr.key,
+		       ORANGEFS_MAX_XATTR_NAMELEN, "%s%s", prefix, name);
+
+	/*
+	 * NOTE: Although keys are meant to be NULL terminated textual
+	 * strings, I am going to explicitly pass the length just in case
+	 * we change this later on...
+	 */
+	new_op->upcall.req.getxattr.key_sz = ret + 1;
+
+	ret = service_operation(new_op, "orangefs_inode_getxattr",
+				get_interruptible_flag(inode));
+	if (ret != 0) {
+		if (ret == -ENOENT) {
+			ret = -ENODATA;
+			gossip_debug(GOSSIP_XATTR_DEBUG,
+				     "orangefs_inode_getxattr: inode %pU key %s"
+				     " does not exist!\n",
+				     get_khandle_from_ino(inode),
+				     (char *)new_op->upcall.req.getxattr.key);
+		}
+		goto out_release_op;
+	}
+
+	/*
+	 * Length returned includes null terminator.
+	 */
+	length = new_op->downcall.resp.getxattr.val_sz;
+
+	/*
+	 * Just return the length of the queried attribute.
+	 */
+	if (size == 0) {
+		ret = length;
+		goto out_release_op;
+	}
+
+	/*
+	 * Check to see if key length is > provided buffer size.
+	 */
+	if (length > size) {
+		ret = -ERANGE;
+		goto out_release_op;
+	}
+
+	memcpy(buffer, new_op->downcall.resp.getxattr.val, length);
+	memset(buffer + length, 0, size - length);
+	gossip_debug(GOSSIP_XATTR_DEBUG,
+	     "orangefs_inode_getxattr: inode %pU "
+	     "key %s key_sz %d, val_len %d\n",
+	     get_khandle_from_ino(inode),
+	     (char *)new_op->
+		upcall.req.getxattr.key,
+		     (int)new_op->
+		upcall.req.getxattr.key_sz,
+	     (int)ret);
+
+	ret = length;
+
+out_release_op:
+	op_release(new_op);
+out_unlock:
+	up_read(&orangefs_inode->xattr_sem);
+	return ret;
+}
+
+static int orangefs_inode_removexattr(struct inode *inode,
+			    const char *prefix,
+			    const char *name,
+			    int flags)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	struct orangefs_kernel_op_s *new_op = NULL;
+	int ret = -ENOMEM;
+
+	down_write(&orangefs_inode->xattr_sem);
+	new_op = op_alloc(ORANGEFS_VFS_OP_REMOVEXATTR);
+	if (!new_op)
+		goto out_unlock;
+
+	new_op->upcall.req.removexattr.refn = orangefs_inode->refn;
+	/*
+	 * NOTE: Although keys are meant to be NULL terminated
+	 * textual strings, I am going to explicitly pass the
+	 * length just in case we change this later on...
+	 */
+	ret = snprintf((char *)new_op->upcall.req.removexattr.key,
+		       ORANGEFS_MAX_XATTR_NAMELEN,
+		       "%s%s",
+		       (prefix ? prefix : ""),
+		       name);
+	new_op->upcall.req.removexattr.key_sz = ret + 1;
+
+	gossip_debug(GOSSIP_XATTR_DEBUG,
+		     "orangefs_inode_removexattr: key %s, key_sz %d\n",
+		     (char *)new_op->upcall.req.removexattr.key,
+		     (int)new_op->upcall.req.removexattr.key_sz);
+
+	ret = service_operation(new_op,
+				"orangefs_inode_removexattr",
+				get_interruptible_flag(inode));
+	if (ret == -ENOENT) {
+		/*
+		 * Request to replace a non-existent attribute is an error.
+		 */
+		if (flags & XATTR_REPLACE)
+			ret = -ENODATA;
+		else
+			ret = 0;
+	}
+
+	gossip_debug(GOSSIP_XATTR_DEBUG,
+		     "orangefs_inode_removexattr: returning %d\n", ret);
+
+	op_release(new_op);
+out_unlock:
+	up_write(&orangefs_inode->xattr_sem);
+	return ret;
+}
+
+/*
+ * Tries to set an attribute for a given key on a file.
+ *
+ * Returns a -ve number on error and 0 on success.  Key is text, but value
+ * can be binary!
+ */
+int orangefs_inode_setxattr(struct inode *inode, const char *prefix,
+		const char *name, const void *value, size_t size, int flags)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	struct orangefs_kernel_op_s *new_op;
+	int internal_flag = 0;
+	int ret = -ENOMEM;
+
+	gossip_debug(GOSSIP_XATTR_DEBUG,
+		     "%s: prefix %s, name %s, buffer_size %zd\n",
+		     __func__, prefix, name, size);
+
+	if (size >= ORANGEFS_MAX_XATTR_VALUELEN ||
+	    flags < 0) {
+		gossip_err("orangefs_inode_setxattr: bogus values of size(%d), flags(%d)\n",
+			   (int)size,
+			   flags);
+		return -EINVAL;
+	}
+
+	internal_flag = convert_to_internal_xattr_flags(flags);
+
+	if (prefix) {
+		if (strlen(name) + strlen(prefix) >= ORANGEFS_MAX_XATTR_NAMELEN) {
+			gossip_err
+			    ("orangefs_inode_setxattr: bogus key size (%d)\n",
+			     (int)(strlen(name) + strlen(prefix)));
+			return -EINVAL;
+		}
+	} else {
+		if (strlen(name) >= ORANGEFS_MAX_XATTR_NAMELEN) {
+			gossip_err
+			    ("orangefs_inode_setxattr: bogus key size (%d)\n",
+			     (int)(strlen(name)));
+			return -EINVAL;
+		}
+	}
+
+	/* This is equivalent to a removexattr */
+	if (size == 0 && value == NULL) {
+		gossip_debug(GOSSIP_XATTR_DEBUG,
+			     "removing xattr (%s%s)\n",
+			     prefix,
+			     name);
+		return orangefs_inode_removexattr(inode, prefix, name, flags);
+	}
+
+	gossip_debug(GOSSIP_XATTR_DEBUG,
+		     "setxattr on inode %pU, name %s\n",
+		     get_khandle_from_ino(inode),
+		     name);
+
+	down_write(&orangefs_inode->xattr_sem);
+	new_op = op_alloc(ORANGEFS_VFS_OP_SETXATTR);
+	if (!new_op)
+		goto out_unlock;
+
+
+	new_op->upcall.req.setxattr.refn = orangefs_inode->refn;
+	new_op->upcall.req.setxattr.flags = internal_flag;
+	/*
+	 * NOTE: Although keys are meant to be NULL terminated textual
+	 * strings, I am going to explicitly pass the length just in
+	 * case we change this later on...
+	 */
+	ret = snprintf((char *)new_op->upcall.req.setxattr.keyval.key,
+		       ORANGEFS_MAX_XATTR_NAMELEN,
+		       "%s%s",
+		       prefix, name);
+	new_op->upcall.req.setxattr.keyval.key_sz = ret + 1;
+	memcpy(new_op->upcall.req.setxattr.keyval.val, value, size);
+	new_op->upcall.req.setxattr.keyval.val_sz = size;
+
+	gossip_debug(GOSSIP_XATTR_DEBUG,
+		     "orangefs_inode_setxattr: key %s, key_sz %d "
+		     " value size %zd\n",
+		     (char *)new_op->upcall.req.setxattr.keyval.key,
+		     (int)new_op->upcall.req.setxattr.keyval.key_sz,
+		     size);
+
+	ret = service_operation(new_op,
+				"orangefs_inode_setxattr",
+				get_interruptible_flag(inode));
+
+	gossip_debug(GOSSIP_XATTR_DEBUG,
+		     "orangefs_inode_setxattr: returning %d\n",
+		     ret);
+
+	/* when request is serviced properly, free req op struct */
+	op_release(new_op);
+out_unlock:
+	up_write(&orangefs_inode->xattr_sem);
+	return ret;
+}
+
+/*
+ * Tries to get a specified object's keys into a user-specified buffer of a
+ * given size.  Note that like the previous instances of xattr routines, this
+ * also allows you to pass in a NULL pointer and 0 size to probe the size for
+ * subsequent memory allocations. Thus our return value is always the size of
+ * all the keys unless there were errors in fetching the keys!
+ */
+ssize_t orangefs_listxattr(struct dentry *dentry, char *buffer, size_t size)
+{
+	struct inode *inode = dentry->d_inode;
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	struct orangefs_kernel_op_s *new_op;
+	__u64 token = ORANGEFS_ITERATE_START;
+	ssize_t ret = -ENOMEM;
+	ssize_t total = 0;
+	int count_keys = 0;
+	int key_size;
+	int i = 0;
+	int returned_count = 0;
+
+	if (size > 0 && buffer == NULL) {
+		gossip_err("%s: bogus NULL pointers\n", __func__);
+		return -EINVAL;
+	}
+
+	down_read(&orangefs_inode->xattr_sem);
+	new_op = op_alloc(ORANGEFS_VFS_OP_LISTXATTR);
+	if (!new_op)
+		goto out_unlock;
+
+	if (buffer && size > 0)
+		memset(buffer, 0, size);
+
+try_again:
+	key_size = 0;
+	new_op->upcall.req.listxattr.refn = orangefs_inode->refn;
+	new_op->upcall.req.listxattr.token = token;
+	new_op->upcall.req.listxattr.requested_count =
+	    (size == 0) ? 0 : ORANGEFS_MAX_XATTR_LISTLEN;
+	ret = service_operation(new_op, __func__,
+				get_interruptible_flag(inode));
+	if (ret != 0)
+		goto done;
+
+	if (size == 0) {
+		/*
+		 * This is a bit of a big upper limit, but I did not want to
+		 * spend too much time getting this correct, since users end
+		 * up allocating memory rather than us...
+		 */
+		total = new_op->downcall.resp.listxattr.returned_count *
+			ORANGEFS_MAX_XATTR_NAMELEN;
+		goto done;
+	}
+
+	returned_count = new_op->downcall.resp.listxattr.returned_count;
+	if (returned_count < 0 ||
+	    returned_count >= ORANGEFS_MAX_XATTR_LISTLEN) {
+		gossip_err("%s: impossible value for returned_count:%d:\n",
+		__func__,
+		returned_count);
+		ret = -EIO;
+		goto done;
+	}
+
+	/*
+	 * Check to see how much can be fit in the buffer. Fit only whole keys.
+	 */
+	for (i = 0; i < returned_count; i++) {
+		if (new_op->downcall.resp.listxattr.lengths[i] < 0 ||
+		    new_op->downcall.resp.listxattr.lengths[i] >
+		    ORANGEFS_MAX_XATTR_NAMELEN) {
+			gossip_err("%s: impossible value for lengths[%d]\n",
+			    __func__,
+			    new_op->downcall.resp.listxattr.lengths[i]);
+			ret = -EIO;
+			goto done;
+		}
+		if (total + new_op->downcall.resp.listxattr.lengths[i] > size)
+			goto done;
+
+		/*
+		 * Since many dumb programs try to setxattr() on our reserved
+		 * xattrs this is a feeble attempt at defeating those by not
+		 * listing them in the output of listxattr.. sigh
+		 */
+		if (is_reserved_key(new_op->downcall.resp.listxattr.key +
+				    key_size,
+				    new_op->downcall.resp.
+					listxattr.lengths[i])) {
+			gossip_debug(GOSSIP_XATTR_DEBUG, "Copying key %d -> %s\n",
+					i, new_op->downcall.resp.listxattr.key +
+						key_size);
+			memcpy(buffer + total,
+				new_op->downcall.resp.listxattr.key + key_size,
+				new_op->downcall.resp.listxattr.lengths[i]);
+			total += new_op->downcall.resp.listxattr.lengths[i];
+			count_keys++;
+		} else {
+			gossip_debug(GOSSIP_XATTR_DEBUG, "[RESERVED] key %d -> %s\n",
+					i, new_op->downcall.resp.listxattr.key +
+						key_size);
+		}
+		key_size += new_op->downcall.resp.listxattr.lengths[i];
+	}
+
+	/*
+	 * Since the buffer was large enough, we might have to continue
+	 * fetching more keys!
+	 */
+	token = new_op->downcall.resp.listxattr.token;
+	if (token != ORANGEFS_ITERATE_END)
+		goto try_again;
+
+done:
+	gossip_debug(GOSSIP_XATTR_DEBUG, "%s: returning %d"
+		     " [size of buffer %ld] (filled in %d keys)\n",
+		     __func__,
+		     ret ? (int)ret : (int)total,
+		     (long)size,
+		     count_keys);
+	op_release(new_op);
+	if (ret == 0)
+		ret = total;
+out_unlock:
+	up_read(&orangefs_inode->xattr_sem);
+	return ret;
+}
+
+static int orangefs_xattr_set_default(const struct xattr_handler *handler,
+				      struct dentry *dentry,
+				      const char *name,
+				      const void *buffer,
+				      size_t size,
+				      int flags)
+{
+	return orangefs_inode_setxattr(dentry->d_inode,
+				    ORANGEFS_XATTR_NAME_DEFAULT_PREFIX,
+				    name,
+				    buffer,
+				    size,
+				    flags);
+}
+
+static int orangefs_xattr_get_default(const struct xattr_handler *handler,
+				      struct dentry *dentry,
+				      const char *name,
+				      void *buffer,
+				      size_t size)
+{
+	return orangefs_inode_getxattr(dentry->d_inode,
+				    ORANGEFS_XATTR_NAME_DEFAULT_PREFIX,
+				    name,
+				    buffer,
+				    size);
+
+}
+
+static int orangefs_xattr_set_trusted(const struct xattr_handler *handler,
+				     struct dentry *dentry,
+				     const char *name,
+				     const void *buffer,
+				     size_t size,
+				     int flags)
+{
+	return orangefs_inode_setxattr(dentry->d_inode,
+				    ORANGEFS_XATTR_NAME_TRUSTED_PREFIX,
+				    name,
+				    buffer,
+				    size,
+				    flags);
+}
+
+static int orangefs_xattr_get_trusted(const struct xattr_handler *handler,
+				      struct dentry *dentry,
+				      const char *name,
+				      void *buffer,
+				      size_t size)
+{
+	return orangefs_inode_getxattr(dentry->d_inode,
+				    ORANGEFS_XATTR_NAME_TRUSTED_PREFIX,
+				    name,
+				    buffer,
+				    size);
+}
+
+static struct xattr_handler orangefs_xattr_trusted_handler = {
+	.prefix = ORANGEFS_XATTR_NAME_TRUSTED_PREFIX,
+	.get = orangefs_xattr_get_trusted,
+	.set = orangefs_xattr_set_trusted,
+};
+
+static struct xattr_handler orangefs_xattr_default_handler = {
+	/*
+	 * NOTE: this is set to be the empty string.
+	 * so that all un-prefixed xattrs keys get caught
+	 * here!
+	 */
+	.prefix = ORANGEFS_XATTR_NAME_DEFAULT_PREFIX,
+	.get = orangefs_xattr_get_default,
+	.set = orangefs_xattr_set_default,
+};
+
+const struct xattr_handler *orangefs_xattr_handlers[] = {
+	&posix_acl_access_xattr_handler,
+	&posix_acl_default_xattr_handler,
+	&orangefs_xattr_trusted_handler,
+	&orangefs_xattr_default_handler,
+	NULL
+};
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 871fcb67be97..cc514da6f3e7 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -7,6 +7,7 @@
  * the Free Software Foundation.
  */
 
+#include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/file.h>
@@ -16,15 +17,46 @@
 #include <linux/uaccess.h>
 #include <linux/sched.h>
 #include <linux/namei.h>
+#include <linux/fdtable.h>
+#include <linux/ratelimit.h>
 #include "overlayfs.h"
 
 #define OVL_COPY_UP_CHUNK_SIZE (1 << 20)
 
+static bool __read_mostly ovl_check_copy_up;
+module_param_named(check_copy_up, ovl_check_copy_up, bool,
+		   S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(ovl_check_copy_up,
+		 "Warn on copy-up when causing process also has a R/O fd open");
+
+static int ovl_check_fd(const void *data, struct file *f, unsigned int fd)
+{
+	const struct dentry *dentry = data;
+
+	if (f->f_inode == d_inode(dentry))
+		pr_warn_ratelimited("overlayfs: Warning: Copying up %pD, but open R/O on fd %u which will cease to be coherent [pid=%d %s]\n",
+				    f, fd, current->pid, current->comm);
+	return 0;
+}
+
+/*
+ * Check the fds open by this process and warn if something like the following
+ * scenario is about to occur:
+ *
+ *	fd1 = open("foo", O_RDONLY);
+ *	fd2 = open("foo", O_RDWR);
+ */
+static void ovl_do_check_copy_up(struct dentry *dentry)
+{
+	if (ovl_check_copy_up)
+		iterate_fd(current->files, 0, ovl_check_fd, dentry);
+}
+
 int ovl_copy_xattr(struct dentry *old, struct dentry *new)
 {
-	ssize_t list_size, size;
-	char *buf, *name, *value;
-	int error;
+	ssize_t list_size, size, value_size = 0;
+	char *buf, *name, *value = NULL;
+	int uninitialized_var(error);
 
 	if (!old->d_inode->i_op->getxattr ||
 	    !new->d_inode->i_op->getxattr)
@@ -41,29 +73,40 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new)
 	if (!buf)
 		return -ENOMEM;
 
-	error = -ENOMEM;
-	value = kmalloc(XATTR_SIZE_MAX, GFP_KERNEL);
-	if (!value)
-		goto out;
-
 	list_size = vfs_listxattr(old, buf, list_size);
 	if (list_size <= 0) {
 		error = list_size;
-		goto out_free_value;
+		goto out;
 	}
 
 	for (name = buf; name < (buf + list_size); name += strlen(name) + 1) {
-		size = vfs_getxattr(old, name, value, XATTR_SIZE_MAX);
-		if (size <= 0) {
+retry:
+		size = vfs_getxattr(old, name, value, value_size);
+		if (size == -ERANGE)
+			size = vfs_getxattr(old, name, NULL, 0);
+
+		if (size < 0) {
 			error = size;
-			goto out_free_value;
+			break;
 		}
+
+		if (size > value_size) {
+			void *new;
+
+			new = krealloc(value, size, GFP_KERNEL);
+			if (!new) {
+				error = -ENOMEM;
+				break;
+			}
+			value = new;
+			value_size = size;
+			goto retry;
+		}
+
 		error = vfs_setxattr(new, name, value, size, 0);
 		if (error)
-			goto out_free_value;
+			break;
 	}
-
-out_free_value:
 	kfree(value);
 out:
 	kfree(buf);
@@ -195,8 +238,7 @@ int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat)
 
 static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
 			      struct dentry *dentry, struct path *lowerpath,
-			      struct kstat *stat, struct iattr *attr,
-			      const char *link)
+			      struct kstat *stat, const char *link)
 {
 	struct inode *wdir = workdir->d_inode;
 	struct inode *udir = upperdir->d_inode;
@@ -225,6 +267,7 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
 
 	if (S_ISREG(stat->mode)) {
 		struct path upperpath;
+
 		ovl_path_upper(dentry, &upperpath);
 		BUG_ON(upperpath.dentry != NULL);
 		upperpath.dentry = newdentry;
@@ -238,11 +281,9 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
 	if (err)
 		goto out_cleanup;
 
-	mutex_lock(&newdentry->d_inode->i_mutex);
+	inode_lock(newdentry->d_inode);
 	err = ovl_set_attr(newdentry, stat);
-	if (!err && attr)
-		err = notify_change(newdentry, attr, NULL);
-	mutex_unlock(&newdentry->d_inode->i_mutex);
+	inode_unlock(newdentry->d_inode);
 	if (err)
 		goto out_cleanup;
 
@@ -286,8 +327,7 @@ out_cleanup:
  * that point the file will have already been copied up anyway.
  */
 int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
-		    struct path *lowerpath, struct kstat *stat,
-		    struct iattr *attr)
+		    struct path *lowerpath, struct kstat *stat)
 {
 	struct dentry *workdir = ovl_workdir(dentry);
 	int err;
@@ -302,6 +342,8 @@ int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 	if (WARN_ON(!workdir))
 		return -EROFS;
 
+	ovl_do_check_copy_up(lowerpath->dentry);
+
 	ovl_path_upper(parent, &parentpath);
 	upperdir = parentpath.dentry;
 
@@ -345,26 +387,19 @@ int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 	}
 	upperdentry = ovl_dentry_upper(dentry);
 	if (upperdentry) {
-		unlock_rename(workdir, upperdir);
+		/* Raced with another copy-up?  Nothing to do, then... */
 		err = 0;
-		/* Raced with another copy-up?  Do the setattr here */
-		if (attr) {
-			mutex_lock(&upperdentry->d_inode->i_mutex);
-			err = notify_change(upperdentry, attr, NULL);
-			mutex_unlock(&upperdentry->d_inode->i_mutex);
-		}
-		goto out_put_cred;
+		goto out_unlock;
 	}
 
 	err = ovl_copy_up_locked(workdir, upperdir, dentry, lowerpath,
-				 stat, attr, link);
+				 stat, link);
 	if (!err) {
 		/* Restore timestamps on parent (best effort) */
 		ovl_set_timestamps(upperdir, &pstat);
 	}
 out_unlock:
 	unlock_rename(workdir, upperdir);
-out_put_cred:
 	revert_creds(old_cred);
 	put_cred(override_cred);
 
@@ -406,7 +441,7 @@ int ovl_copy_up(struct dentry *dentry)
 		ovl_path_lower(next, &lowerpath);
 		err = vfs_getattr(&lowerpath, &stat);
 		if (!err)
-			err = ovl_copy_up_one(parent, next, &lowerpath, &stat, NULL);
+			err = ovl_copy_up_one(parent, next, &lowerpath, &stat);
 
 		dput(parent);
 		dput(next);
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 692ceda3bc21..b3fc0a35bf62 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -167,7 +167,7 @@ static int ovl_create_upper(struct dentry *dentry, struct inode *inode,
 	struct dentry *newdentry;
 	int err;
 
-	mutex_lock_nested(&udir->i_mutex, I_MUTEX_PARENT);
+	inode_lock_nested(udir, I_MUTEX_PARENT);
 	newdentry = lookup_one_len(dentry->d_name.name, upperdir,
 				   dentry->d_name.len);
 	err = PTR_ERR(newdentry);
@@ -185,7 +185,7 @@ static int ovl_create_upper(struct dentry *dentry, struct inode *inode,
 out_dput:
 	dput(newdentry);
 out_unlock:
-	mutex_unlock(&udir->i_mutex);
+	inode_unlock(udir);
 	return err;
 }
 
@@ -258,9 +258,9 @@ static struct dentry *ovl_clear_empty(struct dentry *dentry,
 	if (err)
 		goto out_cleanup;
 
-	mutex_lock(&opaquedir->d_inode->i_mutex);
+	inode_lock(opaquedir->d_inode);
 	err = ovl_set_attr(opaquedir, &stat);
-	mutex_unlock(&opaquedir->d_inode->i_mutex);
+	inode_unlock(opaquedir->d_inode);
 	if (err)
 		goto out_cleanup;
 
@@ -596,21 +596,25 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir)
 {
 	struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
 	struct inode *dir = upperdir->d_inode;
-	struct dentry *upper = ovl_dentry_upper(dentry);
+	struct dentry *upper;
 	int err;
 
-	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
+	inode_lock_nested(dir, I_MUTEX_PARENT);
+	upper = lookup_one_len(dentry->d_name.name, upperdir,
+			       dentry->d_name.len);
+	err = PTR_ERR(upper);
+	if (IS_ERR(upper))
+		goto out_unlock;
+
 	err = -ESTALE;
-	if (upper->d_parent == upperdir) {
-		/* Don't let d_delete() think it can reset d_inode */
-		dget(upper);
+	if (upper == ovl_dentry_upper(dentry)) {
 		if (is_dir)
 			err = vfs_rmdir(dir, upper);
 		else
 			err = vfs_unlink(dir, upper, NULL);
-		dput(upper);
 		ovl_dentry_version_inc(dentry->d_parent);
 	}
+	dput(upper);
 
 	/*
 	 * Keeping this dentry hashed would mean having to release
@@ -618,8 +622,10 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir)
 	 * sole user of this dentry.  Too tricky...  Just unhash for
 	 * now.
 	 */
-	d_drop(dentry);
-	mutex_unlock(&dir->i_mutex);
+	if (!err)
+		d_drop(dentry);
+out_unlock:
+	inode_unlock(dir);
 
 	return err;
 }
@@ -713,7 +719,6 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 	struct dentry *trap;
 	bool old_opaque;
 	bool new_opaque;
-	bool new_create = false;
 	bool cleanup_whiteout = false;
 	bool overwrite = !(flags & RENAME_EXCHANGE);
 	bool is_dir = d_is_dir(old);
@@ -839,29 +844,38 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 
 	trap = lock_rename(new_upperdir, old_upperdir);
 
-	olddentry = ovl_dentry_upper(old);
-	newdentry = ovl_dentry_upper(new);
-	if (newdentry) {
+
+	olddentry = lookup_one_len(old->d_name.name, old_upperdir,
+				   old->d_name.len);
+	err = PTR_ERR(olddentry);
+	if (IS_ERR(olddentry))
+		goto out_unlock;
+
+	err = -ESTALE;
+	if (olddentry != ovl_dentry_upper(old))
+		goto out_dput_old;
+
+	newdentry = lookup_one_len(new->d_name.name, new_upperdir,
+				   new->d_name.len);
+	err = PTR_ERR(newdentry);
+	if (IS_ERR(newdentry))
+		goto out_dput_old;
+
+	err = -ESTALE;
+	if (ovl_dentry_upper(new)) {
 		if (opaquedir) {
-			newdentry = opaquedir;
-			opaquedir = NULL;
+			if (newdentry != opaquedir)
+				goto out_dput;
 		} else {
-			dget(newdentry);
+			if (newdentry != ovl_dentry_upper(new))
+				goto out_dput;
 		}
 	} else {
-		new_create = true;
-		newdentry = lookup_one_len(new->d_name.name, new_upperdir,
-					   new->d_name.len);
-		err = PTR_ERR(newdentry);
-		if (IS_ERR(newdentry))
-			goto out_unlock;
+		if (!d_is_negative(newdentry) &&
+		    (!new_opaque || !ovl_is_whiteout(newdentry)))
+			goto out_dput;
 	}
 
-	err = -ESTALE;
-	if (olddentry->d_parent != old_upperdir)
-		goto out_dput;
-	if (newdentry->d_parent != new_upperdir)
-		goto out_dput;
 	if (olddentry == trap)
 		goto out_dput;
 	if (newdentry == trap)
@@ -903,6 +917,13 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 	if (!overwrite && new_is_dir && !old_opaque && new_opaque)
 		ovl_remove_opaque(newdentry);
 
+	/*
+	 * Old dentry now lives in different location. Dentries in
+	 * lowerstack are stale. We cannot drop them here because
+	 * access to them is lockless. This could be only pure upper
+	 * or opaque directory - numlower is zero. Or upper non-dir
+	 * entry - its pureness is tracked by flag opaque.
+	 */
 	if (old_opaque != new_opaque) {
 		ovl_dentry_set_opaque(old, new_opaque);
 		if (!overwrite)
@@ -917,6 +938,8 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 
 out_dput:
 	dput(newdentry);
+out_dput_old:
+	dput(olddentry);
 out_unlock:
 	unlock_rename(new_upperdir, old_upperdir);
 out_revert_creds:
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index ec0c2a050043..a4ff5d0d7db9 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -12,8 +12,7 @@
 #include <linux/xattr.h>
 #include "overlayfs.h"
 
-static int ovl_copy_up_last(struct dentry *dentry, struct iattr *attr,
-			    bool no_data)
+static int ovl_copy_up_truncate(struct dentry *dentry)
 {
 	int err;
 	struct dentry *parent;
@@ -30,10 +29,8 @@ static int ovl_copy_up_last(struct dentry *dentry, struct iattr *attr,
 	if (err)
 		goto out_dput_parent;
 
-	if (no_data)
-		stat.size = 0;
-
-	err = ovl_copy_up_one(parent, dentry, &lowerpath, &stat, attr);
+	stat.size = 0;
+	err = ovl_copy_up_one(parent, dentry, &lowerpath, &stat);
 
 out_dput_parent:
 	dput(parent);
@@ -45,17 +42,32 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr)
 	int err;
 	struct dentry *upperdentry;
 
+	/*
+	 * Check for permissions before trying to copy-up.  This is redundant
+	 * since it will be rechecked later by ->setattr() on upper dentry.  But
+	 * without this, copy-up can be triggered by just about anybody.
+	 *
+	 * We don't initialize inode->size, which just means that
+	 * inode_newsize_ok() will always check against MAX_LFS_FILESIZE and not
+	 * check for a swapfile (which this won't be anyway).
+	 */
+	err = inode_change_ok(dentry->d_inode, attr);
+	if (err)
+		return err;
+
 	err = ovl_want_write(dentry);
 	if (err)
 		goto out;
 
-	upperdentry = ovl_dentry_upper(dentry);
-	if (upperdentry) {
-		mutex_lock(&upperdentry->d_inode->i_mutex);
+	err = ovl_copy_up(dentry);
+	if (!err) {
+		upperdentry = ovl_dentry_upper(dentry);
+
+		inode_lock(upperdentry->d_inode);
 		err = notify_change(upperdentry, attr, NULL);
-		mutex_unlock(&upperdentry->d_inode->i_mutex);
-	} else {
-		err = ovl_copy_up_last(dentry, attr, false);
+		if (!err)
+			ovl_copyattr(upperdentry->d_inode, dentry->d_inode);
+		inode_unlock(upperdentry->d_inode);
 	}
 	ovl_drop_write(dentry);
 out:
@@ -98,6 +110,29 @@ int ovl_permission(struct inode *inode, int mask)
 
 	realdentry = ovl_entry_real(oe, &is_upper);
 
+	if (ovl_is_default_permissions(inode)) {
+		struct kstat stat;
+		struct path realpath = { .dentry = realdentry };
+
+		if (mask & MAY_NOT_BLOCK)
+			return -ECHILD;
+
+		realpath.mnt = ovl_entry_mnt_real(oe, inode, is_upper);
+
+		err = vfs_getattr(&realpath, &stat);
+		if (err)
+			return err;
+
+		if ((stat.mode ^ inode->i_mode) & S_IFMT)
+			return -ESTALE;
+
+		inode->i_mode = stat.mode;
+		inode->i_uid = stat.uid;
+		inode->i_gid = stat.gid;
+
+		return generic_permission(inode, mask);
+	}
+
 	/* Careful in RCU walk mode */
 	realinode = ACCESS_ONCE(realdentry->d_inode);
 	if (!realinode) {
@@ -134,57 +169,23 @@ out_dput:
 	return err;
 }
 
-
-struct ovl_link_data {
-	struct dentry *realdentry;
-	void *cookie;
-};
-
-static const char *ovl_follow_link(struct dentry *dentry, void **cookie)
+static const char *ovl_get_link(struct dentry *dentry,
+				struct inode *inode,
+				struct delayed_call *done)
 {
 	struct dentry *realdentry;
 	struct inode *realinode;
-	struct ovl_link_data *data = NULL;
-	const char *ret;
+
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
 
 	realdentry = ovl_dentry_real(dentry);
 	realinode = realdentry->d_inode;
 
-	if (WARN_ON(!realinode->i_op->follow_link))
+	if (WARN_ON(!realinode->i_op->get_link))
 		return ERR_PTR(-EPERM);
 
-	if (realinode->i_op->put_link) {
-		data = kmalloc(sizeof(struct ovl_link_data), GFP_KERNEL);
-		if (!data)
-			return ERR_PTR(-ENOMEM);
-		data->realdentry = realdentry;
-	}
-
-	ret = realinode->i_op->follow_link(realdentry, cookie);
-	if (IS_ERR_OR_NULL(ret)) {
-		kfree(data);
-		return ret;
-	}
-
-	if (data)
-		data->cookie = *cookie;
-
-	*cookie = data;
-
-	return ret;
-}
-
-static void ovl_put_link(struct inode *unused, void *c)
-{
-	struct inode *realinode;
-	struct ovl_link_data *data = c;
-
-	if (!data)
-		return;
-
-	realinode = data->realdentry->d_inode;
-	realinode->i_op->put_link(realinode, data->cookie);
-	kfree(data);
+	return realinode->i_op->get_link(realdentry, realinode, done);
 }
 
 static int ovl_readlink(struct dentry *dentry, char __user *buf, int bufsiz)
@@ -353,7 +354,7 @@ struct inode *ovl_d_select_inode(struct dentry *dentry, unsigned file_flags)
 			return ERR_PTR(err);
 
 		if (file_flags & O_TRUNC)
-			err = ovl_copy_up_last(dentry, NULL, true);
+			err = ovl_copy_up_truncate(dentry);
 		else
 			err = ovl_copy_up(dentry);
 		ovl_drop_write(dentry);
@@ -381,8 +382,7 @@ static const struct inode_operations ovl_file_inode_operations = {
 
 static const struct inode_operations ovl_symlink_inode_operations = {
 	.setattr	= ovl_setattr,
-	.follow_link	= ovl_follow_link,
-	.put_link	= ovl_put_link,
+	.get_link	= ovl_get_link,
 	.readlink	= ovl_readlink,
 	.getattr	= ovl_getattr,
 	.setxattr	= ovl_setxattr,
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index ea5a40b06e3a..6a7090f4a441 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -142,7 +142,10 @@ struct dentry *ovl_dentry_upper(struct dentry *dentry);
 struct dentry *ovl_dentry_lower(struct dentry *dentry);
 struct dentry *ovl_dentry_real(struct dentry *dentry);
 struct dentry *ovl_entry_real(struct ovl_entry *oe, bool *is_upper);
+struct vfsmount *ovl_entry_mnt_real(struct ovl_entry *oe, struct inode *inode,
+				    bool is_upper);
 struct ovl_dir_cache *ovl_dir_cache(struct dentry *dentry);
+bool ovl_is_default_permissions(struct inode *inode);
 void ovl_set_dir_cache(struct dentry *dentry, struct ovl_dir_cache *cache);
 struct dentry *ovl_workdir(struct dentry *dentry);
 int ovl_want_write(struct dentry *dentry);
@@ -163,6 +166,7 @@ extern const struct file_operations ovl_dir_operations;
 int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list);
 void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list);
 void ovl_cache_free(struct list_head *list);
+int ovl_check_d_type_supported(struct path *realpath);
 
 /* inode.c */
 int ovl_setattr(struct dentry *dentry, struct iattr *attr);
@@ -194,7 +198,6 @@ void ovl_cleanup(struct inode *dir, struct dentry *dentry);
 /* copy_up.c */
 int ovl_copy_up(struct dentry *dentry);
 int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
-		    struct path *lowerpath, struct kstat *stat,
-		    struct iattr *attr);
+		    struct path *lowerpath, struct kstat *stat);
 int ovl_copy_xattr(struct dentry *old, struct dentry *new);
 int ovl_set_attr(struct dentry *upper, struct kstat *stat);
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 70e9af551600..6ec1e43a9a54 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -36,13 +36,14 @@ struct ovl_dir_cache {
 
 struct ovl_readdir_data {
 	struct dir_context ctx;
-	bool is_merge;
+	bool is_lowest;
 	struct rb_root root;
 	struct list_head *list;
 	struct list_head middle;
 	struct ovl_cache_entry *first_maybe_whiteout;
 	int count;
 	int err;
+	bool d_type_supported;
 };
 
 struct ovl_dir_file {
@@ -139,9 +140,9 @@ static int ovl_cache_entry_add_rb(struct ovl_readdir_data *rdd,
 	return 0;
 }
 
-static int ovl_fill_lower(struct ovl_readdir_data *rdd,
-			  const char *name, int namelen,
-			  loff_t offset, u64 ino, unsigned int d_type)
+static int ovl_fill_lowest(struct ovl_readdir_data *rdd,
+			   const char *name, int namelen,
+			   loff_t offset, u64 ino, unsigned int d_type)
 {
 	struct ovl_cache_entry *p;
 
@@ -193,10 +194,10 @@ static int ovl_fill_merge(struct dir_context *ctx, const char *name,
 		container_of(ctx, struct ovl_readdir_data, ctx);
 
 	rdd->count++;
-	if (!rdd->is_merge)
+	if (!rdd->is_lowest)
 		return ovl_cache_entry_add_rb(rdd, name, namelen, ino, d_type);
 	else
-		return ovl_fill_lower(rdd, name, namelen, offset, ino, d_type);
+		return ovl_fill_lowest(rdd, name, namelen, offset, ino, d_type);
 }
 
 static int ovl_check_whiteouts(struct dentry *dir, struct ovl_readdir_data *rdd)
@@ -228,7 +229,7 @@ static int ovl_check_whiteouts(struct dentry *dir, struct ovl_readdir_data *rdd)
 				dput(dentry);
 			}
 		}
-		mutex_unlock(&dir->d_inode->i_mutex);
+		inode_unlock(dir->d_inode);
 	}
 	revert_creds(old_cred);
 	put_cred(override_cred);
@@ -289,7 +290,7 @@ static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list)
 		.ctx.actor = ovl_fill_merge,
 		.list = list,
 		.root = RB_ROOT,
-		.is_merge = false,
+		.is_lowest = false,
 	};
 	int idx, next;
 
@@ -306,7 +307,7 @@ static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list)
 			 * allows offsets to be reasonably constant
 			 */
 			list_add(&rdd.middle, rdd.list);
-			rdd.is_merge = true;
+			rdd.is_lowest = true;
 			err = ovl_dir_read(&realpath, &rdd);
 			list_del(&rdd.middle);
 		}
@@ -399,7 +400,7 @@ static loff_t ovl_dir_llseek(struct file *file, loff_t offset, int origin)
 	loff_t res;
 	struct ovl_dir_file *od = file->private_data;
 
-	mutex_lock(&file_inode(file)->i_mutex);
+	inode_lock(file_inode(file));
 	if (!file->f_pos)
 		ovl_dir_reset(file);
 
@@ -429,7 +430,7 @@ static loff_t ovl_dir_llseek(struct file *file, loff_t offset, int origin)
 		res = offset;
 	}
 out_unlock:
-	mutex_unlock(&file_inode(file)->i_mutex);
+	inode_unlock(file_inode(file));
 
 	return res;
 }
@@ -454,10 +455,10 @@ static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end,
 			ovl_path_upper(dentry, &upperpath);
 			realfile = ovl_path_open(&upperpath, O_RDONLY);
 			smp_mb__before_spinlock();
-			mutex_lock(&inode->i_mutex);
+			inode_lock(inode);
 			if (!od->upperfile) {
 				if (IS_ERR(realfile)) {
-					mutex_unlock(&inode->i_mutex);
+					inode_unlock(inode);
 					return PTR_ERR(realfile);
 				}
 				od->upperfile = realfile;
@@ -467,7 +468,7 @@ static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end,
 					fput(realfile);
 				realfile = od->upperfile;
 			}
-			mutex_unlock(&inode->i_mutex);
+			inode_unlock(inode);
 		}
 	}
 
@@ -479,9 +480,9 @@ static int ovl_dir_release(struct inode *inode, struct file *file)
 	struct ovl_dir_file *od = file->private_data;
 
 	if (od->cache) {
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		ovl_cache_put(od, file->f_path.dentry);
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 	}
 	fput(od->realfile);
 	if (od->upperfile)
@@ -557,7 +558,7 @@ void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list)
 {
 	struct ovl_cache_entry *p;
 
-	mutex_lock_nested(&upper->d_inode->i_mutex, I_MUTEX_CHILD);
+	inode_lock_nested(upper->d_inode, I_MUTEX_CHILD);
 	list_for_each_entry(p, list, l_node) {
 		struct dentry *dentry;
 
@@ -571,8 +572,45 @@ void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list)
 			       (int) PTR_ERR(dentry));
 			continue;
 		}
-		ovl_cleanup(upper->d_inode, dentry);
+		if (dentry->d_inode)
+			ovl_cleanup(upper->d_inode, dentry);
 		dput(dentry);
 	}
-	mutex_unlock(&upper->d_inode->i_mutex);
+	inode_unlock(upper->d_inode);
+}
+
+static int ovl_check_d_type(struct dir_context *ctx, const char *name,
+			  int namelen, loff_t offset, u64 ino,
+			  unsigned int d_type)
+{
+	struct ovl_readdir_data *rdd =
+		container_of(ctx, struct ovl_readdir_data, ctx);
+
+	/* Even if d_type is not supported, DT_DIR is returned for . and .. */
+	if (!strncmp(name, ".", namelen) || !strncmp(name, "..", namelen))
+		return 0;
+
+	if (d_type != DT_UNKNOWN)
+		rdd->d_type_supported = true;
+
+	return 0;
+}
+
+/*
+ * Returns 1 if d_type is supported, 0 not supported/unknown. Negative values
+ * if error is encountered.
+ */
+int ovl_check_d_type_supported(struct path *realpath)
+{
+	int err;
+	struct ovl_readdir_data rdd = {
+		.ctx.actor = ovl_check_d_type,
+		.d_type_supported = false,
+	};
+
+	err = ovl_dir_read(realpath, &rdd);
+	if (err)
+		return err;
+
+	return rdd.d_type_supported;
 }
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index e38ee0fed24a..5d972e6cd3fe 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -9,12 +9,14 @@
 
 #include <linux/fs.h>
 #include <linux/namei.h>
+#include <linux/pagemap.h>
 #include <linux/xattr.h>
 #include <linux/security.h>
 #include <linux/mount.h>
 #include <linux/slab.h>
 #include <linux/parser.h>
 #include <linux/module.h>
+#include <linux/pagemap.h>
 #include <linux/sched.h>
 #include <linux/statfs.h>
 #include <linux/seq_file.h>
@@ -24,12 +26,11 @@ MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
 MODULE_DESCRIPTION("Overlay filesystem");
 MODULE_LICENSE("GPL");
 
-#define OVERLAYFS_SUPER_MAGIC 0x794c7630
-
 struct ovl_config {
 	char *lowerdir;
 	char *upperdir;
 	char *workdir;
+	bool default_permissions;
 };
 
 /* private information held for overlayfs's superblock */
@@ -75,12 +76,14 @@ enum ovl_path_type ovl_path_type(struct dentry *dentry)
 	if (oe->__upperdentry) {
 		type = __OVL_PATH_UPPER;
 
-		if (oe->numlower) {
-			if (S_ISDIR(dentry->d_inode->i_mode))
-				type |= __OVL_PATH_MERGE;
-		} else if (!oe->opaque) {
+		/*
+		 * Non-dir dentry can hold lower dentry from previous
+		 * location. Its purity depends only on opaque flag.
+		 */
+		if (oe->numlower && S_ISDIR(dentry->d_inode->i_mode))
+			type |= __OVL_PATH_MERGE;
+		else if (!oe->opaque)
 			type |= __OVL_PATH_PURE;
-		}
 	} else {
 		if (oe->numlower > 1)
 			type |= __OVL_PATH_MERGE;
@@ -154,6 +157,18 @@ struct dentry *ovl_entry_real(struct ovl_entry *oe, bool *is_upper)
 	return realdentry;
 }
 
+struct vfsmount *ovl_entry_mnt_real(struct ovl_entry *oe, struct inode *inode,
+				    bool is_upper)
+{
+	if (is_upper) {
+		struct ovl_fs *ofs = inode->i_sb->s_fs_info;
+
+		return ofs->upper_mnt;
+	} else {
+		return oe->numlower ? oe->lowerstack[0].mnt : NULL;
+	}
+}
+
 struct ovl_dir_cache *ovl_dir_cache(struct dentry *dentry)
 {
 	struct ovl_entry *oe = dentry->d_fsdata;
@@ -161,6 +176,13 @@ struct ovl_dir_cache *ovl_dir_cache(struct dentry *dentry)
 	return oe->cache;
 }
 
+bool ovl_is_default_permissions(struct inode *inode)
+{
+	struct ovl_fs *ofs = inode->i_sb->s_fs_info;
+
+	return ofs->config.default_permissions;
+}
+
 void ovl_set_dir_cache(struct dentry *dentry, struct ovl_dir_cache *cache)
 {
 	struct ovl_entry *oe = dentry->d_fsdata;
@@ -209,7 +231,7 @@ void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry)
 {
 	struct ovl_entry *oe = dentry->d_fsdata;
 
-	WARN_ON(!mutex_is_locked(&upperdentry->d_parent->d_inode->i_mutex));
+	WARN_ON(!inode_is_locked(upperdentry->d_parent->d_inode));
 	WARN_ON(oe->__upperdentry);
 	BUG_ON(!upperdentry->d_inode);
 	/*
@@ -224,7 +246,7 @@ void ovl_dentry_version_inc(struct dentry *dentry)
 {
 	struct ovl_entry *oe = dentry->d_fsdata;
 
-	WARN_ON(!mutex_is_locked(&dentry->d_inode->i_mutex));
+	WARN_ON(!inode_is_locked(dentry->d_inode));
 	oe->version++;
 }
 
@@ -232,7 +254,7 @@ u64 ovl_dentry_version_get(struct dentry *dentry)
 {
 	struct ovl_entry *oe = dentry->d_fsdata;
 
-	WARN_ON(!mutex_is_locked(&dentry->d_inode->i_mutex));
+	WARN_ON(!inode_is_locked(dentry->d_inode));
 	return oe->version;
 }
 
@@ -273,6 +295,37 @@ static void ovl_dentry_release(struct dentry *dentry)
 	}
 }
 
+static struct dentry *ovl_d_real(struct dentry *dentry, struct inode *inode)
+{
+	struct dentry *real;
+
+	if (d_is_dir(dentry)) {
+		if (!inode || inode == d_inode(dentry))
+			return dentry;
+		goto bug;
+	}
+
+	real = ovl_dentry_upper(dentry);
+	if (real && (!inode || inode == d_inode(real)))
+		return real;
+
+	real = ovl_dentry_lower(dentry);
+	if (!real)
+		goto bug;
+
+	if (!inode || inode == d_inode(real))
+		return real;
+
+	/* Handle recursion */
+	if (real->d_flags & DCACHE_OP_REAL)
+		return real->d_op->d_real(real, inode);
+
+bug:
+	WARN(1, "ovl_d_real(%pd4, %s:%lu\n): real dentry not found\n", dentry,
+	     inode ? inode->i_sb->s_id : "NULL", inode ? inode->i_ino : 0);
+	return dentry;
+}
+
 static int ovl_dentry_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct ovl_entry *oe = dentry->d_fsdata;
@@ -317,10 +370,13 @@ static int ovl_dentry_weak_revalidate(struct dentry *dentry, unsigned int flags)
 static const struct dentry_operations ovl_dentry_operations = {
 	.d_release = ovl_dentry_release,
 	.d_select_inode = ovl_d_select_inode,
+	.d_real = ovl_d_real,
 };
 
 static const struct dentry_operations ovl_reval_dentry_operations = {
 	.d_release = ovl_dentry_release,
+	.d_select_inode = ovl_d_select_inode,
+	.d_real = ovl_d_real,
 	.d_revalidate = ovl_dentry_revalidate,
 	.d_weak_revalidate = ovl_dentry_weak_revalidate,
 };
@@ -355,9 +411,9 @@ static inline struct dentry *ovl_lookup_real(struct dentry *dir,
 {
 	struct dentry *dentry;
 
-	mutex_lock(&dir->d_inode->i_mutex);
+	inode_lock(dir->d_inode);
 	dentry = lookup_one_len(name->name, dir, name->len);
-	mutex_unlock(&dir->d_inode->i_mutex);
+	inode_unlock(dir->d_inode);
 
 	if (IS_ERR(dentry)) {
 		if (PTR_ERR(dentry) == -ENOENT)
@@ -594,6 +650,8 @@ static int ovl_show_options(struct seq_file *m, struct dentry *dentry)
 		seq_show_option(m, "upperdir", ufs->config.upperdir);
 		seq_show_option(m, "workdir", ufs->config.workdir);
 	}
+	if (ufs->config.default_permissions)
+		seq_puts(m, ",default_permissions");
 	return 0;
 }
 
@@ -618,6 +676,7 @@ enum {
 	OPT_LOWERDIR,
 	OPT_UPPERDIR,
 	OPT_WORKDIR,
+	OPT_DEFAULT_PERMISSIONS,
 	OPT_ERR,
 };
 
@@ -625,6 +684,7 @@ static const match_table_t ovl_tokens = {
 	{OPT_LOWERDIR,			"lowerdir=%s"},
 	{OPT_UPPERDIR,			"upperdir=%s"},
 	{OPT_WORKDIR,			"workdir=%s"},
+	{OPT_DEFAULT_PERMISSIONS,	"default_permissions"},
 	{OPT_ERR,			NULL}
 };
 
@@ -685,6 +745,10 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config)
 				return -ENOMEM;
 			break;
 
+		case OPT_DEFAULT_PERMISSIONS:
+			config->default_permissions = true;
+			break;
+
 		default:
 			pr_err("overlayfs: unrecognized mount option \"%s\" or missing value\n", p);
 			return -EINVAL;
@@ -716,7 +780,7 @@ static struct dentry *ovl_workdir_create(struct vfsmount *mnt,
 	if (err)
 		return ERR_PTR(err);
 
-	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
+	inode_lock_nested(dir, I_MUTEX_PARENT);
 retry:
 	work = lookup_one_len(OVL_WORKDIR_NAME, dentry,
 			      strlen(OVL_WORKDIR_NAME));
@@ -742,7 +806,7 @@ retry:
 			goto out_dput;
 	}
 out_unlock:
-	mutex_unlock(&dir->i_mutex);
+	inode_unlock(dir);
 	mnt_drop_write(mnt);
 
 	return work;
@@ -905,11 +969,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 
 	err = -EINVAL;
 	if (!ufs->config.lowerdir) {
-		pr_err("overlayfs: missing 'lowerdir'\n");
+		if (!silent)
+			pr_err("overlayfs: missing 'lowerdir'\n");
 		goto out_free_config;
 	}
 
 	sb->s_stack_depth = 0;
+	sb->s_maxbytes = MAX_LFS_FILESIZE;
 	if (ufs->config.upperdir) {
 		if (!ufs->config.workdir) {
 			pr_err("overlayfs: missing 'workdir'\n");
@@ -996,6 +1062,21 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 			sb->s_flags |= MS_RDONLY;
 			ufs->workdir = NULL;
 		}
+
+		/*
+		 * Upper should support d_type, else whiteouts are visible.
+		 * Given workdir and upper are on same fs, we can do
+		 * iterate_dir() on workdir.
+		 */
+		err = ovl_check_d_type_supported(&workpath);
+		if (err < 0)
+			goto out_put_workdir;
+
+		if (!err) {
+			pr_err("overlayfs: upper fs needs to support d_type.\n");
+			err = -EINVAL;
+			goto out_put_workdir;
+		}
 	}
 
 	err = -ENOMEM;
@@ -1053,6 +1134,9 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 
 	root_dentry->d_fsdata = oe;
 
+	ovl_copyattr(ovl_dentry_real(root_dentry)->d_inode,
+		     root_dentry->d_inode);
+
 	sb->s_magic = OVERLAYFS_SUPER_MAGIC;
 	sb->s_op = &ovl_super_operations;
 	sb->s_root = root_dentry;
diff --git a/fs/pipe.c b/fs/pipe.c
index 8865f7963700..0d3f5165cb0b 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -38,6 +38,12 @@ unsigned int pipe_max_size = 1048576;
  */
 unsigned int pipe_min_size = PAGE_SIZE;
 
+/* Maximum allocatable pages per user. Hard limit is unset by default, soft
+ * matches default values.
+ */
+unsigned long pipe_user_pages_hard;
+unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR;
+
 /*
  * We use a start+len construction, which provides full use of the 
  * allocated memory.
@@ -128,7 +134,7 @@ static void anon_pipe_buf_release(struct pipe_inode_info *pipe,
 	if (page_count(page) == 1 && !pipe->tmp_page)
 		pipe->tmp_page = page;
 	else
-		page_cache_release(page);
+		put_page(page);
 }
 
 /**
@@ -174,7 +180,7 @@ EXPORT_SYMBOL(generic_pipe_buf_steal);
  */
 void generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf)
 {
-	page_cache_get(buf->page);
+	get_page(buf->page);
 }
 EXPORT_SYMBOL(generic_pipe_buf_get);
 
@@ -205,7 +211,7 @@ EXPORT_SYMBOL(generic_pipe_buf_confirm);
 void generic_pipe_buf_release(struct pipe_inode_info *pipe,
 			      struct pipe_buffer *buf)
 {
-	page_cache_release(buf->page);
+	put_page(buf->page);
 }
 EXPORT_SYMBOL(generic_pipe_buf_release);
 
@@ -366,18 +372,17 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
 		int offset = buf->offset + buf->len;
 
 		if (ops->can_merge && offset + chars <= PAGE_SIZE) {
-			int error = ops->confirm(pipe, buf);
-			if (error)
+			ret = ops->confirm(pipe, buf);
+			if (ret)
 				goto out;
 
 			ret = copy_page_from_iter(buf->page, offset, chars, from);
 			if (unlikely(ret < chars)) {
-				error = -EFAULT;
+				ret = -EFAULT;
 				goto out;
 			}
 			do_wakeup = 1;
-			buf->len += chars;
-			ret = chars;
+			buf->len += ret;
 			if (!iov_iter_count(from))
 				goto out;
 		}
@@ -584,20 +589,49 @@ pipe_fasync(int fd, struct file *filp, int on)
 	return retval;
 }
 
+static void account_pipe_buffers(struct pipe_inode_info *pipe,
+                                 unsigned long old, unsigned long new)
+{
+	atomic_long_add(new - old, &pipe->user->pipe_bufs);
+}
+
+static bool too_many_pipe_buffers_soft(struct user_struct *user)
+{
+	return pipe_user_pages_soft &&
+	       atomic_long_read(&user->pipe_bufs) >= pipe_user_pages_soft;
+}
+
+static bool too_many_pipe_buffers_hard(struct user_struct *user)
+{
+	return pipe_user_pages_hard &&
+	       atomic_long_read(&user->pipe_bufs) >= pipe_user_pages_hard;
+}
+
 struct pipe_inode_info *alloc_pipe_info(void)
 {
 	struct pipe_inode_info *pipe;
 
 	pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL);
 	if (pipe) {
-		pipe->bufs = kzalloc(sizeof(struct pipe_buffer) * PIPE_DEF_BUFFERS, GFP_KERNEL);
+		unsigned long pipe_bufs = PIPE_DEF_BUFFERS;
+		struct user_struct *user = get_current_user();
+
+		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);
+		}
+
 		if (pipe->bufs) {
 			init_waitqueue_head(&pipe->wait);
 			pipe->r_counter = pipe->w_counter = 1;
-			pipe->buffers = PIPE_DEF_BUFFERS;
+			pipe->buffers = pipe_bufs;
+			pipe->user = user;
+			account_pipe_buffers(pipe, 0, pipe_bufs);
 			mutex_init(&pipe->mutex);
 			return pipe;
 		}
+		free_uid(user);
 		kfree(pipe);
 	}
 
@@ -608,6 +642,8 @@ void free_pipe_info(struct pipe_inode_info *pipe)
 {
 	int i;
 
+	account_pipe_buffers(pipe, pipe->buffers, 0);
+	free_uid(pipe->user);
 	for (i = 0; i < pipe->buffers; i++) {
 		struct pipe_buffer *buf = pipe->bufs + i;
 		if (buf->ops)
@@ -693,17 +729,20 @@ int create_pipe_files(struct file **res, int flags)
 
 	d_instantiate(path.dentry, inode);
 
-	err = -ENFILE;
 	f = alloc_file(&path, FMODE_WRITE, &pipefifo_fops);
-	if (IS_ERR(f))
+	if (IS_ERR(f)) {
+		err = PTR_ERR(f);
 		goto err_dentry;
+	}
 
 	f->f_flags = O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT));
 	f->private_data = inode->i_pipe;
 
 	res[0] = alloc_file(&path, FMODE_READ, &pipefifo_fops);
-	if (IS_ERR(res[0]))
+	if (IS_ERR(res[0])) {
+		err = PTR_ERR(res[0]);
 		goto err_file;
+	}
 
 	path_get(&path);
 	res[0]->private_data = inode->i_pipe;
@@ -996,6 +1035,7 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long nr_pages)
 			memcpy(bufs + head, pipe->bufs, tail * sizeof(struct pipe_buffer));
 	}
 
+	account_pipe_buffers(pipe, pipe->buffers, nr_pages);
 	pipe->curbuf = 0;
 	kfree(pipe->bufs);
 	pipe->bufs = bufs;
@@ -1067,6 +1107,11 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
 		if (!capable(CAP_SYS_RESOURCE) && size > pipe_max_size) {
 			ret = -EPERM;
 			goto out;
+		} else if ((too_many_pipe_buffers_hard(pipe->user) ||
+			    too_many_pipe_buffers_soft(pipe->user)) &&
+		           !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) {
+			ret = -EPERM;
+			goto out;
 		}
 		ret = pipe_set_size(pipe, nr_pages);
 		break;
diff --git a/fs/pnode.c b/fs/pnode.c
index 6367e1e435c6..c524fdddc7fb 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -202,6 +202,11 @@ static struct mount *last_dest, *last_source, *dest_master;
 static struct mountpoint *mp;
 static struct hlist_head *list;
 
+static inline bool peers(struct mount *m1, struct mount *m2)
+{
+	return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id;
+}
+
 static int propagate_one(struct mount *m)
 {
 	struct mount *child;
@@ -212,7 +217,7 @@ static int propagate_one(struct mount *m)
 	/* skip if mountpoint isn't covered by it */
 	if (!is_subdir(mp->m_dentry, m->mnt.mnt_root))
 		return 0;
-	if (m->mnt_group_id == last_dest->mnt_group_id) {
+	if (peers(m, last_dest)) {
 		type = CL_MAKE_SHARED;
 	} else {
 		struct mount *n, *p;
@@ -223,7 +228,7 @@ static int propagate_one(struct mount *m)
 					last_source = last_source->mnt_master;
 					last_dest = last_source->mnt_parent;
 				}
-				if (n->mnt_group_id != last_dest->mnt_group_id) {
+				if (!peers(n, last_dest)) {
 					last_source = last_source->mnt_master;
 					last_dest = last_source->mnt_parent;
 				}
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 4fb17ded7d47..711dd5170376 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -762,8 +762,9 @@ posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl,
 EXPORT_SYMBOL (posix_acl_to_xattr);
 
 static int
-posix_acl_xattr_get(struct dentry *dentry, const char *name,
-		void *value, size_t size, int type)
+posix_acl_xattr_get(const struct xattr_handler *handler,
+		    struct dentry *dentry, const char *name,
+		    void *value, size_t size)
 {
 	struct posix_acl *acl;
 	int error;
@@ -773,7 +774,7 @@ posix_acl_xattr_get(struct dentry *dentry, const char *name,
 	if (d_is_symlink(dentry))
 		return -EOPNOTSUPP;
 
-	acl = get_acl(d_backing_inode(dentry), type);
+	acl = get_acl(d_backing_inode(dentry), handler->flags);
 	if (IS_ERR(acl))
 		return PTR_ERR(acl);
 	if (acl == NULL)
@@ -786,8 +787,9 @@ posix_acl_xattr_get(struct dentry *dentry, const char *name,
 }
 
 static int
-posix_acl_xattr_set(struct dentry *dentry, const char *name,
-		const void *value, size_t size, int flags, int type)
+posix_acl_xattr_set(const struct xattr_handler *handler,
+		    struct dentry *dentry, const char *name,
+		    const void *value, size_t size, int flags)
 {
 	struct inode *inode = d_backing_inode(dentry);
 	struct posix_acl *acl = NULL;
@@ -798,7 +800,7 @@ posix_acl_xattr_set(struct dentry *dentry, const char *name,
 	if (!inode->i_op->set_acl)
 		return -EOPNOTSUPP;
 
-	if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
+	if (handler->flags == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
 		return value ? -EACCES : 0;
 	if (!inode_owner_or_capable(inode))
 		return -EPERM;
@@ -815,37 +817,20 @@ posix_acl_xattr_set(struct dentry *dentry, const char *name,
 		}
 	}
 
-	ret = inode->i_op->set_acl(inode, acl, type);
+	ret = inode->i_op->set_acl(inode, acl, handler->flags);
 out:
 	posix_acl_release(acl);
 	return ret;
 }
 
-static size_t
-posix_acl_xattr_list(struct dentry *dentry, char *list, size_t list_size,
-		const char *name, size_t name_len, int type)
+static bool
+posix_acl_xattr_list(struct dentry *dentry)
 {
-	const char *xname;
-	size_t size;
-
-	if (!IS_POSIXACL(d_backing_inode(dentry)))
-		return -EOPNOTSUPP;
-	if (d_is_symlink(dentry))
-		return -EOPNOTSUPP;
-
-	if (type == ACL_TYPE_ACCESS)
-		xname = POSIX_ACL_XATTR_ACCESS;
-	else
-		xname = POSIX_ACL_XATTR_DEFAULT;
-
-	size = strlen(xname) + 1;
-	if (list && size <= list_size)
-		memcpy(list, xname, size);
-	return size;
+	return IS_POSIXACL(d_backing_inode(dentry));
 }
 
 const struct xattr_handler posix_acl_access_xattr_handler = {
-	.prefix = POSIX_ACL_XATTR_ACCESS,
+	.name = XATTR_NAME_POSIX_ACL_ACCESS,
 	.flags = ACL_TYPE_ACCESS,
 	.list = posix_acl_xattr_list,
 	.get = posix_acl_xattr_get,
@@ -854,7 +839,7 @@ const struct xattr_handler posix_acl_access_xattr_handler = {
 EXPORT_SYMBOL_GPL(posix_acl_access_xattr_handler);
 
 const struct xattr_handler posix_acl_default_xattr_handler = {
-	.prefix = POSIX_ACL_XATTR_DEFAULT,
+	.name = XATTR_NAME_POSIX_ACL_DEFAULT,
 	.flags = ACL_TYPE_DEFAULT,
 	.list = posix_acl_xattr_list,
 	.get = posix_acl_xattr_get,
diff --git a/fs/proc/array.c b/fs/proc/array.c
index eed2050db9be..b6c00ce0e29e 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -91,18 +91,18 @@
 static inline void task_name(struct seq_file *m, struct task_struct *p)
 {
 	char *buf;
+	size_t size;
 	char tcomm[sizeof(p->comm)];
+	int ret;
 
 	get_task_comm(tcomm, p);
 
 	seq_puts(m, "Name:\t");
-	buf = m->buf + m->count;
 
-	/* Ignore error for now */
-	buf += string_escape_str(tcomm, buf, m->size - m->count,
-				 ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\");
+	size = seq_get_buf(m, &buf);
+	ret = string_escape_str(tcomm, buf, size, ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\");
+	seq_commit(m, ret < size ? ret : -1);
 
-	m->count = buf - m->buf;
 	seq_putc(m, '\n');
 }
 
@@ -395,7 +395,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 
 	state = *get_task_state(task);
 	vsize = eip = esp = 0;
-	permitted = ptrace_may_access(task, PTRACE_MODE_READ | PTRACE_MODE_NOAUDIT);
+	permitted = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS | PTRACE_MODE_NOAUDIT);
 	mm = get_task_mm(task);
 	if (mm) {
 		vsize = task_vsize(mm);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index bd3e9e68125b..b1755b23893e 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -403,7 +403,7 @@ static const struct file_operations proc_pid_cmdline_ops = {
 static int proc_pid_auxv(struct seq_file *m, struct pid_namespace *ns,
 			 struct pid *pid, struct task_struct *task)
 {
-	struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ);
+	struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
 	if (mm && !IS_ERR(mm)) {
 		unsigned int nwords = 0;
 		do {
@@ -430,10 +430,11 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns,
 
 	wchan = get_wchan(task);
 
-	if (wchan && ptrace_may_access(task, PTRACE_MODE_READ) && !lookup_symbol_name(wchan, symname))
+	if (wchan && ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)
+			&& !lookup_symbol_name(wchan, symname))
 		seq_printf(m, "%s", symname);
 	else
-		seq_putc(m, '0');
+		seq_puts(m, "0\n");
 
 	return 0;
 }
@@ -444,7 +445,7 @@ static int lock_trace(struct task_struct *task)
 	int err = mutex_lock_killable(&task->signal->cred_guard_mutex);
 	if (err)
 		return err;
-	if (!ptrace_may_access(task, PTRACE_MODE_ATTACH)) {
+	if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) {
 		mutex_unlock(&task->signal->cred_guard_mutex);
 		return -EPERM;
 	}
@@ -697,7 +698,7 @@ static int proc_fd_access_allowed(struct inode *inode)
 	 */
 	task = get_proc_task(inode);
 	if (task) {
-		allowed = ptrace_may_access(task, PTRACE_MODE_READ);
+		allowed = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
 		put_task_struct(task);
 	}
 	return allowed;
@@ -732,7 +733,7 @@ static bool has_pid_permissions(struct pid_namespace *pid,
 		return true;
 	if (in_group_p(pid->pid_gid))
 		return true;
-	return ptrace_may_access(task, PTRACE_MODE_READ);
+	return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
 }
 
 
@@ -809,7 +810,7 @@ struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode)
 	struct mm_struct *mm = ERR_PTR(-ESRCH);
 
 	if (task) {
-		mm = mm_access(task, mode);
+		mm = mm_access(task, mode | PTRACE_MODE_FSCREDS);
 		put_task_struct(task);
 
 		if (!IS_ERR_OR_NULL(mm)) {
@@ -952,6 +953,7 @@ static ssize_t environ_read(struct file *file, char __user *buf,
 	unsigned long src = *ppos;
 	int ret = 0;
 	struct mm_struct *mm = file->private_data;
+	unsigned long env_start, env_end;
 
 	if (!mm)
 		return 0;
@@ -963,19 +965,25 @@ static ssize_t environ_read(struct file *file, char __user *buf,
 	ret = 0;
 	if (!atomic_inc_not_zero(&mm->mm_users))
 		goto free;
+
+	down_read(&mm->mmap_sem);
+	env_start = mm->env_start;
+	env_end = mm->env_end;
+	up_read(&mm->mmap_sem);
+
 	while (count > 0) {
 		size_t this_len, max_len;
 		int retval;
 
-		if (src >= (mm->env_end - mm->env_start))
+		if (src >= (env_end - env_start))
 			break;
 
-		this_len = mm->env_end - (mm->env_start + src);
+		this_len = env_end - (env_start + src);
 
 		max_len = min_t(size_t, PAGE_SIZE, count);
 		this_len = min(max_len, this_len);
 
-		retval = access_remote_vm(mm, (mm->env_start + src),
+		retval = access_remote_vm(mm, (env_start + src),
 			page, this_len, 0);
 
 		if (retval <= 0) {
@@ -1564,12 +1572,16 @@ static int proc_exe_link(struct dentry *dentry, struct path *exe_path)
 		return -ENOENT;
 }
 
-static const char *proc_pid_follow_link(struct dentry *dentry, void **cookie)
+static const char *proc_pid_get_link(struct dentry *dentry,
+				     struct inode *inode,
+				     struct delayed_call *done)
 {
-	struct inode *inode = d_inode(dentry);
 	struct path path;
 	int error = -EACCES;
 
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
 	/* Are we allowed to snoop on the tasks file descriptors? */
 	if (!proc_fd_access_allowed(inode))
 		goto out;
@@ -1630,7 +1642,7 @@ out:
 
 const struct inode_operations proc_pid_link_inode_operations = {
 	.readlink	= proc_pid_readlink,
-	.follow_link	= proc_pid_follow_link,
+	.get_link	= proc_pid_get_link,
 	.setattr	= proc_setattr,
 };
 
@@ -1856,7 +1868,7 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags)
 	if (!task)
 		goto out_notask;
 
-	mm = mm_access(task, PTRACE_MODE_READ);
+	mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
 	if (IS_ERR_OR_NULL(mm))
 		goto out;
 
@@ -1895,7 +1907,7 @@ static const struct dentry_operations tid_map_files_dentry_operations = {
 	.d_delete	= pid_delete_dentry,
 };
 
-static int proc_map_files_get_link(struct dentry *dentry, struct path *path)
+static int map_files_get_link(struct dentry *dentry, struct path *path)
 {
 	unsigned long vm_start, vm_end;
 	struct vm_area_struct *vma;
@@ -1945,20 +1957,22 @@ struct map_files_info {
  * path to the file in question.
  */
 static const char *
-proc_map_files_follow_link(struct dentry *dentry, void **cookie)
+proc_map_files_get_link(struct dentry *dentry,
+			struct inode *inode,
+		        struct delayed_call *done)
 {
 	if (!capable(CAP_SYS_ADMIN))
 		return ERR_PTR(-EPERM);
 
-	return proc_pid_follow_link(dentry, NULL);
+	return proc_pid_get_link(dentry, inode, done);
 }
 
 /*
- * Identical to proc_pid_link_inode_operations except for follow_link()
+ * Identical to proc_pid_link_inode_operations except for get_link()
  */
 static const struct inode_operations proc_map_files_link_inode_operations = {
 	.readlink	= proc_pid_readlink,
-	.follow_link	= proc_map_files_follow_link,
+	.get_link	= proc_map_files_get_link,
 	.setattr	= proc_setattr,
 };
 
@@ -1975,7 +1989,7 @@ proc_map_files_instantiate(struct inode *dir, struct dentry *dentry,
 		return -ENOENT;
 
 	ei = PROC_I(inode);
-	ei->op.proc_get_link = proc_map_files_get_link;
+	ei->op.proc_get_link = map_files_get_link;
 
 	inode->i_op = &proc_map_files_link_inode_operations;
 	inode->i_size = 64;
@@ -2007,7 +2021,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
 		goto out;
 
 	result = -EACCES;
-	if (!ptrace_may_access(task, PTRACE_MODE_READ))
+	if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
 		goto out_put_task;
 
 	result = -ENOENT;
@@ -2060,7 +2074,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
 		goto out;
 
 	ret = -EACCES;
-	if (!ptrace_may_access(task, PTRACE_MODE_READ))
+	if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
 		goto out_put_task;
 
 	ret = 0;
@@ -2144,6 +2158,7 @@ static const struct file_operations proc_map_files_operations = {
 	.llseek		= default_llseek,
 };
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
 struct timers_private {
 	struct pid *pid;
 	struct task_struct *task;
@@ -2242,6 +2257,73 @@ static const struct file_operations proc_timers_operations = {
 	.llseek		= seq_lseek,
 	.release	= seq_release_private,
 };
+#endif
+
+static ssize_t timerslack_ns_write(struct file *file, const char __user *buf,
+					size_t count, loff_t *offset)
+{
+	struct inode *inode = file_inode(file);
+	struct task_struct *p;
+	u64 slack_ns;
+	int err;
+
+	err = kstrtoull_from_user(buf, count, 10, &slack_ns);
+	if (err < 0)
+		return err;
+
+	p = get_proc_task(inode);
+	if (!p)
+		return -ESRCH;
+
+	if (ptrace_may_access(p, PTRACE_MODE_ATTACH_FSCREDS)) {
+		task_lock(p);
+		if (slack_ns == 0)
+			p->timer_slack_ns = p->default_timer_slack_ns;
+		else
+			p->timer_slack_ns = slack_ns;
+		task_unlock(p);
+	} else
+		count = -EPERM;
+
+	put_task_struct(p);
+
+	return count;
+}
+
+static int timerslack_ns_show(struct seq_file *m, void *v)
+{
+	struct inode *inode = m->private;
+	struct task_struct *p;
+	int err =  0;
+
+	p = get_proc_task(inode);
+	if (!p)
+		return -ESRCH;
+
+	if (ptrace_may_access(p, PTRACE_MODE_ATTACH_FSCREDS)) {
+		task_lock(p);
+		seq_printf(m, "%llu\n", p->timer_slack_ns);
+		task_unlock(p);
+	} else
+		err = -EPERM;
+
+	put_task_struct(p);
+
+	return err;
+}
+
+static int timerslack_ns_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, timerslack_ns_show, inode);
+}
+
+static const struct file_operations proc_pid_set_timerslack_ns_operations = {
+	.open		= timerslack_ns_open,
+	.read		= seq_read,
+	.write		= timerslack_ns_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
 
 static int proc_pident_instantiate(struct inode *dir,
 	struct dentry *dentry, struct task_struct *task, const void *ptr)
@@ -2359,7 +2441,7 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
 				   size_t count, loff_t *ppos)
 {
 	struct inode * inode = file_inode(file);
-	char *page;
+	void *page;
 	ssize_t length;
 	struct task_struct *task = get_proc_task(inode);
 
@@ -2374,14 +2456,11 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
 	if (*ppos != 0)
 		goto out;
 
-	length = -ENOMEM;
-	page = (char*)__get_free_page(GFP_TEMPORARY);
-	if (!page)
+	page = memdup_user(buf, count);
+	if (IS_ERR(page)) {
+		length = PTR_ERR(page);
 		goto out;
-
-	length = -EFAULT;
-	if (copy_from_user(page, buf, count))
-		goto out_free;
+	}
 
 	/* Guard against adverse ptrace interaction */
 	length = mutex_lock_interruptible(&task->signal->cred_guard_mutex);
@@ -2390,10 +2469,10 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
 
 	length = security_setprocattr(task,
 				      (char*)file->f_path.dentry->d_name.name,
-				      (void*)page, count);
+				      page, count);
 	mutex_unlock(&task->signal->cred_guard_mutex);
 out_free:
-	free_page((unsigned long) page);
+	kfree(page);
 out:
 	put_task_struct(task);
 out_no_task:
@@ -2494,6 +2573,7 @@ static ssize_t proc_coredump_filter_write(struct file *file,
 	mm = get_task_mm(task);
 	if (!mm)
 		goto out_no_mm;
+	ret = 0;
 
 	for (i = 0, mask = 1; i < MMF_DUMP_FILTER_BITS; i++, mask <<= 1) {
 		if (val & mask)
@@ -2529,7 +2609,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh
 	if (result)
 		return result;
 
-	if (!ptrace_may_access(task, PTRACE_MODE_READ)) {
+	if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
 		result = -EACCES;
 		goto out_unlock;
 	}
@@ -2819,6 +2899,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_CHECKPOINT_RESTORE
 	REG("timers",	  S_IRUGO, proc_timers_operations),
 #endif
+	REG("timerslack_ns", S_IRUGO|S_IWUGO, proc_pid_set_timerslack_ns_operations),
 };
 
 static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx)
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 6e5fcd00733e..56afa5ef08f2 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -258,6 +258,7 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx,
 				     name, len, instantiate, p,
 				     (void *)(unsigned long)fd))
 			goto out_fd_loop;
+		cond_resched();
 		rcu_read_lock();
 	}
 	rcu_read_unlock();
@@ -291,11 +292,19 @@ static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry,
  */
 int proc_fd_permission(struct inode *inode, int mask)
 {
-	int rv = generic_permission(inode, mask);
+	struct task_struct *p;
+	int rv;
+
+	rv = generic_permission(inode, mask);
 	if (rv == 0)
-		return 0;
-	if (task_tgid(current) == proc_pid(inode))
+		return rv;
+
+	rcu_read_lock();
+	p = pid_task(proc_pid(inode), PIDTYPE_PID);
+	if (p && same_thread_group(p, current))
 		rv = 0;
+	rcu_read_unlock();
+
 	return rv;
 }
 
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index bd95b9fdebb0..42305ddcbaa0 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -95,7 +95,8 @@ void __init proc_init_inodecache(void)
 	proc_inode_cachep = kmem_cache_create("proc_inode_cache",
 					     sizeof(struct proc_inode),
 					     0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD|SLAB_PANIC),
+						SLAB_MEM_SPREAD|SLAB_ACCOUNT|
+						SLAB_PANIC),
 					     init_once);
 }
 
@@ -393,24 +394,25 @@ static const struct file_operations proc_reg_file_ops_no_compat = {
 };
 #endif
 
-static const char *proc_follow_link(struct dentry *dentry, void **cookie)
+static void proc_put_link(void *p)
 {
-	struct proc_dir_entry *pde = PDE(d_inode(dentry));
-	if (unlikely(!use_pde(pde)))
-		return ERR_PTR(-EINVAL);
-	*cookie = pde;
-	return pde->data;
+	unuse_pde(p);
 }
 
-static void proc_put_link(struct inode *unused, void *p)
+static const char *proc_get_link(struct dentry *dentry,
+				 struct inode *inode,
+				 struct delayed_call *done)
 {
-	unuse_pde(p);
+	struct proc_dir_entry *pde = PDE(inode);
+	if (unlikely(!use_pde(pde)))
+		return ERR_PTR(-EINVAL);
+	set_delayed_call(done, proc_put_link, pde);
+	return pde->data;
 }
 
 const struct inode_operations proc_link_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= proc_follow_link,
-	.put_link	= proc_put_link,
+	.get_link	= proc_get_link,
 };
 
 struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 92e6726f6e37..a939f5ed7f89 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -552,9 +552,9 @@ static int open_kcore(struct inode *inode, struct file *filp)
 	if (kcore_need_update)
 		kcore_update_ram();
 	if (i_size_read(inode) != proc_root_kcore->size) {
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		i_size_write(inode, proc_root_kcore->size);
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 	}
 	return 0;
 }
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 9155a5a0d3b9..83720460c5bc 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -29,10 +29,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	unsigned long committed;
 	long cached;
 	long available;
-	unsigned long pagecache;
-	unsigned long wmark_low = 0;
 	unsigned long pages[NR_LRU_LISTS];
-	struct zone *zone;
 	int lru;
 
 /*
@@ -51,36 +48,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
 		pages[lru] = global_page_state(NR_LRU_BASE + lru);
 
-	for_each_zone(zone)
-		wmark_low += zone->watermark[WMARK_LOW];
-
-	/*
-	 * Estimate the amount of memory available for userspace allocations,
-	 * without causing swapping.
-	 *
-	 * Free memory cannot be taken below the low watermark, before the
-	 * system starts swapping.
-	 */
-	available = i.freeram - wmark_low;
-
-	/*
-	 * Not all the page cache can be freed, otherwise the system will
-	 * start swapping. Assume at least half of the page cache, or the
-	 * low watermark worth of cache, needs to stay.
-	 */
-	pagecache = pages[LRU_ACTIVE_FILE] + pages[LRU_INACTIVE_FILE];
-	pagecache -= min(pagecache / 2, wmark_low);
-	available += pagecache;
-
-	/*
-	 * Part of the reclaimable slab consists of items that are in use,
-	 * and cannot be freed. Cap this estimate at the low watermark.
-	 */
-	available += global_page_state(NR_SLAB_RECLAIMABLE) -
-		     min(global_page_state(NR_SLAB_RECLAIMABLE) / 2, wmark_low);
-
-	if (available < 0)
-		available = 0;
+	available = si_mem_available();
 
 	/*
 	 * Tagged format, for easy grepping and expansion.
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index f6e8354b8cea..72cb26f85d58 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -28,21 +28,28 @@ static const struct proc_ns_operations *ns_entries[] = {
 	&userns_operations,
 #endif
 	&mntns_operations,
+#ifdef CONFIG_CGROUPS
+	&cgroupns_operations,
+#endif
 };
 
-static const char *proc_ns_follow_link(struct dentry *dentry, void **cookie)
+static const char *proc_ns_get_link(struct dentry *dentry,
+				    struct inode *inode,
+				    struct delayed_call *done)
 {
-	struct inode *inode = d_inode(dentry);
 	const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops;
 	struct task_struct *task;
 	struct path ns_path;
 	void *error = ERR_PTR(-EACCES);
 
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
 	task = get_proc_task(inode);
 	if (!task)
 		return error;
 
-	if (ptrace_may_access(task, PTRACE_MODE_READ)) {
+	if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
 		error = ns_get_path(&ns_path, task, ns_ops);
 		if (!error)
 			nd_jump_link(&ns_path);
@@ -63,7 +70,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl
 	if (!task)
 		return res;
 
-	if (ptrace_may_access(task, PTRACE_MODE_READ)) {
+	if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
 		res = ns_get_name(name, sizeof(name), task, ns_ops);
 		if (res >= 0)
 			res = readlink_copy(buffer, buflen, name);
@@ -74,7 +81,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl
 
 static const struct inode_operations proc_ns_link_inode_operations = {
 	.readlink	= proc_ns_readlink,
-	.follow_link	= proc_ns_follow_link,
+	.get_link	= proc_ns_get_link,
 	.setattr	= proc_setattr,
 };
 
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 93484034a03d..712f1b9992cc 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -148,6 +148,8 @@ u64 stable_page_flags(struct page *page)
 	 */
 	if (PageBuddy(page))
 		u |= 1 << KPF_BUDDY;
+	else if (page_count(page) == 0 && is_free_buddy_page(page))
+		u |= 1 << KPF_BUDDY;
 
 	if (PageBalloon(page))
 		u |= 1 << KPF_BALLOON;
@@ -158,6 +160,8 @@ u64 stable_page_flags(struct page *page)
 	u |= kpf_copy_bit(k, KPF_LOCKED,	PG_locked);
 
 	u |= kpf_copy_bit(k, KPF_SLAB,		PG_slab);
+	if (PageTail(page) && PageSlab(compound_head(page)))
+		u |= 1 << KPF_SLAB;
 
 	u |= kpf_copy_bit(k, KPF_ERROR,		PG_error);
 	u |= kpf_copy_bit(k, KPF_DIRTY,		PG_dirty);
diff --git a/fs/proc/self.c b/fs/proc/self.c
index 113b8d061fc0..b6a8d3529fea 100644
--- a/fs/proc/self.c
+++ b/fs/proc/self.c
@@ -18,26 +18,28 @@ static int proc_self_readlink(struct dentry *dentry, char __user *buffer,
 	return readlink_copy(buffer, buflen, tmp);
 }
 
-static const char *proc_self_follow_link(struct dentry *dentry, void **cookie)
+static const char *proc_self_get_link(struct dentry *dentry,
+				      struct inode *inode,
+				      struct delayed_call *done)
 {
-	struct pid_namespace *ns = dentry->d_sb->s_fs_info;
+	struct pid_namespace *ns = inode->i_sb->s_fs_info;
 	pid_t tgid = task_tgid_nr_ns(current, ns);
 	char *name;
 
 	if (!tgid)
 		return ERR_PTR(-ENOENT);
 	/* 11 for max length of signed int in decimal + NULL term */
-	name = kmalloc(12, GFP_KERNEL);
-	if (!name)
-		return ERR_PTR(-ENOMEM);
+	name = kmalloc(12, dentry ? GFP_KERNEL : GFP_ATOMIC);
+	if (unlikely(!name))
+		return dentry ? ERR_PTR(-ENOMEM) : ERR_PTR(-ECHILD);
 	sprintf(name, "%d", tgid);
-	return *cookie = name;
+	set_delayed_call(done, kfree_link, name);
+	return name;
 }
 
 static const struct inode_operations proc_self_inode_operations = {
 	.readlink	= proc_self_readlink,
-	.follow_link	= proc_self_follow_link,
-	.put_link	= kfree_put_link,
+	.get_link	= proc_self_get_link,
 };
 
 static unsigned self_inum;
@@ -48,7 +50,7 @@ int proc_setup_self(struct super_block *s)
 	struct pid_namespace *ns = s->s_fs_info;
 	struct dentry *self;
 	
-	mutex_lock(&root_inode->i_mutex);
+	inode_lock(root_inode);
 	self = d_alloc_name(s->s_root, "self");
 	if (self) {
 		struct inode *inode = new_inode_pseudo(s);
@@ -67,7 +69,7 @@ int proc_setup_self(struct super_block *s)
 	} else {
 		self = ERR_PTR(-ENOMEM);
 	}
-	mutex_unlock(&root_inode->i_mutex);
+	inode_unlock(root_inode);
 	if (IS_ERR(self)) {
 		pr_err("proc_fill_super: can't allocate /proc/self\n");
 		return PTR_ERR(self);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 187b3b5f242e..229cb546bee0 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -14,6 +14,7 @@
 #include <linux/swapops.h>
 #include <linux/mmu_notifier.h>
 #include <linux/page_idle.h>
+#include <linux/shmem_fs.h>
 
 #include <asm/elf.h>
 #include <asm/uaccess.h>
@@ -22,9 +23,13 @@
 
 void task_mem(struct seq_file *m, struct mm_struct *mm)
 {
-	unsigned long data, text, lib, swap, ptes, pmds;
+	unsigned long text, lib, swap, ptes, pmds, anon, file, shmem;
 	unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
 
+	anon = get_mm_counter(mm, MM_ANONPAGES);
+	file = get_mm_counter(mm, MM_FILEPAGES);
+	shmem = get_mm_counter(mm, MM_SHMEMPAGES);
+
 	/*
 	 * Note: to minimize their overhead, mm maintains hiwater_vm and
 	 * hiwater_rss only when about to *lower* total_vm or rss.  Any
@@ -35,11 +40,10 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 	hiwater_vm = total_vm = mm->total_vm;
 	if (hiwater_vm < mm->hiwater_vm)
 		hiwater_vm = mm->hiwater_vm;
-	hiwater_rss = total_rss = get_mm_rss(mm);
+	hiwater_rss = total_rss = anon + file + shmem;
 	if (hiwater_rss < mm->hiwater_rss)
 		hiwater_rss = mm->hiwater_rss;
 
-	data = mm->total_vm - mm->shared_vm - mm->stack_vm;
 	text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10;
 	lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text;
 	swap = get_mm_counter(mm, MM_SWAPENTS);
@@ -52,6 +56,9 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 		"VmPin:\t%8lu kB\n"
 		"VmHWM:\t%8lu kB\n"
 		"VmRSS:\t%8lu kB\n"
+		"RssAnon:\t%8lu kB\n"
+		"RssFile:\t%8lu kB\n"
+		"RssShmem:\t%8lu kB\n"
 		"VmData:\t%8lu kB\n"
 		"VmStk:\t%8lu kB\n"
 		"VmExe:\t%8lu kB\n"
@@ -65,7 +72,10 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 		mm->pinned_vm << (PAGE_SHIFT-10),
 		hiwater_rss << (PAGE_SHIFT-10),
 		total_rss << (PAGE_SHIFT-10),
-		data << (PAGE_SHIFT-10),
+		anon << (PAGE_SHIFT-10),
+		file << (PAGE_SHIFT-10),
+		shmem << (PAGE_SHIFT-10),
+		mm->data_vm << (PAGE_SHIFT-10),
 		mm->stack_vm << (PAGE_SHIFT-10), text, lib,
 		ptes >> 10,
 		pmds >> 10,
@@ -82,10 +92,11 @@ unsigned long task_statm(struct mm_struct *mm,
 			 unsigned long *shared, unsigned long *text,
 			 unsigned long *data, unsigned long *resident)
 {
-	*shared = get_mm_counter(mm, MM_FILEPAGES);
+	*shared = get_mm_counter(mm, MM_FILEPAGES) +
+			get_mm_counter(mm, MM_SHMEMPAGES);
 	*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
 								>> PAGE_SHIFT;
-	*data = mm->total_vm - mm->shared_vm;
+	*data = mm->data_vm + mm->stack_vm;
 	*resident = *shared + get_mm_counter(mm, MM_ANONPAGES);
 	return mm->total_vm;
 }
@@ -248,23 +259,29 @@ static int do_maps_open(struct inode *inode, struct file *file,
 				sizeof(struct proc_maps_private));
 }
 
-static pid_t pid_of_stack(struct proc_maps_private *priv,
-				struct vm_area_struct *vma, bool is_pid)
+/*
+ * Indicate if the VMA is a stack for the given task; for
+ * /proc/PID/maps that is the stack of the main task.
+ */
+static int is_stack(struct proc_maps_private *priv,
+		    struct vm_area_struct *vma, int is_pid)
 {
-	struct inode *inode = priv->inode;
-	struct task_struct *task;
-	pid_t ret = 0;
+	int stack = 0;
 
-	rcu_read_lock();
-	task = pid_task(proc_pid(inode), PIDTYPE_PID);
-	if (task) {
-		task = task_of_stack(task, vma, is_pid);
+	if (is_pid) {
+		stack = vma->vm_start <= vma->vm_mm->start_stack &&
+			vma->vm_end >= vma->vm_mm->start_stack;
+	} else {
+		struct inode *inode = priv->inode;
+		struct task_struct *task;
+
+		rcu_read_lock();
+		task = pid_task(proc_pid(inode), PIDTYPE_PID);
 		if (task)
-			ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info);
+			stack = vma_is_stack_for_task(vma, task);
+		rcu_read_unlock();
 	}
-	rcu_read_unlock();
-
-	return ret;
+	return stack;
 }
 
 static void
@@ -324,8 +341,6 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 
 	name = arch_vma_name(vma);
 	if (!name) {
-		pid_t tid;
-
 		if (!mm) {
 			name = "[vdso]";
 			goto done;
@@ -337,21 +352,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 			goto done;
 		}
 
-		tid = pid_of_stack(priv, vma, is_pid);
-		if (tid != 0) {
-			/*
-			 * Thread stack in /proc/PID/task/TID/maps or
-			 * the main process stack.
-			 */
-			if (!is_pid || (vma->vm_start <= mm->start_stack &&
-			    vma->vm_end >= mm->start_stack)) {
-				name = "[stack]";
-			} else {
-				/* Thread stack in /proc/PID/maps */
-				seq_pad(m, ' ');
-				seq_printf(m, "[stack:%d]", tid);
-			}
-		}
+		if (is_stack(priv, vma, is_pid))
+			name = "[stack]";
 	}
 
 done:
@@ -451,12 +453,14 @@ struct mem_size_stats {
 	unsigned long private_hugetlb;
 	u64 pss;
 	u64 swap_pss;
+	bool check_shmem_swap;
 };
 
 static void smaps_account(struct mem_size_stats *mss, struct page *page,
-		unsigned long size, bool young, bool dirty)
+		bool compound, bool young, bool dirty)
 {
-	int mapcount;
+	int i, nr = compound ? 1 << compound_order(page) : 1;
+	unsigned long size = nr * PAGE_SIZE;
 
 	if (PageAnon(page))
 		mss->anonymous += size;
@@ -465,25 +469,52 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
 	/* Accumulate the size in pages that have been accessed. */
 	if (young || page_is_young(page) || PageReferenced(page))
 		mss->referenced += size;
-	mapcount = page_mapcount(page);
-	if (mapcount >= 2) {
-		u64 pss_delta;
 
-		if (dirty || PageDirty(page))
-			mss->shared_dirty += size;
-		else
-			mss->shared_clean += size;
-		pss_delta = (u64)size << PSS_SHIFT;
-		do_div(pss_delta, mapcount);
-		mss->pss += pss_delta;
-	} else {
+	/*
+	 * page_count(page) == 1 guarantees the page is mapped exactly once.
+	 * If any subpage of the compound page mapped with PTE it would elevate
+	 * page_count().
+	 */
+	if (page_count(page) == 1) {
 		if (dirty || PageDirty(page))
 			mss->private_dirty += size;
 		else
 			mss->private_clean += size;
 		mss->pss += (u64)size << PSS_SHIFT;
+		return;
 	}
+
+	for (i = 0; i < nr; i++, page++) {
+		int mapcount = page_mapcount(page);
+
+		if (mapcount >= 2) {
+			if (dirty || PageDirty(page))
+				mss->shared_dirty += PAGE_SIZE;
+			else
+				mss->shared_clean += PAGE_SIZE;
+			mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount;
+		} else {
+			if (dirty || PageDirty(page))
+				mss->private_dirty += PAGE_SIZE;
+			else
+				mss->private_clean += PAGE_SIZE;
+			mss->pss += PAGE_SIZE << PSS_SHIFT;
+		}
+	}
+}
+
+#ifdef CONFIG_SHMEM
+static int smaps_pte_hole(unsigned long addr, unsigned long end,
+		struct mm_walk *walk)
+{
+	struct mem_size_stats *mss = walk->private;
+
+	mss->swap += shmem_partial_swap_usage(
+			walk->vma->vm_file->f_mapping, addr, end);
+
+	return 0;
 }
+#endif
 
 static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 		struct mm_walk *walk)
@@ -512,11 +543,25 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 			}
 		} else if (is_migration_entry(swpent))
 			page = migration_entry_to_page(swpent);
+	} else if (unlikely(IS_ENABLED(CONFIG_SHMEM) && mss->check_shmem_swap
+							&& pte_none(*pte))) {
+		page = find_get_entry(vma->vm_file->f_mapping,
+						linear_page_index(vma, addr));
+		if (!page)
+			return;
+
+		if (radix_tree_exceptional_entry(page))
+			mss->swap += PAGE_SIZE;
+		else
+			put_page(page);
+
+		return;
 	}
 
 	if (!page)
 		return;
-	smaps_account(mss, page, PAGE_SIZE, pte_young(*pte), pte_dirty(*pte));
+
+	smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte));
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -532,8 +577,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
 	if (IS_ERR_OR_NULL(page))
 		return;
 	mss->anonymous_thp += HPAGE_PMD_SIZE;
-	smaps_account(mss, page, HPAGE_PMD_SIZE,
-			pmd_young(*pmd), pmd_dirty(*pmd));
+	smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd));
 }
 #else
 static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
@@ -549,7 +593,8 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	pte_t *pte;
 	spinlock_t *ptl;
 
-	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+	ptl = pmd_trans_huge_lock(pmd, vma);
+	if (ptl) {
 		smaps_pmd_entry(pmd, addr, walk);
 		spin_unlock(ptl);
 		return 0;
@@ -615,11 +660,20 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 		[ilog2(VM_MERGEABLE)]	= "mg",
 		[ilog2(VM_UFFD_MISSING)]= "um",
 		[ilog2(VM_UFFD_WP)]	= "uw",
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+		/* These come out via ProtectionKey: */
+		[ilog2(VM_PKEY_BIT0)]	= "",
+		[ilog2(VM_PKEY_BIT1)]	= "",
+		[ilog2(VM_PKEY_BIT2)]	= "",
+		[ilog2(VM_PKEY_BIT3)]	= "",
+#endif
 	};
 	size_t i;
 
 	seq_puts(m, "VmFlags: ");
 	for (i = 0; i < BITS_PER_LONG; i++) {
+		if (!mnemonics[i][0])
+			continue;
 		if (vma->vm_flags & (1UL << i)) {
 			seq_printf(m, "%c%c ",
 				   mnemonics[i][0], mnemonics[i][1]);
@@ -657,6 +711,10 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
 }
 #endif /* HUGETLB_PAGE */
 
+void __weak arch_show_smap(struct seq_file *m, struct vm_area_struct *vma)
+{
+}
+
 static int show_smap(struct seq_file *m, void *v, int is_pid)
 {
 	struct vm_area_struct *vma = v;
@@ -671,6 +729,31 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 	};
 
 	memset(&mss, 0, sizeof mss);
+
+#ifdef CONFIG_SHMEM
+	if (vma->vm_file && shmem_mapping(vma->vm_file->f_mapping)) {
+		/*
+		 * For shared or readonly shmem mappings we know that all
+		 * swapped out pages belong to the shmem object, and we can
+		 * obtain the swap value much more efficiently. For private
+		 * writable mappings, we might have COW pages that are
+		 * not affected by the parent swapped out pages of the shmem
+		 * object, so we have to distinguish them during the page walk.
+		 * Unless we know that the shmem object (or the part mapped by
+		 * our VMA) has no swapped out pages at all.
+		 */
+		unsigned long shmem_swapped = shmem_swap_usage(vma);
+
+		if (!shmem_swapped || (vma->vm_flags & VM_SHARED) ||
+					!(vma->vm_flags & VM_WRITE)) {
+			mss.swap = shmem_swapped;
+		} else {
+			mss.check_shmem_swap = true;
+			smaps_walk.pte_hole = smaps_pte_hole;
+		}
+	}
+#endif
+
 	/* mmap_sem is held in m_start */
 	walk_page_vma(vma, &smaps_walk);
 
@@ -713,6 +796,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		   (vma->vm_flags & VM_LOCKED) ?
 			(unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0);
 
+	arch_show_smap(m, vma);
 	show_smap_vma_flags(m, vma);
 	m_cache_vma(m, vma);
 	return 0;
@@ -817,9 +901,6 @@ static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
 	pmd = pmd_wrprotect(pmd);
 	pmd = pmd_clear_soft_dirty(pmd);
 
-	if (vma->vm_flags & VM_SOFTDIRTY)
-		vma->vm_flags &= ~VM_SOFTDIRTY;
-
 	set_pmd_at(vma->vm_mm, addr, pmdp, pmd);
 }
 #else
@@ -838,7 +919,8 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 	spinlock_t *ptl;
 	struct page *page;
 
-	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+	ptl = pmd_trans_huge_lock(pmd, vma);
+	if (ptl) {
 		if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
 			clear_soft_dirty_pmd(vma, addr, pmd);
 			goto out;
@@ -1112,7 +1194,8 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 	int err = 0;
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	if (pmd_trans_huge_lock(pmdp, vma, &ptl) == 1) {
+	ptl = pmd_trans_huge_lock(pmdp, vma);
+	if (ptl) {
 		u64 flags = 0, frame = 0;
 		pmd_t pmd = *pmdp;
 
@@ -1444,7 +1527,8 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 	pte_t *orig_pte;
 	pte_t *pte;
 
-	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+	ptl = pmd_trans_huge_lock(pmd, vma);
+	if (ptl) {
 		pte_t huge_pte = *(pte_t *)pmd;
 		struct page *page;
 
@@ -1473,18 +1557,19 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask,
 		unsigned long addr, unsigned long end, struct mm_walk *walk)
 {
+	pte_t huge_pte = huge_ptep_get(pte);
 	struct numa_maps *md;
 	struct page *page;
 
-	if (!pte_present(*pte))
+	if (!pte_present(huge_pte))
 		return 0;
 
-	page = pte_page(*pte);
+	page = pte_page(huge_pte);
 	if (!page)
 		return 0;
 
 	md = walk->private;
-	gather_stats(page, md, pte_dirty(*pte), 1);
+	gather_stats(page, md, pte_dirty(huge_pte), 1);
 	return 0;
 }
 
@@ -1538,19 +1623,8 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 		seq_file_path(m, file, "\n\t= ");
 	} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
 		seq_puts(m, " heap");
-	} else {
-		pid_t tid = pid_of_stack(proc_priv, vma, is_pid);
-		if (tid != 0) {
-			/*
-			 * Thread stack in /proc/PID/task/TID/maps or
-			 * the main process stack.
-			 */
-			if (!is_pid || (vma->vm_start <= mm->start_stack &&
-			    vma->vm_end >= mm->start_stack))
-				seq_puts(m, " stack");
-			else
-				seq_printf(m, " stack:%d", tid);
-		}
+	} else if (is_stack(proc_priv, vma, is_pid)) {
+		seq_puts(m, " stack");
 	}
 
 	if (is_vm_hugetlb_page(vma))
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index e0d64c92e4f6..faacb0c0d857 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -123,23 +123,26 @@ unsigned long task_statm(struct mm_struct *mm,
 	return size;
 }
 
-static pid_t pid_of_stack(struct proc_maps_private *priv,
-				struct vm_area_struct *vma, bool is_pid)
+static int is_stack(struct proc_maps_private *priv,
+		    struct vm_area_struct *vma, int is_pid)
 {
-	struct inode *inode = priv->inode;
-	struct task_struct *task;
-	pid_t ret = 0;
-
-	rcu_read_lock();
-	task = pid_task(proc_pid(inode), PIDTYPE_PID);
-	if (task) {
-		task = task_of_stack(task, vma, is_pid);
+	struct mm_struct *mm = vma->vm_mm;
+	int stack = 0;
+
+	if (is_pid) {
+		stack = vma->vm_start <= mm->start_stack &&
+			vma->vm_end >= mm->start_stack;
+	} else {
+		struct inode *inode = priv->inode;
+		struct task_struct *task;
+
+		rcu_read_lock();
+		task = pid_task(proc_pid(inode), PIDTYPE_PID);
 		if (task)
-			ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info);
+			stack = vma_is_stack_for_task(vma, task);
+		rcu_read_unlock();
 	}
-	rcu_read_unlock();
-
-	return ret;
+	return stack;
 }
 
 /*
@@ -181,21 +184,9 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
 	if (file) {
 		seq_pad(m, ' ');
 		seq_file_path(m, file, "");
-	} else if (mm) {
-		pid_t tid = pid_of_stack(priv, vma, is_pid);
-
-		if (tid != 0) {
-			seq_pad(m, ' ');
-			/*
-			 * Thread stack in /proc/PID/task/TID/maps or
-			 * the main process stack.
-			 */
-			if (!is_pid || (vma->vm_start <= mm->start_stack &&
-			    vma->vm_end >= mm->start_stack))
-				seq_printf(m, "[stack]");
-			else
-				seq_printf(m, "[stack:%d]", tid);
-		}
+	} else if (mm && is_stack(priv, vma, is_pid)) {
+		seq_pad(m, ' ');
+		seq_printf(m, "[stack]");
 	}
 
 	seq_putc(m, '\n');
diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c
index 947b0f4fd0a1..e58a31e8fb2a 100644
--- a/fs/proc/thread_self.c
+++ b/fs/proc/thread_self.c
@@ -19,26 +19,29 @@ static int proc_thread_self_readlink(struct dentry *dentry, char __user *buffer,
 	return readlink_copy(buffer, buflen, tmp);
 }
 
-static const char *proc_thread_self_follow_link(struct dentry *dentry, void **cookie)
+static const char *proc_thread_self_get_link(struct dentry *dentry,
+					     struct inode *inode,
+					     struct delayed_call *done)
 {
-	struct pid_namespace *ns = dentry->d_sb->s_fs_info;
+	struct pid_namespace *ns = inode->i_sb->s_fs_info;
 	pid_t tgid = task_tgid_nr_ns(current, ns);
 	pid_t pid = task_pid_nr_ns(current, ns);
 	char *name;
 
 	if (!pid)
 		return ERR_PTR(-ENOENT);
-	name = kmalloc(PROC_NUMBUF + 6 + PROC_NUMBUF, GFP_KERNEL);
-	if (!name)
-		return ERR_PTR(-ENOMEM);
+	name = kmalloc(PROC_NUMBUF + 6 + PROC_NUMBUF,
+				dentry ? GFP_KERNEL : GFP_ATOMIC);
+	if (unlikely(!name))
+		return dentry ? ERR_PTR(-ENOMEM) : ERR_PTR(-ECHILD);
 	sprintf(name, "%d/task/%d", tgid, pid);
-	return *cookie = name;
+	set_delayed_call(done, kfree_link, name);
+	return name;
 }
 
 static const struct inode_operations proc_thread_self_inode_operations = {
 	.readlink	= proc_thread_self_readlink,
-	.follow_link	= proc_thread_self_follow_link,
-	.put_link	= kfree_put_link,
+	.get_link	= proc_thread_self_get_link,
 };
 
 static unsigned thread_self_inum;
@@ -49,7 +52,7 @@ int proc_setup_thread_self(struct super_block *s)
 	struct pid_namespace *ns = s->s_fs_info;
 	struct dentry *thread_self;
 
-	mutex_lock(&root_inode->i_mutex);
+	inode_lock(root_inode);
 	thread_self = d_alloc_name(s->s_root, "thread-self");
 	if (thread_self) {
 		struct inode *inode = new_inode_pseudo(s);
@@ -68,7 +71,7 @@ int proc_setup_thread_self(struct super_block *s)
 	} else {
 		thread_self = ERR_PTR(-ENOMEM);
 	}
-	mutex_unlock(&root_inode->i_mutex);
+	inode_unlock(root_inode);
 	if (IS_ERR(thread_self)) {
 		pr_err("proc_fill_super: can't allocate /proc/thread_self\n");
 		return PTR_ERR(thread_self);
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 4e61388ec03d..8afe10cf7df8 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -231,7 +231,9 @@ static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos,
 
 	list_for_each_entry(m, &vmcore_list, list) {
 		if (*fpos < m->offset + m->size) {
-			tsz = min_t(size_t, m->offset + m->size - *fpos, buflen);
+			tsz = (size_t)min_t(unsigned long long,
+					    m->offset + m->size - *fpos,
+					    buflen);
 			start = m->paddr + *fpos - m->offset;
 			tmp = read_from_oldmem(buffer, tsz, &start, userbuf);
 			if (tmp < 0)
@@ -277,12 +279,12 @@ static int mmap_vmcore_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (!page)
 		return VM_FAULT_OOM;
 	if (!PageUptodate(page)) {
-		offset = (loff_t) index << PAGE_CACHE_SHIFT;
+		offset = (loff_t) index << PAGE_SHIFT;
 		buf = __va((page_to_pfn(page) << PAGE_SHIFT));
 		rc = __read_vmcore(buf, PAGE_SIZE, &offset, 0);
 		if (rc < 0) {
 			unlock_page(page);
-			page_cache_release(page);
+			put_page(page);
 			return (rc == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS;
 		}
 		SetPageUptodate(page);
@@ -461,7 +463,8 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
 		if (start < m->offset + m->size) {
 			u64 paddr = 0;
 
-			tsz = min_t(size_t, m->offset + m->size - start, size);
+			tsz = (size_t)min_t(unsigned long long,
+					    m->offset + m->size - start, size);
 			paddr = m->paddr + start - m->offset;
 			if (vmcore_remap_oldmem_pfn(vma, vma->vm_start + len,
 						    paddr >> PAGE_SHIFT, tsz,
diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c
index 8ebd9a334085..3f1190d18991 100644
--- a/fs/proc_namespace.c
+++ b/fs/proc_namespace.c
@@ -95,9 +95,9 @@ static int show_vfsmnt(struct seq_file *m, struct vfsmount *mnt)
 {
 	struct proc_mounts *p = m->private;
 	struct mount *r = real_mount(mnt);
-	int err = 0;
 	struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
 	struct super_block *sb = mnt_path.dentry->d_sb;
+	int err;
 
 	if (sb->s_op->show_devname) {
 		err = sb->s_op->show_devname(m, mnt_path.dentry);
@@ -131,16 +131,17 @@ static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt)
 	struct mount *r = real_mount(mnt);
 	struct super_block *sb = mnt->mnt_sb;
 	struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
-	int err = 0;
+	int err;
 
 	seq_printf(m, "%i %i %u:%u ", r->mnt_id, r->mnt_parent->mnt_id,
 		   MAJOR(sb->s_dev), MINOR(sb->s_dev));
-	if (sb->s_op->show_path)
+	if (sb->s_op->show_path) {
 		err = sb->s_op->show_path(m, mnt->mnt_root);
-	else
+		if (err)
+			goto out;
+	} else {
 		seq_dentry(m, mnt->mnt_root, " \t\n\\");
-	if (err)
-		goto out;
+	}
 	seq_putc(m, ' ');
 
 	/* mountpoints outside of chroot jail will give SEQ_SKIP on this */
@@ -168,12 +169,13 @@ static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt)
 	seq_puts(m, " - ");
 	show_type(m, sb);
 	seq_putc(m, ' ');
-	if (sb->s_op->show_devname)
+	if (sb->s_op->show_devname) {
 		err = sb->s_op->show_devname(m, mnt->mnt_root);
-	else
+		if (err)
+			goto out;
+	} else {
 		mangle(m, r->mnt_devname ? r->mnt_devname : "none");
-	if (err)
-		goto out;
+	}
 	seq_puts(m, sb->s_flags & MS_RDONLY ? " ro" : " rw");
 	err = show_sb_opts(m, sb);
 	if (err)
@@ -191,12 +193,14 @@ static int show_vfsstat(struct seq_file *m, struct vfsmount *mnt)
 	struct mount *r = real_mount(mnt);
 	struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
 	struct super_block *sb = mnt_path.dentry->d_sb;
-	int err = 0;
+	int err;
 
 	/* device */
 	if (sb->s_op->show_devname) {
 		seq_puts(m, "device ");
 		err = sb->s_op->show_devname(m, mnt_path.dentry);
+		if (err)
+			goto out;
 	} else {
 		if (r->mnt_devname) {
 			seq_puts(m, "device ");
@@ -220,8 +224,7 @@ static int show_vfsstat(struct seq_file *m, struct vfsmount *mnt)
 	/* optional statistics */
 	if (sb->s_op->show_stats) {
 		seq_putc(m, ' ');
-		if (!err)
-			err = sb->s_op->show_stats(m, mnt_path.dentry);
+		err = sb->s_op->show_stats(m, mnt_path.dentry);
 	}
 
 	seq_putc(m, '\n');
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index d8c439d813ce..45d6110744cb 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -377,7 +377,7 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count,
 		break;
 	}
 
-	mutex_lock(&d_inode(root)->i_mutex);
+	inode_lock(d_inode(root));
 
 	dentry = d_alloc_name(root, name);
 	if (!dentry)
@@ -397,12 +397,12 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count,
 	list_add(&private->list, &allpstore);
 	spin_unlock_irqrestore(&allpstore_lock, flags);
 
-	mutex_unlock(&d_inode(root)->i_mutex);
+	inode_unlock(d_inode(root));
 
 	return 0;
 
 fail_lockedalloc:
-	mutex_unlock(&d_inode(root)->i_mutex);
+	inode_unlock(d_inode(root));
 	kfree(private);
 fail_alloc:
 	iput(inode);
@@ -420,8 +420,8 @@ static int pstore_fill_super(struct super_block *sb, void *data, int silent)
 	pstore_sb = sb;
 
 	sb->s_maxbytes		= MAX_LFS_FILESIZE;
-	sb->s_blocksize		= PAGE_CACHE_SIZE;
-	sb->s_blocksize_bits	= PAGE_CACHE_SHIFT;
+	sb->s_blocksize		= PAGE_SIZE;
+	sb->s_blocksize_bits	= PAGE_SHIFT;
 	sb->s_magic		= PSTOREFS_MAGIC;
 	sb->s_op		= &pstore_ops;
 	sb->s_time_gran		= 1;
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index 319c3a60cfa5..bd9812e83461 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -55,8 +55,8 @@ static ulong ramoops_pmsg_size = MIN_MEM_SIZE;
 module_param_named(pmsg_size, ramoops_pmsg_size, ulong, 0400);
 MODULE_PARM_DESC(pmsg_size, "size of user space message log");
 
-static ulong mem_address;
-module_param(mem_address, ulong, 0400);
+static unsigned long long mem_address;
+module_param(mem_address, ullong, 0400);
 MODULE_PARM_DESC(mem_address,
 		"start of reserved RAM used to store oops/panic logs");
 
diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c
index c4bcb778886e..3a67cfb142d8 100644
--- a/fs/qnx4/inode.c
+++ b/fs/qnx4/inode.c
@@ -316,6 +316,7 @@ struct inode *qnx4_iget(struct super_block *sb, unsigned long ino)
 		inode->i_fop = &qnx4_dir_operations;
 	} else if (S_ISLNK(inode->i_mode)) {
 		inode->i_op = &page_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &qnx4_aops;
 		qnx4_i(inode)->mmu_private = inode->i_size;
 	} else {
@@ -364,7 +365,7 @@ static int init_inodecache(void)
 	qnx4_inode_cachep = kmem_cache_create("qnx4_inode_cache",
 					     sizeof(struct qnx4_inode_info),
 					     0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD),
+						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
 					     init_once);
 	if (qnx4_inode_cachep == NULL)
 		return -ENOMEM;
diff --git a/fs/qnx6/dir.c b/fs/qnx6/dir.c
index e1f37278cf97..144ceda4948e 100644
--- a/fs/qnx6/dir.c
+++ b/fs/qnx6/dir.c
@@ -35,9 +35,9 @@ static struct page *qnx6_get_page(struct inode *dir, unsigned long n)
 static unsigned last_entry(struct inode *inode, unsigned long page_nr)
 {
 	unsigned long last_byte = inode->i_size;
-	last_byte -= page_nr << PAGE_CACHE_SHIFT;
-	if (last_byte > PAGE_CACHE_SIZE)
-		last_byte = PAGE_CACHE_SIZE;
+	last_byte -= page_nr << PAGE_SHIFT;
+	if (last_byte > PAGE_SIZE)
+		last_byte = PAGE_SIZE;
 	return last_byte / QNX6_DIR_ENTRY_SIZE;
 }
 
@@ -47,9 +47,9 @@ static struct qnx6_long_filename *qnx6_longname(struct super_block *sb,
 {
 	struct qnx6_sb_info *sbi = QNX6_SB(sb);
 	u32 s = fs32_to_cpu(sbi, de->de_long_inode); /* in block units */
-	u32 n = s >> (PAGE_CACHE_SHIFT - sb->s_blocksize_bits); /* in pages */
+	u32 n = s >> (PAGE_SHIFT - sb->s_blocksize_bits); /* in pages */
 	/* within page */
-	u32 offs = (s << sb->s_blocksize_bits) & ~PAGE_CACHE_MASK;
+	u32 offs = (s << sb->s_blocksize_bits) & ~PAGE_MASK;
 	struct address_space *mapping = sbi->longfile->i_mapping;
 	struct page *page = read_mapping_page(mapping, n, NULL);
 	if (IS_ERR(page))
@@ -115,8 +115,8 @@ static int qnx6_readdir(struct file *file, struct dir_context *ctx)
 	struct qnx6_sb_info *sbi = QNX6_SB(s);
 	loff_t pos = ctx->pos & ~(QNX6_DIR_ENTRY_SIZE - 1);
 	unsigned long npages = dir_pages(inode);
-	unsigned long n = pos >> PAGE_CACHE_SHIFT;
-	unsigned start = (pos & ~PAGE_CACHE_MASK) / QNX6_DIR_ENTRY_SIZE;
+	unsigned long n = pos >> PAGE_SHIFT;
+	unsigned start = (pos & ~PAGE_MASK) / QNX6_DIR_ENTRY_SIZE;
 	bool done = false;
 
 	ctx->pos = pos;
@@ -131,7 +131,7 @@ static int qnx6_readdir(struct file *file, struct dir_context *ctx)
 
 		if (IS_ERR(page)) {
 			pr_err("%s(): read failed\n", __func__);
-			ctx->pos = (n + 1) << PAGE_CACHE_SHIFT;
+			ctx->pos = (n + 1) << PAGE_SHIFT;
 			return PTR_ERR(page);
 		}
 		de = ((struct qnx6_dir_entry *)page_address(page)) + start;
diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c
index 32d2e1a9774c..1192422a1c56 100644
--- a/fs/qnx6/inode.c
+++ b/fs/qnx6/inode.c
@@ -542,8 +542,8 @@ struct inode *qnx6_iget(struct super_block *sb, unsigned ino)
 		iget_failed(inode);
 		return ERR_PTR(-EIO);
 	}
-	n = (ino - 1) >> (PAGE_CACHE_SHIFT - QNX6_INODE_SIZE_BITS);
-	offs = (ino - 1) & (~PAGE_CACHE_MASK >> QNX6_INODE_SIZE_BITS);
+	n = (ino - 1) >> (PAGE_SHIFT - QNX6_INODE_SIZE_BITS);
+	offs = (ino - 1) & (~PAGE_MASK >> QNX6_INODE_SIZE_BITS);
 	mapping = sbi->inodes->i_mapping;
 	page = read_mapping_page(mapping, n, NULL);
 	if (IS_ERR(page)) {
@@ -582,6 +582,7 @@ struct inode *qnx6_iget(struct super_block *sb, unsigned ino)
 		inode->i_mapping->a_ops = &qnx6_aops;
 	} else if (S_ISLNK(inode->i_mode)) {
 		inode->i_op = &page_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &qnx6_aops;
 	} else
 		init_special_inode(inode, inode->i_mode, 0);
@@ -624,7 +625,7 @@ static int init_inodecache(void)
 	qnx6_inode_cachep = kmem_cache_create("qnx6_inode_cache",
 					     sizeof(struct qnx6_inode_info),
 					     0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD),
+						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
 					     init_once);
 	if (!qnx6_inode_cachep)
 		return -ENOMEM;
diff --git a/fs/qnx6/qnx6.h b/fs/qnx6/qnx6.h
index d3fb2b698800..f23b5c4a66ad 100644
--- a/fs/qnx6/qnx6.h
+++ b/fs/qnx6/qnx6.h
@@ -128,7 +128,7 @@ extern struct qnx6_super_block *qnx6_mmi_fill_super(struct super_block *s,
 static inline void qnx6_put_page(struct page *page)
 {
 	kunmap(page);
-	page_cache_release(page);
+	put_page(page);
 }
 
 extern unsigned qnx6_find_entry(int len, struct inode *dir, const char *name,
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index ef0d64b2a6d9..ff21980d0119 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -411,6 +411,8 @@ int dquot_acquire(struct dquot *dquot)
 		ret = dqopt->ops[dquot->dq_id.type]->read_dqblk(dquot);
 	if (ret < 0)
 		goto out_iolock;
+	/* Make sure flags update is visible after dquot has been filled */
+	smp_mb__before_atomic();
 	set_bit(DQ_READ_B, &dquot->dq_flags);
 	/* Instantiate dquot if needed */
 	if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags) && !dquot->dq_off) {
@@ -427,6 +429,11 @@ int dquot_acquire(struct dquot *dquot)
 			goto out_iolock;
 		}
 	}
+	/*
+	 * Make sure flags update is visible after on-disk struct has been
+	 * allocated. Paired with smp_rmb() in dqget().
+	 */
+	smp_mb__before_atomic();
 	set_bit(DQ_ACTIVE_B, &dquot->dq_flags);
 out_iolock:
 	mutex_unlock(&dqopt->dqio_mutex);
@@ -682,9 +689,9 @@ int dquot_quota_sync(struct super_block *sb, int type)
 			continue;
 		if (!sb_has_quota_active(sb, cnt))
 			continue;
-		mutex_lock(&dqopt->files[cnt]->i_mutex);
+		inode_lock(dqopt->files[cnt]);
 		truncate_inode_pages(&dqopt->files[cnt]->i_data, 0);
-		mutex_unlock(&dqopt->files[cnt]->i_mutex);
+		inode_unlock(dqopt->files[cnt]);
 	}
 	mutex_unlock(&dqopt->dqonoff_mutex);
 
@@ -887,6 +894,11 @@ we_slept:
 			goto out;
 		}
 	}
+	/*
+	 * Make sure following reads see filled structure - paired with
+	 * smp_mb__before_atomic() in dquot_acquire().
+	 */
+	smp_rmb();
 #ifdef CONFIG_QUOTA_DEBUG
 	BUG_ON(!dquot->dq_sb);	/* Has somebody invalidated entry under us? */
 #endif
@@ -1398,7 +1410,7 @@ static int dquot_active(const struct inode *inode)
 static int __dquot_initialize(struct inode *inode, int type)
 {
 	int cnt, init_needed = 0;
-	struct dquot **dquots, *got[MAXQUOTAS];
+	struct dquot **dquots, *got[MAXQUOTAS] = {};
 	struct super_block *sb = inode->i_sb;
 	qsize_t rsv;
 	int ret = 0;
@@ -1415,7 +1427,6 @@ static int __dquot_initialize(struct inode *inode, int type)
 		int rc;
 		struct dquot *dquot;
 
-		got[cnt] = NULL;
 		if (type != -1 && cnt != type)
 			continue;
 		/*
@@ -2031,6 +2042,30 @@ int dquot_commit_info(struct super_block *sb, int type)
 }
 EXPORT_SYMBOL(dquot_commit_info);
 
+int dquot_get_next_id(struct super_block *sb, struct kqid *qid)
+{
+	struct quota_info *dqopt = sb_dqopt(sb);
+	int err;
+
+	mutex_lock(&dqopt->dqonoff_mutex);
+	if (!sb_has_quota_active(sb, qid->type)) {
+		err = -ESRCH;
+		goto out;
+	}
+	if (!dqopt->ops[qid->type]->get_next_id) {
+		err = -ENOSYS;
+		goto out;
+	}
+	mutex_lock(&dqopt->dqio_mutex);
+	err = dqopt->ops[qid->type]->get_next_id(sb, qid);
+	mutex_unlock(&dqopt->dqio_mutex);
+out:
+	mutex_unlock(&dqopt->dqonoff_mutex);
+
+	return err;
+}
+EXPORT_SYMBOL(dquot_get_next_id);
+
 /*
  * Definitions of diskquota operations.
  */
@@ -2042,6 +2077,7 @@ const struct dquot_operations dquot_operations = {
 	.write_info	= dquot_commit_info,
 	.alloc_dquot	= dquot_alloc,
 	.destroy_dquot	= dquot_destroy,
+	.get_next_id	= dquot_get_next_id,
 };
 EXPORT_SYMBOL(dquot_operations);
 
@@ -2162,12 +2198,12 @@ int dquot_disable(struct super_block *sb, int type, unsigned int flags)
 			/* If quota was reenabled in the meantime, we have
 			 * nothing to do */
 			if (!sb_has_quota_loaded(sb, cnt)) {
-				mutex_lock(&toputinode[cnt]->i_mutex);
+				inode_lock(toputinode[cnt]);
 				toputinode[cnt]->i_flags &= ~(S_IMMUTABLE |
 				  S_NOATIME | S_NOQUOTA);
 				truncate_inode_pages(&toputinode[cnt]->i_data,
 						     0);
-				mutex_unlock(&toputinode[cnt]->i_mutex);
+				inode_unlock(toputinode[cnt]);
 				mark_inode_dirty_sync(toputinode[cnt]);
 			}
 			mutex_unlock(&dqopt->dqonoff_mutex);
@@ -2258,11 +2294,11 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id,
 		/* We don't want quota and atime on quota files (deadlocks
 		 * possible) Also nobody should write to the file - we use
 		 * special IO operations which ignore the immutable bit. */
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		oldflags = inode->i_flags & (S_NOATIME | S_IMMUTABLE |
 					     S_NOQUOTA);
 		inode->i_flags |= S_NOQUOTA | S_NOATIME | S_IMMUTABLE;
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 		/*
 		 * When S_NOQUOTA is set, remove dquot references as no more
 		 * references can be added
@@ -2305,12 +2341,12 @@ out_file_init:
 	iput(inode);
 out_lock:
 	if (oldflags != -1) {
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		/* Set the flags back (in the case of accidental quotaon()
 		 * on a wrong file we don't want to mess up the flags) */
 		inode->i_flags &= ~(S_NOATIME | S_NOQUOTA | S_IMMUTABLE);
 		inode->i_flags |= oldflags;
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 	}
 	mutex_unlock(&dqopt->dqonoff_mutex);
 out_fmt:
@@ -2430,9 +2466,7 @@ int dquot_quota_on_mount(struct super_block *sb, char *qf_name,
 	struct dentry *dentry;
 	int error;
 
-	mutex_lock(&d_inode(sb->s_root)->i_mutex);
-	dentry = lookup_one_len(qf_name, sb->s_root, strlen(qf_name));
-	mutex_unlock(&d_inode(sb->s_root)->i_mutex);
+	dentry = lookup_one_len_unlocked(qf_name, sb->s_root, strlen(qf_name));
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
@@ -2565,6 +2599,27 @@ int dquot_get_dqblk(struct super_block *sb, struct kqid qid,
 }
 EXPORT_SYMBOL(dquot_get_dqblk);
 
+int dquot_get_next_dqblk(struct super_block *sb, struct kqid *qid,
+			 struct qc_dqblk *di)
+{
+	struct dquot *dquot;
+	int err;
+
+	if (!sb->dq_op->get_next_id)
+		return -ENOSYS;
+	err = sb->dq_op->get_next_id(sb, qid);
+	if (err < 0)
+		return err;
+	dquot = dqget(sb, *qid);
+	if (IS_ERR(dquot))
+		return PTR_ERR(dquot);
+	do_get_dqblk(dquot, di);
+	dqput(dquot);
+
+	return 0;
+}
+EXPORT_SYMBOL(dquot_get_next_dqblk);
+
 #define VFS_QC_MASK \
 	(QC_SPACE | QC_SPC_SOFT | QC_SPC_HARD | \
 	 QC_INO_COUNT | QC_INO_SOFT | QC_INO_HARD | \
@@ -2765,6 +2820,7 @@ const struct quotactl_ops dquot_quotactl_ops = {
 	.get_state	= dquot_get_state,
 	.set_info	= dquot_set_dqinfo,
 	.get_dqblk	= dquot_get_dqblk,
+	.get_nextdqblk	= dquot_get_next_dqblk,
 	.set_dqblk	= dquot_set_dqblk
 };
 EXPORT_SYMBOL(dquot_quotactl_ops);
@@ -2776,6 +2832,7 @@ const struct quotactl_ops dquot_quotactl_sysfile_ops = {
 	.get_state	= dquot_get_state,
 	.set_info	= dquot_set_dqinfo,
 	.get_dqblk	= dquot_get_dqblk,
+	.get_nextdqblk	= dquot_get_next_dqblk,
 	.set_dqblk	= dquot_set_dqblk
 };
 EXPORT_SYMBOL(dquot_quotactl_sysfile_ops);
@@ -2924,4 +2981,4 @@ static int __init dquot_init(void)
 
 	return 0;
 }
-module_init(dquot_init);
+fs_initcall(dquot_init);
diff --git a/fs/quota/netlink.c b/fs/quota/netlink.c
index bb2869f5dfd8..d07a2f91d858 100644
--- a/fs/quota/netlink.c
+++ b/fs/quota/netlink.c
@@ -1,7 +1,5 @@
-
 #include <linux/cred.h>
 #include <linux/init.h>
-#include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/quotaops.h>
 #include <linux/sched.h>
@@ -105,5 +103,4 @@ static int __init quota_init(void)
 		       "VFS: Failed to create quota netlink interface.\n");
 	return 0;
 };
-
-module_init(quota_init);
+fs_initcall(quota_init);
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 3746367098fd..0f10ee9892ce 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -79,7 +79,7 @@ unsigned int qtype_enforce_flag(int type)
 	return 0;
 }
 
-static int quota_quotaon(struct super_block *sb, int type, int cmd, qid_t id,
+static int quota_quotaon(struct super_block *sb, int type, qid_t id,
 		         struct path *path)
 {
 	if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_enable)
@@ -222,6 +222,34 @@ static int quota_getquota(struct super_block *sb, int type, qid_t id,
 	return 0;
 }
 
+/*
+ * Return quota for next active quota >= this id, if any exists,
+ * otherwise return -ENOENT via ->get_nextdqblk
+ */
+static int quota_getnextquota(struct super_block *sb, int type, qid_t id,
+			  void __user *addr)
+{
+	struct kqid qid;
+	struct qc_dqblk fdq;
+	struct if_nextdqblk idq;
+	int ret;
+
+	if (!sb->s_qcop->get_nextdqblk)
+		return -ENOSYS;
+	qid = make_kqid(current_user_ns(), type, id);
+	if (!qid_valid(qid))
+		return -EINVAL;
+	ret = sb->s_qcop->get_nextdqblk(sb, &qid, &fdq);
+	if (ret)
+		return ret;
+	/* struct if_nextdqblk is a superset of struct if_dqblk */
+	copy_to_if_dqblk((struct if_dqblk *)&idq, &fdq);
+	idq.dqb_id = from_kqid(current_user_ns(), qid);
+	if (copy_to_user(addr, &idq, sizeof(idq)))
+		return -EFAULT;
+	return 0;
+}
+
 static void copy_from_if_dqblk(struct qc_dqblk *dst, struct if_dqblk *src)
 {
 	dst->d_spc_hardlimit = qbtos(src->dqb_bhardlimit);
@@ -625,6 +653,34 @@ static int quota_getxquota(struct super_block *sb, int type, qid_t id,
 	return ret;
 }
 
+/*
+ * Return quota for next active quota >= this id, if any exists,
+ * otherwise return -ENOENT via ->get_nextdqblk.
+ */
+static int quota_getnextxquota(struct super_block *sb, int type, qid_t id,
+			    void __user *addr)
+{
+	struct fs_disk_quota fdq;
+	struct qc_dqblk qdq;
+	struct kqid qid;
+	qid_t id_out;
+	int ret;
+
+	if (!sb->s_qcop->get_nextdqblk)
+		return -ENOSYS;
+	qid = make_kqid(current_user_ns(), type, id);
+	if (!qid_valid(qid))
+		return -EINVAL;
+	ret = sb->s_qcop->get_nextdqblk(sb, &qid, &qdq);
+	if (ret)
+		return ret;
+	id_out = from_kqid(current_user_ns(), qid);
+	copy_to_xfs_dqblk(&fdq, &qdq, type, id_out);
+	if (copy_to_user(addr, &fdq, sizeof(fdq)))
+		return -EFAULT;
+	return ret;
+}
+
 static int quota_rmxquota(struct super_block *sb, void __user *addr)
 {
 	__u32 flags;
@@ -659,7 +715,7 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
 
 	switch (cmd) {
 	case Q_QUOTAON:
-		return quota_quotaon(sb, type, cmd, id, path);
+		return quota_quotaon(sb, type, id, path);
 	case Q_QUOTAOFF:
 		return quota_quotaoff(sb, type);
 	case Q_GETFMT:
@@ -670,6 +726,8 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
 		return quota_setinfo(sb, type, addr);
 	case Q_GETQUOTA:
 		return quota_getquota(sb, type, id, addr);
+	case Q_GETNEXTQUOTA:
+		return quota_getnextquota(sb, type, id, addr);
 	case Q_SETQUOTA:
 		return quota_setquota(sb, type, id, addr);
 	case Q_SYNC:
@@ -690,6 +748,8 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
 		return quota_setxquota(sb, type, id, addr);
 	case Q_XGETQUOTA:
 		return quota_getxquota(sb, type, id, addr);
+	case Q_XGETNEXTQUOTA:
+		return quota_getnextxquota(sb, type, id, addr);
 	case Q_XQUOTASYNC:
 		if (sb->s_flags & MS_RDONLY)
 			return -EROFS;
@@ -705,6 +765,11 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
 /* Return 1 if 'cmd' will block on frozen filesystem */
 static int quotactl_cmd_write(int cmd)
 {
+	/*
+	 * We cannot allow Q_GETQUOTA and Q_GETNEXTQUOTA without write access
+	 * as dquot_acquire() may allocate space for new structure and OCFS2
+	 * needs to increment on-disk use count.
+	 */
 	switch (cmd) {
 	case Q_GETFMT:
 	case Q_GETINFO:
@@ -712,6 +777,7 @@ static int quotactl_cmd_write(int cmd)
 	case Q_XGETQSTAT:
 	case Q_XGETQSTATV:
 	case Q_XGETQUOTA:
+	case Q_XGETNEXTQUOTA:
 	case Q_XQUOTASYNC:
 		return 0;
 	}
diff --git a/fs/quota/quota_tree.c b/fs/quota/quota_tree.c
index 58efb83dec1c..0738972e8d3f 100644
--- a/fs/quota/quota_tree.c
+++ b/fs/quota/quota_tree.c
@@ -22,10 +22,9 @@ MODULE_LICENSE("GPL");
 
 #define __QUOTA_QT_PARANOIA
 
-static int get_index(struct qtree_mem_dqinfo *info, struct kqid qid, int depth)
+static int __get_index(struct qtree_mem_dqinfo *info, qid_t id, int depth)
 {
 	unsigned int epb = info->dqi_usable_bs >> 2;
-	qid_t id = from_kqid(&init_user_ns, qid);
 
 	depth = info->dqi_qtree_depth - depth - 1;
 	while (depth--)
@@ -33,6 +32,13 @@ static int get_index(struct qtree_mem_dqinfo *info, struct kqid qid, int depth)
 	return id % epb;
 }
 
+static int get_index(struct qtree_mem_dqinfo *info, struct kqid qid, int depth)
+{
+	qid_t id = from_kqid(&init_user_ns, qid);
+
+	return __get_index(info, id, depth);
+}
+
 /* Number of entries in one blocks */
 static int qtree_dqstr_in_blk(struct qtree_mem_dqinfo *info)
 {
@@ -668,3 +674,60 @@ int qtree_release_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot)
 	return 0;
 }
 EXPORT_SYMBOL(qtree_release_dquot);
+
+static int find_next_id(struct qtree_mem_dqinfo *info, qid_t *id,
+			unsigned int blk, int depth)
+{
+	char *buf = getdqbuf(info->dqi_usable_bs);
+	__le32 *ref = (__le32 *)buf;
+	ssize_t ret;
+	unsigned int epb = info->dqi_usable_bs >> 2;
+	unsigned int level_inc = 1;
+	int i;
+
+	if (!buf)
+		return -ENOMEM;
+
+	for (i = depth; i < info->dqi_qtree_depth - 1; i++)
+		level_inc *= epb;
+
+	ret = read_blk(info, blk, buf);
+	if (ret < 0) {
+		quota_error(info->dqi_sb,
+			    "Can't read quota tree block %u", blk);
+		goto out_buf;
+	}
+	for (i = __get_index(info, *id, depth); i < epb; i++) {
+		if (ref[i] == cpu_to_le32(0)) {
+			*id += level_inc;
+			continue;
+		}
+		if (depth == info->dqi_qtree_depth - 1) {
+			ret = 0;
+			goto out_buf;
+		}
+		ret = find_next_id(info, id, le32_to_cpu(ref[i]), depth + 1);
+		if (ret != -ENOENT)
+			break;
+	}
+	if (i == epb) {
+		ret = -ENOENT;
+		goto out_buf;
+	}
+out_buf:
+	kfree(buf);
+	return ret;
+}
+
+int qtree_get_next_id(struct qtree_mem_dqinfo *info, struct kqid *qid)
+{
+	qid_t id = from_kqid(&init_user_ns, *qid);
+	int ret;
+
+	ret = find_next_id(info, &id, QT_TREEOFF, 0);
+	if (ret < 0)
+		return ret;
+	*qid = make_kqid(&init_user_ns, qid->type, id);
+	return 0;
+}
+EXPORT_SYMBOL(qtree_get_next_id);
diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c
index 2aa012a68e90..ca71bf881ad1 100644
--- a/fs/quota/quota_v2.c
+++ b/fs/quota/quota_v2.c
@@ -30,13 +30,13 @@ static void v2r1_mem2diskdqb(void *dp, struct dquot *dquot);
 static void v2r1_disk2memdqb(struct dquot *dquot, void *dp);
 static int v2r1_is_id(void *dp, struct dquot *dquot);
 
-static struct qtree_fmt_operations v2r0_qtree_ops = {
+static const struct qtree_fmt_operations v2r0_qtree_ops = {
 	.mem2disk_dqblk = v2r0_mem2diskdqb,
 	.disk2mem_dqblk = v2r0_disk2memdqb,
 	.is_id = v2r0_is_id,
 };
 
-static struct qtree_fmt_operations v2r1_qtree_ops = {
+static const struct qtree_fmt_operations v2r1_qtree_ops = {
 	.mem2disk_dqblk = v2r1_mem2diskdqb,
 	.disk2mem_dqblk = v2r1_disk2memdqb,
 	.is_id = v2r1_is_id,
@@ -304,6 +304,11 @@ static int v2_free_file_info(struct super_block *sb, int type)
 	return 0;
 }
 
+static int v2_get_next_id(struct super_block *sb, struct kqid *qid)
+{
+	return qtree_get_next_id(sb_dqinfo(sb, qid->type)->dqi_priv, qid);
+}
+
 static const struct quota_format_ops v2_format_ops = {
 	.check_quota_file	= v2_check_quota_file,
 	.read_file_info		= v2_read_file_info,
@@ -312,6 +317,7 @@ static const struct quota_format_ops v2_format_ops = {
 	.read_dqblk		= v2_read_dquot,
 	.commit_dqblk		= v2_write_dquot,
 	.release_dqblk		= v2_release_dquot,
+	.get_next_id		= v2_get_next_id,
 };
 
 static struct quota_format_type v2r0_quota_format = {
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index 889d558b4e05..1ab6e6c2e60e 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -79,6 +79,7 @@ struct inode *ramfs_get_inode(struct super_block *sb,
 			break;
 		case S_IFLNK:
 			inode->i_op = &page_symlink_inode_operations;
+			inode_nohighmem(inode);
 			break;
 		}
 	}
@@ -222,8 +223,8 @@ int ramfs_fill_super(struct super_block *sb, void *data, int silent)
 		return err;
 
 	sb->s_maxbytes		= MAX_LFS_FILESIZE;
-	sb->s_blocksize		= PAGE_CACHE_SIZE;
-	sb->s_blocksize_bits	= PAGE_CACHE_SHIFT;
+	sb->s_blocksize		= PAGE_SIZE;
+	sb->s_blocksize_bits	= PAGE_SHIFT;
 	sb->s_magic		= RAMFS_MAGIC;
 	sb->s_op		= &ramfs_ops;
 	sb->s_time_gran		= 1;
diff --git a/fs/read_write.c b/fs/read_write.c
index 819ef3faf1bb..cf377cf9dfe3 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -16,6 +16,8 @@
 #include <linux/pagemap.h>
 #include <linux/splice.h>
 #include <linux/compat.h>
+#include <linux/mount.h>
+#include <linux/fs.h>
 #include "internal.h"
 
 #include <asm/uaccess.h>
@@ -171,6 +173,45 @@ loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t si
 EXPORT_SYMBOL(fixed_size_llseek);
 
 /**
+ * no_seek_end_llseek - llseek implementation for fixed-sized devices
+ * @file:	file structure to seek on
+ * @offset:	file offset to seek to
+ * @whence:	type of seek
+ *
+ */
+loff_t no_seek_end_llseek(struct file *file, loff_t offset, int whence)
+{
+	switch (whence) {
+	case SEEK_SET: case SEEK_CUR:
+		return generic_file_llseek_size(file, offset, whence,
+						OFFSET_MAX, 0);
+	default:
+		return -EINVAL;
+	}
+}
+EXPORT_SYMBOL(no_seek_end_llseek);
+
+/**
+ * no_seek_end_llseek_size - llseek implementation for fixed-sized devices
+ * @file:	file structure to seek on
+ * @offset:	file offset to seek to
+ * @whence:	type of seek
+ * @size:	maximal offset allowed
+ *
+ */
+loff_t no_seek_end_llseek_size(struct file *file, loff_t offset, int whence, loff_t size)
+{
+	switch (whence) {
+	case SEEK_SET: case SEEK_CUR:
+		return generic_file_llseek_size(file, offset, whence,
+						size, 0);
+	default:
+		return -EINVAL;
+	}
+}
+EXPORT_SYMBOL(no_seek_end_llseek_size);
+
+/**
  * noop_llseek - No Operation Performed llseek implementation
  * @file:	file structure to seek on
  * @offset:	file offset to seek to
@@ -198,7 +239,7 @@ loff_t default_llseek(struct file *file, loff_t offset, int whence)
 	struct inode *inode = file_inode(file);
 	loff_t retval;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	switch (whence) {
 		case SEEK_END:
 			offset += i_size_read(inode);
@@ -243,7 +284,7 @@ loff_t default_llseek(struct file *file, loff_t offset, int whence)
 		retval = offset;
 	}
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return retval;
 }
 EXPORT_SYMBOL(default_llseek);
@@ -395,9 +436,8 @@ int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t
 	}
 
 	if (unlikely(inode->i_flctx && mandatory_lock(inode))) {
-		retval = locks_mandatory_area(
-			read_write == READ ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE,
-			inode, file, pos, count);
+		retval = locks_mandatory_area(inode, file, pos, pos + count - 1,
+				read_write == READ ? F_RDLCK : F_WRLCK);
 		if (retval < 0)
 			return retval;
 	}
@@ -653,12 +693,17 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to)
 EXPORT_SYMBOL(iov_shorten);
 
 static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
-		loff_t *ppos, iter_fn_t fn)
+		loff_t *ppos, iter_fn_t fn, int flags)
 {
 	struct kiocb kiocb;
 	ssize_t ret;
 
+	if (flags & ~RWF_HIPRI)
+		return -EOPNOTSUPP;
+
 	init_sync_kiocb(&kiocb, filp);
+	if (flags & RWF_HIPRI)
+		kiocb.ki_flags |= IOCB_HIPRI;
 	kiocb.ki_pos = *ppos;
 
 	ret = fn(&kiocb, iter);
@@ -669,10 +714,13 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
 
 /* Do it by hand, with file-ops */
 static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
-		loff_t *ppos, io_fn_t fn)
+		loff_t *ppos, io_fn_t fn, int flags)
 {
 	ssize_t ret = 0;
 
+	if (flags & ~RWF_HIPRI)
+		return -EOPNOTSUPP;
+
 	while (iov_iter_count(iter)) {
 		struct iovec iovec = iov_iter_iovec(iter);
 		ssize_t nr;
@@ -773,7 +821,8 @@ out:
 
 static ssize_t do_readv_writev(int type, struct file *file,
 			       const struct iovec __user * uvector,
-			       unsigned long nr_segs, loff_t *pos)
+			       unsigned long nr_segs, loff_t *pos,
+			       int flags)
 {
 	size_t tot_len;
 	struct iovec iovstack[UIO_FASTIOV];
@@ -805,9 +854,9 @@ static ssize_t do_readv_writev(int type, struct file *file,
 	}
 
 	if (iter_fn)
-		ret = do_iter_readv_writev(file, &iter, pos, iter_fn);
+		ret = do_iter_readv_writev(file, &iter, pos, iter_fn, flags);
 	else
-		ret = do_loop_readv_writev(file, &iter, pos, fn);
+		ret = do_loop_readv_writev(file, &iter, pos, fn, flags);
 
 	if (type != READ)
 		file_end_write(file);
@@ -824,40 +873,40 @@ out:
 }
 
 ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
-		  unsigned long vlen, loff_t *pos)
+		  unsigned long vlen, loff_t *pos, int flags)
 {
 	if (!(file->f_mode & FMODE_READ))
 		return -EBADF;
 	if (!(file->f_mode & FMODE_CAN_READ))
 		return -EINVAL;
 
-	return do_readv_writev(READ, file, vec, vlen, pos);
+	return do_readv_writev(READ, file, vec, vlen, pos, flags);
 }
 
 EXPORT_SYMBOL(vfs_readv);
 
 ssize_t vfs_writev(struct file *file, const struct iovec __user *vec,
-		   unsigned long vlen, loff_t *pos)
+		   unsigned long vlen, loff_t *pos, int flags)
 {
 	if (!(file->f_mode & FMODE_WRITE))
 		return -EBADF;
 	if (!(file->f_mode & FMODE_CAN_WRITE))
 		return -EINVAL;
 
-	return do_readv_writev(WRITE, file, vec, vlen, pos);
+	return do_readv_writev(WRITE, file, vec, vlen, pos, flags);
 }
 
 EXPORT_SYMBOL(vfs_writev);
 
-SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
-		unsigned long, vlen)
+static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec,
+			unsigned long vlen, int flags)
 {
 	struct fd f = fdget_pos(fd);
 	ssize_t ret = -EBADF;
 
 	if (f.file) {
 		loff_t pos = file_pos_read(f.file);
-		ret = vfs_readv(f.file, vec, vlen, &pos);
+		ret = vfs_readv(f.file, vec, vlen, &pos, flags);
 		if (ret >= 0)
 			file_pos_write(f.file, pos);
 		fdput_pos(f);
@@ -869,15 +918,15 @@ SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
 	return ret;
 }
 
-SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
-		unsigned long, vlen)
+static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec,
+			 unsigned long vlen, int flags)
 {
 	struct fd f = fdget_pos(fd);
 	ssize_t ret = -EBADF;
 
 	if (f.file) {
 		loff_t pos = file_pos_read(f.file);
-		ret = vfs_writev(f.file, vec, vlen, &pos);
+		ret = vfs_writev(f.file, vec, vlen, &pos, flags);
 		if (ret >= 0)
 			file_pos_write(f.file, pos);
 		fdput_pos(f);
@@ -895,10 +944,9 @@ static inline loff_t pos_from_hilo(unsigned long high, unsigned long low)
 	return (((loff_t)high << HALF_LONG_BITS) << HALF_LONG_BITS) | low;
 }
 
-SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
-		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
+static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec,
+			 unsigned long vlen, loff_t pos, int flags)
 {
-	loff_t pos = pos_from_hilo(pos_h, pos_l);
 	struct fd f;
 	ssize_t ret = -EBADF;
 
@@ -909,7 +957,7 @@ SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
 	if (f.file) {
 		ret = -ESPIPE;
 		if (f.file->f_mode & FMODE_PREAD)
-			ret = vfs_readv(f.file, vec, vlen, &pos);
+			ret = vfs_readv(f.file, vec, vlen, &pos, flags);
 		fdput(f);
 	}
 
@@ -919,10 +967,9 @@ SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
 	return ret;
 }
 
-SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
-		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
+static ssize_t do_pwritev(unsigned long fd, const struct iovec __user *vec,
+			  unsigned long vlen, loff_t pos, int flags)
 {
-	loff_t pos = pos_from_hilo(pos_h, pos_l);
 	struct fd f;
 	ssize_t ret = -EBADF;
 
@@ -933,7 +980,7 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
 	if (f.file) {
 		ret = -ESPIPE;
 		if (f.file->f_mode & FMODE_PWRITE)
-			ret = vfs_writev(f.file, vec, vlen, &pos);
+			ret = vfs_writev(f.file, vec, vlen, &pos, flags);
 		fdput(f);
 	}
 
@@ -943,11 +990,64 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
 	return ret;
 }
 
+SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
+		unsigned long, vlen)
+{
+	return do_readv(fd, vec, vlen, 0);
+}
+
+SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
+		unsigned long, vlen)
+{
+	return do_writev(fd, vec, vlen, 0);
+}
+
+SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
+		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
+{
+	loff_t pos = pos_from_hilo(pos_h, pos_l);
+
+	return do_preadv(fd, vec, vlen, pos, 0);
+}
+
+SYSCALL_DEFINE6(preadv2, unsigned long, fd, const struct iovec __user *, vec,
+		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h,
+		int, flags)
+{
+	loff_t pos = pos_from_hilo(pos_h, pos_l);
+
+	if (pos == -1)
+		return do_readv(fd, vec, vlen, flags);
+
+	return do_preadv(fd, vec, vlen, pos, flags);
+}
+
+SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
+		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
+{
+	loff_t pos = pos_from_hilo(pos_h, pos_l);
+
+	return do_pwritev(fd, vec, vlen, pos, 0);
+}
+
+SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec,
+		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h,
+		int, flags)
+{
+	loff_t pos = pos_from_hilo(pos_h, pos_l);
+
+	if (pos == -1)
+		return do_writev(fd, vec, vlen, flags);
+
+	return do_pwritev(fd, vec, vlen, pos, flags);
+}
+
 #ifdef CONFIG_COMPAT
 
 static ssize_t compat_do_readv_writev(int type, struct file *file,
 			       const struct compat_iovec __user *uvector,
-			       unsigned long nr_segs, loff_t *pos)
+			       unsigned long nr_segs, loff_t *pos,
+			       int flags)
 {
 	compat_ssize_t tot_len;
 	struct iovec iovstack[UIO_FASTIOV];
@@ -979,9 +1079,9 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
 	}
 
 	if (iter_fn)
-		ret = do_iter_readv_writev(file, &iter, pos, iter_fn);
+		ret = do_iter_readv_writev(file, &iter, pos, iter_fn, flags);
 	else
-		ret = do_loop_readv_writev(file, &iter, pos, fn);
+		ret = do_loop_readv_writev(file, &iter, pos, fn, flags);
 
 	if (type != READ)
 		file_end_write(file);
@@ -999,7 +1099,7 @@ out:
 
 static size_t compat_readv(struct file *file,
 			   const struct compat_iovec __user *vec,
-			   unsigned long vlen, loff_t *pos)
+			   unsigned long vlen, loff_t *pos, int flags)
 {
 	ssize_t ret = -EBADF;
 
@@ -1010,7 +1110,7 @@ static size_t compat_readv(struct file *file,
 	if (!(file->f_mode & FMODE_CAN_READ))
 		goto out;
 
-	ret = compat_do_readv_writev(READ, file, vec, vlen, pos);
+	ret = compat_do_readv_writev(READ, file, vec, vlen, pos, flags);
 
 out:
 	if (ret > 0)
@@ -1019,9 +1119,9 @@ out:
 	return ret;
 }
 
-COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
-		const struct compat_iovec __user *,vec,
-		compat_ulong_t, vlen)
+static size_t do_compat_readv(compat_ulong_t fd,
+				 const struct compat_iovec __user *vec,
+				 compat_ulong_t vlen, int flags)
 {
 	struct fd f = fdget_pos(fd);
 	ssize_t ret;
@@ -1030,16 +1130,24 @@ COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
 	if (!f.file)
 		return -EBADF;
 	pos = f.file->f_pos;
-	ret = compat_readv(f.file, vec, vlen, &pos);
+	ret = compat_readv(f.file, vec, vlen, &pos, flags);
 	if (ret >= 0)
 		f.file->f_pos = pos;
 	fdput_pos(f);
 	return ret;
+
 }
 
-static long __compat_sys_preadv64(unsigned long fd,
+COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
+		const struct compat_iovec __user *,vec,
+		compat_ulong_t, vlen)
+{
+	return do_compat_readv(fd, vec, vlen, 0);
+}
+
+static long do_compat_preadv64(unsigned long fd,
 				  const struct compat_iovec __user *vec,
-				  unsigned long vlen, loff_t pos)
+				  unsigned long vlen, loff_t pos, int flags)
 {
 	struct fd f;
 	ssize_t ret;
@@ -1051,7 +1159,7 @@ static long __compat_sys_preadv64(unsigned long fd,
 		return -EBADF;
 	ret = -ESPIPE;
 	if (f.file->f_mode & FMODE_PREAD)
-		ret = compat_readv(f.file, vec, vlen, &pos);
+		ret = compat_readv(f.file, vec, vlen, &pos, flags);
 	fdput(f);
 	return ret;
 }
@@ -1061,7 +1169,7 @@ COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
 		const struct compat_iovec __user *,vec,
 		unsigned long, vlen, loff_t, pos)
 {
-	return __compat_sys_preadv64(fd, vec, vlen, pos);
+	return do_compat_preadv64(fd, vec, vlen, pos, 0);
 }
 #endif
 
@@ -1071,12 +1179,25 @@ COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd,
 {
 	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 
-	return __compat_sys_preadv64(fd, vec, vlen, pos);
+	return do_compat_preadv64(fd, vec, vlen, pos, 0);
+}
+
+COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd,
+		const struct compat_iovec __user *,vec,
+		compat_ulong_t, vlen, u32, pos_low, u32, pos_high,
+		int, flags)
+{
+	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+
+	if (pos == -1)
+		return do_compat_readv(fd, vec, vlen, flags);
+
+	return do_compat_preadv64(fd, vec, vlen, pos, flags);
 }
 
 static size_t compat_writev(struct file *file,
 			    const struct compat_iovec __user *vec,
-			    unsigned long vlen, loff_t *pos)
+			    unsigned long vlen, loff_t *pos, int flags)
 {
 	ssize_t ret = -EBADF;
 
@@ -1087,7 +1208,7 @@ static size_t compat_writev(struct file *file,
 	if (!(file->f_mode & FMODE_CAN_WRITE))
 		goto out;
 
-	ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos);
+	ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos, 0);
 
 out:
 	if (ret > 0)
@@ -1096,9 +1217,9 @@ out:
 	return ret;
 }
 
-COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
-		const struct compat_iovec __user *, vec,
-		compat_ulong_t, vlen)
+static size_t do_compat_writev(compat_ulong_t fd,
+				  const struct compat_iovec __user* vec,
+				  compat_ulong_t vlen, int flags)
 {
 	struct fd f = fdget_pos(fd);
 	ssize_t ret;
@@ -1107,16 +1228,23 @@ COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
 	if (!f.file)
 		return -EBADF;
 	pos = f.file->f_pos;
-	ret = compat_writev(f.file, vec, vlen, &pos);
+	ret = compat_writev(f.file, vec, vlen, &pos, flags);
 	if (ret >= 0)
 		f.file->f_pos = pos;
 	fdput_pos(f);
 	return ret;
 }
 
-static long __compat_sys_pwritev64(unsigned long fd,
+COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
+		const struct compat_iovec __user *, vec,
+		compat_ulong_t, vlen)
+{
+	return do_compat_writev(fd, vec, vlen, 0);
+}
+
+static long do_compat_pwritev64(unsigned long fd,
 				   const struct compat_iovec __user *vec,
-				   unsigned long vlen, loff_t pos)
+				   unsigned long vlen, loff_t pos, int flags)
 {
 	struct fd f;
 	ssize_t ret;
@@ -1128,7 +1256,7 @@ static long __compat_sys_pwritev64(unsigned long fd,
 		return -EBADF;
 	ret = -ESPIPE;
 	if (f.file->f_mode & FMODE_PWRITE)
-		ret = compat_writev(f.file, vec, vlen, &pos);
+		ret = compat_writev(f.file, vec, vlen, &pos, flags);
 	fdput(f);
 	return ret;
 }
@@ -1138,7 +1266,7 @@ COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
 		const struct compat_iovec __user *,vec,
 		unsigned long, vlen, loff_t, pos)
 {
-	return __compat_sys_pwritev64(fd, vec, vlen, pos);
+	return do_compat_pwritev64(fd, vec, vlen, pos, 0);
 }
 #endif
 
@@ -1148,8 +1276,21 @@ COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd,
 {
 	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 
-	return __compat_sys_pwritev64(fd, vec, vlen, pos);
+	return do_compat_pwritev64(fd, vec, vlen, pos, 0);
 }
+
+COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd,
+		const struct compat_iovec __user *,vec,
+		compat_ulong_t, vlen, u32, pos_low, u32, pos_high, int, flags)
+{
+	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+
+	if (pos == -1)
+		return do_compat_writev(fd, vec, vlen, flags);
+
+	return do_compat_pwritev64(fd, vec, vlen, pos, flags);
+}
+
 #endif
 
 static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
@@ -1327,3 +1468,304 @@ COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd,
 	return do_sendfile(out_fd, in_fd, NULL, count, 0);
 }
 #endif
+
+/*
+ * copy_file_range() differs from regular file read and write in that it
+ * specifically allows return partial success.  When it does so is up to
+ * the copy_file_range method.
+ */
+ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
+			    struct file *file_out, loff_t pos_out,
+			    size_t len, unsigned int flags)
+{
+	struct inode *inode_in = file_inode(file_in);
+	struct inode *inode_out = file_inode(file_out);
+	ssize_t ret;
+
+	if (flags != 0)
+		return -EINVAL;
+
+	/* copy_file_range allows full ssize_t len, ignoring MAX_RW_COUNT  */
+	ret = rw_verify_area(READ, file_in, &pos_in, len);
+	if (ret >= 0)
+		ret = rw_verify_area(WRITE, file_out, &pos_out, len);
+	if (ret < 0)
+		return ret;
+
+	if (!(file_in->f_mode & FMODE_READ) ||
+	    !(file_out->f_mode & FMODE_WRITE) ||
+	    (file_out->f_flags & O_APPEND))
+		return -EBADF;
+
+	/* this could be relaxed once a method supports cross-fs copies */
+	if (inode_in->i_sb != inode_out->i_sb)
+		return -EXDEV;
+
+	if (len == 0)
+		return 0;
+
+	ret = mnt_want_write_file(file_out);
+	if (ret)
+		return ret;
+
+	ret = -EOPNOTSUPP;
+	if (file_out->f_op->copy_file_range)
+		ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out,
+						      pos_out, len, flags);
+	if (ret == -EOPNOTSUPP)
+		ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out,
+				len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0);
+
+	if (ret > 0) {
+		fsnotify_access(file_in);
+		add_rchar(current, ret);
+		fsnotify_modify(file_out);
+		add_wchar(current, ret);
+	}
+	inc_syscr(current);
+	inc_syscw(current);
+
+	mnt_drop_write_file(file_out);
+
+	return ret;
+}
+EXPORT_SYMBOL(vfs_copy_file_range);
+
+SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in,
+		int, fd_out, loff_t __user *, off_out,
+		size_t, len, unsigned int, flags)
+{
+	loff_t pos_in;
+	loff_t pos_out;
+	struct fd f_in;
+	struct fd f_out;
+	ssize_t ret = -EBADF;
+
+	f_in = fdget(fd_in);
+	if (!f_in.file)
+		goto out2;
+
+	f_out = fdget(fd_out);
+	if (!f_out.file)
+		goto out1;
+
+	ret = -EFAULT;
+	if (off_in) {
+		if (copy_from_user(&pos_in, off_in, sizeof(loff_t)))
+			goto out;
+	} else {
+		pos_in = f_in.file->f_pos;
+	}
+
+	if (off_out) {
+		if (copy_from_user(&pos_out, off_out, sizeof(loff_t)))
+			goto out;
+	} else {
+		pos_out = f_out.file->f_pos;
+	}
+
+	ret = vfs_copy_file_range(f_in.file, pos_in, f_out.file, pos_out, len,
+				  flags);
+	if (ret > 0) {
+		pos_in += ret;
+		pos_out += ret;
+
+		if (off_in) {
+			if (copy_to_user(off_in, &pos_in, sizeof(loff_t)))
+				ret = -EFAULT;
+		} else {
+			f_in.file->f_pos = pos_in;
+		}
+
+		if (off_out) {
+			if (copy_to_user(off_out, &pos_out, sizeof(loff_t)))
+				ret = -EFAULT;
+		} else {
+			f_out.file->f_pos = pos_out;
+		}
+	}
+
+out:
+	fdput(f_out);
+out1:
+	fdput(f_in);
+out2:
+	return ret;
+}
+
+static int clone_verify_area(struct file *file, loff_t pos, u64 len, bool write)
+{
+	struct inode *inode = file_inode(file);
+
+	if (unlikely(pos < 0))
+		return -EINVAL;
+
+	 if (unlikely((loff_t) (pos + len) < 0))
+		return -EINVAL;
+
+	if (unlikely(inode->i_flctx && mandatory_lock(inode))) {
+		loff_t end = len ? pos + len - 1 : OFFSET_MAX;
+		int retval;
+
+		retval = locks_mandatory_area(inode, file, pos, end,
+				write ? F_WRLCK : F_RDLCK);
+		if (retval < 0)
+			return retval;
+	}
+
+	return security_file_permission(file, write ? MAY_WRITE : MAY_READ);
+}
+
+int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
+		struct file *file_out, loff_t pos_out, u64 len)
+{
+	struct inode *inode_in = file_inode(file_in);
+	struct inode *inode_out = file_inode(file_out);
+	int ret;
+
+	if (inode_in->i_sb != inode_out->i_sb ||
+	    file_in->f_path.mnt != file_out->f_path.mnt)
+		return -EXDEV;
+
+	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
+		return -EISDIR;
+	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
+		return -EINVAL;
+
+	if (!(file_in->f_mode & FMODE_READ) ||
+	    !(file_out->f_mode & FMODE_WRITE) ||
+	    (file_out->f_flags & O_APPEND))
+		return -EBADF;
+
+	if (!file_in->f_op->clone_file_range)
+		return -EOPNOTSUPP;
+
+	ret = clone_verify_area(file_in, pos_in, len, false);
+	if (ret)
+		return ret;
+
+	ret = clone_verify_area(file_out, pos_out, len, true);
+	if (ret)
+		return ret;
+
+	if (pos_in + len > i_size_read(inode_in))
+		return -EINVAL;
+
+	ret = mnt_want_write_file(file_out);
+	if (ret)
+		return ret;
+
+	ret = file_in->f_op->clone_file_range(file_in, pos_in,
+			file_out, pos_out, len);
+	if (!ret) {
+		fsnotify_access(file_in);
+		fsnotify_modify(file_out);
+	}
+
+	mnt_drop_write_file(file_out);
+	return ret;
+}
+EXPORT_SYMBOL(vfs_clone_file_range);
+
+int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
+{
+	struct file_dedupe_range_info *info;
+	struct inode *src = file_inode(file);
+	u64 off;
+	u64 len;
+	int i;
+	int ret;
+	bool is_admin = capable(CAP_SYS_ADMIN);
+	u16 count = same->dest_count;
+	struct file *dst_file;
+	loff_t dst_off;
+	ssize_t deduped;
+
+	if (!(file->f_mode & FMODE_READ))
+		return -EINVAL;
+
+	if (same->reserved1 || same->reserved2)
+		return -EINVAL;
+
+	off = same->src_offset;
+	len = same->src_length;
+
+	ret = -EISDIR;
+	if (S_ISDIR(src->i_mode))
+		goto out;
+
+	ret = -EINVAL;
+	if (!S_ISREG(src->i_mode))
+		goto out;
+
+	ret = clone_verify_area(file, off, len, false);
+	if (ret < 0)
+		goto out;
+	ret = 0;
+
+	/* pre-format output fields to sane values */
+	for (i = 0; i < count; i++) {
+		same->info[i].bytes_deduped = 0ULL;
+		same->info[i].status = FILE_DEDUPE_RANGE_SAME;
+	}
+
+	for (i = 0, info = same->info; i < count; i++, info++) {
+		struct inode *dst;
+		struct fd dst_fd = fdget(info->dest_fd);
+
+		dst_file = dst_fd.file;
+		if (!dst_file) {
+			info->status = -EBADF;
+			goto next_loop;
+		}
+		dst = file_inode(dst_file);
+
+		ret = mnt_want_write_file(dst_file);
+		if (ret) {
+			info->status = ret;
+			goto next_loop;
+		}
+
+		dst_off = info->dest_offset;
+		ret = clone_verify_area(dst_file, dst_off, len, true);
+		if (ret < 0) {
+			info->status = ret;
+			goto next_file;
+		}
+		ret = 0;
+
+		if (info->reserved) {
+			info->status = -EINVAL;
+		} else if (!(is_admin || (dst_file->f_mode & FMODE_WRITE))) {
+			info->status = -EINVAL;
+		} else if (file->f_path.mnt != dst_file->f_path.mnt) {
+			info->status = -EXDEV;
+		} else if (S_ISDIR(dst->i_mode)) {
+			info->status = -EISDIR;
+		} else if (dst_file->f_op->dedupe_file_range == NULL) {
+			info->status = -EINVAL;
+		} else {
+			deduped = dst_file->f_op->dedupe_file_range(file, off,
+							len, dst_file,
+							info->dest_offset);
+			if (deduped == -EBADE)
+				info->status = FILE_DEDUPE_RANGE_DIFFERS;
+			else if (deduped < 0)
+				info->status = deduped;
+			else
+				info->bytes_deduped += deduped;
+		}
+
+next_file:
+		mnt_drop_write_file(dst_file);
+next_loop:
+		fdput(dst_fd);
+
+		if (fatal_signal_pending(current))
+			goto out;
+	}
+
+out:
+	return ret;
+}
+EXPORT_SYMBOL(vfs_dedupe_file_range);
diff --git a/fs/readdir.c b/fs/readdir.c
index ced679179cac..e69ef3b79787 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -44,7 +44,7 @@ int iterate_dir(struct file *file, struct dir_context *ctx)
 		fsnotify_access(file);
 		file_accessed(file);
 	}
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 out:
 	return res;
 }
diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c
index 4a024e2ceb9f..3abd4004184b 100644
--- a/fs/reiserfs/dir.c
+++ b/fs/reiserfs/dir.c
@@ -38,11 +38,11 @@ static int reiserfs_dir_fsync(struct file *filp, loff_t start, loff_t end,
 	if (err)
 		return err;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	reiserfs_write_lock(inode->i_sb);
 	err = reiserfs_commit_for_inode(inode);
 	reiserfs_write_unlock(inode->i_sb);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	if (err < 0)
 		return err;
 	return 0;
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index 96a1bcf33db4..389773711de4 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -158,7 +158,7 @@ static int reiserfs_sync_file(struct file *filp, loff_t start, loff_t end,
 	if (err)
 		return err;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	BUG_ON(!S_ISREG(inode->i_mode));
 	err = sync_mapping_buffers(inode->i_mapping);
 	reiserfs_write_lock(inode->i_sb);
@@ -166,7 +166,7 @@ static int reiserfs_sync_file(struct file *filp, loff_t start, loff_t end,
 	reiserfs_write_unlock(inode->i_sb);
 	if (barrier_done != 1 && reiserfs_barrier_flush(inode->i_sb))
 		blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	if (barrier_done < 0)
 		return barrier_done;
 	return (err < 0) ? -EIO : 0;
@@ -180,11 +180,11 @@ int reiserfs_commit_page(struct inode *inode, struct page *page,
 	int partial = 0;
 	unsigned blocksize;
 	struct buffer_head *bh, *head;
-	unsigned long i_size_index = inode->i_size >> PAGE_CACHE_SHIFT;
+	unsigned long i_size_index = inode->i_size >> PAGE_SHIFT;
 	int new;
 	int logit = reiserfs_file_data_log(inode);
 	struct super_block *s = inode->i_sb;
-	int bh_per_page = PAGE_CACHE_SIZE / s->s_blocksize;
+	int bh_per_page = PAGE_SIZE / s->s_blocksize;
 	struct reiserfs_transaction_handle th;
 	int ret = 0;
 
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 3d8e7e671d5b..d5c2e9c865de 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -386,7 +386,7 @@ static int _get_block_create_0(struct inode *inode, sector_t block,
 		goto finished;
 	}
 	/* read file tail into part of page */
-	offset = (cpu_key_k_offset(&key) - 1) & (PAGE_CACHE_SIZE - 1);
+	offset = (cpu_key_k_offset(&key) - 1) & (PAGE_SIZE - 1);
 	copy_item_head(&tmp_ih, ih);
 
 	/*
@@ -587,10 +587,10 @@ static int convert_tail_for_hole(struct inode *inode,
 		return -EIO;
 
 	/* always try to read until the end of the block */
-	tail_start = tail_offset & (PAGE_CACHE_SIZE - 1);
+	tail_start = tail_offset & (PAGE_SIZE - 1);
 	tail_end = (tail_start | (bh_result->b_size - 1)) + 1;
 
-	index = tail_offset >> PAGE_CACHE_SHIFT;
+	index = tail_offset >> PAGE_SHIFT;
 	/*
 	 * hole_page can be zero in case of direct_io, we are sure
 	 * that we cannot get here if we write with O_DIRECT into tail page
@@ -629,7 +629,7 @@ static int convert_tail_for_hole(struct inode *inode,
 unlock:
 	if (tail_page != hole_page) {
 		unlock_page(tail_page);
-		page_cache_release(tail_page);
+		put_page(tail_page);
 	}
 out:
 	return retval;
@@ -1361,6 +1361,7 @@ static void init_inode(struct inode *inode, struct treepath *path)
 		inode->i_fop = &reiserfs_dir_operations;
 	} else if (S_ISLNK(inode->i_mode)) {
 		inode->i_op = &reiserfs_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &reiserfs_address_space_operations;
 	} else {
 		inode->i_blocks = 0;
@@ -2188,11 +2189,11 @@ static int grab_tail_page(struct inode *inode,
 	 * we want the page with the last byte in the file,
 	 * not the page that will hold the next byte for appending
 	 */
-	unsigned long index = (inode->i_size - 1) >> PAGE_CACHE_SHIFT;
+	unsigned long index = (inode->i_size - 1) >> PAGE_SHIFT;
 	unsigned long pos = 0;
 	unsigned long start = 0;
 	unsigned long blocksize = inode->i_sb->s_blocksize;
-	unsigned long offset = (inode->i_size) & (PAGE_CACHE_SIZE - 1);
+	unsigned long offset = (inode->i_size) & (PAGE_SIZE - 1);
 	struct buffer_head *bh;
 	struct buffer_head *head;
 	struct page *page;
@@ -2250,7 +2251,7 @@ out:
 
 unlock:
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 	return error;
 }
 
@@ -2264,7 +2265,7 @@ int reiserfs_truncate_file(struct inode *inode, int update_timestamps)
 {
 	struct reiserfs_transaction_handle th;
 	/* we want the offset for the first byte after the end of the file */
-	unsigned long offset = inode->i_size & (PAGE_CACHE_SIZE - 1);
+	unsigned long offset = inode->i_size & (PAGE_SIZE - 1);
 	unsigned blocksize = inode->i_sb->s_blocksize;
 	unsigned length;
 	struct page *page = NULL;
@@ -2344,7 +2345,7 @@ int reiserfs_truncate_file(struct inode *inode, int update_timestamps)
 			}
 		}
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 	}
 
 	reiserfs_write_unlock(inode->i_sb);
@@ -2353,7 +2354,7 @@ int reiserfs_truncate_file(struct inode *inode, int update_timestamps)
 out:
 	if (page) {
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 	}
 
 	reiserfs_write_unlock(inode->i_sb);
@@ -2425,7 +2426,7 @@ research:
 	} else if (is_direct_le_ih(ih)) {
 		char *p;
 		p = page_address(bh_result->b_page);
-		p += (byte_offset - 1) & (PAGE_CACHE_SIZE - 1);
+		p += (byte_offset - 1) & (PAGE_SIZE - 1);
 		copy_size = ih_item_len(ih) - pos_in_item;
 
 		fs_gen = get_generation(inode->i_sb);
@@ -2524,7 +2525,7 @@ static int reiserfs_write_full_page(struct page *page,
 				    struct writeback_control *wbc)
 {
 	struct inode *inode = page->mapping->host;
-	unsigned long end_index = inode->i_size >> PAGE_CACHE_SHIFT;
+	unsigned long end_index = inode->i_size >> PAGE_SHIFT;
 	int error = 0;
 	unsigned long block;
 	sector_t last_block;
@@ -2534,7 +2535,7 @@ static int reiserfs_write_full_page(struct page *page,
 	int checked = PageChecked(page);
 	struct reiserfs_transaction_handle th;
 	struct super_block *s = inode->i_sb;
-	int bh_per_page = PAGE_CACHE_SIZE / s->s_blocksize;
+	int bh_per_page = PAGE_SIZE / s->s_blocksize;
 	th.t_trans_id = 0;
 
 	/* no logging allowed when nonblocking or from PF_MEMALLOC */
@@ -2563,16 +2564,16 @@ static int reiserfs_write_full_page(struct page *page,
 	if (page->index >= end_index) {
 		unsigned last_offset;
 
-		last_offset = inode->i_size & (PAGE_CACHE_SIZE - 1);
+		last_offset = inode->i_size & (PAGE_SIZE - 1);
 		/* no file contents in this page */
 		if (page->index >= end_index + 1 || !last_offset) {
 			unlock_page(page);
 			return 0;
 		}
-		zero_user_segment(page, last_offset, PAGE_CACHE_SIZE);
+		zero_user_segment(page, last_offset, PAGE_SIZE);
 	}
 	bh = head;
-	block = page->index << (PAGE_CACHE_SHIFT - s->s_blocksize_bits);
+	block = page->index << (PAGE_SHIFT - s->s_blocksize_bits);
 	last_block = (i_size_read(inode) - 1) >> inode->i_blkbits;
 	/* first map all the buffers, logging any direct items we find */
 	do {
@@ -2773,7 +2774,7 @@ static int reiserfs_write_begin(struct file *file,
 		*fsdata = (void *)(unsigned long)flags;
 	}
 
-	index = pos >> PAGE_CACHE_SHIFT;
+	index = pos >> PAGE_SHIFT;
 	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
 		return -ENOMEM;
@@ -2821,7 +2822,7 @@ static int reiserfs_write_begin(struct file *file,
 	}
 	if (ret) {
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 		/* Truncate allocated blocks */
 		reiserfs_truncate_failed_write(inode);
 	}
@@ -2908,7 +2909,7 @@ static int reiserfs_write_end(struct file *file, struct address_space *mapping,
 	else
 		th = NULL;
 
-	start = pos & (PAGE_CACHE_SIZE - 1);
+	start = pos & (PAGE_SIZE - 1);
 	if (unlikely(copied < len)) {
 		if (!PageUptodate(page))
 			copied = 0;
@@ -2973,7 +2974,7 @@ out:
 	if (locked)
 		reiserfs_write_unlock(inode->i_sb);
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 
 	if (pos + len > inode->i_size)
 		reiserfs_truncate_failed_write(inode);
@@ -2995,7 +2996,7 @@ int reiserfs_commit_write(struct file *f, struct page *page,
 			  unsigned from, unsigned to)
 {
 	struct inode *inode = page->mapping->host;
-	loff_t pos = ((loff_t) page->index << PAGE_CACHE_SHIFT) + to;
+	loff_t pos = ((loff_t) page->index << PAGE_SHIFT) + to;
 	int ret = 0;
 	int update_sd = 0;
 	struct reiserfs_transaction_handle *th = NULL;
@@ -3180,7 +3181,7 @@ static void reiserfs_invalidatepage(struct page *page, unsigned int offset,
 	struct inode *inode = page->mapping->host;
 	unsigned int curr_off = 0;
 	unsigned int stop = offset + length;
-	int partial_page = (offset || length < PAGE_CACHE_SIZE);
+	int partial_page = (offset || length < PAGE_SIZE);
 	int ret = 1;
 
 	BUG_ON(!PageLocked(page));
diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c
index 6ec8a30a0911..57045f423893 100644
--- a/fs/reiserfs/ioctl.c
+++ b/fs/reiserfs/ioctl.c
@@ -203,7 +203,7 @@ int reiserfs_unpack(struct inode *inode, struct file *filp)
 	 * __reiserfs_write_begin on that page.  This will force a
 	 * reiserfs_get_block to unpack the tail for us.
 	 */
-	index = inode->i_size >> PAGE_CACHE_SHIFT;
+	index = inode->i_size >> PAGE_SHIFT;
 	mapping = inode->i_mapping;
 	page = grab_cache_page(mapping, index);
 	retval = -ENOMEM;
@@ -221,10 +221,10 @@ int reiserfs_unpack(struct inode *inode, struct file *filp)
 
 out_unlock:
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	reiserfs_write_unlock(inode->i_sb);
 	return retval;
 }
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 9d6486d416a3..2ace90e981f0 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -599,18 +599,18 @@ static int journal_list_still_alive(struct super_block *s,
  * This does a check to see if the buffer belongs to one of these
  * lost pages before doing the final put_bh.  If page->mapping was
  * null, it tries to free buffers on the page, which should make the
- * final page_cache_release drop the page from the lru.
+ * final put_page drop the page from the lru.
  */
 static void release_buffer_page(struct buffer_head *bh)
 {
 	struct page *page = bh->b_page;
 	if (!page->mapping && trylock_page(page)) {
-		page_cache_get(page);
+		get_page(page);
 		put_bh(bh);
 		if (!page->mapping)
 			try_to_free_buffers(page);
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 	} else {
 		put_bh(bh);
 	}
@@ -618,12 +618,10 @@ static void release_buffer_page(struct buffer_head *bh)
 
 static void reiserfs_end_buffer_io_sync(struct buffer_head *bh, int uptodate)
 {
-	char b[BDEVNAME_SIZE];
-
 	if (buffer_journaled(bh)) {
 		reiserfs_warning(NULL, "clm-2084",
-				 "pinned buffer %lu:%s sent to disk",
-				 bh->b_blocknr, bdevname(bh->b_bdev, b));
+				 "pinned buffer %lu:%pg sent to disk",
+				 bh->b_blocknr, bh->b_bdev);
 	}
 	if (uptodate)
 		set_buffer_uptodate(bh);
@@ -2387,11 +2385,10 @@ static int journal_read(struct super_block *sb)
 	int replay_count = 0;
 	int continue_replay = 1;
 	int ret;
-	char b[BDEVNAME_SIZE];
 
 	cur_dblock = SB_ONDISK_JOURNAL_1st_BLOCK(sb);
-	reiserfs_info(sb, "checking transaction log (%s)\n",
-		      bdevname(journal->j_dev_bd, b));
+	reiserfs_info(sb, "checking transaction log (%pg)\n",
+		      journal->j_dev_bd);
 	start = get_seconds();
 
 	/*
@@ -2651,8 +2648,8 @@ static int journal_init_dev(struct super_block *super,
 
 	set_blocksize(journal->j_dev_bd, super->s_blocksize);
 	reiserfs_info(super,
-		      "journal_init_dev: journal device: %s\n",
-		      bdevname(journal->j_dev_bd, b));
+		      "journal_init_dev: journal device: %pg\n",
+		      journal->j_dev_bd);
 	return 0;
 }
 
@@ -2724,7 +2721,6 @@ int journal_init(struct super_block *sb, const char *j_dev_name,
 	struct reiserfs_journal_header *jh;
 	struct reiserfs_journal *journal;
 	struct reiserfs_journal_list *jl;
-	char b[BDEVNAME_SIZE];
 	int ret;
 
 	journal = SB_JOURNAL(sb) = vzalloc(sizeof(struct reiserfs_journal));
@@ -2794,10 +2790,10 @@ int journal_init(struct super_block *sb, const char *j_dev_name,
 	    && (le32_to_cpu(jh->jh_journal.jp_journal_magic) !=
 		sb_jp_journal_magic(rs))) {
 		reiserfs_warning(sb, "sh-460",
-				 "journal header magic %x (device %s) does "
+				 "journal header magic %x (device %pg) does "
 				 "not match to magic found in super block %x",
 				 jh->jh_journal.jp_journal_magic,
-				 bdevname(journal->j_dev_bd, b),
+				 journal->j_dev_bd,
 				 sb_jp_journal_magic(rs));
 		brelse(bhjh);
 		goto free_and_return;
@@ -2818,10 +2814,10 @@ int journal_init(struct super_block *sb, const char *j_dev_name,
 		journal->j_max_trans_age = commit_max_age;
 	}
 
-	reiserfs_info(sb, "journal params: device %s, size %u, "
+	reiserfs_info(sb, "journal params: device %pg, size %u, "
 		      "journal first block %u, max trans len %u, max batch %u, "
 		      "max commit age %u, max trans age %u\n",
-		      bdevname(journal->j_dev_bd, b),
+		      journal->j_dev_bd,
 		      SB_ONDISK_JOURNAL_SIZE(sb),
 		      SB_ONDISK_JOURNAL_1st_BLOCK(sb),
 		      journal->j_trans_max,
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index 5f1c9c29eb8c..2a12d46d7fb4 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -712,9 +712,6 @@ static int reiserfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode
 	    2 * (REISERFS_QUOTA_INIT_BLOCKS(dir->i_sb) +
 		 REISERFS_QUOTA_TRANS_BLOCKS(dir->i_sb));
 
-	if (!new_valid_dev(rdev))
-		return -EINVAL;
-
 	retval = dquot_initialize(dir);
 	if (retval)
 		return retval;
@@ -1173,6 +1170,7 @@ static int reiserfs_symlink(struct inode *parent_dir,
 	reiserfs_update_inode_transaction(parent_dir);
 
 	inode->i_op = &reiserfs_symlink_inode_operations;
+	inode_nohighmem(inode);
 	inode->i_mapping->a_ops = &reiserfs_address_space_operations;
 
 	retval = reiserfs_add_entry(&th, parent_dir, dentry->d_name.name,
@@ -1667,8 +1665,7 @@ const struct inode_operations reiserfs_dir_inode_operations = {
  */
 const struct inode_operations reiserfs_symlink_inode_operations = {
 	.readlink = generic_readlink,
-	.follow_link = page_follow_link_light,
-	.put_link = page_put_link,
+	.get_link	= page_get_link,
 	.setattr = reiserfs_setattr,
 	.setxattr = reiserfs_setxattr,
 	.getxattr = reiserfs_getxattr,
diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c
index ae1dc841db3a..4f3f928076f3 100644
--- a/fs/reiserfs/prints.c
+++ b/fs/reiserfs/prints.c
@@ -139,11 +139,9 @@ static void sprintf_block_head(char *buf, struct buffer_head *bh)
 
 static void sprintf_buffer_head(char *buf, struct buffer_head *bh)
 {
-	char b[BDEVNAME_SIZE];
-
 	sprintf(buf,
-		"dev %s, size %zd, blocknr %llu, count %d, state 0x%lx, page %p, (%s, %s, %s)",
-		bdevname(bh->b_bdev, b), bh->b_size,
+		"dev %pg, size %zd, blocknr %llu, count %d, state 0x%lx, page %p, (%s, %s, %s)",
+		bh->b_bdev, bh->b_size,
 		(unsigned long long)bh->b_blocknr, atomic_read(&(bh->b_count)),
 		bh->b_state, bh->b_page,
 		buffer_uptodate(bh) ? "UPTODATE" : "!UPTODATE",
@@ -530,7 +528,6 @@ static int print_super_block(struct buffer_head *bh)
 	    (struct reiserfs_super_block *)(bh->b_data);
 	int skipped, data_blocks;
 	char *version;
-	char b[BDEVNAME_SIZE];
 
 	if (is_reiserfs_3_5(rs)) {
 		version = "3.5";
@@ -543,7 +540,7 @@ static int print_super_block(struct buffer_head *bh)
 		return 1;
 	}
 
-	printk("%s\'s super block is in block %llu\n", bdevname(bh->b_bdev, b),
+	printk("%pg\'s super block is in block %llu\n", bh->b_bdev,
 	       (unsigned long long)bh->b_blocknr);
 	printk("Reiserfs version %s\n", version);
 	printk("Block count %u\n", sb_block_count(rs));
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index 621b9f381fe1..fe999157dd97 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -303,11 +303,10 @@ static int show_journal(struct seq_file *m, void *unused)
 	struct reiserfs_sb_info *r = REISERFS_SB(sb);
 	struct reiserfs_super_block *rs = r->s_rs;
 	struct journal_params *jp = &rs->s_v1.s_journal;
-	char b[BDEVNAME_SIZE];
 
 	seq_printf(m,		/* on-disk fields */
 		   "jp_journal_1st_block: \t%i\n"
-		   "jp_journal_dev: \t%s[%x]\n"
+		   "jp_journal_dev: \t%pg[%x]\n"
 		   "jp_journal_size: \t%i\n"
 		   "jp_journal_trans_max: \t%i\n"
 		   "jp_journal_magic: \t%i\n"
@@ -348,7 +347,7 @@ static int show_journal(struct seq_file *m, void *unused)
 		   "prepare: \t%12lu\n"
 		   "prepare_retry: \t%12lu\n",
 		   DJP(jp_journal_1st_block),
-		   bdevname(SB_JOURNAL(sb)->j_dev_bd, b),
+		   SB_JOURNAL(sb)->j_dev_bd,
 		   DJP(jp_journal_dev),
 		   DJP(jp_journal_size),
 		   DJP(jp_journal_trans_max),
diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c
index 24cbe013240f..5feacd689241 100644
--- a/fs/reiserfs/stree.c
+++ b/fs/reiserfs/stree.c
@@ -1342,7 +1342,7 @@ int reiserfs_delete_item(struct reiserfs_transaction_handle *th,
 		 */
 
 		data = kmap_atomic(un_bh->b_page);
-		off = ((le_ih_k_offset(&s_ih) - 1) & (PAGE_CACHE_SIZE - 1));
+		off = ((le_ih_k_offset(&s_ih) - 1) & (PAGE_SIZE - 1));
 		memcpy(data + off,
 		       ih_item_body(PATH_PLAST_BUFFER(path), &s_ih),
 		       ret_value);
@@ -1511,7 +1511,7 @@ static void unmap_buffers(struct page *page, loff_t pos)
 
 	if (page) {
 		if (page_has_buffers(page)) {
-			tail_index = pos & (PAGE_CACHE_SIZE - 1);
+			tail_index = pos & (PAGE_SIZE - 1);
 			cur_index = 0;
 			head = page_buffers(page);
 			bh = head;
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 4a62fe8cc3bf..b8f2d1e8c645 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -288,7 +288,7 @@ static int finish_unfinished(struct super_block *s)
 		pathrelse(&path);
 
 		inode = reiserfs_iget(s, &obj_key);
-		if (!inode) {
+		if (IS_ERR_OR_NULL(inode)) {
 			/*
 			 * the unlink almost completed, it just did not
 			 * manage to remove "save" link and release objectid
@@ -626,7 +626,8 @@ static int __init init_inodecache(void)
 						  sizeof(struct
 							 reiserfs_inode_info),
 						  0, (SLAB_RECLAIM_ACCOUNT|
-							SLAB_MEM_SPREAD),
+						      SLAB_MEM_SPREAD|
+						      SLAB_ACCOUNT),
 						  init_once);
 	if (reiserfs_inode_cachep == NULL)
 		return -ENOMEM;
@@ -801,6 +802,7 @@ static const struct dquot_operations reiserfs_quota_operations = {
 	.write_info = reiserfs_write_info,
 	.alloc_dquot	= dquot_alloc,
 	.destroy_dquot	= dquot_destroy,
+	.get_next_id	= dquot_get_next_id,
 };
 
 static const struct quotactl_ops reiserfs_qctl_operations = {
diff --git a/fs/reiserfs/tail_conversion.c b/fs/reiserfs/tail_conversion.c
index f41e19b4bb42..2d5489b0a269 100644
--- a/fs/reiserfs/tail_conversion.c
+++ b/fs/reiserfs/tail_conversion.c
@@ -151,7 +151,7 @@ int direct2indirect(struct reiserfs_transaction_handle *th, struct inode *inode,
 	 */
 	if (up_to_date_bh) {
 		unsigned pgoff =
-		    (tail_offset + total_tail - 1) & (PAGE_CACHE_SIZE - 1);
+		    (tail_offset + total_tail - 1) & (PAGE_SIZE - 1);
 		char *kaddr = kmap_atomic(up_to_date_bh->b_page);
 		memset(kaddr + pgoff, 0, blk_size - total_tail);
 		kunmap_atomic(kaddr);
@@ -271,7 +271,7 @@ int indirect2direct(struct reiserfs_transaction_handle *th,
 	 * the page was locked and this part of the page was up to date when
 	 * indirect2direct was called, so we know the bytes are still valid
 	 */
-	tail = tail + (pos & (PAGE_CACHE_SIZE - 1));
+	tail = tail + (pos & (PAGE_SIZE - 1));
 
 	PATH_LAST_POSITION(path)++;
 
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index e87f9b52bf06..28f5f8b11370 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -64,14 +64,14 @@
 #ifdef CONFIG_REISERFS_FS_XATTR
 static int xattr_create(struct inode *dir, struct dentry *dentry, int mode)
 {
-	BUG_ON(!mutex_is_locked(&dir->i_mutex));
+	BUG_ON(!inode_is_locked(dir));
 	return dir->i_op->create(dir, dentry, mode, true);
 }
 #endif
 
 static int xattr_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 {
-	BUG_ON(!mutex_is_locked(&dir->i_mutex));
+	BUG_ON(!inode_is_locked(dir));
 	return dir->i_op->mkdir(dir, dentry, mode);
 }
 
@@ -85,11 +85,11 @@ static int xattr_unlink(struct inode *dir, struct dentry *dentry)
 {
 	int error;
 
-	BUG_ON(!mutex_is_locked(&dir->i_mutex));
+	BUG_ON(!inode_is_locked(dir));
 
-	mutex_lock_nested(&d_inode(dentry)->i_mutex, I_MUTEX_CHILD);
+	inode_lock_nested(d_inode(dentry), I_MUTEX_CHILD);
 	error = dir->i_op->unlink(dir, dentry);
-	mutex_unlock(&d_inode(dentry)->i_mutex);
+	inode_unlock(d_inode(dentry));
 
 	if (!error)
 		d_delete(dentry);
@@ -100,13 +100,13 @@ static int xattr_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	int error;
 
-	BUG_ON(!mutex_is_locked(&dir->i_mutex));
+	BUG_ON(!inode_is_locked(dir));
 
-	mutex_lock_nested(&d_inode(dentry)->i_mutex, I_MUTEX_CHILD);
+	inode_lock_nested(d_inode(dentry), I_MUTEX_CHILD);
 	error = dir->i_op->rmdir(dir, dentry);
 	if (!error)
 		d_inode(dentry)->i_flags |= S_DEAD;
-	mutex_unlock(&d_inode(dentry)->i_mutex);
+	inode_unlock(d_inode(dentry));
 	if (!error)
 		d_delete(dentry);
 
@@ -123,7 +123,7 @@ static struct dentry *open_xa_root(struct super_block *sb, int flags)
 	if (d_really_is_negative(privroot))
 		return ERR_PTR(-ENODATA);
 
-	mutex_lock_nested(&d_inode(privroot)->i_mutex, I_MUTEX_XATTR);
+	inode_lock_nested(d_inode(privroot), I_MUTEX_XATTR);
 
 	xaroot = dget(REISERFS_SB(sb)->xattr_root);
 	if (!xaroot)
@@ -139,7 +139,7 @@ static struct dentry *open_xa_root(struct super_block *sb, int flags)
 		}
 	}
 
-	mutex_unlock(&d_inode(privroot)->i_mutex);
+	inode_unlock(d_inode(privroot));
 	return xaroot;
 }
 
@@ -156,7 +156,7 @@ static struct dentry *open_xa_dir(const struct inode *inode, int flags)
 		 le32_to_cpu(INODE_PKEY(inode)->k_objectid),
 		 inode->i_generation);
 
-	mutex_lock_nested(&d_inode(xaroot)->i_mutex, I_MUTEX_XATTR);
+	inode_lock_nested(d_inode(xaroot), I_MUTEX_XATTR);
 
 	xadir = lookup_one_len(namebuf, xaroot, strlen(namebuf));
 	if (!IS_ERR(xadir) && d_really_is_negative(xadir)) {
@@ -170,7 +170,7 @@ static struct dentry *open_xa_dir(const struct inode *inode, int flags)
 		}
 	}
 
-	mutex_unlock(&d_inode(xaroot)->i_mutex);
+	inode_unlock(d_inode(xaroot));
 	dput(xaroot);
 	return xadir;
 }
@@ -195,7 +195,7 @@ fill_with_dentries(struct dir_context *ctx, const char *name, int namelen,
 		container_of(ctx, struct reiserfs_dentry_buf, ctx);
 	struct dentry *dentry;
 
-	WARN_ON_ONCE(!mutex_is_locked(&d_inode(dbuf->xadir)->i_mutex));
+	WARN_ON_ONCE(!inode_is_locked(d_inode(dbuf->xadir)));
 
 	if (dbuf->count == ARRAY_SIZE(dbuf->dentries))
 		return -ENOSPC;
@@ -254,7 +254,7 @@ static int reiserfs_for_each_xattr(struct inode *inode,
 		goto out_dir;
 	}
 
-	mutex_lock_nested(&d_inode(dir)->i_mutex, I_MUTEX_XATTR);
+	inode_lock_nested(d_inode(dir), I_MUTEX_XATTR);
 
 	buf.xadir = dir;
 	while (1) {
@@ -276,7 +276,7 @@ static int reiserfs_for_each_xattr(struct inode *inode,
 			break;
 		buf.count = 0;
 	}
-	mutex_unlock(&d_inode(dir)->i_mutex);
+	inode_unlock(d_inode(dir));
 
 	cleanup_dentry_buf(&buf);
 
@@ -298,13 +298,13 @@ static int reiserfs_for_each_xattr(struct inode *inode,
 		if (!err) {
 			int jerror;
 
-			mutex_lock_nested(&d_inode(dir->d_parent)->i_mutex,
+			inode_lock_nested(d_inode(dir->d_parent),
 					  I_MUTEX_XATTR);
 			err = action(dir, data);
 			reiserfs_write_lock(inode->i_sb);
 			jerror = journal_end(&th);
 			reiserfs_write_unlock(inode->i_sb);
-			mutex_unlock(&d_inode(dir->d_parent)->i_mutex);
+			inode_unlock(d_inode(dir->d_parent));
 			err = jerror ?: err;
 		}
 	}
@@ -384,7 +384,7 @@ static struct dentry *xattr_lookup(struct inode *inode, const char *name,
 	if (IS_ERR(xadir))
 		return ERR_CAST(xadir);
 
-	mutex_lock_nested(&d_inode(xadir)->i_mutex, I_MUTEX_XATTR);
+	inode_lock_nested(d_inode(xadir), I_MUTEX_XATTR);
 	xafile = lookup_one_len(name, xadir, strlen(name));
 	if (IS_ERR(xafile)) {
 		err = PTR_ERR(xafile);
@@ -404,7 +404,7 @@ static struct dentry *xattr_lookup(struct inode *inode, const char *name,
 	if (err)
 		dput(xafile);
 out:
-	mutex_unlock(&d_inode(xadir)->i_mutex);
+	inode_unlock(d_inode(xadir));
 	dput(xadir);
 	if (err)
 		return ERR_PTR(err);
@@ -415,7 +415,7 @@ out:
 static inline void reiserfs_put_page(struct page *page)
 {
 	kunmap(page);
-	page_cache_release(page);
+	put_page(page);
 }
 
 static struct page *reiserfs_get_page(struct inode *dir, size_t n)
@@ -427,7 +427,7 @@ static struct page *reiserfs_get_page(struct inode *dir, size_t n)
 	 * and an unlink/rmdir has just occurred - GFP_NOFS avoids this
 	 */
 	mapping_set_gfp_mask(mapping, GFP_NOFS);
-	page = read_mapping_page(mapping, n >> PAGE_CACHE_SHIFT, NULL);
+	page = read_mapping_page(mapping, n >> PAGE_SHIFT, NULL);
 	if (!IS_ERR(page)) {
 		kmap(page);
 		if (PageError(page))
@@ -469,7 +469,7 @@ static int lookup_and_delete_xattr(struct inode *inode, const char *name)
 	if (IS_ERR(xadir))
 		return PTR_ERR(xadir);
 
-	mutex_lock_nested(&d_inode(xadir)->i_mutex, I_MUTEX_XATTR);
+	inode_lock_nested(d_inode(xadir), I_MUTEX_XATTR);
 	dentry = lookup_one_len(name, xadir, strlen(name));
 	if (IS_ERR(dentry)) {
 		err = PTR_ERR(dentry);
@@ -483,7 +483,7 @@ static int lookup_and_delete_xattr(struct inode *inode, const char *name)
 
 	dput(dentry);
 out_dput:
-	mutex_unlock(&d_inode(xadir)->i_mutex);
+	inode_unlock(d_inode(xadir));
 	dput(xadir);
 	return err;
 }
@@ -526,10 +526,10 @@ reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th,
 	while (buffer_pos < buffer_size || buffer_pos == 0) {
 		size_t chunk;
 		size_t skip = 0;
-		size_t page_offset = (file_pos & (PAGE_CACHE_SIZE - 1));
+		size_t page_offset = (file_pos & (PAGE_SIZE - 1));
 
-		if (buffer_size - buffer_pos > PAGE_CACHE_SIZE)
-			chunk = PAGE_CACHE_SIZE;
+		if (buffer_size - buffer_pos > PAGE_SIZE)
+			chunk = PAGE_SIZE;
 		else
 			chunk = buffer_size - buffer_pos;
 
@@ -546,8 +546,8 @@ reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th,
 			struct reiserfs_xattr_header *rxh;
 
 			skip = file_pos = sizeof(struct reiserfs_xattr_header);
-			if (chunk + skip > PAGE_CACHE_SIZE)
-				chunk = PAGE_CACHE_SIZE - skip;
+			if (chunk + skip > PAGE_SIZE)
+				chunk = PAGE_SIZE - skip;
 			rxh = (struct reiserfs_xattr_header *)data;
 			rxh->h_magic = cpu_to_le32(REISERFS_XATTR_MAGIC);
 			rxh->h_hash = cpu_to_le32(xahash);
@@ -580,11 +580,11 @@ reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th,
 			.ia_valid = ATTR_SIZE | ATTR_CTIME,
 		};
 
-		mutex_lock_nested(&d_inode(dentry)->i_mutex, I_MUTEX_XATTR);
+		inode_lock_nested(d_inode(dentry), I_MUTEX_XATTR);
 		inode_dio_wait(d_inode(dentry));
 
 		err = reiserfs_setattr(dentry, &newattrs);
-		mutex_unlock(&d_inode(dentry)->i_mutex);
+		inode_unlock(d_inode(dentry));
 	} else
 		update_ctime(inode);
 out_unlock:
@@ -675,8 +675,8 @@ reiserfs_xattr_get(struct inode *inode, const char *name, void *buffer,
 		char *data;
 		size_t skip = 0;
 
-		if (isize - file_pos > PAGE_CACHE_SIZE)
-			chunk = PAGE_CACHE_SIZE;
+		if (isize - file_pos > PAGE_SIZE)
+			chunk = PAGE_SIZE;
 		else
 			chunk = isize - file_pos;
 
@@ -756,7 +756,8 @@ find_xattr_handler_prefix(const struct xattr_handler **handlers,
 		return NULL;
 
 	for_each_xattr_handler(handlers, xah) {
-		if (strncmp(xah->prefix, name, strlen(xah->prefix)) == 0)
+		const char *prefix = xattr_prefix(xah);
+		if (strncmp(prefix, name, strlen(prefix)) == 0)
 			break;
 	}
 
@@ -778,7 +779,7 @@ reiserfs_getxattr(struct dentry * dentry, const char *name, void *buffer,
 	if (!handler || get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1)
 		return -EOPNOTSUPP;
 
-	return handler->get(dentry, name, buffer, size, handler->flags);
+	return handler->get(handler, dentry, name, buffer, size);
 }
 
 /*
@@ -797,7 +798,7 @@ reiserfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 	if (!handler || get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1)
 		return -EOPNOTSUPP;
 
-	return handler->set(dentry, name, value, size, flags, handler->flags);
+	return handler->set(handler, dentry, name, value, size, flags);
 }
 
 /*
@@ -814,7 +815,7 @@ int reiserfs_removexattr(struct dentry *dentry, const char *name)
 	if (!handler || get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1)
 		return -EOPNOTSUPP;
 
-	return handler->set(dentry, name, NULL, 0, XATTR_REPLACE, handler->flags);
+	return handler->set(handler, dentry, name, NULL, 0, XATTR_REPLACE);
 }
 
 struct listxattr_buf {
@@ -839,19 +840,16 @@ static int listxattr_filler(struct dir_context *ctx, const char *name,
 
 		handler = find_xattr_handler_prefix(b->dentry->d_sb->s_xattr,
 						    name);
-		if (!handler)	/* Unsupported xattr name */
+		if (!handler /* Unsupported xattr name */ ||
+		    (handler->list && !handler->list(b->dentry)))
 			return 0;
+		size = namelen + 1;
 		if (b->buf) {
-			size = handler->list(b->dentry, b->buf + b->pos,
-					 b->size, name, namelen,
-					 handler->flags);
 			if (size > b->size)
 				return -ERANGE;
-		} else {
-			size = handler->list(b->dentry, NULL, 0, name,
-					     namelen, handler->flags);
+			memcpy(b->buf + b->pos, name, namelen);
+			b->buf[b->pos + namelen] = 0;
 		}
-
 		b->pos += size;
 	}
 	return 0;
@@ -890,9 +888,9 @@ ssize_t reiserfs_listxattr(struct dentry * dentry, char *buffer, size_t size)
 		goto out;
 	}
 
-	mutex_lock_nested(&d_inode(dir)->i_mutex, I_MUTEX_XATTR);
+	inode_lock_nested(d_inode(dir), I_MUTEX_XATTR);
 	err = reiserfs_readdir_inode(d_inode(dir), &buf.ctx);
-	mutex_unlock(&d_inode(dir)->i_mutex);
+	inode_unlock(d_inode(dir));
 
 	if (!err)
 		err = buf.pos;
@@ -907,7 +905,7 @@ static int create_privroot(struct dentry *dentry)
 	int err;
 	struct inode *inode = d_inode(dentry->d_parent);
 
-	WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex));
+	WARN_ON_ONCE(!inode_is_locked(inode));
 
 	err = xattr_mkdir(inode, dentry, 0700);
 	if (err || d_really_is_negative(dentry)) {
@@ -997,7 +995,7 @@ int reiserfs_lookup_privroot(struct super_block *s)
 	int err = 0;
 
 	/* If we don't have the privroot located yet - go find it */
-	mutex_lock(&d_inode(s->s_root)->i_mutex);
+	inode_lock(d_inode(s->s_root));
 	dentry = lookup_one_len(PRIVROOT_NAME, s->s_root,
 				strlen(PRIVROOT_NAME));
 	if (!IS_ERR(dentry)) {
@@ -1007,7 +1005,7 @@ int reiserfs_lookup_privroot(struct super_block *s)
 			d_inode(dentry)->i_flags |= S_PRIVATE;
 	} else
 		err = PTR_ERR(dentry);
-	mutex_unlock(&d_inode(s->s_root)->i_mutex);
+	inode_unlock(d_inode(s->s_root));
 
 	return err;
 }
@@ -1027,14 +1025,14 @@ int reiserfs_xattr_init(struct super_block *s, int mount_flags)
 		goto error;
 
 	if (d_really_is_negative(privroot) && !(mount_flags & MS_RDONLY)) {
-		mutex_lock(&d_inode(s->s_root)->i_mutex);
+		inode_lock(d_inode(s->s_root));
 		err = create_privroot(REISERFS_SB(s)->priv_root);
-		mutex_unlock(&d_inode(s->s_root)->i_mutex);
+		inode_unlock(d_inode(s->s_root));
 	}
 
 	if (d_really_is_positive(privroot)) {
 		s->s_xattr = reiserfs_xattr_handlers;
-		mutex_lock(&d_inode(privroot)->i_mutex);
+		inode_lock(d_inode(privroot));
 		if (!REISERFS_SB(s)->xattr_root) {
 			struct dentry *dentry;
 
@@ -1045,7 +1043,7 @@ int reiserfs_xattr_init(struct super_block *s, int mount_flags)
 			else
 				err = PTR_ERR(dentry);
 		}
-		mutex_unlock(&d_inode(privroot)->i_mutex);
+		inode_unlock(d_inode(privroot));
 	}
 
 error:
diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c
index 4b34b9dc03dd..558a16beaacb 100644
--- a/fs/reiserfs/xattr_acl.c
+++ b/fs/reiserfs/xattr_acl.c
@@ -186,10 +186,10 @@ struct posix_acl *reiserfs_get_acl(struct inode *inode, int type)
 
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		name = POSIX_ACL_XATTR_ACCESS;
+		name = XATTR_NAME_POSIX_ACL_ACCESS;
 		break;
 	case ACL_TYPE_DEFAULT:
-		name = POSIX_ACL_XATTR_DEFAULT;
+		name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		break;
 	default:
 		BUG();
@@ -244,7 +244,7 @@ __reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode,
 
 	switch (type) {
 	case ACL_TYPE_ACCESS:
-		name = POSIX_ACL_XATTR_ACCESS;
+		name = XATTR_NAME_POSIX_ACL_ACCESS;
 		if (acl) {
 			error = posix_acl_equiv_mode(acl, &inode->i_mode);
 			if (error < 0)
@@ -256,7 +256,7 @@ __reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode,
 		}
 		break;
 	case ACL_TYPE_DEFAULT:
-		name = POSIX_ACL_XATTR_DEFAULT;
+		name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		if (!S_ISDIR(inode->i_mode))
 			return acl ? -EACCES : 0;
 		break;
diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c
index 9a3b0616f283..ab0217d32039 100644
--- a/fs/reiserfs/xattr_security.c
+++ b/fs/reiserfs/xattr_security.c
@@ -9,8 +9,8 @@
 #include <linux/uaccess.h>
 
 static int
-security_get(struct dentry *dentry, const char *name, void *buffer, size_t size,
-		int handler_flags)
+security_get(const struct xattr_handler *handler, struct dentry *dentry,
+	     const char *name, void *buffer, size_t size)
 {
 	if (strlen(name) < sizeof(XATTR_SECURITY_PREFIX))
 		return -EINVAL;
@@ -22,8 +22,8 @@ security_get(struct dentry *dentry, const char *name, void *buffer, size_t size,
 }
 
 static int
-security_set(struct dentry *dentry, const char *name, const void *buffer,
-	     size_t size, int flags, int handler_flags)
+security_set(const struct xattr_handler *handler, struct dentry *dentry,
+	     const char *name, const void *buffer, size_t size, int flags)
 {
 	if (strlen(name) < sizeof(XATTR_SECURITY_PREFIX))
 		return -EINVAL;
@@ -34,20 +34,9 @@ security_set(struct dentry *dentry, const char *name, const void *buffer,
 	return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags);
 }
 
-static size_t security_list(struct dentry *dentry, char *list, size_t list_len,
-			    const char *name, size_t namelen, int handler_flags)
+static bool security_list(struct dentry *dentry)
 {
-	const size_t len = namelen + 1;
-
-	if (IS_PRIVATE(d_inode(dentry)))
-		return 0;
-
-	if (list && len <= list_len) {
-		memcpy(list, name, namelen);
-		list[namelen] = '\0';
-	}
-
-	return len;
+	return !IS_PRIVATE(d_inode(dentry));
 }
 
 /* Initializes the security context for a new inode and returns the number
diff --git a/fs/reiserfs/xattr_trusted.c b/fs/reiserfs/xattr_trusted.c
index e4f1343714e0..64b67aa643a9 100644
--- a/fs/reiserfs/xattr_trusted.c
+++ b/fs/reiserfs/xattr_trusted.c
@@ -8,8 +8,8 @@
 #include <linux/uaccess.h>
 
 static int
-trusted_get(struct dentry *dentry, const char *name, void *buffer, size_t size,
-	    int handler_flags)
+trusted_get(const struct xattr_handler *handler, struct dentry *dentry,
+	    const char *name, void *buffer, size_t size)
 {
 	if (strlen(name) < sizeof(XATTR_TRUSTED_PREFIX))
 		return -EINVAL;
@@ -21,8 +21,8 @@ trusted_get(struct dentry *dentry, const char *name, void *buffer, size_t size,
 }
 
 static int
-trusted_set(struct dentry *dentry, const char *name, const void *buffer,
-	    size_t size, int flags, int handler_flags)
+trusted_set(const struct xattr_handler *handler, struct dentry *dentry,
+	    const char *name, const void *buffer, size_t size, int flags)
 {
 	if (strlen(name) < sizeof(XATTR_TRUSTED_PREFIX))
 		return -EINVAL;
@@ -33,19 +33,9 @@ trusted_set(struct dentry *dentry, const char *name, const void *buffer,
 	return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags);
 }
 
-static size_t trusted_list(struct dentry *dentry, char *list, size_t list_size,
-			   const char *name, size_t name_len, int handler_flags)
+static bool trusted_list(struct dentry *dentry)
 {
-	const size_t len = name_len + 1;
-
-	if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(d_inode(dentry)))
-		return 0;
-
-	if (list && len <= list_size) {
-		memcpy(list, name, name_len);
-		list[name_len] = '\0';
-	}
-	return len;
+	return capable(CAP_SYS_ADMIN) && !IS_PRIVATE(d_inode(dentry));
 }
 
 const struct xattr_handler reiserfs_xattr_trusted_handler = {
diff --git a/fs/reiserfs/xattr_user.c b/fs/reiserfs/xattr_user.c
index d0b08d3e5689..12e6306f562a 100644
--- a/fs/reiserfs/xattr_user.c
+++ b/fs/reiserfs/xattr_user.c
@@ -7,8 +7,8 @@
 #include <linux/uaccess.h>
 
 static int
-user_get(struct dentry *dentry, const char *name, void *buffer, size_t size,
-	 int handler_flags)
+user_get(const struct xattr_handler *handler, struct dentry *dentry,
+	 const char *name, void *buffer, size_t size)
 {
 
 	if (strlen(name) < sizeof(XATTR_USER_PREFIX))
@@ -19,8 +19,8 @@ user_get(struct dentry *dentry, const char *name, void *buffer, size_t size,
 }
 
 static int
-user_set(struct dentry *dentry, const char *name, const void *buffer,
-	 size_t size, int flags, int handler_flags)
+user_set(const struct xattr_handler *handler, struct dentry *dentry,
+	 const char *name, const void *buffer, size_t size, int flags)
 {
 	if (strlen(name) < sizeof(XATTR_USER_PREFIX))
 		return -EINVAL;
@@ -30,18 +30,9 @@ user_set(struct dentry *dentry, const char *name, const void *buffer,
 	return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags);
 }
 
-static size_t user_list(struct dentry *dentry, char *list, size_t list_size,
-			const char *name, size_t name_len, int handler_flags)
+static bool user_list(struct dentry *dentry)
 {
-	const size_t len = name_len + 1;
-
-	if (!reiserfs_xattrs_user(dentry->d_sb))
-		return 0;
-	if (list && len <= list_size) {
-		memcpy(list, name, name_len);
-		list[name_len] = '\0';
-	}
-	return len;
+	return reiserfs_xattrs_user(dentry->d_sb);
 }
 
 const struct xattr_handler reiserfs_xattr_user_handler = {
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index 268733cda397..6b00ca357c58 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -360,6 +360,7 @@ static struct inode *romfs_iget(struct super_block *sb, unsigned long pos)
 		break;
 	case ROMFH_SYM:
 		i->i_op = &page_symlink_inode_operations;
+		inode_nohighmem(i);
 		i->i_data.a_ops = &romfs_aops;
 		mode |= S_IRWXUGO;
 		break;
@@ -618,8 +619,8 @@ static int __init init_romfs_fs(void)
 	romfs_inode_cachep =
 		kmem_cache_create("romfs_i",
 				  sizeof(struct romfs_inode_info), 0,
-				  SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD,
-				  romfs_i_init_once);
+				  SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD |
+				  SLAB_ACCOUNT, romfs_i_init_once);
 
 	if (!romfs_inode_cachep) {
 		pr_err("Failed to initialise inode cache\n");
diff --git a/fs/select.c b/fs/select.c
index 015547330e88..869293988c2a 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -70,9 +70,9 @@ static long __estimate_accuracy(struct timespec *tv)
 	return slack;
 }
 
-long select_estimate_accuracy(struct timespec *tv)
+u64 select_estimate_accuracy(struct timespec *tv)
 {
-	unsigned long ret;
+	u64 ret;
 	struct timespec now;
 
 	/*
@@ -402,7 +402,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
 	struct poll_wqueues table;
 	poll_table *wait;
 	int retval, i, timed_out = 0;
-	unsigned long slack = 0;
+	u64 slack = 0;
 	unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
 	unsigned long busy_end = 0;
 
@@ -778,13 +778,13 @@ static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait,
 	return mask;
 }
 
-static int do_poll(unsigned int nfds,  struct poll_list *list,
-		   struct poll_wqueues *wait, struct timespec *end_time)
+static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
+		   struct timespec *end_time)
 {
 	poll_table* pt = &wait->pt;
 	ktime_t expire, *to = NULL;
 	int timed_out = 0, count = 0;
-	unsigned long slack = 0;
+	u64 slack = 0;
 	unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
 	unsigned long busy_end = 0;
 
@@ -908,7 +908,7 @@ int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
 	}
 
 	poll_initwait(&table);
-	fdcount = do_poll(nfds, head, &table, end_time);
+	fdcount = do_poll(head, &table, end_time);
 	poll_freewait(&table);
 
 	for (walk = head; walk; walk = walk->next) {
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 225586e141ca..19f532e7d35e 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -13,6 +13,7 @@
 #include <linux/cred.h>
 #include <linux/mm.h>
 #include <linux/printk.h>
+#include <linux/string_helpers.h>
 
 #include <asm/uaccess.h>
 #include <asm/page.h>
@@ -25,12 +26,17 @@ static void seq_set_overflow(struct seq_file *m)
 static void *seq_buf_alloc(unsigned long size)
 {
 	void *buf;
+	gfp_t gfp = GFP_KERNEL;
 
 	/*
-	 * __GFP_NORETRY to avoid oom-killings with high-order allocations -
-	 * it's better to fall back to vmalloc() than to kill things.
+	 * For high order allocations, use __GFP_NORETRY to avoid oom-killing -
+	 * it's better to fall back to vmalloc() than to kill things.  For small
+	 * allocations, just use GFP_KERNEL which will oom kill, thus no need
+	 * for vmalloc fallback.
 	 */
-	buf = kmalloc(size, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
+	if (size > PAGE_SIZE)
+		gfp |= __GFP_NORETRY | __GFP_NOWARN;
+	buf = kmalloc(size, gfp);
 	if (!buf && size > PAGE_SIZE)
 		buf = vmalloc(size);
 	return buf;
@@ -66,9 +72,10 @@ int seq_open(struct file *file, const struct seq_operations *op)
 
 	mutex_init(&p->lock);
 	p->op = op;
-#ifdef CONFIG_USER_NS
-	p->user_ns = file->f_cred->user_ns;
-#endif
+
+	// No refcounting: the lifetime of 'p' is constrained
+	// to the lifetime of the file.
+	p->file = file;
 
 	/*
 	 * Wrappers around seq_open(e.g. swaps_open) need to be
@@ -377,26 +384,12 @@ EXPORT_SYMBOL(seq_release);
  */
 void seq_escape(struct seq_file *m, const char *s, const char *esc)
 {
-	char *end = m->buf + m->size;
-	char *p;
-	char c;
+	char *buf;
+	size_t size = seq_get_buf(m, &buf);
+	int ret;
 
-	for (p = m->buf + m->count; (c = *s) != '\0' && p < end; s++) {
-		if (!strchr(esc, c)) {
-			*p++ = c;
-			continue;
-		}
-		if (p + 3 < end) {
-			*p++ = '\\';
-			*p++ = '0' + ((c & 0300) >> 6);
-			*p++ = '0' + ((c & 070) >> 3);
-			*p++ = '0' + (c & 07);
-			continue;
-		}
-		seq_set_overflow(m);
-		return;
-	}
-	m->count = p - m->buf;
+	ret = string_escape_str(s, buf, size, ESCAPE_OCTAL, esc);
+	seq_commit(m, ret < size ? ret : -1);
 }
 EXPORT_SYMBOL(seq_escape);
 
@@ -773,6 +766,8 @@ void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type,
 {
 	const u8 *ptr = buf;
 	int i, linelen, remaining = len;
+	char *buffer;
+	size_t size;
 	int ret;
 
 	if (rowsize != 16 && rowsize != 32)
@@ -794,15 +789,12 @@ void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type,
 			break;
 		}
 
+		size = seq_get_buf(m, &buffer);
 		ret = hex_dump_to_buffer(ptr + i, linelen, rowsize, groupsize,
-					 m->buf + m->count, m->size - m->count,
-					 ascii);
-		if (ret >= m->size - m->count) {
-			seq_set_overflow(m);
-		} else {
-			m->count += ret;
-			seq_putc(m, '\n');
-		}
+					 buffer, size, ascii);
+		seq_commit(m, ret < size ? ret : -1);
+
+		seq_putc(m, '\n');
 	}
 }
 EXPORT_SYMBOL(seq_hex_dump);
diff --git a/fs/splice.c b/fs/splice.c
index 5fc1e50a7f30..b018eb485019 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -88,7 +88,7 @@ out_unlock:
 static void page_cache_pipe_buf_release(struct pipe_inode_info *pipe,
 					struct pipe_buffer *buf)
 {
-	page_cache_release(buf->page);
+	put_page(buf->page);
 	buf->flags &= ~PIPE_BUF_FLAG_LRU;
 }
 
@@ -185,6 +185,9 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
 	unsigned int spd_pages = spd->nr_pages;
 	int ret, do_wakeup, page_nr;
 
+	if (!spd_pages)
+		return 0;
+
 	ret = 0;
 	do_wakeup = 0;
 	page_nr = 0;
@@ -265,7 +268,7 @@ EXPORT_SYMBOL_GPL(splice_to_pipe);
 
 void spd_release_page(struct splice_pipe_desc *spd, unsigned int i)
 {
-	page_cache_release(spd->pages[i]);
+	put_page(spd->pages[i]);
 }
 
 /*
@@ -325,9 +328,9 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
 	if (splice_grow_spd(pipe, &spd))
 		return -ENOMEM;
 
-	index = *ppos >> PAGE_CACHE_SHIFT;
-	loff = *ppos & ~PAGE_CACHE_MASK;
-	req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	index = *ppos >> PAGE_SHIFT;
+	loff = *ppos & ~PAGE_MASK;
+	req_pages = (len + loff + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	nr_pages = min(req_pages, spd.nr_pages_max);
 
 	/*
@@ -360,9 +363,9 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
 				break;
 
 			error = add_to_page_cache_lru(page, mapping, index,
-					GFP_KERNEL & mapping_gfp_mask(mapping));
+				   mapping_gfp_constraint(mapping, GFP_KERNEL));
 			if (unlikely(error)) {
-				page_cache_release(page);
+				put_page(page);
 				if (error == -EEXIST)
 					continue;
 				break;
@@ -382,7 +385,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
 	 * Now loop over the map and see if we need to start IO on any
 	 * pages, fill in the partial map, etc.
 	 */
-	index = *ppos >> PAGE_CACHE_SHIFT;
+	index = *ppos >> PAGE_SHIFT;
 	nr_pages = spd.nr_pages;
 	spd.nr_pages = 0;
 	for (page_nr = 0; page_nr < nr_pages; page_nr++) {
@@ -394,7 +397,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
 		/*
 		 * this_len is the max we'll use from this page
 		 */
-		this_len = min_t(unsigned long, len, PAGE_CACHE_SIZE - loff);
+		this_len = min_t(unsigned long, len, PAGE_SIZE - loff);
 		page = spd.pages[page_nr];
 
 		if (PageReadahead(page))
@@ -415,6 +418,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
 			 */
 			if (!page->mapping) {
 				unlock_page(page);
+retry_lookup:
 				page = find_or_create_page(mapping, index,
 						mapping_gfp_mask(mapping));
 
@@ -422,7 +426,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
 					error = -ENOMEM;
 					break;
 				}
-				page_cache_release(spd.pages[page_nr]);
+				put_page(spd.pages[page_nr]);
 				spd.pages[page_nr] = page;
 			}
 			/*
@@ -439,13 +443,10 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
 			error = mapping->a_ops->readpage(in, page);
 			if (unlikely(error)) {
 				/*
-				 * We really should re-lookup the page here,
-				 * but it complicates things a lot. Instead
-				 * lets just do what we already stored, and
-				 * we'll get it the next time we are called.
+				 * Re-lookup the page
 				 */
 				if (error == AOP_TRUNCATED_PAGE)
-					error = 0;
+					goto retry_lookup;
 
 				break;
 			}
@@ -455,7 +456,7 @@ fill_it:
 		 * i_size must be checked after PageUptodate.
 		 */
 		isize = i_size_read(mapping->host);
-		end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
+		end_index = (isize - 1) >> PAGE_SHIFT;
 		if (unlikely(!isize || index > end_index))
 			break;
 
@@ -469,7 +470,7 @@ fill_it:
 			/*
 			 * max good bytes in this page
 			 */
-			plen = ((isize - 1) & ~PAGE_CACHE_MASK) + 1;
+			plen = ((isize - 1) & ~PAGE_MASK) + 1;
 			if (plen <= loff)
 				break;
 
@@ -493,8 +494,8 @@ fill_it:
 	 * we got, 'nr_pages' is how many pages are in the map.
 	 */
 	while (page_nr < nr_pages)
-		page_cache_release(spd.pages[page_nr++]);
-	in->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT;
+		put_page(spd.pages[page_nr++]);
+	in->f_ra.prev_pos = (loff_t)index << PAGE_SHIFT;
 
 	if (spd.nr_pages)
 		error = splice_to_pipe(pipe, &spd);
@@ -579,7 +580,7 @@ static ssize_t kernel_readv(struct file *file, const struct iovec *vec,
 	old_fs = get_fs();
 	set_fs(get_ds());
 	/* The cast to a user pointer is valid due to the set_fs() */
-	res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos);
+	res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos, 0);
 	set_fs(old_fs);
 
 	return res;
@@ -635,8 +636,8 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
 			goto shrink_ret;
 	}
 
-	offset = *ppos & ~PAGE_CACHE_MASK;
-	nr_pages = (len + offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	offset = *ppos & ~PAGE_MASK;
+	nr_pages = (len + offset + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
 	for (i = 0; i < nr_pages && i < spd.nr_pages_max && len; i++) {
 		struct page *page;
@@ -646,7 +647,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
 		if (!page)
 			goto err;
 
-		this_len = min_t(size_t, len, PAGE_CACHE_SIZE - offset);
+		this_len = min_t(size_t, len, PAGE_SIZE - offset);
 		vec[i].iov_base = (void __user *) page_address(page);
 		vec[i].iov_len = this_len;
 		spd.pages[i] = page;
@@ -809,6 +810,13 @@ static int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_des
  */
 static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_desc *sd)
 {
+	/*
+	 * Check for signal early to make process killable when there are
+	 * always buffers available
+	 */
+	if (signal_pending(current))
+		return -ERESTARTSYS;
+
 	while (!pipe->nrbufs) {
 		if (!pipe->writers)
 			return 0;
@@ -884,6 +892,7 @@ ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, struct splice_desc *sd,
 
 	splice_from_pipe_begin(sd);
 	do {
+		cond_resched();
 		ret = splice_from_pipe_next(pipe, sd);
 		if (ret > 0)
 			ret = splice_from_pipe_feed(pipe, sd, actor);
diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c
index 0cea9b9236d0..2c2618410d51 100644
--- a/fs/squashfs/block.c
+++ b/fs/squashfs/block.c
@@ -181,11 +181,11 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length,
 			in = min(bytes, msblk->devblksize - offset);
 			bytes -= in;
 			while (in) {
-				if (pg_offset == PAGE_CACHE_SIZE) {
+				if (pg_offset == PAGE_SIZE) {
 					data = squashfs_next_page(output);
 					pg_offset = 0;
 				}
-				avail = min_t(int, in, PAGE_CACHE_SIZE -
+				avail = min_t(int, in, PAGE_SIZE -
 						pg_offset);
 				memcpy(data + pg_offset, bh[k]->b_data + offset,
 						avail);
diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c
index 1cb70a0b2168..23813c078cc9 100644
--- a/fs/squashfs/cache.c
+++ b/fs/squashfs/cache.c
@@ -30,7 +30,7 @@
  * access the metadata and fragment caches.
  *
  * To avoid out of memory and fragmentation issues with vmalloc the cache
- * uses sequences of kmalloced PAGE_CACHE_SIZE buffers.
+ * uses sequences of kmalloced PAGE_SIZE buffers.
  *
  * It should be noted that the cache is not used for file datablocks, these
  * are decompressed and cached in the page-cache in the normal way.  The
@@ -231,7 +231,7 @@ void squashfs_cache_delete(struct squashfs_cache *cache)
 /*
  * Initialise cache allocating the specified number of entries, each of
  * size block_size.  To avoid vmalloc fragmentation issues each entry
- * is allocated as a sequence of kmalloced PAGE_CACHE_SIZE buffers.
+ * is allocated as a sequence of kmalloced PAGE_SIZE buffers.
  */
 struct squashfs_cache *squashfs_cache_init(char *name, int entries,
 	int block_size)
@@ -255,7 +255,7 @@ struct squashfs_cache *squashfs_cache_init(char *name, int entries,
 	cache->unused = entries;
 	cache->entries = entries;
 	cache->block_size = block_size;
-	cache->pages = block_size >> PAGE_CACHE_SHIFT;
+	cache->pages = block_size >> PAGE_SHIFT;
 	cache->pages = cache->pages ? cache->pages : 1;
 	cache->name = name;
 	cache->num_waiters = 0;
@@ -275,7 +275,7 @@ struct squashfs_cache *squashfs_cache_init(char *name, int entries,
 		}
 
 		for (j = 0; j < cache->pages; j++) {
-			entry->data[j] = kmalloc(PAGE_CACHE_SIZE, GFP_KERNEL);
+			entry->data[j] = kmalloc(PAGE_SIZE, GFP_KERNEL);
 			if (entry->data[j] == NULL) {
 				ERROR("Failed to allocate %s buffer\n", name);
 				goto cleanup;
@@ -314,10 +314,10 @@ int squashfs_copy_data(void *buffer, struct squashfs_cache_entry *entry,
 		return min(length, entry->length - offset);
 
 	while (offset < entry->length) {
-		void *buff = entry->data[offset / PAGE_CACHE_SIZE]
-				+ (offset % PAGE_CACHE_SIZE);
+		void *buff = entry->data[offset / PAGE_SIZE]
+				+ (offset % PAGE_SIZE);
 		int bytes = min_t(int, entry->length - offset,
-				PAGE_CACHE_SIZE - (offset % PAGE_CACHE_SIZE));
+				PAGE_SIZE - (offset % PAGE_SIZE));
 
 		if (bytes >= remaining) {
 			memcpy(buffer, buff, remaining);
@@ -415,7 +415,7 @@ struct squashfs_cache_entry *squashfs_get_datablock(struct super_block *sb,
  */
 void *squashfs_read_table(struct super_block *sb, u64 block, int length)
 {
-	int pages = (length + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	int pages = (length + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	int i, res;
 	void *table, *buffer, **data;
 	struct squashfs_page_actor *actor;
@@ -436,7 +436,7 @@ void *squashfs_read_table(struct super_block *sb, u64 block, int length)
 		goto failed2;
 	}
 
-	for (i = 0; i < pages; i++, buffer += PAGE_CACHE_SIZE)
+	for (i = 0; i < pages; i++, buffer += PAGE_SIZE)
 		data[i] = buffer;
 
 	res = squashfs_read_data(sb, block, length |
diff --git a/fs/squashfs/decompressor.c b/fs/squashfs/decompressor.c
index e9034bf6e5ae..d2bc13636f79 100644
--- a/fs/squashfs/decompressor.c
+++ b/fs/squashfs/decompressor.c
@@ -102,7 +102,7 @@ static void *get_comp_opts(struct super_block *sb, unsigned short flags)
 	 * Read decompressor specific options from file system if present
 	 */
 	if (SQUASHFS_COMP_OPTS(flags)) {
-		buffer = kmalloc(PAGE_CACHE_SIZE, GFP_KERNEL);
+		buffer = kmalloc(PAGE_SIZE, GFP_KERNEL);
 		if (buffer == NULL) {
 			comp_opts = ERR_PTR(-ENOMEM);
 			goto out;
diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
index e5c9689062ba..13d80947bf9e 100644
--- a/fs/squashfs/file.c
+++ b/fs/squashfs/file.c
@@ -175,7 +175,7 @@ static long long read_indexes(struct super_block *sb, int n,
 {
 	int err, i;
 	long long block = 0;
-	__le32 *blist = kmalloc(PAGE_CACHE_SIZE, GFP_KERNEL);
+	__le32 *blist = kmalloc(PAGE_SIZE, GFP_KERNEL);
 
 	if (blist == NULL) {
 		ERROR("read_indexes: Failed to allocate block_list\n");
@@ -183,7 +183,7 @@ static long long read_indexes(struct super_block *sb, int n,
 	}
 
 	while (n) {
-		int blocks = min_t(int, n, PAGE_CACHE_SIZE >> 2);
+		int blocks = min_t(int, n, PAGE_SIZE >> 2);
 
 		err = squashfs_read_metadata(sb, blist, start_block,
 				offset, blocks << 2);
@@ -377,19 +377,19 @@ void squashfs_copy_cache(struct page *page, struct squashfs_cache_entry *buffer,
 	struct inode *inode = page->mapping->host;
 	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
 	void *pageaddr;
-	int i, mask = (1 << (msblk->block_log - PAGE_CACHE_SHIFT)) - 1;
+	int i, mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1;
 	int start_index = page->index & ~mask, end_index = start_index | mask;
 
 	/*
 	 * Loop copying datablock into pages.  As the datablock likely covers
-	 * many PAGE_CACHE_SIZE pages (default block size is 128 KiB) explicitly
+	 * many PAGE_SIZE pages (default block size is 128 KiB) explicitly
 	 * grab the pages from the page cache, except for the page that we've
 	 * been called to fill.
 	 */
 	for (i = start_index; i <= end_index && bytes > 0; i++,
-			bytes -= PAGE_CACHE_SIZE, offset += PAGE_CACHE_SIZE) {
+			bytes -= PAGE_SIZE, offset += PAGE_SIZE) {
 		struct page *push_page;
-		int avail = buffer ? min_t(int, bytes, PAGE_CACHE_SIZE) : 0;
+		int avail = buffer ? min_t(int, bytes, PAGE_SIZE) : 0;
 
 		TRACE("bytes %d, i %d, available_bytes %d\n", bytes, i, avail);
 
@@ -404,14 +404,14 @@ void squashfs_copy_cache(struct page *page, struct squashfs_cache_entry *buffer,
 
 		pageaddr = kmap_atomic(push_page);
 		squashfs_copy_data(pageaddr, buffer, offset, avail);
-		memset(pageaddr + avail, 0, PAGE_CACHE_SIZE - avail);
+		memset(pageaddr + avail, 0, PAGE_SIZE - avail);
 		kunmap_atomic(pageaddr);
 		flush_dcache_page(push_page);
 		SetPageUptodate(push_page);
 skip_page:
 		unlock_page(push_page);
 		if (i != page->index)
-			page_cache_release(push_page);
+			put_page(push_page);
 	}
 }
 
@@ -454,7 +454,7 @@ static int squashfs_readpage(struct file *file, struct page *page)
 {
 	struct inode *inode = page->mapping->host;
 	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
-	int index = page->index >> (msblk->block_log - PAGE_CACHE_SHIFT);
+	int index = page->index >> (msblk->block_log - PAGE_SHIFT);
 	int file_end = i_size_read(inode) >> msblk->block_log;
 	int res;
 	void *pageaddr;
@@ -462,8 +462,8 @@ static int squashfs_readpage(struct file *file, struct page *page)
 	TRACE("Entered squashfs_readpage, page index %lx, start block %llx\n",
 				page->index, squashfs_i(inode)->start);
 
-	if (page->index >= ((i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
-					PAGE_CACHE_SHIFT))
+	if (page->index >= ((i_size_read(inode) + PAGE_SIZE - 1) >>
+					PAGE_SHIFT))
 		goto out;
 
 	if (index < file_end || squashfs_i(inode)->fragment_block ==
@@ -487,7 +487,7 @@ error_out:
 	SetPageError(page);
 out:
 	pageaddr = kmap_atomic(page);
-	memset(pageaddr, 0, PAGE_CACHE_SIZE);
+	memset(pageaddr, 0, PAGE_SIZE);
 	kunmap_atomic(pageaddr);
 	flush_dcache_page(page);
 	if (!PageError(page))
diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c
index 43e7a7eddac0..cb485d8e0e91 100644
--- a/fs/squashfs/file_direct.c
+++ b/fs/squashfs/file_direct.c
@@ -30,8 +30,8 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize)
 	struct inode *inode = target_page->mapping->host;
 	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
 
-	int file_end = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT;
-	int mask = (1 << (msblk->block_log - PAGE_CACHE_SHIFT)) - 1;
+	int file_end = (i_size_read(inode) - 1) >> PAGE_SHIFT;
+	int mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1;
 	int start_index = target_page->index & ~mask;
 	int end_index = start_index | mask;
 	int i, n, pages, missing_pages, bytes, res = -ENOMEM;
@@ -68,7 +68,7 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize)
 
 		if (PageUptodate(page[i])) {
 			unlock_page(page[i]);
-			page_cache_release(page[i]);
+			put_page(page[i]);
 			page[i] = NULL;
 			missing_pages++;
 		}
@@ -96,10 +96,10 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize)
 		goto mark_errored;
 
 	/* Last page may have trailing bytes not filled */
-	bytes = res % PAGE_CACHE_SIZE;
+	bytes = res % PAGE_SIZE;
 	if (bytes) {
 		pageaddr = kmap_atomic(page[pages - 1]);
-		memset(pageaddr + bytes, 0, PAGE_CACHE_SIZE - bytes);
+		memset(pageaddr + bytes, 0, PAGE_SIZE - bytes);
 		kunmap_atomic(pageaddr);
 	}
 
@@ -109,7 +109,7 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize)
 		SetPageUptodate(page[i]);
 		unlock_page(page[i]);
 		if (page[i] != target_page)
-			page_cache_release(page[i]);
+			put_page(page[i]);
 	}
 
 	kfree(actor);
@@ -127,7 +127,7 @@ mark_errored:
 		flush_dcache_page(page[i]);
 		SetPageError(page[i]);
 		unlock_page(page[i]);
-		page_cache_release(page[i]);
+		put_page(page[i]);
 	}
 
 out:
@@ -153,21 +153,21 @@ static int squashfs_read_cache(struct page *target_page, u64 block, int bsize,
 	}
 
 	for (n = 0; n < pages && bytes > 0; n++,
-			bytes -= PAGE_CACHE_SIZE, offset += PAGE_CACHE_SIZE) {
-		int avail = min_t(int, bytes, PAGE_CACHE_SIZE);
+			bytes -= PAGE_SIZE, offset += PAGE_SIZE) {
+		int avail = min_t(int, bytes, PAGE_SIZE);
 
 		if (page[n] == NULL)
 			continue;
 
 		pageaddr = kmap_atomic(page[n]);
 		squashfs_copy_data(pageaddr, buffer, offset, avail);
-		memset(pageaddr + avail, 0, PAGE_CACHE_SIZE - avail);
+		memset(pageaddr + avail, 0, PAGE_SIZE - avail);
 		kunmap_atomic(pageaddr);
 		flush_dcache_page(page[n]);
 		SetPageUptodate(page[n]);
 		unlock_page(page[n]);
 		if (page[n] != target_page)
-			page_cache_release(page[n]);
+			put_page(page[n]);
 	}
 
 out:
diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c
index a1ce5ce60632..0927b1e80ab6 100644
--- a/fs/squashfs/inode.c
+++ b/fs/squashfs/inode.c
@@ -41,6 +41,7 @@
 #include <linux/fs.h>
 #include <linux/vfs.h>
 #include <linux/xattr.h>
+#include <linux/pagemap.h>
 
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
@@ -291,6 +292,7 @@ int squashfs_read_inode(struct inode *inode, long long ino)
 		set_nlink(inode, le32_to_cpu(sqsh_ino->nlink));
 		inode->i_size = le32_to_cpu(sqsh_ino->symlink_size);
 		inode->i_op = &squashfs_symlink_inode_ops;
+		inode_nohighmem(inode);
 		inode->i_data.a_ops = &squashfs_symlink_aops;
 		inode->i_mode |= S_IFLNK;
 		squashfs_i(inode)->start = block;
diff --git a/fs/squashfs/lz4_wrapper.c b/fs/squashfs/lz4_wrapper.c
index c31e2bc9c081..ff4468bd18b0 100644
--- a/fs/squashfs/lz4_wrapper.c
+++ b/fs/squashfs/lz4_wrapper.c
@@ -117,13 +117,13 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	data = squashfs_first_page(output);
 	buff = stream->output;
 	while (data) {
-		if (bytes <= PAGE_CACHE_SIZE) {
+		if (bytes <= PAGE_SIZE) {
 			memcpy(data, buff, bytes);
 			break;
 		}
-		memcpy(data, buff, PAGE_CACHE_SIZE);
-		buff += PAGE_CACHE_SIZE;
-		bytes -= PAGE_CACHE_SIZE;
+		memcpy(data, buff, PAGE_SIZE);
+		buff += PAGE_SIZE;
+		bytes -= PAGE_SIZE;
 		data = squashfs_next_page(output);
 	}
 	squashfs_finish_page(output);
diff --git a/fs/squashfs/lzo_wrapper.c b/fs/squashfs/lzo_wrapper.c
index 244b9fbfff7b..934c17e96590 100644
--- a/fs/squashfs/lzo_wrapper.c
+++ b/fs/squashfs/lzo_wrapper.c
@@ -102,13 +102,13 @@ static int lzo_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	data = squashfs_first_page(output);
 	buff = stream->output;
 	while (data) {
-		if (bytes <= PAGE_CACHE_SIZE) {
+		if (bytes <= PAGE_SIZE) {
 			memcpy(data, buff, bytes);
 			break;
 		} else {
-			memcpy(data, buff, PAGE_CACHE_SIZE);
-			buff += PAGE_CACHE_SIZE;
-			bytes -= PAGE_CACHE_SIZE;
+			memcpy(data, buff, PAGE_SIZE);
+			buff += PAGE_SIZE;
+			bytes -= PAGE_SIZE;
 			data = squashfs_next_page(output);
 		}
 	}
diff --git a/fs/squashfs/page_actor.c b/fs/squashfs/page_actor.c
index 5a1c11f56441..9b7b1b6a7892 100644
--- a/fs/squashfs/page_actor.c
+++ b/fs/squashfs/page_actor.c
@@ -48,7 +48,7 @@ struct squashfs_page_actor *squashfs_page_actor_init(void **buffer,
 	if (actor == NULL)
 		return NULL;
 
-	actor->length = length ? : pages * PAGE_CACHE_SIZE;
+	actor->length = length ? : pages * PAGE_SIZE;
 	actor->buffer = buffer;
 	actor->pages = pages;
 	actor->next_page = 0;
@@ -88,7 +88,7 @@ struct squashfs_page_actor *squashfs_page_actor_init_special(struct page **page,
 	if (actor == NULL)
 		return NULL;
 
-	actor->length = length ? : pages * PAGE_CACHE_SIZE;
+	actor->length = length ? : pages * PAGE_SIZE;
 	actor->page = page;
 	actor->pages = pages;
 	actor->next_page = 0;
diff --git a/fs/squashfs/page_actor.h b/fs/squashfs/page_actor.h
index 26dd82008b82..98537eab27e2 100644
--- a/fs/squashfs/page_actor.h
+++ b/fs/squashfs/page_actor.h
@@ -24,7 +24,7 @@ static inline struct squashfs_page_actor *squashfs_page_actor_init(void **page,
 	if (actor == NULL)
 		return NULL;
 
-	actor->length = length ? : pages * PAGE_CACHE_SIZE;
+	actor->length = length ? : pages * PAGE_SIZE;
 	actor->page = page;
 	actor->pages = pages;
 	actor->next_page = 0;
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 5056babe00df..cf01e15a7b16 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -80,7 +80,6 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct squashfs_sb_info *msblk;
 	struct squashfs_super_block *sblk = NULL;
-	char b[BDEVNAME_SIZE];
 	struct inode *root;
 	long long root_inode;
 	unsigned short flags;
@@ -124,8 +123,8 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_magic = le32_to_cpu(sblk->s_magic);
 	if (sb->s_magic != SQUASHFS_MAGIC) {
 		if (!silent)
-			ERROR("Can't find a SQUASHFS superblock on %s\n",
-						bdevname(sb->s_bdev, b));
+			ERROR("Can't find a SQUASHFS superblock on %pg\n",
+						sb->s_bdev);
 		goto failed_mount;
 	}
 
@@ -153,7 +152,7 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent)
 	 * Check the system page size is not larger than the filesystem
 	 * block size (by default 128K).  This is currently not supported.
 	 */
-	if (PAGE_CACHE_SIZE > msblk->block_size) {
+	if (PAGE_SIZE > msblk->block_size) {
 		ERROR("Page size > filesystem block size (%d).  This is "
 			"currently not supported!\n", msblk->block_size);
 		goto failed_mount;
@@ -178,7 +177,7 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent)
 	msblk->inodes = le32_to_cpu(sblk->inodes);
 	flags = le16_to_cpu(sblk->flags);
 
-	TRACE("Found valid superblock on %s\n", bdevname(sb->s_bdev, b));
+	TRACE("Found valid superblock on %pg\n", sb->s_bdev);
 	TRACE("Inodes are %scompressed\n", SQUASHFS_UNCOMPRESSED_INODES(flags)
 				? "un" : "");
 	TRACE("Data is %scompressed\n", SQUASHFS_UNCOMPRESSED_DATA(flags)
@@ -420,7 +419,8 @@ static int __init init_inodecache(void)
 {
 	squashfs_inode_cachep = kmem_cache_create("squashfs_inode_cache",
 		sizeof(struct squashfs_inode_info), 0,
-		SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT, init_once);
+		SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT,
+		init_once);
 
 	return squashfs_inode_cachep ? 0 : -ENOMEM;
 }
diff --git a/fs/squashfs/symlink.c b/fs/squashfs/symlink.c
index 12806dffb345..d688ef42a6a1 100644
--- a/fs/squashfs/symlink.c
+++ b/fs/squashfs/symlink.c
@@ -48,10 +48,10 @@ static int squashfs_symlink_readpage(struct file *file, struct page *page)
 	struct inode *inode = page->mapping->host;
 	struct super_block *sb = inode->i_sb;
 	struct squashfs_sb_info *msblk = sb->s_fs_info;
-	int index = page->index << PAGE_CACHE_SHIFT;
+	int index = page->index << PAGE_SHIFT;
 	u64 block = squashfs_i(inode)->start;
 	int offset = squashfs_i(inode)->offset;
-	int length = min_t(int, i_size_read(inode) - index, PAGE_CACHE_SIZE);
+	int length = min_t(int, i_size_read(inode) - index, PAGE_SIZE);
 	int bytes, copied;
 	void *pageaddr;
 	struct squashfs_cache_entry *entry;
@@ -94,7 +94,7 @@ static int squashfs_symlink_readpage(struct file *file, struct page *page)
 		copied = squashfs_copy_data(pageaddr + bytes, entry, offset,
 								length - bytes);
 		if (copied == length - bytes)
-			memset(pageaddr + length, 0, PAGE_CACHE_SIZE - length);
+			memset(pageaddr + length, 0, PAGE_SIZE - length);
 		else
 			block = entry->next_index;
 		kunmap_atomic(pageaddr);
@@ -119,8 +119,7 @@ const struct address_space_operations squashfs_symlink_aops = {
 
 const struct inode_operations squashfs_symlink_inode_ops = {
 	.readlink = generic_readlink,
-	.follow_link = page_follow_link_light,
-	.put_link = page_put_link,
+	.get_link = page_get_link,
 	.getxattr = generic_getxattr,
 	.listxattr = squashfs_listxattr
 };
diff --git a/fs/squashfs/xattr.c b/fs/squashfs/xattr.c
index e5e0ddf5b143..1e9de96288d8 100644
--- a/fs/squashfs/xattr.c
+++ b/fs/squashfs/xattr.c
@@ -58,7 +58,7 @@ ssize_t squashfs_listxattr(struct dentry *d, char *buffer,
 		struct squashfs_xattr_entry entry;
 		struct squashfs_xattr_val val;
 		const struct xattr_handler *handler;
-		int name_size, prefix_size = 0;
+		int name_size;
 
 		err = squashfs_read_metadata(sb, &entry, &start, &offset,
 							sizeof(entry));
@@ -67,15 +67,16 @@ ssize_t squashfs_listxattr(struct dentry *d, char *buffer,
 
 		name_size = le16_to_cpu(entry.size);
 		handler = squashfs_xattr_handler(le16_to_cpu(entry.type));
-		if (handler)
-			prefix_size = handler->list(d, buffer, rest, NULL,
-				name_size, handler->flags);
-		if (prefix_size) {
+		if (handler && (!handler->list || handler->list(d))) {
+			const char *prefix = handler->prefix ?: handler->name;
+			size_t prefix_size = strlen(prefix);
+
 			if (buffer) {
 				if (prefix_size + name_size + 1 > rest) {
 					err = -ERANGE;
 					goto failed;
 				}
+				memcpy(buffer, prefix, prefix_size);
 				buffer += prefix_size;
 			}
 			err = squashfs_read_metadata(sb, buffer, &start,
@@ -212,88 +213,45 @@ failed:
 }
 
 
-/*
- * User namespace support
- */
-static size_t squashfs_user_list(struct dentry *d, char *list, size_t list_size,
-	const char *name, size_t name_len, int type)
-{
-	if (list && XATTR_USER_PREFIX_LEN <= list_size)
-		memcpy(list, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN);
-	return XATTR_USER_PREFIX_LEN;
-}
-
-static int squashfs_user_get(struct dentry *d, const char *name, void *buffer,
-	size_t size, int type)
+static int squashfs_xattr_handler_get(const struct xattr_handler *handler,
+				      struct dentry *d, const char *name,
+				      void *buffer, size_t size)
 {
-	if (name[0] == '\0')
-		return  -EINVAL;
-
-	return squashfs_xattr_get(d_inode(d), SQUASHFS_XATTR_USER, name,
+	return squashfs_xattr_get(d_inode(d), handler->flags, name,
 		buffer, size);
 }
 
+/*
+ * User namespace support
+ */
 static const struct xattr_handler squashfs_xattr_user_handler = {
 	.prefix	= XATTR_USER_PREFIX,
-	.list	= squashfs_user_list,
-	.get	= squashfs_user_get
+	.flags	= SQUASHFS_XATTR_USER,
+	.get	= squashfs_xattr_handler_get
 };
 
 /*
  * Trusted namespace support
  */
-static size_t squashfs_trusted_list(struct dentry *d, char *list,
-	size_t list_size, const char *name, size_t name_len, int type)
+static bool squashfs_trusted_xattr_handler_list(struct dentry *d)
 {
-	if (!capable(CAP_SYS_ADMIN))
-		return 0;
-
-	if (list && XATTR_TRUSTED_PREFIX_LEN <= list_size)
-		memcpy(list, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN);
-	return XATTR_TRUSTED_PREFIX_LEN;
-}
-
-static int squashfs_trusted_get(struct dentry *d, const char *name,
-	void *buffer, size_t size, int type)
-{
-	if (name[0] == '\0')
-		return  -EINVAL;
-
-	return squashfs_xattr_get(d_inode(d), SQUASHFS_XATTR_TRUSTED, name,
-		buffer, size);
+	return capable(CAP_SYS_ADMIN);
 }
 
 static const struct xattr_handler squashfs_xattr_trusted_handler = {
 	.prefix	= XATTR_TRUSTED_PREFIX,
-	.list	= squashfs_trusted_list,
-	.get	= squashfs_trusted_get
+	.flags	= SQUASHFS_XATTR_TRUSTED,
+	.list	= squashfs_trusted_xattr_handler_list,
+	.get	= squashfs_xattr_handler_get
 };
 
 /*
  * Security namespace support
  */
-static size_t squashfs_security_list(struct dentry *d, char *list,
-	size_t list_size, const char *name, size_t name_len, int type)
-{
-	if (list && XATTR_SECURITY_PREFIX_LEN <= list_size)
-		memcpy(list, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN);
-	return XATTR_SECURITY_PREFIX_LEN;
-}
-
-static int squashfs_security_get(struct dentry *d, const char *name,
-	void *buffer, size_t size, int type)
-{
-	if (name[0] == '\0')
-		return  -EINVAL;
-
-	return squashfs_xattr_get(d_inode(d), SQUASHFS_XATTR_SECURITY, name,
-		buffer, size);
-}
-
 static const struct xattr_handler squashfs_xattr_security_handler = {
 	.prefix	= XATTR_SECURITY_PREFIX,
-	.list	= squashfs_security_list,
-	.get	= squashfs_security_get
+	.flags	= SQUASHFS_XATTR_SECURITY,
+	.get	= squashfs_xattr_handler_get
 };
 
 static const struct xattr_handler *squashfs_xattr_handler(int type)
diff --git a/fs/squashfs/xz_wrapper.c b/fs/squashfs/xz_wrapper.c
index c609624e4b8a..6bfaef73d065 100644
--- a/fs/squashfs/xz_wrapper.c
+++ b/fs/squashfs/xz_wrapper.c
@@ -141,7 +141,7 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	stream->buf.in_pos = 0;
 	stream->buf.in_size = 0;
 	stream->buf.out_pos = 0;
-	stream->buf.out_size = PAGE_CACHE_SIZE;
+	stream->buf.out_size = PAGE_SIZE;
 	stream->buf.out = squashfs_first_page(output);
 
 	do {
@@ -158,7 +158,7 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm,
 			stream->buf.out = squashfs_next_page(output);
 			if (stream->buf.out != NULL) {
 				stream->buf.out_pos = 0;
-				total += PAGE_CACHE_SIZE;
+				total += PAGE_SIZE;
 			}
 		}
 
diff --git a/fs/squashfs/zlib_wrapper.c b/fs/squashfs/zlib_wrapper.c
index 8727caba6882..2ec24d128bce 100644
--- a/fs/squashfs/zlib_wrapper.c
+++ b/fs/squashfs/zlib_wrapper.c
@@ -69,7 +69,7 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	int zlib_err, zlib_init = 0, k = 0;
 	z_stream *stream = strm;
 
-	stream->avail_out = PAGE_CACHE_SIZE;
+	stream->avail_out = PAGE_SIZE;
 	stream->next_out = squashfs_first_page(output);
 	stream->avail_in = 0;
 
@@ -85,7 +85,7 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm,
 		if (stream->avail_out == 0) {
 			stream->next_out = squashfs_next_page(output);
 			if (stream->next_out != NULL)
-				stream->avail_out = PAGE_CACHE_SIZE;
+				stream->avail_out = PAGE_SIZE;
 		}
 
 		if (!zlib_init) {
diff --git a/fs/stat.c b/fs/stat.c
index cccc1aab9a8b..bc045c7994e1 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -219,7 +219,7 @@ SYSCALL_DEFINE2(fstat, unsigned int, fd, struct __old_kernel_stat __user *, stat
 #  define choose_32_64(a,b) b
 #endif
 
-#define valid_dev(x)  choose_32_64(old_valid_dev,new_valid_dev)(x)
+#define valid_dev(x)  choose_32_64(old_valid_dev(x),true)
 #define encode_dev(x) choose_32_64(old_encode_dev,new_encode_dev)(x)
 
 #ifndef INIT_STRUCT_STAT_PADDING
@@ -367,8 +367,6 @@ static long cp_new_stat64(struct kstat *stat, struct stat64 __user *statbuf)
 	INIT_STRUCT_STAT64_PADDING(tmp);
 #ifdef CONFIG_MIPS
 	/* mips has weird padding, so we don't get 64 bits there */
-	if (!new_valid_dev(stat->dev) || !new_valid_dev(stat->rdev))
-		return -EOVERFLOW;
 	tmp.st_dev = new_encode_dev(stat->dev);
 	tmp.st_rdev = new_encode_dev(stat->rdev);
 #else
diff --git a/fs/super.c b/fs/super.c
index 6cd9f719cf61..d78b9847e6cb 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -415,6 +415,7 @@ void generic_shutdown_super(struct super_block *sb)
 		sb->s_flags &= ~MS_ACTIVE;
 
 		fsnotify_unmount_inodes(sb);
+		cgroup_writeback_umount();
 
 		evict_inodes(sb);
 
@@ -1012,10 +1013,8 @@ struct dentry *mount_bdev(struct file_system_type *fs_type,
 		blkdev_put(bdev, mode);
 		down_write(&s->s_umount);
 	} else {
-		char b[BDEVNAME_SIZE];
-
 		s->s_mode = mode;
-		strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
+		snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
 		sb_set_blocksize(s, block_size(bdev));
 		error = fill_super(s, data, flags & MS_SILENT ? 1 : 0);
 		if (error) {
diff --git a/fs/sync.c b/fs/sync.c
index 4ec430ae2b0d..2a54c1f22035 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -302,7 +302,7 @@ SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes,
 		goto out;
 
 	if (sizeof(pgoff_t) == 4) {
-		if (offset >= (0x100000000ULL << PAGE_CACHE_SHIFT)) {
+		if (offset >= (0x100000000ULL << PAGE_SHIFT)) {
 			/*
 			 * The range starts outside a 32 bit machine's
 			 * pagecache addressing capabilities.  Let it "succeed"
@@ -310,7 +310,7 @@ SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes,
 			ret = 0;
 			goto out;
 		}
-		if (endbyte >= (0x100000000ULL << PAGE_CACHE_SHIFT)) {
+		if (endbyte >= (0x100000000ULL << PAGE_SHIFT)) {
 			/*
 			 * Out to EOF
 			 */
@@ -348,7 +348,8 @@ SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes,
 	}
 
 	if (flags & SYNC_FILE_RANGE_WRITE) {
-		ret = filemap_fdatawrite_range(mapping, offset, endbyte);
+		ret = __filemap_fdatawrite_range(mapping, offset, endbyte,
+						 WB_SYNC_NONE);
 		if (ret < 0)
 			goto out_put;
 	}
diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c
index e1236594fffe..dc1358b5ec95 100644
--- a/fs/sysfs/group.c
+++ b/fs/sysfs/group.c
@@ -73,13 +73,26 @@ static int create_files(struct kernfs_node *parent, struct kobject *kobj,
 	}
 
 	if (grp->bin_attrs) {
-		for (bin_attr = grp->bin_attrs; *bin_attr; bin_attr++) {
+		for (i = 0, bin_attr = grp->bin_attrs; *bin_attr; i++, bin_attr++) {
+			umode_t mode = (*bin_attr)->attr.mode;
+
 			if (update)
 				kernfs_remove_by_name(parent,
 						(*bin_attr)->attr.name);
+			if (grp->is_bin_visible) {
+				mode = grp->is_bin_visible(kobj, *bin_attr, i);
+				if (!mode)
+					continue;
+			}
+
+			WARN(mode & ~(SYSFS_PREALLOC | 0664),
+			     "Attribute %s: Invalid permissions 0%o\n",
+			     (*bin_attr)->attr.name, mode);
+
+			mode &= SYSFS_PREALLOC | 0664;
 			error = sysfs_add_file_mode_ns(parent,
 					&(*bin_attr)->attr, true,
-					(*bin_attr)->attr.mode, NULL);
+					mode, NULL);
 			if (error)
 				break;
 		}
diff --git a/fs/sysv/dir.c b/fs/sysv/dir.c
index 63c1bcb224ee..c0f0a3e643eb 100644
--- a/fs/sysv/dir.c
+++ b/fs/sysv/dir.c
@@ -30,7 +30,7 @@ const struct file_operations sysv_dir_operations = {
 static inline void dir_put_page(struct page *page)
 {
 	kunmap(page);
-	page_cache_release(page);
+	put_page(page);
 }
 
 static int dir_commit_chunk(struct page *page, loff_t pos, unsigned len)
@@ -73,8 +73,8 @@ static int sysv_readdir(struct file *file, struct dir_context *ctx)
 	if (pos >= inode->i_size)
 		return 0;
 
-	offset = pos & ~PAGE_CACHE_MASK;
-	n = pos >> PAGE_CACHE_SHIFT;
+	offset = pos & ~PAGE_MASK;
+	n = pos >> PAGE_SHIFT;
 
 	for ( ; n < npages; n++, offset = 0) {
 		char *kaddr, *limit;
@@ -85,7 +85,7 @@ static int sysv_readdir(struct file *file, struct dir_context *ctx)
 			continue;
 		kaddr = (char *)page_address(page);
 		de = (struct sysv_dir_entry *)(kaddr+offset);
-		limit = kaddr + PAGE_CACHE_SIZE - SYSV_DIRSIZE;
+		limit = kaddr + PAGE_SIZE - SYSV_DIRSIZE;
 		for ( ;(char*)de <= limit; de++, ctx->pos += sizeof(*de)) {
 			char *name = de->name;
 
@@ -146,7 +146,7 @@ struct sysv_dir_entry *sysv_find_entry(struct dentry *dentry, struct page **res_
 		if (!IS_ERR(page)) {
 			kaddr = (char*)page_address(page);
 			de = (struct sysv_dir_entry *) kaddr;
-			kaddr += PAGE_CACHE_SIZE - SYSV_DIRSIZE;
+			kaddr += PAGE_SIZE - SYSV_DIRSIZE;
 			for ( ; (char *) de <= kaddr ; de++) {
 				if (!de->inode)
 					continue;
@@ -190,7 +190,7 @@ int sysv_add_link(struct dentry *dentry, struct inode *inode)
 			goto out;
 		kaddr = (char*)page_address(page);
 		de = (struct sysv_dir_entry *)kaddr;
-		kaddr += PAGE_CACHE_SIZE - SYSV_DIRSIZE;
+		kaddr += PAGE_SIZE - SYSV_DIRSIZE;
 		while ((char *)de <= kaddr) {
 			if (!de->inode)
 				goto got_it;
@@ -261,7 +261,7 @@ int sysv_make_empty(struct inode *inode, struct inode *dir)
 	kmap(page);
 
 	base = (char*)page_address(page);
-	memset(base, 0, PAGE_CACHE_SIZE);
+	memset(base, 0, PAGE_SIZE);
 
 	de = (struct sysv_dir_entry *) base;
 	de->inode = cpu_to_fs16(SYSV_SB(inode->i_sb), inode->i_ino);
@@ -273,7 +273,7 @@ int sysv_make_empty(struct inode *inode, struct inode *dir)
 	kunmap(page);
 	err = dir_commit_chunk(page, 0, 2 * SYSV_DIRSIZE);
 fail:
-	page_cache_release(page);
+	put_page(page);
 	return err;
 }
 
@@ -296,7 +296,7 @@ int sysv_empty_dir(struct inode * inode)
 
 		kaddr = (char *)page_address(page);
 		de = (struct sysv_dir_entry *)kaddr;
-		kaddr += PAGE_CACHE_SIZE-SYSV_DIRSIZE;
+		kaddr += PAGE_SIZE-SYSV_DIRSIZE;
 
 		for ( ;(char *)de <= kaddr; de++) {
 			if (!de->inode)
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index 590ad9206e3f..d62c423a5a2d 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -146,8 +146,7 @@ static inline void write3byte(struct sysv_sb_info *sbi,
 
 static const struct inode_operations sysv_symlink_inode_operations = {
 	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
+	.get_link	= page_get_link,
 	.getattr	= sysv_getattr,
 };
 
@@ -162,15 +161,9 @@ void sysv_set_inode(struct inode *inode, dev_t rdev)
 		inode->i_fop = &sysv_dir_operations;
 		inode->i_mapping->a_ops = &sysv_aops;
 	} else if (S_ISLNK(inode->i_mode)) {
-		if (inode->i_blocks) {
-			inode->i_op = &sysv_symlink_inode_operations;
-			inode->i_mapping->a_ops = &sysv_aops;
-		} else {
-			inode->i_op = &simple_symlink_inode_operations;
-			inode->i_link = (char *)SYSV_I(inode)->i_data;
-			nd_terminate_link(inode->i_link, inode->i_size,
-				sizeof(SYSV_I(inode)->i_data) - 1);
-		}
+		inode->i_op = &sysv_symlink_inode_operations;
+		inode_nohighmem(inode);
+		inode->i_mapping->a_ops = &sysv_aops;
 	} else
 		init_special_inode(inode, inode->i_mode, rdev);
 }
@@ -353,7 +346,7 @@ int __init sysv_init_icache(void)
 {
 	sysv_inode_cachep = kmem_cache_create("sysv_inode_cache",
 			sizeof(struct sysv_inode_info), 0,
-			SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD,
+			SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT,
 			init_once);
 	if (!sysv_inode_cachep)
 		return -ENOMEM;
diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c
index 11e83ed0b4bf..90b60c03b588 100644
--- a/fs/sysv/namei.c
+++ b/fs/sysv/namei.c
@@ -264,11 +264,11 @@ static int sysv_rename(struct inode * old_dir, struct dentry * old_dentry,
 out_dir:
 	if (dir_de) {
 		kunmap(dir_page);
-		page_cache_release(dir_page);
+		put_page(dir_page);
 	}
 out_old:
 	kunmap(old_page);
-	page_cache_release(old_page);
+	put_page(old_page);
 out:
 	return err;
 }
diff --git a/fs/timerfd.c b/fs/timerfd.c
index b94fa6c3c6eb..053818dd6c18 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -153,7 +153,7 @@ static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx)
 	if (isalarm(ctx))
 		remaining = alarm_expires_remaining(&ctx->t.alarm);
 	else
-		remaining = hrtimer_expires_remaining(&ctx->t.tmr);
+		remaining = hrtimer_expires_remaining_adjusted(&ctx->t.tmr);
 
 	return remaining.tv64 < 0 ? ktime_set(0, 0): remaining;
 }
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index c66f2423e1f5..4a0e48f92104 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -84,9 +84,9 @@ static int tracefs_syscall_mkdir(struct inode *inode, struct dentry *dentry, umo
 	 * the files within the tracefs system. It is up to the individual
 	 * mkdir routine to handle races.
 	 */
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	ret = tracefs_ops.mkdir(name);
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	kfree(name);
 
@@ -109,13 +109,13 @@ static int tracefs_syscall_rmdir(struct inode *inode, struct dentry *dentry)
 	 * This time we need to unlock not only the parent (inode) but
 	 * also the directory that is being deleted.
 	 */
-	mutex_unlock(&inode->i_mutex);
-	mutex_unlock(&dentry->d_inode->i_mutex);
+	inode_unlock(inode);
+	inode_unlock(dentry->d_inode);
 
 	ret = tracefs_ops.rmdir(name);
 
-	mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT);
-	mutex_lock(&dentry->d_inode->i_mutex);
+	inode_lock_nested(inode, I_MUTEX_PARENT);
+	inode_lock(dentry->d_inode);
 
 	kfree(name);
 
@@ -334,7 +334,7 @@ static struct dentry *start_creating(const char *name, struct dentry *parent)
 	if (!parent)
 		parent = tracefs_mount->mnt_root;
 
-	mutex_lock(&parent->d_inode->i_mutex);
+	inode_lock(parent->d_inode);
 	dentry = lookup_one_len(name, parent, strlen(name));
 	if (!IS_ERR(dentry) && dentry->d_inode) {
 		dput(dentry);
@@ -342,7 +342,7 @@ static struct dentry *start_creating(const char *name, struct dentry *parent)
 	}
 
 	if (IS_ERR(dentry)) {
-		mutex_unlock(&parent->d_inode->i_mutex);
+		inode_unlock(parent->d_inode);
 		simple_release_fs(&tracefs_mount, &tracefs_mount_count);
 	}
 
@@ -351,7 +351,7 @@ static struct dentry *start_creating(const char *name, struct dentry *parent)
 
 static struct dentry *failed_creating(struct dentry *dentry)
 {
-	mutex_unlock(&dentry->d_parent->d_inode->i_mutex);
+	inode_unlock(dentry->d_parent->d_inode);
 	dput(dentry);
 	simple_release_fs(&tracefs_mount, &tracefs_mount_count);
 	return NULL;
@@ -359,7 +359,7 @@ static struct dentry *failed_creating(struct dentry *dentry)
 
 static struct dentry *end_creating(struct dentry *dentry)
 {
-	mutex_unlock(&dentry->d_parent->d_inode->i_mutex);
+	inode_unlock(dentry->d_parent->d_inode);
 	return dentry;
 }
 
@@ -544,9 +544,9 @@ void tracefs_remove(struct dentry *dentry)
 	if (!parent || !parent->d_inode)
 		return;
 
-	mutex_lock(&parent->d_inode->i_mutex);
+	inode_lock(parent->d_inode);
 	ret = __tracefs_remove(dentry, parent);
-	mutex_unlock(&parent->d_inode->i_mutex);
+	inode_unlock(parent->d_inode);
 	if (!ret)
 		simple_release_fs(&tracefs_mount, &tracefs_mount_count);
 }
@@ -572,7 +572,7 @@ void tracefs_remove_recursive(struct dentry *dentry)
 
 	parent = dentry;
  down:
-	mutex_lock(&parent->d_inode->i_mutex);
+	inode_lock(parent->d_inode);
  loop:
 	/*
 	 * The parent->d_subdirs is protected by the d_lock. Outside that
@@ -587,7 +587,7 @@ void tracefs_remove_recursive(struct dentry *dentry)
 		/* perhaps simple_empty(child) makes more sense */
 		if (!list_empty(&child->d_subdirs)) {
 			spin_unlock(&parent->d_lock);
-			mutex_unlock(&parent->d_inode->i_mutex);
+			inode_unlock(parent->d_inode);
 			parent = child;
 			goto down;
 		}
@@ -608,10 +608,10 @@ void tracefs_remove_recursive(struct dentry *dentry)
 	}
 	spin_unlock(&parent->d_lock);
 
-	mutex_unlock(&parent->d_inode->i_mutex);
+	inode_unlock(parent->d_inode);
 	child = parent;
 	parent = parent->d_parent;
-	mutex_lock(&parent->d_inode->i_mutex);
+	inode_lock(parent->d_inode);
 
 	if (child != dentry)
 		/* go up */
@@ -619,7 +619,7 @@ void tracefs_remove_recursive(struct dentry *dentry)
 
 	if (!__tracefs_remove(child, parent))
 		simple_release_fs(&tracefs_mount, &tracefs_mount_count);
-	mutex_unlock(&parent->d_inode->i_mutex);
+	inode_unlock(parent->d_inode);
 }
 
 /**
diff --git a/fs/ubifs/Kconfig b/fs/ubifs/Kconfig
index ba66d508006a..7ff7712f284e 100644
--- a/fs/ubifs/Kconfig
+++ b/fs/ubifs/Kconfig
@@ -35,3 +35,18 @@ config UBIFS_FS_ZLIB
 	default y
 	help
 	  Zlib compresses better than LZO but it is slower. Say 'Y' if unsure.
+
+config UBIFS_ATIME_SUPPORT
+	bool "Access time support" if UBIFS_FS
+	depends on UBIFS_FS
+	default n
+	help
+	  Originally UBIFS did not support atime, because it looked like a bad idea due
+	  increased flash wear. This option adds atime support and it is disabled by default
+	  to preserve the old behavior. If you enable this option, UBIFS starts updating atime,
+	  which means that file-system read operations will cause writes (inode atime
+	  updates). This may affect file-system performance and increase flash device wear,
+	  so be careful. How often atime is updated depends on the selected strategy:
+	  strictatime is the "heavy", relatime is "lighter", etc.
+
+	  If unsure, say 'N'
diff --git a/fs/ubifs/Makefile b/fs/ubifs/Makefile
index 2c6f0cb816b4..c54a24360f85 100644
--- a/fs/ubifs/Makefile
+++ b/fs/ubifs/Makefile
@@ -4,3 +4,4 @@ ubifs-y += shrinker.o journal.o file.o dir.o super.o sb.o io.o
 ubifs-y += tnc.o master.o scan.o replay.o log.o commit.o gc.o orphan.o
 ubifs-y += budget.o find.o tnc_commit.o compress.o lpt.o lprops.o
 ubifs-y += recovery.o ioctl.o lpt_commit.o tnc_misc.o xattr.o debug.o
+ubifs-y += misc.o
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index 4c46a9865fa7..595ca0debe11 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -2573,7 +2573,7 @@ int dbg_leb_write(struct ubifs_info *c, int lnum, const void *buf,
 {
 	int err, failing;
 
-	if (c->dbg->pc_happened)
+	if (dbg_is_power_cut(c))
 		return -EROFS;
 
 	failing = power_cut_emulated(c, lnum, 1);
@@ -2595,7 +2595,7 @@ int dbg_leb_change(struct ubifs_info *c, int lnum, const void *buf,
 {
 	int err;
 
-	if (c->dbg->pc_happened)
+	if (dbg_is_power_cut(c))
 		return -EROFS;
 	if (power_cut_emulated(c, lnum, 1))
 		return -EROFS;
@@ -2611,7 +2611,7 @@ int dbg_leb_unmap(struct ubifs_info *c, int lnum)
 {
 	int err;
 
-	if (c->dbg->pc_happened)
+	if (dbg_is_power_cut(c))
 		return -EROFS;
 	if (power_cut_emulated(c, lnum, 0))
 		return -EROFS;
@@ -2627,7 +2627,7 @@ int dbg_leb_map(struct ubifs_info *c, int lnum)
 {
 	int err;
 
-	if (c->dbg->pc_happened)
+	if (dbg_is_power_cut(c))
 		return -EROFS;
 	if (power_cut_emulated(c, lnum, 0))
 		return -EROFS;
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 5c27c66c224a..795992a8321e 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -449,13 +449,14 @@ static int ubifs_readdir(struct file *file, struct dir_context *ctx)
 	}
 
 out:
+	kfree(file->private_data);
+	file->private_data = NULL;
+
 	if (err != -ENOENT) {
 		ubifs_err(c, "cannot find next direntry, error %d", err);
 		return err;
 	}
 
-	kfree(file->private_data);
-	file->private_data = NULL;
 	/* 2 is a special value indicating that there are no more direntries */
 	ctx->pos = 2;
 	return 0;
@@ -514,8 +515,8 @@ static int ubifs_link(struct dentry *old_dentry, struct inode *dir,
 	dbg_gen("dent '%pd' to ino %lu (nlink %d) in dir ino %lu",
 		dentry, inode->i_ino,
 		inode->i_nlink, dir->i_ino);
-	ubifs_assert(mutex_is_locked(&dir->i_mutex));
-	ubifs_assert(mutex_is_locked(&inode->i_mutex));
+	ubifs_assert(inode_is_locked(dir));
+	ubifs_assert(inode_is_locked(inode));
 
 	err = dbg_check_synced_i_size(c, inode);
 	if (err)
@@ -571,8 +572,8 @@ static int ubifs_unlink(struct inode *dir, struct dentry *dentry)
 	dbg_gen("dent '%pd' from ino %lu (nlink %d) in dir ino %lu",
 		dentry, inode->i_ino,
 		inode->i_nlink, dir->i_ino);
-	ubifs_assert(mutex_is_locked(&dir->i_mutex));
-	ubifs_assert(mutex_is_locked(&inode->i_mutex));
+	ubifs_assert(inode_is_locked(dir));
+	ubifs_assert(inode_is_locked(inode));
 	err = dbg_check_synced_i_size(c, inode);
 	if (err)
 		return err;
@@ -660,8 +661,8 @@ static int ubifs_rmdir(struct inode *dir, struct dentry *dentry)
 
 	dbg_gen("directory '%pd', ino %lu in dir ino %lu", dentry,
 		inode->i_ino, dir->i_ino);
-	ubifs_assert(mutex_is_locked(&dir->i_mutex));
-	ubifs_assert(mutex_is_locked(&inode->i_mutex));
+	ubifs_assert(inode_is_locked(dir));
+	ubifs_assert(inode_is_locked(inode));
 	err = check_dir_empty(c, d_inode(dentry));
 	if (err)
 		return err;
@@ -787,9 +788,6 @@ static int ubifs_mknod(struct inode *dir, struct dentry *dentry,
 
 	dbg_gen("dent '%pd' in dir ino %lu", dentry, dir->i_ino);
 
-	if (!new_valid_dev(rdev))
-		return -EINVAL;
-
 	if (S_ISBLK(mode) || S_ISCHR(mode)) {
 		dev = kmalloc(sizeof(union ubifs_dev_desc), GFP_NOFS);
 		if (!dev)
@@ -998,10 +996,10 @@ static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	dbg_gen("dent '%pd' ino %lu in dir ino %lu to dent '%pd' in dir ino %lu",
 		old_dentry, old_inode->i_ino, old_dir->i_ino,
 		new_dentry, new_dir->i_ino);
-	ubifs_assert(mutex_is_locked(&old_dir->i_mutex));
-	ubifs_assert(mutex_is_locked(&new_dir->i_mutex));
+	ubifs_assert(inode_is_locked(old_dir));
+	ubifs_assert(inode_is_locked(new_dir));
 	if (unlink)
-		ubifs_assert(mutex_is_locked(&new_inode->i_mutex));
+		ubifs_assert(inode_is_locked(new_inode));
 
 
 	if (unlink && is_dir) {
@@ -1188,6 +1186,9 @@ const struct inode_operations ubifs_dir_inode_operations = {
 	.getxattr    = ubifs_getxattr,
 	.listxattr   = ubifs_listxattr,
 	.removexattr = ubifs_removexattr,
+#ifdef CONFIG_UBIFS_ATIME_SUPPORT
+	.update_time = ubifs_update_time,
+#endif
 };
 
 const struct file_operations ubifs_dir_operations = {
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index a3dfe2ae79f2..446753d8ac34 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -121,7 +121,7 @@ static int do_readpage(struct page *page)
 	if (block >= beyond) {
 		/* Reading beyond inode */
 		SetPageChecked(page);
-		memset(addr, 0, PAGE_CACHE_SIZE);
+		memset(addr, 0, PAGE_SIZE);
 		goto out;
 	}
 
@@ -223,7 +223,7 @@ static int write_begin_slow(struct address_space *mapping,
 {
 	struct inode *inode = mapping->host;
 	struct ubifs_info *c = inode->i_sb->s_fs_info;
-	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+	pgoff_t index = pos >> PAGE_SHIFT;
 	struct ubifs_budget_req req = { .new_page = 1 };
 	int uninitialized_var(err), appending = !!(pos + len > inode->i_size);
 	struct page *page;
@@ -254,13 +254,13 @@ static int write_begin_slow(struct address_space *mapping,
 	}
 
 	if (!PageUptodate(page)) {
-		if (!(pos & ~PAGE_CACHE_MASK) && len == PAGE_CACHE_SIZE)
+		if (!(pos & ~PAGE_MASK) && len == PAGE_SIZE)
 			SetPageChecked(page);
 		else {
 			err = do_readpage(page);
 			if (err) {
 				unlock_page(page);
-				page_cache_release(page);
+				put_page(page);
 				ubifs_release_budget(c, &req);
 				return err;
 			}
@@ -428,7 +428,7 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping,
 	struct inode *inode = mapping->host;
 	struct ubifs_info *c = inode->i_sb->s_fs_info;
 	struct ubifs_inode *ui = ubifs_inode(inode);
-	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+	pgoff_t index = pos >> PAGE_SHIFT;
 	int uninitialized_var(err), appending = !!(pos + len > inode->i_size);
 	int skipped_read = 0;
 	struct page *page;
@@ -446,7 +446,7 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping,
 
 	if (!PageUptodate(page)) {
 		/* The page is not loaded from the flash */
-		if (!(pos & ~PAGE_CACHE_MASK) && len == PAGE_CACHE_SIZE) {
+		if (!(pos & ~PAGE_MASK) && len == PAGE_SIZE) {
 			/*
 			 * We change whole page so no need to load it. But we
 			 * do not know whether this page exists on the media or
@@ -462,7 +462,7 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping,
 			err = do_readpage(page);
 			if (err) {
 				unlock_page(page);
-				page_cache_release(page);
+				put_page(page);
 				return err;
 			}
 		}
@@ -494,7 +494,7 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping,
 			mutex_unlock(&ui->ui_mutex);
 		}
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 
 		return write_begin_slow(mapping, pos, len, pagep, flags);
 	}
@@ -549,12 +549,12 @@ static int ubifs_write_end(struct file *file, struct address_space *mapping,
 	dbg_gen("ino %lu, pos %llu, pg %lu, len %u, copied %d, i_size %lld",
 		inode->i_ino, pos, page->index, len, copied, inode->i_size);
 
-	if (unlikely(copied < len && len == PAGE_CACHE_SIZE)) {
+	if (unlikely(copied < len && len == PAGE_SIZE)) {
 		/*
 		 * VFS copied less data to the page that it intended and
 		 * declared in its '->write_begin()' call via the @len
 		 * argument. If the page was not up-to-date, and @len was
-		 * @PAGE_CACHE_SIZE, the 'ubifs_write_begin()' function did
+		 * @PAGE_SIZE, the 'ubifs_write_begin()' function did
 		 * not load it from the media (for optimization reasons). This
 		 * means that part of the page contains garbage. So read the
 		 * page now.
@@ -593,7 +593,7 @@ static int ubifs_write_end(struct file *file, struct address_space *mapping,
 
 out:
 	unlock_page(page);
-	page_cache_release(page);
+	put_page(page);
 	return copied;
 }
 
@@ -621,10 +621,10 @@ static int populate_page(struct ubifs_info *c, struct page *page,
 
 	addr = zaddr = kmap(page);
 
-	end_index = (i_size - 1) >> PAGE_CACHE_SHIFT;
+	end_index = (i_size - 1) >> PAGE_SHIFT;
 	if (!i_size || page->index > end_index) {
 		hole = 1;
-		memset(addr, 0, PAGE_CACHE_SIZE);
+		memset(addr, 0, PAGE_SIZE);
 		goto out_hole;
 	}
 
@@ -673,7 +673,7 @@ static int populate_page(struct ubifs_info *c, struct page *page,
 	}
 
 	if (end_index == page->index) {
-		int len = i_size & (PAGE_CACHE_SIZE - 1);
+		int len = i_size & (PAGE_SIZE - 1);
 
 		if (len && len < read)
 			memset(zaddr + len, 0, read - len);
@@ -773,7 +773,7 @@ static int ubifs_do_bulk_read(struct ubifs_info *c, struct bu_info *bu,
 	isize = i_size_read(inode);
 	if (isize == 0)
 		goto out_free;
-	end_index = ((isize - 1) >> PAGE_CACHE_SHIFT);
+	end_index = ((isize - 1) >> PAGE_SHIFT);
 
 	for (page_idx = 1; page_idx < page_cnt; page_idx++) {
 		pgoff_t page_offset = offset + page_idx;
@@ -788,7 +788,7 @@ static int ubifs_do_bulk_read(struct ubifs_info *c, struct bu_info *bu,
 		if (!PageUptodate(page))
 			err = populate_page(c, page, bu, &n);
 		unlock_page(page);
-		page_cache_release(page);
+		put_page(page);
 		if (err)
 			break;
 	}
@@ -905,7 +905,7 @@ static int do_writepage(struct page *page, int len)
 #ifdef UBIFS_DEBUG
 	struct ubifs_inode *ui = ubifs_inode(inode);
 	spin_lock(&ui->ui_lock);
-	ubifs_assert(page->index <= ui->synced_i_size >> PAGE_CACHE_SHIFT);
+	ubifs_assert(page->index <= ui->synced_i_size >> PAGE_SHIFT);
 	spin_unlock(&ui->ui_lock);
 #endif
 
@@ -1001,8 +1001,8 @@ static int ubifs_writepage(struct page *page, struct writeback_control *wbc)
 	struct inode *inode = page->mapping->host;
 	struct ubifs_inode *ui = ubifs_inode(inode);
 	loff_t i_size =  i_size_read(inode), synced_i_size;
-	pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
-	int err, len = i_size & (PAGE_CACHE_SIZE - 1);
+	pgoff_t end_index = i_size >> PAGE_SHIFT;
+	int err, len = i_size & (PAGE_SIZE - 1);
 	void *kaddr;
 
 	dbg_gen("ino %lu, pg %lu, pg flags %#lx",
@@ -1021,7 +1021,7 @@ static int ubifs_writepage(struct page *page, struct writeback_control *wbc)
 
 	/* Is the page fully inside @i_size? */
 	if (page->index < end_index) {
-		if (page->index >= synced_i_size >> PAGE_CACHE_SHIFT) {
+		if (page->index >= synced_i_size >> PAGE_SHIFT) {
 			err = inode->i_sb->s_op->write_inode(inode, NULL);
 			if (err)
 				goto out_unlock;
@@ -1034,7 +1034,7 @@ static int ubifs_writepage(struct page *page, struct writeback_control *wbc)
 			 * with this.
 			 */
 		}
-		return do_writepage(page, PAGE_CACHE_SIZE);
+		return do_writepage(page, PAGE_SIZE);
 	}
 
 	/*
@@ -1045,7 +1045,7 @@ static int ubifs_writepage(struct page *page, struct writeback_control *wbc)
 	 * writes to that region are not written out to the file."
 	 */
 	kaddr = kmap_atomic(page);
-	memset(kaddr + len, 0, PAGE_CACHE_SIZE - len);
+	memset(kaddr + len, 0, PAGE_SIZE - len);
 	flush_dcache_page(page);
 	kunmap_atomic(kaddr);
 
@@ -1138,7 +1138,7 @@ static int do_truncation(struct ubifs_info *c, struct inode *inode,
 	truncate_setsize(inode, new_size);
 
 	if (offset) {
-		pgoff_t index = new_size >> PAGE_CACHE_SHIFT;
+		pgoff_t index = new_size >> PAGE_SHIFT;
 		struct page *page;
 
 		page = find_lock_page(inode->i_mapping, index);
@@ -1157,9 +1157,9 @@ static int do_truncation(struct ubifs_info *c, struct inode *inode,
 				clear_page_dirty_for_io(page);
 				if (UBIFS_BLOCKS_PER_PAGE_SHIFT)
 					offset = new_size &
-						 (PAGE_CACHE_SIZE - 1);
+						 (PAGE_SIZE - 1);
 				err = do_writepage(page, offset);
-				page_cache_release(page);
+				put_page(page);
 				if (err)
 					goto out_budg;
 				/*
@@ -1173,7 +1173,7 @@ static int do_truncation(struct ubifs_info *c, struct inode *inode,
 				 * having to read it.
 				 */
 				unlock_page(page);
-				page_cache_release(page);
+				put_page(page);
 			}
 		}
 	}
@@ -1285,7 +1285,7 @@ static void ubifs_invalidatepage(struct page *page, unsigned int offset,
 	struct ubifs_info *c = inode->i_sb->s_fs_info;
 
 	ubifs_assert(PagePrivate(page));
-	if (offset || length < PAGE_CACHE_SIZE)
+	if (offset || length < PAGE_SIZE)
 		/* Partial page remains dirty */
 		return;
 
@@ -1317,7 +1317,7 @@ int ubifs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	err = filemap_write_and_wait_range(inode->i_mapping, start, end);
 	if (err)
 		return err;
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	/* Synchronize the inode unless this is a 'datasync()' call. */
 	if (!datasync || (inode->i_state & I_DIRTY_DATASYNC)) {
@@ -1332,7 +1332,7 @@ int ubifs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	 */
 	err = ubifs_sync_wbufs_by_inode(c, inode);
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return err;
 }
 
@@ -1354,6 +1354,47 @@ static inline int mctime_update_needed(const struct inode *inode,
 	return 0;
 }
 
+#ifdef CONFIG_UBIFS_ATIME_SUPPORT
+/**
+ * ubifs_update_time - update time of inode.
+ * @inode: inode to update
+ *
+ * This function updates time of the inode.
+ */
+int ubifs_update_time(struct inode *inode, struct timespec *time,
+			     int flags)
+{
+	struct ubifs_inode *ui = ubifs_inode(inode);
+	struct ubifs_info *c = inode->i_sb->s_fs_info;
+	struct ubifs_budget_req req = { .dirtied_ino = 1,
+			.dirtied_ino_d = ALIGN(ui->data_len, 8) };
+	int iflags = I_DIRTY_TIME;
+	int err, release;
+
+	err = ubifs_budget_space(c, &req);
+	if (err)
+		return err;
+
+	mutex_lock(&ui->ui_mutex);
+	if (flags & S_ATIME)
+		inode->i_atime = *time;
+	if (flags & S_CTIME)
+		inode->i_ctime = *time;
+	if (flags & S_MTIME)
+		inode->i_mtime = *time;
+
+	if (!(inode->i_sb->s_flags & MS_LAZYTIME))
+		iflags |= I_DIRTY_SYNC;
+
+	release = ui->dirty;
+	__mark_inode_dirty(inode, iflags);
+	mutex_unlock(&ui->ui_mutex);
+	if (release)
+		ubifs_release_budget(c, &req);
+	return 0;
+}
+#endif
+
 /**
  * update_ctime - update mtime and ctime of an inode.
  * @inode: inode to update
@@ -1537,6 +1578,9 @@ static int ubifs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	if (err)
 		return err;
 	vma->vm_ops = &ubifs_file_vm_ops;
+#ifdef CONFIG_UBIFS_ATIME_SUPPORT
+	file_accessed(file);
+#endif
 	return 0;
 }
 
@@ -1557,17 +1601,23 @@ const struct inode_operations ubifs_file_inode_operations = {
 	.getxattr    = ubifs_getxattr,
 	.listxattr   = ubifs_listxattr,
 	.removexattr = ubifs_removexattr,
+#ifdef CONFIG_UBIFS_ATIME_SUPPORT
+	.update_time = ubifs_update_time,
+#endif
 };
 
 const struct inode_operations ubifs_symlink_inode_operations = {
 	.readlink    = generic_readlink,
-	.follow_link = simple_follow_link,
+	.get_link    = simple_get_link,
 	.setattr     = ubifs_setattr,
 	.getattr     = ubifs_getattr,
 	.setxattr    = ubifs_setxattr,
 	.getxattr    = ubifs_getxattr,
 	.listxattr   = ubifs_listxattr,
 	.removexattr = ubifs_removexattr,
+#ifdef CONFIG_UBIFS_ATIME_SUPPORT
+	.update_time = ubifs_update_time,
+#endif
 };
 
 const struct file_operations ubifs_file_operations = {
diff --git a/fs/ubifs/key.h b/fs/ubifs/key.h
index 92a8491a8f8c..c0a95e393347 100644
--- a/fs/ubifs/key.h
+++ b/fs/ubifs/key.h
@@ -34,6 +34,12 @@
  * node. We use "r5" hash borrowed from reiserfs.
  */
 
+/*
+ * Lot's of the key helpers require a struct ubifs_info *c as the first parameter.
+ * But we are not using it at all currently. That's designed for future extensions of
+ * different c->key_format. But right now, there is only one key type, UBIFS_SIMPLE_KEY_FMT.
+ */
+
 #ifndef __UBIFS_KEY_H__
 #define __UBIFS_KEY_H__
 
diff --git a/fs/ubifs/lpt.c b/fs/ubifs/lpt.c
index dc9f27e9d61b..9a517109da0f 100644
--- a/fs/ubifs/lpt.c
+++ b/fs/ubifs/lpt.c
@@ -1498,11 +1498,10 @@ static struct ubifs_nnode *dirty_cow_nnode(struct ubifs_info *c,
 	}
 
 	/* nnode is being committed, so copy it */
-	n = kmalloc(sizeof(struct ubifs_nnode), GFP_NOFS);
+	n = kmemdup(nnode, sizeof(struct ubifs_nnode), GFP_NOFS);
 	if (unlikely(!n))
 		return ERR_PTR(-ENOMEM);
 
-	memcpy(n, nnode, sizeof(struct ubifs_nnode));
 	n->cnext = NULL;
 	__set_bit(DIRTY_CNODE, &n->flags);
 	__clear_bit(COW_CNODE, &n->flags);
@@ -1549,11 +1548,10 @@ static struct ubifs_pnode *dirty_cow_pnode(struct ubifs_info *c,
 	}
 
 	/* pnode is being committed, so copy it */
-	p = kmalloc(sizeof(struct ubifs_pnode), GFP_NOFS);
+	p = kmemdup(pnode, sizeof(struct ubifs_pnode), GFP_NOFS);
 	if (unlikely(!p))
 		return ERR_PTR(-ENOMEM);
 
-	memcpy(p, pnode, sizeof(struct ubifs_pnode));
 	p->cnext = NULL;
 	__set_bit(DIRTY_CNODE, &p->flags);
 	__clear_bit(COW_CNODE, &p->flags);
diff --git a/fs/ubifs/misc.c b/fs/ubifs/misc.c
new file mode 100644
index 000000000000..486a2844949f
--- /dev/null
+++ b/fs/ubifs/misc.c
@@ -0,0 +1,57 @@
+#include <linux/kernel.h>
+#include "ubifs.h"
+
+/* Normal UBIFS messages */
+void ubifs_msg(const struct ubifs_info *c, const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	pr_notice("UBIFS (ubi%d:%d): %pV\n",
+		  c->vi.ubi_num, c->vi.vol_id, &vaf);
+
+	va_end(args);
+}								    \
+
+/* UBIFS error messages */
+void ubifs_err(const struct ubifs_info *c, const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	pr_err("UBIFS error (ubi%d:%d pid %d): %ps: %pV\n",
+	       c->vi.ubi_num, c->vi.vol_id, current->pid,
+	       __builtin_return_address(0),
+	       &vaf);
+
+	va_end(args);
+}								    \
+
+/* UBIFS warning messages */
+void ubifs_warn(const struct ubifs_info *c, const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	pr_warn("UBIFS warning (ubi%d:%d pid %d): %ps: %pV\n",
+		c->vi.ubi_num, c->vi.vol_id, current->pid,
+		__builtin_return_address(0),
+		&vaf);
+
+	va_end(args);
+}
diff --git a/fs/ubifs/misc.h b/fs/ubifs/misc.h
index ee7cb5ebb6e8..8ece6ca58c0b 100644
--- a/fs/ubifs/misc.h
+++ b/fs/ubifs/misc.h
@@ -155,13 +155,8 @@ static inline int ubifs_wbuf_sync(struct ubifs_wbuf *wbuf)
  */
 static inline int ubifs_encode_dev(union ubifs_dev_desc *dev, dev_t rdev)
 {
-	if (new_valid_dev(rdev)) {
-		dev->new = cpu_to_le32(new_encode_dev(rdev));
-		return sizeof(dev->new);
-	} else {
-		dev->huge = cpu_to_le64(huge_encode_dev(rdev));
-		return sizeof(dev->huge);
-	}
+	dev->new = cpu_to_le32(new_encode_dev(rdev));
+	return sizeof(dev->new);
 }
 
 /**
diff --git a/fs/ubifs/recovery.c b/fs/ubifs/recovery.c
index 695fc71d5244..586d59347fff 100644
--- a/fs/ubifs/recovery.c
+++ b/fs/ubifs/recovery.c
@@ -789,7 +789,7 @@ struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum,
 corrupted_rescan:
 	/* Re-scan the corrupted data with verbose messages */
 	ubifs_err(c, "corruption %d", ret);
-	ubifs_scan_a_node(c, buf, len, lnum, offs, 1);
+	ubifs_scan_a_node(c, buf, len, lnum, offs, 0);
 corrupted:
 	ubifs_scanned_corruption(c, lnum, offs, buf);
 	err = -EUCLEAN;
@@ -1331,8 +1331,7 @@ void ubifs_destroy_size_tree(struct ubifs_info *c)
 	struct size_entry *e, *n;
 
 	rbtree_postorder_for_each_entry_safe(e, n, &c->size_tree, rb) {
-		if (e->inode)
-			iput(e->inode);
+		iput(e->inode);
 		kfree(e);
 	}
 
@@ -1533,8 +1532,7 @@ int ubifs_recover_size(struct ubifs_info *c)
 				err = fix_size_in_place(c, e);
 				if (err)
 					return err;
-				if (e->inode)
-					iput(e->inode);
+				iput(e->inode);
 			}
 		}
 
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 9547a27868ad..e98c24ee25a1 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -128,7 +128,10 @@ struct inode *ubifs_iget(struct super_block *sb, unsigned long inum)
 	if (err)
 		goto out_ino;
 
-	inode->i_flags |= (S_NOCMTIME | S_NOATIME);
+	inode->i_flags |= S_NOCMTIME;
+#ifndef CONFIG_UBIFS_ATIME_SUPPORT
+	inode->i_flags |= S_NOATIME;
+#endif
 	set_nlink(inode, le32_to_cpu(ino->nlink));
 	i_uid_write(inode, le32_to_cpu(ino->uid));
 	i_gid_write(inode, le32_to_cpu(ino->gid));
@@ -2037,7 +2040,6 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
 	if (c->max_inode_sz > MAX_LFS_FILESIZE)
 		sb->s_maxbytes = c->max_inode_sz = MAX_LFS_FILESIZE;
 	sb->s_op = &ubifs_super_operations;
-	sb->s_xattr = ubifs_xattr_handlers;
 
 	mutex_lock(&c->umount_mutex);
 	err = mount_ubifs(c);
@@ -2139,7 +2141,12 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags,
 		if (err)
 			goto out_deact;
 		/* We do not support atime */
-		sb->s_flags |= MS_ACTIVE | MS_NOATIME;
+		sb->s_flags |= MS_ACTIVE;
+#ifndef CONFIG_UBIFS_ATIME_SUPPORT
+		sb->s_flags |= MS_NOATIME;
+#else
+		ubifs_msg(c, "full atime support is enabled.");
+#endif
 	}
 
 	/* 'fill_super()' opens ubi again so we must close it here */
@@ -2230,19 +2237,19 @@ static int __init ubifs_init(void)
 	BUILD_BUG_ON(UBIFS_COMPR_TYPES_CNT > 4);
 
 	/*
-	 * We require that PAGE_CACHE_SIZE is greater-than-or-equal-to
+	 * We require that PAGE_SIZE is greater-than-or-equal-to
 	 * UBIFS_BLOCK_SIZE. It is assumed that both are powers of 2.
 	 */
-	if (PAGE_CACHE_SIZE < UBIFS_BLOCK_SIZE) {
+	if (PAGE_SIZE < UBIFS_BLOCK_SIZE) {
 		pr_err("UBIFS error (pid %d): VFS page cache size is %u bytes, but UBIFS requires at least 4096 bytes",
-		       current->pid, (unsigned int)PAGE_CACHE_SIZE);
+		       current->pid, (unsigned int)PAGE_SIZE);
 		return -EINVAL;
 	}
 
 	ubifs_inode_slab = kmem_cache_create("ubifs_inode_slab",
 				sizeof(struct ubifs_inode), 0,
-				SLAB_MEM_SPREAD | SLAB_RECLAIM_ACCOUNT,
-				&inode_slab_ctor);
+				SLAB_MEM_SPREAD | SLAB_RECLAIM_ACCOUNT |
+				SLAB_ACCOUNT, &inode_slab_ctor);
 	if (!ubifs_inode_slab)
 		return -ENOMEM;
 
diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c
index 957f5757f374..fa9a20cc60d6 100644
--- a/fs/ubifs/tnc.c
+++ b/fs/ubifs/tnc.c
@@ -198,11 +198,10 @@ static struct ubifs_znode *copy_znode(struct ubifs_info *c,
 {
 	struct ubifs_znode *zn;
 
-	zn = kmalloc(c->max_znode_sz, GFP_NOFS);
+	zn = kmemdup(znode, c->max_znode_sz, GFP_NOFS);
 	if (unlikely(!zn))
 		return ERR_PTR(-ENOMEM);
 
-	memcpy(zn, znode, c->max_znode_sz);
 	zn->cnext = NULL;
 	__set_bit(DIRTY_ZNODE, &zn->flags);
 	__clear_bit(COW_ZNODE, &zn->flags);
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index de759022f3d6..4cd7e569cd00 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -42,36 +42,12 @@
 /* Version of this UBIFS implementation */
 #define UBIFS_VERSION 1
 
-/* Normal UBIFS messages */
-#define ubifs_msg(c, fmt, ...)                                      \
-	pr_notice("UBIFS (ubi%d:%d): " fmt "\n",                    \
-		  (c)->vi.ubi_num, (c)->vi.vol_id, ##__VA_ARGS__)
-/* UBIFS error messages */
-#define ubifs_err(c, fmt, ...)                                      \
-	pr_err("UBIFS error (ubi%d:%d pid %d): %s: " fmt "\n",      \
-	       (c)->vi.ubi_num, (c)->vi.vol_id, current->pid,       \
-	       __func__, ##__VA_ARGS__)
-/* UBIFS warning messages */
-#define ubifs_warn(c, fmt, ...)                                     \
-	pr_warn("UBIFS warning (ubi%d:%d pid %d): %s: " fmt "\n",   \
-		(c)->vi.ubi_num, (c)->vi.vol_id, current->pid,      \
-		__func__, ##__VA_ARGS__)
-/*
- * A variant of 'ubifs_err()' which takes the UBIFS file-sytem description
- * object as an argument.
- */
-#define ubifs_errc(c, fmt, ...)                                     \
-	do {                                                        \
-		if (!(c)->probing)                                  \
-			ubifs_err(c, fmt, ##__VA_ARGS__);           \
-	} while (0)
-
 /* UBIFS file system VFS magic number */
 #define UBIFS_SUPER_MAGIC 0x24051905
 
 /* Number of UBIFS blocks per VFS page */
-#define UBIFS_BLOCKS_PER_PAGE (PAGE_CACHE_SIZE / UBIFS_BLOCK_SIZE)
-#define UBIFS_BLOCKS_PER_PAGE_SHIFT (PAGE_CACHE_SHIFT - UBIFS_BLOCK_SHIFT)
+#define UBIFS_BLOCKS_PER_PAGE (PAGE_SIZE / UBIFS_BLOCK_SIZE)
+#define UBIFS_BLOCKS_PER_PAGE_SHIFT (PAGE_SHIFT - UBIFS_BLOCK_SHIFT)
 
 /* "File system end of life" sequence number watermark */
 #define SQNUM_WARN_WATERMARK 0xFFFFFFFF00000000ULL
@@ -858,9 +834,9 @@ struct ubifs_compressor {
  * @mod_dent: non-zero if the operation removes or modifies an existing
  *            directory entry
  * @new_ino: non-zero if the operation adds a new inode
- * @new_ino_d: now much data newly created inode contains
+ * @new_ino_d: how much data newly created inode contains
  * @dirtied_ino: how many inodes the operation makes dirty
- * @dirtied_ino_d: now much data dirtied inode contains
+ * @dirtied_ino_d: how much data dirtied inode contains
  * @idx_growth: how much the index will supposedly grow
  * @data_growth: how much new data the operation will supposedly add
  * @dd_growth: how much data that makes other data dirty the operation will
@@ -1470,7 +1446,6 @@ extern spinlock_t ubifs_infos_lock;
 extern atomic_long_t ubifs_clean_zn_cnt;
 extern struct kmem_cache *ubifs_inode_slab;
 extern const struct super_operations ubifs_super_operations;
-extern const struct xattr_handler *ubifs_xattr_handlers[];
 extern const struct address_space_operations ubifs_file_address_operations;
 extern const struct file_operations ubifs_file_operations;
 extern const struct inode_operations ubifs_file_inode_operations;
@@ -1746,6 +1721,9 @@ int ubifs_calc_dark(const struct ubifs_info *c, int spc);
 /* file.c */
 int ubifs_fsync(struct file *file, loff_t start, loff_t end, int datasync);
 int ubifs_setattr(struct dentry *dentry, struct iattr *attr);
+#ifdef CONFIG_UBIFS_ATIME_SUPPORT
+int ubifs_update_time(struct inode *inode, struct timespec *time, int flags);
+#endif
 
 /* dir.c */
 struct inode *ubifs_new_inode(struct ubifs_info *c, const struct inode *dir,
@@ -1800,4 +1778,21 @@ int ubifs_decompress(const struct ubifs_info *c, const void *buf, int len,
 #include "misc.h"
 #include "key.h"
 
+/* Normal UBIFS messages */
+__printf(2, 3)
+void ubifs_msg(const struct ubifs_info *c, const char *fmt, ...);
+__printf(2, 3)
+void ubifs_err(const struct ubifs_info *c, const char *fmt, ...);
+__printf(2, 3)
+void ubifs_warn(const struct ubifs_info *c, const char *fmt, ...);
+/*
+ * A variant of 'ubifs_err()' which takes the UBIFS file-sytem description
+ * object as an argument.
+ */
+#define ubifs_errc(c, fmt, ...)						\
+do {									\
+	if (!(c)->probing)						\
+		ubifs_err(c, fmt, ##__VA_ARGS__);			\
+} while (0)
+
 #endif /* !__UBIFS_H__ */
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index fd65b3f1923c..b043e044121d 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -59,7 +59,6 @@
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/xattr.h>
-#include <linux/posix_acl_xattr.h>
 
 /*
  * Limit the number of extended attributes per inode so that the total size
@@ -200,6 +199,7 @@ static int change_xattr(struct ubifs_info *c, struct inode *host,
 	int err;
 	struct ubifs_inode *host_ui = ubifs_inode(host);
 	struct ubifs_inode *ui = ubifs_inode(inode);
+	void *buf = NULL;
 	struct ubifs_budget_req req = { .dirtied_ino = 2,
 		.dirtied_ino_d = ALIGN(size, 8) + ALIGN(host_ui->data_len, 8) };
 
@@ -208,14 +208,17 @@ static int change_xattr(struct ubifs_info *c, struct inode *host,
 	if (err)
 		return err;
 
-	kfree(ui->data);
-	ui->data = kmemdup(value, size, GFP_NOFS);
-	if (!ui->data) {
+	buf = kmemdup(value, size, GFP_NOFS);
+	if (!buf) {
 		err = -ENOMEM;
 		goto out_free;
 	}
+	mutex_lock(&ui->ui_mutex);
+	kfree(ui->data);
+	ui->data = buf;
 	inode->i_size = ui->ui_size = size;
 	ui->data_len = size;
+	mutex_unlock(&ui->ui_mutex);
 
 	mutex_lock(&host_ui->ui_mutex);
 	host->i_ctime = ubifs_current_time(host);
@@ -263,7 +266,7 @@ static int check_namespace(const struct qstr *nm)
 
 	if (!strncmp(nm->name, XATTR_TRUSTED_PREFIX,
 		     XATTR_TRUSTED_PREFIX_LEN)) {
-		if (nm->name[sizeof(XATTR_TRUSTED_PREFIX) - 1] == '\0')
+		if (nm->name[XATTR_TRUSTED_PREFIX_LEN] == '\0')
 			return -EINVAL;
 		type = TRUSTED_XATTR;
 	} else if (!strncmp(nm->name, XATTR_USER_PREFIX,
@@ -273,7 +276,7 @@ static int check_namespace(const struct qstr *nm)
 		type = USER_XATTR;
 	} else if (!strncmp(nm->name, XATTR_SECURITY_PREFIX,
 				     XATTR_SECURITY_PREFIX_LEN)) {
-		if (nm->name[sizeof(XATTR_SECURITY_PREFIX) - 1] == '\0')
+		if (nm->name[XATTR_SECURITY_PREFIX_LEN] == '\0')
 			return -EINVAL;
 		type = SECURITY_XATTR;
 	} else
@@ -309,7 +312,7 @@ static int setxattr(struct inode *host, const char *name, const void *value,
 	union ubifs_key key;
 	int err, type;
 
-	ubifs_assert(mutex_is_locked(&host->i_mutex));
+	ubifs_assert(inode_is_locked(host));
 
 	if (size > UBIFS_MAX_INO_DATA)
 		return -ERANGE;
@@ -409,6 +412,7 @@ ssize_t ubifs_getxattr(struct dentry *dentry, const char *name, void *buf,
 	ubifs_assert(inode->i_size == ui->data_len);
 	ubifs_assert(ubifs_inode(host)->xattr_size > ui->data_len);
 
+	mutex_lock(&ui->ui_mutex);
 	if (buf) {
 		/* If @buf is %NULL we are supposed to return the length */
 		if (ui->data_len > size) {
@@ -423,6 +427,7 @@ ssize_t ubifs_getxattr(struct dentry *dentry, const char *name, void *buf,
 	err = ui->data_len;
 
 out_iput:
+	mutex_unlock(&ui->ui_mutex);
 	iput(inode);
 out_unlock:
 	kfree(xent);
@@ -544,7 +549,7 @@ int ubifs_removexattr(struct dentry *dentry, const char *name)
 
 	dbg_gen("xattr '%s', ino %lu ('%pd')", name,
 		host->i_ino, dentry);
-	ubifs_assert(mutex_is_locked(&host->i_mutex));
+	ubifs_assert(inode_is_locked(host));
 
 	err = check_namespace(&nm);
 	if (err < 0)
@@ -582,46 +587,6 @@ out_free:
 	return err;
 }
 
-static size_t security_listxattr(struct dentry *d, char *list, size_t list_size,
-				 const char *name, size_t name_len, int flags)
-{
-	const int prefix_len = XATTR_SECURITY_PREFIX_LEN;
-	const size_t total_len = prefix_len + name_len + 1;
-
-	if (list && total_len <= list_size) {
-		memcpy(list, XATTR_SECURITY_PREFIX, prefix_len);
-		memcpy(list + prefix_len, name, name_len);
-		list[prefix_len + name_len] = '\0';
-	}
-
-	return total_len;
-}
-
-static int security_getxattr(struct dentry *d, const char *name, void *buffer,
-		      size_t size, int flags)
-{
-	return ubifs_getxattr(d, name, buffer, size);
-}
-
-static int security_setxattr(struct dentry *d, const char *name,
-			     const void *value, size_t size, int flags,
-			     int handler_flags)
-{
-	return ubifs_setxattr(d, name, value, size, flags);
-}
-
-static const struct xattr_handler ubifs_xattr_security_handler = {
-	.prefix = XATTR_SECURITY_PREFIX,
-	.list   = security_listxattr,
-	.get    = security_getxattr,
-	.set    = security_setxattr,
-};
-
-const struct xattr_handler *ubifs_xattr_handlers[] = {
-	&ubifs_xattr_security_handler,
-	NULL,
-};
-
 static int init_xattrs(struct inode *inode, const struct xattr *xattr_array,
 		      void *fs_info)
 {
diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c
index 6d6a96b4e73f..e0fd65fe73e8 100644
--- a/fs/udf/balloc.c
+++ b/fs/udf/balloc.c
@@ -447,9 +447,6 @@ static void udf_table_free_blocks(struct super_block *sb,
 		 */
 
 		int adsize;
-		struct short_ad *sad = NULL;
-		struct long_ad *lad = NULL;
-		struct allocExtDesc *aed;
 
 		eloc.logicalBlockNum = start;
 		elen = EXT_RECORDED_ALLOCATED |
@@ -466,102 +463,17 @@ static void udf_table_free_blocks(struct super_block *sb,
 		}
 
 		if (epos.offset + (2 * adsize) > sb->s_blocksize) {
-			unsigned char *sptr, *dptr;
-			int loffset;
-
-			brelse(oepos.bh);
-			oepos = epos;
-
 			/* Steal a block from the extent being free'd */
-			epos.block.logicalBlockNum = eloc.logicalBlockNum;
+			udf_setup_indirect_aext(table, eloc.logicalBlockNum,
+						&epos);
+
 			eloc.logicalBlockNum++;
 			elen -= sb->s_blocksize;
-
-			epos.bh = udf_tread(sb,
-					udf_get_lb_pblock(sb, &epos.block, 0));
-			if (!epos.bh) {
-				brelse(oepos.bh);
-				goto error_return;
-			}
-			aed = (struct allocExtDesc *)(epos.bh->b_data);
-			aed->previousAllocExtLocation =
-				cpu_to_le32(oepos.block.logicalBlockNum);
-			if (epos.offset + adsize > sb->s_blocksize) {
-				loffset = epos.offset;
-				aed->lengthAllocDescs = cpu_to_le32(adsize);
-				sptr = iinfo->i_ext.i_data + epos.offset
-								- adsize;
-				dptr = epos.bh->b_data +
-					sizeof(struct allocExtDesc);
-				memcpy(dptr, sptr, adsize);
-				epos.offset = sizeof(struct allocExtDesc) +
-						adsize;
-			} else {
-				loffset = epos.offset + adsize;
-				aed->lengthAllocDescs = cpu_to_le32(0);
-				if (oepos.bh) {
-					sptr = oepos.bh->b_data + epos.offset;
-					aed = (struct allocExtDesc *)
-						oepos.bh->b_data;
-					le32_add_cpu(&aed->lengthAllocDescs,
-							adsize);
-				} else {
-					sptr = iinfo->i_ext.i_data +
-								epos.offset;
-					iinfo->i_lenAlloc += adsize;
-					mark_inode_dirty(table);
-				}
-				epos.offset = sizeof(struct allocExtDesc);
-			}
-			if (sbi->s_udfrev >= 0x0200)
-				udf_new_tag(epos.bh->b_data, TAG_IDENT_AED,
-					    3, 1, epos.block.logicalBlockNum,
-					    sizeof(struct tag));
-			else
-				udf_new_tag(epos.bh->b_data, TAG_IDENT_AED,
-					    2, 1, epos.block.logicalBlockNum,
-					    sizeof(struct tag));
-
-			switch (iinfo->i_alloc_type) {
-			case ICBTAG_FLAG_AD_SHORT:
-				sad = (struct short_ad *)sptr;
-				sad->extLength = cpu_to_le32(
-					EXT_NEXT_EXTENT_ALLOCDECS |
-					sb->s_blocksize);
-				sad->extPosition =
-					cpu_to_le32(epos.block.logicalBlockNum);
-				break;
-			case ICBTAG_FLAG_AD_LONG:
-				lad = (struct long_ad *)sptr;
-				lad->extLength = cpu_to_le32(
-					EXT_NEXT_EXTENT_ALLOCDECS |
-					sb->s_blocksize);
-				lad->extLocation =
-					cpu_to_lelb(epos.block);
-				break;
-			}
-			if (oepos.bh) {
-				udf_update_tag(oepos.bh->b_data, loffset);
-				mark_buffer_dirty(oepos.bh);
-			} else {
-				mark_inode_dirty(table);
-			}
 		}
 
 		/* It's possible that stealing the block emptied the extent */
-		if (elen) {
-			udf_write_aext(table, &epos, &eloc, elen, 1);
-
-			if (!epos.bh) {
-				iinfo->i_lenAlloc += adsize;
-				mark_inode_dirty(table);
-			} else {
-				aed = (struct allocExtDesc *)epos.bh->b_data;
-				le32_add_cpu(&aed->lengthAllocDescs, adsize);
-				udf_update_tag(epos.bh->b_data, epos.offset);
-				mark_buffer_dirty(epos.bh);
-			}
-		}
+		if (elen)
+			__udf_add_aext(table, &epos, &eloc, elen, 1);
 	}
 
 	brelse(epos.bh);
diff --git a/fs/udf/dir.c b/fs/udf/dir.c
index 541d9c65014d..b51b371b874a 100644
--- a/fs/udf/dir.c
+++ b/fs/udf/dir.c
@@ -45,7 +45,7 @@ static int udf_readdir(struct file *file, struct dir_context *ctx)
 	int block, iblock;
 	loff_t nf_pos;
 	int flen;
-	unsigned char *fname = NULL;
+	unsigned char *fname = NULL, *copy_name = NULL;
 	unsigned char *nameptr;
 	uint16_t liu;
 	uint8_t lfi;
@@ -143,7 +143,15 @@ static int udf_readdir(struct file *file, struct dir_context *ctx)
 			if (poffset >= lfi) {
 				nameptr = (char *)(fibh.ebh->b_data + poffset - lfi);
 			} else {
-				nameptr = fname;
+				if (!copy_name) {
+					copy_name = kmalloc(UDF_NAME_LEN,
+							    GFP_NOFS);
+					if (!copy_name) {
+						ret = -ENOMEM;
+						goto out;
+					}
+				}
+				nameptr = copy_name;
 				memcpy(nameptr, fi->fileIdent + liu,
 				       lfi - poffset);
 				memcpy(nameptr + lfi - poffset,
@@ -185,6 +193,7 @@ out:
 	brelse(fibh.sbh);
 	brelse(epos.bh);
 	kfree(fname);
+	kfree(copy_name);
 
 	return ret;
 }
diff --git a/fs/udf/file.c b/fs/udf/file.c
index bddf3d071dae..877ba1c9b461 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -46,7 +46,7 @@ static void __udf_adinicb_readpage(struct page *page)
 
 	kaddr = kmap(page);
 	memcpy(kaddr, iinfo->i_ext.i_data + iinfo->i_lenEAttr, inode->i_size);
-	memset(kaddr + inode->i_size, 0, PAGE_CACHE_SIZE - inode->i_size);
+	memset(kaddr + inode->i_size, 0, PAGE_SIZE - inode->i_size);
 	flush_dcache_page(page);
 	SetPageUptodate(page);
 	kunmap(page);
@@ -87,14 +87,14 @@ static int udf_adinicb_write_begin(struct file *file,
 {
 	struct page *page;
 
-	if (WARN_ON_ONCE(pos >= PAGE_CACHE_SIZE))
+	if (WARN_ON_ONCE(pos >= PAGE_SIZE))
 		return -EIO;
 	page = grab_cache_page_write_begin(mapping, 0, flags);
 	if (!page)
 		return -ENOMEM;
 	*pagep = page;
 
-	if (!PageUptodate(page) && len != PAGE_CACHE_SIZE)
+	if (!PageUptodate(page) && len != PAGE_SIZE)
 		__udf_adinicb_readpage(page);
 	return 0;
 }
@@ -122,7 +122,7 @@ static ssize_t udf_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct udf_inode_info *iinfo = UDF_I(inode);
 	int err;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	retval = generic_write_checks(iocb, from);
 	if (retval <= 0)
@@ -136,7 +136,7 @@ static ssize_t udf_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 				(udf_file_entry_alloc_offset(inode) + end)) {
 			err = udf_expand_file_adinicb(inode);
 			if (err) {
-				mutex_unlock(&inode->i_mutex);
+				inode_unlock(inode);
 				udf_debug("udf_expand_adinicb: err=%d\n", err);
 				return err;
 			}
@@ -149,7 +149,7 @@ static ssize_t udf_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 
 	retval = __generic_file_write_iter(iocb, from);
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	if (retval > 0) {
 		mark_inode_dirty(inode);
@@ -223,12 +223,12 @@ static int udf_release_file(struct inode *inode, struct file *filp)
 		 * Grab i_mutex to avoid races with writes changing i_size
 		 * while we are running.
 		 */
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		down_write(&UDF_I(inode)->i_data_sem);
 		udf_discard_prealloc(inode);
 		udf_truncate_tail_extent(inode);
 		up_write(&UDF_I(inode)->i_data_sem);
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 	}
 	return 0;
 }
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 8d0b3ade0ff0..2dc461eeb415 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -262,7 +262,7 @@ int udf_expand_file_adinicb(struct inode *inode)
 		.nr_to_write = 1,
 	};
 
-	WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex));
+	WARN_ON_ONCE(!inode_is_locked(inode));
 	if (!iinfo->i_lenAlloc) {
 		if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_SHORT_AD))
 			iinfo->i_alloc_type = ICBTAG_FLAG_AD_SHORT;
@@ -287,7 +287,7 @@ int udf_expand_file_adinicb(struct inode *inode)
 	if (!PageUptodate(page)) {
 		kaddr = kmap(page);
 		memset(kaddr + iinfo->i_lenAlloc, 0x00,
-		       PAGE_CACHE_SIZE - iinfo->i_lenAlloc);
+		       PAGE_SIZE - iinfo->i_lenAlloc);
 		memcpy(kaddr, iinfo->i_ext.i_data + iinfo->i_lenEAttr,
 			iinfo->i_lenAlloc);
 		flush_dcache_page(page);
@@ -319,7 +319,7 @@ int udf_expand_file_adinicb(struct inode *inode)
 		inode->i_data.a_ops = &udf_adinicb_aops;
 		up_write(&iinfo->i_data_sem);
 	}
-	page_cache_release(page);
+	put_page(page);
 	mark_inode_dirty(inode);
 
 	return err;
@@ -539,9 +539,18 @@ static int udf_do_extend_file(struct inode *inode,
 		udf_add_aext(inode, last_pos, &last_ext->extLocation,
 			     last_ext->extLength, 1);
 		count++;
-	} else
+	} else {
+		struct kernel_lb_addr tmploc;
+		uint32_t tmplen;
+
 		udf_write_aext(inode, last_pos, &last_ext->extLocation,
 				last_ext->extLength, 1);
+		/*
+		 * We've rewritten the last extent but there may be empty
+		 * indirect extent after it - enter it.
+		 */
+		udf_next_aext(inode, last_pos, &tmploc, &tmplen, 0);
+	}
 
 	/* Managed to do everything necessary? */
 	if (!blocks)
@@ -1540,7 +1549,8 @@ reread:
 		break;
 	case ICBTAG_FILE_TYPE_SYMLINK:
 		inode->i_data.a_ops = &udf_symlink_aops;
-		inode->i_op = &udf_symlink_inode_operations;
+		inode->i_op = &page_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mode = S_IFLNK | S_IRWXUGO;
 		break;
 	case ICBTAG_FILE_TYPE_MAIN:
@@ -1866,22 +1876,90 @@ struct inode *__udf_iget(struct super_block *sb, struct kernel_lb_addr *ino,
 	return inode;
 }
 
-int udf_add_aext(struct inode *inode, struct extent_position *epos,
-		 struct kernel_lb_addr *eloc, uint32_t elen, int inc)
+int udf_setup_indirect_aext(struct inode *inode, int block,
+			    struct extent_position *epos)
 {
-	int adsize;
-	struct short_ad *sad = NULL;
-	struct long_ad *lad = NULL;
+	struct super_block *sb = inode->i_sb;
+	struct buffer_head *bh;
 	struct allocExtDesc *aed;
-	uint8_t *ptr;
-	struct udf_inode_info *iinfo = UDF_I(inode);
+	struct extent_position nepos;
+	struct kernel_lb_addr neloc;
+	int ver, adsize;
 
-	if (!epos->bh)
-		ptr = iinfo->i_ext.i_data + epos->offset -
-			udf_file_entry_alloc_offset(inode) +
-			iinfo->i_lenEAttr;
+	if (UDF_I(inode)->i_alloc_type == ICBTAG_FLAG_AD_SHORT)
+		adsize = sizeof(struct short_ad);
+	else if (UDF_I(inode)->i_alloc_type == ICBTAG_FLAG_AD_LONG)
+		adsize = sizeof(struct long_ad);
 	else
-		ptr = epos->bh->b_data + epos->offset;
+		return -EIO;
+
+	neloc.logicalBlockNum = block;
+	neloc.partitionReferenceNum = epos->block.partitionReferenceNum;
+
+	bh = udf_tgetblk(sb, udf_get_lb_pblock(sb, &neloc, 0));
+	if (!bh)
+		return -EIO;
+	lock_buffer(bh);
+	memset(bh->b_data, 0x00, sb->s_blocksize);
+	set_buffer_uptodate(bh);
+	unlock_buffer(bh);
+	mark_buffer_dirty_inode(bh, inode);
+
+	aed = (struct allocExtDesc *)(bh->b_data);
+	if (!UDF_QUERY_FLAG(sb, UDF_FLAG_STRICT)) {
+		aed->previousAllocExtLocation =
+				cpu_to_le32(epos->block.logicalBlockNum);
+	}
+	aed->lengthAllocDescs = cpu_to_le32(0);
+	if (UDF_SB(sb)->s_udfrev >= 0x0200)
+		ver = 3;
+	else
+		ver = 2;
+	udf_new_tag(bh->b_data, TAG_IDENT_AED, ver, 1, block,
+		    sizeof(struct tag));
+
+	nepos.block = neloc;
+	nepos.offset = sizeof(struct allocExtDesc);
+	nepos.bh = bh;
+
+	/*
+	 * Do we have to copy current last extent to make space for indirect
+	 * one?
+	 */
+	if (epos->offset + adsize > sb->s_blocksize) {
+		struct kernel_lb_addr cp_loc;
+		uint32_t cp_len;
+		int cp_type;
+
+		epos->offset -= adsize;
+		cp_type = udf_current_aext(inode, epos, &cp_loc, &cp_len, 0);
+		cp_len |= ((uint32_t)cp_type) << 30;
+
+		__udf_add_aext(inode, &nepos, &cp_loc, cp_len, 1);
+		udf_write_aext(inode, epos, &nepos.block,
+			       sb->s_blocksize | EXT_NEXT_EXTENT_ALLOCDECS, 0);
+	} else {
+		__udf_add_aext(inode, epos, &nepos.block,
+			       sb->s_blocksize | EXT_NEXT_EXTENT_ALLOCDECS, 0);
+	}
+
+	brelse(epos->bh);
+	*epos = nepos;
+
+	return 0;
+}
+
+/*
+ * Append extent at the given position - should be the first free one in inode
+ * / indirect extent. This function assumes there is enough space in the inode
+ * or indirect extent. Use udf_add_aext() if you didn't check for this before.
+ */
+int __udf_add_aext(struct inode *inode, struct extent_position *epos,
+		   struct kernel_lb_addr *eloc, uint32_t elen, int inc)
+{
+	struct udf_inode_info *iinfo = UDF_I(inode);
+	struct allocExtDesc *aed;
+	int adsize;
 
 	if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT)
 		adsize = sizeof(struct short_ad);
@@ -1890,88 +1968,14 @@ int udf_add_aext(struct inode *inode, struct extent_position *epos,
 	else
 		return -EIO;
 
-	if (epos->offset + (2 * adsize) > inode->i_sb->s_blocksize) {
-		unsigned char *sptr, *dptr;
-		struct buffer_head *nbh;
-		int err, loffset;
-		struct kernel_lb_addr obloc = epos->block;
-
-		epos->block.logicalBlockNum = udf_new_block(inode->i_sb, NULL,
-						obloc.partitionReferenceNum,
-						obloc.logicalBlockNum, &err);
-		if (!epos->block.logicalBlockNum)
-			return -ENOSPC;
-		nbh = udf_tgetblk(inode->i_sb, udf_get_lb_pblock(inode->i_sb,
-								 &epos->block,
-								 0));
-		if (!nbh)
-			return -EIO;
-		lock_buffer(nbh);
-		memset(nbh->b_data, 0x00, inode->i_sb->s_blocksize);
-		set_buffer_uptodate(nbh);
-		unlock_buffer(nbh);
-		mark_buffer_dirty_inode(nbh, inode);
-
-		aed = (struct allocExtDesc *)(nbh->b_data);
-		if (!UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_STRICT))
-			aed->previousAllocExtLocation =
-					cpu_to_le32(obloc.logicalBlockNum);
-		if (epos->offset + adsize > inode->i_sb->s_blocksize) {
-			loffset = epos->offset;
-			aed->lengthAllocDescs = cpu_to_le32(adsize);
-			sptr = ptr - adsize;
-			dptr = nbh->b_data + sizeof(struct allocExtDesc);
-			memcpy(dptr, sptr, adsize);
-			epos->offset = sizeof(struct allocExtDesc) + adsize;
-		} else {
-			loffset = epos->offset + adsize;
-			aed->lengthAllocDescs = cpu_to_le32(0);
-			sptr = ptr;
-			epos->offset = sizeof(struct allocExtDesc);
-
-			if (epos->bh) {
-				aed = (struct allocExtDesc *)epos->bh->b_data;
-				le32_add_cpu(&aed->lengthAllocDescs, adsize);
-			} else {
-				iinfo->i_lenAlloc += adsize;
-				mark_inode_dirty(inode);
-			}
-		}
-		if (UDF_SB(inode->i_sb)->s_udfrev >= 0x0200)
-			udf_new_tag(nbh->b_data, TAG_IDENT_AED, 3, 1,
-				    epos->block.logicalBlockNum, sizeof(struct tag));
-		else
-			udf_new_tag(nbh->b_data, TAG_IDENT_AED, 2, 1,
-				    epos->block.logicalBlockNum, sizeof(struct tag));
-		switch (iinfo->i_alloc_type) {
-		case ICBTAG_FLAG_AD_SHORT:
-			sad = (struct short_ad *)sptr;
-			sad->extLength = cpu_to_le32(EXT_NEXT_EXTENT_ALLOCDECS |
-						     inode->i_sb->s_blocksize);
-			sad->extPosition =
-				cpu_to_le32(epos->block.logicalBlockNum);
-			break;
-		case ICBTAG_FLAG_AD_LONG:
-			lad = (struct long_ad *)sptr;
-			lad->extLength = cpu_to_le32(EXT_NEXT_EXTENT_ALLOCDECS |
-						     inode->i_sb->s_blocksize);
-			lad->extLocation = cpu_to_lelb(epos->block);
-			memset(lad->impUse, 0x00, sizeof(lad->impUse));
-			break;
-		}
-		if (epos->bh) {
-			if (!UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_STRICT) ||
-			    UDF_SB(inode->i_sb)->s_udfrev >= 0x0201)
-				udf_update_tag(epos->bh->b_data, loffset);
-			else
-				udf_update_tag(epos->bh->b_data,
-						sizeof(struct allocExtDesc));
-			mark_buffer_dirty_inode(epos->bh, inode);
-			brelse(epos->bh);
-		} else {
-			mark_inode_dirty(inode);
-		}
-		epos->bh = nbh;
+	if (!epos->bh) {
+		WARN_ON(iinfo->i_lenAlloc !=
+			epos->offset - udf_file_entry_alloc_offset(inode));
+	} else {
+		aed = (struct allocExtDesc *)epos->bh->b_data;
+		WARN_ON(le32_to_cpu(aed->lengthAllocDescs) !=
+			epos->offset - sizeof(struct allocExtDesc));
+		WARN_ON(epos->offset + adsize > inode->i_sb->s_blocksize);
 	}
 
 	udf_write_aext(inode, epos, eloc, elen, inc);
@@ -1995,6 +1999,41 @@ int udf_add_aext(struct inode *inode, struct extent_position *epos,
 	return 0;
 }
 
+/*
+ * Append extent at given position - should be the first free one in inode
+ * / indirect extent. Takes care of allocating and linking indirect blocks.
+ */
+int udf_add_aext(struct inode *inode, struct extent_position *epos,
+		 struct kernel_lb_addr *eloc, uint32_t elen, int inc)
+{
+	int adsize;
+	struct super_block *sb = inode->i_sb;
+
+	if (UDF_I(inode)->i_alloc_type == ICBTAG_FLAG_AD_SHORT)
+		adsize = sizeof(struct short_ad);
+	else if (UDF_I(inode)->i_alloc_type == ICBTAG_FLAG_AD_LONG)
+		adsize = sizeof(struct long_ad);
+	else
+		return -EIO;
+
+	if (epos->offset + (2 * adsize) > sb->s_blocksize) {
+		int err;
+		int new_block;
+
+		new_block = udf_new_block(sb, NULL,
+					  epos->block.partitionReferenceNum,
+					  epos->block.logicalBlockNum, &err);
+		if (!new_block)
+			return -ENOSPC;
+
+		err = udf_setup_indirect_aext(inode, new_block, epos);
+		if (err)
+			return err;
+	}
+
+	return __udf_add_aext(inode, epos, eloc, elen, inc);
+}
+
 void udf_write_aext(struct inode *inode, struct extent_position *epos,
 		    struct kernel_lb_addr *eloc, uint32_t elen, int inc)
 {
@@ -2047,14 +2086,29 @@ void udf_write_aext(struct inode *inode, struct extent_position *epos,
 		epos->offset += adsize;
 }
 
+/*
+ * Only 1 indirect extent in a row really makes sense but allow upto 16 in case
+ * someone does some weird stuff.
+ */
+#define UDF_MAX_INDIR_EXTS 16
+
 int8_t udf_next_aext(struct inode *inode, struct extent_position *epos,
 		     struct kernel_lb_addr *eloc, uint32_t *elen, int inc)
 {
 	int8_t etype;
+	unsigned int indirections = 0;
 
 	while ((etype = udf_current_aext(inode, epos, eloc, elen, inc)) ==
 	       (EXT_NEXT_EXTENT_ALLOCDECS >> 30)) {
 		int block;
+
+		if (++indirections > UDF_MAX_INDIR_EXTS) {
+			udf_err(inode->i_sb,
+				"too many indirect extents in inode %lu\n",
+				inode->i_ino);
+			return -1;
+		}
+
 		epos->block = *eloc;
 		epos->offset = sizeof(struct allocExtDesc);
 		brelse(epos->bh);
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index c97b5a8d1e24..a2ba11eca995 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -165,7 +165,7 @@ static struct fileIdentDesc *udf_find_entry(struct inode *dir,
 	struct fileIdentDesc *fi = NULL;
 	loff_t f_pos;
 	int block, flen;
-	unsigned char *fname = NULL;
+	unsigned char *fname = NULL, *copy_name = NULL;
 	unsigned char *nameptr;
 	uint8_t lfi;
 	uint16_t liu;
@@ -236,7 +236,15 @@ static struct fileIdentDesc *udf_find_entry(struct inode *dir,
 				nameptr = (uint8_t *)(fibh->ebh->b_data +
 						      poffset - lfi);
 			else {
-				nameptr = fname;
+				if (!copy_name) {
+					copy_name = kmalloc(UDF_NAME_LEN,
+							    GFP_NOFS);
+					if (!copy_name) {
+						fi = ERR_PTR(-ENOMEM);
+						goto out_err;
+					}
+				}
+				nameptr = copy_name;
 				memcpy(nameptr, fi->fileIdent + liu,
 					lfi - poffset);
 				memcpy(nameptr + lfi - poffset,
@@ -279,6 +287,7 @@ out_err:
 out_ok:
 	brelse(epos.bh);
 	kfree(fname);
+	kfree(copy_name);
 
 	return fi;
 }
@@ -291,7 +300,7 @@ static struct dentry *udf_lookup(struct inode *dir, struct dentry *dentry,
 	struct udf_fileident_bh fibh;
 	struct fileIdentDesc *fi;
 
-	if (dentry->d_name.len > UDF_NAME_LEN - 2)
+	if (dentry->d_name.len > UDF_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
 #ifdef UDF_RECOVERY
@@ -351,7 +360,7 @@ static struct fileIdentDesc *udf_add_entry(struct inode *dir,
 	struct udf_inode_info *dinfo;
 
 	fibh->sbh = fibh->ebh = NULL;
-	name = kmalloc(UDF_NAME_LEN, GFP_NOFS);
+	name = kmalloc(UDF_NAME_LEN_CS0, GFP_NOFS);
 	if (!name) {
 		*err = -ENOMEM;
 		goto out_err;
@@ -362,8 +371,9 @@ static struct fileIdentDesc *udf_add_entry(struct inode *dir,
 			*err = -EINVAL;
 			goto out_err;
 		}
-		namelen = udf_put_filename(sb, dentry->d_name.name, name,
-						 dentry->d_name.len);
+		namelen = udf_put_filename(sb, dentry->d_name.name,
+					   dentry->d_name.len,
+					   name, UDF_NAME_LEN_CS0);
 		if (!namelen) {
 			*err = -ENAMETOOLONG;
 			goto out_err;
@@ -914,14 +924,15 @@ static int udf_symlink(struct inode *dir, struct dentry *dentry,
 
 	iinfo = UDF_I(inode);
 	down_write(&iinfo->i_data_sem);
-	name = kmalloc(UDF_NAME_LEN, GFP_NOFS);
+	name = kmalloc(UDF_NAME_LEN_CS0, GFP_NOFS);
 	if (!name) {
 		err = -ENOMEM;
 		goto out_no_entry;
 	}
 
 	inode->i_data.a_ops = &udf_symlink_aops;
-	inode->i_op = &udf_symlink_inode_operations;
+	inode->i_op = &page_symlink_inode_operations;
+	inode_nohighmem(inode);
 
 	if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) {
 		struct kernel_lb_addr eloc;
@@ -996,8 +1007,9 @@ static int udf_symlink(struct inode *dir, struct dentry *dentry,
 		}
 
 		if (pc->componentType == 5) {
-			namelen = udf_put_filename(sb, compstart, name,
-						   symname - compstart);
+			namelen = udf_put_filename(sb, compstart,
+						   symname - compstart,
+						   name, UDF_NAME_LEN_CS0);
 			if (!namelen)
 				goto out_no_entry;
 
@@ -1344,8 +1356,3 @@ const struct inode_operations udf_dir_inode_operations = {
 	.rename				= udf_rename,
 	.tmpfile			= udf_tmpfile,
 };
-const struct inode_operations udf_symlink_inode_operations = {
-	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
-};
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 81155b9b445b..fa92fe839fda 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -179,7 +179,8 @@ static int __init init_inodecache(void)
 	udf_inode_cachep = kmem_cache_create("udf_inode_cache",
 					     sizeof(struct udf_inode_info),
 					     0, (SLAB_RECLAIM_ACCOUNT |
-						 SLAB_MEM_SPREAD),
+						 SLAB_MEM_SPREAD |
+						 SLAB_ACCOUNT),
 					     init_once);
 	if (!udf_inode_cachep)
 		return -ENOMEM;
@@ -278,17 +279,12 @@ static void udf_sb_free_bitmap(struct udf_bitmap *bitmap)
 {
 	int i;
 	int nr_groups = bitmap->s_nr_groups;
-	int size = sizeof(struct udf_bitmap) + (sizeof(struct buffer_head *) *
-						nr_groups);
 
 	for (i = 0; i < nr_groups; i++)
 		if (bitmap->s_block_bitmap[i])
 			brelse(bitmap->s_block_bitmap[i]);
 
-	if (size <= PAGE_SIZE)
-		kfree(bitmap);
-	else
-		vfree(bitmap);
+	kvfree(bitmap);
 }
 
 static void udf_free_partition(struct udf_part_map *map)
@@ -891,18 +887,14 @@ static int udf_find_fileset(struct super_block *sb,
 static int udf_load_pvoldesc(struct super_block *sb, sector_t block)
 {
 	struct primaryVolDesc *pvoldesc;
-	struct ustr *instr, *outstr;
+	uint8_t *outstr;
 	struct buffer_head *bh;
 	uint16_t ident;
 	int ret = -ENOMEM;
 
-	instr = kmalloc(sizeof(struct ustr), GFP_NOFS);
-	if (!instr)
-		return -ENOMEM;
-
-	outstr = kmalloc(sizeof(struct ustr), GFP_NOFS);
+	outstr = kmalloc(128, GFP_NOFS);
 	if (!outstr)
-		goto out1;
+		return -ENOMEM;
 
 	bh = udf_read_tagged(sb, block, block, &ident);
 	if (!bh) {
@@ -927,31 +919,25 @@ static int udf_load_pvoldesc(struct super_block *sb, sector_t block)
 #endif
 	}
 
-	if (!udf_build_ustr(instr, pvoldesc->volIdent, 32)) {
-		ret = udf_CS0toUTF8(outstr, instr);
-		if (ret < 0)
-			goto out_bh;
+	ret = udf_CS0toUTF8(outstr, 31, pvoldesc->volIdent, 32);
+	if (ret < 0)
+		goto out_bh;
 
-		strncpy(UDF_SB(sb)->s_volume_ident, outstr->u_name,
-			outstr->u_len > 31 ? 31 : outstr->u_len);
-		udf_debug("volIdent[] = '%s'\n", UDF_SB(sb)->s_volume_ident);
-	}
+	strncpy(UDF_SB(sb)->s_volume_ident, outstr, ret);
+	udf_debug("volIdent[] = '%s'\n", UDF_SB(sb)->s_volume_ident);
 
-	if (!udf_build_ustr(instr, pvoldesc->volSetIdent, 128)) {
-		ret = udf_CS0toUTF8(outstr, instr);
-		if (ret < 0)
-			goto out_bh;
+	ret = udf_CS0toUTF8(outstr, 127, pvoldesc->volSetIdent, 128);
+	if (ret < 0)
+		goto out_bh;
 
-		udf_debug("volSetIdent[] = '%s'\n", outstr->u_name);
-	}
+	outstr[ret] = 0;
+	udf_debug("volSetIdent[] = '%s'\n", outstr);
 
 	ret = 0;
 out_bh:
 	brelse(bh);
 out2:
 	kfree(outstr);
-out1:
-	kfree(instr);
 	return ret;
 }
 
@@ -1586,6 +1572,13 @@ static void udf_load_logicalvolint(struct super_block *sb, struct kernel_extent_
 }
 
 /*
+ * Maximum number of Terminating Descriptor redirections. The chosen number is
+ * arbitrary - just that we hopefully don't limit any real use of rewritten
+ * inode on write-once media but avoid looping for too long on corrupted media.
+ */
+#define UDF_MAX_TD_NESTING 64
+
+/*
  * Process a main/reserve volume descriptor sequence.
  *   @block		First block of first extent of the sequence.
  *   @lastblock		Lastblock of first extent of the sequence.
@@ -1609,6 +1602,7 @@ static noinline int udf_process_sequence(
 	uint16_t ident;
 	long next_s = 0, next_e = 0;
 	int ret;
+	unsigned int indirections = 0;
 
 	memset(vds, 0, sizeof(struct udf_vds_record) * VDS_POS_LENGTH);
 
@@ -1679,6 +1673,12 @@ static noinline int udf_process_sequence(
 			}
 			break;
 		case TAG_IDENT_TD: /* ISO 13346 3/10.9 */
+			if (++indirections > UDF_MAX_TD_NESTING) {
+				udf_err(sb, "too many TDs (max %u supported)\n", UDF_MAX_TD_NESTING);
+				brelse(bh);
+				return -EIO;
+			}
+
 			vds[VDS_POS_TERMINATING_DESC].block = block;
 			if (next_e) {
 				block = next_s;
@@ -2348,7 +2348,7 @@ static int udf_statfs(struct dentry *dentry, struct kstatfs *buf)
 					  le32_to_cpu(lvidiu->numDirs)) : 0)
 			+ buf->f_bfree;
 	buf->f_ffree = buf->f_bfree;
-	buf->f_namelen = UDF_NAME_LEN - 2;
+	buf->f_namelen = UDF_NAME_LEN;
 	buf->f_fsid.val[0] = (u32)id;
 	buf->f_fsid.val[1] = (u32)(id >> 32);
 
diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c
index 862535b3ba58..8d619773056b 100644
--- a/fs/udf/symlink.c
+++ b/fs/udf/symlink.c
@@ -107,7 +107,7 @@ static int udf_symlink_filler(struct file *file, struct page *page)
 	struct buffer_head *bh = NULL;
 	unsigned char *symlink;
 	int err;
-	unsigned char *p = kmap(page);
+	unsigned char *p = page_address(page);
 	struct udf_inode_info *iinfo;
 	uint32_t pos;
 
@@ -141,7 +141,6 @@ static int udf_symlink_filler(struct file *file, struct page *page)
 
 	up_read(&iinfo->i_data_sem);
 	SetPageUptodate(page);
-	kunmap(page);
 	unlock_page(page);
 	return 0;
 
@@ -149,7 +148,6 @@ out_unlock_inode:
 	up_read(&iinfo->i_data_sem);
 	SetPageError(page);
 out_unmap:
-	kunmap(page);
 	unlock_page(page);
 	return err;
 }
diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h
index 47bb3f5ca360..972b70625614 100644
--- a/fs/udf/udfdecl.h
+++ b/fs/udf/udfdecl.h
@@ -49,8 +49,8 @@ extern __printf(3, 4) void _udf_warn(struct super_block *sb,
 #define UDF_EXTENT_FLAG_MASK	0xC0000000
 
 #define UDF_NAME_PAD		4
-#define UDF_NAME_LEN		256
-#define UDF_PATH_LEN		1023
+#define UDF_NAME_LEN		254
+#define UDF_NAME_LEN_CS0	255
 
 static inline size_t udf_file_entry_alloc_offset(struct inode *inode)
 {
@@ -85,7 +85,6 @@ extern const struct inode_operations udf_dir_inode_operations;
 extern const struct file_operations udf_dir_operations;
 extern const struct inode_operations udf_file_inode_operations;
 extern const struct file_operations udf_file_operations;
-extern const struct inode_operations udf_symlink_inode_operations;
 extern const struct address_space_operations udf_aops;
 extern const struct address_space_operations udf_adinicb_aops;
 extern const struct address_space_operations udf_symlink_aops;
@@ -107,12 +106,6 @@ struct generic_desc {
 	__le32		volDescSeqNum;
 };
 
-struct ustr {
-	uint8_t u_cmpID;
-	uint8_t u_name[UDF_NAME_LEN - 2];
-	uint8_t u_len;
-};
-
 
 /* super.c */
 
@@ -159,6 +152,10 @@ extern int udf_write_inode(struct inode *, struct writeback_control *wbc);
 extern long udf_block_map(struct inode *, sector_t);
 extern int8_t inode_bmap(struct inode *, sector_t, struct extent_position *,
 			 struct kernel_lb_addr *, uint32_t *, sector_t *);
+extern int udf_setup_indirect_aext(struct inode *inode, int block,
+				   struct extent_position *epos);
+extern int __udf_add_aext(struct inode *inode, struct extent_position *epos,
+			  struct kernel_lb_addr *eloc, uint32_t elen, int inc);
 extern int udf_add_aext(struct inode *, struct extent_position *,
 			struct kernel_lb_addr *, uint32_t, int);
 extern void udf_write_aext(struct inode *, struct extent_position *,
@@ -211,12 +208,11 @@ udf_get_lb_pblock(struct super_block *sb, struct kernel_lb_addr *loc,
 }
 
 /* unicode.c */
-extern int udf_get_filename(struct super_block *, uint8_t *, int, uint8_t *,
-			    int);
-extern int udf_put_filename(struct super_block *, const uint8_t *, uint8_t *,
-			    int);
-extern int udf_build_ustr(struct ustr *, dstring *, int);
-extern int udf_CS0toUTF8(struct ustr *, const struct ustr *);
+extern int udf_get_filename(struct super_block *, const uint8_t *, int,
+			    uint8_t *, int);
+extern int udf_put_filename(struct super_block *, const uint8_t *, int,
+			    uint8_t *, int);
+extern int udf_CS0toUTF8(uint8_t *, int, const uint8_t *, int);
 
 /* ialloc.c */
 extern void udf_free_inode(struct inode *);
diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c
index ab478e62baae..3ff42f4437f3 100644
--- a/fs/udf/unicode.c
+++ b/fs/udf/unicode.c
@@ -28,190 +28,72 @@
 
 #include "udf_sb.h"
 
-static int udf_translate_to_linux(uint8_t *, int, uint8_t *, int, uint8_t *,
-				  int);
-
-static int udf_char_to_ustr(struct ustr *dest, const uint8_t *src, int strlen)
-{
-	if ((!dest) || (!src) || (!strlen) || (strlen > UDF_NAME_LEN - 2))
-		return 0;
-
-	memset(dest, 0, sizeof(struct ustr));
-	memcpy(dest->u_name, src, strlen);
-	dest->u_cmpID = 0x08;
-	dest->u_len = strlen;
-
-	return strlen;
-}
-
-/*
- * udf_build_ustr
- */
-int udf_build_ustr(struct ustr *dest, dstring *ptr, int size)
+static int udf_uni2char_utf8(wchar_t uni,
+			     unsigned char *out,
+			     int boundlen)
 {
-	int usesize;
-
-	if (!dest || !ptr || !size)
-		return -1;
-	BUG_ON(size < 2);
-
-	usesize = min_t(size_t, ptr[size - 1], sizeof(dest->u_name));
-	usesize = min(usesize, size - 2);
-	dest->u_cmpID = ptr[0];
-	dest->u_len = usesize;
-	memcpy(dest->u_name, ptr + 1, usesize);
-	memset(dest->u_name + usesize, 0, sizeof(dest->u_name) - usesize);
-
-	return 0;
-}
-
-/*
- * udf_build_ustr_exact
- */
-static void udf_build_ustr_exact(struct ustr *dest, dstring *ptr, int exactsize)
-{
-	memset(dest, 0, sizeof(struct ustr));
-	dest->u_cmpID = ptr[0];
-	dest->u_len = exactsize - 1;
-	memcpy(dest->u_name, ptr + 1, exactsize - 1);
-}
-
-/*
- * udf_CS0toUTF8
- *
- * PURPOSE
- *	Convert OSTA Compressed Unicode to the UTF-8 equivalent.
- *
- * PRE-CONDITIONS
- *	utf			Pointer to UTF-8 output buffer.
- *	ocu			Pointer to OSTA Compressed Unicode input buffer
- *				of size UDF_NAME_LEN bytes.
- * 				both of type "struct ustr *"
- *
- * POST-CONDITIONS
- *	<return>		>= 0 on success.
- *
- * HISTORY
- *	November 12, 1997 - Andrew E. Mileski
- *	Written, tested, and released.
- */
-int udf_CS0toUTF8(struct ustr *utf_o, const struct ustr *ocu_i)
-{
-	const uint8_t *ocu;
-	uint8_t cmp_id, ocu_len;
-	int i;
-
-	ocu_len = ocu_i->u_len;
-	if (ocu_len == 0) {
-		memset(utf_o, 0, sizeof(struct ustr));
-		return 0;
-	}
-
-	cmp_id = ocu_i->u_cmpID;
-	if (cmp_id != 8 && cmp_id != 16) {
-		memset(utf_o, 0, sizeof(struct ustr));
-		pr_err("unknown compression code (%d) stri=%s\n",
-		       cmp_id, ocu_i->u_name);
-		return -EINVAL;
-	}
-
-	ocu = ocu_i->u_name;
-	utf_o->u_len = 0;
-	for (i = 0; (i < ocu_len) && (utf_o->u_len <= (UDF_NAME_LEN - 3));) {
-
-		/* Expand OSTA compressed Unicode to Unicode */
-		uint32_t c = ocu[i++];
-		if (cmp_id == 16)
-			c = (c << 8) | ocu[i++];
-
-		/* Compress Unicode to UTF-8 */
-		if (c < 0x80U)
-			utf_o->u_name[utf_o->u_len++] = (uint8_t)c;
-		else if (c < 0x800U) {
-			utf_o->u_name[utf_o->u_len++] =
-						(uint8_t)(0xc0 | (c >> 6));
-			utf_o->u_name[utf_o->u_len++] =
-						(uint8_t)(0x80 | (c & 0x3f));
-		} else {
-			utf_o->u_name[utf_o->u_len++] =
-						(uint8_t)(0xe0 | (c >> 12));
-			utf_o->u_name[utf_o->u_len++] =
-						(uint8_t)(0x80 |
-							  ((c >> 6) & 0x3f));
-			utf_o->u_name[utf_o->u_len++] =
-						(uint8_t)(0x80 | (c & 0x3f));
-		}
+	int u_len = 0;
+
+	if (boundlen <= 0)
+		return -ENAMETOOLONG;
+
+	if (uni < 0x80) {
+		out[u_len++] = (unsigned char)uni;
+	} else if (uni < 0x800) {
+		if (boundlen < 2)
+			return -ENAMETOOLONG;
+		out[u_len++] = (unsigned char)(0xc0 | (uni >> 6));
+		out[u_len++] = (unsigned char)(0x80 | (uni & 0x3f));
+	} else {
+		if (boundlen < 3)
+			return -ENAMETOOLONG;
+		out[u_len++] = (unsigned char)(0xe0 | (uni >> 12));
+		out[u_len++] = (unsigned char)(0x80 | ((uni >> 6) & 0x3f));
+		out[u_len++] = (unsigned char)(0x80 | (uni & 0x3f));
 	}
-	utf_o->u_cmpID = 8;
-
-	return utf_o->u_len;
+	return u_len;
 }
 
-/*
- *
- * udf_UTF8toCS0
- *
- * PURPOSE
- *	Convert UTF-8 to the OSTA Compressed Unicode equivalent.
- *
- * DESCRIPTION
- *	This routine is only called by udf_lookup().
- *
- * PRE-CONDITIONS
- *	ocu			Pointer to OSTA Compressed Unicode output
- *				buffer of size UDF_NAME_LEN bytes.
- *	utf			Pointer to UTF-8 input buffer.
- *	utf_len			Length of UTF-8 input buffer in bytes.
- *
- * POST-CONDITIONS
- *	<return>		Zero on success.
- *
- * HISTORY
- *	November 12, 1997 - Andrew E. Mileski
- *	Written, tested, and released.
- */
-static int udf_UTF8toCS0(dstring *ocu, struct ustr *utf, int length)
+static int udf_char2uni_utf8(const unsigned char *in,
+			     int boundlen,
+			     wchar_t *uni)
 {
-	unsigned c, i, max_val, utf_char;
+	unsigned int utf_char;
+	unsigned char c;
 	int utf_cnt, u_len;
 
-	memset(ocu, 0, sizeof(dstring) * length);
-	ocu[0] = 8;
-	max_val = 0xffU;
-
-try_again:
-	u_len = 0U;
-	utf_char = 0U;
-	utf_cnt = 0U;
-	for (i = 0U; i < utf->u_len; i++) {
-		c = (uint8_t)utf->u_name[i];
+	utf_char = 0;
+	utf_cnt = 0;
+	for (u_len = 0; u_len < boundlen;) {
+		c = in[u_len++];
 
 		/* Complete a multi-byte UTF-8 character */
 		if (utf_cnt) {
-			utf_char = (utf_char << 6) | (c & 0x3fU);
+			utf_char = (utf_char << 6) | (c & 0x3f);
 			if (--utf_cnt)
 				continue;
 		} else {
 			/* Check for a multi-byte UTF-8 character */
-			if (c & 0x80U) {
+			if (c & 0x80) {
 				/* Start a multi-byte UTF-8 character */
-				if ((c & 0xe0U) == 0xc0U) {
-					utf_char = c & 0x1fU;
+				if ((c & 0xe0) == 0xc0) {
+					utf_char = c & 0x1f;
 					utf_cnt = 1;
-				} else if ((c & 0xf0U) == 0xe0U) {
-					utf_char = c & 0x0fU;
+				} else if ((c & 0xf0) == 0xe0) {
+					utf_char = c & 0x0f;
 					utf_cnt = 2;
-				} else if ((c & 0xf8U) == 0xf0U) {
-					utf_char = c & 0x07U;
+				} else if ((c & 0xf8) == 0xf0) {
+					utf_char = c & 0x07;
 					utf_cnt = 3;
-				} else if ((c & 0xfcU) == 0xf8U) {
-					utf_char = c & 0x03U;
+				} else if ((c & 0xfc) == 0xf8) {
+					utf_char = c & 0x03;
 					utf_cnt = 4;
-				} else if ((c & 0xfeU) == 0xfcU) {
-					utf_char = c & 0x01U;
+				} else if ((c & 0xfe) == 0xfc) {
+					utf_char = c & 0x01;
 					utf_cnt = 5;
 				} else {
-					goto error_out;
+					utf_cnt = -1;
+					break;
 				}
 				continue;
 			} else {
@@ -219,92 +101,216 @@ try_again:
 				utf_char = c;
 			}
 		}
-
-		/* Choose no compression if necessary */
-		if (utf_char > max_val) {
-			if (max_val == 0xffU) {
-				max_val = 0xffffU;
-				ocu[0] = (uint8_t)0x10U;
-				goto try_again;
-			}
-			goto error_out;
-		}
-
-		if (max_val == 0xffffU)
-			ocu[++u_len] = (uint8_t)(utf_char >> 8);
-		ocu[++u_len] = (uint8_t)(utf_char & 0xffU);
+		*uni = utf_char;
+		break;
 	}
-
 	if (utf_cnt) {
-error_out:
-		ocu[++u_len] = '?';
-		printk(KERN_DEBUG pr_fmt("bad UTF-8 character\n"));
+		*uni = '?';
+		return -EINVAL;
 	}
+	return u_len;
+}
+
+#define ILLEGAL_CHAR_MARK	'_'
+#define EXT_MARK		'.'
+#define CRC_MARK		'#'
+#define EXT_SIZE		5
+/* Number of chars we need to store generated CRC to make filename unique */
+#define CRC_LEN			5
 
-	ocu[length - 1] = (uint8_t)u_len + 1;
+static int udf_name_conv_char(uint8_t *str_o, int str_o_max_len,
+			      int *str_o_idx,
+			      const uint8_t *str_i, int str_i_max_len,
+			      int *str_i_idx,
+			      int u_ch, int *needsCRC,
+			      int (*conv_f)(wchar_t, unsigned char *, int),
+			      int translate)
+{
+	uint32_t c;
+	int illChar = 0;
+	int len, gotch = 0;
+
+	for (; (!gotch) && (*str_i_idx < str_i_max_len); *str_i_idx += u_ch) {
+		if (*str_o_idx >= str_o_max_len) {
+			*needsCRC = 1;
+			return gotch;
+		}
 
-	return u_len + 1;
+		/* Expand OSTA compressed Unicode to Unicode */
+		c = str_i[*str_i_idx];
+		if (u_ch > 1)
+			c = (c << 8) | str_i[*str_i_idx + 1];
+
+		if (translate && (c == '/' || c == 0))
+			illChar = 1;
+		else if (illChar)
+			break;
+		else
+			gotch = 1;
+	}
+	if (illChar) {
+		*needsCRC = 1;
+		c = ILLEGAL_CHAR_MARK;
+		gotch = 1;
+	}
+	if (gotch) {
+		len = conv_f(c, &str_o[*str_o_idx], str_o_max_len - *str_o_idx);
+		/* Valid character? */
+		if (len >= 0)
+			*str_o_idx += len;
+		else if (len == -ENAMETOOLONG) {
+			*needsCRC = 1;
+			gotch = 0;
+		} else {
+			str_o[(*str_o_idx)++] = '?';
+			*needsCRC = 1;
+		}
+	}
+	return gotch;
 }
 
-static int udf_CS0toNLS(struct nls_table *nls, struct ustr *utf_o,
-			const struct ustr *ocu_i)
+static int udf_name_from_CS0(uint8_t *str_o, int str_max_len,
+			     const uint8_t *ocu, int ocu_len,
+			     int (*conv_f)(wchar_t, unsigned char *, int),
+			     int translate)
 {
-	const uint8_t *ocu;
-	uint8_t cmp_id, ocu_len;
-	int i, len;
+	uint32_t c;
+	uint8_t cmp_id;
+	int idx, len;
+	int u_ch;
+	int needsCRC = 0;
+	int ext_i_len, ext_max_len;
+	int str_o_len = 0;	/* Length of resulting output */
+	int ext_o_len = 0;	/* Extension output length */
+	int ext_crc_len = 0;	/* Extension output length if used with CRC */
+	int i_ext = -1;		/* Extension position in input buffer */
+	int o_crc = 0;		/* Rightmost possible output pos for CRC+ext */
+	unsigned short valueCRC;
+	uint8_t ext[EXT_SIZE * NLS_MAX_CHARSET_SIZE + 1];
+	uint8_t crc[CRC_LEN];
 
+	if (str_max_len <= 0)
+		return 0;
 
-	ocu_len = ocu_i->u_len;
 	if (ocu_len == 0) {
-		memset(utf_o, 0, sizeof(struct ustr));
+		memset(str_o, 0, str_max_len);
 		return 0;
 	}
 
-	cmp_id = ocu_i->u_cmpID;
+	cmp_id = ocu[0];
 	if (cmp_id != 8 && cmp_id != 16) {
-		memset(utf_o, 0, sizeof(struct ustr));
-		pr_err("unknown compression code (%d) stri=%s\n",
-		       cmp_id, ocu_i->u_name);
+		memset(str_o, 0, str_max_len);
+		pr_err("unknown compression code (%d)\n", cmp_id);
 		return -EINVAL;
 	}
+	u_ch = cmp_id >> 3;
 
-	ocu = ocu_i->u_name;
-	utf_o->u_len = 0;
-	for (i = 0; (i < ocu_len) && (utf_o->u_len <= (UDF_NAME_LEN - 3));) {
-		/* Expand OSTA compressed Unicode to Unicode */
-		uint32_t c = ocu[i++];
-		if (cmp_id == 16)
-			c = (c << 8) | ocu[i++];
+	ocu++;
+	ocu_len--;
 
-		len = nls->uni2char(c, &utf_o->u_name[utf_o->u_len],
-				    UDF_NAME_LEN - utf_o->u_len);
-		/* Valid character? */
-		if (len >= 0)
-			utf_o->u_len += len;
-		else
-			utf_o->u_name[utf_o->u_len++] = '?';
+	if (ocu_len % u_ch) {
+		pr_err("incorrect filename length (%d)\n", ocu_len + 1);
+		return -EINVAL;
+	}
+
+	if (translate) {
+		/* Look for extension */
+		for (idx = ocu_len - u_ch, ext_i_len = 0;
+		     (idx >= 0) && (ext_i_len < EXT_SIZE);
+		     idx -= u_ch, ext_i_len++) {
+			c = ocu[idx];
+			if (u_ch > 1)
+				c = (c << 8) | ocu[idx + 1];
+
+			if (c == EXT_MARK) {
+				if (ext_i_len)
+					i_ext = idx;
+				break;
+			}
+		}
+		if (i_ext >= 0) {
+			/* Convert extension */
+			ext_max_len = min_t(int, sizeof(ext), str_max_len);
+			ext[ext_o_len++] = EXT_MARK;
+			idx = i_ext + u_ch;
+			while (udf_name_conv_char(ext, ext_max_len, &ext_o_len,
+						  ocu, ocu_len, &idx,
+						  u_ch, &needsCRC,
+						  conv_f, translate)) {
+				if ((ext_o_len + CRC_LEN) < str_max_len)
+					ext_crc_len = ext_o_len;
+			}
+		}
+	}
+
+	idx = 0;
+	while (1) {
+		if (translate && (idx == i_ext)) {
+			if (str_o_len > (str_max_len - ext_o_len))
+				needsCRC = 1;
+			break;
+		}
+
+		if (!udf_name_conv_char(str_o, str_max_len, &str_o_len,
+					ocu, ocu_len, &idx,
+					u_ch, &needsCRC, conv_f, translate))
+			break;
+
+		if (translate &&
+		    (str_o_len <= (str_max_len - ext_o_len - CRC_LEN)))
+			o_crc = str_o_len;
+	}
+
+	if (translate) {
+		if (str_o_len <= 2 && str_o[0] == '.' &&
+		    (str_o_len == 1 || str_o[1] == '.'))
+			needsCRC = 1;
+		if (needsCRC) {
+			str_o_len = o_crc;
+			valueCRC = crc_itu_t(0, ocu, ocu_len);
+			crc[0] = CRC_MARK;
+			crc[1] = hex_asc_upper_hi(valueCRC >> 8);
+			crc[2] = hex_asc_upper_lo(valueCRC >> 8);
+			crc[3] = hex_asc_upper_hi(valueCRC);
+			crc[4] = hex_asc_upper_lo(valueCRC);
+			len = min_t(int, CRC_LEN, str_max_len - str_o_len);
+			memcpy(&str_o[str_o_len], crc, len);
+			str_o_len += len;
+			ext_o_len = ext_crc_len;
+		}
+		if (ext_o_len > 0) {
+			memcpy(&str_o[str_o_len], ext, ext_o_len);
+			str_o_len += ext_o_len;
+		}
 	}
-	utf_o->u_cmpID = 8;
 
-	return utf_o->u_len;
+	return str_o_len;
 }
 
-static int udf_NLStoCS0(struct nls_table *nls, dstring *ocu, struct ustr *uni,
-			int length)
+static int udf_name_to_CS0(uint8_t *ocu, int ocu_max_len,
+			   const uint8_t *str_i, int str_len,
+			   int (*conv_f)(const unsigned char *, int, wchar_t *))
 {
-	int len;
-	unsigned i, max_val;
-	uint16_t uni_char;
-	int u_len;
+	int i, len;
+	unsigned int max_val;
+	wchar_t uni_char;
+	int u_len, u_ch;
 
-	memset(ocu, 0, sizeof(dstring) * length);
+	if (ocu_max_len <= 0)
+		return 0;
+
+	memset(ocu, 0, ocu_max_len);
 	ocu[0] = 8;
-	max_val = 0xffU;
+	max_val = 0xff;
+	u_ch = 1;
 
 try_again:
-	u_len = 0U;
-	for (i = 0U; i < uni->u_len; i++) {
-		len = nls->char2uni(&uni->u_name[i], uni->u_len - i, &uni_char);
+	u_len = 1;
+	for (i = 0; i < str_len; i++) {
+		/* Name didn't fit? */
+		if (u_len + u_ch > ocu_max_len)
+			return 0;
+		len = conv_f(&str_i[i], str_len - i, &uni_char);
 		if (!len)
 			continue;
 		/* Invalid character, deal with it */
@@ -314,186 +320,65 @@ try_again:
 		}
 
 		if (uni_char > max_val) {
-			max_val = 0xffffU;
-			ocu[0] = (uint8_t)0x10U;
+			max_val = 0xffff;
+			ocu[0] = 0x10;
+			u_ch = 2;
 			goto try_again;
 		}
 
-		if (max_val == 0xffffU)
-			ocu[++u_len] = (uint8_t)(uni_char >> 8);
-		ocu[++u_len] = (uint8_t)(uni_char & 0xffU);
+		if (max_val == 0xffff)
+			ocu[u_len++] = (uint8_t)(uni_char >> 8);
+		ocu[u_len++] = (uint8_t)(uni_char & 0xff);
 		i += len - 1;
 	}
 
-	ocu[length - 1] = (uint8_t)u_len + 1;
-	return u_len + 1;
+	return u_len;
+}
+
+int udf_CS0toUTF8(uint8_t *utf_o, int o_len, const uint8_t *ocu_i, int i_len)
+{
+	return udf_name_from_CS0(utf_o, o_len, ocu_i, i_len,
+				 udf_uni2char_utf8, 0);
 }
 
-int udf_get_filename(struct super_block *sb, uint8_t *sname, int slen,
+int udf_get_filename(struct super_block *sb, const uint8_t *sname, int slen,
 		     uint8_t *dname, int dlen)
 {
-	struct ustr *filename, *unifilename;
+	int (*conv_f)(wchar_t, unsigned char *, int);
 	int ret;
 
 	if (!slen)
 		return -EIO;
 
-	filename = kmalloc(sizeof(struct ustr), GFP_NOFS);
-	if (!filename)
-		return -ENOMEM;
-
-	unifilename = kmalloc(sizeof(struct ustr), GFP_NOFS);
-	if (!unifilename) {
-		ret = -ENOMEM;
-		goto out1;
-	}
+	if (dlen <= 0)
+		return 0;
 
-	udf_build_ustr_exact(unifilename, sname, slen);
 	if (UDF_QUERY_FLAG(sb, UDF_FLAG_UTF8)) {
-		ret = udf_CS0toUTF8(filename, unifilename);
-		if (ret < 0) {
-			udf_debug("Failed in udf_get_filename: sname = %s\n",
-				  sname);
-			goto out2;
-		}
+		conv_f = udf_uni2char_utf8;
 	} else if (UDF_QUERY_FLAG(sb, UDF_FLAG_NLS_MAP)) {
-		ret = udf_CS0toNLS(UDF_SB(sb)->s_nls_map, filename,
-				   unifilename);
-		if (ret < 0) {
-			udf_debug("Failed in udf_get_filename: sname = %s\n",
-				  sname);
-			goto out2;
-		}
+		conv_f = UDF_SB(sb)->s_nls_map->uni2char;
 	} else
 		BUG();
 
-	ret = udf_translate_to_linux(dname, dlen,
-				     filename->u_name, filename->u_len,
-				     unifilename->u_name, unifilename->u_len);
+	ret = udf_name_from_CS0(dname, dlen, sname, slen, conv_f, 1);
 	/* Zero length filename isn't valid... */
 	if (ret == 0)
 		ret = -EINVAL;
-out2:
-	kfree(unifilename);
-out1:
-	kfree(filename);
 	return ret;
 }
 
-int udf_put_filename(struct super_block *sb, const uint8_t *sname,
-		     uint8_t *dname, int flen)
+int udf_put_filename(struct super_block *sb, const uint8_t *sname, int slen,
+		     uint8_t *dname, int dlen)
 {
-	struct ustr unifilename;
-	int namelen;
-
-	if (!udf_char_to_ustr(&unifilename, sname, flen))
-		return 0;
+	int (*conv_f)(const unsigned char *, int, wchar_t *);
 
 	if (UDF_QUERY_FLAG(sb, UDF_FLAG_UTF8)) {
-		namelen = udf_UTF8toCS0(dname, &unifilename, UDF_NAME_LEN);
-		if (!namelen)
-			return 0;
+		conv_f = udf_char2uni_utf8;
 	} else if (UDF_QUERY_FLAG(sb, UDF_FLAG_NLS_MAP)) {
-		namelen = udf_NLStoCS0(UDF_SB(sb)->s_nls_map, dname,
-					&unifilename, UDF_NAME_LEN);
-		if (!namelen)
-			return 0;
+		conv_f = UDF_SB(sb)->s_nls_map->char2uni;
 	} else
-		return 0;
+		BUG();
 
-	return namelen;
+	return udf_name_to_CS0(dname, dlen, sname, slen, conv_f);
 }
 
-#define ILLEGAL_CHAR_MARK	'_'
-#define EXT_MARK		'.'
-#define CRC_MARK		'#'
-#define EXT_SIZE 		5
-/* Number of chars we need to store generated CRC to make filename unique */
-#define CRC_LEN			5
-
-static int udf_translate_to_linux(uint8_t *newName, int newLen,
-				  uint8_t *udfName, int udfLen,
-				  uint8_t *fidName, int fidNameLen)
-{
-	int index, newIndex = 0, needsCRC = 0;
-	int extIndex = 0, newExtIndex = 0, hasExt = 0;
-	unsigned short valueCRC;
-	uint8_t curr;
-
-	if (udfName[0] == '.' &&
-	    (udfLen == 1 || (udfLen == 2 && udfName[1] == '.'))) {
-		needsCRC = 1;
-		newIndex = udfLen;
-		memcpy(newName, udfName, udfLen);
-	} else {
-		for (index = 0; index < udfLen; index++) {
-			curr = udfName[index];
-			if (curr == '/' || curr == 0) {
-				needsCRC = 1;
-				curr = ILLEGAL_CHAR_MARK;
-				while (index + 1 < udfLen &&
-						(udfName[index + 1] == '/' ||
-						 udfName[index + 1] == 0))
-					index++;
-			}
-			if (curr == EXT_MARK &&
-					(udfLen - index - 1) <= EXT_SIZE) {
-				if (udfLen == index + 1)
-					hasExt = 0;
-				else {
-					hasExt = 1;
-					extIndex = index;
-					newExtIndex = newIndex;
-				}
-			}
-			if (newIndex < newLen)
-				newName[newIndex++] = curr;
-			else
-				needsCRC = 1;
-		}
-	}
-	if (needsCRC) {
-		uint8_t ext[EXT_SIZE];
-		int localExtIndex = 0;
-
-		if (hasExt) {
-			int maxFilenameLen;
-			for (index = 0;
-			     index < EXT_SIZE && extIndex + index + 1 < udfLen;
-			     index++) {
-				curr = udfName[extIndex + index + 1];
-
-				if (curr == '/' || curr == 0) {
-					needsCRC = 1;
-					curr = ILLEGAL_CHAR_MARK;
-					while (extIndex + index + 2 < udfLen &&
-					      (index + 1 < EXT_SIZE &&
-						(udfName[extIndex + index + 2] == '/' ||
-						 udfName[extIndex + index + 2] == 0)))
-						index++;
-				}
-				ext[localExtIndex++] = curr;
-			}
-			maxFilenameLen = newLen - CRC_LEN - localExtIndex;
-			if (newIndex > maxFilenameLen)
-				newIndex = maxFilenameLen;
-			else
-				newIndex = newExtIndex;
-		} else if (newIndex > newLen - CRC_LEN)
-			newIndex = newLen - CRC_LEN;
-		newName[newIndex++] = CRC_MARK;
-		valueCRC = crc_itu_t(0, fidName, fidNameLen);
-		newName[newIndex++] = hex_asc_upper_hi(valueCRC >> 8);
-		newName[newIndex++] = hex_asc_upper_lo(valueCRC >> 8);
-		newName[newIndex++] = hex_asc_upper_hi(valueCRC);
-		newName[newIndex++] = hex_asc_upper_lo(valueCRC);
-
-		if (hasExt) {
-			newName[newIndex++] = EXT_MARK;
-			for (index = 0; index < localExtIndex; index++)
-				newName[newIndex++] = ext[index];
-		}
-	}
-
-	return newIndex;
-}
diff --git a/fs/ufs/Makefile b/fs/ufs/Makefile
index 392db25c0b56..ec4a6b49fa13 100644
--- a/fs/ufs/Makefile
+++ b/fs/ufs/Makefile
@@ -5,5 +5,5 @@
 obj-$(CONFIG_UFS_FS) += ufs.o
 
 ufs-objs := balloc.o cylinder.o dir.o file.o ialloc.o inode.o \
-	    namei.o super.o symlink.o util.o
+	    namei.o super.o util.o
 ccflags-$(CONFIG_UFS_DEBUG)    += -DDEBUG
diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c
index dc5fae601c24..0447b949c7f5 100644
--- a/fs/ufs/balloc.c
+++ b/fs/ufs/balloc.c
@@ -237,7 +237,7 @@ static void ufs_change_blocknr(struct inode *inode, sector_t beg,
 			       sector_t newb, struct page *locked_page)
 {
 	const unsigned blks_per_page =
-		1 << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+		1 << (PAGE_SHIFT - inode->i_blkbits);
 	const unsigned mask = blks_per_page - 1;
 	struct address_space * const mapping = inode->i_mapping;
 	pgoff_t index, cur_index, last_index;
@@ -255,9 +255,9 @@ static void ufs_change_blocknr(struct inode *inode, sector_t beg,
 
 	cur_index = locked_page->index;
 	end = count + beg;
-	last_index = end >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+	last_index = end >> (PAGE_SHIFT - inode->i_blkbits);
 	for (i = beg; i < end; i = (i | mask) + 1) {
-		index = i >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+		index = i >> (PAGE_SHIFT - inode->i_blkbits);
 
 		if (likely(cur_index != index)) {
 			page = ufs_get_locked_page(mapping, index);
diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c
index 74f2e80288bf..0b1457292734 100644
--- a/fs/ufs/dir.c
+++ b/fs/ufs/dir.c
@@ -62,7 +62,7 @@ static int ufs_commit_chunk(struct page *page, loff_t pos, unsigned len)
 static inline void ufs_put_page(struct page *page)
 {
 	kunmap(page);
-	page_cache_release(page);
+	put_page(page);
 }
 
 ino_t ufs_inode_by_name(struct inode *dir, const struct qstr *qstr)
@@ -111,13 +111,13 @@ static void ufs_check_page(struct page *page)
 	struct super_block *sb = dir->i_sb;
 	char *kaddr = page_address(page);
 	unsigned offs, rec_len;
-	unsigned limit = PAGE_CACHE_SIZE;
+	unsigned limit = PAGE_SIZE;
 	const unsigned chunk_mask = UFS_SB(sb)->s_uspi->s_dirblksize - 1;
 	struct ufs_dir_entry *p;
 	char *error;
 
-	if ((dir->i_size >> PAGE_CACHE_SHIFT) == page->index) {
-		limit = dir->i_size & ~PAGE_CACHE_MASK;
+	if ((dir->i_size >> PAGE_SHIFT) == page->index) {
+		limit = dir->i_size & ~PAGE_MASK;
 		if (limit & chunk_mask)
 			goto Ebadsize;
 		if (!limit)
@@ -170,7 +170,7 @@ Einumber:
 bad_entry:
 	ufs_error (sb, "ufs_check_page", "bad entry in directory #%lu: %s - "
 		   "offset=%lu, rec_len=%d, name_len=%d",
-		   dir->i_ino, error, (page->index<<PAGE_CACHE_SHIFT)+offs,
+		   dir->i_ino, error, (page->index<<PAGE_SHIFT)+offs,
 		   rec_len, ufs_get_de_namlen(sb, p));
 	goto fail;
 Eend:
@@ -178,7 +178,7 @@ Eend:
 	ufs_error(sb, __func__,
 		   "entry in directory #%lu spans the page boundary"
 		   "offset=%lu",
-		   dir->i_ino, (page->index<<PAGE_CACHE_SHIFT)+offs);
+		   dir->i_ino, (page->index<<PAGE_SHIFT)+offs);
 fail:
 	SetPageChecked(page);
 	SetPageError(page);
@@ -211,9 +211,9 @@ ufs_last_byte(struct inode *inode, unsigned long page_nr)
 {
 	unsigned last_byte = inode->i_size;
 
-	last_byte -= page_nr << PAGE_CACHE_SHIFT;
-	if (last_byte > PAGE_CACHE_SIZE)
-		last_byte = PAGE_CACHE_SIZE;
+	last_byte -= page_nr << PAGE_SHIFT;
+	if (last_byte > PAGE_SIZE)
+		last_byte = PAGE_SIZE;
 	return last_byte;
 }
 
@@ -341,7 +341,7 @@ int ufs_add_link(struct dentry *dentry, struct inode *inode)
 		kaddr = page_address(page);
 		dir_end = kaddr + ufs_last_byte(dir, n);
 		de = (struct ufs_dir_entry *)kaddr;
-		kaddr += PAGE_CACHE_SIZE - reclen;
+		kaddr += PAGE_SIZE - reclen;
 		while ((char *)de <= kaddr) {
 			if ((char *)de == dir_end) {
 				/* We hit i_size */
@@ -432,8 +432,8 @@ ufs_readdir(struct file *file, struct dir_context *ctx)
 	loff_t pos = ctx->pos;
 	struct inode *inode = file_inode(file);
 	struct super_block *sb = inode->i_sb;
-	unsigned int offset = pos & ~PAGE_CACHE_MASK;
-	unsigned long n = pos >> PAGE_CACHE_SHIFT;
+	unsigned int offset = pos & ~PAGE_MASK;
+	unsigned long n = pos >> PAGE_SHIFT;
 	unsigned long npages = dir_pages(inode);
 	unsigned chunk_mask = ~(UFS_SB(sb)->s_uspi->s_dirblksize - 1);
 	int need_revalidate = file->f_version != inode->i_version;
@@ -454,14 +454,14 @@ ufs_readdir(struct file *file, struct dir_context *ctx)
 			ufs_error(sb, __func__,
 				  "bad page in #%lu",
 				  inode->i_ino);
-			ctx->pos += PAGE_CACHE_SIZE - offset;
+			ctx->pos += PAGE_SIZE - offset;
 			return -EIO;
 		}
 		kaddr = page_address(page);
 		if (unlikely(need_revalidate)) {
 			if (offset) {
 				offset = ufs_validate_entry(sb, kaddr, offset, chunk_mask);
-				ctx->pos = (n<<PAGE_CACHE_SHIFT) + offset;
+				ctx->pos = (n<<PAGE_SHIFT) + offset;
 			}
 			file->f_version = inode->i_version;
 			need_revalidate = 0;
@@ -574,7 +574,7 @@ int ufs_make_empty(struct inode * inode, struct inode *dir)
 
 	kmap(page);
 	base = (char*)page_address(page);
-	memset(base, 0, PAGE_CACHE_SIZE);
+	memset(base, 0, PAGE_SIZE);
 
 	de = (struct ufs_dir_entry *) base;
 
@@ -594,7 +594,7 @@ int ufs_make_empty(struct inode * inode, struct inode *dir)
 
 	err = ufs_commit_chunk(page, 0, chunk_size);
 fail:
-	page_cache_release(page);
+	put_page(page);
 	return err;
 }
 
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index a064cf44b143..9f49431e798d 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -528,11 +528,12 @@ static void ufs_set_inode_ops(struct inode *inode)
 		inode->i_mapping->a_ops = &ufs_aops;
 	} else if (S_ISLNK(inode->i_mode)) {
 		if (!inode->i_blocks) {
-			inode->i_op = &ufs_fast_symlink_inode_operations;
 			inode->i_link = (char *)UFS_I(inode)->i_u1.i_symlink;
+			inode->i_op = &simple_symlink_inode_operations;
 		} else {
-			inode->i_op = &ufs_symlink_inode_operations;
 			inode->i_mapping->a_ops = &ufs_aops;
+			inode->i_op = &page_symlink_inode_operations;
+			inode_nohighmem(inode);
 		}
 	} else
 		init_special_inode(inode, inode->i_mode,
@@ -1050,13 +1051,13 @@ static int ufs_alloc_lastblock(struct inode *inode, loff_t size)
 	lastfrag--;
 
 	lastpage = ufs_get_locked_page(mapping, lastfrag >>
-				       (PAGE_CACHE_SHIFT - inode->i_blkbits));
+				       (PAGE_SHIFT - inode->i_blkbits));
        if (IS_ERR(lastpage)) {
                err = -EIO;
                goto out;
        }
 
-       end = lastfrag & ((1 << (PAGE_CACHE_SHIFT - inode->i_blkbits)) - 1);
+       end = lastfrag & ((1 << (PAGE_SHIFT - inode->i_blkbits)) - 1);
        bh = page_buffers(lastpage);
        for (i = 0; i < end; ++i)
                bh = bh->b_this_page;
diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c
index 47966554317c..a1559f762805 100644
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -123,14 +123,15 @@ static int ufs_symlink (struct inode * dir, struct dentry * dentry,
 
 	if (l > UFS_SB(sb)->s_uspi->s_maxsymlinklen) {
 		/* slow symlink */
-		inode->i_op = &ufs_symlink_inode_operations;
+		inode->i_op = &page_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &ufs_aops;
 		err = page_symlink(inode, symname, l);
 		if (err)
 			goto out_fail;
 	} else {
 		/* fast symlink */
-		inode->i_op = &ufs_fast_symlink_inode_operations;
+		inode->i_op = &simple_symlink_inode_operations;
 		inode->i_link = (char *)UFS_I(inode)->i_u1.i_symlink;
 		memcpy(inode->i_link, symname, l);
 		inode->i_size = l-1;
@@ -304,7 +305,7 @@ static int ufs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			ufs_set_link(old_inode, dir_de, dir_page, new_dir, 0);
 		else {
 			kunmap(dir_page);
-			page_cache_release(dir_page);
+			put_page(dir_page);
 		}
 		inode_dec_link_count(old_dir);
 	}
@@ -314,11 +315,11 @@ static int ufs_rename(struct inode *old_dir, struct dentry *old_dentry,
 out_dir:
 	if (dir_de) {
 		kunmap(dir_page);
-		page_cache_release(dir_page);
+		put_page(dir_page);
 	}
 out_old:
 	kunmap(old_page);
-	page_cache_release(old_page);
+	put_page(old_page);
 out:
 	return err;
 }
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index f6390eec02ca..442fd52ebffe 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -1427,7 +1427,7 @@ static int __init init_inodecache(void)
 	ufs_inode_cachep = kmem_cache_create("ufs_inode_cache",
 					     sizeof(struct ufs_inode_info),
 					     0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD),
+						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
 					     init_once);
 	if (ufs_inode_cachep == NULL)
 		return -ENOMEM;
diff --git a/fs/ufs/symlink.c b/fs/ufs/symlink.c
deleted file mode 100644
index 874480bb43e9..000000000000
--- a/fs/ufs/symlink.c
+++ /dev/null
@@ -1,42 +0,0 @@
-/*
- *  linux/fs/ufs/symlink.c
- *
- * Only fast symlinks left here - the rest is done by generic code. AV, 1999
- *
- * Copyright (C) 1998
- * Daniel Pirkl <daniel.pirkl@emai.cz>
- * Charles University, Faculty of Mathematics and Physics
- *
- *  from
- *
- *  linux/fs/ext2/symlink.c
- *
- * Copyright (C) 1992, 1993, 1994, 1995
- * Remy Card (card@masi.ibp.fr)
- * Laboratoire MASI - Institut Blaise Pascal
- * Universite Pierre et Marie Curie (Paris VI)
- *
- *  from
- *
- *  linux/fs/minix/symlink.c
- *
- *  Copyright (C) 1991, 1992  Linus Torvalds
- *
- *  ext2 symlink handling code
- */
-
-#include "ufs_fs.h"
-#include "ufs.h"
-
-const struct inode_operations ufs_fast_symlink_inode_operations = {
-	.readlink	= generic_readlink,
-	.follow_link	= simple_follow_link,
-	.setattr	= ufs_setattr,
-};
-
-const struct inode_operations ufs_symlink_inode_operations = {
-	.readlink	= generic_readlink,
-	.follow_link	= page_follow_link_light,
-	.put_link	= page_put_link,
-	.setattr	= ufs_setattr,
-};
diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h
index 7da4aca868c0..c87f4c3fa9dd 100644
--- a/fs/ufs/ufs.h
+++ b/fs/ufs/ufs.h
@@ -136,10 +136,6 @@ extern __printf(3, 4)
 void ufs_panic(struct super_block *, const char *, const char *, ...);
 void ufs_mark_sb_dirty(struct super_block *sb);
 
-/* symlink.c */
-extern const struct inode_operations ufs_fast_symlink_inode_operations;
-extern const struct inode_operations ufs_symlink_inode_operations;
-
 static inline struct ufs_sb_info *UFS_SB(struct super_block *sb)
 {
 	return sb->s_fs_info;
diff --git a/fs/ufs/util.c b/fs/ufs/util.c
index b6c2f94e041e..a409e3e7827a 100644
--- a/fs/ufs/util.c
+++ b/fs/ufs/util.c
@@ -261,14 +261,14 @@ struct page *ufs_get_locked_page(struct address_space *mapping,
 		if (unlikely(page->mapping == NULL)) {
 			/* Truncate got there first */
 			unlock_page(page);
-			page_cache_release(page);
+			put_page(page);
 			page = NULL;
 			goto out;
 		}
 
 		if (!PageUptodate(page) || PageError(page)) {
 			unlock_page(page);
-			page_cache_release(page);
+			put_page(page);
 
 			printk(KERN_ERR "ufs_change_blocknr: "
 			       "can not read page: ino %lu, index: %lu\n",
diff --git a/fs/ufs/util.h b/fs/ufs/util.h
index 954175928240..b7fbf53dbc81 100644
--- a/fs/ufs/util.h
+++ b/fs/ufs/util.h
@@ -283,7 +283,7 @@ extern struct page *ufs_get_locked_page(struct address_space *mapping,
 static inline void ufs_put_locked_page(struct page *page)
 {
        unlock_page(page);
-       page_cache_release(page);
+       put_page(page);
 }
 
 
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 50311703135b..66cdb44616d5 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -287,6 +287,12 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address,
 		goto out;
 
 	/*
+	 * We don't do userfault handling for the final child pid update.
+	 */
+	if (current->flags & PF_EXITING)
+		goto out;
+
+	/*
 	 * Check that we can return VM_FAULT_RETRY.
 	 *
 	 * NOTE: it should become possible to return VM_FAULT_RETRY
diff --git a/fs/utimes.c b/fs/utimes.c
index aa138d64560a..85c40f4f373d 100644
--- a/fs/utimes.c
+++ b/fs/utimes.c
@@ -103,9 +103,9 @@ static int utimes_common(struct path *path, struct timespec *times)
 		}
 	}
 retry_deleg:
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	error = notify_change(path->dentry, &newattrs, &delegated_inode);
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	if (delegated_inode) {
 		error = break_deleg_wait(&delegated_inode);
 		if (!error)
diff --git a/fs/xattr.c b/fs/xattr.c
index 072fee1258dd..4861322e28e8 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -129,7 +129,7 @@ vfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 	if (error)
 		return error;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	error = security_inode_setxattr(dentry, name, value, size, flags);
 	if (error)
 		goto out;
@@ -137,7 +137,7 @@ vfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 	error = __vfs_setxattr_noperm(dentry, name, value, size, flags);
 
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return error;
 }
 EXPORT_SYMBOL_GPL(vfs_setxattr);
@@ -208,25 +208,6 @@ vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value,
 	return error;
 }
 
-/* Compare an extended attribute value with the given value */
-int vfs_xattr_cmp(struct dentry *dentry, const char *xattr_name,
-		  const char *value, size_t size, gfp_t flags)
-{
-	char *xattr_value = NULL;
-	int rc;
-
-	rc = vfs_getxattr_alloc(dentry, xattr_name, &xattr_value, 0, flags);
-	if (rc < 0)
-		return rc;
-
-	if ((rc != size) || (memcmp(xattr_value, value, rc) != 0))
-		rc = -EINVAL;
-	else
-		rc = 0;
-	kfree(xattr_value);
-	return rc;
-}
-
 ssize_t
 vfs_getxattr(struct dentry *dentry, const char *name, void *value, size_t size)
 {
@@ -296,7 +277,7 @@ vfs_removexattr(struct dentry *dentry, const char *name)
 	if (error)
 		return error;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	error = security_inode_removexattr(dentry, name);
 	if (error)
 		goto out;
@@ -309,7 +290,7 @@ vfs_removexattr(struct dentry *dentry, const char *name)
 	}
 
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return error;
 }
 EXPORT_SYMBOL_GPL(vfs_removexattr);
@@ -324,7 +305,6 @@ setxattr(struct dentry *d, const char __user *name, const void __user *value,
 {
 	int error;
 	void *kvalue = NULL;
-	void *vvalue = NULL;	/* If non-NULL, we used vmalloc() */
 	char kname[XATTR_NAME_MAX + 1];
 
 	if (flags & ~(XATTR_CREATE|XATTR_REPLACE))
@@ -341,10 +321,9 @@ setxattr(struct dentry *d, const char __user *name, const void __user *value,
 			return -E2BIG;
 		kvalue = kmalloc(size, GFP_KERNEL | __GFP_NOWARN);
 		if (!kvalue) {
-			vvalue = vmalloc(size);
-			if (!vvalue)
+			kvalue = vmalloc(size);
+			if (!kvalue)
 				return -ENOMEM;
-			kvalue = vvalue;
 		}
 		if (copy_from_user(kvalue, value, size)) {
 			error = -EFAULT;
@@ -357,10 +336,8 @@ setxattr(struct dentry *d, const char __user *name, const void __user *value,
 
 	error = vfs_setxattr(d, kname, kvalue, size, flags);
 out:
-	if (vvalue)
-		vfree(vvalue);
-	else
-		kfree(kvalue);
+	kvfree(kvalue);
+
 	return error;
 }
 
@@ -428,7 +405,6 @@ getxattr(struct dentry *d, const char __user *name, void __user *value,
 {
 	ssize_t error;
 	void *kvalue = NULL;
-	void *vvalue = NULL;
 	char kname[XATTR_NAME_MAX + 1];
 
 	error = strncpy_from_user(kname, name, sizeof(kname));
@@ -442,10 +418,9 @@ getxattr(struct dentry *d, const char __user *name, void __user *value,
 			size = XATTR_SIZE_MAX;
 		kvalue = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
 		if (!kvalue) {
-			vvalue = vmalloc(size);
-			if (!vvalue)
+			kvalue = vmalloc(size);
+			if (!kvalue)
 				return -ENOMEM;
-			kvalue = vvalue;
 		}
 	}
 
@@ -461,10 +436,9 @@ getxattr(struct dentry *d, const char __user *name, void __user *value,
 		   than XATTR_SIZE_MAX bytes. Not possible. */
 		error = -E2BIG;
 	}
-	if (vvalue)
-		vfree(vvalue);
-	else
-		kfree(kvalue);
+
+	kvfree(kvalue);
+
 	return error;
 }
 
@@ -521,17 +495,15 @@ listxattr(struct dentry *d, char __user *list, size_t size)
 {
 	ssize_t error;
 	char *klist = NULL;
-	char *vlist = NULL;	/* If non-NULL, we used vmalloc() */
 
 	if (size) {
 		if (size > XATTR_LIST_MAX)
 			size = XATTR_LIST_MAX;
 		klist = kmalloc(size, __GFP_NOWARN | GFP_KERNEL);
 		if (!klist) {
-			vlist = vmalloc(size);
-			if (!vlist)
+			klist = vmalloc(size);
+			if (!klist)
 				return -ENOMEM;
-			klist = vlist;
 		}
 	}
 
@@ -544,10 +516,9 @@ listxattr(struct dentry *d, char __user *list, size_t size)
 		   than XATTR_LIST_MAX bytes. Not possible. */
 		error = -E2BIG;
 	}
-	if (vlist)
-		vfree(vlist);
-	else
-		kfree(klist);
+
+	kvfree(klist);
+
 	return error;
 }
 
@@ -700,13 +671,20 @@ xattr_resolve_name(const struct xattr_handler **handlers, const char **name)
 		return NULL;
 
 	for_each_xattr_handler(handlers, handler) {
-		const char *n = strcmp_prefix(*name, handler->prefix);
+		const char *n;
+
+		n = strcmp_prefix(*name, xattr_prefix(handler));
 		if (n) {
+			if (!handler->prefix ^ !*n) {
+				if (*n)
+					continue;
+				return ERR_PTR(-EINVAL);
+			}
 			*name = n;
-			break;
+			return handler;
 		}
 	}
-	return handler;
+	return ERR_PTR(-EOPNOTSUPP);
 }
 
 /*
@@ -718,9 +696,9 @@ generic_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t s
 	const struct xattr_handler *handler;
 
 	handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name);
-	if (!handler)
-		return -EOPNOTSUPP;
-	return handler->get(dentry, name, buffer, size, handler->flags);
+	if (IS_ERR(handler))
+		return PTR_ERR(handler);
+	return handler->get(handler, dentry, name, buffer, size);
 }
 
 /*
@@ -735,19 +713,25 @@ generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
 
 	if (!buffer) {
 		for_each_xattr_handler(handlers, handler) {
-			size += handler->list(dentry, NULL, 0, NULL, 0,
-					      handler->flags);
+			if (!handler->name ||
+			    (handler->list && !handler->list(dentry)))
+				continue;
+			size += strlen(handler->name) + 1;
 		}
 	} else {
 		char *buf = buffer;
+		size_t len;
 
 		for_each_xattr_handler(handlers, handler) {
-			size = handler->list(dentry, buf, buffer_size,
-					     NULL, 0, handler->flags);
-			if (size > buffer_size)
+			if (!handler->name ||
+			    (handler->list && !handler->list(dentry)))
+				continue;
+			len = strlen(handler->name);
+			if (len + 1 > buffer_size)
 				return -ERANGE;
-			buf += size;
-			buffer_size -= size;
+			memcpy(buf, handler->name, len + 1);
+			buf += len + 1;
+			buffer_size -= len + 1;
 		}
 		size = buf - buffer;
 	}
@@ -765,9 +749,9 @@ generic_setxattr(struct dentry *dentry, const char *name, const void *value, siz
 	if (size == 0)
 		value = "";  /* empty EA, do not remove */
 	handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name);
-	if (!handler)
-		return -EOPNOTSUPP;
-	return handler->set(dentry, name, value, size, flags, handler->flags);
+	if (IS_ERR(handler))
+		return PTR_ERR(handler);
+	return handler->set(handler, dentry, name, value, size, flags);
 }
 
 /*
@@ -780,10 +764,9 @@ generic_removexattr(struct dentry *dentry, const char *name)
 	const struct xattr_handler *handler;
 
 	handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name);
-	if (!handler)
-		return -EOPNOTSUPP;
-	return handler->set(dentry, name, NULL, 0,
-			    XATTR_REPLACE, handler->flags);
+	if (IS_ERR(handler))
+		return PTR_ERR(handler);
+	return handler->set(handler, dentry, name, NULL, 0, XATTR_REPLACE);
 }
 
 EXPORT_SYMBOL(generic_getxattr);
@@ -791,6 +774,30 @@ EXPORT_SYMBOL(generic_listxattr);
 EXPORT_SYMBOL(generic_setxattr);
 EXPORT_SYMBOL(generic_removexattr);
 
+/**
+ * xattr_full_name  -  Compute full attribute name from suffix
+ *
+ * @handler:	handler of the xattr_handler operation
+ * @name:	name passed to the xattr_handler operation
+ *
+ * The get and set xattr handler operations are called with the remainder of
+ * the attribute name after skipping the handler's prefix: for example, "foo"
+ * is passed to the get operation of a handler with prefix "user." to get
+ * attribute "user.foo".  The full name is still "there" in the name though.
+ *
+ * Note: the list xattr handler operation when called from the vfs is passed a
+ * NULL name; some file systems use this operation internally, with varying
+ * semantics.
+ */
+const char *xattr_full_name(const struct xattr_handler *handler,
+			    const char *name)
+{
+	size_t prefix_len = strlen(xattr_prefix(handler));
+
+	return name - prefix_len;
+}
+EXPORT_SYMBOL(xattr_full_name);
+
 /*
  * Allocate new xattr and copy in the value; but leave the name to callers.
  */
@@ -840,8 +847,22 @@ int simple_xattr_get(struct simple_xattrs *xattrs, const char *name,
 	return ret;
 }
 
-static int __simple_xattr_set(struct simple_xattrs *xattrs, const char *name,
-			      const void *value, size_t size, int flags)
+/**
+ * simple_xattr_set - xattr SET operation for in-memory/pseudo filesystems
+ * @xattrs: target simple_xattr list
+ * @name: name of the extended attribute
+ * @value: value of the xattr. If %NULL, will remove the attribute.
+ * @size: size of the new xattr
+ * @flags: %XATTR_{CREATE|REPLACE}
+ *
+ * %XATTR_CREATE is set, the xattr shouldn't exist already; otherwise fails
+ * with -EEXIST.  If %XATTR_REPLACE is set, the xattr should exist;
+ * otherwise, fails with -ENODATA.
+ *
+ * Returns 0 on success, -errno on failure.
+ */
+int simple_xattr_set(struct simple_xattrs *xattrs, const char *name,
+		     const void *value, size_t size, int flags)
 {
 	struct simple_xattr *xattr;
 	struct simple_xattr *new_xattr = NULL;
@@ -891,73 +912,64 @@ out:
 
 }
 
-/**
- * simple_xattr_set - xattr SET operation for in-memory/pseudo filesystems
- * @xattrs: target simple_xattr list
- * @name: name of the new extended attribute
- * @value: value of the new xattr. If %NULL, will remove the attribute
- * @size: size of the new xattr
- * @flags: %XATTR_{CREATE|REPLACE}
- *
- * %XATTR_CREATE is set, the xattr shouldn't exist already; otherwise fails
- * with -EEXIST.  If %XATTR_REPLACE is set, the xattr should exist;
- * otherwise, fails with -ENODATA.
- *
- * Returns 0 on success, -errno on failure.
- */
-int simple_xattr_set(struct simple_xattrs *xattrs, const char *name,
-		     const void *value, size_t size, int flags)
-{
-	if (size == 0)
-		value = ""; /* empty EA, do not remove */
-	return __simple_xattr_set(xattrs, name, value, size, flags);
-}
-
-/*
- * xattr REMOVE operation for in-memory/pseudo filesystems
- */
-int simple_xattr_remove(struct simple_xattrs *xattrs, const char *name)
+static bool xattr_is_trusted(const char *name)
 {
-	return __simple_xattr_set(xattrs, name, NULL, 0, XATTR_REPLACE);
+	return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN);
 }
 
-static bool xattr_is_trusted(const char *name)
+static int xattr_list_one(char **buffer, ssize_t *remaining_size,
+			  const char *name)
 {
-	return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN);
+	size_t len = strlen(name) + 1;
+	if (*buffer) {
+		if (*remaining_size < len)
+			return -ERANGE;
+		memcpy(*buffer, name, len);
+		*buffer += len;
+	}
+	*remaining_size -= len;
+	return 0;
 }
 
 /*
  * xattr LIST operation for in-memory/pseudo filesystems
  */
-ssize_t simple_xattr_list(struct simple_xattrs *xattrs, char *buffer,
-			  size_t size)
+ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
+			  char *buffer, size_t size)
 {
 	bool trusted = capable(CAP_SYS_ADMIN);
 	struct simple_xattr *xattr;
-	size_t used = 0;
+	ssize_t remaining_size = size;
+	int err = 0;
+
+#ifdef CONFIG_FS_POSIX_ACL
+	if (inode->i_acl) {
+		err = xattr_list_one(&buffer, &remaining_size,
+				     XATTR_NAME_POSIX_ACL_ACCESS);
+		if (err)
+			return err;
+	}
+	if (inode->i_default_acl) {
+		err = xattr_list_one(&buffer, &remaining_size,
+				     XATTR_NAME_POSIX_ACL_DEFAULT);
+		if (err)
+			return err;
+	}
+#endif
 
 	spin_lock(&xattrs->lock);
 	list_for_each_entry(xattr, &xattrs->head, list) {
-		size_t len;
-
 		/* skip "trusted." attributes for unprivileged callers */
 		if (!trusted && xattr_is_trusted(xattr->name))
 			continue;
 
-		len = strlen(xattr->name) + 1;
-		used += len;
-		if (buffer) {
-			if (size < used) {
-				used = -ERANGE;
-				break;
-			}
-			memcpy(buffer, xattr->name, len);
-			buffer += len;
-		}
+		err = xattr_list_one(&buffer, &remaining_size, xattr->name);
+		if (err)
+			break;
 	}
 	spin_unlock(&xattrs->lock);
 
-	return used;
+	return err ? err : size - remaining_size;
 }
 
 /*
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index a096841bd06c..3542d94fddce 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -84,6 +84,7 @@ xfs-y				+= xfs_aops.o \
 				   xfs_message.o \
 				   xfs_mount.o \
 				   xfs_mru_cache.o \
+				   xfs_stats.o \
 				   xfs_super.o \
 				   xfs_symlink.o \
 				   xfs_sysfs.o \
@@ -118,7 +119,7 @@ xfs-$(CONFIG_XFS_QUOTA)		+= xfs_dquot.o \
 xfs-$(CONFIG_XFS_RT)		+= xfs_rtalloc.o
 
 xfs-$(CONFIG_XFS_POSIX_ACL)	+= xfs_acl.o
-xfs-$(CONFIG_PROC_FS)		+= xfs_stats.o
 xfs-$(CONFIG_SYSCTL)		+= xfs_sysctl.o
 xfs-$(CONFIG_COMPAT)		+= xfs_ioctl32.o
-xfs-$(CONFIG_NFSD_PNFS)		+= xfs_pnfs.o
+xfs-$(CONFIG_NFSD_BLOCKLAYOUT)	+= xfs_pnfs.o
+xfs-$(CONFIG_NFSD_SCSILAYOUT)	+= xfs_pnfs.o
diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c
index a7a3a63bb360..686ba6fb20dd 100644
--- a/fs/xfs/kmem.c
+++ b/fs/xfs/kmem.c
@@ -55,8 +55,9 @@ kmem_alloc(size_t size, xfs_km_flags_t flags)
 			return ptr;
 		if (!(++retries % 100))
 			xfs_err(NULL,
-		"possible memory allocation deadlock in %s (mode:0x%x)",
-					__func__, lflags);
+	"%s(%u) possible memory allocation deadlock size %u in %s (mode:0x%x)",
+				current->comm, current->pid,
+				(unsigned int)size, __func__, lflags);
 		congestion_wait(BLK_RW_ASYNC, HZ/50);
 	} while (1);
 }
@@ -120,8 +121,9 @@ kmem_zone_alloc(kmem_zone_t *zone, xfs_km_flags_t flags)
 			return ptr;
 		if (!(++retries % 100))
 			xfs_err(NULL,
-		"possible memory allocation deadlock in %s (mode:0x%x)",
-					__func__, lflags);
+		"%s(%u) possible memory allocation deadlock in %s (mode:0x%x)",
+				current->comm, current->pid,
+				__func__, lflags);
 		congestion_wait(BLK_RW_ASYNC, HZ/50);
 	} while (1);
 }
diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h
index cc6b768fc068..d1c66e465ca5 100644
--- a/fs/xfs/kmem.h
+++ b/fs/xfs/kmem.h
@@ -84,6 +84,7 @@ kmem_zalloc(size_t size, xfs_km_flags_t flags)
 #define KM_ZONE_HWALIGN	SLAB_HWCACHE_ALIGN
 #define KM_ZONE_RECLAIM	SLAB_RECLAIM_ACCOUNT
 #define KM_ZONE_SPREAD	SLAB_MEM_SPREAD
+#define KM_ZONE_ACCOUNT	SLAB_ACCOUNT
 
 #define kmem_zone	kmem_cache
 #define kmem_zone_t	struct kmem_cache
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index ffad7f20342f..a708e38b494c 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -482,7 +482,9 @@ xfs_agfl_verify(
 		    be32_to_cpu(agfl->agfl_bno[i]) >= mp->m_sb.sb_agblocks)
 			return false;
 	}
-	return true;
+
+	return xfs_log_check_lsn(mp,
+				 be64_to_cpu(XFS_BUF_TO_AGFL(bp)->agfl_lsn));
 }
 
 static void
@@ -533,6 +535,7 @@ xfs_agfl_write_verify(
 }
 
 const struct xfs_buf_ops xfs_agfl_buf_ops = {
+	.name = "xfs_agfl",
 	.verify_read = xfs_agfl_read_verify,
 	.verify_write = xfs_agfl_write_verify,
 };
@@ -651,8 +654,8 @@ xfs_alloc_ag_vextent(
 				 -((long)(args->len)));
 	}
 
-	XFS_STATS_INC(xs_allocx);
-	XFS_STATS_ADD(xs_allocb, args->len);
+	XFS_STATS_INC(args->mp, xs_allocx);
+	XFS_STATS_ADD(args->mp, xs_allocb, args->len);
 	return error;
 }
 
@@ -1808,8 +1811,8 @@ xfs_free_ag_extent(
 
 	if (!isfl)
 		xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, (long)len);
-	XFS_STATS_INC(xs_freex);
-	XFS_STATS_ADD(xs_freeb, len);
+	XFS_STATS_INC(mp, xs_freex);
+	XFS_STATS_ADD(mp, xs_freeb, len);
 
 	trace_xfs_free_extent(mp, agno, bno, len, isfl, haveleft, haveright);
 
@@ -1924,7 +1927,7 @@ xfs_alloc_space_available(
  * Decide whether to use this allocation group for this allocation.
  * If so, fix up the btree freelist's size.
  */
-STATIC int			/* error */
+int			/* error */
 xfs_alloc_fix_freelist(
 	struct xfs_alloc_arg	*args,	/* allocation argument structure */
 	int			flags)	/* XFS_ALLOC_FLAG_... */
@@ -2259,9 +2262,13 @@ xfs_agf_verify(
  {
 	struct xfs_agf	*agf = XFS_BUF_TO_AGF(bp);
 
-	if (xfs_sb_version_hascrc(&mp->m_sb) &&
-	    !uuid_equal(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid))
+	if (xfs_sb_version_hascrc(&mp->m_sb)) {
+		if (!uuid_equal(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid))
+			return false;
+		if (!xfs_log_check_lsn(mp,
+				be64_to_cpu(XFS_BUF_TO_AGF(bp)->agf_lsn)))
 			return false;
+	}
 
 	if (!(agf->agf_magicnum == cpu_to_be32(XFS_AGF_MAGIC) &&
 	      XFS_AGF_GOOD_VERSION(be32_to_cpu(agf->agf_versionnum)) &&
@@ -2333,6 +2340,7 @@ xfs_agf_write_verify(
 }
 
 const struct xfs_buf_ops xfs_agf_buf_ops = {
+	.name = "xfs_agf",
 	.verify_read = xfs_agf_read_verify,
 	.verify_write = xfs_agf_write_verify,
 };
@@ -2503,7 +2511,7 @@ xfs_alloc_vextent(
 		 * Try near allocation first, then anywhere-in-ag after
 		 * the first a.g. fails.
 		 */
-		if ((args->userdata  == XFS_ALLOC_INITIAL_USER_DATA) &&
+		if ((args->userdata & XFS_ALLOC_INITIAL_USER_DATA) &&
 		    (mp->m_flags & XFS_MOUNT_32BITINODES)) {
 			args->fsbno = XFS_AGB_TO_FSB(mp,
 					((mp->m_agfrotor / rotorstep) %
@@ -2634,6 +2642,14 @@ xfs_alloc_vextent(
 		XFS_AG_CHECK_DADDR(mp, XFS_FSB_TO_DADDR(mp, args->fsbno),
 			args->len);
 #endif
+
+		/* Zero the extent if we were asked to do so */
+		if (args->userdata & XFS_ALLOC_USERDATA_ZERO) {
+			error = xfs_zero_extent(args->ip, args->fsbno, args->len);
+			if (error)
+				goto error0;
+		}
+
 	}
 	xfs_perag_put(args->pag);
 	return 0;
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index ca1c8168373a..135eb3d24db7 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -101,6 +101,7 @@ typedef struct xfs_alloc_arg {
 	struct xfs_mount *mp;		/* file system mount point */
 	struct xfs_buf	*agbp;		/* buffer for a.g. freelist header */
 	struct xfs_perag *pag;		/* per-ag struct for this agno */
+	struct xfs_inode *ip;		/* for userdata zeroing method */
 	xfs_fsblock_t	fsbno;		/* file system block number */
 	xfs_agnumber_t	agno;		/* allocation group number */
 	xfs_agblock_t	agbno;		/* allocation group-relative block # */
@@ -120,15 +121,16 @@ typedef struct xfs_alloc_arg {
 	char		wasdel;		/* set if allocation was prev delayed */
 	char		wasfromfl;	/* set if allocation is from freelist */
 	char		isfl;		/* set if is freelist blocks - !acctg */
-	char		userdata;	/* set if this is user data */
+	char		userdata;	/* mask defining userdata treatment */
 	xfs_fsblock_t	firstblock;	/* io first block allocated */
 } xfs_alloc_arg_t;
 
 /*
  * Defines for userdata
  */
-#define XFS_ALLOC_USERDATA		1	/* allocation is for user data*/
-#define XFS_ALLOC_INITIAL_USER_DATA	2	/* special case start of file */
+#define XFS_ALLOC_USERDATA		(1 << 0)/* allocation is for user data*/
+#define XFS_ALLOC_INITIAL_USER_DATA	(1 << 1)/* special case start of file */
+#define XFS_ALLOC_USERDATA_ZERO		(1 << 2)/* zero extent on allocation */
 
 xfs_extlen_t xfs_alloc_longest_free_extent(struct xfs_mount *mp,
 		struct xfs_perag *pag, xfs_extlen_t need);
@@ -233,5 +235,6 @@ xfs_alloc_get_rec(
 
 int xfs_read_agf(struct xfs_mount *mp, struct xfs_trans *tp,
 			xfs_agnumber_t agno, int flags, struct xfs_buf **bpp);
+int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, int flags);
 
 #endif	/* __XFS_ALLOC_H__ */
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index 90de071dd4c2..d9b42425291e 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -118,8 +118,6 @@ xfs_allocbt_free_block(
 	xfs_extent_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1,
 			      XFS_EXTENT_BUSY_SKIP_DISCARD);
 	xfs_trans_agbtree_delta(cur->bc_tp, -1);
-
-	xfs_trans_binval(cur->bc_tp, bp);
 	return 0;
 }
 
@@ -293,14 +291,7 @@ xfs_allocbt_verify(
 	level = be16_to_cpu(block->bb_level);
 	switch (block->bb_magic) {
 	case cpu_to_be32(XFS_ABTB_CRC_MAGIC):
-		if (!xfs_sb_version_hascrc(&mp->m_sb))
-			return false;
-		if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid))
-			return false;
-		if (block->bb_u.s.bb_blkno != cpu_to_be64(bp->b_bn))
-			return false;
-		if (pag &&
-		    be32_to_cpu(block->bb_u.s.bb_owner) != pag->pag_agno)
+		if (!xfs_btree_sblock_v5hdr_verify(bp))
 			return false;
 		/* fall through */
 	case cpu_to_be32(XFS_ABTB_MAGIC):
@@ -311,14 +302,7 @@ xfs_allocbt_verify(
 			return false;
 		break;
 	case cpu_to_be32(XFS_ABTC_CRC_MAGIC):
-		if (!xfs_sb_version_hascrc(&mp->m_sb))
-			return false;
-		if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid))
-			return false;
-		if (block->bb_u.s.bb_blkno != cpu_to_be64(bp->b_bn))
-			return false;
-		if (pag &&
-		    be32_to_cpu(block->bb_u.s.bb_owner) != pag->pag_agno)
+		if (!xfs_btree_sblock_v5hdr_verify(bp))
 			return false;
 		/* fall through */
 	case cpu_to_be32(XFS_ABTC_MAGIC):
@@ -332,21 +316,7 @@ xfs_allocbt_verify(
 		return false;
 	}
 
-	/* numrecs verification */
-	if (be16_to_cpu(block->bb_numrecs) > mp->m_alloc_mxr[level != 0])
-		return false;
-
-	/* sibling pointer verification */
-	if (!block->bb_u.s.bb_leftsib ||
-	    (be32_to_cpu(block->bb_u.s.bb_leftsib) >= mp->m_sb.sb_agblocks &&
-	     block->bb_u.s.bb_leftsib != cpu_to_be32(NULLAGBLOCK)))
-		return false;
-	if (!block->bb_u.s.bb_rightsib ||
-	    (be32_to_cpu(block->bb_u.s.bb_rightsib) >= mp->m_sb.sb_agblocks &&
-	     block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK)))
-		return false;
-
-	return true;
+	return xfs_btree_sblock_verify(bp, mp->m_alloc_mxr[level != 0]);
 }
 
 static void
@@ -379,6 +349,7 @@ xfs_allocbt_write_verify(
 }
 
 const struct xfs_buf_ops xfs_allocbt_buf_ops = {
+	.name = "xfs_allocbt",
 	.verify_read = xfs_allocbt_read_verify,
 	.verify_write = xfs_allocbt_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index ff065578969f..fa3b948ef9c2 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -125,7 +125,7 @@ xfs_attr_get(
 	uint			lock_mode;
 	int			error;
 
-	XFS_STATS_INC(xs_attr_get);
+	XFS_STATS_INC(ip->i_mount, xs_attr_get);
 
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
 		return -EIO;
@@ -207,9 +207,9 @@ xfs_attr_set(
 	struct xfs_trans_res	tres;
 	xfs_fsblock_t		firstblock;
 	int			rsvd = (flags & ATTR_ROOT) != 0;
-	int			error, err2, committed, local;
+	int			error, err2, local;
 
-	XFS_STATS_INC(xs_attr_set);
+	XFS_STATS_INC(mp, xs_attr_set);
 
 	if (XFS_FORCED_SHUTDOWN(dp->i_mount))
 		return -EIO;
@@ -334,25 +334,15 @@ xfs_attr_set(
 		 */
 		xfs_bmap_init(args.flist, args.firstblock);
 		error = xfs_attr_shortform_to_leaf(&args);
-		if (!error) {
-			error = xfs_bmap_finish(&args.trans, args.flist,
-						&committed);
-		}
+		if (!error)
+			error = xfs_bmap_finish(&args.trans, args.flist, dp);
 		if (error) {
-			ASSERT(committed);
 			args.trans = NULL;
 			xfs_bmap_cancel(&flist);
 			goto out;
 		}
 
 		/*
-		 * bmap_finish() may have committed the last trans and started
-		 * a new one.  We need the inode to be in all transactions.
-		 */
-		if (committed)
-			xfs_trans_ijoin(args.trans, dp, 0);
-
-		/*
 		 * Commit the leaf transformation.  We'll need another (linked)
 		 * transaction to add the new attribute to the leaf.
 		 */
@@ -412,7 +402,7 @@ xfs_attr_remove(
 	xfs_fsblock_t		firstblock;
 	int			error;
 
-	XFS_STATS_INC(xs_attr_remove);
+	XFS_STATS_INC(mp, xs_attr_remove);
 
 	if (XFS_FORCED_SHUTDOWN(dp->i_mount))
 		return -EIO;
@@ -568,7 +558,7 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 {
 	xfs_inode_t *dp;
 	struct xfs_buf *bp;
-	int retval, error, committed, forkoff;
+	int retval, error, forkoff;
 
 	trace_xfs_attr_leaf_addname(args);
 
@@ -628,25 +618,15 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 		 */
 		xfs_bmap_init(args->flist, args->firstblock);
 		error = xfs_attr3_leaf_to_node(args);
-		if (!error) {
-			error = xfs_bmap_finish(&args->trans, args->flist,
-						&committed);
-		}
+		if (!error)
+			error = xfs_bmap_finish(&args->trans, args->flist, dp);
 		if (error) {
-			ASSERT(committed);
 			args->trans = NULL;
 			xfs_bmap_cancel(args->flist);
 			return error;
 		}
 
 		/*
-		 * bmap_finish() may have committed the last trans and started
-		 * a new one.  We need the inode to be in all transactions.
-		 */
-		if (committed)
-			xfs_trans_ijoin(args->trans, dp, 0);
-
-		/*
 		 * Commit the current trans (including the inode) and start
 		 * a new one.
 		 */
@@ -729,25 +709,14 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 			xfs_bmap_init(args->flist, args->firstblock);
 			error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 			/* bp is gone due to xfs_da_shrink_inode */
-			if (!error) {
+			if (!error)
 				error = xfs_bmap_finish(&args->trans,
-							args->flist,
-							&committed);
-			}
+							args->flist, dp);
 			if (error) {
-				ASSERT(committed);
 				args->trans = NULL;
 				xfs_bmap_cancel(args->flist);
 				return error;
 			}
-
-			/*
-			 * bmap_finish() may have committed the last trans
-			 * and started a new one.  We need the inode to be
-			 * in all transactions.
-			 */
-			if (committed)
-				xfs_trans_ijoin(args->trans, dp, 0);
 		}
 
 		/*
@@ -775,7 +744,7 @@ xfs_attr_leaf_removename(xfs_da_args_t *args)
 {
 	xfs_inode_t *dp;
 	struct xfs_buf *bp;
-	int error, committed, forkoff;
+	int error, forkoff;
 
 	trace_xfs_attr_leaf_removename(args);
 
@@ -803,23 +772,13 @@ xfs_attr_leaf_removename(xfs_da_args_t *args)
 		xfs_bmap_init(args->flist, args->firstblock);
 		error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 		/* bp is gone due to xfs_da_shrink_inode */
-		if (!error) {
-			error = xfs_bmap_finish(&args->trans, args->flist,
-						&committed);
-		}
+		if (!error)
+			error = xfs_bmap_finish(&args->trans, args->flist, dp);
 		if (error) {
-			ASSERT(committed);
 			args->trans = NULL;
 			xfs_bmap_cancel(args->flist);
 			return error;
 		}
-
-		/*
-		 * bmap_finish() may have committed the last trans and started
-		 * a new one.  We need the inode to be in all transactions.
-		 */
-		if (committed)
-			xfs_trans_ijoin(args->trans, dp, 0);
 	}
 	return 0;
 }
@@ -877,7 +836,7 @@ xfs_attr_node_addname(xfs_da_args_t *args)
 	xfs_da_state_blk_t *blk;
 	xfs_inode_t *dp;
 	xfs_mount_t *mp;
-	int committed, retval, error;
+	int retval, error;
 
 	trace_xfs_attr_node_addname(args);
 
@@ -938,27 +897,16 @@ restart:
 			state = NULL;
 			xfs_bmap_init(args->flist, args->firstblock);
 			error = xfs_attr3_leaf_to_node(args);
-			if (!error) {
+			if (!error)
 				error = xfs_bmap_finish(&args->trans,
-							args->flist,
-							&committed);
-			}
+							args->flist, dp);
 			if (error) {
-				ASSERT(committed);
 				args->trans = NULL;
 				xfs_bmap_cancel(args->flist);
 				goto out;
 			}
 
 			/*
-			 * bmap_finish() may have committed the last trans
-			 * and started a new one.  We need the inode to be
-			 * in all transactions.
-			 */
-			if (committed)
-				xfs_trans_ijoin(args->trans, dp, 0);
-
-			/*
 			 * Commit the node conversion and start the next
 			 * trans in the chain.
 			 */
@@ -977,23 +925,13 @@ restart:
 		 */
 		xfs_bmap_init(args->flist, args->firstblock);
 		error = xfs_da3_split(state);
-		if (!error) {
-			error = xfs_bmap_finish(&args->trans, args->flist,
-						&committed);
-		}
+		if (!error)
+			error = xfs_bmap_finish(&args->trans, args->flist, dp);
 		if (error) {
-			ASSERT(committed);
 			args->trans = NULL;
 			xfs_bmap_cancel(args->flist);
 			goto out;
 		}
-
-		/*
-		 * bmap_finish() may have committed the last trans and started
-		 * a new one.  We need the inode to be in all transactions.
-		 */
-		if (committed)
-			xfs_trans_ijoin(args->trans, dp, 0);
 	} else {
 		/*
 		 * Addition succeeded, update Btree hashvals.
@@ -1086,25 +1024,14 @@ restart:
 		if (retval && (state->path.active > 1)) {
 			xfs_bmap_init(args->flist, args->firstblock);
 			error = xfs_da3_join(state);
-			if (!error) {
+			if (!error)
 				error = xfs_bmap_finish(&args->trans,
-							args->flist,
-							&committed);
-			}
+							args->flist, dp);
 			if (error) {
-				ASSERT(committed);
 				args->trans = NULL;
 				xfs_bmap_cancel(args->flist);
 				goto out;
 			}
-
-			/*
-			 * bmap_finish() may have committed the last trans
-			 * and started a new one.  We need the inode to be
-			 * in all transactions.
-			 */
-			if (committed)
-				xfs_trans_ijoin(args->trans, dp, 0);
 		}
 
 		/*
@@ -1146,7 +1073,7 @@ xfs_attr_node_removename(xfs_da_args_t *args)
 	xfs_da_state_blk_t *blk;
 	xfs_inode_t *dp;
 	struct xfs_buf *bp;
-	int retval, error, committed, forkoff;
+	int retval, error, forkoff;
 
 	trace_xfs_attr_node_removename(args);
 
@@ -1220,24 +1147,13 @@ xfs_attr_node_removename(xfs_da_args_t *args)
 	if (retval && (state->path.active > 1)) {
 		xfs_bmap_init(args->flist, args->firstblock);
 		error = xfs_da3_join(state);
-		if (!error) {
-			error = xfs_bmap_finish(&args->trans, args->flist,
-						&committed);
-		}
+		if (!error)
+			error = xfs_bmap_finish(&args->trans, args->flist, dp);
 		if (error) {
-			ASSERT(committed);
 			args->trans = NULL;
 			xfs_bmap_cancel(args->flist);
 			goto out;
 		}
-
-		/*
-		 * bmap_finish() may have committed the last trans and started
-		 * a new one.  We need the inode to be in all transactions.
-		 */
-		if (committed)
-			xfs_trans_ijoin(args->trans, dp, 0);
-
 		/*
 		 * Commit the Btree join operation and start a new trans.
 		 */
@@ -1265,25 +1181,14 @@ xfs_attr_node_removename(xfs_da_args_t *args)
 			xfs_bmap_init(args->flist, args->firstblock);
 			error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 			/* bp is gone due to xfs_da_shrink_inode */
-			if (!error) {
+			if (!error)
 				error = xfs_bmap_finish(&args->trans,
-							args->flist,
-							&committed);
-			}
+							args->flist, dp);
 			if (error) {
-				ASSERT(committed);
 				args->trans = NULL;
 				xfs_bmap_cancel(args->flist);
 				goto out;
 			}
-
-			/*
-			 * bmap_finish() may have committed the last trans
-			 * and started a new one.  We need the inode to be
-			 * in all transactions.
-			 */
-			if (committed)
-				xfs_trans_ijoin(args->trans, dp, 0);
 		} else
 			xfs_trans_brelse(args->trans, bp);
 	}
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 33df52d97ec7..01a5ecfedfcf 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -41,6 +41,7 @@
 #include "xfs_buf_item.h"
 #include "xfs_cksum.h"
 #include "xfs_dir2.h"
+#include "xfs_log.h"
 
 
 /*
@@ -266,6 +267,8 @@ xfs_attr3_leaf_verify(
 			return false;
 		if (be64_to_cpu(hdr3->info.blkno) != bp->b_bn)
 			return false;
+		if (!xfs_log_check_lsn(mp, be64_to_cpu(hdr3->info.lsn)))
+			return false;
 	} else {
 		if (ichdr.magic != XFS_ATTR_LEAF_MAGIC)
 			return false;
@@ -325,6 +328,7 @@ xfs_attr3_leaf_read_verify(
 }
 
 const struct xfs_buf_ops xfs_attr3_leaf_buf_ops = {
+	.name = "xfs_attr3_leaf",
 	.verify_read = xfs_attr3_leaf_read_verify,
 	.verify_write = xfs_attr3_leaf_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index f38f9bd81557..a572532a55cd 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -107,7 +107,7 @@ xfs_attr3_rmt_verify(
 	if (be32_to_cpu(rmt->rm_bytes) > fsbsize - sizeof(*rmt))
 		return false;
 	if (be32_to_cpu(rmt->rm_offset) +
-				be32_to_cpu(rmt->rm_bytes) > XATTR_SIZE_MAX)
+				be32_to_cpu(rmt->rm_bytes) > XFS_XATTR_SIZE_MAX)
 		return false;
 	if (rmt->rm_owner == 0)
 		return false;
@@ -201,6 +201,7 @@ xfs_attr3_rmt_write_verify(
 }
 
 const struct xfs_buf_ops xfs_attr3_rmt_buf_ops = {
+	.name = "xfs_attr3_rmt",
 	.verify_read = xfs_attr3_rmt_read_verify,
 	.verify_write = xfs_attr3_rmt_write_verify,
 };
@@ -447,8 +448,6 @@ xfs_attr_rmtval_set(
 	 * Roll through the "value", allocating blocks on disk as required.
 	 */
 	while (blkcnt > 0) {
-		int	committed;
-
 		/*
 		 * Allocate a single extent, up to the size of the value.
 		 *
@@ -466,24 +465,14 @@ xfs_attr_rmtval_set(
 		error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
 				  blkcnt, XFS_BMAPI_ATTRFORK, args->firstblock,
 				  args->total, &map, &nmap, args->flist);
-		if (!error) {
-			error = xfs_bmap_finish(&args->trans, args->flist,
-						&committed);
-		}
+		if (!error)
+			error = xfs_bmap_finish(&args->trans, args->flist, dp);
 		if (error) {
-			ASSERT(committed);
 			args->trans = NULL;
 			xfs_bmap_cancel(args->flist);
 			return error;
 		}
 
-		/*
-		 * bmap_finish() may have committed the last trans and started
-		 * a new one.  We need the inode to be in all transactions.
-		 */
-		if (committed)
-			xfs_trans_ijoin(args->trans, dp, 0);
-
 		ASSERT(nmap == 1);
 		ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
 		       (map.br_startblock != HOLESTARTBLOCK));
@@ -614,31 +603,20 @@ xfs_attr_rmtval_remove(
 	blkcnt = args->rmtblkcnt;
 	done = 0;
 	while (!done) {
-		int committed;
-
 		xfs_bmap_init(args->flist, args->firstblock);
 		error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt,
 				    XFS_BMAPI_ATTRFORK, 1, args->firstblock,
 				    args->flist, &done);
-		if (!error) {
+		if (!error)
 			error = xfs_bmap_finish(&args->trans, args->flist,
-						&committed);
-		}
+						args->dp);
 		if (error) {
-			ASSERT(committed);
 			args->trans = NULL;
 			xfs_bmap_cancel(args->flist);
 			return error;
 		}
 
 		/*
-		 * bmap_finish() may have committed the last trans and started
-		 * a new one.  We need the inode to be in all transactions.
-		 */
-		if (committed)
-			xfs_trans_ijoin(args->trans, args->dp, 0);
-
-		/*
 		 * Close out trans and start the next one in the chain.
 		 */
 		error = xfs_trans_roll(&args->trans, args->dp);
diff --git a/fs/xfs/libxfs/xfs_attr_sf.h b/fs/xfs/libxfs/xfs_attr_sf.h
index 919756e3ba53..90928bbe693c 100644
--- a/fs/xfs/libxfs/xfs_attr_sf.h
+++ b/fs/xfs/libxfs/xfs_attr_sf.h
@@ -24,22 +24,6 @@
  * Small attribute lists are packed as tightly as possible so as
  * to fit into the literal area of the inode.
  */
-
-/*
- * Entries are packed toward the top as tight as possible.
- */
-typedef struct xfs_attr_shortform {
-	struct xfs_attr_sf_hdr {	/* constant-structure header block */
-		__be16	totsize;	/* total bytes in shortform list */
-		__u8	count;	/* count of active entries */
-	} hdr;
-	struct xfs_attr_sf_entry {
-		__uint8_t namelen;	/* actual length of name (no NULL) */
-		__uint8_t valuelen;	/* actual length of value (no NULL) */
-		__uint8_t flags;	/* flags bits (see xfs_attr_leaf.h) */
-		__uint8_t nameval[1];	/* name & value bytes concatenated */
-	} list[1];			/* variable sized array */
-} xfs_attr_shortform_t;
 typedef struct xfs_attr_sf_hdr xfs_attr_sf_hdr_t;
 typedef struct xfs_attr_sf_entry xfs_attr_sf_entry_t;
 
diff --git a/fs/xfs/libxfs/xfs_bit.c b/fs/xfs/libxfs/xfs_bit.c
index 0e8885a59646..0a94cce5ea35 100644
--- a/fs/xfs/libxfs/xfs_bit.c
+++ b/fs/xfs/libxfs/xfs_bit.c
@@ -32,13 +32,13 @@ int
 xfs_bitmap_empty(uint *map, uint size)
 {
 	uint i;
-	uint ret = 0;
 
 	for (i = 0; i < size; i++) {
-		ret |= map[i];
+		if (map[i] != 0)
+			return 0;
 	}
 
-	return (ret == 0);
+	return 1;
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 8e2010d53b07..ce41d7fe753c 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -325,9 +325,11 @@ xfs_check_block(
 
 /*
  * Check that the extents for the inode ip are in the right order in all
- * btree leaves.
+ * btree leaves. THis becomes prohibitively expensive for large extent count
+ * files, so don't bother with inodes that have more than 10,000 extents in
+ * them. The btree record ordering checks will still be done, so for such large
+ * bmapbt constructs that is going to catch most corruptions.
  */
-
 STATIC void
 xfs_bmap_check_leaf_extents(
 	xfs_btree_cur_t		*cur,	/* btree cursor or null */
@@ -352,6 +354,10 @@ xfs_bmap_check_leaf_extents(
 		return;
 	}
 
+	/* skip large extent count inodes */
+	if (ip->i_d.di_nextents > 10000)
+		return;
+
 	bno = NULLFSBLOCK;
 	mp = ip->i_mount;
 	ifp = XFS_IFORK_PTR(ip, whichfork);
@@ -471,10 +477,7 @@ xfs_bmap_check_leaf_extents(
 		}
 		block = XFS_BUF_TO_BLOCK(bp);
 	}
-	if (bp_release) {
-		bp_release = 0;
-		xfs_trans_brelse(NULL, bp);
-	}
+
 	return;
 
 error0:
@@ -906,7 +909,7 @@ xfs_bmap_local_to_extents(
 	 * We don't want to deal with the case of keeping inode data inline yet.
 	 * So sending the data fork of a regular inode is invalid.
 	 */
-	ASSERT(!(S_ISREG(ip->i_d.di_mode) && whichfork == XFS_DATA_FORK));
+	ASSERT(!(S_ISREG(VFS_I(ip)->i_mode) && whichfork == XFS_DATA_FORK));
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL);
 
@@ -948,14 +951,16 @@ xfs_bmap_local_to_extents(
 	bp = xfs_btree_get_bufl(args.mp, tp, args.fsbno, 0);
 
 	/*
-	 * Initialise the block and copy the data
+	 * Initialize the block, copy the data and log the remote buffer.
 	 *
-	 * Note: init_fn must set the buffer log item type correctly!
+	 * The callout is responsible for logging because the remote format
+	 * might differ from the local format and thus we don't know how much to
+	 * log here. Note that init_fn must also set the buffer log item type
+	 * correctly.
 	 */
 	init_fn(tp, bp, ip, ifp);
 
-	/* account for the change in fork size and log everything */
-	xfs_trans_log_buf(tp, bp, 0, ifp->if_bytes - 1);
+	/* account for the change in fork size */
 	xfs_idata_realloc(ip, -ifp->if_bytes, whichfork);
 	xfs_bmap_local_to_extents_empty(ip, whichfork);
 	flags |= XFS_ILOG_CORE;
@@ -1071,7 +1076,7 @@ xfs_bmap_add_attrfork_local(
 	if (ip->i_df.if_bytes <= XFS_IFORK_DSIZE(ip))
 		return 0;
 
-	if (S_ISDIR(ip->i_d.di_mode)) {
+	if (S_ISDIR(VFS_I(ip)->i_mode)) {
 		memset(&dargs, 0, sizeof(dargs));
 		dargs.geo = ip->i_mount->m_dir_geo;
 		dargs.dp = ip;
@@ -1083,7 +1088,7 @@ xfs_bmap_add_attrfork_local(
 		return xfs_dir2_sf_to_block(&dargs);
 	}
 
-	if (S_ISLNK(ip->i_d.di_mode))
+	if (S_ISLNK(VFS_I(ip)->i_mode))
 		return xfs_bmap_local_to_extents(tp, ip, firstblock, 1,
 						 flags, XFS_DATA_FORK,
 						 xfs_symlink_local_to_remote);
@@ -1109,7 +1114,6 @@ xfs_bmap_add_attrfork(
 	xfs_trans_t		*tp;		/* transaction pointer */
 	int			blks;		/* space reservation */
 	int			version = 1;	/* superblock attr version */
-	int			committed;	/* xaction was committed */
 	int			logflags;	/* logging flags */
 	int			error;		/* error return value */
 
@@ -1212,7 +1216,7 @@ xfs_bmap_add_attrfork(
 			xfs_log_sb(tp);
 	}
 
-	error = xfs_bmap_finish(&tp, &flist, &committed);
+	error = xfs_bmap_finish(&tp, &flist, NULL);
 	if (error)
 		goto bmap_cancel;
 	error = xfs_trans_commit(tp);
@@ -1435,7 +1439,7 @@ xfs_bmap_search_extents(
 	xfs_ifork_t	*ifp;		/* inode fork pointer */
 	xfs_bmbt_rec_host_t  *ep;            /* extent record pointer */
 
-	XFS_STATS_INC(xs_look_exlist);
+	XFS_STATS_INC(ip->i_mount, xs_look_exlist);
 	ifp = XFS_IFORK_PTR(ip, fork);
 
 	ep = xfs_bmap_search_multi_extents(ifp, bno, eofp, lastxp, gotp, prevp);
@@ -1721,10 +1725,11 @@ xfs_bmap_add_extent_delay_real(
 	xfs_filblks_t		temp=0;	/* value for da_new calculations */
 	xfs_filblks_t		temp2=0;/* value for da_new calculations */
 	int			tmp_rval;	/* partial logging flags */
+	int			whichfork = XFS_DATA_FORK;
 	struct xfs_mount	*mp;
 
-	mp  = bma->tp ? bma->tp->t_mountp : NULL;
-	ifp = XFS_IFORK_PTR(bma->ip, XFS_DATA_FORK);
+	mp = bma->ip->i_mount;
+	ifp = XFS_IFORK_PTR(bma->ip, whichfork);
 
 	ASSERT(bma->idx >= 0);
 	ASSERT(bma->idx <= ifp->if_bytes / sizeof(struct xfs_bmbt_rec));
@@ -1732,7 +1737,7 @@ xfs_bmap_add_extent_delay_real(
 	ASSERT(!bma->cur ||
 	       (bma->cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL));
 
-	XFS_STATS_INC(xs_add_exlist);
+	XFS_STATS_INC(mp, xs_add_exlist);
 
 #define	LEFT		r[0]
 #define	RIGHT		r[1]
@@ -1783,7 +1788,7 @@ xfs_bmap_add_extent_delay_real(
 	 * Don't set contiguous if the combined extent would be too large.
 	 * Also check for all-three-contiguous being too large.
 	 */
-	if (bma->idx < bma->ip->i_df.if_bytes / (uint)sizeof(xfs_bmbt_rec_t) - 1) {
+	if (bma->idx < ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t) - 1) {
 		state |= BMAP_RIGHT_VALID;
 		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, bma->idx + 1), &RIGHT);
 
@@ -2014,10 +2019,10 @@ xfs_bmap_add_extent_delay_real(
 			XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
 		}
 
-		if (xfs_bmap_needs_btree(bma->ip, XFS_DATA_FORK)) {
+		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
 					bma->firstblock, bma->flist,
-					&bma->cur, 1, &tmp_rval, XFS_DATA_FORK);
+					&bma->cur, 1, &tmp_rval, whichfork);
 			rval |= tmp_rval;
 			if (error)
 				goto done;
@@ -2098,10 +2103,10 @@ xfs_bmap_add_extent_delay_real(
 			XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
 		}
 
-		if (xfs_bmap_needs_btree(bma->ip, XFS_DATA_FORK)) {
+		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
 				bma->firstblock, bma->flist, &bma->cur, 1,
-				&tmp_rval, XFS_DATA_FORK);
+				&tmp_rval, whichfork);
 			rval |= tmp_rval;
 			if (error)
 				goto done;
@@ -2167,10 +2172,10 @@ xfs_bmap_add_extent_delay_real(
 			XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
 		}
 
-		if (xfs_bmap_needs_btree(bma->ip, XFS_DATA_FORK)) {
+		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
 					bma->firstblock, bma->flist, &bma->cur,
-					1, &tmp_rval, XFS_DATA_FORK);
+					1, &tmp_rval, whichfork);
 			rval |= tmp_rval;
 			if (error)
 				goto done;
@@ -2213,13 +2218,13 @@ xfs_bmap_add_extent_delay_real(
 	}
 
 	/* convert to a btree if necessary */
-	if (xfs_bmap_needs_btree(bma->ip, XFS_DATA_FORK)) {
+	if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 		int	tmp_logflags;	/* partial log flag return val */
 
 		ASSERT(bma->cur == NULL);
 		error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
 				bma->firstblock, bma->flist, &bma->cur,
-				da_old > 0, &tmp_logflags, XFS_DATA_FORK);
+				da_old > 0, &tmp_logflags, whichfork);
 		bma->logflags |= tmp_logflags;
 		if (error)
 			goto done;
@@ -2240,7 +2245,7 @@ xfs_bmap_add_extent_delay_real(
 	if (bma->cur)
 		bma->cur->bc_private.b.allocated = 0;
 
-	xfs_bmap_check_leaf_extents(bma->cur, bma->ip, XFS_DATA_FORK);
+	xfs_bmap_check_leaf_extents(bma->cur, bma->ip, whichfork);
 done:
 	bma->logflags |= rval;
 	return error;
@@ -2286,7 +2291,7 @@ xfs_bmap_add_extent_unwritten_real(
 	ASSERT(*idx <= ifp->if_bytes / sizeof(struct xfs_bmbt_rec));
 	ASSERT(!isnullstartblock(new->br_startblock));
 
-	XFS_STATS_INC(xs_add_exlist);
+	XFS_STATS_INC(mp, xs_add_exlist);
 
 #define	LEFT		r[0]
 #define	RIGHT		r[1]
@@ -2937,7 +2942,7 @@ xfs_bmap_add_extent_hole_real(
 	int			state;	/* state bits, accessed thru macros */
 	struct xfs_mount	*mp;
 
-	mp = bma->tp ? bma->tp->t_mountp : NULL;
+	mp = bma->ip->i_mount;
 	ifp = XFS_IFORK_PTR(bma->ip, whichfork);
 
 	ASSERT(bma->idx >= 0);
@@ -2946,7 +2951,7 @@ xfs_bmap_add_extent_hole_real(
 	ASSERT(!bma->cur ||
 	       !(bma->cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL));
 
-	XFS_STATS_INC(xs_add_exlist);
+	XFS_STATS_INC(mp, xs_add_exlist);
 
 	state = 0;
 	if (whichfork == XFS_ATTR_FORK)
@@ -3737,11 +3742,11 @@ xfs_bmap_btalloc(
 		args.prod = align;
 		if ((args.mod = (xfs_extlen_t)do_mod(ap->offset, args.prod)))
 			args.mod = (xfs_extlen_t)(args.prod - args.mod);
-	} else if (mp->m_sb.sb_blocksize >= PAGE_CACHE_SIZE) {
+	} else if (mp->m_sb.sb_blocksize >= PAGE_SIZE) {
 		args.prod = 1;
 		args.mod = 0;
 	} else {
-		args.prod = PAGE_CACHE_SIZE >> mp->m_sb.sb_blocklog;
+		args.prod = PAGE_SIZE >> mp->m_sb.sb_blocklog;
 		if ((args.mod = (xfs_extlen_t)(do_mod(ap->offset, args.prod))))
 			args.mod = (xfs_extlen_t)(args.prod - args.mod);
 	}
@@ -3800,8 +3805,13 @@ xfs_bmap_btalloc(
 	args.wasdel = ap->wasdel;
 	args.isfl = 0;
 	args.userdata = ap->userdata;
-	if ((error = xfs_alloc_vextent(&args)))
+	if (ap->userdata & XFS_ALLOC_USERDATA_ZERO)
+		args.ip = ap->ip;
+
+	error = xfs_alloc_vextent(&args);
+	if (error)
 		return error;
+
 	if (tryagain && args.fsbno == NULLFSBLOCK) {
 		/*
 		 * Exact allocation failed. Now try with alignment
@@ -4036,7 +4046,7 @@ xfs_bmapi_read(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	XFS_STATS_INC(xs_blk_mapr);
+	XFS_STATS_INC(mp, xs_blk_mapr);
 
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 
@@ -4221,7 +4231,7 @@ xfs_bmapi_delay(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	XFS_STATS_INC(xs_blk_mapw);
+	XFS_STATS_INC(mp, xs_blk_mapw);
 
 	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
 		error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
@@ -4300,11 +4310,14 @@ xfs_bmapi_allocate(
 
 	/*
 	 * Indicate if this is the first user data in the file, or just any
-	 * user data.
+	 * user data. And if it is userdata, indicate whether it needs to
+	 * be initialised to zero during allocation.
 	 */
 	if (!(bma->flags & XFS_BMAPI_METADATA)) {
 		bma->userdata = (bma->offset == 0) ?
 			XFS_ALLOC_INITIAL_USER_DATA : XFS_ALLOC_USERDATA;
+		if (bma->flags & XFS_BMAPI_ZERO)
+			bma->userdata |= XFS_ALLOC_USERDATA_ZERO;
 	}
 
 	bma->minlen = (bma->flags & XFS_BMAPI_CONTIG) ? bma->length : 1;
@@ -4419,6 +4432,17 @@ xfs_bmapi_convert_unwritten(
 	mval->br_state = (mval->br_state == XFS_EXT_UNWRITTEN)
 				? XFS_EXT_NORM : XFS_EXT_UNWRITTEN;
 
+	/*
+	 * Before insertion into the bmbt, zero the range being converted
+	 * if required.
+	 */
+	if (flags & XFS_BMAPI_ZERO) {
+		error = xfs_zero_extent(bma->ip, mval->br_startblock,
+					mval->br_blockcount);
+		if (error)
+			return error;
+	}
+
 	error = xfs_bmap_add_extent_unwritten_real(bma->tp, bma->ip, &bma->idx,
 			&bma->cur, mval, bma->firstblock, bma->flist,
 			&tmp_logflags);
@@ -4512,6 +4536,18 @@ xfs_bmapi_write(
 	ASSERT(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_LOCAL);
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 
+	/* zeroing is for currently only for data extents, not metadata */
+	ASSERT((flags & (XFS_BMAPI_METADATA | XFS_BMAPI_ZERO)) !=
+			(XFS_BMAPI_METADATA | XFS_BMAPI_ZERO));
+	/*
+	 * we can allocate unwritten extents or pre-zero allocated blocks,
+	 * but it makes no sense to do both at once. This would result in
+	 * zeroing the unwritten extent twice, but it still being an
+	 * unwritten extent....
+	 */
+	ASSERT((flags & (XFS_BMAPI_PREALLOC | XFS_BMAPI_ZERO)) !=
+			(XFS_BMAPI_PREALLOC | XFS_BMAPI_ZERO));
+
 	if (unlikely(XFS_TEST_ERROR(
 	    (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
 	     XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE),
@@ -4525,7 +4561,7 @@ xfs_bmapi_write(
 
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 
-	XFS_STATS_INC(xs_blk_mapw);
+	XFS_STATS_INC(mp, xs_blk_mapw);
 
 	if (*firstblock == NULLFSBLOCK) {
 		if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE)
@@ -4682,6 +4718,66 @@ error0:
 }
 
 /*
+ * When a delalloc extent is split (e.g., due to a hole punch), the original
+ * indlen reservation must be shared across the two new extents that are left
+ * behind.
+ *
+ * Given the original reservation and the worst case indlen for the two new
+ * extents (as calculated by xfs_bmap_worst_indlen()), split the original
+ * reservation fairly across the two new extents. If necessary, steal available
+ * blocks from a deleted extent to make up a reservation deficiency (e.g., if
+ * ores == 1). The number of stolen blocks is returned. The availability and
+ * subsequent accounting of stolen blocks is the responsibility of the caller.
+ */
+static xfs_filblks_t
+xfs_bmap_split_indlen(
+	xfs_filblks_t			ores,		/* original res. */
+	xfs_filblks_t			*indlen1,	/* ext1 worst indlen */
+	xfs_filblks_t			*indlen2,	/* ext2 worst indlen */
+	xfs_filblks_t			avail)		/* stealable blocks */
+{
+	xfs_filblks_t			len1 = *indlen1;
+	xfs_filblks_t			len2 = *indlen2;
+	xfs_filblks_t			nres = len1 + len2; /* new total res. */
+	xfs_filblks_t			stolen = 0;
+
+	/*
+	 * Steal as many blocks as we can to try and satisfy the worst case
+	 * indlen for both new extents.
+	 */
+	while (nres > ores && avail) {
+		nres--;
+		avail--;
+		stolen++;
+	}
+
+	/*
+	 * The only blocks available are those reserved for the original
+	 * extent and what we can steal from the extent being removed.
+	 * If this still isn't enough to satisfy the combined
+	 * requirements for the two new extents, skim blocks off of each
+	 * of the new reservations until they match what is available.
+	 */
+	while (nres > ores) {
+		if (len1) {
+			len1--;
+			nres--;
+		}
+		if (nres == ores)
+			break;
+		if (len2) {
+			len2--;
+			nres--;
+		}
+	}
+
+	*indlen1 = len1;
+	*indlen2 = len2;
+
+	return stolen;
+}
+
+/*
  * Called by xfs_bmapi to update file extent records and the btree
  * after removing space (or undoing a delayed allocation).
  */
@@ -4718,12 +4814,12 @@ xfs_bmap_del_extent(
 	xfs_filblks_t		temp2;	/* for indirect length calculations */
 	int			state = 0;
 
-	XFS_STATS_INC(xs_del_exlist);
+	mp = ip->i_mount;
+	XFS_STATS_INC(mp, xs_del_exlist);
 
 	if (whichfork == XFS_ATTR_FORK)
 		state |= BMAP_ATTRFORK;
 
-	mp = ip->i_mount;
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	ASSERT((*idx >= 0) && (*idx < ifp->if_bytes /
 		(uint)sizeof(xfs_bmbt_rec_t)));
@@ -4945,28 +5041,29 @@ xfs_bmap_del_extent(
 			XFS_IFORK_NEXT_SET(ip, whichfork,
 				XFS_IFORK_NEXTENTS(ip, whichfork) + 1);
 		} else {
+			xfs_filblks_t	stolen;
 			ASSERT(whichfork == XFS_DATA_FORK);
-			temp = xfs_bmap_worst_indlen(ip, temp);
+
+			/*
+			 * Distribute the original indlen reservation across the
+			 * two new extents. Steal blocks from the deleted extent
+			 * if necessary. Stealing blocks simply fudges the
+			 * fdblocks accounting in xfs_bunmapi().
+			 */
+			temp = xfs_bmap_worst_indlen(ip, got.br_blockcount);
+			temp2 = xfs_bmap_worst_indlen(ip, new.br_blockcount);
+			stolen = xfs_bmap_split_indlen(da_old, &temp, &temp2,
+						       del->br_blockcount);
+			da_new = temp + temp2 - stolen;
+			del->br_blockcount -= stolen;
+
+			/*
+			 * Set the reservation for each extent. Warn if either
+			 * is zero as this can lead to delalloc problems.
+			 */
+			WARN_ON_ONCE(!temp || !temp2);
 			xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
-			temp2 = xfs_bmap_worst_indlen(ip, temp2);
 			new.br_startblock = nullstartblock((int)temp2);
-			da_new = temp + temp2;
-			while (da_new > da_old) {
-				if (temp) {
-					temp--;
-					da_new--;
-					xfs_bmbt_set_startblock(ep,
-						nullstartblock((int)temp));
-				}
-				if (da_new == da_old)
-					break;
-				if (temp2) {
-					temp2--;
-					da_new--;
-					new.br_startblock =
-						nullstartblock((int)temp2);
-				}
-			}
 		}
 		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
 		xfs_iext_insert(ip, *idx + 1, 1, &new, state);
@@ -5070,7 +5167,7 @@ xfs_bunmapi(
 		*done = 1;
 		return 0;
 	}
-	XFS_STATS_INC(xs_blk_unmap);
+	XFS_STATS_INC(mp, xs_blk_unmap);
 	isrt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(ip);
 	start = bno;
 	bno = start + len - 1;
@@ -5171,7 +5268,7 @@ xfs_bunmapi(
 			 * This is better than zeroing it.
 			 */
 			ASSERT(del.br_state == XFS_EXT_NORM);
-			ASSERT(xfs_trans_get_block_res(tp) > 0);
+			ASSERT(tp->t_blk_res > 0);
 			/*
 			 * If this spans a realtime extent boundary,
 			 * chop it back to the start of the one we end at.
@@ -5202,7 +5299,7 @@ xfs_bunmapi(
 				del.br_startblock += mod;
 			} else if ((del.br_startoff == start &&
 				    (del.br_state == XFS_EXT_UNWRITTEN ||
-				     xfs_trans_get_block_res(tp) == 0)) ||
+				     tp->t_blk_res == 0)) ||
 				   !xfs_sb_version_hasextflgbit(&mp->m_sb)) {
 				/*
 				 * Can't make it unwritten.  There isn't
@@ -5257,9 +5354,37 @@ xfs_bunmapi(
 				goto nodelete;
 			}
 		}
+
+		/*
+		 * If it's the case where the directory code is running
+		 * with no block reservation, and the deleted block is in
+		 * the middle of its extent, and the resulting insert
+		 * of an extent would cause transformation to btree format,
+		 * then reject it.  The calling code will then swap
+		 * blocks around instead.
+		 * We have to do this now, rather than waiting for the
+		 * conversion to btree format, since the transaction
+		 * will be dirty.
+		 */
+		if (!wasdel && tp->t_blk_res == 0 &&
+		    XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS &&
+		    XFS_IFORK_NEXTENTS(ip, whichfork) >= /* Note the >= */
+			XFS_IFORK_MAXEXT(ip, whichfork) &&
+		    del.br_startoff > got.br_startoff &&
+		    del.br_startoff + del.br_blockcount <
+		    got.br_startoff + got.br_blockcount) {
+			error = -ENOSPC;
+			goto error0;
+		}
+
+		/*
+		 * Unreserve quota and update realtime free space, if
+		 * appropriate. If delayed allocation, update the inode delalloc
+		 * counter now and wait to update the sb counters as
+		 * xfs_bmap_del_extent() might need to borrow some blocks.
+		 */
 		if (wasdel) {
 			ASSERT(startblockval(del.br_startblock) > 0);
-			/* Update realtime/data freespace, unreserve quota */
 			if (isrt) {
 				xfs_filblks_t rtexts;
 
@@ -5270,8 +5395,6 @@ xfs_bunmapi(
 					ip, -((long)del.br_blockcount), 0,
 					XFS_QMOPT_RES_RTBLKS);
 			} else {
-				xfs_mod_fdblocks(mp, (int64_t)del.br_blockcount,
-						 false);
 				(void)xfs_trans_reserve_quota_nblks(NULL,
 					ip, -((long)del.br_blockcount), 0,
 					XFS_QMOPT_RES_REGBLKS);
@@ -5282,32 +5405,16 @@ xfs_bunmapi(
 					XFS_BTCUR_BPRV_WASDEL;
 		} else if (cur)
 			cur->bc_private.b.flags &= ~XFS_BTCUR_BPRV_WASDEL;
-		/*
-		 * If it's the case where the directory code is running
-		 * with no block reservation, and the deleted block is in
-		 * the middle of its extent, and the resulting insert
-		 * of an extent would cause transformation to btree format,
-		 * then reject it.  The calling code will then swap
-		 * blocks around instead.
-		 * We have to do this now, rather than waiting for the
-		 * conversion to btree format, since the transaction
-		 * will be dirty.
-		 */
-		if (!wasdel && xfs_trans_get_block_res(tp) == 0 &&
-		    XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS &&
-		    XFS_IFORK_NEXTENTS(ip, whichfork) >= /* Note the >= */
-			XFS_IFORK_MAXEXT(ip, whichfork) &&
-		    del.br_startoff > got.br_startoff &&
-		    del.br_startoff + del.br_blockcount <
-		    got.br_startoff + got.br_blockcount) {
-			error = -ENOSPC;
-			goto error0;
-		}
+
 		error = xfs_bmap_del_extent(ip, tp, &lastx, flist, cur, &del,
 				&tmp_logflags, whichfork);
 		logflags |= tmp_logflags;
 		if (error)
 			goto error0;
+
+		if (!isrt && wasdel)
+			xfs_mod_fdblocks(mp, (int64_t)del.br_blockcount, false);
+
 		bno = del.br_startoff - 1;
 nodelete:
 		/*
@@ -5917,7 +6024,6 @@ xfs_bmap_split_extent(
 	struct xfs_trans        *tp;
 	struct xfs_bmap_free    free_list;
 	xfs_fsblock_t           firstfsb;
-	int                     committed;
 	int                     error;
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
@@ -5938,7 +6044,7 @@ xfs_bmap_split_extent(
 	if (error)
 		goto out;
 
-	error = xfs_bmap_finish(&tp, &free_list, &committed);
+	error = xfs_bmap_finish(&tp, &free_list, NULL);
 	if (error)
 		goto out;
 
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 6aaa0c1c7200..423a34e832bd 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -52,9 +52,9 @@ struct xfs_bmalloca {
 	xfs_extlen_t		minleft; /* amount must be left after alloc */
 	bool			eof;	/* set if allocating past last extent */
 	bool			wasdel;	/* replacing a delayed allocation */
-	bool			userdata;/* set if is user data */
 	bool			aeof;	/* allocated space at eof */
 	bool			conv;	/* overwriting unwritten extents */
+	char			userdata;/* userdata mask */
 	int			flags;
 };
 
@@ -109,6 +109,14 @@ typedef	struct xfs_bmap_free
  */
 #define XFS_BMAPI_CONVERT	0x040
 
+/*
+ * allocate zeroed extents - this requires all newly allocated user data extents
+ * to be initialised to zero. It will be ignored if XFS_BMAPI_METADATA is set.
+ * Use in conjunction with XFS_BMAPI_CONVERT to convert unwritten extents found
+ * during the allocation range to zeroed written extents.
+ */
+#define XFS_BMAPI_ZERO		0x080
+
 #define XFS_BMAPI_FLAGS \
 	{ XFS_BMAPI_ENTIRE,	"ENTIRE" }, \
 	{ XFS_BMAPI_METADATA,	"METADATA" }, \
@@ -116,7 +124,8 @@ typedef	struct xfs_bmap_free
 	{ XFS_BMAPI_PREALLOC,	"PREALLOC" }, \
 	{ XFS_BMAPI_IGSTATE,	"IGSTATE" }, \
 	{ XFS_BMAPI_CONTIG,	"CONTIG" }, \
-	{ XFS_BMAPI_CONVERT,	"CONVERT" }
+	{ XFS_BMAPI_CONVERT,	"CONVERT" }, \
+	{ XFS_BMAPI_ZERO,	"ZERO" }
 
 
 static inline int xfs_bmapi_aflag(int w)
@@ -186,7 +195,7 @@ void	xfs_bmap_add_free(xfs_fsblock_t bno, xfs_filblks_t len,
 		struct xfs_bmap_free *flist, struct xfs_mount *mp);
 void	xfs_bmap_cancel(struct xfs_bmap_free *flist);
 int	xfs_bmap_finish(struct xfs_trans **tp, struct xfs_bmap_free *flist,
-			int *committed);
+			struct xfs_inode *ip);
 void	xfs_bmap_compute_maxlevels(struct xfs_mount *mp, int whichfork);
 int	xfs_bmap_first_unused(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_extlen_t len, xfs_fileoff_t *unused, int whichfork);
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 6b0cf6546a82..6282f6e708af 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -461,7 +461,7 @@ xfs_bmbt_alloc_block(
 		 * reservation amount is insufficient then we may fail a
 		 * block allocation here and corrupt the filesystem.
 		 */
-		args.minleft = xfs_trans_get_block_res(args.tp);
+		args.minleft = args.tp->t_blk_res;
 	} else if (cur->bc_private.b.flist->xbf_low) {
 		args.type = XFS_ALLOCTYPE_START_BNO;
 	} else {
@@ -470,7 +470,7 @@ xfs_bmbt_alloc_block(
 
 	args.minlen = args.maxlen = args.prod = 1;
 	args.wasdel = cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL;
-	if (!args.wasdel && xfs_trans_get_block_res(args.tp) == 0) {
+	if (!args.wasdel && args.tp->t_blk_res == 0) {
 		error = -ENOSPC;
 		goto error0;
 	}
@@ -531,7 +531,6 @@ xfs_bmbt_free_block(
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
-	xfs_trans_binval(tp, bp);
 	return 0;
 }
 
@@ -720,6 +719,7 @@ xfs_bmbt_write_verify(
 }
 
 const struct xfs_buf_ops xfs_bmbt_buf_ops = {
+	.name = "xfs_bmbt",
 	.verify_read = xfs_bmbt_read_verify,
 	.verify_write = xfs_bmbt_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index f7d7ee7a2607..1f88e1ce770f 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -32,6 +32,7 @@
 #include "xfs_trace.h"
 #include "xfs_cksum.h"
 #include "xfs_alloc.h"
+#include "xfs_log.h"
 
 /*
  * Cursor allocation zone.
@@ -222,7 +223,7 @@ xfs_btree_check_ptr(
  * long-form btree header.
  *
  * Prior to calculting the CRC, pull the LSN out of the buffer log item and put
- * it into the buffer so recovery knows what the last modifcation was that made
+ * it into the buffer so recovery knows what the last modification was that made
  * it to disk.
  */
 void
@@ -243,8 +244,14 @@ bool
 xfs_btree_lblock_verify_crc(
 	struct xfs_buf		*bp)
 {
-	if (xfs_sb_version_hascrc(&bp->b_target->bt_mount->m_sb))
+	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
+	struct xfs_mount	*mp = bp->b_target->bt_mount;
+
+	if (xfs_sb_version_hascrc(&mp->m_sb)) {
+		if (!xfs_log_check_lsn(mp, be64_to_cpu(block->bb_u.l.bb_lsn)))
+			return false;
 		return xfs_buf_verify_cksum(bp, XFS_BTREE_LBLOCK_CRC_OFF);
+	}
 
 	return true;
 }
@@ -254,7 +261,7 @@ xfs_btree_lblock_verify_crc(
  * short-form btree header.
  *
  * Prior to calculting the CRC, pull the LSN out of the buffer log item and put
- * it into the buffer so recovery knows what the last modifcation was that made
+ * it into the buffer so recovery knows what the last modification was that made
  * it to disk.
  */
 void
@@ -275,12 +282,33 @@ bool
 xfs_btree_sblock_verify_crc(
 	struct xfs_buf		*bp)
 {
-	if (xfs_sb_version_hascrc(&bp->b_target->bt_mount->m_sb))
+	struct xfs_btree_block  *block = XFS_BUF_TO_BLOCK(bp);
+	struct xfs_mount	*mp = bp->b_target->bt_mount;
+
+	if (xfs_sb_version_hascrc(&mp->m_sb)) {
+		if (!xfs_log_check_lsn(mp, be64_to_cpu(block->bb_u.s.bb_lsn)))
+			return false;
 		return xfs_buf_verify_cksum(bp, XFS_BTREE_SBLOCK_CRC_OFF);
+	}
 
 	return true;
 }
 
+static int
+xfs_btree_free_block(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp)
+{
+	int			error;
+
+	error = cur->bc_ops->free_block(cur, bp);
+	if (!error) {
+		xfs_trans_binval(cur->bc_tp, bp);
+		XFS_BTREE_STATS_INC(cur, free);
+	}
+	return error;
+}
+
 /*
  * Delete the btree cursor.
  */
@@ -3196,6 +3224,7 @@ xfs_btree_kill_iroot(
 	int			level;
 	int			index;
 	int			numrecs;
+	int			error;
 #ifdef DEBUG
 	union xfs_btree_ptr	ptr;
 	int			i;
@@ -3259,8 +3288,6 @@ xfs_btree_kill_iroot(
 	cpp = xfs_btree_ptr_addr(cur, 1, cblock);
 #ifdef DEBUG
 	for (i = 0; i < numrecs; i++) {
-		int		error;
-
 		error = xfs_btree_check_ptr(cur, cpp, i, level - 1);
 		if (error) {
 			XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
@@ -3270,8 +3297,11 @@ xfs_btree_kill_iroot(
 #endif
 	xfs_btree_copy_ptrs(cur, pp, cpp, numrecs);
 
-	cur->bc_ops->free_block(cur, cbp);
-	XFS_BTREE_STATS_INC(cur, free);
+	error = xfs_btree_free_block(cur, cbp);
+	if (error) {
+		XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
+		return error;
+	}
 
 	cur->bc_bufs[level - 1] = NULL;
 	be16_add_cpu(&block->bb_level, -1);
@@ -3304,14 +3334,12 @@ xfs_btree_kill_root(
 	 */
 	cur->bc_ops->set_root(cur, newroot, -1);
 
-	error = cur->bc_ops->free_block(cur, bp);
+	error = xfs_btree_free_block(cur, bp);
 	if (error) {
 		XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
 		return error;
 	}
 
-	XFS_BTREE_STATS_INC(cur, free);
-
 	cur->bc_bufs[level] = NULL;
 	cur->bc_ra[level] = 0;
 	cur->bc_nlevels--;
@@ -3817,10 +3845,9 @@ xfs_btree_delrec(
 	}
 
 	/* Free the deleted block. */
-	error = cur->bc_ops->free_block(cur, rbp);
+	error = xfs_btree_free_block(cur, rbp);
 	if (error)
 		goto error0;
-	XFS_BTREE_STATS_INC(cur, free);
 
 	/*
 	 * If we joined with the left neighbor, set the buffer in the
@@ -4067,3 +4094,61 @@ xfs_btree_change_owner(
 
 	return 0;
 }
+
+/**
+ * xfs_btree_sblock_v5hdr_verify() -- verify the v5 fields of a short-format
+ *				      btree block
+ *
+ * @bp: buffer containing the btree block
+ * @max_recs: pointer to the m_*_mxr max records field in the xfs mount
+ * @pag_max_level: pointer to the per-ag max level field
+ */
+bool
+xfs_btree_sblock_v5hdr_verify(
+	struct xfs_buf		*bp)
+{
+	struct xfs_mount	*mp = bp->b_target->bt_mount;
+	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
+	struct xfs_perag	*pag = bp->b_pag;
+
+	if (!xfs_sb_version_hascrc(&mp->m_sb))
+		return false;
+	if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid))
+		return false;
+	if (block->bb_u.s.bb_blkno != cpu_to_be64(bp->b_bn))
+		return false;
+	if (pag && be32_to_cpu(block->bb_u.s.bb_owner) != pag->pag_agno)
+		return false;
+	return true;
+}
+
+/**
+ * xfs_btree_sblock_verify() -- verify a short-format btree block
+ *
+ * @bp: buffer containing the btree block
+ * @max_recs: maximum records allowed in this btree node
+ */
+bool
+xfs_btree_sblock_verify(
+	struct xfs_buf		*bp,
+	unsigned int		max_recs)
+{
+	struct xfs_mount	*mp = bp->b_target->bt_mount;
+	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
+
+	/* numrecs verification */
+	if (be16_to_cpu(block->bb_numrecs) > max_recs)
+		return false;
+
+	/* sibling pointer verification */
+	if (!block->bb_u.s.bb_leftsib ||
+	    (be32_to_cpu(block->bb_u.s.bb_leftsib) >= mp->m_sb.sb_agblocks &&
+	     block->bb_u.s.bb_leftsib != cpu_to_be32(NULLAGBLOCK)))
+		return false;
+	if (!block->bb_u.s.bb_rightsib ||
+	    (be32_to_cpu(block->bb_u.s.bb_rightsib) >= mp->m_sb.sb_agblocks &&
+	     block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK)))
+		return false;
+
+	return true;
+}
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 8f18bab73ea5..2e874be70209 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -84,31 +84,38 @@ union xfs_btree_rec {
 /*
  * Generic stats interface
  */
-#define __XFS_BTREE_STATS_INC(type, stat) \
-	XFS_STATS_INC(xs_ ## type ## _2_ ## stat)
-#define XFS_BTREE_STATS_INC(cur, stat)  \
+#define __XFS_BTREE_STATS_INC(mp, type, stat) \
+	XFS_STATS_INC(mp, xs_ ## type ## _2_ ## stat)
+#define XFS_BTREE_STATS_INC(cur, stat)	\
 do {    \
+	struct xfs_mount *__mp = cur->bc_mp; \
 	switch (cur->bc_btnum) {  \
-	case XFS_BTNUM_BNO: __XFS_BTREE_STATS_INC(abtb, stat); break;	\
-	case XFS_BTNUM_CNT: __XFS_BTREE_STATS_INC(abtc, stat); break;	\
-	case XFS_BTNUM_BMAP: __XFS_BTREE_STATS_INC(bmbt, stat); break;	\
-	case XFS_BTNUM_INO: __XFS_BTREE_STATS_INC(ibt, stat); break;	\
-	case XFS_BTNUM_FINO: __XFS_BTREE_STATS_INC(fibt, stat); break;	\
+	case XFS_BTNUM_BNO: __XFS_BTREE_STATS_INC(__mp, abtb, stat); break; \
+	case XFS_BTNUM_CNT: __XFS_BTREE_STATS_INC(__mp, abtc, stat); break; \
+	case XFS_BTNUM_BMAP: __XFS_BTREE_STATS_INC(__mp, bmbt, stat); break; \
+	case XFS_BTNUM_INO: __XFS_BTREE_STATS_INC(__mp, ibt, stat); break; \
+	case XFS_BTNUM_FINO: __XFS_BTREE_STATS_INC(__mp, fibt, stat); break; \
 	case XFS_BTNUM_MAX: ASSERT(0); /* fucking gcc */ ; break;	\
 	}       \
 } while (0)
 
-#define __XFS_BTREE_STATS_ADD(type, stat, val) \
-	XFS_STATS_ADD(xs_ ## type ## _2_ ## stat, val)
+#define __XFS_BTREE_STATS_ADD(mp, type, stat, val) \
+	XFS_STATS_ADD(mp, xs_ ## type ## _2_ ## stat, val)
 #define XFS_BTREE_STATS_ADD(cur, stat, val)  \
 do {    \
+	struct xfs_mount *__mp = cur->bc_mp; \
 	switch (cur->bc_btnum) {  \
-	case XFS_BTNUM_BNO: __XFS_BTREE_STATS_ADD(abtb, stat, val); break; \
-	case XFS_BTNUM_CNT: __XFS_BTREE_STATS_ADD(abtc, stat, val); break; \
-	case XFS_BTNUM_BMAP: __XFS_BTREE_STATS_ADD(bmbt, stat, val); break; \
-	case XFS_BTNUM_INO: __XFS_BTREE_STATS_ADD(ibt, stat, val); break; \
-	case XFS_BTNUM_FINO: __XFS_BTREE_STATS_ADD(fibt, stat, val); break; \
-	case XFS_BTNUM_MAX: ASSERT(0); /* fucking gcc */ ; break;	\
+	case XFS_BTNUM_BNO:	\
+		__XFS_BTREE_STATS_ADD(__mp, abtb, stat, val); break; \
+	case XFS_BTNUM_CNT:	\
+		__XFS_BTREE_STATS_ADD(__mp, abtc, stat, val); break; \
+	case XFS_BTNUM_BMAP:	\
+		__XFS_BTREE_STATS_ADD(__mp, bmbt, stat, val); break; \
+	case XFS_BTNUM_INO:	\
+		__XFS_BTREE_STATS_ADD(__mp, ibt, stat, val); break; \
+	case XFS_BTNUM_FINO:	\
+		__XFS_BTREE_STATS_ADD(__mp, fibt, stat, val); break; \
+	case XFS_BTNUM_MAX: ASSERT(0); /* fucking gcc */ ; break; \
 	}       \
 } while (0)
 
@@ -465,4 +472,7 @@ static inline int xfs_btree_get_level(struct xfs_btree_block *block)
 #define XFS_BTREE_TRACE_ARGR(c, r)
 #define	XFS_BTREE_TRACE_CURSOR(c, t)
 
+bool xfs_btree_sblock_v5hdr_verify(struct xfs_buf *bp);
+bool xfs_btree_sblock_verify(struct xfs_buf *bp, unsigned int max_recs);
+
 #endif	/* __XFS_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index be43248a5822..097bf7717d80 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -39,6 +39,7 @@
 #include "xfs_trace.h"
 #include "xfs_cksum.h"
 #include "xfs_buf_item.h"
+#include "xfs_log.h"
 
 /*
  * xfs_da_btree.c
@@ -150,6 +151,8 @@ xfs_da3_node_verify(
 			return false;
 		if (be64_to_cpu(hdr3->info.blkno) != bp->b_bn)
 			return false;
+		if (!xfs_log_check_lsn(mp, be64_to_cpu(hdr3->info.lsn)))
+			return false;
 	} else {
 		if (ichdr.magic != XFS_DA_NODE_MAGIC)
 			return false;
@@ -242,6 +245,7 @@ xfs_da3_node_read_verify(
 }
 
 const struct xfs_buf_ops xfs_da3_node_buf_ops = {
+	.name = "xfs_da3_node",
 	.verify_read = xfs_da3_node_read_verify,
 	.verify_write = xfs_da3_node_write_verify,
 };
@@ -322,6 +326,7 @@ xfs_da3_node_create(
 	if (xfs_sb_version_hascrc(&mp->m_sb)) {
 		struct xfs_da3_node_hdr *hdr3 = bp->b_addr;
 
+		memset(hdr3, 0, sizeof(struct xfs_da3_node_hdr));
 		ichdr.magic = XFS_DA3_NODE_MAGIC;
 		hdr3->info.blkno = cpu_to_be64(bp->b_bn);
 		hdr3->info.owner = cpu_to_be64(args->dp->i_ino);
diff --git a/fs/xfs/libxfs/xfs_da_format.h b/fs/xfs/libxfs/xfs_da_format.h
index b14bbd6bb05f..8d4d8bce41bf 100644
--- a/fs/xfs/libxfs/xfs_da_format.h
+++ b/fs/xfs/libxfs/xfs_da_format.h
@@ -641,6 +641,22 @@ xfs_dir2_block_leaf_p(struct xfs_dir2_block_tail *btp)
  */
 #define XFS_ATTR_LEAF_MAPSIZE	3	/* how many freespace slots */
 
+/*
+ * Entries are packed toward the top as tight as possible.
+ */
+typedef struct xfs_attr_shortform {
+	struct xfs_attr_sf_hdr {	/* constant-structure header block */
+		__be16	totsize;	/* total bytes in shortform list */
+		__u8	count;	/* count of active entries */
+	} hdr;
+	struct xfs_attr_sf_entry {
+		__uint8_t namelen;	/* actual length of name (no NULL) */
+		__uint8_t valuelen;	/* actual length of value (no NULL) */
+		__uint8_t flags;	/* flags bits (see xfs_attr_leaf.h) */
+		__uint8_t nameval[1];	/* name & value bytes concatenated */
+	} list[1];			/* variable sized array */
+} xfs_attr_shortform_t;
+
 typedef struct xfs_attr_leaf_map {	/* RLE map of free bytes */
 	__be16	base;			  /* base of free region */
 	__be16	size;			  /* length of free region */
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index 9de401d297e5..af0f9d171f8a 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -176,7 +176,7 @@ xfs_dir_isempty(
 {
 	xfs_dir2_sf_hdr_t	*sfp;
 
-	ASSERT(S_ISDIR(dp->i_d.di_mode));
+	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
 	if (dp->i_d.di_size == 0)	/* might happen during shutdown. */
 		return 1;
 	if (dp->i_d.di_size > XFS_IFORK_DSIZE(dp))
@@ -231,7 +231,7 @@ xfs_dir_init(
 	struct xfs_da_args *args;
 	int		error;
 
-	ASSERT(S_ISDIR(dp->i_d.di_mode));
+	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
 	error = xfs_dir_ino_validate(tp->t_mountp, pdp->i_ino);
 	if (error)
 		return error;
@@ -266,12 +266,12 @@ xfs_dir_createname(
 	int			rval;
 	int			v;		/* type-checking value */
 
-	ASSERT(S_ISDIR(dp->i_d.di_mode));
+	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
 	if (inum) {
 		rval = xfs_dir_ino_validate(tp->t_mountp, inum);
 		if (rval)
 			return rval;
-		XFS_STATS_INC(xs_dir_create);
+		XFS_STATS_INC(dp->i_mount, xs_dir_create);
 	}
 
 	args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS);
@@ -364,8 +364,8 @@ xfs_dir_lookup(
 	int		v;		/* type-checking value */
 	int		lock_mode;
 
-	ASSERT(S_ISDIR(dp->i_d.di_mode));
-	XFS_STATS_INC(xs_dir_lookup);
+	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
+	XFS_STATS_INC(dp->i_mount, xs_dir_lookup);
 
 	/*
 	 * We need to use KM_NOFS here so that lockdep will not throw false
@@ -443,8 +443,8 @@ xfs_dir_removename(
 	int		rval;
 	int		v;		/* type-checking value */
 
-	ASSERT(S_ISDIR(dp->i_d.di_mode));
-	XFS_STATS_INC(xs_dir_remove);
+	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
+	XFS_STATS_INC(dp->i_mount, xs_dir_remove);
 
 	args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS);
 	if (!args)
@@ -505,7 +505,7 @@ xfs_dir_replace(
 	int		rval;
 	int		v;		/* type-checking value */
 
-	ASSERT(S_ISDIR(dp->i_d.di_mode));
+	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
 
 	rval = xfs_dir_ino_validate(tp->t_mountp, inum);
 	if (rval)
diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c
index 4778d1dd511a..aa17cb788946 100644
--- a/fs/xfs/libxfs/xfs_dir2_block.c
+++ b/fs/xfs/libxfs/xfs_dir2_block.c
@@ -34,6 +34,7 @@
 #include "xfs_error.h"
 #include "xfs_trace.h"
 #include "xfs_cksum.h"
+#include "xfs_log.h"
 
 /*
  * Local function prototypes.
@@ -71,6 +72,8 @@ xfs_dir3_block_verify(
 			return false;
 		if (be64_to_cpu(hdr3->blkno) != bp->b_bn)
 			return false;
+		if (!xfs_log_check_lsn(mp, be64_to_cpu(hdr3->lsn)))
+			return false;
 	} else {
 		if (hdr3->magic != cpu_to_be32(XFS_DIR2_BLOCK_MAGIC))
 			return false;
@@ -120,6 +123,7 @@ xfs_dir3_block_write_verify(
 }
 
 const struct xfs_buf_ops xfs_dir3_block_buf_ops = {
+	.name = "xfs_dir3_block",
 	.verify_read = xfs_dir3_block_read_verify,
 	.verify_write = xfs_dir3_block_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c
index 824131e71bc5..725fc7841fde 100644
--- a/fs/xfs/libxfs/xfs_dir2_data.c
+++ b/fs/xfs/libxfs/xfs_dir2_data.c
@@ -31,6 +31,7 @@
 #include "xfs_trans.h"
 #include "xfs_buf_item.h"
 #include "xfs_cksum.h"
+#include "xfs_log.h"
 
 /*
  * Check the consistency of the data block.
@@ -224,6 +225,8 @@ xfs_dir3_data_verify(
 			return false;
 		if (be64_to_cpu(hdr3->blkno) != bp->b_bn)
 			return false;
+		if (!xfs_log_check_lsn(mp, be64_to_cpu(hdr3->lsn)))
+			return false;
 	} else {
 		if (hdr3->magic != cpu_to_be32(XFS_DIR2_DATA_MAGIC))
 			return false;
@@ -302,11 +305,13 @@ xfs_dir3_data_write_verify(
 }
 
 const struct xfs_buf_ops xfs_dir3_data_buf_ops = {
+	.name = "xfs_dir3_data",
 	.verify_read = xfs_dir3_data_read_verify,
 	.verify_write = xfs_dir3_data_write_verify,
 };
 
 static const struct xfs_buf_ops xfs_dir3_data_reada_buf_ops = {
+	.name = "xfs_dir3_data_reada",
 	.verify_read = xfs_dir3_data_reada_verify,
 	.verify_write = xfs_dir3_data_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c
index f300240ebb8d..b887fb2a2bcf 100644
--- a/fs/xfs/libxfs/xfs_dir2_leaf.c
+++ b/fs/xfs/libxfs/xfs_dir2_leaf.c
@@ -33,6 +33,7 @@
 #include "xfs_trans.h"
 #include "xfs_buf_item.h"
 #include "xfs_cksum.h"
+#include "xfs_log.h"
 
 /*
  * Local function declarations.
@@ -164,6 +165,8 @@ xfs_dir3_leaf_verify(
 			return false;
 		if (be64_to_cpu(leaf3->info.blkno) != bp->b_bn)
 			return false;
+		if (!xfs_log_check_lsn(mp, be64_to_cpu(leaf3->info.lsn)))
+			return false;
 	} else {
 		if (leaf->hdr.info.magic != cpu_to_be16(magic))
 			return false;
@@ -242,11 +245,13 @@ xfs_dir3_leafn_write_verify(
 }
 
 const struct xfs_buf_ops xfs_dir3_leaf1_buf_ops = {
+	.name = "xfs_dir3_leaf1",
 	.verify_read = xfs_dir3_leaf1_read_verify,
 	.verify_write = xfs_dir3_leaf1_write_verify,
 };
 
 const struct xfs_buf_ops xfs_dir3_leafn_buf_ops = {
+	.name = "xfs_dir3_leafn",
 	.verify_read = xfs_dir3_leafn_read_verify,
 	.verify_write = xfs_dir3_leafn_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c
index cc28e924545b..75a557432d0f 100644
--- a/fs/xfs/libxfs/xfs_dir2_node.c
+++ b/fs/xfs/libxfs/xfs_dir2_node.c
@@ -33,6 +33,7 @@
 #include "xfs_trans.h"
 #include "xfs_buf_item.h"
 #include "xfs_cksum.h"
+#include "xfs_log.h"
 
 /*
  * Function declarations.
@@ -97,6 +98,8 @@ xfs_dir3_free_verify(
 			return false;
 		if (be64_to_cpu(hdr3->blkno) != bp->b_bn)
 			return false;
+		if (!xfs_log_check_lsn(mp, be64_to_cpu(hdr3->lsn)))
+			return false;
 	} else {
 		if (hdr->magic != cpu_to_be32(XFS_DIR2_FREE_MAGIC))
 			return false;
@@ -147,6 +150,7 @@ xfs_dir3_free_write_verify(
 }
 
 const struct xfs_buf_ops xfs_dir3_free_buf_ops = {
+	.name = "xfs_dir3_free",
 	.verify_read = xfs_dir3_free_read_verify,
 	.verify_write = xfs_dir3_free_write_verify,
 };
@@ -2231,6 +2235,9 @@ xfs_dir2_node_trim_free(
 
 	dp = args->dp;
 	tp = args->trans;
+
+	*rvalp = 0;
+
 	/*
 	 * Read the freespace block.
 	 */
@@ -2251,7 +2258,6 @@ xfs_dir2_node_trim_free(
 	 */
 	if (freehdr.nused > 0) {
 		xfs_trans_brelse(tp, bp);
-		*rvalp = 0;
 		return 0;
 	}
 	/*
diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c
index 5331b7f0460c..3cc3cf767474 100644
--- a/fs/xfs/libxfs/xfs_dquot_buf.c
+++ b/fs/xfs/libxfs/xfs_dquot_buf.c
@@ -54,7 +54,7 @@ xfs_dqcheck(
 	xfs_dqid_t	 id,
 	uint		 type,	  /* used only when IO_dorepair is true */
 	uint		 flags,
-	char		 *str)
+	const char	 *str)
 {
 	xfs_dqblk_t	 *d = (xfs_dqblk_t *)ddq;
 	int		errs = 0;
@@ -207,7 +207,8 @@ xfs_dquot_buf_verify_crc(
 STATIC bool
 xfs_dquot_buf_verify(
 	struct xfs_mount	*mp,
-	struct xfs_buf		*bp)
+	struct xfs_buf		*bp,
+	int			warn)
 {
 	struct xfs_dqblk	*d = (struct xfs_dqblk *)bp->b_addr;
 	xfs_dqid_t		id = 0;
@@ -240,8 +241,7 @@ xfs_dquot_buf_verify(
 		if (i == 0)
 			id = be32_to_cpu(ddq->d_id);
 
-		error = xfs_dqcheck(mp, ddq, id + i, 0, XFS_QMOPT_DOWARN,
-				       "xfs_dquot_buf_verify");
+		error = xfs_dqcheck(mp, ddq, id + i, 0, warn, __func__);
 		if (error)
 			return false;
 	}
@@ -256,7 +256,7 @@ xfs_dquot_buf_read_verify(
 
 	if (!xfs_dquot_buf_verify_crc(mp, bp))
 		xfs_buf_ioerror(bp, -EFSBADCRC);
-	else if (!xfs_dquot_buf_verify(mp, bp))
+	else if (!xfs_dquot_buf_verify(mp, bp, XFS_QMOPT_DOWARN))
 		xfs_buf_ioerror(bp, -EFSCORRUPTED);
 
 	if (bp->b_error)
@@ -264,6 +264,25 @@ xfs_dquot_buf_read_verify(
 }
 
 /*
+ * readahead errors are silent and simply leave the buffer as !done so a real
+ * read will then be run with the xfs_dquot_buf_ops verifier. See
+ * xfs_inode_buf_verify() for why we use EIO and ~XBF_DONE here rather than
+ * reporting the failure.
+ */
+static void
+xfs_dquot_buf_readahead_verify(
+	struct xfs_buf	*bp)
+{
+	struct xfs_mount	*mp = bp->b_target->bt_mount;
+
+	if (!xfs_dquot_buf_verify_crc(mp, bp) ||
+	    !xfs_dquot_buf_verify(mp, bp, 0)) {
+		xfs_buf_ioerror(bp, -EIO);
+		bp->b_flags &= ~XBF_DONE;
+	}
+}
+
+/*
  * we don't calculate the CRC here as that is done when the dquot is flushed to
  * the buffer after the update is done. This ensures that the dquot in the
  * buffer always has an up-to-date CRC value.
@@ -274,7 +293,7 @@ xfs_dquot_buf_write_verify(
 {
 	struct xfs_mount	*mp = bp->b_target->bt_mount;
 
-	if (!xfs_dquot_buf_verify(mp, bp)) {
+	if (!xfs_dquot_buf_verify(mp, bp, XFS_QMOPT_DOWARN)) {
 		xfs_buf_ioerror(bp, -EFSCORRUPTED);
 		xfs_verifier_error(bp);
 		return;
@@ -282,7 +301,13 @@ xfs_dquot_buf_write_verify(
 }
 
 const struct xfs_buf_ops xfs_dquot_buf_ops = {
+	.name = "xfs_dquot",
 	.verify_read = xfs_dquot_buf_read_verify,
 	.verify_write = xfs_dquot_buf_write_verify,
 };
 
+const struct xfs_buf_ops xfs_dquot_buf_ra_ops = {
+	.name = "xfs_dquot_ra",
+	.verify_read = xfs_dquot_buf_readahead_verify,
+	.verify_write = xfs_dquot_buf_write_verify,
+};
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 9590a069e556..dc97eb21af07 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -60,6 +60,14 @@ struct xfs_ifork;
 #define	XFS_SB_VERSION_MOREBITSBIT	0x8000
 
 /*
+ * The size of a single extended attribute on disk is limited by
+ * the size of index values within the attribute entries themselves.
+ * These are be16 fields, so we can only support attribute data
+ * sizes up to 2^16 bytes in length.
+ */
+#define XFS_XATTR_SIZE_MAX (1 << 16)
+
+/*
  * Supported feature bit list is just all bits in the versionnum field because
  * we've used them all up and understand them all. Except, of course, for the
  * shared superblock bit, which nobody knows what it does and so is unsupported.
@@ -778,7 +786,7 @@ typedef struct xfs_agfl {
 	__be64		agfl_lsn;
 	__be32		agfl_crc;
 	__be32		agfl_bno[];	/* actually XFS_AGFL_SIZE(mp) */
-} xfs_agfl_t;
+} __attribute__((packed)) xfs_agfl_t;
 
 #define XFS_AGFL_CRC_OFF	offsetof(struct xfs_agfl, agfl_crc)
 
@@ -976,8 +984,6 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev)
 
 /*
  * Values for di_flags
- * There should be a one-to-one correspondence between these flags and the
- * XFS_XFLAG_s.
  */
 #define XFS_DIFLAG_REALTIME_BIT  0	/* file's blocks come from rt area */
 #define XFS_DIFLAG_PREALLOC_BIT  1	/* file space has been preallocated */
@@ -1018,6 +1024,15 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev)
 	 XFS_DIFLAG_EXTSZINHERIT | XFS_DIFLAG_NODEFRAG | XFS_DIFLAG_FILESTREAM)
 
 /*
+ * Values for di_flags2 These start by being exposed to userspace in the upper
+ * 16 bits of the XFS_XFLAG_s range.
+ */
+#define XFS_DIFLAG2_DAX_BIT	0	/* use DAX for this inode */
+#define XFS_DIFLAG2_DAX		(1 << XFS_DIFLAG2_DAX_BIT)
+
+#define XFS_DIFLAG2_ANY		(XFS_DIFLAG2_DAX)
+
+/*
  * Inode number format:
  * low inopblog bits - offset in block
  * next agblklog bits - block number in ag
@@ -1483,13 +1498,17 @@ struct xfs_acl {
  */
 #define XFS_ACL_MAX_ENTRIES(mp)	\
 	(xfs_sb_version_hascrc(&mp->m_sb) \
-		?  (XATTR_SIZE_MAX - sizeof(struct xfs_acl)) / \
+		?  (XFS_XATTR_SIZE_MAX - sizeof(struct xfs_acl)) / \
 						sizeof(struct xfs_acl_entry) \
 		: 25)
 
-#define XFS_ACL_MAX_SIZE(mp) \
+#define XFS_ACL_SIZE(cnt) \
 	(sizeof(struct xfs_acl) + \
-		sizeof(struct xfs_acl_entry) * XFS_ACL_MAX_ENTRIES((mp)))
+		sizeof(struct xfs_acl_entry) * cnt)
+
+#define XFS_ACL_MAX_SIZE(mp) \
+	XFS_ACL_SIZE(XFS_ACL_MAX_ENTRIES((mp)))
+
 
 /* On-disk XFS extended attribute names */
 #define SGI_ACL_FILE		"SGI_ACL_FILE"
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 89689c6a43e2..fffe3d01bd9f 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -36,40 +36,6 @@ struct dioattr {
 #endif
 
 /*
- * Structure for XFS_IOC_FSGETXATTR[A] and XFS_IOC_FSSETXATTR.
- */
-#ifndef HAVE_FSXATTR
-struct fsxattr {
-	__u32		fsx_xflags;	/* xflags field value (get/set) */
-	__u32		fsx_extsize;	/* extsize field value (get/set)*/
-	__u32		fsx_nextents;	/* nextents field value (get)	*/
-	__u32		fsx_projid;	/* project identifier (get/set) */
-	unsigned char	fsx_pad[12];
-};
-#endif
-
-/*
- * Flags for the bs_xflags/fsx_xflags field
- * There should be a one-to-one correspondence between these flags and the
- * XFS_DIFLAG_s.
- */
-#define XFS_XFLAG_REALTIME	0x00000001	/* data in realtime volume */
-#define XFS_XFLAG_PREALLOC	0x00000002	/* preallocated file extents */
-#define XFS_XFLAG_IMMUTABLE	0x00000008	/* file cannot be modified */
-#define XFS_XFLAG_APPEND	0x00000010	/* all writes append */
-#define XFS_XFLAG_SYNC		0x00000020	/* all writes synchronous */
-#define XFS_XFLAG_NOATIME	0x00000040	/* do not update access time */
-#define XFS_XFLAG_NODUMP	0x00000080	/* do not include in backups */
-#define XFS_XFLAG_RTINHERIT	0x00000100	/* create with rt bit set */
-#define XFS_XFLAG_PROJINHERIT	0x00000200	/* create with parents projid */
-#define XFS_XFLAG_NOSYMLINKS	0x00000400	/* disallow symlink creation */
-#define XFS_XFLAG_EXTSIZE	0x00000800	/* extent size allocator hint */
-#define XFS_XFLAG_EXTSZINHERIT	0x00001000	/* inherit inode extent size */
-#define XFS_XFLAG_NODEFRAG	0x00002000  	/* do not defragment */
-#define XFS_XFLAG_FILESTREAM	0x00004000	/* use filestream allocator */
-#define XFS_XFLAG_HASATTR	0x80000000	/* no DIFLAG for this	*/
-
-/*
  * Structure for XFS_IOC_GETBMAP.
  * On input, fill in bmv_offset and bmv_length of the first structure
  * to indicate the area of interest in the file, and bmv_entries with
@@ -490,6 +456,16 @@ typedef struct xfs_swapext
 #define XFS_FSOP_GOING_FLAGS_NOLOGFLUSH		0x2	/* don't flush log nor data */
 
 /*
+ * ioctl limits
+ */
+#ifdef XATTR_LIST_MAX
+#  define XFS_XATTR_LIST_MAX XATTR_LIST_MAX
+#else
+#  define XFS_XATTR_LIST_MAX 65536
+#endif
+
+
+/*
  * ioctl commands that are used by Linux filesystems
  */
 #define XFS_IOC_GETXFLAGS	FS_IOC_GETFLAGS
@@ -504,8 +480,8 @@ typedef struct xfs_swapext
 #define XFS_IOC_ALLOCSP		_IOW ('X', 10, struct xfs_flock64)
 #define XFS_IOC_FREESP		_IOW ('X', 11, struct xfs_flock64)
 #define XFS_IOC_DIOINFO		_IOR ('X', 30, struct dioattr)
-#define XFS_IOC_FSGETXATTR	_IOR ('X', 31, struct fsxattr)
-#define XFS_IOC_FSSETXATTR	_IOW ('X', 32, struct fsxattr)
+#define XFS_IOC_FSGETXATTR	FS_IOC_FSGETXATTR
+#define XFS_IOC_FSSETXATTR	FS_IOC_FSSETXATTR
 #define XFS_IOC_ALLOCSP64	_IOW ('X', 36, struct xfs_flock64)
 #define XFS_IOC_FREESP64	_IOW ('X', 37, struct xfs_flock64)
 #define XFS_IOC_GETBMAP		_IOWR('X', 38, struct getbmap)
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 54deb2d12ac6..22297f9b0fd5 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -38,6 +38,7 @@
 #include "xfs_icreate_item.h"
 #include "xfs_icache.h"
 #include "xfs_trace.h"
+#include "xfs_log.h"
 
 
 /*
@@ -2402,8 +2403,8 @@ xfs_ialloc_compute_maxlevels(
 
 	maxleafents = (1LL << XFS_INO_AGINO_BITS(mp)) >>
 		XFS_INODES_PER_CHUNK_LOG;
-	minleafrecs = mp->m_alloc_mnr[0];
-	minnoderecs = mp->m_alloc_mnr[1];
+	minleafrecs = mp->m_inobt_mnr[0];
+	minnoderecs = mp->m_inobt_mnr[1];
 	maxblocks = (maxleafents + minleafrecs - 1) / minleafrecs;
 	for (level = 1; maxblocks > 1; level++)
 		maxblocks = (maxblocks + minnoderecs - 1) / minnoderecs;
@@ -2500,9 +2501,14 @@ xfs_agi_verify(
 	struct xfs_mount *mp = bp->b_target->bt_mount;
 	struct xfs_agi	*agi = XFS_BUF_TO_AGI(bp);
 
-	if (xfs_sb_version_hascrc(&mp->m_sb) &&
-	    !uuid_equal(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid))
+	if (xfs_sb_version_hascrc(&mp->m_sb)) {
+		if (!uuid_equal(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid))
+			return false;
+		if (!xfs_log_check_lsn(mp,
+				be64_to_cpu(XFS_BUF_TO_AGI(bp)->agi_lsn)))
 			return false;
+	}
+
 	/*
 	 * Validate the magic number of the agi block.
 	 */
@@ -2566,6 +2572,7 @@ xfs_agi_write_verify(
 }
 
 const struct xfs_buf_ops xfs_agi_buf_ops = {
+	.name = "xfs_agi",
 	.verify_read = xfs_agi_read_verify,
 	.verify_write = xfs_agi_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index f39b285beb19..89c21d771e35 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -125,16 +125,8 @@ xfs_inobt_free_block(
 	struct xfs_btree_cur	*cur,
 	struct xfs_buf		*bp)
 {
-	xfs_fsblock_t		fsbno;
-	int			error;
-
-	fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, XFS_BUF_ADDR(bp));
-	error = xfs_free_extent(cur->bc_tp, fsbno, 1);
-	if (error)
-		return error;
-
-	xfs_trans_binval(cur->bc_tp, bp);
-	return error;
+	return xfs_free_extent(cur->bc_tp,
+			XFS_DADDR_TO_FSB(cur->bc_mp, XFS_BUF_ADDR(bp)), 1);
 }
 
 STATIC int
@@ -221,7 +213,6 @@ xfs_inobt_verify(
 {
 	struct xfs_mount	*mp = bp->b_target->bt_mount;
 	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
-	struct xfs_perag	*pag = bp->b_pag;
 	unsigned int		level;
 
 	/*
@@ -237,14 +228,7 @@ xfs_inobt_verify(
 	switch (block->bb_magic) {
 	case cpu_to_be32(XFS_IBT_CRC_MAGIC):
 	case cpu_to_be32(XFS_FIBT_CRC_MAGIC):
-		if (!xfs_sb_version_hascrc(&mp->m_sb))
-			return false;
-		if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid))
-			return false;
-		if (block->bb_u.s.bb_blkno != cpu_to_be64(bp->b_bn))
-			return false;
-		if (pag &&
-		    be32_to_cpu(block->bb_u.s.bb_owner) != pag->pag_agno)
+		if (!xfs_btree_sblock_v5hdr_verify(bp))
 			return false;
 		/* fall through */
 	case cpu_to_be32(XFS_IBT_MAGIC):
@@ -254,24 +238,12 @@ xfs_inobt_verify(
 		return 0;
 	}
 
-	/* numrecs and level verification */
+	/* level verification */
 	level = be16_to_cpu(block->bb_level);
 	if (level >= mp->m_in_maxlevels)
 		return false;
-	if (be16_to_cpu(block->bb_numrecs) > mp->m_inobt_mxr[level != 0])
-		return false;
-
-	/* sibling pointer verification */
-	if (!block->bb_u.s.bb_leftsib ||
-	    (be32_to_cpu(block->bb_u.s.bb_leftsib) >= mp->m_sb.sb_agblocks &&
-	     block->bb_u.s.bb_leftsib != cpu_to_be32(NULLAGBLOCK)))
-		return false;
-	if (!block->bb_u.s.bb_rightsib ||
-	    (be32_to_cpu(block->bb_u.s.bb_rightsib) >= mp->m_sb.sb_agblocks &&
-	     block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK)))
-		return false;
 
-	return true;
+	return xfs_btree_sblock_verify(bp, mp->m_inobt_mxr[level != 0]);
 }
 
 static void
@@ -304,6 +276,7 @@ xfs_inobt_write_verify(
 }
 
 const struct xfs_buf_ops xfs_inobt_buf_ops = {
+	.name = "xfs_inobt",
 	.verify_read = xfs_inobt_read_verify,
 	.verify_write = xfs_inobt_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 268c00f4f83a..9d9559eb2835 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -62,11 +62,14 @@ xfs_inobp_check(
  * has not had the inode cores stamped into it. Hence for readahead, the buffer
  * may be potentially invalid.
  *
- * If the readahead buffer is invalid, we don't want to mark it with an error,
- * but we do want to clear the DONE status of the buffer so that a followup read
- * will re-read it from disk. This will ensure that we don't get an unnecessary
- * warnings during log recovery and we don't get unnecssary panics on debug
- * kernels.
+ * If the readahead buffer is invalid, we need to mark it with an error and
+ * clear the DONE status of the buffer so that a followup read will re-read it
+ * from disk. We don't report the error otherwise to avoid warnings during log
+ * recovery and we don't get unnecssary panics on debug kernels. We use EIO here
+ * because all we want to do is say readahead failed; there is no-one to report
+ * the error to, so this will distinguish it from a non-ra verifier failure.
+ * Changes to this readahead error behavour also need to be reflected in
+ * xfs_dquot_buf_readahead_verify().
  */
 static void
 xfs_inode_buf_verify(
@@ -93,6 +96,7 @@ xfs_inode_buf_verify(
 						XFS_RANDOM_ITOBP_INOTOBP))) {
 			if (readahead) {
 				bp->b_flags &= ~XBF_DONE;
+				xfs_buf_ioerror(bp, -EIO);
 				return;
 			}
 
@@ -132,11 +136,13 @@ xfs_inode_buf_write_verify(
 }
 
 const struct xfs_buf_ops xfs_inode_buf_ops = {
+	.name = "xfs_inode",
 	.verify_read = xfs_inode_buf_read_verify,
 	.verify_write = xfs_inode_buf_write_verify,
 };
 
 const struct xfs_buf_ops xfs_inode_buf_ra_ops = {
+	.name = "xxfs_inode_ra",
 	.verify_read = xfs_inode_buf_readahead_verify,
 	.verify_write = xfs_inode_buf_write_verify,
 };
@@ -189,28 +195,50 @@ xfs_imap_to_bp(
 }
 
 void
-xfs_dinode_from_disk(
-	xfs_icdinode_t		*to,
-	xfs_dinode_t		*from)
+xfs_inode_from_disk(
+	struct xfs_inode	*ip,
+	struct xfs_dinode	*from)
 {
-	to->di_magic = be16_to_cpu(from->di_magic);
-	to->di_mode = be16_to_cpu(from->di_mode);
-	to->di_version = from ->di_version;
+	struct xfs_icdinode	*to = &ip->i_d;
+	struct inode		*inode = VFS_I(ip);
+
+
+	/*
+	 * Convert v1 inodes immediately to v2 inode format as this is the
+	 * minimum inode version format we support in the rest of the code.
+	 */
+	to->di_version = from->di_version;
+	if (to->di_version == 1) {
+		set_nlink(inode, be16_to_cpu(from->di_onlink));
+		to->di_projid_lo = 0;
+		to->di_projid_hi = 0;
+		to->di_version = 2;
+	} else {
+		set_nlink(inode, be32_to_cpu(from->di_nlink));
+		to->di_projid_lo = be16_to_cpu(from->di_projid_lo);
+		to->di_projid_hi = be16_to_cpu(from->di_projid_hi);
+	}
+
 	to->di_format = from->di_format;
-	to->di_onlink = be16_to_cpu(from->di_onlink);
 	to->di_uid = be32_to_cpu(from->di_uid);
 	to->di_gid = be32_to_cpu(from->di_gid);
-	to->di_nlink = be32_to_cpu(from->di_nlink);
-	to->di_projid_lo = be16_to_cpu(from->di_projid_lo);
-	to->di_projid_hi = be16_to_cpu(from->di_projid_hi);
-	memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
 	to->di_flushiter = be16_to_cpu(from->di_flushiter);
-	to->di_atime.t_sec = be32_to_cpu(from->di_atime.t_sec);
-	to->di_atime.t_nsec = be32_to_cpu(from->di_atime.t_nsec);
-	to->di_mtime.t_sec = be32_to_cpu(from->di_mtime.t_sec);
-	to->di_mtime.t_nsec = be32_to_cpu(from->di_mtime.t_nsec);
-	to->di_ctime.t_sec = be32_to_cpu(from->di_ctime.t_sec);
-	to->di_ctime.t_nsec = be32_to_cpu(from->di_ctime.t_nsec);
+
+	/*
+	 * Time is signed, so need to convert to signed 32 bit before
+	 * storing in inode timestamp which may be 64 bit. Otherwise
+	 * a time before epoch is converted to a time long after epoch
+	 * on 64 bit systems.
+	 */
+	inode->i_atime.tv_sec = (int)be32_to_cpu(from->di_atime.t_sec);
+	inode->i_atime.tv_nsec = (int)be32_to_cpu(from->di_atime.t_nsec);
+	inode->i_mtime.tv_sec = (int)be32_to_cpu(from->di_mtime.t_sec);
+	inode->i_mtime.tv_nsec = (int)be32_to_cpu(from->di_mtime.t_nsec);
+	inode->i_ctime.tv_sec = (int)be32_to_cpu(from->di_ctime.t_sec);
+	inode->i_ctime.tv_nsec = (int)be32_to_cpu(from->di_ctime.t_nsec);
+	inode->i_generation = be32_to_cpu(from->di_gen);
+	inode->i_mode = be16_to_cpu(from->di_mode);
+
 	to->di_size = be64_to_cpu(from->di_size);
 	to->di_nblocks = be64_to_cpu(from->di_nblocks);
 	to->di_extsize = be32_to_cpu(from->di_extsize);
@@ -221,42 +249,96 @@ xfs_dinode_from_disk(
 	to->di_dmevmask	= be32_to_cpu(from->di_dmevmask);
 	to->di_dmstate	= be16_to_cpu(from->di_dmstate);
 	to->di_flags	= be16_to_cpu(from->di_flags);
-	to->di_gen	= be32_to_cpu(from->di_gen);
 
 	if (to->di_version == 3) {
-		to->di_changecount = be64_to_cpu(from->di_changecount);
+		inode->i_version = be64_to_cpu(from->di_changecount);
 		to->di_crtime.t_sec = be32_to_cpu(from->di_crtime.t_sec);
 		to->di_crtime.t_nsec = be32_to_cpu(from->di_crtime.t_nsec);
 		to->di_flags2 = be64_to_cpu(from->di_flags2);
-		to->di_ino = be64_to_cpu(from->di_ino);
-		to->di_lsn = be64_to_cpu(from->di_lsn);
-		memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
-		uuid_copy(&to->di_uuid, &from->di_uuid);
 	}
 }
 
 void
-xfs_dinode_to_disk(
-	xfs_dinode_t		*to,
-	xfs_icdinode_t		*from)
+xfs_inode_to_disk(
+	struct xfs_inode	*ip,
+	struct xfs_dinode	*to,
+	xfs_lsn_t		lsn)
+{
+	struct xfs_icdinode	*from = &ip->i_d;
+	struct inode		*inode = VFS_I(ip);
+
+	to->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
+	to->di_onlink = 0;
+
+	to->di_version = from->di_version;
+	to->di_format = from->di_format;
+	to->di_uid = cpu_to_be32(from->di_uid);
+	to->di_gid = cpu_to_be32(from->di_gid);
+	to->di_projid_lo = cpu_to_be16(from->di_projid_lo);
+	to->di_projid_hi = cpu_to_be16(from->di_projid_hi);
+
+	memset(to->di_pad, 0, sizeof(to->di_pad));
+	to->di_atime.t_sec = cpu_to_be32(inode->i_atime.tv_sec);
+	to->di_atime.t_nsec = cpu_to_be32(inode->i_atime.tv_nsec);
+	to->di_mtime.t_sec = cpu_to_be32(inode->i_mtime.tv_sec);
+	to->di_mtime.t_nsec = cpu_to_be32(inode->i_mtime.tv_nsec);
+	to->di_ctime.t_sec = cpu_to_be32(inode->i_ctime.tv_sec);
+	to->di_ctime.t_nsec = cpu_to_be32(inode->i_ctime.tv_nsec);
+	to->di_nlink = cpu_to_be32(inode->i_nlink);
+	to->di_gen = cpu_to_be32(inode->i_generation);
+	to->di_mode = cpu_to_be16(inode->i_mode);
+
+	to->di_size = cpu_to_be64(from->di_size);
+	to->di_nblocks = cpu_to_be64(from->di_nblocks);
+	to->di_extsize = cpu_to_be32(from->di_extsize);
+	to->di_nextents = cpu_to_be32(from->di_nextents);
+	to->di_anextents = cpu_to_be16(from->di_anextents);
+	to->di_forkoff = from->di_forkoff;
+	to->di_aformat = from->di_aformat;
+	to->di_dmevmask = cpu_to_be32(from->di_dmevmask);
+	to->di_dmstate = cpu_to_be16(from->di_dmstate);
+	to->di_flags = cpu_to_be16(from->di_flags);
+
+	if (from->di_version == 3) {
+		to->di_changecount = cpu_to_be64(inode->i_version);
+		to->di_crtime.t_sec = cpu_to_be32(from->di_crtime.t_sec);
+		to->di_crtime.t_nsec = cpu_to_be32(from->di_crtime.t_nsec);
+		to->di_flags2 = cpu_to_be64(from->di_flags2);
+
+		to->di_ino = cpu_to_be64(ip->i_ino);
+		to->di_lsn = cpu_to_be64(lsn);
+		memset(to->di_pad2, 0, sizeof(to->di_pad2));
+		uuid_copy(&to->di_uuid, &ip->i_mount->m_sb.sb_meta_uuid);
+		to->di_flushiter = 0;
+	} else {
+		to->di_flushiter = cpu_to_be16(from->di_flushiter);
+	}
+}
+
+void
+xfs_log_dinode_to_disk(
+	struct xfs_log_dinode	*from,
+	struct xfs_dinode	*to)
 {
 	to->di_magic = cpu_to_be16(from->di_magic);
 	to->di_mode = cpu_to_be16(from->di_mode);
-	to->di_version = from ->di_version;
+	to->di_version = from->di_version;
 	to->di_format = from->di_format;
-	to->di_onlink = cpu_to_be16(from->di_onlink);
+	to->di_onlink = 0;
 	to->di_uid = cpu_to_be32(from->di_uid);
 	to->di_gid = cpu_to_be32(from->di_gid);
 	to->di_nlink = cpu_to_be32(from->di_nlink);
 	to->di_projid_lo = cpu_to_be16(from->di_projid_lo);
 	to->di_projid_hi = cpu_to_be16(from->di_projid_hi);
 	memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
+
 	to->di_atime.t_sec = cpu_to_be32(from->di_atime.t_sec);
 	to->di_atime.t_nsec = cpu_to_be32(from->di_atime.t_nsec);
 	to->di_mtime.t_sec = cpu_to_be32(from->di_mtime.t_sec);
 	to->di_mtime.t_nsec = cpu_to_be32(from->di_mtime.t_nsec);
 	to->di_ctime.t_sec = cpu_to_be32(from->di_ctime.t_sec);
 	to->di_ctime.t_nsec = cpu_to_be32(from->di_ctime.t_nsec);
+
 	to->di_size = cpu_to_be64(from->di_size);
 	to->di_nblocks = cpu_to_be64(from->di_nblocks);
 	to->di_extsize = cpu_to_be32(from->di_extsize);
@@ -361,13 +443,10 @@ xfs_iread(
 	    !(mp->m_flags & XFS_MOUNT_IKEEP)) {
 		/* initialise the on-disk inode core */
 		memset(&ip->i_d, 0, sizeof(ip->i_d));
-		ip->i_d.di_magic = XFS_DINODE_MAGIC;
-		ip->i_d.di_gen = prandom_u32();
-		if (xfs_sb_version_hascrc(&mp->m_sb)) {
+		VFS_I(ip)->i_generation = prandom_u32();
+		if (xfs_sb_version_hascrc(&mp->m_sb))
 			ip->i_d.di_version = 3;
-			ip->i_d.di_ino = ip->i_ino;
-			uuid_copy(&ip->i_d.di_uuid, &mp->m_sb.sb_meta_uuid);
-		} else
+		else
 			ip->i_d.di_version = 2;
 		return 0;
 	}
@@ -397,7 +476,7 @@ xfs_iread(
 	 * Otherwise, just get the truly permanent information.
 	 */
 	if (dip->di_mode) {
-		xfs_dinode_from_disk(&ip->i_d, dip);
+		xfs_inode_from_disk(ip, dip);
 		error = xfs_iformat_fork(ip, dip);
 		if (error)  {
 #ifdef DEBUG
@@ -411,16 +490,10 @@ xfs_iread(
 		 * Partial initialisation of the in-core inode. Just the bits
 		 * that xfs_ialloc won't overwrite or relies on being correct.
 		 */
-		ip->i_d.di_magic = be16_to_cpu(dip->di_magic);
 		ip->i_d.di_version = dip->di_version;
-		ip->i_d.di_gen = be32_to_cpu(dip->di_gen);
+		VFS_I(ip)->i_generation = be32_to_cpu(dip->di_gen);
 		ip->i_d.di_flushiter = be16_to_cpu(dip->di_flushiter);
 
-		if (dip->di_version == 3) {
-			ip->i_d.di_ino = be64_to_cpu(dip->di_ino);
-			uuid_copy(&ip->i_d.di_uuid, &dip->di_uuid);
-		}
-
 		/*
 		 * Make sure to pull in the mode here as well in
 		 * case the inode is released without being used.
@@ -428,25 +501,10 @@ xfs_iread(
 		 * the inode is already free and not try to mess
 		 * with the uninitialized part of it.
 		 */
-		ip->i_d.di_mode = 0;
-	}
-
-	/*
-	 * Automatically convert version 1 inode formats in memory to version 2
-	 * inode format. If the inode is modified, it will get logged and
-	 * rewritten as a version 2 inode. We can do this because we set the
-	 * superblock feature bit for v2 inodes unconditionally during mount
-	 * and it means the reast of the code can assume the inode version is 2
-	 * or higher.
-	 */
-	if (ip->i_d.di_version == 1) {
-		ip->i_d.di_version = 2;
-		memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
-		ip->i_d.di_nlink = ip->i_d.di_onlink;
-		ip->i_d.di_onlink = 0;
-		xfs_set_projid(ip, 0);
+		VFS_I(ip)->i_mode = 0;
 	}
 
+	ASSERT(ip->i_d.di_version >= 2);
 	ip->i_delayed_blks = 0;
 
 	/*
diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h
index 9308c47f2a52..7c4dd321b215 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.h
+++ b/fs/xfs/libxfs/xfs_inode_buf.h
@@ -20,7 +20,36 @@
 
 struct xfs_inode;
 struct xfs_dinode;
-struct xfs_icdinode;
+
+/*
+ * In memory representation of the XFS inode. This is held in the in-core struct
+ * xfs_inode and represents the current on disk values but the structure is not
+ * in on-disk format.  That is, this structure is always translated to on-disk
+ * format specific structures at the appropriate time.
+ */
+struct xfs_icdinode {
+	__int8_t	di_version;	/* inode version */
+	__int8_t	di_format;	/* format of di_c data */
+	__uint16_t	di_flushiter;	/* incremented on flush */
+	__uint32_t	di_uid;		/* owner's user id */
+	__uint32_t	di_gid;		/* owner's group id */
+	__uint16_t	di_projid_lo;	/* lower part of owner's project id */
+	__uint16_t	di_projid_hi;	/* higher part of owner's project id */
+	xfs_fsize_t	di_size;	/* number of bytes in file */
+	xfs_rfsblock_t	di_nblocks;	/* # of direct & btree blocks used */
+	xfs_extlen_t	di_extsize;	/* basic/minimum extent size for file */
+	xfs_extnum_t	di_nextents;	/* number of extents in data fork */
+	xfs_aextnum_t	di_anextents;	/* number of extents in attribute fork*/
+	__uint8_t	di_forkoff;	/* attr fork offs, <<3 for 64b align */
+	__int8_t	di_aformat;	/* format of attr fork's data */
+	__uint32_t	di_dmevmask;	/* DMIG event mask */
+	__uint16_t	di_dmstate;	/* DMIG state info */
+	__uint16_t	di_flags;	/* random flags, XFS_DIFLAG_... */
+
+	__uint64_t	di_flags2;	/* more random flags */
+
+	xfs_ictimestamp_t di_crtime;	/* time created */
+};
 
 /*
  * Inode location information.  Stored in the inode and passed to
@@ -38,8 +67,11 @@ int	xfs_imap_to_bp(struct xfs_mount *, struct xfs_trans *,
 int	xfs_iread(struct xfs_mount *, struct xfs_trans *,
 		  struct xfs_inode *, uint);
 void	xfs_dinode_calc_crc(struct xfs_mount *, struct xfs_dinode *);
-void	xfs_dinode_to_disk(struct xfs_dinode *to, struct xfs_icdinode *from);
-void	xfs_dinode_from_disk(struct xfs_icdinode *to, struct xfs_dinode *from);
+void	xfs_inode_to_disk(struct xfs_inode *ip, struct xfs_dinode *to,
+			  xfs_lsn_t lsn);
+void	xfs_inode_from_disk(struct xfs_inode *ip, struct xfs_dinode *from);
+void	xfs_log_dinode_to_disk(struct xfs_log_dinode *from,
+			       struct xfs_dinode *to);
 
 #if defined(DEBUG)
 void	xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index 0defbd02f62d..11faf7df14c8 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -31,6 +31,7 @@
 #include "xfs_error.h"
 #include "xfs_trace.h"
 #include "xfs_attr_sf.h"
+#include "xfs_da_format.h"
 
 kmem_zone_t *xfs_ifork_zone;
 
@@ -120,7 +121,7 @@ xfs_iformat_fork(
 		return -EFSCORRUPTED;
 	}
 
-	switch (ip->i_d.di_mode & S_IFMT) {
+	switch (VFS_I(ip)->i_mode & S_IFMT) {
 	case S_IFIFO:
 	case S_IFCHR:
 	case S_IFBLK:
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index 265314690415..d54a8018b079 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -290,6 +290,7 @@ typedef struct xfs_inode_log_format_64 {
 	__int32_t		ilf_boffset;	/* off of inode in buffer */
 } xfs_inode_log_format_64_t;
 
+
 /*
  * Flags for xfs_trans_log_inode flags field.
  */
@@ -360,15 +361,15 @@ typedef struct xfs_ictimestamp {
 } xfs_ictimestamp_t;
 
 /*
- * NOTE:  This structure must be kept identical to struct xfs_dinode
- *	  except for the endianness annotations.
+ * Define the format of the inode core that is logged. This structure must be
+ * kept identical to struct xfs_dinode except for the endianness annotations.
  */
-typedef struct xfs_icdinode {
+struct xfs_log_dinode {
 	__uint16_t	di_magic;	/* inode magic # = XFS_DINODE_MAGIC */
 	__uint16_t	di_mode;	/* mode and type of file */
 	__int8_t	di_version;	/* inode version */
 	__int8_t	di_format;	/* format of di_c data */
-	__uint16_t	di_onlink;	/* old number of links to file */
+	__uint8_t	di_pad3[2];	/* unused in v2/3 inodes */
 	__uint32_t	di_uid;		/* owner's user id */
 	__uint32_t	di_gid;		/* owner's group id */
 	__uint32_t	di_nlink;	/* number of links to file */
@@ -407,13 +408,13 @@ typedef struct xfs_icdinode {
 	uuid_t		di_uuid;	/* UUID of the filesystem */
 
 	/* structure must be padded to 64 bit alignment */
-} xfs_icdinode_t;
+};
 
-static inline uint xfs_icdinode_size(int version)
+static inline uint xfs_log_dinode_size(int version)
 {
 	if (version == 3)
-		return sizeof(struct xfs_icdinode);
-	return offsetof(struct xfs_icdinode, di_next_unlinked);
+		return sizeof(struct xfs_log_dinode);
+	return offsetof(struct xfs_log_dinode, di_next_unlinked);
 }
 
 /*
@@ -495,6 +496,8 @@ enum xfs_blft {
 	XFS_BLFT_ATTR_LEAF_BUF,
 	XFS_BLFT_ATTR_RMT_BUF,
 	XFS_BLFT_SB_BUF,
+	XFS_BLFT_RTBITMAP_BUF,
+	XFS_BLFT_RTSUMMARY_BUF,
 	XFS_BLFT_MAX_BUF = (1 << XFS_BLFT_BITS),
 };
 
diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h
index 1c55ccbb379d..8e385f91d660 100644
--- a/fs/xfs/libxfs/xfs_log_recover.h
+++ b/fs/xfs/libxfs/xfs_log_recover.h
@@ -60,6 +60,7 @@ typedef struct xlog_recover {
  */
 #define	XLOG_BC_TABLE_SIZE	64
 
+#define	XLOG_RECOVER_CRCPASS	0
 #define	XLOG_RECOVER_PASS1	1
 #define	XLOG_RECOVER_PASS2	2
 
diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h
index 1b0a08379759..8eed51275bb3 100644
--- a/fs/xfs/libxfs/xfs_quota_defs.h
+++ b/fs/xfs/libxfs/xfs_quota_defs.h
@@ -37,7 +37,7 @@ typedef __uint16_t	xfs_qwarncnt_t;
 #define XFS_DQ_PROJ		0x0002		/* project quota */
 #define XFS_DQ_GROUP		0x0004		/* a group quota */
 #define XFS_DQ_DIRTY		0x0008		/* dquot is dirty */
-#define XFS_DQ_FREEING		0x0010		/* dquot is beeing torn down */
+#define XFS_DQ_FREEING		0x0010		/* dquot is being torn down */
 
 #define XFS_DQ_ALLTYPES		(XFS_DQ_USER|XFS_DQ_PROJ|XFS_DQ_GROUP)
 
@@ -116,6 +116,7 @@ typedef __uint16_t	xfs_qwarncnt_t;
 #define XFS_QMOPT_DQREPAIR	0x0001000 /* repair dquot if damaged */
 #define XFS_QMOPT_GQUOTA	0x0002000 /* group dquot requested */
 #define XFS_QMOPT_ENOSPC	0x0004000 /* enospc instead of edquot (prj) */
+#define XFS_QMOPT_DQNEXT	0x0008000 /* return next dquot >= this ID */
 
 /*
  * flags to xfs_trans_mod_dquot to indicate which field needs to be
@@ -153,7 +154,7 @@ typedef __uint16_t	xfs_qwarncnt_t;
 #define XFS_QMOPT_RESBLK_MASK	(XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_RES_RTBLKS)
 
 extern int xfs_dqcheck(struct xfs_mount *mp, xfs_disk_dquot_t *ddq,
-		       xfs_dqid_t id, uint type, uint flags, char *str);
+		       xfs_dqid_t id, uint type, uint flags, const char *str);
 extern int xfs_calc_dquots_per_chunk(unsigned int nbblks);
 
 #endif	/* __XFS_QUOTA_H__ */
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 9b59ffa1fc19..951c044e24e4 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -42,6 +42,31 @@
  */
 
 /*
+ * Real time buffers need verifiers to avoid runtime warnings during IO.
+ * We don't have anything to verify, however, so these are just dummy
+ * operations.
+ */
+static void
+xfs_rtbuf_verify_read(
+	struct xfs_buf	*bp)
+{
+	return;
+}
+
+static void
+xfs_rtbuf_verify_write(
+	struct xfs_buf	*bp)
+{
+	return;
+}
+
+const struct xfs_buf_ops xfs_rtbuf_ops = {
+	.name = "rtbuf",
+	.verify_read = xfs_rtbuf_verify_read,
+	.verify_write = xfs_rtbuf_verify_write,
+};
+
+/*
  * Get a buffer for the bitmap or summary file block specified.
  * The buffer is returned read and locked.
  */
@@ -68,9 +93,12 @@ xfs_rtbuf_get(
 	ASSERT(map.br_startblock != NULLFSBLOCK);
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
 				   XFS_FSB_TO_DADDR(mp, map.br_startblock),
-				   mp->m_bsize, 0, &bp, NULL);
+				   mp->m_bsize, 0, &bp, &xfs_rtbuf_ops);
 	if (error)
 		return error;
+
+	xfs_trans_buf_set_type(tp, bp, issum ? XFS_BLFT_RTSUMMARY_BUF
+					     : XFS_BLFT_RTBITMAP_BUF);
 	*bpp = bp;
 	return 0;
 }
@@ -983,7 +1011,7 @@ xfs_rtfree_extent(
 	    mp->m_sb.sb_rextents) {
 		if (!(mp->m_rbmip->i_d.di_flags & XFS_DIFLAG_NEWRTBM))
 			mp->m_rbmip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM;
-		*(__uint64_t *)&mp->m_rbmip->i_d.di_atime = 0;
+		*(__uint64_t *)&VFS_I(mp->m_rbmip)->i_atime = 0;
 		xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE);
 	}
 	return 0;
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 47425140f343..8a53eaa349f4 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -35,6 +35,7 @@
 #include "xfs_bmap_btree.h"
 #include "xfs_alloc_btree.h"
 #include "xfs_ialloc_btree.h"
+#include "xfs_log.h"
 
 /*
  * Physical superblock buffer manipulations. Shared with libxfs in userspace.
@@ -163,6 +164,15 @@ xfs_mount_validate_sb(
 "Filesystem can not be safely mounted by this kernel.");
 			return -EINVAL;
 		}
+	} else if (xfs_sb_version_hascrc(sbp)) {
+		/*
+		 * We can't read verify the sb LSN because the read verifier is
+		 * called before the log is allocated and processed. We know the
+		 * log is set up before write verifier (!check_version) calls,
+		 * so just check it here.
+		 */
+		if (!xfs_log_check_lsn(mp, sbp->sb_lsn))
+			return -EFSCORRUPTED;
 	}
 
 	if (xfs_sb_version_has_pquotino(sbp)) {
@@ -669,11 +679,13 @@ xfs_sb_write_verify(
 }
 
 const struct xfs_buf_ops xfs_sb_buf_ops = {
+	.name = "xfs_sb",
 	.verify_read = xfs_sb_read_verify,
 	.verify_write = xfs_sb_write_verify,
 };
 
 const struct xfs_buf_ops xfs_sb_quiet_buf_ops = {
+	.name = "xfs_sb_quiet",
 	.verify_read = xfs_sb_quiet_read_verify,
 	.verify_write = xfs_sb_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h
index b25bb9a343f3..961e6475a309 100644
--- a/fs/xfs/libxfs/xfs_sb.h
+++ b/fs/xfs/libxfs/xfs_sb.h
@@ -27,7 +27,6 @@ extern struct xfs_perag *xfs_perag_get_tag(struct xfs_mount *, xfs_agnumber_t,
 extern void	xfs_perag_put(struct xfs_perag *pag);
 extern int	xfs_initialize_perag_data(struct xfs_mount *, xfs_agnumber_t);
 
-extern void	xfs_sb_calc_crc(struct xfs_buf *bp);
 extern void	xfs_log_sb(struct xfs_trans *tp);
 extern int	xfs_sync_sb(struct xfs_mount *mp, bool wait);
 extern void	xfs_sb_mount_common(struct xfs_mount *mp, struct xfs_sb *sbp);
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index 5be529707903..81ac870834da 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -49,9 +49,11 @@ extern const struct xfs_buf_ops xfs_inobt_buf_ops;
 extern const struct xfs_buf_ops xfs_inode_buf_ops;
 extern const struct xfs_buf_ops xfs_inode_buf_ra_ops;
 extern const struct xfs_buf_ops xfs_dquot_buf_ops;
+extern const struct xfs_buf_ops xfs_dquot_buf_ra_ops;
 extern const struct xfs_buf_ops xfs_sb_buf_ops;
 extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops;
 extern const struct xfs_buf_ops xfs_symlink_buf_ops;
+extern const struct xfs_buf_ops xfs_rtbuf_ops;
 
 /*
  * Transaction types.  Used to distinguish types of buffers. These never reach
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c
index 8f8af05b3f13..2e2c6716b623 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.c
+++ b/fs/xfs/libxfs/xfs_symlink_remote.c
@@ -31,6 +31,7 @@
 #include "xfs_cksum.h"
 #include "xfs_trans.h"
 #include "xfs_buf_item.h"
+#include "xfs_log.h"
 
 
 /*
@@ -60,6 +61,7 @@ xfs_symlink_hdr_set(
 	if (!xfs_sb_version_hascrc(&mp->m_sb))
 		return 0;
 
+	memset(dsl, 0, sizeof(struct xfs_dsymlink_hdr));
 	dsl->sl_magic = cpu_to_be32(XFS_SYMLINK_MAGIC);
 	dsl->sl_offset = cpu_to_be32(offset);
 	dsl->sl_bytes = cpu_to_be32(size);
@@ -116,6 +118,8 @@ xfs_symlink_verify(
 		return false;
 	if (dsl->sl_owner == 0)
 		return false;
+	if (!xfs_log_check_lsn(mp, be64_to_cpu(dsl->sl_lsn)))
+		return false;
 
 	return true;
 }
@@ -164,6 +168,7 @@ xfs_symlink_write_verify(
 }
 
 const struct xfs_buf_ops xfs_symlink_buf_ops = {
+	.name = "xfs_symlink",
 	.verify_read = xfs_symlink_read_verify,
 	.verify_write = xfs_symlink_write_verify,
 };
@@ -183,6 +188,7 @@ xfs_symlink_local_to_remote(
 	if (!xfs_sb_version_hascrc(&mp->m_sb)) {
 		bp->b_ops = NULL;
 		memcpy(bp->b_addr, ifp->if_u1.if_data, ifp->if_bytes);
+		xfs_trans_log_buf(tp, bp, 0, ifp->if_bytes - 1);
 		return;
 	}
 
@@ -198,4 +204,6 @@ xfs_symlink_local_to_remote(
 	buf = bp->b_addr;
 	buf += xfs_symlink_hdr_set(mp, ip->i_ino, 0, ifp->if_bytes, bp);
 	memcpy(buf, ifp->if_u1.if_data, ifp->if_bytes);
+	xfs_trans_log_buf(tp, bp, 0, sizeof(struct xfs_dsymlink_hdr) +
+					ifp->if_bytes - 1);
 }
diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c
index 4b641676f258..2d5df1f23bbc 100644
--- a/fs/xfs/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
@@ -37,16 +37,19 @@
 
 STATIC struct posix_acl *
 xfs_acl_from_disk(
-	struct xfs_acl	*aclp,
-	int		max_entries)
+	const struct xfs_acl	*aclp,
+	int			len,
+	int			max_entries)
 {
 	struct posix_acl_entry *acl_e;
 	struct posix_acl *acl;
-	struct xfs_acl_entry *ace;
+	const struct xfs_acl_entry *ace;
 	unsigned int count, i;
 
+	if (len < sizeof(*aclp))
+		return ERR_PTR(-EFSCORRUPTED);
 	count = be32_to_cpu(aclp->acl_cnt);
-	if (count > max_entries)
+	if (count > max_entries || XFS_ACL_SIZE(count) != len)
 		return ERR_PTR(-EFSCORRUPTED);
 
 	acl = posix_acl_alloc(count, GFP_KERNEL);
@@ -160,10 +163,11 @@ xfs_get_acl(struct inode *inode, int type)
 		 */
 		if (error == -ENOATTR)
 			goto out_update_cache;
+		acl = ERR_PTR(error);
 		goto out;
 	}
 
-	acl = xfs_acl_from_disk(xfs_acl, XFS_ACL_MAX_ENTRIES(ip->i_mount));
+	acl = xfs_acl_from_disk(xfs_acl, len, XFS_ACL_MAX_ENTRIES(ip->i_mount));
 	if (IS_ERR(acl))
 		goto out;
 
@@ -248,29 +252,6 @@ xfs_set_mode(struct inode *inode, umode_t mode)
 	return error;
 }
 
-static int
-xfs_acl_exists(struct inode *inode, unsigned char *name)
-{
-	int len = XFS_ACL_MAX_SIZE(XFS_M(inode->i_sb));
-
-	return (xfs_attr_get(XFS_I(inode), name, NULL, &len,
-			    ATTR_ROOT|ATTR_KERNOVAL) == 0);
-}
-
-int
-posix_acl_access_exists(struct inode *inode)
-{
-	return xfs_acl_exists(inode, SGI_ACL_FILE);
-}
-
-int
-posix_acl_default_exists(struct inode *inode)
-{
-	if (!S_ISDIR(inode->i_mode))
-		return 0;
-	return xfs_acl_exists(inode, SGI_ACL_DEFAULT);
-}
-
 int
 xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
diff --git a/fs/xfs/xfs_acl.h b/fs/xfs/xfs_acl.h
index 3841b07f27bf..286fa89217f5 100644
--- a/fs/xfs/xfs_acl.h
+++ b/fs/xfs/xfs_acl.h
@@ -20,20 +20,18 @@
 
 struct inode;
 struct posix_acl;
-struct xfs_inode;
 
 #ifdef CONFIG_XFS_POSIX_ACL
 extern struct posix_acl *xfs_get_acl(struct inode *inode, int type);
 extern int xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
-extern int posix_acl_access_exists(struct inode *inode);
-extern int posix_acl_default_exists(struct inode *inode);
 #else
 static inline struct posix_acl *xfs_get_acl(struct inode *inode, int type)
 {
 	return NULL;
 }
 # define xfs_set_acl					NULL
-# define posix_acl_access_exists(inode)			0
-# define posix_acl_default_exists(inode)		0
 #endif /* CONFIG_XFS_POSIX_ACL */
+
+extern void xfs_forget_acl(struct inode *inode, const char *name, int xflags);
+
 #endif	/* __XFS_ACL_H__ */
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 50ab2879b9da..e49b2406d15d 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -36,6 +36,21 @@
 #include <linux/pagevec.h>
 #include <linux/writeback.h>
 
+/* flags for direct write completions */
+#define XFS_DIO_FLAG_UNWRITTEN	(1 << 0)
+#define XFS_DIO_FLAG_APPEND	(1 << 1)
+
+/*
+ * structure owned by writepages passed to individual writepage calls
+ */
+struct xfs_writepage_ctx {
+	struct xfs_bmbt_irec    imap;
+	bool			imap_valid;
+	unsigned int		io_type;
+	struct xfs_ioend	*ioend;
+	sector_t		last_block;
+};
+
 void
 xfs_count_page_state(
 	struct page		*page,
@@ -55,7 +70,7 @@ xfs_count_page_state(
 	} while ((bh = bh->b_this_page) != head);
 }
 
-STATIC struct block_device *
+struct block_device *
 xfs_find_bdev_for_inode(
 	struct inode		*inode)
 {
@@ -172,6 +187,12 @@ xfs_setfilesize_ioend(
 	current_set_flags_nested(&tp->t_pflags, PF_FSTRANS);
 	__sb_writers_acquired(VFS_I(ip)->i_sb, SB_FREEZE_FS);
 
+	/* we abort the update if there was an IO error */
+	if (ioend->io_error) {
+		xfs_trans_cancel(tp);
+		return ioend->io_error;
+	}
+
 	return xfs_setfilesize(ip, tp, ioend->io_offset, ioend->io_size);
 }
 
@@ -208,18 +229,23 @@ xfs_end_io(
 	struct xfs_inode *ip = XFS_I(ioend->io_inode);
 	int		error = 0;
 
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
+	/*
+	 * Set an error if the mount has shut down and proceed with end I/O
+	 * processing so it can perform whatever cleanups are necessary.
+	 */
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
 		ioend->io_error = -EIO;
-		goto done;
-	}
-	if (ioend->io_error)
-		goto done;
 
 	/*
 	 * For unwritten extents we need to issue transactions to convert a
 	 * range to normal written extens after the data I/O has finished.
+	 * Detecting and handling completion IO errors is done individually
+	 * for each case as different cleanup operations need to be performed
+	 * on error.
 	 */
 	if (ioend->io_type == XFS_IO_UNWRITTEN) {
+		if (ioend->io_error)
+			goto done;
 		error = xfs_iomap_write_unwritten(ip, ioend->io_offset,
 						  ioend->io_size);
 	} else if (ioend->io_append_trans) {
@@ -256,7 +282,7 @@ xfs_alloc_ioend(
 	 */
 	atomic_set(&ioend->io_remaining, 1);
 	ioend->io_error = 0;
-	ioend->io_list = NULL;
+	INIT_LIST_HEAD(&ioend->io_list);
 	ioend->io_type = type;
 	ioend->io_inode = inode;
 	ioend->io_buffer_head = NULL;
@@ -274,8 +300,7 @@ xfs_map_blocks(
 	struct inode		*inode,
 	loff_t			offset,
 	struct xfs_bmbt_irec	*imap,
-	int			type,
-	int			nonblocking)
+	int			type)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
@@ -291,12 +316,7 @@ xfs_map_blocks(
 	if (type == XFS_IO_UNWRITTEN)
 		bmapi_flags |= XFS_BMAPI_IGSTATE;
 
-	if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) {
-		if (nonblocking)
-			return -EAGAIN;
-		xfs_ilock(ip, XFS_ILOCK_SHARED);
-	}
-
+	xfs_ilock(ip, XFS_ILOCK_SHARED);
 	ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
 	       (ip->i_df.if_flags & XFS_IFEXTENTS));
 	ASSERT(offset <= mp->m_super->s_maxbytes);
@@ -332,7 +352,7 @@ xfs_map_blocks(
 	return 0;
 }
 
-STATIC int
+STATIC bool
 xfs_imap_valid(
 	struct inode		*inode,
 	struct xfs_bmbt_irec	*imap,
@@ -405,8 +425,7 @@ xfs_start_buffer_writeback(
 STATIC void
 xfs_start_page_writeback(
 	struct page		*page,
-	int			clear_dirty,
-	int			buffers)
+	int			clear_dirty)
 {
 	ASSERT(PageLocked(page));
 	ASSERT(!PageWriteback(page));
@@ -425,10 +444,6 @@ xfs_start_page_writeback(
 		set_page_writeback_keepwrite(page);
 
 	unlock_page(page);
-
-	/* If no buffers on the page are to be written, finish it here */
-	if (!buffers)
-		end_page_writeback(page);
 }
 
 static inline int xfs_bio_add_buffer(struct bio *bio, struct buffer_head *bh)
@@ -437,153 +452,101 @@ static inline int xfs_bio_add_buffer(struct bio *bio, struct buffer_head *bh)
 }
 
 /*
- * Submit all of the bios for all of the ioends we have saved up, covering the
- * initial writepage page and also any probed pages.
- *
- * Because we may have multiple ioends spanning a page, we need to start
- * writeback on all the buffers before we submit them for I/O. If we mark the
- * buffers as we got, then we can end up with a page that only has buffers
- * marked async write and I/O complete on can occur before we mark the other
- * buffers async write.
- *
- * The end result of this is that we trip a bug in end_page_writeback() because
- * we call it twice for the one page as the code in end_buffer_async_write()
- * assumes that all buffers on the page are started at the same time.
- *
- * The fix is two passes across the ioend list - one to start writeback on the
- * buffer_heads, and then submit them for I/O on the second pass.
+ * Submit all of the bios for an ioend. We are only passed a single ioend at a
+ * time; the caller is responsible for chaining prior to submission.
  *
  * If @fail is non-zero, it means that we have a situation where some part of
  * the submission process has failed after we have marked paged for writeback
  * and unlocked them. In this situation, we need to fail the ioend chain rather
  * than submit it to IO. This typically only happens on a filesystem shutdown.
  */
-STATIC void
+STATIC int
 xfs_submit_ioend(
 	struct writeback_control *wbc,
 	xfs_ioend_t		*ioend,
-	int			fail)
+	int			status)
 {
-	xfs_ioend_t		*head = ioend;
-	xfs_ioend_t		*next;
 	struct buffer_head	*bh;
 	struct bio		*bio;
 	sector_t		lastblock = 0;
 
-	/* Pass 1 - start writeback */
-	do {
-		next = ioend->io_list;
-		for (bh = ioend->io_buffer_head; bh; bh = bh->b_private)
-			xfs_start_buffer_writeback(bh);
-	} while ((ioend = next) != NULL);
+	/* Reserve log space if we might write beyond the on-disk inode size. */
+	if (!status &&
+	     ioend->io_type != XFS_IO_UNWRITTEN && xfs_ioend_is_append(ioend))
+		status = xfs_setfilesize_trans_alloc(ioend);
+	/*
+	 * If we are failing the IO now, just mark the ioend with an
+	 * error and finish it. This will run IO completion immediately
+	 * as there is only one reference to the ioend at this point in
+	 * time.
+	 */
+	if (status) {
+		ioend->io_error = status;
+		xfs_finish_ioend(ioend);
+		return status;
+	}
 
-	/* Pass 2 - submit I/O */
-	ioend = head;
-	do {
-		next = ioend->io_list;
-		bio = NULL;
+	bio = NULL;
+	for (bh = ioend->io_buffer_head; bh; bh = bh->b_private) {
 
-		/*
-		 * If we are failing the IO now, just mark the ioend with an
-		 * error and finish it. This will run IO completion immediately
-		 * as there is only one reference to the ioend at this point in
-		 * time.
-		 */
-		if (fail) {
-			ioend->io_error = fail;
-			xfs_finish_ioend(ioend);
-			continue;
+		if (!bio) {
+retry:
+			bio = xfs_alloc_ioend_bio(bh);
+		} else if (bh->b_blocknr != lastblock + 1) {
+			xfs_submit_ioend_bio(wbc, ioend, bio);
+			goto retry;
 		}
 
-		for (bh = ioend->io_buffer_head; bh; bh = bh->b_private) {
-
-			if (!bio) {
- retry:
-				bio = xfs_alloc_ioend_bio(bh);
-			} else if (bh->b_blocknr != lastblock + 1) {
-				xfs_submit_ioend_bio(wbc, ioend, bio);
-				goto retry;
-			}
-
-			if (xfs_bio_add_buffer(bio, bh) != bh->b_size) {
-				xfs_submit_ioend_bio(wbc, ioend, bio);
-				goto retry;
-			}
-
-			lastblock = bh->b_blocknr;
-		}
-		if (bio)
+		if (xfs_bio_add_buffer(bio, bh) != bh->b_size) {
 			xfs_submit_ioend_bio(wbc, ioend, bio);
-		xfs_finish_ioend(ioend);
-	} while ((ioend = next) != NULL);
-}
-
-/*
- * Cancel submission of all buffer_heads so far in this endio.
- * Toss the endio too.  Only ever called for the initial page
- * in a writepage request, so only ever one page.
- */
-STATIC void
-xfs_cancel_ioend(
-	xfs_ioend_t		*ioend)
-{
-	xfs_ioend_t		*next;
-	struct buffer_head	*bh, *next_bh;
-
-	do {
-		next = ioend->io_list;
-		bh = ioend->io_buffer_head;
-		do {
-			next_bh = bh->b_private;
-			clear_buffer_async_write(bh);
-			/*
-			 * The unwritten flag is cleared when added to the
-			 * ioend. We're not submitting for I/O so mark the
-			 * buffer unwritten again for next time around.
-			 */
-			if (ioend->io_type == XFS_IO_UNWRITTEN)
-				set_buffer_unwritten(bh);
-			unlock_buffer(bh);
-		} while ((bh = next_bh) != NULL);
+			goto retry;
+		}
 
-		mempool_free(ioend, xfs_ioend_pool);
-	} while ((ioend = next) != NULL);
+		lastblock = bh->b_blocknr;
+	}
+	if (bio)
+		xfs_submit_ioend_bio(wbc, ioend, bio);
+	xfs_finish_ioend(ioend);
+	return 0;
 }
 
 /*
  * Test to see if we've been building up a completion structure for
  * earlier buffers -- if so, we try to append to this ioend if we
  * can, otherwise we finish off any current ioend and start another.
- * Return true if we've finished the given ioend.
+ * Return the ioend we finished off so that the caller can submit it
+ * once it has finished processing the dirty page.
  */
 STATIC void
 xfs_add_to_ioend(
 	struct inode		*inode,
 	struct buffer_head	*bh,
 	xfs_off_t		offset,
-	unsigned int		type,
-	xfs_ioend_t		**result,
-	int			need_ioend)
+	struct xfs_writepage_ctx *wpc,
+	struct list_head	*iolist)
 {
-	xfs_ioend_t		*ioend = *result;
-
-	if (!ioend || need_ioend || type != ioend->io_type) {
-		xfs_ioend_t	*previous = *result;
-
-		ioend = xfs_alloc_ioend(inode, type);
-		ioend->io_offset = offset;
-		ioend->io_buffer_head = bh;
-		ioend->io_buffer_tail = bh;
-		if (previous)
-			previous->io_list = ioend;
-		*result = ioend;
+	if (!wpc->ioend || wpc->io_type != wpc->ioend->io_type ||
+	    bh->b_blocknr != wpc->last_block + 1 ||
+	    offset != wpc->ioend->io_offset + wpc->ioend->io_size) {
+		struct xfs_ioend	*new;
+
+		if (wpc->ioend)
+			list_add(&wpc->ioend->io_list, iolist);
+
+		new = xfs_alloc_ioend(inode, wpc->io_type);
+		new->io_offset = offset;
+		new->io_buffer_head = bh;
+		new->io_buffer_tail = bh;
+		wpc->ioend = new;
 	} else {
-		ioend->io_buffer_tail->b_private = bh;
-		ioend->io_buffer_tail = bh;
+		wpc->ioend->io_buffer_tail->b_private = bh;
+		wpc->ioend->io_buffer_tail = bh;
 	}
 
 	bh->b_private = NULL;
-	ioend->io_size += bh->b_size;
+	wpc->ioend->io_size += bh->b_size;
+	wpc->last_block = bh->b_blocknr;
+	xfs_start_buffer_writeback(bh);
 }
 
 STATIC void
@@ -669,183 +632,6 @@ xfs_check_page_type(
 	return false;
 }
 
-/*
- * Allocate & map buffers for page given the extent map. Write it out.
- * except for the original page of a writepage, this is called on
- * delalloc/unwritten pages only, for the original page it is possible
- * that the page has no mapping at all.
- */
-STATIC int
-xfs_convert_page(
-	struct inode		*inode,
-	struct page		*page,
-	loff_t			tindex,
-	struct xfs_bmbt_irec	*imap,
-	xfs_ioend_t		**ioendp,
-	struct writeback_control *wbc)
-{
-	struct buffer_head	*bh, *head;
-	xfs_off_t		end_offset;
-	unsigned long		p_offset;
-	unsigned int		type;
-	int			len, page_dirty;
-	int			count = 0, done = 0, uptodate = 1;
- 	xfs_off_t		offset = page_offset(page);
-
-	if (page->index != tindex)
-		goto fail;
-	if (!trylock_page(page))
-		goto fail;
-	if (PageWriteback(page))
-		goto fail_unlock_page;
-	if (page->mapping != inode->i_mapping)
-		goto fail_unlock_page;
-	if (!xfs_check_page_type(page, (*ioendp)->io_type, false))
-		goto fail_unlock_page;
-
-	/*
-	 * page_dirty is initially a count of buffers on the page before
-	 * EOF and is decremented as we move each into a cleanable state.
-	 *
-	 * Derivation:
-	 *
-	 * End offset is the highest offset that this page should represent.
-	 * If we are on the last page, (end_offset & (PAGE_CACHE_SIZE - 1))
-	 * will evaluate non-zero and be less than PAGE_CACHE_SIZE and
-	 * hence give us the correct page_dirty count. On any other page,
-	 * it will be zero and in that case we need page_dirty to be the
-	 * count of buffers on the page.
-	 */
-	end_offset = min_t(unsigned long long,
-			(xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT,
-			i_size_read(inode));
-
-	/*
-	 * If the current map does not span the entire page we are about to try
-	 * to write, then give up. The only way we can write a page that spans
-	 * multiple mappings in a single writeback iteration is via the
-	 * xfs_vm_writepage() function. Data integrity writeback requires the
-	 * entire page to be written in a single attempt, otherwise the part of
-	 * the page we don't write here doesn't get written as part of the data
-	 * integrity sync.
-	 *
-	 * For normal writeback, we also don't attempt to write partial pages
-	 * here as it simply means that write_cache_pages() will see it under
-	 * writeback and ignore the page until some point in the future, at
-	 * which time this will be the only page in the file that needs
-	 * writeback.  Hence for more optimal IO patterns, we should always
-	 * avoid partial page writeback due to multiple mappings on a page here.
-	 */
-	if (!xfs_imap_valid(inode, imap, end_offset))
-		goto fail_unlock_page;
-
-	len = 1 << inode->i_blkbits;
-	p_offset = min_t(unsigned long, end_offset & (PAGE_CACHE_SIZE - 1),
-					PAGE_CACHE_SIZE);
-	p_offset = p_offset ? roundup(p_offset, len) : PAGE_CACHE_SIZE;
-	page_dirty = p_offset / len;
-
-	/*
-	 * The moment we find a buffer that doesn't match our current type
-	 * specification or can't be written, abort the loop and start
-	 * writeback. As per the above xfs_imap_valid() check, only
-	 * xfs_vm_writepage() can handle partial page writeback fully - we are
-	 * limited here to the buffers that are contiguous with the current
-	 * ioend, and hence a buffer we can't write breaks that contiguity and
-	 * we have to defer the rest of the IO to xfs_vm_writepage().
-	 */
-	bh = head = page_buffers(page);
-	do {
-		if (offset >= end_offset)
-			break;
-		if (!buffer_uptodate(bh))
-			uptodate = 0;
-		if (!(PageUptodate(page) || buffer_uptodate(bh))) {
-			done = 1;
-			break;
-		}
-
-		if (buffer_unwritten(bh) || buffer_delay(bh) ||
-		    buffer_mapped(bh)) {
-			if (buffer_unwritten(bh))
-				type = XFS_IO_UNWRITTEN;
-			else if (buffer_delay(bh))
-				type = XFS_IO_DELALLOC;
-			else
-				type = XFS_IO_OVERWRITE;
-
-			/*
-			 * imap should always be valid because of the above
-			 * partial page end_offset check on the imap.
-			 */
-			ASSERT(xfs_imap_valid(inode, imap, offset));
-
-			lock_buffer(bh);
-			if (type != XFS_IO_OVERWRITE)
-				xfs_map_at_offset(inode, bh, imap, offset);
-			xfs_add_to_ioend(inode, bh, offset, type,
-					 ioendp, done);
-
-			page_dirty--;
-			count++;
-		} else {
-			done = 1;
-			break;
-		}
-	} while (offset += len, (bh = bh->b_this_page) != head);
-
-	if (uptodate && bh == head)
-		SetPageUptodate(page);
-
-	if (count) {
-		if (--wbc->nr_to_write <= 0 &&
-		    wbc->sync_mode == WB_SYNC_NONE)
-			done = 1;
-	}
-	xfs_start_page_writeback(page, !page_dirty, count);
-
-	return done;
- fail_unlock_page:
-	unlock_page(page);
- fail:
-	return 1;
-}
-
-/*
- * Convert & write out a cluster of pages in the same extent as defined
- * by mp and following the start page.
- */
-STATIC void
-xfs_cluster_write(
-	struct inode		*inode,
-	pgoff_t			tindex,
-	struct xfs_bmbt_irec	*imap,
-	xfs_ioend_t		**ioendp,
-	struct writeback_control *wbc,
-	pgoff_t			tlast)
-{
-	struct pagevec		pvec;
-	int			done = 0, i;
-
-	pagevec_init(&pvec, 0);
-	while (!done && tindex <= tlast) {
-		unsigned len = min_t(pgoff_t, PAGEVEC_SIZE, tlast - tindex + 1);
-
-		if (!pagevec_lookup(&pvec, inode->i_mapping, tindex, len))
-			break;
-
-		for (i = 0; i < pagevec_count(&pvec); i++) {
-			done = xfs_convert_page(inode, pvec.pages[i], tindex++,
-					imap, ioendp, wbc);
-			if (done)
-				break;
-		}
-
-		pagevec_release(&pvec);
-		cond_resched();
-	}
-}
-
 STATIC void
 xfs_vm_invalidatepage(
 	struct page		*page,
@@ -918,11 +704,169 @@ next_buffer:
 
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 out_invalidate:
-	xfs_vm_invalidatepage(page, 0, PAGE_CACHE_SIZE);
+	xfs_vm_invalidatepage(page, 0, PAGE_SIZE);
 	return;
 }
 
 /*
+ * We implement an immediate ioend submission policy here to avoid needing to
+ * chain multiple ioends and hence nest mempool allocations which can violate
+ * forward progress guarantees we need to provide. The current ioend we are
+ * adding buffers to is cached on the writepage context, and if the new buffer
+ * does not append to the cached ioend it will create a new ioend and cache that
+ * instead.
+ *
+ * If a new ioend is created and cached, the old ioend is returned and queued
+ * locally for submission once the entire page is processed or an error has been
+ * detected.  While ioends are submitted immediately after they are completed,
+ * batching optimisations are provided by higher level block plugging.
+ *
+ * At the end of a writeback pass, there will be a cached ioend remaining on the
+ * writepage context that the caller will need to submit.
+ */
+static int
+xfs_writepage_map(
+	struct xfs_writepage_ctx *wpc,
+	struct writeback_control *wbc,
+	struct inode		*inode,
+	struct page		*page,
+	loff_t			offset,
+	__uint64_t              end_offset)
+{
+	LIST_HEAD(submit_list);
+	struct xfs_ioend	*ioend, *next;
+	struct buffer_head	*bh, *head;
+	ssize_t			len = 1 << inode->i_blkbits;
+	int			error = 0;
+	int			count = 0;
+	int			uptodate = 1;
+
+	bh = head = page_buffers(page);
+	offset = page_offset(page);
+	do {
+		if (offset >= end_offset)
+			break;
+		if (!buffer_uptodate(bh))
+			uptodate = 0;
+
+		/*
+		 * set_page_dirty dirties all buffers in a page, independent
+		 * of their state.  The dirty state however is entirely
+		 * meaningless for holes (!mapped && uptodate), so skip
+		 * buffers covering holes here.
+		 */
+		if (!buffer_mapped(bh) && buffer_uptodate(bh)) {
+			wpc->imap_valid = false;
+			continue;
+		}
+
+		if (buffer_unwritten(bh)) {
+			if (wpc->io_type != XFS_IO_UNWRITTEN) {
+				wpc->io_type = XFS_IO_UNWRITTEN;
+				wpc->imap_valid = false;
+			}
+		} else if (buffer_delay(bh)) {
+			if (wpc->io_type != XFS_IO_DELALLOC) {
+				wpc->io_type = XFS_IO_DELALLOC;
+				wpc->imap_valid = false;
+			}
+		} else if (buffer_uptodate(bh)) {
+			if (wpc->io_type != XFS_IO_OVERWRITE) {
+				wpc->io_type = XFS_IO_OVERWRITE;
+				wpc->imap_valid = false;
+			}
+		} else {
+			if (PageUptodate(page))
+				ASSERT(buffer_mapped(bh));
+			/*
+			 * This buffer is not uptodate and will not be
+			 * written to disk.  Ensure that we will put any
+			 * subsequent writeable buffers into a new
+			 * ioend.
+			 */
+			wpc->imap_valid = false;
+			continue;
+		}
+
+		if (wpc->imap_valid)
+			wpc->imap_valid = xfs_imap_valid(inode, &wpc->imap,
+							 offset);
+		if (!wpc->imap_valid) {
+			error = xfs_map_blocks(inode, offset, &wpc->imap,
+					     wpc->io_type);
+			if (error)
+				goto out;
+			wpc->imap_valid = xfs_imap_valid(inode, &wpc->imap,
+							 offset);
+		}
+		if (wpc->imap_valid) {
+			lock_buffer(bh);
+			if (wpc->io_type != XFS_IO_OVERWRITE)
+				xfs_map_at_offset(inode, bh, &wpc->imap, offset);
+			xfs_add_to_ioend(inode, bh, offset, wpc, &submit_list);
+			count++;
+		}
+
+	} while (offset += len, ((bh = bh->b_this_page) != head));
+
+	if (uptodate && bh == head)
+		SetPageUptodate(page);
+
+	ASSERT(wpc->ioend || list_empty(&submit_list));
+
+out:
+	/*
+	 * On error, we have to fail the ioend here because we have locked
+	 * buffers in the ioend. If we don't do this, we'll deadlock
+	 * invalidating the page as that tries to lock the buffers on the page.
+	 * Also, because we may have set pages under writeback, we have to make
+	 * sure we run IO completion to mark the error state of the IO
+	 * appropriately, so we can't cancel the ioend directly here. That means
+	 * we have to mark this page as under writeback if we included any
+	 * buffers from it in the ioend chain so that completion treats it
+	 * correctly.
+	 *
+	 * If we didn't include the page in the ioend, the on error we can
+	 * simply discard and unlock it as there are no other users of the page
+	 * or it's buffers right now. The caller will still need to trigger
+	 * submission of outstanding ioends on the writepage context so they are
+	 * treated correctly on error.
+	 */
+	if (count) {
+		xfs_start_page_writeback(page, !error);
+
+		/*
+		 * Preserve the original error if there was one, otherwise catch
+		 * submission errors here and propagate into subsequent ioend
+		 * submissions.
+		 */
+		list_for_each_entry_safe(ioend, next, &submit_list, io_list) {
+			int error2;
+
+			list_del_init(&ioend->io_list);
+			error2 = xfs_submit_ioend(wbc, ioend, error);
+			if (error2 && !error)
+				error = error2;
+		}
+	} else if (error) {
+		xfs_aops_discard_page(page);
+		ClearPageUptodate(page);
+		unlock_page(page);
+	} else {
+		/*
+		 * We can end up here with no error and nothing to write if we
+		 * race with a partial page truncate on a sub-page block sized
+		 * filesystem. In that case we need to mark the page clean.
+		 */
+		xfs_start_page_writeback(page, 1);
+		end_page_writeback(page);
+	}
+
+	mapping_set_error(page->mapping, error);
+	return error;
+}
+
+/*
  * Write out a dirty page.
  *
  * For delalloc space on the page we need to allocate space and flush it.
@@ -931,22 +875,16 @@ out_invalidate:
  * For any other dirty buffer heads on the page we should flush them.
  */
 STATIC int
-xfs_vm_writepage(
+xfs_do_writepage(
 	struct page		*page,
-	struct writeback_control *wbc)
+	struct writeback_control *wbc,
+	void			*data)
 {
+	struct xfs_writepage_ctx *wpc = data;
 	struct inode		*inode = page->mapping->host;
-	struct buffer_head	*bh, *head;
-	struct xfs_bmbt_irec	imap;
-	xfs_ioend_t		*ioend = NULL, *iohead = NULL;
 	loff_t			offset;
-	unsigned int		type;
 	__uint64_t              end_offset;
-	pgoff_t                 end_index, last_index;
-	ssize_t			len;
-	int			err, imap_valid = 0, uptodate = 1;
-	int			count = 0;
-	int			nonblocking = 0;
+	pgoff_t                 end_index;
 
 	trace_xfs_writepage(inode, page, 0, 0);
 
@@ -973,12 +911,9 @@ xfs_vm_writepage(
 	if (WARN_ON_ONCE(current->flags & PF_FSTRANS))
 		goto redirty;
 
-	/* Is this page beyond the end of the file? */
-	offset = i_size_read(inode);
-	end_index = offset >> PAGE_CACHE_SHIFT;
-	last_index = (offset - 1) >> PAGE_CACHE_SHIFT;
-
 	/*
+	 * Is this page beyond the end of the file?
+	 *
 	 * The page index is less than the end_index, adjust the end_offset
 	 * to the highest offset that this page should represent.
 	 * -----------------------------------------------------
@@ -989,8 +924,10 @@ xfs_vm_writepage(
 	 * |     desired writeback range    |      see else    |
 	 * ---------------------------------^------------------|
 	 */
+	offset = i_size_read(inode);
+	end_index = offset >> PAGE_SHIFT;
 	if (page->index < end_index)
-		end_offset = (xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT;
+		end_offset = (xfs_off_t)(page->index + 1) << PAGE_SHIFT;
 	else {
 		/*
 		 * Check whether the page to write out is beyond or straddles
@@ -1003,7 +940,7 @@ xfs_vm_writepage(
 		 * |				    |      Straddles     |
 		 * ---------------------------------^-----------|--------|
 		 */
-		unsigned offset_into_page = offset & (PAGE_CACHE_SIZE - 1);
+		unsigned offset_into_page = offset & (PAGE_SIZE - 1);
 
 		/*
 		 * Skip the page if it is fully outside i_size, e.g. due to a
@@ -1034,158 +971,13 @@ xfs_vm_writepage(
 		 * memory is zeroed when mapped, and writes to that region are
 		 * not written out to the file."
 		 */
-		zero_user_segment(page, offset_into_page, PAGE_CACHE_SIZE);
+		zero_user_segment(page, offset_into_page, PAGE_SIZE);
 
 		/* Adjust the end_offset to the end of file */
 		end_offset = offset;
 	}
 
-	len = 1 << inode->i_blkbits;
-
-	bh = head = page_buffers(page);
-	offset = page_offset(page);
-	type = XFS_IO_OVERWRITE;
-
-	if (wbc->sync_mode == WB_SYNC_NONE)
-		nonblocking = 1;
-
-	do {
-		int new_ioend = 0;
-
-		if (offset >= end_offset)
-			break;
-		if (!buffer_uptodate(bh))
-			uptodate = 0;
-
-		/*
-		 * set_page_dirty dirties all buffers in a page, independent
-		 * of their state.  The dirty state however is entirely
-		 * meaningless for holes (!mapped && uptodate), so skip
-		 * buffers covering holes here.
-		 */
-		if (!buffer_mapped(bh) && buffer_uptodate(bh)) {
-			imap_valid = 0;
-			continue;
-		}
-
-		if (buffer_unwritten(bh)) {
-			if (type != XFS_IO_UNWRITTEN) {
-				type = XFS_IO_UNWRITTEN;
-				imap_valid = 0;
-			}
-		} else if (buffer_delay(bh)) {
-			if (type != XFS_IO_DELALLOC) {
-				type = XFS_IO_DELALLOC;
-				imap_valid = 0;
-			}
-		} else if (buffer_uptodate(bh)) {
-			if (type != XFS_IO_OVERWRITE) {
-				type = XFS_IO_OVERWRITE;
-				imap_valid = 0;
-			}
-		} else {
-			if (PageUptodate(page))
-				ASSERT(buffer_mapped(bh));
-			/*
-			 * This buffer is not uptodate and will not be
-			 * written to disk.  Ensure that we will put any
-			 * subsequent writeable buffers into a new
-			 * ioend.
-			 */
-			imap_valid = 0;
-			continue;
-		}
-
-		if (imap_valid)
-			imap_valid = xfs_imap_valid(inode, &imap, offset);
-		if (!imap_valid) {
-			/*
-			 * If we didn't have a valid mapping then we need to
-			 * put the new mapping into a separate ioend structure.
-			 * This ensures non-contiguous extents always have
-			 * separate ioends, which is particularly important
-			 * for unwritten extent conversion at I/O completion
-			 * time.
-			 */
-			new_ioend = 1;
-			err = xfs_map_blocks(inode, offset, &imap, type,
-					     nonblocking);
-			if (err)
-				goto error;
-			imap_valid = xfs_imap_valid(inode, &imap, offset);
-		}
-		if (imap_valid) {
-			lock_buffer(bh);
-			if (type != XFS_IO_OVERWRITE)
-				xfs_map_at_offset(inode, bh, &imap, offset);
-			xfs_add_to_ioend(inode, bh, offset, type, &ioend,
-					 new_ioend);
-			count++;
-		}
-
-		if (!iohead)
-			iohead = ioend;
-
-	} while (offset += len, ((bh = bh->b_this_page) != head));
-
-	if (uptodate && bh == head)
-		SetPageUptodate(page);
-
-	xfs_start_page_writeback(page, 1, count);
-
-	/* if there is no IO to be submitted for this page, we are done */
-	if (!ioend)
-		return 0;
-
-	ASSERT(iohead);
-
-	/*
-	 * Any errors from this point onwards need tobe reported through the IO
-	 * completion path as we have marked the initial page as under writeback
-	 * and unlocked it.
-	 */
-	if (imap_valid) {
-		xfs_off_t		end_index;
-
-		end_index = imap.br_startoff + imap.br_blockcount;
-
-		/* to bytes */
-		end_index <<= inode->i_blkbits;
-
-		/* to pages */
-		end_index = (end_index - 1) >> PAGE_CACHE_SHIFT;
-
-		/* check against file size */
-		if (end_index > last_index)
-			end_index = last_index;
-
-		xfs_cluster_write(inode, page->index + 1, &imap, &ioend,
-				  wbc, end_index);
-	}
-
-
-	/*
-	 * Reserve log space if we might write beyond the on-disk inode size.
-	 */
-	err = 0;
-	if (ioend->io_type != XFS_IO_UNWRITTEN && xfs_ioend_is_append(ioend))
-		err = xfs_setfilesize_trans_alloc(ioend);
-
-	xfs_submit_ioend(wbc, iohead, err);
-
-	return 0;
-
-error:
-	if (iohead)
-		xfs_cancel_ioend(iohead);
-
-	if (err == -EAGAIN)
-		goto redirty;
-
-	xfs_aops_discard_page(page);
-	ClearPageUptodate(page);
-	unlock_page(page);
-	return err;
+	return xfs_writepage_map(wpc, wbc, inode, page, offset, end_offset);
 
 redirty:
 	redirty_page_for_writepage(wbc, page);
@@ -1194,12 +986,40 @@ redirty:
 }
 
 STATIC int
+xfs_vm_writepage(
+	struct page		*page,
+	struct writeback_control *wbc)
+{
+	struct xfs_writepage_ctx wpc = {
+		.io_type = XFS_IO_INVALID,
+	};
+	int			ret;
+
+	ret = xfs_do_writepage(page, wbc, &wpc);
+	if (wpc.ioend)
+		ret = xfs_submit_ioend(wbc, wpc.ioend, ret);
+	return ret;
+}
+
+STATIC int
 xfs_vm_writepages(
 	struct address_space	*mapping,
 	struct writeback_control *wbc)
 {
+	struct xfs_writepage_ctx wpc = {
+		.io_type = XFS_IO_INVALID,
+	};
+	int			ret;
+
 	xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED);
-	return generic_writepages(mapping, wbc);
+	if (dax_mapping(mapping))
+		return dax_writeback_mapping_range(mapping,
+				xfs_find_bdev_for_inode(mapping->host), wbc);
+
+	ret = write_cache_pages(mapping, wbc, xfs_do_writepage, &wpc);
+	if (wpc.ioend)
+		ret = xfs_submit_ioend(wbc, wpc.ioend, ret);
+	return ret;
 }
 
 /*
@@ -1229,27 +1049,15 @@ xfs_vm_releasepage(
 }
 
 /*
- * When we map a DIO buffer, we may need to attach an ioend that describes the
- * type of write IO we are doing. This passes to the completion function the
- * operations it needs to perform. If the mapping is for an overwrite wholly
- * within the EOF then we don't need an ioend and so we don't allocate one.
- * This avoids the unnecessary overhead of allocating and freeing ioends for
- * workloads that don't require transactions on IO completion.
- *
- * If we get multiple mappings in a single IO, we might be mapping different
- * types. But because the direct IO can only have a single private pointer, we
- * need to ensure that:
+ * When we map a DIO buffer, we may need to pass flags to
+ * xfs_end_io_direct_write to tell it what kind of write IO we are doing.
  *
- * a) i) the ioend spans the entire region of unwritten mappings; or
- *    ii) the ioend spans all the mappings that cross or are beyond EOF; and
- * b) if it contains unwritten extents, it is *permanently* marked as such
- *
- * We could do this by chaining ioends like buffered IO does, but we only
- * actually get one IO completion callback from the direct IO, and that spans
- * the entire IO regardless of how many mappings and IOs are needed to complete
- * the DIO. There is only going to be one reference to the ioend and its life
- * cycle is constrained by the DIO completion code. hence we don't need
- * reference counting here.
+ * Note that for DIO, an IO to the highest supported file block offset (i.e.
+ * 2^63 - 1FSB bytes) will result in the offset + count overflowing a signed 64
+ * bit variable. Hence if we see this overflow, we have to assume that the IO is
+ * extending the file size. We won't know for sure until IO completion is run
+ * and the actual max write offset is communicated to the IO completion
+ * routine.
  */
 static void
 xfs_map_direct(
@@ -1258,44 +1066,18 @@ xfs_map_direct(
 	struct xfs_bmbt_irec	*imap,
 	xfs_off_t		offset)
 {
-	struct xfs_ioend	*ioend;
+	uintptr_t		*flags = (uintptr_t *)&bh_result->b_private;
 	xfs_off_t		size = bh_result->b_size;
-	int			type;
 
-	if (ISUNWRITTEN(imap))
-		type = XFS_IO_UNWRITTEN;
-	else
-		type = XFS_IO_OVERWRITE;
-
-	trace_xfs_gbmap_direct(XFS_I(inode), offset, size, type, imap);
-
-	if (bh_result->b_private) {
-		ioend = bh_result->b_private;
-		ASSERT(ioend->io_size > 0);
-		ASSERT(offset >= ioend->io_offset);
-		if (offset + size > ioend->io_offset + ioend->io_size)
-			ioend->io_size = offset - ioend->io_offset + size;
-
-		if (type == XFS_IO_UNWRITTEN && type != ioend->io_type)
-			ioend->io_type = XFS_IO_UNWRITTEN;
-
-		trace_xfs_gbmap_direct_update(XFS_I(inode), ioend->io_offset,
-					      ioend->io_size, ioend->io_type,
-					      imap);
-	} else if (type == XFS_IO_UNWRITTEN ||
-		   offset + size > i_size_read(inode)) {
-		ioend = xfs_alloc_ioend(inode, type);
-		ioend->io_offset = offset;
-		ioend->io_size = size;
-
-		bh_result->b_private = ioend;
-		set_buffer_defer_completion(bh_result);
+	trace_xfs_get_blocks_map_direct(XFS_I(inode), offset, size,
+		ISUNWRITTEN(imap) ? XFS_IO_UNWRITTEN : XFS_IO_OVERWRITE, imap);
 
-		trace_xfs_gbmap_direct_new(XFS_I(inode), offset, size, type,
-					   imap);
-	} else {
-		trace_xfs_gbmap_direct_none(XFS_I(inode), offset, size, type,
-					    imap);
+	if (ISUNWRITTEN(imap)) {
+		*flags |= XFS_DIO_FLAG_UNWRITTEN;
+		set_buffer_defer_completion(bh_result);
+	} else if (offset + size > i_size_read(inode) || offset + size < 0) {
+		*flags |= XFS_DIO_FLAG_APPEND;
+		set_buffer_defer_completion(bh_result);
 	}
 }
 
@@ -1345,7 +1127,8 @@ __xfs_get_blocks(
 	sector_t		iblock,
 	struct buffer_head	*bh_result,
 	int			create,
-	bool			direct)
+	bool			direct,
+	bool			dax_fault)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
@@ -1393,18 +1176,20 @@ __xfs_get_blocks(
 	if (error)
 		goto out_unlock;
 
+	/* for DAX, we convert unwritten extents directly */
 	if (create &&
 	    (!nimaps ||
 	     (imap.br_startblock == HOLESTARTBLOCK ||
-	      imap.br_startblock == DELAYSTARTBLOCK))) {
+	      imap.br_startblock == DELAYSTARTBLOCK) ||
+	     (IS_DAX(inode) && ISUNWRITTEN(&imap)))) {
 		if (direct || xfs_get_extsz_hint(ip)) {
 			/*
-			 * Drop the ilock in preparation for starting the block
-			 * allocation transaction.  It will be retaken
-			 * exclusively inside xfs_iomap_write_direct for the
-			 * actual allocation.
+			 * xfs_iomap_write_direct() expects the shared lock. It
+			 * is unlocked on return.
 			 */
-			xfs_iunlock(ip, lockmode);
+			if (lockmode == XFS_ILOCK_EXCL)
+				xfs_ilock_demote(ip, lockmode);
+
 			error = xfs_iomap_write_direct(ip, offset, size,
 						       &imap, nimaps);
 			if (error)
@@ -1441,6 +1226,12 @@ __xfs_get_blocks(
 		goto out_unlock;
 	}
 
+	if (IS_DAX(inode) && create) {
+		ASSERT(!ISUNWRITTEN(&imap));
+		/* zeroing is not needed at a higher layer */
+		new = 0;
+	}
+
 	/* trim mapping down to size requested */
 	if (direct || size > (1 << inode->i_blkbits))
 		xfs_map_trim_size(inode, iblock, bh_result,
@@ -1457,8 +1248,12 @@ __xfs_get_blocks(
 		if (ISUNWRITTEN(&imap))
 			set_buffer_unwritten(bh_result);
 		/* direct IO needs special help */
-		if (create && direct)
-			xfs_map_direct(inode, bh_result, &imap, offset);
+		if (create && direct) {
+			if (dax_fault)
+				ASSERT(!ISUNWRITTEN(&imap));
+			else
+				xfs_map_direct(inode, bh_result, &imap, offset);
+		}
 	}
 
 	/*
@@ -1505,7 +1300,7 @@ xfs_get_blocks(
 	struct buffer_head	*bh_result,
 	int			create)
 {
-	return __xfs_get_blocks(inode, iblock, bh_result, create, false);
+	return __xfs_get_blocks(inode, iblock, bh_result, create, false, false);
 }
 
 int
@@ -1515,45 +1310,63 @@ xfs_get_blocks_direct(
 	struct buffer_head	*bh_result,
 	int			create)
 {
-	return __xfs_get_blocks(inode, iblock, bh_result, create, true);
+	return __xfs_get_blocks(inode, iblock, bh_result, create, true, false);
 }
 
-static void
-__xfs_end_io_direct_write(
+int
+xfs_get_blocks_dax_fault(
 	struct inode		*inode,
-	struct xfs_ioend	*ioend,
+	sector_t		iblock,
+	struct buffer_head	*bh_result,
+	int			create)
+{
+	return __xfs_get_blocks(inode, iblock, bh_result, create, true, true);
+}
+
+/*
+ * Complete a direct I/O write request.
+ *
+ * xfs_map_direct passes us some flags in the private data to tell us what to
+ * do.  If no flags are set, then the write IO is an overwrite wholly within
+ * the existing allocated file size and so there is nothing for us to do.
+ *
+ * Note that in this case the completion can be called in interrupt context,
+ * whereas if we have flags set we will always be called in task context
+ * (i.e. from a workqueue).
+ */
+STATIC int
+xfs_end_io_direct_write(
+	struct kiocb		*iocb,
 	loff_t			offset,
-	ssize_t			size)
+	ssize_t			size,
+	void			*private)
 {
-	struct xfs_mount	*mp = XFS_I(inode)->i_mount;
+	struct inode		*inode = file_inode(iocb->ki_filp);
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	uintptr_t		flags = (uintptr_t)private;
+	int			error = 0;
 
-	if (XFS_FORCED_SHUTDOWN(mp) || ioend->io_error)
-		goto out_end_io;
+	trace_xfs_end_io_direct_write(ip, offset, size);
 
-	/*
-	 * dio completion end_io functions are only called on writes if more
-	 * than 0 bytes was written.
-	 */
-	ASSERT(size > 0);
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return -EIO;
 
-	/*
-	 * The ioend only maps whole blocks, while the IO may be sector aligned.
-	 * Hence the ioend offset/size may not match the IO offset/size exactly.
-	 * Because we don't map overwrites within EOF into the ioend, the offset
-	 * may not match, but only if the endio spans EOF.  Either way, write
-	 * the IO sizes into the ioend so that completion processing does the
-	 * right thing.
-	 */
-	ASSERT(offset + size <= ioend->io_offset + ioend->io_size);
-	ioend->io_size = size;
-	ioend->io_offset = offset;
+	if (size <= 0)
+		return size;
 
 	/*
-	 * The ioend tells us whether we are doing unwritten extent conversion
+	 * The flags tell us whether we are doing unwritten extent conversions
 	 * or an append transaction that updates the on-disk file size. These
 	 * cases are the only cases where we should *potentially* be needing
 	 * to update the VFS inode size.
-	 *
+	 */
+	if (flags == 0) {
+		ASSERT(offset + size <= i_size_read(inode));
+		return 0;
+	}
+
+	/*
 	 * We need to update the in-core inode size here so that we don't end up
 	 * with the on-disk inode size being outside the in-core inode size. We
 	 * have no other method of updating EOF for AIO, so always do it here
@@ -1564,130 +1377,56 @@ __xfs_end_io_direct_write(
 	 * here can result in EOF moving backwards and Bad Things Happen when
 	 * that occurs.
 	 */
-	spin_lock(&XFS_I(inode)->i_flags_lock);
+	spin_lock(&ip->i_flags_lock);
 	if (offset + size > i_size_read(inode))
 		i_size_write(inode, offset + size);
-	spin_unlock(&XFS_I(inode)->i_flags_lock);
+	spin_unlock(&ip->i_flags_lock);
 
-	/*
-	 * If we are doing an append IO that needs to update the EOF on disk,
-	 * do the transaction reserve now so we can use common end io
-	 * processing. Stashing the error (if there is one) in the ioend will
-	 * result in the ioend processing passing on the error if it is
-	 * possible as we can't return it from here.
-	 */
-	if (ioend->io_type == XFS_IO_OVERWRITE)
-		ioend->io_error = xfs_setfilesize_trans_alloc(ioend);
+	if (flags & XFS_DIO_FLAG_UNWRITTEN) {
+		trace_xfs_end_io_direct_write_unwritten(ip, offset, size);
 
-out_end_io:
-	xfs_end_io(&ioend->io_work);
-	return;
-}
+		error = xfs_iomap_write_unwritten(ip, offset, size);
+	} else if (flags & XFS_DIO_FLAG_APPEND) {
+		struct xfs_trans *tp;
 
-/*
- * Complete a direct I/O write request.
- *
- * The ioend structure is passed from __xfs_get_blocks() to tell us what to do.
- * If no ioend exists (i.e. @private == NULL) then the write IO is an overwrite
- * wholly within the EOF and so there is nothing for us to do. Note that in this
- * case the completion can be called in interrupt context, whereas if we have an
- * ioend we will always be called in task context (i.e. from a workqueue).
- */
-STATIC void
-xfs_end_io_direct_write(
-	struct kiocb		*iocb,
-	loff_t			offset,
-	ssize_t			size,
-	void			*private)
-{
-	struct inode		*inode = file_inode(iocb->ki_filp);
-	struct xfs_ioend	*ioend = private;
+		trace_xfs_end_io_direct_write_append(ip, offset, size);
 
-	trace_xfs_gbmap_direct_endio(XFS_I(inode), offset, size,
-				     ioend ? ioend->io_type : 0, NULL);
-
-	if (!ioend) {
-		ASSERT(offset + size <= i_size_read(inode));
-		return;
+		tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
+		error = xfs_trans_reserve(tp, &M_RES(mp)->tr_fsyncts, 0, 0);
+		if (error) {
+			xfs_trans_cancel(tp);
+			return error;
+		}
+		error = xfs_setfilesize(ip, tp, offset, size);
 	}
 
-	__xfs_end_io_direct_write(inode, ioend, offset, size);
-}
-
-/*
- * For DAX we need a mapping buffer callback for unwritten extent conversion
- * when page faults allocate blocks and then zero them. Note that in this
- * case the mapping indicated by the ioend may extend beyond EOF. We most
- * definitely do not want to extend EOF here, so we trim back the ioend size to
- * EOF.
- */
-#ifdef CONFIG_FS_DAX
-void
-xfs_end_io_dax_write(
-	struct buffer_head	*bh,
-	int			uptodate)
-{
-	struct xfs_ioend	*ioend = bh->b_private;
-	struct inode		*inode = ioend->io_inode;
-	ssize_t			size = ioend->io_size;
-
-	ASSERT(IS_DAX(ioend->io_inode));
-
-	/* if there was an error zeroing, then don't convert it */
-	if (!uptodate)
-		ioend->io_error = -EIO;
-
-	/*
-	 * Trim update to EOF, so we don't extend EOF during unwritten extent
-	 * conversion of partial EOF blocks.
-	 */
-	spin_lock(&XFS_I(inode)->i_flags_lock);
-	if (ioend->io_offset + size > i_size_read(inode))
-		size = i_size_read(inode) - ioend->io_offset;
-	spin_unlock(&XFS_I(inode)->i_flags_lock);
-
-	__xfs_end_io_direct_write(inode, ioend, ioend->io_offset, size);
-
+	return error;
 }
-#else
-void xfs_end_io_dax_write(struct buffer_head *bh, int uptodate) { }
-#endif
 
-static inline ssize_t
-xfs_vm_do_dio(
-	struct inode		*inode,
+STATIC ssize_t
+xfs_vm_direct_IO(
 	struct kiocb		*iocb,
 	struct iov_iter		*iter,
-	loff_t			offset,
-	void			(*endio)(struct kiocb	*iocb,
-					 loff_t		offset,
-					 ssize_t	size,
-					 void		*private),
-	int			flags)
+	loff_t			offset)
 {
+	struct inode		*inode = iocb->ki_filp->f_mapping->host;
+	dio_iodone_t		*endio = NULL;
+	int			flags = 0;
 	struct block_device	*bdev;
 
-	if (IS_DAX(inode))
+	if (iov_iter_rw(iter) == WRITE) {
+		endio = xfs_end_io_direct_write;
+		flags = DIO_ASYNC_EXTEND;
+	}
+
+	if (IS_DAX(inode)) {
 		return dax_do_io(iocb, inode, iter, offset,
 				 xfs_get_blocks_direct, endio, 0);
+	}
 
 	bdev = xfs_find_bdev_for_inode(inode);
 	return  __blockdev_direct_IO(iocb, inode, bdev, iter, offset,
-				     xfs_get_blocks_direct, endio, NULL, flags);
-}
-
-STATIC ssize_t
-xfs_vm_direct_IO(
-	struct kiocb		*iocb,
-	struct iov_iter		*iter,
-	loff_t			offset)
-{
-	struct inode		*inode = iocb->ki_filp->f_mapping->host;
-
-	if (iov_iter_rw(iter) == WRITE)
-		return xfs_vm_do_dio(inode, iocb, iter, offset,
-				     xfs_end_io_direct_write, DIO_ASYNC_EXTEND);
-	return xfs_vm_do_dio(inode, iocb, iter, offset, NULL, 0);
+			xfs_get_blocks_direct, endio, NULL, flags);
 }
 
 /*
@@ -1736,9 +1475,10 @@ xfs_vm_write_failed(
 	loff_t			block_offset;
 	loff_t			block_start;
 	loff_t			block_end;
-	loff_t			from = pos & (PAGE_CACHE_SIZE - 1);
+	loff_t			from = pos & (PAGE_SIZE - 1);
 	loff_t			to = from + len;
 	struct buffer_head	*bh, *head;
+	struct xfs_mount	*mp = XFS_I(inode)->i_mount;
 
 	/*
 	 * The request pos offset might be 32 or 64 bit, this is all fine
@@ -1751,7 +1491,7 @@ xfs_vm_write_failed(
 	 * start of the page by using shifts rather than masks the mismatch
 	 * problem.
 	 */
-	block_offset = (pos >> PAGE_CACHE_SHIFT) << PAGE_CACHE_SHIFT;
+	block_offset = (pos >> PAGE_SHIFT) << PAGE_SHIFT;
 
 	ASSERT(block_offset + from == pos);
 
@@ -1770,14 +1510,23 @@ xfs_vm_write_failed(
 		if (block_start >= to)
 			break;
 
-		if (!buffer_delay(bh))
+		/*
+		 * Process delalloc and unwritten buffers beyond EOF. We can
+		 * encounter unwritten buffers in the event that a file has
+		 * post-EOF unwritten extents and an extending write happens to
+		 * fail (e.g., an unaligned write that also involves a delalloc
+		 * to the same page).
+		 */
+		if (!buffer_delay(bh) && !buffer_unwritten(bh))
 			continue;
 
-		if (!buffer_new(bh) && block_offset < i_size_read(inode))
+		if (!xfs_mp_fail_writes(mp) && !buffer_new(bh) &&
+		    block_offset < i_size_read(inode))
 			continue;
 
-		xfs_vm_kill_delalloc_range(inode, block_offset,
-					   block_offset + bh->b_size);
+		if (buffer_delay(bh))
+			xfs_vm_kill_delalloc_range(inode, block_offset,
+						   block_offset + bh->b_size);
 
 		/*
 		 * This buffer does not contain data anymore. make sure anyone
@@ -1788,6 +1537,7 @@ xfs_vm_write_failed(
 		clear_buffer_mapped(bh);
 		clear_buffer_new(bh);
 		clear_buffer_dirty(bh);
+		clear_buffer_unwritten(bh);
 	}
 
 }
@@ -1808,17 +1558,20 @@ xfs_vm_write_begin(
 	struct page		**pagep,
 	void			**fsdata)
 {
-	pgoff_t			index = pos >> PAGE_CACHE_SHIFT;
+	pgoff_t			index = pos >> PAGE_SHIFT;
 	struct page		*page;
 	int			status;
+	struct xfs_mount	*mp = XFS_I(mapping->host)->i_mount;
 
-	ASSERT(len <= PAGE_CACHE_SIZE);
+	ASSERT(len <= PAGE_SIZE);
 
 	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
 		return -ENOMEM;
 
 	status = __block_write_begin(page, pos, len, xfs_get_blocks);
+	if (xfs_mp_fail_writes(mp))
+		status = -EIO;
 	if (unlikely(status)) {
 		struct inode	*inode = mapping->host;
 		size_t		isize = i_size_read(inode);
@@ -1831,13 +1584,15 @@ xfs_vm_write_begin(
 		 * allocated in this write, not blocks that were previously
 		 * written successfully.
 		 */
+		if (xfs_mp_fail_writes(mp))
+			isize = 0;
 		if (pos + len > isize) {
 			ssize_t start = max_t(ssize_t, pos, isize);
 
 			truncate_pagecache_range(inode, start, pos + len);
 		}
 
-		page_cache_release(page);
+		put_page(page);
 		page = NULL;
 	}
 
@@ -1865,7 +1620,7 @@ xfs_vm_write_end(
 {
 	int			ret;
 
-	ASSERT(len <= PAGE_CACHE_SIZE);
+	ASSERT(len <= PAGE_SIZE);
 
 	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
 	if (unlikely(ret < len)) {
@@ -1904,6 +1659,7 @@ xfs_vm_readpage(
 	struct file		*unused,
 	struct page		*page)
 {
+	trace_xfs_vm_readpage(page->mapping->host, 1);
 	return mpage_readpage(page, xfs_get_blocks);
 }
 
@@ -1914,6 +1670,7 @@ xfs_vm_readpages(
 	struct list_head	*pages,
 	unsigned		nr_pages)
 {
+	trace_xfs_vm_readpages(mapping->host, nr_pages);
 	return mpage_readpages(mapping, pages, nr_pages, xfs_get_blocks);
 }
 
@@ -1938,7 +1695,6 @@ xfs_vm_set_page_dirty(
 	loff_t			end_offset;
 	loff_t			offset;
 	int			newly_dirty;
-	struct mem_cgroup	*memcg;
 
 	if (unlikely(!mapping))
 		return !TestSetPageDirty(page);
@@ -1959,10 +1715,10 @@ xfs_vm_set_page_dirty(
 		} while (bh != head);
 	}
 	/*
-	 * Use mem_group_begin_page_stat() to keep PageDirty synchronized with
-	 * per-memcg dirty page counters.
+	 * Lock out page->mem_cgroup migration to keep PageDirty
+	 * synchronized with per-memcg dirty page counters.
 	 */
-	memcg = mem_cgroup_begin_page_stat(page);
+	lock_page_memcg(page);
 	newly_dirty = !TestSetPageDirty(page);
 	spin_unlock(&mapping->private_lock);
 
@@ -1973,13 +1729,13 @@ xfs_vm_set_page_dirty(
 		spin_lock_irqsave(&mapping->tree_lock, flags);
 		if (page->mapping) {	/* Race with truncate? */
 			WARN_ON_ONCE(!PageUptodate(page));
-			account_page_dirtied(page, mapping, memcg);
+			account_page_dirtied(page, mapping);
 			radix_tree_tag_set(&mapping->page_tree,
 					page_index(page), PAGECACHE_TAG_DIRTY);
 		}
 		spin_unlock_irqrestore(&mapping->tree_lock, flags);
 	}
-	mem_cgroup_end_page_stat(memcg);
+	unlock_page_memcg(page);
 	if (newly_dirty)
 		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 	return newly_dirty;
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index 86afd1ac7895..b4421177b68d 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -24,12 +24,14 @@ extern mempool_t *xfs_ioend_pool;
  * Types of I/O for bmap clustering and I/O completion tracking.
  */
 enum {
+	XFS_IO_INVALID,		/* initial state */
 	XFS_IO_DELALLOC,	/* covers delalloc region */
 	XFS_IO_UNWRITTEN,	/* covers allocated but uninitialized data */
 	XFS_IO_OVERWRITE,	/* covers already allocated extent */
 };
 
 #define XFS_IO_TYPES \
+	{ XFS_IO_INVALID,		"invalid" }, \
 	{ XFS_IO_DELALLOC,		"delalloc" }, \
 	{ XFS_IO_UNWRITTEN,		"unwritten" }, \
 	{ XFS_IO_OVERWRITE,		"overwrite" }
@@ -39,7 +41,7 @@ enum {
  * It can manage several multi-page bio's at once.
  */
 typedef struct xfs_ioend {
-	struct xfs_ioend	*io_list;	/* next ioend in chain */
+	struct list_head	io_list;	/* next ioend in chain */
 	unsigned int		io_type;	/* delalloc / unwritten */
 	int			io_error;	/* I/O error code */
 	atomic_t		io_remaining;	/* hold count */
@@ -58,8 +60,10 @@ int	xfs_get_blocks(struct inode *inode, sector_t offset,
 		       struct buffer_head *map_bh, int create);
 int	xfs_get_blocks_direct(struct inode *inode, sector_t offset,
 			      struct buffer_head *map_bh, int create);
-void	xfs_end_io_dax_write(struct buffer_head *bh, int uptodate);
+int	xfs_get_blocks_dax_fault(struct inode *inode, sector_t offset,
+			         struct buffer_head *map_bh, int create);
 
 extern void xfs_count_page_state(struct page *, int *, int *);
+extern struct block_device *xfs_find_bdev_for_inode(struct inode *);
 
 #endif /* __XFS_AOPS_H__ */
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index 65fb37a18e92..4fa14820e2e2 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -202,8 +202,10 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context)
 					sbp->namelen,
 					sbp->valuelen,
 					&sbp->name[sbp->namelen]);
-		if (error)
+		if (error) {
+			kmem_free(sbuf);
 			return error;
+		}
 		if (context->seen_enough)
 			break;
 		cursor->offset++;
@@ -454,14 +456,13 @@ xfs_attr3_leaf_list_int(
 				args.rmtblkcnt = xfs_attr3_rmt_blocks(
 							args.dp->i_mount, valuelen);
 				retval = xfs_attr_rmtval_get(&args);
-				if (retval)
-					return retval;
-				retval = context->put_listent(context,
-						entry->flags,
-						name_rmt->name,
-						(int)name_rmt->namelen,
-						valuelen,
-						args.value);
+				if (!retval)
+					retval = context->put_listent(context,
+							entry->flags,
+							name_rmt->name,
+							(int)name_rmt->namelen,
+							valuelen,
+							args.value);
 				kmem_free(args.value);
 			} else {
 				retval = context->put_listent(context,
@@ -511,7 +512,7 @@ xfs_attr_list_int(
 	xfs_inode_t *dp = context->dp;
 	uint		lock_mode;
 
-	XFS_STATS_INC(xs_attr_list);
+	XFS_STATS_INC(dp->i_mount, xs_attr_list);
 
 	if (XFS_FORCED_SHUTDOWN(dp->i_mount))
 		return -EIO;
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 3bf4ad0d19e4..3b6309865c65 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -57,37 +57,67 @@ xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb)
 }
 
 /*
+ * Routine to zero an extent on disk allocated to the specific inode.
+ *
+ * The VFS functions take a linearised filesystem block offset, so we have to
+ * convert the sparse xfs fsb to the right format first.
+ * VFS types are real funky, too.
+ */
+int
+xfs_zero_extent(
+	struct xfs_inode *ip,
+	xfs_fsblock_t	start_fsb,
+	xfs_off_t	count_fsb)
+{
+	struct xfs_mount *mp = ip->i_mount;
+	xfs_daddr_t	sector = xfs_fsb_to_db(ip, start_fsb);
+	sector_t	block = XFS_BB_TO_FSBT(mp, sector);
+	ssize_t		size = XFS_FSB_TO_B(mp, count_fsb);
+
+	if (IS_DAX(VFS_I(ip)))
+		return dax_clear_sectors(xfs_find_bdev_for_inode(VFS_I(ip)),
+				sector, size);
+
+	/*
+	 * let the block layer decide on the fastest method of
+	 * implementing the zeroing.
+	 */
+	return sb_issue_zeroout(mp->m_super, block, count_fsb, GFP_NOFS);
+
+}
+
+/*
  * Routine to be called at transaction's end by xfs_bmapi, xfs_bunmapi
  * caller.  Frees all the extents that need freeing, which must be done
  * last due to locking considerations.  We never free any extents in
  * the first transaction.
  *
- * Return 1 if the given transaction was committed and a new one
- * started, and 0 otherwise in the committed parameter.
+ * If an inode *ip is provided, rejoin it to the transaction if
+ * the transaction was committed.
  */
 int						/* error */
 xfs_bmap_finish(
 	struct xfs_trans		**tp,	/* transaction pointer addr */
 	struct xfs_bmap_free		*flist,	/* i/o: list extents to free */
-	int				*committed)/* xact committed or not */
+	struct xfs_inode		*ip)
 {
 	struct xfs_efd_log_item		*efd;	/* extent free data */
 	struct xfs_efi_log_item		*efi;	/* extent free intention */
 	int				error;	/* error return value */
+	int				committed;/* xact committed or not */
 	struct xfs_bmap_free_item	*free;	/* free extent item */
 	struct xfs_bmap_free_item	*next;	/* next item on free list */
 
 	ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
-	if (flist->xbf_count == 0) {
-		*committed = 0;
+	if (flist->xbf_count == 0)
 		return 0;
-	}
+
 	efi = xfs_trans_get_efi(*tp, flist->xbf_count);
 	for (free = flist->xbf_first; free; free = free->xbfi_next)
 		xfs_trans_log_efi_extent(*tp, efi, free->xbfi_startblock,
 			free->xbfi_blockcount);
 
-	error = __xfs_trans_roll(tp, NULL, committed);
+	error = __xfs_trans_roll(tp, ip, &committed);
 	if (error) {
 		/*
 		 * If the transaction was committed, drop the EFD reference
@@ -99,16 +129,13 @@ xfs_bmap_finish(
 		 * transaction so we should return committed=1 even though we're
 		 * returning an error.
 		 */
-		if (*committed) {
+		if (committed) {
 			xfs_efi_release(efi);
 			xfs_force_shutdown((*tp)->t_mountp,
 				(error == -EFSCORRUPTED) ?
 					SHUTDOWN_CORRUPT_INCORE :
 					SHUTDOWN_META_IO_ERROR);
-		} else {
-			*committed = 1;
 		}
-
 		return error;
 	}
 
@@ -176,10 +203,12 @@ xfs_bmap_rtalloc(
 		ralen = MAXEXTLEN / mp->m_sb.sb_rextsize;
 
 	/*
-	 * Lock out other modifications to the RT bitmap inode.
+	 * Lock out modifications to both the RT bitmap and summary inodes
 	 */
 	xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(ap->tp, mp->m_rbmip, XFS_ILOCK_EXCL);
+	xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(ap->tp, mp->m_rsumip, XFS_ILOCK_EXCL);
 
 	/*
 	 * If it's an allocation to an empty file at offset 0,
@@ -229,6 +258,13 @@ xfs_bmap_rtalloc(
 		xfs_trans_mod_dquot_byino(ap->tp, ap->ip,
 			ap->wasdel ? XFS_TRANS_DQ_DELRTBCOUNT :
 					XFS_TRANS_DQ_RTBCOUNT, (long) ralen);
+
+		/* Zero the extent if we were asked to do so */
+		if (ap->userdata & XFS_ALLOC_USERDATA_ZERO) {
+			error = xfs_zero_extent(ap->ip, ap->blkno, ap->length);
+			if (error)
+				return error;
+		}
 	} else {
 		ap->length = 0;
 	}
@@ -788,7 +824,7 @@ bool
 xfs_can_free_eofblocks(struct xfs_inode *ip, bool force)
 {
 	/* prealloc/delalloc exists only on regular files */
-	if (!S_ISREG(ip->i_d.di_mode))
+	if (!S_ISREG(VFS_I(ip)->i_mode))
 		return false;
 
 	/*
@@ -933,7 +969,6 @@ xfs_alloc_file_space(
 	xfs_bmbt_irec_t		imaps[1], *imapp;
 	xfs_bmap_free_t		free_list;
 	uint			qblocks, resblks, resrtextents;
-	int			committed;
 	int			error;
 
 	trace_xfs_alloc_file_space(ip);
@@ -1027,24 +1062,21 @@ xfs_alloc_file_space(
 		xfs_bmap_init(&free_list, &firstfsb);
 		error = xfs_bmapi_write(tp, ip, startoffset_fsb,
 					allocatesize_fsb, alloc_type, &firstfsb,
-					0, imapp, &nimaps, &free_list);
-		if (error) {
+					resblks, imapp, &nimaps, &free_list);
+		if (error)
 			goto error0;
-		}
 
 		/*
 		 * Complete the transaction
 		 */
-		error = xfs_bmap_finish(&tp, &free_list, &committed);
-		if (error) {
+		error = xfs_bmap_finish(&tp, &free_list, NULL);
+		if (error)
 			goto error0;
-		}
 
 		error = xfs_trans_commit(tp);
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		if (error) {
+		if (error)
 			break;
-		}
 
 		allocated_fsb = imapp->br_blockcount;
 
@@ -1170,7 +1202,6 @@ xfs_free_file_space(
 	xfs_off_t		offset,
 	xfs_off_t		len)
 {
-	int			committed;
 	int			done;
 	xfs_fileoff_t		endoffset_fsb;
 	int			error;
@@ -1206,7 +1237,7 @@ xfs_free_file_space(
 	/* wait for the completion of any pending DIOs */
 	inode_dio_wait(VFS_I(ip));
 
-	rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE);
+	rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_SIZE);
 	ioffset = round_down(offset, rounding);
 	iendoffset = round_up(offset + len, rounding) - 1;
 	error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping, ioffset,
@@ -1310,17 +1341,15 @@ xfs_free_file_space(
 		error = xfs_bunmapi(tp, ip, startoffset_fsb,
 				  endoffset_fsb - startoffset_fsb,
 				  0, 2, &firstfsb, &free_list, &done);
-		if (error) {
+		if (error)
 			goto error0;
-		}
 
 		/*
 		 * complete the transaction
 		 */
-		error = xfs_bmap_finish(&tp, &free_list, &committed);
-		if (error) {
+		error = xfs_bmap_finish(&tp, &free_list, NULL);
+		if (error)
 			goto error0;
-		}
 
 		error = xfs_trans_commit(tp);
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -1398,7 +1427,6 @@ xfs_shift_file_space(
 	int			error;
 	struct xfs_bmap_free	free_list;
 	xfs_fsblock_t		first_block;
-	int			committed;
 	xfs_fileoff_t		stop_fsb;
 	xfs_fileoff_t		next_fsb;
 	xfs_fileoff_t		shift_fsb;
@@ -1438,7 +1466,7 @@ xfs_shift_file_space(
 	if (error)
 		return error;
 	error = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping,
-					offset >> PAGE_CACHE_SHIFT, -1);
+					offset >> PAGE_SHIFT, -1);
 	if (error)
 		return error;
 
@@ -1490,7 +1518,7 @@ xfs_shift_file_space(
 		if (error)
 			goto out_bmap_cancel;
 
-		error = xfs_bmap_finish(&tp, &free_list, &committed);
+		error = xfs_bmap_finish(&tp, &free_list, NULL);
 		if (error)
 			goto out_bmap_cancel;
 
@@ -1701,7 +1729,7 @@ xfs_swap_extents(
 	xfs_lock_two_inodes(ip, tip, XFS_MMAPLOCK_EXCL);
 
 	/* Verify that both files have the same format */
-	if ((ip->i_d.di_mode & S_IFMT) != (tip->i_d.di_mode & S_IFMT)) {
+	if ((VFS_I(ip)->i_mode & S_IFMT) != (VFS_I(tip)->i_mode & S_IFMT)) {
 		error = -EINVAL;
 		goto out_unlock;
 	}
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 8ecffb35935b..9a2191b91137 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -201,7 +201,7 @@ _xfs_buf_alloc(
 	atomic_set(&bp->b_pin_count, 0);
 	init_waitqueue_head(&bp->b_waiters);
 
-	XFS_STATS_INC(xb_create);
+	XFS_STATS_INC(target->bt_mount, xb_create);
 	trace_xfs_buf_init(bp, _RET_IP_);
 
 	return bp;
@@ -354,15 +354,16 @@ retry:
 			 */
 			if (!(++retries % 100))
 				xfs_err(NULL,
-		"possible memory allocation deadlock in %s (mode:0x%x)",
+		"%s(%u) possible memory allocation deadlock in %s (mode:0x%x)",
+					current->comm, current->pid,
 					__func__, gfp_mask);
 
-			XFS_STATS_INC(xb_page_retries);
+			XFS_STATS_INC(bp->b_target->bt_mount, xb_page_retries);
 			congestion_wait(BLK_RW_ASYNC, HZ/50);
 			goto retry;
 		}
 
-		XFS_STATS_INC(xb_page_found);
+		XFS_STATS_INC(bp->b_target->bt_mount, xb_page_found);
 
 		nbytes = min_t(size_t, size, PAGE_SIZE - offset);
 		size -= nbytes;
@@ -516,7 +517,7 @@ _xfs_buf_find(
 		new_bp->b_pag = pag;
 		spin_unlock(&pag->pag_buf_lock);
 	} else {
-		XFS_STATS_INC(xb_miss_locked);
+		XFS_STATS_INC(btp->bt_mount, xb_miss_locked);
 		spin_unlock(&pag->pag_buf_lock);
 		xfs_perag_put(pag);
 	}
@@ -529,11 +530,11 @@ found:
 	if (!xfs_buf_trylock(bp)) {
 		if (flags & XBF_TRYLOCK) {
 			xfs_buf_rele(bp);
-			XFS_STATS_INC(xb_busy_locked);
+			XFS_STATS_INC(btp->bt_mount, xb_busy_locked);
 			return NULL;
 		}
 		xfs_buf_lock(bp);
-		XFS_STATS_INC(xb_get_locked_waited);
+		XFS_STATS_INC(btp->bt_mount, xb_get_locked_waited);
 	}
 
 	/*
@@ -549,7 +550,7 @@ found:
 	}
 
 	trace_xfs_buf_find(bp, flags, _RET_IP_);
-	XFS_STATS_INC(xb_get_locked);
+	XFS_STATS_INC(btp->bt_mount, xb_get_locked);
 	return bp;
 }
 
@@ -603,7 +604,14 @@ found:
 		}
 	}
 
-	XFS_STATS_INC(xb_get);
+	/*
+	 * Clear b_error if this is a lookup from a caller that doesn't expect
+	 * valid data to be found in the buffer.
+	 */
+	if (!(flags & XBF_READ))
+		xfs_buf_ioerror(bp, 0);
+
+	XFS_STATS_INC(target->bt_mount, xb_get);
 	trace_xfs_buf_get(bp, flags, _RET_IP_);
 	return bp;
 }
@@ -642,8 +650,8 @@ xfs_buf_read_map(
 	if (bp) {
 		trace_xfs_buf_read(bp, flags, _RET_IP_);
 
-		if (!XFS_BUF_ISDONE(bp)) {
-			XFS_STATS_INC(xb_get_read);
+		if (!(bp->b_flags & XBF_DONE)) {
+			XFS_STATS_INC(target->bt_mount, xb_get_read);
 			bp->b_ops = ops;
 			_xfs_buf_read(bp, flags);
 		} else if (flags & XBF_ASYNC) {
@@ -1044,7 +1052,7 @@ xfs_buf_ioend_work(
 	xfs_buf_ioend(bp);
 }
 
-void
+static void
 xfs_buf_ioend_async(
 	struct xfs_buf	*bp)
 {
@@ -1519,6 +1527,16 @@ xfs_wait_buftarg(
 	LIST_HEAD(dispose);
 	int loop = 0;
 
+	/*
+	 * We need to flush the buffer workqueue to ensure that all IO
+	 * completion processing is 100% done. Just waiting on buffer locks is
+	 * not sufficient for async IO as the reference count held over IO is
+	 * not released until after the buffer lock is dropped. Hence we need to
+	 * ensure here that all reference counts have been dropped before we
+	 * start walking the LRU list.
+	 */
+	drain_workqueue(btp->bt_mount->m_buf_workqueue);
+
 	/* loop until there is nothing left on the lru list. */
 	while (list_lru_count(&btp->bt_lru)) {
 		list_lru_walk(&btp->bt_lru, xfs_buftarg_wait_rele,
@@ -1631,13 +1649,9 @@ xfs_setsize_buftarg(
 	btp->bt_meta_sectormask = sectorsize - 1;
 
 	if (set_blocksize(btp->bt_bdev, sectorsize)) {
-		char name[BDEVNAME_SIZE];
-
-		bdevname(btp->bt_bdev, name);
-
 		xfs_warn(btp->bt_mount,
-			"Cannot set_blocksize to %u on device %s",
-			sectorsize, name);
+			"Cannot set_blocksize to %u on device %pg",
+			sectorsize, btp->bt_bdev);
 		return -EINVAL;
 	}
 
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index c79b717d9b88..4eb89bd4ee73 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -132,6 +132,7 @@ struct xfs_buf_map {
 	struct xfs_buf_map (map) = { .bm_bn = (blkno), .bm_len = (numblk) };
 
 struct xfs_buf_ops {
+	char *name;
 	void (*verify_read)(struct xfs_buf *);
 	void (*verify_write)(struct xfs_buf *);
 };
@@ -301,6 +302,7 @@ extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *,
 
 /* Buffer Utility Routines */
 extern void *xfs_buf_offset(struct xfs_buf *, size_t);
+extern void xfs_buf_stale(struct xfs_buf *bp);
 
 /* Delayed Write Buffer Routines */
 extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *);
@@ -311,31 +313,6 @@ extern int xfs_buf_delwri_submit_nowait(struct list_head *);
 extern int xfs_buf_init(void);
 extern void xfs_buf_terminate(void);
 
-#define XFS_BUF_ZEROFLAGS(bp) \
-	((bp)->b_flags &= ~(XBF_READ|XBF_WRITE|XBF_ASYNC| \
-			    XBF_SYNCIO|XBF_FUA|XBF_FLUSH| \
-			    XBF_WRITE_FAIL))
-
-void xfs_buf_stale(struct xfs_buf *bp);
-#define XFS_BUF_UNSTALE(bp)	((bp)->b_flags &= ~XBF_STALE)
-#define XFS_BUF_ISSTALE(bp)	((bp)->b_flags & XBF_STALE)
-
-#define XFS_BUF_DONE(bp)	((bp)->b_flags |= XBF_DONE)
-#define XFS_BUF_UNDONE(bp)	((bp)->b_flags &= ~XBF_DONE)
-#define XFS_BUF_ISDONE(bp)	((bp)->b_flags & XBF_DONE)
-
-#define XFS_BUF_ASYNC(bp)	((bp)->b_flags |= XBF_ASYNC)
-#define XFS_BUF_UNASYNC(bp)	((bp)->b_flags &= ~XBF_ASYNC)
-#define XFS_BUF_ISASYNC(bp)	((bp)->b_flags & XBF_ASYNC)
-
-#define XFS_BUF_READ(bp)	((bp)->b_flags |= XBF_READ)
-#define XFS_BUF_UNREAD(bp)	((bp)->b_flags &= ~XBF_READ)
-#define XFS_BUF_ISREAD(bp)	((bp)->b_flags & XBF_READ)
-
-#define XFS_BUF_WRITE(bp)	((bp)->b_flags |= XBF_WRITE)
-#define XFS_BUF_UNWRITE(bp)	((bp)->b_flags &= ~XBF_WRITE)
-#define XFS_BUF_ISWRITE(bp)	((bp)->b_flags & XBF_WRITE)
-
 /*
  * These macros use the IO block map rather than b_bn. b_bn is now really
  * just for the buffer cache index for cached buffers. As IO does not use b_bn
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 7e986da34f6c..99e91a0e554e 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -431,7 +431,7 @@ xfs_buf_item_unpin(
 	if (freed && stale) {
 		ASSERT(bip->bli_flags & XFS_BLI_STALE);
 		ASSERT(xfs_buf_islocked(bp));
-		ASSERT(XFS_BUF_ISSTALE(bp));
+		ASSERT(bp->b_flags & XBF_STALE);
 		ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
 
 		trace_xfs_buf_item_unpin_stale(bip);
@@ -493,7 +493,7 @@ xfs_buf_item_unpin(
 		xfs_buf_hold(bp);
 		bp->b_flags |= XBF_ASYNC;
 		xfs_buf_ioerror(bp, -EIO);
-		XFS_BUF_UNDONE(bp);
+		bp->b_flags &= ~XBF_DONE;
 		xfs_buf_stale(bp);
 		xfs_buf_ioend(bp);
 	}
@@ -1067,7 +1067,7 @@ xfs_buf_iodone_callbacks(
 	 */
 	if (XFS_FORCED_SHUTDOWN(mp)) {
 		xfs_buf_stale(bp);
-		XFS_BUF_DONE(bp);
+		bp->b_flags |= XBF_DONE;
 		trace_xfs_buf_item_iodone(bp, _RET_IP_);
 		goto do_callbacks;
 	}
@@ -1090,7 +1090,7 @@ xfs_buf_iodone_callbacks(
 	 * errors tend to affect the whole device and a failing log write
 	 * will make us give up.  But we really ought to do better here.
 	 */
-	if (XFS_BUF_ISASYNC(bp)) {
+	if (bp->b_flags & XBF_ASYNC) {
 		ASSERT(bp->b_iodone != NULL);
 
 		trace_xfs_buf_item_iodone_async(bp, _RET_IP_);
@@ -1113,7 +1113,7 @@ xfs_buf_iodone_callbacks(
 	 * sure to return the error to the caller of xfs_bwrite().
 	 */
 	xfs_buf_stale(bp);
-	XFS_BUF_DONE(bp);
+	bp->b_flags |= XBF_DONE;
 
 	trace_xfs_buf_error_relse(bp, _RET_IP_);
 
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index a989a9c7edb7..93b3ab0c5435 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -665,8 +665,8 @@ xfs_readdir(
 	if (XFS_FORCED_SHUTDOWN(dp->i_mount))
 		return -EIO;
 
-	ASSERT(S_ISDIR(dp->i_d.di_mode));
-	XFS_STATS_INC(xs_dir_getdents);
+	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
+	XFS_STATS_INC(dp->i_mount, xs_dir_getdents);
 
 	args.dp = dp;
 	args.geo = dp->i_mount->m_dir_geo;
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index e85a9519a5ae..272c3f8b6f7d 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -227,7 +227,7 @@ xfs_discard_extents(
 				GFP_NOFS, 0);
 		if (error && error != -EOPNOTSUPP) {
 			xfs_info(mp,
-	 "discard failed for extent [0x%llu,%u], error %d",
+	 "discard failed for extent [0x%llx,%u], error %d",
 				 (unsigned long long)busyp->bno,
 				 busyp->length,
 				 error);
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 30cb3afb67f0..316b2a1bdba5 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -75,9 +75,9 @@ xfs_qm_dqdestroy(
 	ASSERT(list_empty(&dqp->q_lru));
 
 	mutex_destroy(&dqp->q_qlock);
-	kmem_zone_free(xfs_qm_dqzone, dqp);
 
-	XFS_STATS_DEC(xs_qm_dquot);
+	XFS_STATS_DEC(dqp->q_mount, xs_qm_dquot);
+	kmem_zone_free(xfs_qm_dqzone, dqp);
 }
 
 /*
@@ -92,26 +92,28 @@ xfs_qm_adjust_dqlimits(
 {
 	struct xfs_quotainfo	*q = mp->m_quotainfo;
 	struct xfs_disk_dquot	*d = &dq->q_core;
+	struct xfs_def_quota	*defq;
 	int			prealloc = 0;
 
 	ASSERT(d->d_id);
+	defq = xfs_get_defquota(dq, q);
 
-	if (q->qi_bsoftlimit && !d->d_blk_softlimit) {
-		d->d_blk_softlimit = cpu_to_be64(q->qi_bsoftlimit);
+	if (defq->bsoftlimit && !d->d_blk_softlimit) {
+		d->d_blk_softlimit = cpu_to_be64(defq->bsoftlimit);
 		prealloc = 1;
 	}
-	if (q->qi_bhardlimit && !d->d_blk_hardlimit) {
-		d->d_blk_hardlimit = cpu_to_be64(q->qi_bhardlimit);
+	if (defq->bhardlimit && !d->d_blk_hardlimit) {
+		d->d_blk_hardlimit = cpu_to_be64(defq->bhardlimit);
 		prealloc = 1;
 	}
-	if (q->qi_isoftlimit && !d->d_ino_softlimit)
-		d->d_ino_softlimit = cpu_to_be64(q->qi_isoftlimit);
-	if (q->qi_ihardlimit && !d->d_ino_hardlimit)
-		d->d_ino_hardlimit = cpu_to_be64(q->qi_ihardlimit);
-	if (q->qi_rtbsoftlimit && !d->d_rtb_softlimit)
-		d->d_rtb_softlimit = cpu_to_be64(q->qi_rtbsoftlimit);
-	if (q->qi_rtbhardlimit && !d->d_rtb_hardlimit)
-		d->d_rtb_hardlimit = cpu_to_be64(q->qi_rtbhardlimit);
+	if (defq->isoftlimit && !d->d_ino_softlimit)
+		d->d_ino_softlimit = cpu_to_be64(defq->isoftlimit);
+	if (defq->ihardlimit && !d->d_ino_hardlimit)
+		d->d_ino_hardlimit = cpu_to_be64(defq->ihardlimit);
+	if (defq->rtbsoftlimit && !d->d_rtb_softlimit)
+		d->d_rtb_softlimit = cpu_to_be64(defq->rtbsoftlimit);
+	if (defq->rtbhardlimit && !d->d_rtb_hardlimit)
+		d->d_rtb_hardlimit = cpu_to_be64(defq->rtbhardlimit);
 
 	if (prealloc)
 		xfs_dquot_set_prealloc_limits(dq);
@@ -232,7 +234,8 @@ xfs_qm_init_dquot_blk(
 {
 	struct xfs_quotainfo	*q = mp->m_quotainfo;
 	xfs_dqblk_t	*d;
-	int		curid, i;
+	xfs_dqid_t	curid;
+	int		i;
 
 	ASSERT(tp);
 	ASSERT(xfs_buf_islocked(bp));
@@ -243,7 +246,6 @@ xfs_qm_init_dquot_blk(
 	 * ID of the first dquot in the block - id's are zero based.
 	 */
 	curid = id - (id % q->qi_dqperchunk);
-	ASSERT(curid >= 0);
 	memset(d, 0, BBTOB(q->qi_dqchunklen));
 	for (i = 0; i < q->qi_dqperchunk; i++, d++, curid++) {
 		d->dd_diskdq.d_magic = cpu_to_be16(XFS_DQUOT_MAGIC);
@@ -306,7 +308,7 @@ xfs_qm_dqalloc(
 	xfs_fsblock_t	firstblock;
 	xfs_bmap_free_t flist;
 	xfs_bmbt_irec_t map;
-	int		nmaps, error, committed;
+	int		nmaps, error;
 	xfs_buf_t	*bp;
 	xfs_trans_t	*tp = *tpp;
 
@@ -379,11 +381,12 @@ xfs_qm_dqalloc(
 
 	xfs_trans_bhold(tp, bp);
 
-	if ((error = xfs_bmap_finish(tpp, &flist, &committed))) {
+	error = xfs_bmap_finish(tpp, &flist, NULL);
+	if (error)
 		goto error1;
-	}
 
-	if (committed) {
+	/* Transaction was committed? */
+	if (*tpp != tp) {
 		tp = *tpp;
 		xfs_trans_bjoin(tp, bp);
 	} else {
@@ -393,9 +396,9 @@ xfs_qm_dqalloc(
 	*O_bpp = bp;
 	return 0;
 
-      error1:
+error1:
 	xfs_bmap_cancel(&flist);
-      error0:
+error0:
 	xfs_iunlock(quotip, XFS_ILOCK_EXCL);
 
 	return error;
@@ -463,12 +466,13 @@ xfs_qm_dqtobp(
 	struct xfs_bmbt_irec	map;
 	int			nmaps = 1, error;
 	struct xfs_buf		*bp;
-	struct xfs_inode	*quotip = xfs_dq_to_quota_inode(dqp);
+	struct xfs_inode	*quotip;
 	struct xfs_mount	*mp = dqp->q_mount;
 	xfs_dqid_t		id = be32_to_cpu(dqp->q_core.d_id);
 	struct xfs_trans	*tp = (tpp ? *tpp : NULL);
 	uint			lock_mode;
 
+	quotip = xfs_quota_inode(dqp->q_mount, dqp->dq_flags);
 	dqp->q_fileoffset = (xfs_fileoff_t)id / mp->m_quotainfo->qi_dqperchunk;
 
 	lock_mode = xfs_ilock_data_map_shared(quotip);
@@ -605,7 +609,7 @@ xfs_qm_dqread(
 		break;
 	}
 
-	XFS_STATS_INC(xs_qm_dquot);
+	XFS_STATS_INC(mp, xs_qm_dquot);
 
 	trace_xfs_dqread(dqp);
 
@@ -684,6 +688,56 @@ error0:
 }
 
 /*
+ * Advance to the next id in the current chunk, or if at the
+ * end of the chunk, skip ahead to first id in next allocated chunk
+ * using the SEEK_DATA interface.
+ */
+int
+xfs_dq_get_next_id(
+	xfs_mount_t		*mp,
+	uint			type,
+	xfs_dqid_t		*id,
+	loff_t			eof)
+{
+	struct xfs_inode	*quotip;
+	xfs_fsblock_t		start;
+	loff_t			offset;
+	uint			lock;
+	xfs_dqid_t		next_id;
+	int			error = 0;
+
+	/* Simple advance */
+	next_id = *id + 1;
+
+	/* If new ID is within the current chunk, advancing it sufficed */
+	if (next_id % mp->m_quotainfo->qi_dqperchunk) {
+		*id = next_id;
+		return 0;
+	}
+
+	/* Nope, next_id is now past the current chunk, so find the next one */
+	start = (xfs_fsblock_t)next_id / mp->m_quotainfo->qi_dqperchunk;
+
+	quotip = xfs_quota_inode(mp, type);
+	lock = xfs_ilock_data_map_shared(quotip);
+
+	offset = __xfs_seek_hole_data(VFS_I(quotip), XFS_FSB_TO_B(mp, start),
+				      eof, SEEK_DATA);
+	if (offset < 0)
+		error = offset;
+
+	xfs_iunlock(quotip, lock);
+
+	/* -ENXIO is essentially "no more data" */
+	if (error)
+		return (error == -ENXIO ? -ENOENT: error);
+
+	/* Convert next data offset back to a quota id */
+	*id = XFS_B_TO_FSB(mp, offset) * mp->m_quotainfo->qi_dqperchunk;
+	return 0;
+}
+
+/*
  * Given the file system, inode OR id, and type (UDQUOT/GDQUOT), return a
  * a locked dquot, doing an allocation (if requested) as needed.
  * When both an inode and an id are given, the inode's id takes precedence.
@@ -703,6 +757,7 @@ xfs_qm_dqget(
 	struct xfs_quotainfo	*qi = mp->m_quotainfo;
 	struct radix_tree_root *tree = xfs_dquot_tree(qi, type);
 	struct xfs_dquot	*dqp;
+	loff_t			eof = 0;
 	int			error;
 
 	ASSERT(XFS_IS_QUOTA_RUNNING(mp));
@@ -730,6 +785,21 @@ xfs_qm_dqget(
 	}
 #endif
 
+	/* Get the end of the quota file if we need it */
+	if (flags & XFS_QMOPT_DQNEXT) {
+		struct xfs_inode	*quotip;
+		xfs_fileoff_t		last;
+		uint			lock_mode;
+
+		quotip = xfs_quota_inode(mp, type);
+		lock_mode = xfs_ilock_data_map_shared(quotip);
+		error = xfs_bmap_last_offset(quotip, &last, XFS_DATA_FORK);
+		xfs_iunlock(quotip, lock_mode);
+		if (error)
+			return error;
+		eof = XFS_FSB_TO_B(mp, last);
+	}
+
 restart:
 	mutex_lock(&qi->qi_tree_lock);
 	dqp = radix_tree_lookup(tree, id);
@@ -743,16 +813,28 @@ restart:
 			goto restart;
 		}
 
+		/* uninit / unused quota found in radix tree, keep looking  */
+		if (flags & XFS_QMOPT_DQNEXT) {
+			if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) {
+				xfs_dqunlock(dqp);
+				mutex_unlock(&qi->qi_tree_lock);
+				error = xfs_dq_get_next_id(mp, type, &id, eof);
+				if (error)
+					return error;
+				goto restart;
+			}
+		}
+
 		dqp->q_nrefs++;
 		mutex_unlock(&qi->qi_tree_lock);
 
 		trace_xfs_dqget_hit(dqp);
-		XFS_STATS_INC(xs_qm_dqcachehits);
+		XFS_STATS_INC(mp, xs_qm_dqcachehits);
 		*O_dqpp = dqp;
 		return 0;
 	}
 	mutex_unlock(&qi->qi_tree_lock);
-	XFS_STATS_INC(xs_qm_dqcachemisses);
+	XFS_STATS_INC(mp, xs_qm_dqcachemisses);
 
 	/*
 	 * Dquot cache miss. We don't want to keep the inode lock across
@@ -769,6 +851,13 @@ restart:
 	if (ip)
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 
+	/* If we are asked to find next active id, keep looking */
+	if (error == -ENOENT && (flags & XFS_QMOPT_DQNEXT)) {
+		error = xfs_dq_get_next_id(mp, type, &id, eof);
+		if (!error)
+			goto restart;
+	}
+
 	if (error)
 		return error;
 
@@ -806,7 +895,7 @@ restart:
 		mutex_unlock(&qi->qi_tree_lock);
 		trace_xfs_dqget_dup(dqp);
 		xfs_qm_dqdestroy(dqp);
-		XFS_STATS_INC(xs_qm_dquot_dups);
+		XFS_STATS_INC(mp, xs_qm_dquot_dups);
 		goto restart;
 	}
 
@@ -819,6 +908,17 @@ restart:
 	qi->qi_dquots++;
 	mutex_unlock(&qi->qi_tree_lock);
 
+	/* If we are asked to find next active id, keep looking */
+	if (flags & XFS_QMOPT_DQNEXT) {
+		if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) {
+			xfs_qm_dqput(dqp);
+			error = xfs_dq_get_next_id(mp, type, &id, eof);
+			if (error)
+				return error;
+			goto restart;
+		}
+	}
+
  dqret:
 	ASSERT((ip == NULL) || xfs_isilocked(ip, XFS_ILOCK_EXCL));
 	trace_xfs_dqget_miss(dqp);
@@ -846,7 +946,7 @@ xfs_qm_dqput(
 		trace_xfs_dqput_free(dqp);
 
 		if (list_lru_add(&qi->qi_lru, &dqp->q_lru))
-			XFS_STATS_INC(xs_qm_dquot_unused);
+			XFS_STATS_INC(dqp->q_mount, xs_qm_dquot_unused);
 	}
 	xfs_dqunlock(dqp);
 }
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index 74d0e5966ebc..88693a98fac5 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -164,9 +164,9 @@ xfs_verifier_error(
 {
 	struct xfs_mount *mp = bp->b_target->bt_mount;
 
-	xfs_alert(mp, "Metadata %s detected at %pF, block 0x%llx",
+	xfs_alert(mp, "Metadata %s detected at %pF, %s block 0x%llx",
 		  bp->b_error == -EFSBADCRC ? "CRC error" : "corruption",
-		  __return_address, bp->b_bn);
+		  __return_address, bp->b_ops->name, bp->b_bn);
 
 	xfs_alert(mp, "Unmount and run xfs_repair");
 
diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c
index 652cd3c5b58c..a1b2dd828b9d 100644
--- a/fs/xfs/xfs_export.c
+++ b/fs/xfs/xfs_export.c
@@ -152,7 +152,7 @@ xfs_nfs_get_inode(
 		return ERR_PTR(error);
 	}
 
-	if (ip->i_d.di_gen != generation) {
+	if (VFS_I(ip)->i_generation != generation) {
 		IRELE(ip);
 		return ERR_PTR(-ESTALE);
 	}
@@ -246,7 +246,7 @@ const struct export_operations xfs_export_operations = {
 	.fh_to_parent		= xfs_fs_fh_to_parent,
 	.get_parent		= xfs_fs_get_parent,
 	.commit_metadata	= xfs_fs_nfs_commit_metadata,
-#ifdef CONFIG_NFSD_PNFS
+#ifdef CONFIG_NFSD_BLOCKLAYOUT
 	.get_uuid		= xfs_fs_get_uuid,
 	.map_blocks		= xfs_fs_map_blocks,
 	.commit_blocks		= xfs_fs_commit_blocks,
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index e78feb400e22..569938a4a357 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -55,7 +55,7 @@ xfs_rw_ilock(
 	int			type)
 {
 	if (type & XFS_IOLOCK_EXCL)
-		mutex_lock(&VFS_I(ip)->i_mutex);
+		inode_lock(VFS_I(ip));
 	xfs_ilock(ip, type);
 }
 
@@ -66,7 +66,7 @@ xfs_rw_iunlock(
 {
 	xfs_iunlock(ip, type);
 	if (type & XFS_IOLOCK_EXCL)
-		mutex_unlock(&VFS_I(ip)->i_mutex);
+		inode_unlock(VFS_I(ip));
 }
 
 static inline void
@@ -76,7 +76,7 @@ xfs_rw_ilock_demote(
 {
 	xfs_ilock_demote(ip, type);
 	if (type & XFS_IOLOCK_EXCL)
-		mutex_unlock(&VFS_I(ip)->i_mutex);
+		inode_unlock(VFS_I(ip));
 }
 
 /*
@@ -106,8 +106,8 @@ xfs_iozero(
 		unsigned offset, bytes;
 		void *fsdata;
 
-		offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
-		bytes = PAGE_CACHE_SIZE - offset;
+		offset = (pos & (PAGE_SIZE -1)); /* Within page */
+		bytes = PAGE_SIZE - offset;
 		if (bytes > count)
 			bytes = count;
 
@@ -156,9 +156,9 @@ xfs_update_prealloc_flags(
 	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
 	if (!(flags & XFS_PREALLOC_INVISIBLE)) {
-		ip->i_d.di_mode &= ~S_ISUID;
-		if (ip->i_d.di_mode & S_IXGRP)
-			ip->i_d.di_mode &= ~S_ISGID;
+		VFS_I(ip)->i_mode &= ~S_ISUID;
+		if (VFS_I(ip)->i_mode & S_IXGRP)
+			VFS_I(ip)->i_mode &= ~S_ISGID;
 		xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 	}
 
@@ -242,19 +242,30 @@ xfs_file_fsync(
 	}
 
 	/*
-	 * All metadata updates are logged, which means that we just have
-	 * to flush the log up to the latest LSN that touched the inode.
+	 * All metadata updates are logged, which means that we just have to
+	 * flush the log up to the latest LSN that touched the inode. If we have
+	 * concurrent fsync/fdatasync() calls, we need them to all block on the
+	 * log force before we clear the ili_fsync_fields field. This ensures
+	 * that we don't get a racing sync operation that does not wait for the
+	 * metadata to hit the journal before returning. If we race with
+	 * clearing the ili_fsync_fields, then all that will happen is the log
+	 * force will do nothing as the lsn will already be on disk. We can't
+	 * race with setting ili_fsync_fields because that is done under
+	 * XFS_ILOCK_EXCL, and that can't happen because we hold the lock shared
+	 * until after the ili_fsync_fields is cleared.
 	 */
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
 	if (xfs_ipincount(ip)) {
 		if (!datasync ||
-		    (ip->i_itemp->ili_fields & ~XFS_ILOG_TIMESTAMP))
+		    (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
 			lsn = ip->i_itemp->ili_last_lsn;
 	}
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
 
-	if (lsn)
+	if (lsn) {
 		error = _xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed);
+		ip->i_itemp->ili_fsync_fields = 0;
+	}
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
 
 	/*
 	 * If we only have a single device, and the log force about was
@@ -287,7 +298,7 @@ xfs_file_read_iter(
 	xfs_fsize_t		n;
 	loff_t			pos = iocb->ki_pos;
 
-	XFS_STATS_INC(xs_read_calls);
+	XFS_STATS_INC(mp, xs_read_calls);
 
 	if (unlikely(iocb->ki_flags & IOCB_DIRECT))
 		ioflags |= XFS_IO_ISDIRECT;
@@ -365,7 +376,7 @@ xfs_file_read_iter(
 
 	ret = generic_file_read_iter(iocb, to);
 	if (ret > 0)
-		XFS_STATS_ADD(xs_read_bytes, ret);
+		XFS_STATS_ADD(mp, xs_read_bytes, ret);
 
 	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 	return ret;
@@ -383,7 +394,7 @@ xfs_file_splice_read(
 	int			ioflags = 0;
 	ssize_t			ret;
 
-	XFS_STATS_INC(xs_read_calls);
+	XFS_STATS_INC(ip->i_mount, xs_read_calls);
 
 	if (infilp->f_mode & FMODE_NOCMTIME)
 		ioflags |= XFS_IO_INVIS;
@@ -391,19 +402,26 @@ xfs_file_splice_read(
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
 		return -EIO;
 
-	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
-
 	trace_xfs_file_splice_read(ip, count, *ppos, ioflags);
 
-	/* for dax, we need to avoid the page cache */
-	if (IS_DAX(VFS_I(ip)))
-		ret = default_file_splice_read(infilp, ppos, pipe, count, flags);
-	else
-		ret = generic_file_splice_read(infilp, ppos, pipe, count, flags);
-	if (ret > 0)
-		XFS_STATS_ADD(xs_read_bytes, ret);
+	/*
+	 * DAX inodes cannot ues the page cache for splice, so we have to push
+	 * them through the VFS IO path. This means it goes through
+	 * ->read_iter, which for us takes the XFS_IOLOCK_SHARED. Hence we
+	 * cannot lock the splice operation at this level for DAX inodes.
+	 */
+	if (IS_DAX(VFS_I(ip))) {
+		ret = default_file_splice_read(infilp, ppos, pipe, count,
+					       flags);
+		goto out;
+	}
 
+	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
+	ret = generic_file_splice_read(infilp, ppos, pipe, count, flags);
 	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
+out:
+	if (ret > 0)
+		XFS_STATS_ADD(ip->i_mount, xs_read_bytes, ret);
 	return ret;
 }
 
@@ -482,6 +500,8 @@ xfs_zero_eof(
 	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
 	ASSERT(offset > isize);
 
+	trace_xfs_zero_eof(ip, isize, offset - isize);
+
 	/*
 	 * First handle zeroing the block on which isize resides.
 	 *
@@ -574,6 +594,7 @@ xfs_file_aio_write_checks(
 	struct xfs_inode	*ip = XFS_I(inode);
 	ssize_t			error = 0;
 	size_t			count = iov_iter_count(from);
+	bool			drained_dio = false;
 
 restart:
 	error = generic_write_checks(iocb, from);
@@ -611,12 +632,13 @@ restart:
 		bool	zero = false;
 
 		spin_unlock(&ip->i_flags_lock);
-		if (*iolock == XFS_IOLOCK_SHARED) {
-			xfs_rw_iunlock(ip, *iolock);
-			*iolock = XFS_IOLOCK_EXCL;
-			xfs_rw_ilock(ip, *iolock);
-			iov_iter_reexpand(from, count);
-
+		if (!drained_dio) {
+			if (*iolock == XFS_IOLOCK_SHARED) {
+				xfs_rw_iunlock(ip, *iolock);
+				*iolock = XFS_IOLOCK_EXCL;
+				xfs_rw_ilock(ip, *iolock);
+				iov_iter_reexpand(from, count);
+			}
 			/*
 			 * We now have an IO submission barrier in place, but
 			 * AIO can do EOF updates during IO completion and hence
@@ -626,6 +648,7 @@ restart:
 			 * no-op.
 			 */
 			inode_dio_wait(inode);
+			drained_dio = true;
 			goto restart;
 		}
 		error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), &zero);
@@ -776,8 +799,8 @@ xfs_file_dio_aio_write(
 	/* see generic_file_direct_write() for why this is necessary */
 	if (mapping->nrpages) {
 		invalidate_inode_pages2_range(mapping,
-					      pos >> PAGE_CACHE_SHIFT,
-					      end >> PAGE_CACHE_SHIFT);
+					      pos >> PAGE_SHIFT,
+					      end >> PAGE_SHIFT);
 	}
 
 	if (ret > 0) {
@@ -867,7 +890,7 @@ xfs_file_write_iter(
 	ssize_t			ret;
 	size_t			ocount = iov_iter_count(from);
 
-	XFS_STATS_INC(xs_write_calls);
+	XFS_STATS_INC(ip->i_mount, xs_write_calls);
 
 	if (ocount == 0)
 		return 0;
@@ -883,7 +906,7 @@ xfs_file_write_iter(
 	if (ret > 0) {
 		ssize_t err;
 
-		XFS_STATS_ADD(xs_write_bytes, ret);
+		XFS_STATS_ADD(ip->i_mount, xs_write_bytes, ret);
 
 		/* Handle various SYNC-type writes */
 		err = generic_write_sync(file, iocb->ki_pos - ret, ret);
@@ -1184,9 +1207,9 @@ xfs_find_get_desired_pgoff(
 
 	pagevec_init(&pvec, 0);
 
-	index = startoff >> PAGE_CACHE_SHIFT;
+	index = startoff >> PAGE_SHIFT;
 	endoff = XFS_FSB_TO_B(mp, map->br_startoff + map->br_blockcount);
-	end = endoff >> PAGE_CACHE_SHIFT;
+	end = endoff >> PAGE_SHIFT;
 	do {
 		int		want;
 		unsigned	nr_pages;
@@ -1314,31 +1337,31 @@ out:
 	return found;
 }
 
-STATIC loff_t
-xfs_seek_hole_data(
-	struct file		*file,
+/*
+ * caller must lock inode with xfs_ilock_data_map_shared,
+ * can we craft an appropriate ASSERT?
+ *
+ * end is because the VFS-level lseek interface is defined such that any
+ * offset past i_size shall return -ENXIO, but we use this for quota code
+ * which does not maintain i_size, and we want to SEEK_DATA past i_size.
+ */
+loff_t
+__xfs_seek_hole_data(
+	struct inode		*inode,
 	loff_t			start,
+	loff_t			end,
 	int			whence)
 {
-	struct inode		*inode = file->f_mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
 	loff_t			uninitialized_var(offset);
-	xfs_fsize_t		isize;
 	xfs_fileoff_t		fsbno;
-	xfs_filblks_t		end;
-	uint			lock;
+	xfs_filblks_t		lastbno;
 	int			error;
 
-	if (XFS_FORCED_SHUTDOWN(mp))
-		return -EIO;
-
-	lock = xfs_ilock_data_map_shared(ip);
-
-	isize = i_size_read(inode);
-	if (start >= isize) {
+	if (start >= end) {
 		error = -ENXIO;
-		goto out_unlock;
+		goto out_error;
 	}
 
 	/*
@@ -1346,22 +1369,22 @@ xfs_seek_hole_data(
 	 * by fsbno to the end block of the file.
 	 */
 	fsbno = XFS_B_TO_FSBT(mp, start);
-	end = XFS_B_TO_FSB(mp, isize);
+	lastbno = XFS_B_TO_FSB(mp, end);
 
 	for (;;) {
 		struct xfs_bmbt_irec	map[2];
 		int			nmap = 2;
 		unsigned int		i;
 
-		error = xfs_bmapi_read(ip, fsbno, end - fsbno, map, &nmap,
+		error = xfs_bmapi_read(ip, fsbno, lastbno - fsbno, map, &nmap,
 				       XFS_BMAPI_ENTIRE);
 		if (error)
-			goto out_unlock;
+			goto out_error;
 
 		/* No extents at given offset, must be beyond EOF */
 		if (nmap == 0) {
 			error = -ENXIO;
-			goto out_unlock;
+			goto out_error;
 		}
 
 		for (i = 0; i < nmap; i++) {
@@ -1403,7 +1426,7 @@ xfs_seek_hole_data(
 			 * hole at the end of any file).
 		 	 */
 			if (whence == SEEK_HOLE) {
-				offset = isize;
+				offset = end;
 				break;
 			}
 			/*
@@ -1411,7 +1434,7 @@ xfs_seek_hole_data(
 			 */
 			ASSERT(whence == SEEK_DATA);
 			error = -ENXIO;
-			goto out_unlock;
+			goto out_error;
 		}
 
 		ASSERT(i > 1);
@@ -1422,14 +1445,14 @@ xfs_seek_hole_data(
 		 */
 		fsbno = map[i - 1].br_startoff + map[i - 1].br_blockcount;
 		start = XFS_FSB_TO_B(mp, fsbno);
-		if (start >= isize) {
+		if (start >= end) {
 			if (whence == SEEK_HOLE) {
-				offset = isize;
+				offset = end;
 				break;
 			}
 			ASSERT(whence == SEEK_DATA);
 			error = -ENXIO;
-			goto out_unlock;
+			goto out_error;
 		}
 	}
 
@@ -1441,7 +1464,39 @@ out:
 	 * situation in particular.
 	 */
 	if (whence == SEEK_HOLE)
-		offset = min_t(loff_t, offset, isize);
+		offset = min_t(loff_t, offset, end);
+
+	return offset;
+
+out_error:
+	return error;
+}
+
+STATIC loff_t
+xfs_seek_hole_data(
+	struct file		*file,
+	loff_t			start,
+	int			whence)
+{
+	struct inode		*inode = file->f_mapping->host;
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	uint			lock;
+	loff_t			offset, end;
+	int			error = 0;
+
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return -EIO;
+
+	lock = xfs_ilock_data_map_shared(ip);
+
+	end = i_size_read(inode);
+	offset = __xfs_seek_hole_data(inode, start, end, whence);
+	if (offset < 0) {
+		error = offset;
+		goto out_unlock;
+	}
+
 	offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
 
 out_unlock:
@@ -1477,7 +1532,7 @@ xfs_file_llseek(
  *
  * mmap_sem (MM)
  *   sb_start_pagefault(vfs, freeze)
- *     i_mmap_lock (XFS - truncate serialisation)
+ *     i_mmaplock (XFS - truncate serialisation)
  *       page_lock (MM)
  *         i_lock (XFS - extent map serialisation)
  */
@@ -1503,10 +1558,9 @@ xfs_filemap_page_mkwrite(
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (IS_DAX(inode)) {
-		ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_direct,
-				    xfs_end_io_dax_write);
+		ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault, NULL);
 	} else {
-		ret = __block_page_mkwrite(vma, vmf, xfs_get_blocks);
+		ret = block_page_mkwrite(vma, vmf, xfs_get_blocks);
 		ret = block_page_mkwrite_return(ret);
 	}
 
@@ -1538,7 +1592,7 @@ 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_direct, NULL);
+		ret = __dax_fault(vma, vmf, xfs_get_blocks_dax_fault, NULL);
 	} else
 		ret = filemap_fault(vma, vmf);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
@@ -1546,6 +1600,13 @@ xfs_filemap_fault(
 	return ret;
 }
 
+/*
+ * Similar to xfs_filemap_fault(), the DAX fault path can call into here on
+ * both read and write faults. Hence we need to handle both cases. There is no
+ * ->pmd_mkwrite callout for huge pages, so we have a single function here to
+ * handle both cases here. @flags carries the information on the type of fault
+ * occuring.
+ */
 STATIC int
 xfs_filemap_pmd_fault(
 	struct vm_area_struct	*vma,
@@ -1562,15 +1623,55 @@ xfs_filemap_pmd_fault(
 
 	trace_xfs_filemap_pmd_fault(ip);
 
-	sb_start_pagefault(inode->i_sb);
-	file_update_time(vma->vm_file);
+	if (flags & FAULT_FLAG_WRITE) {
+		sb_start_pagefault(inode->i_sb);
+		file_update_time(vma->vm_file);
+	}
+
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_direct,
-				    xfs_end_io_dax_write);
+	ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault,
+			      NULL);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	sb_end_pagefault(inode->i_sb);
 
+	if (flags & FAULT_FLAG_WRITE)
+		sb_end_pagefault(inode->i_sb);
+
+	return ret;
+}
+
+/*
+ * pfn_mkwrite was originally inteneded to ensure we capture time stamp
+ * updates on write faults. In reality, it's need to serialise against
+ * truncate similar to page_mkwrite. Hence we cycle the XFS_MMAPLOCK_SHARED
+ * to ensure we serialise the fault barrier in place.
+ */
+static int
+xfs_filemap_pfn_mkwrite(
+	struct vm_area_struct	*vma,
+	struct vm_fault		*vmf)
+{
+
+	struct inode		*inode = file_inode(vma->vm_file);
+	struct xfs_inode	*ip = XFS_I(inode);
+	int			ret = VM_FAULT_NOPAGE;
+	loff_t			size;
+
+	trace_xfs_filemap_pfn_mkwrite(ip);
+
+	sb_start_pagefault(inode->i_sb);
+	file_update_time(vma->vm_file);
+
+	/* check if the faulting page hasn't raced with truncate */
+	xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
+	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (vmf->pgoff >= size)
+		ret = VM_FAULT_SIGBUS;
+	else if (IS_DAX(inode))
+		ret = dax_pfn_mkwrite(vma, vmf);
+	xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
+	sb_end_pagefault(inode->i_sb);
 	return ret;
+
 }
 
 static const struct vm_operations_struct xfs_file_vm_ops = {
@@ -1578,6 +1679,7 @@ static const struct vm_operations_struct xfs_file_vm_ops = {
 	.pmd_fault	= xfs_filemap_pmd_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= xfs_filemap_page_mkwrite,
+	.pfn_mkwrite	= xfs_filemap_pfn_mkwrite,
 };
 
 STATIC int
diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c
index c4c130f9bfb6..a51353a1f87f 100644
--- a/fs/xfs/xfs_filestream.c
+++ b/fs/xfs/xfs_filestream.c
@@ -151,7 +151,7 @@ xfs_filestream_pick_ag(
 	xfs_agnumber_t		ag, max_ag = NULLAGNUMBER;
 	int			err, trylock, nscan;
 
-	ASSERT(S_ISDIR(ip->i_d.di_mode));
+	ASSERT(S_ISDIR(VFS_I(ip)->i_mode));
 
 	/* 2% of an AG's blocks must be free for it to be chosen. */
 	minfree = mp->m_sb.sb_agblocks / 50;
@@ -319,7 +319,7 @@ xfs_filestream_lookup_ag(
 	xfs_agnumber_t		startag, ag = NULLAGNUMBER;
 	struct xfs_mru_cache_elem *mru;
 
-	ASSERT(S_ISREG(ip->i_d.di_mode));
+	ASSERT(S_ISREG(VFS_I(ip)->i_mode));
 
 	pip = xfs_filestream_get_parent(ip);
 	if (!pip)
diff --git a/fs/xfs/xfs_fsops.h b/fs/xfs/xfs_fsops.h
index 1b6a98b66886..f32713f14f9a 100644
--- a/fs/xfs/xfs_fsops.h
+++ b/fs/xfs/xfs_fsops.h
@@ -25,6 +25,5 @@ extern int xfs_fs_counts(xfs_mount_t *mp, xfs_fsop_counts_t *cnt);
 extern int xfs_reserve_blocks(xfs_mount_t *mp, __uint64_t *inval,
 				xfs_fsop_resblks_t *outval);
 extern int xfs_fs_goingdown(xfs_mount_t *mp, __uint32_t inflags);
-extern int xfs_fs_log_dummy(struct xfs_mount *mp);
 
 #endif	/* __XFS_FSOPS_H__ */
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 0a326bd64d4e..bf2d60749278 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -63,7 +63,10 @@ xfs_inode_alloc(
 		return NULL;
 	}
 
-	XFS_STATS_INC(vn_active);
+	/* VFS doesn't initialise i_mode! */
+	VFS_I(ip)->i_mode = 0;
+
+	XFS_STATS_INC(mp, vn_active);
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
 	ASSERT(!spin_is_locked(&ip->i_flags_lock));
 	ASSERT(!xfs_isiflocked(ip));
@@ -79,7 +82,7 @@ xfs_inode_alloc(
 	memset(&ip->i_df, 0, sizeof(xfs_ifork_t));
 	ip->i_flags = 0;
 	ip->i_delayed_blks = 0;
-	memset(&ip->i_d, 0, sizeof(xfs_icdinode_t));
+	memset(&ip->i_d, 0, sizeof(ip->i_d));
 
 	return ip;
 }
@@ -98,7 +101,7 @@ void
 xfs_inode_free(
 	struct xfs_inode	*ip)
 {
-	switch (ip->i_d.di_mode & S_IFMT) {
+	switch (VFS_I(ip)->i_mode & S_IFMT) {
 	case S_IFREG:
 	case S_IFDIR:
 	case S_IFLNK:
@@ -129,12 +132,40 @@ xfs_inode_free(
 	/* asserts to verify all state is correct here */
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
 	ASSERT(!xfs_isiflocked(ip));
-	XFS_STATS_DEC(vn_active);
+	XFS_STATS_DEC(ip->i_mount, vn_active);
 
 	call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback);
 }
 
 /*
+ * When we recycle a reclaimable inode, we need to re-initialise the VFS inode
+ * part of the structure. This is made more complex by the fact we store
+ * information about the on-disk values in the VFS inode and so we can't just
+ * overwrite the values unconditionally. Hence we save the parameters we
+ * need to retain across reinitialisation, and rewrite them into the VFS inode
+ * after reinitialisation even if it fails.
+ */
+static int
+xfs_reinit_inode(
+	struct xfs_mount	*mp,
+	struct inode		*inode)
+{
+	int		error;
+	uint32_t	nlink = inode->i_nlink;
+	uint32_t	generation = inode->i_generation;
+	uint64_t	version = inode->i_version;
+	umode_t		mode = inode->i_mode;
+
+	error = inode_init_always(mp->m_super, inode);
+
+	set_nlink(inode, nlink);
+	inode->i_generation = generation;
+	inode->i_version = version;
+	inode->i_mode = mode;
+	return error;
+}
+
+/*
  * Check the validity of the inode we just found it the cache
  */
 static int
@@ -159,7 +190,7 @@ xfs_iget_cache_hit(
 	spin_lock(&ip->i_flags_lock);
 	if (ip->i_ino != ino) {
 		trace_xfs_iget_skip(ip);
-		XFS_STATS_INC(xs_ig_frecycle);
+		XFS_STATS_INC(mp, xs_ig_frecycle);
 		error = -EAGAIN;
 		goto out_error;
 	}
@@ -177,7 +208,7 @@ xfs_iget_cache_hit(
 	 */
 	if (ip->i_flags & (XFS_INEW|XFS_IRECLAIM)) {
 		trace_xfs_iget_skip(ip);
-		XFS_STATS_INC(xs_ig_frecycle);
+		XFS_STATS_INC(mp, xs_ig_frecycle);
 		error = -EAGAIN;
 		goto out_error;
 	}
@@ -185,7 +216,7 @@ xfs_iget_cache_hit(
 	/*
 	 * If lookup is racing with unlink return an error immediately.
 	 */
-	if (ip->i_d.di_mode == 0 && !(flags & XFS_IGET_CREATE)) {
+	if (VFS_I(ip)->i_mode == 0 && !(flags & XFS_IGET_CREATE)) {
 		error = -ENOENT;
 		goto out_error;
 	}
@@ -208,7 +239,7 @@ xfs_iget_cache_hit(
 		spin_unlock(&ip->i_flags_lock);
 		rcu_read_unlock();
 
-		error = inode_init_always(mp->m_super, inode);
+		error = xfs_reinit_inode(mp, inode);
 		if (error) {
 			/*
 			 * Re-initializing the inode failed, and we are in deep
@@ -259,7 +290,7 @@ xfs_iget_cache_hit(
 		xfs_ilock(ip, lock_flags);
 
 	xfs_iflags_clear(ip, XFS_ISTALE | XFS_IDONTCACHE);
-	XFS_STATS_INC(xs_ig_found);
+	XFS_STATS_INC(mp, xs_ig_found);
 
 	return 0;
 
@@ -295,7 +326,7 @@ xfs_iget_cache_miss(
 
 	trace_xfs_iget_miss(ip);
 
-	if ((ip->i_d.di_mode == 0) && !(flags & XFS_IGET_CREATE)) {
+	if ((VFS_I(ip)->i_mode == 0) && !(flags & XFS_IGET_CREATE)) {
 		error = -ENOENT;
 		goto out_destroy;
 	}
@@ -342,7 +373,7 @@ xfs_iget_cache_miss(
 	error = radix_tree_insert(&pag->pag_ici_root, agino, ip);
 	if (unlikely(error)) {
 		WARN_ON(error != -EEXIST);
-		XFS_STATS_INC(xs_ig_dup);
+		XFS_STATS_INC(mp, xs_ig_dup);
 		error = -EAGAIN;
 		goto out_preload_end;
 	}
@@ -412,7 +443,7 @@ xfs_iget(
 	if (!ino || XFS_INO_TO_AGNO(mp, ino) >= mp->m_sb.sb_agcount)
 		return -EINVAL;
 
-	XFS_STATS_INC(xs_ig_attempts);
+	XFS_STATS_INC(mp, xs_ig_attempts);
 
 	/* get the perag structure and ensure that it's inode capable */
 	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ino));
@@ -429,7 +460,7 @@ again:
 			goto out_error_or_again;
 	} else {
 		rcu_read_unlock();
-		XFS_STATS_INC(xs_ig_missed);
+		XFS_STATS_INC(mp, xs_ig_missed);
 
 		error = xfs_iget_cache_miss(mp, pag, tp, ino, &ip,
 							flags, lock_flags);
@@ -444,7 +475,7 @@ again:
 	 * If we have a real type for an on-disk inode, we can setup the inode
 	 * now.	 If it's a new inode being created, xfs_ialloc will handle it.
 	 */
-	if (xfs_iflags_test(ip, XFS_INEW) && ip->i_d.di_mode != 0)
+	if (xfs_iflags_test(ip, XFS_INEW) && VFS_I(ip)->i_mode != 0)
 		xfs_setup_existing_inode(ip);
 	return 0;
 
@@ -965,7 +996,7 @@ reclaim:
 	xfs_ifunlock(ip);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 
-	XFS_STATS_INC(xs_ig_reclaims);
+	XFS_STATS_INC(ip->i_mount, xs_ig_reclaims);
 	/*
 	 * Remove the inode from the per-AG radix tree.
 	 *
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index dc40a6d5ae0d..96f606deee31 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -57,9 +57,9 @@ kmem_zone_t *xfs_inode_zone;
  */
 #define	XFS_ITRUNC_MAX_EXTENTS	2
 
-STATIC int xfs_iflush_int(xfs_inode_t *, xfs_buf_t *);
-
-STATIC int xfs_iunlink_remove(xfs_trans_t *, xfs_inode_t *);
+STATIC int xfs_iflush_int(struct xfs_inode *, struct xfs_buf *);
+STATIC int xfs_iunlink(struct xfs_trans *, struct xfs_inode *);
+STATIC int xfs_iunlink_remove(struct xfs_trans *, struct xfs_inode *);
 
 /*
  * helper function to extract extent size hint from inode
@@ -610,60 +610,69 @@ __xfs_iflock(
 
 STATIC uint
 _xfs_dic2xflags(
-	__uint16_t		di_flags)
+	__uint16_t		di_flags,
+	uint64_t		di_flags2,
+	bool			has_attr)
 {
 	uint			flags = 0;
 
 	if (di_flags & XFS_DIFLAG_ANY) {
 		if (di_flags & XFS_DIFLAG_REALTIME)
-			flags |= XFS_XFLAG_REALTIME;
+			flags |= FS_XFLAG_REALTIME;
 		if (di_flags & XFS_DIFLAG_PREALLOC)
-			flags |= XFS_XFLAG_PREALLOC;
+			flags |= FS_XFLAG_PREALLOC;
 		if (di_flags & XFS_DIFLAG_IMMUTABLE)
-			flags |= XFS_XFLAG_IMMUTABLE;
+			flags |= FS_XFLAG_IMMUTABLE;
 		if (di_flags & XFS_DIFLAG_APPEND)
-			flags |= XFS_XFLAG_APPEND;
+			flags |= FS_XFLAG_APPEND;
 		if (di_flags & XFS_DIFLAG_SYNC)
-			flags |= XFS_XFLAG_SYNC;
+			flags |= FS_XFLAG_SYNC;
 		if (di_flags & XFS_DIFLAG_NOATIME)
-			flags |= XFS_XFLAG_NOATIME;
+			flags |= FS_XFLAG_NOATIME;
 		if (di_flags & XFS_DIFLAG_NODUMP)
-			flags |= XFS_XFLAG_NODUMP;
+			flags |= FS_XFLAG_NODUMP;
 		if (di_flags & XFS_DIFLAG_RTINHERIT)
-			flags |= XFS_XFLAG_RTINHERIT;
+			flags |= FS_XFLAG_RTINHERIT;
 		if (di_flags & XFS_DIFLAG_PROJINHERIT)
-			flags |= XFS_XFLAG_PROJINHERIT;
+			flags |= FS_XFLAG_PROJINHERIT;
 		if (di_flags & XFS_DIFLAG_NOSYMLINKS)
-			flags |= XFS_XFLAG_NOSYMLINKS;
+			flags |= FS_XFLAG_NOSYMLINKS;
 		if (di_flags & XFS_DIFLAG_EXTSIZE)
-			flags |= XFS_XFLAG_EXTSIZE;
+			flags |= FS_XFLAG_EXTSIZE;
 		if (di_flags & XFS_DIFLAG_EXTSZINHERIT)
-			flags |= XFS_XFLAG_EXTSZINHERIT;
+			flags |= FS_XFLAG_EXTSZINHERIT;
 		if (di_flags & XFS_DIFLAG_NODEFRAG)
-			flags |= XFS_XFLAG_NODEFRAG;
+			flags |= FS_XFLAG_NODEFRAG;
 		if (di_flags & XFS_DIFLAG_FILESTREAM)
-			flags |= XFS_XFLAG_FILESTREAM;
+			flags |= FS_XFLAG_FILESTREAM;
+	}
+
+	if (di_flags2 & XFS_DIFLAG2_ANY) {
+		if (di_flags2 & XFS_DIFLAG2_DAX)
+			flags |= FS_XFLAG_DAX;
 	}
 
+	if (has_attr)
+		flags |= FS_XFLAG_HASATTR;
+
 	return flags;
 }
 
 uint
 xfs_ip2xflags(
-	xfs_inode_t		*ip)
+	struct xfs_inode	*ip)
 {
-	xfs_icdinode_t		*dic = &ip->i_d;
+	struct xfs_icdinode	*dic = &ip->i_d;
 
-	return _xfs_dic2xflags(dic->di_flags) |
-				(XFS_IFORK_Q(ip) ? XFS_XFLAG_HASATTR : 0);
+	return _xfs_dic2xflags(dic->di_flags, dic->di_flags2, XFS_IFORK_Q(ip));
 }
 
 uint
 xfs_dic2xflags(
-	xfs_dinode_t		*dip)
+	struct xfs_dinode	*dip)
 {
-	return _xfs_dic2xflags(be16_to_cpu(dip->di_flags)) |
-				(XFS_DFORK_Q(dip) ? XFS_XFLAG_HASATTR : 0);
+	return _xfs_dic2xflags(be16_to_cpu(dip->di_flags),
+				be64_to_cpu(dip->di_flags2), XFS_DFORK_Q(dip));
 }
 
 /*
@@ -757,6 +766,7 @@ xfs_ialloc(
 	uint		flags;
 	int		error;
 	struct timespec	tv;
+	struct inode	*inode;
 
 	/*
 	 * Call the space management code to pick
@@ -782,6 +792,7 @@ xfs_ialloc(
 	if (error)
 		return error;
 	ASSERT(ip != NULL);
+	inode = VFS_I(ip);
 
 	/*
 	 * We always convert v1 inodes to v2 now - we only support filesystems
@@ -791,20 +802,16 @@ xfs_ialloc(
 	if (ip->i_d.di_version == 1)
 		ip->i_d.di_version = 2;
 
-	ip->i_d.di_mode = mode;
-	ip->i_d.di_onlink = 0;
-	ip->i_d.di_nlink = nlink;
-	ASSERT(ip->i_d.di_nlink == nlink);
+	inode->i_mode = mode;
+	set_nlink(inode, nlink);
 	ip->i_d.di_uid = xfs_kuid_to_uid(current_fsuid());
 	ip->i_d.di_gid = xfs_kgid_to_gid(current_fsgid());
 	xfs_set_projid(ip, prid);
-	memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
 
 	if (pip && XFS_INHERIT_GID(pip)) {
 		ip->i_d.di_gid = pip->i_d.di_gid;
-		if ((pip->i_d.di_mode & S_ISGID) && S_ISDIR(mode)) {
-			ip->i_d.di_mode |= S_ISGID;
-		}
+		if ((VFS_I(pip)->i_mode & S_ISGID) && S_ISDIR(mode))
+			inode->i_mode |= S_ISGID;
 	}
 
 	/*
@@ -813,38 +820,29 @@ xfs_ialloc(
 	 * (and only if the irix_sgid_inherit compatibility variable is set).
 	 */
 	if ((irix_sgid_inherit) &&
-	    (ip->i_d.di_mode & S_ISGID) &&
-	    (!in_group_p(xfs_gid_to_kgid(ip->i_d.di_gid)))) {
-		ip->i_d.di_mode &= ~S_ISGID;
-	}
+	    (inode->i_mode & S_ISGID) &&
+	    (!in_group_p(xfs_gid_to_kgid(ip->i_d.di_gid))))
+		inode->i_mode &= ~S_ISGID;
 
 	ip->i_d.di_size = 0;
 	ip->i_d.di_nextents = 0;
 	ASSERT(ip->i_d.di_nblocks == 0);
 
 	tv = current_fs_time(mp->m_super);
-	ip->i_d.di_mtime.t_sec = (__int32_t)tv.tv_sec;
-	ip->i_d.di_mtime.t_nsec = (__int32_t)tv.tv_nsec;
-	ip->i_d.di_atime = ip->i_d.di_mtime;
-	ip->i_d.di_ctime = ip->i_d.di_mtime;
+	inode->i_mtime = tv;
+	inode->i_atime = tv;
+	inode->i_ctime = tv;
 
-	/*
-	 * di_gen will have been taken care of in xfs_iread.
-	 */
 	ip->i_d.di_extsize = 0;
 	ip->i_d.di_dmevmask = 0;
 	ip->i_d.di_dmstate = 0;
 	ip->i_d.di_flags = 0;
 
 	if (ip->i_d.di_version == 3) {
-		ASSERT(ip->i_d.di_ino == ino);
-		ASSERT(uuid_equal(&ip->i_d.di_uuid, &mp->m_sb.sb_meta_uuid));
-		ip->i_d.di_crc = 0;
-		ip->i_d.di_changecount = 1;
-		ip->i_d.di_lsn = 0;
+		inode->i_version = 1;
 		ip->i_d.di_flags2 = 0;
-		memset(&(ip->i_d.di_pad2[0]), 0, sizeof(ip->i_d.di_pad2));
-		ip->i_d.di_crtime = ip->i_d.di_mtime;
+		ip->i_d.di_crtime.t_sec = (__int32_t)tv.tv_sec;
+		ip->i_d.di_crtime.t_nsec = (__int32_t)tv.tv_nsec;
 	}
 
 
@@ -862,7 +860,8 @@ xfs_ialloc(
 	case S_IFREG:
 	case S_IFDIR:
 		if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY)) {
-			uint	di_flags = 0;
+			uint64_t	di_flags2 = 0;
+			uint		di_flags = 0;
 
 			if (S_ISDIR(mode)) {
 				if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT)
@@ -898,7 +897,11 @@ xfs_ialloc(
 				di_flags |= XFS_DIFLAG_NODEFRAG;
 			if (pip->i_d.di_flags & XFS_DIFLAG_FILESTREAM)
 				di_flags |= XFS_DIFLAG_FILESTREAM;
+			if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX)
+				di_flags2 |= XFS_DIFLAG2_DAX;
+
 			ip->i_d.di_flags |= di_flags;
+			ip->i_d.di_flags2 |= di_flags2;
 		}
 		/* FALLTHROUGH */
 	case S_IFLNK:
@@ -1078,35 +1081,24 @@ xfs_dir_ialloc(
 }
 
 /*
- * Decrement the link count on an inode & log the change.
- * If this causes the link count to go to zero, initiate the
- * logging activity required to truncate a file.
+ * Decrement the link count on an inode & log the change.  If this causes the
+ * link count to go to zero, move the inode to AGI unlinked list so that it can
+ * be freed when the last active reference goes away via xfs_inactive().
  */
 int				/* error */
 xfs_droplink(
 	xfs_trans_t *tp,
 	xfs_inode_t *ip)
 {
-	int	error;
-
 	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
 
-	ASSERT (ip->i_d.di_nlink > 0);
-	ip->i_d.di_nlink--;
 	drop_nlink(VFS_I(ip));
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
-	error = 0;
-	if (ip->i_d.di_nlink == 0) {
-		/*
-		 * We're dropping the last link to this file.
-		 * Move the on-disk inode to the AGI unlinked list.
-		 * From xfs_inactive() we will pull the inode from
-		 * the list and free it.
-		 */
-		error = xfs_iunlink(tp, ip);
-	}
-	return error;
+	if (VFS_I(ip)->i_nlink)
+		return 0;
+
+	return xfs_iunlink(tp, ip);
 }
 
 /*
@@ -1120,8 +1112,6 @@ xfs_bumplink(
 	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
 
 	ASSERT(ip->i_d.di_version > 1);
-	ASSERT(ip->i_d.di_nlink > 0 || (VFS_I(ip)->i_state & I_LINKABLE));
-	ip->i_d.di_nlink++;
 	inc_nlink(VFS_I(ip));
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 	return 0;
@@ -1143,7 +1133,6 @@ xfs_create(
 	xfs_bmap_free_t		free_list;
 	xfs_fsblock_t		first_block;
 	bool                    unlock_dp_on_error = false;
-	int			committed;
 	prid_t			prid;
 	struct xfs_dquot	*udqp = NULL;
 	struct xfs_dquot	*gdqp = NULL;
@@ -1226,7 +1215,7 @@ xfs_create(
 	 * pointing to itself.
 	 */
 	error = xfs_dir_ialloc(&tp, dp, mode, is_dir ? 2 : 1, rdev,
-			       prid, resblks > 0, &ip, &committed);
+			       prid, resblks > 0, &ip, NULL);
 	if (error)
 		goto out_trans_cancel;
 
@@ -1275,7 +1264,7 @@ xfs_create(
 	 */
 	xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp);
 
-	error = xfs_bmap_finish(&tp, &free_list, &committed);
+	error = xfs_bmap_finish(&tp, &free_list, NULL);
 	if (error)
 		goto out_bmap_cancel;
 
@@ -1380,7 +1369,6 @@ xfs_create_tmpfile(
 	 */
 	xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp);
 
-	ip->i_d.di_nlink--;
 	error = xfs_iunlink(tp, ip);
 	if (error)
 		goto out_trans_cancel;
@@ -1427,12 +1415,11 @@ xfs_link(
 	int			error;
 	xfs_bmap_free_t         free_list;
 	xfs_fsblock_t           first_block;
-	int			committed;
 	int			resblks;
 
 	trace_xfs_link(tdp, target_name);
 
-	ASSERT(!S_ISDIR(sip->i_d.di_mode));
+	ASSERT(!S_ISDIR(VFS_I(sip)->i_mode));
 
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
@@ -1480,7 +1467,10 @@ xfs_link(
 
 	xfs_bmap_init(&free_list, &first_block);
 
-	if (sip->i_d.di_nlink == 0) {
+	/*
+	 * Handle initial link state of O_TMPFILE inode
+	 */
+	if (VFS_I(sip)->i_nlink == 0) {
 		error = xfs_iunlink_remove(tp, sip);
 		if (error)
 			goto error_return;
@@ -1502,11 +1492,10 @@ xfs_link(
 	 * link transaction goes to disk before returning to
 	 * the user.
 	 */
-	if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) {
+	if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
 		xfs_trans_set_sync(tp);
-	}
 
-	error = xfs_bmap_finish (&tp, &free_list, &committed);
+	error = xfs_bmap_finish(&tp, &free_list, NULL);
 	if (error) {
 		xfs_bmap_cancel(&free_list);
 		goto error_return;
@@ -1555,7 +1544,6 @@ xfs_itruncate_extents(
 	xfs_fileoff_t		first_unmap_block;
 	xfs_fileoff_t		last_block;
 	xfs_filblks_t		unmap_len;
-	int			committed;
 	int			error = 0;
 	int			done = 0;
 
@@ -1601,9 +1589,7 @@ xfs_itruncate_extents(
 		 * Duplicate the transaction that has the permanent
 		 * reservation and commit the old transaction.
 		 */
-		error = xfs_bmap_finish(&tp, &free_list, &committed);
-		if (committed)
-			xfs_trans_ijoin(tp, ip, 0);
+		error = xfs_bmap_finish(&tp, &free_list, ip);
 		if (error)
 			goto out_bmap_cancel;
 
@@ -1640,7 +1626,7 @@ xfs_release(
 	xfs_mount_t	*mp = ip->i_mount;
 	int		error;
 
-	if (!S_ISREG(ip->i_d.di_mode) || (ip->i_d.di_mode == 0))
+	if (!S_ISREG(VFS_I(ip)->i_mode) || (VFS_I(ip)->i_mode == 0))
 		return 0;
 
 	/* If this is a read-only mount, don't do this (would generate I/O) */
@@ -1671,7 +1657,7 @@ xfs_release(
 		}
 	}
 
-	if (ip->i_d.di_nlink == 0)
+	if (VFS_I(ip)->i_nlink == 0)
 		return 0;
 
 	if (xfs_can_free_eofblocks(ip, false)) {
@@ -1774,7 +1760,6 @@ xfs_inactive_ifree(
 {
 	xfs_bmap_free_t		free_list;
 	xfs_fsblock_t		first_block;
-	int			committed;
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
 	int			error;
@@ -1841,7 +1826,7 @@ xfs_inactive_ifree(
 	 * Just ignore errors at this point.  There is nothing we can do except
 	 * to try to keep going. Make sure it's not a silent error.
 	 */
-	error = xfs_bmap_finish(&tp,  &free_list, &committed);
+	error = xfs_bmap_finish(&tp, &free_list, NULL);
 	if (error) {
 		xfs_notice(mp, "%s: xfs_bmap_finish returned error %d",
 			__func__, error);
@@ -1876,7 +1861,7 @@ xfs_inactive(
 	 * If the inode is already free, then there can be nothing
 	 * to clean up here.
 	 */
-	if (ip->i_d.di_mode == 0) {
+	if (VFS_I(ip)->i_mode == 0) {
 		ASSERT(ip->i_df.if_real_bytes == 0);
 		ASSERT(ip->i_df.if_broot_bytes == 0);
 		return;
@@ -1888,7 +1873,7 @@ xfs_inactive(
 	if (mp->m_flags & XFS_MOUNT_RDONLY)
 		return;
 
-	if (ip->i_d.di_nlink != 0) {
+	if (VFS_I(ip)->i_nlink != 0) {
 		/*
 		 * force is true because we are evicting an inode from the
 		 * cache. Post-eof blocks must be freed, lest we end up with
@@ -1900,7 +1885,7 @@ xfs_inactive(
 		return;
 	}
 
-	if (S_ISREG(ip->i_d.di_mode) &&
+	if (S_ISREG(VFS_I(ip)->i_mode) &&
 	    (ip->i_d.di_size != 0 || XFS_ISIZE(ip) != 0 ||
 	     ip->i_d.di_nextents > 0 || ip->i_delayed_blks > 0))
 		truncate = 1;
@@ -1909,7 +1894,7 @@ xfs_inactive(
 	if (error)
 		return;
 
-	if (S_ISLNK(ip->i_d.di_mode))
+	if (S_ISLNK(VFS_I(ip)->i_mode))
 		error = xfs_inactive_symlink(ip);
 	else if (truncate)
 		error = xfs_inactive_truncate(ip);
@@ -1945,16 +1930,21 @@ xfs_inactive(
 }
 
 /*
- * This is called when the inode's link count goes to 0.
- * We place the on-disk inode on a list in the AGI.  It
- * will be pulled from this list when the inode is freed.
+ * This is called when the inode's link count goes to 0 or we are creating a
+ * tmpfile via O_TMPFILE. In the case of a tmpfile, @ignore_linkcount will be
+ * set to true as the link count is dropped to zero by the VFS after we've
+ * created the file successfully, so we have to add it to the unlinked list
+ * while the link count is non-zero.
+ *
+ * We place the on-disk inode on a list in the AGI.  It will be pulled from this
+ * list when the inode is freed.
  */
-int
+STATIC int
 xfs_iunlink(
-	xfs_trans_t	*tp,
-	xfs_inode_t	*ip)
+	struct xfs_trans *tp,
+	struct xfs_inode *ip)
 {
-	xfs_mount_t	*mp;
+	xfs_mount_t	*mp = tp->t_mountp;
 	xfs_agi_t	*agi;
 	xfs_dinode_t	*dip;
 	xfs_buf_t	*agibp;
@@ -1964,10 +1954,7 @@ xfs_iunlink(
 	int		offset;
 	int		error;
 
-	ASSERT(ip->i_d.di_nlink == 0);
-	ASSERT(ip->i_d.di_mode != 0);
-
-	mp = tp->t_mountp;
+	ASSERT(VFS_I(ip)->i_mode != 0);
 
 	/*
 	 * Get the agi buffer first.  It ensures lock ordering
@@ -2365,6 +2352,7 @@ retry:
 
 			iip->ili_last_fields = iip->ili_fields;
 			iip->ili_fields = 0;
+			iip->ili_fsync_fields = 0;
 			iip->ili_logged = 1;
 			xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn,
 						&iip->ili_item.li_lsn);
@@ -2404,10 +2392,10 @@ xfs_ifree(
 	struct xfs_icluster	xic = { 0 };
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-	ASSERT(ip->i_d.di_nlink == 0);
+	ASSERT(VFS_I(ip)->i_nlink == 0);
 	ASSERT(ip->i_d.di_nextents == 0);
 	ASSERT(ip->i_d.di_anextents == 0);
-	ASSERT(ip->i_d.di_size == 0 || !S_ISREG(ip->i_d.di_mode));
+	ASSERT(ip->i_d.di_size == 0 || !S_ISREG(VFS_I(ip)->i_mode));
 	ASSERT(ip->i_d.di_nblocks == 0);
 
 	/*
@@ -2421,7 +2409,7 @@ xfs_ifree(
 	if (error)
 		return error;
 
-	ip->i_d.di_mode = 0;		/* mark incore inode as free */
+	VFS_I(ip)->i_mode = 0;		/* mark incore inode as free */
 	ip->i_d.di_flags = 0;
 	ip->i_d.di_dmevmask = 0;
 	ip->i_d.di_forkoff = 0;		/* mark the attr fork not in use */
@@ -2431,7 +2419,7 @@ xfs_ifree(
 	 * Bump the generation count so no one will be confused
 	 * by reincarnations of this inode.
 	 */
-	ip->i_d.di_gen++;
+	VFS_I(ip)->i_generation++;
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
 	if (xic.deleted)
@@ -2518,11 +2506,10 @@ xfs_remove(
 {
 	xfs_mount_t		*mp = dp->i_mount;
 	xfs_trans_t             *tp = NULL;
-	int			is_dir = S_ISDIR(ip->i_d.di_mode);
+	int			is_dir = S_ISDIR(VFS_I(ip)->i_mode);
 	int                     error = 0;
 	xfs_bmap_free_t         free_list;
 	xfs_fsblock_t           first_block;
-	int			committed;
 	uint			resblks;
 
 	trace_xfs_remove(dp, name);
@@ -2573,8 +2560,8 @@ xfs_remove(
 	 * If we're removing a directory perform some additional validation.
 	 */
 	if (is_dir) {
-		ASSERT(ip->i_d.di_nlink >= 2);
-		if (ip->i_d.di_nlink != 2) {
+		ASSERT(VFS_I(ip)->i_nlink >= 2);
+		if (VFS_I(ip)->i_nlink != 2) {
 			error = -ENOTEMPTY;
 			goto out_trans_cancel;
 		}
@@ -2623,7 +2610,7 @@ xfs_remove(
 	if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
 		xfs_trans_set_sync(tp);
 
-	error = xfs_bmap_finish(&tp, &free_list, &committed);
+	error = xfs_bmap_finish(&tp, &free_list, NULL);
 	if (error)
 		goto out_bmap_cancel;
 
@@ -2700,7 +2687,6 @@ xfs_finish_rename(
 	struct xfs_trans	*tp,
 	struct xfs_bmap_free	*free_list)
 {
-	int			committed = 0;
 	int			error;
 
 	/*
@@ -2710,7 +2696,7 @@ xfs_finish_rename(
 	if (tp->t_mountp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
 		xfs_trans_set_sync(tp);
 
-	error = xfs_bmap_finish(&tp, free_list, &committed);
+	error = xfs_bmap_finish(&tp, free_list, NULL);
 	if (error) {
 		xfs_bmap_cancel(free_list);
 		xfs_trans_cancel(tp);
@@ -2765,7 +2751,7 @@ xfs_cross_rename(
 	if (dp1 != dp2) {
 		dp2_flags = XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
 
-		if (S_ISDIR(ip2->i_d.di_mode)) {
+		if (S_ISDIR(VFS_I(ip2)->i_mode)) {
 			error = xfs_dir_replace(tp, ip2, &xfs_name_dotdot,
 						dp1->i_ino, first_block,
 						free_list, spaceres);
@@ -2773,7 +2759,7 @@ xfs_cross_rename(
 				goto out_trans_abort;
 
 			/* transfer ip2 ".." reference to dp1 */
-			if (!S_ISDIR(ip1->i_d.di_mode)) {
+			if (!S_ISDIR(VFS_I(ip1)->i_mode)) {
 				error = xfs_droplink(tp, dp2);
 				if (error)
 					goto out_trans_abort;
@@ -2792,7 +2778,7 @@ xfs_cross_rename(
 			ip2_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
 		}
 
-		if (S_ISDIR(ip1->i_d.di_mode)) {
+		if (S_ISDIR(VFS_I(ip1)->i_mode)) {
 			error = xfs_dir_replace(tp, ip1, &xfs_name_dotdot,
 						dp2->i_ino, first_block,
 						free_list, spaceres);
@@ -2800,7 +2786,7 @@ xfs_cross_rename(
 				goto out_trans_abort;
 
 			/* transfer ip1 ".." reference to dp2 */
-			if (!S_ISDIR(ip2->i_d.di_mode)) {
+			if (!S_ISDIR(VFS_I(ip2)->i_mode)) {
 				error = xfs_droplink(tp, dp1);
 				if (error)
 					goto out_trans_abort;
@@ -2897,7 +2883,7 @@ xfs_rename(
 	struct xfs_inode	*inodes[__XFS_SORT_INODES];
 	int			num_inodes = __XFS_SORT_INODES;
 	bool			new_parent = (src_dp != target_dp);
-	bool			src_is_directory = S_ISDIR(src_ip->i_d.di_mode);
+	bool			src_is_directory = S_ISDIR(VFS_I(src_ip)->i_mode);
 	int			spaceres;
 	int			error;
 
@@ -3026,12 +3012,12 @@ xfs_rename(
 		 * target and source are directories and that target can be
 		 * destroyed, or that neither is a directory.
 		 */
-		if (S_ISDIR(target_ip->i_d.di_mode)) {
+		if (S_ISDIR(VFS_I(target_ip)->i_mode)) {
 			/*
 			 * Make sure target dir is empty.
 			 */
 			if (!(xfs_dir_isempty(target_ip)) ||
-			    (target_ip->i_d.di_nlink > 2)) {
+			    (VFS_I(target_ip)->i_nlink > 2)) {
 				error = -EEXIST;
 				goto out_trans_cancel;
 			}
@@ -3138,7 +3124,7 @@ xfs_rename(
 	 * intermediate state on disk.
 	 */
 	if (wip) {
-		ASSERT(VFS_I(wip)->i_nlink == 0 && wip->i_d.di_nlink == 0);
+		ASSERT(VFS_I(wip)->i_nlink == 0);
 		error = xfs_bumplink(tp, wip);
 		if (error)
 			goto out_bmap_cancel;
@@ -3271,8 +3257,8 @@ xfs_iflush_cluster(
 	}
 
 	if (clcount) {
-		XFS_STATS_INC(xs_icluster_flushcnt);
-		XFS_STATS_ADD(xs_icluster_flushinode, clcount);
+		XFS_STATS_INC(mp, xs_icluster_flushcnt);
+		XFS_STATS_ADD(mp, xs_icluster_flushinode, clcount);
 	}
 
 out_free:
@@ -3307,7 +3293,7 @@ cluster_corrupt_out:
 		 * mark it as stale and brelse.
 		 */
 		if (bp->b_iodone) {
-			XFS_BUF_UNDONE(bp);
+			bp->b_flags &= ~XBF_DONE;
 			xfs_buf_stale(bp);
 			xfs_buf_ioerror(bp, -EIO);
 			xfs_buf_ioend(bp);
@@ -3345,7 +3331,7 @@ xfs_iflush(
 	struct xfs_dinode	*dip;
 	int			error;
 
-	XFS_STATS_INC(xs_iflush_count);
+	XFS_STATS_INC(mp, xs_iflush_count);
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
 	ASSERT(xfs_isiflocked(ip));
@@ -3456,14 +3442,7 @@ xfs_iflush_int(
 			__func__, ip->i_ino, be16_to_cpu(dip->di_magic), dip);
 		goto corrupt_out;
 	}
-	if (XFS_TEST_ERROR(ip->i_d.di_magic != XFS_DINODE_MAGIC,
-				mp, XFS_ERRTAG_IFLUSH_2, XFS_RANDOM_IFLUSH_2)) {
-		xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
-			"%s: Bad inode %Lu, ptr 0x%p, magic number 0x%x",
-			__func__, ip->i_ino, ip, ip->i_d.di_magic);
-		goto corrupt_out;
-	}
-	if (S_ISREG(ip->i_d.di_mode)) {
+	if (S_ISREG(VFS_I(ip)->i_mode)) {
 		if (XFS_TEST_ERROR(
 		    (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) &&
 		    (ip->i_d.di_format != XFS_DINODE_FMT_BTREE),
@@ -3473,7 +3452,7 @@ xfs_iflush_int(
 				__func__, ip->i_ino, ip);
 			goto corrupt_out;
 		}
-	} else if (S_ISDIR(ip->i_d.di_mode)) {
+	} else if (S_ISDIR(VFS_I(ip)->i_mode)) {
 		if (XFS_TEST_ERROR(
 		    (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) &&
 		    (ip->i_d.di_format != XFS_DINODE_FMT_BTREE) &&
@@ -3517,12 +3496,11 @@ xfs_iflush_int(
 		ip->i_d.di_flushiter++;
 
 	/*
-	 * Copy the dirty parts of the inode into the on-disk
-	 * inode.  We always copy out the core of the inode,
-	 * because if the inode is dirty at all the core must
-	 * be.
+	 * Copy the dirty parts of the inode into the on-disk inode.  We always
+	 * copy out the core of the inode, because if the inode is dirty at all
+	 * the core must be.
 	 */
-	xfs_dinode_to_disk(dip, &ip->i_d);
+	xfs_inode_to_disk(ip, dip, iip->ili_item.li_lsn);
 
 	/* Wrap, we never let the log put out DI_MAX_FLUSH */
 	if (ip->i_d.di_flushiter == DI_MAX_FLUSH)
@@ -3560,6 +3538,7 @@ xfs_iflush_int(
 	 */
 	iip->ili_last_fields = iip->ili_fields;
 	iip->ili_fields = 0;
+	iip->ili_fsync_fields = 0;
 	iip->ili_logged = 1;
 
 	xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn,
@@ -3573,10 +3552,6 @@ xfs_iflush_int(
 	 */
 	xfs_buf_attach_iodone(bp, xfs_iflush_done, &iip->ili_item);
 
-	/* update the lsn in the on disk inode if required */
-	if (ip->i_d.di_version == 3)
-		dip->di_lsn = cpu_to_be64(iip->ili_item.li_lsn);
-
 	/* generate the checksum. */
 	xfs_dinode_calc_crc(mp, dip);
 
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index ca9e11989cbd..43e1d51b15eb 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -63,7 +63,7 @@ typedef struct xfs_inode {
 	unsigned long		i_flags;	/* see defined flags below */
 	unsigned int		i_delayed_blks;	/* count of delay alloc blks */
 
-	xfs_icdinode_t		i_d;		/* most of ondisk inode */
+	struct xfs_icdinode	i_d;		/* most of ondisk inode */
 
 	/* VFS inode */
 	struct inode		i_vnode;	/* embedded VFS inode */
@@ -88,7 +88,7 @@ static inline struct inode *VFS_I(struct xfs_inode *ip)
  */
 static inline xfs_fsize_t XFS_ISIZE(struct xfs_inode *ip)
 {
-	if (S_ISREG(ip->i_d.di_mode))
+	if (S_ISREG(VFS_I(ip)->i_mode))
 		return i_size_read(VFS_I(ip));
 	return ip->i_d.di_size;
 }
@@ -369,7 +369,7 @@ static inline int xfs_isiflocked(struct xfs_inode *ip)
  */
 #define XFS_INHERIT_GID(pip)	\
 	(((pip)->i_mount->m_flags & XFS_MOUNT_GRPID) || \
-	 ((pip)->i_d.di_mode & S_ISGID))
+	 (VFS_I(pip)->i_mode & S_ISGID))
 
 int		xfs_release(struct xfs_inode *ip);
 void		xfs_inactive(struct xfs_inode *ip);
@@ -405,8 +405,6 @@ int		xfs_ifree(struct xfs_trans *, xfs_inode_t *,
 			   struct xfs_bmap_free *);
 int		xfs_itruncate_extents(struct xfs_trans **, struct xfs_inode *,
 				      int, xfs_fsize_t);
-int		xfs_iunlink(struct xfs_trans *, xfs_inode_t *);
-
 void		xfs_iext_realloc(xfs_inode_t *, int, int);
 
 void		xfs_iunpin_wait(xfs_inode_t *);
@@ -437,6 +435,8 @@ int	xfs_update_prealloc_flags(struct xfs_inode *ip,
 int	xfs_zero_eof(struct xfs_inode *ip, xfs_off_t offset,
 		     xfs_fsize_t isize, bool *did_zeroing);
 int	xfs_iozero(struct xfs_inode *ip, loff_t pos, size_t count);
+loff_t	__xfs_seek_hole_data(struct inode *inode, loff_t start,
+			     loff_t eof, int whence);
 
 
 /* from xfs_iops.c */
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 62bd80f4edd9..c48b5b18d771 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -135,7 +135,7 @@ xfs_inode_item_size(
 
 	*nvecs += 2;
 	*nbytes += sizeof(struct xfs_inode_log_format) +
-		   xfs_icdinode_size(ip->i_d.di_version);
+		   xfs_log_dinode_size(ip->i_d.di_version);
 
 	xfs_inode_item_data_fork_size(iip, nvecs, nbytes);
 	if (XFS_IFORK_Q(ip))
@@ -322,6 +322,81 @@ xfs_inode_item_format_attr_fork(
 	}
 }
 
+static void
+xfs_inode_to_log_dinode(
+	struct xfs_inode	*ip,
+	struct xfs_log_dinode	*to,
+	xfs_lsn_t		lsn)
+{
+	struct xfs_icdinode	*from = &ip->i_d;
+	struct inode		*inode = VFS_I(ip);
+
+	to->di_magic = XFS_DINODE_MAGIC;
+
+	to->di_version = from->di_version;
+	to->di_format = from->di_format;
+	to->di_uid = from->di_uid;
+	to->di_gid = from->di_gid;
+	to->di_projid_lo = from->di_projid_lo;
+	to->di_projid_hi = from->di_projid_hi;
+
+	memset(to->di_pad, 0, sizeof(to->di_pad));
+	memset(to->di_pad3, 0, sizeof(to->di_pad3));
+	to->di_atime.t_sec = inode->i_atime.tv_sec;
+	to->di_atime.t_nsec = inode->i_atime.tv_nsec;
+	to->di_mtime.t_sec = inode->i_mtime.tv_sec;
+	to->di_mtime.t_nsec = inode->i_mtime.tv_nsec;
+	to->di_ctime.t_sec = inode->i_ctime.tv_sec;
+	to->di_ctime.t_nsec = inode->i_ctime.tv_nsec;
+	to->di_nlink = inode->i_nlink;
+	to->di_gen = inode->i_generation;
+	to->di_mode = inode->i_mode;
+
+	to->di_size = from->di_size;
+	to->di_nblocks = from->di_nblocks;
+	to->di_extsize = from->di_extsize;
+	to->di_nextents = from->di_nextents;
+	to->di_anextents = from->di_anextents;
+	to->di_forkoff = from->di_forkoff;
+	to->di_aformat = from->di_aformat;
+	to->di_dmevmask = from->di_dmevmask;
+	to->di_dmstate = from->di_dmstate;
+	to->di_flags = from->di_flags;
+
+	if (from->di_version == 3) {
+		to->di_changecount = inode->i_version;
+		to->di_crtime.t_sec = from->di_crtime.t_sec;
+		to->di_crtime.t_nsec = from->di_crtime.t_nsec;
+		to->di_flags2 = from->di_flags2;
+
+		to->di_ino = ip->i_ino;
+		to->di_lsn = lsn;
+		memset(to->di_pad2, 0, sizeof(to->di_pad2));
+		uuid_copy(&to->di_uuid, &ip->i_mount->m_sb.sb_meta_uuid);
+		to->di_flushiter = 0;
+	} else {
+		to->di_flushiter = from->di_flushiter;
+	}
+}
+
+/*
+ * Format the inode core. Current timestamp data is only in the VFS inode
+ * fields, so we need to grab them from there. Hence rather than just copying
+ * the XFS inode core structure, format the fields directly into the iovec.
+ */
+static void
+xfs_inode_item_format_core(
+	struct xfs_inode	*ip,
+	struct xfs_log_vec	*lv,
+	struct xfs_log_iovec	**vecp)
+{
+	struct xfs_log_dinode	*dic;
+
+	dic = xlog_prepare_iovec(lv, vecp, XLOG_REG_TYPE_ICORE);
+	xfs_inode_to_log_dinode(ip, dic, ip->i_itemp->ili_item.li_lsn);
+	xlog_finish_iovec(lv, *vecp, xfs_log_dinode_size(ip->i_d.di_version));
+}
+
 /*
  * This is called to fill in the vector of log iovecs for the given inode
  * log item.  It fills the first item with an inode log format structure,
@@ -351,10 +426,7 @@ xfs_inode_item_format(
 	ilf->ilf_size = 2; /* format + core */
 	xlog_finish_iovec(lv, vecp, sizeof(struct xfs_inode_log_format));
 
-	xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_ICORE,
-			&ip->i_d,
-			xfs_icdinode_size(ip->i_d.di_version));
-
+	xfs_inode_item_format_core(ip, lv, &vecp);
 	xfs_inode_item_format_data_fork(iip, ilf, lv, &vecp);
 	if (XFS_IFORK_Q(ip)) {
 		xfs_inode_item_format_attr_fork(iip, ilf, lv, &vecp);
@@ -719,6 +791,7 @@ xfs_iflush_abort(
 		 * attempted.
 		 */
 		iip->ili_fields = 0;
+		iip->ili_fsync_fields = 0;
 	}
 	/*
 	 * Release the inode's flush lock since we're done with it.
diff --git a/fs/xfs/xfs_inode_item.h b/fs/xfs/xfs_inode_item.h
index 488d81254e28..4c7722e325b3 100644
--- a/fs/xfs/xfs_inode_item.h
+++ b/fs/xfs/xfs_inode_item.h
@@ -34,6 +34,7 @@ typedef struct xfs_inode_log_item {
 	unsigned short		ili_logged;	   /* flushed logged data */
 	unsigned int		ili_last_fields;   /* fields when flushed */
 	unsigned int		ili_fields;	   /* fields to be logged */
+	unsigned int		ili_fsync_fields;  /* logged since last fsync */
 } xfs_inode_log_item_t;
 
 static inline int xfs_inode_clean(xfs_inode_t *ip)
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index ea7d85af5310..bcb6c19ce3ea 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -40,6 +40,7 @@
 #include "xfs_symlink.h"
 #include "xfs_trans.h"
 #include "xfs_pnfs.h"
+#include "xfs_acl.h"
 
 #include <linux/capability.h>
 #include <linux/dcache.h>
@@ -113,7 +114,7 @@ xfs_find_handle(
 		handle.ha_fid.fid_len = sizeof(xfs_fid_t) -
 					sizeof(handle.ha_fid.fid_len);
 		handle.ha_fid.fid_pad = 0;
-		handle.ha_fid.fid_gen = ip->i_d.di_gen;
+		handle.ha_fid.fid_gen = inode->i_generation;
 		handle.ha_fid.fid_ino = ip->i_ino;
 
 		hsize = XFS_HSIZE(handle);
@@ -411,7 +412,7 @@ xfs_attrlist_by_handle(
 	if (copy_from_user(&al_hreq, arg, sizeof(xfs_fsop_attrlist_handlereq_t)))
 		return -EFAULT;
 	if (al_hreq.buflen < sizeof(struct attrlist) ||
-	    al_hreq.buflen > XATTR_LIST_MAX)
+	    al_hreq.buflen > XFS_XATTR_LIST_MAX)
 		return -EINVAL;
 
 	/*
@@ -455,7 +456,7 @@ xfs_attrmulti_attr_get(
 	unsigned char		*kbuf;
 	int			error = -EFAULT;
 
-	if (*len > XATTR_SIZE_MAX)
+	if (*len > XFS_XATTR_SIZE_MAX)
 		return -EINVAL;
 	kbuf = kmem_zalloc_large(*len, KM_SLEEP);
 	if (!kbuf)
@@ -482,17 +483,22 @@ xfs_attrmulti_attr_set(
 	__uint32_t		flags)
 {
 	unsigned char		*kbuf;
+	int			error;
 
 	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
 		return -EPERM;
-	if (len > XATTR_SIZE_MAX)
+	if (len > XFS_XATTR_SIZE_MAX)
 		return -EINVAL;
 
 	kbuf = memdup_user(ubuf, len);
 	if (IS_ERR(kbuf))
 		return PTR_ERR(kbuf);
 
-	return xfs_attr_set(XFS_I(inode), name, kbuf, len, flags);
+	error = xfs_attr_set(XFS_I(inode), name, kbuf, len, flags);
+	if (!error)
+		xfs_forget_acl(inode, name, flags);
+	kfree(kbuf);
+	return error;
 }
 
 int
@@ -501,9 +507,14 @@ xfs_attrmulti_attr_remove(
 	unsigned char		*name,
 	__uint32_t		flags)
 {
+	int			error;
+
 	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
 		return -EPERM;
-	return xfs_attr_remove(XFS_I(inode), name, flags);
+	error = xfs_attr_remove(XFS_I(inode), name, flags);
+	if (!error)
+		xfs_forget_acl(inode, name, flags);
+	return error;
 }
 
 STATIC int
@@ -848,25 +859,25 @@ xfs_merge_ioc_xflags(
 	unsigned int	xflags = start;
 
 	if (flags & FS_IMMUTABLE_FL)
-		xflags |= XFS_XFLAG_IMMUTABLE;
+		xflags |= FS_XFLAG_IMMUTABLE;
 	else
-		xflags &= ~XFS_XFLAG_IMMUTABLE;
+		xflags &= ~FS_XFLAG_IMMUTABLE;
 	if (flags & FS_APPEND_FL)
-		xflags |= XFS_XFLAG_APPEND;
+		xflags |= FS_XFLAG_APPEND;
 	else
-		xflags &= ~XFS_XFLAG_APPEND;
+		xflags &= ~FS_XFLAG_APPEND;
 	if (flags & FS_SYNC_FL)
-		xflags |= XFS_XFLAG_SYNC;
+		xflags |= FS_XFLAG_SYNC;
 	else
-		xflags &= ~XFS_XFLAG_SYNC;
+		xflags &= ~FS_XFLAG_SYNC;
 	if (flags & FS_NOATIME_FL)
-		xflags |= XFS_XFLAG_NOATIME;
+		xflags |= FS_XFLAG_NOATIME;
 	else
-		xflags &= ~XFS_XFLAG_NOATIME;
+		xflags &= ~FS_XFLAG_NOATIME;
 	if (flags & FS_NODUMP_FL)
-		xflags |= XFS_XFLAG_NODUMP;
+		xflags |= FS_XFLAG_NODUMP;
 	else
-		xflags &= ~XFS_XFLAG_NODUMP;
+		xflags &= ~FS_XFLAG_NODUMP;
 
 	return xflags;
 }
@@ -934,40 +945,51 @@ xfs_set_diflags(
 	unsigned int		xflags)
 {
 	unsigned int		di_flags;
+	uint64_t		di_flags2;
 
 	/* can't set PREALLOC this way, just preserve it */
 	di_flags = (ip->i_d.di_flags & XFS_DIFLAG_PREALLOC);
-	if (xflags & XFS_XFLAG_IMMUTABLE)
+	if (xflags & FS_XFLAG_IMMUTABLE)
 		di_flags |= XFS_DIFLAG_IMMUTABLE;
-	if (xflags & XFS_XFLAG_APPEND)
+	if (xflags & FS_XFLAG_APPEND)
 		di_flags |= XFS_DIFLAG_APPEND;
-	if (xflags & XFS_XFLAG_SYNC)
+	if (xflags & FS_XFLAG_SYNC)
 		di_flags |= XFS_DIFLAG_SYNC;
-	if (xflags & XFS_XFLAG_NOATIME)
+	if (xflags & FS_XFLAG_NOATIME)
 		di_flags |= XFS_DIFLAG_NOATIME;
-	if (xflags & XFS_XFLAG_NODUMP)
+	if (xflags & FS_XFLAG_NODUMP)
 		di_flags |= XFS_DIFLAG_NODUMP;
-	if (xflags & XFS_XFLAG_NODEFRAG)
+	if (xflags & FS_XFLAG_NODEFRAG)
 		di_flags |= XFS_DIFLAG_NODEFRAG;
-	if (xflags & XFS_XFLAG_FILESTREAM)
+	if (xflags & FS_XFLAG_FILESTREAM)
 		di_flags |= XFS_DIFLAG_FILESTREAM;
-	if (S_ISDIR(ip->i_d.di_mode)) {
-		if (xflags & XFS_XFLAG_RTINHERIT)
+	if (S_ISDIR(VFS_I(ip)->i_mode)) {
+		if (xflags & FS_XFLAG_RTINHERIT)
 			di_flags |= XFS_DIFLAG_RTINHERIT;
-		if (xflags & XFS_XFLAG_NOSYMLINKS)
+		if (xflags & FS_XFLAG_NOSYMLINKS)
 			di_flags |= XFS_DIFLAG_NOSYMLINKS;
-		if (xflags & XFS_XFLAG_EXTSZINHERIT)
+		if (xflags & FS_XFLAG_EXTSZINHERIT)
 			di_flags |= XFS_DIFLAG_EXTSZINHERIT;
-		if (xflags & XFS_XFLAG_PROJINHERIT)
+		if (xflags & FS_XFLAG_PROJINHERIT)
 			di_flags |= XFS_DIFLAG_PROJINHERIT;
-	} else if (S_ISREG(ip->i_d.di_mode)) {
-		if (xflags & XFS_XFLAG_REALTIME)
+	} else if (S_ISREG(VFS_I(ip)->i_mode)) {
+		if (xflags & FS_XFLAG_REALTIME)
 			di_flags |= XFS_DIFLAG_REALTIME;
-		if (xflags & XFS_XFLAG_EXTSIZE)
+		if (xflags & FS_XFLAG_EXTSIZE)
 			di_flags |= XFS_DIFLAG_EXTSIZE;
 	}
-
 	ip->i_d.di_flags = di_flags;
+
+	/* diflags2 only valid for v3 inodes. */
+	if (ip->i_d.di_version < 3)
+		return;
+
+	di_flags2 = 0;
+	if (xflags & FS_XFLAG_DAX)
+		di_flags2 |= XFS_DIFLAG2_DAX;
+
+	ip->i_d.di_flags2 = di_flags2;
+
 }
 
 STATIC void
@@ -977,22 +999,27 @@ xfs_diflags_to_linux(
 	struct inode		*inode = VFS_I(ip);
 	unsigned int		xflags = xfs_ip2xflags(ip);
 
-	if (xflags & XFS_XFLAG_IMMUTABLE)
+	if (xflags & FS_XFLAG_IMMUTABLE)
 		inode->i_flags |= S_IMMUTABLE;
 	else
 		inode->i_flags &= ~S_IMMUTABLE;
-	if (xflags & XFS_XFLAG_APPEND)
+	if (xflags & FS_XFLAG_APPEND)
 		inode->i_flags |= S_APPEND;
 	else
 		inode->i_flags &= ~S_APPEND;
-	if (xflags & XFS_XFLAG_SYNC)
+	if (xflags & FS_XFLAG_SYNC)
 		inode->i_flags |= S_SYNC;
 	else
 		inode->i_flags &= ~S_SYNC;
-	if (xflags & XFS_XFLAG_NOATIME)
+	if (xflags & FS_XFLAG_NOATIME)
 		inode->i_flags |= S_NOATIME;
 	else
 		inode->i_flags &= ~S_NOATIME;
+	if (xflags & FS_XFLAG_DAX)
+		inode->i_flags |= S_DAX;
+	else
+		inode->i_flags &= ~S_DAX;
+
 }
 
 static int
@@ -1005,11 +1032,11 @@ xfs_ioctl_setattr_xflags(
 
 	/* Can't change realtime flag if any extents are allocated. */
 	if ((ip->i_d.di_nextents || ip->i_delayed_blks) &&
-	    XFS_IS_REALTIME_INODE(ip) != (fa->fsx_xflags & XFS_XFLAG_REALTIME))
+	    XFS_IS_REALTIME_INODE(ip) != (fa->fsx_xflags & FS_XFLAG_REALTIME))
 		return -EINVAL;
 
 	/* If realtime flag is set then must have realtime device */
-	if (fa->fsx_xflags & XFS_XFLAG_REALTIME) {
+	if (fa->fsx_xflags & FS_XFLAG_REALTIME) {
 		if (mp->m_sb.sb_rblocks == 0 || mp->m_sb.sb_rextsize == 0 ||
 		    (ip->i_d.di_extsize % mp->m_sb.sb_rextsize))
 			return -EINVAL;
@@ -1020,7 +1047,7 @@ xfs_ioctl_setattr_xflags(
 	 * we have appropriate permission.
 	 */
 	if (((ip->i_d.di_flags & (XFS_DIFLAG_IMMUTABLE | XFS_DIFLAG_APPEND)) ||
-	     (fa->fsx_xflags & (XFS_XFLAG_IMMUTABLE | XFS_XFLAG_APPEND))) &&
+	     (fa->fsx_xflags & (FS_XFLAG_IMMUTABLE | FS_XFLAG_APPEND))) &&
 	    !capable(CAP_LINUX_IMMUTABLE))
 		return -EPERM;
 
@@ -1028,8 +1055,63 @@ xfs_ioctl_setattr_xflags(
 	xfs_diflags_to_linux(ip);
 	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-	XFS_STATS_INC(xs_ig_attrchg);
+	XFS_STATS_INC(mp, xs_ig_attrchg);
+	return 0;
+}
+
+/*
+ * If we are changing DAX flags, we have to ensure the file is clean and any
+ * cached objects in the address space are invalidated and removed. This
+ * requires us to lock out other IO and page faults similar to a truncate
+ * operation. The locks need to be held until the transaction has been committed
+ * so that the cache invalidation is atomic with respect to the DAX flag
+ * manipulation.
+ */
+static int
+xfs_ioctl_setattr_dax_invalidate(
+	struct xfs_inode	*ip,
+	struct fsxattr		*fa,
+	int			*join_flags)
+{
+	struct inode		*inode = VFS_I(ip);
+	int			error;
+
+	*join_flags = 0;
+
+	/*
+	 * It is only valid to set the DAX flag on regular files and
+	 * directories on filesystems where the block size is equal to the page
+	 * size. On directories it serves as an inherit hint.
+	 */
+	if (fa->fsx_xflags & FS_XFLAG_DAX) {
+		if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
+			return -EINVAL;
+		if (ip->i_mount->m_sb.sb_blocksize != PAGE_SIZE)
+			return -EINVAL;
+	}
+
+	/* If the DAX state is not changing, we have nothing to do here. */
+	if ((fa->fsx_xflags & FS_XFLAG_DAX) && IS_DAX(inode))
+		return 0;
+	if (!(fa->fsx_xflags & FS_XFLAG_DAX) && !IS_DAX(inode))
+		return 0;
+
+	/* lock, flush and invalidate mapping in preparation for flag change */
+	xfs_ilock(ip, XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL);
+	error = filemap_write_and_wait(inode->i_mapping);
+	if (error)
+		goto out_unlock;
+	error = invalidate_inode_pages2(inode->i_mapping);
+	if (error)
+		goto out_unlock;
+
+	*join_flags = XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL;
 	return 0;
+
+out_unlock:
+	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL);
+	return error;
+
 }
 
 /*
@@ -1037,19 +1119,27 @@ xfs_ioctl_setattr_xflags(
  * have permission to do so. On success, return a clean transaction and the
  * inode locked exclusively ready for further operation specific checks. On
  * failure, return an error without modifying or locking the inode.
+ *
+ * The inode might already be IO locked on call. If this is the case, it is
+ * indicated in @join_flags and we take full responsibility for ensuring they
+ * are unlocked from now on. Hence if we have an error here, we still have to
+ * unlock them. Otherwise, once they are joined to the transaction, they will
+ * be unlocked on commit/cancel.
  */
 static struct xfs_trans *
 xfs_ioctl_setattr_get_trans(
-	struct xfs_inode	*ip)
+	struct xfs_inode	*ip,
+	int			join_flags)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
-	int			error;
+	int			error = -EROFS;
 
 	if (mp->m_flags & XFS_MOUNT_RDONLY)
-		return ERR_PTR(-EROFS);
+		goto out_unlock;
+	error = -EIO;
 	if (XFS_FORCED_SHUTDOWN(mp))
-		return ERR_PTR(-EIO);
+		goto out_unlock;
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
 	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
@@ -1057,7 +1147,8 @@ xfs_ioctl_setattr_get_trans(
 		goto out_cancel;
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | join_flags);
+	join_flags = 0;
 
 	/*
 	 * CAP_FOWNER overrides the following restrictions:
@@ -1077,6 +1168,9 @@ xfs_ioctl_setattr_get_trans(
 
 out_cancel:
 	xfs_trans_cancel(tp);
+out_unlock:
+	if (join_flags)
+		xfs_iunlock(ip, join_flags);
 	return ERR_PTR(error);
 }
 
@@ -1084,8 +1178,8 @@ out_cancel:
  * extent size hint validation is somewhat cumbersome. Rules are:
  *
  * 1. extent size hint is only valid for directories and regular files
- * 2. XFS_XFLAG_EXTSIZE is only valid for regular files
- * 3. XFS_XFLAG_EXTSZINHERIT is only valid for directories.
+ * 2. FS_XFLAG_EXTSIZE is only valid for regular files
+ * 3. FS_XFLAG_EXTSZINHERIT is only valid for directories.
  * 4. can only be changed on regular files if no extents are allocated
  * 5. can be changed on directories at any time
  * 6. extsize hint of 0 turns off hints, clears inode flags.
@@ -1101,14 +1195,14 @@ xfs_ioctl_setattr_check_extsize(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 
-	if ((fa->fsx_xflags & XFS_XFLAG_EXTSIZE) && !S_ISREG(ip->i_d.di_mode))
+	if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(VFS_I(ip)->i_mode))
 		return -EINVAL;
 
-	if ((fa->fsx_xflags & XFS_XFLAG_EXTSZINHERIT) &&
-	    !S_ISDIR(ip->i_d.di_mode))
+	if ((fa->fsx_xflags & FS_XFLAG_EXTSZINHERIT) &&
+	    !S_ISDIR(VFS_I(ip)->i_mode))
 		return -EINVAL;
 
-	if (S_ISREG(ip->i_d.di_mode) && ip->i_d.di_nextents &&
+	if (S_ISREG(VFS_I(ip)->i_mode) && ip->i_d.di_nextents &&
 	    ((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) != fa->fsx_extsize))
 		return -EINVAL;
 
@@ -1121,7 +1215,7 @@ xfs_ioctl_setattr_check_extsize(
 			return -EINVAL;
 
 		if (XFS_IS_REALTIME_INODE(ip) ||
-		    (fa->fsx_xflags & XFS_XFLAG_REALTIME)) {
+		    (fa->fsx_xflags & FS_XFLAG_REALTIME)) {
 			size = mp->m_sb.sb_rextsize << mp->m_sb.sb_blocklog;
 		} else {
 			size = mp->m_sb.sb_blocksize;
@@ -1132,7 +1226,7 @@ xfs_ioctl_setattr_check_extsize(
 		if (fa->fsx_extsize % size)
 			return -EINVAL;
 	} else
-		fa->fsx_xflags &= ~(XFS_XFLAG_EXTSIZE | XFS_XFLAG_EXTSZINHERIT);
+		fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE | FS_XFLAG_EXTSZINHERIT);
 
 	return 0;
 }
@@ -1157,7 +1251,7 @@ xfs_ioctl_setattr_check_projid(
 
 	if (xfs_get_projid(ip) != fa->fsx_projid)
 		return -EINVAL;
-	if ((fa->fsx_xflags & XFS_XFLAG_PROJINHERIT) !=
+	if ((fa->fsx_xflags & FS_XFLAG_PROJINHERIT) !=
 	    (ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT))
 		return -EINVAL;
 
@@ -1175,6 +1269,7 @@ xfs_ioctl_setattr(
 	struct xfs_dquot	*pdqp = NULL;
 	struct xfs_dquot	*olddquot = NULL;
 	int			code;
+	int			join_flags = 0;
 
 	trace_xfs_ioctl_setattr(ip);
 
@@ -1198,7 +1293,18 @@ xfs_ioctl_setattr(
 			return code;
 	}
 
-	tp = xfs_ioctl_setattr_get_trans(ip);
+	/*
+	 * Changing DAX config may require inode locking for mapping
+	 * invalidation. These need to be held all the way to transaction commit
+	 * or cancel time, so need to be passed through to
+	 * xfs_ioctl_setattr_get_trans() so it can apply them to the join call
+	 * appropriately.
+	 */
+	code = xfs_ioctl_setattr_dax_invalidate(ip, fa, &join_flags);
+	if (code)
+		goto error_free_dquots;
+
+	tp = xfs_ioctl_setattr_get_trans(ip, join_flags);
 	if (IS_ERR(tp)) {
 		code = PTR_ERR(tp);
 		goto error_free_dquots;
@@ -1229,9 +1335,9 @@ xfs_ioctl_setattr(
 	 * successful return from chown()
 	 */
 
-	if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
+	if ((VFS_I(ip)->i_mode & (S_ISUID|S_ISGID)) &&
 	    !capable_wrt_inode_uidgid(VFS_I(ip), CAP_FSETID))
-		ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);
+		VFS_I(ip)->i_mode &= ~(S_ISUID|S_ISGID);
 
 	/* Change the ownerships and register project quota modifications */
 	if (xfs_get_projid(ip) != fa->fsx_projid) {
@@ -1314,6 +1420,7 @@ xfs_ioc_setxflags(
 	struct xfs_trans	*tp;
 	struct fsxattr		fa;
 	unsigned int		flags;
+	int			join_flags = 0;
 	int			error;
 
 	if (copy_from_user(&flags, arg, sizeof(flags)))
@@ -1330,7 +1437,18 @@ xfs_ioc_setxflags(
 	if (error)
 		return error;
 
-	tp = xfs_ioctl_setattr_get_trans(ip);
+	/*
+	 * Changing DAX config may require inode locking for mapping
+	 * invalidation. These need to be held all the way to transaction commit
+	 * or cancel time, so need to be passed through to
+	 * xfs_ioctl_setattr_get_trans() so it can apply them to the join call
+	 * appropriately.
+	 */
+	error = xfs_ioctl_setattr_dax_invalidate(ip, &fa, &join_flags);
+	if (error)
+		goto out_drop_write;
+
+	tp = xfs_ioctl_setattr_get_trans(ip, join_flags);
 	if (IS_ERR(tp)) {
 		error = PTR_ERR(tp);
 		goto out_drop_write;
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index b88bdc85dd3d..1a05d8ae327d 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -356,7 +356,7 @@ xfs_compat_attrlist_by_handle(
 			   sizeof(compat_xfs_fsop_attrlist_handlereq_t)))
 		return -EFAULT;
 	if (al_hreq.buflen < sizeof(struct attrlist) ||
-	    al_hreq.buflen > XATTR_LIST_MAX)
+	    al_hreq.buflen > XFS_XATTR_LIST_MAX)
 		return -EINVAL;
 
 	/*
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 1f86033171c8..d81bdc080370 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -129,22 +129,31 @@ xfs_iomap_write_direct(
 	xfs_trans_t	*tp;
 	xfs_bmap_free_t free_list;
 	uint		qblocks, resblks, resrtextents;
-	int		committed;
 	int		error;
-
-	error = xfs_qm_dqattach(ip, 0);
-	if (error)
-		return error;
+	int		lockmode;
+	int		bmapi_flags = XFS_BMAPI_PREALLOC;
 
 	rt = XFS_IS_REALTIME_INODE(ip);
 	extsz = xfs_get_extsz_hint(ip);
+	lockmode = XFS_ILOCK_SHARED;	/* locked by caller */
+
+	ASSERT(xfs_isilocked(ip, lockmode));
 
 	offset_fsb = XFS_B_TO_FSBT(mp, offset);
 	last_fsb = XFS_B_TO_FSB(mp, ((xfs_ufsize_t)(offset + count)));
 	if ((offset + count) > XFS_ISIZE(ip)) {
+		/*
+		 * Assert that the in-core extent list is present since this can
+		 * call xfs_iread_extents() and we only have the ilock shared.
+		 * This should be safe because the lock was held around a bmapi
+		 * call in the caller and we only need it to access the in-core
+		 * list.
+		 */
+		ASSERT(XFS_IFORK_PTR(ip, XFS_DATA_FORK)->if_flags &
+								XFS_IFEXTENTS);
 		error = xfs_iomap_eof_align_last_fsb(mp, ip, extsz, &last_fsb);
 		if (error)
-			return error;
+			goto out_unlock;
 	} else {
 		if (nmaps && (imap->br_startblock == HOLESTARTBLOCK))
 			last_fsb = MIN(last_fsb, (xfs_fileoff_t)
@@ -174,9 +183,40 @@ xfs_iomap_write_direct(
 	}
 
 	/*
+	 * Drop the shared lock acquired by the caller, attach the dquot if
+	 * necessary and move on to transaction setup.
+	 */
+	xfs_iunlock(ip, lockmode);
+	error = xfs_qm_dqattach(ip, 0);
+	if (error)
+		return error;
+
+	/*
 	 * Allocate and setup the transaction
 	 */
 	tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
+
+	/*
+	 * For DAX, we do not allocate unwritten extents, but instead we zero
+	 * the block before we commit the transaction.  Ideally we'd like to do
+	 * this outside the transaction context, but if we commit and then crash
+	 * we may not have zeroed the blocks and this will be exposed on
+	 * recovery of the allocation. Hence we must zero before commit.
+	 *
+	 * Further, if we are mapping unwritten extents here, we need to zero
+	 * and convert them to written so that we don't need an unwritten extent
+	 * callback for DAX. This also means that we need to be able to dip into
+	 * the reserve block pool for bmbt block allocation if there is no space
+	 * left but we need to do unwritten extent conversion.
+	 */
+
+	if (IS_DAX(VFS_I(ip))) {
+		bmapi_flags = XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO;
+		if (ISUNWRITTEN(imap)) {
+			tp->t_flags |= XFS_TRANS_RESERVE;
+			resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0) << 1;
+		}
+	}
 	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write,
 				  resblks, resrtextents);
 	/*
@@ -187,7 +227,8 @@ xfs_iomap_write_direct(
 		return error;
 	}
 
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	lockmode = XFS_ILOCK_EXCL;
+	xfs_ilock(ip, lockmode);
 
 	error = xfs_trans_reserve_quota_nblks(tp, ip, qblocks, 0, quota_flag);
 	if (error)
@@ -202,17 +243,18 @@ xfs_iomap_write_direct(
 	xfs_bmap_init(&free_list, &firstfsb);
 	nimaps = 1;
 	error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
-				XFS_BMAPI_PREALLOC, &firstfsb, 0,
-				imap, &nimaps, &free_list);
+				bmapi_flags, &firstfsb, resblks, imap,
+				&nimaps, &free_list);
 	if (error)
 		goto out_bmap_cancel;
 
 	/*
 	 * Complete the transaction
 	 */
-	error = xfs_bmap_finish(&tp, &free_list, &committed);
+	error = xfs_bmap_finish(&tp, &free_list, NULL);
 	if (error)
 		goto out_bmap_cancel;
+
 	error = xfs_trans_commit(tp);
 	if (error)
 		goto out_unlock;
@@ -229,7 +271,7 @@ xfs_iomap_write_direct(
 		error = xfs_alert_fsblock_zero(ip, imap);
 
 out_unlock:
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	xfs_iunlock(ip, lockmode);
 	return error;
 
 out_bmap_cancel:
@@ -655,7 +697,7 @@ xfs_iomap_write_allocate(
 	xfs_bmap_free_t	free_list;
 	xfs_filblks_t	count_fsb;
 	xfs_trans_t	*tp;
-	int		nimaps, committed;
+	int		nimaps;
 	int		error = 0;
 	int		nres;
 
@@ -670,7 +712,7 @@ xfs_iomap_write_allocate(
 	count_fsb = imap->br_blockcount;
 	map_start_fsb = imap->br_startoff;
 
-	XFS_STATS_ADD(xs_xstrat_bytes, XFS_FSB_TO_B(mp, count_fsb));
+	XFS_STATS_ADD(mp, xs_xstrat_bytes, XFS_FSB_TO_B(mp, count_fsb));
 
 	while (count_fsb != 0) {
 		/*
@@ -750,13 +792,13 @@ xfs_iomap_write_allocate(
 			 * pointer that the caller gave to us.
 			 */
 			error = xfs_bmapi_write(tp, ip, map_start_fsb,
-						count_fsb, 0,
-						&first_block, 1,
-						imap, &nimaps, &free_list);
+						count_fsb, 0, &first_block,
+						nres, imap, &nimaps,
+						&free_list);
 			if (error)
 				goto trans_cancel;
 
-			error = xfs_bmap_finish(&tp, &free_list, &committed);
+			error = xfs_bmap_finish(&tp, &free_list, NULL);
 			if (error)
 				goto trans_cancel;
 
@@ -777,7 +819,7 @@ xfs_iomap_write_allocate(
 		if ((offset_fsb >= imap->br_startoff) &&
 		    (offset_fsb < (imap->br_startoff +
 				   imap->br_blockcount))) {
-			XFS_STATS_INC(xs_xstrat_quick);
+			XFS_STATS_INC(mp, xs_xstrat_quick);
 			return 0;
 		}
 
@@ -814,7 +856,6 @@ xfs_iomap_write_unwritten(
 	xfs_bmap_free_t free_list;
 	xfs_fsize_t	i_size;
 	uint		resblks;
-	int		committed;
 	int		error;
 
 	trace_xfs_unwritten_convert(ip, offset, count);
@@ -866,8 +907,8 @@ xfs_iomap_write_unwritten(
 		xfs_bmap_init(&free_list, &firstfsb);
 		nimaps = 1;
 		error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
-				  XFS_BMAPI_CONVERT, &firstfsb,
-				  1, &imap, &nimaps, &free_list);
+					XFS_BMAPI_CONVERT, &firstfsb, resblks,
+					&imap, &nimaps, &free_list);
 		if (error)
 			goto error_on_bmapi_transaction;
 
@@ -886,7 +927,7 @@ xfs_iomap_write_unwritten(
 			xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 		}
 
-		error = xfs_bmap_finish(&tp, &free_list, &committed);
+		error = xfs_bmap_finish(&tp, &free_list, NULL);
 		if (error)
 			goto error_on_bmapi_transaction;
 
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 8294132e6a3c..fb7dc61f4a29 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -414,13 +414,17 @@ xfs_vn_rename(
  * uio is kmalloced for this reason...
  */
 STATIC const char *
-xfs_vn_follow_link(
+xfs_vn_get_link(
 	struct dentry		*dentry,
-	void			**cookie)
+	struct inode		*inode,
+	struct delayed_call	*done)
 {
 	char			*link;
 	int			error = -ENOMEM;
 
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
 	link = kmalloc(MAXPATHLEN+1, GFP_KERNEL);
 	if (!link)
 		goto out_err;
@@ -429,7 +433,8 @@ xfs_vn_follow_link(
 	if (unlikely(error))
 		goto out_kfree;
 
-	return *cookie = link;
+	set_delayed_call(done, kfree_link, link);
+	return link;
 
  out_kfree:
 	kfree(link);
@@ -454,8 +459,8 @@ xfs_vn_getattr(
 
 	stat->size = XFS_ISIZE(ip);
 	stat->dev = inode->i_sb->s_dev;
-	stat->mode = ip->i_d.di_mode;
-	stat->nlink = ip->i_d.di_nlink;
+	stat->mode = inode->i_mode;
+	stat->nlink = inode->i_nlink;
 	stat->uid = inode->i_uid;
 	stat->gid = inode->i_gid;
 	stat->ino = ip->i_ino;
@@ -501,9 +506,6 @@ xfs_setattr_mode(
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 
-	ip->i_d.di_mode &= S_IFMT;
-	ip->i_d.di_mode |= mode & ~S_IFMT;
-
 	inode->i_mode &= S_IFMT;
 	inode->i_mode |= mode & ~S_IFMT;
 }
@@ -517,21 +519,12 @@ xfs_setattr_time(
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 
-	if (iattr->ia_valid & ATTR_ATIME) {
+	if (iattr->ia_valid & ATTR_ATIME)
 		inode->i_atime = iattr->ia_atime;
-		ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec;
-		ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec;
-	}
-	if (iattr->ia_valid & ATTR_CTIME) {
+	if (iattr->ia_valid & ATTR_CTIME)
 		inode->i_ctime = iattr->ia_ctime;
-		ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec;
-		ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec;
-	}
-	if (iattr->ia_valid & ATTR_MTIME) {
+	if (iattr->ia_valid & ATTR_MTIME)
 		inode->i_mtime = iattr->ia_mtime;
-		ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec;
-		ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec;
-	}
 }
 
 int
@@ -656,9 +649,9 @@ xfs_setattr_nonsize(
 		 * The set-user-ID and set-group-ID bits of a file will be
 		 * cleared upon successful return from chown()
 		 */
-		if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
+		if ((inode->i_mode & (S_ISUID|S_ISGID)) &&
 		    !capable(CAP_FSETID))
-			ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);
+			inode->i_mode &= ~(S_ISUID|S_ISGID);
 
 		/*
 		 * Change the ownerships and register quota modifications
@@ -695,7 +688,7 @@ xfs_setattr_nonsize(
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
-	XFS_STATS_INC(xs_ig_attrchg);
+	XFS_STATS_INC(mp, xs_ig_attrchg);
 
 	if (mp->m_flags & XFS_MOUNT_WSYNC)
 		xfs_trans_set_sync(tp);
@@ -768,7 +761,7 @@ xfs_setattr_size(
 
 	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
 	ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL));
-	ASSERT(S_ISREG(ip->i_d.di_mode));
+	ASSERT(S_ISREG(inode->i_mode));
 	ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
 		ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
 
@@ -922,7 +915,7 @@ xfs_setattr_size(
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
-	XFS_STATS_INC(xs_ig_attrchg);
+	XFS_STATS_INC(mp, xs_ig_attrchg);
 
 	if (mp->m_flags & XFS_MOUNT_WSYNC)
 		xfs_trans_set_sync(tp);
@@ -986,21 +979,13 @@ xfs_vn_update_time(
 	}
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	if (flags & S_CTIME) {
+	if (flags & S_CTIME)
 		inode->i_ctime = *now;
-		ip->i_d.di_ctime.t_sec = (__int32_t)now->tv_sec;
-		ip->i_d.di_ctime.t_nsec = (__int32_t)now->tv_nsec;
-	}
-	if (flags & S_MTIME) {
+	if (flags & S_MTIME)
 		inode->i_mtime = *now;
-		ip->i_d.di_mtime.t_sec = (__int32_t)now->tv_sec;
-		ip->i_d.di_mtime.t_nsec = (__int32_t)now->tv_nsec;
-	}
-	if (flags & S_ATIME) {
+	if (flags & S_ATIME)
 		inode->i_atime = *now;
-		ip->i_d.di_atime.t_sec = (__int32_t)now->tv_sec;
-		ip->i_d.di_atime.t_nsec = (__int32_t)now->tv_nsec;
-	}
+
 	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_TIMESTAMP);
 	return xfs_trans_commit(tp);
@@ -1172,8 +1157,7 @@ static const struct inode_operations xfs_dir_ci_inode_operations = {
 
 static const struct inode_operations xfs_symlink_inode_operations = {
 	.readlink		= generic_readlink,
-	.follow_link		= xfs_vn_follow_link,
-	.put_link		= kfree_put_link,
+	.get_link		= xfs_vn_get_link,
 	.getattr		= xfs_vn_getattr,
 	.setattr		= xfs_vn_setattr,
 	.setxattr		= generic_setxattr,
@@ -1201,8 +1185,10 @@ xfs_diflags_to_iflags(
 		inode->i_flags |= S_SYNC;
 	if (flags & XFS_DIFLAG_NOATIME)
 		inode->i_flags |= S_NOATIME;
-	/* XXX: Also needs an on-disk per inode flag! */
-	if (ip->i_mount->m_flags & XFS_MOUNT_DAX)
+	if (S_ISREG(inode->i_mode) &&
+	    ip->i_mount->m_sb.sb_blocksize == PAGE_SIZE &&
+	    (ip->i_mount->m_flags & XFS_MOUNT_DAX ||
+	     ip->i_d.di_flags2 & XFS_DIFLAG2_DAX))
 		inode->i_flags |= S_DAX;
 }
 
@@ -1228,8 +1214,6 @@ xfs_setup_inode(
 	/* make the inode look hashed for the writeback code */
 	hlist_add_fake(&inode->i_hash);
 
-	inode->i_mode	= ip->i_d.di_mode;
-	set_nlink(inode, ip->i_d.di_nlink);
 	inode->i_uid    = xfs_uid_to_kuid(ip->i_d.di_uid);
 	inode->i_gid    = xfs_gid_to_kgid(ip->i_d.di_gid);
 
@@ -1245,14 +1229,7 @@ xfs_setup_inode(
 		break;
 	}
 
-	inode->i_generation = ip->i_d.di_gen;
 	i_size_write(inode, ip->i_d.di_size);
-	inode->i_atime.tv_sec	= ip->i_d.di_atime.t_sec;
-	inode->i_atime.tv_nsec	= ip->i_d.di_atime.t_nsec;
-	inode->i_mtime.tv_sec	= ip->i_d.di_mtime.t_sec;
-	inode->i_mtime.tv_nsec	= ip->i_d.di_mtime.t_nsec;
-	inode->i_ctime.tv_sec	= ip->i_d.di_ctime.t_sec;
-	inode->i_ctime.tv_nsec	= ip->i_d.di_ctime.t_nsec;
 	xfs_diflags_to_iflags(inode, ip);
 
 	ip->d_ops = ip->i_mount->m_nondir_inode_ops;
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 930ebd86beba..ce73eb34620d 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -57,6 +57,7 @@ xfs_bulkstat_one_int(
 {
 	struct xfs_icdinode	*dic;		/* dinode core info pointer */
 	struct xfs_inode	*ip;		/* incore inode pointer */
+	struct inode		*inode;
 	struct xfs_bstat	*buf;		/* return buffer */
 	int			error = 0;	/* error value */
 
@@ -77,30 +78,33 @@ xfs_bulkstat_one_int(
 
 	ASSERT(ip != NULL);
 	ASSERT(ip->i_imap.im_blkno != 0);
+	inode = VFS_I(ip);
 
 	dic = &ip->i_d;
 
 	/* xfs_iget returns the following without needing
 	 * further change.
 	 */
-	buf->bs_nlink = dic->di_nlink;
 	buf->bs_projid_lo = dic->di_projid_lo;
 	buf->bs_projid_hi = dic->di_projid_hi;
 	buf->bs_ino = ino;
-	buf->bs_mode = dic->di_mode;
 	buf->bs_uid = dic->di_uid;
 	buf->bs_gid = dic->di_gid;
 	buf->bs_size = dic->di_size;
-	buf->bs_atime.tv_sec = dic->di_atime.t_sec;
-	buf->bs_atime.tv_nsec = dic->di_atime.t_nsec;
-	buf->bs_mtime.tv_sec = dic->di_mtime.t_sec;
-	buf->bs_mtime.tv_nsec = dic->di_mtime.t_nsec;
-	buf->bs_ctime.tv_sec = dic->di_ctime.t_sec;
-	buf->bs_ctime.tv_nsec = dic->di_ctime.t_nsec;
+
+	buf->bs_nlink = inode->i_nlink;
+	buf->bs_atime.tv_sec = inode->i_atime.tv_sec;
+	buf->bs_atime.tv_nsec = inode->i_atime.tv_nsec;
+	buf->bs_mtime.tv_sec = inode->i_mtime.tv_sec;
+	buf->bs_mtime.tv_nsec = inode->i_mtime.tv_nsec;
+	buf->bs_ctime.tv_sec = inode->i_ctime.tv_sec;
+	buf->bs_ctime.tv_nsec = inode->i_ctime.tv_nsec;
+	buf->bs_gen = inode->i_generation;
+	buf->bs_mode = inode->i_mode;
+
 	buf->bs_xflags = xfs_ip2xflags(ip);
 	buf->bs_extsize = dic->di_extsize << mp->m_sb.sb_blocklog;
 	buf->bs_extents = dic->di_nextents;
-	buf->bs_gen = dic->di_gen;
 	memset(buf->bs_pad, 0, sizeof(buf->bs_pad));
 	buf->bs_dmevmask = dic->di_dmevmask;
 	buf->bs_dmstate = dic->di_dmstate;
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index 85f883dd6207..a8192dc797dc 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -135,7 +135,7 @@ typedef __u32			xfs_nlink_t;
  * Size of block device i/o is parameterized here.
  * Currently the system supports page-sized i/o.
  */
-#define	BLKDEV_IOSHIFT		PAGE_CACHE_SHIFT
+#define	BLKDEV_IOSHIFT		PAGE_SHIFT
 #define	BLKDEV_IOSIZE		(1<<BLKDEV_IOSHIFT)
 /* number of BB's per block device block */
 #define	BLKDEV_BB		BTOBB(BLKDEV_IOSIZE)
@@ -171,6 +171,13 @@ struct xfs_kobj {
 	struct completion	complete;
 };
 
+struct xstats {
+	struct xfsstats __percpu	*xs_stats;
+	struct xfs_kobj			xs_kobj;
+};
+
+extern struct xstats xfsstats;
+
 /* Kernel uid/gid conversion. These are used to convert to/from the on disk
  * uid_t/gid_t types to the kuid_t/kgid_t types that the kernel uses internally.
  * The conversion here is type only, the value will remain the same since we
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index aaadee0969c9..b49ccf5c1d75 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -268,7 +268,7 @@ xlog_grant_head_wait(
 		__set_current_state(TASK_UNINTERRUPTIBLE);
 		spin_unlock(&head->lock);
 
-		XFS_STATS_INC(xs_sleep_logspace);
+		XFS_STATS_INC(log->l_mp, xs_sleep_logspace);
 
 		trace_xfs_log_grant_sleep(log, tic);
 		schedule();
@@ -379,7 +379,7 @@ xfs_log_regrant(
 	if (XLOG_FORCED_SHUTDOWN(log))
 		return -EIO;
 
-	XFS_STATS_INC(xs_try_logspace);
+	XFS_STATS_INC(mp, xs_try_logspace);
 
 	/*
 	 * This is a new transaction on the ticket, so we need to change the
@@ -448,7 +448,7 @@ xfs_log_reserve(
 	if (XLOG_FORCED_SHUTDOWN(log))
 		return -EIO;
 
-	XFS_STATS_INC(xs_try_logspace);
+	XFS_STATS_INC(mp, xs_try_logspace);
 
 	ASSERT(*ticp == NULL);
 	tic = xlog_ticket_alloc(log, unit_bytes, cnt, client, permanent,
@@ -1188,10 +1188,16 @@ xlog_iodone(xfs_buf_t *bp)
 	int			aborted = 0;
 
 	/*
-	 * Race to shutdown the filesystem if we see an error.
+	 * Race to shutdown the filesystem if we see an error or the iclog is in
+	 * IOABORT state. The IOABORT state is only set in DEBUG mode to inject
+	 * CRC errors into log recovery.
 	 */
-	if (XFS_TEST_ERROR(bp->b_error, l->l_mp,
-			XFS_ERRTAG_IODONE_IOERR, XFS_RANDOM_IODONE_IOERR)) {
+	if (XFS_TEST_ERROR(bp->b_error, l->l_mp, XFS_ERRTAG_IODONE_IOERR,
+			   XFS_RANDOM_IODONE_IOERR) ||
+	    iclog->ic_state & XLOG_STATE_IOABORT) {
+		if (iclog->ic_state & XLOG_STATE_IOABORT)
+			iclog->ic_state &= ~XLOG_STATE_IOABORT;
+
 		xfs_buf_ioerror_alert(bp, __func__);
 		xfs_buf_stale(bp);
 		xfs_force_shutdown(l->l_mp, SHUTDOWN_LOG_IO_ERROR);
@@ -1206,7 +1212,7 @@ xlog_iodone(xfs_buf_t *bp)
 	}
 
 	/* log I/O is always issued ASYNC */
-	ASSERT(XFS_BUF_ISASYNC(bp));
+	ASSERT(bp->b_flags & XBF_ASYNC);
 	xlog_state_done_syncing(iclog, aborted);
 
 	/*
@@ -1768,7 +1774,7 @@ xlog_sync(
 	int		v2 = xfs_sb_version_haslogv2(&log->l_mp->m_sb);
 	int		size;
 
-	XFS_STATS_INC(xs_log_writes);
+	XFS_STATS_INC(log->l_mp, xs_log_writes);
 	ASSERT(atomic_read(&iclog->ic_refcnt) == 0);
 
 	/* Add for LR header */
@@ -1805,7 +1811,7 @@ xlog_sync(
 	bp = iclog->ic_bp;
 	XFS_BUF_SET_ADDR(bp, BLOCK_LSN(be64_to_cpu(iclog->ic_header.h_lsn)));
 
-	XFS_STATS_ADD(xs_log_blocks, BTOBB(count));
+	XFS_STATS_ADD(log->l_mp, xs_log_blocks, BTOBB(count));
 
 	/* Do we need to split this write into 2 parts? */
 	if (XFS_BUF_ADDR(bp) + BTOBB(count) > log->l_logBBsize) {
@@ -1838,12 +1844,28 @@ xlog_sync(
 	/* calculcate the checksum */
 	iclog->ic_header.h_crc = xlog_cksum(log, &iclog->ic_header,
 					    iclog->ic_datap, size);
+#ifdef DEBUG
+	/*
+	 * Intentionally corrupt the log record CRC based on the error injection
+	 * frequency, if defined. This facilitates testing log recovery in the
+	 * event of torn writes. Hence, set the IOABORT state to abort the log
+	 * write on I/O completion and shutdown the fs. The subsequent mount
+	 * detects the bad CRC and attempts to recover.
+	 */
+	if (log->l_badcrc_factor &&
+	    (prandom_u32() % log->l_badcrc_factor == 0)) {
+		iclog->ic_header.h_crc &= 0xAAAAAAAA;
+		iclog->ic_state |= XLOG_STATE_IOABORT;
+		xfs_warn(log->l_mp,
+	"Intentionally corrupted log record at LSN 0x%llx. Shutdown imminent.",
+			 be64_to_cpu(iclog->ic_header.h_lsn));
+	}
+#endif
 
 	bp->b_io_length = BTOBB(count);
 	bp->b_fspriv = iclog;
-	XFS_BUF_ZEROFLAGS(bp);
-	XFS_BUF_ASYNC(bp);
-	bp->b_flags |= XBF_SYNCIO;
+	bp->b_flags &= ~(XBF_FUA | XBF_FLUSH);
+	bp->b_flags |= (XBF_ASYNC | XBF_SYNCIO | XBF_WRITE);
 
 	if (log->l_mp->m_flags & XFS_MOUNT_BARRIER) {
 		bp->b_flags |= XBF_FUA;
@@ -1870,12 +1892,11 @@ xlog_sync(
 
 	/* account for log which doesn't start at block #0 */
 	XFS_BUF_SET_ADDR(bp, XFS_BUF_ADDR(bp) + log->l_logBBstart);
+
 	/*
 	 * Don't call xfs_bwrite here. We do log-syncs even when the filesystem
 	 * is shutting down.
 	 */
-	XFS_BUF_WRITE(bp);
-
 	error = xlog_bdstrat(bp);
 	if (error) {
 		xfs_buf_ioerror_alert(bp, "xlog_sync");
@@ -1887,9 +1908,8 @@ xlog_sync(
 		xfs_buf_associate_memory(bp,
 				(char *)&iclog->ic_header + count, split);
 		bp->b_fspriv = iclog;
-		XFS_BUF_ZEROFLAGS(bp);
-		XFS_BUF_ASYNC(bp);
-		bp->b_flags |= XBF_SYNCIO;
+		bp->b_flags &= ~(XBF_FUA | XBF_FLUSH);
+		bp->b_flags |= (XBF_ASYNC | XBF_SYNCIO | XBF_WRITE);
 		if (log->l_mp->m_flags & XFS_MOUNT_BARRIER)
 			bp->b_flags |= XBF_FUA;
 
@@ -1898,7 +1918,6 @@ xlog_sync(
 
 		/* account for internal log which doesn't start at block #0 */
 		XFS_BUF_SET_ADDR(bp, XFS_BUF_ADDR(bp) + log->l_logBBstart);
-		XFS_BUF_WRITE(bp);
 		error = xlog_bdstrat(bp);
 		if (error) {
 			xfs_buf_ioerror_alert(bp, "xlog_sync (split)");
@@ -1989,75 +2008,81 @@ xlog_print_tic_res(
 	uint ophdr_spc = ticket->t_res_num_ophdrs * (uint)sizeof(xlog_op_header_t);
 
 	/* match with XLOG_REG_TYPE_* in xfs_log.h */
-	static char *res_type_str[XLOG_REG_TYPE_MAX] = {
-	    "bformat",
-	    "bchunk",
-	    "efi_format",
-	    "efd_format",
-	    "iformat",
-	    "icore",
-	    "iext",
-	    "ibroot",
-	    "ilocal",
-	    "iattr_ext",
-	    "iattr_broot",
-	    "iattr_local",
-	    "qformat",
-	    "dquot",
-	    "quotaoff",
-	    "LR header",
-	    "unmount",
-	    "commit",
-	    "trans header"
+#define REG_TYPE_STR(type, str)	[XLOG_REG_TYPE_##type] = str
+	static char *res_type_str[XLOG_REG_TYPE_MAX + 1] = {
+	    REG_TYPE_STR(BFORMAT, "bformat"),
+	    REG_TYPE_STR(BCHUNK, "bchunk"),
+	    REG_TYPE_STR(EFI_FORMAT, "efi_format"),
+	    REG_TYPE_STR(EFD_FORMAT, "efd_format"),
+	    REG_TYPE_STR(IFORMAT, "iformat"),
+	    REG_TYPE_STR(ICORE, "icore"),
+	    REG_TYPE_STR(IEXT, "iext"),
+	    REG_TYPE_STR(IBROOT, "ibroot"),
+	    REG_TYPE_STR(ILOCAL, "ilocal"),
+	    REG_TYPE_STR(IATTR_EXT, "iattr_ext"),
+	    REG_TYPE_STR(IATTR_BROOT, "iattr_broot"),
+	    REG_TYPE_STR(IATTR_LOCAL, "iattr_local"),
+	    REG_TYPE_STR(QFORMAT, "qformat"),
+	    REG_TYPE_STR(DQUOT, "dquot"),
+	    REG_TYPE_STR(QUOTAOFF, "quotaoff"),
+	    REG_TYPE_STR(LRHEADER, "LR header"),
+	    REG_TYPE_STR(UNMOUNT, "unmount"),
+	    REG_TYPE_STR(COMMIT, "commit"),
+	    REG_TYPE_STR(TRANSHDR, "trans header"),
+	    REG_TYPE_STR(ICREATE, "inode create")
 	};
+#undef REG_TYPE_STR
+#define TRANS_TYPE_STR(type)	[XFS_TRANS_##type] = #type
 	static char *trans_type_str[XFS_TRANS_TYPE_MAX] = {
-	    "SETATTR_NOT_SIZE",
-	    "SETATTR_SIZE",
-	    "INACTIVE",
-	    "CREATE",
-	    "CREATE_TRUNC",
-	    "TRUNCATE_FILE",
-	    "REMOVE",
-	    "LINK",
-	    "RENAME",
-	    "MKDIR",
-	    "RMDIR",
-	    "SYMLINK",
-	    "SET_DMATTRS",
-	    "GROWFS",
-	    "STRAT_WRITE",
-	    "DIOSTRAT",
-	    "WRITE_SYNC",
-	    "WRITEID",
-	    "ADDAFORK",
-	    "ATTRINVAL",
-	    "ATRUNCATE",
-	    "ATTR_SET",
-	    "ATTR_RM",
-	    "ATTR_FLAG",
-	    "CLEAR_AGI_BUCKET",
-	    "QM_SBCHANGE",
-	    "DUMMY1",
-	    "DUMMY2",
-	    "QM_QUOTAOFF",
-	    "QM_DQALLOC",
-	    "QM_SETQLIM",
-	    "QM_DQCLUSTER",
-	    "QM_QINOCREATE",
-	    "QM_QUOTAOFF_END",
-	    "SB_UNIT",
-	    "FSYNC_TS",
-	    "GROWFSRT_ALLOC",
-	    "GROWFSRT_ZERO",
-	    "GROWFSRT_FREE",
-	    "SWAPEXT"
+	    TRANS_TYPE_STR(SETATTR_NOT_SIZE),
+	    TRANS_TYPE_STR(SETATTR_SIZE),
+	    TRANS_TYPE_STR(INACTIVE),
+	    TRANS_TYPE_STR(CREATE),
+	    TRANS_TYPE_STR(CREATE_TRUNC),
+	    TRANS_TYPE_STR(TRUNCATE_FILE),
+	    TRANS_TYPE_STR(REMOVE),
+	    TRANS_TYPE_STR(LINK),
+	    TRANS_TYPE_STR(RENAME),
+	    TRANS_TYPE_STR(MKDIR),
+	    TRANS_TYPE_STR(RMDIR),
+	    TRANS_TYPE_STR(SYMLINK),
+	    TRANS_TYPE_STR(SET_DMATTRS),
+	    TRANS_TYPE_STR(GROWFS),
+	    TRANS_TYPE_STR(STRAT_WRITE),
+	    TRANS_TYPE_STR(DIOSTRAT),
+	    TRANS_TYPE_STR(WRITEID),
+	    TRANS_TYPE_STR(ADDAFORK),
+	    TRANS_TYPE_STR(ATTRINVAL),
+	    TRANS_TYPE_STR(ATRUNCATE),
+	    TRANS_TYPE_STR(ATTR_SET),
+	    TRANS_TYPE_STR(ATTR_RM),
+	    TRANS_TYPE_STR(ATTR_FLAG),
+	    TRANS_TYPE_STR(CLEAR_AGI_BUCKET),
+	    TRANS_TYPE_STR(SB_CHANGE),
+	    TRANS_TYPE_STR(DUMMY1),
+	    TRANS_TYPE_STR(DUMMY2),
+	    TRANS_TYPE_STR(QM_QUOTAOFF),
+	    TRANS_TYPE_STR(QM_DQALLOC),
+	    TRANS_TYPE_STR(QM_SETQLIM),
+	    TRANS_TYPE_STR(QM_DQCLUSTER),
+	    TRANS_TYPE_STR(QM_QINOCREATE),
+	    TRANS_TYPE_STR(QM_QUOTAOFF_END),
+	    TRANS_TYPE_STR(FSYNC_TS),
+	    TRANS_TYPE_STR(GROWFSRT_ALLOC),
+	    TRANS_TYPE_STR(GROWFSRT_ZERO),
+	    TRANS_TYPE_STR(GROWFSRT_FREE),
+	    TRANS_TYPE_STR(SWAPEXT),
+	    TRANS_TYPE_STR(CHECKPOINT),
+	    TRANS_TYPE_STR(ICREATE),
+	    TRANS_TYPE_STR(CREATE_TMPFILE)
 	};
+#undef TRANS_TYPE_STR
 
 	xfs_warn(mp, "xlog_write: reservation summary:");
 	xfs_warn(mp, "  trans type  = %s (%u)",
 		 ((ticket->t_trans_type <= 0 ||
 		   ticket->t_trans_type > XFS_TRANS_TYPE_MAX) ?
-		  "bad-trans-type" : trans_type_str[ticket->t_trans_type-1]),
+		  "bad-trans-type" : trans_type_str[ticket->t_trans_type]),
 		 ticket->t_trans_type);
 	xfs_warn(mp, "  unit res    = %d bytes",
 		 ticket->t_unit_res);
@@ -2076,7 +2101,7 @@ xlog_print_tic_res(
 		uint r_type = ticket->t_res_arr[i].r_type;
 		xfs_warn(mp, "region[%u]: %s - %u bytes", i,
 			    ((r_type <= 0 || r_type > XLOG_REG_TYPE_MAX) ?
-			    "bad-rtype" : res_type_str[r_type-1]),
+			    "bad-rtype" : res_type_str[r_type]),
 			    ticket->t_res_arr[i].r_len);
 	}
 
@@ -2422,11 +2447,20 @@ xlog_write(
 						     &partial_copy_len);
 			xlog_verify_dest_ptr(log, ptr);
 
-			/* copy region */
+			/*
+			 * Copy region.
+			 *
+			 * Unmount records just log an opheader, so can have
+			 * empty payloads with no data region to copy. Hence we
+			 * only copy the payload if the vector says it has data
+			 * to copy.
+			 */
 			ASSERT(copy_len >= 0);
-			memcpy(ptr, reg->i_addr + copy_off, copy_len);
-			xlog_write_adv_cnt(&ptr, &len, &log_offset, copy_len);
-
+			if (copy_len > 0) {
+				memcpy(ptr, reg->i_addr + copy_off, copy_len);
+				xlog_write_adv_cnt(&ptr, &len, &log_offset,
+						   copy_len);
+			}
 			copy_len += start_rec_copy + sizeof(xlog_op_header_t);
 			record_cnt++;
 			data_cnt += contwr ? copy_len : 0;
@@ -2782,11 +2816,19 @@ xlog_state_do_callback(
 		}
 	} while (!ioerrors && loopdidcallbacks);
 
+#ifdef DEBUG
 	/*
-	 * make one last gasp attempt to see if iclogs are being left in
-	 * limbo..
+	 * Make one last gasp attempt to see if iclogs are being left in limbo.
+	 * If the above loop finds an iclog earlier than the current iclog and
+	 * in one of the syncing states, the current iclog is put into
+	 * DO_CALLBACK and the callbacks are deferred to the completion of the
+	 * earlier iclog. Walk the iclogs in order and make sure that no iclog
+	 * is in DO_CALLBACK unless an earlier iclog is in one of the syncing
+	 * states.
+	 *
+	 * Note that SYNCING|IOABORT is a valid state so we cannot just check
+	 * for ic_state == SYNCING.
 	 */
-#ifdef DEBUG
 	if (funcdidcallbacks) {
 		first_iclog = iclog = log->l_iclog;
 		do {
@@ -2801,7 +2843,7 @@ xlog_state_do_callback(
 			 * IOERROR - give up hope all ye who enter here
 			 */
 			if (iclog->ic_state == XLOG_STATE_WANT_SYNC ||
-			    iclog->ic_state == XLOG_STATE_SYNCING ||
+			    iclog->ic_state & XLOG_STATE_SYNCING ||
 			    iclog->ic_state == XLOG_STATE_DONE_SYNC ||
 			    iclog->ic_state == XLOG_STATE_IOERROR )
 				break;
@@ -2913,7 +2955,7 @@ restart:
 
 	iclog = log->l_iclog;
 	if (iclog->ic_state != XLOG_STATE_ACTIVE) {
-		XFS_STATS_INC(xs_log_noiclogs);
+		XFS_STATS_INC(log->l_mp, xs_log_noiclogs);
 
 		/* Wait for log writes to have flushed */
 		xlog_wait(&log->l_flush_wait, &log->l_icloglock);
@@ -3165,11 +3207,19 @@ xlog_state_switch_iclogs(
 	}
 
 	if (log->l_curr_block >= log->l_logBBsize) {
+		/*
+		 * Rewind the current block before the cycle is bumped to make
+		 * sure that the combined LSN never transiently moves forward
+		 * when the log wraps to the next cycle. This is to support the
+		 * unlocked sample of these fields from xlog_valid_lsn(). Most
+		 * other cases should acquire l_icloglock.
+		 */
+		log->l_curr_block -= log->l_logBBsize;
+		ASSERT(log->l_curr_block >= 0);
+		smp_wmb();
 		log->l_curr_cycle++;
 		if (log->l_curr_cycle == XLOG_HEADER_MAGIC_NUM)
 			log->l_curr_cycle++;
-		log->l_curr_block -= log->l_logBBsize;
-		ASSERT(log->l_curr_block >= 0);
 	}
 	ASSERT(iclog == log->l_iclog);
 	log->l_iclog = iclog->ic_next;
@@ -3212,7 +3262,7 @@ _xfs_log_force(
 	struct xlog_in_core	*iclog;
 	xfs_lsn_t		lsn;
 
-	XFS_STATS_INC(xs_log_force);
+	XFS_STATS_INC(mp, xs_log_force);
 
 	xlog_cil_force(log);
 
@@ -3297,7 +3347,7 @@ maybe_sleep:
 			spin_unlock(&log->l_icloglock);
 			return -EIO;
 		}
-		XFS_STATS_INC(xs_log_force_sleep);
+		XFS_STATS_INC(mp, xs_log_force_sleep);
 		xlog_wait(&iclog->ic_force_wait, &log->l_icloglock);
 		/*
 		 * No need to grab the log lock here since we're
@@ -3362,7 +3412,7 @@ _xfs_log_force_lsn(
 
 	ASSERT(lsn != 0);
 
-	XFS_STATS_INC(xs_log_force);
+	XFS_STATS_INC(mp, xs_log_force);
 
 	lsn = xlog_cil_force_lsn(log, lsn);
 	if (lsn == NULLCOMMITLSN)
@@ -3411,7 +3461,7 @@ try_again:
 			     (XLOG_STATE_WANT_SYNC | XLOG_STATE_SYNCING))) {
 				ASSERT(!(iclog->ic_state & XLOG_STATE_IOERROR));
 
-				XFS_STATS_INC(xs_log_force_sleep);
+				XFS_STATS_INC(mp, xs_log_force_sleep);
 
 				xlog_wait(&iclog->ic_prev->ic_write_wait,
 							&log->l_icloglock);
@@ -3441,7 +3491,7 @@ try_again:
 				spin_unlock(&log->l_icloglock);
 				return -EIO;
 			}
-			XFS_STATS_INC(xs_log_force_sleep);
+			XFS_STATS_INC(mp, xs_log_force_sleep);
 			xlog_wait(&iclog->ic_force_wait, &log->l_icloglock);
 			/*
 			 * No need to grab the log lock here since we're
@@ -3929,7 +3979,7 @@ xfs_log_force_umount(
 	    log->l_flags & XLOG_ACTIVE_RECOVERY) {
 		mp->m_flags |= XFS_MOUNT_FS_SHUTDOWN;
 		if (mp->m_sb_bp)
-			XFS_BUF_DONE(mp->m_sb_bp);
+			mp->m_sb_bp->b_flags |= XBF_DONE;
 		return 0;
 	}
 
@@ -3959,7 +4009,7 @@ xfs_log_force_umount(
 	spin_lock(&log->l_icloglock);
 	mp->m_flags |= XFS_MOUNT_FS_SHUTDOWN;
 	if (mp->m_sb_bp)
-		XFS_BUF_DONE(mp->m_sb_bp);
+		mp->m_sb_bp->b_flags |= XBF_DONE;
 
 	/*
 	 * Mark the log and the iclogs with IO error flags to prevent any
@@ -4023,3 +4073,45 @@ xlog_iclogs_empty(
 	return 1;
 }
 
+/*
+ * Verify that an LSN stamped into a piece of metadata is valid. This is
+ * intended for use in read verifiers on v5 superblocks.
+ */
+bool
+xfs_log_check_lsn(
+	struct xfs_mount	*mp,
+	xfs_lsn_t		lsn)
+{
+	struct xlog		*log = mp->m_log;
+	bool			valid;
+
+	/*
+	 * norecovery mode skips mount-time log processing and unconditionally
+	 * resets the in-core LSN. We can't validate in this mode, but
+	 * modifications are not allowed anyways so just return true.
+	 */
+	if (mp->m_flags & XFS_MOUNT_NORECOVERY)
+		return true;
+
+	/*
+	 * Some metadata LSNs are initialized to NULL (e.g., the agfl). This is
+	 * handled by recovery and thus safe to ignore here.
+	 */
+	if (lsn == NULLCOMMITLSN)
+		return true;
+
+	valid = xlog_valid_lsn(mp->m_log, lsn);
+
+	/* warn the user about what's gone wrong before verifier failure */
+	if (!valid) {
+		spin_lock(&log->l_icloglock);
+		xfs_warn(mp,
+"Corruption warning: Metadata has LSN (%d:%d) ahead of current LSN (%d:%d). "
+"Please unmount and run xfs_repair (>= v4.3) to resolve.",
+			 CYCLE_LSN(lsn), BLOCK_LSN(lsn),
+			 log->l_curr_cycle, log->l_curr_block);
+		spin_unlock(&log->l_icloglock);
+	}
+
+	return valid;
+}
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index 09d91d3166cd..aa533a7d50f2 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -181,5 +181,6 @@ bool	xfs_log_item_in_current_chkpt(struct xfs_log_item *lip);
 void	xfs_log_work_queue(struct xfs_mount *mp);
 void	xfs_log_worker(struct work_struct *work);
 void	xfs_log_quiesce(struct xfs_mount *mp);
+bool	xfs_log_check_lsn(struct xfs_mount *, xfs_lsn_t);
 
 #endif	/* __XFS_LOG_H__ */
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index 950f3f94720c..ed8896310c00 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -62,6 +62,7 @@ static inline uint xlog_get_client_id(__be32 i)
 #define XLOG_STATE_CALLBACK  0x0020 /* Callback functions now */
 #define XLOG_STATE_DIRTY     0x0040 /* Dirty IC log, not ready for ACTIVE status*/
 #define XLOG_STATE_IOERROR   0x0080 /* IO error happened in sync'ing log */
+#define XLOG_STATE_IOABORT   0x0100 /* force abort on I/O completion (debug) */
 #define XLOG_STATE_ALL	     0x7FFF /* All possible valid flags */
 #define XLOG_STATE_NOTUSED   0x8000 /* This IC log not being used */
 
@@ -410,6 +411,8 @@ struct xlog {
 	/* The following field are used for debugging; need to hold icloglock */
 #ifdef DEBUG
 	void			*l_iclog_bak[XLOG_MAX_ICLOGS];
+	/* log record crc error injection factor */
+	uint32_t		l_badcrc_factor;
 #endif
 
 };
@@ -560,4 +563,55 @@ static inline void xlog_wait(wait_queue_head_t *wq, spinlock_t *lock)
 	remove_wait_queue(wq, &wait);
 }
 
+/*
+ * The LSN is valid so long as it is behind the current LSN. If it isn't, this
+ * means that the next log record that includes this metadata could have a
+ * smaller LSN. In turn, this means that the modification in the log would not
+ * replay.
+ */
+static inline bool
+xlog_valid_lsn(
+	struct xlog	*log,
+	xfs_lsn_t	lsn)
+{
+	int		cur_cycle;
+	int		cur_block;
+	bool		valid = true;
+
+	/*
+	 * First, sample the current lsn without locking to avoid added
+	 * contention from metadata I/O. The current cycle and block are updated
+	 * (in xlog_state_switch_iclogs()) and read here in a particular order
+	 * to avoid false negatives (e.g., thinking the metadata LSN is valid
+	 * when it is not).
+	 *
+	 * The current block is always rewound before the cycle is bumped in
+	 * xlog_state_switch_iclogs() to ensure the current LSN is never seen in
+	 * a transiently forward state. Instead, we can see the LSN in a
+	 * transiently behind state if we happen to race with a cycle wrap.
+	 */
+	cur_cycle = ACCESS_ONCE(log->l_curr_cycle);
+	smp_rmb();
+	cur_block = ACCESS_ONCE(log->l_curr_block);
+
+	if ((CYCLE_LSN(lsn) > cur_cycle) ||
+	    (CYCLE_LSN(lsn) == cur_cycle && BLOCK_LSN(lsn) > cur_block)) {
+		/*
+		 * If the metadata LSN appears invalid, it's possible the check
+		 * above raced with a wrap to the next log cycle. Grab the lock
+		 * to check for sure.
+		 */
+		spin_lock(&log->l_icloglock);
+		cur_cycle = log->l_curr_cycle;
+		cur_block = log->l_curr_block;
+		spin_unlock(&log->l_icloglock);
+
+		if ((CYCLE_LSN(lsn) > cur_cycle) ||
+		    (CYCLE_LSN(lsn) == cur_cycle && BLOCK_LSN(lsn) > cur_block))
+			valid = false;
+	}
+
+	return valid;
+}
+
 #endif	/* __XFS_LOG_PRIV_H__ */
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 512a0945d52a..396565f43247 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -61,6 +61,9 @@ xlog_recover_check_summary(
 #else
 #define	xlog_recover_check_summary(log)
 #endif
+STATIC int
+xlog_do_recovery_pass(
+        struct xlog *, xfs_daddr_t, xfs_daddr_t, int, xfs_daddr_t *);
 
 /*
  * This structure is used during recovery to record the buf log items which
@@ -187,7 +190,7 @@ xlog_bread_noalign(
 	ASSERT(nbblks <= bp->b_length);
 
 	XFS_BUF_SET_ADDR(bp, log->l_logBBstart + blk_no);
-	XFS_BUF_READ(bp);
+	bp->b_flags |= XBF_READ;
 	bp->b_io_length = nbblks;
 	bp->b_error = 0;
 
@@ -272,7 +275,6 @@ xlog_bwrite(
 	ASSERT(nbblks <= bp->b_length);
 
 	XFS_BUF_SET_ADDR(bp, log->l_logBBstart + blk_no);
-	XFS_BUF_ZEROFLAGS(bp);
 	xfs_buf_hold(bp);
 	xfs_buf_lock(bp);
 	bp->b_io_length = nbblks;
@@ -868,136 +870,365 @@ validate_head:
 }
 
 /*
- * Find the sync block number or the tail of the log.
- *
- * This will be the block number of the last record to have its
- * associated buffers synced to disk.  Every log record header has
- * a sync lsn embedded in it.  LSNs hold block numbers, so it is easy
- * to get a sync block number.  The only concern is to figure out which
- * log record header to believe.
- *
- * The following algorithm uses the log record header with the largest
- * lsn.  The entire log record does not need to be valid.  We only care
- * that the header is valid.
+ * Seek backwards in the log for log record headers.
  *
- * We could speed up search by using current head_blk buffer, but it is not
- * available.
+ * Given a starting log block, walk backwards until we find the provided number
+ * of records or hit the provided tail block. The return value is the number of
+ * records encountered or a negative error code. The log block and buffer
+ * pointer of the last record seen are returned in rblk and rhead respectively.
  */
 STATIC int
-xlog_find_tail(
+xlog_rseek_logrec_hdr(
 	struct xlog		*log,
-	xfs_daddr_t		*head_blk,
-	xfs_daddr_t		*tail_blk)
+	xfs_daddr_t		head_blk,
+	xfs_daddr_t		tail_blk,
+	int			count,
+	struct xfs_buf		*bp,
+	xfs_daddr_t		*rblk,
+	struct xlog_rec_header	**rhead,
+	bool			*wrapped)
 {
-	xlog_rec_header_t	*rhead;
-	xlog_op_header_t	*op_head;
+	int			i;
+	int			error;
+	int			found = 0;
 	char			*offset = NULL;
-	xfs_buf_t		*bp;
-	int			error, i, found;
-	xfs_daddr_t		umount_data_blk;
-	xfs_daddr_t		after_umount_blk;
-	xfs_lsn_t		tail_lsn;
-	int			hblks;
+	xfs_daddr_t		end_blk;
 
-	found = 0;
+	*wrapped = false;
 
 	/*
-	 * Find previous log record
+	 * Walk backwards from the head block until we hit the tail or the first
+	 * block in the log.
 	 */
-	if ((error = xlog_find_head(log, head_blk)))
-		return error;
-
-	bp = xlog_get_bp(log, 1);
-	if (!bp)
-		return -ENOMEM;
-	if (*head_blk == 0) {				/* special case */
-		error = xlog_bread(log, 0, 1, bp, &offset);
+	end_blk = head_blk > tail_blk ? tail_blk : 0;
+	for (i = (int) head_blk - 1; i >= end_blk; i--) {
+		error = xlog_bread(log, i, 1, bp, &offset);
 		if (error)
-			goto done;
+			goto out_error;
 
-		if (xlog_get_cycle(offset) == 0) {
-			*tail_blk = 0;
-			/* leave all other log inited values alone */
-			goto done;
+		if (*(__be32 *) offset == cpu_to_be32(XLOG_HEADER_MAGIC_NUM)) {
+			*rblk = i;
+			*rhead = (struct xlog_rec_header *) offset;
+			if (++found == count)
+				break;
 		}
 	}
 
 	/*
-	 * Search backwards looking for log record header block
+	 * If we haven't hit the tail block or the log record header count,
+	 * start looking again from the end of the physical log. Note that
+	 * callers can pass head == tail if the tail is not yet known.
 	 */
-	ASSERT(*head_blk < INT_MAX);
-	for (i = (int)(*head_blk) - 1; i >= 0; i--) {
+	if (tail_blk >= head_blk && found != count) {
+		for (i = log->l_logBBsize - 1; i >= (int) tail_blk; i--) {
+			error = xlog_bread(log, i, 1, bp, &offset);
+			if (error)
+				goto out_error;
+
+			if (*(__be32 *)offset ==
+			    cpu_to_be32(XLOG_HEADER_MAGIC_NUM)) {
+				*wrapped = true;
+				*rblk = i;
+				*rhead = (struct xlog_rec_header *) offset;
+				if (++found == count)
+					break;
+			}
+		}
+	}
+
+	return found;
+
+out_error:
+	return error;
+}
+
+/*
+ * Seek forward in the log for log record headers.
+ *
+ * Given head and tail blocks, walk forward from the tail block until we find
+ * the provided number of records or hit the head block. The return value is the
+ * number of records encountered or a negative error code. The log block and
+ * buffer pointer of the last record seen are returned in rblk and rhead
+ * respectively.
+ */
+STATIC int
+xlog_seek_logrec_hdr(
+	struct xlog		*log,
+	xfs_daddr_t		head_blk,
+	xfs_daddr_t		tail_blk,
+	int			count,
+	struct xfs_buf		*bp,
+	xfs_daddr_t		*rblk,
+	struct xlog_rec_header	**rhead,
+	bool			*wrapped)
+{
+	int			i;
+	int			error;
+	int			found = 0;
+	char			*offset = NULL;
+	xfs_daddr_t		end_blk;
+
+	*wrapped = false;
+
+	/*
+	 * Walk forward from the tail block until we hit the head or the last
+	 * block in the log.
+	 */
+	end_blk = head_blk > tail_blk ? head_blk : log->l_logBBsize - 1;
+	for (i = (int) tail_blk; i <= end_blk; i++) {
 		error = xlog_bread(log, i, 1, bp, &offset);
 		if (error)
-			goto done;
+			goto out_error;
 
-		if (*(__be32 *)offset == cpu_to_be32(XLOG_HEADER_MAGIC_NUM)) {
-			found = 1;
-			break;
+		if (*(__be32 *) offset == cpu_to_be32(XLOG_HEADER_MAGIC_NUM)) {
+			*rblk = i;
+			*rhead = (struct xlog_rec_header *) offset;
+			if (++found == count)
+				break;
 		}
 	}
+
 	/*
-	 * If we haven't found the log record header block, start looking
-	 * again from the end of the physical log.  XXXmiken: There should be
-	 * a check here to make sure we didn't search more than N blocks in
-	 * the previous code.
+	 * If we haven't hit the head block or the log record header count,
+	 * start looking again from the start of the physical log.
 	 */
-	if (!found) {
-		for (i = log->l_logBBsize - 1; i >= (int)(*head_blk); i--) {
+	if (tail_blk > head_blk && found != count) {
+		for (i = 0; i < (int) head_blk; i++) {
 			error = xlog_bread(log, i, 1, bp, &offset);
 			if (error)
-				goto done;
+				goto out_error;
 
 			if (*(__be32 *)offset ==
 			    cpu_to_be32(XLOG_HEADER_MAGIC_NUM)) {
-				found = 2;
-				break;
+				*wrapped = true;
+				*rblk = i;
+				*rhead = (struct xlog_rec_header *) offset;
+				if (++found == count)
+					break;
 			}
 		}
 	}
-	if (!found) {
-		xfs_warn(log->l_mp, "%s: couldn't find sync record", __func__);
-		xlog_put_bp(bp);
-		ASSERT(0);
-		return -EIO;
+
+	return found;
+
+out_error:
+	return error;
+}
+
+/*
+ * Check the log tail for torn writes. This is required when torn writes are
+ * detected at the head and the head had to be walked back to a previous record.
+ * The tail of the previous record must now be verified to ensure the torn
+ * writes didn't corrupt the previous tail.
+ *
+ * Return an error if CRC verification fails as recovery cannot proceed.
+ */
+STATIC int
+xlog_verify_tail(
+	struct xlog		*log,
+	xfs_daddr_t		head_blk,
+	xfs_daddr_t		tail_blk)
+{
+	struct xlog_rec_header	*thead;
+	struct xfs_buf		*bp;
+	xfs_daddr_t		first_bad;
+	int			count;
+	int			error = 0;
+	bool			wrapped;
+	xfs_daddr_t		tmp_head;
+
+	bp = xlog_get_bp(log, 1);
+	if (!bp)
+		return -ENOMEM;
+
+	/*
+	 * Seek XLOG_MAX_ICLOGS + 1 records past the current tail record to get
+	 * a temporary head block that points after the last possible
+	 * concurrently written record of the tail.
+	 */
+	count = xlog_seek_logrec_hdr(log, head_blk, tail_blk,
+				     XLOG_MAX_ICLOGS + 1, bp, &tmp_head, &thead,
+				     &wrapped);
+	if (count < 0) {
+		error = count;
+		goto out;
 	}
 
-	/* find blk_no of tail of log */
-	rhead = (xlog_rec_header_t *)offset;
-	*tail_blk = BLOCK_LSN(be64_to_cpu(rhead->h_tail_lsn));
+	/*
+	 * If the call above didn't find XLOG_MAX_ICLOGS + 1 records, we ran
+	 * into the actual log head. tmp_head points to the start of the record
+	 * so update it to the actual head block.
+	 */
+	if (count < XLOG_MAX_ICLOGS + 1)
+		tmp_head = head_blk;
 
 	/*
-	 * Reset log values according to the state of the log when we
-	 * crashed.  In the case where head_blk == 0, we bump curr_cycle
-	 * one because the next write starts a new cycle rather than
-	 * continuing the cycle of the last good log record.  At this
-	 * point we have guaranteed that all partial log records have been
-	 * accounted for.  Therefore, we know that the last good log record
-	 * written was complete and ended exactly on the end boundary
-	 * of the physical log.
+	 * We now have a tail and temporary head block that covers at least
+	 * XLOG_MAX_ICLOGS records from the tail. We need to verify that these
+	 * records were completely written. Run a CRC verification pass from
+	 * tail to head and return the result.
 	 */
-	log->l_prev_block = i;
-	log->l_curr_block = (int)*head_blk;
-	log->l_curr_cycle = be32_to_cpu(rhead->h_cycle);
-	if (found == 2)
-		log->l_curr_cycle++;
-	atomic64_set(&log->l_tail_lsn, be64_to_cpu(rhead->h_tail_lsn));
-	atomic64_set(&log->l_last_sync_lsn, be64_to_cpu(rhead->h_lsn));
-	xlog_assign_grant_head(&log->l_reserve_head.grant, log->l_curr_cycle,
-					BBTOB(log->l_curr_block));
-	xlog_assign_grant_head(&log->l_write_head.grant, log->l_curr_cycle,
-					BBTOB(log->l_curr_block));
+	error = xlog_do_recovery_pass(log, tmp_head, tail_blk,
+				      XLOG_RECOVER_CRCPASS, &first_bad);
+
+out:
+	xlog_put_bp(bp);
+	return error;
+}
+
+/*
+ * Detect and trim torn writes from the head of the log.
+ *
+ * Storage without sector atomicity guarantees can result in torn writes in the
+ * log in the event of a crash. Our only means to detect this scenario is via
+ * CRC verification. While we can't always be certain that CRC verification
+ * failure is due to a torn write vs. an unrelated corruption, we do know that
+ * only a certain number (XLOG_MAX_ICLOGS) of log records can be written out at
+ * one time. Therefore, CRC verify up to XLOG_MAX_ICLOGS records at the head of
+ * the log and treat failures in this range as torn writes as a matter of
+ * policy. In the event of CRC failure, the head is walked back to the last good
+ * record in the log and the tail is updated from that record and verified.
+ */
+STATIC int
+xlog_verify_head(
+	struct xlog		*log,
+	xfs_daddr_t		*head_blk,	/* in/out: unverified head */
+	xfs_daddr_t		*tail_blk,	/* out: tail block */
+	struct xfs_buf		*bp,
+	xfs_daddr_t		*rhead_blk,	/* start blk of last record */
+	struct xlog_rec_header	**rhead,	/* ptr to last record */
+	bool			*wrapped)	/* last rec. wraps phys. log */
+{
+	struct xlog_rec_header	*tmp_rhead;
+	struct xfs_buf		*tmp_bp;
+	xfs_daddr_t		first_bad;
+	xfs_daddr_t		tmp_rhead_blk;
+	int			found;
+	int			error;
+	bool			tmp_wrapped;
+
+	/*
+	 * Check the head of the log for torn writes. Search backwards from the
+	 * head until we hit the tail or the maximum number of log record I/Os
+	 * that could have been in flight at one time. Use a temporary buffer so
+	 * we don't trash the rhead/bp pointers from the caller.
+	 */
+	tmp_bp = xlog_get_bp(log, 1);
+	if (!tmp_bp)
+		return -ENOMEM;
+	error = xlog_rseek_logrec_hdr(log, *head_blk, *tail_blk,
+				      XLOG_MAX_ICLOGS, tmp_bp, &tmp_rhead_blk,
+				      &tmp_rhead, &tmp_wrapped);
+	xlog_put_bp(tmp_bp);
+	if (error < 0)
+		return error;
+
+	/*
+	 * Now run a CRC verification pass over the records starting at the
+	 * block found above to the current head. If a CRC failure occurs, the
+	 * log block of the first bad record is saved in first_bad.
+	 */
+	error = xlog_do_recovery_pass(log, *head_blk, tmp_rhead_blk,
+				      XLOG_RECOVER_CRCPASS, &first_bad);
+	if (error == -EFSBADCRC) {
+		/*
+		 * We've hit a potential torn write. Reset the error and warn
+		 * about it.
+		 */
+		error = 0;
+		xfs_warn(log->l_mp,
+"Torn write (CRC failure) detected at log block 0x%llx. Truncating head block from 0x%llx.",
+			 first_bad, *head_blk);
+
+		/*
+		 * Get the header block and buffer pointer for the last good
+		 * record before the bad record.
+		 *
+		 * Note that xlog_find_tail() clears the blocks at the new head
+		 * (i.e., the records with invalid CRC) if the cycle number
+		 * matches the the current cycle.
+		 */
+		found = xlog_rseek_logrec_hdr(log, first_bad, *tail_blk, 1, bp,
+					      rhead_blk, rhead, wrapped);
+		if (found < 0)
+			return found;
+		if (found == 0)		/* XXX: right thing to do here? */
+			return -EIO;
+
+		/*
+		 * Reset the head block to the starting block of the first bad
+		 * log record and set the tail block based on the last good
+		 * record.
+		 *
+		 * Bail out if the updated head/tail match as this indicates
+		 * possible corruption outside of the acceptable
+		 * (XLOG_MAX_ICLOGS) range. This is a job for xfs_repair...
+		 */
+		*head_blk = first_bad;
+		*tail_blk = BLOCK_LSN(be64_to_cpu((*rhead)->h_tail_lsn));
+		if (*head_blk == *tail_blk) {
+			ASSERT(0);
+			return 0;
+		}
+
+		/*
+		 * Now verify the tail based on the updated head. This is
+		 * required because the torn writes trimmed from the head could
+		 * have been written over the tail of a previous record. Return
+		 * any errors since recovery cannot proceed if the tail is
+		 * corrupt.
+		 *
+		 * XXX: This leaves a gap in truly robust protection from torn
+		 * writes in the log. If the head is behind the tail, the tail
+		 * pushes forward to create some space and then a crash occurs
+		 * causing the writes into the previous record's tail region to
+		 * tear, log recovery isn't able to recover.
+		 *
+		 * How likely is this to occur? If possible, can we do something
+		 * more intelligent here? Is it safe to push the tail forward if
+		 * we can determine that the tail is within the range of the
+		 * torn write (e.g., the kernel can only overwrite the tail if
+		 * it has actually been pushed forward)? Alternatively, could we
+		 * somehow prevent this condition at runtime?
+		 */
+		error = xlog_verify_tail(log, *head_blk, *tail_blk);
+	}
+
+	return error;
+}
+
+/*
+ * Check whether the head of the log points to an unmount record. In other
+ * words, determine whether the log is clean. If so, update the in-core state
+ * appropriately.
+ */
+static int
+xlog_check_unmount_rec(
+	struct xlog		*log,
+	xfs_daddr_t		*head_blk,
+	xfs_daddr_t		*tail_blk,
+	struct xlog_rec_header	*rhead,
+	xfs_daddr_t		rhead_blk,
+	struct xfs_buf		*bp,
+	bool			*clean)
+{
+	struct xlog_op_header	*op_head;
+	xfs_daddr_t		umount_data_blk;
+	xfs_daddr_t		after_umount_blk;
+	int			hblks;
+	int			error;
+	char			*offset;
+
+	*clean = false;
 
 	/*
-	 * Look for unmount record.  If we find it, then we know there
-	 * was a clean unmount.  Since 'i' could be the last block in
-	 * the physical log, we convert to a log block before comparing
-	 * to the head_blk.
+	 * Look for unmount record. If we find it, then we know there was a
+	 * clean unmount. Since 'i' could be the last block in the physical
+	 * log, we convert to a log block before comparing to the head_blk.
 	 *
-	 * Save the current tail lsn to use to pass to
-	 * xlog_clear_stale_blocks() below.  We won't want to clear the
-	 * unmount record if there is one, so we pass the lsn of the
-	 * unmount record rather than the block after it.
+	 * Save the current tail lsn to use to pass to xlog_clear_stale_blocks()
+	 * below. We won't want to clear the unmount record if there is one, so
+	 * we pass the lsn of the unmount record rather than the block after it.
 	 */
 	if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) {
 		int	h_size = be32_to_cpu(rhead->h_size);
@@ -1014,22 +1245,22 @@ xlog_find_tail(
 	} else {
 		hblks = 1;
 	}
-	after_umount_blk = (i + hblks + (int)
-		BTOBB(be32_to_cpu(rhead->h_len))) % log->l_logBBsize;
-	tail_lsn = atomic64_read(&log->l_tail_lsn);
+	after_umount_blk = rhead_blk + hblks + BTOBB(be32_to_cpu(rhead->h_len));
+	after_umount_blk = do_mod(after_umount_blk, log->l_logBBsize);
 	if (*head_blk == after_umount_blk &&
 	    be32_to_cpu(rhead->h_num_logops) == 1) {
-		umount_data_blk = (i + hblks) % log->l_logBBsize;
+		umount_data_blk = rhead_blk + hblks;
+		umount_data_blk = do_mod(umount_data_blk, log->l_logBBsize);
 		error = xlog_bread(log, umount_data_blk, 1, bp, &offset);
 		if (error)
-			goto done;
+			return error;
 
-		op_head = (xlog_op_header_t *)offset;
+		op_head = (struct xlog_op_header *)offset;
 		if (op_head->oh_flags & XLOG_UNMOUNT_TRANS) {
 			/*
-			 * Set tail and last sync so that newly written
-			 * log records will point recovery to after the
-			 * current unmount record.
+			 * Set tail and last sync so that newly written log
+			 * records will point recovery to after the current
+			 * unmount record.
 			 */
 			xlog_assign_atomic_lsn(&log->l_tail_lsn,
 					log->l_curr_cycle, after_umount_blk);
@@ -1037,17 +1268,167 @@ xlog_find_tail(
 					log->l_curr_cycle, after_umount_blk);
 			*tail_blk = after_umount_blk;
 
-			/*
-			 * Note that the unmount was clean. If the unmount
-			 * was not clean, we need to know this to rebuild the
-			 * superblock counters from the perag headers if we
-			 * have a filesystem using non-persistent counters.
-			 */
-			log->l_mp->m_flags |= XFS_MOUNT_WAS_CLEAN;
+			*clean = true;
+		}
+	}
+
+	return 0;
+}
+
+static void
+xlog_set_state(
+	struct xlog		*log,
+	xfs_daddr_t		head_blk,
+	struct xlog_rec_header	*rhead,
+	xfs_daddr_t		rhead_blk,
+	bool			bump_cycle)
+{
+	/*
+	 * Reset log values according to the state of the log when we
+	 * crashed.  In the case where head_blk == 0, we bump curr_cycle
+	 * one because the next write starts a new cycle rather than
+	 * continuing the cycle of the last good log record.  At this
+	 * point we have guaranteed that all partial log records have been
+	 * accounted for.  Therefore, we know that the last good log record
+	 * written was complete and ended exactly on the end boundary
+	 * of the physical log.
+	 */
+	log->l_prev_block = rhead_blk;
+	log->l_curr_block = (int)head_blk;
+	log->l_curr_cycle = be32_to_cpu(rhead->h_cycle);
+	if (bump_cycle)
+		log->l_curr_cycle++;
+	atomic64_set(&log->l_tail_lsn, be64_to_cpu(rhead->h_tail_lsn));
+	atomic64_set(&log->l_last_sync_lsn, be64_to_cpu(rhead->h_lsn));
+	xlog_assign_grant_head(&log->l_reserve_head.grant, log->l_curr_cycle,
+					BBTOB(log->l_curr_block));
+	xlog_assign_grant_head(&log->l_write_head.grant, log->l_curr_cycle,
+					BBTOB(log->l_curr_block));
+}
+
+/*
+ * Find the sync block number or the tail of the log.
+ *
+ * This will be the block number of the last record to have its
+ * associated buffers synced to disk.  Every log record header has
+ * a sync lsn embedded in it.  LSNs hold block numbers, so it is easy
+ * to get a sync block number.  The only concern is to figure out which
+ * log record header to believe.
+ *
+ * The following algorithm uses the log record header with the largest
+ * lsn.  The entire log record does not need to be valid.  We only care
+ * that the header is valid.
+ *
+ * We could speed up search by using current head_blk buffer, but it is not
+ * available.
+ */
+STATIC int
+xlog_find_tail(
+	struct xlog		*log,
+	xfs_daddr_t		*head_blk,
+	xfs_daddr_t		*tail_blk)
+{
+	xlog_rec_header_t	*rhead;
+	char			*offset = NULL;
+	xfs_buf_t		*bp;
+	int			error;
+	xfs_daddr_t		rhead_blk;
+	xfs_lsn_t		tail_lsn;
+	bool			wrapped = false;
+	bool			clean = false;
+
+	/*
+	 * Find previous log record
+	 */
+	if ((error = xlog_find_head(log, head_blk)))
+		return error;
+	ASSERT(*head_blk < INT_MAX);
+
+	bp = xlog_get_bp(log, 1);
+	if (!bp)
+		return -ENOMEM;
+	if (*head_blk == 0) {				/* special case */
+		error = xlog_bread(log, 0, 1, bp, &offset);
+		if (error)
+			goto done;
+
+		if (xlog_get_cycle(offset) == 0) {
+			*tail_blk = 0;
+			/* leave all other log inited values alone */
+			goto done;
+		}
+	}
+
+	/*
+	 * Search backwards through the log looking for the log record header
+	 * block. This wraps all the way back around to the head so something is
+	 * seriously wrong if we can't find it.
+	 */
+	error = xlog_rseek_logrec_hdr(log, *head_blk, *head_blk, 1, bp,
+				      &rhead_blk, &rhead, &wrapped);
+	if (error < 0)
+		return error;
+	if (!error) {
+		xfs_warn(log->l_mp, "%s: couldn't find sync record", __func__);
+		return -EIO;
+	}
+	*tail_blk = BLOCK_LSN(be64_to_cpu(rhead->h_tail_lsn));
+
+	/*
+	 * Set the log state based on the current head record.
+	 */
+	xlog_set_state(log, *head_blk, rhead, rhead_blk, wrapped);
+	tail_lsn = atomic64_read(&log->l_tail_lsn);
+
+	/*
+	 * Look for an unmount record at the head of the log. This sets the log
+	 * state to determine whether recovery is necessary.
+	 */
+	error = xlog_check_unmount_rec(log, head_blk, tail_blk, rhead,
+				       rhead_blk, bp, &clean);
+	if (error)
+		goto done;
+
+	/*
+	 * Verify the log head if the log is not clean (e.g., we have anything
+	 * but an unmount record at the head). This uses CRC verification to
+	 * detect and trim torn writes. If discovered, CRC failures are
+	 * considered torn writes and the log head is trimmed accordingly.
+	 *
+	 * Note that we can only run CRC verification when the log is dirty
+	 * because there's no guarantee that the log data behind an unmount
+	 * record is compatible with the current architecture.
+	 */
+	if (!clean) {
+		xfs_daddr_t	orig_head = *head_blk;
+
+		error = xlog_verify_head(log, head_blk, tail_blk, bp,
+					 &rhead_blk, &rhead, &wrapped);
+		if (error)
+			goto done;
+
+		/* update in-core state again if the head changed */
+		if (*head_blk != orig_head) {
+			xlog_set_state(log, *head_blk, rhead, rhead_blk,
+				       wrapped);
+			tail_lsn = atomic64_read(&log->l_tail_lsn);
+			error = xlog_check_unmount_rec(log, head_blk, tail_blk,
+						       rhead, rhead_blk, bp,
+						       &clean);
+			if (error)
+				goto done;
 		}
 	}
 
 	/*
+	 * Note that the unmount was clean. If the unmount was not clean, we
+	 * need to know this to rebuild the superblock counters from the perag
+	 * headers if we have a filesystem using non-persistent counters.
+	 */
+	if (clean)
+		log->l_mp->m_flags |= XFS_MOUNT_WAS_CLEAN;
+
+	/*
 	 * Make sure that there are no blocks in front of the head
 	 * with the same cycle number as the head.  This can happen
 	 * because we allow multiple outstanding log writes concurrently,
@@ -2156,6 +2537,13 @@ xlog_recover_validate_buf_type(
 		}
 		bp->b_ops = &xfs_sb_buf_ops;
 		break;
+#ifdef CONFIG_XFS_RT
+	case XFS_BLFT_RTBITMAP_BUF:
+	case XFS_BLFT_RTSUMMARY_BUF:
+		/* no magic numbers for verification of RT buffers */
+		bp->b_ops = &xfs_rtbuf_ops;
+		break;
+#endif /* CONFIG_XFS_RT */
 	default:
 		xfs_warn(mp, "Unknown buffer type %d!",
 			 xfs_blft_from_flags(buf_f));
@@ -2476,7 +2864,7 @@ xfs_recover_inode_owner_change(
 		return -ENOMEM;
 
 	/* instantiate the inode */
-	xfs_dinode_from_disk(&ip->i_d, dip);
+	xfs_inode_from_disk(ip, dip);
 	ASSERT(ip->i_d.di_version >= 3);
 
 	error = xfs_iformat_fork(ip, dip);
@@ -2522,7 +2910,7 @@ xlog_recover_inode_pass2(
 	int			error;
 	int			attr_index;
 	uint			fields;
-	xfs_icdinode_t		*dicp;
+	struct xfs_log_dinode	*ldip;
 	uint			isize;
 	int			need_free = 0;
 
@@ -2575,8 +2963,8 @@ xlog_recover_inode_pass2(
 		error = -EFSCORRUPTED;
 		goto out_release;
 	}
-	dicp = item->ri_buf[1].i_addr;
-	if (unlikely(dicp->di_magic != XFS_DINODE_MAGIC)) {
+	ldip = item->ri_buf[1].i_addr;
+	if (unlikely(ldip->di_magic != XFS_DINODE_MAGIC)) {
 		xfs_alert(mp,
 			"%s: Bad inode log record, rec ptr 0x%p, ino %Ld",
 			__func__, item, in_f->ilf_ino);
@@ -2612,13 +3000,13 @@ xlog_recover_inode_pass2(
 	 * to skip replay when the on disk inode is newer than the log one
 	 */
 	if (!xfs_sb_version_hascrc(&mp->m_sb) &&
-	    dicp->di_flushiter < be16_to_cpu(dip->di_flushiter)) {
+	    ldip->di_flushiter < be16_to_cpu(dip->di_flushiter)) {
 		/*
 		 * Deal with the wrap case, DI_MAX_FLUSH is less
 		 * than smaller numbers
 		 */
 		if (be16_to_cpu(dip->di_flushiter) == DI_MAX_FLUSH &&
-		    dicp->di_flushiter < (DI_MAX_FLUSH >> 1)) {
+		    ldip->di_flushiter < (DI_MAX_FLUSH >> 1)) {
 			/* do nothing */
 		} else {
 			trace_xfs_log_recover_inode_skip(log, in_f);
@@ -2628,13 +3016,13 @@ xlog_recover_inode_pass2(
 	}
 
 	/* Take the opportunity to reset the flush iteration count */
-	dicp->di_flushiter = 0;
+	ldip->di_flushiter = 0;
 
-	if (unlikely(S_ISREG(dicp->di_mode))) {
-		if ((dicp->di_format != XFS_DINODE_FMT_EXTENTS) &&
-		    (dicp->di_format != XFS_DINODE_FMT_BTREE)) {
+	if (unlikely(S_ISREG(ldip->di_mode))) {
+		if ((ldip->di_format != XFS_DINODE_FMT_EXTENTS) &&
+		    (ldip->di_format != XFS_DINODE_FMT_BTREE)) {
 			XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(3)",
-					 XFS_ERRLEVEL_LOW, mp, dicp);
+					 XFS_ERRLEVEL_LOW, mp, ldip);
 			xfs_alert(mp,
 		"%s: Bad regular inode log record, rec ptr 0x%p, "
 		"ino ptr = 0x%p, ino bp = 0x%p, ino %Ld",
@@ -2642,12 +3030,12 @@ xlog_recover_inode_pass2(
 			error = -EFSCORRUPTED;
 			goto out_release;
 		}
-	} else if (unlikely(S_ISDIR(dicp->di_mode))) {
-		if ((dicp->di_format != XFS_DINODE_FMT_EXTENTS) &&
-		    (dicp->di_format != XFS_DINODE_FMT_BTREE) &&
-		    (dicp->di_format != XFS_DINODE_FMT_LOCAL)) {
+	} else if (unlikely(S_ISDIR(ldip->di_mode))) {
+		if ((ldip->di_format != XFS_DINODE_FMT_EXTENTS) &&
+		    (ldip->di_format != XFS_DINODE_FMT_BTREE) &&
+		    (ldip->di_format != XFS_DINODE_FMT_LOCAL)) {
 			XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(4)",
-					     XFS_ERRLEVEL_LOW, mp, dicp);
+					     XFS_ERRLEVEL_LOW, mp, ldip);
 			xfs_alert(mp,
 		"%s: Bad dir inode log record, rec ptr 0x%p, "
 		"ino ptr = 0x%p, ino bp = 0x%p, ino %Ld",
@@ -2656,32 +3044,32 @@ xlog_recover_inode_pass2(
 			goto out_release;
 		}
 	}
-	if (unlikely(dicp->di_nextents + dicp->di_anextents > dicp->di_nblocks)){
+	if (unlikely(ldip->di_nextents + ldip->di_anextents > ldip->di_nblocks)){
 		XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(5)",
-				     XFS_ERRLEVEL_LOW, mp, dicp);
+				     XFS_ERRLEVEL_LOW, mp, ldip);
 		xfs_alert(mp,
 	"%s: Bad inode log record, rec ptr 0x%p, dino ptr 0x%p, "
 	"dino bp 0x%p, ino %Ld, total extents = %d, nblocks = %Ld",
 			__func__, item, dip, bp, in_f->ilf_ino,
-			dicp->di_nextents + dicp->di_anextents,
-			dicp->di_nblocks);
+			ldip->di_nextents + ldip->di_anextents,
+			ldip->di_nblocks);
 		error = -EFSCORRUPTED;
 		goto out_release;
 	}
-	if (unlikely(dicp->di_forkoff > mp->m_sb.sb_inodesize)) {
+	if (unlikely(ldip->di_forkoff > mp->m_sb.sb_inodesize)) {
 		XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(6)",
-				     XFS_ERRLEVEL_LOW, mp, dicp);
+				     XFS_ERRLEVEL_LOW, mp, ldip);
 		xfs_alert(mp,
 	"%s: Bad inode log record, rec ptr 0x%p, dino ptr 0x%p, "
 	"dino bp 0x%p, ino %Ld, forkoff 0x%x", __func__,
-			item, dip, bp, in_f->ilf_ino, dicp->di_forkoff);
+			item, dip, bp, in_f->ilf_ino, ldip->di_forkoff);
 		error = -EFSCORRUPTED;
 		goto out_release;
 	}
-	isize = xfs_icdinode_size(dicp->di_version);
+	isize = xfs_log_dinode_size(ldip->di_version);
 	if (unlikely(item->ri_buf[1].i_len > isize)) {
 		XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(7)",
-				     XFS_ERRLEVEL_LOW, mp, dicp);
+				     XFS_ERRLEVEL_LOW, mp, ldip);
 		xfs_alert(mp,
 			"%s: Bad inode log record length %d, rec ptr 0x%p",
 			__func__, item->ri_buf[1].i_len, item);
@@ -2689,8 +3077,8 @@ xlog_recover_inode_pass2(
 		goto out_release;
 	}
 
-	/* The core is in in-core format */
-	xfs_dinode_to_disk(dip, dicp);
+	/* recover the log dinode inode into the on disk inode */
+	xfs_log_dinode_to_disk(ldip, dip);
 
 	/* the rest is in on-disk format */
 	if (item->ri_buf[1].i_len > isize) {
@@ -3204,6 +3592,7 @@ xlog_recover_dquot_ra_pass2(
 	struct xfs_disk_dquot	*recddq;
 	struct xfs_dq_logformat	*dq_f;
 	uint			type;
+	int			len;
 
 
 	if (mp->m_qflags == 0)
@@ -3224,8 +3613,12 @@ xlog_recover_dquot_ra_pass2(
 	ASSERT(dq_f);
 	ASSERT(dq_f->qlf_len == 1);
 
-	xfs_buf_readahead(mp->m_ddev_targp, dq_f->qlf_blkno,
-			  XFS_FSB_TO_BB(mp, dq_f->qlf_len), NULL);
+	len = XFS_FSB_TO_BB(mp, dq_f->qlf_len);
+	if (xlog_peek_buffer_cancelled(log, dq_f->qlf_blkno, len, 0))
+		return;
+
+	xfs_buf_readahead(mp->m_ddev_targp, dq_f->qlf_blkno, len,
+			  &xfs_dquot_buf_ra_ops);
 }
 
 STATIC void
@@ -3431,7 +3824,7 @@ xlog_recover_add_to_cont_trans(
 	 * previous record. Copy the rest of the header.
 	 */
 	if (list_empty(&trans->r_itemq)) {
-		ASSERT(len < sizeof(struct xfs_trans_header));
+		ASSERT(len <= sizeof(struct xfs_trans_header));
 		if (len > sizeof(struct xfs_trans_header)) {
 			xfs_warn(log->l_mp, "%s: bad header length", __func__);
 			return -EIO;
@@ -4015,8 +4408,8 @@ xlog_recover_process_one_iunlink(
 	if (error)
 		goto fail_iput;
 
-	ASSERT(ip->i_d.di_nlink == 0);
-	ASSERT(ip->i_d.di_mode != 0);
+	ASSERT(VFS_I(ip)->i_nlink == 0);
+	ASSERT(VFS_I(ip)->i_mode != 0);
 
 	/* setup for the next pass */
 	agino = be32_to_cpu(dip->di_next_unlinked);
@@ -4118,25 +4511,68 @@ xlog_recover_process_iunlinks(
 	mp->m_dmevmask = mp_dmevmask;
 }
 
+STATIC int
+xlog_unpack_data(
+	struct xlog_rec_header	*rhead,
+	char			*dp,
+	struct xlog		*log)
+{
+	int			i, j, k;
+
+	for (i = 0; i < BTOBB(be32_to_cpu(rhead->h_len)) &&
+		  i < (XLOG_HEADER_CYCLE_SIZE / BBSIZE); i++) {
+		*(__be32 *)dp = *(__be32 *)&rhead->h_cycle_data[i];
+		dp += BBSIZE;
+	}
+
+	if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) {
+		xlog_in_core_2_t *xhdr = (xlog_in_core_2_t *)rhead;
+		for ( ; i < BTOBB(be32_to_cpu(rhead->h_len)); i++) {
+			j = i / (XLOG_HEADER_CYCLE_SIZE / BBSIZE);
+			k = i % (XLOG_HEADER_CYCLE_SIZE / BBSIZE);
+			*(__be32 *)dp = xhdr[j].hic_xheader.xh_cycle_data[k];
+			dp += BBSIZE;
+		}
+	}
+
+	return 0;
+}
+
 /*
- * Upack the log buffer data and crc check it. If the check fails, issue a
- * warning if and only if the CRC in the header is non-zero. This makes the
- * check an advisory warning, and the zero CRC check will prevent failure
- * warnings from being emitted when upgrading the kernel from one that does not
- * add CRCs by default.
- *
- * When filesystems are CRC enabled, this CRC mismatch becomes a fatal log
- * corruption failure
+ * CRC check, unpack and process a log record.
  */
 STATIC int
-xlog_unpack_data_crc(
+xlog_recover_process(
+	struct xlog		*log,
+	struct hlist_head	rhash[],
 	struct xlog_rec_header	*rhead,
 	char			*dp,
-	struct xlog		*log)
+	int			pass)
 {
+	int			error;
 	__le32			crc;
 
 	crc = xlog_cksum(log, rhead, dp, be32_to_cpu(rhead->h_len));
+
+	/*
+	 * Nothing else to do if this is a CRC verification pass. Just return
+	 * if this a record with a non-zero crc. Unfortunately, mkfs always
+	 * sets h_crc to 0 so we must consider this valid even on v5 supers.
+	 * Otherwise, return EFSBADCRC on failure so the callers up the stack
+	 * know precisely what failed.
+	 */
+	if (pass == XLOG_RECOVER_CRCPASS) {
+		if (rhead->h_crc && crc != rhead->h_crc)
+			return -EFSBADCRC;
+		return 0;
+	}
+
+	/*
+	 * We're in the normal recovery path. Issue a warning if and only if the
+	 * CRC in the header is non-zero. This is an advisory warning and the
+	 * zero CRC check prevents warnings from being emitted when upgrading
+	 * the kernel from one that does not add CRCs by default.
+	 */
 	if (crc != rhead->h_crc) {
 		if (rhead->h_crc || xfs_sb_version_hascrc(&log->l_mp->m_sb)) {
 			xfs_alert(log->l_mp,
@@ -4147,47 +4583,18 @@ xlog_unpack_data_crc(
 		}
 
 		/*
-		 * If we've detected a log record corruption, then we can't
-		 * recover past this point. Abort recovery if we are enforcing
-		 * CRC protection by punting an error back up the stack.
+		 * If the filesystem is CRC enabled, this mismatch becomes a
+		 * fatal log corruption failure.
 		 */
 		if (xfs_sb_version_hascrc(&log->l_mp->m_sb))
 			return -EFSCORRUPTED;
 	}
 
-	return 0;
-}
-
-STATIC int
-xlog_unpack_data(
-	struct xlog_rec_header	*rhead,
-	char			*dp,
-	struct xlog		*log)
-{
-	int			i, j, k;
-	int			error;
-
-	error = xlog_unpack_data_crc(rhead, dp, log);
+	error = xlog_unpack_data(rhead, dp, log);
 	if (error)
 		return error;
 
-	for (i = 0; i < BTOBB(be32_to_cpu(rhead->h_len)) &&
-		  i < (XLOG_HEADER_CYCLE_SIZE / BBSIZE); i++) {
-		*(__be32 *)dp = *(__be32 *)&rhead->h_cycle_data[i];
-		dp += BBSIZE;
-	}
-
-	if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) {
-		xlog_in_core_2_t *xhdr = (xlog_in_core_2_t *)rhead;
-		for ( ; i < BTOBB(be32_to_cpu(rhead->h_len)); i++) {
-			j = i / (XLOG_HEADER_CYCLE_SIZE / BBSIZE);
-			k = i % (XLOG_HEADER_CYCLE_SIZE / BBSIZE);
-			*(__be32 *)dp = xhdr[j].hic_xheader.xh_cycle_data[k];
-			dp += BBSIZE;
-		}
-	}
-
-	return 0;
+	return xlog_recover_process_data(log, rhash, rhead, dp, pass);
 }
 
 STATIC int
@@ -4239,18 +4646,21 @@ xlog_do_recovery_pass(
 	struct xlog		*log,
 	xfs_daddr_t		head_blk,
 	xfs_daddr_t		tail_blk,
-	int			pass)
+	int			pass,
+	xfs_daddr_t		*first_bad)	/* out: first bad log rec */
 {
 	xlog_rec_header_t	*rhead;
 	xfs_daddr_t		blk_no;
+	xfs_daddr_t		rhead_blk;
 	char			*offset;
 	xfs_buf_t		*hbp, *dbp;
-	int			error = 0, h_size;
+	int			error = 0, h_size, h_len;
 	int			bblks, split_bblks;
 	int			hblks, split_hblks, wrapped_hblks;
 	struct hlist_head	rhash[XLOG_RHASH_SIZE];
 
 	ASSERT(head_blk != tail_blk);
+	rhead_blk = 0;
 
 	/*
 	 * Read the header of the tail block and get the iclog buffer size from
@@ -4274,7 +4684,31 @@ xlog_do_recovery_pass(
 		error = xlog_valid_rec_header(log, rhead, tail_blk);
 		if (error)
 			goto bread_err1;
+
+		/*
+		 * xfsprogs has a bug where record length is based on lsunit but
+		 * h_size (iclog size) is hardcoded to 32k. Now that we
+		 * unconditionally CRC verify the unmount record, this means the
+		 * log buffer can be too small for the record and cause an
+		 * overrun.
+		 *
+		 * Detect this condition here. Use lsunit for the buffer size as
+		 * long as this looks like the mkfs case. Otherwise, return an
+		 * error to avoid a buffer overrun.
+		 */
 		h_size = be32_to_cpu(rhead->h_size);
+		h_len = be32_to_cpu(rhead->h_len);
+		if (h_len > h_size) {
+			if (h_len <= log->l_mp->m_logbsize &&
+			    be32_to_cpu(rhead->h_num_logops) == 1) {
+				xfs_warn(log->l_mp,
+		"invalid iclog size (%d bytes), using lsunit (%d bytes)",
+					 h_size, log->l_mp->m_logbsize);
+				h_size = log->l_mp->m_logbsize;
+			} else
+				return -EFSCORRUPTED;
+		}
+
 		if ((be32_to_cpu(rhead->h_version) & XLOG_VERSION_2) &&
 		    (h_size > XLOG_HEADER_CYCLE_SIZE)) {
 			hblks = h_size / XLOG_HEADER_CYCLE_SIZE;
@@ -4301,7 +4735,7 @@ xlog_do_recovery_pass(
 	}
 
 	memset(rhash, 0, sizeof(rhash));
-	blk_no = tail_blk;
+	blk_no = rhead_blk = tail_blk;
 	if (tail_blk > head_blk) {
 		/*
 		 * Perform recovery around the end of the physical log.
@@ -4408,19 +4842,18 @@ xlog_do_recovery_pass(
 					goto bread_err2;
 			}
 
-			error = xlog_unpack_data(rhead, offset, log);
+			error = xlog_recover_process(log, rhash, rhead, offset,
+						     pass);
 			if (error)
 				goto bread_err2;
 
-			error = xlog_recover_process_data(log, rhash,
-							rhead, offset, pass);
-			if (error)
-				goto bread_err2;
 			blk_no += bblks;
+			rhead_blk = blk_no;
 		}
 
 		ASSERT(blk_no >= log->l_logBBsize);
 		blk_no -= log->l_logBBsize;
+		rhead_blk = blk_no;
 	}
 
 	/* read first part of physical log */
@@ -4441,21 +4874,22 @@ xlog_do_recovery_pass(
 		if (error)
 			goto bread_err2;
 
-		error = xlog_unpack_data(rhead, offset, log);
+		error = xlog_recover_process(log, rhash, rhead, offset, pass);
 		if (error)
 			goto bread_err2;
 
-		error = xlog_recover_process_data(log, rhash,
-						rhead, offset, pass);
-		if (error)
-			goto bread_err2;
 		blk_no += bblks + hblks;
+		rhead_blk = blk_no;
 	}
 
  bread_err2:
 	xlog_put_bp(dbp);
  bread_err1:
 	xlog_put_bp(hbp);
+
+	if (error && first_bad)
+		*first_bad = rhead_blk;
+
 	return error;
 }
 
@@ -4493,7 +4927,7 @@ xlog_do_log_recovery(
 		INIT_LIST_HEAD(&log->l_buf_cancel_table[i]);
 
 	error = xlog_do_recovery_pass(log, head_blk, tail_blk,
-				      XLOG_RECOVER_PASS1);
+				      XLOG_RECOVER_PASS1, NULL);
 	if (error != 0) {
 		kmem_free(log->l_buf_cancel_table);
 		log->l_buf_cancel_table = NULL;
@@ -4504,7 +4938,7 @@ xlog_do_log_recovery(
 	 * When it is complete free the table of buf cancel items.
 	 */
 	error = xlog_do_recovery_pass(log, head_blk, tail_blk,
-				      XLOG_RECOVER_PASS2);
+				      XLOG_RECOVER_PASS2, NULL);
 #ifdef DEBUG
 	if (!error) {
 		int	i;
@@ -4529,6 +4963,7 @@ xlog_do_recover(
 	xfs_daddr_t	head_blk,
 	xfs_daddr_t	tail_blk)
 {
+	struct xfs_mount *mp = log->l_mp;
 	int		error;
 	xfs_buf_t	*bp;
 	xfs_sb_t	*sbp;
@@ -4543,7 +4978,7 @@ xlog_do_recover(
 	/*
 	 * If IO errors happened during recovery, bail out.
 	 */
-	if (XFS_FORCED_SHUTDOWN(log->l_mp)) {
+	if (XFS_FORCED_SHUTDOWN(mp)) {
 		return -EIO;
 	}
 
@@ -4556,22 +4991,21 @@ xlog_do_recover(
 	 * or iunlinks they will have some entries in the AIL; so we look at
 	 * the AIL to determine how to set the tail_lsn.
 	 */
-	xlog_assign_tail_lsn(log->l_mp);
+	xlog_assign_tail_lsn(mp);
 
 	/*
 	 * Now that we've finished replaying all buffer and inode
 	 * updates, re-read in the superblock and reverify it.
 	 */
-	bp = xfs_getsb(log->l_mp, 0);
-	XFS_BUF_UNDONE(bp);
-	ASSERT(!(XFS_BUF_ISWRITE(bp)));
-	XFS_BUF_READ(bp);
-	XFS_BUF_UNASYNC(bp);
+	bp = xfs_getsb(mp, 0);
+	bp->b_flags &= ~(XBF_DONE | XBF_ASYNC);
+	ASSERT(!(bp->b_flags & XBF_WRITE));
+	bp->b_flags |= XBF_READ;
 	bp->b_ops = &xfs_sb_buf_ops;
 
 	error = xfs_buf_submit_wait(bp);
 	if (error) {
-		if (!XFS_FORCED_SHUTDOWN(log->l_mp)) {
+		if (!XFS_FORCED_SHUTDOWN(mp)) {
 			xfs_buf_ioerror_alert(bp, __func__);
 			ASSERT(0);
 		}
@@ -4580,14 +5014,17 @@ xlog_do_recover(
 	}
 
 	/* Convert superblock from on-disk format */
-	sbp = &log->l_mp->m_sb;
+	sbp = &mp->m_sb;
 	xfs_sb_from_disk(sbp, XFS_BUF_TO_SBP(bp));
-	ASSERT(sbp->sb_magicnum == XFS_SB_MAGIC);
-	ASSERT(xfs_sb_good_version(sbp));
-	xfs_reinit_percpu_counters(log->l_mp);
-
 	xfs_buf_relse(bp);
 
+	/* re-initialise in-core superblock and geometry structures */
+	xfs_reinit_percpu_counters(mp);
+	error = xfs_initialize_perag(mp, sbp->sb_agcount, &mp->m_maxagi);
+	if (error) {
+		xfs_warn(mp, "Failed post-recovery per-ag init: %d", error);
+		return error;
+	}
 
 	xlog_recover_check_summary(log);
 
@@ -4609,9 +5046,19 @@ xlog_recover(
 	int		error;
 
 	/* find the tail of the log */
-	if ((error = xlog_find_tail(log, &head_blk, &tail_blk)))
+	error = xlog_find_tail(log, &head_blk, &tail_blk);
+	if (error)
 		return error;
 
+	/*
+	 * The superblock was read before the log was available and thus the LSN
+	 * could not be verified. Check the superblock LSN against the current
+	 * LSN now that it's known.
+	 */
+	if (xfs_sb_version_hascrc(&log->l_mp->m_sb) &&
+	    !xfs_log_check_lsn(log->l_mp, log->l_mp->m_sb.sb_lsn))
+		return -EINVAL;
+
 	if (tail_blk != head_blk) {
 		/* There used to be a comment here:
 		 *
diff --git a/fs/xfs/xfs_message.c b/fs/xfs/xfs_message.c
index d8b67547ab34..11792d888e4e 100644
--- a/fs/xfs/xfs_message.c
+++ b/fs/xfs/xfs_message.c
@@ -17,6 +17,7 @@
 
 #include "xfs.h"
 #include "xfs_fs.h"
+#include "xfs_error.h"
 #include "xfs_format.h"
 #include "xfs_log_format.h"
 #include "xfs_trans_resv.h"
@@ -43,6 +44,7 @@ void func(const struct xfs_mount *mp, const char *fmt, ...)	\
 {								\
 	struct va_format	vaf;				\
 	va_list			args;				\
+	int			level;				\
 								\
 	va_start(args, fmt);					\
 								\
@@ -51,6 +53,11 @@ void func(const struct xfs_mount *mp, const char *fmt, ...)	\
 								\
 	__xfs_printk(kern_level, mp, &vaf);			\
 	va_end(args);						\
+								\
+	if (!kstrtoint(kern_level, 0, &level) &&		\
+	    level <= LOGLEVEL_ERR &&				\
+	    xfs_error_level >= XFS_ERRLEVEL_HIGH)		\
+		xfs_stack_trace();				\
 }								\
 
 define_xfs_printk_level(xfs_emerg, KERN_EMERG);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index bf92e0c037c7..cfd4210dd015 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -47,6 +47,16 @@ static DEFINE_MUTEX(xfs_uuid_table_mutex);
 static int xfs_uuid_table_size;
 static uuid_t *xfs_uuid_table;
 
+void
+xfs_uuid_table_free(void)
+{
+	if (xfs_uuid_table_size == 0)
+		return;
+	kmem_free(xfs_uuid_table);
+	xfs_uuid_table = NULL;
+	xfs_uuid_table_size = 0;
+}
+
 /*
  * See if the UUID is unique among mounted XFS filesystems.
  * Mount fails if UUID is nil or a FS with the same UUID is already mounted.
@@ -161,7 +171,7 @@ xfs_sb_validate_fsb_count(
 	ASSERT(sbp->sb_blocklog >= BBSHIFT);
 
 	/* Limited by ULONG_MAX of page cache index */
-	if (nblocks >> (PAGE_CACHE_SHIFT - sbp->sb_blocklog) > ULONG_MAX)
+	if (nblocks >> (PAGE_SHIFT - sbp->sb_blocklog) > ULONG_MAX)
 		return -EFBIG;
 	return 0;
 }
@@ -175,9 +185,6 @@ xfs_initialize_perag(
 	xfs_agnumber_t	index;
 	xfs_agnumber_t	first_initialised = 0;
 	xfs_perag_t	*pag;
-	xfs_agino_t	agino;
-	xfs_ino_t	ino;
-	xfs_sb_t	*sbp = &mp->m_sb;
 	int		error = -ENOMEM;
 
 	/*
@@ -220,22 +227,7 @@ xfs_initialize_perag(
 		radix_tree_preload_end();
 	}
 
-	/*
-	 * If we mount with the inode64 option, or no inode overflows
-	 * the legacy 32-bit address space clear the inode32 option.
-	 */
-	agino = XFS_OFFBNO_TO_AGINO(mp, sbp->sb_agblocks - 1, 0);
-	ino = XFS_AGINO_TO_INO(mp, agcount - 1, agino);
-
-	if ((mp->m_flags & XFS_MOUNT_SMALL_INUMS) && ino > XFS_MAXINUMBER_32)
-		mp->m_flags |= XFS_MOUNT_32BITINODES;
-	else
-		mp->m_flags &= ~XFS_MOUNT_32BITINODES;
-
-	if (mp->m_flags & XFS_MOUNT_32BITINODES)
-		index = xfs_set_inode32(mp, agcount);
-	else
-		index = xfs_set_inode64(mp, agcount);
+	index = xfs_set_inode_alloc(mp, agcount);
 
 	if (maxagi)
 		*maxagi = index;
@@ -693,10 +685,15 @@ xfs_mountfs(
 	if (error)
 		goto out;
 
-	error = xfs_uuid_mount(mp);
+	error = xfs_sysfs_init(&mp->m_stats.xs_kobj, &xfs_stats_ktype,
+			       &mp->m_kobj, "stats");
 	if (error)
 		goto out_remove_sysfs;
 
+	error = xfs_uuid_mount(mp);
+	if (error)
+		goto out_del_stats;
+
 	/*
 	 * Set the minimum read and write sizes
 	 */
@@ -850,7 +847,7 @@ xfs_mountfs(
 
 	ASSERT(rip != NULL);
 
-	if (unlikely(!S_ISDIR(rip->i_d.di_mode))) {
+	if (unlikely(!S_ISDIR(VFS_I(rip)->i_mode))) {
 		xfs_warn(mp, "corrupted root inode %llu: not a directory",
 			(unsigned long long)rip->i_ino);
 		xfs_iunlock(rip, XFS_ILOCK_EXCL);
@@ -971,6 +968,8 @@ xfs_mountfs(
 	xfs_da_unmount(mp);
  out_remove_uuid:
 	xfs_uuid_unmount(mp);
+ out_del_stats:
+	xfs_sysfs_del(&mp->m_stats.xs_kobj);
  out_remove_sysfs:
 	xfs_sysfs_del(&mp->m_kobj);
  out:
@@ -1047,6 +1046,7 @@ xfs_unmountfs(
 		xfs_warn(mp, "Unable to update superblock counters. "
 				"Freespace may not be correct on next mount.");
 
+
 	xfs_log_unmount(mp);
 	xfs_da_unmount(mp);
 	xfs_uuid_unmount(mp);
@@ -1056,6 +1056,7 @@ xfs_unmountfs(
 #endif
 	xfs_free_perag(mp);
 
+	xfs_sysfs_del(&mp->m_stats.xs_kobj);
 	xfs_sysfs_del(&mp->m_kobj);
 }
 
@@ -1265,7 +1266,7 @@ xfs_getsb(
 	}
 
 	xfs_buf_hold(bp);
-	ASSERT(XFS_BUF_ISDONE(bp));
+	ASSERT(bp->b_flags & XBF_DONE);
 	return bp;
 }
 
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 7999e91cd49a..eafe257b357a 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -127,6 +127,7 @@ typedef struct xfs_mount {
 	int64_t			m_low_space[XFS_LOWSP_MAX];
 						/* low free space thresholds */
 	struct xfs_kobj		m_kobj;
+	struct xstats		m_stats;	/* per-fs stats */
 
 	struct workqueue_struct *m_buf_workqueue;
 	struct workqueue_struct	*m_data_workqueue;
@@ -146,6 +147,17 @@ typedef struct xfs_mount {
 	 * to various other kinds of pain inflicted on the pNFS server.
 	 */
 	__uint32_t		m_generation;
+
+#ifdef DEBUG
+	/*
+	 * DEBUG mode instrumentation to test and/or trigger delayed allocation
+	 * block killing in the event of failed writes. When enabled, all
+	 * buffered writes are forced to fail. All delalloc blocks in the range
+	 * of the write (including pre-existing delalloc blocks!) are tossed as
+	 * part of the write failure error handling sequence.
+	 */
+	bool			m_fail_writes;
+#endif
 } xfs_mount_t;
 
 /*
@@ -165,9 +177,8 @@ typedef struct xfs_mount {
 #define XFS_MOUNT_GRPID		(1ULL << 9)	/* group-ID assigned from directory */
 #define XFS_MOUNT_NORECOVERY	(1ULL << 10)	/* no recovery - dirty fs */
 #define XFS_MOUNT_DFLT_IOSIZE	(1ULL << 12)	/* set default i/o size */
-#define XFS_MOUNT_32BITINODES	(1ULL << 14)	/* do not create inodes above
-						 * 32 bits in size */
-#define XFS_MOUNT_SMALL_INUMS	(1ULL << 15)	/* users wants 32bit inodes */
+#define XFS_MOUNT_SMALL_INUMS	(1ULL << 14)	/* user wants 32bit inodes */
+#define XFS_MOUNT_32BITINODES	(1ULL << 15)	/* inode32 allocator active */
 #define XFS_MOUNT_NOUUID	(1ULL << 16)	/* ignore uuid during mount */
 #define XFS_MOUNT_BARRIER	(1ULL << 17)
 #define XFS_MOUNT_IKEEP		(1ULL << 18)	/* keep empty inode clusters*/
@@ -220,12 +231,12 @@ static inline unsigned long
 xfs_preferred_iosize(xfs_mount_t *mp)
 {
 	if (mp->m_flags & XFS_MOUNT_COMPAT_IOSIZE)
-		return PAGE_CACHE_SIZE;
+		return PAGE_SIZE;
 	return (mp->m_swidth ?
 		(mp->m_swidth << mp->m_sb.sb_blocklog) :
 		((mp->m_flags & XFS_MOUNT_DFLT_IOSIZE) ?
 			(1 << (int)MAX(mp->m_readio_log, mp->m_writeio_log)) :
-			PAGE_CACHE_SIZE));
+			PAGE_SIZE));
 }
 
 #define XFS_LAST_UNMOUNT_WAS_CLEAN(mp)	\
@@ -263,6 +274,20 @@ xfs_daddr_to_agbno(struct xfs_mount *mp, xfs_daddr_t d)
 	return (xfs_agblock_t) do_div(ld, mp->m_sb.sb_agblocks);
 }
 
+#ifdef DEBUG
+static inline bool
+xfs_mp_fail_writes(struct xfs_mount *mp)
+{
+	return mp->m_fail_writes;
+}
+#else
+static inline bool
+xfs_mp_fail_writes(struct xfs_mount *mp)
+{
+	return 0;
+}
+#endif
+
 /*
  * Per-ag incore structure, copies of information in agf and agi, to improve the
  * performance of allocation group selection.
@@ -312,6 +337,7 @@ typedef struct xfs_perag {
 	int		pagb_count;	/* pagb slots in use */
 } xfs_perag_t;
 
+extern void	xfs_uuid_table_free(void);
 extern int	xfs_log_sbcount(xfs_mount_t *);
 extern __uint64_t xfs_default_resblks(xfs_mount_t *mp);
 extern int	xfs_mountfs(xfs_mount_t *mp);
@@ -325,7 +351,6 @@ extern int	xfs_mod_fdblocks(struct xfs_mount *mp, int64_t delta,
 				 bool reserved);
 extern int	xfs_mod_frextents(struct xfs_mount *mp, int64_t delta);
 
-extern int	xfs_mount_log_sb(xfs_mount_t *);
 extern struct xfs_buf *xfs_getsb(xfs_mount_t *, int);
 extern int	xfs_readsb(xfs_mount_t *, int);
 extern void	xfs_freesb(xfs_mount_t *);
@@ -336,4 +361,7 @@ extern int	xfs_dev_is_read_only(struct xfs_mount *, char *);
 
 extern void	xfs_set_low_space_thresholds(struct xfs_mount *);
 
+int	xfs_zero_extent(struct xfs_inode *ip, xfs_fsblock_t start_fsb,
+			xfs_off_t count_fsb);
+
 #endif	/* __XFS_MOUNT_H__ */
diff --git a/fs/xfs/xfs_ondisk.h b/fs/xfs/xfs_ondisk.h
new file mode 100644
index 000000000000..184c44effdd5
--- /dev/null
+++ b/fs/xfs/xfs_ondisk.h
@@ -0,0 +1,117 @@
+/*
+ * Copyright (c) 2016 Oracle.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+#ifndef __XFS_ONDISK_H
+#define __XFS_ONDISK_H
+
+#define XFS_CHECK_STRUCT_SIZE(structname, size) \
+	BUILD_BUG_ON_MSG(sizeof(structname) != (size), "XFS: sizeof(" \
+		#structname ") is wrong, expected " #size)
+
+static inline void __init
+xfs_check_ondisk_structs(void)
+{
+	/* ag/file structures */
+	XFS_CHECK_STRUCT_SIZE(struct xfs_acl,			4);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_acl_entry,		12);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_agf,			224);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_agfl,			36);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_agi,			336);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_bmbt_key,		8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_bmbt_rec,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_bmdr_block,		4);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_btree_block,		72);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dinode,		176);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_disk_dquot,		104);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dqblk,			136);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dsb,			264);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dsymlink_hdr,		56);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_inobt_key,		4);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_inobt_rec,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_timestamp,		8);
+	XFS_CHECK_STRUCT_SIZE(xfs_alloc_key_t,			8);
+	XFS_CHECK_STRUCT_SIZE(xfs_alloc_ptr_t,			4);
+	XFS_CHECK_STRUCT_SIZE(xfs_alloc_rec_t,			8);
+	XFS_CHECK_STRUCT_SIZE(xfs_inobt_ptr_t,			4);
+
+	/* dir/attr trees */
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attr3_leaf_hdr,	80);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attr3_leafblock,	88);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attr3_rmt_hdr,		56);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_da3_blkinfo,		56);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_da3_intnode,		64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_da3_node_hdr,		64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_blk_hdr,		48);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_data_hdr,		64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_free,		64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_free_hdr,		64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_leaf,		64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_leaf_hdr,		64);
+	XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_entry_t,		8);
+	XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_hdr_t,		32);
+	XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_map_t,		4);
+	XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_name_local_t,	4);
+
+	/*
+	 * m68k has problems with xfs_attr_leaf_name_remote_t, but we pad it to
+	 * 4 bytes anyway so it's not obviously a problem.  Hence for the moment
+	 * we don't check this structure. This can be re-instated when the attr
+	 * definitions are updated to use c99 VLA definitions.
+	 *
+	XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_name_remote_t,	12);
+	 */
+
+	XFS_CHECK_STRUCT_SIZE(xfs_attr_leafblock_t,		40);
+	XFS_CHECK_STRUCT_SIZE(xfs_attr_shortform_t,		8);
+	XFS_CHECK_STRUCT_SIZE(xfs_da_blkinfo_t,			12);
+	XFS_CHECK_STRUCT_SIZE(xfs_da_intnode_t,			16);
+	XFS_CHECK_STRUCT_SIZE(xfs_da_node_entry_t,		8);
+	XFS_CHECK_STRUCT_SIZE(xfs_da_node_hdr_t,		16);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_data_free_t,		4);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_data_hdr_t,		16);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_data_unused_t,		6);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_free_hdr_t,		16);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_free_t,			16);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_ino4_t,			4);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_ino8_t,			8);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_inou_t,			8);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_leaf_entry_t,		8);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_leaf_hdr_t,		16);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_leaf_t,			16);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_leaf_tail_t,		4);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_sf_entry_t,		3);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_sf_hdr_t,		10);
+	XFS_CHECK_STRUCT_SIZE(xfs_dir2_sf_off_t,		2);
+
+	/* log structures */
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dq_logformat,		24);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_32,	28);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_64,	32);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_32,	28);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_64,	32);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_extent_32,		12);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_extent_64,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_log_dinode,		176);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_icreate_log,		28);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_ictimestamp,		8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format_32,	52);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format_64,	56);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_qoff_logformat,	20);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_trans_header,		16);
+}
+
+#endif /* __XFS_ONDISK_H */
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index ab4a6066f7ca..51ddaf2c2b8c 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -42,11 +42,11 @@ xfs_break_layouts(
 	while ((error = break_layout(inode, false) == -EWOULDBLOCK)) {
 		xfs_iunlock(ip, *iolock);
 		if (with_imutex && (*iolock & XFS_IOLOCK_EXCL))
-			mutex_unlock(&inode->i_mutex);
+			inode_unlock(inode);
 		error = break_layout(inode, true);
 		*iolock = XFS_IOLOCK_EXCL;
 		if (with_imutex)
-			mutex_lock(&inode->i_mutex);
+			inode_lock(inode);
 		xfs_ilock(ip, *iolock);
 	}
 
@@ -181,6 +181,11 @@ xfs_fs_map_blocks(
 		ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
 
 		if (!nimaps || imap.br_startblock == HOLESTARTBLOCK) {
+			/*
+			 * xfs_iomap_write_direct() expects to take ownership of
+			 * the shared ilock.
+			 */
+			xfs_ilock(ip, XFS_ILOCK_SHARED);
 			error = xfs_iomap_write_direct(ip, offset, length,
 						       &imap, nimaps);
 			if (error)
@@ -288,8 +293,8 @@ xfs_fs_commit_blocks(
 		 * Make sure reads through the pagecache see the new data.
 		 */
 		error = invalidate_inode_pages2_range(inode->i_mapping,
-					start >> PAGE_CACHE_SHIFT,
-					(end - 1) >> PAGE_CACHE_SHIFT);
+					start >> PAGE_SHIFT,
+					(end - 1) >> PAGE_SHIFT);
 		WARN_ON_ONCE(error);
 
 		error = xfs_iomap_write_unwritten(ip, start, length);
diff --git a/fs/xfs/xfs_pnfs.h b/fs/xfs/xfs_pnfs.h
index 8147ac108820..93f74853961b 100644
--- a/fs/xfs/xfs_pnfs.h
+++ b/fs/xfs/xfs_pnfs.h
@@ -1,7 +1,7 @@
 #ifndef _XFS_PNFS_H
 #define _XFS_PNFS_H 1
 
-#ifdef CONFIG_NFSD_PNFS
+#if defined(CONFIG_NFSD_BLOCKLAYOUT) || defined(CONFIG_NFSD_SCSILAYOUT)
 int xfs_fs_get_uuid(struct super_block *sb, u8 *buf, u32 *len, u64 *offset);
 int xfs_fs_map_blocks(struct inode *inode, loff_t offset, u64 length,
 		struct iomap *iomap, bool write, u32 *device_generation);
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index eac9549efd52..be125e1758c1 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -184,7 +184,7 @@ xfs_qm_dqpurge(
 	 */
 	ASSERT(!list_empty(&dqp->q_lru));
 	list_lru_del(&qi->qi_lru, &dqp->q_lru);
-	XFS_STATS_DEC(xs_qm_dquot_unused);
+	XFS_STATS_DEC(mp, xs_qm_dquot_unused);
 
 	xfs_qm_dqdestroy(dqp);
 	return 0;
@@ -448,11 +448,11 @@ xfs_qm_dquot_isolate(
 	 */
 	if (dqp->q_nrefs) {
 		xfs_dqunlock(dqp);
-		XFS_STATS_INC(xs_qm_dqwants);
+		XFS_STATS_INC(dqp->q_mount, xs_qm_dqwants);
 
 		trace_xfs_dqreclaim_want(dqp);
 		list_lru_isolate(lru, &dqp->q_lru);
-		XFS_STATS_DEC(xs_qm_dquot_unused);
+		XFS_STATS_DEC(dqp->q_mount, xs_qm_dquot_unused);
 		return LRU_REMOVED;
 	}
 
@@ -496,19 +496,19 @@ xfs_qm_dquot_isolate(
 
 	ASSERT(dqp->q_nrefs == 0);
 	list_lru_isolate_move(lru, &dqp->q_lru, &isol->dispose);
-	XFS_STATS_DEC(xs_qm_dquot_unused);
+	XFS_STATS_DEC(dqp->q_mount, xs_qm_dquot_unused);
 	trace_xfs_dqreclaim_done(dqp);
-	XFS_STATS_INC(xs_qm_dqreclaims);
+	XFS_STATS_INC(dqp->q_mount, xs_qm_dqreclaims);
 	return LRU_REMOVED;
 
 out_miss_busy:
 	trace_xfs_dqreclaim_busy(dqp);
-	XFS_STATS_INC(xs_qm_dqreclaim_misses);
+	XFS_STATS_INC(dqp->q_mount, xs_qm_dqreclaim_misses);
 	return LRU_SKIP;
 
 out_unlock_dirty:
 	trace_xfs_dqreclaim_busy(dqp);
-	XFS_STATS_INC(xs_qm_dqreclaim_misses);
+	XFS_STATS_INC(dqp->q_mount, xs_qm_dqreclaim_misses);
 	xfs_dqunlock(dqp);
 	spin_lock(lru_lock);
 	return LRU_RETRY;
@@ -525,7 +525,7 @@ xfs_qm_shrink_scan(
 	unsigned long		freed;
 	int			error;
 
-	if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT))
+	if ((sc->gfp_mask & (__GFP_FS|__GFP_DIRECT_RECLAIM)) != (__GFP_FS|__GFP_DIRECT_RECLAIM))
 		return 0;
 
 	INIT_LIST_HEAD(&isol.buffers);
@@ -560,6 +560,37 @@ xfs_qm_shrink_count(
 	return list_lru_shrink_count(&qi->qi_lru, sc);
 }
 
+STATIC void
+xfs_qm_set_defquota(
+	xfs_mount_t	*mp,
+	uint		type,
+	xfs_quotainfo_t	*qinf)
+{
+	xfs_dquot_t		*dqp;
+	struct xfs_def_quota    *defq;
+	int			error;
+
+	error = xfs_qm_dqread(mp, 0, type, XFS_QMOPT_DOWARN, &dqp);
+
+	if (!error) {
+		xfs_disk_dquot_t        *ddqp = &dqp->q_core;
+
+		defq = xfs_get_defquota(dqp, qinf);
+
+		/*
+		 * Timers and warnings have been already set, let's just set the
+		 * default limits for this quota type
+		 */
+		defq->bhardlimit = be64_to_cpu(ddqp->d_blk_hardlimit);
+		defq->bsoftlimit = be64_to_cpu(ddqp->d_blk_softlimit);
+		defq->ihardlimit = be64_to_cpu(ddqp->d_ino_hardlimit);
+		defq->isoftlimit = be64_to_cpu(ddqp->d_ino_softlimit);
+		defq->rtbhardlimit = be64_to_cpu(ddqp->d_rtb_hardlimit);
+		defq->rtbsoftlimit = be64_to_cpu(ddqp->d_rtb_softlimit);
+		xfs_qm_dqdestroy(dqp);
+	}
+}
+
 /*
  * This initializes all the quota information that's kept in the
  * mount structure
@@ -606,19 +637,19 @@ xfs_qm_init_quotainfo(
 	 * We try to get the limits from the superuser's limits fields.
 	 * This is quite hacky, but it is standard quota practice.
 	 *
-	 * We look at the USR dquot with id == 0 first, but if user quotas
-	 * are not enabled we goto the GRP dquot with id == 0.
-	 * We don't really care to keep separate default limits for user
-	 * and group quotas, at least not at this point.
-	 *
 	 * Since we may not have done a quotacheck by this point, just read
 	 * the dquot without attaching it to any hashtables or lists.
+	 *
+	 * Timers and warnings are globally set by the first timer found in
+	 * user/group/proj quota types, otherwise a default value is used.
+	 * This should be split into different fields per quota type.
 	 */
 	error = xfs_qm_dqread(mp, 0,
 			XFS_IS_UQUOTA_RUNNING(mp) ? XFS_DQ_USER :
 			 (XFS_IS_GQUOTA_RUNNING(mp) ? XFS_DQ_GROUP :
 			  XFS_DQ_PROJ),
 			XFS_QMOPT_DOWARN, &dqp);
+
 	if (!error) {
 		xfs_disk_dquot_t	*ddqp = &dqp->q_core;
 
@@ -639,13 +670,6 @@ xfs_qm_init_quotainfo(
 			be16_to_cpu(ddqp->d_iwarns) : XFS_QM_IWARNLIMIT;
 		qinf->qi_rtbwarnlimit = ddqp->d_rtbwarns ?
 			be16_to_cpu(ddqp->d_rtbwarns) : XFS_QM_RTBWARNLIMIT;
-		qinf->qi_bhardlimit = be64_to_cpu(ddqp->d_blk_hardlimit);
-		qinf->qi_bsoftlimit = be64_to_cpu(ddqp->d_blk_softlimit);
-		qinf->qi_ihardlimit = be64_to_cpu(ddqp->d_ino_hardlimit);
-		qinf->qi_isoftlimit = be64_to_cpu(ddqp->d_ino_softlimit);
-		qinf->qi_rtbhardlimit = be64_to_cpu(ddqp->d_rtb_hardlimit);
-		qinf->qi_rtbsoftlimit = be64_to_cpu(ddqp->d_rtb_softlimit);
-
 		xfs_qm_dqdestroy(dqp);
 	} else {
 		qinf->qi_btimelimit = XFS_QM_BTIMELIMIT;
@@ -656,6 +680,13 @@ xfs_qm_init_quotainfo(
 		qinf->qi_rtbwarnlimit = XFS_QM_RTBWARNLIMIT;
 	}
 
+	if (XFS_IS_UQUOTA_RUNNING(mp))
+		xfs_qm_set_defquota(mp, XFS_DQ_USER, qinf);
+	if (XFS_IS_GQUOTA_RUNNING(mp))
+		xfs_qm_set_defquota(mp, XFS_DQ_GROUP, qinf);
+	if (XFS_IS_PQUOTA_RUNNING(mp))
+		xfs_qm_set_defquota(mp, XFS_DQ_PROJ, qinf);
+
 	qinf->qi_shrinker.count_objects = xfs_qm_shrink_count;
 	qinf->qi_shrinker.scan_objects = xfs_qm_shrink_scan;
 	qinf->qi_shrinker.seeks = DEFAULT_SEEKS;
diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h
index 996a04064894..2975a822e9f0 100644
--- a/fs/xfs/xfs_qm.h
+++ b/fs/xfs/xfs_qm.h
@@ -53,6 +53,15 @@ extern struct kmem_zone	*xfs_qm_dqtrxzone;
  */
 #define XFS_DQUOT_CLUSTER_SIZE_FSB	(xfs_filblks_t)1
 
+struct xfs_def_quota {
+	xfs_qcnt_t       bhardlimit;     /* default data blk hard limit */
+	xfs_qcnt_t       bsoftlimit;	 /* default data blk soft limit */
+	xfs_qcnt_t       ihardlimit;	 /* default inode count hard limit */
+	xfs_qcnt_t       isoftlimit;	 /* default inode count soft limit */
+	xfs_qcnt_t	 rtbhardlimit;   /* default realtime blk hard limit */
+	xfs_qcnt_t	 rtbsoftlimit;   /* default realtime blk soft limit */
+};
+
 /*
  * Various quota information for individual filesystems.
  * The mount structure keeps a pointer to this.
@@ -76,12 +85,9 @@ typedef struct xfs_quotainfo {
 	struct mutex	 qi_quotaofflock;/* to serialize quotaoff */
 	xfs_filblks_t	 qi_dqchunklen;	 /* # BBs in a chunk of dqs */
 	uint		 qi_dqperchunk;	 /* # ondisk dqs in above chunk */
-	xfs_qcnt_t	 qi_bhardlimit;	 /* default data blk hard limit */
-	xfs_qcnt_t	 qi_bsoftlimit;	 /* default data blk soft limit */
-	xfs_qcnt_t	 qi_ihardlimit;	 /* default inode count hard limit */
-	xfs_qcnt_t	 qi_isoftlimit;	 /* default inode count soft limit */
-	xfs_qcnt_t	 qi_rtbhardlimit;/* default realtime blk hard limit */
-	xfs_qcnt_t	 qi_rtbsoftlimit;/* default realtime blk soft limit */
+	struct xfs_def_quota	qi_usr_default;
+	struct xfs_def_quota	qi_grp_default;
+	struct xfs_def_quota	qi_prj_default;
 	struct shrinker  qi_shrinker;
 } xfs_quotainfo_t;
 
@@ -104,15 +110,15 @@ xfs_dquot_tree(
 }
 
 static inline struct xfs_inode *
-xfs_dq_to_quota_inode(struct xfs_dquot *dqp)
+xfs_quota_inode(xfs_mount_t *mp, uint dq_flags)
 {
-	switch (dqp->dq_flags & XFS_DQ_ALLTYPES) {
+	switch (dq_flags & XFS_DQ_ALLTYPES) {
 	case XFS_DQ_USER:
-		return dqp->q_mount->m_quotainfo->qi_uquotaip;
+		return mp->m_quotainfo->qi_uquotaip;
 	case XFS_DQ_GROUP:
-		return dqp->q_mount->m_quotainfo->qi_gquotaip;
+		return mp->m_quotainfo->qi_gquotaip;
 	case XFS_DQ_PROJ:
-		return dqp->q_mount->m_quotainfo->qi_pquotaip;
+		return mp->m_quotainfo->qi_pquotaip;
 	default:
 		ASSERT(0);
 	}
@@ -164,11 +170,27 @@ extern void		xfs_qm_dqrele_all_inodes(struct xfs_mount *, uint);
 
 /* quota ops */
 extern int		xfs_qm_scall_trunc_qfiles(struct xfs_mount *, uint);
-extern int		xfs_qm_scall_getquota(struct xfs_mount *, xfs_dqid_t,
-					uint, struct qc_dqblk *);
+extern int		xfs_qm_scall_getquota(struct xfs_mount *, xfs_dqid_t *,
+					uint, struct qc_dqblk *, uint);
 extern int		xfs_qm_scall_setqlim(struct xfs_mount *, xfs_dqid_t, uint,
 					struct qc_dqblk *);
 extern int		xfs_qm_scall_quotaon(struct xfs_mount *, uint);
 extern int		xfs_qm_scall_quotaoff(struct xfs_mount *, uint);
 
+static inline struct xfs_def_quota *
+xfs_get_defquota(struct xfs_dquot *dqp, struct xfs_quotainfo *qi)
+{
+	struct xfs_def_quota *defq;
+
+	if (XFS_QM_ISUDQ(dqp))
+		defq = &qi->qi_usr_default;
+	else if (XFS_QM_ISGDQ(dqp))
+		defq = &qi->qi_grp_default;
+	else {
+		ASSERT(XFS_QM_ISPDQ(dqp));
+		defq = &qi->qi_prj_default;
+	}
+	return defq;
+}
+
 #endif /* __XFS_QM_H__ */
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index 3640c6e896af..f4d0e0a8f517 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -404,6 +404,7 @@ xfs_qm_scall_setqlim(
 	struct xfs_disk_dquot	*ddq;
 	struct xfs_dquot	*dqp;
 	struct xfs_trans	*tp;
+	struct xfs_def_quota	*defq;
 	int			error;
 	xfs_qcnt_t		hard, soft;
 
@@ -431,6 +432,8 @@ xfs_qm_scall_setqlim(
 		ASSERT(error != -ENOENT);
 		goto out_unlock;
 	}
+
+	defq = xfs_get_defquota(dqp, q);
 	xfs_dqunlock(dqp);
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SETQLIM);
@@ -458,8 +461,8 @@ xfs_qm_scall_setqlim(
 		ddq->d_blk_softlimit = cpu_to_be64(soft);
 		xfs_dquot_set_prealloc_limits(dqp);
 		if (id == 0) {
-			q->qi_bhardlimit = hard;
-			q->qi_bsoftlimit = soft;
+			defq->bhardlimit = hard;
+			defq->bsoftlimit = soft;
 		}
 	} else {
 		xfs_debug(mp, "blkhard %Ld < blksoft %Ld", hard, soft);
@@ -474,8 +477,8 @@ xfs_qm_scall_setqlim(
 		ddq->d_rtb_hardlimit = cpu_to_be64(hard);
 		ddq->d_rtb_softlimit = cpu_to_be64(soft);
 		if (id == 0) {
-			q->qi_rtbhardlimit = hard;
-			q->qi_rtbsoftlimit = soft;
+			defq->rtbhardlimit = hard;
+			defq->rtbsoftlimit = soft;
 		}
 	} else {
 		xfs_debug(mp, "rtbhard %Ld < rtbsoft %Ld", hard, soft);
@@ -491,8 +494,8 @@ xfs_qm_scall_setqlim(
 		ddq->d_ino_hardlimit = cpu_to_be64(hard);
 		ddq->d_ino_softlimit = cpu_to_be64(soft);
 		if (id == 0) {
-			q->qi_ihardlimit = hard;
-			q->qi_isoftlimit = soft;
+			defq->ihardlimit = hard;
+			defq->isoftlimit = soft;
 		}
 	} else {
 		xfs_debug(mp, "ihard %Ld < isoft %Ld", hard, soft);
@@ -635,9 +638,10 @@ out:
 int
 xfs_qm_scall_getquota(
 	struct xfs_mount	*mp,
-	xfs_dqid_t		id,
+	xfs_dqid_t		*id,
 	uint			type,
-	struct qc_dqblk		*dst)
+	struct qc_dqblk		*dst,
+	uint			dqget_flags)
 {
 	struct xfs_dquot	*dqp;
 	int			error;
@@ -647,7 +651,7 @@ xfs_qm_scall_getquota(
 	 * we aren't passing the XFS_QMOPT_DOALLOC flag. If it doesn't
 	 * exist, we'll get ENOENT back.
 	 */
-	error = xfs_qm_dqget(mp, NULL, id, type, 0, &dqp);
+	error = xfs_qm_dqget(mp, NULL, *id, type, dqget_flags, &dqp);
 	if (error)
 		return error;
 
@@ -660,6 +664,9 @@ xfs_qm_scall_getquota(
 		goto out_put;
 	}
 
+	/* Fill in the ID we actually read from disk */
+	*id = be32_to_cpu(dqp->q_core.d_id);
+
 	memset(dst, 0, sizeof(*dst));
 	dst->d_spc_hardlimit =
 		XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_blk_hardlimit));
@@ -701,7 +708,7 @@ xfs_qm_scall_getquota(
 	if (((XFS_IS_UQUOTA_ENFORCED(mp) && type == XFS_DQ_USER) ||
 	     (XFS_IS_GQUOTA_ENFORCED(mp) && type == XFS_DQ_GROUP) ||
 	     (XFS_IS_PQUOTA_ENFORCED(mp) && type == XFS_DQ_PROJ)) &&
-	    id != 0) {
+	    *id != 0) {
 		if ((dst->d_space > dst->d_spc_softlimit) &&
 		    (dst->d_spc_softlimit > 0)) {
 			ASSERT(dst->d_spc_timer != 0);
diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
index 7795e0d01382..f82d79a8c694 100644
--- a/fs/xfs/xfs_quotaops.c
+++ b/fs/xfs/xfs_quotaops.c
@@ -231,14 +231,45 @@ xfs_fs_get_dqblk(
 	struct qc_dqblk		*qdq)
 {
 	struct xfs_mount	*mp = XFS_M(sb);
+	xfs_dqid_t		id;
 
 	if (!XFS_IS_QUOTA_RUNNING(mp))
 		return -ENOSYS;
 	if (!XFS_IS_QUOTA_ON(mp))
 		return -ESRCH;
 
-	return xfs_qm_scall_getquota(mp, from_kqid(&init_user_ns, qid),
-				      xfs_quota_type(qid.type), qdq);
+	id = from_kqid(&init_user_ns, qid);
+	return xfs_qm_scall_getquota(mp, &id,
+				      xfs_quota_type(qid.type), qdq, 0);
+}
+
+/* Return quota info for active quota >= this qid */
+STATIC int
+xfs_fs_get_nextdqblk(
+	struct super_block	*sb,
+	struct kqid		*qid,
+	struct qc_dqblk		*qdq)
+{
+	int			ret;
+	struct xfs_mount	*mp = XFS_M(sb);
+	xfs_dqid_t		id;
+
+	if (!XFS_IS_QUOTA_RUNNING(mp))
+		return -ENOSYS;
+	if (!XFS_IS_QUOTA_ON(mp))
+		return -ESRCH;
+
+	id = from_kqid(&init_user_ns, *qid);
+	ret = xfs_qm_scall_getquota(mp, &id,
+				    xfs_quota_type(qid->type), qdq,
+				    XFS_QMOPT_DQNEXT);
+	if (ret)
+		return ret;
+
+	/* ID may be different, so convert back what we got */
+	*qid = make_kqid(current_user_ns(), qid->type, id);
+	return 0;
+	
 }
 
 STATIC int
@@ -267,5 +298,6 @@ const struct quotactl_ops xfs_quotactl_operations = {
 	.quota_disable		= xfs_quota_disable,
 	.rm_xquota		= xfs_fs_rm_xquota,
 	.get_dqblk		= xfs_fs_get_dqblk,
+	.get_nextdqblk		= xfs_fs_get_nextdqblk,
 	.set_dqblk		= xfs_fs_set_dqblk,
 };
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index ab1bac6a3a1c..abf44435d04a 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -766,7 +766,6 @@ xfs_growfs_rt_alloc(
 {
 	xfs_fileoff_t		bno;		/* block number in file */
 	struct xfs_buf		*bp;	/* temporary buffer for zeroing */
-	int			committed;	/* transaction committed flag */
 	xfs_daddr_t		d;		/* disk block address */
 	int			error;		/* error return value */
 	xfs_fsblock_t		firstblock;/* first block allocated in xaction */
@@ -811,7 +810,7 @@ xfs_growfs_rt_alloc(
 		/*
 		 * Free any blocks freed up in the transaction, then commit.
 		 */
-		error = xfs_bmap_finish(&tp, &flist, &committed);
+		error = xfs_bmap_finish(&tp, &flist, NULL);
 		if (error)
 			goto out_bmap_cancel;
 		error = xfs_trans_commit(tp);
@@ -1273,7 +1272,7 @@ xfs_rtpick_extent(
 
 	ASSERT(xfs_isilocked(mp->m_rbmip, XFS_ILOCK_EXCL));
 
-	seqp = (__uint64_t *)&mp->m_rbmip->i_d.di_atime;
+	seqp = (__uint64_t *)&VFS_I(mp->m_rbmip)->i_atime;
 	if (!(mp->m_rbmip->i_d.di_flags & XFS_DIFLAG_NEWRTBM)) {
 		mp->m_rbmip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM;
 		*seqp = 0;
diff --git a/fs/xfs/xfs_stats.c b/fs/xfs/xfs_stats.c
index f2240383d4bb..8686df6c7609 100644
--- a/fs/xfs/xfs_stats.c
+++ b/fs/xfs/xfs_stats.c
@@ -18,20 +18,21 @@
 #include "xfs.h"
 #include <linux/proc_fs.h>
 
-DEFINE_PER_CPU(struct xfsstats, xfsstats);
+struct xstats xfsstats;
 
-static int counter_val(int idx)
+static int counter_val(struct xfsstats __percpu *stats, int idx)
 {
 	int val = 0, cpu;
 
 	for_each_possible_cpu(cpu)
-		val += *(((__u32 *)&per_cpu(xfsstats, cpu) + idx));
+		val += *(((__u32 *)per_cpu_ptr(stats, cpu) + idx));
 	return val;
 }
 
-static int xfs_stat_proc_show(struct seq_file *m, void *v)
+int xfs_stats_format(struct xfsstats __percpu *stats, char *buf)
 {
 	int		i, j;
+	int		len = 0;
 	__uint64_t	xs_xstrat_bytes = 0;
 	__uint64_t	xs_write_bytes = 0;
 	__uint64_t	xs_read_bytes = 0;
@@ -65,54 +66,59 @@ static int xfs_stat_proc_show(struct seq_file *m, void *v)
 	};
 
 	/* Loop over all stats groups */
+
 	for (i = j = 0; i < ARRAY_SIZE(xstats); i++) {
-		seq_printf(m, "%s", xstats[i].desc);
+		len += snprintf(buf + len, PATH_MAX - len, "%s",
+				xstats[i].desc);
 		/* inner loop does each group */
 		for (; j < xstats[i].endpoint; j++)
-			seq_printf(m, " %u", counter_val(j));
-		seq_putc(m, '\n');
+			len += snprintf(buf + len, PATH_MAX - len, " %u",
+					counter_val(stats, j));
+		len += snprintf(buf + len, PATH_MAX - len, "\n");
 	}
 	/* extra precision counters */
 	for_each_possible_cpu(i) {
-		xs_xstrat_bytes += per_cpu(xfsstats, i).xs_xstrat_bytes;
-		xs_write_bytes += per_cpu(xfsstats, i).xs_write_bytes;
-		xs_read_bytes += per_cpu(xfsstats, i).xs_read_bytes;
+		xs_xstrat_bytes += per_cpu_ptr(stats, i)->xs_xstrat_bytes;
+		xs_write_bytes += per_cpu_ptr(stats, i)->xs_write_bytes;
+		xs_read_bytes += per_cpu_ptr(stats, i)->xs_read_bytes;
 	}
 
-	seq_printf(m, "xpc %Lu %Lu %Lu\n",
+	len += snprintf(buf + len, PATH_MAX-len, "xpc %Lu %Lu %Lu\n",
 			xs_xstrat_bytes, xs_write_bytes, xs_read_bytes);
-	seq_printf(m, "debug %u\n",
+	len += snprintf(buf + len, PATH_MAX-len, "debug %u\n",
 #if defined(DEBUG)
 		1);
 #else
 		0);
 #endif
-	return 0;
+
+	return len;
 }
 
-static int xfs_stat_proc_open(struct inode *inode, struct file *file)
+void xfs_stats_clearall(struct xfsstats __percpu *stats)
 {
-	return single_open(file, xfs_stat_proc_show, NULL);
+	int		c;
+	__uint32_t	vn_active;
+
+	xfs_notice(NULL, "Clearing xfsstats");
+	for_each_possible_cpu(c) {
+		preempt_disable();
+		/* save vn_active, it's a universal truth! */
+		vn_active = per_cpu_ptr(stats, c)->vn_active;
+		memset(per_cpu_ptr(stats, c), 0, sizeof(*stats));
+		per_cpu_ptr(stats, c)->vn_active = vn_active;
+		preempt_enable();
+	}
 }
 
-static const struct file_operations xfs_stat_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= xfs_stat_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 /* legacy quota interfaces */
 #ifdef CONFIG_XFS_QUOTA
 static int xqm_proc_show(struct seq_file *m, void *v)
 {
 	/* maximum; incore; ratio free to inuse; freelist */
 	seq_printf(m, "%d\t%d\t%d\t%u\n",
-			0,
-			counter_val(XFSSTAT_END_XQMSTAT),
-			0,
-			counter_val(XFSSTAT_END_XQMSTAT + 1));
+		   0, counter_val(xfsstats.xs_stats, XFSSTAT_END_XQMSTAT),
+		   0, counter_val(xfsstats.xs_stats, XFSSTAT_END_XQMSTAT + 1));
 	return 0;
 }
 
@@ -136,7 +142,7 @@ static int xqmstat_proc_show(struct seq_file *m, void *v)
 
 	seq_printf(m, "qm");
 	for (j = XFSSTAT_END_IBT_V2; j < XFSSTAT_END_XQMSTAT; j++)
-		seq_printf(m, " %u", counter_val(j));
+		seq_printf(m, " %u", counter_val(xfsstats.xs_stats, j));
 	seq_putc(m, '\n');
 	return 0;
 }
@@ -155,44 +161,35 @@ static const struct file_operations xqmstat_proc_fops = {
 };
 #endif /* CONFIG_XFS_QUOTA */
 
+#ifdef CONFIG_PROC_FS
 int
 xfs_init_procfs(void)
 {
 	if (!proc_mkdir("fs/xfs", NULL))
+		return -ENOMEM;
+
+	if (!proc_symlink("fs/xfs/stat", NULL,
+			  "/sys/fs/xfs/stats/stats"))
 		goto out;
 
-	if (!proc_create("fs/xfs/stat", 0, NULL,
-			 &xfs_stat_proc_fops))
-		goto out_remove_xfs_dir;
 #ifdef CONFIG_XFS_QUOTA
 	if (!proc_create("fs/xfs/xqmstat", 0, NULL,
 			 &xqmstat_proc_fops))
-		goto out_remove_stat_file;
+		goto out;
 	if (!proc_create("fs/xfs/xqm", 0, NULL,
 			 &xqm_proc_fops))
-		goto out_remove_xqmstat_file;
+		goto out;
 #endif
 	return 0;
 
-#ifdef CONFIG_XFS_QUOTA
- out_remove_xqmstat_file:
-	remove_proc_entry("fs/xfs/xqmstat", NULL);
- out_remove_stat_file:
-	remove_proc_entry("fs/xfs/stat", NULL);
-#endif
- out_remove_xfs_dir:
-	remove_proc_entry("fs/xfs", NULL);
- out:
+out:
+	remove_proc_subtree("fs/xfs", NULL);
 	return -ENOMEM;
 }
 
 void
 xfs_cleanup_procfs(void)
 {
-#ifdef CONFIG_XFS_QUOTA
-	remove_proc_entry("fs/xfs/xqm", NULL);
-	remove_proc_entry("fs/xfs/xqmstat", NULL);
-#endif
-	remove_proc_entry("fs/xfs/stat", NULL);
-	remove_proc_entry("fs/xfs", NULL);
+	remove_proc_subtree("fs/xfs", NULL);
 }
+#endif /* CONFIG_PROC_FS */
diff --git a/fs/xfs/xfs_stats.h b/fs/xfs/xfs_stats.h
index c8f238b8299a..483b0eff1988 100644
--- a/fs/xfs/xfs_stats.h
+++ b/fs/xfs/xfs_stats.h
@@ -19,8 +19,6 @@
 #define __XFS_STATS_H__
 
 
-#if defined(CONFIG_PROC_FS) && !defined(XFS_STATS_OFF)
-
 #include <linux/percpu.h>
 
 /*
@@ -215,15 +213,29 @@ struct xfsstats {
 	__uint64_t		xs_read_bytes;
 };
 
-DECLARE_PER_CPU(struct xfsstats, xfsstats);
+int xfs_stats_format(struct xfsstats __percpu *stats, char *buf);
+void xfs_stats_clearall(struct xfsstats __percpu *stats);
+extern struct xstats xfsstats;
 
-/*
- * We don't disable preempt, not too worried about poking the
- * wrong CPU's stat for now (also aggregated before reporting).
- */
-#define XFS_STATS_INC(v)	(per_cpu(xfsstats, current_cpu()).v++)
-#define XFS_STATS_DEC(v)	(per_cpu(xfsstats, current_cpu()).v--)
-#define XFS_STATS_ADD(v, inc)	(per_cpu(xfsstats, current_cpu()).v += (inc))
+#define XFS_STATS_INC(mp, v)					\
+do {								\
+	per_cpu_ptr(xfsstats.xs_stats, current_cpu())->v++;	\
+	per_cpu_ptr(mp->m_stats.xs_stats, current_cpu())->v++;	\
+} while (0)
+
+#define XFS_STATS_DEC(mp, v)					\
+do {								\
+	per_cpu_ptr(xfsstats.xs_stats, current_cpu())->v--;	\
+	per_cpu_ptr(mp->m_stats.xs_stats, current_cpu())->v--;	\
+} while (0)
+
+#define XFS_STATS_ADD(mp, v, inc)					\
+do {									\
+	per_cpu_ptr(xfsstats.xs_stats, current_cpu())->v += (inc);	\
+	per_cpu_ptr(mp->m_stats.xs_stats, current_cpu())->v += (inc);	\
+} while (0)
+
+#if defined(CONFIG_PROC_FS)
 
 extern int xfs_init_procfs(void);
 extern void xfs_cleanup_procfs(void);
@@ -231,10 +243,6 @@ extern void xfs_cleanup_procfs(void);
 
 #else	/* !CONFIG_PROC_FS */
 
-# define XFS_STATS_INC(count)
-# define XFS_STATS_DEC(count)
-# define XFS_STATS_ADD(count, inc)
-
 static inline int xfs_init_procfs(void)
 {
 	return 0;
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 904f637cfa5f..187e14b696c2 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -45,6 +45,7 @@
 #include "xfs_filestream.h"
 #include "xfs_quota.h"
 #include "xfs_sysfs.h"
+#include "xfs_ondisk.h"
 
 #include <linux/namei.h>
 #include <linux/init.h>
@@ -65,83 +66,85 @@ static struct kset *xfs_kset;		/* top-level xfs sysfs dir */
 static struct xfs_kobj xfs_dbg_kobj;	/* global debug sysfs attrs */
 #endif
 
-#define MNTOPT_LOGBUFS	"logbufs"	/* number of XFS log buffers */
-#define MNTOPT_LOGBSIZE	"logbsize"	/* size of XFS log buffers */
-#define MNTOPT_LOGDEV	"logdev"	/* log device */
-#define MNTOPT_RTDEV	"rtdev"		/* realtime I/O device */
-#define MNTOPT_BIOSIZE	"biosize"	/* log2 of preferred buffered io size */
-#define MNTOPT_WSYNC	"wsync"		/* safe-mode nfs compatible mount */
-#define MNTOPT_NOALIGN	"noalign"	/* turn off stripe alignment */
-#define MNTOPT_SWALLOC	"swalloc"	/* turn on stripe width allocation */
-#define MNTOPT_SUNIT	"sunit"		/* data volume stripe unit */
-#define MNTOPT_SWIDTH	"swidth"	/* data volume stripe width */
-#define MNTOPT_NOUUID	"nouuid"	/* ignore filesystem UUID */
-#define MNTOPT_MTPT	"mtpt"		/* filesystem mount point */
-#define MNTOPT_GRPID	"grpid"		/* group-ID from parent directory */
-#define MNTOPT_NOGRPID	"nogrpid"	/* group-ID from current process */
-#define MNTOPT_BSDGROUPS    "bsdgroups"    /* group-ID from parent directory */
-#define MNTOPT_SYSVGROUPS   "sysvgroups"   /* group-ID from current process */
-#define MNTOPT_ALLOCSIZE    "allocsize"    /* preferred allocation size */
-#define MNTOPT_NORECOVERY   "norecovery"   /* don't run XFS recovery */
-#define MNTOPT_BARRIER	"barrier"	/* use writer barriers for log write and
-					 * unwritten extent conversion */
-#define MNTOPT_NOBARRIER "nobarrier"	/* .. disable */
-#define MNTOPT_64BITINODE   "inode64"	/* inodes can be allocated anywhere */
-#define MNTOPT_32BITINODE   "inode32"	/* inode allocation limited to
-					 * XFS_MAXINUMBER_32 */
-#define MNTOPT_IKEEP	"ikeep"		/* do not free empty inode clusters */
-#define MNTOPT_NOIKEEP	"noikeep"	/* free empty inode clusters */
-#define MNTOPT_LARGEIO	   "largeio"	/* report large I/O sizes in stat() */
-#define MNTOPT_NOLARGEIO   "nolargeio"	/* do not report large I/O sizes
-					 * in stat(). */
-#define MNTOPT_ATTR2	"attr2"		/* do use attr2 attribute format */
-#define MNTOPT_NOATTR2	"noattr2"	/* do not use attr2 attribute format */
-#define MNTOPT_FILESTREAM  "filestreams" /* use filestreams allocator */
-#define MNTOPT_QUOTA	"quota"		/* disk quotas (user) */
-#define MNTOPT_NOQUOTA	"noquota"	/* no quotas */
-#define MNTOPT_USRQUOTA	"usrquota"	/* user quota enabled */
-#define MNTOPT_GRPQUOTA	"grpquota"	/* group quota enabled */
-#define MNTOPT_PRJQUOTA	"prjquota"	/* project quota enabled */
-#define MNTOPT_UQUOTA	"uquota"	/* user quota (IRIX variant) */
-#define MNTOPT_GQUOTA	"gquota"	/* group quota (IRIX variant) */
-#define MNTOPT_PQUOTA	"pquota"	/* project quota (IRIX variant) */
-#define MNTOPT_UQUOTANOENF "uqnoenforce"/* user quota limit enforcement */
-#define MNTOPT_GQUOTANOENF "gqnoenforce"/* group quota limit enforcement */
-#define MNTOPT_PQUOTANOENF "pqnoenforce"/* project quota limit enforcement */
-#define MNTOPT_QUOTANOENF  "qnoenforce"	/* same as uqnoenforce */
-#define MNTOPT_DISCARD	   "discard"	/* Discard unused blocks */
-#define MNTOPT_NODISCARD   "nodiscard"	/* Do not discard unused blocks */
-
-#define MNTOPT_DAX	"dax"		/* Enable direct access to bdev pages */
-
 /*
  * Table driven mount option parser.
- *
- * Currently only used for remount, but it will be used for mount
- * in the future, too.
  */
 enum {
-	Opt_barrier,
-	Opt_nobarrier,
-	Opt_inode64,
-	Opt_inode32,
-	Opt_err
+	Opt_logbufs, Opt_logbsize, Opt_logdev, Opt_rtdev, Opt_biosize,
+	Opt_wsync, Opt_noalign, Opt_swalloc, Opt_sunit, Opt_swidth, Opt_nouuid,
+	Opt_mtpt, Opt_grpid, Opt_nogrpid, Opt_bsdgroups, Opt_sysvgroups,
+	Opt_allocsize, Opt_norecovery, Opt_barrier, Opt_nobarrier,
+	Opt_inode64, Opt_inode32, Opt_ikeep, Opt_noikeep,
+	Opt_largeio, Opt_nolargeio, Opt_attr2, Opt_noattr2, Opt_filestreams,
+	Opt_quota, Opt_noquota, Opt_usrquota, Opt_grpquota, Opt_prjquota,
+	Opt_uquota, Opt_gquota, Opt_pquota,
+	Opt_uqnoenforce, Opt_gqnoenforce, Opt_pqnoenforce, Opt_qnoenforce,
+	Opt_discard, Opt_nodiscard, Opt_dax, Opt_err,
 };
 
 static const match_table_t tokens = {
-	{Opt_barrier, "barrier"},
-	{Opt_nobarrier, "nobarrier"},
-	{Opt_inode64, "inode64"},
-	{Opt_inode32, "inode32"},
-	{Opt_err, NULL}
+	{Opt_logbufs,	"logbufs=%u"},	/* number of XFS log buffers */
+	{Opt_logbsize,	"logbsize=%s"},	/* size of XFS log buffers */
+	{Opt_logdev,	"logdev=%s"},	/* log device */
+	{Opt_rtdev,	"rtdev=%s"},	/* realtime I/O device */
+	{Opt_biosize,	"biosize=%u"},	/* log2 of preferred buffered io size */
+	{Opt_wsync,	"wsync"},	/* safe-mode nfs compatible mount */
+	{Opt_noalign,	"noalign"},	/* turn off stripe alignment */
+	{Opt_swalloc,	"swalloc"},	/* turn on stripe width allocation */
+	{Opt_sunit,	"sunit=%u"},	/* data volume stripe unit */
+	{Opt_swidth,	"swidth=%u"},	/* data volume stripe width */
+	{Opt_nouuid,	"nouuid"},	/* ignore filesystem UUID */
+	{Opt_mtpt,	"mtpt"},	/* filesystem mount point */
+	{Opt_grpid,	"grpid"},	/* group-ID from parent directory */
+	{Opt_nogrpid,	"nogrpid"},	/* group-ID from current process */
+	{Opt_bsdgroups,	"bsdgroups"},	/* group-ID from parent directory */
+	{Opt_sysvgroups,"sysvgroups"},	/* group-ID from current process */
+	{Opt_allocsize,	"allocsize=%s"},/* preferred allocation size */
+	{Opt_norecovery,"norecovery"},	/* don't run XFS recovery */
+	{Opt_barrier,	"barrier"},	/* use writer barriers for log write and
+					 * unwritten extent conversion */
+	{Opt_nobarrier,	"nobarrier"},	/* .. disable */
+	{Opt_inode64,	"inode64"},	/* inodes can be allocated anywhere */
+	{Opt_inode32,   "inode32"},	/* inode allocation limited to
+					 * XFS_MAXINUMBER_32 */
+	{Opt_ikeep,	"ikeep"},	/* do not free empty inode clusters */
+	{Opt_noikeep,	"noikeep"},	/* free empty inode clusters */
+	{Opt_largeio,	"largeio"},	/* report large I/O sizes in stat() */
+	{Opt_nolargeio,	"nolargeio"},	/* do not report large I/O sizes
+					 * in stat(). */
+	{Opt_attr2,	"attr2"},	/* do use attr2 attribute format */
+	{Opt_noattr2,	"noattr2"},	/* do not use attr2 attribute format */
+	{Opt_filestreams,"filestreams"},/* use filestreams allocator */
+	{Opt_quota,	"quota"},	/* disk quotas (user) */
+	{Opt_noquota,	"noquota"},	/* no quotas */
+	{Opt_usrquota,	"usrquota"},	/* user quota enabled */
+	{Opt_grpquota,	"grpquota"},	/* group quota enabled */
+	{Opt_prjquota,	"prjquota"},	/* project quota enabled */
+	{Opt_uquota,	"uquota"},	/* user quota (IRIX variant) */
+	{Opt_gquota,	"gquota"},	/* group quota (IRIX variant) */
+	{Opt_pquota,	"pquota"},	/* project quota (IRIX variant) */
+	{Opt_uqnoenforce,"uqnoenforce"},/* user quota limit enforcement */
+	{Opt_gqnoenforce,"gqnoenforce"},/* group quota limit enforcement */
+	{Opt_pqnoenforce,"pqnoenforce"},/* project quota limit enforcement */
+	{Opt_qnoenforce, "qnoenforce"},	/* same as uqnoenforce */
+	{Opt_discard,	"discard"},	/* Discard unused blocks */
+	{Opt_nodiscard,	"nodiscard"},	/* Do not discard unused blocks */
+
+	{Opt_dax,	"dax"},		/* Enable direct access to bdev pages */
+	{Opt_err,	NULL},
 };
 
 
-STATIC unsigned long
-suffix_kstrtoint(char *s, unsigned int base, int *res)
+STATIC int
+suffix_kstrtoint(const substring_t *s, unsigned int base, int *res)
 {
 	int	last, shift_left_factor = 0, _res;
-	char	*value = s;
+	char	*value;
+	int	ret = 0;
+
+	value = match_strdup(s);
+	if (!value)
+		return -ENOMEM;
 
 	last = strlen(value) - 1;
 	if (value[last] == 'K' || value[last] == 'k') {
@@ -157,10 +160,11 @@ suffix_kstrtoint(char *s, unsigned int base, int *res)
 		value[last] = '\0';
 	}
 
-	if (kstrtoint(s, base, &_res))
-		return -EINVAL;
+	if (kstrtoint(value, base, &_res))
+		ret = -EINVAL;
+	kfree(value);
 	*res = _res << shift_left_factor;
-	return 0;
+	return ret;
 }
 
 /*
@@ -169,14 +173,19 @@ suffix_kstrtoint(char *s, unsigned int base, int *res)
  *
  * Note that this function leaks the various device name allocations on
  * failure.  The caller takes care of them.
+ *
+ * *sb is const because this is also used to test options on the remount
+ * path, and we don't want this to have any side effects at remount time.
+ * Today this function does not change *sb, but just to future-proof...
  */
 STATIC int
 xfs_parseargs(
 	struct xfs_mount	*mp,
 	char			*options)
 {
-	struct super_block	*sb = mp->m_super;
-	char			*this_char, *value;
+	const struct super_block *sb = mp->m_super;
+	char			*p;
+	substring_t		args[MAX_OPT_ARGS];
 	int			dsunit = 0;
 	int			dswidth = 0;
 	int			iosize = 0;
@@ -217,152 +226,152 @@ xfs_parseargs(
 	if (!options)
 		goto done;
 
-	while ((this_char = strsep(&options, ",")) != NULL) {
-		if (!*this_char)
+	while ((p = strsep(&options, ",")) != NULL) {
+		int		token;
+
+		if (!*p)
 			continue;
-		if ((value = strchr(this_char, '=')) != NULL)
-			*value++ = 0;
 
-		if (!strcmp(this_char, MNTOPT_LOGBUFS)) {
-			if (!value || !*value) {
-				xfs_warn(mp, "%s option requires an argument",
-					this_char);
-				return -EINVAL;
-			}
-			if (kstrtoint(value, 10, &mp->m_logbufs))
-				return -EINVAL;
-		} else if (!strcmp(this_char, MNTOPT_LOGBSIZE)) {
-			if (!value || !*value) {
-				xfs_warn(mp, "%s option requires an argument",
-					this_char);
-				return -EINVAL;
-			}
-			if (suffix_kstrtoint(value, 10, &mp->m_logbsize))
+		token = match_token(p, tokens, args);
+		switch (token) {
+		case Opt_logbufs:
+			if (match_int(args, &mp->m_logbufs))
 				return -EINVAL;
-		} else if (!strcmp(this_char, MNTOPT_LOGDEV)) {
-			if (!value || !*value) {
-				xfs_warn(mp, "%s option requires an argument",
-					this_char);
+			break;
+		case Opt_logbsize:
+			if (suffix_kstrtoint(args, 10, &mp->m_logbsize))
 				return -EINVAL;
-			}
-			mp->m_logname = kstrndup(value, MAXNAMELEN, GFP_KERNEL);
+			break;
+		case Opt_logdev:
+			mp->m_logname = match_strdup(args);
 			if (!mp->m_logname)
 				return -ENOMEM;
-		} else if (!strcmp(this_char, MNTOPT_MTPT)) {
-			xfs_warn(mp, "%s option not allowed on this system",
-				this_char);
+			break;
+		case Opt_mtpt:
+			xfs_warn(mp, "%s option not allowed on this system", p);
 			return -EINVAL;
-		} else if (!strcmp(this_char, MNTOPT_RTDEV)) {
-			if (!value || !*value) {
-				xfs_warn(mp, "%s option requires an argument",
-					this_char);
-				return -EINVAL;
-			}
-			mp->m_rtname = kstrndup(value, MAXNAMELEN, GFP_KERNEL);
+		case Opt_rtdev:
+			mp->m_rtname = match_strdup(args);
 			if (!mp->m_rtname)
 				return -ENOMEM;
-		} else if (!strcmp(this_char, MNTOPT_ALLOCSIZE) ||
-			   !strcmp(this_char, MNTOPT_BIOSIZE)) {
-			if (!value || !*value) {
-				xfs_warn(mp, "%s option requires an argument",
-					this_char);
-				return -EINVAL;
-			}
-			if (suffix_kstrtoint(value, 10, &iosize))
+			break;
+		case Opt_allocsize:
+		case Opt_biosize:
+			if (suffix_kstrtoint(args, 10, &iosize))
 				return -EINVAL;
 			iosizelog = ffs(iosize) - 1;
-		} else if (!strcmp(this_char, MNTOPT_GRPID) ||
-			   !strcmp(this_char, MNTOPT_BSDGROUPS)) {
+			break;
+		case Opt_grpid:
+		case Opt_bsdgroups:
 			mp->m_flags |= XFS_MOUNT_GRPID;
-		} else if (!strcmp(this_char, MNTOPT_NOGRPID) ||
-			   !strcmp(this_char, MNTOPT_SYSVGROUPS)) {
+			break;
+		case Opt_nogrpid:
+		case Opt_sysvgroups:
 			mp->m_flags &= ~XFS_MOUNT_GRPID;
-		} else if (!strcmp(this_char, MNTOPT_WSYNC)) {
+			break;
+		case Opt_wsync:
 			mp->m_flags |= XFS_MOUNT_WSYNC;
-		} else if (!strcmp(this_char, MNTOPT_NORECOVERY)) {
+			break;
+		case Opt_norecovery:
 			mp->m_flags |= XFS_MOUNT_NORECOVERY;
-		} else if (!strcmp(this_char, MNTOPT_NOALIGN)) {
+			break;
+		case Opt_noalign:
 			mp->m_flags |= XFS_MOUNT_NOALIGN;
-		} else if (!strcmp(this_char, MNTOPT_SWALLOC)) {
+			break;
+		case Opt_swalloc:
 			mp->m_flags |= XFS_MOUNT_SWALLOC;
-		} else if (!strcmp(this_char, MNTOPT_SUNIT)) {
-			if (!value || !*value) {
-				xfs_warn(mp, "%s option requires an argument",
-					this_char);
-				return -EINVAL;
-			}
-			if (kstrtoint(value, 10, &dsunit))
-				return -EINVAL;
-		} else if (!strcmp(this_char, MNTOPT_SWIDTH)) {
-			if (!value || !*value) {
-				xfs_warn(mp, "%s option requires an argument",
-					this_char);
+			break;
+		case Opt_sunit:
+			if (match_int(args, &dsunit))
 				return -EINVAL;
-			}
-			if (kstrtoint(value, 10, &dswidth))
+			break;
+		case Opt_swidth:
+			if (match_int(args, &dswidth))
 				return -EINVAL;
-		} else if (!strcmp(this_char, MNTOPT_32BITINODE)) {
+			break;
+		case Opt_inode32:
 			mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
-		} else if (!strcmp(this_char, MNTOPT_64BITINODE)) {
+			break;
+		case Opt_inode64:
 			mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
-		} else if (!strcmp(this_char, MNTOPT_NOUUID)) {
+			break;
+		case Opt_nouuid:
 			mp->m_flags |= XFS_MOUNT_NOUUID;
-		} else if (!strcmp(this_char, MNTOPT_BARRIER)) {
+			break;
+		case Opt_barrier:
 			mp->m_flags |= XFS_MOUNT_BARRIER;
-		} else if (!strcmp(this_char, MNTOPT_NOBARRIER)) {
+			break;
+		case Opt_nobarrier:
 			mp->m_flags &= ~XFS_MOUNT_BARRIER;
-		} else if (!strcmp(this_char, MNTOPT_IKEEP)) {
+			break;
+		case Opt_ikeep:
 			mp->m_flags |= XFS_MOUNT_IKEEP;
-		} else if (!strcmp(this_char, MNTOPT_NOIKEEP)) {
+			break;
+		case Opt_noikeep:
 			mp->m_flags &= ~XFS_MOUNT_IKEEP;
-		} else if (!strcmp(this_char, MNTOPT_LARGEIO)) {
+			break;
+		case Opt_largeio:
 			mp->m_flags &= ~XFS_MOUNT_COMPAT_IOSIZE;
-		} else if (!strcmp(this_char, MNTOPT_NOLARGEIO)) {
+			break;
+		case Opt_nolargeio:
 			mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
-		} else if (!strcmp(this_char, MNTOPT_ATTR2)) {
+			break;
+		case Opt_attr2:
 			mp->m_flags |= XFS_MOUNT_ATTR2;
-		} else if (!strcmp(this_char, MNTOPT_NOATTR2)) {
+			break;
+		case Opt_noattr2:
 			mp->m_flags &= ~XFS_MOUNT_ATTR2;
 			mp->m_flags |= XFS_MOUNT_NOATTR2;
-		} else if (!strcmp(this_char, MNTOPT_FILESTREAM)) {
+			break;
+		case Opt_filestreams:
 			mp->m_flags |= XFS_MOUNT_FILESTREAMS;
-		} else if (!strcmp(this_char, MNTOPT_NOQUOTA)) {
+			break;
+		case Opt_noquota:
 			mp->m_qflags &= ~XFS_ALL_QUOTA_ACCT;
 			mp->m_qflags &= ~XFS_ALL_QUOTA_ENFD;
 			mp->m_qflags &= ~XFS_ALL_QUOTA_ACTIVE;
-		} else if (!strcmp(this_char, MNTOPT_QUOTA) ||
-			   !strcmp(this_char, MNTOPT_UQUOTA) ||
-			   !strcmp(this_char, MNTOPT_USRQUOTA)) {
+			break;
+		case Opt_quota:
+		case Opt_uquota:
+		case Opt_usrquota:
 			mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE |
 					 XFS_UQUOTA_ENFD);
-		} else if (!strcmp(this_char, MNTOPT_QUOTANOENF) ||
-			   !strcmp(this_char, MNTOPT_UQUOTANOENF)) {
+			break;
+		case Opt_qnoenforce:
+		case Opt_uqnoenforce:
 			mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE);
 			mp->m_qflags &= ~XFS_UQUOTA_ENFD;
-		} else if (!strcmp(this_char, MNTOPT_PQUOTA) ||
-			   !strcmp(this_char, MNTOPT_PRJQUOTA)) {
+			break;
+		case Opt_pquota:
+		case Opt_prjquota:
 			mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE |
 					 XFS_PQUOTA_ENFD);
-		} else if (!strcmp(this_char, MNTOPT_PQUOTANOENF)) {
+			break;
+		case Opt_pqnoenforce:
 			mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE);
 			mp->m_qflags &= ~XFS_PQUOTA_ENFD;
-		} else if (!strcmp(this_char, MNTOPT_GQUOTA) ||
-			   !strcmp(this_char, MNTOPT_GRPQUOTA)) {
+		case Opt_gquota:
+		case Opt_grpquota:
 			mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE |
 					 XFS_GQUOTA_ENFD);
-		} else if (!strcmp(this_char, MNTOPT_GQUOTANOENF)) {
+			break;
+		case Opt_gqnoenforce:
 			mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE);
 			mp->m_qflags &= ~XFS_GQUOTA_ENFD;
-		} else if (!strcmp(this_char, MNTOPT_DISCARD)) {
+			break;
+		case Opt_discard:
 			mp->m_flags |= XFS_MOUNT_DISCARD;
-		} else if (!strcmp(this_char, MNTOPT_NODISCARD)) {
+			break;
+		case Opt_nodiscard:
 			mp->m_flags &= ~XFS_MOUNT_DISCARD;
+			break;
 #ifdef CONFIG_FS_DAX
-		} else if (!strcmp(this_char, MNTOPT_DAX)) {
+		case Opt_dax:
 			mp->m_flags |= XFS_MOUNT_DAX;
+			break;
 #endif
-		} else {
-			xfs_warn(mp, "unknown mount option [%s].", this_char);
+		default:
+			xfs_warn(mp, "unknown mount option [%s].", p);
 			return -EINVAL;
 		}
 	}
@@ -461,25 +470,25 @@ xfs_showargs(
 {
 	static struct proc_xfs_info xfs_info_set[] = {
 		/* the few simple ones we can get from the mount struct */
-		{ XFS_MOUNT_IKEEP,		"," MNTOPT_IKEEP },
-		{ XFS_MOUNT_WSYNC,		"," MNTOPT_WSYNC },
-		{ XFS_MOUNT_NOALIGN,		"," MNTOPT_NOALIGN },
-		{ XFS_MOUNT_SWALLOC,		"," MNTOPT_SWALLOC },
-		{ XFS_MOUNT_NOUUID,		"," MNTOPT_NOUUID },
-		{ XFS_MOUNT_NORECOVERY,		"," MNTOPT_NORECOVERY },
-		{ XFS_MOUNT_ATTR2,		"," MNTOPT_ATTR2 },
-		{ XFS_MOUNT_FILESTREAMS,	"," MNTOPT_FILESTREAM },
-		{ XFS_MOUNT_GRPID,		"," MNTOPT_GRPID },
-		{ XFS_MOUNT_DISCARD,		"," MNTOPT_DISCARD },
-		{ XFS_MOUNT_SMALL_INUMS,	"," MNTOPT_32BITINODE },
-		{ XFS_MOUNT_DAX,		"," MNTOPT_DAX },
+		{ XFS_MOUNT_IKEEP,		",ikeep" },
+		{ XFS_MOUNT_WSYNC,		",wsync" },
+		{ XFS_MOUNT_NOALIGN,		",noalign" },
+		{ XFS_MOUNT_SWALLOC,		",swalloc" },
+		{ XFS_MOUNT_NOUUID,		",nouuid" },
+		{ XFS_MOUNT_NORECOVERY,		",norecovery" },
+		{ XFS_MOUNT_ATTR2,		",attr2" },
+		{ XFS_MOUNT_FILESTREAMS,	",filestreams" },
+		{ XFS_MOUNT_GRPID,		",grpid" },
+		{ XFS_MOUNT_DISCARD,		",discard" },
+		{ XFS_MOUNT_SMALL_INUMS,	",inode32" },
+		{ XFS_MOUNT_DAX,		",dax" },
 		{ 0, NULL }
 	};
 	static struct proc_xfs_info xfs_info_unset[] = {
 		/* the few simple ones we can get from the mount struct */
-		{ XFS_MOUNT_COMPAT_IOSIZE,	"," MNTOPT_LARGEIO },
-		{ XFS_MOUNT_BARRIER,		"," MNTOPT_NOBARRIER },
-		{ XFS_MOUNT_SMALL_INUMS,	"," MNTOPT_64BITINODE },
+		{ XFS_MOUNT_COMPAT_IOSIZE,	",largeio" },
+		{ XFS_MOUNT_BARRIER,		",nobarrier" },
+		{ XFS_MOUNT_SMALL_INUMS,	",inode64" },
 		{ 0, NULL }
 	};
 	struct proc_xfs_info	*xfs_infop;
@@ -494,46 +503,46 @@ xfs_showargs(
 	}
 
 	if (mp->m_flags & XFS_MOUNT_DFLT_IOSIZE)
-		seq_printf(m, "," MNTOPT_ALLOCSIZE "=%dk",
+		seq_printf(m, ",allocsize=%dk",
 				(int)(1 << mp->m_writeio_log) >> 10);
 
 	if (mp->m_logbufs > 0)
-		seq_printf(m, "," MNTOPT_LOGBUFS "=%d", mp->m_logbufs);
+		seq_printf(m, ",logbufs=%d", mp->m_logbufs);
 	if (mp->m_logbsize > 0)
-		seq_printf(m, "," MNTOPT_LOGBSIZE "=%dk", mp->m_logbsize >> 10);
+		seq_printf(m, ",logbsize=%dk", mp->m_logbsize >> 10);
 
 	if (mp->m_logname)
-		seq_show_option(m, MNTOPT_LOGDEV, mp->m_logname);
+		seq_show_option(m, "logdev", mp->m_logname);
 	if (mp->m_rtname)
-		seq_show_option(m, MNTOPT_RTDEV, mp->m_rtname);
+		seq_show_option(m, "rtdev", mp->m_rtname);
 
 	if (mp->m_dalign > 0)
-		seq_printf(m, "," MNTOPT_SUNIT "=%d",
+		seq_printf(m, ",sunit=%d",
 				(int)XFS_FSB_TO_BB(mp, mp->m_dalign));
 	if (mp->m_swidth > 0)
-		seq_printf(m, "," MNTOPT_SWIDTH "=%d",
+		seq_printf(m, ",swidth=%d",
 				(int)XFS_FSB_TO_BB(mp, mp->m_swidth));
 
 	if (mp->m_qflags & (XFS_UQUOTA_ACCT|XFS_UQUOTA_ENFD))
-		seq_puts(m, "," MNTOPT_USRQUOTA);
+		seq_puts(m, ",usrquota");
 	else if (mp->m_qflags & XFS_UQUOTA_ACCT)
-		seq_puts(m, "," MNTOPT_UQUOTANOENF);
+		seq_puts(m, ",uqnoenforce");
 
 	if (mp->m_qflags & XFS_PQUOTA_ACCT) {
 		if (mp->m_qflags & XFS_PQUOTA_ENFD)
-			seq_puts(m, "," MNTOPT_PRJQUOTA);
+			seq_puts(m, ",prjquota");
 		else
-			seq_puts(m, "," MNTOPT_PQUOTANOENF);
+			seq_puts(m, ",pqnoenforce");
 	}
 	if (mp->m_qflags & XFS_GQUOTA_ACCT) {
 		if (mp->m_qflags & XFS_GQUOTA_ENFD)
-			seq_puts(m, "," MNTOPT_GRPQUOTA);
+			seq_puts(m, ",grpquota");
 		else
-			seq_puts(m, "," MNTOPT_GQUOTANOENF);
+			seq_puts(m, ",gqnoenforce");
 	}
 
 	if (!(mp->m_qflags & XFS_ALL_QUOTA_ACCT))
-		seq_puts(m, "," MNTOPT_NOQUOTA);
+		seq_puts(m, ",noquota");
 
 	return 0;
 }
@@ -547,10 +556,10 @@ xfs_max_file_offset(
 	/* Figure out maximum filesize, on Linux this can depend on
 	 * the filesystem blocksize (on 32 bit platforms).
 	 * __block_write_begin does this in an [unsigned] long...
-	 *      page->index << (PAGE_CACHE_SHIFT - bbits)
+	 *      page->index << (PAGE_SHIFT - bbits)
 	 * So, for page sized blocks (4K on 32 bit platforms),
 	 * this wraps at around 8Tb (hence MAX_LFS_FILESIZE which is
-	 *      (((u64)PAGE_CACHE_SIZE << (BITS_PER_LONG-1))-1)
+	 *      (((u64)PAGE_SIZE << (BITS_PER_LONG-1))-1)
 	 * but for smaller blocksizes it is less (bbits = log2 bsize).
 	 * Note1: get_block_t takes a long (implicit cast from above)
 	 * Note2: The Large Block Device (LBD and HAVE_SECTOR_T) patch
@@ -561,10 +570,10 @@ xfs_max_file_offset(
 #if BITS_PER_LONG == 32
 # if defined(CONFIG_LBDAF)
 	ASSERT(sizeof(sector_t) == 8);
-	pagefactor = PAGE_CACHE_SIZE;
+	pagefactor = PAGE_SIZE;
 	bitshift = BITS_PER_LONG;
 # else
-	pagefactor = PAGE_CACHE_SIZE >> (PAGE_CACHE_SHIFT - blockshift);
+	pagefactor = PAGE_SIZE >> (PAGE_SHIFT - blockshift);
 # endif
 #endif
 
@@ -572,23 +581,35 @@ xfs_max_file_offset(
 }
 
 /*
- * xfs_set_inode32() and xfs_set_inode64() are passed an agcount
- * because in the growfs case, mp->m_sb.sb_agcount is not updated
- * yet to the potentially higher ag count.
+ * Set parameters for inode allocation heuristics, taking into account
+ * filesystem size and inode32/inode64 mount options; i.e. specifically
+ * whether or not XFS_MOUNT_SMALL_INUMS is set.
+ *
+ * Inode allocation patterns are altered only if inode32 is requested
+ * (XFS_MOUNT_SMALL_INUMS), and the filesystem is sufficiently large.
+ * If altered, XFS_MOUNT_32BITINODES is set as well.
+ *
+ * An agcount independent of that in the mount structure is provided
+ * because in the growfs case, mp->m_sb.sb_agcount is not yet updated
+ * to the potentially higher ag count.
+ *
+ * Returns the maximum AG index which may contain inodes.
  */
 xfs_agnumber_t
-xfs_set_inode32(struct xfs_mount *mp, xfs_agnumber_t agcount)
+xfs_set_inode_alloc(
+	struct xfs_mount *mp,
+	xfs_agnumber_t	agcount)
 {
-	xfs_agnumber_t	index = 0;
+	xfs_agnumber_t	index;
 	xfs_agnumber_t	maxagi = 0;
 	xfs_sb_t	*sbp = &mp->m_sb;
 	xfs_agnumber_t	max_metadata;
 	xfs_agino_t	agino;
 	xfs_ino_t	ino;
-	xfs_perag_t	*pag;
 
-	/* Calculate how much should be reserved for inodes to meet
-	 * the max inode percentage.
+	/*
+	 * Calculate how much should be reserved for inodes to meet
+	 * the max inode percentage.  Used only for inode32.
 	 */
 	if (mp->m_maxicount) {
 		__uint64_t	icount;
@@ -602,54 +623,48 @@ xfs_set_inode32(struct xfs_mount *mp, xfs_agnumber_t agcount)
 		max_metadata = agcount;
 	}
 
+	/* Get the last possible inode in the filesystem */
 	agino =	XFS_OFFBNO_TO_AGINO(mp, sbp->sb_agblocks - 1, 0);
+	ino = XFS_AGINO_TO_INO(mp, agcount - 1, agino);
+
+	/*
+	 * If user asked for no more than 32-bit inodes, and the fs is
+	 * sufficiently large, set XFS_MOUNT_32BITINODES if we must alter
+	 * the allocator to accommodate the request.
+	 */
+	if ((mp->m_flags & XFS_MOUNT_SMALL_INUMS) && ino > XFS_MAXINUMBER_32)
+		mp->m_flags |= XFS_MOUNT_32BITINODES;
+	else
+		mp->m_flags &= ~XFS_MOUNT_32BITINODES;
 
 	for (index = 0; index < agcount; index++) {
-		ino = XFS_AGINO_TO_INO(mp, index, agino);
+		struct xfs_perag	*pag;
 
-		if (ino > XFS_MAXINUMBER_32) {
-			pag = xfs_perag_get(mp, index);
-			pag->pagi_inodeok = 0;
-			pag->pagf_metadata = 0;
-			xfs_perag_put(pag);
-			continue;
-		}
+		ino = XFS_AGINO_TO_INO(mp, index, agino);
 
 		pag = xfs_perag_get(mp, index);
-		pag->pagi_inodeok = 1;
-		maxagi++;
-		if (index < max_metadata)
-			pag->pagf_metadata = 1;
-		xfs_perag_put(pag);
-	}
-	mp->m_flags |= (XFS_MOUNT_32BITINODES |
-			XFS_MOUNT_SMALL_INUMS);
 
-	return maxagi;
-}
-
-xfs_agnumber_t
-xfs_set_inode64(struct xfs_mount *mp, xfs_agnumber_t agcount)
-{
-	xfs_agnumber_t index = 0;
-
-	for (index = 0; index < agcount; index++) {
-		struct xfs_perag	*pag;
+		if (mp->m_flags & XFS_MOUNT_32BITINODES) {
+			if (ino > XFS_MAXINUMBER_32) {
+				pag->pagi_inodeok = 0;
+				pag->pagf_metadata = 0;
+			} else {
+				pag->pagi_inodeok = 1;
+				maxagi++;
+				if (index < max_metadata)
+					pag->pagf_metadata = 1;
+				else
+					pag->pagf_metadata = 0;
+			}
+		} else {
+			pag->pagi_inodeok = 1;
+			pag->pagf_metadata = 0;
+		}
 
-		pag = xfs_perag_get(mp, index);
-		pag->pagi_inodeok = 1;
-		pag->pagf_metadata = 0;
 		xfs_perag_put(pag);
 	}
 
-	/* There is no need for lock protection on m_flags,
-	 * the rw_semaphore of the VFS superblock is locked
-	 * during mount/umount/remount operations, so this is
-	 * enough to avoid concurency on the m_flags field
-	 */
-	mp->m_flags &= ~(XFS_MOUNT_32BITINODES |
-			 XFS_MOUNT_SMALL_INUMS);
-	return index;
+	return (mp->m_flags & XFS_MOUNT_32BITINODES) ? maxagi : agcount;
 }
 
 STATIC int
@@ -838,17 +853,18 @@ xfs_init_mount_workqueues(
 		goto out_destroy_unwritten;
 
 	mp->m_reclaim_workqueue = alloc_workqueue("xfs-reclaim/%s",
-			WQ_FREEZABLE, 0, mp->m_fsname);
+			WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
 	if (!mp->m_reclaim_workqueue)
 		goto out_destroy_cil;
 
 	mp->m_log_workqueue = alloc_workqueue("xfs-log/%s",
-			WQ_FREEZABLE|WQ_HIGHPRI, 0, mp->m_fsname);
+			WQ_MEM_RECLAIM|WQ_FREEZABLE|WQ_HIGHPRI, 0,
+			mp->m_fsname);
 	if (!mp->m_log_workqueue)
 		goto out_destroy_reclaim;
 
 	mp->m_eofblocks_workqueue = alloc_workqueue("xfs-eofblocks/%s",
-			WQ_FREEZABLE, 0, mp->m_fsname);
+			WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
 	if (!mp->m_eofblocks_workqueue)
 		goto out_destroy_log;
 
@@ -922,7 +938,7 @@ xfs_fs_destroy_inode(
 
 	trace_xfs_destroy_inode(ip);
 
-	XFS_STATS_INC(vn_reclaim);
+	XFS_STATS_INC(ip->i_mount, vn_reclaim);
 
 	ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || ip->i_delayed_blks == 0);
 
@@ -983,8 +999,8 @@ xfs_fs_evict_inode(
 
 	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
-	XFS_STATS_INC(vn_rele);
-	XFS_STATS_INC(vn_remove);
+	XFS_STATS_INC(ip->i_mount, vn_rele);
+	XFS_STATS_INC(ip->i_mount, vn_remove);
 
 	xfs_inactive(ip);
 }
@@ -1165,6 +1181,27 @@ xfs_quiesce_attr(
 }
 
 STATIC int
+xfs_test_remount_options(
+	struct super_block	*sb,
+	struct xfs_mount	*mp,
+	char			*options)
+{
+	int			error = 0;
+	struct xfs_mount	*tmp_mp;
+
+	tmp_mp = kmem_zalloc(sizeof(*tmp_mp), KM_MAYFAIL);
+	if (!tmp_mp)
+		return -ENOMEM;
+
+	tmp_mp->m_super = sb;
+	error = xfs_parseargs(tmp_mp, options);
+	xfs_free_fsname(tmp_mp);
+	kfree(tmp_mp);
+
+	return error;
+}
+
+STATIC int
 xfs_fs_remount(
 	struct super_block	*sb,
 	int			*flags,
@@ -1176,6 +1213,11 @@ xfs_fs_remount(
 	char			*p;
 	int			error;
 
+	/* First, check for complete junk; i.e. invalid options */
+	error = xfs_test_remount_options(sb, mp, options);
+	if (error)
+		return error;
+
 	sync_filesystem(sb);
 	while ((p = strsep(&options, ",")) != NULL) {
 		int token;
@@ -1192,10 +1234,12 @@ xfs_fs_remount(
 			mp->m_flags &= ~XFS_MOUNT_BARRIER;
 			break;
 		case Opt_inode64:
-			mp->m_maxagi = xfs_set_inode64(mp, sbp->sb_agcount);
+			mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
+			mp->m_maxagi = xfs_set_inode_alloc(mp, sbp->sb_agcount);
 			break;
 		case Opt_inode32:
-			mp->m_maxagi = xfs_set_inode32(mp, sbp->sb_agcount);
+			mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
+			mp->m_maxagi = xfs_set_inode_alloc(mp, sbp->sb_agcount);
 			break;
 		default:
 			/*
@@ -1343,9 +1387,8 @@ xfs_finish_flags(
 	 */
 	if (xfs_sb_version_hascrc(&mp->m_sb) &&
 	    (mp->m_flags & XFS_MOUNT_NOATTR2)) {
-		xfs_warn(mp,
-"Cannot mount a V5 filesystem as %s. %s is always enabled for V5 filesystems.",
-			MNTOPT_NOATTR2, MNTOPT_ATTR2);
+		xfs_warn(mp, "Cannot mount a V5 filesystem as noattr2. "
+			     "attr2 is always enabled for V5 filesystems.");
 		return -EINVAL;
 	}
 
@@ -1474,9 +1517,16 @@ xfs_fs_fill_super(
 	if (error)
 		goto out_destroy_workqueues;
 
+	/* Allocate stats memory before we do operations that might use it */
+	mp->m_stats.xs_stats = alloc_percpu(struct xfsstats);
+	if (!mp->m_stats.xs_stats) {
+		error = -ENOMEM;
+		goto out_destroy_counters;
+	}
+
 	error = xfs_readsb(mp, flags);
 	if (error)
-		goto out_destroy_counters;
+		goto out_free_stats;
 
 	error = xfs_finish_flags(mp);
 	if (error)
@@ -1545,9 +1595,11 @@ xfs_fs_fill_super(
 	xfs_filestream_unmount(mp);
  out_free_sb:
 	xfs_freesb(mp);
+ out_free_stats:
+	free_percpu(mp->m_stats.xs_stats);
  out_destroy_counters:
 	xfs_destroy_percpu_counters(mp);
-out_destroy_workqueues:
+ out_destroy_workqueues:
 	xfs_destroy_mount_workqueues(mp);
  out_close_devices:
 	xfs_close_devices(mp);
@@ -1574,6 +1626,7 @@ xfs_fs_put_super(
 	xfs_unmountfs(mp);
 
 	xfs_freesb(mp);
+	free_percpu(mp->m_stats.xs_stats);
 	xfs_destroy_percpu_counters(mp);
 	xfs_destroy_mount_workqueues(mp);
 	xfs_close_devices(mp);
@@ -1703,8 +1756,8 @@ xfs_init_zones(void)
 
 	xfs_inode_zone =
 		kmem_zone_init_flags(sizeof(xfs_inode_t), "xfs_inode",
-			KM_ZONE_HWALIGN | KM_ZONE_RECLAIM | KM_ZONE_SPREAD,
-			xfs_fs_inode_init_once);
+			KM_ZONE_HWALIGN | KM_ZONE_RECLAIM | KM_ZONE_SPREAD |
+			KM_ZONE_ACCOUNT, xfs_fs_inode_init_once);
 	if (!xfs_inode_zone)
 		goto out_destroy_efi_zone;
 
@@ -1806,6 +1859,8 @@ init_xfs_fs(void)
 {
 	int			error;
 
+	xfs_check_ondisk_structs();
+
 	printk(KERN_INFO XFS_VERSION_STRING " with "
 			 XFS_BUILD_OPTIONS " enabled\n");
 
@@ -1838,19 +1893,32 @@ init_xfs_fs(void)
 	xfs_kset = kset_create_and_add("xfs", NULL, fs_kobj);
 	if (!xfs_kset) {
 		error = -ENOMEM;
-		goto out_sysctl_unregister;;
+		goto out_sysctl_unregister;
 	}
 
+	xfsstats.xs_kobj.kobject.kset = xfs_kset;
+
+	xfsstats.xs_stats = alloc_percpu(struct xfsstats);
+	if (!xfsstats.xs_stats) {
+		error = -ENOMEM;
+		goto out_kset_unregister;
+	}
+
+	error = xfs_sysfs_init(&xfsstats.xs_kobj, &xfs_stats_ktype, NULL,
+			       "stats");
+	if (error)
+		goto out_free_stats;
+
 #ifdef DEBUG
 	xfs_dbg_kobj.kobject.kset = xfs_kset;
 	error = xfs_sysfs_init(&xfs_dbg_kobj, &xfs_dbg_ktype, NULL, "debug");
 	if (error)
-		goto out_kset_unregister;
+		goto out_remove_stats_kobj;
 #endif
 
 	error = xfs_qm_init();
 	if (error)
-		goto out_remove_kobj;
+		goto out_remove_dbg_kobj;
 
 	error = register_filesystem(&xfs_fs_type);
 	if (error)
@@ -1859,11 +1927,15 @@ init_xfs_fs(void)
 
  out_qm_exit:
 	xfs_qm_exit();
- out_remove_kobj:
+ out_remove_dbg_kobj:
 #ifdef DEBUG
 	xfs_sysfs_del(&xfs_dbg_kobj);
- out_kset_unregister:
+ out_remove_stats_kobj:
 #endif
+	xfs_sysfs_del(&xfsstats.xs_kobj);
+ out_free_stats:
+	free_percpu(xfsstats.xs_stats);
+ out_kset_unregister:
 	kset_unregister(xfs_kset);
  out_sysctl_unregister:
 	xfs_sysctl_unregister();
@@ -1889,6 +1961,8 @@ exit_xfs_fs(void)
 #ifdef DEBUG
 	xfs_sysfs_del(&xfs_dbg_kobj);
 #endif
+	xfs_sysfs_del(&xfsstats.xs_kobj);
+	free_percpu(xfsstats.xs_stats);
 	kset_unregister(xfs_kset);
 	xfs_sysctl_unregister();
 	xfs_cleanup_procfs();
@@ -1896,6 +1970,7 @@ exit_xfs_fs(void)
 	xfs_mru_cache_uninit();
 	xfs_destroy_workqueues();
 	xfs_destroy_zones();
+	xfs_uuid_table_free();
 }
 
 module_init(init_xfs_fs);
diff --git a/fs/xfs/xfs_super.h b/fs/xfs/xfs_super.h
index 499058fea303..2dfb1ce4585f 100644
--- a/fs/xfs/xfs_super.h
+++ b/fs/xfs/xfs_super.h
@@ -65,8 +65,8 @@ extern __uint64_t xfs_max_file_offset(unsigned int);
 
 extern void xfs_flush_inodes(struct xfs_mount *mp);
 extern void xfs_blkdev_issue_flush(struct xfs_buftarg *);
-extern xfs_agnumber_t xfs_set_inode32(struct xfs_mount *, xfs_agnumber_t agcount);
-extern xfs_agnumber_t xfs_set_inode64(struct xfs_mount *, xfs_agnumber_t agcount);
+extern xfs_agnumber_t xfs_set_inode_alloc(struct xfs_mount *,
+					   xfs_agnumber_t agcount);
 
 extern const struct export_operations xfs_export_operations;
 extern const struct xattr_handler *xfs_xattr_handlers[];
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 996481eeb491..b44284c1adda 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -178,7 +178,6 @@ xfs_symlink(
 	struct xfs_bmap_free	free_list;
 	xfs_fsblock_t		first_block;
 	bool                    unlock_dp_on_error = false;
-	int			committed;
 	xfs_fileoff_t		first_fsb;
 	xfs_filblks_t		fs_blocks;
 	int			nmaps;
@@ -387,7 +386,7 @@ xfs_symlink(
 		xfs_trans_set_sync(tp);
 	}
 
-	error = xfs_bmap_finish(&tp, &free_list, &committed);
+	error = xfs_bmap_finish(&tp, &free_list, NULL);
 	if (error)
 		goto out_bmap_cancel;
 
@@ -434,7 +433,6 @@ xfs_inactive_symlink_rmt(
 	struct xfs_inode *ip)
 {
 	xfs_buf_t	*bp;
-	int		committed;
 	int		done;
 	int		error;
 	xfs_fsblock_t	first_block;
@@ -510,16 +508,10 @@ xfs_inactive_symlink_rmt(
 	/*
 	 * Commit the first transaction.  This logs the EFI and the inode.
 	 */
-	error = xfs_bmap_finish(&tp, &free_list, &committed);
+	error = xfs_bmap_finish(&tp, &free_list, ip);
 	if (error)
 		goto error_bmap_cancel;
 	/*
-	 * The transaction must have been committed, since there were
-	 * actually extents freed by xfs_bunmapi.  See xfs_bmap_finish.
-	 * The new tp has the extent freeing and EFDs.
-	 */
-	ASSERT(committed);
-	/*
 	 * The first xact was committed, so add the inode to the new one.
 	 * Mark it dirty so it will be logged and moved forward in the log as
 	 * part of every commit.
diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c
index a0c8067cea6f..aed74d3f8da9 100644
--- a/fs/xfs/xfs_sysctl.c
+++ b/fs/xfs/xfs_sysctl.c
@@ -19,6 +19,7 @@
 #include <linux/sysctl.h>
 #include <linux/proc_fs.h>
 #include "xfs_error.h"
+#include "xfs_stats.h"
 
 static struct ctl_table_header *xfs_table_header;
 
@@ -31,22 +32,12 @@ xfs_stats_clear_proc_handler(
 	size_t			*lenp,
 	loff_t			*ppos)
 {
-	int		c, ret, *valp = ctl->data;
-	__uint32_t	vn_active;
+	int		ret, *valp = ctl->data;
 
 	ret = proc_dointvec_minmax(ctl, write, buffer, lenp, ppos);
 
 	if (!ret && write && *valp) {
-		xfs_notice(NULL, "Clearing xfsstats");
-		for_each_possible_cpu(c) {
-			preempt_disable();
-			/* save vn_active, it's a universal truth! */
-			vn_active = per_cpu(xfsstats, c).vn_active;
-			memset(&per_cpu(xfsstats, c), 0,
-			       sizeof(struct xfsstats));
-			per_cpu(xfsstats, c).vn_active = vn_active;
-			preempt_enable();
-		}
+		xfs_stats_clearall(xfsstats.xs_stats);
 		xfs_stats_clear = 0;
 	}
 
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index aa03670851d8..6ced4f143494 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -18,14 +18,19 @@
 
 #include "xfs.h"
 #include "xfs_sysfs.h"
+#include "xfs_format.h"
 #include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_log.h"
 #include "xfs_log_priv.h"
+#include "xfs_stats.h"
+#include "xfs_mount.h"
 
 struct xfs_sysfs_attr {
 	struct attribute attr;
-	ssize_t (*show)(char *buf, void *data);
-	ssize_t (*store)(const char *buf, size_t count, void *data);
+	ssize_t (*show)(struct kobject *kobject, char *buf);
+	ssize_t (*store)(struct kobject *kobject, const char *buf,
+			 size_t count);
 };
 
 static inline struct xfs_sysfs_attr *
@@ -38,17 +43,102 @@ to_attr(struct attribute *attr)
 	static struct xfs_sysfs_attr xfs_sysfs_attr_##name = __ATTR_RW(name)
 #define XFS_SYSFS_ATTR_RO(name) \
 	static struct xfs_sysfs_attr xfs_sysfs_attr_##name = __ATTR_RO(name)
+#define XFS_SYSFS_ATTR_WO(name) \
+	static struct xfs_sysfs_attr xfs_sysfs_attr_##name = __ATTR_WO(name)
 
 #define ATTR_LIST(name) &xfs_sysfs_attr_##name.attr
 
+STATIC ssize_t
+xfs_sysfs_object_show(
+	struct kobject		*kobject,
+	struct attribute	*attr,
+	char			*buf)
+{
+	struct xfs_sysfs_attr *xfs_attr = to_attr(attr);
+
+	return xfs_attr->show ? xfs_attr->show(kobject, buf) : 0;
+}
+
+STATIC ssize_t
+xfs_sysfs_object_store(
+	struct kobject		*kobject,
+	struct attribute	*attr,
+	const char		*buf,
+	size_t			count)
+{
+	struct xfs_sysfs_attr *xfs_attr = to_attr(attr);
+
+	return xfs_attr->store ? xfs_attr->store(kobject, buf, count) : 0;
+}
+
+static const struct sysfs_ops xfs_sysfs_ops = {
+	.show = xfs_sysfs_object_show,
+	.store = xfs_sysfs_object_store,
+};
+
 /*
- * xfs_mount kobject. This currently has no attributes and thus no need for show
- * and store helpers. The mp kobject serves as the per-mount parent object that
- * is identified by the fsname under sysfs.
+ * xfs_mount kobject. The mp kobject also serves as the per-mount parent object
+ * that is identified by the fsname under sysfs.
  */
 
+static inline struct xfs_mount *
+to_mp(struct kobject *kobject)
+{
+	struct xfs_kobj *kobj = to_kobj(kobject);
+
+	return container_of(kobj, struct xfs_mount, m_kobj);
+}
+
+#ifdef DEBUG
+
+STATIC ssize_t
+fail_writes_store(
+	struct kobject		*kobject,
+	const char		*buf,
+	size_t			count)
+{
+	struct xfs_mount	*mp = to_mp(kobject);
+	int			ret;
+	int			val;
+
+	ret = kstrtoint(buf, 0, &val);
+	if (ret)
+		return ret;
+
+	if (val == 1)
+		mp->m_fail_writes = true;
+	else if (val == 0)
+		mp->m_fail_writes = false;
+	else
+		return -EINVAL;
+
+	return count;
+}
+
+STATIC ssize_t
+fail_writes_show(
+	struct kobject		*kobject,
+	char			*buf)
+{
+	struct xfs_mount	*mp = to_mp(kobject);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", mp->m_fail_writes ? 1 : 0);
+}
+XFS_SYSFS_ATTR_RW(fail_writes);
+
+#endif /* DEBUG */
+
+static struct attribute *xfs_mp_attrs[] = {
+#ifdef DEBUG
+	ATTR_LIST(fail_writes),
+#endif
+	NULL,
+};
+
 struct kobj_type xfs_mp_ktype = {
 	.release = xfs_sysfs_release,
+	.sysfs_ops = &xfs_sysfs_ops,
+	.default_attrs = xfs_mp_attrs,
 };
 
 #ifdef DEBUG
@@ -56,9 +146,9 @@ struct kobj_type xfs_mp_ktype = {
 
 STATIC ssize_t
 log_recovery_delay_store(
+	struct kobject	*kobject,
 	const char	*buf,
-	size_t		count,
-	void		*data)
+	size_t		count)
 {
 	int		ret;
 	int		val;
@@ -77,8 +167,8 @@ log_recovery_delay_store(
 
 STATIC ssize_t
 log_recovery_delay_show(
-	char	*buf,
-	void	*data)
+	struct kobject	*kobject,
+	char		*buf)
 {
 	return snprintf(buf, PAGE_SIZE, "%d\n", xfs_globals.log_recovery_delay);
 }
@@ -89,52 +179,87 @@ static struct attribute *xfs_dbg_attrs[] = {
 	NULL,
 };
 
+struct kobj_type xfs_dbg_ktype = {
+	.release = xfs_sysfs_release,
+	.sysfs_ops = &xfs_sysfs_ops,
+	.default_attrs = xfs_dbg_attrs,
+};
+
+#endif /* DEBUG */
+
+/* stats */
+
+static inline struct xstats *
+to_xstats(struct kobject *kobject)
+{
+	struct xfs_kobj *kobj = to_kobj(kobject);
+
+	return container_of(kobj, struct xstats, xs_kobj);
+}
+
 STATIC ssize_t
-xfs_dbg_show(
-	struct kobject		*kobject,
-	struct attribute	*attr,
-	char			*buf)
+stats_show(
+	struct kobject	*kobject,
+	char		*buf)
 {
-	struct xfs_sysfs_attr *xfs_attr = to_attr(attr);
+	struct xstats	*stats = to_xstats(kobject);
 
-	return xfs_attr->show ? xfs_attr->show(buf, NULL) : 0;
+	return xfs_stats_format(stats->xs_stats, buf);
 }
+XFS_SYSFS_ATTR_RO(stats);
 
 STATIC ssize_t
-xfs_dbg_store(
-	struct kobject		*kobject,
-	struct attribute	*attr,
-	const char		*buf,
-	size_t			count)
+stats_clear_store(
+	struct kobject	*kobject,
+	const char	*buf,
+	size_t		count)
 {
-	struct xfs_sysfs_attr *xfs_attr = to_attr(attr);
+	int		ret;
+	int		val;
+	struct xstats	*stats = to_xstats(kobject);
 
-	return xfs_attr->store ? xfs_attr->store(buf, count, NULL) : 0;
+	ret = kstrtoint(buf, 0, &val);
+	if (ret)
+		return ret;
+
+	if (val != 1)
+		return -EINVAL;
+
+	xfs_stats_clearall(stats->xs_stats);
+	return count;
 }
+XFS_SYSFS_ATTR_WO(stats_clear);
 
-static struct sysfs_ops xfs_dbg_ops = {
-	.show = xfs_dbg_show,
-	.store = xfs_dbg_store,
+static struct attribute *xfs_stats_attrs[] = {
+	ATTR_LIST(stats),
+	ATTR_LIST(stats_clear),
+	NULL,
 };
 
-struct kobj_type xfs_dbg_ktype = {
+struct kobj_type xfs_stats_ktype = {
 	.release = xfs_sysfs_release,
-	.sysfs_ops = &xfs_dbg_ops,
-	.default_attrs = xfs_dbg_attrs,
+	.sysfs_ops = &xfs_sysfs_ops,
+	.default_attrs = xfs_stats_attrs,
 };
 
-#endif /* DEBUG */
-
 /* xlog */
 
+static inline struct xlog *
+to_xlog(struct kobject *kobject)
+{
+	struct xfs_kobj *kobj = to_kobj(kobject);
+
+	return container_of(kobj, struct xlog, l_kobj);
+}
+
 STATIC ssize_t
 log_head_lsn_show(
-	char	*buf,
-	void	*data)
+	struct kobject	*kobject,
+	char		*buf)
 {
-	struct xlog *log = data;
 	int cycle;
 	int block;
+	struct xlog *log = to_xlog(kobject);
 
 	spin_lock(&log->l_icloglock);
 	cycle = log->l_curr_cycle;
@@ -147,12 +272,12 @@ XFS_SYSFS_ATTR_RO(log_head_lsn);
 
 STATIC ssize_t
 log_tail_lsn_show(
-	char	*buf,
-	void	*data)
+	struct kobject	*kobject,
+	char		*buf)
 {
-	struct xlog *log = data;
 	int cycle;
 	int block;
+	struct xlog *log = to_xlog(kobject);
 
 	xlog_crack_atomic_lsn(&log->l_tail_lsn, &cycle, &block);
 	return snprintf(buf, PAGE_SIZE, "%d:%d\n", cycle, block);
@@ -161,12 +286,13 @@ XFS_SYSFS_ATTR_RO(log_tail_lsn);
 
 STATIC ssize_t
 reserve_grant_head_show(
-	char	*buf,
-	void	*data)
+	struct kobject	*kobject,
+	char		*buf)
+
 {
-	struct xlog *log = data;
 	int cycle;
 	int bytes;
+	struct xlog *log = to_xlog(kobject);
 
 	xlog_crack_grant_head(&log->l_reserve_head.grant, &cycle, &bytes);
 	return snprintf(buf, PAGE_SIZE, "%d:%d\n", cycle, bytes);
@@ -175,65 +301,64 @@ XFS_SYSFS_ATTR_RO(reserve_grant_head);
 
 STATIC ssize_t
 write_grant_head_show(
-	char	*buf,
-	void	*data)
+	struct kobject	*kobject,
+	char		*buf)
 {
-	struct xlog *log = data;
 	int cycle;
 	int bytes;
+	struct xlog *log = to_xlog(kobject);
 
 	xlog_crack_grant_head(&log->l_write_head.grant, &cycle, &bytes);
 	return snprintf(buf, PAGE_SIZE, "%d:%d\n", cycle, bytes);
 }
 XFS_SYSFS_ATTR_RO(write_grant_head);
 
-static struct attribute *xfs_log_attrs[] = {
-	ATTR_LIST(log_head_lsn),
-	ATTR_LIST(log_tail_lsn),
-	ATTR_LIST(reserve_grant_head),
-	ATTR_LIST(write_grant_head),
-	NULL,
-};
-
-static inline struct xlog *
-to_xlog(struct kobject *kobject)
-{
-	struct xfs_kobj *kobj = to_kobj(kobject);
-	return container_of(kobj, struct xlog, l_kobj);
-}
-
+#ifdef DEBUG
 STATIC ssize_t
-xfs_log_show(
-	struct kobject		*kobject,
-	struct attribute	*attr,
-	char			*buf)
+log_badcrc_factor_store(
+	struct kobject	*kobject,
+	const char	*buf,
+	size_t		count)
 {
-	struct xlog *log = to_xlog(kobject);
-	struct xfs_sysfs_attr *xfs_attr = to_attr(attr);
+	struct xlog	*log = to_xlog(kobject);
+	int		ret;
+	uint32_t	val;
 
-	return xfs_attr->show ? xfs_attr->show(buf, log) : 0;
+	ret = kstrtouint(buf, 0, &val);
+	if (ret)
+		return ret;
+
+	log->l_badcrc_factor = val;
+
+	return count;
 }
 
 STATIC ssize_t
-xfs_log_store(
-	struct kobject		*kobject,
-	struct attribute	*attr,
-	const char		*buf,
-	size_t			count)
+log_badcrc_factor_show(
+	struct kobject	*kobject,
+	char		*buf)
 {
-	struct xlog *log = to_xlog(kobject);
-	struct xfs_sysfs_attr *xfs_attr = to_attr(attr);
+	struct xlog	*log = to_xlog(kobject);
 
-	return xfs_attr->store ? xfs_attr->store(buf, count, log) : 0;
+	return snprintf(buf, PAGE_SIZE, "%d\n", log->l_badcrc_factor);
 }
 
-static struct sysfs_ops xfs_log_ops = {
-	.show = xfs_log_show,
-	.store = xfs_log_store,
+XFS_SYSFS_ATTR_RW(log_badcrc_factor);
+#endif	/* DEBUG */
+
+static struct attribute *xfs_log_attrs[] = {
+	ATTR_LIST(log_head_lsn),
+	ATTR_LIST(log_tail_lsn),
+	ATTR_LIST(reserve_grant_head),
+	ATTR_LIST(write_grant_head),
+#ifdef DEBUG
+	ATTR_LIST(log_badcrc_factor),
+#endif
+	NULL,
 };
 
 struct kobj_type xfs_log_ktype = {
 	.release = xfs_sysfs_release,
-	.sysfs_ops = &xfs_log_ops,
+	.sysfs_ops = &xfs_sysfs_ops,
 	.default_attrs = xfs_log_attrs,
 };
diff --git a/fs/xfs/xfs_sysfs.h b/fs/xfs/xfs_sysfs.h
index 240eee35f342..be692e59938d 100644
--- a/fs/xfs/xfs_sysfs.h
+++ b/fs/xfs/xfs_sysfs.h
@@ -22,6 +22,7 @@
 extern struct kobj_type xfs_mp_ktype;	/* xfs_mount */
 extern struct kobj_type xfs_dbg_ktype;	/* debug */
 extern struct kobj_type xfs_log_ktype;	/* xlog */
+extern struct kobj_type xfs_stats_ktype;	/* stats */
 
 static inline struct xfs_kobj *
 to_kobj(struct kobject *kobject)
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 5ed36b1e04c1..c8d58426008e 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -689,6 +689,7 @@ DEFINE_INODE_EVENT(xfs_inode_free_eofblocks_invalid);
 DEFINE_INODE_EVENT(xfs_filemap_fault);
 DEFINE_INODE_EVENT(xfs_filemap_pmd_fault);
 DEFINE_INODE_EVENT(xfs_filemap_page_mkwrite);
+DEFINE_INODE_EVENT(xfs_filemap_pfn_mkwrite);
 
 DECLARE_EVENT_CLASS(xfs_iref_class,
 	TP_PROTO(struct xfs_inode *ip, unsigned long caller_ip),
@@ -1221,6 +1222,32 @@ DEFINE_PAGE_EVENT(xfs_writepage);
 DEFINE_PAGE_EVENT(xfs_releasepage);
 DEFINE_PAGE_EVENT(xfs_invalidatepage);
 
+DECLARE_EVENT_CLASS(xfs_readpage_class,
+	TP_PROTO(struct inode *inode, int nr_pages),
+	TP_ARGS(inode, nr_pages),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(int, nr_pages)
+	),
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->nr_pages = nr_pages;
+	),
+	TP_printk("dev %d:%d ino 0x%llx nr_pages %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->nr_pages)
+)
+
+#define DEFINE_READPAGE_EVENT(name)		\
+DEFINE_EVENT(xfs_readpage_class, name,	\
+	TP_PROTO(struct inode *inode, int nr_pages), \
+	TP_ARGS(inode, nr_pages))
+DEFINE_READPAGE_EVENT(xfs_vm_readpage);
+DEFINE_READPAGE_EVENT(xfs_vm_readpages);
+
 DECLARE_EVENT_CLASS(xfs_imap_class,
 	TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count,
 		 int type, struct xfs_bmbt_irec *irec),
@@ -1269,11 +1296,7 @@ DEFINE_IOMAP_EVENT(xfs_map_blocks_found);
 DEFINE_IOMAP_EVENT(xfs_map_blocks_alloc);
 DEFINE_IOMAP_EVENT(xfs_get_blocks_found);
 DEFINE_IOMAP_EVENT(xfs_get_blocks_alloc);
-DEFINE_IOMAP_EVENT(xfs_gbmap_direct);
-DEFINE_IOMAP_EVENT(xfs_gbmap_direct_new);
-DEFINE_IOMAP_EVENT(xfs_gbmap_direct_update);
-DEFINE_IOMAP_EVENT(xfs_gbmap_direct_none);
-DEFINE_IOMAP_EVENT(xfs_gbmap_direct_endio);
+DEFINE_IOMAP_EVENT(xfs_get_blocks_map_direct);
 
 DECLARE_EVENT_CLASS(xfs_simple_io_class,
 	TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count),
@@ -1312,6 +1335,10 @@ DEFINE_SIMPLE_IO_EVENT(xfs_delalloc_enospc);
 DEFINE_SIMPLE_IO_EVENT(xfs_unwritten_convert);
 DEFINE_SIMPLE_IO_EVENT(xfs_get_blocks_notfound);
 DEFINE_SIMPLE_IO_EVENT(xfs_setfilesize);
+DEFINE_SIMPLE_IO_EVENT(xfs_zero_eof);
+DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write);
+DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write_unwritten);
+DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write_append);
 
 DECLARE_EVENT_CLASS(xfs_itrunc_class,
 	TP_PROTO(struct xfs_inode *ip, xfs_fsize_t new_size),
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index a0ab1dae9c31..20c53666cb4b 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -930,9 +930,9 @@ __xfs_trans_commit(
 	 */
 	if (sync) {
 		error = _xfs_log_force_lsn(mp, commit_lsn, XFS_LOG_SYNC, NULL);
-		XFS_STATS_INC(xs_trans_sync);
+		XFS_STATS_INC(mp, xs_trans_sync);
 	} else {
-		XFS_STATS_INC(xs_trans_async);
+		XFS_STATS_INC(mp, xs_trans_async);
 	}
 
 	return error;
@@ -955,7 +955,7 @@ out_unreserve:
 	xfs_trans_free_items(tp, NULLCOMMITLSN, !!error);
 	xfs_trans_free(tp);
 
-	XFS_STATS_INC(xs_trans_empty);
+	XFS_STATS_INC(mp, xs_trans_empty);
 	return error;
 }
 
@@ -1028,6 +1028,8 @@ __xfs_trans_roll(
 	struct xfs_trans_res	tres;
 	int			error;
 
+	*committed = 0;
+
 	/*
 	 * Ensure that the inode is always logged.
 	 */
@@ -1082,6 +1084,6 @@ xfs_trans_roll(
 	struct xfs_trans	**tpp,
 	struct xfs_inode	*dp)
 {
-	int			committed = 0;
+	int			committed;
 	return __xfs_trans_roll(tpp, dp, &committed);
 }
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 4643070d7cae..e7c49cf43fbc 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -133,7 +133,6 @@ typedef struct xfs_trans {
  * XFS transaction mechanism exported interfaces that are
  * actually macros.
  */
-#define	xfs_trans_get_block_res(tp)	((tp)->t_blk_res)
 #define	xfs_trans_set_sync(tp)		((tp)->t_flags |= XFS_TRANS_SYNC)
 
 #if defined(DEBUG) || defined(XFS_WARN)
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 1098cf490189..d6c9c3e9e02b 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -349,7 +349,7 @@ xfsaild_push(
 	     xfs_ail_min_lsn(ailp))) {
 		ailp->xa_log_flush = 0;
 
-		XFS_STATS_INC(xs_push_ail_flush);
+		XFS_STATS_INC(mp, xs_push_ail_flush);
 		xfs_log_force(mp, XFS_LOG_SYNC);
 	}
 
@@ -371,7 +371,7 @@ xfsaild_push(
 		goto out_done;
 	}
 
-	XFS_STATS_INC(xs_push_ail);
+	XFS_STATS_INC(mp, xs_push_ail);
 
 	lsn = lip->li_lsn;
 	while ((XFS_LSN_CMP(lip->li_lsn, target) <= 0)) {
@@ -385,7 +385,7 @@ xfsaild_push(
 		lock_result = lip->li_ops->iop_push(lip, &ailp->xa_buf_list);
 		switch (lock_result) {
 		case XFS_ITEM_SUCCESS:
-			XFS_STATS_INC(xs_push_ail_success);
+			XFS_STATS_INC(mp, xs_push_ail_success);
 			trace_xfs_ail_push(lip);
 
 			ailp->xa_last_pushed_lsn = lsn;
@@ -403,7 +403,7 @@ xfsaild_push(
 			 * re-try the flushing relatively soon if most of the
 			 * AIL is beeing flushed.
 			 */
-			XFS_STATS_INC(xs_push_ail_flushing);
+			XFS_STATS_INC(mp, xs_push_ail_flushing);
 			trace_xfs_ail_flushing(lip);
 
 			flushing++;
@@ -411,14 +411,14 @@ xfsaild_push(
 			break;
 
 		case XFS_ITEM_PINNED:
-			XFS_STATS_INC(xs_push_ail_pinned);
+			XFS_STATS_INC(mp, xs_push_ail_pinned);
 			trace_xfs_ail_pinned(lip);
 
 			stuck++;
 			ailp->xa_log_flush++;
 			break;
 		case XFS_ITEM_LOCKED:
-			XFS_STATS_INC(xs_push_ail_locked);
+			XFS_STATS_INC(mp, xs_push_ail_locked);
 			trace_xfs_ail_locked(lip);
 
 			stuck++;
@@ -497,6 +497,7 @@ xfsaild(
 	long		tout = 0;	/* milliseconds */
 
 	current->flags |= PF_MEMALLOC;
+	set_freezable();
 
 	while (!kthread_should_stop()) {
 		if (tout && tout <= 20)
@@ -519,14 +520,14 @@ xfsaild(
 		if (!xfs_ail_min(ailp) &&
 		    ailp->xa_target == ailp->xa_target_prev) {
 			spin_unlock(&ailp->xa_lock);
-			schedule();
+			freezable_schedule();
 			tout = 0;
 			continue;
 		}
 		spin_unlock(&ailp->xa_lock);
 
 		if (tout)
-			schedule_timeout(msecs_to_jiffies(tout));
+			freezable_schedule_timeout(msecs_to_jiffies(tout));
 
 		__set_current_state(TASK_RUNNING);
 
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index 75798412859a..8ee29ca132dc 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -155,7 +155,7 @@ xfs_trans_get_buf_map(
 		ASSERT(xfs_buf_islocked(bp));
 		if (XFS_FORCED_SHUTDOWN(tp->t_mountp)) {
 			xfs_buf_stale(bp);
-			XFS_BUF_DONE(bp);
+			bp->b_flags |= XBF_DONE;
 		}
 
 		ASSERT(bp->b_transp == tp);
@@ -518,7 +518,7 @@ xfs_trans_log_buf(xfs_trans_t	*tp,
 	 * inside the b_bdstrat callback so that this won't get written to
 	 * disk.
 	 */
-	XFS_BUF_DONE(bp);
+	bp->b_flags |= XBF_DONE;
 
 	ASSERT(atomic_read(&bip->bli_refcount) > 0);
 	bp->b_iodone = xfs_buf_iodone_callbacks;
@@ -534,8 +534,8 @@ xfs_trans_log_buf(xfs_trans_t	*tp,
 	 */
 	if (bip->bli_flags & XFS_BLI_STALE) {
 		bip->bli_flags &= ~XFS_BLI_STALE;
-		ASSERT(XFS_BUF_ISSTALE(bp));
-		XFS_BUF_UNSTALE(bp);
+		ASSERT(bp->b_flags & XBF_STALE);
+		bp->b_flags &= ~XBF_STALE;
 		bip->__bli_format.blf_flags &= ~XFS_BLF_CANCEL;
 	}
 
@@ -600,7 +600,7 @@ xfs_trans_binval(
 		 * If the buffer is already invalidated, then
 		 * just return.
 		 */
-		ASSERT(XFS_BUF_ISSTALE(bp));
+		ASSERT(bp->b_flags & XBF_STALE);
 		ASSERT(!(bip->bli_flags & (XFS_BLI_LOGGED | XFS_BLI_DIRTY)));
 		ASSERT(!(bip->__bli_format.blf_flags & XFS_BLF_INODE_BUF));
 		ASSERT(!(bip->__bli_format.blf_flags & XFS_BLFT_MASK));
diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c
index ce78534a047e..c3d547211d16 100644
--- a/fs/xfs/xfs_trans_dquot.c
+++ b/fs/xfs/xfs_trans_dquot.c
@@ -572,12 +572,16 @@ xfs_quota_warn(
 	struct xfs_dquot	*dqp,
 	int			type)
 {
-	/* no warnings for project quotas - we just return ENOSPC later */
+	enum quota_type qtype;
+
 	if (dqp->dq_flags & XFS_DQ_PROJ)
-		return;
-	quota_send_warning(make_kqid(&init_user_ns,
-				     (dqp->dq_flags & XFS_DQ_USER) ?
-				     USRQUOTA : GRPQUOTA,
+		qtype = PRJQUOTA;
+	else if (dqp->dq_flags & XFS_DQ_USER)
+		qtype = USRQUOTA;
+	else
+		qtype = GRPQUOTA;
+
+	quota_send_warning(make_kqid(&init_user_ns, qtype,
 				     be32_to_cpu(dqp->q_core.d_id)),
 			   mp->m_super->s_dev, type);
 }
@@ -605,17 +609,20 @@ xfs_trans_dqresv(
 	xfs_qcnt_t	total_count;
 	xfs_qcnt_t	*resbcountp;
 	xfs_quotainfo_t	*q = mp->m_quotainfo;
+	struct xfs_def_quota	*defq;
 
 
 	xfs_dqlock(dqp);
 
+	defq = xfs_get_defquota(dqp, q);
+
 	if (flags & XFS_TRANS_DQ_RES_BLKS) {
 		hardlimit = be64_to_cpu(dqp->q_core.d_blk_hardlimit);
 		if (!hardlimit)
-			hardlimit = q->qi_bhardlimit;
+			hardlimit = defq->bhardlimit;
 		softlimit = be64_to_cpu(dqp->q_core.d_blk_softlimit);
 		if (!softlimit)
-			softlimit = q->qi_bsoftlimit;
+			softlimit = defq->bsoftlimit;
 		timer = be32_to_cpu(dqp->q_core.d_btimer);
 		warns = be16_to_cpu(dqp->q_core.d_bwarns);
 		warnlimit = dqp->q_mount->m_quotainfo->qi_bwarnlimit;
@@ -624,10 +631,10 @@ xfs_trans_dqresv(
 		ASSERT(flags & XFS_TRANS_DQ_RES_RTBLKS);
 		hardlimit = be64_to_cpu(dqp->q_core.d_rtb_hardlimit);
 		if (!hardlimit)
-			hardlimit = q->qi_rtbhardlimit;
+			hardlimit = defq->rtbhardlimit;
 		softlimit = be64_to_cpu(dqp->q_core.d_rtb_softlimit);
 		if (!softlimit)
-			softlimit = q->qi_rtbsoftlimit;
+			softlimit = defq->rtbsoftlimit;
 		timer = be32_to_cpu(dqp->q_core.d_rtbtimer);
 		warns = be16_to_cpu(dqp->q_core.d_rtbwarns);
 		warnlimit = dqp->q_mount->m_quotainfo->qi_rtbwarnlimit;
@@ -668,10 +675,10 @@ xfs_trans_dqresv(
 			warnlimit = dqp->q_mount->m_quotainfo->qi_iwarnlimit;
 			hardlimit = be64_to_cpu(dqp->q_core.d_ino_hardlimit);
 			if (!hardlimit)
-				hardlimit = q->qi_ihardlimit;
+				hardlimit = defq->ihardlimit;
 			softlimit = be64_to_cpu(dqp->q_core.d_ino_softlimit);
 			if (!softlimit)
-				softlimit = q->qi_isoftlimit;
+				softlimit = defq->isoftlimit;
 
 			if (hardlimit && total_count > hardlimit) {
 				xfs_quota_warn(mp, dqp, QUOTA_NL_IHARDWARN);
diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c
index 17280cd71934..11a3af08b5c7 100644
--- a/fs/xfs/xfs_trans_inode.c
+++ b/fs/xfs/xfs_trans_inode.c
@@ -75,18 +75,10 @@ xfs_trans_ichgtime(
 
 	tv = current_fs_time(inode->i_sb);
 
-	if ((flags & XFS_ICHGTIME_MOD) &&
-	    !timespec_equal(&inode->i_mtime, &tv)) {
+	if (flags & XFS_ICHGTIME_MOD)
 		inode->i_mtime = tv;
-		ip->i_d.di_mtime.t_sec = tv.tv_sec;
-		ip->i_d.di_mtime.t_nsec = tv.tv_nsec;
-	}
-	if ((flags & XFS_ICHGTIME_CHG) &&
-	    !timespec_equal(&inode->i_ctime, &tv)) {
+	if (flags & XFS_ICHGTIME_CHG)
 		inode->i_ctime = tv;
-		ip->i_d.di_ctime.t_sec = tv.tv_sec;
-		ip->i_d.di_ctime.t_nsec = tv.tv_nsec;
-	}
 }
 
 /*
@@ -108,6 +100,15 @@ xfs_trans_log_inode(
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 
 	/*
+	 * Record the specific change for fdatasync optimisation. This
+	 * allows fdatasync to skip log forces for inodes that are only
+	 * timestamp dirty. We do this before the change count so that
+	 * the core being logged in this case does not impact on fdatasync
+	 * behaviour.
+	 */
+	ip->i_itemp->ili_fsync_fields |= flags;
+
+	/*
 	 * First time we log the inode in a transaction, bump the inode change
 	 * counter if it is configured for this to occur. We don't use
 	 * inode_inc_version() because there is no need for extra locking around
@@ -116,7 +117,7 @@ xfs_trans_log_inode(
 	 */
 	if (!(ip->i_itemp->ili_item.li_desc->lid_flags & XFS_LID_DIRTY) &&
 	    IS_I_VERSION(VFS_I(ip))) {
-		ip->i_d.di_changecount = ++VFS_I(ip)->i_version;
+		VFS_I(ip)->i_version++;
 		flags |= XFS_ILOG_CORE;
 	}
 
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index c036815183cb..110f1d7d86b0 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -32,15 +32,13 @@
 
 
 static int
-xfs_xattr_get(struct dentry *dentry, const char *name,
-		void *value, size_t size, int xflags)
+xfs_xattr_get(const struct xattr_handler *handler, struct dentry *dentry,
+		const char *name, void *value, size_t size)
 {
+	int xflags = handler->flags;
 	struct xfs_inode *ip = XFS_I(d_inode(dentry));
 	int error, asize = size;
 
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
-
 	/* Convert Linux syscall to XFS internal ATTR flags */
 	if (!size) {
 		xflags |= ATTR_KERNOVAL;
@@ -53,14 +51,35 @@ xfs_xattr_get(struct dentry *dentry, const char *name,
 	return asize;
 }
 
-static int
-xfs_xattr_set(struct dentry *dentry, const char *name, const void *value,
-		size_t size, int flags, int xflags)
+void
+xfs_forget_acl(
+	struct inode		*inode,
+	const char		*name,
+	int			xflags)
 {
-	struct xfs_inode *ip = XFS_I(d_inode(dentry));
+	/*
+	 * Invalidate any cached ACLs if the user has bypassed the ACL
+	 * interface. We don't validate the content whatsoever so it is caller
+	 * responsibility to provide data in valid format and ensure i_mode is
+	 * consistent.
+	 */
+	if (xflags & ATTR_ROOT) {
+#ifdef CONFIG_XFS_POSIX_ACL
+		if (!strcmp(name, SGI_ACL_FILE))
+			forget_cached_acl(inode, ACL_TYPE_ACCESS);
+		else if (!strcmp(name, SGI_ACL_DEFAULT))
+			forget_cached_acl(inode, ACL_TYPE_DEFAULT);
+#endif
+	}
+}
 
-	if (strcmp(name, "") == 0)
-		return -EINVAL;
+static int
+xfs_xattr_set(const struct xattr_handler *handler, struct dentry *dentry,
+		const char *name, const void *value, size_t size, int flags)
+{
+	int			xflags = handler->flags;
+	struct xfs_inode	*ip = XFS_I(d_inode(dentry));
+	int			error;
 
 	/* Convert Linux syscall to XFS internal ATTR flags */
 	if (flags & XATTR_CREATE)
@@ -70,8 +89,12 @@ xfs_xattr_set(struct dentry *dentry, const char *name, const void *value,
 
 	if (!value)
 		return xfs_attr_remove(ip, (unsigned char *)name, xflags);
-	return xfs_attr_set(ip, (unsigned char *)name,
+	error = xfs_attr_set(ip, (unsigned char *)name,
 				(void *)value, size, xflags);
+	if (!error)
+		xfs_forget_acl(d_inode(dentry), name, xflags);
+
+	return error;
 }
 
 static const struct xattr_handler xfs_xattr_user_handler = {
@@ -106,47 +129,19 @@ const struct xattr_handler *xfs_xattr_handlers[] = {
 	NULL
 };
 
-static unsigned int xfs_xattr_prefix_len(int flags)
-{
-	if (flags & XFS_ATTR_SECURE)
-		return sizeof("security");
-	else if (flags & XFS_ATTR_ROOT)
-		return sizeof("trusted");
-	else
-		return sizeof("user");
-}
-
-static const char *xfs_xattr_prefix(int flags)
-{
-	if (flags & XFS_ATTR_SECURE)
-		return xfs_xattr_security_handler.prefix;
-	else if (flags & XFS_ATTR_ROOT)
-		return xfs_xattr_trusted_handler.prefix;
-	else
-		return xfs_xattr_user_handler.prefix;
-}
-
 static int
-xfs_xattr_put_listent(
+__xfs_xattr_put_listent(
 	struct xfs_attr_list_context *context,
-	int		flags,
-	unsigned char	*name,
-	int		namelen,
-	int		valuelen,
-	unsigned char	*value)
+	char *prefix,
+	int prefix_len,
+	unsigned char *name,
+	int namelen)
 {
-	unsigned int prefix_len = xfs_xattr_prefix_len(flags);
 	char *offset;
 	int arraytop;
 
-	ASSERT(context->count >= 0);
-
-	/*
-	 * Only show root namespace entries if we are actually allowed to
-	 * see them.
-	 */
-	if ((flags & XFS_ATTR_ROOT) && !capable(CAP_SYS_ADMIN))
-		return 0;
+	if (!context->alist)
+		goto compute_size;
 
 	arraytop = context->count + prefix_len + namelen + 1;
 	if (arraytop > context->firstu) {
@@ -154,17 +149,19 @@ xfs_xattr_put_listent(
 		return 1;
 	}
 	offset = (char *)context->alist + context->count;
-	strncpy(offset, xfs_xattr_prefix(flags), prefix_len);
+	strncpy(offset, prefix, prefix_len);
 	offset += prefix_len;
 	strncpy(offset, (char *)name, namelen);			/* real name */
 	offset += namelen;
 	*offset = '\0';
+
+compute_size:
 	context->count += prefix_len + namelen + 1;
 	return 0;
 }
 
 static int
-xfs_xattr_put_listent_sizes(
+xfs_xattr_put_listent(
 	struct xfs_attr_list_context *context,
 	int		flags,
 	unsigned char	*name,
@@ -172,24 +169,55 @@ xfs_xattr_put_listent_sizes(
 	int		valuelen,
 	unsigned char	*value)
 {
-	context->count += xfs_xattr_prefix_len(flags) + namelen + 1;
-	return 0;
-}
+	char *prefix;
+	int prefix_len;
 
-static int
-list_one_attr(const char *name, const size_t len, void *data,
-		size_t size, ssize_t *result)
-{
-	char *p = data + *result;
+	ASSERT(context->count >= 0);
 
-	*result += len;
-	if (!size)
-		return 0;
-	if (*result > size)
-		return -ERANGE;
+	if (flags & XFS_ATTR_ROOT) {
+#ifdef CONFIG_XFS_POSIX_ACL
+		if (namelen == SGI_ACL_FILE_SIZE &&
+		    strncmp(name, SGI_ACL_FILE,
+			    SGI_ACL_FILE_SIZE) == 0) {
+			int ret = __xfs_xattr_put_listent(
+					context, XATTR_SYSTEM_PREFIX,
+					XATTR_SYSTEM_PREFIX_LEN,
+					XATTR_POSIX_ACL_ACCESS,
+					strlen(XATTR_POSIX_ACL_ACCESS));
+			if (ret)
+				return ret;
+		} else if (namelen == SGI_ACL_DEFAULT_SIZE &&
+			 strncmp(name, SGI_ACL_DEFAULT,
+				 SGI_ACL_DEFAULT_SIZE) == 0) {
+			int ret = __xfs_xattr_put_listent(
+					context, XATTR_SYSTEM_PREFIX,
+					XATTR_SYSTEM_PREFIX_LEN,
+					XATTR_POSIX_ACL_DEFAULT,
+					strlen(XATTR_POSIX_ACL_DEFAULT));
+			if (ret)
+				return ret;
+		}
+#endif
 
-	strcpy(p, name);
-	return 0;
+		/*
+		 * Only show root namespace entries if we are actually allowed to
+		 * see them.
+		 */
+		if (!capable(CAP_SYS_ADMIN))
+			return 0;
+
+		prefix = XATTR_TRUSTED_PREFIX;
+		prefix_len = XATTR_TRUSTED_PREFIX_LEN;
+	} else if (flags & XFS_ATTR_SECURE) {
+		prefix = XATTR_SECURITY_PREFIX;
+		prefix_len = XATTR_SECURITY_PREFIX_LEN;
+	} else {
+		prefix = XATTR_USER_PREFIX;
+		prefix_len = XATTR_USER_PREFIX_LEN;
+	}
+
+	return __xfs_xattr_put_listent(context, prefix, prefix_len, name,
+				       namelen);
 }
 
 ssize_t
@@ -198,7 +226,6 @@ xfs_vn_listxattr(struct dentry *dentry, char *data, size_t size)
 	struct xfs_attr_list_context context;
 	struct attrlist_cursor_kern cursor = { 0 };
 	struct inode		*inode = d_inode(dentry);
-	int			error;
 
 	/*
 	 * First read the regular on-disk attributes.
@@ -207,37 +234,14 @@ xfs_vn_listxattr(struct dentry *dentry, char *data, size_t size)
 	context.dp = XFS_I(inode);
 	context.cursor = &cursor;
 	context.resynch = 1;
-	context.alist = data;
+	context.alist = size ? data : NULL;
 	context.bufsize = size;
 	context.firstu = context.bufsize;
-
-	if (size)
-		context.put_listent = xfs_xattr_put_listent;
-	else
-		context.put_listent = xfs_xattr_put_listent_sizes;
+	context.put_listent = xfs_xattr_put_listent;
 
 	xfs_attr_list_int(&context);
 	if (context.count < 0)
 		return -ERANGE;
 
-	/*
-	 * Then add the two synthetic ACL attributes.
-	 */
-	if (posix_acl_access_exists(inode)) {
-		error = list_one_attr(POSIX_ACL_XATTR_ACCESS,
-				strlen(POSIX_ACL_XATTR_ACCESS) + 1,
-				data, size, &context.count);
-		if (error)
-			return error;
-	}
-
-	if (posix_acl_default_exists(inode)) {
-		error = list_one_attr(POSIX_ACL_XATTR_DEFAULT,
-				strlen(POSIX_ACL_XATTR_DEFAULT) + 1,
-				data, size, &context.count);
-		if (error)
-			return error;
-	}
-
 	return context.count;
 }