Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless

204 files changed, 6929 insertions, 5478 deletions

diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index fc06fd27065e..dd6f7ee1e312 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -610,6 +610,9 @@ v9fs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	p9_debug(P9_DEBUG_VFS, "page %p fid %lx\n",
 		 page, (unsigned long)filp->private_data);
 
+	/* Update file times before taking page lock */
+	file_update_time(filp);
+
 	v9inode = V9FS_I(inode);
 	/* make sure the cache has finished storing the page */
 	v9fs_fscache_wait_on_page_write(inode, page);
diff --git a/fs/affs/bitmap.c b/fs/affs/bitmap.c
index 6e0be43ef6ef..a32246b8359e 100644
--- a/fs/affs/bitmap.c
+++ b/fs/affs/bitmap.c
@@ -10,30 +10,6 @@
 #include <linux/slab.h>
 #include "affs.h"
 
-/* This is, of course, shamelessly stolen from fs/minix */
-
-static const int nibblemap[] = { 0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4 };
-
-static u32
-affs_count_free_bits(u32 blocksize, const void *data)
-{
-	const u32 *map;
-	u32 free;
-	u32 tmp;
-
-	map = data;
-	free = 0;
-	for (blocksize /= 4; blocksize > 0; blocksize--) {
-		tmp = *map++;
-		while (tmp) {
-			free += nibblemap[tmp & 0xf];
-			tmp >>= 4;
-		}
-	}
-
-	return free;
-}
-
 u32
 affs_count_free_blocks(struct super_block *sb)
 {
@@ -317,7 +293,7 @@ int affs_init_bitmap(struct super_block *sb, int *flags)
 			goto out;
 		}
 		pr_debug("AFFS: read bitmap block %d: %d\n", blk, bm->bm_key);
-		bm->bm_free = affs_count_free_bits(sb->s_blocksize - 4, bh->b_data + 4);
+		bm->bm_free = memweight(bh->b_data + 4, sb->s_blocksize - 4);
 
 		/* Don't try read the extension if this is the last block,
 		 * but we also need the right bm pointer below
@@ -367,7 +343,7 @@ int affs_init_bitmap(struct super_block *sb, int *flags)
 
 	/* recalculate bitmap count for last block */
 	bm--;
-	bm->bm_free = affs_count_free_bits(sb->s_blocksize - 4, bh->b_data + 4);
+	bm->bm_free = memweight(bh->b_data + 4, sb->s_blocksize - 4);
 
 out:
 	affs_brelse(bh);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index adb1cd7ceb9b..4bab807227ad 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3342,10 +3342,22 @@ 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_sync_fs(struct super_block *sb, int wait);
+
+#ifdef CONFIG_PRINTK
+__printf(2, 3)
 void btrfs_printk(struct btrfs_fs_info *fs_info, const char *fmt, ...);
+#else
+static inline __printf(2, 3)
+void btrfs_printk(struct btrfs_fs_info *fs_info, const char *fmt, ...)
+{
+}
+#endif
+
+__printf(5, 6)
 void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
 		     unsigned int line, int errno, const char *fmt, ...);
 
+
 void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *root, const char *function,
 			       unsigned int line, int errno);
@@ -3386,6 +3398,7 @@ do {								\
 			  (errno), fmt, ##args);		\
 } while (0)
 
+__printf(5, 6)
 void __btrfs_panic(struct btrfs_fs_info *fs_info, const char *function,
 		   unsigned int line, int errno, const char *fmt, ...);
 
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 502b20c56e84..62e0cafd6e25 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1114,7 +1114,7 @@ void clean_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 				spin_unlock(&root->fs_info->delalloc_lock);
 				btrfs_panic(root->fs_info, -EOVERFLOW,
 					  "Can't clear %lu bytes from "
-					  " dirty_mdatadata_bytes (%lu)",
+					  " dirty_mdatadata_bytes (%llu)",
 					  buf->len,
 					  root->fs_info->dirty_metadata_bytes);
 			}
@@ -1614,8 +1614,6 @@ static int cleaner_kthread(void *arg)
 	struct btrfs_root *root = arg;
 
 	do {
-		vfs_check_frozen(root->fs_info->sb, SB_FREEZE_WRITE);
-
 		if (!(root->fs_info->sb->s_flags & MS_RDONLY) &&
 		    mutex_trylock(&root->fs_info->cleaner_mutex)) {
 			btrfs_run_delayed_iputs(root);
@@ -1647,7 +1645,6 @@ static int transaction_kthread(void *arg)
 	do {
 		cannot_commit = false;
 		delay = HZ * 30;
-		vfs_check_frozen(root->fs_info->sb, SB_FREEZE_WRITE);
 		mutex_lock(&root->fs_info->transaction_kthread_mutex);
 
 		spin_lock(&root->fs_info->trans_lock);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 9aa01ec2138d..5caf285c6e4d 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1379,7 +1379,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 	ssize_t err = 0;
 	size_t count, ocount;
 
-	vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
+	sb_start_write(inode->i_sb);
 
 	mutex_lock(&inode->i_mutex);
 
@@ -1469,6 +1469,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 			num_written = err;
 	}
 out:
+	sb_end_write(inode->i_sb);
 	current->backing_dev_info = NULL;
 	return num_written ? num_written : err;
 }
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 48bdfd2591c2..83baec24946d 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6629,6 +6629,7 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	u64 page_start;
 	u64 page_end;
 
+	sb_start_pagefault(inode->i_sb);
 	ret  = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE);
 	if (!ret) {
 		ret = file_update_time(vma->vm_file);
@@ -6718,12 +6719,15 @@ again:
 	unlock_extent_cached(io_tree, page_start, page_end, &cached_state, GFP_NOFS);
 
 out_unlock:
-	if (!ret)
+	if (!ret) {
+		sb_end_pagefault(inode->i_sb);
 		return VM_FAULT_LOCKED;
+	}
 	unlock_page(page);
 out:
 	btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE);
 out_noreserve:
+	sb_end_pagefault(inode->i_sb);
 	return ret;
 }
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 43f0012016e3..bc2f6ffff3cf 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -195,6 +195,10 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 	if (!inode_owner_or_capable(inode))
 		return -EACCES;
 
+	ret = mnt_want_write_file(file);
+	if (ret)
+		return ret;
+
 	mutex_lock(&inode->i_mutex);
 
 	ip_oldflags = ip->flags;
@@ -209,10 +213,6 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 		}
 	}
 
-	ret = mnt_want_write_file(file);
-	if (ret)
-		goto out_unlock;
-
 	if (flags & FS_SYNC_FL)
 		ip->flags |= BTRFS_INODE_SYNC;
 	else
@@ -275,9 +275,9 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 		inode->i_flags = i_oldflags;
 	}
 
-	mnt_drop_write_file(file);
  out_unlock:
 	mutex_unlock(&inode->i_mutex);
+	mnt_drop_write_file(file);
 	return ret;
 }
 
@@ -664,6 +664,10 @@ static noinline int btrfs_mksubvol(struct path *parent,
 	struct dentry *dentry;
 	int error;
 
+	error = mnt_want_write(parent->mnt);
+	if (error)
+		return error;
+
 	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
 
 	dentry = lookup_one_len(name, parent->dentry, namelen);
@@ -699,6 +703,7 @@ out_dput:
 	dput(dentry);
 out_unlock:
 	mutex_unlock(&dir->i_mutex);
+	mnt_drop_write(parent->mnt);
 	return error;
 }
 
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index c5dbd9149679..4da08652004d 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1241,7 +1241,7 @@ static int __must_check __add_reloc_root(struct btrfs_root *root)
 	if (rb_node) {
 		btrfs_panic(root->fs_info, -EEXIST, "Duplicate root found "
 			    "for start=%llu while inserting into relocation "
-			    "tree\n");
+			    "tree\n", node->bytenr);
 		kfree(node);
 		return -EEXIST;
 	}
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index fa61ef59cd61..8c6e61d6eed5 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -125,6 +125,7 @@ static void btrfs_handle_error(struct btrfs_fs_info *fs_info)
 	}
 }
 
+#ifdef CONFIG_PRINTK
 /*
  * __btrfs_std_error decodes expected errors from the caller and
  * invokes the approciate error response.
@@ -167,7 +168,7 @@ void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
 	va_end(args);
 }
 
-const char *logtypes[] = {
+static const char * const logtypes[] = {
 	"emergency",
 	"alert",
 	"critical",
@@ -185,22 +186,50 @@ void btrfs_printk(struct btrfs_fs_info *fs_info, const char *fmt, ...)
 	struct va_format vaf;
 	va_list args;
 	const char *type = logtypes[4];
+	int kern_level;
 
 	va_start(args, fmt);
 
-	if (fmt[0] == '<' && isdigit(fmt[1]) && fmt[2] == '>') {
-		memcpy(lvl, fmt, 3);
-		lvl[3] = '\0';
-		fmt += 3;
-		type = logtypes[fmt[1] - '0'];
+	kern_level = printk_get_level(fmt);
+	if (kern_level) {
+		size_t size = printk_skip_level(fmt) - fmt;
+		memcpy(lvl, fmt,  size);
+		lvl[size] = '\0';
+		fmt += size;
+		type = logtypes[kern_level - '0'];
 	} else
 		*lvl = '\0';
 
 	vaf.fmt = fmt;
 	vaf.va = &args;
+
 	printk("%sBTRFS %s (device %s): %pV", lvl, type, sb->s_id, &vaf);
+
+	va_end(args);
 }
 
+#else
+
+void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
+		       unsigned int line, int errno, const char *fmt, ...)
+{
+	struct super_block *sb = fs_info->sb;
+
+	/*
+	 * Special case: if the error is EROFS, and we're already
+	 * under MS_RDONLY, then it is safe here.
+	 */
+	if (errno == -EROFS && (sb->s_flags & MS_RDONLY))
+		return;
+
+	/* Don't go through full error handling during mount */
+	if (sb->s_flags & MS_BORN) {
+		save_error_info(fs_info);
+		btrfs_handle_error(fs_info);
+	}
+}
+#endif
+
 /*
  * We only mark the transaction aborted and then set the file system read-only.
  * This will prevent new transactions from starting or trying to join this
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 7ac7cdcc294e..17be3dedacba 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -335,6 +335,8 @@ again:
 	if (!h)
 		return ERR_PTR(-ENOMEM);
 
+	sb_start_intwrite(root->fs_info->sb);
+
 	if (may_wait_transaction(root, type))
 		wait_current_trans(root);
 
@@ -345,6 +347,7 @@ again:
 	} while (ret == -EBUSY);
 
 	if (ret < 0) {
+		sb_end_intwrite(root->fs_info->sb);
 		kmem_cache_free(btrfs_trans_handle_cachep, h);
 		return ERR_PTR(ret);
 	}
@@ -548,6 +551,8 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 	btrfs_trans_release_metadata(trans, root);
 	trans->block_rsv = NULL;
 
+	sb_end_intwrite(root->fs_info->sb);
+
 	if (lock && !atomic_read(&root->fs_info->open_ioctl_trans) &&
 	    should_end_transaction(trans, root)) {
 		trans->transaction->blocked = 1;
@@ -1578,6 +1583,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	put_transaction(cur_trans);
 	put_transaction(cur_trans);
 
+	sb_end_intwrite(root->fs_info->sb);
+
 	trace_btrfs_transaction_commit(root);
 
 	btrfs_scrub_continue(root);
diff --git a/fs/buffer.c b/fs/buffer.c
index c7062c896d7c..9f6d2e41281d 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2306,8 +2306,8 @@ EXPORT_SYMBOL(block_commit_write);
  * beyond EOF, then the page is guaranteed safe against truncation until we
  * unlock the page.
  *
- * Direct callers of this function should call vfs_check_frozen() so that page
- * fault does not busyloop until the fs is thawed.
+ * Direct callers of this function should protect against filesystem freezing
+ * using sb_start_write() - sb_end_write() functions.
  */
 int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 			 get_block_t get_block)
@@ -2318,6 +2318,12 @@ int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 	loff_t size;
 	int ret;
 
+	/*
+	 * 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);
+
 	lock_page(page);
 	size = i_size_read(inode);
 	if ((page->mapping != inode->i_mapping) ||
@@ -2339,18 +2345,7 @@ int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 
 	if (unlikely(ret < 0))
 		goto out_unlock;
-	/*
-	 * Freezing in progress? We check after the page is marked dirty and
-	 * with page lock held so if the test here fails, we are sure freezing
-	 * code will wait during syncing until the page fault is done - at that
-	 * point page will be dirty and unlocked so freezing code will write it
-	 * and writeprotect it again.
-	 */
 	set_page_dirty(page);
-	if (inode->i_sb->s_frozen != SB_UNFROZEN) {
-		ret = -EAGAIN;
-		goto out_unlock;
-	}
 	wait_on_page_writeback(page);
 	return 0;
 out_unlock:
@@ -2365,12 +2360,9 @@ int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 	int ret;
 	struct super_block *sb = vma->vm_file->f_path.dentry->d_inode->i_sb;
 
-	/*
-	 * This check is racy but catches the common case. The check in
-	 * __block_page_mkwrite() is reliable.
-	 */
-	vfs_check_frozen(sb, SB_FREEZE_WRITE);
+	sb_start_pagefault(sb);
 	ret = __block_page_mkwrite(vma, vmf, get_block);
+	sb_end_pagefault(sb);
 	return block_page_mkwrite_return(ret);
 }
 EXPORT_SYMBOL(block_page_mkwrite);
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index c0353dfac51f..c994691d9445 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -919,7 +919,7 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page)
 	 * own time */
 	path.mnt = cache->mnt;
 	path.dentry = object->backer;
-	file = dentry_open(&path, O_RDWR, cache->cache_cred);
+	file = dentry_open(&path, O_RDWR | O_LARGEFILE, cache->cache_cred);
 	if (IS_ERR(file)) {
 		ret = PTR_ERR(file);
 	} else {
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 8b67304e4b80..452e71a1b753 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1184,6 +1184,9 @@ static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	loff_t size, len;
 	int ret;
 
+	/* Update time before taking page lock */
+	file_update_time(vma->vm_file);
+
 	size = i_size_read(inode);
 	if (off + PAGE_CACHE_SIZE <= size)
 		len = PAGE_CACHE_SIZE;
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 00894ff9246c..f391f1e75414 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -51,8 +51,7 @@ int ceph_init_dentry(struct dentry *dentry)
 		goto out_unlock;
 	}
 
-	if (dentry->d_parent == NULL ||   /* nfs fh_to_dentry */
-	    ceph_snap(dentry->d_parent->d_inode) == CEPH_NOSNAP)
+	if (ceph_snap(dentry->d_parent->d_inode) == CEPH_NOSNAP)
 		d_set_d_op(dentry, &ceph_dentry_ops);
 	else if (ceph_snap(dentry->d_parent->d_inode) == CEPH_SNAPDIR)
 		d_set_d_op(dentry, &ceph_snapdir_dentry_ops);
@@ -79,7 +78,7 @@ struct inode *ceph_get_dentry_parent_inode(struct dentry *dentry)
 		return NULL;
 
 	spin_lock(&dentry->d_lock);
-	if (dentry->d_parent) {
+	if (!IS_ROOT(dentry)) {
 		inode = dentry->d_parent->d_inode;
 		ihold(inode);
 	}
@@ -1154,7 +1153,7 @@ static void ceph_d_prune(struct dentry *dentry)
 	dout("ceph_d_prune %p\n", dentry);
 
 	/* do we have a valid parent? */
-	if (!dentry->d_parent || IS_ROOT(dentry))
+	if (IS_ROOT(dentry))
 		return;
 
 	/* if we are not hashed, we don't affect D_COMPLETE */
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 200bc87eceb1..a5a735422aa7 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -10,6 +10,7 @@
 #include "super.h"
 #include "mds_client.h"
 
+#include <linux/ceph/ceph_features.h>
 #include <linux/ceph/messenger.h>
 #include <linux/ceph/decode.h>
 #include <linux/ceph/pagelist.h>
@@ -394,11 +395,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 	s->s_seq = 0;
 	mutex_init(&s->s_mutex);
 
-	ceph_con_init(mdsc->fsc->client->msgr, &s->s_con);
-	s->s_con.private = s;
-	s->s_con.ops = &mds_con_ops;
-	s->s_con.peer_name.type = CEPH_ENTITY_TYPE_MDS;
-	s->s_con.peer_name.num = cpu_to_le64(mds);
+	ceph_con_init(&s->s_con, s, &mds_con_ops, &mdsc->fsc->client->msgr);
 
 	spin_lock_init(&s->s_gen_ttl_lock);
 	s->s_cap_gen = 0;
@@ -440,7 +437,8 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 	mdsc->sessions[mds] = s;
 	atomic_inc(&s->s_ref);  /* one ref to sessions[], one to caller */
 
-	ceph_con_open(&s->s_con, ceph_mdsmap_get_addr(mdsc->mdsmap, mds));
+	ceph_con_open(&s->s_con, CEPH_ENTITY_TYPE_MDS, mds,
+		      ceph_mdsmap_get_addr(mdsc->mdsmap, mds));
 
 	return s;
 
@@ -1472,11 +1470,6 @@ retry:
 		else
 			len += 1 + temp->d_name.len;
 		temp = temp->d_parent;
-		if (temp == NULL) {
-			rcu_read_unlock();
-			pr_err("build_path corrupt dentry %p\n", dentry);
-			return ERR_PTR(-EINVAL);
-		}
 	}
 	rcu_read_unlock();
 	if (len)
@@ -1513,12 +1506,6 @@ retry:
 		if (pos)
 			path[--pos] = '/';
 		temp = temp->d_parent;
-		if (temp == NULL) {
-			rcu_read_unlock();
-			pr_err("build_path corrupt dentry\n");
-			kfree(path);
-			return ERR_PTR(-EINVAL);
-		}
 	}
 	rcu_read_unlock();
 	if (pos != 0 || read_seqretry(&rename_lock, seq)) {
@@ -2531,7 +2518,9 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
 	session->s_state = CEPH_MDS_SESSION_RECONNECTING;
 	session->s_seq = 0;
 
+	ceph_con_close(&session->s_con);
 	ceph_con_open(&session->s_con,
+		      CEPH_ENTITY_TYPE_MDS, mds,
 		      ceph_mdsmap_get_addr(mdsc->mdsmap, mds));
 
 	/* replay unsafe requests */
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index e5206fc76562..cbb2f54a3019 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -296,8 +296,7 @@ static int build_snap_context(struct ceph_snap_realm *realm)
 	struct ceph_snap_realm *parent = realm->parent;
 	struct ceph_snap_context *snapc;
 	int err = 0;
-	int i;
-	int num = realm->num_prior_parent_snaps + realm->num_snaps;
+	u32 num = realm->num_prior_parent_snaps + realm->num_snaps;
 
 	/*
 	 * build parent context, if it hasn't been built.
@@ -321,11 +320,11 @@ static int build_snap_context(struct ceph_snap_realm *realm)
 	    realm->cached_context->seq == realm->seq &&
 	    (!parent ||
 	     realm->cached_context->seq >= parent->cached_context->seq)) {
-		dout("build_snap_context %llx %p: %p seq %lld (%d snaps)"
+		dout("build_snap_context %llx %p: %p seq %lld (%u snaps)"
 		     " (unchanged)\n",
 		     realm->ino, realm, realm->cached_context,
 		     realm->cached_context->seq,
-		     realm->cached_context->num_snaps);
+		     (unsigned int) realm->cached_context->num_snaps);
 		return 0;
 	}
 
@@ -342,6 +341,8 @@ static int build_snap_context(struct ceph_snap_realm *realm)
 	num = 0;
 	snapc->seq = realm->seq;
 	if (parent) {
+		u32 i;
+
 		/* include any of parent's snaps occurring _after_ my
 		   parent became my parent */
 		for (i = 0; i < parent->cached_context->num_snaps; i++)
@@ -361,8 +362,9 @@ static int build_snap_context(struct ceph_snap_realm *realm)
 
 	sort(snapc->snaps, num, sizeof(u64), cmpu64_rev, NULL);
 	snapc->num_snaps = num;
-	dout("build_snap_context %llx %p: %p seq %lld (%d snaps)\n",
-	     realm->ino, realm, snapc, snapc->seq, snapc->num_snaps);
+	dout("build_snap_context %llx %p: %p seq %lld (%u snaps)\n",
+	     realm->ino, realm, snapc, snapc->seq,
+	     (unsigned int) snapc->num_snaps);
 
 	if (realm->cached_context)
 		ceph_put_snap_context(realm->cached_context);
@@ -402,9 +404,9 @@ static void rebuild_snap_realms(struct ceph_snap_realm *realm)
  * helper to allocate and decode an array of snapids.  free prior
  * instance, if any.
  */
-static int dup_array(u64 **dst, __le64 *src, int num)
+static int dup_array(u64 **dst, __le64 *src, u32 num)
 {
-	int i;
+	u32 i;
 
 	kfree(*dst);
 	if (num) {
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 7076109f014d..b982239f38f9 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -18,6 +18,7 @@
 #include "super.h"
 #include "mds_client.h"
 
+#include <linux/ceph/ceph_features.h>
 #include <linux/ceph/decode.h>
 #include <linux/ceph/mon_client.h>
 #include <linux/ceph/auth.h>
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index f4d5522cb619..ebc95cc652be 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -612,9 +612,9 @@ struct ceph_snap_realm {
 	u64 parent_since;   /* snapid when our current parent became so */
 
 	u64 *prior_parent_snaps;      /* snaps inherited from any parents we */
-	int num_prior_parent_snaps;   /*  had prior to parent_since */
+	u32 num_prior_parent_snaps;   /*  had prior to parent_since */
 	u64 *snaps;                   /* snaps specific to this realm */
-	int num_snaps;
+	u32 num_snaps;
 
 	struct ceph_snap_realm *parent;
 	struct list_head children;       /* list of child realms */
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 785cb3057c95..2c2ae5be9902 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -457,6 +457,7 @@ start:
 			for (i = 0; i < numattr; i++)
 				kfree(xattrs[i]);
 			kfree(xattrs);
+			xattrs = NULL;
 			goto start;
 		}
 		err = -EIO;
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index ffa2be57804d..c3ca12c33ca2 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -318,21 +318,20 @@ static int ecryptfs_lookup_interpose(struct dentry *dentry,
 	struct vfsmount *lower_mnt;
 	int rc = 0;
 
-	lower_mnt = mntget(ecryptfs_dentry_to_lower_mnt(dentry->d_parent));
-	fsstack_copy_attr_atime(dir_inode, lower_dentry->d_parent->d_inode);
-	BUG_ON(!lower_dentry->d_count);
-
 	dentry_info = kmem_cache_alloc(ecryptfs_dentry_info_cache, GFP_KERNEL);
-	ecryptfs_set_dentry_private(dentry, dentry_info);
 	if (!dentry_info) {
 		printk(KERN_ERR "%s: Out of memory whilst attempting "
 		       "to allocate ecryptfs_dentry_info struct\n",
 			__func__);
 		dput(lower_dentry);
-		mntput(lower_mnt);
-		d_drop(dentry);
 		return -ENOMEM;
 	}
+
+	lower_mnt = mntget(ecryptfs_dentry_to_lower_mnt(dentry->d_parent));
+	fsstack_copy_attr_atime(dir_inode, lower_dentry->d_parent->d_inode);
+	BUG_ON(!lower_dentry->d_count);
+
+	ecryptfs_set_dentry_private(dentry, dentry_info);
 	ecryptfs_set_dentry_lower(dentry, lower_dentry);
 	ecryptfs_set_dentry_lower_mnt(dentry, lower_mnt);
 
@@ -381,12 +380,6 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
 	struct dentry *lower_dir_dentry, *lower_dentry;
 	int rc = 0;
 
-	if ((ecryptfs_dentry->d_name.len == 1
-	     && !strcmp(ecryptfs_dentry->d_name.name, "."))
-	    || (ecryptfs_dentry->d_name.len == 2
-		&& !strcmp(ecryptfs_dentry->d_name.name, ".."))) {
-		goto out_d_drop;
-	}
 	lower_dir_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry->d_parent);
 	mutex_lock(&lower_dir_dentry->d_inode->i_mutex);
 	lower_dentry = lookup_one_len(ecryptfs_dentry->d_name.name,
@@ -397,8 +390,8 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
 		rc = PTR_ERR(lower_dentry);
 		ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned "
 				"[%d] on lower_dentry = [%s]\n", __func__, rc,
-				encrypted_and_encoded_name);
-		goto out_d_drop;
+				ecryptfs_dentry->d_name.name);
+		goto out;
 	}
 	if (lower_dentry->d_inode)
 		goto interpose;
@@ -415,7 +408,7 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
 	if (rc) {
 		printk(KERN_ERR "%s: Error attempting to encrypt and encode "
 		       "filename; rc = [%d]\n", __func__, rc);
-		goto out_d_drop;
+		goto out;
 	}
 	mutex_lock(&lower_dir_dentry->d_inode->i_mutex);
 	lower_dentry = lookup_one_len(encrypted_and_encoded_name,
@@ -427,14 +420,11 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
 		ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned "
 				"[%d] on lower_dentry = [%s]\n", __func__, rc,
 				encrypted_and_encoded_name);
-		goto out_d_drop;
+		goto out;
 	}
 interpose:
 	rc = ecryptfs_lookup_interpose(ecryptfs_dentry, lower_dentry,
 				       ecryptfs_dir_inode);
-	goto out;
-out_d_drop:
-	d_drop(ecryptfs_dentry);
 out:
 	kfree(encrypted_and_encoded_name);
 	return ERR_PTR(rc);
diff --git a/fs/exec.c b/fs/exec.c
index e95aeeddd25c..574cf4de4ec3 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -2002,17 +2002,17 @@ static void coredump_finish(struct mm_struct *mm)
 void set_dumpable(struct mm_struct *mm, int value)
 {
 	switch (value) {
-	case 0:
+	case SUID_DUMPABLE_DISABLED:
 		clear_bit(MMF_DUMPABLE, &mm->flags);
 		smp_wmb();
 		clear_bit(MMF_DUMP_SECURELY, &mm->flags);
 		break;
-	case 1:
+	case SUID_DUMPABLE_ENABLED:
 		set_bit(MMF_DUMPABLE, &mm->flags);
 		smp_wmb();
 		clear_bit(MMF_DUMP_SECURELY, &mm->flags);
 		break;
-	case 2:
+	case SUID_DUMPABLE_SAFE:
 		set_bit(MMF_DUMP_SECURELY, &mm->flags);
 		smp_wmb();
 		set_bit(MMF_DUMPABLE, &mm->flags);
@@ -2025,7 +2025,7 @@ static int __get_dumpable(unsigned long mm_flags)
 	int ret;
 
 	ret = mm_flags & MMF_DUMPABLE_MASK;
-	return (ret >= 2) ? 2 : ret;
+	return (ret > SUID_DUMPABLE_ENABLED) ? SUID_DUMPABLE_SAFE : ret;
 }
 
 int get_dumpable(struct mm_struct *mm)
@@ -2069,25 +2069,18 @@ static void wait_for_dump_helpers(struct file *file)
  */
 static int umh_pipe_setup(struct subprocess_info *info, struct cred *new)
 {
-	struct file *rp, *wp;
+	struct file *files[2];
 	struct fdtable *fdt;
 	struct coredump_params *cp = (struct coredump_params *)info->data;
 	struct files_struct *cf = current->files;
+	int err = create_pipe_files(files, 0);
+	if (err)
+		return err;
 
-	wp = create_write_pipe(0);
-	if (IS_ERR(wp))
-		return PTR_ERR(wp);
-
-	rp = create_read_pipe(wp, 0);
-	if (IS_ERR(rp)) {
-		free_write_pipe(wp);
-		return PTR_ERR(rp);
-	}
-
-	cp->file = wp;
+	cp->file = files[1];
 
 	sys_close(0);
-	fd_install(0, rp);
+	fd_install(0, files[0]);
 	spin_lock(&cf->file_lock);
 	fdt = files_fdtable(cf);
 	__set_open_fd(0, fdt);
@@ -2111,6 +2104,7 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs)
 	int retval = 0;
 	int flag = 0;
 	int ispipe;
+	bool need_nonrelative = false;
 	static atomic_t core_dump_count = ATOMIC_INIT(0);
 	struct coredump_params cprm = {
 		.signr = signr,
@@ -2136,14 +2130,16 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs)
 	if (!cred)
 		goto fail;
 	/*
-	 *	We cannot trust fsuid as being the "true" uid of the
-	 *	process nor do we know its entire history. We only know it
-	 *	was tainted so we dump it as root in mode 2.
+	 * We cannot trust fsuid as being the "true" uid of the process
+	 * nor do we know its entire history. We only know it was tainted
+	 * so we dump it as root in mode 2, and only into a controlled
+	 * environment (pipe handler or fully qualified path).
 	 */
-	if (__get_dumpable(cprm.mm_flags) == 2) {
+	if (__get_dumpable(cprm.mm_flags) == SUID_DUMPABLE_SAFE) {
 		/* Setuid core dump mode */
 		flag = O_EXCL;		/* Stop rewrite attacks */
 		cred->fsuid = GLOBAL_ROOT_UID;	/* Dump root private */
+		need_nonrelative = true;
 	}
 
 	retval = coredump_wait(exit_code, &core_state);
@@ -2171,15 +2167,16 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs)
 		}
 
 		if (cprm.limit == 1) {
-			/*
+			/* See umh_pipe_setup() which sets RLIMIT_CORE = 1.
+			 *
 			 * Normally core limits are irrelevant to pipes, since
 			 * we're not writing to the file system, but we use
-			 * cprm.limit of 1 here as a speacial value. Any
-			 * non-1 limit gets set to RLIM_INFINITY below, but
-			 * a limit of 0 skips the dump.  This is a consistent
-			 * way to catch recursive crashes.  We can still crash
-			 * if the core_pattern binary sets RLIM_CORE =  !1
-			 * but it runs as root, and can do lots of stupid things
+			 * cprm.limit of 1 here as a speacial value, this is a
+			 * consistent way to catch recursive crashes.
+			 * We can still crash if the core_pattern binary sets
+			 * RLIM_CORE = !1, but it runs as root, and can do
+			 * lots of stupid things.
+			 *
 			 * Note that we use task_tgid_vnr here to grab the pid
 			 * of the process group leader.  That way we get the
 			 * right pid if a thread in a multi-threaded
@@ -2223,6 +2220,14 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs)
 		if (cprm.limit < binfmt->min_coredump)
 			goto fail_unlock;
 
+		if (need_nonrelative && cn.corename[0] != '/') {
+			printk(KERN_WARNING "Pid %d(%s) can only dump core "\
+				"to fully qualified path!\n",
+				task_tgid_vnr(current), current->comm);
+			printk(KERN_WARNING "Skipping core dump\n");
+			goto fail_unlock;
+		}
+
 		cprm.file = filp_open(cn.corename,
 				 O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag,
 				 0600);
diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c
index 1c3613998862..376aa77f3ca7 100644
--- a/fs/ext2/balloc.c
+++ b/fs/ext2/balloc.c
@@ -1444,19 +1444,9 @@ ext2_fsblk_t ext2_new_block(struct inode *inode, unsigned long goal, int *errp)
 
 #ifdef EXT2FS_DEBUG
 
-static const int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0};
-
-unsigned long ext2_count_free (struct buffer_head * map, unsigned int numchars)
+unsigned long ext2_count_free(struct buffer_head *map, unsigned int numchars)
 {
-	unsigned int i;
-	unsigned long sum = 0;
-
-	if (!map)
-		return (0);
-	for (i = 0; i < numchars; i++)
-		sum += nibblemap[map->b_data[i] & 0xf] +
-			nibblemap[(map->b_data[i] >> 4) & 0xf];
-	return (sum);
+	return numchars * BITS_PER_BYTE - memweight(map->b_data, numchars);
 }
 
 #endif  /*  EXT2FS_DEBUG  */
diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index c13eb7b91a11..8f370e012e61 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -644,6 +644,7 @@ unsigned long ext2_count_free_inodes (struct super_block * sb)
 	}
 	brelse(bitmap_bh);
 	printk("ext2_count_free_inodes: stored = %lu, computed = %lu, %lu\n",
+		(unsigned long)
 		percpu_counter_read(&EXT2_SB(sb)->s_freeinodes_counter),
 		desc_count, bitmap_count);
 	return desc_count;
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 264d315f6c47..6363ac66fafa 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -79,6 +79,7 @@ void ext2_evict_inode(struct inode * inode)
 	truncate_inode_pages(&inode->i_data, 0);
 
 	if (want_delete) {
+		sb_start_intwrite(inode->i_sb);
 		/* set dtime */
 		EXT2_I(inode)->i_dtime	= get_seconds();
 		mark_inode_dirty(inode);
@@ -98,8 +99,10 @@ void ext2_evict_inode(struct inode * inode)
 	if (unlikely(rsv))
 		kfree(rsv);
 
-	if (want_delete)
+	if (want_delete) {
 		ext2_free_inode(inode);
+		sb_end_intwrite(inode->i_sb);
+	}
 }
 
 typedef struct {
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 9f311d27b16f..af74d9e27b71 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -42,6 +42,8 @@ static void ext2_sync_super(struct super_block *sb,
 static int ext2_remount (struct super_block * sb, int * flags, char * data);
 static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf);
 static int ext2_sync_fs(struct super_block *sb, int wait);
+static int ext2_freeze(struct super_block *sb);
+static int ext2_unfreeze(struct super_block *sb);
 
 void ext2_error(struct super_block *sb, const char *function,
 		const char *fmt, ...)
@@ -305,6 +307,8 @@ static const struct super_operations ext2_sops = {
 	.evict_inode	= ext2_evict_inode,
 	.put_super	= ext2_put_super,
 	.sync_fs	= ext2_sync_fs,
+	.freeze_fs	= ext2_freeze,
+	.unfreeze_fs	= ext2_unfreeze,
 	.statfs		= ext2_statfs,
 	.remount_fs	= ext2_remount,
 	.show_options	= ext2_show_options,
@@ -1200,6 +1204,35 @@ static int ext2_sync_fs(struct super_block *sb, int wait)
 	return 0;
 }
 
+static int ext2_freeze(struct super_block *sb)
+{
+	struct ext2_sb_info *sbi = EXT2_SB(sb);
+
+	/*
+	 * Open but unlinked files present? Keep EXT2_VALID_FS flag cleared
+	 * because we have unattached inodes and thus filesystem is not fully
+	 * consistent.
+	 */
+	if (atomic_long_read(&sb->s_remove_count)) {
+		ext2_sync_fs(sb, 1);
+		return 0;
+	}
+	/* Set EXT2_FS_VALID flag */
+	spin_lock(&sbi->s_lock);
+	sbi->s_es->s_state = cpu_to_le16(sbi->s_mount_state);
+	spin_unlock(&sbi->s_lock);
+	ext2_sync_super(sb, sbi->s_es, 1);
+
+	return 0;
+}
+
+static int ext2_unfreeze(struct super_block *sb)
+{
+	/* Just write sb to clear EXT2_VALID_FS flag */
+	ext2_write_super(sb);
+
+	return 0;
+}
 
 void ext2_write_super(struct super_block *sb)
 {
diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c
index 25cd60892116..90d901f0486b 100644
--- a/fs/ext3/balloc.c
+++ b/fs/ext3/balloc.c
@@ -1813,7 +1813,7 @@ ext3_fsblk_t ext3_count_free_blocks(struct super_block *sb)
 	brelse(bitmap_bh);
 	printk("ext3_count_free_blocks: stored = "E3FSBLK
 		", computed = "E3FSBLK", "E3FSBLK"\n",
-	       le32_to_cpu(es->s_free_blocks_count),
+	       (ext3_fsblk_t)le32_to_cpu(es->s_free_blocks_count),
 		desc_count, bitmap_count);
 	return bitmap_count;
 #else
diff --git a/fs/ext3/bitmap.c b/fs/ext3/bitmap.c
index 909d13e26560..ef9c643e8e9d 100644
--- a/fs/ext3/bitmap.c
+++ b/fs/ext3/bitmap.c
@@ -11,19 +11,9 @@
 
 #ifdef EXT3FS_DEBUG
 
-static const int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0};
-
 unsigned long ext3_count_free (struct buffer_head * map, unsigned int numchars)
 {
-	unsigned int i;
-	unsigned long sum = 0;
-
-	if (!map)
-		return (0);
-	for (i = 0; i < numchars; i++)
-		sum += nibblemap[map->b_data[i] & 0xf] +
-			nibblemap[(map->b_data[i] >> 4) & 0xf];
-	return (sum);
+	return numchars * BITS_PER_BYTE - memweight(map->b_data, numchars);
 }
 
 #endif  /*  EXT3FS_DEBUG  */
diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c
index a94b9c63ee5c..f8716eab9995 100644
--- a/fs/ext4/bitmap.c
+++ b/fs/ext4/bitmap.c
@@ -11,16 +11,9 @@
 #include <linux/jbd2.h>
 #include "ext4.h"
 
-static const int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0};
-
 unsigned int ext4_count_free(char *bitmap, unsigned int numchars)
 {
-	unsigned int i, sum = 0;
-
-	for (i = 0; i < numchars; i++)
-		sum += nibblemap[bitmap[i] & 0xf] +
-			nibblemap[(bitmap[i] >> 4) & 0xf];
-	return sum;
+	return numchars * BITS_PER_BYTE - memweight(bitmap, numchars);
 }
 
 int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 89b59cb7f9b8..6324f74e0342 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -233,6 +233,11 @@ void ext4_evict_inode(struct inode *inode)
 	if (is_bad_inode(inode))
 		goto no_delete;
 
+	/*
+	 * Protect us against freezing - iput() caller didn't have to have any
+	 * protection against it
+	 */
+	sb_start_intwrite(inode->i_sb);
 	handle = ext4_journal_start(inode, ext4_blocks_for_truncate(inode)+3);
 	if (IS_ERR(handle)) {
 		ext4_std_error(inode->i_sb, PTR_ERR(handle));
@@ -242,6 +247,7 @@ void ext4_evict_inode(struct inode *inode)
 		 * cleaned up.
 		 */
 		ext4_orphan_del(NULL, inode);
+		sb_end_intwrite(inode->i_sb);
 		goto no_delete;
 	}
 
@@ -273,6 +279,7 @@ void ext4_evict_inode(struct inode *inode)
 		stop_handle:
 			ext4_journal_stop(handle);
 			ext4_orphan_del(NULL, inode);
+			sb_end_intwrite(inode->i_sb);
 			goto no_delete;
 		}
 	}
@@ -301,6 +308,7 @@ void ext4_evict_inode(struct inode *inode)
 	else
 		ext4_free_inode(handle, inode);
 	ext4_journal_stop(handle);
+	sb_end_intwrite(inode->i_sb);
 	return;
 no_delete:
 	ext4_clear_inode(inode);	/* We must guarantee clearing of inode... */
@@ -4779,11 +4787,7 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	get_block_t *get_block;
 	int retries = 0;
 
-	/*
-	 * This check is racy but catches the common case. We rely on
-	 * __block_page_mkwrite() to do a reliable check.
-	 */
-	vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
+	sb_start_pagefault(inode->i_sb);
 	/* Delalloc case is easy... */
 	if (test_opt(inode->i_sb, DELALLOC) &&
 	    !ext4_should_journal_data(inode) &&
@@ -4851,5 +4855,6 @@ retry_alloc:
 out_ret:
 	ret = block_page_mkwrite_return(ret);
 out:
+	sb_end_pagefault(inode->i_sb);
 	return ret;
 }
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index f99a1311e847..fe7c63f4717e 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -44,6 +44,11 @@ static int write_mmp_block(struct super_block *sb, struct buffer_head *bh)
 {
 	struct mmp_struct *mmp = (struct mmp_struct *)(bh->b_data);
 
+	/*
+	 * We protect against freezing so that we don't create dirty buffers
+	 * on frozen filesystem.
+	 */
+	sb_start_write(sb);
 	ext4_mmp_csum_set(sb, mmp);
 	mark_buffer_dirty(bh);
 	lock_buffer(bh);
@@ -51,6 +56,7 @@ static int write_mmp_block(struct super_block *sb, struct buffer_head *bh)
 	get_bh(bh);
 	submit_bh(WRITE_SYNC, bh);
 	wait_on_buffer(bh);
+	sb_end_write(sb);
 	if (unlikely(!buffer_uptodate(bh)))
 		return 1;
 
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 2d51cd9af225..d76ec8277d3f 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -331,33 +331,17 @@ static void ext4_put_nojournal(handle_t *handle)
  * journal_end calls result in the superblock being marked dirty, so
  * that sync() will call the filesystem's write_super callback if
  * appropriate.
- *
- * To avoid j_barrier hold in userspace when a user calls freeze(),
- * ext4 prevents a new handle from being started by s_frozen, which
- * is in an upper layer.
  */
 handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks)
 {
 	journal_t *journal;
-	handle_t  *handle;
 
 	trace_ext4_journal_start(sb, nblocks, _RET_IP_);
 	if (sb->s_flags & MS_RDONLY)
 		return ERR_PTR(-EROFS);
 
+	WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE);
 	journal = EXT4_SB(sb)->s_journal;
-	handle = ext4_journal_current_handle();
-
-	/*
-	 * If a handle has been started, it should be allowed to
-	 * finish, otherwise deadlock could happen between freeze
-	 * and others(e.g. truncate) due to the restart of the
-	 * journal handle if the filesystem is forzen and active
-	 * handles are not stopped.
-	 */
-	if (!handle)
-		vfs_check_frozen(sb, SB_FREEZE_TRANS);
-
 	if (!journal)
 		return ext4_get_nojournal();
 	/*
@@ -2747,6 +2731,7 @@ static int ext4_run_li_request(struct ext4_li_request *elr)
 	sb = elr->lr_super;
 	ngroups = EXT4_SB(sb)->s_groups_count;
 
+	sb_start_write(sb);
 	for (group = elr->lr_next_group; group < ngroups; group++) {
 		gdp = ext4_get_group_desc(sb, group, NULL);
 		if (!gdp) {
@@ -2773,6 +2758,7 @@ static int ext4_run_li_request(struct ext4_li_request *elr)
 		elr->lr_next_sched = jiffies + elr->lr_timeout;
 		elr->lr_next_group = group + 1;
 	}
+	sb_end_write(sb);
 
 	return ret;
 }
@@ -4460,10 +4446,8 @@ int ext4_force_commit(struct super_block *sb)
 		return 0;
 
 	journal = EXT4_SB(sb)->s_journal;
-	if (journal) {
-		vfs_check_frozen(sb, SB_FREEZE_TRANS);
+	if (journal)
 		ret = ext4_journal_force_commit(journal);
-	}
 
 	return ret;
 }
@@ -4493,9 +4477,8 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
  * gives us a chance to flush the journal completely and mark the fs clean.
  *
  * Note that only this function cannot bring a filesystem to be in a clean
- * state independently, because ext4 prevents a new handle from being started
- * by @sb->s_frozen, which stays in an upper layer.  It thus needs help from
- * the upper layer.
+ * state independently. It relies on upper layer to stop all data & metadata
+ * modifications.
  */
 static int ext4_freeze(struct super_block *sb)
 {
@@ -4522,7 +4505,7 @@ static int ext4_freeze(struct super_block *sb)
 	EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
 	error = ext4_commit_super(sb, 1);
 out:
-	/* we rely on s_frozen to stop further updates */
+	/* we rely on upper layer to stop further updates */
 	jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
 	return error;
 }
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 6eaa28c98ad1..dc49ed2cbffa 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -35,6 +35,11 @@
 #define FAT_MAX_UNI_CHARS	((MSDOS_SLOTS - 1) * 13 + 1)
 #define FAT_MAX_UNI_SIZE	(FAT_MAX_UNI_CHARS * sizeof(wchar_t))
 
+static inline unsigned char fat_tolower(unsigned char c)
+{
+	return ((c >= 'A') && (c <= 'Z')) ? c+32 : c;
+}
+
 static inline loff_t fat_make_i_pos(struct super_block *sb,
 				    struct buffer_head *bh,
 				    struct msdos_dir_entry *de)
@@ -333,6 +338,124 @@ parse_long:
 	return 0;
 }
 
+/**
+ * fat_parse_short - Parse MS-DOS (short) directory entry.
+ * @sb:		superblock
+ * @de:		directory entry to parse
+ * @name:	FAT_MAX_SHORT_SIZE array in which to place extracted name
+ * @dot_hidden:	Nonzero == prepend '.' to names with ATTR_HIDDEN
+ *
+ * Returns the number of characters extracted into 'name'.
+ */
+static int fat_parse_short(struct super_block *sb,
+			   const struct msdos_dir_entry *de,
+			   unsigned char *name, int dot_hidden)
+{
+	const struct msdos_sb_info *sbi = MSDOS_SB(sb);
+	int isvfat = sbi->options.isvfat;
+	int nocase = sbi->options.nocase;
+	unsigned short opt_shortname = sbi->options.shortname;
+	struct nls_table *nls_disk = sbi->nls_disk;
+	wchar_t uni_name[14];
+	unsigned char c, work[MSDOS_NAME];
+	unsigned char *ptname = name;
+	int chi, chl, i, j, k;
+	int dotoffset = 0;
+	int name_len = 0, uni_len = 0;
+
+	if (!isvfat && dot_hidden && (de->attr & ATTR_HIDDEN)) {
+		*ptname++ = '.';
+		dotoffset = 1;
+	}
+
+	memcpy(work, de->name, sizeof(work));
+	/* see namei.c, msdos_format_name */
+	if (work[0] == 0x05)
+		work[0] = 0xE5;
+
+	/* Filename */
+	for (i = 0, j = 0; i < 8;) {
+		c = work[i];
+		if (!c)
+			break;
+		chl = fat_shortname2uni(nls_disk, &work[i], 8 - i,
+					&uni_name[j++], opt_shortname,
+					de->lcase & CASE_LOWER_BASE);
+		if (chl <= 1) {
+			if (!isvfat)
+				ptname[i] = nocase ? c : fat_tolower(c);
+			i++;
+			if (c != ' ') {
+				name_len = i;
+				uni_len  = j;
+			}
+		} else {
+			uni_len = j;
+			if (isvfat)
+				i += min(chl, 8-i);
+			else {
+				for (chi = 0; chi < chl && i < 8; chi++, i++)
+					ptname[i] = work[i];
+			}
+			if (chl)
+				name_len = i;
+		}
+	}
+
+	i = name_len;
+	j = uni_len;
+	fat_short2uni(nls_disk, ".", 1, &uni_name[j++]);
+	if (!isvfat)
+		ptname[i] = '.';
+	i++;
+
+	/* Extension */
+	for (k = 8; k < MSDOS_NAME;) {
+		c = work[k];
+		if (!c)
+			break;
+		chl = fat_shortname2uni(nls_disk, &work[k], MSDOS_NAME - k,
+					&uni_name[j++], opt_shortname,
+					de->lcase & CASE_LOWER_EXT);
+		if (chl <= 1) {
+			k++;
+			if (!isvfat)
+				ptname[i] = nocase ? c : fat_tolower(c);
+			i++;
+			if (c != ' ') {
+				name_len = i;
+				uni_len  = j;
+			}
+		} else {
+			uni_len = j;
+			if (isvfat) {
+				int offset = min(chl, MSDOS_NAME-k);
+				k += offset;
+				i += offset;
+			} else {
+				for (chi = 0; chi < chl && k < MSDOS_NAME;
+				     chi++, i++, k++) {
+						ptname[i] = work[k];
+				}
+			}
+			if (chl)
+				name_len = i;
+		}
+	}
+
+	if (name_len > 0) {
+		name_len += dotoffset;
+
+		if (sbi->options.isvfat) {
+			uni_name[uni_len] = 0x0000;
+			name_len = fat_uni_to_x8(sb, uni_name, name,
+						 FAT_MAX_SHORT_SIZE);
+		}
+	}
+
+	return name_len;
+}
+
 /*
  * Return values: negative -> error, 0 -> not found, positive -> found,
  * value is the total amount of slots, including the shortname entry.
@@ -344,15 +467,11 @@ int fat_search_long(struct inode *inode, const unsigned char *name,
 	struct msdos_sb_info *sbi = MSDOS_SB(sb);
 	struct buffer_head *bh = NULL;
 	struct msdos_dir_entry *de;
-	struct nls_table *nls_disk = sbi->nls_disk;
 	unsigned char nr_slots;
-	wchar_t bufuname[14];
 	wchar_t *unicode = NULL;
-	unsigned char work[MSDOS_NAME];
 	unsigned char bufname[FAT_MAX_SHORT_SIZE];
-	unsigned short opt_shortname = sbi->options.shortname;
 	loff_t cpos = 0;
-	int chl, i, j, last_u, err, len;
+	int err, len;
 
 	err = -ENOENT;
 	while (1) {
@@ -380,47 +499,16 @@ parse_record:
 				goto end_of_dir;
 		}
 
-		memcpy(work, de->name, sizeof(de->name));
-		/* see namei.c, msdos_format_name */
-		if (work[0] == 0x05)
-			work[0] = 0xE5;
-		for (i = 0, j = 0, last_u = 0; i < 8;) {
-			if (!work[i])
-				break;
-			chl = fat_shortname2uni(nls_disk, &work[i], 8 - i,
-						&bufuname[j++], opt_shortname,
-						de->lcase & CASE_LOWER_BASE);
-			if (chl <= 1) {
-				if (work[i] != ' ')
-					last_u = j;
-			} else {
-				last_u = j;
-			}
-			i += chl;
-		}
-		j = last_u;
-		fat_short2uni(nls_disk, ".", 1, &bufuname[j++]);
-		for (i = 8; i < MSDOS_NAME;) {
-			if (!work[i])
-				break;
-			chl = fat_shortname2uni(nls_disk, &work[i],
-						MSDOS_NAME - i,
-						&bufuname[j++], opt_shortname,
-						de->lcase & CASE_LOWER_EXT);
-			if (chl <= 1) {
-				if (work[i] != ' ')
-					last_u = j;
-			} else {
-				last_u = j;
-			}
-			i += chl;
-		}
-		if (!last_u)
+		/* Never prepend '.' to hidden files here.
+		 * That is done only for msdos mounts (and only when
+		 * 'dotsOK=yes'); if we are executing here, it is in the
+		 * context of a vfat mount.
+		 */
+		len = fat_parse_short(sb, de, bufname, 0);
+		if (len == 0)
 			continue;
 
 		/* Compare shortname */
-		bufuname[last_u] = 0x0000;
-		len = fat_uni_to_x8(sb, bufuname, bufname, sizeof(bufname));
 		if (fat_name_match(sbi, name, name_len, bufname, len))
 			goto found;
 
@@ -469,20 +557,15 @@ static int __fat_readdir(struct inode *inode, struct file *filp, void *dirent,
 	struct msdos_sb_info *sbi = MSDOS_SB(sb);
 	struct buffer_head *bh;
 	struct msdos_dir_entry *de;
-	struct nls_table *nls_disk = sbi->nls_disk;
 	unsigned char nr_slots;
-	wchar_t bufuname[14];
 	wchar_t *unicode = NULL;
-	unsigned char c, work[MSDOS_NAME];
-	unsigned char bufname[FAT_MAX_SHORT_SIZE], *ptname = bufname;
-	unsigned short opt_shortname = sbi->options.shortname;
+	unsigned char bufname[FAT_MAX_SHORT_SIZE];
 	int isvfat = sbi->options.isvfat;
-	int nocase = sbi->options.nocase;
 	const char *fill_name = NULL;
 	unsigned long inum;
 	unsigned long lpos, dummy, *furrfu = &lpos;
 	loff_t cpos;
-	int chi, chl, i, i2, j, last, last_u, dotoffset = 0, fill_len = 0;
+	int short_len = 0, fill_len = 0;
 	int ret = 0;
 
 	lock_super(sb);
@@ -556,74 +639,10 @@ parse_record:
 		}
 	}
 
-	if (sbi->options.dotsOK) {
-		ptname = bufname;
-		dotoffset = 0;
-		if (de->attr & ATTR_HIDDEN) {
-			*ptname++ = '.';
-			dotoffset = 1;
-		}
-	}
-
-	memcpy(work, de->name, sizeof(de->name));
-	/* see namei.c, msdos_format_name */
-	if (work[0] == 0x05)
-		work[0] = 0xE5;
-	for (i = 0, j = 0, last = 0, last_u = 0; i < 8;) {
-		if (!(c = work[i]))
-			break;
-		chl = fat_shortname2uni(nls_disk, &work[i], 8 - i,
-					&bufuname[j++], opt_shortname,
-					de->lcase & CASE_LOWER_BASE);
-		if (chl <= 1) {
-			ptname[i++] = (!nocase && c>='A' && c<='Z') ? c+32 : c;
-			if (c != ' ') {
-				last = i;
-				last_u = j;
-			}
-		} else {
-			last_u = j;
-			for (chi = 0; chi < chl && i < 8; chi++) {
-				ptname[i] = work[i];
-				i++; last = i;
-			}
-		}
-	}
-	i = last;
-	j = last_u;
-	fat_short2uni(nls_disk, ".", 1, &bufuname[j++]);
-	ptname[i++] = '.';
-	for (i2 = 8; i2 < MSDOS_NAME;) {
-		if (!(c = work[i2]))
-			break;
-		chl = fat_shortname2uni(nls_disk, &work[i2], MSDOS_NAME - i2,
-					&bufuname[j++], opt_shortname,
-					de->lcase & CASE_LOWER_EXT);
-		if (chl <= 1) {
-			i2++;
-			ptname[i++] = (!nocase && c>='A' && c<='Z') ? c+32 : c;
-			if (c != ' ') {
-				last = i;
-				last_u = j;
-			}
-		} else {
-			last_u = j;
-			for (chi = 0; chi < chl && i2 < MSDOS_NAME; chi++) {
-				ptname[i++] = work[i2++];
-				last = i;
-			}
-		}
-	}
-	if (!last)
+	short_len = fat_parse_short(sb, de, bufname, sbi->options.dotsOK);
+	if (short_len == 0)
 		goto record_end;
 
-	i = last + dotoffset;
-	j = last_u;
-
-	if (isvfat) {
-		bufuname[j] = 0x0000;
-		i = fat_uni_to_x8(sb, bufuname, bufname, sizeof(bufname));
-	}
 	if (nr_slots) {
 		/* hack for fat_ioctl_filldir() */
 		struct fat_ioctl_filldir_callback *p = dirent;
@@ -631,12 +650,12 @@ parse_record:
 		p->longname = fill_name;
 		p->long_len = fill_len;
 		p->shortname = bufname;
-		p->short_len = i;
+		p->short_len = short_len;
 		fill_name = NULL;
 		fill_len = 0;
 	} else {
 		fill_name = bufname;
-		fill_len = i;
+		fill_len = short_len;
 	}
 
 start_filldir:
diff --git a/fs/fat/fat.h b/fs/fat/fat.h
index fc35c5c69136..2deeeb86f331 100644
--- a/fs/fat/fat.h
+++ b/fs/fat/fat.h
@@ -217,6 +217,21 @@ static inline void fat16_towchar(wchar_t *dst, const __u8 *src, size_t len)
 #endif
 }
 
+static inline int fat_get_start(const struct msdos_sb_info *sbi,
+				const struct msdos_dir_entry *de)
+{
+	int cluster = le16_to_cpu(de->start);
+	if (sbi->fat_bits == 32)
+		cluster |= (le16_to_cpu(de->starthi) << 16);
+	return cluster;
+}
+
+static inline void fat_set_start(struct msdos_dir_entry *de, int cluster)
+{
+	de->start   = cpu_to_le16(cluster);
+	de->starthi = cpu_to_le16(cluster >> 16);
+}
+
 static inline void fatwchar_to16(__u8 *dst, const wchar_t *src, size_t len)
 {
 #ifdef __BIG_ENDIAN
diff --git a/fs/fat/file.c b/fs/fat/file.c
index a71fe3715ee8..e007b8bd8e5e 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -43,10 +43,10 @@ static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr)
 	if (err)
 		goto out;
 
-	mutex_lock(&inode->i_mutex);
 	err = mnt_want_write_file(file);
 	if (err)
-		goto out_unlock_inode;
+		goto out;
+	mutex_lock(&inode->i_mutex);
 
 	/*
 	 * ATTR_VOLUME and ATTR_DIR cannot be changed; this also
@@ -73,14 +73,14 @@ static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr)
 	/* The root directory has no attributes */
 	if (inode->i_ino == MSDOS_ROOT_INO && attr != ATTR_DIR) {
 		err = -EINVAL;
-		goto out_drop_write;
+		goto out_unlock_inode;
 	}
 
 	if (sbi->options.sys_immutable &&
 	    ((attr | oldattr) & ATTR_SYS) &&
 	    !capable(CAP_LINUX_IMMUTABLE)) {
 		err = -EPERM;
-		goto out_drop_write;
+		goto out_unlock_inode;
 	}
 
 	/*
@@ -90,12 +90,12 @@ static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr)
 	 */
 	err = security_inode_setattr(file->f_path.dentry, &ia);
 	if (err)
-		goto out_drop_write;
+		goto out_unlock_inode;
 
 	/* This MUST be done before doing anything irreversible... */
 	err = fat_setattr(file->f_path.dentry, &ia);
 	if (err)
-		goto out_drop_write;
+		goto out_unlock_inode;
 
 	fsnotify_change(file->f_path.dentry, ia.ia_valid);
 	if (sbi->options.sys_immutable) {
@@ -107,10 +107,9 @@ static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr)
 
 	fat_save_attrs(inode, attr);
 	mark_inode_dirty(inode);
-out_drop_write:
-	mnt_drop_write_file(file);
 out_unlock_inode:
 	mutex_unlock(&inode->i_mutex);
+	mnt_drop_write_file(file);
 out:
 	return err;
 }
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 0038b32cb362..05e897fe9866 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -369,10 +369,7 @@ static int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
 		inode->i_op = sbi->dir_ops;
 		inode->i_fop = &fat_dir_operations;
 
-		MSDOS_I(inode)->i_start = le16_to_cpu(de->start);
-		if (sbi->fat_bits == 32)
-			MSDOS_I(inode)->i_start |= (le16_to_cpu(de->starthi) << 16);
-
+		MSDOS_I(inode)->i_start = fat_get_start(sbi, de);
 		MSDOS_I(inode)->i_logstart = MSDOS_I(inode)->i_start;
 		error = fat_calc_dir_size(inode);
 		if (error < 0)
@@ -385,9 +382,7 @@ static int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
 		inode->i_mode = fat_make_mode(sbi, de->attr,
 			((sbi->options.showexec && !is_exec(de->name + 8))
 			 ? S_IRUGO|S_IWUGO : S_IRWXUGO));
-		MSDOS_I(inode)->i_start = le16_to_cpu(de->start);
-		if (sbi->fat_bits == 32)
-			MSDOS_I(inode)->i_start |= (le16_to_cpu(de->starthi) << 16);
+		MSDOS_I(inode)->i_start = fat_get_start(sbi, de);
 
 		MSDOS_I(inode)->i_logstart = MSDOS_I(inode)->i_start;
 		inode->i_size = le32_to_cpu(de->size);
@@ -613,8 +608,7 @@ retry:
 	else
 		raw_entry->size = cpu_to_le32(inode->i_size);
 	raw_entry->attr = fat_make_attrs(inode);
-	raw_entry->start = cpu_to_le16(MSDOS_I(inode)->i_logstart);
-	raw_entry->starthi = cpu_to_le16(MSDOS_I(inode)->i_logstart >> 16);
+	fat_set_start(raw_entry, MSDOS_I(inode)->i_logstart);
 	fat_time_unix2fat(sbi, &inode->i_mtime, &raw_entry->time,
 			  &raw_entry->date, NULL);
 	if (sbi->options.isvfat) {
diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c
index 70d993a93805..b0e12bf9f4a1 100644
--- a/fs/fat/namei_msdos.c
+++ b/fs/fat/namei_msdos.c
@@ -246,8 +246,7 @@ static int msdos_add_entry(struct inode *dir, const unsigned char *name,
 	de.ctime_cs = 0;
 	de.time = time;
 	de.date = date;
-	de.start = cpu_to_le16(cluster);
-	de.starthi = cpu_to_le16(cluster >> 16);
+	fat_set_start(&de, cluster);
 	de.size = 0;
 
 	err = fat_add_entries(dir, &de, 1, sinfo);
@@ -530,9 +529,7 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name,
 		mark_inode_dirty(old_inode);
 
 	if (update_dotdot) {
-		int start = MSDOS_I(new_dir)->i_logstart;
-		dotdot_de->start = cpu_to_le16(start);
-		dotdot_de->starthi = cpu_to_le16(start >> 16);
+		fat_set_start(dotdot_de, MSDOS_I(new_dir)->i_logstart);
 		mark_buffer_dirty_inode(dotdot_bh, old_inode);
 		if (IS_DIRSYNC(new_dir)) {
 			err = sync_dirty_buffer(dotdot_bh);
@@ -572,9 +569,7 @@ error_dotdot:
 	corrupt = 1;
 
 	if (update_dotdot) {
-		int start = MSDOS_I(old_dir)->i_logstart;
-		dotdot_de->start = cpu_to_le16(start);
-		dotdot_de->starthi = cpu_to_le16(start >> 16);
+		fat_set_start(dotdot_de, MSDOS_I(old_dir)->i_logstart);
 		mark_buffer_dirty_inode(dotdot_bh, old_inode);
 		corrupt |= sync_dirty_buffer(dotdot_bh);
 	}
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index 6cc480652433..6a6d8c0715a1 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -651,8 +651,7 @@ shortname:
 	de->time = de->ctime = time;
 	de->date = de->cdate = de->adate = date;
 	de->ctime_cs = time_cs;
-	de->start = cpu_to_le16(cluster);
-	de->starthi = cpu_to_le16(cluster >> 16);
+	fat_set_start(de, cluster);
 	de->size = 0;
 out_free:
 	__putname(uname);
@@ -965,9 +964,7 @@ static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry,
 		mark_inode_dirty(old_inode);
 
 	if (update_dotdot) {
-		int start = MSDOS_I(new_dir)->i_logstart;
-		dotdot_de->start = cpu_to_le16(start);
-		dotdot_de->starthi = cpu_to_le16(start >> 16);
+		fat_set_start(dotdot_de, MSDOS_I(new_dir)->i_logstart);
 		mark_buffer_dirty_inode(dotdot_bh, old_inode);
 		if (IS_DIRSYNC(new_dir)) {
 			err = sync_dirty_buffer(dotdot_bh);
@@ -1009,9 +1006,7 @@ error_dotdot:
 	corrupt = 1;
 
 	if (update_dotdot) {
-		int start = MSDOS_I(old_dir)->i_logstart;
-		dotdot_de->start = cpu_to_le16(start);
-		dotdot_de->starthi = cpu_to_le16(start >> 16);
+		fat_set_start(dotdot_de, MSDOS_I(old_dir)->i_logstart);
 		mark_buffer_dirty_inode(dotdot_bh, old_inode);
 		corrupt |= sync_dirty_buffer(dotdot_bh);
 	}
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 81b70e665bf0..887b5ba8c9b5 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -20,6 +20,7 @@
 #include <linux/signal.h>
 #include <linux/rcupdate.h>
 #include <linux/pid_namespace.h>
+#include <linux/user_namespace.h>
 
 #include <asm/poll.h>
 #include <asm/siginfo.h>
@@ -340,6 +341,31 @@ static int f_getown_ex(struct file *filp, unsigned long arg)
 	return ret;
 }
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
+static int f_getowner_uids(struct file *filp, unsigned long arg)
+{
+	struct user_namespace *user_ns = current_user_ns();
+	uid_t * __user dst = (void * __user)arg;
+	uid_t src[2];
+	int err;
+
+	read_lock(&filp->f_owner.lock);
+	src[0] = from_kuid(user_ns, filp->f_owner.uid);
+	src[1] = from_kuid(user_ns, filp->f_owner.euid);
+	read_unlock(&filp->f_owner.lock);
+
+	err  = put_user(src[0], &dst[0]);
+	err |= put_user(src[1], &dst[1]);
+
+	return err;
+}
+#else
+static int f_getowner_uids(struct file *filp, unsigned long arg)
+{
+	return -EINVAL;
+}
+#endif
+
 static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 		struct file *filp)
 {
@@ -396,6 +422,9 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 	case F_SETOWN_EX:
 		err = f_setown_ex(filp, arg);
 		break;
+	case F_GETOWNER_UIDS:
+		err = f_getowner_uids(filp, arg);
+		break;
 	case F_GETSIG:
 		err = filp->f_owner.signum;
 		break;
diff --git a/fs/file_table.c b/fs/file_table.c
index b3fc4d67a26b..701985e4ccda 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -43,7 +43,7 @@ static struct kmem_cache *filp_cachep __read_mostly;
 
 static struct percpu_counter nr_files __cacheline_aligned_in_smp;
 
-static inline void file_free_rcu(struct rcu_head *head)
+static void file_free_rcu(struct rcu_head *head)
 {
 	struct file *f = container_of(head, struct file, f_u.fu_rcuhead);
 
@@ -217,7 +217,7 @@ static void drop_file_write_access(struct file *file)
 		return;
 	if (file_check_writeable(file) != 0)
 		return;
-	mnt_drop_write(mnt);
+	__mnt_drop_write(mnt);
 	file_release_write(file);
 }
 
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 8f660dd6137a..be3efc4f64f4 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -52,11 +52,6 @@ struct wb_writeback_work {
 	struct completion *done;	/* set if the caller waits */
 };
 
-/*
- * We don't actually have pdflush, but this one is exported though /proc...
- */
-int nr_pdflush_threads;
-
 /**
  * writeback_in_progress - determine whether there is writeback in progress
  * @bdi: the device's backing_dev_info structure.
@@ -628,8 +623,8 @@ static long writeback_sb_inodes(struct super_block *sb,
 		}
 
 		/*
-		 * Don't bother with new inodes or inodes beeing freed, first
-		 * kind does not need peridic writeout yet, and for the latter
+		 * Don't bother with new inodes or inodes being freed, first
+		 * kind does not need periodic writeout yet, and for the latter
 		 * kind writeout is handled by the freer.
 		 */
 		spin_lock(&inode->i_lock);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index b321a688cde7..93d8d6c9494d 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -944,9 +944,8 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		return err;
 
 	count = ocount;
-
+	sb_start_write(inode->i_sb);
 	mutex_lock(&inode->i_mutex);
-	vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
 
 	/* We can write back this queue in page reclaim */
 	current->backing_dev_info = mapping->backing_dev_info;
@@ -1004,6 +1003,7 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 out:
 	current->backing_dev_info = NULL;
 	mutex_unlock(&inode->i_mutex);
+	sb_end_write(inode->i_sb);
 
 	return written ? written : err;
 }
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 9aa6af13823c..d1d791ef38de 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -373,11 +373,10 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	loff_t size;
 	int ret;
 
-	/* Wait if fs is frozen. This is racy so we check again later on
-	 * and retry if the fs has been frozen after the page lock has
-	 * been acquired
-	 */
-	vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
+	sb_start_pagefault(inode->i_sb);
+
+	/* Update file times before taking page lock */
+	file_update_time(vma->vm_file);
 
 	ret = gfs2_rs_alloc(ip);
 	if (ret)
@@ -462,14 +461,9 @@ out:
 	gfs2_holder_uninit(&gh);
 	if (ret == 0) {
 		set_page_dirty(page);
-		/* This check must be post dropping of transaction lock */
-		if (inode->i_sb->s_frozen == SB_UNFROZEN) {
-			wait_on_page_writeback(page);
-		} else {
-			ret = -EAGAIN;
-			unlock_page(page);
-		}
+		wait_on_page_writeback(page);
 	}
+	sb_end_pagefault(inode->i_sb);
 	return block_page_mkwrite_return(ret);
 }
 
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index ad3e2fb763d7..adbd27875ef9 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -50,6 +50,7 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
 	if (revokes)
 		tr->tr_reserved += gfs2_struct2blk(sdp, revokes,
 						   sizeof(u64));
+	sb_start_intwrite(sdp->sd_vfs);
 	gfs2_holder_init(sdp->sd_trans_gl, LM_ST_SHARED, 0, &tr->tr_t_gh);
 
 	error = gfs2_glock_nq(&tr->tr_t_gh);
@@ -68,6 +69,7 @@ fail_gunlock:
 	gfs2_glock_dq(&tr->tr_t_gh);
 
 fail_holder_uninit:
+	sb_end_intwrite(sdp->sd_vfs);
 	gfs2_holder_uninit(&tr->tr_t_gh);
 	kfree(tr);
 
@@ -116,6 +118,7 @@ void gfs2_trans_end(struct gfs2_sbd *sdp)
 			gfs2_holder_uninit(&tr->tr_t_gh);
 			kfree(tr);
 		}
+		sb_end_intwrite(sdp->sd_vfs);
 		return;
 	}
 
@@ -136,6 +139,7 @@ void gfs2_trans_end(struct gfs2_sbd *sdp)
 
 	if (sdp->sd_vfs->s_flags & MS_SYNCHRONOUS)
 		gfs2_log_flush(sdp, NULL);
+	sb_end_intwrite(sdp->sd_vfs);
 }
 
 /**
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 473332098013..fdafb2d71654 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -365,7 +365,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 	u64 last_fs_block, last_fs_page;
 	int err;
 
-	err = -EINVAL;
+	err = -ENOMEM;
 	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
 	if (!sbi)
 		goto out;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index e13e9bdb0bf5..8349a899912e 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -416,8 +416,8 @@ hugetlb_vmtruncate_list(struct prio_tree_root *root, pgoff_t pgoff)
 		else
 			v_offset = 0;
 
-		__unmap_hugepage_range(vma,
-				vma->vm_start + v_offset, vma->vm_end, NULL);
+		unmap_hugepage_range(vma, vma->vm_start + v_offset,
+				     vma->vm_end, NULL);
 	}
 }
 
diff --git a/fs/inode.c b/fs/inode.c
index 3cc504320467..ac8d904b3f16 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1542,9 +1542,11 @@ void touch_atime(struct path *path)
 	if (timespec_equal(&inode->i_atime, &now))
 		return;
 
-	if (mnt_want_write(mnt))
+	if (!sb_start_write_trylock(inode->i_sb))
 		return;
 
+	if (__mnt_want_write(mnt))
+		goto skip_update;
 	/*
 	 * File systems can error out when updating inodes if they need to
 	 * allocate new space to modify an inode (such is the case for
@@ -1555,7 +1557,9 @@ void touch_atime(struct path *path)
 	 * of the fs read only, e.g. subvolumes in Btrfs.
 	 */
 	update_time(inode, &now, S_ATIME);
-	mnt_drop_write(mnt);
+	__mnt_drop_write(mnt);
+skip_update:
+	sb_end_write(inode->i_sb);
 }
 EXPORT_SYMBOL(touch_atime);
 
@@ -1662,11 +1666,11 @@ int file_update_time(struct file *file)
 		return 0;
 
 	/* Finally allowed to write? Takes lock. */
-	if (mnt_want_write_file(file))
+	if (__mnt_want_write_file(file))
 		return 0;
 
 	ret = update_time(inode, &now, sync_it);
-	mnt_drop_write_file(file);
+	__mnt_drop_write_file(file);
 
 	return ret;
 }
diff --git a/fs/internal.h b/fs/internal.h
index a6fd56c68b11..371bcc4b1697 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -61,6 +61,10 @@ extern void __init mnt_init(void);
 
 extern struct lglock vfsmount_lock;
 
+extern int __mnt_want_write(struct vfsmount *);
+extern int __mnt_want_write_file(struct file *);
+extern void __mnt_drop_write(struct vfsmount *);
+extern void __mnt_drop_write_file(struct file *);
 
 /*
  * fs_struct.c
diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index 8392cb85bd54..05d29124c6ab 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -156,12 +156,16 @@ int nlmclnt_proc(struct nlm_host *host, int cmd, struct file_lock *fl)
 	struct nlm_rqst		*call;
 	int			status;
 
-	nlm_get_host(host);
 	call = nlm_alloc_call(host);
 	if (call == NULL)
 		return -ENOMEM;
 
 	nlmclnt_locks_init_private(fl, host);
+	if (!fl->fl_u.nfs_fl.owner) {
+		/* lockowner allocation has failed */
+		nlmclnt_release_call(call);
+		return -ENOMEM;
+	}
 	/* Set up the argument struct */
 	nlmclnt_setlockargs(call, fl);
 
@@ -185,9 +189,6 @@ EXPORT_SYMBOL_GPL(nlmclnt_proc);
 
 /*
  * Allocate an NLM RPC call struct
- *
- * Note: the caller must hold a reference to host. In case of failure,
- * this reference will be released.
  */
 struct nlm_rqst *nlm_alloc_call(struct nlm_host *host)
 {
@@ -199,7 +200,7 @@ struct nlm_rqst *nlm_alloc_call(struct nlm_host *host)
 			atomic_set(&call->a_count, 1);
 			locks_init_lock(&call->a_args.lock.fl);
 			locks_init_lock(&call->a_res.lock.fl);
-			call->a_host = host;
+			call->a_host = nlm_get_host(host);
 			return call;
 		}
 		if (signalled())
@@ -207,7 +208,6 @@ struct nlm_rqst *nlm_alloc_call(struct nlm_host *host)
 		printk("nlm_alloc_call: failed, waiting for memory\n");
 		schedule_timeout_interruptible(5*HZ);
 	}
-	nlmclnt_release_host(host);
 	return NULL;
 }
 
@@ -750,7 +750,7 @@ static int nlmclnt_cancel(struct nlm_host *host, int block, struct file_lock *fl
 	dprintk("lockd: blocking lock attempt was interrupted by a signal.\n"
 		"       Attempting to cancel lock.\n");
 
-	req = nlm_alloc_call(nlm_get_host(host));
+	req = nlm_alloc_call(host);
 	if (!req)
 		return -ENOMEM;
 	req->a_flags = RPC_TASK_ASYNC;
diff --git a/fs/lockd/grace.c b/fs/lockd/grace.c
index 183cc1f0af1c..6d1ee7204c88 100644
--- a/fs/lockd/grace.c
+++ b/fs/lockd/grace.c
@@ -4,8 +4,10 @@
 
 #include <linux/module.h>
 #include <linux/lockd/bind.h>
+#include <net/net_namespace.h>
+
+#include "netns.h"
 
-static LIST_HEAD(grace_list);
 static DEFINE_SPINLOCK(grace_lock);
 
 /**
@@ -19,10 +21,12 @@ static DEFINE_SPINLOCK(grace_lock);
  *
  * This function is called to start a grace period.
  */
-void locks_start_grace(struct lock_manager *lm)
+void locks_start_grace(struct net *net, struct lock_manager *lm)
 {
+	struct lockd_net *ln = net_generic(net, lockd_net_id);
+
 	spin_lock(&grace_lock);
-	list_add(&lm->list, &grace_list);
+	list_add(&lm->list, &ln->grace_list);
 	spin_unlock(&grace_lock);
 }
 EXPORT_SYMBOL_GPL(locks_start_grace);
@@ -52,8 +56,10 @@ EXPORT_SYMBOL_GPL(locks_end_grace);
  * to answer ordinary lock requests, and when they should accept only
  * lock reclaims.
  */
-int locks_in_grace(void)
+int locks_in_grace(struct net *net)
 {
-	return !list_empty(&grace_list);
+	struct lockd_net *ln = net_generic(net, lockd_net_id);
+
+	return !list_empty(&ln->grace_list);
 }
 EXPORT_SYMBOL_GPL(locks_in_grace);
diff --git a/fs/lockd/host.c b/fs/lockd/host.c
index eb75ca7c2d6e..f9b22e58f78f 100644
--- a/fs/lockd/host.c
+++ b/fs/lockd/host.c
@@ -21,6 +21,8 @@
 
 #include <net/ipv6.h>
 
+#include "netns.h"
+
 #define NLMDBG_FACILITY		NLMDBG_HOSTCACHE
 #define NLM_HOST_NRHASH		32
 #define NLM_HOST_REBIND		(60 * HZ)
@@ -41,11 +43,10 @@ static struct hlist_head	nlm_client_hosts[NLM_HOST_NRHASH];
 		hlist_for_each_entry_safe((host), (pos), (next), \
 						(chain), h_hash)
 
-static unsigned long		next_gc;
 static unsigned long		nrhosts;
 static DEFINE_MUTEX(nlm_host_mutex);
 
-static void			nlm_gc_hosts(void);
+static void			nlm_gc_hosts(struct net *net);
 
 struct nlm_lookup_host_info {
 	const int		server;		/* search for server|client */
@@ -172,6 +173,7 @@ out:
 static void nlm_destroy_host_locked(struct nlm_host *host)
 {
 	struct rpc_clnt	*clnt;
+	struct lockd_net *ln = net_generic(host->net, lockd_net_id);
 
 	dprintk("lockd: destroy host %s\n", host->h_name);
 
@@ -188,6 +190,7 @@ static void nlm_destroy_host_locked(struct nlm_host *host)
 		rpc_shutdown_client(clnt);
 	kfree(host);
 
+	ln->nrhosts--;
 	nrhosts--;
 }
 
@@ -228,6 +231,7 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap,
 	struct hlist_node *pos;
 	struct nlm_host	*host;
 	struct nsm_handle *nsm = NULL;
+	struct lockd_net *ln = net_generic(net, lockd_net_id);
 
 	dprintk("lockd: %s(host='%s', vers=%u, proto=%s)\n", __func__,
 			(hostname ? hostname : "<none>"), version,
@@ -262,6 +266,7 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap,
 		goto out;
 
 	hlist_add_head(&host->h_hash, chain);
+	ln->nrhosts++;
 	nrhosts++;
 
 	dprintk("lockd: %s created host %s (%s)\n", __func__,
@@ -326,7 +331,7 @@ struct nlm_host *nlmsvc_lookup_host(const struct svc_rqst *rqstp,
 	struct nsm_handle *nsm = NULL;
 	struct sockaddr *src_sap = svc_daddr(rqstp);
 	size_t src_len = rqstp->rq_daddrlen;
-	struct net *net = rqstp->rq_xprt->xpt_net;
+	struct net *net = SVC_NET(rqstp);
 	struct nlm_lookup_host_info ni = {
 		.server		= 1,
 		.sap		= svc_addr(rqstp),
@@ -337,6 +342,7 @@ struct nlm_host *nlmsvc_lookup_host(const struct svc_rqst *rqstp,
 		.hostname_len	= hostname_len,
 		.net		= net,
 	};
+	struct lockd_net *ln = net_generic(net, lockd_net_id);
 
 	dprintk("lockd: %s(host='%*s', vers=%u, proto=%s)\n", __func__,
 			(int)hostname_len, hostname, rqstp->rq_vers,
@@ -344,8 +350,8 @@ struct nlm_host *nlmsvc_lookup_host(const struct svc_rqst *rqstp,
 
 	mutex_lock(&nlm_host_mutex);
 
-	if (time_after_eq(jiffies, next_gc))
-		nlm_gc_hosts();
+	if (time_after_eq(jiffies, ln->next_gc))
+		nlm_gc_hosts(net);
 
 	chain = &nlm_server_hosts[nlm_hash_address(ni.sap)];
 	hlist_for_each_entry(host, pos, chain, h_hash) {
@@ -382,6 +388,7 @@ struct nlm_host *nlmsvc_lookup_host(const struct svc_rqst *rqstp,
 	memcpy(nlm_srcaddr(host), src_sap, src_len);
 	host->h_srcaddrlen = src_len;
 	hlist_add_head(&host->h_hash, chain);
+	ln->nrhosts++;
 	nrhosts++;
 
 	dprintk("lockd: %s created host %s (%s)\n",
@@ -565,6 +572,35 @@ void nlm_host_rebooted(const struct nlm_reboot *info)
 	nsm_release(nsm);
 }
 
+static void nlm_complain_hosts(struct net *net)
+{
+	struct hlist_head *chain;
+	struct hlist_node *pos;
+	struct nlm_host	*host;
+
+	if (net) {
+		struct lockd_net *ln = net_generic(net, lockd_net_id);
+
+		if (ln->nrhosts == 0)
+			return;
+		printk(KERN_WARNING "lockd: couldn't shutdown host module for net %p!\n", net);
+		dprintk("lockd: %lu hosts left in net %p:\n", ln->nrhosts, net);
+	} else {
+		if (nrhosts == 0)
+			return;
+		printk(KERN_WARNING "lockd: couldn't shutdown host module!\n");
+		dprintk("lockd: %lu hosts left:\n", nrhosts);
+	}
+
+	for_each_host(host, pos, chain, nlm_server_hosts) {
+		if (net && host->net != net)
+			continue;
+		dprintk("       %s (cnt %d use %d exp %ld net %p)\n",
+			host->h_name, atomic_read(&host->h_count),
+			host->h_inuse, host->h_expires, host->net);
+	}
+}
+
 void
 nlm_shutdown_hosts_net(struct net *net)
 {
@@ -572,11 +608,10 @@ nlm_shutdown_hosts_net(struct net *net)
 	struct hlist_node *pos;
 	struct nlm_host	*host;
 
-	dprintk("lockd: shutting down host module\n");
 	mutex_lock(&nlm_host_mutex);
 
 	/* First, make all hosts eligible for gc */
-	dprintk("lockd: nuking all hosts...\n");
+	dprintk("lockd: nuking all hosts in net %p...\n", net);
 	for_each_host(host, pos, chain, nlm_server_hosts) {
 		if (net && host->net != net)
 			continue;
@@ -588,8 +623,10 @@ nlm_shutdown_hosts_net(struct net *net)
 	}
 
 	/* Then, perform a garbage collection pass */
-	nlm_gc_hosts();
+	nlm_gc_hosts(net);
 	mutex_unlock(&nlm_host_mutex);
+
+	nlm_complain_hosts(net);
 }
 
 /*
@@ -599,22 +636,8 @@ nlm_shutdown_hosts_net(struct net *net)
 void
 nlm_shutdown_hosts(void)
 {
-	struct hlist_head *chain;
-	struct hlist_node *pos;
-	struct nlm_host	*host;
-
+	dprintk("lockd: shutting down host module\n");
 	nlm_shutdown_hosts_net(NULL);
-
-	/* complain if any hosts are left */
-	if (nrhosts != 0) {
-		printk(KERN_WARNING "lockd: couldn't shutdown host module!\n");
-		dprintk("lockd: %lu hosts left:\n", nrhosts);
-		for_each_host(host, pos, chain, nlm_server_hosts) {
-			dprintk("       %s (cnt %d use %d exp %ld net %p)\n",
-				host->h_name, atomic_read(&host->h_count),
-				host->h_inuse, host->h_expires, host->net);
-		}
-	}
 }
 
 /*
@@ -623,30 +646,39 @@ nlm_shutdown_hosts(void)
  * mark & sweep for resources held by remote clients.
  */
 static void
-nlm_gc_hosts(void)
+nlm_gc_hosts(struct net *net)
 {
 	struct hlist_head *chain;
 	struct hlist_node *pos, *next;
 	struct nlm_host	*host;
 
-	dprintk("lockd: host garbage collection\n");
-	for_each_host(host, pos, chain, nlm_server_hosts)
+	dprintk("lockd: host garbage collection for net %p\n", net);
+	for_each_host(host, pos, chain, nlm_server_hosts) {
+		if (net && host->net != net)
+			continue;
 		host->h_inuse = 0;
+	}
 
 	/* Mark all hosts that hold locks, blocks or shares */
-	nlmsvc_mark_resources();
+	nlmsvc_mark_resources(net);
 
 	for_each_host_safe(host, pos, next, chain, nlm_server_hosts) {
+		if (net && host->net != net)
+			continue;
 		if (atomic_read(&host->h_count) || host->h_inuse
 		 || time_before(jiffies, host->h_expires)) {
 			dprintk("nlm_gc_hosts skipping %s "
-				"(cnt %d use %d exp %ld)\n",
+				"(cnt %d use %d exp %ld net %p)\n",
 				host->h_name, atomic_read(&host->h_count),
-				host->h_inuse, host->h_expires);
+				host->h_inuse, host->h_expires, host->net);
 			continue;
 		}
 		nlm_destroy_host_locked(host);
 	}
 
-	next_gc = jiffies + NLM_HOST_COLLECT;
+	if (net) {
+		struct lockd_net *ln = net_generic(net, lockd_net_id);
+
+		ln->next_gc = jiffies + NLM_HOST_COLLECT;
+	}
 }
diff --git a/fs/lockd/netns.h b/fs/lockd/netns.h
index ce227e0fbc5c..4eee248ba96e 100644
--- a/fs/lockd/netns.h
+++ b/fs/lockd/netns.h
@@ -1,10 +1,17 @@
 #ifndef __LOCKD_NETNS_H__
 #define __LOCKD_NETNS_H__
 
+#include <linux/fs.h>
 #include <net/netns/generic.h>
 
 struct lockd_net {
 	unsigned int nlmsvc_users;
+	unsigned long next_gc;
+	unsigned long nrhosts;
+
+	struct delayed_work grace_period_end;
+	struct lock_manager lockd_manager;
+	struct list_head grace_list;
 };
 
 extern int lockd_net_id;
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 80938fda67e0..31a63f87b806 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -87,32 +87,36 @@ static unsigned long get_lockd_grace_period(void)
 		return nlm_timeout * 5 * HZ;
 }
 
-static struct lock_manager lockd_manager = {
-};
-
-static void grace_ender(struct work_struct *not_used)
+static void grace_ender(struct work_struct *grace)
 {
-	locks_end_grace(&lockd_manager);
-}
+	struct delayed_work *dwork = container_of(grace, struct delayed_work,
+						  work);
+	struct lockd_net *ln = container_of(dwork, struct lockd_net,
+					    grace_period_end);
 
-static DECLARE_DELAYED_WORK(grace_period_end, grace_ender);
+	locks_end_grace(&ln->lockd_manager);
+}
 
-static void set_grace_period(void)
+static void set_grace_period(struct net *net)
 {
 	unsigned long grace_period = get_lockd_grace_period();
+	struct lockd_net *ln = net_generic(net, lockd_net_id);
 
-	locks_start_grace(&lockd_manager);
-	cancel_delayed_work_sync(&grace_period_end);
-	schedule_delayed_work(&grace_period_end, grace_period);
+	locks_start_grace(net, &ln->lockd_manager);
+	cancel_delayed_work_sync(&ln->grace_period_end);
+	schedule_delayed_work(&ln->grace_period_end, grace_period);
 }
 
 static void restart_grace(void)
 {
 	if (nlmsvc_ops) {
-		cancel_delayed_work_sync(&grace_period_end);
-		locks_end_grace(&lockd_manager);
+		struct net *net = &init_net;
+		struct lockd_net *ln = net_generic(net, lockd_net_id);
+
+		cancel_delayed_work_sync(&ln->grace_period_end);
+		locks_end_grace(&ln->lockd_manager);
 		nlmsvc_invalidate_all();
-		set_grace_period();
+		set_grace_period(net);
 	}
 }
 
@@ -137,8 +141,6 @@ lockd(void *vrqstp)
 		nlm_timeout = LOCKD_DFLT_TIMEO;
 	nlmsvc_timeout = nlm_timeout * HZ;
 
-	set_grace_period();
-
 	/*
 	 * The main request loop. We don't terminate until the last
 	 * NFS mount or NFS daemon has gone away.
@@ -184,8 +186,6 @@ lockd(void *vrqstp)
 		svc_process(rqstp);
 	}
 	flush_signals(current);
-	cancel_delayed_work_sync(&grace_period_end);
-	locks_end_grace(&lockd_manager);
 	if (nlmsvc_ops)
 		nlmsvc_invalidate_all();
 	nlm_shutdown_hosts();
@@ -266,6 +266,7 @@ static int lockd_up_net(struct svc_serv *serv, struct net *net)
 	error = make_socks(serv, net);
 	if (error < 0)
 		goto err_socks;
+	set_grace_period(net);
 	dprintk("lockd_up_net: per-net data created; net=%p\n", net);
 	return 0;
 
@@ -283,6 +284,8 @@ static void lockd_down_net(struct svc_serv *serv, struct net *net)
 	if (ln->nlmsvc_users) {
 		if (--ln->nlmsvc_users == 0) {
 			nlm_shutdown_hosts_net(net);
+			cancel_delayed_work_sync(&ln->grace_period_end);
+			locks_end_grace(&ln->lockd_manager);
 			svc_shutdown_net(serv, net);
 			dprintk("lockd_down_net: per-net data destroyed; net=%p\n", net);
 		}
@@ -589,6 +592,10 @@ module_param(nlm_max_connections, uint, 0644);
 
 static int lockd_init_net(struct net *net)
 {
+	struct lockd_net *ln = net_generic(net, lockd_net_id);
+
+	INIT_DELAYED_WORK(&ln->grace_period_end, grace_ender);
+	INIT_LIST_HEAD(&ln->grace_list);
 	return 0;
 }
 
diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index 9a41fdc19511..b147d1ae71fd 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -11,6 +11,7 @@
 #include <linux/time.h>
 #include <linux/lockd/lockd.h>
 #include <linux/lockd/share.h>
+#include <linux/sunrpc/svc_xprt.h>
 
 #define NLMDBG_FACILITY		NLMDBG_CLIENT
 
@@ -151,7 +152,7 @@ nlm4svc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp,
 	resp->cookie = argp->cookie;
 
 	/* Don't accept requests during grace period */
-	if (locks_in_grace()) {
+	if (locks_in_grace(SVC_NET(rqstp))) {
 		resp->status = nlm_lck_denied_grace_period;
 		return rpc_success;
 	}
@@ -161,7 +162,7 @@ nlm4svc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp,
 		return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
 
 	/* Try to cancel request. */
-	resp->status = nlmsvc_cancel_blocked(file, &argp->lock);
+	resp->status = nlmsvc_cancel_blocked(SVC_NET(rqstp), file, &argp->lock);
 
 	dprintk("lockd: CANCEL        status %d\n", ntohl(resp->status));
 	nlmsvc_release_host(host);
@@ -184,7 +185,7 @@ nlm4svc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp,
 	resp->cookie = argp->cookie;
 
 	/* Don't accept new lock requests during grace period */
-	if (locks_in_grace()) {
+	if (locks_in_grace(SVC_NET(rqstp))) {
 		resp->status = nlm_lck_denied_grace_period;
 		return rpc_success;
 	}
@@ -194,7 +195,7 @@ nlm4svc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp,
 		return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
 
 	/* Now try to remove the lock */
-	resp->status = nlmsvc_unlock(file, &argp->lock);
+	resp->status = nlmsvc_unlock(SVC_NET(rqstp), file, &argp->lock);
 
 	dprintk("lockd: UNLOCK        status %d\n", ntohl(resp->status));
 	nlmsvc_release_host(host);
@@ -256,6 +257,7 @@ static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args
 		return rpc_system_err;
 
 	call = nlm_alloc_call(host);
+	nlmsvc_release_host(host);
 	if (call == NULL)
 		return rpc_system_err;
 
@@ -321,7 +323,7 @@ nlm4svc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp,
 	resp->cookie = argp->cookie;
 
 	/* Don't accept new lock requests during grace period */
-	if (locks_in_grace() && !argp->reclaim) {
+	if (locks_in_grace(SVC_NET(rqstp)) && !argp->reclaim) {
 		resp->status = nlm_lck_denied_grace_period;
 		return rpc_success;
 	}
@@ -354,7 +356,7 @@ nlm4svc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp,
 	resp->cookie = argp->cookie;
 
 	/* Don't accept requests during grace period */
-	if (locks_in_grace()) {
+	if (locks_in_grace(SVC_NET(rqstp))) {
 		resp->status = nlm_lck_denied_grace_period;
 		return rpc_success;
 	}
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index e46353f41a42..fb1a2bedbe97 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -26,7 +26,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/svc.h>
+#include <linux/sunrpc/svc_xprt.h>
 #include <linux/lockd/nlm.h>
 #include <linux/lockd/lockd.h>
 #include <linux/kthread.h>
@@ -219,7 +219,6 @@ nlmsvc_create_block(struct svc_rqst *rqstp, struct nlm_host *host,
 	struct nlm_block	*block;
 	struct nlm_rqst		*call = NULL;
 
-	nlm_get_host(host);
 	call = nlm_alloc_call(host);
 	if (call == NULL)
 		return NULL;
@@ -447,11 +446,11 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 		goto out;
 	}
 
-	if (locks_in_grace() && !reclaim) {
+	if (locks_in_grace(SVC_NET(rqstp)) && !reclaim) {
 		ret = nlm_lck_denied_grace_period;
 		goto out;
 	}
-	if (reclaim && !locks_in_grace()) {
+	if (reclaim && !locks_in_grace(SVC_NET(rqstp))) {
 		ret = nlm_lck_denied_grace_period;
 		goto out;
 	}
@@ -559,7 +558,7 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
 		goto out;
 	}
 
-	if (locks_in_grace()) {
+	if (locks_in_grace(SVC_NET(rqstp))) {
 		ret = nlm_lck_denied_grace_period;
 		goto out;
 	}
@@ -603,7 +602,7 @@ out:
  * must be removed.
  */
 __be32
-nlmsvc_unlock(struct nlm_file *file, struct nlm_lock *lock)
+nlmsvc_unlock(struct net *net, struct nlm_file *file, struct nlm_lock *lock)
 {
 	int	error;
 
@@ -615,7 +614,7 @@ nlmsvc_unlock(struct nlm_file *file, struct nlm_lock *lock)
 				(long long)lock->fl.fl_end);
 
 	/* First, cancel any lock that might be there */
-	nlmsvc_cancel_blocked(file, lock);
+	nlmsvc_cancel_blocked(net, file, lock);
 
 	lock->fl.fl_type = F_UNLCK;
 	error = vfs_lock_file(file->f_file, F_SETLK, &lock->fl, NULL);
@@ -631,7 +630,7 @@ nlmsvc_unlock(struct nlm_file *file, struct nlm_lock *lock)
  * The calling procedure must check whether the file can be closed.
  */
 __be32
-nlmsvc_cancel_blocked(struct nlm_file *file, struct nlm_lock *lock)
+nlmsvc_cancel_blocked(struct net *net, struct nlm_file *file, struct nlm_lock *lock)
 {
 	struct nlm_block	*block;
 	int status = 0;
@@ -643,7 +642,7 @@ nlmsvc_cancel_blocked(struct nlm_file *file, struct nlm_lock *lock)
 				(long long)lock->fl.fl_start,
 				(long long)lock->fl.fl_end);
 
-	if (locks_in_grace())
+	if (locks_in_grace(net))
 		return nlm_lck_denied_grace_period;
 
 	mutex_lock(&file->f_mutex);
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index d27aab11f324..3009a365e082 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -11,6 +11,7 @@
 #include <linux/time.h>
 #include <linux/lockd/lockd.h>
 #include <linux/lockd/share.h>
+#include <linux/sunrpc/svc_xprt.h>
 
 #define NLMDBG_FACILITY		NLMDBG_CLIENT
 
@@ -175,13 +176,14 @@ nlmsvc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp,
 {
 	struct nlm_host	*host;
 	struct nlm_file	*file;
+	struct net *net = SVC_NET(rqstp);
 
 	dprintk("lockd: CANCEL        called\n");
 
 	resp->cookie = argp->cookie;
 
 	/* Don't accept requests during grace period */
-	if (locks_in_grace()) {
+	if (locks_in_grace(net)) {
 		resp->status = nlm_lck_denied_grace_period;
 		return rpc_success;
 	}
@@ -191,7 +193,7 @@ nlmsvc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp,
 		return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
 
 	/* Try to cancel request. */
-	resp->status = cast_status(nlmsvc_cancel_blocked(file, &argp->lock));
+	resp->status = cast_status(nlmsvc_cancel_blocked(net, file, &argp->lock));
 
 	dprintk("lockd: CANCEL        status %d\n", ntohl(resp->status));
 	nlmsvc_release_host(host);
@@ -208,13 +210,14 @@ nlmsvc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp,
 {
 	struct nlm_host	*host;
 	struct nlm_file	*file;
+	struct net *net = SVC_NET(rqstp);
 
 	dprintk("lockd: UNLOCK        called\n");
 
 	resp->cookie = argp->cookie;
 
 	/* Don't accept new lock requests during grace period */
-	if (locks_in_grace()) {
+	if (locks_in_grace(net)) {
 		resp->status = nlm_lck_denied_grace_period;
 		return rpc_success;
 	}
@@ -224,7 +227,7 @@ nlmsvc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp,
 		return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
 
 	/* Now try to remove the lock */
-	resp->status = cast_status(nlmsvc_unlock(file, &argp->lock));
+	resp->status = cast_status(nlmsvc_unlock(net, file, &argp->lock));
 
 	dprintk("lockd: UNLOCK        status %d\n", ntohl(resp->status));
 	nlmsvc_release_host(host);
@@ -294,6 +297,7 @@ static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args
 		return rpc_system_err;
 
 	call = nlm_alloc_call(host);
+	nlmsvc_release_host(host);
 	if (call == NULL)
 		return rpc_system_err;
 
@@ -361,7 +365,7 @@ nlmsvc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp,
 	resp->cookie = argp->cookie;
 
 	/* Don't accept new lock requests during grace period */
-	if (locks_in_grace() && !argp->reclaim) {
+	if (locks_in_grace(SVC_NET(rqstp)) && !argp->reclaim) {
 		resp->status = nlm_lck_denied_grace_period;
 		return rpc_success;
 	}
@@ -394,7 +398,7 @@ nlmsvc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp,
 	resp->cookie = argp->cookie;
 
 	/* Don't accept requests during grace period */
-	if (locks_in_grace()) {
+	if (locks_in_grace(SVC_NET(rqstp))) {
 		resp->status = nlm_lck_denied_grace_period;
 		return rpc_success;
 	}
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index 2240d384d787..0deb5f6c9dd4 100644
--- a/fs/lockd/svcsubs.c
+++ b/fs/lockd/svcsubs.c
@@ -309,7 +309,8 @@ nlm_release_file(struct nlm_file *file)
  * Helpers function for resource traversal
  *
  * nlmsvc_mark_host:
- *	used by the garbage collector; simply sets h_inuse.
+ *	used by the garbage collector; simply sets h_inuse only for those
+ *	hosts, which passed network check.
  *	Always returns 0.
  *
  * nlmsvc_same_host:
@@ -320,12 +321,15 @@ nlm_release_file(struct nlm_file *file)
  *	returns 1 iff the host is a client.
  *	Used by nlmsvc_invalidate_all
  */
+
 static int
-nlmsvc_mark_host(void *data, struct nlm_host *dummy)
+nlmsvc_mark_host(void *data, struct nlm_host *hint)
 {
 	struct nlm_host *host = data;
 
-	host->h_inuse = 1;
+	if ((hint->net == NULL) ||
+	    (host->net == hint->net))
+		host->h_inuse = 1;
 	return 0;
 }
 
@@ -358,10 +362,13 @@ nlmsvc_is_client(void *data, struct nlm_host *dummy)
  * Mark all hosts that still hold resources
  */
 void
-nlmsvc_mark_resources(void)
+nlmsvc_mark_resources(struct net *net)
 {
-	dprintk("lockd: nlmsvc_mark_resources\n");
-	nlm_traverse_files(NULL, nlmsvc_mark_host, NULL);
+	struct nlm_host hint;
+
+	dprintk("lockd: nlmsvc_mark_resources for net %p\n", net);
+	hint.net = net;
+	nlm_traverse_files(&hint, nlmsvc_mark_host, NULL);
 }
 
 /*
diff --git a/fs/locks.c b/fs/locks.c
index 82c353304f9e..7e81bfc75164 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -200,11 +200,7 @@ void locks_release_private(struct file_lock *fl)
 			fl->fl_ops->fl_release_private(fl);
 		fl->fl_ops = NULL;
 	}
-	if (fl->fl_lmops) {
-		if (fl->fl_lmops->lm_release_private)
-			fl->fl_lmops->lm_release_private(fl);
-		fl->fl_lmops = NULL;
-	}
+	fl->fl_lmops = NULL;
 
 }
 EXPORT_SYMBOL_GPL(locks_release_private);
@@ -427,18 +423,8 @@ static void lease_break_callback(struct file_lock *fl)
 	kill_fasync(&fl->fl_fasync, SIGIO, POLL_MSG);
 }
 
-static void lease_release_private_callback(struct file_lock *fl)
-{
-	if (!fl->fl_file)
-		return;
-
-	f_delown(fl->fl_file);
-	fl->fl_file->f_owner.signum = 0;
-}
-
 static const struct lock_manager_operations lease_manager_ops = {
 	.lm_break = lease_break_callback,
-	.lm_release_private = lease_release_private_callback,
 	.lm_change = lease_modify,
 };
 
@@ -580,12 +566,6 @@ static void locks_delete_lock(struct file_lock **thisfl_p)
 	fl->fl_next = NULL;
 	list_del_init(&fl->fl_link);
 
-	fasync_helper(0, fl->fl_file, 0, &fl->fl_fasync);
-	if (fl->fl_fasync != NULL) {
-		printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync);
-		fl->fl_fasync = NULL;
-	}
-
 	if (fl->fl_nspid) {
 		put_pid(fl->fl_nspid);
 		fl->fl_nspid = NULL;
@@ -1155,8 +1135,18 @@ int lease_modify(struct file_lock **before, int arg)
 		return error;
 	lease_clear_pending(fl, arg);
 	locks_wake_up_blocks(fl);
-	if (arg == F_UNLCK)
+	if (arg == F_UNLCK) {
+		struct file *filp = fl->fl_file;
+
+		f_delown(filp);
+		filp->f_owner.signum = 0;
+		fasync_helper(0, fl->fl_file, 0, &fl->fl_fasync);
+		if (fl->fl_fasync != NULL) {
+			printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync);
+			fl->fl_fasync = NULL;
+		}
 		locks_delete_lock(before);
+	}
 	return 0;
 }
 
diff --git a/fs/minix/itree_v2.c b/fs/minix/itree_v2.c
index 13487ad16894..78e2d93e5c83 100644
--- a/fs/minix/itree_v2.c
+++ b/fs/minix/itree_v2.c
@@ -32,7 +32,8 @@ static int block_to_path(struct inode * inode, long block, int offsets[DEPTH])
 	if (block < 0) {
 		printk("MINIX-fs: block_to_path: block %ld < 0 on dev %s\n",
 			block, bdevname(sb->s_bdev, b));
-	} else if (block >= (minix_sb(inode->i_sb)->s_max_size/sb->s_blocksize)) {
+	} 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",
diff --git a/fs/namei.c b/fs/namei.c
index 2ccc35c4dc24..1b464390dde8 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -650,6 +650,121 @@ static inline void put_link(struct nameidata *nd, struct path *link, void *cooki
 	path_put(link);
 }
 
+int sysctl_protected_symlinks __read_mostly = 1;
+int sysctl_protected_hardlinks __read_mostly = 1;
+
+/**
+ * may_follow_link - Check symlink following for unsafe situations
+ * @link: The path of the symlink
+ *
+ * In the case of the sysctl_protected_symlinks sysctl being enabled,
+ * CAP_DAC_OVERRIDE needs to be specifically ignored if the symlink is
+ * in a sticky world-writable directory. This is to protect privileged
+ * processes from failing races against path names that may change out
+ * from under them by way of other users creating malicious symlinks.
+ * It will permit symlinks to be followed only when outside a sticky
+ * world-writable directory, or when the uid of the symlink and follower
+ * match, or when the directory owner matches the symlink's owner.
+ *
+ * Returns 0 if following the symlink is allowed, -ve on error.
+ */
+static inline int may_follow_link(struct path *link, struct nameidata *nd)
+{
+	const struct inode *inode;
+	const struct inode *parent;
+
+	if (!sysctl_protected_symlinks)
+		return 0;
+
+	/* Allowed if owner and follower match. */
+	inode = link->dentry->d_inode;
+	if (current_cred()->fsuid == inode->i_uid)
+		return 0;
+
+	/* Allowed if parent directory not sticky and world-writable. */
+	parent = nd->path.dentry->d_inode;
+	if ((parent->i_mode & (S_ISVTX|S_IWOTH)) != (S_ISVTX|S_IWOTH))
+		return 0;
+
+	/* Allowed if parent directory and link owner match. */
+	if (parent->i_uid == inode->i_uid)
+		return 0;
+
+	path_put_conditional(link, nd);
+	path_put(&nd->path);
+	audit_log_link_denied("follow_link", link);
+	return -EACCES;
+}
+
+/**
+ * safe_hardlink_source - Check for safe hardlink conditions
+ * @inode: the source inode to hardlink from
+ *
+ * Return false if at least one of the following conditions:
+ *    - inode is not a regular file
+ *    - inode is setuid
+ *    - inode is setgid and group-exec
+ *    - access failure for read and write
+ *
+ * Otherwise returns true.
+ */
+static bool safe_hardlink_source(struct inode *inode)
+{
+	umode_t mode = inode->i_mode;
+
+	/* Special files should not get pinned to the filesystem. */
+	if (!S_ISREG(mode))
+		return false;
+
+	/* Setuid files should not get pinned to the filesystem. */
+	if (mode & S_ISUID)
+		return false;
+
+	/* Executable setgid files should not get pinned to the filesystem. */
+	if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP))
+		return false;
+
+	/* Hardlinking to unreadable or unwritable sources is dangerous. */
+	if (inode_permission(inode, MAY_READ | MAY_WRITE))
+		return false;
+
+	return true;
+}
+
+/**
+ * may_linkat - Check permissions for creating a hardlink
+ * @link: the source to hardlink from
+ *
+ * Block hardlink when all of:
+ *  - sysctl_protected_hardlinks enabled
+ *  - fsuid does not match inode
+ *  - hardlink source is unsafe (see safe_hardlink_source() above)
+ *  - not CAP_FOWNER
+ *
+ * Returns 0 if successful, -ve on error.
+ */
+static int may_linkat(struct path *link)
+{
+	const struct cred *cred;
+	struct inode *inode;
+
+	if (!sysctl_protected_hardlinks)
+		return 0;
+
+	cred = current_cred();
+	inode = link->dentry->d_inode;
+
+	/* Source inode owner (or CAP_FOWNER) can hardlink all they like,
+	 * otherwise, it must be a safe source.
+	 */
+	if (cred->fsuid == inode->i_uid || safe_hardlink_source(inode) ||
+	    capable(CAP_FOWNER))
+		return 0;
+
+	audit_log_link_denied("linkat", link);
+	return -EPERM;
+}
+
 static __always_inline int
 follow_link(struct path *link, struct nameidata *nd, void **p)
 {
@@ -1818,6 +1933,9 @@ static int path_lookupat(int dfd, const char *name,
 		while (err > 0) {
 			void *cookie;
 			struct path link = path;
+			err = may_follow_link(&link, nd);
+			if (unlikely(err))
+				break;
 			nd->flags |= LOOKUP_PARENT;
 			err = follow_link(&link, nd, &cookie);
 			if (err)
@@ -2277,7 +2395,7 @@ static int may_o_create(struct path *dir, struct dentry *dentry, umode_t mode)
 static int atomic_open(struct nameidata *nd, struct dentry *dentry,
 			struct path *path, struct file *file,
 			const struct open_flags *op,
-			bool *want_write, bool need_lookup,
+			bool got_write, bool need_lookup,
 			int *opened)
 {
 	struct inode *dir =  nd->path.dentry->d_inode;
@@ -2300,7 +2418,7 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry,
 	if ((open_flag & O_CREAT) && !IS_POSIXACL(dir))
 		mode &= ~current_umask();
 
-	if (open_flag & O_EXCL) {
+	if ((open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT)) {
 		open_flag &= ~O_TRUNC;
 		*opened |= FILE_CREATED;
 	}
@@ -2314,12 +2432,9 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry,
 	 * Another problem is returing the "right" error value (e.g. for an
 	 * O_EXCL open we want to return EEXIST not EROFS).
 	 */
-	if ((open_flag & (O_CREAT | O_TRUNC)) ||
-	    (open_flag & O_ACCMODE) != O_RDONLY) {
-		error = mnt_want_write(nd->path.mnt);
-		if (!error) {
-			*want_write = true;
-		} else if (!(open_flag & O_CREAT)) {
+	if (((open_flag & (O_CREAT | O_TRUNC)) ||
+	    (open_flag & O_ACCMODE) != O_RDONLY) && unlikely(!got_write)) {
+		if (!(open_flag & O_CREAT)) {
 			/*
 			 * No O_CREATE -> atomicity not a requirement -> fall
 			 * back to lookup + open
@@ -2327,11 +2442,11 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry,
 			goto no_open;
 		} else if (open_flag & (O_EXCL | O_TRUNC)) {
 			/* Fall back and fail with the right error */
-			create_error = error;
+			create_error = -EROFS;
 			goto no_open;
 		} else {
 			/* No side effects, safe to clear O_CREAT */
-			create_error = error;
+			create_error = -EROFS;
 			open_flag &= ~O_CREAT;
 		}
 	}
@@ -2438,7 +2553,7 @@ looked_up:
 static int lookup_open(struct nameidata *nd, struct path *path,
 			struct file *file,
 			const struct open_flags *op,
-			bool *want_write, int *opened)
+			bool got_write, int *opened)
 {
 	struct dentry *dir = nd->path.dentry;
 	struct inode *dir_inode = dir->d_inode;
@@ -2456,7 +2571,7 @@ static int lookup_open(struct nameidata *nd, struct path *path,
 		goto out_no_open;
 
 	if ((nd->flags & LOOKUP_OPEN) && dir_inode->i_op->atomic_open) {
-		return atomic_open(nd, dentry, path, file, op, want_write,
+		return atomic_open(nd, dentry, path, file, op, got_write,
 				   need_lookup, opened);
 	}
 
@@ -2480,10 +2595,10 @@ static int lookup_open(struct nameidata *nd, struct path *path,
 		 * a permanent write count is taken through
 		 * the 'struct file' in finish_open().
 		 */
-		error = mnt_want_write(nd->path.mnt);
-		if (error)
+		if (!got_write) {
+			error = -EROFS;
 			goto out_dput;
-		*want_write = true;
+		}
 		*opened |= FILE_CREATED;
 		error = security_path_mknod(&nd->path, dentry, mode, 0);
 		if (error)
@@ -2513,7 +2628,7 @@ static int do_last(struct nameidata *nd, struct path *path,
 	struct dentry *dir = nd->path.dentry;
 	int open_flag = op->open_flag;
 	bool will_truncate = (open_flag & O_TRUNC) != 0;
-	bool want_write = false;
+	bool got_write = false;
 	int acc_mode = op->acc_mode;
 	struct inode *inode;
 	bool symlink_ok = false;
@@ -2582,8 +2697,18 @@ static int do_last(struct nameidata *nd, struct path *path,
 	}
 
 retry_lookup:
+	if (op->open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) {
+		error = mnt_want_write(nd->path.mnt);
+		if (!error)
+			got_write = true;
+		/*
+		 * do _not_ fail yet - we might not need that or fail with
+		 * a different error; let lookup_open() decide; we'll be
+		 * dropping this one anyway.
+		 */
+	}
 	mutex_lock(&dir->d_inode->i_mutex);
-	error = lookup_open(nd, path, file, op, &want_write, opened);
+	error = lookup_open(nd, path, file, op, got_write, opened);
 	mutex_unlock(&dir->d_inode->i_mutex);
 
 	if (error <= 0) {
@@ -2608,22 +2733,23 @@ retry_lookup:
 	}
 
 	/*
-	 * It already exists.
+	 * create/update audit record if it already exists.
 	 */
-	audit_inode(pathname, path->dentry);
+	if (path->dentry->d_inode)
+		audit_inode(pathname, path->dentry);
 
 	/*
 	 * If atomic_open() acquired write access it is dropped now due to
 	 * possible mount and symlink following (this might be optimized away if
 	 * necessary...)
 	 */
-	if (want_write) {
+	if (got_write) {
 		mnt_drop_write(nd->path.mnt);
-		want_write = false;
+		got_write = false;
 	}
 
 	error = -EEXIST;
-	if (open_flag & O_EXCL)
+	if ((open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT))
 		goto exit_dput;
 
 	error = follow_managed(path, nd->flags);
@@ -2684,7 +2810,7 @@ finish_open:
 		error = mnt_want_write(nd->path.mnt);
 		if (error)
 			goto out;
-		want_write = true;
+		got_write = true;
 	}
 finish_open_created:
 	error = may_open(&nd->path, acc_mode, open_flag);
@@ -2711,7 +2837,7 @@ opened:
 			goto exit_fput;
 	}
 out:
-	if (want_write)
+	if (got_write)
 		mnt_drop_write(nd->path.mnt);
 	path_put(&save_parent);
 	terminate_walk(nd);
@@ -2735,9 +2861,9 @@ stale_open:
 	nd->inode = dir->d_inode;
 	save_parent.mnt = NULL;
 	save_parent.dentry = NULL;
-	if (want_write) {
+	if (got_write) {
 		mnt_drop_write(nd->path.mnt);
-		want_write = false;
+		got_write = false;
 	}
 	retried = true;
 	goto retry_lookup;
@@ -2777,6 +2903,9 @@ static struct file *path_openat(int dfd, const char *pathname,
 			error = -ELOOP;
 			break;
 		}
+		error = may_follow_link(&link, nd);
+		if (unlikely(error))
+			break;
 		nd->flags |= LOOKUP_PARENT;
 		nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
 		error = follow_link(&link, nd, &cookie);
@@ -2846,6 +2975,7 @@ struct dentry *kern_path_create(int dfd, const char *pathname, struct path *path
 {
 	struct dentry *dentry = ERR_PTR(-EEXIST);
 	struct nameidata nd;
+	int err2;
 	int error = do_path_lookup(dfd, pathname, LOOKUP_PARENT, &nd);
 	if (error)
 		return ERR_PTR(error);
@@ -2859,16 +2989,19 @@ struct dentry *kern_path_create(int dfd, const char *pathname, struct path *path
 	nd.flags &= ~LOOKUP_PARENT;
 	nd.flags |= LOOKUP_CREATE | LOOKUP_EXCL;
 
+	/* don't fail immediately if it's r/o, at least try to report other errors */
+	err2 = mnt_want_write(nd.path.mnt);
 	/*
 	 * Do the final lookup.
 	 */
 	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
 	dentry = lookup_hash(&nd);
 	if (IS_ERR(dentry))
-		goto fail;
+		goto unlock;
 
+	error = -EEXIST;
 	if (dentry->d_inode)
-		goto eexist;
+		goto fail;
 	/*
 	 * Special case - lookup gave negative, but... we had foo/bar/
 	 * From the vfs_mknod() POV we just have a negative dentry -
@@ -2876,23 +3009,37 @@ struct dentry *kern_path_create(int dfd, const char *pathname, struct path *path
 	 * been asking for (non-existent) directory. -ENOENT for you.
 	 */
 	if (unlikely(!is_dir && nd.last.name[nd.last.len])) {
-		dput(dentry);
-		dentry = ERR_PTR(-ENOENT);
+		error = -ENOENT;
+		goto fail;
+	}
+	if (unlikely(err2)) {
+		error = err2;
 		goto fail;
 	}
 	*path = nd.path;
 	return dentry;
-eexist:
-	dput(dentry);
-	dentry = ERR_PTR(-EEXIST);
 fail:
+	dput(dentry);
+	dentry = ERR_PTR(error);
+unlock:
 	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+	if (!err2)
+		mnt_drop_write(nd.path.mnt);
 out:
 	path_put(&nd.path);
 	return dentry;
 }
 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);
+	mnt_drop_write(path->mnt);
+	path_put(path);
+}
+EXPORT_SYMBOL(done_path_create);
+
 struct dentry *user_path_create(int dfd, const char __user *pathname, struct path *path, int is_dir)
 {
 	char *tmp = getname(pathname);
@@ -2956,8 +3103,9 @@ SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode,
 	struct path path;
 	int error;
 
-	if (S_ISDIR(mode))
-		return -EPERM;
+	error = may_mknod(mode);
+	if (error)
+		return error;
 
 	dentry = user_path_create(dfd, filename, &path, 0);
 	if (IS_ERR(dentry))
@@ -2965,15 +3113,9 @@ SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode,
 
 	if (!IS_POSIXACL(path.dentry->d_inode))
 		mode &= ~current_umask();
-	error = may_mknod(mode);
-	if (error)
-		goto out_dput;
-	error = mnt_want_write(path.mnt);
-	if (error)
-		goto out_dput;
 	error = security_path_mknod(&path, dentry, mode, dev);
 	if (error)
-		goto out_drop_write;
+		goto out;
 	switch (mode & S_IFMT) {
 		case 0: case S_IFREG:
 			error = vfs_create(path.dentry->d_inode,dentry,mode,true);
@@ -2986,13 +3128,8 @@ SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode,
 			error = vfs_mknod(path.dentry->d_inode,dentry,mode,0);
 			break;
 	}
-out_drop_write:
-	mnt_drop_write(path.mnt);
-out_dput:
-	dput(dentry);
-	mutex_unlock(&path.dentry->d_inode->i_mutex);
-	path_put(&path);
-
+out:
+	done_path_create(&path, dentry);
 	return error;
 }
 
@@ -3038,19 +3175,10 @@ SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode)
 
 	if (!IS_POSIXACL(path.dentry->d_inode))
 		mode &= ~current_umask();
-	error = mnt_want_write(path.mnt);
-	if (error)
-		goto out_dput;
 	error = security_path_mkdir(&path, dentry, mode);
-	if (error)
-		goto out_drop_write;
-	error = vfs_mkdir(path.dentry->d_inode, dentry, mode);
-out_drop_write:
-	mnt_drop_write(path.mnt);
-out_dput:
-	dput(dentry);
-	mutex_unlock(&path.dentry->d_inode->i_mutex);
-	path_put(&path);
+	if (!error)
+		error = vfs_mkdir(path.dentry->d_inode, dentry, mode);
+	done_path_create(&path, dentry);
 	return error;
 }
 
@@ -3144,6 +3272,9 @@ static long do_rmdir(int dfd, const char __user *pathname)
 	}
 
 	nd.flags &= ~LOOKUP_PARENT;
+	error = mnt_want_write(nd.path.mnt);
+	if (error)
+		goto exit1;
 
 	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
 	dentry = lookup_hash(&nd);
@@ -3154,19 +3285,15 @@ static long do_rmdir(int dfd, const char __user *pathname)
 		error = -ENOENT;
 		goto exit3;
 	}
-	error = mnt_want_write(nd.path.mnt);
-	if (error)
-		goto exit3;
 	error = security_path_rmdir(&nd.path, dentry);
 	if (error)
-		goto exit4;
+		goto exit3;
 	error = vfs_rmdir(nd.path.dentry->d_inode, dentry);
-exit4:
-	mnt_drop_write(nd.path.mnt);
 exit3:
 	dput(dentry);
 exit2:
 	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+	mnt_drop_write(nd.path.mnt);
 exit1:
 	path_put(&nd.path);
 	putname(name);
@@ -3233,6 +3360,9 @@ static long do_unlinkat(int dfd, const char __user *pathname)
 		goto exit1;
 
 	nd.flags &= ~LOOKUP_PARENT;
+	error = mnt_want_write(nd.path.mnt);
+	if (error)
+		goto exit1;
 
 	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
 	dentry = lookup_hash(&nd);
@@ -3245,21 +3375,17 @@ static long do_unlinkat(int dfd, const char __user *pathname)
 		if (!inode)
 			goto slashes;
 		ihold(inode);
-		error = mnt_want_write(nd.path.mnt);
-		if (error)
-			goto exit2;
 		error = security_path_unlink(&nd.path, dentry);
 		if (error)
-			goto exit3;
+			goto exit2;
 		error = vfs_unlink(nd.path.dentry->d_inode, dentry);
-exit3:
-		mnt_drop_write(nd.path.mnt);
-	exit2:
+exit2:
 		dput(dentry);
 	}
 	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
 	if (inode)
 		iput(inode);	/* truncate the inode here */
+	mnt_drop_write(nd.path.mnt);
 exit1:
 	path_put(&nd.path);
 	putname(name);
@@ -3324,19 +3450,10 @@ SYSCALL_DEFINE3(symlinkat, const char __user *, oldname,
 	if (IS_ERR(dentry))
 		goto out_putname;
 
-	error = mnt_want_write(path.mnt);
-	if (error)
-		goto out_dput;
 	error = security_path_symlink(&path, dentry, from);
-	if (error)
-		goto out_drop_write;
-	error = vfs_symlink(path.dentry->d_inode, dentry, from);
-out_drop_write:
-	mnt_drop_write(path.mnt);
-out_dput:
-	dput(dentry);
-	mutex_unlock(&path.dentry->d_inode->i_mutex);
-	path_put(&path);
+	if (!error)
+		error = vfs_symlink(path.dentry->d_inode, dentry, from);
+	done_path_create(&path, dentry);
 out_putname:
 	putname(from);
 	return error;
@@ -3436,19 +3553,15 @@ SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname,
 	error = -EXDEV;
 	if (old_path.mnt != new_path.mnt)
 		goto out_dput;
-	error = mnt_want_write(new_path.mnt);
-	if (error)
+	error = may_linkat(&old_path);
+	if (unlikely(error))
 		goto out_dput;
 	error = security_path_link(old_path.dentry, &new_path, new_dentry);
 	if (error)
-		goto out_drop_write;
+		goto out_dput;
 	error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry);
-out_drop_write:
-	mnt_drop_write(new_path.mnt);
 out_dput:
-	dput(new_dentry);
-	mutex_unlock(&new_path.dentry->d_inode->i_mutex);
-	path_put(&new_path);
+	done_path_create(&new_path, new_dentry);
 out:
 	path_put(&old_path);
 
@@ -3644,6 +3757,10 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
 	if (newnd.last_type != LAST_NORM)
 		goto exit2;
 
+	error = mnt_want_write(oldnd.path.mnt);
+	if (error)
+		goto exit2;
+
 	oldnd.flags &= ~LOOKUP_PARENT;
 	newnd.flags &= ~LOOKUP_PARENT;
 	newnd.flags |= LOOKUP_RENAME_TARGET;
@@ -3679,23 +3796,19 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
 	if (new_dentry == trap)
 		goto exit5;
 
-	error = mnt_want_write(oldnd.path.mnt);
-	if (error)
-		goto exit5;
 	error = security_path_rename(&oldnd.path, old_dentry,
 				     &newnd.path, new_dentry);
 	if (error)
-		goto exit6;
+		goto exit5;
 	error = vfs_rename(old_dir->d_inode, old_dentry,
 				   new_dir->d_inode, new_dentry);
-exit6:
-	mnt_drop_write(oldnd.path.mnt);
 exit5:
 	dput(new_dentry);
 exit4:
 	dput(old_dentry);
 exit3:
 	unlock_rename(new_dir, old_dir);
+	mnt_drop_write(oldnd.path.mnt);
 exit2:
 	path_put(&newnd.path);
 	putname(to);
diff --git a/fs/namespace.c b/fs/namespace.c
index c53d3381b0d0..4d31f73e2561 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -283,24 +283,22 @@ static int mnt_is_readonly(struct vfsmount *mnt)
 }
 
 /*
- * Most r/o checks on a fs are for operations that take
- * discrete amounts of time, like a write() or unlink().
- * We must keep track of when those operations start
- * (for permission checks) and when they end, so that
- * we can determine when writes are able to occur to
- * a filesystem.
+ * Most r/o & frozen checks on a fs are for operations that take discrete
+ * amounts of time, like a write() or unlink().  We must keep track of when
+ * those operations start (for permission checks) and when they end, so that we
+ * can determine when writes are able to occur to a filesystem.
  */
 /**
- * mnt_want_write - get write access to a mount
+ * __mnt_want_write - get write access to a mount without freeze protection
  * @m: the mount on which to take a write
  *
- * This tells the low-level filesystem that a write is
- * about to be performed to it, and makes sure that
- * writes are allowed before returning success.  When
- * the write operation is finished, mnt_drop_write()
- * must be called.  This is effectively a refcount.
+ * This tells the low-level filesystem that a write is about to be performed to
+ * it, and makes sure that writes are allowed (mnt it read-write) before
+ * returning success. This operation does not protect against filesystem being
+ * frozen. When the write operation is finished, __mnt_drop_write() must be
+ * called. This is effectively a refcount.
  */
-int mnt_want_write(struct vfsmount *m)
+int __mnt_want_write(struct vfsmount *m)
 {
 	struct mount *mnt = real_mount(m);
 	int ret = 0;
@@ -326,6 +324,27 @@ int mnt_want_write(struct vfsmount *m)
 		ret = -EROFS;
 	}
 	preempt_enable();
+
+	return ret;
+}
+
+/**
+ * mnt_want_write - get write access to a mount
+ * @m: the mount on which to take a write
+ *
+ * This tells the low-level filesystem that a write is about to be performed to
+ * it, and makes sure that writes are allowed (mount is read-write, filesystem
+ * is not frozen) before returning success.  When the write operation is
+ * finished, mnt_drop_write() must be called.  This is effectively a refcount.
+ */
+int mnt_want_write(struct vfsmount *m)
+{
+	int ret;
+
+	sb_start_write(m->mnt_sb);
+	ret = __mnt_want_write(m);
+	if (ret)
+		sb_end_write(m->mnt_sb);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(mnt_want_write);
@@ -355,38 +374,76 @@ int mnt_clone_write(struct vfsmount *mnt)
 EXPORT_SYMBOL_GPL(mnt_clone_write);
 
 /**
- * mnt_want_write_file - get write access to a file's mount
+ * __mnt_want_write_file - get write access to a file's mount
  * @file: the file who's mount on which to take a write
  *
- * This is like mnt_want_write, but it takes a file and can
+ * This is like __mnt_want_write, but it takes a file and can
  * do some optimisations if the file is open for write already
  */
-int mnt_want_write_file(struct file *file)
+int __mnt_want_write_file(struct file *file)
 {
 	struct inode *inode = file->f_dentry->d_inode;
+
 	if (!(file->f_mode & FMODE_WRITE) || special_file(inode->i_mode))
-		return mnt_want_write(file->f_path.mnt);
+		return __mnt_want_write(file->f_path.mnt);
 	else
 		return mnt_clone_write(file->f_path.mnt);
 }
+
+/**
+ * mnt_want_write_file - get write access to a file's mount
+ * @file: the file who's mount on which to take a write
+ *
+ * This is like mnt_want_write, but it takes a file and can
+ * do some optimisations if the file is open for write already
+ */
+int mnt_want_write_file(struct file *file)
+{
+	int ret;
+
+	sb_start_write(file->f_path.mnt->mnt_sb);
+	ret = __mnt_want_write_file(file);
+	if (ret)
+		sb_end_write(file->f_path.mnt->mnt_sb);
+	return ret;
+}
 EXPORT_SYMBOL_GPL(mnt_want_write_file);
 
 /**
- * mnt_drop_write - give up write access to a mount
+ * __mnt_drop_write - give up write access to a mount
  * @mnt: the mount on which to give up write access
  *
  * Tells the low-level filesystem that we are done
  * performing writes to it.  Must be matched with
- * mnt_want_write() call above.
+ * __mnt_want_write() call above.
  */
-void mnt_drop_write(struct vfsmount *mnt)
+void __mnt_drop_write(struct vfsmount *mnt)
 {
 	preempt_disable();
 	mnt_dec_writers(real_mount(mnt));
 	preempt_enable();
 }
+
+/**
+ * mnt_drop_write - give up write access to a mount
+ * @mnt: the mount on which to give up write access
+ *
+ * Tells the low-level filesystem that we are done performing writes to it and
+ * also allows filesystem to be frozen again.  Must be matched with
+ * mnt_want_write() call above.
+ */
+void mnt_drop_write(struct vfsmount *mnt)
+{
+	__mnt_drop_write(mnt);
+	sb_end_write(mnt->mnt_sb);
+}
 EXPORT_SYMBOL_GPL(mnt_drop_write);
 
+void __mnt_drop_write_file(struct file *file)
+{
+	__mnt_drop_write(file->f_path.mnt);
+}
+
 void mnt_drop_write_file(struct file *file)
 {
 	mnt_drop_write(file->f_path.mnt);
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index f90f4f5cd421..db7ad719628a 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -30,7 +30,7 @@ config NFS_FS
 	  If unsure, say N.
 
 config NFS_V2
-	bool "NFS client support for NFS version 2"
+	tristate "NFS client support for NFS version 2"
 	depends on NFS_FS
 	default y
 	help
@@ -40,7 +40,7 @@ config NFS_V2
 	  If unsure, say Y.
 
 config NFS_V3
-	bool "NFS client support for NFS version 3"
+	tristate "NFS client support for NFS version 3"
 	depends on NFS_FS
 	default y
 	help
@@ -72,7 +72,7 @@ config NFS_V3_ACL
 	  If unsure, say N.
 
 config NFS_V4
-	bool "NFS client support for NFS version 4"
+	tristate "NFS client support for NFS version 4"
 	depends on NFS_FS
 	select SUNRPC_GSS
 	select KEYS
@@ -86,11 +86,18 @@ config NFS_V4
 
 	  If unsure, say Y.
 
+config NFS_SWAP
+	bool "Provide swap over NFS support"
+	default n
+	depends on NFS_FS
+	select SUNRPC_SWAP
+	help
+	  This option enables swapon to work on files located on NFS mounts.
+
 config NFS_V4_1
 	bool "NFS client support for NFSv4.1 (EXPERIMENTAL)"
-	depends on NFS_FS && NFS_V4 && EXPERIMENTAL
+	depends on NFS_V4 && EXPERIMENTAL
 	select SUNRPC_BACKCHANNEL
-	select PNFS_FILE_LAYOUT
 	help
 	  This option enables support for minor version 1 of the NFSv4 protocol
 	  (RFC 5661) in the kernel's NFS client.
@@ -99,15 +106,17 @@ config NFS_V4_1
 
 config PNFS_FILE_LAYOUT
 	tristate
+	depends on NFS_V4_1
+	default m
 
 config PNFS_BLOCK
 	tristate
-	depends on NFS_FS && NFS_V4_1 && BLK_DEV_DM
+	depends on NFS_V4_1 && BLK_DEV_DM
 	default m
 
 config PNFS_OBJLAYOUT
 	tristate
-	depends on NFS_FS && NFS_V4_1 && SCSI_OSD_ULD
+	depends on NFS_V4_1 && SCSI_OSD_ULD
 	default m
 
 config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index 7ddd45d9f170..8bf3a3f6925a 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -9,17 +9,23 @@ nfs-y 			:= client.o dir.o file.o getroot.o inode.o super.o \
 			   write.o namespace.o mount_clnt.o \
 			   dns_resolve.o cache_lib.o
 nfs-$(CONFIG_ROOT_NFS)	+= nfsroot.o
-nfs-$(CONFIG_NFS_V2)	+= proc.o nfs2xdr.o
-nfs-$(CONFIG_NFS_V3)	+= nfs3proc.o nfs3xdr.o
-nfs-$(CONFIG_NFS_V3_ACL)	+= nfs3acl.o
-nfs-$(CONFIG_NFS_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o \
-			   delegation.o idmap.o \
-			   callback.o callback_xdr.o callback_proc.o \
-			   nfs4namespace.o
-nfs-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o
-nfs-$(CONFIG_SYSCTL) += sysctl.o
+nfs-$(CONFIG_SYSCTL)	+= sysctl.o
 nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o
 
+obj-$(CONFIG_NFS_V2) += nfs2.o
+nfs2-y := nfs2super.o proc.o nfs2xdr.o
+
+obj-$(CONFIG_NFS_V3) += nfs3.o
+nfs3-y := nfs3super.o nfs3client.o nfs3proc.o nfs3xdr.o
+nfs3-$(CONFIG_NFS_V3_ACL) += nfs3acl.o
+
+obj-$(CONFIG_NFS_V4) += nfs4.o
+nfs4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o \
+	  delegation.o idmap.o callback.o callback_xdr.o callback_proc.o \
+	  nfs4namespace.o nfs4getroot.o nfs4client.o
+nfs4-$(CONFIG_SYSCTL)	+= nfs4sysctl.o
+nfs4-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o
+
 obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o
 nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o
 
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 7ae8a608956f..dd392ed5f2e2 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -228,6 +228,14 @@ bl_end_par_io_read(void *data, int unused)
 	schedule_work(&rdata->task.u.tk_work);
 }
 
+static bool
+bl_check_alignment(u64 offset, u32 len, unsigned long blkmask)
+{
+	if ((offset & blkmask) || (len & blkmask))
+		return false;
+	return true;
+}
+
 static enum pnfs_try_status
 bl_read_pagelist(struct nfs_read_data *rdata)
 {
@@ -244,6 +252,9 @@ bl_read_pagelist(struct nfs_read_data *rdata)
 	dprintk("%s enter nr_pages %u offset %lld count %u\n", __func__,
 	       rdata->pages.npages, f_offset, (unsigned int)rdata->args.count);
 
+	if (!bl_check_alignment(f_offset, rdata->args.count, PAGE_CACHE_MASK))
+		goto use_mds;
+
 	par = alloc_parallel(rdata);
 	if (!par)
 		goto use_mds;
@@ -552,7 +563,7 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync)
 	struct bio *bio = NULL;
 	struct pnfs_block_extent *be = NULL, *cow_read = NULL;
 	sector_t isect, last_isect = 0, extent_length = 0;
-	struct parallel_io *par;
+	struct parallel_io *par = NULL;
 	loff_t offset = wdata->args.offset;
 	size_t count = wdata->args.count;
 	struct page **pages = wdata->args.pages;
@@ -563,6 +574,10 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync)
 	    NFS_SERVER(header->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT;
 
 	dprintk("%s enter, %Zu@%lld\n", __func__, count, offset);
+	/* Check for alignment first */
+	if (!bl_check_alignment(offset, count, PAGE_CACHE_MASK))
+		goto out_mds;
+
 	/* At this point, wdata->pages is a (sequential) list of nfs_pages.
 	 * We want to write each, and if there is an error set pnfs_error
 	 * to have it redone using nfs.
@@ -996,14 +1011,32 @@ bl_clear_layoutdriver(struct nfs_server *server)
 	return 0;
 }
 
+static void
+bl_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
+{
+	if (!bl_check_alignment(req->wb_offset, req->wb_bytes, PAGE_CACHE_MASK))
+		nfs_pageio_reset_read_mds(pgio);
+	else
+		pnfs_generic_pg_init_read(pgio, req);
+}
+
+static void
+bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
+{
+	if (!bl_check_alignment(req->wb_offset, req->wb_bytes, PAGE_CACHE_MASK))
+		nfs_pageio_reset_write_mds(pgio);
+	else
+		pnfs_generic_pg_init_write(pgio, req);
+}
+
 static const struct nfs_pageio_ops bl_pg_read_ops = {
-	.pg_init = pnfs_generic_pg_init_read,
+	.pg_init = bl_pg_init_read,
 	.pg_test = pnfs_generic_pg_test,
 	.pg_doio = pnfs_generic_pg_readpages,
 };
 
 static const struct nfs_pageio_ops bl_pg_write_ops = {
-	.pg_init = pnfs_generic_pg_init_write,
+	.pg_init = bl_pg_init_write,
 	.pg_test = pnfs_generic_pg_test,
 	.pg_doio = pnfs_generic_pg_writepages,
 };
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 23ff18fe080a..4c8459e5bdee 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -37,31 +37,7 @@ static struct nfs_callback_data nfs_callback_info[NFS4_MAX_MINOR_VERSION + 1];
 static DEFINE_MUTEX(nfs_callback_mutex);
 static struct svc_program nfs4_callback_program;
 
-unsigned int nfs_callback_set_tcpport;
-unsigned short nfs_callback_tcpport;
 unsigned short nfs_callback_tcpport6;
-#define NFS_CALLBACK_MAXPORTNR (65535U)
-
-static int param_set_portnr(const char *val, const struct kernel_param *kp)
-{
-	unsigned long num;
-	int ret;
-
-	if (!val)
-		return -EINVAL;
-	ret = strict_strtoul(val, 0, &num);
-	if (ret == -EINVAL || num > NFS_CALLBACK_MAXPORTNR)
-		return -EINVAL;
-	*((unsigned int *)kp->arg) = num;
-	return 0;
-}
-static struct kernel_param_ops param_ops_portnr = {
-	.set = param_set_portnr,
-	.get = param_get_uint,
-};
-#define param_check_portnr(name, p) __param_check(name, p, unsigned int);
-
-module_param_named(callback_tcpport, nfs_callback_set_tcpport, portnr, 0644);
 
 /*
  * This is the NFSv4 callback kernel thread.
@@ -265,6 +241,10 @@ int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt)
 		ret = -ENOMEM;
 		goto out_err;
 	}
+	/* As there is only one thread we need to over-ride the
+	 * default maximum of 80 connections
+	 */
+	serv->sv_maxconn = 1024;
 
 	ret = svc_bind(serv, net);
 	if (ret < 0) {
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index a5527c90a5aa..b44d7b128b71 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -192,7 +192,7 @@ extern __be32 nfs4_callback_getattr(struct cb_getattrargs *args,
 				    struct cb_process_state *cps);
 extern __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy,
 				   struct cb_process_state *cps);
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 extern int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt);
 extern void nfs_callback_down(int minorversion);
 extern int nfs4_validate_delegation_stateid(struct nfs_delegation *delegation,
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index e64b01d2a338..742ff4ffced7 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -863,7 +863,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 		.drc_status = 0,
 		.clp = NULL,
 		.slotid = NFS4_NO_SLOT,
-		.net = rqstp->rq_xprt->xpt_net,
+		.net = SVC_NET(rqstp),
 	};
 	unsigned int nops = 0;
 
@@ -879,7 +879,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 		return rpc_garbage_args;
 
 	if (hdr_arg.minorversion == 0) {
-		cps.clp = nfs4_find_client_ident(rqstp->rq_xprt->xpt_net, hdr_arg.cb_ident);
+		cps.clp = nfs4_find_client_ident(SVC_NET(rqstp), hdr_arg.cb_ident);
 		if (!cps.clp || !check_gss_callback_principal(cps.clp, rqstp))
 			return rpc_drop_reply;
 	}
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index f005b5bebdc7..9fc0d9dfc91b 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -51,54 +51,23 @@
 #include "internal.h"
 #include "fscache.h"
 #include "pnfs.h"
+#include "nfs.h"
 #include "netns.h"
 
 #define NFSDBG_FACILITY		NFSDBG_CLIENT
 
 static DECLARE_WAIT_QUEUE_HEAD(nfs_client_active_wq);
-#ifdef CONFIG_NFS_V4
-
-/*
- * Get a unique NFSv4.0 callback identifier which will be used
- * by the V4.0 callback service to lookup the nfs_client struct
- */
-static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion)
-{
-	int ret = 0;
-	struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
-
-	if (clp->rpc_ops->version != 4 || minorversion != 0)
-		return ret;
-retry:
-	if (!idr_pre_get(&nn->cb_ident_idr, GFP_KERNEL))
-		return -ENOMEM;
-	spin_lock(&nn->nfs_client_lock);
-	ret = idr_get_new(&nn->cb_ident_idr, clp, &clp->cl_cb_ident);
-	spin_unlock(&nn->nfs_client_lock);
-	if (ret == -EAGAIN)
-		goto retry;
-	return ret;
-}
-#endif /* CONFIG_NFS_V4 */
-
-/*
- * Turn off NFSv4 uid/gid mapping when using AUTH_SYS
- */
-static bool nfs4_disable_idmapping = true;
+static DEFINE_SPINLOCK(nfs_version_lock);
+static DEFINE_MUTEX(nfs_version_mutex);
+static LIST_HEAD(nfs_versions);
 
 /*
  * RPC cruft for NFS
  */
 static const struct rpc_version *nfs_version[5] = {
-#ifdef CONFIG_NFS_V2
-	[2]			= &nfs_version2,
-#endif
-#ifdef CONFIG_NFS_V3
-	[3]			= &nfs_version3,
-#endif
-#ifdef CONFIG_NFS_V4
-	[4]			= &nfs_version4,
-#endif
+	[2] = NULL,
+	[3] = NULL,
+	[4] = NULL,
 };
 
 const struct rpc_program nfs_program = {
@@ -114,32 +83,64 @@ struct rpc_stat nfs_rpcstat = {
 	.program		= &nfs_program
 };
 
+static struct nfs_subversion *find_nfs_version(unsigned int version)
+{
+	struct nfs_subversion *nfs;
+	spin_lock(&nfs_version_lock);
 
-#ifdef CONFIG_NFS_V3_ACL
-static struct rpc_stat		nfsacl_rpcstat = { &nfsacl_program };
-static const struct rpc_version *nfsacl_version[] = {
-	[3]			= &nfsacl_version3,
-};
+	list_for_each_entry(nfs, &nfs_versions, list) {
+		if (nfs->rpc_ops->version == version) {
+			spin_unlock(&nfs_version_lock);
+			return nfs;
+		}
+	};
 
-const struct rpc_program nfsacl_program = {
-	.name			= "nfsacl",
-	.number			= NFS_ACL_PROGRAM,
-	.nrvers			= ARRAY_SIZE(nfsacl_version),
-	.version		= nfsacl_version,
-	.stats			= &nfsacl_rpcstat,
-};
-#endif  /* CONFIG_NFS_V3_ACL */
-
-struct nfs_client_initdata {
-	unsigned long init_flags;
-	const char *hostname;
-	const struct sockaddr *addr;
-	size_t addrlen;
-	const struct nfs_rpc_ops *rpc_ops;
-	int proto;
-	u32 minorversion;
-	struct net *net;
-};
+	spin_unlock(&nfs_version_lock);
+	return ERR_PTR(-EPROTONOSUPPORT);;
+}
+
+struct nfs_subversion *get_nfs_version(unsigned int version)
+{
+	struct nfs_subversion *nfs = find_nfs_version(version);
+
+	if (IS_ERR(nfs)) {
+		mutex_lock(&nfs_version_mutex);
+		request_module("nfs%d", version);
+		nfs = find_nfs_version(version);
+		mutex_unlock(&nfs_version_mutex);
+	}
+
+	if (!IS_ERR(nfs))
+		try_module_get(nfs->owner);
+	return nfs;
+}
+
+void put_nfs_version(struct nfs_subversion *nfs)
+{
+	module_put(nfs->owner);
+}
+
+void register_nfs_version(struct nfs_subversion *nfs)
+{
+	spin_lock(&nfs_version_lock);
+
+	list_add(&nfs->list, &nfs_versions);
+	nfs_version[nfs->rpc_ops->version] = nfs->rpc_vers;
+
+	spin_unlock(&nfs_version_lock);
+}
+EXPORT_SYMBOL_GPL(register_nfs_version);
+
+void unregister_nfs_version(struct nfs_subversion *nfs)
+{
+	spin_lock(&nfs_version_lock);
+
+	nfs_version[nfs->rpc_ops->version] = NULL;
+	list_del(&nfs->list);
+
+	spin_unlock(&nfs_version_lock);
+}
+EXPORT_SYMBOL_GPL(unregister_nfs_version);
 
 /*
  * Allocate a shared client record
@@ -147,7 +148,7 @@ struct nfs_client_initdata {
  * Since these are allocated/deallocated very rarely, we don't
  * bother putting them in a slab cache...
  */
-static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
+struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
 {
 	struct nfs_client *clp;
 	struct rpc_cred *cred;
@@ -156,7 +157,10 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
 	if ((clp = kzalloc(sizeof(*clp), GFP_KERNEL)) == NULL)
 		goto error_0;
 
-	clp->rpc_ops = cl_init->rpc_ops;
+	clp->cl_nfs_mod = cl_init->nfs_mod;
+	try_module_get(clp->cl_nfs_mod->owner);
+
+	clp->rpc_ops = clp->cl_nfs_mod->rpc_ops;
 
 	atomic_set(&clp->cl_count, 1);
 	clp->cl_cons_state = NFS_CS_INITING;
@@ -177,18 +181,6 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
 	clp->cl_proto = cl_init->proto;
 	clp->cl_net = get_net(cl_init->net);
 
-#ifdef CONFIG_NFS_V4
-	err = nfs_get_cb_ident_idr(clp, cl_init->minorversion);
-	if (err)
-		goto error_cleanup;
-
-	spin_lock_init(&clp->cl_lock);
-	INIT_DELAYED_WORK(&clp->cl_renewd, nfs4_renew_state);
-	rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client");
-	clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED;
-	clp->cl_minorversion = cl_init->minorversion;
-	clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion];
-#endif
 	cred = rpc_lookup_machine_cred("*");
 	if (!IS_ERR(cred))
 		clp->cl_machine_cred = cred;
@@ -197,51 +189,14 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
 	return clp;
 
 error_cleanup:
+	put_nfs_version(clp->cl_nfs_mod);
 	kfree(clp);
 error_0:
 	return ERR_PTR(err);
 }
+EXPORT_SYMBOL_GPL(nfs_alloc_client);
 
-#ifdef CONFIG_NFS_V4
-#ifdef CONFIG_NFS_V4_1
-static void nfs4_shutdown_session(struct nfs_client *clp)
-{
-	if (nfs4_has_session(clp)) {
-		nfs4_destroy_session(clp->cl_session);
-		nfs4_destroy_clientid(clp);
-	}
-
-}
-#else /* CONFIG_NFS_V4_1 */
-static void nfs4_shutdown_session(struct nfs_client *clp)
-{
-}
-#endif /* CONFIG_NFS_V4_1 */
-
-/*
- * Destroy the NFS4 callback service
- */
-static void nfs4_destroy_callback(struct nfs_client *clp)
-{
-	if (__test_and_clear_bit(NFS_CS_CALLBACK, &clp->cl_res_state))
-		nfs_callback_down(clp->cl_mvops->minor_version);
-}
-
-static void nfs4_shutdown_client(struct nfs_client *clp)
-{
-	if (__test_and_clear_bit(NFS_CS_RENEWD, &clp->cl_res_state))
-		nfs4_kill_renewd(clp);
-	nfs4_shutdown_session(clp);
-	nfs4_destroy_callback(clp);
-	if (__test_and_clear_bit(NFS_CS_IDMAP, &clp->cl_res_state))
-		nfs_idmap_delete(clp);
-
-	rpc_destroy_wait_queue(&clp->cl_rpcwaitq);
-	kfree(clp->cl_serverowner);
-	kfree(clp->cl_serverscope);
-	kfree(clp->cl_implid);
-}
-
+#if IS_ENABLED(CONFIG_NFS_V4)
 /* idr_remove_all is not needed as all id's are removed by nfs_put_client */
 void nfs_cleanup_cb_ident_idr(struct net *net)
 {
@@ -264,16 +219,7 @@ static void pnfs_init_server(struct nfs_server *server)
 	rpc_init_wait_queue(&server->roc_rpcwaitq, "pNFS ROC");
 }
 
-static void nfs4_destroy_server(struct nfs_server *server)
-{
-	nfs4_purge_state_owners(server);
-}
-
 #else
-static void nfs4_shutdown_client(struct nfs_client *clp)
-{
-}
-
 void nfs_cleanup_cb_ident_idr(struct net *net)
 {
 }
@@ -291,12 +237,10 @@ static void pnfs_init_server(struct nfs_server *server)
 /*
  * Destroy a shared client record
  */
-static void nfs_free_client(struct nfs_client *clp)
+void nfs_free_client(struct nfs_client *clp)
 {
 	dprintk("--> nfs_free_client(%u)\n", clp->rpc_ops->version);
 
-	nfs4_shutdown_client(clp);
-
 	nfs_fscache_release_client_cookie(clp);
 
 	/* -EIO all pending I/O */
@@ -307,11 +251,13 @@ static void nfs_free_client(struct nfs_client *clp)
 		put_rpccred(clp->cl_machine_cred);
 
 	put_net(clp->cl_net);
+	put_nfs_version(clp->cl_nfs_mod);
 	kfree(clp->cl_hostname);
 	kfree(clp);
 
 	dprintk("<-- nfs_free_client()\n");
 }
+EXPORT_SYMBOL_GPL(nfs_free_client);
 
 /*
  * Release a reference to a shared client record
@@ -333,7 +279,7 @@ void nfs_put_client(struct nfs_client *clp)
 
 		BUG_ON(!list_empty(&clp->cl_superblocks));
 
-		nfs_free_client(clp);
+		clp->rpc_ops->free_client(clp);
 	}
 }
 EXPORT_SYMBOL_GPL(nfs_put_client);
@@ -412,8 +358,8 @@ static int nfs_sockaddr_cmp_ip4(const struct sockaddr *sa1,
  * Test if two socket addresses represent the same actual socket,
  * by comparing (only) relevant fields, excluding the port number.
  */
-static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1,
-				     const struct sockaddr *sa2)
+int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1,
+			      const struct sockaddr *sa2)
 {
 	if (sa1->sa_family != sa2->sa_family)
 		return 0;
@@ -426,6 +372,7 @@ static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1,
 	}
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nfs_sockaddr_match_ipaddr);
 #endif /* CONFIG_NFS_V4_1 */
 
 /*
@@ -447,33 +394,6 @@ static int nfs_sockaddr_cmp(const struct sockaddr *sa1,
 	return 0;
 }
 
-#if defined(CONFIG_NFS_V4_1)
-/* Common match routine for v4.0 and v4.1 callback services */
-static bool nfs4_cb_match_client(const struct sockaddr *addr,
-		struct nfs_client *clp, u32 minorversion)
-{
-	struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr;
-
-	/* Don't match clients that failed to initialise */
-	if (!(clp->cl_cons_state == NFS_CS_READY ||
-	    clp->cl_cons_state == NFS_CS_SESSION_INITING))
-		return false;
-
-	smp_rmb();
-
-	/* Match the version and minorversion */
-	if (clp->rpc_ops->version != 4 ||
-	    clp->cl_minorversion != minorversion)
-		return false;
-
-	/* Match only the IP address, not the port number */
-	if (!nfs_sockaddr_match_ipaddr(addr, clap))
-		return false;
-
-	return true;
-}
-#endif /* CONFIG_NFS_V4_1 */
-
 /*
  * Find an nfs_client on the list that matches the initialisation data
  * that is supplied.
@@ -491,7 +411,7 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
 			continue;
 
 		/* Different NFS versions cannot share the same nfs_client */
-		if (clp->rpc_ops != data->rpc_ops)
+		if (clp->rpc_ops != data->nfs_mod->rpc_ops)
 			continue;
 
 		if (clp->cl_proto != data->proto)
@@ -519,6 +439,7 @@ int nfs_wait_client_init_complete(const struct nfs_client *clp)
 	return wait_event_killable(nfs_client_active_wq,
 			nfs_client_init_is_complete(clp));
 }
+EXPORT_SYMBOL_GPL(nfs_wait_client_init_complete);
 
 /*
  * Found an existing client.  Make sure it's ready before returning.
@@ -552,7 +473,7 @@ nfs_found_client(const struct nfs_client_initdata *cl_init,
  * Look up a client by IP address and protocol version
  * - creates a new record if one doesn't yet exist
  */
-static struct nfs_client *
+struct nfs_client *
 nfs_get_client(const struct nfs_client_initdata *cl_init,
 	       const struct rpc_timeout *timeparms,
 	       const char *ip_addr,
@@ -560,9 +481,10 @@ nfs_get_client(const struct nfs_client_initdata *cl_init,
 {
 	struct nfs_client *clp, *new = NULL;
 	struct nfs_net *nn = net_generic(cl_init->net, nfs_net_id);
+	const struct nfs_rpc_ops *rpc_ops = cl_init->nfs_mod->rpc_ops;
 
 	dprintk("--> nfs_get_client(%s,v%u)\n",
-		cl_init->hostname ?: "", cl_init->rpc_ops->version);
+		cl_init->hostname ?: "", rpc_ops->version);
 
 	/* see if the client already exists */
 	do {
@@ -572,27 +494,27 @@ nfs_get_client(const struct nfs_client_initdata *cl_init,
 		if (clp) {
 			spin_unlock(&nn->nfs_client_lock);
 			if (new)
-				nfs_free_client(new);
+				new->rpc_ops->free_client(new);
 			return nfs_found_client(cl_init, clp);
 		}
 		if (new) {
 			list_add(&new->cl_share_link, &nn->nfs_client_list);
 			spin_unlock(&nn->nfs_client_lock);
 			new->cl_flags = cl_init->init_flags;
-			return cl_init->rpc_ops->init_client(new,
-						timeparms, ip_addr,
-						authflavour);
+			return rpc_ops->init_client(new, timeparms, ip_addr,
+						    authflavour);
 		}
 
 		spin_unlock(&nn->nfs_client_lock);
 
-		new = nfs_alloc_client(cl_init);
+		new = rpc_ops->alloc_client(cl_init);
 	} while (!IS_ERR(new));
 
 	dprintk("<-- nfs_get_client() Failed to find %s (%ld)\n",
 		cl_init->hostname ?: "", PTR_ERR(new));
 	return new;
 }
+EXPORT_SYMBOL_GPL(nfs_get_client);
 
 /*
  * Mark a server as ready or failed
@@ -603,11 +525,12 @@ void nfs_mark_client_ready(struct nfs_client *clp, int state)
 	clp->cl_cons_state = state;
 	wake_up_all(&nfs_client_active_wq);
 }
+EXPORT_SYMBOL_GPL(nfs_mark_client_ready);
 
 /*
  * Initialise the timeout values for a connection
  */
-static void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
+void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
 				    unsigned int timeo, unsigned int retrans)
 {
 	to->to_initval = timeo * HZ / 10;
@@ -644,13 +567,14 @@ static void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
 		BUG();
 	}
 }
+EXPORT_SYMBOL_GPL(nfs_init_timeout_values);
 
 /*
  * Create an RPC client handle
  */
-static int nfs_create_rpc_client(struct nfs_client *clp,
-				 const struct rpc_timeout *timeparms,
-				 rpc_authflavor_t flavor)
+int nfs_create_rpc_client(struct nfs_client *clp,
+			  const struct rpc_timeout *timeparms,
+			  rpc_authflavor_t flavor)
 {
 	struct rpc_clnt		*clnt = NULL;
 	struct rpc_create_args args = {
@@ -683,6 +607,7 @@ static int nfs_create_rpc_client(struct nfs_client *clp,
 	clp->cl_rpcclient = clnt;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nfs_create_rpc_client);
 
 /*
  * Version 2 or 3 client destruction
@@ -735,39 +660,9 @@ static int nfs_start_lockd(struct nfs_server *server)
 }
 
 /*
- * Initialise an NFSv3 ACL client connection
- */
-#ifdef CONFIG_NFS_V3_ACL
-static void nfs_init_server_aclclient(struct nfs_server *server)
-{
-	if (server->nfs_client->rpc_ops->version != 3)
-		goto out_noacl;
-	if (server->flags & NFS_MOUNT_NOACL)
-		goto out_noacl;
-
-	server->client_acl = rpc_bind_new_program(server->client, &nfsacl_program, 3);
-	if (IS_ERR(server->client_acl))
-		goto out_noacl;
-
-	/* No errors! Assume that Sun nfsacls are supported */
-	server->caps |= NFS_CAP_ACLS;
-	return;
-
-out_noacl:
-	server->caps &= ~NFS_CAP_ACLS;
-}
-#else
-static inline void nfs_init_server_aclclient(struct nfs_server *server)
-{
-	server->flags &= ~NFS_MOUNT_NOACL;
-	server->caps &= ~NFS_CAP_ACLS;
-}
-#endif
-
-/*
  * Create a general RPC client
  */
-static int nfs_init_server_rpcclient(struct nfs_server *server,
+int nfs_init_server_rpcclient(struct nfs_server *server,
 		const struct rpc_timeout *timeo,
 		rpc_authflavor_t pseudoflavour)
 {
@@ -799,6 +694,7 @@ static int nfs_init_server_rpcclient(struct nfs_server *server,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nfs_init_server_rpcclient);
 
 /**
  * nfs_init_client - Initialise an NFS2 or NFS3 client
@@ -838,18 +734,20 @@ error:
 	dprintk("<-- nfs_init_client() = xerror %d\n", error);
 	return ERR_PTR(error);
 }
+EXPORT_SYMBOL_GPL(nfs_init_client);
 
 /*
  * Create a version 2 or 3 client
  */
 static int nfs_init_server(struct nfs_server *server,
-			   const struct nfs_parsed_mount_data *data)
+			   const struct nfs_parsed_mount_data *data,
+			   struct nfs_subversion *nfs_mod)
 {
 	struct nfs_client_initdata cl_init = {
 		.hostname = data->nfs_server.hostname,
 		.addr = (const struct sockaddr *)&data->nfs_server.address,
 		.addrlen = data->nfs_server.addrlen,
-		.rpc_ops = NULL,
+		.nfs_mod = nfs_mod,
 		.proto = data->nfs_server.protocol,
 		.net = data->net,
 	};
@@ -859,21 +757,6 @@ static int nfs_init_server(struct nfs_server *server,
 
 	dprintk("--> nfs_init_server()\n");
 
-	switch (data->version) {
-#ifdef CONFIG_NFS_V2
-	case 2:
-		cl_init.rpc_ops = &nfs_v2_clientops;
-		break;
-#endif
-#ifdef CONFIG_NFS_V3
-	case 3:
-		cl_init.rpc_ops = &nfs_v3_clientops;
-		break;
-#endif
-	default:
-		return -EPROTONOSUPPORT;
-	}
-
 	nfs_init_timeout_values(&timeparms, data->nfs_server.protocol,
 			data->timeo, data->retrans);
 	if (data->flags & NFS_MOUNT_NORESVPORT)
@@ -927,8 +810,6 @@ static int nfs_init_server(struct nfs_server *server,
 	server->mountd_protocol = data->mount_server.protocol;
 
 	server->namelen  = data->namlen;
-	/* Create a client RPC handle for the NFSv3 ACL management interface */
-	nfs_init_server_aclclient(server);
 	dprintk("<-- nfs_init_server() = 0 [new %p]\n", clp);
 	return 0;
 
@@ -975,7 +856,6 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 		server->wsize = NFS_MAX_FILE_IO_SIZE;
 	server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 	server->pnfs_blksize = fsinfo->blksize;
-	set_pnfs_layoutdriver(server, mntfh, fsinfo->layouttype);
 
 	server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL);
 
@@ -1001,7 +881,7 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 /*
  * Probe filesystem information, including the FSID on v2/v3
  */
-static int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, struct nfs_fattr *fattr)
+int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, struct nfs_fattr *fattr)
 {
 	struct nfs_fsinfo fsinfo;
 	struct nfs_client *clp = server->nfs_client;
@@ -1041,11 +921,12 @@ out_error:
 	dprintk("nfs_probe_fsinfo: error = %d\n", -error);
 	return error;
 }
+EXPORT_SYMBOL_GPL(nfs_probe_fsinfo);
 
 /*
  * Copy useful information when duplicating a server record
  */
-static void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_server *source)
+void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_server *source)
 {
 	target->flags = source->flags;
 	target->rsize = source->rsize;
@@ -1057,8 +938,9 @@ static void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_serve
 	target->caps = source->caps;
 	target->options = source->options;
 }
+EXPORT_SYMBOL_GPL(nfs_server_copy_userdata);
 
-static void nfs_server_insert_lists(struct nfs_server *server)
+void nfs_server_insert_lists(struct nfs_server *server)
 {
 	struct nfs_client *clp = server->nfs_client;
 	struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
@@ -1070,6 +952,7 @@ static void nfs_server_insert_lists(struct nfs_server *server)
 	spin_unlock(&nn->nfs_client_lock);
 
 }
+EXPORT_SYMBOL_GPL(nfs_server_insert_lists);
 
 static void nfs_server_remove_lists(struct nfs_server *server)
 {
@@ -1092,7 +975,7 @@ static void nfs_server_remove_lists(struct nfs_server *server)
 /*
  * Allocate and initialise a server record
  */
-static struct nfs_server *nfs_alloc_server(void)
+struct nfs_server *nfs_alloc_server(void)
 {
 	struct nfs_server *server;
 
@@ -1129,6 +1012,7 @@ static struct nfs_server *nfs_alloc_server(void)
 
 	return server;
 }
+EXPORT_SYMBOL_GPL(nfs_alloc_server);
 
 /*
  * Free up a server record
@@ -1138,7 +1022,6 @@ void nfs_free_server(struct nfs_server *server)
 	dprintk("--> nfs_free_server()\n");
 
 	nfs_server_remove_lists(server);
-	unset_pnfs_layoutdriver(server);
 
 	if (server->destroy != NULL)
 		server->destroy(server);
@@ -1158,13 +1041,14 @@ void nfs_free_server(struct nfs_server *server)
 	nfs_release_automount_timer();
 	dprintk("<-- nfs_free_server()\n");
 }
+EXPORT_SYMBOL_GPL(nfs_free_server);
 
 /*
  * Create a version 2 or 3 volume record
  * - keyed on server and FSID
  */
-struct nfs_server *nfs_create_server(const struct nfs_parsed_mount_data *data,
-				     struct nfs_fh *mntfh)
+struct nfs_server *nfs_create_server(struct nfs_mount_info *mount_info,
+				     struct nfs_subversion *nfs_mod)
 {
 	struct nfs_server *server;
 	struct nfs_fattr *fattr;
@@ -1180,7 +1064,7 @@ struct nfs_server *nfs_create_server(const struct nfs_parsed_mount_data *data,
 		goto error;
 
 	/* Get a client representation */
-	error = nfs_init_server(server, data);
+	error = nfs_init_server(server, mount_info->parsed, nfs_mod);
 	if (error < 0)
 		goto error;
 
@@ -1189,13 +1073,13 @@ struct nfs_server *nfs_create_server(const struct nfs_parsed_mount_data *data,
 	BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
 
 	/* Probe the root fh to retrieve its FSID */
-	error = nfs_probe_fsinfo(server, mntfh, fattr);
+	error = nfs_probe_fsinfo(server, mount_info->mntfh, fattr);
 	if (error < 0)
 		goto error;
 	if (server->nfs_client->rpc_ops->version == 3) {
 		if (server->namelen == 0 || server->namelen > NFS3_MAXNAMLEN)
 			server->namelen = NFS3_MAXNAMLEN;
-		if (!(data->flags & NFS_MOUNT_NORDIRPLUS))
+		if (!(mount_info->parsed->flags & NFS_MOUNT_NORDIRPLUS))
 			server->caps |= NFS_CAP_READDIRPLUS;
 	} else {
 		if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN)
@@ -1203,7 +1087,7 @@ struct nfs_server *nfs_create_server(const struct nfs_parsed_mount_data *data,
 	}
 
 	if (!(fattr->valid & NFS_ATTR_FATTR)) {
-		error = server->nfs_client->rpc_ops->getattr(server, mntfh, fattr);
+		error = nfs_mod->rpc_ops->getattr(server, mount_info->mntfh, fattr);
 		if (error < 0) {
 			dprintk("nfs_create_server: getattr error = %d\n", -error);
 			goto error;
@@ -1225,522 +1109,7 @@ error:
 	nfs_free_server(server);
 	return ERR_PTR(error);
 }
-
-#ifdef CONFIG_NFS_V4
-/*
- * NFSv4.0 callback thread helper
- *
- * Find a client by callback identifier
- */
-struct nfs_client *
-nfs4_find_client_ident(struct net *net, int cb_ident)
-{
-	struct nfs_client *clp;
-	struct nfs_net *nn = net_generic(net, nfs_net_id);
-
-	spin_lock(&nn->nfs_client_lock);
-	clp = idr_find(&nn->cb_ident_idr, cb_ident);
-	if (clp)
-		atomic_inc(&clp->cl_count);
-	spin_unlock(&nn->nfs_client_lock);
-	return clp;
-}
-
-#if defined(CONFIG_NFS_V4_1)
-/*
- * NFSv4.1 callback thread helper
- * For CB_COMPOUND calls, find a client by IP address, protocol version,
- * minorversion, and sessionID
- *
- * Returns NULL if no such client
- */
-struct nfs_client *
-nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr,
-			   struct nfs4_sessionid *sid)
-{
-	struct nfs_client *clp;
-	struct nfs_net *nn = net_generic(net, nfs_net_id);
-
-	spin_lock(&nn->nfs_client_lock);
-	list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) {
-		if (nfs4_cb_match_client(addr, clp, 1) == false)
-			continue;
-
-		if (!nfs4_has_session(clp))
-			continue;
-
-		/* Match sessionid*/
-		if (memcmp(clp->cl_session->sess_id.data,
-		    sid->data, NFS4_MAX_SESSIONID_LEN) != 0)
-			continue;
-
-		atomic_inc(&clp->cl_count);
-		spin_unlock(&nn->nfs_client_lock);
-		return clp;
-	}
-	spin_unlock(&nn->nfs_client_lock);
-	return NULL;
-}
-
-#else /* CONFIG_NFS_V4_1 */
-
-struct nfs_client *
-nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr,
-			   struct nfs4_sessionid *sid)
-{
-	return NULL;
-}
-#endif /* CONFIG_NFS_V4_1 */
-
-/*
- * Initialize the NFS4 callback service
- */
-static int nfs4_init_callback(struct nfs_client *clp)
-{
-	int error;
-
-	if (clp->rpc_ops->version == 4) {
-		struct rpc_xprt *xprt;
-
-		xprt = rcu_dereference_raw(clp->cl_rpcclient->cl_xprt);
-
-		if (nfs4_has_session(clp)) {
-			error = xprt_setup_backchannel(xprt,
-						NFS41_BC_MIN_CALLBACKS);
-			if (error < 0)
-				return error;
-		}
-
-		error = nfs_callback_up(clp->cl_mvops->minor_version, xprt);
-		if (error < 0) {
-			dprintk("%s: failed to start callback. Error = %d\n",
-				__func__, error);
-			return error;
-		}
-		__set_bit(NFS_CS_CALLBACK, &clp->cl_res_state);
-	}
-	return 0;
-}
-
-/*
- * Initialize the minor version specific parts of an NFS4 client record
- */
-static int nfs4_init_client_minor_version(struct nfs_client *clp)
-{
-#if defined(CONFIG_NFS_V4_1)
-	if (clp->cl_mvops->minor_version) {
-		struct nfs4_session *session = NULL;
-		/*
-		 * Create the session and mark it expired.
-		 * When a SEQUENCE operation encounters the expired session
-		 * it will do session recovery to initialize it.
-		 */
-		session = nfs4_alloc_session(clp);
-		if (!session)
-			return -ENOMEM;
-
-		clp->cl_session = session;
-		/*
-		 * The create session reply races with the server back
-		 * channel probe. Mark the client NFS_CS_SESSION_INITING
-		 * so that the client back channel can find the
-		 * nfs_client struct
-		 */
-		nfs_mark_client_ready(clp, NFS_CS_SESSION_INITING);
-	}
-#endif /* CONFIG_NFS_V4_1 */
-
-	return nfs4_init_callback(clp);
-}
-
-/**
- * nfs4_init_client - Initialise an NFS4 client record
- *
- * @clp: nfs_client to initialise
- * @timeparms: timeout parameters for underlying RPC transport
- * @ip_addr: callback IP address in presentation format
- * @authflavor: authentication flavor for underlying RPC transport
- *
- * Returns pointer to an NFS client, or an ERR_PTR value.
- */
-struct nfs_client *nfs4_init_client(struct nfs_client *clp,
-				    const struct rpc_timeout *timeparms,
-				    const char *ip_addr,
-				    rpc_authflavor_t authflavour)
-{
-	char buf[INET6_ADDRSTRLEN + 1];
-	int error;
-
-	if (clp->cl_cons_state == NFS_CS_READY) {
-		/* the client is initialised already */
-		dprintk("<-- nfs4_init_client() = 0 [already %p]\n", clp);
-		return clp;
-	}
-
-	/* Check NFS protocol revision and initialize RPC op vector */
-	clp->rpc_ops = &nfs_v4_clientops;
-
-	__set_bit(NFS_CS_DISCRTRY, &clp->cl_flags);
-	error = nfs_create_rpc_client(clp, timeparms, authflavour);
-	if (error < 0)
-		goto error;
-
-	/* If no clientaddr= option was specified, find a usable cb address */
-	if (ip_addr == NULL) {
-		struct sockaddr_storage cb_addr;
-		struct sockaddr *sap = (struct sockaddr *)&cb_addr;
-
-		error = rpc_localaddr(clp->cl_rpcclient, sap, sizeof(cb_addr));
-		if (error < 0)
-			goto error;
-		error = rpc_ntop(sap, buf, sizeof(buf));
-		if (error < 0)
-			goto error;
-		ip_addr = (const char *)buf;
-	}
-	strlcpy(clp->cl_ipaddr, ip_addr, sizeof(clp->cl_ipaddr));
-
-	error = nfs_idmap_new(clp);
-	if (error < 0) {
-		dprintk("%s: failed to create idmapper. Error = %d\n",
-			__func__, error);
-		goto error;
-	}
-	__set_bit(NFS_CS_IDMAP, &clp->cl_res_state);
-
-	error = nfs4_init_client_minor_version(clp);
-	if (error < 0)
-		goto error;
-
-	if (!nfs4_has_session(clp))
-		nfs_mark_client_ready(clp, NFS_CS_READY);
-	return clp;
-
-error:
-	nfs_mark_client_ready(clp, error);
-	nfs_put_client(clp);
-	dprintk("<-- nfs4_init_client() = xerror %d\n", error);
-	return ERR_PTR(error);
-}
-
-/*
- * Set up an NFS4 client
- */
-static int nfs4_set_client(struct nfs_server *server,
-		const char *hostname,
-		const struct sockaddr *addr,
-		const size_t addrlen,
-		const char *ip_addr,
-		rpc_authflavor_t authflavour,
-		int proto, const struct rpc_timeout *timeparms,
-		u32 minorversion, struct net *net)
-{
-	struct nfs_client_initdata cl_init = {
-		.hostname = hostname,
-		.addr = addr,
-		.addrlen = addrlen,
-		.rpc_ops = &nfs_v4_clientops,
-		.proto = proto,
-		.minorversion = minorversion,
-		.net = net,
-	};
-	struct nfs_client *clp;
-	int error;
-
-	dprintk("--> nfs4_set_client()\n");
-
-	if (server->flags & NFS_MOUNT_NORESVPORT)
-		set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
-
-	/* Allocate or find a client reference we can use */
-	clp = nfs_get_client(&cl_init, timeparms, ip_addr, authflavour);
-	if (IS_ERR(clp)) {
-		error = PTR_ERR(clp);
-		goto error;
-	}
-
-	/*
-	 * Query for the lease time on clientid setup or renewal
-	 *
-	 * Note that this will be set on nfs_clients that were created
-	 * only for the DS role and did not set this bit, but now will
-	 * serve a dual role.
-	 */
-	set_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state);
-
-	server->nfs_client = clp;
-	dprintk("<-- nfs4_set_client() = 0 [new %p]\n", clp);
-	return 0;
-error:
-	dprintk("<-- nfs4_set_client() = xerror %d\n", error);
-	return error;
-}
-
-/*
- * Set up a pNFS Data Server client.
- *
- * Return any existing nfs_client that matches server address,port,version
- * and minorversion.
- *
- * For a new nfs_client, use a soft mount (default), a low retrans and a
- * low timeout interval so that if a connection is lost, we retry through
- * the MDS.
- */
-struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
-		const struct sockaddr *ds_addr, int ds_addrlen,
-		int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans)
-{
-	struct nfs_client_initdata cl_init = {
-		.addr = ds_addr,
-		.addrlen = ds_addrlen,
-		.rpc_ops = &nfs_v4_clientops,
-		.proto = ds_proto,
-		.minorversion = mds_clp->cl_minorversion,
-		.net = mds_clp->cl_net,
-	};
-	struct rpc_timeout ds_timeout;
-	struct nfs_client *clp;
-
-	/*
-	 * Set an authflavor equual to the MDS value. Use the MDS nfs_client
-	 * cl_ipaddr so as to use the same EXCHANGE_ID co_ownerid as the MDS
-	 * (section 13.1 RFC 5661).
-	 */
-	nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans);
-	clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr,
-			     mds_clp->cl_rpcclient->cl_auth->au_flavor);
-
-	dprintk("<-- %s %p\n", __func__, clp);
-	return clp;
-}
-EXPORT_SYMBOL_GPL(nfs4_set_ds_client);
-
-/*
- * Session has been established, and the client marked ready.
- * Set the mount rsize and wsize with negotiated fore channel
- * attributes which will be bound checked in nfs_server_set_fsinfo.
- */
-static void nfs4_session_set_rwsize(struct nfs_server *server)
-{
-#ifdef CONFIG_NFS_V4_1
-	struct nfs4_session *sess;
-	u32 server_resp_sz;
-	u32 server_rqst_sz;
-
-	if (!nfs4_has_session(server->nfs_client))
-		return;
-	sess = server->nfs_client->cl_session;
-	server_resp_sz = sess->fc_attrs.max_resp_sz - nfs41_maxread_overhead;
-	server_rqst_sz = sess->fc_attrs.max_rqst_sz - nfs41_maxwrite_overhead;
-
-	if (server->rsize > server_resp_sz)
-		server->rsize = server_resp_sz;
-	if (server->wsize > server_rqst_sz)
-		server->wsize = server_rqst_sz;
-#endif /* CONFIG_NFS_V4_1 */
-}
-
-static int nfs4_server_common_setup(struct nfs_server *server,
-		struct nfs_fh *mntfh)
-{
-	struct nfs_fattr *fattr;
-	int error;
-
-	BUG_ON(!server->nfs_client);
-	BUG_ON(!server->nfs_client->rpc_ops);
-	BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
-
-	/* data servers support only a subset of NFSv4.1 */
-	if (is_ds_only_client(server->nfs_client))
-		return -EPROTONOSUPPORT;
-
-	fattr = nfs_alloc_fattr();
-	if (fattr == NULL)
-		return -ENOMEM;
-
-	/* We must ensure the session is initialised first */
-	error = nfs4_init_session(server);
-	if (error < 0)
-		goto out;
-
-	/* Probe the root fh to retrieve its FSID and filehandle */
-	error = nfs4_get_rootfh(server, mntfh);
-	if (error < 0)
-		goto out;
-
-	dprintk("Server FSID: %llx:%llx\n",
-			(unsigned long long) server->fsid.major,
-			(unsigned long long) server->fsid.minor);
-	dprintk("Mount FH: %d\n", mntfh->size);
-
-	nfs4_session_set_rwsize(server);
-
-	error = nfs_probe_fsinfo(server, mntfh, fattr);
-	if (error < 0)
-		goto out;
-
-	if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN)
-		server->namelen = NFS4_MAXNAMLEN;
-
-	nfs_server_insert_lists(server);
-	server->mount_time = jiffies;
-	server->destroy = nfs4_destroy_server;
-out:
-	nfs_free_fattr(fattr);
-	return error;
-}
-
-/*
- * Create a version 4 volume record
- */
-static int nfs4_init_server(struct nfs_server *server,
-		const struct nfs_parsed_mount_data *data)
-{
-	struct rpc_timeout timeparms;
-	int error;
-
-	dprintk("--> nfs4_init_server()\n");
-
-	nfs_init_timeout_values(&timeparms, data->nfs_server.protocol,
-			data->timeo, data->retrans);
-
-	/* Initialise the client representation from the mount data */
-	server->flags = data->flags;
-	server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR|NFS_CAP_POSIX_LOCK;
-	if (!(data->flags & NFS_MOUNT_NORDIRPLUS))
-			server->caps |= NFS_CAP_READDIRPLUS;
-	server->options = data->options;
-
-	/* Get a client record */
-	error = nfs4_set_client(server,
-			data->nfs_server.hostname,
-			(const struct sockaddr *)&data->nfs_server.address,
-			data->nfs_server.addrlen,
-			data->client_address,
-			data->auth_flavors[0],
-			data->nfs_server.protocol,
-			&timeparms,
-			data->minorversion,
-			data->net);
-	if (error < 0)
-		goto error;
-
-	/*
-	 * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower
-	 * authentication.
-	 */
-	if (nfs4_disable_idmapping && data->auth_flavors[0] == RPC_AUTH_UNIX)
-		server->caps |= NFS_CAP_UIDGID_NOMAP;
-
-	if (data->rsize)
-		server->rsize = nfs_block_size(data->rsize, NULL);
-	if (data->wsize)
-		server->wsize = nfs_block_size(data->wsize, NULL);
-
-	server->acregmin = data->acregmin * HZ;
-	server->acregmax = data->acregmax * HZ;
-	server->acdirmin = data->acdirmin * HZ;
-	server->acdirmax = data->acdirmax * HZ;
-
-	server->port = data->nfs_server.port;
-
-	error = nfs_init_server_rpcclient(server, &timeparms, data->auth_flavors[0]);
-
-error:
-	/* Done */
-	dprintk("<-- nfs4_init_server() = %d\n", error);
-	return error;
-}
-
-/*
- * Create a version 4 volume record
- * - keyed on server and FSID
- */
-struct nfs_server *nfs4_create_server(const struct nfs_parsed_mount_data *data,
-				      struct nfs_fh *mntfh)
-{
-	struct nfs_server *server;
-	int error;
-
-	dprintk("--> nfs4_create_server()\n");
-
-	server = nfs_alloc_server();
-	if (!server)
-		return ERR_PTR(-ENOMEM);
-
-	/* set up the general RPC client */
-	error = nfs4_init_server(server, data);
-	if (error < 0)
-		goto error;
-
-	error = nfs4_server_common_setup(server, mntfh);
-	if (error < 0)
-		goto error;
-
-	dprintk("<-- nfs4_create_server() = %p\n", server);
-	return server;
-
-error:
-	nfs_free_server(server);
-	dprintk("<-- nfs4_create_server() = error %d\n", error);
-	return ERR_PTR(error);
-}
-
-/*
- * Create an NFS4 referral server record
- */
-struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
-					       struct nfs_fh *mntfh)
-{
-	struct nfs_client *parent_client;
-	struct nfs_server *server, *parent_server;
-	int error;
-
-	dprintk("--> nfs4_create_referral_server()\n");
-
-	server = nfs_alloc_server();
-	if (!server)
-		return ERR_PTR(-ENOMEM);
-
-	parent_server = NFS_SB(data->sb);
-	parent_client = parent_server->nfs_client;
-
-	/* Initialise the client representation from the parent server */
-	nfs_server_copy_userdata(server, parent_server);
-	server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR;
-
-	/* Get a client representation.
-	 * Note: NFSv4 always uses TCP, */
-	error = nfs4_set_client(server, data->hostname,
-				data->addr,
-				data->addrlen,
-				parent_client->cl_ipaddr,
-				data->authflavor,
-				rpc_protocol(parent_server->client),
-				parent_server->client->cl_timeout,
-				parent_client->cl_mvops->minor_version,
-				parent_client->cl_net);
-	if (error < 0)
-		goto error;
-
-	error = nfs_init_server_rpcclient(server, parent_server->client->cl_timeout, data->authflavor);
-	if (error < 0)
-		goto error;
-
-	error = nfs4_server_common_setup(server, mntfh);
-	if (error < 0)
-		goto error;
-
-	dprintk("<-- nfs_create_referral_server() = %p\n", server);
-	return server;
-
-error:
-	nfs_free_server(server);
-	dprintk("<-- nfs4_create_referral_server() = error %d\n", error);
-	return ERR_PTR(error);
-}
-
-#endif /* CONFIG_NFS_V4 */
+EXPORT_SYMBOL_GPL(nfs_create_server);
 
 /*
  * Clone an NFS2, NFS3 or NFS4 server record
@@ -1780,8 +1149,6 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source,
 			flavor);
 	if (error < 0)
 		goto out_free_server;
-	if (!IS_ERR(source->client_acl))
-		nfs_init_server_aclclient(server);
 
 	/* probe the filesystem info for this server filesystem */
 	error = nfs_probe_fsinfo(server, fh, fattr_fsinfo);
@@ -1812,6 +1179,7 @@ out_free_server:
 	dprintk("<-- nfs_clone_server() = error %d\n", error);
 	return ERR_PTR(error);
 }
+EXPORT_SYMBOL_GPL(nfs_clone_server);
 
 void nfs_clients_init(struct net *net)
 {
@@ -1819,7 +1187,7 @@ void nfs_clients_init(struct net *net)
 
 	INIT_LIST_HEAD(&nn->nfs_client_list);
 	INIT_LIST_HEAD(&nn->nfs_volume_list);
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 	idr_init(&nn->cb_ident_idr);
 #endif
 	spin_lock_init(&nn->nfs_client_lock);
@@ -2091,7 +1459,3 @@ void nfs_fs_proc_exit(void)
 }
 
 #endif /* CONFIG_PROC_FS */
-
-module_param(nfs4_disable_idmapping, bool, 0644);
-MODULE_PARM_DESC(nfs4_disable_idmapping,
-		"Turn off NFSv4 idmapping when using 'sec=sys'");
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index bd3a9601d32d..81c5eec3cf38 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -47,7 +47,7 @@ void nfs_mark_delegation_referenced(struct nfs_delegation *delegation)
  *
  * Returns one if inode has the indicated delegation, otherwise zero.
  */
-int nfs_have_delegation(struct inode *inode, fmode_t flags)
+int nfs4_have_delegation(struct inode *inode, fmode_t flags)
 {
 	struct nfs_delegation *delegation;
 	int ret = 0;
@@ -388,7 +388,7 @@ void nfs_inode_return_delegation_noreclaim(struct inode *inode)
  *
  * Returns zero on success, or a negative errno value.
  */
-int nfs_inode_return_delegation(struct inode *inode)
+int nfs4_inode_return_delegation(struct inode *inode)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
 	struct nfs_inode *nfsi = NFS_I(inode);
@@ -417,9 +417,8 @@ static void nfs_mark_return_delegation(struct nfs_server *server,
  * @sb: sb to process
  *
  */
-void nfs_super_return_all_delegations(struct super_block *sb)
+void nfs_server_return_all_delegations(struct nfs_server *server)
 {
-	struct nfs_server *server = NFS_SB(sb);
 	struct nfs_client *clp = server->nfs_client;
 	struct nfs_delegation *delegation;
 
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index 72709c4193fa..bbc6a4dba0d8 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -8,7 +8,7 @@
 #ifndef FS_NFS_DELEGATION_H
 #define FS_NFS_DELEGATION_H
 
-#if defined(CONFIG_NFS_V4)
+#if IS_ENABLED(CONFIG_NFS_V4)
 /*
  * NFSv4 delegation
  */
@@ -33,12 +33,12 @@ enum {
 
 int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res);
 void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res);
-int nfs_inode_return_delegation(struct inode *inode);
+int nfs4_inode_return_delegation(struct inode *inode);
 int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid);
 void nfs_inode_return_delegation_noreclaim(struct inode *inode);
 
 struct inode *nfs_delegation_find_inode(struct nfs_client *clp, const struct nfs_fh *fhandle);
-void nfs_super_return_all_delegations(struct super_block *sb);
+void nfs_server_return_all_delegations(struct nfs_server *);
 void nfs_expire_all_delegations(struct nfs_client *clp);
 void nfs_expire_all_delegation_types(struct nfs_client *clp, fmode_t flags);
 void nfs_expire_unreferenced_delegations(struct nfs_client *clp);
@@ -56,24 +56,13 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl);
 bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode, fmode_t flags);
 
 void nfs_mark_delegation_referenced(struct nfs_delegation *delegation);
-int nfs_have_delegation(struct inode *inode, fmode_t flags);
+int nfs4_have_delegation(struct inode *inode, fmode_t flags);
 
-#else
-static inline int nfs_have_delegation(struct inode *inode, fmode_t flags)
-{
-	return 0;
-}
-
-static inline int nfs_inode_return_delegation(struct inode *inode)
-{
-	nfs_wb_all(inode);
-	return 0;
-}
 #endif
 
 static inline int nfs_have_delegated_attributes(struct inode *inode)
 {
-	return nfs_have_delegation(inode, FMODE_READ) &&
+	return NFS_PROTO(inode)->have_delegation(inode, FMODE_READ) &&
 		!(NFS_I(inode)->cache_validity & NFS_INO_REVAL_FORCED);
 }
 
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index a6b1c7fb8232..627f108ede23 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -17,6 +17,7 @@
  *  6 Jun 1999	Cache readdir lookups in the page cache. -DaveM
  */
 
+#include <linux/module.h>
 #include <linux/time.h>
 #include <linux/errno.h>
 #include <linux/stat.h>
@@ -46,16 +47,6 @@
 static int nfs_opendir(struct inode *, struct file *);
 static int nfs_closedir(struct inode *, struct file *);
 static int nfs_readdir(struct file *, void *, filldir_t);
-static struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int);
-static int nfs_create(struct inode *, struct dentry *, umode_t, bool);
-static int nfs_mkdir(struct inode *, struct dentry *, umode_t);
-static int nfs_rmdir(struct inode *, struct dentry *);
-static int nfs_unlink(struct inode *, struct dentry *);
-static int nfs_symlink(struct inode *, struct dentry *, const char *);
-static int nfs_link(struct dentry *, struct inode *, struct dentry *);
-static int nfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
-static int nfs_rename(struct inode *, struct dentry *,
-		      struct inode *, struct dentry *);
 static int nfs_fsync_dir(struct file *, loff_t, loff_t, int);
 static loff_t nfs_llseek_dir(struct file *, loff_t, int);
 static void nfs_readdir_clear_array(struct page*);
@@ -69,73 +60,10 @@ const struct file_operations nfs_dir_operations = {
 	.fsync		= nfs_fsync_dir,
 };
 
-const struct inode_operations nfs_dir_inode_operations = {
-	.create		= nfs_create,
-	.lookup		= nfs_lookup,
-	.link		= nfs_link,
-	.unlink		= nfs_unlink,
-	.symlink	= nfs_symlink,
-	.mkdir		= nfs_mkdir,
-	.rmdir		= nfs_rmdir,
-	.mknod		= nfs_mknod,
-	.rename		= nfs_rename,
-	.permission	= nfs_permission,
-	.getattr	= nfs_getattr,
-	.setattr	= nfs_setattr,
-};
-
 const struct address_space_operations nfs_dir_aops = {
 	.freepage = nfs_readdir_clear_array,
 };
 
-#ifdef CONFIG_NFS_V3
-const struct inode_operations nfs3_dir_inode_operations = {
-	.create		= nfs_create,
-	.lookup		= nfs_lookup,
-	.link		= nfs_link,
-	.unlink		= nfs_unlink,
-	.symlink	= nfs_symlink,
-	.mkdir		= nfs_mkdir,
-	.rmdir		= nfs_rmdir,
-	.mknod		= nfs_mknod,
-	.rename		= nfs_rename,
-	.permission	= nfs_permission,
-	.getattr	= nfs_getattr,
-	.setattr	= nfs_setattr,
-	.listxattr	= nfs3_listxattr,
-	.getxattr	= nfs3_getxattr,
-	.setxattr	= nfs3_setxattr,
-	.removexattr	= nfs3_removexattr,
-};
-#endif  /* CONFIG_NFS_V3 */
-
-#ifdef CONFIG_NFS_V4
-
-static int nfs_atomic_open(struct inode *, struct dentry *,
-			   struct file *, unsigned, umode_t,
-			   int *);
-const struct inode_operations nfs4_dir_inode_operations = {
-	.create		= nfs_create,
-	.lookup		= nfs_lookup,
-	.atomic_open	= nfs_atomic_open,
-	.link		= nfs_link,
-	.unlink		= nfs_unlink,
-	.symlink	= nfs_symlink,
-	.mkdir		= nfs_mkdir,
-	.rmdir		= nfs_rmdir,
-	.mknod		= nfs_mknod,
-	.rename		= nfs_rename,
-	.permission	= nfs_permission,
-	.getattr	= nfs_getattr,
-	.setattr	= nfs_setattr,
-	.getxattr	= generic_getxattr,
-	.setxattr	= generic_setxattr,
-	.listxattr	= generic_listxattr,
-	.removexattr	= generic_removexattr,
-};
-
-#endif /* CONFIG_NFS_V4 */
-
 static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir, struct rpc_cred *cred)
 {
 	struct nfs_open_dir_context *ctx;
@@ -1008,6 +936,7 @@ void nfs_force_lookup_revalidate(struct inode *dir)
 {
 	NFS_I(dir)->cache_change_attribute++;
 }
+EXPORT_SYMBOL_GPL(nfs_force_lookup_revalidate);
 
 /*
  * A check for whether or not the parent directory has changed.
@@ -1128,7 +1057,7 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 		goto out_bad;
 	}
 
-	if (nfs_have_delegation(inode, FMODE_READ))
+	if (NFS_PROTO(dir)->have_delegation(inode, FMODE_READ))
 		goto out_set_verifier;
 
 	/* Force a full look up iff the parent directory has changed */
@@ -1269,8 +1198,9 @@ const struct dentry_operations nfs_dentry_operations = {
 	.d_automount	= nfs_d_automount,
 	.d_release	= nfs_d_release,
 };
+EXPORT_SYMBOL_GPL(nfs_dentry_operations);
 
-static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
+struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
 {
 	struct dentry *res;
 	struct dentry *parent;
@@ -1336,8 +1266,9 @@ out:
 	nfs_free_fhandle(fhandle);
 	return res;
 }
+EXPORT_SYMBOL_GPL(nfs_lookup);
 
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 static int nfs4_lookup_revalidate(struct dentry *, unsigned int);
 
 const struct dentry_operations nfs4_dentry_operations = {
@@ -1347,6 +1278,7 @@ const struct dentry_operations nfs4_dentry_operations = {
 	.d_automount	= nfs_d_automount,
 	.d_release	= nfs_d_release,
 };
+EXPORT_SYMBOL_GPL(nfs4_dentry_operations);
 
 static fmode_t flags_to_mode(int flags)
 {
@@ -1398,9 +1330,9 @@ out:
 	return err;
 }
 
-static int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
-			    struct file *file, unsigned open_flags,
-			    umode_t mode, int *opened)
+int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
+		    struct file *file, unsigned open_flags,
+		    umode_t mode, int *opened)
 {
 	struct nfs_open_context *ctx;
 	struct dentry *res;
@@ -1489,6 +1421,7 @@ no_open:
 
 	return finish_no_open(file, res);
 }
+EXPORT_SYMBOL_GPL(nfs_atomic_open);
 
 static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 {
@@ -1581,6 +1514,7 @@ out_error:
 	dput(parent);
 	return error;
 }
+EXPORT_SYMBOL_GPL(nfs_instantiate);
 
 /*
  * Following a failed create operation, we drop the dentry rather
@@ -1588,7 +1522,7 @@ out_error:
  * that the operation succeeded on the server, but an error in the
  * reply path made it appear to have failed.
  */
-static int nfs_create(struct inode *dir, struct dentry *dentry,
+int nfs_create(struct inode *dir, struct dentry *dentry,
 		umode_t mode, bool excl)
 {
 	struct iattr attr;
@@ -1609,11 +1543,12 @@ out_err:
 	d_drop(dentry);
 	return error;
 }
+EXPORT_SYMBOL_GPL(nfs_create);
 
 /*
  * See comments for nfs_proc_create regarding failed operations.
  */
-static int
+int
 nfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev)
 {
 	struct iattr attr;
@@ -1636,11 +1571,12 @@ out_err:
 	d_drop(dentry);
 	return status;
 }
+EXPORT_SYMBOL_GPL(nfs_mknod);
 
 /*
  * See comments for nfs_proc_create regarding failed operations.
  */
-static int nfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+int nfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 {
 	struct iattr attr;
 	int error;
@@ -1659,6 +1595,7 @@ out_err:
 	d_drop(dentry);
 	return error;
 }
+EXPORT_SYMBOL_GPL(nfs_mkdir);
 
 static void nfs_dentry_handle_enoent(struct dentry *dentry)
 {
@@ -1666,7 +1603,7 @@ static void nfs_dentry_handle_enoent(struct dentry *dentry)
 		d_delete(dentry);
 }
 
-static int nfs_rmdir(struct inode *dir, struct dentry *dentry)
+int nfs_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	int error;
 
@@ -1682,6 +1619,7 @@ static int nfs_rmdir(struct inode *dir, struct dentry *dentry)
 
 	return error;
 }
+EXPORT_SYMBOL_GPL(nfs_rmdir);
 
 /*
  * Remove a file after making sure there are no pending writes,
@@ -1706,7 +1644,7 @@ static int nfs_safe_remove(struct dentry *dentry)
 	}
 
 	if (inode != NULL) {
-		nfs_inode_return_delegation(inode);
+		NFS_PROTO(inode)->return_delegation(inode);
 		error = NFS_PROTO(dir)->remove(dir, &dentry->d_name);
 		/* The VFS may want to delete this inode */
 		if (error == 0)
@@ -1725,7 +1663,7 @@ out:
  *
  *  If sillyrename() returns 0, we do nothing, otherwise we unlink.
  */
-static int nfs_unlink(struct inode *dir, struct dentry *dentry)
+int nfs_unlink(struct inode *dir, struct dentry *dentry)
 {
 	int error;
 	int need_rehash = 0;
@@ -1753,6 +1691,7 @@ static int nfs_unlink(struct inode *dir, struct dentry *dentry)
 		d_rehash(dentry);
 	return error;
 }
+EXPORT_SYMBOL_GPL(nfs_unlink);
 
 /*
  * To create a symbolic link, most file systems instantiate a new inode,
@@ -1769,7 +1708,7 @@ static int nfs_unlink(struct inode *dir, struct dentry *dentry)
  * now have a new file handle and can instantiate an in-core NFS inode
  * and move the raw page into its mapping.
  */
-static int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
+int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
 {
 	struct pagevec lru_pvec;
 	struct page *page;
@@ -1823,8 +1762,9 @@ static int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *sym
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nfs_symlink);
 
-static int 
+int
 nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
 {
 	struct inode *inode = old_dentry->d_inode;
@@ -1834,7 +1774,7 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
 		old_dentry->d_parent->d_name.name, old_dentry->d_name.name,
 		dentry->d_parent->d_name.name, dentry->d_name.name);
 
-	nfs_inode_return_delegation(inode);
+	NFS_PROTO(inode)->return_delegation(inode);
 
 	d_drop(dentry);
 	error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name);
@@ -1844,6 +1784,7 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
 	}
 	return error;
 }
+EXPORT_SYMBOL_GPL(nfs_link);
 
 /*
  * RENAME
@@ -1869,7 +1810,7 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
  * If these conditions are met, we can drop the dentries before doing
  * the rename.
  */
-static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		      struct inode *new_dir, struct dentry *new_dentry)
 {
 	struct inode *old_inode = old_dentry->d_inode;
@@ -1918,9 +1859,9 @@ static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		}
 	}
 
-	nfs_inode_return_delegation(old_inode);
+	NFS_PROTO(old_inode)->return_delegation(old_inode);
 	if (new_inode != NULL)
-		nfs_inode_return_delegation(new_inode);
+		NFS_PROTO(new_inode)->return_delegation(new_inode);
 
 	error = NFS_PROTO(old_dir)->rename(old_dir, &old_dentry->d_name,
 					   new_dir, &new_dentry->d_name);
@@ -1942,6 +1883,7 @@ out:
 		dput(dentry);
 	return error;
 }
+EXPORT_SYMBOL_GPL(nfs_rename);
 
 static DEFINE_SPINLOCK(nfs_access_lru_lock);
 static LIST_HEAD(nfs_access_lru_list);
@@ -2042,6 +1984,7 @@ void nfs_access_zap_cache(struct inode *inode)
 	spin_unlock(&nfs_access_lru_lock);
 	nfs_access_free_list(&head);
 }
+EXPORT_SYMBOL_GPL(nfs_access_zap_cache);
 
 static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, struct rpc_cred *cred)
 {
@@ -2202,6 +2145,7 @@ int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags)
 {
 	return nfs_do_access(inode, cred, nfs_open_permission_mask(openflags));
 }
+EXPORT_SYMBOL_GPL(nfs_may_open);
 
 int nfs_permission(struct inode *inode, int mask)
 {
@@ -2261,6 +2205,7 @@ out_notsup:
 		res = generic_permission(inode, mask);
 	goto out;
 }
+EXPORT_SYMBOL_GPL(nfs_permission);
 
 /*
  * Local variables:
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 48253372ab1d..1ba385b7c90d 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -115,17 +115,28 @@ static inline int put_dreq(struct nfs_direct_req *dreq)
  * @nr_segs: size of iovec array
  *
  * The presence of this routine in the address space ops vector means
- * the NFS client supports direct I/O.  However, we shunt off direct
- * read and write requests before the VFS gets them, so this method
- * should never be called.
+ * the NFS client supports direct I/O. However, for most direct IO, we
+ * shunt off direct read and write requests before the VFS gets them,
+ * so this method is only ever called for swap.
  */
 ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t pos, unsigned long nr_segs)
 {
+#ifndef CONFIG_NFS_SWAP
 	dprintk("NFS: nfs_direct_IO (%s) off/no(%Ld/%lu) EINVAL\n",
 			iocb->ki_filp->f_path.dentry->d_name.name,
 			(long long) pos, nr_segs);
 
 	return -EINVAL;
+#else
+	VM_BUG_ON(iocb->ki_left != PAGE_SIZE);
+	VM_BUG_ON(iocb->ki_nbytes != PAGE_SIZE);
+
+	if (rw == READ || rw == KERNEL_READ)
+		return nfs_file_direct_read(iocb, iov, nr_segs, pos,
+				rw == READ ? true : false);
+	return nfs_file_direct_write(iocb, iov, nr_segs, pos,
+				rw == WRITE ? true : false);
+#endif /* CONFIG_NFS_SWAP */
 }
 
 static void nfs_direct_release_pages(struct page **pages, unsigned int npages)
@@ -303,7 +314,7 @@ static const struct nfs_pgio_completion_ops nfs_direct_read_completion_ops = {
  */
 static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *desc,
 						const struct iovec *iov,
-						loff_t pos)
+						loff_t pos, bool uio)
 {
 	struct nfs_direct_req *dreq = desc->pg_dreq;
 	struct nfs_open_context *ctx = dreq->ctx;
@@ -331,12 +342,20 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *de
 					  GFP_KERNEL);
 		if (!pagevec)
 			break;
-		down_read(&current->mm->mmap_sem);
-		result = get_user_pages(current, current->mm, user_addr,
+		if (uio) {
+			down_read(&current->mm->mmap_sem);
+			result = get_user_pages(current, current->mm, user_addr,
 					npages, 1, 0, pagevec, NULL);
-		up_read(&current->mm->mmap_sem);
-		if (result < 0)
-			break;
+			up_read(&current->mm->mmap_sem);
+			if (result < 0)
+				break;
+		} else {
+			WARN_ON(npages != 1);
+			result = get_kernel_page(user_addr, 1, pagevec);
+			if (WARN_ON(result != 1))
+				break;
+		}
+
 		if ((unsigned)result < npages) {
 			bytes = result * PAGE_SIZE;
 			if (bytes <= pgbase) {
@@ -386,21 +405,21 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *de
 static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 					      const struct iovec *iov,
 					      unsigned long nr_segs,
-					      loff_t pos)
+					      loff_t pos, bool uio)
 {
 	struct nfs_pageio_descriptor desc;
 	ssize_t result = -EINVAL;
 	size_t requested_bytes = 0;
 	unsigned long seg;
 
-	nfs_pageio_init_read(&desc, dreq->inode,
+	NFS_PROTO(dreq->inode)->read_pageio_init(&desc, dreq->inode,
 			     &nfs_direct_read_completion_ops);
 	get_dreq(dreq);
 	desc.pg_dreq = dreq;
 
 	for (seg = 0; seg < nr_segs; seg++) {
 		const struct iovec *vec = &iov[seg];
-		result = nfs_direct_read_schedule_segment(&desc, vec, pos);
+		result = nfs_direct_read_schedule_segment(&desc, vec, pos, uio);
 		if (result < 0)
 			break;
 		requested_bytes += result;
@@ -426,7 +445,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 }
 
 static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov,
-			       unsigned long nr_segs, loff_t pos)
+			       unsigned long nr_segs, loff_t pos, bool uio)
 {
 	ssize_t result = -ENOMEM;
 	struct inode *inode = iocb->ki_filp->f_mapping->host;
@@ -444,7 +463,7 @@ static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov,
 	if (!is_sync_kiocb(iocb))
 		dreq->iocb = iocb;
 
-	result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos);
+	result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos, uio);
 	if (!result)
 		result = nfs_direct_wait(dreq);
 	NFS_I(inode)->read_io += result;
@@ -460,7 +479,7 @@ static void nfs_inode_dio_write_done(struct inode *inode)
 	inode_dio_done(inode);
 }
 
-#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
+#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 {
 	struct nfs_pageio_descriptor desc;
@@ -478,7 +497,7 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 	dreq->count = 0;
 	get_dreq(dreq);
 
-	nfs_pageio_init_write(&desc, dreq->inode, FLUSH_STABLE,
+	NFS_PROTO(dreq->inode)->write_pageio_init(&desc, dreq->inode, FLUSH_STABLE,
 			      &nfs_direct_write_completion_ops);
 	desc.pg_dreq = dreq;
 
@@ -610,7 +629,7 @@ static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode
  */
 static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *desc,
 						 const struct iovec *iov,
-						 loff_t pos)
+						 loff_t pos, bool uio)
 {
 	struct nfs_direct_req *dreq = desc->pg_dreq;
 	struct nfs_open_context *ctx = dreq->ctx;
@@ -638,12 +657,19 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *d
 		if (!pagevec)
 			break;
 
-		down_read(&current->mm->mmap_sem);
-		result = get_user_pages(current, current->mm, user_addr,
-					npages, 0, 0, pagevec, NULL);
-		up_read(&current->mm->mmap_sem);
-		if (result < 0)
-			break;
+		if (uio) {
+			down_read(&current->mm->mmap_sem);
+			result = get_user_pages(current, current->mm, user_addr,
+						npages, 0, 0, pagevec, NULL);
+			up_read(&current->mm->mmap_sem);
+			if (result < 0)
+				break;
+		} else {
+			WARN_ON(npages != 1);
+			result = get_kernel_page(user_addr, 0, pagevec);
+			if (WARN_ON(result != 1))
+				break;
+		}
 
 		if ((unsigned)result < npages) {
 			bytes = result * PAGE_SIZE;
@@ -774,7 +800,7 @@ static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = {
 static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 					       const struct iovec *iov,
 					       unsigned long nr_segs,
-					       loff_t pos)
+					       loff_t pos, bool uio)
 {
 	struct nfs_pageio_descriptor desc;
 	struct inode *inode = dreq->inode;
@@ -782,7 +808,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 	size_t requested_bytes = 0;
 	unsigned long seg;
 
-	nfs_pageio_init_write(&desc, inode, FLUSH_COND_STABLE,
+	NFS_PROTO(inode)->write_pageio_init(&desc, inode, FLUSH_COND_STABLE,
 			      &nfs_direct_write_completion_ops);
 	desc.pg_dreq = dreq;
 	get_dreq(dreq);
@@ -790,7 +816,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 
 	for (seg = 0; seg < nr_segs; seg++) {
 		const struct iovec *vec = &iov[seg];
-		result = nfs_direct_write_schedule_segment(&desc, vec, pos);
+		result = nfs_direct_write_schedule_segment(&desc, vec, pos, uio);
 		if (result < 0)
 			break;
 		requested_bytes += result;
@@ -818,7 +844,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 
 static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov,
 				unsigned long nr_segs, loff_t pos,
-				size_t count)
+				size_t count, bool uio)
 {
 	ssize_t result = -ENOMEM;
 	struct inode *inode = iocb->ki_filp->f_mapping->host;
@@ -836,7 +862,7 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov,
 	if (!is_sync_kiocb(iocb))
 		dreq->iocb = iocb;
 
-	result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos);
+	result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos, uio);
 	if (!result)
 		result = nfs_direct_wait(dreq);
 out_release:
@@ -867,7 +893,7 @@ out:
  * cache.
  */
 ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos)
+				unsigned long nr_segs, loff_t pos, bool uio)
 {
 	ssize_t retval = -EINVAL;
 	struct file *file = iocb->ki_filp;
@@ -892,7 +918,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
 
 	task_io_account_read(count);
 
-	retval = nfs_direct_read(iocb, iov, nr_segs, pos);
+	retval = nfs_direct_read(iocb, iov, nr_segs, pos, uio);
 	if (retval > 0)
 		iocb->ki_pos = pos + retval;
 
@@ -923,7 +949,7 @@ out:
  * is no atomic O_APPEND write facility in the NFS protocol.
  */
 ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos)
+				unsigned long nr_segs, loff_t pos, bool uio)
 {
 	ssize_t retval = -EINVAL;
 	struct file *file = iocb->ki_filp;
@@ -955,7 +981,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 
 	task_io_account_write(count);
 
-	retval = nfs_direct_write(iocb, iov, nr_segs, pos, count);
+	retval = nfs_direct_write(iocb, iov, nr_segs, pos, count, uio);
 	if (retval > 0) {
 		struct inode *inode = mapping->host;
 
diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c
index b3924b8a6000..31c26c4dcc23 100644
--- a/fs/nfs/dns_resolve.c
+++ b/fs/nfs/dns_resolve.c
@@ -8,6 +8,7 @@
 
 #ifdef CONFIG_NFS_USE_KERNEL_DNS
 
+#include <linux/module.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/dns_resolver.h>
 #include "dns_resolve.h"
@@ -27,9 +28,11 @@ ssize_t nfs_dns_resolve_name(struct net *net, char *name, size_t namelen,
 	kfree(ip_addr);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(nfs_dns_resolve_name);
 
 #else
 
+#include <linux/module.h>
 #include <linux/hash.h>
 #include <linux/string.h>
 #include <linux/kmod.h>
@@ -345,6 +348,7 @@ ssize_t nfs_dns_resolve_name(struct net *net, char *name,
 		ret = -ESRCH;
 	return ret;
 }
+EXPORT_SYMBOL_GPL(nfs_dns_resolve_name);
 
 int nfs_dns_resolver_cache_init(struct net *net)
 {
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index a6708e6b438d..75d6d0a3d32e 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -16,6 +16,7 @@
  *  nfs regular file handling functions
  */
 
+#include <linux/module.h>
 #include <linux/time.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
@@ -35,42 +36,24 @@
 #include "internal.h"
 #include "iostat.h"
 #include "fscache.h"
-#include "pnfs.h"
 
 #define NFSDBG_FACILITY		NFSDBG_FILE
 
 static const struct vm_operations_struct nfs_file_vm_ops;
 
-const struct inode_operations nfs_file_inode_operations = {
-	.permission	= nfs_permission,
-	.getattr	= nfs_getattr,
-	.setattr	= nfs_setattr,
-};
-
-#ifdef CONFIG_NFS_V3
-const struct inode_operations nfs3_file_inode_operations = {
-	.permission	= nfs_permission,
-	.getattr	= nfs_getattr,
-	.setattr	= nfs_setattr,
-	.listxattr	= nfs3_listxattr,
-	.getxattr	= nfs3_getxattr,
-	.setxattr	= nfs3_setxattr,
-	.removexattr	= nfs3_removexattr,
-};
-#endif  /* CONFIG_NFS_v3 */
-
 /* Hack for future NFS swap support */
 #ifndef IS_SWAPFILE
 # define IS_SWAPFILE(inode)	(0)
 #endif
 
-static int nfs_check_flags(int flags)
+int nfs_check_flags(int flags)
 {
 	if ((flags & (O_APPEND | O_DIRECT)) == (O_APPEND | O_DIRECT))
 		return -EINVAL;
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nfs_check_flags);
 
 /*
  * Open file
@@ -93,7 +76,7 @@ nfs_file_open(struct inode *inode, struct file *filp)
 	return res;
 }
 
-static int
+int
 nfs_file_release(struct inode *inode, struct file *filp)
 {
 	dprintk("NFS: release(%s/%s)\n",
@@ -103,6 +86,7 @@ nfs_file_release(struct inode *inode, struct file *filp)
 	nfs_inc_stats(inode, NFSIOS_VFSRELEASE);
 	return nfs_release(inode, filp);
 }
+EXPORT_SYMBOL_GPL(nfs_file_release);
 
 /**
  * nfs_revalidate_size - Revalidate the file size
@@ -135,7 +119,7 @@ force_reval:
 	return __nfs_revalidate_inode(server, inode);
 }
 
-static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
+loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
 {
 	dprintk("NFS: llseek file(%s/%s, %lld, %d)\n",
 			filp->f_path.dentry->d_parent->d_name.name,
@@ -156,11 +140,12 @@ static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
 
 	return generic_file_llseek(filp, offset, origin);
 }
+EXPORT_SYMBOL_GPL(nfs_file_llseek);
 
 /*
  * Flush all dirty pages, and check for write errors.
  */
-static int
+int
 nfs_file_flush(struct file *file, fl_owner_t id)
 {
 	struct dentry	*dentry = file->f_path.dentry;
@@ -178,14 +163,15 @@ nfs_file_flush(struct file *file, fl_owner_t id)
 	 * If we're holding a write delegation, then just start the i/o
 	 * but don't wait for completion (or send a commit).
 	 */
-	if (nfs_have_delegation(inode, FMODE_WRITE))
+	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
 		return filemap_fdatawrite(file->f_mapping);
 
 	/* Flush writes to the server and return any errors */
 	return vfs_fsync(file, 0);
 }
+EXPORT_SYMBOL_GPL(nfs_file_flush);
 
-static ssize_t
+ssize_t
 nfs_file_read(struct kiocb *iocb, const struct iovec *iov,
 		unsigned long nr_segs, loff_t pos)
 {
@@ -194,7 +180,7 @@ nfs_file_read(struct kiocb *iocb, const struct iovec *iov,
 	ssize_t result;
 
 	if (iocb->ki_filp->f_flags & O_DIRECT)
-		return nfs_file_direct_read(iocb, iov, nr_segs, pos);
+		return nfs_file_direct_read(iocb, iov, nr_segs, pos, true);
 
 	dprintk("NFS: read(%s/%s, %lu@%lu)\n",
 		dentry->d_parent->d_name.name, dentry->d_name.name,
@@ -208,8 +194,9 @@ nfs_file_read(struct kiocb *iocb, const struct iovec *iov,
 	}
 	return result;
 }
+EXPORT_SYMBOL_GPL(nfs_file_read);
 
-static ssize_t
+ssize_t
 nfs_file_splice_read(struct file *filp, loff_t *ppos,
 		     struct pipe_inode_info *pipe, size_t count,
 		     unsigned int flags)
@@ -230,8 +217,9 @@ nfs_file_splice_read(struct file *filp, loff_t *ppos,
 	}
 	return res;
 }
+EXPORT_SYMBOL_GPL(nfs_file_splice_read);
 
-static int
+int
 nfs_file_mmap(struct file * file, struct vm_area_struct * vma)
 {
 	struct dentry *dentry = file->f_path.dentry;
@@ -251,6 +239,7 @@ nfs_file_mmap(struct file * file, struct vm_area_struct * vma)
 	}
 	return status;
 }
+EXPORT_SYMBOL_GPL(nfs_file_mmap);
 
 /*
  * Flush any dirty pages for this process, and check for write errors.
@@ -264,8 +253,8 @@ nfs_file_mmap(struct file * file, struct vm_area_struct * vma)
  * nfs_file_write() that a write error occurred, and hence cause it to
  * fall back to doing a synchronous write.
  */
-static int
-nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
+int
+nfs_file_fsync_commit(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	struct dentry *dentry = file->f_path.dentry;
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
@@ -277,9 +266,6 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 			dentry->d_parent->d_name.name, dentry->d_name.name,
 			datasync);
 
-	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
-	mutex_lock(&inode->i_mutex);
-
 	nfs_inc_stats(inode, NFSIOS_VFSFSYNC);
 	have_error = test_and_clear_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
 	status = nfs_commit_inode(inode, FLUSH_SYNC);
@@ -290,10 +276,21 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 		ret = xchg(&ctx->error, 0);
 	if (!ret && status < 0)
 		ret = status;
-	if (!ret && !datasync)
-		/* application has asked for meta-data sync */
-		ret = pnfs_layoutcommit_inode(inode, true);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nfs_file_fsync_commit);
+
+static int
+nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
+{
+	int ret;
+	struct inode *inode = file->f_path.dentry->d_inode;
+
+	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
+	mutex_lock(&inode->i_mutex);
+	ret = nfs_file_fsync_commit(file, start, end, datasync);
 	mutex_unlock(&inode->i_mutex);
+
 	return ret;
 }
 
@@ -442,7 +439,7 @@ static void nfs_invalidate_page(struct page *page, unsigned long offset)
 	if (offset != 0)
 		return;
 	/* Cancel any unstarted writes on this page */
-	nfs_wb_page_cancel(page->mapping->host, page);
+	nfs_wb_page_cancel(page_file_mapping(page)->host, page);
 
 	nfs_fscache_invalidate_page(page, page->mapping->host);
 }
@@ -459,8 +456,11 @@ static int nfs_release_page(struct page *page, gfp_t gfp)
 
 	dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page);
 
-	/* Only do I/O if gfp is a superset of GFP_KERNEL */
-	if (mapping && (gfp & GFP_KERNEL) == GFP_KERNEL) {
+	/* Only do I/O if gfp is a superset of GFP_KERNEL, and we're not
+	 * doing this memory reclaim for a fs-related allocation.
+	 */
+	if (mapping && (gfp & GFP_KERNEL) == GFP_KERNEL &&
+	    !(current->flags & PF_FSTRANS)) {
 		int how = FLUSH_SYNC;
 
 		/* Don't let kswapd deadlock waiting for OOM RPC calls */
@@ -484,7 +484,7 @@ static int nfs_release_page(struct page *page, gfp_t gfp)
  */
 static int nfs_launder_page(struct page *page)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	struct nfs_inode *nfsi = NFS_I(inode);
 
 	dfprintk(PAGECACHE, "NFS: launder_page(%ld, %llu)\n",
@@ -494,6 +494,20 @@ static int nfs_launder_page(struct page *page)
 	return nfs_wb_page(inode, page);
 }
 
+#ifdef CONFIG_NFS_SWAP
+static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,
+						sector_t *span)
+{
+	*span = sis->pages;
+	return xs_swapper(NFS_CLIENT(file->f_mapping->host)->cl_xprt, 1);
+}
+
+static void nfs_swap_deactivate(struct file *file)
+{
+	xs_swapper(NFS_CLIENT(file->f_mapping->host)->cl_xprt, 0);
+}
+#endif
+
 const struct address_space_operations nfs_file_aops = {
 	.readpage = nfs_readpage,
 	.readpages = nfs_readpages,
@@ -508,6 +522,10 @@ const struct address_space_operations nfs_file_aops = {
 	.migratepage = nfs_migrate_page,
 	.launder_page = nfs_launder_page,
 	.error_remove_page = generic_error_remove_page,
+#ifdef CONFIG_NFS_SWAP
+	.swap_activate = nfs_swap_activate,
+	.swap_deactivate = nfs_swap_deactivate,
+#endif
 };
 
 /*
@@ -533,7 +551,7 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	nfs_fscache_wait_on_page_write(NFS_I(dentry->d_inode), page);
 
 	lock_page(page);
-	mapping = page->mapping;
+	mapping = page_file_mapping(page);
 	if (mapping != dentry->d_inode->i_mapping)
 		goto out_unlock;
 
@@ -572,8 +590,8 @@ static int nfs_need_sync_write(struct file *filp, struct inode *inode)
 	return 0;
 }
 
-static ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos)
+ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
+		       unsigned long nr_segs, loff_t pos)
 {
 	struct dentry * dentry = iocb->ki_filp->f_path.dentry;
 	struct inode * inode = dentry->d_inode;
@@ -582,7 +600,7 @@ static ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
 	size_t count = iov_length(iov, nr_segs);
 
 	if (iocb->ki_filp->f_flags & O_DIRECT)
-		return nfs_file_direct_write(iocb, iov, nr_segs, pos);
+		return nfs_file_direct_write(iocb, iov, nr_segs, pos, true);
 
 	dprintk("NFS: write(%s/%s, %lu@%Ld)\n",
 		dentry->d_parent->d_name.name, dentry->d_name.name,
@@ -623,10 +641,11 @@ out_swapfile:
 	printk(KERN_INFO "NFS: attempt to write to active swap file!\n");
 	goto out;
 }
+EXPORT_SYMBOL_GPL(nfs_file_write);
 
-static ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe,
-				     struct file *filp, loff_t *ppos,
-				     size_t count, unsigned int flags)
+ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe,
+			      struct file *filp, loff_t *ppos,
+			      size_t count, unsigned int flags)
 {
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
@@ -654,6 +673,7 @@ static ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe,
 		nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(nfs_file_splice_write);
 
 static int
 do_getlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
@@ -670,7 +690,7 @@ do_getlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 	}
 	fl->fl_type = saved_type;
 
-	if (nfs_have_delegation(inode, FMODE_READ))
+	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
 		goto out_noconflict;
 
 	if (is_local)
@@ -765,7 +785,7 @@ do_setlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 	 * This makes locking act as a cache coherency point.
 	 */
 	nfs_sync_mapping(filp->f_mapping);
-	if (!nfs_have_delegation(inode, FMODE_READ)) {
+	if (!NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) {
 		if (is_time_granular(&NFS_SERVER(inode)->time_delta))
 			__nfs_revalidate_inode(NFS_SERVER(inode), inode);
 		else
@@ -778,7 +798,7 @@ out:
 /*
  * Lock a (portion of) a file
  */
-static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
+int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
 {
 	struct inode *inode = filp->f_mapping->host;
 	int ret = -ENOLCK;
@@ -814,11 +834,12 @@ static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
 out_err:
 	return ret;
 }
+EXPORT_SYMBOL_GPL(nfs_lock);
 
 /*
  * Lock a (portion of) a file
  */
-static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
+int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
 {
 	struct inode *inode = filp->f_mapping->host;
 	int is_local = 0;
@@ -831,6 +852,15 @@ static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
 	if (!(fl->fl_flags & FL_FLOCK))
 		return -ENOLCK;
 
+	/*
+	 * The NFSv4 protocol doesn't support LOCK_MAND, which is not part of
+	 * any standard. In principle we might be able to support LOCK_MAND
+	 * on NFSv2/3 since NLMv3/4 support DOS share modes, but for now the
+	 * NFS code is not set up for it.
+	 */
+	if (fl->fl_type & LOCK_MAND)
+		return -EINVAL;
+
 	if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FLOCK)
 		is_local = 1;
 
@@ -843,18 +873,20 @@ static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
 		return do_unlk(filp, cmd, fl, is_local);
 	return do_setlk(filp, cmd, fl, is_local);
 }
+EXPORT_SYMBOL_GPL(nfs_flock);
 
 /*
  * There is no protocol support for leases, so we have no way to implement
  * them correctly in the face of opens by other clients.
  */
-static int nfs_setlease(struct file *file, long arg, struct file_lock **fl)
+int nfs_setlease(struct file *file, long arg, struct file_lock **fl)
 {
 	dprintk("NFS: setlease(%s/%s, arg=%ld)\n",
 			file->f_path.dentry->d_parent->d_name.name,
 			file->f_path.dentry->d_name.name, arg);
 	return -EINVAL;
 }
+EXPORT_SYMBOL_GPL(nfs_setlease);
 
 const struct file_operations nfs_file_operations = {
 	.llseek		= nfs_file_llseek,
@@ -874,104 +906,4 @@ const struct file_operations nfs_file_operations = {
 	.check_flags	= nfs_check_flags,
 	.setlease	= nfs_setlease,
 };
-
-#ifdef CONFIG_NFS_V4
-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 *parent = NULL;
-	struct inode *dir;
-	unsigned openflags = filp->f_flags;
-	struct iattr attr;
-	int err;
-
-	BUG_ON(inode != dentry->d_inode);
-	/*
-	 * If no cached dentry exists or if it's negative, NFSv4 handled the
-	 * opens in ->lookup() or ->create().
-	 *
-	 * We only get this far for a cached positive dentry.  We skipped
-	 * revalidation, so handle it here by dropping the dentry and returning
-	 * -EOPENSTALE.  The VFS will retry the lookup/create/open.
-	 */
-
-	dprintk("NFS: open file(%s/%s)\n",
-		dentry->d_parent->d_name.name,
-		dentry->d_name.name);
-
-	if ((openflags & O_ACCMODE) == 3)
-		openflags--;
-
-	/* We can't create new files here */
-	openflags &= ~(O_CREAT|O_EXCL);
-
-	parent = dget_parent(dentry);
-	dir = parent->d_inode;
-
-	ctx = alloc_nfs_open_context(filp->f_path.dentry, filp->f_mode);
-	err = PTR_ERR(ctx);
-	if (IS_ERR(ctx))
-		goto out;
-
-	attr.ia_valid = ATTR_OPEN;
-	if (openflags & O_TRUNC) {
-		attr.ia_valid |= ATTR_SIZE;
-		attr.ia_size = 0;
-		nfs_wb_all(inode);
-	}
-
-	inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr);
-	if (IS_ERR(inode)) {
-		err = PTR_ERR(inode);
-		switch (err) {
-		case -EPERM:
-		case -EACCES:
-		case -EDQUOT:
-		case -ENOSPC:
-		case -EROFS:
-			goto out_put_ctx;
-		default:
-			goto out_drop;
-		}
-	}
-	iput(inode);
-	if (inode != dentry->d_inode)
-		goto out_drop;
-
-	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
-	nfs_file_set_open_context(filp, ctx);
-	err = 0;
-
-out_put_ctx:
-	put_nfs_open_context(ctx);
-out:
-	dput(parent);
-	return err;
-
-out_drop:
-	d_drop(dentry);
-	err = -EOPENSTALE;
-	goto out_put_ctx;
-}
-
-const struct file_operations nfs4_file_operations = {
-	.llseek		= nfs_file_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-	.aio_read	= nfs_file_read,
-	.aio_write	= nfs_file_write,
-	.mmap		= nfs_file_mmap,
-	.open		= nfs4_file_open,
-	.flush		= nfs_file_flush,
-	.release	= nfs_file_release,
-	.fsync		= nfs_file_fsync,
-	.lock		= nfs_lock,
-	.flock		= nfs_flock,
-	.splice_read	= nfs_file_splice_read,
-	.splice_write	= nfs_file_splice_write,
-	.check_flags	= nfs_check_flags,
-	.setlease	= nfs_setlease,
-};
-#endif /* CONFIG_NFS_V4 */
+EXPORT_SYMBOL_GPL(nfs_file_operations);
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index a67990f90bd7..4654ced096a6 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -23,21 +23,15 @@
 #include <linux/sunrpc/stats.h>
 #include <linux/nfs_fs.h>
 #include <linux/nfs_mount.h>
-#include <linux/nfs4_mount.h>
 #include <linux/lockd/bind.h>
 #include <linux/seq_file.h>
 #include <linux/mount.h>
-#include <linux/nfs_idmap.h>
 #include <linux/vfs.h>
 #include <linux/namei.h>
 #include <linux/security.h>
 
 #include <asm/uaccess.h>
 
-#include "nfs4_fs.h"
-#include "delegation.h"
-#include "internal.h"
-
 #define NFSDBG_FACILITY		NFSDBG_CLIENT
 
 /*
@@ -135,47 +129,3 @@ out:
 	nfs_free_fattr(fsinfo.fattr);
 	return ret;
 }
-
-#ifdef CONFIG_NFS_V4
-
-int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh)
-{
-	struct nfs_fsinfo fsinfo;
-	int ret = -ENOMEM;
-
-	dprintk("--> nfs4_get_rootfh()\n");
-
-	fsinfo.fattr = nfs_alloc_fattr();
-	if (fsinfo.fattr == NULL)
-		goto out;
-
-	/* Start by getting the root filehandle from the server */
-	ret = nfs4_proc_get_rootfh(server, mntfh, &fsinfo);
-	if (ret < 0) {
-		dprintk("nfs4_get_rootfh: getroot error = %d\n", -ret);
-		goto out;
-	}
-
-	if (!(fsinfo.fattr->valid & NFS_ATTR_FATTR_TYPE)
-			|| !S_ISDIR(fsinfo.fattr->mode)) {
-		printk(KERN_ERR "nfs4_get_rootfh:"
-		       " getroot encountered non-directory\n");
-		ret = -ENOTDIR;
-		goto out;
-	}
-
-	if (fsinfo.fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) {
-		printk(KERN_ERR "nfs4_get_rootfh:"
-		       " getroot obtained referral\n");
-		ret = -EREMOTE;
-		goto out;
-	}
-
-	memcpy(&server->fsid, &fsinfo.fattr->fsid, sizeof(server->fsid));
-out:
-	nfs_free_fattr(fsinfo.fattr);
-	dprintk("<-- nfs4_get_rootfh() = %d\n", ret);
-	return ret;
-}
-
-#endif /* CONFIG_NFS_V4 */
diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c
index 864c51e4b400..b701358c39c3 100644
--- a/fs/nfs/idmap.c
+++ b/fs/nfs/idmap.c
@@ -52,8 +52,6 @@
 
 #define NFS_UINT_MAXLEN 11
 
-/* Default cache timeout is 10 minutes */
-unsigned int nfs_idmap_cache_timeout = 600;
 static const struct cred *id_resolver_cache;
 static struct key_type key_type_id_resolver_legacy;
 
@@ -205,12 +203,18 @@ static int nfs_idmap_init_keyring(void)
 	if (ret < 0)
 		goto failed_put_key;
 
+	ret = register_key_type(&key_type_id_resolver_legacy);
+	if (ret < 0)
+		goto failed_reg_legacy;
+
 	set_bit(KEY_FLAG_ROOT_CAN_CLEAR, &keyring->flags);
 	cred->thread_keyring = keyring;
 	cred->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING;
 	id_resolver_cache = cred;
 	return 0;
 
+failed_reg_legacy:
+	unregister_key_type(&key_type_id_resolver);
 failed_put_key:
 	key_put(keyring);
 failed_put_cred:
@@ -222,6 +226,7 @@ static void nfs_idmap_quit_keyring(void)
 {
 	key_revoke(id_resolver_cache->thread_keyring);
 	unregister_key_type(&key_type_id_resolver);
+	unregister_key_type(&key_type_id_resolver_legacy);
 	put_cred(id_resolver_cache);
 }
 
@@ -359,7 +364,6 @@ static int nfs_idmap_lookup_id(const char *name, size_t namelen, const char *typ
 }
 
 /* idmap classic begins here */
-module_param(nfs_idmap_cache_timeout, int, 0644);
 
 enum {
 	Opt_find_uid, Opt_find_gid, Opt_find_user, Opt_find_group, Opt_find_err
@@ -385,7 +389,7 @@ static const struct rpc_pipe_ops idmap_upcall_ops = {
 };
 
 static struct key_type key_type_id_resolver_legacy = {
-	.name		= "id_resolver",
+	.name		= "id_legacy",
 	.instantiate	= user_instantiate,
 	.match		= user_match,
 	.revoke		= user_revoke,
@@ -674,6 +678,7 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons,
 	if (ret < 0)
 		goto out2;
 
+	BUG_ON(idmap->idmap_key_cons != NULL);
 	idmap->idmap_key_cons = cons;
 
 	ret = rpc_queue_upcall(idmap->idmap_pipe, msg);
@@ -687,8 +692,7 @@ out2:
 out1:
 	kfree(msg);
 out0:
-	key_revoke(cons->key);
-	key_revoke(cons->authkey);
+	complete_request_key(cons, ret);
 	return ret;
 }
 
@@ -722,11 +726,18 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
 {
 	struct rpc_inode *rpci = RPC_I(filp->f_path.dentry->d_inode);
 	struct idmap *idmap = (struct idmap *)rpci->private;
-	struct key_construction *cons = idmap->idmap_key_cons;
+	struct key_construction *cons;
 	struct idmap_msg im;
 	size_t namelen_in;
 	int ret;
 
+	/* If instantiation is successful, anyone waiting for key construction
+	 * will have been woken up and someone else may now have used
+	 * idmap_key_cons - so after this point we may no longer touch it.
+	 */
+	cons = ACCESS_ONCE(idmap->idmap_key_cons);
+	idmap->idmap_key_cons = NULL;
+
 	if (mlen != sizeof(im)) {
 		ret = -ENOSPC;
 		goto out;
@@ -739,7 +750,7 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
 
 	if (!(im.im_status & IDMAP_STATUS_SUCCESS)) {
 		ret = mlen;
-		complete_request_key(idmap->idmap_key_cons, -ENOKEY);
+		complete_request_key(cons, -ENOKEY);
 		goto out_incomplete;
 	}
 
@@ -756,7 +767,7 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
 	}
 
 out:
-	complete_request_key(idmap->idmap_key_cons, ret);
+	complete_request_key(cons, ret);
 out_incomplete:
 	return ret;
 }
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index f7296983eba6..c6e895f0fbf3 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -32,7 +32,6 @@
 #include <linux/lockd/bind.h>
 #include <linux/seq_file.h>
 #include <linux/mount.h>
-#include <linux/nfs_idmap.h>
 #include <linux/vfs.h>
 #include <linux/inet.h>
 #include <linux/nfs_xdr.h>
@@ -51,6 +50,7 @@
 #include "fscache.h"
 #include "dns_resolve.h"
 #include "pnfs.h"
+#include "nfs.h"
 #include "netns.h"
 
 #define NFSDBG_FACILITY		NFSDBG_VFS
@@ -82,6 +82,7 @@ int nfs_wait_bit_killable(void *word)
 	freezable_schedule();
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nfs_wait_bit_killable);
 
 /**
  * nfs_compat_user_ino64 - returns the user-visible inode number
@@ -106,7 +107,7 @@ u64 nfs_compat_user_ino64(u64 fileid)
 	return ino;
 }
 
-static void nfs_clear_inode(struct inode *inode)
+void nfs_clear_inode(struct inode *inode)
 {
 	/*
 	 * The following should never happen...
@@ -117,6 +118,7 @@ static void nfs_clear_inode(struct inode *inode)
 	nfs_access_zap_cache(inode);
 	nfs_fscache_release_inode_cookie(inode);
 }
+EXPORT_SYMBOL_GPL(nfs_clear_inode);
 
 void nfs_evict_inode(struct inode *inode)
 {
@@ -186,6 +188,7 @@ void nfs_zap_acl_cache(struct inode *inode)
 	NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_ACL;
 	spin_unlock(&inode->i_lock);
 }
+EXPORT_SYMBOL_GPL(nfs_zap_acl_cache);
 
 void nfs_invalidate_atime(struct inode *inode)
 {
@@ -193,6 +196,7 @@ void nfs_invalidate_atime(struct inode *inode)
 	NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATIME;
 	spin_unlock(&inode->i_lock);
 }
+EXPORT_SYMBOL_GPL(nfs_invalidate_atime);
 
 /*
  * Invalidate, but do not unhash, the inode.
@@ -391,6 +395,7 @@ out_no_inode:
 	dprintk("nfs_fhget: iget failed with error %ld\n", PTR_ERR(inode));
 	goto out;
 }
+EXPORT_SYMBOL_GPL(nfs_fhget);
 
 #define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET|ATTR_FILE|ATTR_OPEN)
 
@@ -430,7 +435,7 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr)
 	 * Return any delegations if we're going to change ACLs
 	 */
 	if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0)
-		nfs_inode_return_delegation(inode);
+		NFS_PROTO(inode)->return_delegation(inode);
 	error = NFS_PROTO(inode)->setattr(dentry, fattr, attr);
 	if (error == 0)
 		nfs_refresh_inode(inode, fattr);
@@ -438,6 +443,7 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr)
 out:
 	return error;
 }
+EXPORT_SYMBOL_GPL(nfs_setattr);
 
 /**
  * nfs_vmtruncate - unmap mappings "freed" by truncate() syscall
@@ -496,6 +502,7 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr)
 		nfs_vmtruncate(inode, attr->ia_size);
 	}
 }
+EXPORT_SYMBOL_GPL(nfs_setattr_update_inode);
 
 int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 {
@@ -535,6 +542,7 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 out:
 	return err;
 }
+EXPORT_SYMBOL_GPL(nfs_getattr);
 
 static void nfs_init_lock_context(struct nfs_lock_context *l_ctx)
 {
@@ -623,6 +631,7 @@ void nfs_close_context(struct nfs_open_context *ctx, int is_sync)
 		return;
 	nfs_revalidate_inode(server, inode);
 }
+EXPORT_SYMBOL_GPL(nfs_close_context);
 
 struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f_mode)
 {
@@ -649,6 +658,7 @@ struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f
 	ctx->mdsthreshold = NULL;
 	return ctx;
 }
+EXPORT_SYMBOL_GPL(alloc_nfs_open_context);
 
 struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx)
 {
@@ -656,6 +666,7 @@ struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx)
 		atomic_inc(&ctx->lock_context.count);
 	return ctx;
 }
+EXPORT_SYMBOL_GPL(get_nfs_open_context);
 
 static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync)
 {
@@ -683,6 +694,7 @@ void put_nfs_open_context(struct nfs_open_context *ctx)
 {
 	__put_nfs_open_context(ctx, 0);
 }
+EXPORT_SYMBOL_GPL(put_nfs_open_context);
 
 /*
  * Ensure that mmap has a recent RPC credential for use when writing out
@@ -698,6 +710,7 @@ void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx)
 	list_add(&ctx->list, &nfsi->open_files);
 	spin_unlock(&inode->i_lock);
 }
+EXPORT_SYMBOL_GPL(nfs_file_set_open_context);
 
 /*
  * Given an inode, search for an open context with the desired characteristics
@@ -842,6 +855,7 @@ int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
 		return NFS_STALE(inode) ? -ESTALE : 0;
 	return __nfs_revalidate_inode(server, inode);
 }
+EXPORT_SYMBOL_GPL(nfs_revalidate_inode);
 
 static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping)
 {
@@ -883,6 +897,10 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
 	struct nfs_inode *nfsi = NFS_I(inode);
 	int ret = 0;
 
+	/* swapfiles are not supposed to be shared. */
+	if (IS_SWAPFILE(inode))
+		goto out;
+
 	if (nfs_mapping_need_revalidate_inode(inode)) {
 		ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
 		if (ret < 0)
@@ -1028,6 +1046,7 @@ void nfs_fattr_init(struct nfs_fattr *fattr)
 	fattr->owner_name = NULL;
 	fattr->group_name = NULL;
 }
+EXPORT_SYMBOL_GPL(nfs_fattr_init);
 
 struct nfs_fattr *nfs_alloc_fattr(void)
 {
@@ -1038,6 +1057,7 @@ struct nfs_fattr *nfs_alloc_fattr(void)
 		nfs_fattr_init(fattr);
 	return fattr;
 }
+EXPORT_SYMBOL_GPL(nfs_alloc_fattr);
 
 struct nfs_fh *nfs_alloc_fhandle(void)
 {
@@ -1048,6 +1068,7 @@ struct nfs_fh *nfs_alloc_fhandle(void)
 		fh->size = 0;
 	return fh;
 }
+EXPORT_SYMBOL_GPL(nfs_alloc_fhandle);
 
 #ifdef NFS_DEBUG
 /*
@@ -1168,6 +1189,7 @@ int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr)
 
 	return status;
 }
+EXPORT_SYMBOL_GPL(nfs_refresh_inode);
 
 static int nfs_post_op_update_inode_locked(struct inode *inode, struct nfs_fattr *fattr)
 {
@@ -1204,6 +1226,7 @@ int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	spin_unlock(&inode->i_lock);
 	return status;
 }
+EXPORT_SYMBOL_GPL(nfs_post_op_update_inode);
 
 /**
  * nfs_post_op_update_inode_force_wcc - try to update the inode attribute cache
@@ -1255,6 +1278,7 @@ out_noforce:
 	spin_unlock(&inode->i_lock);
 	return status;
 }
+EXPORT_SYMBOL_GPL(nfs_post_op_update_inode_force_wcc);
 
 /*
  * Many nfs protocol calls return the new file attributes after
@@ -1457,7 +1481,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)
 				|| S_ISLNK(inode->i_mode)))
 		invalid &= ~NFS_INO_INVALID_DATA;
-	if (!nfs_have_delegation(inode, FMODE_READ) ||
+	if (!NFS_PROTO(inode)->have_delegation(inode, FMODE_READ) ||
 			(save_cache_validity & NFS_INO_REVAL_FORCED))
 		nfsi->cache_validity |= invalid;
 
@@ -1472,27 +1496,6 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	return -ESTALE;
 }
 
-
-#ifdef CONFIG_NFS_V4
-
-/*
- * Clean out any remaining NFSv4 state that might be left over due
- * to open() calls that passed nfs_atomic_lookup, but failed to call
- * nfs_open().
- */
-void nfs4_evict_inode(struct inode *inode)
-{
-	truncate_inode_pages(&inode->i_data, 0);
-	clear_inode(inode);
-	pnfs_return_layout(inode);
-	pnfs_destroy_layout(NFS_I(inode));
-	/* If we are holding a delegation, return it! */
-	nfs_inode_return_delegation_noreclaim(inode);
-	/* First call standard NFS clear_inode() code */
-	nfs_clear_inode(inode);
-}
-#endif
-
 struct inode *nfs_alloc_inode(struct super_block *sb)
 {
 	struct nfs_inode *nfsi;
@@ -1505,11 +1508,12 @@ struct inode *nfs_alloc_inode(struct super_block *sb)
 	nfsi->acl_access = ERR_PTR(-EAGAIN);
 	nfsi->acl_default = ERR_PTR(-EAGAIN);
 #endif
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 	nfsi->nfs4_acl = NULL;
 #endif /* CONFIG_NFS_V4 */
 	return &nfsi->vfs_inode;
 }
+EXPORT_SYMBOL_GPL(nfs_alloc_inode);
 
 static void nfs_i_callback(struct rcu_head *head)
 {
@@ -1521,10 +1525,11 @@ void nfs_destroy_inode(struct inode *inode)
 {
 	call_rcu(&inode->i_rcu, nfs_i_callback);
 }
+EXPORT_SYMBOL_GPL(nfs_destroy_inode);
 
 static inline void nfs4_init_once(struct nfs_inode *nfsi)
 {
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 	INIT_LIST_HEAD(&nfsi->open_states);
 	nfsi->delegation = NULL;
 	nfsi->delegation_state = 0;
@@ -1570,6 +1575,7 @@ static void nfs_destroy_inodecache(void)
 }
 
 struct workqueue_struct *nfsiod_workqueue;
+EXPORT_SYMBOL_GPL(nfsiod_workqueue);
 
 /*
  * start up the nfsiod workqueue
@@ -1628,81 +1634,76 @@ static int __init init_nfs_fs(void)
 {
 	int err;
 
-	err = nfs_idmap_init();
-	if (err < 0)
-		goto out10;
-
 	err = nfs_dns_resolver_init();
 	if (err < 0)
-		goto out9;
+		goto out10;;
 
 	err = register_pernet_subsys(&nfs_net_ops);
 	if (err < 0)
-		goto out8;
+		goto out9;
 
 	err = nfs_fscache_register();
 	if (err < 0)
-		goto out7;
+		goto out8;
 
 	err = nfsiod_start();
 	if (err)
-		goto out6;
+		goto out7;
 
 	err = nfs_fs_proc_init();
 	if (err)
-		goto out5;
+		goto out6;
 
 	err = nfs_init_nfspagecache();
 	if (err)
-		goto out4;
+		goto out5;
 
 	err = nfs_init_inodecache();
 	if (err)
-		goto out3;
+		goto out4;
 
 	err = nfs_init_readpagecache();
 	if (err)
-		goto out2;
+		goto out3;
 
 	err = nfs_init_writepagecache();
 	if (err)
-		goto out1;
+		goto out2;
 
 	err = nfs_init_directcache();
 	if (err)
-		goto out0;
+		goto out1;
 
 #ifdef CONFIG_PROC_FS
 	rpc_proc_register(&init_net, &nfs_rpcstat);
 #endif
 	if ((err = register_nfs_fs()) != 0)
-		goto out;
+		goto out0;
+
 	return 0;
-out:
+out0:
 #ifdef CONFIG_PROC_FS
 	rpc_proc_unregister(&init_net, "nfs");
 #endif
 	nfs_destroy_directcache();
-out0:
-	nfs_destroy_writepagecache();
 out1:
-	nfs_destroy_readpagecache();
+	nfs_destroy_writepagecache();
 out2:
-	nfs_destroy_inodecache();
+	nfs_destroy_readpagecache();
 out3:
-	nfs_destroy_nfspagecache();
+	nfs_destroy_inodecache();
 out4:
-	nfs_fs_proc_exit();
+	nfs_destroy_nfspagecache();
 out5:
-	nfsiod_stop();
+	nfs_fs_proc_exit();
 out6:
-	nfs_fscache_unregister();
+	nfsiod_stop();
 out7:
-	unregister_pernet_subsys(&nfs_net_ops);
+	nfs_fscache_unregister();
 out8:
-	nfs_dns_resolver_destroy();
+	unregister_pernet_subsys(&nfs_net_ops);
 out9:
-	nfs_idmap_quit();
+	nfs_dns_resolver_destroy();
 out10:
 	return err;
 }
@@ -1717,7 +1718,6 @@ static void __exit exit_nfs_fs(void)
 	nfs_fscache_unregister();
 	unregister_pernet_subsys(&nfs_net_ops);
 	nfs_dns_resolver_destroy();
-	nfs_idmap_quit();
 #ifdef CONFIG_PROC_FS
 	rpc_proc_unregister(&init_net, "nfs");
 #endif
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 18f99ef71343..31fdb03225cd 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -85,6 +85,17 @@ struct nfs_clone_mount {
  */
 #define NFS_MAX_READDIR_PAGES 8
 
+struct nfs_client_initdata {
+	unsigned long init_flags;
+	const char *hostname;
+	const struct sockaddr *addr;
+	size_t addrlen;
+	struct nfs_subversion *nfs_mod;
+	int proto;
+	u32 minorversion;
+	struct net *net;
+};
+
 /*
  * In-kernel mount arguments
  */
@@ -142,25 +153,45 @@ struct nfs_mount_request {
 	struct net		*net;
 };
 
+struct nfs_mount_info {
+	void (*fill_super)(struct super_block *, struct nfs_mount_info *);
+	int (*set_security)(struct super_block *, struct dentry *, struct nfs_mount_info *);
+	struct nfs_parsed_mount_data *parsed;
+	struct nfs_clone_mount *cloned;
+	struct nfs_fh *mntfh;
+};
+
 extern int nfs_mount(struct nfs_mount_request *info);
 extern void nfs_umount(const struct nfs_mount_request *info);
 
 /* client.c */
 extern const struct rpc_program nfs_program;
 extern void nfs_clients_init(struct net *net);
+extern struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *);
+int nfs_create_rpc_client(struct nfs_client *, const struct rpc_timeout *, rpc_authflavor_t);
+struct nfs_client *nfs_get_client(const struct nfs_client_initdata *,
+				  const struct rpc_timeout *, const char *,
+				  rpc_authflavor_t);
+int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *, struct nfs_fattr *);
+void nfs_server_insert_lists(struct nfs_server *);
+void nfs_init_timeout_values(struct rpc_timeout *, int, unsigned int, unsigned int);
+int nfs_init_server_rpcclient(struct nfs_server *, const struct rpc_timeout *t,
+		rpc_authflavor_t);
+struct nfs_server *nfs_alloc_server(void);
+void nfs_server_copy_userdata(struct nfs_server *, struct nfs_server *);
 
 extern void nfs_cleanup_cb_ident_idr(struct net *);
 extern void nfs_put_client(struct nfs_client *);
+extern void nfs_free_client(struct nfs_client *);
 extern struct nfs_client *nfs4_find_client_ident(struct net *, int);
 extern struct nfs_client *
 nfs4_find_client_sessionid(struct net *, const struct sockaddr *,
 				struct nfs4_sessionid *);
-extern struct nfs_server *nfs_create_server(
-					const struct nfs_parsed_mount_data *,
-					struct nfs_fh *);
+extern struct nfs_server *nfs_create_server(struct nfs_mount_info *,
+					struct nfs_subversion *);
 extern struct nfs_server *nfs4_create_server(
-					const struct nfs_parsed_mount_data *,
-					struct nfs_fh *);
+					struct nfs_mount_info *,
+					struct nfs_subversion *);
 extern struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *,
 						      struct nfs_fh *);
 extern void nfs_free_server(struct nfs_server *server);
@@ -188,6 +219,17 @@ static inline void nfs_fs_proc_exit(void)
 }
 #endif
 
+#ifdef CONFIG_NFS_V4_1
+int nfs_sockaddr_match_ipaddr(const struct sockaddr *, const struct sockaddr *);
+#endif
+
+/* nfs3client.c */
+#if IS_ENABLED(CONFIG_NFS_V3)
+struct nfs_server *nfs3_create_server(struct nfs_mount_info *, struct nfs_subversion *);
+struct nfs_server *nfs3_clone_server(struct nfs_server *, struct nfs_fh *,
+				     struct nfs_fattr *, rpc_authflavor_t);
+#endif
+
 /* callback_xdr.c */
 extern struct svc_version nfs4_callback_version1;
 extern struct svc_version nfs4_callback_version4;
@@ -220,7 +262,7 @@ extern int nfs3_decode_dirent(struct xdr_stream *,
 				struct nfs_entry *, int);
 
 /* nfs4xdr.c */
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 extern int nfs4_decode_dirent(struct xdr_stream *,
 				struct nfs_entry *, int);
 #endif
@@ -230,7 +272,7 @@ extern const u32 nfs41_maxwrite_overhead;
 #endif
 
 /* nfs4proc.c */
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 extern struct rpc_procinfo nfs4_procedures[];
 #endif
 
@@ -245,25 +287,63 @@ extern struct nfs_client *nfs_init_client(struct nfs_client *clp,
 /* dir.c */
 extern int nfs_access_cache_shrinker(struct shrinker *shrink,
 					struct shrink_control *sc);
+struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int);
+int nfs_create(struct inode *, struct dentry *, umode_t, bool);
+int nfs_mkdir(struct inode *, struct dentry *, umode_t);
+int nfs_rmdir(struct inode *, struct dentry *);
+int nfs_unlink(struct inode *, struct dentry *);
+int nfs_symlink(struct inode *, struct dentry *, const char *);
+int nfs_link(struct dentry *, struct inode *, struct dentry *);
+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);
+loff_t nfs_file_llseek(struct file *, loff_t, int);
+int nfs_file_flush(struct file *, fl_owner_t);
+ssize_t nfs_file_read(struct kiocb *, const struct iovec *, unsigned long, loff_t);
+ssize_t nfs_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *,
+			     size_t, unsigned int);
+int nfs_file_mmap(struct file *, struct vm_area_struct *);
+ssize_t nfs_file_write(struct kiocb *, const struct iovec *, unsigned long, loff_t);
+int nfs_file_release(struct inode *, struct file *);
+int nfs_lock(struct file *, int, struct file_lock *);
+int nfs_flock(struct file *, int, struct file_lock *);
+ssize_t nfs_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *,
+			      size_t, unsigned int);
+int nfs_check_flags(int);
+int nfs_setlease(struct file *, long, struct file_lock **);
 
 /* inode.c */
 extern struct workqueue_struct *nfsiod_workqueue;
 extern struct inode *nfs_alloc_inode(struct super_block *sb);
 extern void nfs_destroy_inode(struct inode *);
 extern int nfs_write_inode(struct inode *, struct writeback_control *);
+extern void nfs_clear_inode(struct inode *);
 extern void nfs_evict_inode(struct inode *);
-#ifdef CONFIG_NFS_V4
-extern void nfs4_evict_inode(struct inode *);
-#endif
 void nfs_zap_acl_cache(struct inode *inode);
 extern int nfs_wait_bit_killable(void *word);
 
 /* super.c */
+extern const struct super_operations nfs_sops;
+extern struct file_system_type nfs_fs_type;
 extern struct file_system_type nfs_xdev_fs_type;
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 extern struct file_system_type nfs4_xdev_fs_type;
 extern struct file_system_type nfs4_referral_fs_type;
 #endif
+struct dentry *nfs_try_mount(int, const char *, struct nfs_mount_info *,
+			struct nfs_subversion *);
+void nfs_initialise_sb(struct super_block *);
+int nfs_set_sb_security(struct super_block *, struct dentry *, struct nfs_mount_info *);
+int nfs_clone_sb_security(struct super_block *, struct dentry *, struct nfs_mount_info *);
+struct dentry *nfs_fs_mount_common(struct nfs_server *, int, const char *,
+				   struct nfs_mount_info *, struct nfs_subversion *);
+struct dentry *nfs_fs_mount(struct file_system_type *, int, const char *, void *);
+struct dentry * nfs_xdev_mount_common(struct file_system_type *, int,
+		const char *, struct nfs_mount_info *);
+void nfs_kill_super(struct super_block *);
+void nfs_fill_super(struct super_block *, struct nfs_mount_info *);
 
 extern struct rpc_stat nfs_rpcstat;
 
@@ -284,7 +364,7 @@ struct vfsmount *nfs_do_submount(struct dentry *, struct nfs_fh *,
 /* getroot.c */
 extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *,
 				   const char *);
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 extern struct dentry *nfs4_get_root(struct super_block *, struct nfs_fh *,
 				    const char *);
 
@@ -304,12 +384,23 @@ extern int nfs_initiate_read(struct rpc_clnt *clnt,
 extern void nfs_read_prepare(struct rpc_task *task, void *calldata);
 extern int nfs_generic_pagein(struct nfs_pageio_descriptor *desc,
 			      struct nfs_pgio_header *hdr);
-extern void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio,
+extern void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
 			struct inode *inode,
 			const struct nfs_pgio_completion_ops *compl_ops);
 extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
 extern void nfs_readdata_release(struct nfs_read_data *rdata);
 
+/* super.c */
+void nfs_clone_super(struct super_block *, struct nfs_mount_info *);
+void nfs_umount_begin(struct super_block *);
+int  nfs_statfs(struct dentry *, struct kstatfs *);
+int  nfs_show_options(struct seq_file *, struct dentry *);
+int  nfs_show_devname(struct seq_file *, struct dentry *);
+int  nfs_show_path(struct seq_file *, struct dentry *);
+int  nfs_show_stats(struct seq_file *, struct dentry *);
+void nfs_put_super(struct super_block *);
+int nfs_remount(struct super_block *sb, int *flags, char *raw_data);
+
 /* write.c */
 extern void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
 			struct inode *inode, int ioflags,
@@ -318,7 +409,7 @@ extern struct nfs_write_header *nfs_writehdr_alloc(void);
 extern void nfs_writehdr_free(struct nfs_pgio_header *hdr);
 extern int nfs_generic_flush(struct nfs_pageio_descriptor *desc,
 			     struct nfs_pgio_header *hdr);
-extern void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio,
+extern void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
 			struct inode *inode, int ioflags,
 			const struct nfs_pgio_completion_ops *compl_ops);
 extern void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio);
@@ -463,13 +554,14 @@ void nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize)
 static inline
 unsigned int nfs_page_length(struct page *page)
 {
-	loff_t i_size = i_size_read(page->mapping->host);
+	loff_t i_size = i_size_read(page_file_mapping(page)->host);
 
 	if (i_size > 0) {
+		pgoff_t page_index = page_file_index(page);
 		pgoff_t end_index = (i_size - 1) >> PAGE_CACHE_SHIFT;
-		if (page->index < end_index)
+		if (page_index < end_index)
 			return PAGE_CACHE_SIZE;
-		if (page->index == end_index)
+		if (page_index == end_index)
 			return ((i_size - 1) & ~PAGE_CACHE_MASK) + 1;
 	}
 	return 0;
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 08b9c93675da..655925373b91 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -7,6 +7,7 @@
  * NFS namespace
  */
 
+#include <linux/module.h>
 #include <linux/dcache.h>
 #include <linux/gfp.h>
 #include <linux/mount.h>
@@ -112,6 +113,7 @@ Elong_unlock:
 Elong:
 	return ERR_PTR(-ENAMETOOLONG);
 }
+EXPORT_SYMBOL_GPL(nfs_path);
 
 /*
  * nfs_d_automount - Handle crossing a mountpoint on the server
@@ -195,20 +197,7 @@ static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server,
 					   const char *devname,
 					   struct nfs_clone_mount *mountdata)
 {
-#ifdef CONFIG_NFS_V4
-	struct vfsmount *mnt = ERR_PTR(-EINVAL);
-	switch (server->nfs_client->rpc_ops->version) {
-		case 2:
-		case 3:
-			mnt = vfs_kern_mount(&nfs_xdev_fs_type, 0, devname, mountdata);
-			break;
-		case 4:
-			mnt = vfs_kern_mount(&nfs4_xdev_fs_type, 0, devname, mountdata);
-	}
-	return mnt;
-#else
 	return vfs_kern_mount(&nfs_xdev_fs_type, 0, devname, mountdata);
-#endif
 }
 
 /**
@@ -253,6 +242,7 @@ out:
 	dprintk("<-- nfs_do_submount() = %p\n", mnt);
 	return mnt;
 }
+EXPORT_SYMBOL_GPL(nfs_do_submount);
 
 struct vfsmount *nfs_submount(struct nfs_server *server, struct dentry *dentry,
 			      struct nfs_fh *fh, struct nfs_fattr *fattr)
@@ -268,3 +258,4 @@ struct vfsmount *nfs_submount(struct nfs_server *server, struct dentry *dentry,
 
 	return nfs_do_submount(dentry, fh, fattr, server->client->cl_auth->au_flavor);
 }
+EXPORT_SYMBOL_GPL(nfs_submount);
diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h
index 8a6394edb8b0..0539de1b8d1f 100644
--- a/fs/nfs/netns.h
+++ b/fs/nfs/netns.h
@@ -20,7 +20,7 @@ struct nfs_net {
 	wait_queue_head_t bl_wq;
 	struct list_head nfs_client_list;
 	struct list_head nfs_volume_list;
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 	struct idr cb_ident_idr; /* Protected by nfs_client_lock */
 #endif
 	spinlock_t nfs_client_lock;
diff --git a/fs/nfs/nfs.h b/fs/nfs/nfs.h
new file mode 100644
index 000000000000..43679df56cd0
--- /dev/null
+++ b/fs/nfs/nfs.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright (c) 2012 Netapp, Inc. All rights reserved.
+ *
+ * Function and structures exported by the NFS module
+ * for use by NFS version-specific modules.
+ */
+#ifndef __LINUX_INTERNAL_NFS_H
+#define __LINUX_INTERNAL_NFS_H
+
+#include <linux/fs.h>
+#include <linux/sunrpc/sched.h>
+#include <linux/nfs_xdr.h>
+
+struct nfs_subversion {
+	struct module *owner;	/* THIS_MODULE pointer */
+	struct file_system_type *nfs_fs;	/* NFS filesystem type */
+	const struct rpc_version *rpc_vers;	/* NFS version information */
+	const struct nfs_rpc_ops *rpc_ops;	/* NFS operations */
+	const struct super_operations *sops;	/* NFS Super operations */
+	const struct xattr_handler **xattr;	/* NFS xattr handlers */
+	struct list_head list;		/* List of NFS versions */
+};
+
+struct nfs_subversion *get_nfs_version(unsigned int);
+void put_nfs_version(struct nfs_subversion *);
+void register_nfs_version(struct nfs_subversion *);
+void unregister_nfs_version(struct nfs_subversion *);
+
+#endif /* __LINUX_INTERNAL_NFS_H */
diff --git a/fs/nfs/nfs2super.c b/fs/nfs/nfs2super.c
new file mode 100644
index 000000000000..0a9782c9171a
--- /dev/null
+++ b/fs/nfs/nfs2super.c
@@ -0,0 +1,31 @@
+/*
+ * Copyright (c) 2012 Netapp, Inc. All rights reserved.
+ */
+#include <linux/module.h>
+#include <linux/nfs_fs.h>
+#include "internal.h"
+#include "nfs.h"
+
+static struct nfs_subversion nfs_v2 = {
+	.owner = THIS_MODULE,
+	.nfs_fs   = &nfs_fs_type,
+	.rpc_vers = &nfs_version2,
+	.rpc_ops  = &nfs_v2_clientops,
+	.sops     = &nfs_sops,
+};
+
+static int __init init_nfs_v2(void)
+{
+	register_nfs_version(&nfs_v2);
+	return 0;
+}
+
+static void __exit exit_nfs_v2(void)
+{
+	unregister_nfs_version(&nfs_v2);
+}
+
+MODULE_LICENSE("GPL");
+
+module_init(init_nfs_v2);
+module_exit(exit_nfs_v2);
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index baf759bccd05..d04f0df7be55 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -106,19 +106,16 @@ static void print_overflow_msg(const char *func, const struct xdr_stream *xdr)
 static int decode_nfsdata(struct xdr_stream *xdr, struct nfs_readres *result)
 {
 	u32 recvd, count;
-	size_t hdrlen;
 	__be32 *p;
 
 	p = xdr_inline_decode(xdr, 4);
 	if (unlikely(p == NULL))
 		goto out_overflow;
 	count = be32_to_cpup(p);
-	hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
-	recvd = xdr->buf->len - hdrlen;
+	recvd = xdr_read_pages(xdr, count);
 	if (unlikely(count > recvd))
 		goto out_cheating;
 out:
-	xdr_read_pages(xdr, count);
 	result->eof = 0;	/* NFSv2 does not pass EOF flag on the wire. */
 	result->count = count;
 	return count;
@@ -440,7 +437,6 @@ static void encode_path(struct xdr_stream *xdr, struct page **pages, u32 length)
 static int decode_path(struct xdr_stream *xdr)
 {
 	u32 length, recvd;
-	size_t hdrlen;
 	__be32 *p;
 
 	p = xdr_inline_decode(xdr, 4);
@@ -449,12 +445,9 @@ static int decode_path(struct xdr_stream *xdr)
 	length = be32_to_cpup(p);
 	if (unlikely(length >= xdr->buf->page_len || length > NFS_MAXPATHLEN))
 		goto out_size;
-	hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
-	recvd = xdr->buf->len - hdrlen;
+	recvd = xdr_read_pages(xdr, length);
 	if (unlikely(length > recvd))
 		goto out_cheating;
-
-	xdr_read_pages(xdr, length);
 	xdr_terminate_string(xdr->buf, length);
 	return 0;
 out_size:
@@ -972,22 +965,7 @@ out_overflow:
  */
 static int decode_readdirok(struct xdr_stream *xdr)
 {
-	u32 recvd, pglen;
-	size_t hdrlen;
-
-	pglen = xdr->buf->page_len;
-	hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
-	recvd = xdr->buf->len - hdrlen;
-	if (unlikely(pglen > recvd))
-		goto out_cheating;
-out:
-	xdr_read_pages(xdr, pglen);
-	return pglen;
-out_cheating:
-	dprintk("NFS: server cheating in readdir result: "
-		"pglen %u > recvd %u\n", pglen, recvd);
-	pglen = recvd;
-	goto out;
+	return xdr_read_pages(xdr, xdr->buf->page_len);
 }
 
 static int nfs2_xdr_dec_readdirres(struct rpc_rqst *req,
diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c
new file mode 100644
index 000000000000..b3fc65ef39ca
--- /dev/null
+++ b/fs/nfs/nfs3client.c
@@ -0,0 +1,65 @@
+#include <linux/nfs_fs.h>
+#include <linux/nfs_mount.h>
+#include "internal.h"
+
+#ifdef CONFIG_NFS_V3_ACL
+static struct rpc_stat		nfsacl_rpcstat = { &nfsacl_program };
+static const struct rpc_version *nfsacl_version[] = {
+	[3]			= &nfsacl_version3,
+};
+
+const struct rpc_program nfsacl_program = {
+	.name			= "nfsacl",
+	.number			= NFS_ACL_PROGRAM,
+	.nrvers			= ARRAY_SIZE(nfsacl_version),
+	.version		= nfsacl_version,
+	.stats			= &nfsacl_rpcstat,
+};
+
+/*
+ * Initialise an NFSv3 ACL client connection
+ */
+static void nfs_init_server_aclclient(struct nfs_server *server)
+{
+	if (server->flags & NFS_MOUNT_NOACL)
+		goto out_noacl;
+
+	server->client_acl = rpc_bind_new_program(server->client, &nfsacl_program, 3);
+	if (IS_ERR(server->client_acl))
+		goto out_noacl;
+
+	/* No errors! Assume that Sun nfsacls are supported */
+	server->caps |= NFS_CAP_ACLS;
+	return;
+
+out_noacl:
+	server->caps &= ~NFS_CAP_ACLS;
+}
+#else
+static inline void nfs_init_server_aclclient(struct nfs_server *server)
+{
+	server->flags &= ~NFS_MOUNT_NOACL;
+	server->caps &= ~NFS_CAP_ACLS;
+}
+#endif
+
+struct nfs_server *nfs3_create_server(struct nfs_mount_info *mount_info,
+				      struct nfs_subversion *nfs_mod)
+{
+	struct nfs_server *server = nfs_create_server(mount_info, nfs_mod);
+	/* Create a client RPC handle for the NFS v3 ACL management interface */
+	if (!IS_ERR(server))
+		nfs_init_server_aclclient(server);
+	return server;
+}
+
+struct nfs_server *nfs3_clone_server(struct nfs_server *source,
+				     struct nfs_fh *fh,
+				     struct nfs_fattr *fattr,
+				     rpc_authflavor_t flavor)
+{
+	struct nfs_server *server = nfs_clone_server(source, fh, fattr, flavor);
+	if (!IS_ERR(server) && !IS_ERR(source->client_acl))
+		nfs_init_server_aclclient(server);
+	return server;
+}
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 3187e24e8f78..0952c791df36 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -877,6 +877,46 @@ nfs3_proc_lock(struct file *filp, int cmd, struct file_lock *fl)
 	return nlmclnt_proc(NFS_SERVER(inode)->nlm_host, cmd, fl);
 }
 
+static int nfs3_have_delegation(struct inode *inode, fmode_t flags)
+{
+	return 0;
+}
+
+static int nfs3_return_delegation(struct inode *inode)
+{
+	nfs_wb_all(inode);
+	return 0;
+}
+
+static const struct inode_operations nfs3_dir_inode_operations = {
+	.create		= nfs_create,
+	.lookup		= nfs_lookup,
+	.link		= nfs_link,
+	.unlink		= nfs_unlink,
+	.symlink	= nfs_symlink,
+	.mkdir		= nfs_mkdir,
+	.rmdir		= nfs_rmdir,
+	.mknod		= nfs_mknod,
+	.rename		= nfs_rename,
+	.permission	= nfs_permission,
+	.getattr	= nfs_getattr,
+	.setattr	= nfs_setattr,
+	.listxattr	= nfs3_listxattr,
+	.getxattr	= nfs3_getxattr,
+	.setxattr	= nfs3_setxattr,
+	.removexattr	= nfs3_removexattr,
+};
+
+static const struct inode_operations nfs3_file_inode_operations = {
+	.permission	= nfs_permission,
+	.getattr	= nfs_getattr,
+	.setattr	= nfs_setattr,
+	.listxattr	= nfs3_listxattr,
+	.getxattr	= nfs3_getxattr,
+	.setxattr	= nfs3_setxattr,
+	.removexattr	= nfs3_removexattr,
+};
+
 const struct nfs_rpc_ops nfs_v3_clientops = {
 	.version	= 3,			/* protocol version */
 	.dentry_ops	= &nfs_dentry_operations,
@@ -885,6 +925,7 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
 	.file_ops	= &nfs_file_operations,
 	.getroot	= nfs3_proc_get_root,
 	.submount	= nfs_submount,
+	.try_mount	= nfs_try_mount,
 	.getattr	= nfs3_proc_getattr,
 	.setattr	= nfs3_proc_setattr,
 	.lookup		= nfs3_proc_lookup,
@@ -910,9 +951,11 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
 	.pathconf	= nfs3_proc_pathconf,
 	.decode_dirent	= nfs3_decode_dirent,
 	.read_setup	= nfs3_proc_read_setup,
+	.read_pageio_init = nfs_pageio_init_read,
 	.read_rpc_prepare = nfs3_proc_read_rpc_prepare,
 	.read_done	= nfs3_read_done,
 	.write_setup	= nfs3_proc_write_setup,
+	.write_pageio_init = nfs_pageio_init_write,
 	.write_rpc_prepare = nfs3_proc_write_rpc_prepare,
 	.write_done	= nfs3_write_done,
 	.commit_setup	= nfs3_proc_commit_setup,
@@ -921,5 +964,11 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
 	.lock		= nfs3_proc_lock,
 	.clear_acl_cache = nfs3_forget_cached_acls,
 	.close_context	= nfs_close_context,
+	.have_delegation = nfs3_have_delegation,
+	.return_delegation = nfs3_return_delegation,
+	.alloc_client	= nfs_alloc_client,
 	.init_client	= nfs_init_client,
+	.free_client	= nfs_free_client,
+	.create_server	= nfs3_create_server,
+	.clone_server	= nfs3_clone_server,
 };
diff --git a/fs/nfs/nfs3super.c b/fs/nfs/nfs3super.c
new file mode 100644
index 000000000000..cc471c725230
--- /dev/null
+++ b/fs/nfs/nfs3super.c
@@ -0,0 +1,31 @@
+/*
+ * Copyright (c) 2012 Netapp, Inc. All rights reserved.
+ */
+#include <linux/module.h>
+#include <linux/nfs_fs.h>
+#include "internal.h"
+#include "nfs.h"
+
+static struct nfs_subversion nfs_v3 = {
+	.owner = THIS_MODULE,
+	.nfs_fs   = &nfs_fs_type,
+	.rpc_vers = &nfs_version3,
+	.rpc_ops  = &nfs_v3_clientops,
+	.sops     = &nfs_sops,
+};
+
+static int __init init_nfs_v3(void)
+{
+	register_nfs_version(&nfs_v3);
+	return 0;
+}
+
+static void __exit exit_nfs_v3(void)
+{
+	unregister_nfs_version(&nfs_v3);
+}
+
+MODULE_LICENSE("GPL");
+
+module_init(init_nfs_v3);
+module_exit(exit_nfs_v3);
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 902de489ec9b..6cbe89400dfc 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -246,7 +246,6 @@ static void encode_nfspath3(struct xdr_stream *xdr, struct page **pages,
 static int decode_nfspath3(struct xdr_stream *xdr)
 {
 	u32 recvd, count;
-	size_t hdrlen;
 	__be32 *p;
 
 	p = xdr_inline_decode(xdr, 4);
@@ -255,12 +254,9 @@ static int decode_nfspath3(struct xdr_stream *xdr)
 	count = be32_to_cpup(p);
 	if (unlikely(count >= xdr->buf->page_len || count > NFS3_MAXPATHLEN))
 		goto out_nametoolong;
-	hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
-	recvd = xdr->buf->len - hdrlen;
+	recvd = xdr_read_pages(xdr, count);
 	if (unlikely(count > recvd))
 		goto out_cheating;
-
-	xdr_read_pages(xdr, count);
 	xdr_terminate_string(xdr->buf, count);
 	return 0;
 
@@ -329,14 +325,14 @@ static void encode_createverf3(struct xdr_stream *xdr, const __be32 *verifier)
 	memcpy(p, verifier, NFS3_CREATEVERFSIZE);
 }
 
-static int decode_writeverf3(struct xdr_stream *xdr, __be32 *verifier)
+static int decode_writeverf3(struct xdr_stream *xdr, struct nfs_write_verifier *verifier)
 {
 	__be32 *p;
 
 	p = xdr_inline_decode(xdr, NFS3_WRITEVERFSIZE);
 	if (unlikely(p == NULL))
 		goto out_overflow;
-	memcpy(verifier, p, NFS3_WRITEVERFSIZE);
+	memcpy(verifier->data, p, NFS3_WRITEVERFSIZE);
 	return 0;
 out_overflow:
 	print_overflow_msg(__func__, xdr);
@@ -1587,7 +1583,6 @@ static int decode_read3resok(struct xdr_stream *xdr,
 			     struct nfs_readres *result)
 {
 	u32 eof, count, ocount, recvd;
-	size_t hdrlen;
 	__be32 *p;
 
 	p = xdr_inline_decode(xdr, 4 + 4 + 4);
@@ -1598,13 +1593,10 @@ static int decode_read3resok(struct xdr_stream *xdr,
 	ocount = be32_to_cpup(p++);
 	if (unlikely(ocount != count))
 		goto out_mismatch;
-	hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
-	recvd = xdr->buf->len - hdrlen;
+	recvd = xdr_read_pages(xdr, count);
 	if (unlikely(count > recvd))
 		goto out_cheating;
-
 out:
-	xdr_read_pages(xdr, count);
 	result->eof = eof;
 	result->count = count;
 	return count;
@@ -1676,20 +1668,22 @@ static int decode_write3resok(struct xdr_stream *xdr,
 {
 	__be32 *p;
 
-	p = xdr_inline_decode(xdr, 4 + 4 + NFS3_WRITEVERFSIZE);
+	p = xdr_inline_decode(xdr, 4 + 4);
 	if (unlikely(p == NULL))
 		goto out_overflow;
 	result->count = be32_to_cpup(p++);
 	result->verf->committed = be32_to_cpup(p++);
 	if (unlikely(result->verf->committed > NFS_FILE_SYNC))
 		goto out_badvalue;
-	memcpy(result->verf->verifier, p, NFS3_WRITEVERFSIZE);
+	if (decode_writeverf3(xdr, &result->verf->verifier))
+		goto out_eio;
 	return result->count;
 out_badvalue:
 	dprintk("NFS: bad stable_how value: %u\n", result->verf->committed);
 	return -EIO;
 out_overflow:
 	print_overflow_msg(__func__, xdr);
+out_eio:
 	return -EIO;
 }
 
@@ -2039,22 +2033,7 @@ out_truncated:
  */
 static int decode_dirlist3(struct xdr_stream *xdr)
 {
-	u32 recvd, pglen;
-	size_t hdrlen;
-
-	pglen = xdr->buf->page_len;
-	hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
-	recvd = xdr->buf->len - hdrlen;
-	if (unlikely(pglen > recvd))
-		goto out_cheating;
-out:
-	xdr_read_pages(xdr, pglen);
-	return pglen;
-out_cheating:
-	dprintk("NFS: server cheating in readdir result: "
-		"pglen %u > recvd %u\n", pglen, recvd);
-	pglen = recvd;
-	goto out;
+	return xdr_read_pages(xdr, xdr->buf->page_len);
 }
 
 static int decode_readdir3resok(struct xdr_stream *xdr,
@@ -2337,7 +2316,7 @@ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req,
 		goto out;
 	if (status != NFS3_OK)
 		goto out_status;
-	error = decode_writeverf3(xdr, result->verf->verifier);
+	error = decode_writeverf3(xdr, &result->verf->verifier);
 out:
 	return error;
 out_status:
@@ -2364,7 +2343,7 @@ static inline int decode_getacl3resok(struct xdr_stream *xdr,
 	if (result->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT))
 		goto out;
 
-	hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
+	hdrlen = xdr_stream_pos(xdr);
 
 	acl = NULL;
 	if (result->mask & NFS_ACL)
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index cc5900ac61b5..3b950dd81e81 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -9,7 +9,7 @@
 #ifndef __LINUX_FS_NFS_NFS4_FS_H
 #define __LINUX_FS_NFS_NFS4_FS_H
 
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 
 struct idmap;
 
@@ -200,7 +200,10 @@ struct nfs4_state_maintenance_ops {
 };
 
 extern const struct dentry_operations nfs4_dentry_operations;
-extern const struct inode_operations nfs4_dir_inode_operations;
+
+/* dir.c */
+int nfs_atomic_open(struct inode *, struct dentry *, struct file *,
+		    unsigned, umode_t, int *);
 
 /* nfs4namespace.c */
 rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *);
@@ -301,6 +304,10 @@ extern const u32 nfs4_pathconf_bitmap[2];
 extern const u32 nfs4_fsinfo_bitmap[3];
 extern const u32 nfs4_fs_locations_bitmap[2];
 
+void nfs4_free_client(struct nfs_client *);
+
+struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *);
+
 /* nfs4renewd.c */
 extern void nfs4_schedule_state_renewal(struct nfs_client *);
 extern void nfs4_renewd_prepare_shutdown(struct nfs_server *);
@@ -354,6 +361,29 @@ extern void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_sta
 
 extern const nfs4_stateid zero_stateid;
 
+/* nfs4super.c */
+struct nfs_mount_info;
+extern struct nfs_subversion nfs_v4;
+struct dentry *nfs4_try_mount(int, const char *, struct nfs_mount_info *, struct nfs_subversion *);
+extern bool nfs4_disable_idmapping;
+extern unsigned short max_session_slots;
+extern unsigned short send_implementation_id;
+
+/* nfs4sysctl.c */
+#ifdef CONFIG_SYSCTL
+int nfs4_register_sysctl(void);
+void nfs4_unregister_sysctl(void);
+#else
+static inline int nfs4_register_sysctl(void)
+{
+	return 0;
+}
+
+static inline void nfs4_unregister_sysctl(void)
+{
+}
+#endif
+
 /* nfs4xdr.c */
 extern struct rpc_procinfo nfs4_procedures[];
 
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
new file mode 100644
index 000000000000..cbcdfaf32505
--- /dev/null
+++ b/fs/nfs/nfs4client.c
@@ -0,0 +1,656 @@
+/*
+ * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+#include <linux/module.h>
+#include <linux/nfs_fs.h>
+#include <linux/nfs_idmap.h>
+#include <linux/nfs_mount.h>
+#include <linux/sunrpc/auth.h>
+#include <linux/sunrpc/xprt.h>
+#include <linux/sunrpc/bc_xprt.h>
+#include "internal.h"
+#include "callback.h"
+#include "delegation.h"
+#include "pnfs.h"
+#include "netns.h"
+
+#define NFSDBG_FACILITY		NFSDBG_CLIENT
+
+/*
+ * Get a unique NFSv4.0 callback identifier which will be used
+ * by the V4.0 callback service to lookup the nfs_client struct
+ */
+static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion)
+{
+	int ret = 0;
+	struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
+
+	if (clp->rpc_ops->version != 4 || minorversion != 0)
+		return ret;
+retry:
+	if (!idr_pre_get(&nn->cb_ident_idr, GFP_KERNEL))
+		return -ENOMEM;
+	spin_lock(&nn->nfs_client_lock);
+	ret = idr_get_new(&nn->cb_ident_idr, clp, &clp->cl_cb_ident);
+	spin_unlock(&nn->nfs_client_lock);
+	if (ret == -EAGAIN)
+		goto retry;
+	return ret;
+}
+
+#ifdef CONFIG_NFS_V4_1
+static void nfs4_shutdown_session(struct nfs_client *clp)
+{
+	if (nfs4_has_session(clp)) {
+		nfs4_destroy_session(clp->cl_session);
+		nfs4_destroy_clientid(clp);
+	}
+
+}
+#else /* CONFIG_NFS_V4_1 */
+static void nfs4_shutdown_session(struct nfs_client *clp)
+{
+}
+#endif /* CONFIG_NFS_V4_1 */
+
+struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init)
+{
+	int err;
+	struct nfs_client *clp = nfs_alloc_client(cl_init);
+	if (IS_ERR(clp))
+		return clp;
+
+	err = nfs_get_cb_ident_idr(clp, cl_init->minorversion);
+	if (err)
+		goto error;
+
+	spin_lock_init(&clp->cl_lock);
+	INIT_DELAYED_WORK(&clp->cl_renewd, nfs4_renew_state);
+	rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client");
+	clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED;
+	clp->cl_minorversion = cl_init->minorversion;
+	clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion];
+	return clp;
+
+error:
+	kfree(clp);
+	return ERR_PTR(err);
+}
+
+/*
+ * Destroy the NFS4 callback service
+ */
+static void nfs4_destroy_callback(struct nfs_client *clp)
+{
+	if (__test_and_clear_bit(NFS_CS_CALLBACK, &clp->cl_res_state))
+		nfs_callback_down(clp->cl_mvops->minor_version);
+}
+
+static void nfs4_shutdown_client(struct nfs_client *clp)
+{
+	if (__test_and_clear_bit(NFS_CS_RENEWD, &clp->cl_res_state))
+		nfs4_kill_renewd(clp);
+	nfs4_shutdown_session(clp);
+	nfs4_destroy_callback(clp);
+	if (__test_and_clear_bit(NFS_CS_IDMAP, &clp->cl_res_state))
+		nfs_idmap_delete(clp);
+
+	rpc_destroy_wait_queue(&clp->cl_rpcwaitq);
+	kfree(clp->cl_serverowner);
+	kfree(clp->cl_serverscope);
+	kfree(clp->cl_implid);
+}
+
+void nfs4_free_client(struct nfs_client *clp)
+{
+	nfs4_shutdown_client(clp);
+	nfs_free_client(clp);
+}
+
+/*
+ * Initialize the NFS4 callback service
+ */
+static int nfs4_init_callback(struct nfs_client *clp)
+{
+	int error;
+
+	if (clp->rpc_ops->version == 4) {
+		struct rpc_xprt *xprt;
+
+		xprt = rcu_dereference_raw(clp->cl_rpcclient->cl_xprt);
+
+		if (nfs4_has_session(clp)) {
+			error = xprt_setup_backchannel(xprt,
+						NFS41_BC_MIN_CALLBACKS);
+			if (error < 0)
+				return error;
+		}
+
+		error = nfs_callback_up(clp->cl_mvops->minor_version, xprt);
+		if (error < 0) {
+			dprintk("%s: failed to start callback. Error = %d\n",
+				__func__, error);
+			return error;
+		}
+		__set_bit(NFS_CS_CALLBACK, &clp->cl_res_state);
+	}
+	return 0;
+}
+
+/*
+ * Initialize the minor version specific parts of an NFS4 client record
+ */
+static int nfs4_init_client_minor_version(struct nfs_client *clp)
+{
+#if defined(CONFIG_NFS_V4_1)
+	if (clp->cl_mvops->minor_version) {
+		struct nfs4_session *session = NULL;
+		/*
+		 * Create the session and mark it expired.
+		 * When a SEQUENCE operation encounters the expired session
+		 * it will do session recovery to initialize it.
+		 */
+		session = nfs4_alloc_session(clp);
+		if (!session)
+			return -ENOMEM;
+
+		clp->cl_session = session;
+		/*
+		 * The create session reply races with the server back
+		 * channel probe. Mark the client NFS_CS_SESSION_INITING
+		 * so that the client back channel can find the
+		 * nfs_client struct
+		 */
+		nfs_mark_client_ready(clp, NFS_CS_SESSION_INITING);
+	}
+#endif /* CONFIG_NFS_V4_1 */
+
+	return nfs4_init_callback(clp);
+}
+
+/**
+ * nfs4_init_client - Initialise an NFS4 client record
+ *
+ * @clp: nfs_client to initialise
+ * @timeparms: timeout parameters for underlying RPC transport
+ * @ip_addr: callback IP address in presentation format
+ * @authflavor: authentication flavor for underlying RPC transport
+ *
+ * Returns pointer to an NFS client, or an ERR_PTR value.
+ */
+struct nfs_client *nfs4_init_client(struct nfs_client *clp,
+				    const struct rpc_timeout *timeparms,
+				    const char *ip_addr,
+				    rpc_authflavor_t authflavour)
+{
+	char buf[INET6_ADDRSTRLEN + 1];
+	int error;
+
+	if (clp->cl_cons_state == NFS_CS_READY) {
+		/* the client is initialised already */
+		dprintk("<-- nfs4_init_client() = 0 [already %p]\n", clp);
+		return clp;
+	}
+
+	/* Check NFS protocol revision and initialize RPC op vector */
+	clp->rpc_ops = &nfs_v4_clientops;
+
+	__set_bit(NFS_CS_DISCRTRY, &clp->cl_flags);
+	error = nfs_create_rpc_client(clp, timeparms, authflavour);
+	if (error < 0)
+		goto error;
+
+	/* If no clientaddr= option was specified, find a usable cb address */
+	if (ip_addr == NULL) {
+		struct sockaddr_storage cb_addr;
+		struct sockaddr *sap = (struct sockaddr *)&cb_addr;
+
+		error = rpc_localaddr(clp->cl_rpcclient, sap, sizeof(cb_addr));
+		if (error < 0)
+			goto error;
+		error = rpc_ntop(sap, buf, sizeof(buf));
+		if (error < 0)
+			goto error;
+		ip_addr = (const char *)buf;
+	}
+	strlcpy(clp->cl_ipaddr, ip_addr, sizeof(clp->cl_ipaddr));
+
+	error = nfs_idmap_new(clp);
+	if (error < 0) {
+		dprintk("%s: failed to create idmapper. Error = %d\n",
+			__func__, error);
+		goto error;
+	}
+	__set_bit(NFS_CS_IDMAP, &clp->cl_res_state);
+
+	error = nfs4_init_client_minor_version(clp);
+	if (error < 0)
+		goto error;
+
+	if (!nfs4_has_session(clp))
+		nfs_mark_client_ready(clp, NFS_CS_READY);
+	return clp;
+
+error:
+	nfs_mark_client_ready(clp, error);
+	nfs_put_client(clp);
+	dprintk("<-- nfs4_init_client() = xerror %d\n", error);
+	return ERR_PTR(error);
+}
+
+static void nfs4_destroy_server(struct nfs_server *server)
+{
+	nfs_server_return_all_delegations(server);
+	unset_pnfs_layoutdriver(server);
+	nfs4_purge_state_owners(server);
+}
+
+/*
+ * NFSv4.0 callback thread helper
+ *
+ * Find a client by callback identifier
+ */
+struct nfs_client *
+nfs4_find_client_ident(struct net *net, int cb_ident)
+{
+	struct nfs_client *clp;
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+	spin_lock(&nn->nfs_client_lock);
+	clp = idr_find(&nn->cb_ident_idr, cb_ident);
+	if (clp)
+		atomic_inc(&clp->cl_count);
+	spin_unlock(&nn->nfs_client_lock);
+	return clp;
+}
+
+#if defined(CONFIG_NFS_V4_1)
+/* Common match routine for v4.0 and v4.1 callback services */
+static bool nfs4_cb_match_client(const struct sockaddr *addr,
+		struct nfs_client *clp, u32 minorversion)
+{
+	struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr;
+
+	/* Don't match clients that failed to initialise */
+	if (!(clp->cl_cons_state == NFS_CS_READY ||
+	    clp->cl_cons_state == NFS_CS_SESSION_INITING))
+		return false;
+
+	smp_rmb();
+
+	/* Match the version and minorversion */
+	if (clp->rpc_ops->version != 4 ||
+	    clp->cl_minorversion != minorversion)
+		return false;
+
+	/* Match only the IP address, not the port number */
+	if (!nfs_sockaddr_match_ipaddr(addr, clap))
+		return false;
+
+	return true;
+}
+
+/*
+ * NFSv4.1 callback thread helper
+ * For CB_COMPOUND calls, find a client by IP address, protocol version,
+ * minorversion, and sessionID
+ *
+ * Returns NULL if no such client
+ */
+struct nfs_client *
+nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr,
+			   struct nfs4_sessionid *sid)
+{
+	struct nfs_client *clp;
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+	spin_lock(&nn->nfs_client_lock);
+	list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) {
+		if (nfs4_cb_match_client(addr, clp, 1) == false)
+			continue;
+
+		if (!nfs4_has_session(clp))
+			continue;
+
+		/* Match sessionid*/
+		if (memcmp(clp->cl_session->sess_id.data,
+		    sid->data, NFS4_MAX_SESSIONID_LEN) != 0)
+			continue;
+
+		atomic_inc(&clp->cl_count);
+		spin_unlock(&nn->nfs_client_lock);
+		return clp;
+	}
+	spin_unlock(&nn->nfs_client_lock);
+	return NULL;
+}
+
+#else /* CONFIG_NFS_V4_1 */
+
+struct nfs_client *
+nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr,
+			   struct nfs4_sessionid *sid)
+{
+	return NULL;
+}
+#endif /* CONFIG_NFS_V4_1 */
+
+/*
+ * Set up an NFS4 client
+ */
+static int nfs4_set_client(struct nfs_server *server,
+		const char *hostname,
+		const struct sockaddr *addr,
+		const size_t addrlen,
+		const char *ip_addr,
+		rpc_authflavor_t authflavour,
+		int proto, const struct rpc_timeout *timeparms,
+		u32 minorversion, struct net *net)
+{
+	struct nfs_client_initdata cl_init = {
+		.hostname = hostname,
+		.addr = addr,
+		.addrlen = addrlen,
+		.nfs_mod = &nfs_v4,
+		.proto = proto,
+		.minorversion = minorversion,
+		.net = net,
+	};
+	struct nfs_client *clp;
+	int error;
+
+	dprintk("--> nfs4_set_client()\n");
+
+	if (server->flags & NFS_MOUNT_NORESVPORT)
+		set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
+
+	/* Allocate or find a client reference we can use */
+	clp = nfs_get_client(&cl_init, timeparms, ip_addr, authflavour);
+	if (IS_ERR(clp)) {
+		error = PTR_ERR(clp);
+		goto error;
+	}
+
+	/*
+	 * Query for the lease time on clientid setup or renewal
+	 *
+	 * Note that this will be set on nfs_clients that were created
+	 * only for the DS role and did not set this bit, but now will
+	 * serve a dual role.
+	 */
+	set_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state);
+
+	server->nfs_client = clp;
+	dprintk("<-- nfs4_set_client() = 0 [new %p]\n", clp);
+	return 0;
+error:
+	dprintk("<-- nfs4_set_client() = xerror %d\n", error);
+	return error;
+}
+
+/*
+ * Set up a pNFS Data Server client.
+ *
+ * Return any existing nfs_client that matches server address,port,version
+ * and minorversion.
+ *
+ * For a new nfs_client, use a soft mount (default), a low retrans and a
+ * low timeout interval so that if a connection is lost, we retry through
+ * the MDS.
+ */
+struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
+		const struct sockaddr *ds_addr, int ds_addrlen,
+		int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans)
+{
+	struct nfs_client_initdata cl_init = {
+		.addr = ds_addr,
+		.addrlen = ds_addrlen,
+		.nfs_mod = &nfs_v4,
+		.proto = ds_proto,
+		.minorversion = mds_clp->cl_minorversion,
+		.net = mds_clp->cl_net,
+	};
+	struct rpc_timeout ds_timeout;
+	struct nfs_client *clp;
+
+	/*
+	 * Set an authflavor equual to the MDS value. Use the MDS nfs_client
+	 * cl_ipaddr so as to use the same EXCHANGE_ID co_ownerid as the MDS
+	 * (section 13.1 RFC 5661).
+	 */
+	nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans);
+	clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr,
+			     mds_clp->cl_rpcclient->cl_auth->au_flavor);
+
+	dprintk("<-- %s %p\n", __func__, clp);
+	return clp;
+}
+EXPORT_SYMBOL_GPL(nfs4_set_ds_client);
+
+/*
+ * Session has been established, and the client marked ready.
+ * Set the mount rsize and wsize with negotiated fore channel
+ * attributes which will be bound checked in nfs_server_set_fsinfo.
+ */
+static void nfs4_session_set_rwsize(struct nfs_server *server)
+{
+#ifdef CONFIG_NFS_V4_1
+	struct nfs4_session *sess;
+	u32 server_resp_sz;
+	u32 server_rqst_sz;
+
+	if (!nfs4_has_session(server->nfs_client))
+		return;
+	sess = server->nfs_client->cl_session;
+	server_resp_sz = sess->fc_attrs.max_resp_sz - nfs41_maxread_overhead;
+	server_rqst_sz = sess->fc_attrs.max_rqst_sz - nfs41_maxwrite_overhead;
+
+	if (server->rsize > server_resp_sz)
+		server->rsize = server_resp_sz;
+	if (server->wsize > server_rqst_sz)
+		server->wsize = server_rqst_sz;
+#endif /* CONFIG_NFS_V4_1 */
+}
+
+static int nfs4_server_common_setup(struct nfs_server *server,
+		struct nfs_fh *mntfh)
+{
+	struct nfs_fattr *fattr;
+	int error;
+
+	BUG_ON(!server->nfs_client);
+	BUG_ON(!server->nfs_client->rpc_ops);
+	BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
+
+	/* data servers support only a subset of NFSv4.1 */
+	if (is_ds_only_client(server->nfs_client))
+		return -EPROTONOSUPPORT;
+
+	fattr = nfs_alloc_fattr();
+	if (fattr == NULL)
+		return -ENOMEM;
+
+	/* We must ensure the session is initialised first */
+	error = nfs4_init_session(server);
+	if (error < 0)
+		goto out;
+
+	/* Probe the root fh to retrieve its FSID and filehandle */
+	error = nfs4_get_rootfh(server, mntfh);
+	if (error < 0)
+		goto out;
+
+	dprintk("Server FSID: %llx:%llx\n",
+			(unsigned long long) server->fsid.major,
+			(unsigned long long) server->fsid.minor);
+	dprintk("Mount FH: %d\n", mntfh->size);
+
+	nfs4_session_set_rwsize(server);
+
+	error = nfs_probe_fsinfo(server, mntfh, fattr);
+	if (error < 0)
+		goto out;
+
+	if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN)
+		server->namelen = NFS4_MAXNAMLEN;
+
+	nfs_server_insert_lists(server);
+	server->mount_time = jiffies;
+	server->destroy = nfs4_destroy_server;
+out:
+	nfs_free_fattr(fattr);
+	return error;
+}
+
+/*
+ * Create a version 4 volume record
+ */
+static int nfs4_init_server(struct nfs_server *server,
+		const struct nfs_parsed_mount_data *data)
+{
+	struct rpc_timeout timeparms;
+	int error;
+
+	dprintk("--> nfs4_init_server()\n");
+
+	nfs_init_timeout_values(&timeparms, data->nfs_server.protocol,
+			data->timeo, data->retrans);
+
+	/* Initialise the client representation from the mount data */
+	server->flags = data->flags;
+	server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR|NFS_CAP_POSIX_LOCK;
+	if (!(data->flags & NFS_MOUNT_NORDIRPLUS))
+			server->caps |= NFS_CAP_READDIRPLUS;
+	server->options = data->options;
+
+	/* Get a client record */
+	error = nfs4_set_client(server,
+			data->nfs_server.hostname,
+			(const struct sockaddr *)&data->nfs_server.address,
+			data->nfs_server.addrlen,
+			data->client_address,
+			data->auth_flavors[0],
+			data->nfs_server.protocol,
+			&timeparms,
+			data->minorversion,
+			data->net);
+	if (error < 0)
+		goto error;
+
+	/*
+	 * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower
+	 * authentication.
+	 */
+	if (nfs4_disable_idmapping && data->auth_flavors[0] == RPC_AUTH_UNIX)
+		server->caps |= NFS_CAP_UIDGID_NOMAP;
+
+	if (data->rsize)
+		server->rsize = nfs_block_size(data->rsize, NULL);
+	if (data->wsize)
+		server->wsize = nfs_block_size(data->wsize, NULL);
+
+	server->acregmin = data->acregmin * HZ;
+	server->acregmax = data->acregmax * HZ;
+	server->acdirmin = data->acdirmin * HZ;
+	server->acdirmax = data->acdirmax * HZ;
+
+	server->port = data->nfs_server.port;
+
+	error = nfs_init_server_rpcclient(server, &timeparms, data->auth_flavors[0]);
+
+error:
+	/* Done */
+	dprintk("<-- nfs4_init_server() = %d\n", error);
+	return error;
+}
+
+/*
+ * Create a version 4 volume record
+ * - keyed on server and FSID
+ */
+/*struct nfs_server *nfs4_create_server(const struct nfs_parsed_mount_data *data,
+				      struct nfs_fh *mntfh)*/
+struct nfs_server *nfs4_create_server(struct nfs_mount_info *mount_info,
+				      struct nfs_subversion *nfs_mod)
+{
+	struct nfs_server *server;
+	int error;
+
+	dprintk("--> nfs4_create_server()\n");
+
+	server = nfs_alloc_server();
+	if (!server)
+		return ERR_PTR(-ENOMEM);
+
+	/* set up the general RPC client */
+	error = nfs4_init_server(server, mount_info->parsed);
+	if (error < 0)
+		goto error;
+
+	error = nfs4_server_common_setup(server, mount_info->mntfh);
+	if (error < 0)
+		goto error;
+
+	dprintk("<-- nfs4_create_server() = %p\n", server);
+	return server;
+
+error:
+	nfs_free_server(server);
+	dprintk("<-- nfs4_create_server() = error %d\n", error);
+	return ERR_PTR(error);
+}
+
+/*
+ * Create an NFS4 referral server record
+ */
+struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
+					       struct nfs_fh *mntfh)
+{
+	struct nfs_client *parent_client;
+	struct nfs_server *server, *parent_server;
+	int error;
+
+	dprintk("--> nfs4_create_referral_server()\n");
+
+	server = nfs_alloc_server();
+	if (!server)
+		return ERR_PTR(-ENOMEM);
+
+	parent_server = NFS_SB(data->sb);
+	parent_client = parent_server->nfs_client;
+
+	/* Initialise the client representation from the parent server */
+	nfs_server_copy_userdata(server, parent_server);
+	server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR;
+
+	/* Get a client representation.
+	 * Note: NFSv4 always uses TCP, */
+	error = nfs4_set_client(server, data->hostname,
+				data->addr,
+				data->addrlen,
+				parent_client->cl_ipaddr,
+				data->authflavor,
+				rpc_protocol(parent_server->client),
+				parent_server->client->cl_timeout,
+				parent_client->cl_mvops->minor_version,
+				parent_client->cl_net);
+	if (error < 0)
+		goto error;
+
+	error = nfs_init_server_rpcclient(server, parent_server->client->cl_timeout, data->authflavor);
+	if (error < 0)
+		goto error;
+
+	error = nfs4_server_common_setup(server, mntfh);
+	if (error < 0)
+		goto error;
+
+	dprintk("<-- nfs_create_referral_server() = %p\n", server);
+	return server;
+
+error:
+	nfs_free_server(server);
+	dprintk("<-- nfs4_create_referral_server() = error %d\n", error);
+	return ERR_PTR(error);
+}
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
new file mode 100644
index 000000000000..acb65e7887f8
--- /dev/null
+++ b/fs/nfs/nfs4file.c
@@ -0,0 +1,126 @@
+/*
+ *  linux/fs/nfs/file.c
+ *
+ *  Copyright (C) 1992  Rick Sladkey
+ */
+#include <linux/nfs_fs.h>
+#include "internal.h"
+#include "pnfs.h"
+
+#define NFSDBG_FACILITY		NFSDBG_FILE
+
+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 *parent = NULL;
+	struct inode *dir;
+	unsigned openflags = filp->f_flags;
+	struct iattr attr;
+	int err;
+
+	BUG_ON(inode != dentry->d_inode);
+	/*
+	 * If no cached dentry exists or if it's negative, NFSv4 handled the
+	 * opens in ->lookup() or ->create().
+	 *
+	 * We only get this far for a cached positive dentry.  We skipped
+	 * revalidation, so handle it here by dropping the dentry and returning
+	 * -EOPENSTALE.  The VFS will retry the lookup/create/open.
+	 */
+
+	dprintk("NFS: open file(%s/%s)\n",
+		dentry->d_parent->d_name.name,
+		dentry->d_name.name);
+
+	if ((openflags & O_ACCMODE) == 3)
+		openflags--;
+
+	/* We can't create new files here */
+	openflags &= ~(O_CREAT|O_EXCL);
+
+	parent = dget_parent(dentry);
+	dir = parent->d_inode;
+
+	ctx = alloc_nfs_open_context(filp->f_path.dentry, filp->f_mode);
+	err = PTR_ERR(ctx);
+	if (IS_ERR(ctx))
+		goto out;
+
+	attr.ia_valid = ATTR_OPEN;
+	if (openflags & O_TRUNC) {
+		attr.ia_valid |= ATTR_SIZE;
+		attr.ia_size = 0;
+		nfs_wb_all(inode);
+	}
+
+	inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr);
+	if (IS_ERR(inode)) {
+		err = PTR_ERR(inode);
+		switch (err) {
+		case -EPERM:
+		case -EACCES:
+		case -EDQUOT:
+		case -ENOSPC:
+		case -EROFS:
+			goto out_put_ctx;
+		default:
+			goto out_drop;
+		}
+	}
+	iput(inode);
+	if (inode != dentry->d_inode)
+		goto out_drop;
+
+	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+	nfs_file_set_open_context(filp, ctx);
+	err = 0;
+
+out_put_ctx:
+	put_nfs_open_context(ctx);
+out:
+	dput(parent);
+	return err;
+
+out_drop:
+	d_drop(dentry);
+	err = -EOPENSTALE;
+	goto out_put_ctx;
+}
+
+static int
+nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
+{
+	int ret;
+	struct inode *inode = file->f_path.dentry->d_inode;
+
+	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
+	mutex_lock(&inode->i_mutex);
+	ret = nfs_file_fsync_commit(file, start, end, datasync);
+	if (!ret && !datasync)
+		/* application has asked for meta-data sync */
+		ret = pnfs_layoutcommit_inode(inode, true);
+	mutex_unlock(&inode->i_mutex);
+
+	return ret;
+}
+
+const struct file_operations nfs4_file_operations = {
+	.llseek		= nfs_file_llseek,
+	.read		= do_sync_read,
+	.write		= do_sync_write,
+	.aio_read	= nfs_file_read,
+	.aio_write	= nfs_file_write,
+	.mmap		= nfs_file_mmap,
+	.open		= nfs4_file_open,
+	.flush		= nfs_file_flush,
+	.release	= nfs_file_release,
+	.fsync		= nfs4_file_fsync,
+	.lock		= nfs_lock,
+	.flock		= nfs_flock,
+	.splice_read	= nfs_file_splice_read,
+	.splice_write	= nfs_file_splice_write,
+	.check_flags	= nfs_check_flags,
+	.setlease	= nfs_setlease,
+};
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index e1340293872c..53f94d915bd1 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -205,9 +205,9 @@ static int filelayout_async_handle_error(struct rpc_task *task,
 	case -EPIPE:
 		dprintk("%s DS connection error %d\n", __func__,
 			task->tk_status);
-		if (!filelayout_test_devid_invalid(devid))
-			_pnfs_return_layout(inode);
 		filelayout_mark_devid_invalid(devid);
+		clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(inode)->flags);
+		_pnfs_return_layout(inode);
 		rpc_wake_up(&tbl->slot_tbl_waitq);
 		nfs4_ds_disconnect(clp);
 		/* fall through */
@@ -351,9 +351,9 @@ static void prepare_to_resend_writes(struct nfs_commit_data *data)
 	struct nfs_page *first = nfs_list_entry(data->pages.next);
 
 	data->task.tk_status = 0;
-	memcpy(data->verf.verifier, first->wb_verf.verifier,
-	       sizeof(first->wb_verf.verifier));
-	data->verf.verifier[0]++; /* ensure verifier mismatch */
+	memcpy(&data->verf.verifier, &first->wb_verf,
+	       sizeof(data->verf.verifier));
+	data->verf.verifier.data[0]++; /* ensure verifier mismatch */
 }
 
 static int filelayout_commit_done_cb(struct rpc_task *task,
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index a1fab8da7f03..f81231f30d94 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -728,7 +728,7 @@ get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_fla
 	pdev->layout_type = LAYOUT_NFSV4_1_FILES;
 	pdev->pages = pages;
 	pdev->pgbase = 0;
-	pdev->pglen = PAGE_SIZE * max_pages;
+	pdev->pglen = max_resp_sz;
 	pdev->mincount = 0;
 
 	rc = nfs4_proc_getdeviceinfo(server, pdev);
diff --git a/fs/nfs/nfs4getroot.c b/fs/nfs/nfs4getroot.c
new file mode 100644
index 000000000000..6a83780e0ce6
--- /dev/null
+++ b/fs/nfs/nfs4getroot.c
@@ -0,0 +1,49 @@
+/*
+* Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
+* Written by David Howells (dhowells@redhat.com)
+*/
+
+#include <linux/nfs_fs.h>
+#include "nfs4_fs.h"
+
+#define NFSDBG_FACILITY		NFSDBG_CLIENT
+
+int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh)
+{
+	struct nfs_fsinfo fsinfo;
+	int ret = -ENOMEM;
+
+	dprintk("--> nfs4_get_rootfh()\n");
+
+	fsinfo.fattr = nfs_alloc_fattr();
+	if (fsinfo.fattr == NULL)
+		goto out;
+
+	/* Start by getting the root filehandle from the server */
+	ret = nfs4_proc_get_rootfh(server, mntfh, &fsinfo);
+	if (ret < 0) {
+		dprintk("nfs4_get_rootfh: getroot error = %d\n", -ret);
+		goto out;
+	}
+
+	if (!(fsinfo.fattr->valid & NFS_ATTR_FATTR_TYPE)
+			|| !S_ISDIR(fsinfo.fattr->mode)) {
+		printk(KERN_ERR "nfs4_get_rootfh:"
+		       " getroot encountered non-directory\n");
+		ret = -ENOTDIR;
+		goto out;
+	}
+
+	if (fsinfo.fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) {
+		printk(KERN_ERR "nfs4_get_rootfh:"
+		       " getroot obtained referral\n");
+		ret = -EREMOTE;
+		goto out;
+	}
+
+	memcpy(&server->fsid, &fsinfo.fattr->fsid, sizeof(server->fsid));
+out:
+	nfs_free_fattr(fsinfo.fattr);
+	dprintk("<-- nfs4_get_rootfh() = %d\n", ret);
+	return ret;
+}
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index c157b2089b47..a99a8d948721 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -43,7 +43,6 @@
 #include <linux/printk.h>
 #include <linux/slab.h>
 #include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/gss_api.h>
 #include <linux/nfs.h>
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
@@ -73,8 +72,6 @@
 
 #define NFS4_MAX_LOOP_ON_RECOVER (10)
 
-static unsigned short max_session_slots = NFS4_DEF_SLOT_TABLE_SIZE;
-
 struct nfs4_opendata;
 static int _nfs4_proc_open(struct nfs4_opendata *data);
 static int _nfs4_recover_proc_open(struct nfs4_opendata *data);
@@ -259,7 +256,12 @@ static int nfs4_wait_clnt_recover(struct nfs_client *clp)
 
 	res = wait_on_bit(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING,
 			nfs_wait_bit_killable, TASK_KILLABLE);
-	return res;
+	if (res)
+		return res;
+
+	if (clp->cl_cons_state < 0)
+		return clp->cl_cons_state;
+	return 0;
 }
 
 static int nfs4_delay(struct rpc_clnt *clnt, long *timeout)
@@ -294,8 +296,8 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
 		case 0:
 			return 0;
 		case -NFS4ERR_OPENMODE:
-			if (inode && nfs_have_delegation(inode, FMODE_READ)) {
-				nfs_inode_return_delegation(inode);
+			if (inode && nfs4_have_delegation(inode, FMODE_READ)) {
+				nfs4_inode_return_delegation(inode);
 				exception->retry = 1;
 				return 0;
 			}
@@ -1065,7 +1067,7 @@ static void nfs4_return_incompatible_delegation(struct inode *inode, fmode_t fmo
 		return;
 	}
 	rcu_read_unlock();
-	nfs_inode_return_delegation(inode);
+	nfs4_inode_return_delegation(inode);
 }
 
 static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
@@ -1756,33 +1758,70 @@ static int nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *sta
 }
 
 #if defined(CONFIG_NFS_V4_1)
-static int nfs41_check_expired_stateid(struct nfs4_state *state, nfs4_stateid *stateid, unsigned int flags)
+static void nfs41_clear_delegation_stateid(struct nfs4_state *state)
 {
-	int status = NFS_OK;
 	struct nfs_server *server = NFS_SERVER(state->inode);
+	nfs4_stateid *stateid = &state->stateid;
+	int status;
 
-	if (state->flags & flags) {
-		status = nfs41_test_stateid(server, stateid);
-		if (status != NFS_OK) {
+	/* If a state reset has been done, test_stateid is unneeded */
+	if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0)
+		return;
+
+	status = nfs41_test_stateid(server, stateid);
+	if (status != NFS_OK) {
+		/* Free the stateid unless the server explicitly
+		 * informs us the stateid is unrecognized. */
+		if (status != -NFS4ERR_BAD_STATEID)
 			nfs41_free_stateid(server, stateid);
-			state->flags &= ~flags;
-		}
+
+		clear_bit(NFS_DELEGATED_STATE, &state->flags);
+	}
+}
+
+/**
+ * nfs41_check_open_stateid - possibly free an open stateid
+ *
+ * @state: NFSv4 state for an inode
+ *
+ * Returns NFS_OK if recovery for this stateid is now finished.
+ * Otherwise a negative NFS4ERR value is returned.
+ */
+static int nfs41_check_open_stateid(struct nfs4_state *state)
+{
+	struct nfs_server *server = NFS_SERVER(state->inode);
+	nfs4_stateid *stateid = &state->stateid;
+	int status;
+
+	/* If a state reset has been done, test_stateid is unneeded */
+	if ((test_bit(NFS_O_RDONLY_STATE, &state->flags) == 0) &&
+	    (test_bit(NFS_O_WRONLY_STATE, &state->flags) == 0) &&
+	    (test_bit(NFS_O_RDWR_STATE, &state->flags) == 0))
+		return -NFS4ERR_BAD_STATEID;
+
+	status = nfs41_test_stateid(server, stateid);
+	if (status != NFS_OK) {
+		/* Free the stateid unless the server explicitly
+		 * informs us the stateid is unrecognized. */
+		if (status != -NFS4ERR_BAD_STATEID)
+			nfs41_free_stateid(server, stateid);
+
+		clear_bit(NFS_O_RDONLY_STATE, &state->flags);
+		clear_bit(NFS_O_WRONLY_STATE, &state->flags);
+		clear_bit(NFS_O_RDWR_STATE, &state->flags);
 	}
 	return status;
 }
 
 static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state)
 {
-	int deleg_status, open_status;
-	int deleg_flags = 1 << NFS_DELEGATED_STATE;
-	int open_flags = (1 << NFS_O_RDONLY_STATE) | (1 << NFS_O_WRONLY_STATE) | (1 << NFS_O_RDWR_STATE);
-
-	deleg_status = nfs41_check_expired_stateid(state, &state->stateid, deleg_flags);
-	open_status = nfs41_check_expired_stateid(state,  &state->open_stateid, open_flags);
+	int status;
 
-	if ((deleg_status == NFS_OK) && (open_status == NFS_OK))
-		return NFS_OK;
-	return nfs4_open_expired(sp, state);
+	nfs41_clear_delegation_stateid(state);
+	status = nfs41_check_open_stateid(state);
+	if (status != NFS_OK)
+		status = nfs4_open_expired(sp, state);
+	return status;
 }
 #endif
 
@@ -2375,11 +2414,15 @@ static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
 	int i, len, status = 0;
 	rpc_authflavor_t flav_array[NFS_MAX_SECFLAVORS];
 
-	len = gss_mech_list_pseudoflavors(&flav_array[0]);
-	flav_array[len] = RPC_AUTH_NULL;
-	len += 1;
+	len = rpcauth_list_flavors(flav_array, ARRAY_SIZE(flav_array));
+	BUG_ON(len < 0);
 
 	for (i = 0; i < len; i++) {
+		/* AUTH_UNIX is the default flavor if none was specified,
+		 * thus has already been tried. */
+		if (flav_array[i] == RPC_AUTH_UNIX)
+			continue;
+
 		status = nfs4_lookup_root_sec(server, fhandle, info, flav_array[i]);
 		if (status == -NFS4ERR_WRONGSEC || status == -EACCES)
 			continue;
@@ -2766,9 +2809,7 @@ static int nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry)
  *
  * In the case of WRITE, we also want to put the GETATTR after
  * the operation -- in this case because we want to make sure
- * we get the post-operation mtime and size.  This means that
- * we can't use xdr_encode_pages() as written: we need a variant
- * of it which would leave room in the 'tail' iovec.
+ * we get the post-operation mtime and size.
  *
  * Both of these changes to the XDR layer would in fact be quite
  * minor, but I decided to leave them for a subsequent patch.
@@ -2821,7 +2862,9 @@ nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
 		return PTR_ERR(ctx);
 
 	sattr->ia_mode &= ~current_umask();
-	state = nfs4_do_open(dir, dentry, ctx->mode, flags, sattr, ctx->cred, NULL);
+	state = nfs4_do_open(dir, dentry, ctx->mode,
+			flags, sattr, ctx->cred,
+			&ctx->mdsthreshold);
 	d_drop(dentry);
 	if (IS_ERR(state)) {
 		status = PTR_ERR(state);
@@ -3315,8 +3358,14 @@ static int nfs4_do_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, str
 
 static int nfs4_proc_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsinfo *fsinfo)
 {
+	int error;
+
 	nfs_fattr_init(fsinfo->fattr);
-	return nfs4_do_fsinfo(server, fhandle, fsinfo);
+	error = nfs4_do_fsinfo(server, fhandle, fsinfo);
+	if (error == 0)
+		set_pnfs_layoutdriver(server, fhandle, fsinfo->layouttype);
+
+	return error;
 }
 
 static int _nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
@@ -3443,7 +3492,7 @@ bool nfs4_write_need_cache_consistency_data(const struct nfs_write_data *data)
 	/* Otherwise, request attributes if and only if we don't hold
 	 * a delegation
 	 */
-	return nfs_have_delegation(hdr->inode, FMODE_READ) == 0;
+	return nfs4_have_delegation(hdr->inode, FMODE_READ) == 0;
 }
 
 static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_message *msg)
@@ -3732,7 +3781,8 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 		.rpc_argp = &args,
 		.rpc_resp = &res,
 	};
-	int ret = -ENOMEM, npages, i, acl_len = 0;
+	int ret = -ENOMEM, npages, i;
+	size_t acl_len = 0;
 
 	npages = (buflen + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	/* As long as we're doing a round trip to the server anyway,
@@ -3847,7 +3897,7 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
 	i = buf_to_pages_noslab(buf, buflen, arg.acl_pages, &arg.acl_pgbase);
 	if (i < 0)
 		return i;
-	nfs_inode_return_delegation(inode);
+	nfs4_inode_return_delegation(inode);
 	ret = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
 
 	/*
@@ -3961,6 +4011,16 @@ static void nfs4_init_boot_verifier(const struct nfs_client *clp,
 	memcpy(bootverf->data, verf, sizeof(bootverf->data));
 }
 
+/**
+ * nfs4_proc_setclientid - Negotiate client ID
+ * @clp: state data structure
+ * @program: RPC program for NFSv4 callback service
+ * @port: IP port number for NFS4 callback service
+ * @cred: RPC credential to use for this call
+ * @res: where to place the result
+ *
+ * Returns zero, a negative errno, or a negative NFS4ERR status code.
+ */
 int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
 		unsigned short port, struct rpc_cred *cred,
 		struct nfs4_setclientid_res *res)
@@ -3977,44 +4037,44 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
 		.rpc_resp = res,
 		.rpc_cred = cred,
 	};
-	int loop = 0;
 	int status;
 
+	/* nfs_client_id4 */
 	nfs4_init_boot_verifier(clp, &sc_verifier);
-
-	for(;;) {
-		rcu_read_lock();
-		setclientid.sc_name_len = scnprintf(setclientid.sc_name,
-				sizeof(setclientid.sc_name), "%s/%s %s %s %u",
-				clp->cl_ipaddr,
-				rpc_peeraddr2str(clp->cl_rpcclient,
-							RPC_DISPLAY_ADDR),
-				rpc_peeraddr2str(clp->cl_rpcclient,
-							RPC_DISPLAY_PROTO),
-				clp->cl_rpcclient->cl_auth->au_ops->au_name,
-				clp->cl_id_uniquifier);
-		setclientid.sc_netid_len = scnprintf(setclientid.sc_netid,
+	rcu_read_lock();
+	setclientid.sc_name_len = scnprintf(setclientid.sc_name,
+			sizeof(setclientid.sc_name), "%s/%s %s",
+			clp->cl_ipaddr,
+			rpc_peeraddr2str(clp->cl_rpcclient,
+						RPC_DISPLAY_ADDR),
+			rpc_peeraddr2str(clp->cl_rpcclient,
+						RPC_DISPLAY_PROTO));
+	/* cb_client4 */
+	setclientid.sc_netid_len = scnprintf(setclientid.sc_netid,
 				sizeof(setclientid.sc_netid),
 				rpc_peeraddr2str(clp->cl_rpcclient,
 							RPC_DISPLAY_NETID));
-		setclientid.sc_uaddr_len = scnprintf(setclientid.sc_uaddr,
+	rcu_read_unlock();
+	setclientid.sc_uaddr_len = scnprintf(setclientid.sc_uaddr,
 				sizeof(setclientid.sc_uaddr), "%s.%u.%u",
 				clp->cl_ipaddr, port >> 8, port & 255);
-		rcu_read_unlock();
 
-		status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
-		if (status != -NFS4ERR_CLID_INUSE)
-			break;
-		if (loop != 0) {
-			++clp->cl_id_uniquifier;
-			break;
-		}
-		++loop;
-		ssleep(clp->cl_lease_time / HZ + 1);
-	}
+	dprintk("NFS call  setclientid auth=%s, '%.*s'\n",
+		clp->cl_rpcclient->cl_auth->au_ops->au_name,
+		setclientid.sc_name_len, setclientid.sc_name);
+	status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
+	dprintk("NFS reply setclientid: %d\n", status);
 	return status;
 }
 
+/**
+ * nfs4_proc_setclientid_confirm - Confirm client ID
+ * @clp: state data structure
+ * @res: result of a previous SETCLIENTID
+ * @cred: RPC credential to use for this call
+ *
+ * Returns zero, a negative errno, or a negative NFS4ERR status code.
+ */
 int nfs4_proc_setclientid_confirm(struct nfs_client *clp,
 		struct nfs4_setclientid_res *arg,
 		struct rpc_cred *cred)
@@ -4029,6 +4089,9 @@ int nfs4_proc_setclientid_confirm(struct nfs_client *clp,
 	unsigned long now;
 	int status;
 
+	dprintk("NFS call  setclientid_confirm auth=%s, (client ID %llx)\n",
+		clp->cl_rpcclient->cl_auth->au_ops->au_name,
+		clp->cl_clientid);
 	now = jiffies;
 	status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
 	if (status == 0) {
@@ -4037,6 +4100,7 @@ int nfs4_proc_setclientid_confirm(struct nfs_client *clp,
 		clp->cl_last_renewal = now;
 		spin_unlock(&clp->cl_lock);
 	}
+	dprintk("NFS reply setclientid_confirm: %d\n", status);
 	return status;
 }
 
@@ -4681,9 +4745,17 @@ out:
 }
 
 #if defined(CONFIG_NFS_V4_1)
+/**
+ * nfs41_check_expired_locks - possibly free a lock stateid
+ *
+ * @state: NFSv4 state for an inode
+ *
+ * Returns NFS_OK if recovery for this stateid is now finished.
+ * Otherwise a negative NFS4ERR value is returned.
+ */
 static int nfs41_check_expired_locks(struct nfs4_state *state)
 {
-	int status, ret = NFS_OK;
+	int status, ret = -NFS4ERR_BAD_STATEID;
 	struct nfs4_lock_state *lsp;
 	struct nfs_server *server = NFS_SERVER(state->inode);
 
@@ -4691,7 +4763,11 @@ static int nfs41_check_expired_locks(struct nfs4_state *state)
 		if (lsp->ls_flags & NFS_LOCK_INITIALIZED) {
 			status = nfs41_test_stateid(server, &lsp->ls_stateid);
 			if (status != NFS_OK) {
-				nfs41_free_stateid(server, &lsp->ls_stateid);
+				/* Free the stateid unless the server
+				 * informs us the stateid is unrecognized. */
+				if (status != -NFS4ERR_BAD_STATEID)
+					nfs41_free_stateid(server,
+							&lsp->ls_stateid);
 				lsp->ls_flags &= ~NFS_LOCK_INITIALIZED;
 				ret = status;
 			}
@@ -4707,9 +4783,9 @@ static int nfs41_lock_expired(struct nfs4_state *state, struct file_lock *reques
 
 	if (test_bit(LK_STATE_IN_USE, &state->flags))
 		status = nfs41_check_expired_locks(state);
-	if (status == NFS_OK)
-		return status;
-	return nfs4_lock_expired(state, request);
+	if (status != NFS_OK)
+		status = nfs4_lock_expired(state, request);
+	return status;
 }
 #endif
 
@@ -4807,7 +4883,7 @@ nfs4_proc_lock(struct file *filp, int cmd, struct file_lock *request)
 	 * Don't rely on the VFS having checked the file open mode,
 	 * since it won't do this for flock() locks.
 	 */
-	switch (request->fl_type & (F_RDLCK|F_WRLCK|F_UNLCK)) {
+	switch (request->fl_type) {
 	case F_RDLCK:
 		if (!(filp->f_mode & FMODE_READ))
 			return -EBADF;
@@ -5168,6 +5244,8 @@ out:
 /*
  * nfs4_proc_exchange_id()
  *
+ * Returns zero, a negative errno, or a negative NFS4ERR status code.
+ *
  * Since the clientid has expired, all compounds using sessions
  * associated with the stale clientid will be returning
  * NFS4ERR_BADSESSION in the sequence operation, and will therefore
@@ -5192,16 +5270,14 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
 		.rpc_cred = cred,
 	};
 
-	dprintk("--> %s\n", __func__);
-	BUG_ON(clp == NULL);
-
 	nfs4_init_boot_verifier(clp, &verifier);
-
 	args.id_len = scnprintf(args.id, sizeof(args.id),
-				"%s/%s/%u",
+				"%s/%s",
 				clp->cl_ipaddr,
-				clp->cl_rpcclient->cl_nodename,
-				clp->cl_rpcclient->cl_auth->au_flavor);
+				clp->cl_rpcclient->cl_nodename);
+	dprintk("NFS call  exchange_id auth=%s, '%.*s'\n",
+		clp->cl_rpcclient->cl_auth->au_ops->au_name,
+		args.id_len, args.id);
 
 	res.server_owner = kzalloc(sizeof(struct nfs41_server_owner),
 					GFP_NOFS);
@@ -5264,12 +5340,12 @@ out_server_scope:
 	kfree(res.server_scope);
 out:
 	if (clp->cl_implid != NULL)
-		dprintk("%s: Server Implementation ID: "
+		dprintk("NFS reply exchange_id: Server Implementation ID: "
 			"domain: %s, name: %s, date: %llu,%u\n",
-			__func__, clp->cl_implid->domain, clp->cl_implid->name,
+			clp->cl_implid->domain, clp->cl_implid->name,
 			clp->cl_implid->date.seconds,
 			clp->cl_implid->date.nseconds);
-	dprintk("<-- %s status= %d\n", __func__, status);
+	dprintk("NFS reply exchange_id: %d\n", status);
 	return status;
 }
 
@@ -6570,22 +6646,36 @@ static int _nfs41_test_stateid(struct nfs_server *server, nfs4_stateid *stateid)
 		.rpc_resp = &res,
 	};
 
+	dprintk("NFS call  test_stateid %p\n", stateid);
 	nfs41_init_sequence(&args.seq_args, &res.seq_res, 0);
 	status = nfs4_call_sync_sequence(server->client, server, &msg, &args.seq_args, &res.seq_res, 1);
-
-	if (status == NFS_OK)
-		return res.status;
-	return status;
+	if (status != NFS_OK) {
+		dprintk("NFS reply test_stateid: failed, %d\n", status);
+		return status;
+	}
+	dprintk("NFS reply test_stateid: succeeded, %d\n", -res.status);
+	return -res.status;
 }
 
+/**
+ * nfs41_test_stateid - perform a TEST_STATEID operation
+ *
+ * @server: server / transport on which to perform the operation
+ * @stateid: state ID to test
+ *
+ * Returns NFS_OK if the server recognizes that "stateid" is valid.
+ * Otherwise a negative NFS4ERR value is returned if the operation
+ * failed or the state ID is not currently valid.
+ */
 static int nfs41_test_stateid(struct nfs_server *server, nfs4_stateid *stateid)
 {
 	struct nfs4_exception exception = { };
 	int err;
 	do {
-		err = nfs4_handle_exception(server,
-				_nfs41_test_stateid(server, stateid),
-				&exception);
+		err = _nfs41_test_stateid(server, stateid);
+		if (err != -NFS4ERR_DELAY)
+			break;
+		nfs4_handle_exception(server, err, &exception);
 	} while (exception.retry);
 	return err;
 }
@@ -6601,19 +6691,34 @@ static int _nfs4_free_stateid(struct nfs_server *server, nfs4_stateid *stateid)
 		.rpc_argp = &args,
 		.rpc_resp = &res,
 	};
+	int status;
 
+	dprintk("NFS call  free_stateid %p\n", stateid);
 	nfs41_init_sequence(&args.seq_args, &res.seq_res, 0);
-	return nfs4_call_sync_sequence(server->client, server, &msg, &args.seq_args, &res.seq_res, 1);
+	status = nfs4_call_sync_sequence(server->client, server, &msg,
+					 &args.seq_args, &res.seq_res, 1);
+	dprintk("NFS reply free_stateid: %d\n", status);
+	return status;
 }
 
+/**
+ * nfs41_free_stateid - perform a FREE_STATEID operation
+ *
+ * @server: server / transport on which to perform the operation
+ * @stateid: state ID to release
+ *
+ * Returns NFS_OK if the server freed "stateid".  Otherwise a
+ * negative NFS4ERR value is returned.
+ */
 static int nfs41_free_stateid(struct nfs_server *server, nfs4_stateid *stateid)
 {
 	struct nfs4_exception exception = { };
 	int err;
 	do {
-		err = nfs4_handle_exception(server,
-				_nfs4_free_stateid(server, stateid),
-				&exception);
+		err = _nfs4_free_stateid(server, stateid);
+		if (err != -NFS4ERR_DELAY)
+			break;
+		nfs4_handle_exception(server, err, &exception);
 	} while (exception.retry);
 	return err;
 }
@@ -6725,6 +6830,26 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = {
 #endif
 };
 
+const struct inode_operations nfs4_dir_inode_operations = {
+	.create		= nfs_create,
+	.lookup		= nfs_lookup,
+	.atomic_open	= nfs_atomic_open,
+	.link		= nfs_link,
+	.unlink		= nfs_unlink,
+	.symlink	= nfs_symlink,
+	.mkdir		= nfs_mkdir,
+	.rmdir		= nfs_rmdir,
+	.mknod		= nfs_mknod,
+	.rename		= nfs_rename,
+	.permission	= nfs_permission,
+	.getattr	= nfs_getattr,
+	.setattr	= nfs_setattr,
+	.getxattr	= generic_getxattr,
+	.setxattr	= generic_setxattr,
+	.listxattr	= generic_listxattr,
+	.removexattr	= generic_removexattr,
+};
+
 static const struct inode_operations nfs4_file_inode_operations = {
 	.permission	= nfs_permission,
 	.getattr	= nfs_getattr,
@@ -6743,6 +6868,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.file_ops	= &nfs4_file_operations,
 	.getroot	= nfs4_proc_get_root,
 	.submount	= nfs4_submount,
+	.try_mount	= nfs4_try_mount,
 	.getattr	= nfs4_proc_getattr,
 	.setattr	= nfs4_proc_setattr,
 	.lookup		= nfs4_proc_lookup,
@@ -6769,9 +6895,11 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.set_capabilities = nfs4_server_capabilities,
 	.decode_dirent	= nfs4_decode_dirent,
 	.read_setup	= nfs4_proc_read_setup,
+	.read_pageio_init = pnfs_pageio_init_read,
 	.read_rpc_prepare = nfs4_proc_read_rpc_prepare,
 	.read_done	= nfs4_read_done,
 	.write_setup	= nfs4_proc_write_setup,
+	.write_pageio_init = pnfs_pageio_init_write,
 	.write_rpc_prepare = nfs4_proc_write_rpc_prepare,
 	.write_done	= nfs4_write_done,
 	.commit_setup	= nfs4_proc_commit_setup,
@@ -6781,7 +6909,13 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.clear_acl_cache = nfs4_zap_acl_attr,
 	.close_context  = nfs4_close_context,
 	.open_context	= nfs4_atomic_open,
+	.have_delegation = nfs4_have_delegation,
+	.return_delegation = nfs4_inode_return_delegation,
+	.alloc_client	= nfs4_alloc_client,
 	.init_client	= nfs4_init_client,
+	.free_client	= nfs4_free_client,
+	.create_server	= nfs4_create_server,
+	.clone_server	= nfs_clone_server,
 };
 
 static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = {
@@ -6796,10 +6930,6 @@ const struct xattr_handler *nfs4_xattr_handlers[] = {
 	NULL
 };
 
-module_param(max_session_slots, ushort, 0644);
-MODULE_PARM_DESC(max_session_slots, "Maximum number of outstanding NFSv4.1 "
-		"requests the client will negotiate");
-
 /*
  * Local variables:
  *  c-basic-offset: 8
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index f38300e9f171..55148def5540 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1606,10 +1606,15 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status)
 			return -ESERVERFAULT;
 		/* Lease confirmation error: retry after purging the lease */
 		ssleep(1);
-	case -NFS4ERR_CLID_INUSE:
 	case -NFS4ERR_STALE_CLIENTID:
 		clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
 		break;
+	case -NFS4ERR_CLID_INUSE:
+		pr_err("NFS: Server %s reports our clientid is in use\n",
+			clp->cl_hostname);
+		nfs_mark_client_ready(clp, -EPERM);
+		clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+		return -EPERM;
 	case -EACCES:
 		if (clp->cl_machine_cred == NULL)
 			return -EACCES;
@@ -1642,7 +1647,7 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status)
 	return 0;
 }
 
-static int nfs4_reclaim_lease(struct nfs_client *clp)
+static int nfs4_establish_lease(struct nfs_client *clp)
 {
 	struct rpc_cred *cred;
 	const struct nfs4_state_recovery_ops *ops =
@@ -1655,7 +1660,41 @@ static int nfs4_reclaim_lease(struct nfs_client *clp)
 	status = ops->establish_clid(clp, cred);
 	put_rpccred(cred);
 	if (status != 0)
+		return status;
+	pnfs_destroy_all_layouts(clp);
+	return 0;
+}
+
+/*
+ * Returns zero or a negative errno.  NFS4ERR values are converted
+ * to local errno values.
+ */
+static int nfs4_reclaim_lease(struct nfs_client *clp)
+{
+	int status;
+
+	status = nfs4_establish_lease(clp);
+	if (status < 0)
+		return nfs4_handle_reclaim_lease_error(clp, status);
+	if (test_and_clear_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH, &clp->cl_state))
+		nfs4_state_start_reclaim_nograce(clp);
+	if (!test_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state))
+		set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state);
+	clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state);
+	clear_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+	return 0;
+}
+
+static int nfs4_purge_lease(struct nfs_client *clp)
+{
+	int status;
+
+	status = nfs4_establish_lease(clp);
+	if (status < 0)
 		return nfs4_handle_reclaim_lease_error(clp, status);
+	clear_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state);
+	set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+	nfs4_state_start_reclaim_nograce(clp);
 	return 0;
 }
 
@@ -1764,6 +1803,8 @@ static int nfs4_reset_session(struct nfs_client *clp)
 	struct rpc_cred *cred;
 	int status;
 
+	if (!nfs4_has_session(clp))
+		return 0;
 	nfs4_begin_drain_session(clp);
 	cred = nfs4_get_exchange_id_cred(clp);
 	status = nfs4_proc_destroy_session(clp->cl_session, cred);
@@ -1792,12 +1833,14 @@ out:
 
 static int nfs4_recall_slot(struct nfs_client *clp)
 {
-	struct nfs4_slot_table *fc_tbl = &clp->cl_session->fc_slot_table;
-	struct nfs4_channel_attrs *fc_attrs = &clp->cl_session->fc_attrs;
+	struct nfs4_slot_table *fc_tbl;
 	struct nfs4_slot *new, *old;
 	int i;
 
+	if (!nfs4_has_session(clp))
+		return 0;
 	nfs4_begin_drain_session(clp);
+	fc_tbl = &clp->cl_session->fc_slot_table;
 	new = kmalloc(fc_tbl->target_max_slots * sizeof(struct nfs4_slot),
 		      GFP_NOFS);
         if (!new)
@@ -1810,11 +1853,10 @@ static int nfs4_recall_slot(struct nfs_client *clp)
 	fc_tbl->slots = new;
 	fc_tbl->max_slots = fc_tbl->target_max_slots;
 	fc_tbl->target_max_slots = 0;
-	fc_attrs->max_reqs = fc_tbl->max_slots;
+	clp->cl_session->fc_attrs.max_reqs = fc_tbl->max_slots;
 	spin_unlock(&fc_tbl->slot_tbl_lock);
 
 	kfree(old);
-	nfs4_end_drain_session(clp);
 	return 0;
 }
 
@@ -1823,6 +1865,8 @@ static int nfs4_bind_conn_to_session(struct nfs_client *clp)
 	struct rpc_cred *cred;
 	int ret;
 
+	if (!nfs4_has_session(clp))
+		return 0;
 	nfs4_begin_drain_session(clp);
 	cred = nfs4_get_exchange_id_cred(clp);
 	ret = nfs4_proc_bind_conn_to_session(clp, cred);
@@ -1857,37 +1901,29 @@ static int nfs4_bind_conn_to_session(struct nfs_client *clp)
 static void nfs4_state_manager(struct nfs_client *clp)
 {
 	int status = 0;
+	const char *section = "", *section_sep = "";
 
 	/* Ensure exclusive access to NFSv4 state */
 	do {
 		if (test_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state)) {
-			status = nfs4_reclaim_lease(clp);
+			section = "purge state";
+			status = nfs4_purge_lease(clp);
 			if (status < 0)
 				goto out_error;
-			clear_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state);
-			set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+			continue;
 		}
 
-		if (test_and_clear_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) {
+		if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) {
+			section = "lease expired";
 			/* We're going to have to re-establish a clientid */
 			status = nfs4_reclaim_lease(clp);
 			if (status < 0)
 				goto out_error;
-			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
-				continue;
-			clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state);
-
-			if (test_and_clear_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH,
-					       &clp->cl_state))
-				nfs4_state_start_reclaim_nograce(clp);
-			else
-				set_bit(NFS4CLNT_RECLAIM_REBOOT,
-					&clp->cl_state);
-
-			pnfs_destroy_all_layouts(clp);
+			continue;
 		}
 
 		if (test_and_clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state)) {
+			section = "check lease";
 			status = nfs4_check_lease(clp);
 			if (status < 0)
 				goto out_error;
@@ -1896,8 +1932,8 @@ static void nfs4_state_manager(struct nfs_client *clp)
 		}
 
 		/* Initialize or reset the session */
-		if (test_and_clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state)
-		   && nfs4_has_session(clp)) {
+		if (test_and_clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state)) {
+			section = "reset session";
 			status = nfs4_reset_session(clp);
 			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
 				continue;
@@ -1907,15 +1943,26 @@ static void nfs4_state_manager(struct nfs_client *clp)
 
 		/* Send BIND_CONN_TO_SESSION */
 		if (test_and_clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION,
-				&clp->cl_state) && nfs4_has_session(clp)) {
+				&clp->cl_state)) {
+			section = "bind conn to session";
 			status = nfs4_bind_conn_to_session(clp);
 			if (status < 0)
 				goto out_error;
 			continue;
 		}
 
+		/* Recall session slots */
+		if (test_and_clear_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state)) {
+			section = "recall slot";
+			status = nfs4_recall_slot(clp);
+			if (status < 0)
+				goto out_error;
+			continue;
+		}
+
 		/* First recover reboot state... */
 		if (test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state)) {
+			section = "reclaim reboot";
 			status = nfs4_do_reclaim(clp,
 				clp->cl_mvops->reboot_recovery_ops);
 			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) ||
@@ -1930,6 +1977,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
 
 		/* Now recover expired state... */
 		if (test_and_clear_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state)) {
+			section = "reclaim nograce";
 			status = nfs4_do_reclaim(clp,
 				clp->cl_mvops->nograce_recovery_ops);
 			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) ||
@@ -1945,15 +1993,6 @@ static void nfs4_state_manager(struct nfs_client *clp)
 			nfs_client_return_marked_delegations(clp);
 			continue;
 		}
-		/* Recall session slots */
-		if (test_and_clear_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state)
-		   && nfs4_has_session(clp)) {
-			status = nfs4_recall_slot(clp);
-			if (status < 0)
-				goto out_error;
-			continue;
-		}
-
 
 		nfs4_clear_state_manager_bit(clp);
 		/* Did we race with an attempt to give us more work? */
@@ -1964,8 +2003,11 @@ static void nfs4_state_manager(struct nfs_client *clp)
 	} while (atomic_read(&clp->cl_count) > 1);
 	return;
 out_error:
-	pr_warn_ratelimited("NFS: state manager failed on NFSv4 server %s"
-			" with error %d\n", clp->cl_hostname, -status);
+	if (strlen(section))
+		section_sep = ": ";
+	pr_warn_ratelimited("NFS: state manager%s%s failed on NFSv4 server %s"
+			" with error %d\n", section_sep, section,
+			clp->cl_hostname, -status);
 	nfs4_end_drain_session(clp);
 	nfs4_clear_state_manager_bit(clp);
 }
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
new file mode 100644
index 000000000000..12a31a9dbcdd
--- /dev/null
+++ b/fs/nfs/nfs4super.c
@@ -0,0 +1,372 @@
+/*
+ * Copyright (c) 2012 Bryan Schumaker <bjschuma@netapp.com>
+ */
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/nfs_idmap.h>
+#include <linux/nfs4_mount.h>
+#include <linux/nfs_fs.h>
+#include "delegation.h"
+#include "internal.h"
+#include "nfs4_fs.h"
+#include "pnfs.h"
+#include "nfs.h"
+
+#define NFSDBG_FACILITY		NFSDBG_VFS
+
+static int nfs4_write_inode(struct inode *inode, struct writeback_control *wbc);
+static void nfs4_evict_inode(struct inode *inode);
+static struct dentry *nfs4_remote_mount(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *raw_data);
+static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *raw_data);
+static struct dentry *nfs4_remote_referral_mount(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *raw_data);
+
+static struct file_system_type nfs4_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "nfs4",
+	.mount		= nfs_fs_mount,
+	.kill_sb	= nfs_kill_super,
+	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+};
+
+static struct file_system_type nfs4_remote_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "nfs4",
+	.mount		= nfs4_remote_mount,
+	.kill_sb	= nfs_kill_super,
+	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+};
+
+static struct file_system_type nfs4_remote_referral_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "nfs4",
+	.mount		= nfs4_remote_referral_mount,
+	.kill_sb	= nfs_kill_super,
+	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+};
+
+struct file_system_type nfs4_referral_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "nfs4",
+	.mount		= nfs4_referral_mount,
+	.kill_sb	= nfs_kill_super,
+	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+};
+
+static const struct super_operations nfs4_sops = {
+	.alloc_inode	= nfs_alloc_inode,
+	.destroy_inode	= nfs_destroy_inode,
+	.write_inode	= nfs4_write_inode,
+	.put_super	= nfs_put_super,
+	.statfs		= nfs_statfs,
+	.evict_inode	= nfs4_evict_inode,
+	.umount_begin	= nfs_umount_begin,
+	.show_options	= nfs_show_options,
+	.show_devname	= nfs_show_devname,
+	.show_path	= nfs_show_path,
+	.show_stats	= nfs_show_stats,
+	.remount_fs	= nfs_remount,
+};
+
+struct nfs_subversion nfs_v4 = {
+	.owner = THIS_MODULE,
+	.nfs_fs   = &nfs4_fs_type,
+	.rpc_vers = &nfs_version4,
+	.rpc_ops  = &nfs_v4_clientops,
+	.sops     = &nfs4_sops,
+	.xattr    = nfs4_xattr_handlers,
+};
+
+static int nfs4_write_inode(struct inode *inode, struct writeback_control *wbc)
+{
+	int ret = nfs_write_inode(inode, wbc);
+
+	if (ret >= 0 && test_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(inode)->flags)) {
+		int status;
+		bool sync = true;
+
+		if (wbc->sync_mode == WB_SYNC_NONE)
+			sync = false;
+
+		status = pnfs_layoutcommit_inode(inode, sync);
+		if (status < 0)
+			return status;
+	}
+	return ret;
+}
+
+/*
+ * Clean out any remaining NFSv4 state that might be left over due
+ * to open() calls that passed nfs_atomic_lookup, but failed to call
+ * nfs_open().
+ */
+static void nfs4_evict_inode(struct inode *inode)
+{
+	truncate_inode_pages(&inode->i_data, 0);
+	clear_inode(inode);
+	pnfs_return_layout(inode);
+	pnfs_destroy_layout(NFS_I(inode));
+	/* If we are holding a delegation, return it! */
+	nfs_inode_return_delegation_noreclaim(inode);
+	/* First call standard NFS clear_inode() code */
+	nfs_clear_inode(inode);
+}
+
+/*
+ * Get the superblock for the NFS4 root partition
+ */
+static struct dentry *
+nfs4_remote_mount(struct file_system_type *fs_type, int flags,
+		  const char *dev_name, void *info)
+{
+	struct nfs_mount_info *mount_info = info;
+	struct nfs_server *server;
+	struct dentry *mntroot = ERR_PTR(-ENOMEM);
+
+	mount_info->set_security = nfs_set_sb_security;
+
+	/* Get a volume representation */
+	server = nfs4_create_server(mount_info, &nfs_v4);
+	if (IS_ERR(server)) {
+		mntroot = ERR_CAST(server);
+		goto out;
+	}
+
+	mntroot = nfs_fs_mount_common(server, flags, dev_name, mount_info, &nfs_v4);
+
+out:
+	return mntroot;
+}
+
+static struct vfsmount *nfs_do_root_mount(struct file_system_type *fs_type,
+		int flags, void *data, const char *hostname)
+{
+	struct vfsmount *root_mnt;
+	char *root_devname;
+	size_t len;
+
+	len = strlen(hostname) + 5;
+	root_devname = kmalloc(len, GFP_KERNEL);
+	if (root_devname == NULL)
+		return ERR_PTR(-ENOMEM);
+	/* Does hostname needs to be enclosed in brackets? */
+	if (strchr(hostname, ':'))
+		snprintf(root_devname, len, "[%s]:/", hostname);
+	else
+		snprintf(root_devname, len, "%s:/", hostname);
+	root_mnt = vfs_kern_mount(fs_type, flags, root_devname, data);
+	kfree(root_devname);
+	return root_mnt;
+}
+
+struct nfs_referral_count {
+	struct list_head list;
+	const struct task_struct *task;
+	unsigned int referral_count;
+};
+
+static LIST_HEAD(nfs_referral_count_list);
+static DEFINE_SPINLOCK(nfs_referral_count_list_lock);
+
+static struct nfs_referral_count *nfs_find_referral_count(void)
+{
+	struct nfs_referral_count *p;
+
+	list_for_each_entry(p, &nfs_referral_count_list, list) {
+		if (p->task == current)
+			return p;
+	}
+	return NULL;
+}
+
+#define NFS_MAX_NESTED_REFERRALS 2
+
+static int nfs_referral_loop_protect(void)
+{
+	struct nfs_referral_count *p, *new;
+	int ret = -ENOMEM;
+
+	new = kmalloc(sizeof(*new), GFP_KERNEL);
+	if (!new)
+		goto out;
+	new->task = current;
+	new->referral_count = 1;
+
+	ret = 0;
+	spin_lock(&nfs_referral_count_list_lock);
+	p = nfs_find_referral_count();
+	if (p != NULL) {
+		if (p->referral_count >= NFS_MAX_NESTED_REFERRALS)
+			ret = -ELOOP;
+		else
+			p->referral_count++;
+	} else {
+		list_add(&new->list, &nfs_referral_count_list);
+		new = NULL;
+	}
+	spin_unlock(&nfs_referral_count_list_lock);
+	kfree(new);
+out:
+	return ret;
+}
+
+static void nfs_referral_loop_unprotect(void)
+{
+	struct nfs_referral_count *p;
+
+	spin_lock(&nfs_referral_count_list_lock);
+	p = nfs_find_referral_count();
+	p->referral_count--;
+	if (p->referral_count == 0)
+		list_del(&p->list);
+	else
+		p = NULL;
+	spin_unlock(&nfs_referral_count_list_lock);
+	kfree(p);
+}
+
+static struct dentry *nfs_follow_remote_path(struct vfsmount *root_mnt,
+		const char *export_path)
+{
+	struct dentry *dentry;
+	int err;
+
+	if (IS_ERR(root_mnt))
+		return ERR_CAST(root_mnt);
+
+	err = nfs_referral_loop_protect();
+	if (err) {
+		mntput(root_mnt);
+		return ERR_PTR(err);
+	}
+
+	dentry = mount_subtree(root_mnt, export_path);
+	nfs_referral_loop_unprotect();
+
+	return dentry;
+}
+
+struct dentry *nfs4_try_mount(int flags, const char *dev_name,
+			      struct nfs_mount_info *mount_info,
+			      struct nfs_subversion *nfs_mod)
+{
+	char *export_path;
+	struct vfsmount *root_mnt;
+	struct dentry *res;
+	struct nfs_parsed_mount_data *data = mount_info->parsed;
+
+	dfprintk(MOUNT, "--> nfs4_try_mount()\n");
+
+	export_path = data->nfs_server.export_path;
+	data->nfs_server.export_path = "/";
+	root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, mount_info,
+			data->nfs_server.hostname);
+	data->nfs_server.export_path = export_path;
+
+	res = nfs_follow_remote_path(root_mnt, export_path);
+
+	dfprintk(MOUNT, "<-- nfs4_try_mount() = %ld%s\n",
+			IS_ERR(res) ? PTR_ERR(res) : 0,
+			IS_ERR(res) ? " [error]" : "");
+	return res;
+}
+
+static struct dentry *
+nfs4_remote_referral_mount(struct file_system_type *fs_type, int flags,
+			   const char *dev_name, void *raw_data)
+{
+	struct nfs_mount_info mount_info = {
+		.fill_super = nfs_fill_super,
+		.set_security = nfs_clone_sb_security,
+		.cloned = raw_data,
+	};
+	struct nfs_server *server;
+	struct dentry *mntroot = ERR_PTR(-ENOMEM);
+
+	dprintk("--> nfs4_referral_get_sb()\n");
+
+	mount_info.mntfh = nfs_alloc_fhandle();
+	if (mount_info.cloned == NULL || mount_info.mntfh == NULL)
+		goto out;
+
+	/* create a new volume representation */
+	server = nfs4_create_referral_server(mount_info.cloned, mount_info.mntfh);
+	if (IS_ERR(server)) {
+		mntroot = ERR_CAST(server);
+		goto out;
+	}
+
+	mntroot = nfs_fs_mount_common(server, flags, dev_name, &mount_info, &nfs_v4);
+out:
+	nfs_free_fhandle(mount_info.mntfh);
+	return mntroot;
+}
+
+/*
+ * Create an NFS4 server record on referral traversal
+ */
+static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type,
+		int flags, const char *dev_name, void *raw_data)
+{
+	struct nfs_clone_mount *data = raw_data;
+	char *export_path;
+	struct vfsmount *root_mnt;
+	struct dentry *res;
+
+	dprintk("--> nfs4_referral_mount()\n");
+
+	export_path = data->mnt_path;
+	data->mnt_path = "/";
+
+	root_mnt = nfs_do_root_mount(&nfs4_remote_referral_fs_type,
+			flags, data, data->hostname);
+	data->mnt_path = export_path;
+
+	res = nfs_follow_remote_path(root_mnt, export_path);
+	dprintk("<-- nfs4_referral_mount() = %ld%s\n",
+			IS_ERR(res) ? PTR_ERR(res) : 0,
+			IS_ERR(res) ? " [error]" : "");
+	return res;
+}
+
+
+static int __init init_nfs_v4(void)
+{
+	int err;
+
+	err = nfs_idmap_init();
+	if (err)
+		goto out;
+
+	err = nfs4_register_sysctl();
+	if (err)
+		goto out1;
+
+	err = register_filesystem(&nfs4_fs_type);
+	if (err < 0)
+		goto out2;
+
+	register_nfs_version(&nfs_v4);
+	return 0;
+out2:
+	nfs4_unregister_sysctl();
+out1:
+	nfs_idmap_quit();
+out:
+	return err;
+}
+
+static void __exit exit_nfs_v4(void)
+{
+	unregister_nfs_version(&nfs_v4);
+	unregister_filesystem(&nfs4_fs_type);
+	nfs4_unregister_sysctl();
+	nfs_idmap_quit();
+}
+
+MODULE_LICENSE("GPL");
+
+module_init(init_nfs_v4);
+module_exit(exit_nfs_v4);
diff --git a/fs/nfs/nfs4sysctl.c b/fs/nfs/nfs4sysctl.c
new file mode 100644
index 000000000000..5729bc8aa75d
--- /dev/null
+++ b/fs/nfs/nfs4sysctl.c
@@ -0,0 +1,68 @@
+/*
+ * linux/fs/nfs/nfs4sysctl.c
+ *
+ * Sysctl interface to NFS v4 parameters
+ *
+ * Copyright (c) 2006 Trond Myklebust <Trond.Myklebust@netapp.com>
+ */
+#include <linux/sysctl.h>
+#include <linux/nfs_idmap.h>
+#include <linux/nfs_fs.h>
+
+#include "callback.h"
+
+static const int nfs_set_port_min = 0;
+static const int nfs_set_port_max = 65535;
+static struct ctl_table_header *nfs4_callback_sysctl_table;
+
+static ctl_table nfs4_cb_sysctls[] = {
+	{
+		.procname = "nfs_callback_tcpport",
+		.data = &nfs_callback_set_tcpport,
+		.maxlen = sizeof(int),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_minmax,
+		.extra1 = (int *)&nfs_set_port_min,
+		.extra2 = (int *)&nfs_set_port_max,
+	},
+	{
+		.procname = "idmap_cache_timeout",
+		.data = &nfs_idmap_cache_timeout,
+		.maxlen = sizeof(int),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_jiffies,
+	},
+	{ }
+};
+
+static ctl_table nfs4_cb_sysctl_dir[] = {
+	{
+		.procname = "nfs",
+		.mode = 0555,
+		.child = nfs4_cb_sysctls,
+	},
+	{ }
+};
+
+static ctl_table nfs4_cb_sysctl_root[] = {
+	{
+		.procname = "fs",
+		.mode = 0555,
+		.child = nfs4_cb_sysctl_dir,
+	},
+	{ }
+};
+
+int nfs4_register_sysctl(void)
+{
+	nfs4_callback_sysctl_table = register_sysctl_table(nfs4_cb_sysctl_root);
+	if (nfs4_callback_sysctl_table == NULL)
+		return -ENOMEM;
+	return 0;
+}
+
+void nfs4_unregister_sysctl(void)
+{
+	unregister_sysctl_table(nfs4_callback_sysctl_table);
+	nfs4_callback_sysctl_table = NULL;
+}
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 18fae29b0301..ca13483edd60 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -852,12 +852,6 @@ const u32 nfs41_maxread_overhead = ((RPC_MAX_HEADER_WITH_AUTH +
 				    XDR_UNIT);
 #endif /* CONFIG_NFS_V4_1 */
 
-static unsigned short send_implementation_id = 1;
-
-module_param(send_implementation_id, ushort, 0644);
-MODULE_PARM_DESC(send_implementation_id,
-		"Send implementation ID with NFSv4.1 exchange_id");
-
 static const umode_t nfs_type2fmt[] = {
 	[NF4BAD] = 0,
 	[NF4REG] = S_IFREG,
@@ -1236,7 +1230,7 @@ static void encode_link(struct xdr_stream *xdr, const struct qstr *name, struct
 
 static inline int nfs4_lock_type(struct file_lock *fl, int block)
 {
-	if ((fl->fl_type & (F_RDLCK|F_WRLCK|F_UNLCK)) == F_RDLCK)
+	if (fl->fl_type == F_RDLCK)
 		return block ? NFS4_READW_LT : NFS4_READ_LT;
 	return block ? NFS4_WRITEW_LT : NFS4_WRITE_LT;
 }
@@ -3078,7 +3072,7 @@ out_overflow:
 	return -EIO;
 }
 
-static inline int decode_attr_length(struct xdr_stream *xdr, uint32_t *attrlen, __be32 **savep)
+static int decode_attr_length(struct xdr_stream *xdr, uint32_t *attrlen, unsigned int *savep)
 {
 	__be32 *p;
 
@@ -3086,7 +3080,7 @@ static inline int decode_attr_length(struct xdr_stream *xdr, uint32_t *attrlen,
 	if (unlikely(!p))
 		goto out_overflow;
 	*attrlen = be32_to_cpup(p);
-	*savep = xdr->p;
+	*savep = xdr_stream_pos(xdr);
 	return 0;
 out_overflow:
 	print_overflow_msg(__func__, xdr);
@@ -4068,10 +4062,10 @@ static int decode_attr_time_modify(struct xdr_stream *xdr, uint32_t *bitmap, str
 	return status;
 }
 
-static int verify_attr_len(struct xdr_stream *xdr, __be32 *savep, uint32_t attrlen)
+static int verify_attr_len(struct xdr_stream *xdr, unsigned int savep, uint32_t attrlen)
 {
 	unsigned int attrwords = XDR_QUADLEN(attrlen);
-	unsigned int nwords = xdr->p - savep;
+	unsigned int nwords = (xdr_stream_pos(xdr) - savep) >> 2;
 
 	if (unlikely(attrwords != nwords)) {
 		dprintk("%s: server returned incorrect attribute length: "
@@ -4158,13 +4152,18 @@ static int decode_verifier(struct xdr_stream *xdr, void *verifier)
 	return decode_opaque_fixed(xdr, verifier, NFS4_VERIFIER_SIZE);
 }
 
+static int decode_write_verifier(struct xdr_stream *xdr, struct nfs_write_verifier *verifier)
+{
+	return decode_opaque_fixed(xdr, verifier->data, NFS4_VERIFIER_SIZE);
+}
+
 static int decode_commit(struct xdr_stream *xdr, struct nfs_commitres *res)
 {
 	int status;
 
 	status = decode_op_hdr(xdr, OP_COMMIT);
 	if (!status)
-		status = decode_verifier(xdr, res->verf->verifier);
+		status = decode_write_verifier(xdr, &res->verf->verifier);
 	return status;
 }
 
@@ -4193,7 +4192,7 @@ out_overflow:
 
 static int decode_server_caps(struct xdr_stream *xdr, struct nfs4_server_caps_res *res)
 {
-	__be32 *savep;
+	unsigned int savep;
 	uint32_t attrlen, bitmap[3] = {0};
 	int status;
 
@@ -4222,7 +4221,7 @@ xdr_error:
 
 static int decode_statfs(struct xdr_stream *xdr, struct nfs_fsstat *fsstat)
 {
-	__be32 *savep;
+	unsigned int savep;
 	uint32_t attrlen, bitmap[3] = {0};
 	int status;
 
@@ -4254,7 +4253,7 @@ xdr_error:
 
 static int decode_pathconf(struct xdr_stream *xdr, struct nfs_pathconf *pathconf)
 {
-	__be32 *savep;
+	unsigned int savep;
 	uint32_t attrlen, bitmap[3] = {0};
 	int status;
 
@@ -4299,7 +4298,8 @@ out_overflow:
 static int decode_first_threshold_item4(struct xdr_stream *xdr,
 					struct nfs4_threshold *res)
 {
-	__be32 *p, *savep;
+	__be32 *p;
+	unsigned int savep;
 	uint32_t bitmap[3] = {0,}, attrlen;
 	int status;
 
@@ -4503,7 +4503,7 @@ static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fat
 		struct nfs_fh *fh, struct nfs4_fs_locations *fs_loc,
 		const struct nfs_server *server)
 {
-	__be32 *savep;
+	unsigned int savep;
 	uint32_t attrlen,
 		 bitmap[3] = {0};
 	int status;
@@ -4615,7 +4615,7 @@ static int decode_attr_layout_blksize(struct xdr_stream *xdr, uint32_t *bitmap,
 
 static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
 {
-	__be32 *savep;
+	unsigned int savep;
 	uint32_t attrlen, bitmap[3];
 	int status;
 
@@ -4920,9 +4920,8 @@ static int decode_putrootfh(struct xdr_stream *xdr)
 
 static int decode_read(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs_readres *res)
 {
-	struct kvec *iov = req->rq_rcv_buf.head;
 	__be32 *p;
-	uint32_t count, eof, recvd, hdrlen;
+	uint32_t count, eof, recvd;
 	int status;
 
 	status = decode_op_hdr(xdr, OP_READ);
@@ -4933,15 +4932,13 @@ static int decode_read(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs_
 		goto out_overflow;
 	eof = be32_to_cpup(p++);
 	count = be32_to_cpup(p);
-	hdrlen = (u8 *) xdr->p - (u8 *) iov->iov_base;
-	recvd = req->rq_rcv_buf.len - hdrlen;
+	recvd = xdr_read_pages(xdr, count);
 	if (count > recvd) {
 		dprintk("NFS: server cheating in read reply: "
 				"count %u > recvd %u\n", count, recvd);
 		count = recvd;
 		eof = 0;
 	}
-	xdr_read_pages(xdr, count);
 	res->eof = eof;
 	res->count = count;
 	return 0;
@@ -4952,10 +4949,6 @@ out_overflow:
 
 static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs4_readdir_res *readdir)
 {
-	struct xdr_buf	*rcvbuf = &req->rq_rcv_buf;
-	struct kvec	*iov = rcvbuf->head;
-	size_t		hdrlen;
-	u32		recvd, pglen = rcvbuf->page_len;
 	int		status;
 	__be32		verf[2];
 
@@ -4967,22 +4960,12 @@ static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct n
 	memcpy(verf, readdir->verifier.data, sizeof(verf));
 	dprintk("%s: verifier = %08x:%08x\n",
 			__func__, verf[0], verf[1]);
-
-	hdrlen = (char *) xdr->p - (char *) iov->iov_base;
-	recvd = rcvbuf->len - hdrlen;
-	if (pglen > recvd)
-		pglen = recvd;
-	xdr_read_pages(xdr, pglen);
-
-
-	return pglen;
+	return xdr_read_pages(xdr, xdr->buf->page_len);
 }
 
 static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req)
 {
 	struct xdr_buf *rcvbuf = &req->rq_rcv_buf;
-	struct kvec *iov = rcvbuf->head;
-	size_t hdrlen;
 	u32 len, recvd;
 	__be32 *p;
 	int status;
@@ -5000,14 +4983,12 @@ static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req)
 		dprintk("nfs: server returned giant symlink!\n");
 		return -ENAMETOOLONG;
 	}
-	hdrlen = (char *) xdr->p - (char *) iov->iov_base;
-	recvd = req->rq_rcv_buf.len - hdrlen;
+	recvd = xdr_read_pages(xdr, len);
 	if (recvd < len) {
 		dprintk("NFS: server cheating in readlink reply: "
 				"count %u > recvd %u\n", len, recvd);
 		return -EIO;
 	}
-	xdr_read_pages(xdr, len);
 	/*
 	 * The XDR encode routine has set things up so that
 	 * the link text will be copied directly into the
@@ -5063,10 +5044,10 @@ decode_restorefh(struct xdr_stream *xdr)
 static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 			 struct nfs_getaclres *res)
 {
-	__be32 *savep, *bm_p;
+	unsigned int savep;
+	__be32 *bm_p;
 	uint32_t attrlen,
 		 bitmap[3] = {0};
-	struct kvec *iov = req->rq_rcv_buf.head;
 	int status;
 	size_t page_len = xdr->buf->page_len;
 
@@ -5089,7 +5070,6 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 	if (unlikely(bitmap[0] & (FATTR4_WORD0_ACL - 1U)))
 		return -EIO;
 	if (likely(bitmap[0] & FATTR4_WORD0_ACL)) {
-		size_t hdrlen;
 
 		/* The bitmap (xdr len + bitmaps) and the attr xdr len words
 		 * are stored with the acl data to handle the problem of
@@ -5098,7 +5078,6 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 
 		/* We ignore &savep and don't do consistency checks on
 		 * the attr length.  Let userspace figure it out.... */
-		hdrlen = (u8 *)xdr->p - (u8 *)iov->iov_base;
 		attrlen += res->acl_data_offset;
 		if (attrlen > page_len) {
 			if (res->acl_flags & NFS4_ACL_LEN_REQUEST) {
@@ -5212,13 +5191,12 @@ static int decode_write(struct xdr_stream *xdr, struct nfs_writeres *res)
 	if (status)
 		return status;
 
-	p = xdr_inline_decode(xdr, 16);
+	p = xdr_inline_decode(xdr, 8);
 	if (unlikely(!p))
 		goto out_overflow;
 	res->count = be32_to_cpup(p++);
 	res->verf->committed = be32_to_cpup(p++);
-	memcpy(res->verf->verifier, p, NFS4_VERIFIER_SIZE);
-	return 0;
+	return decode_write_verifier(xdr, &res->verf->verifier);
 out_overflow:
 	print_overflow_msg(__func__, xdr);
 	return -EIO;
@@ -5599,7 +5577,7 @@ static int decode_getdevicelist(struct xdr_stream *xdr,
 {
 	__be32 *p;
 	int status, i;
-	struct nfs_writeverf verftemp;
+	nfs4_verifier verftemp;
 
 	status = decode_op_hdr(xdr, OP_GETDEVICELIST);
 	if (status)
@@ -5613,7 +5591,7 @@ static int decode_getdevicelist(struct xdr_stream *xdr,
 	p += 2;
 
 	/* Read verifier */
-	p = xdr_decode_opaque_fixed(p, verftemp.verifier, NFS4_VERIFIER_SIZE);
+	p = xdr_decode_opaque_fixed(p, verftemp.data, NFS4_VERIFIER_SIZE);
 
 	res->num_devs = be32_to_cpup(p);
 
@@ -5707,9 +5685,7 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
 	__be32 *p;
 	int status;
 	u32 layout_count;
-	struct xdr_buf *rcvbuf = &req->rq_rcv_buf;
-	struct kvec *iov = rcvbuf->head;
-	u32 hdrlen, recvd;
+	u32 recvd;
 
 	status = decode_op_hdr(xdr, OP_LAYOUTGET);
 	if (status)
@@ -5746,8 +5722,7 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
 		res->type,
 		res->layoutp->len);
 
-	hdrlen = (u8 *) xdr->p - (u8 *) iov->iov_base;
-	recvd = req->rq_rcv_buf.len - hdrlen;
+	recvd = xdr_read_pages(xdr, res->layoutp->len);
 	if (res->layoutp->len > recvd) {
 		dprintk("NFS: server cheating in layoutget reply: "
 				"layout len %u > recvd %u\n",
@@ -5755,8 +5730,6 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
 		return -EINVAL;
 	}
 
-	xdr_read_pages(xdr, res->layoutp->len);
-
 	if (layout_count > 1) {
 		/* We only handle a length one array at the moment.  Any
 		 * further entries are just ignored.  Note that this means
@@ -7103,6 +7076,7 @@ out:
 int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 		       int plus)
 {
+	unsigned int savep;
 	uint32_t bitmap[3] = {0};
 	uint32_t len;
 	__be32 *p = xdr_inline_decode(xdr, 4);
@@ -7141,7 +7115,7 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 	if (decode_attr_bitmap(xdr, bitmap) < 0)
 		goto out_overflow;
 
-	if (decode_attr_length(xdr, &len, &p) < 0)
+	if (decode_attr_length(xdr, &len, &savep) < 0)
 		goto out_overflow;
 
 	if (decode_getfattr_attrs(xdr, bitmap, entry->fattr, entry->fh,
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index aed913c833f4..1a6732ed04a4 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -54,6 +54,7 @@ void nfs_pgheader_init(struct nfs_pageio_descriptor *desc,
 	if (hdr->completion_ops->init_hdr)
 		hdr->completion_ops->init_hdr(hdr);
 }
+EXPORT_SYMBOL_GPL(nfs_pgheader_init);
 
 void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos)
 {
@@ -70,7 +71,7 @@ void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos)
 static inline struct nfs_page *
 nfs_page_alloc(void)
 {
-	struct nfs_page	*p = kmem_cache_zalloc(nfs_page_cachep, GFP_KERNEL);
+	struct nfs_page	*p = kmem_cache_zalloc(nfs_page_cachep, GFP_NOIO);
 	if (p)
 		INIT_LIST_HEAD(&p->wb_list);
 	return p;
@@ -117,7 +118,7 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode,
 	 * 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->index;
+	req->wb_index	= page_file_index(page);
 	page_cache_get(page);
 	req->wb_offset  = offset;
 	req->wb_pgbase	= offset;
@@ -268,6 +269,7 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 	desc->pg_lseg = NULL;
 	desc->pg_dreq = NULL;
 }
+EXPORT_SYMBOL_GPL(nfs_pageio_init);
 
 /**
  * nfs_can_coalesce_requests - test two requests for compatibility
@@ -409,6 +411,7 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
 	} while (ret);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(nfs_pageio_add_request);
 
 /**
  * nfs_pageio_complete - Complete I/O on an nfs_pageio_descriptor
@@ -424,6 +427,7 @@ void nfs_pageio_complete(struct nfs_pageio_descriptor *desc)
 			break;
 	}
 }
+EXPORT_SYMBOL_GPL(nfs_pageio_complete);
 
 /**
  * nfs_pageio_cond_complete - Conditional I/O completion
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index bbc49caa7a82..76875bfcf19c 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -651,7 +651,14 @@ out_err_free:
 	return NULL;
 }
 
-/* Initiates a LAYOUTRETURN(FILE) */
+/*
+ * Initiates a LAYOUTRETURN(FILE), and removes the pnfs_layout_hdr
+ * when the layout segment list is empty.
+ *
+ * Note that a pnfs_layout_hdr can exist with an empty layout segment
+ * list when LAYOUTGET has failed, or when LAYOUTGET succeeded, but the
+ * deviceid is marked invalid.
+ */
 int
 _pnfs_return_layout(struct inode *ino)
 {
@@ -660,22 +667,31 @@ _pnfs_return_layout(struct inode *ino)
 	LIST_HEAD(tmp_list);
 	struct nfs4_layoutreturn *lrp;
 	nfs4_stateid stateid;
-	int status = 0;
+	int status = 0, empty;
 
-	dprintk("--> %s\n", __func__);
+	dprintk("NFS: %s for inode %lu\n", __func__, ino->i_ino);
 
 	spin_lock(&ino->i_lock);
 	lo = nfsi->layout;
-	if (!lo) {
+	if (!lo || pnfs_test_layout_returned(lo)) {
 		spin_unlock(&ino->i_lock);
-		dprintk("%s: no layout to return\n", __func__);
-		return status;
+		dprintk("NFS: %s no layout to return\n", __func__);
+		goto out;
 	}
 	stateid = nfsi->layout->plh_stateid;
 	/* Reference matched in nfs4_layoutreturn_release */
 	get_layout_hdr(lo);
+	empty = list_empty(&lo->plh_segs);
 	mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
+	/* Don't send a LAYOUTRETURN if list was initially empty */
+	if (empty) {
+		spin_unlock(&ino->i_lock);
+		put_layout_hdr(lo);
+		dprintk("NFS: %s no layout segments to return\n", __func__);
+		goto out;
+	}
 	lo->plh_block_lgets++;
+	pnfs_mark_layout_returned(lo);
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&tmp_list);
 
@@ -686,6 +702,7 @@ _pnfs_return_layout(struct inode *ino)
 		status = -ENOMEM;
 		set_bit(NFS_LAYOUT_RW_FAILED, &lo->plh_flags);
 		set_bit(NFS_LAYOUT_RO_FAILED, &lo->plh_flags);
+		pnfs_clear_layout_returned(lo);
 		put_layout_hdr(lo);
 		goto out;
 	}
@@ -1075,6 +1092,10 @@ pnfs_update_layout(struct inode *ino,
 	get_layout_hdr(lo);
 	if (list_empty(&lo->plh_segs))
 		first = true;
+
+	/* Enable LAYOUTRETURNs */
+	pnfs_clear_layout_returned(lo);
+
 	spin_unlock(&ino->i_lock);
 	if (first) {
 		/* The lo must be on the clp list if there is any
@@ -1209,7 +1230,7 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_write);
 
-bool
+void
 pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode,
 		      const struct nfs_pgio_completion_ops *compl_ops)
 {
@@ -1217,13 +1238,12 @@ pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode,
 	struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld;
 
 	if (ld == NULL)
-		return false;
-	nfs_pageio_init(pgio, inode, ld->pg_read_ops, compl_ops,
-			server->rsize, 0);
-	return true;
+		nfs_pageio_init_read(pgio, inode, compl_ops);
+	else
+		nfs_pageio_init(pgio, inode, ld->pg_read_ops, compl_ops, server->rsize, 0);
 }
 
-bool
+void
 pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode,
 		       int ioflags,
 		       const struct nfs_pgio_completion_ops *compl_ops)
@@ -1232,10 +1252,9 @@ pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode,
 	struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld;
 
 	if (ld == NULL)
-		return false;
-	nfs_pageio_init(pgio, inode, ld->pg_write_ops, compl_ops,
-			server->wsize, ioflags);
-	return true;
+		nfs_pageio_init_write(pgio, inode, ioflags, compl_ops);
+	else
+		nfs_pageio_init(pgio, inode, ld->pg_write_ops, compl_ops, server->wsize, ioflags);
 }
 
 bool
@@ -1272,7 +1291,7 @@ int pnfs_write_done_resend_to_mds(struct inode *inode,
 	LIST_HEAD(failed);
 
 	/* Resend all requests through the MDS */
-	nfs_pageio_init_write_mds(&pgio, inode, FLUSH_STABLE, compl_ops);
+	nfs_pageio_init_write(&pgio, inode, FLUSH_STABLE, compl_ops);
 	while (!list_empty(head)) {
 		struct nfs_page *req = nfs_list_entry(head->next);
 
@@ -1388,6 +1407,7 @@ static void pnfs_writehdr_free(struct nfs_pgio_header *hdr)
 	put_lseg(hdr->lseg);
 	nfs_writehdr_free(hdr);
 }
+EXPORT_SYMBOL_GPL(pnfs_writehdr_free);
 
 int
 pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
@@ -1427,7 +1447,7 @@ int pnfs_read_done_resend_to_mds(struct inode *inode,
 	LIST_HEAD(failed);
 
 	/* Resend all requests through the MDS */
-	nfs_pageio_init_read_mds(&pgio, inode, compl_ops);
+	nfs_pageio_init_read(&pgio, inode, compl_ops);
 	while (!list_empty(head)) {
 		struct nfs_page *req = nfs_list_entry(head->next);
 
@@ -1542,6 +1562,7 @@ static void pnfs_readhdr_free(struct nfs_pgio_header *hdr)
 	put_lseg(hdr->lseg);
 	nfs_readhdr_free(hdr);
 }
+EXPORT_SYMBOL_GPL(pnfs_readhdr_free);
 
 int
 pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 64f90d845f6a..2c6c80503ba4 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -64,6 +64,7 @@ enum {
 	NFS_LAYOUT_ROC,			/* some lseg had roc bit set */
 	NFS_LAYOUT_DESTROYED,		/* no new use of layout allowed */
 	NFS_LAYOUT_INVALID,		/* layout is being destroyed */
+	NFS_LAYOUT_RETURNED,		/* layout has already been returned */
 };
 
 enum layoutdriver_policy_flags {
@@ -178,9 +179,9 @@ extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp);
 void get_layout_hdr(struct pnfs_layout_hdr *lo);
 void put_lseg(struct pnfs_layout_segment *lseg);
 
-bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *,
+void pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *,
 			   const struct nfs_pgio_completion_ops *);
-bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *,
+void pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *,
 			    int, const struct nfs_pgio_completion_ops *);
 
 void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, u32);
@@ -255,6 +256,24 @@ struct nfs4_deviceid_node *nfs4_insert_deviceid_node(struct nfs4_deviceid_node *
 bool nfs4_put_deviceid_node(struct nfs4_deviceid_node *);
 void nfs4_deviceid_purge_client(const struct nfs_client *);
 
+static inline void
+pnfs_mark_layout_returned(struct pnfs_layout_hdr *lo)
+{
+	set_bit(NFS_LAYOUT_RETURNED, &lo->plh_flags);
+}
+
+static inline void
+pnfs_clear_layout_returned(struct pnfs_layout_hdr *lo)
+{
+	clear_bit(NFS_LAYOUT_RETURNED, &lo->plh_flags);
+}
+
+static inline bool
+pnfs_test_layout_returned(struct pnfs_layout_hdr *lo)
+{
+	return test_bit(NFS_LAYOUT_RETURNED, &lo->plh_flags);
+}
+
 static inline int lo_fail_bit(u32 iomode)
 {
 	return iomode == IOMODE_RW ?
@@ -438,16 +457,16 @@ static inline void unset_pnfs_layoutdriver(struct nfs_server *s)
 {
 }
 
-static inline bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode,
+static inline void pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode,
 					 const struct nfs_pgio_completion_ops *compl_ops)
 {
-	return false;
+	nfs_pageio_init_read(pgio, inode, compl_ops);
 }
 
-static inline bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags,
+static inline void pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags,
 					  const struct nfs_pgio_completion_ops *compl_ops)
 {
-	return false;
+	nfs_pageio_init_write(pgio, inode, ioflags, compl_ops);
 }
 
 static inline int
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index 4433806e116f..50a88c3546ed 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -734,6 +734,38 @@ out_einval:
 	return -EINVAL;
 }
 
+static int nfs_have_delegation(struct inode *inode, fmode_t flags)
+{
+	return 0;
+}
+
+static int nfs_return_delegation(struct inode *inode)
+{
+	nfs_wb_all(inode);
+	return 0;
+}
+
+static const struct inode_operations nfs_dir_inode_operations = {
+	.create		= nfs_create,
+	.lookup		= nfs_lookup,
+	.link		= nfs_link,
+	.unlink		= nfs_unlink,
+	.symlink	= nfs_symlink,
+	.mkdir		= nfs_mkdir,
+	.rmdir		= nfs_rmdir,
+	.mknod		= nfs_mknod,
+	.rename		= nfs_rename,
+	.permission	= nfs_permission,
+	.getattr	= nfs_getattr,
+	.setattr	= nfs_setattr,
+};
+
+static const struct inode_operations nfs_file_inode_operations = {
+	.permission	= nfs_permission,
+	.getattr	= nfs_getattr,
+	.setattr	= nfs_setattr,
+};
+
 const struct nfs_rpc_ops nfs_v2_clientops = {
 	.version	= 2,		       /* protocol version */
 	.dentry_ops	= &nfs_dentry_operations,
@@ -742,6 +774,7 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
 	.file_ops	= &nfs_file_operations,
 	.getroot	= nfs_proc_get_root,
 	.submount	= nfs_submount,
+	.try_mount	= nfs_try_mount,
 	.getattr	= nfs_proc_getattr,
 	.setattr	= nfs_proc_setattr,
 	.lookup		= nfs_proc_lookup,
@@ -767,9 +800,11 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
 	.pathconf	= nfs_proc_pathconf,
 	.decode_dirent	= nfs2_decode_dirent,
 	.read_setup	= nfs_proc_read_setup,
+	.read_pageio_init = nfs_pageio_init_read,
 	.read_rpc_prepare = nfs_proc_read_rpc_prepare,
 	.read_done	= nfs_read_done,
 	.write_setup	= nfs_proc_write_setup,
+	.write_pageio_init = nfs_pageio_init_write,
 	.write_rpc_prepare = nfs_proc_write_rpc_prepare,
 	.write_done	= nfs_write_done,
 	.commit_setup	= nfs_proc_commit_setup,
@@ -777,5 +812,11 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
 	.lock		= nfs_proc_lock,
 	.lock_check_bounds = nfs_lock_check_bounds,
 	.close_context	= nfs_close_context,
+	.have_delegation = nfs_have_delegation,
+	.return_delegation = nfs_return_delegation,
+	.alloc_client	= nfs_alloc_client,
 	.init_client	= nfs_init_client,
+	.free_client	= nfs_free_client,
+	.create_server	= nfs_create_server,
+	.clone_server	= nfs_clone_server,
 };
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 86ced7836214..b6bdb18e892c 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -20,8 +20,6 @@
 #include <linux/nfs_page.h>
 #include <linux/module.h>
 
-#include "pnfs.h"
-
 #include "nfs4_fs.h"
 #include "internal.h"
 #include "iostat.h"
@@ -50,6 +48,7 @@ struct nfs_read_header *nfs_readhdr_alloc(void)
 	}
 	return rhdr;
 }
+EXPORT_SYMBOL_GPL(nfs_readhdr_alloc);
 
 static struct nfs_read_data *nfs_readdata_alloc(struct nfs_pgio_header *hdr,
 						unsigned int pagecount)
@@ -82,6 +81,7 @@ void nfs_readhdr_free(struct nfs_pgio_header *hdr)
 
 	kmem_cache_free(nfs_rdata_cachep, rhdr);
 }
+EXPORT_SYMBOL_GPL(nfs_readhdr_free);
 
 void nfs_readdata_release(struct nfs_read_data *rdata)
 {
@@ -98,6 +98,7 @@ void nfs_readdata_release(struct nfs_read_data *rdata)
 	if (atomic_dec_and_test(&hdr->refcnt))
 		hdr->completion_ops->completion(hdr);
 }
+EXPORT_SYMBOL_GPL(nfs_readdata_release);
 
 static
 int nfs_return_empty_page(struct page *page)
@@ -108,13 +109,14 @@ int nfs_return_empty_page(struct page *page)
 	return 0;
 }
 
-void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio,
+void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
 			      struct inode *inode,
 			      const struct nfs_pgio_completion_ops *compl_ops)
 {
 	nfs_pageio_init(pgio, inode, &nfs_pageio_read_ops, compl_ops,
 			NFS_SERVER(inode)->rsize, 0);
 }
+EXPORT_SYMBOL_GPL(nfs_pageio_init_read);
 
 void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio)
 {
@@ -123,14 +125,6 @@ void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio)
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds);
 
-void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
-			  struct inode *inode,
-			  const struct nfs_pgio_completion_ops *compl_ops)
-{
-	if (!pnfs_pageio_init_read(pgio, inode, compl_ops))
-		nfs_pageio_init_read_mds(pgio, inode, compl_ops);
-}
-
 int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 		       struct page *page)
 {
@@ -149,7 +143,7 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 	if (len < PAGE_CACHE_SIZE)
 		zero_user_segment(page, len, PAGE_CACHE_SIZE);
 
-	nfs_pageio_init_read(&pgio, inode, &nfs_async_read_completion_ops);
+	NFS_PROTO(inode)->read_pageio_init(&pgio, inode, &nfs_async_read_completion_ops);
 	nfs_pageio_add_request(&pgio, new);
 	nfs_pageio_complete(&pgio);
 	NFS_I(inode)->read_io += pgio.pg_bytes_written;
@@ -407,6 +401,7 @@ int nfs_generic_pagein(struct nfs_pageio_descriptor *desc,
 		return nfs_pagein_multi(desc, hdr);
 	return nfs_pagein_one(desc, hdr);
 }
+EXPORT_SYMBOL_GPL(nfs_generic_pagein);
 
 static int nfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
 {
@@ -532,11 +527,11 @@ static const struct rpc_call_ops nfs_read_common_ops = {
 int nfs_readpage(struct file *file, struct page *page)
 {
 	struct nfs_open_context *ctx;
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	int		error;
 
 	dprintk("NFS: nfs_readpage (%p %ld@%lu)\n",
-		page, PAGE_CACHE_SIZE, page->index);
+		page, PAGE_CACHE_SIZE, page_file_index(page));
 	nfs_inc_stats(inode, NFSIOS_VFSREADPAGE);
 	nfs_add_stats(inode, NFSIOS_READPAGES, 1);
 
@@ -590,7 +585,7 @@ static int
 readpage_async_filler(void *data, struct page *page)
 {
 	struct nfs_readdesc *desc = (struct nfs_readdesc *)data;
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	struct nfs_page *new;
 	unsigned int len;
 	int error;
@@ -652,7 +647,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 	if (ret == 0)
 		goto read_complete; /* all pages were read */
 
-	nfs_pageio_init_read(&pgio, inode, &nfs_async_read_completion_ops);
+	NFS_PROTO(inode)->read_pageio_init(&pgio, inode, &nfs_async_read_completion_ops);
 
 	ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc);
 
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 8b2a2977b720..ac6a3c55dce4 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -64,11 +64,12 @@
 #include "internal.h"
 #include "fscache.h"
 #include "pnfs.h"
+#include "nfs.h"
 
 #define NFSDBG_FACILITY		NFSDBG_VFS
 #define NFS_TEXT_DATA		1
 
-#ifdef CONFIG_NFS_V3
+#if IS_ENABLED(CONFIG_NFS_V3)
 #define NFS_DEFAULT_VERSION 3
 #else
 #define NFS_DEFAULT_VERSION 2
@@ -278,37 +279,17 @@ static match_table_t nfs_vers_tokens = {
 	{ Opt_vers_err, NULL }
 };
 
-struct nfs_mount_info {
-	void (*fill_super)(struct super_block *, struct nfs_mount_info *);
-	int (*set_security)(struct super_block *, struct dentry *, struct nfs_mount_info *);
-	struct nfs_parsed_mount_data *parsed;
-	struct nfs_clone_mount *cloned;
-	struct nfs_fh *mntfh;
-};
-
-static void nfs_umount_begin(struct super_block *);
-static int  nfs_statfs(struct dentry *, struct kstatfs *);
-static int  nfs_show_options(struct seq_file *, struct dentry *);
-static int  nfs_show_devname(struct seq_file *, struct dentry *);
-static int  nfs_show_path(struct seq_file *, struct dentry *);
-static int  nfs_show_stats(struct seq_file *, struct dentry *);
-static struct dentry *nfs_fs_mount_common(struct file_system_type *,
-		struct nfs_server *, int, const char *, struct nfs_mount_info *);
-static struct dentry *nfs_fs_mount(struct file_system_type *,
-		int, const char *, void *);
 static struct dentry *nfs_xdev_mount(struct file_system_type *fs_type,
 		int flags, const char *dev_name, void *raw_data);
-static void nfs_put_super(struct super_block *);
-static void nfs_kill_super(struct super_block *);
-static int nfs_remount(struct super_block *sb, int *flags, char *raw_data);
 
-static struct file_system_type nfs_fs_type = {
+struct file_system_type nfs_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "nfs",
 	.mount		= nfs_fs_mount,
 	.kill_sb	= nfs_kill_super,
 	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
 };
+EXPORT_SYMBOL_GPL(nfs_fs_type);
 
 struct file_system_type nfs_xdev_fs_type = {
 	.owner		= THIS_MODULE,
@@ -318,7 +299,7 @@ struct file_system_type nfs_xdev_fs_type = {
 	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
 };
 
-static const struct super_operations nfs_sops = {
+const struct super_operations nfs_sops = {
 	.alloc_inode	= nfs_alloc_inode,
 	.destroy_inode	= nfs_destroy_inode,
 	.write_inode	= nfs_write_inode,
@@ -332,77 +313,12 @@ static const struct super_operations nfs_sops = {
 	.show_stats	= nfs_show_stats,
 	.remount_fs	= nfs_remount,
 };
+EXPORT_SYMBOL_GPL(nfs_sops);
 
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *);
 static int nfs4_validate_mount_data(void *options,
 	struct nfs_parsed_mount_data *args, const char *dev_name);
-static struct dentry *nfs4_try_mount(int flags, const char *dev_name,
-	struct nfs_mount_info *mount_info);
-static struct dentry *nfs4_remote_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *raw_data);
-static struct dentry *nfs4_xdev_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *raw_data);
-static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *raw_data);
-static struct dentry *nfs4_remote_referral_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *raw_data);
-static void nfs4_kill_super(struct super_block *sb);
-
-static struct file_system_type nfs4_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "nfs4",
-	.mount		= nfs_fs_mount,
-	.kill_sb	= nfs4_kill_super,
-	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
-};
-
-static struct file_system_type nfs4_remote_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "nfs4",
-	.mount		= nfs4_remote_mount,
-	.kill_sb	= nfs4_kill_super,
-	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
-};
-
-struct file_system_type nfs4_xdev_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "nfs4",
-	.mount		= nfs4_xdev_mount,
-	.kill_sb	= nfs4_kill_super,
-	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
-};
-
-static struct file_system_type nfs4_remote_referral_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "nfs4",
-	.mount		= nfs4_remote_referral_mount,
-	.kill_sb	= nfs4_kill_super,
-	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
-};
-
-struct file_system_type nfs4_referral_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "nfs4",
-	.mount		= nfs4_referral_mount,
-	.kill_sb	= nfs4_kill_super,
-	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
-};
-
-static const struct super_operations nfs4_sops = {
-	.alloc_inode	= nfs_alloc_inode,
-	.destroy_inode	= nfs_destroy_inode,
-	.write_inode	= nfs_write_inode,
-	.put_super	= nfs_put_super,
-	.statfs		= nfs_statfs,
-	.evict_inode	= nfs4_evict_inode,
-	.umount_begin	= nfs_umount_begin,
-	.show_options	= nfs_show_options,
-	.show_devname	= nfs_show_devname,
-	.show_path	= nfs_show_path,
-	.show_stats	= nfs_show_stats,
-	.remount_fs	= nfs_remount,
-};
 #endif
 
 static struct shrinker acl_shrinker = {
@@ -424,18 +340,9 @@ int __init register_nfs_fs(void)
 	ret = nfs_register_sysctl();
 	if (ret < 0)
 		goto error_1;
-#ifdef CONFIG_NFS_V4
-	ret = register_filesystem(&nfs4_fs_type);
-	if (ret < 0)
-		goto error_2;
-#endif
 	register_shrinker(&acl_shrinker);
 	return 0;
 
-#ifdef CONFIG_NFS_V4
-error_2:
-	nfs_unregister_sysctl();
-#endif
 error_1:
 	unregister_filesystem(&nfs_fs_type);
 error_0:
@@ -448,9 +355,6 @@ error_0:
 void __exit unregister_nfs_fs(void)
 {
 	unregister_shrinker(&acl_shrinker);
-#ifdef CONFIG_NFS_V4
-	unregister_filesystem(&nfs4_fs_type);
-#endif
 	nfs_unregister_sysctl();
 	unregister_filesystem(&nfs_fs_type);
 }
@@ -462,6 +366,7 @@ void nfs_sb_active(struct super_block *sb)
 	if (atomic_inc_return(&server->active) == 1)
 		atomic_inc(&sb->s_active);
 }
+EXPORT_SYMBOL_GPL(nfs_sb_active);
 
 void nfs_sb_deactive(struct super_block *sb)
 {
@@ -470,11 +375,12 @@ void nfs_sb_deactive(struct super_block *sb)
 	if (atomic_dec_and_test(&server->active))
 		deactivate_super(sb);
 }
+EXPORT_SYMBOL_GPL(nfs_sb_deactive);
 
 /*
  * Deliver file system statistics to userspace
  */
-static int nfs_statfs(struct dentry *dentry, struct kstatfs *buf)
+int nfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct nfs_server *server = NFS_SB(dentry->d_sb);
 	unsigned char blockbits;
@@ -535,6 +441,7 @@ static int nfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	dprintk("%s: statfs error = %d\n", __func__, -error);
 	return error;
 }
+EXPORT_SYMBOL_GPL(nfs_statfs);
 
 /*
  * Map the security flavour number to a name
@@ -640,7 +547,7 @@ static void nfs_show_mountd_options(struct seq_file *m, struct nfs_server *nfss,
 	nfs_show_mountd_netid(m, nfss, showdefaults);
 }
 
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 static void nfs_show_nfsv4_options(struct seq_file *m, struct nfs_server *nfss,
 				    int showdefaults)
 {
@@ -757,7 +664,7 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 /*
  * Describe the mount options on this VFS mountpoint
  */
-static int nfs_show_options(struct seq_file *m, struct dentry *root)
+int nfs_show_options(struct seq_file *m, struct dentry *root)
 {
 	struct nfs_server *nfss = NFS_SB(root->d_sb);
 
@@ -771,8 +678,9 @@ static int nfs_show_options(struct seq_file *m, struct dentry *root)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nfs_show_options);
 
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 #ifdef CONFIG_NFS_V4_1
 static void show_sessions(struct seq_file *m, struct nfs_server *server)
 {
@@ -805,7 +713,7 @@ static void show_implementation_id(struct seq_file *m, struct nfs_server *nfss)
 	}
 }
 #else
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 static void show_pnfs(struct seq_file *m, struct nfs_server *server)
 {
 }
@@ -815,7 +723,7 @@ static void show_implementation_id(struct seq_file *m, struct nfs_server *nfss)
 }
 #endif
 
-static int nfs_show_devname(struct seq_file *m, struct dentry *root)
+int nfs_show_devname(struct seq_file *m, struct dentry *root)
 {
 	char *page = (char *) __get_free_page(GFP_KERNEL);
 	char *devname, *dummy;
@@ -830,17 +738,19 @@ static int nfs_show_devname(struct seq_file *m, struct dentry *root)
 	free_page((unsigned long)page);
 	return err;
 }
+EXPORT_SYMBOL_GPL(nfs_show_devname);
 
-static int nfs_show_path(struct seq_file *m, struct dentry *dentry)
+int nfs_show_path(struct seq_file *m, struct dentry *dentry)
 {
 	seq_puts(m, "/");
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nfs_show_path);
 
 /*
  * Present statistical information for this VFS mountpoint
  */
-static int nfs_show_stats(struct seq_file *m, struct dentry *root)
+int nfs_show_stats(struct seq_file *m, struct dentry *root)
 {
 	int i, cpu;
 	struct nfs_server *nfss = NFS_SB(root->d_sb);
@@ -870,7 +780,7 @@ static int nfs_show_stats(struct seq_file *m, struct dentry *root)
 	seq_printf(m, ",bsize=%u", nfss->bsize);
 	seq_printf(m, ",namlen=%u", nfss->namelen);
 
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 	if (nfss->nfs_client->rpc_ops->version == 4) {
 		seq_printf(m, "\n\tnfsv4:\t");
 		seq_printf(m, "bm0=0x%x", nfss->attr_bitmask[0]);
@@ -928,12 +838,13 @@ static int nfs_show_stats(struct seq_file *m, struct dentry *root)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nfs_show_stats);
 
 /*
  * Begin unmount by attempting to remove all automounted mountpoints we added
  * in response to xdev traversals and referrals
  */
-static void nfs_umount_begin(struct super_block *sb)
+void nfs_umount_begin(struct super_block *sb)
 {
 	struct nfs_server *server;
 	struct rpc_clnt *rpc;
@@ -947,6 +858,7 @@ static void nfs_umount_begin(struct super_block *sb)
 	if (!IS_ERR(rpc))
 		rpc_killall_tasks(rpc);
 }
+EXPORT_SYMBOL_GPL(nfs_umount_begin);
 
 static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(void)
 {
@@ -1748,8 +1660,9 @@ static int nfs_request_mount(struct nfs_parsed_mount_data *args,
 	return nfs_walk_authlist(args, &request);
 }
 
-static struct dentry *nfs_try_mount(int flags, const char *dev_name,
-				    struct nfs_mount_info *mount_info)
+struct dentry *nfs_try_mount(int flags, const char *dev_name,
+			     struct nfs_mount_info *mount_info,
+			     struct nfs_subversion *nfs_mod)
 {
 	int status;
 	struct nfs_server *server;
@@ -1761,12 +1674,13 @@ static struct dentry *nfs_try_mount(int flags, const char *dev_name,
 	}
 
 	/* Get a volume representation */
-	server = nfs_create_server(mount_info->parsed, mount_info->mntfh);
+	server = nfs_mod->rpc_ops->create_server(mount_info, nfs_mod);
 	if (IS_ERR(server))
 		return ERR_CAST(server);
 
-	return nfs_fs_mount_common(&nfs_fs_type, server, flags, dev_name, mount_info);
+	return nfs_fs_mount_common(server, flags, dev_name, mount_info, nfs_mod);
 }
+EXPORT_SYMBOL_GPL(nfs_try_mount);
 
 /*
  * Split "dev_name" into "hostname:export_path".
@@ -1970,7 +1884,7 @@ static int nfs23_validate_mount_data(void *options,
 		return NFS_TEXT_DATA;
 	}
 
-#ifndef CONFIG_NFS_V3
+#if !IS_ENABLED(CONFIG_NFS_V3)
 	if (args->version == 3)
 		goto out_v3_not_compiled;
 #endif /* !CONFIG_NFS_V3 */
@@ -1990,7 +1904,7 @@ out_no_sec:
 	dfprintk(MOUNT, "NFS: nfs_mount_data version supports only AUTH_SYS\n");
 	return -EINVAL;
 
-#ifndef CONFIG_NFS_V3
+#if !IS_ENABLED(CONFIG_NFS_V3)
 out_v3_not_compiled:
 	dfprintk(MOUNT, "NFS: NFSv3 is not compiled into kernel\n");
 	return -EPROTONOSUPPORT;
@@ -2009,7 +1923,7 @@ out_invalid_fh:
 	return -EINVAL;
 }
 
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 static int nfs_validate_mount_data(struct file_system_type *fs_type,
 				   void *options,
 				   struct nfs_parsed_mount_data *args,
@@ -2047,7 +1961,7 @@ static int nfs_validate_text_mount_data(void *options,
 		goto out_no_address;
 
 	if (args->version == 4) {
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 		port = NFS_PORT;
 		max_namelen = NFS4_MAXNAMLEN;
 		max_pathlen = NFS4_MAXPATHLEN;
@@ -2070,7 +1984,7 @@ static int nfs_validate_text_mount_data(void *options,
 				   &args->nfs_server.export_path,
 				   max_pathlen);
 
-#ifndef CONFIG_NFS_V4
+#if !IS_ENABLED(CONFIG_NFS_V4)
 out_v4_not_compiled:
 	dfprintk(MOUNT, "NFS: NFSv4 is not compiled into kernel\n");
 	return -EPROTONOSUPPORT;
@@ -2108,7 +2022,7 @@ nfs_compare_remount_data(struct nfs_server *nfss,
 	return 0;
 }
 
-static int
+int
 nfs_remount(struct super_block *sb, int *flags, char *raw_data)
 {
 	int error;
@@ -2169,11 +2083,12 @@ out:
 	kfree(data);
 	return error;
 }
+EXPORT_SYMBOL_GPL(nfs_remount);
 
 /*
  * Initialise the common bits of the superblock
  */
-static inline void nfs_initialise_sb(struct super_block *sb)
+inline void nfs_initialise_sb(struct super_block *sb)
 {
 	struct nfs_server *server = NFS_SB(sb);
 
@@ -2195,18 +2110,19 @@ static inline void nfs_initialise_sb(struct super_block *sb)
 /*
  * Finish setting up an NFS2/3 superblock
  */
-static void nfs_fill_super(struct super_block *sb,
-			   struct nfs_mount_info *mount_info)
+void nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info)
 {
 	struct nfs_parsed_mount_data *data = mount_info->parsed;
 	struct nfs_server *server = NFS_SB(sb);
 
 	sb->s_blocksize_bits = 0;
 	sb->s_blocksize = 0;
-	if (data->bsize)
+	sb->s_xattr = server->nfs_client->cl_nfs_mod->xattr;
+	sb->s_op = server->nfs_client->cl_nfs_mod->sops;
+	if (data && data->bsize)
 		sb->s_blocksize = nfs_block_size(data->bsize, &sb->s_blocksize_bits);
 
-	if (server->nfs_client->rpc_ops->version == 3) {
+	if (server->nfs_client->rpc_ops->version != 2) {
 		/* The VFS shouldn't apply the umask to mode bits. We will do
 		 * so ourselves when necessary.
 		 */
@@ -2214,15 +2130,14 @@ static void nfs_fill_super(struct super_block *sb,
 		sb->s_time_gran = 1;
 	}
 
-	sb->s_op = &nfs_sops;
  	nfs_initialise_sb(sb);
 }
+EXPORT_SYMBOL_GPL(nfs_fill_super);
 
 /*
- * Finish setting up a cloned NFS2/3 superblock
+ * Finish setting up a cloned NFS2/3/4 superblock
  */
-static void nfs_clone_super(struct super_block *sb,
-			    struct nfs_mount_info *mount_info)
+void nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info)
 {
 	const struct super_block *old_sb = mount_info->cloned->sb;
 	struct nfs_server *server = NFS_SB(sb);
@@ -2230,16 +2145,17 @@ static void nfs_clone_super(struct super_block *sb,
 	sb->s_blocksize_bits = old_sb->s_blocksize_bits;
 	sb->s_blocksize = old_sb->s_blocksize;
 	sb->s_maxbytes = old_sb->s_maxbytes;
+	sb->s_xattr = old_sb->s_xattr;
+	sb->s_op = old_sb->s_op;
+	sb->s_time_gran = 1;
 
-	if (server->nfs_client->rpc_ops->version == 3) {
+	if (server->nfs_client->rpc_ops->version != 2) {
 		/* The VFS shouldn't apply the umask to mode bits. We will do
 		 * so ourselves when necessary.
 		 */
 		sb->s_flags |= MS_POSIXACL;
-		sb->s_time_gran = 1;
 	}
 
-	sb->s_op = old_sb->s_op;
  	nfs_initialise_sb(sb);
 }
 
@@ -2381,14 +2297,15 @@ static int nfs_bdi_register(struct nfs_server *server)
 	return bdi_register_dev(&server->backing_dev_info, server->s_dev);
 }
 
-static int nfs_set_sb_security(struct super_block *s, struct dentry *mntroot,
-			       struct nfs_mount_info *mount_info)
+int nfs_set_sb_security(struct super_block *s, struct dentry *mntroot,
+			struct nfs_mount_info *mount_info)
 {
 	return security_sb_set_mnt_opts(s, &mount_info->parsed->lsm_opts);
 }
+EXPORT_SYMBOL_GPL(nfs_set_sb_security);
 
-static int nfs_clone_sb_security(struct super_block *s, struct dentry *mntroot,
-				 struct nfs_mount_info *mount_info)
+int nfs_clone_sb_security(struct super_block *s, struct dentry *mntroot,
+			  struct nfs_mount_info *mount_info)
 {
 	/* clone any lsm security options from the parent to the new sb */
 	security_sb_clone_mnt_opts(mount_info->cloned->sb, s);
@@ -2396,11 +2313,12 @@ static int nfs_clone_sb_security(struct super_block *s, struct dentry *mntroot,
 		return -ESTALE;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nfs_clone_sb_security);
 
-static struct dentry *nfs_fs_mount_common(struct file_system_type *fs_type,
-					  struct nfs_server *server,
-					  int flags, const char *dev_name,
-					  struct nfs_mount_info *mount_info)
+struct dentry *nfs_fs_mount_common(struct nfs_server *server,
+				   int flags, const char *dev_name,
+				   struct nfs_mount_info *mount_info,
+				   struct nfs_subversion *nfs_mod)
 {
 	struct super_block *s;
 	struct dentry *mntroot = ERR_PTR(-ENOMEM);
@@ -2419,7 +2337,7 @@ static struct dentry *nfs_fs_mount_common(struct file_system_type *fs_type,
 		sb_mntdata.mntflags |= MS_SYNCHRONOUS;
 
 	/* Get a superblock - note that we may end up sharing one that already exists */
-	s = sget(fs_type, compare_super, nfs_set_super, flags, &sb_mntdata);
+	s = sget(nfs_mod->nfs_fs, compare_super, nfs_set_super, flags, &sb_mntdata);
 	if (IS_ERR(s)) {
 		mntroot = ERR_CAST(s);
 		goto out_err_nosb;
@@ -2469,8 +2387,9 @@ error_splat_bdi:
 	deactivate_locked_super(s);
 	goto out;
 }
+EXPORT_SYMBOL_GPL(nfs_fs_mount_common);
 
-static struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
+struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *raw_data)
 {
 	struct nfs_mount_info mount_info = {
@@ -2478,6 +2397,7 @@ static struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
 		.set_security = nfs_set_sb_security,
 	};
 	struct dentry *mntroot = ERR_PTR(-ENOMEM);
+	struct nfs_subversion *nfs_mod;
 	int error;
 
 	mount_info.parsed = nfs_alloc_parsed_mount_data();
@@ -2494,34 +2414,38 @@ static struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
 		goto out;
 	}
 
-#ifdef CONFIG_NFS_V4
-	if (mount_info.parsed->version == 4)
-		mntroot = nfs4_try_mount(flags, dev_name, &mount_info);
-	else
-#endif	/* CONFIG_NFS_V4 */
-		mntroot = nfs_try_mount(flags, dev_name, &mount_info);
+	nfs_mod = get_nfs_version(mount_info.parsed->version);
+	if (IS_ERR(nfs_mod)) {
+		mntroot = ERR_CAST(nfs_mod);
+		goto out;
+	}
+
+	mntroot = nfs_mod->rpc_ops->try_mount(flags, dev_name, &mount_info, nfs_mod);
 
+	put_nfs_version(nfs_mod);
 out:
 	nfs_free_parsed_mount_data(mount_info.parsed);
 	nfs_free_fhandle(mount_info.mntfh);
 	return mntroot;
 }
+EXPORT_SYMBOL_GPL(nfs_fs_mount);
 
 /*
  * Ensure that we unregister the bdi before kill_anon_super
  * releases the device name
  */
-static void nfs_put_super(struct super_block *s)
+void nfs_put_super(struct super_block *s)
 {
 	struct nfs_server *server = NFS_SB(s);
 
 	bdi_unregister(&server->backing_dev_info);
 }
+EXPORT_SYMBOL_GPL(nfs_put_super);
 
 /*
  * Destroy an NFS2/3 superblock
  */
-static void nfs_kill_super(struct super_block *s)
+void nfs_kill_super(struct super_block *s)
 {
 	struct nfs_server *server = NFS_SB(s);
 
@@ -2529,31 +2453,38 @@ static void nfs_kill_super(struct super_block *s)
 	nfs_fscache_release_super_cookie(s);
 	nfs_free_server(server);
 }
+EXPORT_SYMBOL_GPL(nfs_kill_super);
 
 /*
  * Clone an NFS2/3/4 server record on xdev traversal (FSID-change)
  */
-static struct dentry *
-nfs_xdev_mount_common(struct file_system_type *fs_type, int flags,
-		const char *dev_name, struct nfs_mount_info *mount_info)
+struct dentry *
+nfs_xdev_mount(struct file_system_type *fs_type, int flags,
+		const char *dev_name, void *raw_data)
 {
-	struct nfs_clone_mount *data = mount_info->cloned;
+	struct nfs_clone_mount *data = raw_data;
+	struct nfs_mount_info mount_info = {
+		.fill_super = nfs_clone_super,
+		.set_security = nfs_clone_sb_security,
+		.cloned = data,
+	};
 	struct nfs_server *server;
 	struct dentry *mntroot = ERR_PTR(-ENOMEM);
+	struct nfs_subversion *nfs_mod = NFS_SB(data->sb)->nfs_client->cl_nfs_mod;
 	int error;
 
 	dprintk("--> nfs_xdev_mount_common()\n");
 
-	mount_info->mntfh = data->fh;
+	mount_info.mntfh = mount_info.cloned->fh;
 
 	/* create a new volume representation */
-	server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr, data->authflavor);
+	server = nfs_mod->rpc_ops->clone_server(NFS_SB(data->sb), data->fh, data->fattr, data->authflavor);
 	if (IS_ERR(server)) {
 		error = PTR_ERR(server);
 		goto out_err;
 	}
 
-	mntroot = nfs_fs_mount_common(fs_type, server, flags, dev_name, mount_info);
+	mntroot = nfs_fs_mount_common(server, flags, dev_name, &mount_info, nfs_mod);
 	dprintk("<-- nfs_xdev_mount_common() = 0\n");
 out:
 	return mntroot;
@@ -2563,60 +2494,7 @@ out_err:
 	goto out;
 }
 
-/*
- * Clone an NFS2/3 server record on xdev traversal (FSID-change)
- */
-static struct dentry *
-nfs_xdev_mount(struct file_system_type *fs_type, int flags,
-		const char *dev_name, void *raw_data)
-{
-	struct nfs_mount_info mount_info = {
-		.fill_super = nfs_clone_super,
-		.set_security = nfs_clone_sb_security,
-		.cloned   = raw_data,
-	};
-	return nfs_xdev_mount_common(&nfs_fs_type, flags, dev_name, &mount_info);
-}
-
-#ifdef CONFIG_NFS_V4
-
-/*
- * Finish setting up a cloned NFS4 superblock
- */
-static void nfs4_clone_super(struct super_block *sb,
-			     struct nfs_mount_info *mount_info)
-{
-	const struct super_block *old_sb = mount_info->cloned->sb;
-	sb->s_blocksize_bits = old_sb->s_blocksize_bits;
-	sb->s_blocksize = old_sb->s_blocksize;
-	sb->s_maxbytes = old_sb->s_maxbytes;
-	sb->s_time_gran = 1;
-	sb->s_op = old_sb->s_op;
-	/*
-	 * The VFS shouldn't apply the umask to mode bits. We will do
-	 * so ourselves when necessary.
-	 */
-	sb->s_flags  |= MS_POSIXACL;
-	sb->s_xattr  = old_sb->s_xattr;
-	nfs_initialise_sb(sb);
-}
-
-/*
- * Set up an NFS4 superblock
- */
-static void nfs4_fill_super(struct super_block *sb,
-			    struct nfs_mount_info *mount_info)
-{
-	sb->s_time_gran = 1;
-	sb->s_op = &nfs4_sops;
-	/*
-	 * The VFS shouldn't apply the umask to mode bits. We will do
-	 * so ourselves when necessary.
-	 */
-	sb->s_flags  |= MS_POSIXACL;
-	sb->s_xattr = nfs4_xattr_handlers;
-	nfs_initialise_sb(sb);
-}
+#if IS_ENABLED(CONFIG_NFS_V4)
 
 static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *args)
 {
@@ -2716,249 +2594,55 @@ out_no_address:
 }
 
 /*
- * Get the superblock for the NFS4 root partition
+ * NFS v4 module parameters need to stay in the
+ * NFS client for backwards compatibility
  */
-static struct dentry *
-nfs4_remote_mount(struct file_system_type *fs_type, int flags,
-		  const char *dev_name, void *info)
-{
-	struct nfs_mount_info *mount_info = info;
-	struct nfs_server *server;
-	struct dentry *mntroot = ERR_PTR(-ENOMEM);
-
-	mount_info->fill_super = nfs4_fill_super;
-	mount_info->set_security = nfs_set_sb_security;
-
-	/* Get a volume representation */
-	server = nfs4_create_server(mount_info->parsed, mount_info->mntfh);
-	if (IS_ERR(server)) {
-		mntroot = ERR_CAST(server);
-		goto out;
-	}
-
-	mntroot = nfs_fs_mount_common(fs_type, server, flags, dev_name, mount_info);
-
-out:
-	return mntroot;
-}
-
-static struct vfsmount *nfs_do_root_mount(struct file_system_type *fs_type,
-		int flags, void *data, const char *hostname)
-{
-	struct vfsmount *root_mnt;
-	char *root_devname;
-	size_t len;
+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 */
+bool nfs4_disable_idmapping = true;
+unsigned short max_session_slots = NFS4_DEF_SLOT_TABLE_SIZE;
+unsigned short send_implementation_id = 1;
+
+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);
+EXPORT_SYMBOL_GPL(send_implementation_id);
+
+#define NFS_CALLBACK_MAXPORTNR (65535U)
+
+static int param_set_portnr(const char *val, const struct kernel_param *kp)
+{
+	unsigned long num;
+	int ret;
 
-	len = strlen(hostname) + 5;
-	root_devname = kmalloc(len, GFP_KERNEL);
-	if (root_devname == NULL)
-		return ERR_PTR(-ENOMEM);
-	/* Does hostname needs to be enclosed in brackets? */
-	if (strchr(hostname, ':'))
-		snprintf(root_devname, len, "[%s]:/", hostname);
-	else
-		snprintf(root_devname, len, "%s:/", hostname);
-	root_mnt = vfs_kern_mount(fs_type, flags, root_devname, data);
-	kfree(root_devname);
-	return root_mnt;
+	if (!val)
+		return -EINVAL;
+	ret = strict_strtoul(val, 0, &num);
+	if (ret == -EINVAL || num > NFS_CALLBACK_MAXPORTNR)
+		return -EINVAL;
+	*((unsigned int *)kp->arg) = num;
+	return 0;
 }
-
-struct nfs_referral_count {
-	struct list_head list;
-	const struct task_struct *task;
-	unsigned int referral_count;
+static struct kernel_param_ops param_ops_portnr = {
+	.set = param_set_portnr,
+	.get = param_get_uint,
 };
-
-static LIST_HEAD(nfs_referral_count_list);
-static DEFINE_SPINLOCK(nfs_referral_count_list_lock);
-
-static struct nfs_referral_count *nfs_find_referral_count(void)
-{
-	struct nfs_referral_count *p;
-
-	list_for_each_entry(p, &nfs_referral_count_list, list) {
-		if (p->task == current)
-			return p;
-	}
-	return NULL;
-}
-
-#define NFS_MAX_NESTED_REFERRALS 2
-
-static int nfs_referral_loop_protect(void)
-{
-	struct nfs_referral_count *p, *new;
-	int ret = -ENOMEM;
-
-	new = kmalloc(sizeof(*new), GFP_KERNEL);
-	if (!new)
-		goto out;
-	new->task = current;
-	new->referral_count = 1;
-
-	ret = 0;
-	spin_lock(&nfs_referral_count_list_lock);
-	p = nfs_find_referral_count();
-	if (p != NULL) {
-		if (p->referral_count >= NFS_MAX_NESTED_REFERRALS)
-			ret = -ELOOP;
-		else
-			p->referral_count++;
-	} else {
-		list_add(&new->list, &nfs_referral_count_list);
-		new = NULL;
-	}
-	spin_unlock(&nfs_referral_count_list_lock);
-	kfree(new);
-out:
-	return ret;
-}
-
-static void nfs_referral_loop_unprotect(void)
-{
-	struct nfs_referral_count *p;
-
-	spin_lock(&nfs_referral_count_list_lock);
-	p = nfs_find_referral_count();
-	p->referral_count--;
-	if (p->referral_count == 0)
-		list_del(&p->list);
-	else
-		p = NULL;
-	spin_unlock(&nfs_referral_count_list_lock);
-	kfree(p);
-}
-
-static struct dentry *nfs_follow_remote_path(struct vfsmount *root_mnt,
-		const char *export_path)
-{
-	struct dentry *dentry;
-	int err;
-
-	if (IS_ERR(root_mnt))
-		return ERR_CAST(root_mnt);
-
-	err = nfs_referral_loop_protect();
-	if (err) {
-		mntput(root_mnt);
-		return ERR_PTR(err);
-	}
-
-	dentry = mount_subtree(root_mnt, export_path);
-	nfs_referral_loop_unprotect();
-
-	return dentry;
-}
-
-static struct dentry *nfs4_try_mount(int flags, const char *dev_name,
-			 struct nfs_mount_info *mount_info)
-{
-	char *export_path;
-	struct vfsmount *root_mnt;
-	struct dentry *res;
-	struct nfs_parsed_mount_data *data = mount_info->parsed;
-
-	dfprintk(MOUNT, "--> nfs4_try_mount()\n");
-
-	mount_info->fill_super = nfs4_fill_super;
-
-	export_path = data->nfs_server.export_path;
-	data->nfs_server.export_path = "/";
-	root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, mount_info,
-			data->nfs_server.hostname);
-	data->nfs_server.export_path = export_path;
-
-	res = nfs_follow_remote_path(root_mnt, export_path);
-
-	dfprintk(MOUNT, "<-- nfs4_try_mount() = %ld%s\n",
-			IS_ERR(res) ? PTR_ERR(res) : 0,
-			IS_ERR(res) ? " [error]" : "");
-	return res;
-}
-
-static void nfs4_kill_super(struct super_block *sb)
-{
-	struct nfs_server *server = NFS_SB(sb);
-
-	dprintk("--> %s\n", __func__);
-	nfs_super_return_all_delegations(sb);
-	kill_anon_super(sb);
-	nfs_fscache_release_super_cookie(sb);
-	nfs_free_server(server);
-	dprintk("<-- %s\n", __func__);
-}
-
-/*
- * Clone an NFS4 server record on xdev traversal (FSID-change)
- */
-static struct dentry *
-nfs4_xdev_mount(struct file_system_type *fs_type, int flags,
-		 const char *dev_name, void *raw_data)
-{
-	struct nfs_mount_info mount_info = {
-		.fill_super = nfs4_clone_super,
-		.set_security = nfs_clone_sb_security,
-		.cloned = raw_data,
-	};
-	return nfs_xdev_mount_common(&nfs4_fs_type, flags, dev_name, &mount_info);
-}
-
-static struct dentry *
-nfs4_remote_referral_mount(struct file_system_type *fs_type, int flags,
-			   const char *dev_name, void *raw_data)
-{
-	struct nfs_mount_info mount_info = {
-		.fill_super = nfs4_fill_super,
-		.set_security = nfs_clone_sb_security,
-		.cloned = raw_data,
-	};
-	struct nfs_server *server;
-	struct dentry *mntroot = ERR_PTR(-ENOMEM);
-
-	dprintk("--> nfs4_referral_get_sb()\n");
-
-	mount_info.mntfh = nfs_alloc_fhandle();
-	if (mount_info.cloned == NULL || mount_info.mntfh == NULL)
-		goto out;
-
-	/* create a new volume representation */
-	server = nfs4_create_referral_server(mount_info.cloned, mount_info.mntfh);
-	if (IS_ERR(server)) {
-		mntroot = ERR_CAST(server);
-		goto out;
-	}
-
-	mntroot = nfs_fs_mount_common(&nfs4_fs_type, server, flags, dev_name, &mount_info);
-out:
-	nfs_free_fhandle(mount_info.mntfh);
-	return mntroot;
-}
-
-/*
- * Create an NFS4 server record on referral traversal
- */
-static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type,
-		int flags, const char *dev_name, void *raw_data)
-{
-	struct nfs_clone_mount *data = raw_data;
-	char *export_path;
-	struct vfsmount *root_mnt;
-	struct dentry *res;
-
-	dprintk("--> nfs4_referral_mount()\n");
-
-	export_path = data->mnt_path;
-	data->mnt_path = "/";
-
-	root_mnt = nfs_do_root_mount(&nfs4_remote_referral_fs_type,
-			flags, data, data->hostname);
-	data->mnt_path = export_path;
-
-	res = nfs_follow_remote_path(root_mnt, export_path);
-	dprintk("<-- nfs4_referral_mount() = %ld%s\n",
-			IS_ERR(res) ? PTR_ERR(res) : 0,
-			IS_ERR(res) ? " [error]" : "");
-	return res;
-}
-
+#define param_check_portnr(name, p) __param_check(name, p, unsigned int);
+
+module_param_named(callback_tcpport, nfs_callback_set_tcpport, portnr, 0644);
+module_param(nfs_idmap_cache_timeout, int, 0644);
+module_param(nfs4_disable_idmapping, bool, 0644);
+MODULE_PARM_DESC(nfs4_disable_idmapping,
+		"Turn off NFSv4 idmapping when using 'sec=sys'");
+module_param(max_session_slots, ushort, 0644);
+MODULE_PARM_DESC(max_session_slots, "Maximum number of outstanding NFSv4.1 "
+		"requests the client will negotiate");
+module_param(send_implementation_id, ushort, 0644);
+MODULE_PARM_DESC(send_implementation_id,
+		"Send implementation ID with NFSv4.1 exchange_id");
 #endif /* CONFIG_NFS_V4 */
diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c
index ad4d2e787b20..6b3f2535a3ec 100644
--- a/fs/nfs/sysctl.c
+++ b/fs/nfs/sysctl.c
@@ -9,37 +9,11 @@
 #include <linux/fs.h>
 #include <linux/sysctl.h>
 #include <linux/module.h>
-#include <linux/nfs4.h>
-#include <linux/nfs_idmap.h>
 #include <linux/nfs_fs.h>
 
-#include "callback.h"
-
-#ifdef CONFIG_NFS_V4
-static const int nfs_set_port_min = 0;
-static const int nfs_set_port_max = 65535;
-#endif
 static struct ctl_table_header *nfs_callback_sysctl_table;
 
 static ctl_table nfs_cb_sysctls[] = {
-#ifdef CONFIG_NFS_V4
-	{
-		.procname = "nfs_callback_tcpport",
-		.data = &nfs_callback_set_tcpport,
-		.maxlen = sizeof(int),
-		.mode = 0644,
-		.proc_handler = proc_dointvec_minmax,
-		.extra1 = (int *)&nfs_set_port_min,
-		.extra2 = (int *)&nfs_set_port_max,
-	},
-	{
-		.procname = "idmap_cache_timeout",
-		.data = &nfs_idmap_cache_timeout,
-		.maxlen = sizeof(int),
-		.mode = 0644,
-		.proc_handler = proc_dointvec_jiffies,
-	},
-#endif
 	{
 		.procname	= "nfs_mountpoint_timeout",
 		.data		= &nfs_mountpoint_expiry_timeout,
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 3210a03342f9..13cea637eff8 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -501,7 +501,7 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry)
 		(unsigned long long)NFS_FILEID(dentry->d_inode));
 
 	/* Return delegation in anticipation of the rename */
-	nfs_inode_return_delegation(dentry->d_inode);
+	NFS_PROTO(dentry->d_inode)->return_delegation(dentry->d_inode);
 
 	sdentry = NULL;
 	do {
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 4d6861c0dc14..5829d0ce7cfb 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -52,7 +52,7 @@ static mempool_t *nfs_commit_mempool;
 
 struct nfs_commit_data *nfs_commitdata_alloc(void)
 {
-	struct nfs_commit_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOFS);
+	struct nfs_commit_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOIO);
 
 	if (p) {
 		memset(p, 0, sizeof(*p));
@@ -70,7 +70,7 @@ EXPORT_SYMBOL_GPL(nfs_commit_free);
 
 struct nfs_write_header *nfs_writehdr_alloc(void)
 {
-	struct nfs_write_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOFS);
+	struct nfs_write_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOIO);
 
 	if (p) {
 		struct nfs_pgio_header *hdr = &p->header;
@@ -84,6 +84,7 @@ struct nfs_write_header *nfs_writehdr_alloc(void)
 	}
 	return p;
 }
+EXPORT_SYMBOL_GPL(nfs_writehdr_alloc);
 
 static struct nfs_write_data *nfs_writedata_alloc(struct nfs_pgio_header *hdr,
 						  unsigned int pagecount)
@@ -115,6 +116,7 @@ void nfs_writehdr_free(struct nfs_pgio_header *hdr)
 	struct nfs_write_header *whdr = container_of(hdr, struct nfs_write_header, header);
 	mempool_free(whdr, nfs_wdata_mempool);
 }
+EXPORT_SYMBOL_GPL(nfs_writehdr_free);
 
 void nfs_writedata_release(struct nfs_write_data *wdata)
 {
@@ -131,6 +133,7 @@ void nfs_writedata_release(struct nfs_write_data *wdata)
 	if (atomic_dec_and_test(&hdr->refcnt))
 		hdr->completion_ops->completion(hdr);
 }
+EXPORT_SYMBOL_GPL(nfs_writedata_release);
 
 static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error)
 {
@@ -139,25 +142,38 @@ static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error)
 	set_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
 }
 
-static struct nfs_page *nfs_page_find_request_locked(struct page *page)
+static struct nfs_page *
+nfs_page_find_request_locked(struct nfs_inode *nfsi, struct page *page)
 {
 	struct nfs_page *req = NULL;
 
-	if (PagePrivate(page)) {
+	if (PagePrivate(page))
 		req = (struct nfs_page *)page_private(page);
-		if (req != NULL)
-			kref_get(&req->wb_kref);
+	else if (unlikely(PageSwapCache(page))) {
+		struct nfs_page *freq, *t;
+
+		/* Linearly search the commit list for the correct req */
+		list_for_each_entry_safe(freq, t, &nfsi->commit_info.list, wb_list) {
+			if (freq->wb_page == page) {
+				req = freq;
+				break;
+			}
+		}
 	}
+
+	if (req)
+		kref_get(&req->wb_kref);
+
 	return req;
 }
 
 static struct nfs_page *nfs_page_find_request(struct page *page)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	struct nfs_page *req = NULL;
 
 	spin_lock(&inode->i_lock);
-	req = nfs_page_find_request_locked(page);
+	req = nfs_page_find_request_locked(NFS_I(inode), page);
 	spin_unlock(&inode->i_lock);
 	return req;
 }
@@ -165,16 +181,16 @@ static struct nfs_page *nfs_page_find_request(struct page *page)
 /* Adjust the file length if we're writing beyond the end */
 static void nfs_grow_file(struct page *page, unsigned int offset, unsigned int count)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	loff_t end, i_size;
 	pgoff_t end_index;
 
 	spin_lock(&inode->i_lock);
 	i_size = i_size_read(inode);
 	end_index = (i_size - 1) >> PAGE_CACHE_SHIFT;
-	if (i_size > 0 && page->index < end_index)
+	if (i_size > 0 && page_file_index(page) < end_index)
 		goto out;
-	end = ((loff_t)page->index << PAGE_CACHE_SHIFT) + ((loff_t)offset+count);
+	end = page_file_offset(page) + ((loff_t)offset+count);
 	if (i_size >= end)
 		goto out;
 	i_size_write(inode, end);
@@ -187,7 +203,7 @@ out:
 static void nfs_set_pageerror(struct page *page)
 {
 	SetPageError(page);
-	nfs_zap_mapping(page->mapping->host, page->mapping);
+	nfs_zap_mapping(page_file_mapping(page)->host, page_file_mapping(page));
 }
 
 /* We can set the PG_uptodate flag if we see that a write request
@@ -228,7 +244,7 @@ static int nfs_set_page_writeback(struct page *page)
 	int ret = test_set_page_writeback(page);
 
 	if (!ret) {
-		struct inode *inode = page->mapping->host;
+		struct inode *inode = page_file_mapping(page)->host;
 		struct nfs_server *nfss = NFS_SERVER(inode);
 
 		if (atomic_long_inc_return(&nfss->writeback) >
@@ -242,7 +258,7 @@ static int nfs_set_page_writeback(struct page *page)
 
 static void nfs_end_page_writeback(struct page *page)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	struct nfs_server *nfss = NFS_SERVER(inode);
 
 	end_page_writeback(page);
@@ -252,13 +268,13 @@ static void nfs_end_page_writeback(struct page *page)
 
 static struct nfs_page *nfs_find_and_lock_request(struct page *page, bool nonblock)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	struct nfs_page *req;
 	int ret;
 
 	spin_lock(&inode->i_lock);
 	for (;;) {
-		req = nfs_page_find_request_locked(page);
+		req = nfs_page_find_request_locked(NFS_I(inode), page);
 		if (req == NULL)
 			break;
 		if (nfs_lock_request(req))
@@ -313,13 +329,13 @@ out:
 
 static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	int ret;
 
 	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
 	nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1);
 
-	nfs_pageio_cond_complete(pgio, page->index);
+	nfs_pageio_cond_complete(pgio, page_file_index(page));
 	ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE);
 	if (ret == -EAGAIN) {
 		redirty_page_for_writepage(wbc, page);
@@ -336,8 +352,10 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc
 	struct nfs_pageio_descriptor pgio;
 	int err;
 
-	nfs_pageio_init_write(&pgio, page->mapping->host, wb_priority(wbc),
-			      &nfs_async_write_completion_ops);
+	NFS_PROTO(page_file_mapping(page)->host)->write_pageio_init(&pgio,
+							  page->mapping->host,
+							  wb_priority(wbc),
+							  &nfs_async_write_completion_ops);
 	err = nfs_do_writepage(page, wbc, &pgio);
 	nfs_pageio_complete(&pgio);
 	if (err < 0)
@@ -380,8 +398,7 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 
 	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES);
 
-	nfs_pageio_init_write(&pgio, inode, wb_priority(wbc),
-			      &nfs_async_write_completion_ops);
+	NFS_PROTO(inode)->write_pageio_init(&pgio, inode, wb_priority(wbc), &nfs_async_write_completion_ops);
 	err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio);
 	nfs_pageio_complete(&pgio);
 
@@ -410,11 +427,17 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
 	nfs_lock_request(req);
 
 	spin_lock(&inode->i_lock);
-	if (!nfsi->npages && nfs_have_delegation(inode, FMODE_WRITE))
+	if (!nfsi->npages && NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
 		inode->i_version++;
-	set_bit(PG_MAPPED, &req->wb_flags);
-	SetPagePrivate(req->wb_page);
-	set_page_private(req->wb_page, (unsigned long)req);
+	/*
+	 * Swap-space should not get truncated. Hence no need to plug the race
+	 * with invalidate/truncate.
+	 */
+	if (likely(!PageSwapCache(req->wb_page))) {
+		set_bit(PG_MAPPED, &req->wb_flags);
+		SetPagePrivate(req->wb_page);
+		set_page_private(req->wb_page, (unsigned long)req);
+	}
 	nfsi->npages++;
 	kref_get(&req->wb_kref);
 	spin_unlock(&inode->i_lock);
@@ -431,9 +454,11 @@ static void nfs_inode_remove_request(struct nfs_page *req)
 	BUG_ON (!NFS_WBACK_BUSY(req));
 
 	spin_lock(&inode->i_lock);
-	set_page_private(req->wb_page, 0);
-	ClearPagePrivate(req->wb_page);
-	clear_bit(PG_MAPPED, &req->wb_flags);
+	if (likely(!PageSwapCache(req->wb_page))) {
+		set_page_private(req->wb_page, 0);
+		ClearPagePrivate(req->wb_page);
+		clear_bit(PG_MAPPED, &req->wb_flags);
+	}
 	nfsi->npages--;
 	spin_unlock(&inode->i_lock);
 	nfs_release_request(req);
@@ -445,7 +470,7 @@ nfs_mark_request_dirty(struct nfs_page *req)
 	__set_page_dirty_nobuffers(req->wb_page);
 }
 
-#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
+#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 /**
  * nfs_request_add_commit_list - add request to a commit list
  * @req: pointer to a struct nfs_page
@@ -470,7 +495,7 @@ nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst,
 	spin_unlock(cinfo->lock);
 	if (!cinfo->dreq) {
 		inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
-		inc_bdi_stat(req->wb_page->mapping->backing_dev_info,
+		inc_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
 			     BDI_RECLAIMABLE);
 		__mark_inode_dirty(req->wb_context->dentry->d_inode,
 				   I_DIRTY_DATASYNC);
@@ -537,7 +562,7 @@ static void
 nfs_clear_page_commit(struct page *page)
 {
 	dec_zone_page_state(page, NR_UNSTABLE_NFS);
-	dec_bdi_stat(page->mapping->backing_dev_info, BDI_RECLAIMABLE);
+	dec_bdi_stat(page_file_mapping(page)->backing_dev_info, BDI_RECLAIMABLE);
 }
 
 static void
@@ -620,7 +645,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr)
 			goto next;
 		}
 		if (test_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags)) {
-			memcpy(&req->wb_verf, hdr->verf, sizeof(req->wb_verf));
+			memcpy(&req->wb_verf, &hdr->verf->verifier, sizeof(req->wb_verf));
 			nfs_mark_request_commit(req, hdr->lseg, &cinfo);
 			goto next;
 		}
@@ -635,7 +660,7 @@ out:
 	hdr->release(hdr);
 }
 
-#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
+#if  IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 static unsigned long
 nfs_reqs_to_commit(struct nfs_commit_info *cinfo)
 {
@@ -729,7 +754,7 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode,
 	spin_lock(&inode->i_lock);
 
 	for (;;) {
-		req = nfs_page_find_request_locked(page);
+		req = nfs_page_find_request_locked(NFS_I(inode), page);
 		if (req == NULL)
 			goto out_unlock;
 
@@ -788,7 +813,7 @@ out_err:
 static struct nfs_page * nfs_setup_write_request(struct nfs_open_context* ctx,
 		struct page *page, unsigned int offset, unsigned int bytes)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	struct nfs_page	*req;
 
 	req = nfs_try_to_update_request(inode, page, offset, bytes);
@@ -841,7 +866,7 @@ int nfs_flush_incompatible(struct file *file, struct page *page)
 		nfs_release_request(req);
 		if (!do_flush)
 			return 0;
-		status = nfs_wb_page(page->mapping->host, page);
+		status = nfs_wb_page(page_file_mapping(page)->host, page);
 	} while (status == 0);
 	return status;
 }
@@ -871,7 +896,7 @@ int nfs_updatepage(struct file *file, struct page *page,
 		unsigned int offset, unsigned int count)
 {
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
-	struct inode	*inode = page->mapping->host;
+	struct inode	*inode = page_file_mapping(page)->host;
 	int		status = 0;
 
 	nfs_inc_stats(inode, NFSIOS_VFSUPDATEPAGE);
@@ -879,7 +904,7 @@ int nfs_updatepage(struct file *file, struct page *page,
 	dprintk("NFS:       nfs_updatepage(%s/%s %d@%lld)\n",
 		file->f_path.dentry->d_parent->d_name.name,
 		file->f_path.dentry->d_name.name, count,
-		(long long)(page_offset(page) + offset));
+		(long long)(page_file_offset(page) + offset));
 
 	/* If we're not using byte range locks, and we know the page
 	 * is up to date, it may be more efficient to extend the write
@@ -1172,6 +1197,7 @@ int nfs_generic_flush(struct nfs_pageio_descriptor *desc,
 		return nfs_flush_multi(desc, hdr);
 	return nfs_flush_one(desc, hdr);
 }
+EXPORT_SYMBOL_GPL(nfs_generic_flush);
 
 static int nfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
 {
@@ -1202,13 +1228,14 @@ static const struct nfs_pageio_ops nfs_pageio_write_ops = {
 	.pg_doio = nfs_generic_pg_writepages,
 };
 
-void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio,
+void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
 			       struct inode *inode, int ioflags,
 			       const struct nfs_pgio_completion_ops *compl_ops)
 {
 	nfs_pageio_init(pgio, inode, &nfs_pageio_write_ops, compl_ops,
 				NFS_SERVER(inode)->wsize, ioflags);
 }
+EXPORT_SYMBOL_GPL(nfs_pageio_init_write);
 
 void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio)
 {
@@ -1217,13 +1244,6 @@ void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio)
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_reset_write_mds);
 
-void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
-			   struct inode *inode, int ioflags,
-			   const struct nfs_pgio_completion_ops *compl_ops)
-{
-	if (!pnfs_pageio_init_write(pgio, inode, ioflags, compl_ops))
-		nfs_pageio_init_write_mds(pgio, inode, ioflags, compl_ops);
-}
 
 void nfs_write_prepare(struct rpc_task *task, void *calldata)
 {
@@ -1303,7 +1323,7 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
 		return;
 	nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, resp->count);
 
-#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
+#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 	if (resp->verf->committed < argp->stable && task->tk_status >= 0) {
 		/* We tried a write call, but the server did not
 		 * commit data to stable storage even though we
@@ -1363,7 +1383,7 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
 }
 
 
-#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
+#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 static int nfs_commit_set_lock(struct nfs_inode *nfsi, int may_wait)
 {
 	int ret;
@@ -1475,7 +1495,7 @@ void nfs_retry_commit(struct list_head *page_list,
 		nfs_mark_request_commit(req, lseg, cinfo);
 		if (!cinfo->dreq) {
 			dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
-			dec_bdi_stat(req->wb_page->mapping->backing_dev_info,
+			dec_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
 				     BDI_RECLAIMABLE);
 		}
 		nfs_unlock_and_release_request(req);
@@ -1547,7 +1567,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 
 		/* Okay, COMMIT succeeded, apparently. Check the verifier
 		 * returned by the server against all stored verfs. */
-		if (!memcmp(req->wb_verf.verifier, data->verf.verifier, sizeof(data->verf.verifier))) {
+		if (!memcmp(&req->wb_verf, &data->verf.verifier, sizeof(req->wb_verf))) {
 			/* We have a match */
 			nfs_inode_remove_request(req);
 			dprintk(" OK\n");
@@ -1677,22 +1697,9 @@ static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_contr
 
 int nfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 {
-	int ret;
-
-	ret = nfs_commit_unstable_pages(inode, wbc);
-	if (ret >= 0 && test_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(inode)->flags)) {
-		int status;
-		bool sync = true;
-
-		if (wbc->sync_mode == WB_SYNC_NONE)
-			sync = false;
-
-		status = pnfs_layoutcommit_inode(inode, sync);
-		if (status < 0)
-			return status;
-	}
-	return ret;
+	return nfs_commit_unstable_pages(inode, wbc);
 }
+EXPORT_SYMBOL_GPL(nfs_write_inode);
 
 /*
  * flush the inode to disk.
@@ -1708,6 +1715,7 @@ int nfs_wb_all(struct inode *inode)
 
 	return sync_inode(inode, &wbc);
 }
+EXPORT_SYMBOL_GPL(nfs_wb_all);
 
 int nfs_wb_page_cancel(struct inode *inode, struct page *page)
 {
@@ -1744,7 +1752,7 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page)
  */
 int nfs_wb_page(struct inode *inode, struct page *page)
 {
-	loff_t range_start = page_offset(page);
+	loff_t range_start = page_file_offset(page);
 	loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1);
 	struct writeback_control wbc = {
 		.sync_mode = WB_SYNC_ALL,
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index ba233499b9a5..a3946cf13fc8 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -398,7 +398,7 @@ fsloc_parse(char **mesg, char *buf, struct nfsd4_fs_locations *fsloc)
 	int migrated, i, err;
 
 	/* listsize */
-	err = get_int(mesg, &fsloc->locations_count);
+	err = get_uint(mesg, &fsloc->locations_count);
 	if (err)
 		return err;
 	if (fsloc->locations_count > MAX_FS_LOCATIONS)
@@ -456,7 +456,7 @@ static int secinfo_parse(char **mesg, char *buf, struct svc_export *exp)
 		return -EINVAL;
 
 	for (f = exp->ex_flavors; f < exp->ex_flavors + listsize; f++) {
-		err = get_int(mesg, &f->pseudoflavor);
+		err = get_uint(mesg, &f->pseudoflavor);
 		if (err)
 			return err;
 		/*
@@ -465,7 +465,7 @@ static int secinfo_parse(char **mesg, char *buf, struct svc_export *exp)
 		 * problem at export time instead of when a client fails
 		 * to authenticate.
 		 */
-		err = get_int(mesg, &f->flags);
+		err = get_uint(mesg, &f->flags);
 		if (err)
 			return err;
 		/* Only some flags are allowed to differ between flavors: */
@@ -929,7 +929,7 @@ struct svc_export *
 rqst_exp_get_by_name(struct svc_rqst *rqstp, struct path *path)
 {
 	struct svc_export *gssexp, *exp = ERR_PTR(-ENOENT);
-	struct nfsd_net *nn = net_generic(rqstp->rq_xprt->xpt_net, nfsd_net_id);
+	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 	struct cache_detail *cd = nn->svc_export_cache;
 
 	if (rqstp->rq_client == NULL)
@@ -960,7 +960,7 @@ struct svc_export *
 rqst_exp_find(struct svc_rqst *rqstp, int fsid_type, u32 *fsidv)
 {
 	struct svc_export *gssexp, *exp = ERR_PTR(-ENOENT);
-	struct nfsd_net *nn = net_generic(rqstp->rq_xprt->xpt_net, nfsd_net_id);
+	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 	struct cache_detail *cd = nn->svc_export_cache;
 
 	if (rqstp->rq_client == NULL)
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index 39365636b244..65c2431ea32f 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -34,6 +34,10 @@ struct nfsd_net {
 
 	struct cache_detail *idtoname_cache;
 	struct cache_detail *nametoid_cache;
+
+	struct lock_manager nfsd4_manager;
+	bool grace_ended;
+	time_t boot_time;
 };
 
 extern int nfsd_net_id;
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index a5fd6b982f27..cbaf4f8bb7b7 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -756,7 +756,6 @@ static void do_probe_callback(struct nfs4_client *clp)
  */
 void nfsd4_probe_callback(struct nfs4_client *clp)
 {
-	/* XXX: atomicity?  Also, should we be using cl_flags? */
 	clp->cl_cb_state = NFSD4_CB_UNKNOWN;
 	set_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags);
 	do_probe_callback(clp);
diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
index dae36f1dee95..fdc91a6fc9c4 100644
--- a/fs/nfsd/nfs4idmap.c
+++ b/fs/nfsd/nfs4idmap.c
@@ -546,7 +546,7 @@ idmap_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen
 		.type = type,
 	};
 	int ret;
-	struct nfsd_net *nn = net_generic(rqstp->rq_xprt->xpt_net, nfsd_net_id);
+	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 
 	if (namelen + 1 > sizeof(key.name))
 		return nfserr_badowner;
@@ -571,7 +571,7 @@ idmap_id_to_name(struct svc_rqst *rqstp, int type, uid_t id, char *name)
 		.type = type,
 	};
 	int ret;
-	struct nfsd_net *nn = net_generic(rqstp->rq_xprt->xpt_net, nfsd_net_id);
+	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 
 	strlcpy(key.authname, rqst_authname(rqstp), sizeof(key.authname));
 	ret = idmap_lookup(rqstp, idtoname_lookup, &key, nn->idtoname_cache, &item);
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 987e719fbae8..c9c1c0a25417 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -354,10 +354,10 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	/* Openowner is now set, so sequence id will get bumped.  Now we need
 	 * these checks before we do any creates: */
 	status = nfserr_grace;
-	if (locks_in_grace() && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS)
+	if (locks_in_grace(SVC_NET(rqstp)) && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS)
 		goto out;
 	status = nfserr_no_grace;
-	if (!locks_in_grace() && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
+	if (!locks_in_grace(SVC_NET(rqstp)) && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
 		goto out;
 
 	switch (open->op_claim_type) {
@@ -686,7 +686,8 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	nfs4_lock_state();
 	/* check stateid */
-	if ((status = nfs4_preprocess_stateid_op(cstate, &read->rd_stateid,
+	if ((status = nfs4_preprocess_stateid_op(SVC_NET(rqstp),
+						 cstate, &read->rd_stateid,
 						 RD_STATE, &read->rd_filp))) {
 		dprintk("NFSD: nfsd4_read: couldn't process stateid!\n");
 		goto out;
@@ -741,7 +742,7 @@ nfsd4_remove(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 {
 	__be32 status;
 
-	if (locks_in_grace())
+	if (locks_in_grace(SVC_NET(rqstp)))
 		return nfserr_grace;
 	status = nfsd_unlink(rqstp, &cstate->current_fh, 0,
 			     remove->rm_name, remove->rm_namelen);
@@ -760,8 +761,8 @@ nfsd4_rename(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	if (!cstate->save_fh.fh_dentry)
 		return status;
-	if (locks_in_grace() && !(cstate->save_fh.fh_export->ex_flags
-					& NFSEXP_NOSUBTREECHECK))
+	if (locks_in_grace(SVC_NET(rqstp)) &&
+		!(cstate->save_fh.fh_export->ex_flags & NFSEXP_NOSUBTREECHECK))
 		return nfserr_grace;
 	status = nfsd_rename(rqstp, &cstate->save_fh, rename->rn_sname,
 			     rename->rn_snamelen, &cstate->current_fh,
@@ -845,7 +846,7 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	if (setattr->sa_iattr.ia_valid & ATTR_SIZE) {
 		nfs4_lock_state();
-		status = nfs4_preprocess_stateid_op(cstate,
+		status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), cstate,
 			&setattr->sa_stateid, WR_STATE, NULL);
 		nfs4_unlock_state();
 		if (status) {
@@ -890,7 +891,8 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		return nfserr_inval;
 
 	nfs4_lock_state();
-	status = nfs4_preprocess_stateid_op(cstate, stateid, WR_STATE, &filp);
+	status = nfs4_preprocess_stateid_op(SVC_NET(rqstp),
+					cstate, stateid, WR_STATE, &filp);
 	if (filp)
 		get_file(filp);
 	nfs4_unlock_state();
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 5ff0b7b9fc08..43295d45cc2b 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -154,6 +154,10 @@ nfsd4_create_clid_dir(struct nfs4_client *clp)
 	if (status < 0)
 		return;
 
+	status = mnt_want_write_file(rec_file);
+	if (status)
+		return;
+
 	dir = rec_file->f_path.dentry;
 	/* lock the parent */
 	mutex_lock(&dir->d_inode->i_mutex);
@@ -173,11 +177,7 @@ nfsd4_create_clid_dir(struct nfs4_client *clp)
 		 * as well be forgiving and just succeed silently.
 		 */
 		goto out_put;
-	status = mnt_want_write_file(rec_file);
-	if (status)
-		goto out_put;
 	status = vfs_mkdir(dir->d_inode, dentry, S_IRWXU);
-	mnt_drop_write_file(rec_file);
 out_put:
 	dput(dentry);
 out_unlock:
@@ -189,6 +189,7 @@ out_unlock:
 				" (err %d); please check that %s exists"
 				" and is writeable", status,
 				user_recovery_dirname);
+	mnt_drop_write_file(rec_file);
 	nfs4_reset_creds(original_cred);
 }
 
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 94effd5bc4a1..cc894eda385a 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -38,18 +38,21 @@
 #include <linux/namei.h>
 #include <linux/swap.h>
 #include <linux/pagemap.h>
+#include <linux/ratelimit.h>
 #include <linux/sunrpc/svcauth_gss.h>
 #include <linux/sunrpc/clnt.h>
 #include "xdr4.h"
 #include "vfs.h"
 #include "current_stateid.h"
+#include "fault_inject.h"
+
+#include "netns.h"
 
 #define NFSDDBG_FACILITY                NFSDDBG_PROC
 
 /* Globals */
 time_t nfsd4_lease = 90;     /* default lease time */
 time_t nfsd4_grace = 90;
-static time_t boot_time;
 
 #define all_ones {{~0,~0},~0}
 static const stateid_t one_stateid = {
@@ -862,6 +865,11 @@ static __be32 nfsd4_new_conn(struct svc_rqst *rqstp, struct nfsd4_session *ses,
 	if (ret)
 		/* oops; xprt is already down: */
 		nfsd4_conn_lost(&conn->cn_xpt_user);
+	if (ses->se_client->cl_cb_state == NFSD4_CB_DOWN &&
+		dir & NFS4_CDFC4_BACK) {
+		/* callback channel may be back up */
+		nfsd4_probe_callback(ses->se_client);
+	}
 	return nfs_ok;
 }
 
@@ -1047,12 +1055,12 @@ renew_client(struct nfs4_client *clp)
 
 /* SETCLIENTID and SETCLIENTID_CONFIRM Helper functions */
 static int
-STALE_CLIENTID(clientid_t *clid)
+STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn)
 {
-	if (clid->cl_boot == boot_time)
+	if (clid->cl_boot == nn->boot_time)
 		return 0;
 	dprintk("NFSD stale clientid (%08x/%08x) boot_time %08lx\n",
-		clid->cl_boot, clid->cl_id, boot_time);
+		clid->cl_boot, clid->cl_id, nn->boot_time);
 	return 1;
 }
 
@@ -1215,7 +1223,7 @@ static bool groups_equal(struct group_info *g1, struct group_info *g2)
 	return true;
 }
 
-static int
+static bool
 same_creds(struct svc_cred *cr1, struct svc_cred *cr2)
 {
 	if ((cr1->cr_flavor != cr2->cr_flavor)
@@ -1227,14 +1235,15 @@ same_creds(struct svc_cred *cr1, struct svc_cred *cr2)
 		return true;
 	if (!cr1->cr_principal || !cr2->cr_principal)
 		return false;
-	return 0 == strcmp(cr1->cr_principal, cr1->cr_principal);
+	return 0 == strcmp(cr1->cr_principal, cr2->cr_principal);
 }
 
 static void gen_clid(struct nfs4_client *clp)
 {
 	static u32 current_clientid = 1;
+	struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
 
-	clp->cl_clientid.cl_boot = boot_time;
+	clp->cl_clientid.cl_boot = nn->boot_time;
 	clp->cl_clientid.cl_id = current_clientid++; 
 }
 
@@ -2217,8 +2226,9 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
 	nfs4_verifier confirm = setclientid_confirm->sc_confirm; 
 	clientid_t * clid = &setclientid_confirm->sc_clientid;
 	__be32 status;
+	struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
 
-	if (STALE_CLIENTID(clid))
+	if (STALE_CLIENTID(clid, nn))
 		return nfserr_stale_clientid;
 	nfs4_lock_state();
 
@@ -2577,8 +2587,9 @@ nfsd4_process_open1(struct nfsd4_compound_state *cstate,
 	unsigned int strhashval;
 	struct nfs4_openowner *oo = NULL;
 	__be32 status;
+	struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
 
-	if (STALE_CLIENTID(&open->op_clientid))
+	if (STALE_CLIENTID(&open->op_clientid, nn))
 		return nfserr_stale_clientid;
 	/*
 	 * In case we need it later, after we've already created the
@@ -2876,7 +2887,8 @@ static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status)
  * Attempt to hand out a delegation.
  */
 static void
-nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, struct nfs4_ol_stateid *stp)
+nfs4_open_delegation(struct net *net, struct svc_fh *fh,
+		     struct nfsd4_open *open, struct nfs4_ol_stateid *stp)
 {
 	struct nfs4_delegation *dp;
 	struct nfs4_openowner *oo = container_of(stp->st_stateowner, struct nfs4_openowner, oo_owner);
@@ -2897,7 +2909,7 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, struct nfs4_ol_
 		case NFS4_OPEN_CLAIM_NULL:
 			/* Let's not give out any delegations till everyone's
 			 * had the chance to reclaim theirs.... */
-			if (locks_in_grace())
+			if (locks_in_grace(net))
 				goto out;
 			if (!cb_up || !(oo->oo_flags & NFS4_OO_CONFIRMED))
 				goto out;
@@ -3007,14 +3019,12 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 		status = nfs4_get_vfs_file(rqstp, fp, current_fh, open);
 		if (status)
 			goto out;
+		status = nfsd4_truncate(rqstp, current_fh, open);
+		if (status)
+			goto out;
 		stp = open->op_stp;
 		open->op_stp = NULL;
 		init_open_stateid(stp, fp, open);
-		status = nfsd4_truncate(rqstp, current_fh, open);
-		if (status) {
-			release_open_stateid(stp);
-			goto out;
-		}
 	}
 	update_stateid(&stp->st_stid.sc_stateid);
 	memcpy(&open->op_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
@@ -3033,7 +3043,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 	* Attempt to hand out a delegation. No error return, because the
 	* OPEN succeeds even if we fail.
 	*/
-	nfs4_open_delegation(current_fh, open, stp);
+	nfs4_open_delegation(SVC_NET(rqstp), current_fh, open, stp);
 nodeleg:
 	status = nfs_ok;
 
@@ -3087,12 +3097,13 @@ nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 {
 	struct nfs4_client *clp;
 	__be32 status;
+	struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
 
 	nfs4_lock_state();
 	dprintk("process_renew(%08x/%08x): starting\n", 
 			clid->cl_boot, clid->cl_id);
 	status = nfserr_stale_clientid;
-	if (STALE_CLIENTID(clid))
+	if (STALE_CLIENTID(clid, nn))
 		goto out;
 	clp = find_confirmed_client(clid);
 	status = nfserr_expired;
@@ -3111,22 +3122,19 @@ out:
 	return status;
 }
 
-static struct lock_manager nfsd4_manager = {
-};
-
-static bool grace_ended;
-
 static void
-nfsd4_end_grace(void)
+nfsd4_end_grace(struct net *net)
 {
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
 	/* do nothing if grace period already ended */
-	if (grace_ended)
+	if (nn->grace_ended)
 		return;
 
 	dprintk("NFSD: end of grace period\n");
-	grace_ended = true;
-	nfsd4_record_grace_done(&init_net, boot_time);
-	locks_end_grace(&nfsd4_manager);
+	nn->grace_ended = true;
+	nfsd4_record_grace_done(net, nn->boot_time);
+	locks_end_grace(&nn->nfsd4_manager);
 	/*
 	 * Now that every NFSv4 client has had the chance to recover and
 	 * to see the (possibly new, possibly shorter) lease time, we
@@ -3149,7 +3157,7 @@ nfs4_laundromat(void)
 	nfs4_lock_state();
 
 	dprintk("NFSD: laundromat service - starting\n");
-	nfsd4_end_grace();
+	nfsd4_end_grace(&init_net);
 	INIT_LIST_HEAD(&reaplist);
 	spin_lock(&client_lock);
 	list_for_each_safe(pos, next, &client_lru) {
@@ -3231,9 +3239,9 @@ static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_ol_stateid *s
 }
 
 static int
-STALE_STATEID(stateid_t *stateid)
+STALE_STATEID(stateid_t *stateid, struct nfsd_net *nn)
 {
-	if (stateid->si_opaque.so_clid.cl_boot == boot_time)
+	if (stateid->si_opaque.so_clid.cl_boot == nn->boot_time)
 		return 0;
 	dprintk("NFSD: stale stateid " STATEID_FMT "!\n",
 		STATEID_VAL(stateid));
@@ -3273,11 +3281,11 @@ out:
 }
 
 static inline __be32
-check_special_stateids(svc_fh *current_fh, stateid_t *stateid, int flags)
+check_special_stateids(struct net *net, svc_fh *current_fh, stateid_t *stateid, int flags)
 {
 	if (ONE_STATEID(stateid) && (flags & RD_STATE))
 		return nfs_ok;
-	else if (locks_in_grace()) {
+	else if (locks_in_grace(net)) {
 		/* Answer in remaining cases depends on existence of
 		 * conflicting state; so we must wait out the grace period. */
 		return nfserr_grace;
@@ -3294,9 +3302,9 @@ check_special_stateids(svc_fh *current_fh, stateid_t *stateid, int flags)
  * that are not able to provide mandatory locking.
  */
 static inline int
-grace_disallows_io(struct inode *inode)
+grace_disallows_io(struct net *net, struct inode *inode)
 {
-	return locks_in_grace() && mandatory_lock(inode);
+	return locks_in_grace(net) && mandatory_lock(inode);
 }
 
 /* Returns true iff a is later than b: */
@@ -3333,18 +3341,26 @@ static __be32 check_stateid_generation(stateid_t *in, stateid_t *ref, bool has_s
 	return nfserr_old_stateid;
 }
 
-__be32 nfs4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
+static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
 {
 	struct nfs4_stid *s;
 	struct nfs4_ol_stateid *ols;
 	__be32 status;
 
-	if (STALE_STATEID(stateid))
-		return nfserr_stale_stateid;
-
+	if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
+		return nfserr_bad_stateid;
+	/* Client debugging aid. */
+	if (!same_clid(&stateid->si_opaque.so_clid, &cl->cl_clientid)) {
+		char addr_str[INET6_ADDRSTRLEN];
+		rpc_ntop((struct sockaddr *)&cl->cl_addr, addr_str,
+				 sizeof(addr_str));
+		pr_warn_ratelimited("NFSD: client %s testing state ID "
+					"with incorrect client ID\n", addr_str);
+		return nfserr_bad_stateid;
+	}
 	s = find_stateid(cl, stateid);
 	if (!s)
-		 return nfserr_stale_stateid;
+		return nfserr_bad_stateid;
 	status = check_stateid_generation(stateid, &s->sc_stateid, 1);
 	if (status)
 		return status;
@@ -3360,10 +3376,11 @@ __be32 nfs4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
 static __be32 nfsd4_lookup_stateid(stateid_t *stateid, unsigned char typemask, struct nfs4_stid **s)
 {
 	struct nfs4_client *cl;
+	struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
 
 	if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
 		return nfserr_bad_stateid;
-	if (STALE_STATEID(stateid))
+	if (STALE_STATEID(stateid, nn))
 		return nfserr_stale_stateid;
 	cl = find_confirmed_client(&stateid->si_opaque.so_clid);
 	if (!cl)
@@ -3379,7 +3396,7 @@ static __be32 nfsd4_lookup_stateid(stateid_t *stateid, unsigned char typemask, s
 * Checks for stateid operations
 */
 __be32
-nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate,
+nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
 			   stateid_t *stateid, int flags, struct file **filpp)
 {
 	struct nfs4_stid *s;
@@ -3392,11 +3409,11 @@ nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate,
 	if (filpp)
 		*filpp = NULL;
 
-	if (grace_disallows_io(ino))
+	if (grace_disallows_io(net, ino))
 		return nfserr_grace;
 
 	if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
-		return check_special_stateids(current_fh, stateid, flags);
+		return check_special_stateids(net, current_fh, stateid, flags);
 
 	status = nfsd4_lookup_stateid(stateid, NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID, &s);
 	if (status)
@@ -3463,7 +3480,8 @@ nfsd4_test_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	nfs4_lock_state();
 	list_for_each_entry(stateid, &test_stateid->ts_stateid_list, ts_id_list)
-		stateid->ts_id_status = nfs4_validate_stateid(cl, &stateid->ts_id_stateid);
+		stateid->ts_id_status =
+			nfsd4_validate_stateid(cl, &stateid->ts_id_stateid);
 	nfs4_unlock_state();
 
 	return nfs_ok;
@@ -3750,12 +3768,19 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	nfsd4_close_open_stateid(stp);
 	oo->oo_last_closed_stid = stp;
 
-	/* place unused nfs4_stateowners on so_close_lru list to be
-	 * released by the laundromat service after the lease period
-	 * to enable us to handle CLOSE replay
-	 */
-	if (list_empty(&oo->oo_owner.so_stateids))
-		move_to_close_lru(oo);
+	if (list_empty(&oo->oo_owner.so_stateids)) {
+		if (cstate->minorversion) {
+			release_openowner(oo);
+			cstate->replay_owner = NULL;
+		} else {
+			/*
+			 * In the 4.0 case we need to keep the owners around a
+			 * little while to handle CLOSE replay.
+			 */
+			if (list_empty(&oo->oo_owner.so_stateids))
+				move_to_close_lru(oo);
+		}
+	}
 out:
 	if (!cstate->replay_owner)
 		nfs4_unlock_state();
@@ -4027,6 +4052,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	bool new_state = false;
 	int lkflg;
 	int err;
+	struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
 
 	dprintk("NFSD: nfsd4_lock: start=%Ld length=%Ld\n",
 		(long long) lock->lk_offset,
@@ -4044,11 +4070,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	nfs4_lock_state();
 
 	if (lock->lk_is_new) {
-		/*
-		 * Client indicates that this is a new lockowner.
-		 * Use open owner and open stateid to create lock owner and
-		 * lock stateid.
-		 */
 		struct nfs4_ol_stateid *open_stp = NULL;
 
 		if (nfsd4_has_session(cstate))
@@ -4058,7 +4079,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 				sizeof(clientid_t));
 
 		status = nfserr_stale_clientid;
-		if (STALE_CLIENTID(&lock->lk_new_clientid))
+		if (STALE_CLIENTID(&lock->lk_new_clientid, nn))
 			goto out;
 
 		/* validate and update open stateid and open seqid */
@@ -4075,17 +4096,13 @@ 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_state);
-		if (status)
-			goto out;
-	} else {
-		/* lock (lock owner + lock stateid) already exists */
+	} else
 		status = nfs4_preprocess_seqid_op(cstate,
 				       lock->lk_old_lock_seqid,
 				       &lock->lk_old_lock_stateid,
 				       NFS4_LOCK_STID, &lock_stp);
-		if (status)
-			goto out;
-	}
+	if (status)
+		goto out;
 	lock_sop = lockowner(lock_stp->st_stateowner);
 
 	lkflg = setlkflg(lock->lk_type);
@@ -4094,10 +4111,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		goto out;
 
 	status = nfserr_grace;
-	if (locks_in_grace() && !lock->lk_reclaim)
+	if (locks_in_grace(SVC_NET(rqstp)) && !lock->lk_reclaim)
 		goto out;
 	status = nfserr_no_grace;
-	if (!locks_in_grace() && lock->lk_reclaim)
+	if (!locks_in_grace(SVC_NET(rqstp)) && lock->lk_reclaim)
 		goto out;
 
 	locks_init_lock(&file_lock);
@@ -4196,8 +4213,9 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	struct file_lock file_lock;
 	struct nfs4_lockowner *lo;
 	__be32 status;
+	struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
 
-	if (locks_in_grace())
+	if (locks_in_grace(SVC_NET(rqstp)))
 		return nfserr_grace;
 
 	if (check_lock_length(lockt->lt_offset, lockt->lt_length))
@@ -4206,7 +4224,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	nfs4_lock_state();
 
 	status = nfserr_stale_clientid;
-	if (!nfsd4_has_session(cstate) && STALE_CLIENTID(&lockt->lt_clientid))
+	if (!nfsd4_has_session(cstate) && STALE_CLIENTID(&lockt->lt_clientid, nn))
 		goto out;
 
 	if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0)))
@@ -4355,6 +4373,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
 	struct list_head matches;
 	unsigned int hashval = ownerstr_hashval(clid->cl_id, owner);
 	__be32 status;
+	struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
 
 	dprintk("nfsd4_release_lockowner clientid: (%08x/%08x):\n",
 		clid->cl_boot, clid->cl_id);
@@ -4362,7 +4381,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
 	/* XXX check for lease expiration */
 
 	status = nfserr_stale_clientid;
-	if (STALE_CLIENTID(clid))
+	if (STALE_CLIENTID(clid, nn))
 		return status;
 
 	nfs4_lock_state();
@@ -4564,7 +4583,7 @@ void nfsd_forget_openowners(u64 num)
 	printk(KERN_INFO "NFSD: Forgot %d open owners", count);
 }
 
-int nfsd_process_n_delegations(u64 num, void (*deleg_func)(struct nfs4_delegation *))
+int nfsd_process_n_delegations(u64 num, struct list_head *list)
 {
 	int i, count = 0;
 	struct nfs4_file *fp, *fnext;
@@ -4573,7 +4592,7 @@ int nfsd_process_n_delegations(u64 num, void (*deleg_func)(struct nfs4_delegatio
 	for (i = 0; i < FILE_HASH_SIZE; i++) {
 		list_for_each_entry_safe(fp, fnext, &file_hashtbl[i], fi_hash) {
 			list_for_each_entry_safe(dp, dnext, &fp->fi_delegations, dl_perfile) {
-				deleg_func(dp);
+				list_move(&dp->dl_recall_lru, list);
 				if (++count == num)
 					return count;
 			}
@@ -4586,9 +4605,16 @@ int nfsd_process_n_delegations(u64 num, void (*deleg_func)(struct nfs4_delegatio
 void nfsd_forget_delegations(u64 num)
 {
 	unsigned int count;
+	LIST_HEAD(victims);
+	struct nfs4_delegation *dp, *dnext;
+
+	spin_lock(&recall_lock);
+	count = nfsd_process_n_delegations(num, &victims);
+	spin_unlock(&recall_lock);
 
 	nfs4_lock_state();
-	count = nfsd_process_n_delegations(num, unhash_delegation);
+	list_for_each_entry_safe(dp, dnext, &victims, dl_recall_lru)
+		unhash_delegation(dp);
 	nfs4_unlock_state();
 
 	printk(KERN_INFO "NFSD: Forgot %d delegations", count);
@@ -4597,12 +4623,16 @@ void nfsd_forget_delegations(u64 num)
 void nfsd_recall_delegations(u64 num)
 {
 	unsigned int count;
+	LIST_HEAD(victims);
+	struct nfs4_delegation *dp, *dnext;
 
-	nfs4_lock_state();
 	spin_lock(&recall_lock);
-	count = nfsd_process_n_delegations(num, nfsd_break_one_deleg);
+	count = nfsd_process_n_delegations(num, &victims);
+	list_for_each_entry_safe(dp, dnext, &victims, dl_recall_lru) {
+		list_del(&dp->dl_recall_lru);
+		nfsd_break_one_deleg(dp);
+	}
 	spin_unlock(&recall_lock);
-	nfs4_unlock_state();
 
 	printk(KERN_INFO "NFSD: Recalled %d delegations", count);
 }
@@ -4665,6 +4695,8 @@ set_max_delegations(void)
 int
 nfs4_state_start(void)
 {
+	struct net *net = &init_net;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 	int ret;
 
 	/*
@@ -4674,11 +4706,11 @@ nfs4_state_start(void)
 	 * to that instead and then do most of the rest of this on a per-net
 	 * basis.
 	 */
-	get_net(&init_net);
-	nfsd4_client_tracking_init(&init_net);
-	boot_time = get_seconds();
-	locks_start_grace(&nfsd4_manager);
-	grace_ended = false;
+	get_net(net);
+	nfsd4_client_tracking_init(net);
+	nn->boot_time = get_seconds();
+	locks_start_grace(net, &nn->nfsd4_manager);
+	nn->grace_ended = false;
 	printk(KERN_INFO "NFSD: starting %ld-second grace period\n",
 	       nfsd4_grace);
 	ret = set_callback_cred();
@@ -4700,8 +4732,8 @@ nfs4_state_start(void)
 out_free_laundry:
 	destroy_workqueue(laundry_wq);
 out_recovery:
-	nfsd4_client_tracking_exit(&init_net);
-	put_net(&init_net);
+	nfsd4_client_tracking_exit(net);
+	put_net(net);
 	return ret;
 }
 
@@ -4742,9 +4774,12 @@ __nfs4_state_shutdown(void)
 void
 nfs4_state_shutdown(void)
 {
+	struct net *net = &init_net;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
 	cancel_delayed_work_sync(&laundromat_work);
 	destroy_workqueue(laundry_wq);
-	locks_end_grace(&nfsd4_manager);
+	locks_end_grace(&nn->nfsd4_manager);
 	nfs4_lock_state();
 	__nfs4_state_shutdown();
 	nfs4_unlock_state();
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 4949667c84ea..6322df36031f 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2259,7 +2259,7 @@ out_acl:
 	if (bmval0 & FATTR4_WORD0_CASE_INSENSITIVE) {
 		if ((buflen -= 4) < 0)
 			goto out_resource;
-		WRITE32(1);
+		WRITE32(0);
 	}
 	if (bmval0 & FATTR4_WORD0_CASE_PRESERVING) {
 		if ((buflen -= 4) < 0)
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index c55298ed5772..fa49cff5ee65 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -673,9 +673,7 @@ static ssize_t __write_ports_addfd(char *buf)
 
 	err = svc_addsock(nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT);
 	if (err < 0) {
-		if (nfsd_serv->sv_nrthreads == 1)
-			svc_shutdown_net(nfsd_serv, net);
-		svc_destroy(nfsd_serv);
+		nfsd_destroy(net);
 		return err;
 	}
 
@@ -744,9 +742,7 @@ out_close:
 		svc_xprt_put(xprt);
 	}
 out_err:
-	if (nfsd_serv->sv_nrthreads == 1)
-		svc_shutdown_net(nfsd_serv, net);
-	svc_destroy(nfsd_serv);
+	nfsd_destroy(net);
 	return err;
 }
 
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 1671429ffa66..2244222368ab 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -72,6 +72,19 @@ int		nfsd_nrthreads(void);
 int		nfsd_nrpools(void);
 int		nfsd_get_nrthreads(int n, int *);
 int		nfsd_set_nrthreads(int n, int *);
+int		nfsd_pool_stats_open(struct inode *, struct file *);
+int		nfsd_pool_stats_release(struct inode *, struct file *);
+
+static inline void nfsd_destroy(struct net *net)
+{
+	int destroy = (nfsd_serv->sv_nrthreads == 1);
+
+	if (destroy)
+		svc_shutdown_net(nfsd_serv, net);
+	svc_destroy(nfsd_serv);
+	if (destroy)
+		nfsd_serv = NULL;
+}
 
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
 #ifdef CONFIG_NFSD_V2_ACL
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index cc793005a87c..032af381b3aa 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -635,6 +635,7 @@ fh_put(struct svc_fh *fhp)
 		fhp->fh_post_saved = 0;
 #endif
 	}
+	fh_drop_write(fhp);
 	if (exp) {
 		exp_put(exp);
 		fhp->fh_export = NULL;
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index e15dc45fc5ec..aad6d457b9e8 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -196,6 +196,7 @@ nfsd_proc_create(struct svc_rqst *rqstp, struct nfsd_createargs *argp,
 	struct dentry	*dchild;
 	int		type, mode;
 	__be32		nfserr;
+	int		hosterr;
 	dev_t		rdev = 0, wanted = new_decode_dev(attr->ia_size);
 
 	dprintk("nfsd: CREATE   %s %.*s\n",
@@ -214,6 +215,12 @@ nfsd_proc_create(struct svc_rqst *rqstp, struct nfsd_createargs *argp,
 	nfserr = nfserr_exist;
 	if (isdotent(argp->name, argp->len))
 		goto done;
+	hosterr = fh_want_write(dirfhp);
+	if (hosterr) {
+		nfserr = nfserrno(hosterr);
+		goto done;
+	}
+
 	fh_lock_nested(dirfhp, I_MUTEX_PARENT);
 	dchild = lookup_one_len(argp->name, dirfhp->fh_dentry, argp->len);
 	if (IS_ERR(dchild)) {
@@ -330,7 +337,7 @@ nfsd_proc_create(struct svc_rqst *rqstp, struct nfsd_createargs *argp,
 out_unlock:
 	/* We don't really need to unlock, as fh_put does it. */
 	fh_unlock(dirfhp);
-
+	fh_drop_write(dirfhp);
 done:
 	fh_put(dirfhp);
 	return nfsd_return_dirop(nfserr, resp);
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index ee709fc8f58b..240473cb708f 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -254,8 +254,6 @@ static void nfsd_shutdown(void)
 
 static void nfsd_last_thread(struct svc_serv *serv, struct net *net)
 {
-	/* When last nfsd thread exits we need to do some clean-up */
-	nfsd_serv = NULL;
 	nfsd_shutdown();
 
 	svc_rpcb_cleanup(serv, net);
@@ -332,6 +330,7 @@ static int nfsd_get_default_max_blksize(void)
 int nfsd_create_serv(void)
 {
 	int error;
+	struct net *net = current->nsproxy->net_ns;
 
 	WARN_ON(!mutex_is_locked(&nfsd_mutex));
 	if (nfsd_serv) {
@@ -346,7 +345,7 @@ int nfsd_create_serv(void)
 	if (nfsd_serv == NULL)
 		return -ENOMEM;
 
-	error = svc_bind(nfsd_serv, current->nsproxy->net_ns);
+	error = svc_bind(nfsd_serv, net);
 	if (error < 0) {
 		svc_destroy(nfsd_serv);
 		return error;
@@ -427,11 +426,7 @@ int nfsd_set_nrthreads(int n, int *nthreads)
 		if (err)
 			break;
 	}
-
-	if (nfsd_serv->sv_nrthreads == 1)
-		svc_shutdown_net(nfsd_serv, net);
-	svc_destroy(nfsd_serv);
-
+	nfsd_destroy(net);
 	return err;
 }
 
@@ -478,9 +473,7 @@ out_shutdown:
 	if (error < 0 && !nfsd_up_before)
 		nfsd_shutdown();
 out_destroy:
-	if (nfsd_serv->sv_nrthreads == 1)
-		svc_shutdown_net(nfsd_serv, net);
-	svc_destroy(nfsd_serv);		/* Release server */
+	nfsd_destroy(net);		/* Release server */
 out:
 	mutex_unlock(&nfsd_mutex);
 	return error;
@@ -563,12 +556,13 @@ nfsd(void *vrqstp)
 	nfsdstats.th_cnt --;
 
 out:
-	if (rqstp->rq_server->sv_nrthreads == 1)
-		svc_shutdown_net(rqstp->rq_server, &init_net);
+	rqstp->rq_server = NULL;
 
 	/* Release the thread */
 	svc_exit_thread(rqstp);
 
+	nfsd_destroy(&init_net);
+
 	/* Release module */
 	mutex_unlock(&nfsd_mutex);
 	module_put_and_exit(0);
@@ -682,9 +676,7 @@ int nfsd_pool_stats_release(struct inode *inode, struct file *file)
 
 	mutex_lock(&nfsd_mutex);
 	/* this function really, really should have been called svc_put() */
-	if (nfsd_serv->sv_nrthreads == 1)
-		svc_shutdown_net(nfsd_serv, net);
-	svc_destroy(nfsd_serv);
+	nfsd_destroy(net);
 	mutex_unlock(&nfsd_mutex);
 	return ret;
 }
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 849091e16ea6..e6173147f982 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -450,8 +450,10 @@ static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s)
 #define WR_STATE	        0x00000020
 
 struct nfsd4_compound_state;
+struct nfsd_net;
 
-extern __be32 nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate,
+extern __be32 nfs4_preprocess_stateid_op(struct net *net,
+		struct nfsd4_compound_state *cstate,
 		stateid_t *stateid, int flags, struct file **filp);
 extern void nfs4_lock_state(void);
 extern void nfs4_unlock_state(void);
@@ -475,7 +477,6 @@ extern __be32 nfs4_make_rec_clidname(char *clidname, struct xdr_netobj *clname);
 extern int nfs4_client_to_reclaim(const char *name);
 extern int nfs4_has_reclaimed_state(const char *name, bool use_exchange_id);
 extern void release_session_client(struct nfsd4_session *);
-extern __be32 nfs4_validate_stateid(struct nfs4_client *, stateid_t *);
 extern void nfsd4_purge_closed_stateid(struct nfs4_stateowner *);
 
 /* nfs4recover operations */
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 4700a0a929d7..a9269f142cc4 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -757,8 +757,16 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
 	 * If we get here, then the client has already done an "open",
 	 * and (hopefully) checked permission - so allow OWNER_OVERRIDE
 	 * in case a chmod has now revoked permission.
+	 *
+	 * Arguably we should also allow the owner override for
+	 * directories, but we never have and it doesn't seem to have
+	 * caused anyone a problem.  If we were to change this, note
+	 * also that our filldir callbacks would need a variant of
+	 * lookup_one_len that doesn't check permissions.
 	 */
-	err = fh_verify(rqstp, fhp, type, may_flags | NFSD_MAY_OWNER_OVERRIDE);
+	if (type == S_IFREG)
+		may_flags |= NFSD_MAY_OWNER_OVERRIDE;
+	err = fh_verify(rqstp, fhp, type, may_flags);
 	if (err)
 		goto out;
 
@@ -1276,6 +1284,10 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	 * If it has, the parent directory should already be locked.
 	 */
 	if (!resfhp->fh_dentry) {
+		host_err = fh_want_write(fhp);
+		if (host_err)
+			goto out_nfserr;
+
 		/* called from nfsd_proc_mkdir, or possibly nfsd3_proc_create */
 		fh_lock_nested(fhp, I_MUTEX_PARENT);
 		dchild = lookup_one_len(fname, dentry, flen);
@@ -1319,14 +1331,11 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		goto out;
 	}
 
-	host_err = fh_want_write(fhp);
-	if (host_err)
-		goto out_nfserr;
-
 	/*
 	 * Get the dir op function pointer.
 	 */
 	err = 0;
+	host_err = 0;
 	switch (type) {
 	case S_IFREG:
 		host_err = vfs_create(dirp, dchild, iap->ia_mode, true);
@@ -1343,10 +1352,8 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		host_err = vfs_mknod(dirp, dchild, iap->ia_mode, rdev);
 		break;
 	}
-	if (host_err < 0) {
-		fh_drop_write(fhp);
+	if (host_err < 0)
 		goto out_nfserr;
-	}
 
 	err = nfsd_create_setattr(rqstp, resfhp, iap);
 
@@ -1358,7 +1365,6 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	err2 = nfserrno(commit_metadata(fhp));
 	if (err2)
 		err = err2;
-	fh_drop_write(fhp);
 	/*
 	 * Update the file handle to get the new inode info.
 	 */
@@ -1417,6 +1423,11 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	err = nfserr_notdir;
 	if (!dirp->i_op->lookup)
 		goto out;
+
+	host_err = fh_want_write(fhp);
+	if (host_err)
+		goto out_nfserr;
+
 	fh_lock_nested(fhp, I_MUTEX_PARENT);
 
 	/*
@@ -1449,9 +1460,6 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		v_atime = verifier[1]&0x7fffffff;
 	}
 	
-	host_err = fh_want_write(fhp);
-	if (host_err)
-		goto out_nfserr;
 	if (dchild->d_inode) {
 		err = 0;
 
@@ -1522,7 +1530,6 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	if (!err)
 		err = nfserrno(commit_metadata(fhp));
 
-	fh_drop_write(fhp);
 	/*
 	 * Update the filehandle to get the new inode info.
 	 */
@@ -1533,6 +1540,7 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	fh_unlock(fhp);
 	if (dchild && !IS_ERR(dchild))
 		dput(dchild);
+	fh_drop_write(fhp);
  	return err;
  
  out_nfserr:
@@ -1613,6 +1621,11 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE);
 	if (err)
 		goto out;
+
+	host_err = fh_want_write(fhp);
+	if (host_err)
+		goto out_nfserr;
+
 	fh_lock(fhp);
 	dentry = fhp->fh_dentry;
 	dnew = lookup_one_len(fname, dentry, flen);
@@ -1620,10 +1633,6 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	if (IS_ERR(dnew))
 		goto out_nfserr;
 
-	host_err = fh_want_write(fhp);
-	if (host_err)
-		goto out_nfserr;
-
 	if (unlikely(path[plen] != 0)) {
 		char *path_alloced = kmalloc(plen+1, GFP_KERNEL);
 		if (path_alloced == NULL)
@@ -1683,6 +1692,12 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
 	if (isdotent(name, len))
 		goto out;
 
+	host_err = fh_want_write(tfhp);
+	if (host_err) {
+		err = nfserrno(host_err);
+		goto out;
+	}
+
 	fh_lock_nested(ffhp, I_MUTEX_PARENT);
 	ddir = ffhp->fh_dentry;
 	dirp = ddir->d_inode;
@@ -1694,18 +1709,13 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
 
 	dold = tfhp->fh_dentry;
 
-	host_err = fh_want_write(tfhp);
-	if (host_err) {
-		err = nfserrno(host_err);
-		goto out_dput;
-	}
 	err = nfserr_noent;
 	if (!dold->d_inode)
-		goto out_drop_write;
+		goto out_dput;
 	host_err = nfsd_break_lease(dold->d_inode);
 	if (host_err) {
 		err = nfserrno(host_err);
-		goto out_drop_write;
+		goto out_dput;
 	}
 	host_err = vfs_link(dold, dirp, dnew);
 	if (!host_err) {
@@ -1718,12 +1728,11 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
 		else
 			err = nfserrno(host_err);
 	}
-out_drop_write:
-	fh_drop_write(tfhp);
 out_dput:
 	dput(dnew);
 out_unlock:
 	fh_unlock(ffhp);
+	fh_drop_write(tfhp);
 out:
 	return err;
 
@@ -1766,6 +1775,12 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 	if (!flen || isdotent(fname, flen) || !tlen || isdotent(tname, tlen))
 		goto out;
 
+	host_err = fh_want_write(ffhp);
+	if (host_err) {
+		err = nfserrno(host_err);
+		goto out;
+	}
+
 	/* cannot use fh_lock as we need deadlock protective ordering
 	 * so do it by hand */
 	trap = lock_rename(tdentry, fdentry);
@@ -1796,17 +1811,14 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 	host_err = -EXDEV;
 	if (ffhp->fh_export->ex_path.mnt != tfhp->fh_export->ex_path.mnt)
 		goto out_dput_new;
-	host_err = fh_want_write(ffhp);
-	if (host_err)
-		goto out_dput_new;
 
 	host_err = nfsd_break_lease(odentry->d_inode);
 	if (host_err)
-		goto out_drop_write;
+		goto out_dput_new;
 	if (ndentry->d_inode) {
 		host_err = nfsd_break_lease(ndentry->d_inode);
 		if (host_err)
-			goto out_drop_write;
+			goto out_dput_new;
 	}
 	host_err = vfs_rename(fdir, odentry, tdir, ndentry);
 	if (!host_err) {
@@ -1814,8 +1826,6 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 		if (!host_err)
 			host_err = commit_metadata(ffhp);
 	}
-out_drop_write:
-	fh_drop_write(ffhp);
  out_dput_new:
 	dput(ndentry);
  out_dput_old:
@@ -1831,6 +1841,7 @@ out_drop_write:
 	fill_post_wcc(tfhp);
 	unlock_rename(tdentry, fdentry);
 	ffhp->fh_locked = tfhp->fh_locked = 0;
+	fh_drop_write(ffhp);
 
 out:
 	return err;
@@ -1856,6 +1867,10 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 	if (err)
 		goto out;
 
+	host_err = fh_want_write(fhp);
+	if (host_err)
+		goto out_nfserr;
+
 	fh_lock_nested(fhp, I_MUTEX_PARENT);
 	dentry = fhp->fh_dentry;
 	dirp = dentry->d_inode;
@@ -1874,21 +1889,15 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 	if (!type)
 		type = rdentry->d_inode->i_mode & S_IFMT;
 
-	host_err = fh_want_write(fhp);
-	if (host_err)
-		goto out_put;
-
 	host_err = nfsd_break_lease(rdentry->d_inode);
 	if (host_err)
-		goto out_drop_write;
+		goto out_put;
 	if (type != S_IFDIR)
 		host_err = vfs_unlink(dirp, rdentry);
 	else
 		host_err = vfs_rmdir(dirp, rdentry);
 	if (!host_err)
 		host_err = commit_metadata(fhp);
-out_drop_write:
-	fh_drop_write(fhp);
 out_put:
 	dput(rdentry);
 
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index ec0611b2b738..359594c393d2 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -110,12 +110,19 @@ int nfsd_set_posix_acl(struct svc_fh *, int, struct posix_acl *);
 
 static inline int fh_want_write(struct svc_fh *fh)
 {
-	return mnt_want_write(fh->fh_export->ex_path.mnt);
+	int ret = mnt_want_write(fh->fh_export->ex_path.mnt);
+
+	if (!ret)
+		fh->fh_want_write = 1;
+	return ret;
 }
 
 static inline void fh_drop_write(struct svc_fh *fh)
 {
-	mnt_drop_write(fh->fh_export->ex_path.mnt);
+	if (fh->fh_want_write) {
+		fh->fh_want_write = 0;
+		mnt_drop_write(fh->fh_export->ex_path.mnt);
+	}
 }
 
 #endif /* LINUX_NFSD_VFS_H */
diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h
index f5fde36b9e28..fb7238100548 100644
--- a/fs/nilfs2/alloc.h
+++ b/fs/nilfs2/alloc.h
@@ -76,15 +76,23 @@ int nilfs_palloc_freev(struct inode *, __u64 *, size_t);
 #define nilfs_clear_bit_atomic		ext2_clear_bit_atomic
 #define nilfs_find_next_zero_bit	find_next_zero_bit_le
 
-/*
- * persistent object allocator cache
+/**
+ * struct nilfs_bh_assoc - block offset and buffer head association
+ * @blkoff: block offset
+ * @bh: buffer head
  */
-
 struct nilfs_bh_assoc {
 	unsigned long blkoff;
 	struct buffer_head *bh;
 };
 
+/**
+ * struct nilfs_palloc_cache - persistent object allocator cache
+ * @lock: cache protecting lock
+ * @prev_desc: blockgroup descriptors cache
+ * @prev_bitmap: blockgroup bitmap cache
+ * @prev_entry: translation entries cache
+ */
 struct nilfs_palloc_cache {
 	spinlock_t lock;
 	struct nilfs_bh_assoc prev_desc;
diff --git a/fs/nilfs2/bmap.h b/fs/nilfs2/bmap.h
index 40d9f453d31c..b89e68076adc 100644
--- a/fs/nilfs2/bmap.h
+++ b/fs/nilfs2/bmap.h
@@ -135,6 +135,13 @@ struct nilfs_bmap {
 /* state */
 #define NILFS_BMAP_DIRTY	0x00000001
 
+/**
+ * struct nilfs_bmap_store - shadow copy of bmap state
+ * @data: cached raw block mapping of on-disk inode
+ * @last_allocated_key: cached value of last allocated key for data block
+ * @last_allocated_ptr: cached value of last allocated ptr for data block
+ * @state: cached value of state field of bmap structure
+ */
 struct nilfs_bmap_store {
 	__le64 data[NILFS_BMAP_SIZE / sizeof(__le64)];
 	__u64 last_allocated_key;
diff --git a/fs/nilfs2/btnode.h b/fs/nilfs2/btnode.h
index 3a4dd2d8d3fc..d876b565ce64 100644
--- a/fs/nilfs2/btnode.h
+++ b/fs/nilfs2/btnode.h
@@ -29,7 +29,13 @@
 #include <linux/fs.h>
 #include <linux/backing-dev.h>
 
-
+/**
+ * struct nilfs_btnode_chkey_ctxt - change key context
+ * @oldkey: old key of block's moving content
+ * @newkey: new key for block's content
+ * @bh: buffer head of old buffer
+ * @newbh: buffer head of new buffer
+ */
 struct nilfs_btnode_chkey_ctxt {
 	__u64 oldkey;
 	__u64 newkey;
diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c
index dab5c4c6dfaf..deaa3d33a0aa 100644
--- a/fs/nilfs2/cpfile.c
+++ b/fs/nilfs2/cpfile.c
@@ -286,7 +286,7 @@ int nilfs_cpfile_delete_checkpoints(struct inode *cpfile,
 	__u64 cno;
 	void *kaddr;
 	unsigned long tnicps;
-	int ret, ncps, nicps, count, i;
+	int ret, ncps, nicps, nss, count, i;
 
 	if (unlikely(start == 0 || start > end)) {
 		printk(KERN_ERR "%s: invalid range of checkpoint numbers: "
@@ -301,6 +301,7 @@ int nilfs_cpfile_delete_checkpoints(struct inode *cpfile,
 	if (ret < 0)
 		goto out_sem;
 	tnicps = 0;
+	nss = 0;
 
 	for (cno = start; cno < end; cno += ncps) {
 		ncps = nilfs_cpfile_checkpoints_in_block(cpfile, cno, end);
@@ -318,8 +319,9 @@ int nilfs_cpfile_delete_checkpoints(struct inode *cpfile,
 			cpfile, cno, cp_bh, kaddr);
 		nicps = 0;
 		for (i = 0; i < ncps; i++, cp = (void *)cp + cpsz) {
-			WARN_ON(nilfs_checkpoint_snapshot(cp));
-			if (!nilfs_checkpoint_invalid(cp)) {
+			if (nilfs_checkpoint_snapshot(cp)) {
+				nss++;
+			} else if (!nilfs_checkpoint_invalid(cp)) {
 				nilfs_checkpoint_set_invalid(cp);
 				nicps++;
 			}
@@ -364,6 +366,8 @@ int nilfs_cpfile_delete_checkpoints(struct inode *cpfile,
 	}
 
 	brelse(header_bh);
+	if (nss > 0)
+		ret = -EBUSY;
 
  out_sem:
 	up_write(&NILFS_MDT(cpfile)->mi_sem);
diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c
index b5c13f3576b9..fa0f80308c2d 100644
--- a/fs/nilfs2/dat.c
+++ b/fs/nilfs2/dat.c
@@ -33,6 +33,12 @@
 #define NILFS_CNO_MIN	((__u64)1)
 #define NILFS_CNO_MAX	(~(__u64)0)
 
+/**
+ * struct nilfs_dat_info - on-memory private data of DAT file
+ * @mi: on-memory private data of metadata file
+ * @palloc_cache: persistent object allocator cache of DAT file
+ * @shadow: shadow map of DAT file
+ */
 struct nilfs_dat_info {
 	struct nilfs_mdt_info mi;
 	struct nilfs_palloc_cache palloc_cache;
diff --git a/fs/nilfs2/export.h b/fs/nilfs2/export.h
index a71cc412b651..19ccbf9522ab 100644
--- a/fs/nilfs2/export.h
+++ b/fs/nilfs2/export.h
@@ -5,6 +5,14 @@
 
 extern const struct export_operations nilfs_export_ops;
 
+/**
+ * struct nilfs_fid - NILFS file id type
+ * @cno: checkpoint number
+ * @ino: inode number
+ * @gen: file generation (version) for NFS
+ * @parent_gen: parent generation (version) for NFS
+ * @parent_ino: parent inode number
+ */
 struct nilfs_fid {
 	u64 cno;
 	u64 ino;
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index 62cebc8e1a1f..a4d56ac02e6c 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -69,16 +69,18 @@ static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	struct page *page = vmf->page;
 	struct inode *inode = vma->vm_file->f_dentry->d_inode;
 	struct nilfs_transaction_info ti;
-	int ret;
+	int ret = 0;
 
 	if (unlikely(nilfs_near_disk_full(inode->i_sb->s_fs_info)))
 		return VM_FAULT_SIGBUS; /* -ENOSPC */
 
+	sb_start_pagefault(inode->i_sb);
 	lock_page(page);
 	if (page->mapping != inode->i_mapping ||
 	    page_offset(page) >= i_size_read(inode) || !PageUptodate(page)) {
 		unlock_page(page);
-		return VM_FAULT_NOPAGE; /* make the VM retry the fault */
+		ret = -EFAULT;	/* make the VM retry the fault */
+		goto out;
 	}
 
 	/*
@@ -112,19 +114,21 @@ static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	ret = nilfs_transaction_begin(inode->i_sb, &ti, 1);
 	/* never returns -ENOMEM, but may return -ENOSPC */
 	if (unlikely(ret))
-		return VM_FAULT_SIGBUS;
+		goto out;
 
-	ret = block_page_mkwrite(vma, vmf, nilfs_get_block);
-	if (ret != VM_FAULT_LOCKED) {
+	ret = __block_page_mkwrite(vma, vmf, nilfs_get_block);
+	if (ret) {
 		nilfs_transaction_abort(inode->i_sb);
-		return ret;
+		goto out;
 	}
 	nilfs_set_file_dirty(inode, 1 << (PAGE_SHIFT - inode->i_blkbits));
 	nilfs_transaction_commit(inode->i_sb);
 
  mapped:
 	wait_on_page_writeback(page);
-	return VM_FAULT_LOCKED;
+ out:
+	sb_end_pagefault(inode->i_sb);
+	return block_page_mkwrite_return(ret);
 }
 
 static const struct vm_operations_struct nilfs_file_vm_ops = {
diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c
index 5a48df79d674..d8e65bde083c 100644
--- a/fs/nilfs2/ifile.c
+++ b/fs/nilfs2/ifile.c
@@ -29,7 +29,11 @@
 #include "alloc.h"
 #include "ifile.h"
 
-
+/**
+ * struct nilfs_ifile_info - on-memory private data of ifile
+ * @mi: on-memory private data of metadata file
+ * @palloc_cache: persistent object allocator cache of ifile
+ */
 struct nilfs_ifile_info {
 	struct nilfs_mdt_info mi;
 	struct nilfs_palloc_cache palloc_cache;
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 7cc64465ec26..6e2c3db976b2 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -34,6 +34,13 @@
 #include "cpfile.h"
 #include "ifile.h"
 
+/**
+ * struct nilfs_iget_args - arguments used during comparison between inodes
+ * @ino: inode number
+ * @cno: checkpoint number
+ * @root: pointer on NILFS root object (mounted checkpoint)
+ * @for_gc: inode for GC flag
+ */
 struct nilfs_iget_args {
 	u64 ino;
 	__u64 cno;
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 06658caa18bd..fdb180769485 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -182,7 +182,7 @@ static int nilfs_ioctl_change_cpmode(struct inode *inode, struct file *filp,
 	if (copy_from_user(&cpmode, argp, sizeof(cpmode)))
 		goto out;
 
-	down_read(&inode->i_sb->s_umount);
+	mutex_lock(&nilfs->ns_snapshot_mount_mutex);
 
 	nilfs_transaction_begin(inode->i_sb, &ti, 0);
 	ret = nilfs_cpfile_change_cpmode(
@@ -192,7 +192,7 @@ static int nilfs_ioctl_change_cpmode(struct inode *inode, struct file *filp,
 	else
 		nilfs_transaction_commit(inode->i_sb); /* never fails */
 
-	up_read(&inode->i_sb->s_umount);
+	mutex_unlock(&nilfs->ns_snapshot_mount_mutex);
 out:
 	mnt_drop_write_file(filp);
 	return ret;
@@ -660,8 +660,6 @@ static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp,
 		goto out_free;
 	}
 
-	vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
-
 	ret = nilfs_ioctl_move_blocks(inode->i_sb, &argv[0], kbufs[0]);
 	if (ret < 0)
 		printk(KERN_ERR "NILFS: GC failed during preparation: "
diff --git a/fs/nilfs2/mdt.h b/fs/nilfs2/mdt.h
index ab20a4baa50f..ab172e8549c5 100644
--- a/fs/nilfs2/mdt.h
+++ b/fs/nilfs2/mdt.h
@@ -28,6 +28,13 @@
 #include "nilfs.h"
 #include "page.h"
 
+/**
+ * struct nilfs_shadow_map - shadow mapping of meta data file
+ * @bmap_store: shadow copy of bmap state
+ * @frozen_data: shadowed dirty data pages
+ * @frozen_btnodes: shadowed dirty b-tree nodes' pages
+ * @frozen_buffers: list of frozen buffers
+ */
 struct nilfs_shadow_map {
 	struct nilfs_bmap_store bmap_store;
 	struct address_space frozen_data;
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index 250add84da76..74cece80e9a3 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -32,8 +32,21 @@
 #include "the_nilfs.h"
 #include "bmap.h"
 
-/*
- * nilfs inode data in memory
+/**
+ * struct nilfs_inode_info - nilfs inode data in memory
+ * @i_flags: inode flags
+ * @i_state: dynamic state flags
+ * @i_bmap: pointer on i_bmap_data
+ * @i_bmap_data: raw block mapping
+ * @i_xattr: <TODO>
+ * @i_dir_start_lookup: page index of last successful search
+ * @i_cno: checkpoint number for GC inode
+ * @i_btnode_cache: cached pages of b-tree nodes
+ * @i_dirty: list for connecting dirty files
+ * @xattr_sem: semaphore for extended attributes processing
+ * @i_bh: buffer contains disk inode
+ * @i_root: root object of the current filesystem tree
+ * @vfs_inode: VFS inode object
  */
 struct nilfs_inode_info {
 	__u32 i_flags;
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 88e11fb346b6..a5752a589932 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -189,7 +189,7 @@ int nilfs_transaction_begin(struct super_block *sb,
 	if (ret > 0)
 		return 0;
 
-	vfs_check_frozen(sb, SB_FREEZE_WRITE);
+	sb_start_intwrite(sb);
 
 	nilfs = sb->s_fs_info;
 	down_read(&nilfs->ns_segctor_sem);
@@ -205,6 +205,7 @@ int nilfs_transaction_begin(struct super_block *sb,
 	current->journal_info = ti->ti_save;
 	if (ti->ti_flags & NILFS_TI_DYNAMIC_ALLOC)
 		kmem_cache_free(nilfs_transaction_cachep, ti);
+	sb_end_intwrite(sb);
 	return ret;
 }
 
@@ -246,6 +247,7 @@ int nilfs_transaction_commit(struct super_block *sb)
 		err = nilfs_construct_segment(sb);
 	if (ti->ti_flags & NILFS_TI_DYNAMIC_ALLOC)
 		kmem_cache_free(nilfs_transaction_cachep, ti);
+	sb_end_intwrite(sb);
 	return err;
 }
 
@@ -264,6 +266,7 @@ void nilfs_transaction_abort(struct super_block *sb)
 	current->journal_info = ti->ti_save;
 	if (ti->ti_flags & NILFS_TI_DYNAMIC_ALLOC)
 		kmem_cache_free(nilfs_transaction_cachep, ti);
+	sb_end_intwrite(sb);
 }
 
 void nilfs_relax_pressure_in_lock(struct super_block *sb)
diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c
index c5b7653a4391..3127e9f438a7 100644
--- a/fs/nilfs2/sufile.c
+++ b/fs/nilfs2/sufile.c
@@ -30,7 +30,13 @@
 #include "mdt.h"
 #include "sufile.h"
 
-
+/**
+ * struct nilfs_sufile_info - on-memory private data of sufile
+ * @mi: on-memory private data of metadata file
+ * @ncleansegs: number of clean segments
+ * @allocmin: lower limit of allocatable segment range
+ * @allocmax: upper limit of allocatable segment range
+ */
 struct nilfs_sufile_info {
 	struct nilfs_mdt_info mi;
 	unsigned long ncleansegs;/* number of clean segments */
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index d57c42f974ea..6522cac6057c 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -677,7 +677,6 @@ static const struct super_operations nilfs_sops = {
 	.destroy_inode  = nilfs_destroy_inode,
 	.dirty_inode    = nilfs_dirty_inode,
 	/* .write_inode    = nilfs_write_inode, */
-	/* .put_inode      = nilfs_put_inode, */
 	/* .drop_inode	  = nilfs_drop_inode, */
 	.evict_inode    = nilfs_evict_inode,
 	.put_super      = nilfs_put_super,
@@ -685,8 +684,6 @@ static const struct super_operations nilfs_sops = {
 	.sync_fs        = nilfs_sync_fs,
 	.freeze_fs	= nilfs_freeze,
 	.unfreeze_fs	= nilfs_unfreeze,
-	/* .write_super_lockfs */
-	/* .unlockfs */
 	.statfs         = nilfs_statfs,
 	.remount_fs     = nilfs_remount,
 	/* .umount_begin */
@@ -948,6 +945,8 @@ static int nilfs_attach_snapshot(struct super_block *s, __u64 cno,
 	struct nilfs_root *root;
 	int ret;
 
+	mutex_lock(&nilfs->ns_snapshot_mount_mutex);
+
 	down_read(&nilfs->ns_segctor_sem);
 	ret = nilfs_cpfile_is_snapshot(nilfs->ns_cpfile, cno);
 	up_read(&nilfs->ns_segctor_sem);
@@ -972,6 +971,7 @@ static int nilfs_attach_snapshot(struct super_block *s, __u64 cno,
 	ret = nilfs_get_root_dentry(s, root, root_dentry);
 	nilfs_put_root(root);
  out:
+	mutex_unlock(&nilfs->ns_snapshot_mount_mutex);
 	return ret;
 }
 
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 501b7f8b739f..41e6a04a561f 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -76,6 +76,7 @@ struct the_nilfs *alloc_nilfs(struct block_device *bdev)
 	nilfs->ns_bdev = bdev;
 	atomic_set(&nilfs->ns_ndirtyblks, 0);
 	init_rwsem(&nilfs->ns_sem);
+	mutex_init(&nilfs->ns_snapshot_mount_mutex);
 	INIT_LIST_HEAD(&nilfs->ns_dirty_files);
 	INIT_LIST_HEAD(&nilfs->ns_gc_inodes);
 	spin_lock_init(&nilfs->ns_inode_lock);
diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h
index 9992b11312ff..6eee4177807b 100644
--- a/fs/nilfs2/the_nilfs.h
+++ b/fs/nilfs2/the_nilfs.h
@@ -47,11 +47,13 @@ enum {
  * @ns_flags: flags
  * @ns_bdev: block device
  * @ns_sem: semaphore for shared states
+ * @ns_snapshot_mount_mutex: mutex to protect snapshot mounts
  * @ns_sbh: buffer heads of on-disk super blocks
  * @ns_sbp: pointers to super block data
  * @ns_sbwtime: previous write time of super block
  * @ns_sbwcount: write count of super block
  * @ns_sbsize: size of valid data in super block
+ * @ns_mount_state: file system state
  * @ns_seg_seq: segment sequence counter
  * @ns_segnum: index number of the latest full segment.
  * @ns_nextnum: index number of the full segment index to be used next
@@ -99,6 +101,7 @@ struct the_nilfs {
 
 	struct block_device    *ns_bdev;
 	struct rw_semaphore	ns_sem;
+	struct mutex		ns_snapshot_mount_mutex;
 
 	/*
 	 * used for
@@ -229,9 +232,8 @@ THE_NILFS_FNS(SB_DIRTY, sb_dirty)
  * @count: refcount of this structure
  * @nilfs: nilfs object
  * @ifile: inode file
- * @root: root inode
  * @inodes_count: number of inodes
- * @blocks_count: number of blocks (Reserved)
+ * @blocks_count: number of blocks
  */
 struct nilfs_root {
 	__u64 cno;
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index 7389d2d5e51d..1ecf46448f85 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -2084,7 +2084,6 @@ static ssize_t ntfs_file_aio_write_nolock(struct kiocb *iocb,
 	if (err)
 		return err;
 	pos = *ppos;
-	vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
 	/* We can write back this queue in page reclaim. */
 	current->backing_dev_info = mapping->backing_dev_info;
 	written = 0;
@@ -2119,6 +2118,7 @@ static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 
 	BUG_ON(iocb->ki_pos != pos);
 
+	sb_start_write(inode->i_sb);
 	mutex_lock(&inode->i_mutex);
 	ret = ntfs_file_aio_write_nolock(iocb, iov, nr_segs, &iocb->ki_pos);
 	mutex_unlock(&inode->i_mutex);
@@ -2127,6 +2127,7 @@ static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		if (err < 0)
 			ret = err;
 	}
+	sb_end_write(inode->i_sb);
 	return ret;
 }
 
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index b341492542ca..2bc149d6a784 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -2660,31 +2660,14 @@ static const struct super_operations ntfs_sops = {
 	.alloc_inode	= ntfs_alloc_big_inode,	  /* VFS: Allocate new inode. */
 	.destroy_inode	= ntfs_destroy_big_inode, /* VFS: Deallocate inode. */
 #ifdef NTFS_RW
-	//.dirty_inode	= NULL,			/* VFS: Called from
-	//					   __mark_inode_dirty(). */
 	.write_inode	= ntfs_write_inode,	/* VFS: Write dirty inode to
 						   disk. */
-	//.drop_inode	= NULL,			/* VFS: Called just after the
-	//					   inode reference count has
-	//					   been decreased to zero.
-	//					   NOTE: The inode lock is
-	//					   held. See fs/inode.c::
-	//					   generic_drop_inode(). */
-	//.delete_inode	= NULL,			/* VFS: Delete inode from disk.
-	//					   Called when i_count becomes
-	//					   0 and i_nlink is also 0. */
-	//.write_super	= NULL,			/* Flush dirty super block to
-	//					   disk. */
-	//.sync_fs	= NULL,			/* ? */
-	//.write_super_lockfs	= NULL,		/* ? */
-	//.unlockfs	= NULL,			/* ? */
 #endif /* NTFS_RW */
 	.put_super	= ntfs_put_super,	/* Syscall: umount. */
 	.statfs		= ntfs_statfs,		/* Syscall: statfs */
 	.remount_fs	= ntfs_remount,		/* Syscall: mount -o remount. */
 	.evict_inode	= ntfs_evict_big_inode,	/* VFS: Called when an inode is
 						   removed from memory. */
-	//.umount_begin	= NULL,			/* Forced umount. */
 	.show_options	= ntfs_show_options,	/* Show mount options in
 						   proc. */
 };
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 7602783d7f41..46a1f6d75104 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1971,6 +1971,7 @@ int ocfs2_change_file_space(struct file *file, unsigned int cmd,
 {
 	struct inode *inode = file->f_path.dentry->d_inode;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	int ret;
 
 	if ((cmd == OCFS2_IOC_RESVSP || cmd == OCFS2_IOC_RESVSP64) &&
 	    !ocfs2_writes_unwritten_extents(osb))
@@ -1985,7 +1986,12 @@ int ocfs2_change_file_space(struct file *file, unsigned int cmd,
 	if (!(file->f_mode & FMODE_WRITE))
 		return -EBADF;
 
-	return __ocfs2_change_file_space(file, inode, file->f_pos, cmd, sr, 0);
+	ret = mnt_want_write_file(file);
+	if (ret)
+		return ret;
+	ret = __ocfs2_change_file_space(file, inode, file->f_pos, cmd, sr, 0);
+	mnt_drop_write_file(file);
+	return ret;
 }
 
 static long ocfs2_fallocate(struct file *file, int mode, loff_t offset,
@@ -2261,7 +2267,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
 	if (iocb->ki_left == 0)
 		return 0;
 
-	vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
+	sb_start_write(inode->i_sb);
 
 	appending = file->f_flags & O_APPEND ? 1 : 0;
 	direct_io = file->f_flags & O_DIRECT ? 1 : 0;
@@ -2436,6 +2442,7 @@ out_sems:
 		ocfs2_iocb_clear_sem_locked(iocb);
 
 	mutex_unlock(&inode->i_mutex);
+	sb_end_write(inode->i_sb);
 
 	if (written)
 		ret = written;
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index d96f7f81d8dd..f20edcbfe700 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -928,7 +928,12 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		if (get_user(new_clusters, (int __user *)arg))
 			return -EFAULT;
 
-		return ocfs2_group_extend(inode, new_clusters);
+		status = mnt_want_write_file(filp);
+		if (status)
+			return status;
+		status = ocfs2_group_extend(inode, new_clusters);
+		mnt_drop_write_file(filp);
+		return status;
 	case OCFS2_IOC_GROUP_ADD:
 	case OCFS2_IOC_GROUP_ADD64:
 		if (!capable(CAP_SYS_RESOURCE))
@@ -937,7 +942,12 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		if (copy_from_user(&input, (int __user *) arg, sizeof(input)))
 			return -EFAULT;
 
-		return ocfs2_group_add(inode, &input);
+		status = mnt_want_write_file(filp);
+		if (status)
+			return status;
+		status = ocfs2_group_add(inode, &input);
+		mnt_drop_write_file(filp);
+		return status;
 	case OCFS2_IOC_REFLINK:
 		if (copy_from_user(&args, argp, sizeof(args)))
 			return -EFAULT;
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 0a42ae96dca7..2dd36af79e26 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -355,11 +355,14 @@ handle_t *ocfs2_start_trans(struct ocfs2_super *osb, int max_buffs)
 	if (journal_current_handle())
 		return jbd2_journal_start(journal, max_buffs);
 
+	sb_start_intwrite(osb->sb);
+
 	down_read(&osb->journal->j_trans_barrier);
 
 	handle = jbd2_journal_start(journal, max_buffs);
 	if (IS_ERR(handle)) {
 		up_read(&osb->journal->j_trans_barrier);
+		sb_end_intwrite(osb->sb);
 
 		mlog_errno(PTR_ERR(handle));
 
@@ -388,8 +391,10 @@ int ocfs2_commit_trans(struct ocfs2_super *osb,
 	if (ret < 0)
 		mlog_errno(ret);
 
-	if (!nested)
+	if (!nested) {
 		up_read(&journal->j_trans_barrier);
+		sb_end_intwrite(osb->sb);
+	}
 
 	return ret;
 }
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index 210c35237548..a9f78c74d687 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -784,14 +784,10 @@ bail:
 
 static u32 ocfs2_local_alloc_count_bits(struct ocfs2_dinode *alloc)
 {
-	int i;
-	u8 *buffer;
-	u32 count = 0;
+	u32 count;
 	struct ocfs2_local_alloc *la = OCFS2_LOCAL_ALLOC(alloc);
 
-	buffer = la->la_bitmap;
-	for (i = 0; i < le16_to_cpu(la->la_size); i++)
-		count += hweight8(buffer[i]);
+	count = memweight(la->la_bitmap, le16_to_cpu(la->la_size));
 
 	trace_ocfs2_local_alloc_count_bits(count);
 	return count;
diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c
index 9cd41083e991..d150372fd81d 100644
--- a/fs/ocfs2/mmap.c
+++ b/fs/ocfs2/mmap.c
@@ -136,6 +136,7 @@ static int ocfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	sigset_t oldset;
 	int ret;
 
+	sb_start_pagefault(inode->i_sb);
 	ocfs2_block_signals(&oldset);
 
 	/*
@@ -165,6 +166,7 @@ static int ocfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 out:
 	ocfs2_unblock_signals(&oldset);
+	sb_end_pagefault(inode->i_sb);
 	return ret;
 }
 
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 9f32d7cbb7a3..30a055049e16 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -4466,20 +4466,11 @@ int ocfs2_reflink_ioctl(struct inode *inode,
 		goto out_dput;
 	}
 
-	error = mnt_want_write(new_path.mnt);
-	if (error) {
-		mlog_errno(error);
-		goto out_dput;
-	}
-
 	error = ocfs2_vfs_reflink(old_path.dentry,
 				  new_path.dentry->d_inode,
 				  new_dentry, preserve);
-	mnt_drop_write(new_path.mnt);
 out_dput:
-	dput(new_dentry);
-	mutex_unlock(&new_path.dentry->d_inode->i_mutex);
-	path_put(&new_path);
+	done_path_create(&new_path, new_dentry);
 out:
 	path_put(&old_path);
 
diff --git a/fs/open.c b/fs/open.c
index 1e914b397e12..f3d96e7e7b19 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -164,11 +164,13 @@ static long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
 	if (IS_APPEND(inode))
 		goto out_putf;
 
+	sb_start_write(inode->i_sb);
 	error = locks_verify_truncate(inode, file, length);
 	if (!error)
 		error = security_path_truncate(&file->f_path);
 	if (!error)
 		error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, file);
+	sb_end_write(inode->i_sb);
 out_putf:
 	fput(file);
 out:
@@ -266,7 +268,10 @@ int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	if (!file->f_op->fallocate)
 		return -EOPNOTSUPP;
 
-	return file->f_op->fallocate(file, mode, offset, len);
+	sb_start_write(inode->i_sb);
+	ret = file->f_op->fallocate(file, mode, offset, len);
+	sb_end_write(inode->i_sb);
+	return ret;
 }
 
 SYSCALL_DEFINE(fallocate)(int fd, int mode, loff_t offset, loff_t len)
@@ -620,7 +625,7 @@ static inline int __get_file_write_access(struct inode *inode,
 		/*
 		 * Balanced in __fput()
 		 */
-		error = mnt_want_write(mnt);
+		error = __mnt_want_write(mnt);
 		if (error)
 			put_write_access(inode);
 	}
@@ -654,6 +659,7 @@ static int do_dentry_open(struct file *f,
 	if (unlikely(f->f_flags & O_PATH))
 		f->f_mode = FMODE_PATH;
 
+	path_get(&f->f_path);
 	inode = f->f_path.dentry->d_inode;
 	if (f->f_mode & FMODE_WRITE) {
 		error = __get_file_write_access(inode, f->f_path.mnt);
@@ -739,9 +745,7 @@ int finish_open(struct file *file, struct dentry *dentry,
 	int error;
 	BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
 
-	mntget(file->f_path.mnt);
-	file->f_path.dentry = dget(dentry);
-
+	file->f_path.dentry = dentry;
 	error = do_dentry_open(file, open, current_cred());
 	if (!error)
 		*opened |= FILE_OPENED;
@@ -784,7 +788,6 @@ struct file *dentry_open(const struct path *path, int flags,
 
 	f->f_flags = flags;
 	f->f_path = *path;
-	path_get(&f->f_path);
 	error = do_dentry_open(f, NULL, cred);
 	if (!error) {
 		error = open_check_o_direct(f);
diff --git a/fs/pipe.c b/fs/pipe.c
index 95cbd6b227e6..8d85d7068c1e 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -1016,18 +1016,16 @@ fail_inode:
 	return NULL;
 }
 
-struct file *create_write_pipe(int flags)
+int create_pipe_files(struct file **res, int flags)
 {
 	int err;
-	struct inode *inode;
+	struct inode *inode = get_pipe_inode();
 	struct file *f;
 	struct path path;
-	struct qstr name = { .name = "" };
+	static struct qstr name = { .name = "" };
 
-	err = -ENFILE;
-	inode = get_pipe_inode();
 	if (!inode)
-		goto err;
+		return -ENFILE;
 
 	err = -ENOMEM;
 	path.dentry = d_alloc_pseudo(pipe_mnt->mnt_sb, &name);
@@ -1041,62 +1039,43 @@ struct file *create_write_pipe(int flags)
 	f = alloc_file(&path, FMODE_WRITE, &write_pipefifo_fops);
 	if (!f)
 		goto err_dentry;
-	f->f_mapping = inode->i_mapping;
 
 	f->f_flags = O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT));
-	f->f_version = 0;
 
-	return f;
+	res[0] = alloc_file(&path, FMODE_READ, &read_pipefifo_fops);
+	if (!res[0])
+		goto err_file;
+
+	path_get(&path);
+	res[0]->f_flags = O_RDONLY | (flags & O_NONBLOCK);
+	res[1] = f;
+	return 0;
 
- err_dentry:
+err_file:
+	put_filp(f);
+err_dentry:
 	free_pipe_info(inode);
 	path_put(&path);
-	return ERR_PTR(err);
+	return err;
 
- err_inode:
+err_inode:
 	free_pipe_info(inode);
 	iput(inode);
- err:
-	return ERR_PTR(err);
-}
-
-void free_write_pipe(struct file *f)
-{
-	free_pipe_info(f->f_dentry->d_inode);
-	path_put(&f->f_path);
-	put_filp(f);
-}
-
-struct file *create_read_pipe(struct file *wrf, int flags)
-{
-	/* Grab pipe from the writer */
-	struct file *f = alloc_file(&wrf->f_path, FMODE_READ,
-				    &read_pipefifo_fops);
-	if (!f)
-		return ERR_PTR(-ENFILE);
-
-	path_get(&wrf->f_path);
-	f->f_flags = O_RDONLY | (flags & O_NONBLOCK);
-
-	return f;
+	return err;
 }
 
 int do_pipe_flags(int *fd, int flags)
 {
-	struct file *fw, *fr;
+	struct file *files[2];
 	int error;
 	int fdw, fdr;
 
 	if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT))
 		return -EINVAL;
 
-	fw = create_write_pipe(flags);
-	if (IS_ERR(fw))
-		return PTR_ERR(fw);
-	fr = create_read_pipe(fw, flags);
-	error = PTR_ERR(fr);
-	if (IS_ERR(fr))
-		goto err_write_pipe;
+	error = create_pipe_files(files, flags);
+	if (error)
+		return error;
 
 	error = get_unused_fd_flags(flags);
 	if (error < 0)
@@ -1109,8 +1088,8 @@ int do_pipe_flags(int *fd, int flags)
 	fdw = error;
 
 	audit_fd_pair(fdr, fdw);
-	fd_install(fdr, fr);
-	fd_install(fdw, fw);
+	fd_install(fdr, files[0]);
+	fd_install(fdw, files[1]);
 	fd[0] = fdr;
 	fd[1] = fdw;
 
@@ -1119,10 +1098,8 @@ int do_pipe_flags(int *fd, int flags)
  err_fdr:
 	put_unused_fd(fdr);
  err_read_pipe:
-	path_put(&fr->f_path);
-	put_filp(fr);
- err_write_pipe:
-	free_write_pipe(fw);
+	fput(files[0]);
+	fput(files[1]);
 	return error;
 }
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 2772208338f8..1b6c84cbdb73 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -695,8 +695,6 @@ static int __mem_open(struct inode *inode, struct file *file, unsigned int mode)
 		mmput(mm);
 	}
 
-	/* OK to pass negative loff_t, we can catch out-of-range */
-	file->f_mode |= FMODE_UNSIGNED_OFFSET;
 	file->private_data = mm;
 
 	return 0;
@@ -704,7 +702,12 @@ static int __mem_open(struct inode *inode, struct file *file, unsigned int mode)
 
 static int mem_open(struct inode *inode, struct file *file)
 {
-	return __mem_open(inode, file, PTRACE_MODE_ATTACH);
+	int ret = __mem_open(inode, file, PTRACE_MODE_ATTACH);
+
+	/* OK to pass negative loff_t, we can catch out-of-range */
+	file->f_mode |= FMODE_UNSIGNED_OFFSET;
+
+	return ret;
 }
 
 static ssize_t mem_rw(struct file *file, char __user *buf,
@@ -827,15 +830,16 @@ static ssize_t environ_read(struct file *file, char __user *buf,
 	if (!atomic_inc_not_zero(&mm->mm_users))
 		goto free;
 	while (count > 0) {
-		int this_len, retval, max_len;
-
-		this_len = mm->env_end - (mm->env_start + src);
+		size_t this_len, max_len;
+		int retval;
 
-		if (this_len <= 0)
+		if (src >= (mm->env_end - mm->env_start))
 			break;
 
-		max_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
-		this_len = (this_len > max_len) ? max_len : this_len;
+		this_len = mm->env_end - (mm->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),
 			page, this_len, 0);
diff --git a/fs/qnx4/bitmap.c b/fs/qnx4/bitmap.c
index 22e0d60e53ef..76a7a697b778 100644
--- a/fs/qnx4/bitmap.c
+++ b/fs/qnx4/bitmap.c
@@ -17,23 +17,6 @@
 #include <linux/bitops.h>
 #include "qnx4.h"
 
-static void count_bits(register const char *bmPart, register int size,
-		       int *const tf)
-{
-	char b;
-	int tot = *tf;
-
-	if (size > QNX4_BLOCK_SIZE) {
-		size = QNX4_BLOCK_SIZE;
-	}
-	do {
-		b = *bmPart++;
-		tot += 8 - hweight8(b);
-		size--;
-	} while (size != 0);
-	*tf = tot;
-}
-
 unsigned long qnx4_count_free_blocks(struct super_block *sb)
 {
 	int start = le32_to_cpu(qnx4_sb(sb)->BitMap->di_first_xtnt.xtnt_blk) - 1;
@@ -44,13 +27,16 @@ unsigned long qnx4_count_free_blocks(struct super_block *sb)
 	struct buffer_head *bh;
 
 	while (total < size) {
+		int bytes = min(size - total, QNX4_BLOCK_SIZE);
+
 		if ((bh = sb_bread(sb, start + offset)) == NULL) {
 			printk(KERN_ERR "qnx4: I/O error in counting free blocks\n");
 			break;
 		}
-		count_bits(bh->b_data, size - total, &total_free);
+		total_free += bytes * BITS_PER_BYTE -
+				memweight(bh->b_data, bytes);
 		brelse(bh);
-		total += QNX4_BLOCK_SIZE;
+		total += bytes;
 		offset++;
 	}
 
diff --git a/fs/splice.c b/fs/splice.c
index 7bf08fa22ec9..41514dd89462 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -996,6 +996,8 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 	};
 	ssize_t ret;
 
+	sb_start_write(inode->i_sb);
+
 	pipe_lock(pipe);
 
 	splice_from_pipe_begin(&sd);
@@ -1034,6 +1036,7 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 			*ppos += ret;
 		balance_dirty_pages_ratelimited_nr(mapping, nr_pages);
 	}
+	sb_end_write(inode->i_sb);
 
 	return ret;
 }
diff --git a/fs/super.c b/fs/super.c
index c743fb3be4b8..b05cf47463d0 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -33,12 +33,19 @@
 #include <linux/rculist_bl.h>
 #include <linux/cleancache.h>
 #include <linux/fsnotify.h>
+#include <linux/lockdep.h>
 #include "internal.h"
 
 
 LIST_HEAD(super_blocks);
 DEFINE_SPINLOCK(sb_lock);
 
+static char *sb_writers_name[SB_FREEZE_LEVELS] = {
+	"sb_writers",
+	"sb_pagefaults",
+	"sb_internal",
+};
+
 /*
  * One thing we have to be careful of with a per-sb shrinker is that we don't
  * drop the last active reference to the superblock from within the shrinker.
@@ -62,7 +69,7 @@ static int prune_super(struct shrinker *shrink, struct shrink_control *sc)
 		return -1;
 
 	if (!grab_super_passive(sb))
-		return !sc->nr_to_scan ? 0 : -1;
+		return -1;
 
 	if (sb->s_op && sb->s_op->nr_cached_objects)
 		fs_objects = sb->s_op->nr_cached_objects(sb);
@@ -102,6 +109,35 @@ static int prune_super(struct shrinker *shrink, struct shrink_control *sc)
 	return total_objects;
 }
 
+static int init_sb_writers(struct super_block *s, struct file_system_type *type)
+{
+	int err;
+	int i;
+
+	for (i = 0; i < SB_FREEZE_LEVELS; i++) {
+		err = percpu_counter_init(&s->s_writers.counter[i], 0);
+		if (err < 0)
+			goto err_out;
+		lockdep_init_map(&s->s_writers.lock_map[i], sb_writers_name[i],
+				 &type->s_writers_key[i], 0);
+	}
+	init_waitqueue_head(&s->s_writers.wait);
+	init_waitqueue_head(&s->s_writers.wait_unfrozen);
+	return 0;
+err_out:
+	while (--i >= 0)
+		percpu_counter_destroy(&s->s_writers.counter[i]);
+	return err;
+}
+
+static void destroy_sb_writers(struct super_block *s)
+{
+	int i;
+
+	for (i = 0; i < SB_FREEZE_LEVELS; i++)
+		percpu_counter_destroy(&s->s_writers.counter[i]);
+}
+
 /**
  *	alloc_super	-	create new superblock
  *	@type:	filesystem type superblock should belong to
@@ -117,18 +153,19 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 
 	if (s) {
 		if (security_sb_alloc(s)) {
+			/*
+			 * We cannot call security_sb_free() without
+			 * security_sb_alloc() succeeding. So bail out manually
+			 */
 			kfree(s);
 			s = NULL;
 			goto out;
 		}
 #ifdef CONFIG_SMP
 		s->s_files = alloc_percpu(struct list_head);
-		if (!s->s_files) {
-			security_sb_free(s);
-			kfree(s);
-			s = NULL;
-			goto out;
-		} else {
+		if (!s->s_files)
+			goto err_out;
+		else {
 			int i;
 
 			for_each_possible_cpu(i)
@@ -137,6 +174,8 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 #else
 		INIT_LIST_HEAD(&s->s_files);
 #endif
+		if (init_sb_writers(s, type))
+			goto err_out;
 		s->s_flags = flags;
 		s->s_bdi = &default_backing_dev_info;
 		INIT_HLIST_NODE(&s->s_instances);
@@ -178,7 +217,6 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 		mutex_init(&s->s_dquot.dqio_mutex);
 		mutex_init(&s->s_dquot.dqonoff_mutex);
 		init_rwsem(&s->s_dquot.dqptr_sem);
-		init_waitqueue_head(&s->s_wait_unfrozen);
 		s->s_maxbytes = MAX_NON_LFS;
 		s->s_op = &default_op;
 		s->s_time_gran = 1000000000;
@@ -190,6 +228,16 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 	}
 out:
 	return s;
+err_out:
+	security_sb_free(s);
+#ifdef CONFIG_SMP
+	if (s->s_files)
+		free_percpu(s->s_files);
+#endif
+	destroy_sb_writers(s);
+	kfree(s);
+	s = NULL;
+	goto out;
 }
 
 /**
@@ -203,6 +251,7 @@ static inline void destroy_super(struct super_block *s)
 #ifdef CONFIG_SMP
 	free_percpu(s->s_files);
 #endif
+	destroy_sb_writers(s);
 	security_sb_free(s);
 	WARN_ON(!list_empty(&s->s_mounts));
 	kfree(s->s_subtype);
@@ -320,7 +369,7 @@ static int grab_super(struct super_block *s) __releases(sb_lock)
 
 /*
  *	grab_super_passive - acquire a passive reference
- *	@s: reference we are trying to grab
+ *	@sb: reference we are trying to grab
  *
  *	Tries to acquire a passive reference. This is used in places where we
  *	cannot take an active reference but we need to ensure that the
@@ -651,10 +700,11 @@ struct super_block *get_super_thawed(struct block_device *bdev)
 {
 	while (1) {
 		struct super_block *s = get_super(bdev);
-		if (!s || s->s_frozen == SB_UNFROZEN)
+		if (!s || s->s_writers.frozen == SB_UNFROZEN)
 			return s;
 		up_read(&s->s_umount);
-		vfs_check_frozen(s, SB_FREEZE_WRITE);
+		wait_event(s->s_writers.wait_unfrozen,
+			   s->s_writers.frozen == SB_UNFROZEN);
 		put_super(s);
 	}
 }
@@ -732,7 +782,7 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
 	int retval;
 	int remount_ro;
 
-	if (sb->s_frozen != SB_UNFROZEN)
+	if (sb->s_writers.frozen != SB_UNFROZEN)
 		return -EBUSY;
 
 #ifdef CONFIG_BLOCK
@@ -1163,6 +1213,120 @@ out:
 	return ERR_PTR(error);
 }
 
+/*
+ * This is an internal function, please use sb_end_{write,pagefault,intwrite}
+ * instead.
+ */
+void __sb_end_write(struct super_block *sb, int level)
+{
+	percpu_counter_dec(&sb->s_writers.counter[level-1]);
+	/*
+	 * Make sure s_writers are updated before we wake up waiters in
+	 * freeze_super().
+	 */
+	smp_mb();
+	if (waitqueue_active(&sb->s_writers.wait))
+		wake_up(&sb->s_writers.wait);
+	rwsem_release(&sb->s_writers.lock_map[level-1], 1, _RET_IP_);
+}
+EXPORT_SYMBOL(__sb_end_write);
+
+#ifdef CONFIG_LOCKDEP
+/*
+ * We want lockdep to tell us about possible deadlocks with freezing but
+ * it's it bit tricky to properly instrument it. Getting a freeze protection
+ * works as getting a read lock but there are subtle problems. XFS for example
+ * gets freeze protection on internal level twice in some cases, which is OK
+ * only because we already hold a freeze protection also on higher level. Due
+ * to these cases we have to tell lockdep we are doing trylock when we
+ * already hold a freeze protection for a higher freeze level.
+ */
+static void acquire_freeze_lock(struct super_block *sb, int level, bool trylock,
+				unsigned long ip)
+{
+	int i;
+
+	if (!trylock) {
+		for (i = 0; i < level - 1; i++)
+			if (lock_is_held(&sb->s_writers.lock_map[i])) {
+				trylock = true;
+				break;
+			}
+	}
+	rwsem_acquire_read(&sb->s_writers.lock_map[level-1], 0, trylock, ip);
+}
+#endif
+
+/*
+ * This is an internal function, please use sb_start_{write,pagefault,intwrite}
+ * instead.
+ */
+int __sb_start_write(struct super_block *sb, int level, bool wait)
+{
+retry:
+	if (unlikely(sb->s_writers.frozen >= level)) {
+		if (!wait)
+			return 0;
+		wait_event(sb->s_writers.wait_unfrozen,
+			   sb->s_writers.frozen < level);
+	}
+
+#ifdef CONFIG_LOCKDEP
+	acquire_freeze_lock(sb, level, !wait, _RET_IP_);
+#endif
+	percpu_counter_inc(&sb->s_writers.counter[level-1]);
+	/*
+	 * Make sure counter is updated before we check for frozen.
+	 * freeze_super() first sets frozen and then checks the counter.
+	 */
+	smp_mb();
+	if (unlikely(sb->s_writers.frozen >= level)) {
+		__sb_end_write(sb, level);
+		goto retry;
+	}
+	return 1;
+}
+EXPORT_SYMBOL(__sb_start_write);
+
+/**
+ * sb_wait_write - wait until all writers to given file system finish
+ * @sb: the super for which we wait
+ * @level: type of writers we wait for (normal vs page fault)
+ *
+ * This function waits until there are no writers of given type to given file
+ * system. Caller of this function should make sure there can be no new writers
+ * of type @level before calling this function. Otherwise this function can
+ * livelock.
+ */
+static void sb_wait_write(struct super_block *sb, int level)
+{
+	s64 writers;
+
+	/*
+	 * We just cycle-through lockdep here so that it does not complain
+	 * about returning with lock to userspace
+	 */
+	rwsem_acquire(&sb->s_writers.lock_map[level-1], 0, 0, _THIS_IP_);
+	rwsem_release(&sb->s_writers.lock_map[level-1], 1, _THIS_IP_);
+
+	do {
+		DEFINE_WAIT(wait);
+
+		/*
+		 * We use a barrier in prepare_to_wait() to separate setting
+		 * of frozen and checking of the counter
+		 */
+		prepare_to_wait(&sb->s_writers.wait, &wait,
+				TASK_UNINTERRUPTIBLE);
+
+		writers = percpu_counter_sum(&sb->s_writers.counter[level-1]);
+		if (writers)
+			schedule();
+
+		finish_wait(&sb->s_writers.wait, &wait);
+	} while (writers);
+}
+
 /**
  * freeze_super - lock the filesystem and force it into a consistent state
  * @sb: the super to lock
@@ -1170,6 +1334,31 @@ out:
  * Syncs the super to make sure the filesystem is consistent and calls the fs's
  * freeze_fs.  Subsequent calls to this without first thawing the fs will return
  * -EBUSY.
+ *
+ * During this function, sb->s_writers.frozen goes through these values:
+ *
+ * SB_UNFROZEN: File system is normal, all writes progress as usual.
+ *
+ * SB_FREEZE_WRITE: The file system is in the process of being frozen.  New
+ * writes should be blocked, though page faults are still allowed. We wait for
+ * all writes to complete and then proceed to the next stage.
+ *
+ * SB_FREEZE_PAGEFAULT: Freezing continues. Now also page faults are blocked
+ * but internal fs threads can still modify the filesystem (although they
+ * should not dirty new pages or inodes), writeback can run etc. After waiting
+ * for all running page faults we sync the filesystem which will clean all
+ * dirty pages and inodes (no new dirty pages or inodes can be created when
+ * sync is running).
+ *
+ * SB_FREEZE_FS: The file system is frozen. Now all internal sources of fs
+ * modification are blocked (e.g. XFS preallocation truncation on inode
+ * reclaim). This is usually implemented by blocking new transactions for
+ * filesystems that have them and need this additional guard. After all
+ * internal writers are finished we call ->freeze_fs() to finish filesystem
+ * freezing. Then we transition to SB_FREEZE_COMPLETE state. This state is
+ * mostly auxiliary for filesystems to verify they do not modify frozen fs.
+ *
+ * sb->s_writers.frozen is protected by sb->s_umount.
  */
 int freeze_super(struct super_block *sb)
 {
@@ -1177,7 +1366,7 @@ int freeze_super(struct super_block *sb)
 
 	atomic_inc(&sb->s_active);
 	down_write(&sb->s_umount);
-	if (sb->s_frozen) {
+	if (sb->s_writers.frozen != SB_UNFROZEN) {
 		deactivate_locked_super(sb);
 		return -EBUSY;
 	}
@@ -1188,33 +1377,53 @@ int freeze_super(struct super_block *sb)
 	}
 
 	if (sb->s_flags & MS_RDONLY) {
-		sb->s_frozen = SB_FREEZE_TRANS;
-		smp_wmb();
+		/* Nothing to do really... */
+		sb->s_writers.frozen = SB_FREEZE_COMPLETE;
 		up_write(&sb->s_umount);
 		return 0;
 	}
 
-	sb->s_frozen = SB_FREEZE_WRITE;
+	/* From now on, no new normal writers can start */
+	sb->s_writers.frozen = SB_FREEZE_WRITE;
+	smp_wmb();
+
+	/* Release s_umount to preserve sb_start_write -> s_umount ordering */
+	up_write(&sb->s_umount);
+
+	sb_wait_write(sb, SB_FREEZE_WRITE);
+
+	/* Now we go and block page faults... */
+	down_write(&sb->s_umount);
+	sb->s_writers.frozen = SB_FREEZE_PAGEFAULT;
 	smp_wmb();
 
+	sb_wait_write(sb, SB_FREEZE_PAGEFAULT);
+
+	/* All writers are done so after syncing there won't be dirty data */
 	sync_filesystem(sb);
 
-	sb->s_frozen = SB_FREEZE_TRANS;
+	/* Now wait for internal filesystem counter */
+	sb->s_writers.frozen = SB_FREEZE_FS;
 	smp_wmb();
+	sb_wait_write(sb, SB_FREEZE_FS);
 
-	sync_blockdev(sb->s_bdev);
 	if (sb->s_op->freeze_fs) {
 		ret = sb->s_op->freeze_fs(sb);
 		if (ret) {
 			printk(KERN_ERR
 				"VFS:Filesystem freeze failed\n");
-			sb->s_frozen = SB_UNFROZEN;
+			sb->s_writers.frozen = SB_UNFROZEN;
 			smp_wmb();
-			wake_up(&sb->s_wait_unfrozen);
+			wake_up(&sb->s_writers.wait_unfrozen);
 			deactivate_locked_super(sb);
 			return ret;
 		}
 	}
+	/*
+	 * This is just for debugging purposes so that fs can warn if it
+	 * sees write activity when frozen is set to SB_FREEZE_COMPLETE.
+	 */
+	sb->s_writers.frozen = SB_FREEZE_COMPLETE;
 	up_write(&sb->s_umount);
 	return 0;
 }
@@ -1231,7 +1440,7 @@ int thaw_super(struct super_block *sb)
 	int error;
 
 	down_write(&sb->s_umount);
-	if (sb->s_frozen == SB_UNFROZEN) {
+	if (sb->s_writers.frozen == SB_UNFROZEN) {
 		up_write(&sb->s_umount);
 		return -EINVAL;
 	}
@@ -1244,16 +1453,15 @@ int thaw_super(struct super_block *sb)
 		if (error) {
 			printk(KERN_ERR
 				"VFS:Filesystem thaw failed\n");
-			sb->s_frozen = SB_FREEZE_TRANS;
 			up_write(&sb->s_umount);
 			return error;
 		}
 	}
 
 out:
-	sb->s_frozen = SB_UNFROZEN;
+	sb->s_writers.frozen = SB_UNFROZEN;
 	smp_wmb();
-	wake_up(&sb->s_wait_unfrozen);
+	wake_up(&sb->s_writers.wait_unfrozen);
 	deactivate_locked_super(sb);
 
 	return 0;
diff --git a/fs/sysfs/bin.c b/fs/sysfs/bin.c
index a4759833d62d..614b2b544880 100644
--- a/fs/sysfs/bin.c
+++ b/fs/sysfs/bin.c
@@ -228,6 +228,8 @@ static int bin_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	ret = 0;
 	if (bb->vm_ops->page_mkwrite)
 		ret = bb->vm_ops->page_mkwrite(vma, vmf);
+	else
+		file_update_time(file);
 
 	sysfs_put_active(attr_sd);
 	return ret;
diff --git a/fs/xattr.c b/fs/xattr.c
index 1d7ac3790458..4d45b7189e7e 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -427,6 +427,7 @@ 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));
@@ -438,9 +439,13 @@ getxattr(struct dentry *d, const char __user *name, void __user *value,
 	if (size) {
 		if (size > XATTR_SIZE_MAX)
 			size = XATTR_SIZE_MAX;
-		kvalue = kzalloc(size, GFP_KERNEL);
-		if (!kvalue)
-			return -ENOMEM;
+		kvalue = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
+		if (!kvalue) {
+			vvalue = vmalloc(size);
+			if (!vvalue)
+				return -ENOMEM;
+			kvalue = vvalue;
+		}
 	}
 
 	error = vfs_getxattr(d, kname, kvalue, size);
@@ -452,7 +457,10 @@ getxattr(struct dentry *d, const char __user *name, void __user *value,
 		   than XATTR_SIZE_MAX bytes. Not possible. */
 		error = -E2BIG;
 	}
-	kfree(kvalue);
+	if (vvalue)
+		vfree(vvalue);
+	else
+		kfree(kvalue);
 	return error;
 }
 
diff --git a/fs/xfs/xfs_alloc_btree.h b/fs/xfs/xfs_alloc_btree.h
index a6caa0022c9b..359fb86ed876 100644
--- a/fs/xfs/xfs_alloc_btree.h
+++ b/fs/xfs/xfs_alloc_btree.h
@@ -51,20 +51,6 @@ typedef struct xfs_alloc_rec_incore {
 typedef __be32 xfs_alloc_ptr_t;
 
 /*
- * Minimum and maximum blocksize and sectorsize.
- * The blocksize upper limit is pretty much arbitrary.
- * The sectorsize upper limit is due to sizeof(sb_sectsize).
- */
-#define XFS_MIN_BLOCKSIZE_LOG	9	/* i.e. 512 bytes */
-#define XFS_MAX_BLOCKSIZE_LOG	16	/* i.e. 65536 bytes */
-#define XFS_MIN_BLOCKSIZE	(1 << XFS_MIN_BLOCKSIZE_LOG)
-#define XFS_MAX_BLOCKSIZE	(1 << XFS_MAX_BLOCKSIZE_LOG)
-#define XFS_MIN_SECTORSIZE_LOG	9	/* i.e. 512 bytes */
-#define XFS_MAX_SECTORSIZE_LOG	15	/* i.e. 32768 bytes */
-#define XFS_MIN_SECTORSIZE	(1 << XFS_MIN_SECTORSIZE_LOG)
-#define XFS_MAX_SECTORSIZE	(1 << XFS_MAX_SECTORSIZE_LOG)
-
-/*
  * Block numbers in the AG:
  * SB is sector 0, AGF is sector 1, AGI is sector 2, AGFL is sector 3.
  */
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 8dad722c0041..e562dd43f41f 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -124,6 +124,12 @@ xfs_setfilesize_trans_alloc(
 	ioend->io_append_trans = tp;
 
 	/*
+	 * We will pass freeze protection with a transaction.  So tell lockdep
+	 * we released it.
+	 */
+	rwsem_release(&ioend->io_inode->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
+		      1, _THIS_IP_);
+	/*
 	 * We hand off the transaction to the completion thread now, so
 	 * clear the flag here.
 	 */
@@ -179,7 +185,7 @@ xfs_finish_ioend(
 	if (atomic_dec_and_test(&ioend->io_remaining)) {
 		struct xfs_mount	*mp = XFS_I(ioend->io_inode)->i_mount;
 
-		if (ioend->io_type == IO_UNWRITTEN)
+		if (ioend->io_type == XFS_IO_UNWRITTEN)
 			queue_work(mp->m_unwritten_workqueue, &ioend->io_work);
 		else if (ioend->io_append_trans)
 			queue_work(mp->m_data_workqueue, &ioend->io_work);
@@ -199,6 +205,15 @@ xfs_end_io(
 	struct xfs_inode *ip = XFS_I(ioend->io_inode);
 	int		error = 0;
 
+	if (ioend->io_append_trans) {
+		/*
+		 * We've got freeze protection passed with the transaction.
+		 * Tell lockdep about it.
+		 */
+		rwsem_acquire_read(
+			&ioend->io_inode->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
+			0, 1, _THIS_IP_);
+	}
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
 		ioend->io_error = -EIO;
 		goto done;
@@ -210,7 +225,7 @@ xfs_end_io(
 	 * For unwritten extents we need to issue transactions to convert a
 	 * range to normal written extens after the data I/O has finished.
 	 */
-	if (ioend->io_type == IO_UNWRITTEN) {
+	if (ioend->io_type == XFS_IO_UNWRITTEN) {
 		/*
 		 * For buffered I/O we never preallocate a transaction when
 		 * doing the unwritten extent conversion, but for direct I/O
@@ -312,7 +327,7 @@ xfs_map_blocks(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -XFS_ERROR(EIO);
 
-	if (type == IO_UNWRITTEN)
+	if (type == XFS_IO_UNWRITTEN)
 		bmapi_flags |= XFS_BMAPI_IGSTATE;
 
 	if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) {
@@ -323,10 +338,10 @@ xfs_map_blocks(
 
 	ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
 	       (ip->i_df.if_flags & XFS_IFEXTENTS));
-	ASSERT(offset <= mp->m_maxioffset);
+	ASSERT(offset <= mp->m_super->s_maxbytes);
 
-	if (offset + count > mp->m_maxioffset)
-		count = mp->m_maxioffset - offset;
+	if (offset + count > mp->m_super->s_maxbytes)
+		count = mp->m_super->s_maxbytes - offset;
 	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
 	offset_fsb = XFS_B_TO_FSBT(mp, offset);
 	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
@@ -336,7 +351,7 @@ xfs_map_blocks(
 	if (error)
 		return -XFS_ERROR(error);
 
-	if (type == IO_DELALLOC &&
+	if (type == XFS_IO_DELALLOC &&
 	    (!nimaps || isnullstartblock(imap->br_startblock))) {
 		error = xfs_iomap_write_allocate(ip, offset, count, imap);
 		if (!error)
@@ -345,7 +360,7 @@ xfs_map_blocks(
 	}
 
 #ifdef DEBUG
-	if (type == IO_UNWRITTEN) {
+	if (type == XFS_IO_UNWRITTEN) {
 		ASSERT(nimaps);
 		ASSERT(imap->br_startblock != HOLESTARTBLOCK);
 		ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
@@ -634,11 +649,11 @@ xfs_check_page_type(
 		bh = head = page_buffers(page);
 		do {
 			if (buffer_unwritten(bh))
-				acceptable += (type == IO_UNWRITTEN);
+				acceptable += (type == XFS_IO_UNWRITTEN);
 			else if (buffer_delay(bh))
-				acceptable += (type == IO_DELALLOC);
+				acceptable += (type == XFS_IO_DELALLOC);
 			else if (buffer_dirty(bh) && buffer_mapped(bh))
-				acceptable += (type == IO_OVERWRITE);
+				acceptable += (type == XFS_IO_OVERWRITE);
 			else
 				break;
 		} while ((bh = bh->b_this_page) != head);
@@ -721,11 +736,11 @@ xfs_convert_page(
 		if (buffer_unwritten(bh) || buffer_delay(bh) ||
 		    buffer_mapped(bh)) {
 			if (buffer_unwritten(bh))
-				type = IO_UNWRITTEN;
+				type = XFS_IO_UNWRITTEN;
 			else if (buffer_delay(bh))
-				type = IO_DELALLOC;
+				type = XFS_IO_DELALLOC;
 			else
-				type = IO_OVERWRITE;
+				type = XFS_IO_OVERWRITE;
 
 			if (!xfs_imap_valid(inode, imap, offset)) {
 				done = 1;
@@ -733,7 +748,7 @@ xfs_convert_page(
 			}
 
 			lock_buffer(bh);
-			if (type != IO_OVERWRITE)
+			if (type != XFS_IO_OVERWRITE)
 				xfs_map_at_offset(inode, bh, imap, offset);
 			xfs_add_to_ioend(inode, bh, offset, type,
 					 ioendp, done);
@@ -831,7 +846,7 @@ xfs_aops_discard_page(
 	struct buffer_head	*bh, *head;
 	loff_t			offset = page_offset(page);
 
-	if (!xfs_check_page_type(page, IO_DELALLOC))
+	if (!xfs_check_page_type(page, XFS_IO_DELALLOC))
 		goto out_invalidate;
 
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
@@ -927,11 +942,26 @@ xfs_vm_writepage(
 	end_index = offset >> PAGE_CACHE_SHIFT;
 	last_index = (offset - 1) >> PAGE_CACHE_SHIFT;
 	if (page->index >= end_index) {
-		if ((page->index >= end_index + 1) ||
-		    !(i_size_read(inode) & (PAGE_CACHE_SIZE - 1))) {
+		unsigned offset_into_page = offset & (PAGE_CACHE_SIZE - 1);
+
+		/*
+		 * Just skip the page if it is fully outside i_size, e.g. due
+		 * to a truncate operation that is in progress.
+		 */
+		if (page->index >= end_index + 1 || offset_into_page == 0) {
 			unlock_page(page);
 			return 0;
 		}
+
+		/*
+		 * The page straddles i_size.  It must be zeroed out on each
+		 * and every writepage invocation because it may be mmapped.
+		 * "A file is mapped in multiples of the page size.  For a file
+		 * that is not a multiple of 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_into_page, PAGE_CACHE_SIZE);
 	}
 
 	end_offset = min_t(unsigned long long,
@@ -941,7 +971,7 @@ xfs_vm_writepage(
 
 	bh = head = page_buffers(page);
 	offset = page_offset(page);
-	type = IO_OVERWRITE;
+	type = XFS_IO_OVERWRITE;
 
 	if (wbc->sync_mode == WB_SYNC_NONE)
 		nonblocking = 1;
@@ -966,18 +996,18 @@ xfs_vm_writepage(
 		}
 
 		if (buffer_unwritten(bh)) {
-			if (type != IO_UNWRITTEN) {
-				type = IO_UNWRITTEN;
+			if (type != XFS_IO_UNWRITTEN) {
+				type = XFS_IO_UNWRITTEN;
 				imap_valid = 0;
 			}
 		} else if (buffer_delay(bh)) {
-			if (type != IO_DELALLOC) {
-				type = IO_DELALLOC;
+			if (type != XFS_IO_DELALLOC) {
+				type = XFS_IO_DELALLOC;
 				imap_valid = 0;
 			}
 		} else if (buffer_uptodate(bh)) {
-			if (type != IO_OVERWRITE) {
-				type = IO_OVERWRITE;
+			if (type != XFS_IO_OVERWRITE) {
+				type = XFS_IO_OVERWRITE;
 				imap_valid = 0;
 			}
 		} else {
@@ -1013,7 +1043,7 @@ xfs_vm_writepage(
 		}
 		if (imap_valid) {
 			lock_buffer(bh);
-			if (type != IO_OVERWRITE)
+			if (type != XFS_IO_OVERWRITE)
 				xfs_map_at_offset(inode, bh, &imap, offset);
 			xfs_add_to_ioend(inode, bh, offset, type, &ioend,
 					 new_ioend);
@@ -1054,7 +1084,7 @@ xfs_vm_writepage(
 		 * Reserve log space if we might write beyond the on-disk
 		 * inode size.
 		 */
-		if (ioend->io_type != IO_UNWRITTEN &&
+		if (ioend->io_type != XFS_IO_UNWRITTEN &&
 		    xfs_ioend_is_append(ioend)) {
 			err = xfs_setfilesize_trans_alloc(ioend);
 			if (err)
@@ -1162,9 +1192,9 @@ __xfs_get_blocks(
 		lockmode = xfs_ilock_map_shared(ip);
 	}
 
-	ASSERT(offset <= mp->m_maxioffset);
-	if (offset + size > mp->m_maxioffset)
-		size = mp->m_maxioffset - offset;
+	ASSERT(offset <= mp->m_super->s_maxbytes);
+	if (offset + size > mp->m_super->s_maxbytes)
+		size = mp->m_super->s_maxbytes - offset;
 	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + size);
 	offset_fsb = XFS_B_TO_FSBT(mp, offset);
 
@@ -1351,7 +1381,7 @@ xfs_end_io_direct_write(
 	ioend->io_iocb = iocb;
 	ioend->io_result = ret;
 	if (private && size > 0)
-		ioend->io_type = IO_UNWRITTEN;
+		ioend->io_type = XFS_IO_UNWRITTEN;
 
 	if (is_async) {
 		ioend->io_isasync = 1;
@@ -1383,7 +1413,7 @@ xfs_vm_direct_IO(
 		 * and converts at least on unwritten extent we will cancel
 		 * the still clean transaction after the I/O has finished.
 		 */
-		iocb->private = ioend = xfs_alloc_ioend(inode, IO_DIRECT);
+		iocb->private = ioend = xfs_alloc_ioend(inode, XFS_IO_DIRECT);
 		if (offset + size > XFS_I(inode)->i_d.di_size) {
 			ret = xfs_setfilesize_trans_alloc(ioend);
 			if (ret)
@@ -1410,6 +1440,9 @@ out_trans_cancel:
 	if (ioend->io_append_trans) {
 		current_set_flags_nested(&ioend->io_append_trans->t_pflags,
 					 PF_FSTRANS);
+		rwsem_acquire_read(
+			&inode->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
+			0, 1, _THIS_IP_);
 		xfs_trans_cancel(ioend->io_append_trans, 0);
 	}
 out_destroy_ioend:
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index 84eafbcb0d9d..c325abb8d61a 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -24,17 +24,17 @@ extern mempool_t *xfs_ioend_pool;
  * Types of I/O for bmap clustering and I/O completion tracking.
  */
 enum {
-	IO_DIRECT = 0,	/* special case for direct I/O ioends */
-	IO_DELALLOC,	/* mapping covers delalloc region */
-	IO_UNWRITTEN,	/* mapping covers allocated but uninitialized data */
-	IO_OVERWRITE,	/* mapping covers already allocated extent */
+	XFS_IO_DIRECT = 0,	/* special case for direct I/O ioends */
+	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 \
 	{ 0,			"" }, \
-	{ IO_DELALLOC,		"delalloc" }, \
-	{ IO_UNWRITTEN,		"unwritten" }, \
-	{ IO_OVERWRITE,		"overwrite" }
+	{ XFS_IO_DELALLOC,		"delalloc" }, \
+	{ XFS_IO_UNWRITTEN,		"unwritten" }, \
+	{ XFS_IO_OVERWRITE,		"overwrite" }
 
 /*
  * xfs_ioend struct manages large extent writes for XFS.
diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c
index a17ff01b5adf..0ca1f0be62d2 100644
--- a/fs/xfs/xfs_attr.c
+++ b/fs/xfs/xfs_attr.c
@@ -893,7 +893,7 @@ STATIC int
 xfs_attr_leaf_addname(xfs_da_args_t *args)
 {
 	xfs_inode_t *dp;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int retval, error, committed, forkoff;
 
 	trace_xfs_attr_leaf_addname(args);
@@ -915,11 +915,11 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 	 */
 	retval = xfs_attr_leaf_lookup_int(bp, args);
 	if ((args->flags & ATTR_REPLACE) && (retval == ENOATTR)) {
-		xfs_da_brelse(args->trans, bp);
+		xfs_trans_brelse(args->trans, bp);
 		return(retval);
 	} else if (retval == EEXIST) {
 		if (args->flags & ATTR_CREATE) {	/* pure create op */
-			xfs_da_brelse(args->trans, bp);
+			xfs_trans_brelse(args->trans, bp);
 			return(retval);
 		}
 
@@ -937,7 +937,6 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 	 * if required.
 	 */
 	retval = xfs_attr_leaf_add(bp, args);
-	xfs_da_buf_done(bp);
 	if (retval == ENOSPC) {
 		/*
 		 * Promote the attribute list to the Btree format, then
@@ -1065,8 +1064,7 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 			 */
 			if (committed)
 				xfs_trans_ijoin(args->trans, dp, 0);
-		} else
-			xfs_da_buf_done(bp);
+		}
 
 		/*
 		 * Commit the remove and start the next trans in series.
@@ -1092,7 +1090,7 @@ STATIC int
 xfs_attr_leaf_removename(xfs_da_args_t *args)
 {
 	xfs_inode_t *dp;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error, committed, forkoff;
 
 	trace_xfs_attr_leaf_removename(args);
@@ -1111,7 +1109,7 @@ xfs_attr_leaf_removename(xfs_da_args_t *args)
 	ASSERT(bp != NULL);
 	error = xfs_attr_leaf_lookup_int(bp, args);
 	if (error == ENOATTR) {
-		xfs_da_brelse(args->trans, bp);
+		xfs_trans_brelse(args->trans, bp);
 		return(error);
 	}
 
@@ -1141,8 +1139,7 @@ xfs_attr_leaf_removename(xfs_da_args_t *args)
 		 */
 		if (committed)
 			xfs_trans_ijoin(args->trans, dp, 0);
-	} else
-		xfs_da_buf_done(bp);
+	}
 	return(0);
 }
 
@@ -1155,7 +1152,7 @@ xfs_attr_leaf_removename(xfs_da_args_t *args)
 STATIC int
 xfs_attr_leaf_get(xfs_da_args_t *args)
 {
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error;
 
 	args->blkno = 0;
@@ -1167,11 +1164,11 @@ xfs_attr_leaf_get(xfs_da_args_t *args)
 
 	error = xfs_attr_leaf_lookup_int(bp, args);
 	if (error != EEXIST)  {
-		xfs_da_brelse(args->trans, bp);
+		xfs_trans_brelse(args->trans, bp);
 		return(error);
 	}
 	error = xfs_attr_leaf_getvalue(bp, args);
-	xfs_da_brelse(args->trans, bp);
+	xfs_trans_brelse(args->trans, bp);
 	if (!error && (args->rmtblkno > 0) && !(args->flags & ATTR_KERNOVAL)) {
 		error = xfs_attr_rmtval_get(args);
 	}
@@ -1186,23 +1183,23 @@ xfs_attr_leaf_list(xfs_attr_list_context_t *context)
 {
 	xfs_attr_leafblock_t *leaf;
 	int error;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 
 	context->cursor->blkno = 0;
 	error = xfs_da_read_buf(NULL, context->dp, 0, -1, &bp, XFS_ATTR_FORK);
 	if (error)
 		return XFS_ERROR(error);
 	ASSERT(bp != NULL);
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	if (unlikely(leaf->hdr.info.magic != cpu_to_be16(XFS_ATTR_LEAF_MAGIC))) {
 		XFS_CORRUPTION_ERROR("xfs_attr_leaf_list", XFS_ERRLEVEL_LOW,
 				     context->dp->i_mount, leaf);
-		xfs_da_brelse(NULL, bp);
+		xfs_trans_brelse(NULL, bp);
 		return XFS_ERROR(EFSCORRUPTED);
 	}
 
 	error = xfs_attr_leaf_list_int(bp, context);
-	xfs_da_brelse(NULL, bp);
+	xfs_trans_brelse(NULL, bp);
 	return XFS_ERROR(error);
 }
 
@@ -1489,7 +1486,7 @@ xfs_attr_node_removename(xfs_da_args_t *args)
 	xfs_da_state_t *state;
 	xfs_da_state_blk_t *blk;
 	xfs_inode_t *dp;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int retval, error, committed, forkoff;
 
 	trace_xfs_attr_node_removename(args);
@@ -1601,14 +1598,13 @@ xfs_attr_node_removename(xfs_da_args_t *args)
 		 */
 		ASSERT(state->path.active == 1);
 		ASSERT(state->path.blk[0].bp);
-		xfs_da_buf_done(state->path.blk[0].bp);
 		state->path.blk[0].bp = NULL;
 
 		error = xfs_da_read_buf(args->trans, args->dp, 0, -1, &bp,
 						     XFS_ATTR_FORK);
 		if (error)
 			goto out;
-		ASSERT((((xfs_attr_leafblock_t *)bp->data)->hdr.info.magic) ==
+		ASSERT((((xfs_attr_leafblock_t *)bp->b_addr)->hdr.info.magic) ==
 		       cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 
 		if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
@@ -1635,7 +1631,7 @@ xfs_attr_node_removename(xfs_da_args_t *args)
 			if (committed)
 				xfs_trans_ijoin(args->trans, dp, 0);
 		} else
-			xfs_da_brelse(args->trans, bp);
+			xfs_trans_brelse(args->trans, bp);
 	}
 	error = 0;
 
@@ -1665,8 +1661,7 @@ xfs_attr_fillstate(xfs_da_state_t *state)
 	ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH));
 	for (blk = path->blk, level = 0; level < path->active; blk++, level++) {
 		if (blk->bp) {
-			blk->disk_blkno = xfs_da_blkno(blk->bp);
-			xfs_da_buf_done(blk->bp);
+			blk->disk_blkno = XFS_BUF_ADDR(blk->bp);
 			blk->bp = NULL;
 		} else {
 			blk->disk_blkno = 0;
@@ -1681,8 +1676,7 @@ xfs_attr_fillstate(xfs_da_state_t *state)
 	ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH));
 	for (blk = path->blk, level = 0; level < path->active; blk++, level++) {
 		if (blk->bp) {
-			blk->disk_blkno = xfs_da_blkno(blk->bp);
-			xfs_da_buf_done(blk->bp);
+			blk->disk_blkno = XFS_BUF_ADDR(blk->bp);
 			blk->bp = NULL;
 		} else {
 			blk->disk_blkno = 0;
@@ -1792,7 +1786,7 @@ xfs_attr_node_get(xfs_da_args_t *args)
 	 * If not in a transaction, we have to release all the buffers.
 	 */
 	for (i = 0; i < state->path.active; i++) {
-		xfs_da_brelse(args->trans, state->path.blk[i].bp);
+		xfs_trans_brelse(args->trans, state->path.blk[i].bp);
 		state->path.blk[i].bp = NULL;
 	}
 
@@ -1808,7 +1802,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 	xfs_da_intnode_t *node;
 	xfs_da_node_entry_t *btree;
 	int error, i;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 
 	cursor = context->cursor;
 	cursor->initted = 1;
@@ -1825,30 +1819,30 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 		if ((error != 0) && (error != EFSCORRUPTED))
 			return(error);
 		if (bp) {
-			node = bp->data;
+			node = bp->b_addr;
 			switch (be16_to_cpu(node->hdr.info.magic)) {
 			case XFS_DA_NODE_MAGIC:
 				trace_xfs_attr_list_wrong_blk(context);
-				xfs_da_brelse(NULL, bp);
+				xfs_trans_brelse(NULL, bp);
 				bp = NULL;
 				break;
 			case XFS_ATTR_LEAF_MAGIC:
-				leaf = bp->data;
+				leaf = bp->b_addr;
 				if (cursor->hashval > be32_to_cpu(leaf->entries[
 				    be16_to_cpu(leaf->hdr.count)-1].hashval)) {
 					trace_xfs_attr_list_wrong_blk(context);
-					xfs_da_brelse(NULL, bp);
+					xfs_trans_brelse(NULL, bp);
 					bp = NULL;
 				} else if (cursor->hashval <=
 					     be32_to_cpu(leaf->entries[0].hashval)) {
 					trace_xfs_attr_list_wrong_blk(context);
-					xfs_da_brelse(NULL, bp);
+					xfs_trans_brelse(NULL, bp);
 					bp = NULL;
 				}
 				break;
 			default:
 				trace_xfs_attr_list_wrong_blk(context);
-				xfs_da_brelse(NULL, bp);
+				xfs_trans_brelse(NULL, bp);
 				bp = NULL;
 			}
 		}
@@ -1873,7 +1867,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 						 context->dp->i_mount);
 				return(XFS_ERROR(EFSCORRUPTED));
 			}
-			node = bp->data;
+			node = bp->b_addr;
 			if (node->hdr.info.magic ==
 			    cpu_to_be16(XFS_ATTR_LEAF_MAGIC))
 				break;
@@ -1883,7 +1877,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 						     XFS_ERRLEVEL_LOW,
 						     context->dp->i_mount,
 						     node);
-				xfs_da_brelse(NULL, bp);
+				xfs_trans_brelse(NULL, bp);
 				return(XFS_ERROR(EFSCORRUPTED));
 			}
 			btree = node->btree;
@@ -1898,10 +1892,10 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 				}
 			}
 			if (i == be16_to_cpu(node->hdr.count)) {
-				xfs_da_brelse(NULL, bp);
+				xfs_trans_brelse(NULL, bp);
 				return(0);
 			}
-			xfs_da_brelse(NULL, bp);
+			xfs_trans_brelse(NULL, bp);
 		}
 	}
 	ASSERT(bp != NULL);
@@ -1912,24 +1906,24 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 	 * adding the information.
 	 */
 	for (;;) {
-		leaf = bp->data;
+		leaf = bp->b_addr;
 		if (unlikely(leaf->hdr.info.magic !=
 			     cpu_to_be16(XFS_ATTR_LEAF_MAGIC))) {
 			XFS_CORRUPTION_ERROR("xfs_attr_node_list(4)",
 					     XFS_ERRLEVEL_LOW,
 					     context->dp->i_mount, leaf);
-			xfs_da_brelse(NULL, bp);
+			xfs_trans_brelse(NULL, bp);
 			return(XFS_ERROR(EFSCORRUPTED));
 		}
 		error = xfs_attr_leaf_list_int(bp, context);
 		if (error) {
-			xfs_da_brelse(NULL, bp);
+			xfs_trans_brelse(NULL, bp);
 			return error;
 		}
 		if (context->seen_enough || leaf->hdr.info.forw == 0)
 			break;
 		cursor->blkno = be32_to_cpu(leaf->hdr.info.forw);
-		xfs_da_brelse(NULL, bp);
+		xfs_trans_brelse(NULL, bp);
 		error = xfs_da_read_buf(NULL, context->dp, cursor->blkno, -1,
 					      &bp, XFS_ATTR_FORK);
 		if (error)
@@ -1941,7 +1935,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 			return(XFS_ERROR(EFSCORRUPTED));
 		}
 	}
-	xfs_da_brelse(NULL, bp);
+	xfs_trans_brelse(NULL, bp);
 	return(0);
 }
 
diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c
index 7d89d800f517..d330111ca738 100644
--- a/fs/xfs/xfs_attr_leaf.c
+++ b/fs/xfs/xfs_attr_leaf.c
@@ -54,10 +54,10 @@
  * Routines used for growing the Btree.
  */
 STATIC int xfs_attr_leaf_create(xfs_da_args_t *args, xfs_dablk_t which_block,
-				    xfs_dabuf_t **bpp);
-STATIC int xfs_attr_leaf_add_work(xfs_dabuf_t *leaf_buffer, xfs_da_args_t *args,
-					      int freemap_index);
-STATIC void xfs_attr_leaf_compact(xfs_trans_t *trans, xfs_dabuf_t *leaf_buffer);
+				struct xfs_buf **bpp);
+STATIC int xfs_attr_leaf_add_work(struct xfs_buf *leaf_buffer,
+				  xfs_da_args_t *args, int freemap_index);
+STATIC void xfs_attr_leaf_compact(xfs_trans_t *tp, struct xfs_buf *leaf_buffer);
 STATIC void xfs_attr_leaf_rebalance(xfs_da_state_t *state,
 						   xfs_da_state_blk_t *blk1,
 						   xfs_da_state_blk_t *blk2);
@@ -71,9 +71,9 @@ STATIC int xfs_attr_leaf_figure_balance(xfs_da_state_t *state,
  * Routines used for shrinking the Btree.
  */
 STATIC int xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp,
-				  xfs_dabuf_t *bp, int level);
+				  struct xfs_buf *bp, int level);
 STATIC int xfs_attr_leaf_inactive(xfs_trans_t **trans, xfs_inode_t *dp,
-				  xfs_dabuf_t *bp);
+				  struct xfs_buf *bp);
 STATIC int xfs_attr_leaf_freextent(xfs_trans_t **trans, xfs_inode_t *dp,
 				   xfs_dablk_t blkno, int blkcnt);
 
@@ -480,7 +480,7 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args)
 	char *tmpbuffer;
 	int error, i, size;
 	xfs_dablk_t blkno;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	xfs_ifork_t *ifp;
 
 	trace_xfs_attr_sf_to_leaf(args);
@@ -550,8 +550,6 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args)
 	error = 0;
 
 out:
-	if(bp)
-		xfs_da_buf_done(bp);
 	kmem_free(tmpbuffer);
 	return(error);
 }
@@ -737,14 +735,16 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context)
  * a shortform attribute list.
  */
 int
-xfs_attr_shortform_allfit(xfs_dabuf_t *bp, xfs_inode_t *dp)
+xfs_attr_shortform_allfit(
+	struct xfs_buf	*bp,
+	struct xfs_inode *dp)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_entry_t *entry;
 	xfs_attr_leaf_name_local_t *name_loc;
 	int bytes, i;
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 
 	entry = &leaf->entries[0];
@@ -774,7 +774,10 @@ xfs_attr_shortform_allfit(xfs_dabuf_t *bp, xfs_inode_t *dp)
  * Convert a leaf attribute list to shortform attribute list
  */
 int
-xfs_attr_leaf_to_shortform(xfs_dabuf_t *bp, xfs_da_args_t *args, int forkoff)
+xfs_attr_leaf_to_shortform(
+	struct xfs_buf	*bp,
+	xfs_da_args_t	*args,
+	int		forkoff)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_entry_t *entry;
@@ -791,10 +794,10 @@ xfs_attr_leaf_to_shortform(xfs_dabuf_t *bp, xfs_da_args_t *args, int forkoff)
 	ASSERT(tmpbuffer != NULL);
 
 	ASSERT(bp != NULL);
-	memcpy(tmpbuffer, bp->data, XFS_LBSIZE(dp->i_mount));
+	memcpy(tmpbuffer, bp->b_addr, XFS_LBSIZE(dp->i_mount));
 	leaf = (xfs_attr_leafblock_t *)tmpbuffer;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
-	memset(bp->data, 0, XFS_LBSIZE(dp->i_mount));
+	memset(bp->b_addr, 0, XFS_LBSIZE(dp->i_mount));
 
 	/*
 	 * Clean out the prior contents of the attribute list.
@@ -855,7 +858,7 @@ xfs_attr_leaf_to_node(xfs_da_args_t *args)
 	xfs_attr_leafblock_t *leaf;
 	xfs_da_intnode_t *node;
 	xfs_inode_t *dp;
-	xfs_dabuf_t *bp1, *bp2;
+	struct xfs_buf *bp1, *bp2;
 	xfs_dablk_t blkno;
 	int error;
 
@@ -877,10 +880,9 @@ xfs_attr_leaf_to_node(xfs_da_args_t *args)
 	if (error)
 		goto out;
 	ASSERT(bp2 != NULL);
-	memcpy(bp2->data, bp1->data, XFS_LBSIZE(dp->i_mount));
-	xfs_da_buf_done(bp1);
+	memcpy(bp2->b_addr, bp1->b_addr, XFS_LBSIZE(dp->i_mount));
 	bp1 = NULL;
-	xfs_da_log_buf(args->trans, bp2, 0, XFS_LBSIZE(dp->i_mount) - 1);
+	xfs_trans_log_buf(args->trans, bp2, 0, XFS_LBSIZE(dp->i_mount) - 1);
 
 	/*
 	 * Set up the new root node.
@@ -888,21 +890,17 @@ xfs_attr_leaf_to_node(xfs_da_args_t *args)
 	error = xfs_da_node_create(args, 0, 1, &bp1, XFS_ATTR_FORK);
 	if (error)
 		goto out;
-	node = bp1->data;
-	leaf = bp2->data;
+	node = bp1->b_addr;
+	leaf = bp2->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	/* both on-disk, don't endian-flip twice */
 	node->btree[0].hashval =
 		leaf->entries[be16_to_cpu(leaf->hdr.count)-1 ].hashval;
 	node->btree[0].before = cpu_to_be32(blkno);
 	node->hdr.count = cpu_to_be16(1);
-	xfs_da_log_buf(args->trans, bp1, 0, XFS_LBSIZE(dp->i_mount) - 1);
+	xfs_trans_log_buf(args->trans, bp1, 0, XFS_LBSIZE(dp->i_mount) - 1);
 	error = 0;
 out:
-	if (bp1)
-		xfs_da_buf_done(bp1);
-	if (bp2)
-		xfs_da_buf_done(bp2);
 	return(error);
 }
 
@@ -916,12 +914,15 @@ out:
  * or a leaf in a node attribute list.
  */
 STATIC int
-xfs_attr_leaf_create(xfs_da_args_t *args, xfs_dablk_t blkno, xfs_dabuf_t **bpp)
+xfs_attr_leaf_create(
+	xfs_da_args_t	*args,
+	xfs_dablk_t	blkno,
+	struct xfs_buf	**bpp)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_hdr_t *hdr;
 	xfs_inode_t *dp;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error;
 
 	trace_xfs_attr_leaf_create(args);
@@ -933,7 +934,7 @@ xfs_attr_leaf_create(xfs_da_args_t *args, xfs_dablk_t blkno, xfs_dabuf_t **bpp)
 	if (error)
 		return(error);
 	ASSERT(bp != NULL);
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	memset((char *)leaf, 0, XFS_LBSIZE(dp->i_mount));
 	hdr = &leaf->hdr;
 	hdr->info.magic = cpu_to_be16(XFS_ATTR_LEAF_MAGIC);
@@ -947,7 +948,7 @@ xfs_attr_leaf_create(xfs_da_args_t *args, xfs_dablk_t blkno, xfs_dabuf_t **bpp)
 	hdr->freemap[0].size = cpu_to_be16(be16_to_cpu(hdr->firstused) -
 					   sizeof(xfs_attr_leaf_hdr_t));
 
-	xfs_da_log_buf(args->trans, bp, 0, XFS_LBSIZE(dp->i_mount) - 1);
+	xfs_trans_log_buf(args->trans, bp, 0, XFS_LBSIZE(dp->i_mount) - 1);
 
 	*bpp = bp;
 	return(0);
@@ -1014,7 +1015,9 @@ xfs_attr_leaf_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
  * Add a name to the leaf attribute list structure.
  */
 int
-xfs_attr_leaf_add(xfs_dabuf_t *bp, xfs_da_args_t *args)
+xfs_attr_leaf_add(
+	struct xfs_buf		*bp,
+	struct xfs_da_args	*args)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_hdr_t *hdr;
@@ -1023,7 +1026,7 @@ xfs_attr_leaf_add(xfs_dabuf_t *bp, xfs_da_args_t *args)
 
 	trace_xfs_attr_leaf_add(args);
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT((args->index >= 0)
 		&& (args->index <= be16_to_cpu(leaf->hdr.count)));
@@ -1085,7 +1088,10 @@ xfs_attr_leaf_add(xfs_dabuf_t *bp, xfs_da_args_t *args)
  * Add a name to a leaf attribute list structure.
  */
 STATIC int
-xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
+xfs_attr_leaf_add_work(
+	struct xfs_buf	*bp,
+	xfs_da_args_t	*args,
+	int		mapindex)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_hdr_t *hdr;
@@ -1096,7 +1102,7 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
 	xfs_mount_t *mp;
 	int tmp, i;
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	hdr = &leaf->hdr;
 	ASSERT((mapindex >= 0) && (mapindex < XFS_ATTR_LEAF_MAPSIZE));
@@ -1110,7 +1116,7 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
 		tmp  = be16_to_cpu(hdr->count) - args->index;
 		tmp *= sizeof(xfs_attr_leaf_entry_t);
 		memmove((char *)(entry+1), (char *)entry, tmp);
-		xfs_da_log_buf(args->trans, bp,
+		xfs_trans_log_buf(args->trans, bp,
 		    XFS_DA_LOGRANGE(leaf, entry, tmp + sizeof(*entry)));
 	}
 	be16_add_cpu(&hdr->count, 1);
@@ -1142,7 +1148,7 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
 			args->index2++;
 		}
 	}
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 			  XFS_DA_LOGRANGE(leaf, entry, sizeof(*entry)));
 	ASSERT((args->index == 0) ||
 	       (be32_to_cpu(entry->hashval) >= be32_to_cpu((entry-1)->hashval)));
@@ -1174,7 +1180,7 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
 		args->rmtblkno = 1;
 		args->rmtblkcnt = XFS_B_TO_FSB(mp, args->valuelen);
 	}
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 	     XFS_DA_LOGRANGE(leaf, xfs_attr_leaf_name(leaf, args->index),
 				   xfs_attr_leaf_entsize(leaf, args->index)));
 
@@ -1198,7 +1204,7 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
 		}
 	}
 	be16_add_cpu(&hdr->usedbytes, xfs_attr_leaf_entsize(leaf, args->index));
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 		XFS_DA_LOGRANGE(leaf, hdr, sizeof(*hdr)));
 	return(0);
 }
@@ -1207,7 +1213,9 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
  * Garbage collect a leaf attribute list block by copying it to a new buffer.
  */
 STATIC void
-xfs_attr_leaf_compact(xfs_trans_t *trans, xfs_dabuf_t *bp)
+xfs_attr_leaf_compact(
+	struct xfs_trans *trans,
+	struct xfs_buf	*bp)
 {
 	xfs_attr_leafblock_t *leaf_s, *leaf_d;
 	xfs_attr_leaf_hdr_t *hdr_s, *hdr_d;
@@ -1217,14 +1225,14 @@ xfs_attr_leaf_compact(xfs_trans_t *trans, xfs_dabuf_t *bp)
 	mp = trans->t_mountp;
 	tmpbuffer = kmem_alloc(XFS_LBSIZE(mp), KM_SLEEP);
 	ASSERT(tmpbuffer != NULL);
-	memcpy(tmpbuffer, bp->data, XFS_LBSIZE(mp));
-	memset(bp->data, 0, XFS_LBSIZE(mp));
+	memcpy(tmpbuffer, bp->b_addr, XFS_LBSIZE(mp));
+	memset(bp->b_addr, 0, XFS_LBSIZE(mp));
 
 	/*
 	 * Copy basic information
 	 */
 	leaf_s = (xfs_attr_leafblock_t *)tmpbuffer;
-	leaf_d = bp->data;
+	leaf_d = bp->b_addr;
 	hdr_s = &leaf_s->hdr;
 	hdr_d = &leaf_d->hdr;
 	hdr_d->info = hdr_s->info;	/* struct copy */
@@ -1247,7 +1255,7 @@ xfs_attr_leaf_compact(xfs_trans_t *trans, xfs_dabuf_t *bp)
 	 */
 	xfs_attr_leaf_moveents(leaf_s, 0, leaf_d, 0,
 				be16_to_cpu(hdr_s->count), mp);
-	xfs_da_log_buf(trans, bp, 0, XFS_LBSIZE(mp) - 1);
+	xfs_trans_log_buf(trans, bp, 0, XFS_LBSIZE(mp) - 1);
 
 	kmem_free(tmpbuffer);
 }
@@ -1279,8 +1287,8 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 	 */
 	ASSERT(blk1->magic == XFS_ATTR_LEAF_MAGIC);
 	ASSERT(blk2->magic == XFS_ATTR_LEAF_MAGIC);
-	leaf1 = blk1->bp->data;
-	leaf2 = blk2->bp->data;
+	leaf1 = blk1->bp->b_addr;
+	leaf2 = blk2->bp->b_addr;
 	ASSERT(leaf1->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(leaf2->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	args = state->args;
@@ -1298,8 +1306,8 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 		tmp_blk = blk1;
 		blk1 = blk2;
 		blk2 = tmp_blk;
-		leaf1 = blk1->bp->data;
-		leaf2 = blk2->bp->data;
+		leaf1 = blk1->bp->b_addr;
+		leaf2 = blk2->bp->b_addr;
 		swap = 1;
 	}
 	hdr1 = &leaf1->hdr;
@@ -1346,8 +1354,8 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 		xfs_attr_leaf_moveents(leaf1, be16_to_cpu(hdr1->count) - count,
 				leaf2, 0, count, state->mp);
 
-		xfs_da_log_buf(args->trans, blk1->bp, 0, state->blocksize-1);
-		xfs_da_log_buf(args->trans, blk2->bp, 0, state->blocksize-1);
+		xfs_trans_log_buf(args->trans, blk1->bp, 0, state->blocksize-1);
+		xfs_trans_log_buf(args->trans, blk2->bp, 0, state->blocksize-1);
 	} else if (count > be16_to_cpu(hdr1->count)) {
 		/*
 		 * I assert that since all callers pass in an empty
@@ -1378,8 +1386,8 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 		xfs_attr_leaf_moveents(leaf2, 0, leaf1,
 				be16_to_cpu(hdr1->count), count, state->mp);
 
-		xfs_da_log_buf(args->trans, blk1->bp, 0, state->blocksize-1);
-		xfs_da_log_buf(args->trans, blk2->bp, 0, state->blocksize-1);
+		xfs_trans_log_buf(args->trans, blk1->bp, 0, state->blocksize-1);
+		xfs_trans_log_buf(args->trans, blk2->bp, 0, state->blocksize-1);
 	}
 
 	/*
@@ -1448,8 +1456,8 @@ xfs_attr_leaf_figure_balance(xfs_da_state_t *state,
 	/*
 	 * Set up environment.
 	 */
-	leaf1 = blk1->bp->data;
-	leaf2 = blk2->bp->data;
+	leaf1 = blk1->bp->b_addr;
+	leaf2 = blk2->bp->b_addr;
 	hdr1 = &leaf1->hdr;
 	hdr2 = &leaf2->hdr;
 	foundit = 0;
@@ -1551,7 +1559,7 @@ xfs_attr_leaf_toosmall(xfs_da_state_t *state, int *action)
 	xfs_da_blkinfo_t *info;
 	int count, bytes, forward, error, retval, i;
 	xfs_dablk_t blkno;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 
 	/*
 	 * Check for the degenerate case of the block being over 50% full.
@@ -1559,7 +1567,7 @@ xfs_attr_leaf_toosmall(xfs_da_state_t *state, int *action)
 	 * to coalesce with a sibling.
 	 */
 	blk = &state->path.blk[ state->path.active-1 ];
-	info = blk->bp->data;
+	info = blk->bp->b_addr;
 	ASSERT(info->magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	leaf = (xfs_attr_leafblock_t *)info;
 	count = be16_to_cpu(leaf->hdr.count);
@@ -1622,13 +1630,13 @@ xfs_attr_leaf_toosmall(xfs_da_state_t *state, int *action)
 		count  = be16_to_cpu(leaf->hdr.count);
 		bytes  = state->blocksize - (state->blocksize>>2);
 		bytes -= be16_to_cpu(leaf->hdr.usedbytes);
-		leaf = bp->data;
+		leaf = bp->b_addr;
 		ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 		count += be16_to_cpu(leaf->hdr.count);
 		bytes -= be16_to_cpu(leaf->hdr.usedbytes);
 		bytes -= count * sizeof(xfs_attr_leaf_entry_t);
 		bytes -= sizeof(xfs_attr_leaf_hdr_t);
-		xfs_da_brelse(state->args->trans, bp);
+		xfs_trans_brelse(state->args->trans, bp);
 		if (bytes >= 0)
 			break;	/* fits with at least 25% to spare */
 	}
@@ -1666,7 +1674,9 @@ xfs_attr_leaf_toosmall(xfs_da_state_t *state, int *action)
  * If two leaves are 37% full, when combined they will leave 25% free.
  */
 int
-xfs_attr_leaf_remove(xfs_dabuf_t *bp, xfs_da_args_t *args)
+xfs_attr_leaf_remove(
+	struct xfs_buf	*bp,
+	xfs_da_args_t	*args)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_hdr_t *hdr;
@@ -1676,7 +1686,7 @@ xfs_attr_leaf_remove(xfs_dabuf_t *bp, xfs_da_args_t *args)
 	int tablesize, tmp, i;
 	xfs_mount_t *mp;
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	hdr = &leaf->hdr;
 	mp = args->trans->t_mountp;
@@ -1769,7 +1779,7 @@ xfs_attr_leaf_remove(xfs_dabuf_t *bp, xfs_da_args_t *args)
 	 */
 	memset(xfs_attr_leaf_name(leaf, args->index), 0, entsize);
 	be16_add_cpu(&hdr->usedbytes, -entsize);
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 	     XFS_DA_LOGRANGE(leaf, xfs_attr_leaf_name(leaf, args->index),
 				   entsize));
 
@@ -1777,7 +1787,7 @@ xfs_attr_leaf_remove(xfs_dabuf_t *bp, xfs_da_args_t *args)
 					* sizeof(xfs_attr_leaf_entry_t);
 	memmove((char *)entry, (char *)(entry+1), tmp);
 	be16_add_cpu(&hdr->count, -1);
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 	    XFS_DA_LOGRANGE(leaf, entry, tmp + sizeof(*entry)));
 	entry = &leaf->entries[be16_to_cpu(hdr->count)];
 	memset((char *)entry, 0, sizeof(xfs_attr_leaf_entry_t));
@@ -1807,7 +1817,7 @@ xfs_attr_leaf_remove(xfs_dabuf_t *bp, xfs_da_args_t *args)
 	} else {
 		hdr->holes = 1;		/* mark as needing compaction */
 	}
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 			  XFS_DA_LOGRANGE(leaf, hdr, sizeof(*hdr)));
 
 	/*
@@ -1840,8 +1850,8 @@ xfs_attr_leaf_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 	mp = state->mp;
 	ASSERT(drop_blk->magic == XFS_ATTR_LEAF_MAGIC);
 	ASSERT(save_blk->magic == XFS_ATTR_LEAF_MAGIC);
-	drop_leaf = drop_blk->bp->data;
-	save_leaf = save_blk->bp->data;
+	drop_leaf = drop_blk->bp->b_addr;
+	save_leaf = save_blk->bp->b_addr;
 	ASSERT(drop_leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(save_leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	drop_hdr = &drop_leaf->hdr;
@@ -1906,7 +1916,7 @@ xfs_attr_leaf_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 		kmem_free(tmpbuffer);
 	}
 
-	xfs_da_log_buf(state->args->trans, save_blk->bp, 0,
+	xfs_trans_log_buf(state->args->trans, save_blk->bp, 0,
 					   state->blocksize - 1);
 
 	/*
@@ -1934,7 +1944,9 @@ xfs_attr_leaf_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
  * Don't change the args->value unless we find the attribute.
  */
 int
-xfs_attr_leaf_lookup_int(xfs_dabuf_t *bp, xfs_da_args_t *args)
+xfs_attr_leaf_lookup_int(
+	struct xfs_buf	*bp,
+	xfs_da_args_t	*args)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_entry_t *entry;
@@ -1945,7 +1957,7 @@ xfs_attr_leaf_lookup_int(xfs_dabuf_t *bp, xfs_da_args_t *args)
 
 	trace_xfs_attr_leaf_lookup(args);
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(be16_to_cpu(leaf->hdr.count)
 					< (XFS_LBSIZE(args->dp->i_mount)/8));
@@ -2041,7 +2053,9 @@ xfs_attr_leaf_lookup_int(xfs_dabuf_t *bp, xfs_da_args_t *args)
  * list structure.
  */
 int
-xfs_attr_leaf_getvalue(xfs_dabuf_t *bp, xfs_da_args_t *args)
+xfs_attr_leaf_getvalue(
+	struct xfs_buf	*bp,
+	xfs_da_args_t	*args)
 {
 	int valuelen;
 	xfs_attr_leafblock_t *leaf;
@@ -2049,7 +2063,7 @@ xfs_attr_leaf_getvalue(xfs_dabuf_t *bp, xfs_da_args_t *args)
 	xfs_attr_leaf_name_local_t *name_loc;
 	xfs_attr_leaf_name_remote_t *name_rmt;
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(be16_to_cpu(leaf->hdr.count)
 					< (XFS_LBSIZE(args->dp->i_mount)/8));
@@ -2247,12 +2261,14 @@ xfs_attr_leaf_moveents(xfs_attr_leafblock_t *leaf_s, int start_s,
  * Return 0 unless leaf2 should go before leaf1.
  */
 int
-xfs_attr_leaf_order(xfs_dabuf_t *leaf1_bp, xfs_dabuf_t *leaf2_bp)
+xfs_attr_leaf_order(
+	struct xfs_buf	*leaf1_bp,
+	struct xfs_buf	*leaf2_bp)
 {
 	xfs_attr_leafblock_t *leaf1, *leaf2;
 
-	leaf1 = leaf1_bp->data;
-	leaf2 = leaf2_bp->data;
+	leaf1 = leaf1_bp->b_addr;
+	leaf2 = leaf2_bp->b_addr;
 	ASSERT((leaf1->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)) &&
 	       (leaf2->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)));
 	if ((be16_to_cpu(leaf1->hdr.count) > 0) &&
@@ -2272,11 +2288,13 @@ xfs_attr_leaf_order(xfs_dabuf_t *leaf1_bp, xfs_dabuf_t *leaf2_bp)
  * Pick up the last hashvalue from a leaf block.
  */
 xfs_dahash_t
-xfs_attr_leaf_lasthash(xfs_dabuf_t *bp, int *count)
+xfs_attr_leaf_lasthash(
+	struct xfs_buf	*bp,
+	int		*count)
 {
 	xfs_attr_leafblock_t *leaf;
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	if (count)
 		*count = be16_to_cpu(leaf->hdr.count);
@@ -2337,7 +2355,9 @@ xfs_attr_leaf_newentsize(int namelen, int valuelen, int blocksize, int *local)
  * Copy out attribute list entries for attr_list(), for leaf attribute lists.
  */
 int
-xfs_attr_leaf_list_int(xfs_dabuf_t *bp, xfs_attr_list_context_t *context)
+xfs_attr_leaf_list_int(
+	struct xfs_buf		*bp,
+	xfs_attr_list_context_t	*context)
 {
 	attrlist_cursor_kern_t *cursor;
 	xfs_attr_leafblock_t *leaf;
@@ -2345,7 +2365,7 @@ xfs_attr_leaf_list_int(xfs_dabuf_t *bp, xfs_attr_list_context_t *context)
 	int retval, i;
 
 	ASSERT(bp != NULL);
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	cursor = context->cursor;
 	cursor->initted = 1;
 
@@ -2463,7 +2483,7 @@ xfs_attr_leaf_clearflag(xfs_da_args_t *args)
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_entry_t *entry;
 	xfs_attr_leaf_name_remote_t *name_rmt;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error;
 #ifdef DEBUG
 	xfs_attr_leaf_name_local_t *name_loc;
@@ -2482,7 +2502,7 @@ xfs_attr_leaf_clearflag(xfs_da_args_t *args)
 	}
 	ASSERT(bp != NULL);
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(args->index < be16_to_cpu(leaf->hdr.count));
 	ASSERT(args->index >= 0);
@@ -2505,7 +2525,7 @@ xfs_attr_leaf_clearflag(xfs_da_args_t *args)
 #endif /* DEBUG */
 
 	entry->flags &= ~XFS_ATTR_INCOMPLETE;
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 			 XFS_DA_LOGRANGE(leaf, entry, sizeof(*entry)));
 
 	if (args->rmtblkno) {
@@ -2513,10 +2533,9 @@ xfs_attr_leaf_clearflag(xfs_da_args_t *args)
 		name_rmt = xfs_attr_leaf_name_remote(leaf, args->index);
 		name_rmt->valueblk = cpu_to_be32(args->rmtblkno);
 		name_rmt->valuelen = cpu_to_be32(args->valuelen);
-		xfs_da_log_buf(args->trans, bp,
+		xfs_trans_log_buf(args->trans, bp,
 			 XFS_DA_LOGRANGE(leaf, name_rmt, sizeof(*name_rmt)));
 	}
-	xfs_da_buf_done(bp);
 
 	/*
 	 * Commit the flag value change and start the next trans in series.
@@ -2533,7 +2552,7 @@ xfs_attr_leaf_setflag(xfs_da_args_t *args)
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_entry_t *entry;
 	xfs_attr_leaf_name_remote_t *name_rmt;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error;
 
 	trace_xfs_attr_leaf_setflag(args);
@@ -2548,7 +2567,7 @@ xfs_attr_leaf_setflag(xfs_da_args_t *args)
 	}
 	ASSERT(bp != NULL);
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(args->index < be16_to_cpu(leaf->hdr.count));
 	ASSERT(args->index >= 0);
@@ -2556,16 +2575,15 @@ xfs_attr_leaf_setflag(xfs_da_args_t *args)
 
 	ASSERT((entry->flags & XFS_ATTR_INCOMPLETE) == 0);
 	entry->flags |= XFS_ATTR_INCOMPLETE;
-	xfs_da_log_buf(args->trans, bp,
+	xfs_trans_log_buf(args->trans, bp,
 			XFS_DA_LOGRANGE(leaf, entry, sizeof(*entry)));
 	if ((entry->flags & XFS_ATTR_LOCAL) == 0) {
 		name_rmt = xfs_attr_leaf_name_remote(leaf, args->index);
 		name_rmt->valueblk = 0;
 		name_rmt->valuelen = 0;
-		xfs_da_log_buf(args->trans, bp,
+		xfs_trans_log_buf(args->trans, bp,
 			 XFS_DA_LOGRANGE(leaf, name_rmt, sizeof(*name_rmt)));
 	}
-	xfs_da_buf_done(bp);
 
 	/*
 	 * Commit the flag value change and start the next trans in series.
@@ -2586,7 +2604,7 @@ xfs_attr_leaf_flipflags(xfs_da_args_t *args)
 	xfs_attr_leafblock_t *leaf1, *leaf2;
 	xfs_attr_leaf_entry_t *entry1, *entry2;
 	xfs_attr_leaf_name_remote_t *name_rmt;
-	xfs_dabuf_t *bp1, *bp2;
+	struct xfs_buf *bp1, *bp2;
 	int error;
 #ifdef DEBUG
 	xfs_attr_leaf_name_local_t *name_loc;
@@ -2620,13 +2638,13 @@ xfs_attr_leaf_flipflags(xfs_da_args_t *args)
 		bp2 = bp1;
 	}
 
-	leaf1 = bp1->data;
+	leaf1 = bp1->b_addr;
 	ASSERT(leaf1->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(args->index < be16_to_cpu(leaf1->hdr.count));
 	ASSERT(args->index >= 0);
 	entry1 = &leaf1->entries[ args->index ];
 
-	leaf2 = bp2->data;
+	leaf2 = bp2->b_addr;
 	ASSERT(leaf2->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	ASSERT(args->index2 < be16_to_cpu(leaf2->hdr.count));
 	ASSERT(args->index2 >= 0);
@@ -2660,30 +2678,27 @@ xfs_attr_leaf_flipflags(xfs_da_args_t *args)
 	ASSERT((entry2->flags & XFS_ATTR_INCOMPLETE) == 0);
 
 	entry1->flags &= ~XFS_ATTR_INCOMPLETE;
-	xfs_da_log_buf(args->trans, bp1,
+	xfs_trans_log_buf(args->trans, bp1,
 			  XFS_DA_LOGRANGE(leaf1, entry1, sizeof(*entry1)));
 	if (args->rmtblkno) {
 		ASSERT((entry1->flags & XFS_ATTR_LOCAL) == 0);
 		name_rmt = xfs_attr_leaf_name_remote(leaf1, args->index);
 		name_rmt->valueblk = cpu_to_be32(args->rmtblkno);
 		name_rmt->valuelen = cpu_to_be32(args->valuelen);
-		xfs_da_log_buf(args->trans, bp1,
+		xfs_trans_log_buf(args->trans, bp1,
 			 XFS_DA_LOGRANGE(leaf1, name_rmt, sizeof(*name_rmt)));
 	}
 
 	entry2->flags |= XFS_ATTR_INCOMPLETE;
-	xfs_da_log_buf(args->trans, bp2,
+	xfs_trans_log_buf(args->trans, bp2,
 			  XFS_DA_LOGRANGE(leaf2, entry2, sizeof(*entry2)));
 	if ((entry2->flags & XFS_ATTR_LOCAL) == 0) {
 		name_rmt = xfs_attr_leaf_name_remote(leaf2, args->index2);
 		name_rmt->valueblk = 0;
 		name_rmt->valuelen = 0;
-		xfs_da_log_buf(args->trans, bp2,
+		xfs_trans_log_buf(args->trans, bp2,
 			 XFS_DA_LOGRANGE(leaf2, name_rmt, sizeof(*name_rmt)));
 	}
-	xfs_da_buf_done(bp1);
-	if (bp1 != bp2)
-		xfs_da_buf_done(bp2);
 
 	/*
 	 * Commit the flag value change and start the next trans in series.
@@ -2706,7 +2721,7 @@ xfs_attr_root_inactive(xfs_trans_t **trans, xfs_inode_t *dp)
 {
 	xfs_da_blkinfo_t *info;
 	xfs_daddr_t blkno;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error;
 
 	/*
@@ -2718,20 +2733,20 @@ xfs_attr_root_inactive(xfs_trans_t **trans, xfs_inode_t *dp)
 	error = xfs_da_read_buf(*trans, dp, 0, -1, &bp, XFS_ATTR_FORK);
 	if (error)
 		return(error);
-	blkno = xfs_da_blkno(bp);
+	blkno = XFS_BUF_ADDR(bp);
 
 	/*
 	 * Invalidate the tree, even if the "tree" is only a single leaf block.
 	 * This is a depth-first traversal!
 	 */
-	info = bp->data;
+	info = bp->b_addr;
 	if (info->magic == cpu_to_be16(XFS_DA_NODE_MAGIC)) {
 		error = xfs_attr_node_inactive(trans, dp, bp, 1);
 	} else if (info->magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)) {
 		error = xfs_attr_leaf_inactive(trans, dp, bp);
 	} else {
 		error = XFS_ERROR(EIO);
-		xfs_da_brelse(*trans, bp);
+		xfs_trans_brelse(*trans, bp);
 	}
 	if (error)
 		return(error);
@@ -2742,7 +2757,7 @@ xfs_attr_root_inactive(xfs_trans_t **trans, xfs_inode_t *dp)
 	error = xfs_da_get_buf(*trans, dp, 0, blkno, &bp, XFS_ATTR_FORK);
 	if (error)
 		return(error);
-	xfs_da_binval(*trans, bp);	/* remove from cache */
+	xfs_trans_binval(*trans, bp);	/* remove from cache */
 	/*
 	 * Commit the invalidate and start the next transaction.
 	 */
@@ -2756,34 +2771,37 @@ xfs_attr_root_inactive(xfs_trans_t **trans, xfs_inode_t *dp)
  * We're doing a depth-first traversal in order to invalidate everything.
  */
 STATIC int
-xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp,
-				   int level)
+xfs_attr_node_inactive(
+	struct xfs_trans **trans,
+	struct xfs_inode *dp,
+	struct xfs_buf	*bp,
+	int		level)
 {
 	xfs_da_blkinfo_t *info;
 	xfs_da_intnode_t *node;
 	xfs_dablk_t child_fsb;
 	xfs_daddr_t parent_blkno, child_blkno;
 	int error, count, i;
-	xfs_dabuf_t *child_bp;
+	struct xfs_buf *child_bp;
 
 	/*
 	 * Since this code is recursive (gasp!) we must protect ourselves.
 	 */
 	if (level > XFS_DA_NODE_MAXDEPTH) {
-		xfs_da_brelse(*trans, bp);	/* no locks for later trans */
+		xfs_trans_brelse(*trans, bp);	/* no locks for later trans */
 		return(XFS_ERROR(EIO));
 	}
 
-	node = bp->data;
+	node = bp->b_addr;
 	ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
-	parent_blkno = xfs_da_blkno(bp);	/* save for re-read later */
+	parent_blkno = XFS_BUF_ADDR(bp);	/* save for re-read later */
 	count = be16_to_cpu(node->hdr.count);
 	if (!count) {
-		xfs_da_brelse(*trans, bp);
+		xfs_trans_brelse(*trans, bp);
 		return(0);
 	}
 	child_fsb = be32_to_cpu(node->btree[0].before);
-	xfs_da_brelse(*trans, bp);	/* no locks for later trans */
+	xfs_trans_brelse(*trans, bp);	/* no locks for later trans */
 
 	/*
 	 * If this is the node level just above the leaves, simply loop
@@ -2803,12 +2821,12 @@ xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp,
 			return(error);
 		if (child_bp) {
 						/* save for re-read later */
-			child_blkno = xfs_da_blkno(child_bp);
+			child_blkno = XFS_BUF_ADDR(child_bp);
 
 			/*
 			 * Invalidate the subtree, however we have to.
 			 */
-			info = child_bp->data;
+			info = child_bp->b_addr;
 			if (info->magic == cpu_to_be16(XFS_DA_NODE_MAGIC)) {
 				error = xfs_attr_node_inactive(trans, dp,
 						child_bp, level+1);
@@ -2817,7 +2835,7 @@ xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp,
 						child_bp);
 			} else {
 				error = XFS_ERROR(EIO);
-				xfs_da_brelse(*trans, child_bp);
+				xfs_trans_brelse(*trans, child_bp);
 			}
 			if (error)
 				return(error);
@@ -2830,7 +2848,7 @@ xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp,
 				&child_bp, XFS_ATTR_FORK);
 			if (error)
 				return(error);
-			xfs_da_binval(*trans, child_bp);
+			xfs_trans_binval(*trans, child_bp);
 		}
 
 		/*
@@ -2843,7 +2861,7 @@ xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp,
 			if (error)
 				return(error);
 			child_fsb = be32_to_cpu(node->btree[i+1].before);
-			xfs_da_brelse(*trans, bp);
+			xfs_trans_brelse(*trans, bp);
 		}
 		/*
 		 * Atomically commit the whole invalidate stuff.
@@ -2863,7 +2881,10 @@ xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp,
  * caught holding something that the logging code wants to flush to disk.
  */
 STATIC int
-xfs_attr_leaf_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp)
+xfs_attr_leaf_inactive(
+	struct xfs_trans **trans,
+	struct xfs_inode *dp,
+	struct xfs_buf	*bp)
 {
 	xfs_attr_leafblock_t *leaf;
 	xfs_attr_leaf_entry_t *entry;
@@ -2871,7 +2892,7 @@ xfs_attr_leaf_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp)
 	xfs_attr_inactive_list_t *list, *lp;
 	int error, count, size, tmp, i;
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 
 	/*
@@ -2892,7 +2913,7 @@ xfs_attr_leaf_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp)
 	 * If there are no "remote" values, we're done.
 	 */
 	if (count == 0) {
-		xfs_da_brelse(*trans, bp);
+		xfs_trans_brelse(*trans, bp);
 		return(0);
 	}
 
@@ -2919,7 +2940,7 @@ xfs_attr_leaf_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp)
 			}
 		}
 	}
-	xfs_da_brelse(*trans, bp);	/* unlock for trans. in freextent() */
+	xfs_trans_brelse(*trans, bp);	/* unlock for trans. in freextent() */
 
 	/*
 	 * Invalidate each of the "remote" value extents.
diff --git a/fs/xfs/xfs_attr_leaf.h b/fs/xfs/xfs_attr_leaf.h
index 9c7d22fdcf4d..dea17722945e 100644
--- a/fs/xfs/xfs_attr_leaf.h
+++ b/fs/xfs/xfs_attr_leaf.h
@@ -31,7 +31,6 @@
 struct attrlist;
 struct attrlist_cursor_kern;
 struct xfs_attr_list_context;
-struct xfs_dabuf;
 struct xfs_da_args;
 struct xfs_da_state;
 struct xfs_da_state_blk;
@@ -215,7 +214,7 @@ int	xfs_attr_shortform_getvalue(struct xfs_da_args *args);
 int	xfs_attr_shortform_to_leaf(struct xfs_da_args *args);
 int	xfs_attr_shortform_remove(struct xfs_da_args *args);
 int	xfs_attr_shortform_list(struct xfs_attr_list_context *context);
-int	xfs_attr_shortform_allfit(struct xfs_dabuf *bp, struct xfs_inode *dp);
+int	xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp);
 int	xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes);
 
 
@@ -223,7 +222,7 @@ int	xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes);
  * Internal routines when attribute fork size == XFS_LBSIZE(mp).
  */
 int	xfs_attr_leaf_to_node(struct xfs_da_args *args);
-int	xfs_attr_leaf_to_shortform(struct xfs_dabuf *bp,
+int	xfs_attr_leaf_to_shortform(struct xfs_buf *bp,
 				   struct xfs_da_args *args, int forkoff);
 int	xfs_attr_leaf_clearflag(struct xfs_da_args *args);
 int	xfs_attr_leaf_setflag(struct xfs_da_args *args);
@@ -235,14 +234,14 @@ int	xfs_attr_leaf_flipflags(xfs_da_args_t *args);
 int	xfs_attr_leaf_split(struct xfs_da_state *state,
 				   struct xfs_da_state_blk *oldblk,
 				   struct xfs_da_state_blk *newblk);
-int	xfs_attr_leaf_lookup_int(struct xfs_dabuf *leaf,
+int	xfs_attr_leaf_lookup_int(struct xfs_buf *leaf,
 					struct xfs_da_args *args);
-int	xfs_attr_leaf_getvalue(struct xfs_dabuf *bp, struct xfs_da_args *args);
-int	xfs_attr_leaf_add(struct xfs_dabuf *leaf_buffer,
+int	xfs_attr_leaf_getvalue(struct xfs_buf *bp, struct xfs_da_args *args);
+int	xfs_attr_leaf_add(struct xfs_buf *leaf_buffer,
 				 struct xfs_da_args *args);
-int	xfs_attr_leaf_remove(struct xfs_dabuf *leaf_buffer,
+int	xfs_attr_leaf_remove(struct xfs_buf *leaf_buffer,
 				    struct xfs_da_args *args);
-int	xfs_attr_leaf_list_int(struct xfs_dabuf *bp,
+int	xfs_attr_leaf_list_int(struct xfs_buf *bp,
 				      struct xfs_attr_list_context *context);
 
 /*
@@ -257,9 +256,9 @@ int	xfs_attr_root_inactive(struct xfs_trans **trans, struct xfs_inode *dp);
 /*
  * Utility routines.
  */
-xfs_dahash_t	xfs_attr_leaf_lasthash(struct xfs_dabuf *bp, int *count);
-int	xfs_attr_leaf_order(struct xfs_dabuf *leaf1_bp,
-				   struct xfs_dabuf *leaf2_bp);
+xfs_dahash_t	xfs_attr_leaf_lasthash(struct xfs_buf *bp, int *count);
+int	xfs_attr_leaf_order(struct xfs_buf *leaf1_bp,
+				   struct xfs_buf *leaf2_bp);
 int	xfs_attr_leaf_newentsize(int namelen, int valuelen, int blocksize,
 					int *local);
 #endif	/* __XFS_ATTR_LEAF_H__ */
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 58b815ec8c91..848ffa77707b 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -5517,7 +5517,7 @@ xfs_getbmap(
 		if (xfs_get_extsz_hint(ip) ||
 		    ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC|XFS_DIFLAG_APPEND)){
 			prealloced = 1;
-			fixlen = XFS_MAXIOFFSET(mp);
+			fixlen = mp->m_super->s_maxbytes;
 		} else {
 			prealloced = 0;
 			fixlen = XFS_ISIZE(ip);
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 269b35c084da..d7a9dd735e1e 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -164,14 +164,49 @@ xfs_buf_stale(
 	ASSERT(atomic_read(&bp->b_hold) >= 1);
 }
 
+static int
+xfs_buf_get_maps(
+	struct xfs_buf		*bp,
+	int			map_count)
+{
+	ASSERT(bp->b_maps == NULL);
+	bp->b_map_count = map_count;
+
+	if (map_count == 1) {
+		bp->b_maps = &bp->b_map;
+		return 0;
+	}
+
+	bp->b_maps = kmem_zalloc(map_count * sizeof(struct xfs_buf_map),
+				KM_NOFS);
+	if (!bp->b_maps)
+		return ENOMEM;
+	return 0;
+}
+
+/*
+ *	Frees b_pages if it was allocated.
+ */
+static void
+xfs_buf_free_maps(
+	struct xfs_buf	*bp)
+{
+	if (bp->b_maps != &bp->b_map) {
+		kmem_free(bp->b_maps);
+		bp->b_maps = NULL;
+	}
+}
+
 struct xfs_buf *
-xfs_buf_alloc(
+_xfs_buf_alloc(
 	struct xfs_buftarg	*target,
-	xfs_daddr_t		blkno,
-	size_t			numblks,
+	struct xfs_buf_map	*map,
+	int			nmaps,
 	xfs_buf_flags_t		flags)
 {
 	struct xfs_buf		*bp;
+	int			error;
+	int			i;
 
 	bp = kmem_zone_zalloc(xfs_buf_zone, KM_NOFS);
 	if (unlikely(!bp))
@@ -192,16 +227,28 @@ xfs_buf_alloc(
 	sema_init(&bp->b_sema, 0); /* held, no waiters */
 	XB_SET_OWNER(bp);
 	bp->b_target = target;
+	bp->b_flags = flags;
 
 	/*
 	 * Set length and io_length to the same value initially.
 	 * I/O routines should use io_length, which will be the same in
 	 * most cases but may be reset (e.g. XFS recovery).
 	 */
-	bp->b_length = numblks;
-	bp->b_io_length = numblks;
-	bp->b_flags = flags;
-	bp->b_bn = blkno;
+	error = xfs_buf_get_maps(bp, nmaps);
+	if (error)  {
+		kmem_zone_free(xfs_buf_zone, bp);
+		return NULL;
+	}
+
+	bp->b_bn = map[0].bm_bn;
+	bp->b_length = 0;
+	for (i = 0; i < nmaps; i++) {
+		bp->b_maps[i].bm_bn = map[i].bm_bn;
+		bp->b_maps[i].bm_len = map[i].bm_len;
+		bp->b_length += map[i].bm_len;
+	}
+	bp->b_io_length = bp->b_length;
+
 	atomic_set(&bp->b_pin_count, 0);
 	init_waitqueue_head(&bp->b_waiters);
 
@@ -280,6 +327,7 @@ xfs_buf_free(
 	} else if (bp->b_flags & _XBF_KMEM)
 		kmem_free(bp->b_addr);
 	_xfs_buf_free_pages(bp);
+	xfs_buf_free_maps(bp);
 	kmem_zone_free(xfs_buf_zone, bp);
 }
 
@@ -327,8 +375,9 @@ xfs_buf_allocate_memory(
 	}
 
 use_alloc_page:
-	start = BBTOB(bp->b_bn) >> PAGE_SHIFT;
-	end = (BBTOB(bp->b_bn + bp->b_length) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	start = BBTOB(bp->b_map.bm_bn) >> PAGE_SHIFT;
+	end = (BBTOB(bp->b_map.bm_bn + bp->b_length) + PAGE_SIZE - 1)
+								>> PAGE_SHIFT;
 	page_count = end - start;
 	error = _xfs_buf_get_pages(bp, page_count, flags);
 	if (unlikely(error))
@@ -425,8 +474,8 @@ _xfs_buf_map_pages(
 xfs_buf_t *
 _xfs_buf_find(
 	struct xfs_buftarg	*btp,
-	xfs_daddr_t		blkno,
-	size_t			numblks,
+	struct xfs_buf_map	*map,
+	int			nmaps,
 	xfs_buf_flags_t		flags,
 	xfs_buf_t		*new_bp)
 {
@@ -435,7 +484,12 @@ _xfs_buf_find(
 	struct rb_node		**rbp;
 	struct rb_node		*parent;
 	xfs_buf_t		*bp;
+	xfs_daddr_t		blkno = map[0].bm_bn;
+	int			numblks = 0;
+	int			i;
 
+	for (i = 0; i < nmaps; i++)
+		numblks += map[i].bm_len;
 	numbytes = BBTOB(numblks);
 
 	/* Check for IOs smaller than the sector size / not sector aligned */
@@ -527,31 +581,31 @@ found:
  * more hits than misses.
  */
 struct xfs_buf *
-xfs_buf_get(
-	xfs_buftarg_t		*target,
-	xfs_daddr_t		blkno,
-	size_t			numblks,
+xfs_buf_get_map(
+	struct xfs_buftarg	*target,
+	struct xfs_buf_map	*map,
+	int			nmaps,
 	xfs_buf_flags_t		flags)
 {
 	struct xfs_buf		*bp;
 	struct xfs_buf		*new_bp;
 	int			error = 0;
 
-	bp = _xfs_buf_find(target, blkno, numblks, flags, NULL);
+	bp = _xfs_buf_find(target, map, nmaps, flags, NULL);
 	if (likely(bp))
 		goto found;
 
-	new_bp = xfs_buf_alloc(target, blkno, numblks, flags);
+	new_bp = _xfs_buf_alloc(target, map, nmaps, flags);
 	if (unlikely(!new_bp))
 		return NULL;
 
 	error = xfs_buf_allocate_memory(new_bp, flags);
 	if (error) {
-		kmem_zone_free(xfs_buf_zone, new_bp);
+		xfs_buf_free(new_bp);
 		return NULL;
 	}
 
-	bp = _xfs_buf_find(target, blkno, numblks, flags, new_bp);
+	bp = _xfs_buf_find(target, map, nmaps, flags, new_bp);
 	if (!bp) {
 		xfs_buf_free(new_bp);
 		return NULL;
@@ -560,8 +614,6 @@ xfs_buf_get(
 	if (bp != new_bp)
 		xfs_buf_free(new_bp);
 
-	bp->b_io_length = bp->b_length;
-
 found:
 	if (!bp->b_addr) {
 		error = _xfs_buf_map_pages(bp, flags);
@@ -584,7 +636,7 @@ _xfs_buf_read(
 	xfs_buf_flags_t		flags)
 {
 	ASSERT(!(flags & XBF_WRITE));
-	ASSERT(bp->b_bn != XFS_BUF_DADDR_NULL);
+	ASSERT(bp->b_map.bm_bn != XFS_BUF_DADDR_NULL);
 
 	bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD);
 	bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD);
@@ -596,17 +648,17 @@ _xfs_buf_read(
 }
 
 xfs_buf_t *
-xfs_buf_read(
-	xfs_buftarg_t		*target,
-	xfs_daddr_t		blkno,
-	size_t			numblks,
+xfs_buf_read_map(
+	struct xfs_buftarg	*target,
+	struct xfs_buf_map	*map,
+	int			nmaps,
 	xfs_buf_flags_t		flags)
 {
-	xfs_buf_t		*bp;
+	struct xfs_buf		*bp;
 
 	flags |= XBF_READ;
 
-	bp = xfs_buf_get(target, blkno, numblks, flags);
+	bp = xfs_buf_get_map(target, map, nmaps, flags);
 	if (bp) {
 		trace_xfs_buf_read(bp, flags, _RET_IP_);
 
@@ -634,15 +686,15 @@ xfs_buf_read(
  *	safe manner.
  */
 void
-xfs_buf_readahead(
-	xfs_buftarg_t		*target,
-	xfs_daddr_t		blkno,
-	size_t			numblks)
+xfs_buf_readahead_map(
+	struct xfs_buftarg	*target,
+	struct xfs_buf_map	*map,
+	int			nmaps)
 {
 	if (bdi_read_congested(target->bt_bdi))
 		return;
 
-	xfs_buf_read(target, blkno, numblks,
+	xfs_buf_read_map(target, map, nmaps,
 		     XBF_TRYLOCK|XBF_ASYNC|XBF_READ_AHEAD);
 }
 
@@ -665,8 +717,10 @@ xfs_buf_read_uncached(
 		return NULL;
 
 	/* set up the buffer for a read IO */
-	XFS_BUF_SET_ADDR(bp, daddr);
-	XFS_BUF_READ(bp);
+	ASSERT(bp->b_map_count == 1);
+	bp->b_bn = daddr;
+	bp->b_maps[0].bm_bn = daddr;
+	bp->b_flags |= XBF_READ;
 
 	xfsbdstrat(target->bt_mount, bp);
 	error = xfs_buf_iowait(bp);
@@ -694,7 +748,11 @@ xfs_buf_set_empty(
 	bp->b_addr = NULL;
 	bp->b_length = numblks;
 	bp->b_io_length = numblks;
+
+	ASSERT(bp->b_map_count == 1);
 	bp->b_bn = XFS_BUF_DADDR_NULL;
+	bp->b_maps[0].bm_bn = XFS_BUF_DADDR_NULL;
+	bp->b_maps[0].bm_len = bp->b_length;
 }
 
 static inline struct page *
@@ -758,9 +816,10 @@ xfs_buf_get_uncached(
 {
 	unsigned long		page_count;
 	int			error, i;
-	xfs_buf_t		*bp;
+	struct xfs_buf		*bp;
+	DEFINE_SINGLE_BUF_MAP(map, XFS_BUF_DADDR_NULL, numblks);
 
-	bp = xfs_buf_alloc(target, XFS_BUF_DADDR_NULL, numblks, 0);
+	bp = _xfs_buf_alloc(target, &map, 1, 0);
 	if (unlikely(bp == NULL))
 		goto fail;
 
@@ -791,6 +850,7 @@ xfs_buf_get_uncached(
 		__free_page(bp->b_pages[i]);
 	_xfs_buf_free_pages(bp);
  fail_free_buf:
+	xfs_buf_free_maps(bp);
 	kmem_zone_free(xfs_buf_zone, bp);
  fail:
 	return NULL;
@@ -1144,36 +1204,39 @@ xfs_buf_bio_end_io(
 	bio_put(bio);
 }
 
-STATIC void
-_xfs_buf_ioapply(
-	xfs_buf_t		*bp)
+static void
+xfs_buf_ioapply_map(
+	struct xfs_buf	*bp,
+	int		map,
+	int		*buf_offset,
+	int		*count,
+	int		rw)
 {
-	int			rw, map_i, total_nr_pages, nr_pages;
-	struct bio		*bio;
-	int			offset = bp->b_offset;
-	int			size = BBTOB(bp->b_io_length);
-	sector_t		sector = bp->b_bn;
+	int		page_index;
+	int		total_nr_pages = bp->b_page_count;
+	int		nr_pages;
+	struct bio	*bio;
+	sector_t	sector =  bp->b_maps[map].bm_bn;
+	int		size;
+	int		offset;
 
 	total_nr_pages = bp->b_page_count;
-	map_i = 0;
 
-	if (bp->b_flags & XBF_WRITE) {
-		if (bp->b_flags & XBF_SYNCIO)
-			rw = WRITE_SYNC;
-		else
-			rw = WRITE;
-		if (bp->b_flags & XBF_FUA)
-			rw |= REQ_FUA;
-		if (bp->b_flags & XBF_FLUSH)
-			rw |= REQ_FLUSH;
-	} else if (bp->b_flags & XBF_READ_AHEAD) {
-		rw = READA;
-	} else {
-		rw = READ;
+	/* skip the pages in the buffer before the start offset */
+	page_index = 0;
+	offset = *buf_offset;
+	while (offset >= PAGE_SIZE) {
+		page_index++;
+		offset -= PAGE_SIZE;
 	}
 
-	/* we only use the buffer cache for meta-data */
-	rw |= REQ_META;
+	/*
+	 * Limit the IO size to the length of the current vector, and update the
+	 * remaining IO count for the next time around.
+	 */
+	size = min_t(int, BBTOB(bp->b_maps[map].bm_len), *count);
+	*count -= size;
+	*buf_offset += size;
 
 next_chunk:
 	atomic_inc(&bp->b_io_remaining);
@@ -1188,13 +1251,14 @@ next_chunk:
 	bio->bi_private = bp;
 
 
-	for (; size && nr_pages; nr_pages--, map_i++) {
+	for (; size && nr_pages; nr_pages--, page_index++) {
 		int	rbytes, nbytes = PAGE_SIZE - offset;
 
 		if (nbytes > size)
 			nbytes = size;
 
-		rbytes = bio_add_page(bio, bp->b_pages[map_i], nbytes, offset);
+		rbytes = bio_add_page(bio, bp->b_pages[page_index], nbytes,
+				      offset);
 		if (rbytes < nbytes)
 			break;
 
@@ -1216,6 +1280,54 @@ next_chunk:
 		xfs_buf_ioerror(bp, EIO);
 		bio_put(bio);
 	}
+
+}
+
+STATIC void
+_xfs_buf_ioapply(
+	struct xfs_buf	*bp)
+{
+	struct blk_plug	plug;
+	int		rw;
+	int		offset;
+	int		size;
+	int		i;
+
+	if (bp->b_flags & XBF_WRITE) {
+		if (bp->b_flags & XBF_SYNCIO)
+			rw = WRITE_SYNC;
+		else
+			rw = WRITE;
+		if (bp->b_flags & XBF_FUA)
+			rw |= REQ_FUA;
+		if (bp->b_flags & XBF_FLUSH)
+			rw |= REQ_FLUSH;
+	} else if (bp->b_flags & XBF_READ_AHEAD) {
+		rw = READA;
+	} else {
+		rw = READ;
+	}
+
+	/* we only use the buffer cache for meta-data */
+	rw |= REQ_META;
+
+	/*
+	 * Walk all the vectors issuing IO on them. Set up the initial offset
+	 * into the buffer and the desired IO size before we start -
+	 * _xfs_buf_ioapply_vec() will modify them appropriately for each
+	 * subsequent call.
+	 */
+	offset = bp->b_offset;
+	size = BBTOB(bp->b_io_length);
+	blk_start_plug(&plug);
+	for (i = 0; i < bp->b_map_count; i++) {
+		xfs_buf_ioapply_map(bp, i, &offset, &size, rw);
+		if (bp->b_error)
+			break;
+		if (size <= 0)
+			break;	/* all done */
+	}
+	blk_finish_plug(&plug);
 }
 
 void
@@ -1557,7 +1669,7 @@ xfs_buf_cmp(
 	struct xfs_buf	*bp = container_of(b, struct xfs_buf, b_list);
 	xfs_daddr_t		diff;
 
-	diff = ap->b_bn - bp->b_bn;
+	diff = ap->b_map.bm_bn - bp->b_map.bm_bn;
 	if (diff < 0)
 		return -1;
 	if (diff > 0)
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 79344c48008e..d03b73b9604e 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -58,6 +58,7 @@ typedef enum {
 #define _XBF_PAGES	(1 << 20)/* backed by refcounted pages */
 #define _XBF_KMEM	(1 << 21)/* backed by heap memory */
 #define _XBF_DELWRI_Q	(1 << 22)/* buffer on a delwri queue */
+#define _XBF_COMPOUND	(1 << 23)/* compound buffer */
 
 typedef unsigned int xfs_buf_flags_t;
 
@@ -75,7 +76,8 @@ typedef unsigned int xfs_buf_flags_t;
 	{ XBF_UNMAPPED,		"UNMAPPED" },	/* ditto */\
 	{ _XBF_PAGES,		"PAGES" }, \
 	{ _XBF_KMEM,		"KMEM" }, \
-	{ _XBF_DELWRI_Q,	"DELWRI_Q" }
+	{ _XBF_DELWRI_Q,	"DELWRI_Q" }, \
+	{ _XBF_COMPOUND,	"COMPOUND" }
 
 typedef struct xfs_buftarg {
 	dev_t			bt_dev;
@@ -98,6 +100,14 @@ typedef void (*xfs_buf_iodone_t)(struct xfs_buf *);
 
 #define XB_PAGES	2
 
+struct xfs_buf_map {
+	xfs_daddr_t		bm_bn;	/* block number for I/O */
+	int			bm_len;	/* size of I/O */
+};
+
+#define DEFINE_SINGLE_BUF_MAP(map, blkno, numblk) \
+	struct xfs_buf_map (map) = { .bm_bn = (blkno), .bm_len = (numblk) };
+
 typedef struct xfs_buf {
 	/*
 	 * first cacheline holds all the fields needed for an uncontended cache
@@ -107,7 +117,7 @@ typedef struct xfs_buf {
 	 * fast-path on locking.
 	 */
 	struct rb_node		b_rbnode;	/* rbtree node */
-	xfs_daddr_t		b_bn;		/* block number for I/O */
+	xfs_daddr_t		b_bn;		/* block number of buffer */
 	int			b_length;	/* size of buffer in BBs */
 	atomic_t		b_hold;		/* reference count */
 	atomic_t		b_lru_ref;	/* lru reclaim ref count */
@@ -127,12 +137,16 @@ typedef struct xfs_buf {
 	struct xfs_trans	*b_transp;
 	struct page		**b_pages;	/* array of page pointers */
 	struct page		*b_page_array[XB_PAGES]; /* inline pages */
+	struct xfs_buf_map	*b_maps;	/* compound buffer map */
+	struct xfs_buf_map	b_map;		/* inline compound buffer map */
+	int			b_map_count;
 	int			b_io_length;	/* IO size in BBs */
 	atomic_t		b_pin_count;	/* pin count */
 	atomic_t		b_io_remaining;	/* #outstanding I/O requests */
 	unsigned int		b_page_count;	/* size of page array */
 	unsigned int		b_offset;	/* page offset in first page */
 	unsigned short		b_error;	/* error code on I/O */
+
 #ifdef XFS_BUF_LOCK_TRACKING
 	int			b_last_holder;
 #endif
@@ -140,22 +154,78 @@ typedef struct xfs_buf {
 
 
 /* Finding and Reading Buffers */
-struct xfs_buf *_xfs_buf_find(struct xfs_buftarg *target, xfs_daddr_t blkno,
-				size_t numblks, xfs_buf_flags_t flags,
-				struct xfs_buf *new_bp);
-#define xfs_incore(buftarg,blkno,len,lockit) \
-	_xfs_buf_find(buftarg, blkno ,len, lockit, NULL)
-
-struct xfs_buf *xfs_buf_get(struct xfs_buftarg *target, xfs_daddr_t blkno,
-				size_t numblks, xfs_buf_flags_t flags);
-struct xfs_buf *xfs_buf_read(struct xfs_buftarg *target, xfs_daddr_t blkno,
-				size_t numblks, xfs_buf_flags_t flags);
-void xfs_buf_readahead(struct xfs_buftarg *target, xfs_daddr_t blkno,
-				size_t numblks);
+struct xfs_buf *_xfs_buf_find(struct xfs_buftarg *target,
+			      struct xfs_buf_map *map, int nmaps,
+			      xfs_buf_flags_t flags, struct xfs_buf *new_bp);
+
+static inline struct xfs_buf *
+xfs_incore(
+	struct xfs_buftarg	*target,
+	xfs_daddr_t		blkno,
+	size_t			numblks,
+	xfs_buf_flags_t		flags)
+{
+	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
+	return _xfs_buf_find(target, &map, 1, flags, NULL);
+}
+
+struct xfs_buf *_xfs_buf_alloc(struct xfs_buftarg *target,
+			       struct xfs_buf_map *map, int nmaps,
+			       xfs_buf_flags_t flags);
+
+static inline struct xfs_buf *
+xfs_buf_alloc(
+	struct xfs_buftarg	*target,
+	xfs_daddr_t		blkno,
+	size_t			numblks,
+	xfs_buf_flags_t		flags)
+{
+	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
+	return _xfs_buf_alloc(target, &map, 1, flags);
+}
+
+struct xfs_buf *xfs_buf_get_map(struct xfs_buftarg *target,
+			       struct xfs_buf_map *map, int nmaps,
+			       xfs_buf_flags_t flags);
+struct xfs_buf *xfs_buf_read_map(struct xfs_buftarg *target,
+			       struct xfs_buf_map *map, int nmaps,
+			       xfs_buf_flags_t flags);
+void xfs_buf_readahead_map(struct xfs_buftarg *target,
+			       struct xfs_buf_map *map, int nmaps);
+
+static inline struct xfs_buf *
+xfs_buf_get(
+	struct xfs_buftarg	*target,
+	xfs_daddr_t		blkno,
+	size_t			numblks,
+	xfs_buf_flags_t		flags)
+{
+	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
+	return xfs_buf_get_map(target, &map, 1, flags);
+}
+
+static inline struct xfs_buf *
+xfs_buf_read(
+	struct xfs_buftarg	*target,
+	xfs_daddr_t		blkno,
+	size_t			numblks,
+	xfs_buf_flags_t		flags)
+{
+	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
+	return xfs_buf_read_map(target, &map, 1, flags);
+}
+
+static inline void
+xfs_buf_readahead(
+	struct xfs_buftarg	*target,
+	xfs_daddr_t		blkno,
+	size_t			numblks)
+{
+	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
+	return xfs_buf_readahead_map(target, &map, 1);
+}
 
 struct xfs_buf *xfs_buf_get_empty(struct xfs_buftarg *target, size_t numblks);
-struct xfs_buf *xfs_buf_alloc(struct xfs_buftarg *target, xfs_daddr_t blkno,
-				size_t numblks, xfs_buf_flags_t flags);
 void xfs_buf_set_empty(struct xfs_buf *bp, size_t numblks);
 int xfs_buf_associate_memory(struct xfs_buf *bp, void *mem, size_t length);
 
@@ -232,8 +302,18 @@ void xfs_buf_stale(struct xfs_buf *bp);
 #define XFS_BUF_UNWRITE(bp)	((bp)->b_flags &= ~XBF_WRITE)
 #define XFS_BUF_ISWRITE(bp)	((bp)->b_flags & XBF_WRITE)
 
-#define XFS_BUF_ADDR(bp)		((bp)->b_bn)
-#define XFS_BUF_SET_ADDR(bp, bno)	((bp)->b_bn = (xfs_daddr_t)(bno))
+/*
+ * 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
+ * anymore, uncached buffers do not use b_bn at all and hence must modify the IO
+ * map directly. Uncached buffers are not allowed to be discontiguous, so this
+ * is safe to do.
+ *
+ * In future, uncached buffers will pass the block number directly to the io
+ * request function and hence these macros will go away at that point.
+ */
+#define XFS_BUF_ADDR(bp)		((bp)->b_map.bm_bn)
+#define XFS_BUF_SET_ADDR(bp, bno)	((bp)->b_map.bm_bn = (xfs_daddr_t)(bno))
 
 static inline void xfs_buf_set_ref(struct xfs_buf *bp, int lru_ref)
 {
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index d9e451115f98..a8d0ed911196 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -153,33 +153,25 @@ STATIC void	xfs_buf_do_callbacks(struct xfs_buf *bp);
  * If the XFS_BLI_STALE flag has been set, then log nothing.
  */
 STATIC uint
-xfs_buf_item_size(
-	struct xfs_log_item	*lip)
+xfs_buf_item_size_segment(
+	struct xfs_buf_log_item	*bip,
+	struct xfs_buf_log_format *blfp)
 {
-	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
 	struct xfs_buf		*bp = bip->bli_buf;
 	uint			nvecs;
 	int			next_bit;
 	int			last_bit;
 
-	ASSERT(atomic_read(&bip->bli_refcount) > 0);
-	if (bip->bli_flags & XFS_BLI_STALE) {
-		/*
-		 * The buffer is stale, so all we need to log
-		 * is the buf log format structure with the
-		 * cancel flag in it.
-		 */
-		trace_xfs_buf_item_size_stale(bip);
-		ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
-		return 1;
-	}
+	last_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
+	if (last_bit == -1)
+		return 0;
+
+	/*
+	 * initial count for a dirty buffer is 2 vectors - the format structure
+	 * and the first dirty region.
+	 */
+	nvecs = 2;
 
-	ASSERT(bip->bli_flags & XFS_BLI_LOGGED);
-	nvecs = 1;
-	last_bit = xfs_next_bit(bip->bli_format.blf_data_map,
-					 bip->bli_format.blf_map_size, 0);
-	ASSERT(last_bit != -1);
-	nvecs++;
 	while (last_bit != -1) {
 		/*
 		 * This takes the bit number to start looking from and
@@ -187,16 +179,15 @@ xfs_buf_item_size(
 		 * if there are no more bits set or the start bit is
 		 * beyond the end of the bitmap.
 		 */
-		next_bit = xfs_next_bit(bip->bli_format.blf_data_map,
-						 bip->bli_format.blf_map_size,
-						 last_bit + 1);
+		next_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
+					last_bit + 1);
 		/*
 		 * If we run out of bits, leave the loop,
 		 * else if we find a new set of bits bump the number of vecs,
 		 * else keep scanning the current set of bits.
 		 */
 		if (next_bit == -1) {
-			last_bit = -1;
+			break;
 		} else if (next_bit != last_bit + 1) {
 			last_bit = next_bit;
 			nvecs++;
@@ -210,22 +201,73 @@ xfs_buf_item_size(
 		}
 	}
 
-	trace_xfs_buf_item_size(bip);
 	return nvecs;
 }
 
 /*
- * This is called to fill in the vector of log iovecs for the
- * given log buf item.  It fills the first entry with a buf log
- * format structure, and the rest point to contiguous chunks
- * within the buffer.
+ * This returns the number of log iovecs needed to log the given buf log item.
+ *
+ * It calculates this as 1 iovec for the buf log format structure and 1 for each
+ * stretch of non-contiguous chunks to be logged.  Contiguous chunks are logged
+ * in a single iovec.
+ *
+ * Discontiguous buffers need a format structure per region that that is being
+ * logged. This makes the changes in the buffer appear to log recovery as though
+ * they came from separate buffers, just like would occur if multiple buffers
+ * were used instead of a single discontiguous buffer. This enables
+ * discontiguous buffers to be in-memory constructs, completely transparent to
+ * what ends up on disk.
+ *
+ * If the XFS_BLI_STALE flag has been set, then log nothing but the buf log
+ * format structures.
  */
-STATIC void
-xfs_buf_item_format(
-	struct xfs_log_item	*lip,
-	struct xfs_log_iovec	*vecp)
+STATIC uint
+xfs_buf_item_size(
+	struct xfs_log_item	*lip)
 {
 	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
+	uint			nvecs;
+	int			i;
+
+	ASSERT(atomic_read(&bip->bli_refcount) > 0);
+	if (bip->bli_flags & XFS_BLI_STALE) {
+		/*
+		 * The buffer is stale, so all we need to log
+		 * is the buf log format structure with the
+		 * cancel flag in it.
+		 */
+		trace_xfs_buf_item_size_stale(bip);
+		ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
+		return bip->bli_format_count;
+	}
+
+	ASSERT(bip->bli_flags & XFS_BLI_LOGGED);
+
+	/*
+	 * the vector count is based on the number of buffer vectors we have
+	 * dirty bits in. This will only be greater than one when we have a
+	 * compound buffer with more than one segment dirty. Hence for compound
+	 * buffers we need to track which segment the dirty bits correspond to,
+	 * and when we move from one segment to the next increment the vector
+	 * count for the extra buf log format structure that will need to be
+	 * written.
+	 */
+	nvecs = 0;
+	for (i = 0; i < bip->bli_format_count; i++) {
+		nvecs += xfs_buf_item_size_segment(bip, &bip->bli_formats[i]);
+	}
+
+	trace_xfs_buf_item_size(bip);
+	return nvecs;
+}
+
+static struct xfs_log_iovec *
+xfs_buf_item_format_segment(
+	struct xfs_buf_log_item	*bip,
+	struct xfs_log_iovec	*vecp,
+	uint			offset,
+	struct xfs_buf_log_format *blfp)
+{
 	struct xfs_buf	*bp = bip->bli_buf;
 	uint		base_size;
 	uint		nvecs;
@@ -235,40 +277,22 @@ xfs_buf_item_format(
 	uint		nbits;
 	uint		buffer_offset;
 
-	ASSERT(atomic_read(&bip->bli_refcount) > 0);
-	ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
-	       (bip->bli_flags & XFS_BLI_STALE));
+	/* copy the flags across from the base format item */
+	blfp->blf_flags = bip->bli_format.blf_flags;
 
 	/*
-	 * The size of the base structure is the size of the
-	 * declared structure plus the space for the extra words
-	 * of the bitmap.  We subtract one from the map size, because
-	 * the first element of the bitmap is accounted for in the
-	 * size of the base structure.
+	 * Base size is the actual size of the ondisk structure - it reflects
+	 * the actual size of the dirty bitmap rather than the size of the in
+	 * memory structure.
 	 */
-	base_size =
-		(uint)(sizeof(xfs_buf_log_format_t) +
-		       ((bip->bli_format.blf_map_size - 1) * sizeof(uint)));
-	vecp->i_addr = &bip->bli_format;
+	base_size = offsetof(struct xfs_buf_log_format, blf_data_map) +
+			(blfp->blf_map_size * sizeof(blfp->blf_data_map[0]));
+	vecp->i_addr = blfp;
 	vecp->i_len = base_size;
 	vecp->i_type = XLOG_REG_TYPE_BFORMAT;
 	vecp++;
 	nvecs = 1;
 
-	/*
-	 * If it is an inode buffer, transfer the in-memory state to the
-	 * format flags and clear the in-memory state. We do not transfer
-	 * this state if the inode buffer allocation has not yet been committed
-	 * to the log as setting the XFS_BLI_INODE_BUF flag will prevent
-	 * correct replay of the inode allocation.
-	 */
-	if (bip->bli_flags & XFS_BLI_INODE_BUF) {
-		if (!((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) &&
-		      xfs_log_item_in_current_chkpt(lip)))
-			bip->bli_format.blf_flags |= XFS_BLF_INODE_BUF;
-		bip->bli_flags &= ~XFS_BLI_INODE_BUF;
-	}
-
 	if (bip->bli_flags & XFS_BLI_STALE) {
 		/*
 		 * The buffer is stale, so all we need to log
@@ -276,16 +300,15 @@ xfs_buf_item_format(
 		 * cancel flag in it.
 		 */
 		trace_xfs_buf_item_format_stale(bip);
-		ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
-		bip->bli_format.blf_size = nvecs;
-		return;
+		ASSERT(blfp->blf_flags & XFS_BLF_CANCEL);
+		blfp->blf_size = nvecs;
+		return vecp;
 	}
 
 	/*
 	 * Fill in an iovec for each set of contiguous chunks.
 	 */
-	first_bit = xfs_next_bit(bip->bli_format.blf_data_map,
-					 bip->bli_format.blf_map_size, 0);
+	first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
 	ASSERT(first_bit != -1);
 	last_bit = first_bit;
 	nbits = 1;
@@ -296,9 +319,8 @@ xfs_buf_item_format(
 		 * if there are no more bits set or the start bit is
 		 * beyond the end of the bitmap.
 		 */
-		next_bit = xfs_next_bit(bip->bli_format.blf_data_map,
-						 bip->bli_format.blf_map_size,
-						 (uint)last_bit + 1);
+		next_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
+					(uint)last_bit + 1);
 		/*
 		 * If we run out of bits fill in the last iovec and get
 		 * out of the loop.
@@ -309,14 +331,14 @@ xfs_buf_item_format(
 		 * keep counting and scanning.
 		 */
 		if (next_bit == -1) {
-			buffer_offset = first_bit * XFS_BLF_CHUNK;
+			buffer_offset = offset + first_bit * XFS_BLF_CHUNK;
 			vecp->i_addr = xfs_buf_offset(bp, buffer_offset);
 			vecp->i_len = nbits * XFS_BLF_CHUNK;
 			vecp->i_type = XLOG_REG_TYPE_BCHUNK;
 			nvecs++;
 			break;
 		} else if (next_bit != last_bit + 1) {
-			buffer_offset = first_bit * XFS_BLF_CHUNK;
+			buffer_offset = offset + first_bit * XFS_BLF_CHUNK;
 			vecp->i_addr = xfs_buf_offset(bp, buffer_offset);
 			vecp->i_len = nbits * XFS_BLF_CHUNK;
 			vecp->i_type = XLOG_REG_TYPE_BCHUNK;
@@ -325,14 +347,17 @@ xfs_buf_item_format(
 			first_bit = next_bit;
 			last_bit = next_bit;
 			nbits = 1;
-		} else if (xfs_buf_offset(bp, next_bit << XFS_BLF_SHIFT) !=
-			   (xfs_buf_offset(bp, last_bit << XFS_BLF_SHIFT) +
+		} else if (xfs_buf_offset(bp, offset +
+					      (next_bit << XFS_BLF_SHIFT)) !=
+			   (xfs_buf_offset(bp, offset +
+					       (last_bit << XFS_BLF_SHIFT)) +
 			    XFS_BLF_CHUNK)) {
-			buffer_offset = first_bit * XFS_BLF_CHUNK;
+			buffer_offset = offset + first_bit * XFS_BLF_CHUNK;
 			vecp->i_addr = xfs_buf_offset(bp, buffer_offset);
 			vecp->i_len = nbits * XFS_BLF_CHUNK;
 			vecp->i_type = XLOG_REG_TYPE_BCHUNK;
-/* You would think we need to bump the nvecs here too, but we do not
+/*
+ * You would think we need to bump the nvecs here too, but we do not
  * this number is used by recovery, and it gets confused by the boundary
  * split here
  *			nvecs++;
@@ -347,6 +372,48 @@ xfs_buf_item_format(
 		}
 	}
 	bip->bli_format.blf_size = nvecs;
+	return vecp;
+}
+
+/*
+ * This is called to fill in the vector of log iovecs for the
+ * given log buf item.  It fills the first entry with a buf log
+ * format structure, and the rest point to contiguous chunks
+ * within the buffer.
+ */
+STATIC void
+xfs_buf_item_format(
+	struct xfs_log_item	*lip,
+	struct xfs_log_iovec	*vecp)
+{
+	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
+	struct xfs_buf		*bp = bip->bli_buf;
+	uint			offset = 0;
+	int			i;
+
+	ASSERT(atomic_read(&bip->bli_refcount) > 0);
+	ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
+	       (bip->bli_flags & XFS_BLI_STALE));
+
+	/*
+	 * If it is an inode buffer, transfer the in-memory state to the
+	 * format flags and clear the in-memory state. We do not transfer
+	 * this state if the inode buffer allocation has not yet been committed
+	 * to the log as setting the XFS_BLI_INODE_BUF flag will prevent
+	 * correct replay of the inode allocation.
+	 */
+	if (bip->bli_flags & XFS_BLI_INODE_BUF) {
+		if (!((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) &&
+		      xfs_log_item_in_current_chkpt(lip)))
+			bip->bli_format.blf_flags |= XFS_BLF_INODE_BUF;
+		bip->bli_flags &= ~XFS_BLI_INODE_BUF;
+	}
+
+	for (i = 0; i < bip->bli_format_count; i++) {
+		vecp = xfs_buf_item_format_segment(bip, vecp, offset,
+						&bip->bli_formats[i]);
+		offset += bp->b_maps[i].bm_len;
+	}
 
 	/*
 	 * Check to make sure everything is consistent.
@@ -622,6 +689,35 @@ static const struct xfs_item_ops xfs_buf_item_ops = {
 	.iop_committing = xfs_buf_item_committing
 };
 
+STATIC int
+xfs_buf_item_get_format(
+	struct xfs_buf_log_item	*bip,
+	int			count)
+{
+	ASSERT(bip->bli_formats == NULL);
+	bip->bli_format_count = count;
+
+	if (count == 1) {
+		bip->bli_formats = &bip->bli_format;
+		return 0;
+	}
+
+	bip->bli_formats = kmem_zalloc(count * sizeof(struct xfs_buf_log_format),
+				KM_SLEEP);
+	if (!bip->bli_formats)
+		return ENOMEM;
+	return 0;
+}
+
+STATIC void
+xfs_buf_item_free_format(
+	struct xfs_buf_log_item	*bip)
+{
+	if (bip->bli_formats != &bip->bli_format) {
+		kmem_free(bip->bli_formats);
+		bip->bli_formats = NULL;
+	}
+}
 
 /*
  * Allocate a new buf log item to go with the given buffer.
@@ -639,6 +735,8 @@ xfs_buf_item_init(
 	xfs_buf_log_item_t	*bip;
 	int			chunks;
 	int			map_size;
+	int			error;
+	int			i;
 
 	/*
 	 * Check to see if there is already a buf log item for
@@ -650,25 +748,33 @@ xfs_buf_item_init(
 	if (lip != NULL && lip->li_type == XFS_LI_BUF)
 		return;
 
-	/*
-	 * chunks is the number of XFS_BLF_CHUNK size pieces
-	 * the buffer can be divided into. Make sure not to
-	 * truncate any pieces.  map_size is the size of the
-	 * bitmap needed to describe the chunks of the buffer.
-	 */
-	chunks = (int)((BBTOB(bp->b_length) + (XFS_BLF_CHUNK - 1)) >>
-								XFS_BLF_SHIFT);
-	map_size = (int)((chunks + NBWORD) >> BIT_TO_WORD_SHIFT);
-
-	bip = (xfs_buf_log_item_t*)kmem_zone_zalloc(xfs_buf_item_zone,
-						    KM_SLEEP);
+	bip = kmem_zone_zalloc(xfs_buf_item_zone, KM_SLEEP);
 	xfs_log_item_init(mp, &bip->bli_item, XFS_LI_BUF, &xfs_buf_item_ops);
 	bip->bli_buf = bp;
 	xfs_buf_hold(bp);
-	bip->bli_format.blf_type = XFS_LI_BUF;
-	bip->bli_format.blf_blkno = (__int64_t)XFS_BUF_ADDR(bp);
-	bip->bli_format.blf_len = (ushort)bp->b_length;
-	bip->bli_format.blf_map_size = map_size;
+
+	/*
+	 * chunks is the number of XFS_BLF_CHUNK size pieces the buffer
+	 * can be divided into. Make sure not to truncate any pieces.
+	 * map_size is the size of the bitmap needed to describe the
+	 * chunks of the buffer.
+	 *
+	 * Discontiguous buffer support follows the layout of the underlying
+	 * buffer. This makes the implementation as simple as possible.
+	 */
+	error = xfs_buf_item_get_format(bip, bp->b_map_count);
+	ASSERT(error == 0);
+
+	for (i = 0; i < bip->bli_format_count; i++) {
+		chunks = DIV_ROUND_UP(BBTOB(bp->b_maps[i].bm_len),
+				      XFS_BLF_CHUNK);
+		map_size = DIV_ROUND_UP(chunks, NBWORD);
+
+		bip->bli_formats[i].blf_type = XFS_LI_BUF;
+		bip->bli_formats[i].blf_blkno = bp->b_maps[i].bm_bn;
+		bip->bli_formats[i].blf_len = bp->b_maps[i].bm_len;
+		bip->bli_formats[i].blf_map_size = map_size;
+	}
 
 #ifdef XFS_TRANS_DEBUG
 	/*
@@ -699,10 +805,11 @@ xfs_buf_item_init(
  * item's bitmap.
  */
 void
-xfs_buf_item_log(
-	xfs_buf_log_item_t	*bip,
+xfs_buf_item_log_segment(
+	struct xfs_buf_log_item	*bip,
 	uint			first,
-	uint			last)
+	uint			last,
+	uint			*map)
 {
 	uint		first_bit;
 	uint		last_bit;
@@ -715,12 +822,6 @@ xfs_buf_item_log(
 	uint		mask;
 
 	/*
-	 * Mark the item as having some dirty data for
-	 * quick reference in xfs_buf_item_dirty.
-	 */
-	bip->bli_flags |= XFS_BLI_DIRTY;
-
-	/*
 	 * Convert byte offsets to bit numbers.
 	 */
 	first_bit = first >> XFS_BLF_SHIFT;
@@ -736,7 +837,7 @@ xfs_buf_item_log(
 	 * to set a bit in.
 	 */
 	word_num = first_bit >> BIT_TO_WORD_SHIFT;
-	wordp = &(bip->bli_format.blf_data_map[word_num]);
+	wordp = &map[word_num];
 
 	/*
 	 * Calculate the starting bit in the first word.
@@ -783,6 +884,51 @@ xfs_buf_item_log(
 	xfs_buf_item_log_debug(bip, first, last);
 }
 
+/*
+ * Mark bytes first through last inclusive as dirty in the buf
+ * item's bitmap.
+ */
+void
+xfs_buf_item_log(
+	xfs_buf_log_item_t	*bip,
+	uint			first,
+	uint			last)
+{
+	int			i;
+	uint			start;
+	uint			end;
+	struct xfs_buf		*bp = bip->bli_buf;
+
+	/*
+	 * Mark the item as having some dirty data for
+	 * quick reference in xfs_buf_item_dirty.
+	 */
+	bip->bli_flags |= XFS_BLI_DIRTY;
+
+	/*
+	 * walk each buffer segment and mark them dirty appropriately.
+	 */
+	start = 0;
+	for (i = 0; i < bip->bli_format_count; i++) {
+		if (start > last)
+			break;
+		end = start + BBTOB(bp->b_maps[i].bm_len);
+		if (first > end) {
+			start += BBTOB(bp->b_maps[i].bm_len);
+			continue;
+		}
+		if (first < start)
+			first = start;
+		if (end > last)
+			end = last;
+
+		xfs_buf_item_log_segment(bip, first, end,
+					 &bip->bli_formats[i].blf_data_map[0]);
+
+		start += bp->b_maps[i].bm_len;
+	}
+}
+
 
 /*
  * Return 1 if the buffer has some data that has been logged (at any
@@ -804,6 +950,7 @@ xfs_buf_item_free(
 	kmem_free(bip->bli_logged);
 #endif /* XFS_TRANS_DEBUG */
 
+	xfs_buf_item_free_format(bip);
 	kmem_zone_free(xfs_buf_item_zone, bip);
 }
 
diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h
index b6ecd2061e7c..6850f49f4af3 100644
--- a/fs/xfs/xfs_buf_item.h
+++ b/fs/xfs/xfs_buf_item.h
@@ -21,23 +21,6 @@
 extern kmem_zone_t	*xfs_buf_item_zone;
 
 /*
- * This is the structure used to lay out a buf log item in the
- * log.  The data map describes which 128 byte chunks of the buffer
- * have been logged.
- * For 6.2 and beyond, this is XFS_LI_BUF.  We use this to log everything.
- */
-typedef struct xfs_buf_log_format {
-	unsigned short	blf_type;	/* buf log item type indicator */
-	unsigned short	blf_size;	/* size of this item */
-	ushort		blf_flags;	/* misc state */
-	ushort		blf_len;	/* number of blocks in this buf */
-	__int64_t	blf_blkno;	/* starting blkno of this buf */
-	unsigned int	blf_map_size;	/* size of data bitmap in words */
-	unsigned int	blf_data_map[1];/* variable size bitmap of */
-					/*   regions of buffer in this item */
-} xfs_buf_log_format_t;
-
-/*
  * This flag indicates that the buffer contains on disk inodes
  * and requires special recovery handling.
  */
@@ -61,6 +44,23 @@ typedef struct xfs_buf_log_format {
 #define	NBWORD			(NBBY * sizeof(unsigned int))
 
 /*
+ * This is the structure used to lay out a buf log item in the
+ * log.  The data map describes which 128 byte chunks of the buffer
+ * have been logged.
+ */
+#define XFS_BLF_DATAMAP_SIZE	((XFS_MAX_BLOCKSIZE / XFS_BLF_CHUNK) / NBWORD)
+
+typedef struct xfs_buf_log_format {
+	unsigned short	blf_type;	/* buf log item type indicator */
+	unsigned short	blf_size;	/* size of this item */
+	ushort		blf_flags;	/* misc state */
+	ushort		blf_len;	/* number of blocks in this buf */
+	__int64_t	blf_blkno;	/* starting blkno of this buf */
+	unsigned int	blf_map_size;	/* used size of data bitmap in words */
+	unsigned int	blf_data_map[XFS_BLF_DATAMAP_SIZE]; /* dirty bitmap */
+} xfs_buf_log_format_t;
+
+/*
  * buf log item flags
  */
 #define	XFS_BLI_HOLD		0x01
@@ -102,7 +102,9 @@ typedef struct xfs_buf_log_item {
 	char			*bli_orig;	/* original buffer copy */
 	char			*bli_logged;	/* bytes logged (bitmap) */
 #endif
-	xfs_buf_log_format_t	bli_format;	/* in-log header */
+	int			bli_format_count;	/* count of headers */
+	struct xfs_buf_log_format *bli_formats;	/* array of in-log header ptrs */
+	struct xfs_buf_log_format bli_format;	/* embedded in-log header */
 } xfs_buf_log_item_t;
 
 void	xfs_buf_item_init(struct xfs_buf *, struct xfs_mount *);
diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
index 015b946c5808..7bfb7dd334fc 100644
--- a/fs/xfs/xfs_da_btree.c
+++ b/fs/xfs/xfs_da_btree.c
@@ -83,9 +83,9 @@ STATIC void xfs_da_node_unbalance(xfs_da_state_t *state,
 /*
  * Utility routines.
  */
-STATIC uint	xfs_da_node_lasthash(xfs_dabuf_t *bp, int *count);
-STATIC int	xfs_da_node_order(xfs_dabuf_t *node1_bp, xfs_dabuf_t *node2_bp);
-STATIC xfs_dabuf_t *xfs_da_buf_make(int nbuf, xfs_buf_t **bps);
+STATIC uint	xfs_da_node_lasthash(struct xfs_buf *bp, int *count);
+STATIC int	xfs_da_node_order(struct xfs_buf *node1_bp,
+				  struct xfs_buf *node2_bp);
 STATIC int	xfs_da_blk_unlink(xfs_da_state_t *state,
 				  xfs_da_state_blk_t *drop_blk,
 				  xfs_da_state_blk_t *save_blk);
@@ -100,10 +100,10 @@ STATIC void	xfs_da_state_kill_altpath(xfs_da_state_t *state);
  */
 int
 xfs_da_node_create(xfs_da_args_t *args, xfs_dablk_t blkno, int level,
-				 xfs_dabuf_t **bpp, int whichfork)
+				 struct xfs_buf **bpp, int whichfork)
 {
 	xfs_da_intnode_t *node;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error;
 	xfs_trans_t *tp;
 
@@ -114,7 +114,7 @@ xfs_da_node_create(xfs_da_args_t *args, xfs_dablk_t blkno, int level,
 	if (error)
 		return(error);
 	ASSERT(bp != NULL);
-	node = bp->data;
+	node = bp->b_addr;
 	node->hdr.info.forw = 0;
 	node->hdr.info.back = 0;
 	node->hdr.info.magic = cpu_to_be16(XFS_DA_NODE_MAGIC);
@@ -122,7 +122,7 @@ xfs_da_node_create(xfs_da_args_t *args, xfs_dablk_t blkno, int level,
 	node->hdr.count = 0;
 	node->hdr.level = cpu_to_be16(level);
 
-	xfs_da_log_buf(tp, bp,
+	xfs_trans_log_buf(tp, bp,
 		XFS_DA_LOGRANGE(node, &node->hdr, sizeof(node->hdr)));
 
 	*bpp = bp;
@@ -138,7 +138,7 @@ xfs_da_split(xfs_da_state_t *state)
 {
 	xfs_da_state_blk_t *oldblk, *newblk, *addblk;
 	xfs_da_intnode_t *node;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int max, action, error, i;
 
 	trace_xfs_da_split(state->args);
@@ -203,7 +203,6 @@ xfs_da_split(xfs_da_state_t *state)
 		case XFS_DA_NODE_MAGIC:
 			error = xfs_da_node_split(state, oldblk, newblk, addblk,
 							 max - i, &action);
-			xfs_da_buf_done(addblk->bp);
 			addblk->bp = NULL;
 			if (error)
 				return(error);	/* GROT: dir is inconsistent */
@@ -221,13 +220,6 @@ xfs_da_split(xfs_da_state_t *state)
 		 * Update the btree to show the new hashval for this child.
 		 */
 		xfs_da_fixhashpath(state, &state->path);
-		/*
-		 * If we won't need this block again, it's getting dropped
-		 * from the active path by the loop control, so we need
-		 * to mark it done now.
-		 */
-		if (i > 0 || !addblk)
-			xfs_da_buf_done(oldblk->bp);
 	}
 	if (!addblk)
 		return(0);
@@ -239,8 +231,6 @@ xfs_da_split(xfs_da_state_t *state)
 	oldblk = &state->path.blk[0];
 	error = xfs_da_root_split(state, oldblk, addblk);
 	if (error) {
-		xfs_da_buf_done(oldblk->bp);
-		xfs_da_buf_done(addblk->bp);
 		addblk->bp = NULL;
 		return(error);	/* GROT: dir is inconsistent */
 	}
@@ -252,7 +242,7 @@ xfs_da_split(xfs_da_state_t *state)
 	 * and the original block 0 could be at any position in the list.
 	 */
 
-	node = oldblk->bp->data;
+	node = oldblk->bp->b_addr;
 	if (node->hdr.info.forw) {
 		if (be32_to_cpu(node->hdr.info.forw) == addblk->blkno) {
 			bp = addblk->bp;
@@ -260,13 +250,13 @@ xfs_da_split(xfs_da_state_t *state)
 			ASSERT(state->extravalid);
 			bp = state->extrablk.bp;
 		}
-		node = bp->data;
+		node = bp->b_addr;
 		node->hdr.info.back = cpu_to_be32(oldblk->blkno);
-		xfs_da_log_buf(state->args->trans, bp,
+		xfs_trans_log_buf(state->args->trans, bp,
 		    XFS_DA_LOGRANGE(node, &node->hdr.info,
 		    sizeof(node->hdr.info)));
 	}
-	node = oldblk->bp->data;
+	node = oldblk->bp->b_addr;
 	if (node->hdr.info.back) {
 		if (be32_to_cpu(node->hdr.info.back) == addblk->blkno) {
 			bp = addblk->bp;
@@ -274,14 +264,12 @@ xfs_da_split(xfs_da_state_t *state)
 			ASSERT(state->extravalid);
 			bp = state->extrablk.bp;
 		}
-		node = bp->data;
+		node = bp->b_addr;
 		node->hdr.info.forw = cpu_to_be32(oldblk->blkno);
-		xfs_da_log_buf(state->args->trans, bp,
+		xfs_trans_log_buf(state->args->trans, bp,
 		    XFS_DA_LOGRANGE(node, &node->hdr.info,
 		    sizeof(node->hdr.info)));
 	}
-	xfs_da_buf_done(oldblk->bp);
-	xfs_da_buf_done(addblk->bp);
 	addblk->bp = NULL;
 	return(0);
 }
@@ -298,7 +286,7 @@ xfs_da_root_split(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 	xfs_da_intnode_t *node, *oldroot;
 	xfs_da_args_t *args;
 	xfs_dablk_t blkno;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error, size;
 	xfs_inode_t *dp;
 	xfs_trans_t *tp;
@@ -323,8 +311,8 @@ xfs_da_root_split(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 	if (error)
 		return(error);
 	ASSERT(bp != NULL);
-	node = bp->data;
-	oldroot = blk1->bp->data;
+	node = bp->b_addr;
+	oldroot = blk1->bp->b_addr;
 	if (oldroot->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC)) {
 		size = (int)((char *)&oldroot->btree[be16_to_cpu(oldroot->hdr.count)] -
 			     (char *)oldroot);
@@ -335,8 +323,7 @@ xfs_da_root_split(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 			     (char *)leaf);
 	}
 	memcpy(node, oldroot, size);
-	xfs_da_log_buf(tp, bp, 0, size - 1);
-	xfs_da_buf_done(blk1->bp);
+	xfs_trans_log_buf(tp, bp, 0, size - 1);
 	blk1->bp = bp;
 	blk1->blkno = blkno;
 
@@ -348,7 +335,7 @@ xfs_da_root_split(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 		be16_to_cpu(node->hdr.level) + 1, &bp, args->whichfork);
 	if (error)
 		return(error);
-	node = bp->data;
+	node = bp->b_addr;
 	node->btree[0].hashval = cpu_to_be32(blk1->hashval);
 	node->btree[0].before = cpu_to_be32(blk1->blkno);
 	node->btree[1].hashval = cpu_to_be32(blk2->hashval);
@@ -365,10 +352,9 @@ xfs_da_root_split(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 #endif
 
 	/* Header is already logged by xfs_da_node_create */
-	xfs_da_log_buf(tp, bp,
+	xfs_trans_log_buf(tp, bp,
 		XFS_DA_LOGRANGE(node, node->btree,
 			sizeof(xfs_da_node_entry_t) * 2));
-	xfs_da_buf_done(bp);
 
 	return(0);
 }
@@ -389,7 +375,7 @@ xfs_da_node_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
 
 	trace_xfs_da_node_split(state->args);
 
-	node = oldblk->bp->data;
+	node = oldblk->bp->b_addr;
 	ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 
 	/*
@@ -436,7 +422,7 @@ xfs_da_node_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
 	 *
 	 * If we had double-split op below us, then add the extra block too.
 	 */
-	node = oldblk->bp->data;
+	node = oldblk->bp->b_addr;
 	if (oldblk->index <= be16_to_cpu(node->hdr.count)) {
 		oldblk->index++;
 		xfs_da_node_add(state, oldblk, addblk);
@@ -477,8 +463,8 @@ xfs_da_node_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 
 	trace_xfs_da_node_rebalance(state->args);
 
-	node1 = blk1->bp->data;
-	node2 = blk2->bp->data;
+	node1 = blk1->bp->b_addr;
+	node2 = blk2->bp->b_addr;
 	/*
 	 * Figure out how many entries need to move, and in which direction.
 	 * Swap the nodes around if that makes it simpler.
@@ -532,7 +518,7 @@ xfs_da_node_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 		btree_d = &node1->btree[be16_to_cpu(node1->hdr.count)];
 		memcpy(btree_d, btree_s, tmp);
 		be16_add_cpu(&node1->hdr.count, count);
-		xfs_da_log_buf(tp, blk1->bp,
+		xfs_trans_log_buf(tp, blk1->bp,
 			XFS_DA_LOGRANGE(node1, btree_d, tmp));
 
 		/*
@@ -549,9 +535,9 @@ xfs_da_node_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 	/*
 	 * Log header of node 1 and all current bits of node 2.
 	 */
-	xfs_da_log_buf(tp, blk1->bp,
+	xfs_trans_log_buf(tp, blk1->bp,
 		XFS_DA_LOGRANGE(node1, &node1->hdr, sizeof(node1->hdr)));
-	xfs_da_log_buf(tp, blk2->bp,
+	xfs_trans_log_buf(tp, blk2->bp,
 		XFS_DA_LOGRANGE(node2, &node2->hdr,
 			sizeof(node2->hdr) +
 			sizeof(node2->btree[0]) * be16_to_cpu(node2->hdr.count)));
@@ -560,8 +546,8 @@ xfs_da_node_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 	 * Record the last hashval from each block for upward propagation.
 	 * (note: don't use the swapped node pointers)
 	 */
-	node1 = blk1->bp->data;
-	node2 = blk2->bp->data;
+	node1 = blk1->bp->b_addr;
+	node2 = blk2->bp->b_addr;
 	blk1->hashval = be32_to_cpu(node1->btree[be16_to_cpu(node1->hdr.count)-1].hashval);
 	blk2->hashval = be32_to_cpu(node2->btree[be16_to_cpu(node2->hdr.count)-1].hashval);
 
@@ -587,7 +573,7 @@ xfs_da_node_add(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
 
 	trace_xfs_da_node_add(state->args);
 
-	node = oldblk->bp->data;
+	node = oldblk->bp->b_addr;
 	ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 	ASSERT((oldblk->index >= 0) && (oldblk->index <= be16_to_cpu(node->hdr.count)));
 	ASSERT(newblk->blkno != 0);
@@ -606,10 +592,10 @@ xfs_da_node_add(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk,
 	}
 	btree->hashval = cpu_to_be32(newblk->hashval);
 	btree->before = cpu_to_be32(newblk->blkno);
-	xfs_da_log_buf(state->args->trans, oldblk->bp,
+	xfs_trans_log_buf(state->args->trans, oldblk->bp,
 		XFS_DA_LOGRANGE(node, btree, tmp + sizeof(*btree)));
 	be16_add_cpu(&node->hdr.count, 1);
-	xfs_da_log_buf(state->args->trans, oldblk->bp,
+	xfs_trans_log_buf(state->args->trans, oldblk->bp,
 		XFS_DA_LOGRANGE(node, &node->hdr, sizeof(node->hdr)));
 
 	/*
@@ -735,7 +721,7 @@ xfs_da_root_join(xfs_da_state_t *state, xfs_da_state_blk_t *root_blk)
 	xfs_da_intnode_t *oldroot;
 	xfs_da_args_t *args;
 	xfs_dablk_t child;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error;
 
 	trace_xfs_da_root_join(state->args);
@@ -743,7 +729,7 @@ xfs_da_root_join(xfs_da_state_t *state, xfs_da_state_blk_t *root_blk)
 	args = state->args;
 	ASSERT(args != NULL);
 	ASSERT(root_blk->magic == XFS_DA_NODE_MAGIC);
-	oldroot = root_blk->bp->data;
+	oldroot = root_blk->bp->b_addr;
 	ASSERT(oldroot->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 	ASSERT(!oldroot->hdr.info.forw);
 	ASSERT(!oldroot->hdr.info.back);
@@ -765,11 +751,11 @@ xfs_da_root_join(xfs_da_state_t *state, xfs_da_state_blk_t *root_blk)
 	if (error)
 		return(error);
 	ASSERT(bp != NULL);
-	xfs_da_blkinfo_onlychild_validate(bp->data,
+	xfs_da_blkinfo_onlychild_validate(bp->b_addr,
 					be16_to_cpu(oldroot->hdr.level));
 
-	memcpy(root_blk->bp->data, bp->data, state->blocksize);
-	xfs_da_log_buf(args->trans, root_blk->bp, 0, state->blocksize - 1);
+	memcpy(root_blk->bp->b_addr, bp->b_addr, state->blocksize);
+	xfs_trans_log_buf(args->trans, root_blk->bp, 0, state->blocksize - 1);
 	error = xfs_da_shrink_inode(args, child, bp);
 	return(error);
 }
@@ -791,7 +777,7 @@ xfs_da_node_toosmall(xfs_da_state_t *state, int *action)
 	xfs_da_blkinfo_t *info;
 	int count, forward, error, retval, i;
 	xfs_dablk_t blkno;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 
 	/*
 	 * Check for the degenerate case of the block being over 50% full.
@@ -799,7 +785,7 @@ xfs_da_node_toosmall(xfs_da_state_t *state, int *action)
 	 * to coalesce with a sibling.
 	 */
 	blk = &state->path.blk[ state->path.active-1 ];
-	info = blk->bp->data;
+	info = blk->bp->b_addr;
 	ASSERT(info->magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 	node = (xfs_da_intnode_t *)info;
 	count = be16_to_cpu(node->hdr.count);
@@ -859,10 +845,10 @@ xfs_da_node_toosmall(xfs_da_state_t *state, int *action)
 		count  = state->node_ents;
 		count -= state->node_ents >> 2;
 		count -= be16_to_cpu(node->hdr.count);
-		node = bp->data;
+		node = bp->b_addr;
 		ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 		count -= be16_to_cpu(node->hdr.count);
-		xfs_da_brelse(state->args->trans, bp);
+		xfs_trans_brelse(state->args->trans, bp);
 		if (count >= 0)
 			break;	/* fits with at least 25% to spare */
 	}
@@ -934,14 +920,14 @@ xfs_da_fixhashpath(xfs_da_state_t *state, xfs_da_state_path_t *path)
 		break;
 	}
 	for (blk--, level--; level >= 0; blk--, level--) {
-		node = blk->bp->data;
+		node = blk->bp->b_addr;
 		ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 		btree = &node->btree[ blk->index ];
 		if (be32_to_cpu(btree->hashval) == lasthash)
 			break;
 		blk->hashval = lasthash;
 		btree->hashval = cpu_to_be32(lasthash);
-		xfs_da_log_buf(state->args->trans, blk->bp,
+		xfs_trans_log_buf(state->args->trans, blk->bp,
 				  XFS_DA_LOGRANGE(node, btree, sizeof(*btree)));
 
 		lasthash = be32_to_cpu(node->btree[be16_to_cpu(node->hdr.count)-1].hashval);
@@ -960,7 +946,7 @@ xfs_da_node_remove(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk)
 
 	trace_xfs_da_node_remove(state->args);
 
-	node = drop_blk->bp->data;
+	node = drop_blk->bp->b_addr;
 	ASSERT(drop_blk->index < be16_to_cpu(node->hdr.count));
 	ASSERT(drop_blk->index >= 0);
 
@@ -972,15 +958,15 @@ xfs_da_node_remove(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk)
 		tmp  = be16_to_cpu(node->hdr.count) - drop_blk->index - 1;
 		tmp *= (uint)sizeof(xfs_da_node_entry_t);
 		memmove(btree, btree + 1, tmp);
-		xfs_da_log_buf(state->args->trans, drop_blk->bp,
+		xfs_trans_log_buf(state->args->trans, drop_blk->bp,
 		    XFS_DA_LOGRANGE(node, btree, tmp));
 		btree = &node->btree[be16_to_cpu(node->hdr.count)-1];
 	}
 	memset((char *)btree, 0, sizeof(xfs_da_node_entry_t));
-	xfs_da_log_buf(state->args->trans, drop_blk->bp,
+	xfs_trans_log_buf(state->args->trans, drop_blk->bp,
 	    XFS_DA_LOGRANGE(node, btree, sizeof(*btree)));
 	be16_add_cpu(&node->hdr.count, -1);
-	xfs_da_log_buf(state->args->trans, drop_blk->bp,
+	xfs_trans_log_buf(state->args->trans, drop_blk->bp,
 	    XFS_DA_LOGRANGE(node, &node->hdr, sizeof(node->hdr)));
 
 	/*
@@ -1005,8 +991,8 @@ xfs_da_node_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 
 	trace_xfs_da_node_unbalance(state->args);
 
-	drop_node = drop_blk->bp->data;
-	save_node = save_blk->bp->data;
+	drop_node = drop_blk->bp->b_addr;
+	save_node = save_blk->bp->b_addr;
 	ASSERT(drop_node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 	ASSERT(save_node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 	tp = state->args->trans;
@@ -1023,13 +1009,13 @@ xfs_da_node_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 		tmp = be16_to_cpu(save_node->hdr.count) * (uint)sizeof(xfs_da_node_entry_t);
 		memmove(btree, &save_node->btree[0], tmp);
 		btree = &save_node->btree[0];
-		xfs_da_log_buf(tp, save_blk->bp,
+		xfs_trans_log_buf(tp, save_blk->bp,
 			XFS_DA_LOGRANGE(save_node, btree,
 				(be16_to_cpu(save_node->hdr.count) + be16_to_cpu(drop_node->hdr.count)) *
 				sizeof(xfs_da_node_entry_t)));
 	} else {
 		btree = &save_node->btree[be16_to_cpu(save_node->hdr.count)];
-		xfs_da_log_buf(tp, save_blk->bp,
+		xfs_trans_log_buf(tp, save_blk->bp,
 			XFS_DA_LOGRANGE(save_node, btree,
 				be16_to_cpu(drop_node->hdr.count) *
 				sizeof(xfs_da_node_entry_t)));
@@ -1042,7 +1028,7 @@ xfs_da_node_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 	memcpy(btree, &drop_node->btree[0], tmp);
 	be16_add_cpu(&save_node->hdr.count, be16_to_cpu(drop_node->hdr.count));
 
-	xfs_da_log_buf(tp, save_blk->bp,
+	xfs_trans_log_buf(tp, save_blk->bp,
 		XFS_DA_LOGRANGE(save_node, &save_node->hdr,
 			sizeof(save_node->hdr)));
 
@@ -1100,7 +1086,7 @@ xfs_da_node_lookup_int(xfs_da_state_t *state, int *result)
 			state->path.active--;
 			return(error);
 		}
-		curr = blk->bp->data;
+		curr = blk->bp->b_addr;
 		blk->magic = be16_to_cpu(curr->magic);
 		ASSERT(blk->magic == XFS_DA_NODE_MAGIC ||
 		       blk->magic == XFS_DIR2_LEAFN_MAGIC ||
@@ -1110,7 +1096,7 @@ xfs_da_node_lookup_int(xfs_da_state_t *state, int *result)
 		 * Search an intermediate node for a match.
 		 */
 		if (blk->magic == XFS_DA_NODE_MAGIC) {
-			node = blk->bp->data;
+			node = blk->bp->b_addr;
 			max = be16_to_cpu(node->hdr.count);
 			blk->hashval = be32_to_cpu(node->btree[max-1].hashval);
 
@@ -1216,15 +1202,15 @@ xfs_da_blk_link(xfs_da_state_t *state, xfs_da_state_blk_t *old_blk,
 	xfs_da_blkinfo_t *old_info, *new_info, *tmp_info;
 	xfs_da_args_t *args;
 	int before=0, error;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 
 	/*
 	 * Set up environment.
 	 */
 	args = state->args;
 	ASSERT(args != NULL);
-	old_info = old_blk->bp->data;
-	new_info = new_blk->bp->data;
+	old_info = old_blk->bp->b_addr;
+	new_info = new_blk->bp->b_addr;
 	ASSERT(old_blk->magic == XFS_DA_NODE_MAGIC ||
 	       old_blk->magic == XFS_DIR2_LEAFN_MAGIC ||
 	       old_blk->magic == XFS_ATTR_LEAF_MAGIC);
@@ -1261,12 +1247,11 @@ xfs_da_blk_link(xfs_da_state_t *state, xfs_da_state_blk_t *old_blk,
 			if (error)
 				return(error);
 			ASSERT(bp != NULL);
-			tmp_info = bp->data;
+			tmp_info = bp->b_addr;
 			ASSERT(be16_to_cpu(tmp_info->magic) == be16_to_cpu(old_info->magic));
 			ASSERT(be32_to_cpu(tmp_info->forw) == old_blk->blkno);
 			tmp_info->forw = cpu_to_be32(new_blk->blkno);
-			xfs_da_log_buf(args->trans, bp, 0, sizeof(*tmp_info)-1);
-			xfs_da_buf_done(bp);
+			xfs_trans_log_buf(args->trans, bp, 0, sizeof(*tmp_info)-1);
 		}
 		old_info->back = cpu_to_be32(new_blk->blkno);
 	} else {
@@ -1283,18 +1268,17 @@ xfs_da_blk_link(xfs_da_state_t *state, xfs_da_state_blk_t *old_blk,
 			if (error)
 				return(error);
 			ASSERT(bp != NULL);
-			tmp_info = bp->data;
+			tmp_info = bp->b_addr;
 			ASSERT(tmp_info->magic == old_info->magic);
 			ASSERT(be32_to_cpu(tmp_info->back) == old_blk->blkno);
 			tmp_info->back = cpu_to_be32(new_blk->blkno);
-			xfs_da_log_buf(args->trans, bp, 0, sizeof(*tmp_info)-1);
-			xfs_da_buf_done(bp);
+			xfs_trans_log_buf(args->trans, bp, 0, sizeof(*tmp_info)-1);
 		}
 		old_info->forw = cpu_to_be32(new_blk->blkno);
 	}
 
-	xfs_da_log_buf(args->trans, old_blk->bp, 0, sizeof(*tmp_info) - 1);
-	xfs_da_log_buf(args->trans, new_blk->bp, 0, sizeof(*tmp_info) - 1);
+	xfs_trans_log_buf(args->trans, old_blk->bp, 0, sizeof(*tmp_info) - 1);
+	xfs_trans_log_buf(args->trans, new_blk->bp, 0, sizeof(*tmp_info) - 1);
 	return(0);
 }
 
@@ -1302,12 +1286,14 @@ xfs_da_blk_link(xfs_da_state_t *state, xfs_da_state_blk_t *old_blk,
  * Compare two intermediate nodes for "order".
  */
 STATIC int
-xfs_da_node_order(xfs_dabuf_t *node1_bp, xfs_dabuf_t *node2_bp)
+xfs_da_node_order(
+	struct xfs_buf	*node1_bp,
+	struct xfs_buf	*node2_bp)
 {
 	xfs_da_intnode_t *node1, *node2;
 
-	node1 = node1_bp->data;
-	node2 = node2_bp->data;
+	node1 = node1_bp->b_addr;
+	node2 = node2_bp->b_addr;
 	ASSERT(node1->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC) &&
 	       node2->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 	if ((be16_to_cpu(node1->hdr.count) > 0) && (be16_to_cpu(node2->hdr.count) > 0) &&
@@ -1324,11 +1310,13 @@ xfs_da_node_order(xfs_dabuf_t *node1_bp, xfs_dabuf_t *node2_bp)
  * Pick up the last hashvalue from an intermediate node.
  */
 STATIC uint
-xfs_da_node_lasthash(xfs_dabuf_t *bp, int *count)
+xfs_da_node_lasthash(
+	struct xfs_buf	*bp,
+	int		*count)
 {
 	xfs_da_intnode_t *node;
 
-	node = bp->data;
+	node = bp->b_addr;
 	ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 	if (count)
 		*count = be16_to_cpu(node->hdr.count);
@@ -1346,7 +1334,7 @@ xfs_da_blk_unlink(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 {
 	xfs_da_blkinfo_t *drop_info, *save_info, *tmp_info;
 	xfs_da_args_t *args;
-	xfs_dabuf_t *bp;
+	struct xfs_buf *bp;
 	int error;
 
 	/*
@@ -1354,8 +1342,8 @@ xfs_da_blk_unlink(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 	 */
 	args = state->args;
 	ASSERT(args != NULL);
-	save_info = save_blk->bp->data;
-	drop_info = drop_blk->bp->data;
+	save_info = save_blk->bp->b_addr;
+	drop_info = drop_blk->bp->b_addr;
 	ASSERT(save_blk->magic == XFS_DA_NODE_MAGIC ||
 	       save_blk->magic == XFS_DIR2_LEAFN_MAGIC ||
 	       save_blk->magic == XFS_ATTR_LEAF_MAGIC);
@@ -1380,13 +1368,12 @@ xfs_da_blk_unlink(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 			if (error)
 				return(error);
 			ASSERT(bp != NULL);
-			tmp_info = bp->data;
+			tmp_info = bp->b_addr;
 			ASSERT(tmp_info->magic == save_info->magic);
 			ASSERT(be32_to_cpu(tmp_info->forw) == drop_blk->blkno);
 			tmp_info->forw = cpu_to_be32(save_blk->blkno);
-			xfs_da_log_buf(args->trans, bp, 0,
+			xfs_trans_log_buf(args->trans, bp, 0,
 						    sizeof(*tmp_info) - 1);
-			xfs_da_buf_done(bp);
 		}
 	} else {
 		trace_xfs_da_unlink_forward(args);
@@ -1398,17 +1385,16 @@ xfs_da_blk_unlink(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
 			if (error)
 				return(error);
 			ASSERT(bp != NULL);
-			tmp_info = bp->data;
+			tmp_info = bp->b_addr;
 			ASSERT(tmp_info->magic == save_info->magic);
 			ASSERT(be32_to_cpu(tmp_info->back) == drop_blk->blkno);
 			tmp_info->back = cpu_to_be32(save_blk->blkno);
-			xfs_da_log_buf(args->trans, bp, 0,
+			xfs_trans_log_buf(args->trans, bp, 0,
 						    sizeof(*tmp_info) - 1);
-			xfs_da_buf_done(bp);
 		}
 	}
 
-	xfs_da_log_buf(args->trans, save_blk->bp, 0, sizeof(*save_info) - 1);
+	xfs_trans_log_buf(args->trans, save_blk->bp, 0, sizeof(*save_info) - 1);
 	return(0);
 }
 
@@ -1443,7 +1429,7 @@ xfs_da_path_shift(xfs_da_state_t *state, xfs_da_state_path_t *path,
 	level = (path->active-1) - 1;	/* skip bottom layer in path */
 	for (blk = &path->blk[level]; level >= 0; blk--, level--) {
 		ASSERT(blk->bp != NULL);
-		node = blk->bp->data;
+		node = blk->bp->b_addr;
 		ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC));
 		if (forward && (blk->index < be16_to_cpu(node->hdr.count)-1)) {
 			blk->index++;
@@ -1471,7 +1457,7 @@ xfs_da_path_shift(xfs_da_state_t *state, xfs_da_state_path_t *path,
 		 * (if it's dirty, trans won't actually let go)
 		 */
 		if (release)
-			xfs_da_brelse(args->trans, blk->bp);
+			xfs_trans_brelse(args->trans, blk->bp);
 
 		/*
 		 * Read the next child block.
@@ -1482,7 +1468,7 @@ xfs_da_path_shift(xfs_da_state_t *state, xfs_da_state_path_t *path,
 		if (error)
 			return(error);
 		ASSERT(blk->bp != NULL);
-		info = blk->bp->data;
+		info = blk->bp->b_addr;
 		ASSERT(info->magic == cpu_to_be16(XFS_DA_NODE_MAGIC) ||
 		       info->magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC) ||
 		       info->magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
@@ -1702,11 +1688,13 @@ xfs_da_grow_inode(
  * a bmap btree split to do that.
  */
 STATIC int
-xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
-		      xfs_dabuf_t **dead_bufp)
+xfs_da_swap_lastblock(
+	xfs_da_args_t	*args,
+	xfs_dablk_t	*dead_blknop,
+	struct xfs_buf	**dead_bufp)
 {
 	xfs_dablk_t dead_blkno, last_blkno, sib_blkno, par_blkno;
-	xfs_dabuf_t *dead_buf, *last_buf, *sib_buf, *par_buf;
+	struct xfs_buf *dead_buf, *last_buf, *sib_buf, *par_buf;
 	xfs_fileoff_t lastoff;
 	xfs_inode_t *ip;
 	xfs_trans_t *tp;
@@ -1744,9 +1732,9 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
 	/*
 	 * Copy the last block into the dead buffer and log it.
 	 */
-	memcpy(dead_buf->data, last_buf->data, mp->m_dirblksize);
-	xfs_da_log_buf(tp, dead_buf, 0, mp->m_dirblksize - 1);
-	dead_info = dead_buf->data;
+	memcpy(dead_buf->b_addr, last_buf->b_addr, mp->m_dirblksize);
+	xfs_trans_log_buf(tp, dead_buf, 0, mp->m_dirblksize - 1);
+	dead_info = dead_buf->b_addr;
 	/*
 	 * Get values from the moved block.
 	 */
@@ -1767,7 +1755,7 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
 	if ((sib_blkno = be32_to_cpu(dead_info->back))) {
 		if ((error = xfs_da_read_buf(tp, ip, sib_blkno, -1, &sib_buf, w)))
 			goto done;
-		sib_info = sib_buf->data;
+		sib_info = sib_buf->b_addr;
 		if (unlikely(
 		    be32_to_cpu(sib_info->forw) != last_blkno ||
 		    sib_info->magic != dead_info->magic)) {
@@ -1777,10 +1765,9 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
 			goto done;
 		}
 		sib_info->forw = cpu_to_be32(dead_blkno);
-		xfs_da_log_buf(tp, sib_buf,
+		xfs_trans_log_buf(tp, sib_buf,
 			XFS_DA_LOGRANGE(sib_info, &sib_info->forw,
 					sizeof(sib_info->forw)));
-		xfs_da_buf_done(sib_buf);
 		sib_buf = NULL;
 	}
 	/*
@@ -1789,7 +1776,7 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
 	if ((sib_blkno = be32_to_cpu(dead_info->forw))) {
 		if ((error = xfs_da_read_buf(tp, ip, sib_blkno, -1, &sib_buf, w)))
 			goto done;
-		sib_info = sib_buf->data;
+		sib_info = sib_buf->b_addr;
 		if (unlikely(
 		       be32_to_cpu(sib_info->back) != last_blkno ||
 		       sib_info->magic != dead_info->magic)) {
@@ -1799,10 +1786,9 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
 			goto done;
 		}
 		sib_info->back = cpu_to_be32(dead_blkno);
-		xfs_da_log_buf(tp, sib_buf,
+		xfs_trans_log_buf(tp, sib_buf,
 			XFS_DA_LOGRANGE(sib_info, &sib_info->back,
 					sizeof(sib_info->back)));
-		xfs_da_buf_done(sib_buf);
 		sib_buf = NULL;
 	}
 	par_blkno = mp->m_dirleafblk;
@@ -1813,7 +1799,7 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
 	for (;;) {
 		if ((error = xfs_da_read_buf(tp, ip, par_blkno, -1, &par_buf, w)))
 			goto done;
-		par_node = par_buf->data;
+		par_node = par_buf->b_addr;
 		if (unlikely(par_node->hdr.info.magic !=
 		    cpu_to_be16(XFS_DA_NODE_MAGIC) ||
 		    (level >= 0 && level != be16_to_cpu(par_node->hdr.level) + 1))) {
@@ -1837,7 +1823,7 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
 		par_blkno = be32_to_cpu(par_node->btree[entno].before);
 		if (level == dead_level + 1)
 			break;
-		xfs_da_brelse(tp, par_buf);
+		xfs_trans_brelse(tp, par_buf);
 		par_buf = NULL;
 	}
 	/*
@@ -1853,7 +1839,7 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
 		if (entno < be16_to_cpu(par_node->hdr.count))
 			break;
 		par_blkno = be32_to_cpu(par_node->hdr.info.forw);
-		xfs_da_brelse(tp, par_buf);
+		xfs_trans_brelse(tp, par_buf);
 		par_buf = NULL;
 		if (unlikely(par_blkno == 0)) {
 			XFS_ERROR_REPORT("xfs_da_swap_lastblock(6)",
@@ -1863,7 +1849,7 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
 		}
 		if ((error = xfs_da_read_buf(tp, ip, par_blkno, -1, &par_buf, w)))
 			goto done;
-		par_node = par_buf->data;
+		par_node = par_buf->b_addr;
 		if (unlikely(
 		    be16_to_cpu(par_node->hdr.level) != level ||
 		    par_node->hdr.info.magic != cpu_to_be16(XFS_DA_NODE_MAGIC))) {
@@ -1878,20 +1864,18 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop,
 	 * Update the parent entry pointing to the moved block.
 	 */
 	par_node->btree[entno].before = cpu_to_be32(dead_blkno);
-	xfs_da_log_buf(tp, par_buf,
+	xfs_trans_log_buf(tp, par_buf,
 		XFS_DA_LOGRANGE(par_node, &par_node->btree[entno].before,
 				sizeof(par_node->btree[entno].before)));
-	xfs_da_buf_done(par_buf);
-	xfs_da_buf_done(dead_buf);
 	*dead_blknop = last_blkno;
 	*dead_bufp = last_buf;
 	return 0;
 done:
 	if (par_buf)
-		xfs_da_brelse(tp, par_buf);
+		xfs_trans_brelse(tp, par_buf);
 	if (sib_buf)
-		xfs_da_brelse(tp, sib_buf);
-	xfs_da_brelse(tp, last_buf);
+		xfs_trans_brelse(tp, sib_buf);
+	xfs_trans_brelse(tp, last_buf);
 	return error;
 }
 
@@ -1899,8 +1883,10 @@ done:
  * Remove a btree block from a directory or attribute.
  */
 int
-xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno,
-		    xfs_dabuf_t *dead_buf)
+xfs_da_shrink_inode(
+	xfs_da_args_t	*args,
+	xfs_dablk_t	dead_blkno,
+	struct xfs_buf	*dead_buf)
 {
 	xfs_inode_t *dp;
 	int done, error, w, count;
@@ -1935,7 +1921,7 @@ xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno,
 			break;
 		}
 	}
-	xfs_da_binval(tp, dead_buf);
+	xfs_trans_binval(tp, dead_buf);
 	return error;
 }
 
@@ -1967,35 +1953,75 @@ xfs_da_map_covers_blocks(
 }
 
 /*
- * Make a dabuf.
- * Used for get_buf, read_buf, read_bufr, and reada_buf.
+ * Convert a struct xfs_bmbt_irec to a struct xfs_buf_map.
+ *
+ * For the single map case, it is assumed that the caller has provided a pointer
+ * to a valid xfs_buf_map.  For the multiple map case, this function will
+ * allocate the xfs_buf_map to hold all the maps and replace the caller's single
+ * map pointer with the allocated map.
  */
-STATIC int
-xfs_da_do_buf(
-	xfs_trans_t	*trans,
-	xfs_inode_t	*dp,
-	xfs_dablk_t	bno,
-	xfs_daddr_t	*mappedbnop,
-	xfs_dabuf_t	**bpp,
-	int		whichfork,
-	int		caller)
+static int
+xfs_buf_map_from_irec(
+	struct xfs_mount	*mp,
+	struct xfs_buf_map	**mapp,
+	unsigned int		*nmaps,
+	struct xfs_bmbt_irec	*irecs,
+	unsigned int		nirecs)
 {
-	xfs_buf_t	*bp = NULL;
-	xfs_buf_t	**bplist;
-	int		error=0;
-	int		i;
-	xfs_bmbt_irec_t	map;
-	xfs_bmbt_irec_t	*mapp;
-	xfs_daddr_t	mappedbno;
-	xfs_mount_t	*mp;
-	int		nbplist=0;
-	int		nfsb;
-	int		nmap;
-	xfs_dabuf_t	*rbp;
+	struct xfs_buf_map	*map;
+	int			i;
+
+	ASSERT(*nmaps == 1);
+	ASSERT(nirecs >= 1);
+
+	if (nirecs > 1) {
+		map = kmem_zalloc(nirecs * sizeof(struct xfs_buf_map), KM_SLEEP);
+		if (!map)
+			return ENOMEM;
+		*mapp = map;
+	}
+
+	*nmaps = nirecs;
+	map = *mapp;
+	for (i = 0; i < *nmaps; i++) {
+		ASSERT(irecs[i].br_startblock != DELAYSTARTBLOCK &&
+		       irecs[i].br_startblock != HOLESTARTBLOCK);
+		map[i].bm_bn = XFS_FSB_TO_DADDR(mp, irecs[i].br_startblock);
+		map[i].bm_len = XFS_FSB_TO_BB(mp, irecs[i].br_blockcount);
+	}
+	return 0;
+}
+
+/*
+ * Map the block we are given ready for reading. There are three possible return
+ * values:
+ *	-1 - will be returned if we land in a hole and mappedbno == -2 so the
+ *	     caller knows not to execute a subsequent read.
+ *	 0 - if we mapped the block successfully
+ *	>0 - positive error number if there was an error.
+ */
+static int
+xfs_dabuf_map(
+	struct xfs_trans	*trans,
+	struct xfs_inode	*dp,
+	xfs_dablk_t		bno,
+	xfs_daddr_t		mappedbno,
+	int			whichfork,
+	struct xfs_buf_map	**map,
+	int			*nmaps)
+{
+	struct xfs_mount	*mp = dp->i_mount;
+	int			nfsb;
+	int			error = 0;
+	struct xfs_bmbt_irec	irec;
+	struct xfs_bmbt_irec	*irecs = &irec;
+	int			nirecs;
+
+	ASSERT(map && *map);
+	ASSERT(*nmaps == 1);
 
-	mp = dp->i_mount;
 	nfsb = (whichfork == XFS_DATA_FORK) ? mp->m_dirblkfsbs : 1;
-	mappedbno = *mappedbnop;
+
 	/*
 	 * Caller doesn't have a mapping.  -2 means don't complain
 	 * if we land in a hole.
@@ -2004,112 +2030,150 @@ xfs_da_do_buf(
 		/*
 		 * Optimize the one-block case.
 		 */
-		if (nfsb == 1)
-			mapp = &map;
-		else
-			mapp = kmem_alloc(sizeof(*mapp) * nfsb, KM_SLEEP);
+		if (nfsb != 1)
+			irecs = kmem_zalloc(sizeof(irec) * nfsb, KM_SLEEP);
 
-		nmap = nfsb;
-		error = xfs_bmapi_read(dp, (xfs_fileoff_t)bno, nfsb, mapp,
-				       &nmap, xfs_bmapi_aflag(whichfork));
+		nirecs = nfsb;
+		error = xfs_bmapi_read(dp, (xfs_fileoff_t)bno, nfsb, irecs,
+				       &nirecs, xfs_bmapi_aflag(whichfork));
 		if (error)
-			goto exit0;
+			goto out;
 	} else {
-		map.br_startblock = XFS_DADDR_TO_FSB(mp, mappedbno);
-		map.br_startoff = (xfs_fileoff_t)bno;
-		map.br_blockcount = nfsb;
-		mapp = &map;
-		nmap = 1;
+		irecs->br_startblock = XFS_DADDR_TO_FSB(mp, mappedbno);
+		irecs->br_startoff = (xfs_fileoff_t)bno;
+		irecs->br_blockcount = nfsb;
+		irecs->br_state = 0;
+		nirecs = 1;
 	}
-	if (!xfs_da_map_covers_blocks(nmap, mapp, bno, nfsb)) {
-		error = mappedbno == -2 ? 0 : XFS_ERROR(EFSCORRUPTED);
+
+	if (!xfs_da_map_covers_blocks(nirecs, irecs, bno, nfsb)) {
+		error = mappedbno == -2 ? -1 : XFS_ERROR(EFSCORRUPTED);
 		if (unlikely(error == EFSCORRUPTED)) {
 			if (xfs_error_level >= XFS_ERRLEVEL_LOW) {
+				int i;
 				xfs_alert(mp, "%s: bno %lld dir: inode %lld",
 					__func__, (long long)bno,
 					(long long)dp->i_ino);
-				for (i = 0; i < nmap; i++) {
+				for (i = 0; i < *nmaps; i++) {
 					xfs_alert(mp,
 "[%02d] br_startoff %lld br_startblock %lld br_blockcount %lld br_state %d",
 						i,
-						(long long)mapp[i].br_startoff,
-						(long long)mapp[i].br_startblock,
-						(long long)mapp[i].br_blockcount,
-						mapp[i].br_state);
+						(long long)irecs[i].br_startoff,
+						(long long)irecs[i].br_startblock,
+						(long long)irecs[i].br_blockcount,
+						irecs[i].br_state);
 				}
 			}
 			XFS_ERROR_REPORT("xfs_da_do_buf(1)",
 					 XFS_ERRLEVEL_LOW, mp);
 		}
-		goto exit0;
+		goto out;
 	}
-	if (caller != 3 && nmap > 1) {
-		bplist = kmem_alloc(sizeof(*bplist) * nmap, KM_SLEEP);
-		nbplist = 0;
-	} else
-		bplist = NULL;
-	/*
-	 * Turn the mapping(s) into buffer(s).
-	 */
-	for (i = 0; i < nmap; i++) {
-		int	nmapped;
-
-		mappedbno = XFS_FSB_TO_DADDR(mp, mapp[i].br_startblock);
-		if (i == 0)
-			*mappedbnop = mappedbno;
-		nmapped = (int)XFS_FSB_TO_BB(mp, mapp[i].br_blockcount);
-		switch (caller) {
-		case 0:
-			bp = xfs_trans_get_buf(trans, mp->m_ddev_targp,
-				mappedbno, nmapped, 0);
-			error = bp ? bp->b_error : XFS_ERROR(EIO);
-			break;
-		case 1:
-		case 2:
-			bp = NULL;
-			error = xfs_trans_read_buf(mp, trans, mp->m_ddev_targp,
-				mappedbno, nmapped, 0, &bp);
-			break;
-		case 3:
-			xfs_buf_readahead(mp->m_ddev_targp, mappedbno, nmapped);
+	error = xfs_buf_map_from_irec(mp, map, nmaps, irecs, nirecs);
+out:
+	if (irecs != &irec)
+		kmem_free(irecs);
+	return error;
+}
+
+/*
+ * Get a buffer for the dir/attr block.
+ */
+int
+xfs_da_get_buf(
+	struct xfs_trans	*trans,
+	struct xfs_inode	*dp,
+	xfs_dablk_t		bno,
+	xfs_daddr_t		mappedbno,
+	struct xfs_buf		**bpp,
+	int			whichfork)
+{
+	struct xfs_buf		*bp;
+	struct xfs_buf_map	map;
+	struct xfs_buf_map	*mapp;
+	int			nmap;
+	int			error;
+
+	*bpp = NULL;
+	mapp = &map;
+	nmap = 1;
+	error = xfs_dabuf_map(trans, dp, bno, mappedbno, whichfork,
+				&mapp, &nmap);
+	if (error) {
+		/* mapping a hole is not an error, but we don't continue */
+		if (error == -1)
 			error = 0;
-			bp = NULL;
-			break;
-		}
-		if (error) {
-			if (bp)
-				xfs_trans_brelse(trans, bp);
-			goto exit1;
-		}
-		if (!bp)
-			continue;
-		if (caller == 1) {
-			if (whichfork == XFS_ATTR_FORK)
-				xfs_buf_set_ref(bp, XFS_ATTR_BTREE_REF);
-			else
-				xfs_buf_set_ref(bp, XFS_DIR_BTREE_REF);
-		}
-		if (bplist) {
-			bplist[nbplist++] = bp;
-		}
+		goto out_free;
 	}
-	/*
-	 * Build a dabuf structure.
-	 */
-	if (bplist) {
-		rbp = xfs_da_buf_make(nbplist, bplist);
-	} else if (bp)
-		rbp = xfs_da_buf_make(1, &bp);
+
+	bp = xfs_trans_get_buf_map(trans, dp->i_mount->m_ddev_targp,
+				    mapp, nmap, 0);
+	error = bp ? bp->b_error : XFS_ERROR(EIO);
+	if (error) {
+		xfs_trans_brelse(trans, bp);
+		goto out_free;
+	}
+
+	*bpp = bp;
+
+out_free:
+	if (mapp != &map)
+		kmem_free(mapp);
+
+	return error;
+}
+
+/*
+ * Get a buffer for the dir/attr block, fill in the contents.
+ */
+int
+xfs_da_read_buf(
+	struct xfs_trans	*trans,
+	struct xfs_inode	*dp,
+	xfs_dablk_t		bno,
+	xfs_daddr_t		mappedbno,
+	struct xfs_buf		**bpp,
+	int			whichfork)
+{
+	struct xfs_buf		*bp;
+	struct xfs_buf_map	map;
+	struct xfs_buf_map	*mapp;
+	int			nmap;
+	int			error;
+
+	*bpp = NULL;
+	mapp = &map;
+	nmap = 1;
+	error = xfs_dabuf_map(trans, dp, bno, mappedbno, whichfork,
+				&mapp, &nmap);
+	if (error) {
+		/* mapping a hole is not an error, but we don't continue */
+		if (error == -1)
+			error = 0;
+		goto out_free;
+	}
+
+	error = xfs_trans_read_buf_map(dp->i_mount, trans,
+					dp->i_mount->m_ddev_targp,
+					mapp, nmap, 0, &bp);
+	if (error)
+		goto out_free;
+
+	if (whichfork == XFS_ATTR_FORK)
+		xfs_buf_set_ref(bp, XFS_ATTR_BTREE_REF);
 	else
-		rbp = NULL;
+		xfs_buf_set_ref(bp, XFS_DIR_BTREE_REF);
+
 	/*
-	 * For read_buf, check the magic number.
+	 * This verification code will be moved to a CRC verification callback
+	 * function so just leave it here unchanged until then.
 	 */
-	if (caller == 1) {
-		xfs_dir2_data_hdr_t	*hdr = rbp->data;
-		xfs_dir2_free_t		*free = rbp->data;
-		xfs_da_blkinfo_t	*info = rbp->data;
+	{
+		xfs_dir2_data_hdr_t	*hdr = bp->b_addr;
+		xfs_dir2_free_t		*free = bp->b_addr;
+		xfs_da_blkinfo_t	*info = bp->b_addr;
 		uint			magic, magic1;
+		struct xfs_mount	*mp = dp->i_mount;
 
 		magic = be16_to_cpu(info->magic);
 		magic1 = be32_to_cpu(hdr->magic);
@@ -2123,66 +2187,20 @@ xfs_da_do_buf(
 				   (free->hdr.magic != cpu_to_be32(XFS_DIR2_FREE_MAGIC)),
 				mp, XFS_ERRTAG_DA_READ_BUF,
 				XFS_RANDOM_DA_READ_BUF))) {
-			trace_xfs_da_btree_corrupt(rbp->bps[0], _RET_IP_);
+			trace_xfs_da_btree_corrupt(bp, _RET_IP_);
 			XFS_CORRUPTION_ERROR("xfs_da_do_buf(2)",
 					     XFS_ERRLEVEL_LOW, mp, info);
 			error = XFS_ERROR(EFSCORRUPTED);
-			xfs_da_brelse(trans, rbp);
-			nbplist = 0;
-			goto exit1;
+			xfs_trans_brelse(trans, bp);
+			goto out_free;
 		}
 	}
-	if (bplist) {
-		kmem_free(bplist);
-	}
-	if (mapp != &map) {
-		kmem_free(mapp);
-	}
-	if (bpp)
-		*bpp = rbp;
-	return 0;
-exit1:
-	if (bplist) {
-		for (i = 0; i < nbplist; i++)
-			xfs_trans_brelse(trans, bplist[i]);
-		kmem_free(bplist);
-	}
-exit0:
+	*bpp = bp;
+out_free:
 	if (mapp != &map)
 		kmem_free(mapp);
-	if (bpp)
-		*bpp = NULL;
-	return error;
-}
-
-/*
- * Get a buffer for the dir/attr block.
- */
-int
-xfs_da_get_buf(
-	xfs_trans_t	*trans,
-	xfs_inode_t	*dp,
-	xfs_dablk_t	bno,
-	xfs_daddr_t		mappedbno,
-	xfs_dabuf_t	**bpp,
-	int		whichfork)
-{
-	return xfs_da_do_buf(trans, dp, bno, &mappedbno, bpp, whichfork, 0);
-}
 
-/*
- * Get a buffer for the dir/attr block, fill in the contents.
- */
-int
-xfs_da_read_buf(
-	xfs_trans_t	*trans,
-	xfs_inode_t	*dp,
-	xfs_dablk_t	bno,
-	xfs_daddr_t		mappedbno,
-	xfs_dabuf_t	**bpp,
-	int		whichfork)
-{
-	return xfs_da_do_buf(trans, dp, bno, &mappedbno, bpp, whichfork, 1);
+	return error;
 }
 
 /*
@@ -2190,22 +2208,41 @@ xfs_da_read_buf(
  */
 xfs_daddr_t
 xfs_da_reada_buf(
-	xfs_trans_t	*trans,
-	xfs_inode_t	*dp,
-	xfs_dablk_t	bno,
-	int		whichfork)
+	struct xfs_trans	*trans,
+	struct xfs_inode	*dp,
+	xfs_dablk_t		bno,
+	int			whichfork)
 {
-	xfs_daddr_t		rval;
+	xfs_daddr_t		mappedbno = -1;
+	struct xfs_buf_map	map;
+	struct xfs_buf_map	*mapp;
+	int			nmap;
+	int			error;
+
+	mapp = &map;
+	nmap = 1;
+	error = xfs_dabuf_map(trans, dp, bno, -1, whichfork,
+				&mapp, &nmap);
+	if (error) {
+		/* mapping a hole is not an error, but we don't continue */
+		if (error == -1)
+			error = 0;
+		goto out_free;
+	}
 
-	rval = -1;
-	if (xfs_da_do_buf(trans, dp, bno, &rval, NULL, whichfork, 3))
+	mappedbno = mapp[0].bm_bn;
+	xfs_buf_readahead_map(dp->i_mount->m_ddev_targp, mapp, nmap);
+
+out_free:
+	if (mapp != &map)
+		kmem_free(mapp);
+
+	if (error)
 		return -1;
-	else
-		return rval;
+	return mappedbno;
 }
 
 kmem_zone_t *xfs_da_state_zone;	/* anchor for state struct zone */
-kmem_zone_t *xfs_dabuf_zone;		/* dabuf zone */
 
 /*
  * Allocate a dir-state structure.
@@ -2225,13 +2262,8 @@ xfs_da_state_kill_altpath(xfs_da_state_t *state)
 {
 	int	i;
 
-	for (i = 0; i < state->altpath.active; i++) {
-		if (state->altpath.blk[i].bp) {
-			if (state->altpath.blk[i].bp != state->path.blk[i].bp)
-				xfs_da_buf_done(state->altpath.blk[i].bp);
-			state->altpath.blk[i].bp = NULL;
-		}
-	}
+	for (i = 0; i < state->altpath.active; i++)
+		state->altpath.blk[i].bp = NULL;
 	state->altpath.active = 0;
 }
 
@@ -2241,204 +2273,9 @@ xfs_da_state_kill_altpath(xfs_da_state_t *state)
 void
 xfs_da_state_free(xfs_da_state_t *state)
 {
-	int	i;
-
 	xfs_da_state_kill_altpath(state);
-	for (i = 0; i < state->path.active; i++) {
-		if (state->path.blk[i].bp)
-			xfs_da_buf_done(state->path.blk[i].bp);
-	}
-	if (state->extravalid && state->extrablk.bp)
-		xfs_da_buf_done(state->extrablk.bp);
 #ifdef DEBUG
 	memset((char *)state, 0, sizeof(*state));
 #endif /* DEBUG */
 	kmem_zone_free(xfs_da_state_zone, state);
 }
-
-/*
- * Create a dabuf.
- */
-/* ARGSUSED */
-STATIC xfs_dabuf_t *
-xfs_da_buf_make(int nbuf, xfs_buf_t **bps)
-{
-	xfs_buf_t	*bp;
-	xfs_dabuf_t	*dabuf;
-	int		i;
-	int		off;
-
-	if (nbuf == 1)
-		dabuf = kmem_zone_alloc(xfs_dabuf_zone, KM_NOFS);
-	else
-		dabuf = kmem_alloc(XFS_DA_BUF_SIZE(nbuf), KM_NOFS);
-	dabuf->dirty = 0;
-	if (nbuf == 1) {
-		dabuf->nbuf = 1;
-		bp = bps[0];
-		dabuf->bbcount = bp->b_length;
-		dabuf->data = bp->b_addr;
-		dabuf->bps[0] = bp;
-	} else {
-		dabuf->nbuf = nbuf;
-		for (i = 0, dabuf->bbcount = 0; i < nbuf; i++) {
-			dabuf->bps[i] = bp = bps[i];
-			dabuf->bbcount += bp->b_length;
-		}
-		dabuf->data = kmem_alloc(BBTOB(dabuf->bbcount), KM_SLEEP);
-		for (i = off = 0; i < nbuf; i++, off += BBTOB(bp->b_length)) {
-			bp = bps[i];
-			memcpy((char *)dabuf->data + off, bp->b_addr,
-				BBTOB(bp->b_length));
-		}
-	}
-	return dabuf;
-}
-
-/*
- * Un-dirty a dabuf.
- */
-STATIC void
-xfs_da_buf_clean(xfs_dabuf_t *dabuf)
-{
-	xfs_buf_t	*bp;
-	int		i;
-	int		off;
-
-	if (dabuf->dirty) {
-		ASSERT(dabuf->nbuf > 1);
-		dabuf->dirty = 0;
-		for (i = off = 0; i < dabuf->nbuf;
-				i++, off += BBTOB(bp->b_length)) {
-			bp = dabuf->bps[i];
-			memcpy(bp->b_addr, dabuf->data + off,
-						BBTOB(bp->b_length));
-		}
-	}
-}
-
-/*
- * Release a dabuf.
- */
-void
-xfs_da_buf_done(xfs_dabuf_t *dabuf)
-{
-	ASSERT(dabuf);
-	ASSERT(dabuf->nbuf && dabuf->data && dabuf->bbcount && dabuf->bps[0]);
-	if (dabuf->dirty)
-		xfs_da_buf_clean(dabuf);
-	if (dabuf->nbuf > 1) {
-		kmem_free(dabuf->data);
-		kmem_free(dabuf);
-	} else {
-		kmem_zone_free(xfs_dabuf_zone, dabuf);
-	}
-}
-
-/*
- * Log transaction from a dabuf.
- */
-void
-xfs_da_log_buf(xfs_trans_t *tp, xfs_dabuf_t *dabuf, uint first, uint last)
-{
-	xfs_buf_t	*bp;
-	uint		f;
-	int		i;
-	uint		l;
-	int		off;
-
-	ASSERT(dabuf->nbuf && dabuf->data && dabuf->bbcount && dabuf->bps[0]);
-	if (dabuf->nbuf == 1) {
-		ASSERT(dabuf->data == dabuf->bps[0]->b_addr);
-		xfs_trans_log_buf(tp, dabuf->bps[0], first, last);
-		return;
-	}
-	dabuf->dirty = 1;
-	ASSERT(first <= last);
-	for (i = off = 0; i < dabuf->nbuf; i++, off += BBTOB(bp->b_length)) {
-		bp = dabuf->bps[i];
-		f = off;
-		l = f + BBTOB(bp->b_length) - 1;
-		if (f < first)
-			f = first;
-		if (l > last)
-			l = last;
-		if (f <= l)
-			xfs_trans_log_buf(tp, bp, f - off, l - off);
-		/*
-		 * B_DONE is set by xfs_trans_log buf.
-		 * If we don't set it on a new buffer (get not read)
-		 * then if we don't put anything in the buffer it won't
-		 * be set, and at commit it it released into the cache,
-		 * and then a read will fail.
-		 */
-		else if (!(XFS_BUF_ISDONE(bp)))
-		  XFS_BUF_DONE(bp);
-	}
-	ASSERT(last < off);
-}
-
-/*
- * Release dabuf from a transaction.
- * Have to free up the dabuf before the buffers are released,
- * since the synchronization on the dabuf is really the lock on the buffer.
- */
-void
-xfs_da_brelse(xfs_trans_t *tp, xfs_dabuf_t *dabuf)
-{
-	xfs_buf_t	*bp;
-	xfs_buf_t	**bplist;
-	int		i;
-	int		nbuf;
-
-	ASSERT(dabuf->nbuf && dabuf->data && dabuf->bbcount && dabuf->bps[0]);
-	if ((nbuf = dabuf->nbuf) == 1) {
-		bplist = &bp;
-		bp = dabuf->bps[0];
-	} else {
-		bplist = kmem_alloc(nbuf * sizeof(*bplist), KM_SLEEP);
-		memcpy(bplist, dabuf->bps, nbuf * sizeof(*bplist));
-	}
-	xfs_da_buf_done(dabuf);
-	for (i = 0; i < nbuf; i++)
-		xfs_trans_brelse(tp, bplist[i]);
-	if (bplist != &bp)
-		kmem_free(bplist);
-}
-
-/*
- * Invalidate dabuf from a transaction.
- */
-void
-xfs_da_binval(xfs_trans_t *tp, xfs_dabuf_t *dabuf)
-{
-	xfs_buf_t	*bp;
-	xfs_buf_t	**bplist;
-	int		i;
-	int		nbuf;
-
-	ASSERT(dabuf->nbuf && dabuf->data && dabuf->bbcount && dabuf->bps[0]);
-	if ((nbuf = dabuf->nbuf) == 1) {
-		bplist = &bp;
-		bp = dabuf->bps[0];
-	} else {
-		bplist = kmem_alloc(nbuf * sizeof(*bplist), KM_SLEEP);
-		memcpy(bplist, dabuf->bps, nbuf * sizeof(*bplist));
-	}
-	xfs_da_buf_done(dabuf);
-	for (i = 0; i < nbuf; i++)
-		xfs_trans_binval(tp, bplist[i]);
-	if (bplist != &bp)
-		kmem_free(bplist);
-}
-
-/*
- * Get the first daddr from a dabuf.
- */
-xfs_daddr_t
-xfs_da_blkno(xfs_dabuf_t *dabuf)
-{
-	ASSERT(dabuf->nbuf);
-	ASSERT(dabuf->data);
-	return XFS_BUF_ADDR(dabuf->bps[0]);
-}
diff --git a/fs/xfs/xfs_da_btree.h b/fs/xfs/xfs_da_btree.h
index dbf7c074ae73..132adafb041e 100644
--- a/fs/xfs/xfs_da_btree.h
+++ b/fs/xfs/xfs_da_btree.h
@@ -32,7 +32,7 @@ struct zone;
 /*
  * This structure is common to both leaf nodes and non-leaf nodes in the Btree.
  *
- * Is is used to manage a doubly linked list of all blocks at the same
+ * It is used to manage a doubly linked list of all blocks at the same
  * level in the Btree, and to identify which type of block this is.
  */
 #define XFS_DA_NODE_MAGIC	0xfebe	/* magic number: non-leaf blocks */
@@ -133,24 +133,6 @@ typedef struct xfs_da_args {
 	{ XFS_DA_OP_CILOOKUP,	"CILOOKUP" }
 
 /*
- * Structure to describe buffer(s) for a block.
- * This is needed in the directory version 2 format case, when
- * multiple non-contiguous fsblocks might be needed to cover one
- * logical directory block.
- * If the buffer count is 1 then the data pointer points to the
- * same place as the b_addr field for the buffer, else to kmem_alloced memory.
- */
-typedef struct xfs_dabuf {
-	int		nbuf;		/* number of buffer pointers present */
-	short		dirty;		/* data needs to be copied back */
-	short		bbcount;	/* how large is data in bbs */
-	void		*data;		/* pointer for buffers' data */
-	struct xfs_buf	*bps[1];	/* actually nbuf of these */
-} xfs_dabuf_t;
-#define	XFS_DA_BUF_SIZE(n)	\
-	(sizeof(xfs_dabuf_t) + sizeof(struct xfs_buf *) * ((n) - 1))
-
-/*
  * Storage for holding state during Btree searches and split/join ops.
  *
  * Only need space for 5 intermediate nodes.  With a minimum of 62-way
@@ -158,7 +140,7 @@ typedef struct xfs_dabuf {
  * which is slightly more than enough.
  */
 typedef struct xfs_da_state_blk {
-	xfs_dabuf_t	*bp;		/* buffer containing block */
+	struct xfs_buf	*bp;		/* buffer containing block */
 	xfs_dablk_t	blkno;		/* filesystem blkno of buffer */
 	xfs_daddr_t	disk_blkno;	/* on-disk blkno (in BBs) of buffer */
 	int		index;		/* relevant index into block */
@@ -211,7 +193,7 @@ struct xfs_nameops {
  * Routines used for growing the Btree.
  */
 int	xfs_da_node_create(xfs_da_args_t *args, xfs_dablk_t blkno, int level,
-					 xfs_dabuf_t **bpp, int whichfork);
+					 struct xfs_buf **bpp, int whichfork);
 int	xfs_da_split(xfs_da_state_t *state);
 
 /*
@@ -241,14 +223,14 @@ int	xfs_da_grow_inode_int(struct xfs_da_args *args, xfs_fileoff_t *bno,
 			      int count);
 int	xfs_da_get_buf(struct xfs_trans *trans, struct xfs_inode *dp,
 			      xfs_dablk_t bno, xfs_daddr_t mappedbno,
-			      xfs_dabuf_t **bp, int whichfork);
+			      struct xfs_buf **bp, int whichfork);
 int	xfs_da_read_buf(struct xfs_trans *trans, struct xfs_inode *dp,
 			       xfs_dablk_t bno, xfs_daddr_t mappedbno,
-			       xfs_dabuf_t **bpp, int whichfork);
+			       struct xfs_buf **bpp, int whichfork);
 xfs_daddr_t	xfs_da_reada_buf(struct xfs_trans *trans, struct xfs_inode *dp,
 			xfs_dablk_t bno, int whichfork);
 int	xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno,
-					  xfs_dabuf_t *dead_buf);
+					  struct xfs_buf *dead_buf);
 
 uint xfs_da_hashname(const __uint8_t *name_string, int name_length);
 enum xfs_dacmp xfs_da_compname(struct xfs_da_args *args,
@@ -258,15 +240,7 @@ enum xfs_dacmp xfs_da_compname(struct xfs_da_args *args,
 xfs_da_state_t *xfs_da_state_alloc(void);
 void xfs_da_state_free(xfs_da_state_t *state);
 
-void xfs_da_buf_done(xfs_dabuf_t *dabuf);
-void xfs_da_log_buf(struct xfs_trans *tp, xfs_dabuf_t *dabuf, uint first,
-			   uint last);
-void xfs_da_brelse(struct xfs_trans *tp, xfs_dabuf_t *dabuf);
-void xfs_da_binval(struct xfs_trans *tp, xfs_dabuf_t *dabuf);
-xfs_daddr_t xfs_da_blkno(xfs_dabuf_t *dabuf);
-
 extern struct kmem_zone *xfs_da_state_zone;
-extern struct kmem_zone *xfs_dabuf_zone;
 extern const struct xfs_nameops xfs_default_nameops;
 
 #endif	/* __XFS_DA_BTREE_H__ */
diff --git a/fs/xfs/xfs_dinode.h b/fs/xfs/xfs_dinode.h
index a3721633abc8..1d9643b3dce6 100644
--- a/fs/xfs/xfs_dinode.h
+++ b/fs/xfs/xfs_dinode.h
@@ -33,7 +33,7 @@ typedef struct xfs_timestamp {
  * variable size the leftover area split into a data and an attribute fork.
  * The format of the data and attribute fork depends on the format of the
  * inode as indicated by di_format and di_aformat.  To access the data and
- * attribute use the XFS_DFORK_PTR, XFS_DFORK_DPTR, and XFS_DFORK_PTR macros
+ * attribute use the XFS_DFORK_DPTR, XFS_DFORK_APTR, and XFS_DFORK_PTR macros
  * below.
  *
  * There is a very similar struct icdinode in xfs_inode which matches the
diff --git a/fs/xfs/xfs_dir2.c b/fs/xfs/xfs_dir2.c
index 67a250c36d41..b26a50f9921d 100644
--- a/fs/xfs/xfs_dir2.c
+++ b/fs/xfs/xfs_dir2.c
@@ -592,7 +592,7 @@ int
 xfs_dir2_shrink_inode(
 	xfs_da_args_t	*args,
 	xfs_dir2_db_t	db,
-	xfs_dabuf_t	*bp)
+	struct xfs_buf	*bp)
 {
 	xfs_fileoff_t	bno;		/* directory file offset */
 	xfs_dablk_t	da;		/* directory file offset */
@@ -634,7 +634,7 @@ xfs_dir2_shrink_inode(
 	/*
 	 * Invalidate the buffer from the transaction.
 	 */
-	xfs_da_binval(tp, bp);
+	xfs_trans_binval(tp, bp);
 	/*
 	 * If it's not a data block, we're done.
 	 */
diff --git a/fs/xfs/xfs_dir2_block.c b/fs/xfs/xfs_dir2_block.c
index 586732f2d80d..e93ca8f054f4 100644
--- a/fs/xfs/xfs_dir2_block.c
+++ b/fs/xfs/xfs_dir2_block.c
@@ -37,10 +37,10 @@
 /*
  * Local function prototypes.
  */
-static void xfs_dir2_block_log_leaf(xfs_trans_t *tp, xfs_dabuf_t *bp, int first,
-				    int last);
-static void xfs_dir2_block_log_tail(xfs_trans_t *tp, xfs_dabuf_t *bp);
-static int xfs_dir2_block_lookup_int(xfs_da_args_t *args, xfs_dabuf_t **bpp,
+static void xfs_dir2_block_log_leaf(xfs_trans_t *tp, struct xfs_buf *bp,
+				    int first, int last);
+static void xfs_dir2_block_log_tail(xfs_trans_t *tp, struct xfs_buf *bp);
+static int xfs_dir2_block_lookup_int(xfs_da_args_t *args, struct xfs_buf **bpp,
 				     int *entno);
 static int xfs_dir2_block_sort(const void *a, const void *b);
 
@@ -66,7 +66,7 @@ xfs_dir2_block_addname(
 	xfs_dir2_data_free_t	*bf;		/* bestfree table in block */
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
 	xfs_dir2_leaf_entry_t	*blp;		/* block leaf entries */
-	xfs_dabuf_t		*bp;		/* buffer for block */
+	struct xfs_buf		*bp;		/* buffer for block */
 	xfs_dir2_block_tail_t	*btp;		/* block tail */
 	int			compact;	/* need to compact leaf ents */
 	xfs_dir2_data_entry_t	*dep;		/* block data entry */
@@ -102,14 +102,14 @@ xfs_dir2_block_addname(
 		return error;
 	}
 	ASSERT(bp != NULL);
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	/*
 	 * Check the magic number, corrupted if wrong.
 	 */
 	if (unlikely(hdr->magic != cpu_to_be32(XFS_DIR2_BLOCK_MAGIC))) {
 		XFS_CORRUPTION_ERROR("xfs_dir2_block_addname",
 				     XFS_ERRLEVEL_LOW, mp, hdr);
-		xfs_da_brelse(tp, bp);
+		xfs_trans_brelse(tp, bp);
 		return XFS_ERROR(EFSCORRUPTED);
 	}
 	len = xfs_dir2_data_entsize(args->namelen);
@@ -212,7 +212,7 @@ xfs_dir2_block_addname(
 	 * If this isn't a real add, we're done with the buffer.
 	 */
 	if (args->op_flags & XFS_DA_OP_JUSTCHECK)
-		xfs_da_brelse(tp, bp);
+		xfs_trans_brelse(tp, bp);
 	/*
 	 * If we don't have space for the new entry & leaf ...
 	 */
@@ -228,7 +228,6 @@ xfs_dir2_block_addname(
 		 * Then add the new entry in that format.
 		 */
 		error = xfs_dir2_block_to_leaf(args, bp);
-		xfs_da_buf_done(bp);
 		if (error)
 			return error;
 		return xfs_dir2_leaf_addname(args);
@@ -422,7 +421,6 @@ xfs_dir2_block_addname(
 	xfs_dir2_block_log_tail(tp, bp);
 	xfs_dir2_data_log_entry(tp, bp, dep);
 	xfs_dir2_data_check(dp, bp);
-	xfs_da_buf_done(bp);
 	return 0;
 }
 
@@ -437,7 +435,7 @@ xfs_dir2_block_getdents(
 	filldir_t		filldir)
 {
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
-	xfs_dabuf_t		*bp;		/* buffer for block */
+	struct xfs_buf		*bp;		/* buffer for block */
 	xfs_dir2_block_tail_t	*btp;		/* block tail */
 	xfs_dir2_data_entry_t	*dep;		/* block data entry */
 	xfs_dir2_data_unused_t	*dup;		/* block unused entry */
@@ -469,7 +467,7 @@ xfs_dir2_block_getdents(
 	 * We'll skip entries before this.
 	 */
 	wantoff = xfs_dir2_dataptr_to_off(mp, *offset);
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	xfs_dir2_data_check(dp, bp);
 	/*
 	 * Set up values for the loop.
@@ -514,7 +512,7 @@ xfs_dir2_block_getdents(
 			    cook & 0x7fffffff, be64_to_cpu(dep->inumber),
 			    DT_UNKNOWN)) {
 			*offset = cook & 0x7fffffff;
-			xfs_da_brelse(NULL, bp);
+			xfs_trans_brelse(NULL, bp);
 			return 0;
 		}
 	}
@@ -525,7 +523,7 @@ xfs_dir2_block_getdents(
 	 */
 	*offset = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk + 1, 0) &
 			0x7fffffff;
-	xfs_da_brelse(NULL, bp);
+	xfs_trans_brelse(NULL, bp);
 	return 0;
 }
 
@@ -535,17 +533,17 @@ xfs_dir2_block_getdents(
 static void
 xfs_dir2_block_log_leaf(
 	xfs_trans_t		*tp,		/* transaction structure */
-	xfs_dabuf_t		*bp,		/* block buffer */
+	struct xfs_buf		*bp,		/* block buffer */
 	int			first,		/* index of first logged leaf */
 	int			last)		/* index of last logged leaf */
 {
-	xfs_dir2_data_hdr_t	*hdr = bp->data;
+	xfs_dir2_data_hdr_t	*hdr = bp->b_addr;
 	xfs_dir2_leaf_entry_t	*blp;
 	xfs_dir2_block_tail_t	*btp;
 
 	btp = xfs_dir2_block_tail_p(tp->t_mountp, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
-	xfs_da_log_buf(tp, bp, (uint)((char *)&blp[first] - (char *)hdr),
+	xfs_trans_log_buf(tp, bp, (uint)((char *)&blp[first] - (char *)hdr),
 		(uint)((char *)&blp[last + 1] - (char *)hdr - 1));
 }
 
@@ -555,13 +553,13 @@ xfs_dir2_block_log_leaf(
 static void
 xfs_dir2_block_log_tail(
 	xfs_trans_t		*tp,		/* transaction structure */
-	xfs_dabuf_t		*bp)		/* block buffer */
+	struct xfs_buf		*bp)		/* block buffer */
 {
-	xfs_dir2_data_hdr_t	*hdr = bp->data;
+	xfs_dir2_data_hdr_t	*hdr = bp->b_addr;
 	xfs_dir2_block_tail_t	*btp;
 
 	btp = xfs_dir2_block_tail_p(tp->t_mountp, hdr);
-	xfs_da_log_buf(tp, bp, (uint)((char *)btp - (char *)hdr),
+	xfs_trans_log_buf(tp, bp, (uint)((char *)btp - (char *)hdr),
 		(uint)((char *)(btp + 1) - (char *)hdr - 1));
 }
 
@@ -575,7 +573,7 @@ xfs_dir2_block_lookup(
 {
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
 	xfs_dir2_leaf_entry_t	*blp;		/* block leaf entries */
-	xfs_dabuf_t		*bp;		/* block buffer */
+	struct xfs_buf		*bp;		/* block buffer */
 	xfs_dir2_block_tail_t	*btp;		/* block tail */
 	xfs_dir2_data_entry_t	*dep;		/* block data entry */
 	xfs_inode_t		*dp;		/* incore inode */
@@ -593,7 +591,7 @@ xfs_dir2_block_lookup(
 		return error;
 	dp = args->dp;
 	mp = dp->i_mount;
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	xfs_dir2_data_check(dp, bp);
 	btp = xfs_dir2_block_tail_p(mp, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
@@ -607,7 +605,7 @@ xfs_dir2_block_lookup(
 	 */
 	args->inumber = be64_to_cpu(dep->inumber);
 	error = xfs_dir_cilookup_result(args, dep->name, dep->namelen);
-	xfs_da_brelse(args->trans, bp);
+	xfs_trans_brelse(args->trans, bp);
 	return XFS_ERROR(error);
 }
 
@@ -617,13 +615,13 @@ xfs_dir2_block_lookup(
 static int					/* error */
 xfs_dir2_block_lookup_int(
 	xfs_da_args_t		*args,		/* dir lookup arguments */
-	xfs_dabuf_t		**bpp,		/* returned block buffer */
+	struct xfs_buf		**bpp,		/* returned block buffer */
 	int			*entno)		/* returned entry number */
 {
 	xfs_dir2_dataptr_t	addr;		/* data entry address */
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
 	xfs_dir2_leaf_entry_t	*blp;		/* block leaf entries */
-	xfs_dabuf_t		*bp;		/* block buffer */
+	struct xfs_buf		*bp;		/* block buffer */
 	xfs_dir2_block_tail_t	*btp;		/* block tail */
 	xfs_dir2_data_entry_t	*dep;		/* block data entry */
 	xfs_inode_t		*dp;		/* incore inode */
@@ -647,7 +645,7 @@ xfs_dir2_block_lookup_int(
 		return error;
 	}
 	ASSERT(bp != NULL);
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	xfs_dir2_data_check(dp, bp);
 	btp = xfs_dir2_block_tail_p(mp, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
@@ -666,7 +664,7 @@ xfs_dir2_block_lookup_int(
 			high = mid - 1;
 		if (low > high) {
 			ASSERT(args->op_flags & XFS_DA_OP_OKNOENT);
-			xfs_da_brelse(tp, bp);
+			xfs_trans_brelse(tp, bp);
 			return XFS_ERROR(ENOENT);
 		}
 	}
@@ -714,7 +712,7 @@ xfs_dir2_block_lookup_int(
 	/*
 	 * No match, release the buffer and return ENOENT.
 	 */
-	xfs_da_brelse(tp, bp);
+	xfs_trans_brelse(tp, bp);
 	return XFS_ERROR(ENOENT);
 }
 
@@ -728,7 +726,7 @@ xfs_dir2_block_removename(
 {
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
 	xfs_dir2_leaf_entry_t	*blp;		/* block leaf pointer */
-	xfs_dabuf_t		*bp;		/* block buffer */
+	struct xfs_buf		*bp;		/* block buffer */
 	xfs_dir2_block_tail_t	*btp;		/* block tail */
 	xfs_dir2_data_entry_t	*dep;		/* block data entry */
 	xfs_inode_t		*dp;		/* incore inode */
@@ -753,7 +751,7 @@ xfs_dir2_block_removename(
 	dp = args->dp;
 	tp = args->trans;
 	mp = dp->i_mount;
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	btp = xfs_dir2_block_tail_p(mp, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
 	/*
@@ -790,10 +788,9 @@ xfs_dir2_block_removename(
 	 * See if the size as a shortform is good enough.
 	 */
 	size = xfs_dir2_block_sfsize(dp, hdr, &sfh);
-	if (size > XFS_IFORK_DSIZE(dp)) {
-		xfs_da_buf_done(bp);
+	if (size > XFS_IFORK_DSIZE(dp))
 		return 0;
-	}
+
 	/*
 	 * If it works, do the conversion.
 	 */
@@ -810,7 +807,7 @@ xfs_dir2_block_replace(
 {
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
 	xfs_dir2_leaf_entry_t	*blp;		/* block leaf entries */
-	xfs_dabuf_t		*bp;		/* block buffer */
+	struct xfs_buf		*bp;		/* block buffer */
 	xfs_dir2_block_tail_t	*btp;		/* block tail */
 	xfs_dir2_data_entry_t	*dep;		/* block data entry */
 	xfs_inode_t		*dp;		/* incore inode */
@@ -829,7 +826,7 @@ xfs_dir2_block_replace(
 	}
 	dp = args->dp;
 	mp = dp->i_mount;
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	btp = xfs_dir2_block_tail_p(mp, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
 	/*
@@ -844,7 +841,6 @@ xfs_dir2_block_replace(
 	dep->inumber = cpu_to_be64(args->inumber);
 	xfs_dir2_data_log_entry(args->trans, bp, dep);
 	xfs_dir2_data_check(dp, bp);
-	xfs_da_buf_done(bp);
 	return 0;
 }
 
@@ -871,8 +867,8 @@ xfs_dir2_block_sort(
 int						/* error */
 xfs_dir2_leaf_to_block(
 	xfs_da_args_t		*args,		/* operation arguments */
-	xfs_dabuf_t		*lbp,		/* leaf buffer */
-	xfs_dabuf_t		*dbp)		/* data buffer */
+	struct xfs_buf		*lbp,		/* leaf buffer */
+	struct xfs_buf		*dbp)		/* data buffer */
 {
 	__be16			*bestsp;	/* leaf bests table */
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
@@ -898,7 +894,7 @@ xfs_dir2_leaf_to_block(
 	dp = args->dp;
 	tp = args->trans;
 	mp = dp->i_mount;
-	leaf = lbp->data;
+	leaf = lbp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC));
 	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
 	/*
@@ -914,11 +910,9 @@ xfs_dir2_leaf_to_block(
 			if ((error =
 			    xfs_dir2_leaf_trim_data(args, lbp,
 				    (xfs_dir2_db_t)(be32_to_cpu(ltp->bestcount) - 1))))
-				goto out;
-		} else {
-			error = 0;
-			goto out;
-		}
+				return error;
+		} else
+			return 0;
 	}
 	/*
 	 * Read the data block if we don't already have it, give up if it fails.
@@ -926,9 +920,9 @@ xfs_dir2_leaf_to_block(
 	if (dbp == NULL &&
 	    (error = xfs_da_read_buf(tp, dp, mp->m_dirdatablk, -1, &dbp,
 		    XFS_DATA_FORK))) {
-		goto out;
+		return error;
 	}
-	hdr = dbp->data;
+	hdr = dbp->b_addr;
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC));
 	/*
 	 * Size of the "leaf" area in the block.
@@ -944,10 +938,9 @@ xfs_dir2_leaf_to_block(
 	 * If it's not free or is too short we can't do it.
 	 */
 	if (be16_to_cpu(dup->freetag) != XFS_DIR2_DATA_FREE_TAG ||
-	    be16_to_cpu(dup->length) < size) {
-		error = 0;
-		goto out;
-	}
+	    be16_to_cpu(dup->length) < size)
+		return 0;
+
 	/*
 	 * Start converting it to block form.
 	 */
@@ -989,25 +982,17 @@ xfs_dir2_leaf_to_block(
 	 * Pitch the old leaf block.
 	 */
 	error = xfs_da_shrink_inode(args, mp->m_dirleafblk, lbp);
-	lbp = NULL;
-	if (error) {
-		goto out;
-	}
+	if (error)
+		return error;
+
 	/*
 	 * Now see if the resulting block can be shrunken to shortform.
 	 */
 	size = xfs_dir2_block_sfsize(dp, hdr, &sfh);
-	if (size > XFS_IFORK_DSIZE(dp)) {
-		error = 0;
-		goto out;
-	}
+	if (size > XFS_IFORK_DSIZE(dp))
+		return 0;
+
 	return xfs_dir2_block_to_sf(args, dbp, size, &sfh);
-out:
-	if (lbp)
-		xfs_da_buf_done(lbp);
-	if (dbp)
-		xfs_da_buf_done(dbp);
-	return error;
 }
 
 /*
@@ -1020,7 +1005,7 @@ xfs_dir2_sf_to_block(
 	xfs_dir2_db_t		blkno;		/* dir-relative block # (0) */
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
 	xfs_dir2_leaf_entry_t	*blp;		/* block leaf entries */
-	xfs_dabuf_t		*bp;		/* block buffer */
+	struct xfs_buf		*bp;		/* block buffer */
 	xfs_dir2_block_tail_t	*btp;		/* block tail pointer */
 	xfs_dir2_data_entry_t	*dep;		/* data entry pointer */
 	xfs_inode_t		*dp;		/* incore directory inode */
@@ -1088,7 +1073,7 @@ xfs_dir2_sf_to_block(
 		kmem_free(sfp);
 		return error;
 	}
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	hdr->magic = cpu_to_be32(XFS_DIR2_BLOCK_MAGIC);
 	/*
 	 * Compute size of block "tail" area.
@@ -1217,6 +1202,5 @@ xfs_dir2_sf_to_block(
 	xfs_dir2_block_log_leaf(tp, bp, 0, be32_to_cpu(btp->count) - 1);
 	xfs_dir2_block_log_tail(tp, bp);
 	xfs_dir2_data_check(dp, bp);
-	xfs_da_buf_done(bp);
 	return 0;
 }
diff --git a/fs/xfs/xfs_dir2_data.c b/fs/xfs/xfs_dir2_data.c
index 2046988e9eb2..44ffd4d6bc91 100644
--- a/fs/xfs/xfs_dir2_data.c
+++ b/fs/xfs/xfs_dir2_data.c
@@ -42,8 +42,8 @@ xfs_dir2_data_freefind(xfs_dir2_data_hdr_t *hdr, xfs_dir2_data_unused_t *dup);
  */
 void
 xfs_dir2_data_check(
-	xfs_inode_t		*dp,		/* incore inode pointer */
-	xfs_dabuf_t		*bp)		/* data block's buffer */
+	struct xfs_inode	*dp,		/* incore inode pointer */
+	struct xfs_buf		*bp)		/* data block's buffer */
 {
 	xfs_dir2_dataptr_t	addr;		/* addr for leaf lookup */
 	xfs_dir2_data_free_t	*bf;		/* bestfree table */
@@ -65,7 +65,7 @@ xfs_dir2_data_check(
 	struct xfs_name		name;
 
 	mp = dp->i_mount;
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	bf = hdr->bestfree;
 	p = (char *)(hdr + 1);
 
@@ -389,9 +389,9 @@ int						/* error */
 xfs_dir2_data_init(
 	xfs_da_args_t		*args,		/* directory operation args */
 	xfs_dir2_db_t		blkno,		/* logical dir block number */
-	xfs_dabuf_t		**bpp)		/* output block buffer */
+	struct xfs_buf		**bpp)		/* output block buffer */
 {
-	xfs_dabuf_t		*bp;		/* block buffer */
+	struct xfs_buf		*bp;		/* block buffer */
 	xfs_dir2_data_hdr_t	*hdr;		/* data block header */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	xfs_dir2_data_unused_t	*dup;		/* unused entry pointer */
@@ -417,7 +417,7 @@ xfs_dir2_data_init(
 	/*
 	 * Initialize the header.
 	 */
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	hdr->magic = cpu_to_be32(XFS_DIR2_DATA_MAGIC);
 	hdr->bestfree[0].offset = cpu_to_be16(sizeof(*hdr));
 	for (i = 1; i < XFS_DIR2_DATA_FD_COUNT; i++) {
@@ -449,16 +449,16 @@ xfs_dir2_data_init(
  */
 void
 xfs_dir2_data_log_entry(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp,		/* block buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp,
 	xfs_dir2_data_entry_t	*dep)		/* data entry pointer */
 {
-	xfs_dir2_data_hdr_t	*hdr = bp->data;
+	xfs_dir2_data_hdr_t	*hdr = bp->b_addr;
 
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
 	       hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC));
 
-	xfs_da_log_buf(tp, bp, (uint)((char *)dep - (char *)hdr),
+	xfs_trans_log_buf(tp, bp, (uint)((char *)dep - (char *)hdr),
 		(uint)((char *)(xfs_dir2_data_entry_tag_p(dep) + 1) -
 		       (char *)hdr - 1));
 }
@@ -468,15 +468,15 @@ xfs_dir2_data_log_entry(
  */
 void
 xfs_dir2_data_log_header(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp)		/* block buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp)
 {
-	xfs_dir2_data_hdr_t	*hdr = bp->data;
+	xfs_dir2_data_hdr_t	*hdr = bp->b_addr;
 
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
 	       hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC));
 
-	xfs_da_log_buf(tp, bp, 0, sizeof(*hdr) - 1);
+	xfs_trans_log_buf(tp, bp, 0, sizeof(*hdr) - 1);
 }
 
 /*
@@ -484,11 +484,11 @@ xfs_dir2_data_log_header(
  */
 void
 xfs_dir2_data_log_unused(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp,		/* block buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp,
 	xfs_dir2_data_unused_t	*dup)		/* data unused pointer */
 {
-	xfs_dir2_data_hdr_t	*hdr = bp->data;
+	xfs_dir2_data_hdr_t	*hdr = bp->b_addr;
 
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
 	       hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC));
@@ -496,13 +496,13 @@ xfs_dir2_data_log_unused(
 	/*
 	 * Log the first part of the unused entry.
 	 */
-	xfs_da_log_buf(tp, bp, (uint)((char *)dup - (char *)hdr),
+	xfs_trans_log_buf(tp, bp, (uint)((char *)dup - (char *)hdr),
 		(uint)((char *)&dup->length + sizeof(dup->length) -
 		       1 - (char *)hdr));
 	/*
 	 * Log the end (tag) of the unused entry.
 	 */
-	xfs_da_log_buf(tp, bp,
+	xfs_trans_log_buf(tp, bp,
 		(uint)((char *)xfs_dir2_data_unused_tag_p(dup) - (char *)hdr),
 		(uint)((char *)xfs_dir2_data_unused_tag_p(dup) - (char *)hdr +
 		       sizeof(xfs_dir2_data_off_t) - 1));
@@ -514,8 +514,8 @@ xfs_dir2_data_log_unused(
  */
 void
 xfs_dir2_data_make_free(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp,		/* block buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp,
 	xfs_dir2_data_aoff_t	offset,		/* starting byte offset */
 	xfs_dir2_data_aoff_t	len,		/* length in bytes */
 	int			*needlogp,	/* out: log header */
@@ -531,7 +531,7 @@ xfs_dir2_data_make_free(
 	xfs_dir2_data_unused_t	*prevdup;	/* unused entry before us */
 
 	mp = tp->t_mountp;
-	hdr = bp->data;
+	hdr = bp->b_addr;
 
 	/*
 	 * Figure out where the end of the data area is.
@@ -696,8 +696,8 @@ xfs_dir2_data_make_free(
  */
 void
 xfs_dir2_data_use_free(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp,		/* data block buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp,
 	xfs_dir2_data_unused_t	*dup,		/* unused entry */
 	xfs_dir2_data_aoff_t	offset,		/* starting offset to use */
 	xfs_dir2_data_aoff_t	len,		/* length to use */
@@ -713,7 +713,7 @@ xfs_dir2_data_use_free(
 	xfs_dir2_data_unused_t	*newdup2;	/* another new unused entry */
 	int			oldlen;		/* old unused entry's length */
 
-	hdr = bp->data;
+	hdr = bp->b_addr;
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
 	       hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC));
 	ASSERT(be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG);
diff --git a/fs/xfs/xfs_dir2_leaf.c b/fs/xfs/xfs_dir2_leaf.c
index 397ffbcbab1d..0b296253bd01 100644
--- a/fs/xfs/xfs_dir2_leaf.c
+++ b/fs/xfs/xfs_dir2_leaf.c
@@ -38,15 +38,15 @@
  * Local function declarations.
  */
 #ifdef DEBUG
-static void xfs_dir2_leaf_check(xfs_inode_t *dp, xfs_dabuf_t *bp);
+static void xfs_dir2_leaf_check(struct xfs_inode *dp, struct xfs_buf *bp);
 #else
 #define	xfs_dir2_leaf_check(dp, bp)
 #endif
-static int xfs_dir2_leaf_lookup_int(xfs_da_args_t *args, xfs_dabuf_t **lbpp,
-				    int *indexp, xfs_dabuf_t **dbpp);
-static void xfs_dir2_leaf_log_bests(struct xfs_trans *tp, struct xfs_dabuf *bp,
+static int xfs_dir2_leaf_lookup_int(xfs_da_args_t *args, struct xfs_buf **lbpp,
+				    int *indexp, struct xfs_buf **dbpp);
+static void xfs_dir2_leaf_log_bests(struct xfs_trans *tp, struct xfs_buf *bp,
 				    int first, int last);
-static void xfs_dir2_leaf_log_tail(struct xfs_trans *tp, struct xfs_dabuf *bp);
+static void xfs_dir2_leaf_log_tail(struct xfs_trans *tp, struct xfs_buf *bp);
 
 
 /*
@@ -55,7 +55,7 @@ static void xfs_dir2_leaf_log_tail(struct xfs_trans *tp, struct xfs_dabuf *bp);
 int						/* error */
 xfs_dir2_block_to_leaf(
 	xfs_da_args_t		*args,		/* operation arguments */
-	xfs_dabuf_t		*dbp)		/* input block's buffer */
+	struct xfs_buf		*dbp)		/* input block's buffer */
 {
 	__be16			*bestsp;	/* leaf's bestsp entries */
 	xfs_dablk_t		blkno;		/* leaf block's bno */
@@ -64,7 +64,7 @@ xfs_dir2_block_to_leaf(
 	xfs_dir2_block_tail_t	*btp;		/* block's tail */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return code */
-	xfs_dabuf_t		*lbp;		/* leaf block's buffer */
+	struct xfs_buf		*lbp;		/* leaf block's buffer */
 	xfs_dir2_db_t		ldb;		/* leaf block's bno */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
 	xfs_dir2_leaf_tail_t	*ltp;		/* leaf's tail */
@@ -95,8 +95,8 @@ xfs_dir2_block_to_leaf(
 		return error;
 	}
 	ASSERT(lbp != NULL);
-	leaf = lbp->data;
-	hdr = dbp->data;
+	leaf = lbp->b_addr;
+	hdr = dbp->b_addr;
 	xfs_dir2_data_check(dp, dbp);
 	btp = xfs_dir2_block_tail_p(mp, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
@@ -143,7 +143,6 @@ xfs_dir2_block_to_leaf(
 	xfs_dir2_leaf_check(dp, lbp);
 	xfs_dir2_data_check(dp, dbp);
 	xfs_dir2_leaf_log_bests(tp, lbp, 0, 0);
-	xfs_da_buf_done(lbp);
 	return 0;
 }
 
@@ -282,7 +281,7 @@ xfs_dir2_leaf_addname(
 	__be16			*bestsp;	/* freespace table in leaf */
 	int			compact;	/* need to compact leaves */
 	xfs_dir2_data_hdr_t	*hdr;		/* data block header */
-	xfs_dabuf_t		*dbp;		/* data block buffer */
+	struct xfs_buf		*dbp;		/* data block buffer */
 	xfs_dir2_data_entry_t	*dep;		/* data block entry */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	xfs_dir2_data_unused_t	*dup;		/* data unused entry */
@@ -291,7 +290,7 @@ xfs_dir2_leaf_addname(
 	int			highstale;	/* index of next stale leaf */
 	int			i;		/* temporary, index */
 	int			index;		/* leaf table position */
-	xfs_dabuf_t		*lbp;		/* leaf's buffer */
+	struct xfs_buf		*lbp;		/* leaf's buffer */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
 	int			length;		/* length of new entry */
 	xfs_dir2_leaf_entry_t	*lep;		/* leaf entry table pointer */
@@ -328,7 +327,7 @@ xfs_dir2_leaf_addname(
 	 * But if there are dup hash values the index is of the first of those.
 	 */
 	index = xfs_dir2_leaf_search_hash(args, lbp);
-	leaf = lbp->data;
+	leaf = lbp->b_addr;
 	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
 	bestsp = xfs_dir2_leaf_bests_p(ltp);
 	length = xfs_dir2_data_entsize(args->namelen);
@@ -402,14 +401,13 @@ xfs_dir2_leaf_addname(
 		 */
 		if ((args->op_flags & XFS_DA_OP_JUSTCHECK) ||
 							args->total == 0) {
-			xfs_da_brelse(tp, lbp);
+			xfs_trans_brelse(tp, lbp);
 			return XFS_ERROR(ENOSPC);
 		}
 		/*
 		 * Convert to node form.
 		 */
 		error = xfs_dir2_leaf_to_node(args, lbp);
-		xfs_da_buf_done(lbp);
 		if (error)
 			return error;
 		/*
@@ -427,7 +425,7 @@ xfs_dir2_leaf_addname(
 	 * a new data block.
 	 */
 	if (args->op_flags & XFS_DA_OP_JUSTCHECK) {
-		xfs_da_brelse(tp, lbp);
+		xfs_trans_brelse(tp, lbp);
 		return use_block == -1 ? XFS_ERROR(ENOSPC) : 0;
 	}
 	/*
@@ -435,7 +433,7 @@ xfs_dir2_leaf_addname(
 	 * changed anything.
 	 */
 	if (args->total == 0 && use_block == -1) {
-		xfs_da_brelse(tp, lbp);
+		xfs_trans_brelse(tp, lbp);
 		return XFS_ERROR(ENOSPC);
 	}
 	/*
@@ -466,14 +464,14 @@ xfs_dir2_leaf_addname(
 		 */
 		if ((error = xfs_dir2_grow_inode(args, XFS_DIR2_DATA_SPACE,
 				&use_block))) {
-			xfs_da_brelse(tp, lbp);
+			xfs_trans_brelse(tp, lbp);
 			return error;
 		}
 		/*
 		 * Initialize the block.
 		 */
 		if ((error = xfs_dir2_data_init(args, use_block, &dbp))) {
-			xfs_da_brelse(tp, lbp);
+			xfs_trans_brelse(tp, lbp);
 			return error;
 		}
 		/*
@@ -493,7 +491,7 @@ xfs_dir2_leaf_addname(
 		 */
 		else
 			xfs_dir2_leaf_log_bests(tp, lbp, use_block, use_block);
-		hdr = dbp->data;
+		hdr = dbp->b_addr;
 		bestsp[use_block] = hdr->bestfree[0].length;
 		grown = 1;
 	}
@@ -505,10 +503,10 @@ xfs_dir2_leaf_addname(
 		if ((error =
 		    xfs_da_read_buf(tp, dp, xfs_dir2_db_to_da(mp, use_block),
 			    -1, &dbp, XFS_DATA_FORK))) {
-			xfs_da_brelse(tp, lbp);
+			xfs_trans_brelse(tp, lbp);
 			return error;
 		}
-		hdr = dbp->data;
+		hdr = dbp->b_addr;
 		grown = 0;
 	}
 	xfs_dir2_data_check(dp, dbp);
@@ -570,9 +568,7 @@ xfs_dir2_leaf_addname(
 	xfs_dir2_leaf_log_header(tp, lbp);
 	xfs_dir2_leaf_log_ents(tp, lbp, lfloglow, lfloghigh);
 	xfs_dir2_leaf_check(dp, lbp);
-	xfs_da_buf_done(lbp);
 	xfs_dir2_data_check(dp, dbp);
-	xfs_da_buf_done(dbp);
 	return 0;
 }
 
@@ -583,8 +579,8 @@ xfs_dir2_leaf_addname(
  */
 STATIC void
 xfs_dir2_leaf_check(
-	xfs_inode_t		*dp,		/* incore directory inode */
-	xfs_dabuf_t		*bp)		/* leaf's buffer */
+	struct xfs_inode	*dp,		/* incore directory inode */
+	struct xfs_buf		*bp)		/* leaf's buffer */
 {
 	int			i;		/* leaf index */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
@@ -592,7 +588,7 @@ xfs_dir2_leaf_check(
 	xfs_mount_t		*mp;		/* filesystem mount point */
 	int			stale;		/* count of stale leaves */
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	mp = dp->i_mount;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC));
 	/*
@@ -628,14 +624,14 @@ xfs_dir2_leaf_check(
 void
 xfs_dir2_leaf_compact(
 	xfs_da_args_t	*args,		/* operation arguments */
-	xfs_dabuf_t	*bp)		/* leaf buffer */
+	struct xfs_buf	*bp)		/* leaf buffer */
 {
 	int		from;		/* source leaf index */
 	xfs_dir2_leaf_t	*leaf;		/* leaf structure */
 	int		loglow;		/* first leaf entry to log */
 	int		to;		/* target leaf index */
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	if (!leaf->hdr.stale) {
 		return;
 	}
@@ -677,7 +673,7 @@ xfs_dir2_leaf_compact(
  */
 void
 xfs_dir2_leaf_compact_x1(
-	xfs_dabuf_t	*bp,		/* leaf buffer */
+	struct xfs_buf	*bp,		/* leaf buffer */
 	int		*indexp,	/* insertion index */
 	int		*lowstalep,	/* out: stale entry before us */
 	int		*highstalep,	/* out: stale entry after us */
@@ -693,7 +689,7 @@ xfs_dir2_leaf_compact_x1(
 	int		newindex=0;	/* new insertion index */
 	int		to;		/* destination copy index */
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(be16_to_cpu(leaf->hdr.stale) > 1);
 	index = *indexp;
 
@@ -763,6 +759,218 @@ xfs_dir2_leaf_compact_x1(
 	*highstalep = highstale;
 }
 
+struct xfs_dir2_leaf_map_info {
+	xfs_extlen_t	map_blocks;	/* number of fsbs in map */
+	xfs_dablk_t	map_off;	/* last mapped file offset */
+	int		map_size;	/* total entries in *map */
+	int		map_valid;	/* valid entries in *map */
+	int		nmap;		/* mappings to ask xfs_bmapi */
+	xfs_dir2_db_t	curdb;		/* db for current block */
+	int		ra_current;	/* number of read-ahead blks */
+	int		ra_index;	/* *map index for read-ahead */
+	int		ra_offset;	/* map entry offset for ra */
+	int		ra_want;	/* readahead count wanted */
+	struct xfs_bmbt_irec map[];	/* map vector for blocks */
+};
+
+STATIC int
+xfs_dir2_leaf_readbuf(
+	struct xfs_inode	*dp,
+	size_t			bufsize,
+	struct xfs_dir2_leaf_map_info *mip,
+	xfs_dir2_off_t		*curoff,
+	struct xfs_buf		**bpp)
+{
+	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_buf		*bp = *bpp;
+	struct xfs_bmbt_irec	*map = mip->map;
+	int			error = 0;
+	int			length;
+	int			i;
+	int			j;
+
+	/*
+	 * If we have a buffer, we need to release it and
+	 * take it out of the mapping.
+	 */
+
+	if (bp) {
+		xfs_trans_brelse(NULL, bp);
+		bp = NULL;
+		mip->map_blocks -= mp->m_dirblkfsbs;
+		/*
+		 * Loop to get rid of the extents for the
+		 * directory block.
+		 */
+		for (i = mp->m_dirblkfsbs; i > 0; ) {
+			j = min_t(int, map->br_blockcount, i);
+			map->br_blockcount -= j;
+			map->br_startblock += j;
+			map->br_startoff += j;
+			/*
+			 * If mapping is done, pitch it from
+			 * the table.
+			 */
+			if (!map->br_blockcount && --mip->map_valid)
+				memmove(&map[0], &map[1],
+					sizeof(map[0]) * mip->map_valid);
+			i -= j;
+		}
+	}
+
+	/*
+	 * Recalculate the readahead blocks wanted.
+	 */
+	mip->ra_want = howmany(bufsize + mp->m_dirblksize,
+			       mp->m_sb.sb_blocksize) - 1;
+	ASSERT(mip->ra_want >= 0);
+
+	/*
+	 * If we don't have as many as we want, and we haven't
+	 * run out of data blocks, get some more mappings.
+	 */
+	if (1 + mip->ra_want > mip->map_blocks &&
+	    mip->map_off < xfs_dir2_byte_to_da(mp, XFS_DIR2_LEAF_OFFSET)) {
+		/*
+		 * Get more bmaps, fill in after the ones
+		 * we already have in the table.
+		 */
+		mip->nmap = mip->map_size - mip->map_valid;
+		error = xfs_bmapi_read(dp, mip->map_off,
+				xfs_dir2_byte_to_da(mp, XFS_DIR2_LEAF_OFFSET) -
+								mip->map_off,
+				&map[mip->map_valid], &mip->nmap, 0);
+
+		/*
+		 * Don't know if we should ignore this or try to return an
+		 * error.  The trouble with returning errors is that readdir
+		 * will just stop without actually passing the error through.
+		 */
+		if (error)
+			goto out;	/* XXX */
+
+		/*
+		 * If we got all the mappings we asked for, set the final map
+		 * offset based on the last bmap value received.  Otherwise,
+		 * we've reached the end.
+		 */
+		if (mip->nmap == mip->map_size - mip->map_valid) {
+			i = mip->map_valid + mip->nmap - 1;
+			mip->map_off = map[i].br_startoff + map[i].br_blockcount;
+		} else
+			mip->map_off = xfs_dir2_byte_to_da(mp,
+							XFS_DIR2_LEAF_OFFSET);
+
+		/*
+		 * Look for holes in the mapping, and eliminate them.  Count up
+		 * the valid blocks.
+		 */
+		for (i = mip->map_valid; i < mip->map_valid + mip->nmap; ) {
+			if (map[i].br_startblock == HOLESTARTBLOCK) {
+				mip->nmap--;
+				length = mip->map_valid + mip->nmap - i;
+				if (length)
+					memmove(&map[i], &map[i + 1],
+						sizeof(map[i]) * length);
+			} else {
+				mip->map_blocks += map[i].br_blockcount;
+				i++;
+			}
+		}
+		mip->map_valid += mip->nmap;
+	}
+
+	/*
+	 * No valid mappings, so no more data blocks.
+	 */
+	if (!mip->map_valid) {
+		*curoff = xfs_dir2_da_to_byte(mp, mip->map_off);
+		goto out;
+	}
+
+	/*
+	 * Read the directory block starting at the first mapping.
+	 */
+	mip->curdb = xfs_dir2_da_to_db(mp, map->br_startoff);
+	error = xfs_da_read_buf(NULL, dp, map->br_startoff,
+			map->br_blockcount >= mp->m_dirblkfsbs ?
+			    XFS_FSB_TO_DADDR(mp, map->br_startblock) : -1,
+			&bp, XFS_DATA_FORK);
+
+	/*
+	 * Should just skip over the data block instead of giving up.
+	 */
+	if (error)
+		goto out;	/* XXX */
+
+	/*
+	 * Adjust the current amount of read-ahead: we just read a block that
+	 * was previously ra.
+	 */
+	if (mip->ra_current)
+		mip->ra_current -= mp->m_dirblkfsbs;
+
+	/*
+	 * Do we need more readahead?
+	 */
+	for (mip->ra_index = mip->ra_offset = i = 0;
+	     mip->ra_want > mip->ra_current && i < mip->map_blocks;
+	     i += mp->m_dirblkfsbs) {
+		ASSERT(mip->ra_index < mip->map_valid);
+		/*
+		 * Read-ahead a contiguous directory block.
+		 */
+		if (i > mip->ra_current &&
+		    map[mip->ra_index].br_blockcount >= mp->m_dirblkfsbs) {
+			xfs_buf_readahead(mp->m_ddev_targp,
+				XFS_FSB_TO_DADDR(mp,
+					map[mip->ra_index].br_startblock +
+							mip->ra_offset),
+				(int)BTOBB(mp->m_dirblksize));
+			mip->ra_current = i;
+		}
+
+		/*
+		 * Read-ahead a non-contiguous directory block.  This doesn't
+		 * use our mapping, but this is a very rare case.
+		 */
+		else if (i > mip->ra_current) {
+			xfs_da_reada_buf(NULL, dp,
+					map[mip->ra_index].br_startoff +
+							mip->ra_offset,
+					XFS_DATA_FORK);
+			mip->ra_current = i;
+		}
+
+		/*
+		 * Advance offset through the mapping table.
+		 */
+		for (j = 0; j < mp->m_dirblkfsbs; j++) {
+			/*
+			 * The rest of this extent but not more than a dir
+			 * block.
+			 */
+			length = min_t(int, mp->m_dirblkfsbs,
+					map[mip->ra_index].br_blockcount -
+							mip->ra_offset);
+			j += length;
+			mip->ra_offset += length;
+
+			/*
+			 * Advance to the next mapping if this one is used up.
+			 */
+			if (mip->ra_offset == map[mip->ra_index].br_blockcount) {
+				mip->ra_offset = 0;
+				mip->ra_index++;
+			}
+		}
+	}
+
+out:
+	*bpp = bp;
+	return error;
+}
+
 /*
  * Getdents (readdir) for leaf and node directories.
  * This reads the data blocks only, so is the same for both forms.
@@ -775,30 +983,18 @@ xfs_dir2_leaf_getdents(
 	xfs_off_t		*offset,
 	filldir_t		filldir)
 {
-	xfs_dabuf_t		*bp;		/* data block buffer */
-	int			byteoff;	/* offset in current block */
-	xfs_dir2_db_t		curdb;		/* db for current block */
-	xfs_dir2_off_t		curoff;		/* current overall offset */
+	struct xfs_buf		*bp = NULL;	/* data block buffer */
 	xfs_dir2_data_hdr_t	*hdr;		/* data block header */
 	xfs_dir2_data_entry_t	*dep;		/* data entry */
 	xfs_dir2_data_unused_t	*dup;		/* unused entry */
 	int			error = 0;	/* error return value */
-	int			i;		/* temporary loop index */
-	int			j;		/* temporary loop index */
 	int			length;		/* temporary length value */
-	xfs_bmbt_irec_t		*map;		/* map vector for blocks */
-	xfs_extlen_t		map_blocks;	/* number of fsbs in map */
-	xfs_dablk_t		map_off;	/* last mapped file offset */
-	int			map_size;	/* total entries in *map */
-	int			map_valid;	/* valid entries in *map */
 	xfs_mount_t		*mp;		/* filesystem mount point */
+	int			byteoff;	/* offset in current block */
+	xfs_dir2_off_t		curoff;		/* current overall offset */
 	xfs_dir2_off_t		newoff;		/* new curoff after new blk */
-	int			nmap;		/* mappings to ask xfs_bmapi */
 	char			*ptr = NULL;	/* pointer to current data */
-	int			ra_current;	/* number of read-ahead blks */
-	int			ra_index;	/* *map index for read-ahead */
-	int			ra_offset;	/* map entry offset for ra */
-	int			ra_want;	/* readahead count wanted */
+	struct xfs_dir2_leaf_map_info *map_info;
 
 	/*
 	 * If the offset is at or past the largest allowed value,
@@ -814,10 +1010,12 @@ xfs_dir2_leaf_getdents(
 	 * buffer size, the directory block size, and the filesystem
 	 * block size.
 	 */
-	map_size = howmany(bufsize + mp->m_dirblksize, mp->m_sb.sb_blocksize);
-	map = kmem_alloc(map_size * sizeof(*map), KM_SLEEP);
-	map_valid = ra_index = ra_offset = ra_current = map_blocks = 0;
-	bp = NULL;
+	length = howmany(bufsize + mp->m_dirblksize,
+				     mp->m_sb.sb_blocksize);
+	map_info = kmem_zalloc(offsetof(struct xfs_dir2_leaf_map_info, map) +
+				(length * sizeof(struct xfs_bmbt_irec)),
+			       KM_SLEEP);
+	map_info->map_size = length;
 
 	/*
 	 * Inside the loop we keep the main offset value as a byte offset
@@ -829,7 +1027,9 @@ xfs_dir2_leaf_getdents(
 	 * Force this conversion through db so we truncate the offset
 	 * down to get the start of the data block.
 	 */
-	map_off = xfs_dir2_db_to_da(mp, xfs_dir2_byte_to_db(mp, curoff));
+	map_info->map_off = xfs_dir2_db_to_da(mp,
+					      xfs_dir2_byte_to_db(mp, curoff));
+
 	/*
 	 * Loop over directory entries until we reach the end offset.
 	 * Get more blocks and readahead as necessary.
@@ -839,191 +1039,17 @@ xfs_dir2_leaf_getdents(
 		 * If we have no buffer, or we're off the end of the
 		 * current buffer, need to get another one.
 		 */
-		if (!bp || ptr >= (char *)bp->data + mp->m_dirblksize) {
-			/*
-			 * If we have a buffer, we need to release it and
-			 * take it out of the mapping.
-			 */
-			if (bp) {
-				xfs_da_brelse(NULL, bp);
-				bp = NULL;
-				map_blocks -= mp->m_dirblkfsbs;
-				/*
-				 * Loop to get rid of the extents for the
-				 * directory block.
-				 */
-				for (i = mp->m_dirblkfsbs; i > 0; ) {
-					j = MIN((int)map->br_blockcount, i);
-					map->br_blockcount -= j;
-					map->br_startblock += j;
-					map->br_startoff += j;
-					/*
-					 * If mapping is done, pitch it from
-					 * the table.
-					 */
-					if (!map->br_blockcount && --map_valid)
-						memmove(&map[0], &map[1],
-							sizeof(map[0]) *
-							map_valid);
-					i -= j;
-				}
-			}
-			/*
-			 * Recalculate the readahead blocks wanted.
-			 */
-			ra_want = howmany(bufsize + mp->m_dirblksize,
-					  mp->m_sb.sb_blocksize) - 1;
-			ASSERT(ra_want >= 0);
+		if (!bp || ptr >= (char *)bp->b_addr + mp->m_dirblksize) {
 
-			/*
-			 * If we don't have as many as we want, and we haven't
-			 * run out of data blocks, get some more mappings.
-			 */
-			if (1 + ra_want > map_blocks &&
-			    map_off <
-			    xfs_dir2_byte_to_da(mp, XFS_DIR2_LEAF_OFFSET)) {
-				/*
-				 * Get more bmaps, fill in after the ones
-				 * we already have in the table.
-				 */
-				nmap = map_size - map_valid;
-				error = xfs_bmapi_read(dp, map_off,
-					xfs_dir2_byte_to_da(mp,
-						XFS_DIR2_LEAF_OFFSET) - map_off,
-					&map[map_valid], &nmap, 0);
-				/*
-				 * Don't know if we should ignore this or
-				 * try to return an error.
-				 * The trouble with returning errors
-				 * is that readdir will just stop without
-				 * actually passing the error through.
-				 */
-				if (error)
-					break;	/* XXX */
-				/*
-				 * If we got all the mappings we asked for,
-				 * set the final map offset based on the
-				 * last bmap value received.
-				 * Otherwise, we've reached the end.
-				 */
-				if (nmap == map_size - map_valid)
-					map_off =
-					map[map_valid + nmap - 1].br_startoff +
-					map[map_valid + nmap - 1].br_blockcount;
-				else
-					map_off =
-						xfs_dir2_byte_to_da(mp,
-							XFS_DIR2_LEAF_OFFSET);
-				/*
-				 * Look for holes in the mapping, and
-				 * eliminate them.  Count up the valid blocks.
-				 */
-				for (i = map_valid; i < map_valid + nmap; ) {
-					if (map[i].br_startblock ==
-					    HOLESTARTBLOCK) {
-						nmap--;
-						length = map_valid + nmap - i;
-						if (length)
-							memmove(&map[i],
-								&map[i + 1],
-								sizeof(map[i]) *
-								length);
-					} else {
-						map_blocks +=
-							map[i].br_blockcount;
-						i++;
-					}
-				}
-				map_valid += nmap;
-			}
-			/*
-			 * No valid mappings, so no more data blocks.
-			 */
-			if (!map_valid) {
-				curoff = xfs_dir2_da_to_byte(mp, map_off);
+			error = xfs_dir2_leaf_readbuf(dp, bufsize, map_info,
+						      &curoff, &bp);
+			if (error || !map_info->map_valid)
 				break;
-			}
-			/*
-			 * Read the directory block starting at the first
-			 * mapping.
-			 */
-			curdb = xfs_dir2_da_to_db(mp, map->br_startoff);
-			error = xfs_da_read_buf(NULL, dp, map->br_startoff,
-				map->br_blockcount >= mp->m_dirblkfsbs ?
-				    XFS_FSB_TO_DADDR(mp, map->br_startblock) :
-				    -1,
-				&bp, XFS_DATA_FORK);
-			/*
-			 * Should just skip over the data block instead
-			 * of giving up.
-			 */
-			if (error)
-				break;	/* XXX */
-			/*
-			 * Adjust the current amount of read-ahead: we just
-			 * read a block that was previously ra.
-			 */
-			if (ra_current)
-				ra_current -= mp->m_dirblkfsbs;
-			/*
-			 * Do we need more readahead?
-			 */
-			for (ra_index = ra_offset = i = 0;
-			     ra_want > ra_current && i < map_blocks;
-			     i += mp->m_dirblkfsbs) {
-				ASSERT(ra_index < map_valid);
-				/*
-				 * Read-ahead a contiguous directory block.
-				 */
-				if (i > ra_current &&
-				    map[ra_index].br_blockcount >=
-				    mp->m_dirblkfsbs) {
-					xfs_buf_readahead(mp->m_ddev_targp,
-						XFS_FSB_TO_DADDR(mp,
-						   map[ra_index].br_startblock +
-						   ra_offset),
-						(int)BTOBB(mp->m_dirblksize));
-					ra_current = i;
-				}
-				/*
-				 * Read-ahead a non-contiguous directory block.
-				 * This doesn't use our mapping, but this
-				 * is a very rare case.
-				 */
-				else if (i > ra_current) {
-					(void)xfs_da_reada_buf(NULL, dp,
-						map[ra_index].br_startoff +
-						ra_offset, XFS_DATA_FORK);
-					ra_current = i;
-				}
-				/*
-				 * Advance offset through the mapping table.
-				 */
-				for (j = 0; j < mp->m_dirblkfsbs; j++) {
-					/*
-					 * The rest of this extent but not
-					 * more than a dir block.
-					 */
-					length = MIN(mp->m_dirblkfsbs,
-						(int)(map[ra_index].br_blockcount -
-						ra_offset));
-					j += length;
-					ra_offset += length;
-					/*
-					 * Advance to the next mapping if
-					 * this one is used up.
-					 */
-					if (ra_offset ==
-					    map[ra_index].br_blockcount) {
-						ra_offset = 0;
-						ra_index++;
-					}
-				}
-			}
+
 			/*
 			 * Having done a read, we need to set a new offset.
 			 */
-			newoff = xfs_dir2_db_off_to_byte(mp, curdb, 0);
+			newoff = xfs_dir2_db_off_to_byte(mp, map_info->curdb, 0);
 			/*
 			 * Start of the current block.
 			 */
@@ -1034,8 +1060,8 @@ xfs_dir2_leaf_getdents(
 			 */
 			else if (curoff > newoff)
 				ASSERT(xfs_dir2_byte_to_db(mp, curoff) ==
-				       curdb);
-			hdr = bp->data;
+				       map_info->curdb);
+			hdr = bp->b_addr;
 			xfs_dir2_data_check(dp, bp);
 			/*
 			 * Find our position in the block.
@@ -1117,9 +1143,9 @@ xfs_dir2_leaf_getdents(
 		*offset = XFS_DIR2_MAX_DATAPTR & 0x7fffffff;
 	else
 		*offset = xfs_dir2_byte_to_dataptr(mp, curoff) & 0x7fffffff;
-	kmem_free(map);
+	kmem_free(map_info);
 	if (bp)
-		xfs_da_brelse(NULL, bp);
+		xfs_trans_brelse(NULL, bp);
 	return error;
 }
 
@@ -1130,10 +1156,10 @@ int
 xfs_dir2_leaf_init(
 	xfs_da_args_t		*args,		/* operation arguments */
 	xfs_dir2_db_t		bno,		/* directory block number */
-	xfs_dabuf_t		**bpp,		/* out: leaf buffer */
+	struct xfs_buf		**bpp,		/* out: leaf buffer */
 	int			magic)		/* magic number for block */
 {
-	xfs_dabuf_t		*bp;		/* leaf buffer */
+	struct xfs_buf		*bp;		/* leaf buffer */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return code */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
@@ -1156,7 +1182,7 @@ xfs_dir2_leaf_init(
 		return error;
 	}
 	ASSERT(bp != NULL);
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	/*
 	 * Initialize the header.
 	 */
@@ -1186,7 +1212,7 @@ xfs_dir2_leaf_init(
 static void
 xfs_dir2_leaf_log_bests(
 	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp,		/* leaf buffer */
+	struct xfs_buf		*bp,		/* leaf buffer */
 	int			first,		/* first entry to log */
 	int			last)		/* last entry to log */
 {
@@ -1195,12 +1221,12 @@ xfs_dir2_leaf_log_bests(
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
 	xfs_dir2_leaf_tail_t	*ltp;		/* leaf tail structure */
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC));
 	ltp = xfs_dir2_leaf_tail_p(tp->t_mountp, leaf);
 	firstb = xfs_dir2_leaf_bests_p(ltp) + first;
 	lastb = xfs_dir2_leaf_bests_p(ltp) + last;
-	xfs_da_log_buf(tp, bp, (uint)((char *)firstb - (char *)leaf),
+	xfs_trans_log_buf(tp, bp, (uint)((char *)firstb - (char *)leaf),
 		(uint)((char *)lastb - (char *)leaf + sizeof(*lastb) - 1));
 }
 
@@ -1210,7 +1236,7 @@ xfs_dir2_leaf_log_bests(
 void
 xfs_dir2_leaf_log_ents(
 	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp,		/* leaf buffer */
+	struct xfs_buf		*bp,		/* leaf buffer */
 	int			first,		/* first entry to log */
 	int			last)		/* last entry to log */
 {
@@ -1218,12 +1244,12 @@ xfs_dir2_leaf_log_ents(
 	xfs_dir2_leaf_entry_t	*lastlep;	/* pointer to last entry */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC) ||
 	       leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	firstlep = &leaf->ents[first];
 	lastlep = &leaf->ents[last];
-	xfs_da_log_buf(tp, bp, (uint)((char *)firstlep - (char *)leaf),
+	xfs_trans_log_buf(tp, bp, (uint)((char *)firstlep - (char *)leaf),
 		(uint)((char *)lastlep - (char *)leaf + sizeof(*lastlep) - 1));
 }
 
@@ -1232,15 +1258,15 @@ xfs_dir2_leaf_log_ents(
  */
 void
 xfs_dir2_leaf_log_header(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp)		/* leaf buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp)
 {
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC) ||
 	       leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
-	xfs_da_log_buf(tp, bp, (uint)((char *)&leaf->hdr - (char *)leaf),
+	xfs_trans_log_buf(tp, bp, (uint)((char *)&leaf->hdr - (char *)leaf),
 		(uint)(sizeof(leaf->hdr) - 1));
 }
 
@@ -1249,18 +1275,18 @@ xfs_dir2_leaf_log_header(
  */
 STATIC void
 xfs_dir2_leaf_log_tail(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp)		/* leaf buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp)
 {
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
 	xfs_dir2_leaf_tail_t	*ltp;		/* leaf tail structure */
 	xfs_mount_t		*mp;		/* filesystem mount point */
 
 	mp = tp->t_mountp;
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC));
 	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
-	xfs_da_log_buf(tp, bp, (uint)((char *)ltp - (char *)leaf),
+	xfs_trans_log_buf(tp, bp, (uint)((char *)ltp - (char *)leaf),
 		(uint)(mp->m_dirblksize - 1));
 }
 
@@ -1273,12 +1299,12 @@ int
 xfs_dir2_leaf_lookup(
 	xfs_da_args_t		*args)		/* operation arguments */
 {
-	xfs_dabuf_t		*dbp;		/* data block buffer */
+	struct xfs_buf		*dbp;		/* data block buffer */
 	xfs_dir2_data_entry_t	*dep;		/* data block entry */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return code */
 	int			index;		/* found entry index */
-	xfs_dabuf_t		*lbp;		/* leaf buffer */
+	struct xfs_buf		*lbp;		/* leaf buffer */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
 	xfs_dir2_leaf_entry_t	*lep;		/* leaf entry */
 	xfs_trans_t		*tp;		/* transaction pointer */
@@ -1294,7 +1320,7 @@ xfs_dir2_leaf_lookup(
 	tp = args->trans;
 	dp = args->dp;
 	xfs_dir2_leaf_check(dp, lbp);
-	leaf = lbp->data;
+	leaf = lbp->b_addr;
 	/*
 	 * Get to the leaf entry and contained data entry address.
 	 */
@@ -1303,15 +1329,15 @@ xfs_dir2_leaf_lookup(
 	 * Point to the data entry.
 	 */
 	dep = (xfs_dir2_data_entry_t *)
-	      ((char *)dbp->data +
+	      ((char *)dbp->b_addr +
 	       xfs_dir2_dataptr_to_off(dp->i_mount, be32_to_cpu(lep->address)));
 	/*
 	 * Return the found inode number & CI name if appropriate
 	 */
 	args->inumber = be64_to_cpu(dep->inumber);
 	error = xfs_dir_cilookup_result(args, dep->name, dep->namelen);
-	xfs_da_brelse(tp, dbp);
-	xfs_da_brelse(tp, lbp);
+	xfs_trans_brelse(tp, dbp);
+	xfs_trans_brelse(tp, lbp);
 	return XFS_ERROR(error);
 }
 
@@ -1324,17 +1350,17 @@ xfs_dir2_leaf_lookup(
 static int					/* error */
 xfs_dir2_leaf_lookup_int(
 	xfs_da_args_t		*args,		/* operation arguments */
-	xfs_dabuf_t		**lbpp,		/* out: leaf buffer */
+	struct xfs_buf		**lbpp,		/* out: leaf buffer */
 	int			*indexp,	/* out: index in leaf block */
-	xfs_dabuf_t		**dbpp)		/* out: data buffer */
+	struct xfs_buf		**dbpp)		/* out: data buffer */
 {
 	xfs_dir2_db_t		curdb = -1;	/* current data block number */
-	xfs_dabuf_t		*dbp = NULL;	/* data buffer */
+	struct xfs_buf		*dbp = NULL;	/* data buffer */
 	xfs_dir2_data_entry_t	*dep;		/* data entry */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return code */
 	int			index;		/* index in leaf block */
-	xfs_dabuf_t		*lbp;		/* leaf buffer */
+	struct xfs_buf		*lbp;		/* leaf buffer */
 	xfs_dir2_leaf_entry_t	*lep;		/* leaf entry */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
 	xfs_mount_t		*mp;		/* filesystem mount point */
@@ -1354,7 +1380,7 @@ xfs_dir2_leaf_lookup_int(
 	if (error)
 		return error;
 	*lbpp = lbp;
-	leaf = lbp->data;
+	leaf = lbp->b_addr;
 	xfs_dir2_leaf_check(dp, lbp);
 	/*
 	 * Look for the first leaf entry with our hash value.
@@ -1382,12 +1408,12 @@ xfs_dir2_leaf_lookup_int(
 		 */
 		if (newdb != curdb) {
 			if (dbp)
-				xfs_da_brelse(tp, dbp);
+				xfs_trans_brelse(tp, dbp);
 			error = xfs_da_read_buf(tp, dp,
 						xfs_dir2_db_to_da(mp, newdb),
 						-1, &dbp, XFS_DATA_FORK);
 			if (error) {
-				xfs_da_brelse(tp, lbp);
+				xfs_trans_brelse(tp, lbp);
 				return error;
 			}
 			xfs_dir2_data_check(dp, dbp);
@@ -1396,7 +1422,7 @@ xfs_dir2_leaf_lookup_int(
 		/*
 		 * Point to the data entry.
 		 */
-		dep = (xfs_dir2_data_entry_t *)((char *)dbp->data +
+		dep = (xfs_dir2_data_entry_t *)((char *)dbp->b_addr +
 			xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address)));
 		/*
 		 * Compare name and if it's an exact match, return the index
@@ -1424,12 +1450,12 @@ xfs_dir2_leaf_lookup_int(
 	if (args->cmpresult == XFS_CMP_CASE) {
 		ASSERT(cidb != -1);
 		if (cidb != curdb) {
-			xfs_da_brelse(tp, dbp);
+			xfs_trans_brelse(tp, dbp);
 			error = xfs_da_read_buf(tp, dp,
 						xfs_dir2_db_to_da(mp, cidb),
 						-1, &dbp, XFS_DATA_FORK);
 			if (error) {
-				xfs_da_brelse(tp, lbp);
+				xfs_trans_brelse(tp, lbp);
 				return error;
 			}
 		}
@@ -1441,8 +1467,8 @@ xfs_dir2_leaf_lookup_int(
 	 */
 	ASSERT(cidb == -1);
 	if (dbp)
-		xfs_da_brelse(tp, dbp);
-	xfs_da_brelse(tp, lbp);
+		xfs_trans_brelse(tp, dbp);
+	xfs_trans_brelse(tp, lbp);
 	return XFS_ERROR(ENOENT);
 }
 
@@ -1456,13 +1482,13 @@ xfs_dir2_leaf_removename(
 	__be16			*bestsp;	/* leaf block best freespace */
 	xfs_dir2_data_hdr_t	*hdr;		/* data block header */
 	xfs_dir2_db_t		db;		/* data block number */
-	xfs_dabuf_t		*dbp;		/* data block buffer */
+	struct xfs_buf		*dbp;		/* data block buffer */
 	xfs_dir2_data_entry_t	*dep;		/* data entry structure */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return code */
 	xfs_dir2_db_t		i;		/* temporary data block # */
 	int			index;		/* index into leaf entries */
-	xfs_dabuf_t		*lbp;		/* leaf buffer */
+	struct xfs_buf		*lbp;		/* leaf buffer */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
 	xfs_dir2_leaf_entry_t	*lep;		/* leaf entry */
 	xfs_dir2_leaf_tail_t	*ltp;		/* leaf tail structure */
@@ -1483,8 +1509,8 @@ xfs_dir2_leaf_removename(
 	dp = args->dp;
 	tp = args->trans;
 	mp = dp->i_mount;
-	leaf = lbp->data;
-	hdr = dbp->data;
+	leaf = lbp->b_addr;
+	hdr = dbp->b_addr;
 	xfs_dir2_data_check(dp, dbp);
 	/*
 	 * Point to the leaf entry, use that to point to the data entry.
@@ -1541,12 +1567,9 @@ xfs_dir2_leaf_removename(
 			 * Just go on, returning success, leaving the
 			 * empty block in place.
 			 */
-			if (error == ENOSPC && args->total == 0) {
-				xfs_da_buf_done(dbp);
+			if (error == ENOSPC && args->total == 0)
 				error = 0;
-			}
 			xfs_dir2_leaf_check(dp, lbp);
-			xfs_da_buf_done(lbp);
 			return error;
 		}
 		dbp = NULL;
@@ -1577,10 +1600,9 @@ xfs_dir2_leaf_removename(
 	/*
 	 * If the data block was not the first one, drop it.
 	 */
-	else if (db != mp->m_dirdatablk && dbp != NULL) {
-		xfs_da_buf_done(dbp);
+	else if (db != mp->m_dirdatablk)
 		dbp = NULL;
-	}
+
 	xfs_dir2_leaf_check(dp, lbp);
 	/*
 	 * See if we can convert to block form.
@@ -1595,12 +1617,12 @@ int						/* error */
 xfs_dir2_leaf_replace(
 	xfs_da_args_t		*args)		/* operation arguments */
 {
-	xfs_dabuf_t		*dbp;		/* data block buffer */
+	struct xfs_buf		*dbp;		/* data block buffer */
 	xfs_dir2_data_entry_t	*dep;		/* data block entry */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return code */
 	int			index;		/* index of leaf entry */
-	xfs_dabuf_t		*lbp;		/* leaf buffer */
+	struct xfs_buf		*lbp;		/* leaf buffer */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
 	xfs_dir2_leaf_entry_t	*lep;		/* leaf entry */
 	xfs_trans_t		*tp;		/* transaction pointer */
@@ -1614,7 +1636,7 @@ xfs_dir2_leaf_replace(
 		return error;
 	}
 	dp = args->dp;
-	leaf = lbp->data;
+	leaf = lbp->b_addr;
 	/*
 	 * Point to the leaf entry, get data address from it.
 	 */
@@ -1623,7 +1645,7 @@ xfs_dir2_leaf_replace(
 	 * Point to the data entry.
 	 */
 	dep = (xfs_dir2_data_entry_t *)
-	      ((char *)dbp->data +
+	      ((char *)dbp->b_addr +
 	       xfs_dir2_dataptr_to_off(dp->i_mount, be32_to_cpu(lep->address)));
 	ASSERT(args->inumber != be64_to_cpu(dep->inumber));
 	/*
@@ -1632,9 +1654,8 @@ xfs_dir2_leaf_replace(
 	dep->inumber = cpu_to_be64(args->inumber);
 	tp = args->trans;
 	xfs_dir2_data_log_entry(tp, dbp, dep);
-	xfs_da_buf_done(dbp);
 	xfs_dir2_leaf_check(dp, lbp);
-	xfs_da_brelse(tp, lbp);
+	xfs_trans_brelse(tp, lbp);
 	return 0;
 }
 
@@ -1646,7 +1667,7 @@ xfs_dir2_leaf_replace(
 int						/* index value */
 xfs_dir2_leaf_search_hash(
 	xfs_da_args_t		*args,		/* operation arguments */
-	xfs_dabuf_t		*lbp)		/* leaf buffer */
+	struct xfs_buf		*lbp)		/* leaf buffer */
 {
 	xfs_dahash_t		hash=0;		/* hash from this entry */
 	xfs_dahash_t		hashwant;	/* hash value looking for */
@@ -1656,7 +1677,7 @@ xfs_dir2_leaf_search_hash(
 	xfs_dir2_leaf_entry_t	*lep;		/* leaf entry */
 	int			mid=0;		/* current leaf index */
 
-	leaf = lbp->data;
+	leaf = lbp->b_addr;
 #ifndef __KERNEL__
 	if (!leaf->hdr.count)
 		return 0;
@@ -1699,11 +1720,11 @@ xfs_dir2_leaf_search_hash(
 int						/* error */
 xfs_dir2_leaf_trim_data(
 	xfs_da_args_t		*args,		/* operation arguments */
-	xfs_dabuf_t		*lbp,		/* leaf buffer */
+	struct xfs_buf		*lbp,		/* leaf buffer */
 	xfs_dir2_db_t		db)		/* data block number */
 {
 	__be16			*bestsp;	/* leaf bests table */
-	xfs_dabuf_t		*dbp;		/* data block buffer */
+	struct xfs_buf		*dbp;		/* data block buffer */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return value */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
@@ -1722,12 +1743,12 @@ xfs_dir2_leaf_trim_data(
 		return error;
 	}
 
-	leaf = lbp->data;
+	leaf = lbp->b_addr;
 	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
 
 #ifdef DEBUG
 {
-	struct xfs_dir2_data_hdr *hdr = dbp->data;
+	struct xfs_dir2_data_hdr *hdr = dbp->b_addr;
 
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC));
 	ASSERT(be16_to_cpu(hdr->bestfree[0].length) ==
@@ -1741,7 +1762,7 @@ xfs_dir2_leaf_trim_data(
 	 */
 	if ((error = xfs_dir2_shrink_inode(args, db, dbp))) {
 		ASSERT(error != ENOSPC);
-		xfs_da_brelse(tp, dbp);
+		xfs_trans_brelse(tp, dbp);
 		return error;
 	}
 	/*
@@ -1781,10 +1802,10 @@ xfs_dir2_node_to_leaf(
 	xfs_da_args_t		*args;		/* operation arguments */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return code */
-	xfs_dabuf_t		*fbp;		/* buffer for freespace block */
+	struct xfs_buf		*fbp;		/* buffer for freespace block */
 	xfs_fileoff_t		fo;		/* freespace file offset */
 	xfs_dir2_free_t		*free;		/* freespace structure */
-	xfs_dabuf_t		*lbp;		/* buffer for leaf block */
+	struct xfs_buf		*lbp;		/* buffer for leaf block */
 	xfs_dir2_leaf_tail_t	*ltp;		/* tail of leaf structure */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
 	xfs_mount_t		*mp;		/* filesystem mount point */
@@ -1838,7 +1859,7 @@ xfs_dir2_node_to_leaf(
 	if (XFS_FSB_TO_B(mp, fo) > XFS_DIR2_LEAF_OFFSET + mp->m_dirblksize)
 		return 0;
 	lbp = state->path.blk[0].bp;
-	leaf = lbp->data;
+	leaf = lbp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	/*
 	 * Read the freespace block.
@@ -1847,7 +1868,7 @@ xfs_dir2_node_to_leaf(
 			XFS_DATA_FORK))) {
 		return error;
 	}
-	free = fbp->data;
+	free = fbp->b_addr;
 	ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
 	ASSERT(!free->hdr.firstdb);
 
@@ -1857,7 +1878,7 @@ xfs_dir2_node_to_leaf(
 	 */
 	if (xfs_dir2_leaf_size(&leaf->hdr, be32_to_cpu(free->hdr.nvalid)) >
 			mp->m_dirblksize) {
-		xfs_da_brelse(tp, fbp);
+		xfs_trans_brelse(tp, fbp);
 		return 0;
 	}
 
diff --git a/fs/xfs/xfs_dir2_node.c b/fs/xfs/xfs_dir2_node.c
index b0f26780449d..6c7052406605 100644
--- a/fs/xfs/xfs_dir2_node.c
+++ b/fs/xfs/xfs_dir2_node.c
@@ -36,20 +36,20 @@
 /*
  * Function declarations.
  */
-static void xfs_dir2_free_log_header(xfs_trans_t *tp, xfs_dabuf_t *bp);
-static int xfs_dir2_leafn_add(xfs_dabuf_t *bp, xfs_da_args_t *args, int index);
+static int xfs_dir2_leafn_add(struct xfs_buf *bp, xfs_da_args_t *args,
+			      int index);
 #ifdef DEBUG
-static void xfs_dir2_leafn_check(xfs_inode_t *dp, xfs_dabuf_t *bp);
+static void xfs_dir2_leafn_check(struct xfs_inode *dp, struct xfs_buf *bp);
 #else
 #define	xfs_dir2_leafn_check(dp, bp)
 #endif
-static void xfs_dir2_leafn_moveents(xfs_da_args_t *args, xfs_dabuf_t *bp_s,
-				    int start_s, xfs_dabuf_t *bp_d, int start_d,
-				    int count);
+static void xfs_dir2_leafn_moveents(xfs_da_args_t *args, struct xfs_buf *bp_s,
+				    int start_s, struct xfs_buf *bp_d,
+				    int start_d, int count);
 static void xfs_dir2_leafn_rebalance(xfs_da_state_t *state,
 				     xfs_da_state_blk_t *blk1,
 				     xfs_da_state_blk_t *blk2);
-static int xfs_dir2_leafn_remove(xfs_da_args_t *args, xfs_dabuf_t *bp,
+static int xfs_dir2_leafn_remove(xfs_da_args_t *args, struct xfs_buf *bp,
 				 int index, xfs_da_state_blk_t *dblk,
 				 int *rval);
 static int xfs_dir2_node_addname_int(xfs_da_args_t *args,
@@ -60,16 +60,16 @@ static int xfs_dir2_node_addname_int(xfs_da_args_t *args,
  */
 STATIC void
 xfs_dir2_free_log_bests(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp,		/* freespace buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp,
 	int			first,		/* first entry to log */
 	int			last)		/* last entry to log */
 {
 	xfs_dir2_free_t		*free;		/* freespace structure */
 
-	free = bp->data;
+	free = bp->b_addr;
 	ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
-	xfs_da_log_buf(tp, bp,
+	xfs_trans_log_buf(tp, bp,
 		(uint)((char *)&free->bests[first] - (char *)free),
 		(uint)((char *)&free->bests[last] - (char *)free +
 		       sizeof(free->bests[0]) - 1));
@@ -80,14 +80,14 @@ xfs_dir2_free_log_bests(
  */
 static void
 xfs_dir2_free_log_header(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_dabuf_t		*bp)		/* freespace buffer */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp)
 {
 	xfs_dir2_free_t		*free;		/* freespace structure */
 
-	free = bp->data;
+	free = bp->b_addr;
 	ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
-	xfs_da_log_buf(tp, bp, (uint)((char *)&free->hdr - (char *)free),
+	xfs_trans_log_buf(tp, bp, (uint)((char *)&free->hdr - (char *)free),
 		(uint)(sizeof(xfs_dir2_free_hdr_t) - 1));
 }
 
@@ -99,11 +99,11 @@ xfs_dir2_free_log_header(
 int						/* error */
 xfs_dir2_leaf_to_node(
 	xfs_da_args_t		*args,		/* operation arguments */
-	xfs_dabuf_t		*lbp)		/* leaf buffer */
+	struct xfs_buf		*lbp)		/* leaf buffer */
 {
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return value */
-	xfs_dabuf_t		*fbp;		/* freespace buffer */
+	struct xfs_buf		*fbp;		/* freespace buffer */
 	xfs_dir2_db_t		fdb;		/* freespace block number */
 	xfs_dir2_free_t		*free;		/* freespace structure */
 	__be16			*from;		/* pointer to freespace entry */
@@ -136,8 +136,8 @@ xfs_dir2_leaf_to_node(
 		return error;
 	}
 	ASSERT(fbp != NULL);
-	free = fbp->data;
-	leaf = lbp->data;
+	free = fbp->b_addr;
+	leaf = lbp->b_addr;
 	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
 	/*
 	 * Initialize the freespace block header.
@@ -164,7 +164,6 @@ xfs_dir2_leaf_to_node(
 	xfs_dir2_leaf_log_header(tp, lbp);
 	xfs_dir2_free_log_header(tp, fbp);
 	xfs_dir2_free_log_bests(tp, fbp, 0, be32_to_cpu(free->hdr.nvalid) - 1);
-	xfs_da_buf_done(fbp);
 	xfs_dir2_leafn_check(dp, lbp);
 	return 0;
 }
@@ -175,7 +174,7 @@ xfs_dir2_leaf_to_node(
  */
 static int					/* error */
 xfs_dir2_leafn_add(
-	xfs_dabuf_t		*bp,		/* leaf buffer */
+	struct xfs_buf		*bp,		/* leaf buffer */
 	xfs_da_args_t		*args,		/* operation arguments */
 	int			index)		/* insertion pt for new entry */
 {
@@ -195,7 +194,7 @@ xfs_dir2_leafn_add(
 	dp = args->dp;
 	mp = dp->i_mount;
 	tp = args->trans;
-	leaf = bp->data;
+	leaf = bp->b_addr;
 
 	/*
 	 * Quick check just to make sure we are not going to index
@@ -261,15 +260,15 @@ xfs_dir2_leafn_add(
  */
 void
 xfs_dir2_leafn_check(
-	xfs_inode_t	*dp,			/* incore directory inode */
-	xfs_dabuf_t	*bp)			/* leaf buffer */
+	struct xfs_inode *dp,
+	struct xfs_buf	*bp)
 {
 	int		i;			/* leaf index */
 	xfs_dir2_leaf_t	*leaf;			/* leaf structure */
 	xfs_mount_t	*mp;			/* filesystem mount point */
 	int		stale;			/* count of stale leaves */
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	mp = dp->i_mount;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	ASSERT(be16_to_cpu(leaf->hdr.count) <= xfs_dir2_max_leaf_ents(mp));
@@ -291,12 +290,12 @@ xfs_dir2_leafn_check(
  */
 xfs_dahash_t					/* hash value */
 xfs_dir2_leafn_lasthash(
-	xfs_dabuf_t	*bp,			/* leaf buffer */
+	struct xfs_buf	*bp,			/* leaf buffer */
 	int		*count)			/* count of entries in leaf */
 {
 	xfs_dir2_leaf_t	*leaf;			/* leaf structure */
 
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	if (count)
 		*count = be16_to_cpu(leaf->hdr.count);
@@ -311,12 +310,12 @@ xfs_dir2_leafn_lasthash(
  */
 STATIC int
 xfs_dir2_leafn_lookup_for_addname(
-	xfs_dabuf_t		*bp,		/* leaf buffer */
+	struct xfs_buf		*bp,		/* leaf buffer */
 	xfs_da_args_t		*args,		/* operation arguments */
 	int			*indexp,	/* out: leaf entry index */
 	xfs_da_state_t		*state)		/* state to fill in */
 {
-	xfs_dabuf_t		*curbp = NULL;	/* current data/free buffer */
+	struct xfs_buf		*curbp = NULL;	/* current data/free buffer */
 	xfs_dir2_db_t		curdb = -1;	/* current data block number */
 	xfs_dir2_db_t		curfdb = -1;	/* current free block number */
 	xfs_inode_t		*dp;		/* incore directory inode */
@@ -335,7 +334,7 @@ xfs_dir2_leafn_lookup_for_addname(
 	dp = args->dp;
 	tp = args->trans;
 	mp = dp->i_mount;
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 #ifdef __KERNEL__
 	ASSERT(be16_to_cpu(leaf->hdr.count) > 0);
@@ -352,7 +351,7 @@ xfs_dir2_leafn_lookup_for_addname(
 		/* If so, it's a free block buffer, get the block number. */
 		curbp = state->extrablk.bp;
 		curfdb = state->extrablk.blkno;
-		free = curbp->data;
+		free = curbp->b_addr;
 		ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
 	}
 	length = xfs_dir2_data_entsize(args->namelen);
@@ -394,7 +393,7 @@ xfs_dir2_leafn_lookup_for_addname(
 				 * If we had one before, drop it.
 				 */
 				if (curbp)
-					xfs_da_brelse(tp, curbp);
+					xfs_trans_brelse(tp, curbp);
 				/*
 				 * Read the free block.
 				 */
@@ -403,7 +402,7 @@ xfs_dir2_leafn_lookup_for_addname(
 						-1, &curbp, XFS_DATA_FORK);
 				if (error)
 					return error;
-				free = curbp->data;
+				free = curbp->b_addr;
 				ASSERT(be32_to_cpu(free->hdr.magic) ==
 					XFS_DIR2_FREE_MAGIC);
 				ASSERT((be32_to_cpu(free->hdr.firstdb) %
@@ -424,7 +423,7 @@ xfs_dir2_leafn_lookup_for_addname(
 				XFS_ERROR_REPORT("xfs_dir2_leafn_lookup_int",
 							XFS_ERRLEVEL_LOW, mp);
 				if (curfdb != newfdb)
-					xfs_da_brelse(tp, curbp);
+					xfs_trans_brelse(tp, curbp);
 				return XFS_ERROR(EFSCORRUPTED);
 			}
 			curfdb = newfdb;
@@ -459,12 +458,12 @@ out:
  */
 STATIC int
 xfs_dir2_leafn_lookup_for_entry(
-	xfs_dabuf_t		*bp,		/* leaf buffer */
+	struct xfs_buf		*bp,		/* leaf buffer */
 	xfs_da_args_t		*args,		/* operation arguments */
 	int			*indexp,	/* out: leaf entry index */
 	xfs_da_state_t		*state)		/* state to fill in */
 {
-	xfs_dabuf_t		*curbp = NULL;	/* current data/free buffer */
+	struct xfs_buf		*curbp = NULL;	/* current data/free buffer */
 	xfs_dir2_db_t		curdb = -1;	/* current data block number */
 	xfs_dir2_data_entry_t	*dep;		/* data block entry */
 	xfs_inode_t		*dp;		/* incore directory inode */
@@ -480,7 +479,7 @@ xfs_dir2_leafn_lookup_for_entry(
 	dp = args->dp;
 	tp = args->trans;
 	mp = dp->i_mount;
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 #ifdef __KERNEL__
 	ASSERT(be16_to_cpu(leaf->hdr.count) > 0);
@@ -525,7 +524,7 @@ xfs_dir2_leafn_lookup_for_entry(
 			 */
 			if (curbp && (args->cmpresult == XFS_CMP_DIFFERENT ||
 						curdb != state->extrablk.blkno))
-				xfs_da_brelse(tp, curbp);
+				xfs_trans_brelse(tp, curbp);
 			/*
 			 * If needing the block that is saved with a CI match,
 			 * use it otherwise read in the new data block.
@@ -547,7 +546,7 @@ xfs_dir2_leafn_lookup_for_entry(
 		/*
 		 * Point to the data entry.
 		 */
-		dep = (xfs_dir2_data_entry_t *)((char *)curbp->data +
+		dep = (xfs_dir2_data_entry_t *)((char *)curbp->b_addr +
 			xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address)));
 		/*
 		 * Compare the entry and if it's an exact match, return
@@ -559,7 +558,7 @@ xfs_dir2_leafn_lookup_for_entry(
 			/* If there is a CI match block, drop it */
 			if (args->cmpresult != XFS_CMP_DIFFERENT &&
 						curdb != state->extrablk.blkno)
-				xfs_da_brelse(tp, state->extrablk.bp);
+				xfs_trans_brelse(tp, state->extrablk.bp);
 			args->cmpresult = cmp;
 			args->inumber = be64_to_cpu(dep->inumber);
 			*indexp = index;
@@ -567,7 +566,7 @@ xfs_dir2_leafn_lookup_for_entry(
 			state->extrablk.bp = curbp;
 			state->extrablk.blkno = curdb;
 			state->extrablk.index = (int)((char *)dep -
-							(char *)curbp->data);
+							(char *)curbp->b_addr);
 			state->extrablk.magic = XFS_DIR2_DATA_MAGIC;
 			if (cmp == XFS_CMP_EXACT)
 				return XFS_ERROR(EEXIST);
@@ -586,7 +585,7 @@ xfs_dir2_leafn_lookup_for_entry(
 		} else {
 			/* If the curbp is not the CI match block, drop it */
 			if (state->extrablk.bp != curbp)
-				xfs_da_brelse(tp, curbp);
+				xfs_trans_brelse(tp, curbp);
 		}
 	} else {
 		state->extravalid = 0;
@@ -602,7 +601,7 @@ xfs_dir2_leafn_lookup_for_entry(
  */
 int
 xfs_dir2_leafn_lookup_int(
-	xfs_dabuf_t		*bp,		/* leaf buffer */
+	struct xfs_buf		*bp,		/* leaf buffer */
 	xfs_da_args_t		*args,		/* operation arguments */
 	int			*indexp,	/* out: leaf entry index */
 	xfs_da_state_t		*state)		/* state to fill in */
@@ -620,9 +619,9 @@ xfs_dir2_leafn_lookup_int(
 static void
 xfs_dir2_leafn_moveents(
 	xfs_da_args_t	*args,			/* operation arguments */
-	xfs_dabuf_t	*bp_s,			/* source leaf buffer */
+	struct xfs_buf	*bp_s,			/* source leaf buffer */
 	int		start_s,		/* source leaf index */
-	xfs_dabuf_t	*bp_d,			/* destination leaf buffer */
+	struct xfs_buf	*bp_d,			/* destination leaf buffer */
 	int		start_d,		/* destination leaf index */
 	int		count)			/* count of leaves to copy */
 {
@@ -640,8 +639,8 @@ xfs_dir2_leafn_moveents(
 		return;
 	}
 	tp = args->trans;
-	leaf_s = bp_s->data;
-	leaf_d = bp_d->data;
+	leaf_s = bp_s->b_addr;
+	leaf_d = bp_d->b_addr;
 	/*
 	 * If the destination index is not the end of the current
 	 * destination leaf entries, open up a hole in the destination
@@ -702,14 +701,14 @@ xfs_dir2_leafn_moveents(
  */
 int						/* sort order */
 xfs_dir2_leafn_order(
-	xfs_dabuf_t	*leaf1_bp,		/* leaf1 buffer */
-	xfs_dabuf_t	*leaf2_bp)		/* leaf2 buffer */
+	struct xfs_buf	*leaf1_bp,		/* leaf1 buffer */
+	struct xfs_buf	*leaf2_bp)		/* leaf2 buffer */
 {
 	xfs_dir2_leaf_t	*leaf1;			/* leaf1 structure */
 	xfs_dir2_leaf_t	*leaf2;			/* leaf2 structure */
 
-	leaf1 = leaf1_bp->data;
-	leaf2 = leaf2_bp->data;
+	leaf1 = leaf1_bp->b_addr;
+	leaf2 = leaf2_bp->b_addr;
 	ASSERT(leaf1->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	ASSERT(leaf2->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	if (be16_to_cpu(leaf1->hdr.count) > 0 &&
@@ -757,8 +756,8 @@ xfs_dir2_leafn_rebalance(
 		blk1 = blk2;
 		blk2 = tmp;
 	}
-	leaf1 = blk1->bp->data;
-	leaf2 = blk2->bp->data;
+	leaf1 = blk1->bp->b_addr;
+	leaf2 = blk2->bp->b_addr;
 	oldsum = be16_to_cpu(leaf1->hdr.count) + be16_to_cpu(leaf2->hdr.count);
 #ifdef DEBUG
 	oldstale = be16_to_cpu(leaf1->hdr.stale) + be16_to_cpu(leaf2->hdr.stale);
@@ -834,14 +833,14 @@ xfs_dir2_leafn_rebalance(
 static int					/* error */
 xfs_dir2_leafn_remove(
 	xfs_da_args_t		*args,		/* operation arguments */
-	xfs_dabuf_t		*bp,		/* leaf buffer */
+	struct xfs_buf		*bp,		/* leaf buffer */
 	int			index,		/* leaf entry index */
 	xfs_da_state_blk_t	*dblk,		/* data block */
 	int			*rval)		/* resulting block needs join */
 {
 	xfs_dir2_data_hdr_t	*hdr;		/* data block header */
 	xfs_dir2_db_t		db;		/* data block number */
-	xfs_dabuf_t		*dbp;		/* data block buffer */
+	struct xfs_buf		*dbp;		/* data block buffer */
 	xfs_dir2_data_entry_t	*dep;		/* data block entry */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
@@ -858,7 +857,7 @@ xfs_dir2_leafn_remove(
 	dp = args->dp;
 	tp = args->trans;
 	mp = dp->i_mount;
-	leaf = bp->data;
+	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	/*
 	 * Point to the entry we're removing.
@@ -884,7 +883,7 @@ xfs_dir2_leafn_remove(
 	 * in the data block in case it changes.
 	 */
 	dbp = dblk->bp;
-	hdr = dbp->data;
+	hdr = dbp->b_addr;
 	dep = (xfs_dir2_data_entry_t *)((char *)hdr + off);
 	longest = be16_to_cpu(hdr->bestfree[0].length);
 	needlog = needscan = 0;
@@ -905,7 +904,7 @@ xfs_dir2_leafn_remove(
 	 */
 	if (longest < be16_to_cpu(hdr->bestfree[0].length)) {
 		int		error;		/* error return value */
-		xfs_dabuf_t	*fbp;		/* freeblock buffer */
+		struct xfs_buf	*fbp;		/* freeblock buffer */
 		xfs_dir2_db_t	fdb;		/* freeblock block number */
 		int		findex;		/* index in freeblock entries */
 		xfs_dir2_free_t	*free;		/* freeblock structure */
@@ -920,7 +919,7 @@ xfs_dir2_leafn_remove(
 				-1, &fbp, XFS_DATA_FORK))) {
 			return error;
 		}
-		free = fbp->data;
+		free = fbp->b_addr;
 		ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
 		ASSERT(be32_to_cpu(free->hdr.firstdb) ==
 		       xfs_dir2_free_max_bests(mp) *
@@ -948,9 +947,7 @@ xfs_dir2_leafn_remove(
 			 * In this case just drop the buffer and some one else
 			 * will eventually get rid of the empty block.
 			 */
-			else if (error == ENOSPC && args->total == 0)
-				xfs_da_buf_done(dbp);
-			else
+			else if (!(error == ENOSPC && args->total == 0))
 				return error;
 		}
 		/*
@@ -1018,11 +1015,6 @@ xfs_dir2_leafn_remove(
 		 */
 		if (logfree)
 			xfs_dir2_free_log_bests(tp, fbp, findex, findex);
-		/*
-		 * Drop the buffer if we still have it.
-		 */
-		if (fbp)
-			xfs_da_buf_done(fbp);
 	}
 	xfs_dir2_leafn_check(dp, bp);
 	/*
@@ -1114,7 +1106,7 @@ xfs_dir2_leafn_toosmall(
 {
 	xfs_da_state_blk_t	*blk;		/* leaf block */
 	xfs_dablk_t		blkno;		/* leaf block number */
-	xfs_dabuf_t		*bp;		/* leaf buffer */
+	struct xfs_buf		*bp;		/* leaf buffer */
 	int			bytes;		/* bytes in use */
 	int			count;		/* leaf live entry count */
 	int			error;		/* error return value */
@@ -1130,7 +1122,7 @@ xfs_dir2_leafn_toosmall(
 	 * to coalesce with a sibling.
 	 */
 	blk = &state->path.blk[state->path.active - 1];
-	info = blk->bp->data;
+	info = blk->bp->b_addr;
 	ASSERT(info->magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	leaf = (xfs_dir2_leaf_t *)info;
 	count = be16_to_cpu(leaf->hdr.count) - be16_to_cpu(leaf->hdr.stale);
@@ -1189,7 +1181,7 @@ xfs_dir2_leafn_toosmall(
 		leaf = (xfs_dir2_leaf_t *)info;
 		count = be16_to_cpu(leaf->hdr.count) - be16_to_cpu(leaf->hdr.stale);
 		bytes = state->blocksize - (state->blocksize >> 2);
-		leaf = bp->data;
+		leaf = bp->b_addr;
 		ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 		count += be16_to_cpu(leaf->hdr.count) - be16_to_cpu(leaf->hdr.stale);
 		bytes -= count * (uint)sizeof(leaf->ents[0]);
@@ -1198,7 +1190,7 @@ xfs_dir2_leafn_toosmall(
 		 */
 		if (bytes >= 0)
 			break;
-		xfs_da_brelse(state->args->trans, bp);
+		xfs_trans_brelse(state->args->trans, bp);
 	}
 	/*
 	 * Didn't like either block, give up.
@@ -1207,11 +1199,7 @@ xfs_dir2_leafn_toosmall(
 		*action = 0;
 		return 0;
 	}
-	/*
-	 * Done with the sibling leaf block here, drop the dabuf
-	 * so path_shift can get it.
-	 */
-	xfs_da_buf_done(bp);
+
 	/*
 	 * Make altpath point to the block we want to keep (the lower
 	 * numbered block) and path point to the block we want to drop.
@@ -1247,8 +1235,8 @@ xfs_dir2_leafn_unbalance(
 	args = state->args;
 	ASSERT(drop_blk->magic == XFS_DIR2_LEAFN_MAGIC);
 	ASSERT(save_blk->magic == XFS_DIR2_LEAFN_MAGIC);
-	drop_leaf = drop_blk->bp->data;
-	save_leaf = save_blk->bp->data;
+	drop_leaf = drop_blk->bp->b_addr;
+	save_leaf = save_blk->bp->b_addr;
 	ASSERT(drop_leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	ASSERT(save_leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC));
 	/*
@@ -1356,13 +1344,13 @@ xfs_dir2_node_addname_int(
 {
 	xfs_dir2_data_hdr_t	*hdr;		/* data block header */
 	xfs_dir2_db_t		dbno;		/* data block number */
-	xfs_dabuf_t		*dbp;		/* data block buffer */
+	struct xfs_buf		*dbp;		/* data block buffer */
 	xfs_dir2_data_entry_t	*dep;		/* data entry pointer */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	xfs_dir2_data_unused_t	*dup;		/* data unused entry pointer */
 	int			error;		/* error return value */
 	xfs_dir2_db_t		fbno;		/* freespace block number */
-	xfs_dabuf_t		*fbp;		/* freespace buffer */
+	struct xfs_buf		*fbp;		/* freespace buffer */
 	int			findex;		/* freespace entry index */
 	xfs_dir2_free_t		*free=NULL;	/* freespace block structure */
 	xfs_dir2_db_t		ifbno;		/* initial freespace block no */
@@ -1390,7 +1378,7 @@ xfs_dir2_node_addname_int(
 		 * Remember initial freespace block number.
 		 */
 		ifbno = fblk->blkno;
-		free = fbp->data;
+		free = fbp->b_addr;
 		ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
 		findex = fblk->index;
 		/*
@@ -1474,7 +1462,7 @@ xfs_dir2_node_addname_int(
 			if (unlikely(fbp == NULL)) {
 				continue;
 			}
-			free = fbp->data;
+			free = fbp->b_addr;
 			ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
 			findex = 0;
 		}
@@ -1492,7 +1480,7 @@ xfs_dir2_node_addname_int(
 				/*
 				 * Drop the block.
 				 */
-				xfs_da_brelse(tp, fbp);
+				xfs_trans_brelse(tp, fbp);
 				fbp = NULL;
 				if (fblk && fblk->bp)
 					fblk->bp = NULL;
@@ -1507,36 +1495,23 @@ xfs_dir2_node_addname_int(
 		/*
 		 * Not allowed to allocate, return failure.
 		 */
-		if ((args->op_flags & XFS_DA_OP_JUSTCHECK) ||
-							args->total == 0) {
-			/*
-			 * Drop the freespace buffer unless it came from our
-			 * caller.
-			 */
-			if ((fblk == NULL || fblk->bp == NULL) && fbp != NULL)
-				xfs_da_buf_done(fbp);
+		if ((args->op_flags & XFS_DA_OP_JUSTCHECK) || args->total == 0)
 			return XFS_ERROR(ENOSPC);
-		}
+
 		/*
 		 * Allocate and initialize the new data block.
 		 */
 		if (unlikely((error = xfs_dir2_grow_inode(args,
 							 XFS_DIR2_DATA_SPACE,
 							 &dbno)) ||
-		    (error = xfs_dir2_data_init(args, dbno, &dbp)))) {
-			/*
-			 * Drop the freespace buffer unless it came from our
-			 * caller.
-			 */
-			if ((fblk == NULL || fblk->bp == NULL) && fbp != NULL)
-				xfs_da_buf_done(fbp);
+		    (error = xfs_dir2_data_init(args, dbno, &dbp))))
 			return error;
-		}
+
 		/*
 		 * If (somehow) we have a freespace block, get rid of it.
 		 */
 		if (fbp)
-			xfs_da_brelse(tp, fbp);
+			xfs_trans_brelse(tp, fbp);
 		if (fblk && fblk->bp)
 			fblk->bp = NULL;
 
@@ -1547,10 +1522,9 @@ xfs_dir2_node_addname_int(
 		fbno = xfs_dir2_db_to_fdb(mp, dbno);
 		if (unlikely(error = xfs_da_read_buf(tp, dp,
 				xfs_dir2_db_to_da(mp, fbno), -2, &fbp,
-				XFS_DATA_FORK))) {
-			xfs_da_buf_done(dbp);
+				XFS_DATA_FORK)))
 			return error;
-  		}
+
 		/*
 		 * If there wasn't a freespace block, the read will
 		 * return a NULL fbp.  Allocate and initialize a new one.
@@ -1598,7 +1572,7 @@ xfs_dir2_node_addname_int(
 			 * Initialize the new block to be empty, and remember
 			 * its first slot as our empty slot.
 			 */
-			free = fbp->data;
+			free = fbp->b_addr;
 			free->hdr.magic = cpu_to_be32(XFS_DIR2_FREE_MAGIC);
 			free->hdr.firstdb = cpu_to_be32(
 				(fbno - XFS_DIR2_FREE_FIRSTDB(mp)) *
@@ -1606,7 +1580,7 @@ xfs_dir2_node_addname_int(
 			free->hdr.nvalid = 0;
 			free->hdr.nused = 0;
 		} else {
-			free = fbp->data;
+			free = fbp->b_addr;
 			ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
 		}
 
@@ -1639,7 +1613,7 @@ xfs_dir2_node_addname_int(
 		 * We haven't allocated the data entry yet so this will
 		 * change again.
 		 */
-		hdr = dbp->data;
+		hdr = dbp->b_addr;
 		free->bests[findex] = hdr->bestfree[0].length;
 		logfree = 1;
 	}
@@ -1650,22 +1624,17 @@ xfs_dir2_node_addname_int(
 		/*
 		 * If just checking, we succeeded.
 		 */
-		if (args->op_flags & XFS_DA_OP_JUSTCHECK) {
-			if ((fblk == NULL || fblk->bp == NULL) && fbp != NULL)
-				xfs_da_buf_done(fbp);
+		if (args->op_flags & XFS_DA_OP_JUSTCHECK)
 			return 0;
-		}
+
 		/*
 		 * Read the data block in.
 		 */
-		if (unlikely(
-		    error = xfs_da_read_buf(tp, dp, xfs_dir2_db_to_da(mp, dbno),
-				-1, &dbp, XFS_DATA_FORK))) {
-			if ((fblk == NULL || fblk->bp == NULL) && fbp != NULL)
-				xfs_da_buf_done(fbp);
+		error = xfs_da_read_buf(tp, dp, xfs_dir2_db_to_da(mp, dbno),
+				-1, &dbp, XFS_DATA_FORK);
+		if (error)
 			return error;
-		}
-		hdr = dbp->data;
+		hdr = dbp->b_addr;
 		logfree = 0;
 	}
 	ASSERT(be16_to_cpu(hdr->bestfree[0].length) >= length);
@@ -1714,16 +1683,10 @@ xfs_dir2_node_addname_int(
 	if (logfree)
 		xfs_dir2_free_log_bests(tp, fbp, findex, findex);
 	/*
-	 * If the caller didn't hand us the freespace block, drop it.
-	 */
-	if ((fblk == NULL || fblk->bp == NULL) && fbp != NULL)
-		xfs_da_buf_done(fbp);
-	/*
 	 * Return the data block and offset in args, then drop the data block.
 	 */
 	args->blkno = (xfs_dablk_t)dbno;
 	args->index = be16_to_cpu(*tagp);
-	xfs_da_buf_done(dbp);
 	return 0;
 }
 
@@ -1761,22 +1724,23 @@ xfs_dir2_node_lookup(
 		/* If a CI match, dup the actual name and return EEXIST */
 		xfs_dir2_data_entry_t	*dep;
 
-		dep = (xfs_dir2_data_entry_t *)((char *)state->extrablk.bp->
-						data + state->extrablk.index);
+		dep = (xfs_dir2_data_entry_t *)
+			((char *)state->extrablk.bp->b_addr +
+						 state->extrablk.index);
 		rval = xfs_dir_cilookup_result(args, dep->name, dep->namelen);
 	}
 	/*
 	 * Release the btree blocks and leaf block.
 	 */
 	for (i = 0; i < state->path.active; i++) {
-		xfs_da_brelse(args->trans, state->path.blk[i].bp);
+		xfs_trans_brelse(args->trans, state->path.blk[i].bp);
 		state->path.blk[i].bp = NULL;
 	}
 	/*
 	 * Release the data block if we have it.
 	 */
 	if (state->extravalid && state->extrablk.bp) {
-		xfs_da_brelse(args->trans, state->extrablk.bp);
+		xfs_trans_brelse(args->trans, state->extrablk.bp);
 		state->extrablk.bp = NULL;
 	}
 	xfs_da_state_free(state);
@@ -1893,13 +1857,13 @@ xfs_dir2_node_replace(
 		 */
 		blk = &state->path.blk[state->path.active - 1];
 		ASSERT(blk->magic == XFS_DIR2_LEAFN_MAGIC);
-		leaf = blk->bp->data;
+		leaf = blk->bp->b_addr;
 		lep = &leaf->ents[blk->index];
 		ASSERT(state->extravalid);
 		/*
 		 * Point to the data entry.
 		 */
-		hdr = state->extrablk.bp->data;
+		hdr = state->extrablk.bp->b_addr;
 		ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC));
 		dep = (xfs_dir2_data_entry_t *)
 		      ((char *)hdr +
@@ -1916,14 +1880,14 @@ xfs_dir2_node_replace(
 	 * Didn't find it, and we're holding a data block.  Drop it.
 	 */
 	else if (state->extravalid) {
-		xfs_da_brelse(args->trans, state->extrablk.bp);
+		xfs_trans_brelse(args->trans, state->extrablk.bp);
 		state->extrablk.bp = NULL;
 	}
 	/*
 	 * Release all the buffers in the cursor.
 	 */
 	for (i = 0; i < state->path.active; i++) {
-		xfs_da_brelse(args->trans, state->path.blk[i].bp);
+		xfs_trans_brelse(args->trans, state->path.blk[i].bp);
 		state->path.blk[i].bp = NULL;
 	}
 	xfs_da_state_free(state);
@@ -1940,7 +1904,7 @@ xfs_dir2_node_trim_free(
 	xfs_fileoff_t		fo,		/* free block number */
 	int			*rvalp)		/* out: did something */
 {
-	xfs_dabuf_t		*bp;		/* freespace buffer */
+	struct xfs_buf		*bp;		/* freespace buffer */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return code */
 	xfs_dir2_free_t		*free;		/* freespace structure */
@@ -1965,13 +1929,13 @@ xfs_dir2_node_trim_free(
 	if (bp == NULL) {
 		return 0;
 	}
-	free = bp->data;
+	free = bp->b_addr;
 	ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC));
 	/*
 	 * If there are used entries, there's nothing to do.
 	 */
 	if (be32_to_cpu(free->hdr.nused) > 0) {
-		xfs_da_brelse(tp, bp);
+		xfs_trans_brelse(tp, bp);
 		*rvalp = 0;
 		return 0;
 	}
@@ -1987,7 +1951,7 @@ xfs_dir2_node_trim_free(
 		 * pieces.  This is the last block of an extent.
 		 */
 		ASSERT(error != ENOSPC);
-		xfs_da_brelse(tp, bp);
+		xfs_trans_brelse(tp, bp);
 		return error;
 	}
 	/*
diff --git a/fs/xfs/xfs_dir2_priv.h b/fs/xfs/xfs_dir2_priv.h
index 067f403ecf8a..3523d3e15aa8 100644
--- a/fs/xfs/xfs_dir2_priv.h
+++ b/fs/xfs/xfs_dir2_priv.h
@@ -25,7 +25,7 @@ extern int xfs_dir2_isleaf(struct xfs_trans *tp, struct xfs_inode *dp, int *r);
 extern int xfs_dir2_grow_inode(struct xfs_da_args *args, int space,
 				xfs_dir2_db_t *dbp);
 extern int xfs_dir2_shrink_inode(struct xfs_da_args *args, xfs_dir2_db_t db,
-				struct xfs_dabuf *bp);
+				struct xfs_buf *bp);
 extern int xfs_dir_cilookup_result(struct xfs_da_args *args,
 				const unsigned char *name, int len);
 
@@ -37,11 +37,11 @@ extern int xfs_dir2_block_lookup(struct xfs_da_args *args);
 extern int xfs_dir2_block_removename(struct xfs_da_args *args);
 extern int xfs_dir2_block_replace(struct xfs_da_args *args);
 extern int xfs_dir2_leaf_to_block(struct xfs_da_args *args,
-		struct xfs_dabuf *lbp, struct xfs_dabuf *dbp);
+		struct xfs_buf *lbp, struct xfs_buf *dbp);
 
 /* xfs_dir2_data.c */
 #ifdef DEBUG
-extern void xfs_dir2_data_check(struct xfs_inode *dp, struct xfs_dabuf *bp);
+extern void xfs_dir2_data_check(struct xfs_inode *dp, struct xfs_buf *bp);
 #else
 #define	xfs_dir2_data_check(dp,bp)
 #endif
@@ -51,43 +51,43 @@ xfs_dir2_data_freeinsert(struct xfs_dir2_data_hdr *hdr,
 extern void xfs_dir2_data_freescan(struct xfs_mount *mp,
 		struct xfs_dir2_data_hdr *hdr, int *loghead);
 extern int xfs_dir2_data_init(struct xfs_da_args *args, xfs_dir2_db_t blkno,
-		struct xfs_dabuf **bpp);
-extern void xfs_dir2_data_log_entry(struct xfs_trans *tp, struct xfs_dabuf *bp,
+		struct xfs_buf **bpp);
+extern void xfs_dir2_data_log_entry(struct xfs_trans *tp, struct xfs_buf *bp,
 		struct xfs_dir2_data_entry *dep);
 extern void xfs_dir2_data_log_header(struct xfs_trans *tp,
-		struct xfs_dabuf *bp);
-extern void xfs_dir2_data_log_unused(struct xfs_trans *tp, struct xfs_dabuf *bp,
+		struct xfs_buf *bp);
+extern void xfs_dir2_data_log_unused(struct xfs_trans *tp, struct xfs_buf *bp,
 		struct xfs_dir2_data_unused *dup);
-extern void xfs_dir2_data_make_free(struct xfs_trans *tp, struct xfs_dabuf *bp,
+extern void xfs_dir2_data_make_free(struct xfs_trans *tp, struct xfs_buf *bp,
 		xfs_dir2_data_aoff_t offset, xfs_dir2_data_aoff_t len,
 		int *needlogp, int *needscanp);
-extern void xfs_dir2_data_use_free(struct xfs_trans *tp, struct xfs_dabuf *bp,
+extern void xfs_dir2_data_use_free(struct xfs_trans *tp, struct xfs_buf *bp,
 		struct xfs_dir2_data_unused *dup, xfs_dir2_data_aoff_t offset,
 		xfs_dir2_data_aoff_t len, int *needlogp, int *needscanp);
 
 /* xfs_dir2_leaf.c */
 extern int xfs_dir2_block_to_leaf(struct xfs_da_args *args,
-		struct xfs_dabuf *dbp);
+		struct xfs_buf *dbp);
 extern int xfs_dir2_leaf_addname(struct xfs_da_args *args);
 extern void xfs_dir2_leaf_compact(struct xfs_da_args *args,
-		struct xfs_dabuf *bp);
-extern void xfs_dir2_leaf_compact_x1(struct xfs_dabuf *bp, int *indexp,
+		struct xfs_buf *bp);
+extern void xfs_dir2_leaf_compact_x1(struct xfs_buf *bp, int *indexp,
 		int *lowstalep, int *highstalep, int *lowlogp, int *highlogp);
 extern int xfs_dir2_leaf_getdents(struct xfs_inode *dp, void *dirent,
 		size_t bufsize, xfs_off_t *offset, filldir_t filldir);
 extern int xfs_dir2_leaf_init(struct xfs_da_args *args, xfs_dir2_db_t bno,
-		struct xfs_dabuf **bpp, int magic);
-extern void xfs_dir2_leaf_log_ents(struct xfs_trans *tp, struct xfs_dabuf *bp,
+		struct xfs_buf **bpp, int magic);
+extern void xfs_dir2_leaf_log_ents(struct xfs_trans *tp, struct xfs_buf *bp,
 		int first, int last);
 extern void xfs_dir2_leaf_log_header(struct xfs_trans *tp,
-		struct xfs_dabuf *bp);
+		struct xfs_buf *bp);
 extern int xfs_dir2_leaf_lookup(struct xfs_da_args *args);
 extern int xfs_dir2_leaf_removename(struct xfs_da_args *args);
 extern int xfs_dir2_leaf_replace(struct xfs_da_args *args);
 extern int xfs_dir2_leaf_search_hash(struct xfs_da_args *args,
-		struct xfs_dabuf *lbp);
+		struct xfs_buf *lbp);
 extern int xfs_dir2_leaf_trim_data(struct xfs_da_args *args,
-		struct xfs_dabuf *lbp, xfs_dir2_db_t db);
+		struct xfs_buf *lbp, xfs_dir2_db_t db);
 extern struct xfs_dir2_leaf_entry *
 xfs_dir2_leaf_find_entry(struct xfs_dir2_leaf *leaf, int index, int compact,
 		int lowstale, int highstale,
@@ -96,13 +96,13 @@ extern int xfs_dir2_node_to_leaf(struct xfs_da_state *state);
 
 /* xfs_dir2_node.c */
 extern int xfs_dir2_leaf_to_node(struct xfs_da_args *args,
-		struct xfs_dabuf *lbp);
-extern xfs_dahash_t xfs_dir2_leafn_lasthash(struct xfs_dabuf *bp, int *count);
-extern int xfs_dir2_leafn_lookup_int(struct xfs_dabuf *bp,
+		struct xfs_buf *lbp);
+extern xfs_dahash_t xfs_dir2_leafn_lasthash(struct xfs_buf *bp, int *count);
+extern int xfs_dir2_leafn_lookup_int(struct xfs_buf *bp,
 		struct xfs_da_args *args, int *indexp,
 		struct xfs_da_state *state);
-extern int xfs_dir2_leafn_order(struct xfs_dabuf *leaf1_bp,
-		struct xfs_dabuf *leaf2_bp);
+extern int xfs_dir2_leafn_order(struct xfs_buf *leaf1_bp,
+		struct xfs_buf *leaf2_bp);
 extern int xfs_dir2_leafn_split(struct xfs_da_state *state,
 	struct xfs_da_state_blk *oldblk, struct xfs_da_state_blk *newblk);
 extern int xfs_dir2_leafn_toosmall(struct xfs_da_state *state, int *action);
@@ -122,7 +122,7 @@ extern xfs_ino_t xfs_dir2_sfe_get_ino(struct xfs_dir2_sf_hdr *sfp,
 		struct xfs_dir2_sf_entry *sfep);
 extern int xfs_dir2_block_sfsize(struct xfs_inode *dp,
 		struct xfs_dir2_data_hdr *block, struct xfs_dir2_sf_hdr *sfhp);
-extern int xfs_dir2_block_to_sf(struct xfs_da_args *args, struct xfs_dabuf *bp,
+extern int xfs_dir2_block_to_sf(struct xfs_da_args *args, struct xfs_buf *bp,
 		int size, xfs_dir2_sf_hdr_t *sfhp);
 extern int xfs_dir2_sf_addname(struct xfs_da_args *args);
 extern int xfs_dir2_sf_create(struct xfs_da_args *args, xfs_ino_t pino);
diff --git a/fs/xfs/xfs_dir2_sf.c b/fs/xfs/xfs_dir2_sf.c
index 19bf0c5e38f4..1b9fc3ec7e4b 100644
--- a/fs/xfs/xfs_dir2_sf.c
+++ b/fs/xfs/xfs_dir2_sf.c
@@ -222,7 +222,7 @@ xfs_dir2_block_sfsize(
 int						/* error */
 xfs_dir2_block_to_sf(
 	xfs_da_args_t		*args,		/* operation arguments */
-	xfs_dabuf_t		*bp,		/* block buffer */
+	struct xfs_buf		*bp,
 	int			size,		/* shortform directory size */
 	xfs_dir2_sf_hdr_t	*sfhp)		/* shortform directory hdr */
 {
@@ -249,7 +249,7 @@ xfs_dir2_block_to_sf(
 	 * and add local data.
 	 */
 	hdr = kmem_alloc(mp->m_dirblksize, KM_SLEEP);
-	memcpy(hdr, bp->data, mp->m_dirblksize);
+	memcpy(hdr, bp->b_addr, mp->m_dirblksize);
 	logflags = XFS_ILOG_CORE;
 	if ((error = xfs_dir2_shrink_inode(args, mp->m_dirdatablk, bp))) {
 		ASSERT(error != ENOSPC);
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 9f7ec15a6522..56afcdb2377d 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -236,7 +236,6 @@ xfs_file_aio_read(
 	ssize_t			ret = 0;
 	int			ioflags = 0;
 	xfs_fsize_t		n;
-	unsigned long		seg;
 
 	XFS_STATS_INC(xs_read_calls);
 
@@ -247,19 +246,9 @@ xfs_file_aio_read(
 	if (file->f_mode & FMODE_NOCMTIME)
 		ioflags |= IO_INVIS;
 
-	/* START copy & waste from filemap.c */
-	for (seg = 0; seg < nr_segs; seg++) {
-		const struct iovec *iv = &iovp[seg];
-
-		/*
-		 * If any segment has a negative length, or the cumulative
-		 * length ever wraps negative then return -EINVAL.
-		 */
-		size += iv->iov_len;
-		if (unlikely((ssize_t)(size|iv->iov_len) < 0))
-			return XFS_ERROR(-EINVAL);
-	}
-	/* END copy & waste from filemap.c */
+	ret = generic_segment_checks(iovp, &nr_segs, &size, VERIFY_WRITE);
+	if (ret < 0)
+		return ret;
 
 	if (unlikely(ioflags & IO_ISDIRECT)) {
 		xfs_buftarg_t	*target =
@@ -273,7 +262,7 @@ xfs_file_aio_read(
 		}
 	}
 
-	n = XFS_MAXIOFFSET(mp) - iocb->ki_pos;
+	n = mp->m_super->s_maxbytes - iocb->ki_pos;
 	if (n <= 0 || size == 0)
 		return 0;
 
@@ -781,10 +770,12 @@ xfs_file_aio_write(
 	if (ocount == 0)
 		return 0;
 
-	xfs_wait_for_freeze(ip->i_mount, SB_FREEZE_WRITE);
+	sb_start_write(inode->i_sb);
 
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
-		return -EIO;
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
+		ret = -EIO;
+		goto out;
+	}
 
 	if (unlikely(file->f_flags & O_DIRECT))
 		ret = xfs_file_dio_aio_write(iocb, iovp, nr_segs, pos, ocount);
@@ -803,6 +794,8 @@ xfs_file_aio_write(
 			ret = err;
 	}
 
+out:
+	sb_end_write(inode->i_sb);
 	return ret;
 }
 
diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c
index 177a21a7ac49..21e37b55f7e5 100644
--- a/fs/xfs/xfs_ialloc.c
+++ b/fs/xfs/xfs_ialloc.c
@@ -442,14 +442,13 @@ xfs_ialloc_next_ag(
  * Select an allocation group to look for a free inode in, based on the parent
  * inode and then mode.  Return the allocation group buffer.
  */
-STATIC xfs_buf_t *			/* allocation group buffer */
+STATIC xfs_agnumber_t
 xfs_ialloc_ag_select(
 	xfs_trans_t	*tp,		/* transaction pointer */
 	xfs_ino_t	parent,		/* parent directory inode number */
 	umode_t		mode,		/* bits set to indicate file type */
 	int		okalloc)	/* ok to allocate more space */
 {
-	xfs_buf_t	*agbp;		/* allocation group header buffer */
 	xfs_agnumber_t	agcount;	/* number of ag's in the filesystem */
 	xfs_agnumber_t	agno;		/* current ag number */
 	int		flags;		/* alloc buffer locking flags */
@@ -459,6 +458,7 @@ xfs_ialloc_ag_select(
 	int		needspace;	/* file mode implies space allocated */
 	xfs_perag_t	*pag;		/* per allocation group data */
 	xfs_agnumber_t	pagno;		/* parent (starting) ag number */
+	int		error;
 
 	/*
 	 * Files of these types need at least one block if length > 0
@@ -474,7 +474,9 @@ xfs_ialloc_ag_select(
 		if (pagno >= agcount)
 			pagno = 0;
 	}
+
 	ASSERT(pagno < agcount);
+
 	/*
 	 * Loop through allocation groups, looking for one with a little
 	 * free space in it.  Note we don't look for free inodes, exactly.
@@ -486,51 +488,45 @@ xfs_ialloc_ag_select(
 	flags = XFS_ALLOC_FLAG_TRYLOCK;
 	for (;;) {
 		pag = xfs_perag_get(mp, agno);
+		if (!pag->pagi_inodeok) {
+			xfs_ialloc_next_ag(mp);
+			goto nextag;
+		}
+
 		if (!pag->pagi_init) {
-			if (xfs_ialloc_read_agi(mp, tp, agno, &agbp)) {
-				agbp = NULL;
+			error = xfs_ialloc_pagi_init(mp, tp, agno);
+			if (error)
 				goto nextag;
-			}
-		} else
-			agbp = NULL;
+		}
 
-		if (!pag->pagi_inodeok) {
-			xfs_ialloc_next_ag(mp);
-			goto unlock_nextag;
+		if (pag->pagi_freecount) {
+			xfs_perag_put(pag);
+			return agno;
 		}
 
-		/*
-		 * Is there enough free space for the file plus a block
-		 * of inodes (if we need to allocate some)?
-		 */
-		ineed = pag->pagi_freecount ? 0 : XFS_IALLOC_BLOCKS(mp);
-		if (ineed && !pag->pagf_init) {
-			if (agbp == NULL &&
-			    xfs_ialloc_read_agi(mp, tp, agno, &agbp)) {
-				agbp = NULL;
+		if (!okalloc)
+			goto nextag;
+
+		if (!pag->pagf_init) {
+			error = xfs_alloc_pagf_init(mp, tp, agno, flags);
+			if (error)
 				goto nextag;
-			}
-			(void)xfs_alloc_pagf_init(mp, tp, agno, flags);
 		}
-		if (!ineed || pag->pagf_init) {
-			if (ineed && !(longest = pag->pagf_longest))
-				longest = pag->pagf_flcount > 0;
-			if (!ineed ||
-			    (pag->pagf_freeblks >= needspace + ineed &&
-			     longest >= ineed &&
-			     okalloc)) {
-				if (agbp == NULL &&
-				    xfs_ialloc_read_agi(mp, tp, agno, &agbp)) {
-					agbp = NULL;
-					goto nextag;
-				}
-				xfs_perag_put(pag);
-				return agbp;
-			}
+
+		/*
+		 * Is there enough free space for the file plus a block of
+		 * inodes? (if we need to allocate some)?
+		 */
+		ineed = XFS_IALLOC_BLOCKS(mp);
+		longest = pag->pagf_longest;
+		if (!longest)
+			longest = pag->pagf_flcount > 0;
+
+		if (pag->pagf_freeblks >= needspace + ineed &&
+		    longest >= ineed) {
+			xfs_perag_put(pag);
+			return agno;
 		}
-unlock_nextag:
-		if (agbp)
-			xfs_trans_brelse(tp, agbp);
 nextag:
 		xfs_perag_put(pag);
 		/*
@@ -538,13 +534,13 @@ nextag:
 		 * down.
 		 */
 		if (XFS_FORCED_SHUTDOWN(mp))
-			return NULL;
+			return NULLAGNUMBER;
 		agno++;
 		if (agno >= agcount)
 			agno = 0;
 		if (agno == pagno) {
 			if (flags == 0)
-				return NULL;
+				return NULLAGNUMBER;
 			flags = 0;
 		}
 	}
@@ -607,195 +603,39 @@ xfs_ialloc_get_rec(
 }
 
 /*
- * Visible inode allocation functions.
- */
-/*
- * Find a free (set) bit in the inode bitmask.
- */
-static inline int xfs_ialloc_find_free(xfs_inofree_t *fp)
-{
-	return xfs_lowbit64(*fp);
-}
-
-/*
- * Allocate an inode on disk.
- * Mode is used to tell whether the new inode will need space, and whether
- * it is a directory.
- *
- * The arguments IO_agbp and alloc_done are defined to work within
- * the constraint of one allocation per transaction.
- * xfs_dialloc() is designed to be called twice if it has to do an
- * allocation to make more free inodes.  On the first call,
- * IO_agbp should be set to NULL. If an inode is available,
- * i.e., xfs_dialloc() did not need to do an allocation, an inode
- * number is returned.  In this case, IO_agbp would be set to the
- * current ag_buf and alloc_done set to false.
- * If an allocation needed to be done, xfs_dialloc would return
- * the current ag_buf in IO_agbp and set alloc_done to true.
- * The caller should then commit the current transaction, allocate a new
- * transaction, and call xfs_dialloc() again, passing in the previous
- * value of IO_agbp.  IO_agbp should be held across the transactions.
- * Since the agbp is locked across the two calls, the second call is
- * guaranteed to have a free inode available.
+ * Allocate an inode.
  *
- * Once we successfully pick an inode its number is returned and the
- * on-disk data structures are updated.  The inode itself is not read
- * in, since doing so would break ordering constraints with xfs_reclaim.
+ * The caller selected an AG for us, and made sure that free inodes are
+ * available.
  */
-int
-xfs_dialloc(
-	xfs_trans_t	*tp,		/* transaction pointer */
-	xfs_ino_t	parent,		/* parent inode (directory) */
-	umode_t		mode,		/* mode bits for new inode */
-	int		okalloc,	/* ok to allocate more space */
-	xfs_buf_t	**IO_agbp,	/* in/out ag header's buffer */
-	boolean_t	*alloc_done,	/* true if we needed to replenish
-					   inode freelist */
-	xfs_ino_t	*inop)		/* inode number allocated */
+STATIC int
+xfs_dialloc_ag(
+	struct xfs_trans	*tp,
+	struct xfs_buf		*agbp,
+	xfs_ino_t		parent,
+	xfs_ino_t		*inop)
 {
-	xfs_agnumber_t	agcount;	/* number of allocation groups */
-	xfs_buf_t	*agbp;		/* allocation group header's buffer */
-	xfs_agnumber_t	agno;		/* allocation group number */
-	xfs_agi_t	*agi;		/* allocation group header structure */
-	xfs_btree_cur_t	*cur;		/* inode allocation btree cursor */
-	int		error;		/* error return value */
-	int		i;		/* result code */
-	int		ialloced;	/* inode allocation status */
-	int		noroom = 0;	/* no space for inode blk allocation */
-	xfs_ino_t	ino;		/* fs-relative inode to be returned */
-	/* REFERENCED */
-	int		j;		/* result code */
-	xfs_mount_t	*mp;		/* file system mount structure */
-	int		offset;		/* index of inode in chunk */
-	xfs_agino_t	pagino;		/* parent's AG relative inode # */
-	xfs_agnumber_t	pagno;		/* parent's AG number */
-	xfs_inobt_rec_incore_t rec;	/* inode allocation record */
-	xfs_agnumber_t	tagno;		/* testing allocation group number */
-	xfs_btree_cur_t	*tcur;		/* temp cursor */
-	xfs_inobt_rec_incore_t trec;	/* temp inode allocation record */
-	struct xfs_perag *pag;
-
-
-	if (*IO_agbp == NULL) {
-		/*
-		 * We do not have an agbp, so select an initial allocation
-		 * group for inode allocation.
-		 */
-		agbp = xfs_ialloc_ag_select(tp, parent, mode, okalloc);
-		/*
-		 * Couldn't find an allocation group satisfying the
-		 * criteria, give up.
-		 */
-		if (!agbp) {
-			*inop = NULLFSINO;
-			return 0;
-		}
-		agi = XFS_BUF_TO_AGI(agbp);
-		ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC));
-	} else {
-		/*
-		 * Continue where we left off before.  In this case, we
-		 * know that the allocation group has free inodes.
-		 */
-		agbp = *IO_agbp;
-		agi = XFS_BUF_TO_AGI(agbp);
-		ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC));
-		ASSERT(be32_to_cpu(agi->agi_freecount) > 0);
-	}
-	mp = tp->t_mountp;
-	agcount = mp->m_sb.sb_agcount;
-	agno = be32_to_cpu(agi->agi_seqno);
-	tagno = agno;
-	pagno = XFS_INO_TO_AGNO(mp, parent);
-	pagino = XFS_INO_TO_AGINO(mp, parent);
-
-	/*
-	 * If we have already hit the ceiling of inode blocks then clear
-	 * okalloc so we scan all available agi structures for a free
-	 * inode.
-	 */
-
-	if (mp->m_maxicount &&
-	    mp->m_sb.sb_icount + XFS_IALLOC_INODES(mp) > mp->m_maxicount) {
-		noroom = 1;
-		okalloc = 0;
-	}
+	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agbp);
+	xfs_agnumber_t		agno = be32_to_cpu(agi->agi_seqno);
+	xfs_agnumber_t		pagno = XFS_INO_TO_AGNO(mp, parent);
+	xfs_agino_t		pagino = XFS_INO_TO_AGINO(mp, parent);
+	struct xfs_perag	*pag;
+	struct xfs_btree_cur	*cur, *tcur;
+	struct xfs_inobt_rec_incore rec, trec;
+	xfs_ino_t		ino;
+	int			error;
+	int			offset;
+	int			i, j;
 
-	/*
-	 * Loop until we find an allocation group that either has free inodes
-	 * or in which we can allocate some inodes.  Iterate through the
-	 * allocation groups upward, wrapping at the end.
-	 */
-	*alloc_done = B_FALSE;
-	while (!agi->agi_freecount) {
-		/*
-		 * Don't do anything if we're not supposed to allocate
-		 * any blocks, just go on to the next ag.
-		 */
-		if (okalloc) {
-			/*
-			 * Try to allocate some new inodes in the allocation
-			 * group.
-			 */
-			if ((error = xfs_ialloc_ag_alloc(tp, agbp, &ialloced))) {
-				xfs_trans_brelse(tp, agbp);
-				if (error == ENOSPC) {
-					*inop = NULLFSINO;
-					return 0;
-				} else
-					return error;
-			}
-			if (ialloced) {
-				/*
-				 * We successfully allocated some inodes, return
-				 * the current context to the caller so that it
-				 * can commit the current transaction and call
-				 * us again where we left off.
-				 */
-				ASSERT(be32_to_cpu(agi->agi_freecount) > 0);
-				*alloc_done = B_TRUE;
-				*IO_agbp = agbp;
-				*inop = NULLFSINO;
-				return 0;
-			}
-		}
-		/*
-		 * If it failed, give up on this ag.
-		 */
-		xfs_trans_brelse(tp, agbp);
-		/*
-		 * Go on to the next ag: get its ag header.
-		 */
-nextag:
-		if (++tagno == agcount)
-			tagno = 0;
-		if (tagno == agno) {
-			*inop = NULLFSINO;
-			return noroom ? ENOSPC : 0;
-		}
-		pag = xfs_perag_get(mp, tagno);
-		if (pag->pagi_inodeok == 0) {
-			xfs_perag_put(pag);
-			goto nextag;
-		}
-		error = xfs_ialloc_read_agi(mp, tp, tagno, &agbp);
-		xfs_perag_put(pag);
-		if (error)
-			goto nextag;
-		agi = XFS_BUF_TO_AGI(agbp);
-		ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC));
-	}
-	/*
-	 * Here with an allocation group that has a free inode.
-	 * Reset agno since we may have chosen a new ag in the
-	 * loop above.
-	 */
-	agno = tagno;
-	*IO_agbp = NULL;
 	pag = xfs_perag_get(mp, agno);
 
+	ASSERT(pag->pagi_init);
+	ASSERT(pag->pagi_inodeok);
+	ASSERT(pag->pagi_freecount > 0);
+
  restart_pagno:
-	cur = xfs_inobt_init_cursor(mp, tp, agbp, be32_to_cpu(agi->agi_seqno));
+	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno);
 	/*
 	 * If pagino is 0 (this is the root inode allocation) use newino.
 	 * This must work because we've just allocated some.
@@ -995,7 +835,7 @@ newino:
 	}
 
 alloc_inode:
-	offset = xfs_ialloc_find_free(&rec.ir_free);
+	offset = xfs_lowbit64(rec.ir_free);
 	ASSERT(offset >= 0);
 	ASSERT(offset < XFS_INODES_PER_CHUNK);
 	ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) %
@@ -1028,6 +868,164 @@ error0:
 }
 
 /*
+ * Allocate an inode on disk.
+ *
+ * Mode is used to tell whether the new inode will need space, and whether it
+ * is a directory.
+ *
+ * This function is designed to be called twice if it has to do an allocation
+ * to make more free inodes.  On the first call, *IO_agbp should be set to NULL.
+ * If an inode is available without having to performn an allocation, an inode
+ * number is returned.  In this case, *IO_agbp would be NULL.  If an allocation
+ * needes to be done, xfs_dialloc would return the current AGI buffer in
+ * *IO_agbp.  The caller should then commit the current transaction, allocate a
+ * new transaction, and call xfs_dialloc() again, passing in the previous value
+ * of *IO_agbp.  IO_agbp should be held across the transactions. Since the AGI
+ * buffer is locked across the two calls, the second call is guaranteed to have
+ * a free inode available.
+ *
+ * Once we successfully pick an inode its number is returned and the on-disk
+ * data structures are updated.  The inode itself is not read in, since doing so
+ * would break ordering constraints with xfs_reclaim.
+ */
+int
+xfs_dialloc(
+	struct xfs_trans	*tp,
+	xfs_ino_t		parent,
+	umode_t			mode,
+	int			okalloc,
+	struct xfs_buf		**IO_agbp,
+	xfs_ino_t		*inop)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_buf		*agbp;
+	xfs_agnumber_t		agno;
+	int			error;
+	int			ialloced;
+	int			noroom = 0;
+	xfs_agnumber_t		start_agno;
+	struct xfs_perag	*pag;
+
+	if (*IO_agbp) {
+		/*
+		 * If the caller passes in a pointer to the AGI buffer,
+		 * continue where we left off before.  In this case, we
+		 * know that the allocation group has free inodes.
+		 */
+		agbp = *IO_agbp;
+		goto out_alloc;
+	}
+
+	/*
+	 * We do not have an agbp, so select an initial allocation
+	 * group for inode allocation.
+	 */
+	start_agno = xfs_ialloc_ag_select(tp, parent, mode, okalloc);
+	if (start_agno == NULLAGNUMBER) {
+		*inop = NULLFSINO;
+		return 0;
+	}
+
+	/*
+	 * If we have already hit the ceiling of inode blocks then clear
+	 * okalloc so we scan all available agi structures for a free
+	 * inode.
+	 */
+	if (mp->m_maxicount &&
+	    mp->m_sb.sb_icount + XFS_IALLOC_INODES(mp) > mp->m_maxicount) {
+		noroom = 1;
+		okalloc = 0;
+	}
+
+	/*
+	 * Loop until we find an allocation group that either has free inodes
+	 * or in which we can allocate some inodes.  Iterate through the
+	 * allocation groups upward, wrapping at the end.
+	 */
+	agno = start_agno;
+	for (;;) {
+		pag = xfs_perag_get(mp, agno);
+		if (!pag->pagi_inodeok) {
+			xfs_ialloc_next_ag(mp);
+			goto nextag;
+		}
+
+		if (!pag->pagi_init) {
+			error = xfs_ialloc_pagi_init(mp, tp, agno);
+			if (error)
+				goto out_error;
+		}
+
+		/*
+		 * Do a first racy fast path check if this AG is usable.
+		 */
+		if (!pag->pagi_freecount && !okalloc)
+			goto nextag;
+
+		error = xfs_ialloc_read_agi(mp, tp, agno, &agbp);
+		if (error)
+			goto out_error;
+
+		/*
+		 * Once the AGI has been read in we have to recheck
+		 * pagi_freecount with the AGI buffer lock held.
+		 */
+		if (pag->pagi_freecount) {
+			xfs_perag_put(pag);
+			goto out_alloc;
+		}
+
+		if (!okalloc) {
+			xfs_trans_brelse(tp, agbp);
+			goto nextag;
+		}
+
+		error = xfs_ialloc_ag_alloc(tp, agbp, &ialloced);
+		if (error) {
+			xfs_trans_brelse(tp, agbp);
+
+			if (error != ENOSPC)
+				goto out_error;
+
+			xfs_perag_put(pag);
+			*inop = NULLFSINO;
+			return 0;
+		}
+
+		if (ialloced) {
+			/*
+			 * We successfully allocated some inodes, return
+			 * the current context to the caller so that it
+			 * can commit the current transaction and call
+			 * us again where we left off.
+			 */
+			ASSERT(pag->pagi_freecount > 0);
+			xfs_perag_put(pag);
+
+			*IO_agbp = agbp;
+			*inop = NULLFSINO;
+			return 0;
+		}
+
+nextag:
+		xfs_perag_put(pag);
+		if (++agno == mp->m_sb.sb_agcount)
+			agno = 0;
+		if (agno == start_agno) {
+			*inop = NULLFSINO;
+			return noroom ? ENOSPC : 0;
+		}
+	}
+
+out_alloc:
+	*IO_agbp = NULL;
+	return xfs_dialloc_ag(tp, agbp, parent, inop);
+out_error:
+	xfs_perag_put(pag);
+	return XFS_ERROR(error);
+}
+
+/*
  * Free disk inode.  Carefully avoids touching the incore inode, all
  * manipulations incore are the caller's responsibility.
  * The on-disk inode is not changed by this operation, only the
diff --git a/fs/xfs/xfs_ialloc.h b/fs/xfs/xfs_ialloc.h
index 65ac57c8063c..1fd6ea4e9c91 100644
--- a/fs/xfs/xfs_ialloc.h
+++ b/fs/xfs/xfs_ialloc.h
@@ -75,8 +75,6 @@ xfs_dialloc(
 	umode_t		mode,		/* mode bits for new inode */
 	int		okalloc,	/* ok to allocate more space */
 	struct xfs_buf	**agbp,		/* buf for a.g. inode header */
-	boolean_t	*alloc_done,	/* an allocation was done to replenish
-					   the free inodes */
 	xfs_ino_t	*inop);		/* inode number allocated */
 
 /*
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index 1bb4365e8c25..784a803383ec 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -41,17 +41,6 @@
 
 
 /*
- * Define xfs inode iolock lockdep classes. We need to ensure that all active
- * inodes are considered the same for lockdep purposes, including inodes that
- * are recycled through the XFS_IRECLAIMABLE state. This is the the only way to
- * guarantee the locks are considered the same when there are multiple lock
- * initialisation siteѕ. Also, define a reclaimable inode class so it is
- * obvious in lockdep reports which class the report is against.
- */
-static struct lock_class_key xfs_iolock_active;
-struct lock_class_key xfs_iolock_reclaimable;
-
-/*
  * Allocate and initialise an xfs_inode.
  */
 STATIC struct xfs_inode *
@@ -80,8 +69,6 @@ xfs_inode_alloc(
 	ASSERT(ip->i_ino == 0);
 
 	mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino);
-	lockdep_set_class_and_name(&ip->i_iolock.mr_lock,
-			&xfs_iolock_active, "xfs_iolock_active");
 
 	/* initialise the xfs inode */
 	ip->i_ino = ino;
@@ -250,8 +237,6 @@ xfs_iget_cache_hit(
 
 		ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock));
 		mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino);
-		lockdep_set_class_and_name(&ip->i_iolock.mr_lock,
-				&xfs_iolock_active, "xfs_iolock_active");
 
 		spin_unlock(&ip->i_flags_lock);
 		spin_unlock(&pag->pag_ici_lock);
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index a59eea09930a..2778258fcfa2 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -132,23 +132,28 @@ xfs_inobp_check(
 #endif
 
 /*
- * Find the buffer associated with the given inode map
- * We do basic validation checks on the buffer once it has been
- * retrieved from disk.
+ * This routine is called to map an inode to the buffer containing the on-disk
+ * version of the inode.  It returns a pointer to the buffer containing the
+ * on-disk inode in the bpp parameter, and in the dipp parameter it returns a
+ * pointer to the on-disk inode within that buffer.
+ *
+ * If a non-zero error is returned, then the contents of bpp and dipp are
+ * undefined.
  */
-STATIC int
+int
 xfs_imap_to_bp(
-	xfs_mount_t	*mp,
-	xfs_trans_t	*tp,
-	struct xfs_imap	*imap,
-	xfs_buf_t	**bpp,
-	uint		buf_flags,
-	uint		iget_flags)
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	struct xfs_imap		*imap,
+	struct xfs_dinode	**dipp,
+	struct xfs_buf		**bpp,
+	uint			buf_flags,
+	uint			iget_flags)
 {
-	int		error;
-	int		i;
-	int		ni;
-	xfs_buf_t	*bp;
+	struct xfs_buf		*bp;
+	int			error;
+	int			i;
+	int			ni;
 
 	buf_flags |= XBF_UNMAPPED;
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
@@ -189,8 +194,8 @@ xfs_imap_to_bp(
 				xfs_trans_brelse(tp, bp);
 				return XFS_ERROR(EINVAL);
 			}
-			XFS_CORRUPTION_ERROR("xfs_imap_to_bp",
-						XFS_ERRLEVEL_HIGH, mp, dip);
+			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_HIGH,
+					     mp, dip);
 #ifdef DEBUG
 			xfs_emerg(mp,
 				"bad inode magic/vsn daddr %lld #%d (magic=%x)",
@@ -204,96 +209,9 @@ xfs_imap_to_bp(
 	}
 
 	xfs_inobp_check(mp, bp);
-	*bpp = bp;
-	return 0;
-}
-
-/*
- * This routine is called to map an inode number within a file
- * system to the buffer containing the on-disk version of the
- * inode.  It returns a pointer to the buffer containing the
- * on-disk inode in the bpp parameter, and in the dip parameter
- * it returns a pointer to the on-disk inode within that buffer.
- *
- * If a non-zero error is returned, then the contents of bpp and
- * dipp are undefined.
- *
- * Use xfs_imap() to determine the size and location of the
- * buffer to read from disk.
- */
-int
-xfs_inotobp(
-	xfs_mount_t	*mp,
-	xfs_trans_t	*tp,
-	xfs_ino_t	ino,
-	xfs_dinode_t	**dipp,
-	xfs_buf_t	**bpp,
-	int		*offset,
-	uint		imap_flags)
-{
-	struct xfs_imap	imap;
-	xfs_buf_t	*bp;
-	int		error;
-
-	imap.im_blkno = 0;
-	error = xfs_imap(mp, tp, ino, &imap, imap_flags);
-	if (error)
-		return error;
-
-	error = xfs_imap_to_bp(mp, tp, &imap, &bp, 0, imap_flags);
-	if (error)
-		return error;
-
-	*dipp = (xfs_dinode_t *)xfs_buf_offset(bp, imap.im_boffset);
-	*bpp = bp;
-	*offset = imap.im_boffset;
-	return 0;
-}
-
-
-/*
- * This routine is called to map an inode to the buffer containing
- * the on-disk version of the inode.  It returns a pointer to the
- * buffer containing the on-disk inode in the bpp parameter, and in
- * the dip parameter it returns a pointer to the on-disk inode within
- * that buffer.
- *
- * If a non-zero error is returned, then the contents of bpp and
- * dipp are undefined.
- *
- * The inode is expected to already been mapped to its buffer and read
- * in once, thus we can use the mapping information stored in the inode
- * rather than calling xfs_imap().  This allows us to avoid the overhead
- * of looking at the inode btree for small block file systems
- * (see xfs_imap()).
- */
-int
-xfs_itobp(
-	xfs_mount_t	*mp,
-	xfs_trans_t	*tp,
-	xfs_inode_t	*ip,
-	xfs_dinode_t	**dipp,
-	xfs_buf_t	**bpp,
-	uint		buf_flags)
-{
-	xfs_buf_t	*bp;
-	int		error;
-
-	ASSERT(ip->i_imap.im_blkno != 0);
-
-	error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &bp, buf_flags, 0);
-	if (error)
-		return error;
 
-	if (!bp) {
-		ASSERT(buf_flags & XBF_TRYLOCK);
-		ASSERT(tp == NULL);
-		*bpp = NULL;
-		return EAGAIN;
-	}
-
-	*dipp = (xfs_dinode_t *)xfs_buf_offset(bp, ip->i_imap.im_boffset);
 	*bpp = bp;
+	*dipp = (struct xfs_dinode *)xfs_buf_offset(bp, imap->im_boffset);
 	return 0;
 }
 
@@ -796,10 +714,9 @@ xfs_iread(
 	/*
 	 * Get pointers to the on-disk inode and the buffer containing it.
 	 */
-	error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &bp, 0, iget_flags);
+	error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &bp, 0, iget_flags);
 	if (error)
 		return error;
-	dip = (xfs_dinode_t *)xfs_buf_offset(bp, ip->i_imap.im_boffset);
 
 	/*
 	 * If we got something that isn't an inode it means someone
@@ -876,7 +793,7 @@ xfs_iread(
 	/*
 	 * Use xfs_trans_brelse() to release the buffer containing the
 	 * on-disk inode, because it was acquired with xfs_trans_read_buf()
-	 * in xfs_itobp() above.  If tp is NULL, this is just a normal
+	 * in xfs_imap_to_bp() above.  If tp is NULL, this is just a normal
 	 * brelse().  If we're within a transaction, then xfs_trans_brelse()
 	 * will only release the buffer if it is not dirty within the
 	 * transaction.  It will be OK to release the buffer in this case,
@@ -970,7 +887,6 @@ xfs_ialloc(
 	prid_t		prid,
 	int		okalloc,
 	xfs_buf_t	**ialloc_context,
-	boolean_t	*call_again,
 	xfs_inode_t	**ipp)
 {
 	xfs_ino_t	ino;
@@ -985,10 +901,10 @@ xfs_ialloc(
 	 * the on-disk inode to be allocated.
 	 */
 	error = xfs_dialloc(tp, pip ? pip->i_ino : 0, mode, okalloc,
-			    ialloc_context, call_again, &ino);
+			    ialloc_context, &ino);
 	if (error)
 		return error;
-	if (*call_again || ino == NULLFSINO) {
+	if (*ialloc_context || ino == NULLFSINO) {
 		*ipp = NULL;
 		return 0;
 	}
@@ -1207,7 +1123,9 @@ xfs_itruncate_extents(
 	int			error = 0;
 	int			done = 0;
 
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+	ASSERT(!atomic_read(&VFS_I(ip)->i_count) ||
+	       xfs_isilocked(ip, XFS_IOLOCK_EXCL));
 	ASSERT(new_size <= XFS_ISIZE(ip));
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
 	ASSERT(ip->i_itemp != NULL);
@@ -1226,7 +1144,7 @@ xfs_itruncate_extents(
 	 * then there is nothing to do.
 	 */
 	first_unmap_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)new_size);
-	last_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_MAXIOFFSET(mp));
+	last_block = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
 	if (first_unmap_block == last_block)
 		return 0;
 
@@ -1355,7 +1273,8 @@ xfs_iunlink(
 		 * Here we put the head pointer into our next pointer,
 		 * and then we fall through to point the head at us.
 		 */
-		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0);
+		error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &ibp,
+				       0, 0);
 		if (error)
 			return error;
 
@@ -1429,16 +1348,16 @@ xfs_iunlink_remove(
 
 	if (be32_to_cpu(agi->agi_unlinked[bucket_index]) == agino) {
 		/*
-		 * We're at the head of the list.  Get the inode's
-		 * on-disk buffer to see if there is anyone after us
-		 * on the list.  Only modify our next pointer if it
-		 * is not already NULLAGINO.  This saves us the overhead
-		 * of dealing with the buffer when there is no need to
-		 * change it.
+		 * We're at the head of the list.  Get the inode's on-disk
+		 * buffer to see if there is anyone after us on the list.
+		 * Only modify our next pointer if it is not already NULLAGINO.
+		 * This saves us the overhead of dealing with the buffer when
+		 * there is no need to change it.
 		 */
-		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0);
+		error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &ibp,
+				       0, 0);
 		if (error) {
-			xfs_warn(mp, "%s: xfs_itobp() returned error %d.",
+			xfs_warn(mp, "%s: xfs_imap_to_bp returned error %d.",
 				__func__, error);
 			return error;
 		}
@@ -1472,34 +1391,45 @@ xfs_iunlink_remove(
 		next_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]);
 		last_ibp = NULL;
 		while (next_agino != agino) {
-			/*
-			 * If the last inode wasn't the one pointing to
-			 * us, then release its buffer since we're not
-			 * going to do anything with it.
-			 */
-			if (last_ibp != NULL) {
+			struct xfs_imap	imap;
+
+			if (last_ibp)
 				xfs_trans_brelse(tp, last_ibp);
-			}
+
+			imap.im_blkno = 0;
 			next_ino = XFS_AGINO_TO_INO(mp, agno, next_agino);
-			error = xfs_inotobp(mp, tp, next_ino, &last_dip,
-					    &last_ibp, &last_offset, 0);
+
+			error = xfs_imap(mp, tp, next_ino, &imap, 0);
+			if (error) {
+				xfs_warn(mp,
+	"%s: xfs_imap returned error %d.",
+					 __func__, error);
+				return error;
+			}
+
+			error = xfs_imap_to_bp(mp, tp, &imap, &last_dip,
+					       &last_ibp, 0, 0);
 			if (error) {
 				xfs_warn(mp,
-					"%s: xfs_inotobp() returned error %d.",
+	"%s: xfs_imap_to_bp returned error %d.",
 					__func__, error);
 				return error;
 			}
+
+			last_offset = imap.im_boffset;
 			next_agino = be32_to_cpu(last_dip->di_next_unlinked);
 			ASSERT(next_agino != NULLAGINO);
 			ASSERT(next_agino != 0);
 		}
+
 		/*
-		 * Now last_ibp points to the buffer previous to us on
-		 * the unlinked list.  Pull us from the list.
+		 * Now last_ibp points to the buffer previous to us on the
+		 * unlinked list.  Pull us from the list.
 		 */
-		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0);
+		error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &ibp,
+				       0, 0);
 		if (error) {
-			xfs_warn(mp, "%s: xfs_itobp(2) returned error %d.",
+			xfs_warn(mp, "%s: xfs_imap_to_bp(2) returned error %d.",
 				__func__, error);
 			return error;
 		}
@@ -1749,7 +1679,8 @@ xfs_ifree(
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
-	error = xfs_itobp(ip->i_mount, tp, ip, &dip, &ibp, 0);
+	error = xfs_imap_to_bp(ip->i_mount, tp, &ip->i_imap, &dip, &ibp,
+			       0, 0);
 	if (error)
 		return error;
 
@@ -2428,7 +2359,7 @@ xfs_iflush(
 	/*
 	 * For stale inodes we cannot rely on the backing buffer remaining
 	 * stale in cache for the remaining life of the stale inode and so
-	 * xfs_itobp() below may give us a buffer that no longer contains
+	 * xfs_imap_to_bp() below may give us a buffer that no longer contains
 	 * inodes below. We have to check this after ensuring the inode is
 	 * unpinned so that it is safe to reclaim the stale inode after the
 	 * flush call.
@@ -2454,7 +2385,8 @@ xfs_iflush(
 	/*
 	 * Get the buffer containing the on-disk inode.
 	 */
-	error = xfs_itobp(mp, NULL, ip, &dip, &bp, XBF_TRYLOCK);
+	error = xfs_imap_to_bp(mp, NULL, &ip->i_imap, &dip, &bp, XBF_TRYLOCK,
+			       0);
 	if (error || !bp) {
 		xfs_ifunlock(ip);
 		return error;
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 1efff36a75b6..94b32f906e79 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -487,8 +487,6 @@ static inline int xfs_isiflocked(struct xfs_inode *ip)
 #define XFS_IOLOCK_DEP(flags)	(((flags) & XFS_IOLOCK_DEP_MASK) >> XFS_IOLOCK_SHIFT)
 #define XFS_ILOCK_DEP(flags)	(((flags) & XFS_ILOCK_DEP_MASK) >> XFS_ILOCK_SHIFT)
 
-extern struct lock_class_key xfs_iolock_reclaimable;
-
 /*
  * For multiple groups support: if S_ISGID bit is set in the parent
  * directory, group of new file is set to that of the parent, and
@@ -517,7 +515,7 @@ void		xfs_inode_free(struct xfs_inode *ip);
  */
 int		xfs_ialloc(struct xfs_trans *, xfs_inode_t *, umode_t,
 			   xfs_nlink_t, xfs_dev_t, prid_t, int,
-			   struct xfs_buf **, boolean_t *, xfs_inode_t **);
+			   struct xfs_buf **, xfs_inode_t **);
 
 uint		xfs_ip2xflags(struct xfs_inode *);
 uint		xfs_dic2xflags(struct xfs_dinode *);
@@ -557,12 +555,9 @@ do { \
 #define XFS_IGET_UNTRUSTED	0x2
 #define XFS_IGET_DONTCACHE	0x4
 
-int		xfs_inotobp(struct xfs_mount *, struct xfs_trans *,
-			    xfs_ino_t, struct xfs_dinode **,
-			    struct xfs_buf **, int *, uint);
-int		xfs_itobp(struct xfs_mount *, struct xfs_trans *,
-			  struct xfs_inode *, struct xfs_dinode **,
-			  struct xfs_buf **, uint);
+int		xfs_imap_to_bp(struct xfs_mount *, struct xfs_trans *,
+			       struct xfs_imap *, struct xfs_dinode **,
+			       struct xfs_buf **, uint, uint);
 int		xfs_iread(struct xfs_mount *, struct xfs_trans *,
 			  struct xfs_inode *, uint);
 void		xfs_dinode_to_disk(struct xfs_dinode *,
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 1f1535d25a9b..0e0232c3b6d9 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -364,9 +364,15 @@ xfs_fssetdm_by_handle(
 	if (copy_from_user(&dmhreq, arg, sizeof(xfs_fsop_setdm_handlereq_t)))
 		return -XFS_ERROR(EFAULT);
 
+	error = mnt_want_write_file(parfilp);
+	if (error)
+		return error;
+
 	dentry = xfs_handlereq_to_dentry(parfilp, &dmhreq.hreq);
-	if (IS_ERR(dentry))
+	if (IS_ERR(dentry)) {
+		mnt_drop_write_file(parfilp);
 		return PTR_ERR(dentry);
+	}
 
 	if (IS_IMMUTABLE(dentry->d_inode) || IS_APPEND(dentry->d_inode)) {
 		error = -XFS_ERROR(EPERM);
@@ -382,6 +388,7 @@ xfs_fssetdm_by_handle(
 				 fsd.fsd_dmstate);
 
  out:
+	mnt_drop_write_file(parfilp);
 	dput(dentry);
 	return error;
 }
@@ -634,7 +641,11 @@ xfs_ioc_space(
 	if (ioflags & IO_INVIS)
 		attr_flags |= XFS_ATTR_DMI;
 
+	error = mnt_want_write_file(filp);
+	if (error)
+		return error;
 	error = xfs_change_file_space(ip, cmd, bf, filp->f_pos, attr_flags);
+	mnt_drop_write_file(filp);
 	return -error;
 }
 
@@ -1163,6 +1174,7 @@ xfs_ioc_fssetxattr(
 {
 	struct fsxattr		fa;
 	unsigned int		mask;
+	int error;
 
 	if (copy_from_user(&fa, arg, sizeof(fa)))
 		return -EFAULT;
@@ -1171,7 +1183,12 @@ xfs_ioc_fssetxattr(
 	if (filp->f_flags & (O_NDELAY|O_NONBLOCK))
 		mask |= FSX_NONBLOCK;
 
-	return -xfs_ioctl_setattr(ip, &fa, mask);
+	error = mnt_want_write_file(filp);
+	if (error)
+		return error;
+	error = xfs_ioctl_setattr(ip, &fa, mask);
+	mnt_drop_write_file(filp);
+	return -error;
 }
 
 STATIC int
@@ -1196,6 +1213,7 @@ xfs_ioc_setxflags(
 	struct fsxattr		fa;
 	unsigned int		flags;
 	unsigned int		mask;
+	int error;
 
 	if (copy_from_user(&flags, arg, sizeof(flags)))
 		return -EFAULT;
@@ -1210,7 +1228,12 @@ xfs_ioc_setxflags(
 		mask |= FSX_NONBLOCK;
 	fa.fsx_xflags = xfs_merge_ioc_xflags(flags, xfs_ip2xflags(ip));
 
-	return -xfs_ioctl_setattr(ip, &fa, mask);
+	error = mnt_want_write_file(filp);
+	if (error)
+		return error;
+	error = xfs_ioctl_setattr(ip, &fa, mask);
+	mnt_drop_write_file(filp);
+	return -error;
 }
 
 STATIC int
@@ -1385,8 +1408,13 @@ xfs_file_ioctl(
 		if (copy_from_user(&dmi, arg, sizeof(dmi)))
 			return -XFS_ERROR(EFAULT);
 
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
+
 		error = xfs_set_dmattrs(ip, dmi.fsd_dmevmask,
 				dmi.fsd_dmstate);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 
@@ -1434,7 +1462,11 @@ xfs_file_ioctl(
 
 		if (copy_from_user(&sxp, arg, sizeof(xfs_swapext_t)))
 			return -XFS_ERROR(EFAULT);
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_swapext(&sxp);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 
@@ -1463,9 +1495,14 @@ xfs_file_ioctl(
 		if (copy_from_user(&inout, arg, sizeof(inout)))
 			return -XFS_ERROR(EFAULT);
 
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
+
 		/* input parameter is passed in resblks field of structure */
 		in = inout.resblks;
 		error = xfs_reserve_blocks(mp, &in, &inout);
+		mnt_drop_write_file(filp);
 		if (error)
 			return -error;
 
@@ -1496,7 +1533,11 @@ xfs_file_ioctl(
 		if (copy_from_user(&in, arg, sizeof(in)))
 			return -XFS_ERROR(EFAULT);
 
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_growfs_data(mp, &in);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 
@@ -1506,7 +1547,11 @@ xfs_file_ioctl(
 		if (copy_from_user(&in, arg, sizeof(in)))
 			return -XFS_ERROR(EFAULT);
 
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_growfs_log(mp, &in);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 
@@ -1516,7 +1561,11 @@ xfs_file_ioctl(
 		if (copy_from_user(&in, arg, sizeof(in)))
 			return -XFS_ERROR(EFAULT);
 
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_growfs_rt(mp, &in);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index c4f2da0d2bf5..1244274a5674 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -600,7 +600,11 @@ xfs_file_compat_ioctl(
 
 		if (xfs_compat_growfs_data_copyin(&in, arg))
 			return -XFS_ERROR(EFAULT);
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_growfs_data(mp, &in);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 	case XFS_IOC_FSGROWFSRT_32: {
@@ -608,7 +612,11 @@ xfs_file_compat_ioctl(
 
 		if (xfs_compat_growfs_rt_copyin(&in, arg))
 			return -XFS_ERROR(EFAULT);
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_growfs_rt(mp, &in);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 #endif
@@ -627,7 +635,11 @@ xfs_file_compat_ioctl(
 				   offsetof(struct xfs_swapext, sx_stat)) ||
 		    xfs_ioctl32_bstat_copyin(&sxp.sx_stat, &sxu->sx_stat))
 			return -XFS_ERROR(EFAULT);
+		error = mnt_want_write_file(filp);
+		if (error)
+			return error;
 		error = xfs_swapext(&sxp);
+		mnt_drop_write_file(filp);
 		return -error;
 	}
 	case XFS_IOC_FSBULKSTAT_32:
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index aadfce6681ee..973dff6ad935 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -285,7 +285,7 @@ xfs_iomap_eof_want_preallocate(
 	 * do any speculative allocation.
 	 */
 	start_fsb = XFS_B_TO_FSBT(mp, ((xfs_ufsize_t)(offset + count - 1)));
-	count_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_MAXIOFFSET(mp));
+	count_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
 	while (count_fsb > 0) {
 		imaps = nimaps;
 		firstblock = NULLFSBLOCK;
@@ -416,8 +416,8 @@ retry:
 	 * Make sure preallocation does not create extents beyond the range we
 	 * actually support in this filesystem.
 	 */
-	if (last_fsb > XFS_B_TO_FSB(mp, mp->m_maxioffset))
-		last_fsb = XFS_B_TO_FSB(mp, mp->m_maxioffset);
+	if (last_fsb > XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes))
+		last_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
 
 	ASSERT(last_fsb > offset_fsb);
 
@@ -680,9 +680,9 @@ xfs_iomap_write_unwritten(
 		 * the same inode that we complete here and might deadlock
 		 * on the iolock.
 		 */
-		xfs_wait_for_freeze(mp, SB_FREEZE_TRANS);
+		sb_start_intwrite(mp->m_super);
 		tp = _xfs_trans_alloc(mp, XFS_TRANS_STRAT_WRITE, KM_NOFS);
-		tp->t_flags |= XFS_TRANS_RESERVE;
+		tp->t_flags |= XFS_TRANS_RESERVE | XFS_TRANS_FREEZE_PROT;
 		error = xfs_trans_reserve(tp, resblks,
 				XFS_WRITE_LOG_RES(mp), 0,
 				XFS_TRANS_PERM_LOG_RES,
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 9c4340f5c3e0..4e00cf091d2c 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -897,6 +897,47 @@ xfs_vn_setattr(
 	return -xfs_setattr_nonsize(XFS_I(dentry->d_inode), iattr, 0);
 }
 
+STATIC int
+xfs_vn_update_time(
+	struct inode		*inode,
+	struct timespec		*now,
+	int			flags)
+{
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_trans	*tp;
+	int			error;
+
+	trace_xfs_update_time(ip);
+
+	tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
+	error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0);
+	if (error) {
+		xfs_trans_cancel(tp, 0);
+		return -error;
+	}
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	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) {
+		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) {
+		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, 0);
+}
+
 #define XFS_FIEMAP_FLAGS	(FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR)
 
 /*
@@ -991,6 +1032,7 @@ static const struct inode_operations xfs_inode_operations = {
 	.removexattr		= generic_removexattr,
 	.listxattr		= xfs_vn_listxattr,
 	.fiemap			= xfs_vn_fiemap,
+	.update_time		= xfs_vn_update_time,
 };
 
 static const struct inode_operations xfs_dir_inode_operations = {
@@ -1016,6 +1058,7 @@ static const struct inode_operations xfs_dir_inode_operations = {
 	.getxattr		= generic_getxattr,
 	.removexattr		= generic_removexattr,
 	.listxattr		= xfs_vn_listxattr,
+	.update_time		= xfs_vn_update_time,
 };
 
 static const struct inode_operations xfs_dir_ci_inode_operations = {
@@ -1041,6 +1084,7 @@ static const struct inode_operations xfs_dir_ci_inode_operations = {
 	.getxattr		= generic_getxattr,
 	.removexattr		= generic_removexattr,
 	.listxattr		= xfs_vn_listxattr,
+	.update_time		= xfs_vn_update_time,
 };
 
 static const struct inode_operations xfs_symlink_inode_operations = {
@@ -1054,6 +1098,7 @@ static const struct inode_operations xfs_symlink_inode_operations = {
 	.getxattr		= generic_getxattr,
 	.removexattr		= generic_removexattr,
 	.listxattr		= xfs_vn_listxattr,
+	.update_time		= xfs_vn_update_time,
 };
 
 STATIC void
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index eff577a9b67f..01d10a66e302 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -555,7 +555,7 @@ xfs_bulkstat_single(
 
 	/*
 	 * note that requesting valid inode numbers which are not allocated
-	 * to inodes will most likely cause xfs_itobp to generate warning
+	 * to inodes will most likely cause xfs_imap_to_bp to generate warning
 	 * messages about bad magic numbers. This is ok. The fact that
 	 * the inode isn't actually an inode is handled by the
 	 * error check below. Done this way to make the usual case faster
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index d90d4a388609..7f4f9370d0e7 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -45,51 +45,85 @@ xlog_commit_record(
 	struct xlog_in_core	**iclog,
 	xfs_lsn_t		*commitlsnp);
 
-STATIC xlog_t *  xlog_alloc_log(xfs_mount_t	*mp,
-				xfs_buftarg_t	*log_target,
-				xfs_daddr_t	blk_offset,
-				int		num_bblks);
+STATIC struct xlog *
+xlog_alloc_log(
+	struct xfs_mount	*mp,
+	struct xfs_buftarg	*log_target,
+	xfs_daddr_t		blk_offset,
+	int			num_bblks);
 STATIC int
 xlog_space_left(
 	struct xlog		*log,
 	atomic64_t		*head);
-STATIC int	 xlog_sync(xlog_t *log, xlog_in_core_t *iclog);
-STATIC void	 xlog_dealloc_log(xlog_t *log);
+STATIC int
+xlog_sync(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog);
+STATIC void
+xlog_dealloc_log(
+	struct xlog		*log);
 
 /* local state machine functions */
 STATIC void xlog_state_done_syncing(xlog_in_core_t *iclog, int);
-STATIC void xlog_state_do_callback(xlog_t *log,int aborted, xlog_in_core_t *iclog);
-STATIC int  xlog_state_get_iclog_space(xlog_t		*log,
-				       int		len,
-				       xlog_in_core_t	**iclog,
-				       xlog_ticket_t	*ticket,
-				       int		*continued_write,
-				       int		*logoffsetp);
-STATIC int  xlog_state_release_iclog(xlog_t		*log,
-				     xlog_in_core_t	*iclog);
-STATIC void xlog_state_switch_iclogs(xlog_t		*log,
-				     xlog_in_core_t *iclog,
-				     int		eventual_size);
-STATIC void xlog_state_want_sync(xlog_t	*log, xlog_in_core_t *iclog);
+STATIC void
+xlog_state_do_callback(
+	struct xlog		*log,
+	int			aborted,
+	struct xlog_in_core	*iclog);
+STATIC int
+xlog_state_get_iclog_space(
+	struct xlog		*log,
+	int			len,
+	struct xlog_in_core	**iclog,
+	struct xlog_ticket	*ticket,
+	int			*continued_write,
+	int			*logoffsetp);
+STATIC int
+xlog_state_release_iclog(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog);
+STATIC void
+xlog_state_switch_iclogs(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog,
+	int			eventual_size);
+STATIC void
+xlog_state_want_sync(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog);
 
 STATIC void
 xlog_grant_push_ail(
-	struct xlog	*log,
-	int		need_bytes);
-STATIC void xlog_regrant_reserve_log_space(xlog_t	 *log,
-					   xlog_ticket_t *ticket);
-STATIC void xlog_ungrant_log_space(xlog_t	 *log,
-				   xlog_ticket_t *ticket);
+	struct xlog		*log,
+	int			need_bytes);
+STATIC void
+xlog_regrant_reserve_log_space(
+	struct xlog		*log,
+	struct xlog_ticket	*ticket);
+STATIC void
+xlog_ungrant_log_space(
+	struct xlog		*log,
+	struct xlog_ticket	*ticket);
 
 #if defined(DEBUG)
-STATIC void	xlog_verify_dest_ptr(xlog_t *log, char *ptr);
+STATIC void
+xlog_verify_dest_ptr(
+	struct xlog		*log,
+	char			*ptr);
 STATIC void
 xlog_verify_grant_tail(
-	struct xlog	*log);
-STATIC void	xlog_verify_iclog(xlog_t *log, xlog_in_core_t *iclog,
-				  int count, boolean_t syncing);
-STATIC void	xlog_verify_tail_lsn(xlog_t *log, xlog_in_core_t *iclog,
-				     xfs_lsn_t tail_lsn);
+	struct xlog *log);
+STATIC void
+xlog_verify_iclog(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog,
+	int			count,
+	boolean_t		syncing);
+STATIC void
+xlog_verify_tail_lsn(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog,
+	xfs_lsn_t		tail_lsn);
 #else
 #define xlog_verify_dest_ptr(a,b)
 #define xlog_verify_grant_tail(a)
@@ -97,7 +131,9 @@ STATIC void	xlog_verify_tail_lsn(xlog_t *log, xlog_in_core_t *iclog,
 #define xlog_verify_tail_lsn(a,b,c)
 #endif
 
-STATIC int	xlog_iclogs_empty(xlog_t *log);
+STATIC int
+xlog_iclogs_empty(
+	struct xlog		*log);
 
 static void
 xlog_grant_sub_space(
@@ -684,7 +720,7 @@ xfs_log_mount_finish(xfs_mount_t *mp)
 int
 xfs_log_unmount_write(xfs_mount_t *mp)
 {
-	xlog_t		 *log = mp->m_log;
+	struct xlog	 *log = mp->m_log;
 	xlog_in_core_t	 *iclog;
 #ifdef DEBUG
 	xlog_in_core_t	 *first_iclog;
@@ -893,7 +929,7 @@ int
 xfs_log_need_covered(xfs_mount_t *mp)
 {
 	int		needed = 0;
-	xlog_t		*log = mp->m_log;
+	struct xlog	*log = mp->m_log;
 
 	if (!xfs_fs_writable(mp))
 		return 0;
@@ -1024,9 +1060,9 @@ xlog_space_left(
 void
 xlog_iodone(xfs_buf_t *bp)
 {
-	xlog_in_core_t	*iclog = bp->b_fspriv;
-	xlog_t		*l = iclog->ic_log;
-	int		aborted = 0;
+	struct xlog_in_core	*iclog = bp->b_fspriv;
+	struct xlog		*l = iclog->ic_log;
+	int			aborted = 0;
 
 	/*
 	 * Race to shutdown the filesystem if we see an error.
@@ -1067,8 +1103,9 @@ xlog_iodone(xfs_buf_t *bp)
  */
 
 STATIC void
-xlog_get_iclog_buffer_size(xfs_mount_t	*mp,
-			   xlog_t	*log)
+xlog_get_iclog_buffer_size(
+	struct xfs_mount	*mp,
+	struct xlog		*log)
 {
 	int size;
 	int xhdrs;
@@ -1129,13 +1166,14 @@ done:
  * Its primary purpose is to fill in enough, so recovery can occur.  However,
  * some other stuff may be filled in too.
  */
-STATIC xlog_t *
-xlog_alloc_log(xfs_mount_t	*mp,
-	       xfs_buftarg_t	*log_target,
-	       xfs_daddr_t	blk_offset,
-	       int		num_bblks)
+STATIC struct xlog *
+xlog_alloc_log(
+	struct xfs_mount	*mp,
+	struct xfs_buftarg	*log_target,
+	xfs_daddr_t		blk_offset,
+	int			num_bblks)
 {
-	xlog_t			*log;
+	struct xlog		*log;
 	xlog_rec_header_t	*head;
 	xlog_in_core_t		**iclogp;
 	xlog_in_core_t		*iclog, *prev_iclog=NULL;
@@ -1144,7 +1182,7 @@ xlog_alloc_log(xfs_mount_t	*mp,
 	int			error = ENOMEM;
 	uint			log2_size = 0;
 
-	log = kmem_zalloc(sizeof(xlog_t), KM_MAYFAIL);
+	log = kmem_zalloc(sizeof(struct xlog), KM_MAYFAIL);
 	if (!log) {
 		xfs_warn(mp, "Log allocation failed: No memory!");
 		goto out;
@@ -1434,8 +1472,9 @@ xlog_bdstrat(
  */
 
 STATIC int
-xlog_sync(xlog_t		*log,
-	  xlog_in_core_t	*iclog)
+xlog_sync(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog)
 {
 	xfs_caddr_t	dptr;		/* pointer to byte sized element */
 	xfs_buf_t	*bp;
@@ -1584,7 +1623,8 @@ xlog_sync(xlog_t		*log,
  * Deallocate a log structure
  */
 STATIC void
-xlog_dealloc_log(xlog_t *log)
+xlog_dealloc_log(
+	struct xlog	*log)
 {
 	xlog_in_core_t	*iclog, *next_iclog;
 	int		i;
@@ -1616,10 +1656,11 @@ xlog_dealloc_log(xlog_t *log)
  */
 /* ARGSUSED */
 static inline void
-xlog_state_finish_copy(xlog_t		*log,
-		       xlog_in_core_t	*iclog,
-		       int		record_cnt,
-		       int		copy_bytes)
+xlog_state_finish_copy(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog,
+	int			record_cnt,
+	int			copy_bytes)
 {
 	spin_lock(&log->l_icloglock);
 
@@ -2142,7 +2183,8 @@ xlog_write(
  * State Change: DIRTY -> ACTIVE
  */
 STATIC void
-xlog_state_clean_log(xlog_t *log)
+xlog_state_clean_log(
+	struct xlog *log)
 {
 	xlog_in_core_t	*iclog;
 	int changed = 0;
@@ -2222,7 +2264,7 @@ xlog_state_clean_log(xlog_t *log)
 
 STATIC xfs_lsn_t
 xlog_get_lowest_lsn(
-	xlog_t		*log)
+	struct xlog	*log)
 {
 	xlog_in_core_t  *lsn_log;
 	xfs_lsn_t	lowest_lsn, lsn;
@@ -2245,9 +2287,9 @@ xlog_get_lowest_lsn(
 
 STATIC void
 xlog_state_do_callback(
-	xlog_t		*log,
-	int		aborted,
-	xlog_in_core_t	*ciclog)
+	struct xlog		*log,
+	int			aborted,
+	struct xlog_in_core	*ciclog)
 {
 	xlog_in_core_t	   *iclog;
 	xlog_in_core_t	   *first_iclog;	/* used to know when we've
@@ -2467,7 +2509,7 @@ xlog_state_done_syncing(
 	xlog_in_core_t	*iclog,
 	int		aborted)
 {
-	xlog_t		   *log = iclog->ic_log;
+	struct xlog	   *log = iclog->ic_log;
 
 	spin_lock(&log->l_icloglock);
 
@@ -2521,12 +2563,13 @@ xlog_state_done_syncing(
  *		is copied.
  */
 STATIC int
-xlog_state_get_iclog_space(xlog_t	  *log,
-			   int		  len,
-			   xlog_in_core_t **iclogp,
-			   xlog_ticket_t  *ticket,
-			   int		  *continued_write,
-			   int		  *logoffsetp)
+xlog_state_get_iclog_space(
+	struct xlog		*log,
+	int			len,
+	struct xlog_in_core	**iclogp,
+	struct xlog_ticket	*ticket,
+	int			*continued_write,
+	int			*logoffsetp)
 {
 	int		  log_offset;
 	xlog_rec_header_t *head;
@@ -2631,8 +2674,9 @@ restart:
  * move grant reservation head forward.
  */
 STATIC void
-xlog_regrant_reserve_log_space(xlog_t	     *log,
-			       xlog_ticket_t *ticket)
+xlog_regrant_reserve_log_space(
+	struct xlog		*log,
+	struct xlog_ticket	*ticket)
 {
 	trace_xfs_log_regrant_reserve_enter(log, ticket);
 
@@ -2677,8 +2721,9 @@ xlog_regrant_reserve_log_space(xlog_t	     *log,
  * in the current reservation field.
  */
 STATIC void
-xlog_ungrant_log_space(xlog_t	     *log,
-		       xlog_ticket_t *ticket)
+xlog_ungrant_log_space(
+	struct xlog		*log,
+	struct xlog_ticket	*ticket)
 {
 	int	bytes;
 
@@ -2717,8 +2762,8 @@ xlog_ungrant_log_space(xlog_t	     *log,
  */
 STATIC int
 xlog_state_release_iclog(
-	xlog_t		*log,
-	xlog_in_core_t	*iclog)
+	struct xlog		*log,
+	struct xlog_in_core	*iclog)
 {
 	int		sync = 0;	/* do we sync? */
 
@@ -2768,9 +2813,10 @@ xlog_state_release_iclog(
  * that every data block.  We have run out of space in this log record.
  */
 STATIC void
-xlog_state_switch_iclogs(xlog_t		*log,
-			 xlog_in_core_t *iclog,
-			 int		eventual_size)
+xlog_state_switch_iclogs(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog,
+	int			eventual_size)
 {
 	ASSERT(iclog->ic_state == XLOG_STATE_ACTIVE);
 	if (!eventual_size)
@@ -3114,7 +3160,9 @@ xfs_log_force_lsn(
  * disk.
  */
 STATIC void
-xlog_state_want_sync(xlog_t *log, xlog_in_core_t *iclog)
+xlog_state_want_sync(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog)
 {
 	assert_spin_locked(&log->l_icloglock);
 
@@ -3158,7 +3206,7 @@ xfs_log_ticket_get(
 /*
  * Allocate and initialise a new log ticket.
  */
-xlog_ticket_t *
+struct xlog_ticket *
 xlog_ticket_alloc(
 	struct xlog	*log,
 	int		unit_bytes,
@@ -3346,9 +3394,10 @@ xlog_verify_grant_tail(
 
 /* check if it will fit */
 STATIC void
-xlog_verify_tail_lsn(xlog_t	    *log,
-		     xlog_in_core_t *iclog,
-		     xfs_lsn_t	    tail_lsn)
+xlog_verify_tail_lsn(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog,
+	xfs_lsn_t		tail_lsn)
 {
     int blocks;
 
@@ -3385,10 +3434,11 @@ xlog_verify_tail_lsn(xlog_t	    *log,
  *	the cycle numbers agree with the current cycle number.
  */
 STATIC void
-xlog_verify_iclog(xlog_t	 *log,
-		  xlog_in_core_t *iclog,
-		  int		 count,
-		  boolean_t	 syncing)
+xlog_verify_iclog(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog,
+	int			count,
+	boolean_t		syncing)
 {
 	xlog_op_header_t	*ophead;
 	xlog_in_core_t		*icptr;
@@ -3482,7 +3532,7 @@ xlog_verify_iclog(xlog_t	 *log,
  */
 STATIC int
 xlog_state_ioerror(
-	xlog_t	*log)
+	struct xlog	*log)
 {
 	xlog_in_core_t	*iclog, *ic;
 
@@ -3527,7 +3577,7 @@ xfs_log_force_umount(
 	struct xfs_mount	*mp,
 	int			logerror)
 {
-	xlog_t		*log;
+	struct xlog	*log;
 	int		retval;
 
 	log = mp->m_log;
@@ -3634,7 +3684,8 @@ xfs_log_force_umount(
 }
 
 STATIC int
-xlog_iclogs_empty(xlog_t *log)
+xlog_iclogs_empty(
+	struct xlog	*log)
 {
 	xlog_in_core_t	*iclog;
 
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index 72eba2201b14..18a801d76a42 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -487,7 +487,7 @@ struct xlog_grant_head {
  * overflow 31 bits worth of byte offset, so using a byte number will mean
  * that round off problems won't occur when releasing partial reservations.
  */
-typedef struct xlog {
+struct xlog {
 	/* The following fields don't need locking */
 	struct xfs_mount	*l_mp;	        /* mount point */
 	struct xfs_ail		*l_ailp;	/* AIL log is working with */
@@ -540,7 +540,7 @@ typedef struct xlog {
 	char			*l_iclog_bak[XLOG_MAX_ICLOGS];
 #endif
 
-} xlog_t;
+};
 
 #define XLOG_BUF_CANCEL_BUCKET(log, blkno) \
 	((log)->l_buf_cancel_table + ((__uint64_t)blkno % XLOG_BC_TABLE_SIZE))
@@ -548,9 +548,17 @@ typedef struct xlog {
 #define XLOG_FORCED_SHUTDOWN(log)	((log)->l_flags & XLOG_IO_ERROR)
 
 /* common routines */
-extern int	 xlog_recover(xlog_t *log);
-extern int	 xlog_recover_finish(xlog_t *log);
-extern void	 xlog_pack_data(xlog_t *log, xlog_in_core_t *iclog, int);
+extern int
+xlog_recover(
+	struct xlog		*log);
+extern int
+xlog_recover_finish(
+	struct xlog		*log);
+extern void
+xlog_pack_data(
+	struct xlog		*log,
+	struct xlog_in_core	*iclog,
+	int);
 
 extern kmem_zone_t *xfs_log_ticket_zone;
 struct xlog_ticket *
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index a7be98abd6a9..5da3ace352bf 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -43,10 +43,18 @@
 #include "xfs_utils.h"
 #include "xfs_trace.h"
 
-STATIC int	xlog_find_zeroed(xlog_t *, xfs_daddr_t *);
-STATIC int	xlog_clear_stale_blocks(xlog_t *, xfs_lsn_t);
+STATIC int
+xlog_find_zeroed(
+	struct xlog	*,
+	xfs_daddr_t	*);
+STATIC int
+xlog_clear_stale_blocks(
+	struct xlog	*,
+	xfs_lsn_t);
 #if defined(DEBUG)
-STATIC void	xlog_recover_check_summary(xlog_t *);
+STATIC void
+xlog_recover_check_summary(
+	struct xlog *);
 #else
 #define	xlog_recover_check_summary(log)
 #endif
@@ -74,7 +82,7 @@ struct xfs_buf_cancel {
 
 static inline int
 xlog_buf_bbcount_valid(
-	xlog_t		*log,
+	struct xlog	*log,
 	int		bbcount)
 {
 	return bbcount > 0 && bbcount <= log->l_logBBsize;
@@ -87,7 +95,7 @@ xlog_buf_bbcount_valid(
  */
 STATIC xfs_buf_t *
 xlog_get_bp(
-	xlog_t		*log,
+	struct xlog	*log,
 	int		nbblks)
 {
 	struct xfs_buf	*bp;
@@ -138,10 +146,10 @@ xlog_put_bp(
  */
 STATIC xfs_caddr_t
 xlog_align(
-	xlog_t		*log,
+	struct xlog	*log,
 	xfs_daddr_t	blk_no,
 	int		nbblks,
-	xfs_buf_t	*bp)
+	struct xfs_buf	*bp)
 {
 	xfs_daddr_t	offset = blk_no & ((xfs_daddr_t)log->l_sectBBsize - 1);
 
@@ -155,10 +163,10 @@ xlog_align(
  */
 STATIC int
 xlog_bread_noalign(
-	xlog_t		*log,
+	struct xlog	*log,
 	xfs_daddr_t	blk_no,
 	int		nbblks,
-	xfs_buf_t	*bp)
+	struct xfs_buf	*bp)
 {
 	int		error;
 
@@ -189,10 +197,10 @@ xlog_bread_noalign(
 
 STATIC int
 xlog_bread(
-	xlog_t		*log,
+	struct xlog	*log,
 	xfs_daddr_t	blk_no,
 	int		nbblks,
-	xfs_buf_t	*bp,
+	struct xfs_buf	*bp,
 	xfs_caddr_t	*offset)
 {
 	int		error;
@@ -211,10 +219,10 @@ xlog_bread(
  */
 STATIC int
 xlog_bread_offset(
-	xlog_t		*log,
+	struct xlog	*log,
 	xfs_daddr_t	blk_no,		/* block to read from */
 	int		nbblks,		/* blocks to read */
-	xfs_buf_t	*bp,
+	struct xfs_buf	*bp,
 	xfs_caddr_t	offset)
 {
 	xfs_caddr_t	orig_offset = bp->b_addr;
@@ -241,10 +249,10 @@ xlog_bread_offset(
  */
 STATIC int
 xlog_bwrite(
-	xlog_t		*log,
+	struct xlog	*log,
 	xfs_daddr_t	blk_no,
 	int		nbblks,
-	xfs_buf_t	*bp)
+	struct xfs_buf	*bp)
 {
 	int		error;
 
@@ -378,8 +386,8 @@ xlog_recover_iodone(
  */
 STATIC int
 xlog_find_cycle_start(
-	xlog_t		*log,
-	xfs_buf_t	*bp,
+	struct xlog	*log,
+	struct xfs_buf	*bp,
 	xfs_daddr_t	first_blk,
 	xfs_daddr_t	*last_blk,
 	uint		cycle)
@@ -421,7 +429,7 @@ xlog_find_cycle_start(
  */
 STATIC int
 xlog_find_verify_cycle(
-	xlog_t		*log,
+	struct xlog	*log,
 	xfs_daddr_t	start_blk,
 	int		nbblks,
 	uint		stop_on_cycle_no,
@@ -490,7 +498,7 @@ out:
  */
 STATIC int
 xlog_find_verify_log_record(
-	xlog_t			*log,
+	struct xlog		*log,
 	xfs_daddr_t		start_blk,
 	xfs_daddr_t		*last_blk,
 	int			extra_bblks)
@@ -600,7 +608,7 @@ out:
  */
 STATIC int
 xlog_find_head(
-	xlog_t 		*log,
+	struct xlog	*log,
 	xfs_daddr_t	*return_head_blk)
 {
 	xfs_buf_t	*bp;
@@ -871,7 +879,7 @@ validate_head:
  */
 STATIC int
 xlog_find_tail(
-	xlog_t			*log,
+	struct xlog		*log,
 	xfs_daddr_t		*head_blk,
 	xfs_daddr_t		*tail_blk)
 {
@@ -1080,7 +1088,7 @@ done:
  */
 STATIC int
 xlog_find_zeroed(
-	xlog_t		*log,
+	struct xlog	*log,
 	xfs_daddr_t	*blk_no)
 {
 	xfs_buf_t	*bp;
@@ -1183,7 +1191,7 @@ bp_err:
  */
 STATIC void
 xlog_add_record(
-	xlog_t			*log,
+	struct xlog		*log,
 	xfs_caddr_t		buf,
 	int			cycle,
 	int			block,
@@ -1205,7 +1213,7 @@ xlog_add_record(
 
 STATIC int
 xlog_write_log_records(
-	xlog_t		*log,
+	struct xlog	*log,
 	int		cycle,
 	int		start_block,
 	int		blocks,
@@ -1305,7 +1313,7 @@ xlog_write_log_records(
  */
 STATIC int
 xlog_clear_stale_blocks(
-	xlog_t		*log,
+	struct xlog	*log,
 	xfs_lsn_t	tail_lsn)
 {
 	int		tail_cycle, head_cycle;
@@ -2050,11 +2058,11 @@ xfs_qm_dqcheck(
  */
 STATIC void
 xlog_recover_do_dquot_buffer(
-	xfs_mount_t		*mp,
-	xlog_t			*log,
-	xlog_recover_item_t	*item,
-	xfs_buf_t		*bp,
-	xfs_buf_log_format_t	*buf_f)
+	struct xfs_mount		*mp,
+	struct xlog			*log,
+	struct xlog_recover_item	*item,
+	struct xfs_buf			*bp,
+	struct xfs_buf_log_format	*buf_f)
 {
 	uint			type;
 
@@ -2108,9 +2116,9 @@ xlog_recover_do_dquot_buffer(
  */
 STATIC int
 xlog_recover_buffer_pass2(
-	xlog_t			*log,
-	struct list_head	*buffer_list,
-	xlog_recover_item_t	*item)
+	struct xlog			*log,
+	struct list_head		*buffer_list,
+	struct xlog_recover_item	*item)
 {
 	xfs_buf_log_format_t	*buf_f = item->ri_buf[0].i_addr;
 	xfs_mount_t		*mp = log->l_mp;
@@ -2189,9 +2197,9 @@ xlog_recover_buffer_pass2(
 
 STATIC int
 xlog_recover_inode_pass2(
-	xlog_t			*log,
-	struct list_head	*buffer_list,
-	xlog_recover_item_t	*item)
+	struct xlog			*log,
+	struct list_head		*buffer_list,
+	struct xlog_recover_item	*item)
 {
 	xfs_inode_log_format_t	*in_f;
 	xfs_mount_t		*mp = log->l_mp;
@@ -2452,14 +2460,14 @@ error:
 }
 
 /*
- * Recover QUOTAOFF records. We simply make a note of it in the xlog_t
+ * Recover QUOTAOFF records. We simply make a note of it in the xlog
  * structure, so that we know not to do any dquot item or dquot buffer recovery,
  * of that type.
  */
 STATIC int
 xlog_recover_quotaoff_pass1(
-	xlog_t			*log,
-	xlog_recover_item_t	*item)
+	struct xlog			*log,
+	struct xlog_recover_item	*item)
 {
 	xfs_qoff_logformat_t	*qoff_f = item->ri_buf[0].i_addr;
 	ASSERT(qoff_f);
@@ -2483,9 +2491,9 @@ xlog_recover_quotaoff_pass1(
  */
 STATIC int
 xlog_recover_dquot_pass2(
-	xlog_t			*log,
-	struct list_head	*buffer_list,
-	xlog_recover_item_t	*item)
+	struct xlog			*log,
+	struct list_head		*buffer_list,
+	struct xlog_recover_item	*item)
 {
 	xfs_mount_t		*mp = log->l_mp;
 	xfs_buf_t		*bp;
@@ -2578,9 +2586,9 @@ xlog_recover_dquot_pass2(
  */
 STATIC int
 xlog_recover_efi_pass2(
-	xlog_t			*log,
-	xlog_recover_item_t	*item,
-	xfs_lsn_t		lsn)
+	struct xlog			*log,
+	struct xlog_recover_item	*item,
+	xfs_lsn_t			lsn)
 {
 	int			error;
 	xfs_mount_t		*mp = log->l_mp;
@@ -2616,8 +2624,8 @@ xlog_recover_efi_pass2(
  */
 STATIC int
 xlog_recover_efd_pass2(
-	xlog_t			*log,
-	xlog_recover_item_t	*item)
+	struct xlog			*log,
+	struct xlog_recover_item	*item)
 {
 	xfs_efd_log_format_t	*efd_formatp;
 	xfs_efi_log_item_t	*efip = NULL;
@@ -2812,9 +2820,9 @@ xlog_recover_unmount_trans(
  */
 STATIC int
 xlog_recover_process_data(
-	xlog_t			*log,
+	struct xlog		*log,
 	struct hlist_head	rhash[],
-	xlog_rec_header_t	*rhead,
+	struct xlog_rec_header	*rhead,
 	xfs_caddr_t		dp,
 	int			pass)
 {
@@ -2986,7 +2994,7 @@ abort_error:
  */
 STATIC int
 xlog_recover_process_efis(
-	xlog_t			*log)
+	struct xlog	*log)
 {
 	xfs_log_item_t		*lip;
 	xfs_efi_log_item_t	*efip;
@@ -3098,7 +3106,7 @@ xlog_recover_process_one_iunlink(
 	/*
 	 * Get the on disk inode to find the next inode in the bucket.
 	 */
-	error = xfs_itobp(mp, NULL, ip, &dip, &ibp, 0);
+	error = xfs_imap_to_bp(mp, NULL, &ip->i_imap, &dip, &ibp, 0, 0);
 	if (error)
 		goto fail_iput;
 
@@ -3147,7 +3155,7 @@ xlog_recover_process_one_iunlink(
  */
 STATIC void
 xlog_recover_process_iunlinks(
-	xlog_t		*log)
+	struct xlog	*log)
 {
 	xfs_mount_t	*mp;
 	xfs_agnumber_t	agno;
@@ -3209,9 +3217,9 @@ xlog_recover_process_iunlinks(
 #ifdef DEBUG
 STATIC void
 xlog_pack_data_checksum(
-	xlog_t		*log,
-	xlog_in_core_t	*iclog,
-	int		size)
+	struct xlog		*log,
+	struct xlog_in_core	*iclog,
+	int			size)
 {
 	int		i;
 	__be32		*up;
@@ -3234,8 +3242,8 @@ xlog_pack_data_checksum(
  */
 void
 xlog_pack_data(
-	xlog_t			*log,
-	xlog_in_core_t		*iclog,
+	struct xlog		*log,
+	struct xlog_in_core	*iclog,
 	int			roundoff)
 {
 	int			i, j, k;
@@ -3274,9 +3282,9 @@ xlog_pack_data(
 
 STATIC void
 xlog_unpack_data(
-	xlog_rec_header_t	*rhead,
+	struct xlog_rec_header	*rhead,
 	xfs_caddr_t		dp,
-	xlog_t			*log)
+	struct xlog		*log)
 {
 	int			i, j, k;
 
@@ -3299,8 +3307,8 @@ xlog_unpack_data(
 
 STATIC int
 xlog_valid_rec_header(
-	xlog_t			*log,
-	xlog_rec_header_t	*rhead,
+	struct xlog		*log,
+	struct xlog_rec_header	*rhead,
 	xfs_daddr_t		blkno)
 {
 	int			hlen;
@@ -3343,7 +3351,7 @@ xlog_valid_rec_header(
  */
 STATIC int
 xlog_do_recovery_pass(
-	xlog_t			*log,
+	struct xlog		*log,
 	xfs_daddr_t		head_blk,
 	xfs_daddr_t		tail_blk,
 	int			pass)
@@ -3595,7 +3603,7 @@ xlog_do_recovery_pass(
  */
 STATIC int
 xlog_do_log_recovery(
-	xlog_t		*log,
+	struct xlog	*log,
 	xfs_daddr_t	head_blk,
 	xfs_daddr_t	tail_blk)
 {
@@ -3646,7 +3654,7 @@ xlog_do_log_recovery(
  */
 STATIC int
 xlog_do_recover(
-	xlog_t		*log,
+	struct xlog	*log,
 	xfs_daddr_t	head_blk,
 	xfs_daddr_t	tail_blk)
 {
@@ -3721,7 +3729,7 @@ xlog_do_recover(
  */
 int
 xlog_recover(
-	xlog_t		*log)
+	struct xlog	*log)
 {
 	xfs_daddr_t	head_blk, tail_blk;
 	int		error;
@@ -3767,7 +3775,7 @@ xlog_recover(
  */
 int
 xlog_recover_finish(
-	xlog_t		*log)
+	struct xlog	*log)
 {
 	/*
 	 * Now we're ready to do the transactions needed for the
@@ -3814,7 +3822,7 @@ xlog_recover_finish(
  */
 void
 xlog_recover_check_summary(
-	xlog_t		*log)
+	struct xlog	*log)
 {
 	xfs_mount_t	*mp;
 	xfs_agf_t	*agfp;
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 536021fb3d4e..29c2f83d4147 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1200,8 +1200,6 @@ xfs_mountfs(
 
 	xfs_set_maxicount(mp);
 
-	mp->m_maxioffset = xfs_max_file_offset(sbp->sb_blocklog);
-
 	error = xfs_uuid_mount(mp);
 	if (error)
 		goto out;
@@ -1531,6 +1529,15 @@ xfs_unmountfs(
 	xfs_ail_push_all_sync(mp->m_ail);
 	xfs_wait_buftarg(mp->m_ddev_targp);
 
+	/*
+	 * The superblock buffer is uncached and xfsaild_push() will lock and
+	 * set the XBF_ASYNC flag on the buffer. We cannot do xfs_buf_iowait()
+	 * here but a lock on the superblock buffer will block until iodone()
+	 * has completed.
+	 */
+	xfs_buf_lock(mp->m_sb_bp);
+	xfs_buf_unlock(mp->m_sb_bp);
+
 	xfs_log_unmount_write(mp);
 	xfs_log_unmount(mp);
 	xfs_uuid_unmount(mp);
@@ -1544,7 +1551,7 @@ xfs_unmountfs(
 int
 xfs_fs_writable(xfs_mount_t *mp)
 {
-	return !(xfs_test_for_freeze(mp) || XFS_FORCED_SHUTDOWN(mp) ||
+	return !(mp->m_super->s_writers.frozen || XFS_FORCED_SHUTDOWN(mp) ||
 		(mp->m_flags & XFS_MOUNT_RDONLY));
 }
 
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 90c1fc9eaea4..05a05a7b6119 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -176,7 +176,6 @@ typedef struct xfs_mount {
 	uint			m_qflags;	/* quota status flags */
 	xfs_trans_reservations_t m_reservations;/* precomputed res values */
 	__uint64_t		m_maxicount;	/* maximum inode count */
-	__uint64_t		m_maxioffset;	/* maximum inode offset */
 	__uint64_t		m_resblks;	/* total reserved blocks */
 	__uint64_t		m_resblks_avail;/* available reserved blocks */
 	__uint64_t		m_resblks_save;	/* reserved blks @ remount,ro */
@@ -297,8 +296,6 @@ xfs_preferred_iosize(xfs_mount_t *mp)
 			PAGE_CACHE_SIZE));
 }
 
-#define XFS_MAXIOFFSET(mp)	((mp)->m_maxioffset)
-
 #define XFS_LAST_UNMOUNT_WAS_CLEAN(mp)	\
 				((mp)->m_flags & XFS_MOUNT_WAS_CLEAN)
 #define XFS_FORCED_SHUTDOWN(mp)	((mp)->m_flags & XFS_MOUNT_FS_SHUTDOWN)
@@ -314,9 +311,6 @@ void xfs_do_force_shutdown(struct xfs_mount *mp, int flags, char *fname,
 #define SHUTDOWN_REMOTE_REQ	0x0010	/* shutdown came from remote cell */
 #define SHUTDOWN_DEVICE_REQ	0x0020	/* failed all paths to the device */
 
-#define xfs_test_for_freeze(mp)		((mp)->m_super->s_frozen)
-#define xfs_wait_for_freeze(mp,l)	vfs_check_frozen((mp)->m_super, (l))
-
 /*
  * Flags for xfs_mountfs
  */
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 249db1987764..2e86fa0cfc0d 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -940,7 +940,7 @@ xfs_qm_dqiterate(
 	map = kmem_alloc(XFS_DQITER_MAP_SIZE * sizeof(*map), KM_SLEEP);
 
 	lblkno = 0;
-	maxlblkcnt = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_MAXIOFFSET(mp));
+	maxlblkcnt = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
 	do {
 		nmaps = XFS_DQITER_MAP_SIZE;
 		/*
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 0d9de41a7151..bdaf4cb9f4a2 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -868,67 +868,14 @@ xfs_fs_inode_init_once(
 		     "xfsino", ip->i_ino);
 }
 
-/*
- * This is called by the VFS when dirtying inode metadata.  This can happen
- * for a few reasons, but we only care about timestamp updates, given that
- * we handled the rest ourselves.  In theory no other calls should happen,
- * but for example generic_write_end() keeps dirtying the inode after
- * updating i_size.  Thus we check that the flags are exactly I_DIRTY_SYNC,
- * and skip this call otherwise.
- *
- * We'll hopefull get a different method just for updating timestamps soon,
- * at which point this hack can go away, and maybe we'll also get real
- * error handling here.
- */
-STATIC void
-xfs_fs_dirty_inode(
-	struct inode		*inode,
-	int			flags)
-{
-	struct xfs_inode	*ip = XFS_I(inode);
-	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_trans	*tp;
-	int			error;
-
-	if (flags != I_DIRTY_SYNC)
-		return;
-
-	trace_xfs_dirty_inode(ip);
-
-	tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
-	error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0);
-	if (error) {
-		xfs_trans_cancel(tp, 0);
-		goto trouble;
-	}
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	/*
-	 * Grab all the latest timestamps from the Linux inode.
-	 */
-	ip->i_d.di_atime.t_sec = (__int32_t)inode->i_atime.tv_sec;
-	ip->i_d.di_atime.t_nsec = (__int32_t)inode->i_atime.tv_nsec;
-	ip->i_d.di_ctime.t_sec = (__int32_t)inode->i_ctime.tv_sec;
-	ip->i_d.di_ctime.t_nsec = (__int32_t)inode->i_ctime.tv_nsec;
-	ip->i_d.di_mtime.t_sec = (__int32_t)inode->i_mtime.tv_sec;
-	ip->i_d.di_mtime.t_nsec = (__int32_t)inode->i_mtime.tv_nsec;
-
-	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-	xfs_trans_log_inode(tp, ip, XFS_ILOG_TIMESTAMP);
-	error = xfs_trans_commit(tp, 0);
-	if (error)
-		goto trouble;
-	return;
-
-trouble:
-	xfs_warn(mp, "failed to update timestamps for inode 0x%llx", ip->i_ino);
-}
-
 STATIC void
 xfs_fs_evict_inode(
 	struct inode		*inode)
 {
 	xfs_inode_t		*ip = XFS_I(inode);
 
+	ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock));
+
 	trace_xfs_evict_inode(ip);
 
 	truncate_inode_pages(&inode->i_data, 0);
@@ -937,22 +884,6 @@ xfs_fs_evict_inode(
 	XFS_STATS_INC(vn_remove);
 	XFS_STATS_DEC(vn_active);
 
-	/*
-	 * The iolock is used by the file system to coordinate reads,
-	 * writes, and block truncates.  Up to this point the lock
-	 * protected concurrent accesses by users of the inode.  But
-	 * from here forward we're doing some final processing of the
-	 * inode because we're done with it, and although we reuse the
-	 * iolock for protection it is really a distinct lock class
-	 * (in the lockdep sense) from before.  To keep lockdep happy
-	 * (and basically indicate what we are doing), we explicitly
-	 * re-init the iolock here.
-	 */
-	ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock));
-	mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino);
-	lockdep_set_class_and_name(&ip->i_iolock.mr_lock,
-			&xfs_iolock_reclaimable, "xfs_iolock_reclaimable");
-
 	xfs_inactive(ip);
 }
 
@@ -1436,7 +1367,6 @@ xfs_fs_free_cached_objects(
 static const struct super_operations xfs_super_operations = {
 	.alloc_inode		= xfs_fs_alloc_inode,
 	.destroy_inode		= xfs_fs_destroy_inode,
-	.dirty_inode		= xfs_fs_dirty_inode,
 	.evict_inode		= xfs_fs_evict_inode,
 	.drop_inode		= xfs_fs_drop_inode,
 	.put_super		= xfs_fs_put_super,
@@ -1491,13 +1421,9 @@ xfs_init_zones(void)
 	if (!xfs_da_state_zone)
 		goto out_destroy_btree_cur_zone;
 
-	xfs_dabuf_zone = kmem_zone_init(sizeof(xfs_dabuf_t), "xfs_dabuf");
-	if (!xfs_dabuf_zone)
-		goto out_destroy_da_state_zone;
-
 	xfs_ifork_zone = kmem_zone_init(sizeof(xfs_ifork_t), "xfs_ifork");
 	if (!xfs_ifork_zone)
-		goto out_destroy_dabuf_zone;
+		goto out_destroy_da_state_zone;
 
 	xfs_trans_zone = kmem_zone_init(sizeof(xfs_trans_t), "xfs_trans");
 	if (!xfs_trans_zone)
@@ -1514,9 +1440,8 @@ xfs_init_zones(void)
 	 * size possible under XFS.  This wastes a little bit of memory,
 	 * but it is much faster.
 	 */
-	xfs_buf_item_zone = kmem_zone_init((sizeof(xfs_buf_log_item_t) +
-				(((XFS_MAX_BLOCKSIZE / XFS_BLF_CHUNK) /
-				  NBWORD) * sizeof(int))), "xfs_buf_item");
+	xfs_buf_item_zone = kmem_zone_init(sizeof(struct xfs_buf_log_item),
+					   "xfs_buf_item");
 	if (!xfs_buf_item_zone)
 		goto out_destroy_log_item_desc_zone;
 
@@ -1561,8 +1486,6 @@ xfs_init_zones(void)
 	kmem_zone_destroy(xfs_trans_zone);
  out_destroy_ifork_zone:
 	kmem_zone_destroy(xfs_ifork_zone);
- out_destroy_dabuf_zone:
-	kmem_zone_destroy(xfs_dabuf_zone);
  out_destroy_da_state_zone:
 	kmem_zone_destroy(xfs_da_state_zone);
  out_destroy_btree_cur_zone:
@@ -1590,7 +1513,6 @@ xfs_destroy_zones(void)
 	kmem_zone_destroy(xfs_log_item_desc_zone);
 	kmem_zone_destroy(xfs_trans_zone);
 	kmem_zone_destroy(xfs_ifork_zone);
-	kmem_zone_destroy(xfs_dabuf_zone);
 	kmem_zone_destroy(xfs_da_state_zone);
 	kmem_zone_destroy(xfs_btree_cur_zone);
 	kmem_zone_destroy(xfs_bmap_free_item_zone);
diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c
index 1e9ee064dbb2..96548176db80 100644
--- a/fs/xfs/xfs_sync.c
+++ b/fs/xfs/xfs_sync.c
@@ -359,6 +359,15 @@ xfs_quiesce_attr(
 	 * added an item to the AIL, thus flush it again.
 	 */
 	xfs_ail_push_all_sync(mp->m_ail);
+
+	/*
+	 * The superblock buffer is uncached and xfsaild_push() will lock and
+	 * set the XBF_ASYNC flag on the buffer. We cannot do xfs_buf_iowait()
+	 * here but a lock on the superblock buffer will block until iodone()
+	 * has completed.
+	 */
+	xfs_buf_lock(mp->m_sb_bp);
+	xfs_buf_unlock(mp->m_sb_bp);
 }
 
 static void
@@ -394,7 +403,7 @@ xfs_sync_worker(
 	if (!(mp->m_super->s_flags & MS_ACTIVE) &&
 	    !(mp->m_flags & XFS_MOUNT_RDONLY)) {
 		/* dgc: errors ignored here */
-		if (mp->m_super->s_frozen == SB_UNFROZEN &&
+		if (mp->m_super->s_writers.frozen == SB_UNFROZEN &&
 		    xfs_log_need_covered(mp))
 			error = xfs_fs_log_dummy(mp);
 		else
@@ -712,8 +721,8 @@ restart:
 	 * Note that xfs_iflush will never block on the inode buffer lock, as
 	 * xfs_ifree_cluster() can lock the inode buffer before it locks the
 	 * ip->i_lock, and we are doing the exact opposite here.  As a result,
-	 * doing a blocking xfs_itobp() to get the cluster buffer would result
-	 * in an ABBA deadlock with xfs_ifree_cluster().
+	 * doing a blocking xfs_imap_to_bp() to get the cluster buffer would
+	 * result in an ABBA deadlock with xfs_ifree_cluster().
 	 *
 	 * As xfs_ifree_cluser() must gather all inodes that are active in the
 	 * cache to mark them stale, if we hit this case we don't actually want
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index caf5dabfd553..e5795dd6013a 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -578,8 +578,8 @@ DEFINE_INODE_EVENT(xfs_ioctl_setattr);
 DEFINE_INODE_EVENT(xfs_dir_fsync);
 DEFINE_INODE_EVENT(xfs_file_fsync);
 DEFINE_INODE_EVENT(xfs_destroy_inode);
-DEFINE_INODE_EVENT(xfs_dirty_inode);
 DEFINE_INODE_EVENT(xfs_evict_inode);
+DEFINE_INODE_EVENT(xfs_update_time);
 
 DEFINE_INODE_EVENT(xfs_dquot_dqalloc);
 DEFINE_INODE_EVENT(xfs_dquot_dqdetach);
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index fdf324508c5e..06ed520a767f 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -576,8 +576,12 @@ xfs_trans_alloc(
 	xfs_mount_t	*mp,
 	uint		type)
 {
-	xfs_wait_for_freeze(mp, SB_FREEZE_TRANS);
-	return _xfs_trans_alloc(mp, type, KM_SLEEP);
+	xfs_trans_t     *tp;
+
+	sb_start_intwrite(mp->m_super);
+	tp = _xfs_trans_alloc(mp, type, KM_SLEEP);
+	tp->t_flags |= XFS_TRANS_FREEZE_PROT;
+	return tp;
 }
 
 xfs_trans_t *
@@ -588,6 +592,7 @@ _xfs_trans_alloc(
 {
 	xfs_trans_t	*tp;
 
+	WARN_ON(mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE);
 	atomic_inc(&mp->m_active_trans);
 
 	tp = kmem_zone_zalloc(xfs_trans_zone, memflags);
@@ -611,6 +616,8 @@ xfs_trans_free(
 	xfs_extent_busy_clear(tp->t_mountp, &tp->t_busy, false);
 
 	atomic_dec(&tp->t_mountp->m_active_trans);
+	if (tp->t_flags & XFS_TRANS_FREEZE_PROT)
+		sb_end_intwrite(tp->t_mountp->m_super);
 	xfs_trans_free_dqinfo(tp);
 	kmem_zone_free(xfs_trans_zone, tp);
 }
@@ -643,7 +650,11 @@ xfs_trans_dup(
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
 	ASSERT(tp->t_ticket != NULL);
 
-	ntp->t_flags = XFS_TRANS_PERM_LOG_RES | (tp->t_flags & XFS_TRANS_RESERVE);
+	ntp->t_flags = XFS_TRANS_PERM_LOG_RES |
+		       (tp->t_flags & XFS_TRANS_RESERVE) |
+		       (tp->t_flags & XFS_TRANS_FREEZE_PROT);
+	/* We gave our writer reference to the new transaction */
+	tp->t_flags &= ~XFS_TRANS_FREEZE_PROT;
 	ntp->t_ticket = xfs_log_ticket_get(tp->t_ticket);
 	ntp->t_blk_res = tp->t_blk_res - tp->t_blk_res_used;
 	tp->t_blk_res = tp->t_blk_res_used;
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 7c37b533aa8e..db056544cbb5 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -179,6 +179,8 @@ struct xfs_log_item_desc {
 #define	XFS_TRANS_SYNC		0x08	/* make commit synchronous */
 #define XFS_TRANS_DQ_DIRTY	0x10	/* at least one dquot in trx dirty */
 #define XFS_TRANS_RESERVE	0x20    /* OK to use reserved data blocks */
+#define XFS_TRANS_FREEZE_PROT	0x40	/* Transaction has elevated writer
+					   count in superblock */
 
 /*
  * Values for call flags parameter.
@@ -448,11 +450,51 @@ xfs_trans_t	*xfs_trans_dup(xfs_trans_t *);
 int		xfs_trans_reserve(xfs_trans_t *, uint, uint, uint,
 				  uint, uint);
 void		xfs_trans_mod_sb(xfs_trans_t *, uint, int64_t);
-struct xfs_buf	*xfs_trans_get_buf(xfs_trans_t *, struct xfs_buftarg *, xfs_daddr_t,
-				   int, uint);
-int		xfs_trans_read_buf(struct xfs_mount *, xfs_trans_t *,
-				   struct xfs_buftarg *, xfs_daddr_t, int, uint,
-				   struct xfs_buf **);
+
+struct xfs_buf	*xfs_trans_get_buf_map(struct xfs_trans *tp,
+				       struct xfs_buftarg *target,
+				       struct xfs_buf_map *map, int nmaps,
+				       uint flags);
+
+static inline struct xfs_buf *
+xfs_trans_get_buf(
+	struct xfs_trans	*tp,
+	struct xfs_buftarg	*target,
+	xfs_daddr_t		blkno,
+	int			numblks,
+	uint			flags)
+{
+	struct xfs_buf_map	map = {
+		.bm_bn = blkno,
+		.bm_len = numblks,
+	};
+	return xfs_trans_get_buf_map(tp, target, &map, 1, flags);
+}
+
+int		xfs_trans_read_buf_map(struct xfs_mount *mp,
+				       struct xfs_trans *tp,
+				       struct xfs_buftarg *target,
+				       struct xfs_buf_map *map, int nmaps,
+				       xfs_buf_flags_t flags,
+				       struct xfs_buf **bpp);
+
+static inline int
+xfs_trans_read_buf(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	struct xfs_buftarg	*target,
+	xfs_daddr_t		blkno,
+	int			numblks,
+	xfs_buf_flags_t		flags,
+	struct xfs_buf		**bpp)
+{
+	struct xfs_buf_map	map = {
+		.bm_bn = blkno,
+		.bm_len = numblks,
+	};
+	return xfs_trans_read_buf_map(mp, tp, target, &map, 1, flags, bpp);
+}
+
 struct xfs_buf	*xfs_trans_getsb(xfs_trans_t *, struct xfs_mount *, int);
 
 void		xfs_trans_brelse(xfs_trans_t *, struct xfs_buf *);
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 9c514483e599..6011ee661339 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -383,6 +383,12 @@ xfsaild_push(
 	}
 
 	spin_lock(&ailp->xa_lock);
+
+	/* barrier matches the xa_target update in xfs_ail_push() */
+	smp_rmb();
+	target = ailp->xa_target;
+	ailp->xa_target_prev = target;
+
 	lip = xfs_trans_ail_cursor_first(ailp, &cur, ailp->xa_last_pushed_lsn);
 	if (!lip) {
 		/*
@@ -397,7 +403,6 @@ xfsaild_push(
 	XFS_STATS_INC(xs_push_ail);
 
 	lsn = lip->li_lsn;
-	target = ailp->xa_target;
 	while ((XFS_LSN_CMP(lip->li_lsn, target) <= 0)) {
 		int	lock_result;
 
@@ -527,8 +532,32 @@ xfsaild(
 			__set_current_state(TASK_KILLABLE);
 		else
 			__set_current_state(TASK_INTERRUPTIBLE);
-		schedule_timeout(tout ?
-				 msecs_to_jiffies(tout) : MAX_SCHEDULE_TIMEOUT);
+
+		spin_lock(&ailp->xa_lock);
+
+		/*
+		 * Idle if the AIL is empty and we are not racing with a target
+		 * update. We check the AIL after we set the task to a sleep
+		 * state to guarantee that we either catch an xa_target update
+		 * or that a wake_up resets the state to TASK_RUNNING.
+		 * Otherwise, we run the risk of sleeping indefinitely.
+		 *
+		 * The barrier matches the xa_target update in xfs_ail_push().
+		 */
+		smp_rmb();
+		if (!xfs_ail_min(ailp) &&
+		    ailp->xa_target == ailp->xa_target_prev) {
+			spin_unlock(&ailp->xa_lock);
+			schedule();
+			tout = 0;
+			continue;
+		}
+		spin_unlock(&ailp->xa_lock);
+
+		if (tout)
+			schedule_timeout(msecs_to_jiffies(tout));
+
+		__set_current_state(TASK_RUNNING);
 
 		try_to_freeze();
 
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index 21c5a5e3700d..6311b99c267f 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -41,20 +41,26 @@ STATIC struct xfs_buf *
 xfs_trans_buf_item_match(
 	struct xfs_trans	*tp,
 	struct xfs_buftarg	*target,
-	xfs_daddr_t		blkno,
-	int			len)
+	struct xfs_buf_map	*map,
+	int			nmaps)
 {
 	struct xfs_log_item_desc *lidp;
 	struct xfs_buf_log_item	*blip;
+	int			len = 0;
+	int			i;
+
+	for (i = 0; i < nmaps; i++)
+		len += map[i].bm_len;
 
-	len = BBTOB(len);
 	list_for_each_entry(lidp, &tp->t_items, lid_trans) {
 		blip = (struct xfs_buf_log_item *)lidp->lid_item;
 		if (blip->bli_item.li_type == XFS_LI_BUF &&
 		    blip->bli_buf->b_target == target &&
-		    XFS_BUF_ADDR(blip->bli_buf) == blkno &&
-		    BBTOB(blip->bli_buf->b_length) == len)
+		    XFS_BUF_ADDR(blip->bli_buf) == map[0].bm_bn &&
+		    blip->bli_buf->b_length == len) {
+			ASSERT(blip->bli_buf->b_map_count == nmaps);
 			return blip->bli_buf;
+		}
 	}
 
 	return NULL;
@@ -128,21 +134,19 @@ xfs_trans_bjoin(
  * If the transaction pointer is NULL, make this just a normal
  * get_buf() call.
  */
-xfs_buf_t *
-xfs_trans_get_buf(xfs_trans_t	*tp,
-		  xfs_buftarg_t	*target_dev,
-		  xfs_daddr_t	blkno,
-		  int		len,
-		  uint		flags)
+struct xfs_buf *
+xfs_trans_get_buf_map(
+	struct xfs_trans	*tp,
+	struct xfs_buftarg	*target,
+	struct xfs_buf_map	*map,
+	int			nmaps,
+	xfs_buf_flags_t		flags)
 {
 	xfs_buf_t		*bp;
 	xfs_buf_log_item_t	*bip;
 
-	/*
-	 * Default to a normal get_buf() call if the tp is NULL.
-	 */
-	if (tp == NULL)
-		return xfs_buf_get(target_dev, blkno, len, flags);
+	if (!tp)
+		return xfs_buf_get_map(target, map, nmaps, flags);
 
 	/*
 	 * If we find the buffer in the cache with this transaction
@@ -150,7 +154,7 @@ xfs_trans_get_buf(xfs_trans_t	*tp,
 	 * have it locked.  In this case we just increment the lock
 	 * recursion count and return the buffer to the caller.
 	 */
-	bp = xfs_trans_buf_item_match(tp, target_dev, blkno, len);
+	bp = xfs_trans_buf_item_match(tp, target, map, nmaps);
 	if (bp != NULL) {
 		ASSERT(xfs_buf_islocked(bp));
 		if (XFS_FORCED_SHUTDOWN(tp->t_mountp)) {
@@ -167,7 +171,7 @@ xfs_trans_get_buf(xfs_trans_t	*tp,
 		return (bp);
 	}
 
-	bp = xfs_buf_get(target_dev, blkno, len, flags);
+	bp = xfs_buf_get_map(target, map, nmaps, flags);
 	if (bp == NULL) {
 		return NULL;
 	}
@@ -246,26 +250,22 @@ int	xfs_error_mod = 33;
  * read_buf() call.
  */
 int
-xfs_trans_read_buf(
-	xfs_mount_t	*mp,
-	xfs_trans_t	*tp,
-	xfs_buftarg_t	*target,
-	xfs_daddr_t	blkno,
-	int		len,
-	uint		flags,
-	xfs_buf_t	**bpp)
+xfs_trans_read_buf_map(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	struct xfs_buftarg	*target,
+	struct xfs_buf_map	*map,
+	int			nmaps,
+	xfs_buf_flags_t		flags,
+	struct xfs_buf		**bpp)
 {
 	xfs_buf_t		*bp;
 	xfs_buf_log_item_t	*bip;
 	int			error;
 
 	*bpp = NULL;
-
-	/*
-	 * Default to a normal get_buf() call if the tp is NULL.
-	 */
-	if (tp == NULL) {
-		bp = xfs_buf_read(target, blkno, len, flags);
+	if (!tp) {
+		bp = xfs_buf_read_map(target, map, nmaps, flags);
 		if (!bp)
 			return (flags & XBF_TRYLOCK) ?
 					EAGAIN : XFS_ERROR(ENOMEM);
@@ -303,7 +303,7 @@ xfs_trans_read_buf(
 	 * If the buffer is not yet read in, then we read it in, increment
 	 * the lock recursion count, and return it to the caller.
 	 */
-	bp = xfs_trans_buf_item_match(tp, target, blkno, len);
+	bp = xfs_trans_buf_item_match(tp, target, map, nmaps);
 	if (bp != NULL) {
 		ASSERT(xfs_buf_islocked(bp));
 		ASSERT(bp->b_transp == tp);
@@ -349,7 +349,7 @@ xfs_trans_read_buf(
 		return 0;
 	}
 
-	bp = xfs_buf_read(target, blkno, len, flags);
+	bp = xfs_buf_read_map(target, map, nmaps, flags);
 	if (bp == NULL) {
 		*bpp = NULL;
 		return (flags & XBF_TRYLOCK) ?
diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h
index fb62377d1cbc..53b7c9b0f8f7 100644
--- a/fs/xfs/xfs_trans_priv.h
+++ b/fs/xfs/xfs_trans_priv.h
@@ -67,6 +67,7 @@ struct xfs_ail {
 	struct task_struct	*xa_task;
 	struct list_head	xa_ail;
 	xfs_lsn_t		xa_target;
+	xfs_lsn_t		xa_target_prev;
 	struct list_head	xa_cursors;
 	spinlock_t		xa_lock;
 	xfs_lsn_t		xa_last_pushed_lsn;
diff --git a/fs/xfs/xfs_types.h b/fs/xfs/xfs_types.h
index 398cf681d025..7a41874f4c20 100644
--- a/fs/xfs/xfs_types.h
+++ b/fs/xfs/xfs_types.h
@@ -133,6 +133,20 @@ typedef __uint64_t	xfs_filblks_t;	/* number of blocks in a file */
 #define	MAXAEXTNUM	((xfs_aextnum_t)0x7fff)		/* signed short */
 
 /*
+ * Minimum and maximum blocksize and sectorsize.
+ * The blocksize upper limit is pretty much arbitrary.
+ * The sectorsize upper limit is due to sizeof(sb_sectsize).
+ */
+#define XFS_MIN_BLOCKSIZE_LOG	9	/* i.e. 512 bytes */
+#define XFS_MAX_BLOCKSIZE_LOG	16	/* i.e. 65536 bytes */
+#define XFS_MIN_BLOCKSIZE	(1 << XFS_MIN_BLOCKSIZE_LOG)
+#define XFS_MAX_BLOCKSIZE	(1 << XFS_MAX_BLOCKSIZE_LOG)
+#define XFS_MIN_SECTORSIZE_LOG	9	/* i.e. 512 bytes */
+#define XFS_MAX_SECTORSIZE_LOG	15	/* i.e. 32768 bytes */
+#define XFS_MIN_SECTORSIZE	(1 << XFS_MIN_SECTORSIZE_LOG)
+#define XFS_MAX_SECTORSIZE	(1 << XFS_MAX_SECTORSIZE_LOG)
+
+/*
  * Min numbers of data/attr fork btree root pointers.
  */
 #define MINDBTPTRS	3
diff --git a/fs/xfs/xfs_utils.c b/fs/xfs/xfs_utils.c
index 4e5b9ad5cb97..0025c78ac03c 100644
--- a/fs/xfs/xfs_utils.c
+++ b/fs/xfs/xfs_utils.c
@@ -65,7 +65,6 @@ xfs_dir_ialloc(
 	xfs_trans_t	*ntp;
 	xfs_inode_t	*ip;
 	xfs_buf_t	*ialloc_context = NULL;
-	boolean_t	call_again = B_FALSE;
 	int		code;
 	uint		log_res;
 	uint		log_count;
@@ -91,7 +90,7 @@ xfs_dir_ialloc(
 	 * the inode(s) that we've just allocated.
 	 */
 	code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid, okalloc,
-			  &ialloc_context, &call_again, &ip);
+			  &ialloc_context, &ip);
 
 	/*
 	 * Return an error if we were unable to allocate a new inode.
@@ -102,19 +101,18 @@ xfs_dir_ialloc(
 		*ipp = NULL;
 		return code;
 	}
-	if (!call_again && (ip == NULL)) {
+	if (!ialloc_context && !ip) {
 		*ipp = NULL;
 		return XFS_ERROR(ENOSPC);
 	}
 
 	/*
-	 * If call_again is set, then we were unable to get an
+	 * If the AGI buffer is non-NULL, then we were unable to get an
 	 * inode in one operation.  We need to commit the current
 	 * transaction and call xfs_ialloc() again.  It is guaranteed
 	 * to succeed the second time.
 	 */
-	if (call_again) {
-
+	if (ialloc_context) {
 		/*
 		 * Normally, xfs_trans_commit releases all the locks.
 		 * We call bhold to hang on to the ialloc_context across
@@ -195,7 +193,7 @@ xfs_dir_ialloc(
 		 * this call should always succeed.
 		 */
 		code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid,
-				  okalloc, &ialloc_context, &call_again, &ip);
+				  okalloc, &ialloc_context, &ip);
 
 		/*
 		 * If we get an error at this point, return to the caller
@@ -206,12 +204,11 @@ xfs_dir_ialloc(
 			*ipp = NULL;
 			return code;
 		}
-		ASSERT ((!call_again) && (ip != NULL));
+		ASSERT(!ialloc_context && ip);
 
 	} else {
-		if (committed != NULL) {
+		if (committed != NULL)
 			*committed = 0;
-		}
 	}
 
 	*ipp = ip;
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index b6a82d817a82..2a5c637344b4 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -146,11 +146,6 @@ xfs_readlink(
 }
 
 /*
- * Flags for xfs_free_eofblocks
- */
-#define XFS_FREE_EOF_TRYLOCK	(1<<0)
-
-/*
  * This is called by xfs_inactive to free any blocks beyond eof
  * when the link count isn't zero and by xfs_dm_punch_hole() when
  * punching a hole to EOF.
@@ -159,7 +154,7 @@ STATIC int
 xfs_free_eofblocks(
 	xfs_mount_t	*mp,
 	xfs_inode_t	*ip,
-	int		flags)
+	bool		need_iolock)
 {
 	xfs_trans_t	*tp;
 	int		error;
@@ -174,7 +169,7 @@ xfs_free_eofblocks(
 	 * of the file.  If not, then there is nothing to do.
 	 */
 	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_ISIZE(ip));
-	last_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_MAXIOFFSET(mp));
+	last_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
 	if (last_fsb <= end_fsb)
 		return 0;
 	map_len = last_fsb - end_fsb;
@@ -201,13 +196,11 @@ xfs_free_eofblocks(
 		 */
 		tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
 
-		if (flags & XFS_FREE_EOF_TRYLOCK) {
+		if (need_iolock) {
 			if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
 				xfs_trans_cancel(tp, 0);
 				return 0;
 			}
-		} else {
-			xfs_ilock(ip, XFS_IOLOCK_EXCL);
 		}
 
 		error = xfs_trans_reserve(tp, 0,
@@ -217,7 +210,8 @@ xfs_free_eofblocks(
 		if (error) {
 			ASSERT(XFS_FORCED_SHUTDOWN(mp));
 			xfs_trans_cancel(tp, 0);
-			xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+			if (need_iolock)
+				xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 			return error;
 		}
 
@@ -244,7 +238,10 @@ xfs_free_eofblocks(
 			error = xfs_trans_commit(tp,
 						XFS_TRANS_RELEASE_LOG_RES);
 		}
-		xfs_iunlock(ip, XFS_IOLOCK_EXCL|XFS_ILOCK_EXCL);
+
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		if (need_iolock)
+			xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 	}
 	return error;
 }
@@ -282,23 +279,15 @@ xfs_inactive_symlink_rmt(
 	 * free them all in one bunmapi call.
 	 */
 	ASSERT(ip->i_d.di_nextents > 0 && ip->i_d.di_nextents <= 2);
-	if ((error = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0,
-			XFS_TRANS_PERM_LOG_RES, XFS_ITRUNCATE_LOG_COUNT))) {
-		ASSERT(XFS_FORCED_SHUTDOWN(mp));
-		xfs_trans_cancel(tp, 0);
-		*tpp = NULL;
-		return error;
-	}
+
 	/*
 	 * Lock the inode, fix the size, and join it to the transaction.
 	 * Hold it so in the normal path, we still have it locked for
 	 * the second transaction.  In the error paths we need it
 	 * held so the cancel won't rele it, see below.
 	 */
-	xfs_ilock(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL);
 	size = (int)ip->i_d.di_size;
 	ip->i_d.di_size = 0;
-	xfs_trans_ijoin(tp, ip, 0);
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 	/*
 	 * Find the block(s) so we can inval and unmap them.
@@ -385,114 +374,14 @@ xfs_inactive_symlink_rmt(
 		ASSERT(XFS_FORCED_SHUTDOWN(mp));
 		goto error0;
 	}
-	/*
-	 * Return with the inode locked but not joined to the transaction.
-	 */
+
+	xfs_trans_ijoin(tp, ip, 0);
 	*tpp = tp;
 	return 0;
 
  error1:
 	xfs_bmap_cancel(&free_list);
  error0:
-	/*
-	 * Have to come here with the inode locked and either
-	 * (held and in the transaction) or (not in the transaction).
-	 * If the inode isn't held then cancel would iput it, but
-	 * that's wrong since this is inactive and the vnode ref
-	 * count is 0 already.
-	 * Cancel won't do anything to the inode if held, but it still
-	 * needs to be locked until the cancel is done, if it was
-	 * joined to the transaction.
-	 */
-	xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
-	xfs_iunlock(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL);
-	*tpp = NULL;
-	return error;
-
-}
-
-STATIC int
-xfs_inactive_symlink_local(
-	xfs_inode_t	*ip,
-	xfs_trans_t	**tpp)
-{
-	int		error;
-
-	ASSERT(ip->i_d.di_size <= XFS_IFORK_DSIZE(ip));
-	/*
-	 * We're freeing a symlink which fit into
-	 * the inode.  Just free the memory used
-	 * to hold the old symlink.
-	 */
-	error = xfs_trans_reserve(*tpp, 0,
-				  XFS_ITRUNCATE_LOG_RES(ip->i_mount),
-				  0, XFS_TRANS_PERM_LOG_RES,
-				  XFS_ITRUNCATE_LOG_COUNT);
-
-	if (error) {
-		xfs_trans_cancel(*tpp, 0);
-		*tpp = NULL;
-		return error;
-	}
-	xfs_ilock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
-
-	/*
-	 * Zero length symlinks _can_ exist.
-	 */
-	if (ip->i_df.if_bytes > 0) {
-		xfs_idata_realloc(ip,
-				  -(ip->i_df.if_bytes),
-				  XFS_DATA_FORK);
-		ASSERT(ip->i_df.if_bytes == 0);
-	}
-	return 0;
-}
-
-STATIC int
-xfs_inactive_attrs(
-	xfs_inode_t	*ip,
-	xfs_trans_t	**tpp)
-{
-	xfs_trans_t	*tp;
-	int		error;
-	xfs_mount_t	*mp;
-
-	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
-	tp = *tpp;
-	mp = ip->i_mount;
-	ASSERT(ip->i_d.di_forkoff != 0);
-	error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	if (error)
-		goto error_unlock;
-
-	error = xfs_attr_inactive(ip);
-	if (error)
-		goto error_unlock;
-
-	tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
-	error = xfs_trans_reserve(tp, 0,
-				  XFS_IFREE_LOG_RES(mp),
-				  0, XFS_TRANS_PERM_LOG_RES,
-				  XFS_INACTIVE_LOG_COUNT);
-	if (error)
-		goto error_cancel;
-
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, ip, 0);
-	xfs_idestroy_fork(ip, XFS_ATTR_FORK);
-
-	ASSERT(ip->i_d.di_anextents == 0);
-
-	*tpp = tp;
-	return 0;
-
-error_cancel:
-	ASSERT(XFS_FORCED_SHUTDOWN(mp));
-	xfs_trans_cancel(tp, 0);
-error_unlock:
-	*tpp = NULL;
-	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 	return error;
 }
 
@@ -574,8 +463,7 @@ xfs_release(
 		if (xfs_iflags_test(ip, XFS_IDIRTY_RELEASE))
 			return 0;
 
-		error = xfs_free_eofblocks(mp, ip,
-					   XFS_FREE_EOF_TRYLOCK);
+		error = xfs_free_eofblocks(mp, ip, true);
 		if (error)
 			return error;
 
@@ -604,7 +492,7 @@ xfs_inactive(
 	xfs_trans_t	*tp;
 	xfs_mount_t	*mp;
 	int		error;
-	int		truncate;
+	int		truncate = 0;
 
 	/*
 	 * If the inode is already free, then there can be nothing
@@ -616,17 +504,6 @@ xfs_inactive(
 		return VN_INACTIVE_CACHE;
 	}
 
-	/*
-	 * Only do a truncate if it's a regular file with
-	 * some actual space in it.  It's OK to look at the
-	 * inode's fields without the lock because we're the
-	 * only one with a reference to the inode.
-	 */
-	truncate = ((ip->i_d.di_nlink == 0) &&
-	    ((ip->i_d.di_size != 0) || XFS_ISIZE(ip) != 0 ||
-	     (ip->i_d.di_nextents > 0) || (ip->i_delayed_blks > 0)) &&
-	    S_ISREG(ip->i_d.di_mode));
-
 	mp = ip->i_mount;
 
 	error = 0;
@@ -643,99 +520,100 @@ xfs_inactive(
 		    (!(ip->i_d.di_flags &
 				(XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)) ||
 		     ip->i_delayed_blks != 0))) {
-			error = xfs_free_eofblocks(mp, ip, 0);
+			error = xfs_free_eofblocks(mp, ip, false);
 			if (error)
 				return VN_INACTIVE_CACHE;
 		}
 		goto out;
 	}
 
-	ASSERT(ip->i_d.di_nlink == 0);
+	if (S_ISREG(ip->i_d.di_mode) &&
+	    (ip->i_d.di_size != 0 || XFS_ISIZE(ip) != 0 ||
+	     ip->i_d.di_nextents > 0 || ip->i_delayed_blks > 0))
+		truncate = 1;
 
 	error = xfs_qm_dqattach(ip, 0);
 	if (error)
 		return VN_INACTIVE_CACHE;
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
-	if (truncate) {
-		xfs_ilock(ip, XFS_IOLOCK_EXCL);
-
-		error = xfs_trans_reserve(tp, 0,
-					  XFS_ITRUNCATE_LOG_RES(mp),
-					  0, XFS_TRANS_PERM_LOG_RES,
-					  XFS_ITRUNCATE_LOG_COUNT);
-		if (error) {
-			/* Don't call itruncate_cleanup */
-			ASSERT(XFS_FORCED_SHUTDOWN(mp));
-			xfs_trans_cancel(tp, 0);
-			xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-			return VN_INACTIVE_CACHE;
-		}
+	error = xfs_trans_reserve(tp, 0,
+			(truncate || S_ISLNK(ip->i_d.di_mode)) ?
+				XFS_ITRUNCATE_LOG_RES(mp) :
+				XFS_IFREE_LOG_RES(mp),
+			0,
+			XFS_TRANS_PERM_LOG_RES,
+			XFS_ITRUNCATE_LOG_COUNT);
+	if (error) {
+		ASSERT(XFS_FORCED_SHUTDOWN(mp));
+		xfs_trans_cancel(tp, 0);
+		return VN_INACTIVE_CACHE;
+	}
 
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-		xfs_trans_ijoin(tp, ip, 0);
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, 0);
 
+	if (S_ISLNK(ip->i_d.di_mode)) {
+		/*
+		 * Zero length symlinks _can_ exist.
+		 */
+		if (ip->i_d.di_size > XFS_IFORK_DSIZE(ip)) {
+			error = xfs_inactive_symlink_rmt(ip, &tp);
+			if (error)
+				goto out_cancel;
+		} else if (ip->i_df.if_bytes > 0) {
+			xfs_idata_realloc(ip, -(ip->i_df.if_bytes),
+					  XFS_DATA_FORK);
+			ASSERT(ip->i_df.if_bytes == 0);
+		}
+	} else if (truncate) {
 		ip->i_d.di_size = 0;
 		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
 		error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, 0);
-		if (error) {
-			xfs_trans_cancel(tp,
-				XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
-			xfs_iunlock(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL);
-			return VN_INACTIVE_CACHE;
-		}
+		if (error)
+			goto out_cancel;
 
 		ASSERT(ip->i_d.di_nextents == 0);
-	} else if (S_ISLNK(ip->i_d.di_mode)) {
+	}
 
-		/*
-		 * If we get an error while cleaning up a
-		 * symlink we bail out.
-		 */
-		error = (ip->i_d.di_size > XFS_IFORK_DSIZE(ip)) ?
-			xfs_inactive_symlink_rmt(ip, &tp) :
-			xfs_inactive_symlink_local(ip, &tp);
+	/*
+	 * If there are attributes associated with the file then blow them away
+	 * now.  The code calls a routine that recursively deconstructs the
+	 * attribute fork.  We need to just commit the current transaction
+	 * because we can't use it for xfs_attr_inactive().
+	 */
+	if (ip->i_d.di_anextents > 0) {
+		ASSERT(ip->i_d.di_forkoff != 0);
 
-		if (error) {
-			ASSERT(tp == NULL);
-			return VN_INACTIVE_CACHE;
-		}
+		error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+		if (error)
+			goto out_unlock;
 
-		xfs_trans_ijoin(tp, ip, 0);
-	} else {
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+		error = xfs_attr_inactive(ip);
+		if (error)
+			goto out;
+
+		tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
 		error = xfs_trans_reserve(tp, 0,
 					  XFS_IFREE_LOG_RES(mp),
 					  0, XFS_TRANS_PERM_LOG_RES,
 					  XFS_INACTIVE_LOG_COUNT);
 		if (error) {
-			ASSERT(XFS_FORCED_SHUTDOWN(mp));
 			xfs_trans_cancel(tp, 0);
-			return VN_INACTIVE_CACHE;
+			goto out;
 		}
 
-		xfs_ilock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		xfs_trans_ijoin(tp, ip, 0);
 	}
 
-	/*
-	 * If there are attributes associated with the file
-	 * then blow them away now.  The code calls a routine
-	 * that recursively deconstructs the attribute fork.
-	 * We need to just commit the current transaction
-	 * because we can't use it for xfs_attr_inactive().
-	 */
-	if (ip->i_d.di_anextents > 0) {
-		error = xfs_inactive_attrs(ip, &tp);
-		/*
-		 * If we got an error, the transaction is already
-		 * cancelled, and the inode is unlocked. Just get out.
-		 */
-		 if (error)
-			 return VN_INACTIVE_CACHE;
-	} else if (ip->i_afp) {
+	if (ip->i_afp)
 		xfs_idestroy_fork(ip, XFS_ATTR_FORK);
-	}
+
+	ASSERT(ip->i_d.di_anextents == 0);
 
 	/*
 	 * Free the inode.
@@ -779,10 +657,13 @@ xfs_inactive(
 	 * Release the dquots held by inode, if any.
 	 */
 	xfs_qm_dqdetach(ip);
-	xfs_iunlock(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL);
-
- out:
+out_unlock:
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+out:
 	return VN_INACTIVE_CACHE;
+out_cancel:
+	xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
+	goto out_unlock;
 }
 
 /*
@@ -2262,10 +2143,10 @@ xfs_change_file_space(
 
 	llen = bf->l_len > 0 ? bf->l_len - 1 : bf->l_len;
 
-	if (   (bf->l_start < 0)
-	    || (bf->l_start > XFS_MAXIOFFSET(mp))
-	    || (bf->l_start + llen < 0)
-	    || (bf->l_start + llen > XFS_MAXIOFFSET(mp)))
+	if (bf->l_start < 0 ||
+	    bf->l_start > mp->m_super->s_maxbytes ||
+	    bf->l_start + llen < 0 ||
+	    bf->l_start + llen > mp->m_super->s_maxbytes)
 		return XFS_ERROR(EINVAL);
 
 	bf->l_whence = 0;