15 files changed, 162 insertions, 155 deletions

diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 9561c8fc8bd..281ae95932c 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -176,17 +176,6 @@ retry:
 	return bio;
 }
 
-static void bl_set_lo_fail(struct pnfs_layout_segment *lseg)
-{
-	if (lseg->pls_range.iomode == IOMODE_RW) {
-		dprintk("%s Setting layout IOMODE_RW fail bit\n", __func__);
-		set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
-	} else {
-		dprintk("%s Setting layout IOMODE_READ fail bit\n", __func__);
-		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
-	}
-}
-
 /* This is basically copied from mpage_end_io_read */
 static void bl_end_io_read(struct bio *bio, int err)
 {
@@ -206,7 +195,7 @@ static void bl_end_io_read(struct bio *bio, int err)
 	if (!uptodate) {
 		if (!rdata->pnfs_error)
 			rdata->pnfs_error = -EIO;
-		bl_set_lo_fail(rdata->lseg);
+		pnfs_set_lo_fail(rdata->lseg);
 	}
 	bio_put(bio);
 	put_parallel(par);
@@ -303,6 +292,7 @@ bl_read_pagelist(struct nfs_read_data *rdata)
 						 bl_end_io_read, par);
 			if (IS_ERR(bio)) {
 				rdata->pnfs_error = PTR_ERR(bio);
+				bio = NULL;
 				goto out;
 			}
 		}
@@ -370,7 +360,7 @@ static void bl_end_io_write_zero(struct bio *bio, int err)
 	if (!uptodate) {
 		if (!wdata->pnfs_error)
 			wdata->pnfs_error = -EIO;
-		bl_set_lo_fail(wdata->lseg);
+		pnfs_set_lo_fail(wdata->lseg);
 	}
 	bio_put(bio);
 	put_parallel(par);
@@ -386,7 +376,7 @@ static void bl_end_io_write(struct bio *bio, int err)
 	if (!uptodate) {
 		if (!wdata->pnfs_error)
 			wdata->pnfs_error = -EIO;
-		bl_set_lo_fail(wdata->lseg);
+		pnfs_set_lo_fail(wdata->lseg);
 	}
 	bio_put(bio);
 	put_parallel(par);
@@ -543,6 +533,11 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync)
 fill_invalid_ext:
 		dprintk("%s need to zero %d pages\n", __func__, npg_zero);
 		for (;npg_zero > 0; npg_zero--) {
+			if (bl_is_sector_init(be->be_inval, isect)) {
+				dprintk("isect %llu already init\n",
+					(unsigned long long)isect);
+				goto next_page;
+			}
 			/* page ref released in bl_end_io_write_zero */
 			index = isect >> PAGE_CACHE_SECTOR_SHIFT;
 			dprintk("%s zero %dth page: index %lu isect %llu\n",
@@ -562,8 +557,7 @@ fill_invalid_ext:
 			 * PageUptodate: It was read before
 			 * sector_initialized: already written out
 			 */
-			if (PageDirty(page) || PageWriteback(page) ||
-			    bl_is_sector_init(be->be_inval, isect)) {
+			if (PageDirty(page) || PageWriteback(page)) {
 				print_page(page);
 				unlock_page(page);
 				page_cache_release(page);
@@ -592,6 +586,7 @@ fill_invalid_ext:
 						 bl_end_io_write_zero, par);
 			if (IS_ERR(bio)) {
 				wdata->pnfs_error = PTR_ERR(bio);
+				bio = NULL;
 				goto out;
 			}
 			/* FIXME: This should be done in bi_end_io */
@@ -640,6 +635,7 @@ next_page:
 					 bl_end_io_write, par);
 		if (IS_ERR(bio)) {
 			wdata->pnfs_error = PTR_ERR(bio);
+			bio = NULL;
 			goto out;
 		}
 		isect += PAGE_CACHE_SECTORS;
@@ -805,7 +801,7 @@ nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh,
 			struct nfs4_deviceid *d_id)
 {
 	struct pnfs_device *dev;
-	struct pnfs_block_dev *rv = NULL;
+	struct pnfs_block_dev *rv;
 	u32 max_resp_sz;
 	int max_pages;
 	struct page **pages = NULL;
@@ -823,18 +819,20 @@ nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh,
 	dev = kmalloc(sizeof(*dev), GFP_NOFS);
 	if (!dev) {
 		dprintk("%s kmalloc failed\n", __func__);
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 
 	pages = kzalloc(max_pages * sizeof(struct page *), GFP_NOFS);
 	if (pages == NULL) {
 		kfree(dev);
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 	for (i = 0; i < max_pages; i++) {
 		pages[i] = alloc_page(GFP_NOFS);
-		if (!pages[i])
+		if (!pages[i]) {
+			rv = ERR_PTR(-ENOMEM);
 			goto out_free;
+		}
 	}
 
 	memcpy(&dev->dev_id, d_id, sizeof(*d_id));
@@ -847,8 +845,10 @@ nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh,
 	dprintk("%s: dev_id: %s\n", __func__, dev->dev_id.data);
 	rc = nfs4_proc_getdeviceinfo(server, dev);
 	dprintk("%s getdevice info returns %d\n", __func__, rc);
-	if (rc)
+	if (rc) {
+		rv = ERR_PTR(rc);
 		goto out_free;
+	}
 
 	rv = nfs4_blk_decode_device(server, dev);
  out_free:
@@ -866,7 +866,7 @@ bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh)
 	struct pnfs_devicelist *dlist = NULL;
 	struct pnfs_block_dev *bdev;
 	LIST_HEAD(block_disklist);
-	int status = 0, i;
+	int status, i;
 
 	dprintk("%s enter\n", __func__);
 
@@ -898,8 +898,8 @@ bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh)
 		for (i = 0; i < dlist->num_devs; i++) {
 			bdev = nfs4_blk_get_deviceinfo(server, fh,
 						       &dlist->dev_id[i]);
-			if (!bdev) {
-				status = -ENODEV;
+			if (IS_ERR(bdev)) {
+				status = PTR_ERR(bdev);
 				goto out_error;
 			}
 			spin_lock(&b_mt_id->bm_lock);
@@ -960,7 +960,7 @@ static struct pnfs_layoutdriver_type blocklayout_type = {
 };
 
 static const struct rpc_pipe_ops bl_upcall_ops = {
-	.upcall		= bl_pipe_upcall,
+	.upcall		= rpc_pipe_generic_upcall,
 	.downcall	= bl_pipe_downcall,
 	.destroy_msg	= bl_pipe_destroy_msg,
 };
@@ -989,17 +989,20 @@ static int __init nfs4blocklayout_init(void)
 			      mnt,
 			      NFS_PIPE_DIRNAME, 0, &path);
 	if (ret)
-		goto out_remove;
+		goto out_putrpc;
 
 	bl_device_pipe = rpc_mkpipe(path.dentry, "blocklayout", NULL,
 				    &bl_upcall_ops, 0);
+	path_put(&path);
 	if (IS_ERR(bl_device_pipe)) {
 		ret = PTR_ERR(bl_device_pipe);
-		goto out_remove;
+		goto out_putrpc;
 	}
 out:
 	return ret;
 
+out_putrpc:
+	rpc_put_mount();
 out_remove:
 	pnfs_unregister_layoutdriver(&blocklayout_type);
 	return ret;
@@ -1012,6 +1015,7 @@ static void __exit nfs4blocklayout_exit(void)
 
 	pnfs_unregister_layoutdriver(&blocklayout_type);
 	rpc_unlink(bl_device_pipe);
+	rpc_put_mount();
 }
 
 MODULE_ALIAS("nfs-layouttype4-3");
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index f27d827960a..42acf7ef599 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -150,7 +150,7 @@ BLK_LSEG2EXT(struct pnfs_layout_segment *lseg)
 }
 
 struct bl_dev_msg {
-	int status;
+	int32_t status;
 	uint32_t major, minor;
 };
 
@@ -169,8 +169,6 @@ extern wait_queue_head_t bl_wq;
 #define BL_DEVICE_REQUEST_ERR          0x2 /* User level process fails */
 
 /* blocklayoutdev.c */
-ssize_t bl_pipe_upcall(struct file *, struct rpc_pipe_msg *,
-		       char __user *, size_t);
 ssize_t bl_pipe_downcall(struct file *, const char __user *, size_t);
 void bl_pipe_destroy_msg(struct rpc_pipe_msg *);
 struct block_device *nfs4_blkdev_get(dev_t dev);
diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c
index a83b393fb01..d08ba9107fd 100644
--- a/fs/nfs/blocklayout/blocklayoutdev.c
+++ b/fs/nfs/blocklayout/blocklayoutdev.c
@@ -79,28 +79,6 @@ int nfs4_blkdev_put(struct block_device *bdev)
 	return blkdev_put(bdev, FMODE_READ);
 }
 
-/*
- * Shouldn't there be a rpc_generic_upcall() to do this for us?
- */
-ssize_t bl_pipe_upcall(struct file *filp, struct rpc_pipe_msg *msg,
-		       char __user *dst, size_t buflen)
-{
-	char *data = (char *)msg->data + msg->copied;
-	size_t mlen = min(msg->len - msg->copied, buflen);
-	unsigned long left;
-
-	left = copy_to_user(dst, data, mlen);
-	if (left == mlen) {
-		msg->errno = -EFAULT;
-		return -EFAULT;
-	}
-
-	mlen -= left;
-	msg->copied += mlen;
-	msg->errno = 0;
-	return mlen;
-}
-
 static struct bl_dev_msg bl_mount_reply;
 
 ssize_t bl_pipe_downcall(struct file *filp, const char __user *src,
@@ -131,7 +109,7 @@ struct pnfs_block_dev *
 nfs4_blk_decode_device(struct nfs_server *server,
 		       struct pnfs_device *dev)
 {
-	struct pnfs_block_dev *rv = NULL;
+	struct pnfs_block_dev *rv;
 	struct block_device *bd = NULL;
 	struct rpc_pipe_msg msg;
 	struct bl_msg_hdr bl_msg = {
@@ -141,7 +119,7 @@ nfs4_blk_decode_device(struct nfs_server *server,
 	uint8_t *dataptr;
 	DECLARE_WAITQUEUE(wq, current);
 	struct bl_dev_msg *reply = &bl_mount_reply;
-	int offset, len, i;
+	int offset, len, i, rc;
 
 	dprintk("%s CREATING PIPEFS MESSAGE\n", __func__);
 	dprintk("%s: deviceid: %s, mincount: %d\n", __func__, dev->dev_id.data,
@@ -168,8 +146,10 @@ nfs4_blk_decode_device(struct nfs_server *server,
 
 	dprintk("%s CALLING USERSPACE DAEMON\n", __func__);
 	add_wait_queue(&bl_wq, &wq);
-	if (rpc_queue_upcall(bl_device_pipe->d_inode, &msg) < 0) {
+	rc = rpc_queue_upcall(bl_device_pipe->d_inode, &msg);
+	if (rc < 0) {
 		remove_wait_queue(&bl_wq, &wq);
+		rv = ERR_PTR(rc);
 		goto out;
 	}
 
@@ -187,8 +167,9 @@ nfs4_blk_decode_device(struct nfs_server *server,
 
 	bd = nfs4_blkdev_get(MKDEV(reply->major, reply->minor));
 	if (IS_ERR(bd)) {
-		dprintk("%s failed to open device : %ld\n",
-			__func__, PTR_ERR(bd));
+		rc = PTR_ERR(bd);
+		dprintk("%s failed to open device : %d\n", __func__, rc);
+		rv = ERR_PTR(rc);
 		goto out;
 	}
 
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index b238d95ac48..ac289909814 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1468,12 +1468,12 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
 				res = NULL;
 				goto out;
 			/* This turned out not to be a regular file */
+			case -EISDIR:
 			case -ENOTDIR:
 				goto no_open;
 			case -ELOOP:
 				if (!(nd->intent.open.flags & O_NOFOLLOW))
 					goto no_open;
-			/* case -EISDIR: */
 			/* case -EINVAL: */
 			default:
 				res = ERR_CAST(inode);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 28b8c3f3cda..5b3d9842c40 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -895,3 +895,35 @@ static int nfs_setlease(struct file *file, long arg, struct file_lock **fl)
 			file->f_path.dentry->d_name.name, arg);
 	return -EINVAL;
 }
+
+#ifdef CONFIG_NFS_V4
+static int
+nfs4_file_open(struct inode *inode, struct file *filp)
+{
+	/*
+	 * NFSv4 opens are handled in d_lookup and d_revalidate. If we get to
+	 * this point, then something is very wrong
+	 */
+	dprintk("NFS: %s called! inode=%p filp=%p\n", __func__, inode, filp);
+	return -ENOTDIR;
+}
+
+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 */
diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c
index f20801ae0a1..47d1c6ff2d8 100644
--- a/fs/nfs/idmap.c
+++ b/fs/nfs/idmap.c
@@ -336,8 +336,6 @@ struct idmap {
 	struct idmap_hashtable	idmap_group_hash;
 };
 
-static ssize_t idmap_pipe_upcall(struct file *, struct rpc_pipe_msg *,
-				 char __user *, size_t);
 static ssize_t idmap_pipe_downcall(struct file *, const char __user *,
 				   size_t);
 static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *);
@@ -345,7 +343,7 @@ static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *);
 static unsigned int fnvhash32(const void *, size_t);
 
 static const struct rpc_pipe_ops idmap_upcall_ops = {
-	.upcall		= idmap_pipe_upcall,
+	.upcall		= rpc_pipe_generic_upcall,
 	.downcall	= idmap_pipe_downcall,
 	.destroy_msg	= idmap_pipe_destroy_msg,
 };
@@ -595,27 +593,6 @@ nfs_idmap_name(struct idmap *idmap, struct idmap_hashtable *h,
 	return ret;
 }
 
-/* RPC pipefs upcall/downcall routines */
-static ssize_t
-idmap_pipe_upcall(struct file *filp, struct rpc_pipe_msg *msg,
-		  char __user *dst, size_t buflen)
-{
-	char *data = (char *)msg->data + msg->copied;
-	size_t mlen = min(msg->len, buflen);
-	unsigned long left;
-
-	left = copy_to_user(dst, data, mlen);
-	if (left == mlen) {
-		msg->errno = -EFAULT;
-		return -EFAULT;
-	}
-
-	mlen -= left;
-	msg->copied += mlen;
-	msg->errno = 0;
-	return mlen;
-}
-
 static ssize_t
 idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
 {
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index fe1203797b2..679d2f50b14 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -291,7 +291,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		 */
 		inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->file_inode_ops;
 		if (S_ISREG(inode->i_mode)) {
-			inode->i_fop = &nfs_file_operations;
+			inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops;
 			inode->i_data.a_ops = &nfs_file_aops;
 			inode->i_data.backing_dev_info = &NFS_SB(sb)->backing_dev_info;
 		} else if (S_ISDIR(inode->i_mode)) {
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 85f1690ca08..d4bc9ed9174 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -853,6 +853,7 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
 	.dentry_ops	= &nfs_dentry_operations,
 	.dir_inode_ops	= &nfs3_dir_inode_operations,
 	.file_inode_ops	= &nfs3_file_inode_operations,
+	.file_ops	= &nfs_file_operations,
 	.getroot	= nfs3_proc_get_root,
 	.getattr	= nfs3_proc_getattr,
 	.setattr	= nfs3_proc_setattr,
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index e8915d4840a..4c78c62639e 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -77,19 +77,6 @@ filelayout_get_dserver_offset(struct pnfs_layout_segment *lseg, loff_t offset)
 	BUG();
 }
 
-/* For data server errors we don't recover from */
-static void
-filelayout_set_lo_fail(struct pnfs_layout_segment *lseg)
-{
-	if (lseg->pls_range.iomode == IOMODE_RW) {
-		dprintk("%s Setting layout IOMODE_RW fail bit\n", __func__);
-		set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
-	} else {
-		dprintk("%s Setting layout IOMODE_READ fail bit\n", __func__);
-		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
-	}
-}
-
 static int filelayout_async_handle_error(struct rpc_task *task,
 					 struct nfs4_state *state,
 					 struct nfs_client *clp,
@@ -145,7 +132,7 @@ static int filelayout_read_done_cb(struct rpc_task *task,
 		dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n",
 			__func__, data->ds_clp, data->ds_clp->cl_session);
 		if (reset) {
-			filelayout_set_lo_fail(data->lseg);
+			pnfs_set_lo_fail(data->lseg);
 			nfs4_reset_read(task, data);
 			clp = NFS_SERVER(data->inode)->nfs_client;
 		}
@@ -221,7 +208,7 @@ static int filelayout_write_done_cb(struct rpc_task *task,
 		dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n",
 			__func__, data->ds_clp, data->ds_clp->cl_session);
 		if (reset) {
-			filelayout_set_lo_fail(data->lseg);
+			pnfs_set_lo_fail(data->lseg);
 			nfs4_reset_write(task, data);
 			clp = NFS_SERVER(data->inode)->nfs_client;
 		} else
@@ -256,7 +243,7 @@ static int filelayout_commit_done_cb(struct rpc_task *task,
 			__func__, data->ds_clp, data->ds_clp->cl_session);
 		if (reset) {
 			prepare_to_resend_writes(data);
-			filelayout_set_lo_fail(data->lseg);
+			pnfs_set_lo_fail(data->lseg);
 		} else
 			nfs_restart_rpc(task, data->ds_clp);
 		return -EAGAIN;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 4700fae1ada..2d8a1693ed0 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -6267,6 +6267,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.dentry_ops	= &nfs4_dentry_operations,
 	.dir_inode_ops	= &nfs4_dir_inode_operations,
 	.file_inode_ops	= &nfs4_file_inode_operations,
+	.file_ops	= &nfs4_file_operations,
 	.getroot	= nfs4_proc_get_root,
 	.getattr	= nfs4_proc_getattr,
 	.setattr	= nfs4_proc_setattr,
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index e550e8836c3..ee73d9a4f70 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1168,23 +1168,17 @@ EXPORT_SYMBOL_GPL(pnfs_generic_pg_test);
 /*
  * Called by non rpc-based layout drivers
  */
-int
-pnfs_ld_write_done(struct nfs_write_data *data)
+void pnfs_ld_write_done(struct nfs_write_data *data)
 {
-	int status;
-
-	if (!data->pnfs_error) {
+	if (likely(!data->pnfs_error)) {
 		pnfs_set_layoutcommit(data);
 		data->mds_ops->rpc_call_done(&data->task, data);
-		data->mds_ops->rpc_release(data);
-		return 0;
+	} else {
+		put_lseg(data->lseg);
+		data->lseg = NULL;
+		dprintk("pnfs write error = %d\n", data->pnfs_error);
 	}
-
-	dprintk("%s: pnfs_error=%d, retry via MDS\n", __func__,
-		data->pnfs_error);
-	status = nfs_initiate_write(data, NFS_CLIENT(data->inode),
-				    data->mds_ops, NFS_FILE_SYNC);
-	return status ? : -EAGAIN;
+	data->mds_ops->rpc_release(data);
 }
 EXPORT_SYMBOL_GPL(pnfs_ld_write_done);
 
@@ -1268,23 +1262,17 @@ EXPORT_SYMBOL_GPL(pnfs_generic_pg_writepages);
 /*
  * Called by non rpc-based layout drivers
  */
-int
-pnfs_ld_read_done(struct nfs_read_data *data)
+void pnfs_ld_read_done(struct nfs_read_data *data)
 {
-	int status;
-
-	if (!data->pnfs_error) {
+	if (likely(!data->pnfs_error)) {
 		__nfs4_read_done_cb(data);
 		data->mds_ops->rpc_call_done(&data->task, data);
-		data->mds_ops->rpc_release(data);
-		return 0;
+	} else {
+		put_lseg(data->lseg);
+		data->lseg = NULL;
+		dprintk("pnfs write error = %d\n", data->pnfs_error);
 	}
-
-	dprintk("%s: pnfs_error=%d, retry via MDS\n", __func__,
-		data->pnfs_error);
-	status = nfs_initiate_read(data, NFS_CLIENT(data->inode),
-				   data->mds_ops);
-	return status ? : -EAGAIN;
+	data->mds_ops->rpc_release(data);
 }
 EXPORT_SYMBOL_GPL(pnfs_ld_read_done);
 
@@ -1381,6 +1369,18 @@ static void pnfs_list_write_lseg(struct inode *inode, struct list_head *listp)
 	}
 }
 
+void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg)
+{
+	if (lseg->pls_range.iomode == IOMODE_RW) {
+		dprintk("%s Setting layout IOMODE_RW fail bit\n", __func__);
+		set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
+	} else {
+		dprintk("%s Setting layout IOMODE_READ fail bit\n", __func__);
+		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
+	}
+}
+EXPORT_SYMBOL_GPL(pnfs_set_lo_fail);
+
 void
 pnfs_set_layoutcommit(struct nfs_write_data *wdata)
 {
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 01cbfd54f3c..1509530cb11 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -178,6 +178,7 @@ int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc);
 void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *, struct nfs_page *);
 int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc);
 bool pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req);
+void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg);
 int pnfs_layout_process(struct nfs4_layoutget *lgp);
 void pnfs_free_lseg_list(struct list_head *tmp_list);
 void pnfs_destroy_layout(struct nfs_inode *);
@@ -200,8 +201,8 @@ void pnfs_set_layoutcommit(struct nfs_write_data *wdata);
 void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data);
 int pnfs_layoutcommit_inode(struct inode *inode, bool sync);
 int _pnfs_return_layout(struct inode *);
-int pnfs_ld_write_done(struct nfs_write_data *);
-int pnfs_ld_read_done(struct nfs_read_data *);
+void pnfs_ld_write_done(struct nfs_write_data *);
+void pnfs_ld_read_done(struct nfs_read_data *);
 struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino,
 					       struct nfs_open_context *ctx,
 					       loff_t pos,
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index ac40b8535d7..f48125da198 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -710,6 +710,7 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
 	.dentry_ops	= &nfs_dentry_operations,
 	.dir_inode_ops	= &nfs_dir_inode_operations,
 	.file_inode_ops	= &nfs_file_inode_operations,
+	.file_ops	= &nfs_file_operations,
 	.getroot	= nfs_proc_get_root,
 	.getattr	= nfs_proc_getattr,
 	.setattr	= nfs_proc_setattr,
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 2171c043ab0..bfc20b16024 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -541,13 +541,23 @@ static void nfs_readpage_result_full(struct rpc_task *task, void *calldata)
 static void nfs_readpage_release_full(void *calldata)
 {
 	struct nfs_read_data *data = calldata;
+	struct nfs_pageio_descriptor pgio;
 
+	if (data->pnfs_error) {
+		nfs_pageio_init_read_mds(&pgio, data->inode);
+		pgio.pg_recoalesce = 1;
+	}
 	while (!list_empty(&data->pages)) {
 		struct nfs_page *req = nfs_list_entry(data->pages.next);
 
 		nfs_list_remove_request(req);
-		nfs_readpage_release(req);
+		if (!data->pnfs_error)
+			nfs_readpage_release(req);
+		else
+			nfs_pageio_add_request(&pgio, req);
 	}
+	if (data->pnfs_error)
+		nfs_pageio_complete(&pgio);
 	nfs_readdata_release(calldata);
 }
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index c9bd2a6b7d4..106fd0634ab 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -428,7 +428,6 @@ static void
 nfs_mark_request_dirty(struct nfs_page *req)
 {
 	__set_page_dirty_nobuffers(req->wb_page);
-	__mark_inode_dirty(req->wb_page->mapping->host, I_DIRTY_DATASYNC);
 }
 
 #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
@@ -762,6 +761,8 @@ int nfs_updatepage(struct file *file, struct page *page,
 	status = nfs_writepage_setup(ctx, page, offset, count);
 	if (status < 0)
 		nfs_set_pageerror(page);
+	else
+		__set_page_dirty_nobuffers(page);
 
 	dprintk("NFS:       nfs_updatepage returns %d (isize %lld)\n",
 			status, (long long)i_size_read(inode));
@@ -1165,7 +1166,13 @@ static void nfs_writeback_done_full(struct rpc_task *task, void *calldata)
 static void nfs_writeback_release_full(void *calldata)
 {
 	struct nfs_write_data	*data = calldata;
-	int status = data->task.tk_status;
+	int ret, status = data->task.tk_status;
+	struct nfs_pageio_descriptor pgio;
+
+	if (data->pnfs_error) {
+		nfs_pageio_init_write_mds(&pgio, data->inode, FLUSH_STABLE);
+		pgio.pg_recoalesce = 1;
+	}
 
 	/* Update attributes as result of writeback. */
 	while (!list_empty(&data->pages)) {
@@ -1181,6 +1188,11 @@ static void nfs_writeback_release_full(void *calldata)
 			req->wb_bytes,
 			(long long)req_offset(req));
 
+		if (data->pnfs_error) {
+			dprintk(", pnfs error = %d\n", data->pnfs_error);
+			goto next;
+		}
+
 		if (status < 0) {
 			nfs_set_pageerror(page);
 			nfs_context_set_write_error(req->wb_context, status);
@@ -1200,7 +1212,19 @@ remove_request:
 	next:
 		nfs_clear_page_tag_locked(req);
 		nfs_end_page_writeback(page);
+		if (data->pnfs_error) {
+			lock_page(page);
+			nfs_pageio_cond_complete(&pgio, page->index);
+			ret = nfs_page_async_flush(&pgio, page, 0);
+			if (ret) {
+				nfs_set_pageerror(page);
+				dprintk("rewrite to MDS error = %d\n", ret);
+			}
+			unlock_page(page);
+		}
 	}
+	if (data->pnfs_error)
+		nfs_pageio_complete(&pgio);
 	nfs_writedata_release(calldata);
 }
 
@@ -1553,6 +1577,10 @@ static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_contr
 	int flags = FLUSH_SYNC;
 	int ret = 0;
 
+	/* no commits means nothing needs to be done */
+	if (!nfsi->ncommit)
+		return ret;
+
 	if (wbc->sync_mode == WB_SYNC_NONE) {
 		/* Don't commit yet if this is a non-blocking flush and there
 		 * are a lot of outstanding writes for this mapping.
@@ -1686,34 +1714,20 @@ out_error:
 int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
 		struct page *page)
 {
-	struct nfs_page *req;
-	int ret;
+	/*
+	 * If PagePrivate is set, then the page is currently associated with
+	 * an in-progress read or write request. Don't try to migrate it.
+	 *
+	 * FIXME: we could do this in principle, but we'll need a way to ensure
+	 *        that we can safely release the inode reference while holding
+	 *        the page lock.
+	 */
+	if (PagePrivate(page))
+		return -EBUSY;
 
 	nfs_fscache_release_page(page, GFP_KERNEL);
 
-	req = nfs_find_and_lock_request(page, false);
-	ret = PTR_ERR(req);
-	if (IS_ERR(req))
-		goto out;
-
-	ret = migrate_page(mapping, newpage, page);
-	if (!req)
-		goto out;
-	if (ret)
-		goto out_unlock;
-	page_cache_get(newpage);
-	spin_lock(&mapping->host->i_lock);
-	req->wb_page = newpage;
-	SetPagePrivate(newpage);
-	set_page_private(newpage, (unsigned long)req);
-	ClearPagePrivate(page);
-	set_page_private(page, 0);
-	spin_unlock(&mapping->host->i_lock);
-	page_cache_release(page);
-out_unlock:
-	nfs_clear_page_tag_locked(req);
-out:
-	return ret;
+	return migrate_page(mapping, newpage, page);
 }
 #endif