1 files changed, 146 insertions, 385 deletions

diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index e4b62c6f5a6..e818a475ca6 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -18,8 +18,7 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/nfs_fs.h>
 #include <linux/nfs_page.h>
-
-#include <asm/system.h>
+#include <linux/module.h>
 
 #include "nfs4_fs.h"
 #include "internal.h"
@@ -29,48 +28,19 @@
 
 #define NFSDBG_FACILITY		NFSDBG_PAGECACHE
 
-static int nfs_pagein_multi(struct inode *, struct list_head *, unsigned int, size_t, int);
-static int nfs_pagein_one(struct inode *, struct list_head *, unsigned int, size_t, int);
-static const struct rpc_call_ops nfs_read_partial_ops;
-static const struct rpc_call_ops nfs_read_full_ops;
+static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops;
+static const struct nfs_rw_ops nfs_rw_read_ops;
 
 static struct kmem_cache *nfs_rdata_cachep;
-static mempool_t *nfs_rdata_mempool;
-
-#define MIN_POOL_READ	(32)
-
-struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount)
-{
-	struct nfs_read_data *p = mempool_alloc(nfs_rdata_mempool, GFP_KERNEL);
-
-	if (p) {
-		memset(p, 0, sizeof(*p));
-		INIT_LIST_HEAD(&p->pages);
-		p->npages = pagecount;
-		if (pagecount <= ARRAY_SIZE(p->page_array))
-			p->pagevec = p->page_array;
-		else {
-			p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL);
-			if (!p->pagevec) {
-				mempool_free(p, nfs_rdata_mempool);
-				p = NULL;
-			}
-		}
-	}
-	return p;
-}
 
-void nfs_readdata_free(struct nfs_read_data *p)
+static struct nfs_rw_header *nfs_readhdr_alloc(void)
 {
-	if (p && (p->pagevec != &p->page_array[0]))
-		kfree(p->pagevec);
-	mempool_free(p, nfs_rdata_mempool);
+	return kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL);
 }
 
-static void nfs_readdata_release(struct nfs_read_data *rdata)
+static void nfs_readhdr_free(struct nfs_rw_header *rhdr)
 {
-	put_nfs_open_context(rdata->args.context);
-	nfs_readdata_free(rdata);
+	kmem_cache_free(nfs_rdata_cachep, rhdr);
 }
 
 static
@@ -82,47 +52,40 @@ int nfs_return_empty_page(struct page *page)
 	return 0;
 }
 
-static void nfs_readpage_truncate_uninitialised_page(struct nfs_read_data *data)
+void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
+			      struct inode *inode, bool force_mds,
+			      const struct nfs_pgio_completion_ops *compl_ops)
 {
-	unsigned int remainder = data->args.count - data->res.count;
-	unsigned int base = data->args.pgbase + data->res.count;
-	unsigned int pglen;
-	struct page **pages;
+	struct nfs_server *server = NFS_SERVER(inode);
+	const struct nfs_pageio_ops *pg_ops = &nfs_pgio_rw_ops;
+
+#ifdef CONFIG_NFS_V4_1
+	if (server->pnfs_curr_ld && !force_mds)
+		pg_ops = server->pnfs_curr_ld->pg_read_ops;
+#endif
+	nfs_pageio_init(pgio, inode, pg_ops, compl_ops, &nfs_rw_read_ops,
+			server->rsize, 0);
+}
+EXPORT_SYMBOL_GPL(nfs_pageio_init_read);
 
-	if (data->res.eof == 0 || remainder == 0)
-		return;
-	/*
-	 * Note: "remainder" can never be negative, since we check for
-	 * 	this in the XDR code.
-	 */
-	pages = &data->args.pages[base >> PAGE_CACHE_SHIFT];
-	base &= ~PAGE_CACHE_MASK;
-	pglen = PAGE_CACHE_SIZE - base;
-	for (;;) {
-		if (remainder <= pglen) {
-			zero_user(*pages, base, remainder);
-			break;
-		}
-		zero_user(*pages, base, pglen);
-		pages++;
-		remainder -= pglen;
-		pglen = PAGE_CACHE_SIZE;
-		base = 0;
-	}
+void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio)
+{
+	pgio->pg_ops = &nfs_pgio_rw_ops;
+	pgio->pg_bsize = NFS_SERVER(pgio->pg_inode)->rsize;
 }
+EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds);
 
 int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 		       struct page *page)
 {
-	LIST_HEAD(one_request);
 	struct nfs_page	*new;
 	unsigned int len;
+	struct nfs_pageio_descriptor pgio;
 
 	len = nfs_page_length(page);
 	if (len == 0)
 		return nfs_return_empty_page(page);
-	pnfs_update_layout(inode, ctx, IOMODE_READ);
-	new = nfs_create_request(ctx, inode, page, 0, len);
+	new = nfs_create_request(ctx, page, NULL, 0, len);
 	if (IS_ERR(new)) {
 		unlock_page(page);
 		return PTR_ERR(new);
@@ -130,370 +93,171 @@ 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_list_add_request(new, &one_request);
-	if (NFS_SERVER(inode)->rsize < PAGE_CACHE_SIZE)
-		nfs_pagein_multi(inode, &one_request, 1, len, 0);
-	else
-		nfs_pagein_one(inode, &one_request, 1, len, 0);
+	nfs_pageio_init_read(&pgio, inode, false,
+			     &nfs_async_read_completion_ops);
+	nfs_pageio_add_request(&pgio, new);
+	nfs_pageio_complete(&pgio);
+	NFS_I(inode)->read_io += pgio.pg_bytes_written;
 	return 0;
 }
 
 static void nfs_readpage_release(struct nfs_page *req)
 {
-	struct inode *d_inode = req->wb_context->path.dentry->d_inode;
+	struct inode *d_inode = req->wb_context->dentry->d_inode;
 
-	if (PageUptodate(req->wb_page))
-		nfs_readpage_to_fscache(d_inode, req->wb_page, 0);
+	dprintk("NFS: read done (%s/%llu %d@%lld)\n", d_inode->i_sb->s_id,
+		(unsigned long long)NFS_FILEID(d_inode), req->wb_bytes,
+		(long long)req_offset(req));
 
-	unlock_page(req->wb_page);
+	if (nfs_page_group_sync_on_bit(req, PG_UNLOCKPAGE)) {
+		if (PageUptodate(req->wb_page))
+			nfs_readpage_to_fscache(d_inode, req->wb_page, 0);
 
-	dprintk("NFS: read done (%s/%Ld %d@%Ld)\n",
-			req->wb_context->path.dentry->d_inode->i_sb->s_id,
-			(long long)NFS_FILEID(req->wb_context->path.dentry->d_inode),
+		unlock_page(req->wb_page);
+	}
+
+	dprintk("NFS: read done (%s/%Lu %d@%Ld)\n",
+			req->wb_context->dentry->d_inode->i_sb->s_id,
+			(unsigned long long)NFS_FILEID(req->wb_context->dentry->d_inode),
 			req->wb_bytes,
 			(long long)req_offset(req));
-	nfs_clear_request(req);
 	nfs_release_request(req);
 }
 
-/*
- * Set up the NFS read request struct
- */
-static int nfs_read_rpcsetup(struct nfs_page *req, struct nfs_read_data *data,
-		const struct rpc_call_ops *call_ops,
-		unsigned int count, unsigned int offset)
+static void nfs_page_group_set_uptodate(struct nfs_page *req)
 {
-	struct inode *inode = req->wb_context->path.dentry->d_inode;
-	int swap_flags = IS_SWAPFILE(inode) ? NFS_RPC_SWAPFLAGS : 0;
-	struct rpc_task *task;
-	struct rpc_message msg = {
-		.rpc_argp = &data->args,
-		.rpc_resp = &data->res,
-		.rpc_cred = req->wb_context->cred,
-	};
-	struct rpc_task_setup task_setup_data = {
-		.task = &data->task,
-		.rpc_client = NFS_CLIENT(inode),
-		.rpc_message = &msg,
-		.callback_ops = call_ops,
-		.callback_data = data,
-		.workqueue = nfsiod_workqueue,
-		.flags = RPC_TASK_ASYNC | swap_flags,
-	};
-
-	data->req	  = req;
-	data->inode	  = inode;
-	data->cred	  = msg.rpc_cred;
-
-	data->args.fh     = NFS_FH(inode);
-	data->args.offset = req_offset(req) + offset;
-	data->args.pgbase = req->wb_pgbase + offset;
-	data->args.pages  = data->pagevec;
-	data->args.count  = count;
-	data->args.context = get_nfs_open_context(req->wb_context);
-	data->args.lock_context = req->wb_lock_context;
-
-	data->res.fattr   = &data->fattr;
-	data->res.count   = count;
-	data->res.eof     = 0;
-	nfs_fattr_init(&data->fattr);
-
-	/* Set up the initial task struct. */
-	NFS_PROTO(inode)->read_setup(data, &msg);
-
-	dprintk("NFS: %5u initiated read call (req %s/%Ld, %u bytes @ offset %Lu)\n",
-			data->task.tk_pid,
-			inode->i_sb->s_id,
-			(long long)NFS_FILEID(inode),
-			count,
-			(unsigned long long)data->args.offset);
-
-	task = rpc_run_task(&task_setup_data);
-	if (IS_ERR(task))
-		return PTR_ERR(task);
-	rpc_put_task(task);
-	return 0;
+	if (nfs_page_group_sync_on_bit(req, PG_UPTODATE))
+		SetPageUptodate(req->wb_page);
 }
 
-static void
-nfs_async_read_error(struct list_head *head)
+static void nfs_read_completion(struct nfs_pgio_header *hdr)
 {
-	struct nfs_page	*req;
+	unsigned long bytes = 0;
 
-	while (!list_empty(head)) {
-		req = nfs_list_entry(head->next);
+	if (test_bit(NFS_IOHDR_REDO, &hdr->flags))
+		goto out;
+	while (!list_empty(&hdr->pages)) {
+		struct nfs_page *req = nfs_list_entry(hdr->pages.next);
+		struct page *page = req->wb_page;
+		unsigned long start = req->wb_pgbase;
+		unsigned long end = req->wb_pgbase + req->wb_bytes;
+
+		if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) {
+			/* note: regions of the page not covered by a
+			 * request are zeroed in nfs_readpage_async /
+			 * readpage_async_filler */
+			if (bytes > hdr->good_bytes) {
+				/* nothing in this request was good, so zero
+				 * the full extent of the request */
+				zero_user_segment(page, start, end);
+
+			} else if (hdr->good_bytes - bytes < req->wb_bytes) {
+				/* part of this request has good bytes, but
+				 * not all. zero the bad bytes */
+				start += hdr->good_bytes - bytes;
+				WARN_ON(start < req->wb_pgbase);
+				zero_user_segment(page, start, end);
+			}
+		}
+		bytes += req->wb_bytes;
+		if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) {
+			if (bytes <= hdr->good_bytes)
+				nfs_page_group_set_uptodate(req);
+		} else
+			nfs_page_group_set_uptodate(req);
 		nfs_list_remove_request(req);
-		SetPageError(req->wb_page);
 		nfs_readpage_release(req);
 	}
+out:
+	hdr->release(hdr);
 }
 
-/*
- * Generate multiple requests to fill a single page.
- *
- * We optimize to reduce the number of read operations on the wire.  If we
- * detect that we're reading a page, or an area of a page, that is past the
- * end of file, we do not generate NFS read operations but just clear the
- * parts of the page that would have come back zero from the server anyway.
- *
- * We rely on the cached value of i_size to make this determination; another
- * client can fill pages on the server past our cached end-of-file, but we
- * won't see the new data until our attribute cache is updated.  This is more
- * or less conventional NFS client behavior.
- */
-static int nfs_pagein_multi(struct inode *inode, struct list_head *head, unsigned int npages, size_t count, int flags)
+static void nfs_initiate_read(struct nfs_pgio_data *data, struct rpc_message *msg,
+			      struct rpc_task_setup *task_setup_data, int how)
 {
-	struct nfs_page *req = nfs_list_entry(head->next);
-	struct page *page = req->wb_page;
-	struct nfs_read_data *data;
-	size_t rsize = NFS_SERVER(inode)->rsize, nbytes;
-	unsigned int offset;
-	int requests = 0;
-	int ret = 0;
-	LIST_HEAD(list);
-
-	nfs_list_remove_request(req);
-
-	nbytes = count;
-	do {
-		size_t len = min(nbytes,rsize);
-
-		data = nfs_readdata_alloc(1);
-		if (!data)
-			goto out_bad;
-		list_add(&data->pages, &list);
-		requests++;
-		nbytes -= len;
-	} while(nbytes != 0);
-	atomic_set(&req->wb_complete, requests);
-
-	ClearPageError(page);
-	offset = 0;
-	nbytes = count;
-	do {
-		int ret2;
-
-		data = list_entry(list.next, struct nfs_read_data, pages);
-		list_del_init(&data->pages);
-
-		data->pagevec[0] = page;
-
-		if (nbytes < rsize)
-			rsize = nbytes;
-		ret2 = nfs_read_rpcsetup(req, data, &nfs_read_partial_ops,
-				  rsize, offset);
-		if (ret == 0)
-			ret = ret2;
-		offset += rsize;
-		nbytes -= rsize;
-	} while (nbytes != 0);
-
-	return ret;
+	struct inode *inode = data->header->inode;
+	int swap_flags = IS_SWAPFILE(inode) ? NFS_RPC_SWAPFLAGS : 0;
 
-out_bad:
-	while (!list_empty(&list)) {
-		data = list_entry(list.next, struct nfs_read_data, pages);
-		list_del(&data->pages);
-		nfs_readdata_free(data);
-	}
-	SetPageError(page);
-	nfs_readpage_release(req);
-	return -ENOMEM;
+	task_setup_data->flags |= swap_flags;
+	NFS_PROTO(inode)->read_setup(data, msg);
 }
 
-static int nfs_pagein_one(struct inode *inode, struct list_head *head, unsigned int npages, size_t count, int flags)
+static void
+nfs_async_read_error(struct list_head *head)
 {
-	struct nfs_page		*req;
-	struct page		**pages;
-	struct nfs_read_data	*data;
-	int ret = -ENOMEM;
-
-	data = nfs_readdata_alloc(npages);
-	if (!data)
-		goto out_bad;
+	struct nfs_page	*req;
 
-	pages = data->pagevec;
 	while (!list_empty(head)) {
 		req = nfs_list_entry(head->next);
 		nfs_list_remove_request(req);
-		nfs_list_add_request(req, &data->pages);
-		ClearPageError(req->wb_page);
-		*pages++ = req->wb_page;
+		nfs_readpage_release(req);
 	}
-	req = nfs_list_entry(data->pages.next);
-
-	return nfs_read_rpcsetup(req, data, &nfs_read_full_ops, count, 0);
-out_bad:
-	nfs_async_read_error(head);
-	return ret;
 }
 
+static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops = {
+	.error_cleanup = nfs_async_read_error,
+	.completion = nfs_read_completion,
+};
+
 /*
  * This is the callback from RPC telling us whether a reply was
  * received or some error occurred (timeout or socket shutdown).
  */
-int nfs_readpage_result(struct rpc_task *task, struct nfs_read_data *data)
+static int nfs_readpage_done(struct rpc_task *task, struct nfs_pgio_data *data,
+			     struct inode *inode)
 {
-	int status;
-
-	dprintk("NFS: %s: %5u, (status %d)\n", __func__, task->tk_pid,
-			task->tk_status);
-
-	status = NFS_PROTO(data->inode)->read_done(task, data);
+	int status = NFS_PROTO(inode)->read_done(task, data);
 	if (status != 0)
 		return status;
 
-	nfs_add_stats(data->inode, NFSIOS_SERVERREADBYTES, data->res.count);
+	nfs_add_stats(inode, NFSIOS_SERVERREADBYTES, data->res.count);
 
 	if (task->tk_status == -ESTALE) {
-		set_bit(NFS_INO_STALE, &NFS_I(data->inode)->flags);
-		nfs_mark_for_revalidate(data->inode);
+		set_bit(NFS_INO_STALE, &NFS_I(inode)->flags);
+		nfs_mark_for_revalidate(inode);
 	}
 	return 0;
 }
 
-static void nfs_readpage_retry(struct rpc_task *task, struct nfs_read_data *data)
+static void nfs_readpage_retry(struct rpc_task *task, struct nfs_pgio_data *data)
 {
-	struct nfs_readargs *argp = &data->args;
-	struct nfs_readres *resp = &data->res;
-
-	if (resp->eof || resp->count == argp->count)
-		return;
+	struct nfs_pgio_args *argp = &data->args;
+	struct nfs_pgio_res  *resp = &data->res;
 
 	/* This is a short read! */
-	nfs_inc_stats(data->inode, NFSIOS_SHORTREAD);
+	nfs_inc_stats(data->header->inode, NFSIOS_SHORTREAD);
 	/* Has the server at least made some progress? */
-	if (resp->count == 0)
+	if (resp->count == 0) {
+		nfs_set_pgio_error(data->header, -EIO, argp->offset);
 		return;
-
+	}
 	/* Yes, so retry the read at the end of the data */
+	data->mds_offset += resp->count;
 	argp->offset += resp->count;
 	argp->pgbase += resp->count;
 	argp->count -= resp->count;
-	nfs_restart_rpc(task, NFS_SERVER(data->inode)->nfs_client);
-}
-
-/*
- * Handle a read reply that fills part of a page.
- */
-static void nfs_readpage_result_partial(struct rpc_task *task, void *calldata)
-{
-	struct nfs_read_data *data = calldata;
- 
-	if (nfs_readpage_result(task, data) != 0)
-		return;
-	if (task->tk_status < 0)
-		return;
-
-	nfs_readpage_truncate_uninitialised_page(data);
-	nfs_readpage_retry(task, data);
+	rpc_restart_call_prepare(task);
 }
 
-static void nfs_readpage_release_partial(void *calldata)
+static void nfs_readpage_result(struct rpc_task *task, struct nfs_pgio_data *data)
 {
-	struct nfs_read_data *data = calldata;
-	struct nfs_page *req = data->req;
-	struct page *page = req->wb_page;
-	int status = data->task.tk_status;
+	struct nfs_pgio_header *hdr = data->header;
 
-	if (status < 0)
-		SetPageError(page);
+	if (data->res.eof) {
+		loff_t bound;
 
-	if (atomic_dec_and_test(&req->wb_complete)) {
-		if (!PageError(page))
-			SetPageUptodate(page);
-		nfs_readpage_release(req);
-	}
-	nfs_readdata_release(calldata);
-}
-
-#if defined(CONFIG_NFS_V4_1)
-void nfs_read_prepare(struct rpc_task *task, void *calldata)
-{
-	struct nfs_read_data *data = calldata;
-
-	if (nfs4_setup_sequence(NFS_SERVER(data->inode),
-				&data->args.seq_args, &data->res.seq_res,
-				0, task))
-		return;
-	rpc_call_start(task);
-}
-#endif /* CONFIG_NFS_V4_1 */
-
-static const struct rpc_call_ops nfs_read_partial_ops = {
-#if defined(CONFIG_NFS_V4_1)
-	.rpc_call_prepare = nfs_read_prepare,
-#endif /* CONFIG_NFS_V4_1 */
-	.rpc_call_done = nfs_readpage_result_partial,
-	.rpc_release = nfs_readpage_release_partial,
-};
-
-static void nfs_readpage_set_pages_uptodate(struct nfs_read_data *data)
-{
-	unsigned int count = data->res.count;
-	unsigned int base = data->args.pgbase;
-	struct page **pages;
-
-	if (data->res.eof)
-		count = data->args.count;
-	if (unlikely(count == 0))
-		return;
-	pages = &data->args.pages[base >> PAGE_CACHE_SHIFT];
-	base &= ~PAGE_CACHE_MASK;
-	count += base;
-	for (;count >= PAGE_CACHE_SIZE; count -= PAGE_CACHE_SIZE, pages++)
-		SetPageUptodate(*pages);
-	if (count == 0)
-		return;
-	/* Was this a short read? */
-	if (data->res.eof || data->res.count == data->args.count)
-		SetPageUptodate(*pages);
-}
-
-/*
- * This is the callback from RPC telling us whether a reply was
- * received or some error occurred (timeout or socket shutdown).
- */
-static void nfs_readpage_result_full(struct rpc_task *task, void *calldata)
-{
-	struct nfs_read_data *data = calldata;
-
-	if (nfs_readpage_result(task, data) != 0)
-		return;
-	if (task->tk_status < 0)
-		return;
-	/*
-	 * Note: nfs_readpage_retry may change the values of
-	 * data->args. In the multi-page case, we therefore need
-	 * to ensure that we call nfs_readpage_set_pages_uptodate()
-	 * first.
-	 */
-	nfs_readpage_truncate_uninitialised_page(data);
-	nfs_readpage_set_pages_uptodate(data);
-	nfs_readpage_retry(task, data);
-}
-
-static void nfs_readpage_release_full(void *calldata)
-{
-	struct nfs_read_data *data = calldata;
-
-	while (!list_empty(&data->pages)) {
-		struct nfs_page *req = nfs_list_entry(data->pages.next);
-
-		nfs_list_remove_request(req);
-		nfs_readpage_release(req);
-	}
-	nfs_readdata_release(calldata);
+		bound = data->args.offset + data->res.count;
+		spin_lock(&hdr->lock);
+		if (bound < hdr->io_start + hdr->good_bytes) {
+			set_bit(NFS_IOHDR_EOF, &hdr->flags);
+			clear_bit(NFS_IOHDR_ERROR, &hdr->flags);
+			hdr->good_bytes = bound - hdr->io_start;
+		}
+		spin_unlock(&hdr->lock);
+	} else if (data->res.count != data->args.count)
+		nfs_readpage_retry(task, data);
 }
 
-static const struct rpc_call_ops nfs_read_full_ops = {
-#if defined(CONFIG_NFS_V4_1)
-	.rpc_call_prepare = nfs_read_prepare,
-#endif /* CONFIG_NFS_V4_1 */
-	.rpc_call_done = nfs_readpage_result_full,
-	.rpc_release = nfs_readpage_release_full,
-};
-
 /*
  * Read a page over NFS.
  * We read the page synchronously in the following case:
@@ -503,11 +267,11 @@ static const struct rpc_call_ops nfs_read_full_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);
 
@@ -561,7 +325,6 @@ 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 nfs_page *new;
 	unsigned int len;
 	int error;
@@ -570,7 +333,7 @@ readpage_async_filler(void *data, struct page *page)
 	if (len == 0)
 		return nfs_return_empty_page(page);
 
-	new = nfs_create_request(desc->ctx, inode, page, 0, len);
+	new = nfs_create_request(desc->ctx, page, NULL, 0, len);
 	if (IS_ERR(new))
 		goto out_error;
 
@@ -583,7 +346,6 @@ readpage_async_filler(void *data, struct page *page)
 	return 0;
 out_error:
 	error = PTR_ERR(new);
-	SetPageError(page);
 out_unlock:
 	unlock_page(page);
 	return error;
@@ -597,14 +359,12 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 		.pgio = &pgio,
 	};
 	struct inode *inode = mapping->host;
-	struct nfs_server *server = NFS_SERVER(inode);
-	size_t rsize = server->rsize;
 	unsigned long npages;
 	int ret = -ESTALE;
 
-	dprintk("NFS: nfs_readpages (%s/%Ld %d)\n",
+	dprintk("NFS: nfs_readpages (%s/%Lu %d)\n",
 			inode->i_sb->s_id,
-			(long long)NFS_FILEID(inode),
+			(unsigned long long)NFS_FILEID(inode),
 			nr_pages);
 	nfs_inc_stats(inode, NFSIOS_VFSREADPAGES);
 
@@ -626,15 +386,13 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 	if (ret == 0)
 		goto read_complete; /* all pages were read */
 
-	pnfs_update_layout(inode, desc.ctx, IOMODE_READ);
-	if (rsize < PAGE_CACHE_SIZE)
-		nfs_pageio_init(&pgio, inode, nfs_pagein_multi, rsize, 0);
-	else
-		nfs_pageio_init(&pgio, inode, nfs_pagein_one, rsize, 0);
+	nfs_pageio_init_read(&pgio, inode, false,
+			     &nfs_async_read_completion_ops);
 
 	ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc);
 
 	nfs_pageio_complete(&pgio);
+	NFS_I(inode)->read_io += pgio.pg_bytes_written;
 	npages = (pgio.pg_bytes_written + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 	nfs_add_stats(inode, NFSIOS_READPAGES, npages);
 read_complete:
@@ -646,22 +404,25 @@ out:
 int __init nfs_init_readpagecache(void)
 {
 	nfs_rdata_cachep = kmem_cache_create("nfs_read_data",
-					     sizeof(struct nfs_read_data),
+					     sizeof(struct nfs_rw_header),
 					     0, SLAB_HWCACHE_ALIGN,
 					     NULL);
 	if (nfs_rdata_cachep == NULL)
 		return -ENOMEM;
 
-	nfs_rdata_mempool = mempool_create_slab_pool(MIN_POOL_READ,
-						     nfs_rdata_cachep);
-	if (nfs_rdata_mempool == NULL)
-		return -ENOMEM;
-
 	return 0;
 }
 
 void nfs_destroy_readpagecache(void)
 {
-	mempool_destroy(nfs_rdata_mempool);
 	kmem_cache_destroy(nfs_rdata_cachep);
 }
+
+static const struct nfs_rw_ops nfs_rw_read_ops = {
+	.rw_mode		= FMODE_READ,
+	.rw_alloc_header	= nfs_readhdr_alloc,
+	.rw_free_header		= nfs_readhdr_free,
+	.rw_done		= nfs_readpage_done,
+	.rw_result		= nfs_readpage_result,
+	.rw_initiate		= nfs_initiate_read,
+};