NFS: create common nfs_pgio_header for both read and write

In order to avoid duplicating all the data in nfs_read_data whenever we
split it up into multiple RPC calls (either due to a short read result
or due to rsize < PAGE_SIZE), we split out the bits that are the same
per RPC call into a separate "header" structure.

The goal this patch moves towards is to have a single header
refcounted by several rpc_data structures.  Thus, want to always refer
from rpc_data to the header, and not the other way.  This patch comes
close to that ideal, but the directio code currently needs some
special casing, isolated in the nfs_direct_[read_write]hdr_release()
functions.  This will be dealt with in a future patch.

Signed-off-by: Fred Isaman <iisaman@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>

12 files changed, 349 insertions, 245 deletions

diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 7f6a23f0244..7a482517f4c 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -187,7 +187,6 @@ static void bl_end_io_read(struct bio *bio, int err)
 	struct parallel_io *par = bio->bi_private;
 	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
-	struct nfs_read_data *rdata = (struct nfs_read_data *)par->data;
 
 	do {
 		struct page *page = bvec->bv_page;
@@ -198,9 +197,12 @@ static void bl_end_io_read(struct bio *bio, int err)
 			SetPageUptodate(page);
 	} while (bvec >= bio->bi_io_vec);
 	if (!uptodate) {
-		if (!rdata->pnfs_error)
-			rdata->pnfs_error = -EIO;
-		pnfs_set_lo_fail(rdata->lseg);
+		struct nfs_read_data *rdata = par->data;
+		struct nfs_pgio_header *header = rdata->header;
+
+		if (!header->pnfs_error)
+			header->pnfs_error = -EIO;
+		pnfs_set_lo_fail(header->lseg);
 	}
 	bio_put(bio);
 	put_parallel(par);
@@ -221,7 +223,7 @@ bl_end_par_io_read(void *data, int unused)
 {
 	struct nfs_read_data *rdata = data;
 
-	rdata->task.tk_status = rdata->pnfs_error;
+	rdata->task.tk_status = rdata->header->pnfs_error;
 	INIT_WORK(&rdata->task.u.tk_work, bl_read_cleanup);
 	schedule_work(&rdata->task.u.tk_work);
 }
@@ -229,6 +231,7 @@ bl_end_par_io_read(void *data, int unused)
 static enum pnfs_try_status
 bl_read_pagelist(struct nfs_read_data *rdata)
 {
+	struct nfs_pgio_header *header = rdata->header;
 	int i, hole;
 	struct bio *bio = NULL;
 	struct pnfs_block_extent *be = NULL, *cow_read = NULL;
@@ -256,10 +259,10 @@ bl_read_pagelist(struct nfs_read_data *rdata)
 			bl_put_extent(cow_read);
 			bio = bl_submit_bio(READ, bio);
 			/* Get the next one */
-			be = bl_find_get_extent(BLK_LSEG2EXT(rdata->lseg),
+			be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg),
 					     isect, &cow_read);
 			if (!be) {
-				rdata->pnfs_error = -EIO;
+				header->pnfs_error = -EIO;
 				goto out;
 			}
 			extent_length = be->be_length -
@@ -286,7 +289,7 @@ bl_read_pagelist(struct nfs_read_data *rdata)
 						 isect, pages[i], be_read,
 						 bl_end_io_read, par);
 			if (IS_ERR(bio)) {
-				rdata->pnfs_error = PTR_ERR(bio);
+				header->pnfs_error = PTR_ERR(bio);
 				bio = NULL;
 				goto out;
 			}
@@ -294,9 +297,9 @@ bl_read_pagelist(struct nfs_read_data *rdata)
 		isect += PAGE_CACHE_SECTORS;
 		extent_length -= PAGE_CACHE_SECTORS;
 	}
-	if ((isect << SECTOR_SHIFT) >= rdata->inode->i_size) {
+	if ((isect << SECTOR_SHIFT) >= header->inode->i_size) {
 		rdata->res.eof = 1;
-		rdata->res.count = rdata->inode->i_size - f_offset;
+		rdata->res.count = header->inode->i_size - f_offset;
 	} else {
 		rdata->res.count = (isect << SECTOR_SHIFT) - f_offset;
 	}
@@ -345,7 +348,6 @@ static void bl_end_io_write_zero(struct bio *bio, int err)
 	struct parallel_io *par = bio->bi_private;
 	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
-	struct nfs_write_data *wdata = (struct nfs_write_data *)par->data;
 
 	do {
 		struct page *page = bvec->bv_page;
@@ -358,9 +360,12 @@ static void bl_end_io_write_zero(struct bio *bio, int err)
 	} while (bvec >= bio->bi_io_vec);
 
 	if (unlikely(!uptodate)) {
-		if (!wdata->pnfs_error)
-			wdata->pnfs_error = -EIO;
-		pnfs_set_lo_fail(wdata->lseg);
+		struct nfs_write_data *data = par->data;
+		struct nfs_pgio_header *header = data->header;
+
+		if (!header->pnfs_error)
+			header->pnfs_error = -EIO;
+		pnfs_set_lo_fail(header->lseg);
 	}
 	bio_put(bio);
 	put_parallel(par);
@@ -370,12 +375,13 @@ static void bl_end_io_write(struct bio *bio, int err)
 {
 	struct parallel_io *par = bio->bi_private;
 	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
-	struct nfs_write_data *wdata = (struct nfs_write_data *)par->data;
+	struct nfs_write_data *data = par->data;
+	struct nfs_pgio_header *header = data->header;
 
 	if (!uptodate) {
-		if (!wdata->pnfs_error)
-			wdata->pnfs_error = -EIO;
-		pnfs_set_lo_fail(wdata->lseg);
+		if (!header->pnfs_error)
+			header->pnfs_error = -EIO;
+		pnfs_set_lo_fail(header->lseg);
 	}
 	bio_put(bio);
 	put_parallel(par);
@@ -391,9 +397,9 @@ static void bl_write_cleanup(struct work_struct *work)
 	dprintk("%s enter\n", __func__);
 	task = container_of(work, struct rpc_task, u.tk_work);
 	wdata = container_of(task, struct nfs_write_data, task);
-	if (likely(!wdata->pnfs_error)) {
+	if (likely(!wdata->header->pnfs_error)) {
 		/* Marks for LAYOUTCOMMIT */
-		mark_extents_written(BLK_LSEG2EXT(wdata->lseg),
+		mark_extents_written(BLK_LSEG2EXT(wdata->header->lseg),
 				     wdata->args.offset, wdata->args.count);
 	}
 	pnfs_ld_write_done(wdata);
@@ -404,12 +410,12 @@ static void bl_end_par_io_write(void *data, int num_se)
 {
 	struct nfs_write_data *wdata = data;
 
-	if (unlikely(wdata->pnfs_error)) {
-		bl_free_short_extents(&BLK_LSEG2EXT(wdata->lseg)->bl_inval,
+	if (unlikely(wdata->header->pnfs_error)) {
+		bl_free_short_extents(&BLK_LSEG2EXT(wdata->header->lseg)->bl_inval,
 					num_se);
 	}
 
-	wdata->task.tk_status = wdata->pnfs_error;
+	wdata->task.tk_status = wdata->header->pnfs_error;
 	wdata->verf.committed = NFS_FILE_SYNC;
 	INIT_WORK(&wdata->task.u.tk_work, bl_write_cleanup);
 	schedule_work(&wdata->task.u.tk_work);
@@ -540,6 +546,7 @@ check_page:
 static enum pnfs_try_status
 bl_write_pagelist(struct nfs_write_data *wdata, int sync)
 {
+	struct nfs_pgio_header *header = wdata->header;
 	int i, ret, npg_zero, pg_index, last = 0;
 	struct bio *bio = NULL;
 	struct pnfs_block_extent *be = NULL, *cow_read = NULL;
@@ -552,7 +559,7 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync)
 	pgoff_t index;
 	u64 temp;
 	int npg_per_block =
-	    NFS_SERVER(wdata->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT;
+	    NFS_SERVER(header->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT;
 
 	dprintk("%s enter, %Zu@%lld\n", __func__, count, offset);
 	/* At this point, wdata->pages is a (sequential) list of nfs_pages.
@@ -566,7 +573,7 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync)
 	/* At this point, have to be more careful with error handling */
 
 	isect = (sector_t) ((offset & (long)PAGE_CACHE_MASK) >> SECTOR_SHIFT);
-	be = bl_find_get_extent(BLK_LSEG2EXT(wdata->lseg), isect, &cow_read);
+	be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg), isect, &cow_read);
 	if (!be || !is_writable(be, isect)) {
 		dprintk("%s no matching extents!\n", __func__);
 		goto out_mds;
@@ -597,10 +604,10 @@ fill_invalid_ext:
 			dprintk("%s zero %dth page: index %lu isect %llu\n",
 				__func__, npg_zero, index,
 				(unsigned long long)isect);
-			page = bl_find_get_zeroing_page(wdata->inode, index,
+			page = bl_find_get_zeroing_page(header->inode, index,
 							cow_read);
 			if (unlikely(IS_ERR(page))) {
-				wdata->pnfs_error = PTR_ERR(page);
+				header->pnfs_error = PTR_ERR(page);
 				goto out;
 			} else if (page == NULL)
 				goto next_page;
@@ -612,7 +619,7 @@ fill_invalid_ext:
 					__func__, ret);
 				end_page_writeback(page);
 				page_cache_release(page);
-				wdata->pnfs_error = ret;
+				header->pnfs_error = ret;
 				goto out;
 			}
 			if (likely(!bl_push_one_short_extent(be->be_inval)))
@@ -620,11 +627,11 @@ fill_invalid_ext:
 			else {
 				end_page_writeback(page);
 				page_cache_release(page);
-				wdata->pnfs_error = -ENOMEM;
+				header->pnfs_error = -ENOMEM;
 				goto out;
 			}
 			/* FIXME: This should be done in bi_end_io */
-			mark_extents_written(BLK_LSEG2EXT(wdata->lseg),
+			mark_extents_written(BLK_LSEG2EXT(header->lseg),
 					     page->index << PAGE_CACHE_SHIFT,
 					     PAGE_CACHE_SIZE);
 
@@ -632,7 +639,7 @@ fill_invalid_ext:
 						 isect, page, be,
 						 bl_end_io_write_zero, par);
 			if (IS_ERR(bio)) {
-				wdata->pnfs_error = PTR_ERR(bio);
+				header->pnfs_error = PTR_ERR(bio);
 				bio = NULL;
 				goto out;
 			}
@@ -653,10 +660,10 @@ next_page:
 			bl_put_extent(be);
 			bio = bl_submit_bio(WRITE, bio);
 			/* Get the next one */
-			be = bl_find_get_extent(BLK_LSEG2EXT(wdata->lseg),
+			be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg),
 					     isect, NULL);
 			if (!be || !is_writable(be, isect)) {
-				wdata->pnfs_error = -EINVAL;
+				header->pnfs_error = -EINVAL;
 				goto out;
 			}
 			if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
@@ -664,7 +671,7 @@ next_page:
 								be->be_inval)))
 					par->bse_count++;
 				else {
-					wdata->pnfs_error = -ENOMEM;
+					header->pnfs_error = -ENOMEM;
 					goto out;
 				}
 			}
@@ -677,7 +684,7 @@ next_page:
 			if (unlikely(ret)) {
 				dprintk("%s bl_mark_sectors_init fail %d\n",
 					__func__, ret);
-				wdata->pnfs_error = ret;
+				header->pnfs_error = ret;
 				goto out;
 			}
 		}
@@ -685,7 +692,7 @@ next_page:
 					 isect, pages[i], be,
 					 bl_end_io_write, par);
 		if (IS_ERR(bio)) {
-			wdata->pnfs_error = PTR_ERR(bio);
+			header->pnfs_error = PTR_ERR(bio);
 			bio = NULL;
 			goto out;
 		}
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index fb7fbaa79c2..56176af1436 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -242,7 +242,7 @@ static void nfs_direct_read_release(void *calldata)
 {
 
 	struct nfs_read_data *data = calldata;
-	struct nfs_direct_req *dreq = (struct nfs_direct_req *) data->req;
+	struct nfs_direct_req *dreq = (struct nfs_direct_req *)data->header->req;
 	int status = data->task.tk_status;
 
 	spin_lock(&dreq->lock);
@@ -269,6 +269,15 @@ static const struct rpc_call_ops nfs_read_direct_ops = {
 	.rpc_release = nfs_direct_read_release,
 };
 
+static void nfs_direct_readhdr_release(struct nfs_read_header *rhdr)
+{
+	struct nfs_read_data *data = &rhdr->rpc_data;
+
+	if (data->pagevec != data->page_array)
+		kfree(data->pagevec);
+	nfs_readhdr_free(&rhdr->header);
+}
+
 /*
  * For each rsize'd chunk of the user's buffer, dispatch an NFS READ
  * operation.  If nfs_readdata_alloc() or get_user_pages() fails,
@@ -301,6 +310,7 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq,
 	ssize_t started = 0;
 
 	do {
+		struct nfs_read_header *rhdr;
 		struct nfs_read_data *data;
 		size_t bytes;
 
@@ -308,23 +318,24 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq,
 		bytes = min(rsize,count);
 
 		result = -ENOMEM;
-		data = nfs_readdata_alloc(nfs_page_array_len(pgbase, bytes));
-		if (unlikely(!data))
+		rhdr = nfs_readhdr_alloc(nfs_page_array_len(pgbase, bytes));
+		if (unlikely(!rhdr))
 			break;
+		data = &rhdr->rpc_data;
 
 		down_read(&current->mm->mmap_sem);
 		result = get_user_pages(current, current->mm, user_addr,
 					data->npages, 1, 0, data->pagevec, NULL);
 		up_read(&current->mm->mmap_sem);
 		if (result < 0) {
-			nfs_readdata_free(data);
+			nfs_direct_readhdr_release(rhdr);
 			break;
 		}
 		if ((unsigned)result < data->npages) {
 			bytes = result * PAGE_SIZE;
 			if (bytes <= pgbase) {
 				nfs_direct_release_pages(data->pagevec, result);
-				nfs_readdata_free(data);
+				nfs_direct_readhdr_release(rhdr);
 				break;
 			}
 			bytes -= pgbase;
@@ -333,9 +344,9 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq,
 
 		get_dreq(dreq);
 
-		data->req = (struct nfs_page *) dreq;
-		data->inode = inode;
-		data->cred = msg.rpc_cred;
+		rhdr->header.req = (struct nfs_page *) dreq;
+		rhdr->header.inode = inode;
+		rhdr->header.cred = msg.rpc_cred;
 		data->args.fh = NFS_FH(inode);
 		data->args.context = get_nfs_open_context(ctx);
 		data->args.lock_context = dreq->l_ctx;
@@ -447,13 +458,23 @@ out:
 	return result;
 }
 
+static void nfs_direct_writehdr_release(struct nfs_write_header *whdr)
+{
+	struct nfs_write_data *data = &whdr->rpc_data;
+
+	if (data->pagevec != data->page_array)
+		kfree(data->pagevec);
+	nfs_writehdr_free(&whdr->header);
+}
+
 static void nfs_direct_free_writedata(struct nfs_direct_req *dreq)
 {
 	while (!list_empty(&dreq->rewrite_list)) {
-		struct nfs_write_data *data = list_entry(dreq->rewrite_list.next, struct nfs_write_data, pages);
-		list_del(&data->pages);
-		nfs_direct_release_pages(data->pagevec, data->npages);
-		nfs_writedata_free(data);
+		struct nfs_pgio_header *hdr = list_entry(dreq->rewrite_list.next, struct nfs_pgio_header, pages);
+		struct nfs_write_header *whdr = container_of(hdr, struct nfs_write_header, header);
+		list_del(&hdr->pages);
+		nfs_direct_release_pages(whdr->rpc_data.pagevec, whdr->rpc_data.npages);
+		nfs_direct_writehdr_release(whdr);
 	}
 }
 
@@ -463,6 +484,7 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 	struct inode *inode = dreq->inode;
 	struct list_head *p;
 	struct nfs_write_data *data;
+	struct nfs_pgio_header *hdr;
 	struct rpc_task *task;
 	struct rpc_message msg = {
 		.rpc_cred = dreq->ctx->cred,
@@ -479,7 +501,8 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 	get_dreq(dreq);
 
 	list_for_each(p, &dreq->rewrite_list) {
-		data = list_entry(p, struct nfs_write_data, pages);
+		hdr = list_entry(p, struct nfs_pgio_header, pages);
+		data = &(container_of(hdr, struct nfs_write_header, header))->rpc_data;
 
 		get_dreq(dreq);
 
@@ -652,7 +675,8 @@ static void nfs_direct_write_result(struct rpc_task *task, void *calldata)
 static void nfs_direct_write_release(void *calldata)
 {
 	struct nfs_write_data *data = calldata;
-	struct nfs_direct_req *dreq = (struct nfs_direct_req *) data->req;
+	struct nfs_pgio_header *hdr = data->header;
+	struct nfs_direct_req *dreq = (struct nfs_direct_req *) hdr->req;
 	int status = data->task.tk_status;
 
 	spin_lock(&dreq->lock);
@@ -684,7 +708,7 @@ out_unlock:
 	spin_unlock(&dreq->lock);
 
 	if (put_dreq(dreq))
-		nfs_direct_write_complete(dreq, data->inode);
+		nfs_direct_write_complete(dreq, hdr->inode);
 }
 
 static const struct rpc_call_ops nfs_write_direct_ops = {
@@ -725,6 +749,7 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq,
 	ssize_t started = 0;
 
 	do {
+		struct nfs_write_header *whdr;
 		struct nfs_write_data *data;
 		size_t bytes;
 
@@ -732,23 +757,25 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq,
 		bytes = min(wsize,count);
 
 		result = -ENOMEM;
-		data = nfs_writedata_alloc(nfs_page_array_len(pgbase, bytes));
-		if (unlikely(!data))
+		whdr = nfs_writehdr_alloc(nfs_page_array_len(pgbase, bytes));
+		if (unlikely(!whdr))
 			break;
 
+		data = &whdr->rpc_data;
+
 		down_read(&current->mm->mmap_sem);
 		result = get_user_pages(current, current->mm, user_addr,
 					data->npages, 0, 0, data->pagevec, NULL);
 		up_read(&current->mm->mmap_sem);
 		if (result < 0) {
-			nfs_writedata_free(data);
+			nfs_direct_writehdr_release(whdr);
 			break;
 		}
 		if ((unsigned)result < data->npages) {
 			bytes = result * PAGE_SIZE;
 			if (bytes <= pgbase) {
 				nfs_direct_release_pages(data->pagevec, result);
-				nfs_writedata_free(data);
+				nfs_direct_writehdr_release(whdr);
 				break;
 			}
 			bytes -= pgbase;
@@ -757,11 +784,11 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq,
 
 		get_dreq(dreq);
 
-		list_move_tail(&data->pages, &dreq->rewrite_list);
+		list_move_tail(&whdr->header.pages, &dreq->rewrite_list);
 
-		data->req = (struct nfs_page *) dreq;
-		data->inode = inode;
-		data->cred = msg.rpc_cred;
+		whdr->header.req = (struct nfs_page *) dreq;
+		whdr->header.inode = inode;
+		whdr->header.cred = msg.rpc_cred;
 		data->args.fh = NFS_FH(inode);
 		data->args.context = ctx;
 		data->args.lock_context = dreq->l_ctx;
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 650127fd24b..7dc9be1a6e1 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -296,6 +296,8 @@ extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh);
 
 struct nfs_pageio_descriptor;
 /* read.c */
+extern struct nfs_read_header *nfs_readhdr_alloc(unsigned int npages);
+extern void nfs_readhdr_free(struct nfs_pgio_header *hdr);
 extern int nfs_initiate_read(struct rpc_clnt *clnt,
 			     struct nfs_read_data *data,
 			     const struct rpc_call_ops *call_ops);
@@ -309,6 +311,8 @@ extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
 extern void nfs_readdata_release(struct nfs_read_data *rdata);
 
 /* write.c */
+extern struct nfs_write_header *nfs_writehdr_alloc(unsigned int npages);
+extern void nfs_writehdr_free(struct nfs_pgio_header *hdr);
 extern int nfs_generic_flush(struct nfs_pageio_descriptor *desc,
 		struct list_head *head);
 extern void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio,
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index b1daca7f0f7..56dcefc2f3f 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -811,11 +811,13 @@ nfs3_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
 
 static int nfs3_read_done(struct rpc_task *task, struct nfs_read_data *data)
 {
-	if (nfs3_async_handle_jukebox(task, data->inode))
+	struct inode *inode = data->header->inode;
+
+	if (nfs3_async_handle_jukebox(task, inode))
 		return -EAGAIN;
 
-	nfs_invalidate_atime(data->inode);
-	nfs_refresh_inode(data->inode, &data->fattr);
+	nfs_invalidate_atime(inode);
+	nfs_refresh_inode(inode, &data->fattr);
 	return 0;
 }
 
@@ -831,10 +833,12 @@ static void nfs3_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_da
 
 static int nfs3_write_done(struct rpc_task *task, struct nfs_write_data *data)
 {
-	if (nfs3_async_handle_jukebox(task, data->inode))
+	struct inode *inode = data->header->inode;
+
+	if (nfs3_async_handle_jukebox(task, inode))
 		return -EAGAIN;
 	if (task->tk_status >= 0)
-		nfs_post_op_update_inode_force_wcc(data->inode, data->res.fattr);
+		nfs_post_op_update_inode_force_wcc(inode, data->res.fattr);
 	return 0;
 }
 
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index c536328557c..ad1d68013a5 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -148,6 +148,7 @@ wait_on_recovery:
 static int filelayout_read_done_cb(struct rpc_task *task,
 				struct nfs_read_data *data)
 {
+	struct nfs_pgio_header *hdr = data->header;
 	int reset = 0;
 
 	dprintk("%s DS read\n", __func__);
@@ -157,7 +158,7 @@ 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) {
-			pnfs_set_lo_fail(data->lseg);
+			pnfs_set_lo_fail(hdr->lseg);
 			nfs4_reset_read(task, data);
 		}
 		rpc_restart_call_prepare(task);
@@ -175,13 +176,15 @@ static int filelayout_read_done_cb(struct rpc_task *task,
 static void
 filelayout_set_layoutcommit(struct nfs_write_data *wdata)
 {
-	if (FILELAYOUT_LSEG(wdata->lseg)->commit_through_mds ||
+	struct nfs_pgio_header *hdr = wdata->header;
+
+	if (FILELAYOUT_LSEG(hdr->lseg)->commit_through_mds ||
 	    wdata->res.verf->committed == NFS_FILE_SYNC)
 		return;
 
 	pnfs_set_layoutcommit(wdata);
-	dprintk("%s ionde %lu pls_end_pos %lu\n", __func__, wdata->inode->i_ino,
-		(unsigned long) NFS_I(wdata->inode)->layout->plh_lwb);
+	dprintk("%s ionde %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino,
+		(unsigned long) NFS_I(hdr->inode)->layout->plh_lwb);
 }
 
 /*
@@ -210,27 +213,28 @@ static void filelayout_read_call_done(struct rpc_task *task, void *data)
 	dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status);
 
 	/* Note this may cause RPC to be resent */
-	rdata->mds_ops->rpc_call_done(task, data);
+	rdata->header->mds_ops->rpc_call_done(task, data);
 }
 
 static void filelayout_read_count_stats(struct rpc_task *task, void *data)
 {
 	struct nfs_read_data *rdata = data;
 
-	rpc_count_iostats(task, NFS_SERVER(rdata->inode)->client->cl_metrics);
+	rpc_count_iostats(task, NFS_SERVER(rdata->header->inode)->client->cl_metrics);
 }
 
 static void filelayout_read_release(void *data)
 {
 	struct nfs_read_data *rdata = data;
 
-	put_lseg(rdata->lseg);
-	rdata->mds_ops->rpc_release(data);
+	put_lseg(rdata->header->lseg);
+	rdata->header->mds_ops->rpc_release(data);
 }
 
 static int filelayout_write_done_cb(struct rpc_task *task,
 				struct nfs_write_data *data)
 {
+	struct nfs_pgio_header *hdr = data->header;
 	int reset = 0;
 
 	if (filelayout_async_handle_error(task, data->args.context->state,
@@ -238,7 +242,7 @@ 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) {
-			pnfs_set_lo_fail(data->lseg);
+			pnfs_set_lo_fail(hdr->lseg);
 			nfs4_reset_write(task, data);
 		}
 		rpc_restart_call_prepare(task);
@@ -297,22 +301,22 @@ static void filelayout_write_call_done(struct rpc_task *task, void *data)
 	struct nfs_write_data *wdata = data;
 
 	/* Note this may cause RPC to be resent */
-	wdata->mds_ops->rpc_call_done(task, data);
+	wdata->header->mds_ops->rpc_call_done(task, data);
 }
 
 static void filelayout_write_count_stats(struct rpc_task *task, void *data)
 {
 	struct nfs_write_data *wdata = data;
 
-	rpc_count_iostats(task, NFS_SERVER(wdata->inode)->client->cl_metrics);
+	rpc_count_iostats(task, NFS_SERVER(wdata->header->inode)->client->cl_metrics);
 }
 
 static void filelayout_write_release(void *data)
 {
 	struct nfs_write_data *wdata = data;
 
-	put_lseg(wdata->lseg);
-	wdata->mds_ops->rpc_release(data);
+	put_lseg(wdata->header->lseg);
+	wdata->header->mds_ops->rpc_release(data);
 }
 
 static void filelayout_commit_prepare(struct rpc_task *task, void *data)
@@ -377,7 +381,8 @@ static const struct rpc_call_ops filelayout_commit_call_ops = {
 static enum pnfs_try_status
 filelayout_read_pagelist(struct nfs_read_data *data)
 {
-	struct pnfs_layout_segment *lseg = data->lseg;
+	struct nfs_pgio_header *hdr = data->header;
+	struct pnfs_layout_segment *lseg = hdr->lseg;
 	struct nfs4_pnfs_ds *ds;
 	loff_t offset = data->args.offset;
 	u32 j, idx;
@@ -385,7 +390,7 @@ filelayout_read_pagelist(struct nfs_read_data *data)
 	int status;
 
 	dprintk("--> %s ino %lu pgbase %u req %Zu@%llu\n",
-		__func__, data->inode->i_ino,
+		__func__, hdr->inode->i_ino,
 		data->args.pgbase, (size_t)data->args.count, offset);
 
 	if (test_bit(NFS_DEVICEID_INVALID, &FILELAYOUT_DEVID_NODE(lseg)->flags))
@@ -423,7 +428,8 @@ filelayout_read_pagelist(struct nfs_read_data *data)
 static enum pnfs_try_status
 filelayout_write_pagelist(struct nfs_write_data *data, int sync)
 {
-	struct pnfs_layout_segment *lseg = data->lseg;
+	struct nfs_pgio_header *hdr = data->header;
+	struct pnfs_layout_segment *lseg = hdr->lseg;
 	struct nfs4_pnfs_ds *ds;
 	loff_t offset = data->args.offset;
 	u32 j, idx;
@@ -445,7 +451,7 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync)
 		return PNFS_NOT_ATTEMPTED;
 	}
 	dprintk("%s ino %lu sync %d req %Zu@%llu DS: %s\n", __func__,
-		data->inode->i_ino, sync, (size_t) data->args.count, offset,
+		hdr->inode->i_ino, sync, (size_t) data->args.count, offset,
 		ds->ds_remotestr);
 
 	data->write_done_cb = filelayout_write_done_cb;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index cc04b6e409e..5375862075d 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3336,12 +3336,12 @@ static int nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
 
 void __nfs4_read_done_cb(struct nfs_read_data *data)
 {
-	nfs_invalidate_atime(data->inode);
+	nfs_invalidate_atime(data->header->inode);
 }
 
 static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_read_data *data)
 {
-	struct nfs_server *server = NFS_SERVER(data->inode);
+	struct nfs_server *server = NFS_SERVER(data->header->inode);
 
 	if (nfs4_async_handle_error(task, server, data->args.context->state) == -EAGAIN) {
 		rpc_restart_call_prepare(task);
@@ -3376,7 +3376,7 @@ static void nfs4_proc_read_setup(struct nfs_read_data *data, struct rpc_message
 
 static void nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
 {
-	if (nfs4_setup_sequence(NFS_SERVER(data->inode),
+	if (nfs4_setup_sequence(NFS_SERVER(data->header->inode),
 				&data->args.seq_args,
 				&data->res.seq_res,
 				task))
@@ -3387,22 +3387,25 @@ static void nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_da
 /* Reset the the nfs_read_data to send the read to the MDS. */
 void nfs4_reset_read(struct rpc_task *task, struct nfs_read_data *data)
 {
+	struct nfs_pgio_header *hdr = data->header;
+	struct inode *inode = hdr->inode;
+
 	dprintk("%s Reset task for i/o through\n", __func__);
-	put_lseg(data->lseg);
-	data->lseg = NULL;
+	put_lseg(hdr->lseg);
+	hdr->lseg = NULL;
+	data->ds_clp = NULL;
 	/* offsets will differ in the dense stripe case */
 	data->args.offset = data->mds_offset;
-	data->ds_clp = NULL;
-	data->args.fh     = NFS_FH(data->inode);
+	data->args.fh     = NFS_FH(inode);
 	data->read_done_cb = nfs4_read_done_cb;
-	task->tk_ops = data->mds_ops;
-	rpc_task_reset_client(task, NFS_CLIENT(data->inode));
+	task->tk_ops = hdr->mds_ops;
+	rpc_task_reset_client(task, NFS_CLIENT(inode));
 }
 EXPORT_SYMBOL_GPL(nfs4_reset_read);
 
 static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_write_data *data)
 {
-	struct inode *inode = data->inode;
+	struct inode *inode = data->header->inode;
 	
 	if (nfs4_async_handle_error(task, NFS_SERVER(inode), data->args.context->state) == -EAGAIN) {
 		rpc_restart_call_prepare(task);
@@ -3426,25 +3429,28 @@ static int nfs4_write_done(struct rpc_task *task, struct nfs_write_data *data)
 /* Reset the the nfs_write_data to send the write to the MDS. */
 void nfs4_reset_write(struct rpc_task *task, struct nfs_write_data *data)
 {
+	struct nfs_pgio_header *hdr = data->header;
+	struct inode *inode = hdr->inode;
+
 	dprintk("%s Reset task for i/o through\n", __func__);
-	put_lseg(data->lseg);
-	data->lseg          = NULL;
-	data->ds_clp        = NULL;
+	put_lseg(hdr->lseg);
+	hdr->lseg        = NULL;
+	data->ds_clp     = NULL;
 	data->write_done_cb = nfs4_write_done_cb;
-	data->args.fh       = NFS_FH(data->inode);
+	data->args.fh       = NFS_FH(inode);
 	data->args.bitmask  = data->res.server->cache_consistency_bitmask;
 	data->args.offset   = data->mds_offset;
 	data->res.fattr     = &data->fattr;
-	task->tk_ops        = data->mds_ops;
-	rpc_task_reset_client(task, NFS_CLIENT(data->inode));
+	task->tk_ops        = hdr->mds_ops;
+	rpc_task_reset_client(task, NFS_CLIENT(inode));
 }
 EXPORT_SYMBOL_GPL(nfs4_reset_write);
 
 static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_message *msg)
 {
-	struct nfs_server *server = NFS_SERVER(data->inode);
+	struct nfs_server *server = NFS_SERVER(data->header->inode);
 
-	if (data->lseg) {
+	if (data->header->lseg) {
 		data->args.bitmask = NULL;
 		data->res.fattr = NULL;
 	} else
@@ -3460,7 +3466,7 @@ static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_messag
 
 static void nfs4_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
 {
-	if (nfs4_setup_sequence(NFS_SERVER(data->inode),
+	if (nfs4_setup_sequence(NFS_SERVER(data->header->inode),
 				&data->args.seq_args,
 				&data->res.seq_res,
 				task))
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index 4bff4a3dab4..fbf4874ec25 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -440,11 +440,12 @@ static void _read_done(struct ore_io_state *ios, void *private)
 
 int objio_read_pagelist(struct nfs_read_data *rdata)
 {
+	struct nfs_pgio_header *hdr = rdata->header;
 	struct objio_state *objios;
 	int ret;
 
-	ret = objio_alloc_io_state(NFS_I(rdata->inode)->layout, true,
-			rdata->lseg, rdata->args.pages, rdata->args.pgbase,
+	ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, true,
+			hdr->lseg, rdata->args.pages, rdata->args.pgbase,
 			rdata->args.offset, rdata->args.count, rdata,
 			GFP_KERNEL, &objios);
 	if (unlikely(ret))
@@ -483,12 +484,12 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
 {
 	struct objio_state *objios = priv;
 	struct nfs_write_data *wdata = objios->oir.rpcdata;
+	struct address_space *mapping = wdata->header->inode->i_mapping;
 	pgoff_t index = offset / PAGE_SIZE;
-	struct page *page = find_get_page(wdata->inode->i_mapping, index);
+	struct page *page = find_get_page(mapping, index);
 
 	if (!page) {
-		page = find_or_create_page(wdata->inode->i_mapping,
-						index, GFP_NOFS);
+		page = find_or_create_page(mapping, index, GFP_NOFS);
 		if (unlikely(!page)) {
 			dprintk("%s: grab_cache_page Failed index=0x%lx\n",
 				__func__, index);
@@ -518,11 +519,12 @@ static const struct _ore_r4w_op _r4w_op = {
 
 int objio_write_pagelist(struct nfs_write_data *wdata, int how)
 {
+	struct nfs_pgio_header *hdr = wdata->header;
 	struct objio_state *objios;
 	int ret;
 
-	ret = objio_alloc_io_state(NFS_I(wdata->inode)->layout, false,
-			wdata->lseg, wdata->args.pages, wdata->args.pgbase,
+	ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, false,
+			hdr->lseg, wdata->args.pages, wdata->args.pgbase,
 			wdata->args.offset, wdata->args.count, wdata, GFP_NOFS,
 			&objios);
 	if (unlikely(ret))
diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c
index 595c5fc21a1..87461354530 100644
--- a/fs/nfs/objlayout/objlayout.c
+++ b/fs/nfs/objlayout/objlayout.c
@@ -258,7 +258,7 @@ objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
 	if (status >= 0)
 		rdata->res.count = status;
 	else
-		rdata->pnfs_error = status;
+		rdata->header->pnfs_error = status;
 	objlayout_iodone(oir);
 	/* must not use oir after this point */
 
@@ -279,12 +279,14 @@ objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
 enum pnfs_try_status
 objlayout_read_pagelist(struct nfs_read_data *rdata)
 {
+	struct nfs_pgio_header *hdr = rdata->header;
+	struct inode *inode = hdr->inode;
 	loff_t offset = rdata->args.offset;
 	size_t count = rdata->args.count;
 	int err;
 	loff_t eof;
 
-	eof = i_size_read(rdata->inode);
+	eof = i_size_read(inode);
 	if (unlikely(offset + count > eof)) {
 		if (offset >= eof) {
 			err = 0;
@@ -297,17 +299,17 @@ objlayout_read_pagelist(struct nfs_read_data *rdata)
 	}
 
 	rdata->res.eof = (offset + count) >= eof;
-	_fix_verify_io_params(rdata->lseg, &rdata->args.pages,
+	_fix_verify_io_params(hdr->lseg, &rdata->args.pages,
 			      &rdata->args.pgbase,
 			      rdata->args.offset, rdata->args.count);
 
 	dprintk("%s: inode(%lx) offset 0x%llx count 0x%Zx eof=%d\n",
-		__func__, rdata->inode->i_ino, offset, count, rdata->res.eof);
+		__func__, inode->i_ino, offset, count, rdata->res.eof);
 
 	err = objio_read_pagelist(rdata);
  out:
 	if (unlikely(err)) {
-		rdata->pnfs_error = err;
+		hdr->pnfs_error = err;
 		dprintk("%s: Returned Error %d\n", __func__, err);
 		return PNFS_NOT_ATTEMPTED;
 	}
@@ -340,7 +342,7 @@ objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
 		wdata->res.count = status;
 		wdata->verf.committed = oir->committed;
 	} else {
-		wdata->pnfs_error = status;
+		wdata->header->pnfs_error = status;
 	}
 	objlayout_iodone(oir);
 	/* must not use oir after this point */
@@ -363,15 +365,16 @@ enum pnfs_try_status
 objlayout_write_pagelist(struct nfs_write_data *wdata,
 			 int how)
 {
+	struct nfs_pgio_header *hdr = wdata->header;
 	int err;
 
-	_fix_verify_io_params(wdata->lseg, &wdata->args.pages,
+	_fix_verify_io_params(hdr->lseg, &wdata->args.pages,
 			      &wdata->args.pgbase,