Adding upstream version 4.19.249.upstream/4.19.249

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

4 files changed, 1632 insertions, 0 deletions

diff --git a/fs/nfs/filelayout/Makefile b/fs/nfs/filelayout/Makefile
new file mode 100644
index 000000000..8516cdffb
--- /dev/null
+++ b/fs/nfs/filelayout/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the pNFS Files Layout Driver kernel module
+#
+obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o
+nfs_layout_nfsv41_files-y := filelayout.o filelayoutdev.o
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
new file mode 100644
index 000000000..e8e825497
--- /dev/null
+++ b/fs/nfs/filelayout/filelayout.c
@@ -0,0 +1,1204 @@
+/*
+ *  Module for the pnfs nfs4 file layout driver.
+ *  Defines all I/O and Policy interface operations, plus code
+ *  to register itself with the pNFS client.
+ *
+ *  Copyright (c) 2002
+ *  The Regents of the University of Michigan
+ *  All Rights Reserved
+ *
+ *  Dean Hildebrand <dhildebz@umich.edu>
+ *
+ *  Permission is granted to use, copy, create derivative works, and
+ *  redistribute this software and such derivative works for any purpose,
+ *  so long as the name of the University of Michigan is not used in
+ *  any advertising or publicity pertaining to the use or distribution
+ *  of this software without specific, written prior authorization. If
+ *  the above copyright notice or any other identification of the
+ *  University of Michigan is included in any copy of any portion of
+ *  this software, then the disclaimer below must also be included.
+ *
+ *  This software is provided as is, without representation or warranty
+ *  of any kind either express or implied, including without limitation
+ *  the implied warranties of merchantability, fitness for a particular
+ *  purpose, or noninfringement.  The Regents of the University of
+ *  Michigan shall not be liable for any damages, including special,
+ *  indirect, incidental, or consequential damages, with respect to any
+ *  claim arising out of or in connection with the use of the software,
+ *  even if it has been or is hereafter advised of the possibility of
+ *  such damages.
+ */
+
+#include <linux/nfs_fs.h>
+#include <linux/nfs_page.h>
+#include <linux/module.h>
+#include <linux/backing-dev.h>
+
+#include <linux/sunrpc/metrics.h>
+
+#include "../nfs4session.h"
+#include "../internal.h"
+#include "../delegation.h"
+#include "filelayout.h"
+#include "../nfs4trace.h"
+
+#define NFSDBG_FACILITY         NFSDBG_PNFS_LD
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Dean Hildebrand <dhildebz@umich.edu>");
+MODULE_DESCRIPTION("The NFSv4 file layout driver");
+
+#define FILELAYOUT_POLL_RETRY_MAX     (15*HZ)
+
+static loff_t
+filelayout_get_dense_offset(struct nfs4_filelayout_segment *flseg,
+			    loff_t offset)
+{
+	u32 stripe_width = flseg->stripe_unit * flseg->dsaddr->stripe_count;
+	u64 stripe_no;
+	u32 rem;
+
+	offset -= flseg->pattern_offset;
+	stripe_no = div_u64(offset, stripe_width);
+	div_u64_rem(offset, flseg->stripe_unit, &rem);
+
+	return stripe_no * flseg->stripe_unit + rem;
+}
+
+/* This function is used by the layout driver to calculate the
+ * offset of the file on the dserver based on whether the
+ * layout type is STRIPE_DENSE or STRIPE_SPARSE
+ */
+static loff_t
+filelayout_get_dserver_offset(struct pnfs_layout_segment *lseg, loff_t offset)
+{
+	struct nfs4_filelayout_segment *flseg = FILELAYOUT_LSEG(lseg);
+
+	switch (flseg->stripe_type) {
+	case STRIPE_SPARSE:
+		return offset;
+
+	case STRIPE_DENSE:
+		return filelayout_get_dense_offset(flseg, offset);
+	}
+
+	BUG();
+}
+
+static void filelayout_reset_write(struct nfs_pgio_header *hdr)
+{
+	struct rpc_task *task = &hdr->task;
+
+	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+		dprintk("%s Reset task %5u for i/o through MDS "
+			"(req %s/%llu, %u bytes @ offset %llu)\n", __func__,
+			hdr->task.tk_pid,
+			hdr->inode->i_sb->s_id,
+			(unsigned long long)NFS_FILEID(hdr->inode),
+			hdr->args.count,
+			(unsigned long long)hdr->args.offset);
+
+		task->tk_status = pnfs_write_done_resend_to_mds(hdr);
+	}
+}
+
+static void filelayout_reset_read(struct nfs_pgio_header *hdr)
+{
+	struct rpc_task *task = &hdr->task;
+
+	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+		dprintk("%s Reset task %5u for i/o through MDS "
+			"(req %s/%llu, %u bytes @ offset %llu)\n", __func__,
+			hdr->task.tk_pid,
+			hdr->inode->i_sb->s_id,
+			(unsigned long long)NFS_FILEID(hdr->inode),
+			hdr->args.count,
+			(unsigned long long)hdr->args.offset);
+
+		task->tk_status = pnfs_read_done_resend_to_mds(hdr);
+	}
+}
+
+static int filelayout_async_handle_error(struct rpc_task *task,
+					 struct nfs4_state *state,
+					 struct nfs_client *clp,
+					 struct pnfs_layout_segment *lseg)
+{
+	struct pnfs_layout_hdr *lo = lseg->pls_layout;
+	struct inode *inode = lo->plh_inode;
+	struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
+	struct nfs4_slot_table *tbl = &clp->cl_session->fc_slot_table;
+
+	if (task->tk_status >= 0)
+		return 0;
+
+	switch (task->tk_status) {
+	/* DS session errors */
+	case -NFS4ERR_BADSESSION:
+	case -NFS4ERR_BADSLOT:
+	case -NFS4ERR_BAD_HIGH_SLOT:
+	case -NFS4ERR_DEADSESSION:
+	case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+	case -NFS4ERR_SEQ_FALSE_RETRY:
+	case -NFS4ERR_SEQ_MISORDERED:
+		dprintk("%s ERROR %d, Reset session. Exchangeid "
+			"flags 0x%x\n", __func__, task->tk_status,
+			clp->cl_exchange_flags);
+		nfs4_schedule_session_recovery(clp->cl_session, task->tk_status);
+		break;
+	case -NFS4ERR_DELAY:
+	case -NFS4ERR_GRACE:
+		rpc_delay(task, FILELAYOUT_POLL_RETRY_MAX);
+		break;
+	case -NFS4ERR_RETRY_UNCACHED_REP:
+		break;
+	/* Invalidate Layout errors */
+	case -NFS4ERR_ACCESS:
+	case -NFS4ERR_PNFS_NO_LAYOUT:
+	case -ESTALE:           /* mapped NFS4ERR_STALE */
+	case -EBADHANDLE:       /* mapped NFS4ERR_BADHANDLE */
+	case -EISDIR:           /* mapped NFS4ERR_ISDIR */
+	case -NFS4ERR_FHEXPIRED:
+	case -NFS4ERR_WRONG_TYPE:
+		dprintk("%s Invalid layout error %d\n", __func__,
+			task->tk_status);
+		/*
+		 * Destroy layout so new i/o will get a new layout.
+		 * Layout will not be destroyed until all current lseg
+		 * references are put. Mark layout as invalid to resend failed
+		 * i/o and all i/o waiting on the slot table to the MDS until
+		 * layout is destroyed and a new valid layout is obtained.
+		 */
+		pnfs_destroy_layout(NFS_I(inode));
+		rpc_wake_up(&tbl->slot_tbl_waitq);
+		goto reset;
+	/* RPC connection errors */
+	case -ECONNREFUSED:
+	case -EHOSTDOWN:
+	case -EHOSTUNREACH:
+	case -ENETUNREACH:
+	case -EIO:
+	case -ETIMEDOUT:
+	case -EPIPE:
+		dprintk("%s DS connection error %d\n", __func__,
+			task->tk_status);
+		nfs4_mark_deviceid_unavailable(devid);
+		pnfs_error_mark_layout_for_return(inode, lseg);
+		pnfs_set_lo_fail(lseg);
+		rpc_wake_up(&tbl->slot_tbl_waitq);
+		/* fall through */
+	default:
+reset:
+		dprintk("%s Retry through MDS. Error %d\n", __func__,
+			task->tk_status);
+		return -NFS4ERR_RESET_TO_MDS;
+	}
+	task->tk_status = 0;
+	return -EAGAIN;
+}
+
+/* NFS_PROTO call done callback routines */
+
+static int filelayout_read_done_cb(struct rpc_task *task,
+				struct nfs_pgio_header *hdr)
+{
+	int err;
+
+	trace_nfs4_pnfs_read(hdr, task->tk_status);
+	err = filelayout_async_handle_error(task, hdr->args.context->state,
+					    hdr->ds_clp, hdr->lseg);
+
+	switch (err) {
+	case -NFS4ERR_RESET_TO_MDS:
+		filelayout_reset_read(hdr);
+		return task->tk_status;
+	case -EAGAIN:
+		rpc_restart_call_prepare(task);
+		return -EAGAIN;
+	}
+
+	return 0;
+}
+
+/*
+ * We reference the rpc_cred of the first WRITE that triggers the need for
+ * a LAYOUTCOMMIT, and use it to send the layoutcommit compound.
+ * rfc5661 is not clear about which credential should be used.
+ */
+static void
+filelayout_set_layoutcommit(struct nfs_pgio_header *hdr)
+{
+	loff_t end_offs = 0;
+
+	if (FILELAYOUT_LSEG(hdr->lseg)->commit_through_mds ||
+	    hdr->res.verf->committed == NFS_FILE_SYNC)
+		return;
+	if (hdr->res.verf->committed == NFS_DATA_SYNC)
+		end_offs = hdr->mds_offset + (loff_t)hdr->res.count;
+
+	/* Note: if the write is unstable, don't set end_offs until commit */
+	pnfs_set_layoutcommit(hdr->inode, hdr->lseg, end_offs);
+	dprintk("%s inode %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino,
+		(unsigned long) NFS_I(hdr->inode)->layout->plh_lwb);
+}
+
+bool
+filelayout_test_devid_unavailable(struct nfs4_deviceid_node *node)
+{
+	return filelayout_test_devid_invalid(node) ||
+		nfs4_test_deviceid_unavailable(node);
+}
+
+static bool
+filelayout_reset_to_mds(struct pnfs_layout_segment *lseg)
+{
+	struct nfs4_deviceid_node *node = FILELAYOUT_DEVID_NODE(lseg);
+
+	return filelayout_test_devid_unavailable(node);
+}
+
+/*
+ * Call ops for the async read/write cases
+ * In the case of dense layouts, the offset needs to be reset to its
+ * original value.
+ */
+static void filelayout_read_prepare(struct rpc_task *task, void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) {
+		rpc_exit(task, -EIO);
+		return;
+	}
+	if (filelayout_reset_to_mds(hdr->lseg)) {
+		dprintk("%s task %u reset io to MDS\n", __func__, task->tk_pid);
+		filelayout_reset_read(hdr);
+		rpc_exit(task, 0);
+		return;
+	}
+	hdr->pgio_done_cb = filelayout_read_done_cb;
+
+	if (nfs4_setup_sequence(hdr->ds_clp,
+			&hdr->args.seq_args,
+			&hdr->res.seq_res,
+			task))
+		return;
+	if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context,
+			hdr->args.lock_context, FMODE_READ) == -EIO)
+		rpc_exit(task, -EIO); /* lost lock, terminate I/O */
+}
+
+static void filelayout_read_call_done(struct rpc_task *task, void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status);
+
+	if (test_bit(NFS_IOHDR_REDO, &hdr->flags) &&
+	    task->tk_status == 0) {
+		nfs41_sequence_done(task, &hdr->res.seq_res);
+		return;
+	}
+
+	/* Note this may cause RPC to be resent */
+	hdr->mds_ops->rpc_call_done(task, data);
+}
+
+static void filelayout_read_count_stats(struct rpc_task *task, void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	rpc_count_iostats(task, NFS_SERVER(hdr->inode)->client->cl_metrics);
+}
+
+static int filelayout_write_done_cb(struct rpc_task *task,
+				struct nfs_pgio_header *hdr)
+{
+	int err;
+
+	trace_nfs4_pnfs_write(hdr, task->tk_status);
+	err = filelayout_async_handle_error(task, hdr->args.context->state,
+					    hdr->ds_clp, hdr->lseg);
+
+	switch (err) {
+	case -NFS4ERR_RESET_TO_MDS:
+		filelayout_reset_write(hdr);
+		return task->tk_status;
+	case -EAGAIN:
+		rpc_restart_call_prepare(task);
+		return -EAGAIN;
+	}
+
+	filelayout_set_layoutcommit(hdr);
+
+	/* zero out the fattr */
+	hdr->fattr.valid = 0;
+	if (task->tk_status >= 0)
+		nfs_writeback_update_inode(hdr);
+
+	return 0;
+}
+
+static int filelayout_commit_done_cb(struct rpc_task *task,
+				     struct nfs_commit_data *data)
+{
+	int err;
+
+	trace_nfs4_pnfs_commit_ds(data, task->tk_status);
+	err = filelayout_async_handle_error(task, NULL, data->ds_clp,
+					    data->lseg);
+
+	switch (err) {
+	case -NFS4ERR_RESET_TO_MDS:
+		pnfs_generic_prepare_to_resend_writes(data);
+		return -EAGAIN;
+	case -EAGAIN:
+		rpc_restart_call_prepare(task);
+		return -EAGAIN;
+	}
+
+	pnfs_set_layoutcommit(data->inode, data->lseg, data->lwb);
+
+	return 0;
+}
+
+static void filelayout_write_prepare(struct rpc_task *task, void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) {
+		rpc_exit(task, -EIO);
+		return;
+	}
+	if (filelayout_reset_to_mds(hdr->lseg)) {
+		dprintk("%s task %u reset io to MDS\n", __func__, task->tk_pid);
+		filelayout_reset_write(hdr);
+		rpc_exit(task, 0);
+		return;
+	}
+	if (nfs4_setup_sequence(hdr->ds_clp,
+			&hdr->args.seq_args,
+			&hdr->res.seq_res,
+			task))
+		return;
+	if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context,
+			hdr->args.lock_context, FMODE_WRITE) == -EIO)
+		rpc_exit(task, -EIO); /* lost lock, terminate I/O */
+}
+
+static void filelayout_write_call_done(struct rpc_task *task, void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	if (test_bit(NFS_IOHDR_REDO, &hdr->flags) &&
+	    task->tk_status == 0) {
+		nfs41_sequence_done(task, &hdr->res.seq_res);
+		return;
+	}
+
+	/* Note this may cause RPC to be resent */
+	hdr->mds_ops->rpc_call_done(task, data);
+}
+
+static void filelayout_write_count_stats(struct rpc_task *task, void *data)
+{
+	struct nfs_pgio_header *hdr = data;
+
+	rpc_count_iostats(task, NFS_SERVER(hdr->inode)->client->cl_metrics);
+}
+
+static void filelayout_commit_prepare(struct rpc_task *task, void *data)
+{
+	struct nfs_commit_data *wdata = data;
+
+	nfs4_setup_sequence(wdata->ds_clp,
+			&wdata->args.seq_args,
+			&wdata->res.seq_res,
+			task);
+}
+
+static void filelayout_commit_count_stats(struct rpc_task *task, void *data)
+{
+	struct nfs_commit_data *cdata = data;
+
+	rpc_count_iostats(task, NFS_SERVER(cdata->inode)->client->cl_metrics);
+}
+
+static const struct rpc_call_ops filelayout_read_call_ops = {
+	.rpc_call_prepare = filelayout_read_prepare,
+	.rpc_call_done = filelayout_read_call_done,
+	.rpc_count_stats = filelayout_read_count_stats,
+	.rpc_release = pnfs_generic_rw_release,
+};
+
+static const struct rpc_call_ops filelayout_write_call_ops = {
+	.rpc_call_prepare = filelayout_write_prepare,
+	.rpc_call_done = filelayout_write_call_done,
+	.rpc_count_stats = filelayout_write_count_stats,
+	.rpc_release = pnfs_generic_rw_release,
+};
+
+static const struct rpc_call_ops filelayout_commit_call_ops = {
+	.rpc_call_prepare = filelayout_commit_prepare,
+	.rpc_call_done = pnfs_generic_write_commit_done,
+	.rpc_count_stats = filelayout_commit_count_stats,
+	.rpc_release = pnfs_generic_commit_release,
+};
+
+static enum pnfs_try_status
+filelayout_read_pagelist(struct nfs_pgio_header *hdr)
+{
+	struct pnfs_layout_segment *lseg = hdr->lseg;
+	struct nfs4_pnfs_ds *ds;
+	struct rpc_clnt *ds_clnt;
+	loff_t offset = hdr->args.offset;
+	u32 j, idx;
+	struct nfs_fh *fh;
+
+	dprintk("--> %s ino %lu pgbase %u req %zu@%llu\n",
+		__func__, hdr->inode->i_ino,
+		hdr->args.pgbase, (size_t)hdr->args.count, offset);
+
+	/* Retrieve the correct rpc_client for the byte range */
+	j = nfs4_fl_calc_j_index(lseg, offset);
+	idx = nfs4_fl_calc_ds_index(lseg, j);
+	ds = nfs4_fl_prepare_ds(lseg, idx);
+	if (!ds)
+		return PNFS_NOT_ATTEMPTED;
+
+	ds_clnt = nfs4_find_or_create_ds_client(ds->ds_clp, hdr->inode);
+	if (IS_ERR(ds_clnt))
+		return PNFS_NOT_ATTEMPTED;
+
+	dprintk("%s USE DS: %s cl_count %d\n", __func__,
+		ds->ds_remotestr, refcount_read(&ds->ds_clp->cl_count));
+
+	/* No multipath support. Use first DS */
+	refcount_inc(&ds->ds_clp->cl_count);
+	hdr->ds_clp = ds->ds_clp;
+	hdr->ds_commit_idx = idx;
+	fh = nfs4_fl_select_ds_fh(lseg, j);
+	if (fh)
+		hdr->args.fh = fh;
+
+	hdr->args.offset = filelayout_get_dserver_offset(lseg, offset);
+	hdr->mds_offset = offset;
+
+	/* Perform an asynchronous read to ds */
+	nfs_initiate_pgio(ds_clnt, hdr, hdr->cred,
+			  NFS_PROTO(hdr->inode), &filelayout_read_call_ops,
+			  0, RPC_TASK_SOFTCONN);
+	return PNFS_ATTEMPTED;
+}
+
+/* Perform async writes. */
+static enum pnfs_try_status
+filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
+{
+	struct pnfs_layout_segment *lseg = hdr->lseg;
+	struct nfs4_pnfs_ds *ds;
+	struct rpc_clnt *ds_clnt;
+	loff_t offset = hdr->args.offset;
+	u32 j, idx;
+	struct nfs_fh *fh;
+
+	/* Retrieve the correct rpc_client for the byte range */
+	j = nfs4_fl_calc_j_index(lseg, offset);
+	idx = nfs4_fl_calc_ds_index(lseg, j);
+	ds = nfs4_fl_prepare_ds(lseg, idx);
+	if (!ds)
+		return PNFS_NOT_ATTEMPTED;
+
+	ds_clnt = nfs4_find_or_create_ds_client(ds->ds_clp, hdr->inode);
+	if (IS_ERR(ds_clnt))
+		return PNFS_NOT_ATTEMPTED;
+
+	dprintk("%s ino %lu sync %d req %zu@%llu DS: %s cl_count %d\n",
+		__func__, hdr->inode->i_ino, sync, (size_t) hdr->args.count,
+		offset, ds->ds_remotestr, refcount_read(&ds->ds_clp->cl_count));
+
+	hdr->pgio_done_cb = filelayout_write_done_cb;
+	refcount_inc(&ds->ds_clp->cl_count);
+	hdr->ds_clp = ds->ds_clp;
+	hdr->ds_commit_idx = idx;
+	fh = nfs4_fl_select_ds_fh(lseg, j);
+	if (fh)
+		hdr->args.fh = fh;
+	hdr->args.offset = filelayout_get_dserver_offset(lseg, offset);
+
+	/* Perform an asynchronous write */
+	nfs_initiate_pgio(ds_clnt, hdr, hdr->cred,
+			  NFS_PROTO(hdr->inode), &filelayout_write_call_ops,
+			  sync, RPC_TASK_SOFTCONN);
+	return PNFS_ATTEMPTED;
+}
+
+static int
+filelayout_check_deviceid(struct pnfs_layout_hdr *lo,
+			  struct nfs4_filelayout_segment *fl,
+			  gfp_t gfp_flags)
+{
+	struct nfs4_deviceid_node *d;
+	struct nfs4_file_layout_dsaddr *dsaddr;
+	int status = -EINVAL;
+
+	/* Is the deviceid already set? If so, we're good. */
+	if (fl->dsaddr != NULL)
+		return 0;
+
+	/* find and reference the deviceid */
+	d = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode), &fl->deviceid,
+			lo->plh_lc_cred, gfp_flags);
+	if (d == NULL)
+		goto out;
+
+	dsaddr = container_of(d, struct nfs4_file_layout_dsaddr, id_node);
+	/* Found deviceid is unavailable */
+	if (filelayout_test_devid_unavailable(&dsaddr->id_node))
+		goto out_put;
+
+	if (fl->first_stripe_index >= dsaddr->stripe_count) {
+		dprintk("%s Bad first_stripe_index %u\n",
+				__func__, fl->first_stripe_index);
+		goto out_put;
+	}
+
+	if ((fl->stripe_type == STRIPE_SPARSE &&
+	    fl->num_fh > 1 && fl->num_fh != dsaddr->ds_num) ||
+	    (fl->stripe_type == STRIPE_DENSE &&
+	    fl->num_fh != dsaddr->stripe_count)) {
+		dprintk("%s num_fh %u not valid for given packing\n",
+			__func__, fl->num_fh);
+		goto out_put;
+	}
+	status = 0;
+
+	/*
+	 * Atomic compare and xchange to ensure we don't scribble
+	 * over a non-NULL pointer.
+	 */
+	if (cmpxchg(&fl->dsaddr, NULL, dsaddr) != NULL)
+		goto out_put;
+out:
+	return status;
+out_put:
+	nfs4_fl_put_deviceid(dsaddr);
+	goto out;
+}
+
+/*
+ * filelayout_check_layout()
+ *
+ * Make sure layout segment parameters are sane WRT the device.
+ * At this point no generic layer initialization of the lseg has occurred,
+ * and nothing has been added to the layout_hdr cache.
+ *
+ */
+static int
+filelayout_check_layout(struct pnfs_layout_hdr *lo,
+			struct nfs4_filelayout_segment *fl,
+			struct nfs4_layoutget_res *lgr,
+			gfp_t gfp_flags)
+{
+	int status = -EINVAL;
+
+	dprintk("--> %s\n", __func__);
+
+	/* FIXME: remove this check when layout segment support is added */
+	if (lgr->range.offset != 0 ||
+	    lgr->range.length != NFS4_MAX_UINT64) {
+		dprintk("%s Only whole file layouts supported. Use MDS i/o\n",
+			__func__);
+		goto out;
+	}
+
+	if (fl->pattern_offset > lgr->range.offset) {
+		dprintk("%s pattern_offset %lld too large\n",
+				__func__, fl->pattern_offset);
+		goto out;
+	}
+
+	if (!fl->stripe_unit) {
+		dprintk("%s Invalid stripe unit (%u)\n",
+			__func__, fl->stripe_unit);
+		goto out;
+	}
+
+	status = 0;
+out:
+	dprintk("--> %s returns %d\n", __func__, status);
+	return status;
+}
+
+static void _filelayout_free_lseg(struct nfs4_filelayout_segment *fl)
+{
+	int i;
+
+	if (fl->fh_array) {
+		for (i = 0; i < fl->num_fh; i++) {
+			if (!fl->fh_array[i])
+				break;
+			kfree(fl->fh_array[i]);
+		}
+		kfree(fl->fh_array);
+	}
+	kfree(fl);
+}
+
+static int
+filelayout_decode_layout(struct pnfs_layout_hdr *flo,
+			 struct nfs4_filelayout_segment *fl,
+			 struct nfs4_layoutget_res *lgr,
+			 gfp_t gfp_flags)
+{
+	struct xdr_stream stream;
+	struct xdr_buf buf;
+	struct page *scratch;
+	__be32 *p;
+	uint32_t nfl_util;
+	int i;
+
+	dprintk("%s: set_layout_map Begin\n", __func__);
+
+	scratch = alloc_page(gfp_flags);
+	if (!scratch)
+		return -ENOMEM;
+
+	xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages, lgr->layoutp->len);
+	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
+
+	/* 20 = ufl_util (4), first_stripe_index (4), pattern_offset (8),
+	 * num_fh (4) */
+	p = xdr_inline_decode(&stream, NFS4_DEVICEID4_SIZE + 20);
+	if (unlikely(!p))
+		goto out_err;
+
+	memcpy(&fl->deviceid, p, sizeof(fl->deviceid));
+	p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE);
+	nfs4_print_deviceid(&fl->deviceid);
+
+	nfl_util = be32_to_cpup(p++);
+	if (nfl_util & NFL4_UFLG_COMMIT_THRU_MDS)
+		fl->commit_through_mds = 1;
+	if (nfl_util & NFL4_UFLG_DENSE)
+		fl->stripe_type = STRIPE_DENSE;
+	else
+		fl->stripe_type = STRIPE_SPARSE;
+	fl->stripe_unit = nfl_util & ~NFL4_UFLG_MASK;
+
+	fl->first_stripe_index = be32_to_cpup(p++);
+	p = xdr_decode_hyper(p, &fl->pattern_offset);
+	fl->num_fh = be32_to_cpup(p++);
+
+	dprintk("%s: nfl_util 0x%X num_fh %u fsi %u po %llu\n",
+		__func__, nfl_util, fl->num_fh, fl->first_stripe_index,
+		fl->pattern_offset);
+
+	/* Note that a zero value for num_fh is legal for STRIPE_SPARSE.
+	 * Futher checking is done in filelayout_check_layout */
+	if (fl->num_fh >
+	    max(NFS4_PNFS_MAX_STRIPE_CNT, NFS4_PNFS_MAX_MULTI_CNT))
+		goto out_err;
+
+	if (fl->num_fh > 0) {
+		fl->fh_array = kcalloc(fl->num_fh, sizeof(fl->fh_array[0]),
+				       gfp_flags);
+		if (!fl->fh_array)
+			goto out_err;
+	}
+
+	for (i = 0; i < fl->num_fh; i++) {
+		/* Do we want to use a mempool here? */
+		fl->fh_array[i] = kmalloc(sizeof(struct nfs_fh), gfp_flags);
+		if (!fl->fh_array[i])
+			goto out_err;
+
+		p = xdr_inline_decode(&stream, 4);
+		if (unlikely(!p))
+			goto out_err;
+		fl->fh_array[i]->size = be32_to_cpup(p++);
+		if (fl->fh_array[i]->size > NFS_MAXFHSIZE) {
+			printk(KERN_ERR "NFS: Too big fh %d received %d\n",
+			       i, fl->fh_array[i]->size);
+			goto out_err;
+		}
+
+		p = xdr_inline_decode(&stream, fl->fh_array[i]->size);
+		if (unlikely(!p))
+			goto out_err;
+		memcpy(fl->fh_array[i]->data, p, fl->fh_array[i]->size);
+		dprintk("DEBUG: %s: fh len %d\n", __func__,
+			fl->fh_array[i]->size);
+	}
+
+	__free_page(scratch);
+	return 0;
+
+out_err:
+	__free_page(scratch);
+	return -EIO;
+}
+
+static void
+filelayout_free_lseg(struct pnfs_layout_segment *lseg)
+{
+	struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg);
+
+	dprintk("--> %s\n", __func__);
+	if (fl->dsaddr != NULL)
+		nfs4_fl_put_deviceid(fl->dsaddr);
+	/* This assumes a single RW lseg */
+	if (lseg->pls_range.iomode == IOMODE_RW) {
+		struct nfs4_filelayout *flo;
+
+		flo = FILELAYOUT_FROM_HDR(lseg->pls_layout);
+		flo->commit_info.nbuckets = 0;
+		kfree(flo->commit_info.buckets);
+		flo->commit_info.buckets = NULL;
+	}
+	_filelayout_free_lseg(fl);
+}
+
+static int
+filelayout_alloc_commit_info(struct pnfs_layout_segment *lseg,
+			     struct nfs_commit_info *cinfo,
+			     gfp_t gfp_flags)
+{
+	struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg);
+	struct pnfs_commit_bucket *buckets;
+	int size, i;
+
+	if (fl->commit_through_mds)
+		return 0;
+
+	size = (fl->stripe_type == STRIPE_SPARSE) ?
+		fl->dsaddr->ds_num : fl->dsaddr->stripe_count;
+
+	if (cinfo->ds->nbuckets >= size) {
+		/* This assumes there is only one IOMODE_RW lseg.  What
+		 * we really want to do is have a layout_hdr level
+		 * dictionary of <multipath_list4, fh> keys, each
+		 * associated with a struct list_head, populated by calls
+		 * to filelayout_write_pagelist().
+		 * */
+		return 0;
+	}
+
+	buckets = kcalloc(size, sizeof(struct pnfs_commit_bucket),
+			  gfp_flags);
+	if (!buckets)
+		return -ENOMEM;
+	for (i = 0; i < size; i++) {
+		INIT_LIST_HEAD(&buckets[i].written);
+		INIT_LIST_HEAD(&buckets[i].committing);
+		/* mark direct verifier as unset */
+		buckets[i].direct_verf.committed = NFS_INVALID_STABLE_HOW;
+	}
+
+	spin_lock(&cinfo->inode->i_lock);
+	if (cinfo->ds->nbuckets >= size)
+		goto out;
+	for (i = 0; i < cinfo->ds->nbuckets; i++) {
+		list_splice(&cinfo->ds->buckets[i].written,
+			    &buckets[i].written);
+		list_splice(&cinfo->ds->buckets[i].committing,
+			    &buckets[i].committing);
+		buckets[i].direct_verf.committed =
+			cinfo->ds->buckets[i].direct_verf.committed;
+		buckets[i].wlseg = cinfo->ds->buckets[i].wlseg;
+		buckets[i].clseg = cinfo->ds->buckets[i].clseg;
+	}
+	swap(cinfo->ds->buckets, buckets);
+	cinfo->ds->nbuckets = size;
+out:
+	spin_unlock(&cinfo->inode->i_lock);
+	kfree(buckets);
+	return 0;
+}
+
+static struct pnfs_layout_segment *
+filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
+		      struct nfs4_layoutget_res *lgr,
+		      gfp_t gfp_flags)
+{
+	struct nfs4_filelayout_segment *fl;
+	int rc;
+
+	dprintk("--> %s\n", __func__);
+	fl = kzalloc(sizeof(*fl), gfp_flags);
+	if (!fl)
+		return NULL;
+
+	rc = filelayout_decode_layout(layoutid, fl, lgr, gfp_flags);
+	if (rc != 0 || filelayout_check_layout(layoutid, fl, lgr, gfp_flags)) {
+		_filelayout_free_lseg(fl);
+		return NULL;
+	}
+	return &fl->generic_hdr;
+}
+
+/*
+ * filelayout_pg_test(). Called by nfs_can_coalesce_requests()
+ *
+ * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
+ * of bytes (maximum @req->wb_bytes) that can be coalesced.
+ */
+static size_t
+filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
+		   struct nfs_page *req)
+{
+	unsigned int size;
+	u64 p_stripe, r_stripe;
+	u32 stripe_offset;
+	u64 segment_offset = pgio->pg_lseg->pls_range.offset;
+	u32 stripe_unit = FILELAYOUT_LSEG(pgio->pg_lseg)->stripe_unit;
+
+	/* calls nfs_generic_pg_test */
+	size = pnfs_generic_pg_test(pgio, prev, req);
+	if (!size)
+		return 0;
+
+	/* see if req and prev are in the same stripe */
+	if (prev) {
+		p_stripe = (u64)req_offset(prev) - segment_offset;
+		r_stripe = (u64)req_offset(req) - segment_offset;
+		do_div(p_stripe, stripe_unit);
+		do_div(r_stripe, stripe_unit);
+
+		if (p_stripe != r_stripe)
+			return 0;
+	}
+
+	/* calculate remaining bytes in the current stripe */
+	div_u64_rem((u64)req_offset(req) - segment_offset,
+			stripe_unit,
+			&stripe_offset);
+	WARN_ON_ONCE(stripe_offset > stripe_unit);
+	if (stripe_offset >= stripe_unit)
+		return 0;
+	return min(stripe_unit - (unsigned int)stripe_offset, size);
+}
+
+static struct pnfs_layout_segment *
+fl_pnfs_update_layout(struct inode *ino,
+		      struct nfs_open_context *ctx,
+		      loff_t pos,
+		      u64 count,
+		      enum pnfs_iomode iomode,
+		      bool strict_iomode,
+		      gfp_t gfp_flags)
+{
+	struct pnfs_layout_segment *lseg = NULL;
+	struct pnfs_layout_hdr *lo;
+	struct nfs4_filelayout_segment *fl;
+	int status;
+
+	lseg = pnfs_update_layout(ino, ctx, pos, count, iomode, strict_iomode,
+				  gfp_flags);
+	if (IS_ERR_OR_NULL(lseg))
+		goto out;
+
+	lo = NFS_I(ino)->layout;
+	fl = FILELAYOUT_LSEG(lseg);
+
+	status = filelayout_check_deviceid(lo, fl, gfp_flags);
+	if (status) {
+		pnfs_put_lseg(lseg);
+		lseg = NULL;
+	}
+out:
+	return lseg;
+}
+
+static void
+filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
+			struct nfs_page *req)
+{
+	pnfs_generic_pg_check_layout(pgio);
+	if (!pgio->pg_lseg) {
+		pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode,
+						      req->wb_context,
+						      0,
+						      NFS4_MAX_UINT64,
+						      IOMODE_READ,
+						      false,
+						      GFP_KERNEL);
+		if (IS_ERR(pgio->pg_lseg)) {
+			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
+			pgio->pg_lseg = NULL;
+			return;
+		}
+	}
+	/* If no lseg, fall back to read through mds */
+	if (pgio->pg_lseg == NULL)
+		nfs_pageio_reset_read_mds(pgio);
+}
+
+static void
+filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
+			 struct nfs_page *req)
+{
+	struct nfs_commit_info cinfo;
+	int status;
+
+	pnfs_generic_pg_check_layout(pgio);
+	if (!pgio->pg_lseg) {
+		pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode,
+						      req->wb_context,
+						      0,
+						      NFS4_MAX_UINT64,
+						      IOMODE_RW,
+						      false,
+						      GFP_NOFS);
+		if (IS_ERR(pgio->pg_lseg)) {
+			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
+			pgio->pg_lseg = NULL;
+			return;
+		}
+	}
+
+	/* If no lseg, fall back to write through mds */
+	if (pgio->pg_lseg == NULL)
+		goto out_mds;
+	nfs_init_cinfo(&cinfo, pgio->pg_inode, pgio->pg_dreq);
+	status = filelayout_alloc_commit_info(pgio->pg_lseg, &cinfo, GFP_NOFS);
+	if (status < 0) {
+		pnfs_put_lseg(pgio->pg_lseg);
+		pgio->pg_lseg = NULL;
+		goto out_mds;
+	}
+	return;
+out_mds:
+	nfs_pageio_reset_write_mds(pgio);
+}
+
+static const struct nfs_pageio_ops filelayout_pg_read_ops = {
+	.pg_init = filelayout_pg_init_read,
+	.pg_test = filelayout_pg_test,
+	.pg_doio = pnfs_generic_pg_readpages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
+};
+
+static const struct nfs_pageio_ops filelayout_pg_write_ops = {
+	.pg_init = filelayout_pg_init_write,
+	.pg_test = filelayout_pg_test,
+	.pg_doio = pnfs_generic_pg_writepages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
+};
+
+static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j)
+{
+	if (fl->stripe_type == STRIPE_SPARSE)
+		return nfs4_fl_calc_ds_index(&fl->generic_hdr, j);
+	else
+		return j;
+}
+
+static void
+filelayout_mark_request_commit(struct nfs_page *req,
+			       struct pnfs_layout_segment *lseg,
+			       struct nfs_commit_info *cinfo,
+			       u32 ds_commit_idx)
+
+{
+	struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg);
+	u32 i, j;
+
+	if (fl->commit_through_mds) {
+		nfs_request_add_commit_list(req, cinfo);
+	} else {
+		/* Note that we are calling nfs4_fl_calc_j_index on each page
+		 * that ends up being committed to a data server.  An attractive
+		 * alternative is to add a field to nfs_write_data and nfs_page
+		 * to store the value calculated in filelayout_write_pagelist
+		 * and just use that here.
+		 */
+		j = nfs4_fl_calc_j_index(lseg, req_offset(req));
+		i = select_bucket_index(fl, j);
+		pnfs_layout_mark_request_commit(req, lseg, cinfo, i);
+	}
+}
+
+static u32 calc_ds_index_from_commit(struct pnfs_layout_segment *lseg, u32 i)
+{
+	struct nfs4_filelayout_segment *flseg = FILELAYOUT_LSEG(lseg);
+
+	if (flseg->stripe_type == STRIPE_SPARSE)
+		return i;
+	else
+		return nfs4_fl_calc_ds_index(lseg, i);
+}
+
+static struct nfs_fh *
+select_ds_fh_from_commit(struct pnfs_layout_segment *lseg, u32 i)
+{
+	struct nfs4_filelayout_segment *flseg = FILELAYOUT_LSEG(lseg);
+
+	if (flseg->stripe_type == STRIPE_SPARSE) {
+		if (flseg->num_fh == 1)
+			i = 0;
+		else if (flseg->num_fh == 0)
+			/* Use the MDS OPEN fh set in nfs_read_rpcsetup */
+			return NULL;
+	}
+	return flseg->fh_array[i];
+}
+
+static int filelayout_initiate_commit(struct nfs_commit_data *data, int how)
+{
+	struct pnfs_layout_segment *lseg = data->lseg;
+	struct nfs4_pnfs_ds *ds;
+	struct rpc_clnt *ds_clnt;
+	u32 idx;
+	struct nfs_fh *fh;
+
+	idx = calc_ds_index_from_commit(lseg, data->ds_commit_index);
+	ds = nfs4_fl_prepare_ds(lseg, idx);
+	if (!ds)
+		goto out_err;
+
+	ds_clnt = nfs4_find_or_create_ds_client(ds->ds_clp, data->inode);
+	if (IS_ERR(ds_clnt))
+		goto out_err;
+
+	dprintk("%s ino %lu, how %d cl_count %d\n", __func__,
+		data->inode->i_ino, how, refcount_read(&ds->ds_clp->cl_count));
+	data->commit_done_cb = filelayout_commit_done_cb;
+	refcount_inc(&ds->ds_clp->cl_count);
+	data->ds_clp = ds->ds_clp;
+	fh = select_ds_fh_from_commit(lseg, data->ds_commit_index);
+	if (fh)
+		data->args.fh = fh;
+	return nfs_initiate_commit(ds_clnt, data, NFS_PROTO(data->inode),
+				   &filelayout_commit_call_ops, how,
+				   RPC_TASK_SOFTCONN);
+out_err:
+	pnfs_generic_prepare_to_resend_writes(data);
+	pnfs_generic_commit_release(data);
+	return -EAGAIN;
+}
+
+/* filelayout_search_commit_reqs - Search lists in @cinfo for the head reqest
+ *				   for @page
+ * @cinfo - commit info for current inode
+ * @page - page to search for matching head request
+ *
+ * Returns a the head request if one is found, otherwise returns NULL.
+ */
+static struct nfs_page *
+filelayout_search_commit_reqs(struct nfs_commit_info *cinfo, struct page *page)
+{
+	struct nfs_page *freq, *t;
+	struct pnfs_commit_bucket *b;
+	int i;
+
+	/* Linearly search the commit lists for each bucket until a matching
+	 * request is found */
+	for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) {
+		list_for_each_entry_safe(freq, t, &b->written, wb_list) {
+			if (freq->wb_page == page)
+				return freq->wb_head;
+		}
+		list_for_each_entry_safe(freq, t, &b->committing, wb_list) {
+			if (freq->wb_page == page)
+				return freq->wb_head;
+		}
+	}
+
+	return NULL;
+}
+
+static int
+filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
+			   int how, struct nfs_commit_info *cinfo)
+{
+	return pnfs_generic_commit_pagelist(inode, mds_pages, how, cinfo,
+					    filelayout_initiate_commit);
+}
+
+static struct nfs4_deviceid_node *
+filelayout_alloc_deviceid_node(struct nfs_server *server,
+		struct pnfs_device *pdev, gfp_t gfp_flags)
+{
+	struct nfs4_file_layout_dsaddr *dsaddr;
+
+	dsaddr = nfs4_fl_alloc_deviceid_node(server, pdev, gfp_flags);
+	if (!dsaddr)
+		return NULL;
+	return &dsaddr->id_node;
+}
+
+static void
+filelayout_free_deviceid_node(struct nfs4_deviceid_node *d)
+{
+	nfs4_fl_free_deviceid(container_of(d, struct nfs4_file_layout_dsaddr, id_node));
+}
+
+static struct pnfs_layout_hdr *
+filelayout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags)
+{
+	struct nfs4_filelayout *flo;
+
+	flo = kzalloc(sizeof(*flo), gfp_flags);
+	return flo != NULL ? &flo->generic_hdr : NULL;
+}
+
+static void
+filelayout_free_layout_hdr(struct pnfs_layout_hdr *lo)
+{
+	kfree(FILELAYOUT_FROM_HDR(lo));
+}
+
+static struct pnfs_ds_commit_info *
+filelayout_get_ds_info(struct inode *inode)
+{
+	struct pnfs_layout_hdr *layout = NFS_I(inode)->layout;
+
+	if (layout == NULL)
+		return NULL;
+	else
+		return &FILELAYOUT_FROM_HDR(layout)->commit_info;
+}
+
+static struct pnfs_layoutdriver_type filelayout_type = {
+	.id			= LAYOUT_NFSV4_1_FILES,
+	.name			= "LAYOUT_NFSV4_1_FILES",
+	.owner			= THIS_MODULE,
+	.alloc_layout_hdr	= filelayout_alloc_layout_hdr,
+	.free_layout_hdr	= filelayout_free_layout_hdr,
+	.alloc_lseg		= filelayout_alloc_lseg,
+	.free_lseg		= filelayout_free_lseg,
+	.pg_read_ops		= &filelayout_pg_read_ops,
+	.pg_write_ops		= &filelayout_pg_write_ops,
+	.get_ds_info		= &filelayout_get_ds_info,
+	.mark_request_commit	= filelayout_mark_request_commit,
+	.clear_request_commit	= pnfs_generic_clear_request_commit,
+	.scan_commit_lists	= pnfs_generic_scan_commit_lists,
+	.recover_commit_reqs	= pnfs_generic_recover_commit_reqs,
+	.search_commit_reqs	= filelayout_search_commit_reqs,
+	.commit_pagelist	= filelayout_commit_pagelist,
+	.read_pagelist		= filelayout_read_pagelist,
+	.write_pagelist		= filelayout_write_pagelist,
+	.alloc_deviceid_node	= filelayout_alloc_deviceid_node,
+	.free_deviceid_node	= filelayout_free_deviceid_node,
+	.sync			= pnfs_nfs_generic_sync,
+};
+
+static int __init nfs4filelayout_init(void)
+{
+	printk(KERN_INFO "%s: NFSv4 File Layout Driver Registering...\n",
+	       __func__);
+	return pnfs_register_layoutdriver(&filelayout_type);
+}
+
+static void __exit nfs4filelayout_exit(void)
+{
+	printk(KERN_INFO "%s: NFSv4 File Layout Driver Unregistering...\n",
+	       __func__);
+	pnfs_unregister_layoutdriver(&filelayout_type);
+}
+
+MODULE_ALIAS("nfs-layouttype4-1");
+
+module_init(nfs4filelayout_init);
+module_exit(nfs4filelayout_exit);
diff --git a/fs/nfs/filelayout/filelayout.h b/fs/nfs/filelayout/filelayout.h
new file mode 100644
index 000000000..79323b5da
--- /dev/null
+++ b/fs/nfs/filelayout/filelayout.h
@@ -0,0 +1,118 @@
+/*
+ *  NFSv4 file layout driver data structures.
+ *
+ *  Copyright (c) 2002
+ *  The Regents of the University of Michigan
+ *  All Rights Reserved
+ *
+ *  Dean Hildebrand <dhildebz@umich.edu>
+ *
+ *  Permission is granted to use, copy, create derivative works, and
+ *  redistribute this software and such derivative works for any purpose,
+ *  so long as the name of the University of Michigan is not used in
+ *  any advertising or publicity pertaining to the use or distribution
+ *  of this software without specific, written prior authorization. If
+ *  the above copyright notice or any other identification of the
+ *  University of Michigan is included in any copy of any portion of
+ *  this software, then the disclaimer below must also be included.
+ *
+ *  This software is provided as is, without representation or warranty
+ *  of any kind either express or implied, including without limitation
+ *  the implied warranties of merchantability, fitness for a particular
+ *  purpose, or noninfringement.  The Regents of the University of
+ *  Michigan shall not be liable for any damages, including special,
+ *  indirect, incidental, or consequential damages, with respect to any
+ *  claim arising out of or in connection with the use of the software,
+ *  even if it has been or is hereafter advised of the possibility of
+ *  such damages.
+ */
+
+#ifndef FS_NFS_NFS4FILELAYOUT_H
+#define FS_NFS_NFS4FILELAYOUT_H
+
+#include "../pnfs.h"
+
+/*
+ * Field testing shows we need to support up to 4096 stripe indices.
+ * We store each index as a u8 (u32 on the wire) to keep the memory footprint
+ * reasonable. This in turn means we support a maximum of 256
+ * RFC 5661 multipath_list4 structures.
+ */
+#define NFS4_PNFS_MAX_STRIPE_CNT 4096
+#define NFS4_PNFS_MAX_MULTI_CNT  256 /* 256 fit into a u8 stripe_index */
+
+enum stripetype4 {
+	STRIPE_SPARSE = 1,
+	STRIPE_DENSE = 2
+};
+
+struct nfs4_file_layout_dsaddr {
+	struct nfs4_deviceid_node	id_node;
+	u32				stripe_count;
+	u8				*stripe_indices;
+	u32				ds_num;
+	struct nfs4_pnfs_ds		*ds_list[1];
+};
+
+struct nfs4_filelayout_segment {
+	struct pnfs_layout_segment	generic_hdr;
+	u32				stripe_type;
+	u32				commit_through_mds;
+	u32				stripe_unit;
+	u32				first_stripe_index;
+	u64				pattern_offset;
+	struct nfs4_deviceid		deviceid;
+	struct nfs4_file_layout_dsaddr	*dsaddr; /* Point to GETDEVINFO data */
+	unsigned int			num_fh;
+	struct nfs_fh			**fh_array;
+};
+
+struct nfs4_filelayout {
+	struct pnfs_layout_hdr generic_hdr;
+	struct pnfs_ds_commit_info commit_info;
+};
+
+static inline struct nfs4_filelayout *
+FILELAYOUT_FROM_HDR(struct pnfs_layout_hdr *lo)
+{
+	return container_of(lo, struct nfs4_filelayout, generic_hdr);
+}
+
+static inline struct nfs4_filelayout_segment *
+FILELAYOUT_LSEG(struct pnfs_layout_segment *lseg)
+{
+	return container_of(lseg,
+			    struct nfs4_filelayout_segment,
+			    generic_hdr);
+}
+
+static inline struct nfs4_deviceid_node *
+FILELAYOUT_DEVID_NODE(struct pnfs_layout_segment *lseg)
+{
+	return &FILELAYOUT_LSEG(lseg)->dsaddr->id_node;
+}
+
+static inline bool
+filelayout_test_devid_invalid(struct nfs4_deviceid_node *node)
+{
+	return test_bit(NFS_DEVICEID_INVALID, &node->flags);
+}
+
+extern bool
+filelayout_test_devid_unavailable(struct nfs4_deviceid_node *node);
+
+extern struct nfs_fh *
+nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j);
+
+u32 nfs4_fl_calc_j_index(struct pnfs_layout_segment *lseg, loff_t offset);
+u32 nfs4_fl_calc_ds_index(struct pnfs_layout_segment *lseg, u32 j);
+struct nfs4_pnfs_ds *nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg,
+					u32 ds_idx);
+
+extern struct nfs4_file_layout_dsaddr *
+nfs4_fl_alloc_deviceid_node(struct nfs_server *server,
+	struct pnfs_device *pdev, gfp_t gfp_flags);
+extern void nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr);
+extern void nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr);
+
+#endif /* FS_NFS_NFS4FILELAYOUT_H */
diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c
new file mode 100644
index 000000000..d913e8188
--- /dev/null
+++ b/fs/nfs/filelayout/filelayoutdev.c
@@ -0,0 +1,305 @@
+/*
+ *  Device operations for the pnfs nfs4 file layout driver.
+ *
+ *  Copyright (c) 2002
+ *  The Regents of the University of Michigan
+ *  All Rights Reserved
+ *
+ *  Dean Hildebrand <dhildebz@umich.edu>
+ *  Garth Goodson   <Garth.Goodson@netapp.com>
+ *
+ *  Permission is granted to use, copy, create derivative works, and
+ *  redistribute this software and such derivative works for any purpose,
+ *  so long as the name of the University of Michigan is not used in
+ *  any advertising or publicity pertaining to the use or distribution
+ *  of this software without specific, written prior authorization. If
+ *  the above copyright notice or any other identification of the
+ *  University of Michigan is included in any copy of any portion of
+ *  this software, then the disclaimer below must also be included.
+ *
+ *  This software is provided as is, without representation or warranty
+ *  of any kind either express or implied, including without limitation
+ *  the implied warranties of merchantability, fitness for a particular
+ *  purpose, or noninfringement.  The Regents of the University of
+ *  Michigan shall not be liable for any damages, including special,
+ *  indirect, incidental, or consequential damages, with respect to any
+ *  claim arising out of or in connection with the use of the software,
+ *  even if it has been or is hereafter advised of the possibility of
+ *  such damages.
+ */
+
+#include <linux/nfs_fs.h>
+#include <linux/vmalloc.h>
+#include <linux/module.h>
+
+#include "../internal.h"
+#include "../nfs4session.h"
+#include "filelayout.h"
+
+#define NFSDBG_FACILITY		NFSDBG_PNFS_LD
+
+static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO;
+static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS;
+
+void
+nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
+{
+	struct nfs4_pnfs_ds *ds;
+	int i;
+
+	nfs4_print_deviceid(&dsaddr->id_node.deviceid);
+
+	for (i = 0; i < dsaddr->ds_num; i++) {
+		ds = dsaddr->ds_list[i];
+		if (ds != NULL)
+			nfs4_pnfs_ds_put(ds);
+	}
+	kfree(dsaddr->stripe_indices);
+	kfree_rcu(dsaddr, id_node.rcu);
+}
+
+/* Decode opaque device data and return the result */
+struct nfs4_file_layout_dsaddr *
+nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
+		gfp_t gfp_flags)
+{
+	int i;
+	u32 cnt, num;
+	u8 *indexp;
+	__be32 *p;
+	u8 *stripe_indices;
+	u8 max_stripe_index;
+	struct nfs4_file_layout_dsaddr *dsaddr = NULL;
+	struct xdr_stream stream;
+	struct xdr_buf buf;
+	struct page *scratch;
+	struct list_head dsaddrs;
+	struct nfs4_pnfs_ds_addr *da;
+
+	/* set up xdr stream */
+	scratch = alloc_page(gfp_flags);
+	if (!scratch)
+		goto out_err;
+
+	xdr_init_decode_pages(&stream, &buf, pdev->pages, pdev->pglen);
+	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
+
+	/* Get the stripe count (number of stripe index) */
+	p = xdr_inline_decode(&stream, 4);
+	if (unlikely(!p))
+		goto out_err_free_scratch;
+
+	cnt = be32_to_cpup(p);
+	dprintk("%s stripe count  %d\n", __func__, cnt);
+	if (cnt > NFS4_PNFS_MAX_STRIPE_CNT) {
+		printk(KERN_WARNING "NFS: %s: stripe count %d greater than "
+		       "supported maximum %d\n", __func__,
+			cnt, NFS4_PNFS_MAX_STRIPE_CNT);
+		goto out_err_free_scratch;
+	}
+
+	/* read stripe indices */
+	stripe_indices = kcalloc(cnt, sizeof(u8), gfp_flags);
+	if (!stripe_indices)
+		goto out_err_free_scratch;
+
+	p = xdr_inline_decode(&stream, cnt << 2);
+	if (unlikely(!p))
+		goto out_err_free_stripe_indices;
+
+	indexp = &stripe_indices[0];
+	max_stripe_index = 0;
+	for (i = 0; i < cnt; i++) {
+		*indexp = be32_to_cpup(p++);
+		max_stripe_index = max(max_stripe_index, *indexp);
+		indexp++;
+	}
+
+	/* Check the multipath list count */
+	p = xdr_inline_decode(&stream, 4);
+	if (unlikely(!p))
+		goto out_err_free_stripe_indices;
+
+	num = be32_to_cpup(p);
+	dprintk("%s ds_num %u\n", __func__, num);
+	if (num > NFS4_PNFS_MAX_MULTI_CNT) {
+		printk(KERN_WARNING "NFS: %s: multipath count %d greater than "
+			"supported maximum %d\n", __func__,
+			num, NFS4_PNFS_MAX_MULTI_CNT);
+		goto out_err_free_stripe_indices;
+	}
+
+	/* validate stripe indices are all < num */
+	if (max_stripe_index >= num) {
+		printk(KERN_WARNING "NFS: %s: stripe index %u >= num ds %u\n",
+			__func__, max_stripe_index, num);
+		goto out_err_free_stripe_indices;
+	}
+
+	dsaddr = kzalloc(sizeof(*dsaddr) +
+			(sizeof(struct nfs4_pnfs_ds *) * (num - 1)),
+			gfp_flags);
+	if (!dsaddr)
+		goto out_err_free_stripe_indices;
+
+	dsaddr->stripe_count = cnt;
+	dsaddr->stripe_indices = stripe_indices;
+	stripe_indices = NULL;
+	dsaddr->ds_num = num;
+	nfs4_init_deviceid_node(&dsaddr->id_node, server, &pdev->dev_id);
+
+	INIT_LIST_HEAD(&dsaddrs);
+
+	for (i = 0; i < dsaddr->ds_num; i++) {
+		int j;
+		u32 mp_count;
+
+		p = xdr_inline_decode(&stream, 4);
+		if (unlikely(!p))
+			goto out_err_free_deviceid;
+
+		mp_count = be32_to_cpup(p); /* multipath count */
+		for (j = 0; j < mp_count; j++) {
+			da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net,
+						    &stream, gfp_flags);
+			if (da)
+				list_add_tail(&da->da_node, &dsaddrs);
+		}
+		if (list_empty(&dsaddrs)) {
+			dprintk("%s: no suitable DS addresses found\n",
+				__func__);
+			goto out_err_free_deviceid;
+		}
+
+		dsaddr->ds_list[i] = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags);
+		if (!dsaddr->ds_list[i])
+			goto out_err_drain_dsaddrs;
+
+		/* If DS was already in cache, free ds addrs */
+		while (!list_empty(&dsaddrs)) {
+			da = list_first_entry(&dsaddrs,
+					      struct nfs4_pnfs_ds_addr,
+					      da_node);
+			list_del_init(&da->da_node);
+			kfree(da->da_remotestr);
+			kfree(da);
+		}
+	}
+
+	__free_page(scratch);
+	return dsaddr;
+
+out_err_drain_dsaddrs:
+	while (!list_empty(&dsaddrs)) {
+		da = list_first_entry(&dsaddrs, struct nfs4_pnfs_ds_addr,
+				      da_node);
+		list_del_init(&da->da_node);
+		kfree(da->da_remotestr);
+		kfree(da);
+	}
+out_err_free_deviceid:
+	nfs4_fl_free_deviceid(dsaddr);
+	/* stripe_indicies was part of dsaddr */
+	goto out_err_free_scratch;
+out_err_free_stripe_indices:
+	kfree(stripe_indices);
+out_err_free_scratch:
+	__free_page(scratch);
+out_err:
+	dprintk("%s ERROR: returning NULL\n", __func__);
+	return NULL;
+}
+
+void
+nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
+{
+	nfs4_put_deviceid_node(&dsaddr->id_node);
+}
+
+/*
+ * Want res = (offset - layout->pattern_offset)/ layout->stripe_unit
+ * Then: ((res + fsi) % dsaddr->stripe_count)
+ */
+u32
+nfs4_fl_calc_j_index(struct pnfs_layout_segment *lseg, loff_t offset)
+{
+	struct nfs4_filelayout_segment *flseg = FILELAYOUT_LSEG(lseg);
+	u64 tmp;
+
+	tmp = offset - flseg->pattern_offset;
+	do_div(tmp, flseg->stripe_unit);
+	tmp += flseg->first_stripe_index;
+	return do_div(tmp, flseg->dsaddr->stripe_count);
+}
+
+u32
+nfs4_fl_calc_ds_index(struct pnfs_layout_segment *lseg, u32 j)
+{
+	return FILELAYOUT_LSEG(lseg)->dsaddr->stripe_indices[j];
+}
+
+struct nfs_fh *
+nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j)
+{
+	struct nfs4_filelayout_segment *flseg = FILELAYOUT_LSEG(lseg);
+	u32 i;
+
+	if (flseg->stripe_type == STRIPE_SPARSE) {
+		if (flseg->num_fh == 1)
+			i = 0;
+		else if (flseg->num_fh == 0)
+			/* Use the MDS OPEN fh set in nfs_read_rpcsetup */
+			return NULL;
+		else
+			i = nfs4_fl_calc_ds_index(lseg, j);
+	} else
+		i = j;
+	return flseg->fh_array[i];
+}
+
+/* Upon return, either ds is connected, or ds is NULL */
+struct nfs4_pnfs_ds *
+nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
+{
+	struct nfs4_file_layout_dsaddr *dsaddr = FILELAYOUT_LSEG(lseg)->dsaddr;
+	struct nfs4_pnfs_ds *ds = dsaddr->ds_list[ds_idx];
+	struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
+	struct nfs4_pnfs_ds *ret = ds;
+	struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode);
+	int status;
+
+	if (ds == NULL) {
+		printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",
+			__func__, ds_idx);
+		pnfs_generic_mark_devid_invalid(devid);
+		goto out;
+	}
+	smp_rmb();
+	if (ds->ds_clp)
+		goto out_test_devid;
+
+	status = nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
+			     dataserver_retrans, 4,
+			     s->nfs_client->cl_minorversion);
+	if (status) {
+		nfs4_mark_deviceid_unavailable(devid);
+		ret = NULL;
+		goto out;
+	}
+
+out_test_devid:
+	if (ret->ds_clp == NULL ||
+	    filelayout_test_devid_unavailable(devid))
+		ret = NULL;
+out:
+	return ret;
+}
+
+module_param(dataserver_retrans, uint, 0644);
+MODULE_PARM_DESC(dataserver_retrans, "The  number of times the NFSv4.1 client "
+			"retries a request before it attempts further "
+			" recovery  action.");
+module_param(dataserver_timeo, uint, 0644);
+MODULE_PARM_DESC(dataserver_timeo, "The time (in tenths of a second) the "
+			"NFSv4.1  client  waits for a response from a "
+			" data server before it retries an NFS request.");