24 files changed, 2550 insertions, 45 deletions

diff --git a/Documentation/filesystems/nfs/00-INDEX b/Documentation/filesystems/nfs/00-INDEX
index 3225a5662114..a57e12411d2a 100644
--- a/Documentation/filesystems/nfs/00-INDEX
+++ b/Documentation/filesystems/nfs/00-INDEX
@@ -12,6 +12,8 @@ nfs-rdma.txt
 	- how to install and setup the Linux NFS/RDMA client and server software
 nfsroot.txt
 	- short guide on setting up a diskless box with NFS root filesystem.
+pnfs.txt
+	- short explanation of some of the internals of the pnfs client code
 rpc-cache.txt
 	- introduction to the caching mechanisms in the sunrpc layer.
 idmapper.txt
diff --git a/Documentation/filesystems/nfs/pnfs.txt b/Documentation/filesystems/nfs/pnfs.txt
new file mode 100644
index 000000000000..bc0b9cfe095b
--- /dev/null
+++ b/Documentation/filesystems/nfs/pnfs.txt
@@ -0,0 +1,48 @@
+Reference counting in pnfs:
+==========================
+
+The are several inter-related caches.  We have layouts which can
+reference multiple devices, each of which can reference multiple data servers.
+Each data server can be referenced by multiple devices.  Each device
+can be referenced by multiple layouts.  To keep all of this straight,
+we need to reference count.
+
+
+struct pnfs_layout_hdr
+----------------------
+The on-the-wire command LAYOUTGET corresponds to struct
+pnfs_layout_segment, usually referred to by the variable name lseg.
+Each nfs_inode may hold a pointer to a cache of of these layout
+segments in nfsi->layout, of type struct pnfs_layout_hdr.
+
+We reference the header for the inode pointing to it, across each
+outstanding RPC call that references it (LAYOUTGET, LAYOUTRETURN,
+LAYOUTCOMMIT), and for each lseg held within.
+
+Each header is also (when non-empty) put on a list associated with
+struct nfs_client (cl_layouts).  Being put on this list does not bump
+the reference count, as the layout is kept around by the lseg that
+keeps it in the list.
+
+deviceid_cache
+--------------
+lsegs reference device ids, which are resolved per nfs_client and
+layout driver type.  The device ids are held in a RCU cache (struct
+nfs4_deviceid_cache).  The cache itself is referenced across each
+mount.  The entries (struct nfs4_deviceid) themselves are held across
+the lifetime of each lseg referencing them.
+
+RCU is used because the deviceid is basically a write once, read many
+data structure.  The hlist size of 32 buckets needs better
+justification, but seems reasonable given that we can have multiple
+deviceid's per filesystem, and multiple filesystems per nfs_client.
+
+The hash code is copied from the nfsd code base.  A discussion of
+hashing and variations of this algorithm can be found at:
+http://groups.google.com/group/comp.lang.c/browse_thread/thread/9522965e2b8d3809
+
+data server cache
+-----------------
+file driver devices refer to data servers, which are kept in a module
+level cache.  Its reference is held over the lifetime of the deviceid
+pointing to it.
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 5c55c26af165..fd667652c502 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -77,13 +77,17 @@ config NFS_V4
 
 config NFS_V4_1
 	bool "NFS client support for NFSv4.1 (EXPERIMENTAL)"
-	depends on NFS_V4 && EXPERIMENTAL
+	depends on NFS_FS && NFS_V4 && EXPERIMENTAL
+	select PNFS_FILE_LAYOUT
 	help
 	  This option enables support for minor version 1 of the NFSv4 protocol
-	  (draft-ietf-nfsv4-minorversion1) in the kernel's NFS client.
+	  (RFC 5661) in the kernel's NFS client.
 
 	  If unsure, say N.
 
+config PNFS_FILE_LAYOUT
+	tristate
+
 config ROOT_NFS
 	bool "Root file system on NFS"
 	depends on NFS_FS=y && IP_PNP
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index da7fda639eac..4776ff9e3814 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -15,5 +15,9 @@ nfs-$(CONFIG_NFS_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o \
 			   delegation.o idmap.o \
 			   callback.o callback_xdr.o callback_proc.o \
 			   nfs4namespace.o
+nfs-$(CONFIG_NFS_V4_1)	+= pnfs.o
 nfs-$(CONFIG_SYSCTL) += sysctl.o
 nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o
+
+obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o
+nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 930d10fecdaf..2950fca0c61b 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -118,11 +118,11 @@ int nfs41_validate_delegation_stateid(struct nfs_delegation *delegation, const n
 	if (delegation == NULL)
 		return 0;
 
-	/* seqid is 4-bytes long */
-	if (((u32 *) &stateid->data)[0] != 0)
+	if (stateid->stateid.seqid != 0)
 		return 0;
-	if (memcmp(&delegation->stateid.data[4], &stateid->data[4],
-		   sizeof(stateid->data)-4))
+	if (memcmp(&delegation->stateid.stateid.other,
+		   &stateid->stateid.other,
+		   NFS4_STATEID_OTHER_SIZE))
 		return 0;
 
 	return 1;
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index a882785eba41..fd6f0a70021b 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -48,6 +48,7 @@
 #include "iostat.h"
 #include "internal.h"
 #include "fscache.h"
+#include "pnfs.h"
 
 #define NFSDBG_FACILITY		NFSDBG_CLIENT
 
@@ -155,7 +156,9 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
 	cred = rpc_lookup_machine_cred();
 	if (!IS_ERR(cred))
 		clp->cl_machine_cred = cred;
-
+#if defined(CONFIG_NFS_V4_1)
+	INIT_LIST_HEAD(&clp->cl_layouts);
+#endif
 	nfs_fscache_get_client_cookie(clp);
 
 	return clp;
@@ -252,6 +255,7 @@ void nfs_put_client(struct nfs_client *clp)
 		nfs_free_client(clp);
 	}
 }
+EXPORT_SYMBOL_GPL(nfs_put_client);
 
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 /*
@@ -900,6 +904,8 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo *
 	if (server->wsize > NFS_MAX_FILE_IO_SIZE)
 		server->wsize = NFS_MAX_FILE_IO_SIZE;
 	server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	set_pnfs_layoutdriver(server, fsinfo->layouttype);
+
 	server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL);
 
 	server->dtsize = nfs_block_size(fsinfo->dtpref, NULL);
@@ -939,6 +945,7 @@ static int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, str
 	}
 
 	fsinfo.fattr = fattr;
+	fsinfo.layouttype = 0;
 	error = clp->rpc_ops->fsinfo(server, mntfh, &fsinfo);
 	if (error < 0)
 		goto out_error;
@@ -1021,6 +1028,7 @@ void nfs_free_server(struct nfs_server *server)
 {
 	dprintk("--> nfs_free_server()\n");
 
+	unset_pnfs_layoutdriver(server);
 	spin_lock(&nfs_client_lock);
 	list_del(&server->client_link);
 	list_del(&server->master_link);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index e18c31e08a28..e756075637b0 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -36,6 +36,7 @@
 #include "internal.h"
 #include "iostat.h"
 #include "fscache.h"
+#include "pnfs.h"
 
 #define NFSDBG_FACILITY		NFSDBG_FILE
 
@@ -386,6 +387,10 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping,
 		file->f_path.dentry->d_name.name,
 		mapping->host->i_ino, len, (long long) pos);
 
+	pnfs_update_layout(mapping->host,
+			   nfs_file_open_context(file),
+			   IOMODE_RW);
+
 start:
 	/*
 	 * Prevent starvation issues if someone is doing a consistency
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 6eec28656415..314f57164602 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -48,6 +48,7 @@
 #include "internal.h"
 #include "fscache.h"
 #include "dns_resolve.h"
+#include "pnfs.h"
 
 #define NFSDBG_FACILITY		NFSDBG_VFS
 
@@ -1410,6 +1411,7 @@ void nfs4_evict_inode(struct inode *inode)
 {
 	truncate_inode_pages(&inode->i_data, 0);
 	end_writeback(inode);
+	pnfs_destroy_layout(NFS_I(inode));
 	/* If we are holding a delegation, return it! */
 	nfs_inode_return_delegation_noreclaim(inode);
 	/* First call standard NFS clear_inode() code */
@@ -1447,6 +1449,7 @@ static inline void nfs4_init_once(struct nfs_inode *nfsi)
 	nfsi->delegation = NULL;
 	nfsi->delegation_state = 0;
 	init_rwsem(&nfsi->rwsem);
+	nfsi->layout = NULL;
 #endif
 }
 
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
new file mode 100644
index 000000000000..2e92f0d8d654
--- /dev/null
+++ b/fs/nfs/nfs4filelayout.c
@@ -0,0 +1,280 @@
+/*
+ *  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 "internal.h"
+#include "nfs4filelayout.h"
+
+#define NFSDBG_FACILITY         NFSDBG_PNFS_LD
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Dean Hildebrand <dhildebz@umich.edu>");
+MODULE_DESCRIPTION("The NFSv4 file layout driver");
+
+static int
+filelayout_set_layoutdriver(struct nfs_server *nfss)
+{
+	int status = pnfs_alloc_init_deviceid_cache(nfss->nfs_client,
+						nfs4_fl_free_deviceid_callback);
+	if (status) {
+		printk(KERN_WARNING "%s: deviceid cache could not be "
+			"initialized\n", __func__);
+		return status;
+	}
+	dprintk("%s: deviceid cache has been initialized successfully\n",
+		__func__);
+	return 0;
+}
+
+/* Clear out the layout by destroying its device list */
+static int
+filelayout_clear_layoutdriver(struct nfs_server *nfss)
+{
+	dprintk("--> %s\n", __func__);
+
+	if (nfss->nfs_client->cl_devid_cache)
+		pnfs_put_deviceid_cache(nfss->nfs_client);
+	return 0;
+}
+
+/*
+ * 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,
+			struct nfs4_deviceid *id)
+{
+	struct nfs4_file_layout_dsaddr *dsaddr;
+	int status = -EINVAL;
+	struct nfs_server *nfss = NFS_SERVER(lo->inode);
+
+	dprintk("--> %s\n", __func__);
+
+	if (fl->pattern_offset > lgr->range.offset) {
+		dprintk("%s pattern_offset %lld to large\n",
+				__func__, fl->pattern_offset);
+		goto out;
+	}
+
+	if (fl->stripe_unit % PAGE_SIZE) {
+		dprintk("%s Stripe unit (%u) not page aligned\n",
+			__func__, fl->stripe_unit);
+		goto out;
+	}
+
+	/* find and reference the deviceid */
+	dsaddr = nfs4_fl_find_get_deviceid(nfss->nfs_client, id);
+	if (dsaddr == NULL) {
+		dsaddr = get_device_info(lo->inode, id);
+		if (dsaddr == NULL)
+			goto out;
+	}
+	fl->dsaddr = dsaddr;
+
+	if (fl->first_stripe_index < 0 ||
+	    fl->first_stripe_index >= dsaddr->stripe_count) {
+		dprintk("%s Bad first_stripe_index %d\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;
+	}
+
+	if (fl->stripe_unit % nfss->rsize || fl->stripe_unit % nfss->wsize) {
+		dprintk("%s Stripe unit (%u) not aligned with rsize %u "
+			"wsize %u\n", __func__, fl->stripe_unit, nfss->rsize,
+			nfss->wsize);
+	}
+
+	status = 0;
+out:
+	dprintk("--> %s returns %d\n", __func__, status);
+	return status;
+out_put:
+	pnfs_put_deviceid(nfss->nfs_client->cl_devid_cache, &dsaddr->deviceid);
+	goto out;
+}
+
+static void filelayout_free_fh_array(struct nfs4_filelayout_segment *fl)
+{
+	int i;
+
+	for (i = 0; i < fl->num_fh; i++) {
+		if (!fl->fh_array[i])
+			break;
+		kfree(fl->fh_array[i]);
+	}
+	kfree(fl->fh_array);
+	fl->fh_array = NULL;
+}
+
+static void
+_filelayout_free_lseg(struct nfs4_filelayout_segment *fl)
+{
+	filelayout_free_fh_array(fl);
+	kfree(fl);
+}
+
+static int
+filelayout_decode_layout(struct pnfs_layout_hdr *flo,
+			 struct nfs4_filelayout_segment *fl,
+			 struct nfs4_layoutget_res *lgr,
+			 struct nfs4_deviceid *id)
+{
+	uint32_t *p = (uint32_t *)lgr->layout.buf;
+	uint32_t nfl_util;
+	int i;
+
+	dprintk("%s: set_layout_map Begin\n", __func__);
+
+	memcpy(id, p, sizeof(*id));
+	p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE);
+	print_deviceid(id);
+
+	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);
+
+	fl->fh_array = kzalloc(fl->num_fh * sizeof(struct nfs_fh *),
+			       GFP_KERNEL);
+	if (!fl->fh_array)
+		return -ENOMEM;
+
+	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_KERNEL);
+		if (!fl->fh_array[i]) {
+			filelayout_free_fh_array(fl);
+			return -ENOMEM;
+		}
+		fl->fh_array[i]->size = be32_to_cpup(p++);
+		if (sizeof(struct nfs_fh) < fl->fh_array[i]->size) {
+			printk(KERN_ERR "Too big fh %d received %d\n",
+			       i, fl->fh_array[i]->size);
+			filelayout_free_fh_array(fl);
+			return -EIO;
+		}
+		memcpy(fl->fh_array[i]->data, p, fl->fh_array[i]->size);
+		p += XDR_QUADLEN(fl->fh_array[i]->size);
+		dprintk("DEBUG: %s: fh len %d\n", __func__,
+			fl->fh_array[i]->size);
+	}
+
+	return 0;
+}
+
+static struct pnfs_layout_segment *
+filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
+		      struct nfs4_layoutget_res *lgr)
+{
+	struct nfs4_filelayout_segment *fl;
+	int rc;
+	struct nfs4_deviceid id;
+
+	dprintk("--> %s\n", __func__);
+	fl = kzalloc(sizeof(*fl), GFP_KERNEL);
+	if (!fl)
+		return NULL;
+
+	rc = filelayout_decode_layout(layoutid, fl, lgr, &id);
+	if (rc != 0 || filelayout_check_layout(layoutid, fl, lgr, &id)) {
+		_filelayout_free_lseg(fl);
+		return NULL;
+	}
+	return &fl->generic_hdr;
+}
+
+static void
+filelayout_free_lseg(struct pnfs_layout_segment *lseg)
+{
+	struct nfs_server *nfss = NFS_SERVER(lseg->layout->inode);
+	struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg);
+
+	dprintk("--> %s\n", __func__);
+	pnfs_put_deviceid(nfss->nfs_client->cl_devid_cache,
+			  &fl->dsaddr->deviceid);
+	_filelayout_free_lseg(fl);
+}
+
+static struct pnfs_layoutdriver_type filelayout_type = {
+	.id = LAYOUT_NFSV4_1_FILES,
+	.name = "LAYOUT_NFSV4_1_FILES",
+	.owner = THIS_MODULE,
+	.set_layoutdriver = filelayout_set_layoutdriver,
+	.clear_layoutdriver = filelayout_clear_layoutdriver,
+	.alloc_lseg              = filelayout_alloc_lseg,
+	.free_lseg               = filelayout_free_lseg,
+};
+
+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_init(nfs4filelayout_init);
+module_exit(nfs4filelayout_exit);
diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h
new file mode 100644
index 000000000000..bbf60dd2ab9d
--- /dev/null
+++ b/fs/nfs/nfs4filelayout.h
@@ -0,0 +1,94 @@
+/*
+ *  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 upto 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
+};
+
+/* Individual ip address */
+struct nfs4_pnfs_ds {
+	struct list_head	ds_node;  /* nfs4_pnfs_dev_hlist dev_dslist */
+	u32			ds_ip_addr;
+	u32			ds_port;
+	struct nfs_client	*ds_clp;
+	atomic_t		ds_count;
+};
+
+struct nfs4_file_layout_dsaddr {
+	struct pnfs_deviceid_node	deviceid;
+	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_file_layout_dsaddr *dsaddr; /* Point to GETDEVINFO data */
+	unsigned int num_fh;
+	struct nfs_fh **fh_array;
+};
+
+static inline struct nfs4_filelayout_segment *
+FILELAYOUT_LSEG(struct pnfs_layout_segment *lseg)
+{
+	return container_of(lseg,
+			    struct nfs4_filelayout_segment,
+			    generic_hdr);
+}
+
+extern void nfs4_fl_free_deviceid_callback(struct pnfs_deviceid_node *);
+extern void print_ds(struct nfs4_pnfs_ds *ds);
+extern void print_deviceid(struct nfs4_deviceid *dev_id);
+extern struct nfs4_file_layout_dsaddr *
+nfs4_fl_find_get_deviceid(struct nfs_client *, struct nfs4_deviceid *dev_id);
+struct nfs4_file_layout_dsaddr *
+get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id);
+
+#endif /* FS_NFS_NFS4FILELAYOUT_H */
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
new file mode 100644
index 000000000000..51fe64ace55a
--- /dev/null
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -0,0 +1,448 @@
+/*
+ *  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 "internal.h"
+#include "nfs4filelayout.h"
+
+#define NFSDBG_FACILITY		NFSDBG_PNFS_LD
+
+/*
+ * Data server cache
+ *
+ * Data servers can be mapped to different device ids.
+ * nfs4_pnfs_ds reference counting
+ *   - set to 1 on allocation
+ *   - incremented when a device id maps a data server already in the cache.
+ *   - decremented when deviceid is removed from the cache.
+ */
+DEFINE_SPINLOCK(nfs4_ds_cache_lock);
+static LIST_HEAD(nfs4_data_server_cache);
+
+/* Debug routines */
+void
+print_ds(struct nfs4_pnfs_ds *ds)
+{
+	if (ds == NULL) {
+		printk("%s NULL device\n", __func__);
+		return;
+	}
+	printk("        ip_addr %x port %hu\n"
+		"        ref count %d\n"
+		"        client %p\n"
+		"        cl_exchange_flags %x\n",
+		ntohl(ds->ds_ip_addr), ntohs(ds->ds_port),
+		atomic_read(&ds->ds_count), ds->ds_clp,
+		ds->ds_clp ? ds->ds_clp->cl_exchange_flags : 0);
+}
+
+void
+print_ds_list(struct nfs4_file_layout_dsaddr *dsaddr)
+{
+	int i;
+
+	ifdebug(FACILITY) {
+		printk("%s dsaddr->ds_num %d\n", __func__,
+		       dsaddr->ds_num);
+		for (i = 0; i < dsaddr->ds_num; i++)
+			print_ds(dsaddr->ds_list[i]);
+	}
+}
+
+void print_deviceid(struct nfs4_deviceid *id)
+{
+	u32 *p = (u32 *)id;
+
+	dprintk("%s: device id= [%x%x%x%x]\n", __func__,
+		p[0], p[1], p[2], p[3]);
+}
+
+/* nfs4_ds_cache_lock is held */
+static struct nfs4_pnfs_ds *
+_data_server_lookup_locked(u32 ip_addr, u32 port)
+{
+	struct nfs4_pnfs_ds *ds;
+
+	dprintk("_data_server_lookup: ip_addr=%x port=%hu\n",
+			ntohl(ip_addr), ntohs(port));
+
+	list_for_each_entry(ds, &nfs4_data_server_cache, ds_node) {
+		if (ds->ds_ip_addr == ip_addr &&
+		    ds->ds_port == port) {
+			return ds;
+		}
+	}
+	return NULL;
+}
+
+static void
+destroy_ds(struct nfs4_pnfs_ds *ds)
+{
+	dprintk("--> %s\n", __func__);
+	ifdebug(FACILITY)
+		print_ds(ds);
+
+	if (ds->ds_clp)
+		nfs_put_client(ds->ds_clp);
+	kfree(ds);
+}
+
+static void
+nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
+{
+	struct nfs4_pnfs_ds *ds;
+	int i;
+
+	print_deviceid(&dsaddr->deviceid.de_id);
+
+	for (i = 0; i < dsaddr->ds_num; i++) {
+		ds = dsaddr->ds_list[i];
+		if (ds != NULL) {
+			if (atomic_dec_and_lock(&ds->ds_count,
+						&nfs4_ds_cache_lock)) {
+				list_del_init(&ds->ds_node);
+				spin_unlock(&nfs4_ds_cache_lock);
+				destroy_ds(ds);
+			}
+		}
+	}
+	kfree(dsaddr->stripe_indices);
+	kfree(dsaddr);
+}
+
+void
+nfs4_fl_free_deviceid_callback(struct pnfs_deviceid_node *device)
+{
+	struct nfs4_file_layout_dsaddr *dsaddr =
+		container_of(device, struct nfs4_file_layout_dsaddr, deviceid);
+
+	nfs4_fl_free_deviceid(dsaddr);
+}
+
+static struct nfs4_pnfs_ds *
+nfs4_pnfs_ds_add(struct inode *inode, u32 ip_addr, u32 port)
+{
+	struct nfs4_pnfs_ds *tmp_ds, *ds;
+
+	ds = kzalloc(sizeof(*tmp_ds), GFP_KERNEL);
+	if (!ds)
+		goto out;
+
+	spin_lock(&nfs4_ds_cache_lock);
+	tmp_ds = _data_server_lookup_locked(ip_addr, port);
+	if (tmp_ds == NULL) {
+		ds->ds_ip_addr = ip_addr;
+		ds->ds_port = port;
+		atomic_set(&ds->ds_count, 1);
+		INIT_LIST_HEAD(&ds->ds_node);
+		ds->ds_clp = NULL;
+		list_add(&ds->ds_node, &nfs4_data_server_cache);
+		dprintk("%s add new data server ip 0x%x\n", __func__,
+			ds->ds_ip_addr);
+	} else {
+		kfree(ds);
+		atomic_inc(&tmp_ds->ds_count);
+		dprintk("%s data server found ip 0x%x, inc'ed ds_count to %d\n",
+			__func__, tmp_ds->ds_ip_addr,
+			atomic_read(&tmp_ds->ds_count));
+		ds = tmp_ds;
+	}
+	spin_unlock(&nfs4_ds_cache_lock);
+out:
+	return ds;
+}
+
+/*
+ * Currently only support ipv4, and one multi-path address.
+ */
+static struct nfs4_pnfs_ds *
+decode_and_add_ds(__be32 **pp, struct inode *inode)
+{
+	struct nfs4_pnfs_ds *ds = NULL;
+	char *buf;
+	const char *ipend, *pstr;
+	u32 ip_addr, port;
+	int nlen, rlen, i;
+	int tmp[2];
+	__be32 *r_netid, *r_addr, *p = *pp;
+
+	/* r_netid */
+	nlen = be32_to_cpup(p++);
+	r_netid = p;
+	p += XDR_QUADLEN(nlen);
+
+	/* r_addr */
+	rlen = be32_to_cpup(p++);
+	r_addr = p;
+	p += XDR_QUADLEN(rlen);
+	*pp = p;
+
+	/* Check that netid is "tcp" */
+	if (nlen != 3 ||  memcmp((char *)r_netid, "tcp", 3)) {
+		dprintk("%s: ERROR: non ipv4 TCP r_netid\n", __func__);
+		goto out_err;
+	}
+
+	/* ipv6 length plus port is legal */
+	if (rlen > INET6_ADDRSTRLEN + 8) {
+		dprintk("%s Invalid address, length %d\n", __func__,
+			rlen);
+		goto out_err;
+	}
+	buf = kmalloc(rlen + 1, GFP_KERNEL);
+	buf[rlen] = '\0';
+	memcpy(buf, r_addr, rlen);
+
+	/* replace the port dots with dashes for the in4_pton() delimiter*/
+	for (i = 0; i < 2; i++) {
+		char *res = strrchr(buf, '.');
+		*res = '-';
+	}
+
+	/* Currently only support ipv4 address */
+	if (in4_pton(buf, rlen, (u8 *)&ip_addr, '-', &ipend) == 0) {
+		dprintk("%s: Only ipv4 addresses supported\n", __func__);
+		goto out_free;
+	}
+
+	/* port */
+	pstr = ipend;
+	sscanf(pstr, "-%d-%d", &tmp[0], &tmp[1]);
+	port = htons((tmp[0] << 8) | (tmp[1]));
+
+	ds = nfs4_pnfs_ds_add(inode, ip_addr, port);
+	dprintk("%s Decoded address and port %s\n", __func__, buf);
+out_free:
+	kfree(buf);
+out_err:
+	return ds;
+}
+
+/* Decode opaque device data and return the result */
+static struct nfs4_file_layout_dsaddr*
+decode_device(struct inode *ino, struct pnfs_device *pdev)
+{
+	int i, dummy;
+	u32 cnt, num;
+	u8 *indexp;
+	__be32 *p = (__be32 *)pdev->area, *indicesp;
+	struct nfs4_file_layout_dsaddr *dsaddr;
+
+	/* Get the stripe count (number of stripe index) */
+	cnt = be32_to_cpup(p++);
+	dprintk("%s stripe count  %d\n", __func__, cnt);
+	if (cnt > NFS4_PNFS_MAX_STRIPE_CNT) {
+		printk(KERN_WARNING "%s: stripe count %d greater than "
+		       "supported maximum %d\n", __func__,
+			cnt, NFS4_PNFS_MAX_STRIPE_CNT);
+		goto out_err;
+	}
+
+	/* Check the multipath list count */
+	indicesp = p;
+	p += XDR_QUADLEN(cnt << 2);
+	num = be32_to_cpup(p++);
+	dprintk("%s ds_num %u\n", __func__, num);
+	if (num > NFS4_PNFS_MAX_MULTI_CNT) {
+		printk(KERN_WARNING "%s: multipath count %d greater than "
+			"supported maximum %d\n", __func__,
+			num, NFS4_PNFS_MAX_MULTI_CNT);
+		goto out_err;
+	}
+	dsaddr = kzalloc(sizeof(*dsaddr) +
+			(sizeof(struct nfs4_pnfs_ds *) * (num - 1)),
+			GFP_KERNEL);
+	if (!dsaddr)
+		goto out_err;
+
+	dsaddr->stripe_indices = kzalloc(sizeof(u8) * cnt, GFP_KERNEL);
+	if (!dsaddr->stripe_indices)
+		goto out_err_free;
+
+	dsaddr->stripe_count = cnt;
+	dsaddr->ds_num = num;
+
+	memcpy(&dsaddr->deviceid.de_id, &pdev->dev_id, sizeof(pdev->dev_id));
+
+	/* Go back an read stripe indices */
+	p = indicesp;
+	indexp = &dsaddr->stripe_indices[0];
+	for (i = 0; i < dsaddr->stripe_count; i++) {
+		*indexp = be32_to_cpup(p++);
+		if (*indexp >= num)
+			goto out_err_free;
+		indexp++;
+	}
+	/* Skip already read multipath list count */
+	p++;