22 files changed, 1434 insertions, 692 deletions

diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 89587573fe5..2f41dccea18 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -188,10 +188,10 @@ static u32 initiate_bulk_draining(struct nfs_client *clp,
 			rv = NFS4ERR_DELAY;
 		list_del_init(&lo->plh_bulk_recall);
 		spin_unlock(&ino->i_lock);
+		pnfs_free_lseg_list(&free_me_list);
 		put_layout_hdr(lo);
 		iput(ino);
 	}
-	pnfs_free_lseg_list(&free_me_list);
 	return rv;
 }
 
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index bd3ca32879e..139be9647d8 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -82,6 +82,11 @@ retry:
 #endif /* CONFIG_NFS_V4 */
 
 /*
+ * Turn off NFSv4 uid/gid mapping when using AUTH_SYS
+ */
+static int nfs4_disable_idmapping = 0;
+
+/*
  * RPC cruft for NFS
  */
 static struct rpc_version *nfs_version[5] = {
@@ -481,7 +486,12 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
  * Look up a client by IP address and protocol version
  * - creates a new record if one doesn't yet exist
  */
-static struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init)
+static struct nfs_client *
+nfs_get_client(const struct nfs_client_initdata *cl_init,
+	       const struct rpc_timeout *timeparms,
+	       const char *ip_addr,
+	       rpc_authflavor_t authflavour,
+	       int noresvport)
 {
 	struct nfs_client *clp, *new = NULL;
 	int error;
@@ -512,6 +522,13 @@ install_client:
 	clp = new;
 	list_add(&clp->cl_share_link, &nfs_client_list);
 	spin_unlock(&nfs_client_lock);
+
+	error = cl_init->rpc_ops->init_client(clp, timeparms, ip_addr,
+					      authflavour, noresvport);
+	if (error < 0) {
+		nfs_put_client(clp);
+		return ERR_PTR(error);
+	}
 	dprintk("--> nfs_get_client() = %p [new]\n", clp);
 	return clp;
 
@@ -767,9 +784,9 @@ static int nfs_init_server_rpcclient(struct nfs_server *server,
 /*
  * Initialise an NFS2 or NFS3 client
  */
-static int nfs_init_client(struct nfs_client *clp,
-			   const struct rpc_timeout *timeparms,
-			   const struct nfs_parsed_mount_data *data)
+int nfs_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms,
+		    const char *ip_addr, rpc_authflavor_t authflavour,
+		    int noresvport)
 {
 	int error;
 
@@ -784,7 +801,7 @@ static int nfs_init_client(struct nfs_client *clp,
 	 * - RFC 2623, sec 2.3.2
 	 */
 	error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX,
-				      0, data->flags & NFS_MOUNT_NORESVPORT);
+				      0, noresvport);
 	if (error < 0)
 		goto error;
 	nfs_mark_client_ready(clp, NFS_CS_READY);
@@ -820,19 +837,17 @@ static int nfs_init_server(struct nfs_server *server,
 		cl_init.rpc_ops = &nfs_v3_clientops;
 #endif
 
+	nfs_init_timeout_values(&timeparms, data->nfs_server.protocol,
+			data->timeo, data->retrans);
+
 	/* Allocate or find a client reference we can use */
-	clp = nfs_get_client(&cl_init);
+	clp = nfs_get_client(&cl_init, &timeparms, NULL, RPC_AUTH_UNIX,
+			     data->flags & NFS_MOUNT_NORESVPORT);
 	if (IS_ERR(clp)) {
 		dprintk("<-- nfs_init_server() = error %ld\n", PTR_ERR(clp));
 		return PTR_ERR(clp);
 	}
 
-	nfs_init_timeout_values(&timeparms, data->nfs_server.protocol,
-			data->timeo, data->retrans);
-	error = nfs_init_client(clp, &timeparms, data);
-	if (error < 0)
-		goto error;
-
 	server->nfs_client = clp;
 
 	/* Initialise the client representation from the mount data */
@@ -1009,14 +1024,19 @@ static void nfs_server_insert_lists(struct nfs_server *server)
 	spin_lock(&nfs_client_lock);
 	list_add_tail_rcu(&server->client_link, &clp->cl_superblocks);
 	list_add_tail(&server->master_link, &nfs_volume_list);
+	clear_bit(NFS_CS_STOP_RENEW, &clp->cl_res_state);
 	spin_unlock(&nfs_client_lock);
 
 }
 
 static void nfs_server_remove_lists(struct nfs_server *server)
 {
+	struct nfs_client *clp = server->nfs_client;
+
 	spin_lock(&nfs_client_lock);
 	list_del_rcu(&server->client_link);
+	if (clp && list_empty(&clp->cl_superblocks))
+		set_bit(NFS_CS_STOP_RENEW, &clp->cl_res_state);
 	list_del(&server->master_link);
 	spin_unlock(&nfs_client_lock);
 
@@ -1307,11 +1327,11 @@ static int nfs4_init_client_minor_version(struct nfs_client *clp)
 /*
  * Initialise an NFS4 client record
  */
-static int nfs4_init_client(struct nfs_client *clp,
-		const struct rpc_timeout *timeparms,
-		const char *ip_addr,
-		rpc_authflavor_t authflavour,
-		int flags)
+int nfs4_init_client(struct nfs_client *clp,
+		     const struct rpc_timeout *timeparms,
+		     const char *ip_addr,
+		     rpc_authflavor_t authflavour,
+		     int noresvport)
 {
 	int error;
 
@@ -1325,7 +1345,7 @@ static int nfs4_init_client(struct nfs_client *clp,
 	clp->rpc_ops = &nfs_v4_clientops;
 
 	error = nfs_create_rpc_client(clp, timeparms, authflavour,
-				      1, flags & NFS_MOUNT_NORESVPORT);
+				      1, noresvport);
 	if (error < 0)
 		goto error;
 	strlcpy(clp->cl_ipaddr, ip_addr, sizeof(clp->cl_ipaddr));
@@ -1378,27 +1398,71 @@ static int nfs4_set_client(struct nfs_server *server,
 	dprintk("--> nfs4_set_client()\n");
 
 	/* Allocate or find a client reference we can use */
-	clp = nfs_get_client(&cl_init);
+	clp = nfs_get_client(&cl_init, timeparms, ip_addr, authflavour,
+			     server->flags & NFS_MOUNT_NORESVPORT);
 	if (IS_ERR(clp)) {
 		error = PTR_ERR(clp);
 		goto error;
 	}
-	error = nfs4_init_client(clp, timeparms, ip_addr, authflavour,
-					server->flags);
-	if (error < 0)
-		goto error_put;
+
+	/*
+	 * Query for the lease time on clientid setup or renewal
+	 *
+	 * Note that this will be set on nfs_clients that were created
+	 * only for the DS role and did not set this bit, but now will
+	 * serve a dual role.
+	 */
+	set_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state);
 
 	server->nfs_client = clp;
 	dprintk("<-- nfs4_set_client() = 0 [new %p]\n", clp);
 	return 0;
-
-error_put:
-	nfs_put_client(clp);
 error:
 	dprintk("<-- nfs4_set_client() = xerror %d\n", error);
 	return error;
 }
 
+/*
+ * Set up a pNFS Data Server client.
+ *
+ * Return any existing nfs_client that matches server address,port,version
+ * and minorversion.
+ *
+ * For a new nfs_client, use a soft mount (default), a low retrans and a
+ * low timeout interval so that if a connection is lost, we retry through
+ * the MDS.
+ */
+struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
+		const struct sockaddr *ds_addr,
+		int ds_addrlen, int ds_proto)
+{
+	struct nfs_client_initdata cl_init = {
+		.addr = ds_addr,
+		.addrlen = ds_addrlen,
+		.rpc_ops = &nfs_v4_clientops,
+		.proto = ds_proto,
+		.minorversion = mds_clp->cl_minorversion,
+	};
+	struct rpc_timeout ds_timeout = {
+		.to_initval = 15 * HZ,
+		.to_maxval = 15 * HZ,
+		.to_retries = 1,
+		.to_exponential = 1,
+	};
+	struct nfs_client *clp;
+
+	/*
+	 * Set an authflavor equual to the MDS value. Use the MDS nfs_client
+	 * cl_ipaddr so as to use the same EXCHANGE_ID co_ownerid as the MDS
+	 * (section 13.1 RFC 5661).
+	 */
+	clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr,
+			     mds_clp->cl_rpcclient->cl_auth->au_flavor, 0);
+
+	dprintk("<-- %s %p\n", __func__, clp);
+	return clp;
+}
+EXPORT_SYMBOL(nfs4_set_ds_client);
 
 /*
  * Session has been established, and the client marked ready.
@@ -1435,6 +1499,10 @@ static int nfs4_server_common_setup(struct nfs_server *server,
 	BUG_ON(!server->nfs_client->rpc_ops);
 	BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
 
+	/* data servers support only a subset of NFSv4.1 */
+	if (is_ds_only_client(server->nfs_client))
+		return -EPROTONOSUPPORT;
+
 	fattr = nfs_alloc_fattr();
 	if (fattr == NULL)
 		return -ENOMEM;
@@ -1504,6 +1572,13 @@ static int nfs4_init_server(struct nfs_server *server,
 	if (error < 0)
 		goto error;
 
+	/*
+	 * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower
+	 * authentication.
+	 */
+	if (nfs4_disable_idmapping && data->auth_flavors[0] == RPC_AUTH_UNIX)
+		server->caps |= NFS_CAP_UIDGID_NOMAP;
+
 	if (data->rsize)
 		server->rsize = nfs_block_size(data->rsize, NULL);
 	if (data->wsize)
@@ -1921,3 +1996,7 @@ void nfs_fs_proc_exit(void)
 }
 
 #endif /* CONFIG_PROC_FS */
+
+module_param(nfs4_disable_idmapping, bool, 0644);
+MODULE_PARM_DESC(nfs4_disable_idmapping,
+		"Turn off NFSv4 idmapping when using 'sec=sys'");
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 9943a75bb6d..8eea2536671 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -45,6 +45,7 @@
 #include <linux/pagemap.h>
 #include <linux/kref.h>
 #include <linux/slab.h>
+#include <linux/task_io_accounting_ops.h>
 
 #include <linux/nfs_fs.h>
 #include <linux/nfs_page.h>
@@ -649,8 +650,7 @@ static void nfs_direct_write_result(struct rpc_task *task, void *calldata)
 {
 	struct nfs_write_data *data = calldata;
 
-	if (nfs_writeback_done(task, data) != 0)
-		return;
+	nfs_writeback_done(task, data);
 }
 
 /*
@@ -938,6 +938,8 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
 	if (retval)
 		goto out;
 
+	task_io_account_read(count);
+
 	retval = nfs_direct_read(iocb, iov, nr_segs, pos);
 	if (retval > 0)
 		iocb->ki_pos = pos + retval;
@@ -999,6 +1001,8 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 	if (retval)
 		goto out;
 
+	task_io_account_write(count);
+
 	retval = nfs_direct_write(iocb, iov, nr_segs, pos, count);
 
 	if (retval > 0)
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 7bf029ef408..d85a534b15c 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -387,10 +387,6 @@ 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/idmap.c b/fs/nfs/idmap.c
index 18696882f1c..79664a1025a 100644
--- a/fs/nfs/idmap.c
+++ b/fs/nfs/idmap.c
@@ -33,16 +33,41 @@
  *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
  *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+
+static int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *res)
+{
+	unsigned long val;
+	char buf[16];
+
+	if (memchr(name, '@', namelen) != NULL || namelen >= sizeof(buf))
+		return 0;
+	memcpy(buf, name, namelen);
+	buf[namelen] = '\0';
+	if (strict_strtoul(buf, 0, &val) != 0)
+		return 0;
+	*res = val;
+	return 1;
+}
+
+static int nfs_map_numeric_to_string(__u32 id, char *buf, size_t buflen)
+{
+	return snprintf(buf, buflen, "%u", id);
+}
 
 #ifdef CONFIG_NFS_USE_NEW_IDMAPPER
 
 #include <linux/slab.h>
 #include <linux/cred.h>
+#include <linux/sunrpc/sched.h>
+#include <linux/nfs4.h>
+#include <linux/nfs_fs_sb.h>
 #include <linux/nfs_idmap.h>
 #include <linux/keyctl.h>
 #include <linux/key-type.h>
 #include <linux/rcupdate.h>
-#include <linux/kernel.h>
 #include <linux/err.h>
 
 #include <keys/user-type.h>
@@ -219,23 +244,39 @@ static int nfs_idmap_lookup_id(const char *name, size_t namelen,
 	return ret;
 }
 
-int nfs_map_name_to_uid(struct nfs_client *clp, const char *name, size_t namelen, __u32 *uid)
+int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *uid)
 {
+	if (nfs_map_string_to_numeric(name, namelen, uid))
+		return 0;
 	return nfs_idmap_lookup_id(name, namelen, "uid", uid);
 }
 
-int nfs_map_group_to_gid(struct nfs_client *clp, const char *name, size_t namelen, __u32 *gid)
+int nfs_map_group_to_gid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *gid)
 {
+	if (nfs_map_string_to_numeric(name, namelen, gid))
+		return 0;
 	return nfs_idmap_lookup_id(name, namelen, "gid", gid);
 }
 
-int nfs_map_uid_to_name(struct nfs_client *clp, __u32 uid, char *buf, size_t buflen)
+int nfs_map_uid_to_name(const struct nfs_server *server, __u32 uid, char *buf, size_t buflen)
 {
-	return nfs_idmap_lookup_name(uid, "user", buf, buflen);
+	int ret = -EINVAL;
+
+	if (!(server->caps & NFS_CAP_UIDGID_NOMAP))
+		ret = nfs_idmap_lookup_name(uid, "user", buf, buflen);
+	if (ret < 0)
+		ret = nfs_map_numeric_to_string(uid, buf, buflen);
+	return ret;
 }
-int nfs_map_gid_to_group(struct nfs_client *clp, __u32 gid, char *buf, size_t buflen)
+int nfs_map_gid_to_group(const struct nfs_server *server, __u32 gid, char *buf, size_t buflen)
 {
-	return nfs_idmap_lookup_name(gid, "group", buf, buflen);
+	int ret = -EINVAL;
+
+	if (!(server->caps & NFS_CAP_UIDGID_NOMAP))
+		ret = nfs_idmap_lookup_name(gid, "group", buf, buflen);
+	if (ret < 0)
+		ret = nfs_map_numeric_to_string(gid, buf, buflen);
+	return ret;
 }
 
 #else  /* CONFIG_NFS_USE_NEW_IDMAPPER not defined */
@@ -243,7 +284,6 @@ int nfs_map_gid_to_group(struct nfs_client *clp, __u32 gid, char *buf, size_t bu
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/init.h>
-#include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/socket.h>
 #include <linux/in.h>
@@ -695,31 +735,45 @@ static unsigned int fnvhash32(const void *buf, size_t buflen)
 	return hash;
 }
 
-int nfs_map_name_to_uid(struct nfs_client *clp, const char *name, size_t namelen, __u32 *uid)
+int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *uid)
 {
-	struct idmap *idmap = clp->cl_idmap;
+	struct idmap *idmap = server->nfs_client->cl_idmap;
 
+	if (nfs_map_string_to_numeric(name, namelen, uid))
+		return 0;
 	return nfs_idmap_id(idmap, &idmap->idmap_user_hash, name, namelen, uid);
 }
 
-int nfs_map_group_to_gid(struct nfs_client *clp, const char *name, size_t namelen, __u32 *uid)
+int nfs_map_group_to_gid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *uid)
 {
-	struct idmap *idmap = clp->cl_idmap;
+	struct idmap *idmap = server->nfs_client->cl_idmap;
 
+	if (nfs_map_string_to_numeric(name, namelen, uid))
+		return 0;
 	return nfs_idmap_id(idmap, &idmap->idmap_group_hash, name, namelen, uid);
 }
 
-int nfs_map_uid_to_name(struct nfs_client *clp, __u32 uid, char *buf, size_t buflen)
+int nfs_map_uid_to_name(const struct nfs_server *server, __u32 uid, char *buf, size_t buflen)
 {
-	struct idmap *idmap = clp->cl_idmap;
+	struct idmap *idmap = server->nfs_client->cl_idmap;
+	int ret = -EINVAL;
 
-	return nfs_idmap_name(idmap, &idmap->idmap_user_hash, uid, buf);
+	if (!(server->caps & NFS_CAP_UIDGID_NOMAP))
+		ret = nfs_idmap_name(idmap, &idmap->idmap_user_hash, uid, buf);
+	if (ret < 0)
+		ret = nfs_map_numeric_to_string(uid, buf, buflen);
+	return ret;
 }
-int nfs_map_gid_to_group(struct nfs_client *clp, __u32 uid, char *buf, size_t buflen)
+int nfs_map_gid_to_group(const struct nfs_server *server, __u32 uid, char *buf, size_t buflen)
 {
-	struct idmap *idmap = clp->cl_idmap;
+	struct idmap *idmap = server->nfs_client->cl_idmap;
+	int ret = -EINVAL;
 
-	return nfs_idmap_name(idmap, &idmap->idmap_group_hash, uid, buf);
+	if (!(server->caps & NFS_CAP_UIDGID_NOMAP))
+		ret = nfs_idmap_name(idmap, &idmap->idmap_group_hash, uid, buf);
+	if (ret < 0)
+		ret = nfs_map_numeric_to_string(uid, buf, buflen);
+	return ret;
 }
 
 #endif /* CONFIG_NFS_USE_NEW_IDMAPPER */
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index e94ad22da5d..72e0bddf7a2 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -148,6 +148,9 @@ extern struct nfs_server *nfs_clone_server(struct nfs_server *,
 					   struct nfs_fattr *);
 extern void nfs_mark_client_ready(struct nfs_client *clp, int state);
 extern int nfs4_check_client_ready(struct nfs_client *clp);
+extern struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
+					     const struct sockaddr *ds_addr,
+					     int ds_addrlen, int ds_proto);
 #ifdef CONFIG_PROC_FS
 extern int __init nfs_fs_proc_init(void);
 extern void nfs_fs_proc_exit(void);
@@ -213,8 +216,14 @@ extern const u32 nfs41_maxwrite_overhead;
 extern struct rpc_procinfo nfs4_procedures[];
 #endif
 
+extern int nfs4_init_ds_session(struct nfs_client *clp);
+
 /* proc.c */
 void nfs_close_context(struct nfs_open_context *ctx, int is_sync);
+extern int nfs_init_client(struct nfs_client *clp,
+			   const struct rpc_timeout *timeparms,
+			   const char *ip_addr, rpc_authflavor_t authflavour,
+			   int noresvport);
 
 /* dir.c */
 extern int nfs_access_cache_shrinker(struct shrinker *shrink,
@@ -262,9 +271,15 @@ extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh);
 #endif
 
 /* read.c */
+extern int nfs_initiate_read(struct nfs_read_data *data, struct rpc_clnt *clnt,
+			     const struct rpc_call_ops *call_ops);
 extern void nfs_read_prepare(struct rpc_task *task, void *calldata);
 
 /* write.c */
+extern int nfs_initiate_write(struct nfs_write_data *data,
+			      struct rpc_clnt *clnt,
+			      const struct rpc_call_ops *call_ops,
+			      int how);
 extern void nfs_write_prepare(struct rpc_task *task, void *calldata);
 #ifdef CONFIG_MIGRATION
 extern int nfs_migrate_page(struct address_space *,
@@ -274,6 +289,13 @@ extern int nfs_migrate_page(struct address_space *,
 #endif
 
 /* nfs4proc.c */
+extern void nfs4_reset_read(struct rpc_task *task, struct nfs_read_data *data);
+extern int nfs4_init_client(struct nfs_client *clp,
+			    const struct rpc_timeout *timeparms,
+			    const char *ip_addr,
+			    rpc_authflavor_t authflavour,
+			    int noresvport);
+extern void nfs4_reset_write(struct rpc_task *task, struct nfs_write_data *data);
 extern int _nfs4_call_sync(struct nfs_server *server,
 			   struct rpc_message *msg,
 			   struct nfs4_sequence_args *args,
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index ce939c062a5..d0c80d8b3f9 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -885,4 +885,5 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
 	.lock		= nfs3_proc_lock,
 	.clear_acl_cache = nfs3_forget_cached_acls,
 	.close_context	= nfs_close_context,
+	.init_client	= nfs_init_client,
 };
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 1be36cf65bf..c64be1cff08 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -252,6 +252,9 @@ static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *ser
 extern int nfs4_setup_sequence(const struct nfs_server *server,
 		struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
 		int cache_reply, struct rpc_task *task);
+extern int nfs41_setup_sequence(struct nfs4_session *session,
+		struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
+		int cache_reply, struct rpc_task *task);
 extern void nfs4_destroy_session(struct nfs4_session *session);
 extern struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp);
 extern int nfs4_proc_create_session(struct nfs_client *);
@@ -259,6 +262,19 @@ extern int nfs4_proc_destroy_session(struct nfs4_session *);
 extern int nfs4_init_session(struct nfs_server *server);
 extern int nfs4_proc_get_lease_time(struct nfs_client *clp,
 		struct nfs_fsinfo *fsinfo);
+
+static inline bool
+is_ds_only_client(struct nfs_client *clp)
+{
+	return (clp->cl_exchange_flags & EXCHGID4_FLAG_MASK_PNFS) ==
+		EXCHGID4_FLAG_USE_PNFS_DS;
+}
+
+static inline bool
+is_ds_client(struct nfs_client *clp)
+{
+	return clp->cl_exchange_flags & EXCHGID4_FLAG_USE_PNFS_DS;
+}
 #else /* CONFIG_NFS_v4_1 */
 static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *server)
 {
@@ -276,6 +292,18 @@ static inline int nfs4_init_session(struct nfs_server *server)
 {
 	return 0;
 }
+
+static inline bool
+is_ds_only_client(struct nfs_client *clp)
+{
+	return false;
+}
+
+static inline bool
+is_ds_client(struct nfs_client *clp)
+{
+	return false;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 extern const struct nfs4_minor_version_ops *nfs_v4_minor_ops[];
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index 23f930caf1e..42855846481 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -40,32 +40,309 @@ 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)
+#define FILELAYOUT_POLL_RETRY_MAX     (15*HZ)
+
+static loff_t
+filelayout_get_dense_offset(struct nfs4_filelayout_segment *flseg,
+			    loff_t offset)
 {
-	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;
+	u32 stripe_width = flseg->stripe_unit * flseg->dsaddr->stripe_count;
+	u64 tmp;
+
+	offset -= flseg->pattern_offset;
+	tmp = offset;
+	do_div(tmp, stripe_width);
+
+	return tmp * flseg->stripe_unit + do_div(offset, flseg->stripe_unit);
+}
+
+/* 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);
 	}
-	dprintk("%s: deviceid cache has been initialized successfully\n",
-		__func__);
+
+	BUG();
+}
+
+/* For data server errors we don't recover from */
+static void
+filelayout_set_lo_fail(struct pnfs_layout_segment *lseg)
+{
+	if (lseg->pls_range.iomode == IOMODE_RW) {
+		dprintk("%s Setting layout IOMODE_RW fail bit\n", __func__);
+		set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
+	} else {
+		dprintk("%s Setting layout IOMODE_READ fail bit\n", __func__);
+		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
+	}
+}
+
+static int filelayout_async_handle_error(struct rpc_task *task,
+					 struct nfs4_state *state,
+					 struct nfs_client *clp,
+					 int *reset)
+{
+	if (task->tk_status >= 0)
+		return 0;
+
+	*reset = 0;
+
+	switch (task->tk_status) {
+	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);
+		break;
+	case -NFS4ERR_DELAY:
+	case -NFS4ERR_GRACE:
+	case -EKEYEXPIRED:
+		rpc_delay(task, FILELAYOUT_POLL_RETRY_MAX);
+		break;
+	default:
+		dprintk("%s DS error. Retry through MDS %d\n", __func__,
+			task->tk_status);
+		*reset = 1;
+		break;
+	}
+	task->tk_status = 0;
+	return -EAGAIN;
+}
+
+/* NFS_PROTO call done callback routines */
+
+static int filelayout_read_done_cb(struct rpc_task *task,
+				struct nfs_read_data *data)
+{
+	struct nfs_client *clp = data->ds_clp;
+	int reset = 0;
+
+	dprintk("%s DS read\n", __func__);
+
+	if (filelayout_async_handle_error(task, data->args.context->state,
+					  data->ds_clp, &reset) == -EAGAIN) {
+		dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n",
+			__func__, data->ds_clp, data->ds_clp->cl_session);
+		if (reset) {
+			filelayout_set_lo_fail(data->lseg);
+			nfs4_reset_read(task, data);
+			clp = NFS_SERVER(data->inode)->nfs_client;
+		}
+		nfs_restart_rpc(task, clp);
+		return -EAGAIN;
+	}
+
 	return 0;
 }
 
-/* Clear out the layout by destroying its device list */
-static int
-filelayout_clear_layoutdriver(struct nfs_server *nfss)
+/*
+ * 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)
 {
-	dprintk("--> %s\n", __func__);
+	struct nfs_read_data *rdata = (struct nfs_read_data *)data;
+
+	rdata->read_done_cb = filelayout_read_done_cb;
+
+	if (nfs41_setup_sequence(rdata->ds_clp->cl_session,
+				&rdata->args.seq_args, &rdata->res.seq_res,
+				0, task))
+		return;
+
+	rpc_call_start(task);
+}
+
+static void filelayout_read_call_done(struct rpc_task *task, void *data)
+{
+	struct nfs_read_data *rdata = (struct nfs_read_data *)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);
+}
+
+static void filelayout_read_release(void *data)
+{
+	struct nfs_read_data *rdata = (struct nfs_read_data *)data;
+
+	rdata->mds_ops->rpc_release(data);
+}
+
+static int filelayout_write_done_cb(struct rpc_task *task,
+				struct nfs_write_data *data)
+{
+	int reset = 0;
+
+	if (filelayout_async_handle_error(task, data->args.context->state,
+					  data->ds_clp, &reset) == -EAGAIN) {
+		struct nfs_client *clp;
+
+		dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n",
+			__func__, data->ds_clp, data->ds_clp->cl_session);
+		if (reset) {
+			filelayout_set_lo_fail(data->lseg);
+			nfs4_reset_write(task, data);
+			clp = NFS_SERVER(data->inode)->nfs_client;
+		} else
+			clp = data->ds_clp;
+		nfs_restart_rpc(task, clp);
+		return -EAGAIN;
+	}
 
-	if (nfss->nfs_client->cl_devid_cache)
-		pnfs_put_deviceid_cache(nfss->nfs_client);
 	return 0;
 }
 
+static void filelayout_write_prepare(struct rpc_task *task, void *data)
+{
+	struct nfs_write_data *wdata = (struct nfs_write_data *)data;
+
+	if (nfs41_setup_sequence(wdata->ds_clp->cl_session,
+				&wdata->args.seq_args, &wdata->res.seq_res,
+				0, task))
+		return;
+
+	rpc_call_start(task);
+}
+
+static void filelayout_write_call_done(struct rpc_task *task, void *data)
+{
+	struct nfs_write_data *wdata = (struct nfs_write_data *)data;
+
+	/* Note this may cause RPC to be resent */
+	wdata->mds_ops->rpc_call_done(task, data);
+}
+
+static void filelayout_write_release(void *data)
+{
+	struct nfs_write_data *wdata = (struct nfs_write_data *)data;
+
+	wdata->mds_ops->rpc_release(data);
+}
+
+struct rpc_call_ops filelayout_read_call_ops = {
+	.rpc_call_prepare = filelayout_read_prepare,
+	.rpc_call_done = filelayout_read_call_done,
+	.rpc_release = filelayout_read_release,
+};
+
+struct rpc_call_ops filelayout_write_call_ops = {
+	.rpc_call_prepare = filelayout_write_prepare,
+	.rpc_call_done = filelayout_write_call_done,
+	.rpc_release = filelayout_write_release,
+};
+
+static enum pnfs_try_status
+filelayout_read_pagelist(struct nfs_read_data *data)
+{
+	struct pnfs_layout_segment *lseg = data->lseg;
+	struct nfs4_pnfs_ds *ds;
+	loff_t offset = data->args.offset;
+	u32 j, idx;
+	struct nfs_fh *fh;
+	int status;
+
+	dprintk("--> %s ino %lu pgbase %u req %Zu@%llu\n",
+		__func__, data->inode->i_ino,
+		data->args.pgbase, (size_t)data->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) {
+		/* Either layout fh index faulty, or ds connect failed */
+		set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
+		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
+		return PNFS_NOT_ATTEMPTED;
+	}
+	dprintk("%s USE DS:ip %x %hu\n", __func__,
+		ntohl(ds->ds_ip_addr), ntohs(ds->ds_port));
+
+	/* No multipath support. Use first DS */
+	data->ds_clp = ds->ds_clp;
+	fh = nfs4_fl_select_ds_fh(lseg, j);
+	if (fh)
+		data->args.fh = fh;
+
+	data->args.offset = filelayout_get_dserver_offset(lseg, offset);
+	data->mds_offset = offset;
+
+	/* Perform an asynchronous read to ds */
+	status = nfs_initiate_read(data, ds->ds_clp->cl_rpcclient,
+				   &filelayout_read_call_ops);
+	BUG_ON(status != 0);
+	return PNFS_ATTEMPTED;
+}
+
+/* Perform async writes. */
+static enum pnfs_try_status
+filelayout_write_pagelist(struct nfs_write_data *data, int sync)
+{
+	struct pnfs_layout_segment *lseg = data->lseg;
+	struct nfs4_pnfs_ds *ds;
+	loff_t offset = data->args.offset;
+	u32 j, idx;
+	struct nfs_fh *fh;
+	int status;
+
+	/* 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) {
+		printk(KERN_ERR "%s: prepare_ds failed, use MDS\n", __func__);
+		set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
+		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
+		return PNFS_NOT_ATTEMPTED;
+	}
+	dprintk("%s ino %lu sync %d req %Zu@%llu DS:%x:%hu\n", __func__,
+		data->inode->i_ino, sync, (size_t) data->args.count, offset,
+		ntohl(ds->ds_ip_addr), ntohs(ds->ds_port));
+
+	/* We can't handle commit to ds yet */
+	if (!FILELAYOUT_LSEG(lseg)->commit_through_mds)
+		data->args.stable = NFS_FILE_SYNC;
+
+	data->write_done_cb = filelayout_write_done_cb;
+	data->ds_clp = ds->ds_clp;
+	fh = nfs4_fl_select_ds_fh(lseg, j);
+	if (fh)
+		data->args.fh = fh;
+	/*
+	 * Get the file offset on the dserver. Set the write offset to
+	 * this offset and save the original offset.
+	 */
+	data->args.offset = filelayout_get_dserver_offset(lseg, offset);
+	data->mds_offset = offset;
+
+	/* Perform an asynchronous write */
+	status = nfs_initiate_write(data, ds->ds_clp->cl_rpcclient,
+				    &filelayout_write_call_ops, sync);
+	BUG_ON(status != 0);
+	return PNFS_ATTEMPTED;
+