21 files changed, 1494 insertions, 434 deletions

diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 81515545ba7..2cde5d95475 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -77,6 +77,7 @@ config NFS_V4
 config NFS_V4_1
 	bool "NFS client support for NFSv4.1 (EXPERIMENTAL)"
 	depends on NFS_FS && NFS_V4 && EXPERIMENTAL
+	select SUNRPC_BACKCHANNEL
 	select PNFS_FILE_LAYOUT
 	help
 	  This option enables support for minor version 1 of the NFSv4 protocol
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index d4d1954e9bb..74780f9f852 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -111,6 +111,7 @@ int nfs4_validate_delegation_stateid(struct nfs_delegation *delegation, const nf
 static u32 initiate_file_draining(struct nfs_client *clp,
 				  struct cb_layoutrecallargs *args)
 {
+	struct nfs_server *server;
 	struct pnfs_layout_hdr *lo;
 	struct inode *ino;
 	bool found = false;
@@ -118,21 +119,28 @@ static u32 initiate_file_draining(struct nfs_client *clp,
 	LIST_HEAD(free_me_list);
 
 	spin_lock(&clp->cl_lock);
-	list_for_each_entry(lo, &clp->cl_layouts, plh_layouts) {
-		if (nfs_compare_fh(&args->cbl_fh,
-				   &NFS_I(lo->plh_inode)->fh))
-			continue;
-		ino = igrab(lo->plh_inode);
-		if (!ino)
-			continue;
-		found = true;
-		/* Without this, layout can be freed as soon
-		 * as we release cl_lock.
-		 */
-		get_layout_hdr(lo);
-		break;
+	rcu_read_lock();
+	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
+		list_for_each_entry(lo, &server->layouts, plh_layouts) {
+			if (nfs_compare_fh(&args->cbl_fh,
+					   &NFS_I(lo->plh_inode)->fh))
+				continue;
+			ino = igrab(lo->plh_inode);
+			if (!ino)
+				continue;
+			found = true;
+			/* Without this, layout can be freed as soon
+			 * as we release cl_lock.
+			 */
+			get_layout_hdr(lo);
+			break;
+		}
+		if (found)
+			break;
 	}
+	rcu_read_unlock();
 	spin_unlock(&clp->cl_lock);
+
 	if (!found)
 		return NFS4ERR_NOMATCHING_LAYOUT;
 
@@ -154,6 +162,7 @@ static u32 initiate_file_draining(struct nfs_client *clp,
 static u32 initiate_bulk_draining(struct nfs_client *clp,
 				  struct cb_layoutrecallargs *args)
 {
+	struct nfs_server *server;
 	struct pnfs_layout_hdr *lo;
 	struct inode *ino;
 	u32 rv = NFS4ERR_NOMATCHING_LAYOUT;
@@ -167,18 +176,24 @@ static u32 initiate_bulk_draining(struct nfs_client *clp,
 	};
 
 	spin_lock(&clp->cl_lock);
-	list_for_each_entry(lo, &clp->cl_layouts, plh_layouts) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
 		if ((args->cbl_recall_type == RETURN_FSID) &&
-		    memcmp(&NFS_SERVER(lo->plh_inode)->fsid,
-			   &args->cbl_fsid, sizeof(struct nfs_fsid)))
-			continue;
-		if (!igrab(lo->plh_inode))
+		    memcmp(&server->fsid, &args->cbl_fsid,
+			   sizeof(struct nfs_fsid)))
 			continue;
-		get_layout_hdr(lo);
-		BUG_ON(!list_empty(&lo->plh_bulk_recall));
-		list_add(&lo->plh_bulk_recall, &recall_list);
+
+		list_for_each_entry(lo, &server->layouts, plh_layouts) {
+			if (!igrab(lo->plh_inode))
+				continue;
+			get_layout_hdr(lo);
+			BUG_ON(!list_empty(&lo->plh_bulk_recall));
+			list_add(&lo->plh_bulk_recall, &recall_list);
+		}
 	}
+	rcu_read_unlock();
 	spin_unlock(&clp->cl_lock);
+
 	list_for_each_entry_safe(lo, tmp,
 				 &recall_list, plh_bulk_recall) {
 		ino = lo->plh_inode;
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index b3dc2b88b65..19ea7d9c75e 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -188,9 +188,6 @@ 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;
@@ -293,6 +290,7 @@ static void nfs_free_client(struct nfs_client *clp)
 	nfs4_deviceid_purge_client(clp);
 
 	kfree(clp->cl_hostname);
+	kfree(clp->server_scope);
 	kfree(clp);
 
 	dprintk("<-- nfs_free_client()\n");
@@ -1062,6 +1060,7 @@ static struct nfs_server *nfs_alloc_server(void)
 	INIT_LIST_HEAD(&server->client_link);
 	INIT_LIST_HEAD(&server->master_link);
 	INIT_LIST_HEAD(&server->delegations);
+	INIT_LIST_HEAD(&server->layouts);
 
 	atomic_set(&server->active, 0);
 
@@ -1464,7 +1463,7 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
 	dprintk("<-- %s %p\n", __func__, clp);
 	return clp;
 }
-EXPORT_SYMBOL(nfs4_set_ds_client);
+EXPORT_SYMBOL_GPL(nfs4_set_ds_client);
 
 /*
  * Session has been established, and the client marked ready.
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index dd25c2aec37..321a66bc384 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -398,12 +398,11 @@ int nfs_inode_return_delegation(struct inode *inode)
 	return err;
 }
 
-static void nfs_mark_return_delegation(struct nfs_delegation *delegation)
+static void nfs_mark_return_delegation(struct nfs_server *server,
+		struct nfs_delegation *delegation)
 {
-	struct nfs_client *clp = NFS_SERVER(delegation->inode)->nfs_client;
-
 	set_bit(NFS_DELEGATION_RETURN, &delegation->flags);
-	set_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state);
+	set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state);
 }
 
 /**
@@ -441,7 +440,7 @@ static void nfs_mark_return_all_delegation_types(struct nfs_server *server,
 		if ((delegation->type == (FMODE_READ|FMODE_WRITE)) && !(flags & FMODE_WRITE))
 			continue;
 		if (delegation->type & flags)
-			nfs_mark_return_delegation(delegation);
+			nfs_mark_return_delegation(server, delegation);
 	}
 }
 
@@ -508,7 +507,7 @@ static void nfs_mark_return_unreferenced_delegations(struct nfs_server *server)
 	list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
 		if (test_and_clear_bit(NFS_DELEGATION_REFERENCED, &delegation->flags))
 			continue;
-		nfs_mark_return_delegation(delegation);
+		nfs_mark_return_delegation(server, delegation);
 	}
 }
 
@@ -539,7 +538,8 @@ void nfs_expire_unreferenced_delegations(struct nfs_client *clp)
 int nfs_async_inode_return_delegation(struct inode *inode,
 				      const nfs4_stateid *stateid)
 {
-	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
+	struct nfs_server *server = NFS_SERVER(inode);
+	struct nfs_client *clp = server->nfs_client;
 	struct nfs_delegation *delegation;
 
 	rcu_read_lock();
@@ -549,7 +549,7 @@ int nfs_async_inode_return_delegation(struct inode *inode,
 		rcu_read_unlock();
 		return -ENOENT;
 	}
-	nfs_mark_return_delegation(delegation);
+	nfs_mark_return_delegation(server, delegation);
 	rcu_read_unlock();
 
 	nfs_delegation_run_state_manager(clp);
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 2a55347a2da..ab12913dd47 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -277,6 +277,9 @@ extern void nfs_sb_deactive(struct super_block *sb);
 extern char *nfs_path(char **p, struct dentry *dentry,
 		      char *buffer, ssize_t buflen);
 extern struct vfsmount *nfs_d_automount(struct path *path);
+#ifdef CONFIG_NFS_V4
+rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *);
+#endif
 
 /* getroot.c */
 extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *,
@@ -288,12 +291,22 @@ extern struct dentry *nfs4_get_root(struct super_block *, struct nfs_fh *,
 extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh);
 #endif
 
+struct nfs_pageio_descriptor;
 /* 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);
+extern int nfs_generic_pagein(struct nfs_pageio_descriptor *desc,
+		struct list_head *head);
+
+extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
+extern void nfs_readdata_release(struct nfs_read_data *rdata);
 
 /* write.c */
+extern int nfs_generic_flush(struct nfs_pageio_descriptor *desc,
+		struct list_head *head);
+extern void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio);
+extern void nfs_writedata_release(struct nfs_write_data *wdata);
 extern void nfs_commit_free(struct nfs_write_data *p);
 extern int nfs_initiate_write(struct nfs_write_data *data,
 			      struct rpc_clnt *clnt,
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 1f063bacd28..8102391bb37 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -119,7 +119,7 @@ Elong:
 }
 
 #ifdef CONFIG_NFS_V4
-static rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors)
+rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors)
 {
 	struct gss_api_mech *mech;
 	struct xdr_netobj oid;
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index b788f2eb1ba..1909ee8be35 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -48,6 +48,7 @@ enum nfs4_client_state {
 	NFS4CLNT_SESSION_RESET,
 	NFS4CLNT_RECALL_SLOT,
 	NFS4CLNT_LEASE_CONFIRM,
+	NFS4CLNT_SERVER_SCOPE_MISMATCH,
 };
 
 enum nfs4_session_state {
@@ -66,6 +67,8 @@ struct nfs4_minor_version_ops {
 			int cache_reply);
 	int	(*validate_stateid)(struct nfs_delegation *,
 			const nfs4_stateid *);
+	int	(*find_root_sec)(struct nfs_server *, struct nfs_fh *,
+			struct nfs_fsinfo *);
 	const struct nfs4_state_recovery_ops *reboot_recovery_ops;
 	const struct nfs4_state_recovery_ops *nograce_recovery_ops;
 	const struct nfs4_state_maintenance_ops *state_renewal_ops;
@@ -349,6 +352,8 @@ extern void nfs4_schedule_state_manager(struct nfs_client *);
 extern void nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs4_state *);
 extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags);
 extern void nfs41_handle_recall_slot(struct nfs_client *clp);
+extern void nfs41_handle_server_scope(struct nfs_client *,
+				      struct server_scope **);
 extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp);
 extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl);
 extern void nfs4_copy_stateid(nfs4_stateid *, struct nfs4_state *, fl_owner_t, pid_t);
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index f9d03abcd04..be93a622872 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -334,6 +334,9 @@ filelayout_read_pagelist(struct nfs_read_data *data)
 		__func__, data->inode->i_ino,
 		data->args.pgbase, (size_t)data->args.count, offset);
 
+	if (test_bit(NFS_DEVICEID_INVALID, &FILELAYOUT_DEVID_NODE(lseg)->flags))
+		return PNFS_NOT_ATTEMPTED;
+
 	/* 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);
@@ -344,8 +347,7 @@ filelayout_read_pagelist(struct nfs_read_data *data)
 		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));
+	dprintk("%s USE DS: %s\n", __func__, ds->ds_remotestr);
 
 	/* No multipath support. Use first DS */
 	data->ds_clp = ds->ds_clp;
@@ -374,6 +376,9 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync)
 	struct nfs_fh *fh;
 	int status;
 
+	if (test_bit(NFS_DEVICEID_INVALID, &FILELAYOUT_DEVID_NODE(lseg)->flags))
+		return PNFS_NOT_ATTEMPTED;
+
 	/* 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);
@@ -384,9 +389,9 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync)
 		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__,
+	dprintk("%s ino %lu sync %d req %Zu@%llu DS: %s\n", __func__,
 		data->inode->i_ino, sync, (size_t) data->args.count, offset,
-		ntohl(ds->ds_ip_addr), ntohs(ds->ds_port));
+		ds->ds_remotestr);
 
 	data->write_done_cb = filelayout_write_done_cb;
 	data->ds_clp = ds->ds_clp;
@@ -428,6 +433,14 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
 
 	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);
@@ -449,6 +462,10 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
 			goto out;
 	} else
 		dsaddr = container_of(d, struct nfs4_file_layout_dsaddr, id_node);
+	/* Found deviceid is being reaped */
+	if (test_bit(NFS_DEVICEID_INVALID, &dsaddr->id_node.flags))
+			goto out_put;
+
 	fl->dsaddr = dsaddr;
 
 	if (fl->first_stripe_index < 0 ||
@@ -659,7 +676,7 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
  * return true  : coalesce page
  * return false : don't coalesce page
  */
-bool
+static bool
 filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 		   struct nfs_page *req)
 {
@@ -670,8 +687,6 @@ filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 	    !nfs_generic_pg_test(pgio, prev, req))
 		return false;
 
-	if (!pgio->pg_lseg)
-		return 1;
 	p_stripe = (u64)prev->wb_index << PAGE_CACHE_SHIFT;
 	r_stripe = (u64)req->wb_index << PAGE_CACHE_SHIFT;
 	stripe_unit = FILELAYOUT_LSEG(pgio->pg_lseg)->stripe_unit;
@@ -682,6 +697,52 @@ filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 	return (p_stripe == r_stripe);
 }
 
+void
+filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
+			struct nfs_page *req)
+{
+	BUG_ON(pgio->pg_lseg != NULL);
+
+	pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
+					   req->wb_context,
+					   0,
+					   NFS4_MAX_UINT64,
+					   IOMODE_READ,
+					   GFP_KERNEL);
+	/* If no lseg, fall back to read through mds */
+	if (pgio->pg_lseg == NULL)
+		nfs_pageio_reset_read_mds(pgio);
+}
+
+void
+filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
+			 struct nfs_page *req)
+{
+	BUG_ON(pgio->pg_lseg != NULL);
+
+	pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
+					   req->wb_context,
+					   0,
+					   NFS4_MAX_UINT64,
+					   IOMODE_RW,
+					   GFP_NOFS);
+	/* If no lseg, fall back to write through mds */
+	if (pgio->pg_lseg == NULL)
+		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,
+};
+
+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,
+};
+
 static bool filelayout_mark_pnfs_commit(struct pnfs_layout_segment *lseg)
 {
 	return !FILELAYOUT_LSEG(lseg)->commit_through_mds;
@@ -879,7 +940,8 @@ static struct pnfs_layoutdriver_type filelayout_type = {
 	.owner			= THIS_MODULE,
 	.alloc_lseg		= filelayout_alloc_lseg,
 	.free_lseg		= filelayout_free_lseg,
-	.pg_test		= filelayout_pg_test,
+	.pg_read_ops		= &filelayout_pg_read_ops,
+	.pg_write_ops		= &filelayout_pg_write_ops,
 	.mark_pnfs_commit	= filelayout_mark_pnfs_commit,
 	.choose_commit_list	= filelayout_choose_commit_list,
 	.commit_pagelist	= filelayout_commit_pagelist,
@@ -902,5 +964,7 @@ static void __exit nfs4filelayout_exit(void)
 	pnfs_unregister_layoutdriver(&filelayout_type);
 }
 
+MODULE_ALIAS("nfs-layouttype4-1");
+
 module_init(nfs4filelayout_init);
 module_exit(nfs4filelayout_exit);
diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h
index cebe01e3795..2e42284253f 100644
--- a/fs/nfs/nfs4filelayout.h
+++ b/fs/nfs/nfs4filelayout.h
@@ -47,10 +47,17 @@ enum stripetype4 {
 };
 
 /* Individual ip address */
+struct nfs4_pnfs_ds_addr {
+	struct sockaddr_storage	da_addr;
+	size_t			da_addrlen;
+	struct list_head	da_node;  /* nfs4_pnfs_dev_hlist dev_dslist */
+	char			*da_remotestr;	/* human readable addr+port */
+};
+
 struct nfs4_pnfs_ds {
 	struct list_head	ds_node;  /* nfs4_pnfs_dev_hlist dev_dslist */
-	u32			ds_ip_addr;
-	u32			ds_port;
+	char			*ds_remotestr;	/* comma sep list of addrs */
+	struct list_head	ds_addrs;
 	struct nfs_client	*ds_clp;
 	atomic_t		ds_count;
 };
@@ -89,6 +96,12 @@ FILELAYOUT_LSEG(struct pnfs_layout_segment *lseg)
 			    generic_hdr);
 }
 
+static inline struct nfs4_deviceid_node *
+FILELAYOUT_DEVID_NODE(struct pnfs_layout_segment *lseg)
+{
+	return &FILELAYOUT_LSEG(lseg)->dsaddr->id_node;
+}
+
 extern struct nfs_fh *
 nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j);
 
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index 3b7bf137726..ed388aae968 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -56,54 +56,139 @@ print_ds(struct nfs4_pnfs_ds *ds)
 		printk("%s NULL device\n", __func__);
 		return;
 	}
-	printk("        ip_addr %x port %hu\n"
+	printk("        ds %s\n"
 		"        ref count %d\n"
 		"        client %p\n"
 		"        cl_exchange_flags %x\n",
-		ntohl(ds->ds_ip_addr), ntohs(ds->ds_port),
+		ds->ds_remotestr,
 		atomic_read(&ds->ds_count), ds->ds_clp,
 		ds->ds_clp ? ds->ds_clp->cl_exchange_flags : 0);
 }
 
-/* nfs4_ds_cache_lock is held */
-static struct nfs4_pnfs_ds *
-_data_server_lookup_locked(u32 ip_addr, u32 port)
+static bool
+same_sockaddr(struct sockaddr *addr1, struct sockaddr *addr2)
 {
-	struct nfs4_pnfs_ds *ds;
+	struct sockaddr_in *a, *b;
+	struct sockaddr_in6 *a6, *b6;
+
+	if (addr1->sa_family != addr2->sa_family)
+		return false;
+
+	switch (addr1->sa_family) {
+	case AF_INET:
+		a = (struct sockaddr_in *)addr1;
+		b = (struct sockaddr_in *)addr2;
+
+		if (a->sin_addr.s_addr == b->sin_addr.s_addr &&
+		    a->sin_port == b->sin_port)
+			return true;
+		break;
+
+	case AF_INET6:
+		a6 = (struct sockaddr_in6 *)addr1;
+		b6 = (struct sockaddr_in6 *)addr2;
+
+		/* LINKLOCAL addresses must have matching scope_id */
+		if (ipv6_addr_scope(&a6->sin6_addr) ==
+		    IPV6_ADDR_SCOPE_LINKLOCAL &&
+		    a6->sin6_scope_id != b6->sin6_scope_id)
+			return false;
+
+		if (ipv6_addr_equal(&a6->sin6_addr, &b6->sin6_addr) &&
+		    a6->sin6_port == b6->sin6_port)
+			return true;
+		break;
+
+	default:
+		dprintk("%s: unhandled address family: %u\n",
+			__func__, addr1->sa_family);
+		return false;
+	}
 
-	dprintk("_data_server_lookup: ip_addr=%x port=%hu\n",
-			ntohl(ip_addr), ntohs(port));
+	return false;
+}
 
-	list_for_each_entry(ds, &nfs4_data_server_cache, ds_node) {
-		if (ds->ds_ip_addr == ip_addr &&
-		    ds->ds_port == port) {
-			return ds;
+/*
+ * Lookup DS by addresses.  The first matching address returns true.
+ * nfs4_ds_cache_lock is held
+ */
+static struct nfs4_pnfs_ds *
+_data_server_lookup_locked(struct list_head *dsaddrs)
+{
+	struct nfs4_pnfs_ds *ds;
+	struct nfs4_pnfs_ds_addr *da1, *da2;
+
+	list_for_each_entry(da1, dsaddrs, da_node) {
+		list_for_each_entry(ds, &nfs4_data_server_cache, ds_node) {
+			list_for_each_entry(da2, &ds->ds_addrs, da_node) {
+				if (same_sockaddr(
+					(struct sockaddr *)&da1->da_addr,
+					(struct sockaddr *)&da2->da_addr))
+					return ds;
+			}
 		}
 	}
 	return NULL;
 }
 
 /*
+ * Compare two lists of addresses.
+ */
+static bool
+_data_server_match_all_addrs_locked(struct list_head *dsaddrs1,
+				    struct list_head *dsaddrs2)
+{
+	struct nfs4_pnfs_ds_addr *da1, *da2;
+	size_t count1 = 0,
+	       count2 = 0;
+
+	list_for_each_entry(da1, dsaddrs1, da_node)
+		count1++;
+
+	list_for_each_entry(da2, dsaddrs2, da_node) {
+		bool found = false;
+		count2++;
+		list_for_each_entry(da1, dsaddrs1, da_node) {
+			if (same_sockaddr((struct sockaddr *)&da1->da_addr,
+				(struct sockaddr *)&da2->da_addr)) {
+				found = true;
+				break;
+			}
+		}
+		if (!found)
+			return false;
+	}
+
+	return (count1 == count2);
+}
+
+/*
  * Create an rpc connection to the nfs4_pnfs_ds data server
- * Currently only support IPv4
+ * Currently only supports IPv4 and IPv6 addresses
  */
 static int
 nfs4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds)
 {
-	struct nfs_client *clp;
-	struct sockaddr_in sin;
+	struct nfs_client *clp = ERR_PTR(-EIO);
+	struct nfs4_pnfs_ds_addr *da;
 	int status = 0;
 
-	dprintk("--> %s ip:port %x:%hu au_flavor %d\n", __func__,
-		ntohl(ds->ds_ip_addr), ntohs(ds->ds_port),
+	dprintk("--> %s DS %s au_flavor %d\n", __func__, ds->ds_remotestr,
 		mds_srv->nfs_client->cl_rpcclient->cl_auth->au_flavor);
 
-	sin.sin_family = AF_INET;
-	sin.sin_addr.s_addr = ds->ds_ip_addr;
-	sin.sin_port = ds->ds_port;
+	BUG_ON(list_empty(&ds->ds_addrs));
+
+	list_for_each_entry(da, &ds->ds_addrs, da_node) {
+		dprintk("%s: DS %s: trying address %s\n",
+			__func__, ds->ds_remotestr, da->da_remotestr);
+
+		clp = nfs4_set_ds_client(mds_srv->nfs_client,
+				 (struct sockaddr *)&da->da_addr,
+				 da->da_addrlen, IPPROTO_TCP);
+		if (!IS_ERR(clp))
+			break;
+	}
 
-	clp = nfs4_set_ds_client(mds_srv->nfs_client, (struct sockaddr *)&sin,
-				 sizeof(sin), IPPROTO_TCP);
 	if (IS_ERR(clp)) {
 		status = PTR_ERR(clp);
 		goto out;
@@ -115,8 +200,8 @@ nfs4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds)
 			goto out_put;
 		}
 		ds->ds_clp = clp;
-		dprintk("%s [existing] ip=%x, port=%hu\n", __func__,
-			ntohl(ds->ds_ip_addr), ntohs(ds->ds_port));
+		dprintk("%s [existing] server=%s\n", __func__,
+			ds->ds_remotestr);
 		goto out;
 	}
 
@@ -135,8 +220,7 @@ nfs4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds)
 		goto out_put;
 
 	ds->ds_clp = clp;
-	dprintk("%s [new] ip=%x, port=%hu\n", __func__, ntohl(ds->ds_ip_addr),
-		ntohs(ds->ds_port));
+	dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr);
 out:
 	return status;
 out_put:
@@ -147,12 +231,25 @@ out_put:
 static void
 destroy_ds(struct nfs4_pnfs_ds *ds)
 {
+	struct nfs4_pnfs_ds_addr *da;
+
 	dprintk("--> %s\n", __func__);
 	ifdebug(FACILITY)
 		print_ds(ds);
 
 	if (ds->ds_clp)
 		nfs_put_client(ds->ds_clp);
+
+	while (!list_empty(&ds->ds_addrs)) {
+		da = list_first_entry(&ds->ds_addrs,
+				      struct nfs4_pnfs_ds_addr,
+				      da_node);
+		list_del_init(&da->da_node);
+		kfree(da->da_remotestr);
+		kfree(da);
+	}
+
+	kfree(ds->ds_remotestr);
 	kfree(ds);
 }
 
@@ -179,31 +276,96 @@ nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
 	kfree(dsaddr);
 }
 
+/*
+ * Create a string with a human readable address and port to avoid
+ * complicated setup around many dprinks.
+ */
+static char *
+nfs4_pnfs_remotestr(struct list_head *dsaddrs, gfp_t gfp_flags)
+{
+	struct nfs4_pnfs_ds_addr *da;
+	char *remotestr;
+	size_t len;
+	char *p;
+
+	len = 3;        /* '{', '}' and eol */
+	list_for_each_entry(da, dsaddrs, da_node) {
+		len += strlen(da->da_remotestr) + 1;    /* string plus comma */
+	}
+
+	remotestr = kzalloc(len, gfp_flags);
+	if (!remotestr)
+		return NULL;
+
+	p = remotestr;
+	*(p++) = '{';
+	len--;
+	list_for_each_entry(da, dsaddrs, da_node) {
+		size_t ll = strlen(da->da_remotestr);
+
+		if (ll > len)
+			goto out_err;
+
+		memcpy(p, da->da_remotestr, ll);
+		p += ll;
+		len -= ll;
+
+		if (len < 1)
+			goto out_err;
+		(*p++) = ',';
+		len--;
+	}
+	if (len < 2)
+		goto out_err;
+	*(p++) = '}';
+	*p = '\0';
+	return remotestr;
+out_err:
+	kfree(remotestr);
+	return NULL;
+}
+
 static struct nfs4_pnfs_ds *
-nfs4_pnfs_ds_add(struct inode *inode, u32 ip_addr, u32 port, gfp_t gfp_flags)
+nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
 {
-	struct nfs4_pnfs_ds *tmp_ds, *ds;
+	struct nfs4_pnfs_ds *tmp_ds, *ds = NULL;
+	char *remotestr;
 
-	ds = kzalloc(sizeof(*tmp_ds), gfp_flags);
+	if (list_empty(dsaddrs)) {
+		dprintk("%s: no addresses defined\n", __func__);
+		goto out;
+	}
+
+	ds = kzalloc(sizeof(*ds), gfp_flags);
 	if (!ds)
 		goto out;
 
+	/* this is only used for debugging, so it's ok if its NULL */
+	remotestr = nfs4_pnfs_remotestr(dsaddrs, gfp_flags);
+
 	spin_lock(&nfs4_ds_cache_lock);
-	tmp_ds = _data_server_lookup_locked(ip_addr, port);
+	tmp_ds = _data_server_lookup_locked(dsaddrs);
 	if (tmp_ds == NULL) {
-		ds->ds_ip_addr = ip_addr;
-		ds->ds_port = port;
+		INIT_LIST_HEAD(&ds->ds_addrs);
+		list_splice_init(dsaddrs, &ds->ds_addrs);
+		ds->ds_remotestr = remotestr;
 		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);
+		dprintk("%s add new data server %s\n", __func__,
+			ds->ds_remotestr);
 	} else {
+		if (!_data_server_match_all_addrs_locked(&tmp_ds->ds_addrs,
+							 dsaddrs)) {
+			dprintk("%s:  multipath address mismatch: %s != %s",
+				__func__, tmp_ds->ds_remotestr, remotestr);
+		}
+		kfree(remotestr);
 		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,
+		dprintk("%s data server %s found, inc'ed ds_count to %d\n",
+			__func__, tmp_ds->ds_remotestr,
 			atomic_read(&tmp_ds->ds_count));
 		ds = tmp_ds;
 	}
@@ -213,18 +375,22 @@ out:
 }
 
 /*
- * Currently only support ipv4, and one multi-path address.
+ * Currently only supports ipv4, ipv6 and one multi-path address.
  */
-static struct nfs4_pnfs_ds *
-decode_and_add_ds(struct xdr_stream *streamp, struct inode *inode, gfp_t gfp_flags)
+static struct nfs4_pnfs_ds_addr *
+decode_ds_addr(struct xdr_stream *streamp, gfp_t gfp_flags)
 {
-	struct nfs4_pnfs_ds *ds = NULL;
-	char *buf;
-	const char *ipend, *pstr;
-	u32 ip_addr, port;
-	int nlen, rlen, i;
+	struct nfs4_pnfs_ds_addr *da = NULL;
+	char *buf, *portstr;
+	u32 port;
+	int nlen, rlen;
 	int tmp[2];
 	__be32 *p;
+	char *netid, *match_netid;
+	size_t len, match_netid_len;
+	char *startsep = "";
+	char *endsep = "";
+
 
 	/* r_netid */
 	p = xdr_inline_decode(streamp, 4);
@@ -236,64 +402,123 @@ decode_and_add_ds(struct xdr_stream *streamp, struct inode *inode, gfp_t gfp_fla
 	if (unlikely(!p))
 		goto out_err;
 
-	/* Check that netid is "tcp" */
-	if (nlen != 3 ||  memcmp((char *)p, "tcp", 3)) {
-		dprintk("%s: ERROR: non ipv4 TCP r_netid\n", __func__);
+	netid = kmalloc(nlen+1, gfp_flags);
+	if (unlikely(!netid))
 		goto out_err;
-	}
 
-	/* r_addr */
+	netid[nlen] = '\0';
+	memcpy(netid, p, nlen);
+
+	/* r_addr: ip/ip6addr with port in dec octets - see RFC 5665 */
 	p = xdr_inline_decode(streamp, 4);
 	if (unlikely(!p))
-		goto out_err;
+		goto out_free_netid;
 	rlen = be32_to_cpup(p);
 
 	p = xdr_inline_decode(streamp, rlen);
 	if (unlikely(!p))
-		goto out_err;
+		goto out_free_netid;
 
-	/* ipv6 length plus port is legal */
-	if (rlen > INET6_ADDRSTRLEN + 8) {
+	/* port is ".ABC.DEF", 8 chars max */
+	if (rlen > INET6_ADDRSTRLEN + IPV6_SCOPE_ID_LEN + 8) {
 		dprintk("%s: Invalid address, length %d\n", __func__,
 			rlen);
-		goto out_err;
+		goto out_free_netid;
 	}
 	buf = kmalloc(rlen + 1, gfp_flags);
 	if (!buf) {
 		dprintk("%s: Not enough memory\n", __func__);
-		goto out_err;
+		goto out_free_netid;
 	}
 	buf[rlen] = '\0';
 	memcpy(buf, p, rlen);
 
-	/* replace the port dots with dashes for the in4_pton() delimiter*/
-	for (i = 0; i < 2; i++) {
-		char *res = strrchr(buf, '.');
-		if (!res) {
-			dprintk("%s: Failed finding expected dots in port\n",
-				__func__);
-			goto out_free;
-		}
-		*res = '-';
+	/* replace port '.' with '-' */
+	portstr = strrchr(buf, '.');
+	if (!portstr) {
+		dprintk("%s: Failed finding expected dot in port\n",
+			__func__);
+		goto out_free_buf;
+	}
+	*portstr = '-';
+
+	/* find '.' between address and port */
+	portstr = strrchr(buf, '.');
+	if (!portstr) {
+		dprintk("%s: Failed finding expected dot between address and "
+			"port\n", __func__);
+		goto out_free_buf;
 	}
+	*portstr = '\0';
 
-	/* 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;
+	da = kzalloc(sizeof(*da), gfp_flags);
+	if (unlikely(!da))
+		goto out_free_buf;
+
+	INIT_LIST_HEAD(&da->da_node);
+
+	if (!rpc_pton(buf, portstr-buf, (struct sockaddr *)&da->da_addr,
+		      sizeof(d