Merge branch 'nfs-for-3.3' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

* 'nfs-for-3.3' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  NFSv4: Change the default setting of the nfs4_disable_idmapping parameter
  NFSv4: Save the owner/group name string when doing open
  NFS: Remove pNFS bloat from the generic write path
  pnfs-obj: Must return layout on IO error
  pnfs-obj: pNFS errors are communicated on iodata->pnfs_error
  NFS: Cache state owners after files are closed
  NFS: Clean up nfs4_find_state_owners_locked()
  NFSv4: include bitmap in nfsv4 get acl data
  nfs: fix a minor do_div portability issue
  NFSv4.1: cleanup comment and debug printk
  NFSv4.1: change nfs4_free_slot parameters for dynamic slots
  NFSv4.1: cleanup init and reset of session slot tables
  NFSv4.1: fix backchannel slotid off-by-one bug
  nfs: fix regression in handling of context= option in NFSv4
  NFS - fix recent breakage to NFS error handling.
  NFS: Retry mounting NFSROOT
  SUNRPC: Clean up the RPCSEC_GSS service ticket requests

17 files changed, 422 insertions, 233 deletions

diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 43926add945b..54cea8ad5a76 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -339,7 +339,7 @@ validate_seqid(struct nfs4_slot_table *tbl, struct cb_sequenceargs * args)
 	dprintk("%s enter. slotid %d seqid %d\n",
 		__func__, args->csa_slotid, args->csa_sequenceid);
 
-	if (args->csa_slotid > NFS41_BC_MAX_CALLBACKS)
+	if (args->csa_slotid >= NFS41_BC_MAX_CALLBACKS)
 		return htonl(NFS4ERR_BADSLOT);
 
 	slot = tbl->slots + args->csa_slotid;
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 873bf00d51a2..277dfaf2e99a 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -84,7 +84,7 @@ retry:
 /*
  * Turn off NFSv4 uid/gid mapping when using AUTH_SYS
  */
-static int nfs4_disable_idmapping = 0;
+static int nfs4_disable_idmapping = 1;
 
 /*
  * RPC cruft for NFS
@@ -185,7 +185,7 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
 	clp->cl_minorversion = cl_init->minorversion;
 	clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion];
 #endif
-	cred = rpc_lookup_machine_cred();
+	cred = rpc_lookup_machine_cred("*");
 	if (!IS_ERR(cred))
 		clp->cl_machine_cred = cred;
 	nfs_fscache_get_client_cookie(clp);
@@ -250,6 +250,11 @@ static void pnfs_init_server(struct nfs_server *server)
 	rpc_init_wait_queue(&server->roc_rpcwaitq, "pNFS ROC");
 }
 
+static void nfs4_destroy_server(struct nfs_server *server)
+{
+	nfs4_purge_state_owners(server);
+}
+
 #else
 static void nfs4_shutdown_client(struct nfs_client *clp)
 {
@@ -1065,6 +1070,7 @@ static struct nfs_server *nfs_alloc_server(void)
 	INIT_LIST_HEAD(&server->master_link);
 	INIT_LIST_HEAD(&server->delegations);
 	INIT_LIST_HEAD(&server->layouts);
+	INIT_LIST_HEAD(&server->state_owners_lru);
 
 	atomic_set(&server->active, 0);
 
@@ -1538,6 +1544,7 @@ static int nfs4_server_common_setup(struct nfs_server *server,
 
 	nfs_server_insert_lists(server);
 	server->mount_time = jiffies;
+	server->destroy = nfs4_destroy_server;
 out:
 	nfs_free_fattr(fattr);
 	return error;
@@ -1719,6 +1726,7 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source,
 
 	/* Copy data from the source */
 	server->nfs_client = source->nfs_client;
+	server->destroy = source->destroy;
 	atomic_inc(&server->nfs_client->cl_count);
 	nfs_server_copy_userdata(server, source);
 
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 606ef0f20aed..c43a452f7da2 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -272,13 +272,13 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 			datasync);
 
 	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
-	if (ret)
-		return ret;
 	mutex_lock(&inode->i_mutex);
 
 	nfs_inc_stats(inode, NFSIOS_VFSFSYNC);
 	have_error = test_and_clear_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
 	status = nfs_commit_inode(inode, FLUSH_SYNC);
+	if (status >= 0 && ret < 0)
+		status = ret;
 	have_error |= test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
 	if (have_error)
 		ret = xchg(&ctx->error, 0);
diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c
index 47d1c6ff2d8e..2c05f1991e1e 100644
--- a/fs/nfs/idmap.c
+++ b/fs/nfs/idmap.c
@@ -38,6 +38,89 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/nfs_idmap.h>
+#include <linux/nfs_fs.h>
+
+/**
+ * nfs_fattr_init_names - initialise the nfs_fattr owner_name/group_name fields
+ * @fattr: fully initialised struct nfs_fattr
+ * @owner_name: owner name string cache
+ * @group_name: group name string cache
+ */
+void nfs_fattr_init_names(struct nfs_fattr *fattr,
+		struct nfs4_string *owner_name,
+		struct nfs4_string *group_name)
+{
+	fattr->owner_name = owner_name;
+	fattr->group_name = group_name;
+}
+
+static void nfs_fattr_free_owner_name(struct nfs_fattr *fattr)
+{
+	fattr->valid &= ~NFS_ATTR_FATTR_OWNER_NAME;
+	kfree(fattr->owner_name->data);
+}
+
+static void nfs_fattr_free_group_name(struct nfs_fattr *fattr)
+{
+	fattr->valid &= ~NFS_ATTR_FATTR_GROUP_NAME;
+	kfree(fattr->group_name->data);
+}
+
+static bool nfs_fattr_map_owner_name(struct nfs_server *server, struct nfs_fattr *fattr)
+{
+	struct nfs4_string *owner = fattr->owner_name;
+	__u32 uid;
+
+	if (!(fattr->valid & NFS_ATTR_FATTR_OWNER_NAME))
+		return false;
+	if (nfs_map_name_to_uid(server, owner->data, owner->len, &uid) == 0) {
+		fattr->uid = uid;
+		fattr->valid |= NFS_ATTR_FATTR_OWNER;
+	}
+	return true;
+}
+
+static bool nfs_fattr_map_group_name(struct nfs_server *server, struct nfs_fattr *fattr)
+{
+	struct nfs4_string *group = fattr->group_name;
+	__u32 gid;
+
+	if (!(fattr->valid & NFS_ATTR_FATTR_GROUP_NAME))
+		return false;
+	if (nfs_map_group_to_gid(server, group->data, group->len, &gid) == 0) {
+		fattr->gid = gid;
+		fattr->valid |= NFS_ATTR_FATTR_GROUP;
+	}
+	return true;
+}
+
+/**
+ * nfs_fattr_free_names - free up the NFSv4 owner and group strings
+ * @fattr: a fully initialised nfs_fattr structure
+ */
+void nfs_fattr_free_names(struct nfs_fattr *fattr)
+{
+	if (fattr->valid & NFS_ATTR_FATTR_OWNER_NAME)
+		nfs_fattr_free_owner_name(fattr);
+	if (fattr->valid & NFS_ATTR_FATTR_GROUP_NAME)
+		nfs_fattr_free_group_name(fattr);
+}
+
+/**
+ * nfs_fattr_map_and_free_names - map owner/group strings into uid/gid and free
+ * @server: pointer to the filesystem nfs_server structure
+ * @fattr: a fully initialised nfs_fattr structure
+ *
+ * This helper maps the cached NFSv4 owner/group strings in fattr into
+ * their numeric uid/gid equivalents, and then frees the cached strings.
+ */
+void nfs_fattr_map_and_free_names(struct nfs_server *server, struct nfs_fattr *fattr)
+{
+	if (nfs_fattr_map_owner_name(server, fattr))
+		nfs_fattr_free_owner_name(fattr);
+	if (nfs_fattr_map_group_name(server, fattr))
+		nfs_fattr_free_group_name(fattr);
+}
 
 static int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *res)
 {
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 81db25e92e10..25c3bfad7953 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1020,6 +1020,8 @@ void nfs_fattr_init(struct nfs_fattr *fattr)
 	fattr->valid = 0;
 	fattr->time_start = jiffies;
 	fattr->gencount = nfs_inc_attr_generation_counter();
+	fattr->owner_name = NULL;
+	fattr->group_name = NULL;
 }
 
 struct nfs_fattr *nfs_alloc_fattr(void)
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 3f4d95751d52..5ee92538b063 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -307,6 +307,8 @@ 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_init_write_mds(struct nfs_pageio_descriptor *pgio,
+				  struct inode *inode, int ioflags);
 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);
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 693ae22f8731..4d7d0aedc101 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -94,6 +94,8 @@ struct nfs_unique_id {
 struct nfs4_state_owner {
 	struct nfs_unique_id so_owner_id;
 	struct nfs_server    *so_server;
+	struct list_head     so_lru;
+	unsigned long        so_expires;
 	struct rb_node	     so_server_node;
 
 	struct rpc_cred	     *so_cred;	 /* Associated cred */
@@ -319,6 +321,7 @@ static inline void nfs4_schedule_session_recovery(struct nfs4_session *session)
 
 extern struct nfs4_state_owner * nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *);
 extern void nfs4_put_state_owner(struct nfs4_state_owner *);
+extern void nfs4_purge_state_owners(struct nfs_server *);
 extern struct nfs4_state * nfs4_get_open_state(struct inode *, struct nfs4_state_owner *);
 extern void nfs4_put_open_state(struct nfs4_state *);
 extern void nfs4_close_state(struct nfs4_state *, fmode_t);
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index a62d36b9a99e..71ec08617e23 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -49,13 +49,14 @@ filelayout_get_dense_offset(struct nfs4_filelayout_segment *flseg,
 			    loff_t offset)
 {
 	u32 stripe_width = flseg->stripe_unit * flseg->dsaddr->stripe_count;
-	u64 tmp;
+	u64 stripe_no;
+	u32 rem;
 
 	offset -= flseg->pattern_offset;
-	tmp = offset;
-	do_div(tmp, stripe_width);
+	stripe_no = div_u64(offset, stripe_width);
+	div_u64_rem(offset, flseg->stripe_unit, &rem);
 
-	return tmp * flseg->stripe_unit + do_div(offset, flseg->stripe_unit);
+	return stripe_no * flseg->stripe_unit + rem;
 }
 
 /* This function is used by the layout driver to calculate the
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index dcda0ba7af60..75366dc89686 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -52,6 +52,7 @@
 #include <linux/namei.h>
 #include <linux/mount.h>
 #include <linux/module.h>
+#include <linux/nfs_idmap.h>
 #include <linux/sunrpc/bc_xprt.h>
 #include <linux/xattr.h>
 #include <linux/utsname.h>
@@ -364,9 +365,8 @@ static void renew_lease(const struct nfs_server *server, unsigned long timestamp
  * Must be called while holding tbl->slot_tbl_lock
  */
 static void
-nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *free_slot)
+nfs4_free_slot(struct nfs4_slot_table *tbl, u8 free_slotid)
 {
-	int free_slotid = free_slot - tbl->slots;
 	int slotid = free_slotid;
 
 	BUG_ON(slotid < 0 || slotid >= NFS4_MAX_SLOT_TABLE);
@@ -431,7 +431,7 @@ static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res)
 	}
 
 	spin_lock(&tbl->slot_tbl_lock);
-	nfs4_free_slot(tbl, res->sr_slot);
+	nfs4_free_slot(tbl, res->sr_slot - tbl->slots);
 	nfs4_check_drain_fc_complete(res->sr_session);
 	spin_unlock(&tbl->slot_tbl_lock);
 	res->sr_slot = NULL;
@@ -554,13 +554,10 @@ int nfs41_setup_sequence(struct nfs4_session *session,
 	spin_lock(&tbl->slot_tbl_lock);
 	if (test_bit(NFS4_SESSION_DRAINING, &session->session_state) &&
 	    !rpc_task_has_priority(task, RPC_PRIORITY_PRIVILEGED)) {
-		/*
-		 * The state manager will wait until the slot table is empty.
-		 * Schedule the reset thread
-		 */
+		/* The state manager will wait until the slot table is empty */
 		rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL);
 		spin_unlock(&tbl->slot_tbl_lock);
-		dprintk("%s Schedule Session Reset\n", __func__);
+		dprintk("%s session is draining\n", __func__);
 		return -EAGAIN;
 	}
 
@@ -765,6 +762,8 @@ struct nfs4_opendata {
 	struct nfs_openres o_res;
 	struct nfs_open_confirmargs c_arg;
 	struct nfs_open_confirmres c_res;
+	struct nfs4_string owner_name;
+	struct nfs4_string group_name;
 	struct nfs_fattr f_attr;
 	struct nfs_fattr dir_attr;
 	struct dentry *dir;
@@ -788,6 +787,7 @@ static void nfs4_init_opendata_res(struct nfs4_opendata *p)
 	p->o_res.server = p->o_arg.server;
 	nfs_fattr_init(&p->f_attr);
 	nfs_fattr_init(&p->dir_attr);
+	nfs_fattr_init_names(&p->f_attr, &p->owner_name, &p->group_name);
 }
 
 static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
@@ -819,6 +819,7 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
 	p->o_arg.name = &dentry->d_name;
 	p->o_arg.server = server;
 	p->o_arg.bitmask = server->attr_bitmask;
+	p->o_arg.dir_bitmask = server->cache_consistency_bitmask;
 	p->o_arg.claim = NFS4_OPEN_CLAIM_NULL;
 	if (flags & O_CREAT) {
 		u32 *s;
@@ -855,6 +856,7 @@ static void nfs4_opendata_free(struct kref *kref)
 	dput(p->dir);
 	dput(p->dentry);
 	nfs_sb_deactive(sb);
+	nfs_fattr_free_names(&p->f_attr);
 	kfree(p);
 }
 
@@ -1579,6 +1581,8 @@ static int _nfs4_recover_proc_open(struct nfs4_opendata *data)
 	if (status != 0 || !data->rpc_done)
 		return status;
 
+	nfs_fattr_map_and_free_names(NFS_SERVER(dir), &data->f_attr);
+
 	nfs_refresh_inode(dir, o_res->dir_attr);
 
 	if (o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) {
@@ -1611,6 +1615,8 @@ static int _nfs4_proc_open(struct nfs4_opendata *data)
 		return status;
 	}
 
+	nfs_fattr_map_and_free_names(server, &data->f_attr);
+
 	if (o_arg->open_flags & O_CREAT) {
 		update_changeattr(dir, &o_res->cinfo);
 		nfs_post_op_update_inode(dir, o_res->dir_attr);
@@ -3431,19 +3437,6 @@ static inline int nfs4_server_supports_acls(struct nfs_server *server)
  */
 #define NFS4ACL_MAXPAGES (XATTR_SIZE_MAX >> PAGE_CACHE_SHIFT)
 
-static void buf_to_pages(const void *buf, size_t buflen,
-		struct page **pages, unsigned int *pgbase)
-{
-	const void *p = buf;
-
-	*pgbase = offset_in_page(buf);
-	p -= *pgbase;
-	while (p < buf + buflen) {
-		*(pages++) = virt_to_page(p);
-		p += PAGE_CACHE_SIZE;
-	}
-}
-
 static int buf_to_pages_noslab(const void *buf, size_t buflen,
 		struct page **pages, unsigned int *pgbase)
 {
@@ -3540,9 +3533,19 @@ out:
 	nfs4_set_cached_acl(inode, acl);
 }
 
+/*
+ * The getxattr API returns the required buffer length when called with a
+ * NULL buf. The NFSv4 acl tool then calls getxattr again after allocating
+ * the required buf.  On a NULL buf, we send a page of data to the server
+ * guessing that the ACL request can be serviced by a page. If so, we cache
+ * up to the page of ACL data, and the 2nd call to getxattr is serviced by
+ * the cache. If not so, we throw away the page, and cache the required
+ * length. The next getxattr call will then produce another round trip to
+ * the server, this time with the input buf of the required size.
+ */
 static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen)
 {
-	struct page *pages[NFS4ACL_MAXPAGES];
+	struct page *pages[NFS4ACL_MAXPAGES] = {NULL, };
 	struct nfs_getaclargs args = {
 		.fh = NFS_FH(inode),
 		.acl_pages = pages,
@@ -3557,41 +3560,60 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 		.rpc_argp = &args,
 		.rpc_resp = &res,
 	};
-	struct page *localpage = NULL;
-	int ret;
+	int ret = -ENOMEM, npages, i, acl_len = 0;
 
-	if (buflen < PAGE_SIZE) {
-		/* As long as we're doing a round trip to the server anyway,
-		 * let's be prepared for a page of acl data. */
-		localpage = alloc_page(GFP_KERNEL);
-		resp_buf = page_address(localpage);
-		if (localpage == NULL)
-			return -ENOMEM;
-		args.acl_pages[0] = localpage;
-		args.acl_pgbase = 0;
-		args.acl_len = PAGE_SIZE;
-	} else {
-		resp_buf = buf;
-		buf_to_pages(buf, buflen, args.acl_pages, &args.acl_pgbase);
+	npages = (buflen + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	/* As long as we're doing a round trip to the server anyway,
+	 * let's be prepared for a page of acl data. */
+	if (npages == 0)
+		npages = 1;
+
+	for (i = 0; i < npages; i++) {
+		pages[i] = alloc_page(GFP_KERNEL);
+		if (!pages[i])
+			goto out_free;
 	}
-	ret = nfs4_call_sync(NFS_SERVER(inode)->client, NFS_SERVER(inode), &msg, &args.seq_args, &res.seq_res, 0);
+	if (npages > 1) {
+		/* for decoding across pages */
+		args.acl_scratch = alloc_page(GFP_KERNEL);
+		if (!args.acl_scratch)
+			goto out_free;
+	}
+	args.acl_len = npages * PAGE_SIZE;
+	args.acl_pgbase = 0;
+	/* Let decode_getfacl know not to fail if the ACL data is larger than
+	 * the page we send as a guess */
+	if (buf == NULL)
+		res.acl_flags |= NFS4_ACL_LEN_REQUEST;
+	resp_buf = page_address(pages[0]);
+
+	dprintk("%s  buf %p buflen %ld npages %d args.acl_len %ld\n",
+		__func__, buf, buflen, npages, args.acl_len);
+	ret = nfs4_call_sync(NFS_SERVER(inode)->client, NFS_SERVER(inode),
+			     &msg, &args.seq_args, &res.seq_res, 0);
 	if (ret)
 		goto out_free;
-	if (res.acl_len > args.acl_len)
-		nfs4_write_cached_acl(inode, NULL, res.acl_len);
+
+	acl_len = res.acl_len - res.acl_data_offset;
+	if (acl_len > args.acl_len)
+		nfs4_write_cached_acl(inode, NULL, acl_len);
 	else
-		nfs4_write_cached_acl(inode, resp_buf, res.acl_len);
+		nfs4_write_cached_acl(inode, resp_buf + res.acl_data_offset,
+				      acl_len);
 	if (buf) {
 		ret = -ERANGE;
-		if (res.acl_len > buflen)
+		if (acl_len > buflen)
 			goto out_free;
-		if (localpage)
-			memcpy(buf, resp_buf, res.acl_len);
+		_copy_from_pages(buf, pages, res.acl_data_offset,
+				res.acl_len);
 	}
-	ret = res.acl_len;
+	ret = acl_len;
 out_free:
-	if (localpage)
-		__free_page(localpage);
+	for (i = 0; i < npages; i++)
+		if (pages[i])
+			__free_page(pages[i]);
+	if (args.acl_scratch)
+		__free_page(args.acl_scratch);
 	return ret;
 }
 
@@ -3622,6 +3644,8 @@ static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen)
 		nfs_zap_acl_cache(inode);
 	ret = nfs4_read_cached_acl(inode, buf, buflen);
 	if (ret != -ENOENT)
+		/* -ENOENT is returned if there is no ACL or if there is an ACL
+		 * but no cached acl data, just the acl length */
 		return ret;
 	return nfs4_get_acl_uncached(inode, buf, buflen);
 }
@@ -5022,23 +5046,6 @@ out:
 	return ret;
 }
 
-/*
- * Reset the forechannel and backchannel slot tables
- */
-static int nfs4_reset_slot_tables(struct nfs4_session *session)
-{
-	int status;
-
-	status = nfs4_reset_slot_table(&session->fc_slot_table,
-			session->fc_attrs.max_reqs, 1);
-	if (status)
-		return status;
-
-	status = nfs4_reset_slot_table(&session->bc_slot_table,
-			session->bc_attrs.max_reqs, 0);
-	return status;
-}
-
 /* Destroy the slot table */
 static void nfs4_destroy_slot_tables(struct nfs4_session *session)
 {
@@ -5084,29 +5091,35 @@ out:
 }
 
 /*
- * Initialize the forechannel and backchannel tables
+ * Initialize or reset the forechannel and backchannel tables
  */
-static int nfs4_init_slot_tables(struct nfs4_session *session)
+static int nfs4_setup_session_slot_tables(struct nfs4_session *ses)
 {
 	struct nfs4_slot_table *tbl;
-	int status = 0;
+	int status;
 
-	tbl = &session->fc_slot_table;
+	dprintk("--> %s\n", __func__);
+	/* Fore channel */
+	tbl = &ses->fc_slot_table;
 	if (tbl->slots == NULL) {
-		status = nfs4_init_slot_table(tbl,
-				session->fc_attrs.max_reqs, 1);
+		status = nfs4_init_slot_table(tbl, ses->fc_attrs.max_reqs, 1);
+		if (status) /* -ENOMEM */
+			return status;
+	} else {
+		status = nfs4_reset_slot_table(tbl, ses->fc_attrs.max_reqs, 1);
 		if (status)
 			return status;
 	}
-
-	tbl = &session->bc_slot_table;
+	/* Back channel */
+	tbl = &ses->bc_slot_table;
 	if (tbl->slots == NULL) {
-		status = nfs4_init_slot_table(tbl,
-				session->bc_attrs.max_reqs, 0);
+		status = nfs4_init_slot_table(tbl, ses->bc_attrs.max_reqs, 0);
 		if (status)
-			nfs4_destroy_slot_tables(session);
-	}
-
+			/* Fore and back channel share a connection so get
+			 * both slot tables or neither */
+			nfs4_destroy_slot_tables(ses);
+	} else
+		status = nfs4_reset_slot_table(tbl, ses->bc_attrs.max_reqs, 0);
 	return status;
 }
 
@@ -5294,13 +5307,9 @@ int nfs4_proc_create_session(struct nfs_client *clp)
 	if (status)
 		goto out;
 
-	/* Init and reset the fore channel */
-	status = nfs4_init_slot_tables(session);
-	dprintk("slot table initialization returned %d\n", status);
-	if (status)
-		goto out;
-	status = nfs4_reset_slot_tables(session);
-	dprintk("slot table reset returned %d\n", status);
+	/* Init or reset the session slot tables */
+	status = nfs4_setup_session_slot_tables(session);
+	dprintk("slot table setup returned %d\n", status);
 	if (status)
 		goto out;
 
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 6a7107ae6b72..a53f33b4ac3a 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -49,6 +49,7 @@
 #include <linux/ratelimit.h>
 #include <linux/workqueue.h>
 #include <linux/bitops.h>
+#include <linux/jiffies.h>
 
 #include "nfs4_fs.h"
 #include "callback.h"
@@ -377,31 +378,24 @@ nfs4_find_state_owner_locked(struct nfs_server *server, struct rpc_cred *cred)
 {
 	struct rb_node **p = &server->state_owners.rb_node,
 		       *parent = NULL;
-	struct nfs4_state_owner *sp, *res = NULL;
+	struct nfs4_state_owner *sp;
 
 	while (*p != NULL) {
 		parent = *p;
 		sp = rb_entry(parent, struct nfs4_state_owner, so_server_node);
 
-		if (server < sp->so_server) {
-			p = &parent->rb_left;
-			continue;
-		}
-		if (server > sp->so_server) {
-			p = &parent->rb_right;
-			continue;
-		}
 		if (cred < sp->so_cred)
 			p = &parent->rb_left;
 		else if (cred > sp->so_cred)
 			p = &parent->rb_right;
 		else {
+			if (!list_empty(&sp->so_lru))
+				list_del_init(&sp->so_lru);
 			atomic_inc(&sp->so_count);
-			res = sp;
-			break;
+			return sp;
 		}
 	}
-	return res;
+	return NULL;
 }
 
 static struct nfs4_state_owner *
@@ -421,6 +415,8 @@ nfs4_insert_state_owner_locked(struct nfs4_state_owner *new)
 		else if (new->so_cred > sp->so_cred)
 			p = &parent->rb_right;
 		else {
+			if (!list_empty(&sp->so_lru))
+				list_del_init(&sp->so_lru);
 			atomic_inc(&sp->so_count);
 			return sp;
 		}
@@ -462,6 +458,7 @@ nfs4_alloc_state_owner(void)
 	spin_lock_init(&sp->so_sequence.lock);
 	INIT_LIST_HEAD(&sp->so_sequence.list);
 	atomic_set(&sp->so_count, 1);
+	INIT_LIST_HEAD(&sp->so_lru);
 	return sp;
 }
 
@@ -479,6 +476,38 @@ nfs4_drop_state_owner(struct nfs4_state_owner *sp)
 	}
 }
 
+static void nfs4_free_state_owner(struct nfs4_state_owner *sp)
+{
+	rpc_destroy_wait_queue(&sp->so_sequence.wait);
+	put_rpccred(sp->so_cred);
+	kfree(sp);
+}
+
+static void nfs4_gc_state_owners(struct nfs_server *server)
+{
+	struct nfs_client *clp = server->nfs_client;
+	struct nfs4_state_owner *sp, *tmp;
+	unsigned long time_min, time_max;
+	LIST_HEAD(doomed);
+
+	spin_lock(&clp->cl_lock);
+	time_max = jiffies;
+	time_min = (long)time_max - (long)clp->cl_lease_time;
+	list_for_each_entry_safe(sp, tmp, &server->state_owners_lru, so_lru) {
+		/* NB: LRU is sorted so that oldest is at the head */
+		if (time_in_range(sp->so_expires, time_min, time_max))
+			break;
+		list_move(&sp->so_lru, &doomed);
+		nfs4_remove_state_owner_locked(sp);
+	}
+	spin_unlock(&clp->cl_lock);
+
+	list_for_each_entry_safe(sp, tmp, &doomed, so_lru) {
+		list_del(&sp->so_lru);
+		nfs4_free_state_owner(sp);
+	}
+}
+
 /**
  * nfs4_get_state_owner - Look up a state owner given a credential
  * @server: nfs_server to search
@@ -496,10 +525,10 @@ struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *server,
 	sp = nfs4_find_state_owner_locked(server, cred);
 	spin_unlock(&clp->cl_lock);
 	if (sp != NULL)
-		return sp;
+		goto out;
 	new = nfs4_alloc_state_owner();
 	if (new == NULL)
-		return NULL;
+		goto out;
 	new->so_server = server;
 	new->so_cred = cred;
 	spin_lock(&clp->cl_lock);
@@ -511,26 +540,58 @@ struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *server,
 		rpc_destroy_wait_queue(&new->so_sequence.wait);
 		kfree(new);
 	}
+out:
+	nfs4_gc_state_owners(server);
 	return sp;
 }
 
 /**
  * nfs4_put_state_owner - Release a nfs4_state_owner
  * @sp: state owner data to release
- *
  */
 void nfs4_put_state_owner(struct nfs4_state_owner *sp)
 {
-	struct nfs_client *clp = sp->so_server->nfs_client;
-	struct rpc_cred *cred = sp->so_cred;
+	struct nfs_server *server = sp->so_server;
+	struct nfs_client *clp = server->nfs_client;
 
 	if (!atomic_dec_and_lock(&sp->so_count, &clp->cl_lock))
 		return;
-	nfs4_remove_state_owner_locked(sp);
+
+	if (!RB_EMPTY_NODE(&sp->so_server_node)) {
+		sp->so_expires = jiffies;
+		list_add_tail(&sp->so_lru, &server->state_owners_lru);
+		spin_unlock(&clp->cl_lock);
+	} else {
+		nfs4_remove_state_owner_locked(sp);
+		spin_unlock(&clp->cl_lock);
+		nfs4_free_state_owner(sp);
+	}
+}
+
+/**
+ * nfs4_purge_state_owners - Release all cached state owners
+ * @server: nfs_server with cached state owners to release
+ *
+ * Called at umount time.  Remaining state owners will be on
+ * the LRU with ref count of zero.
+ */
+void nfs4_purge_state_owners(struct nfs_server *server)
+{
+	struct nfs_client *clp = server->nfs_client;
+	struct nfs4_state_owner *sp, *tmp;
+	LIST_HEAD(doomed);
+
+	spin_lock(&clp->cl_lock);
+	list_for_each_entry_safe(sp, tmp, &server->state_owners_lru, so_lru) {
+		list_move(&sp->so_lru, &doomed);
+		nfs4_remove_state_owner_locked(sp);
+	}
 	spin_unlock(&clp->cl_lock);
-	rpc_destroy_wait_queue(&sp->so_sequence.wait);
-	put_rpccred(cred);
-	kfree(sp);
+
+	list_for_each_entry_safe(sp, tmp, &doomed, so_lru) {
+		list_del(&sp->so_lru);
+		nfs4_free_state_owner(sp);
+	}
 }
 
 static struct nfs4_state *
@@ -1402,6 +1463,7 @@ static int nfs4_do_reclaim(struct nfs_client *clp, const struct nfs4_state_recov
 restart:
 	rcu_read_lock();
 	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
+		nfs4_purge_state_owners(server);
 		spin_lock(&clp->cl_lock);
 		for (pos = rb_first(&server->state_owners);
 		     pos != NULL;
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index e6161b213ed1..95e92e438407 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -2298,7 +2298,7 @@ static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr,
 	encode_getfh(xdr, &hdr);
 	encode_getfattr(xdr, args->bitmask, &hdr);
 	encode_restorefh(xdr, &hdr);
-	encode_getfattr(xdr, args->bitmask, &hdr);
+	encode_getfattr(xdr, args->dir_bitmask, &hdr);
 	encode_nops(&hdr);
 }
 
@@ -2517,11 +2517,13 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr,
 	encode_compound_hdr(xdr, req, &hdr);
 	encode_sequence(xdr, &args->seq_args, &hdr);
 	encode_putfh(xdr, args->fh, &hdr);
-	replen = hdr.replen + op_decode_hdr_maxsz + nfs4_fattr_bitmap_maxsz + 1;
+	replen = hdr.replen + op_decode_hdr_maxsz + 1;
 	encode_getattr_two(xdr, FATTR4_WORD0_ACL, 0, &hdr);
 
 	xdr_inline_pages(&req->rq_rcv_buf, replen << 2,
 		args->acl_pages, args->acl_pgbase, args->acl_len);
+	xdr_set_scratch_buffer(xdr, page_address(args->acl_scratch), PAGE_SIZE);
+
 	encode_nops(&hdr);
 }
 
@@ -3790,7 +3792,8 @@ out_overflow:
 }
 
 static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap,
-		const struct nfs_server *server, uint32_t *uid, int may_sleep)
+		const struct nfs_server *server, uint32_t *uid,
+		struct nfs4_string *owner_name)
 {
 	uint32_t len;
 	__be32 *p;
@@ -3807,8 +3810,12 @@ static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap,
 		p = xdr_inline_decode(xdr, len);
 		if (unlikely(!p))
 			goto out_overflow;
-		if (!may_sleep) {
-			/* do nothing */
+		if (owner_name != NULL) {
+			owner_name->data = kmemdup(p, len, GFP_NOWAIT);
+			if (owner_name->data != NULL) {
+				owner_name->len = len;
+				ret = NFS_ATTR_FATTR_OWNER_NAME;
+			}
 		} else if (len < XDR_MAX_NETOBJ) {
 			if (nfs_map_name_to_uid(server, (char *)p, len, uid) == 0)
 				ret = NFS_ATTR_FATTR_OWNER;
@@ -3828,7 +3835,8 @@ out_overflow:
 }
 
 static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap,
-		const struct nfs_server *server, uint32_t *gid, int may_sleep)
+		const struct nfs_server *server, uint32_t *gid,
+		struct nfs4_string *group_name)
 {
 	uint32_t len;
 	__be32 *p;
@@ -3845,8 +3853,12 @@ static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap,
 		p = xdr_inline_decode(xdr, len);
 		if (unlikely(!p))
 			goto out_overflow;
-		if (!may_sleep) {
-			/* do nothing */
+		if (group_name != NULL) {
+			group_name->data = kmemdup(p, len, GFP_NOWAIT);
+			if (group_name->data != NULL) {
+				group_name->len = len;
+				ret = NFS_ATTR_FATTR_GROUP_NAME;
+			}
 		} else if (len < XDR_MAX_NETOBJ) {
 			if (nfs_map_group_to_gid(server, (char *)p, len, gid) == 0)
 				ret = NFS_ATTR_FATTR_GROUP;
@@ -4283,7 +4295,7 @@ xdr_error:
 
 static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
 		struct nfs_fattr *fattr, struct nfs_fh *fh,
-		const struct nfs_server *server, int may_sleep)
+		const struct nfs_server *server)
 {
 	int status;
 	umode_t fmode = 0;
@@ -4350,12 +4362,12 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
 		goto xdr_error;
 	fattr->valid |= status;
 
-	status = decode_attr_owner(xdr, bitmap, server, &fattr->uid, may_sleep);
+	status = decode_attr_owner(xdr, bitmap, server, &fattr->uid, fattr->owner_name);
 	if (status < 0)
 		goto xdr_error;
 	fattr->valid |= status;
 
-	status = decode_attr_group(xdr, bitmap, server, &fattr->gid, may_sleep);
+	status = decode_attr_group(xdr, bitmap, server, &fattr->gid, fattr->group_name);
 	if (status < 0)
 		goto xdr_error;
 	fattr->valid |= status;
@@ -4396,7 +4408,7 @@ xdr_error:
 }
 
 static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fattr,
-		struct nfs_fh *fh, const struct nfs_server *server, int may_sleep)
+		struct nfs_fh *fh, const struct nfs_server *server)
 {
 	__be32 *savep;
 	uint32_t attrlen,
@@ -4415,7 +4427,7 @@ static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fat
 	if (status < 0)
 		goto xdr_error;
 
-	status = decode_getfattr_attrs(xdr, bitmap, fattr, fh, server, may_sleep);
+	status = decode_getfattr_attrs(xdr, bitmap, fattr, fh, server);
 	if (status < 0)
 		goto xdr_error;
 
@@ -4426,9 +4438,9 @@ xdr_error:
 }
 
 static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr,
-		const struct nfs_server *server, int may_sleep)
+		const struct nfs_server *server)
 {
-	return decode_getfattr_generic(xdr, fattr, NULL, server, may_sleep);
+	return decode_getfattr_generic(xdr, fattr, NULL, server);
 }
 
 /*
@@ -4957,17 +4969,18 @@ decode_restorefh(struct xdr_stream *xdr)
 }
 
 static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
-		size_t *acl_len)
+			 struct nfs_getaclres *res)
 {
-	__be32 *savep;
+	__be32 *savep, *bm_p;
 	uint32_t attrlen,
 		 bitmap[3] = {0};
 	struct kvec *iov = req->rq_rcv_buf.head;
 	int status;
 
-	*acl_len = 0;
+	res->acl_len = 0;
 	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
 		goto out;
+	bm_p = xdr->p;
 	if ((status = decode_attr_bitmap(xdr, bitmap)) != 0)
 		goto out;
 	if ((status = decode_attr_length(xdr, &attrlen, &savep)) != 0)
@@ -4979,18 +4992,30 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 		size_t hdrlen;
 		u32 recvd;
 
+		/* The bitmap (xdr len + bitmaps) and the attr xdr len words
+		 * are stored with the acl data to handle the problem of
+		 * variable length bitmaps.*/
+		xdr->p = bm_p;
+		res->acl_data_offset = be32_to_cpup(bm_p) + 2;
+		res->acl_data_offset <<= 2;
+
 		/* We ignore &savep and don't do consistency checks on
 		 * the attr length.  Let userspace figure it out.... */
 		hdrlen = (u8 *)xdr->p - (u8 *)iov->iov_base;
+		attrlen += res->acl_data_offset;
 		recvd = req->rq_rcv_buf.len - hdrlen;
 		if (attrlen > recvd) {
-			dprintk("NFS: server cheating in getattr"
-					" acl reply: attrlen %u > recvd %u\n",
+			if (res->acl_flags & NFS4_ACL_LEN_REQUEST) {
+				/* getxattr interface called with a NULL buf */
+				res->acl_len = attrlen;
+				goto out;
+			}
+			dprintk("NFS: acl reply: attrlen %u > recvd %u\n",
 					attrlen, recvd);
 			return -EINVAL;
 		}
 		xdr_read_pages(xdr, attrlen);
-		*acl_len = attrlen;
+		res->acl_len = attrlen;
 	} else
 		status = -EOPNOTSUPP;
 
@@ -5696,8 +5721,7 @@ static int nfs4_xdr_dec_open_downgrade(struct rpc_rqst *rqstp,
 	status = decode_open_downgrade(xdr, res);
 	if (status != 0)
 		goto out;
-	decode_getfattr(xdr, res->fattr, res->server,
-			!RPC_IS_ASYNC(rqstp->rq_task));
+	decode_getfattr(xdr, res->fattr, res->server);
 out:
 	return status;
 }
@@ -5723,8 +5747,7 @@ static int nfs4_xdr_dec_access(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	status = decode_access(xdr, res);
 	if (status != 0)
 		goto out;
-	decode_getfattr(xdr, res->fattr, res->server,
-			!RPC_IS_ASYNC(rqstp->rq_task));
+	decode_getfattr(xdr, res->fattr, res->server);
 out:
 	return status;
 }
@@ -5753,8 +5776,7 @@ static int nfs4_xdr_dec_lookup(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	status = decode_getfh(xdr, res->fh);
 	if (status)
 		goto out;
-	status = decode_getfattr(xdr, res->fattr, res->server
-			,!RPC_IS_ASYNC(rqstp->rq_task));
+	status = decode_getfattr(xdr, res->fattr, res->server);
 out:
 	return status;
 }
@@ -5780,8 +5802,7 @@ static int nfs4_xdr_dec_lookup_root(struct rpc_rqst *rqstp,
 		goto out;
 	status = decode_getfh(xdr, res->fh);
 	if (status == 0)
-		status = decode_getfattr(xdr, res->fattr, res->server,
-				!RPC_IS_ASYNC(rqstp->rq_task));
+		status = decode_getfattr(xdr, res->fattr, res->server);
 out:
 	return status;
 }
@@ -5807,8 +5828,7 @@ static int nfs4_xdr_dec_remove(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	status = decode_remove(xdr, &res->cinfo);
 	if (status)
 		goto out;
-	decode_getfattr(xdr, res->dir_attr, res->server,
-			!RPC_IS_ASYNC(rqstp->rq_task));
+	decode_getfattr(xdr, res->dir_attr, res->server);
 out:
 	return status;
 }
@@ -5841,14 +5861,12 @@ static int nfs4_xdr_dec_rename(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	if (status)
 		goto out;
 	/* Current FH is target directory */
-	if (decode_getfattr(xdr, res->new_fattr, res->server,
-				!RPC_IS_ASYNC(rqstp->rq_task)) != 0)
+	if (decode_getfattr(xdr, res->new_fattr, res->server))
 		goto out;
 	status = decode_restorefh(xdr);
 	if (status)
 		goto out;
-	decode_getfattr(xdr, res->old_fattr, res->server,
-			!RPC_IS_ASYNC(rqstp->rq_task));
+	decode_getfattr(xdr, res->old_fattr, res->server);
 out:
 	return status;
 }
@@ -5884,14 +5902,12 @@ static int nfs4_xdr_dec_link(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	 * Note order: OP_LINK leaves the directory as the current
 	 *             filehandle.
 	 */
-	if (decode_getfattr(xdr, res->dir_attr, res->server,
-				!RPC_IS_ASYNC(rqstp->rq_task)) != 0)
+	if (decode_getfattr(xdr, res->dir_attr, res->server))
 		goto out;
 	status = decode_restorefh(xdr);
 	if (status)
 		goto out;
-	decode_getfattr(xdr, res->fattr, res->server,
-			!RPC_IS_ASYNC(rqstp->rq_task));
+	decode_getfattr(xdr, res->fattr, res->server);
 out:
 	return status;
 }
@@ -5923,14 +5939,12 @@ static int nfs4_xdr_dec_create(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	status = decode_getfh(xdr, res->fh);
 	if (status)
 		goto out;
-	if (decode_getfattr(xdr, res->fattr, res->server,
-				!RPC_IS_ASYNC(rqstp->rq_task)) != 0)
+	if (decode_getfattr(xdr, res->fattr, res->server))
 		goto out;
 	status = decode_restorefh(xdr);
 	if (status)
 		goto out;
-	decode_getfattr(xdr, res->dir_fattr, res->server,
-			!RPC_IS_ASYNC(rqstp->rq_task));
+	decode_getfattr(xdr, res->dir_fattr, res->server);
 out:
 	return status;
 }
@@ -5962,8 +5976,7 @@ static int nfs4_xdr_dec_getattr(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	status = decode_putfh(xdr);
 	if (status)
 		goto out;
-	status = decode_getfattr(xdr, res->fattr, res->server,
-			!RPC_IS_ASYNC(rqstp->rq_task));
+	status = decode_getfattr(xdr, res->fattr, res->server);
 out:
 	return status;
 }
@@ -6028,7 +6041,7 @@ nfs4_xdr_dec_getacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	status = decode_putfh(xdr);
 	if (status)
 		goto out;
-	status = decode_getacl(xdr, rqstp, &res->acl_len);
+	status = decode_getacl(xdr, rqstp, res);
 
 out:
 	return status;
@@ -6061,8 +6074,7 @@ static int nfs4_xdr_dec_close(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	 * 	an ESTALE error. Shouldn't be a problem,
 	 * 	though, since fattr->valid will remain unset.
 	 */
-	decode_getfattr(xdr, res->fattr, res->server,
-			!RPC_IS_ASYNC(rqstp->rq_task));
+	decode_getfattr(xdr, res->fattr, res->server);
 out:
 	return status;
 }
@@ -6093,13 +6105,11 @@ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 		goto out;
 	if (decode_getfh(xdr, &res->fh) != 0)
 		goto out;
-	if (decode_getfattr(xdr, res->f_attr, res->server,
-				!RPC_IS_ASYNC(rqstp->rq_task)) != 0)
+	if (decode_getfattr(xdr, res->f_attr, res->server) != 0)
 		goto out;
 	if (decode_restorefh(xdr) != 0)
 		goto out;
-	decode_getfattr(xdr, res->dir_attr, res->server,
-			!RPC_IS_ASYNC(rqstp->rq_task));
+	decode_getfattr(xdr, res->dir_attr, res->server);
 out:
 	return status;
 }
@@ -6147,8 +6157,7 @@ static int nfs4_xdr_dec_open_noattr(struct rpc_rqst *rqstp,
 	status = decode_open(xdr, res);
 	if (status)
 		goto out;
-	decode_getfattr(xdr, res->f_attr, res->server,
-			!RPC_IS_ASYNC(rqstp->rq_task));
+	decode_getfattr(xdr, res->f_attr, res->server);
 out:
 	return status;
 }
@@ -6175,8 +6184,7 @@ static int nfs4_xdr_dec_setattr(struct rpc_rqst *rqstp,
 	status = decode_setattr(xdr);
 	if (status)
 		goto out;
-	decode_getfattr(xdr, res->fattr, res->server,
-			!RPC_IS_ASYNC(rqstp->rq_task));
+	decode_getfattr(xdr, res->fattr, res->server);
 out:
 	return status;
 }
@@ -6356,8 +6364,7 @@ static int nfs4_xdr_dec_write(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	if (status)
 		goto out;
 	if (res->fattr)
-		decode_getfattr(xdr, res->fattr, res->server,
-				!RPC_IS_ASYNC(rqstp->rq_task));
+		decode_getfattr(xdr, res->fattr, res->server);
 	if (!status)
 		status = res->count;
 out:
@@ -6386,8 +6393,7 @@ static int nfs4_xdr_dec_commit(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	if (status)
 		goto out;
 	if (res->fattr)
-		decode_getfattr(xdr, res->fattr, res->server,
-				!RPC_IS_ASYNC(rqstp->rq_task));
+		decode_getfattr(xdr, res->fattr, res->server);
 out:
 	return status;
 }
@@ -6546,8 +6552,7 @@ static int nfs4_xdr_dec_delegreturn(struct rpc_rqst *rqstp,
 	status = decode_delegreturn(xdr);
 	if (status != 0)
 		goto out;
-	decode_getfattr(xdr, res->fattr, res->server,
-			!RPC_IS_ASYNC(rqstp->rq_task));
+	decode_getfattr(xdr, res->fattr, res->server);
 out:
 	return status;
 }
@@ -6576,8 +6581,7 @@ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req,
 		goto out;
 	xdr_enter_page(xdr, PAGE_SIZE);
 	status = decode_getfattr(xdr, &res->fs_locations->fattr,
-				 res->fs_locations->server,
-				 !RPC_IS_ASYNC(req->rq_task));
+				 res->fs_locations->server);
 out:
 	return status;
 }
@@ -6826,8 +6830,7 @@ static int nfs4_xdr_dec_layoutcommit(struct rpc_rqst *rqstp,
 	status = decode_layoutcommit(xdr, rqstp, res);
 	if (status)
 		goto out;
-	decode_getfattr(xdr, res->fattr, res->server,
-			!RPC_IS_ASYNC(rqstp->rq_task));
+	decode_getfattr(xdr, res->fattr, res->server);
 out:
 	return status;
 }
@@ -6958,7 +6961,7 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 		goto out_overflow;
 
 	if (decode_getfattr_attrs(xdr, bitmap, entry->fattr, entry->fh,
-					entry->server, 1) < 0)
+					entry->server) < 0)
 		goto out_overflow;
 	if (entry->fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID)
 		entry->ino = entry->fattr->mounted_on_fileid;
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index c807ab93140e..55d01280a609 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -551,7 +551,8 @@ static const struct nfs_pageio_ops objio_pg_write_ops = {
 static struct pnfs_layoutdriver_type objlayout_type = {
 	.id = LAYOUT_OSD2_OBJECTS,
 	.name = "LAYOUT_OSD2_OBJECTS",
-	.flags                   = PNFS_LAYOUTRET_ON_SETATTR,
+	.flags                   = PNFS_LAYOUTRET_ON_SETATTR |
+				   PNFS_LAYOUTRET_ON_ERROR,
 
 	.alloc_layout_hdr        = objlayout_alloc_layout_hdr,
 	.free_layout_hdr         = objlayout_free_layout_hdr,
diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c
index 72074e3a04f9..b3c29039f5b8 100644
--- a/fs/nfs/objlayout/objlayout.c
+++ b/fs/nfs/objlayout/objlayout.c
@@ -254,6 +254,8 @@ objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
 	oir->status = rdata->task.tk_status = status;
 	if (status >= 0)
 		rdata->res.count = status;
+	else
+		rdata->pnfs_error = status;
 	objlayout_iodone(oir);
 	/* must not use oir after this point */
 
@@ -334,6 +336,8 @@ objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
 	if (status >= 0) {
 		wdata->res.count = status;
 		wdata->verf.committed = oir->committed;
+	} else {
+		wdata->pnfs_error = status;
 	}
 	objlayout_iodone(oir);
 	/* must not use oir after this point */
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 8e672a2b2d69..17149a490065 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1166,6 +1166,33 @@ pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_pg_test);
 
+static int pnfs_write_done_resend_to_mds(struct inode *inode, struct list_head *head)
+{
+	struct nfs_pageio_descriptor pgio;
+	LIST_HEAD(failed);
+
+	/* Resend all requests through the MDS */
+	nfs_pageio_init_write_mds(&pgio, inode, FLUSH_STABLE);
+	while (!list_empty(head)) {
+		struct nfs_page *req = nfs_list_entry(head->next);
+
+		nfs_list_remove_request(req);
+		if (!nfs_pageio_add_request(&pgio, req))
+			nfs_list_add_request(req, &failed);
+	}
+	nfs_pageio_complete(&pgio);
+
+	if (!list_empty(&failed)) {
+		/* For some reason our attempt to resend pages. Mark the
+		 * overall send request as having failed, and let
+		 * nfs_writeback_release_full deal with the error.
+		 */
+		list_move(&failed, head);
+		return -EIO;
+	}
+	return 0;
+}
+
 /*
  * Called by non rpc-based layout drivers
  */
@@ -1175,9 +1202,17 @@ void pnfs_ld_write_done(struct nfs_write_data *data)
 		pnfs_set_layoutcommit(data);
 		data->mds_ops->rpc_call_done(&data->task, data);
 	} else {
-		put_lseg(data->lseg);
-		data->lseg = NULL;
 		dprintk("pnfs write error = %d\n", data->pnfs_error);
+		if (NFS_SERVER(data->inode)->pnfs_curr_ld->flags &
+						PNFS_LAYOUTRET_ON_ERROR) {
+			/* Don't lo_commit on error, Server will needs to
+			 * preform a file recovery.
+			 */
+			clear_bit(NFS_INO_LAYOUTCOMMIT,
+				  &NFS_I(data->inode)->flags);
+			pnfs_return_layout(data->inode);
+		}
+		data->task.tk_status = pnfs_write_done_resend_to_mds(data->inode, &data->pages);
 	}
 	data->mds_ops->rpc_release(data);
 }
@@ -1267,6 +1302,9 @@ static void pnfs_ld_handle_read_error(struct nfs_read_data *data)
 	put_lseg(data->lseg);
 	data->lseg = NULL;
 	dprintk("pnfs write error = %d\n", data->pnfs_error);
+	if (NFS_SERVER(data->inode)->pnfs_curr_ld->flags &
+						PNFS_LAYOUTRET_ON_ERROR)
+		pnfs_return_layout(data->inode);
 
 	nfs_pageio_init_read_mds(&pgio, data->inode);
 
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 1509530cb111..53d593a0a4f2 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -68,6 +68,7 @@ enum {
 enum layoutdriver_policy_flags {
 	/* Should the pNFS client commit and return the layout upon a setattr */
 	PNFS_LAYOUTRET_ON_SETATTR	= 1 << 0,
+	PNFS_LAYOUTRET_ON_ERROR		= 1 << 1,
 };
 
 struct nfs4_deviceid_node;
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index e463967aafb8..3dfa4f112c0a 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -908,10 +908,24 @@ static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(unsigned int ve
 		data->auth_flavor_len	= 1;
 		data->version		= version;
 		data->minorversion	= 0;
+		security_init_mnt_opts(&data->lsm_opts);
 	}
 	return data;
 }
 
+static void nfs_free_parsed_mount_data(struct nfs_parsed_mount_data *data)
+{
+	if (data) {
+		kfree(data->client_address);
+		kfree(data->mount_server.hostname);
+		kfree(data->nfs_server.export_path);
+		kfree(data->nfs_server.hostname);
+		kfree(data->fscache_uniq);
+		security_free_mnt_opts(&data->lsm_opts);
+		kfree(data);
+	}
+}
+
 /*
  * Sanity-check a server address provided by the mount command.
  *
@@ -2219,9 +2233,7 @@ static struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
 	data = nfs_alloc_parsed_mount_data(NFS_DEFAULT_VERSION);
 	mntfh = nfs_alloc_fhandle();
 	if (data == NULL || mntfh == NULL)
-		goto out_free_fh;
-
-	security_init_mnt_opts(&data->lsm_opts);
+		goto out;
 
 	/* Validate the mount data */
 	error = nfs_validate_mount_data(raw_data, data, mntfh, dev_name);
@@ -2233,8 +2245,6 @@ static struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
 #ifdef CONFIG_NFS_V4
 	if (data->version == 4) {
 		mntroot = nfs4_try_mount(flags, dev_name, data);
-		kfree(data->client_address);
-		kfree(data->nfs_server.export_path);
 		goto out;
 	}
 #endif	/* CONFIG_NFS_V4 */
@@ -2289,13 +2299,8 @@ static struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
 	s->s_flags |= MS_ACTIVE;
 
 out:
-	kfree(data->nfs_server.hostname);
-	kfree(data->mount_server.hostname);
-	kfree(data->fscache_uniq);
-	security_free_mnt_opts(&data->lsm_opts);
-out_free_fh:
+	nfs_free_parsed_mount_data(data);
 	nfs_free_fhandle(mntfh);
-	kfree(data);
 	return mntroot;
 
 out_err_nosb:
@@ -2622,9 +2627,7 @@ nfs4_remote_mount(struct file_system_type *fs_type, int flags,
 
 	mntfh = nfs_alloc_fhandle();
 	if (data == NULL || mntfh == NULL)
-		goto out_free_fh;
-
-	security_init_mnt_opts(&data->lsm_opts);
+		goto out;
 
 	/* Get a volume representation */
 	server = nfs4_create_server(data, mntfh);
@@ -2676,13 +2679,10 @@ nfs4_remote_mount(struct file_system_type *fs_type, int flags,
 
 	s->s_flags |= MS_ACTIVE;
 
-	security_free_mnt_opts(&data->lsm_opts);
 	nfs_free_fhandle(mntfh);
 	return mntroot;
 
 out:
-	security_free_mnt_opts(&data->lsm_opts);
-out_free_fh:
 	nfs_free_fhandle(mntfh);
 	return ERR_PTR(error);
 
@@ -2839,7 +2839,7 @@ static struct dentry *nfs4_mount(struct file_system_type *fs_type,
 
 	data = nfs_alloc_parsed_mount_data(4);
 	if (data == NULL)
-		goto out_free_data;
+		goto out;
 
 	/* Validate the mount data */
 	error = nfs4_validate_mount_data(raw_data, data, dev_name);
@@ -2853,12 +2853,7 @@ static struct dentry *nfs4_mount(struct file_system_type *fs_type,
 		error = PTR_ERR(res);
 
 out:
-	kfree(data->client_address);
-	kfree(data->nfs_server.export_path);
-	kfree(data->nfs_server.hostname);
-	kfree(data->fscache_uniq);
-out_free_data:
-	kfree(data);
+	nfs_free_parsed_mount_data(data);
 	dprintk("<-- nfs4_mount() = %d%s\n", error,
 			error != 0 ? " [error]" : "");
 	return res;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 1dda78db6a73..0c3885255f97 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1052,7 +1052,7 @@ static const struct nfs_pageio_ops nfs_pageio_write_ops = {
 	.pg_doio = nfs_generic_pg_writepages,
 };
 
-static void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio,
+void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio,
 				  struct inode *inode, int ioflags)
 {
 	nfs_pageio_init(pgio, inode, &nfs_pageio_write_ops,
@@ -1166,13 +1166,7 @@ static void nfs_writeback_done_full(struct rpc_task *task, void *calldata)
 static void nfs_writeback_release_full(void *calldata)
 {
 	struct nfs_write_data	*data = calldata;
-	int ret, status = data->task.tk_status;
-	struct nfs_pageio_descriptor pgio;
-
-	if (data->pnfs_error) {
-		nfs_pageio_init_write_mds(&pgio, data->inode, FLUSH_STABLE);
-		pgio.pg_recoalesce = 1;
-	}
+	int status = data->task.tk_status;
 
 	/* Update attributes as result of writeback. */
 	while (!list_empty(&data->pages)) {
@@ -1188,11 +1182,6 @@ static void nfs_writeback_release_full(void *calldata)
 			req->wb_bytes,
 			(long long)req_offset(req));
 
-		if (data->pnfs_error) {
-			dprintk(", pnfs error = %d\n", data->pnfs_error);
-			goto next;
-		}
-
 		if (status < 0) {
 			nfs_set_pageerror(page);
 			nfs_context_set_write_error(req->wb_context, status);
@@ -1212,19 +1201,7 @@ remove_request:
 	next:
 		nfs_clear_page_tag_locked(req);
 		nfs_end_page_writeback(page);
-		if (data->pnfs_error) {
-			lock_page(page);
-			nfs_pageio_cond_complete(&pgio, page->index);
-			ret = nfs_page_async_flush(&pgio, page, 0);
-			if (ret) {
-				nfs_set_pageerror(page);
-				dprintk("rewrite to MDS error = %d\n", ret);
-			}
-			unlock_page(page);
-		}
 	}
-	if (data->pnfs_error)
-		nfs_pageio_complete(&pgio);
 	nfs_writedata_release(calldata);
 }