30 files changed, 1078 insertions, 469 deletions

diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 293fa0528a6e..73ab220354df 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -78,11 +78,6 @@ nfs4_callback_svc(void *vrqstp)
 
 	set_freezable();
 
-	/*
-	 * FIXME: do we really need to run this under the BKL? If so, please
-	 * add a comment about what it's intended to protect.
-	 */
-	lock_kernel();
 	while (!kthread_should_stop()) {
 		/*
 		 * Listen for a request on the socket
@@ -104,7 +99,6 @@ nfs4_callback_svc(void *vrqstp)
 		preverr = err;
 		svc_process(rqstp);
 	}
-	unlock_kernel();
 	return 0;
 }
 
@@ -160,11 +154,6 @@ nfs41_callback_svc(void *vrqstp)
 
 	set_freezable();
 
-	/*
-	 * FIXME: do we really need to run this under the BKL? If so, please
-	 * add a comment about what it's intended to protect.
-	 */
-	lock_kernel();
 	while (!kthread_should_stop()) {
 		prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE);
 		spin_lock_bh(&serv->sv_cb_lock);
@@ -183,7 +172,6 @@ nfs41_callback_svc(void *vrqstp)
 		}
 		finish_wait(&serv->sv_cb_waitq, &wq);
 	}
-	unlock_kernel();
 	return 0;
 }
 
@@ -397,6 +385,7 @@ static int nfs_callback_authenticate(struct svc_rqst *rqstp)
  */
 static struct svc_version *nfs4_callback_version[] = {
 	[1] = &nfs4_callback_version1,
+	[4] = &nfs4_callback_version4,
 };
 
 static struct svc_stat nfs4_callback_stats;
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index 07baa8254ca1..d4036be0b589 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -106,6 +106,19 @@ struct cb_sequenceres {
 extern unsigned nfs4_callback_sequence(struct cb_sequenceargs *args,
 				       struct cb_sequenceres *res);
 
+extern int nfs41_validate_delegation_stateid(struct nfs_delegation *delegation,
+					     const nfs4_stateid *stateid);
+
+#define RCA4_TYPE_MASK_RDATA_DLG	0
+#define RCA4_TYPE_MASK_WDATA_DLG	1
+
+struct cb_recallanyargs {
+	struct sockaddr	*craa_addr;
+	uint32_t	craa_objs_to_keep;
+	uint32_t	craa_type_mask;
+};
+
+extern unsigned nfs4_callback_recallany(struct cb_recallanyargs *args, void *dummy);
 #endif /* CONFIG_NFS_V4_1 */
 
 extern __be32 nfs4_callback_getattr(struct cb_getattrargs *args, struct cb_getattrres *res);
@@ -114,8 +127,9 @@ extern __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy);
 #ifdef CONFIG_NFS_V4
 extern int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt);
 extern void nfs_callback_down(int minorversion);
+extern int nfs4_validate_delegation_stateid(struct nfs_delegation *delegation,
+					    const nfs4_stateid *stateid);
 #endif /* CONFIG_NFS_V4 */
-
 /*
  * nfs41: Callbacks are expected to not cause substantial latency,
  * so we limit their concurrency to 1 by setting up the maximum number
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index b7da1f54da68..defa9b4c470e 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -61,6 +61,16 @@ out:
 	return res->status;
 }
 
+static int (*nfs_validate_delegation_stateid(struct nfs_client *clp))(struct nfs_delegation *, const nfs4_stateid *)
+{
+#if defined(CONFIG_NFS_V4_1)
+	if (clp->cl_minorversion > 0)
+		return nfs41_validate_delegation_stateid;
+#endif
+	return nfs4_validate_delegation_stateid;
+}
+
+
 __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy)
 {
 	struct nfs_client *clp;
@@ -81,7 +91,8 @@ __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy)
 		inode = nfs_delegation_find_inode(clp, &args->fh);
 		if (inode != NULL) {
 			/* Set up a helper thread to actually return the delegation */
-			switch(nfs_async_inode_return_delegation(inode, &args->stateid)) {
+			switch (nfs_async_inode_return_delegation(inode, &args->stateid,
+								  nfs_validate_delegation_stateid(clp))) {
 				case 0:
 					res = 0;
 					break;
@@ -102,8 +113,31 @@ out:
 	return res;
 }
 
+int nfs4_validate_delegation_stateid(struct nfs_delegation *delegation, const nfs4_stateid *stateid)
+{
+	if (delegation == NULL || memcmp(delegation->stateid.data, stateid->data,
+					 sizeof(delegation->stateid.data)) != 0)
+		return 0;
+	return 1;
+}
+
 #if defined(CONFIG_NFS_V4_1)
 
+int nfs41_validate_delegation_stateid(struct nfs_delegation *delegation, const nfs4_stateid *stateid)
+{
+	if (delegation == NULL)
+		return 0;
+
+	/* seqid is 4-bytes long */
+	if (((u32 *) &stateid->data)[0] != 0)
+		return 0;
+	if (memcmp(&delegation->stateid.data[4], &stateid->data[4],
+		   sizeof(stateid->data)-4))
+		return 0;
+
+	return 1;
+}
+
 /*
  * Validate the sequenceID sent by the server.
  * Return success if the sequenceID is one more than what we last saw on
@@ -227,4 +261,32 @@ out:
 	return res->csr_status;
 }
 
+unsigned nfs4_callback_recallany(struct cb_recallanyargs *args, void *dummy)
+{
+	struct nfs_client *clp;
+	int status;
+	fmode_t flags = 0;
+
+	status = htonl(NFS4ERR_OP_NOT_IN_SESSION);
+	clp = nfs_find_client(args->craa_addr, 4);
+	if (clp == NULL)
+		goto out;
+
+	dprintk("NFS: RECALL_ANY callback request from %s\n",
+		rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR));
+
+	if (test_bit(RCA4_TYPE_MASK_RDATA_DLG, (const unsigned long *)
+		     &args->craa_type_mask))
+		flags = FMODE_READ;
+	if (test_bit(RCA4_TYPE_MASK_WDATA_DLG, (const unsigned long *)
+		     &args->craa_type_mask))
+		flags |= FMODE_WRITE;
+
+	if (flags)
+		nfs_expire_all_delegation_types(clp, flags);
+	status = htonl(NFS4_OK);
+out:
+	dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
+	return status;
+}
 #endif /* CONFIG_NFS_V4_1 */
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 76b0aa0f73bf..8e1a2511c8be 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -23,6 +23,7 @@
 #if defined(CONFIG_NFS_V4_1)
 #define CB_OP_SEQUENCE_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ + \
 					4 + 1 + 3)
+#define CB_OP_RECALLANY_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ)
 #endif /* CONFIG_NFS_V4_1 */
 
 #define NFSDBG_FACILITY NFSDBG_CALLBACK
@@ -326,6 +327,25 @@ out_free:
 	goto out;
 }
 
+static unsigned decode_recallany_args(struct svc_rqst *rqstp,
+				      struct xdr_stream *xdr,
+				      struct cb_recallanyargs *args)
+{
+	uint32_t *p;
+
+	args->craa_addr = svc_addr(rqstp);
+	p = read_buf(xdr, 4);
+	if (unlikely(p == NULL))
+		return htonl(NFS4ERR_BADXDR);
+	args->craa_objs_to_keep = ntohl(*p++);
+	p = read_buf(xdr, 4);
+	if (unlikely(p == NULL))
+		return htonl(NFS4ERR_BADXDR);
+	args->craa_type_mask = ntohl(*p);
+
+	return 0;
+}
+
 #endif /* CONFIG_NFS_V4_1 */
 
 static __be32 encode_string(struct xdr_stream *xdr, unsigned int len, const char *str)
@@ -533,6 +553,7 @@ preprocess_nfs41_op(int nop, unsigned int op_nr, struct callback_op **op)
 	case OP_CB_GETATTR:
 	case OP_CB_RECALL:
 	case OP_CB_SEQUENCE:
+	case OP_CB_RECALL_ANY:
 		*op = &callback_ops[op_nr];
 		break;
 
@@ -540,7 +561,6 @@ preprocess_nfs41_op(int nop, unsigned int op_nr, struct callback_op **op)
 	case OP_CB_NOTIFY_DEVICEID:
 	case OP_CB_NOTIFY:
 	case OP_CB_PUSH_DELEG:
-	case OP_CB_RECALL_ANY:
 	case OP_CB_RECALLABLE_OBJ_AVAIL:
 	case OP_CB_RECALL_SLOT:
 	case OP_CB_WANTS_CANCELLED:
@@ -688,6 +708,11 @@ static struct callback_op callback_ops[] = {
 		.encode_res = (callback_encode_res_t)encode_cb_sequence_res,
 		.res_maxsize = CB_OP_SEQUENCE_RES_MAXSZ,
 	},
+	[OP_CB_RECALL_ANY] = {
+		.process_op = (callback_process_op_t)nfs4_callback_recallany,
+		.decode_args = (callback_decode_arg_t)decode_recallany_args,
+		.res_maxsize = CB_OP_RECALLANY_RES_MAXSZ,
+	},
 #endif /* CONFIG_NFS_V4_1 */
 };
 
@@ -718,3 +743,10 @@ struct svc_version nfs4_callback_version1 = {
 	.vs_dispatch = NULL,
 };
 
+struct svc_version nfs4_callback_version4 = {
+	.vs_vers = 4,
+	.vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1),
+	.vs_proc = nfs4_callback_procedures1,
+	.vs_xdrsize = NFS4_CALLBACK_XDRSIZE,
+	.vs_dispatch = NULL,
+};
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 99ea196f071f..ee77713ce68b 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -1260,10 +1260,20 @@ error:
 static void nfs4_session_set_rwsize(struct nfs_server *server)
 {
 #ifdef CONFIG_NFS_V4_1
+	struct nfs4_session *sess;
+	u32 server_resp_sz;
+	u32 server_rqst_sz;
+
 	if (!nfs4_has_session(server->nfs_client))
 		return;
-	server->rsize = server->nfs_client->cl_session->fc_attrs.max_resp_sz;
-	server->wsize = server->nfs_client->cl_session->fc_attrs.max_rqst_sz;
+	sess = server->nfs_client->cl_session;
+	server_resp_sz = sess->fc_attrs.max_resp_sz - nfs41_maxread_overhead;
+	server_rqst_sz = sess->fc_attrs.max_rqst_sz - nfs41_maxwrite_overhead;
+
+	if (server->rsize > server_resp_sz)
+		server->rsize = server_resp_sz;
+	if (server->wsize > server_rqst_sz)
+		server->wsize = server_rqst_sz;
 #endif /* CONFIG_NFS_V4_1 */
 }
 
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 6dd48a4405b4..2563bebc4c67 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -92,7 +92,7 @@ out:
 	return status;
 }
 
-static void nfs_delegation_claim_opens(struct inode *inode, const nfs4_stateid *stateid)
+static int nfs_delegation_claim_opens(struct inode *inode, const nfs4_stateid *stateid)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_open_context *ctx;
@@ -116,10 +116,11 @@ again:
 			err = nfs_delegation_claim_locks(ctx, state);
 		put_nfs_open_context(ctx);
 		if (err != 0)
-			return;
+			return err;
 		goto again;
 	}
 	spin_unlock(&inode->i_lock);
+	return 0;
 }
 
 /*
@@ -261,30 +262,34 @@ static void nfs_msync_inode(struct inode *inode)
 /*
  * Basic procedure for returning a delegation to the server
  */
-static int __nfs_inode_return_delegation(struct inode *inode, struct nfs_delegation *delegation)
+static int __nfs_inode_return_delegation(struct inode *inode, struct nfs_delegation *delegation, int issync)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
+	int err;
 
-	nfs_msync_inode(inode);
 	/*
 	 * Guard against new delegated open/lock/unlock calls and against
 	 * state recovery
 	 */
 	down_write(&nfsi->rwsem);
-	nfs_delegation_claim_opens(inode, &delegation->stateid);
+	err = nfs_delegation_claim_opens(inode, &delegation->stateid);
 	up_write(&nfsi->rwsem);
-	nfs_msync_inode(inode);
+	if (err)
+		goto out;
 
-	return nfs_do_return_delegation(inode, delegation, 1);
+	err = nfs_do_return_delegation(inode, delegation, issync);
+out:
+	return err;
 }
 
 /*
  * Return all delegations that have been marked for return
  */
-void nfs_client_return_marked_delegations(struct nfs_client *clp)
+int nfs_client_return_marked_delegations(struct nfs_client *clp)
 {
 	struct nfs_delegation *delegation;
 	struct inode *inode;
+	int err = 0;
 
 restart:
 	rcu_read_lock();
@@ -298,12 +303,18 @@ restart:
 		delegation = nfs_detach_delegation_locked(NFS_I(inode), NULL);
 		spin_unlock(&clp->cl_lock);
 		rcu_read_unlock();
-		if (delegation != NULL)
-			__nfs_inode_return_delegation(inode, delegation);
+		if (delegation != NULL) {
+			filemap_flush(inode->i_mapping);
+			err = __nfs_inode_return_delegation(inode, delegation, 0);
+		}
 		iput(inode);
-		goto restart;
+		if (!err)
+			goto restart;
+		set_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state);
+		return err;
 	}
 	rcu_read_unlock();
+	return 0;
 }
 
 /*
@@ -338,8 +349,10 @@ int nfs_inode_return_delegation(struct inode *inode)
 		spin_lock(&clp->cl_lock);
 		delegation = nfs_detach_delegation_locked(nfsi, NULL);
 		spin_unlock(&clp->cl_lock);
-		if (delegation != NULL)
-			err = __nfs_inode_return_delegation(inode, delegation);
+		if (delegation != NULL) {
+			nfs_msync_inode(inode);
+			err = __nfs_inode_return_delegation(inode, delegation, 1);
+		}
 	}
 	return err;
 }
@@ -368,33 +381,47 @@ void nfs_super_return_all_delegations(struct super_block *sb)
 		spin_unlock(&delegation->lock);
 	}
 	rcu_read_unlock();
-	nfs_client_return_marked_delegations(clp);
+	if (nfs_client_return_marked_delegations(clp) != 0)
+		nfs4_schedule_state_manager(clp);
 }
 
-static void nfs_client_mark_return_all_delegations(struct nfs_client *clp)
+static
+void nfs_client_mark_return_all_delegation_types(struct nfs_client *clp, fmode_t flags)
 {
 	struct nfs_delegation *delegation;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(delegation, &clp->cl_delegations, super_list) {
-		set_bit(NFS_DELEGATION_RETURN, &delegation->flags);
-		set_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state);
+		if ((delegation->type == (FMODE_READ|FMODE_WRITE)) && !(flags & FMODE_WRITE))
+			continue;
+		if (delegation->type & flags)
+			nfs_mark_return_delegation(clp, delegation);
 	}
 	rcu_read_unlock();
 }
 
+static void nfs_client_mark_return_all_delegations(struct nfs_client *clp)
+{
+	nfs_client_mark_return_all_delegation_types(clp, FMODE_READ|FMODE_WRITE);
+}
+
 static void nfs_delegation_run_state_manager(struct nfs_client *clp)
 {
 	if (test_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state))
 		nfs4_schedule_state_manager(clp);
 }
 
-void nfs_expire_all_delegations(struct nfs_client *clp)
+void nfs_expire_all_delegation_types(struct nfs_client *clp, fmode_t flags)
 {
-	nfs_client_mark_return_all_delegations(clp);
+	nfs_client_mark_return_all_delegation_types(clp, flags);
 	nfs_delegation_run_state_manager(clp);
 }
 
+void nfs_expire_all_delegations(struct nfs_client *clp)
+{
+	nfs_expire_all_delegation_types(clp, FMODE_READ|FMODE_WRITE);
+}
+
 /*
  * Return all delegations following an NFS4ERR_CB_PATH_DOWN error.
  */
@@ -413,8 +440,7 @@ static void nfs_client_mark_return_unreferenced_delegations(struct nfs_client *c
 	list_for_each_entry_rcu(delegation, &clp->cl_delegations, super_list) {
 		if (test_and_clear_bit(NFS_DELEGATION_REFERENCED, &delegation->flags))
 			continue;
-		set_bit(NFS_DELEGATION_RETURN, &delegation->flags);
-		set_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state);
+		nfs_mark_return_delegation(clp, delegation);
 	}
 	rcu_read_unlock();
 }
@@ -428,18 +454,21 @@ void nfs_expire_unreferenced_delegations(struct nfs_client *clp)
 /*
  * Asynchronous delegation recall!
  */
-int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid)
+int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid,
+				      int (*validate_stateid)(struct nfs_delegation *delegation,
+							      const nfs4_stateid *stateid))
 {
 	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
 	struct nfs_delegation *delegation;
 
 	rcu_read_lock();
 	delegation = rcu_dereference(NFS_I(inode)->delegation);
-	if (delegation == NULL || memcmp(delegation->stateid.data, stateid->data,
-				sizeof(delegation->stateid.data)) != 0) {
+
+	if (!validate_stateid(delegation, stateid)) {
 		rcu_read_unlock();
 		return -ENOENT;
 	}
+
 	nfs_mark_return_delegation(clp, delegation);
 	rcu_read_unlock();
 	nfs_delegation_run_state_manager(clp);
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index 09f383795174..944b627ec6e1 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -34,15 +34,18 @@ enum {
 int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res);
 void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res);
 int nfs_inode_return_delegation(struct inode *inode);
-int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid);
+int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid,
+				      int (*validate_stateid)(struct nfs_delegation *delegation,
+							      const nfs4_stateid *stateid));
 void nfs_inode_return_delegation_noreclaim(struct inode *inode);
 
 struct inode *nfs_delegation_find_inode(struct nfs_client *clp, const struct nfs_fh *fhandle);
 void nfs_super_return_all_delegations(struct super_block *sb);
 void nfs_expire_all_delegations(struct nfs_client *clp);
+void nfs_expire_all_delegation_types(struct nfs_client *clp, fmode_t flags);
 void nfs_expire_unreferenced_delegations(struct nfs_client *clp);
 void nfs_handle_cb_pathdown(struct nfs_client *clp);
-void nfs_client_return_marked_delegations(struct nfs_client *clp);
+int nfs_client_return_marked_delegations(struct nfs_client *clp);
 
 void nfs_delegation_mark_reclaim(struct nfs_client *clp);
 void nfs_delegation_reap_unclaimed(struct nfs_client *clp);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 7cb298525eef..2c5ace4f00a7 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1579,55 +1579,46 @@ static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct dentry *dentry = NULL, *rehash = NULL;
 	int error = -EBUSY;
 
-	/*
-	 * To prevent any new references to the target during the rename,
-	 * we unhash the dentry and free the inode in advance.
-	 */
-	if (!d_unhashed(new_dentry)) {
-		d_drop(new_dentry);
-		rehash = new_dentry;
-	}
-
 	dfprintk(VFS, "NFS: rename(%s/%s -> %s/%s, ct=%d)\n",
 		 old_dentry->d_parent->d_name.name, old_dentry->d_name.name,
 		 new_dentry->d_parent->d_name.name, new_dentry->d_name.name,
 		 atomic_read(&new_dentry->d_count));
 
 	/*
-	 * First check whether the target is busy ... we can't
-	 * safely do _any_ rename if the target is in use.
-	 *
-	 * For files, make a copy of the dentry and then do a 
-	 * silly-rename. If the silly-rename succeeds, the
-	 * copied dentry is hashed and becomes the new target.
+	 * For non-directories, check whether the target is busy and if so,
+	 * make a copy of the dentry and then do a silly-rename. If the
+	 * silly-rename succeeds, the copied dentry is hashed and becomes
+	 * the new target.
 	 */
-	if (!new_inode)
-		goto go_ahead;
-	if (S_ISDIR(new_inode->i_mode)) {
-		error = -EISDIR;
-		if (!S_ISDIR(old_inode->i_mode))
-			goto out;
-	} else if (atomic_read(&new_dentry->d_count) > 2) {
-		int err;
-		/* copy the target dentry's name */
-		dentry = d_alloc(new_dentry->d_parent,
-				 &new_dentry->d_name);
-		if (!dentry)
-			goto out;
+	if (new_inode && !S_ISDIR(new_inode->i_mode)) {
+		/*
+		 * To prevent any new references to the target during the
+		 * rename, we unhash the dentry in advance.
+		 */
+		if (!d_unhashed(new_dentry)) {
+			d_drop(new_dentry);
+			rehash = new_dentry;
+		}
+
+		if (atomic_read(&new_dentry->d_count) > 2) {
+			int err;
+
+			/* copy the target dentry's name */
+			dentry = d_alloc(new_dentry->d_parent,
+					 &new_dentry->d_name);
+			if (!dentry)
+				goto out;
 
-		/* silly-rename the existing target ... */
-		err = nfs_sillyrename(new_dir, new_dentry);
-		if (!err) {
-			new_dentry = rehash = dentry;
+			/* silly-rename the existing target ... */
+			err = nfs_sillyrename(new_dir, new_dentry);
+			if (err)
+				goto out;
+
+			new_dentry = dentry;
 			new_inode = NULL;
-			/* instantiate the replacement target */
-			d_instantiate(new_dentry, NULL);
-		} else if (atomic_read(&new_dentry->d_count) > 1)
-			/* dentry still busy? */
-			goto out;
+		}
 	}
 
-go_ahead:
 	/*
 	 * ... prune child dentries and writebacks if needed.
 	 */
diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c
index f4d54ba97cc6..95e1ca765d47 100644
--- a/fs/nfs/dns_resolve.c
+++ b/fs/nfs/dns_resolve.c
@@ -146,7 +146,7 @@ static int nfs_dns_show(struct seq_file *m, struct cache_detail *cd,
 	return 0;
 }
 
-struct nfs_dns_ent *nfs_dns_lookup(struct cache_detail *cd,
+static struct nfs_dns_ent *nfs_dns_lookup(struct cache_detail *cd,
 		struct nfs_dns_ent *key)
 {
 	struct cache_head *ch;
@@ -159,7 +159,7 @@ struct nfs_dns_ent *nfs_dns_lookup(struct cache_detail *cd,
 	return container_of(ch, struct nfs_dns_ent, h);
 }
 
-struct nfs_dns_ent *nfs_dns_update(struct cache_detail *cd,
+static struct nfs_dns_ent *nfs_dns_update(struct cache_detail *cd,
 		struct nfs_dns_ent *new,
 		struct nfs_dns_ent *key)
 {
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index e21b1bb9972f..29e464d23b32 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -30,6 +30,15 @@ static inline int nfs4_has_session(const struct nfs_client *clp)
 	return 0;
 }
 
+static inline int nfs4_has_persistent_session(const struct nfs_client *clp)
+{
+#ifdef CONFIG_NFS_V4_1
+	if (nfs4_has_session(clp))
+		return (clp->cl_session->flags & SESSION4_PERSIST);
+#endif /* CONFIG_NFS_V4_1 */
+	return 0;
+}
+
 struct nfs_clone_mount {
 	const struct super_block *sb;
 	const struct dentry *dentry;
@@ -156,6 +165,7 @@ struct vfsmount *nfs_do_refmount(const struct vfsmount *mnt_parent, struct dentr
 
 /* callback_xdr.c */
 extern struct svc_version nfs4_callback_version1;
+extern struct svc_version nfs4_callback_version4;
 
 /* pagelist.c */
 extern int __init nfs_init_nfspagecache(void);
@@ -177,24 +187,14 @@ extern __be32 * nfs_decode_dirent(__be32 *, struct nfs_entry *, int);
 extern struct rpc_procinfo nfs3_procedures[];
 extern __be32 *nfs3_decode_dirent(__be32 *, struct nfs_entry *, int);
 
-/* nfs4proc.c */
-static inline void nfs4_restart_rpc(struct rpc_task *task,
-				    const struct nfs_client *clp)
-{
-#ifdef CONFIG_NFS_V4_1
-	if (nfs4_has_session(clp) &&
-	    test_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state)) {
-		rpc_restart_call_prepare(task);
-		return;
-	}
-#endif /* CONFIG_NFS_V4_1 */
-	rpc_restart_call(task);
-}
-
 /* nfs4xdr.c */
 #ifdef CONFIG_NFS_V4
 extern __be32 *nfs4_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus);
 #endif
+#ifdef CONFIG_NFS_V4_1
+extern const u32 nfs41_maxread_overhead;
+extern const u32 nfs41_maxwrite_overhead;
+#endif
 
 /* nfs4proc.c */
 #ifdef CONFIG_NFS_V4
@@ -273,20 +273,6 @@ extern int _nfs4_call_sync_session(struct nfs_server *server,
 				   struct nfs4_sequence_res *res,
 				   int cache_reply);
 
-#ifdef CONFIG_NFS_V4_1
-extern void nfs41_sequence_free_slot(const struct nfs_client *,
-				     struct nfs4_sequence_res *res);
-#endif /* CONFIG_NFS_V4_1 */
-
-static inline void nfs4_sequence_free_slot(const struct nfs_client *clp,
-					   struct nfs4_sequence_res *res)
-{
-#ifdef CONFIG_NFS_V4_1
-	if (nfs4_has_session(clp))
-		nfs41_sequence_free_slot(clp, res);
-#endif /* CONFIG_NFS_V4_1 */
-}
-
 /*
  * Determine the device name as a string
  */
@@ -380,3 +366,15 @@ unsigned int nfs_page_array_len(unsigned int base, size_t len)
 	return ((unsigned long)len + (unsigned long)base +
 		PAGE_SIZE - 1) >> PAGE_SHIFT;
 }
+
+/*
+ * Helper for restarting RPC calls in the possible presence of NFSv4.1
+ * sessions.
+ */
+static inline void nfs_restart_rpc(struct rpc_task *task, const struct nfs_client *clp)
+{
+	if (nfs4_has_session(clp))
+		rpc_restart_call_prepare(task);
+	else
+		rpc_restart_call(task);
+}
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 6ea07a3c75d4..7e57b04e4014 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -44,7 +44,8 @@ enum nfs4_client_state {
 	NFS4CLNT_RECLAIM_REBOOT,
 	NFS4CLNT_RECLAIM_NOGRACE,
 	NFS4CLNT_DELEGRETURN,
-	NFS4CLNT_SESSION_SETUP,
+	NFS4CLNT_SESSION_RESET,
+	NFS4CLNT_SESSION_DRAINING,
 };
 
 /*
@@ -180,6 +181,7 @@ struct nfs4_state_recovery_ops {
 	int (*recover_lock)(struct nfs4_state *, struct file_lock *);
 	int (*establish_clid)(struct nfs_client *, struct rpc_cred *);
 	struct rpc_cred * (*get_clid_cred)(struct nfs_client *);
+	int (*reclaim_complete)(struct nfs_client *);
 };
 
 struct nfs4_state_maintenance_ops {
@@ -200,9 +202,11 @@ extern ssize_t nfs4_listxattr(struct dentry *, char *, size_t);
 /* nfs4proc.c */
 extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *);
 extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct rpc_cred *);
+extern int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred);
 extern int nfs4_proc_async_renew(struct nfs_client *, struct rpc_cred *);
 extern int nfs4_proc_renew(struct nfs_client *, struct rpc_cred *);
 extern int nfs4_init_clientid(struct nfs_client *, struct rpc_cred *);
+extern int nfs41_init_clientid(struct nfs_client *, struct rpc_cred *);
 extern int nfs4_do_close(struct path *path, struct nfs4_state *state, int wait);
 extern struct dentry *nfs4_atomic_open(struct inode *, struct dentry *, struct nameidata *);
 extern int nfs4_open_revalidate(struct inode *, struct dentry *, int, struct nameidata *);
@@ -218,9 +222,11 @@ extern int nfs4_setup_sequence(struct nfs_client *clp,
 		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 *, int reset);
+extern int nfs4_proc_create_session(struct nfs_client *);
 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);
 #else /* CONFIG_NFS_v4_1 */
 static inline int nfs4_setup_sequence(struct nfs_client *clp,
 		struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
@@ -267,6 +273,7 @@ extern void nfs4_state_set_mode_locked(struct nfs4_state *, fmode_t);
 extern void nfs4_schedule_state_recovery(struct nfs_client *);
 extern void nfs4_schedule_state_manager(struct nfs_client *);
 extern int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *state);
+extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags);
 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);
@@ -287,6 +294,7 @@ struct nfs4_mount_data;
 
 /* callback_xdr.c */
 extern struct svc_version nfs4_callback_version1;
+extern struct svc_version nfs4_callback_version4;
 
 #else
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 741a562177fc..9f5f11ecfd93 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -270,11 +270,18 @@ static int nfs4_handle_exception(const struct nfs_server *server, int errorcode,
 		case -NFS4ERR_SEQ_MISORDERED:
 			dprintk("%s ERROR: %d Reset session\n", __func__,
 				errorcode);
-			set_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state);
+			nfs4_schedule_state_recovery(clp);
 			exception->retry = 1;
-			/* FALLTHROUGH */
+			break;
 #endif /* !defined(CONFIG_NFS_V4_1) */
 		case -NFS4ERR_FILE_OPEN:
+			if (exception->timeout > HZ) {
+				/* We have retried a decent amount, time to
+				 * fail
+				 */
+				ret = -EBUSY;
+				break;
+			}
 		case -NFS4ERR_GRACE:
 		case -NFS4ERR_DELAY:
 			ret = nfs4_delay(server->client, &exception->timeout);
@@ -311,48 +318,54 @@ static void renew_lease(const struct nfs_server *server, unsigned long timestamp
  * so we need to scan down from highest_used_slotid to 0 looking for the now
  * highest slotid in use.
  * If none found, highest_used_slotid is set to -1.
+ *
+ * Must be called while holding tbl->slot_tbl_lock
  */
 static void
 nfs4_free_slot(struct nfs4_slot_table *tbl, u8 free_slotid)
 {
 	int slotid = free_slotid;
 
-	spin_lock(&tbl->slot_tbl_lock);
 	/* clear used bit in bitmap */
 	__clear_bit(slotid, tbl->used_slots);
 
 	/* update highest_used_slotid when it is freed */
 	if (slotid == tbl->highest_used_slotid) {
 		slotid = find_last_bit(tbl->used_slots, tbl->max_slots);
-		if (slotid >= 0 && slotid < tbl->max_slots)
+		if (slotid < tbl->max_slots)
 			tbl->highest_used_slotid = slotid;
 		else
 			tbl->highest_used_slotid = -1;
 	}
-	rpc_wake_up_next(&tbl->slot_tbl_waitq);
-	spin_unlock(&tbl->slot_tbl_lock);
 	dprintk("%s: free_slotid %u highest_used_slotid %d\n", __func__,
 		free_slotid, tbl->highest_used_slotid);
 }
 
-void nfs41_sequence_free_slot(const struct nfs_client *clp,
+static void nfs41_sequence_free_slot(const struct nfs_client *clp,
 			      struct nfs4_sequence_res *res)
 {
 	struct nfs4_slot_table *tbl;
 
-	if (!nfs4_has_session(clp)) {
-		dprintk("%s: No session\n", __func__);
-		return;
-	}
 	tbl = &clp->cl_session->fc_slot_table;
 	if (res->sr_slotid == NFS4_MAX_SLOT_TABLE) {
-		dprintk("%s: No slot\n", __func__);
 		/* just wake up the next guy waiting since
 		 * we may have not consumed a slot after all */
-		rpc_wake_up_next(&tbl->slot_tbl_waitq);
+		dprintk("%s: No slot\n", __func__);
 		return;
 	}
+
+	spin_lock(&tbl->slot_tbl_lock);
 	nfs4_free_slot(tbl, res->sr_slotid);
+
+	/* Signal state manager thread if session is drained */
+	if (test_bit(NFS4CLNT_SESSION_DRAINING, &clp->cl_state)) {
+		if (tbl->highest_used_slotid == -1) {
+			dprintk("%s COMPLETE: Session Drained\n", __func__);
+			complete(&clp->cl_session->complete);
+		}
+	} else
+		rpc_wake_up_next(&tbl->slot_tbl_waitq);
+	spin_unlock(&tbl->slot_tbl_lock);