Merge branch 'for-2.6.38' of git://linux-nfs.org/~bfields/linux

* 'for-2.6.38' of git://linux-nfs.org/~bfields/linux: (62 commits) nfsd4: fix callback restarting nfsd: break lease on unlink, link, and rename nfsd4: break lease on nfsd setattr nfsd: don't support msnfs export option nfsd4: initialize cb_per_client nfsd4: allow restarting callbacks nfsd4: simplify nfsd4_cb_prepare nfsd4: give out delegations more quickly in 4.1 case nfsd4: add helper function to run callbacks nfsd4: make sure sequence flags are set after destroy_session nfsd4: re-probe callback on connection loss nfsd4: set sequence flag when backchannel is down nfsd4: keep finer-grained callback status rpc: allow xprt_class->setup to return a preexisting xprt rpc: keep backchannel xprt as long as server connection rpc: move sk_bc_xprt to svc_xprt nfsd4: allow backchannel recovery nfsd4: support BIND_CONN_TO_SESSION nfsd4: modify session list under cl_lock Documentation: fl_mylease no longer exists ... Fix up conflicts in fs/nfsd/vfs.c with the vfs-scale work. The vfs-scale work touched some msnfs cases, and this merge removes support for that entirely, so the conflict was trivial to resolve.
author: Linus Torvalds <torvalds@linux-foundation.org> 2011-01-15 00:17:26 +0300
committer: Linus Torvalds <torvalds@linux-foundation.org> 2011-01-15 00:17:26 +0300
commit: 18bce371ae09af6c20ee62c1092a4d1d0e84dd49 (patch)
tree: f3467fafd8e49392e3f6efef7b88a7b4dd3b7b06
parent: ec08bdb148767f1193f5f3028749ed865ac27181 (diff)
parent: a8f2800b4f7b76cecb7209cb6a7d2b14904fc711 (diff)
download: linux-18bce371ae09af6c20ee62c1092a4d1d0e84dd49.tar.xz
38 files changed, 608 insertions, 383 deletions
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 977d8919cc69..ef9349a4b5d1 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -343,7 +343,6 @@ prototypes:
 	int (*fl_grant)(struct file_lock *, struct file_lock *, int);
 	void (*fl_release_private)(struct file_lock *);
 	void (*fl_break)(struct file_lock *); /* break_lease callback */
-	int (*fl_mylease)(struct file_lock *, struct file_lock *);
 	int (*fl_change)(struct file_lock **, int);
 
 locking rules:
@@ -353,7 +352,6 @@ fl_notify:		yes		no
 fl_grant:		no		no
 fl_release_private:	maybe		no
 fl_break:		yes		no
-fl_mylease:		yes		no
 fl_change		yes		no
 
 --------------------------- buffer_head -----------------------------------
diff --git a/fs/locks.c b/fs/locks.c
index 08415b2a6d36..0f3998291f78 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -444,15 +444,9 @@ static void lease_release_private_callback(struct file_lock *fl)
 	fl->fl_file->f_owner.signum = 0;
 }
 
-static int lease_mylease_callback(struct file_lock *fl, struct file_lock *try)
-{
-	return fl->fl_file == try->fl_file;
-}
-
 static const struct lock_manager_operations lease_manager_ops = {
 	.fl_break = lease_break_callback,
 	.fl_release_private = lease_release_private_callback,
-	.fl_mylease = lease_mylease_callback,
 	.fl_change = lease_modify,
 };
 
@@ -1405,7 +1399,7 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp)
 	for (before = &inode->i_flock;
 			((fl = *before) != NULL) && IS_LEASE(fl);
 			before = &fl->fl_next) {
-		if (lease->fl_lmops->fl_mylease(fl, lease))
+		if (fl->fl_file == filp)
 			my_before = before;
 		else if (fl->fl_type == (F_INPROGRESS | F_UNLCK))
 			/*
diff --git a/include/linux/nfs4_acl.h b/fs/nfsd/acl.h
index c9c05a78e9bb..34e5c40af5ef 100644
--- a/include/linux/nfs4_acl.h
+++ b/fs/nfsd/acl.h
@@ -1,6 +1,4 @@
 /*
- *  include/linux/nfs4_acl.c
- *
  *  Common NFSv4 ACL handling definitions.
  *
  *  Copyright (c) 2002 The Regents of the University of Michigan.
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index c0fcb7ab7f6d..8b31e5f8795d 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -1,4 +1,3 @@
-#define MSNFS	/* HACK HACK */
 /*
  * NFS exporting and validation.
  *
@@ -1444,9 +1443,6 @@ static struct flags {
 	{ NFSEXP_NOSUBTREECHECK, {"no_subtree_check", ""}},
 	{ NFSEXP_NOAUTHNLM, {"insecure_locks", ""}},
 	{ NFSEXP_V4ROOT, {"v4root", ""}},
-#ifdef MSNFS
-	{ NFSEXP_MSNFS, {"msnfs", ""}},
-#endif
 	{ 0, {"", ""}}
 };
 
diff --git a/include/linux/nfsd_idmap.h b/fs/nfsd/idmap.h
index d4a2ac18bd4c..2f3be1321534 100644
--- a/include/linux/nfsd_idmap.h
+++ b/fs/nfsd/idmap.h
@@ -1,6 +1,4 @@
 /*
- *  include/linux/nfsd_idmap.h
- *
  *  Mapping of UID to name and vice versa.
  *
  *  Copyright (c) 2002, 2003 The Regents of the University of
@@ -56,8 +54,8 @@ static inline void nfsd_idmap_shutdown(void)
 }
 #endif
 
-int nfsd_map_name_to_uid(struct svc_rqst *, const char *, size_t, __u32 *);
-int nfsd_map_name_to_gid(struct svc_rqst *, const char *, size_t, __u32 *);
+__be32 nfsd_map_name_to_uid(struct svc_rqst *, const char *, size_t, __u32 *);
+__be32 nfsd_map_name_to_gid(struct svc_rqst *, const char *, size_t, __u32 *);
 int nfsd_map_uid_to_name(struct svc_rqst *, __u32, char *);
 int nfsd_map_gid_to_name(struct svc_rqst *, __u32, char *);
 
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 5b7e3021e06b..2247fc91d5e9 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -151,10 +151,10 @@ nfsd3_proc_read(struct svc_rqst *rqstp, struct nfsd3_readargs *argp,
 	__be32	nfserr;
 	u32	max_blocksize = svc_max_payload(rqstp);
 
-	dprintk("nfsd: READ(3) %s %lu bytes at %lu\n",
+	dprintk("nfsd: READ(3) %s %lu bytes at %Lu\n",
 				SVCFH_fmt(&argp->fh),
 				(unsigned long) argp->count,
-				(unsigned long) argp->offset);
+				(unsigned long long) argp->offset);
 
 	/* Obtain buffer pointer for payload.
 	 * 1 (status) + 22 (post_op_attr) + 1 (count) + 1 (eof)
@@ -191,10 +191,10 @@ nfsd3_proc_write(struct svc_rqst *rqstp, struct nfsd3_writeargs *argp,
 	__be32	nfserr;
 	unsigned long cnt = argp->len;
 
-	dprintk("nfsd: WRITE(3)    %s %d bytes at %ld%s\n",
+	dprintk("nfsd: WRITE(3)    %s %d bytes at %Lu%s\n",
 				SVCFH_fmt(&argp->fh),
 				argp->len,
-				(unsigned long) argp->offset,
+				(unsigned long long) argp->offset,
 				argp->stable? " stable" : "");
 
 	fh_copy(&resp->fh, &argp->fh);
diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index e48052615159..ad88f1c0a4c3 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -36,7 +36,7 @@
 
 #include <linux/slab.h>
 #include <linux/nfs_fs.h>
-#include <linux/nfs4_acl.h>
+#include "acl.h"
 
 
 /* mode bit translations: */
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 21a63da305ff..3be975e18919 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -628,10 +628,8 @@ static int max_cb_time(void)
 	return max(nfsd4_lease/10, (time_t)1) * HZ;
 }
 
-/* Reference counting, callback cleanup, etc., all look racy as heck.
- * And why is cl_cb_set an atomic? */
 
-int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn)
+static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn, struct nfsd4_session *ses)
 {
 	struct rpc_timeout	timeparms = {
 		.to_initval	= max_cb_time(),
@@ -641,6 +639,7 @@ int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn)
 		.net		= &init_net,
 		.address	= (struct sockaddr *) &conn->cb_addr,
 		.addrsize	= conn->cb_addrlen,
+		.saddress	= (struct sockaddr *) &conn->cb_saddr,
 		.timeout	= &timeparms,
 		.program	= &cb_program,
 		.version	= 0,
@@ -657,6 +656,10 @@ int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn)
 		args.protocol = XPRT_TRANSPORT_TCP;
 		clp->cl_cb_ident = conn->cb_ident;
 	} else {
+		if (!conn->cb_xprt)
+			return -EINVAL;
+		clp->cl_cb_conn.cb_xprt = conn->cb_xprt;
+		clp->cl_cb_session = ses;
 		args.bc_xprt = conn->cb_xprt;
 		args.prognumber = clp->cl_cb_session->se_cb_prog;
 		args.protocol = XPRT_TRANSPORT_BC_TCP;
@@ -679,14 +682,20 @@ static void warn_no_callback_path(struct nfs4_client *clp, int reason)
 		(int)clp->cl_name.len, clp->cl_name.data, reason);
 }
 
+static void nfsd4_mark_cb_down(struct nfs4_client *clp, int reason)
+{
+	clp->cl_cb_state = NFSD4_CB_DOWN;
+	warn_no_callback_path(clp, reason);
+}
+
 static void nfsd4_cb_probe_done(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_client *clp = container_of(calldata, struct nfs4_client, cl_cb_null);
 
 	if (task->tk_status)
-		warn_no_callback_path(clp, task->tk_status);
+		nfsd4_mark_cb_down(clp, task->tk_status);
 	else
-		atomic_set(&clp->cl_cb_set, 1);
+		clp->cl_cb_state = NFSD4_CB_UP;
 }
 
 static const struct rpc_call_ops nfsd4_cb_probe_ops = {
@@ -709,6 +718,11 @@ int set_callback_cred(void)
 
 static struct workqueue_struct *callback_wq;
 
+static void run_nfsd4_cb(struct nfsd4_callback *cb)
+{
+	queue_work(callback_wq, &cb->cb_work);
+}
+
 static void do_probe_callback(struct nfs4_client *clp)
 {
 	struct nfsd4_callback *cb = &clp->cl_cb_null;
@@ -723,7 +737,7 @@ static void do_probe_callback(struct nfs4_client *clp)
 
 	cb->cb_ops = &nfsd4_cb_probe_ops;
 
-	queue_work(callback_wq, &cb->cb_work);
+	run_nfsd4_cb(cb);
 }
 
 /*
@@ -732,14 +746,21 @@ static void do_probe_callback(struct nfs4_client *clp)
  */
 void nfsd4_probe_callback(struct nfs4_client *clp)
 {
+	/* XXX: atomicity?  Also, should we be using cl_cb_flags? */
+	clp->cl_cb_state = NFSD4_CB_UNKNOWN;
 	set_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_cb_flags);
 	do_probe_callback(clp);
 }
 
-void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *conn)
+void nfsd4_probe_callback_sync(struct nfs4_client *clp)
 {
-	BUG_ON(atomic_read(&clp->cl_cb_set));
+	nfsd4_probe_callback(clp);
+	flush_workqueue(callback_wq);
+}
 
+void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *conn)
+{
+	clp->cl_cb_state = NFSD4_CB_UNKNOWN;
 	spin_lock(&clp->cl_lock);
 	memcpy(&clp->cl_cb_conn, conn, sizeof(struct nfs4_cb_conn));
 	spin_unlock(&clp->cl_lock);
@@ -750,24 +771,14 @@ void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *conn)
  * If the slot is available, then mark it busy.  Otherwise, set the
  * thread for sleeping on the callback RPC wait queue.
  */
-static int nfsd41_cb_setup_sequence(struct nfs4_client *clp,
-		struct rpc_task *task)
+static bool nfsd41_cb_get_slot(struct nfs4_client *clp, struct rpc_task *task)
 {
-	u32 *ptr = (u32 *)clp->cl_cb_session->se_sessionid.data;
-	int status = 0;
-
-	dprintk("%s: %u:%u:%u:%u\n", __func__,
-		ptr[0], ptr[1], ptr[2], ptr[3]);
-
 	if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) {
 		rpc_sleep_on(&clp->cl_cb_waitq, task, NULL);
 		dprintk("%s slot is busy\n", __func__);
-		status = -EAGAIN;
-		goto out;
+		return false;
 	}
-out:
-	dprintk("%s status=%d\n", __func__, status);
-	return status;
+	return true;
 }
 
 /*
@@ -780,20 +791,19 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata)
 	struct nfs4_delegation *dp = container_of(cb, struct nfs4_delegation, dl_recall);
 	struct nfs4_client *clp = dp->dl_client;
 	u32 minorversion = clp->cl_minorversion;
-	int status = 0;
 
 	cb->cb_minorversion = minorversion;
 	if (minorversion) {
-		status = nfsd41_cb_setup_sequence(clp, task);
-		if (status) {
-			if (status != -EAGAIN) {
-				/* terminate rpc task */
-				task->tk_status = status;
-				task->tk_action = NULL;
-			}
+		if (!nfsd41_cb_get_slot(clp, task))
 			return;
-		}
 	}
+	spin_lock(&clp->cl_lock);
+	if (list_empty(&cb->cb_per_client)) {
+		/* This is the first call, not a restart */
+		cb->cb_done = false;
+		list_add(&cb->cb_per_client, &clp->cl_callbacks);
+	}
+	spin_unlock(&clp->cl_lock);
 	rpc_call_start(task);
 }
 
@@ -829,15 +839,18 @@ static void nfsd4_cb_recall_done(struct rpc_task *task, void *calldata)
 
 	nfsd4_cb_done(task, calldata);
 
-	if (current_rpc_client == NULL) {
-		/* We're shutting down; give up. */
-		/* XXX: err, or is it ok just to fall through
-		 * and rpc_restart_call? */
+	if (current_rpc_client != task->tk_client) {
+		/* We're shutting down or changing cl_cb_client; leave
+		 * it to nfsd4_process_cb_update to restart the call if
+		 * necessary. */
 		return;
 	}
 
+	if (cb->cb_done)
+		return;
 	switch (task->tk_status) {
 	case 0:
+		cb->cb_done = true;
 		return;
 	case -EBADHANDLE:
 	case -NFS4ERR_BAD_STATEID:
@@ -846,32 +859,30 @@ static void nfsd4_cb_recall_done(struct rpc_task *task, void *calldata)
 		break;
 	default:
 		/* Network partition? */
-		atomic_set(&clp->cl_cb_set, 0);
-		warn_no_callback_path(clp, task->tk_status);
-		if (current_rpc_client != task->tk_client) {
-			/* queue a callback on the new connection: */
-			atomic_inc(&dp->dl_count);
-			nfsd4_cb_recall(dp);
-			return;
-		}
+		nfsd4_mark_cb_down(clp, task->tk_status);
 	}
 	if (dp->dl_retries--) {
 		rpc_delay(task, 2*HZ);
 		task->tk_status = 0;
 		rpc_restart_call_prepare(task);
 		return;
-	} else {
-		atomic_set(&clp->cl_cb_set, 0);
-		warn_no_callback_path(clp, task->tk_status);
 	}
+	nfsd4_mark_cb_down(clp, task->tk_status);
+	cb->cb_done = true;
 }
 
 static void nfsd4_cb_recall_release(void *calldata)
 {
 	struct nfsd4_callback *cb = calldata;
+	struct nfs4_client *clp = cb->cb_clp;
 	struct nfs4_delegation *dp = container_of(cb, struct nfs4_delegation, dl_recall);
 
-	nfs4_put_delegation(dp);
+	if (cb->cb_done) {
+		spin_lock(&clp->cl_lock);
+		list_del(&cb->cb_per_client);
+		spin_unlock(&clp->cl_lock);
+		nfs4_put_delegation(dp);
+	}
 }
 
 static const struct rpc_call_ops nfsd4_cb_recall_ops = {
@@ -906,16 +917,33 @@ void nfsd4_shutdown_callback(struct nfs4_client *clp)
 	flush_workqueue(callback_wq);
 }
 
-void nfsd4_release_cb(struct nfsd4_callback *cb)
+static void nfsd4_release_cb(struct nfsd4_callback *cb)
 {
 	if (cb->cb_ops->rpc_release)
 		cb->cb_ops->rpc_release(cb);
 }
 
-void nfsd4_process_cb_update(struct nfsd4_callback *cb)
+/* requires cl_lock: */
+static struct nfsd4_conn * __nfsd4_find_backchannel(struct nfs4_client *clp)
+{
+	struct nfsd4_session *s;
+	struct nfsd4_conn *c;
+
+	list_for_each_entry(s, &clp->cl_sessions, se_perclnt) {
+		list_for_each_entry(c, &s->se_conns, cn_persession) {
+			if (c->cn_flags & NFS4_CDFC4_BACK)
+				return c;
+		}
+	}
+	return NULL;
+}
+
+static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
 {
 	struct nfs4_cb_conn conn;
 	struct nfs4_client *clp = cb->cb_clp;
+	struct nfsd4_session *ses = NULL;
+	struct nfsd4_conn *c;
 	int err;
 
 	/*
@@ -926,6 +954,10 @@ void nfsd4_process_cb_update(struct nfsd4_callback *cb)
 		rpc_shutdown_client(clp->cl_cb_client);
 		clp->cl_cb_client = NULL;
 	}
+	if (clp->cl_cb_conn.cb_xprt) {
+		svc_xprt_put(clp->cl_cb_conn.cb_xprt);
+		clp->cl_cb_conn.cb_xprt = NULL;
+	}
 	if (test_bit(NFSD4_CLIENT_KILL, &clp->cl_cb_flags))
 		return;
 	spin_lock(&clp->cl_lock);
@@ -936,11 +968,22 @@ void nfsd4_process_cb_update(struct nfsd4_callback *cb)
 	BUG_ON(!clp->cl_cb_flags);
 	clear_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_cb_flags);
 	memcpy(&conn, &cb->cb_clp->cl_cb_conn, sizeof(struct nfs4_cb_conn));
+	c = __nfsd4_find_backchannel(clp);
+	if (c) {
+		svc_xprt_get(c->cn_xprt);
+		conn.cb_xprt = c->cn_xprt;
+		ses = c->cn_session;
+	}
 	spin_unlock(&clp->cl_lock);
 
-	err = setup_callback_client(clp, &conn);
-	if (err)
+	err = setup_callback_client(clp, &conn, ses);
+	if (err) {
 		warn_no_callback_path(clp, err);
+		return;
+	}
+	/* Yay, the callback channel's back! Restart any callbacks: */
+	list_for_each_entry(cb, &clp->cl_callbacks, cb_per_client)
+		run_nfsd4_cb(cb);
 }
 
 void nfsd4_do_callback_rpc(struct work_struct *w)
@@ -965,10 +1008,11 @@ void nfsd4_do_callback_rpc(struct work_struct *w)
 void nfsd4_cb_recall(struct nfs4_delegation *dp)
 {
 	struct nfsd4_callback *cb = &dp->dl_recall;
+	struct nfs4_client *clp = dp->dl_client;
 
 	dp->dl_retries = 1;
 	cb->cb_op = dp;
-	cb->cb_clp = dp->dl_client;
+	cb->cb_clp = clp;
 	cb->cb_msg.rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_RECALL];
 	cb->cb_msg.rpc_argp = cb;
 	cb->cb_msg.rpc_resp = cb;
@@ -977,5 +1021,8 @@ void nfsd4_cb_recall(struct nfs4_delegation *dp)
 	cb->cb_ops = &nfsd4_cb_recall_ops;
 	dp->dl_retries = 1;
 
-	queue_work(callback_wq, &dp->dl_recall.cb_work);
+	INIT_LIST_HEAD(&cb->cb_per_client);
+	cb->cb_done = true;
+
+	run_nfsd4_cb(&dp->dl_recall);
 }
diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
index f0695e815f0e..6d2c397d458b 100644
--- a/fs/nfsd/nfs4idmap.c
+++ b/fs/nfsd/nfs4idmap.c
@@ -33,10 +33,11 @@
  */
 
 #include <linux/module.h>
-#include <linux/nfsd_idmap.h>
 #include <linux/seq_file.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include "idmap.h"
+#include "nfsd.h"
 
 /*
  * Cache entry
@@ -514,7 +515,7 @@ rqst_authname(struct svc_rqst *rqstp)
 	return clp->name;
 }
 
-static int
+static __be32
 idmap_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen,
 		uid_t *id)
 {
@@ -524,15 +525,15 @@ idmap_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen
 	int ret;
 
 	if (namelen + 1 > sizeof(key.name))
-		return -EINVAL;
+		return nfserr_badowner;
 	memcpy(key.name, name, namelen);
 	key.name[namelen] = '\0';
 	strlcpy(key.authname, rqst_authname(rqstp), sizeof(key.authname));
 	ret = idmap_lookup(rqstp, nametoid_lookup, &key, &nametoid_cache, &item);
 	if (ret == -ENOENT)
-		ret = -ESRCH; /* nfserr_badname */
+		return nfserr_badowner;
 	if (ret)
-		return ret;
+		return nfserrno(ret);
 	*id = item->id;
 	cache_put(&item->h, &nametoid_cache);
 	return 0;
@@ -560,14 +561,14 @@ idmap_id_to_name(struct svc_rqst *rqstp, int type, uid_t id, char *name)
 	return ret;
 }
 
-int
+__be32
 nfsd_map_name_to_uid(struct svc_rqst *rqstp, const char *name, size_t namelen,
 		__u32 *id)
 {
 	return idmap_name_to_id(rqstp, IDMAP_TYPE_USER, name, namelen, id);
 }
 
-int
+__be32
 nfsd_map_name_to_gid(struct svc_rqst *rqstp, const char *name, size_t namelen,
 		__u32 *id)
 {
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 0cdfd022bb7b..db52546143d1 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -604,9 +604,7 @@ nfsd4_link(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	return status;
 }
 
-static __be32
-nfsd4_lookupp(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	      void *arg)
+static __be32 nfsd4_do_lookupp(struct svc_rqst *rqstp, struct svc_fh *fh)
 {
 	struct svc_fh tmp_fh;
 	__be32 ret;
@@ -615,13 +613,19 @@ nfsd4_lookupp(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	ret = exp_pseudoroot(rqstp, &tmp_fh);
 	if (ret)
 		return ret;
-	if (tmp_fh.fh_dentry == cstate->current_fh.fh_dentry) {
+	if (tmp_fh.fh_dentry == fh->fh_dentry) {
 		fh_put(&tmp_fh);
 		return nfserr_noent;
 	}
 	fh_put(&tmp_fh);
-	return nfsd_lookup(rqstp, &cstate->current_fh,
-			   "..", 2, &cstate->current_fh);
+	return nfsd_lookup(rqstp, fh, "..", 2, fh);
+}
+
+static __be32
+nfsd4_lookupp(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+	      void *arg)
+{
+	return nfsd4_do_lookupp(rqstp, &cstate->current_fh);
 }
 
 static __be32
@@ -769,10 +773,36 @@ nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	} else
 		secinfo->si_exp = exp;
 	dput(dentry);
+	if (cstate->minorversion)
+		/* See rfc 5661 section 2.6.3.1.1.8 */
+		fh_put(&cstate->current_fh);
 	return err;
 }
 
 static __be32
+nfsd4_secinfo_no_name(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+	      struct nfsd4_secinfo_no_name *sin)
+{
+	__be32 err;
+
+	switch (sin->sin_style) {
+	case NFS4_SECINFO_STYLE4_CURRENT_FH:
+		break;
+	case NFS4_SECINFO_STYLE4_PARENT:
+		err = nfsd4_do_lookupp(rqstp, &cstate->current_fh);
+		if (err)
+			return err;
+		break;
+	default:
+		return nfserr_inval;
+	}
+	exp_get(cstate->current_fh.fh_export);
+	sin->sin_exp = cstate->current_fh.fh_export;
+	fh_put(&cstate->current_fh);
+	return nfs_ok;
+}
+
+static __be32
 nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	      struct nfsd4_setattr *setattr)
 {
@@ -974,8 +1004,8 @@ static const char *nfsd4_op_name(unsigned opnum);
  * Also note, enforced elsewhere:
  *	- SEQUENCE other than as first op results in
  *	  NFS4ERR_SEQUENCE_POS. (Enforced in nfsd4_sequence().)
- *	- BIND_CONN_TO_SESSION must be the only op in its compound
- *	  (Will be enforced in nfsd4_bind_conn_to_session().)
+ *	- BIND_CONN_TO_SESSION must be the only op in its compound.
+ *	  (Enforced in nfsd4_bind_conn_to_session().)
  *	- DESTROY_SESSION must be the final operation in a compound, if
  *	  sessionid's in SEQUENCE and DESTROY_SESSION are the same.
  *	  (Enforced in nfsd4_destroy_session().)
@@ -1126,10 +1156,6 @@ encode_op:
 
 		nfsd4_increment_op_stats(op->opnum);
 	}
-	if (!rqstp->rq_usedeferral && status == nfserr_dropit) {
-		dprintk("%s Dropit - send NFS4ERR_DELAY\n", __func__);
-		status = nfserr_jukebox;
-	}
 
 	resp->cstate.status = status;
 	fh_put(&resp->cstate.current_fh);
@@ -1300,6 +1326,11 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP,
 		.op_name = "OP_EXCHANGE_ID",
 	},
+	[OP_BIND_CONN_TO_SESSION] = {
+		.op_func = (nfsd4op_func)nfsd4_bind_conn_to_session,
+		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP,
+		.op_name = "OP_BIND_CONN_TO_SESSION",
+	},
 	[OP_CREATE_SESSION] = {
 		.op_func = (nfsd4op_func)nfsd4_create_session,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP,
@@ -1320,6 +1351,10 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_flags = ALLOWED_WITHOUT_FH,
 		.op_name = "OP_RECLAIM_COMPLETE",
 	},
+	[OP_SECINFO_NO_NAME] = {
+		.op_func = (nfsd4op_func)nfsd4_secinfo_no_name,
+		.op_name = "OP_SECINFO_NO_NAME",
+	},
 };
 
 static const char *nfsd4_op_name(unsigned opnum)
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 7e26caab2a26..ffb59ef6f82f 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -302,7 +302,6 @@ purge_old(struct dentry *parent, struct dentry *child)
 {
 	int status;
 
-	/* note: we currently use this path only for minorversion 0 */
 	if (nfs4_has_reclaimed_state(child->d_name.name, false))
 		return 0;
 
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index fbd18c3074bb..d98d0213285d 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -230,7 +230,8 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_stateid *stp, struct svc_f
 	dp->dl_client = clp;
 	get_nfs4_file(fp);
 	dp->dl_file = fp;
-	nfs4_file_get_access(fp, O_RDONLY);
+	dp->dl_vfs_file = find_readable_file(fp);
+	get_file(dp->dl_vfs_file);
 	dp->dl_flock = NULL;
 	dp->dl_type = type;
 	dp->dl_stateid.si_boot = boot_time;
@@ -252,6 +253,7 @@ nfs4_put_delegation(struct nfs4_delegation *dp)
 	if (atomic_dec_and_test(&dp->dl_count)) {
 		dprintk("NFSD: freeing dp %p\n",dp);
 		put_nfs4_file(dp->dl_file);
+		fput(dp->dl_vfs_file);
 		kmem_cache_free(deleg_slab, dp);
 		num_delegations--;
 	}
@@ -265,12 +267,10 @@ nfs4_put_delegation(struct nfs4_delegation *dp)
 static void
 nfs4_close_delegation(struct nfs4_delegation *dp)
 {
-	struct file *filp = find_readable_file(dp->dl_file);
-
 	dprintk("NFSD: close_delegation dp %p\n",dp);
+	/* XXX: do we even need this check?: */
 	if (dp->dl_flock)
-		vfs_setlease(filp, F_UNLCK, &dp->dl_flock);
-	nfs4_file_put_access(dp->dl_file, O_RDONLY);
+		vfs_setlease(dp->dl_vfs_file, F_UNLCK, &dp->dl_flock);
 }
 
 /* Called under the state lock. */
@@ -642,6 +642,7 @@ static void nfsd4_conn_lost(struct svc_xpt_user *u)
 		free_conn(c);
 	}
 	spin_unlock(&clp->cl_lock);
+	nfsd4_probe_callback(clp);
 }
 
 static struct nfsd4_conn *alloc_conn(struct svc_rqst *rqstp, u32 flags)
@@ -679,15 +680,12 @@ static int nfsd4_register_conn(struct nfsd4_conn *conn)
 	return register_xpt_user(conn->cn_xprt, &conn->cn_xpt_user);
 }
 
-static __be32 nfsd4_new_conn(struct svc_rqst *rqstp, struct nfsd4_session *ses)
+static __be32 nfsd4_new_conn(struct svc_rqst *rqstp, struct nfsd4_session *ses, u32 dir)
 {
 	struct nfsd4_conn *conn;
-	u32 flags = NFS4_CDFC4_FORE;
 	int ret;
 
-	if (ses->se_flags & SESSION4_BACK_CHAN)
-		flags |= NFS4_CDFC4_BACK;
-	conn = alloc_conn(rqstp, flags);
+	conn = alloc_conn(rqstp, dir);
 	if (!conn)
 		return nfserr_jukebox;
 	nfsd4_hash_conn(conn, ses);
@@ -698,6 +696,17 @@ static __be32 nfsd4_new_conn(struct svc_rqst *rqstp, struct nfsd4_session *ses)
 	return nfs_ok;
 }
 
+static __be32 nfsd4_new_conn_from_crses(struct svc_rqst *rqstp, struct nfsd4_session *ses)
+{
+	u32 dir = NFS4_CDFC4_FORE;
+
+	if (ses->se_flags & SESSION4_BACK_CHAN)
+		dir |= NFS4_CDFC4_BACK;
+
+	return nfsd4_new_conn(rqstp, ses, dir);
+}
+
+/* must be called under client_lock */
 static void nfsd4_del_conns(struct nfsd4_session *s)
 {
 	struct nfs4_client *clp = s->se_client;
@@ -749,6 +758,8 @@ static struct nfsd4_session *alloc_init_session(struct svc_rqst *rqstp, struct n
 	 */
 	slotsize = nfsd4_sanitize_slot_size(fchan->maxresp_cached);
 	numslots = nfsd4_get_drc_mem(slotsize, fchan->maxreqs);
+	if (numslots < 1)
+		return NULL;
 
 	new = alloc_session(slotsize, numslots);
 	if (!new) {
@@ -769,25 +780,30 @@ static struct nfsd4_session *alloc_init_session(struct svc_rqst *rqstp, struct n
 	idx = hash_sessionid(&new->se_sessionid);
 	spin_lock(&client_lock);
 	list_add(&new->se_hash, &sessionid_hashtbl[idx]);
+	spin_lock(&clp->cl_lock);
 	list_add(&new->se_perclnt, &clp->cl_sessions);
+	spin_unlock(&clp->cl_lock);
 	spin_unlock(&client_lock);
 
-	status = nfsd4_new_conn(rqstp, new);
+	status = nfsd4_new_conn_from_crses(rqstp, new);
 	/* whoops: benny points out, status is ignored! (err, or bogus) */
 	if (status) {
 		free_session(&new->se_ref);
 		return NULL;
 	}
-	if (!clp->cl_cb_session && (cses->flags & SESSION4_BACK_CHAN)) {
+	if (cses->flags & SESSION4_BACK_CHAN) {
 		struct sockaddr *sa = svc_addr(rqstp);
-
-		clp->cl_cb_session = new;
-		clp->cl_cb_conn.cb_xprt = rqstp->rq_xprt;
-		svc_xprt_get(rqstp->rq_xprt);
+		/*
+		 * This is a little silly; with sessions there's no real
+		 * use for the callback address.  Use the peer address
+		 * as a reasonable default for now, but consider fixing
+		 * the rpc client not to require an address in the
+		 * future:
+		 */
 		rpc_copy_addr((struct sockaddr *)&clp->cl_cb_conn.cb_addr, sa);
 		clp->cl_cb_conn.cb_addrlen = svc_addr_len(sa);
-		nfsd4_probe_callback(clp);
 	}
+	nfsd4_probe_callback(clp);
 	return new;
 }
 
@@ -817,7 +833,9 @@ static void
 unhash_session(struct nfsd4_session *ses)
 {
 	list_del(&ses->se_hash);
+	spin_lock(&ses->se_client->cl_lock);
 	list_del(&ses->se_perclnt);
+	spin_unlock(&ses->se_client->cl_lock);
 }
 
 /* must be called under the client_lock */
@@ -923,8 +941,10 @@ unhash_client_locked(struct nfs4_client *clp)
 
 	mark_client_expired(clp);
 	list_del(&clp->cl_lru);
+	spin_lock(&clp->cl_lock);
 	list_for_each_entry(ses, &clp->cl_sessions, se_perclnt)
 		list_del_init(&ses->se_hash);
+	spin_unlock(&clp->cl_lock);
 }
 
 static void
@@ -1051,12 +1071,13 @@ static struct nfs4_client *create_client(struct xdr_netobj name, char *recdir,
 
 	memcpy(clp->cl_recdir, recdir, HEXDIR_LEN);
 	atomic_set(&clp->cl_refcount, 0);
-	atomic_set(&clp->cl_cb_set, 0);
+	clp->cl_cb_state = NFSD4_CB_UNKNOWN;
 	INIT_LIST_HEAD(&clp->cl_idhash);
 	INIT_LIST_HEAD(&clp->cl_strhash);
 	INIT_LIST_HEAD(&clp->cl_openowners);
 	INIT_LIST_HEAD(&clp->cl_delegations);
 	INIT_LIST_HEAD(&clp->cl_lru);
+	INIT_LIST_HEAD(&clp->cl_callbacks);
 	spin_lock_init(&clp->cl_lock);
 	INIT_WORK(&clp->cl_cb_null.cb_work, nfsd4_do_callback_rpc);
 	clp->cl_time = get_seconds();
@@ -1132,54 +1153,55 @@ find_unconfirmed_client(clientid_t *clid)
 	return NULL;
 }
 
-/*
- * Return 1 iff clp's clientid establishment method matches the use_exchange_id
- * parameter. Matching is based on the fact the at least one of the
- * EXCHGID4_FLAG_USE_{NON_PNFS,PNFS_MDS,PNFS_DS} flags must be set for v4.1
- *
- * FIXME: we need to unify the clientid namespaces for nfsv4.x
- * and correctly deal with client upgrade/downgrade in EXCHANGE_ID
- * and SET_CLIENTID{,_CONFIRM}
- */
-static inline int
-match_clientid_establishment(struct nfs4_client *clp, bool use_exchange_id)
+static bool clp_used_exchangeid(struct nfs4_client *clp)
 {
-	bool has_exchange_flags = (clp->cl_exchange_flags != 0);
-	return use_exchange_id == has_exchange_flags;
-}
+	return clp->cl_exchange_flags != 0;
+} 
 
 static struct nfs4_client *
-find_confirmed_client_by_str(const char *dname, unsigned int hashval,
-			     bool use_exchange_id)
+find_confirmed_client_by_str(const char *dname, unsigned int hashval)
 {
 	struct nfs4_client *clp;
 
 	list_for_each_entry(clp, &conf_str_hashtbl[hashval], cl_strhash) {
-		if (same_name(clp->cl_recdir, dname) &&
-		    match_clientid_establishment(clp, use_exchange_id))
+		if (same_name(clp->cl_recdir, dname))
 			return clp;
 	}
 	return NULL;
 }
 
 static struct nfs4_client *
-find_unconfirmed_client_by_str(const char *dname, unsigned int hashval,
-			       bool use_exchange_id)
+find_unconfirmed_client_by_str(const char *dname, unsigned int hashval)
 {
 	struct nfs4_client *clp;
 
 	list_for_each_entry(clp, &unconf_str_hashtbl[hashval], cl_strhash) {
-		if (same_name(clp->cl_recdir, dname) &&
-		    match_clientid_establishment(clp, use_exchange_id))
+		if (same_name(clp->cl_recdir, dname))
 			return clp;
 	}
 	return NULL;
 }
 
+static void rpc_svcaddr2sockaddr(struct sockaddr *sa, unsigned short family, union svc_addr_u *svcaddr)
+{
+	switch (family) {
+	case AF_INET:
+		((struct sockaddr_in *)sa)->sin_family = AF_INET;
+		((struct sockaddr_in *)sa)->sin_addr = svcaddr->addr;
+		return;
+	case AF_INET6:
+		((struct sockaddr_in6 *)sa)->sin6_family = AF_INET6;
+		((struct sockaddr_in6 *)sa)->sin6_addr = svcaddr->addr6;
+		return;
+	}
+}
+
 static void
-gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, u32 scopeid)
+gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, struct svc_rqst *rqstp)
 {
 	struct nfs4_cb_conn *conn = &clp->cl_cb_conn;
+	struct sockaddr	*sa = svc_addr(rqstp);
+	u32 scopeid = rpc_get_scope_id(sa);
 	unsigned short expected_family;
 
 	/* Currently, we only support tcp and tcp6 for the callback channel */
@@ -1205,6 +1227,7 @@ gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, u32 scopeid)
 
 	conn->cb_prog = se->se_callback_prog;
 	conn->cb_ident = se->se_callback_ident;
+	rpc_svcaddr2sockaddr((struct sockaddr *)&conn->cb_saddr, expected_family, &rqstp->rq_daddr);
 	return;
 out_err:
 	conn->cb_addr.ss_family = AF_UNSPEC;
@@ -1344,7 +1367,7 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
 	case SP4_NONE:
 		break;
 	case SP4_SSV:
-		return nfserr_encr_alg_unsupp;
+		return nfserr_serverfault;
 	default:
 		BUG();				/* checked by xdr code */
 	case SP4_MACH_CRED:
@@ -1361,8 +1384,12 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
 	nfs4_lock_state();
 	status = nfs_ok;
 
-	conf = find_confirmed_client_by_str(dname, strhashval, true);
+	conf = find_confirmed_client_by_str(dname, strhashval);
 	if (conf) {
+		if (!clp_used_exchangeid(conf)) {
+			status = nfserr_clid_inuse; /* XXX: ? */
+			goto out;
+		}
 		if (!same_verf(&verf, &conf->cl_verifier)) {
 			/* 18.35.4 case 8 */
 			if (exid->flags & EXCHGID4_FLAG_UPD_CONFIRMED_REC_A) {
@@ -1403,7 +1430,7 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
 		goto out;
 	}
 
-	unconf  = find_unconfirmed_client_by_str(dname, strhashval, true);
+	unconf  = find_unconfirmed_client_by_str(dname, strhashval);
 	if (unconf) {
 		/*
 		 * Possible retry or client restart.  Per 18.35.4 case 4,
@@ -1560,6 +1587,8 @@ nfsd4_create_session(struct svc_rqst *rqstp,
 	status = nfs_ok;
 	memcpy(cr_ses->sessionid.data, new->se_sessionid.data,
 	       NFS4_MAX_SESSIONID_LEN);
+	memcpy(&cr_ses->fore_channel, &new->se_fchannel,
+		sizeof(struct nfsd4_channel_attrs));
 	cs_slot->sl_seqid++;
 	cr_ses->seqid = cs_slot->sl_seqid;
 
@@ -1581,6 +1610,45 @@ static bool nfsd4_last_compound_op(struct svc_rqst *rqstp)
 	return argp->opcnt == resp->opcnt;
 }
 
+static __be32 nfsd4_map_bcts_dir(u32 *dir)
+{
+	switch (*dir) {
+	case NFS4_CDFC4_FORE:
+	case NFS4_CDFC4_BACK:
+		return nfs_ok;
+	case NFS4_CDFC4_FORE_OR_BOTH:
+	case NFS4_CDFC4_BACK_OR_BOTH:
+		*dir = NFS4_CDFC4_BOTH;
+		return nfs_ok;
+	};
+	return nfserr_inval;
+}
+
+__be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp,
+		     struct nfsd4_compound_state *cstate,
+		     struct nfsd4_bind_conn_to_session *bcts)
+{
+	__be32 status;
+
+	if (!nfsd4_last_compound_op(rqstp))
+		return nfserr_not_only_op;
+	spin_lock(&client_lock);
+	cstate->session = find_in_sessionid_hashtbl(&bcts->sessionid);
+	/* Sorta weird: we only need the refcnt'ing because new_conn acquires
+	 * client_lock iself: */
+	if (cstate->session) {
+		nfsd4_get_session(cstate->session);
+		atomic_inc(&cstate->session->se_client->cl_refcount);
+	}
+	spin_unlock(&client_lock);
+	if (!cstate->session)
+		return nfserr_badsession;
+
+	status = nfsd4_map_bcts_dir(&bcts->dir);
+	nfsd4_new_conn(rqstp, cstate->session, bcts->dir);
+	return nfs_ok;
+}
+
 static bool nfsd4_compound_in_session(struct nfsd4_session *session, struct nfs4_sessionid *sid)
 {
 	if (!session)
@@ -1619,8 +1687,7 @@ nfsd4_destroy_session(struct svc_rqst *r,
 	spin_unlock(&client_lock);
 
 	nfs4_lock_state();
-	/* wait for callbacks */
-	nfsd4_shutdown_callback(ses->se_client);
+	nfsd4_probe_callback_sync(ses->se_client);
 	nfs4_unlock_state();
 
 	nfsd4_del_conns(ses);
@@ -1733,8 +1800,12 @@ nfsd4_sequence(struct svc_rqst *rqstp,
 out:
 	/* Hold a session reference until done processing the compound. */
 	if (cstate->session) {
+		struct nfs4_client *clp = session->se_client;
+
 		nfsd4_get_session(cstate->session);
-		atomic_inc(&session->se_client->cl_refcount);
+		atomic_inc(&clp->cl_refcount);
+		if (clp->cl_cb_state == NFSD4_CB_DOWN)
+			seq->status_flags |= SEQ4_STATUS_CB_PATH_DOWN;
 	}
 	kfree(conn);
 	spin_unlock(&client_lock);
@@ -1775,7 +1846,6 @@ __be32
 nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		  struct nfsd4_setclientid *setclid)
 {
-	struct sockaddr		*sa = svc_addr(rqstp);
 	struct xdr_netobj 	clname = { 
 		.len = setclid->se_namelen,
 		.data = setclid->se_name,
@@ -1801,10 +1871,12 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	strhashval = clientstr_hashval(dname);
 
 	nfs4_lock_state();
-	conf = find_confirmed_client_by_str(dname, strhashval, false);
+	conf = find_confirmed_client_by_str(dname, strhashval);
 	if (conf) {
 		/* RFC 3530 14.2.33 CASE 0: */
 		status = nfserr_clid_inuse;
+		if (clp_used_exchangeid(conf))
+			goto out;
 		if (!same_creds(&conf->cl_cred, &rqstp->rq_cred)) {
 			char addr_str[INET6_ADDRSTRLEN];
 			rpc_ntop((struct sockaddr *) &conf->cl_addr, addr_str,
@@ -1819,7 +1891,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	 * has a description of SETCLIENTID request processing consisting
 	 * of 5 bullet points, labeled as CASE0 - CASE4 below.
 	 */
-	unconf = find_unconfirmed_client_by_str(dname, strhashval, false);
+	unconf = find_unconfirmed_client_by_str(dname, strhashval);
 	status = nfserr_resource;
 	if (!conf) {
 		/*
@@ -1876,7 +1948,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	 * for consistent minorversion use throughout:
 	 */
 	new->cl_minorversion = 0;
-	gen_callback(new, setclid, rpc_get_scope_id(sa));
+	gen_callback(new, setclid, rqstp);
 	add_to_unconfirmed(new, strhashval);
 	setclid->se_clientid.cl_boot = new->cl_clientid.cl_boot;
 	setclid->se_clientid.cl_id = new->cl_clientid.cl_id;
@@ -1935,7 +2007,6 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
 		if (!same_creds(&conf->cl_cred, &unconf->cl_cred))
 			status = nfserr_clid_inuse;
 		else {
-			atomic_set(&conf->cl_cb_set, 0);
 			nfsd4_change_callback(conf, &unconf->cl_cb_conn);
 			nfsd4_probe_callback(conf);
 			expire_client(unconf);
@@ -1964,7 +2035,7 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
 			unsigned int hash =
 				clientstr_hashval(unconf->cl_recdir);
 			conf = find_confirmed_client_by_str(unconf->cl_recdir,
-							    hash, false);
+							    hash);
 			if (conf) {
 				nfsd4_remove_clid_dir(conf);
 				expire_client(conf);
@@ -2300,41 +2371,6 @@ void nfsd_break_deleg_cb(struct file_lock *fl)
 	nfsd4_cb_recall(dp);
 }
 
-/*
- * The file_lock is being reapd.
- *
- * Called by locks_free_lock() with lock_flocks() held.
- */
-static
-void nfsd_release_deleg_cb(struct file_lock *fl)
-{
-	struct nfs4_delegation *dp = (struct nfs4_delegation *)fl->fl_owner;
-
-	dprintk("NFSD nfsd_release_deleg_cb: fl %p dp %p dl_count %d\n", fl,dp, atomic_read(&dp->dl_count));
-
-	if (!(fl->fl_flags & FL_LEASE) || !dp)
-		return;
-	dp->dl_flock = NULL;
-}
-
-/*
- * Called from setlease() with lock_flocks() held
- */
-static
-int nfsd_same_client_deleg_cb(struct file_lock *onlist, struct file_lock *try)
-{
-	struct nfs4_delegation *onlistd =
-		(struct nfs4_delegation *)onlist->fl_owner;
-	struct nfs4_delegation *tryd =
-		(struct nfs4_delegation *)try->fl_owner;
-
-	if (onlist->fl_lmops != try->fl_lmops)
-		return 0;
-
-	return onlistd->dl_client == tryd->dl_client;
-}
-
-
 static
 int nfsd_change_deleg_cb(struct file_lock **onlist, int arg)
 {
@@ -2346,8 +2382,6 @@ int nfsd_change_deleg_cb(struct file_lock **onlist, int arg)
 
 static const struct lock_manager_operations nfsd_lease_mng_ops = {
 	.fl_break = nfsd_break_deleg_cb,
-	.fl_release_private = nfsd_release_deleg_cb,
-	.fl_mylease = nfsd_same_client_deleg_cb,
 	.fl_change = nfsd_change_deleg_cb,
 };
 
@@ -2514,8 +2548,6 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file
 	if (!fp->fi_fds[oflag]) {
 		status = nfsd_open(rqstp, cur_fh, S_IFREG, access,
 			&fp->fi_fds[oflag]);
-		if (status == nfserr_dropit)
-			status = nfserr_jukebox;
 		if (status)
 			return status;
 	}
@@ -2596,6 +2628,19 @@ nfs4_set_claim_prev(struct nfsd4_open *open)
 	open->op_stateowner->so_client->cl_firststate = 1;
 }
 
+/* Should we give out recallable state?: */
+static bool nfsd4_cb_channel_good(struct nfs4_client *clp)
+{
+	if (clp->cl_cb_state == NFSD4_CB_UP)
+		return true;
+	/*
+	 * In the sessions case, since we don't have to establish a
+	 * separate connection for callbacks, we assume it's OK
+	 * until we hear otherwise:
+	 */
+	return clp->cl_minorversion && clp->cl_cb_state == NFSD4_CB_UNKNOWN;
+}
+
 /*
  * Attempt to hand out a delegation.
  */
@@ -2604,10 +2649,11 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, struct nfs4_sta
 {
 	struct nfs4_delegation *dp;
 	struct nfs4_stateowner *sop = stp->st_stateowner;
-	int cb_up = atomic_read(&sop->so_client->cl_cb_set);
+	int cb_up;
 	struct file_lock *fl;
 	int status, flag = 0;
 
+	cb_up = nfsd4_cb_channel_good(sop->so_client);
 	flag = NFS4_OPEN_DELEGATE_NONE;
 	open->op_recall = 0;
 	switch (open->op_claim_type) {
@@ -2655,7 +2701,7 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, struct nfs4_sta
 	dp->dl_flock = fl;
 
 	/* vfs_setlease checks to see if delegation should be handed out.
-	 * the lock_manager callbacks fl_mylease and fl_change are used
+	 * the lock_manager callback fl_change is used
 	 */
 	if ((status = vfs_setlease(fl->fl_file, fl->fl_type, &fl))) {
 		dprintk("NFSD: setlease failed [%d], no delegation\n", status);
@@ -2794,7 +2840,7 @@ nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	renew_client(clp);
 	status = nfserr_cb_path_down;
 	if (!list_empty(&clp->cl_delegations)
-			&& !atomic_read(&clp->cl_cb_set))
+			&& clp->cl_cb_state != NFSD4_CB_UP)
 		goto out;
 	status = nfs_ok;
 out:
@@ -3081,9 +3127,10 @@ nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate,
 		if (status)
 			goto out;
 		renew_client(dp->dl_client);
-		if (filpp)
+		if (filpp) {
 			*filpp = find_readable_file(dp->dl_file);
-		BUG_ON(!*filpp);
+			BUG_ON(!*filpp);
+		}
 	} else { /* open or lock stateid */
 		stp = find_stateid(stateid, flags);
 		if (!stp)
@@ -4107,7 +4154,7 @@ nfs4_has_reclaimed_state(const char *name, bool use_exchange_id)
 	unsigned int strhashval = clientstr_hashval(name);
 	struct nfs4_client *clp;
 
-	clp = find_confirmed_client_by_str(name, strhashval, use_exchange_id);
+	clp = find_confirmed_client_by_str(name, strhashval);
 	return clp ? 1 : 0;
 }
 
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index f35a94a04026..956629b9cdc9 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -44,13 +44,14 @@
 #include <linux/namei.h>
 #include <linux/statfs.h>
 #include <linux/utsname.h>
-#include <linux/nfsd_idmap.h>
-#include <linux/nfs4_acl.h>
 #include <linux/sunrpc/svcauth_gss.h>
 
+#include "idmap.h"
+#include "acl.h"
 #include "xdr4.h"
 #include "vfs.h"
 
+
 #define NFSDDBG_FACILITY		NFSDDBG_XDR
 
 /*
@@ -288,17 +289,17 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 			len += XDR_QUADLEN(dummy32) << 2;
 			READMEM(buf, dummy32);
 			ace->whotype = nfs4_acl_get_whotype(buf, dummy32);
-			host_err = 0;
+			status = nfs_ok;
 			if (ace->whotype != NFS4_ACL_WHO_NAMED)
 				ace->who = 0;
 			else if (ace->flag & NFS4_ACE_IDENTIFIER_GROUP)
-				host_err = nfsd_map_name_to_gid(argp->rqstp,
+				status = nfsd_map_name_to_gid(argp->rqstp,
 						buf, dummy32, &ace->who);
 			else
-				host_err = nfsd_map_name_to_uid(argp->rqstp,
+				status = nfsd_map_name_to_uid(argp->rqstp,
 						buf, dummy32, &ace->who);
-			if (host_err)
-				goto out_nfserr;
+			if (status)
+				return status;
 		}
 	} else
 		*acl = NULL;
@@ -420,6 +421,21 @@ nfsd4_decode_access(struct nfsd4_compoundargs *argp, struct nfsd4_access *access
 	DECODE_TAIL;
 }
 
+static __be32 nfsd4_decode_bind_conn_to_session(struct nfsd4_compoundargs *argp, struct nfsd4_bind_conn_to_session *bcts)
+{
+	DECODE_HEAD;
+	u32 dummy;
+
+	READ_BUF(NFS4_MAX_SESSIONID_LEN + 8);
+	COPYMEM(bcts->sessionid.data, NFS4_MAX_SESSIONID_LEN);
+	READ32(bcts->dir);
+	/* XXX: Perhaps Tom Tucker could help us figure out how we
+	 * should be using ctsa_use_conn_in_rdma_mode: */
+	READ32(dummy);
+
+	DECODE_TAIL;
+}
+
 static __be32
 nfsd4_decode_close(struct nfsd4_compoundargs *argp, struct nfsd4_close *close)
 {
@@ -847,6 +863,17 @@ nfsd4_decode_secinfo(struct nfsd4_compoundargs *argp,
 }
 
 static __be32
+nfsd4_decode_secinfo_no_name(struct nfsd4_compoundargs *argp,
+		     struct nfsd4_secinfo_no_name *sin)
+{
+	DECODE_HEAD;
+
+	READ_BUF(4);
+	READ32(sin->sin_style);
+	DECODE_TAIL;
+}
+
+static __be32
 nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, struct nfsd4_setattr *setattr)
 {
 	__be32 status;
@@ -1005,7 +1032,7 @@ static __be32
 nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp,
 			 struct nfsd4_exchange_id *exid)
 {
-	int dummy;
+	int dummy, tmp;
 	DECODE_HEAD;
 
 	READ_BUF(NFS4_VERIFIER_SIZE);
@@ -1053,15 +1080,23 @@ nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp,
 
 		/* ssp_hash_algs<> */
 		READ_BUF(4);
-		READ32(dummy);
-		READ_BUF(dummy);
-		p += XDR_QUADLEN(dummy);
+		READ32(tmp);
+		while (tmp--) {
+			READ_BUF(4);
+			READ32(dummy);
+			READ_BUF(dummy);
+			p += XDR_QUADLEN(dummy);
+		}
 
 		/* ssp_encr_algs<> */
 		READ_BUF(4);
-		READ32(dummy);
-		READ_BUF(dummy);
-		p += XDR_QUADLEN(dummy);
+		READ32(tmp);
+		while (tmp--) {
+			READ_BUF(4);
+			READ32(dummy);
+			READ_BUF(dummy);
+			p += XDR_QUADLEN(dummy);
+		}
 
 		/* ssp_window and ssp_num_gss_handles */
 		READ_BUF(8);
@@ -1339,7 +1374,7 @@ static nfsd4_dec nfsd41_dec_ops[] = {
 
 	/* new operations for NFSv4.1 */
 	[OP_BACKCHANNEL_CTL]	= (nfsd4_dec)nfsd4_decode_notsupp,
-	[OP_BIND_CONN_TO_SESSION]= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_BIND_CONN_TO_SESSION]= (nfsd4_dec)nfsd4_decode_bind_conn_to_session,
 	[OP_EXCHANGE_ID]	= (nfsd4_dec)nfsd4_decode_exchange_id,
 	[OP_CREATE_SESSION]	= (nfsd4_dec)nfsd4_decode_create_session,
 	[OP_DESTROY_SESSION]	= (nfsd4_dec)nfsd4_decode_destroy_session,
@@ -1350,7 +1385,7 @@ static nfsd4_dec nfsd41_dec_ops[] = {
 	[OP_LAYOUTCOMMIT]	= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_LAYOUTGET]		= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_LAYOUTRETURN]	= (nfsd4_dec)nfsd4_decode_notsupp,
-	[OP_SECINFO_NO_NAME]	= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_SECINFO_NO_NAME]	= (nfsd4_dec)nfsd4_decode_secinfo_no_name,
 	[OP_SEQUENCE]		= (nfsd4_dec)nfsd4_decode_sequence,
 	[OP_SET_SSV]		= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_TEST_STATEID]	= (nfsd4_dec)nfsd4_decode_notsupp,
@@ -2309,8 +2344,6 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen,
 	case nfserr_resource:
 		nfserr = nfserr_toosmall;
 		goto fail;
-	case nfserr_dropit:
-		goto fail;
 	case nfserr_noent:
 		goto skip_entry;
 	default:
@@ -2365,6 +2398,21 @@ nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
 	return nfserr;
 }
 
+static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_bind_conn_to_session *bcts)
+{
+	__be32 *p;
+
+	if (!nfserr) {
+		RESERVE_SPACE(NFS4_MAX_SESSIONID_LEN + 8);
+		WRITEMEM(bcts->sessionid.data, NFS4_MAX_SESSIONID_LEN);
+		WRITE32(bcts->dir);
+		/* XXX: ? */
+		WRITE32(0);
+		ADJUST_ARGS();
+	}
+	return nfserr;
+}
+
 static __be32
 nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_close *close)
 {
@@ -2826,11 +2874,10 @@ nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
 }
 
 static __be32
-nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
-		     struct nfsd4_secinfo *secinfo)
+nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp,
+			 __be32 nfserr,struct svc_export *exp)
 {
 	int i = 0;
-	struct svc_export *exp = secinfo->si_exp;
 	u32 nflavs;
 	struct exp_flavor_info *flavs;
 	struct exp_flavor_info def_flavs[2];
@@ -2892,6 +2939,20 @@ out:
 	return nfserr;
 }
 
+static __be32
+nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
+		     struct nfsd4_secinfo *secinfo)
+{
+	return nfsd4_do_encode_secinfo(resp, nfserr, secinfo->si_exp);
+}
+
+static __be32
+nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr,
+		     struct nfsd4_secinfo_no_name *secinfo)
+{
+	return nfsd4_do_encode_secinfo(resp, nfserr, secinfo->sin_exp);
+}
+
 /*
  * The SETATTR encode routine is special -- it always encodes a bitmap,
  * regardless of the error status.
@@ -3076,13 +3137,9 @@ nfsd4_encode_sequence(struct nfsd4_compoundres *resp, int nfserr,
 	WRITE32(seq->seqid);
 	WRITE32(seq->slotid);
 	WRITE32(seq->maxslots);
-	/*
-	 * FIXME: for now:
-	 *   target_maxslots = maxslots
-	 *   status_flags = 0
-	 */
+	/* For now: target_maxslots = maxslots */
 	WRITE32(seq->maxslots);
-	WRITE32(0);
+	WRITE32(seq->status_flags);
 
 	ADJUST_ARGS();
 	resp->cstate.datap = p; /* DRC cache data pointer */
@@ -3143,7 +3200,7 @@ static nfsd4_enc nfsd4_enc_ops[] = {
 
 	/* NFSv4.1 operations */
 	[OP_BACKCHANNEL_CTL]	= (nfsd4_enc)nfsd4_encode_noop,
-	[OP_BIND_CONN_TO_SESSION] = (nfsd4_enc)nfsd4_encode_noop,
+	[OP_BIND_CONN_TO_SESSION] = (nfsd4_enc)nfsd4_encode_bind_conn_to_session,
 	[OP_EXCHANGE_ID]	= (nfsd4_enc)nfsd4_encode_exchange_id,
 	[OP_CREATE_SESSION]	= (nfsd4_enc)nfsd4_encode_create_session,
 	[OP_DESTROY_SESSION]	= (nfsd4_enc)nfsd4_encode_destroy_session,
@@ -3154,7 +3211,7 @@ static nfsd4_enc nfsd4_enc_ops[] = {
 	[OP_LAYOUTCOMMIT]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_LAYOUTGET]		= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_LAYOUTRETURN]	= (nfsd4_enc)nfsd4_encode_noop,
-	[OP_SECINFO_NO_NAME]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_SECINFO_NO_NAME]	= (nfsd4_enc)nfsd4_encode_secinfo_no_name,
 	[OP_SEQUENCE]		= (nfsd4_enc)nfsd4_encode_sequence,
 	[OP_SET_SSV]		= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_TEST_STATEID]	= (nfsd4_enc)nfsd4_encode_noop,
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 4514ebbee4d6..33b3e2b06779 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -8,12 +8,12 @@
 #include <linux/namei.h>
 #include <linux/ctype.h>
 
-#include <linux/nfsd_idmap.h>
 #include <linux/sunrpc/svcsock.h>
 #include <linux/nfsd/syscall.h>
 #include <linux/lockd/lockd.h>
 #include <linux/sunrpc/clnt.h>
 
+#include "idmap.h"
 #include "nfsd.h"
 #include "cache.h"
 
@@ -127,6 +127,7 @@ static ssize_t nfsctl_transaction_write(struct file *file, const char __user *bu
 
 static ssize_t nfsctl_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos)
 {
+#ifdef CONFIG_NFSD_DEPRECATED
 	static int warned;
 	if (file->f_dentry->d_name.name[0] == '.' && !warned) {
 		printk(KERN_INFO
@@ -135,6 +136,7 @@ static ssize_t nfsctl_transaction_read(struct file *file, char __user *buf, size
 		       current->comm, file->f_dentry->d_name.name);
 		warned = 1;
 	}
+#endif
 	if (! file->private_data) {
 		/* An attempt to read a transaction file without writing
 		 * causes a 0-byte write so that the file can return
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 6b641cf2c19a..7ecfa2420307 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -158,6 +158,7 @@ void		nfsd_lockd_shutdown(void);
 #define	nfserr_attrnotsupp	cpu_to_be32(NFSERR_ATTRNOTSUPP)
 #define	nfserr_bad_xdr		cpu_to_be32(NFSERR_BAD_XDR)
 #define	nfserr_openmode		cpu_to_be32(NFSERR_OPENMODE)
+#define	nfserr_badowner		cpu_to_be32(NFSERR_BADOWNER)
 #define	nfserr_locks_held	cpu_to_be32(NFSERR_LOCKS_HELD)
 #define	nfserr_op_illegal	cpu_to_be32(NFSERR_OP_ILLEGAL)
 #define	nfserr_grace		cpu_to_be32(NFSERR_GRACE)
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 08e17264784b..e15dc45fc5ec 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -735,9 +735,9 @@ nfserrno (int errno)
 		{ nfserr_stale, -ESTALE },
 		{ nfserr_jukebox, -ETIMEDOUT },
 		{ nfserr_jukebox, -ERESTARTSYS },
-		{ nfserr_dropit, -EAGAIN },
-		{ nfserr_dropit, -ENOMEM },
-		{ nfserr_badname, -ESRCH },
+		{ nfserr_jukebox, -EAGAIN },
+		{ nfserr_jukebox, -EWOULDBLOCK },
+		{ nfserr_jukebox, -ENOMEM },
 		{ nfserr_io, -ETXTBSY },
 		{ nfserr_notsupp, -EOPNOTSUPP },
 		{ nfserr_toosmall, -ETOOSMALL },
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 2bae1d86f5f2..18743c4d8bca 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -608,7 +608,7 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 	/* Now call the procedure handler, and encode NFS status. */
 	nfserr = proc->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp);
 	nfserr = map_new_errors(rqstp->rq_vers, nfserr);
-	if (nfserr == nfserr_dropit) {
+	if (nfserr == nfserr_dropit || rqstp->rq_dropme) {
 		dprintk("nfsd: Dropping request; may be revisited later\n");
 		nfsd_cache_update(rqstp, RC_NOCACHE, NULL);
 		return 0;
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 39adc27b0685..3074656ba7bf 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -68,10 +68,12 @@ typedef struct {
 struct nfsd4_callback {
 	void *cb_op;
 	struct nfs4_client *cb_clp;
+	struct list_head cb_per_client;
 	u32 cb_minorversion;
 	struct rpc_message cb_msg;
 	const struct rpc_call_ops *cb_ops;
 	struct work_struct cb_work;
+	bool cb_done;
 };
 
 struct nfs4_delegation {
@@ -81,6 +83,7 @@ struct nfs4_delegation {
 	atomic_t		dl_count;       /* ref count */
 	struct nfs4_client	*dl_client;
 	struct nfs4_file	*dl_file;
+	struct file		*dl_vfs_file;
 	struct file_lock	*dl_flock;
 	u32			dl_type;
 	time_t			dl_time;
@@ -95,6 +98,7 @@ struct nfs4_delegation {
 struct nfs4_cb_conn {
 	/* SETCLIENTID info */
 	struct sockaddr_storage	cb_addr;
+	struct sockaddr_storage	cb_saddr;
 	size_t			cb_addrlen;
 	u32                     cb_prog; /* used only in 4.0 case;
 					    per-session otherwise */
@@ -146,6 +150,11 @@ struct nfsd4_create_session {
 	u32				gid;
 };
 
+struct nfsd4_bind_conn_to_session {
+	struct nfs4_sessionid		sessionid;
+	u32				dir;
+};
+
 /* The single slot clientid cache structure */
 struct nfsd4_clid_slot {
 	u32				sl_seqid;
@@ -235,9 +244,13 @@ struct nfs4_client {
 	unsigned long		cl_cb_flags;
 	struct rpc_clnt		*cl_cb_client;
 	u32			cl_cb_ident;
-	atomic_t		cl_cb_set;
+#define NFSD4_CB_UP		0
+#define NFSD4_CB_UNKNOWN	1
+#define NFSD4_CB_DOWN		2
+	int			cl_cb_state;
 	struct nfsd4_callback	cl_cb_null;
 	struct nfsd4_session	*cl_cb_session;
+	struct list_head	cl_callbacks; /* list of in-progress callbacks */
 
 	/* for all client information that callback code might need: */
 	spinlock_t		cl_lock;
@@ -454,6 +467,7 @@ extern __be32 nfs4_check_open_reclaim(clientid_t *clid);
 extern void nfs4_free_stateowner(struct kref *kref);
 extern int set_callback_cred(void);
 extern void nfsd4_probe_callback(struct nfs4_client *clp);
+extern void nfsd4_probe_callback_sync(struct nfs4_client *clp);
 extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *);
 extern void nfsd4_do_callback_rpc(struct work_struct *);
 extern void nfsd4_cb_recall(struct nfs4_delegation *dp);
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 230b79fbf005..a3c7f701395a 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1,4 +1,3 @@
-#define MSNFS	/* HACK HACK */
 /*
  * File operations used by nfsd. Some of these have been ripped from
  * other parts of the kernel because they weren't exported, others
@@ -35,8 +34,8 @@
 #endif /* CONFIG_NFSD_V3 */
 
 #ifdef CONFIG_NFSD_V4
-#include <linux/nfs4_acl.h>
-#include <linux/nfsd_idmap.h>
+#include "acl.h"
+#include "idmap.h"
 #endif /* CONFIG_NFSD_V4 */
 
 #include "nfsd.h"
@@ -273,6 +272,13 @@ out:
 	return err;
 }
 
+static int nfsd_break_lease(struct inode *inode)
+{
+	if (!S_ISREG(inode->i_mode))
+		return 0;
+	return break_lease(inode, O_WRONLY | O_NONBLOCK);
+}
+
 /*
  * Commit metadata changes to stable storage.
  */
@@ -375,16 +381,6 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 				goto out;
 		}
 
-		/*
-		 * If we are changing the size of the file, then
-		 * we need to break all leases.
-		 */
-		host_err = break_lease(inode, O_WRONLY | O_NONBLOCK);
-		if (host_err == -EWOULDBLOCK)
-			host_err = -ETIMEDOUT;
-		if (host_err) /* ENOMEM or EWOULDBLOCK */
-			goto out_nfserr;
-
 		host_err = get_write_access(inode);
 		if (host_err)
 			goto out_nfserr;
@@ -425,7 +421,11 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 
 	err = nfserr_notsync;
 	if (!check_guard || guardtime == inode->i_ctime.tv_sec) {
+		host_err = nfsd_break_lease(inode);
+		if (host_err)
+			goto out_nfserr;
 		fh_lock(fhp);
+
 		host_err = notify_change(dentry, iap);
 		err = nfserrno(host_err);
 		fh_unlock(fhp);
@@ -752,8 +752,6 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 	 */
 	if (!(access & NFSD_MAY_NOT_BREAK_LEASE))
 		host_err = break_lease(inode, O_NONBLOCK | ((access & NFSD_MAY_WRITE) ? O_WRONLY : 0));
-	if (host_err == -EWOULDBLOCK)
-		host_err = -ETIMEDOUT;
 	if (host_err) /* NOMEM or WOULDBLOCK */
 		goto out_nfserr;
 
@@ -874,15 +872,6 @@ static int nfsd_direct_splice_actor(struct pipe_inode_info *pipe,
 	return __splice_from_pipe(pipe, sd, nfsd_splice_actor);
 }
 
-static inline int svc_msnfs(struct svc_fh *ffhp)
-{
-#ifdef MSNFS
-	return (ffhp->fh_export->ex_flags & NFSEXP_MSNFS);
-#else
-	return 0;
-#endif
-}
-
 static __be32
 nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
               loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
@@ -895,9 +884,6 @@ nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 	err = nfserr_perm;
 	inode = file->f_path.dentry->d_inode;
 
-	if (svc_msnfs(fhp) && !lock_may_read(inode, offset, *count))
-		goto out;
-
 	if (file->f_op->splice_read && rqstp->rq_splice_ok) {
 		struct splice_desc sd = {
 			.len		= 0,
@@ -922,7 +908,6 @@ nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 		fsnotify_access(file);
 	} else 
 		err = nfserrno(host_err);
-out:
 	return err;
 }
 
@@ -987,14 +972,6 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 	int			stable = *stablep;
 	int			use_wgather;
 
-#ifdef MSNFS
-	err = nfserr_perm;
-
-	if ((fhp->fh_export->ex_flags & NFSEXP_MSNFS) &&
-		(!lock_may_write(file->f_path.dentry->d_inode, offset, *cnt)))
-		goto out;
-#endif
-
 	dentry = file->f_path.dentry;
 	inode = dentry->d_inode;
 	exp   = fhp->fh_export;
@@ -1045,7 +1022,6 @@ out_nfserr:
 		err = 0;
 	else
 		err = nfserrno(host_err);
-out:
 	return err;
 }
 
@@ -1665,6 +1641,12 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
 		err = nfserrno(host_err);
 		goto out_dput;
 	}
+	err = nfserr_noent;
+	if (!dold->d_inode)
+		goto out_drop_write;
+	host_err = nfsd_break_lease(dold->d_inode);
+	if (host_err)
+		goto out_drop_write;
 	host_err = vfs_link(dold, dirp, dnew);
 	if (!host_err) {
 		err = nfserrno(commit_metadata(ffhp));
@@ -1676,6 +1658,7 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
 		else
 			err = nfserrno(host_err);
 	}
+out_drop_write:
 	mnt_drop_write(tfhp->fh_export->ex_path.mnt);
 out_dput:
 	dput(dnew);
@@ -1750,12 +1733,6 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 	if (ndentry == trap)
 		goto out_dput_new;
 
-	if (svc_msnfs(ffhp) &&
-		((odentry->d_count > 1) || (ndentry->d_count > 1))) {
-			host_err = -EPERM;
-			goto out_dput_new;
-	}
-
 	host_err = -EXDEV;
 	if (ffhp->fh_export->ex_path.mnt != tfhp->fh_export->ex_path.mnt)
 		goto out_dput_new;
@@ -1763,15 +1740,17 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 	if (host_err)
 		goto out_dput_new;
 
+	host_err = nfsd_break_lease(odentry->d_inode);
+	if (host_err)
+		goto out_drop_write;
 	host_err = vfs_rename(fdir, odentry, tdir, ndentry);
 	if (!host_err) {
 		host_err = commit_metadata(tfhp);
 		if (!host_err)
 			host_err = commit_metadata(ffhp);
 	}
-
+out_drop_write:
 	mnt_drop_write(ffhp->fh_export->ex_path.mnt);
-
  out_dput_new:
 	dput(ndentry);
  out_dput_old:
@@ -1834,18 +1813,14 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 	if (host_err)
 		goto out_nfserr;
 
-	if (type != S_IFDIR) { /* It's UNLINK */
-#ifdef MSNFS
-		if ((fhp->fh_export->ex_flags & NFSEXP_MSNFS) &&
-			(rdentry->d_count > 1)) {
-			host_err = -EPERM;
-		} else
-#endif
+	host_err = nfsd_break_lease(rdentry->d_inode);
+	if (host_err)
+		goto out_put;
+	if (type != S_IFDIR)
 		host_err = vfs_unlink(dirp, rdentry);
-	} else { /* It's RMDIR */
+	else
 		host_err = vfs_rmdir(dirp, rdentry);
-	}
-
+out_put:
 	dput(rdentry);
 
 	if (!host_err)
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 60fce3dc5cb5..366401e1a536 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -311,6 +311,11 @@ struct nfsd4_secinfo {
 	struct svc_export *si_exp;			/* response */
 };
 
+struct nfsd4_secinfo_no_name {
+	u32 sin_style;					/* request */
+	struct svc_export *sin_exp;			/* response */
+};
+
 struct nfsd4_setattr {
 	stateid_t	sa_stateid;         /* request */
 	u32		sa_bmval[3];        /* request */
@@ -373,8 +378,8 @@ struct nfsd4_sequence {
 	u32			cachethis;		/* request */
 #if 0
 	u32			target_maxslots;	/* response */
-	u32			status_flags;		/* response */
 #endif /* not yet */
+	u32			status_flags;		/* response */
 };
 
 struct nfsd4_destroy_session {
@@ -422,6 +427,7 @@ struct nfsd4_op {
 
 		/* NFSv4.1 */
 		struct nfsd4_exchange_id	exchange_id;
+		struct nfsd4_bind_conn_to_session bind_conn_to_session;
 		struct nfsd4_create_session	create_session;
 		struct nfsd4_destroy_session	destroy_session;
 		struct nfsd4_sequence		sequence;
@@ -518,6 +524,7 @@ extern __be32 nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
 		struct nfsd4_sequence *seq);
 extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *, struct nfsd4_exchange_id *);
+extern __be32 nfsd4_bind_conn_to_session(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_bind_conn_to_session *);
 extern __be32 nfsd4_create_session(struct svc_rqst *,
 		struct nfsd4_compound_state *,
 		struct nfsd4_create_session *);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3984f2358d1f..ed6ee473cc8a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1066,7 +1066,6 @@ struct lock_manager_operations {
 	int (*fl_grant)(struct file_lock *, struct file_lock *, int);
 	void (*fl_release_private)(struct file_lock *);
 	void (*fl_break)(struct file_lock *);
-	int (*fl_mylease)(struct file_lock *, struct file_lock *);
 	int (*fl_change)(struct file_lock **, int);
 };
 
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 9b46300b4305..134716e5e350 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -65,6 +65,9 @@
 
 #define NFS4_CDFC4_FORE	0x1
 #define NFS4_CDFC4_BACK 0x2
+#define NFS4_CDFC4_BOTH 0x3
+#define NFS4_CDFC4_FORE_OR_BOTH 0x3
+#define NFS4_CDFC4_BACK_OR_BOTH 0x7
 
 #define NFS4_SET_TO_SERVER_TIME	0
 #define NFS4_SET_TO_CLIENT_TIME	1
@@ -140,6 +143,9 @@
 #define SEQ4_STATUS_CB_PATH_DOWN_SESSION	0x00000200
 #define SEQ4_STATUS_BACKCHANNEL_FAULT		0x00000400
 
+#define NFS4_SECINFO_STYLE4_CURRENT_FH	0
+#define NFS4_SECINFO_STYLE4_PARENT	1
+
 #define NFS4_MAX_UINT64	(~(u64)0)
 
 /* An NFS4 sessions server must support at least NFS4_MAX_OPS operations.
diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h
index 8ae78a61eea4..bd316159278c 100644
--- a/include/linux/nfsd/export.h
+++ b/include/linux/nfsd/export.h
@@ -35,7 +35,7 @@
 #define NFSEXP_NOHIDE		0x0200
 #define NFSEXP_NOSUBTREECHECK	0x0400
 #define	NFSEXP_NOAUTHNLM	0x0800		/* Don't authenticate NLM requests - just trust */
-#define NFSEXP_MSNFS		0x1000	/* do silly things that MS clients expect */
+#define NFSEXP_MSNFS		0x1000	/* do silly things that MS clients expect; no longer supported */
 #define NFSEXP_FSID		0x2000
 #define	NFSEXP_CROSSMOUNT	0x4000
 #define	NFSEXP_NOACL		0x8000	/* reserved for possible ACL related use */
diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h
index 78aa104250b7..7898ea13de70 100644
--- a/include/linux/sunrpc/cache.h
+++ b/include/linux/sunrpc/cache.h
@@ -256,10 +256,13 @@ static inline time_t get_expiry(char **bpp)
 	return rv - boot.tv_sec;
 }
 
+#ifdef CONFIG_NFSD_DEPRECATED
 static inline void sunrpc_invalidate(struct cache_head *h,
 				     struct cache_detail *detail)
 {
 	h->expiry_time = seconds_since_boot() - 1;
 	detail->nextcheck = seconds_since_boot();
 }
+#endif /* CONFIG_NFSD_DEPRECATED */
+
 #endif /*  _LINUX_SUNRPC_CACHE_H_ */
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index c81d4d8be3a9..ea29330b78bd 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -269,6 +269,7 @@ struct svc_rqst {
 	struct cache_req	rq_chandle;	/* handle passed to caches for 
 						 * request delaying 
 						 */
+	bool			rq_dropme;
 	/* Catering to nfsd */
 	struct auth_domain *	rq_client;	/* RPC peer info */
 	struct auth_domain *	rq_gssclient;	/* "gss/"-style peer info */
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index 357da5e0daa3..059877b4d85b 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -63,7 +63,6 @@ struct svc_xprt {
 #define XPT_LISTENER	11		/* listening endpoint */
 #define XPT_CACHE_AUTH	12		/* cache auth info */
 
-	struct svc_pool		*xpt_pool;	/* current pool iff queued */
 	struct svc_serv		*xpt_server;	/* service for transport */
 	atomic_t    	    	xpt_reserved;	/* space on outq that is rsvd */
 	struct mutex		xpt_mutex;	/* to serialize sending data */
@@ -81,6 +80,7 @@ struct svc_xprt {
 	void			*xpt_bc_sid;	/* back channel session ID */
 
 	struct net		*xpt_net;
+	struct rpc_xprt		*xpt_bc_xprt;	/* NFSv4.1 backchannel */
 };
 
 static inline void unregister_xpt_user(struct svc_xprt *xpt, struct svc_xpt_user *u)
diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h
index 1b353a76c304..04dba23c59f2 100644
--- a/include/linux/sunrpc/svcsock.h
+++ b/include/linux/sunrpc/svcsock.h
@@ -28,7 +28,6 @@ struct svc_sock {
 	/* private TCP part */
 	u32			sk_reclen;	/* length of record */
 	u32			sk_tcplen;	/* current read length */
-	struct rpc_xprt		*sk_bc_xprt;	/* NFSv4.1 backchannel xprt */
 };
 
 /*
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 89d10d279a20..bef0f535f746 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -321,6 +321,7 @@ void			xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie);
 #define XPRT_CLOSING		(6)
 #define XPRT_CONNECTION_ABORT	(7)
 #define XPRT_CONNECTION_CLOSE	(8)
+#define XPRT_INITIALIZED	(9)
 
 static inline void xprt_set_connected(struct rpc_xprt *xprt)
 {
diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c
index 75ee993ea057..9576f35ab701 100644
--- a/net/sunrpc/auth_gss/gss_krb5_crypto.c
+++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c
@@ -137,7 +137,7 @@ arcfour_hmac_md5_usage_to_salt(unsigned int usage, u8 salt[4])
 		ms_usage = 13;
 		break;
 	default:
-		return EINVAL;;
+		return -EINVAL;
 	}
 	salt[0] = (ms_usage >> 0) & 0xff;
 	salt[1] = (ms_usage >> 8) & 0xff;
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index dec2a6fc7c12..bcdae78fdfc6 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -67,7 +67,6 @@ static int netobj_equal(struct xdr_netobj *a, struct xdr_netobj *b)
 
 #define	RSI_HASHBITS	6
 #define	RSI_HASHMAX	(1<<RSI_HASHBITS)
-#define	RSI_HASHMASK	(RSI_HASHMAX-1)
 
 struct rsi {
 	struct cache_head	h;
@@ -319,7 +318,6 @@ static struct rsi *rsi_update(struct rsi *new, struct rsi *old)
 
 #define	RSC_HASHBITS	10
 #define	RSC_HASHMAX	(1<<RSC_HASHBITS)
-#define	RSC_HASHMASK	(RSC_HASHMAX-1)
 
 #define GSS_SEQ_WIN	128
 
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index e433e7580e27..72ad836e4fe0 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -37,7 +37,7 @@
 
 #define	 RPCDBG_FACILITY RPCDBG_CACHE
 
-static void cache_defer_req(struct cache_req *req, struct cache_head *item);
+static bool cache_defer_req(struct cache_req *req, struct cache_head *item);
 static void cache_revisit_request(struct cache_head *item);
 
 static void cache_init(struct cache_head *h)
@@ -128,6 +128,7 @@ static void cache_fresh_locked(struct cache_head *head, time_t expiry)
 {
 	head->expiry_time = expiry;
 	head->last_refresh = seconds_since_boot();
+	smp_wmb(); /* paired with smp_rmb() in cache_is_valid() */
 	set_bit(CACHE_VALID, &head->flags);
 }
 
@@ -208,11 +209,36 @@ static inline int cache_is_valid(struct cache_detail *detail, struct cache_head
 		/* entry is valid */
 		if (test_bit(CACHE_NEGATIVE, &h->flags))
 			return -ENOENT;
-		else
+		else {
+			/*
+			 * In combination with write barrier in
+			 * sunrpc_cache_update, ensures that anyone
+			 * using the cache entry after this sees the
+			 * updated contents:
+			 */
+			smp_rmb();
 			return 0;
+		}
 	}
 }
 
+static int try_to_negate_entry(struct cache_detail *detail, struct cache_head *h)
+{
+	int rv;
+
+	write_lock(&detail->hash_lock);
+	rv = cache_is_valid(detail, h);
+	if (rv != -EAGAIN) {
+		write_unlock(&detail->hash_lock);
+		return rv;
+	}
+	set_bit(CACHE_NEGATIVE, &h->flags);
+	cache_fresh_locked(h, seconds_since_boot()+CACHE_NEW_EXPIRY);
+	write_unlock(&detail->hash_lock);
+	cache_fresh_unlocked(h, detail);
+	return -ENOENT;
+}
+
 /*
  * This is the generic cache management routine for all
  * the authentication caches.
@@ -251,14 +277,8 @@ int cache_check(struct cache_detail *detail,
 			case -EINVAL:
 				clear_bit(CACHE_PENDING, &h->flags);
 				cache_revisit_request(h);
-				if (rv == -EAGAIN) {
-					set_bit(CACHE_NEGATIVE, &h->flags);
-					cache_fresh_locked(h, seconds_since_boot()+CACHE_NEW_EXPIRY);
-					cache_fresh_unlocked(h, detail);
-					rv = -ENOENT;
-				}
+				rv = try_to_negate_entry(detail, h);
 				break;
-
 			case -EAGAIN:
 				clear_bit(CACHE_PENDING, &h->flags);
 				cache_revisit_request(h);
@@ -268,9 +288,11 @@ int cache_check(struct cache_detail *detail,
 	}
 
 	if (rv == -EAGAIN) {
-		cache_defer_req(rqstp, h);
-		if (!test_bit(CACHE_PENDING, &h->flags)) {
-			/* Request is not deferred */
+		if (!cache_defer_req(rqstp, h)) {
+			/*
+			 * Request was not deferred; handle it as best
+			 * we can ourselves:
+			 */
 			rv = cache_is_valid(detail, h);
 			if (rv == -EAGAIN)
 				rv = -ETIMEDOUT;
@@ -618,18 +640,19 @@ static void cache_limit_defers(void)
 		discard->revisit(discard, 1);
 }
 
-static void cache_defer_req(struct cache_req *req, struct cache_head *item)
+/* Return true if and only if a deferred request is queued. */
+static bool cache_defer_req(struct cache_req *req, struct cache_head *item)
 {
 	struct cache_deferred_req *dreq;
 
 	if (req->thread_wait) {
 		cache_wait_req(req, item);
 		if (!test_bit(CACHE_PENDING, &item->flags))
-			return;
+			return false;
 	}
 	dreq = req->defer(req);
 	if (dreq == NULL)
-		return;
+		return false;
 	setup_deferral(dreq, item, 1);
 	if (!test_bit(CACHE_PENDING, &item->flags))
 		/* Bit could have been cleared before we managed to
@@ -638,6 +661,7 @@ static void cache_defer_req(struct cache_req *req, struct cache_head *item)
 		cache_revisit_request(item);
 
 	cache_limit_defers();
+	return true;
 }
 
 static void cache_revisit_request(struct cache_head *item)
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 0e659c665a8d..08e05a8ce025 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1001,6 +1001,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 	rqstp->rq_splice_ok = 1;
 	/* Will be turned off only when NFSv4 Sessions are used */
 	rqstp->rq_usedeferral = 1;
+	rqstp->rq_dropme = false;
 
 	/* Setup reply header */
 	rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp);
@@ -1102,7 +1103,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 		*statp = procp->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp);
 
 		/* Encode reply */
-		if (*statp == rpc_drop_reply) {
+		if (rqstp->rq_dropme) {
 			if (procp->pc_release)
 				procp->pc_release(rqstp, NULL, rqstp->rq_resp);
 			goto dropit;
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 3f2c5559ca1a..ab86b7927f84 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -13,6 +13,7 @@
 #include <linux/sunrpc/stats.h>
 #include <linux/sunrpc/svc_xprt.h>
 #include <linux/sunrpc/svcsock.h>
+#include <linux/sunrpc/xprt.h>
 
 #define RPCDBG_FACILITY	RPCDBG_SVCXPRT
 
@@ -128,6 +129,9 @@ static void svc_xprt_free(struct kref *kref)
 	if (test_bit(XPT_CACHE_AUTH, &xprt->xpt_flags))
 		svcauth_unix_info_release(xprt);
 	put_net(xprt->xpt_net);
+	/* See comment on corresponding get in xs_setup_bc_tcp(): */
+	if (xprt->xpt_bc_xprt)
+		xprt_put(xprt->xpt_bc_xprt);
 	xprt->xpt_ops->xpo_free(xprt);
 	module_put(owner);
 }
@@ -303,6 +307,15 @@ static void svc_thread_dequeue(struct svc_pool *pool, struct svc_rqst *rqstp)
 	list_del(&rqstp->rq_list);
 }
 
+static bool svc_xprt_has_something_to_do(struct svc_xprt *xprt)
+{
+	if (xprt->xpt_flags & ((1<<XPT_CONN)|(1<<XPT_CLOSE)))
+		return true;
+	if (xprt->xpt_flags & ((1<<XPT_DATA)|(1<<XPT_DEFERRED)))
+		return xprt->xpt_ops->xpo_has_wspace(xprt);
+	return false;
+}
+
 /*
  * Queue up a transport with data pending. If there are idle nfsd
  * processes, wake 'em up.
@@ -315,8 +328,7 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
 	struct svc_rqst	*rqstp;
 	int cpu;
 
-	if (!(xprt->xpt_flags &
-	      ((1<<XPT_CONN)|(1<<XPT_DATA)|(1<<XPT_CLOSE)|(1<<XPT_DEFERRED))))
+	if (!svc_xprt_has_something_to_do(xprt))
 		return;
 
 	cpu = get_cpu();
@@ -343,28 +355,7 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
 		dprintk("svc: transport %p busy, not enqueued\n", xprt);
 		goto out_unlock;
 	}
-	BUG_ON(xprt->xpt_pool != NULL);
-	xprt->xpt_pool = pool;
-
-	/* Handle pending connection */
-	if (test_bit(XPT_CONN, &xprt->xpt_flags))
-		goto process;
-
-	/* Handle close in-progress */
-	if (test_bit(XPT_CLOSE, &xprt->xpt_flags))
-		goto process;
-
-	/* Check if we have space to reply to a request */
-	if (!xprt->xpt_ops->xpo_has_wspace(xprt)) {
-		/* Don't enqueue while not enough space for reply */
-		dprintk("svc: no write space, transport %p  not enqueued\n",
-			xprt);
-		xprt->xpt_pool = NULL;
-		clear_bit(XPT_BUSY, &xprt->xpt_flags);
-		goto out_unlock;
-	}
 
- process:
 	if (!list_empty(&pool->sp_threads)) {
 		rqstp = list_entry(pool->sp_threads.next,
 				   struct svc_rqst,
@@ -381,13 +372,11 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
 		rqstp->rq_reserved = serv->sv_max_mesg;
 		atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved);
 		pool->sp_stats.threads_woken++;
-		BUG_ON(xprt->xpt_pool != pool);
 		wake_up(&rqstp->rq_wait);
 	} else {
 		dprintk("svc: transport %p put into queue\n", xprt);
 		list_add_tail(&xprt->xpt_ready, &pool->sp_sockets);
 		pool->sp_stats.sockets_queued++;
-		BUG_ON(xprt->xpt_pool != pool);
 	}
 
 out_unlock:
@@ -426,7 +415,6 @@ static struct svc_xprt *svc_xprt_dequeue(struct svc_pool *pool)
 void svc_xprt_received(struct svc_xprt *xprt)
 {
 	BUG_ON(!test_bit(XPT_BUSY, &xprt->xpt_flags));
-	xprt->xpt_pool = NULL;
 	/* As soon as we clear busy, the xprt could be closed and
 	 * 'put', so we need a reference to call svc_xprt_enqueue with:
 	 */
@@ -722,7 +710,10 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 	if (test_bit(XPT_CLOSE, &xprt->xpt_flags)) {
 		dprintk("svc_recv: found XPT_CLOSE\n");
 		svc_delete_xprt(xprt);
-	} else if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) {
+		/* Leave XPT_BUSY set on the dead xprt: */
+		goto out;
+	}
+	if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) {
 		struct svc_xprt *newxpt;
 		newxpt = xprt->xpt_ops->xpo_accept(xprt);
 		if (newxpt) {
@@ -747,28 +738,23 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 			spin_unlock_bh(&serv->sv_lock);
 			svc_xprt_received(newxpt);
 		}
-		svc_xprt_received(xprt);
-	} else {
+	} else if (xprt->xpt_ops->xpo_has_wspace(xprt)) {
 		dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n",
 			rqstp, pool->sp_id, xprt,
 			atomic_read(&xprt->xpt_ref.refcount));
 		rqstp->rq_deferred = svc_deferred_dequeue(xprt);
-		if (rqstp->rq_deferred) {
-			svc_xprt_received(xprt);
+		if (rqstp->rq_deferred)
 			len = svc_deferred_recv(rqstp);
-		} else {
+		else
 			len = xprt->xpt_ops->xpo_recvfrom(rqstp);
-			svc_xprt_received(xprt);
-		}
 		dprintk("svc: got len=%d\n", len);
 	}
+	svc_xprt_received(xprt);
 
 	/* No data, incomplete (TCP) read, or accept() */
-	if (len == 0 || len == -EAGAIN) {
-		rqstp->rq_res.len = 0;
-		svc_xprt_release(rqstp);
-		return -EAGAIN;
-	}
+	if (len == 0 || len == -EAGAIN)
+		goto out;
+
 	clear_bit(XPT_OLD, &xprt->xpt_flags);
 
 	rqstp->rq_secure = svc_port_is_privileged(svc_addr(rqstp));
@@ -777,6 +763,10 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 	if (serv->sv_stats)
 		serv->sv_stats->netcnt++;
 	return len;
+out:
+	rqstp->rq_res.len = 0;
+	svc_xprt_release(rqstp);
+	return -EAGAIN;
 }
 EXPORT_SYMBOL_GPL(svc_recv);
 
@@ -935,7 +925,12 @@ void svc_close_xprt(struct svc_xprt *xprt)
 	if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags))
 		/* someone else will have to effect the close */
 		return;
-
+	/*
+	 * We expect svc_close_xprt() to work even when no threads are
+	 * running (e.g., while configuring the server before starting
+	 * any threads), so if the transport isn't busy, we delete
+	 * it ourself:
+	 */
 	svc_delete_xprt(xprt);
 }
 EXPORT_SYMBOL_GPL(svc_close_xprt);
@@ -945,16 +940,16 @@ void svc_close_all(struct list_head *xprt_list)
 	struct svc_xprt *xprt;
 	struct svc_xprt *tmp;
 
+	/*
+	 * The server is shutting down, and no more threads are running.
+	 * svc_xprt_enqueue() might still be running, but at worst it
+	 * will re-add the xprt to sp_sockets, which will soon get
+	 * freed.  So we don't bother with any more locking, and don't
+	 * leave the close to the (nonexistent) server threads:
+	 */
 	list_for_each_entry_safe(xprt, tmp, xprt_list, xpt_list) {
 		set_bit(XPT_CLOSE, &xprt->xpt_flags);
-		if (test_bit(XPT_BUSY, &xprt->xpt_flags)) {
-			/* Waiting to be processed, but no threads left,
-			 * So just remove it from the waiting list
-			 */
-			list_del_init(&xprt->xpt_ready);
-			clear_bit(XPT_BUSY, &xprt->xpt_flags);
-		}
-		svc_close_xprt(xprt);
+		svc_delete_xprt(xprt);
 	}
 }
 
@@ -1028,6 +1023,7 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req)
 	}
 	svc_xprt_get(rqstp->rq_xprt);
 	dr->xprt = rqstp->rq_xprt;
+	rqstp->rq_dropme = true;
 
 	dr->handle.revisit = svc_revisit;
 	return &dr->handle;
@@ -1065,14 +1061,13 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt)
 	if (!test_bit(XPT_DEFERRED, &xprt->xpt_flags))
 		return NULL;
 	spin_lock(&xprt->xpt_lock);
-	clear_bit(XPT_DEFERRED, &xprt->xpt_flags);
 	if (!list_empty(&xprt->xpt_deferred)) {
 		dr = list_entry(xprt->xpt_deferred.next,
 				struct svc_deferred_req,
 				handle.recent);
 		list_del_init(&dr->handle.recent);
-		set_bit(XPT_DEFERRED, &xprt->xpt_flags);
-	}
+	} else
+		clear_bit(XPT_DEFERRED, &xprt->xpt_flags);
 	spin_unlock(&xprt->xpt_lock);
 	return dr;
 }
diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c
index 4e9393c24687..7963569fc04f 100644
--- a/net/sunrpc/svcauth.c
+++ b/net/sunrpc/svcauth.c
@@ -118,7 +118,6 @@ EXPORT_SYMBOL_GPL(svc_auth_unregister);
 
 #define	DN_HASHBITS	6
 #define	DN_HASHMAX	(1<<DN_HASHBITS)
-#define	DN_HASHMASK	(DN_HASHMAX-1)
 
 static struct hlist_head	auth_domain_table[DN_HASHMAX];
 static spinlock_t	auth_domain_lock =
diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c
index 560677d187f1..30916b06c12b 100644
--- a/net/sunrpc/svcauth_unix.c
+++ b/net/sunrpc/svcauth_unix.c
@@ -30,7 +30,9 @@
 
 struct unix_domain {
 	struct auth_domain	h;
+#ifdef CONFIG_NFSD_DEPRECATED
 	int	addr_changes;
+#endif /* CONFIG_NFSD_DEPRECATED */
 	/* other stuff later */
 };
 
@@ -64,7 +66,9 @@ struct auth_domain *unix_domain_find(char *name)
 			return NULL;
 		}
 		new->h.flavour = &svcauth_unix;
+#ifdef CONFIG_NFSD_DEPRECATED
 		new->addr_changes = 0;
+#endif /* CONFIG_NFSD_DEPRECATED */
 		rv = auth_domain_lookup(name, &new->h);
 	}
 }
@@ -85,14 +89,15 @@ static void svcauth_unix_domain_release(struct auth_domain *dom)
  */
 #define	IP_HASHBITS	8
 #define	IP_HASHMAX	(1<<IP_HASHBITS)
-#define	IP_HASHMASK	(IP_HASHMAX-1)
 
 struct ip_map {
 	struct cache_head	h;
 	char			m_class[8]; /* e.g. "nfsd" */
 	struct in6_addr		m_addr;
 	struct unix_domain	*m_client;
+#ifdef CONFIG_NFSD_DEPRECATED
 	int			m_add_change;
+#endif /* CONFIG_NFSD_DEPRECATED */
 };
 
 static void ip_map_put(struct kref *kref)
@@ -146,7 +151,9 @@ static void update(struct cache_head *cnew, struct cache_head *citem)
 
 	kref_get(&item->m_client->h.ref);
 	new->m_client = item->m_client;
+#ifdef CONFIG_NFSD_DEPRECATED
 	new->m_add_change = item->m_add_change;
+#endif /* CONFIG_NFSD_DEPRECATED */
 }
 static struct cache_head *ip_map_alloc(void)
 {
@@ -331,6 +338,7 @@ static int __ip_map_update(struct cache_detail *cd, struct ip_map *ipm,
 	ip.h.flags = 0;
 	if (!udom)
 		set_bit(CACHE_NEGATIVE, &ip.h.flags);
+#ifdef CONFIG_NFSD_DEPRECATED
 	else {
 		ip.m_add_change = udom->addr_changes;
 		/* if this is from the legacy set_client system call,
@@ -339,6 +347,7 @@ static int __ip_map_update(struct cache_detail *cd, struct ip_map *ipm,
 		if (expiry == NEVER)
 			ip.m_add_change++;
 	}
+#endif /* CONFIG_NFSD_DEPRECATED */
 	ip.h.expiry_time = expiry;
 	ch = sunrpc_cache_update(cd, &ip.h, &ipm->h,
 				 hash_str(ipm->m_class, IP_HASHBITS) ^
@@ -358,6 +367,7 @@ static inline int ip_map_update(struct net *net, struct ip_map *ipm,
 	return __ip_map_update(sn->ip_map_cache, ipm, udom, expiry);
 }
 
+#ifdef CONFIG_NFSD_DEPRECATED
 int auth_unix_add_addr(struct net *net, struct in6_addr *addr, struct auth_domain *dom)
 {
 	struct unix_domain *udom;
@@ -402,8 +412,7 @@ struct auth_domain *auth_unix_lookup(struct net *net, struct in6_addr *addr)
 		return NULL;
 
 	if ((ipm->m_client->addr_changes - ipm->m_add_change) >0) {
-		if (test_and_set_bit(CACHE_NEGATIVE, &ipm->h.flags) == 0)
-			auth_domain_put(&ipm->m_client->h);
+		sunrpc_invalidate(&ipm->h, sn->ip_map_cache);
 		rv = NULL;
 	} else {
 		rv = &ipm->m_client->h;
@@ -413,6 +422,7 @@ struct auth_domain *auth_unix_lookup(struct net *net, struct in6_addr *addr)
 	return rv;
 }
 EXPORT_SYMBOL_GPL(auth_unix_lookup);
+#endif /* CONFIG_NFSD_DEPRECATED */
 
 void svcauth_unix_purge(void)
 {
@@ -497,7 +507,6 @@ svcauth_unix_info_release(struct svc_xprt *xpt)
  */
 #define	GID_HASHBITS	8
 #define	GID_HASHMAX	(1<<GID_HASHBITS)
-#define	GID_HASHMASK	(GID_HASHMAX - 1)
 
 struct unix_gid {
 	struct cache_head	h;
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index d265aa700bb3..7bd3bbba4710 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -331,19 +331,21 @@ int svc_sock_names(struct svc_serv *serv, char *buf, const size_t buflen,
 			len = onelen;
 			break;
 		}
-		if (toclose && strcmp(toclose, buf + len) == 0)
+		if (toclose && strcmp(toclose, buf + len) == 0) {
 			closesk = svsk;
-		else
+			svc_xprt_get(&closesk->sk_xprt);
+		} else
 			len += onelen;
 	}
 	spin_unlock_bh(&serv->sv_lock);
 
-	if (closesk)
+	if (closesk) {
 		/* Should unregister with portmap, but you cannot
 		 * unregister just one protocol...
 		 */
 		svc_close_xprt(&closesk->sk_xprt);
-	else if (toclose)
+		svc_xprt_put(&closesk->sk_xprt);
+	} else if (toclose)
 		return -ENOENT;
 	return len;
 }
@@ -992,15 +994,17 @@ static int svc_process_calldir(struct svc_sock *svsk, struct svc_rqst *rqstp,
 		vec[0] = rqstp->rq_arg.head[0];
 	} else {
 		/* REPLY */
-		if (svsk->sk_bc_xprt)
-			req = xprt_lookup_rqst(svsk->sk_bc_xprt, xid);
+		struct rpc_xprt *bc_xprt = svsk->sk_xprt.xpt_bc_xprt;
+
+		if (bc_xprt)
+			req = xprt_lookup_rqst(bc_xprt, xid);
 
 		if (!req) {
 			printk(KERN_NOTICE
 				"%s: Got unrecognized reply: "
-				"calldir 0x%x sk_bc_xprt %p xid %08x\n",
+				"calldir 0x%x xpt_bc_xprt %p xid %08x\n",
 				__func__, ntohl(calldir),
-				svsk->sk_bc_xprt, xid);
+				bc_xprt, xid);
 			vec[0] = rqstp->rq_arg.head[0];
 			goto out;
 		}
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 4c8f18aff7c3..856274d7e85c 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -965,6 +965,7 @@ struct rpc_xprt *xprt_alloc(struct net *net, int size, int max_req)
 	xprt = kzalloc(size, GFP_KERNEL);
 	if (xprt == NULL)
 		goto out;
+	kref_init(&xprt->kref);
 
 	xprt->max_reqs = max_req;
 	xprt->slot = kcalloc(max_req, sizeof(struct rpc_rqst), GFP_KERNEL);
@@ -1101,8 +1102,10 @@ found:
 				-PTR_ERR(xprt));
 		return xprt;
 	}
+	if (test_and_set_bit(XPRT_INITIALIZED, &xprt->state))
+		/* ->setup returned a pre-initialized xprt: */
+		return xprt;
 
-	kref_init(&xprt->kref);
 	spin_lock_init(&xprt->transport_lock);
 	spin_lock_init(&xprt->reserve_lock);
 
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 96549df836ee..c431f5a57960 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2359,6 +2359,15 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args)
 	struct svc_sock *bc_sock;
 	struct rpc_xprt *ret;
 
+	if (args->bc_xprt->xpt_bc_xprt) {
+		/*
+		 * This server connection already has a backchannel
+		 * export; we can't create a new one, as we wouldn't be
+		 * able to match replies based on xid any more.  So,
+		 * reuse the already-existing one:
+		 */
+		 return args->bc_xprt->xpt_bc_xprt;
+	}
 	xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries);
 	if (IS_ERR(xprt))
 		return xprt;
@@ -2375,16 +2384,6 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args)
 	xprt->reestablish_timeout = 0;
 	xprt->idle_timeout = 0;
 
-	/*
-	 * The backchannel uses the same socket connection as the
-	 * forechannel
-	 */
-	xprt->bc_xprt = args->bc_xprt;
-	bc_sock = container_of(args->bc_xprt, struct svc_sock, sk_xprt);
-	bc_sock->sk_bc_xprt = xprt;
-	transport->sock = bc_sock->sk_sock;
-	transport->inet = bc_sock->sk_sk;
-
 	xprt->ops = &bc_tcp_ops;
 
 	switch (addr->sa_family) {
@@ -2407,6 +2406,20 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args)
 			xprt->address_strings[RPC_DISPLAY_PROTO]);
 
 	/*
+	 * Once we've associated a backchannel xprt with a connection,
+	 * we want to keep it around as long as long as the connection
+	 * lasts, in case we need to start using it for a backchannel
+	 * again; this reference won't be dropped until bc_xprt is
+	 * destroyed.
+	 */
+	xprt_get(xprt);
+	args->bc_xprt->xpt_bc_xprt = xprt;
+	xprt->bc_xprt = args->bc_xprt;
+	bc_sock = container_of(args->bc_xprt, struct svc_sock, sk_xprt);
+	transport->sock = bc_sock->sk_sock;
+	transport->inet = bc_sock->sk_sk;
+
+	/*
 	 * Since we don't want connections for the backchannel, we set
 	 * the xprt status to connected
 	 */
@@ -2415,6 +2428,7 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args)
 
 	if (try_module_get(THIS_MODULE))
 		return xprt;
+	xprt_put(xprt);
 	ret = ERR_PTR(-EINVAL);
 out_err:
 	xprt_free(xprt);
author	Linus Torvalds <torvalds@linux-foundation.org>	2011-01-15 00:17:26 +0300
committer	Linus Torvalds <torvalds@linux-foundation.org>	2011-01-15 00:17:26 +0300
commit	18bce371ae09af6c20ee62c1092a4d1d0e84dd49 (patch)
tree	f3467fafd8e49392e3f6efef7b88a7b4dd3b7b06
parent	ec08bdb148767f1193f5f3028749ed865ac27181 (diff)
parent	a8f2800b4f7b76cecb7209cb6a7d2b14904fc711 (diff)
download	linux-18bce371ae09af6c20ee62c1092a4d1d0e84dd49.tar.xz