Merge branch 'for-2.6.30' of git://linux-nfs.org/~bfields/linux

* 'for-2.6.30' of git://linux-nfs.org/~bfields/linux: (81 commits)
  nfsd41: define nfsd4_set_statp as noop for !CONFIG_NFSD_V4
  nfsd41: define NFSD_DRC_SIZE_SHIFT in set_max_drc
  nfsd41: Documentation/filesystems/nfs41-server.txt
  nfsd41: CREATE_EXCLUSIVE4_1
  nfsd41: SUPPATTR_EXCLCREAT attribute
  nfsd41: support for 3-word long attribute bitmask
  nfsd: dynamically skip encoded fattr bitmap in _nfsd4_verify
  nfsd41: pass writable attrs mask to nfsd4_decode_fattr
  nfsd41: provide support for minor version 1 at rpc level
  nfsd41: control nfsv4.1 svc via /proc/fs/nfsd/versions
  nfsd41: add OPEN4_SHARE_ACCESS_WANT nfs4_stateid bmap
  nfsd41: access_valid
  nfsd41: clientid handling
  nfsd41: check encode size for sessions maxresponse cached
  nfsd41: stateid handling
  nfsd: pass nfsd4_compound_state* to nfs4_preprocess_{state,seq}id_op
  nfsd41: destroy_session operation
  nfsd41: non-page DRC for solo sequence responses
  nfsd41: Add a create session replay cache
  nfsd41: create_session operation
  ...

29 files changed, 2997 insertions, 555 deletions

diff --git a/Documentation/filesystems/knfsd-stats.txt b/Documentation/filesystems/knfsd-stats.txt
new file mode 100644
index 00000000000..64ced5149d3
--- /dev/null
+++ b/Documentation/filesystems/knfsd-stats.txt
@@ -0,0 +1,159 @@
+
+Kernel NFS Server Statistics
+============================
+
+This document describes the format and semantics of the statistics
+which the kernel NFS server makes available to userspace.  These
+statistics are available in several text form pseudo files, each of
+which is described separately below.
+
+In most cases you don't need to know these formats, as the nfsstat(8)
+program from the nfs-utils distribution provides a helpful command-line
+interface for extracting and printing them.
+
+All the files described here are formatted as a sequence of text lines,
+separated by newline '\n' characters.  Lines beginning with a hash
+'#' character are comments intended for humans and should be ignored
+by parsing routines.  All other lines contain a sequence of fields
+separated by whitespace.
+
+/proc/fs/nfsd/pool_stats
+------------------------
+
+This file is available in kernels from 2.6.30 onwards, if the
+/proc/fs/nfsd filesystem is mounted (it almost always should be).
+
+The first line is a comment which describes the fields present in
+all the other lines.  The other lines present the following data as
+a sequence of unsigned decimal numeric fields.  One line is shown
+for each NFS thread pool.
+
+All counters are 64 bits wide and wrap naturally.  There is no way
+to zero these counters, instead applications should do their own
+rate conversion.
+
+pool
+	The id number of the NFS thread pool to which this line applies.
+	This number does not change.
+
+	Thread pool ids are a contiguous set of small integers starting
+	at zero.  The maximum value depends on the thread pool mode, but
+	currently cannot be larger than the number of CPUs in the system.
+	Note that in the default case there will be a single thread pool
+	which contains all the nfsd threads and all the CPUs in the system,
+	and thus this file will have a single line with a pool id of "0".
+
+packets-arrived
+	Counts how many NFS packets have arrived.  More precisely, this
+	is the number of times that the network stack has notified the
+	sunrpc server layer that new data may be available on a transport
+	(e.g. an NFS or UDP socket or an NFS/RDMA endpoint).
+
+	Depending on the NFS workload patterns and various network stack
+	effects (such as Large Receive Offload) which can combine packets
+	on the wire, this may be either more or less than the number
+	of NFS calls received (which statistic is available elsewhere).
+	However this is a more accurate and less workload-dependent measure
+	of how much CPU load is being placed on the sunrpc server layer
+	due to NFS network traffic.
+
+sockets-enqueued
+	Counts how many times an NFS transport is enqueued to wait for
+	an nfsd thread to service it, i.e. no nfsd thread was considered
+	available.
+
+	The circumstance this statistic tracks indicates that there was NFS
+	network-facing work to be done but it couldn't be done immediately,
+	thus introducing a small delay in servicing NFS calls.  The ideal
+	rate of change for this counter is zero; significantly non-zero
+	values may indicate a performance limitation.
+
+	This can happen either because there are too few nfsd threads in the
+	thread pool for the NFS workload (the workload is thread-limited),
+	or because the NFS workload needs more CPU time than is available in
+	the thread pool (the workload is CPU-limited).  In the former case,
+	configuring more nfsd threads will probably improve the performance
+	of the NFS workload.  In the latter case, the sunrpc server layer is
+	already choosing not to wake idle nfsd threads because there are too
+	many nfsd threads which want to run but cannot, so configuring more
+	nfsd threads will make no difference whatsoever.  The overloads-avoided
+	statistic (see below) can be used to distinguish these cases.
+
+threads-woken
+	Counts how many times an idle nfsd thread is woken to try to
+	receive some data from an NFS transport.
+
+	This statistic tracks the circumstance where incoming
+	network-facing NFS work is being handled quickly, which is a good
+	thing.  The ideal rate of change for this counter will be close
+	to but less than the rate of change of the packets-arrived counter.
+
+overloads-avoided
+	Counts how many times the sunrpc server layer chose not to wake an
+	nfsd thread, despite the presence of idle nfsd threads, because
+	too many nfsd threads had been recently woken but could not get
+	enough CPU time to actually run.
+
+	This statistic counts a circumstance where the sunrpc layer
+	heuristically avoids overloading the CPU scheduler with too many
+	runnable nfsd threads.  The ideal rate of change for this counter
+	is zero.  Significant non-zero values indicate that the workload
+	is CPU limited.  Usually this is associated with heavy CPU usage
+	on all the CPUs in the nfsd thread pool.
+
+	If a sustained large overloads-avoided rate is detected on a pool,
+	the top(1) utility should be used to check for the following
+	pattern of CPU usage on all the CPUs associated with the given
+	nfsd thread pool.
+
+	 - %us ~= 0 (as you're *NOT* running applications on your NFS server)
+
+	 - %wa ~= 0
+
+	 - %id ~= 0
+
+	 - %sy + %hi + %si ~= 100
+
+	If this pattern is seen, configuring more nfsd threads will *not*
+	improve the performance of the workload.  If this patten is not
+	seen, then something more subtle is wrong.
+
+threads-timedout
+	Counts how many times an nfsd thread triggered an idle timeout,
+	i.e. was not woken to handle any incoming network packets for
+	some time.
+
+	This statistic counts a circumstance where there are more nfsd
+	threads configured than can be used by the NFS workload.  This is
+	a clue that the number of nfsd threads can be reduced without
+	affecting performance.  Unfortunately, it's only a clue and not
+	a strong indication, for a couple of reasons:
+
+	 - Currently the rate at which the counter is incremented is quite
+	   slow; the idle timeout is 60 minutes.  Unless the NFS workload
+	   remains constant for hours at a time, this counter is unlikely
+	   to be providing information that is still useful.
+
+	 - It is usually a wise policy to provide some slack,
+	   i.e. configure a few more nfsds than are currently needed,
+	   to allow for future spikes in load.
+
+
+Note that incoming packets on NFS transports will be dealt with in
+one of three ways.  An nfsd thread can be woken (threads-woken counts
+this case), or the transport can be enqueued for later attention
+(sockets-enqueued counts this case), or the packet can be temporarily
+deferred because the transport is currently being used by an nfsd
+thread.  This last case is not very interesting and is not explicitly
+counted, but can be inferred from the other counters thus:
+
+packets-deferred = packets-arrived - ( sockets-enqueued + threads-woken )
+
+
+More
+----
+Descriptions of the other statistics file should go here.
+
+
+Greg Banks <gnb@sgi.com>
+26 Mar 2009
diff --git a/Documentation/filesystems/nfs41-server.txt b/Documentation/filesystems/nfs41-server.txt
new file mode 100644
index 00000000000..05d81cbcb2e
--- /dev/null
+++ b/Documentation/filesystems/nfs41-server.txt
@@ -0,0 +1,161 @@
+NFSv4.1 Server Implementation
+
+Server support for minorversion 1 can be controlled using the
+/proc/fs/nfsd/versions control file.  The string output returned
+by reading this file will contain either "+4.1" or "-4.1"
+correspondingly.
+
+Currently, server support for minorversion 1 is disabled by default.
+It can be enabled at run time by writing the string "+4.1" to
+the /proc/fs/nfsd/versions control file.  Note that to write this
+control file, the nfsd service must be taken down.  Use your user-mode
+nfs-utils to set this up; see rpc.nfsd(8)
+
+The NFSv4 minorversion 1 (NFSv4.1) implementation in nfsd is based
+on the latest NFSv4.1 Internet Draft:
+http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-29
+
+From the many new features in NFSv4.1 the current implementation
+focuses on the mandatory-to-implement NFSv4.1 Sessions, providing
+"exactly once" semantics and better control and throttling of the
+resources allocated for each client.
+
+Other NFSv4.1 features, Parallel NFS operations in particular,
+are still under development out of tree.
+See http://wiki.linux-nfs.org/wiki/index.php/PNFS_prototype_design
+for more information.
+
+The table below, taken from the NFSv4.1 document, lists
+the operations that are mandatory to implement (REQ), optional
+(OPT), and NFSv4.0 operations that are required not to implement (MNI)
+in minor version 1.  The first column indicates the operations that
+are not supported yet by the linux server implementation.
+
+The OPTIONAL features identified and their abbreviations are as follows:
+	pNFS	Parallel NFS
+	FDELG	File Delegations
+	DDELG	Directory Delegations
+
+The following abbreviations indicate the linux server implementation status.
+	I	Implemented NFSv4.1 operations.
+	NS	Not Supported.
+	NS*	unimplemented optional feature.
+	P	pNFS features implemented out of tree.
+	PNS	pNFS features that are not supported yet (out of tree).
+
+Operations
+
+   +----------------------+------------+--------------+----------------+
+   | Operation            | REQ, REC,  | Feature      | Definition     |
+   |                      | OPT, or    | (REQ, REC,   |                |
+   |                      | MNI        | or OPT)      |                |
+   +----------------------+------------+--------------+----------------+
+   | ACCESS               | REQ        |              | Section 18.1   |
+NS | BACKCHANNEL_CTL      | REQ        |              | Section 18.33  |
+NS | BIND_CONN_TO_SESSION | REQ        |              | Section 18.34  |
+   | CLOSE                | REQ        |              | Section 18.2   |
+   | COMMIT               | REQ        |              | Section 18.3   |
+   | CREATE               | REQ        |              | Section 18.4   |
+I  | CREATE_SESSION       | REQ        |              | Section 18.36  |
+NS*| DELEGPURGE           | OPT        | FDELG (REQ)  | Section 18.5   |
+   | DELEGRETURN          | OPT        | FDELG,       | Section 18.6   |
+   |                      |            | DDELG, pNFS  |                |
+   |                      |            | (REQ)        |                |
+NS | DESTROY_CLIENTID     | REQ        |              | Section 18.50  |
+I  | DESTROY_SESSION      | REQ        |              | Section 18.37  |
+I  | EXCHANGE_ID          | REQ        |              | Section 18.35  |
+NS | FREE_STATEID         | REQ        |              | Section 18.38  |
+   | GETATTR              | REQ        |              | Section 18.7   |
+P  | GETDEVICEINFO        | OPT        | pNFS (REQ)   | Section 18.40  |
+P  | GETDEVICELIST        | OPT        | pNFS (OPT)   | Section 18.41  |
+   | GETFH                | REQ        |              | Section 18.8   |
+NS*| GET_DIR_DELEGATION   | OPT        | DDELG (REQ)  | Section 18.39  |
+P  | LAYOUTCOMMIT         | OPT        | pNFS (REQ)   | Section 18.42  |
+P  | LAYOUTGET            | OPT        | pNFS (REQ)   | Section 18.43  |
+P  | LAYOUTRETURN         | OPT        | pNFS (REQ)   | Section 18.44  |
+   | LINK                 | OPT        |              | Section 18.9   |
+   | LOCK                 | REQ        |              | Section 18.10  |
+   | LOCKT                | REQ        |              | Section 18.11  |
+   | LOCKU                | REQ        |              | Section 18.12  |
+   | LOOKUP               | REQ        |              | Section 18.13  |
+   | LOOKUPP              | REQ        |              | Section 18.14  |
+   | NVERIFY              | REQ        |              | Section 18.15  |
+   | OPEN                 | REQ        |              | Section 18.16  |
+NS*| OPENATTR             | OPT        |              | Section 18.17  |
+   | OPEN_CONFIRM         | MNI        |              | N/A            |
+   | OPEN_DOWNGRADE       | REQ        |              | Section 18.18  |
+   | PUTFH                | REQ        |              | Section 18.19  |
+   | PUTPUBFH             | REQ        |              | Section 18.20  |
+   | PUTROOTFH            | REQ        |              | Section 18.21  |
+   | READ                 | REQ        |              | Section 18.22  |
+   | READDIR              | REQ        |              | Section 18.23  |
+   | READLINK             | OPT        |              | Section 18.24  |
+NS | RECLAIM_COMPLETE     | REQ        |              | Section 18.51  |
+   | RELEASE_LOCKOWNER    | MNI        |              | N/A            |
+   | REMOVE               | REQ        |              | Section 18.25  |
+   | RENAME               | REQ        |              | Section 18.26  |
+   | RENEW                | MNI        |              | N/A            |
+   | RESTOREFH            | REQ        |              | Section 18.27  |
+   | SAVEFH               | REQ        |              | Section 18.28  |
+   | SECINFO              | REQ        |              | Section 18.29  |
+NS | SECINFO_NO_NAME      | REC        | pNFS files   | Section 18.45, |
+   |                      |            | layout (REQ) | Section 13.12  |
+I  | SEQUENCE             | REQ        |              | Section 18.46  |
+   | SETATTR              | REQ        |              | Section 18.30  |
+   | SETCLIENTID          | MNI        |              | N/A            |
+   | SETCLIENTID_CONFIRM  | MNI        |              | N/A            |
+NS | SET_SSV              | REQ        |              | Section 18.47  |
+NS | TEST_STATEID         | REQ        |              | Section 18.48  |
+   | VERIFY               | REQ        |              | Section 18.31  |
+NS*| WANT_DELEGATION      | OPT        | FDELG (OPT)  | Section 18.49  |
+   | WRITE                | REQ        |              | Section 18.32  |
+
+Callback Operations
+
+   +-------------------------+-----------+-------------+---------------+
+   | Operation               | REQ, REC, | Feature     | Definition    |
+   |                         | OPT, or   | (REQ, REC,  |               |
+   |                         | MNI       | or OPT)     |               |
+   +-------------------------+-----------+-------------+---------------+
+   | CB_GETATTR              | OPT       | FDELG (REQ) | Section 20.1  |
+P  | CB_LAYOUTRECALL         | OPT       | pNFS (REQ)  | Section 20.3  |
+NS*| CB_NOTIFY               | OPT       | DDELG (REQ) | Section 20.4  |
+P  | CB_NOTIFY_DEVICEID      | OPT       | pNFS (OPT)  | Section 20.12 |
+NS*| CB_NOTIFY_LOCK          | OPT       |             | Section 20.11 |
+NS*| CB_PUSH_DELEG           | OPT       | FDELG (OPT) | Section 20.5  |
+   | CB_RECALL               | OPT       | FDELG,      | Section 20.2  |
+   |                         |           | DDELG, pNFS |               |
+   |                         |           | (REQ)       |               |
+NS*| CB_RECALL_ANY           | OPT       | FDELG,      | Section 20.6  |
+   |                         |           | DDELG, pNFS |               |
+   |                         |           | (REQ)       |               |
+NS | CB_RECALL_SLOT          | REQ       |             | Section 20.8  |
+NS*| CB_RECALLABLE_OBJ_AVAIL | OPT       | DDELG, pNFS | Section 20.7  |
+   |                         |           | (REQ)       |               |
+I  | CB_SEQUENCE             | OPT       | FDELG,      | Section 20.9  |
+   |                         |           | DDELG, pNFS |               |
+   |                         |           | (REQ)       |               |
+NS*| CB_WANTS_CANCELLED      | OPT       | FDELG,      | Section 20.10 |
+   |                         |           | DDELG, pNFS |               |
+   |                         |           | (REQ)       |               |
+   +-------------------------+-----------+-------------+---------------+
+
+Implementation notes:
+
+EXCHANGE_ID:
+* only SP4_NONE state protection supported
+* implementation ids are ignored
+
+CREATE_SESSION:
+* backchannel attributes are ignored
+* backchannel security parameters are ignored
+
+SEQUENCE:
+* no support for dynamic slot table renegotiation (optional)
+
+nfsv4.1 COMPOUND rules:
+The following cases aren't supported yet:
+* Enforcing of NFS4ERR_NOT_ONLY_OP for: BIND_CONN_TO_SESSION, CREATE_SESSION,
+  DESTROY_CLIENTID, DESTROY_SESSION, EXCHANGE_ID.
+* DESTROY_SESSION MUST be the final operation in the COMPOUND request.
+
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index 763b78a6e9d..83ee34203bd 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -426,8 +426,15 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 			ret = nlm_granted;
 			goto out;
 		case -EAGAIN:
+			/*
+			 * If this is a blocking request for an
+			 * already pending lock request then we need
+			 * to put it back on lockd's block list
+			 */
+			if (wait)
+				break;
 			ret = nlm_lck_denied;
-			break;
+			goto out;
 		case FILE_LOCK_DEFERRED:
 			if (wait)
 				break;
@@ -443,10 +450,6 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 			goto out;
 	}
 
-	ret = nlm_lck_denied;
-	if (!wait)
-		goto out;
-
 	ret = nlm_lck_blocked;
 
 	/* Append to list of blocked */
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 44d7d04dab9..503b9da159a 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -1,6 +1,7 @@
 config NFSD
 	tristate "NFS server support"
 	depends on INET
+	depends on FILE_LOCKING
 	select LOCKD
 	select SUNRPC
 	select EXPORTFS
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 9dbd2eb9128..7c9fe838f03 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -18,6 +18,7 @@
 #include <linux/unistd.h>
 #include <linux/slab.h>
 #include <linux/major.h>
+#include <linux/magic.h>
 
 #include <linux/sunrpc/svc.h>
 #include <linux/nfsd/nfsd.h>
@@ -202,6 +203,7 @@ nfsd3_proc_write(struct svc_rqst *rqstp, struct nfsd3_writeargs *argp,
 					 struct nfsd3_writeres  *resp)
 {
 	__be32	nfserr;
+	unsigned long cnt = argp->len;
 
 	dprintk("nfsd: WRITE(3)    %s %d bytes at %ld%s\n",
 				SVCFH_fmt(&argp->fh),
@@ -214,9 +216,9 @@ nfsd3_proc_write(struct svc_rqst *rqstp, struct nfsd3_writeargs *argp,
 	nfserr = nfsd_write(rqstp, &resp->fh, NULL,
 				   argp->offset,
 				   rqstp->rq_vec, argp->vlen,
-				   argp->len,
+				   &cnt,
 				   &resp->committed);
-	resp->count = argp->count;
+	resp->count = cnt;
 	RETURN_STATUS(nfserr);
 }
 
@@ -569,7 +571,7 @@ nfsd3_proc_fsinfo(struct svc_rqst * rqstp, struct nfsd_fhandle    *argp,
 		struct super_block *sb = argp->fh.fh_dentry->d_inode->i_sb;
 
 		/* Note that we don't care for remote fs's here */
-		if (sb->s_magic == 0x4d44 /* MSDOS_SUPER_MAGIC */) {
+		if (sb->s_magic == MSDOS_SUPER_MAGIC) {
 			resp->f_properties = NFS3_FSF_BILLYBOY;
 		}
 		resp->f_maxfilesize = sb->s_maxbytes;
@@ -610,7 +612,7 @@ nfsd3_proc_pathconf(struct svc_rqst * rqstp, struct nfsd_fhandle      *argp,
 			resp->p_link_max = EXT2_LINK_MAX;
 			resp->p_name_max = EXT2_NAME_LEN;
 			break;
-		case 0x4d44:	/* MSDOS_SUPER_MAGIC */
+		case MSDOS_SUPER_MAGIC:
 			resp->p_case_insensitive = 1;
 			resp->p_case_preserving  = 0;
 			break;
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index c464181b599..290289bd44f 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -218,7 +218,7 @@ static int
 encode_cb_recall(struct xdr_stream *xdr, struct nfs4_cb_recall *cb_rec)
 {
 	__be32 *p;
-	int len = cb_rec->cbr_fhlen;
+	int len = cb_rec->cbr_fh.fh_size;
 
 	RESERVE_SPACE(12+sizeof(cb_rec->cbr_stateid) + len);
 	WRITE32(OP_CB_RECALL);
@@ -226,7 +226,7 @@ encode_cb_recall(struct xdr_stream *xdr, struct nfs4_cb_recall *cb_rec)
 	WRITEMEM(&cb_rec->cbr_stateid.si_opaque, sizeof(stateid_opaque_t));
 	WRITE32(cb_rec->cbr_trunc);
 	WRITE32(len);
-	WRITEMEM(cb_rec->cbr_fhval, len);
+	WRITEMEM(&cb_rec->cbr_fh.fh_base, len);
 	return 0;
 }
 
@@ -361,9 +361,8 @@ static struct rpc_program cb_program = {
 /* Reference counting, callback cleanup, etc., all look racy as heck.
  * And why is cb_set an atomic? */
 
-static int do_probe_callback(void *data)
+static struct rpc_clnt *setup_callback_client(struct nfs4_client *clp)
 {
-	struct nfs4_client *clp = data;
 	struct sockaddr_in	addr;
 	struct nfs4_callback    *cb = &clp->cl_callback;
 	struct rpc_timeout	timeparms = {
@@ -384,17 +383,10 @@ static int do_probe_callback(void *data)
 		.flags		= (RPC_CLNT_CREATE_NOPING | RPC_CLNT_CREATE_QUIET),
 		.client_name    = clp->cl_principal,
 	};
-	struct rpc_message msg = {
-		.rpc_proc       = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL],
-		.rpc_argp       = clp,
-	};
 	struct rpc_clnt *client;
-	int status;
 
-	if (!clp->cl_principal && (clp->cl_flavor >= RPC_AUTH_GSS_KRB5)) {
-		status = nfserr_cb_path_down;
-		goto out_err;
-	}
+	if (!clp->cl_principal && (clp->cl_flavor >= RPC_AUTH_GSS_KRB5))
+		return ERR_PTR(-EINVAL);
 
 	/* Initialize address */
 	memset(&addr, 0, sizeof(addr));
@@ -404,9 +396,29 @@ static int do_probe_callback(void *data)
 
 	/* Create RPC client */
 	client = rpc_create(&args);
+	if (IS_ERR(client))
+		dprintk("NFSD: couldn't create callback client: %ld\n",
+			PTR_ERR(client));
+	return client;
+
+}
+
+static int do_probe_callback(void *data)
+{
+	struct nfs4_client *clp = data;
+	struct nfs4_callback    *cb = &clp->cl_callback;
+	struct rpc_message msg = {
+		.rpc_proc       = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL],
+		.rpc_argp       = clp,
+	};
+	struct rpc_clnt *client;
+	int status;
+
+	client = setup_callback_client(clp);
 	if (IS_ERR(client)) {
-		dprintk("NFSD: couldn't create callback client\n");
 		status = PTR_ERR(client);
+		dprintk("NFSD: couldn't create callback client: %d\n",
+								status);
 		goto out_err;
 	}
 
@@ -422,10 +434,10 @@ static int do_probe_callback(void *data)
 out_release_client:
 	rpc_shutdown_client(client);
 out_err:
-	dprintk("NFSD: warning: no callback path to client %.*s\n",
-		(int)clp->cl_name.len, clp->cl_name.data);
+	dprintk("NFSD: warning: no callback path to client %.*s: error %d\n",
+		(int)clp->cl_name.len, clp->cl_name.data, status);
 	put_nfs4_client(clp);
-	return status;
+	return 0;
 }
 
 /*
@@ -451,7 +463,6 @@ nfsd4_probe_callback(struct nfs4_client *clp)
 
 /*
  * called with dp->dl_count inc'ed.
- * nfs4_lock_state() may or may not have been called.
  */
 void
 nfsd4_cb_recall(struct nfs4_delegation *dp)
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 9fa60a3ad48..b2883e9c638 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -93,6 +93,21 @@ do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_o
 	open->op_truncate = 0;
 
 	if (open->op_create) {
+		/* FIXME: check session persistence and pnfs flags.
+		 * The nfsv4.1 spec requires the following semantics:
+		 *
+		 * Persistent   | pNFS   | Server REQUIRED | Client Allowed
+		 * Reply Cache  | server |                 |
+		 * -------------+--------+-----------------+--------------------
+		 * no           | no     | EXCLUSIVE4_1    | EXCLUSIVE4_1
+		 *              |        |                 | (SHOULD)
+		 *              |        | and EXCLUSIVE4  | or EXCLUSIVE4
+		 *              |        |                 | (SHOULD NOT)
+		 * no           | yes    | EXCLUSIVE4_1    | EXCLUSIVE4_1
+		 * yes          | no     | GUARDED4        | GUARDED4
+		 * yes          | yes    | GUARDED4        | GUARDED4
+		 */
+
 		/*
 		 * Note: create modes (UNCHECKED,GUARDED...) are the same
 		 * in NFSv4 as in v3.
@@ -103,11 +118,13 @@ do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_o
 					(u32 *)open->op_verf.data,
 					&open->op_truncate, &created);
 
-		/* If we ever decide to use different attrs to store the
-		 * verifier in nfsd_create_v3, then we'll need to change this
+		/*
+		 * Following rfc 3530 14.2.16, use the returned bitmask
+		 * to indicate which attributes we used to store the
+		 * verifier:
 		 */
 		if (open->op_createmode == NFS4_CREATE_EXCLUSIVE && status == 0)
-			open->op_bmval[1] |= (FATTR4_WORD1_TIME_ACCESS |
+			open->op_bmval[1] = (FATTR4_WORD1_TIME_ACCESS |
 						FATTR4_WORD1_TIME_MODIFY);
 	} else {
 		status = nfsd_lookup(rqstp, current_fh,
@@ -118,13 +135,11 @@ do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_o
 		goto out;
 
 	set_change_info(&open->op_cinfo, current_fh);
-
-	/* set reply cache */
 	fh_dup2(current_fh, &resfh);
-	open->op_stateowner->so_replay.rp_openfh_len = resfh.fh_handle.fh_size;
-	memcpy(open->op_stateowner->so_replay.rp_openfh,
-			&resfh.fh_handle.fh_base, resfh.fh_handle.fh_size);
 
+	/* set reply cache */
+	fh_copy_shallow(&open->op_stateowner->so_replay.rp_openfh,
+			&resfh.fh_handle);
 	if (!created)
 		status = do_open_permission(rqstp, current_fh, open,
 					    NFSD_MAY_NOP);
@@ -150,10 +165,8 @@ do_open_fhandle(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_
 	memset(&open->op_cinfo, 0, sizeof(struct nfsd4_change_info));
 
 	/* set replay cache */
-	open->op_stateowner->so_replay.rp_openfh_len = current_fh->fh_handle.fh_size;
-	memcpy(open->op_stateowner->so_replay.rp_openfh,
-		&current_fh->fh_handle.fh_base,
-		current_fh->fh_handle.fh_size);
+	fh_copy_shallow(&open->op_stateowner->so_replay.rp_openfh,
+			&current_fh->fh_handle);
 
 	open->op_truncate = (open->op_iattr.ia_valid & ATTR_SIZE) &&
 		(open->op_iattr.ia_size == 0);
@@ -164,12 +177,23 @@ do_open_fhandle(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_
 	return status;
 }
 
+static void
+copy_clientid(clientid_t *clid, struct nfsd4_session *session)
+{
+	struct nfsd4_sessionid *sid =
+			(struct nfsd4_sessionid *)session->se_sessionid.data;
+
+	clid->cl_boot = sid->clientid.cl_boot;
+	clid->cl_id = sid->clientid.cl_id;
+}
 
 static __be32
 nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	   struct nfsd4_open *open)
 {
 	__be32 status;
+	struct nfsd4_compoundres *resp;
+
 	dprintk("NFSD: nfsd4_open filename %.*s op_stateowner %p\n",
 		(int)open->op_fname.len, open->op_fname.data,
 		open->op_stateowner);
@@ -178,16 +202,19 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (open->op_create && open->op_claim_type != NFS4_OPEN_CLAIM_NULL)
 		return nfserr_inval;
 
+	if (nfsd4_has_session(cstate))
+		copy_clientid(&open->op_clientid, cstate->session);
+
 	nfs4_lock_state();
 
 	/* check seqid for replay. set nfs4_owner */
-	status = nfsd4_process_open1(open);
+	resp = rqstp->rq_resp;
+	status = nfsd4_process_open1(&resp->cstate, open);
 	if (status == nfserr_replay_me) {
 		struct nfs4_replay *rp = &open->op_stateowner->so_replay;
 		fh_put(&cstate->current_fh);
-		cstate->current_fh.fh_handle.fh_size = rp->rp_openfh_len;
-		memcpy(&cstate->current_fh.fh_handle.fh_base, rp->rp_openfh,
-				rp->rp_openfh_len);
+		fh_copy_shallow(&cstate->current_fh.fh_handle,
+				&rp->rp_openfh);
 		status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
 		if (status)
 			dprintk("nfsd4_open: replay failed"
@@ -209,10 +236,6 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	switch (open->op_claim_type) {
 		case NFS4_OPEN_CLAIM_DELEGATE_CUR:
-			status = nfserr_inval;
-			if (open->op_create)
-				goto out;
-			/* fall through */
 		case NFS4_OPEN_CLAIM_NULL:
 			/*
 			 * (1) set CURRENT_FH to the file being opened,
@@ -455,8 +478,9 @@ nfsd4_getattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (getattr->ga_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1)
 		return nfserr_inval;
 
-	getattr->ga_bmval[0] &= NFSD_SUPPORTED_ATTRS_WORD0;
-	getattr->ga_bmval[1] &= NFSD_SUPPORTED_ATTRS_WORD1;
+	getattr->ga_bmval[0] &= nfsd_suppattrs0(cstate->minorversion);
+	getattr->ga_bmval[1] &= nfsd_suppattrs1(cstate->minorversion);
+	getattr->ga_bmval[2] &= nfsd_suppattrs2(cstate->minorversion);
 
 	getattr->ga_fhp = &cstate->current_fh;
 	return nfs_ok;
@@ -520,9 +544,8 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	nfs4_lock_state();
 	/* check stateid */
-	if ((status = nfs4_preprocess_stateid_op(&cstate->current_fh,
-				&read->rd_stateid,
-				CHECK_FH | RD_STATE, &read->rd_filp))) {
+	if ((status = nfs4_preprocess_stateid_op(cstate, &read->rd_stateid,
+						 RD_STATE, &read->rd_filp))) {
 		dprintk("NFSD: nfsd4_read: couldn't process stateid!\n");
 		goto out;
 	}
@@ -548,8 +571,9 @@ nfsd4_readdir(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (readdir->rd_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1)
 		return nfserr_inval;
 
-	readdir->rd_bmval[0] &= NFSD_SUPPORTED_ATTRS_WORD0;
-	readdir->rd_bmval[1] &= NFSD_SUPPORTED_ATTRS_WORD1;
+	readdir->rd_bmval[0] &= nfsd_suppattrs0(cstate->minorversion);
+	readdir->rd_bmval[1] &= nfsd_suppattrs1(cstate->minorversion);
+	readdir->rd_bmval[2] &= nfsd_suppattrs2(cstate->minorversion);
 
 	if ((cookie > ~(u32)0) || (cookie == 1) || (cookie == 2) ||
 	    (cookie == 0 && memcmp(readdir->rd_verf.data, zeroverf.data, NFS4_VERIFIER_SIZE)))
@@ -653,8 +677,8 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	if (setattr->sa_iattr.ia_valid & ATTR_SIZE) {
 		nfs4_lock_state();
-		status = nfs4_preprocess_stateid_op(&cstate->current_fh,
-			&setattr->sa_stateid, CHECK_FH | WR_STATE, NULL);
+		status = nfs4_preprocess_stateid_op(cstate,
+			&setattr->sa_stateid, W