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
  ...

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

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.
+

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 */

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

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;

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)

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, WR_STATE, NULL);
 		nfs4_unlock_state();
 		if (status) {
 			dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n");
@@ -685,6 +709,7 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	struct file *filp = NULL;
 	u32 *p;
 	__be32 status = nfs_ok;
+	unsigned long cnt;
 
 	/* no need to check permission - this will be done in nfsd_write() */
 
@@ -692,8 +717,7 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		return nfserr_inval;
 
 	nfs4_lock_state();
-	status = nfs4_preprocess_stateid_op(&cstate->current_fh, stateid,
-					CHECK_FH | WR_STATE, &filp);
+	status = nfs4_preprocess_stateid_op(cstate, stateid, WR_STATE, &filp);
 	if (filp)
 		get_file(filp);
 	nfs4_unlock_state();
@@ -703,7 +727,7 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		return status;
 	}
 
-	write->wr_bytes_written = write->wr_buflen;
+	cnt = write->wr_buflen;
 	write->wr_how_written = write->wr_stable_how;
 	p = (u32 *)write->wr_verifier.data;
 	*p++ = nfssvc_boot.tv_sec;
@@ -711,10 +735,12 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	status =  nfsd_write(rqstp, &cstate->current_fh, filp,
 			     write->wr_offset, rqstp->rq_vec, write->wr_vlen,
-			     write->wr_buflen, &write->wr_how_written);
+			     &cnt, &write->wr_how_written);
 	if (filp)
 		fput(filp);
 
+	write->wr_bytes_written = cnt;
+
 	if (status == nfserr_symlink)
 		status = nfserr_inval;
 	return status;
@@ -737,8 +763,9 @@ _nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (status)
 		return status;
 
-	if ((verify->ve_bmval[0] & ~NFSD_SUPPORTED_ATTRS_WORD0)
-	    || (verify->ve_bmval[1] & ~NFSD_SUPPORTED_ATTRS_WORD1))
+	if ((verify->ve_bmval[0] & ~nfsd_suppattrs0(cstate->minorversion))
+	    || (verify->ve_bmval[1] & ~nfsd_suppattrs1(cstate->minorversion))
+	    || (verify->ve_bmval[2] & ~nfsd_suppattrs2(cstate->minorversion)))
 		return nfserr_attrnotsupp;
 	if ((verify->ve_bmval[0] & FATTR4_WORD0_RDATTR_ERROR)
 	    || (verify->ve_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1))
@@ -766,7 +793,8 @@ _nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (status)
 		goto out_kfree;
 
-	p = buf + 3;
+	/* skip bitmap */
+	p = buf + 1 + ntohl(buf[0]);
 	status = nfserr_not_same;
 	if (ntohl(*p++) != verify->ve_attrlen)
 		goto out_kfree;
@@ -813,39 +841,17 @@ static inline void nfsd4_increment_op_stats(u32 opnum)
 		nfsdstats.nfs4_opcount[opnum]++;
 }
 
-static void cstate_free(struct nfsd4_compound_state *cstate)
-{
-	if (cstate == NULL)
-		return;
-	fh_put(&cstate->current_fh);
-	fh_put(&cstate->save_fh);
-	BUG_ON(cstate->replay_owner);
-	kfree(cstate);
-}
-
-static struct nfsd4_compound_state *cstate_alloc(void)
-{
-	struct nfsd4_compound_state *cstate;
-
-	cstate = kmalloc(sizeof(struct nfsd4_compound_state), GFP_KERNEL);
-	if (cstate == NULL)
-		return NULL;
-	fh_init(&cstate->current_fh, NFS4_FHSIZE);
-	fh_init(&cstate->save_fh, NFS4_FHSIZE);
-	cstate->replay_owner = NULL;
-	return cstate;
-}
-
 typedef __be32(*nfsd4op_func)(struct svc_rqst *, struct nfsd4_compound_state *,
 			      void *);
+enum nfsd4_op_flags {
+	ALLOWED_WITHOUT_FH = 1 << 0,	/* No current filehandle required */
+	ALLOWED_ON_ABSENT_FS = 2 << 0,	/* ops processed on absent fs */
+	ALLOWED_AS_FIRST_OP = 3 << 0,	/* ops reqired first in compound */
+};
 
 struct nfsd4_operation {
 	nfsd4op_func op_func;
 	u32 op_flags;
-/* Most ops require a valid current filehandle; a few don't: */
-#define ALLOWED_WITHOUT_FH 1
-/* GETATTR and ops not listed as returning NFS4ERR_MOVED: */
-#define ALLOWED_ON_ABSENT_FS 2
 	char *op_name;
 };
 
@@ -853,6 +859,51 @@ static struct nfsd4_operation nfsd4_ops[];
 
 static const char *nfsd4_op_name(unsigned opnum);
 
+/*
+ * This is a replay of a compound for which no cache entry pages
+ * were used. Encode the sequence operation, and if cachethis is FALSE
+ * encode the uncache rep error on the next operation.
+ */
+static __be32
+nfsd4_enc_uncached_replay(struct nfsd4_compoundargs *args,
+			 struct nfsd4_compoundres *resp)
+{
+	struct nfsd4_op *op;
+
+	dprintk("--> %s resp->opcnt %d ce_cachethis %u \n", __func__,
+		resp->opcnt, resp->cstate.slot->sl_cache_entry.ce_cachethis);
+
+	/* Encode the replayed sequence operation */
+	BUG_ON(resp->opcnt != 1);
+	op = &args->ops[resp->opcnt - 1];
+	nfsd4_encode_operation(resp, op);
+
+	/*return nfserr_retry_uncached_rep in next operation. */
+	if (resp->cstate.slot->sl_cache_entry.ce_cachethis == 0) {
+		op = &args->ops[resp->opcnt++];
+		op->status = nfserr_retry_uncached_rep;
+		nfsd4_encode_operation(resp, op);
+	}
+	return op->status;
+}
+
+/*
+ * Enforce NFSv4.1 COMPOUND ordering rules.
+ *
+ * TODO:
+ * - enforce NFS4ERR_NOT_ONLY_OP,
+ * - DESTROY_SESSION MUST be the final operation in the COMPOUND request.
+ */
+static bool nfs41_op_ordering_ok(struct nfsd4_compoundargs *args)
+{
+	if (args->minorversion && args->opcnt > 0) {
+		struct nfsd4_op *op = &args->ops[0];
+		return (op->status == nfserr_op_illegal) ||
+		       (nfsd4_ops[op->opnum].op_flags & ALLOWED_AS_FIRST_OP);
+	}
+	return true;
+}
+
 /*
  * COMPOUND call.
  */
@@ -863,12 +914,13 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 {
 	struct nfsd4_op	*op;
 	struct nfsd4_operation *opdesc;
-	struct nfsd4_compound_state *cstate = NULL;
+	struct nfsd4_compound_state *cstate = &resp->cstate;
 	int		slack_bytes;
 	__be32		status;
 
 	resp->xbuf = &rqstp->rq_res;
-	resp->p = rqstp->rq_res.head[0].iov_base + rqstp->rq_res.head[0].iov_len;
+	resp->p = rqstp->rq_res.head[0].iov_base +
+						rqstp->rq_res.head[0].iov_len;
 	resp->tagp = resp->p;
 	/* reserve space for: taglen, tag, and opcnt */
 	resp->p += 2 + XDR_QUADLEN(args->taglen);
@@ -877,18 +929,25 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 	resp->tag = args->tag;
 	resp->opcnt = 0;
 	resp->rqstp = rqstp;
+	resp->cstate.minorversion = args->minorversion;
+	resp->cstate.replay_owner = NULL;
+	fh_init(&resp->cstate.current_fh, NFS4_FHSIZE);
+	fh_init(&resp->cstate.save_fh, NFS4_FHSIZE);
+	/* Use the deferral mechanism only for NFSv4.0 compounds */
+	rqstp->rq_usedeferral = (args->minorversion == 0);
 
 	/*
 	 * According to RFC3010, this takes precedence over all other errors.
 	 */
 	status = nfserr_minor_vers_mismatch;
-	if (args->minorversion > NFSD_SUPPORTED_MINOR_VERSION)
+	if (args->minorversion > nfsd_supported_minorversion)
 		goto out;
 
-	status = nfserr_resource;
-	cstate = cstate_alloc();
-	if (cstate == NULL)
-		goto out;
+	if (!nfs41_op_ordering_ok(args)) {
+		op = &args->ops[0];
+		op->status = nfserr_sequence_pos;
+		goto encode_op;
+	}
 
 	status = nfs_ok;
 	while (!status && resp->opcnt < args->opcnt) {
@@ -897,7 +956,6 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 		dprintk("nfsv4 compound op #%d/%d: %d (%s)\n",
 			resp->opcnt, args->opcnt, op->opnum,
 			nfsd4_op_name(op->opnum));
-
 		/*
 		 * The XDR decode routines may have pre-set op->status;
 		 * for example, if there is a miscellaneous XDR error
@@ -938,6 +996,15 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 			BUG_ON(op->status == nfs_ok);
 
 encode_op:
+		/* Only from SEQUENCE or CREATE_SESSION */
+		if (resp->cstate.status == nfserr_replay_cache) {
+			dprintk("%s NFS4.1 replay from cache\n", __func__);
+			if (nfsd4_not_cached(resp))
+				status = nfsd4_enc_uncached_replay(args, resp);
+			else
+				status = op->status;
+			goto out;
+		}
 		if (op->status == nfserr_replay_me) {
 			op->replay = &cstate->replay_owner->so_replay;
 			nfsd4_encode_replay(resp, op);
@@ -961,15 +1028,24 @@ 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;
+	}
 
-	cstate_free(cstate);
+	resp->cstate.status = status;
+	fh_put(&resp->cstate.current_fh);
+	fh_put(&resp->cstate.save_fh);
+	BUG_ON(resp->cstate.replay_owner);
 out:
 	nfsd4_release_compoundargs(args);
+	/* Reset deferral mechanism for RPC deferrals */
+	rqstp->rq_usedeferral = 1;
 	dprintk("nfsv4 compound returned %d\n", ntohl(status));
 	return status;
 }
 
-static struct nfsd4_operation nfsd4_ops[OP_RELEASE_LOCKOWNER+1] = {
+static struct nfsd4_operation nfsd4_ops[] = {
 	[OP_ACCESS] = {
 		.op_func = (nfsd4op_func)nfsd4_access,
 		.op_name = "OP_ACCESS",
@@ -1045,7 +1121,7 @@ static struct nfsd4_operation nfsd4_ops[OP_RELEASE_LOCKOWNER+1] = {
 		.op_name = "OP_PUTFH",
 	},
 	[OP_PUTPUBFH] = {
-		/* unsupported, just for future reference: */
+		.op_func = (nfsd4op_func)nfsd4_putrootfh,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
 		.op_name = "OP_PUTPUBFH",
 	},
@@ -1119,6 +1195,28 @@ static struct nfsd4_operation nfsd4_ops[OP_RELEASE_LOCKOWNER+1] = {
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
 		.op_name = "OP_RELEASE_LOCKOWNER",
 	},
+
+	/* NFSv4.1 operations */
+	[OP_EXCHANGE_ID] = {
+		.op_func = (nfsd4op_func)nfsd4_exchange_id,
+		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP,
+		.op_name = "OP_EXCHANGE_ID",
+	},
+	[OP_CREATE_SESSION] = {
+		.op_func = (nfsd4op_func)nfsd4_create_session,
+		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP,
+		.op_name = "OP_CREATE_SESSION",
+	},
+	[OP_DESTROY_SESSION] = {
+		.op_func = (nfsd4op_func)nfsd4_destroy_session,
+		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP,
+		.op_name = "OP_DESTROY_SESSION",
+	},
+	[OP_SEQUENCE] = {
+		.op_func = (nfsd4op_func)nfsd4_sequence,
+		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP,
+		.op_name = "OP_SEQUENCE",
+	},
 };
 
 static const char *nfsd4_op_name(unsigned opnum)

fs/nfsd/nfs4recover.c

@@ -182,36 +182,26 @@ out_unlock:
 
 typedef int (recdir_func)(struct dentry *, struct dentry *);
 
-struct dentry_list {
-	struct dentry *dentry;
+struct name_list {
+	char name[HEXDIR_LEN];
 	struct list_head list;
 };
 
-struct dentry_list_arg {
-	struct list_head dentries;
-	struct dentry *parent;
-};
-
 static int
-nfsd4_build_dentrylist(void *arg, const char *name, int namlen,
+nfsd4_build_namelist(void *arg, const char *name, int namlen,
 		loff_t offset, u64 ino, unsigned int d_type)
 {
-	struct dentry_list_arg *dla = arg;
-	struct list_head *dentries = &dla->dentries;
-	struct dentry *parent = dla->parent;
-	struct dentry *dentry;
-	struct dentry_list *child;
+	struct list_head *names = arg;
+	struct name_list *entry;
 
-	if (name && isdotent(name, namlen))
+	if (namlen != HEXDIR_LEN - 1)
 		return 0;
-	dentry = lookup_one_len(name, parent, namlen);
-	if (IS_ERR(dentry))
-		return PTR_ERR(dentry);
-	child = kmalloc(sizeof(*child), GFP_KERNEL);
-	if (child == NULL)
+	entry = kmalloc(sizeof(struct name_list), GFP_KERNEL);
+	if (entry == NULL)
 		return -ENOMEM;
-	child->dentry = dentry;
-	list_add(&child->list, dentries);
+	memcpy(entry->name, name, HEXDIR_LEN - 1);
+	entry->name[HEXDIR_LEN - 1] = '\0';
+	list_add(&entry->list, names);
 	return 0;
 }
 
@@ -220,11 +210,9 @@ nfsd4_list_rec_dir(struct dentry *dir, recdir_func *f)
 {
 	const struct cred *original_cred;
 	struct file *filp;
-	struct dentry_list_arg dla = {
-		.parent = dir,
-	};
-	struct list_head *dentries = &dla.dentries;
-	struct dentry_list *child;
+	LIST_HEAD(names);
+	struct name_list *entry;
+	struct dentry *dentry;
 	int status;
 
 	if (!rec_dir_init)
@@ -233,31 +221,34 @@ nfsd4_list_rec_dir(struct dentry *dir, recdir_func *f)
 	status = nfs4_save_creds(&original_cred);
 	if (status < 0)
 		return status;
-	INIT_LIST_HEAD(dentries);
 
 	filp = dentry_open(dget(dir), mntget(rec_dir.mnt), O_RDONLY,
 			   current_cred());
 	status = PTR_ERR(filp);
 	if (IS_ERR(filp))
 		goto out;
-	INIT_LIST_HEAD(dentries);
-	status = vfs_readdir(filp, nfsd4_build_dentrylist, &dla);
+	status = vfs_readdir(filp, nfsd4_build_namelist, &names);
 	fput(filp);
-	while (!list_empty(dentries)) {
-		child = list_entry(dentries->next, struct dentry_list, list);
-		status = f(dir, child->dentry);
+	while (!list_empty(&names)) {
+		entry = list_entry(names.next, struct name_list, list);
+
+		dentry = lookup_one_len(entry->name, dir, HEXDIR_LEN-1);
+		if (IS_ERR(dentry)) {
+			status = PTR_ERR(dentry);
+			goto out;
+		}
+		status = f(dir, dentry);
+		dput(dentry);
 		if (status)
 			goto out;
-		list_del(&child->list);
-		dput(child->dentry);
-		kfree(child);
+		list_del(&entry->list);
+		kfree(entry);
 	}
 out:
-	while (!list_empty(dentries)) {
-		child = list_entry(dentries->next, struct dentry_list, list);
-		list_del(&child->list);
-		dput(child->dentry);
-		kfree(child);
+	while (!list_empty(&names)) {
+		entry = list_entry(names.next, struct name_list, list);
+		list_del(&entry->list);
+		kfree(entry);
 	}
 	nfs4_reset_creds(original_cred);
 	return status;
@@ -353,7 +344,8 @@ purge_old(struct dentry *parent, struct dentry *child)
 {
 	int status;
 
-	if (nfs4_has_reclaimed_state(child->d_name.name))
+	/* note: we currently use this path only for minorversion 0 */
+	if (nfs4_has_reclaimed_state(child->d_name.name, false))
 		return 0;
 
 	status = nfsd4_clear_clid_dir(parent, child);

fs/nfsd/nfs4xdr.c

@@ -45,6 +45,7 @@
 #include <linux/fs.h>
 #include <linux/namei.h>
 #include <linux/vfs.h>
+#include <linux/utsname.h>
 #include <linux/sunrpc/xdr.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/clnt.h>
@@ -188,6 +189,11 @@ static __be32 *read_buf(struct nfsd4_compoundargs *argp, u32 nbytes)
 	return p;
 }
 
+static int zero_clientid(clientid_t *clid)
+{
+	return (clid->cl_boot == 0) && (clid->cl_id == 0);
+}
+
 static int
 defer_free(struct nfsd4_compoundargs *argp,
 		void (*release)(const void *), void *p)
@@ -230,6 +236,7 @@ nfsd4_decode_bitmap(struct nfsd4_compoundargs *argp, u32 *bmval)
 
 	bmval[0] = 0;
 	bmval[1] = 0;
+	bmval[2] = 0;
 
 	READ_BUF(4);
 	READ32(bmlen);
@@ -241,13 +248,27 @@ nfsd4_decode_bitmap(struct nfsd4_compoundargs *argp, u32 *bmval)
 		READ32(bmval[0]);
 	if (bmlen > 1)
 		READ32(bmval[1]);
+	if (bmlen > 2)
+		READ32(bmval[2]);
 
 	DECODE_TAIL;
 }
 
+static u32 nfsd_attrmask[] = {
+	NFSD_WRITEABLE_ATTRS_WORD0,
+	NFSD_WRITEABLE_ATTRS_WORD1,
+	NFSD_WRITEABLE_ATTRS_WORD2
+};
+
+static u32 nfsd41_ex_attrmask[] = {
+	NFSD_SUPPATTR_EXCLCREAT_WORD0,
+	NFSD_SUPPATTR_EXCLCREAT_WORD1,
+	NFSD_SUPPATTR_EXCLCREAT_WORD2
+};
+
 static __be32
-nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, struct iattr *iattr,
-    struct nfs4_acl **acl)
+nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, u32 *writable,
+		   struct iattr *iattr, struct nfs4_acl **acl)
 {
 	int expected_len, len = 0;
 	u32 dummy32;
@@ -263,9 +284,12 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, struct iattr *ia
 	 * According to spec, unsupported attributes return ERR_ATTRNOTSUPP;
 	 * read-only attributes return ERR_INVAL.
 	 */
-	if ((bmval[0] & ~NFSD_SUPPORTED_ATTRS_WORD0) || (bmval[1] & ~NFSD_SUPPORTED_ATTRS_WORD1))
+	if ((bmval[0] & ~nfsd_suppattrs0(argp->minorversion)) ||
+	    (bmval[1] & ~nfsd_suppattrs1(argp->minorversion)) ||
+	    (bmval[2] & ~nfsd_suppattrs2(argp->minorversion)))
 		return nfserr_attrnotsupp;
-	if ((bmval[0] & ~NFSD_WRITEABLE_ATTRS_WORD0) || (bmval[1] & ~NFSD_WRITEABLE_ATTRS_WORD1))
+	if ((bmval[0] & ~writable[0]) || (bmval[1] & ~writable[1]) ||
+	    (bmval[2] & ~writable[2]))
 		return nfserr_inval;
 
 	READ_BUF(4);
@@ -400,6 +424,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, struct iattr *ia
 			goto xdr_error;
 		}
 	}
+	BUG_ON(bmval[2]);	/* no such writeable attr supported yet */
 	if (len != expected_len)
 		goto xdr_error;
 
@@ -493,7 +518,9 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create
 	if ((status = check_filename(create->cr_name, create->cr_namelen, nfserr_inval)))
 		return status;
 
-	if ((status = nfsd4_decode_fattr(argp, create->cr_bmval, &create->cr_iattr, &create->cr_acl)))
+	status = nfsd4_decode_fattr(argp, create->cr_bmval, nfsd_attrmask,
+				    &create->cr_iattr, &create->cr_acl);
+	if (status)
 		goto out;
 
 	DECODE_TAIL;
@@ -583,6 +610,8 @@ nfsd4_decode_lockt(struct nfsd4_compoundargs *argp, struct nfsd4_lockt *lockt)
 	READ_BUF(lockt->lt_owner.len);
 	READMEM(lockt->lt_owner.data, lockt->lt_owner.len);
 
+	if (argp->minorversion && !zero_clientid(&lockt->lt_clientid))
+		return nfserr_inval;
 	DECODE_TAIL;
 }
 
@@ -652,13 +681,26 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
 		switch (open->op_createmode) {
 		case NFS4_CREATE_UNCHECKED:
 		case NFS4_CREATE_GUARDED:
-			if ((status = nfsd4_decode_fattr(argp, open->op_bmval, &open->op_iattr, &open->op_acl)))
+			status = nfsd4_decode_fattr(argp, open->op_bmval,
+				nfsd_attrmask, &open->op_iattr, &open->op_acl);
+			if (status)
 				goto out;
 			break;
 		case NFS4_CREATE_EXCLUSIVE:
 			READ_BUF(8);
 			COPYMEM(open->op_verf.data, 8);
 			break;
+		case NFS4_CREATE_EXCLUSIVE4_1:
+			if (argp->minorversion < 1)
+				goto xdr_error;
+			READ_BUF(8);
+			COPYMEM(open->op_verf.data, 8);
+			status = nfsd4_decode_fattr(argp, open->op_bmval,
+				nfsd41_ex_attrmask, &open->op_iattr,
+				&open->op_acl);
+			if (status)
+				goto out;
+			break;
 		default:
 			goto xdr_error;
 		}
@@ -851,7 +893,7 @@ nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, struct nfsd4_setattr *seta
 	status = nfsd4_decode_stateid(argp, &setattr->sa_stateid);
 	if (status)
 		return status;
-	return nfsd4_decode_fattr(argp, setattr->sa_bmval,
+	return nfsd4_decode_fattr(argp, setattr->sa_bmval, nfsd_attrmask,
 				  &setattr->sa_iattr, &setattr->sa_acl);
 }
 
@@ -993,6 +1035,241 @@ nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, struct nfsd4_rel
 	READ_BUF(rlockowner->rl_owner.len);
 	READMEM(rlockowner->rl_owner.data, rlockowner->rl_owner.len);
 
+	if (argp->minorversion && !zero_clientid(&rlockowner->rl_clientid))
+		return nfserr_inval;
+	DECODE_TAIL;
+}
+
+static __be32
+nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp,
+			 struct nfsd4_exchange_id *exid)
+{
+	int dummy;
+	DECODE_HEAD;
+
+	READ_BUF(NFS4_VERIFIER_SIZE);
+	COPYMEM(exid->verifier.data, NFS4_VERIFIER_SIZE);
+
+	READ_BUF(4);
+	READ32(exid->clname.len);
+
+	READ_BUF(exid->clname.len);
+	SAVEMEM(exid->clname.data, exid->clname.len);
+
+	READ_BUF(4);
+	READ32(exid->flags);
+
+	/* Ignore state_protect4_a */
+	READ_BUF(4);
+	READ32(exid->spa_how);
+	switch (exid->spa_how) {
+	case SP4_NONE:
+		break;
+	case SP4_MACH_CRED:
+		/* spo_must_enforce */
+		READ_BUF(4);
+		READ32(dummy);
+		READ_BUF(dummy * 4);
+		p += dummy;
+
+		/* spo_must_allow */
+		READ_BUF(4);
+		READ32(dummy);
+		READ_BUF(dummy * 4);
+		p += dummy;
+		break;
+	case SP4_SSV:
+		/* ssp_ops */
+		READ_BUF(4);
+		READ32(dummy);
+		READ_BUF(dummy * 4);
+		p += dummy;
+
+		READ_BUF(4);
+		READ32(dummy);
+		READ_BUF(dummy * 4);
+		p += dummy;
+
+		/* ssp_hash_algs<> */
+		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);
+
+		/* ssp_window and ssp_num_gss_handles */
+		READ_BUF(8);
+		READ32(dummy);
+		READ32(dummy);
+		break;
+	default:
+		goto xdr_error;
+	}
+
+	/* Ignore Implementation ID */
+	READ_BUF(4);    /* nfs_impl_id4 array length */
+	READ32(dummy);
+
+	if (dummy > 1)
+		goto xdr_error;
+
+	if (dummy == 1) {
+		/* nii_domain */
+		READ_BUF(4);
+		READ32(dummy);
+		READ_BUF(dummy);
+		p += XDR_QUADLEN(dummy);
+
+		/* nii_name */
+		READ_BUF(4);
+		READ32(dummy);
+		READ_BUF(dummy);
+		p += XDR_QUADLEN(dummy);
+
+		/* nii_date */
+		READ_BUF(12);
+		p += 3;
+	}
+	DECODE_TAIL;
+}
+
+static __be32
+nfsd4_decode_create_session(struct nfsd4_compoundargs *argp,
+			    struct nfsd4_create_session *sess)
+{
+	DECODE_HEAD;
+
+	u32 dummy;
+	char *machine_name;
+	int i;
+	int nr_secflavs;
+
+	READ_BUF(16);
+	COPYMEM(&sess->clientid, 8);
+	READ32(sess->seqid);
+	READ32(sess->flags);
+
+	/* Fore channel attrs */
+	READ_BUF(28);
+	READ32(dummy); /* headerpadsz is always 0 */
+	READ32(sess->fore_channel.maxreq_sz);
+	READ32(sess->fore_channel.maxresp_sz);
+	READ32(sess->fore_channel.maxresp_cached);
+	READ32(sess->fore_channel.maxops);
+	READ32(sess->fore_channel.maxreqs);
+	READ32(sess->fore_channel.nr_rdma_attrs);
+	if (sess->fore_channel.nr_rdma_attrs == 1) {
+		READ_BUF(4);
+		READ32(sess->fore_channel.rdma_attrs);
+	} else if (sess->fore_channel.nr_rdma_attrs > 1) {
+		dprintk("Too many fore channel attr bitmaps!\n");
+		goto xdr_error;
+	}
+
+	/* Back channel attrs */
+	READ_BUF(28);
+	READ32(dummy); /* headerpadsz is always 0 */
+	READ32(sess->back_channel.maxreq_sz);
+	READ32(sess->back_channel.maxresp_sz);
+	READ32(sess->back_channel.maxresp_cached);
+	READ32(sess->back_channel.maxops);
+	READ32(sess->back_channel.maxreqs);
+	READ32(sess->back_channel.nr_rdma_attrs);
+	if (sess->back_channel.nr_rdma_attrs == 1) {
+		READ_BUF(4);
+		READ32(sess->back_channel.rdma_attrs);
+	} else if (sess->back_channel.nr_rdma_attrs > 1) {
+		dprintk("Too many back channel attr bitmaps!\n");
+		goto xdr_error;
+	}
+
+	READ_BUF(8);
+	READ32(sess->callback_prog);
+
+	/* callback_sec_params4 */
+	READ32(nr_secflavs);
+	for (i = 0; i < nr_secflavs; ++i) {
+		READ_BUF(4);
+		READ32(dummy);
+		switch (dummy) {
+		case RPC_AUTH_NULL:
+			/* Nothing to read */
+			break;
+		case RPC_AUTH_UNIX:
+			READ_BUF(8);
+			/* stamp */
+			READ32(dummy);
+
+			/* machine name */
+			READ32(dummy);
+			READ_BUF(dummy);
+			SAVEMEM(machine_name, dummy);
+
+			/* uid, gid */
+			READ_BUF(8);
+			READ32(sess->uid);
+			READ32(sess->gid);
+
+			/* more gids */
+			READ_BUF(4);
+			READ32(dummy);
+			READ_BUF(dummy * 4);
+			for (i = 0; i < dummy; ++i)
+				READ32(dummy);
+			break;
+		case RPC_AUTH_GSS:
+			dprintk("RPC_AUTH_GSS callback secflavor "
+				"not supported!\n");
+			READ_BUF(8);
+			/* gcbp_service */
+			READ32(dummy);
+			/* gcbp_handle_from_server */
+			READ32(dummy);
+			READ_BUF(dummy);
+			p += XDR_QUADLEN(dummy);
+			/* gcbp_handle_from_client */
+			READ_BUF(4);
+			READ32(dummy);
+			READ_BUF(dummy);
+			p += XDR_QUADLEN(dummy);
+			break;
+		default:
+			dprintk("Illegal callback secflavor\n");
+			return nfserr_inval;
+		}
+	}
+	DECODE_TAIL;
+}
+
+static __be32
+nfsd4_decode_destroy_session(struct nfsd4_compoundargs *argp,
+			     struct nfsd4_destroy_session *destroy_session)
+{
+	DECODE_HEAD;
+	READ_BUF(NFS4_MAX_SESSIONID_LEN);
+	COPYMEM(destroy_session->sessionid.data, NFS4_MAX_SESSIONID_LEN);
+
+	DECODE_TAIL;
+}
+
+static __be32
+nfsd4_decode_sequence(struct nfsd4_compoundargs *argp,
+		      struct nfsd4_sequence *seq)
+{
+	DECODE_HEAD;
+
+	READ_BUF(NFS4_MAX_SESSIONID_LEN + 16);
+	COPYMEM(seq->sessionid.data, NFS4_MAX_SESSIONID_LEN);
+	READ32(seq->seqid);
+	READ32(seq->slotid);
+	READ32(seq->maxslots);
+	READ32(seq->cachethis);
+
 	DECODE_TAIL;
 }
 
@@ -1005,7 +1282,7 @@ nfsd4_decode_noop(struct nfsd4_compoundargs *argp, void *p)
 static __be32
 nfsd4_decode_notsupp(struct nfsd4_compoundargs *argp, void *p)
 {
-	return nfserr_opnotsupp;
+	return nfserr_notsupp;
 }
 
 typedef __be32(*nfsd4_dec)(struct nfsd4_compoundargs *argp, void *);
@@ -1031,7 +1308,7 @@ static nfsd4_dec nfsd4_dec_ops[] = {
 	[OP_OPEN_CONFIRM]	= (nfsd4_dec)nfsd4_decode_open_confirm,
 	[OP_OPEN_DOWNGRADE]	= (nfsd4_dec)nfsd4_decode_open_downgrade,
 	[OP_PUTFH]		= (nfsd4_dec)nfsd4_decode_putfh,
-	[OP_PUTPUBFH]		= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_PUTPUBFH]		= (nfsd4_dec)nfsd4_decode_noop,
 	[OP_PUTROOTFH]		= (nfsd4_dec)nfsd4_decode_noop,
 	[OP_READ]		= (nfsd4_dec)nfsd4_decode_read,
 	[OP_READDIR]		= (nfsd4_dec)nfsd4_decode_readdir,
@@ -1050,6 +1327,67 @@ static nfsd4_dec nfsd4_dec_ops[] = {
 	[OP_RELEASE_LOCKOWNER]	= (nfsd4_dec)nfsd4_decode_release_lockowner,
 };
 
+static nfsd4_dec nfsd41_dec_ops[] = {
+	[OP_ACCESS]		(nfsd4_dec)nfsd4_decode_access,
+	[OP_CLOSE]		(nfsd4_dec)nfsd4_decode_close,
+	[OP_COMMIT]		(nfsd4_dec)nfsd4_decode_commit,
+	[OP_CREATE]		(nfsd4_dec)nfsd4_decode_create,
+	[OP_DELEGPURGE]		(nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_DELEGRETURN]	(nfsd4_dec)nfsd4_decode_delegreturn,
+	[OP_GETATTR]		(nfsd4_dec)nfsd4_decode_getattr,
+	[OP_GETFH]		(nfsd4_dec)nfsd4_decode_noop,
+	[OP_LINK]		(nfsd4_dec)nfsd4_decode_link,
+	[OP_LOCK]		(nfsd4_dec)nfsd4_decode_lock,
+	[OP_LOCKT]		(nfsd4_dec)nfsd4_decode_lockt,
+	[OP_LOCKU]		(nfsd4_dec)nfsd4_decode_locku,
+	[OP_LOOKUP]		(nfsd4_dec)nfsd4_decode_lookup,
+	[OP_LOOKUPP]		(nfsd4_dec)nfsd4_decode_noop,
+	[OP_NVERIFY]		(nfsd4_dec)nfsd4_decode_verify,
+	[OP_OPEN]		(nfsd4_dec)nfsd4_decode_open,
+	[OP_OPENATTR]		(nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_OPEN_CONFIRM]	(nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_OPEN_DOWNGRADE]	(nfsd4_dec)nfsd4_decode_open_downgrade,
+	[OP_PUTFH]		(nfsd4_dec)nfsd4_decode_putfh,
+	[OP_PUTPUBFH]		(nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_PUTROOTFH]		(nfsd4_dec)nfsd4_decode_noop,
+	[OP_READ]		(nfsd4_dec)nfsd4_decode_read,
+	[OP_READDIR]		(nfsd4_dec)nfsd4_decode_readdir,
+	[OP_READLINK]		(nfsd4_dec)nfsd4_decode_noop,
+	[OP_REMOVE]		(nfsd4_dec)nfsd4_decode_remove,
+	[OP_RENAME]		(nfsd4_dec)nfsd4_decode_rename,
+	[OP_RENEW]		(nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_RESTOREFH]		(nfsd4_dec)nfsd4_decode_noop,
+	[OP_SAVEFH]		(nfsd4_dec)nfsd4_decode_noop,
+	[OP_SECINFO]		(nfsd4_dec)nfsd4_decode_secinfo,
+	[OP_SETATTR]		(nfsd4_dec)nfsd4_decode_setattr,
+	[OP_SETCLIENTID]	(nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_SETCLIENTID_CONFIRM](nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_VERIFY]		(nfsd4_dec)nfsd4_decode_verify,
+	[OP_WRITE]		(nfsd4_dec)nfsd4_decode_write,
+	[OP_RELEASE_LOCKOWNER]	(nfsd4_dec)nfsd4_decode_notsupp,
+
+	/* new operations for NFSv4.1 */
+	[OP_BACKCHANNEL_CTL]	(nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_BIND_CONN_TO_SESSION](nfsd4_dec)nfsd4_decode_notsupp,
+	[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,
+	[OP_FREE_STATEID]	(nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_GET_DIR_DELEGATION]	(nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_GETDEVICEINFO]	(nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_GETDEVICELIST]	(nfsd4_dec)nfsd4_decode_notsupp,
+	[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_SEQUENCE]		(nfsd4_dec)nfsd4_decode_sequence,
+	[OP_SET_SSV]		(nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_TEST_STATEID]	(nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_WANT_DELEGATION]	(nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_DESTROY_CLIENTID]	(nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_RECLAIM_COMPLETE]	(nfsd4_dec)nfsd4_decode_notsupp,
+};
+
 struct nfsd4_minorversion_ops {
 	nfsd4_dec *decoders;
 	int nops;
@@ -1057,6 +1395,7 @@ struct nfsd4_minorversion_ops {
 
 static struct nfsd4_minorversion_ops nfsd4_minorversion[] = {
 	[0] = { nfsd4_dec_ops, ARRAY_SIZE(nfsd4_dec_ops) },
+	[1] = { nfsd41_dec_ops, ARRAY_SIZE(nfsd41_dec_ops) },
 };
 
 static __be32
@@ -1412,6 +1751,7 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
 {
 	u32 bmval0 = bmval[0];
 	u32 bmval1 = bmval[1];
+	u32 bmval2 = bmval[2];
 	struct kstat stat;
 	struct svc_fh tempfh;
 	struct kstatfs statfs;
@@ -1425,12 +1765,16 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
 	int err;
 	int aclsupport = 0;
 	struct nfs4_acl *acl = NULL;
+	struct nfsd4_compoundres *resp = rqstp->rq_resp;
+	u32 minorversion = resp->cstate.minorversion;
 
 	BUG_ON(bmval1 & NFSD_WRITEONLY_ATTRS_WORD1);
-	BUG_ON(bmval0 & ~NFSD_SUPPORTED_ATTRS_WORD0);
-	BUG_ON(bmval1 & ~NFSD_SUPPORTED_ATTRS_WORD1);
+	BUG_ON(bmval0 & ~nfsd_suppattrs0(minorversion));
+	BUG_ON(bmval1 & ~nfsd_suppattrs1(minorversion));
+	BUG_ON(bmval2 & ~nfsd_suppattrs2(minorversion));
 
 	if (exp->ex_fslocs.migrated) {
+		BUG_ON(bmval[2]);
 		status = fattr_handle_absent_fs(&bmval0, &bmval1, &rdattr_err);
 		if (status)
 			goto out;
@@ -1476,22 +1820,42 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
 	if ((buflen -= 16) < 0)
 		goto out_resource;
 
-	WRITE32(2);
-	WRITE32(bmval0);
-	WRITE32(bmval1);
+	if (unlikely(bmval2)) {
+		WRITE32(3);
+		WRITE32(bmval0);
+		WRITE32(bmval1);
+		WRITE32(bmval2);
+	} else if (likely(bmval1)) {
+		WRITE32(2);
+		WRITE32(bmval0);
+		WRITE32(bmval1);
+	} else {
+		WRITE32(1);
+		WRITE32(bmval0);
+	}
 	attrlenp = p++;                /* to be backfilled later */
 
 	if (bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) {
-		u32 word0 = NFSD_SUPPORTED_ATTRS_WORD0;
+		u32 word0 = nfsd_suppattrs0(minorversion);
+		u32 word1 = nfsd_suppattrs1(minorversion);
+		u32 word2 = nfsd_suppattrs2(minorversion);
+
 		if ((buflen -= 12) < 0)
 			goto out_resource;
 		if (!aclsupport)
 			word0 &= ~FATTR4_WORD0_ACL;
 		if (!exp->ex_fslocs.locations)
 			word0 &= ~FATTR4_WORD0_FS_LOCATIONS;
-		WRITE32(2);
-		WRITE32(word0);
-		WRITE32(NFSD_SUPPORTED_ATTRS_WORD1);
+		if (!word2) {
+			WRITE32(2);
+			WRITE32(word0);
+			WRITE32(word1);
+		} else {
+			WRITE32(3);
+			WRITE32(word0);
+			WRITE32(word1);
+			WRITE32(word2);
+		}
 	}
 	if (bmval0 & FATTR4_WORD0_TYPE) {
 		if ((buflen -= 4) < 0)
@@ -1801,6 +2165,13 @@ out_acl:
 		}
 		WRITE64(stat.ino);
 	}
+	if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) {
+		WRITE32(3);
+		WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD0);
+		WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD1);
+		WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD2);
+	}
+
 	*attrlenp = htonl((char *)p - (char *)attrlenp - 4);
 	*countp = p - buffer;
 	status = nfs_ok;
@@ -2571,6 +2942,143 @@ nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_w
 	return nfserr;
 }
 
+static __be32
+nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, int nfserr,
+			 struct nfsd4_exchange_id *exid)
+{
+	ENCODE_HEAD;
+	char *major_id;
+	char *server_scope;
+	int major_id_sz;
+	int server_scope_sz;
+	uint64_t minor_id = 0;
+
+	if (nfserr)
+		return nfserr;
+
+	major_id = utsname()->nodename;
+	major_id_sz = strlen(major_id);
+	server_scope = utsname()->nodename;
+	server_scope_sz = strlen(server_scope);
+
+	RESERVE_SPACE(
+		8 /* eir_clientid */ +
+		4 /* eir_sequenceid */ +
+		4 /* eir_flags */ +
+		4 /* spr_how (SP4_NONE) */ +
+		8 /* so_minor_id */ +
+		4 /* so_major_id.len */ +
+		(XDR_QUADLEN(major_id_sz) * 4) +
+		4 /* eir_server_scope.len */ +
+		(XDR_QUADLEN(server_scope_sz) * 4) +
+		4 /* eir_server_impl_id.count (0) */);
+
+	WRITEMEM(&exid->clientid, 8);
+	WRITE32(exid->seqid);
+	WRITE32(exid->flags);
+
+	/* state_protect4_r. Currently only support SP4_NONE */
+	BUG_ON(exid->spa_how != SP4_NONE);
+	WRITE32(exid->spa_how);
+
+	/* The server_owner struct */
+	WRITE64(minor_id);      /* Minor id */
+	/* major id */
+	WRITE32(major_id_sz);
+	WRITEMEM(major_id, major_id_sz);
+
+	/* Server scope */
+	WRITE32(server_scope_sz);
+	WRITEMEM(server_scope, server_scope_sz);
+
+	/* Implementation id */
+	WRITE32(0);	/* zero length nfs_impl_id4 array */
+	ADJUST_ARGS();
+	return 0;
+}
+
+static __be32
+nfsd4_encode_create_session(struct nfsd4_compoundres *resp, int nfserr,
+			    struct nfsd4_create_session *sess)
+{
+	ENCODE_HEAD;
+
+	if (nfserr)
+		return nfserr;
+
+	RESERVE_SPACE(24);
+	WRITEMEM(sess->sessionid.data, NFS4_MAX_SESSIONID_LEN);
+	WRITE32(sess->seqid);
+	WRITE32(sess->flags);
+	ADJUST_ARGS();
+
+	RESERVE_SPACE(28);
+	WRITE32(0); /* headerpadsz */
+	WRITE32(sess->fore_channel.maxreq_sz);
+	WRITE32(sess->fore_channel.maxresp_sz);
+	WRITE32(sess->fore_channel.maxresp_cached);
+	WRITE32(sess->fore_channel.maxops);
+	WRITE32(sess->fore_channel.maxreqs);
+	WRITE32(sess->fore_channel.nr_rdma_attrs);
+	ADJUST_ARGS();
+
+	if (sess->fore_channel.nr_rdma_attrs) {
+		RESERVE_SPACE(4);
+		WRITE32(sess->fore_channel.rdma_attrs);
+		ADJUST_ARGS();
+	}
+
+	RESERVE_SPACE(28);
+	WRITE32(0); /* headerpadsz */
+	WRITE32(sess->back_channel.maxreq_sz);
+	WRITE32(sess->back_channel.maxresp_sz);
+	WRITE32(sess->back_channel.maxresp_cached);
+	WRITE32(sess->back_channel.maxops);
+	WRITE32(sess->back_channel.maxreqs);
+	WRITE32(sess->back_channel.nr_rdma_attrs);
+	ADJUST_ARGS();
+
+	if (sess->back_channel.nr_rdma_attrs) {
+		RESERVE_SPACE(4);
+		WRITE32(sess->back_channel.rdma_attrs);
+		ADJUST_ARGS();
+	}
+	return 0;
+}
+
+static __be32
+nfsd4_encode_destroy_session(struct nfsd4_compoundres *resp, int nfserr,
+			     struct nfsd4_destroy_session *destroy_session)
+{
+	return nfserr;
+}
+
+__be32
+nfsd4_encode_sequence(struct nfsd4_compoundres *resp, int nfserr,
+		      struct nfsd4_sequence *seq)
+{
+	ENCODE_HEAD;
+
+	if (nfserr)
+		return nfserr;
+
+	RESERVE_SPACE(NFS4_MAX_SESSIONID_LEN + 20);
+	WRITEMEM(seq->sessionid.data, NFS4_MAX_SESSIONID_LEN);
+	WRITE32(seq->seqid);
+	WRITE32(seq->slotid);
+	WRITE32(seq->maxslots);
+	/*
+	 * FIXME: for now:
+	 *   target_maxslots = maxslots
+	 *   status_flags = 0
+	 */
+	WRITE32(seq->maxslots);
+	WRITE32(0);
+
+	ADJUST_ARGS();
+	return 0;
+}
+
 static __be32
 nfsd4_encode_noop(struct nfsd4_compoundres *resp, __be32 nfserr, void *p)
 {
@@ -2579,6 +3087,11 @@ nfsd4_encode_noop(struct nfsd4_compoundres *resp, __be32 nfserr, void *p)
 
 typedef __be32(* nfsd4_enc)(struct nfsd4_compoundres *, __be32, void *);
 
+/*
+ * Note: nfsd4_enc_ops vector is shared for v4.0 and v4.1
+ * since we don't need to filter out obsolete ops as this is
+ * done in the decoding phase.
+ */
 static nfsd4_enc nfsd4_enc_ops[] = {
 	[OP_ACCESS]		= (nfsd4_enc)nfsd4_encode_access,
 	[OP_CLOSE]		= (nfsd4_enc)nfsd4_encode_close,
@@ -2617,8 +3130,77 @@ static nfsd4_enc nfsd4_enc_ops[] = {
 	[OP_VERIFY]		= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_WRITE]		= (nfsd4_enc)nfsd4_encode_write,
 	[OP_RELEASE_LOCKOWNER]	= (nfsd4_enc)nfsd4_encode_noop,
+
+	/* NFSv4.1 operations */
+	[OP_BACKCHANNEL_CTL]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_BIND_CONN_TO_SESSION] = (nfsd4_enc)nfsd4_encode_noop,
+	[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,
+	[OP_FREE_STATEID]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_GET_DIR_DELEGATION]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_GETDEVICEINFO]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_GETDEVICELIST]	= (nfsd4_enc)nfsd4_encode_noop,
+	[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_SEQUENCE]		= (nfsd4_enc)nfsd4_encode_sequence,
+	[OP_SET_SSV]		= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_TEST_STATEID]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_WANT_DELEGATION]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_DESTROY_CLIENTID]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_RECLAIM_COMPLETE]	= (nfsd4_enc)nfsd4_encode_noop,
 };
 
+/*
+ * Calculate the total amount of memory that the compound response has taken
+ * after encoding the current operation.
+ *
+ * pad: add on 8 bytes for the next operation's op_code and status so that
+ * there is room to cache a failure on the next operation.
+ *
+ * Compare this length to the session se_fmaxresp_cached.
+ *
+ * Our se_fmaxresp_cached will always be a multiple of PAGE_SIZE, and so
+ * will be at least a page and will therefore hold the xdr_buf head.
+ */
+static int nfsd4_check_drc_limit(struct nfsd4_compoundres *resp)
+{
+	int status = 0;
+	struct xdr_buf *xb = &resp->rqstp->rq_res;
+	struct nfsd4_compoundargs *args = resp->rqstp->rq_argp;
+	struct nfsd4_session *session = NULL;
+	struct nfsd4_slot *slot = resp->cstate.slot;
+	u32 length, tlen = 0, pad = 8;
+
+	if (!nfsd4_has_session(&resp->cstate))
+		return status;
+
+	session = resp->cstate.session;
+	if (session == NULL || slot->sl_cache_entry.ce_cachethis == 0)
+		return status;
+
+	if (resp->opcnt >= args->opcnt)
+		pad = 0; /* this is the last operation */
+
+	if (xb->page_len == 0) {
+		length = (char *)resp->p - (char *)xb->head[0].iov_base + pad;
+	} else {
+		if (xb->tail[0].iov_base && xb->tail[0].iov_len > 0)
+			tlen = (char *)resp->p - (char *)xb->tail[0].iov_base;
+
+		length = xb->head[0].iov_len + xb->page_len + tlen + pad;
+	}
+	dprintk("%s length %u, xb->page_len %u tlen %u pad %u\n", __func__,
+		length, xb->page_len, tlen, pad);
+
+	if (length <= session->se_fmaxresp_cached)
+		return status;
+	else
+		return nfserr_rep_too_big_to_cache;
+}
+
 void
 nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op)
 {
@@ -2635,6 +3217,9 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op)
 	BUG_ON(op->opnum < 0 || op->opnum >= ARRAY_SIZE(nfsd4_enc_ops) ||
 	       !nfsd4_enc_ops[op->opnum]);
 	op->status = nfsd4_enc_ops[op->opnum](resp, op->status, &op->u);
+	/* nfsd4_check_drc_limit guarantees enough room for error status */
+	if (!op->status && nfsd4_check_drc_limit(resp))
+		op->status = nfserr_rep_too_big_to_cache;
 status:
 	/*
 	 * Note: We write the status directly, instead of using WRITE32(),
@@ -2735,6 +3320,18 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compo
 		iov = &rqstp->rq_res.head[0];
 	iov->iov_len = ((char*)resp->p) - (char*)iov->iov_base;
 	BUG_ON(iov->iov_len > PAGE_SIZE);
+	if (nfsd4_has_session(&resp->cstate)) {
+		if (resp->cstate.status == nfserr_replay_cache &&
+				!nfsd4_not_cached(resp)) {
+			iov->iov_len = resp->cstate.iovlen;
+		} else {
+			nfsd4_store_cache_entry(resp);
+			dprintk("%s: SET SLOT STATE TO AVAILABLE\n", __func__);
+			resp->cstate.slot->sl_inuse = 0;
+		}
+		if (resp->cstate.session)
+			nfsd4_put_session(resp->cstate.session);
+	}
 	return 1;
 }
 

fs/nfsd/nfsctl.c

@@ -60,6 +60,7 @@ enum {
 	NFSD_FO_UnlockFS,
 	NFSD_Threads,
 	NFSD_Pool_Threads,
+	NFSD_Pool_Stats,
 	NFSD_Versions,
 	NFSD_Ports,
 	NFSD_MaxBlkSize,
@@ -172,6 +173,16 @@ static const struct file_operations exports_operations = {
 	.owner		= THIS_MODULE,
 };
 
+extern int nfsd_pool_stats_open(struct inode *inode, struct file *file);
+
+static struct file_operations pool_stats_operations = {
+	.open		= nfsd_pool_stats_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+	.owner		= THIS_MODULE,
+};
+
 /*----------------------------------------------------------------------------*/
 /*
  * payload - write methods
@@ -781,8 +792,9 @@ out_free:
 static ssize_t __write_versions(struct file *file, char *buf, size_t size)
 {
 	char *mesg = buf;
-	char *vers, sign;
+	char *vers, *minorp, sign;
 	int len, num;
+	unsigned minor;
 	ssize_t tlen = 0;
 	char *sep;
 
@@ -803,9 +815,20 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
 		do {
 			sign = *vers;
 			if (sign == '+' || sign == '-')
-				num = simple_strtol((vers+1), NULL, 0);
+				num = simple_strtol((vers+1), &minorp, 0);
 			else
-				num = simple_strtol(vers, NULL, 0);
+				num = simple_strtol(vers, &minorp, 0);
+			if (*minorp == '.') {
+				if (num < 4)
+					return -EINVAL;
+				minor = simple_strtoul(minorp+1, NULL, 0);
+				if (minor == 0)
+					return -EINVAL;
+				if (nfsd_minorversion(minor, sign == '-' ?
+						     NFSD_CLEAR : NFSD_SET) < 0)
+					return -EINVAL;
+				goto next;
+			}
 			switch(num) {
 			case 2:
 			case 3:
@@ -815,6 +838,7 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
 			default:
 				return -EINVAL;
 			}
+		next:
 			vers += len + 1;
 			tlen += len;
 		} while ((len = qword_get(&mesg, vers, size)) > 0);
@@ -833,6 +857,13 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
 				       num);
 			sep = " ";
 		}
+	if (nfsd_vers(4, NFSD_AVAIL))
+		for (minor = 1; minor <= NFSD_SUPPORTED_MINOR_VERSION; minor++)
+			len += sprintf(buf+len, " %c4.%u",
+					(nfsd_vers(4, NFSD_TEST) &&
+					 nfsd_minorversion(minor, NFSD_TEST)) ?
+						'+' : '-',
+					minor);
 	len += sprintf(buf+len, "\n");
 	return len;
 }
@@ -1248,6 +1279,7 @@ static int nfsd_fill_super(struct super_block * sb, void * data, int silent)
 		[NFSD_Fh] = {"filehandle", &transaction_ops, S_IWUSR|S_IRUSR},
 		[NFSD_Threads] = {"threads", &transaction_ops, S_IWUSR|S_IRUSR},
 		[NFSD_Pool_Threads] = {"pool_threads", &transaction_ops, S_IWUSR|S_IRUSR},
+		[NFSD_Pool_Stats] = {"pool_stats", &pool_stats_operations, S_IRUGO},
 		[NFSD_Versions] = {"versions", &transaction_ops, S_IWUSR|S_IRUSR},
 		[NFSD_Ports] = {"portlist", &transaction_ops, S_IWUSR|S_IRUGO},
 		[NFSD_MaxBlkSize] = {"max_block_size", &transaction_ops, S_IWUSR|S_IRUGO},

fs/nfsd/nfsproc.c

@@ -180,6 +180,7 @@ nfsd_proc_write(struct svc_rqst *rqstp, struct nfsd_writeargs *argp,
 {
 	__be32	nfserr;
 	int	stable = 1;
+	unsigned long cnt = argp->len;
 
 	dprintk("nfsd: WRITE    %s %d bytes at %d\n",
 		SVCFH_fmt(&argp->fh),
@@ -188,7 +189,7 @@ nfsd_proc_write(struct svc_rqst *rqstp, struct nfsd_writeargs *argp,
 	nfserr = nfsd_write(rqstp, fh_copy(&resp->fh, &argp->fh), NULL,
 				   argp->offset,
 				   rqstp->rq_vec, argp->vlen,
-				   argp->len,
+			           &cnt,
 				   &stable);
 	return nfsd_return_attrs(nfserr, resp);
 }

fs/nfsd/nfssvc.c

@@ -22,6 +22,7 @@
 #include <linux/freezer.h>
 #include <linux/fs_struct.h>
 #include <linux/kthread.h>
+#include <linux/swap.h>
 
 #include <linux/sunrpc/types.h>
 #include <linux/sunrpc/stats.h>
@@ -40,9 +41,6 @@
 extern struct svc_program	nfsd_program;
 static int			nfsd(void *vrqstp);
 struct timeval			nfssvc_boot;
-static atomic_t			nfsd_busy;
-static unsigned long		nfsd_last_call;
-static DEFINE_SPINLOCK(nfsd_call_lock);
 
 /*
  * nfsd_mutex protects nfsd_serv -- both the pointer itself and the members
@@ -123,6 +121,8 @@ struct svc_program		nfsd_program = {
 
 };
 
+u32 nfsd_supported_minorversion;
+
 int nfsd_vers(int vers, enum vers_op change)
 {
 	if (vers < NFSD_MINVERS || vers >= NFSD_NRVERS)
@@ -149,6 +149,28 @@ int nfsd_vers(int vers, enum vers_op change)
 	}
 	return 0;
 }
+
+int nfsd_minorversion(u32 minorversion, enum vers_op change)
+{
+	if (minorversion > NFSD_SUPPORTED_MINOR_VERSION)
+		return -1;
+	switch(change) {
+	case NFSD_SET:
+		nfsd_supported_minorversion = minorversion;
+		break;
+	case NFSD_CLEAR:
+		if (minorversion == 0)
+			return -1;
+		nfsd_supported_minorversion = minorversion - 1;
+		break;
+	case NFSD_TEST:
+		return minorversion <= nfsd_supported_minorversion;
+	case NFSD_AVAIL:
+		return minorversion <= NFSD_SUPPORTED_MINOR_VERSION;
+	}
+	return 0;
+}
+
 /*
  * Maximum number of nfsd processes
  */
@@ -200,6 +222,28 @@ void nfsd_reset_versions(void)
 	}
 }
 
+/*
+ * Each session guarantees a negotiated per slot memory cache for replies
+ * which in turn consumes memory beyond the v2/v3/v4.0 server. A dedicated
+ * NFSv4.1 server might want to use more memory for a DRC than a machine
+ * with mutiple services.
+ *
+ * Impose a hard limit on the number of pages for the DRC which varies
+ * according to the machines free pages. This is of course only a default.
+ *
+ * For now this is a #defined shift which could be under admin control
+ * in the future.
+ */
+static void set_max_drc(void)
+{
+	/* The percent of nr_free_buffer_pages used by the V4.1 server DRC */
+	#define NFSD_DRC_SIZE_SHIFT	7
+	nfsd_serv->sv_drc_max_pages = nr_free_buffer_pages()
+						>> NFSD_DRC_SIZE_SHIFT;
+	nfsd_serv->sv_drc_pages_used = 0;
+	dprintk("%s svc_drc_max_pages %u\n", __func__,
+		nfsd_serv->sv_drc_max_pages);
+}
 
 int nfsd_create_serv(void)
 {
@@ -227,11 +271,12 @@ int nfsd_create_serv(void)
 			nfsd_max_blksize /= 2;
 	}
 
-	atomic_set(&nfsd_busy, 0);
 	nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize,
 				      nfsd_last_thread, nfsd, THIS_MODULE);
 	if (nfsd_serv == NULL)
 		err = -ENOMEM;
+	else
+		set_max_drc();
 
 	do_gettimeofday(&nfssvc_boot);		/* record boot time */
 	return err;
@@ -375,26 +420,6 @@ nfsd_svc(unsigned short port, int nrservs)
 	return error;
 }
 
-static inline void
-update_thread_usage(int busy_threads)
-{
-	unsigned long prev_call;
-	unsigned long diff;
-	int decile;
-
-	spin_lock(&nfsd_call_lock);
-	prev_call = nfsd_last_call;
-	nfsd_last_call = jiffies;
-	decile = busy_threads*10/nfsdstats.th_cnt;
-	if (decile>0 && decile <= 10) {
-		diff = nfsd_last_call - prev_call;
-		if ( (nfsdstats.th_usage[decile-1] += diff) >= NFSD_USAGE_WRAP)
-			nfsdstats.th_usage[decile-1] -= NFSD_USAGE_WRAP;
-		if (decile == 10)
-			nfsdstats.th_fullcnt++;
-	}
-	spin_unlock(&nfsd_call_lock);
-}
 
 /*
  * This is the NFS server kernel thread
@@ -460,8 +485,6 @@ nfsd(void *vrqstp)
 			continue;
 		}
 
-		update_thread_usage(atomic_read(&nfsd_busy));
-		atomic_inc(&nfsd_busy);
 
 		/* Lock the export hash tables for reading. */
 		exp_readlock();
@@ -470,8 +493,6 @@ nfsd(void *vrqstp)
 
 		/* Unlock export hash tables */
 		exp_readunlock();
-		update_thread_usage(atomic_read(&nfsd_busy));
-		atomic_dec(&nfsd_busy);
 	}
 
 	/* Clear signals before calling svc_exit_thread() */
@@ -539,6 +560,10 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 		+ rqstp->rq_res.head[0].iov_len;
 	rqstp->rq_res.head[0].iov_len += sizeof(__be32);
 
+	/* NFSv4.1 DRC requires statp */
+	if (rqstp->rq_vers == 4)
+		nfsd4_set_statp(rqstp, 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);
@@ -570,3 +595,10 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 	nfsd_cache_update(rqstp, proc->pc_cachetype, statp + 1);
 	return 1;
 }
+
+int nfsd_pool_stats_open(struct inode *inode, struct file *file)
+{
+	if (nfsd_serv == NULL)
+		return -ENODEV;
+	return svc_pool_stats_open(nfsd_serv, file);
+}

fs/nfsd/vfs.c

@@ -366,8 +366,9 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 	}
 
 	/* Revoke setuid/setgid on chown */
-	if (((iap->ia_valid & ATTR_UID) && iap->ia_uid != inode->i_uid) ||
-	    ((iap->ia_valid & ATTR_GID) && iap->ia_gid != inode->i_gid)) {
+	if (!S_ISDIR(inode->i_mode) &&
+	    (((iap->ia_valid & ATTR_UID) && iap->ia_uid != inode->i_uid) ||
+	     ((iap->ia_valid & ATTR_GID) && iap->ia_gid != inode->i_gid))) {
 		iap->ia_valid |= ATTR_KILL_PRIV;
 		if (iap->ia_valid & ATTR_MODE) {
 			/* we're setting mode too, just clear the s*id bits */
@@ -960,7 +961,7 @@ static void kill_suid(struct dentry *dentry)
 static __be32
 nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 				loff_t offset, struct kvec *vec, int vlen,
-	   			unsigned long cnt, int *stablep)
+				unsigned long *cnt, int *stablep)
 {
 	struct svc_export	*exp;
 	struct dentry		*dentry;
@@ -974,7 +975,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 	err = nfserr_perm;
 
 	if ((fhp->fh_export->ex_flags & NFSEXP_MSNFS) &&
-		(!lock_may_write(file->f_path.dentry->d_inode, offset, cnt)))
+		(!lock_may_write(file->f_path.dentry->d_inode, offset, *cnt)))
 		goto out;
 #endif
 
@@ -1009,7 +1010,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 	host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &offset);
 	set_fs(oldfs);
 	if (host_err >= 0) {
-		nfsdstats.io_write += cnt;
+		nfsdstats.io_write += host_err;
 		fsnotify_modify(file->f_path.dentry);
 	}
 
@@ -1054,9 +1055,10 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 	}
 
 	dprintk("nfsd: write complete host_err=%d\n", host_err);
-	if (host_err >= 0)
+	if (host_err >= 0) {
 		err = 0;
-	else 
+		*cnt = host_err;
+	} else
 		err = nfserrno(host_err);
 out:
 	return err;
@@ -1098,7 +1100,7 @@ out:
  */
 __be32
 nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
-		loff_t offset, struct kvec *vec, int vlen, unsigned long cnt,
+		loff_t offset, struct kvec *vec, int vlen, unsigned long *cnt,
 		int *stablep)
 {
 	__be32			err = 0;
@@ -1179,6 +1181,21 @@ nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *resfhp,
 	return 0;
 }
 
+/* HPUX client sometimes creates a file in mode 000, and sets size to 0.
+ * setting size to 0 may fail for some specific file systems by the permission
+ * checking which requires WRITE permission but the mode is 000.
+ * we ignore the resizing(to 0) on the just new created file, since the size is
+ * 0 after file created.
+ *
+ * call this only after vfs_create() is called.
+ * */
+static void
+nfsd_check_ignore_resizing(struct iattr *iap)
+{
+	if ((iap->ia_valid & ATTR_SIZE) && (iap->ia_size == 0))
+		iap->ia_valid &= ~ATTR_SIZE;
+}
+
 /*
  * Create a file (regular, directory, device, fifo); UNIX sockets 
  * not yet implemented.
@@ -1274,6 +1291,8 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	switch (type) {
 	case S_IFREG:
 		host_err = vfs_create(dirp, dchild, iap->ia_mode, NULL);
+		if (!host_err)
+			nfsd_check_ignore_resizing(iap);
 		break;
 	case S_IFDIR:
 		host_err = vfs_mkdir(dirp, dchild, iap->ia_mode);
@@ -1427,6 +1446,8 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		/* setattr will sync the child (or not) */
 	}
 
+	nfsd_check_ignore_resizing(iap);
+
 	if (createmode == NFS3_CREATE_EXCLUSIVE) {
 		/* Cram the verifier into atime/mtime */
 		iap->ia_valid = ATTR_MTIME|ATTR_ATIME

include/linux/lockd/xdr.h

@@ -25,13 +25,13 @@ struct svc_rqst;
 #define NLM_MAXCOOKIELEN    	32
 #define NLM_MAXSTRLEN		1024
 
-#define	nlm_granted		__constant_htonl(NLM_LCK_GRANTED)
-#define	nlm_lck_denied		__constant_htonl(NLM_LCK_DENIED)
-#define	nlm_lck_denied_nolocks	__constant_htonl(NLM_LCK_DENIED_NOLOCKS)
-#define	nlm_lck_blocked		__constant_htonl(NLM_LCK_BLOCKED)
-#define	nlm_lck_denied_grace_period	__constant_htonl(NLM_LCK_DENIED_GRACE_PERIOD)
+#define	nlm_granted		cpu_to_be32(NLM_LCK_GRANTED)
+#define	nlm_lck_denied		cpu_to_be32(NLM_LCK_DENIED)
+#define	nlm_lck_denied_nolocks	cpu_to_be32(NLM_LCK_DENIED_NOLOCKS)
+#define	nlm_lck_blocked		cpu_to_be32(NLM_LCK_BLOCKED)
+#define	nlm_lck_denied_grace_period	cpu_to_be32(NLM_LCK_DENIED_GRACE_PERIOD)
 
-#define nlm_drop_reply		__constant_htonl(30000)
+#define nlm_drop_reply		cpu_to_be32(30000)
 
 /* Lock info passed via NLM */
 struct nlm_lock {

include/linux/lockd/xdr4.h

@@ -15,11 +15,11 @@
 #include <linux/lockd/xdr.h>
 
 /* error codes new to NLMv4 */
-#define	nlm4_deadlock		__constant_htonl(NLM_DEADLCK)
-#define	nlm4_rofs		__constant_htonl(NLM_ROFS)
-#define	nlm4_stale_fh		__constant_htonl(NLM_STALE_FH)
-#define	nlm4_fbig		__constant_htonl(NLM_FBIG)
-#define	nlm4_failed		__constant_htonl(NLM_FAILED)
+#define	nlm4_deadlock		cpu_to_be32(NLM_DEADLCK)
+#define	nlm4_rofs		cpu_to_be32(NLM_ROFS)
+#define	nlm4_stale_fh		cpu_to_be32(NLM_STALE_FH)
+#define	nlm4_fbig		cpu_to_be32(NLM_FBIG)
+#define	nlm4_failed		cpu_to_be32(NLM_FAILED)
 
 
 

include/linux/nfs.h

@@ -109,7 +109,6 @@
 	NFSERR_FILE_OPEN = 10046,      /*       v4 */
 	NFSERR_ADMIN_REVOKED = 10047,  /*       v4 */
 	NFSERR_CB_PATH_DOWN = 10048,   /*       v4 */
-	NFSERR_REPLAY_ME = 10049	/*       v4 */
 };
 
 /* NFSv2 file types - beware, these are not the same in NFSv3 */

include/linux/nfs4.h

@@ -21,6 +21,7 @@
 #define NFS4_FHSIZE		128
 #define NFS4_MAXPATHLEN		PATH_MAX
 #define NFS4_MAXNAMLEN		NAME_MAX
+#define NFS4_MAX_SESSIONID_LEN	16
 
 #define NFS4_ACCESS_READ        0x0001
 #define NFS4_ACCESS_LOOKUP      0x0002
@@ -38,6 +39,7 @@
 #define NFS4_OPEN_RESULT_CONFIRM 0x0002
 #define NFS4_OPEN_RESULT_LOCKTYPE_POSIX 0x0004
 
+#define NFS4_SHARE_ACCESS_MASK	0x000F
 #define NFS4_SHARE_ACCESS_READ	0x0001
 #define NFS4_SHARE_ACCESS_WRITE	0x0002
 #define NFS4_SHARE_ACCESS_BOTH	0x0003
@@ -45,6 +47,19 @@
 #define NFS4_SHARE_DENY_WRITE	0x0002
 #define NFS4_SHARE_DENY_BOTH	0x0003
 
+/* nfs41 */
+#define NFS4_SHARE_WANT_MASK		0xFF00
+#define NFS4_SHARE_WANT_NO_PREFERENCE	0x0000
+#define NFS4_SHARE_WANT_READ_DELEG	0x0100
+#define NFS4_SHARE_WANT_WRITE_DELEG	0x0200
+#define NFS4_SHARE_WANT_ANY_DELEG	0x0300
+#define NFS4_SHARE_WANT_NO_DELEG	0x0400
+#define NFS4_SHARE_WANT_CANCEL		0x0500
+
+#define NFS4_SHARE_WHEN_MASK		0xF0000
+#define NFS4_SHARE_SIGNAL_DELEG_WHEN_RESRC_AVAIL	0x10000
+#define NFS4_SHARE_PUSH_DELEG_WHEN_UNCONTENDED		0x20000
+
 #define NFS4_SET_TO_SERVER_TIME	0
 #define NFS4_SET_TO_CLIENT_TIME	1
 
@@ -88,6 +103,31 @@
 #define NFS4_ACE_GENERIC_EXECUTE              0x001200A0
 #define NFS4_ACE_MASK_ALL                     0x001F01FF
 
+#define EXCHGID4_FLAG_SUPP_MOVED_REFER		0x00000001
+#define EXCHGID4_FLAG_SUPP_MOVED_MIGR		0x00000002
+#define EXCHGID4_FLAG_USE_NON_PNFS		0x00010000
+#define EXCHGID4_FLAG_USE_PNFS_MDS		0x00020000
+#define EXCHGID4_FLAG_USE_PNFS_DS		0x00040000
+#define EXCHGID4_FLAG_UPD_CONFIRMED_REC_A	0x40000000
+#define EXCHGID4_FLAG_CONFIRMED_R		0x80000000
+/*
+ * Since the validity of these bits depends on whether
+ * they're set in the argument or response, have separate
+ * invalid flag masks for arg (_A) and resp (_R).
+ */
+#define EXCHGID4_FLAG_MASK_A			0x40070003
+#define EXCHGID4_FLAG_MASK_R			0x80070003
+
+#define SEQ4_STATUS_CB_PATH_DOWN		0x00000001
+#define SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRING	0x00000002
+#define SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRED	0x00000004
+#define SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED	0x00000008
+#define SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED	0x00000010
+#define SEQ4_STATUS_ADMIN_STATE_REVOKED		0x00000020
+#define SEQ4_STATUS_RECALLABLE_STATE_REVOKED	0x00000040
+#define SEQ4_STATUS_LEASE_MOVED			0x00000080
+#define SEQ4_STATUS_RESTART_RECLAIM_NEEDED	0x00000100
+
 #define NFS4_MAX_UINT64	(~(u64)0)
 
 enum nfs4_acl_whotype {
@@ -154,6 +194,28 @@ enum nfs_opnum4 {
 	OP_VERIFY = 37,
 	OP_WRITE = 38,
 	OP_RELEASE_LOCKOWNER = 39,
+
+	/* nfs41 */
+	OP_BACKCHANNEL_CTL = 40,
+	OP_BIND_CONN_TO_SESSION = 41,
+	OP_EXCHANGE_ID = 42,
+	OP_CREATE_SESSION = 43,
+	OP_DESTROY_SESSION = 44,
+	OP_FREE_STATEID = 45,
+	OP_GET_DIR_DELEGATION = 46,
+	OP_GETDEVICEINFO = 47,
+	OP_GETDEVICELIST = 48,
+	OP_LAYOUTCOMMIT = 49,
+	OP_LAYOUTGET = 50,
+	OP_LAYOUTRETURN = 51,
+	OP_SECINFO_NO_NAME = 52,
+	OP_SEQUENCE = 53,
+	OP_SET_SSV = 54,
+	OP_TEST_STATEID = 55,
+	OP_WANT_DELEGATION = 56,
+	OP_DESTROY_CLIENTID = 57,
+	OP_RECLAIM_COMPLETE = 58,
+
 	OP_ILLEGAL = 10044,
 };
 
@@ -230,7 +292,48 @@ enum nfsstat4 {
 	NFS4ERR_DEADLOCK = 10045,
 	NFS4ERR_FILE_OPEN = 10046,
 	NFS4ERR_ADMIN_REVOKED = 10047,
-	NFS4ERR_CB_PATH_DOWN = 10048
+	NFS4ERR_CB_PATH_DOWN = 10048,
+
+	/* nfs41 */
+	NFS4ERR_BADIOMODE	= 10049,
+	NFS4ERR_BADLAYOUT	= 10050,
+	NFS4ERR_BAD_SESSION_DIGEST = 10051,
+	NFS4ERR_BADSESSION	= 10052,
+	NFS4ERR_BADSLOT		= 10053,
+	NFS4ERR_COMPLETE_ALREADY = 10054,
+	NFS4ERR_CONN_NOT_BOUND_TO_SESSION = 10055,
+	NFS4ERR_DELEG_ALREADY_WANTED = 10056,
+	NFS4ERR_BACK_CHAN_BUSY	= 10057,	/* backchan reqs outstanding */
+	NFS4ERR_LAYOUTTRYLATER	= 10058,
+	NFS4ERR_LAYOUTUNAVAILABLE = 10059,
+	NFS4ERR_NOMATCHING_LAYOUT = 10060,
+	NFS4ERR_RECALLCONFLICT	= 10061,
+	NFS4ERR_UNKNOWN_LAYOUTTYPE = 10062,
+	NFS4ERR_SEQ_MISORDERED = 10063, 	/* unexpected seq.id in req */
+	NFS4ERR_SEQUENCE_POS	= 10064,	/* [CB_]SEQ. op not 1st op */
+	NFS4ERR_REQ_TOO_BIG	= 10065,	/* request too big */
+	NFS4ERR_REP_TOO_BIG	= 10066,	/* reply too big */
+	NFS4ERR_REP_TOO_BIG_TO_CACHE = 10067,	/* rep. not all cached */
+	NFS4ERR_RETRY_UNCACHED_REP = 10068,	/* retry & rep. uncached */
+	NFS4ERR_UNSAFE_COMPOUND = 10069,	/* retry/recovery too hard */
+	NFS4ERR_TOO_MANY_OPS	= 10070,	/* too many ops in [CB_]COMP */
+	NFS4ERR_OP_NOT_IN_SESSION = 10071,	/* op needs [CB_]SEQ. op */
+	NFS4ERR_HASH_ALG_UNSUPP = 10072,	/* hash alg. not supp. */
+						/* Error 10073 is unused. */
+	NFS4ERR_CLIENTID_BUSY	= 10074,	/* clientid has state */
+	NFS4ERR_PNFS_IO_HOLE	= 10075,	/* IO to _SPARSE file hole */
+	NFS4ERR_SEQ_FALSE_RETRY	= 10076,	/* retry not origional */
+	NFS4ERR_BAD_HIGH_SLOT	= 10077,	/* sequence arg bad */
+	NFS4ERR_DEADSESSION	= 10078,	/* persistent session dead */
+	NFS4ERR_ENCR_ALG_UNSUPP = 10079,	/* SSV alg mismatch */
+	NFS4ERR_PNFS_NO_LAYOUT	= 10080,	/* direct I/O with no layout */
+	NFS4ERR_NOT_ONLY_OP	= 10081,	/* bad compound */
+	NFS4ERR_WRONG_CRED	= 10082,	/* permissions:state change */
+	NFS4ERR_WRONG_TYPE	= 10083,	/* current operation mismatch */
+	NFS4ERR_DIRDELEG_UNAVAIL = 10084,	/* no directory delegation */
+	NFS4ERR_REJECT_DELEG	= 10085,	/* on callback */
+	NFS4ERR_RETURNCONFLICT	= 10086,	/* outstanding layoutreturn */
+	NFS4ERR_DELEG_REVOKED	= 10087,	/* deleg./layout revoked */
 };
 
 /*
@@ -265,7 +368,13 @@ enum opentype4 {
 enum createmode4 {
 	NFS4_CREATE_UNCHECKED = 0,
 	NFS4_CREATE_GUARDED = 1,
-	NFS4_CREATE_EXCLUSIVE = 2
+	NFS4_CREATE_EXCLUSIVE = 2,
+	/*
+	 * New to NFSv4.1. If session is persistent,
+	 * GUARDED4 MUST be used. Otherwise, use
+	 * EXCLUSIVE4_1 instead of EXCLUSIVE4.
+	 */
+	NFS4_CREATE_EXCLUSIVE4_1 = 3
 };
 
 enum limit_by4 {
@@ -301,6 +410,8 @@ enum lock_type4 {
 #define FATTR4_WORD0_UNIQUE_HANDLES     (1UL << 9)
 #define FATTR4_WORD0_LEASE_TIME         (1UL << 10)
 #define FATTR4_WORD0_RDATTR_ERROR       (1UL << 11)
+/* Mandatory in NFSv4.1 */
+#define FATTR4_WORD2_SUPPATTR_EXCLCREAT (1UL << 11)
 
 /* Recommended Attributes */
 #define FATTR4_WORD0_ACL                (1UL << 12)
@@ -391,6 +502,29 @@ enum {
 	NFSPROC4_CLNT_GETACL,
 	NFSPROC4_CLNT_SETACL,
 	NFSPROC4_CLNT_FS_LOCATIONS,
+
+	/* nfs41 */
+	NFSPROC4_CLNT_EXCHANGE_ID,
+	NFSPROC4_CLNT_CREATE_SESSION,
+	NFSPROC4_CLNT_DESTROY_SESSION,
+	NFSPROC4_CLNT_SEQUENCE,
+	NFSPROC4_CLNT_GET_LEASE_TIME,
+};
+
+/* nfs41 types */
+struct nfs4_sessionid {
+	unsigned char data[NFS4_MAX_SESSIONID_LEN];
+};
+
+/* Create Session Flags */
+#define SESSION4_PERSIST	 0x001
+#define SESSION4_BACK_CHAN 	 0x002
+#define SESSION4_RDMA		 0x004
+
+enum state_protect_how4 {
+	SP4_NONE	= 0,
+	SP4_MACH_CRED	= 1,
+	SP4_SSV		= 2
 };
 
 #endif

include/linux/nfsd/cache.h

@@ -76,4 +76,12 @@ void	nfsd_reply_cache_shutdown(void);
 int	nfsd_cache_lookup(struct svc_rqst *, int);
 void	nfsd_cache_update(struct svc_rqst *, int, __be32 *);
 
+#ifdef CONFIG_NFSD_V4
+void	nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp);
+#else  /* CONFIG_NFSD_V4 */
+static inline void nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp)
+{
+}
+#endif /* CONFIG_NFSD_V4 */
+
 #endif /* NFSCACHE_H */

include/linux/nfsd/nfsd.h

@@ -23,7 +23,7 @@
 /*
  * nfsd version
  */
-#define NFSD_SUPPORTED_MINOR_VERSION	0
+#define NFSD_SUPPORTED_MINOR_VERSION	1
 
 /*
  * Flags for nfsd_permission
@@ -53,6 +53,7 @@ typedef int (*nfsd_dirop_t)(struct inode *, struct dentry *, int, int);
 extern struct svc_program	nfsd_program;
 extern struct svc_version	nfsd_version2, nfsd_version3,
 				nfsd_version4;
+extern u32			nfsd_supported_minorversion;
 extern struct mutex		nfsd_mutex;
 extern struct svc_serv		*nfsd_serv;
 
@@ -105,7 +106,7 @@ void		nfsd_close(struct file *);
 __be32 		nfsd_read(struct svc_rqst *, struct svc_fh *, struct file *,
 				loff_t, struct kvec *, int, unsigned long *);
 __be32 		nfsd_write(struct svc_rqst *, struct svc_fh *,struct file *,
-				loff_t, struct kvec *,int, unsigned long, int *);
+				loff_t, struct kvec *,int, unsigned long *, int *);
 __be32		nfsd_readlink(struct svc_rqst *, struct svc_fh *,
 				char *, int *);
 __be32		nfsd_symlink(struct svc_rqst *, struct svc_fh *,
@@ -149,6 +150,7 @@ int nfsd_set_posix_acl(struct svc_fh *, int, struct posix_acl *);
 
 enum vers_op {NFSD_SET, NFSD_CLEAR, NFSD_TEST, NFSD_AVAIL };
 int nfsd_vers(int vers, enum vers_op change);
+int nfsd_minorversion(u32 minorversion, enum vers_op change);
 void nfsd_reset_versions(void);
 int nfsd_create_serv(void);
 
@@ -186,78 +188,119 @@ void		nfsd_lockd_shutdown(void);
 /*
  * These macros provide pre-xdr'ed values for faster operation.
  */
-#define	nfs_ok			__constant_htonl(NFS_OK)
-#define	nfserr_perm		__constant_htonl(NFSERR_PERM)
-#define	nfserr_noent		__constant_htonl(NFSERR_NOENT)
-#define	nfserr_io		__constant_htonl(NFSERR_IO)
-#define	nfserr_nxio		__constant_htonl(NFSERR_NXIO)
-#define	nfserr_eagain		__constant_htonl(NFSERR_EAGAIN)
-#define	nfserr_acces		__constant_htonl(NFSERR_ACCES)
-#define	nfserr_exist		__constant_htonl(NFSERR_EXIST)
-#define	nfserr_xdev		__constant_htonl(NFSERR_XDEV)
-#define	nfserr_nodev		__constant_htonl(NFSERR_NODEV)
-#define	nfserr_notdir		__constant_htonl(NFSERR_NOTDIR)
-#define	nfserr_isdir		__constant_htonl(NFSERR_ISDIR)
-#define	nfserr_inval		__constant_htonl(NFSERR_INVAL)
-#define	nfserr_fbig		__constant_htonl(NFSERR_FBIG)
-#define	nfserr_nospc		__constant_htonl(NFSERR_NOSPC)
-#define	nfserr_rofs		__constant_htonl(NFSERR_ROFS)
-#define	nfserr_mlink		__constant_htonl(NFSERR_MLINK)
-#define	nfserr_opnotsupp	__constant_htonl(NFSERR_OPNOTSUPP)
-#define	nfserr_nametoolong	__constant_htonl(NFSERR_NAMETOOLONG)
-#define	nfserr_notempty		__constant_htonl(NFSERR_NOTEMPTY)
-#define	nfserr_dquot		__constant_htonl(NFSERR_DQUOT)
-#define	nfserr_stale		__constant_htonl(NFSERR_STALE)
-#define	nfserr_remote		__constant_htonl(NFSERR_REMOTE)
-#define	nfserr_wflush		__constant_htonl(NFSERR_WFLUSH)
-#define	nfserr_badhandle	__constant_htonl(NFSERR_BADHANDLE)
-#define	nfserr_notsync		__constant_htonl(NFSERR_NOT_SYNC)
-#define	nfserr_badcookie	__constant_htonl(NFSERR_BAD_COOKIE)
-#define	nfserr_notsupp		__constant_htonl(NFSERR_NOTSUPP)
-#define	nfserr_toosmall		__constant_htonl(NFSERR_TOOSMALL)
-#define	nfserr_serverfault	__constant_htonl(NFSERR_SERVERFAULT)
-#define	nfserr_badtype		__constant_htonl(NFSERR_BADTYPE)
-#define	nfserr_jukebox		__constant_htonl(NFSERR_JUKEBOX)
-#define	nfserr_denied		__constant_htonl(NFSERR_DENIED)
-#define	nfserr_deadlock		__constant_htonl(NFSERR_DEADLOCK)
-#define nfserr_expired          __constant_htonl(NFSERR_EXPIRED)
-#define	nfserr_bad_cookie	__constant_htonl(NFSERR_BAD_COOKIE)
-#define	nfserr_same		__constant_htonl(NFSERR_SAME)
-#define	nfserr_clid_inuse	__constant_htonl(NFSERR_CLID_INUSE)
-#define	nfserr_stale_clientid	__constant_htonl(NFSERR_STALE_CLIENTID)
-#define	nfserr_resource		__constant_htonl(NFSERR_RESOURCE)
-#define	nfserr_moved		__constant_htonl(NFSERR_MOVED)
-#define	nfserr_nofilehandle	__constant_htonl(NFSERR_NOFILEHANDLE)
-#define	nfserr_minor_vers_mismatch	__constant_htonl(NFSERR_MINOR_VERS_MISMATCH)
-#define nfserr_share_denied	__constant_htonl(NFSERR_SHARE_DENIED)
-#define nfserr_stale_stateid	__constant_htonl(NFSERR_STALE_STATEID)
-#define nfserr_old_stateid	__constant_htonl(NFSERR_OLD_STATEID)
-#define nfserr_bad_stateid	__constant_htonl(NFSERR_BAD_STATEID)
-#define nfserr_bad_seqid	__constant_htonl(NFSERR_BAD_SEQID)
-#define	nfserr_symlink		__constant_htonl(NFSERR_SYMLINK)
-#define	nfserr_not_same		__constant_htonl(NFSERR_NOT_SAME)
-#define	nfserr_restorefh	__constant_htonl(NFSERR_RESTOREFH)
-#define	nfserr_attrnotsupp	__constant_htonl(NFSERR_ATTRNOTSUPP)
-#define	nfserr_bad_xdr		__constant_htonl(NFSERR_BAD_XDR)
-#define	nfserr_openmode		__constant_htonl(NFSERR_OPENMODE)
-#define	nfserr_locks_held	__constant_htonl(NFSERR_LOCKS_HELD)
-#define	nfserr_op_illegal	__constant_htonl(NFSERR_OP_ILLEGAL)
-#define	nfserr_grace		__constant_htonl(NFSERR_GRACE)
-#define	nfserr_no_grace		__constant_htonl(NFSERR_NO_GRACE)
-#define	nfserr_reclaim_bad	__constant_htonl(NFSERR_RECLAIM_BAD)
-#define	nfserr_badname		__constant_htonl(NFSERR_BADNAME)
-#define	nfserr_cb_path_down	__constant_htonl(NFSERR_CB_PATH_DOWN)
-#define	nfserr_locked		__constant_htonl(NFSERR_LOCKED)
-#define	nfserr_wrongsec		__constant_htonl(NFSERR_WRONGSEC)
-#define	nfserr_replay_me	__constant_htonl(NFSERR_REPLAY_ME)
+#define	nfs_ok			cpu_to_be32(NFS_OK)
+#define	nfserr_perm		cpu_to_be32(NFSERR_PERM)
+#define	nfserr_noent		cpu_to_be32(NFSERR_NOENT)
+#define	nfserr_io		cpu_to_be32(NFSERR_IO)
+#define	nfserr_nxio		cpu_to_be32(NFSERR_NXIO)
+#define	nfserr_eagain		cpu_to_be32(NFSERR_EAGAIN)
+#define	nfserr_acces		cpu_to_be32(NFSERR_ACCES)
+#define	nfserr_exist		cpu_to_be32(NFSERR_EXIST)
+#define	nfserr_xdev		cpu_to_be32(NFSERR_XDEV)
+#define	nfserr_nodev		cpu_to_be32(NFSERR_NODEV)
+#define	nfserr_notdir		cpu_to_be32(NFSERR_NOTDIR)
+#define	nfserr_isdir		cpu_to_be32(NFSERR_ISDIR)
+#define	nfserr_inval		cpu_to_be32(NFSERR_INVAL)
+#define	nfserr_fbig		cpu_to_be32(NFSERR_FBIG)
+#define	nfserr_nospc		cpu_to_be32(NFSERR_NOSPC)
+#define	nfserr_rofs		cpu_to_be32(NFSERR_ROFS)
+#define	nfserr_mlink		cpu_to_be32(NFSERR_MLINK)
+#define	nfserr_opnotsupp	cpu_to_be32(NFSERR_OPNOTSUPP)
+#define	nfserr_nametoolong	cpu_to_be32(NFSERR_NAMETOOLONG)
+#define	nfserr_notempty		cpu_to_be32(NFSERR_NOTEMPTY)
+#define	nfserr_dquot		cpu_to_be32(NFSERR_DQUOT)
+#define	nfserr_stale		cpu_to_be32(NFSERR_STALE)
+#define	nfserr_remote		cpu_to_be32(NFSERR_REMOTE)
+#define	nfserr_wflush		cpu_to_be32(NFSERR_WFLUSH)
+#define	nfserr_badhandle	cpu_to_be32(NFSERR_BADHANDLE)
+#define	nfserr_notsync		cpu_to_be32(NFSERR_NOT_SYNC)
+#define	nfserr_badcookie	cpu_to_be32(NFSERR_BAD_COOKIE)
+#define	nfserr_notsupp		cpu_to_be32(NFSERR_NOTSUPP)
+#define	nfserr_toosmall		cpu_to_be32(NFSERR_TOOSMALL)
+#define	nfserr_serverfault	cpu_to_be32(NFSERR_SERVERFAULT)
+#define	nfserr_badtype		cpu_to_be32(NFSERR_BADTYPE)
+#define	nfserr_jukebox		cpu_to_be32(NFSERR_JUKEBOX)
+#define	nfserr_denied		cpu_to_be32(NFSERR_DENIED)
+#define	nfserr_deadlock		cpu_to_be32(NFSERR_DEADLOCK)
+#define nfserr_expired          cpu_to_be32(NFSERR_EXPIRED)
+#define	nfserr_bad_cookie	cpu_to_be32(NFSERR_BAD_COOKIE)
+#define	nfserr_same		cpu_to_be32(NFSERR_SAME)
+#define	nfserr_clid_inuse	cpu_to_be32(NFSERR_CLID_INUSE)
+#define	nfserr_stale_clientid	cpu_to_be32(NFSERR_STALE_CLIENTID)
+#define	nfserr_resource		cpu_to_be32(NFSERR_RESOURCE)
+#define	nfserr_moved		cpu_to_be32(NFSERR_MOVED)
+#define	nfserr_nofilehandle	cpu_to_be32(NFSERR_NOFILEHANDLE)
+#define	nfserr_minor_vers_mismatch	cpu_to_be32(NFSERR_MINOR_VERS_MISMATCH)
+#define nfserr_share_denied	cpu_to_be32(NFSERR_SHARE_DENIED)
+#define nfserr_stale_stateid	cpu_to_be32(NFSERR_STALE_STATEID)
+#define nfserr_old_stateid	cpu_to_be32(NFSERR_OLD_STATEID)
+#define nfserr_bad_stateid	cpu_to_be32(NFSERR_BAD_STATEID)
+#define nfserr_bad_seqid	cpu_to_be32(NFSERR_BAD_SEQID)
+#define	nfserr_symlink		cpu_to_be32(NFSERR_SYMLINK)
+#define	nfserr_not_same		cpu_to_be32(NFSERR_NOT_SAME)
+#define	nfserr_restorefh	cpu_to_be32(NFSERR_RESTOREFH)
+#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_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)
+#define	nfserr_no_grace		cpu_to_be32(NFSERR_NO_GRACE)
+#define	nfserr_reclaim_bad	cpu_to_be32(NFSERR_RECLAIM_BAD)
+#define	nfserr_badname		cpu_to_be32(NFSERR_BADNAME)
+#define	nfserr_cb_path_down	cpu_to_be32(NFSERR_CB_PATH_DOWN)
+#define	nfserr_locked		cpu_to_be32(NFSERR_LOCKED)
+#define	nfserr_wrongsec		cpu_to_be32(NFSERR_WRONGSEC)
+#define nfserr_badiomode		cpu_to_be32(NFS4ERR_BADIOMODE)
+#define nfserr_badlayout		cpu_to_be32(NFS4ERR_BADLAYOUT)
+#define nfserr_bad_session_digest	cpu_to_be32(NFS4ERR_BAD_SESSION_DIGEST)
+#define nfserr_badsession		cpu_to_be32(NFS4ERR_BADSESSION)
+#define nfserr_badslot			cpu_to_be32(NFS4ERR_BADSLOT)
+#define nfserr_complete_already		cpu_to_be32(NFS4ERR_COMPLETE_ALREADY)
+#define nfserr_conn_not_bound_to_session cpu_to_be32(NFS4ERR_CONN_NOT_BOUND_TO_SESSION)
+#define nfserr_deleg_already_wanted	cpu_to_be32(NFS4ERR_DELEG_ALREADY_WANTED)
+#define nfserr_back_chan_busy		cpu_to_be32(NFS4ERR_BACK_CHAN_BUSY)
+#define nfserr_layouttrylater		cpu_to_be32(NFS4ERR_LAYOUTTRYLATER)
+#define nfserr_layoutunavailable	cpu_to_be32(NFS4ERR_LAYOUTUNAVAILABLE)
+#define nfserr_nomatching_layout	cpu_to_be32(NFS4ERR_NOMATCHING_LAYOUT)
+#define nfserr_recallconflict		cpu_to_be32(NFS4ERR_RECALLCONFLICT)
+#define nfserr_unknown_layouttype	cpu_to_be32(NFS4ERR_UNKNOWN_LAYOUTTYPE)
+#define nfserr_seq_misordered		cpu_to_be32(NFS4ERR_SEQ_MISORDERED)
+#define nfserr_sequence_pos		cpu_to_be32(NFS4ERR_SEQUENCE_POS)
+#define nfserr_req_too_big		cpu_to_be32(NFS4ERR_REQ_TOO_BIG)
+#define nfserr_rep_too_big		cpu_to_be32(NFS4ERR_REP_TOO_BIG)
+#define nfserr_rep_too_big_to_cache	cpu_to_be32(NFS4ERR_REP_TOO_BIG_TO_CACHE)
+#define nfserr_retry_uncached_rep	cpu_to_be32(NFS4ERR_RETRY_UNCACHED_REP)
+#define nfserr_unsafe_compound		cpu_to_be32(NFS4ERR_UNSAFE_COMPOUND)
+#define nfserr_too_many_ops		cpu_to_be32(NFS4ERR_TOO_MANY_OPS)
+#define nfserr_op_not_in_session	cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION)
+#define nfserr_hash_alg_unsupp		cpu_to_be32(NFS4ERR_HASH_ALG_UNSUPP)
+#define nfserr_clientid_busy		cpu_to_be32(NFS4ERR_CLIENTID_BUSY)
+#define nfserr_pnfs_io_hole		cpu_to_be32(NFS4ERR_PNFS_IO_HOLE)
+#define nfserr_seq_false_retry		cpu_to_be32(NFS4ERR_SEQ_FALSE_RETRY)
+#define nfserr_bad_high_slot		cpu_to_be32(NFS4ERR_BAD_HIGH_SLOT)
+#define nfserr_deadsession		cpu_to_be32(NFS4ERR_DEADSESSION)
+#define nfserr_encr_alg_unsupp		cpu_to_be32(NFS4ERR_ENCR_ALG_UNSUPP)
+#define nfserr_pnfs_no_layout		cpu_to_be32(NFS4ERR_PNFS_NO_LAYOUT)
+#define nfserr_not_only_op		cpu_to_be32(NFS4ERR_NOT_ONLY_OP)
+#define nfserr_wrong_cred		cpu_to_be32(NFS4ERR_WRONG_CRED)
+#define nfserr_wrong_type		cpu_to_be32(NFS4ERR_WRONG_TYPE)
+#define nfserr_dirdeleg_unavail		cpu_to_be32(NFS4ERR_DIRDELEG_UNAVAIL)
+#define nfserr_reject_deleg		cpu_to_be32(NFS4ERR_REJECT_DELEG)
+#define nfserr_returnconflict		cpu_to_be32(NFS4ERR_RETURNCONFLICT)
+#define nfserr_deleg_revoked		cpu_to_be32(NFS4ERR_DELEG_REVOKED)
 
 /* error codes for internal use */
 /* if a request fails due to kmalloc failure, it gets dropped.
  *  Client should resend eventually
  */
-#define	nfserr_dropit		__constant_htonl(30000)
+#define	nfserr_dropit		cpu_to_be32(30000)
 /* end-of-file indicator in readdir */
-#define	nfserr_eof		__constant_htonl(30001)
+#define	nfserr_eof		cpu_to_be32(30001)
+/* replay detected */
+#define	nfserr_replay_me	cpu_to_be32(11001)
+/* nfs41 replay detected */
+#define	nfserr_replay_cache	cpu_to_be32(11002)
 
 /* Check for dir entries '.' and '..' */
 #define isdotent(n, l)	(l < 3 && n[0] == '.' && (l == 1 || n[1] == '.'))
@@ -300,7 +343,7 @@ extern struct timeval	nfssvc_boot;
  *    TIME_BACKUP   (unlikely to be supported any time soon)
  *    TIME_CREATE   (unlikely to be supported any time soon)
  */
-#define NFSD_SUPPORTED_ATTRS_WORD0                                                          \
+#define NFSD4_SUPPORTED_ATTRS_WORD0                                                         \
 (FATTR4_WORD0_SUPPORTED_ATTRS   | FATTR4_WORD0_TYPE         | FATTR4_WORD0_FH_EXPIRE_TYPE   \
  | FATTR4_WORD0_CHANGE          | FATTR4_WORD0_SIZE         | FATTR4_WORD0_LINK_SUPPORT     \
  | FATTR4_WORD0_SYMLINK_SUPPORT | FATTR4_WORD0_NAMED_ATTR   | FATTR4_WORD0_FSID             \
@@ -312,7 +355,7 @@ extern struct timeval	nfssvc_boot;
  | FATTR4_WORD0_MAXFILESIZE     | FATTR4_WORD0_MAXLINK      | FATTR4_WORD0_MAXNAME          \
  | FATTR4_WORD0_MAXREAD         | FATTR4_WORD0_MAXWRITE     | FATTR4_WORD0_ACL)
 
-#define NFSD_SUPPORTED_ATTRS_WORD1                                                          \
+#define NFSD4_SUPPORTED_ATTRS_WORD1                                                         \
 (FATTR4_WORD1_MODE              | FATTR4_WORD1_NO_TRUNC     | FATTR4_WORD1_NUMLINKS         \
  | FATTR4_WORD1_OWNER	        | FATTR4_WORD1_OWNER_GROUP  | FATTR4_WORD1_RAWDEV           \
  | FATTR4_WORD1_SPACE_AVAIL     | FATTR4_WORD1_SPACE_FREE   | FATTR4_WORD1_SPACE_TOTAL      \
@@ -320,6 +363,35 @@ extern struct timeval	nfssvc_boot;
  | FATTR4_WORD1_TIME_DELTA   | FATTR4_WORD1_TIME_METADATA    \
  | FATTR4_WORD1_TIME_MODIFY     | FATTR4_WORD1_TIME_MODIFY_SET | FATTR4_WORD1_MOUNTED_ON_FILEID)
 
+#define NFSD4_SUPPORTED_ATTRS_WORD2 0
+
+#define NFSD4_1_SUPPORTED_ATTRS_WORD0 \
+	NFSD4_SUPPORTED_ATTRS_WORD0
+
+#define NFSD4_1_SUPPORTED_ATTRS_WORD1 \
+	NFSD4_SUPPORTED_ATTRS_WORD1
+
+#define NFSD4_1_SUPPORTED_ATTRS_WORD2 \
+	(NFSD4_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SUPPATTR_EXCLCREAT)
+
+static inline u32 nfsd_suppattrs0(u32 minorversion)
+{
+	return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD0
+			    : NFSD4_SUPPORTED_ATTRS_WORD0;
+}
+
+static inline u32 nfsd_suppattrs1(u32 minorversion)
+{
+	return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD1
+			    : NFSD4_SUPPORTED_ATTRS_WORD1;
+}
+
+static inline u32 nfsd_suppattrs2(u32 minorversion)
+{
+	return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD2
+			    : NFSD4_SUPPORTED_ATTRS_WORD2;
+}
+
 /* These will return ERR_INVAL if specified in GETATTR or READDIR. */
 #define NFSD_WRITEONLY_ATTRS_WORD1							    \
 (FATTR4_WORD1_TIME_ACCESS_SET   | FATTR4_WORD1_TIME_MODIFY_SET)
@@ -330,6 +402,19 @@ extern struct timeval	nfssvc_boot;
 #define NFSD_WRITEABLE_ATTRS_WORD1                                                          \
 (FATTR4_WORD1_MODE              | FATTR4_WORD1_OWNER         | FATTR4_WORD1_OWNER_GROUP     \
  | FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET)
+#define NFSD_WRITEABLE_ATTRS_WORD2 0
+
+#define NFSD_SUPPATTR_EXCLCREAT_WORD0 \
+	NFSD_WRITEABLE_ATTRS_WORD0
+/*
+ * we currently store the exclusive create verifier in the v_{a,m}time
+ * attributes so the client can't set these at create time using EXCLUSIVE4_1
+ */
+#define NFSD_SUPPATTR_EXCLCREAT_WORD1 \
+	(NFSD_WRITEABLE_ATTRS_WORD1 & \
+	 ~(FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET))
+#define NFSD_SUPPATTR_EXCLCREAT_WORD2 \
+	NFSD_WRITEABLE_ATTRS_WORD2
 
 #endif /* CONFIG_NFSD_V4 */
 

include/linux/nfsd/nfsfh.h

@@ -269,6 +269,13 @@ fh_copy(struct svc_fh *dst, struct svc_fh *src)
 	return dst;
 }
 
+static inline void
+fh_copy_shallow(struct knfsd_fh *dst, struct knfsd_fh *src)
+{
+	dst->fh_size = src->fh_size;
+	memcpy(&dst->fh_base, &src->fh_base, src->fh_size);
+}
+
 static __inline__ struct svc_fh *
 fh_init(struct svc_fh *fhp, int maxsize)
 {

include/linux/nfsd/state.h

@@ -66,8 +66,7 @@ struct nfs4_cb_recall {
 	u32			cbr_ident;
 	int			cbr_trunc;
 	stateid_t		cbr_stateid;
-	u32			cbr_fhlen;
-	char			cbr_fhval[NFS4_FHSIZE];
+	struct knfsd_fh		cbr_fh;
 	struct nfs4_delegation	*cbr_dp;
 };
 
@@ -86,8 +85,7 @@ struct nfs4_delegation {
 };
 
 #define dl_stateid      dl_recall.cbr_stateid
-#define dl_fhlen        dl_recall.cbr_fhlen
-#define dl_fhval        dl_recall.cbr_fhval
+#define dl_fh           dl_recall.cbr_fh
 
 /* client delegation callback info */
 struct nfs4_callback {
@@ -101,6 +99,64 @@ struct nfs4_callback {
 	struct rpc_clnt *       cb_client;
 };
 
+/* Maximum number of slots per session. 128 is useful for long haul TCP */
+#define NFSD_MAX_SLOTS_PER_SESSION	128
+/* Maximum number of pages per slot cache entry */
+#define NFSD_PAGES_PER_SLOT	1
+/* Maximum number of operations per session compound */
+#define NFSD_MAX_OPS_PER_COMPOUND	16
+
+struct nfsd4_cache_entry {
+	__be32		ce_status;
+	struct kvec	ce_datav; /* encoded NFSv4.1 data in rq_res.head[0] */
+	struct page	*ce_respages[NFSD_PAGES_PER_SLOT + 1];
+	int		ce_cachethis;
+	short		ce_resused;
+	int		ce_opcnt;
+	int		ce_rpchdrlen;
+};
+
+struct nfsd4_slot {
+	bool				sl_inuse;
+	u32				sl_seqid;
+	struct nfsd4_cache_entry	sl_cache_entry;
+};
+
+struct nfsd4_session {
+	struct kref		se_ref;
+	struct list_head	se_hash;	/* hash by sessionid */
+	struct list_head	se_perclnt;
+	u32			se_flags;
+	struct nfs4_client	*se_client;	/* for expire_client */
+	struct nfs4_sessionid	se_sessionid;
+	u32			se_fmaxreq_sz;
+	u32			se_fmaxresp_sz;
+	u32			se_fmaxresp_cached;
+	u32			se_fmaxops;
+	u32			se_fnumslots;
+	struct nfsd4_slot	se_slots[];	/* forward channel slots */
+};
+
+static inline void
+nfsd4_put_session(struct nfsd4_session *ses)
+{
+	extern void free_session(struct kref *kref);
+	kref_put(&ses->se_ref, free_session);
+}
+
+static inline void
+nfsd4_get_session(struct nfsd4_session *ses)
+{
+	kref_get(&ses->se_ref);
+}
+
+/* formatted contents of nfs4_sessionid */
+struct nfsd4_sessionid {
+	clientid_t	clientid;
+	u32		sequence;
+	u32		reserved;
+};
+
 #define HEXDIR_LEN     33 /* hex version of 16 byte md5 of cl_name plus '\0' */
 
 /*
@@ -132,6 +188,12 @@ struct nfs4_client {
 	struct nfs4_callback	cl_callback;    /* callback info */
 	atomic_t		cl_count;	/* ref count */
 	u32			cl_firststate;	/* recovery dir creation */
+
+	/* for nfs41 */
+	struct list_head	cl_sessions;
+	struct nfsd4_slot	cl_slot;	/* create_session slot */
+	u32			cl_exchange_flags;
+	struct nfs4_sessionid	cl_sessionid;
 };
 
 /* struct nfs4_client_reset
@@ -168,8 +230,7 @@ struct nfs4_replay {
 	unsigned int		rp_buflen;
 	char			*rp_buf;
 	unsigned		intrp_allocated;
-	int			rp_openfh_len;
-	char			rp_openfh[NFS4_FHSIZE];
+	struct knfsd_fh		rp_openfh;
 	char			rp_ibuf[NFSD4_REPLAY_ISIZE];
 };
 
@@ -217,7 +278,7 @@ struct nfs4_stateowner {
 *      share_acces, share_deny on the file.
 */
 struct nfs4_file {
-	struct kref		fi_ref;
+	atomic_t		fi_ref;
 	struct list_head        fi_hash;    /* hash by "struct inode *" */
 	struct list_head        fi_stateids;
 	struct list_head	fi_delegations;
@@ -259,14 +320,13 @@ struct nfs4_stateid {
 };
 
 /* flags for preprocess_seqid_op() */
-#define CHECK_FH                0x00000001
+#define HAS_SESSION             0x00000001
 #define CONFIRM                 0x00000002
 #define OPEN_STATE              0x00000004
 #define LOCK_STATE              0x00000008
 #define RD_STATE	        0x00000010
 #define WR_STATE	        0x00000020
 #define CLOSE_STATE             0x00000040
-#define DELEG_RET               0x00000080
 
 #define seqid_mutating_err(err)                       \
 	(((err) != nfserr_stale_clientid) &&    \
@@ -274,7 +334,9 @@ struct nfs4_stateid {
 	((err) != nfserr_stale_stateid) &&      \
 	((err) != nfserr_bad_stateid))
 
-extern __be32 nfs4_preprocess_stateid_op(struct svc_fh *current_fh,
+struct nfsd4_compound_state;
+
+extern __be32 nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate,
 		stateid_t *stateid, int flags, struct file **filp);
 extern void nfs4_lock_state(void);
 extern void nfs4_unlock_state(void);
@@ -290,7 +352,7 @@ extern void nfsd4_init_recdir(char *recdir_name);
 extern int nfsd4_recdir_load(void);
 extern void nfsd4_shutdown_recdir(void);
 extern int nfs4_client_to_reclaim(const char *name);
-extern int nfs4_has_reclaimed_state(const char *name);
+extern int nfs4_has_reclaimed_state(const char *name, bool use_exchange_id);
 extern void nfsd4_recdir_purge_old(void);
 extern int nfsd4_create_clid_dir(struct nfs4_client *clp);
 extern void nfsd4_remove_clid_dir(struct nfs4_client *clp);

include/linux/nfsd/stats.h

@@ -11,6 +11,11 @@
 
 #include <linux/nfs4.h>
 
+/* thread usage wraps very million seconds (approx one fortnight) */
+#define	NFSD_USAGE_WRAP	(HZ*1000000)
+
+#ifdef __KERNEL__
+
 struct nfsd_stats {
 	unsigned int	rchits;		/* repcache hits */
 	unsigned int	rcmisses;	/* repcache hits */
@@ -35,10 +40,6 @@ struct nfsd_stats {
 
 };
 
-/* thread usage wraps very million seconds (approx one fortnight) */
-#define	NFSD_USAGE_WRAP	(HZ*1000000)
-
-#ifdef __KERNEL__
 
 extern struct nfsd_stats	nfsdstats;
 extern struct svc_stat		nfsd_svcstats;

include/linux/nfsd/xdr4.h

@@ -45,10 +45,22 @@
 #define XDR_LEN(n)                     (((n) + 3) & ~3)
 
 struct nfsd4_compound_state {
-	struct svc_fh current_fh;
-	struct svc_fh save_fh;
-	struct nfs4_stateowner *replay_owner;
-};
+	struct svc_fh		current_fh;
+	struct svc_fh		save_fh;
+	struct nfs4_stateowner	*replay_owner;
+	/* For sessions DRC */
+	struct nfsd4_session	*session;
+	struct nfsd4_slot	*slot;
+	__be32			*statp;
+	size_t			iovlen;
+	u32			minorversion;
+	u32			status;
+};
+
+static inline bool nfsd4_has_session(struct nfsd4_compound_state *cs)
+{
+	return cs->slot != NULL;
+}
 
 struct nfsd4_change_info {
 	u32		atomic;
@@ -90,7 +102,7 @@ struct nfsd4_create {
 			u32 specdata2;
 		} dev;    /* NF4BLK, NF4CHR */
 	} u;
-	u32		cr_bmval[2];        /* request */
+	u32		cr_bmval[3];        /* request */
 	struct iattr	cr_iattr;           /* request */
 	struct nfsd4_change_info  cr_cinfo; /* response */
 	struct nfs4_acl *cr_acl;
@@ -105,7 +117,7 @@ struct nfsd4_delegreturn {
 };
 
 struct nfsd4_getattr {
-	u32		ga_bmval[2];        /* request */
+	u32		ga_bmval[3];        /* request */
 	struct svc_fh	*ga_fhp;            /* response */
 };
 
@@ -206,11 +218,9 @@ struct nfsd4_open {
 	stateid_t       op_delegate_stateid; /* request - response */
 	u32		op_create;     	    /* request */
 	u32		op_createmode;      /* request */
-	u32		op_bmval[2];        /* request */
-	union {                             /* request */
-		struct iattr	iattr;                      /* UNCHECKED4,GUARDED4 */
-		nfs4_verifier	verf;                                /* EXCLUSIVE4 */
-	} u;
+	u32		op_bmval[3];        /* request */
+	struct iattr	iattr;              /* UNCHECKED4, GUARDED4, EXCLUSIVE4_1 */
+	nfs4_verifier	verf;               /* EXCLUSIVE4 */
 	clientid_t	op_clientid;        /* request */
 	struct xdr_netobj op_owner;           /* request */
 	u32		op_seqid;           /* request */
@@ -224,8 +234,8 @@ struct nfsd4_open {
 	struct nfs4_stateowner *op_stateowner; /* used during processing */
 	struct nfs4_acl *op_acl;
 };
-#define op_iattr	u.iattr
-#define op_verf		u.verf
+#define op_iattr	iattr
+#define op_verf		verf
 
 struct nfsd4_open_confirm {
 	stateid_t	oc_req_stateid		/* request */;
@@ -259,7 +269,7 @@ struct nfsd4_readdir {
 	nfs4_verifier	rd_verf;            /* request */
 	u32		rd_dircount;        /* request */
 	u32		rd_maxcount;        /* request */
-	u32		rd_bmval[2];        /* request */
+	u32		rd_bmval[3];        /* request */
 	struct svc_rqst *rd_rqstp;          /* response */
 	struct svc_fh * rd_fhp;             /* response */
 
@@ -301,7 +311,7 @@ struct nfsd4_secinfo {
 
 struct nfsd4_setattr {
 	stateid_t	sa_stateid;         /* request */
-	u32		sa_bmval[2];        /* request */
+	u32		sa_bmval[3];        /* request */
 	struct iattr	sa_iattr;           /* request */
 	struct nfs4_acl *sa_acl;
 };
@@ -327,7 +337,7 @@ struct nfsd4_setclientid_confirm {
 
 /* also used for NVERIFY */
 struct nfsd4_verify {
-	u32		ve_bmval[2];        /* request */
+	u32		ve_bmval[3];        /* request */
 	u32		ve_attrlen;         /* request */
 	char *		ve_attrval;         /* request */
 };
@@ -344,6 +354,54 @@ struct nfsd4_write {
 	nfs4_verifier	wr_verifier;        /* response */
 };
 
+struct nfsd4_exchange_id {
+	nfs4_verifier	verifier;
+	struct xdr_netobj clname;
+	u32		flags;
+	clientid_t	clientid;
+	u32		seqid;
+	int		spa_how;
+};
+
+struct nfsd4_channel_attrs {
+	u32		headerpadsz;
+	u32		maxreq_sz;
+	u32		maxresp_sz;
+	u32		maxresp_cached;
+	u32		maxops;
+	u32		maxreqs;
+	u32		nr_rdma_attrs;
+	u32		rdma_attrs;
+};
+
+struct nfsd4_create_session {
+	clientid_t		clientid;
+	struct nfs4_sessionid	sessionid;
+	u32			seqid;
+	u32			flags;
+	struct nfsd4_channel_attrs fore_channel;
+	struct nfsd4_channel_attrs back_channel;
+	u32			callback_prog;
+	u32			uid;
+	u32			gid;
+};
+
+struct nfsd4_sequence {
+	struct nfs4_sessionid	sessionid;		/* request/response */
+	u32			seqid;			/* request/response */
+	u32			slotid;			/* request/response */
+	u32			maxslots;		/* request/response */
+	u32			cachethis;		/* request */
+#if 0
+	u32			target_maxslots;	/* response */
+	u32			status_flags;		/* response */
+#endif /* not yet */
+};
+
+struct nfsd4_destroy_session {
+	struct nfs4_sessionid	sessionid;
+};
+
 struct nfsd4_op {
 	int					opnum;
 	__be32					status;
@@ -378,6 +436,12 @@ struct nfsd4_op {
 		struct nfsd4_verify		verify;
 		struct nfsd4_write		write;
 		struct nfsd4_release_lockowner	release_lockowner;
+
+		/* NFSv4.1 */
+		struct nfsd4_exchange_id	exchange_id;
+		struct nfsd4_create_session	create_session;
+		struct nfsd4_destroy_session	destroy_session;
+		struct nfsd4_sequence		sequence;
 	} u;
 	struct nfs4_replay *			replay;
 };
@@ -416,9 +480,22 @@ struct nfsd4_compoundres {
 	u32				taglen;
 	char *				tag;
 	u32				opcnt;
-	__be32 *			tagp; /* where to encode tag and  opcount */
+	__be32 *			tagp; /* tag, opcount encode location */
+	struct nfsd4_compound_state	cstate;
 };
 
+static inline bool nfsd4_is_solo_sequence(struct nfsd4_compoundres *resp)
+{
+	struct nfsd4_compoundargs *args = resp->rqstp->rq_argp;
+	return args->opcnt == 1;
+}
+
+static inline bool nfsd4_not_cached(struct nfsd4_compoundres *resp)
+{
+	return !resp->cstate.slot->sl_cache_entry.ce_cachethis ||
+			nfsd4_is_solo_sequence(resp);
+}
+
 #define NFS4_SVC_XDRSIZE		sizeof(struct nfsd4_compoundargs)
 
 static inline void
@@ -448,7 +525,23 @@ extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp,
 extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *,
 		struct nfsd4_setclientid_confirm *setclientid_confirm);
-extern __be32 nfsd4_process_open1(struct nfsd4_open *open);
+extern void nfsd4_store_cache_entry(struct nfsd4_compoundres *resp);
+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_create_session(struct svc_rqst *,
+		struct nfsd4_compound_state *,
+		struct nfsd4_create_session *);
+extern __be32 nfsd4_sequence(struct svc_rqst *,
+		struct nfsd4_compound_state *,
+		struct nfsd4_sequence *);
+extern __be32 nfsd4_destroy_session(struct svc_rqst *,
+		struct nfsd4_compound_state *,
+		struct nfsd4_destroy_session *);
+extern __be32 nfsd4_process_open1(struct nfsd4_compound_state *,
+		struct nfsd4_open *open);
 extern __be32 nfsd4_process_open2(struct svc_rqst *rqstp,
 		struct svc_fh *current_fh, struct nfsd4_open *open);
 extern __be32 nfsd4_open_confirm(struct svc_rqst *rqstp,

include/linux/sunrpc/svc.h

@@ -24,6 +24,15 @@
  */
 typedef int		(*svc_thread_fn)(void *);
 
+/* statistics for svc_pool structures */
+struct svc_pool_stats {
+	unsigned long	packets;
+	unsigned long	sockets_queued;
+	unsigned long	threads_woken;
+	unsigned long	overloads_avoided;
+	unsigned long	threads_timedout;
+};
+
 /*
  *
  * RPC service thread pool.
@@ -41,6 +50,8 @@ struct svc_pool {
 	struct list_head	sp_sockets;	/* pending sockets */
 	unsigned int		sp_nrthreads;	/* # of threads in pool */
 	struct list_head	sp_all_threads;	/* all server threads */
+	int			sp_nwaking;	/* number of threads woken but not yet active */
+	struct svc_pool_stats	sp_stats;	/* statistics on pool operation */
 } ____cacheline_aligned_in_smp;
 
 /*
@@ -83,6 +94,8 @@ struct svc_serv {
 	struct module *		sv_module;	/* optional module to count when
 						 * adding threads */
 	svc_thread_fn		sv_function;	/* main function for threads */
+	unsigned int		sv_drc_max_pages; /* Total pages for DRC */
+	unsigned int		sv_drc_pages_used;/* DRC pages used */
 };
 
 /*
@@ -218,6 +231,7 @@ struct svc_rqst {
 	struct svc_cred		rq_cred;	/* auth info */
 	void *			rq_xprt_ctxt;	/* transport specific context ptr */
 	struct svc_deferred_req*rq_deferred;	/* deferred request we are replaying */
+	int			rq_usedeferral;	/* use deferral */
 
 	size_t			rq_xprt_hlen;	/* xprt header len */
 	struct xdr_buf		rq_arg;
@@ -263,6 +277,7 @@ struct svc_rqst {
 						 * cache pages */
 	wait_queue_head_t	rq_wait;	/* synchronization */
 	struct task_struct	*rq_task;	/* service thread */
+	int			rq_waking;	/* 1 if thread is being woken */
 };
 
 /*
@@ -393,6 +408,7 @@ struct svc_serv *  svc_create_pooled(struct svc_program *, unsigned int,
 			void (*shutdown)(struct svc_serv *),
 			svc_thread_fn, struct module *);
 int		   svc_set_num_threads(struct svc_serv *, struct svc_pool *, int);
+int		   svc_pool_stats_open(struct svc_serv *serv, struct file *file);
 void		   svc_destroy(struct svc_serv *);
 int		   svc_process(struct svc_rqst *);
 int		   svc_register(const struct svc_serv *, const int,

include/linux/sunrpc/xdr.h

@@ -69,27 +69,27 @@ struct xdr_buf {
  * pre-xdr'ed macros.
  */
 
-#define	xdr_zero	__constant_htonl(0)
-#define	xdr_one		__constant_htonl(1)
-#define	xdr_two		__constant_htonl(2)
-
-#define	rpc_success		__constant_htonl(RPC_SUCCESS)
-#define	rpc_prog_unavail	__constant_htonl(RPC_PROG_UNAVAIL)
-#define	rpc_prog_mismatch	__constant_htonl(RPC_PROG_MISMATCH)
-#define	rpc_proc_unavail	__constant_htonl(RPC_PROC_UNAVAIL)
-#define	rpc_garbage_args	__constant_htonl(RPC_GARBAGE_ARGS)
-#define	rpc_system_err		__constant_htonl(RPC_SYSTEM_ERR)
-#define	rpc_drop_reply		__constant_htonl(RPC_DROP_REPLY)
-
-#define	rpc_auth_ok		__constant_htonl(RPC_AUTH_OK)
-#define	rpc_autherr_badcred	__constant_htonl(RPC_AUTH_BADCRED)
-#define	rpc_autherr_rejectedcred __constant_htonl(RPC_AUTH_REJECTEDCRED)
-#define	rpc_autherr_badverf	__constant_htonl(RPC_AUTH_BADVERF)
-#define	rpc_autherr_rejectedverf __constant_htonl(RPC_AUTH_REJECTEDVERF)
-#define	rpc_autherr_tooweak	__constant_htonl(RPC_AUTH_TOOWEAK)
-#define	rpcsec_gsserr_credproblem	__constant_htonl(RPCSEC_GSS_CREDPROBLEM)
-#define	rpcsec_gsserr_ctxproblem	__constant_htonl(RPCSEC_GSS_CTXPROBLEM)
-#define	rpc_autherr_oldseqnum	__constant_htonl(101)
+#define	xdr_zero	cpu_to_be32(0)
+#define	xdr_one		cpu_to_be32(1)
+#define	xdr_two		cpu_to_be32(2)
+
+#define	rpc_success		cpu_to_be32(RPC_SUCCESS)
+#define	rpc_prog_unavail	cpu_to_be32(RPC_PROG_UNAVAIL)
+#define	rpc_prog_mismatch	cpu_to_be32(RPC_PROG_MISMATCH)
+#define	rpc_proc_unavail	cpu_to_be32(RPC_PROC_UNAVAIL)
+#define	rpc_garbage_args	cpu_to_be32(RPC_GARBAGE_ARGS)
+#define	rpc_system_err		cpu_to_be32(RPC_SYSTEM_ERR)
+#define	rpc_drop_reply		cpu_to_be32(RPC_DROP_REPLY)
+
+#define	rpc_auth_ok		cpu_to_be32(RPC_AUTH_OK)
+#define	rpc_autherr_badcred	cpu_to_be32(RPC_AUTH_BADCRED)
+#define	rpc_autherr_rejectedcred cpu_to_be32(RPC_AUTH_REJECTEDCRED)
+#define	rpc_autherr_badverf	cpu_to_be32(RPC_AUTH_BADVERF)
+#define	rpc_autherr_rejectedverf cpu_to_be32(RPC_AUTH_REJECTEDVERF)
+#define	rpc_autherr_tooweak	cpu_to_be32(RPC_AUTH_TOOWEAK)
+#define	rpcsec_gsserr_credproblem	cpu_to_be32(RPCSEC_GSS_CREDPROBLEM)
+#define	rpcsec_gsserr_ctxproblem	cpu_to_be32(RPCSEC_GSS_CTXPROBLEM)
+#define	rpc_autherr_oldseqnum	cpu_to_be32(101)
 
 /*
  * Miscellaneous XDR helper functions

net/sunrpc/svc.c

@@ -1008,6 +1008,8 @@ svc_process(struct svc_rqst *rqstp)
 	rqstp->rq_res.tail[0].iov_len = 0;
 	/* Will be turned off only in gss privacy case: */
 	rqstp->rq_splice_ok = 1;
+	/* Will be turned off only when NFSv4 Sessions are used */
+	rqstp->rq_usedeferral = 1;
 
 	/* Setup reply header */
 	rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp);
@@ -1078,7 +1080,6 @@ svc_process(struct svc_rqst *rqstp)
 	procp = versp->vs_proc + proc;
 	if (proc >= versp->vs_nproc || !procp->pc_func)
 		goto err_bad_proc;
-	rqstp->rq_server   = serv;
 	rqstp->rq_procinfo = procp;
 
 	/* Syntactic check complete */

net/sunrpc/svc_xprt.c

@@ -14,6 +14,8 @@
 
 #define RPCDBG_FACILITY	RPCDBG_SVCXPRT
 
+#define SVC_MAX_WAKING 5
+
 static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt);
 static int svc_deferred_recv(struct svc_rqst *rqstp);
 static struct cache_deferred_req *svc_defer(struct cache_req *req);
@@ -301,6 +303,7 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
 	struct svc_pool *pool;
 	struct svc_rqst	*rqstp;
 	int cpu;
+	int thread_avail;
 
 	if (!(xprt->xpt_flags &
 	      ((1<<XPT_CONN)|(1<<XPT_DATA)|(1<<XPT_CLOSE)|(1<<XPT_DEFERRED))))
@@ -312,18 +315,14 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
 
 	spin_lock_bh(&pool->sp_lock);
 
-	if (!list_empty(&pool->sp_threads) &&
-	    !list_empty(&pool->sp_sockets))
-		printk(KERN_ERR
-		       "svc_xprt_enqueue: "
-		       "threads and transports both waiting??\n");
-
 	if (test_bit(XPT_DEAD, &xprt->xpt_flags)) {
 		/* Don't enqueue dead transports */
 		dprintk("svc: transport %p is dead, not enqueued\n", xprt);
 		goto out_unlock;
 	}
 
+	pool->sp_stats.packets++;
+
 	/* Mark transport as busy. It will remain in this state until
 	 * the provider calls svc_xprt_received. We update XPT_BUSY
 	 * atomically because it also guards against trying to enqueue
@@ -356,7 +355,15 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
 	}
 
  process:
-	if (!list_empty(&pool->sp_threads)) {
+	/* Work out whether threads are available */
+	thread_avail = !list_empty(&pool->sp_threads);	/* threads are asleep */
+	if (pool->sp_nwaking >= SVC_MAX_WAKING) {
+		/* too many threads are runnable and trying to wake up */
+		thread_avail = 0;
+		pool->sp_stats.overloads_avoided++;
+	}
+
+	if (thread_avail) {
 		rqstp = list_entry(pool->sp_threads.next,
 				   struct svc_rqst,
 				   rq_list);
@@ -371,11 +378,15 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
 		svc_xprt_get(xprt);
 		rqstp->rq_reserved = serv->sv_max_mesg;
 		atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved);
+		rqstp->rq_waking = 1;
+		pool->sp_nwaking++;
+		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);
 	}
 
@@ -588,6 +599,7 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 	int			pages;
 	struct xdr_buf		*arg;
 	DECLARE_WAITQUEUE(wait, current);
+	long			time_left;
 
 	dprintk("svc: server %p waiting for data (to = %ld)\n",
 		rqstp, timeout);
@@ -636,6 +648,11 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 		return -EINTR;
 
 	spin_lock_bh(&pool->sp_lock);
+	if (rqstp->rq_waking) {
+		rqstp->rq_waking = 0;
+		pool->sp_nwaking--;
+		BUG_ON(pool->sp_nwaking < 0);
+	}
 	xprt = svc_xprt_dequeue(pool);
 	if (xprt) {
 		rqstp->rq_xprt = xprt;
@@ -668,12 +685,14 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 		add_wait_queue(&rqstp->rq_wait, &wait);
 		spin_unlock_bh(&pool->sp_lock);
 
-		schedule_timeout(timeout);
+		time_left = schedule_timeout(timeout);
 
 		try_to_freeze();
 
 		spin_lock_bh(&pool->sp_lock);
 		remove_wait_queue(&rqstp->rq_wait, &wait);
+		if (!time_left)
+			pool->sp_stats.threads_timedout++;
 
 		xprt = rqstp->rq_xprt;
 		if (!xprt) {
@@ -958,7 +977,7 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req)
 	struct svc_rqst *rqstp = container_of(req, struct svc_rqst, rq_chandle);
 	struct svc_deferred_req *dr;
 
-	if (rqstp->rq_arg.page_len)
+	if (rqstp->rq_arg.page_len || !rqstp->rq_usedeferral)
 		return NULL; /* if more than a page, give up FIXME */
 	if (rqstp->rq_deferred) {
 		dr = rqstp->rq_deferred;
@@ -1112,3 +1131,93 @@ int svc_xprt_names(struct svc_serv *serv, char *buf, int buflen)
 	return totlen;
 }
 EXPORT_SYMBOL_GPL(svc_xprt_names);
+
+
+/*----------------------------------------------------------------------------*/
+
+static void *svc_pool_stats_start(struct seq_file *m, loff_t *pos)
+{
+	unsigned int pidx = (unsigned int)*pos;
+	struct svc_serv *serv = m->private;
+
+	dprintk("svc_pool_stats_start, *pidx=%u\n", pidx);
+
+	lock_kernel();
+	/* bump up the pseudo refcount while traversing */
+	svc_get(serv);
+	unlock_kernel();
+
+	if (!pidx)
+		return SEQ_START_TOKEN;
+	return (pidx > serv->sv_nrpools ? NULL : &serv->sv_pools[pidx-1]);
+}
+
+static void *svc_pool_stats_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	struct svc_pool *pool = p;
+	struct svc_serv *serv = m->private;
+
+	dprintk("svc_pool_stats_next, *pos=%llu\n", *pos);
+
+	if (p == SEQ_START_TOKEN) {
+		pool = &serv->sv_pools[0];
+	} else {
+		unsigned int pidx = (pool - &serv->sv_pools[0]);
+		if (pidx < serv->sv_nrpools-1)
+			pool = &serv->sv_pools[pidx+1];
+		else
+			pool = NULL;
+	}
+	++*pos;
+	return pool;
+}
+
+static void svc_pool_stats_stop(struct seq_file *m, void *p)
+{
+	struct svc_serv *serv = m->private;
+
+	lock_kernel();
+	/* this function really, really should have been called svc_put() */
+	svc_destroy(serv);
+	unlock_kernel();
+}
+
+static int svc_pool_stats_show(struct seq_file *m, void *p)
+{
+	struct svc_pool *pool = p;
+
+	if (p == SEQ_START_TOKEN) {
+		seq_puts(m, "# pool packets-arrived sockets-enqueued threads-woken overloads-avoided threads-timedout\n");
+		return 0;
+	}
+
+	seq_printf(m, "%u %lu %lu %lu %lu %lu\n",
+		pool->sp_id,
+		pool->sp_stats.packets,
+		pool->sp_stats.sockets_queued,
+		pool->sp_stats.threads_woken,
+		pool->sp_stats.overloads_avoided,
+		pool->sp_stats.threads_timedout);
+
+	return 0;
+}
+
+static const struct seq_operations svc_pool_stats_seq_ops = {
+	.start	= svc_pool_stats_start,
+	.next	= svc_pool_stats_next,
+	.stop	= svc_pool_stats_stop,
+	.show	= svc_pool_stats_show,
+};
+
+int svc_pool_stats_open(struct svc_serv *serv, struct file *file)
+{
+	int err;
+
+	err = seq_open(file, &svc_pool_stats_seq_ops);
+	if (!err)
+		((struct seq_file *) file->private_data)->private = serv;
+	return err;
+}
+EXPORT_SYMBOL(svc_pool_stats_open);
+
+/*----------------------------------------------------------------------------*/

net/sunrpc/svcsock.c

@@ -345,7 +345,6 @@ static void svc_sock_setbufsize(struct socket *sock, unsigned int snd,
 	lock_sock(sock->sk);
 	sock->sk->sk_sndbuf = snd * 2;
 	sock->sk->sk_rcvbuf = rcv * 2;
-	sock->sk->sk_userlocks |= SOCK_SNDBUF_LOCK|SOCK_RCVBUF_LOCK;
 	release_sock(sock->sk);
 #endif
 }
@@ -797,23 +796,6 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
 		test_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags),
 		test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags));
 
-	if (test_and_clear_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags))
-		/* sndbuf needs to have room for one request
-		 * per thread, otherwise we can stall even when the
-		 * network isn't a bottleneck.
-		 *
-		 * We count all threads rather than threads in a
-		 * particular pool, which provides an upper bound
-		 * on the number of threads which will access the socket.
-		 *
-		 * rcvbuf just needs to be able to hold a few requests.
-		 * Normally they will be removed from the queue
-		 * as soon a a complete request arrives.
-		 */
-		svc_sock_setbufsize(svsk->sk_sock,
-				    (serv->sv_nrthreads+3) * serv->sv_max_mesg,
-				    3 * serv->sv_max_mesg);
-
 	clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 
 	/* Receive data. If we haven't got the record length yet, get
@@ -1061,15 +1043,6 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv)
 
 		tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF;
 
-		/* initialise setting must have enough space to
-		 * receive and respond to one request.
-		 * svc_tcp_recvfrom will re-adjust if necessary
-		 */
-		svc_sock_setbufsize(svsk->sk_sock,
-				    3 * svsk->sk_xprt.xpt_server->sv_max_mesg,
-				    3 * svsk->sk_xprt.xpt_server->sv_max_mesg);
-
-		set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
 		set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 		if (sk->sk_state != TCP_ESTABLISHED)
 			set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
@@ -1139,8 +1112,14 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 	/* Initialize the socket */
 	if (sock->type == SOCK_DGRAM)
 		svc_udp_init(svsk, serv);
-	else
+	else {
+		/* initialise setting must have enough space to
+		 * receive and respond to one request.
+		 */
+		svc_sock_setbufsize(svsk->sk_sock, 4 * serv->sv_max_mesg,
+					4 * serv->sv_max_mesg);
 		svc_tcp_init(svsk, serv);
+	}
 
 	dprintk("svc: svc_setup_socket created %p (inet %p)\n",
 				svsk, svsk->sk_sk);