Fixed MTP to work with TWRP

fs/nfsd/Kconfig

@@ -0,0 +1,106 @@
+config NFSD
+	tristate "NFS server support"
+	depends on INET
+	depends on FILE_LOCKING
+	select LOCKD
+	select SUNRPC
+	select EXPORTFS
+	select NFS_ACL_SUPPORT if NFSD_V2_ACL
+	help
+	  Choose Y here if you want to allow other computers to access
+	  files residing on this system using Sun's Network File System
+	  protocol.  To compile the NFS server support as a module,
+	  choose M here: the module will be called nfsd.
+
+	  You may choose to use a user-space NFS server instead, in which
+	  case you can choose N here.
+
+	  To export local file systems using NFS, you also need to install
+	  user space programs which can be found in the Linux nfs-utils
+	  package, available from http://linux-nfs.org/.  More detail about
+	  the Linux NFS server implementation is available via the
+	  exports(5) man page.
+
+	  Below you can choose which versions of the NFS protocol are
+	  available to clients mounting the NFS server on this system.
+	  Support for NFS version 2 (RFC 1094) is always available when
+	  CONFIG_NFSD is selected.
+
+	  If unsure, say N.
+
+config NFSD_V2_ACL
+	bool
+	depends on NFSD
+
+config NFSD_V3
+	bool "NFS server support for NFS version 3"
+	depends on NFSD
+	help
+	  This option enables support in your system's NFS server for
+	  version 3 of the NFS protocol (RFC 1813).
+
+	  If unsure, say Y.
+
+config NFSD_V3_ACL
+	bool "NFS server support for the NFSv3 ACL protocol extension"
+	depends on NFSD_V3
+	select NFSD_V2_ACL
+	help
+	  Solaris NFS servers support an auxiliary NFSv3 ACL protocol that
+	  never became an official part of the NFS version 3 protocol.
+	  This protocol extension allows applications on NFS clients to
+	  manipulate POSIX Access Control Lists on files residing on NFS
+	  servers.  NFS servers enforce POSIX ACLs on local files whether
+	  this protocol is available or not.
+
+	  This option enables support in your system's NFS server for the
+	  NFSv3 ACL protocol extension allowing NFS clients to manipulate
+	  POSIX ACLs on files exported by your system's NFS server.  NFS
+	  clients which support the Solaris NFSv3 ACL protocol can then
+	  access and modify ACLs on your NFS server.
+
+	  To store ACLs on your NFS server, you also need to enable ACL-
+	  related CONFIG options for your local file systems of choice.
+
+	  If unsure, say N.
+
+config NFSD_V4
+	bool "NFS server support for NFS version 4"
+	depends on NFSD && PROC_FS
+	select NFSD_V3
+	select FS_POSIX_ACL
+	select SUNRPC_GSS
+	select CRYPTO
+	select GRACE_PERIOD
+	help
+	  This option enables support in your system's NFS server for
+	  version 4 of the NFS protocol (RFC 3530).
+
+	  To export files using NFSv4, you need to install additional user
+	  space programs which can be found in the Linux nfs-utils package,
+	  available from http://linux-nfs.org/.
+
+	  If unsure, say N.
+
+config NFSD_V4_SECURITY_LABEL
+	bool "Provide Security Label support for NFSv4 server"
+	depends on NFSD_V4 && SECURITY
+	help
+
+	Say Y here if you want enable fine-grained security label attribute
+	support for NFS version 4.  Security labels allow security modules like
+	SELinux and Smack to label files to facilitate enforcement of their policies.
+	Without this an NFSv4 mount will have the same label on each file.
+
+	If you do not wish to enable fine-grained security labels SELinux or
+	Smack policies on NFSv4 files, say N.
+
+config NFSD_FAULT_INJECTION
+	bool "NFS server manual fault injection"
+	depends on NFSD_V4 && DEBUG_KERNEL
+	help
+	  This option enables support for manually injecting faults
+	  into the NFS server.  This is intended to be used for
+	  testing error recovery on the NFS client.
+
+	  If unsure, say N.

fs/nfsd/Makefile

@@ -0,0 +1,14 @@
+#
+# Makefile for the Linux nfs server
+#
+
+obj-$(CONFIG_NFSD)	+= nfsd.o
+
+nfsd-y 			:= nfssvc.o nfsctl.o nfsproc.o nfsfh.o vfs.o \
+			   export.o auth.o lockd.o nfscache.o nfsxdr.o stats.o
+nfsd-$(CONFIG_NFSD_FAULT_INJECTION) += fault_inject.o
+nfsd-$(CONFIG_NFSD_V2_ACL) += nfs2acl.o
+nfsd-$(CONFIG_NFSD_V3)	+= nfs3proc.o nfs3xdr.o
+nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o
+nfsd-$(CONFIG_NFSD_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \
+			   nfs4acl.o nfs4callback.o nfs4recover.o

fs/nfsd/acl.h

@@ -0,0 +1,59 @@
+/*
+ *  Common NFSv4 ACL handling definitions.
+ *
+ *  Copyright (c) 2002 The Regents of the University of Michigan.
+ *  All rights reserved.
+ *
+ *  Marius Aamodt Eriksen <marius@umich.edu>
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the University nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef LINUX_NFS4_ACL_H
+#define LINUX_NFS4_ACL_H
+
+struct nfs4_acl;
+struct svc_fh;
+struct svc_rqst;
+
+/*
+ * Maximum ACL we'll accept from a client; chosen (somewhat
+ * arbitrarily) so that kmalloc'ing the ACL shouldn't require a
+ * high-order allocation.  This allows 204 ACEs on x86_64:
+ */
+#define NFS4_ACL_MAX ((PAGE_SIZE - sizeof(struct nfs4_acl)) \
+			/ sizeof(struct nfs4_ace))
+
+int nfs4_acl_bytes(int entries);
+int nfs4_acl_get_whotype(char *, u32);
+__be32 nfs4_acl_write_who(struct xdr_stream *xdr, int who);
+
+int nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry,
+		struct nfs4_acl **acl);
+__be32 nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		struct nfs4_acl *acl);
+
+#endif /* LINUX_NFS4_ACL_H */

fs/nfsd/auth.c

@@ -0,0 +1,90 @@
+/* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de> */
+
+#include <linux/sched.h>
+#include "nfsd.h"
+#include "auth.h"
+
+int nfsexp_flags(struct svc_rqst *rqstp, struct svc_export *exp)
+{
+	struct exp_flavor_info *f;
+	struct exp_flavor_info *end = exp->ex_flavors + exp->ex_nflavors;
+
+	for (f = exp->ex_flavors; f < end; f++) {
+		if (f->pseudoflavor == rqstp->rq_cred.cr_flavor)
+			return f->flags;
+	}
+	return exp->ex_flags;
+
+}
+
+int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
+{
+	struct group_info *rqgi;
+	struct group_info *gi;
+	struct cred *new;
+	int i;
+	int flags = nfsexp_flags(rqstp, exp);
+
+	validate_process_creds();
+
+	/* discard any old override before preparing the new set */
+	revert_creds(get_cred(current_real_cred()));
+	new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+
+	new->fsuid = rqstp->rq_cred.cr_uid;
+	new->fsgid = rqstp->rq_cred.cr_gid;
+
+	rqgi = rqstp->rq_cred.cr_group_info;
+
+	if (flags & NFSEXP_ALLSQUASH) {
+		new->fsuid = exp->ex_anon_uid;
+		new->fsgid = exp->ex_anon_gid;
+		gi = groups_alloc(0);
+		if (!gi)
+			goto oom;
+	} else if (flags & NFSEXP_ROOTSQUASH) {
+		if (uid_eq(new->fsuid, GLOBAL_ROOT_UID))
+			new->fsuid = exp->ex_anon_uid;
+		if (gid_eq(new->fsgid, GLOBAL_ROOT_GID))
+			new->fsgid = exp->ex_anon_gid;
+
+		gi = groups_alloc(rqgi->ngroups);
+		if (!gi)
+			goto oom;
+
+		for (i = 0; i < rqgi->ngroups; i++) {
+			if (gid_eq(GLOBAL_ROOT_GID, GROUP_AT(rqgi, i)))
+				GROUP_AT(gi, i) = exp->ex_anon_gid;
+			else
+				GROUP_AT(gi, i) = GROUP_AT(rqgi, i);
+		}
+	} else {
+		gi = get_group_info(rqgi);
+	}
+
+	if (uid_eq(new->fsuid, INVALID_UID))
+		new->fsuid = exp->ex_anon_uid;
+	if (gid_eq(new->fsgid, INVALID_GID))
+		new->fsgid = exp->ex_anon_gid;
+
+	set_groups(new, gi);
+	put_group_info(gi);
+
+	if (!uid_eq(new->fsuid, GLOBAL_ROOT_UID))
+		new->cap_effective = cap_drop_nfsd_set(new->cap_effective);
+	else
+		new->cap_effective = cap_raise_nfsd_set(new->cap_effective,
+							new->cap_permitted);
+	validate_process_creds();
+	put_cred(override_creds(new));
+	put_cred(new);
+	validate_process_creds();
+	return 0;
+
+oom:
+	abort_creds(new);
+	return -ENOMEM;
+}
+

fs/nfsd/auth.h

@@ -0,0 +1,16 @@
+/*
+ * nfsd-specific authentication stuff.
+ *
+ * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
+ */
+
+#ifndef LINUX_NFSD_AUTH_H
+#define LINUX_NFSD_AUTH_H
+
+/*
+ * Set the current process's fsuid/fsgid etc to those of the NFS
+ * client user
+ */
+int nfsd_setuser(struct svc_rqst *, struct svc_export *);
+
+#endif /* LINUX_NFSD_AUTH_H */

fs/nfsd/cache.h

@@ -0,0 +1,86 @@
+/*
+ * Request reply cache. This was heavily inspired by the
+ * implementation in 4.3BSD/4.4BSD.
+ *
+ * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
+ */
+
+#ifndef NFSCACHE_H
+#define NFSCACHE_H
+
+#include <linux/sunrpc/svc.h>
+
+/*
+ * Representation of a reply cache entry.
+ *
+ * Note that we use a sockaddr_in6 to hold the address instead of the more
+ * typical sockaddr_storage. This is for space reasons, since sockaddr_storage
+ * is much larger than a sockaddr_in6.
+ */
+struct svc_cacherep {
+	struct list_head	c_lru;
+
+	unsigned char		c_state,	/* unused, inprog, done */
+				c_type,		/* status, buffer */
+				c_secure : 1;	/* req came from port < 1024 */
+	struct sockaddr_in6	c_addr;
+	__be32			c_xid;
+	u32			c_prot;
+	u32			c_proc;
+	u32			c_vers;
+	unsigned int		c_len;
+	__wsum			c_csum;
+	unsigned long		c_timestamp;
+	union {
+		struct kvec	u_vec;
+		__be32		u_status;
+	}			c_u;
+};
+
+#define c_replvec		c_u.u_vec
+#define c_replstat		c_u.u_status
+
+/* cache entry states */
+enum {
+	RC_UNUSED,
+	RC_INPROG,
+	RC_DONE
+};
+
+/* return values */
+enum {
+	RC_DROPIT,
+	RC_REPLY,
+	RC_DOIT
+};
+
+/*
+ * Cache types.
+ * We may want to add more types one day, e.g. for diropres and
+ * attrstat replies. Using cache entries with fixed length instead
+ * of buffer pointers may be more efficient.
+ */
+enum {
+	RC_NOCACHE,
+	RC_REPLSTAT,
+	RC_REPLBUFF,
+};
+
+/*
+ * If requests are retransmitted within this interval, they're dropped.
+ */
+#define RC_DELAY		(HZ/5)
+
+/* Cache entries expire after this time period */
+#define RC_EXPIRE		(120 * HZ)
+
+/* Checksum this amount of the request */
+#define RC_CSUMLEN		(256U)
+
+int	nfsd_reply_cache_init(void);
+void	nfsd_reply_cache_shutdown(void);
+int	nfsd_cache_lookup(struct svc_rqst *);
+void	nfsd_cache_update(struct svc_rqst *, int, __be32 *);
+int	nfsd_reply_cache_stats_open(struct inode *, struct file *);
+
+#endif /* NFSCACHE_H */

fs/nfsd/current_stateid.h

@@ -0,0 +1,28 @@
+#ifndef _NFSD4_CURRENT_STATE_H
+#define _NFSD4_CURRENT_STATE_H
+
+#include "state.h"
+#include "xdr4.h"
+
+extern void clear_current_stateid(struct nfsd4_compound_state *cstate);
+/*
+ * functions to set current state id
+ */
+extern void nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *);
+extern void nfsd4_set_openstateid(struct nfsd4_compound_state *, struct nfsd4_open *);
+extern void nfsd4_set_lockstateid(struct nfsd4_compound_state *, struct nfsd4_lock *);
+extern void nfsd4_set_closestateid(struct nfsd4_compound_state *, struct nfsd4_close *);
+
+/*
+ * functions to consume current state id
+ */
+extern void nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *);
+extern void nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *, struct nfsd4_delegreturn *);
+extern void nfsd4_get_freestateid(struct nfsd4_compound_state *, struct nfsd4_free_stateid *);
+extern void nfsd4_get_setattrstateid(struct nfsd4_compound_state *, struct nfsd4_setattr *);
+extern void nfsd4_get_closestateid(struct nfsd4_compound_state *, struct nfsd4_close *);
+extern void nfsd4_get_lockustateid(struct nfsd4_compound_state *, struct nfsd4_locku *);
+extern void nfsd4_get_readstateid(struct nfsd4_compound_state *, struct nfsd4_read *);
+extern void nfsd4_get_writestateid(struct nfsd4_compound_state *, struct nfsd4_write *);
+
+#endif   /* _NFSD4_CURRENT_STATE_H */

fs/nfsd/export.h

@@ -0,0 +1,111 @@
+/*
+ * Copyright (C) 1995-1997 Olaf Kirch <okir@monad.swb.de>
+ */
+#ifndef NFSD_EXPORT_H
+#define NFSD_EXPORT_H
+
+#include <linux/sunrpc/cache.h>
+#include <uapi/linux/nfsd/export.h>
+
+struct knfsd_fh;
+struct svc_fh;
+struct svc_rqst;
+
+/*
+ * FS Locations
+ */
+
+#define MAX_FS_LOCATIONS	128
+
+struct nfsd4_fs_location {
+	char *hosts; /* colon separated list of hosts */
+	char *path;  /* slash separated list of path components */
+};
+
+struct nfsd4_fs_locations {
+	uint32_t locations_count;
+	struct nfsd4_fs_location *locations;
+/* If we're not actually serving this data ourselves (only providing a
+ * list of replicas that do serve it) then we set "migrated": */
+	int migrated;
+};
+
+/*
+ * We keep an array of pseudoflavors with the export, in order from most
+ * to least preferred.  For the foreseeable future, we don't expect more
+ * than the eight pseudoflavors null, unix, krb5, krb5i, krb5p, skpm3,
+ * spkm3i, and spkm3p (and using all 8 at once should be rare).
+ */
+#define MAX_SECINFO_LIST	8
+#define EX_UUID_LEN		16
+
+struct exp_flavor_info {
+	u32	pseudoflavor;
+	u32	flags;
+};
+
+struct svc_export {
+	struct cache_head	h;
+	struct auth_domain *	ex_client;
+	int			ex_flags;
+	struct path		ex_path;
+	kuid_t			ex_anon_uid;
+	kgid_t			ex_anon_gid;
+	int			ex_fsid;
+	unsigned char *		ex_uuid; /* 16 byte fsid */
+	struct nfsd4_fs_locations ex_fslocs;
+	uint32_t		ex_nflavors;
+	struct exp_flavor_info	ex_flavors[MAX_SECINFO_LIST];
+	struct cache_detail	*cd;
+};
+
+/* an "export key" (expkey) maps a filehandlefragement to an
+ * svc_export for a given client.  There can be several per export,
+ * for the different fsid types.
+ */
+struct svc_expkey {
+	struct cache_head	h;
+
+	struct auth_domain *	ek_client;
+	int			ek_fsidtype;
+	u32			ek_fsid[6];
+
+	struct path		ek_path;
+};
+
+#define EX_ISSYNC(exp)		(!((exp)->ex_flags & NFSEXP_ASYNC))
+#define EX_NOHIDE(exp)		((exp)->ex_flags & NFSEXP_NOHIDE)
+#define EX_WGATHER(exp)		((exp)->ex_flags & NFSEXP_GATHERED_WRITES)
+
+int nfsexp_flags(struct svc_rqst *rqstp, struct svc_export *exp);
+__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp);
+
+/*
+ * Function declarations
+ */
+int			nfsd_export_init(struct net *);
+void			nfsd_export_shutdown(struct net *);
+void			nfsd_export_flush(struct net *);
+struct svc_export *	rqst_exp_get_by_name(struct svc_rqst *,
+					     struct path *);
+struct svc_export *	rqst_exp_parent(struct svc_rqst *,
+					struct path *);
+struct svc_export *	rqst_find_fsidzero_export(struct svc_rqst *);
+int			exp_rootfh(struct net *, struct auth_domain *,
+					char *path, struct knfsd_fh *, int maxsize);
+__be32			exp_pseudoroot(struct svc_rqst *, struct svc_fh *);
+__be32			nfserrno(int errno);
+
+static inline void exp_put(struct svc_export *exp)
+{
+	cache_put(&exp->h, exp->cd);
+}
+
+static inline struct svc_export *exp_get(struct svc_export *exp)
+{
+	cache_get(&exp->h);
+	return exp;
+}
+struct svc_export * rqst_exp_find(struct svc_rqst *, int, u32 *);
+
+#endif /* NFSD_EXPORT_H */

fs/nfsd/fault_inject.c

@@ -0,0 +1,150 @@
+/*
+ * Copyright (c) 2011 Bryan Schumaker <bjschuma@netapp.com>
+ *
+ * Uses debugfs to create fault injection points for client testing
+ */
+
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/debugfs.h>
+#include <linux/module.h>
+#include <linux/nsproxy.h>
+#include <linux/sunrpc/addr.h>
+#include <asm/uaccess.h>
+
+#include "state.h"
+#include "netns.h"
+
+struct nfsd_fault_inject_op {
+	char *file;
+	u64 (*get)(void);
+	u64 (*set_val)(u64);
+	u64 (*set_clnt)(struct sockaddr_storage *, size_t);
+};
+
+static struct dentry *debug_dir;
+
+static ssize_t fault_inject_read(struct file *file, char __user *buf,
+				 size_t len, loff_t *ppos)
+{
+	static u64 val;
+	char read_buf[25];
+	size_t size;
+	loff_t pos = *ppos;
+	struct nfsd_fault_inject_op *op = file_inode(file)->i_private;
+
+	if (!pos)
+		val = op->get();
+	size = scnprintf(read_buf, sizeof(read_buf), "%llu\n", val);
+
+	return simple_read_from_buffer(buf, len, ppos, read_buf, size);
+}
+
+static ssize_t fault_inject_write(struct file *file, const char __user *buf,
+				  size_t len, loff_t *ppos)
+{
+	char write_buf[INET6_ADDRSTRLEN];
+	size_t size = min(sizeof(write_buf) - 1, len);
+	struct net *net = current->nsproxy->net_ns;
+	struct sockaddr_storage sa;
+	struct nfsd_fault_inject_op *op = file_inode(file)->i_private;
+	u64 val;
+	char *nl;
+
+	if (copy_from_user(write_buf, buf, size))
+		return -EFAULT;
+	write_buf[size] = '\0';
+
+	/* Deal with any embedded newlines in the string */
+	nl = strchr(write_buf, '\n');
+	if (nl) {
+		size = nl - write_buf;
+		*nl = '\0';
+	}
+
+	size = rpc_pton(net, write_buf, size, (struct sockaddr *)&sa, sizeof(sa));
+	if (size > 0) {
+		val = op->set_clnt(&sa, size);
+		if (val)
+			pr_info("NFSD [%s]: Client %s had %llu state object(s)\n",
+				op->file, write_buf, val);
+	} else {
+		val = simple_strtoll(write_buf, NULL, 0);
+		if (val == 0)
+			pr_info("NFSD Fault Injection: %s (all)", op->file);
+		else
+			pr_info("NFSD Fault Injection: %s (n = %llu)",
+				op->file, val);
+		val = op->set_val(val);
+		pr_info("NFSD: %s: found %llu", op->file, val);
+	}
+	return len; /* on success, claim we got the whole input */
+}
+
+static const struct file_operations fops_nfsd = {
+	.owner   = THIS_MODULE,
+	.read    = fault_inject_read,
+	.write   = fault_inject_write,
+};
+
+void nfsd_fault_inject_cleanup(void)
+{
+	debugfs_remove_recursive(debug_dir);
+}
+
+static struct nfsd_fault_inject_op inject_ops[] = {
+	{
+		.file     = "forget_clients",
+		.get	  = nfsd_inject_print_clients,
+		.set_val  = nfsd_inject_forget_clients,
+		.set_clnt = nfsd_inject_forget_client,
+	},
+	{
+		.file     = "forget_locks",
+		.get	  = nfsd_inject_print_locks,
+		.set_val  = nfsd_inject_forget_locks,
+		.set_clnt = nfsd_inject_forget_client_locks,
+	},
+	{
+		.file     = "forget_openowners",
+		.get	  = nfsd_inject_print_openowners,
+		.set_val  = nfsd_inject_forget_openowners,
+		.set_clnt = nfsd_inject_forget_client_openowners,
+	},
+	{
+		.file     = "forget_delegations",
+		.get	  = nfsd_inject_print_delegations,
+		.set_val  = nfsd_inject_forget_delegations,
+		.set_clnt = nfsd_inject_forget_client_delegations,
+	},
+	{
+		.file     = "recall_delegations",
+		.get	  = nfsd_inject_print_delegations,
+		.set_val  = nfsd_inject_recall_delegations,
+		.set_clnt = nfsd_inject_recall_client_delegations,
+	},
+};
+
+#define NUM_INJECT_OPS (sizeof(inject_ops)/sizeof(struct nfsd_fault_inject_op))
+
+int nfsd_fault_inject_init(void)
+{
+	unsigned int i;
+	struct nfsd_fault_inject_op *op;
+	umode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
+
+	debug_dir = debugfs_create_dir("nfsd", NULL);
+	if (!debug_dir)
+		goto fail;
+
+	for (i = 0; i < NUM_INJECT_OPS; i++) {
+		op = &inject_ops[i];
+		if (!debugfs_create_file(op->file, mode, debug_dir, op, &fops_nfsd))
+			goto fail;
+	}
+	return 0;
+
+fail:
+	nfsd_fault_inject_cleanup();
+	return -ENOMEM;
+}

fs/nfsd/idmap.h

@@ -0,0 +1,62 @@
+/*
+ *  Mapping of UID to name and vice versa.
+ *
+ *  Copyright (c) 2002, 2003 The Regents of the University of
+ *  Michigan.  All rights reserved.
+> *
+ *  Marius Aamodt Eriksen <marius@umich.edu>
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the University nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef LINUX_NFSD_IDMAP_H
+#define LINUX_NFSD_IDMAP_H
+
+#include <linux/in.h>
+#include <linux/sunrpc/svc.h>
+
+/* XXX from linux/nfs_idmap.h */
+#define IDMAP_NAMESZ 128
+
+#ifdef CONFIG_NFSD_V4
+int nfsd_idmap_init(struct net *);
+void nfsd_idmap_shutdown(struct net *);
+#else
+static inline int nfsd_idmap_init(struct net *net)
+{
+	return 0;
+}
+static inline void nfsd_idmap_shutdown(struct net *net)
+{
+}
+#endif
+
+__be32 nfsd_map_name_to_uid(struct svc_rqst *, const char *, size_t, kuid_t *);
+__be32 nfsd_map_name_to_gid(struct svc_rqst *, const char *, size_t, kgid_t *);
+__be32 nfsd4_encode_user(struct xdr_stream *, struct svc_rqst *, kuid_t);
+__be32 nfsd4_encode_group(struct xdr_stream *, struct svc_rqst *, kgid_t);
+
+#endif /* LINUX_NFSD_IDMAP_H */

fs/nfsd/lockd.c

@@ -0,0 +1,77 @@
+/*
+ * This file contains all the stubs needed when communicating with lockd.
+ * This level of indirection is necessary so we can run nfsd+lockd without
+ * requiring the nfs client to be compiled in/loaded, and vice versa.
+ *
+ * Copyright (C) 1996, Olaf Kirch <okir@monad.swb.de>
+ */
+
+#include <linux/file.h>
+#include <linux/lockd/bind.h>
+#include "nfsd.h"
+#include "vfs.h"
+
+#define NFSDDBG_FACILITY		NFSDDBG_LOCKD
+
+#ifdef CONFIG_LOCKD_V4
+#define nlm_stale_fh	nlm4_stale_fh
+#define nlm_failed	nlm4_failed
+#else
+#define nlm_stale_fh	nlm_lck_denied_nolocks
+#define nlm_failed	nlm_lck_denied_nolocks
+#endif
+/*
+ * Note: we hold the dentry use count while the file is open.
+ */
+static __be32
+nlm_fopen(struct svc_rqst *rqstp, struct nfs_fh *f, struct file **filp)
+{
+	__be32		nfserr;
+	struct svc_fh	fh;
+
+	/* must initialize before using! but maxsize doesn't matter */
+	fh_init(&fh,0);
+	fh.fh_handle.fh_size = f->size;
+	memcpy((char*)&fh.fh_handle.fh_base, f->data, f->size);
+	fh.fh_export = NULL;
+
+	nfserr = nfsd_open(rqstp, &fh, S_IFREG, NFSD_MAY_LOCK, filp);
+	fh_put(&fh);
+ 	/* We return nlm error codes as nlm doesn't know
+	 * about nfsd, but nfsd does know about nlm..
+	 */
+	switch (nfserr) {
+	case nfs_ok:
+		return 0;
+	case nfserr_dropit:
+		return nlm_drop_reply;
+	case nfserr_stale:
+		return nlm_stale_fh;
+	default:
+		return nlm_failed;
+	}
+}
+
+static void
+nlm_fclose(struct file *filp)
+{
+	fput(filp);
+}
+
+static struct nlmsvc_binding	nfsd_nlm_ops = {
+	.fopen		= nlm_fopen,		/* open file for locking */
+	.fclose		= nlm_fclose,		/* close file */
+};
+
+void
+nfsd_lockd_init(void)
+{
+	dprintk("nfsd: initializing lockd\n");
+	nlmsvc_ops = &nfsd_nlm_ops;
+}
+
+void
+nfsd_lockd_shutdown(void)
+{
+	nlmsvc_ops = NULL;
+}

fs/nfsd/netns.h

@@ -0,0 +1,121 @@
+/*
+ * per net namespace data structures for nfsd
+ *
+ * Copyright (C) 2012, Jeff Layton <jlayton@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 51
+ * Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ */
+
+#ifndef __NFSD_NETNS_H__
+#define __NFSD_NETNS_H__
+
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+
+/* Hash tables for nfs4_clientid state */
+#define CLIENT_HASH_BITS                 4
+#define CLIENT_HASH_SIZE                (1 << CLIENT_HASH_BITS)
+#define CLIENT_HASH_MASK                (CLIENT_HASH_SIZE - 1)
+
+#define SESSION_HASH_SIZE	512
+
+struct cld_net;
+struct nfsd4_client_tracking_ops;
+
+/*
+ * Represents a nfsd "container". With respect to nfsv4 state tracking, the
+ * fields of interest are the *_id_hashtbls and the *_name_tree. These track
+ * the nfs4_client objects by either short or long form clientid.
+ *
+ * Each nfsd_net runs a nfs4_laundromat workqueue job when necessary to clean
+ * up expired clients and delegations within the container.
+ */
+struct nfsd_net {
+	struct cld_net *cld_net;
+
+	struct cache_detail *svc_expkey_cache;
+	struct cache_detail *svc_export_cache;
+
+	struct cache_detail *idtoname_cache;
+	struct cache_detail *nametoid_cache;
+
+	struct lock_manager nfsd4_manager;
+	bool grace_ended;
+	time_t boot_time;
+
+	/*
+	 * reclaim_str_hashtbl[] holds known client info from previous reset/reboot
+	 * used in reboot/reset lease grace period processing
+	 *
+	 * conf_id_hashtbl[], and conf_name_tree hold confirmed
+	 * setclientid_confirmed info.
+	 *
+	 * unconf_str_hastbl[] and unconf_name_tree hold unconfirmed
+	 * setclientid info.
+	 */
+	struct list_head *reclaim_str_hashtbl;
+	int reclaim_str_hashtbl_size;
+	struct list_head *conf_id_hashtbl;
+	struct rb_root conf_name_tree;
+	struct list_head *unconf_id_hashtbl;
+	struct rb_root unconf_name_tree;
+	struct list_head *sessionid_hashtbl;
+	/*
+	 * client_lru holds client queue ordered by nfs4_client.cl_time
+	 * for lease renewal.
+	 *
+	 * close_lru holds (open) stateowner queue ordered by nfs4_stateowner.so_time
+	 * for last close replay.
+	 *
+	 * All of the above fields are protected by the client_mutex.
+	 */
+	struct list_head client_lru;
+	struct list_head close_lru;
+	struct list_head del_recall_lru;
+
+	struct delayed_work laundromat_work;
+
+	/* client_lock protects the client lru list and session hash table */
+	spinlock_t client_lock;
+
+	struct file *rec_file;
+	bool in_grace;
+	struct nfsd4_client_tracking_ops *client_tracking_ops;
+
+	time_t nfsd4_lease;
+	time_t nfsd4_grace;
+
+	bool nfsd_net_up;
+	bool lockd_up;
+
+	/* Time of server startup */
+	struct timeval nfssvc_boot;
+
+	/*
+	 * Max number of connections this nfsd container will allow. Defaults
+	 * to '0' which is means that it bases this on the number of threads.
+	 */
+	unsigned int max_connections;
+
+	u32 clientid_counter;
+
+	struct svc_serv *nfsd_serv;
+};
+
+/* Simple check to find out if a given net was properly initialized */
+#define nfsd_netns_ready(nn) ((nn)->sessionid_hashtbl)
+
+extern int nfsd_net_id;
+#endif /* __NFSD_NETNS_H__ */

fs/nfsd/nfs2acl.c

@@ -0,0 +1,382 @@
+/*
+ * Process version 2 NFSACL requests.
+ *
+ * Copyright (C) 2002-2003 Andreas Gruenbacher <agruen@suse.de>
+ */
+
+#include "nfsd.h"
+/* FIXME: nfsacl.h is a broken header */
+#include <linux/nfsacl.h>
+#include <linux/gfp.h>
+#include "cache.h"
+#include "xdr3.h"
+#include "vfs.h"
+
+#define NFSDDBG_FACILITY		NFSDDBG_PROC
+#define RETURN_STATUS(st)	{ resp->status = (st); return (st); }
+
+/*
+ * NULL call.
+ */
+static __be32
+nfsacld_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+{
+	return nfs_ok;
+}
+
+/*
+ * Get the Access and/or Default ACL of a file.
+ */
+static __be32 nfsacld_proc_getacl(struct svc_rqst * rqstp,
+		struct nfsd3_getaclargs *argp, struct nfsd3_getaclres *resp)
+{
+	struct posix_acl *acl;
+	struct inode *inode;
+	svc_fh *fh;
+	__be32 nfserr = 0;
+
+	dprintk("nfsd: GETACL(2acl)   %s\n", SVCFH_fmt(&argp->fh));
+
+	fh = fh_copy(&resp->fh, &argp->fh);
+	nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP);
+	if (nfserr)
+		RETURN_STATUS(nfserr);
+
+	inode = fh->fh_dentry->d_inode;
+
+	if (argp->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT))
+		RETURN_STATUS(nfserr_inval);
+	resp->mask = argp->mask;
+
+	nfserr = fh_getattr(fh, &resp->stat);
+	if (nfserr)
+		goto fail;
+
+	if (resp->mask & (NFS_ACL|NFS_ACLCNT)) {
+		acl = get_acl(inode, ACL_TYPE_ACCESS);
+		if (acl == NULL) {
+			/* Solaris returns the inode's minimum ACL. */
+			acl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
+		}
+		if (IS_ERR(acl)) {
+			nfserr = nfserrno(PTR_ERR(acl));
+			goto fail;
+		}
+		resp->acl_access = acl;
+	}
+	if (resp->mask & (NFS_DFACL|NFS_DFACLCNT)) {
+		/* Check how Solaris handles requests for the Default ACL
+		   of a non-directory! */
+		acl = get_acl(inode, ACL_TYPE_DEFAULT);
+		if (IS_ERR(acl)) {
+			nfserr = nfserrno(PTR_ERR(acl));
+			goto fail;
+		}
+		resp->acl_default = acl;
+	}
+
+	/* resp->acl_{access,default} are released in nfssvc_release_getacl. */
+	RETURN_STATUS(0);
+
+fail:
+	posix_acl_release(resp->acl_access);
+	posix_acl_release(resp->acl_default);
+	RETURN_STATUS(nfserr);
+}
+
+/*
+ * Set the Access and/or Default ACL of a file.
+ */
+static __be32 nfsacld_proc_setacl(struct svc_rqst * rqstp,
+		struct nfsd3_setaclargs *argp,
+		struct nfsd_attrstat *resp)
+{
+	struct inode *inode;
+	svc_fh *fh;
+	__be32 nfserr = 0;
+	int error;
+
+	dprintk("nfsd: SETACL(2acl)   %s\n", SVCFH_fmt(&argp->fh));
+
+	fh = fh_copy(&resp->fh, &argp->fh);
+	nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_SATTR);
+	if (nfserr)
+		goto out;
+
+	inode = fh->fh_dentry->d_inode;
+	if (!IS_POSIXACL(inode) || !inode->i_op->set_acl) {
+		error = -EOPNOTSUPP;
+		goto out_errno;
+	}
+
+	error = fh_want_write(fh);
+	if (error)
+		goto out_errno;
+
+	error = inode->i_op->set_acl(inode, argp->acl_access, ACL_TYPE_ACCESS);
+	if (error)
+		goto out_drop_write;
+	error = inode->i_op->set_acl(inode, argp->acl_default,
+				     ACL_TYPE_DEFAULT);
+	if (error)
+		goto out_drop_write;
+
+	fh_drop_write(fh);
+
+	nfserr = fh_getattr(fh, &resp->stat);
+
+out:
+	/* argp->acl_{access,default} may have been allocated in
+	   nfssvc_decode_setaclargs. */
+	posix_acl_release(argp->acl_access);
+	posix_acl_release(argp->acl_default);
+	return nfserr;
+out_drop_write:
+	fh_drop_write(fh);
+out_errno:
+	nfserr = nfserrno(error);
+	goto out;
+}
+
+/*
+ * Check file attributes
+ */
+static __be32 nfsacld_proc_getattr(struct svc_rqst * rqstp,
+		struct nfsd_fhandle *argp, struct nfsd_attrstat *resp)
+{
+	__be32 nfserr;
+	dprintk("nfsd: GETATTR  %s\n", SVCFH_fmt(&argp->fh));
+
+	fh_copy(&resp->fh, &argp->fh);
+	nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP);
+	if (nfserr)
+		return nfserr;
+	nfserr = fh_getattr(&resp->fh, &resp->stat);
+	return nfserr;
+}
+
+/*
+ * Check file access
+ */
+static __be32 nfsacld_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessargs *argp,
+		struct nfsd3_accessres *resp)
+{
+	__be32 nfserr;
+
+	dprintk("nfsd: ACCESS(2acl)   %s 0x%x\n",
+			SVCFH_fmt(&argp->fh),
+			argp->access);
+
+	fh_copy(&resp->fh, &argp->fh);
+	resp->access = argp->access;
+	nfserr = nfsd_access(rqstp, &resp->fh, &resp->access, NULL);
+	if (nfserr)
+		return nfserr;
+	nfserr = fh_getattr(&resp->fh, &resp->stat);
+	return nfserr;
+}
+
+/*
+ * XDR decode functions
+ */
+static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p,
+		struct nfsd3_getaclargs *argp)
+{
+	p = nfs2svc_decode_fh(p, &argp->fh);
+	if (!p)
+		return 0;
+	argp->mask = ntohl(*p); p++;
+
+	return xdr_argsize_check(rqstp, p);
+}
+
+
+static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p,
+		struct nfsd3_setaclargs *argp)
+{
+	struct kvec *head = rqstp->rq_arg.head;
+	unsigned int base;
+	int n;
+
+	p = nfs2svc_decode_fh(p, &argp->fh);
+	if (!p)
+		return 0;
+	argp->mask = ntohl(*p++);
+	if (argp->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT) ||
+	    !xdr_argsize_check(rqstp, p))
+		return 0;
+
+	base = (char *)p - (char *)head->iov_base;
+	n = nfsacl_decode(&rqstp->rq_arg, base, NULL,
+			  (argp->mask & NFS_ACL) ?
+			  &argp->acl_access : NULL);
+	if (n > 0)
+		n = nfsacl_decode(&rqstp->rq_arg, base + n, NULL,
+				  (argp->mask & NFS_DFACL) ?
+				  &argp->acl_default : NULL);
+	return (n > 0);
+}
+
+static int nfsaclsvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p,
+		struct nfsd_fhandle *argp)
+{
+	p = nfs2svc_decode_fh(p, &argp->fh);
+	if (!p)
+		return 0;
+	return xdr_argsize_check(rqstp, p);
+}
+
+static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p,
+		struct nfsd3_accessargs *argp)
+{
+	p = nfs2svc_decode_fh(p, &argp->fh);
+	if (!p)
+		return 0;
+	argp->access = ntohl(*p++);
+
+	return xdr_argsize_check(rqstp, p);
+}
+
+/*
+ * XDR encode functions
+ */
+
+/*
+ * There must be an encoding function for void results so svc_process
+ * will work properly.
+ */
+static int nfsaclsvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+{
+	return xdr_ressize_check(rqstp, p);
+}
+
+/* GETACL */
+static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
+		struct nfsd3_getaclres *resp)
+{
+	struct dentry *dentry = resp->fh.fh_dentry;
+	struct inode *inode;
+	struct kvec *head = rqstp->rq_res.head;
+	unsigned int base;
+	int n;
+	int w;
+
+	/*
+	 * Since this is version 2, the check for nfserr in
+	 * nfsd_dispatch actually ensures the following cannot happen.
+	 * However, it seems fragile to depend on that.
+	 */
+	if (dentry == NULL || dentry->d_inode == NULL)
+		return 0;
+	inode = dentry->d_inode;
+
+	p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
+	*p++ = htonl(resp->mask);
+	if (!xdr_ressize_check(rqstp, p))
+		return 0;
+	base = (char *)p - (char *)head->iov_base;
+
+	rqstp->rq_res.page_len = w = nfsacl_size(
+		(resp->mask & NFS_ACL)   ? resp->acl_access  : NULL,
+		(resp->mask & NFS_DFACL) ? resp->acl_default : NULL);
+	while (w > 0) {
+		if (!*(rqstp->rq_next_page++))
+			return 0;
+		w -= PAGE_SIZE;
+	}
+
+	n = nfsacl_encode(&rqstp->rq_res, base, inode,
+			  resp->acl_access,
+			  resp->mask & NFS_ACL, 0);
+	if (n > 0)
+		n = nfsacl_encode(&rqstp->rq_res, base + n, inode,
+				  resp->acl_default,
+				  resp->mask & NFS_DFACL,
+				  NFS_ACL_DEFAULT);
+	if (n <= 0)
+		return 0;
+	return 1;
+}
+
+static int nfsaclsvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p,
+		struct nfsd_attrstat *resp)
+{
+	p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
+	return xdr_ressize_check(rqstp, p);
+}
+
+/* ACCESS */
+static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p,
+		struct nfsd3_accessres *resp)
+{
+	p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
+	*p++ = htonl(resp->access);
+	return xdr_ressize_check(rqstp, p);
+}
+
+/*
+ * XDR release functions
+ */
+static int nfsaclsvc_release_getacl(struct svc_rqst *rqstp, __be32 *p,
+		struct nfsd3_getaclres *resp)
+{
+	fh_put(&resp->fh);
+	posix_acl_release(resp->acl_access);
+	posix_acl_release(resp->acl_default);
+	return 1;
+}
+
+static int nfsaclsvc_release_attrstat(struct svc_rqst *rqstp, __be32 *p,
+		struct nfsd_attrstat *resp)
+{
+	fh_put(&resp->fh);
+	return 1;
+}
+
+static int nfsaclsvc_release_access(struct svc_rqst *rqstp, __be32 *p,
+               struct nfsd3_accessres *resp)
+{
+       fh_put(&resp->fh);
+       return 1;
+}
+
+#define nfsaclsvc_decode_voidargs	NULL
+#define nfsaclsvc_release_void		NULL
+#define nfsd3_fhandleargs	nfsd_fhandle
+#define nfsd3_attrstatres	nfsd_attrstat
+#define nfsd3_voidres		nfsd3_voidargs
+struct nfsd3_voidargs { int dummy; };
+
+#define PROC(name, argt, rest, relt, cache, respsize)	\
+ { (svc_procfunc) nfsacld_proc_##name,		\
+   (kxdrproc_t) nfsaclsvc_decode_##argt##args,	\
+   (kxdrproc_t) nfsaclsvc_encode_##rest##res,	\
+   (kxdrproc_t) nfsaclsvc_release_##relt,		\
+   sizeof(struct nfsd3_##argt##args),		\
+   sizeof(struct nfsd3_##rest##res),		\
+   0,						\
+   cache,					\
+   respsize,					\
+ }
+
+#define ST 1		/* status*/
+#define AT 21		/* attributes */
+#define pAT (1+AT)	/* post attributes - conditional */
+#define ACL (1+NFS_ACL_MAX_ENTRIES*3)  /* Access Control List */
+
+static struct svc_procedure		nfsd_acl_procedures2[] = {
+  PROC(null,	void,		void,		void,	  RC_NOCACHE, ST),
+  PROC(getacl,	getacl,		getacl,		getacl,	  RC_NOCACHE, ST+1+2*(1+ACL)),
+  PROC(setacl,	setacl,		attrstat,	attrstat, RC_NOCACHE, ST+AT),
+  PROC(getattr, fhandle,	attrstat,	attrstat, RC_NOCACHE, ST+AT),
+  PROC(access,	access,		access,		access,   RC_NOCACHE, ST+AT+1),
+};
+
+struct svc_version	nfsd_acl_version2 = {
+		.vs_vers	= 2,
+		.vs_nproc	= 5,
+		.vs_proc	= nfsd_acl_procedures2,
+		.vs_dispatch	= nfsd_dispatch,
+		.vs_xdrsize	= NFS3_SVC_XDRSIZE,
+		.vs_hidden	= 0,
+};

fs/nfsd/nfs3acl.c

@@ -0,0 +1,273 @@
+/*
+ * Process version 3 NFSACL requests.
+ *
+ * Copyright (C) 2002-2003 Andreas Gruenbacher <agruen@suse.de>
+ */
+
+#include "nfsd.h"
+/* FIXME: nfsacl.h is a broken header */
+#include <linux/nfsacl.h>
+#include <linux/gfp.h>
+#include "cache.h"
+#include "xdr3.h"
+#include "vfs.h"
+
+#define RETURN_STATUS(st)	{ resp->status = (st); return (st); }
+
+/*
+ * NULL call.
+ */
+static __be32
+nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+{
+	return nfs_ok;
+}
+
+/*
+ * Get the Access and/or Default ACL of a file.
+ */
+static __be32 nfsd3_proc_getacl(struct svc_rqst * rqstp,
+		struct nfsd3_getaclargs *argp, struct nfsd3_getaclres *resp)
+{
+	struct posix_acl *acl;
+	struct inode *inode;
+	svc_fh *fh;
+	__be32 nfserr = 0;
+
+	fh = fh_copy(&resp->fh, &argp->fh);
+	nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP);
+	if (nfserr)
+		RETURN_STATUS(nfserr);
+
+	inode = fh->fh_dentry->d_inode;
+
+	if (argp->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT))
+		RETURN_STATUS(nfserr_inval);
+	resp->mask = argp->mask;
+
+	if (resp->mask & (NFS_ACL|NFS_ACLCNT)) {
+		acl = get_acl(inode, ACL_TYPE_ACCESS);
+		if (acl == NULL) {
+			/* Solaris returns the inode's minimum ACL. */
+			acl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
+		}
+		if (IS_ERR(acl)) {
+			nfserr = nfserrno(PTR_ERR(acl));
+			goto fail;
+		}
+		resp->acl_access = acl;
+	}
+	if (resp->mask & (NFS_DFACL|NFS_DFACLCNT)) {
+		/* Check how Solaris handles requests for the Default ACL
+		   of a non-directory! */
+		acl = get_acl(inode, ACL_TYPE_DEFAULT);
+		if (IS_ERR(acl)) {
+			nfserr = nfserrno(PTR_ERR(acl));
+			goto fail;
+		}
+		resp->acl_default = acl;
+	}
+
+	/* resp->acl_{access,default} are released in nfs3svc_release_getacl. */
+	RETURN_STATUS(0);
+
+fail:
+	posix_acl_release(resp->acl_access);
+	posix_acl_release(resp->acl_default);
+	RETURN_STATUS(nfserr);
+}
+
+/*
+ * Set the Access and/or Default ACL of a file.
+ */
+static __be32 nfsd3_proc_setacl(struct svc_rqst * rqstp,
+		struct nfsd3_setaclargs *argp,
+		struct nfsd3_attrstat *resp)
+{
+	struct inode *inode;
+	svc_fh *fh;
+	__be32 nfserr = 0;
+	int error;
+
+	fh = fh_copy(&resp->fh, &argp->fh);
+	nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_SATTR);
+	if (nfserr)
+		goto out;
+
+	inode = fh->fh_dentry->d_inode;
+	if (!IS_POSIXACL(inode) || !inode->i_op->set_acl) {
+		error = -EOPNOTSUPP;
+		goto out_errno;
+	}
+
+	error = fh_want_write(fh);
+	if (error)
+		goto out_errno;
+
+	error = inode->i_op->set_acl(inode, argp->acl_access, ACL_TYPE_ACCESS);
+	if (error)
+		goto out_drop_write;
+	error = inode->i_op->set_acl(inode, argp->acl_default,
+				     ACL_TYPE_DEFAULT);
+
+out_drop_write:
+	fh_drop_write(fh);
+out_errno:
+	nfserr = nfserrno(error);
+out:
+	/* argp->acl_{access,default} may have been allocated in
+	   nfs3svc_decode_setaclargs. */
+	posix_acl_release(argp->acl_access);
+	posix_acl_release(argp->acl_default);
+	RETURN_STATUS(nfserr);
+}
+
+/*
+ * XDR decode functions
+ */
+static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p,
+		struct nfsd3_getaclargs *args)
+{
+	p = nfs3svc_decode_fh(p, &args->fh);
+	if (!p)
+		return 0;
+	args->mask = ntohl(*p); p++;
+
+	return xdr_argsize_check(rqstp, p);
+}
+
+
+static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p,
+		struct nfsd3_setaclargs *args)
+{
+	struct kvec *head = rqstp->rq_arg.head;
+	unsigned int base;
+	int n;
+
+	p = nfs3svc_decode_fh(p, &args->fh);
+	if (!p)
+		return 0;
+	args->mask = ntohl(*p++);
+	if (args->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT) ||
+	    !xdr_argsize_check(rqstp, p))
+		return 0;
+
+	base = (char *)p - (char *)head->iov_base;
+	n = nfsacl_decode(&rqstp->rq_arg, base, NULL,
+			  (args->mask & NFS_ACL) ?
+			  &args->acl_access : NULL);
+	if (n > 0)
+		n = nfsacl_decode(&rqstp->rq_arg, base + n, NULL,
+				  (args->mask & NFS_DFACL) ?
+				  &args->acl_default : NULL);
+	return (n > 0);
+}
+
+/*
+ * XDR encode functions
+ */
+
+/* GETACL */
+static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
+		struct nfsd3_getaclres *resp)
+{
+	struct dentry *dentry = resp->fh.fh_dentry;
+
+	p = nfs3svc_encode_post_op_attr(rqstp, p, &resp->fh);
+	if (resp->status == 0 && dentry && dentry->d_inode) {
+		struct inode *inode = dentry->d_inode;
+		struct kvec *head = rqstp->rq_res.head;
+		unsigned int base;
+		int n;
+		int w;
+
+		*p++ = htonl(resp->mask);
+		if (!xdr_ressize_check(rqstp, p))
+			return 0;
+		base = (char *)p - (char *)head->iov_base;
+
+		rqstp->rq_res.page_len = w = nfsacl_size(
+			(resp->mask & NFS_ACL)   ? resp->acl_access  : NULL,
+			(resp->mask & NFS_DFACL) ? resp->acl_default : NULL);
+		while (w > 0) {
+			if (!*(rqstp->rq_next_page++))
+				return 0;
+			w -= PAGE_SIZE;
+		}
+
+		n = nfsacl_encode(&rqstp->rq_res, base, inode,
+				  resp->acl_access,
+				  resp->mask & NFS_ACL, 0);
+		if (n > 0)
+			n = nfsacl_encode(&rqstp->rq_res, base + n, inode,
+					  resp->acl_default,
+					  resp->mask & NFS_DFACL,
+					  NFS_ACL_DEFAULT);
+		if (n <= 0)
+			return 0;
+	} else
+		if (!xdr_ressize_check(rqstp, p))
+			return 0;
+
+	return 1;
+}
+
+/* SETACL */
+static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p,
+		struct nfsd3_attrstat *resp)
+{
+	p = nfs3svc_encode_post_op_attr(rqstp, p, &resp->fh);
+
+	return xdr_ressize_check(rqstp, p);
+}
+
+/*
+ * XDR release functions
+ */
+static int nfs3svc_release_getacl(struct svc_rqst *rqstp, __be32 *p,
+		struct nfsd3_getaclres *resp)
+{
+	fh_put(&resp->fh);
+	posix_acl_release(resp->acl_access);
+	posix_acl_release(resp->acl_default);
+	return 1;
+}
+
+#define nfs3svc_decode_voidargs		NULL
+#define nfs3svc_release_void		NULL
+#define nfsd3_setaclres			nfsd3_attrstat
+#define nfsd3_voidres			nfsd3_voidargs
+struct nfsd3_voidargs { int dummy; };
+
+#define PROC(name, argt, rest, relt, cache, respsize)	\
+ { (svc_procfunc) nfsd3_proc_##name,		\
+   (kxdrproc_t) nfs3svc_decode_##argt##args,	\
+   (kxdrproc_t) nfs3svc_encode_##rest##res,	\
+   (kxdrproc_t) nfs3svc_release_##relt,		\
+   sizeof(struct nfsd3_##argt##args),		\
+   sizeof(struct nfsd3_##rest##res),		\
+   0,						\
+   cache,					\
+   respsize,					\
+ }
+
+#define ST 1		/* status*/
+#define AT 21		/* attributes */
+#define pAT (1+AT)	/* post attributes - conditional */
+#define ACL (1+NFS_ACL_MAX_ENTRIES*3)  /* Access Control List */
+
+static struct svc_procedure		nfsd_acl_procedures3[] = {
+  PROC(null,	void,		void,		void,	  RC_NOCACHE, ST),
+  PROC(getacl,	getacl,		getacl,		getacl,	  RC_NOCACHE, ST+1+2*(1+ACL)),
+  PROC(setacl,	setacl,		setacl,		fhandle,  RC_NOCACHE, ST+pAT),
+};
+
+struct svc_version	nfsd_acl_version3 = {
+		.vs_vers	= 3,
+		.vs_nproc	= 3,
+		.vs_proc	= nfsd_acl_procedures3,
+		.vs_dispatch	= nfsd_dispatch,
+		.vs_xdrsize	= NFS3_SVC_XDRSIZE,
+		.vs_hidden	= 0,
+};
+

fs/nfsd/nfs3proc.c

@@ -0,0 +1,891 @@
+/*
+ * Process version 3 NFS requests.
+ *
+ * Copyright (C) 1996, 1997, 1998 Olaf Kirch <okir@monad.swb.de>
+ */
+
+#include <linux/fs.h>
+#include <linux/ext2_fs.h>
+#include <linux/magic.h>
+
+#include "cache.h"
+#include "xdr3.h"
+#include "vfs.h"
+
+#define NFSDDBG_FACILITY		NFSDDBG_PROC
+
+#define RETURN_STATUS(st)	{ resp->status = (st); return (st); }
+
+static int	nfs3_ftypes[] = {
+	0,			/* NF3NON */
+	S_IFREG,		/* NF3REG */
+	S_IFDIR,		/* NF3DIR */
+	S_IFBLK,		/* NF3BLK */
+	S_IFCHR,		/* NF3CHR */
+	S_IFLNK,		/* NF3LNK */
+	S_IFSOCK,		/* NF3SOCK */
+	S_IFIFO,		/* NF3FIFO */
+};
+
+/*
+ * NULL call.
+ */
+static __be32
+nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+{
+	return nfs_ok;
+}
+
+/*
+ * Get a file's attributes
+ */
+static __be32
+nfsd3_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle  *argp,
+					   struct nfsd3_attrstat *resp)
+{
+	__be32	nfserr;
+
+	dprintk("nfsd: GETATTR(3)  %s\n",
+		SVCFH_fmt(&argp->fh));
+
+	fh_copy(&resp->fh, &argp->fh);
+	nfserr = fh_verify(rqstp, &resp->fh, 0,
+			NFSD_MAY_NOP | NFSD_MAY_BYPASS_GSS_ON_ROOT);
+	if (nfserr)
+		RETURN_STATUS(nfserr);
+
+	nfserr = fh_getattr(&resp->fh, &resp->stat);
+
+	RETURN_STATUS(nfserr);
+}
+
+/*
+ * Set a file's attributes
+ */
+static __be32
+nfsd3_proc_setattr(struct svc_rqst *rqstp, struct nfsd3_sattrargs *argp,
+					   struct nfsd3_attrstat  *resp)
+{
+	__be32	nfserr;
+
+	dprintk("nfsd: SETATTR(3)  %s\n",
+				SVCFH_fmt(&argp->fh));
+
+	fh_copy(&resp->fh, &argp->fh);
+	nfserr = nfsd_setattr(rqstp, &resp->fh, &argp->attrs,
+			      argp->check_guard, argp->guardtime);
+	RETURN_STATUS(nfserr);
+}
+
+/*
+ * Look up a path name component
+ */
+static __be32
+nfsd3_proc_lookup(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp,
+					  struct nfsd3_diropres  *resp)
+{
+	__be32	nfserr;
+
+	dprintk("nfsd: LOOKUP(3)   %s %.*s\n",
+				SVCFH_fmt(&argp->fh),
+				argp->len,
+				argp->name);
+
+	fh_copy(&resp->dirfh, &argp->fh);
+	fh_init(&resp->fh, NFS3_FHSIZE);
+
+	nfserr = nfsd_lookup(rqstp, &resp->dirfh,
+				    argp->name,
+				    argp->len,
+				    &resp->fh);
+	RETURN_STATUS(nfserr);
+}
+
+/*
+ * Check file access
+ */
+static __be32
+nfsd3_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessargs *argp,
+					  struct nfsd3_accessres *resp)
+{
+	__be32	nfserr;
+
+	dprintk("nfsd: ACCESS(3)   %s 0x%x\n",
+				SVCFH_fmt(&argp->fh),
+				argp->access);
+
+	fh_copy(&resp->fh, &argp->fh);
+	resp->access = argp->access;
+	nfserr = nfsd_access(rqstp, &resp->fh, &resp->access, NULL);
+	RETURN_STATUS(nfserr);
+}
+
+/*
+ * Read a symlink.
+ */
+static __be32
+nfsd3_proc_readlink(struct svc_rqst *rqstp, struct nfsd3_readlinkargs *argp,
+					   struct nfsd3_readlinkres *resp)
+{
+	__be32 nfserr;
+
+	dprintk("nfsd: READLINK(3) %s\n", SVCFH_fmt(&argp->fh));
+
+	/* Read the symlink. */
+	fh_copy(&resp->fh, &argp->fh);
+	resp->len = NFS3_MAXPATHLEN;
+	nfserr = nfsd_readlink(rqstp, &resp->fh, argp->buffer, &resp->len);
+	RETURN_STATUS(nfserr);
+}
+
+/*
+ * Read a portion of a file.
+ */
+static __be32
+nfsd3_proc_read(struct svc_rqst *rqstp, struct nfsd3_readargs *argp,
+				        struct nfsd3_readres  *resp)
+{
+	__be32	nfserr;
+	u32	max_blocksize = svc_max_payload(rqstp);
+
+	dprintk("nfsd: READ(3) %s %lu bytes at %Lu\n",
+				SVCFH_fmt(&argp->fh),
+				(unsigned long) argp->count,
+				(unsigned long long) argp->offset);
+
+	/* Obtain buffer pointer for payload.
+	 * 1 (status) + 22 (post_op_attr) + 1 (count) + 1 (eof)
+	 * + 1 (xdr opaque byte count) = 26
+	 */
+	resp->count = min(argp->count, max_blocksize);
+	svc_reserve_auth(rqstp, ((1 + NFS3_POST_OP_ATTR_WORDS + 3)<<2) + resp->count +4);
+
+	fh_copy(&resp->fh, &argp->fh);
+	nfserr = nfsd_read(rqstp, &resp->fh,
+				  argp->offset,
+			   	  rqstp->rq_vec, argp->vlen,
+				  &resp->count);
+	if (nfserr == 0) {
+		struct inode	*inode = resp->fh.fh_dentry->d_inode;
+
+		resp->eof = (argp->offset + resp->count) >= inode->i_size;
+	}
+
+	RETURN_STATUS(nfserr);
+}
+
+/*
+ * Write data to a file
+ */
+static __be32
+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 %Lu%s\n",
+				SVCFH_fmt(&argp->fh),
+				argp->len,
+				(unsigned long long) argp->offset,
+				argp->stable? " stable" : "");
+
+	fh_copy(&resp->fh, &argp->fh);
+	resp->committed = argp->stable;
+	nfserr = nfsd_write(rqstp, &resp->fh, NULL,
+				   argp->offset,
+				   rqstp->rq_vec, argp->vlen,
+				   &cnt,
+				   &resp->committed);
+	resp->count = cnt;
+	RETURN_STATUS(nfserr);
+}
+
+/*
+ * With NFSv3, CREATE processing is a lot easier than with NFSv2.
+ * At least in theory; we'll see how it fares in practice when the
+ * first reports about SunOS compatibility problems start to pour in...
+ */
+static __be32
+nfsd3_proc_create(struct svc_rqst *rqstp, struct nfsd3_createargs *argp,
+					  struct nfsd3_diropres   *resp)
+{
+	svc_fh		*dirfhp, *newfhp = NULL;
+	struct iattr	*attr;
+	__be32		nfserr;
+
+	dprintk("nfsd: CREATE(3)   %s %.*s\n",
+				SVCFH_fmt(&argp->fh),
+				argp->len,
+				argp->name);
+
+	dirfhp = fh_copy(&resp->dirfh, &argp->fh);
+	newfhp = fh_init(&resp->fh, NFS3_FHSIZE);
+	attr   = &argp->attrs;
+
+	/* Unfudge the mode bits */
+	attr->ia_mode &= ~S_IFMT;
+	if (!(attr->ia_valid & ATTR_MODE)) { 
+		attr->ia_valid |= ATTR_MODE;
+		attr->ia_mode = S_IFREG;
+	} else {
+		attr->ia_mode = (attr->ia_mode & ~S_IFMT) | S_IFREG;
+	}
+
+	/* Now create the file and set attributes */
+	nfserr = do_nfsd_create(rqstp, dirfhp, argp->name, argp->len,
+				attr, newfhp,
+				argp->createmode, (u32 *)argp->verf, NULL, NULL);
+
+	RETURN_STATUS(nfserr);
+}
+
+/*
+ * Make directory. This operation is not idempotent.
+ */
+static __be32
+nfsd3_proc_mkdir(struct svc_rqst *rqstp, struct nfsd3_createargs *argp,
+					 struct nfsd3_diropres   *resp)
+{
+	__be32	nfserr;
+
+	dprintk("nfsd: MKDIR(3)    %s %.*s\n",
+				SVCFH_fmt(&argp->fh),
+				argp->len,
+				argp->name);
+
+	argp->attrs.ia_valid &= ~ATTR_SIZE;
+	fh_copy(&resp->dirfh, &argp->fh);
+	fh_init(&resp->fh, NFS3_FHSIZE);
+	nfserr = nfsd_create(rqstp, &resp->dirfh, argp->name, argp->len,
+				    &argp->attrs, S_IFDIR, 0, &resp->fh);
+	fh_unlock(&resp->dirfh);
+	RETURN_STATUS(nfserr);
+}
+
+static __be32
+nfsd3_proc_symlink(struct svc_rqst *rqstp, struct nfsd3_symlinkargs *argp,
+					   struct nfsd3_diropres    *resp)
+{
+	__be32	nfserr;
+
+	dprintk("nfsd: SYMLINK(3)  %s %.*s -> %.*s\n",
+				SVCFH_fmt(&argp->ffh),
+				argp->flen, argp->fname,
+				argp->tlen, argp->tname);
+
+	fh_copy(&resp->dirfh, &argp->ffh);
+	fh_init(&resp->fh, NFS3_FHSIZE);
+	nfserr = nfsd_symlink(rqstp, &resp->dirfh, argp->fname, argp->flen,
+						   argp->tname, &resp->fh);
+	RETURN_STATUS(nfserr);
+}
+
+/*
+ * Make socket/fifo/device.
+ */
+static __be32
+nfsd3_proc_mknod(struct svc_rqst *rqstp, struct nfsd3_mknodargs *argp,
+					 struct nfsd3_diropres  *resp)
+{
+	__be32	nfserr;
+	int type;
+	dev_t	rdev = 0;
+
+	dprintk("nfsd: MKNOD(3)    %s %.*s\n",
+				SVCFH_fmt(&argp->fh),
+				argp->len,
+				argp->name);
+
+	fh_copy(&resp->dirfh, &argp->fh);
+	fh_init(&resp->fh, NFS3_FHSIZE);
+
+	if (argp->ftype == 0 || argp->ftype >= NF3BAD)
+		RETURN_STATUS(nfserr_inval);
+	if (argp->ftype == NF3CHR || argp->ftype == NF3BLK) {
+		rdev = MKDEV(argp->major, argp->minor);
+		if (MAJOR(rdev) != argp->major ||
+		    MINOR(rdev) != argp->minor)
+			RETURN_STATUS(nfserr_inval);
+	} else
+		if (argp->ftype != NF3SOCK && argp->ftype != NF3FIFO)
+			RETURN_STATUS(nfserr_inval);
+
+	type = nfs3_ftypes[argp->ftype];
+	nfserr = nfsd_create(rqstp, &resp->dirfh, argp->name, argp->len,
+				    &argp->attrs, type, rdev, &resp->fh);
+	fh_unlock(&resp->dirfh);
+	RETURN_STATUS(nfserr);
+}
+
+/*
+ * Remove file/fifo/socket etc.
+ */
+static __be32
+nfsd3_proc_remove(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp,
+					  struct nfsd3_attrstat  *resp)
+{
+	__be32	nfserr;
+
+	dprintk("nfsd: REMOVE(3)   %s %.*s\n",
+				SVCFH_fmt(&argp->fh),
+				argp->len,
+				argp->name);
+
+	/* Unlink. -S_IFDIR means file must not be a directory */
+	fh_copy(&resp->fh, &argp->fh);
+	nfserr = nfsd_unlink(rqstp, &resp->fh, -S_IFDIR, argp->name, argp->len);
+	fh_unlock(&resp->fh);
+	RETURN_STATUS(nfserr);
+}
+
+/*
+ * Remove a directory
+ */
+static __be32
+nfsd3_proc_rmdir(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp,
+					 struct nfsd3_attrstat  *resp)
+{
+	__be32	nfserr;
+
+	dprintk("nfsd: RMDIR(3)    %s %.*s\n",
+				SVCFH_fmt(&argp->fh),
+				argp->len,
+				argp->name);
+
+	fh_copy(&resp->fh, &argp->fh);
+	nfserr = nfsd_unlink(rqstp, &resp->fh, S_IFDIR, argp->name, argp->len);
+	fh_unlock(&resp->fh);
+	RETURN_STATUS(nfserr);
+}
+
+static __be32
+nfsd3_proc_rename(struct svc_rqst *rqstp, struct nfsd3_renameargs *argp,
+					  struct nfsd3_renameres  *resp)
+{
+	__be32	nfserr;
+
+	dprintk("nfsd: RENAME(3)   %s %.*s ->\n",
+				SVCFH_fmt(&argp->ffh),
+				argp->flen,
+				argp->fname);
+	dprintk("nfsd: -> %s %.*s\n",
+				SVCFH_fmt(&argp->tfh),
+				argp->tlen,
+				argp->tname);
+
+	fh_copy(&resp->ffh, &argp->ffh);
+	fh_copy(&resp->tfh, &argp->tfh);
+	nfserr = nfsd_rename(rqstp, &resp->ffh, argp->fname, argp->flen,
+				    &resp->tfh, argp->tname, argp->tlen);
+	RETURN_STATUS(nfserr);
+}
+
+static __be32
+nfsd3_proc_link(struct svc_rqst *rqstp, struct nfsd3_linkargs *argp,
+					struct nfsd3_linkres  *resp)
+{
+	__be32	nfserr;
+
+	dprintk("nfsd: LINK(3)     %s ->\n",
+				SVCFH_fmt(&argp->ffh));
+	dprintk("nfsd:   -> %s %.*s\n",
+				SVCFH_fmt(&argp->tfh),
+				argp->tlen,
+				argp->tname);
+
+	fh_copy(&resp->fh,  &argp->ffh);
+	fh_copy(&resp->tfh, &argp->tfh);
+	nfserr = nfsd_link(rqstp, &resp->tfh, argp->tname, argp->tlen,
+				  &resp->fh);
+	RETURN_STATUS(nfserr);
+}
+
+/*
+ * Read a portion of a directory.
+ */
+static __be32
+nfsd3_proc_readdir(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
+					   struct nfsd3_readdirres  *resp)
+{
+	__be32		nfserr;
+	int		count;
+
+	dprintk("nfsd: READDIR(3)  %s %d bytes at %d\n",
+				SVCFH_fmt(&argp->fh),
+				argp->count, (u32) argp->cookie);
+
+	/* Make sure we've room for the NULL ptr & eof flag, and shrink to
+	 * client read size */
+	count = (argp->count >> 2) - 2;
+
+	/* Read directory and encode entries on the fly */
+	fh_copy(&resp->fh, &argp->fh);
+
+	resp->buflen = count;
+	resp->common.err = nfs_ok;
+	resp->buffer = argp->buffer;
+	resp->rqstp = rqstp;
+	nfserr = nfsd_readdir(rqstp, &resp->fh, (loff_t*) &argp->cookie, 
+					&resp->common, nfs3svc_encode_entry);
+	memcpy(resp->verf, argp->verf, 8);
+	resp->count = resp->buffer - argp->buffer;
+	if (resp->offset)
+		xdr_encode_hyper(resp->offset, argp->cookie);
+
+	RETURN_STATUS(nfserr);
+}
+
+/*
+ * Read a portion of a directory, including file handles and attrs.
+ * For now, we choose to ignore the dircount parameter.
+ */
+static __be32
+nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
+					       struct nfsd3_readdirres  *resp)
+{
+	__be32	nfserr;
+	int	count = 0;
+	loff_t	offset;
+	struct page **p;
+	caddr_t	page_addr = NULL;
+
+	dprintk("nfsd: READDIR+(3) %s %d bytes at %d\n",
+				SVCFH_fmt(&argp->fh),
+				argp->count, (u32) argp->cookie);
+
+	/* Convert byte count to number of words (i.e. >> 2),
+	 * and reserve room for the NULL ptr & eof flag (-2 words) */
+	resp->count = (argp->count >> 2) - 2;
+
+	/* Read directory and encode entries on the fly */
+	fh_copy(&resp->fh, &argp->fh);
+
+	resp->common.err = nfs_ok;
+	resp->buffer = argp->buffer;
+	resp->buflen = resp->count;
+	resp->rqstp = rqstp;
+	offset = argp->cookie;
+
+	nfserr = fh_verify(rqstp, &resp->fh, S_IFDIR, NFSD_MAY_NOP);
+	if (nfserr)
+		RETURN_STATUS(nfserr);
+
+	if (resp->fh.fh_export->ex_flags & NFSEXP_NOREADDIRPLUS)
+		RETURN_STATUS(nfserr_notsupp);
+
+	nfserr = nfsd_readdir(rqstp, &resp->fh,
+				     &offset,
+				     &resp->common,
+				     nfs3svc_encode_entry_plus);
+	memcpy(resp->verf, argp->verf, 8);
+	for (p = rqstp->rq_respages + 1; p < rqstp->rq_next_page; p++) {
+		page_addr = page_address(*p);
+
+		if (((caddr_t)resp->buffer >= page_addr) &&
+		    ((caddr_t)resp->buffer < page_addr + PAGE_SIZE)) {
+			count += (caddr_t)resp->buffer - page_addr;
+			break;
+		}
+		count += PAGE_SIZE;
+	}
+	resp->count = count >> 2;
+	if (resp->offset) {
+		if (unlikely(resp->offset1)) {
+			/* we ended up with offset on a page boundary */
+			*resp->offset = htonl(offset >> 32);
+			*resp->offset1 = htonl(offset & 0xffffffff);
+			resp->offset1 = NULL;
+		} else {
+			xdr_encode_hyper(resp->offset, offset);
+		}
+	}
+
+	RETURN_STATUS(nfserr);
+}
+
+/*
+ * Get file system stats
+ */
+static __be32
+nfsd3_proc_fsstat(struct svc_rqst * rqstp, struct nfsd_fhandle    *argp,
+					   struct nfsd3_fsstatres *resp)
+{
+	__be32	nfserr;
+
+	dprintk("nfsd: FSSTAT(3)   %s\n",
+				SVCFH_fmt(&argp->fh));
+
+	nfserr = nfsd_statfs(rqstp, &argp->fh, &resp->stats, 0);
+	fh_put(&argp->fh);
+	RETURN_STATUS(nfserr);
+}
+
+/*
+ * Get file system info
+ */
+static __be32
+nfsd3_proc_fsinfo(struct svc_rqst * rqstp, struct nfsd_fhandle    *argp,
+					   struct nfsd3_fsinfores *resp)
+{
+	__be32	nfserr;
+	u32	max_blocksize = svc_max_payload(rqstp);
+
+	dprintk("nfsd: FSINFO(3)   %s\n",
+				SVCFH_fmt(&argp->fh));
+
+	resp->f_rtmax  = max_blocksize;
+	resp->f_rtpref = max_blocksize;
+	resp->f_rtmult = PAGE_SIZE;
+	resp->f_wtmax  = max_blocksize;
+	resp->f_wtpref = max_blocksize;
+	resp->f_wtmult = PAGE_SIZE;
+	resp->f_dtpref = PAGE_SIZE;
+	resp->f_maxfilesize = ~(u32) 0;
+	resp->f_properties = NFS3_FSF_DEFAULT;
+
+	nfserr = fh_verify(rqstp, &argp->fh, 0,
+			NFSD_MAY_NOP | NFSD_MAY_BYPASS_GSS_ON_ROOT);
+
+	/* Check special features of the file system. May request
+	 * different read/write sizes for file systems known to have
+	 * problems with large blocks */
+	if (nfserr == 0) {
+		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 == MSDOS_SUPER_MAGIC) {
+			resp->f_properties = NFS3_FSF_BILLYBOY;
+		}
+		resp->f_maxfilesize = sb->s_maxbytes;
+	}
+
+	fh_put(&argp->fh);
+	RETURN_STATUS(nfserr);
+}
+
+/*
+ * Get pathconf info for the specified file
+ */
+static __be32
+nfsd3_proc_pathconf(struct svc_rqst * rqstp, struct nfsd_fhandle      *argp,
+					     struct nfsd3_pathconfres *resp)
+{
+	__be32	nfserr;
+
+	dprintk("nfsd: PATHCONF(3) %s\n",
+				SVCFH_fmt(&argp->fh));
+
+	/* Set default pathconf */
+	resp->p_link_max = 255;		/* at least */
+	resp->p_name_max = 255;		/* at least */
+	resp->p_no_trunc = 0;
+	resp->p_chown_restricted = 1;
+	resp->p_case_insensitive = 0;
+	resp->p_case_preserving = 1;
+
+	nfserr = fh_verify(rqstp, &argp->fh, 0, NFSD_MAY_NOP);
+
+	if (nfserr == 0) {
+		struct super_block *sb = argp->fh.fh_dentry->d_inode->i_sb;
+
+		/* Note that we don't care for remote fs's here */
+		switch (sb->s_magic) {
+		case EXT2_SUPER_MAGIC:
+			resp->p_link_max = EXT2_LINK_MAX;
+			resp->p_name_max = EXT2_NAME_LEN;
+			break;
+		case MSDOS_SUPER_MAGIC:
+			resp->p_case_insensitive = 1;
+			resp->p_case_preserving  = 0;
+			break;
+		}
+	}
+
+	fh_put(&argp->fh);
+	RETURN_STATUS(nfserr);
+}
+
+
+/*
+ * Commit a file (range) to stable storage.
+ */
+static __be32
+nfsd3_proc_commit(struct svc_rqst * rqstp, struct nfsd3_commitargs *argp,
+					   struct nfsd3_commitres  *resp)
+{
+	__be32	nfserr;
+
+	dprintk("nfsd: COMMIT(3)   %s %u@%Lu\n",
+				SVCFH_fmt(&argp->fh),
+				argp->count,
+				(unsigned long long) argp->offset);
+
+	if (argp->offset > NFS_OFFSET_MAX)
+		RETURN_STATUS(nfserr_inval);
+
+	fh_copy(&resp->fh, &argp->fh);
+	nfserr = nfsd_commit(rqstp, &resp->fh, argp->offset, argp->count);
+
+	RETURN_STATUS(nfserr);
+}
+
+
+/*
+ * NFSv3 Server procedures.
+ * Only the results of non-idempotent operations are cached.
+ */
+#define nfs3svc_decode_fhandleargs	nfs3svc_decode_fhandle
+#define nfs3svc_encode_attrstatres	nfs3svc_encode_attrstat
+#define nfs3svc_encode_wccstatres	nfs3svc_encode_wccstat
+#define nfsd3_mkdirargs			nfsd3_createargs
+#define nfsd3_readdirplusargs		nfsd3_readdirargs
+#define nfsd3_fhandleargs		nfsd_fhandle
+#define nfsd3_fhandleres		nfsd3_attrstat
+#define nfsd3_attrstatres		nfsd3_attrstat
+#define nfsd3_wccstatres		nfsd3_attrstat
+#define nfsd3_createres			nfsd3_diropres
+#define nfsd3_voidres			nfsd3_voidargs
+struct nfsd3_voidargs { int dummy; };
+
+#define PROC(name, argt, rest, relt, cache, respsize)	\
+ { (svc_procfunc) nfsd3_proc_##name,		\
+   (kxdrproc_t) nfs3svc_decode_##argt##args,	\
+   (kxdrproc_t) nfs3svc_encode_##rest##res,	\
+   (kxdrproc_t) nfs3svc_release_##relt,		\
+   sizeof(struct nfsd3_##argt##args),		\
+   sizeof(struct nfsd3_##rest##res),		\
+   0,						\
+   cache,					\
+   respsize,					\
+ }
+
+#define ST 1		/* status*/
+#define FH 17		/* filehandle with length */
+#define AT 21		/* attributes */
+#define pAT (1+AT)	/* post attributes - conditional */
+#define WC (7+pAT)	/* WCC attributes */
+
+static struct svc_procedure		nfsd_procedures3[22] = {
+	[NFS3PROC_NULL] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_null,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_voidres,
+		.pc_argsize = sizeof(struct nfsd3_voidargs),
+		.pc_ressize = sizeof(struct nfsd3_voidres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST,
+	},
+	[NFS3PROC_GETATTR] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_getattr,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_attrstatres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
+		.pc_ressize = sizeof(struct nfsd3_attrstatres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+AT,
+	},
+	[NFS3PROC_SETATTR] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_setattr,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_sattrargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd3_sattrargs),
+		.pc_ressize = sizeof(struct nfsd3_wccstatres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+WC,
+	},
+	[NFS3PROC_LOOKUP] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_lookup,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_diropres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_argsize = sizeof(struct nfsd3_diropargs),
+		.pc_ressize = sizeof(struct nfsd3_diropres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+FH+pAT+pAT,
+	},
+	[NFS3PROC_ACCESS] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_access,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_accessargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_accessres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd3_accessargs),
+		.pc_ressize = sizeof(struct nfsd3_accessres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+pAT+1,
+	},
+	[NFS3PROC_READLINK] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_readlink,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_readlinkargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_readlinkres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd3_readlinkargs),
+		.pc_ressize = sizeof(struct nfsd3_readlinkres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+pAT+1+NFS3_MAXPATHLEN/4,
+	},
+	[NFS3PROC_READ] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_read,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_readargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_readres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd3_readargs),
+		.pc_ressize = sizeof(struct nfsd3_readres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+pAT+4+NFSSVC_MAXBLKSIZE/4,
+	},
+	[NFS3PROC_WRITE] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_write,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_writeargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_writeres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd3_writeargs),
+		.pc_ressize = sizeof(struct nfsd3_writeres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+WC+4,
+	},
+	[NFS3PROC_CREATE] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_create,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_createargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_argsize = sizeof(struct nfsd3_createargs),
+		.pc_ressize = sizeof(struct nfsd3_createres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+(1+FH+pAT)+WC,
+	},
+	[NFS3PROC_MKDIR] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_mkdir,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_mkdirargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_argsize = sizeof(struct nfsd3_mkdirargs),
+		.pc_ressize = sizeof(struct nfsd3_createres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+(1+FH+pAT)+WC,
+	},
+	[NFS3PROC_SYMLINK] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_symlink,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_symlinkargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_argsize = sizeof(struct nfsd3_symlinkargs),
+		.pc_ressize = sizeof(struct nfsd3_createres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+(1+FH+pAT)+WC,
+	},
+	[NFS3PROC_MKNOD] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_mknod,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_mknodargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_argsize = sizeof(struct nfsd3_mknodargs),
+		.pc_ressize = sizeof(struct nfsd3_createres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+(1+FH+pAT)+WC,
+	},
+	[NFS3PROC_REMOVE] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_remove,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd3_diropargs),
+		.pc_ressize = sizeof(struct nfsd3_wccstatres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+WC,
+	},
+	[NFS3PROC_RMDIR] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_rmdir,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd3_diropargs),
+		.pc_ressize = sizeof(struct nfsd3_wccstatres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+WC,
+	},
+	[NFS3PROC_RENAME] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_rename,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_renameargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_renameres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_argsize = sizeof(struct nfsd3_renameargs),
+		.pc_ressize = sizeof(struct nfsd3_renameres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+WC+WC,
+	},
+	[NFS3PROC_LINK] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_link,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_linkargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_linkres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_argsize = sizeof(struct nfsd3_linkargs),
+		.pc_ressize = sizeof(struct nfsd3_linkres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+pAT+WC,
+	},
+	[NFS3PROC_READDIR] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_readdir,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_readdirargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd3_readdirargs),
+		.pc_ressize = sizeof(struct nfsd3_readdirres),
+		.pc_cachetype = RC_NOCACHE,
+	},
+	[NFS3PROC_READDIRPLUS] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_readdirplus,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_readdirplusargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd3_readdirplusargs),
+		.pc_ressize = sizeof(struct nfsd3_readdirres),
+		.pc_cachetype = RC_NOCACHE,
+	},
+	[NFS3PROC_FSSTAT] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_fsstat,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_fsstatres,
+		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
+		.pc_ressize = sizeof(struct nfsd3_fsstatres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+pAT+2*6+1,
+	},
+	[NFS3PROC_FSINFO] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_fsinfo,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_fsinfores,
+		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
+		.pc_ressize = sizeof(struct nfsd3_fsinfores),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+pAT+12,
+	},
+	[NFS3PROC_PATHCONF] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_pathconf,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_pathconfres,
+		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
+		.pc_ressize = sizeof(struct nfsd3_pathconfres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+pAT+6,
+	},
+	[NFS3PROC_COMMIT] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_commit,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_commitargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_commitres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd3_commitargs),
+		.pc_ressize = sizeof(struct nfsd3_commitres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+WC+2,
+	},
+};
+
+struct svc_version	nfsd_version3 = {
+		.vs_vers	= 3,
+		.vs_nproc	= 22,
+		.vs_proc	= nfsd_procedures3,
+		.vs_dispatch	= nfsd_dispatch,
+		.vs_xdrsize	= NFS3_SVC_XDRSIZE,
+};

fs/nfsd/nfs4acl.c

@@ -0,0 +1,944 @@
+/*
+ *  Common NFSv4 ACL handling code.
+ *
+ *  Copyright (c) 2002, 2003 The Regents of the University of Michigan.
+ *  All rights reserved.
+ *
+ *  Marius Aamodt Eriksen <marius@umich.edu>
+ *  Jeff Sedlak <jsedlak@umich.edu>
+ *  J. Bruce Fields <bfields@umich.edu>
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the University nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/slab.h>
+#include <linux/nfs_fs.h>
+#include "nfsfh.h"
+#include "nfsd.h"
+#include "acl.h"
+#include "vfs.h"
+
+#define NFS4_ACL_TYPE_DEFAULT	0x01
+#define NFS4_ACL_DIR		0x02
+#define NFS4_ACL_OWNER		0x04
+
+/* mode bit translations: */
+#define NFS4_READ_MODE (NFS4_ACE_READ_DATA)
+#define NFS4_WRITE_MODE (NFS4_ACE_WRITE_DATA | NFS4_ACE_APPEND_DATA)
+#define NFS4_EXECUTE_MODE NFS4_ACE_EXECUTE
+#define NFS4_ANYONE_MODE (NFS4_ACE_READ_ATTRIBUTES | NFS4_ACE_READ_ACL | NFS4_ACE_SYNCHRONIZE)
+#define NFS4_OWNER_MODE (NFS4_ACE_WRITE_ATTRIBUTES | NFS4_ACE_WRITE_ACL)
+
+/* We don't support these bits; insist they be neither allowed nor denied */
+#define NFS4_MASK_UNSUPP (NFS4_ACE_DELETE | NFS4_ACE_WRITE_OWNER \
+		| NFS4_ACE_READ_NAMED_ATTRS | NFS4_ACE_WRITE_NAMED_ATTRS)
+
+/* flags used to simulate posix default ACLs */
+#define NFS4_INHERITANCE_FLAGS (NFS4_ACE_FILE_INHERIT_ACE \
+		| NFS4_ACE_DIRECTORY_INHERIT_ACE)
+
+#define NFS4_SUPPORTED_FLAGS (NFS4_INHERITANCE_FLAGS \
+		| NFS4_ACE_INHERIT_ONLY_ACE \
+		| NFS4_ACE_IDENTIFIER_GROUP)
+
+#define MASK_EQUAL(mask1, mask2) \
+	( ((mask1) & NFS4_ACE_MASK_ALL) == ((mask2) & NFS4_ACE_MASK_ALL) )
+
+static u32
+mask_from_posix(unsigned short perm, unsigned int flags)
+{
+	int mask = NFS4_ANYONE_MODE;
+
+	if (flags & NFS4_ACL_OWNER)
+		mask |= NFS4_OWNER_MODE;
+	if (perm & ACL_READ)
+		mask |= NFS4_READ_MODE;
+	if (perm & ACL_WRITE)
+		mask |= NFS4_WRITE_MODE;
+	if ((perm & ACL_WRITE) && (flags & NFS4_ACL_DIR))
+		mask |= NFS4_ACE_DELETE_CHILD;
+	if (perm & ACL_EXECUTE)
+		mask |= NFS4_EXECUTE_MODE;
+	return mask;
+}
+
+static u32
+deny_mask_from_posix(unsigned short perm, u32 flags)
+{
+	u32 mask = 0;
+
+	if (perm & ACL_READ)
+		mask |= NFS4_READ_MODE;
+	if (perm & ACL_WRITE)
+		mask |= NFS4_WRITE_MODE;
+	if ((perm & ACL_WRITE) && (flags & NFS4_ACL_DIR))
+		mask |= NFS4_ACE_DELETE_CHILD;
+	if (perm & ACL_EXECUTE)
+		mask |= NFS4_EXECUTE_MODE;
+	return mask;
+}
+
+/* XXX: modify functions to return NFS errors; they're only ever
+ * used by nfs code, after all.... */
+
+/* We only map from NFSv4 to POSIX ACLs when setting ACLs, when we err on the
+ * side of being more restrictive, so the mode bit mapping below is
+ * pessimistic.  An optimistic version would be needed to handle DENY's,
+ * but we espect to coalesce all ALLOWs and DENYs before mapping to mode
+ * bits. */
+
+static void
+low_mode_from_nfs4(u32 perm, unsigned short *mode, unsigned int flags)
+{
+	u32 write_mode = NFS4_WRITE_MODE;
+
+	if (flags & NFS4_ACL_DIR)
+		write_mode |= NFS4_ACE_DELETE_CHILD;
+	*mode = 0;
+	if ((perm & NFS4_READ_MODE) == NFS4_READ_MODE)
+		*mode |= ACL_READ;
+	if ((perm & write_mode) == write_mode)
+		*mode |= ACL_WRITE;
+	if ((perm & NFS4_EXECUTE_MODE) == NFS4_EXECUTE_MODE)
+		*mode |= ACL_EXECUTE;
+}
+
+struct ace_container {
+	struct nfs4_ace  *ace;
+	struct list_head  ace_l;
+};
+
+static short ace2type(struct nfs4_ace *);
+static void _posix_to_nfsv4_one(struct posix_acl *, struct nfs4_acl *,
+				unsigned int);
+
+int
+nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry,
+		struct nfs4_acl **acl)
+{
+	struct inode *inode = dentry->d_inode;
+	int error = 0;
+	struct posix_acl *pacl = NULL, *dpacl = NULL;
+	unsigned int flags = 0;
+	int size = 0;
+
+	pacl = get_acl(inode, ACL_TYPE_ACCESS);
+	if (!pacl)
+		pacl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
+
+	if (IS_ERR(pacl))
+		return PTR_ERR(pacl);
+
+	/* allocate for worst case: one (deny, allow) pair each: */
+	size += 2 * pacl->a_count;
+
+	if (S_ISDIR(inode->i_mode)) {
+		flags = NFS4_ACL_DIR;
+		dpacl = get_acl(inode, ACL_TYPE_DEFAULT);
+		if (IS_ERR(dpacl)) {
+			error = PTR_ERR(dpacl);
+			goto rel_pacl;
+		}
+
+		if (dpacl)
+			size += 2 * dpacl->a_count;
+	}
+
+	*acl = kmalloc(nfs4_acl_bytes(size), GFP_KERNEL);
+	if (*acl == NULL) {
+		error = -ENOMEM;
+		goto out;
+	}
+	(*acl)->naces = 0;
+
+	_posix_to_nfsv4_one(pacl, *acl, flags & ~NFS4_ACL_TYPE_DEFAULT);
+
+	if (dpacl)
+		_posix_to_nfsv4_one(dpacl, *acl, flags | NFS4_ACL_TYPE_DEFAULT);
+
+out:
+	posix_acl_release(dpacl);
+rel_pacl:
+	posix_acl_release(pacl);
+	return error;
+}
+
+struct posix_acl_summary {
+	unsigned short owner;
+	unsigned short users;
+	unsigned short group;
+	unsigned short groups;
+	unsigned short other;
+	unsigned short mask;
+};
+
+static void
+summarize_posix_acl(struct posix_acl *acl, struct posix_acl_summary *pas)
+{
+	struct posix_acl_entry *pa, *pe;
+
+	/*
+	 * Only pas.users and pas.groups need initialization; previous
+	 * posix_acl_valid() calls ensure that the other fields will be
+	 * initialized in the following loop.  But, just to placate gcc:
+	 */
+	memset(pas, 0, sizeof(*pas));
+	pas->mask = 07;
+
+	pe = acl->a_entries + acl->a_count;
+
+	FOREACH_ACL_ENTRY(pa, acl, pe) {
+		switch (pa->e_tag) {
+			case ACL_USER_OBJ:
+				pas->owner = pa->e_perm;
+				break;
+			case ACL_GROUP_OBJ:
+				pas->group = pa->e_perm;
+				break;
+			case ACL_USER:
+				pas->users |= pa->e_perm;
+				break;
+			case ACL_GROUP:
+				pas->groups |= pa->e_perm;
+				break;
+			case ACL_OTHER:
+				pas->other = pa->e_perm;
+				break;
+			case ACL_MASK:
+				pas->mask = pa->e_perm;
+				break;
+		}
+	}
+	/* We'll only care about effective permissions: */
+	pas->users &= pas->mask;
+	pas->group &= pas->mask;
+	pas->groups &= pas->mask;
+}
+
+/* We assume the acl has been verified with posix_acl_valid. */
+static void
+_posix_to_nfsv4_one(struct posix_acl *pacl, struct nfs4_acl *acl,
+						unsigned int flags)
+{
+	struct posix_acl_entry *pa, *group_owner_entry;
+	struct nfs4_ace *ace;
+	struct posix_acl_summary pas;
+	unsigned short deny;
+	int eflag = ((flags & NFS4_ACL_TYPE_DEFAULT) ?
+		NFS4_INHERITANCE_FLAGS | NFS4_ACE_INHERIT_ONLY_ACE : 0);
+
+	BUG_ON(pacl->a_count < 3);
+	summarize_posix_acl(pacl, &pas);
+
+	pa = pacl->a_entries;
+	ace = acl->aces + acl->naces;
+
+	/* We could deny everything not granted by the owner: */
+	deny = ~pas.owner;
+	/*
+	 * but it is equivalent (and simpler) to deny only what is not
+	 * granted by later entries:
+	 */
+	deny &= pas.users | pas.group | pas.groups | pas.other;
+	if (deny) {
+		ace->type = NFS4_ACE_ACCESS_DENIED_ACE_TYPE;
+		ace->flag = eflag;
+		ace->access_mask = deny_mask_from_posix(deny, flags);
+		ace->whotype = NFS4_ACL_WHO_OWNER;
+		ace++;
+		acl->naces++;
+	}
+
+	ace->type = NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE;
+	ace->flag = eflag;
+	ace->access_mask = mask_from_posix(pa->e_perm, flags | NFS4_ACL_OWNER);
+	ace->whotype = NFS4_ACL_WHO_OWNER;
+	ace++;
+	acl->naces++;
+	pa++;
+
+	while (pa->e_tag == ACL_USER) {
+		deny = ~(pa->e_perm & pas.mask);
+		deny &= pas.groups | pas.group | pas.other;
+		if (deny) {
+			ace->type = NFS4_ACE_ACCESS_DENIED_ACE_TYPE;
+			ace->flag = eflag;
+			ace->access_mask = deny_mask_from_posix(deny, flags);
+			ace->whotype = NFS4_ACL_WHO_NAMED;
+			ace->who_uid = pa->e_uid;
+			ace++;
+			acl->naces++;
+		}
+		ace->type = NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE;
+		ace->flag = eflag;
+		ace->access_mask = mask_from_posix(pa->e_perm & pas.mask,
+						   flags);
+		ace->whotype = NFS4_ACL_WHO_NAMED;
+		ace->who_uid = pa->e_uid;
+		ace++;
+		acl->naces++;
+		pa++;
+	}
+
+	/* In the case of groups, we apply allow ACEs first, then deny ACEs,
+	 * since a user can be in more than one group.  */
+
+	/* allow ACEs */
+
+	group_owner_entry = pa;
+
+	ace->type = NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE;
+	ace->flag = eflag;
+	ace->access_mask = mask_from_posix(pas.group, flags);
+	ace->whotype = NFS4_ACL_WHO_GROUP;
+	ace++;
+	acl->naces++;
+	pa++;
+
+	while (pa->e_tag == ACL_GROUP) {
+		ace->type = NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE;
+		ace->flag = eflag | NFS4_ACE_IDENTIFIER_GROUP;
+		ace->access_mask = mask_from_posix(pa->e_perm & pas.mask,
+						   flags);
+		ace->whotype = NFS4_ACL_WHO_NAMED;
+		ace->who_gid = pa->e_gid;
+		ace++;
+		acl->naces++;
+		pa++;
+	}
+
+	/* deny ACEs */
+
+	pa = group_owner_entry;
+
+	deny = ~pas.group & pas.other;
+	if (deny) {
+		ace->type = NFS4_ACE_ACCESS_DENIED_ACE_TYPE;
+		ace->flag = eflag;
+		ace->access_mask = deny_mask_from_posix(deny, flags);
+		ace->whotype = NFS4_ACL_WHO_GROUP;
+		ace++;
+		acl->naces++;
+	}
+	pa++;
+
+	while (pa->e_tag == ACL_GROUP) {
+		deny = ~(pa->e_perm & pas.mask);
+		deny &= pas.other;
+		if (deny) {
+			ace->type = NFS4_ACE_ACCESS_DENIED_ACE_TYPE;
+			ace->flag = eflag | NFS4_ACE_IDENTIFIER_GROUP;
+			ace->access_mask = deny_mask_from_posix(deny, flags);
+			ace->whotype = NFS4_ACL_WHO_NAMED;
+			ace->who_gid = pa->e_gid;
+			ace++;
+			acl->naces++;
+		}
+		pa++;
+	}
+
+	if (pa->e_tag == ACL_MASK)
+		pa++;
+	ace->type = NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE;
+	ace->flag = eflag;
+	ace->access_mask = mask_from_posix(pa->e_perm, flags);
+	ace->whotype = NFS4_ACL_WHO_EVERYONE;
+	acl->naces++;
+}
+
+static bool
+pace_gt(struct posix_acl_entry *pace1, struct posix_acl_entry *pace2)
+{
+	if (pace1->e_tag != pace2->e_tag)
+		return pace1->e_tag > pace2->e_tag;
+	if (pace1->e_tag == ACL_USER)
+		return uid_gt(pace1->e_uid, pace2->e_uid);
+	if (pace1->e_tag == ACL_GROUP)
+		return gid_gt(pace1->e_gid, pace2->e_gid);
+	return false;
+}
+
+static void
+sort_pacl_range(struct posix_acl *pacl, int start, int end) {
+	int sorted = 0, i;
+	struct posix_acl_entry tmp;
+
+	/* We just do a bubble sort; easy to do in place, and we're not
+	 * expecting acl's to be long enough to justify anything more. */
+	while (!sorted) {
+		sorted = 1;
+		for (i = start; i < end; i++) {
+			if (pace_gt(&pacl->a_entries[i],
+				    &pacl->a_entries[i+1])) {
+				sorted = 0;
+				tmp = pacl->a_entries[i];
+				pacl->a_entries[i] = pacl->a_entries[i+1];
+				pacl->a_entries[i+1] = tmp;
+			}
+		}
+	}
+}
+
+static void
+sort_pacl(struct posix_acl *pacl)
+{
+	/* posix_acl_valid requires that users and groups be in order
+	 * by uid/gid. */
+	int i, j;
+
+	/* no users or groups */
+	if (!pacl || pacl->a_count <= 4)
+		return;
+
+	i = 1;
+	while (pacl->a_entries[i].e_tag == ACL_USER)
+		i++;
+	sort_pacl_range(pacl, 1, i-1);
+
+	BUG_ON(pacl->a_entries[i].e_tag != ACL_GROUP_OBJ);
+	j = ++i;
+	while (pacl->a_entries[j].e_tag == ACL_GROUP)
+		j++;
+	sort_pacl_range(pacl, i, j-1);
+	return;
+}
+
+/*
+ * While processing the NFSv4 ACE, this maintains bitmasks representing
+ * which permission bits have been allowed and which denied to a given
+ * entity: */
+struct posix_ace_state {
+	u32 allow;
+	u32 deny;
+};
+
+struct posix_user_ace_state {
+	union {
+		kuid_t uid;
+		kgid_t gid;
+	};
+	struct posix_ace_state perms;
+};
+
+struct posix_ace_state_array {
+	int n;
+	struct posix_user_ace_state aces[];
+};
+
+/*
+ * While processing the NFSv4 ACE, this maintains the partial permissions
+ * calculated so far: */
+
+struct posix_acl_state {
+	int empty;
+	struct posix_ace_state owner;
+	struct posix_ace_state group;
+	struct posix_ace_state other;
+	struct posix_ace_state everyone;
+	struct posix_ace_state mask; /* Deny unused in this case */
+	struct posix_ace_state_array *users;
+	struct posix_ace_state_array *groups;
+};
+
+static int
+init_state(struct posix_acl_state *state, int cnt)
+{
+	int alloc;
+
+	memset(state, 0, sizeof(struct posix_acl_state));
+	state->empty = 1;
+	/*
+	 * In the worst case, each individual acl could be for a distinct
+	 * named user or group, but we don't no which, so we allocate
+	 * enough space for either:
+	 */
+	alloc = sizeof(struct posix_ace_state_array)
+		+ cnt*sizeof(struct posix_user_ace_state);
+	state->users = kzalloc(alloc, GFP_KERNEL);
+	if (!state->users)
+		return -ENOMEM;
+	state->groups = kzalloc(alloc, GFP_KERNEL);
+	if (!state->groups) {
+		kfree(state->users);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+static void
+free_state(struct posix_acl_state *state) {
+	kfree(state->users);
+	kfree(state->groups);
+}
+
+static inline void add_to_mask(struct posix_acl_state *state, struct posix_ace_state *astate)
+{
+	state->mask.allow |= astate->allow;
+}
+
+/*
+ * Certain bits (SYNCHRONIZE, DELETE, WRITE_OWNER, READ/WRITE_NAMED_ATTRS,
+ * READ_ATTRIBUTES, READ_ACL) are currently unenforceable and don't translate
+ * to traditional read/write/execute permissions.
+ *
+ * It's problematic to reject acls that use certain mode bits, because it
+ * places the burden on users to learn the rules about which bits one
+ * particular server sets, without giving the user a lot of help--we return an
+ * error that could mean any number of different things.  To make matters
+ * worse, the problematic bits might be introduced by some application that's
+ * automatically mapping from some other acl model.
+ *
+ * So wherever possible we accept anything, possibly erring on the side of
+ * denying more permissions than necessary.
+ *
+ * However we do reject *explicit* DENY's of a few bits representing
+ * permissions we could never deny:
+ */
+
+static inline int check_deny(u32 mask, int isowner)
+{
+	if (mask & (NFS4_ACE_READ_ATTRIBUTES | NFS4_ACE_READ_ACL))
+		return -EINVAL;
+	if (!isowner)
+		return 0;
+	if (mask & (NFS4_ACE_WRITE_ATTRIBUTES | NFS4_ACE_WRITE_ACL))
+		return -EINVAL;
+	return 0;
+}
+
+static struct posix_acl *
+posix_state_to_acl(struct posix_acl_state *state, unsigned int flags)
+{
+	struct posix_acl_entry *pace;
+	struct posix_acl *pacl;
+	int nace;
+	int i, error = 0;
+
+	/*
+	 * ACLs with no ACEs are treated differently in the inheritable
+	 * and effective cases: when there are no inheritable ACEs,
+	 * calls ->set_acl with a NULL ACL structure.
+	 */
+	if (state->empty && (flags & NFS4_ACL_TYPE_DEFAULT))
+		return NULL;
+
+	/*
+	 * When there are no effective ACEs, the following will end
+	 * up setting a 3-element effective posix ACL with all
+	 * permissions zero.
+	 */
+	if (!state->users->n && !state->groups->n)
+		nace = 3;
+	else /* Note we also include a MASK ACE in this case: */
+		nace = 4 + state->users->n + state->groups->n;
+	pacl = posix_acl_alloc(nace, GFP_KERNEL);
+	if (!pacl)
+		return ERR_PTR(-ENOMEM);
+
+	pace = pacl->a_entries;
+	pace->e_tag = ACL_USER_OBJ;
+	error = check_deny(state->owner.deny, 1);
+	if (error)
+		goto out_err;
+	low_mode_from_nfs4(state->owner.allow, &pace->e_perm, flags);
+
+	for (i=0; i < state->users->n; i++) {
+		pace++;
+		pace->e_tag = ACL_USER;
+		error = check_deny(state->users->aces[i].perms.deny, 0);
+		if (error)
+			goto out_err;
+		low_mode_from_nfs4(state->users->aces[i].perms.allow,
+					&pace->e_perm, flags);
+		pace->e_uid = state->users->aces[i].uid;
+		add_to_mask(state, &state->users->aces[i].perms);
+	}
+
+	pace++;
+	pace->e_tag = ACL_GROUP_OBJ;
+	error = check_deny(state->group.deny, 0);
+	if (error)
+		goto out_err;
+	low_mode_from_nfs4(state->group.allow, &pace->e_perm, flags);
+	add_to_mask(state, &state->group);
+
+	for (i=0; i < state->groups->n; i++) {
+		pace++;
+		pace->e_tag = ACL_GROUP;
+		error = check_deny(state->groups->aces[i].perms.deny, 0);
+		if (error)
+			goto out_err;
+		low_mode_from_nfs4(state->groups->aces[i].perms.allow,
+					&pace->e_perm, flags);
+		pace->e_gid = state->groups->aces[i].gid;
+		add_to_mask(state, &state->groups->aces[i].perms);
+	}
+
+	if (state->users->n || state->groups->n) {
+		pace++;
+		pace->e_tag = ACL_MASK;
+		low_mode_from_nfs4(state->mask.allow, &pace->e_perm, flags);
+	}
+
+	pace++;
+	pace->e_tag = ACL_OTHER;
+	error = check_deny(state->other.deny, 0);
+	if (error)
+		goto out_err;
+	low_mode_from_nfs4(state->other.allow, &pace->e_perm, flags);
+
+	return pacl;
+out_err:
+	posix_acl_release(pacl);
+	return ERR_PTR(error);
+}
+
+static inline void allow_bits(struct posix_ace_state *astate, u32 mask)
+{
+	/* Allow all bits in the mask not already denied: */
+	astate->allow |= mask & ~astate->deny;
+}
+
+static inline void deny_bits(struct posix_ace_state *astate, u32 mask)
+{
+	/* Deny all bits in the mask not already allowed: */
+	astate->deny |= mask & ~astate->allow;
+}
+
+static int find_uid(struct posix_acl_state *state, kuid_t uid)
+{
+	struct posix_ace_state_array *a = state->users;
+	int i;
+
+	for (i = 0; i < a->n; i++)
+		if (uid_eq(a->aces[i].uid, uid))
+			return i;
+	/* Not found: */
+	a->n++;
+	a->aces[i].uid = uid;
+	a->aces[i].perms.allow = state->everyone.allow;
+	a->aces[i].perms.deny  = state->everyone.deny;
+
+	return i;
+}
+
+static int find_gid(struct posix_acl_state *state, kgid_t gid)
+{
+	struct posix_ace_state_array *a = state->groups;
+	int i;
+
+	for (i = 0; i < a->n; i++)
+		if (gid_eq(a->aces[i].gid, gid))
+			return i;
+	/* Not found: */
+	a->n++;
+	a->aces[i].gid = gid;
+	a->aces[i].perms.allow = state->everyone.allow;
+	a->aces[i].perms.deny  = state->everyone.deny;
+
+	return i;
+}
+
+static void deny_bits_array(struct posix_ace_state_array *a, u32 mask)
+{
+	int i;
+
+	for (i=0; i < a->n; i++)
+		deny_bits(&a->aces[i].perms, mask);
+}
+
+static void allow_bits_array(struct posix_ace_state_array *a, u32 mask)
+{
+	int i;
+
+	for (i=0; i < a->n; i++)
+		allow_bits(&a->aces[i].perms, mask);
+}
+
+static void process_one_v4_ace(struct posix_acl_state *state,
+				struct nfs4_ace *ace)
+{
+	u32 mask = ace->access_mask;
+	int i;
+
+	state->empty = 0;
+
+	switch (ace2type(ace)) {
+	case ACL_USER_OBJ:
+		if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
+			allow_bits(&state->owner, mask);
+		} else {
+			deny_bits(&state->owner, mask);
+		}
+		break;
+	case ACL_USER:
+		i = find_uid(state, ace->who_uid);
+		if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
+			allow_bits(&state->users->aces[i].perms, mask);
+		} else {
+			deny_bits(&state->users->aces[i].perms, mask);
+			mask = state->users->aces[i].perms.deny;
+			deny_bits(&state->owner, mask);
+		}
+		break;
+	case ACL_GROUP_OBJ:
+		if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
+			allow_bits(&state->group, mask);
+		} else {
+			deny_bits(&state->group, mask);
+			mask = state->group.deny;
+			deny_bits(&state->owner, mask);
+			deny_bits(&state->everyone, mask);
+			deny_bits_array(state->users, mask);
+			deny_bits_array(state->groups, mask);
+		}
+		break;
+	case ACL_GROUP:
+		i = find_gid(state, ace->who_gid);
+		if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
+			allow_bits(&state->groups->aces[i].perms, mask);
+		} else {
+			deny_bits(&state->groups->aces[i].perms, mask);
+			mask = state->groups->aces[i].perms.deny;
+			deny_bits(&state->owner, mask);
+			deny_bits(&state->group, mask);
+			deny_bits(&state->everyone, mask);
+			deny_bits_array(state->users, mask);
+			deny_bits_array(state->groups, mask);
+		}
+		break;
+	case ACL_OTHER:
+		if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
+			allow_bits(&state->owner, mask);
+			allow_bits(&state->group, mask);
+			allow_bits(&state->other, mask);
+			allow_bits(&state->everyone, mask);
+			allow_bits_array(state->users, mask);
+			allow_bits_array(state->groups, mask);
+		} else {
+			deny_bits(&state->owner, mask);
+			deny_bits(&state->group, mask);
+			deny_bits(&state->other, mask);
+			deny_bits(&state->everyone, mask);
+			deny_bits_array(state->users, mask);
+			deny_bits_array(state->groups, mask);
+		}
+	}
+}
+
+static int nfs4_acl_nfsv4_to_posix(struct nfs4_acl *acl,
+		struct posix_acl **pacl, struct posix_acl **dpacl,
+		unsigned int flags)
+{
+	struct posix_acl_state effective_acl_state, default_acl_state;
+	struct nfs4_ace *ace;
+	int ret;
+
+	ret = init_state(&effective_acl_state, acl->naces);
+	if (ret)
+		return ret;
+	ret = init_state(&default_acl_state, acl->naces);
+	if (ret)
+		goto out_estate;
+	ret = -EINVAL;
+	for (ace = acl->aces; ace < acl->aces + acl->naces; ace++) {
+		if (ace->type != NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE &&
+		    ace->type != NFS4_ACE_ACCESS_DENIED_ACE_TYPE)
+			goto out_dstate;
+		if (ace->flag & ~NFS4_SUPPORTED_FLAGS)
+			goto out_dstate;
+		if ((ace->flag & NFS4_INHERITANCE_FLAGS) == 0) {
+			process_one_v4_ace(&effective_acl_state, ace);
+			continue;
+		}
+		if (!(flags & NFS4_ACL_DIR))
+			goto out_dstate;
+		/*
+		 * Note that when only one of FILE_INHERIT or DIRECTORY_INHERIT
+		 * is set, we're effectively turning on the other.  That's OK,
+		 * according to rfc 3530.
+		 */
+		process_one_v4_ace(&default_acl_state, ace);
+
+		if (!(ace->flag & NFS4_ACE_INHERIT_ONLY_ACE))
+			process_one_v4_ace(&effective_acl_state, ace);
+	}
+	*pacl = posix_state_to_acl(&effective_acl_state, flags);
+	if (IS_ERR(*pacl)) {
+		ret = PTR_ERR(*pacl);
+		*pacl = NULL;
+		goto out_dstate;
+	}
+	*dpacl = posix_state_to_acl(&default_acl_state,
+						flags | NFS4_ACL_TYPE_DEFAULT);
+	if (IS_ERR(*dpacl)) {
+		ret = PTR_ERR(*dpacl);
+		*dpacl = NULL;
+		posix_acl_release(*pacl);
+		*pacl = NULL;
+		goto out_dstate;
+	}
+	sort_pacl(*pacl);
+	sort_pacl(*dpacl);
+	ret = 0;
+out_dstate:
+	free_state(&default_acl_state);
+out_estate:
+	free_state(&effective_acl_state);
+	return ret;
+}
+
+__be32
+nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		struct nfs4_acl *acl)
+{
+	__be32 error;
+	int host_error;
+	struct dentry *dentry;
+	struct inode *inode;
+	struct posix_acl *pacl = NULL, *dpacl = NULL;
+	unsigned int flags = 0;
+
+	/* Get inode */
+	error = fh_verify(rqstp, fhp, 0, NFSD_MAY_SATTR);
+	if (error)
+		return error;
+
+	dentry = fhp->fh_dentry;
+	inode = dentry->d_inode;
+
+	if (!inode->i_op->set_acl || !IS_POSIXACL(inode))
+		return nfserr_attrnotsupp;
+
+	if (S_ISDIR(inode->i_mode))
+		flags = NFS4_ACL_DIR;
+
+	host_error = nfs4_acl_nfsv4_to_posix(acl, &pacl, &dpacl, flags);
+	if (host_error == -EINVAL)
+		return nfserr_attrnotsupp;
+	if (host_error < 0)
+		goto out_nfserr;
+
+	host_error = inode->i_op->set_acl(inode, pacl, ACL_TYPE_ACCESS);
+	if (host_error < 0)
+		goto out_release;
+
+	if (S_ISDIR(inode->i_mode)) {
+		host_error = inode->i_op->set_acl(inode, dpacl,
+						  ACL_TYPE_DEFAULT);
+	}
+
+out_release:
+	posix_acl_release(pacl);
+	posix_acl_release(dpacl);
+out_nfserr:
+	if (host_error == -EOPNOTSUPP)
+		return nfserr_attrnotsupp;
+	else
+		return nfserrno(host_error);
+}
+
+
+static short
+ace2type(struct nfs4_ace *ace)
+{
+	switch (ace->whotype) {
+		case NFS4_ACL_WHO_NAMED:
+			return (ace->flag & NFS4_ACE_IDENTIFIER_GROUP ?
+					ACL_GROUP : ACL_USER);
+		case NFS4_ACL_WHO_OWNER:
+			return ACL_USER_OBJ;
+		case NFS4_ACL_WHO_GROUP:
+			return ACL_GROUP_OBJ;
+		case NFS4_ACL_WHO_EVERYONE:
+			return ACL_OTHER;
+	}
+	BUG();
+	return -1;
+}
+
+/*
+ * return the size of the struct nfs4_acl required to represent an acl
+ * with @entries entries.
+ */
+int nfs4_acl_bytes(int entries)
+{
+	return sizeof(struct nfs4_acl) + entries * sizeof(struct nfs4_ace);
+}
+
+static struct {
+	char *string;
+	int   stringlen;
+	int type;
+} s2t_map[] = {
+	{
+		.string    = "OWNER@",
+		.stringlen = sizeof("OWNER@") - 1,
+		.type      = NFS4_ACL_WHO_OWNER,
+	},
+	{
+		.string    = "GROUP@",
+		.stringlen = sizeof("GROUP@") - 1,
+		.type      = NFS4_ACL_WHO_GROUP,
+	},
+	{
+		.string    = "EVERYONE@",
+		.stringlen = sizeof("EVERYONE@") - 1,
+		.type      = NFS4_ACL_WHO_EVERYONE,
+	},
+};
+
+int
+nfs4_acl_get_whotype(char *p, u32 len)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(s2t_map); i++) {
+		if (s2t_map[i].stringlen == len &&
+				0 == memcmp(s2t_map[i].string, p, len))
+			return s2t_map[i].type;
+	}
+	return NFS4_ACL_WHO_NAMED;
+}
+
+__be32 nfs4_acl_write_who(struct xdr_stream *xdr, int who)
+{
+	__be32 *p;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(s2t_map); i++) {
+		if (s2t_map[i].type != who)
+			continue;
+		p = xdr_reserve_space(xdr, s2t_map[i].stringlen + 4);
+		if (!p)
+			return nfserr_resource;
+		p = xdr_encode_opaque(p, s2t_map[i].string,
+					s2t_map[i].stringlen);
+		return 0;
+	}
+	WARN_ON_ONCE(1);
+	return nfserr_serverfault;
+}

fs/nfsd/nfs4idmap.c

@@ -0,0 +1,666 @@
+/*
+ *  Mapping of UID/GIDs to name and vice versa.
+ *
+ *  Copyright (c) 2002, 2003 The Regents of the University of
+ *  Michigan.  All rights reserved.
+ *
+ *  Marius Aamodt Eriksen <marius@umich.edu>
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the University nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/sunrpc/svc_xprt.h>
+#include <net/net_namespace.h>
+#include "idmap.h"
+#include "nfsd.h"
+#include "netns.h"
+
+/*
+ * Turn off idmapping when using AUTH_SYS.
+ */
+static bool nfs4_disable_idmapping = true;
+module_param(nfs4_disable_idmapping, bool, 0644);
+MODULE_PARM_DESC(nfs4_disable_idmapping,
+		"Turn off server's NFSv4 idmapping when using 'sec=sys'");
+
+/*
+ * Cache entry
+ */
+
+/*
+ * XXX we know that IDMAP_NAMESZ < PAGE_SIZE, but it's ugly to rely on
+ * that.
+ */
+
+#define IDMAP_TYPE_USER  0
+#define IDMAP_TYPE_GROUP 1
+
+struct ent {
+	struct cache_head h;
+	int               type;		       /* User / Group */
+	u32               id;
+	char              name[IDMAP_NAMESZ];
+	char              authname[IDMAP_NAMESZ];
+};
+
+/* Common entry handling */
+
+#define ENT_HASHBITS          8
+#define ENT_HASHMAX           (1 << ENT_HASHBITS)
+
+static void
+ent_init(struct cache_head *cnew, struct cache_head *citm)
+{
+	struct ent *new = container_of(cnew, struct ent, h);
+	struct ent *itm = container_of(citm, struct ent, h);
+
+	new->id = itm->id;
+	new->type = itm->type;
+
+	strlcpy(new->name, itm->name, sizeof(new->name));
+	strlcpy(new->authname, itm->authname, sizeof(new->name));
+}
+
+static void
+ent_put(struct kref *ref)
+{
+	struct ent *map = container_of(ref, struct ent, h.ref);
+	kfree(map);
+}
+
+static struct cache_head *
+ent_alloc(void)
+{
+	struct ent *e = kmalloc(sizeof(*e), GFP_KERNEL);
+	if (e)
+		return &e->h;
+	else
+		return NULL;
+}
+
+/*
+ * ID -> Name cache
+ */
+
+static uint32_t
+idtoname_hash(struct ent *ent)
+{
+	uint32_t hash;
+
+	hash = hash_str(ent->authname, ENT_HASHBITS);
+	hash = hash_long(hash ^ ent->id, ENT_HASHBITS);
+
+	/* Flip LSB for user/group */
+	if (ent->type == IDMAP_TYPE_GROUP)
+		hash ^= 1;
+
+	return hash;
+}
+
+static void
+idtoname_request(struct cache_detail *cd, struct cache_head *ch, char **bpp,
+    int *blen)
+{
+ 	struct ent *ent = container_of(ch, struct ent, h);
+	char idstr[11];
+
+	qword_add(bpp, blen, ent->authname);
+	snprintf(idstr, sizeof(idstr), "%u", ent->id);
+	qword_add(bpp, blen, ent->type == IDMAP_TYPE_GROUP ? "group" : "user");
+	qword_add(bpp, blen, idstr);
+
+	(*bpp)[-1] = '\n';
+}
+
+static int
+idtoname_match(struct cache_head *ca, struct cache_head *cb)
+{
+	struct ent *a = container_of(ca, struct ent, h);
+	struct ent *b = container_of(cb, struct ent, h);
+
+	return (a->id == b->id && a->type == b->type &&
+	    strcmp(a->authname, b->authname) == 0);
+}
+
+static int
+idtoname_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h)
+{
+	struct ent *ent;
+
+	if (h == NULL) {
+		seq_puts(m, "#domain type id [name]\n");
+		return 0;
+	}
+	ent = container_of(h, struct ent, h);
+	seq_printf(m, "%s %s %u", ent->authname,
+			ent->type == IDMAP_TYPE_GROUP ? "group" : "user",
+			ent->id);
+	if (test_bit(CACHE_VALID, &h->flags))
+		seq_printf(m, " %s", ent->name);
+	seq_printf(m, "\n");
+	return 0;
+}
+
+static void
+warn_no_idmapd(struct cache_detail *detail, int has_died)
+{
+	printk("nfsd: nfsv4 idmapping failing: has idmapd %s?\n",
+			has_died ? "died" : "not been started");
+}
+
+
+static int         idtoname_parse(struct cache_detail *, char *, int);
+static struct ent *idtoname_lookup(struct cache_detail *, struct ent *);
+static struct ent *idtoname_update(struct cache_detail *, struct ent *,
+				   struct ent *);
+
+static struct cache_detail idtoname_cache_template = {
+	.owner		= THIS_MODULE,
+	.hash_size	= ENT_HASHMAX,
+	.name		= "nfs4.idtoname",
+	.cache_put	= ent_put,
+	.cache_request	= idtoname_request,
+	.cache_parse	= idtoname_parse,
+	.cache_show	= idtoname_show,
+	.warn_no_listener = warn_no_idmapd,
+	.match		= idtoname_match,
+	.init		= ent_init,
+	.update		= ent_init,
+	.alloc		= ent_alloc,
+};
+
+static int
+idtoname_parse(struct cache_detail *cd, char *buf, int buflen)
+{
+	struct ent ent, *res;
+	char *buf1, *bp;
+	int len;
+	int error = -EINVAL;
+
+	if (buf[buflen - 1] != '\n')
+		return (-EINVAL);
+	buf[buflen - 1]= '\0';
+
+	buf1 = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (buf1 == NULL)
+		return (-ENOMEM);
+
+	memset(&ent, 0, sizeof(ent));
+
+	/* Authentication name */
+	len = qword_get(&buf, buf1, PAGE_SIZE);
+	if (len <= 0 || len >= IDMAP_NAMESZ)
+		goto out;
+	memcpy(ent.authname, buf1, sizeof(ent.authname));
+
+	/* Type */
+	if (qword_get(&buf, buf1, PAGE_SIZE) <= 0)
+		goto out;
+	ent.type = strcmp(buf1, "user") == 0 ?
+		IDMAP_TYPE_USER : IDMAP_TYPE_GROUP;
+
+	/* ID */
+	if (qword_get(&buf, buf1, PAGE_SIZE) <= 0)
+		goto out;
+	ent.id = simple_strtoul(buf1, &bp, 10);
+	if (bp == buf1)
+		goto out;
+
+	/* expiry */
+	ent.h.expiry_time = get_expiry(&buf);
+	if (ent.h.expiry_time == 0)
+		goto out;
+
+	error = -ENOMEM;
+	res = idtoname_lookup(cd, &ent);
+	if (!res)
+		goto out;
+
+	/* Name */
+	error = -EINVAL;
+	len = qword_get(&buf, buf1, PAGE_SIZE);
+	if (len < 0 || len >= IDMAP_NAMESZ)
+		goto out;
+	if (len == 0)
+		set_bit(CACHE_NEGATIVE, &ent.h.flags);
+	else
+		memcpy(ent.name, buf1, sizeof(ent.name));
+	error = -ENOMEM;
+	res = idtoname_update(cd, &ent, res);
+	if (res == NULL)
+		goto out;
+
+	cache_put(&res->h, cd);
+	error = 0;
+out:
+	kfree(buf1);
+	return error;
+}
+
+static struct ent *
+idtoname_lookup(struct cache_detail *cd, struct ent *item)
+{
+	struct cache_head *ch = sunrpc_cache_lookup(cd, &item->h,
+						    idtoname_hash(item));
+	if (ch)
+		return container_of(ch, struct ent, h);
+	else
+		return NULL;
+}
+
+static struct ent *
+idtoname_update(struct cache_detail *cd, struct ent *new, struct ent *old)
+{
+	struct cache_head *ch = sunrpc_cache_update(cd, &new->h, &old->h,
+						    idtoname_hash(new));
+	if (ch)
+		return container_of(ch, struct ent, h);
+	else
+		return NULL;
+}
+
+
+/*
+ * Name -> ID cache
+ */
+
+static inline int
+nametoid_hash(struct ent *ent)
+{
+	return hash_str(ent->name, ENT_HASHBITS);
+}
+
+static void
+nametoid_request(struct cache_detail *cd, struct cache_head *ch, char **bpp,
+    int *blen)
+{
+ 	struct ent *ent = container_of(ch, struct ent, h);
+
+	qword_add(bpp, blen, ent->authname);
+	qword_add(bpp, blen, ent->type == IDMAP_TYPE_GROUP ? "group" : "user");
+	qword_add(bpp, blen, ent->name);
+
+	(*bpp)[-1] = '\n';
+}
+
+static int
+nametoid_match(struct cache_head *ca, struct cache_head *cb)
+{
+	struct ent *a = container_of(ca, struct ent, h);
+	struct ent *b = container_of(cb, struct ent, h);
+
+	return (a->type == b->type && strcmp(a->name, b->name) == 0 &&
+	    strcmp(a->authname, b->authname) == 0);
+}
+
+static int
+nametoid_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h)
+{
+	struct ent *ent;
+
+	if (h == NULL) {
+		seq_puts(m, "#domain type name [id]\n");
+		return 0;
+	}
+	ent = container_of(h, struct ent, h);
+	seq_printf(m, "%s %s %s", ent->authname,
+			ent->type == IDMAP_TYPE_GROUP ? "group" : "user",
+			ent->name);
+	if (test_bit(CACHE_VALID, &h->flags))
+		seq_printf(m, " %u", ent->id);
+	seq_printf(m, "\n");
+	return 0;
+}
+
+static struct ent *nametoid_lookup(struct cache_detail *, struct ent *);
+static struct ent *nametoid_update(struct cache_detail *, struct ent *,
+				   struct ent *);
+static int         nametoid_parse(struct cache_detail *, char *, int);
+
+static struct cache_detail nametoid_cache_template = {
+	.owner		= THIS_MODULE,
+	.hash_size	= ENT_HASHMAX,
+	.name		= "nfs4.nametoid",
+	.cache_put	= ent_put,
+	.cache_request	= nametoid_request,
+	.cache_parse	= nametoid_parse,
+	.cache_show	= nametoid_show,
+	.warn_no_listener = warn_no_idmapd,
+	.match		= nametoid_match,
+	.init		= ent_init,
+	.update		= ent_init,
+	.alloc		= ent_alloc,
+};
+
+static int
+nametoid_parse(struct cache_detail *cd, char *buf, int buflen)
+{
+	struct ent ent, *res;
+	char *buf1;
+	int len, error = -EINVAL;
+
+	if (buf[buflen - 1] != '\n')
+		return (-EINVAL);
+	buf[buflen - 1]= '\0';
+
+	buf1 = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (buf1 == NULL)
+		return (-ENOMEM);
+
+	memset(&ent, 0, sizeof(ent));
+
+	/* Authentication name */
+	len = qword_get(&buf, buf1, PAGE_SIZE);
+	if (len <= 0 || len >= IDMAP_NAMESZ)
+		goto out;
+	memcpy(ent.authname, buf1, sizeof(ent.authname));
+
+	/* Type */
+	if (qword_get(&buf, buf1, PAGE_SIZE) <= 0)
+		goto out;
+	ent.type = strcmp(buf1, "user") == 0 ?
+		IDMAP_TYPE_USER : IDMAP_TYPE_GROUP;
+
+	/* Name */
+	len = qword_get(&buf, buf1, PAGE_SIZE);
+	if (len <= 0 || len >= IDMAP_NAMESZ)
+		goto out;
+	memcpy(ent.name, buf1, sizeof(ent.name));
+
+	/* expiry */
+	ent.h.expiry_time = get_expiry(&buf);
+	if (ent.h.expiry_time == 0)
+		goto out;
+
+	/* ID */
+	error = get_int(&buf, &ent.id);
+	if (error == -EINVAL)
+		goto out;
+	if (error == -ENOENT)
+		set_bit(CACHE_NEGATIVE, &ent.h.flags);
+
+	error = -ENOMEM;
+	res = nametoid_lookup(cd, &ent);
+	if (res == NULL)
+		goto out;
+	res = nametoid_update(cd, &ent, res);
+	if (res == NULL)
+		goto out;
+
+	cache_put(&res->h, cd);
+	error = 0;
+out:
+	kfree(buf1);
+	return (error);
+}
+
+
+static struct ent *
+nametoid_lookup(struct cache_detail *cd, struct ent *item)
+{
+	struct cache_head *ch = sunrpc_cache_lookup(cd, &item->h,
+						    nametoid_hash(item));
+	if (ch)
+		return container_of(ch, struct ent, h);
+	else
+		return NULL;
+}
+
+static struct ent *
+nametoid_update(struct cache_detail *cd, struct ent *new, struct ent *old)
+{
+	struct cache_head *ch = sunrpc_cache_update(cd, &new->h, &old->h,
+						    nametoid_hash(new));
+	if (ch)
+		return container_of(ch, struct ent, h);
+	else
+		return NULL;
+}
+
+/*
+ * Exported API
+ */
+
+int
+nfsd_idmap_init(struct net *net)
+{
+	int rv;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	nn->idtoname_cache = cache_create_net(&idtoname_cache_template, net);
+	if (IS_ERR(nn->idtoname_cache))
+		return PTR_ERR(nn->idtoname_cache);
+	rv = cache_register_net(nn->idtoname_cache, net);
+	if (rv)
+		goto destroy_idtoname_cache;
+	nn->nametoid_cache = cache_create_net(&nametoid_cache_template, net);
+	if (IS_ERR(nn->nametoid_cache)) {
+		rv = PTR_ERR(nn->nametoid_cache);
+		goto unregister_idtoname_cache;
+	}
+	rv = cache_register_net(nn->nametoid_cache, net);
+	if (rv)
+		goto destroy_nametoid_cache;
+	return 0;
+
+destroy_nametoid_cache:
+	cache_destroy_net(nn->nametoid_cache, net);
+unregister_idtoname_cache:
+	cache_unregister_net(nn->idtoname_cache, net);
+destroy_idtoname_cache:
+	cache_destroy_net(nn->idtoname_cache, net);
+	return rv;
+}
+
+void
+nfsd_idmap_shutdown(struct net *net)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	cache_unregister_net(nn->idtoname_cache, net);
+	cache_unregister_net(nn->nametoid_cache, net);
+	cache_destroy_net(nn->idtoname_cache, net);
+	cache_destroy_net(nn->nametoid_cache, net);
+}
+
+static int
+idmap_lookup(struct svc_rqst *rqstp,
+		struct ent *(*lookup_fn)(struct cache_detail *, struct ent *),
+		struct ent *key, struct cache_detail *detail, struct ent **item)
+{
+	int ret;
+
+	*item = lookup_fn(detail, key);
+	if (!*item)
+		return -ENOMEM;
+ retry:
+	ret = cache_check(detail, &(*item)->h, &rqstp->rq_chandle);
+
+	if (ret == -ETIMEDOUT) {
+		struct ent *prev_item = *item;
+		*item = lookup_fn(detail, key);
+		if (*item != prev_item)
+			goto retry;
+		cache_put(&(*item)->h, detail);
+	}
+	return ret;
+}
+
+static char *
+rqst_authname(struct svc_rqst *rqstp)
+{
+	struct auth_domain *clp;
+
+	clp = rqstp->rq_gssclient ? rqstp->rq_gssclient : rqstp->rq_client;
+	return clp->name;
+}
+
+static __be32
+idmap_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen,
+		u32 *id)
+{
+	struct ent *item, key = {
+		.type = type,
+	};
+	int ret;
+	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+
+	if (namelen + 1 > sizeof(key.name))
+		return nfserr_badowner;
+	memcpy(key.name, name, namelen);
+	key.name[namelen] = '\0';
+	strlcpy(key.authname, rqst_authname(rqstp), sizeof(key.authname));
+	ret = idmap_lookup(rqstp, nametoid_lookup, &key, nn->nametoid_cache, &item);
+	if (ret == -ENOENT)
+		return nfserr_badowner;
+	if (ret)
+		return nfserrno(ret);
+	*id = item->id;
+	cache_put(&item->h, nn->nametoid_cache);
+	return 0;
+}
+
+static __be32 encode_ascii_id(struct xdr_stream *xdr, u32 id)
+{
+	char buf[11];
+	int len;
+	__be32 *p;
+
+	len = sprintf(buf, "%u", id);
+	p = xdr_reserve_space(xdr, len + 4);
+	if (!p)
+		return nfserr_resource;
+	p = xdr_encode_opaque(p, buf, len);
+	return 0;
+}
+
+static __be32 idmap_id_to_name(struct xdr_stream *xdr,
+			       struct svc_rqst *rqstp, int type, u32 id)
+{
+	struct ent *item, key = {
+		.id = id,
+		.type = type,
+	};
+	__be32 *p;
+	int ret;
+	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+
+	strlcpy(key.authname, rqst_authname(rqstp), sizeof(key.authname));
+	ret = idmap_lookup(rqstp, idtoname_lookup, &key, nn->idtoname_cache, &item);
+	if (ret == -ENOENT)
+		return encode_ascii_id(xdr, id);
+	if (ret)
+		return nfserrno(ret);
+	ret = strlen(item->name);
+	WARN_ON_ONCE(ret > IDMAP_NAMESZ);
+	p = xdr_reserve_space(xdr, ret + 4);
+	if (!p)
+		return nfserr_resource;
+	p = xdr_encode_opaque(p, item->name, ret);
+	cache_put(&item->h, nn->idtoname_cache);
+	return 0;
+}
+
+static bool
+numeric_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, u32 *id)
+{
+	int ret;
+	char buf[11];
+
+	if (namelen + 1 > sizeof(buf))
+		/* too long to represent a 32-bit id: */
+		return false;
+	/* Just to make sure it's null-terminated: */
+	memcpy(buf, name, namelen);
+	buf[namelen] = '\0';
+	ret = kstrtouint(buf, 10, id);
+	return ret == 0;
+}
+
+static __be32
+do_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, u32 *id)
+{
+	if (nfs4_disable_idmapping && rqstp->rq_cred.cr_flavor < RPC_AUTH_GSS)
+		if (numeric_name_to_id(rqstp, type, name, namelen, id))
+			return 0;
+		/*
+		 * otherwise, fall through and try idmapping, for
+		 * backwards compatibility with clients sending names:
+		 */
+	return idmap_name_to_id(rqstp, type, name, namelen, id);
+}
+
+static __be32 encode_name_from_id(struct xdr_stream *xdr,
+				  struct svc_rqst *rqstp, int type, u32 id)
+{
+	if (nfs4_disable_idmapping && rqstp->rq_cred.cr_flavor < RPC_AUTH_GSS)
+		return encode_ascii_id(xdr, id);
+	return idmap_id_to_name(xdr, rqstp, type, id);
+}
+
+__be32
+nfsd_map_name_to_uid(struct svc_rqst *rqstp, const char *name, size_t namelen,
+		kuid_t *uid)
+{
+	__be32 status;
+	u32 id = -1;
+	status = do_name_to_id(rqstp, IDMAP_TYPE_USER, name, namelen, &id);
+	*uid = make_kuid(&init_user_ns, id);
+	if (!uid_valid(*uid))
+		status = nfserr_badowner;
+	return status;
+}
+
+__be32
+nfsd_map_name_to_gid(struct svc_rqst *rqstp, const char *name, size_t namelen,
+		kgid_t *gid)
+{
+	__be32 status;
+	u32 id = -1;
+	status = do_name_to_id(rqstp, IDMAP_TYPE_GROUP, name, namelen, &id);
+	*gid = make_kgid(&init_user_ns, id);
+	if (!gid_valid(*gid))
+		status = nfserr_badowner;
+	return status;
+}
+
+__be32 nfsd4_encode_user(struct xdr_stream *xdr, struct svc_rqst *rqstp,
+			 kuid_t uid)
+{
+	u32 id = from_kuid(&init_user_ns, uid);
+	return encode_name_from_id(xdr, rqstp, IDMAP_TYPE_USER, id);
+}
+
+__be32 nfsd4_encode_group(struct xdr_stream *xdr, struct svc_rqst *rqstp,
+			  kgid_t gid)
+{
+	u32 id = from_kgid(&init_user_ns, gid);
+	return encode_name_from_id(xdr, rqstp, IDMAP_TYPE_GROUP, id);
+}

fs/nfsd/nfscache.c

@@ -0,0 +1,633 @@
+/*
+ * Request reply cache. This is currently a global cache, but this may
+ * change in the future and be a per-client cache.
+ *
+ * This code is heavily inspired by the 44BSD implementation, although
+ * it does things a bit differently.
+ *
+ * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
+ */
+
+#include <linux/slab.h>
+#include <linux/sunrpc/addr.h>
+#include <linux/highmem.h>
+#include <linux/log2.h>
+#include <linux/hash.h>
+#include <net/checksum.h>
+
+#include "nfsd.h"
+#include "cache.h"
+
+#define NFSDDBG_FACILITY	NFSDDBG_REPCACHE
+
+/*
+ * We use this value to determine the number of hash buckets from the max
+ * cache size, the idea being that when the cache is at its maximum number
+ * of entries, then this should be the average number of entries per bucket.
+ */
+#define TARGET_BUCKET_SIZE	64
+
+struct nfsd_drc_bucket {
+	struct list_head lru_head;
+	spinlock_t cache_lock;
+};
+
+static struct nfsd_drc_bucket	*drc_hashtbl;
+static struct kmem_cache	*drc_slab;
+
+/* max number of entries allowed in the cache */
+static unsigned int		max_drc_entries;
+
+/* number of significant bits in the hash value */
+static unsigned int		maskbits;
+static unsigned int		drc_hashsize;
+
+/*
+ * Stats and other tracking of on the duplicate reply cache. All of these and
+ * the "rc" fields in nfsdstats are protected by the cache_lock
+ */
+
+/* total number of entries */
+static atomic_t			num_drc_entries;
+
+/* cache misses due only to checksum comparison failures */
+static unsigned int		payload_misses;
+
+/* amount of memory (in bytes) currently consumed by the DRC */
+static unsigned int		drc_mem_usage;
+
+/* longest hash chain seen */
+static unsigned int		longest_chain;
+
+/* size of cache when we saw the longest hash chain */
+static unsigned int		longest_chain_cachesize;
+
+static int	nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec);
+static void	cache_cleaner_func(struct work_struct *unused);
+static unsigned long nfsd_reply_cache_count(struct shrinker *shrink,
+					    struct shrink_control *sc);
+static unsigned long nfsd_reply_cache_scan(struct shrinker *shrink,
+					   struct shrink_control *sc);
+
+static struct shrinker nfsd_reply_cache_shrinker = {
+	.scan_objects = nfsd_reply_cache_scan,
+	.count_objects = nfsd_reply_cache_count,
+	.seeks	= 1,
+};
+
+/*
+ * locking for the reply cache:
+ * A cache entry is "single use" if c_state == RC_INPROG
+ * Otherwise, it when accessing _prev or _next, the lock must be held.
+ */
+static DECLARE_DELAYED_WORK(cache_cleaner, cache_cleaner_func);
+
+/*
+ * Put a cap on the size of the DRC based on the amount of available
+ * low memory in the machine.
+ *
+ *  64MB:    8192
+ * 128MB:   11585
+ * 256MB:   16384
+ * 512MB:   23170
+ *   1GB:   32768
+ *   2GB:   46340
+ *   4GB:   65536
+ *   8GB:   92681
+ *  16GB:  131072
+ *
+ * ...with a hard cap of 256k entries. In the worst case, each entry will be
+ * ~1k, so the above numbers should give a rough max of the amount of memory
+ * used in k.
+ */
+static unsigned int
+nfsd_cache_size_limit(void)
+{
+	unsigned int limit;
+	unsigned long low_pages = totalram_pages - totalhigh_pages;
+
+	limit = (16 * int_sqrt(low_pages)) << (PAGE_SHIFT-10);
+	return min_t(unsigned int, limit, 256*1024);
+}
+
+/*
+ * Compute the number of hash buckets we need. Divide the max cachesize by
+ * the "target" max bucket size, and round up to next power of two.
+ */
+static unsigned int
+nfsd_hashsize(unsigned int limit)
+{
+	return roundup_pow_of_two(limit / TARGET_BUCKET_SIZE);
+}
+
+static u32
+nfsd_cache_hash(__be32 xid)
+{
+	return hash_32(be32_to_cpu(xid), maskbits);
+}
+
+static struct svc_cacherep *
+nfsd_reply_cache_alloc(void)
+{
+	struct svc_cacherep	*rp;
+
+	rp = kmem_cache_alloc(drc_slab, GFP_KERNEL);
+	if (rp) {
+		rp->c_state = RC_UNUSED;
+		rp->c_type = RC_NOCACHE;
+		INIT_LIST_HEAD(&rp->c_lru);
+	}
+	return rp;
+}
+
+static void
+nfsd_reply_cache_free_locked(struct svc_cacherep *rp)
+{
+	if (rp->c_type == RC_REPLBUFF && rp->c_replvec.iov_base) {
+		drc_mem_usage -= rp->c_replvec.iov_len;
+		kfree(rp->c_replvec.iov_base);
+	}
+	list_del(&rp->c_lru);
+	atomic_dec(&num_drc_entries);
+	drc_mem_usage -= sizeof(*rp);
+	kmem_cache_free(drc_slab, rp);
+}
+
+static void
+nfsd_reply_cache_free(struct nfsd_drc_bucket *b, struct svc_cacherep *rp)
+{
+	spin_lock(&b->cache_lock);
+	nfsd_reply_cache_free_locked(rp);
+	spin_unlock(&b->cache_lock);
+}
+
+int nfsd_reply_cache_init(void)
+{
+	unsigned int hashsize;
+	unsigned int i;
+
+	max_drc_entries = nfsd_cache_size_limit();
+	atomic_set(&num_drc_entries, 0);
+	hashsize = nfsd_hashsize(max_drc_entries);
+	maskbits = ilog2(hashsize);
+
+	register_shrinker(&nfsd_reply_cache_shrinker);
+	drc_slab = kmem_cache_create("nfsd_drc", sizeof(struct svc_cacherep),
+					0, 0, NULL);
+	if (!drc_slab)
+		goto out_nomem;
+
+	drc_hashtbl = kcalloc(hashsize, sizeof(*drc_hashtbl), GFP_KERNEL);
+	if (!drc_hashtbl)
+		goto out_nomem;
+	for (i = 0; i < hashsize; i++) {
+		INIT_LIST_HEAD(&drc_hashtbl[i].lru_head);
+		spin_lock_init(&drc_hashtbl[i].cache_lock);
+	}
+	drc_hashsize = hashsize;
+
+	return 0;
+out_nomem:
+	printk(KERN_ERR "nfsd: failed to allocate reply cache\n");
+	nfsd_reply_cache_shutdown();
+	return -ENOMEM;
+}
+
+void nfsd_reply_cache_shutdown(void)
+{
+	struct svc_cacherep	*rp;
+	unsigned int i;
+
+	unregister_shrinker(&nfsd_reply_cache_shrinker);
+	cancel_delayed_work_sync(&cache_cleaner);
+
+	for (i = 0; i < drc_hashsize; i++) {
+		struct list_head *head = &drc_hashtbl[i].lru_head;
+		while (!list_empty(head)) {
+			rp = list_first_entry(head, struct svc_cacherep, c_lru);
+			nfsd_reply_cache_free_locked(rp);
+		}
+	}
+
+	kfree (drc_hashtbl);
+	drc_hashtbl = NULL;
+	drc_hashsize = 0;
+
+	if (drc_slab) {
+		kmem_cache_destroy(drc_slab);
+		drc_slab = NULL;
+	}
+}
+
+/*
+ * Move cache entry to end of LRU list, and queue the cleaner to run if it's
+ * not already scheduled.
+ */
+static void
+lru_put_end(struct nfsd_drc_bucket *b, struct svc_cacherep *rp)
+{
+	rp->c_timestamp = jiffies;
+	list_move_tail(&rp->c_lru, &b->lru_head);
+	schedule_delayed_work(&cache_cleaner, RC_EXPIRE);
+}
+
+static long
+prune_bucket(struct nfsd_drc_bucket *b)
+{
+	struct svc_cacherep *rp, *tmp;
+	long freed = 0;
+
+	list_for_each_entry_safe(rp, tmp, &b->lru_head, c_lru) {
+		/*
+		 * Don't free entries attached to calls that are still
+		 * in-progress, but do keep scanning the list.
+		 */
+		if (rp->c_state == RC_INPROG)
+			continue;
+		if (atomic_read(&num_drc_entries) <= max_drc_entries &&
+		    time_before(jiffies, rp->c_timestamp + RC_EXPIRE))
+			break;
+		nfsd_reply_cache_free_locked(rp);
+		freed++;
+	}
+	return freed;
+}
+
+/*
+ * Walk the LRU list and prune off entries that are older than RC_EXPIRE.
+ * Also prune the oldest ones when the total exceeds the max number of entries.
+ */
+static long
+prune_cache_entries(void)
+{
+	unsigned int i;
+	long freed = 0;
+	bool cancel = true;
+
+	for (i = 0; i < drc_hashsize; i++) {
+		struct nfsd_drc_bucket *b = &drc_hashtbl[i];
+
+		if (list_empty(&b->lru_head))
+			continue;
+		spin_lock(&b->cache_lock);
+		freed += prune_bucket(b);
+		if (!list_empty(&b->lru_head))
+			cancel = false;
+		spin_unlock(&b->cache_lock);
+	}
+
+	/*
+	 * Conditionally rearm the job to run in RC_EXPIRE since we just
+	 * ran the pruner.
+	 */
+	if (!cancel)
+		mod_delayed_work(system_wq, &cache_cleaner, RC_EXPIRE);
+	return freed;
+}
+
+static void
+cache_cleaner_func(struct work_struct *unused)
+{
+	prune_cache_entries();
+}
+
+static unsigned long
+nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+	return atomic_read(&num_drc_entries);
+}
+
+static unsigned long
+nfsd_reply_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
+{
+	return prune_cache_entries();
+}
+/*
+ * Walk an xdr_buf and get a CRC for at most the first RC_CSUMLEN bytes
+ */
+static __wsum
+nfsd_cache_csum(struct svc_rqst *rqstp)
+{
+	int idx;
+	unsigned int base;
+	__wsum csum;
+	struct xdr_buf *buf = &rqstp->rq_arg;
+	const unsigned char *p = buf->head[0].iov_base;
+	size_t csum_len = min_t(size_t, buf->head[0].iov_len + buf->page_len,
+				RC_CSUMLEN);
+	size_t len = min(buf->head[0].iov_len, csum_len);
+
+	/* rq_arg.head first */
+	csum = csum_partial(p, len, 0);
+	csum_len -= len;
+
+	/* Continue into page array */
+	idx = buf->page_base / PAGE_SIZE;
+	base = buf->page_base & ~PAGE_MASK;
+	while (csum_len) {
+		p = page_address(buf->pages[idx]) + base;
+		len = min_t(size_t, PAGE_SIZE - base, csum_len);
+		csum = csum_partial(p, len, csum);
+		csum_len -= len;
+		base = 0;
+		++idx;
+	}
+	return csum;
+}
+
+static bool
+nfsd_cache_match(struct svc_rqst *rqstp, __wsum csum, struct svc_cacherep *rp)
+{
+	/* Check RPC XID first */
+	if (rqstp->rq_xid != rp->c_xid)
+		return false;
+	/* compare checksum of NFS data */
+	if (csum != rp->c_csum) {
+		++payload_misses;
+		return false;
+	}
+
+	/* Other discriminators */
+	if (rqstp->rq_proc != rp->c_proc ||
+	    rqstp->rq_prot != rp->c_prot ||
+	    rqstp->rq_vers != rp->c_vers ||
+	    rqstp->rq_arg.len != rp->c_len ||
+	    !rpc_cmp_addr(svc_addr(rqstp), (struct sockaddr *)&rp->c_addr) ||
+	    rpc_get_port(svc_addr(rqstp)) != rpc_get_port((struct sockaddr *)&rp->c_addr))
+		return false;
+
+	return true;
+}
+
+/*
+ * Search the request hash for an entry that matches the given rqstp.
+ * Must be called with cache_lock held. Returns the found entry or
+ * NULL on failure.
+ */
+static struct svc_cacherep *
+nfsd_cache_search(struct nfsd_drc_bucket *b, struct svc_rqst *rqstp,
+		__wsum csum)
+{
+	struct svc_cacherep	*rp, *ret = NULL;
+	struct list_head 	*rh = &b->lru_head;
+	unsigned int		entries = 0;
+
+	list_for_each_entry(rp, rh, c_lru) {
+		++entries;
+		if (nfsd_cache_match(rqstp, csum, rp)) {
+			ret = rp;
+			break;
+		}
+	}
+
+	/* tally hash chain length stats */
+	if (entries > longest_chain) {
+		longest_chain = entries;
+		longest_chain_cachesize = atomic_read(&num_drc_entries);
+	} else if (entries == longest_chain) {
+		/* prefer to keep the smallest cachesize possible here */
+		longest_chain_cachesize = min_t(unsigned int,
+				longest_chain_cachesize,
+				atomic_read(&num_drc_entries));
+	}
+
+	return ret;
+}
+
+/*
+ * Try to find an entry matching the current call in the cache. When none
+ * is found, we try to grab the oldest expired entry off the LRU list. If
+ * a suitable one isn't there, then drop the cache_lock and allocate a
+ * new one, then search again in case one got inserted while this thread
+ * didn't hold the lock.
+ */
+int
+nfsd_cache_lookup(struct svc_rqst *rqstp)
+{
+	struct svc_cacherep	*rp, *found;
+	__be32			xid = rqstp->rq_xid;
+	u32			proto =  rqstp->rq_prot,
+				vers = rqstp->rq_vers,
+				proc = rqstp->rq_proc;
+	__wsum			csum;
+	u32 hash = nfsd_cache_hash(xid);
+	struct nfsd_drc_bucket *b = &drc_hashtbl[hash];
+	unsigned long		age;
+	int type = rqstp->rq_cachetype;
+	int rtn = RC_DOIT;
+
+	rqstp->rq_cacherep = NULL;
+	if (type == RC_NOCACHE) {
+		nfsdstats.rcnocache++;
+		return rtn;
+	}
+
+	csum = nfsd_cache_csum(rqstp);
+
+	/*
+	 * Since the common case is a cache miss followed by an insert,
+	 * preallocate an entry.
+	 */
+	rp = nfsd_reply_cache_alloc();
+	spin_lock(&b->cache_lock);
+	if (likely(rp)) {
+		atomic_inc(&num_drc_entries);
+		drc_mem_usage += sizeof(*rp);
+	}
+
+	/* go ahead and prune the cache */
+	prune_bucket(b);
+
+	found = nfsd_cache_search(b, rqstp, csum);
+	if (found) {
+		if (likely(rp))
+			nfsd_reply_cache_free_locked(rp);
+		rp = found;
+		goto found_entry;
+	}
+
+	if (!rp) {
+		dprintk("nfsd: unable to allocate DRC entry!\n");
+		goto out;
+	}
+
+	nfsdstats.rcmisses++;
+	rqstp->rq_cacherep = rp;
+	rp->c_state = RC_INPROG;
+	rp->c_xid = xid;
+	rp->c_proc = proc;
+	rpc_copy_addr((struct sockaddr *)&rp->c_addr, svc_addr(rqstp));
+	rpc_set_port((struct sockaddr *)&rp->c_addr, rpc_get_port(svc_addr(rqstp)));
+	rp->c_prot = proto;
+	rp->c_vers = vers;
+	rp->c_len = rqstp->rq_arg.len;
+	rp->c_csum = csum;
+
+	lru_put_end(b, rp);
+
+	/* release any buffer */
+	if (rp->c_type == RC_REPLBUFF) {
+		drc_mem_usage -= rp->c_replvec.iov_len;
+		kfree(rp->c_replvec.iov_base);
+		rp->c_replvec.iov_base = NULL;
+	}
+	rp->c_type = RC_NOCACHE;
+ out:
+	spin_unlock(&b->cache_lock);
+	return rtn;
+
+found_entry:
+	nfsdstats.rchits++;
+	/* We found a matching entry which is either in progress or done. */
+	age = jiffies - rp->c_timestamp;
+	lru_put_end(b, rp);
+
+	rtn = RC_DROPIT;
+	/* Request being processed or excessive rexmits */
+	if (rp->c_state == RC_INPROG || age < RC_DELAY)
+		goto out;
+
+	/* From the hall of fame of impractical attacks:
+	 * Is this a user who tries to snoop on the cache? */
+	rtn = RC_DOIT;
+	if (!rqstp->rq_secure && rp->c_secure)
+		goto out;
+
+	/* Compose RPC reply header */
+	switch (rp->c_type) {
+	case RC_NOCACHE:
+		break;
+	case RC_REPLSTAT:
+		svc_putu32(&rqstp->rq_res.head[0], rp->c_replstat);
+		rtn = RC_REPLY;
+		break;
+	case RC_REPLBUFF:
+		if (!nfsd_cache_append(rqstp, &rp->c_replvec))
+			goto out;	/* should not happen */
+		rtn = RC_REPLY;
+		break;
+	default:
+		printk(KERN_WARNING "nfsd: bad repcache type %d\n", rp->c_type);
+		nfsd_reply_cache_free_locked(rp);
+	}
+
+	goto out;
+}
+
+/*
+ * Update a cache entry. This is called from nfsd_dispatch when
+ * the procedure has been executed and the complete reply is in
+ * rqstp->rq_res.
+ *
+ * We're copying around data here rather than swapping buffers because
+ * the toplevel loop requires max-sized buffers, which would be a waste
+ * of memory for a cache with a max reply size of 100 bytes (diropokres).
+ *
+ * If we should start to use different types of cache entries tailored
+ * specifically for attrstat and fh's, we may save even more space.
+ *
+ * Also note that a cachetype of RC_NOCACHE can legally be passed when
+ * nfsd failed to encode a reply that otherwise would have been cached.
+ * In this case, nfsd_cache_update is called with statp == NULL.
+ */
+void
+nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp)
+{
+	struct svc_cacherep *rp = rqstp->rq_cacherep;
+	struct kvec	*resv = &rqstp->rq_res.head[0], *cachv;
+	u32		hash;
+	struct nfsd_drc_bucket *b;
+	int		len;
+	size_t		bufsize = 0;
+
+	if (!rp)
+		return;
+
+	hash = nfsd_cache_hash(rp->c_xid);
+	b = &drc_hashtbl[hash];
+
+	len = resv->iov_len - ((char*)statp - (char*)resv->iov_base);
+	len >>= 2;
+
+	/* Don't cache excessive amounts of data and XDR failures */
+	if (!statp || len > (256 >> 2)) {
+		nfsd_reply_cache_free(b, rp);
+		return;
+	}
+
+	switch (cachetype) {
+	case RC_REPLSTAT:
+		if (len != 1)
+			printk("nfsd: RC_REPLSTAT/reply len %d!\n",len);
+		rp->c_replstat = *statp;
+		break;
+	case RC_REPLBUFF:
+		cachv = &rp->c_replvec;
+		bufsize = len << 2;
+		cachv->iov_base = kmalloc(bufsize, GFP_KERNEL);
+		if (!cachv->iov_base) {
+			nfsd_reply_cache_free(b, rp);
+			return;
+		}
+		cachv->iov_len = bufsize;
+		memcpy(cachv->iov_base, statp, bufsize);
+		break;
+	case RC_NOCACHE:
+		nfsd_reply_cache_free(b, rp);
+		return;
+	}
+	spin_lock(&b->cache_lock);
+	drc_mem_usage += bufsize;
+	lru_put_end(b, rp);
+	rp->c_secure = rqstp->rq_secure;
+	rp->c_type = cachetype;
+	rp->c_state = RC_DONE;
+	spin_unlock(&b->cache_lock);
+	return;
+}
+
+/*
+ * Copy cached reply to current reply buffer. Should always fit.
+ * FIXME as reply is in a page, we should just attach the page, and
+ * keep a refcount....
+ */
+static int
+nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *data)
+{
+	struct kvec	*vec = &rqstp->rq_res.head[0];
+
+	if (vec->iov_len + data->iov_len > PAGE_SIZE) {
+		printk(KERN_WARNING "nfsd: cached reply too large (%Zd).\n",
+				data->iov_len);
+		return 0;
+	}
+	memcpy((char*)vec->iov_base + vec->iov_len, data->iov_base, data->iov_len);
+	vec->iov_len += data->iov_len;
+	return 1;
+}
+
+/*
+ * Note that fields may be added, removed or reordered in the future. Programs
+ * scraping this file for info should test the labels to ensure they're
+ * getting the correct field.
+ */
+static int nfsd_reply_cache_stats_show(struct seq_file *m, void *v)
+{
+	seq_printf(m, "max entries:           %u\n", max_drc_entries);
+	seq_printf(m, "num entries:           %u\n",
+			atomic_read(&num_drc_entries));
+	seq_printf(m, "hash buckets:          %u\n", 1 << maskbits);
+	seq_printf(m, "mem usage:             %u\n", drc_mem_usage);
+	seq_printf(m, "cache hits:            %u\n", nfsdstats.rchits);
+	seq_printf(m, "cache misses:          %u\n", nfsdstats.rcmisses);
+	seq_printf(m, "not cached:            %u\n", nfsdstats.rcnocache);
+	seq_printf(m, "payload misses:        %u\n", payload_misses);
+	seq_printf(m, "longest chain len:     %u\n", longest_chain);
+	seq_printf(m, "cachesize at longest:  %u\n", longest_chain_cachesize);
+	return 0;
+}
+
+int nfsd_reply_cache_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, nfsd_reply_cache_stats_show, NULL);
+}

fs/nfsd/nfsd.h

@@ -0,0 +1,410 @@
+/*
+ * Hodge-podge collection of knfsd-related stuff.
+ * I will sort this out later.
+ *
+ * Copyright (C) 1995-1997 Olaf Kirch <okir@monad.swb.de>
+ */
+
+#ifndef LINUX_NFSD_NFSD_H
+#define LINUX_NFSD_NFSD_H
+
+#include <linux/types.h>
+#include <linux/mount.h>
+
+#include <linux/nfs.h>
+#include <linux/nfs2.h>
+#include <linux/nfs3.h>
+#include <linux/nfs4.h>
+#include <linux/sunrpc/svc.h>
+#include <linux/sunrpc/msg_prot.h>
+
+#include <uapi/linux/nfsd/debug.h>
+
+#include "stats.h"
+#include "export.h"
+
+#undef ifdebug
+#ifdef NFSD_DEBUG
+# define ifdebug(flag)		if (nfsd_debug & NFSDDBG_##flag)
+#else
+# define ifdebug(flag)		if (0)
+#endif
+
+/*
+ * nfsd version
+ */
+#define NFSD_SUPPORTED_MINOR_VERSION	2
+/*
+ * Maximum blocksizes supported by daemon under various circumstances.
+ */
+#define NFSSVC_MAXBLKSIZE       RPCSVC_MAXPAYLOAD
+/* NFSv2 is limited by the protocol specification, see RFC 1094 */
+#define NFSSVC_MAXBLKSIZE_V2    (8*1024)
+
+
+/*
+ * Largest number of bytes we need to allocate for an NFS
+ * call or reply.  Used to control buffer sizes.  We use
+ * the length of v3 WRITE, READDIR and READDIR replies
+ * which are an RPC header, up to 26 XDR units of reply
+ * data, and some page data.
+ *
+ * Note that accuracy here doesn't matter too much as the
+ * size is rounded up to a page size when allocating space.
+ */
+#define NFSD_BUFSIZE            ((RPC_MAX_HEADER_WITH_AUTH+26)*XDR_UNIT + NFSSVC_MAXBLKSIZE)
+
+struct readdir_cd {
+	__be32			err;	/* 0, nfserr, or nfserr_eof */
+};
+
+
+extern struct svc_program	nfsd_program;
+extern struct svc_version	nfsd_version2, nfsd_version3,
+				nfsd_version4;
+extern struct mutex		nfsd_mutex;
+extern spinlock_t		nfsd_drc_lock;
+extern unsigned long		nfsd_drc_max_mem;
+extern unsigned long		nfsd_drc_mem_used;
+
+extern const struct seq_operations nfs_exports_op;
+
+/*
+ * Function prototypes.
+ */
+int		nfsd_svc(int nrservs, struct net *net);
+int		nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp);
+
+int		nfsd_nrthreads(struct net *);
+int		nfsd_nrpools(struct net *);
+int		nfsd_get_nrthreads(int n, int *, struct net *);
+int		nfsd_set_nrthreads(int n, int *, struct net *);
+int		nfsd_pool_stats_open(struct inode *, struct file *);
+int		nfsd_pool_stats_release(struct inode *, struct file *);
+
+void		nfsd_destroy(struct net *net);
+
+#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
+#ifdef CONFIG_NFSD_V2_ACL
+extern struct svc_version nfsd_acl_version2;
+#else
+#define nfsd_acl_version2 NULL
+#endif
+#ifdef CONFIG_NFSD_V3_ACL
+extern struct svc_version nfsd_acl_version3;
+#else
+#define nfsd_acl_version3 NULL
+#endif
+#endif
+
+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(struct net *net);
+
+extern int nfsd_max_blksize;
+
+static inline int nfsd_v4client(struct svc_rqst *rq)
+{
+	return rq->rq_prog == NFS_PROGRAM && rq->rq_vers == 4;
+}
+
+/* 
+ * NFSv4 State
+ */
+#ifdef CONFIG_NFSD_V4
+extern unsigned long max_delegations;
+int nfsd4_init_slabs(void);
+void nfsd4_free_slabs(void);
+int nfs4_state_start(void);
+int nfs4_state_start_net(struct net *net);
+void nfs4_state_shutdown(void);
+void nfs4_state_shutdown_net(struct net *net);
+void nfs4_reset_lease(time_t leasetime);
+int nfs4_reset_recoverydir(char *recdir);
+char * nfs4_recoverydir(void);
+#else
+static inline int nfsd4_init_slabs(void) { return 0; }
+static inline void nfsd4_free_slabs(void) { }
+static inline int nfs4_state_start(void) { return 0; }
+static inline int nfs4_state_start_net(struct net *net) { return 0; }
+static inline void nfs4_state_shutdown(void) { }
+static inline void nfs4_state_shutdown_net(struct net *net) { }
+static inline void nfs4_reset_lease(time_t leasetime) { }
+static inline int nfs4_reset_recoverydir(char *recdir) { return 0; }
+static inline char * nfs4_recoverydir(void) {return NULL; }
+#endif
+
+/*
+ * lockd binding
+ */
+void		nfsd_lockd_init(void);
+void		nfsd_lockd_shutdown(void);
+
+
+/*
+ * These macros provide pre-xdr'ed values for faster operation.
+ */
+#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_lock_range	cpu_to_be32(NFSERR_LOCK_RANGE)
+#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_badowner		cpu_to_be32(NFSERR_BADOWNER)
+#define	nfserr_locks_held	cpu_to_be32(NFSERR_LOCKS_HELD)
+#define	nfserr_op_illegal	cpu_to_be32(NFSERR_OP_ILLEGAL)
+#define	nfserr_grace		cpu_to_be32(NFSERR_GRACE)
+#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)
+#define nfserr_partner_notsupp		cpu_to_be32(NFS4ERR_PARTNER_NOTSUPP)
+#define nfserr_partner_no_auth		cpu_to_be32(NFS4ERR_PARTNER_NO_AUTH)
+#define nfserr_union_notsupp		cpu_to_be32(NFS4ERR_UNION_NOTSUPP)
+#define nfserr_offload_denied		cpu_to_be32(NFS4ERR_OFFLOAD_DENIED)
+#define nfserr_wrong_lfs		cpu_to_be32(NFS4ERR_WRONG_LFS)
+#define nfserr_badlabel		cpu_to_be32(NFS4ERR_BADLABEL)
+
+/* error codes for internal use */
+/* if a request fails due to kmalloc failure, it gets dropped.
+ *  Client should resend eventually
+ */
+#define	nfserr_dropit		cpu_to_be32(30000)
+/* end-of-file indicator in readdir */
+#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] == '.'))
+
+#ifdef CONFIG_NFSD_V4
+
+/* before processing a COMPOUND operation, we have to check that there
+ * is enough space in the buffer for XDR encode to succeed.  otherwise,
+ * we might process an operation with side effects, and be unable to
+ * tell the client that the operation succeeded.
+ *
+ * COMPOUND_SLACK_SPACE - this is the minimum bytes of buffer space
+ * needed to encode an "ordinary" _successful_ operation.  (GETATTR,
+ * READ, READDIR, and READLINK have their own buffer checks.)  if we
+ * fall below this level, we fail the next operation with NFS4ERR_RESOURCE.
+ *
+ * COMPOUND_ERR_SLACK_SPACE - this is the minimum bytes of buffer space
+ * needed to encode an operation which has failed with NFS4ERR_RESOURCE.
+ * care is taken to ensure that we never fall below this level for any
+ * reason.
+ */
+#define	COMPOUND_SLACK_SPACE		140    /* OP_GETFH */
+#define COMPOUND_ERR_SLACK_SPACE	16     /* OP_SETATTR */
+
+#define NFSD_LAUNDROMAT_MINTIMEOUT      1   /* seconds */
+
+/*
+ * The following attributes are currently not supported by the NFSv4 server:
+ *    ARCHIVE       (deprecated anyway)
+ *    HIDDEN        (unlikely to be supported any time soon)
+ *    MIMETYPE      (unlikely to be supported any time soon)
+ *    QUOTA_*       (will be supported in a forthcoming patch)
+ *    SYSTEM        (unlikely to be supported any time soon)
+ *    TIME_BACKUP   (unlikely to be supported any time soon)
+ *    TIME_CREATE   (unlikely to be supported any time soon)
+ */
+#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             \
+ | FATTR4_WORD0_UNIQUE_HANDLES  | FATTR4_WORD0_LEASE_TIME   | FATTR4_WORD0_RDATTR_ERROR     \
+ | FATTR4_WORD0_ACLSUPPORT      | FATTR4_WORD0_CANSETTIME   | FATTR4_WORD0_CASE_INSENSITIVE \
+ | FATTR4_WORD0_CASE_PRESERVING | FATTR4_WORD0_CHOWN_RESTRICTED                             \
+ | FATTR4_WORD0_FILEHANDLE      | FATTR4_WORD0_FILEID       | FATTR4_WORD0_FILES_AVAIL      \
+ | FATTR4_WORD0_FILES_FREE      | FATTR4_WORD0_FILES_TOTAL  | FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_HOMOGENEOUS      \
+ | FATTR4_WORD0_MAXFILESIZE     | FATTR4_WORD0_MAXLINK      | FATTR4_WORD0_MAXNAME          \
+ | FATTR4_WORD0_MAXREAD         | FATTR4_WORD0_MAXWRITE     | FATTR4_WORD0_ACL)
+
+#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      \
+ | FATTR4_WORD1_SPACE_USED      | FATTR4_WORD1_TIME_ACCESS  | FATTR4_WORD1_TIME_ACCESS_SET  \
+ | 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)
+
+#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
+#define NFSD4_2_SECURITY_ATTRS		FATTR4_WORD2_SECURITY_LABEL
+#else
+#define NFSD4_2_SECURITY_ATTRS		0
+#endif
+
+#define NFSD4_2_SUPPORTED_ATTRS_WORD2 \
+	(NFSD4_1_SUPPORTED_ATTRS_WORD2 | \
+	NFSD4_2_SECURITY_ATTRS)
+
+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)
+{
+	switch (minorversion) {
+	default: return NFSD4_2_SUPPORTED_ATTRS_WORD2;
+	case 1:  return NFSD4_1_SUPPORTED_ATTRS_WORD2;
+	case 0:  return 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)
+
+/* These are the only attrs allowed in CREATE/OPEN/SETATTR. */
+#define NFSD_WRITEABLE_ATTRS_WORD0 \
+	(FATTR4_WORD0_SIZE | FATTR4_WORD0_ACL)
+#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)
+#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
+#define NFSD_WRITEABLE_ATTRS_WORD2 FATTR4_WORD2_SECURITY_LABEL
+#else
+#define NFSD_WRITEABLE_ATTRS_WORD2 0
+#endif
+
+#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
+
+extern int nfsd4_is_junction(struct dentry *dentry);
+extern int register_cld_notifier(void);
+extern void unregister_cld_notifier(void);
+#else /* CONFIG_NFSD_V4 */
+static inline int nfsd4_is_junction(struct dentry *dentry)
+{
+	return 0;
+}
+
+#define register_cld_notifier() 0
+#define unregister_cld_notifier() do { } while(0)
+
+#endif /* CONFIG_NFSD_V4 */
+
+#endif /* LINUX_NFSD_NFSD_H */

fs/nfsd/nfsfh.c

@@ -0,0 +1,692 @@
+/*
+ * NFS server file handle treatment.
+ *
+ * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
+ * Portions Copyright (C) 1999 G. Allen Morris III <gam3@acm.org>
+ * Extensive rewrite by Neil Brown <neilb@cse.unsw.edu.au> Southern-Spring 1999
+ * ... and again Southern-Winter 2001 to support export_operations
+ */
+
+#include <linux/exportfs.h>
+
+#include <linux/sunrpc/svcauth_gss.h>
+#include "nfsd.h"
+#include "vfs.h"
+#include "auth.h"
+
+#define NFSDDBG_FACILITY		NFSDDBG_FH
+
+
+/*
+ * our acceptability function.
+ * if NOSUBTREECHECK, accept anything
+ * if not, require that we can walk up to exp->ex_dentry
+ * doing some checks on the 'x' bits
+ */
+static int nfsd_acceptable(void *expv, struct dentry *dentry)
+{
+	struct svc_export *exp = expv;
+	int rv;
+	struct dentry *tdentry;
+	struct dentry *parent;
+
+	if (exp->ex_flags & NFSEXP_NOSUBTREECHECK)
+		return 1;
+
+	tdentry = dget(dentry);
+	while (tdentry != exp->ex_path.dentry && !IS_ROOT(tdentry)) {
+		/* make sure parents give x permission to user */
+		int err;
+		parent = dget_parent(tdentry);
+		err = inode_permission(parent->d_inode, MAY_EXEC);
+		if (err < 0) {
+			dput(parent);
+			break;
+		}
+		dput(tdentry);
+		tdentry = parent;
+	}
+	if (tdentry != exp->ex_path.dentry)
+		dprintk("nfsd_acceptable failed at %p %pd\n", tdentry, tdentry);
+	rv = (tdentry == exp->ex_path.dentry);
+	dput(tdentry);
+	return rv;
+}
+
+/* Type check. The correct error return for type mismatches does not seem to be
+ * generally agreed upon. SunOS seems to use EISDIR if file isn't S_IFREG; a
+ * comment in the NFSv3 spec says this is incorrect (implementation notes for
+ * the write call).
+ */
+static inline __be32
+nfsd_mode_check(struct svc_rqst *rqstp, umode_t mode, umode_t requested)
+{
+	mode &= S_IFMT;
+
+	if (requested == 0) /* the caller doesn't care */
+		return nfs_ok;
+	if (mode == requested)
+		return nfs_ok;
+	/*
+	 * v4 has an error more specific than err_notdir which we should
+	 * return in preference to err_notdir:
+	 */
+	if (rqstp->rq_vers == 4 && mode == S_IFLNK)
+		return nfserr_symlink;
+	if (requested == S_IFDIR)
+		return nfserr_notdir;
+	if (mode == S_IFDIR)
+		return nfserr_isdir;
+	return nfserr_inval;
+}
+
+static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp,
+					  struct svc_export *exp)
+{
+	int flags = nfsexp_flags(rqstp, exp);
+
+	/* Check if the request originated from a secure port. */
+	if (!rqstp->rq_secure && !(flags & NFSEXP_INSECURE_PORT)) {
+		RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
+		dprintk("nfsd: request from insecure port %s!\n",
+		        svc_print_addr(rqstp, buf, sizeof(buf)));
+		return nfserr_perm;
+	}
+
+	/* Set user creds for this exportpoint */
+	return nfserrno(nfsd_setuser(rqstp, exp));
+}
+
+static inline __be32 check_pseudo_root(struct svc_rqst *rqstp,
+	struct dentry *dentry, struct svc_export *exp)
+{
+	if (!(exp->ex_flags & NFSEXP_V4ROOT))
+		return nfs_ok;
+	/*
+	 * v2/v3 clients have no need for the V4ROOT export--they use
+	 * the mount protocl instead; also, further V4ROOT checks may be
+	 * in v4-specific code, in which case v2/v3 clients could bypass
+	 * them.
+	 */
+	if (!nfsd_v4client(rqstp))
+		return nfserr_stale;
+	/*
+	 * We're exposing only the directories and symlinks that have to be
+	 * traversed on the way to real exports:
+	 */
+	if (unlikely(!S_ISDIR(dentry->d_inode->i_mode) &&
+		     !S_ISLNK(dentry->d_inode->i_mode)))
+		return nfserr_stale;
+	/*
+	 * A pseudoroot export gives permission to access only one
+	 * single directory; the kernel has to make another upcall
+	 * before granting access to anything else under it:
+	 */
+	if (unlikely(dentry != exp->ex_path.dentry))
+		return nfserr_stale;
+	return nfs_ok;
+}
+
+/*
+ * Use the given filehandle to look up the corresponding export and
+ * dentry.  On success, the results are used to set fh_export and
+ * fh_dentry.
+ */
+static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
+{
+	struct knfsd_fh	*fh = &fhp->fh_handle;
+	struct fid *fid = NULL, sfid;
+	struct svc_export *exp;
+	struct dentry *dentry;
+	int fileid_type;
+	int data_left = fh->fh_size/4;
+	__be32 error;
+
+	error = nfserr_stale;
+	if (rqstp->rq_vers > 2)
+		error = nfserr_badhandle;
+	if (rqstp->rq_vers == 4 && fh->fh_size == 0)
+		return nfserr_nofilehandle;
+
+	if (fh->fh_version == 1) {
+		int len;
+
+		if (--data_left < 0)
+			return error;
+		if (fh->fh_auth_type != 0)
+			return error;
+		len = key_len(fh->fh_fsid_type) / 4;
+		if (len == 0)
+			return error;
+		if  (fh->fh_fsid_type == FSID_MAJOR_MINOR) {
+			/* deprecated, convert to type 3 */
+			len = key_len(FSID_ENCODE_DEV)/4;
+			fh->fh_fsid_type = FSID_ENCODE_DEV;
+			/*
+			 * struct knfsd_fh uses host-endian fields, which are
+			 * sometimes used to hold net-endian values. This
+			 * confuses sparse, so we must use __force here to
+			 * keep it from complaining.
+			 */
+			fh->fh_fsid[0] = new_encode_dev(MKDEV(ntohl((__force __be32)fh->fh_fsid[0]),
+							ntohl((__force __be32)fh->fh_fsid[1])));
+			fh->fh_fsid[1] = fh->fh_fsid[2];
+		}
+		data_left -= len;
+		if (data_left < 0)
+			return error;
+		exp = rqst_exp_find(rqstp, fh->fh_fsid_type, fh->fh_fsid);
+		fid = (struct fid *)(fh->fh_fsid + len);
+	} else {
+		__u32 tfh[2];
+		dev_t xdev;
+		ino_t xino;
+
+		if (fh->fh_size != NFS_FHSIZE)
+			return error;
+		/* assume old filehandle format */
+		xdev = old_decode_dev(fh->ofh_xdev);
+		xino = u32_to_ino_t(fh->ofh_xino);
+		mk_fsid(FSID_DEV, tfh, xdev, xino, 0, NULL);
+		exp = rqst_exp_find(rqstp, FSID_DEV, tfh);
+	}
+
+	error = nfserr_stale;
+	if (PTR_ERR(exp) == -ENOENT)
+		return error;
+
+	if (IS_ERR(exp))
+		return nfserrno(PTR_ERR(exp));
+
+	if (exp->ex_flags & NFSEXP_NOSUBTREECHECK) {
+		/* Elevate privileges so that the lack of 'r' or 'x'
+		 * permission on some parent directory will
+		 * not stop exportfs_decode_fh from being able
+		 * to reconnect a directory into the dentry cache.
+		 * The same problem can affect "SUBTREECHECK" exports,
+		 * but as nfsd_acceptable depends on correct
+		 * access control settings being in effect, we cannot
+		 * fix that case easily.
+		 */
+		struct cred *new = prepare_creds();
+		if (!new) {
+			error =  nfserrno(-ENOMEM);
+			goto out;
+		}
+		new->cap_effective =
+			cap_raise_nfsd_set(new->cap_effective,
+					   new->cap_permitted);
+		put_cred(override_creds(new));
+		put_cred(new);
+	} else {
+		error = nfsd_setuser_and_check_port(rqstp, exp);
+		if (error)
+			goto out;
+	}
+
+	/*
+	 * Look up the dentry using the NFS file handle.
+	 */
+	error = nfserr_stale;
+	if (rqstp->rq_vers > 2)
+		error = nfserr_badhandle;
+
+	if (fh->fh_version != 1) {
+		sfid.i32.ino = fh->ofh_ino;
+		sfid.i32.gen = fh->ofh_generation;
+		sfid.i32.parent_ino = fh->ofh_dirino;
+		fid = &sfid;
+		data_left = 3;
+		if (fh->ofh_dirino == 0)
+			fileid_type = FILEID_INO32_GEN;
+		else
+			fileid_type = FILEID_INO32_GEN_PARENT;
+	} else
+		fileid_type = fh->fh_fileid_type;
+
+	if (fileid_type == FILEID_ROOT)
+		dentry = dget(exp->ex_path.dentry);
+	else {
+		dentry = exportfs_decode_fh(exp->ex_path.mnt, fid,
+				data_left, fileid_type,
+				nfsd_acceptable, exp);
+	}
+	if (dentry == NULL)
+		goto out;
+	if (IS_ERR(dentry)) {
+		if (PTR_ERR(dentry) != -EINVAL)
+			error = nfserrno(PTR_ERR(dentry));
+		goto out;
+	}
+
+	if (S_ISDIR(dentry->d_inode->i_mode) &&
+			(dentry->d_flags & DCACHE_DISCONNECTED)) {
+		printk("nfsd: find_fh_dentry returned a DISCONNECTED directory: %pd2\n",
+				dentry);
+	}
+
+	fhp->fh_dentry = dentry;
+	fhp->fh_export = exp;
+	return 0;
+out:
+	exp_put(exp);
+	return error;
+}
+
+/**
+ * fh_verify - filehandle lookup and access checking
+ * @rqstp: pointer to current rpc request
+ * @fhp: filehandle to be verified
+ * @type: expected type of object pointed to by filehandle
+ * @access: type of access needed to object
+ *
+ * Look up a dentry from the on-the-wire filehandle, check the client's
+ * access to the export, and set the current task's credentials.
+ *
+ * Regardless of success or failure of fh_verify(), fh_put() should be
+ * called on @fhp when the caller is finished with the filehandle.
+ *
+ * fh_verify() may be called multiple times on a given filehandle, for
+ * example, when processing an NFSv4 compound.  The first call will look
+ * up a dentry using the on-the-wire filehandle.  Subsequent calls will
+ * skip the lookup and just perform the other checks and possibly change
+ * the current task's credentials.
+ *
+ * @type specifies the type of object expected using one of the S_IF*
+ * constants defined in include/linux/stat.h.  The caller may use zero
+ * to indicate that it doesn't care, or a negative integer to indicate
+ * that it expects something not of the given type.
+ *
+ * @access is formed from the NFSD_MAY_* constants defined in
+ * include/linux/nfsd/nfsd.h.
+ */
+__be32
+fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access)
+{
+	struct svc_export *exp;
+	struct dentry	*dentry;
+	__be32		error;
+
+	dprintk("nfsd: fh_verify(%s)\n", SVCFH_fmt(fhp));
+
+	if (!fhp->fh_dentry) {
+		error = nfsd_set_fh_dentry(rqstp, fhp);
+		if (error)
+			goto out;
+	}
+	dentry = fhp->fh_dentry;
+	exp = fhp->fh_export;
+	/*
+	 * We still have to do all these permission checks, even when
+	 * fh_dentry is already set:
+	 * 	- fh_verify may be called multiple times with different
+	 * 	  "access" arguments (e.g. nfsd_proc_create calls
+	 * 	  fh_verify(...,NFSD_MAY_EXEC) first, then later (in
+	 * 	  nfsd_create) calls fh_verify(...,NFSD_MAY_CREATE).
+	 *	- in the NFSv4 case, the filehandle may have been filled
+	 *	  in by fh_compose, and given a dentry, but further
+	 *	  compound operations performed with that filehandle
+	 *	  still need permissions checks.  In the worst case, a
+	 *	  mountpoint crossing may have changed the export
+	 *	  options, and we may now need to use a different uid
+	 *	  (for example, if different id-squashing options are in
+	 *	  effect on the new filesystem).
+	 */
+	error = check_pseudo_root(rqstp, dentry, exp);
+	if (error)
+		goto out;
+
+	error = nfsd_setuser_and_check_port(rqstp, exp);
+	if (error)
+		goto out;
+
+	error = nfsd_mode_check(rqstp, dentry->d_inode->i_mode, type);
+	if (error)
+		goto out;
+
+	/*
+	 * pseudoflavor restrictions are not enforced on NLM,
+	 * which clients virtually always use auth_sys for,
+	 * even while using RPCSEC_GSS for NFS.
+	 */
+	if (access & NFSD_MAY_LOCK || access & NFSD_MAY_BYPASS_GSS)
+		goto skip_pseudoflavor_check;
+	/*
+	 * Clients may expect to be able to use auth_sys during mount,
+	 * even if they use gss for everything else; see section 2.3.2
+	 * of rfc 2623.
+	 */
+	if (access & NFSD_MAY_BYPASS_GSS_ON_ROOT
+			&& exp->ex_path.dentry == dentry)
+		goto skip_pseudoflavor_check;
+
+	error = check_nfsd_access(exp, rqstp);
+	if (error)
+		goto out;
+
+skip_pseudoflavor_check:
+	/* Finally, check access permissions. */
+	error = nfsd_permission(rqstp, exp, dentry, access);
+
+	if (error) {
+		dprintk("fh_verify: %pd2 permission failure, "
+			"acc=%x, error=%d\n",
+			dentry,
+			access, ntohl(error));
+	}
+out:
+	if (error == nfserr_stale)
+		nfsdstats.fh_stale++;
+	return error;
+}
+
+
+/*
+ * Compose a file handle for an NFS reply.
+ *
+ * Note that when first composed, the dentry may not yet have
+ * an inode.  In this case a call to fh_update should be made
+ * before the fh goes out on the wire ...
+ */
+static void _fh_update(struct svc_fh *fhp, struct svc_export *exp,
+		struct dentry *dentry)
+{
+	if (dentry != exp->ex_path.dentry) {
+		struct fid *fid = (struct fid *)
+			(fhp->fh_handle.fh_fsid + fhp->fh_handle.fh_size/4 - 1);
+		int maxsize = (fhp->fh_maxsize - fhp->fh_handle.fh_size)/4;
+		int subtreecheck = !(exp->ex_flags & NFSEXP_NOSUBTREECHECK);
+
+		fhp->fh_handle.fh_fileid_type =
+			exportfs_encode_fh(dentry, fid, &maxsize, subtreecheck);
+		fhp->fh_handle.fh_size += maxsize * 4;
+	} else {
+		fhp->fh_handle.fh_fileid_type = FILEID_ROOT;
+	}
+}
+
+/*
+ * for composing old style file handles
+ */
+static inline void _fh_update_old(struct dentry *dentry,
+				  struct svc_export *exp,
+				  struct knfsd_fh *fh)
+{
+	fh->ofh_ino = ino_t_to_u32(dentry->d_inode->i_ino);
+	fh->ofh_generation = dentry->d_inode->i_generation;
+	if (S_ISDIR(dentry->d_inode->i_mode) ||
+	    (exp->ex_flags & NFSEXP_NOSUBTREECHECK))
+		fh->ofh_dirino = 0;
+}
+
+static bool is_root_export(struct svc_export *exp)
+{
+	return exp->ex_path.dentry == exp->ex_path.dentry->d_sb->s_root;
+}
+
+static struct super_block *exp_sb(struct svc_export *exp)
+{
+	return exp->ex_path.dentry->d_inode->i_sb;
+}
+
+static bool fsid_type_ok_for_exp(u8 fsid_type, struct svc_export *exp)
+{
+	switch (fsid_type) {
+	case FSID_DEV:
+		if (!old_valid_dev(exp_sb(exp)->s_dev))
+			return 0;
+		/* FALL THROUGH */
+	case FSID_MAJOR_MINOR:
+	case FSID_ENCODE_DEV:
+		return exp_sb(exp)->s_type->fs_flags & FS_REQUIRES_DEV;
+	case FSID_NUM:
+		return exp->ex_flags & NFSEXP_FSID;
+	case FSID_UUID8:
+	case FSID_UUID16:
+		if (!is_root_export(exp))
+			return 0;
+		/* fall through */
+	case FSID_UUID4_INUM:
+	case FSID_UUID16_INUM:
+		return exp->ex_uuid != NULL;
+	}
+	return 1;
+}
+
+
+static void set_version_and_fsid_type(struct svc_fh *fhp, struct svc_export *exp, struct svc_fh *ref_fh)
+{
+	u8 version;
+	u8 fsid_type;
+retry:
+	version = 1;
+	if (ref_fh && ref_fh->fh_export == exp) {
+		version = ref_fh->fh_handle.fh_version;
+		fsid_type = ref_fh->fh_handle.fh_fsid_type;
+
+		ref_fh = NULL;
+
+		switch (version) {
+		case 0xca:
+			fsid_type = FSID_DEV;
+			break;
+		case 1:
+			break;
+		default:
+			goto retry;
+		}
+
+		/*
+		 * As the fsid -> filesystem mapping was guided by
+		 * user-space, there is no guarantee that the filesystem
+		 * actually supports that fsid type. If it doesn't we
+		 * loop around again without ref_fh set.
+		 */
+		if (!fsid_type_ok_for_exp(fsid_type, exp))
+			goto retry;
+	} else if (exp->ex_flags & NFSEXP_FSID) {
+		fsid_type = FSID_NUM;
+	} else if (exp->ex_uuid) {
+		if (fhp->fh_maxsize >= 64) {
+			if (is_root_export(exp))
+				fsid_type = FSID_UUID16;
+			else
+				fsid_type = FSID_UUID16_INUM;
+		} else {
+			if (is_root_export(exp))
+				fsid_type = FSID_UUID8;
+			else
+				fsid_type = FSID_UUID4_INUM;
+		}
+	} else if (!old_valid_dev(exp_sb(exp)->s_dev))
+		/* for newer device numbers, we must use a newer fsid format */
+		fsid_type = FSID_ENCODE_DEV;
+	else
+		fsid_type = FSID_DEV;
+	fhp->fh_handle.fh_version = version;
+	if (version)
+		fhp->fh_handle.fh_fsid_type = fsid_type;
+}
+
+__be32
+fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
+	   struct svc_fh *ref_fh)
+{
+	/* ref_fh is a reference file handle.
+	 * if it is non-null and for the same filesystem, then we should compose
+	 * a filehandle which is of the same version, where possible.
+	 * Currently, that means that if ref_fh->fh_handle.fh_version == 0xca
+	 * Then create a 32byte filehandle using nfs_fhbase_old
+	 *
+	 */
+
+	struct inode * inode = dentry->d_inode;
+	dev_t ex_dev = exp_sb(exp)->s_dev;
+
+	dprintk("nfsd: fh_compose(exp %02x:%02x/%ld %pd2, ino=%ld)\n",
+		MAJOR(ex_dev), MINOR(ex_dev),
+		(long) exp->ex_path.dentry->d_inode->i_ino,
+		dentry,
+		(inode ? inode->i_ino : 0));
+
+	/* Choose filehandle version and fsid type based on
+	 * the reference filehandle (if it is in the same export)
+	 * or the export options.
+	 */
+	 set_version_and_fsid_type(fhp, exp, ref_fh);
+
+	if (ref_fh == fhp)
+		fh_put(ref_fh);
+
+	if (fhp->fh_locked || fhp->fh_dentry) {
+		printk(KERN_ERR "fh_compose: fh %pd2 not initialized!\n",
+		       dentry);
+	}
+	if (fhp->fh_maxsize < NFS_FHSIZE)
+		printk(KERN_ERR "fh_compose: called with maxsize %d! %pd2\n",
+		       fhp->fh_maxsize,
+		       dentry);
+
+	fhp->fh_dentry = dget(dentry); /* our internal copy */
+	fhp->fh_export = exp_get(exp);
+
+	if (fhp->fh_handle.fh_version == 0xca) {
+		/* old style filehandle please */
+		memset(&fhp->fh_handle.fh_base, 0, NFS_FHSIZE);
+		fhp->fh_handle.fh_size = NFS_FHSIZE;
+		fhp->fh_handle.ofh_dcookie = 0xfeebbaca;
+		fhp->fh_handle.ofh_dev =  old_encode_dev(ex_dev);
+		fhp->fh_handle.ofh_xdev = fhp->fh_handle.ofh_dev;
+		fhp->fh_handle.ofh_xino =
+			ino_t_to_u32(exp->ex_path.dentry->d_inode->i_ino);
+		fhp->fh_handle.ofh_dirino = ino_t_to_u32(parent_ino(dentry));
+		if (inode)
+			_fh_update_old(dentry, exp, &fhp->fh_handle);
+	} else {
+		fhp->fh_handle.fh_size =
+			key_len(fhp->fh_handle.fh_fsid_type) + 4;
+		fhp->fh_handle.fh_auth_type = 0;
+
+		mk_fsid(fhp->fh_handle.fh_fsid_type,
+			fhp->fh_handle.fh_fsid,
+			ex_dev,
+			exp->ex_path.dentry->d_inode->i_ino,
+			exp->ex_fsid, exp->ex_uuid);
+
+		if (inode)
+			_fh_update(fhp, exp, dentry);
+		if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) {
+			fh_put(fhp);
+			return nfserr_opnotsupp;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Update file handle information after changing a dentry.
+ * This is only called by nfsd_create, nfsd_create_v3 and nfsd_proc_create
+ */
+__be32
+fh_update(struct svc_fh *fhp)
+{
+	struct dentry *dentry;
+
+	if (!fhp->fh_dentry)
+		goto out_bad;
+
+	dentry = fhp->fh_dentry;
+	if (!dentry->d_inode)
+		goto out_negative;
+	if (fhp->fh_handle.fh_version != 1) {
+		_fh_update_old(dentry, fhp->fh_export, &fhp->fh_handle);
+	} else {
+		if (fhp->fh_handle.fh_fileid_type != FILEID_ROOT)
+			return 0;
+
+		_fh_update(fhp, fhp->fh_export, dentry);
+		if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID)
+			return nfserr_opnotsupp;
+	}
+	return 0;
+out_bad:
+	printk(KERN_ERR "fh_update: fh not verified!\n");
+	return nfserr_serverfault;
+out_negative:
+	printk(KERN_ERR "fh_update: %pd2 still negative!\n",
+		dentry);
+	return nfserr_serverfault;
+}
+
+/*
+ * Release a file handle.
+ */
+void
+fh_put(struct svc_fh *fhp)
+{
+	struct dentry * dentry = fhp->fh_dentry;
+	struct svc_export * exp = fhp->fh_export;
+	if (dentry) {
+		fh_unlock(fhp);
+		fhp->fh_dentry = NULL;
+		dput(dentry);
+#ifdef CONFIG_NFSD_V3
+		fhp->fh_pre_saved = 0;
+		fhp->fh_post_saved = 0;
+#endif
+	}
+	fh_drop_write(fhp);
+	if (exp) {
+		exp_put(exp);
+		fhp->fh_export = NULL;
+	}
+	return;
+}
+
+/*
+ * Shorthand for dprintk()'s
+ */
+char * SVCFH_fmt(struct svc_fh *fhp)
+{
+	struct knfsd_fh *fh = &fhp->fh_handle;
+
+	static char buf[80];
+	sprintf(buf, "%d: %08x %08x %08x %08x %08x %08x",
+		fh->fh_size,
+		fh->fh_base.fh_pad[0],
+		fh->fh_base.fh_pad[1],
+		fh->fh_base.fh_pad[2],
+		fh->fh_base.fh_pad[3],
+		fh->fh_base.fh_pad[4],
+		fh->fh_base.fh_pad[5]);
+	return buf;
+}
+
+enum fsid_source fsid_source(struct svc_fh *fhp)
+{
+	if (fhp->fh_handle.fh_version != 1)
+		return FSIDSOURCE_DEV;
+	switch(fhp->fh_handle.fh_fsid_type) {
+	case FSID_DEV:
+	case FSID_ENCODE_DEV:
+	case FSID_MAJOR_MINOR:
+		if (exp_sb(fhp->fh_export)->s_type->fs_flags & FS_REQUIRES_DEV)
+			return FSIDSOURCE_DEV;
+		break;
+	case FSID_NUM:
+		if (fhp->fh_export->ex_flags & NFSEXP_FSID)
+			return FSIDSOURCE_FSID;
+		break;
+	default:
+		break;
+	}
+	/* either a UUID type filehandle, or the filehandle doesn't
+	 * match the export.
+	 */
+	if (fhp->fh_export->ex_flags & NFSEXP_FSID)
+		return FSIDSOURCE_FSID;
+	if (fhp->fh_export->ex_uuid)
+		return FSIDSOURCE_UUID;
+	return FSIDSOURCE_DEV;
+}

fs/nfsd/nfsfh.h

@@ -0,0 +1,274 @@
+/*
+ * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de>
+ *
+ * This file describes the layout of the file handles as passed
+ * over the wire.
+ */
+#ifndef _LINUX_NFSD_NFSFH_H
+#define _LINUX_NFSD_NFSFH_H
+
+#include <linux/sunrpc/svc.h>
+#include <uapi/linux/nfsd/nfsfh.h>
+
+static inline __u32 ino_t_to_u32(ino_t ino)
+{
+	return (__u32) ino;
+}
+
+static inline ino_t u32_to_ino_t(__u32 uino)
+{
+	return (ino_t) uino;
+}
+
+/*
+ * This is the internal representation of an NFS handle used in knfsd.
+ * pre_mtime/post_version will be used to support wcc_attr's in NFSv3.
+ */
+typedef struct svc_fh {
+	struct knfsd_fh		fh_handle;	/* FH data */
+	struct dentry *		fh_dentry;	/* validated dentry */
+	struct svc_export *	fh_export;	/* export pointer */
+	int			fh_maxsize;	/* max size for fh_handle */
+
+	unsigned char		fh_locked;	/* inode locked by us */
+	unsigned char		fh_want_write;	/* remount protection taken */
+
+#ifdef CONFIG_NFSD_V3
+	unsigned char		fh_post_saved;	/* post-op attrs saved */
+	unsigned char		fh_pre_saved;	/* pre-op attrs saved */
+
+	/* Pre-op attributes saved during fh_lock */
+	__u64			fh_pre_size;	/* size before operation */
+	struct timespec		fh_pre_mtime;	/* mtime before oper */
+	struct timespec		fh_pre_ctime;	/* ctime before oper */
+	/*
+	 * pre-op nfsv4 change attr: note must check IS_I_VERSION(inode)
+	 *  to find out if it is valid.
+	 */
+	u64			fh_pre_change;
+
+	/* Post-op attributes saved in fh_unlock */
+	struct kstat		fh_post_attr;	/* full attrs after operation */
+	u64			fh_post_change; /* nfsv4 change; see above */
+#endif /* CONFIG_NFSD_V3 */
+
+} svc_fh;
+
+enum nfsd_fsid {
+	FSID_DEV = 0,
+	FSID_NUM,
+	FSID_MAJOR_MINOR,
+	FSID_ENCODE_DEV,
+	FSID_UUID4_INUM,
+	FSID_UUID8,
+	FSID_UUID16,
+	FSID_UUID16_INUM,
+};
+
+enum fsid_source {
+	FSIDSOURCE_DEV,
+	FSIDSOURCE_FSID,
+	FSIDSOURCE_UUID,
+};
+extern enum fsid_source fsid_source(struct svc_fh *fhp);
+
+
+/*
+ * This might look a little large to "inline" but in all calls except
+ * one, 'vers' is constant so moste of the function disappears.
+ *
+ * In some cases the values are considered to be host endian and in
+ * others, net endian. fsidv is always considered to be u32 as the
+ * callers don't know which it will be. So we must use __force to keep
+ * sparse from complaining. Since these values are opaque to the
+ * client, that shouldn't be a problem.
+ */
+static inline void mk_fsid(int vers, u32 *fsidv, dev_t dev, ino_t ino,
+			   u32 fsid, unsigned char *uuid)
+{
+	u32 *up;
+	switch(vers) {
+	case FSID_DEV:
+		fsidv[0] = (__force __u32)htonl((MAJOR(dev)<<16) |
+				 MINOR(dev));
+		fsidv[1] = ino_t_to_u32(ino);
+		break;
+	case FSID_NUM:
+		fsidv[0] = fsid;
+		break;
+	case FSID_MAJOR_MINOR:
+		fsidv[0] = (__force __u32)htonl(MAJOR(dev));
+		fsidv[1] = (__force __u32)htonl(MINOR(dev));
+		fsidv[2] = ino_t_to_u32(ino);
+		break;
+
+	case FSID_ENCODE_DEV:
+		fsidv[0] = new_encode_dev(dev);
+		fsidv[1] = ino_t_to_u32(ino);
+		break;
+
+	case FSID_UUID4_INUM:
+		/* 4 byte fsid and inode number */
+		up = (u32*)uuid;
+		fsidv[0] = ino_t_to_u32(ino);
+		fsidv[1] = up[0] ^ up[1] ^ up[2] ^ up[3];
+		break;
+
+	case FSID_UUID8:
+		/* 8 byte fsid  */
+		up = (u32*)uuid;
+		fsidv[0] = up[0] ^ up[2];
+		fsidv[1] = up[1] ^ up[3];
+		break;
+
+	case FSID_UUID16:
+		/* 16 byte fsid - NFSv3+ only */
+		memcpy(fsidv, uuid, 16);
+		break;
+
+	case FSID_UUID16_INUM:
+		/* 8 byte inode and 16 byte fsid */
+		*(u64*)fsidv = (u64)ino;
+		memcpy(fsidv+2, uuid, 16);
+		break;
+	default: BUG();
+	}
+}
+
+static inline int key_len(int type)
+{
+	switch(type) {
+	case FSID_DEV:		return 8;
+	case FSID_NUM: 		return 4;
+	case FSID_MAJOR_MINOR:	return 12;
+	case FSID_ENCODE_DEV:	return 8;
+	case FSID_UUID4_INUM:	return 8;
+	case FSID_UUID8:	return 8;
+	case FSID_UUID16:	return 16;
+	case FSID_UUID16_INUM:	return 24;
+	default: return 0;
+	}
+}
+
+/*
+ * Shorthand for dprintk()'s
+ */
+extern char * SVCFH_fmt(struct svc_fh *fhp);
+
+/*
+ * Function prototypes
+ */
+__be32	fh_verify(struct svc_rqst *, struct svc_fh *, umode_t, int);
+__be32	fh_compose(struct svc_fh *, struct svc_export *, struct dentry *, struct svc_fh *);
+__be32	fh_update(struct svc_fh *);
+void	fh_put(struct svc_fh *);
+
+static __inline__ struct svc_fh *
+fh_copy(struct svc_fh *dst, struct svc_fh *src)
+{
+	WARN_ON(src->fh_dentry || src->fh_locked);
+			
+	*dst = *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)
+{
+	memset(fhp, 0, sizeof(*fhp));
+	fhp->fh_maxsize = maxsize;
+	return fhp;
+}
+
+#ifdef CONFIG_NFSD_V3
+/*
+ * The wcc data stored in current_fh should be cleared
+ * between compound ops.
+ */
+static inline void
+fh_clear_wcc(struct svc_fh *fhp)
+{
+	fhp->fh_post_saved = 0;
+	fhp->fh_pre_saved = 0;
+}
+
+/*
+ * Fill in the pre_op attr for the wcc data
+ */
+static inline void
+fill_pre_wcc(struct svc_fh *fhp)
+{
+	struct inode    *inode;
+
+	inode = fhp->fh_dentry->d_inode;
+	if (!fhp->fh_pre_saved) {
+		fhp->fh_pre_mtime = inode->i_mtime;
+		fhp->fh_pre_ctime = inode->i_ctime;
+		fhp->fh_pre_size  = inode->i_size;
+		fhp->fh_pre_change = inode->i_version;
+		fhp->fh_pre_saved = 1;
+	}
+}
+
+extern void fill_post_wcc(struct svc_fh *);
+#else
+#define fh_clear_wcc(ignored)
+#define fill_pre_wcc(ignored)
+#define fill_post_wcc(notused)
+#endif /* CONFIG_NFSD_V3 */
+
+
+/*
+ * Lock a file handle/inode
+ * NOTE: both fh_lock and fh_unlock are done "by hand" in
+ * vfs.c:nfsd_rename as it needs to grab 2 i_mutex's at once
+ * so, any changes here should be reflected there.
+ */
+
+static inline void
+fh_lock_nested(struct svc_fh *fhp, unsigned int subclass)
+{
+	struct dentry	*dentry = fhp->fh_dentry;
+	struct inode	*inode;
+
+	BUG_ON(!dentry);
+
+	if (fhp->fh_locked) {
+		printk(KERN_WARNING "fh_lock: %pd2 already locked!\n",
+			dentry);
+		return;
+	}
+
+	inode = dentry->d_inode;
+	mutex_lock_nested(&inode->i_mutex, subclass);
+	fill_pre_wcc(fhp);
+	fhp->fh_locked = 1;
+}
+
+static inline void
+fh_lock(struct svc_fh *fhp)
+{
+	fh_lock_nested(fhp, I_MUTEX_NORMAL);
+}
+
+/*
+ * Unlock a file handle/inode
+ */
+static inline void
+fh_unlock(struct svc_fh *fhp)
+{
+	if (fhp->fh_locked) {
+		fill_post_wcc(fhp);
+		mutex_unlock(&fhp->fh_dentry->d_inode->i_mutex);
+		fhp->fh_locked = 0;
+	}
+}
+
+#endif /* _LINUX_NFSD_NFSFH_H */

fs/nfsd/nfsproc.c

@@ -0,0 +1,759 @@
+/*
+ * Process version 2 NFS requests.
+ *
+ * Copyright (C) 1995-1997 Olaf Kirch <okir@monad.swb.de>
+ */
+
+#include <linux/namei.h>
+
+#include "cache.h"
+#include "xdr.h"
+#include "vfs.h"
+
+typedef struct svc_rqst	svc_rqst;
+typedef struct svc_buf	svc_buf;
+
+#define NFSDDBG_FACILITY		NFSDDBG_PROC
+
+
+static __be32
+nfsd_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+{
+	return nfs_ok;
+}
+
+static __be32
+nfsd_return_attrs(__be32 err, struct nfsd_attrstat *resp)
+{
+	if (err) return err;
+	return fh_getattr(&resp->fh, &resp->stat);
+}
+static __be32
+nfsd_return_dirop(__be32 err, struct nfsd_diropres *resp)
+{
+	if (err) return err;
+	return fh_getattr(&resp->fh, &resp->stat);
+}
+/*
+ * Get a file's attributes
+ * N.B. After this call resp->fh needs an fh_put
+ */
+static __be32
+nfsd_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle  *argp,
+					  struct nfsd_attrstat *resp)
+{
+	__be32 nfserr;
+	dprintk("nfsd: GETATTR  %s\n", SVCFH_fmt(&argp->fh));
+
+	fh_copy(&resp->fh, &argp->fh);
+	nfserr = fh_verify(rqstp, &resp->fh, 0,
+			NFSD_MAY_NOP | NFSD_MAY_BYPASS_GSS_ON_ROOT);
+	return nfsd_return_attrs(nfserr, resp);
+}
+
+/*
+ * Set a file's attributes
+ * N.B. After this call resp->fh needs an fh_put
+ */
+static __be32
+nfsd_proc_setattr(struct svc_rqst *rqstp, struct nfsd_sattrargs *argp,
+					  struct nfsd_attrstat  *resp)
+{
+	__be32 nfserr;
+	dprintk("nfsd: SETATTR  %s, valid=%x, size=%ld\n",
+		SVCFH_fmt(&argp->fh),
+		argp->attrs.ia_valid, (long) argp->attrs.ia_size);
+
+	fh_copy(&resp->fh, &argp->fh);
+	nfserr = nfsd_setattr(rqstp, &resp->fh, &argp->attrs,0, (time_t)0);
+	return nfsd_return_attrs(nfserr, resp);
+}
+
+/*
+ * Look up a path name component
+ * Note: the dentry in the resp->fh may be negative if the file
+ * doesn't exist yet.
+ * N.B. After this call resp->fh needs an fh_put
+ */
+static __be32
+nfsd_proc_lookup(struct svc_rqst *rqstp, struct nfsd_diropargs *argp,
+					 struct nfsd_diropres  *resp)
+{
+	__be32	nfserr;
+
+	dprintk("nfsd: LOOKUP   %s %.*s\n",
+		SVCFH_fmt(&argp->fh), argp->len, argp->name);
+
+	fh_init(&resp->fh, NFS_FHSIZE);
+	nfserr = nfsd_lookup(rqstp, &argp->fh, argp->name, argp->len,
+				 &resp->fh);
+
+	fh_put(&argp->fh);
+	return nfsd_return_dirop(nfserr, resp);
+}
+
+/*
+ * Read a symlink.
+ */
+static __be32
+nfsd_proc_readlink(struct svc_rqst *rqstp, struct nfsd_readlinkargs *argp,
+					   struct nfsd_readlinkres *resp)
+{
+	__be32	nfserr;
+
+	dprintk("nfsd: READLINK %s\n", SVCFH_fmt(&argp->fh));
+
+	/* Read the symlink. */
+	resp->len = NFS_MAXPATHLEN;
+	nfserr = nfsd_readlink(rqstp, &argp->fh, argp->buffer, &resp->len);
+
+	fh_put(&argp->fh);
+	return nfserr;
+}
+
+/*
+ * Read a portion of a file.
+ * N.B. After this call resp->fh needs an fh_put
+ */
+static __be32
+nfsd_proc_read(struct svc_rqst *rqstp, struct nfsd_readargs *argp,
+				       struct nfsd_readres  *resp)
+{
+	__be32	nfserr;
+
+	dprintk("nfsd: READ    %s %d bytes at %d\n",
+		SVCFH_fmt(&argp->fh),
+		argp->count, argp->offset);
+
+	/* Obtain buffer pointer for payload. 19 is 1 word for
+	 * status, 17 words for fattr, and 1 word for the byte count.
+	 */
+
+	if (NFSSVC_MAXBLKSIZE_V2 < argp->count) {
+		char buf[RPC_MAX_ADDRBUFLEN];
+		printk(KERN_NOTICE
+			"oversized read request from %s (%d bytes)\n",
+				svc_print_addr(rqstp, buf, sizeof(buf)),
+				argp->count);
+		argp->count = NFSSVC_MAXBLKSIZE_V2;
+	}
+	svc_reserve_auth(rqstp, (19<<2) + argp->count + 4);
+
+	resp->count = argp->count;
+	nfserr = nfsd_read(rqstp, fh_copy(&resp->fh, &argp->fh),
+				  argp->offset,
+			   	  rqstp->rq_vec, argp->vlen,
+				  &resp->count);
+
+	if (nfserr) return nfserr;
+	return fh_getattr(&resp->fh, &resp->stat);
+}
+
+/*
+ * Write data to a file
+ * N.B. After this call resp->fh needs an fh_put
+ */
+static __be32
+nfsd_proc_write(struct svc_rqst *rqstp, struct nfsd_writeargs *argp,
+					struct nfsd_attrstat  *resp)
+{
+	__be32	nfserr;
+	int	stable = 1;
+	unsigned long cnt = argp->len;
+
+	dprintk("nfsd: WRITE    %s %d bytes at %d\n",
+		SVCFH_fmt(&argp->fh),
+		argp->len, argp->offset);
+
+	nfserr = nfsd_write(rqstp, fh_copy(&resp->fh, &argp->fh), NULL,
+				   argp->offset,
+				   rqstp->rq_vec, argp->vlen,
+			           &cnt,
+				   &stable);
+	return nfsd_return_attrs(nfserr, resp);
+}
+
+/*
+ * CREATE processing is complicated. The keyword here is `overloaded.'
+ * The parent directory is kept locked between the check for existence
+ * and the actual create() call in compliance with VFS protocols.
+ * N.B. After this call _both_ argp->fh and resp->fh need an fh_put
+ */
+static __be32
+nfsd_proc_create(struct svc_rqst *rqstp, struct nfsd_createargs *argp,
+					 struct nfsd_diropres   *resp)
+{
+	svc_fh		*dirfhp = &argp->fh;
+	svc_fh		*newfhp = &resp->fh;
+	struct iattr	*attr = &argp->attrs;
+	struct inode	*inode;
+	struct dentry	*dchild;
+	int		type, mode;
+	__be32		nfserr;
+	int		hosterr;
+	dev_t		rdev = 0, wanted = new_decode_dev(attr->ia_size);
+
+	dprintk("nfsd: CREATE   %s %.*s\n",
+		SVCFH_fmt(dirfhp), argp->len, argp->name);
+
+	/* First verify the parent file handle */
+	nfserr = fh_verify(rqstp, dirfhp, S_IFDIR, NFSD_MAY_EXEC);
+	if (nfserr)
+		goto done; /* must fh_put dirfhp even on error */
+
+	/* Check for NFSD_MAY_WRITE in nfsd_create if necessary */
+
+	nfserr = nfserr_acces;
+	if (!argp->len)
+		goto done;
+	nfserr = nfserr_exist;
+	if (isdotent(argp->name, argp->len))
+		goto done;
+	hosterr = fh_want_write(dirfhp);
+	if (hosterr) {
+		nfserr = nfserrno(hosterr);
+		goto done;
+	}
+
+	fh_lock_nested(dirfhp, I_MUTEX_PARENT);
+	dchild = lookup_one_len(argp->name, dirfhp->fh_dentry, argp->len);
+	if (IS_ERR(dchild)) {
+		nfserr = nfserrno(PTR_ERR(dchild));
+		goto out_unlock;
+	}
+	fh_init(newfhp, NFS_FHSIZE);
+	nfserr = fh_compose(newfhp, dirfhp->fh_export, dchild, dirfhp);
+	if (!nfserr && !dchild->d_inode)
+		nfserr = nfserr_noent;
+	dput(dchild);
+	if (nfserr) {
+		if (nfserr != nfserr_noent)
+			goto out_unlock;
+		/*
+		 * If the new file handle wasn't verified, we can't tell
+		 * whether the file exists or not. Time to bail ...
+		 */
+		nfserr = nfserr_acces;
+		if (!newfhp->fh_dentry) {
+			printk(KERN_WARNING 
+				"nfsd_proc_create: file handle not verified\n");
+			goto out_unlock;
+		}
+	}
+
+	inode = newfhp->fh_dentry->d_inode;
+
+	/* Unfudge the mode bits */
+	if (attr->ia_valid & ATTR_MODE) {
+		type = attr->ia_mode & S_IFMT;
+		mode = attr->ia_mode & ~S_IFMT;
+		if (!type) {
+			/* no type, so if target exists, assume same as that,
+			 * else assume a file */
+			if (inode) {
+				type = inode->i_mode & S_IFMT;
+				switch(type) {
+				case S_IFCHR:
+				case S_IFBLK:
+					/* reserve rdev for later checking */
+					rdev = inode->i_rdev;
+					attr->ia_valid |= ATTR_SIZE;
+
+					/* FALLTHROUGH */
+				case S_IFIFO:
+					/* this is probably a permission check..
+					 * at least IRIX implements perm checking on
+					 *   echo thing > device-special-file-or-pipe
+					 * by doing a CREATE with type==0
+					 */
+					nfserr = nfsd_permission(rqstp,
+								 newfhp->fh_export,
+								 newfhp->fh_dentry,
+								 NFSD_MAY_WRITE|NFSD_MAY_LOCAL_ACCESS);
+					if (nfserr && nfserr != nfserr_rofs)
+						goto out_unlock;
+				}
+			} else
+				type = S_IFREG;
+		}
+	} else if (inode) {
+		type = inode->i_mode & S_IFMT;
+		mode = inode->i_mode & ~S_IFMT;
+	} else {
+		type = S_IFREG;
+		mode = 0;	/* ??? */
+	}
+
+	attr->ia_valid |= ATTR_MODE;
+	attr->ia_mode = mode;
+
+	/* Special treatment for non-regular files according to the
+	 * gospel of sun micro
+	 */
+	if (type != S_IFREG) {
+		if (type != S_IFBLK && type != S_IFCHR) {
+			rdev = 0;
+		} else if (type == S_IFCHR && !(attr->ia_valid & ATTR_SIZE)) {
+			/* If you think you've seen the worst, grok this. */
+			type = S_IFIFO;
+		} else {
+			/* Okay, char or block special */
+			if (!rdev)
+				rdev = wanted;
+		}
+
+		/* we've used the SIZE information, so discard it */
+		attr->ia_valid &= ~ATTR_SIZE;
+
+		/* Make sure the type and device matches */
+		nfserr = nfserr_exist;
+		if (inode && type != (inode->i_mode & S_IFMT))
+			goto out_unlock;
+	}
+
+	nfserr = 0;
+	if (!inode) {
+		/* File doesn't exist. Create it and set attrs */
+		nfserr = nfsd_create(rqstp, dirfhp, argp->name, argp->len,
+					attr, type, rdev, newfhp);
+	} else if (type == S_IFREG) {
+		dprintk("nfsd:   existing %s, valid=%x, size=%ld\n",
+			argp->name, attr->ia_valid, (long) attr->ia_size);
+		/* File already exists. We ignore all attributes except
+		 * size, so that creat() behaves exactly like
+		 * open(..., O_CREAT|O_TRUNC|O_WRONLY).
+		 */
+		attr->ia_valid &= ATTR_SIZE;
+		if (attr->ia_valid)
+			nfserr = nfsd_setattr(rqstp, newfhp, attr, 0, (time_t)0);
+	}
+
+out_unlock:
+	/* We don't really need to unlock, as fh_put does it. */
+	fh_unlock(dirfhp);
+	fh_drop_write(dirfhp);
+done:
+	fh_put(dirfhp);
+	return nfsd_return_dirop(nfserr, resp);
+}
+
+static __be32
+nfsd_proc_remove(struct svc_rqst *rqstp, struct nfsd_diropargs *argp,
+					 void		       *resp)
+{
+	__be32	nfserr;
+
+	dprintk("nfsd: REMOVE   %s %.*s\n", SVCFH_fmt(&argp->fh),
+		argp->len, argp->name);
+
+	/* Unlink. -SIFDIR means file must not be a directory */
+	nfserr = nfsd_unlink(rqstp, &argp->fh, -S_IFDIR, argp->name, argp->len);
+	fh_put(&argp->fh);
+	return nfserr;
+}
+
+static __be32
+nfsd_proc_rename(struct svc_rqst *rqstp, struct nfsd_renameargs *argp,
+				  	 void		        *resp)
+{
+	__be32	nfserr;
+
+	dprintk("nfsd: RENAME   %s %.*s -> \n",
+		SVCFH_fmt(&argp->ffh), argp->flen, argp->fname);
+	dprintk("nfsd:        ->  %s %.*s\n",
+		SVCFH_fmt(&argp->tfh), argp->tlen, argp->tname);
+
+	nfserr = nfsd_rename(rqstp, &argp->ffh, argp->fname, argp->flen,
+				    &argp->tfh, argp->tname, argp->tlen);
+	fh_put(&argp->ffh);
+	fh_put(&argp->tfh);
+	return nfserr;
+}
+
+static __be32
+nfsd_proc_link(struct svc_rqst *rqstp, struct nfsd_linkargs *argp,
+				void			    *resp)
+{
+	__be32	nfserr;
+
+	dprintk("nfsd: LINK     %s ->\n",
+		SVCFH_fmt(&argp->ffh));
+	dprintk("nfsd:    %s %.*s\n",
+		SVCFH_fmt(&argp->tfh),
+		argp->tlen,
+		argp->tname);
+
+	nfserr = nfsd_link(rqstp, &argp->tfh, argp->tname, argp->tlen,
+				  &argp->ffh);
+	fh_put(&argp->ffh);
+	fh_put(&argp->tfh);
+	return nfserr;
+}
+
+static __be32
+nfsd_proc_symlink(struct svc_rqst *rqstp, struct nfsd_symlinkargs *argp,
+				          void			  *resp)
+{
+	struct svc_fh	newfh;
+	__be32		nfserr;
+
+	dprintk("nfsd: SYMLINK  %s %.*s -> %.*s\n",
+		SVCFH_fmt(&argp->ffh), argp->flen, argp->fname,
+		argp->tlen, argp->tname);
+
+	fh_init(&newfh, NFS_FHSIZE);
+	/*
+	 * Crazy hack: the request fits in a page, and already-decoded
+	 * attributes follow argp->tname, so it's safe to just write a
+	 * null to ensure it's null-terminated:
+	 */
+	argp->tname[argp->tlen] = '\0';
+	nfserr = nfsd_symlink(rqstp, &argp->ffh, argp->fname, argp->flen,
+						 argp->tname, &newfh);
+
+	fh_put(&argp->ffh);
+	fh_put(&newfh);
+	return nfserr;
+}
+
+/*
+ * Make directory. This operation is not idempotent.
+ * N.B. After this call resp->fh needs an fh_put
+ */
+static __be32
+nfsd_proc_mkdir(struct svc_rqst *rqstp, struct nfsd_createargs *argp,
+					struct nfsd_diropres   *resp)
+{
+	__be32	nfserr;
+
+	dprintk("nfsd: MKDIR    %s %.*s\n", SVCFH_fmt(&argp->fh), argp->len, argp->name);
+
+	if (resp->fh.fh_dentry) {
+		printk(KERN_WARNING
+			"nfsd_proc_mkdir: response already verified??\n");
+	}
+
+	argp->attrs.ia_valid &= ~ATTR_SIZE;
+	fh_init(&resp->fh, NFS_FHSIZE);
+	nfserr = nfsd_create(rqstp, &argp->fh, argp->name, argp->len,
+				    &argp->attrs, S_IFDIR, 0, &resp->fh);
+	fh_put(&argp->fh);
+	return nfsd_return_dirop(nfserr, resp);
+}
+
+/*
+ * Remove a directory
+ */
+static __be32
+nfsd_proc_rmdir(struct svc_rqst *rqstp, struct nfsd_diropargs *argp,
+				 	void		      *resp)
+{
+	__be32	nfserr;
+
+	dprintk("nfsd: RMDIR    %s %.*s\n", SVCFH_fmt(&argp->fh), argp->len, argp->name);
+
+	nfserr = nfsd_unlink(rqstp, &argp->fh, S_IFDIR, argp->name, argp->len);
+	fh_put(&argp->fh);
+	return nfserr;
+}
+
+/*
+ * Read a portion of a directory.
+ */
+static __be32
+nfsd_proc_readdir(struct svc_rqst *rqstp, struct nfsd_readdirargs *argp,
+					  struct nfsd_readdirres  *resp)
+{
+	int		count;
+	__be32		nfserr;
+	loff_t		offset;
+
+	dprintk("nfsd: READDIR  %s %d bytes at %d\n",
+		SVCFH_fmt(&argp->fh),		
+		argp->count, argp->cookie);
+
+	/* Shrink to the client read size */
+	count = (argp->count >> 2) - 2;
+
+	/* Make sure we've room for the NULL ptr & eof flag */
+	count -= 2;
+	if (count < 0)
+		count = 0;
+
+	resp->buffer = argp->buffer;
+	resp->offset = NULL;
+	resp->buflen = count;
+	resp->common.err = nfs_ok;
+	/* Read directory and encode entries on the fly */
+	offset = argp->cookie;
+	nfserr = nfsd_readdir(rqstp, &argp->fh, &offset, 
+			      &resp->common, nfssvc_encode_entry);
+
+	resp->count = resp->buffer - argp->buffer;
+	if (resp->offset)
+		*resp->offset = htonl(offset);
+
+	fh_put(&argp->fh);
+	return nfserr;
+}
+
+/*
+ * Get file system info
+ */
+static __be32
+nfsd_proc_statfs(struct svc_rqst * rqstp, struct nfsd_fhandle   *argp,
+					  struct nfsd_statfsres *resp)
+{
+	__be32	nfserr;
+
+	dprintk("nfsd: STATFS   %s\n", SVCFH_fmt(&argp->fh));
+
+	nfserr = nfsd_statfs(rqstp, &argp->fh, &resp->stats,
+			NFSD_MAY_BYPASS_GSS_ON_ROOT);
+	fh_put(&argp->fh);
+	return nfserr;
+}
+
+/*
+ * NFSv2 Server procedures.
+ * Only the results of non-idempotent operations are cached.
+ */
+struct nfsd_void { int dummy; };
+
+#define ST 1		/* status */
+#define FH 8		/* filehandle */
+#define	AT 18		/* attributes */
+
+static struct svc_procedure		nfsd_procedures2[18] = {
+	[NFSPROC_NULL] = {
+		.pc_func = (svc_procfunc) nfsd_proc_null,
+		.pc_decode = (kxdrproc_t) nfssvc_decode_void,
+		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_argsize = sizeof(struct nfsd_void),
+		.pc_ressize = sizeof(struct nfsd_void),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST,
+	},
+	[NFSPROC_GETATTR] = {
+		.pc_func = (svc_procfunc) nfsd_proc_getattr,
+		.pc_decode = (kxdrproc_t) nfssvc_decode_fhandle,
+		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
+		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd_fhandle),
+		.pc_ressize = sizeof(struct nfsd_attrstat),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+AT,
+	},
+	[NFSPROC_SETATTR] = {
+		.pc_func = (svc_procfunc) nfsd_proc_setattr,
+		.pc_decode = (kxdrproc_t) nfssvc_decode_sattrargs,
+		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
+		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd_sattrargs),
+		.pc_ressize = sizeof(struct nfsd_attrstat),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+AT,
+	},
+	[NFSPROC_ROOT] = {
+		.pc_decode = (kxdrproc_t) nfssvc_decode_void,
+		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_argsize = sizeof(struct nfsd_void),
+		.pc_ressize = sizeof(struct nfsd_void),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST,
+	},
+	[NFSPROC_LOOKUP] = {
+		.pc_func = (svc_procfunc) nfsd_proc_lookup,
+		.pc_decode = (kxdrproc_t) nfssvc_decode_diropargs,
+		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
+		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd_diropargs),
+		.pc_ressize = sizeof(struct nfsd_diropres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+FH+AT,
+	},
+	[NFSPROC_READLINK] = {
+		.pc_func = (svc_procfunc) nfsd_proc_readlink,
+		.pc_decode = (kxdrproc_t) nfssvc_decode_readlinkargs,
+		.pc_encode = (kxdrproc_t) nfssvc_encode_readlinkres,
+		.pc_argsize = sizeof(struct nfsd_readlinkargs),
+		.pc_ressize = sizeof(struct nfsd_readlinkres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+1+NFS_MAXPATHLEN/4,
+	},
+	[NFSPROC_READ] = {
+		.pc_func = (svc_procfunc) nfsd_proc_read,
+		.pc_decode = (kxdrproc_t) nfssvc_decode_readargs,
+		.pc_encode = (kxdrproc_t) nfssvc_encode_readres,
+		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd_readargs),
+		.pc_ressize = sizeof(struct nfsd_readres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+AT+1+NFSSVC_MAXBLKSIZE_V2/4,
+	},
+	[NFSPROC_WRITECACHE] = {
+		.pc_decode = (kxdrproc_t) nfssvc_decode_void,
+		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_argsize = sizeof(struct nfsd_void),
+		.pc_ressize = sizeof(struct nfsd_void),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST,
+	},
+	[NFSPROC_WRITE] = {
+		.pc_func = (svc_procfunc) nfsd_proc_write,
+		.pc_decode = (kxdrproc_t) nfssvc_decode_writeargs,
+		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
+		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd_writeargs),
+		.pc_ressize = sizeof(struct nfsd_attrstat),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+AT,
+	},
+	[NFSPROC_CREATE] = {
+		.pc_func = (svc_procfunc) nfsd_proc_create,
+		.pc_decode = (kxdrproc_t) nfssvc_decode_createargs,
+		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
+		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd_createargs),
+		.pc_ressize = sizeof(struct nfsd_diropres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+FH+AT,
+	},
+	[NFSPROC_REMOVE] = {
+		.pc_func = (svc_procfunc) nfsd_proc_remove,
+		.pc_decode = (kxdrproc_t) nfssvc_decode_diropargs,
+		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_argsize = sizeof(struct nfsd_diropargs),
+		.pc_ressize = sizeof(struct nfsd_void),
+		.pc_cachetype = RC_REPLSTAT,
+		.pc_xdrressize = ST,
+	},
+	[NFSPROC_RENAME] = {
+		.pc_func = (svc_procfunc) nfsd_proc_rename,
+		.pc_decode = (kxdrproc_t) nfssvc_decode_renameargs,
+		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_argsize = sizeof(struct nfsd_renameargs),
+		.pc_ressize = sizeof(struct nfsd_void),
+		.pc_cachetype = RC_REPLSTAT,
+		.pc_xdrressize = ST,
+	},
+	[NFSPROC_LINK] = {
+		.pc_func = (svc_procfunc) nfsd_proc_link,
+		.pc_decode = (kxdrproc_t) nfssvc_decode_linkargs,
+		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_argsize = sizeof(struct nfsd_linkargs),
+		.pc_ressize = sizeof(struct nfsd_void),
+		.pc_cachetype = RC_REPLSTAT,
+		.pc_xdrressize = ST,
+	},
+	[NFSPROC_SYMLINK] = {
+		.pc_func = (svc_procfunc) nfsd_proc_symlink,
+		.pc_decode = (kxdrproc_t) nfssvc_decode_symlinkargs,
+		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_argsize = sizeof(struct nfsd_symlinkargs),
+		.pc_ressize = sizeof(struct nfsd_void),
+		.pc_cachetype = RC_REPLSTAT,
+		.pc_xdrressize = ST,
+	},
+	[NFSPROC_MKDIR] = {
+		.pc_func = (svc_procfunc) nfsd_proc_mkdir,
+		.pc_decode = (kxdrproc_t) nfssvc_decode_createargs,
+		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
+		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd_createargs),
+		.pc_ressize = sizeof(struct nfsd_diropres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+FH+AT,
+	},
+	[NFSPROC_RMDIR] = {
+		.pc_func = (svc_procfunc) nfsd_proc_rmdir,
+		.pc_decode = (kxdrproc_t) nfssvc_decode_diropargs,
+		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_argsize = sizeof(struct nfsd_diropargs),
+		.pc_ressize = sizeof(struct nfsd_void),
+		.pc_cachetype = RC_REPLSTAT,
+		.pc_xdrressize = ST,
+	},
+	[NFSPROC_READDIR] = {
+		.pc_func = (svc_procfunc) nfsd_proc_readdir,
+		.pc_decode = (kxdrproc_t) nfssvc_decode_readdirargs,
+		.pc_encode = (kxdrproc_t) nfssvc_encode_readdirres,
+		.pc_argsize = sizeof(struct nfsd_readdirargs),
+		.pc_ressize = sizeof(struct nfsd_readdirres),
+		.pc_cachetype = RC_NOCACHE,
+	},
+	[NFSPROC_STATFS] = {
+		.pc_func = (svc_procfunc) nfsd_proc_statfs,
+		.pc_decode = (kxdrproc_t) nfssvc_decode_fhandle,
+		.pc_encode = (kxdrproc_t) nfssvc_encode_statfsres,
+		.pc_argsize = sizeof(struct nfsd_fhandle),
+		.pc_ressize = sizeof(struct nfsd_statfsres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+5,
+	},
+};
+
+
+struct svc_version	nfsd_version2 = {
+		.vs_vers	= 2,
+		.vs_nproc	= 18,
+		.vs_proc	= nfsd_procedures2,
+		.vs_dispatch	= nfsd_dispatch,
+		.vs_xdrsize	= NFS2_SVC_XDRSIZE,
+};
+
+/*
+ * Map errnos to NFS errnos.
+ */
+__be32
+nfserrno (int errno)
+{
+	static struct {
+		__be32	nfserr;
+		int	syserr;
+	} nfs_errtbl[] = {
+		{ nfs_ok, 0 },
+		{ nfserr_perm, -EPERM },
+		{ nfserr_noent, -ENOENT },
+		{ nfserr_io, -EIO },
+		{ nfserr_nxio, -ENXIO },
+		{ nfserr_fbig, -E2BIG },
+		{ nfserr_acces, -EACCES },
+		{ nfserr_exist, -EEXIST },
+		{ nfserr_xdev, -EXDEV },
+		{ nfserr_mlink, -EMLINK },
+		{ nfserr_nodev, -ENODEV },
+		{ nfserr_notdir, -ENOTDIR },
+		{ nfserr_isdir, -EISDIR },
+		{ nfserr_inval, -EINVAL },
+		{ nfserr_fbig, -EFBIG },
+		{ nfserr_nospc, -ENOSPC },
+		{ nfserr_rofs, -EROFS },
+		{ nfserr_mlink, -EMLINK },
+		{ nfserr_nametoolong, -ENAMETOOLONG },
+		{ nfserr_notempty, -ENOTEMPTY },
+#ifdef EDQUOT
+		{ nfserr_dquot, -EDQUOT },
+#endif
+		{ nfserr_stale, -ESTALE },
+		{ nfserr_jukebox, -ETIMEDOUT },
+		{ nfserr_jukebox, -ERESTARTSYS },
+		{ nfserr_jukebox, -EAGAIN },
+		{ nfserr_jukebox, -EWOULDBLOCK },
+		{ nfserr_jukebox, -ENOMEM },
+		{ nfserr_io, -ETXTBSY },
+		{ nfserr_notsupp, -EOPNOTSUPP },
+		{ nfserr_toosmall, -ETOOSMALL },
+		{ nfserr_serverfault, -ESERVERFAULT },
+		{ nfserr_serverfault, -ENFILE },
+	};
+	int	i;
+
+	for (i = 0; i < ARRAY_SIZE(nfs_errtbl); i++) {
+		if (nfs_errtbl[i].syserr == errno)
+			return nfs_errtbl[i].nfserr;
+	}
+	WARN(1, "nfsd: non-standard errno: %d\n", errno);
+	return nfserr_io;
+}
+

fs/nfsd/nfssvc.c

@@ -0,0 +1,751 @@
+/*
+ * Central processing for nfsd.
+ *
+ * Authors:	Olaf Kirch (okir@monad.swb.de)
+ *
+ * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de>
+ */
+
+#include <linux/sched.h>
+#include <linux/freezer.h>
+#include <linux/module.h>
+#include <linux/fs_struct.h>
+#include <linux/swap.h>
+
+#include <linux/sunrpc/stats.h>
+#include <linux/sunrpc/svcsock.h>
+#include <linux/lockd/bind.h>
+#include <linux/nfsacl.h>
+#include <linux/seq_file.h>
+#include <net/net_namespace.h>
+#include "nfsd.h"
+#include "cache.h"
+#include "vfs.h"
+#include "netns.h"
+
+#define NFSDDBG_FACILITY	NFSDDBG_SVC
+
+extern struct svc_program	nfsd_program;
+static int			nfsd(void *vrqstp);
+
+/*
+ * nfsd_mutex protects nn->nfsd_serv -- both the pointer itself and the members
+ * of the svc_serv struct. In particular, ->sv_nrthreads but also to some
+ * extent ->sv_temp_socks and ->sv_permsocks. It also protects nfsdstats.th_cnt
+ *
+ * If (out side the lock) nn->nfsd_serv is non-NULL, then it must point to a
+ * properly initialised 'struct svc_serv' with ->sv_nrthreads > 0. That number
+ * of nfsd threads must exist and each must listed in ->sp_all_threads in each
+ * entry of ->sv_pools[].
+ *
+ * Transitions of the thread count between zero and non-zero are of particular
+ * interest since the svc_serv needs to be created and initialized at that
+ * point, or freed.
+ *
+ * Finally, the nfsd_mutex also protects some of the global variables that are
+ * accessed when nfsd starts and that are settable via the write_* routines in
+ * nfsctl.c. In particular:
+ *
+ *	user_recovery_dirname
+ *	user_lease_time
+ *	nfsd_versions
+ */
+DEFINE_MUTEX(nfsd_mutex);
+
+/*
+ * nfsd_drc_lock protects nfsd_drc_max_pages and nfsd_drc_pages_used.
+ * nfsd_drc_max_pages limits the total amount of memory available for
+ * version 4.1 DRC caches.
+ * nfsd_drc_pages_used tracks the current version 4.1 DRC memory usage.
+ */
+spinlock_t	nfsd_drc_lock;
+unsigned long	nfsd_drc_max_mem;
+unsigned long	nfsd_drc_mem_used;
+
+#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
+static struct svc_stat	nfsd_acl_svcstats;
+static struct svc_version *	nfsd_acl_version[] = {
+	[2] = &nfsd_acl_version2,
+	[3] = &nfsd_acl_version3,
+};
+
+#define NFSD_ACL_MINVERS            2
+#define NFSD_ACL_NRVERS		ARRAY_SIZE(nfsd_acl_version)
+static struct svc_version *nfsd_acl_versions[NFSD_ACL_NRVERS];
+
+static struct svc_program	nfsd_acl_program = {
+	.pg_prog		= NFS_ACL_PROGRAM,
+	.pg_nvers		= NFSD_ACL_NRVERS,
+	.pg_vers		= nfsd_acl_versions,
+	.pg_name		= "nfsacl",
+	.pg_class		= "nfsd",
+	.pg_stats		= &nfsd_acl_svcstats,
+	.pg_authenticate	= &svc_set_client,
+};
+
+static struct svc_stat	nfsd_acl_svcstats = {
+	.program	= &nfsd_acl_program,
+};
+#endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */
+
+static struct svc_version *	nfsd_version[] = {
+	[2] = &nfsd_version2,
+#if defined(CONFIG_NFSD_V3)
+	[3] = &nfsd_version3,
+#endif
+#if defined(CONFIG_NFSD_V4)
+	[4] = &nfsd_version4,
+#endif
+};
+
+#define NFSD_MINVERS    	2
+#define NFSD_NRVERS		ARRAY_SIZE(nfsd_version)
+static struct svc_version *nfsd_versions[NFSD_NRVERS];
+
+struct svc_program		nfsd_program = {
+#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
+	.pg_next		= &nfsd_acl_program,
+#endif
+	.pg_prog		= NFS_PROGRAM,		/* program number */
+	.pg_nvers		= NFSD_NRVERS,		/* nr of entries in nfsd_version */
+	.pg_vers		= nfsd_versions,	/* version table */
+	.pg_name		= "nfsd",		/* program name */
+	.pg_class		= "nfsd",		/* authentication class */
+	.pg_stats		= &nfsd_svcstats,	/* version table */
+	.pg_authenticate	= &svc_set_client,	/* export authentication */
+
+};
+
+static bool nfsd_supported_minorversions[NFSD_SUPPORTED_MINOR_VERSION + 1] = {
+	[0] = 1,
+	[1] = 1,
+};
+
+int nfsd_vers(int vers, enum vers_op change)
+{
+	if (vers < NFSD_MINVERS || vers >= NFSD_NRVERS)
+		return 0;
+	switch(change) {
+	case NFSD_SET:
+		nfsd_versions[vers] = nfsd_version[vers];
+#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
+		if (vers < NFSD_ACL_NRVERS)
+			nfsd_acl_versions[vers] = nfsd_acl_version[vers];
+#endif
+		break;
+	case NFSD_CLEAR:
+		nfsd_versions[vers] = NULL;
+#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
+		if (vers < NFSD_ACL_NRVERS)
+			nfsd_acl_versions[vers] = NULL;
+#endif
+		break;
+	case NFSD_TEST:
+		return nfsd_versions[vers] != NULL;
+	case NFSD_AVAIL:
+		return nfsd_version[vers] != NULL;
+	}
+	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_minorversions[minorversion] = true;
+		break;
+	case NFSD_CLEAR:
+		nfsd_supported_minorversions[minorversion] = false;
+		break;
+	case NFSD_TEST:
+		return nfsd_supported_minorversions[minorversion];
+	case NFSD_AVAIL:
+		return minorversion <= NFSD_SUPPORTED_MINOR_VERSION;
+	}
+	return 0;
+}
+
+/*
+ * Maximum number of nfsd processes
+ */
+#define	NFSD_MAXSERVS		8192
+
+int nfsd_nrthreads(struct net *net)
+{
+	int rv = 0;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	mutex_lock(&nfsd_mutex);
+	if (nn->nfsd_serv)
+		rv = nn->nfsd_serv->sv_nrthreads;
+	mutex_unlock(&nfsd_mutex);
+	return rv;
+}
+
+static int nfsd_init_socks(struct net *net)
+{
+	int error;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	if (!list_empty(&nn->nfsd_serv->sv_permsocks))
+		return 0;
+
+	error = svc_create_xprt(nn->nfsd_serv, "udp", net, PF_INET, NFS_PORT,
+					SVC_SOCK_DEFAULTS);
+	if (error < 0)
+		return error;
+
+	error = svc_create_xprt(nn->nfsd_serv, "tcp", net, PF_INET, NFS_PORT,
+					SVC_SOCK_DEFAULTS);
+	if (error < 0)
+		return error;
+
+	return 0;
+}
+
+static int nfsd_users = 0;
+
+static int nfsd_startup_generic(int nrservs)
+{
+	int ret;
+
+	if (nfsd_users++)
+		return 0;
+
+	/*
+	 * Readahead param cache - will no-op if it already exists.
+	 * (Note therefore results will be suboptimal if number of
+	 * threads is modified after nfsd start.)
+	 */
+	ret = nfsd_racache_init(2*nrservs);
+	if (ret)
+		goto dec_users;
+
+	ret = nfs4_state_start();
+	if (ret)
+		goto out_racache;
+	return 0;
+
+out_racache:
+	nfsd_racache_shutdown();
+dec_users:
+	nfsd_users--;
+	return ret;
+}
+
+static void nfsd_shutdown_generic(void)
+{
+	if (--nfsd_users)
+		return;
+
+	nfs4_state_shutdown();
+	nfsd_racache_shutdown();
+}
+
+static bool nfsd_needs_lockd(void)
+{
+#if defined(CONFIG_NFSD_V3)
+	return (nfsd_versions[2] != NULL) || (nfsd_versions[3] != NULL);
+#else
+	return (nfsd_versions[2] != NULL);
+#endif
+}
+
+static int nfsd_startup_net(int nrservs, struct net *net)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	int ret;
+
+	if (nn->nfsd_net_up)
+		return 0;
+
+	ret = nfsd_startup_generic(nrservs);
+	if (ret)
+		return ret;
+	ret = nfsd_init_socks(net);
+	if (ret)
+		goto out_socks;
+
+	if (nfsd_needs_lockd() && !nn->lockd_up) {
+		ret = lockd_up(net);
+		if (ret)
+			goto out_socks;
+		nn->lockd_up = 1;
+	}
+
+	ret = nfs4_state_start_net(net);
+	if (ret)
+		goto out_lockd;
+
+	nn->nfsd_net_up = true;
+	return 0;
+
+out_lockd:
+	if (nn->lockd_up) {
+		lockd_down(net);
+		nn->lockd_up = 0;
+	}
+out_socks:
+	nfsd_shutdown_generic();
+	return ret;
+}
+
+static void nfsd_shutdown_net(struct net *net)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	nfs4_state_shutdown_net(net);
+	if (nn->lockd_up) {
+		lockd_down(net);
+		nn->lockd_up = 0;
+	}
+	nn->nfsd_net_up = false;
+	nfsd_shutdown_generic();
+}
+
+static void nfsd_last_thread(struct svc_serv *serv, struct net *net)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	/*
+	 * write_ports can create the server without actually starting
+	 * any threads--if we get shut down before any threads are
+	 * started, then nfsd_last_thread will be run before any of this
+	 * other initialization has been done.
+	 */
+	if (!nn->nfsd_net_up)
+		return;
+	nfsd_shutdown_net(net);
+
+	svc_rpcb_cleanup(serv, net);
+
+	printk(KERN_WARNING "nfsd: last server has exited, flushing export "
+			    "cache\n");
+	nfsd_export_flush(net);
+}
+
+void nfsd_reset_versions(void)
+{
+	int found_one = 0;
+	int i;
+
+	for (i = NFSD_MINVERS; i < NFSD_NRVERS; i++) {
+		if (nfsd_program.pg_vers[i])
+			found_one = 1;
+	}
+
+	if (!found_one) {
+		for (i = NFSD_MINVERS; i < NFSD_NRVERS; i++)
+			nfsd_program.pg_vers[i] = nfsd_version[i];
+#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
+		for (i = NFSD_ACL_MINVERS; i < NFSD_ACL_NRVERS; i++)
+			nfsd_acl_program.pg_vers[i] =
+				nfsd_acl_version[i];
+#endif
+	}
+}
+
+/*
+ * 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)
+{
+	#define NFSD_DRC_SIZE_SHIFT	10
+	nfsd_drc_max_mem = (nr_free_buffer_pages()
+					>> NFSD_DRC_SIZE_SHIFT) * PAGE_SIZE;
+	nfsd_drc_mem_used = 0;
+	spin_lock_init(&nfsd_drc_lock);
+	dprintk("%s nfsd_drc_max_mem %lu \n", __func__, nfsd_drc_max_mem);
+}
+
+static int nfsd_get_default_max_blksize(void)
+{
+	struct sysinfo i;
+	unsigned long long target;
+	unsigned long ret;
+
+	si_meminfo(&i);
+	target = (i.totalram - i.totalhigh) << PAGE_SHIFT;
+	/*
+	 * Aim for 1/4096 of memory per thread This gives 1MB on 4Gig
+	 * machines, but only uses 32K on 128M machines.  Bottom out at
+	 * 8K on 32M and smaller.  Of course, this is only a default.
+	 */
+	target >>= 12;
+
+	ret = NFSSVC_MAXBLKSIZE;
+	while (ret > target && ret >= 8*1024*2)
+		ret /= 2;
+	return ret;
+}
+
+int nfsd_create_serv(struct net *net)
+{
+	int error;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	WARN_ON(!mutex_is_locked(&nfsd_mutex));
+	if (nn->nfsd_serv) {
+		svc_get(nn->nfsd_serv);
+		return 0;
+	}
+	if (nfsd_max_blksize == 0)
+		nfsd_max_blksize = nfsd_get_default_max_blksize();
+	nfsd_reset_versions();
+	nn->nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize,
+				      nfsd_last_thread, nfsd, THIS_MODULE);
+	if (nn->nfsd_serv == NULL)
+		return -ENOMEM;
+
+	nn->nfsd_serv->sv_maxconn = nn->max_connections;
+	error = svc_bind(nn->nfsd_serv, net);
+	if (error < 0) {
+		svc_destroy(nn->nfsd_serv);
+		return error;
+	}
+
+	set_max_drc();
+	do_gettimeofday(&nn->nfssvc_boot);		/* record boot time */
+	return 0;
+}
+
+int nfsd_nrpools(struct net *net)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	if (nn->nfsd_serv == NULL)
+		return 0;
+	else
+		return nn->nfsd_serv->sv_nrpools;
+}
+
+int nfsd_get_nrthreads(int n, int *nthreads, struct net *net)
+{
+	int i = 0;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	if (nn->nfsd_serv != NULL) {
+		for (i = 0; i < nn->nfsd_serv->sv_nrpools && i < n; i++)
+			nthreads[i] = nn->nfsd_serv->sv_pools[i].sp_nrthreads;
+	}
+
+	return 0;
+}
+
+void nfsd_destroy(struct net *net)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	int destroy = (nn->nfsd_serv->sv_nrthreads == 1);
+
+	if (destroy)
+		svc_shutdown_net(nn->nfsd_serv, net);
+	svc_destroy(nn->nfsd_serv);
+	if (destroy)
+		nn->nfsd_serv = NULL;
+}
+
+int nfsd_set_nrthreads(int n, int *nthreads, struct net *net)
+{
+	int i = 0;
+	int tot = 0;
+	int err = 0;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	WARN_ON(!mutex_is_locked(&nfsd_mutex));
+
+	if (nn->nfsd_serv == NULL || n <= 0)
+		return 0;
+
+	if (n > nn->nfsd_serv->sv_nrpools)
+		n = nn->nfsd_serv->sv_nrpools;
+
+	/* enforce a global maximum number of threads */
+	tot = 0;
+	for (i = 0; i < n; i++) {
+		nthreads[i] = min(nthreads[i], NFSD_MAXSERVS);
+		tot += nthreads[i];
+	}
+	if (tot > NFSD_MAXSERVS) {
+		/* total too large: scale down requested numbers */
+		for (i = 0; i < n && tot > 0; i++) {
+		    	int new = nthreads[i] * NFSD_MAXSERVS / tot;
+			tot -= (nthreads[i] - new);
+			nthreads[i] = new;
+		}
+		for (i = 0; i < n && tot > 0; i++) {
+			nthreads[i]--;
+			tot--;
+		}
+	}
+
+	/*
+	 * There must always be a thread in pool 0; the admin
+	 * can't shut down NFS completely using pool_threads.
+	 */
+	if (nthreads[0] == 0)
+		nthreads[0] = 1;
+
+	/* apply the new numbers */
+	svc_get(nn->nfsd_serv);
+	for (i = 0; i < n; i++) {
+		err = svc_set_num_threads(nn->nfsd_serv, &nn->nfsd_serv->sv_pools[i],
+				    	  nthreads[i]);
+		if (err)
+			break;
+	}
+	nfsd_destroy(net);
+	return err;
+}
+
+/*
+ * Adjust the number of threads and return the new number of threads.
+ * This is also the function that starts the server if necessary, if
+ * this is the first time nrservs is nonzero.
+ */
+int
+nfsd_svc(int nrservs, struct net *net)
+{
+	int	error;
+	bool	nfsd_up_before;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	mutex_lock(&nfsd_mutex);
+	dprintk("nfsd: creating service\n");
+
+	nrservs = max(nrservs, 0);
+	nrservs = min(nrservs, NFSD_MAXSERVS);
+	error = 0;
+
+	if (nrservs == 0 && nn->nfsd_serv == NULL)
+		goto out;
+
+	error = nfsd_create_serv(net);
+	if (error)
+		goto out;
+
+	nfsd_up_before = nn->nfsd_net_up;
+
+	error = nfsd_startup_net(nrservs, net);
+	if (error)
+		goto out_destroy;
+	error = svc_set_num_threads(nn->nfsd_serv, NULL, nrservs);
+	if (error)
+		goto out_shutdown;
+	/* We are holding a reference to nn->nfsd_serv which
+	 * we don't want to count in the return value,
+	 * so subtract 1
+	 */
+	error = nn->nfsd_serv->sv_nrthreads - 1;
+out_shutdown:
+	if (error < 0 && !nfsd_up_before)
+		nfsd_shutdown_net(net);
+out_destroy:
+	nfsd_destroy(net);		/* Release server */
+out:
+	mutex_unlock(&nfsd_mutex);
+	return error;
+}
+
+
+/*
+ * This is the NFS server kernel thread
+ */
+static int
+nfsd(void *vrqstp)
+{
+	struct svc_rqst *rqstp = (struct svc_rqst *) vrqstp;
+	struct svc_xprt *perm_sock = list_entry(rqstp->rq_server->sv_permsocks.next, typeof(struct svc_xprt), xpt_list);
+	struct net *net = perm_sock->xpt_net;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	int err;
+
+	/* Lock module and set up kernel thread */
+	mutex_lock(&nfsd_mutex);
+
+	/* At this point, the thread shares current->fs
+	 * with the init process. We need to create files with a
+	 * umask of 0 instead of init's umask. */
+	if (unshare_fs_struct() < 0) {
+		printk("Unable to start nfsd thread: out of memory\n");
+		goto out;
+	}
+
+	current->fs->umask = 0;
+
+	/*
+	 * thread is spawned with all signals set to SIG_IGN, re-enable
+	 * the ones that will bring down the thread
+	 */
+	allow_signal(SIGKILL);
+	allow_signal(SIGHUP);
+	allow_signal(SIGINT);
+	allow_signal(SIGQUIT);
+
+	nfsdstats.th_cnt++;
+	mutex_unlock(&nfsd_mutex);
+
+	set_freezable();
+
+	/*
+	 * The main request loop
+	 */
+	for (;;) {
+		/* Update sv_maxconn if it has changed */
+		rqstp->rq_server->sv_maxconn = nn->max_connections;
+
+		/*
+		 * Find a socket with data available and call its
+		 * recvfrom routine.
+		 */
+		while ((err = svc_recv(rqstp, 60*60*HZ)) == -EAGAIN)
+			;
+		if (err == -EINTR)
+			break;
+		validate_process_creds();
+		svc_process(rqstp);
+		validate_process_creds();
+	}
+
+	/* Clear signals before calling svc_exit_thread() */
+	flush_signals(current);
+
+	mutex_lock(&nfsd_mutex);
+	nfsdstats.th_cnt --;
+
+out:
+	rqstp->rq_server = NULL;
+
+	/* Release the thread */
+	svc_exit_thread(rqstp);
+
+	nfsd_destroy(net);
+
+	/* Release module */
+	mutex_unlock(&nfsd_mutex);
+	module_put_and_exit(0);
+	return 0;
+}
+
+static __be32 map_new_errors(u32 vers, __be32 nfserr)
+{
+	if (nfserr == nfserr_jukebox && vers == 2)
+		return nfserr_dropit;
+	if (nfserr == nfserr_wrongsec && vers < 4)
+		return nfserr_acces;
+	return nfserr;
+}
+
+int
+nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
+{
+	struct svc_procedure	*proc;
+	kxdrproc_t		xdr;
+	__be32			nfserr;
+	__be32			*nfserrp;
+
+	dprintk("nfsd_dispatch: vers %d proc %d\n",
+				rqstp->rq_vers, rqstp->rq_proc);
+	proc = rqstp->rq_procinfo;
+
+	/*
+	 * Give the xdr decoder a chance to change this if it wants
+	 * (necessary in the NFSv4.0 compound case)
+	 */
+	rqstp->rq_cachetype = proc->pc_cachetype;
+	/* Decode arguments */
+	xdr = proc->pc_decode;
+	if (xdr && !xdr(rqstp, (__be32*)rqstp->rq_arg.head[0].iov_base,
+			rqstp->rq_argp)) {
+		dprintk("nfsd: failed to decode arguments!\n");
+		*statp = rpc_garbage_args;
+		return 1;
+	}
+
+	/* Check whether we have this call in the cache. */
+	switch (nfsd_cache_lookup(rqstp)) {
+	case RC_DROPIT:
+		return 0;
+	case RC_REPLY:
+		return 1;
+	case RC_DOIT:;
+		/* do it */
+	}
+
+	/* need to grab the location to store the status, as
+	 * nfsv4 does some encoding while processing 
+	 */
+	nfserrp = rqstp->rq_res.head[0].iov_base
+		+ rqstp->rq_res.head[0].iov_len;
+	rqstp->rq_res.head[0].iov_len += sizeof(__be32);
+
+	/* Now call the procedure handler, and encode NFS status. */
+	nfserr = proc->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp);
+	nfserr = map_new_errors(rqstp->rq_vers, nfserr);
+	if (nfserr == nfserr_dropit || rqstp->rq_dropme) {
+		dprintk("nfsd: Dropping request; may be revisited later\n");
+		nfsd_cache_update(rqstp, RC_NOCACHE, NULL);
+		return 0;
+	}
+
+	if (rqstp->rq_proc != 0)
+		*nfserrp++ = nfserr;
+
+	/* Encode result.
+	 * For NFSv2, additional info is never returned in case of an error.
+	 */
+	if (!(nfserr && rqstp->rq_vers == 2)) {
+		xdr = proc->pc_encode;
+		if (xdr && !xdr(rqstp, nfserrp,
+				rqstp->rq_resp)) {
+			/* Failed to encode result. Release cache entry */
+			dprintk("nfsd: failed to encode result!\n");
+			nfsd_cache_update(rqstp, RC_NOCACHE, NULL);
+			*statp = rpc_system_err;
+			return 1;
+		}
+	}
+
+	/* Store reply in cache. */
+	nfsd_cache_update(rqstp, rqstp->rq_cachetype, statp + 1);
+	return 1;
+}
+
+int nfsd_pool_stats_open(struct inode *inode, struct file *file)
+{
+	int ret;
+	struct nfsd_net *nn = net_generic(inode->i_sb->s_fs_info, nfsd_net_id);
+
+	mutex_lock(&nfsd_mutex);
+	if (nn->nfsd_serv == NULL) {
+		mutex_unlock(&nfsd_mutex);
+		return -ENODEV;
+	}
+	/* bump up the psudo refcount while traversing */
+	svc_get(nn->nfsd_serv);
+	ret = svc_pool_stats_open(nn->nfsd_serv, file);
+	mutex_unlock(&nfsd_mutex);
+	return ret;
+}
+
+int nfsd_pool_stats_release(struct inode *inode, struct file *file)
+{
+	int ret = seq_release(inode, file);
+	struct net *net = inode->i_sb->s_fs_info;
+
+	mutex_lock(&nfsd_mutex);
+	/* this function really, really should have been called svc_put() */
+	nfsd_destroy(net);
+	mutex_unlock(&nfsd_mutex);
+	return ret;
+}

fs/nfsd/nfsxdr.c

@@ -0,0 +1,550 @@
+/*
+ * XDR support for nfsd
+ *
+ * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
+ */
+
+#include "vfs.h"
+#include "xdr.h"
+#include "auth.h"
+
+#define NFSDDBG_FACILITY		NFSDDBG_XDR
+
+/*
+ * Mapping of S_IF* types to NFS file types
+ */
+static u32	nfs_ftypes[] = {
+	NFNON,  NFCHR,  NFCHR, NFBAD,
+	NFDIR,  NFBAD,  NFBLK, NFBAD,
+	NFREG,  NFBAD,  NFLNK, NFBAD,
+	NFSOCK, NFBAD,  NFLNK, NFBAD,
+};
+
+
+/*
+ * XDR functions for basic NFS types
+ */
+static __be32 *
+decode_fh(__be32 *p, struct svc_fh *fhp)
+{
+	fh_init(fhp, NFS_FHSIZE);
+	memcpy(&fhp->fh_handle.fh_base, p, NFS_FHSIZE);
+	fhp->fh_handle.fh_size = NFS_FHSIZE;
+
+	/* FIXME: Look up export pointer here and verify
+	 * Sun Secure RPC if requested */
+	return p + (NFS_FHSIZE >> 2);
+}
+
+/* Helper function for NFSv2 ACL code */
+__be32 *nfs2svc_decode_fh(__be32 *p, struct svc_fh *fhp)
+{
+	return decode_fh(p, fhp);
+}
+
+static __be32 *
+encode_fh(__be32 *p, struct svc_fh *fhp)
+{
+	memcpy(p, &fhp->fh_handle.fh_base, NFS_FHSIZE);
+	return p + (NFS_FHSIZE>> 2);
+}
+
+/*
+ * Decode a file name and make sure that the path contains
+ * no slashes or null bytes.
+ */
+static __be32 *
+decode_filename(__be32 *p, char **namp, unsigned int *lenp)
+{
+	char		*name;
+	unsigned int	i;
+
+	if ((p = xdr_decode_string_inplace(p, namp, lenp, NFS_MAXNAMLEN)) != NULL) {
+		for (i = 0, name = *namp; i < *lenp; i++, name++) {
+			if (*name == '\0' || *name == '/')
+				return NULL;
+		}
+	}
+
+	return p;
+}
+
+static __be32 *
+decode_pathname(__be32 *p, char **namp, unsigned int *lenp)
+{
+	char		*name;
+	unsigned int	i;
+
+	if ((p = xdr_decode_string_inplace(p, namp, lenp, NFS_MAXPATHLEN)) != NULL) {
+		for (i = 0, name = *namp; i < *lenp; i++, name++) {
+			if (*name == '\0')
+				return NULL;
+		}
+	}
+
+	return p;
+}
+
+static __be32 *
+decode_sattr(__be32 *p, struct iattr *iap)
+{
+	u32	tmp, tmp1;
+
+	iap->ia_valid = 0;
+
+	/* Sun client bug compatibility check: some sun clients seem to
+	 * put 0xffff in the mode field when they mean 0xffffffff.
+	 * Quoting the 4.4BSD nfs server code: Nah nah nah nah na nah.
+	 */
+	if ((tmp = ntohl(*p++)) != (u32)-1 && tmp != 0xffff) {
+		iap->ia_valid |= ATTR_MODE;
+		iap->ia_mode = tmp;
+	}
+	if ((tmp = ntohl(*p++)) != (u32)-1) {
+		iap->ia_uid = make_kuid(&init_user_ns, tmp);
+		if (uid_valid(iap->ia_uid))
+			iap->ia_valid |= ATTR_UID;
+	}
+	if ((tmp = ntohl(*p++)) != (u32)-1) {
+		iap->ia_gid = make_kgid(&init_user_ns, tmp);
+		if (gid_valid(iap->ia_gid))
+			iap->ia_valid |= ATTR_GID;
+	}
+	if ((tmp = ntohl(*p++)) != (u32)-1) {
+		iap->ia_valid |= ATTR_SIZE;
+		iap->ia_size = tmp;
+	}
+	tmp  = ntohl(*p++); tmp1 = ntohl(*p++);
+	if (tmp != (u32)-1 && tmp1 != (u32)-1) {
+		iap->ia_valid |= ATTR_ATIME | ATTR_ATIME_SET;
+		iap->ia_atime.tv_sec = tmp;
+		iap->ia_atime.tv_nsec = tmp1 * 1000; 
+	}
+	tmp  = ntohl(*p++); tmp1 = ntohl(*p++);
+	if (tmp != (u32)-1 && tmp1 != (u32)-1) {
+		iap->ia_valid |= ATTR_MTIME | ATTR_MTIME_SET;
+		iap->ia_mtime.tv_sec = tmp;
+		iap->ia_mtime.tv_nsec = tmp1 * 1000; 
+		/*
+		 * Passing the invalid value useconds=1000000 for mtime
+		 * is a Sun convention for "set both mtime and atime to
+		 * current server time".  It's needed to make permissions
+		 * checks for the "touch" program across v2 mounts to
+		 * Solaris and Irix boxes work correctly. See description of
+		 * sattr in section 6.1 of "NFS Illustrated" by
+		 * Brent Callaghan, Addison-Wesley, ISBN 0-201-32750-5
+		 */
+		if (tmp1 == 1000000)
+			iap->ia_valid &= ~(ATTR_ATIME_SET|ATTR_MTIME_SET);
+	}
+	return p;
+}
+
+static __be32 *
+encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
+	     struct kstat *stat)
+{
+	struct dentry	*dentry = fhp->fh_dentry;
+	int type;
+	struct timespec time;
+	u32 f;
+
+	type = (stat->mode & S_IFMT);
+
+	*p++ = htonl(nfs_ftypes[type >> 12]);
+	*p++ = htonl((u32) stat->mode);
+	*p++ = htonl((u32) stat->nlink);
+	*p++ = htonl((u32) from_kuid(&init_user_ns, stat->uid));
+	*p++ = htonl((u32) from_kgid(&init_user_ns, stat->gid));
+
+	if (S_ISLNK(type) && stat->size > NFS_MAXPATHLEN) {
+		*p++ = htonl(NFS_MAXPATHLEN);
+	} else {
+		*p++ = htonl((u32) stat->size);
+	}
+	*p++ = htonl((u32) stat->blksize);
+	if (S_ISCHR(type) || S_ISBLK(type))
+		*p++ = htonl(new_encode_dev(stat->rdev));
+	else
+		*p++ = htonl(0xffffffff);
+	*p++ = htonl((u32) stat->blocks);
+	switch (fsid_source(fhp)) {
+	default:
+	case FSIDSOURCE_DEV:
+		*p++ = htonl(new_encode_dev(stat->dev));
+		break;
+	case FSIDSOURCE_FSID:
+		*p++ = htonl((u32) fhp->fh_export->ex_fsid);
+		break;
+	case FSIDSOURCE_UUID:
+		f = ((u32*)fhp->fh_export->ex_uuid)[0];
+		f ^= ((u32*)fhp->fh_export->ex_uuid)[1];
+		f ^= ((u32*)fhp->fh_export->ex_uuid)[2];
+		f ^= ((u32*)fhp->fh_export->ex_uuid)[3];
+		*p++ = htonl(f);
+		break;
+	}
+	*p++ = htonl((u32) stat->ino);
+	*p++ = htonl((u32) stat->atime.tv_sec);
+	*p++ = htonl(stat->atime.tv_nsec ? stat->atime.tv_nsec / 1000 : 0);
+	lease_get_mtime(dentry->d_inode, &time); 
+	*p++ = htonl((u32) time.tv_sec);
+	*p++ = htonl(time.tv_nsec ? time.tv_nsec / 1000 : 0); 
+	*p++ = htonl((u32) stat->ctime.tv_sec);
+	*p++ = htonl(stat->ctime.tv_nsec ? stat->ctime.tv_nsec / 1000 : 0);
+
+	return p;
+}
+
+/* Helper function for NFSv2 ACL code */
+__be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat)
+{
+	return encode_fattr(rqstp, p, fhp, stat);
+}
+
+/*
+ * XDR decode functions
+ */
+int
+nfssvc_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+{
+	return xdr_argsize_check(rqstp, p);
+}
+
+int
+nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *args)
+{
+	p = decode_fh(p, &args->fh);
+	if (!p)
+		return 0;
+	return xdr_argsize_check(rqstp, p);
+}
+
+int
+nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p,
+					struct nfsd_sattrargs *args)
+{
+	p = decode_fh(p, &args->fh);
+	if (!p)
+		return 0;
+	p = decode_sattr(p, &args->attrs);
+
+	return xdr_argsize_check(rqstp, p);
+}
+
+int
+nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p,
+					struct nfsd_diropargs *args)
+{
+	if (!(p = decode_fh(p, &args->fh))
+	 || !(p = decode_filename(p, &args->name, &args->len)))
+		return 0;
+
+	 return xdr_argsize_check(rqstp, p);
+}
+
+int
+nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
+					struct nfsd_readargs *args)
+{
+	unsigned int len;
+	int v;
+	p = decode_fh(p, &args->fh);
+	if (!p)
+		return 0;
+
+	args->offset    = ntohl(*p++);
+	len = args->count     = ntohl(*p++);
+	p++; /* totalcount - unused */
+
+	len = min_t(unsigned int, len, NFSSVC_MAXBLKSIZE_V2);
+
+	/* set up somewhere to store response.
+	 * We take pages, put them on reslist and include in iovec
+	 */
+	v=0;
+	while (len > 0) {
+		struct page *p = *(rqstp->rq_next_page++);
+
+		rqstp->rq_vec[v].iov_base = page_address(p);
+		rqstp->rq_vec[v].iov_len = min_t(unsigned int, len, PAGE_SIZE);
+		len -= rqstp->rq_vec[v].iov_len;
+		v++;
+	}
+	args->vlen = v;
+	return xdr_argsize_check(rqstp, p);
+}
+
+int
+nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
+					struct nfsd_writeargs *args)
+{
+	unsigned int len, hdr, dlen;
+	int v;
+
+	p = decode_fh(p, &args->fh);
+	if (!p)
+		return 0;
+
+	p++;				/* beginoffset */
+	args->offset = ntohl(*p++);	/* offset */
+	p++;				/* totalcount */
+	len = args->len = ntohl(*p++);
+	/*
+	 * The protocol specifies a maximum of 8192 bytes.
+	 */
+	if (len > NFSSVC_MAXBLKSIZE_V2)
+		return 0;
+
+	/*
+	 * Check to make sure that we got the right number of
+	 * bytes.
+	 */
+	hdr = (void*)p - rqstp->rq_arg.head[0].iov_base;
+	dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len
+		- hdr;
+
+	/*
+	 * Round the length of the data which was specified up to
+	 * the next multiple of XDR units and then compare that
+	 * against the length which was actually received.
+	 * Note that when RPCSEC/GSS (for example) is used, the
+	 * data buffer can be padded so dlen might be larger
+	 * than required.  It must never be smaller.
+	 */
+	if (dlen < XDR_QUADLEN(len)*4)
+		return 0;
+
+	rqstp->rq_vec[0].iov_base = (void*)p;
+	rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len - hdr;
+	v = 0;
+	while (len > rqstp->rq_vec[v].iov_len) {
+		len -= rqstp->rq_vec[v].iov_len;
+		v++;
+		rqstp->rq_vec[v].iov_base = page_address(rqstp->rq_pages[v]);
+		rqstp->rq_vec[v].iov_len = PAGE_SIZE;
+	}
+	rqstp->rq_vec[v].iov_len = len;
+	args->vlen = v + 1;
+	return 1;
+}
+
+int
+nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p,
+					struct nfsd_createargs *args)
+{
+	if (   !(p = decode_fh(p, &args->fh))
+	    || !(p = decode_filename(p, &args->name, &args->len)))
+		return 0;
+	p = decode_sattr(p, &args->attrs);
+
+	return xdr_argsize_check(rqstp, p);
+}
+
+int
+nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p,
+					struct nfsd_renameargs *args)
+{
+	if (!(p = decode_fh(p, &args->ffh))
+	 || !(p = decode_filename(p, &args->fname, &args->flen))
+	 || !(p = decode_fh(p, &args->tfh))
+	 || !(p = decode_filename(p, &args->tname, &args->tlen)))
+		return 0;
+
+	return xdr_argsize_check(rqstp, p);
+}
+
+int
+nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readlinkargs *args)
+{
+	p = decode_fh(p, &args->fh);
+	if (!p)
+		return 0;
+	args->buffer = page_address(*(rqstp->rq_next_page++));
+
+	return xdr_argsize_check(rqstp, p);
+}
+
+int
+nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p,
+					struct nfsd_linkargs *args)
+{
+	if (!(p = decode_fh(p, &args->ffh))
+	 || !(p = decode_fh(p, &args->tfh))
+	 || !(p = decode_filename(p, &args->tname, &args->tlen)))
+		return 0;
+
+	return xdr_argsize_check(rqstp, p);
+}
+
+int
+nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
+					struct nfsd_symlinkargs *args)
+{
+	if (   !(p = decode_fh(p, &args->ffh))
+	    || !(p = decode_filename(p, &args->fname, &args->flen))
+	    || !(p = decode_pathname(p, &args->tname, &args->tlen)))
+		return 0;
+	p = decode_sattr(p, &args->attrs);
+
+	return xdr_argsize_check(rqstp, p);
+}
+
+int
+nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p,
+					struct nfsd_readdirargs *args)
+{
+	p = decode_fh(p, &args->fh);
+	if (!p)
+		return 0;
+	args->cookie = ntohl(*p++);
+	args->count  = ntohl(*p++);
+	args->count  = min_t(u32, args->count, PAGE_SIZE);
+	args->buffer = page_address(*(rqstp->rq_next_page++));
+
+	return xdr_argsize_check(rqstp, p);
+}
+
+/*
+ * XDR encode functions
+ */
+int
+nfssvc_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+{
+	return xdr_ressize_check(rqstp, p);
+}
+
+int
+nfssvc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p,
+					struct nfsd_attrstat *resp)
+{
+	p = encode_fattr(rqstp, p, &resp->fh, &resp->stat);
+	return xdr_ressize_check(rqstp, p);
+}
+
+int
+nfssvc_encode_diropres(struct svc_rqst *rqstp, __be32 *p,
+					struct nfsd_diropres *resp)
+{
+	p = encode_fh(p, &resp->fh);
+	p = encode_fattr(rqstp, p, &resp->fh, &resp->stat);
+	return xdr_ressize_check(rqstp, p);
+}
+
+int
+nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p,
+					struct nfsd_readlinkres *resp)
+{
+	*p++ = htonl(resp->len);
+	xdr_ressize_check(rqstp, p);
+	rqstp->rq_res.page_len = resp->len;
+	if (resp->len & 3) {
+		/* need to pad the tail */
+		rqstp->rq_res.tail[0].iov_base = p;
+		*p = 0;
+		rqstp->rq_res.tail[0].iov_len = 4 - (resp->len&3);
+	}
+	return 1;
+}
+
+int
+nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p,
+					struct nfsd_readres *resp)
+{
+	p = encode_fattr(rqstp, p, &resp->fh, &resp->stat);
+	*p++ = htonl(resp->count);
+	xdr_ressize_check(rqstp, p);
+
+	/* now update rqstp->rq_res to reflect data as well */
+	rqstp->rq_res.page_len = resp->count;
+	if (resp->count & 3) {
+		/* need to pad the tail */
+		rqstp->rq_res.tail[0].iov_base = p;
+		*p = 0;
+		rqstp->rq_res.tail[0].iov_len = 4 - (resp->count&3);
+	}
+	return 1;
+}
+
+int
+nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p,
+					struct nfsd_readdirres *resp)
+{
+	xdr_ressize_check(rqstp, p);
+	p = resp->buffer;
+	*p++ = 0;			/* no more entries */
+	*p++ = htonl((resp->common.err == nfserr_eof));
+	rqstp->rq_res.page_len = (((unsigned long)p-1) & ~PAGE_MASK)+1;
+
+	return 1;
+}
+
+int
+nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p,
+					struct nfsd_statfsres *resp)
+{
+	struct kstatfs	*stat = &resp->stats;
+
+	*p++ = htonl(NFSSVC_MAXBLKSIZE_V2);	/* max transfer size */
+	*p++ = htonl(stat->f_bsize);
+	*p++ = htonl(stat->f_blocks);
+	*p++ = htonl(stat->f_bfree);
+	*p++ = htonl(stat->f_bavail);
+	return xdr_ressize_check(rqstp, p);
+}
+
+int
+nfssvc_encode_entry(void *ccdv, const char *name,
+		    int namlen, loff_t offset, u64 ino, unsigned int d_type)
+{
+	struct readdir_cd *ccd = ccdv;
+	struct nfsd_readdirres *cd = container_of(ccd, struct nfsd_readdirres, common);
+	__be32	*p = cd->buffer;
+	int	buflen, slen;
+
+	/*
+	dprintk("nfsd: entry(%.*s off %ld ino %ld)\n",
+			namlen, name, offset, ino);
+	 */
+
+	if (offset > ~((u32) 0)) {
+		cd->common.err = nfserr_fbig;
+		return -EINVAL;
+	}
+	if (cd->offset)
+		*cd->offset = htonl(offset);
+
+	/* truncate filename */
+	namlen = min(namlen, NFS2_MAXNAMLEN);
+	slen = XDR_QUADLEN(namlen);
+
+	if ((buflen = cd->buflen - slen - 4) < 0) {
+		cd->common.err = nfserr_toosmall;
+		return -EINVAL;
+	}
+	if (ino > ~((u32) 0)) {
+		cd->common.err = nfserr_fbig;
+		return -EINVAL;
+	}
+	*p++ = xdr_one;				/* mark entry present */
+	*p++ = htonl((u32) ino);		/* file id */
+	p    = xdr_encode_array(p, name, namlen);/* name length & name */
+	cd->offset = p;			/* remember pointer */
+	*p++ = htonl(~0U);		/* offset of next entry */
+
+	cd->buflen = buflen;
+	cd->buffer = p;
+	cd->common.err = nfs_ok;
+	return 0;
+}
+
+/*
+ * XDR release functions
+ */
+int
+nfssvc_release_fhandle(struct svc_rqst *rqstp, __be32 *p,
+					struct nfsd_fhandle *resp)
+{
+	fh_put(&resp->fh);
+	return 1;
+}

fs/nfsd/state.h

@@ -0,0 +1,601 @@
+/*
+ *  Copyright (c) 2001 The Regents of the University of Michigan.
+ *  All rights reserved.
+ *
+ *  Kendrick Smith <kmsmith@umich.edu>
+ *  Andy Adamson <andros@umich.edu>
+ *  
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *  
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the University nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+
+#ifndef _NFSD4_STATE_H
+#define _NFSD4_STATE_H
+
+#include <linux/idr.h>
+#include <linux/sunrpc/svc_xprt.h>
+#include "nfsfh.h"
+
+typedef struct {
+	u32             cl_boot;
+	u32             cl_id;
+} clientid_t;
+
+typedef struct {
+	clientid_t	so_clid;
+	u32		so_id;
+} stateid_opaque_t;
+
+typedef struct {
+	u32                     si_generation;
+	stateid_opaque_t        si_opaque;
+} stateid_t;
+
+#define STATEID_FMT	"(%08x/%08x/%08x/%08x)"
+#define STATEID_VAL(s) \
+	(s)->si_opaque.so_clid.cl_boot, \
+	(s)->si_opaque.so_clid.cl_id, \
+	(s)->si_opaque.so_id, \
+	(s)->si_generation
+
+struct nfsd4_callback {
+	struct nfs4_client *cb_clp;
+	struct list_head cb_per_client;
+	u32 cb_minorversion;
+	struct rpc_message cb_msg;
+	struct nfsd4_callback_ops *cb_ops;
+	struct work_struct cb_work;
+	bool cb_done;
+};
+
+struct nfsd4_callback_ops {
+	void (*prepare)(struct nfsd4_callback *);
+	int (*done)(struct nfsd4_callback *, struct rpc_task *);
+	void (*release)(struct nfsd4_callback *);
+};
+
+/*
+ * A core object that represents a "common" stateid. These are generally
+ * embedded within the different (more specific) stateid objects and contain
+ * fields that are of general use to any stateid.
+ */
+struct nfs4_stid {
+	atomic_t sc_count;
+#define NFS4_OPEN_STID 1
+#define NFS4_LOCK_STID 2
+#define NFS4_DELEG_STID 4
+/* For an open stateid kept around *only* to process close replays: */
+#define NFS4_CLOSED_STID 8
+/* For a deleg stateid kept around only to process free_stateid's: */
+#define NFS4_REVOKED_DELEG_STID 16
+#define NFS4_CLOSED_DELEG_STID 32
+	unsigned char sc_type;
+	stateid_t sc_stateid;
+	struct nfs4_client *sc_client;
+	struct nfs4_file *sc_file;
+	void (*sc_free)(struct nfs4_stid *);
+};
+
+/*
+ * Represents a delegation stateid. The nfs4_client holds references to these
+ * and they are put when it is being destroyed or when the delegation is
+ * returned by the client:
+ *
+ * o 1 reference as long as a delegation is still in force (taken when it's
+ *   alloc'd, put when it's returned or revoked)
+ *
+ * o 1 reference as long as a recall rpc is in progress (taken when the lease
+ *   is broken, put when the rpc exits)
+ *
+ * o 1 more ephemeral reference for each nfsd thread currently doing something
+ *   with that delegation without holding the cl_lock
+ *
+ * If the server attempts to recall a delegation and the client doesn't do so
+ * before a timeout, the server may also revoke the delegation. In that case,
+ * the object will either be destroyed (v4.0) or moved to a per-client list of
+ * revoked delegations (v4.1+).
+ *
+ * This object is a superset of the nfs4_stid.
+ */
+struct nfs4_delegation {
+	struct nfs4_stid	dl_stid; /* must be first field */
+	struct list_head	dl_perfile;
+	struct list_head	dl_perclnt;
+	struct list_head	dl_recall_lru;  /* delegation recalled */
+	u32			dl_type;
+	time_t			dl_time;
+/* For recall: */
+	int			dl_retries;
+	struct nfsd4_callback	dl_recall;
+};
+
+#define cb_to_delegation(cb) \
+	container_of(cb, struct nfs4_delegation, dl_recall)
+
+/* client delegation callback info */
+struct nfs4_cb_conn {
+	/* SETCLIENTID info */
+	struct sockaddr_storage	cb_addr;
+	struct sockaddr_storage	cb_saddr;
+	size_t			cb_addrlen;
+	u32                     cb_prog; /* used only in 4.0 case;
+					    per-session otherwise */
+	u32                     cb_ident;	/* minorversion 0 only */
+	struct svc_xprt		*cb_xprt;	/* minorversion 1 only */
+};
+
+static inline struct nfs4_delegation *delegstateid(struct nfs4_stid *s)
+{
+	return container_of(s, struct nfs4_delegation, dl_stid);
+}
+
+/* Maximum number of slots per session. 160 is useful for long haul TCP */
+#define NFSD_MAX_SLOTS_PER_SESSION     160
+/* Maximum number of operations per session compound */
+#define NFSD_MAX_OPS_PER_COMPOUND	16
+/* Maximum  session per slot cache size */
+#define NFSD_SLOT_CACHE_SIZE		2048
+/* Maximum number of NFSD_SLOT_CACHE_SIZE slots per session */
+#define NFSD_CACHE_SIZE_SLOTS_PER_SESSION	32
+#define NFSD_MAX_MEM_PER_SESSION  \
+		(NFSD_CACHE_SIZE_SLOTS_PER_SESSION * NFSD_SLOT_CACHE_SIZE)
+
+struct nfsd4_slot {
+	u32	sl_seqid;
+	__be32	sl_status;
+	u32	sl_datalen;
+	u16	sl_opcnt;
+#define NFSD4_SLOT_INUSE	(1 << 0)
+#define NFSD4_SLOT_CACHETHIS	(1 << 1)
+#define NFSD4_SLOT_INITIALIZED	(1 << 2)
+	u8	sl_flags;
+	char	sl_data[];
+};
+
+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_cb_sec {
+	u32	flavor; /* (u32)(-1) used to mean "no valid flavor" */
+	kuid_t	uid;
+	kgid_t	gid;
+};
+
+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;
+	struct nfsd4_cb_sec		cb_sec;
+};
+
+struct nfsd4_backchannel_ctl {
+	u32	bc_cb_program;
+	struct nfsd4_cb_sec		bc_cb_sec;
+};
+
+struct nfsd4_bind_conn_to_session {
+	struct nfs4_sessionid		sessionid;
+	u32				dir;
+};
+
+/* The single slot clientid cache structure */
+struct nfsd4_clid_slot {
+	u32				sl_seqid;
+	__be32				sl_status;
+	struct nfsd4_create_session	sl_cr_ses;
+};
+
+struct nfsd4_conn {
+	struct list_head cn_persession;
+	struct svc_xprt *cn_xprt;
+	struct svc_xpt_user cn_xpt_user;
+	struct nfsd4_session *cn_session;
+/* CDFC4_FORE, CDFC4_BACK: */
+	unsigned char cn_flags;
+};
+
+/*
+ * Representation of a v4.1+ session. These are refcounted in a similar fashion
+ * to the nfs4_client. References are only taken when the server is actively
+ * working on the object (primarily during the processing of compounds).
+ */
+struct nfsd4_session {
+	atomic_t		se_ref;
+	struct list_head	se_hash;	/* hash by sessionid */
+	struct list_head	se_perclnt;
+/* See SESSION4_PERSIST, etc. for standard flags; this is internal-only: */
+#define NFS4_SESSION_DEAD	0x010
+	u32			se_flags;
+	struct nfs4_client	*se_client;
+	struct nfs4_sessionid	se_sessionid;
+	struct nfsd4_channel_attrs se_fchannel;
+	struct nfsd4_channel_attrs se_bchannel;
+	struct nfsd4_cb_sec	se_cb_sec;
+	struct list_head	se_conns;
+	u32			se_cb_prog;
+	u32			se_cb_seq_nr;
+	struct nfsd4_slot	*se_slots[];	/* forward channel slots */
+};
+
+/* 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' */
+
+/*
+ * struct nfs4_client - one per client.  Clientids live here.
+ *
+ * The initial object created by an NFS client using SETCLIENTID (for NFSv4.0)
+ * or EXCHANGE_ID (for NFSv4.1+). These objects are refcounted and timestamped.
+ * Each nfsd_net_ns object contains a set of these and they are tracked via
+ * short and long form clientid. They are hashed and searched for under the
+ * per-nfsd_net client_lock spinlock.
+ *
+ * References to it are only held during the processing of compounds, and in
+ * certain other operations. In their "resting state" they have a refcount of
+ * 0. If they are not renewed within a lease period, they become eligible for
+ * destruction by the laundromat.
+ *
+ * These objects can also be destroyed prematurely by the fault injection code,
+ * or if the client sends certain forms of SETCLIENTID or EXCHANGE_ID updates.
+ * Care is taken *not* to do this however when the objects have an elevated
+ * refcount.
+ *
+ * o Each nfs4_client is hashed by clientid
+ *
+ * o Each nfs4_clients is also hashed by name (the opaque quantity initially
+ *   sent by the client to identify itself).
+ * 	  
+ * o cl_perclient list is used to ensure no dangling stateowner references
+ *   when we expire the nfs4_client
+ */
+struct nfs4_client {
+	struct list_head	cl_idhash; 	/* hash by cl_clientid.id */
+	struct rb_node		cl_namenode;	/* link into by-name trees */
+	struct list_head	*cl_ownerstr_hashtbl;
+	struct list_head	cl_openowners;
+	struct idr		cl_stateids;	/* stateid lookup */
+	struct list_head	cl_delegations;
+	struct list_head	cl_revoked;	/* unacknowledged, revoked 4.1 state */
+	struct list_head        cl_lru;         /* tail queue */
+	struct xdr_netobj	cl_name; 	/* id generated by client */
+	nfs4_verifier		cl_verifier; 	/* generated by client */
+	time_t                  cl_time;        /* time of last lease renewal */
+	struct sockaddr_storage	cl_addr; 	/* client ipaddress */
+	bool			cl_mach_cred;	/* SP4_MACH_CRED in force */
+	struct svc_cred		cl_cred; 	/* setclientid principal */
+	clientid_t		cl_clientid;	/* generated by server */
+	nfs4_verifier		cl_confirm;	/* generated by server */
+	u32			cl_minorversion;
+
+	/* for v4.0 and v4.1 callbacks: */
+	struct nfs4_cb_conn	cl_cb_conn;
+#define NFSD4_CLIENT_CB_UPDATE		(0)
+#define NFSD4_CLIENT_CB_KILL		(1)
+#define NFSD4_CLIENT_STABLE		(2)	/* client on stable storage */
+#define NFSD4_CLIENT_RECLAIM_COMPLETE	(3)	/* reclaim_complete done */
+#define NFSD4_CLIENT_CONFIRMED		(4)	/* client is confirmed */
+#define NFSD4_CLIENT_UPCALL_LOCK	(5)	/* upcall serialization */
+#define NFSD4_CLIENT_CB_FLAG_MASK	(1 << NFSD4_CLIENT_CB_UPDATE | \
+					 1 << NFSD4_CLIENT_CB_KILL)
+	unsigned long		cl_flags;
+	struct rpc_cred		*cl_cb_cred;
+	struct rpc_clnt		*cl_cb_client;
+	u32			cl_cb_ident;
+#define NFSD4_CB_UP		0
+#define NFSD4_CB_UNKNOWN	1
+#define NFSD4_CB_DOWN		2
+#define NFSD4_CB_FAULT		3
+	int			cl_cb_state;
+	struct nfsd4_callback	cl_cb_null;
+	struct nfsd4_session	*cl_cb_session;
+	struct list_head	cl_callbacks; /* list of in-progress callbacks */
+
+	/* for all client information that callback code might need: */
+	spinlock_t		cl_lock;
+
+	/* for nfs41 */
+	struct list_head	cl_sessions;
+	struct nfsd4_clid_slot	cl_cs_slot;	/* create_session slot */
+	u32			cl_exchange_flags;
+	/* number of rpc's in progress over an associated session: */
+	atomic_t		cl_refcount;
+
+	/* for nfs41 callbacks */
+	/* We currently support a single back channel with a single slot */
+	unsigned long		cl_cb_slot_busy;
+	struct rpc_wait_queue	cl_cb_waitq;	/* backchannel callers may */
+						/* wait here for slots */
+	struct net		*net;
+};
+
+/* struct nfs4_client_reset
+ * one per old client. Populates reset_str_hashtbl. Filled from conf_id_hashtbl
+ * upon lease reset, or from upcall to state_daemon (to read in state
+ * from non-volitile storage) upon reboot.
+ */
+struct nfs4_client_reclaim {
+	struct list_head	cr_strhash;	/* hash by cr_name */
+	struct nfs4_client	*cr_clp;	/* pointer to associated clp */
+	char			cr_recdir[HEXDIR_LEN]; /* recover dir */
+};
+
+static inline void
+update_stateid(stateid_t *stateid)
+{
+	stateid->si_generation++;
+	/* Wraparound recommendation from 3530bis-13 9.1.3.2: */
+	if (stateid->si_generation == 0)
+		stateid->si_generation = 1;
+}
+
+/* A reasonable value for REPLAY_ISIZE was estimated as follows:  
+ * The OPEN response, typically the largest, requires 
+ *   4(status) + 8(stateid) + 20(changeinfo) + 4(rflags) +  8(verifier) + 
+ *   4(deleg. type) + 8(deleg. stateid) + 4(deleg. recall flag) + 
+ *   20(deleg. space limit) + ~32(deleg. ace) = 112 bytes 
+ */
+
+#define NFSD4_REPLAY_ISIZE       112 
+
+/*
+ * Replay buffer, where the result of the last seqid-mutating operation 
+ * is cached. 
+ */
+struct nfs4_replay {
+	__be32			rp_status;
+	unsigned int		rp_buflen;
+	char			*rp_buf;
+	struct knfsd_fh		rp_openfh;
+	struct mutex		rp_mutex;
+	char			rp_ibuf[NFSD4_REPLAY_ISIZE];
+};
+
+struct nfs4_stateowner;
+
+struct nfs4_stateowner_operations {
+	void (*so_unhash)(struct nfs4_stateowner *);
+	void (*so_free)(struct nfs4_stateowner *);
+};
+
+/*
+ * A core object that represents either an open or lock owner. The object and
+ * lock owner objects have one of these embedded within them. Refcounts and
+ * other fields common to both owner types are contained within these
+ * structures.
+ */
+struct nfs4_stateowner {
+	struct list_head			so_strhash;
+	struct list_head			so_stateids;
+	struct nfs4_client			*so_client;
+	const struct nfs4_stateowner_operations	*so_ops;
+	/* after increment in nfsd4_bump_seqid, represents the next
+	 * sequence id expected from the client: */
+	atomic_t				so_count;
+	u32					so_seqid;
+	struct xdr_netobj			so_owner; /* open owner name */
+	struct nfs4_replay			so_replay;
+	bool					so_is_open_owner;
+};
+
+/*
+ * When a file is opened, the client provides an open state owner opaque string
+ * that indicates the "owner" of that open. These objects are refcounted.
+ * References to it are held by each open state associated with it. This object
+ * is a superset of the nfs4_stateowner struct.
+ */
+struct nfs4_openowner {
+	struct nfs4_stateowner	oo_owner; /* must be first field */
+	struct list_head        oo_perclient;
+	/*
+	 * We keep around openowners a little while after last close,
+	 * which saves clients from having to confirm, and allows us to
+	 * handle close replays if they come soon enough.  The close_lru
+	 * is a list of such openowners, to be reaped by the laundromat
+	 * thread eventually if they remain unused:
+	 */
+	struct list_head	oo_close_lru;
+	struct nfs4_ol_stateid *oo_last_closed_stid;
+	time_t			oo_time; /* time of placement on so_close_lru */
+#define NFS4_OO_CONFIRMED   1
+	unsigned char		oo_flags;
+};
+
+/*
+ * Represents a generic "lockowner". Similar to an openowner. References to it
+ * are held by the lock stateids that are created on its behalf. This object is
+ * a superset of the nfs4_stateowner struct (or would be if it needed any extra
+ * fields).
+ */
+struct nfs4_lockowner {
+	struct nfs4_stateowner	lo_owner; /* must be first element */
+};
+
+static inline struct nfs4_openowner * openowner(struct nfs4_stateowner *so)
+{
+	return container_of(so, struct nfs4_openowner, oo_owner);
+}
+
+static inline struct nfs4_lockowner * lockowner(struct nfs4_stateowner *so)
+{
+	return container_of(so, struct nfs4_lockowner, lo_owner);
+}
+
+/*
+ * nfs4_file: a file opened by some number of (open) nfs4_stateowners.
+ *
+ * These objects are global. nfsd only keeps one instance of a nfs4_file per
+ * inode (though it may keep multiple file descriptors open per inode). These
+ * are tracked in the file_hashtbl which is protected by the state_lock
+ * spinlock.
+ */
+struct nfs4_file {
+	atomic_t		fi_ref;
+	spinlock_t		fi_lock;
+	struct hlist_node       fi_hash;    /* hash by "struct inode *" */
+	struct list_head        fi_stateids;
+	struct list_head	fi_delegations;
+	/* One each for O_RDONLY, O_WRONLY, O_RDWR: */
+	struct file *		fi_fds[3];
+	/*
+	 * Each open or lock stateid contributes 0-4 to the counts
+	 * below depending on which bits are set in st_access_bitmap:
+	 *     1 to fi_access[O_RDONLY] if NFS4_SHARE_ACCES_READ is set
+	 *   + 1 to fi_access[O_WRONLY] if NFS4_SHARE_ACCESS_WRITE is set
+	 *   + 1 to both of the above if NFS4_SHARE_ACCESS_BOTH is set.
+	 */
+	atomic_t		fi_access[2];
+	u32			fi_share_deny;
+	struct file		*fi_deleg_file;
+	atomic_t		fi_delegees;
+	struct knfsd_fh		fi_fhandle;
+	bool			fi_had_conflict;
+};
+
+/*
+ * A generic struct representing either a open or lock stateid. The nfs4_client
+ * holds a reference to each of these objects, and they in turn hold a
+ * reference to their respective stateowners. The client's reference is
+ * released in response to a close or unlock (depending on whether it's an open
+ * or lock stateid) or when the client is being destroyed.
+ *
+ * In the case of v4.0 open stateids, these objects are preserved for a little
+ * while after close in order to handle CLOSE replays. Those are eventually
+ * reclaimed via a LRU scheme by the laundromat.
+ *
+ * This object is a superset of the nfs4_stid. "ol" stands for "Open or Lock".
+ * Better suggestions welcome.
+ */
+struct nfs4_ol_stateid {
+	struct nfs4_stid    st_stid; /* must be first field */
+	struct list_head              st_perfile;
+	struct list_head              st_perstateowner;
+	struct list_head              st_locks;
+	struct nfs4_stateowner      * st_stateowner;
+	unsigned char                 st_access_bmap;
+	unsigned char                 st_deny_bmap;
+	struct nfs4_ol_stateid         * st_openstp;
+};
+
+static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s)
+{
+	return container_of(s, struct nfs4_ol_stateid, st_stid);
+}
+
+/* flags for preprocess_seqid_op() */
+#define RD_STATE	        0x00000010
+#define WR_STATE	        0x00000020
+
+enum nfsd4_cb_op {
+	NFSPROC4_CLNT_CB_NULL = 0,
+	NFSPROC4_CLNT_CB_RECALL,
+	NFSPROC4_CLNT_CB_SEQUENCE,
+};
+
+
+struct nfsd4_compound_state;
+struct nfsd_net;
+
+extern __be32 nfs4_preprocess_stateid_op(struct net *net,
+		struct nfsd4_compound_state *cstate,
+		stateid_t *stateid, int flags, struct file **filp);
+void nfs4_put_stid(struct nfs4_stid *s);
+void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *, struct nfsd_net *);
+extern void nfs4_release_reclaim(struct nfsd_net *);
+extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(const char *recdir,
+							struct nfsd_net *nn);
+extern __be32 nfs4_check_open_reclaim(clientid_t *clid,
+		struct nfsd4_compound_state *cstate, struct nfsd_net *nn);
+extern int set_callback_cred(void);
+extern void nfsd4_probe_callback(struct nfs4_client *clp);
+extern void nfsd4_probe_callback_sync(struct nfs4_client *clp);
+extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *);
+extern void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
+		struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op);
+extern void nfsd4_run_cb(struct nfsd4_callback *cb);
+extern int nfsd4_create_callback_queue(void);
+extern void nfsd4_destroy_callback_queue(void);
+extern void nfsd4_shutdown_callback(struct nfs4_client *);
+extern void nfsd4_prepare_cb_recall(struct nfs4_delegation *dp);
+extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(const char *name,
+							struct nfsd_net *nn);
+extern bool nfs4_has_reclaimed_state(const char *name, struct nfsd_net *nn);
+
+/* grace period management */
+void nfsd4_end_grace(struct nfsd_net *nn);
+
+/* nfs4recover operations */
+extern int nfsd4_client_tracking_init(struct net *net);
+extern void nfsd4_client_tracking_exit(struct net *net);
+extern void nfsd4_client_record_create(struct nfs4_client *clp);
+extern void nfsd4_client_record_remove(struct nfs4_client *clp);
+extern int nfsd4_client_record_check(struct nfs4_client *clp);
+extern void nfsd4_record_grace_done(struct nfsd_net *nn);
+
+/* nfs fault injection functions */
+#ifdef CONFIG_NFSD_FAULT_INJECTION
+int nfsd_fault_inject_init(void);
+void nfsd_fault_inject_cleanup(void);
+
+u64 nfsd_inject_print_clients(void);
+u64 nfsd_inject_forget_client(struct sockaddr_storage *, size_t);
+u64 nfsd_inject_forget_clients(u64);
+
+u64 nfsd_inject_print_locks(void);
+u64 nfsd_inject_forget_client_locks(struct sockaddr_storage *, size_t);
+u64 nfsd_inject_forget_locks(u64);
+
+u64 nfsd_inject_print_openowners(void);
+u64 nfsd_inject_forget_client_openowners(struct sockaddr_storage *, size_t);
+u64 nfsd_inject_forget_openowners(u64);
+
+u64 nfsd_inject_print_delegations(void);
+u64 nfsd_inject_forget_client_delegations(struct sockaddr_storage *, size_t);
+u64 nfsd_inject_forget_delegations(u64);
+u64 nfsd_inject_recall_client_delegations(struct sockaddr_storage *, size_t);
+u64 nfsd_inject_recall_delegations(u64);
+#else /* CONFIG_NFSD_FAULT_INJECTION */
+static inline int nfsd_fault_inject_init(void) { return 0; }
+static inline void nfsd_fault_inject_cleanup(void) {}
+#endif /* CONFIG_NFSD_FAULT_INJECTION */
+
+#endif   /* NFSD4_STATE_H */

fs/nfsd/stats.c

@@ -0,0 +1,104 @@
+/*
+ * procfs-based user access to knfsd statistics
+ *
+ * /proc/net/rpc/nfsd
+ *
+ * Format:
+ *	rc <hits> <misses> <nocache>
+ *			Statistsics for the reply cache
+ *	fh <stale> <total-lookups> <anonlookups> <dir-not-in-dcache> <nondir-not-in-dcache>
+ *			statistics for filehandle lookup
+ *	io <bytes-read> <bytes-written>
+ *			statistics for IO throughput
+ *	th <threads> <fullcnt> <10%-20%> <20%-30%> ... <90%-100%> <100%> 
+ *			time (seconds) when nfsd thread usage above thresholds
+ *			and number of times that all threads were in use
+ *	ra cache-size  <10%  <20%  <30% ... <100% not-found
+ *			number of times that read-ahead entry was found that deep in
+ *			the cache.
+ *	plus generic RPC stats (see net/sunrpc/stats.c)
+ *
+ * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de>
+ */
+
+#include <linux/seq_file.h>
+#include <linux/module.h>
+#include <linux/sunrpc/stats.h>
+#include <net/net_namespace.h>
+
+#include "nfsd.h"
+
+struct nfsd_stats	nfsdstats;
+struct svc_stat		nfsd_svcstats = {
+	.program	= &nfsd_program,
+};
+
+static int nfsd_proc_show(struct seq_file *seq, void *v)
+{
+	int i;
+
+	seq_printf(seq, "rc %u %u %u\nfh %u %u %u %u %u\nio %u %u\n",
+		      nfsdstats.rchits,
+		      nfsdstats.rcmisses,
+		      nfsdstats.rcnocache,
+		      nfsdstats.fh_stale,
+		      nfsdstats.fh_lookup,
+		      nfsdstats.fh_anon,
+		      nfsdstats.fh_nocache_dir,
+		      nfsdstats.fh_nocache_nondir,
+		      nfsdstats.io_read,
+		      nfsdstats.io_write);
+	/* thread usage: */
+	seq_printf(seq, "th %u %u", nfsdstats.th_cnt, nfsdstats.th_fullcnt);
+	for (i=0; i<10; i++) {
+		unsigned int jifs = nfsdstats.th_usage[i];
+		unsigned int sec = jifs / HZ, msec = (jifs % HZ)*1000/HZ;
+		seq_printf(seq, " %u.%03u", sec, msec);
+	}
+
+	/* newline and ra-cache */
+	seq_printf(seq, "\nra %u", nfsdstats.ra_size);
+	for (i=0; i<11; i++)
+		seq_printf(seq, " %u", nfsdstats.ra_depth[i]);
+	seq_putc(seq, '\n');
+	
+	/* show my rpc info */
+	svc_seq_show(seq, &nfsd_svcstats);
+
+#ifdef CONFIG_NFSD_V4
+	/* Show count for individual nfsv4 operations */
+	/* Writing operation numbers 0 1 2 also for maintaining uniformity */
+	seq_printf(seq,"proc4ops %u", LAST_NFS4_OP + 1);
+	for (i = 0; i <= LAST_NFS4_OP; i++)
+		seq_printf(seq, " %u", nfsdstats.nfs4_opcount[i]);
+
+	seq_putc(seq, '\n');
+#endif
+
+	return 0;
+}
+
+static int nfsd_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, nfsd_proc_show, NULL);
+}
+
+static const struct file_operations nfsd_proc_fops = {
+	.owner = THIS_MODULE,
+	.open = nfsd_proc_open,
+	.read  = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+void
+nfsd_stat_init(void)
+{
+	svc_proc_register(&init_net, &nfsd_svcstats, &nfsd_proc_fops);
+}
+
+void
+nfsd_stat_shutdown(void)
+{
+	svc_proc_unregister(&init_net, "nfsd");
+}

fs/nfsd/stats.h

@@ -0,0 +1,43 @@
+/*
+ * Statistics for NFS server.
+ *
+ * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
+ */
+#ifndef _NFSD_STATS_H
+#define _NFSD_STATS_H
+
+#include <uapi/linux/nfsd/stats.h>
+
+
+struct nfsd_stats {
+	unsigned int	rchits;		/* repcache hits */
+	unsigned int	rcmisses;	/* repcache hits */
+	unsigned int	rcnocache;	/* uncached reqs */
+	unsigned int	fh_stale;	/* FH stale error */
+	unsigned int	fh_lookup;	/* dentry cached */
+	unsigned int	fh_anon;	/* anon file dentry returned */
+	unsigned int	fh_nocache_dir;	/* filehandle not found in dcache */
+	unsigned int	fh_nocache_nondir;	/* filehandle not found in dcache */
+	unsigned int	io_read;	/* bytes returned to read requests */
+	unsigned int	io_write;	/* bytes passed in write requests */
+	unsigned int	th_cnt;		/* number of available threads */
+	unsigned int	th_usage[10];	/* number of ticks during which n perdeciles
+					 * of available threads were in use */
+	unsigned int	th_fullcnt;	/* number of times last free thread was used */
+	unsigned int	ra_size;	/* size of ra cache */
+	unsigned int	ra_depth[11];	/* number of times ra entry was found that deep
+					 * in the cache (10percentiles). [10] = not found */
+#ifdef CONFIG_NFSD_V4
+	unsigned int	nfs4_opcount[LAST_NFS4_OP + 1];	/* count of individual nfsv4 operations */
+#endif
+
+};
+
+
+extern struct nfsd_stats	nfsdstats;
+extern struct svc_stat		nfsd_svcstats;
+
+void	nfsd_stat_init(void);
+void	nfsd_stat_shutdown(void);
+
+#endif /* _NFSD_STATS_H */

fs/nfsd/vfs.h

@@ -0,0 +1,129 @@
+/*
+ * Copyright (C) 1995-1997 Olaf Kirch <okir@monad.swb.de>
+ */
+
+#ifndef LINUX_NFSD_VFS_H
+#define LINUX_NFSD_VFS_H
+
+#include "nfsfh.h"
+#include "nfsd.h"
+
+/*
+ * Flags for nfsd_permission
+ */
+#define NFSD_MAY_NOP			0
+#define NFSD_MAY_EXEC			0x001 /* == MAY_EXEC */
+#define NFSD_MAY_WRITE			0x002 /* == MAY_WRITE */
+#define NFSD_MAY_READ			0x004 /* == MAY_READ */
+#define NFSD_MAY_SATTR			0x008
+#define NFSD_MAY_TRUNC			0x010
+#define NFSD_MAY_LOCK			0x020
+#define NFSD_MAY_MASK			0x03f
+
+/* extra hints to permission and open routines: */
+#define NFSD_MAY_OWNER_OVERRIDE		0x040
+#define NFSD_MAY_LOCAL_ACCESS		0x080 /* for device special files */
+#define NFSD_MAY_BYPASS_GSS_ON_ROOT	0x100
+#define NFSD_MAY_NOT_BREAK_LEASE	0x200
+#define NFSD_MAY_BYPASS_GSS		0x400
+#define NFSD_MAY_READ_IF_EXEC		0x800
+
+#define NFSD_MAY_64BIT_COOKIE		0x1000 /* 64 bit readdir cookies for >= NFSv3 */
+
+#define NFSD_MAY_CREATE		(NFSD_MAY_EXEC|NFSD_MAY_WRITE)
+#define NFSD_MAY_REMOVE		(NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC)
+
+/*
+ * Callback function for readdir
+ */
+typedef int (*nfsd_dirop_t)(struct inode *, struct dentry *, int, int);
+
+/* nfsd/vfs.c */
+int		nfsd_racache_init(int);
+void		nfsd_racache_shutdown(void);
+int		nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
+		                struct svc_export **expp);
+__be32		nfsd_lookup(struct svc_rqst *, struct svc_fh *,
+				const char *, unsigned int, struct svc_fh *);
+__be32		 nfsd_lookup_dentry(struct svc_rqst *, struct svc_fh *,
+				const char *, unsigned int,
+				struct svc_export **, struct dentry **);
+__be32		nfsd_setattr(struct svc_rqst *, struct svc_fh *,
+				struct iattr *, int, time_t);
+int nfsd_mountpoint(struct dentry *, struct svc_export *);
+#ifdef CONFIG_NFSD_V4
+__be32          nfsd4_set_nfs4_label(struct svc_rqst *, struct svc_fh *,
+		    struct xdr_netobj *);
+#endif /* CONFIG_NFSD_V4 */
+__be32		nfsd_create(struct svc_rqst *, struct svc_fh *,
+				char *name, int len, struct iattr *attrs,
+				int type, dev_t rdev, struct svc_fh *res);
+#ifdef CONFIG_NFSD_V3
+__be32		nfsd_access(struct svc_rqst *, struct svc_fh *, u32 *, u32 *);
+__be32		do_nfsd_create(struct svc_rqst *, struct svc_fh *,
+				char *name, int len, struct iattr *attrs,
+				struct svc_fh *res, int createmode,
+				u32 *verifier, bool *truncp, bool *created);
+__be32		nfsd_commit(struct svc_rqst *, struct svc_fh *,
+				loff_t, unsigned long);
+#endif /* CONFIG_NFSD_V3 */
+__be32		nfsd_open(struct svc_rqst *, struct svc_fh *, umode_t,
+				int, struct file **);
+void		nfsd_close(struct file *);
+struct raparms;
+__be32		nfsd_get_tmp_read_open(struct svc_rqst *, struct svc_fh *,
+				struct file **, struct raparms **);
+void		nfsd_put_tmp_read_open(struct file *, struct raparms *);
+__be32		nfsd_splice_read(struct svc_rqst *,
+				struct file *, loff_t, unsigned long *);
+__be32		nfsd_readv(struct file *, loff_t, struct kvec *, int,
+				unsigned long *);
+__be32 		nfsd_read(struct svc_rqst *, struct svc_fh *,
+				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 *);
+__be32		nfsd_readlink(struct svc_rqst *, struct svc_fh *,
+				char *, int *);
+__be32		nfsd_symlink(struct svc_rqst *, struct svc_fh *,
+				char *name, int len, char *path,
+				struct svc_fh *res);
+__be32		nfsd_link(struct svc_rqst *, struct svc_fh *,
+				char *, int, struct svc_fh *);
+__be32		nfsd_rename(struct svc_rqst *,
+				struct svc_fh *, char *, int,
+				struct svc_fh *, char *, int);
+__be32		nfsd_unlink(struct svc_rqst *, struct svc_fh *, int type,
+				char *name, int len);
+__be32		nfsd_readdir(struct svc_rqst *, struct svc_fh *,
+			     loff_t *, struct readdir_cd *, filldir_t);
+__be32		nfsd_statfs(struct svc_rqst *, struct svc_fh *,
+				struct kstatfs *, int access);
+
+__be32		nfsd_permission(struct svc_rqst *, struct svc_export *,
+				struct dentry *, int);
+
+static inline int fh_want_write(struct svc_fh *fh)
+{
+	int ret = mnt_want_write(fh->fh_export->ex_path.mnt);
+
+	if (!ret)
+		fh->fh_want_write = 1;
+	return ret;
+}
+
+static inline void fh_drop_write(struct svc_fh *fh)
+{
+	if (fh->fh_want_write) {
+		fh->fh_want_write = 0;
+		mnt_drop_write(fh->fh_export->ex_path.mnt);
+	}
+}
+
+static inline __be32 fh_getattr(struct svc_fh *fh, struct kstat *stat)
+{
+	struct path p = {.mnt = fh->fh_export->ex_path.mnt,
+			 .dentry = fh->fh_dentry};
+	return nfserrno(vfs_getattr(&p, stat));
+}
+
+#endif /* LINUX_NFSD_VFS_H */

fs/nfsd/xdr.h

@@ -0,0 +1,173 @@
+/* XDR types for nfsd. This is mainly a typing exercise. */
+
+#ifndef LINUX_NFSD_H
+#define LINUX_NFSD_H
+
+#include <linux/vfs.h>
+#include "nfsd.h"
+#include "nfsfh.h"
+
+struct nfsd_fhandle {
+	struct svc_fh		fh;
+};
+
+struct nfsd_sattrargs {
+	struct svc_fh		fh;
+	struct iattr		attrs;
+};
+
+struct nfsd_diropargs {
+	struct svc_fh		fh;
+	char *			name;
+	unsigned int		len;
+};
+
+struct nfsd_readargs {
+	struct svc_fh		fh;
+	__u32			offset;
+	__u32			count;
+	int			vlen;
+};
+
+struct nfsd_writeargs {
+	svc_fh			fh;
+	__u32			offset;
+	int			len;
+	int			vlen;
+};
+
+struct nfsd_createargs {
+	struct svc_fh		fh;
+	char *			name;
+	unsigned int		len;
+	struct iattr		attrs;
+};
+
+struct nfsd_renameargs {
+	struct svc_fh		ffh;
+	char *			fname;
+	unsigned int		flen;
+	struct svc_fh		tfh;
+	char *			tname;
+	unsigned int		tlen;
+};
+
+struct nfsd_readlinkargs {
+	struct svc_fh		fh;
+	char *			buffer;
+};
+	
+struct nfsd_linkargs {
+	struct svc_fh		ffh;
+	struct svc_fh		tfh;
+	char *			tname;
+	unsigned int		tlen;
+};
+
+struct nfsd_symlinkargs {
+	struct svc_fh		ffh;
+	char *			fname;
+	unsigned int		flen;
+	char *			tname;
+	unsigned int		tlen;
+	struct iattr		attrs;
+};
+
+struct nfsd_readdirargs {
+	struct svc_fh		fh;
+	__u32			cookie;
+	__u32			count;
+	__be32 *		buffer;
+};
+
+struct nfsd_attrstat {
+	struct svc_fh		fh;
+	struct kstat		stat;
+};
+
+struct nfsd_diropres  {
+	struct svc_fh		fh;
+	struct kstat		stat;
+};
+
+struct nfsd_readlinkres {
+	int			len;
+};
+
+struct nfsd_readres {
+	struct svc_fh		fh;
+	unsigned long		count;
+	struct kstat		stat;
+};
+
+struct nfsd_readdirres {
+	int			count;
+
+	struct readdir_cd	common;
+	__be32 *		buffer;
+	int			buflen;
+	__be32 *		offset;
+};
+
+struct nfsd_statfsres {
+	struct kstatfs		stats;
+};
+
+/*
+ * Storage requirements for XDR arguments and results.
+ */
+union nfsd_xdrstore {
+	struct nfsd_sattrargs	sattr;
+	struct nfsd_diropargs	dirop;
+	struct nfsd_readargs	read;
+	struct nfsd_writeargs	write;
+	struct nfsd_createargs	create;
+	struct nfsd_renameargs	rename;
+	struct nfsd_linkargs	link;
+	struct nfsd_symlinkargs	symlink;
+	struct nfsd_readdirargs	readdir;
+};
+
+#define NFS2_SVC_XDRSIZE	sizeof(union nfsd_xdrstore)
+
+
+int nfssvc_decode_void(struct svc_rqst *, __be32 *, void *);
+int nfssvc_decode_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *);
+int nfssvc_decode_sattrargs(struct svc_rqst *, __be32 *,
+				struct nfsd_sattrargs *);
+int nfssvc_decode_diropargs(struct svc_rqst *, __be32 *,
+				struct nfsd_diropargs *);
+int nfssvc_decode_readargs(struct svc_rqst *, __be32 *,
+				struct nfsd_readargs *);
+int nfssvc_decode_writeargs(struct svc_rqst *, __be32 *,
+				struct nfsd_writeargs *);
+int nfssvc_decode_createargs(struct svc_rqst *, __be32 *,
+				struct nfsd_createargs *);
+int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *,
+				struct nfsd_renameargs *);
+int nfssvc_decode_readlinkargs(struct svc_rqst *, __be32 *,
+				struct nfsd_readlinkargs *);
+int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *,
+				struct nfsd_linkargs *);
+int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *,
+				struct nfsd_symlinkargs *);
+int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *,
+				struct nfsd_readdirargs *);
+int nfssvc_encode_void(struct svc_rqst *, __be32 *, void *);
+int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *, struct nfsd_attrstat *);
+int nfssvc_encode_diropres(struct svc_rqst *, __be32 *, struct nfsd_diropres *);
+int nfssvc_encode_readlinkres(struct svc_rqst *, __be32 *, struct nfsd_readlinkres *);
+int nfssvc_encode_readres(struct svc_rqst *, __be32 *, struct nfsd_readres *);
+int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *, struct nfsd_statfsres *);
+int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *, struct nfsd_readdirres *);
+
+int nfssvc_encode_entry(void *, const char *name,
+			int namlen, loff_t offset, u64 ino, unsigned int);
+
+int nfssvc_release_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *);
+
+/* Helper functions for NFSv2 ACL code */
+__be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat);
+__be32 *nfs2svc_decode_fh(__be32 *p, struct svc_fh *fhp);
+
+#endif /* LINUX_NFSD_H */

fs/nfsd/xdr3.h

@@ -0,0 +1,349 @@
+/*
+ * XDR types for NFSv3 in nfsd.
+ *
+ * Copyright (C) 1996-1998, Olaf Kirch <okir@monad.swb.de>
+ */
+
+#ifndef _LINUX_NFSD_XDR3_H
+#define _LINUX_NFSD_XDR3_H
+
+#include "xdr.h"
+
+struct nfsd3_sattrargs {
+	struct svc_fh		fh;
+	struct iattr		attrs;
+	int			check_guard;
+	time_t			guardtime;
+};
+
+struct nfsd3_diropargs {
+	struct svc_fh		fh;
+	char *			name;
+	unsigned int		len;
+};
+
+struct nfsd3_accessargs {
+	struct svc_fh		fh;
+	unsigned int		access;
+};
+
+struct nfsd3_readargs {
+	struct svc_fh		fh;
+	__u64			offset;
+	__u32			count;
+	int			vlen;
+};
+
+struct nfsd3_writeargs {
+	svc_fh			fh;
+	__u64			offset;
+	__u32			count;
+	int			stable;
+	__u32			len;
+	int			vlen;
+};
+
+struct nfsd3_createargs {
+	struct svc_fh		fh;
+	char *			name;
+	unsigned int		len;
+	int			createmode;
+	struct iattr		attrs;
+	__be32 *		verf;
+};
+
+struct nfsd3_mknodargs {
+	struct svc_fh		fh;
+	char *			name;
+	unsigned int		len;
+	__u32			ftype;
+	__u32			major, minor;
+	struct iattr		attrs;
+};
+
+struct nfsd3_renameargs {
+	struct svc_fh		ffh;
+	char *			fname;
+	unsigned int		flen;
+	struct svc_fh		tfh;
+	char *			tname;
+	unsigned int		tlen;
+};
+
+struct nfsd3_readlinkargs {
+	struct svc_fh		fh;
+	char *			buffer;
+};
+
+struct nfsd3_linkargs {
+	struct svc_fh		ffh;
+	struct svc_fh		tfh;
+	char *			tname;
+	unsigned int		tlen;
+};
+
+struct nfsd3_symlinkargs {
+	struct svc_fh		ffh;
+	char *			fname;
+	unsigned int		flen;
+	char *			tname;
+	unsigned int		tlen;
+	struct iattr		attrs;
+};
+
+struct nfsd3_readdirargs {
+	struct svc_fh		fh;
+	__u64			cookie;
+	__u32			dircount;
+	__u32			count;
+	__be32 *		verf;
+	__be32 *		buffer;
+};
+
+struct nfsd3_commitargs {
+	struct svc_fh		fh;
+	__u64			offset;
+	__u32			count;
+};
+
+struct nfsd3_getaclargs {
+	struct svc_fh		fh;
+	int			mask;
+};
+
+struct posix_acl;
+struct nfsd3_setaclargs {
+	struct svc_fh		fh;
+	int			mask;
+	struct posix_acl	*acl_access;
+	struct posix_acl	*acl_default;
+};
+
+struct nfsd3_attrstat {
+	__be32			status;
+	struct svc_fh		fh;
+	struct kstat            stat;
+};
+
+/* LOOKUP, CREATE, MKDIR, SYMLINK, MKNOD */
+struct nfsd3_diropres  {
+	__be32			status;
+	struct svc_fh		dirfh;
+	struct svc_fh		fh;
+};
+
+struct nfsd3_accessres {
+	__be32			status;
+	struct svc_fh		fh;
+	__u32			access;
+	struct kstat		stat;
+};
+
+struct nfsd3_readlinkres {
+	__be32			status;
+	struct svc_fh		fh;
+	__u32			len;
+};
+
+struct nfsd3_readres {
+	__be32			status;
+	struct svc_fh		fh;
+	unsigned long		count;
+	int			eof;
+};
+
+struct nfsd3_writeres {
+	__be32			status;
+	struct svc_fh		fh;
+	unsigned long		count;
+	int			committed;
+};
+
+struct nfsd3_renameres {
+	__be32			status;
+	struct svc_fh		ffh;
+	struct svc_fh		tfh;
+};
+
+struct nfsd3_linkres {
+	__be32			status;
+	struct svc_fh		tfh;
+	struct svc_fh		fh;
+};
+
+struct nfsd3_readdirres {
+	__be32			status;
+	struct svc_fh		fh;
+	/* Just to save kmalloc on every readdirplus entry (svc_fh is a
+	 * little large for the stack): */
+	struct svc_fh		scratch;
+	int			count;
+	__be32			verf[2];
+
+	struct readdir_cd	common;
+	__be32 *		buffer;
+	int			buflen;
+	__be32 *		offset;
+	__be32 *		offset1;
+	struct svc_rqst *	rqstp;
+
+};
+
+struct nfsd3_fsstatres {
+	__be32			status;
+	struct kstatfs		stats;
+	__u32			invarsec;
+};
+
+struct nfsd3_fsinfores {
+	__be32			status;
+	__u32			f_rtmax;
+	__u32			f_rtpref;
+	__u32			f_rtmult;
+	__u32			f_wtmax;
+	__u32			f_wtpref;
+	__u32			f_wtmult;
+	__u32			f_dtpref;
+	__u64			f_maxfilesize;
+	__u32			f_properties;
+};
+
+struct nfsd3_pathconfres {
+	__be32			status;
+	__u32			p_link_max;
+	__u32			p_name_max;
+	__u32			p_no_trunc;
+	__u32			p_chown_restricted;
+	__u32			p_case_insensitive;
+	__u32			p_case_preserving;
+};
+
+struct nfsd3_commitres {
+	__be32			status;
+	struct svc_fh		fh;
+};
+
+struct nfsd3_getaclres {
+	__be32			status;
+	struct svc_fh		fh;
+	int			mask;
+	struct posix_acl	*acl_access;
+	struct posix_acl	*acl_default;
+	struct kstat		stat;
+};
+
+/* dummy type for release */
+struct nfsd3_fhandle_pair {
+	__u32			dummy;
+	struct svc_fh		fh1;
+	struct svc_fh		fh2;
+};
+
+/*
+ * Storage requirements for XDR arguments and results.
+ */
+union nfsd3_xdrstore {
+	struct nfsd3_sattrargs		sattrargs;
+	struct nfsd3_diropargs		diropargs;
+	struct nfsd3_readargs		readargs;
+	struct nfsd3_writeargs		writeargs;
+	struct nfsd3_createargs		createargs;
+	struct nfsd3_renameargs		renameargs;
+	struct nfsd3_linkargs		linkargs;
+	struct nfsd3_symlinkargs	symlinkargs;
+	struct nfsd3_readdirargs	readdirargs;
+	struct nfsd3_diropres 		diropres;
+	struct nfsd3_accessres		accessres;
+	struct nfsd3_readlinkres	readlinkres;
+	struct nfsd3_readres		readres;
+	struct nfsd3_writeres		writeres;
+	struct nfsd3_renameres		renameres;
+	struct nfsd3_linkres		linkres;
+	struct nfsd3_readdirres		readdirres;
+	struct nfsd3_fsstatres		fsstatres;
+	struct nfsd3_fsinfores		fsinfores;
+	struct nfsd3_pathconfres	pathconfres;
+	struct nfsd3_commitres		commitres;
+	struct nfsd3_getaclres		getaclres;
+};
+
+#define NFS3_SVC_XDRSIZE		sizeof(union nfsd3_xdrstore)
+
+int nfs3svc_decode_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *);
+int nfs3svc_decode_sattrargs(struct svc_rqst *, __be32 *,
+				struct nfsd3_sattrargs *);
+int nfs3svc_decode_diropargs(struct svc_rqst *, __be32 *,
+				struct nfsd3_diropargs *);
+int nfs3svc_decode_accessargs(struct svc_rqst *, __be32 *,
+				struct nfsd3_accessargs *);
+int nfs3svc_decode_readargs(struct svc_rqst *, __be32 *,
+				struct nfsd3_readargs *);
+int nfs3svc_decode_writeargs(struct svc_rqst *, __be32 *,
+				struct nfsd3_writeargs *);
+int nfs3svc_decode_createargs(struct svc_rqst *, __be32 *,
+				struct nfsd3_createargs *);
+int nfs3svc_decode_mkdirargs(struct svc_rqst *, __be32 *,
+				struct nfsd3_createargs *);
+int nfs3svc_decode_mknodargs(struct svc_rqst *, __be32 *,
+				struct nfsd3_mknodargs *);
+int nfs3svc_decode_renameargs(struct svc_rqst *, __be32 *,
+				struct nfsd3_renameargs *);
+int nfs3svc_decode_readlinkargs(struct svc_rqst *, __be32 *,
+				struct nfsd3_readlinkargs *);
+int nfs3svc_decode_linkargs(struct svc_rqst *, __be32 *,
+				struct nfsd3_linkargs *);
+int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *,
+				struct nfsd3_symlinkargs *);
+int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *,
+				struct nfsd3_readdirargs *);
+int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *,
+				struct nfsd3_readdirargs *);
+int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *,
+				struct nfsd3_commitargs *);
+int nfs3svc_encode_voidres(struct svc_rqst *, __be32 *, void *);
+int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *,
+				struct nfsd3_attrstat *);
+int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *,
+				struct nfsd3_attrstat *);
+int nfs3svc_encode_diropres(struct svc_rqst *, __be32 *,
+				struct nfsd3_diropres *);
+int nfs3svc_encode_accessres(struct svc_rqst *, __be32 *,
+				struct nfsd3_accessres *);
+int nfs3svc_encode_readlinkres(struct svc_rqst *, __be32 *,
+				struct nfsd3_readlinkres *);
+int nfs3svc_encode_readres(struct svc_rqst *, __be32 *, struct nfsd3_readres *);
+int nfs3svc_encode_writeres(struct svc_rqst *, __be32 *, struct nfsd3_writeres *);
+int nfs3svc_encode_createres(struct svc_rqst *, __be32 *,
+				struct nfsd3_diropres *);
+int nfs3svc_encode_renameres(struct svc_rqst *, __be32 *,
+				struct nfsd3_renameres *);
+int nfs3svc_encode_linkres(struct svc_rqst *, __be32 *,
+				struct nfsd3_linkres *);
+int nfs3svc_encode_readdirres(struct svc_rqst *, __be32 *,
+				struct nfsd3_readdirres *);
+int nfs3svc_encode_fsstatres(struct svc_rqst *, __be32 *,
+				struct nfsd3_fsstatres *);
+int nfs3svc_encode_fsinfores(struct svc_rqst *, __be32 *,
+				struct nfsd3_fsinfores *);
+int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *,
+				struct nfsd3_pathconfres *);
+int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *,
+				struct nfsd3_commitres *);
+
+int nfs3svc_release_fhandle(struct svc_rqst *, __be32 *,
+				struct nfsd3_attrstat *);
+int nfs3svc_release_fhandle2(struct svc_rqst *, __be32 *,
+				struct nfsd3_fhandle_pair *);
+int nfs3svc_encode_entry(void *, const char *name,
+				int namlen, loff_t offset, u64 ino,
+				unsigned int);
+int nfs3svc_encode_entry_plus(void *, const char *name,
+				int namlen, loff_t offset, u64 ino,
+				unsigned int);
+/* Helper functions for NFSv3 ACL code */
+__be32 *nfs3svc_encode_post_op_attr(struct svc_rqst *rqstp, __be32 *p,
+				struct svc_fh *fhp);
+__be32 *nfs3svc_decode_fh(__be32 *p, struct svc_fh *fhp);
+
+
+#endif /* _LINUX_NFSD_XDR3_H */

fs/nfsd/xdr4.h

@@ -0,0 +1,656 @@
+/*
+ *  Server-side types for NFSv4.
+ *
+ *  Copyright (c) 2002 The Regents of the University of Michigan.
+ *  All rights reserved.
+ *
+ *  Kendrick Smith <kmsmith@umich.edu>
+ *  Andy Adamson   <andros@umich.edu>
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the University nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+
+#ifndef _LINUX_NFSD_XDR4_H
+#define _LINUX_NFSD_XDR4_H
+
+#include "state.h"
+#include "nfsd.h"
+
+#define NFSD4_MAX_SEC_LABEL_LEN	2048
+#define NFSD4_MAX_TAGLEN	128
+#define XDR_LEN(n)                     (((n) + 3) & ~3)
+
+#define CURRENT_STATE_ID_FLAG (1<<0)
+#define SAVED_STATE_ID_FLAG (1<<1)
+
+#define SET_STATE_ID(c, f) ((c)->sid_flags |= (f))
+#define HAS_STATE_ID(c, f) ((c)->sid_flags & (f))
+#define CLEAR_STATE_ID(c, f) ((c)->sid_flags &= ~(f))
+
+struct nfsd4_compound_state {
+	struct svc_fh		current_fh;
+	struct svc_fh		save_fh;
+	struct nfs4_stateowner	*replay_owner;
+	struct nfs4_client	*clp;
+	/* For sessions DRC */
+	struct nfsd4_session	*session;
+	struct nfsd4_slot	*slot;
+	int			data_offset;
+	size_t			iovlen;
+	u32			minorversion;
+	__be32			status;
+	stateid_t	current_stateid;
+	stateid_t	save_stateid;
+	/* to indicate current and saved state id presents */
+	u32		sid_flags;
+};
+
+static inline bool nfsd4_has_session(struct nfsd4_compound_state *cs)
+{
+	return cs->slot != NULL;
+}
+
+struct nfsd4_change_info {
+	u32		atomic;
+	bool		change_supported;
+	u32		before_ctime_sec;
+	u32		before_ctime_nsec;
+	u64		before_change;
+	u32		after_ctime_sec;
+	u32		after_ctime_nsec;
+	u64		after_change;
+};
+
+struct nfsd4_access {
+	u32		ac_req_access;      /* request */
+	u32		ac_supported;       /* response */
+	u32		ac_resp_access;     /* response */
+};
+
+struct nfsd4_close {
+	u32		cl_seqid;           /* request */
+	stateid_t	cl_stateid;         /* request+response */
+};
+
+struct nfsd4_commit {
+	u64		co_offset;          /* request */
+	u32		co_count;           /* request */
+	nfs4_verifier	co_verf;            /* response */
+};
+
+struct nfsd4_create {
+	u32		cr_namelen;         /* request */
+	char *		cr_name;            /* request */
+	u32		cr_type;            /* request */
+	union {                             /* request */
+		struct {
+			u32 datalen;
+			char *data;
+		} link;   /* NF4LNK */
+		struct {
+			u32 specdata1;
+			u32 specdata2;
+		} dev;    /* NF4BLK, NF4CHR */
+	} u;
+	u32		cr_bmval[3];        /* request */
+	struct iattr	cr_iattr;           /* request */
+	struct nfsd4_change_info  cr_cinfo; /* response */
+	struct nfs4_acl *cr_acl;
+	struct xdr_netobj cr_label;
+};
+#define cr_datalen	u.link.datalen
+#define cr_data		u.link.data
+#define cr_specdata1	u.dev.specdata1
+#define cr_specdata2	u.dev.specdata2
+
+struct nfsd4_delegreturn {
+	stateid_t	dr_stateid;
+};
+
+struct nfsd4_getattr {
+	u32		ga_bmval[3];        /* request */
+	struct svc_fh	*ga_fhp;            /* response */
+};
+
+struct nfsd4_link {
+	u32		li_namelen;         /* request */
+	char *		li_name;            /* request */
+	struct nfsd4_change_info  li_cinfo; /* response */
+};
+
+struct nfsd4_lock_denied {
+	clientid_t	ld_clientid;
+	struct xdr_netobj	ld_owner;
+	u64             ld_start;
+	u64             ld_length;
+	u32             ld_type;
+};
+
+struct nfsd4_lock {
+	/* request */
+	u32             lk_type;
+	u32             lk_reclaim;         /* boolean */
+	u64             lk_offset;
+	u64             lk_length;
+	u32             lk_is_new;
+	union {
+		struct {
+			u32             open_seqid;
+			stateid_t       open_stateid;
+			u32             lock_seqid;
+			clientid_t      clientid;
+			struct xdr_netobj owner;
+		} new;
+		struct {
+			stateid_t       lock_stateid;
+			u32             lock_seqid;
+		} old;
+	} v;
+
+	/* response */
+	union {
+		struct {
+			stateid_t               stateid;
+		} ok;
+		struct nfsd4_lock_denied        denied;
+	} u;
+};
+#define lk_new_open_seqid       v.new.open_seqid
+#define lk_new_open_stateid     v.new.open_stateid
+#define lk_new_lock_seqid       v.new.lock_seqid
+#define lk_new_clientid         v.new.clientid
+#define lk_new_owner            v.new.owner
+#define lk_old_lock_stateid     v.old.lock_stateid
+#define lk_old_lock_seqid       v.old.lock_seqid
+
+#define lk_resp_stateid u.ok.stateid
+#define lk_denied       u.denied
+
+
+struct nfsd4_lockt {
+	u32				lt_type;
+	clientid_t			lt_clientid;
+	struct xdr_netobj		lt_owner;
+	u64				lt_offset;
+	u64				lt_length;
+	struct nfsd4_lock_denied  	lt_denied;
+};
+
+ 
+struct nfsd4_locku {
+	u32             lu_type;
+	u32             lu_seqid;
+	stateid_t       lu_stateid;
+	u64             lu_offset;
+	u64             lu_length;
+};
+
+
+struct nfsd4_lookup {
+	u32		lo_len;             /* request */
+	char *		lo_name;            /* request */
+};
+
+struct nfsd4_putfh {
+	u32		pf_fhlen;           /* request */
+	char		*pf_fhval;          /* request */
+};
+
+struct nfsd4_open {
+	u32		op_claim_type;      /* request */
+	struct xdr_netobj op_fname;	    /* request - everything but CLAIM_PREV */
+	u32		op_delegate_type;   /* request - CLAIM_PREV only */
+	stateid_t       op_delegate_stateid; /* request - response */
+	u32		op_why_no_deleg;    /* response - DELEG_NONE_EXT only */
+	u32		op_create;     	    /* request */
+	u32		op_createmode;      /* request */
+	u32		op_bmval[3];        /* request */
+	struct iattr	op_iattr;           /* UNCHECKED4, GUARDED4, EXCLUSIVE4_1 */
+	nfs4_verifier	op_verf __attribute__((aligned(32)));
+					    /* EXCLUSIVE4 */
+	clientid_t	op_clientid;        /* request */
+	struct xdr_netobj op_owner;           /* request */
+	u32		op_seqid;           /* request */
+	u32		op_share_access;    /* request */
+	u32		op_share_deny;      /* request */
+	u32		op_deleg_want;      /* request */
+	stateid_t	op_stateid;         /* response */
+	__be32		op_xdr_error;       /* see nfsd4_open_omfg() */
+	u32		op_recall;          /* recall */
+	struct nfsd4_change_info  op_cinfo; /* response */
+	u32		op_rflags;          /* response */
+	bool		op_truncate;        /* used during processing */
+	bool		op_created;         /* used during processing */
+	struct nfs4_openowner *op_openowner; /* used during processing */
+	struct nfs4_file *op_file;          /* used during processing */
+	struct nfs4_ol_stateid *op_stp;	    /* used during processing */
+	struct nfs4_acl *op_acl;
+	struct xdr_netobj op_label;
+};
+
+struct nfsd4_open_confirm {
+	stateid_t	oc_req_stateid		/* request */;
+	u32		oc_seqid    		/* request */;
+	stateid_t	oc_resp_stateid		/* response */;
+};
+
+struct nfsd4_open_downgrade {
+	stateid_t       od_stateid;
+	u32             od_seqid;
+	u32             od_share_access;	/* request */
+	u32		od_deleg_want;		/* request */
+	u32             od_share_deny;		/* request */
+};
+
+
+struct nfsd4_read {
+	stateid_t	rd_stateid;         /* request */
+	u64		rd_offset;          /* request */
+	u32		rd_length;          /* request */
+	int		rd_vlen;
+	struct file     *rd_filp;
+	
+	struct svc_rqst *rd_rqstp;          /* response */
+	struct svc_fh * rd_fhp;             /* response */
+};
+
+struct nfsd4_readdir {
+	u64		rd_cookie;          /* request */
+	nfs4_verifier	rd_verf;            /* request */
+	u32		rd_dircount;        /* request */
+	u32		rd_maxcount;        /* request */
+	u32		rd_bmval[3];        /* request */
+	struct svc_rqst *rd_rqstp;          /* response */
+	struct svc_fh * rd_fhp;             /* response */
+
+	struct readdir_cd	common;
+	struct xdr_stream	*xdr;
+	int			cookie_offset;
+};
+
+struct nfsd4_release_lockowner {
+	clientid_t        rl_clientid;
+	struct xdr_netobj rl_owner;
+};
+struct nfsd4_readlink {
+	struct svc_rqst *rl_rqstp;          /* request */
+	struct svc_fh *	rl_fhp;             /* request */
+};
+
+struct nfsd4_remove {
+	u32		rm_namelen;         /* request */
+	char *		rm_name;            /* request */
+	struct nfsd4_change_info  rm_cinfo; /* response */
+};
+
+struct nfsd4_rename {
+	u32		rn_snamelen;        /* request */
+	char *		rn_sname;           /* request */
+	u32		rn_tnamelen;        /* request */
+	char *		rn_tname;           /* request */
+	struct nfsd4_change_info  rn_sinfo; /* response */
+	struct nfsd4_change_info  rn_tinfo; /* response */
+};
+
+struct nfsd4_secinfo {
+	u32 si_namelen;					/* request */
+	char *si_name;					/* request */
+	struct svc_export *si_exp;			/* response */
+};
+
+struct nfsd4_secinfo_no_name {
+	u32 sin_style;					/* request */
+	struct svc_export *sin_exp;			/* response */
+};
+
+struct nfsd4_setattr {
+	stateid_t	sa_stateid;         /* request */
+	u32		sa_bmval[3];        /* request */
+	struct iattr	sa_iattr;           /* request */
+	struct nfs4_acl *sa_acl;
+	struct xdr_netobj sa_label;
+};
+
+struct nfsd4_setclientid {
+	nfs4_verifier	se_verf;            /* request */
+	struct xdr_netobj se_name;
+	u32		se_callback_prog;   /* request */
+	u32		se_callback_netid_len;  /* request */
+	char *		se_callback_netid_val;  /* request */
+	u32		se_callback_addr_len;   /* request */
+	char *		se_callback_addr_val;   /* request */
+	u32		se_callback_ident;  /* request */
+	clientid_t	se_clientid;        /* response */
+	nfs4_verifier	se_confirm;         /* response */
+};
+
+struct nfsd4_setclientid_confirm {
+	clientid_t	sc_clientid;
+	nfs4_verifier	sc_confirm;
+};
+
+struct nfsd4_saved_compoundargs {
+	__be32 *p;
+	__be32 *end;
+	int pagelen;
+	struct page **pagelist;
+};
+
+struct nfsd4_test_stateid_id {
+	__be32			ts_id_status;
+	stateid_t		ts_id_stateid;
+	struct list_head	ts_id_list;
+};
+
+struct nfsd4_test_stateid {
+	u32		ts_num_ids;
+	struct list_head ts_stateid_list;
+};
+
+struct nfsd4_free_stateid {
+	stateid_t	fr_stateid;         /* request */
+};
+
+/* also used for NVERIFY */
+struct nfsd4_verify {
+	u32		ve_bmval[3];        /* request */
+	u32		ve_attrlen;         /* request */
+	char *		ve_attrval;         /* request */
+};
+
+struct nfsd4_write {
+	stateid_t	wr_stateid;         /* request */
+	u64		wr_offset;          /* request */
+	u32		wr_stable_how;      /* request */
+	u32		wr_buflen;          /* request */
+	struct kvec	wr_head;
+	struct page **	wr_pagelist;        /* request */
+
+	u32		wr_bytes_written;   /* response */
+	u32		wr_how_written;     /* response */
+	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_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 */
+#endif /* not yet */
+	u32			status_flags;		/* response */
+};
+
+struct nfsd4_destroy_session {
+	struct nfs4_sessionid	sessionid;
+};
+
+struct nfsd4_destroy_clientid {
+	clientid_t clientid;
+};
+
+struct nfsd4_reclaim_complete {
+	u32 rca_one_fs;
+};
+
+struct nfsd4_seek {
+	/* request */
+	stateid_t	seek_stateid;
+	loff_t		seek_offset;
+	u32		seek_whence;
+
+	/* response */
+	u32		seek_eof;
+	loff_t		seek_pos;
+};
+
+struct nfsd4_op {
+	int					opnum;
+	__be32					status;
+	union {
+		struct nfsd4_access		access;
+		struct nfsd4_close		close;
+		struct nfsd4_commit		commit;
+		struct nfsd4_create		create;
+		struct nfsd4_delegreturn	delegreturn;
+		struct nfsd4_getattr		getattr;
+		struct svc_fh *			getfh;
+		struct nfsd4_link		link;
+		struct nfsd4_lock		lock;
+		struct nfsd4_lockt		lockt;
+		struct nfsd4_locku		locku;
+		struct nfsd4_lookup		lookup;
+		struct nfsd4_verify		nverify;
+		struct nfsd4_open		open;
+		struct nfsd4_open_confirm	open_confirm;
+		struct nfsd4_open_downgrade	open_downgrade;
+		struct nfsd4_putfh		putfh;
+		struct nfsd4_read		read;
+		struct nfsd4_readdir		readdir;
+		struct nfsd4_readlink		readlink;
+		struct nfsd4_remove		remove;
+		struct nfsd4_rename		rename;
+		clientid_t			renew;
+		struct nfsd4_secinfo		secinfo;
+		struct nfsd4_setattr		setattr;
+		struct nfsd4_setclientid	setclientid;
+		struct nfsd4_setclientid_confirm setclientid_confirm;
+		struct nfsd4_verify		verify;
+		struct nfsd4_write		write;
+		struct nfsd4_release_lockowner	release_lockowner;
+
+		/* NFSv4.1 */
+		struct nfsd4_exchange_id	exchange_id;
+		struct nfsd4_backchannel_ctl	backchannel_ctl;
+		struct nfsd4_bind_conn_to_session bind_conn_to_session;
+		struct nfsd4_create_session	create_session;
+		struct nfsd4_destroy_session	destroy_session;
+		struct nfsd4_sequence		sequence;
+		struct nfsd4_reclaim_complete	reclaim_complete;
+		struct nfsd4_test_stateid	test_stateid;
+		struct nfsd4_free_stateid	free_stateid;
+
+		/* NFSv4.2 */
+		struct nfsd4_seek		seek;
+	} u;
+	struct nfs4_replay *			replay;
+};
+
+bool nfsd4_cache_this_op(struct nfsd4_op *);
+
+/*
+ * Memory needed just for the duration of processing one compound:
+ */
+struct svcxdr_tmpbuf {
+	struct svcxdr_tmpbuf *next;
+	char buf[];
+};
+
+struct nfsd4_compoundargs {
+	/* scratch variables for XDR decode */
+	__be32 *			p;
+	__be32 *			end;
+	struct page **			pagelist;
+	int				pagelen;
+	__be32				tmp[8];
+	__be32 *			tmpp;
+	struct svcxdr_tmpbuf		*to_free;
+
+	struct svc_rqst			*rqstp;
+
+	u32				taglen;
+	char *				tag;
+	u32				minorversion;
+	u32				opcnt;
+	struct nfsd4_op			*ops;
+	struct nfsd4_op			iops[8];
+	int				cachetype;
+};
+
+struct nfsd4_compoundres {
+	/* scratch variables for XDR encode */
+	struct xdr_stream		xdr;
+	struct svc_rqst *		rqstp;
+
+	u32				taglen;
+	char *				tag;
+	u32				opcnt;
+	__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 resp->opcnt == 1 && args->ops[0].opnum == OP_SEQUENCE;
+}
+
+static inline bool nfsd4_not_cached(struct nfsd4_compoundres *resp)
+{
+	return !(resp->cstate.slot->sl_flags & NFSD4_SLOT_CACHETHIS)
+		|| nfsd4_is_solo_sequence(resp);
+}
+
+static inline bool nfsd4_last_compound_op(struct svc_rqst *rqstp)
+{
+	struct nfsd4_compoundres *resp = rqstp->rq_resp;
+	struct nfsd4_compoundargs *argp = rqstp->rq_argp;
+
+	return argp->opcnt == resp->opcnt;
+}
+
+int nfsd4_max_reply(struct svc_rqst *rqstp, struct nfsd4_op *op);
+void warn_on_nonidempotent_op(struct nfsd4_op *op);
+
+#define NFS4_SVC_XDRSIZE		sizeof(struct nfsd4_compoundargs)
+
+static inline void
+set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp)
+{
+	BUG_ON(!fhp->fh_pre_saved);
+	cinfo->atomic = fhp->fh_post_saved;
+	cinfo->change_supported = IS_I_VERSION(fhp->fh_dentry->d_inode);
+
+	cinfo->before_change = fhp->fh_pre_change;
+	cinfo->after_change = fhp->fh_post_change;
+	cinfo->before_ctime_sec = fhp->fh_pre_ctime.tv_sec;
+	cinfo->before_ctime_nsec = fhp->fh_pre_ctime.tv_nsec;
+	cinfo->after_ctime_sec = fhp->fh_post_attr.ctime.tv_sec;
+	cinfo->after_ctime_nsec = fhp->fh_post_attr.ctime.tv_nsec;
+
+}
+
+int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *, void *);
+int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *,
+		struct nfsd4_compoundargs *);
+int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *,
+		struct nfsd4_compoundres *);
+__be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32);
+void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *);
+void nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op);
+__be32 nfsd4_encode_fattr_to_buf(__be32 **p, int words,
+		struct svc_fh *fhp, struct svc_export *exp,
+		struct dentry *dentry,
+		u32 *bmval, struct svc_rqst *, int ignore_crossmnt);
+extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *,
+		struct nfsd4_setclientid *setclid);
+extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *,
+		struct nfsd4_setclientid_confirm *setclientid_confirm);
+extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *, struct nfsd4_exchange_id *);
+extern __be32 nfsd4_backchannel_ctl(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_backchannel_ctl *);
+extern __be32 nfsd4_bind_conn_to_session(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_bind_conn_to_session *);
+extern __be32 nfsd4_create_session(struct svc_rqst *,
+		struct nfsd4_compound_state *,
+		struct nfsd4_create_session *);
+extern __be32 nfsd4_sequence(struct svc_rqst *,
+		struct nfsd4_compound_state *,
+		struct nfsd4_sequence *);
+extern void nfsd4_sequence_done(struct nfsd4_compoundres *resp);
+extern __be32 nfsd4_destroy_session(struct svc_rqst *,
+		struct nfsd4_compound_state *,
+		struct nfsd4_destroy_session *);
+extern __be32 nfsd4_destroy_clientid(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_destroy_clientid *);
+__be32 nfsd4_reclaim_complete(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_reclaim_complete *);
+extern __be32 nfsd4_process_open1(struct nfsd4_compound_state *,
+		struct nfsd4_open *open, struct nfsd_net *nn);
+extern __be32 nfsd4_process_open2(struct svc_rqst *rqstp,
+		struct svc_fh *current_fh, struct nfsd4_open *open);
+extern void nfsd4_cstate_clear_replay(struct nfsd4_compound_state *cstate);
+extern void nfsd4_cleanup_open_state(struct nfsd4_compound_state *cstate,
+		struct nfsd4_open *open, __be32 status);
+extern __be32 nfsd4_open_confirm(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *, struct nfsd4_open_confirm *oc);
+extern __be32 nfsd4_close(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *,
+		struct nfsd4_close *close);
+extern __be32 nfsd4_open_downgrade(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *,
+		struct nfsd4_open_downgrade *od);
+extern __be32 nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *,
+		struct nfsd4_lock *lock);
+extern __be32 nfsd4_lockt(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *,
+		struct nfsd4_lockt *lockt);
+extern __be32 nfsd4_locku(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *,
+		struct nfsd4_locku *locku);
+extern __be32
+nfsd4_release_lockowner(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *,
+		struct nfsd4_release_lockowner *rlockowner);
+extern int nfsd4_release_compoundargs(void *rq, __be32 *p, void *resp);
+extern __be32 nfsd4_delegreturn(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *, struct nfsd4_delegreturn *dr);
+extern __be32 nfsd4_renew(struct svc_rqst *rqstp,
+			  struct nfsd4_compound_state *, clientid_t *clid);
+extern __be32 nfsd4_test_stateid(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *, struct nfsd4_test_stateid *test_stateid);
+extern __be32 nfsd4_free_stateid(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *, struct nfsd4_free_stateid *free_stateid);
+extern void nfsd4_bump_seqid(struct nfsd4_compound_state *, __be32 nfserr);
+
+#endif
+
+/*
+ * Local variables:
+ *  c-basic-offset: 8
+ * End:
+ */

fs/nfsd/xdr4cb.h

@@ -0,0 +1,23 @@
+#define NFS4_MAXTAGLEN		20
+
+#define NFS4_enc_cb_null_sz		0
+#define NFS4_dec_cb_null_sz		0
+#define cb_compound_enc_hdr_sz		4
+#define cb_compound_dec_hdr_sz		(3 + (NFS4_MAXTAGLEN >> 2))
+#define sessionid_sz			(NFS4_MAX_SESSIONID_LEN >> 2)
+#define cb_sequence_enc_sz		(sessionid_sz + 4 +             \
+					1 /* no referring calls list yet */)
+#define cb_sequence_dec_sz		(op_dec_sz + sessionid_sz + 4)
+
+#define op_enc_sz			1
+#define op_dec_sz			2
+#define enc_nfs4_fh_sz			(1 + (NFS4_FHSIZE >> 2))
+#define enc_stateid_sz			(NFS4_STATEID_SIZE >> 2)
+#define NFS4_enc_cb_recall_sz		(cb_compound_enc_hdr_sz +       \
+					cb_sequence_enc_sz +            \
+					1 + enc_stateid_sz +            \
+					enc_nfs4_fh_sz)
+
+#define NFS4_dec_cb_recall_sz		(cb_compound_dec_hdr_sz  +      \
+					cb_sequence_dec_sz +            \
+					op_dec_sz)