fs/nfsd/nfs4state.c

/*
*  Copyright (c) 2001 The Regents of the University of Michigan.
*  All rights reserved.
*
*  Kendrick Smith <kmsmith@umich.edu>
*  Andy Adamson <kandros@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/file.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/namei.h>
#include <linux/swap.h>
#include <linux/pagemap.h>
#include <linux/ratelimit.h>
#include <linux/sunrpc/svcauth_gss.h>
#include <linux/sunrpc/addr.h>
#include <linux/jhash.h>
#include <linux/string_helpers.h>
#include <linux/fsnotify.h>
#include <linux/nfs_ssc.h>
#include "xdr4.h"
#include "xdr4cb.h"
#include "vfs.h"
#include "current_stateid.h"

#include "netns.h"
#include "pnfs.h"
#include "filecache.h"
#include "trace.h"

#define NFSDDBG_FACILITY                NFSDDBG_PROC

#define all_ones {{~0,~0},~0}
static const stateid_t one_stateid = {
	.si_generation = ~0,
	.si_opaque = all_ones,
};
static const stateid_t zero_stateid = {
	/* all fields zero */
};
static const stateid_t currentstateid = {
	.si_generation = 1,
};
static const stateid_t close_stateid = {
	.si_generation = 0xffffffffU,
};

static u64 current_sessionid = 1;

#define ZERO_STATEID(stateid) (!memcmp((stateid), &zero_stateid, sizeof(stateid_t)))
#define ONE_STATEID(stateid)  (!memcmp((stateid), &one_stateid, sizeof(stateid_t)))
#define CURRENT_STATEID(stateid) (!memcmp((stateid), &currentstateid, sizeof(stateid_t)))
#define CLOSE_STATEID(stateid)  (!memcmp((stateid), &close_stateid, sizeof(stateid_t)))

/* forward declarations */
static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner);
static void nfs4_free_ol_stateid(struct nfs4_stid *stid);
void nfsd4_end_grace(struct nfsd_net *nn);
static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps);

/* Locking: */

/*
 * Currently used for the del_recall_lru and file hash table.  In an
 * effort to decrease the scope of the client_mutex, this spinlock may
 * eventually cover more:
 */
static DEFINE_SPINLOCK(state_lock);

enum nfsd4_st_mutex_lock_subclass {
	OPEN_STATEID_MUTEX = 0,
	LOCK_STATEID_MUTEX = 1,
};

/*
 * A waitqueue for all in-progress 4.0 CLOSE operations that are waiting for
 * the refcount on the open stateid to drop.
 */
static DECLARE_WAIT_QUEUE_HEAD(close_wq);

/*
 * A waitqueue where a writer to clients/#/ctl destroying a client can
 * wait for cl_rpc_users to drop to 0 and then for the client to be
 * unhashed.
 */
static DECLARE_WAIT_QUEUE_HEAD(expiry_wq);

static struct kmem_cache *client_slab;
static struct kmem_cache *openowner_slab;
static struct kmem_cache *lockowner_slab;
static struct kmem_cache *file_slab;
static struct kmem_cache *stateid_slab;
static struct kmem_cache *deleg_slab;
static struct kmem_cache *odstate_slab;

static void free_session(struct nfsd4_session *);

static const struct nfsd4_callback_ops nfsd4_cb_recall_ops;
static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops;

static bool is_session_dead(struct nfsd4_session *ses)
{
	return ses->se_flags & NFS4_SESSION_DEAD;
}

static __be32 mark_session_dead_locked(struct nfsd4_session *ses, int ref_held_by_me)
{
	if (atomic_read(&ses->se_ref) > ref_held_by_me)
		return nfserr_jukebox;
	ses->se_flags |= NFS4_SESSION_DEAD;
	return nfs_ok;
}

static bool is_client_expired(struct nfs4_client *clp)
{
	return clp->cl_time == 0;
}

static __be32 get_client_locked(struct nfs4_client *clp)
{
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);

	lockdep_assert_held(&nn->client_lock);

	if (is_client_expired(clp))
		return nfserr_expired;
	atomic_inc(&clp->cl_rpc_users);
	return nfs_ok;
}

/* must be called under the client_lock */
static inline void
renew_client_locked(struct nfs4_client *clp)
{
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);

	if (is_client_expired(clp)) {
		WARN_ON(1);
		printk("%s: client (clientid %08x/%08x) already expired\n",
			__func__,
			clp->cl_clientid.cl_boot,
			clp->cl_clientid.cl_id);
		return;
	}

	list_move_tail(&clp->cl_lru, &nn->client_lru);
	clp->cl_time = ktime_get_boottime_seconds();
}

static void put_client_renew_locked(struct nfs4_client *clp)
{
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);

	lockdep_assert_held(&nn->client_lock);

	if (!atomic_dec_and_test(&clp->cl_rpc_users))
		return;
	if (!is_client_expired(clp))
		renew_client_locked(clp);
	else
		wake_up_all(&expiry_wq);
}

static void put_client_renew(struct nfs4_client *clp)
{
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);

	if (!atomic_dec_and_lock(&clp->cl_rpc_users, &nn->client_lock))
		return;
	if (!is_client_expired(clp))
		renew_client_locked(clp);
	else
		wake_up_all(&expiry_wq);
	spin_unlock(&nn->client_lock);
}

static __be32 nfsd4_get_session_locked(struct nfsd4_session *ses)
{
	__be32 status;

	if (is_session_dead(ses))
		return nfserr_badsession;
	status = get_client_locked(ses->se_client);
	if (status)
		return status;
	atomic_inc(&ses->se_ref);
	return nfs_ok;
}

static void nfsd4_put_session_locked(struct nfsd4_session *ses)
{
	struct nfs4_client *clp = ses->se_client;
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);

	lockdep_assert_held(&nn->client_lock);

	if (atomic_dec_and_test(&ses->se_ref) && is_session_dead(ses))
		free_session(ses);
	put_client_renew_locked(clp);
}

static void nfsd4_put_session(struct nfsd4_session *ses)
{
	struct nfs4_client *clp = ses->se_client;
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);

	spin_lock(&nn->client_lock);
	nfsd4_put_session_locked(ses);
	spin_unlock(&nn->client_lock);
}

static struct nfsd4_blocked_lock *
find_blocked_lock(struct nfs4_lockowner *lo, struct knfsd_fh *fh,
			struct nfsd_net *nn)
{
	struct nfsd4_blocked_lock *cur, *found = NULL;

	spin_lock(&nn->blocked_locks_lock);
	list_for_each_entry(cur, &lo->lo_blocked, nbl_list) {
		if (fh_match(fh, &cur->nbl_fh)) {
			list_del_init(&cur->nbl_list);
			list_del_init(&cur->nbl_lru);
			found = cur;
			break;
		}
	}
	spin_unlock(&nn->blocked_locks_lock);
	if (found)
		locks_delete_block(&found->nbl_lock);
	return found;
}

static struct nfsd4_blocked_lock *
find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh,
			struct nfsd_net *nn)
{
	struct nfsd4_blocked_lock *nbl;

	nbl = find_blocked_lock(lo, fh, nn);
	if (!nbl) {
		nbl= kmalloc(sizeof(*nbl), GFP_KERNEL);
		if (nbl) {
			INIT_LIST_HEAD(&nbl->nbl_list);
			INIT_LIST_HEAD(&nbl->nbl_lru);
			fh_copy_shallow(&nbl->nbl_fh, fh);
			locks_init_lock(&nbl->nbl_lock);
			nfsd4_init_cb(&nbl->nbl_cb, lo->lo_owner.so_client,
					&nfsd4_cb_notify_lock_ops,
					NFSPROC4_CLNT_CB_NOTIFY_LOCK);
		}
	}
	return nbl;
}

static void
free_blocked_lock(struct nfsd4_blocked_lock *nbl)
{
	locks_delete_block(&nbl->nbl_lock);
	locks_release_private(&nbl->nbl_lock);
	kfree(nbl);
}

static void
remove_blocked_locks(struct nfs4_lockowner *lo)
{
	struct nfs4_client *clp = lo->lo_owner.so_client;
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
	struct nfsd4_blocked_lock *nbl;
	LIST_HEAD(reaplist);

	/* Dequeue all blocked locks */
	spin_lock(&nn->blocked_locks_lock);
	while (!list_empty(&lo->lo_blocked)) {
		nbl = list_first_entry(&lo->lo_blocked,
					struct nfsd4_blocked_lock,
					nbl_list);
		list_del_init(&nbl->nbl_list);
		list_move(&nbl->nbl_lru, &reaplist);
	}
	spin_unlock(&nn->blocked_locks_lock);

	/* Now free them */
	while (!list_empty(&reaplist)) {
		nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock,
					nbl_lru);
		list_del_init(&nbl->nbl_lru);
		free_blocked_lock(nbl);
	}
}

static void
nfsd4_cb_notify_lock_prepare(struct nfsd4_callback *cb)
{
	struct nfsd4_blocked_lock	*nbl = container_of(cb,
						struct nfsd4_blocked_lock, nbl_cb);
	locks_delete_block(&nbl->nbl_lock);
}

static int
nfsd4_cb_notify_lock_done(struct nfsd4_callback *cb, struct rpc_task *task)
{
	/*
	 * Since this is just an optimization, we don't try very hard if it
	 * turns out not to succeed. We'll requeue it on NFS4ERR_DELAY, and
	 * just quit trying on anything else.
	 */
	switch (task->tk_status) {
	case -NFS4ERR_DELAY:
		rpc_delay(task, 1 * HZ);
		return 0;
	default:
		return 1;
	}
}

static void
nfsd4_cb_notify_lock_release(struct nfsd4_callback *cb)
{
	struct nfsd4_blocked_lock	*nbl = container_of(cb,
						struct nfsd4_blocked_lock, nbl_cb);

	free_blocked_lock(nbl);
}

static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = {
	.prepare	= nfsd4_cb_notify_lock_prepare,
	.done		= nfsd4_cb_notify_lock_done,
	.release	= nfsd4_cb_notify_lock_release,
};

/*
 * We store the NONE, READ, WRITE, and BOTH bits separately in the
 * st_{access,deny}_bmap field of the stateid, in order to track not
 * only what share bits are currently in force, but also what
 * combinations of share bits previous opens have used.  This allows us
 * to enforce the recommendation of rfc 3530 14.2.19 that the server
 * return an error if the client attempt to downgrade to a combination
 * of share bits not explicable by closing some of its previous opens.
 *
 * XXX: This enforcement is actually incomplete, since we don't keep
 * track of access/deny bit combinations; so, e.g., we allow:
 *
 *	OPEN allow read, deny write
 *	OPEN allow both, deny none
 *	DOWNGRADE allow read, deny none
 *
 * which we should reject.
 */
static unsigned int
bmap_to_share_mode(unsigned long bmap)
{
	int i;
	unsigned int access = 0;

	for (i = 1; i < 4; i++) {
		if (test_bit(i, &bmap))
			access |= i;
	}
	return access;
}

/* set share access for a given stateid */
static inline void
set_access(u32 access, struct nfs4_ol_stateid *stp)
{
	unsigned char mask = 1 << access;

	WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH);
	stp->st_access_bmap |= mask;
}

/* clear share access for a given stateid */
static inline void
clear_access(u32 access, struct nfs4_ol_stateid *stp)
{
	unsigned char mask = 1 << access;

	WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH);
	stp->st_access_bmap &= ~mask;
}

/* test whether a given stateid has access */
static inline bool
test_access(u32 access, struct nfs4_ol_stateid *stp)
{
	unsigned char mask = 1 << access;

	return (bool)(stp->st_access_bmap & mask);
}

/* set share deny for a given stateid */
static inline void
set_deny(u32 deny, struct nfs4_ol_stateid *stp)
{
	unsigned char mask = 1 << deny;

	WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH);
	stp->st_deny_bmap |= mask;
}

/* clear share deny for a given stateid */
static inline void
clear_deny(u32 deny, struct nfs4_ol_stateid *stp)
{
	unsigned char mask = 1 << deny;

	WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH);
	stp->st_deny_bmap &= ~mask;
}

/* test whether a given stateid is denying specific access */
static inline bool
test_deny(u32 deny, struct nfs4_ol_stateid *stp)
{
	unsigned char mask = 1 << deny;

	return (bool)(stp->st_deny_bmap & mask);
}

static int nfs4_access_to_omode(u32 access)
{
	switch (access & NFS4_SHARE_ACCESS_BOTH) {
	case NFS4_SHARE_ACCESS_READ:
		return O_RDONLY;
	case NFS4_SHARE_ACCESS_WRITE:
		return O_WRONLY;
	case NFS4_SHARE_ACCESS_BOTH:
		return O_RDWR;
	}
	WARN_ON_ONCE(1);
	return O_RDONLY;
}

static inline int
access_permit_read(struct nfs4_ol_stateid *stp)
{
	return test_access(NFS4_SHARE_ACCESS_READ, stp) ||
		test_access(NFS4_SHARE_ACCESS_BOTH, stp) ||
		test_access(NFS4_SHARE_ACCESS_WRITE, stp);
}

static inline int
access_permit_write(struct nfs4_ol_stateid *stp)
{
	return test_access(NFS4_SHARE_ACCESS_WRITE, stp) ||
		test_access(NFS4_SHARE_ACCESS_BOTH, stp);
}

static inline struct nfs4_stateowner *
nfs4_get_stateowner(struct nfs4_stateowner *sop)
{
	atomic_inc(&sop->so_count);
	return sop;
}

static int
same_owner_str(struct nfs4_stateowner *sop, struct xdr_netobj *owner)
{
	return (sop->so_owner.len == owner->len) &&
		0 == memcmp(sop->so_owner.data, owner->data, owner->len);
}

static struct nfs4_openowner *
find_openstateowner_str_locked(unsigned int hashval, struct nfsd4_open *open,
			struct nfs4_client *clp)
{
	struct nfs4_stateowner *so;

	lockdep_assert_held(&clp->cl_lock);

	list_for_each_entry(so, &clp->cl_ownerstr_hashtbl[hashval],
			    so_strhash) {
		if (!so->so_is_open_owner)
			continue;
		if (same_owner_str(so, &open->op_owner))
			return openowner(nfs4_get_stateowner(so));
	}
	return NULL;
}

static struct nfs4_openowner *
find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open,
			struct nfs4_client *clp)
{
	struct nfs4_openowner *oo;

	spin_lock(&clp->cl_lock);
	oo = find_openstateowner_str_locked(hashval, open, clp);
	spin_unlock(&clp->cl_lock);
	return oo;
}

static inline u32
opaque_hashval(const void *ptr, int nbytes)
{
	unsigned char *cptr = (unsigned char *) ptr;

	u32 x = 0;
	while (nbytes--) {
		x *= 37;
		x += *cptr++;
	}
	return x;
}

static void nfsd4_free_file_rcu(struct rcu_head *rcu)
{
	struct nfs4_file *fp = container_of(rcu, struct nfs4_file, fi_rcu);

	kmem_cache_free(file_slab, fp);
}

void
put_nfs4_file(struct nfs4_file *fi)
{
	might_lock(&state_lock);

	if (refcount_dec_and_lock(&fi->fi_ref, &state_lock)) {
		hlist_del_rcu(&fi->fi_hash);
		spin_unlock(&state_lock);
		WARN_ON_ONCE(!list_empty(&fi->fi_clnt_odstate));
		WARN_ON_ONCE(!list_empty(&fi->fi_delegations));
		call_rcu(&fi->fi_rcu, nfsd4_free_file_rcu);
	}
}

static struct nfsd_file *
__nfs4_get_fd(struct nfs4_file *f, int oflag)
{
	if (f->fi_fds[oflag])
		return nfsd_file_get(f->fi_fds[oflag]);
	return NULL;
}

static struct nfsd_file *
find_writeable_file_locked(struct nfs4_file *f)
{
	struct nfsd_file *ret;

	lockdep_assert_held(&f->fi_lock);

	ret = __nfs4_get_fd(f, O_WRONLY);
	if (!ret)
		ret = __nfs4_get_fd(f, O_RDWR);
	return ret;
}

static struct nfsd_file *
find_writeable_file(struct nfs4_file *f)
{
	struct nfsd_file *ret;

	spin_lock(&f->fi_lock);
	ret = find_writeable_file_locked(f);
	spin_unlock(&f->fi_lock);

	return ret;
}

static struct nfsd_file *
find_readable_file_locked(struct nfs4_file *f)
{
	struct nfsd_file *ret;

	lockdep_assert_held(&f->fi_lock);

	ret = __nfs4_get_fd(f, O_RDONLY);
	if (!ret)
		ret = __nfs4_get_fd(f, O_RDWR);
	return ret;
}

static struct nfsd_file *
find_readable_file(struct nfs4_file *f)
{
	struct nfsd_file *ret;

	spin_lock(&f->fi_lock);
	ret = find_readable_file_locked(f);
	spin_unlock(&f->fi_lock);

	return ret;
}

struct nfsd_file *
find_any_file(struct nfs4_file *f)
{
	struct nfsd_file *ret;

	if (!f)
		return NULL;
	spin_lock(&f->fi_lock);
	ret = __nfs4_get_fd(f, O_RDWR);
	if (!ret) {
		ret = __nfs4_get_fd(f, O_WRONLY);
		if (!ret)
			ret = __nfs4_get_fd(f, O_RDONLY);
	}
	spin_unlock(&f->fi_lock);
	return ret;
}

static struct nfsd_file *find_deleg_file(struct nfs4_file *f)
{
	struct nfsd_file *ret = NULL;

	spin_lock(&f->fi_lock);
	if (f->fi_deleg_file)
		ret = nfsd_file_get(f->fi_deleg_file);
	spin_unlock(&f->fi_lock);
	return ret;
}

static atomic_long_t num_delegations;
unsigned long max_delegations;

/*
 * Open owner state (share locks)
 */

/* hash tables for lock and open owners */
#define OWNER_HASH_BITS              8
#define OWNER_HASH_SIZE             (1 << OWNER_HASH_BITS)
#define OWNER_HASH_MASK             (OWNER_HASH_SIZE - 1)

static unsigned int ownerstr_hashval(struct xdr_netobj *ownername)
{
	unsigned int ret;

	ret = opaque_hashval(ownername->data, ownername->len);
	return ret & OWNER_HASH_MASK;
}

/* hash table for nfs4_file */
#define FILE_HASH_BITS                   8
#define FILE_HASH_SIZE                  (1 << FILE_HASH_BITS)

static unsigned int file_hashval(struct svc_fh *fh)
{
	struct inode *inode = d_inode(fh->fh_dentry);

	/* XXX: why not (here & in file cache) use inode? */
	return (unsigned int)hash_long(inode->i_ino, FILE_HASH_BITS);
}

static struct hlist_head file_hashtbl[FILE_HASH_SIZE];

static void
__nfs4_file_get_access(struct nfs4_file *fp, u32 access)
{
	lockdep_assert_held(&fp->fi_lock);

	if (access & NFS4_SHARE_ACCESS_WRITE)
		atomic_inc(&fp->fi_access[O_WRONLY]);
	if (access & NFS4_SHARE_ACCESS_READ)
		atomic_inc(&fp->fi_access[O_RDONLY]);
}

static __be32
nfs4_file_get_access(struct nfs4_file *fp, u32 access)
{
	lockdep_assert_held(&fp->fi_lock);

	/* Does this access mode make sense? */
	if (access & ~NFS4_SHARE_ACCESS_BOTH)
		return nfserr_inval;

	/* Does it conflict with a deny mode already set? */
	if ((access & fp->fi_share_deny) != 0)
		return nfserr_share_denied;

	__nfs4_file_get_access(fp, access);
	return nfs_ok;
}

static __be32 nfs4_file_check_deny(struct nfs4_file *fp, u32 deny)
{
	/* Common case is that there is no deny mode. */
	if (deny) {
		/* Does this deny mode make sense? */
		if (deny & ~NFS4_SHARE_DENY_BOTH)
			return nfserr_inval;

		if ((deny & NFS4_SHARE_DENY_READ) &&
		    atomic_read(&fp->fi_access[O_RDONLY]))
			return nfserr_share_denied;

		if ((deny & NFS4_SHARE_DENY_WRITE) &&
		    atomic_read(&fp->fi_access[O_WRONLY]))
			return nfserr_share_denied;
	}
	return nfs_ok;
}

static void __nfs4_file_put_access(struct nfs4_file *fp, int oflag)
{
	might_lock(&fp->fi_lock);

	if (atomic_dec_and_lock(&fp->fi_access[oflag], &fp->fi_lock)) {
		struct nfsd_file *f1 = NULL;
		struct nfsd_file *f2 = NULL;

		swap(f1, fp->fi_fds[oflag]);
		if (atomic_read(&fp->fi_access[1 - oflag]) == 0)
			swap(f2, fp->fi_fds[O_RDWR]);
		spin_unlock(&fp->fi_lock);
		if (f1)
			nfsd_file_put(f1);
		if (f2)
			nfsd_file_put(f2);
	}
}

static void nfs4_file_put_access(struct nfs4_file *fp, u32 access)
{
	WARN_ON_ONCE(access & ~NFS4_SHARE_ACCESS_BOTH);

	if (access & NFS4_SHARE_ACCESS_WRITE)
		__nfs4_file_put_access(fp, O_WRONLY);
	if (access & NFS4_SHARE_ACCESS_READ)
		__nfs4_file_put_access(fp, O_RDONLY);
}

/*
 * Allocate a new open/delegation state counter. This is needed for
 * pNFS for proper return on close semantics.
 *
 * Note that we only allocate it for pNFS-enabled exports, otherwise
 * all pointers to struct nfs4_clnt_odstate are always NULL.
 */
static struct nfs4_clnt_odstate *
alloc_clnt_odstate(struct nfs4_client *clp)
{
	struct nfs4_clnt_odstate *co;

	co = kmem_cache_zalloc(odstate_slab, GFP_KERNEL);
	if (co) {
		co->co_client = clp;
		refcount_set(&co->co_odcount, 1);
	}
	return co;
}

static void
hash_clnt_odstate_locked(struct nfs4_clnt_odstate *co)
{
	struct nfs4_file *fp = co->co_file;

	lockdep_assert_held(&fp->fi_lock);
	list_add(&co->co_perfile, &fp->fi_clnt_odstate);
}

static inline void
get_clnt_odstate(struct nfs4_clnt_odstate *co)
{
	if (co)
		refcount_inc(&co->co_odcount);
}

static void
put_clnt_odstate(struct nfs4_clnt_odstate *co)
{
	struct nfs4_file *fp;

	if (!co)
		return;

	fp = co->co_file;
	if (refcount_dec_and_lock(&co->co_odcount, &fp->fi_lock)) {
		list_del(&co->co_perfile);
		spin_unlock(&fp->fi_lock);

		nfsd4_return_all_file_layouts(co->co_client, fp);
		kmem_cache_free(odstate_slab, co);
	}
}

static struct nfs4_clnt_odstate *
find_or_hash_clnt_odstate(struct nfs4_file *fp, struct nfs4_clnt_odstate *new)
{
	struct nfs4_clnt_odstate *co;
	struct nfs4_client *cl;

	if (!new)
		return NULL;

	cl = new->co_client;

	spin_lock(&fp->fi_lock);
	list_for_each_entry(co, &fp->fi_clnt_odstate, co_perfile) {
		if (co->co_client == cl) {
			get_clnt_odstate(co);
			goto out;
		}
	}
	co = new;
	co->co_file = fp;
	hash_clnt_odstate_locked(new);
out:
	spin_unlock(&fp->fi_lock);
	return co;
}

struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab,
				  void (*sc_free)(struct nfs4_stid *))
{
	struct nfs4_stid *stid;
	int new_id;

	stid = kmem_cache_zalloc(slab, GFP_KERNEL);
	if (!stid)
		return NULL;

	idr_preload(GFP_KERNEL);
	spin_lock(&cl->cl_lock);
	/* Reserving 0 for start of file in nfsdfs "states" file: */
	new_id = idr_alloc_cyclic(&cl->cl_stateids, stid, 1, 0, GFP_NOWAIT);
	spin_unlock(&cl->cl_lock);
	idr_preload_end();
	if (new_id < 0)
		goto out_free;

	stid->sc_free = sc_free;
	stid->sc_client = cl;
	stid->sc_stateid.si_opaque.so_id = new_id;
	stid->sc_stateid.si_opaque.so_clid = cl->cl_clientid;
	/* Will be incremented before return to client: */
	refcount_set(&stid->sc_count, 1);
	spin_lock_init(&stid->sc_lock);
	INIT_LIST_HEAD(&stid->sc_cp_list);

	/*
	 * It shouldn't be a problem to reuse an opaque stateid value.
	 * I don't think it is for 4.1.  But with 4.0 I worry that, for
	 * example, a stray write retransmission could be accepted by
	 * the server when it should have been rejected.  Therefore,
	 * adopt a trick from the sctp code to attempt to maximize the
	 * amount of time until an id is reused, by ensuring they always
	 * "increase" (mod INT_MAX):
	 */
	return stid;
out_free:
	kmem_cache_free(slab, stid);
	return NULL;
}

/*
 * Create a unique stateid_t to represent each COPY.
 */
static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid,
			      unsigned char sc_type)
{
	int new_id;

	stid->stid.si_opaque.so_clid.cl_boot = (u32)nn->boot_time;
	stid->stid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id;
	stid->sc_type = sc_type;

	idr_preload(GFP_KERNEL);
	spin_lock(&nn->s2s_cp_lock);
	new_id = idr_alloc_cyclic(&nn->s2s_cp_stateids, stid, 0, 0, GFP_NOWAIT);
	stid->stid.si_opaque.so_id = new_id;
	stid->stid.si_generation = 1;
	spin_unlock(&nn->s2s_cp_lock);
	idr_preload_end();
	if (new_id < 0)
		return 0;
	return 1;
}

int nfs4_init_copy_state(struct nfsd_net *nn, struct nfsd4_copy *copy)
{
	return nfs4_init_cp_state(nn, &copy->cp_stateid, NFS4_COPY_STID);
}

struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn,
						     struct nfs4_stid *p_stid)
{
	struct nfs4_cpntf_state *cps;

	cps = kzalloc(sizeof(struct nfs4_cpntf_state), GFP_KERNEL);
	if (!cps)
		return NULL;
	cps->cpntf_time = ktime_get_boottime_seconds();
	refcount_set(&cps->cp_stateid.sc_count, 1);
	if (!nfs4_init_cp_state(nn, &cps->cp_stateid, NFS4_COPYNOTIFY_STID))
		goto out_free;
	spin_lock(&nn->s2s_cp_lock);
	list_add(&cps->cp_list, &p_stid->sc_cp_list);
	spin_unlock(&nn->s2s_cp_lock);
	return cps;
out_free:
	kfree(cps);
	return NULL;
}

void nfs4_free_copy_state(struct nfsd4_copy *copy)
{
	struct nfsd_net *nn;

	WARN_ON_ONCE(copy->cp_stateid.sc_type != NFS4_COPY_STID);
	nn = net_generic(copy->cp_clp->net, nfsd_net_id);
	spin_lock(&nn->s2s_cp_lock);
	idr_remove(&nn->s2s_cp_stateids,
		   copy->cp_stateid.stid.si_opaque.so_id);
	spin_unlock(&nn->s2s_cp_lock);
}

static void nfs4_free_cpntf_statelist(struct net *net, struct nfs4_stid *stid)
{
	struct nfs4_cpntf_state *cps;
	struct nfsd_net *nn;

	nn = net_generic(net, nfsd_net_id);
	spin_lock(&nn->s2s_cp_lock);
	while (!list_empty(&stid->sc_cp_list)) {
		cps = list_first_entry(&stid->sc_cp_list,
				       struct nfs4_cpntf_state, cp_list);
		_free_cpntf_state_locked(nn, cps);
	}
	spin_unlock(&nn->s2s_cp_lock);
}

static struct nfs4_ol_stateid * nfs4_alloc_open_stateid(struct nfs4_client *clp)
{
	struct nfs4_stid *stid;

	stid = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_ol_stateid);
	if (!stid)
		return NULL;

	return openlockstateid(stid);
}

static void nfs4_free_deleg(struct nfs4_stid *stid)
{
	kmem_cache_free(deleg_slab, stid);
	atomic_long_dec(&num_delegations);
}

/*
 * When we recall a delegation, we should be careful not to hand it
 * out again straight away.
 * To ensure this we keep a pair of bloom filters ('new' and 'old')
 * in which the filehandles of recalled delegations are "stored".
 * If a filehandle appear in either filter, a delegation is blocked.
 * When a delegation is recalled, the filehandle is stored in the "new"
 * filter.
 * Every 30 seconds we swap the filters and clear the "new" one,
 * unless both are empty of course.
 *
 * Each filter is 256 bits.  We hash the filehandle to 32bit and use the
 * low 3 bytes as hash-table indices.
 *
 * 'blocked_delegations_lock', which is always taken in block_delegations(),
 * is used to manage concurrent access.  Testing does not need the lock
 * except when swapping the two filters.
 */
static DEFINE_SPINLOCK(blocked_delegations_lock);
static struct bloom_pair {
	int	entries, old_entries;
	time64_t swap_time;
	int	new; /* index into 'set' */
	DECLARE_BITMAP(set[2], 256);
} blocked_delegations;

static int delegation_blocked(struct knfsd_fh *fh)
{
	u32 hash;
	struct bloom_pair *bd = &blocked_delegations;

	if (bd->entries == 0)
		return 0;
	if (ktime_get_seconds() - bd->swap_time > 30) {
		spin_lock(&blocked_delegations_lock);
		if (ktime_get_seconds() - bd->swap_time > 30) {
			bd->entries -= bd->old_entries;
			bd->old_entries = bd->entries;
			memset(bd->set[bd->new], 0,
			       sizeof(bd->set[0]));
			bd->new = 1-bd->new;
			bd->swap_time = ktime_get_seconds();
		}
		spin_unlock(&blocked_delegations_lock);
	}
	hash = jhash(&fh->fh_raw, fh->fh_size, 0);
	if (test_bit(hash&255, bd->set[0]) &&
	    test_bit((hash>>8)&255, bd->set[0]) &&
	    test_bit((hash>>16)&255, bd->set[0]))
		return 1;

	if (test_bit(hash&255, bd->set[1]) &&
	    test_bit((hash>>8)&255, bd->set[1]) &&
	    test_bit((hash>>16)&255, bd->set[1]))
		return 1;

	return 0;
}

static void block_delegations(struct knfsd_fh *fh)
{
	u32 hash;
	struct bloom_pair *bd = &blocked_delegations;

	hash = jhash(&fh->fh_raw, fh->fh_size, 0);

	spin_lock(&blocked_delegations_lock);
	__set_bit(hash&255, bd->set[bd->new]);
	__set_bit((hash>>8)&255, bd->set[bd->new]);
	__set_bit((hash>>16)&255, bd->set[bd->new]);
	if (bd->entries == 0)
		bd->swap_time = ktime_get_seconds();
	bd->entries += 1;
	spin_unlock(&blocked_delegations_lock);
}

static struct nfs4_delegation *
alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp,
		 struct svc_fh *current_fh,
		 struct nfs4_clnt_odstate *odstate)
{
	struct nfs4_delegation *dp;
	long n;

	dprintk("NFSD alloc_init_deleg\n");
	n = atomic_long_inc_return(&num_delegations);
	if (n < 0 || n > max_delegations)
		goto out_dec;
	if (delegation_blocked(&current_fh->fh_handle))
		goto out_dec;
	dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg));
	if (dp == NULL)
		goto out_dec;

	/*
	 * delegation seqid's are never incremented.  The 4.1 special
	 * meaning of seqid 0 isn't meaningful, really, but let's avoid
	 * 0 anyway just for consistency and use 1:
	 */
	dp->dl_stid.sc_stateid.si_generation = 1;
	INIT_LIST_HEAD(&dp->dl_perfile);
	INIT_LIST_HEAD(&dp->dl_perclnt);
	INIT_LIST_HEAD(&dp->dl_recall_lru);
	dp->dl_clnt_odstate = odstate;
	get_clnt_odstate(odstate);
	dp->dl_type = NFS4_OPEN_DELEGATE_READ;
	dp->dl_retries = 1;
	nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client,
		      &nfsd4_cb_recall_ops, NFSPROC4_CLNT_CB_RECALL);
	get_nfs4_file(fp);
	dp->dl_stid.sc_file = fp;
	return dp;
out_dec:
	atomic_long_dec(&num_delegations);
	return NULL;
}

void
nfs4_put_stid(struct nfs4_stid *s)
{
	struct nfs4_file *fp = s->sc_file;
	struct nfs4_client *clp = s->sc_client;

	might_lock(&clp->cl_lock);

	if (!refcount_dec_and_lock(&s->sc_count, &clp->cl_lock)) {
		wake_up_all(&close_wq);
		return;
	}
	idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id);
	nfs4_free_cpntf_statelist(clp->net, s);
	spin_unlock(&clp->cl_lock);
	s->sc_free(s);
	if (fp)
		put_nfs4_file(fp);
}

void
nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid)
{
	stateid_t *src = &stid->sc_stateid;

	spin_lock(&stid->sc_lock);
	if (unlikely(++src->si_generation == 0))
		src->si_generation = 1;
	memcpy(dst, src, sizeof(*dst));
	spin_unlock(&stid->sc_lock);
}

static void put_deleg_file(struct nfs4_file *fp)
{
	struct nfsd_file *nf = NULL;

	spin_lock(&fp->fi_lock);
	if (--fp->fi_delegees == 0)
		swap(nf, fp->fi_deleg_file);
	spin_unlock(&fp->fi_lock);

	if (nf)
		nfsd_file_put(nf);
}

static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp)
{
	struct nfs4_file *fp = dp->dl_stid.sc_file;
	struct nfsd_file *nf = fp->fi_deleg_file;

	WARN_ON_ONCE(!fp->fi_delegees);

	vfs_setlease(nf->nf_file, F_UNLCK, NULL, (void **)&dp);
	put_deleg_file(fp);
}

static void destroy_unhashed_deleg(struct nfs4_delegation *dp)
{
	put_clnt_odstate(dp->dl_clnt_odstate);
	nfs4_unlock_deleg_lease(dp);
	nfs4_put_stid(&dp->dl_stid);
}

void nfs4_unhash_stid(struct nfs4_stid *s)
{
	s->sc_type = 0;
}

/**
 * nfs4_delegation_exists - Discover if this delegation already exists
 * @clp:     a pointer to the nfs4_client we're granting a delegation to
 * @fp:      a pointer to the nfs4_file we're granting a delegation on
 *
 * Return:
 *      On success: true iff an existing delegation is found
 */

static bool
nfs4_delegation_exists(struct nfs4_client *clp, struct nfs4_file *fp)
{
	struct nfs4_delegation *searchdp = NULL;
	struct nfs4_client *searchclp = NULL;

	lockdep_assert_held(&state_lock);
	lockdep_assert_held(&fp->fi_lock);

	list_for_each_entry(searchdp, &fp->fi_delegations, dl_perfile) {
		searchclp = searchdp->dl_stid.sc_client;
		if (clp == searchclp) {
			return true;
		}
	}
	return false;
}

/**
 * hash_delegation_locked - Add a delegation to the appropriate lists
 * @dp:     a pointer to the nfs4_delegation we are adding.
 * @fp:     a pointer to the nfs4_file we're granting a delegation on
 *
 * Return:
 *      On success: NULL if the delegation was successfully hashed.
 *
 *      On error: -EAGAIN if one was previously granted to this
 *                 nfs4_client for this nfs4_file. Delegation is not hashed.
 *
 */

static int
hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp)
{
	struct nfs4_client *clp = dp->dl_stid.sc_client;

	lockdep_assert_held(&state_lock);
	lockdep_assert_held(&fp->fi_lock);

	if (nfs4_delegation_exists(clp, fp))
		return -EAGAIN;
	refcount_inc(&dp->dl_stid.sc_count);
	dp->dl_stid.sc_type = NFS4_DELEG_STID;
	list_add(&dp->dl_perfile, &fp->fi_delegations);
	list_add(&dp->dl_perclnt, &clp->cl_delegations);
	return 0;
}

static bool
unhash_delegation_locked(struct nfs4_delegation *dp)
{
	struct nfs4_file *fp = dp->dl_stid.sc_file;

	lockdep_assert_held(&state_lock);

	if (list_empty(&dp->dl_perfile))
		return false;

	dp->dl_stid.sc_type = NFS4_CLOSED_DELEG_STID;
	/* Ensure that deleg break won't try to requeue it */
	++dp->dl_time;
	spin_lock(&fp->fi_lock);
	list_del_init(&dp->dl_perclnt);
	list_del_init(&dp->dl_recall_lru);
	list_del_init(&dp->dl_perfile);
	spin_unlock(&fp->fi_lock);
	return true;
}

static void destroy_delegation(struct nfs4_delegation *dp)
{
	bool unhashed;

	spin_lock(&state_lock);
	unhashed = unhash_delegation_locked(dp);
	spin_unlock(&state_lock);
	if (unhashed)
		destroy_unhashed_deleg(dp);
}

static void revoke_delegation(struct nfs4_delegation *dp)
{
	struct nfs4_client *clp = dp->dl_stid.sc_client;

	WARN_ON(!list_empty(&dp->dl_recall_lru));

	if (clp->cl_minorversion) {
		dp->dl_stid.sc_type = NFS4_REVOKED_DELEG_STID;
		refcount_inc(&dp->dl_stid.sc_count);
		spin_lock(&clp->cl_lock);
		list_add(&dp->dl_recall_lru, &clp->cl_revoked);
		spin_unlock(&clp->cl_lock);
	}
	destroy_unhashed_deleg(dp);
}

/* 
 * SETCLIENTID state 
 */

static unsigned int clientid_hashval(u32 id)
{
	return id & CLIENT_HASH_MASK;
}

static unsigned int clientstr_hashval(struct xdr_netobj name)
{
	return opaque_hashval(name.data, 8) & CLIENT_HASH_MASK;
}

/*
 * A stateid that had a deny mode associated with it is being released
 * or downgraded. Recalculate the deny mode on the file.
 */
static void
recalculate_deny_mode(struct nfs4_file *fp)
{
	struct nfs4_ol_stateid *stp;

	spin_lock(&fp->fi_lock);
	fp->fi_share_deny = 0;
	list_for_each_entry(stp, &fp->fi_stateids, st_perfile)
		fp->fi_share_deny |= bmap_to_share_mode(stp->st_deny_bmap);
	spin_unlock(&fp->fi_lock);
}

static void
reset_union_bmap_deny(u32 deny, struct nfs4_ol_stateid *stp)
{
	int i;
	bool change = false;

	for (i = 1; i < 4; i++) {
		if ((i & deny) != i) {
			change = true;
			clear_deny(i, stp);
		}
	}

	/* Recalculate per-file deny mode if there was a change */
	if (change)
		recalculate_deny_mode(stp->st_stid.sc_file);
}

/* release all access and file references for a given stateid */
static void
release_all_access(struct nfs4_ol_stateid *stp)
{
	int i;
	struct nfs4_file *fp = stp->st_stid.sc_file;

	if (fp && stp->st_deny_bmap != 0)
		recalculate_deny_mode(fp);

	for (i = 1; i < 4; i++) {
		if (test_access(i, stp))
			nfs4_file_put_access(stp->st_stid.sc_file, i);
		clear_access(i, stp);
	}
}

static inline void nfs4_free_stateowner(struct nfs4_stateowner *sop)
{
	kfree(sop->so_owner.data);
	sop->so_ops->so_free(sop);
}

static void nfs4_put_stateowner(struct nfs4_stateowner *sop)
{
	struct nfs4_client *clp = sop->so_client;

	might_lock(&clp->cl_lock);

	if (!atomic_dec_and_lock(&sop->so_count, &clp->cl_lock))
		return;
	sop->so_ops->so_unhash(sop);
	spin_unlock(&clp->cl_lock);
	nfs4_free_stateowner(sop);
}

static bool
nfs4_ol_stateid_unhashed(const struct nfs4_ol_stateid *stp)
{
	return list_empty(&stp->st_perfile);
}

static bool unhash_ol_stateid(struct nfs4_ol_stateid *stp)
{
	struct nfs4_file *fp = stp->st_stid.sc_file;

	lockdep_assert_held(&stp->st_stateowner->so_client->cl_lock);

	if (list_empty(&stp->st_perfile))
		return false;

	spin_lock(&fp->fi_lock);
	list_del_init(&stp->st_perfile);
	spin_unlock(&fp->fi_lock);
	list_del(&stp->st_perstateowner);
	return true;
}

static void nfs4_free_ol_stateid(struct nfs4_stid *stid)
{
	struct nfs4_ol_stateid *stp = openlockstateid(stid);

	put_clnt_odstate(stp->st_clnt_odstate);
	release_all_access(stp);
	if (stp->st_stateowner)
		nfs4_put_stateowner(stp->st_stateowner);
	kmem_cache_free(stateid_slab, stid);
}

static void nfs4_free_lock_stateid(struct nfs4_stid *stid)
{
	struct nfs4_ol_stateid *stp = openlockstateid(stid);
	struct nfs4_lockowner *lo = lockowner(stp->st_stateowner);
	struct nfsd_file *nf;

	nf = find_any_file(stp->st_stid.sc_file);
	if (nf) {
		get_file(nf->nf_file);
		filp_close(nf->nf_file, (fl_owner_t)lo);
		nfsd_file_put(nf);
	}
	nfs4_free_ol_stateid(stid);
}

/*
 * Put the persistent reference to an already unhashed generic stateid, while
 * holding the cl_lock. If it's the last reference, then put it onto the
 * reaplist for later destruction.
 */
static void put_ol_stateid_locked(struct nfs4_ol_stateid *stp,
				       struct list_head *reaplist)
{
	struct nfs4_stid *s = &stp->st_stid;
	struct nfs4_client *clp = s->sc_client;

	lockdep_assert_held(&clp->cl_lock);

	WARN_ON_ONCE(!list_empty(&stp->st_locks));

	if (!refcount_dec_and_test(&s->sc_count)) {
		wake_up_all(&close_wq);
		return;
	}

	idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id);
	list_add(&stp->st_locks, reaplist);
}

static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp)
{
	lockdep_assert_held(&stp->st_stid.sc_client->cl_lock);

	if (!unhash_ol_stateid(stp))
		return false;
	list_del_init(&stp->st_locks);
	nfs4_unhash_stid(&stp->st_stid);
	return true;
}

static void release_lock_stateid(struct nfs4_ol_stateid *stp)
{
	struct nfs4_client *clp = stp->st_stid.sc_client;
	bool unhashed;

	spin_lock(&clp->cl_lock);
	unhashed = unhash_lock_stateid(stp);
	spin_unlock(&clp->cl_lock);
	if (unhashed)
		nfs4_put_stid(&stp->st_stid);
}

static void unhash_lockowner_locked(struct nfs4_lockowner *lo)
{
	struct nfs4_client *clp = lo->lo_owner.so_client;

	lockdep_assert_held(&clp->cl_lock);

	list_del_init(&lo->lo_owner.so_strhash);
}

/*
 * Free a list of generic stateids that were collected earlier after being
 * fully unhashed.
 */
static void
free_ol_stateid_reaplist(struct list_head *reaplist)
{
	struct nfs4_ol_stateid *stp;
	struct nfs4_file *fp;

	might_sleep();

	while (!list_empty(reaplist)) {
		stp = list_first_entry(reaplist, struct nfs4_ol_stateid,
				       st_locks);
		list_del(&stp->st_locks);
		fp = stp->st_stid.sc_file;
		stp->st_stid.sc_free(&stp->st_stid);
		if (fp)
			put_nfs4_file(fp);
	}
}

static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp,
				       struct list_head *reaplist)
{
	struct nfs4_ol_stateid *stp;

	lockdep_assert_held(&open_stp->st_stid.sc_client->cl_lock);

	while (!list_empty(&open_stp->st_locks)) {
		stp = list_entry(open_stp->st_locks.next,
				struct nfs4_ol_stateid, st_locks);
		WARN_ON(!unhash_lock_stateid(stp));
		put_ol_stateid_locked(stp, reaplist);
	}
}

static bool unhash_open_stateid(struct nfs4_ol_stateid *stp,
				struct list_head *reaplist)
{
	lockdep_assert_held(&stp->st_stid.sc_client->cl_lock);

	if (!unhash_ol_stateid(stp))
		return false;
	release_open_stateid_locks(stp, reaplist);
	return true;
}

static void release_open_stateid(struct nfs4_ol_stateid *stp)
{
	LIST_HEAD(reaplist);

	spin_lock(&stp->st_stid.sc_client->cl_lock);
	if (unhash_open_stateid(stp, &reaplist))
		put_ol_stateid_locked(stp, &reaplist);
	spin_unlock(&stp->st_stid.sc_client->cl_lock);
	free_ol_stateid_reaplist(&reaplist);
}

static void unhash_openowner_locked(struct nfs4_openowner *oo)
{
	struct nfs4_client *clp = oo->oo_owner.so_client;

	lockdep_assert_held(&clp->cl_lock);

	list_del_init(&oo->oo_owner.so_strhash);
	list_del_init(&oo->oo_perclient);
}

static void release_last_closed_stateid(struct nfs4_openowner *oo)
{
	struct nfsd_net *nn = net_generic(oo->oo_owner.so_client->net,
					  nfsd_net_id);
	struct nfs4_ol_stateid *s;

	spin_lock(&nn->client_lock);
	s = oo->oo_last_closed_stid;
	if (s) {
		list_del_init(&oo->oo_close_lru);
		oo->oo_last_closed_stid = NULL;
	}
	spin_unlock(&nn->client_lock);
	if (s)
		nfs4_put_stid(&s->st_stid);
}

static void release_openowner(struct nfs4_openowner *oo)
{
	struct nfs4_ol_stateid *stp;
	struct nfs4_client *clp = oo->oo_owner.so_client;
	struct list_head reaplist;

	INIT_LIST_HEAD(&reaplist);

	spin_lock(&clp->cl_lock);
	unhash_openowner_locked(oo);
	while (!list_empty(&oo->oo_owner.so_stateids)) {
		stp = list_first_entry(&oo->oo_owner.so_stateids,
				struct nfs4_ol_stateid, st_perstateowner);
		if (unhash_open_stateid(stp, &reaplist))
			put_ol_stateid_locked(stp, &reaplist);
	}
	spin_unlock(&clp->cl_lock);
	free_ol_stateid_reaplist(&reaplist);
	release_last_closed_stateid(oo);
	nfs4_put_stateowner(&oo->oo_owner);
}

static inline int
hash_sessionid(struct nfs4_sessionid *sessionid)
{
	struct nfsd4_sessionid *sid = (struct nfsd4_sessionid *)sessionid;

	return sid->sequence % SESSION_HASH_SIZE;
}

#ifdef CONFIG_SUNRPC_DEBUG
static inline void
dump_sessionid(const char *fn, struct nfs4_sessionid *sessionid)
{
	u32 *ptr = (u32 *)(&sessionid->data[0]);
	dprintk("%s: %u:%u:%u:%u\n", fn, ptr[0], ptr[1], ptr[2], ptr[3]);
}
#else
static inline void
dump_sessionid(const char *fn, struct nfs4_sessionid *sessionid)
{
}
#endif

/*
 * Bump the seqid on cstate->replay_owner, and clear replay_owner if it
 * won't be used for replay.
 */
void nfsd4_bump_seqid(struct nfsd4_compound_state *cstate, __be32 nfserr)
{
	struct nfs4_stateowner *so = cstate->replay_owner;

	if (nfserr == nfserr_replay_me)
		return;

	if (!seqid_mutating_err(ntohl(nfserr))) {
		nfsd4_cstate_clear_replay(cstate);
		return;
	}
	if (!so)
		return;
	if (so->so_is_open_owner)
		release_last_closed_stateid(openowner(so));
	so->so_seqid++;
	return;
}

static void
gen_sessionid(struct nfsd4_session *ses)
{
	struct nfs4_client *clp = ses->se_client;
	struct nfsd4_sessionid *sid;

	sid = (struct nfsd4_sessionid *)ses->se_sessionid.data;
	sid->clientid = clp->cl_clientid;
	sid->sequence = current_sessionid++;
	sid->reserved = 0;
}

/*
 * The protocol defines ca_maxresponssize_cached to include the size of
 * the rpc header, but all we need to cache is the data starting after
 * the end of the initial SEQUENCE operation--the rest we regenerate
 * each time.  Therefore we can advertise a ca_maxresponssize_cached
 * value that is the number of bytes in our cache plus a few additional
 * bytes.  In order to stay on the safe side, and not promise more than
 * we can cache, those additional bytes must be the minimum possible: 24
 * bytes of rpc header (xid through accept state, with AUTH_NULL
 * verifier), 12 for the compound header (with zero-length tag), and 44
 * for the SEQUENCE op response:
 */
#define NFSD_MIN_HDR_SEQ_SZ  (24 + 12 + 44)

static void
free_session_slots(struct nfsd4_session *ses)
{
	int i;

	for (i = 0; i < ses->se_fchannel.maxreqs; i++) {
		free_svc_cred(&ses->se_slots[i]->sl_cred);
		kfree(ses->se_slots[i]);
	}
}

/*
 * We don't actually need to cache the rpc and session headers, so we
 * can allocate a little less for each slot:
 */
static inline u32 slot_bytes(struct nfsd4_channel_attrs *ca)
{
	u32 size;

	if (ca->maxresp_cached < NFSD_MIN_HDR_SEQ_SZ)
		size = 0;
	else
		size = ca->maxresp_cached - NFSD_MIN_HDR_SEQ_SZ;
	return size + sizeof(struct nfsd4_slot);
}

/*
 * XXX: If we run out of reserved DRC memory we could (up to a point)
 * re-negotiate active sessions and reduce their slot usage to make
 * room for new connections. For now we just fail the create session.
 */
static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca, struct nfsd_net *nn)
{
	u32 slotsize = slot_bytes(ca);
	u32 num = ca->maxreqs;
	unsigned long avail, total_avail;
	unsigned int scale_factor;

	spin_lock(&nfsd_drc_lock);
	if (nfsd_drc_max_mem > nfsd_drc_mem_used)
		total_avail = nfsd_drc_max_mem - nfsd_drc_mem_used;
	else
		/* We have handed out more space than we chose in
		 * set_max_drc() to allow.  That isn't really a
		 * problem as long as that doesn't make us think we
		 * have lots more due to integer overflow.
		 */
		total_avail = 0;
	avail = min((unsigned long)NFSD_MAX_MEM_PER_SESSION, total_avail);
	/*
	 * Never use more than a fraction of the remaining memory,
	 * unless it's the only way to give this client a slot.
	 * The chosen fraction is either 1/8 or 1/number of threads,
	 * whichever is smaller.  This ensures there are adequate
	 * slots to support multiple clients per thread.
	 * Give the client one slot even if that would require
	 * over-allocation--it is better than failure.
	 */
	scale_factor = max_t(unsigned int, 8, nn->nfsd_serv->sv_nrthreads);

	avail = clamp_t(unsigned long, avail, slotsize,
			total_avail/scale_factor);
	num = min_t(int, num, avail / slotsize);
	num = max_t(int, num, 1);
	nfsd_drc_mem_used += num * slotsize;
	spin_unlock(&nfsd_drc_lock);

	return num;
}

static void nfsd4_put_drc_mem(struct nfsd4_channel_attrs *ca)
{
	int slotsize = slot_bytes(ca);

	spin_lock(&nfsd_drc_lock);
	nfsd_drc_mem_used -= slotsize * ca->maxreqs;
	spin_unlock(&nfsd_drc_lock);
}

static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fattrs,
					   struct nfsd4_channel_attrs *battrs)
{
	int numslots = fattrs->maxreqs;
	int slotsize = slot_bytes(fattrs);
	struct nfsd4_session *new;
	int mem, i;

	BUILD_BUG_ON(NFSD_MAX_SLOTS_PER_SESSION * sizeof(struct nfsd4_slot *)
			+ sizeof(struct nfsd4_session) > PAGE_SIZE);
	mem = numslots * sizeof(struct nfsd4_slot *);

	new = kzalloc(sizeof(*new) + mem, GFP_KERNEL);
	if (!new)
		return NULL;
	/* allocate each struct nfsd4_slot and data cache in one piece */
	for (i = 0; i < numslots; i++) {
		new->se_slots[i] = kzalloc(slotsize, GFP_KERNEL);
		if (!new->se_slots[i])
			goto out_free;
	}

	memcpy(&new->se_fchannel, fattrs, sizeof(struct nfsd4_channel_attrs));
	memcpy(&new->se_bchannel, battrs, sizeof(struct nfsd4_channel_attrs));

	return new;
out_free:
	while (i--)
		kfree(new->se_slots[i]);
	kfree(new);
	return NULL;
}

static void free_conn(struct nfsd4_conn *c)
{
	svc_xprt_put(c->cn_xprt);
	kfree(c);
}

static void nfsd4_conn_lost(struct svc_xpt_user *u)
{
	struct nfsd4_conn *c = container_of(u, struct nfsd4_conn, cn_xpt_user);
	struct nfs4_client *clp = c->cn_session->se_client;

	trace_nfsd_cb_lost(clp);

	spin_lock(&clp->cl_lock);
	if (!list_empty(&c->cn_persession)) {
		list_del(&c->cn_persession);
		free_conn(c);
	}
	nfsd4_probe_callback(clp);
	spin_unlock(&clp->cl_lock);
}

static struct nfsd4_conn *alloc_conn(struct svc_rqst *rqstp, u32 flags)
{
	struct nfsd4_conn *conn;

	conn = kmalloc(sizeof(struct nfsd4_conn), GFP_KERNEL);
	if (!conn)
		return NULL;
	svc_xprt_get(rqstp->rq_xprt);
	conn->cn_xprt = rqstp->rq_xprt;
	conn->cn_flags = flags;
	INIT_LIST_HEAD(&conn->cn_xpt_user.list);
	return conn;
}

static void __nfsd4_hash_conn(struct nfsd4_conn *conn, struct nfsd4_session *ses)
{
	conn->cn_session = ses;
	list_add(&conn->cn_persession, &ses->se_conns);
}

static void nfsd4_hash_conn(struct nfsd4_conn *conn, struct nfsd4_session *ses)
{
	struct nfs4_client *clp = ses->se_client;

	spin_lock(&clp->cl_lock);
	__nfsd4_hash_conn(conn, ses);
	spin_unlock(&clp->cl_lock);
}

static int nfsd4_register_conn(struct nfsd4_conn *conn)
{
	conn->cn_xpt_user.callback = nfsd4_conn_lost;
	return register_xpt_user(conn->cn_xprt, &conn->cn_xpt_user);
}

static void nfsd4_init_conn(struct svc_rqst *rqstp, struct nfsd4_conn *conn, struct nfsd4_session *ses)
{
	int ret;

	nfsd4_hash_conn(conn, ses);
	ret = nfsd4_register_conn(conn);
	if (ret)
		/* oops; xprt is already down: */
		nfsd4_conn_lost(&conn->cn_xpt_user);
	/* We may have gained or lost a callback channel: */
	nfsd4_probe_callback_sync(ses->se_client);
}

static struct nfsd4_conn *alloc_conn_from_crses(struct svc_rqst *rqstp, struct nfsd4_create_session *cses)
{
	u32 dir = NFS4_CDFC4_FORE;

	if (cses->flags & SESSION4_BACK_CHAN)
		dir |= NFS4_CDFC4_BACK;
	return alloc_conn(rqstp, dir);
}

/* must be called under client_lock */
static void nfsd4_del_conns(struct nfsd4_session *s)
{
	struct nfs4_client *clp = s->se_client;
	struct nfsd4_conn *c;

	spin_lock(&clp->cl_lock);
	while (!list_empty(&s->se_conns)) {
		c = list_first_entry(&s->se_conns, struct nfsd4_conn, cn_persession);
		list_del_init(&c->cn_persession);
		spin_unlock(&clp->cl_lock);

		unregister_xpt_user(c->cn_xprt, &c->cn_xpt_user);
		free_conn(c);

		spin_lock(&clp->cl_lock);
	}
	spin_unlock(&clp->cl_lock);
}

static void __free_session(struct nfsd4_session *ses)
{
	free_session_slots(ses);
	kfree(ses);
}

static void free_session(struct nfsd4_session *ses)
{
	nfsd4_del_conns(ses);
	nfsd4_put_drc_mem(&ses->se_fchannel);
	__free_session(ses);
}

static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, struct nfs4_client *clp, struct nfsd4_create_session *cses)
{
	int idx;
	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);

	new->se_client = clp;
	gen_sessionid(new);

	INIT_LIST_HEAD(&new->se_conns);

	new->se_cb_seq_nr = 1;
	new->se_flags = cses->flags;
	new->se_cb_prog = cses->callback_prog;
	new->se_cb_sec = cses->cb_sec;
	atomic_set(&new->se_ref, 0);
	idx = hash_sessionid(&new->se_sessionid);
	list_add(&new->se_hash, &nn->sessionid_hashtbl[idx]);
	spin_lock(&clp->cl_lock);
	list_add(&new->se_perclnt, &clp->cl_sessions);
	spin_unlock(&clp->cl_lock);

	{
		struct sockaddr *sa = svc_addr(rqstp);
		/*
		 * This is a little silly; with sessions there's no real
		 * use for the callback address.  Use the peer address
		 * as a reasonable default for now, but consider fixing
		 * the rpc client not to require an address in the
		 * future:
		 */
		rpc_copy_addr((struct sockaddr *)&clp->cl_cb_conn.cb_addr, sa);
		clp->cl_cb_conn.cb_addrlen = svc_addr_len(sa);
	}
}

/* caller must hold client_lock */
static struct nfsd4_session *
__find_in_sessionid_hashtbl(struct nfs4_sessionid *sessionid, struct net *net)
{
	struct nfsd4_session *elem;
	int idx;
	struct nfsd_net *nn = net_generic(net, nfsd_net_id);

	lockdep_assert_held(&nn->client_lock);

	dump_sessionid(__func__, sessionid);
	idx = hash_sessionid(sessionid);
	/* Search in the appropriate list */
	list_for_each_entry(elem, &nn->sessionid_hashtbl[idx], se_hash) {
		if (!memcmp(elem->se_sessionid.data, sessionid->data,
			    NFS4_MAX_SESSIONID_LEN)) {
			return elem;
		}
	}

	dprintk("%s: session not found\n", __func__);
	return NULL;
}

static struct nfsd4_session *
find_in_sessionid_hashtbl(struct nfs4_sessionid *sessionid, struct net *net,
		__be32 *ret)
{
	struct nfsd4_session *session;
	__be32 status = nfserr_badsession;

	session = __find_in_sessionid_hashtbl(sessionid, net);
	if (!session)
		goto out;
	status = nfsd4_get_session_locked(session);
	if (status)
		session = NULL;
out:
	*ret = status;
	return session;
}

/* caller must hold client_lock */
static void
unhash_session(struct nfsd4_session *ses)
{
	struct nfs4_client *clp = ses->se_client;
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);

	lockdep_assert_held(&nn->client_lock);

	list_del(&ses->se_hash);
	spin_lock(&ses->se_client->cl_lock);
	list_del(&ses->se_perclnt);
	spin_unlock(&ses->se_client->cl_lock);
}

/* SETCLIENTID and SETCLIENTID_CONFIRM Helper functions */
static int
STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn)
{
	/*
	 * We're assuming the clid was not given out from a boot
	 * precisely 2^32 (about 136 years) before this one.  That seems
	 * a safe assumption:
	 */
	if (clid->cl_boot == (u32)nn->boot_time)
		return 0;
	trace_nfsd_clid_stale(clid);
	return 1;
}

/* 
 * XXX Should we use a slab cache ?
 * This type of memory management is somewhat inefficient, but we use it
 * anyway since SETCLIENTID is not a common operation.
 */
static struct nfs4_client *alloc_client(struct xdr_netobj name)
{
	struct nfs4_client *clp;
	int i;

	clp = kmem_cache_zalloc(client_slab, GFP_KERNEL);
	if (clp == NULL)
		return NULL;
	xdr_netobj_dup(&clp->cl_name, &name, GFP_KERNEL);
	if (clp->cl_name.data == NULL)
		goto err_no_name;
	clp->cl_ownerstr_hashtbl = kmalloc_array(OWNER_HASH_SIZE,
						 sizeof(struct list_head),
						 GFP_KERNEL);
	if (!clp->cl_ownerstr_hashtbl)
		goto err_no_hashtbl;
	for (i = 0; i < OWNER_HASH_SIZE; i++)
		INIT_LIST_HEAD(&clp->cl_ownerstr_hashtbl[i]);
	INIT_LIST_HEAD(&clp->cl_sessions);
	idr_init(&clp->cl_stateids);
	atomic_set(&clp->cl_rpc_users, 0);
	clp->cl_cb_state = NFSD4_CB_UNKNOWN;
	INIT_LIST_HEAD(&clp->cl_idhash);
	INIT_LIST_HEAD(&clp->cl_openowners);
	INIT_LIST_HEAD(&clp->cl_delegations);
	INIT_LIST_HEAD(&clp->cl_lru);
	INIT_LIST_HEAD(&clp->cl_revoked);
#ifdef CONFIG_NFSD_PNFS
	INIT_LIST_HEAD(&clp->cl_lo_states);
#endif
	INIT_LIST_HEAD(&clp->async_copies);
	spin_lock_init(&clp->async_lock);
	spin_lock_init(&clp->cl_lock);
	rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table");
	return clp;
err_no_hashtbl:
	kfree(clp->cl_name.data);
err_no_name:
	kmem_cache_free(client_slab, clp);
	return NULL;
}

static void __free_client(struct kref *k)
{
	struct nfsdfs_client *c = container_of(k, struct nfsdfs_client, cl_ref);
	struct nfs4_client *clp = container_of(c, struct nfs4_client, cl_nfsdfs);

	free_svc_cred(&clp->cl_cred);
	kfree(clp->cl_ownerstr_hashtbl);
	kfree(clp->cl_name.data);
	kfree(clp->cl_nii_domain.data);
	kfree(clp->cl_nii_name.data);
	idr_destroy(&clp->cl_stateids);
	kmem_cache_free(client_slab, clp);
}

static void drop_client(struct nfs4_client *clp)
{
	kref_put(&clp->cl_nfsdfs.cl_ref, __free_client);
}

static void
free_client(struct nfs4_client *clp)
{
	while (!list_empty(&clp->cl_sessions)) {
		struct nfsd4_session *ses;
		ses = list_entry(clp->cl_sessions.next, struct nfsd4_session,
				se_perclnt);
		list_del(&ses->se_perclnt);
		WARN_ON_ONCE(atomic_read(&ses->se_ref));
		free_session(ses);
	}
	rpc_destroy_wait_queue(&clp->cl_cb_waitq);
	if (clp->cl_nfsd_dentry) {
		nfsd_client_rmdir(clp->cl_nfsd_dentry);
		clp->cl_nfsd_dentry = NULL;
		wake_up_all(&expiry_wq);
	}
	drop_client(clp);
}

/* must be called under the client_lock */
static void
unhash_client_locked(struct nfs4_client *clp)
{
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
	struct nfsd4_session *ses;

	lockdep_assert_held(&nn->client_lock);

	/* Mark the client as expired! */
	clp->cl_time = 0;
	/* Make it invisible */
	if (!list_empty(&clp->cl_idhash)) {
		list_del_init(&clp->cl_idhash);
		if (test_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags))
			rb_erase(&clp->cl_namenode, &nn->conf_name_tree);
		else
			rb_erase(&clp->cl_namenode, &nn->unconf_name_tree);
	}
	list_del_init(&clp->cl_lru);
	spin_lock(&clp->cl_lock);
	list_for_each_entry(ses, &clp->cl_sessions, se_perclnt)
		list_del_init(&ses->se_hash);
	spin_unlock(&clp->cl_lock);
}

static void
unhash_client(struct nfs4_client *clp)
{
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);

	spin_lock(&nn->client_lock);
	unhash_client_locked(clp);
	spin_unlock(&nn->client_lock);
}

static __be32 mark_client_expired_locked(struct nfs4_client *clp)
{
	if (atomic_read(&clp->cl_rpc_users))
		return nfserr_jukebox;
	unhash_client_locked(clp);
	return nfs_ok;
}

static void
__destroy_client(struct nfs4_client *clp)
{
	int i;
	struct nfs4_openowner *oo;
	struct nfs4_delegation *dp;
	struct list_head reaplist;

	INIT_LIST_HEAD(&reaplist);
	spin_lock(&state_lock);
	while (!list_empty(&clp->cl_delegations)) {
		dp = list_entry(clp->cl_delegations.next, struct nfs4_delegation, dl_perclnt);
		WARN_ON(!unhash_delegation_locked(dp));
		list_add(&dp->dl_recall_lru, &reaplist);
	}
	spin_unlock(&state_lock);
	while (!list_empty(&reaplist)) {
		dp = list_entry(reaplist.next, struct nfs4_delegation, dl_recall_lru);
		list_del_init(&dp->dl_recall_lru);
		destroy_unhashed_deleg(dp);
	}
	while (!list_empty(&clp->cl_revoked)) {
		dp = list_entry(clp->cl_revoked.next, struct nfs4_delegation, dl_recall_lru);
		list_del_init(&dp->dl_recall_lru);
		nfs4_put_stid(&dp->dl_stid);
	}
	while (!list_empty(&clp->cl_openowners)) {
		oo = list_entry(clp->cl_openowners.next, struct nfs4_openowner, oo_perclient);
		nfs4_get_stateowner(&oo->oo_owner);
		release_openowner(oo);
	}
	for (i = 0; i < OWNER_HASH_SIZE; i++) {
		struct nfs4_stateowner *so, *tmp;

		list_for_each_entry_safe(so, tmp, &clp->cl_ownerstr_hashtbl[i],
					 so_strhash) {
			/* Should be no openowners at this point */
			WARN_ON_ONCE(so->so_is_open_owner);
			remove_blocked_locks(lockowner(so));
		}
	}
	nfsd4_return_all_client_layouts(clp);
	nfsd4_shutdown_copy(clp);
	nfsd4_shutdown_callback(clp);
	if (clp->cl_cb_conn.cb_xprt)
		svc_xprt_put(clp->cl_cb_conn.cb_xprt);
	free_client(clp);
	wake_up_all(&expiry_wq);
}

static void
destroy_client(struct nfs4_client *clp)
{
	unhash_client(clp);
	__destroy_client(clp);
}

static void inc_reclaim_complete(struct nfs4_client *clp)
{
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);

	if (!nn->track_reclaim_completes)
		return;
	if (!nfsd4_find_reclaim_client(clp->cl_name, nn))
		return;
	if (atomic_inc_return(&nn->nr_reclaim_complete) ==
			nn->reclaim_str_hashtbl_size) {
		printk(KERN_INFO "NFSD: all clients done reclaiming, ending NFSv4 grace period (net %x)\n",
				clp->net->ns.inum);
		nfsd4_end_grace(nn);
	}
}

static void expire_client(struct nfs4_client *clp)
{
	unhash_client(clp);
	nfsd4_client_record_remove(clp);
	__destroy_client(clp);
}

static void copy_verf(struct nfs4_client *target, nfs4_verifier *source)
{
	memcpy(target->cl_verifier.data, source->data,
			sizeof(target->cl_verifier.data));
}

static void copy_clid(struct nfs4_client *target, struct nfs4_client *source)
{
	target->cl_clientid.cl_boot = source->cl_clientid.cl_boot; 
	target->cl_clientid.cl_id = source->cl_clientid.cl_id; 
}

static int copy_cred(struct svc_cred *target, struct svc_cred *source)
{
	target->cr_principal = kstrdup(source->cr_principal, GFP_KERNEL);
	target->cr_raw_principal = kstrdup(source->cr_raw_principal,
								GFP_KERNEL);
	target->cr_targ_princ = kstrdup(source->cr_targ_princ, GFP_KERNEL);
	if ((source->cr_principal && !target->cr_principal) ||
	    (source->cr_raw_principal && !target->cr_raw_principal) ||
	    (source->cr_targ_princ && !target->cr_targ_princ))
		return -ENOMEM;

	target->cr_flavor = source->cr_flavor;
	target->cr_uid = source->cr_uid;
	target->cr_gid = source->cr_gid;
	target->cr_group_info = source->cr_group_info;
	get_group_info(target->cr_group_info);
	target->cr_gss_mech = source->cr_gss_mech;
	if (source->cr_gss_mech)
		gss_mech_get(source->cr_gss_mech);
	return 0;
}

static int
compare_blob(const struct xdr_netobj *o1, const struct xdr_netobj *o2)
{
	if (o1->len < o2->len)
		return -1;
	if (o1->len > o2->len)
		return 1;
	return memcmp(o1->data, o2->data, o1->len);
}

static int
same_verf(nfs4_verifier *v1, nfs4_verifier *v2)
{
	return 0 == memcmp(v1->data, v2->data, sizeof(v1->data));
}

static int
same_clid(clientid_t *cl1, clientid_t *cl2)
{
	return (cl1->cl_boot == cl2->cl_boot) && (cl1->cl_id == cl2->cl_id);
}

static bool groups_equal(struct group_info *g1, struct group_info *g2)
{
	int i;

	if (g1->ngroups != g2->ngroups)
		return false;
	for (i=0; i<g1->ngroups; i++)
		if (!gid_eq(g1->gid[i], g2->gid[i]))
			return false;
	return true;
}

/*
 * RFC 3530 language requires clid_inuse be returned when the
 * "principal" associated with a requests differs from that previously
 * used.  We use uid, gid's, and gss principal string as our best
 * approximation.  We also don't want to allow non-gss use of a client
 * established using gss: in theory cr_principal should catch that
 * change, but in practice cr_principal can be null even in the gss case
 * since gssd doesn't always pass down a principal string.
 */
static bool is_gss_cred(struct svc_cred *cr)
{
	/* Is cr_flavor one of the gss "pseudoflavors"?: */
	return (cr->cr_flavor > RPC_AUTH_MAXFLAVOR);
}


static bool
same_creds(struct svc_cred *cr1, struct svc_cred *cr2)
{
	if ((is_gss_cred(cr1) != is_gss_cred(cr2))
		|| (!uid_eq(cr1->cr_uid, cr2->cr_uid))
		|| (!gid_eq(cr1->cr_gid, cr2->cr_gid))
		|| !groups_equal(cr1->cr_group_info, cr2->cr_group_info))
		return false;
	/* XXX: check that cr_targ_princ fields match ? */
	if (cr1->cr_principal == cr2->cr_principal)
		return true;
	if (!cr1->cr_principal || !cr2->cr_principal)
		return false;
	return 0 == strcmp(cr1->cr_principal, cr2->cr_principal);
}

static bool svc_rqst_integrity_protected(struct svc_rqst *rqstp)
{
	struct svc_cred *cr = &rqstp->rq_cred;
	u32 service;

	if (!cr->cr_gss_mech)
		return false;
	service = gss_pseudoflavor_to_service(cr->cr_gss_mech, cr->cr_flavor);
	return service == RPC_GSS_SVC_INTEGRITY ||
	       service == RPC_GSS_SVC_PRIVACY;
}

bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp)
{
	struct svc_cred *cr = &rqstp->rq_cred;

	if (!cl->cl_mach_cred)
		return true;
	if (cl->cl_cred.cr_gss_mech != cr->cr_gss_mech)
		return false;
	if (!svc_rqst_integrity_protected(rqstp))
		return false;
	if (cl->cl_cred.cr_raw_principal)
		return 0 == strcmp(cl->cl_cred.cr_raw_principal,
						cr->cr_raw_principal);
	if (!cr->cr_principal)
		return false;
	return 0 == strcmp(cl->cl_cred.cr_principal, cr->cr_principal);
}

static void gen_confirm(struct nfs4_client *clp, struct nfsd_net *nn)
{
	__be32 verf[2];

	/*
	 * This is opaque to client, so no need to byte-swap. Use
	 * __force to keep sparse happy
	 */
	verf[0] = (__force __be32)(u32)ktime_get_real_seconds();
	verf[1] = (__force __be32)nn->clverifier_counter++;
	memcpy(clp->cl_confirm.data, verf, sizeof(clp->cl_confirm.data));
}

static void gen_clid(struct nfs4_client *clp, struct nfsd_net *nn)
{
	clp->cl_clientid.cl_boot = (u32)nn->boot_time;
	clp->cl_clientid.cl_id = nn->clientid_counter++;
	gen_confirm(clp, nn);
}

static struct nfs4_stid *
find_stateid_locked(struct nfs4_client *cl, stateid_t *t)
{
	struct nfs4_stid *ret;

	ret = idr_find(&cl->cl_stateids, t->si_opaque.so_id);
	if (!ret || !ret->sc_type)
		return NULL;
	return ret;
}

static struct nfs4_stid *
find_stateid_by_type(struct nfs4_client *cl, stateid_t *t, char typemask)
{
	struct nfs4_stid *s;

	spin_lock(&cl->cl_lock);
	s = find_stateid_locked(cl, t);
	if (s != NULL) {
		if (typemask & s->sc_type)
			refcount_inc(&s->sc_count);
		else
			s = NULL;
	}
	spin_unlock(&cl->cl_lock);
	return s;
}

static struct nfs4_client *get_nfsdfs_clp(struct inode *inode)
{
	struct nfsdfs_client *nc;
	nc = get_nfsdfs_client(inode);
	if (!nc)
		return NULL;
	return container_of(nc, struct nfs4_client, cl_nfsdfs);
}

static void seq_quote_mem(struct seq_file *m, char *data, int len)
{
	seq_printf(m, "\"");
	seq_escape_mem(m, data, len, ESCAPE_HEX | ESCAPE_NAP | ESCAPE_APPEND, "\"\\");
	seq_printf(m, "\"");
}

static const char *cb_state2str(int state)
{
	switch (state) {
	case NFSD4_CB_UP:
		return "UP";
	case NFSD4_CB_UNKNOWN:
		return "UNKNOWN";
	case NFSD4_CB_DOWN:
		return "DOWN";
	case NFSD4_CB_FAULT:
		return "FAULT";
	}
	return "UNDEFINED";
}

static int client_info_show(struct seq_file *m, void *v)
{
	struct inode *inode = m->private;
	struct nfs4_client *clp;
	u64 clid;

	clp = get_nfsdfs_clp(inode);
	if (!clp)
		return -ENXIO;
	memcpy(&clid, &clp->cl_clientid, sizeof(clid));
	seq_printf(m, "clientid: 0x%llx\n", clid);
	seq_printf(m, "address: \"%pISpc\"\n", (struct sockaddr *)&clp->cl_addr);
	if (test_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags))
		seq_puts(m, "status: confirmed\n");
	else
		seq_puts(m, "status: unconfirmed\n");
	seq_printf(m, "name: ");
	seq_quote_mem(m, clp->cl_name.data, clp->cl_name.len);
	seq_printf(m, "\nminor version: %d\n", clp->cl_minorversion);
	if (clp->cl_nii_domain.data) {
		seq_printf(m, "Implementation domain: ");
		seq_quote_mem(m, clp->cl_nii_domain.data,
					clp->cl_nii_domain.len);
		seq_printf(m, "\nImplementation name: ");
		seq_quote_mem(m, clp->cl_nii_name.data, clp->cl_nii_name.len);
		seq_printf(m, "\nImplementation time: [%lld, %ld]\n",
			clp->cl_nii_time.tv_sec, clp->cl_nii_time.tv_nsec);
	}
	seq_printf(m, "callback state: %s\n", cb_state2str(clp->cl_cb_state));
	seq_printf(m, "callback address: %pISpc\n", &clp->cl_cb_conn.cb_addr);
	drop_client(clp);

	return 0;
}

static int client_info_open(struct inode *inode, struct file *file)
{
	return single_open(file, client_info_show, inode);
}

static const struct file_operations client_info_fops = {
	.open		= client_info_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= single_release,
};

static void *states_start(struct seq_file *s, loff_t *pos)
	__acquires(&clp->cl_lock)
{
	struct nfs4_client *clp = s->private;
	unsigned long id = *pos;
	void *ret;

	spin_lock(&clp->cl_lock);
	ret = idr_get_next_ul(&clp->cl_stateids, &id);
	*pos = id;
	return ret;
}

static void *states_next(struct seq_file *s, void *v, loff_t *pos)
{
	struct nfs4_client *clp = s->private;
	unsigned long id = *pos;
	void *ret;

	id = *pos;
	id++;
	ret = idr_get_next_ul(&clp->cl_stateids, &id);
	*pos = id;
	return ret;
}

static void states_stop(struct seq_file *s, void *v)
	__releases(&clp->cl_lock)
{
	struct nfs4_client *clp = s->private;

	spin_unlock(&clp->cl_lock);
}

static void nfs4_show_fname(struct seq_file *s, struct nfsd_file *f)
{
         seq_printf(s, "filename: \"%pD2\"", f->nf_file);
}

static void nfs4_show_superblock(struct seq_file *s, struct nfsd_file *f)
{
	struct inode *inode = f->nf_inode;

	seq_printf(s, "superblock: \"%02x:%02x:%ld\"",
					MAJOR(inode->i_sb->s_dev),
					 MINOR(inode->i_sb->s_dev),
					 inode->i_ino);
}

static void nfs4_show_owner(struct seq_file *s, struct nfs4_stateowner *oo)
{
	seq_printf(s, "owner: ");
	seq_quote_mem(s, oo->so_owner.data, oo->so_owner.len);
}

static void nfs4_show_stateid(struct seq_file *s, stateid_t *stid)
{
	seq_printf(s, "0x%.8x", stid->si_generation);
	seq_printf(s, "%12phN", &stid->si_opaque);
}

static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st)
{
	struct nfs4_ol_stateid *ols;
	struct nfs4_file *nf;
	struct nfsd_file *file;
	struct nfs4_stateowner *oo;
	unsigned int access, deny;

	if (st->sc_type != NFS4_OPEN_STID && st->sc_type != NFS4_LOCK_STID)
		return 0; /* XXX: or SEQ_SKIP? */
	ols = openlockstateid(st);
	oo = ols->st_stateowner;
	nf = st->sc_file;
	file = find_any_file(nf);
	if (!file)
		return 0;

	seq_printf(s, "- ");
	nfs4_show_stateid(s, &st->sc_stateid);
	seq_printf(s, ": { type: open, ");

	access = bmap_to_share_mode(ols->st_access_bmap);
	deny   = bmap_to_share_mode(ols->st_deny_bmap);

	seq_printf(s, "access: %s%s, ",
		access & NFS4_SHARE_ACCESS_READ ? "r" : "-",
		access & NFS4_SHARE_ACCESS_WRITE ? "w" : "-");
	seq_printf(s, "deny: %s%s, ",
		deny & NFS4_SHARE_ACCESS_READ ? "r" : "-",
		deny & NFS4_SHARE_ACCESS_WRITE ? "w" : "-");

	nfs4_show_superblock(s, file);
	seq_printf(s, ", ");
	nfs4_show_fname(s, file);
	seq_printf(s, ", ");
	nfs4_show_owner(s, oo);
	seq_printf(s, " }\n");
	nfsd_file_put(file);

	return 0;
}

static int nfs4_show_lock(struct seq_file *s, struct nfs4_stid *st)
{
	struct nfs4_ol_stateid *ols;
	struct nfs4_file *nf;
	struct nfsd_file *file;
	struct nfs4_stateowner *oo;

	ols = openlockstateid(st);
	oo = ols->st_stateowner;
	nf = st->sc_file;
	file = find_any_file(nf);
	if (!file)
		return 0;

	seq_printf(s, "- ");
	nfs4_show_stateid(s, &st->sc_stateid);
	seq_printf(s, ": { type: lock, ");

	/*
	 * Note: a lock stateid isn't really the same thing as a lock,
	 * it's the locking state held by one owner on a file, and there
	 * may be multiple (or no) lock ranges associated with it.
	 * (Same for the matter is true of open stateids.)
	 */

	nfs4_show_superblock(s, file);
	/* XXX: open stateid? */
	seq_printf(s, ", ");
	nfs4_show_fname(s, file);
	seq_printf(s, ", ");
	nfs4_show_owner(s, oo);
	seq_printf(s, " }\n");
	nfsd_file_put(file);

	return 0;
}

static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st)
{
	struct nfs4_delegation *ds;
	struct nfs4_file *nf;
	struct nfsd_file *file;

	ds = delegstateid(st);
	nf = st->sc_file;
	file = find_deleg_file(nf);
	if (!file)
		return 0;

	seq_printf(s, "- ");
	nfs4_show_stateid(s, &st->sc_stateid);
	seq_printf(s, ": { type: deleg, ");

	/* Kinda dead code as long as we only support read delegs: */
	seq_printf(s, "access: %s, ",
		ds->dl_type == NFS4_OPEN_DELEGATE_READ ? "r" : "w");

	/* XXX: lease time, whether it's being recalled. */

	nfs4_show_superblock(s, file);
	seq_printf(s, ", ");
	nfs4_show_fname(s, file);
	seq_printf(s, " }\n");
	nfsd_file_put(file);

	return 0;
}

static int nfs4_show_layout(struct seq_file *s, struct nfs4_stid *st)
{
	struct nfs4_layout_stateid *ls;
	struct nfsd_file *file;

	ls = container_of(st, struct nfs4_layout_stateid, ls_stid);
	file = ls->ls_file;

	seq_printf(s, "- ");
	nfs4_show_stateid(s, &st->sc_stateid);
	seq_printf(s, ": { type: layout, ");

	/* XXX: What else would be useful? */

	nfs4_show_superblock(s, file);
	seq_printf(s, ", ");
	nfs4_show_fname(s, file);
	seq_printf(s, " }\n");

	return 0;
}

static int states_show(struct seq_file *s, void *v)
{
	struct nfs4_stid *st = v;

	switch (st->sc_type) {
	case NFS4_OPEN_STID:
		return nfs4_show_open(s, st);
	case NFS4_LOCK_STID:
		return nfs4_show_lock(s, st);
	case NFS4_DELEG_STID:
		return nfs4_show_deleg(s, st);
	case NFS4_LAYOUT_STID:
		return nfs4_show_layout(s, st);
	default:
		return 0; /* XXX: or SEQ_SKIP? */
	}
	/* XXX: copy stateids? */
}

static struct seq_operations states_seq_ops = {
	.start = states_start,
	.next = states_next,
	.stop = states_stop,
	.show = states_show
};

static int client_states_open(struct inode *inode, struct file *file)
{
	struct seq_file *s;
	struct nfs4_client *clp;
	int ret;

	clp = get_nfsdfs_clp(inode);
	if (!clp)
		return -ENXIO;

	ret = seq_open(file, &states_seq_ops);
	if (ret)
		return ret;
	s = file->private_data;
	s->private = clp;
	return 0;
}

static int client_opens_release(struct inode *inode, struct file *file)
{
	struct seq_file *m = file->private_data;
	struct nfs4_client *clp = m->private;

	/* XXX: alternatively, we could get/drop in seq start/stop */
	drop_client(clp);
	return 0;
}

static const struct file_operations client_states_fops = {
	.open		= client_states_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= client_opens_release,
};

/*
 * Normally we refuse to destroy clients that are in use, but here the
 * administrator is telling us to just do it.  We also want to wait
 * so the caller has a guarantee that the client's locks are gone by
 * the time the write returns:
 */
static void force_expire_client(struct nfs4_client *clp)
{
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
	bool already_expired;

	trace_nfsd_clid_admin_expired(&clp->cl_clientid);

	spin_lock(&nn->client_lock);
	clp->cl_time = 0;
	spin_unlock(&nn->client_lock);

	wait_event(expiry_wq, atomic_read(&clp->cl_rpc_users) == 0);
	spin_lock(&nn->client_lock);
	already_expired = list_empty(&clp->cl_lru);
	if (!already_expired)
		unhash_client_locked(clp);
	spin_unlock(&nn->client_lock);

	if (!already_expired)
		expire_client(clp);
	else
		wait_event(expiry_wq, clp->cl_nfsd_dentry == NULL);
}

static ssize_t client_ctl_write(struct file *file, const char __user *buf,
				   size_t size, loff_t *pos)
{
	char *data;
	struct nfs4_client *clp;

	data = simple_transaction_get(file, buf, size);
	if (IS_ERR(data))
		return PTR_ERR(data);
	if (size != 7 || 0 != memcmp(data, "expire\n", 7))
		return -EINVAL;
	clp = get_nfsdfs_clp(file_inode(file));
	if (!clp)
		return -ENXIO;
	force_expire_client(clp);
	drop_client(clp);
	return 7;
}

static const struct file_operations client_ctl_fops = {
	.write		= client_ctl_write,
	.release	= simple_transaction_release,
};

static const struct tree_descr client_files[] = {
	[0] = {"info", &client_info_fops, S_IRUSR},
	[1] = {"states", &client_states_fops, S_IRUSR},
	[2] = {"ctl", &client_ctl_fops, S_IWUSR},
	[3] = {""},
};

static struct nfs4_client *create_client(struct xdr_netobj name,
		struct svc_rqst *rqstp, nfs4_verifier *verf)
{
	struct nfs4_client *clp;
	struct sockaddr *sa = svc_addr(rqstp);
	int ret;
	struct net *net = SVC_NET(rqstp);
	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
	struct dentry *dentries[ARRAY_SIZE(client_files)];

	clp = alloc_client(name);
	if (clp == NULL)
		return NULL;

	ret = copy_cred(&clp->cl_cred, &rqstp->rq_cred);
	if (ret) {
		free_client(clp);
		return NULL;
	}
	gen_clid(clp, nn);
	kref_init(&clp->cl_nfsdfs.cl_ref);
	nfsd4_init_cb(&clp->cl_cb_null, clp, NULL, NFSPROC4_CLNT_CB_NULL);
	clp->cl_time = ktime_get_boottime_seconds();
	clear_bit(0, &clp->cl_cb_slot_busy);
	copy_verf(clp, verf);
	memcpy(&clp->cl_addr, sa, sizeof(struct sockaddr_storage));
	clp->cl_cb_session = NULL;
	clp->net = net;
	clp->cl_nfsd_dentry = nfsd_client_mkdir(
		nn, &clp->cl_nfsdfs,
		clp->cl_clientid.cl_id - nn->clientid_base,
		client_files, dentries);
	clp->cl_nfsd_info_dentry = dentries[0];
	if (!clp->cl_nfsd_dentry) {
		free_client(clp);
		return NULL;
	}
	return clp;
}

static void
add_clp_to_name_tree(struct nfs4_client *new_clp, struct rb_root *root)
{
	struct rb_node **new = &(root->rb_node), *parent = NULL;
	struct nfs4_client *clp;

	while (*new) {
		clp = rb_entry(*new, struct nfs4_client, cl_namenode);
		parent = *new;

		if (compare_blob(&clp->cl_name, &new_clp->cl_name) > 0)
			new = &((*new)->rb_left);
		else
			new = &((*new)->rb_right);
	}

	rb_link_node(&new_clp->cl_namenode, parent, new);
	rb_insert_color(&new_clp->cl_namenode, root);
}

static struct nfs4_client *
find_clp_in_name_tree(struct xdr_netobj *name, struct rb_root *root)
{
	int cmp;
	struct rb_node *node = root->rb_node;
	struct nfs4_client *clp;

	while (node) {
		clp = rb_entry(node, struct nfs4_client, cl_namenode);
		cmp = compare_blob(&clp->cl_name, name);
		if (cmp > 0)
			node = node->rb_left;
		else if (cmp < 0)
			node = node->rb_right;
		else
			return clp;
	}
	return NULL;
}

static void
add_to_unconfirmed(struct nfs4_client *clp)
{
	unsigned int idhashval;
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);

	lockdep_assert_held(&nn->client_lock);

	clear_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags);
	add_clp_to_name_tree(clp, &nn->unconf_name_tree);
	idhashval = clientid_hashval(clp->cl_clientid.cl_id);
	list_add(&clp->cl_idhash, &nn->unconf_id_hashtbl[idhashval]);
	renew_client_locked(clp);
}

static void
move_to_confirmed(struct nfs4_client *clp)
{
	unsigned int idhashval = clientid_hashval(clp->cl_clientid.cl_id);
	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);

	lockdep_assert_held(&nn->client_lock);

	list_move(&clp->cl_idhash, &nn->conf_id_hashtbl[idhashval]);
	rb_erase(&clp->cl_namenode, &nn->unconf_name_tree);
	add_clp_to_name_tree(clp, &nn->conf_name_tree);
	set_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags);
	trace_nfsd_clid_confirmed(&clp->cl_clientid);
	renew_client_locked(clp);
}

static struct nfs4_client *
find_client_in_id_table(struct list_head *tbl, clientid_t *clid, bool sessions)
{
	struct nfs4_client *clp;
	unsigned int idhashval = clientid_hashval(clid->cl_id);

	list_for_each_entry(clp, &tbl[idhashval], cl_idhash) {
		if (same_clid(&clp->cl_clientid, clid)) {
			if ((bool)clp->cl_minorversion != sessions)
				return NULL;
			renew_client_locked(clp);
			return clp;
		}
	}
	return NULL;
}

static struct nfs4_client *
find_confirmed_client(clientid_t *clid, bool sessions, struct nfsd_net *nn)
{
	struct list_head *tbl = nn->conf_id_hashtbl;

	lockdep_assert_held(&nn->client_lock);
	return find_client_in_id_table(tbl, clid, sessions);
}

static struct nfs4_client *
find_unconfirmed_client(clientid_t *clid, bool sessions, struct nfsd_net *nn)
{
	struct list_head *tbl = nn->unconf_id_hashtbl;

	lockdep_assert_held(&nn->client_lock);
	return find_client_in_id_table(tbl, clid, sessions);
}

static bool clp_used_exchangeid(struct nfs4_client *clp)
{
	return clp->cl_exchange_flags != 0;
} 

static struct nfs4_client *
find_confirmed_client_by_name(struct xdr_netobj *name, struct nfsd_net *nn)
{
	lockdep_assert_held(&nn->client_lock);
	return find_clp_in_name_tree(name, &nn->conf_name_tree);
}

static struct nfs4_client *
find_unconfirmed_client_by_name(struct xdr_netobj *name, struct nfsd_net *nn)
{
	lockdep_assert_held(&nn->client_lock);
	return find_clp_in_name_tree(name, &nn->unconf_name_tree);
}

static void
gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, struct svc_rqst *rqstp)
{
	struct nfs4_cb_conn *conn = &clp->cl_cb_conn;
	struct sockaddr	*sa = svc_addr(rqstp);
	u32 scopeid = rpc_get_scope_id(sa);
	unsigned short expected_family;

	/* Currently, we only support tcp and tcp6 for the callback channel */
	if (se->se_callback_netid_len == 3 &&
	    !memcmp(se->se_callback_netid_val, "tcp", 3))
		expected_family = AF_INET;
	else if (se->se_callback_netid_len == 4 &&
		 !memcmp(se->se_callback_netid_val, "tcp6", 4))
		expected_family = AF_INET6;
	else
		goto out_err;

	conn->cb_addrlen = rpc_uaddr2sockaddr(clp->net, se->se_callback_addr_val,
					    se->se_callback_addr_len,
					    (struct sockaddr *)&conn->cb_addr,
					    sizeof(conn->cb_addr));

	if (!conn->cb_addrlen || conn->cb_addr.ss_family != expected_family)
		goto out_err;

	if (conn->cb_addr.ss_family == AF_INET6)
		((struct sockaddr_in6 *)&conn->cb_addr)->sin6_scope_id = scopeid;

	conn->cb_prog = se->se_callback_prog;
	conn->cb_ident = se->se_callback_ident;
	memcpy(&conn->cb_saddr, &rqstp->rq_daddr, rqstp->rq_daddrlen);
	trace_nfsd_cb_args(clp, conn);
	return;
out_err:
	conn->cb_addr.ss_family = AF_UNSPEC;
	conn->cb_addrlen = 0;
	trace_nfsd_cb_nodelegs(clp);
	return;
}

/*
 * Cache a reply. nfsd4_check_resp_size() has bounded the cache size.
 */
static void
nfsd4_store_cache_entry(struct nfsd4_compoundres *resp)
{
	struct xdr_buf *buf = resp->xdr->buf;
	struct nfsd4_slot *slot = resp->cstate.slot;
	unsigned int base;

	dprintk("--> %s slot %p\n", __func__, slot);

	slot->sl_flags |= NFSD4_SLOT_INITIALIZED;
	slot->sl_opcnt = resp->opcnt;
	slot->sl_status = resp->cstate.status;
	free_svc_cred(&slot->sl_cred);
	copy_cred(&slot->sl_cred, &resp->rqstp->rq_cred);

	if (!nfsd4_cache_this(resp)) {
		slot->sl_flags &= ~NFSD4_SLOT_CACHED;
		return;
	}
	slot->sl_flags |= NFSD4_SLOT_CACHED;

	base = resp->cstate.data_offset;
	slot->sl_datalen = buf->len - base;
	if (read_bytes_from_xdr_buf(buf, base, slot->sl_data, slot->sl_datalen))
		WARN(1, "%s: sessions DRC could not cache compound\n",
		     __func__);
	return;
}

/*
 * Encode the replay sequence operation from the slot values.
 * If cachethis is FALSE encode the uncached rep error on the next
 * operation which sets resp->p and increments resp->opcnt for
 * nfs4svc_encode_compoundres.
 *
 */
static __be32
nfsd4_enc_sequence_replay(struct nfsd4_compoundargs *args,
			  struct nfsd4_compoundres *resp)
{
	struct nfsd4_op *op;
	struct nfsd4_slot *slot = resp->cstate.slot;

	/* Encode the replayed sequence operation */
	op = &args->ops[resp->opcnt - 1];
	nfsd4_encode_operation(resp, op);

	if (slot->sl_flags & NFSD4_SLOT_CACHED)
		return op->status;
	if (args->opcnt == 1) {
		/*
		 * The original operation wasn't a solo sequence--we
		 * always cache those--so this retry must not match the
		 * original:
		 */
		op->status = nfserr_seq_false_retry;
	} else {
		op = &args->ops[resp->opcnt++];
		op->status = nfserr_retry_uncached_rep;
		nfsd4_encode_operation(resp, op);
	}
	return op->status;
}

/*
 * The sequence operation is not cached because we can use the slot and
 * session values.
 */
static __be32
nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
			 struct nfsd4_sequence *seq)
{
	struct nfsd4_slot *slot = resp->cstate.slot;
	struct xdr_stream *xdr = resp->xdr;
	__be32 *p;
	__be32 status;

	dprintk("--> %s slot %p\n", __func__, slot);

	status = nfsd4_enc_sequence_replay(resp->rqstp->rq_argp, resp);
	if (status)
		return status;

	p = xdr_reserve_space(xdr, slot->sl_datalen);
	if (!p) {
		WARN_ON_ONCE(1);
		return nfserr_serverfault;
	}
	xdr_encode_opaque_fixed(p, slot->sl_data, slot->sl_datalen);
	xdr_commit_encode(xdr);

	resp->opcnt = slot->sl_opcnt;
	return slot->sl_status;
}

/*
 * Set the exchange_id flags returned by the server.
 */
static void
nfsd4_set_ex_flags(struct nfs4_client *new, struct nfsd4_exchange_id *clid)
{
#ifdef CONFIG_NFSD_PNFS
	new->cl_exchange_flags |= EXCHGID4_FLAG_USE_PNFS_MDS;
#else
	new->cl_exchange_flags |= EXCHGID4_FLAG_USE_NON_PNFS;
#endif

	/* Referrals are supported, Migration is not. */
	new->cl_exchange_flags |= EXCHGID4_FLAG_SUPP_MOVED_REFER;

	/* set the wire flags to return to client. */
	clid->flags = new->cl_exchange_flags;
}

static bool client_has_openowners(struct nfs4_client *clp)
{
	struct nfs4_openowner *oo;

	list_for_each_entry(oo, &clp->cl_openowners, oo_perclient) {
		if (!list_empty(&oo->oo_owner.so_stateids))
			return true;
	}
	return false;
}

static bool client_has_state(struct nfs4_client *clp)
{
	return client_has_openowners(clp)
#ifdef CONFIG_NFSD_PNFS
		|| !list_empty(&clp->cl_lo_states)
#endif
		|| !list_empty(&clp->cl_delegations)
		|| !list_empty(&clp->cl_sessions)
		|| !list_empty(&clp->async_copies);
}

static __be32 copy_impl_id(struct nfs4_client *clp,