nfs4state.c

linux 内核源代码

/*
*  linux/fs/nfsd/nfs4state.c
*
*  Copyright (c) 2001 The Regents of the University of Michigan.
*  All rights reserved.
*
*  Kendrick Smith <[e-mail]>
*  Andy Adamson <[e-mail]>
*
*  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/param.h>
#include <linux/major.h>
#include <linux/slab.h>

#include <linux/sunrpc/svc.h>
#include <linux/nfsd/nfsd.h>
#include <linux/nfsd/cache.h>
#include <linux/mount.h>
#include <linux/workqueue.h>
#include <linux/smp_lock.h>
#include <linux/kthread.h>
#include <linux/nfs4.h>
#include <linux/nfsd/state.h>
#include <linux/nfsd/xdr4.h>
#include <linux/namei.h>
#include <linux/swap.h>
#include <linux/mutex.h>
#include <linux/lockd/bind.h>
#include <linux/module.h>

#define NFSDDBG_FACILITY                NFSDDBG_PROC

/* Globals */
static time_t lease_time = 90;     /* default lease time */
static time_t user_lease_time = 90;
static time_t boot_time;
static int in_grace = 1;
static u32 current_clientid = 1;
static u32 current_ownerid = 1;
static u32 current_fileid = 1;
static u32 current_delegid = 1;
static u32 nfs4_init;
static stateid_t zerostateid;             /* bits all 0 */
static stateid_t onestateid;              /* bits all 1 */

#define ZERO_STATEID(stateid) (!memcmp((stateid), &zerostateid, sizeof(stateid_t)))
#define ONE_STATEID(stateid)  (!memcmp((stateid), &onestateid, sizeof(stateid_t)))

/* forward declarations */
static struct nfs4_stateid * find_stateid(stateid_t *stid, int flags);
static struct nfs4_delegation * find_delegation_stateid(struct inode *ino, stateid_t *stid);
static void release_stateid_lockowners(struct nfs4_stateid *open_stp);
static char user_recovery_dirname[PATH_MAX] = "/var/lib/nfs/v4recovery";
static void nfs4_set_recdir(char *recdir);

/* Locking:
 *
 * client_mutex:
 * 	protects clientid_hashtbl[], clientstr_hashtbl[],
 * 	unconfstr_hashtbl[], uncofid_hashtbl[].
 */
static DEFINE_MUTEX(client_mutex);

static struct kmem_cache *stateowner_slab = NULL;
static struct kmem_cache *file_slab = NULL;
static struct kmem_cache *stateid_slab = NULL;
static struct kmem_cache *deleg_slab = NULL;

void
nfs4_lock_state(void)
{
	mutex_lock(&client_mutex);
}

void
nfs4_unlock_state(void)
{
	mutex_unlock(&client_mutex);
}

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;
}

/* forward declarations */
static void release_stateowner(struct nfs4_stateowner *sop);
static void release_stateid(struct nfs4_stateid *stp, int flags);

/*
 * Delegation state
 */

/* recall_lock protects the del_recall_lru */
static DEFINE_SPINLOCK(recall_lock);
static struct list_head del_recall_lru;

static void
free_nfs4_file(struct kref *kref)
{
	struct nfs4_file *fp = container_of(kref, struct nfs4_file, fi_ref);
	list_del(&fp->fi_hash);
	iput(fp->fi_inode);
	kmem_cache_free(file_slab, fp);
}

static inline void
put_nfs4_file(struct nfs4_file *fi)
{
	kref_put(&fi->fi_ref, free_nfs4_file);
}

static inline void
get_nfs4_file(struct nfs4_file *fi)
{
	kref_get(&fi->fi_ref);
}

static int num_delegations;
unsigned int max_delegations;

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

/* hash tables for nfs4_stateowner */
#define OWNER_HASH_BITS              8
#define OWNER_HASH_SIZE             (1 << OWNER_HASH_BITS)
#define OWNER_HASH_MASK             (OWNER_HASH_SIZE - 1)

#define ownerid_hashval(id) \
        ((id) & OWNER_HASH_MASK)
#define ownerstr_hashval(clientid, ownername) \
        (((clientid) + opaque_hashval((ownername.data), (ownername.len))) & OWNER_HASH_MASK)

static struct list_head	ownerid_hashtbl[OWNER_HASH_SIZE];
static struct list_head	ownerstr_hashtbl[OWNER_HASH_SIZE];

/* hash table for nfs4_file */
#define FILE_HASH_BITS                   8
#define FILE_HASH_SIZE                  (1 << FILE_HASH_BITS)
#define FILE_HASH_MASK                  (FILE_HASH_SIZE - 1)
/* hash table for (open)nfs4_stateid */
#define STATEID_HASH_BITS              10
#define STATEID_HASH_SIZE              (1 << STATEID_HASH_BITS)
#define STATEID_HASH_MASK              (STATEID_HASH_SIZE - 1)

#define file_hashval(x) \
        hash_ptr(x, FILE_HASH_BITS)
#define stateid_hashval(owner_id, file_id)  \
        (((owner_id) + (file_id)) & STATEID_HASH_MASK)

static struct list_head file_hashtbl[FILE_HASH_SIZE];
static struct list_head stateid_hashtbl[STATEID_HASH_SIZE];

static struct nfs4_delegation *
alloc_init_deleg(struct nfs4_client *clp, struct nfs4_stateid *stp, struct svc_fh *current_fh, u32 type)
{
	struct nfs4_delegation *dp;
	struct nfs4_file *fp = stp->st_file;
	struct nfs4_callback *cb = &stp->st_stateowner->so_client->cl_callback;

	dprintk("NFSD alloc_init_deleg\n");
	if (fp->fi_had_conflict)
		return NULL;
	if (num_delegations > max_delegations)
		return NULL;
	dp = kmem_cache_alloc(deleg_slab, GFP_KERNEL);
	if (dp == NULL)
		return dp;
	num_delegations++;
	INIT_LIST_HEAD(&dp->dl_perfile);
	INIT_LIST_HEAD(&dp->dl_perclnt);
	INIT_LIST_HEAD(&dp->dl_recall_lru);
	dp->dl_client = clp;
	get_nfs4_file(fp);
	dp->dl_file = fp;
	dp->dl_flock = NULL;
	get_file(stp->st_vfs_file);
	dp->dl_vfs_file = stp->st_vfs_file;
	dp->dl_type = type;
	dp->dl_recall.cbr_dp = NULL;
	dp->dl_recall.cbr_ident = cb->cb_ident;
	dp->dl_recall.cbr_trunc = 0;
	dp->dl_stateid.si_boot = boot_time;
	dp->dl_stateid.si_stateownerid = current_delegid++;
	dp->dl_stateid.si_fileid = 0;
	dp->dl_stateid.si_generation = 0;
	dp->dl_fhlen = current_fh->fh_handle.fh_size;
	memcpy(dp->dl_fhval, &current_fh->fh_handle.fh_base,
		        current_fh->fh_handle.fh_size);
	dp->dl_time = 0;
	atomic_set(&dp->dl_count, 1);
	list_add(&dp->dl_perfile, &fp->fi_delegations);
	list_add(&dp->dl_perclnt, &clp->cl_delegations);
	return dp;
}

void
nfs4_put_delegation(struct nfs4_delegation *dp)
{
	if (atomic_dec_and_test(&dp->dl_count)) {
		dprintk("NFSD: freeing dp %p\n",dp);
		put_nfs4_file(dp->dl_file);
		kmem_cache_free(deleg_slab, dp);
		num_delegations--;
	}
}

/* Remove the associated file_lock first, then remove the delegation.
 * lease_modify() is called to remove the FS_LEASE file_lock from
 * the i_flock list, eventually calling nfsd's lock_manager
 * fl_release_callback.
 */
static void
nfs4_close_delegation(struct nfs4_delegation *dp)
{
	struct file *filp = dp->dl_vfs_file;

	dprintk("NFSD: close_delegation dp %p\n",dp);
	dp->dl_vfs_file = NULL;
	/* The following nfsd_close may not actually close the file,
	 * but we want to remove the lease in any case. */
	if (dp->dl_flock)
		vfs_setlease(filp, F_UNLCK, &dp->dl_flock);
	nfsd_close(filp);
}

/* Called under the state lock. */
static void
unhash_delegation(struct nfs4_delegation *dp)
{
	list_del_init(&dp->dl_perfile);
	list_del_init(&dp->dl_perclnt);
	spin_lock(&recall_lock);
	list_del_init(&dp->dl_recall_lru);
	spin_unlock(&recall_lock);
	nfs4_close_delegation(dp);
	nfs4_put_delegation(dp);
}

/* 
 * SETCLIENTID state 
 */

/* 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 clientid_hashval(id) \
	((id) & CLIENT_HASH_MASK)
#define clientstr_hashval(name) \
	(opaque_hashval((name), 8) & CLIENT_HASH_MASK)
/*
 * reclaim_str_hashtbl[] holds known client info from previous reset/reboot
 * used in reboot/reset lease grace period processing
 *
 * conf_id_hashtbl[], and conf_str_hashtbl[] hold confirmed
 * setclientid_confirmed info. 
 *
 * unconf_str_hastbl[] and unconf_id_hashtbl[] hold unconfirmed 
 * setclientid info.
 *
 * 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.
 */
static struct list_head	reclaim_str_hashtbl[CLIENT_HASH_SIZE];
static int reclaim_str_hashtbl_size = 0;
static struct list_head	conf_id_hashtbl[CLIENT_HASH_SIZE];
static struct list_head	conf_str_hashtbl[CLIENT_HASH_SIZE];
static struct list_head	unconf_str_hashtbl[CLIENT_HASH_SIZE];
static struct list_head	unconf_id_hashtbl[CLIENT_HASH_SIZE];
static struct list_head client_lru;
static struct list_head close_lru;

static inline void
renew_client(struct nfs4_client *clp)
{
	/*
	* Move client to the end to the LRU list.
	*/
	dprintk("renewing client (clientid %08x/%08x)\n", 
			clp->cl_clientid.cl_boot, 
			clp->cl_clientid.cl_id);
	list_move_tail(&clp->cl_lru, &client_lru);
	clp->cl_time = get_seconds();
}

/* SETCLIENTID and SETCLIENTID_CONFIRM Helper functions */
static int
STALE_CLIENTID(clientid_t *clid)
{
	if (clid->cl_boot == boot_time)
		return 0;
	dprintk("NFSD stale clientid (%08x/%08x)\n", 
			clid->cl_boot, clid->cl_id);
	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 inline struct nfs4_client *
alloc_client(struct xdr_netobj name)
{
	struct nfs4_client *clp;

	if ((clp = kzalloc(sizeof(struct nfs4_client), GFP_KERNEL))!= NULL) {
		if ((clp->cl_name.data = kmalloc(name.len, GFP_KERNEL)) != NULL) {
			memcpy(clp->cl_name.data, name.data, name.len);
			clp->cl_name.len = name.len;
		}
		else {
			kfree(clp);
			clp = NULL;
		}
	}
	return clp;
}

static void
shutdown_callback_client(struct nfs4_client *clp)
{
	struct rpc_clnt *clnt = clp->cl_callback.cb_client;

	/* shutdown rpc client, ending any outstanding recall rpcs */
	if (clnt) {
		clp->cl_callback.cb_client = NULL;
		rpc_shutdown_client(clnt);
	}
}

static inline void
free_client(struct nfs4_client *clp)
{
	shutdown_callback_client(clp);
	if (clp->cl_cred.cr_group_info)
		put_group_info(clp->cl_cred.cr_group_info);
	kfree(clp->cl_name.data);
	kfree(clp);
}

void
put_nfs4_client(struct nfs4_client *clp)
{
	if (atomic_dec_and_test(&clp->cl_count))
		free_client(clp);
}

static void
expire_client(struct nfs4_client *clp)
{
	struct nfs4_stateowner *sop;
	struct nfs4_delegation *dp;
	struct list_head reaplist;

	dprintk("NFSD: expire_client cl_count %d\n",
	                    atomic_read(&clp->cl_count));

	INIT_LIST_HEAD(&reaplist);
	spin_lock(&recall_lock);
	while (!list_empty(&clp->cl_delegations)) {
		dp = list_entry(clp->cl_delegations.next, struct nfs4_delegation, dl_perclnt);
		dprintk("NFSD: expire client. dp %p, fp %p\n", dp,
				dp->dl_flock);
		list_del_init(&dp->dl_perclnt);
		list_move(&dp->dl_recall_lru, &reaplist);
	}
	spin_unlock(&recall_lock);
	while (!list_empty(&reaplist)) {
		dp = list_entry(reaplist.next, struct nfs4_delegation, dl_recall_lru);
		list_del_init(&dp->dl_recall_lru);
		unhash_delegation(dp);
	}
	list_del(&clp->cl_idhash);
	list_del(&clp->cl_strhash);
	list_del(&clp->cl_lru);
	while (!list_empty(&clp->cl_openowners)) {
		sop = list_entry(clp->cl_openowners.next, struct nfs4_stateowner, so_perclient);
		release_stateowner(sop);
	}
	put_nfs4_client(clp);
}

static struct nfs4_client *
create_client(struct xdr_netobj name, char *recdir) {
	struct nfs4_client *clp;

	if (!(clp = alloc_client(name)))
		goto out;
	memcpy(clp->cl_recdir, recdir, HEXDIR_LEN);
	atomic_set(&clp->cl_count, 1);
	atomic_set(&clp->cl_callback.cb_set, 0);
	INIT_LIST_HEAD(&clp->cl_idhash);
	INIT_LIST_HEAD(&clp->cl_strhash);
	INIT_LIST_HEAD(&clp->cl_openowners);
	INIT_LIST_HEAD(&clp->cl_delegations);
	INIT_LIST_HEAD(&clp->cl_lru);
out:
	return 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 void
copy_cred(struct svc_cred *target, struct svc_cred *source) {

	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);
}

static inline int
same_name(const char *n1, const char *n2)
{
	return 0 == memcmp(n1, n2, HEXDIR_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);
}

/* XXX what about NGROUP */
static int
same_creds(struct svc_cred *cr1, struct svc_cred *cr2)
{
	return cr1->cr_uid == cr2->cr_uid;
}

static void
gen_clid(struct nfs4_client *clp) {
	clp->cl_clientid.cl_boot = boot_time;