Home Home > GIT Browse
summaryrefslogtreecommitdiff
blob: fefeae27f25e62a784b8e67a483154b283542c64 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
/*
 *  Copyright (c) 2001 The Regents of the University of Michigan.
 *  All rights reserved.
 *
 *  Kendrick Smith <kmsmith@umich.edu>
 *  Andy Adamson <andros@umich.edu>
 *  
 *  Redistribution and use in source and binary forms, with or without
 *  modification, are permitted provided that the following conditions
 *  are met:
 *  
 *  1. Redistributions of source code must retain the above copyright
 *     notice, this list of conditions and the following disclaimer.
 *  2. Redistributions in binary form must reproduce the above copyright
 *     notice, this list of conditions and the following disclaimer in the
 *     documentation and/or other materials provided with the distribution.
 *  3. Neither the name of the University nor the names of its
 *     contributors may be used to endorse or promote products derived
 *     from this software without specific prior written permission.
 *
 *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
 *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
 *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
 *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
 *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
 *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
 *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 *
 */

#ifndef _NFSD4_STATE_H
#define _NFSD4_STATE_H

#include <linux/nfsd/nfsfh.h>
#include "nfsfh.h"

typedef struct {
	u32             cl_boot;
	u32             cl_id;
} clientid_t;

typedef struct {
	u32             so_boot;
	u32             so_stateownerid;
	u32             so_fileid;
} stateid_opaque_t;

typedef struct {
	u32                     si_generation;
	stateid_opaque_t        si_opaque;
} stateid_t;
#define si_boot           si_opaque.so_boot
#define si_stateownerid   si_opaque.so_stateownerid
#define si_fileid         si_opaque.so_fileid

#define STATEID_FMT	"(%08x/%08x/%08x/%08x)"
#define STATEID_VAL(s) \
	(s)->si_boot, \
	(s)->si_stateownerid, \
	(s)->si_fileid, \
	(s)->si_generation

struct nfsd4_cb_sequence {
	/* args/res */
	u32			cbs_minorversion;
	struct nfs4_client	*cbs_clp;
};

struct nfs4_delegation {
	struct list_head	dl_perfile;
	struct list_head	dl_perclnt;
	struct list_head	dl_recall_lru;  /* delegation recalled */
	atomic_t		dl_count;       /* ref count */
	struct nfs4_client	*dl_client;
	struct nfs4_file	*dl_file;
	struct file_lock	*dl_flock;
	struct file		*dl_vfs_file;
	u32			dl_type;
	time_t			dl_time;
/* For recall: */
	u32			dl_ident;
	stateid_t		dl_stateid;
	struct knfsd_fh		dl_fh;
	int			dl_retries;
};

/* client delegation callback info */
struct nfs4_cb_conn {
	/* SETCLIENTID info */
	struct sockaddr_storage	cb_addr;
	size_t			cb_addrlen;
	u32                     cb_prog;
	u32			cb_minorversion;
	u32                     cb_ident;	/* minorversion 0 only */
	/* RPC client info */
	atomic_t		cb_set;     /* successful CB_NULL call */
	struct rpc_clnt *       cb_client;
};

/* Maximum number of slots per session. 160 is useful for long haul TCP */
#define NFSD_MAX_SLOTS_PER_SESSION     160
/* Maximum number of operations per session compound */
#define NFSD_MAX_OPS_PER_COMPOUND	16
/* Maximum  session per slot cache size */
#define NFSD_SLOT_CACHE_SIZE		1024
/* Maximum number of NFSD_SLOT_CACHE_SIZE slots per session */
#define NFSD_CACHE_SIZE_SLOTS_PER_SESSION	32
#define NFSD_MAX_MEM_PER_SESSION  \
		(NFSD_CACHE_SIZE_SLOTS_PER_SESSION * NFSD_SLOT_CACHE_SIZE)

struct nfsd4_slot {
	bool	sl_inuse;
	bool	sl_cachethis;
	u16	sl_opcnt;
	u32	sl_seqid;
	__be32	sl_status;
	u32	sl_datalen;
	char	sl_data[];
};

struct nfsd4_channel_attrs {
	u32		headerpadsz;
	u32		maxreq_sz;
	u32		maxresp_sz;
	u32		maxresp_cached;
	u32		maxops;
	u32		maxreqs;
	u32		nr_rdma_attrs;
	u32		rdma_attrs;
};

struct nfsd4_create_session {
	clientid_t			clientid;
	struct nfs4_sessionid		sessionid;
	u32				seqid;
	u32				flags;
	struct nfsd4_channel_attrs	fore_channel;
	struct nfsd4_channel_attrs	back_channel;
	u32				callback_prog;
	u32				uid;
	u32				gid;
};

/* The single slot clientid cache structure */
struct nfsd4_clid_slot {
	u32				sl_seqid;
	__be32				sl_status;
	struct nfsd4_create_session	sl_cr_ses;
};

struct nfsd4_session {
	struct kref		se_ref;
	struct list_head	se_hash;	/* hash by sessionid */
	struct list_head	se_perclnt;
	u32			se_flags;
	struct nfs4_client	*se_client;	/* for expire_client */
	struct nfs4_sessionid	se_sessionid;
	struct nfsd4_channel_attrs se_fchannel;
	struct nfsd4_channel_attrs se_bchannel;
	struct nfsd4_slot	*se_slots[];	/* forward channel slots */
};

static inline void
nfsd4_put_session(struct nfsd4_session *ses)
{
	extern void free_session(struct kref *kref);
	kref_put(&ses->se_ref, free_session);
}

static inline void
nfsd4_get_session(struct nfsd4_session *ses)
{
	kref_get(&ses->se_ref);
}

/* formatted contents of nfs4_sessionid */
struct nfsd4_sessionid {
	clientid_t	clientid;
	u32		sequence;
	u32		reserved;
};

#define HEXDIR_LEN     33 /* hex version of 16 byte md5 of cl_name plus '\0' */

/*
 * struct nfs4_client - one per client.  Clientids live here.
 * 	o Each nfs4_client is hashed by clientid.
 *
 * 	o Each nfs4_clients is also hashed by name 
 * 	  (the opaque quantity initially sent by the client to identify itself).
 * 	  
 *	o cl_perclient list is used to ensure no dangling stateowner references
 *	  when we expire the nfs4_client
 */
struct nfs4_client {
	struct list_head	cl_idhash; 	/* hash by cl_clientid.id */
	struct list_head	cl_strhash; 	/* hash by cl_name */
	struct list_head	cl_openowners;
	struct list_head	cl_delegations;
	struct list_head        cl_lru;         /* tail queue */
	struct xdr_netobj	cl_name; 	/* id generated by client */
	char                    cl_recdir[HEXDIR_LEN]; /* recovery dir */
	nfs4_verifier		cl_verifier; 	/* generated by client */
	time_t                  cl_time;        /* time of last lease renewal */
	struct sockaddr_storage	cl_addr; 	/* client ipaddress */
	u32			cl_flavor;	/* setclientid pseudoflavor */
	char			*cl_principal;	/* setclientid principal name */
	struct svc_cred		cl_cred; 	/* setclientid principal */
	clientid_t		cl_clientid;	/* generated by server */
	nfs4_verifier		cl_confirm;	/* generated by server */
	struct nfs4_cb_conn	cl_cb_conn;     /* callback info */
	atomic_t		cl_count;	/* ref count */
	u32			cl_firststate;	/* recovery dir creation */

	/* for nfs41 */
	struct list_head	cl_sessions;
	struct nfsd4_clid_slot	cl_cs_slot;	/* create_session slot */
	u32			cl_exchange_flags;
	struct nfs4_sessionid	cl_sessionid;

	/* for nfs41 callbacks */
	/* We currently support a single back channel with a single slot */
	unsigned long		cl_cb_slot_busy;
	u32			cl_cb_seq_nr;
	struct svc_xprt		*cl_cb_xprt;	/* 4.1 callback transport */
	struct rpc_wait_queue	cl_cb_waitq;	/* backchannel callers may */
						/* wait here for slots */
};

/* struct nfs4_client_reset
 * one per old client. Populates reset_str_hashtbl. Filled from conf_id_hashtbl
 * upon lease reset, or from upcall to state_daemon (to read in state
 * from non-volitile storage) upon reboot.
 */
struct nfs4_client_reclaim {
	struct list_head	cr_strhash;	/* hash by cr_name */
	char			cr_recdir[HEXDIR_LEN]; /* recover dir */
};

static inline void
update_stateid(stateid_t *stateid)
{
	stateid->si_generation++;
}

/* A reasonable value for REPLAY_ISIZE was estimated as follows:  
 * The OPEN response, typically the largest, requires 
 *   4(status) + 8(stateid) + 20(changeinfo) + 4(rflags) +  8(verifier) + 
 *   4(deleg. type) + 8(deleg. stateid) + 4(deleg. recall flag) + 
 *   20(deleg. space limit) + ~32(deleg. ace) = 112 bytes 
 */

#define NFSD4_REPLAY_ISIZE       112 

/*
 * Replay buffer, where the result of the last seqid-mutating operation 
 * is cached. 
 */
struct nfs4_replay {
	__be32			rp_status;
	unsigned int		rp_buflen;
	char			*rp_buf;
	unsigned		intrp_allocated;
	struct knfsd_fh		rp_openfh;
	char			rp_ibuf[NFSD4_REPLAY_ISIZE];
};

/*
* nfs4_stateowner can either be an open_owner, or a lock_owner
*
*    so_idhash:  stateid_hashtbl[] for open owner, lockstateid_hashtbl[]
*         for lock_owner
*    so_strhash: ownerstr_hashtbl[] for open_owner, lock_ownerstr_hashtbl[]
*         for lock_owner
*    so_perclient: nfs4_client->cl_perclient entry - used when nfs4_client
*         struct is reaped.
*    so_perfilestate: heads the list of nfs4_stateid (either open or lock) 
*         and is used to ensure no dangling nfs4_stateid references when we 
*         release a stateowner.
*    so_perlockowner: (open) nfs4_stateid->st_perlockowner entry - used when
*         close is called to reap associated byte-range locks
*    so_close_lru: (open) stateowner is placed on this list instead of being
*         reaped (when so_perfilestate is empty) to hold the last close replay.
*         reaped by laundramat thread after lease period.
*/
struct nfs4_stateowner {
	struct kref		so_ref;
	struct list_head        so_idhash;   /* hash by so_id */
	struct list_head        so_strhash;   /* hash by op_name */
	struct list_head        so_perclient;
	struct list_head        so_stateids;
	struct list_head        so_perstateid; /* for lockowners only */
	struct list_head	so_close_lru; /* tail queue */
	time_t			so_time; /* time of placement on so_close_lru */
	int			so_is_open_owner; /* 1=openowner,0=lockowner */
	u32                     so_id;
	struct nfs4_client *    so_client;
	/* after increment in ENCODE_SEQID_OP_TAIL, represents the next
	 * sequence id expected from the client: */
	u32                     so_seqid;
	struct xdr_netobj       so_owner;     /* open owner name */
	int                     so_confirmed; /* successful OPEN_CONFIRM? */
	struct nfs4_replay	so_replay;
};

/*
*  nfs4_file: a file opened by some number of (open) nfs4_stateowners.
*    o fi_perfile list is used to search for conflicting 
*      share_acces, share_deny on the file.
*/
struct nfs4_file {
	atomic_t		fi_ref;
	struct list_head        fi_hash;    /* hash by "struct inode *" */
	struct list_head        fi_stateids;
	struct list_head	fi_delegations;
	struct inode		*fi_inode;
	u32                     fi_id;      /* used with stateowner->so_id 
					     * for stateid_hashtbl hash */
	bool			fi_had_conflict;
};

/*
* nfs4_stateid can either be an open stateid or (eventually) a lock stateid
*
* (open)nfs4_stateid: one per (open)nfs4_stateowner, nfs4_file
*
* 	st_hash: stateid_hashtbl[] entry or lockstateid_hashtbl entry
* 	st_perfile: file_hashtbl[] entry.
* 	st_perfile_state: nfs4_stateowner->so_perfilestate
*       st_perlockowner: (open stateid) list of lock nfs4_stateowners
* 	st_access_bmap: used only for open stateid
* 	st_deny_bmap: used only for open stateid
*	st_openstp: open stateid lock stateid was derived from
*
* XXX: open stateids and lock stateids have diverged sufficiently that
* we should consider defining separate structs for the two cases.
*/

struct nfs4_stateid {
	struct list_head              st_hash; 
	struct list_head              st_perfile;
	struct list_head              st_perstateowner;
	struct list_head              st_lockowners;
	struct nfs4_stateowner      * st_stateowner;
	struct nfs4_file            * st_file;
	stateid_t                     st_stateid;
	struct file                 * st_vfs_file;
	unsigned long                 st_access_bmap;
	unsigned long                 st_deny_bmap;
	struct nfs4_stateid         * st_openstp;
};

/* flags for preprocess_seqid_op() */
#define HAS_SESSION             0x00000001
#define CONFIRM                 0x00000002
#define OPEN_STATE              0x00000004
#define LOCK_STATE              0x00000008
#define RD_STATE	        0x00000010
#define WR_STATE	        0x00000020
#define CLOSE_STATE             0x00000040

#define seqid_mutating_err(err)                       \
	(((err) != nfserr_stale_clientid) &&    \
	((err) != nfserr_bad_seqid) &&          \
	((err) != nfserr_stale_stateid) &&      \
	((err) != nfserr_bad_stateid))

struct nfsd4_compound_state;

extern __be32 nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate,
		stateid_t *stateid, int flags, struct file **filp);
extern void nfs4_lock_state(void);
extern void nfs4_unlock_state(void);
extern int nfs4_in_grace(void);
extern __be32 nfs4_check_open_reclaim(clientid_t *clid);
extern void put_nfs4_client(struct nfs4_client *clp);
extern void nfs4_free_stateowner(struct kref *kref);
extern int set_callback_cred(void);
extern void nfsd4_probe_callback(struct nfs4_client *clp);
extern void nfsd4_cb_recall(struct nfs4_delegation *dp);
extern void nfs4_put_delegation(struct nfs4_delegation *dp);
extern __be32 nfs4_make_rec_clidname(char *clidname, struct xdr_netobj *clname);
extern void nfsd4_init_recdir(char *recdir_name);
extern int nfsd4_recdir_load(void);
extern void nfsd4_shutdown_recdir(void);
extern int nfs4_client_to_reclaim(const char *name);
extern int nfs4_has_reclaimed_state(const char *name, bool use_exchange_id);
extern void nfsd4_recdir_purge_old(void);
extern int nfsd4_create_clid_dir(struct nfs4_client *clp);
extern void nfsd4_remove_clid_dir(struct nfs4_client *clp);

static inline void
nfs4_put_stateowner(struct nfs4_stateowner *so)
{
	kref_put(&so->so_ref, nfs4_free_stateowner);
}

static inline void
nfs4_get_stateowner(struct nfs4_stateowner *so)
{
	kref_get(&so->so_ref);
}

#endif   /* NFSD4_STATE_H */