summaryrefslogtreecommitdiff
path: root/include/linux/sunrpc/svc.h
blob: 877891536c2f4892df4f70ab474ba44f001cd34c (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
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
/* SPDX-License-Identifier: GPL-2.0 */
/*
 * linux/include/linux/sunrpc/svc.h
 *
 * RPC server declarations.
 *
 * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
 */


#ifndef SUNRPC_SVC_H
#define SUNRPC_SVC_H

#include <linux/in.h>
#include <linux/in6.h>
#include <linux/sunrpc/types.h>
#include <linux/sunrpc/xdr.h>
#include <linux/sunrpc/auth.h>
#include <linux/sunrpc/svcauth.h>
#include <linux/wait.h>
#include <linux/mm.h>
#include <linux/pagevec.h>

/*
 *
 * RPC service thread pool.
 *
 * Pool of threads and temporary sockets.  Generally there is only
 * a single one of these per RPC service, but on NUMA machines those
 * services that can benefit from it (i.e. nfs but not lockd) will
 * have one pool per NUMA node.  This optimisation reduces cross-
 * node traffic on multi-node NUMA NFS servers.
 */
struct svc_pool {
	unsigned int		sp_id;	    	/* pool id; also node id on NUMA */
	spinlock_t		sp_lock;	/* protects all fields */
	struct list_head	sp_sockets;	/* pending sockets */
	unsigned int		sp_nrthreads;	/* # of threads in pool */
	struct list_head	sp_all_threads;	/* all server threads */

	/* statistics on pool operation */
	struct percpu_counter	sp_sockets_queued;
	struct percpu_counter	sp_threads_woken;
	struct percpu_counter	sp_threads_timedout;

#define	SP_TASK_PENDING		(0)		/* still work to do even if no
						 * xprt is queued. */
#define SP_CONGESTED		(1)
	unsigned long		sp_flags;
} ____cacheline_aligned_in_smp;

/*
 * RPC service.
 *
 * An RPC service is a ``daemon,'' possibly multithreaded, which
 * receives and processes incoming RPC messages.
 * It has one or more transport sockets associated with it, and maintains
 * a list of idle threads waiting for input.
 *
 * We currently do not support more than one RPC program per daemon.
 */
struct svc_serv {
	struct svc_program *	sv_program;	/* RPC program */
	struct svc_stat *	sv_stats;	/* RPC statistics */
	spinlock_t		sv_lock;
	struct kref		sv_refcnt;
	unsigned int		sv_nrthreads;	/* # of server threads */
	unsigned int		sv_maxconn;	/* max connections allowed or
						 * '0' causing max to be based
						 * on number of threads. */

	unsigned int		sv_max_payload;	/* datagram payload size */
	unsigned int		sv_max_mesg;	/* max_payload + 1 page for overheads */
	unsigned int		sv_xdrsize;	/* XDR buffer size */
	struct list_head	sv_permsocks;	/* all permanent sockets */
	struct list_head	sv_tempsocks;	/* all temporary sockets */
	int			sv_tmpcnt;	/* count of temporary sockets */
	struct timer_list	sv_temptimer;	/* timer for aging temporary sockets */

	char *			sv_name;	/* service name */

	unsigned int		sv_nrpools;	/* number of thread pools */
	struct svc_pool *	sv_pools;	/* array of thread pools */
	int			(*sv_threadfn)(void *data);

#if defined(CONFIG_SUNRPC_BACKCHANNEL)
	struct list_head	sv_cb_list;	/* queue for callback requests
						 * that arrive over the same
						 * connection */
	spinlock_t		sv_cb_lock;	/* protects the svc_cb_list */
	wait_queue_head_t	sv_cb_waitq;	/* sleep here if there are no
						 * entries in the svc_cb_list */
	bool			sv_bc_enabled;	/* service uses backchannel */
#endif /* CONFIG_SUNRPC_BACKCHANNEL */
};

/**
 * svc_get() - increment reference count on a SUNRPC serv
 * @serv:  the svc_serv to have count incremented
 *
 * Returns: the svc_serv that was passed in.
 */
static inline struct svc_serv *svc_get(struct svc_serv *serv)
{
	kref_get(&serv->sv_refcnt);
	return serv;
}

void svc_destroy(struct kref *);

/**
 * svc_put - decrement reference count on a SUNRPC serv
 * @serv:  the svc_serv to have count decremented
 *
 * When the reference count reaches zero, svc_destroy()
 * is called to clean up and free the serv.
 */
static inline void svc_put(struct svc_serv *serv)
{
	kref_put(&serv->sv_refcnt, svc_destroy);
}

/**
 * svc_put_not_last - decrement non-final reference count on SUNRPC serv
 * @serv:  the svc_serv to have count decremented
 *
 * Returns: %true is refcount was decremented.
 *
 * If the refcount is 1, it is not decremented and instead failure is reported.
 */
static inline bool svc_put_not_last(struct svc_serv *serv)
{
	return refcount_dec_not_one(&serv->sv_refcnt.refcount);
}

/*
 * Maximum payload size supported by a kernel RPC server.
 * This is use to determine the max number of pages nfsd is
 * willing to return in a single READ operation.
 *
 * These happen to all be powers of 2, which is not strictly
 * necessary but helps enforce the real limitation, which is
 * that they should be multiples of PAGE_SIZE.
 *
 * For UDP transports, a block plus NFS,RPC, and UDP headers
 * has to fit into the IP datagram limit of 64K.  The largest
 * feasible number for all known page sizes is probably 48K,
 * but we choose 32K here.  This is the same as the historical
 * Linux limit; someone who cares more about NFS/UDP performance
 * can test a larger number.
 *
 * For TCP transports we have more freedom.  A size of 1MB is
 * chosen to match the client limit.  Other OSes are known to
 * have larger limits, but those numbers are probably beyond
 * the point of diminishing returns.
 */
#define RPCSVC_MAXPAYLOAD	(1*1024*1024u)
#define RPCSVC_MAXPAYLOAD_TCP	RPCSVC_MAXPAYLOAD
#define RPCSVC_MAXPAYLOAD_UDP	(32*1024u)

extern u32 svc_max_payload(const struct svc_rqst *rqstp);

/*
 * RPC Requsts and replies are stored in one or more pages.
 * We maintain an array of pages for each server thread.
 * Requests are copied into these pages as they arrive.  Remaining
 * pages are available to write the reply into.
 *
 * Pages are sent using ->sendpage so each server thread needs to
 * allocate more to replace those used in sending.  To help keep track
 * of these pages we have a receive list where all pages initialy live,
 * and a send list where pages are moved to when there are to be part
 * of a reply.
 *
 * We use xdr_buf for holding responses as it fits well with NFS
 * read responses (that have a header, and some data pages, and possibly
 * a tail) and means we can share some client side routines.
 *
 * The xdr_buf.head kvec always points to the first page in the rq_*pages
 * list.  The xdr_buf.pages pointer points to the second page on that
 * list.  xdr_buf.tail points to the end of the first page.
 * This assumes that the non-page part of an rpc reply will fit
 * in a page - NFSd ensures this.  lockd also has no trouble.
 *
 * Each request/reply pair can have at most one "payload", plus two pages,
 * one for the request, and one for the reply.
 * We using ->sendfile to return read data, we might need one extra page
 * if the request is not page-aligned.  So add another '1'.
 */
#define RPCSVC_MAXPAGES		((RPCSVC_MAXPAYLOAD+PAGE_SIZE-1)/PAGE_SIZE \
				+ 2 + 1)

/*
 * The context of a single thread, including the request currently being
 * processed.
 */
struct svc_rqst {
	struct list_head	rq_all;		/* all threads list */
	struct rcu_head		rq_rcu_head;	/* for RCU deferred kfree */
	struct svc_xprt *	rq_xprt;	/* transport ptr */

	struct sockaddr_storage	rq_addr;	/* peer address */
	size_t			rq_addrlen;
	struct sockaddr_storage	rq_daddr;	/* dest addr of request
						 *  - reply from here */
	size_t			rq_daddrlen;

	struct svc_serv *	rq_server;	/* RPC service definition */
	struct svc_pool *	rq_pool;	/* thread pool */
	const struct svc_procedure *rq_procinfo;/* procedure info */
	struct auth_ops *	rq_authop;	/* authentication flavour */
	struct svc_cred		rq_cred;	/* auth info */
	void *			rq_xprt_ctxt;	/* transport specific context ptr */
	struct svc_deferred_req*rq_deferred;	/* deferred request we are replaying */

	struct xdr_buf		rq_arg;
	struct xdr_stream	rq_arg_stream;
	struct xdr_stream	rq_res_stream;
	struct page		*rq_scratch_page;
	struct xdr_buf		rq_res;
	struct page		*rq_pages[RPCSVC_MAXPAGES + 1];
	struct page *		*rq_respages;	/* points into rq_pages */
	struct page *		*rq_next_page; /* next reply page to use */
	struct page *		*rq_page_end;  /* one past the last page */

	struct pagevec		rq_pvec;
	struct kvec		rq_vec[RPCSVC_MAXPAGES]; /* generally useful.. */
	struct bio_vec		rq_bvec[RPCSVC_MAXPAGES];

	__be32			rq_xid;		/* transmission id */
	u32			rq_prog;	/* program number */
	u32			rq_vers;	/* program version */
	u32			rq_proc;	/* procedure number */
	u32			rq_prot;	/* IP protocol */
	int			rq_cachetype;	/* catering to nfsd */
#define	RQ_SECURE	(0)			/* secure port */
#define	RQ_LOCAL	(1)			/* local request */
#define	RQ_USEDEFERRAL	(2)			/* use deferral */
#define	RQ_DROPME	(3)			/* drop current reply */
#define	RQ_SPLICE_OK	(4)			/* turned off in gss privacy
						 * to prevent encrypting page
						 * cache pages */
#define	RQ_VICTIM	(5)			/* about to be shut down */
#define	RQ_BUSY		(6)			/* request is busy */
#define	RQ_DATA		(7)			/* request has data */
	unsigned long		rq_flags;	/* flags field */
	ktime_t			rq_qtime;	/* enqueue time */

	void *			rq_argp;	/* decoded arguments */
	void *			rq_resp;	/* xdr'd results */
	__be32			*rq_accept_statp;
	void *			rq_auth_data;	/* flavor-specific data */
	__be32			rq_auth_stat;	/* authentication status */
	int			rq_auth_slack;	/* extra space xdr code
						 * should leave in head
						 * for krb5i, krb5p.
						 */
	int			rq_reserved;	/* space on socket outq
						 * reserved for this request
						 */
	ktime_t			rq_stime;	/* start time */

	struct cache_req	rq_chandle;	/* handle passed to caches for 
						 * request delaying 
						 */
	/* Catering to nfsd */
	struct auth_domain *	rq_client;	/* RPC peer info */
	struct auth_domain *	rq_gssclient;	/* "gss/"-style peer info */
	struct svc_cacherep *	rq_cacherep;	/* cache info */
	struct task_struct	*rq_task;	/* service thread */
	struct net		*rq_bc_net;	/* pointer to backchannel's
						 * net namespace
						 */
	void **			rq_lease_breaker; /* The v4 client breaking a lease */
};

#define SVC_NET(rqst) (rqst->rq_xprt ? rqst->rq_xprt->xpt_net : rqst->rq_bc_net)

/*
 * Rigorous type checking on sockaddr type conversions
 */
static inline struct sockaddr_in *svc_addr_in(const struct svc_rqst *rqst)
{
	return (struct sockaddr_in *) &rqst->rq_addr;
}

static inline struct sockaddr_in6 *svc_addr_in6(const struct svc_rqst *rqst)
{
	return (struct sockaddr_in6 *) &rqst->rq_addr;
}

static inline struct sockaddr *svc_addr(const struct svc_rqst *rqst)
{
	return (struct sockaddr *) &rqst->rq_addr;
}

static inline struct sockaddr_in *svc_daddr_in(const struct svc_rqst *rqst)
{
	return (struct sockaddr_in *) &rqst->rq_daddr;
}

static inline struct sockaddr_in6 *svc_daddr_in6(const struct svc_rqst *rqst)
{
	return (struct sockaddr_in6 *) &rqst->rq_daddr;
}

static inline struct sockaddr *svc_daddr(const struct svc_rqst *rqst)
{
	return (struct sockaddr *) &rqst->rq_daddr;
}

static inline void svc_free_res_pages(struct svc_rqst *rqstp)
{
	while (rqstp->rq_next_page != rqstp->rq_respages) {
		struct page **pp = --rqstp->rq_next_page;
		if (*pp) {
			put_page(*pp);
			*pp = NULL;
		}
	}
}

struct svc_deferred_req {
	u32			prot;	/* protocol (UDP or TCP) */
	struct svc_xprt		*xprt;
	struct sockaddr_storage	addr;	/* where reply must go */
	size_t			addrlen;
	struct sockaddr_storage	daddr;	/* where reply must come from */
	size_t			daddrlen;
	void			*xprt_ctxt;
	struct cache_deferred_req handle;
	int			argslen;
	__be32			args[];
};

struct svc_process_info {
	union {
		int  (*dispatch)(struct svc_rqst *rqstp);
		struct {
			unsigned int lovers;
			unsigned int hivers;
		} mismatch;
	};
};

/*
 * List of RPC programs on the same transport endpoint
 */
struct svc_program {
	struct svc_program *	pg_next;	/* other programs (same xprt) */
	u32			pg_prog;	/* program number */
	unsigned int		pg_lovers;	/* lowest version */
	unsigned int		pg_hivers;	/* highest version */
	unsigned int		pg_nvers;	/* number of versions */
	const struct svc_version **pg_vers;	/* version array */
	char *			pg_name;	/* service name */
	char *			pg_class;	/* class name: services sharing authentication */
	struct svc_stat *	pg_stats;	/* rpc statistics */
	int			(*pg_authenticate)(struct svc_rqst *);
	__be32			(*pg_init_request)(struct svc_rqst *,
						   const struct svc_program *,
						   struct svc_process_info *);
	int			(*pg_rpcbind_set)(struct net *net,
						  const struct svc_program *,
						  u32 version, int family,
						  unsigned short proto,
						  unsigned short port);
};

/*
 * RPC program version
 */
struct svc_version {
	u32			vs_vers;	/* version number */
	u32			vs_nproc;	/* number of procedures */
	const struct svc_procedure *vs_proc;	/* per-procedure info */
	unsigned long __percpu	*vs_count;	/* call counts */
	u32			vs_xdrsize;	/* xdrsize needed for this version */

	/* Don't register with rpcbind */
	bool			vs_hidden;

	/* Don't care if the rpcbind registration fails */
	bool			vs_rpcb_optnl;

	/* Need xprt with congestion control */
	bool			vs_need_cong_ctrl;

	/* Dispatch function */
	int			(*vs_dispatch)(struct svc_rqst *rqstp);
};

/*
 * RPC procedure info
 */
struct svc_procedure {
	/* process the request: */
	__be32			(*pc_func)(struct svc_rqst *);
	/* XDR decode args: */
	bool			(*pc_decode)(struct svc_rqst *rqstp,
					     struct xdr_stream *xdr);
	/* XDR encode result: */
	bool			(*pc_encode)(struct svc_rqst *rqstp,
					     struct xdr_stream *xdr);
	/* XDR free result: */
	void			(*pc_release)(struct svc_rqst *);
	unsigned int		pc_argsize;	/* argument struct size */
	unsigned int		pc_argzero;	/* how much of argument to clear */
	unsigned int		pc_ressize;	/* result struct size */
	unsigned int		pc_cachetype;	/* cache info (NFS) */
	unsigned int		pc_xdrressize;	/* maximum size of XDR reply */
	const char *		pc_name;	/* for display */
};

/*
 * Function prototypes.
 */
int svc_rpcb_setup(struct svc_serv *serv, struct net *net);
void svc_rpcb_cleanup(struct svc_serv *serv, struct net *net);
int svc_bind(struct svc_serv *serv, struct net *net);
struct svc_serv *svc_create(struct svc_program *, unsigned int,
			    int (*threadfn)(void *data));
struct svc_rqst *svc_rqst_alloc(struct svc_serv *serv,
					struct svc_pool *pool, int node);
void		   svc_rqst_replace_page(struct svc_rqst *rqstp,
					 struct page *page);
void		   svc_rqst_free(struct svc_rqst *);
void		   svc_exit_thread(struct svc_rqst *);
struct svc_serv *  svc_create_pooled(struct svc_program *, unsigned int,
				     int (*threadfn)(void *data));
int		   svc_set_num_threads(struct svc_serv *, struct svc_pool *, int);
int		   svc_pool_stats_open(struct svc_serv *serv, struct file *file);
int		   svc_process(struct svc_rqst *);
int		   bc_svc_process(struct svc_serv *, struct rpc_rqst *,
			struct svc_rqst *);
int		   svc_register(const struct svc_serv *, struct net *, const int,
				const unsigned short, const unsigned short);

void		   svc_wake_up(struct svc_serv *);
void		   svc_reserve(struct svc_rqst *rqstp, int space);
struct svc_pool   *svc_pool_for_cpu(struct svc_serv *serv);
char *		   svc_print_addr(struct svc_rqst *, char *, size_t);
const char *	   svc_proc_name(const struct svc_rqst *rqstp);
int		   svc_encode_result_payload(struct svc_rqst *rqstp,
					     unsigned int offset,
					     unsigned int length);
unsigned int	   svc_fill_write_vector(struct svc_rqst *rqstp,
					 struct xdr_buf *payload);
char		  *svc_fill_symlink_pathname(struct svc_rqst *rqstp,
					     struct kvec *first, void *p,
					     size_t total);
__be32		   svc_generic_init_request(struct svc_rqst *rqstp,
					    const struct svc_program *progp,
					    struct svc_process_info *procinfo);
int		   svc_generic_rpcbind_set(struct net *net,
					   const struct svc_program *progp,
					   u32 version, int family,
					   unsigned short proto,
					   unsigned short port);
int		   svc_rpcbind_set_version(struct net *net,
					   const struct svc_program *progp,
					   u32 version, int family,
					   unsigned short proto,
					   unsigned short port);

#define	RPC_MAX_ADDRBUFLEN	(63U)

/*
 * When we want to reduce the size of the reserved space in the response
 * buffer, we need to take into account the size of any checksum data that
 * may be at the end of the packet. This is difficult to determine exactly
 * for all cases without actually generating the checksum, so we just use a
 * static value.
 */
static inline void svc_reserve_auth(struct svc_rqst *rqstp, int space)
{
	svc_reserve(rqstp, space + rqstp->rq_auth_slack);
}

/**
 * svcxdr_init_decode - Prepare an xdr_stream for Call decoding
 * @rqstp: controlling server RPC transaction context
 *
 */
static inline void svcxdr_init_decode(struct svc_rqst *rqstp)
{
	struct xdr_stream *xdr = &rqstp->rq_arg_stream;
	struct xdr_buf *buf = &rqstp->rq_arg;
	struct kvec *argv = buf->head;

	WARN_ON(buf->len != buf->head->iov_len + buf->page_len + buf->tail->iov_len);
	buf->len = buf->head->iov_len + buf->page_len + buf->tail->iov_len;

	xdr_init_decode(xdr, buf, argv->iov_base, NULL);
	xdr_set_scratch_page(xdr, rqstp->rq_scratch_page);
}

/**
 * svcxdr_init_encode - Prepare an xdr_stream for svc Reply encoding
 * @rqstp: controlling server RPC transaction context
 *
 */
static inline void svcxdr_init_encode(struct svc_rqst *rqstp)
{
	struct xdr_stream *xdr = &rqstp->rq_res_stream;
	struct xdr_buf *buf = &rqstp->rq_res;
	struct kvec *resv = buf->head;

	xdr_reset_scratch_buffer(xdr);

	xdr->buf = buf;
	xdr->iov = resv;
	xdr->p   = resv->iov_base + resv->iov_len;
	xdr->end = resv->iov_base + PAGE_SIZE;
	buf->len = resv->iov_len;
	xdr->page_ptr = buf->pages - 1;
	buf->buflen = PAGE_SIZE * (rqstp->rq_page_end - buf->pages);
	xdr->rqst = NULL;
}

/**
 * svcxdr_set_auth_slack -
 * @rqstp: RPC transaction
 * @slack: buffer space to reserve for the transaction's security flavor
 *
 * Set the request's slack space requirement, and set aside that much
 * space in the rqstp's rq_res.head for use when the auth wraps the Reply.
 */
static inline void svcxdr_set_auth_slack(struct svc_rqst *rqstp, int slack)
{
	struct xdr_stream *xdr = &rqstp->rq_res_stream;
	struct xdr_buf *buf = &rqstp->rq_res;
	struct kvec *resv = buf->head;

	rqstp->rq_auth_slack = slack;

	xdr->end -= XDR_QUADLEN(slack);
	buf->buflen -= rqstp->rq_auth_slack;

	WARN_ON(xdr->iov != resv);
	WARN_ON(xdr->p > xdr->end);
}

/**
 * svcxdr_set_accept_stat - Reserve space for the accept_stat field
 * @rqstp: RPC transaction context
 *
 * Return values:
 *   %true: Success
 *   %false: No response buffer space was available
 */
static inline bool svcxdr_set_accept_stat(struct svc_rqst *rqstp)
{
	struct xdr_stream *xdr = &rqstp->rq_res_stream;

	rqstp->rq_accept_statp = xdr_reserve_space(xdr, XDR_UNIT);
	if (unlikely(!rqstp->rq_accept_statp))
		return false;
	*rqstp->rq_accept_statp = rpc_success;
	return true;
}

#endif /* SUNRPC_SVC_H */