summaryrefslogtreecommitdiffstats
path: root/include/linux/sunrpc/svc.h
blob: 965d6c20086ee2980ddee1f30e7d842df019a1df (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
/*
 * 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/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>

/*
 * This is the RPC server thread function prototype
 */
typedef void		(*svc_thread_fn)(struct svc_rqst *);

/*
 *
 * 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_threads;	/* idle server threads */
	struct list_head	sp_sockets;	/* pending sockets */
	unsigned int		sp_nrthreads;	/* # of threads in pool */
	struct list_head	sp_all_threads;	/* all server threads */
} ____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;
	unsigned int		sv_nrthreads;	/* # of server 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 */

	void			(*sv_shutdown)(struct svc_serv *serv);
						/* Callback to use when last thread
						 * exits.
						 */

	struct module *		sv_module;	/* optional module to count when
						 * adding threads */
	svc_thread_fn		sv_function;	/* main function for threads */
	int			sv_kill_signal;	/* signal to kill threads */
};

/*
 * We use sv_nrthreads as a reference count.  svc_destroy() drops
 * this refcount, so we need to bump it up around operations that
 * change the number of threads.  Horrible, but there it is.
 * Should be called with the BKL held.
 */
static inline void svc_get(struct svc_serv *serv)
{
	serv->sv_nrthreads++;
}

/*
 * 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_CACHE_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.
 */
#define RPCSVC_MAXPAGES		((RPCSVC_MAXPAYLOAD+PAGE_SIZE-1)/PAGE_SIZE + 2)

static inline u32 svc_getnl(struct kvec *iov)
{
	__be32 val, *vp;
	vp = iov->iov_base;
	val = *vp++;
	iov->iov_base = (void*)vp;
	iov->iov_len -= sizeof(__be32);
	return ntohl(val);
}

static inline void svc_putnl(struct kvec *iov, u32 val)
{
	__be32 *vp = iov->iov_base + iov->iov_len;
	*vp = htonl(val);
	iov->iov_len += sizeof(__be32);
}

static inline __be32 svc_getu32(struct kvec *iov)
{
	__be32 val, *vp;
	vp = iov->iov_base;
	val = *vp++;
	iov->iov_base = (void*)vp;
	iov->iov_len -= sizeof(__be32);
	return val;
}

static inline void svc_ungetu32(struct kvec *iov)
{
	__be32 *vp = (__be32 *)iov->iov_base;
	iov->iov_base = (void *)(vp - 1);
	iov->iov_len += sizeof(*vp);
}

static inline void svc_putu32(struct kvec *iov, __be32 val)
{
	__be32 *vp = iov->iov_base + iov->iov_len;
	*vp = val;
	iov->iov_len += sizeof(__be32);
}

	
/*
 * The context of a single thread, including the request currently being
 * processed.
 */
struct svc_rqst {
	struct list_head	rq_list;	/* idle list */
	struct list_head	rq_all;		/* all threads list */
	struct svc_sock *	rq_sock;	/* socket */
	struct sockaddr_in	rq_addr;	/* peer address */
	int			rq_addrlen;

	struct svc_serv *	rq_server;	/* RPC service definition */
	struct svc_pool *	rq_pool;	/* thread pool */
	struct svc_procedure *	rq_procinfo;	/* procedure info */
	struct auth_ops *	rq_authop;	/* authentication flavour */
	struct svc_cred		rq_cred;	/* auth info */
	struct sk_buff *	rq_skbuff;	/* fast recv inet buffer */
	struct svc_deferred_req*rq_deferred;	/* deferred request we are replaying */

	struct xdr_buf		rq_arg;
	struct xdr_buf		rq_res;
	struct page *		rq_pages[RPCSVC_MAXPAGES];
	struct page *		*rq_respages;	/* points into rq_pages */
	int			rq_resused;	/* number of pages used for result */

	struct kvec		rq_vec[RPCSVC_MAXPAGES]; /* generally useful.. */

	__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 */
	unsigned short
				rq_secure  : 1;	/* secure port */


	__be32			rq_daddr;	/* dest addr of request - reply from here */

	void *			rq_argp;	/* decoded arguments */
	void *			rq_resp;	/* xdr'd results */
	void *			rq_auth_data;	/* flavor-specific data */

	int			rq_reserved;	/* space on socket outq
						 * reserved for this request
						 */

	struct cache_req	rq_chandle;	/* handle passed to caches for 
						 * request delaying 
						 */
	/* Catering to nfsd */
	struct auth_domain *	rq_client;	/* RPC peer info */
	struct svc_cacherep *	rq_cacherep;	/* cache info */
	struct knfsd_fh *	rq_reffh;	/* Referrence filehandle, used to
						 * determine what device number
						 * to report (real or virtual)
						 */
	int			rq_sendfile_ok; /* turned off in gss privacy
						 * to prevent encrypting page
						 * cache pages */
	wait_queue_head_t	rq_wait;	/* synchronization */
	struct task_struct	*rq_task;	/* service thread */
};

/*
 * Check buffer bounds after decoding arguments
 */
static inline int
xdr_argsize_check(struct svc_rqst *rqstp, __be32 *p)
{
	char *cp = (char *)p;
	struct kvec *vec = &rqstp->rq_arg.head[0];
	return cp >= (char*)vec->iov_base
		&& cp <= (char*)vec->iov_base + vec->iov_len;
}

static inline int
xdr_ressize_check(struct svc_rqst *rqstp, __be32 *p)
{
	struct kvec *vec = &rqstp->rq_res.head[0];
	char *cp = (char*)p;

	vec->iov_len = cp - (char*)vec->iov_base;

	return vec->iov_len <= PAGE_SIZE;
}

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

struct svc_deferred_req {
	u32			prot;	/* protocol (UDP or TCP) */
	struct sockaddr_in	addr;
	struct svc_sock		*svsk;	/* where reply must go */
	__be32			daddr;	/* where reply must come from */
	struct cache_deferred_req handle;
	int			argslen;
	__be32			args[0];
};

/*
 * 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;	/* lowest version */
	unsigned int		pg_nvers;	/* number of versions */
	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 *);
};

/*
 * RPC program version
 */
struct svc_version {
	u32			vs_vers;	/* version number */
	u32			vs_nproc;	/* number of procedures */
	struct svc_procedure *	vs_proc;	/* per-procedure info */
	u32			vs_xdrsize;	/* xdrsize needed for this version */

	unsigned int		vs_hidden : 1;	/* Don't register with portmapper.
						 * Only used for nfsacl so far. */

	/* Override dispatch function (e.g. when caching replies).
	 * A return value of 0 means drop the request. 
	 * vs_dispatch == NULL means use default dispatcher.
	 */
	int			(*vs_dispatch)(struct svc_rqst *, __be32 *);
};

/*
 * RPC procedure info
 */
typedef __be32	(*svc_procfunc)(struct svc_rqst *, void *argp, void *resp);
struct svc_procedure {
	svc_procfunc		pc_func;	/* process the request */
	kxdrproc_t		pc_decode;	/* XDR decode args */
	kxdrproc_t		pc_encode;	/* XDR encode result */
	kxdrproc_t		pc_release;	/* XDR free result */
	unsigned int		pc_argsize;	/* argument struct size */
	unsigned int		pc_ressize;	/* result struct size */
	unsigned int		pc_count;	/* call count */
	unsigned int		pc_cachetype;	/* cache info (NFS) */
	unsigned int		pc_xdrressize;	/* maximum size of XDR reply */
};

/*
 * Function prototypes.
 */
struct svc_serv *  svc_create(struct svc_program *, unsigned int,
			      void (*shutdown)(struct svc_serv*));
int		   svc_create_thread(svc_thread_fn, struct svc_serv *);
void		   svc_exit_thread(struct svc_rqst *);
struct svc_serv *  svc_create_pooled(struct svc_program *, unsigned int,
			void (*shutdown)(struct svc_serv*),
			svc_thread_fn, int sig, struct module *);
int		   svc_set_num_threads(struct svc_serv *, struct svc_pool *, int);
void		   svc_destroy(struct svc_serv *);
int		   svc_process(struct svc_rqst *);
int		   svc_register(struct svc_serv *, int, 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, int cpu);

#endif /* SUNRPC_SVC_H */