summaryrefslogtreecommitdiff
path: root/fs/nfsd/nfscache.c
blob: da08560c4818defa358feb7b75e88b4d33dee70b (plain) (blame)
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
/*
 * Request reply cache. This is currently a global cache, but this may
 * change in the future and be a per-client cache.
 *
 * This code is heavily inspired by the 44BSD implementation, although
 * it does things a bit differently.
 *
 * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
 */

#include "nfsd.h"
#include "cache.h"

/* Size of reply cache. Common values are:
 * 4.3BSD:	128
 * 4.4BSD:	256
 * Solaris2:	1024
 * DEC Unix:	512-4096
 */
#define CACHESIZE		1024
#define HASHSIZE		64

static struct hlist_head *	cache_hash;
static struct list_head 	lru_head;
static int			cache_disabled = 1;

/*
 * Calculate the hash index from an XID.
 */
static inline u32 request_hash(u32 xid)
{
	u32 h = xid;
	h ^= (xid >> 24);
	return h & (HASHSIZE-1);
}

static int	nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec);

/*
 * locking for the reply cache:
 * A cache entry is "single use" if c_state == RC_INPROG
 * Otherwise, it when accessing _prev or _next, the lock must be held.
 */
static DEFINE_SPINLOCK(cache_lock);

int nfsd_reply_cache_init(void)
{
	struct svc_cacherep	*rp;
	int			i;

	INIT_LIST_HEAD(&lru_head);
	i = CACHESIZE;
	while (i) {
		rp = kmalloc(sizeof(*rp), GFP_KERNEL);
		if (!rp)
			goto out_nomem;
		list_add(&rp->c_lru, &lru_head);
		rp->c_state = RC_UNUSED;
		rp->c_type = RC_NOCACHE;
		INIT_HLIST_NODE(&rp->c_hash);
		i--;
	}

	cache_hash = kcalloc (HASHSIZE, sizeof(struct hlist_head), GFP_KERNEL);
	if (!cache_hash)
		goto out_nomem;

	cache_disabled = 0;
	return 0;
out_nomem:
	printk(KERN_ERR "nfsd: failed to allocate reply cache\n");
	nfsd_reply_cache_shutdown();
	return -ENOMEM;
}

void nfsd_reply_cache_shutdown(void)
{
	struct svc_cacherep	*rp;

	while (!list_empty(&lru_head)) {
		rp = list_entry(lru_head.next, struct svc_cacherep, c_lru);
		if (rp->c_state == RC_DONE && rp->c_type == RC_REPLBUFF)
			kfree(rp->c_replvec.iov_base);
		list_del(&rp->c_lru);
		kfree(rp);
	}

	cache_disabled = 1;

	kfree (cache_hash);
	cache_hash = NULL;
}

/*
 * Move cache entry to end of LRU list
 */
static void
lru_put_end(struct svc_cacherep *rp)
{
	list_move_tail(&rp->c_lru, &lru_head);
}

/*
 * Move a cache entry from one hash list to another
 */
static void
hash_refile(struct svc_cacherep *rp)
{
	hlist_del_init(&rp->c_hash);
	hlist_add_head(&rp->c_hash, cache_hash + request_hash(rp->c_xid));
}

/*
 * Try to find an entry matching the current call in the cache. When none
 * is found, we grab the oldest unlocked entry off the LRU list.
 * Note that no operation within the loop may sleep.
 */
int
nfsd_cache_lookup(struct svc_rqst *rqstp, int type)
{
	struct hlist_node	*hn;
	struct hlist_head 	*rh;
	struct svc_cacherep	*rp;
	__be32			xid = rqstp->rq_xid;
	u32			proto =  rqstp->rq_prot,
				vers = rqstp->rq_vers,
				proc = rqstp->rq_proc;
	unsigned long		age;
	int rtn;

	rqstp->rq_cacherep = NULL;
	if (cache_disabled || type == RC_NOCACHE) {
		nfsdstats.rcnocache++;
		return RC_DOIT;
	}

	spin_lock(&cache_lock);
	rtn = RC_DOIT;

	rh = &cache_hash[request_hash(xid)];
	hlist_for_each_entry(rp, hn, rh, c_hash) {
		if (rp->c_state != RC_UNUSED &&
		    xid == rp->c_xid && proc == rp->c_proc &&
		    proto == rp->c_prot && vers == rp->c_vers &&
		    time_before(jiffies, rp->c_timestamp + 120*HZ) &&
		    memcmp((char*)&rqstp->rq_addr, (char*)&rp->c_addr, sizeof(rp->c_addr))==0) {
			nfsdstats.rchits++;
			goto found_entry;
		}
	}
	nfsdstats.rcmisses++;

	/* This loop shouldn't take more than a few iterations normally */
	{
	int	safe = 0;
	list_for_each_entry(rp, &lru_head, c_lru) {
		if (rp->c_state != RC_INPROG)
			break;
		if (safe++ > CACHESIZE) {
			printk("nfsd: loop in repcache LRU list\n");
			cache_disabled = 1;
			goto out;
		}
	}
	}

	/* All entries on the LRU are in-progress. This should not happen */
	if (&rp->c_lru == &lru_head) {
		static int	complaints;

		printk(KERN_WARNING "nfsd: all repcache entries locked!\n");
		if (++complaints > 5) {
			printk(KERN_WARNING "nfsd: disabling repcache.\n");
			cache_disabled = 1;
		}
		goto out;
	}

	rqstp->rq_cacherep = rp;
	rp->c_state = RC_INPROG;
	rp->c_xid = xid;
	rp->c_proc = proc;
	memcpy(&rp->c_addr, svc_addr_in(rqstp), sizeof(rp->c_addr));
	rp->c_prot = proto;
	rp->c_vers = vers;
	rp->c_timestamp = jiffies;

	hash_refile(rp);

	/* release any buffer */
	if (rp->c_type == RC_REPLBUFF) {
		kfree(rp->c_replvec.iov_base);
		rp->c_replvec.iov_base = NULL;
	}
	rp->c_type = RC_NOCACHE;
 out:
	spin_unlock(&cache_lock);
	return rtn;

found_entry:
	/* We found a matching entry which is either in progress or done. */
	age = jiffies - rp->c_timestamp;
	rp->c_timestamp = jiffies;
	lru_put_end(rp);

	rtn = RC_DROPIT;
	/* Request being processed or excessive rexmits */
	if (rp->c_state == RC_INPROG || age < RC_DELAY)
		goto out;

	/* From the hall of fame of impractical attacks:
	 * Is this a user who tries to snoop on the cache? */
	rtn = RC_DOIT;
	if (!rqstp->rq_secure && rp->c_secure)
		goto out;

	/* Compose RPC reply header */
	switch (rp->c_type) {
	case RC_NOCACHE:
		break;
	case RC_REPLSTAT:
		svc_putu32(&rqstp->rq_res.head[0], rp->c_replstat);
		rtn = RC_REPLY;
		break;
	case RC_REPLBUFF:
		if (!nfsd_cache_append(rqstp, &rp->c_replvec))
			goto out;	/* should not happen */
		rtn = RC_REPLY;
		break;
	default:
		printk(KERN_WARNING "nfsd: bad repcache type %d\n", rp->c_type);
		rp->c_state = RC_UNUSED;
	}

	goto out;
}

/*
 * Update a cache entry. This is called from nfsd_dispatch when
 * the procedure has been executed and the complete reply is in
 * rqstp->rq_res.
 *
 * We're copying around data here rather than swapping buffers because
 * the toplevel loop requires max-sized buffers, which would be a waste
 * of memory for a cache with a max reply size of 100 bytes (diropokres).
 *
 * If we should start to use different types of cache entries tailored
 * specifically for attrstat and fh's, we may save even more space.
 *
 * Also note that a cachetype of RC_NOCACHE can legally be passed when
 * nfsd failed to encode a reply that otherwise would have been cached.
 * In this case, nfsd_cache_update is called with statp == NULL.
 */
void
nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp)
{
	struct svc_cacherep *rp;
	struct kvec	*resv = &rqstp->rq_res.head[0], *cachv;
	int		len;

	if (!(rp = rqstp->rq_cacherep) || cache_disabled)
		return;

	len = resv->iov_len - ((char*)statp - (char*)resv->iov_base);
	len >>= 2;

	/* Don't cache excessive amounts of data and XDR failures */
	if (!statp || len > (256 >> 2)) {
		rp->c_state = RC_UNUSED;
		return;
	}

	switch (cachetype) {
	case RC_REPLSTAT:
		if (len != 1)
			printk("nfsd: RC_REPLSTAT/reply len %d!\n",len);
		rp->c_replstat = *statp;
		break;
	case RC_REPLBUFF:
		cachv = &rp->c_replvec;
		cachv->iov_base = kmalloc(len << 2, GFP_KERNEL);
		if (!cachv->iov_base) {
			spin_lock(&cache_lock);
			rp->c_state = RC_UNUSED;
			spin_unlock(&cache_lock);
			return;
		}
		cachv->iov_len = len << 2;
		memcpy(cachv->iov_base, statp, len << 2);
		break;
	}
	spin_lock(&cache_lock);
	lru_put_end(rp);
	rp->c_secure = rqstp->rq_secure;
	rp->c_type = cachetype;
	rp->c_state = RC_DONE;
	rp->c_timestamp = jiffies;
	spin_unlock(&cache_lock);
	return;
}

/*
 * Copy cached reply to current reply buffer. Should always fit.
 * FIXME as reply is in a page, we should just attach the page, and
 * keep a refcount....
 */
static int
nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *data)
{
	struct kvec	*vec = &rqstp->rq_res.head[0];

	if (vec->iov_len + data->iov_len > PAGE_SIZE) {
		printk(KERN_WARNING "nfsd: cached reply too large (%Zd).\n",
				data->iov_len);
		return 0;
	}
	memcpy((char*)vec->iov_base + vec->iov_len, data->iov_base, data->iov_len);
	vec->iov_len += data->iov_len;
	return 1;
}