summaryrefslogtreecommitdiff
path: root/fs/nfs/pnfs_dev.c
blob: 178001c90156fdb8dd107ae62821f0ebd56b27de (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
/*
 *  Device operations for the pnfs client.
 *
 *  Copyright (c) 2002
 *  The Regents of the University of Michigan
 *  All Rights Reserved
 *
 *  Dean Hildebrand <dhildebz@umich.edu>
 *  Garth Goodson   <Garth.Goodson@netapp.com>
 *
 *  Permission is granted to use, copy, create derivative works, and
 *  redistribute this software and such derivative works for any purpose,
 *  so long as the name of the University of Michigan is not used in
 *  any advertising or publicity pertaining to the use or distribution
 *  of this software without specific, written prior authorization. If
 *  the above copyright notice or any other identification of the
 *  University of Michigan is included in any copy of any portion of
 *  this software, then the disclaimer below must also be included.
 *
 *  This software is provided as is, without representation or warranty
 *  of any kind either express or implied, including without limitation
 *  the implied warranties of merchantability, fitness for a particular
 *  purpose, or noninfringement.  The Regents of the University of
 *  Michigan shall not be liable for any damages, including special,
 *  indirect, incidental, or consequential damages, with respect to any
 *  claim arising out of or in connection with the use of the software,
 *  even if it has been or is hereafter advised of the possibility of
 *  such damages.
 */

#include <linux/export.h>
#include <linux/nfs_fs.h>
#include "nfs4session.h"
#include "internal.h"
#include "pnfs.h"

#include "nfs4trace.h"

#define NFSDBG_FACILITY		NFSDBG_PNFS

/*
 * Device ID RCU cache. A device ID is unique per server and layout type.
 */
#define NFS4_DEVICE_ID_HASH_BITS	5
#define NFS4_DEVICE_ID_HASH_SIZE	(1 << NFS4_DEVICE_ID_HASH_BITS)
#define NFS4_DEVICE_ID_HASH_MASK	(NFS4_DEVICE_ID_HASH_SIZE - 1)


static struct hlist_head nfs4_deviceid_cache[NFS4_DEVICE_ID_HASH_SIZE];
static DEFINE_SPINLOCK(nfs4_deviceid_lock);

#ifdef NFS_DEBUG
void
nfs4_print_deviceid(const struct nfs4_deviceid *id)
{
	u32 *p = (u32 *)id;

	dprintk("%s: device id= [%x%x%x%x]\n", __func__,
		p[0], p[1], p[2], p[3]);
}
EXPORT_SYMBOL_GPL(nfs4_print_deviceid);
#endif

static inline u32
nfs4_deviceid_hash(const struct nfs4_deviceid *id)
{
	unsigned char *cptr = (unsigned char *)id->data;
	unsigned int nbytes = NFS4_DEVICEID4_SIZE;
	u32 x = 0;

	while (nbytes--) {
		x *= 37;
		x += *cptr++;
	}
	return x & NFS4_DEVICE_ID_HASH_MASK;
}

static struct nfs4_deviceid_node *
_lookup_deviceid(const struct pnfs_layoutdriver_type *ld,
		 const struct nfs_client *clp, const struct nfs4_deviceid *id,
		 long hash)
{
	struct nfs4_deviceid_node *d;

	hlist_for_each_entry_rcu(d, &nfs4_deviceid_cache[hash], node)
		if (d->ld == ld && d->nfs_client == clp &&
		    !memcmp(&d->deviceid, id, sizeof(*id))) {
			if (atomic_read(&d->ref))
				return d;
			else
				continue;
		}
	return NULL;
}

static struct nfs4_deviceid_node *
nfs4_get_device_info(struct nfs_server *server,
		const struct nfs4_deviceid *dev_id,
		const struct cred *cred, gfp_t gfp_flags)
{
	struct nfs4_deviceid_node *d = NULL;
	struct pnfs_device *pdev = NULL;
	struct page **pages = NULL;
	u32 max_resp_sz;
	int max_pages;
	int rc, i;

	/*
	 * Use the session max response size as the basis for setting
	 * GETDEVICEINFO's maxcount
	 */
	max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz;
	if (server->pnfs_curr_ld->max_deviceinfo_size &&
	    server->pnfs_curr_ld->max_deviceinfo_size < max_resp_sz)
		max_resp_sz = server->pnfs_curr_ld->max_deviceinfo_size;
	max_pages = nfs_page_array_len(0, max_resp_sz);
	dprintk("%s: server %p max_resp_sz %u max_pages %d\n",
		__func__, server, max_resp_sz, max_pages);

	pdev = kzalloc(sizeof(*pdev), gfp_flags);
	if (!pdev)
		return NULL;

	pages = kcalloc(max_pages, sizeof(struct page *), gfp_flags);
	if (!pages)
		goto out_free_pdev;

	for (i = 0; i < max_pages; i++) {
		pages[i] = alloc_page(gfp_flags);
		if (!pages[i])
			goto out_free_pages;
	}

	memcpy(&pdev->dev_id, dev_id, sizeof(*dev_id));
	pdev->layout_type = server->pnfs_curr_ld->id;
	pdev->pages = pages;
	pdev->pgbase = 0;
	pdev->pglen = max_resp_sz;
	pdev->mincount = 0;
	pdev->maxcount = max_resp_sz - nfs41_maxgetdevinfo_overhead;

	rc = nfs4_proc_getdeviceinfo(server, pdev, cred);
	dprintk("%s getdevice info returns %d\n", __func__, rc);
	if (rc)
		goto out_free_pages;

	/*
	 * Found new device, need to decode it and then add it to the
	 * list of known devices for this mountpoint.
	 */
	d = server->pnfs_curr_ld->alloc_deviceid_node(server, pdev,
			gfp_flags);
	if (d && pdev->nocache)
		set_bit(NFS_DEVICEID_NOCACHE, &d->flags);

out_free_pages:
	while (--i >= 0)
		__free_page(pages[i]);
	kfree(pages);
out_free_pdev:
	kfree(pdev);
	dprintk("<-- %s d %p\n", __func__, d);
	return d;
}

/*
 * Lookup a deviceid in cache and get a reference count on it if found
 *
 * @clp nfs_client associated with deviceid
 * @id deviceid to look up
 */
static struct nfs4_deviceid_node *
__nfs4_find_get_deviceid(struct nfs_server *server,
		const struct nfs4_deviceid *id, long hash)
{
	struct nfs4_deviceid_node *d;

	rcu_read_lock();
	d = _lookup_deviceid(server->pnfs_curr_ld, server->nfs_client, id,
			hash);
	if (d != NULL && !atomic_inc_not_zero(&d->ref))
		d = NULL;
	rcu_read_unlock();
	return d;
}

struct nfs4_deviceid_node *
nfs4_find_get_deviceid(struct nfs_server *server,
		const struct nfs4_deviceid *id, const struct cred *cred,
		gfp_t gfp_mask)
{
	long hash = nfs4_deviceid_hash(id);
	struct nfs4_deviceid_node *d, *new;

	d = __nfs4_find_get_deviceid(server, id, hash);
	if (d)
		goto found;

	new = nfs4_get_device_info(server, id, cred, gfp_mask);
	if (!new) {
		trace_nfs4_find_deviceid(server, id, -ENOENT);
		return new;
	}

	spin_lock(&nfs4_deviceid_lock);
	d = __nfs4_find_get_deviceid(server, id, hash);
	if (d) {
		spin_unlock(&nfs4_deviceid_lock);
		server->pnfs_curr_ld->free_deviceid_node(new);
	} else {
		atomic_inc(&new->ref);
		hlist_add_head_rcu(&new->node, &nfs4_deviceid_cache[hash]);
		spin_unlock(&nfs4_deviceid_lock);
		d = new;
	}
found:
	trace_nfs4_find_deviceid(server, id, 0);
	return d;
}
EXPORT_SYMBOL_GPL(nfs4_find_get_deviceid);

/*
 * Remove a deviceid from cache
 *
 * @clp nfs_client associated with deviceid
 * @id the deviceid to unhash
 *
 * @ret the unhashed node, if found and dereferenced to zero, NULL otherwise.
 */
void
nfs4_delete_deviceid(const struct pnfs_layoutdriver_type *ld,
			 const struct nfs_client *clp, const struct nfs4_deviceid *id)
{
	struct nfs4_deviceid_node *d;

	spin_lock(&nfs4_deviceid_lock);
	rcu_read_lock();
	d = _lookup_deviceid(ld, clp, id, nfs4_deviceid_hash(id));
	rcu_read_unlock();
	if (!d) {
		spin_unlock(&nfs4_deviceid_lock);
		return;
	}
	hlist_del_init_rcu(&d->node);
	clear_bit(NFS_DEVICEID_NOCACHE, &d->flags);
	spin_unlock(&nfs4_deviceid_lock);

	/* balance the initial ref set in pnfs_insert_deviceid */
	nfs4_put_deviceid_node(d);
}
EXPORT_SYMBOL_GPL(nfs4_delete_deviceid);

void
nfs4_init_deviceid_node(struct nfs4_deviceid_node *d, struct nfs_server *server,
			const struct nfs4_deviceid *id)
{
	INIT_HLIST_NODE(&d->node);
	INIT_HLIST_NODE(&d->tmpnode);
	d->ld = server->pnfs_curr_ld;
	d->nfs_client = server->nfs_client;
	d->flags = 0;
	d->deviceid = *id;
	atomic_set(&d->ref, 1);
}
EXPORT_SYMBOL_GPL(nfs4_init_deviceid_node);

/*
 * Dereference a deviceid node and delete it when its reference count drops
 * to zero.
 *
 * @d deviceid node to put
 *
 * return true iff the node was deleted
 * Note that since the test for d->ref == 0 is sufficient to establish
 * that the node is no longer hashed in the global device id cache.
 */
bool
nfs4_put_deviceid_node(struct nfs4_deviceid_node *d)
{
	if (test_bit(NFS_DEVICEID_NOCACHE, &d->flags)) {
		if (atomic_add_unless(&d->ref, -1, 2))
			return false;
		nfs4_delete_deviceid(d->ld, d->nfs_client, &d->deviceid);
	}
	if (!atomic_dec_and_test(&d->ref))
		return false;
	trace_nfs4_deviceid_free(d->nfs_client, &d->deviceid);
	d->ld->free_deviceid_node(d);
	return true;
}
EXPORT_SYMBOL_GPL(nfs4_put_deviceid_node);

void
nfs4_mark_deviceid_available(struct nfs4_deviceid_node *node)
{
	if (test_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags)) {
		clear_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags);
		smp_mb__after_atomic();
	}
}
EXPORT_SYMBOL_GPL(nfs4_mark_deviceid_available);

void
nfs4_mark_deviceid_unavailable(struct nfs4_deviceid_node *node)
{
	node->timestamp_unavailable = jiffies;
	smp_mb__before_atomic();
	set_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags);
	smp_mb__after_atomic();
}
EXPORT_SYMBOL_GPL(nfs4_mark_deviceid_unavailable);

bool
nfs4_test_deviceid_unavailable(struct nfs4_deviceid_node *node)
{
	if (test_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags)) {
		unsigned long start, end;

		end = jiffies;
		start = end - PNFS_DEVICE_RETRY_TIMEOUT;
		if (time_in_range(node->timestamp_unavailable, start, end))
			return true;
		clear_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags);
		smp_mb__after_atomic();
	}
	return false;
}
EXPORT_SYMBOL_GPL(nfs4_test_deviceid_unavailable);

static void
_deviceid_purge_client(const struct nfs_client *clp, long hash)
{
	struct nfs4_deviceid_node *d;
	HLIST_HEAD(tmp);

	spin_lock(&nfs4_deviceid_lock);
	rcu_read_lock();
	hlist_for_each_entry_rcu(d, &nfs4_deviceid_cache[hash], node)
		if (d->nfs_client == clp && atomic_read(&d->ref)) {
			hlist_del_init_rcu(&d->node);
			hlist_add_head(&d->tmpnode, &tmp);
			clear_bit(NFS_DEVICEID_NOCACHE, &d->flags);
		}
	rcu_read_unlock();
	spin_unlock(&nfs4_deviceid_lock);

	if (hlist_empty(&tmp))
		return;

	while (!hlist_empty(&tmp)) {
		d = hlist_entry(tmp.first, struct nfs4_deviceid_node, tmpnode);
		hlist_del(&d->tmpnode);
		nfs4_put_deviceid_node(d);
	}
}

void
nfs4_deviceid_purge_client(const struct nfs_client *clp)
{
	long h;

	if (!(clp->cl_exchange_flags & EXCHGID4_FLAG_USE_PNFS_MDS))
		return;
	for (h = 0; h < NFS4_DEVICE_ID_HASH_SIZE; h++)
		_deviceid_purge_client(clp, h);
}

/*
 * Stop use of all deviceids associated with an nfs_client
 */
void
nfs4_deviceid_mark_client_invalid(struct nfs_client *clp)
{
	struct nfs4_deviceid_node *d;
	int i;

	rcu_read_lock();
	for (i = 0; i < NFS4_DEVICE_ID_HASH_SIZE; i ++){
		hlist_for_each_entry_rcu(d, &nfs4_deviceid_cache[i], node)
			if (d->nfs_client == clp)
				set_bit(NFS_DEVICEID_INVALID, &d->flags);
	}
	rcu_read_unlock();
}