summaryrefslogtreecommitdiff
path: root/fs/nfs/pnfs.c
blob: 891a0c36f9924909e828389b157a78296359994b (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
/*
 *  pNFS functions to call and manage layout drivers.
 *
 *  Copyright (c) 2002 [year of first publication]
 *  The Regents of the University of Michigan
 *  All Rights Reserved
 *
 *  Dean Hildebrand <dhildebz@umich.edu>
 *
 *  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/nfs_fs.h>
#include "internal.h"
#include "pnfs.h"

#define NFSDBG_FACILITY		NFSDBG_PNFS

/* Locking:
 *
 * pnfs_spinlock:
 *      protects pnfs_modules_tbl.
 */
static DEFINE_SPINLOCK(pnfs_spinlock);

/*
 * pnfs_modules_tbl holds all pnfs modules
 */
static LIST_HEAD(pnfs_modules_tbl);

/* Return the registered pnfs layout driver module matching given id */
static struct pnfs_layoutdriver_type *
find_pnfs_driver_locked(u32 id)
{
	struct pnfs_layoutdriver_type *local;

	list_for_each_entry(local, &pnfs_modules_tbl, pnfs_tblid)
		if (local->id == id)
			goto out;
	local = NULL;
out:
	dprintk("%s: Searching for id %u, found %p\n", __func__, id, local);
	return local;
}

static struct pnfs_layoutdriver_type *
find_pnfs_driver(u32 id)
{
	struct pnfs_layoutdriver_type *local;

	spin_lock(&pnfs_spinlock);
	local = find_pnfs_driver_locked(id);
	spin_unlock(&pnfs_spinlock);
	return local;
}

void
unset_pnfs_layoutdriver(struct nfs_server *nfss)
{
	if (nfss->pnfs_curr_ld) {
		nfss->pnfs_curr_ld->uninitialize_mountpoint(nfss);
		module_put(nfss->pnfs_curr_ld->owner);
	}
	nfss->pnfs_curr_ld = NULL;
}

/*
 * Try to set the server's pnfs module to the pnfs layout type specified by id.
 * Currently only one pNFS layout driver per filesystem is supported.
 *
 * @id layout type. Zero (illegal layout type) indicates pNFS not in use.
 */
void
set_pnfs_layoutdriver(struct nfs_server *server, u32 id)
{
	struct pnfs_layoutdriver_type *ld_type = NULL;

	if (id == 0)
		goto out_no_driver;
	if (!(server->nfs_client->cl_exchange_flags &
		 (EXCHGID4_FLAG_USE_NON_PNFS | EXCHGID4_FLAG_USE_PNFS_MDS))) {
		printk(KERN_ERR "%s: id %u cl_exchange_flags 0x%x\n", __func__,
		       id, server->nfs_client->cl_exchange_flags);
		goto out_no_driver;
	}
	ld_type = find_pnfs_driver(id);
	if (!ld_type) {
		request_module("%s-%u", LAYOUT_NFSV4_1_MODULE_PREFIX, id);
		ld_type = find_pnfs_driver(id);
		if (!ld_type) {
			dprintk("%s: No pNFS module found for %u.\n",
				__func__, id);
			goto out_no_driver;
		}
	}
	if (!try_module_get(ld_type->owner)) {
		dprintk("%s: Could not grab reference on module\n", __func__);
		goto out_no_driver;
	}
	server->pnfs_curr_ld = ld_type;
	if (ld_type->initialize_mountpoint(server)) {
		printk(KERN_ERR
		       "%s: Error initializing mount point for layout driver %u.\n",
		       __func__, id);
		module_put(ld_type->owner);
		goto out_no_driver;
	}
	dprintk("%s: pNFS module for %u set\n", __func__, id);
	return;

out_no_driver:
	dprintk("%s: Using NFSv4 I/O\n", __func__);
	server->pnfs_curr_ld = NULL;
}

int
pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *ld_type)
{
	int status = -EINVAL;
	struct pnfs_layoutdriver_type *tmp;

	if (ld_type->id == 0) {
		printk(KERN_ERR "%s id 0 is reserved\n", __func__);
		return status;
	}

	spin_lock(&pnfs_spinlock);
	tmp = find_pnfs_driver_locked(ld_type->id);
	if (!tmp) {
		list_add(&ld_type->pnfs_tblid, &pnfs_modules_tbl);
		status = 0;
		dprintk("%s Registering id:%u name:%s\n", __func__, ld_type->id,
			ld_type->name);
	} else {
		printk(KERN_ERR "%s Module with id %d already loaded!\n",
			__func__, ld_type->id);
	}
	spin_unlock(&pnfs_spinlock);

	return status;
}
EXPORT_SYMBOL_GPL(pnfs_register_layoutdriver);

void
pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *ld_type)
{
	dprintk("%s Deregistering id:%u\n", __func__, ld_type->id);
	spin_lock(&pnfs_spinlock);
	list_del(&ld_type->pnfs_tblid);
	spin_unlock(&pnfs_spinlock);
}
EXPORT_SYMBOL_GPL(pnfs_unregister_layoutdriver);

static void
get_layout_hdr_locked(struct pnfs_layout_hdr *lo)
{
	assert_spin_locked(&lo->inode->i_lock);
	lo->refcount++;
}

static void
put_layout_hdr_locked(struct pnfs_layout_hdr *lo)
{
	assert_spin_locked(&lo->inode->i_lock);
	BUG_ON(lo->refcount == 0);

	lo->refcount--;
	if (!lo->refcount) {
		dprintk("%s: freeing layout cache %p\n", __func__, lo);
		BUG_ON(!list_empty(&lo->layouts));
		NFS_I(lo->inode)->layout = NULL;
		kfree(lo);
	}
}

static void
put_layout_hdr(struct inode *inode)
{
	spin_lock(&inode->i_lock);
	put_layout_hdr_locked(NFS_I(inode)->layout);
	spin_unlock(&inode->i_lock);
}

static void
init_lseg(struct pnfs_layout_hdr *lo, struct pnfs_layout_segment *lseg)
{
	INIT_LIST_HEAD(&lseg->fi_list);
	kref_init(&lseg->kref);
	lseg->layout = lo;
}

/* Called without i_lock held, as the free_lseg call may sleep */
static void
destroy_lseg(struct kref *kref)
{
	struct pnfs_layout_segment *lseg =
		container_of(kref, struct pnfs_layout_segment, kref);
	struct inode *ino = lseg->layout->inode;

	dprintk("--> %s\n", __func__);
	kfree(lseg);
	/* Matched by get_layout_hdr_locked in pnfs_insert_layout */
	put_layout_hdr(ino);
}

static void
put_lseg(struct pnfs_layout_segment *lseg)
{
	if (!lseg)
		return;

	dprintk("%s: lseg %p ref %d\n", __func__, lseg,
		atomic_read(&lseg->kref.refcount));
	kref_put(&lseg->kref, destroy_lseg);
}

static void
pnfs_clear_lseg_list(struct pnfs_layout_hdr *lo, struct list_head *tmp_list)
{
	struct pnfs_layout_segment *lseg, *next;
	struct nfs_client *clp;

	dprintk("%s:Begin lo %p\n", __func__, lo);

	assert_spin_locked(&lo->inode->i_lock);
	list_for_each_entry_safe(lseg, next, &lo->segs, fi_list) {
		dprintk("%s: freeing lseg %p\n", __func__, lseg);
		list_move(&lseg->fi_list, tmp_list);
	}
	clp = NFS_SERVER(lo->inode)->nfs_client;
	spin_lock(&clp->cl_lock);
	/* List does not take a reference, so no need for put here */
	list_del_init(&lo->layouts);
	spin_unlock(&clp->cl_lock);

	dprintk("%s:Return\n", __func__);
}

static void
pnfs_free_lseg_list(struct list_head *tmp_list)
{
	struct pnfs_layout_segment *lseg;

	while (!list_empty(tmp_list)) {
		lseg = list_entry(tmp_list->next, struct pnfs_layout_segment,
				fi_list);
		dprintk("%s calling put_lseg on %p\n", __func__, lseg);
		list_del(&lseg->fi_list);
		put_lseg(lseg);
	}
}

void
pnfs_destroy_layout(struct nfs_inode *nfsi)
{
	struct pnfs_layout_hdr *lo;
	LIST_HEAD(tmp_list);

	spin_lock(&nfsi->vfs_inode.i_lock);
	lo = nfsi->layout;
	if (lo) {
		pnfs_clear_lseg_list(lo, &tmp_list);
		/* Matched by refcount set to 1 in alloc_init_layout_hdr */
		put_layout_hdr_locked(lo);
	}
	spin_unlock(&nfsi->vfs_inode.i_lock);
	pnfs_free_lseg_list(&tmp_list);
}

/*
 * Called by the state manger to remove all layouts established under an
 * expired lease.
 */
void
pnfs_destroy_all_layouts(struct nfs_client *clp)
{
	struct pnfs_layout_hdr *lo;
	LIST_HEAD(tmp_list);

	spin_lock(&clp->cl_lock);
	list_splice_init(&clp->cl_layouts, &tmp_list);
	spin_unlock(&clp->cl_lock);

	while (!list_empty(&tmp_list)) {
		lo = list_entry(tmp_list.next, struct pnfs_layout_hdr,
				layouts);
		dprintk("%s freeing layout for inode %lu\n", __func__,
			lo->inode->i_ino);
		pnfs_destroy_layout(NFS_I(lo->inode));
	}
}

static void pnfs_insert_layout(struct pnfs_layout_hdr *lo,
			       struct pnfs_layout_segment *lseg);

/* Get layout from server. */
static struct pnfs_layout_segment *
send_layoutget(struct pnfs_layout_hdr *lo,
	   struct nfs_open_context *ctx,
	   u32 iomode)
{
	struct inode *ino = lo->inode;
	struct pnfs_layout_segment *lseg;

	/* Lets pretend we sent LAYOUTGET and got a response */
	lseg = kzalloc(sizeof(*lseg), GFP_KERNEL);
	if (!lseg) {
		set_bit(lo_fail_bit(iomode), &lo->state);
		spin_lock(&ino->i_lock);
		put_layout_hdr_locked(lo);
		spin_unlock(&ino->i_lock);
		return NULL;
	}
	init_lseg(lo, lseg);
	lseg->iomode = IOMODE_RW;
	spin_lock(&ino->i_lock);
	pnfs_insert_layout(lo, lseg);
	put_layout_hdr_locked(lo);
	spin_unlock(&ino->i_lock);
	return lseg;
}

static void
pnfs_insert_layout(struct pnfs_layout_hdr *lo,
		   struct pnfs_layout_segment *lseg)
{
	dprintk("%s:Begin\n", __func__);

	assert_spin_locked(&lo->inode->i_lock);
	if (list_empty(&lo->segs)) {
		struct nfs_client *clp = NFS_SERVER(lo->inode)->nfs_client;

		spin_lock(&clp->cl_lock);
		BUG_ON(!list_empty(&lo->layouts));
		list_add_tail(&lo->layouts, &clp->cl_layouts);
		spin_unlock(&clp->cl_lock);
	}
	get_layout_hdr_locked(lo);
	/* STUB - add the constructed lseg if necessary */
	if (list_empty(&lo->segs)) {
		list_add_tail(&lseg->fi_list, &lo->segs);
		dprintk("%s: inserted lseg %p iomode %d at tail\n",
			__func__, lseg, lseg->iomode);
	} else {
		/* There is no harm for the moment in calling this
		 * with the lock held, and the call will be removed
		 * with the STUB.
		 */
		put_lseg(lseg);
	}

	dprintk("%s:Return\n", __func__);
}

static struct pnfs_layout_hdr *
alloc_init_layout_hdr(struct inode *ino)
{
	struct pnfs_layout_hdr *lo;

	lo = kzalloc(sizeof(struct pnfs_layout_hdr), GFP_KERNEL);
	if (!lo)
		return NULL;
	lo->refcount = 1;
	INIT_LIST_HEAD(&lo->layouts);
	INIT_LIST_HEAD(&lo->segs);
	lo->inode = ino;
	return lo;
}

static struct pnfs_layout_hdr *
pnfs_find_alloc_layout(struct inode *ino)
{
	struct nfs_inode *nfsi = NFS_I(ino);
	struct pnfs_layout_hdr *new = NULL;

	dprintk("%s Begin ino=%p layout=%p\n", __func__, ino, nfsi->layout);

	assert_spin_locked(&ino->i_lock);
	if (nfsi->layout)
		return nfsi->layout;

	spin_unlock(&ino->i_lock);
	new = alloc_init_layout_hdr(ino);
	spin_lock(&ino->i_lock);

	if (likely(nfsi->layout == NULL))	/* Won the race? */
		nfsi->layout = new;
	else
		kfree(new);
	return nfsi->layout;
}

/* STUB - LAYOUTGET never succeeds, so cache is empty */
static struct pnfs_layout_segment *
pnfs_has_layout(struct pnfs_layout_hdr *lo, u32 iomode)
{
	return NULL;
}

/*
 * Layout segment is retreived from the server if not cached.
 * The appropriate layout segment is referenced and returned to the caller.
 */
struct pnfs_layout_segment *
pnfs_update_layout(struct inode *ino,
		   struct nfs_open_context *ctx,
		   enum pnfs_iomode iomode)
{
	struct nfs_inode *nfsi = NFS_I(ino);
	struct pnfs_layout_hdr *lo;
	struct pnfs_layout_segment *lseg = NULL;

	if (!pnfs_enabled_sb(NFS_SERVER(ino)))
		return NULL;
	spin_lock(&ino->i_lock);
	lo = pnfs_find_alloc_layout(ino);
	if (lo == NULL) {
		dprintk("%s ERROR: can't get pnfs_layout_hdr\n", __func__);
		goto out_unlock;
	}

	/* Check to see if the layout for the given range already exists */
	lseg = pnfs_has_layout(lo, iomode);
	if (lseg) {
		dprintk("%s: Using cached lseg %p for iomode %d)\n",
			__func__, lseg, iomode);
		goto out_unlock;
	}

	/* if LAYOUTGET already failed once we don't try again */
	if (test_bit(lo_fail_bit(iomode), &nfsi->layout->state))
		goto out_unlock;

	get_layout_hdr_locked(lo);
	spin_unlock(&ino->i_lock);

	lseg = send_layoutget(lo, ctx, iomode);
out:
	dprintk("%s end, state 0x%lx lseg %p\n", __func__,
		nfsi->layout->state, lseg);
	return lseg;
out_unlock:
	spin_unlock(&ino->i_lock);
	goto out;
}