summaryrefslogtreecommitdiffstats
path: root/fs/nfs/delegation.c
blob: ebc06f2da31ad9601c709c185a518fe122783b56 (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
/*
 * linux/fs/nfs/delegation.c
 *
 * Copyright (C) 2004 Trond Myklebust
 *
 * NFS file delegation management
 *
 */
#include <linux/completion.h>
#include <linux/kthread.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/spinlock.h>

#include <linux/nfs4.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_xdr.h>

#include "nfs4_fs.h"
#include "delegation.h"
#include "internal.h"

static void nfs_do_free_delegation(struct nfs_delegation *delegation)
{
	kfree(delegation);
}

static void nfs_free_delegation_callback(struct rcu_head *head)
{
	struct nfs_delegation *delegation = container_of(head, struct nfs_delegation, rcu);

	nfs_do_free_delegation(delegation);
}

static void nfs_free_delegation(struct nfs_delegation *delegation)
{
	struct rpc_cred *cred;

	cred = rcu_dereference(delegation->cred);
	rcu_assign_pointer(delegation->cred, NULL);
	call_rcu(&delegation->rcu, nfs_free_delegation_callback);
	if (cred)
		put_rpccred(cred);
}

static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_state *state)
{
	struct inode *inode = state->inode;
	struct file_lock *fl;
	int status;

	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
		if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK)))
			continue;
		if (nfs_file_open_context(fl->fl_file) != ctx)
			continue;
		status = nfs4_lock_delegation_recall(state, fl);
		if (status >= 0)
			continue;
		switch (status) {
			default:
				printk(KERN_ERR "%s: unhandled error %d.\n",
						__func__, status);
			case -NFS4ERR_EXPIRED:
				/* kill_proc(fl->fl_pid, SIGLOST, 1); */
			case -NFS4ERR_STALE_CLIENTID:
				nfs4_schedule_state_recovery(NFS_SERVER(inode)->nfs_client);
				goto out_err;
		}
	}
	return 0;
out_err:
	return status;
}

static void nfs_delegation_claim_opens(struct inode *inode, const nfs4_stateid *stateid)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	struct nfs_open_context *ctx;
	struct nfs4_state *state;
	int err;

again:
	spin_lock(&inode->i_lock);
	list_for_each_entry(ctx, &nfsi->open_files, list) {
		state = ctx->state;
		if (state == NULL)
			continue;
		if (!test_bit(NFS_DELEGATED_STATE, &state->flags))
			continue;
		if (memcmp(state->stateid.data, stateid->data, sizeof(state->stateid.data)) != 0)
			continue;
		get_nfs_open_context(ctx);
		spin_unlock(&inode->i_lock);
		err = nfs4_open_delegation_recall(ctx, state, stateid);
		if (err >= 0)
			err = nfs_delegation_claim_locks(ctx, state);
		put_nfs_open_context(ctx);
		if (err != 0)
			return;
		goto again;
	}
	spin_unlock(&inode->i_lock);
}

/*
 * Set up a delegation on an inode
 */
void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res)
{
	struct nfs_delegation *delegation = NFS_I(inode)->delegation;
	struct rpc_cred *oldcred;

	if (delegation == NULL)
		return;
	memcpy(delegation->stateid.data, res->delegation.data,
			sizeof(delegation->stateid.data));
	delegation->type = res->delegation_type;
	delegation->maxsize = res->maxsize;
	oldcred = delegation->cred;
	delegation->cred = get_rpccred(cred);
	clear_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags);
	NFS_I(inode)->delegation_state = delegation->type;
	smp_wmb();
	put_rpccred(oldcred);
}

static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation *delegation, int issync)
{
	int res = 0;

	res = nfs4_proc_delegreturn(inode, delegation->cred, &delegation->stateid, issync);
	nfs_free_delegation(delegation);
	return res;
}

static struct inode *nfs_delegation_grab_inode(struct nfs_delegation *delegation)
{
	struct inode *inode = NULL;

	spin_lock(&delegation->lock);
	if (delegation->inode != NULL)
		inode = igrab(delegation->inode);
	spin_unlock(&delegation->lock);
	return inode;
}

static struct nfs_delegation *nfs_detach_delegation_locked(struct nfs_inode *nfsi, const nfs4_stateid *stateid)
{
	struct nfs_delegation *delegation = rcu_dereference(nfsi->delegation);

	if (delegation == NULL)
		goto nomatch;
	spin_lock(&delegation->lock);
	if (stateid != NULL && memcmp(delegation->stateid.data, stateid->data,
				sizeof(delegation->stateid.data)) != 0)
		goto nomatch_unlock;
	list_del_rcu(&delegation->super_list);
	delegation->inode = NULL;
	nfsi->delegation_state = 0;
	rcu_assign_pointer(nfsi->delegation, NULL);
	spin_unlock(&delegation->lock);
	return delegation;
nomatch_unlock:
	spin_unlock(&delegation->lock);
nomatch:
	return NULL;
}

/*
 * Set up a delegation on an inode
 */
int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res)
{
	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
	struct nfs_inode *nfsi = NFS_I(inode);
	struct nfs_delegation *delegation;
	struct nfs_delegation *freeme = NULL;
	int status = 0;

	delegation = kmalloc(sizeof(*delegation), GFP_KERNEL);
	if (delegation == NULL)
		return -ENOMEM;
	memcpy(delegation->stateid.data, res->delegation.data,
			sizeof(delegation->stateid.data));
	delegation->type = res->delegation_type;
	delegation->maxsize = res->maxsize;
	delegation->change_attr = nfsi->change_attr;
	delegation->cred = get_rpccred(cred);
	delegation->inode = inode;
	spin_lock_init(&delegation->lock);

	spin_lock(&clp->cl_lock);
	if (rcu_dereference(nfsi->delegation) != NULL) {
		if (memcmp(&delegation->stateid, &nfsi->delegation->stateid,
					sizeof(delegation->stateid)) == 0 &&
				delegation->type == nfsi->delegation->type) {
			goto out;
		}
		/*
		 * Deal with broken servers that hand out two
		 * delegations for the same file.
		 */
		dfprintk(FILE, "%s: server %s handed out "
				"a duplicate delegation!\n",
				__func__, clp->cl_hostname);
		if (delegation->type <= nfsi->delegation->type) {
			freeme = delegation;
			delegation = NULL;
			goto out;
		}
		freeme = nfs_detach_delegation_locked(nfsi, NULL);
	}
	list_add_rcu(&delegation->super_list, &clp->cl_delegations);
	nfsi->delegation_state = delegation->type;
	rcu_assign_pointer(nfsi->delegation, delegation);
	delegation = NULL;

	/* Ensure we revalidate the attributes and page cache! */
	spin_lock(&inode->i_lock);
	nfsi->cache_validity |= NFS_INO_REVAL_FORCED;
	spin_unlock(&inode->i_lock);

out:
	spin_unlock(&clp->cl_lock);
	if (delegation != NULL)
		nfs_free_delegation(delegation);
	if (freeme != NULL)
		nfs_do_return_delegation(inode, freeme, 0);
	return status;
}

/* Sync all data to disk upon delegation return */
static void nfs_msync_inode(struct inode *inode)
{
	filemap_fdatawrite(inode->i_mapping);
	nfs_wb_all(inode);
	filemap_fdatawait(inode->i_mapping);
}

/*
 * Basic procedure for returning a delegation to the server
 */
static int __nfs_inode_return_delegation(struct inode *inode, struct nfs_delegation *delegation)
{
	struct nfs_inode *nfsi = NFS_I(inode);

	nfs_msync_inode(inode);
	/* Guard against new delegated open calls */
	down_write(&nfsi->rwsem);
	nfs_delegation_claim_opens(inode, &delegation->stateid);
	up_write(&nfsi->rwsem);
	nfs_msync_inode(inode);

	return nfs_do_return_delegation(inode, delegation, 1);
}

/*
 * This function returns the delegation without reclaiming opens
 * or protecting against delegation reclaims.
 * It is therefore really only safe to be called from
 * nfs4_clear_inode()
 */
void nfs_inode_return_delegation_noreclaim(struct inode *inode)
{
	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
	struct nfs_inode *nfsi = NFS_I(inode);
	struct nfs_delegation *delegation;

	if (rcu_dereference(nfsi->delegation) != NULL) {
		spin_lock(&clp->cl_lock);
		delegation = nfs_detach_delegation_locked(nfsi, NULL);
		spin_unlock(&clp->cl_lock);
		if (delegation != NULL)
			nfs_do_return_delegation(inode, delegation, 0);
	}
}

int nfs_inode_return_delegation(struct inode *inode)
{
	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
	struct nfs_inode *nfsi = NFS_I(inode);
	struct nfs_delegation *delegation;
	int err = 0;

	if (rcu_dereference(nfsi->delegation) != NULL) {
		spin_lock(&clp->cl_lock);
		delegation = nfs_detach_delegation_locked(nfsi, NULL);
		spin_unlock(&clp->cl_lock);
		if (delegation != NULL)
			err = __nfs_inode_return_delegation(inode, delegation);
	}
	return err;
}

/*
 * Return all delegations associated to a super block
 */
void nfs_return_all_delegations(struct super_block *sb)
{
	struct nfs_client *clp = NFS_SB(sb)->nfs_client;
	struct nfs_delegation *delegation;
	struct inode *inode;

	if (clp == NULL)
		return;
restart:
	rcu_read_lock();
	list_for_each_entry_rcu(delegation, &clp->cl_delegations, super_list) {
		inode = NULL;
		spin_lock(&delegation->lock);
		if (delegation->inode != NULL && delegation->inode->i_sb == sb)
			inode = igrab(delegation->inode);
		spin_unlock(&delegation->lock);
		if (inode == NULL)
			continue;
		spin_lock(&clp->cl_lock);
		delegation = nfs_detach_delegation_locked(NFS_I(inode), NULL);
		spin_unlock(&clp->cl_lock);
		rcu_read_unlock();
		if (delegation != NULL)
			__nfs_inode_return_delegation(inode, delegation);
		iput(inode);
		goto restart;
	}
	rcu_read_unlock();
}

static int nfs_do_expire_all_delegations(void *ptr)
{
	struct nfs_client *clp = ptr;
	struct nfs_delegation *delegation;
	struct inode *inode;

	allow_signal(SIGKILL);
restart:
	if (test_bit(NFS4CLNT_STATE_RECOVER, &clp->cl_state) != 0)
		goto out;
	if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) == 0)
		goto out;
	rcu_read_lock();
	list_for_each_entry_rcu(delegation, &clp->cl_delegations, super_list) {
		inode = nfs_delegation_grab_inode(delegation);
		if (inode == NULL)
			continue;
		spin_lock(&clp->cl_lock);
		delegation = nfs_detach_delegation_locked(NFS_I(inode), NULL);
		spin_unlock(&clp->cl_lock);
		rcu_read_unlock();
		if (delegation)
			__nfs_inode_return_delegation(inode, delegation);
		iput(inode);
		goto restart;
	}
	rcu_read_unlock();
out:
	nfs_put_client(clp);
	module_put_and_exit(0);
}

void nfs_expire_all_delegations(struct nfs_client *clp)
{
	struct task_struct *task;

	__module_get(THIS_MODULE);
	atomic_inc(&clp->cl_count);
	task = kthread_run(nfs_do_expire_all_delegations, clp,
				"%s-delegreturn",
				rpc_peeraddr2str(clp->cl_rpcclient,
							RPC_DISPLAY_ADDR));
	if (!IS_ERR(task))
		return;
	nfs_put_client(clp);
	module_put(THIS_MODULE);
}

/*
 * Return all delegations following an NFS4ERR_CB_PATH_DOWN error.
 */
void nfs_handle_cb_pathdown(struct nfs_client *clp)
{
	struct nfs_delegation *delegation;
	struct inode *inode;

	if (clp == NULL)
		return;
restart:
	rcu_read_lock();
	list_for_each_entry_rcu(delegation, &clp->cl_delegations, super_list) {
		inode = nfs_delegation_grab_inode(delegation);
		if (inode == NULL)
			continue;
		spin_lock(&clp->cl_lock);
		delegation = nfs_detach_delegation_locked(NFS_I(inode), NULL);
		spin_unlock(&clp->cl_lock);
		rcu_read_unlock();
		if (delegation != NULL)
			__nfs_inode_return_delegation(inode, delegation);
		iput(inode);
		goto restart;
	}
	rcu_read_unlock();
}

struct recall_threadargs {
	struct inode *inode;
	struct nfs_client *clp;
	const nfs4_stateid *stateid;

	struct completion started;
	int result;
};

static int recall_thread(void *data)
{
	struct recall_threadargs *args = (struct recall_threadargs *)data;
	struct inode *inode = igrab(args->inode);
	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
	struct nfs_inode *nfsi = NFS_I(inode);
	struct nfs_delegation *delegation;

	daemonize("nfsv4-delegreturn");

	nfs_msync_inode(inode);
	down_write(&nfsi->rwsem);
	spin_lock(&clp->cl_lock);
	delegation = nfs_detach_delegation_locked(nfsi, args->stateid);
	if (delegation != NULL)
		args->result = 0;
	else
		args->result = -ENOENT;
	spin_unlock(&clp->cl_lock);
	complete(&args->started);
	nfs_delegation_claim_opens(inode, args->stateid);
	up_write(&nfsi->rwsem);
	nfs_msync_inode(inode);

	if (delegation != NULL)
		nfs_do_return_delegation(inode, delegation, 1);
	iput(inode);
	module_put_and_exit(0);
}

/*
 * Asynchronous delegation recall!
 */
int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid)
{
	struct recall_threadargs data = {
		.inode = inode,
		.stateid = stateid,
	};
	int status;

	init_completion(&data.started);
	__module_get(THIS_MODULE);
	status = kernel_thread(recall_thread, &data, CLONE_KERNEL);
	if (status < 0)
		goto out_module_put;
	wait_for_completion(&data.started);
	return data.result;
out_module_put:
	module_put(THIS_MODULE);
	return status;
}

/*
 * Retrieve the inode associated with a delegation
 */
struct inode *nfs_delegation_find_inode(struct nfs_client *clp, const struct nfs_fh *fhandle)
{
	struct nfs_delegation *delegation;
	struct inode *res = NULL;
	rcu_read_lock();
	list_for_each_entry_rcu(delegation, &clp->cl_delegations, super_list) {
		spin_lock(&delegation->lock);
		if (delegation->inode != NULL &&
		    nfs_compare_fh(fhandle, &NFS_I(delegation->inode)->fh) == 0) {
			res = igrab(delegation->inode);
		}
		spin_unlock(&delegation->lock);
		if (res != NULL)
			break;
	}
	rcu_read_unlock();
	return res;
}

/*
 * Mark all delegations as needing to be reclaimed
 */
void nfs_delegation_mark_reclaim(struct nfs_client *clp)
{
	struct nfs_delegation *delegation;
	rcu_read_lock();
	list_for_each_entry_rcu(delegation, &clp->cl_delegations, super_list)
		set_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags);
	rcu_read_unlock();
}

/*
 * Reap all unclaimed delegations after reboot recovery is done
 */
void nfs_delegation_reap_unclaimed(struct nfs_client *clp)
{
	struct nfs_delegation *delegation;
	struct inode *inode;
restart:
	rcu_read_lock();
	list_for_each_entry_rcu(delegation, &clp->cl_delegations, super_list) {
		if (test_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags) == 0)
			continue;
		inode = nfs_delegation_grab_inode(delegation);
		if (inode == NULL)
			continue;
		spin_lock(&clp->cl_lock);
		delegation = nfs_detach_delegation_locked(NFS_I(inode), NULL);
		spin_unlock(&clp->cl_lock);
		rcu_read_unlock();
		if (delegation != NULL)
			nfs_free_delegation(delegation);
		iput(inode);
		goto restart;
	}
	rcu_read_unlock();
}

int nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	struct nfs_delegation *delegation;
	int ret = 0;

	rcu_read_lock();
	delegation = rcu_dereference(nfsi->delegation);
	if (delegation != NULL) {
		memcpy(dst->data, delegation->stateid.data, sizeof(dst->data));
		ret = 1;
	}
	rcu_read_unlock();
	return ret;
}