aboutsummaryrefslogtreecommitdiffstats
path: root/fs/fuse/dev.c
blob: 104a62dadb94c9b8fa489963b51a97bc69b3dba2 (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
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
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
/*
  FUSE: Filesystem in Userspace
  Copyright (C) 2001-2006  Miklos Szeredi <miklos@szeredi.hu>

  This program can be distributed under the terms of the GNU GPL.
  See the file COPYING.
*/

#include "fuse_i.h"

#include <linux/init.h>
#include <linux/module.h>
#include <linux/poll.h>
#include <linux/uio.h>
#include <linux/miscdevice.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/slab.h>

MODULE_ALIAS_MISCDEV(FUSE_MINOR);

static kmem_cache_t *fuse_req_cachep;

static struct fuse_conn *fuse_get_conn(struct file *file)
{
	/*
	 * Lockless access is OK, because file->private data is set
	 * once during mount and is valid until the file is released.
	 */
	return file->private_data;
}

static void fuse_request_init(struct fuse_req *req)
{
	memset(req, 0, sizeof(*req));
	INIT_LIST_HEAD(&req->list);
	init_waitqueue_head(&req->waitq);
	atomic_set(&req->count, 1);
}

struct fuse_req *fuse_request_alloc(void)
{
	struct fuse_req *req = kmem_cache_alloc(fuse_req_cachep, SLAB_KERNEL);
	if (req)
		fuse_request_init(req);
	return req;
}

void fuse_request_free(struct fuse_req *req)
{
	kmem_cache_free(fuse_req_cachep, req);
}

static void block_sigs(sigset_t *oldset)
{
	sigset_t mask;

	siginitsetinv(&mask, sigmask(SIGKILL));
	sigprocmask(SIG_BLOCK, &mask, oldset);
}

static void restore_sigs(sigset_t *oldset)
{
	sigprocmask(SIG_SETMASK, oldset, NULL);
}

/*
 * Reset request, so that it can be reused
 *
 * The caller must be _very_ careful to make sure, that it is holding
 * the only reference to req
 */
void fuse_reset_request(struct fuse_req *req)
{
	BUG_ON(atomic_read(&req->count) != 1);
	fuse_request_init(req);
}

static void __fuse_get_request(struct fuse_req *req)
{
	atomic_inc(&req->count);
}

/* Must be called with > 1 refcount */
static void __fuse_put_request(struct fuse_req *req)
{
	BUG_ON(atomic_read(&req->count) < 2);
	atomic_dec(&req->count);
}

struct fuse_req *fuse_get_req(struct fuse_conn *fc)
{
	struct fuse_req *req;
	sigset_t oldset;
	int intr;
	int err;

	atomic_inc(&fc->num_waiting);
	block_sigs(&oldset);
	intr = wait_event_interruptible(fc->blocked_waitq, !fc->blocked);
	restore_sigs(&oldset);
	err = -EINTR;
	if (intr)
		goto out;

	req = fuse_request_alloc();
	err = -ENOMEM;
	if (!req)
		goto out;

	req->in.h.uid = current->fsuid;
	req->in.h.gid = current->fsgid;
	req->in.h.pid = current->pid;
	req->waiting = 1;
	return req;

 out:
	atomic_dec(&fc->num_waiting);
	return ERR_PTR(err);
}

void fuse_put_request(struct fuse_conn *fc, struct fuse_req *req)
{
	if (atomic_dec_and_test(&req->count)) {
		if (req->waiting)
			atomic_dec(&fc->num_waiting);
		fuse_request_free(req);
	}
}

/*
 * Called with sbput_sem held for read (request_end) or write
 * (fuse_put_super).  By the time fuse_put_super() is finished, all
 * inodes belonging to background requests must be released, so the
 * iputs have to be done within the locked region.
 */
void fuse_release_background(struct fuse_conn *fc, struct fuse_req *req)
{
	iput(req->inode);
	iput(req->inode2);
	spin_lock(&fc->lock);
	list_del(&req->bg_entry);
	if (fc->num_background == FUSE_MAX_BACKGROUND) {
		fc->blocked = 0;
		wake_up_all(&fc->blocked_waitq);
	}
	fc->num_background--;
	spin_unlock(&fc->lock);
}

/*
 * This function is called when a request is finished.  Either a reply
 * has arrived or it was interrupted (and not yet sent) or some error
 * occurred during communication with userspace, or the device file
 * was closed.  In case of a background request the reference to the
 * stored objects are released.  The requester thread is woken up (if
 * still waiting), the 'end' callback is called if given, else the
 * reference to the request is released
 *
 * Releasing extra reference for foreground requests must be done
 * within the same locked region as setting state to finished.  This
 * is because fuse_reset_request() may be called after request is
 * finished and it must be the sole possessor.  If request is
 * interrupted and put in the background, it will return with an error
 * and hence never be reset and reused.
 *
 * Called with fc->lock, unlocks it
 */
static void request_end(struct fuse_conn *fc, struct fuse_req *req)
{
	list_del(&req->list);
	req->state = FUSE_REQ_FINISHED;
	if (!req->background) {
		spin_unlock(&fc->lock);
		wake_up(&req->waitq);
		fuse_put_request(fc, req);
	} else {
		void (*end) (struct fuse_conn *, struct fuse_req *) = req->end;
		req->end = NULL;
		spin_unlock(&fc->lock);
		down_read(&fc->sbput_sem);
		if (fc->mounted)
			fuse_release_background(fc, req);
		up_read(&fc->sbput_sem);

		/* fput must go outside sbput_sem, otherwise it can deadlock */
		if (req->file)
			fput(req->file);

		if (end)
			end(fc, req);
		else
			fuse_put_request(fc, req);
	}
}

/*
 * Unfortunately request interruption not just solves the deadlock
 * problem, it causes problems too.  These stem from the fact, that an
 * interrupted request is continued to be processed in userspace,
 * while all the locks and object references (inode and file) held
 * during the operation are released.
 *
 * To release the locks is exactly why there's a need to interrupt the
 * request, so there's not a lot that can be done about this, except
 * introduce additional locking in userspace.
 *
 * More important is to keep inode and file references until userspace
 * has replied, otherwise FORGET and RELEASE could be sent while the
 * inode/file is still used by the filesystem.
 *
 * For this reason the concept of "background" request is introduced.
 * An interrupted request is backgrounded if it has been already sent
 * to userspace.  Backgrounding involves getting an extra reference to
 * inode(s) or file used in the request, and adding the request to
 * fc->background list.  When a reply is received for a background
 * request, the object references are released, and the request is
 * removed from the list.  If the filesystem is unmounted while there
 * are still background requests, the list is walked and references
 * are released as if a reply was received.
 *
 * There's one more use for a background request.  The RELEASE message is
 * always sent as background, since it doesn't return an error or
 * data.
 */
static void background_request(struct fuse_conn *fc, struct fuse_req *req)
{
	req->background = 1;
	list_add(&req->bg_entry, &fc->background);
	fc->num_background++;
	if (fc->num_background == FUSE_MAX_BACKGROUND)
		fc->blocked = 1;
	if (req->inode)
		req->inode = igrab(req->inode);
	if (req->inode2)
		req->inode2 = igrab(req->inode2);
	if (req->file)
		get_file(req->file);
}

/* Called with fc->lock held.  Releases, and then reacquires it. */
static void request_wait_answer(struct fuse_conn *fc, struct fuse_req *req)
{
	sigset_t oldset;

	spin_unlock(&fc->lock);
	block_sigs(&oldset);
	wait_event_interruptible(req->waitq, req->state == FUSE_REQ_FINISHED);
	restore_sigs(&oldset);
	spin_lock(&fc->lock);
	if (req->state == FUSE_REQ_FINISHED && !req->interrupted)
		return;

	if (!req->interrupted) {
		req->out.h.error = -EINTR;
		req->interrupted = 1;
	}
	if (req->locked) {
		/* This is uninterruptible sleep, because data is
		   being copied to/from the buffers of req.  During
		   locked state, there mustn't be any filesystem
		   operation (e.g. page fault), since that could lead
		   to deadlock */
		spin_unlock(&fc->lock);
		wait_event(req->waitq, !req->locked);
		spin_lock(&fc->lock);
	}
	if (req->state == FUSE_REQ_PENDING) {
		list_del(&req->list);
		__fuse_put_request(req);
	} else if (req->state == FUSE_REQ_SENT)
		background_request(fc, req);
}

static unsigned len_args(unsigned numargs, struct fuse_arg *args)
{
	unsigned nbytes = 0;
	unsigned i;

	for (i = 0; i < numargs; i++)
		nbytes += args[i].size;

	return nbytes;
}

static void queue_request(struct fuse_conn *fc, struct fuse_req *req)
{
	fc->reqctr++;
	/* zero is special */
	if (fc->reqctr == 0)
		fc->reqctr = 1;
	req->in.h.unique = fc->reqctr;
	req->in.h.len = sizeof(struct fuse_in_header) +
		len_args(req->in.numargs, (struct fuse_arg *) req->in.args);
	list_add_tail(&req->list, &fc->pending);
	req->state = FUSE_REQ_PENDING;
	if (!req->waiting) {
		req->waiting = 1;
		atomic_inc(&fc->num_waiting);
	}
	wake_up(&fc->waitq);
	kill_fasync(&fc->fasync, SIGIO, POLL_IN);
}

/*
 * This can only be interrupted by a SIGKILL
 */
void request_send(struct fuse_conn *fc, struct fuse_req *req)
{
	req->isreply = 1;
	spin_lock(&fc->lock);
	if (!fc->connected)
		req->out.h.error = -ENOTCONN;
	else if (fc->conn_error)
		req->out.h.error = -ECONNREFUSED;
	else {
		queue_request(fc, req);
		/* acquire extra reference, since request is still needed
		   after request_end() */
		__fuse_get_request(req);

		request_wait_answer(fc, req);
	}
	spin_unlock(&fc->lock);
}

static void request_send_nowait(struct fuse_conn *fc, struct fuse_req *req)
{
	spin_lock(&fc->lock);
	background_request(fc, req);
	if (fc->connected) {
		queue_request(fc, req);
		spin_unlock(&fc->lock);
	} else {
		req->out.h.error = -ENOTCONN;
		request_end(fc, req);
	}
}

void request_send_noreply(struct fuse_conn *fc, struct fuse_req *req)
{
	req->isreply = 0;
	request_send_nowait(fc, req);
}

void request_send_background(struct fuse_conn *fc, struct fuse_req *req)
{
	req->isreply = 1;
	request_send_nowait(fc, req);
}

/*
 * Lock the request.  Up to the next unlock_request() there mustn't be
 * anything that could cause a page-fault.  If the request was already
 * interrupted bail out.
 */
static int lock_request(struct fuse_conn *fc, struct fuse_req *req)
{
	int err = 0;
	if (req) {
		spin_lock(&fc->lock);
		if (req->interrupted)
			err = -ENOENT;
		else
			req->locked = 1;
		spin_unlock(&fc->lock);
	}
	return err;
}

/*
 * Unlock request.  If it was interrupted during being locked, the
 * requester thread is currently waiting for it to be unlocked, so
 * wake it up.
 */
static void unlock_request(struct fuse_conn *fc, struct fuse_req *req)
{
	if (req) {
		spin_lock(&fc->lock);
		req->locked = 0;
		if (req->interrupted)
			wake_up(&req->waitq);
		spin_unlock(&fc->lock);
	}
}

struct fuse_copy_state {
	struct fuse_conn *fc;
	int write;
	struct fuse_req *req;
	const struct iovec *iov;
	unsigned long nr_segs;
	unsigned long seglen;
	unsigned long addr;
	struct page *pg;
	void *mapaddr;
	void *buf;
	unsigned len;
};

static void fuse_copy_init(struct fuse_copy_state *cs, struct fuse_conn *fc,
			   int write, struct fuse_req *req,
			   const struct iovec *iov, unsigned long nr_segs)
{
	memset(cs, 0, sizeof(*cs));
	cs->fc = fc;
	cs->write = write;
	cs->req = req;
	cs->iov = iov;
	cs->nr_segs = nr_segs;
}

/* Unmap and put previous page of userspace buffer */
static void fuse_copy_finish(struct fuse_copy_state *cs)
{
	if (cs->mapaddr) {
		kunmap_atomic(cs->mapaddr, KM_USER0);
		if (cs->write) {
			flush_dcache_page(cs->pg);
			set_page_dirty_lock(cs->pg);
		}
		put_page(cs->pg);
		cs->mapaddr = NULL;
	}
}

/*
 * Get another pagefull of userspace buffer, and map it to kernel
 * address space, and lock request
 */
static int fuse_copy_fill(struct fuse_copy_state *cs)
{
	unsigned long offset;
	int err;

	unlock_request(cs->fc, cs->req);
	fuse_copy_finish(cs);
	if (!cs->seglen) {
		BUG_ON(!cs->nr_segs);
		cs->seglen = cs->iov[0].iov_len;
		cs->addr = (unsigned long) cs->iov[0].iov_base;
		cs->iov ++;
		cs->nr_segs --;
	}
	down_read(&current->mm->mmap_sem);
	err = get_user_pages(current, current->mm, cs->addr, 1, cs->write, 0,
			     &cs->pg, NULL);
	up_read(&current->mm->mmap_sem);
	if (err < 0)
		return err;
	BUG_ON(err != 1);
	offset = cs->addr % PAGE_SIZE;
	cs->mapaddr = kmap_atomic(cs->pg, KM_USER0);
	cs->buf = cs->mapaddr + offset;
	cs->len = min(PAGE_SIZE - offset, cs->seglen);
	cs->seglen -= cs->len;
	cs->addr += cs->len;

	return lock_request(cs->fc, cs->req);
}

/* Do as much copy to/from userspace buffer as we can */
static int fuse_copy_do(struct fuse_copy_state *cs, void **val, unsigned *size)
{
	unsigned ncpy = min(*size, cs->len);
	if (val) {
		if (cs->write)
			memcpy(cs->buf, *val, ncpy);
		else
			memcpy(*val, cs->buf, ncpy);
		*val += ncpy;
	}
	*size -= ncpy;
	cs->len -= ncpy;
	cs->buf += ncpy;
	return ncpy;
}

/*
 * Copy a page in the request to/from the userspace buffer.  Must be
 * done atomically
 */
static int fuse_copy_page(struct fuse_copy_state *cs, struct page *page,
			  unsigned offset, unsigned count, int zeroing)
{
	if (page && zeroing && count < PAGE_SIZE) {
		void *mapaddr = kmap_atomic(page, KM_USER1);
		memset(mapaddr, 0, PAGE_SIZE);
		kunmap_atomic(mapaddr, KM_USER1);
	}
	while (count) {
		int err;
		if (!cs->len && (err = fuse_copy_fill(cs)))
			return err;
		if (page) {
			void *mapaddr = kmap_atomic(page, KM_USER1);
			void *buf = mapaddr + offset;
			offset += fuse_copy_do(cs, &buf, &count);
			kunmap_atomic(mapaddr, KM_USER1);
		} else
			offset += fuse_copy_do(cs, NULL, &count);
	}
	if (page && !cs->write)
		flush_dcache_page(page);
	return 0;
}

/* Copy pages in the request to/from userspace buffer */
static int fuse_copy_pages(struct fuse_copy_state *cs, unsigned nbytes,
			   int zeroing)
{
	unsigned i;
	struct fuse_req *req = cs->req;
	unsigned offset = req->page_offset;
	unsigned count = min(nbytes, (unsigned) PAGE_SIZE - offset);

	for (i = 0; i < req->num_pages && (nbytes || zeroing); i++) {
		struct page *page = req->pages[i];
		int err = fuse_copy_page(cs, page, offset, count, zeroing);
		if (err)
			return err;

		nbytes -= count;
		count = min(nbytes, (unsigned) PAGE_SIZE);
		offset = 0;
	}
	return 0;
}

/* Copy a single argument in the request to/from userspace buffer */
static int fuse_copy_one(struct fuse_copy_state *cs, void *val, unsigned size)
{
	while (size) {
		int err;
		if (!cs->len && (err = fuse_copy_fill(cs)))
			return err;
		fuse_copy_do(cs, &val, &size);
	}
	return 0;
}

/* Copy request arguments to/from userspace buffer */
static int fuse_copy_args(struct fuse_copy_state *cs, unsigned numargs,
			  unsigned argpages, struct fuse_arg *args,
			  int zeroing)
{
	int err = 0;
	unsigned i;

	for (i = 0; !err && i < numargs; i++)  {
		struct fuse_arg *arg = &args[i];
		if (i == numargs - 1 && argpages)
			err = fuse_copy_pages(cs, arg->size, zeroing);
		else
			err = fuse_copy_one(cs, arg->value, arg->size);
	}
	return err;
}

/* Wait until a request is available on the pending list */
static void request_wait(struct fuse_conn *fc)
{
	DECLARE_WAITQUEUE(wait, current);

	add_wait_queue_exclusive(&fc->waitq, &wait);
	while (fc->connected && list_empty(&fc->pending)) {
		set_current_state(TASK_INTERRUPTIBLE);
		if (signal_pending(current))
			break;

		spin_unlock(&fc->lock);
		schedule();
		spin_lock(&fc->lock);
	}
	set_current_state(TASK_RUNNING);
	remove_wait_queue(&fc->waitq, &wait);
}

/*
 * Read a single request into the userspace filesystem's buffer.  This
 * function waits until a request is available, then removes it from
 * the pending list and copies request data to userspace buffer.  If
 * no reply is needed (FORGET) or request has been interrupted or
 * there was an error during the copying then it's finished by calling
 * request_end().  Otherwise add it to the processing list, and set
 * the 'sent' flag.
 */
static ssize_t fuse_dev_readv(struct file *file, const struct iovec *iov,
			      unsigned long nr_segs, loff_t *off)
{
	int err;
	struct fuse_req *req;
	struct fuse_in *in;
	struct fuse_copy_state cs;
	unsigned reqsize;
	struct fuse_conn *fc = fuse_get_conn(file);
	if (!fc)
		return -EPERM;

 restart:
	spin_lock(&fc->lock);
	err = -EAGAIN;
	if ((file->f_flags & O_NONBLOCK) && fc->connected &&
	    list_empty(&fc->pending))
		goto err_unlock;

	request_wait(fc);
	err = -ENODEV;
	if (!fc->connected)
		goto err_unlock;
	err = -ERESTARTSYS;
	if (list_empty(&fc->pending))
		goto err_unlock;

	req = list_entry(fc->pending.next, struct fuse_req, list);
	req->state = FUSE_REQ_READING;
	list_move(&req->list, &fc->io);

	in = &req->in;
	reqsize = in->h.len;
	/* If request is too large, reply with an error and restart the read */
	if (iov_length(iov, nr_segs) < reqsize) {
		req->out.h.error = -EIO;
		/* SETXATTR is special, since it may contain too large data */
		if (in->h.opcode == FUSE_SETXATTR)
			req->out.h.error = -E2BIG;
		request_end(fc, req);
		goto restart;
	}
	spin_unlock(&fc->lock);
	fuse_copy_init(&cs, fc, 1, req, iov, nr_segs);
	err = fuse_copy_one(&cs, &in->h, sizeof(in->h));
	if (!err)
		err = fuse_copy_args(&cs, in->numargs, in->argpages,
				     (struct fuse_arg *) in->args, 0);
	fuse_copy_finish(&cs);
	spin_lock(&fc->lock);
	req->locked = 0;
	if (!err && req->interrupted)
		err = -ENOENT;
	if (err) {
		if (!req->interrupted)
			req->out.h.error = -EIO;
		request_end(fc, req);
		return err;
	}
	if (!req->isreply)
		request_end(fc, req);
	else {
		req->state = FUSE_REQ_SENT;
		list_move_tail(&req->list, &fc->processing);
		spin_unlock(&fc->lock);
	}
	return reqsize;

 err_unlock:
	spin_unlock(&fc->lock);
	return err;
}

static ssize_t fuse_dev_read(struct file *file, char __user *buf,
			     size_t nbytes, loff_t *off)
{
	struct iovec iov;
	iov.iov_len = nbytes;
	iov.iov_base = buf;
	return fuse_dev_readv(file, &iov, 1, off);
}

/* Look up request on processing list by unique ID */
static struct fuse_req *request_find(struct fuse_conn *fc, u64 unique)
{
	struct list_head *entry;

	list_for_each(entry, &fc->processing) {
		struct fuse_req *req;
		req = list_entry(entry, struct fuse_req, list);
		if (req->in.h.unique == unique)
			return req;
	}
	return NULL;
}

static int copy_out_args(struct fuse_copy_state *cs, struct fuse_out *out,
			 unsigned nbytes)
{
	unsigned reqsize = sizeof(struct fuse_out_header);

	if (out->h.error)
		return nbytes != reqsize ? -EINVAL : 0;

	reqsize += len_args(out->numargs, out->args);

	if (reqsize < nbytes || (reqsize > nbytes && !out->argvar))
		return -EINVAL;
	else if (reqsize > nbytes) {
		struct fuse_arg *lastarg = &out->args[out->numargs-1];
		unsigned diffsize = reqsize - nbytes;
		if (diffsize > lastarg->size)
			return -EINVAL;
		lastarg->size -= diffsize;
	}
	return fuse_copy_args(cs, out->numargs, out->argpages, out->args,
			      out->page_zeroing);
}

/*
 * Write a single reply to a request.  First the header is copied from
 * the write buffer.  The request is then searched on the processing
 * list by the unique ID found in the header.  If found, then remove
 * it from the list and copy the rest of the buffer to the request.
 * The request is finished by calling request_end()
 */
static ssize_t fuse_dev_writev(struct file *file, const struct iovec *iov,
			       unsigned long nr_segs, loff_t *off)
{
	int err;
	unsigned nbytes = iov_length(iov, nr_segs);
	struct fuse_req *req;
	struct fuse_out_header oh;
	struct fuse_copy_state cs;
	struct fuse_conn *fc = fuse_get_conn(file);
	if (!fc)
		return -EPERM;

	fuse_copy_init(&cs, fc, 0, NULL, iov, nr_segs);
	if (nbytes < sizeof(struct fuse_out_header))
		return -EINVAL;

	err = fuse_copy_one(&cs, &oh, sizeof(oh));
	if (err)
		goto err_finish;
	err = -EINVAL;
	if (!oh.unique || oh.error <= -1000 || oh.error > 0 ||
	    oh.len != nbytes)
		goto err_finish;

	spin_lock(&fc->lock);
	err = -ENOENT;
	if (!fc->connected)
		goto err_unlock;

	req = request_find(fc, oh.unique);
	err = -EINVAL;
	if (!req)
		goto err_unlock;

	if (req->interrupted) {
		spin_unlock(&fc->lock);
		fuse_copy_finish(&cs);
		spin_lock(&fc->lock);
		request_end(fc, req);
		return -ENOENT;
	}
	list_move(&req->list, &fc->io);
	req->out.h = oh;
	req->locked = 1;
	cs.req = req;
	spin_unlock(&fc->lock);

	err = copy_out_args(&cs, &req->out, nbytes);
	fuse_copy_finish(&cs);

	spin_lock(&fc->lock);
	req->locked = 0;
	if (!err) {
		if (req->interrupted)
			err = -ENOENT;
	} else if (!req->interrupted)
		req->out.h.error = -EIO;
	request_end(fc, req);

	return err ? err : nbytes;

 err_unlock:
	spin_unlock(&fc->lock);
 err_finish:
	fuse_copy_finish(&cs);
	return err;
}

static ssize_t fuse_dev_write(struct file *file, const char __user *buf,
			      size_t nbytes, loff_t *off)
{
	struct iovec iov;
	iov.iov_len = nbytes;
	iov.iov_base = (char __user *) buf;
	return fuse_dev_writev(file, &iov, 1, off);
}

static unsigned fuse_dev_poll(struct file *file, poll_table *wait)
{
	unsigned mask = POLLOUT | POLLWRNORM;
	struct fuse_conn *fc = fuse_get_conn(file);
	if (!fc)
		return POLLERR;

	poll_wait(file, &fc->waitq, wait);

	spin_lock(&fc->lock);
	if (!fc->connected)
		mask = POLLERR;
	else if (!list_empty(&fc->pending))
		mask |= POLLIN | POLLRDNORM;
	spin_unlock(&fc->lock);

	return mask;
}

/*
 * Abort all requests on the given list (pending or processing)
 *
 * This function releases and reacquires fc->lock
 */
static void end_requests(struct fuse_conn *fc, struct list_head *head)
{
	while (!list_empty(head)) {
		struct fuse_req *req;
		req = list_entry(head->next, struct fuse_req, list);
		req->out.h.error = -ECONNABORTED;
		request_end(fc, req);
		spin_lock(&fc->lock);
	}
}

/*
 * Abort requests under I/O
 *
 * The requests are set to interrupted and finished, and the request
 * waiter is woken up.  This will make request_wait_answer() wait
 * until the request is unlocked and then return.
 *
 * If the request is asynchronous, then the end function needs to be
 * called after waiting for the request to be unlocked (if it was
 * locked).
 */
static void end_io_requests(struct fuse_conn *fc)
{
	while (!list_empty(&fc->io)) {
		struct fuse_req *req =
			list_entry(fc->io.next, struct fuse_req, list);
		void (*end) (struct fuse_conn *, struct fuse_req *) = req->end;

		req->interrupted = 1;
		req->out.h.error = -ECONNABORTED;
		req->state = FUSE_REQ_FINISHED;
		list_del_init(&req->list);
		wake_up(&req->waitq);
		if (end) {
			req->end = NULL;
			/* The end function will consume this reference */
			__fuse_get_request(req);
			spin_unlock(&fc->lock);
			wait_event(req->waitq, !req->locked);
			end(fc, req);
			spin_lock(&fc->lock);
		}
	}
}

/*
 * Abort all requests.
 *
 * Emergency exit in case of a malicious or accidental deadlock, or
 * just a hung filesystem.
 *
 * The same effect is usually achievable through killing the
 * filesystem daemon and all users of the filesystem.  The exception
 * is the combination of an asynchronous request and the tricky
 * deadlock (see Documentation/filesystems/fuse.txt).
 *
 * During the aborting, progression of requests from the pending and
 * processing lists onto the io list, and progression of new requests
 * onto the pending list is prevented by req->connected being false.
 *
 * Progression of requests under I/O to the processing list is
 * prevented by the req->interrupted flag being true for these
 * requests.  For this reason requests on the io list must be aborted
 * first.
 */
void fuse_abort_conn(struct fuse_conn *fc)
{
	spin_lock(&fc->lock);
	if (fc->connected) {
		fc->connected = 0;
		end_io_requests(fc);
		end_requests(fc, &fc->pending);
		end_requests(fc, &fc->processing);
		wake_up_all(&fc->waitq);
		kill_fasync(&fc->fasync, SIGIO, POLL_IN);
	}
	spin_unlock(&fc->lock);
}

static int fuse_dev_release(struct inode *inode, struct file *file)
{
	struct fuse_conn *fc = fuse_get_conn(file);
	if (fc) {
		spin_lock(&fc->lock);
		fc->connected = 0;
		end_requests(fc, &fc->pending);
		end_requests(fc, &fc->processing);
		spin_unlock(&fc->lock);
		fasync_helper(-1, file, 0, &fc->fasync);
		kobject_put(&fc->kobj);
	}

	return 0;
}

static int fuse_dev_fasync(int fd, struct file *file, int on)
{
	struct fuse_conn *fc = fuse_get_conn(file);
	if (!fc)
		return -EPERM;

	/* No locking - fasync_helper does its own locking */
	return fasync_helper(fd, file, on, &fc->fasync);
}

const struct file_operations fuse_dev_operations = {
	.owner		= THIS_MODULE,
	.llseek		= no_llseek,
	.read		= fuse_dev_read,
	.readv		= fuse_dev_readv,
	.write		= fuse_dev_write,
	.writev		= fuse_dev_writev,
	.poll		= fuse_dev_poll,
	.release	= fuse_dev_release,
	.fasync		= fuse_dev_fasync,
};

static struct miscdevice fuse_miscdevice = {
	.minor = FUSE_MINOR,
	.name  = "fuse",
	.fops = &fuse_dev_operations,
};

int __init fuse_dev_init(void)
{
	int err = -ENOMEM;
	fuse_req_cachep = kmem_cache_create("fuse_request",
					    sizeof(struct fuse_req),
					    0, 0, NULL, NULL);
	if (!fuse_req_cachep)
		goto out;

	err = misc_register(&fuse_miscdevice);
	if (err)
		goto out_cache_clean;

	return 0;

 out_cache_clean:
	kmem_cache_destroy(fuse_req_cachep);
 out:
	return err;
}

void fuse_dev_cleanup(void)
{
	misc_deregister(&fuse_miscdevice);
	kmem_cache_destroy(fuse_req_cachep);
}