aboutsummaryrefslogtreecommitdiff
path: root/net/9p/trans_virtio.c
blob: b84d35cf68994631483f2be687ddfbe88739bd0d (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
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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * The Virtio 9p transport driver
 *
 * This is a block based transport driver based on the lguest block driver
 * code.
 *
 *  Copyright (C) 2007, 2008 Eric Van Hensbergen, IBM Corporation
 *
 *  Based on virtio console driver
 *  Copyright (C) 2006, 2007 Rusty Russell, IBM Corporation
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/in.h>
#include <linux/module.h>
#include <linux/net.h>
#include <linux/ipv6.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/un.h>
#include <linux/uaccess.h>
#include <linux/inet.h>
#include <linux/idr.h>
#include <linux/file.h>
#include <linux/highmem.h>
#include <linux/slab.h>
#include <net/9p/9p.h>
#include <linux/parser.h>
#include <net/9p/client.h>
#include <net/9p/transport.h>
#include <linux/scatterlist.h>
#include <linux/swap.h>
#include <linux/virtio.h>
#include <linux/virtio_9p.h>
#include "trans_common.h"

#define VIRTQUEUE_NUM	128

/* a single mutex to manage channel initialization and attachment */
static DEFINE_MUTEX(virtio_9p_lock);
static DECLARE_WAIT_QUEUE_HEAD(vp_wq);
static atomic_t vp_pinned = ATOMIC_INIT(0);

/**
 * struct virtio_chan - per-instance transport information
 * @inuse: whether the channel is in use
 * @lock: protects multiple elements within this structure
 * @client: client instance
 * @vdev: virtio dev associated with this channel
 * @vq: virtio queue associated with this channel
 * @ring_bufs_avail: flag to indicate there is some available in the ring buf
 * @vc_wq: wait queue for waiting for thing to be added to ring buf
 * @p9_max_pages: maximum number of pinned pages
 * @sg: scatter gather list which is used to pack a request (protected?)
 * @chan_list: linked list of channels
 *
 * We keep all per-channel information in a structure.
 * This structure is allocated within the devices dev->mem space.
 * A pointer to the structure will get put in the transport private.
 *
 */

struct virtio_chan {
	bool inuse;

	spinlock_t lock;

	struct p9_client *client;
	struct virtio_device *vdev;
	struct virtqueue *vq;
	int ring_bufs_avail;
	wait_queue_head_t *vc_wq;
	/* This is global limit. Since we don't have a global structure,
	 * will be placing it in each channel.
	 */
	unsigned long p9_max_pages;
	/* Scatterlist: can be too big for stack. */
	struct scatterlist sg[VIRTQUEUE_NUM];
	/**
	 * @tag: name to identify a mount null terminated
	 */
	char *tag;

	struct list_head chan_list;
};

static struct list_head virtio_chan_list;

/* How many bytes left in this page. */
static unsigned int rest_of_page(void *data)
{
	return PAGE_SIZE - offset_in_page(data);
}

/**
 * p9_virtio_close - reclaim resources of a channel
 * @client: client instance
 *
 * This reclaims a channel by freeing its resources and
 * resetting its inuse flag.
 *
 */

static void p9_virtio_close(struct p9_client *client)
{
	struct virtio_chan *chan = client->trans;

	mutex_lock(&virtio_9p_lock);
	if (chan)
		chan->inuse = false;
	mutex_unlock(&virtio_9p_lock);
}

/**
 * req_done - callback which signals activity from the server
 * @vq: virtio queue activity was received on
 *
 * This notifies us that the server has triggered some activity
 * on the virtio channel - most likely a response to request we
 * sent.  Figure out which requests now have responses and wake up
 * those threads.
 *
 * Bugs: could do with some additional sanity checking, but appears to work.
 *
 */

static void req_done(struct virtqueue *vq)
{
	struct virtio_chan *chan = vq->vdev->priv;
	unsigned int len;
	struct p9_req_t *req;
	bool need_wakeup = false;
	unsigned long flags;

	p9_debug(P9_DEBUG_TRANS, ": request done\n");

	spin_lock_irqsave(&chan->lock, flags);
	while ((req = virtqueue_get_buf(chan->vq, &len)) != NULL) {
		if (!chan->ring_bufs_avail) {
			chan->ring_bufs_avail = 1;
			need_wakeup = true;
		}

		if (len) {
			req->rc.size = len;
			p9_client_cb(chan->client, req, REQ_STATUS_RCVD);
		}
	}
	spin_unlock_irqrestore(&chan->lock, flags);
	/* Wakeup if anyone waiting for VirtIO ring space. */
	if (need_wakeup)
		wake_up(chan->vc_wq);
}

/**
 * pack_sg_list - pack a scatter gather list from a linear buffer
 * @sg: scatter/gather list to pack into
 * @start: which segment of the sg_list to start at
 * @limit: maximum segment to pack data to
 * @data: data to pack into scatter/gather list
 * @count: amount of data to pack into the scatter/gather list
 *
 * sg_lists have multiple segments of various sizes.  This will pack
 * arbitrary data into an existing scatter gather list, segmenting the
 * data as necessary within constraints.
 *
 */

static int pack_sg_list(struct scatterlist *sg, int start,
			int limit, char *data, int count)
{
	int s;
	int index = start;

	while (count) {
		s = rest_of_page(data);
		if (s > count)
			s = count;
		BUG_ON(index >= limit);
		/* Make sure we don't terminate early. */
		sg_unmark_end(&sg[index]);
		sg_set_buf(&sg[index++], data, s);
		count -= s;
		data += s;
	}
	if (index-start)
		sg_mark_end(&sg[index - 1]);
	return index-start;
}

/* We don't currently allow canceling of virtio requests */
static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req)
{
	return 1;
}

/* Reply won't come, so drop req ref */
static int p9_virtio_cancelled(struct p9_client *client, struct p9_req_t *req)
{
	p9_req_put(client, req);
	return 0;
}

/**
 * pack_sg_list_p - Just like pack_sg_list. Instead of taking a buffer,
 * this takes a list of pages.
 * @sg: scatter/gather list to pack into
 * @start: which segment of the sg_list to start at
 * @limit: maximum number of pages in sg list.
 * @pdata: a list of pages to add into sg.
 * @nr_pages: number of pages to pack into the scatter/gather list
 * @offs: amount of data in the beginning of first page _not_ to pack
 * @count: amount of data to pack into the scatter/gather list
 */
static int
pack_sg_list_p(struct scatterlist *sg, int start, int limit,
	       struct page **pdata, int nr_pages, size_t offs, int count)
{
	int i = 0, s;
	int data_off = offs;
	int index = start;

	BUG_ON(nr_pages > (limit - start));
	/*
	 * if the first page doesn't start at
	 * page boundary find the offset
	 */
	while (nr_pages) {
		s = PAGE_SIZE - data_off;
		if (s > count)
			s = count;
		BUG_ON(index >= limit);
		/* Make sure we don't terminate early. */
		sg_unmark_end(&sg[index]);
		sg_set_page(&sg[index++], pdata[i++], s, data_off);
		data_off = 0;
		count -= s;
		nr_pages--;
	}

	if (index-start)
		sg_mark_end(&sg[index - 1]);
	return index - start;
}

/**
 * p9_virtio_request - issue a request
 * @client: client instance issuing the request
 * @req: request to be issued
 *
 */

static int
p9_virtio_request(struct p9_client *client, struct p9_req_t *req)
{
	int err;
	int in, out, out_sgs, in_sgs;
	unsigned long flags;
	struct virtio_chan *chan = client->trans;
	struct scatterlist *sgs[2];

	p9_debug(P9_DEBUG_TRANS, "9p debug: virtio request\n");

	req->status = REQ_STATUS_SENT;
req_retry:
	spin_lock_irqsave(&chan->lock, flags);

	out_sgs = in_sgs = 0;
	/* Handle out VirtIO ring buffers */
	out = pack_sg_list(chan->sg, 0,
			   VIRTQUEUE_NUM, req->tc.sdata, req->tc.size);
	if (out)
		sgs[out_sgs++] = chan->sg;

	in = pack_sg_list(chan->sg, out,
			  VIRTQUEUE_NUM, req->rc.sdata, req->rc.capacity);
	if (in)
		sgs[out_sgs + in_sgs++] = chan->sg + out;

	err = virtqueue_add_sgs(chan->vq, sgs, out_sgs, in_sgs, req,
				GFP_ATOMIC);
	if (err < 0) {
		if (err == -ENOSPC) {
			chan->ring_bufs_avail = 0;
			spin_unlock_irqrestore(&chan->lock, flags);
			err = wait_event_killable(*chan->vc_wq,
						  chan->ring_bufs_avail);
			if (err  == -ERESTARTSYS)
				return err;

			p9_debug(P9_DEBUG_TRANS, "Retry virtio request\n");
			goto req_retry;
		} else {
			spin_unlock_irqrestore(&chan->lock, flags);
			p9_debug(P9_DEBUG_TRANS,
				 "virtio rpc add_sgs returned failure\n");
			return -EIO;
		}
	}
	virtqueue_kick(chan->vq);
	spin_unlock_irqrestore(&chan->lock, flags);

	p9_debug(P9_DEBUG_TRANS, "virtio request kicked\n");
	return 0;
}

static int p9_get_mapped_pages(struct virtio_chan *chan,
			       struct page ***pages,
			       struct iov_iter *data,
			       int count,
			       size_t *offs,
			       int *need_drop)
{
	int nr_pages;
	int err;

	if (!iov_iter_count(data))
		return 0;

	if (!iov_iter_is_kvec(data)) {
		int n;
		/*
		 * We allow only p9_max_pages pinned. We wait for the
		 * Other zc request to finish here
		 */
		if (atomic_read(&vp_pinned) >= chan->p9_max_pages) {
			err = wait_event_killable(vp_wq,
			      (atomic_read(&vp_pinned) < chan->p9_max_pages));
			if (err == -ERESTARTSYS)
				return err;
		}
		n = iov_iter_get_pages_alloc2(data, pages, count, offs);
		if (n < 0)
			return n;
		*need_drop = 1;
		nr_pages = DIV_ROUND_UP(n + *offs, PAGE_SIZE);
		atomic_add(nr_pages, &vp_pinned);
		return n;
	} else {
		/* kernel buffer, no need to pin pages */
		int index;
		size_t len;
		void *p;

		/* we'd already checked that it's non-empty */
		while (1) {
			len = iov_iter_single_seg_count(data);
			if (likely(len)) {
				p = data->kvec->iov_base + data->iov_offset;
				break;
			}
			iov_iter_advance(data, 0);
		}
		if (len > count)
			len = count;

		nr_pages = DIV_ROUND_UP((unsigned long)p + len, PAGE_SIZE) -
			   (unsigned long)p / PAGE_SIZE;

		*pages = kmalloc_array(nr_pages, sizeof(struct page *),
				       GFP_NOFS);
		if (!*pages)
			return -ENOMEM;

		*need_drop = 0;
		p -= (*offs = offset_in_page(p));
		for (index = 0; index < nr_pages; index++) {
			if (is_vmalloc_addr(p))
				(*pages)[index] = vmalloc_to_page(p);
			else
				(*pages)[index] = kmap_to_page(p);
			p += PAGE_SIZE;
		}
		iov_iter_advance(data, len);
		return len;
	}
}

static void handle_rerror(struct p9_req_t *req, int in_hdr_len,
			  size_t offs, struct page **pages)
{
	unsigned size, n;
	void *to = req->rc.sdata + in_hdr_len;

	// Fits entirely into the static data?  Nothing to do.
	if (req->rc.size < in_hdr_len)
		return;

	// Really long error message?  Tough, truncate the reply.  Might get
	// rejected (we can't be arsed to adjust the size encoded in header,
	// or string size for that matter), but it wouldn't be anything valid
	// anyway.
	if (unlikely(req->rc.size > P9_ZC_HDR_SZ))
		req->rc.size = P9_ZC_HDR_SZ;

	// data won't span more than two pages
	size = req->rc.size - in_hdr_len;
	n = PAGE_SIZE - offs;
	if (size > n) {
		memcpy_from_page(to, *pages++, offs, n);
		offs = 0;
		to += n;
		size -= n;
	}
	memcpy_from_page(to, *pages, offs, size);
}

/**
 * p9_virtio_zc_request - issue a zero copy request
 * @client: client instance issuing the request
 * @req: request to be issued
 * @uidata: user buffer that should be used for zero copy read
 * @uodata: user buffer that should be used for zero copy write
 * @inlen: read buffer size
 * @outlen: write buffer size
 * @in_hdr_len: reader header size, This is the size of response protocol data
 *
 */
static int
p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
		     struct iov_iter *uidata, struct iov_iter *uodata,
		     int inlen, int outlen, int in_hdr_len)
{
	int in, out, err, out_sgs, in_sgs;
	unsigned long flags;
	int in_nr_pages = 0, out_nr_pages = 0;
	struct page **in_pages = NULL, **out_pages = NULL;
	struct virtio_chan *chan = client->trans;
	struct scatterlist *sgs[4];
	size_t offs;
	int need_drop = 0;
	int kicked = 0;

	p9_debug(P9_DEBUG_TRANS, "virtio request\n");

	if (uodata) {
		__le32 sz;
		int n = p9_get_mapped_pages(chan, &out_pages, uodata,
					    outlen, &offs, &need_drop);
		if (n < 0) {
			err = n;
			goto err_out;
		}
		out_nr_pages = DIV_ROUND_UP(n + offs, PAGE_SIZE);
		if (n != outlen) {
			__le32 v = cpu_to_le32(n);
			memcpy(&req->tc.sdata[req->tc.size - 4], &v, 4);
			outlen = n;
		}
		/* The size field of the message must include the length of the
		 * header and the length of the data.  We didn't actually know
		 * the length of the data until this point so add it in now.
		 */
		sz = cpu_to_le32(req->tc.size + outlen);
		memcpy(&req->tc.sdata[0], &sz, sizeof(sz));
	} else if (uidata) {
		int n = p9_get_mapped_pages(chan, &in_pages, uidata,
					    inlen, &offs, &need_drop);
		if (n < 0) {
			err = n;
			goto err_out;
		}
		in_nr_pages = DIV_ROUND_UP(n + offs, PAGE_SIZE);
		if (n != inlen) {
			__le32 v = cpu_to_le32(n);
			memcpy(&req->tc.sdata[req->tc.size - 4], &v, 4);
			inlen = n;
		}
	}
	req->status = REQ_STATUS_SENT;
req_retry_pinned:
	spin_lock_irqsave(&chan->lock, flags);

	out_sgs = in_sgs = 0;

	/* out data */
	out = pack_sg_list(chan->sg, 0,
			   VIRTQUEUE_NUM, req->tc.sdata, req->tc.size);

	if (out)
		sgs[out_sgs++] = chan->sg;

	if (out_pages) {
		sgs[out_sgs++] = chan->sg + out;
		out += pack_sg_list_p(chan->sg, out, VIRTQUEUE_NUM,
				      out_pages, out_nr_pages, offs, outlen);
	}

	/*
	 * Take care of in data
	 * For example TREAD have 11.
	 * 11 is the read/write header = PDU Header(7) + IO Size (4).
	 * Arrange in such a way that server places header in the
	 * allocated memory and payload onto the user buffer.
	 */
	in = pack_sg_list(chan->sg, out,
			  VIRTQUEUE_NUM, req->rc.sdata, in_hdr_len);
	if (in)
		sgs[out_sgs + in_sgs++] = chan->sg + out;

	if (in_pages) {
		sgs[out_sgs + in_sgs++] = chan->sg + out + in;
		in += pack_sg_list_p(chan->sg, out + in, VIRTQUEUE_NUM,
				     in_pages, in_nr_pages, offs, inlen);
	}

	BUG_ON(out_sgs + in_sgs > ARRAY_SIZE(sgs));
	err = virtqueue_add_sgs(chan->vq, sgs, out_sgs, in_sgs, req,
				GFP_ATOMIC);
	if (err < 0) {
		if (err == -ENOSPC) {
			chan->ring_bufs_avail = 0;
			spin_unlock_irqrestore(&chan->lock, flags);
			err = wait_event_killable(*chan->vc_wq,
						  chan->ring_bufs_avail);
			if (err  == -ERESTARTSYS)
				goto err_out;

			p9_debug(P9_DEBUG_TRANS, "Retry virtio request\n");
			goto req_retry_pinned;
		} else {
			spin_unlock_irqrestore(&chan->lock, flags);
			p9_debug(P9_DEBUG_TRANS,
				 "virtio rpc add_sgs returned failure\n");
			err = -EIO;
			goto err_out;
		}
	}
	virtqueue_kick(chan->vq);
	spin_unlock_irqrestore(&chan->lock, flags);
	kicked = 1;
	p9_debug(P9_DEBUG_TRANS, "virtio request kicked\n");
	err = wait_event_killable(req->wq, req->status >= REQ_STATUS_RCVD);
	// RERROR needs reply (== error string) in static data
	if (req->status == REQ_STATUS_RCVD &&
	    unlikely(req->rc.sdata[4] == P9_RERROR))
		handle_rerror(req, in_hdr_len, offs, in_pages);

	/*
	 * Non kernel buffers are pinned, unpin them
	 */
err_out:
	if (need_drop) {
		if (in_pages) {
			p9_release_pages(in_pages, in_nr_pages);
			atomic_sub(in_nr_pages, &vp_pinned);
		}
		if (out_pages) {
			p9_release_pages(out_pages, out_nr_pages);
			atomic_sub(out_nr_pages, &vp_pinned);
		}
		/* wakeup anybody waiting for slots to pin pages */
		wake_up(&vp_wq);
	}
	kvfree(in_pages);
	kvfree(out_pages);
	if (!kicked) {
		/* reply won't come */
		p9_req_put(client, req);
	}
	return err;
}

static ssize_t p9_mount_tag_show(struct device *dev,
				struct device_attribute *attr, char *buf)
{
	struct virtio_chan *chan;
	struct virtio_device *vdev;
	int tag_len;

	vdev = dev_to_virtio(dev);
	chan = vdev->priv;
	tag_len = strlen(chan->tag);

	memcpy(buf, chan->tag, tag_len + 1);

	return tag_len + 1;
}

static DEVICE_ATTR(mount_tag, 0444, p9_mount_tag_show, NULL);

/**
 * p9_virtio_probe - probe for existence of 9P virtio channels
 * @vdev: virtio device to probe
 *
 * This probes for existing virtio channels.
 *
 */

static int p9_virtio_probe(struct virtio_device *vdev)
{
	__u16 tag_len;
	char *tag;
	int err;
	struct virtio_chan *chan;

	if (!vdev->config->get) {
		dev_err(&vdev->dev, "%s failure: config access disabled\n",
			__func__);
		return -EINVAL;
	}

	chan = kmalloc(sizeof(struct virtio_chan), GFP_KERNEL);
	if (!chan) {
		pr_err("Failed to allocate virtio 9P channel\n");
		err = -ENOMEM;
		goto fail;
	}

	chan->vdev = vdev;

	/* We expect one virtqueue, for requests. */
	chan->vq = virtio_find_single_vq(vdev, req_done, "requests");
	if (IS_ERR(chan->vq)) {
		err = PTR_ERR(chan->vq);
		goto out_free_chan;
	}
	chan->vq->vdev->priv = chan;
	spin_lock_init(&chan->lock);

	sg_init_table(chan->sg, VIRTQUEUE_NUM);

	chan->inuse = false;
	if (virtio_has_feature(vdev, VIRTIO_9P_MOUNT_TAG)) {
		virtio_cread(vdev, struct virtio_9p_config, tag_len, &tag_len);
	} else {
		err = -EINVAL;
		goto out_free_vq;
	}
	tag = kzalloc(tag_len + 1, GFP_KERNEL);
	if (!tag) {
		err = -ENOMEM;
		goto out_free_vq;
	}

	virtio_cread_bytes(vdev, offsetof(struct virtio_9p_config, tag),
			   tag, tag_len);
	chan->tag = tag;
	err = sysfs_create_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr);
	if (err) {
		goto out_free_tag;
	}
	chan->vc_wq = kmalloc(sizeof(wait_queue_head_t), GFP_KERNEL);
	if (!chan->vc_wq) {
		err = -ENOMEM;
		goto out_remove_file;
	}
	init_waitqueue_head(chan->vc_wq);
	chan->ring_bufs_avail = 1;
	/* Ceiling limit to avoid denial of service attacks */
	chan->p9_max_pages = nr_free_buffer_pages()/4;

	virtio_device_ready(vdev);

	mutex_lock(&virtio_9p_lock);
	list_add_tail(&chan->chan_list, &virtio_chan_list);
	mutex_unlock(&virtio_9p_lock);

	/* Let udev rules use the new mount_tag attribute. */
	kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE);

	return 0;

out_remove_file:
	sysfs_remove_file(&vdev->dev.kobj, &dev_attr_mount_tag.attr);
out_free_tag:
	kfree(tag);
out_free_vq:
	vdev->config->del_vqs(vdev);
out_free_chan:
	kfree(chan);
fail:
	return err;
}


/**
 * p9_virtio_create - allocate a new virtio channel
 * @client: client instance invoking this transport
 * @devname: string identifying the channel to connect to (unused)
 * @args: args passed from sys_mount() for per-transport options (unused)
 *
 * This sets up a transport channel for 9p communication.  Right now
 * we only match the first available channel, but eventually we could look up
 * alternate channels by matching devname versus a virtio_config entry.
 * We use a simple reference count mechanism to ensure that only a single
 * mount has a channel open at a time.
 *
 */

static int
p9_virtio_create(struct p9_client *client, const char *devname, char *args)
{
	struct virtio_chan *chan;
	int ret = -ENOENT;
	int found = 0;

	if (devname == NULL)
		return -EINVAL;

	mutex_lock(&virtio_9p_lock);
	list_for_each_entry(chan, &virtio_chan_list, chan_list) {
		if (!strcmp(devname, chan->tag)) {
			if (!chan->inuse) {
				chan->inuse = true;
				found = 1;
				break;
			}
			ret = -EBUSY;
		}
	}
	mutex_unlock(&virtio_9p_lock);

	if (!found) {
		pr_err("no channels available for device %s\n", devname);
		return ret;
	}

	client->trans = (void *)chan;
	client->status = Connected;
	chan->client = client;

	return 0;
}

/**
 * p9_virtio_remove - clean up resources associated with a virtio device
 * @vdev: virtio device to remove
 *
 */

static void p9_virtio_remove(struct virtio_device *vdev)
{
	struct virtio_chan *chan = vdev->priv;
	unsigned long warning_time;

	mutex_lock(&virtio_9p_lock);

	/* Remove self from list so we don't get new users. */
	list_del(&chan->chan_list);
	warning_time = jiffies;

	/* Wait for existing users to close. */
	while (chan->inuse) {
		mutex_unlock(&virtio_9p_lock);
		msleep(250);
		if (time_after(jiffies, warning_time + 10 * HZ)) {
			dev_emerg(&vdev->dev,
				  "p9_virtio_remove: waiting for device in use.\n");
			warning_time = jiffies;
		}
		mutex_lock(&virtio_9p_lock);
	}

	mutex_unlock(&virtio_9p_lock);

	virtio_reset_device(vdev);
	vdev->config->del_vqs(vdev);

	sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr);
	kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE);
	kfree(chan->tag);
	kfree(chan->vc_wq);
	kfree(chan);

}

static struct virtio_device_id id_table[] = {
	{ VIRTIO_ID_9P, VIRTIO_DEV_ANY_ID },
	{ 0 },
};

static unsigned int features[] = {
	VIRTIO_9P_MOUNT_TAG,
};

/* The standard "struct lguest_driver": */
static struct virtio_driver p9_virtio_drv = {
	.feature_table  = features,
	.feature_table_size = ARRAY_SIZE(features),
	.driver.name    = KBUILD_MODNAME,
	.driver.owner	= THIS_MODULE,
	.id_table	= id_table,
	.probe		= p9_virtio_probe,
	.remove		= p9_virtio_remove,
};

static struct p9_trans_module p9_virtio_trans = {
	.name = "virtio",
	.create = p9_virtio_create,
	.close = p9_virtio_close,
	.request = p9_virtio_request,
	.zc_request = p9_virtio_zc_request,
	.cancel = p9_virtio_cancel,
	.cancelled = p9_virtio_cancelled,
	/*
	 * We leave one entry for input and one entry for response
	 * headers. We also skip one more entry to accommodate, address
	 * that are not at page boundary, that can result in an extra
	 * page in zero copy.
	 */
	.maxsize = PAGE_SIZE * (VIRTQUEUE_NUM - 3),
	.def = 1,
	.owner = THIS_MODULE,
};

/* The standard init function */
static int __init p9_virtio_init(void)
{
	int rc;

	INIT_LIST_HEAD(&virtio_chan_list);

	v9fs_register_trans(&p9_virtio_trans);
	rc = register_virtio_driver(&p9_virtio_drv);
	if (rc)
		v9fs_unregister_trans(&p9_virtio_trans);

	return rc;
}

static void __exit p9_virtio_cleanup(void)
{
	unregister_virtio_driver(&p9_virtio_drv);
	v9fs_unregister_trans(&p9_virtio_trans);
}

module_init(p9_virtio_init);
module_exit(p9_virtio_cleanup);
MODULE_ALIAS_9P("virtio");

MODULE_DEVICE_TABLE(virtio, id_table);
MODULE_AUTHOR("Eric Van Hensbergen <ericvh@gmail.com>");
MODULE_DESCRIPTION("Virtio 9p Transport");
MODULE_LICENSE("GPL");