summaryrefslogtreecommitdiffstats
path: root/net/9p/trans_xen.c
blob: dfdbe1ca533872ce189e64ff5f4a083c5261ddee (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * linux/fs/9p/trans_xen
 *
 * Xen transport layer.
 *
 * Copyright (C) 2017 by Stefano Stabellini <stefano@aporeto.com>
 */

#include <xen/events.h>
#include <xen/grant_table.h>
#include <xen/xen.h>
#include <xen/xenbus.h>
#include <xen/interface/io/9pfs.h>

#include <linux/module.h>
#include <linux/spinlock.h>
#include <net/9p/9p.h>
#include <net/9p/client.h>
#include <net/9p/transport.h>

#define XEN_9PFS_NUM_RINGS 2
#define XEN_9PFS_RING_ORDER 9
#define XEN_9PFS_RING_SIZE(ring)  XEN_FLEX_RING_SIZE(ring->intf->ring_order)

struct xen_9pfs_header {
	uint32_t size;
	uint8_t id;
	uint16_t tag;

	/* uint8_t sdata[]; */
} __attribute__((packed));

/* One per ring, more than one per 9pfs share */
struct xen_9pfs_dataring {
	struct xen_9pfs_front_priv *priv;

	struct xen_9pfs_data_intf *intf;
	grant_ref_t ref;
	int evtchn;
	int irq;
	/* protect a ring from concurrent accesses */
	spinlock_t lock;

	struct xen_9pfs_data data;
	wait_queue_head_t wq;
	struct work_struct work;
};

/* One per 9pfs share */
struct xen_9pfs_front_priv {
	struct list_head list;
	struct xenbus_device *dev;
	char *tag;
	struct p9_client *client;

	struct xen_9pfs_dataring *rings;
};

static LIST_HEAD(xen_9pfs_devs);
static DEFINE_RWLOCK(xen_9pfs_lock);

/* We don't currently allow canceling of requests */
static int p9_xen_cancel(struct p9_client *client, struct p9_req_t *req)
{
	return 1;
}

static int p9_xen_create(struct p9_client *client, const char *addr, char *args)
{
	struct xen_9pfs_front_priv *priv;

	if (addr == NULL)
		return -EINVAL;

	read_lock(&xen_9pfs_lock);
	list_for_each_entry(priv, &xen_9pfs_devs, list) {
		if (!strcmp(priv->tag, addr)) {
			priv->client = client;
			read_unlock(&xen_9pfs_lock);
			return 0;
		}
	}
	read_unlock(&xen_9pfs_lock);
	return -EINVAL;
}

static void p9_xen_close(struct p9_client *client)
{
	struct xen_9pfs_front_priv *priv;

	read_lock(&xen_9pfs_lock);
	list_for_each_entry(priv, &xen_9pfs_devs, list) {
		if (priv->client == client) {
			priv->client = NULL;
			read_unlock(&xen_9pfs_lock);
			return;
		}
	}
	read_unlock(&xen_9pfs_lock);
}

static bool p9_xen_write_todo(struct xen_9pfs_dataring *ring, RING_IDX size)
{
	RING_IDX cons, prod;

	cons = ring->intf->out_cons;
	prod = ring->intf->out_prod;
	virt_mb();

	return XEN_9PFS_RING_SIZE(ring) -
		xen_9pfs_queued(prod, cons, XEN_9PFS_RING_SIZE(ring)) >= size;
}

static int p9_xen_request(struct p9_client *client, struct p9_req_t *p9_req)
{
	struct xen_9pfs_front_priv *priv;
	RING_IDX cons, prod, masked_cons, masked_prod;
	unsigned long flags;
	u32 size = p9_req->tc.size;
	struct xen_9pfs_dataring *ring;
	int num;

	read_lock(&xen_9pfs_lock);
	list_for_each_entry(priv, &xen_9pfs_devs, list) {
		if (priv->client == client)
			break;
	}
	read_unlock(&xen_9pfs_lock);
	if (list_entry_is_head(priv, &xen_9pfs_devs, list))
		return -EINVAL;

	num = p9_req->tc.tag % XEN_9PFS_NUM_RINGS;
	ring = &priv->rings[num];

again:
	while (wait_event_killable(ring->wq,
				   p9_xen_write_todo(ring, size)) != 0)
		;

	spin_lock_irqsave(&ring->lock, flags);
	cons = ring->intf->out_cons;
	prod = ring->intf->out_prod;
	virt_mb();

	if (XEN_9PFS_RING_SIZE(ring) -
	    xen_9pfs_queued(prod, cons, XEN_9PFS_RING_SIZE(ring)) < size) {
		spin_unlock_irqrestore(&ring->lock, flags);
		goto again;
	}

	masked_prod = xen_9pfs_mask(prod, XEN_9PFS_RING_SIZE(ring));
	masked_cons = xen_9pfs_mask(cons, XEN_9PFS_RING_SIZE(ring));

	xen_9pfs_write_packet(ring->data.out, p9_req->tc.sdata, size,
			      &masked_prod, masked_cons,
			      XEN_9PFS_RING_SIZE(ring));

	WRITE_ONCE(p9_req->status, REQ_STATUS_SENT);
	virt_wmb();			/* write ring before updating pointer */
	prod += size;
	ring->intf->out_prod = prod;
	spin_unlock_irqrestore(&ring->lock, flags);
	notify_remote_via_irq(ring->irq);
	p9_req_put(client, p9_req);

	return 0;
}

static void p9_xen_response(struct work_struct *work)
{
	struct xen_9pfs_front_priv *priv;
	struct xen_9pfs_dataring *ring;
	RING_IDX cons, prod, masked_cons, masked_prod;
	struct xen_9pfs_header h;
	struct p9_req_t *req;
	int status;

	ring = container_of(work, struct xen_9pfs_dataring, work);
	priv = ring->priv;

	while (1) {
		cons = ring->intf->in_cons;
		prod = ring->intf->in_prod;
		virt_rmb();

		if (xen_9pfs_queued(prod, cons, XEN_9PFS_RING_SIZE(ring)) <
		    sizeof(h)) {
			notify_remote_via_irq(ring->irq);
			return;
		}

		masked_prod = xen_9pfs_mask(prod, XEN_9PFS_RING_SIZE(ring));
		masked_cons = xen_9pfs_mask(cons, XEN_9PFS_RING_SIZE(ring));

		/* First, read just the header */
		xen_9pfs_read_packet(&h, ring->data.in, sizeof(h),
				     masked_prod, &masked_cons,
				     XEN_9PFS_RING_SIZE(ring));

		req = p9_tag_lookup(priv->client, h.tag);
		if (!req || req->status != REQ_STATUS_SENT) {
			dev_warn(&priv->dev->dev, "Wrong req tag=%x\n", h.tag);
			cons += h.size;
			virt_mb();
			ring->intf->in_cons = cons;
			continue;
		}

		if (h.size > req->rc.capacity) {
			dev_warn(&priv->dev->dev,
				 "requested packet size too big: %d for tag %d with capacity %zd\n",
				 h.size, h.tag, req->rc.capacity);
			WRITE_ONCE(req->status, REQ_STATUS_ERROR);
			goto recv_error;
		}

		req->rc.size = h.size;
		req->rc.id = h.id;
		req->rc.tag = h.tag;
		req->rc.offset = 0;

		masked_cons = xen_9pfs_mask(cons, XEN_9PFS_RING_SIZE(ring));
		/* Then, read the whole packet (including the header) */
		xen_9pfs_read_packet(req->rc.sdata, ring->data.in, h.size,
				     masked_prod, &masked_cons,
				     XEN_9PFS_RING_SIZE(ring));

recv_error:
		virt_mb();
		cons += h.size;
		ring->intf->in_cons = cons;

		status = (req->status != REQ_STATUS_ERROR) ?
			REQ_STATUS_RCVD : REQ_STATUS_ERROR;

		p9_client_cb(priv->client, req, status);
	}
}

static irqreturn_t xen_9pfs_front_event_handler(int irq, void *r)
{
	struct xen_9pfs_dataring *ring = r;

	if (!ring || !ring->priv->client) {
		/* ignore spurious interrupt */
		return IRQ_HANDLED;
	}

	wake_up_interruptible(&ring->wq);
	schedule_work(&ring->work);

	return IRQ_HANDLED;
}

static struct p9_trans_module p9_xen_trans = {
	.name = "xen",
	.maxsize = 1 << (XEN_9PFS_RING_ORDER + XEN_PAGE_SHIFT - 2),
	.pooled_rbuffers = false,
	.def = 1,
	.create = p9_xen_create,
	.close = p9_xen_close,
	.request = p9_xen_request,
	.cancel = p9_xen_cancel,
	.owner = THIS_MODULE,
};

static const struct xenbus_device_id xen_9pfs_front_ids[] = {
	{ "9pfs" },
	{ "" }
};

static void xen_9pfs_front_free(struct xen_9pfs_front_priv *priv)
{
	int i, j;

	write_lock(&xen_9pfs_lock);
	list_del(&priv->list);
	write_unlock(&xen_9pfs_lock);

	for (i = 0; i < XEN_9PFS_NUM_RINGS; i++) {
		struct xen_9pfs_dataring *ring = &priv->rings[i];

		cancel_work_sync(&ring->work);

		if (!priv->rings[i].intf)
			break;
		if (priv->rings[i].irq > 0)
			unbind_from_irqhandler(priv->rings[i].irq, priv->dev);
		if (priv->rings[i].data.in) {
			for (j = 0;
			     j < (1 << priv->rings[i].intf->ring_order);
			     j++) {
				grant_ref_t ref;

				ref = priv->rings[i].intf->ref[j];
				gnttab_end_foreign_access(ref, NULL);
			}
			free_pages_exact(priv->rings[i].data.in,
				   1UL << (priv->rings[i].intf->ring_order +
					   XEN_PAGE_SHIFT));
		}
		gnttab_end_foreign_access(priv->rings[i].ref, NULL);
		free_page((unsigned long)priv->rings[i].intf);
	}
	kfree(priv->rings);
	kfree(priv->tag);
	kfree(priv);
}

static void xen_9pfs_front_remove(struct xenbus_device *dev)
{
	struct xen_9pfs_front_priv *priv = dev_get_drvdata(&dev->dev);

	dev_set_drvdata(&dev->dev, NULL);
	xen_9pfs_front_free(priv);
}

static int xen_9pfs_front_alloc_dataring(struct xenbus_device *dev,
					 struct xen_9pfs_dataring *ring,
					 unsigned int order)
{
	int i = 0;
	int ret = -ENOMEM;
	void *bytes = NULL;

	init_waitqueue_head(&ring->wq);
	spin_lock_init(&ring->lock);
	INIT_WORK(&ring->work, p9_xen_response);

	ring->intf = (struct xen_9pfs_data_intf *)get_zeroed_page(GFP_KERNEL);
	if (!ring->intf)
		return ret;
	ret = gnttab_grant_foreign_access(dev->otherend_id,
					  virt_to_gfn(ring->intf), 0);
	if (ret < 0)
		goto out;
	ring->ref = ret;
	bytes = alloc_pages_exact(1UL << (order + XEN_PAGE_SHIFT),
				  GFP_KERNEL | __GFP_ZERO);
	if (!bytes) {
		ret = -ENOMEM;
		goto out;
	}
	for (; i < (1 << order); i++) {
		ret = gnttab_grant_foreign_access(
				dev->otherend_id, virt_to_gfn(bytes) + i, 0);
		if (ret < 0)
			goto out;
		ring->intf->ref[i] = ret;
	}
	ring->intf->ring_order = order;
	ring->data.in = bytes;
	ring->data.out = bytes + XEN_FLEX_RING_SIZE(order);

	ret = xenbus_alloc_evtchn(dev, &ring->evtchn);
	if (ret)
		goto out;
	ring->irq = bind_evtchn_to_irqhandler(ring->evtchn,
					      xen_9pfs_front_event_handler,
					      0, "xen_9pfs-frontend", ring);
	if (ring->irq >= 0)
		return 0;

	xenbus_free_evtchn(dev, ring->evtchn);
	ret = ring->irq;
out:
	if (bytes) {
		for (i--; i >= 0; i--)
			gnttab_end_foreign_access(ring->intf->ref[i], NULL);
		free_pages_exact(bytes, 1UL << (order + XEN_PAGE_SHIFT));
	}
	gnttab_end_foreign_access(ring->ref, NULL);
	free_page((unsigned long)ring->intf);
	return ret;
}

static int xen_9pfs_front_init(struct xenbus_device *dev)
{
	int ret, i;
	struct xenbus_transaction xbt;
	struct xen_9pfs_front_priv *priv = dev_get_drvdata(&dev->dev);
	char *versions, *v;
	unsigned int max_rings, max_ring_order, len = 0;

	versions = xenbus_read(XBT_NIL, dev->otherend, "versions", &len);
	if (IS_ERR(versions))
		return PTR_ERR(versions);
	for (v = versions; *v; v++) {
		if (simple_strtoul(v, &v, 10) == 1) {
			v = NULL;
			break;
		}
	}
	if (v) {
		kfree(versions);
		return -EINVAL;
	}
	kfree(versions);
	max_rings = xenbus_read_unsigned(dev->otherend, "max-rings", 0);
	if (max_rings < XEN_9PFS_NUM_RINGS)
		return -EINVAL;
	max_ring_order = xenbus_read_unsigned(dev->otherend,
					      "max-ring-page-order", 0);
	if (max_ring_order > XEN_9PFS_RING_ORDER)
		max_ring_order = XEN_9PFS_RING_ORDER;
	if (p9_xen_trans.maxsize > XEN_FLEX_RING_SIZE(max_ring_order))
		p9_xen_trans.maxsize = XEN_FLEX_RING_SIZE(max_ring_order) / 2;

	priv->rings = kcalloc(XEN_9PFS_NUM_RINGS, sizeof(*priv->rings),
			      GFP_KERNEL);
	if (!priv->rings) {
		kfree(priv);
		return -ENOMEM;
	}

	for (i = 0; i < XEN_9PFS_NUM_RINGS; i++) {
		priv->rings[i].priv = priv;
		ret = xen_9pfs_front_alloc_dataring(dev, &priv->rings[i],
						    max_ring_order);
		if (ret < 0)
			goto error;
	}

 again:
	ret = xenbus_transaction_start(&xbt);
	if (ret) {
		xenbus_dev_fatal(dev, ret, "starting transaction");
		goto error;
	}
	ret = xenbus_printf(xbt, dev->nodename, "version", "%u", 1);
	if (ret)
		goto error_xenbus;
	ret = xenbus_printf(xbt, dev->nodename, "num-rings", "%u",
			    XEN_9PFS_NUM_RINGS);
	if (ret)
		goto error_xenbus;

	for (i = 0; i < XEN_9PFS_NUM_RINGS; i++) {
		char str[16];

		BUILD_BUG_ON(XEN_9PFS_NUM_RINGS > 9);
		sprintf(str, "ring-ref%d", i);
		ret = xenbus_printf(xbt, dev->nodename, str, "%d",
				    priv->rings[i].ref);
		if (ret)
			goto error_xenbus;

		sprintf(str, "event-channel-%d", i);
		ret = xenbus_printf(xbt, dev->nodename, str, "%u",
				    priv->rings[i].evtchn);
		if (ret)
			goto error_xenbus;
	}
	priv->tag = xenbus_read(xbt, dev->nodename, "tag", NULL);
	if (IS_ERR(priv->tag)) {
		ret = PTR_ERR(priv->tag);
		goto error_xenbus;
	}
	ret = xenbus_transaction_end(xbt, 0);
	if (ret) {
		if (ret == -EAGAIN)
			goto again;
		xenbus_dev_fatal(dev, ret, "completing transaction");
		goto error;
	}

	return 0;

 error_xenbus:
	xenbus_transaction_end(xbt, 1);
	xenbus_dev_fatal(dev, ret, "writing xenstore");
 error:
	xen_9pfs_front_free(priv);
	return ret;
}

static int xen_9pfs_front_probe(struct xenbus_device *dev,
				const struct xenbus_device_id *id)
{
	struct xen_9pfs_front_priv *priv = NULL;

	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
	if (!priv)
		return -ENOMEM;

	priv->dev = dev;
	dev_set_drvdata(&dev->dev, priv);

	write_lock(&xen_9pfs_lock);
	list_add_tail(&priv->list, &xen_9pfs_devs);
	write_unlock(&xen_9pfs_lock);

	return 0;
}

static int xen_9pfs_front_resume(struct xenbus_device *dev)
{
	dev_warn(&dev->dev, "suspend/resume unsupported\n");
	return 0;
}

static void xen_9pfs_front_changed(struct xenbus_device *dev,
				   enum xenbus_state backend_state)
{
	switch (backend_state) {
	case XenbusStateReconfiguring:
	case XenbusStateReconfigured:
	case XenbusStateInitialising:
	case XenbusStateInitialised:
	case XenbusStateUnknown:
		break;

	case XenbusStateInitWait:
		if (!xen_9pfs_front_init(dev))
			xenbus_switch_state(dev, XenbusStateInitialised);
		break;

	case XenbusStateConnected:
		xenbus_switch_state(dev, XenbusStateConnected);
		break;

	case XenbusStateClosed:
		if (dev->state == XenbusStateClosed)
			break;
		fallthrough;	/* Missed the backend's CLOSING state */
	case XenbusStateClosing:
		xenbus_frontend_closed(dev);
		break;
	}
}

static struct xenbus_driver xen_9pfs_front_driver = {
	.ids = xen_9pfs_front_ids,
	.probe = xen_9pfs_front_probe,
	.remove = xen_9pfs_front_remove,
	.resume = xen_9pfs_front_resume,
	.otherend_changed = xen_9pfs_front_changed,
};

static int __init p9_trans_xen_init(void)
{
	int rc;

	if (!xen_domain())
		return -ENODEV;

	pr_info("Initialising Xen transport for 9pfs\n");

	v9fs_register_trans(&p9_xen_trans);
	rc = xenbus_register_frontend(&xen_9pfs_front_driver);
	if (rc)
		v9fs_unregister_trans(&p9_xen_trans);

	return rc;
}
module_init(p9_trans_xen_init);
MODULE_ALIAS_9P("xen");

static void __exit p9_trans_xen_exit(void)
{
	v9fs_unregister_trans(&p9_xen_trans);
	return xenbus_unregister_driver(&xen_9pfs_front_driver);
}
module_exit(p9_trans_xen_exit);

MODULE_ALIAS("xen:9pfs");
MODULE_AUTHOR("Stefano Stabellini <stefano@aporeto.com>");
MODULE_DESCRIPTION("Xen Transport for 9P");
MODULE_LICENSE("GPL");