summaryrefslogtreecommitdiffstats
path: root/drivers/net/xen-netback/interface.c
blob: 625c6f49cfba9923e80dc0834d49a6a6b870f1b3 (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
/*
 * Network-device interface management.
 *
 * Copyright (c) 2004-2005, Keir Fraser
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License version 2
 * as published by the Free Software Foundation; or, when distributed
 * separately from the Linux kernel or incorporated into other
 * software packages, subject to the following license:
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this source file (the "Software"), to deal in the Software without
 * restriction, including without limitation the rights to use, copy, modify,
 * merge, publish, distribute, sublicense, and/or sell copies of the Software,
 * and to permit persons to whom the Software is furnished to do so, subject to
 * the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
 * IN THE SOFTWARE.
 */

#include "common.h"

#include <linux/kthread.h>
#include <linux/ethtool.h>
#include <linux/rtnetlink.h>
#include <linux/if_vlan.h>

#include <xen/events.h>
#include <asm/xen/hypercall.h>

#define XENVIF_QUEUE_LENGTH 32
#define XENVIF_NAPI_WEIGHT  64

int xenvif_schedulable(struct xenvif *vif)
{
	return netif_running(vif->dev) && netif_carrier_ok(vif->dev);
}

static int xenvif_rx_schedulable(struct xenvif *vif)
{
	return xenvif_schedulable(vif) && !xenvif_rx_ring_full(vif);
}

static irqreturn_t xenvif_tx_interrupt(int irq, void *dev_id)
{
	struct xenvif *vif = dev_id;

	if (RING_HAS_UNCONSUMED_REQUESTS(&vif->tx))
		napi_schedule(&vif->napi);

	return IRQ_HANDLED;
}

static int xenvif_poll(struct napi_struct *napi, int budget)
{
	struct xenvif *vif = container_of(napi, struct xenvif, napi);
	int work_done;

	work_done = xenvif_tx_action(vif, budget);

	if (work_done < budget) {
		int more_to_do = 0;
		unsigned long flags;

		/* It is necessary to disable IRQ before calling
		 * RING_HAS_UNCONSUMED_REQUESTS. Otherwise we might
		 * lose event from the frontend.
		 *
		 * Consider:
		 *   RING_HAS_UNCONSUMED_REQUESTS
		 *   <frontend generates event to trigger napi_schedule>
		 *   __napi_complete
		 *
		 * This handler is still in scheduled state so the
		 * event has no effect at all. After __napi_complete
		 * this handler is descheduled and cannot get
		 * scheduled again. We lose event in this case and the ring
		 * will be completely stalled.
		 */

		local_irq_save(flags);

		RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, more_to_do);
		if (!more_to_do)
			__napi_complete(napi);

		local_irq_restore(flags);
	}

	return work_done;
}

static irqreturn_t xenvif_rx_interrupt(int irq, void *dev_id)
{
	struct xenvif *vif = dev_id;

	if (xenvif_rx_schedulable(vif))
		netif_wake_queue(vif->dev);

	return IRQ_HANDLED;
}

static irqreturn_t xenvif_interrupt(int irq, void *dev_id)
{
	xenvif_tx_interrupt(irq, dev_id);
	xenvif_rx_interrupt(irq, dev_id);

	return IRQ_HANDLED;
}

static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct xenvif *vif = netdev_priv(dev);

	BUG_ON(skb->dev != dev);

	/* Drop the packet if vif is not ready */
	if (vif->task == NULL)
		goto drop;

	/* Drop the packet if the target domain has no receive buffers. */
	if (!xenvif_rx_schedulable(vif))
		goto drop;

	/* Reserve ring slots for the worst-case number of fragments. */
	vif->rx_req_cons_peek += xenvif_count_skb_slots(vif, skb);

	if (vif->can_queue && xenvif_must_stop_queue(vif))
		netif_stop_queue(dev);

	xenvif_queue_tx_skb(vif, skb);

	return NETDEV_TX_OK;

 drop:
	vif->dev->stats.tx_dropped++;
	dev_kfree_skb(skb);
	return NETDEV_TX_OK;
}

void xenvif_notify_tx_completion(struct xenvif *vif)
{
	if (netif_queue_stopped(vif->dev) && xenvif_rx_schedulable(vif))
		netif_wake_queue(vif->dev);
}

static struct net_device_stats *xenvif_get_stats(struct net_device *dev)
{
	struct xenvif *vif = netdev_priv(dev);
	return &vif->dev->stats;
}

static void xenvif_up(struct xenvif *vif)
{
	napi_enable(&vif->napi);
	enable_irq(vif->tx_irq);
	if (vif->tx_irq != vif->rx_irq)
		enable_irq(vif->rx_irq);
	xenvif_check_rx_xenvif(vif);
}

static void xenvif_down(struct xenvif *vif)
{
	napi_disable(&vif->napi);
	disable_irq(vif->tx_irq);
	if (vif->tx_irq != vif->rx_irq)
		disable_irq(vif->rx_irq);
	del_timer_sync(&vif->credit_timeout);
}

static int xenvif_open(struct net_device *dev)
{
	struct xenvif *vif = netdev_priv(dev);
	if (netif_carrier_ok(dev))
		xenvif_up(vif);
	netif_start_queue(dev);
	return 0;
}

static int xenvif_close(struct net_device *dev)
{
	struct xenvif *vif = netdev_priv(dev);
	if (netif_carrier_ok(dev))
		xenvif_down(vif);
	netif_stop_queue(dev);
	return 0;
}

static int xenvif_change_mtu(struct net_device *dev, int mtu)
{
	struct xenvif *vif = netdev_priv(dev);
	int max = vif->can_sg ? 65535 - VLAN_ETH_HLEN : ETH_DATA_LEN;

	if (mtu > max)
		return -EINVAL;
	dev->mtu = mtu;
	return 0;
}

static netdev_features_t xenvif_fix_features(struct net_device *dev,
	netdev_features_t features)
{
	struct xenvif *vif = netdev_priv(dev);

	if (!vif->can_sg)
		features &= ~NETIF_F_SG;
	if (!vif->gso && !vif->gso_prefix)
		features &= ~NETIF_F_TSO;
	if (!vif->csum)
		features &= ~NETIF_F_IP_CSUM;

	return features;
}

static const struct xenvif_stat {
	char name[ETH_GSTRING_LEN];
	u16 offset;
} xenvif_stats[] = {
	{
		"rx_gso_checksum_fixup",
		offsetof(struct xenvif, rx_gso_checksum_fixup)
	},
};

static int xenvif_get_sset_count(struct net_device *dev, int string_set)
{
	switch (string_set) {
	case ETH_SS_STATS:
		return ARRAY_SIZE(xenvif_stats);
	default:
		return -EINVAL;
	}
}

static void xenvif_get_ethtool_stats(struct net_device *dev,
				     struct ethtool_stats *stats, u64 * data)
{
	void *vif = netdev_priv(dev);
	int i;

	for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++)
		data[i] = *(unsigned long *)(vif + xenvif_stats[i].offset);
}

static void xenvif_get_strings(struct net_device *dev, u32 stringset, u8 * data)
{
	int i;

	switch (stringset) {
	case ETH_SS_STATS:
		for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++)
			memcpy(data + i * ETH_GSTRING_LEN,
			       xenvif_stats[i].name, ETH_GSTRING_LEN);
		break;
	}
}

static const struct ethtool_ops xenvif_ethtool_ops = {
	.get_link	= ethtool_op_get_link,

	.get_sset_count = xenvif_get_sset_count,
	.get_ethtool_stats = xenvif_get_ethtool_stats,
	.get_strings = xenvif_get_strings,
};

static const struct net_device_ops xenvif_netdev_ops = {
	.ndo_start_xmit	= xenvif_start_xmit,
	.ndo_get_stats	= xenvif_get_stats,
	.ndo_open	= xenvif_open,
	.ndo_stop	= xenvif_close,
	.ndo_change_mtu	= xenvif_change_mtu,
	.ndo_fix_features = xenvif_fix_features,
	.ndo_set_mac_address = eth_mac_addr,
	.ndo_validate_addr   = eth_validate_addr,
};

struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
			    unsigned int handle)
{
	int err;
	struct net_device *dev;
	struct xenvif *vif;
	char name[IFNAMSIZ] = {};
	int i;

	snprintf(name, IFNAMSIZ - 1, "vif%u.%u", domid, handle);
	dev = alloc_netdev(sizeof(struct xenvif), name, ether_setup);
	if (dev == NULL) {
		pr_warn("Could not allocate netdev for %s\n", name);
		return ERR_PTR(-ENOMEM);
	}

	SET_NETDEV_DEV(dev, parent);

	vif = netdev_priv(dev);
	vif->domid  = domid;
	vif->handle = handle;
	vif->can_sg = 1;
	vif->csum = 1;
	vif->dev = dev;

	vif->credit_bytes = vif->remaining_credit = ~0UL;
	vif->credit_usec  = 0UL;
	init_timer(&vif->credit_timeout);
	/* Initialize 'expires' now: it's used to track the credit window. */
	vif->credit_timeout.expires = jiffies;

	dev->netdev_ops	= &xenvif_netdev_ops;
	dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO;
	dev->features = dev->hw_features;
	SET_ETHTOOL_OPS(dev, &xenvif_ethtool_ops);

	dev->tx_queue_len = XENVIF_QUEUE_LENGTH;

	skb_queue_head_init(&vif->rx_queue);
	skb_queue_head_init(&vif->tx_queue);

	vif->pending_cons = 0;
	vif->pending_prod = MAX_PENDING_REQS;
	for (i = 0; i < MAX_PENDING_REQS; i++)
		vif->pending_ring[i] = i;
	for (i = 0; i < MAX_PENDING_REQS; i++)
		vif->mmap_pages[i] = NULL;

	/*
	 * Initialise a dummy MAC address. We choose the numerically
	 * largest non-broadcast address to prevent the address getting
	 * stolen by an Ethernet bridge for STP purposes.
	 * (FE:FF:FF:FF:FF:FF)
	 */
	memset(dev->dev_addr, 0xFF, ETH_ALEN);
	dev->dev_addr[0] &= ~0x01;

	netif_napi_add(dev, &vif->napi, xenvif_poll, XENVIF_NAPI_WEIGHT);

	netif_carrier_off(dev);

	err = register_netdev(dev);
	if (err) {
		netdev_warn(dev, "Could not register device: err=%d\n", err);
		free_netdev(dev);
		return ERR_PTR(err);
	}

	netdev_dbg(dev, "Successfully created xenvif\n");
	return vif;
}

int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
		   unsigned long rx_ring_ref, unsigned int tx_evtchn,
		   unsigned int rx_evtchn)
{
	int err = -ENOMEM;

	/* Already connected through? */
	if (vif->tx_irq)
		return 0;

	__module_get(THIS_MODULE);

	err = xenvif_map_frontend_rings(vif, tx_ring_ref, rx_ring_ref);
	if (err < 0)
		goto err;

	if (tx_evtchn == rx_evtchn) {
		/* feature-split-event-channels == 0 */
		err = bind_interdomain_evtchn_to_irqhandler(
			vif->domid, tx_evtchn, xenvif_interrupt, 0,
			vif->dev->name, vif);
		if (err < 0)
			goto err_unmap;
		vif->tx_irq = vif->rx_irq = err;
		disable_irq(vif->tx_irq);
	} else {
		/* feature-split-event-channels == 1 */
		snprintf(vif->tx_irq_name, sizeof(vif->tx_irq_name),
			 "%s-tx", vif->dev->name);
		err = bind_interdomain_evtchn_to_irqhandler(
			vif->domid, tx_evtchn, xenvif_tx_interrupt, 0,
			vif->tx_irq_name, vif);
		if (err < 0)
			goto err_unmap;
		vif->tx_irq = err;
		disable_irq(vif->tx_irq);

		snprintf(vif->rx_irq_name, sizeof(vif->rx_irq_name),
			 "%s-rx", vif->dev->name);
		err = bind_interdomain_evtchn_to_irqhandler(
			vif->domid, rx_evtchn, xenvif_rx_interrupt, 0,
			vif->rx_irq_name, vif);
		if (err < 0)
			goto err_tx_unbind;
		vif->rx_irq = err;
		disable_irq(vif->rx_irq);
	}

	init_waitqueue_head(&vif->wq);
	vif->task = kthread_create(xenvif_kthread,
				   (void *)vif, vif->dev->name);
	if (IS_ERR(vif->task)) {
		pr_warn("Could not allocate kthread for %s\n", vif->dev->name);
		err = PTR_ERR(vif->task);
		goto err_rx_unbind;
	}

	rtnl_lock();
	if (!vif->can_sg && vif->dev->mtu > ETH_DATA_LEN)
		dev_set_mtu(vif->dev, ETH_DATA_LEN);
	netdev_update_features(vif->dev);
	netif_carrier_on(vif->dev);
	if (netif_running(vif->dev))
		xenvif_up(vif);
	rtnl_unlock();

	wake_up_process(vif->task);

	return 0;

err_rx_unbind:
	unbind_from_irqhandler(vif->rx_irq, vif);
	vif->rx_irq = 0;
err_tx_unbind:
	unbind_from_irqhandler(vif->tx_irq, vif);
	vif->tx_irq = 0;
err_unmap:
	xenvif_unmap_frontend_rings(vif);
err:
	module_put(THIS_MODULE);
	return err;
}

void xenvif_carrier_off(struct xenvif *vif)
{
	struct net_device *dev = vif->dev;

	rtnl_lock();
	netif_carrier_off(dev); /* discard queued packets */
	if (netif_running(dev))
		xenvif_down(vif);
	rtnl_unlock();
}

void xenvif_disconnect(struct xenvif *vif)
{
	/* Disconnect funtion might get called by generic framework
	 * even before vif connects, so we need to check if we really
	 * need to do a module_put.
	 */
	int need_module_put = 0;

	if (netif_carrier_ok(vif->dev))
		xenvif_carrier_off(vif);

	if (vif->tx_irq) {
		if (vif->tx_irq == vif->rx_irq)
			unbind_from_irqhandler(vif->tx_irq, vif);
		else {
			unbind_from_irqhandler(vif->tx_irq, vif);
			unbind_from_irqhandler(vif->rx_irq, vif);
		}
		/* vif->irq is valid, we had a module_get in
		 * xenvif_connect.
		 */
		need_module_put = 1;
	}

	if (vif->task)
		kthread_stop(vif->task);

	netif_napi_del(&vif->napi);

	unregister_netdev(vif->dev);

	xenvif_unmap_frontend_rings(vif);

	free_netdev(vif->dev);

	if (need_module_put)
		module_put(THIS_MODULE);
}
OpenPOWER on IntegriCloud