sunvnet.c 29.6 KB
Newer Older
1
2
/* sunvnet.c: Sun LDOM Virtual Network Driver.
 *
3
 * Copyright (C) 2007, 2008 David S. Miller <davem@davemloft.net>
4
5
 */

6
7
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

8
9
10
11
12
13
14
15
16
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/delay.h>
#include <linux/init.h>
#include <linux/netdevice.h>
#include <linux/ethtool.h>
#include <linux/etherdevice.h>
17
#include <linux/mutex.h>
18
19
20
21
22
23
24
25
26
27

#include <asm/vio.h>
#include <asm/ldc.h>

#include "sunvnet.h"

#define DRV_MODULE_NAME		"sunvnet"
#define DRV_MODULE_VERSION	"1.0"
#define DRV_MODULE_RELDATE	"June 25, 2007"

28
static char version[] =
29
30
31
32
33
34
	DRV_MODULE_NAME ".c:v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n";
MODULE_AUTHOR("David S. Miller (davem@davemloft.net)");
MODULE_DESCRIPTION("Sun LDOM virtual network driver");
MODULE_LICENSE("GPL");
MODULE_VERSION(DRV_MODULE_VERSION);

35
36
37
38
39
/* Heuristic for the number of times to exponentially backoff and
 * retry sending an LDC trigger when EAGAIN is encountered
 */
#define	VNET_MAX_RETRIES	10

40
41
42
43
44
45
46
47
48
49
50
51
52
53
/* Ordered from largest major to lowest */
static struct vio_version vnet_versions[] = {
	{ .major = 1, .minor = 0 },
};

static inline u32 vnet_tx_dring_avail(struct vio_dring_state *dr)
{
	return vio_dring_avail(dr, VNET_TX_RING_SIZE);
}

static int vnet_handle_unknown(struct vnet_port *port, void *arg)
{
	struct vio_msg_tag *pkt = arg;

54
	pr_err("Received unknown msg [%02x:%02x:%04x:%08x]\n",
55
	       pkt->type, pkt->stype, pkt->stype_env, pkt->sid);
56
	pr_err("Resetting connection\n");
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

	ldc_disconnect(port->vio.lp);

	return -ECONNRESET;
}

static int vnet_send_attr(struct vio_driver_state *vio)
{
	struct vnet_port *port = to_vnet_port(vio);
	struct net_device *dev = port->vp->dev;
	struct vio_net_attr_info pkt;
	int i;

	memset(&pkt, 0, sizeof(pkt));
	pkt.tag.type = VIO_TYPE_CTRL;
	pkt.tag.stype = VIO_SUBTYPE_INFO;
	pkt.tag.stype_env = VIO_ATTR_INFO;
	pkt.tag.sid = vio_send_sid(vio);
	pkt.xfer_mode = VIO_DRING_MODE;
	pkt.addr_type = VNET_ADDR_ETHERMAC;
	pkt.ack_freq = 0;
	for (i = 0; i < 6; i++)
		pkt.addr |= (u64)dev->dev_addr[i] << ((5 - i) * 8);
	pkt.mtu = ETH_FRAME_LEN;

	viodbg(HS, "SEND NET ATTR xmode[0x%x] atype[0x%x] addr[%llx] "
	       "ackfreq[%u] mtu[%llu]\n",
	       pkt.xfer_mode, pkt.addr_type,
	       (unsigned long long) pkt.addr,
	       pkt.ack_freq,
	       (unsigned long long) pkt.mtu);

	return vio_ldc_send(vio, &pkt, sizeof(pkt));
}

static int handle_attr_info(struct vio_driver_state *vio,
			    struct vio_net_attr_info *pkt)
{
	viodbg(HS, "GOT NET ATTR INFO xmode[0x%x] atype[0x%x] addr[%llx] "
	       "ackfreq[%u] mtu[%llu]\n",
	       pkt->xfer_mode, pkt->addr_type,
	       (unsigned long long) pkt->addr,
	       pkt->ack_freq,
	       (unsigned long long) pkt->mtu);

	pkt->tag.sid = vio_send_sid(vio);

	if (pkt->xfer_mode != VIO_DRING_MODE ||
	    pkt->addr_type != VNET_ADDR_ETHERMAC ||
	    pkt->mtu != ETH_FRAME_LEN) {
		viodbg(HS, "SEND NET ATTR NACK\n");

		pkt->tag.stype = VIO_SUBTYPE_NACK;

		(void) vio_ldc_send(vio, pkt, sizeof(*pkt));

		return -ECONNRESET;
	} else {
		viodbg(HS, "SEND NET ATTR ACK\n");

		pkt->tag.stype = VIO_SUBTYPE_ACK;

		return vio_ldc_send(vio, pkt, sizeof(*pkt));
	}

}

static int handle_attr_ack(struct vio_driver_state *vio,
			   struct vio_net_attr_info *pkt)
{
	viodbg(HS, "GOT NET ATTR ACK\n");

	return 0;
}

static int handle_attr_nack(struct vio_driver_state *vio,
			    struct vio_net_attr_info *pkt)
{
	viodbg(HS, "GOT NET ATTR NACK\n");

	return -ECONNRESET;
}

static int vnet_handle_attr(struct vio_driver_state *vio, void *arg)
{
	struct vio_net_attr_info *pkt = arg;

	switch (pkt->tag.stype) {
	case VIO_SUBTYPE_INFO:
		return handle_attr_info(vio, pkt);

	case VIO_SUBTYPE_ACK:
		return handle_attr_ack(vio, pkt);

	case VIO_SUBTYPE_NACK:
		return handle_attr_nack(vio, pkt);

	default:
		return -ECONNRESET;
	}
}

static void vnet_handshake_complete(struct vio_driver_state *vio)
{
	struct vio_dring_state *dr;

	dr = &vio->drings[VIO_DRIVER_RX_RING];
	dr->snd_nxt = dr->rcv_nxt = 1;

	dr = &vio->drings[VIO_DRIVER_TX_RING];
	dr->snd_nxt = dr->rcv_nxt = 1;
}

/* The hypervisor interface that implements copying to/from imported
 * memory from another domain requires that copies are done to 8-byte
 * aligned buffers, and that the lengths of such copies are also 8-byte
 * multiples.
 *
 * So we align skb->data to an 8-byte multiple and pad-out the data
 * area so we can round the copy length up to the next multiple of
 * 8 for the copy.
 *
 * The transmitter puts the actual start of the packet 6 bytes into
 * the buffer it sends over, so that the IP headers after the ethernet
 * header are aligned properly.  These 6 bytes are not in the descriptor
 * length, they are simply implied.  This offset is represented using
 * the VNET_PACKET_SKIP macro.
 */
static struct sk_buff *alloc_and_align_skb(struct net_device *dev,
					   unsigned int len)
{
	struct sk_buff *skb = netdev_alloc_skb(dev, len+VNET_PACKET_SKIP+8+8);
	unsigned long addr, off;

	if (unlikely(!skb))
		return NULL;

	addr = (unsigned long) skb->data;
	off = ((addr + 7UL) & ~7UL) - addr;
	if (off)
		skb_reserve(skb, off);

	return skb;
}

static int vnet_rx_one(struct vnet_port *port, unsigned int len,
		       struct ldc_trans_cookie *cookies, int ncookies)
{
	struct net_device *dev = port->vp->dev;
	unsigned int copy_len;
	struct sk_buff *skb;
	int err;

	err = -EMSGSIZE;
	if (unlikely(len < ETH_ZLEN || len > ETH_FRAME_LEN)) {
		dev->stats.rx_length_errors++;
		goto out_dropped;
	}

	skb = alloc_and_align_skb(dev, len);
	err = -ENOMEM;
	if (unlikely(!skb)) {
		dev->stats.rx_missed_errors++;
		goto out_dropped;
	}

	copy_len = (len + VNET_PACKET_SKIP + 7U) & ~7U;
	skb_put(skb, copy_len);
	err = ldc_copy(port->vio.lp, LDC_COPY_IN,
		       skb->data, copy_len, 0,
		       cookies, ncookies);
	if (unlikely(err < 0)) {
		dev->stats.rx_frame_errors++;
		goto out_free_skb;
	}

	skb_pull(skb, VNET_PACKET_SKIP);
	skb_trim(skb, len);
	skb->protocol = eth_type_trans(skb, dev);

	dev->stats.rx_packets++;
	dev->stats.rx_bytes += len;

	netif_rx(skb);

	return 0;

out_free_skb:
	kfree_skb(skb);

out_dropped:
	dev->stats.rx_dropped++;
	return err;
}

static int vnet_send_ack(struct vnet_port *port, struct vio_dring_state *dr,
			 u32 start, u32 end, u8 vio_dring_state)
{
	struct vio_dring_data hdr = {
		.tag = {
			.type		= VIO_TYPE_DATA,
			.stype		= VIO_SUBTYPE_ACK,
			.stype_env	= VIO_DRING_DATA,
			.sid		= vio_send_sid(&port->vio),
		},
		.dring_ident		= dr->ident,
		.start_idx		= start,
		.end_idx		= end,
		.state			= vio_dring_state,
	};
	int err, delay;
268
	int retries = 0;
269
270
271
272
273
274
275
276
277
278
279
280

	hdr.seq = dr->snd_nxt;
	delay = 1;
	do {
		err = vio_ldc_send(&port->vio, &hdr, sizeof(hdr));
		if (err > 0) {
			dr->snd_nxt++;
			break;
		}
		udelay(delay);
		if ((delay <<= 1) > 128)
			delay = 128;
281
282
283
284
285
286
287
		if (retries++ > VNET_MAX_RETRIES) {
			pr_info("ECONNRESET %x:%x:%x:%x:%x:%x\n",
				port->raddr[0], port->raddr[1],
				port->raddr[2], port->raddr[3],
				port->raddr[4], port->raddr[5]);
			err = -ECONNRESET;
		}
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
	} while (err == -EAGAIN);

	return err;
}

static u32 next_idx(u32 idx, struct vio_dring_state *dr)
{
	if (++idx == dr->num_entries)
		idx = 0;
	return idx;
}

static u32 prev_idx(u32 idx, struct vio_dring_state *dr)
{
	if (idx == 0)
		idx = dr->num_entries - 1;
	else
		idx--;

	return idx;
}

static struct vio_net_desc *get_rx_desc(struct vnet_port *port,
					struct vio_dring_state *dr,
					u32 index)
{
	struct vio_net_desc *desc = port->vio.desc_buf;
	int err;

	err = ldc_get_dring_entry(port->vio.lp, desc, dr->entry_size,
				  (index * dr->entry_size),
				  dr->cookies, dr->ncookies);
	if (err < 0)
		return ERR_PTR(err);

	return desc;
}

static int put_rx_desc(struct vnet_port *port,
		       struct vio_dring_state *dr,
		       struct vio_net_desc *desc,
		       u32 index)
{
	int err;

	err = ldc_put_dring_entry(port->vio.lp, desc, dr->entry_size,
				  (index * dr->entry_size),
				  dr->cookies, dr->ncookies);
	if (err < 0)
		return err;

	return 0;
}

static int vnet_walk_rx_one(struct vnet_port *port,
			    struct vio_dring_state *dr,
			    u32 index, int *needs_ack)
{
	struct vio_net_desc *desc = get_rx_desc(port, dr, index);
	struct vio_driver_state *vio = &port->vio;
	int err;

	if (IS_ERR(desc))
		return PTR_ERR(desc);

353
	viodbg(DATA, "vio_walk_rx_one desc[%02x:%02x:%08x:%08x:%llx:%llx]\n",
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
	       desc->hdr.state, desc->hdr.ack,
	       desc->size, desc->ncookies,
	       desc->cookies[0].cookie_addr,
	       desc->cookies[0].cookie_size);

	if (desc->hdr.state != VIO_DESC_READY)
		return 1;
	err = vnet_rx_one(port, desc->size, desc->cookies, desc->ncookies);
	if (err == -ECONNRESET)
		return err;
	desc->hdr.state = VIO_DESC_DONE;
	err = put_rx_desc(port, dr, desc, index);
	if (err < 0)
		return err;
	*needs_ack = desc->hdr.ack;
	return 0;
}

static int vnet_walk_rx(struct vnet_port *port, struct vio_dring_state *dr,
			u32 start, u32 end)
{
	struct vio_driver_state *vio = &port->vio;
	int ack_start = -1, ack_end = -1;

	end = (end == (u32) -1) ? prev_idx(start, dr) : next_idx(end, dr);

	viodbg(DATA, "vnet_walk_rx start[%08x] end[%08x]\n", start, end);

	while (start != end) {
		int ack = 0, err = vnet_walk_rx_one(port, dr, start, &ack);
		if (err == -ECONNRESET)
			return err;
		if (err != 0)
			break;
		if (ack_start == -1)
			ack_start = start;
		ack_end = start;
		start = next_idx(start, dr);
		if (ack && start != end) {
			err = vnet_send_ack(port, dr, ack_start, ack_end,
					    VIO_DRING_ACTIVE);
			if (err == -ECONNRESET)
				return err;
			ack_start = -1;
		}
	}
	if (unlikely(ack_start == -1))
		ack_start = ack_end = prev_idx(start, dr);
	return vnet_send_ack(port, dr, ack_start, ack_end, VIO_DRING_STOPPED);
}

static int vnet_rx(struct vnet_port *port, void *msgbuf)
{
	struct vio_dring_data *pkt = msgbuf;
	struct vio_dring_state *dr = &port->vio.drings[VIO_DRIVER_RX_RING];
	struct vio_driver_state *vio = &port->vio;

411
	viodbg(DATA, "vnet_rx stype_env[%04x] seq[%016llx] rcv_nxt[%016llx]\n",
412
413
414
415
416
	       pkt->tag.stype_env, pkt->seq, dr->rcv_nxt);

	if (unlikely(pkt->tag.stype_env != VIO_DRING_DATA))
		return 0;
	if (unlikely(pkt->seq != dr->rcv_nxt)) {
417
418
		pr_err("RX out of sequence seq[0x%llx] rcv_nxt[0x%llx]\n",
		       pkt->seq, dr->rcv_nxt);
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
		return 0;
	}

	dr->rcv_nxt++;

	/* XXX Validate pkt->start_idx and pkt->end_idx XXX */

	return vnet_walk_rx(port, dr, pkt->start_idx, pkt->end_idx);
}

static int idx_is_pending(struct vio_dring_state *dr, u32 end)
{
	u32 idx = dr->cons;
	int found = 0;

	while (idx != dr->prod) {
		if (idx == end) {
			found = 1;
			break;
		}
		idx = next_idx(idx, dr);
	}
	return found;
}

static int vnet_ack(struct vnet_port *port, void *msgbuf)
{
	struct vio_dring_state *dr = &port->vio.drings[VIO_DRIVER_TX_RING];
	struct vio_dring_data *pkt = msgbuf;
	struct net_device *dev;
	struct vnet *vp;
	u32 end;

	if (unlikely(pkt->tag.stype_env != VIO_DRING_DATA))
		return 0;

	end = pkt->end_idx;
	if (unlikely(!idx_is_pending(dr, end)))
		return 0;

	dr->cons = next_idx(end, dr);

	vp = port->vp;
	dev = vp->dev;
	if (unlikely(netif_queue_stopped(dev) &&
		     vnet_tx_dring_avail(dr) >= VNET_TX_WAKEUP_THRESH(dr)))
		return 1;

	return 0;
}

static int vnet_nack(struct vnet_port *port, void *msgbuf)
{
	/* XXX just reset or similar XXX */
	return 0;
}

476
477
478
479
480
static int handle_mcast(struct vnet_port *port, void *msgbuf)
{
	struct vio_net_mcast_info *pkt = msgbuf;

	if (pkt->tag.stype != VIO_SUBTYPE_ACK)
481
		pr_err("%s: Got unexpected MCAST reply [%02x:%02x:%04x:%08x]\n",
482
483
484
485
486
487
488
489
490
		       port->vp->dev->name,
		       pkt->tag.type,
		       pkt->tag.stype,
		       pkt->tag.stype_env,
		       pkt->tag.sid);

	return 0;
}

491
static void maybe_tx_wakeup(unsigned long param)
492
{
493
	struct vnet *vp = (struct vnet *)param;
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
	struct net_device *dev = vp->dev;

	netif_tx_lock(dev);
	if (likely(netif_queue_stopped(dev))) {
		struct vnet_port *port;
		int wake = 1;

		list_for_each_entry(port, &vp->port_list, list) {
			struct vio_dring_state *dr;

			dr = &port->vio.drings[VIO_DRIVER_TX_RING];
			if (vnet_tx_dring_avail(dr) <
			    VNET_TX_WAKEUP_THRESH(dr)) {
				wake = 0;
				break;
			}
		}
		if (wake)
			netif_wake_queue(dev);
	}
	netif_tx_unlock(dev);
}

static void vnet_event(void *arg, int event)
{
	struct vnet_port *port = arg;
	struct vio_driver_state *vio = &port->vio;
	unsigned long flags;
	int tx_wakeup, err;

	spin_lock_irqsave(&vio->lock, flags);

	if (unlikely(event == LDC_EVENT_RESET ||
		     event == LDC_EVENT_UP)) {
		vio_link_state_change(vio, event);
		spin_unlock_irqrestore(&vio->lock, flags);

531
532
		if (event == LDC_EVENT_RESET)
			vio_port_up(vio);
533
534
535
536
		return;
	}

	if (unlikely(event != LDC_EVENT_DATA_READY)) {
537
		pr_warning("Unexpected LDC event %d\n", event);
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
		spin_unlock_irqrestore(&vio->lock, flags);
		return;
	}

	tx_wakeup = err = 0;
	while (1) {
		union {
			struct vio_msg_tag tag;
			u64 raw[8];
		} msgbuf;

		err = ldc_read(vio->lp, &msgbuf, sizeof(msgbuf));
		if (unlikely(err < 0)) {
			if (err == -ECONNRESET)
				vio_conn_reset(vio);
			break;
		}
		if (err == 0)
			break;
		viodbg(DATA, "TAG [%02x:%02x:%04x:%08x]\n",
		       msgbuf.tag.type,
		       msgbuf.tag.stype,
		       msgbuf.tag.stype_env,
		       msgbuf.tag.sid);
		err = vio_validate_sid(vio, &msgbuf.tag);
		if (err < 0)
			break;

		if (likely(msgbuf.tag.type == VIO_TYPE_DATA)) {
			if (msgbuf.tag.stype == VIO_SUBTYPE_INFO) {
				err = vnet_rx(port, &msgbuf);
			} else if (msgbuf.tag.stype == VIO_SUBTYPE_ACK) {
				err = vnet_ack(port, &msgbuf);
				if (err > 0)
					tx_wakeup |= err;
			} else if (msgbuf.tag.stype == VIO_SUBTYPE_NACK) {
				err = vnet_nack(port, &msgbuf);
			}
		} else if (msgbuf.tag.type == VIO_TYPE_CTRL) {
577
578
579
580
			if (msgbuf.tag.stype_env == VNET_MCAST_INFO)
				err = handle_mcast(port, &msgbuf);
			else
				err = vio_control_pkt_engine(vio, &msgbuf);
581
582
583
584
585
586
587
588
589
			if (err)
				break;
		} else {
			err = vnet_handle_unknown(port, &msgbuf);
		}
		if (err == -ECONNRESET)
			break;
	}
	spin_unlock(&vio->lock);
590
591
592
593
	/* Kick off a tasklet to wake the queue.  We cannot call
	 * maybe_tx_wakeup directly here because we could deadlock on
	 * netif_tx_lock() with dev_watchdog()
	 */
594
	if (unlikely(tx_wakeup && err != -ECONNRESET))
595
596
		tasklet_schedule(&port->vp->vnet_tx_wakeup);

597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
	local_irq_restore(flags);
}

static int __vnet_tx_trigger(struct vnet_port *port)
{
	struct vio_dring_state *dr = &port->vio.drings[VIO_DRIVER_TX_RING];
	struct vio_dring_data hdr = {
		.tag = {
			.type		= VIO_TYPE_DATA,
			.stype		= VIO_SUBTYPE_INFO,
			.stype_env	= VIO_DRING_DATA,
			.sid		= vio_send_sid(&port->vio),
		},
		.dring_ident		= dr->ident,
		.start_idx		= dr->prod,
		.end_idx		= (u32) -1,
	};
	int err, delay;
615
	int retries = 0;
616
617
618
619
620
621
622
623
624
625
626
627

	hdr.seq = dr->snd_nxt;
	delay = 1;
	do {
		err = vio_ldc_send(&port->vio, &hdr, sizeof(hdr));
		if (err > 0) {
			dr->snd_nxt++;
			break;
		}
		udelay(delay);
		if ((delay <<= 1) > 128)
			delay = 128;
628
629
		if (retries++ > VNET_MAX_RETRIES)
			break;
630
631
632
633
634
	} while (err == -EAGAIN);

	return err;
}

635
636
637
638
639
640
641
static inline bool port_is_up(struct vnet_port *vnet)
{
	struct vio_driver_state *vio = &vnet->vio;

	return !!(vio->hs_state & VIO_HS_COMPLETE);
}

642
643
644
645
646
647
struct vnet_port *__tx_port_find(struct vnet *vp, struct sk_buff *skb)
{
	unsigned int hash = vnet_hashfn(skb->data);
	struct hlist_head *hp = &vp->port_hash[hash];
	struct vnet_port *port;

648
	hlist_for_each_entry(port, hp, hash) {
649
650
		if (!port_is_up(port))
			continue;
651
		if (ether_addr_equal(port->raddr, skb->data))
652
653
			return port;
	}
654
655
656
657
658
659
660
661
	list_for_each_entry(port, &vp->port_list, list) {
		if (!port->switch_port)
			continue;
		if (!port_is_up(port))
			continue;
		return port;
	}
	return NULL;
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
}

struct vnet_port *tx_port_find(struct vnet *vp, struct sk_buff *skb)
{
	struct vnet_port *ret;
	unsigned long flags;

	spin_lock_irqsave(&vp->lock, flags);
	ret = __tx_port_find(vp, skb);
	spin_unlock_irqrestore(&vp->lock, flags);

	return ret;
}

static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct vnet *vp = netdev_priv(dev);
	struct vnet_port *port = tx_port_find(vp, skb);
	struct vio_dring_state *dr;
	struct vio_net_desc *d;
	unsigned long flags;
	unsigned int len;
	void *tx_buf;
	int i, err;

	if (unlikely(!port))
		goto out_dropped;

	spin_lock_irqsave(&port->vio.lock, flags);

	dr = &port->vio.drings[VIO_DRIVER_TX_RING];
693
	if (unlikely(vnet_tx_dring_avail(dr) < 1)) {
694
695
696
697
		if (!netif_queue_stopped(dev)) {
			netif_stop_queue(dev);

			/* This is a hard error, log it. */
698
			netdev_err(dev, "BUG! Tx Ring full when queue awake!\n");
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
			dev->stats.tx_errors++;
		}
		spin_unlock_irqrestore(&port->vio.lock, flags);
		return NETDEV_TX_BUSY;
	}

	d = vio_dring_cur(dr);

	tx_buf = port->tx_bufs[dr->prod].buf;
	skb_copy_from_linear_data(skb, tx_buf + VNET_PACKET_SKIP, skb->len);

	len = skb->len;
	if (len < ETH_ZLEN) {
		len = ETH_ZLEN;
		memset(tx_buf+VNET_PACKET_SKIP+skb->len, 0, len - skb->len);
	}

716
717
718
719
720
721
722
723
724
	/* We don't rely on the ACKs to free the skb in vnet_start_xmit(),
	 * thus it is safe to not set VIO_ACK_ENABLE for each transmission:
	 * the protocol itself does not require it as long as the peer
	 * sends a VIO_SUBTYPE_ACK for VIO_DRING_STOPPED.
	 *
	 * An ACK for every packet in the ring is expensive as the
	 * sending of LDC messages is slow and affects performance.
	 */
	d->hdr.ack = VIO_ACK_DISABLE;
725
726
727
728
729
730
731
732
733
734
735
736
737
738
	d->size = len;
	d->ncookies = port->tx_bufs[dr->prod].ncookies;
	for (i = 0; i < d->ncookies; i++)
		d->cookies[i] = port->tx_bufs[dr->prod].cookies[i];

	/* This has to be a non-SMP write barrier because we are writing
	 * to memory which is shared with the peer LDOM.
	 */
	wmb();

	d->hdr.state = VIO_DESC_READY;

	err = __vnet_tx_trigger(port);
	if (unlikely(err < 0)) {
739
		netdev_info(dev, "TX trigger error %d\n", err);
740
741
742
743
744
745
746
747
748
		d->hdr.state = VIO_DESC_FREE;
		dev->stats.tx_carrier_errors++;
		goto out_dropped_unlock;
	}

	dev->stats.tx_packets++;
	dev->stats.tx_bytes += skb->len;

	dr->prod = (dr->prod + 1) & (VNET_TX_RING_SIZE - 1);
749
	if (unlikely(vnet_tx_dring_avail(dr) < 1)) {
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
		netif_stop_queue(dev);
		if (vnet_tx_dring_avail(dr) > VNET_TX_WAKEUP_THRESH(dr))
			netif_wake_queue(dev);
	}

	spin_unlock_irqrestore(&port->vio.lock, flags);

	dev_kfree_skb(skb);

	return NETDEV_TX_OK;

out_dropped_unlock:
	spin_unlock_irqrestore(&port->vio.lock, flags);

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

static void vnet_tx_timeout(struct net_device *dev)
{
	/* XXX Implement me XXX */
}

static int vnet_open(struct net_device *dev)
{
	netif_carrier_on(dev);
	netif_start_queue(dev);

	return 0;
}

static int vnet_close(struct net_device *dev)
{
	netif_stop_queue(dev);
	netif_carrier_off(dev);

	return 0;
}

791
792
793
794
795
static struct vnet_mcast_entry *__vnet_mc_find(struct vnet *vp, u8 *addr)
{
	struct vnet_mcast_entry *m;

	for (m = vp->mcast_list; m; m = m->next) {
796
		if (ether_addr_equal(m->addr, addr))
797
798
799
800
801
802
803
			return m;
	}
	return NULL;
}

static void __update_mc_list(struct vnet *vp, struct net_device *dev)
{
804
	struct netdev_hw_addr *ha;
805

806
	netdev_for_each_mc_addr(ha, dev) {
807
808
		struct vnet_mcast_entry *m;

809
		m = __vnet_mc_find(vp, ha->addr);
810
811
812
813
814
815
816
817
818
		if (m) {
			m->hit = 1;
			continue;
		}

		if (!m) {
			m = kzalloc(sizeof(*m), GFP_ATOMIC);
			if (!m)
				continue;
819
			memcpy(m->addr, ha->addr, ETH_ALEN);
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
			m->hit = 1;

			m->next = vp->mcast_list;
			vp->mcast_list = m;
		}
	}
}

static void __send_mc_list(struct vnet *vp, struct vnet_port *port)
{
	struct vio_net_mcast_info info;
	struct vnet_mcast_entry *m, **pp;
	int n_addrs;

	memset(&info, 0, sizeof(info));

	info.tag.type = VIO_TYPE_CTRL;
	info.tag.stype = VIO_SUBTYPE_INFO;
	info.tag.stype_env = VNET_MCAST_INFO;
	info.tag.sid = vio_send_sid(&port->vio);
	info.set = 1;

	n_addrs = 0;
	for (m = vp->mcast_list; m; m = m->next) {
		if (m->sent)
			continue;
		m->sent = 1;
		memcpy(&info.mcast_addr[n_addrs * ETH_ALEN],
		       m->addr, ETH_ALEN);
		if (++n_addrs == VNET_NUM_MCAST) {
			info.count = n_addrs;

			(void) vio_ldc_send(&port->vio, &info,
					    sizeof(info));
			n_addrs = 0;
		}
	}
	if (n_addrs) {
		info.count = n_addrs;
		(void) vio_ldc_send(&port->vio, &info, sizeof(info));
	}

	info.set = 0;

	n_addrs = 0;
	pp = &vp->mcast_list;
	while ((m = *pp) != NULL) {
		if (m->hit) {
			m->hit = 0;
			pp = &m->next;
			continue;
		}

		memcpy(&info.mcast_addr[n_addrs * ETH_ALEN],
		       m->addr, ETH_ALEN);
		if (++n_addrs == VNET_NUM_MCAST) {
			info.count = n_addrs;
			(void) vio_ldc_send(&port->vio, &info,
					    sizeof(info));
			n_addrs = 0;
		}

		*pp = m->next;
		kfree(m);
	}
	if (n_addrs) {
		info.count = n_addrs;
		(void) vio_ldc_send(&port->vio, &info, sizeof(info));
	}
}

891
892
static void vnet_set_rx_mode(struct net_device *dev)
{
893
894
895
896
897
898
899
900
901
902
903
904
905
906
	struct vnet *vp = netdev_priv(dev);
	struct vnet_port *port;
	unsigned long flags;

	spin_lock_irqsave(&vp->lock, flags);
	if (!list_empty(&vp->port_list)) {
		port = list_entry(vp->port_list.next, struct vnet_port, list);

		if (port->switch_port) {
			__update_mc_list(vp, dev);
			__send_mc_list(vp, port);
		}
	}
	spin_unlock_irqrestore(&vp->lock, flags);
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
}

static int vnet_change_mtu(struct net_device *dev, int new_mtu)
{
	if (new_mtu != ETH_DATA_LEN)
		return -EINVAL;

	dev->mtu = new_mtu;
	return 0;
}

static int vnet_set_mac_addr(struct net_device *dev, void *p)
{
	return -EINVAL;
}

static void vnet_get_drvinfo(struct net_device *dev,
			     struct ethtool_drvinfo *info)
{
926
927
	strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver));
	strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version));
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
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
}

static u32 vnet_get_msglevel(struct net_device *dev)
{
	struct vnet *vp = netdev_priv(dev);
	return vp->msg_enable;
}

static void vnet_set_msglevel(struct net_device *dev, u32 value)
{
	struct vnet *vp = netdev_priv(dev);
	vp->msg_enable = value;
}

static const struct ethtool_ops vnet_ethtool_ops = {
	.get_drvinfo		= vnet_get_drvinfo,
	.get_msglevel		= vnet_get_msglevel,
	.set_msglevel		= vnet_set_msglevel,
	.get_link		= ethtool_op_get_link,
};

static void vnet_port_free_tx_bufs(struct vnet_port *port)
{
	struct vio_dring_state *dr;
	int i;

	dr = &port->vio.drings[VIO_DRIVER_TX_RING];
	if (dr->base) {
		ldc_free_exp_dring(port->vio.lp, dr->base,
				   (dr->entry_size * dr->num_entries),
				   dr->cookies, dr->ncookies);
		dr->base = NULL;
		dr->entry_size = 0;
		dr->num_entries = 0;
		dr->pending = 0;
		dr->ncookies = 0;
	}

	for (i = 0; i < VNET_TX_RING_SIZE; i++) {
		void *buf = port->tx_bufs[i].buf;

		if (!buf)
			continue;

		ldc_unmap(port->vio.lp,
			  port->tx_bufs[i].cookies,
			  port->tx_bufs[i].ncookies);

		kfree(buf);
		port->tx_bufs[i].buf = NULL;
	}
}

981
static int vnet_port_alloc_tx_bufs(struct vnet_port *port)
982
983
984
985
986
987
988
989
990
991
992
{
	struct vio_dring_state *dr;
	unsigned long len;
	int i, err, ncookies;
	void *dring;

	for (i = 0; i < VNET_TX_RING_SIZE; i++) {
		void *buf = kzalloc(ETH_FRAME_LEN + 8, GFP_KERNEL);
		int map_len = (ETH_FRAME_LEN + 7) & ~7;

		err = -ENOMEM;
993
		if (!buf)
994
			goto err_out;
995

996
997
		err = -EFAULT;
		if ((unsigned long)buf & (8UL - 1)) {
998
			pr_err("TX buffer misaligned\n");
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
			kfree(buf);
			goto err_out;
		}

		err = ldc_map_single(port->vio.lp, buf, map_len,
				     port->tx_bufs[i].cookies, 2,
				     (LDC_MAP_SHADOW |
				      LDC_MAP_DIRECT |
				      LDC_MAP_RW));
		if (err < 0) {
			kfree(buf);
			goto err_out;
		}
		port->tx_bufs[i].buf = buf;
		port->tx_bufs[i].ncookies = err;
	}

	dr = &port->vio.drings[VIO_DRIVER_TX_RING];

	len = (VNET_TX_RING_SIZE *
	       (sizeof(struct vio_net_desc) +
		(sizeof(struct ldc_trans_cookie) * 2)));

	ncookies = VIO_MAX_RING_COOKIES;
	dring = ldc_alloc_exp_dring(port->vio.lp, len,
				    dr->cookies, &ncookies,
				    (LDC_MAP_SHADOW |
				     LDC_MAP_DIRECT |
				     LDC_MAP_RW));
	if (IS_ERR(dring)) {
		err = PTR_ERR(dring);
		goto err_out;
	}

	dr->base = dring;
	dr->entry_size = (sizeof(struct vio_net_desc) +
			  (sizeof(struct ldc_trans_cookie) * 2));
	dr->num_entries = VNET_TX_RING_SIZE;
	dr->prod = dr->cons = 0;
	dr->pending = VNET_TX_RING_SIZE;
	dr->ncookies = ncookies;

	return 0;

err_out:
	vnet_port_free_tx_bufs(port);

	return err;
}

1049
1050
1051
static LIST_HEAD(vnet_list);
static DEFINE_MUTEX(vnet_list_mutex);

1052
1053
1054
static const struct net_device_ops vnet_ops = {
	.ndo_open		= vnet_open,
	.ndo_stop		= vnet_close,
1055
	.ndo_set_rx_mode	= vnet_set_rx_mode,
1056
	.ndo_set_mac_address	= vnet_set_mac_addr,
1057
	.ndo_validate_addr	= eth_validate_addr,
1058
1059
1060
1061
1062
	.ndo_tx_timeout		= vnet_tx_timeout,
	.ndo_change_mtu		= vnet_change_mtu,
	.ndo_start_xmit		= vnet_start_xmit,
};

1063
static struct vnet *vnet_new(const u64 *local_mac)
1064
1065
1066
1067
1068
1069
{
	struct net_device *dev;
	struct vnet *vp;
	int err, i;

	dev = alloc_etherdev(sizeof(*vp));
1070
	if (!dev)
1071
1072
1073
1074
1075
1076
1077
1078
		return ERR_PTR(-ENOMEM);

	for (i = 0; i < ETH_ALEN; i++)
		dev->dev_addr[i] = (*local_mac >> (5 - i) * 8) & 0xff;

	vp = netdev_priv(dev);

	spin_lock_init(&vp->lock);
1079
	tasklet_init(&vp->vnet_tx_wakeup, maybe_tx_wakeup, (unsigned long)vp);
1080
1081
1082
1083
1084
1085
1086
1087
	vp->dev = dev;

	INIT_LIST_HEAD(&vp->port_list);
	for (i = 0; i < VNET_PORT_HASH_SIZE; i++)
		INIT_HLIST_HEAD(&vp->port_hash[i]);
	INIT_LIST_HEAD(&vp->list);
	vp->local_mac = *local_mac;

1088
	dev->netdev_ops = &vnet_ops;
1089
1090
1091
1092
1093
	dev->ethtool_ops = &vnet_ethtool_ops;
	dev->watchdog_timeo = VNET_TX_TIMEOUT;

	err = register_netdev(dev);
	if (err) {
1094
		pr_err("Cannot register net device, aborting\n");
1095
1096
1097
		goto err_out_free_dev;
	}

1098
	netdev_info(dev, "Sun LDOM vnet %pM\n", dev->dev_addr);
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109

	list_add(&vp->list, &vnet_list);

	return vp;

err_out_free_dev:
	free_netdev(dev);

	return ERR_PTR(err);
}

1110
static struct vnet *vnet_find_or_create(const u64 *local_mac)
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
{
	struct vnet *iter, *vp;

	mutex_lock(&vnet_list_mutex);
	vp = NULL;
	list_for_each_entry(iter, &vnet_list, list) {
		if (iter->local_mac == *local_mac) {
			vp = iter;
			break;
		}
	}
	if (!vp)
		vp = vnet_new(local_mac);
	mutex_unlock(&vnet_list_mutex);

	return vp;
}

1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
static void vnet_cleanup(void)
{
	struct vnet *vp;
	struct net_device *dev;

	mutex_lock(&vnet_list_mutex);
	while (!list_empty(&vnet_list)) {
		vp = list_first_entry(&vnet_list, struct vnet, list);
		list_del(&vp->list);
		dev = vp->dev;
1139
		tasklet_kill(&vp->vnet_tx_wakeup);
1140
1141
1142
1143
1144
1145
1146
1147
		/* vio_unregister_driver() should have cleaned up port_list */
		BUG_ON(!list_empty(&vp->port_list));
		unregister_netdev(dev);
		free_netdev(dev);
	}
	mutex_unlock(&vnet_list_mutex);
}

1148
1149
static const char *local_mac_prop = "local-mac-address";

1150
static struct vnet *vnet_find_parent(struct mdesc_handle *hp,
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
						u64 port_node)
{
	const u64 *local_mac = NULL;
	u64 a;

	mdesc_for_each_arc(a, hp, port_node, MDESC_ARC_TYPE_BACK) {
		u64 target = mdesc_arc_target(hp, a);
		const char *name;

		name = mdesc_get_property(hp, target, "name", NULL);
		if (!name || strcmp(name, "network"))
			continue;

		local_mac = mdesc_get_property(hp, target,
					       local_mac_prop, NULL);
		if (local_mac)
			break;
	}
	if (!local_mac)
		return ERR_PTR(-ENODEV);

	return vnet_find_or_create(local_mac);
}

1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
static struct ldc_channel_config vnet_ldc_cfg = {
	.event		= vnet_event,
	.mtu		= 64,
	.mode		= LDC_MODE_UNRELIABLE,
};

static struct vio_driver_ops vnet_vio_ops = {
	.send_attr		= vnet_send_attr,
	.handle_attr		= vnet_handle_attr,
	.handshake_complete	= vnet_handshake_complete,
};

1187
static void print_version(void)
1188
{
1189
	printk_once(KERN_INFO "%s", version);
1190
1191
}

1192
1193
const char *remote_macaddr_prop = "remote-mac-address";

1194
static int vnet_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
1195
{
1196
	struct mdesc_handle *hp;
1197
1198
1199
1200
1201
1202
	struct vnet_port *port;
	unsigned long flags;
	struct vnet *vp;
	const u64 *rmac;
	int len, i, err, switch_port;

1203
	print_version();
1204

1205
1206
	hp = mdesc_grab();

1207
1208
	vp = vnet_find_parent(hp, vdev->mp);
	if (IS_ERR(vp)) {
1209
		pr_err("Cannot find port parent vnet\n");
1210
1211
1212
1213
		err = PTR_ERR(vp);
		goto err_out_put_mdesc;
	}

1214
1215
	rmac = mdesc_get_property(hp, vdev->mp, remote_macaddr_prop, &len);
	err = -ENODEV;
1216
	if (!rmac) {
1217
		pr_err("Port lacks %s property\n", remote_macaddr_prop);
1218
		goto err_out_put_mdesc;
1219
1220
1221
	}

	port = kzalloc(sizeof(*port), GFP_KERNEL);
1222
	err = -ENOMEM;
1223
	if (!port)
1224
		goto err_out_put_mdesc;
1225
1226
1227
1228
1229
1230

	for (i = 0; i < ETH_ALEN; i++)
		port->raddr[i] = (*rmac >> (5 - i) * 8) & 0xff;

	port->vp = vp;

1231
	err = vio_driver_init(&port->vio, vdev, VDEV_NETWORK,
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
			      vnet_versions, ARRAY_SIZE(vnet_versions),
			      &vnet_vio_ops, vp->dev->name);
	if (err)
		goto err_out_free_port;

	err = vio_ldc_alloc(&port->vio, &vnet_ldc_cfg, port);
	if (err)
		goto err_out_free_port;

	err = vnet_port_alloc_tx_bufs(port);
	if (err)
		goto err_out_free_ldc;

	INIT_HLIST_NODE(&port->hash);
	INIT_LIST_HEAD(&port->list);

	switch_port = 0;
1249
	if (mdesc_get_property(hp, vdev->mp, "switch-port", NULL) != NULL)
1250
		switch_port = 1;
1251
	port->switch_port = switch_port;
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262

	spin_lock_irqsave(&vp->lock, flags);
	if (switch_port)
		list_add(&port->list, &vp->port_list);
	else
		list_add_tail(&port->list, &vp->port_list);
	hlist_add_head(&port->hash, &vp->port_hash[vnet_hashfn(port->raddr)]);
	spin_unlock_irqrestore(&vp->lock, flags);

	dev_set_drvdata(&vdev->dev, port);

1263
1264
	pr_info("%s: PORT ( remote-mac %pM%s )\n",
		vp->dev->name, port->raddr, switch_port ? " switch-port" : "");
1265
1266
1267

	vio_port_up(&port->vio);

1268
1269
	mdesc_release(hp);

1270
1271
1272
1273
1274
1275
1276
1277
	return 0;

err_out_free_ldc:
	vio_ldc_free(&port->vio);

err_out_free_port:
	kfree(port);

1278
1279
err_out_put_mdesc:
	mdesc_release(hp);
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
	return err;
}

static int vnet_port_remove(struct vio_dev *vdev)
{
	struct vnet_port *port = dev_get_drvdata(&vdev->dev);

	if (port) {
		struct vnet *vp = port->vp;
		unsigned long flags;

		del_timer_sync(&port->vio.timer);

		spin_lock_irqsave(&vp->lock, flags);
		list_del(&port->list);
		hlist_del(&port->hash);
		spin_unlock_irqrestore(&vp->lock, flags);

		vnet_port_free_tx_bufs(port);
		vio_ldc_free(&port->vio);

		dev_set_drvdata(&vdev->dev, NULL);

		kfree(port);
1304

1305
1306
1307
1308
	}
	return 0;
}

1309
static const struct vio_device_id vnet_port_match[] = {
1310
1311
1312
1313
1314
	{
		.type = "vnet-port",
	},
	{},
};
1315
MODULE_DEVICE_TABLE(vio, vnet_port_match);
1316
1317
1318
1319
1320

static struct vio_driver vnet_port_driver = {
	.id_table	= vnet_port_match,
	.probe		= vnet_port_probe,
	.remove		= vnet_port_remove,
1321
	.name		= "vnet_port",
1322
1323
1324
1325
};

static int __init vnet_init(void)
{
1326
	return vio_register_driver(&vnet_port_driver);
1327
1328
1329
1330
1331
}

static void __exit vnet_exit(void)
{
	vio_unregister_driver(&vnet_port_driver);
1332
	vnet_cleanup();
1333
1334
1335
1336
}

module_init(vnet_init);
module_exit(vnet_exit);