sunvnet.c 40.5 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
#include <linux/if_vlan.h>
19

20
21
22
23
24
25
26
#if IS_ENABLED(CONFIG_IPV6)
#include <linux/icmpv6.h>
#endif

#include <net/icmp.h>
#include <net/route.h>

27
28
29
30
31
32
33
34
35
#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"

36
static char version[] =
37
38
39
40
41
42
	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);

43
44
#define	VNET_MAX_TXQS		16

45
46
47
48
49
/* Heuristic for the number of times to exponentially backoff and
 * retry sending an LDC trigger when EAGAIN is encountered
 */
#define	VNET_MAX_RETRIES	10

50
51
static int __vnet_tx_trigger(struct vnet_port *port, u32 start);

52
53
/* Ordered from largest major to lowest */
static struct vio_version vnet_versions[] = {
54
	{ .major = 1, .minor = 6 },
55
56
57
58
59
60
61
62
63
64
65
66
	{ .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;

67
	pr_err("Received unknown msg [%02x:%02x:%04x:%08x]\n",
68
	       pkt->type, pkt->stype, pkt->stype_env, pkt->sid);
69
	pr_err("Resetting connection\n");
70
71
72
73
74
75
76
77
78
79
80

	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;
81
	int framelen = ETH_FRAME_LEN;
82
83
84
85
86
87
88
	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);
89
90
91
92
	if (vio_version_before(vio, 1, 2))
		pkt.xfer_mode = VIO_DRING_MODE;
	else
		pkt.xfer_mode = VIO_NEW_DRING_MODE;
93
94
95
96
	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);
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
	if (vio_version_after(vio, 1, 3)) {
		if (port->rmtu) {
			port->rmtu = min(VNET_MAXPACKET, port->rmtu);
			pkt.mtu = port->rmtu;
		} else {
			port->rmtu = VNET_MAXPACKET;
			pkt.mtu = port->rmtu;
		}
		if (vio_version_after_eq(vio, 1, 6))
			pkt.options = VIO_TX_DRING;
	} else if (vio_version_before(vio, 1, 3)) {
		pkt.mtu = framelen;
	} else { /* v1.3 */
		pkt.mtu = framelen + VLAN_HLEN;
	}

	pkt.plnk_updt = PHYSLINK_UPDATE_NONE;
	pkt.cflags = 0;
115
116

	viodbg(HS, "SEND NET ATTR xmode[0x%x] atype[0x%x] addr[%llx] "
117
118
	       "ackfreq[%u] plnk_updt[0x%02x] opts[0x%02x] mtu[%llu] "
	       "cflags[0x%04x] lso_max[%u]\n",
119
	       pkt.xfer_mode, pkt.addr_type,
120
121
122
123
	       (unsigned long long)pkt.addr,
	       pkt.ack_freq, pkt.plnk_updt, pkt.options,
	       (unsigned long long)pkt.mtu, pkt.cflags, pkt.ipv4_lso_maxlen);

124
125
126
127
128
129
130

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

static int handle_attr_info(struct vio_driver_state *vio,
			    struct vio_net_attr_info *pkt)
{
131
132
133
134
135
136
137
	struct vnet_port *port = to_vnet_port(vio);
	u64	localmtu;
	u8	xfer_mode;

	viodbg(HS, "GOT NET ATTR xmode[0x%x] atype[0x%x] addr[%llx] "
	       "ackfreq[%u] plnk_updt[0x%02x] opts[0x%02x] mtu[%llu] "
	       " (rmtu[%llu]) cflags[0x%04x] lso_max[%u]\n",
138
	       pkt->xfer_mode, pkt->addr_type,
139
140
141
142
	       (unsigned long long)pkt->addr,
	       pkt->ack_freq, pkt->plnk_updt, pkt->options,
	       (unsigned long long)pkt->mtu, port->rmtu, pkt->cflags,
	       pkt->ipv4_lso_maxlen);
143
144
145

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

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
	xfer_mode = pkt->xfer_mode;
	/* for version < 1.2, VIO_DRING_MODE = 0x3 and no bitmask */
	if (vio_version_before(vio, 1, 2) && xfer_mode == VIO_DRING_MODE)
		xfer_mode = VIO_NEW_DRING_MODE;

	/* MTU negotiation:
	 *	< v1.3 - ETH_FRAME_LEN exactly
	 *	> v1.3 - MIN(pkt.mtu, VNET_MAXPACKET, port->rmtu) and change
	 *			pkt->mtu for ACK
	 *	= v1.3 - ETH_FRAME_LEN + VLAN_HLEN exactly
	 */
	if (vio_version_before(vio, 1, 3)) {
		localmtu = ETH_FRAME_LEN;
	} else if (vio_version_after(vio, 1, 3)) {
		localmtu = port->rmtu ? port->rmtu : VNET_MAXPACKET;
		localmtu = min(pkt->mtu, localmtu);
		pkt->mtu = localmtu;
	} else { /* v1.3 */
		localmtu = ETH_FRAME_LEN + VLAN_HLEN;
	}
	port->rmtu = localmtu;

	/* for version >= 1.6, ACK packet mode we support */
	if (vio_version_after_eq(vio, 1, 6)) {
		pkt->xfer_mode = VIO_NEW_DRING_MODE;
		pkt->options = VIO_TX_DRING;
	}

	if (!(xfer_mode | VIO_NEW_DRING_MODE) ||
175
	    pkt->addr_type != VNET_ADDR_ETHERMAC ||
176
	    pkt->mtu != localmtu) {
177
178
179
180
181
182
183
184
		viodbg(HS, "SEND NET ATTR NACK\n");

		pkt->tag.stype = VIO_SUBTYPE_NACK;

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

		return -ECONNRESET;
	} else {
185
186
187
188
189
190
191
192
		viodbg(HS, "SEND NET ATTR ACK xmode[0x%x] atype[0x%x] "
		       "addr[%llx] ackfreq[%u] plnk_updt[0x%02x] opts[0x%02x] "
		       "mtu[%llu] (rmtu[%llu]) cflags[0x%04x] lso_max[%u]\n",
		       pkt->xfer_mode, pkt->addr_type,
		       (unsigned long long)pkt->addr,
		       pkt->ack_freq, pkt->plnk_updt, pkt->options,
		       (unsigned long long)pkt->mtu, port->rmtu, pkt->cflags,
		       pkt->ipv4_lso_maxlen);
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

		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;
288
	if (unlikely(len < ETH_ZLEN || len > port->rmtu)) {
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
		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;
Sowmini Varadhan's avatar
Sowmini Varadhan committed
316
	napi_gro_receive(&port->napi, skb);
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
	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;
343
	int retries = 0;
344
345
346
347
348
349
350
351
352
353
354
355

	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;
356
357
358
359
360
		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]);
361
			break;
362
		}
363
364
	} while (err == -EAGAIN);

365
366
367
368
369
370
371
372
	if (err <= 0 && vio_dring_state == VIO_DRING_STOPPED) {
		port->stop_rx_idx = end;
		port->stop_rx = true;
	} else {
		port->stop_rx_idx = 0;
		port->stop_rx = false;
	}

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
	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;

Sowmini Varadhan's avatar
Sowmini Varadhan committed
433
	BUG_ON(desc == NULL);
434
435
436
	if (IS_ERR(desc))
		return PTR_ERR(desc);

437
438
439
440
441
	if (desc->hdr.state != VIO_DESC_READY)
		return 1;

	rmb();

442
	viodbg(DATA, "vio_walk_rx_one desc[%02x:%02x:%08x:%08x:%llx:%llx]\n",
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
	       desc->hdr.state, desc->hdr.ack,
	       desc->size, desc->ncookies,
	       desc->cookies[0].cookie_addr,
	       desc->cookies[0].cookie_size);

	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,
Sowmini Varadhan's avatar
Sowmini Varadhan committed
460
			u32 start, u32 end, int *npkts, int budget)
461
462
463
{
	struct vio_driver_state *vio = &port->vio;
	int ack_start = -1, ack_end = -1;
Sowmini Varadhan's avatar
Sowmini Varadhan committed
464
	bool send_ack = true;
465
466
467
468
469
470
471
472
473
474
475

	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;
Sowmini Varadhan's avatar
Sowmini Varadhan committed
476
		(*npkts)++;
477
478
479
480
481
482
483
484
485
486
487
		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;
		}
Sowmini Varadhan's avatar
Sowmini Varadhan committed
488
489
490
491
		if ((*npkts) >= budget) {
			send_ack = false;
			break;
		}
492
493
494
	}
	if (unlikely(ack_start == -1))
		ack_start = ack_end = prev_idx(start, dr);
Sowmini Varadhan's avatar
Sowmini Varadhan committed
495
496
497
498
499
500
501
502
503
	if (send_ack) {
		port->napi_resume = false;
		return vnet_send_ack(port, dr, ack_start, ack_end,
				     VIO_DRING_STOPPED);
	} else  {
		port->napi_resume = true;
		port->napi_stop_idx = ack_end;
		return 1;
	}
504
505
}

Sowmini Varadhan's avatar
Sowmini Varadhan committed
506
507
static int vnet_rx(struct vnet_port *port, void *msgbuf, int *npkts,
		   int budget)
508
509
510
511
512
{
	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;

513
	viodbg(DATA, "vnet_rx stype_env[%04x] seq[%016llx] rcv_nxt[%016llx]\n",
514
515
516
517
518
	       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)) {
519
520
		pr_err("RX out of sequence seq[0x%llx] rcv_nxt[0x%llx]\n",
		       pkt->seq, dr->rcv_nxt);
521
522
523
		return 0;
	}

Sowmini Varadhan's avatar
Sowmini Varadhan committed
524
525
	if (!port->napi_resume)
		dr->rcv_nxt++;
526
527
528

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

Sowmini Varadhan's avatar
Sowmini Varadhan committed
529
530
	return vnet_walk_rx(port, dr, pkt->start_idx, pkt->end_idx,
			    npkts, budget);
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
}

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;
555
	struct vio_net_desc *desc;
556
557
	struct netdev_queue *txq;

558
559
560
561
	if (unlikely(pkt->tag.stype_env != VIO_DRING_DATA))
		return 0;

	end = pkt->end_idx;
Sowmini Varadhan's avatar
Sowmini Varadhan committed
562
563
	vp = port->vp;
	dev = vp->dev;
564
565
566
567
568
569
	netif_tx_lock(dev);
	if (unlikely(!idx_is_pending(dr, end))) {
		netif_tx_unlock(dev);
		return 0;
	}

570
571
572
	/* sync for race conditions with vnet_start_xmit() and tell xmit it
	 * is time to send a trigger.
	 */
573
	dr->cons = next_idx(end, dr);
574
	desc = vio_dring_entry(dr, dr->cons);
575
	if (desc->hdr.state == VIO_DESC_READY && !port->start_cons) {
576
577
578
579
580
581
582
583
584
585
586
		/* vnet_start_xmit() just populated this dring but missed
		 * sending the "start" LDC message to the consumer.
		 * Send a "start" trigger on its behalf.
		 */
		if (__vnet_tx_trigger(port, dr->cons) > 0)
			port->start_cons = false;
		else
			port->start_cons = true;
	} else {
		port->start_cons = true;
	}
Sowmini Varadhan's avatar
Sowmini Varadhan committed
587
	netif_tx_unlock(dev);
588

589
590
	txq = netdev_get_tx_queue(dev, port->q_index);
	if (unlikely(netif_tx_queue_stopped(txq) &&
591
592
593
594
595
596
597
598
599
600
601
602
		     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;
}

603
604
605
606
607
static int handle_mcast(struct vnet_port *port, void *msgbuf)
{
	struct vio_net_mcast_info *pkt = msgbuf;

	if (pkt->tag.stype != VIO_SUBTYPE_ACK)
608
		pr_err("%s: Got unexpected MCAST reply [%02x:%02x:%04x:%08x]\n",
609
610
611
612
613
614
615
616
617
		       port->vp->dev->name,
		       pkt->tag.type,
		       pkt->tag.stype,
		       pkt->tag.stype_env,
		       pkt->tag.sid);

	return 0;
}

618
619
620
621
622
/* Got back a STOPPED LDC message on port. If the queue is stopped,
 * wake it up so that we'll send out another START message at the
 * next TX.
 */
static void maybe_tx_wakeup(struct vnet_port *port)
623
{
624
	struct netdev_queue *txq;
625

626
627
628
629
630
631
	txq = netdev_get_tx_queue(port->vp->dev, port->q_index);
	__netif_tx_lock(txq, smp_processor_id());
	if (likely(netif_tx_queue_stopped(txq))) {
		struct vio_dring_state *dr;

		dr = &port->vio.drings[VIO_DRIVER_TX_RING];
632
		netif_tx_wake_queue(txq);
633
	}
634
	__netif_tx_unlock(txq);
635
636
}

Sowmini Varadhan's avatar
Sowmini Varadhan committed
637
638
639
640
641
642
643
644
static inline bool port_is_up(struct vnet_port *vnet)
{
	struct vio_driver_state *vio = &vnet->vio;

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

static int vnet_event_napi(struct vnet_port *port, int budget)
645
646
647
{
	struct vio_driver_state *vio = &port->vio;
	int tx_wakeup, err;
Sowmini Varadhan's avatar
Sowmini Varadhan committed
648
649
	int npkts = 0;
	int event = (port->rx_event & LDC_EVENT_RESET);
650

Sowmini Varadhan's avatar
Sowmini Varadhan committed
651
ldc_ctrl:
652
653
654
655
	if (unlikely(event == LDC_EVENT_RESET ||
		     event == LDC_EVENT_UP)) {
		vio_link_state_change(vio, event);

656
657
		if (event == LDC_EVENT_RESET) {
			port->rmtu = 0;
658
			vio_port_up(vio);
659
		}
Sowmini Varadhan's avatar
Sowmini Varadhan committed
660
661
		port->rx_event = 0;
		return 0;
662
	}
Sowmini Varadhan's avatar
Sowmini Varadhan committed
663
664
665
666
667
668
669
670
	/* We may have multiple LDC events in rx_event. Unroll send_events() */
	event = (port->rx_event & LDC_EVENT_UP);
	port->rx_event &= ~(LDC_EVENT_RESET|LDC_EVENT_UP);
	if (event == LDC_EVENT_UP)
		goto ldc_ctrl;
	event = port->rx_event;
	if (!(event & LDC_EVENT_DATA_READY))
		return 0;
671

Sowmini Varadhan's avatar
Sowmini Varadhan committed
672
673
	/* we dont expect any other bits than RESET, UP, DATA_READY */
	BUG_ON(event != LDC_EVENT_DATA_READY);
674
675
676
677
678
679
680
681

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

Sowmini Varadhan's avatar
Sowmini Varadhan committed
682
683
684
685
686
687
688
689
690
691
692
693
694
695
		if (port->napi_resume) {
			struct vio_dring_data *pkt =
				(struct vio_dring_data *)&msgbuf;
			struct vio_dring_state *dr =
				&port->vio.drings[VIO_DRIVER_RX_RING];

			pkt->tag.type = VIO_TYPE_DATA;
			pkt->tag.stype = VIO_SUBTYPE_INFO;
			pkt->tag.stype_env = VIO_DRING_DATA;
			pkt->seq = dr->rcv_nxt;
			pkt->start_idx = next_idx(port->napi_stop_idx, dr);
			pkt->end_idx = -1;
			goto napi_resume;
		}
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
		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;
Sowmini Varadhan's avatar
Sowmini Varadhan committed
712
napi_resume:
713
714
		if (likely(msgbuf.tag.type == VIO_TYPE_DATA)) {
			if (msgbuf.tag.stype == VIO_SUBTYPE_INFO) {
Sowmini Varadhan's avatar
Sowmini Varadhan committed
715
716
717
718
719
720
721
722
723
724
725
				if (!port_is_up(port)) {
					/* failures like handshake_failure()
					 * may have cleaned up dring, but
					 * NAPI polling may bring us here.
					 */
					err = -ECONNRESET;
					break;
				}
				err = vnet_rx(port, &msgbuf, &npkts, budget);
				if (npkts >= budget)
					break;
726
727
				if (npkts == 0)
					break;
728
729
730
731
732
733
734
735
			} 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) {
736
737
738
739
			if (msgbuf.tag.stype_env == VNET_MCAST_INFO)
				err = handle_mcast(port, &msgbuf);
			else
				err = vio_control_pkt_engine(vio, &msgbuf);
740
741
742
743
744
745
746
747
748
			if (err)
				break;
		} else {
			err = vnet_handle_unknown(port, &msgbuf);
		}
		if (err == -ECONNRESET)
			break;
	}
	if (unlikely(tx_wakeup && err != -ECONNRESET))
749
		maybe_tx_wakeup(port);
Sowmini Varadhan's avatar
Sowmini Varadhan committed
750
751
752
753
754
755
756
757
758
759
760
	return npkts;
}

static int vnet_poll(struct napi_struct *napi, int budget)
{
	struct vnet_port *port = container_of(napi, struct vnet_port, napi);
	struct vio_driver_state *vio = &port->vio;
	int processed = vnet_event_napi(port, budget);

	if (processed < budget) {
		napi_complete(napi);
761
		port->rx_event &= ~LDC_EVENT_DATA_READY;
Sowmini Varadhan's avatar
Sowmini Varadhan committed
762
763
764
765
766
767
768
769
770
771
772
773
774
		vio_set_intr(vio->vdev->rx_ino, HV_INTR_ENABLED);
	}
	return processed;
}

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

	port->rx_event |= event;
	vio_set_intr(vio->vdev->rx_ino, HV_INTR_DISABLED);
	napi_schedule(&port->napi);
775

776
777
}

778
static int __vnet_tx_trigger(struct vnet_port *port, u32 start)
779
780
781
782
783
784
785
786
787
788
{
	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,
789
		.start_idx		= start,
790
791
792
		.end_idx		= (u32) -1,
	};
	int err, delay;
793
	int retries = 0;
794

795
796
797
798
799
800
801
802
803
	if (port->stop_rx) {
		err = vnet_send_ack(port,
				    &port->vio.drings[VIO_DRIVER_RX_RING],
				    port->stop_rx_idx, -1,
				    VIO_DRING_STOPPED);
		if (err <= 0)
			return err;
	}

804
805
806
807
808
809
810
811
812
813
814
	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;
815
816
		if (retries++ > VNET_MAX_RETRIES)
			break;
817
818
819
820
821
822
823
824
825
826
827
	} while (err == -EAGAIN);

	return err;
}

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;

828
	hlist_for_each_entry_rcu(port, hp, hash) {
829
830
		if (!port_is_up(port))
			continue;
831
		if (ether_addr_equal(port->raddr, skb->data))
832
833
			return port;
	}
834
	list_for_each_entry_rcu(port, &vp->port_list, list) {
835
836
837
838
839
840
841
		if (!port->switch_port)
			continue;
		if (!port_is_up(port))
			continue;
		return port;
	}
	return NULL;
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
static struct sk_buff *vnet_clean_tx_ring(struct vnet_port *port,
					  unsigned *pending)
{
	struct vio_dring_state *dr = &port->vio.drings[VIO_DRIVER_TX_RING];
	struct sk_buff *skb = NULL;
	int i, txi;

	*pending = 0;

	txi = dr->prod-1;
	if (txi < 0)
		txi = VNET_TX_RING_SIZE-1;

	for (i = 0; i < VNET_TX_RING_SIZE; ++i) {
		struct vio_net_desc *d;

		d = vio_dring_entry(dr, txi);

		if (d->hdr.state == VIO_DESC_DONE) {
			if (port->tx_bufs[txi].skb) {
				BUG_ON(port->tx_bufs[txi].skb->next);

				port->tx_bufs[txi].skb->next = skb;
				skb = port->tx_bufs[txi].skb;
				port->tx_bufs[txi].skb = NULL;

				ldc_unmap(port->vio.lp,
					  port->tx_bufs[txi].cookies,
					  port->tx_bufs[txi].ncookies);
			}
			d->hdr.state = VIO_DESC_FREE;
		} else if (d->hdr.state == VIO_DESC_READY) {
			(*pending)++;
		} else if (d->hdr.state == VIO_DESC_FREE) {
			break;
		}
		--txi;
		if (txi < 0)
			txi = VNET_TX_RING_SIZE-1;
	}
	return skb;
}

static inline void vnet_free_skbs(struct sk_buff *skb)
{
	struct sk_buff *next;

	while (skb) {
		next = skb->next;
		skb->next = NULL;
		dev_kfree_skb(skb);
		skb = next;
	}
}

static void vnet_clean_timer_expire(unsigned long port0)
{
	struct vnet_port *port = (struct vnet_port *)port0;
	struct sk_buff *freeskbs;
	unsigned pending;

905
	netif_tx_lock(port->vp->dev);
906
	freeskbs = vnet_clean_tx_ring(port, &pending);
907
	netif_tx_unlock(port->vp->dev);
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

	vnet_free_skbs(freeskbs);

	if (pending)
		(void)mod_timer(&port->clean_timer,
				jiffies + VNET_CLEAN_TIMEOUT);
	 else
		del_timer(&port->clean_timer);
}

static inline struct sk_buff *vnet_skb_shape(struct sk_buff *skb, void **pstart,
					     int *plen)
{
	struct sk_buff *nskb;
	int len, pad;

	len = skb->len;
	pad = 0;
	if (len < ETH_ZLEN) {
		pad += ETH_ZLEN - skb->len;
		len += pad;
	}
	len += VNET_PACKET_SKIP;
	pad += 8 - (len & 7);
	len += 8 - (len & 7);

	if (((unsigned long)skb->data & 7) != VNET_PACKET_SKIP ||
	    skb_tailroom(skb) < pad ||
	    skb_headroom(skb) < VNET_PACKET_SKIP) {
		nskb = alloc_and_align_skb(skb->dev, skb->len);
		skb_reserve(nskb, VNET_PACKET_SKIP);
		if (skb_copy_bits(skb, 0, nskb->data, skb->len)) {
			dev_kfree_skb(nskb);
			dev_kfree_skb(skb);
			return NULL;
		}
		(void)skb_put(nskb, skb->len);
		dev_kfree_skb(skb);
		skb = nskb;
	}

	*pstart = skb->data - VNET_PACKET_SKIP;
	*plen = len;
	return skb;
}

954
955
956
957
958
959
960
961
962
963
static u16
vnet_select_queue(struct net_device *dev, struct sk_buff *skb,
		  void *accel_priv, select_queue_fallback_t fallback)
{
	struct vnet *vp = netdev_priv(dev);
	struct vnet_port *port = __tx_port_find(vp, skb);

	return port->q_index;
}

964
965
966
static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct vnet *vp = netdev_priv(dev);
967
	struct vnet_port *port = NULL;
968
969
970
	struct vio_dring_state *dr;
	struct vio_net_desc *d;
	unsigned int len;
971
972
973
974
975
	struct sk_buff *freeskbs = NULL;
	int i, err, txi;
	void *start = NULL;
	int nlen = 0;
	unsigned pending = 0;
976
	struct netdev_queue *txq;
977

978
979
980
981
	skb = vnet_skb_shape(skb, &start, &nlen);
	if (unlikely(!skb))
		goto out_dropped;

982
	rcu_read_lock();
983
	port = __tx_port_find(vp, skb);
984
985
	if (unlikely(!port)) {
		rcu_read_unlock();
986
		goto out_dropped;
987
	}
988

989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
	if (skb->len > port->rmtu) {
		unsigned long localmtu = port->rmtu - ETH_HLEN;

		if (vio_version_after_eq(&port->vio, 1, 3))
			localmtu -= VLAN_HLEN;

		if (skb->protocol == htons(ETH_P_IP)) {
			struct flowi4 fl4;
			struct rtable *rt = NULL;

			memset(&fl4, 0, sizeof(fl4));
			fl4.flowi4_oif = dev->ifindex;
			fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
			fl4.daddr = ip_hdr(skb)->daddr;
			fl4.saddr = ip_hdr(skb)->saddr;

			rt = ip_route_output_key(dev_net(dev), &fl4);
1006
			rcu_read_unlock();
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
			if (!IS_ERR(rt)) {
				skb_dst_set(skb, &rt->dst);
				icmp_send(skb, ICMP_DEST_UNREACH,
					  ICMP_FRAG_NEEDED,
					  htonl(localmtu));
			}
		}
#if IS_ENABLED(CONFIG_IPV6)
		else if (skb->protocol == htons(ETH_P_IPV6))
			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, localmtu);
#endif
1018
		goto out_dropped;
1019
	}
1020

1021
	dr = &port->vio.drings[VIO_DRIVER_TX_RING];
1022
1023
	i = skb_get_queue_mapping(skb);
	txq = netdev_get_tx_queue(dev, i);
1024
	if (unlikely(vnet_tx_dring_avail(dr) < 1)) {
1025
1026
		if (!netif_tx_queue_stopped(txq)) {
			netif_tx_stop_queue(txq);
1027
1028

			/* This is a hard error, log it. */
1029
			netdev_err(dev, "BUG! Tx Ring full when queue awake!\n");
1030
1031
			dev->stats.tx_errors++;
		}
1032
		rcu_read_unlock();
1033
1034
1035
1036
1037
		return NETDEV_TX_BUSY;
	}

	d = vio_dring_cur(dr);

1038
1039
1040
1041
1042
	txi = dr->prod;

	freeskbs = vnet_clean_tx_ring(port, &pending);

	BUG_ON(port->tx_bufs[txi].skb);
1043
1044

	len = skb->len;
1045
	if (len < ETH_ZLEN)
1046
		len = ETH_ZLEN;
1047
1048
1049
1050
1051

	port->tx_bufs[txi].skb = skb;
	skb = NULL;

	err = ldc_map_single(port->vio.lp, start, nlen,
1052
			     port->tx_bufs[txi].cookies, VNET_MAXCOOKIES,
1053
1054
1055
			     (LDC_MAP_SHADOW | LDC_MAP_DIRECT | LDC_MAP_RW));
	if (err < 0) {
		netdev_info(dev, "tx buffer map error %d\n", err);
1056
		goto out_dropped;
1057
	}
1058
	port->tx_bufs[txi].ncookies = err;
1059

1060
1061
1062
1063
1064
1065
1066
1067
1068
	/* 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;
1069
	d->size = len;
1070
	d->ncookies = port->tx_bufs[txi].ncookies;
1071
	for (i = 0; i < d->ncookies; i++)
1072
		d->cookies[i] = port->tx_bufs[txi].cookies[i];
1073
1074
1075
1076
1077
1078
1079
1080

	/* 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;

1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
	/* Exactly one ldc "start" trigger (for dr->cons) needs to be sent
	 * to notify the consumer that some descriptors are READY.
	 * After that "start" trigger, no additional triggers are needed until
	 * a DRING_STOPPED is received from the consumer. The dr->cons field
	 * (set up by vnet_ack()) has the value of the next dring index
	 * that has not yet been ack-ed. We send a "start" trigger here
	 * if, and only if, start_cons is true (reset it afterward). Conversely,
	 * vnet_ack() should check if the dring corresponding to cons
	 * is marked READY, but start_cons was false.
	 * If so, vnet_ack() should send out the missed "start" trigger.
	 *
	 * Note that the wmb() above makes sure the cookies et al. are
	 * not globally visible before the VIO_DESC_READY, and that the
	 * stores are ordered correctly by the compiler. The consumer will
	 * not proceed until the VIO_DESC_READY is visible assuring that
	 * the consumer does not observe anything related to descriptors
	 * out of order. The HV trap from the LDC start trigger is the
	 * producer to consumer announcement that work is available to the
	 * consumer
	 */
	if (!port->start_cons)
		goto ldc_start_done; /* previous trigger suffices */

	err = __vnet_tx_trigger(port, dr->cons);
1105
	if (unlikely(err < 0)) {
1106
		netdev_info(dev, "TX trigger error %d\n", err);
1107
1108
		d->hdr.state = VIO_DESC_FREE;
		dev->stats.tx_carrier_errors++;
1109
		goto out_dropped;
1110
1111
	}

1112
1113
1114
ldc_start_done:
	port->start_cons = false;

1115
	dev->stats.tx_packets++;
1116
	dev->stats.tx_bytes += port->tx_bufs[txi].skb->len;
1117
1118

	dr->prod = (dr->prod + 1) & (VNET_TX_RING_SIZE - 1);
1119
	if (unlikely(vnet_tx_dring_avail(dr) < 1)) {
1120
		netif_tx_stop_queue(txq);
1121
		if (vnet_tx_dring_avail(dr) > VNET_TX_WAKEUP_THRESH(dr))
1122
			netif_tx_wake_queue(txq);
1123
1124
	}

1125
1126
	(void)mod_timer(&port->clean_timer, jiffies + VNET_CLEAN_TIMEOUT);
	rcu_read_unlock();
1127

1128
1129
	vnet_free_skbs(freeskbs);

1130
1131
1132
	return NETDEV_TX_OK;

out_dropped:
1133
1134
1135
	if (pending)
		(void)mod_timer(&port->clean_timer,
				jiffies + VNET_CLEAN_TIMEOUT);
1136
	else if (port)
1137
		del_timer(&port->clean_timer);
1138
1139
1140
1141
1142
	if (port)
		rcu_read_unlock();
	if (skb)
		dev_kfree_skb(skb);
	vnet_free_skbs(freeskbs);
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
	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);
1155
	netif_tx_start_all_queues(dev);
1156
1157
1158
1159
1160
1161

	return 0;
}

static int vnet_close(struct net_device *dev)
{
1162
	netif_tx_stop_all_queues(dev);
1163
1164
1165
1166
1167
	netif_carrier_off(dev);

	return 0;
}

1168
1169
1170
1171
1172
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) {
1173
		if (ether_addr_equal(m->addr, addr))
1174
1175
1176
1177
1178
1179
1180
			return m;
	}
	return NULL;
}

static void __update_mc_list(struct vnet *vp, struct net_device *dev)
{
1181
	struct netdev_hw_addr *ha;
1182

1183
	netdev_for_each_mc_addr(ha, dev) {
1184
1185
		struct vnet_mcast_entry *m;

1186
		m = __vnet_mc_find(vp, ha->addr);
1187
1188
1189
1190
1191
1192
1193
1194
1195
		if (m) {
			m->hit = 1;
			continue;
		}

		if (!m) {
			m = kzalloc(sizeof(*m), GFP_ATOMIC);
			if (!m)
				continue;
1196
			memcpy(m->addr, ha->addr, ETH_ALEN);
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
			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));
	}
}

1268
1269
static void vnet_set_rx_mode(struct net_device *dev)
{
1270
1271
1272
	struct vnet *vp = netdev_priv(dev);
	struct vnet_port *port;

1273
1274
	rcu_read_lock();
	list_for_each_entry_rcu(port, &vp->port_list, list) {
1275
1276
1277
1278

		if (port->switch_port) {
			__update_mc_list(vp, dev);
			__send_mc_list(vp, port);
1279
			break;
1280
1281
		}
	}
1282
	rcu_read_unlock();
1283
1284
1285
1286
}

static int vnet_change_mtu(struct net_device *dev, int new_mtu)
{
1287
	if (new_mtu < 68 || new_mtu > 65535)
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
		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)
{
1302
1303
	strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver));
	strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version));
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
}

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++) {
1343
1344
		struct vio_net_desc *d;
		void *skb = port->tx_bufs[i].skb;
1345

1346
		if (!skb)
1347
1348
			continue;

1349
1350
1351
1352
		d = vio_dring_entry(dr, i);
		if (d->hdr.state == VIO_DESC_READY)
			pr_warn("active transmit buffers freed\n");

1353
1354
1355
		ldc_unmap(port->vio.lp,
			  port->tx_bufs[i].cookies,
			  port->tx_bufs[i].ncookies);
1356
1357
1358
		dev_kfree_skb(skb);
		port->tx_bufs[i].skb = NULL;
		d->hdr.state = VIO_DESC_FREE;
1359
1360
1361
	}
}

1362
static int vnet_port_alloc_tx_bufs(struct vnet_port *port)
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
{
	struct vio_dring_state *dr;
	unsigned long len;
	int i, err, ncookies;
	void *dring;

	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;
1391
	port->start_cons  = true; /* need an initial trigger */
1392
1393
1394
	dr->pending = VNET_TX_RING_SIZE;
	dr->ncookies = ncookies;

1395
1396
1397
1398
1399
1400
	for (i = 0; i < VNET_TX_RING_SIZE; ++i) {
		struct vio_net_desc *d;

		d = vio_dring_entry(dr, i);
		d->hdr.state = VIO_DESC_FREE;
	}
1401
1402
1403
1404
1405
1406
1407
1408
	return 0;

err_out:
	vnet_port_free_tx_bufs(port);

	return err;
}

Sowmini Varadhan's avatar
Sowmini Varadhan committed
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
#ifdef CONFIG_NET_POLL_CONTROLLER
static void vnet_poll_controller(struct net_device *dev)
{
	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);
		napi_schedule(&port->napi);
	}
	spin_unlock_irqrestore(&vp->lock, flags);
}
#endif
1424
1425
1426
static LIST_HEAD(vnet_list);
static DEFINE_MUTEX(vnet_list_mutex);

1427
1428
1429
static const struct net_device_ops vnet_ops = {
	.ndo_open		= vnet_open,
	.ndo_stop		= vnet_close,
1430
	.ndo_set_rx_mode	= vnet_set_rx_mode,
1431
	.ndo_set_mac_address	= vnet_set_mac_addr,
1432
	.ndo_validate_addr	= eth_validate_addr,
1433
1434
1435
	.ndo_tx_timeout		= vnet_tx_timeout,
	.ndo_change_mtu		= vnet_change_mtu,
	.ndo_start_xmit		= vnet_start_xmit,
1436
	.ndo_select_queue	= vnet_select_queue,
Sowmini Varadhan's avatar
Sowmini Varadhan committed
1437
1438
1439
#ifdef CONFIG_NET_POLL_CONTROLLER
	.ndo_poll_controller	= vnet_poll_controller,
#endif
1440
1441
};

1442
static struct vnet *vnet_new(const u64 *local_mac)
1443
1444
1445
1446
1447
{
	struct net_device *dev;
	struct vnet *vp;
	int err, i;

1448
	dev = alloc_etherdev_mqs(sizeof(*vp), VNET_MAX_TXQS, 1);
1449
	if (!dev)
1450
		return ERR_PTR(-ENOMEM);
1451
1452
	dev->needed_headroom = VNET_PACKET_SKIP + 8;
	dev->needed_tailroom = 8;
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467

	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);
	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;

1468
	dev->netdev_ops = &vnet_ops;
1469
1470
1471
1472
1473
	dev->ethtool_ops = &vnet_ethtool_ops;
	dev->watchdog_timeo = VNET_TX_TIMEOUT;

	err = register_netdev(dev);
	if (err) {
1474
		pr_err("Cannot register net device, aborting\n");
1475
1476
1477
		goto err_out_free_dev;
	}

1478
	netdev_info(dev, "Sun LDOM vnet %pM\n", dev->dev_addr);
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489

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

	return vp;

err_out_free_dev:
	free_netdev(dev);

	return ERR_PTR(err);
}

1490
static struct vnet *vnet_find_or_create(const u64 *local_mac)
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
{
	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;
}

1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
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;
		/* 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);
}

1527
1528
static const char *local_mac_prop = "local-mac-address";

1529
static struct vnet *vnet_find_parent(struct mdesc_handle *hp,
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
						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);
}

1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
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,
};