summaryrefslogtreecommitdiffstats
path: root/drivers/net/caif/caif_virtio.c
blob: 7fea00c7ca8a6ae57feeeb150281fbaec3761445 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) ST-Ericsson AB 2013
 * Authors: Vicram Arv
 *	    Dmitry Tarnyagin <dmitry.tarnyagin@lockless.no>
 *	    Sjur Brendeland
 */
#include <linux/module.h>
#include <linux/if_arp.h>
#include <linux/virtio.h>
#include <linux/vringh.h>
#include <linux/debugfs.h>
#include <linux/spinlock.h>
#include <linux/genalloc.h>
#include <linux/interrupt.h>
#include <linux/netdevice.h>
#include <linux/rtnetlink.h>
#include <linux/virtio_ids.h>
#include <linux/virtio_caif.h>
#include <linux/virtio_ring.h>
#include <linux/dma-mapping.h>
#include <net/caif/caif_dev.h>
#include <linux/virtio_config.h>

MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Vicram Arv");
MODULE_AUTHOR("Sjur Brendeland");
MODULE_DESCRIPTION("Virtio CAIF Driver");

/* NAPI schedule quota */
#define CFV_DEFAULT_QUOTA 32

/* Defaults used if virtio config space is unavailable */
#define CFV_DEF_MTU_SIZE 4096
#define CFV_DEF_HEADROOM 32
#define CFV_DEF_TAILROOM 32

/* Required IP header alignment */
#define IP_HDR_ALIGN 4

/* struct cfv_napi_contxt - NAPI context info
 * @riov: IOV holding data read from the ring. Note that riov may
 *	  still hold data when cfv_rx_poll() returns.
 * @head: Last descriptor ID we received from vringh_getdesc_kern.
 *	  We use this to put descriptor back on the used ring. USHRT_MAX is
 *	  used to indicate invalid head-id.
 */
struct cfv_napi_context {
	struct vringh_kiov riov;
	unsigned short head;
};

/* struct cfv_stats - statistics for debugfs
 * @rx_napi_complete:	Number of NAPI completions (RX)
 * @rx_napi_resched:	Number of calls where the full quota was used (RX)
 * @rx_nomem:		Number of SKB alloc failures (RX)
 * @rx_kicks:		Number of RX kicks
 * @tx_full_ring:	Number times TX ring was full
 * @tx_no_mem:		Number of times TX went out of memory
 * @tx_flow_on:		Number of flow on (TX)
 * @tx_kicks:		Number of TX kicks
 */
struct cfv_stats {
	u32 rx_napi_complete;
	u32 rx_napi_resched;
	u32 rx_nomem;
	u32 rx_kicks;
	u32 tx_full_ring;
	u32 tx_no_mem;
	u32 tx_flow_on;
	u32 tx_kicks;
};

/* struct cfv_info - Caif Virtio control structure
 * @cfdev:	caif common header
 * @vdev:	Associated virtio device
 * @vr_rx:	rx/downlink host vring
 * @vq_tx:	tx/uplink virtqueue
 * @ndev:	CAIF link layer device
 * @watermark_tx: indicates number of free descriptors we need
 *		to reopen the tx-queues after overload.
 * @tx_lock:	protects vq_tx from concurrent use
 * @tx_release_tasklet: Tasklet for freeing consumed TX buffers
 * @napi:       Napi context used in cfv_rx_poll()
 * @ctx:        Context data used in cfv_rx_poll()
 * @tx_hr:	transmit headroom
 * @rx_hr:	receive headroom
 * @tx_tr:	transmit tail room
 * @rx_tr:	receive tail room
 * @mtu:	transmit max size
 * @mru:	receive max size
 * @allocsz:    size of dma memory reserved for TX buffers
 * @alloc_addr: virtual address to dma memory for TX buffers
 * @alloc_dma:  dma address to dma memory for TX buffers
 * @genpool:    Gen Pool used for allocating TX buffers
 * @reserved_mem: Pointer to memory reserve allocated from genpool
 * @reserved_size: Size of memory reserve allocated from genpool
 * @stats:       Statistics exposed in sysfs
 * @debugfs:    Debugfs dentry for statistic counters
 */
struct cfv_info {
	struct caif_dev_common cfdev;
	struct virtio_device *vdev;
	struct vringh *vr_rx;
	struct virtqueue *vq_tx;
	struct net_device *ndev;
	unsigned int watermark_tx;
	/* Protect access to vq_tx */
	spinlock_t tx_lock;
	struct tasklet_struct tx_release_tasklet;
	struct napi_struct napi;
	struct cfv_napi_context ctx;
	u16 tx_hr;
	u16 rx_hr;
	u16 tx_tr;
	u16 rx_tr;
	u32 mtu;
	u32 mru;
	size_t allocsz;
	void *alloc_addr;
	dma_addr_t alloc_dma;
	struct gen_pool *genpool;
	unsigned long reserved_mem;
	size_t reserved_size;
	struct cfv_stats stats;
	struct dentry *debugfs;
};

/* struct buf_info - maintains transmit buffer data handle
 * @size:	size of transmit buffer
 * @dma_handle: handle to allocated dma device memory area
 * @vaddr:	virtual address mapping to allocated memory area
 */
struct buf_info {
	size_t size;
	u8 *vaddr;
};

/* Called from virtio device, in IRQ context */
static void cfv_release_cb(struct virtqueue *vq_tx)
{
	struct cfv_info *cfv = vq_tx->vdev->priv;

	++cfv->stats.tx_kicks;
	tasklet_schedule(&cfv->tx_release_tasklet);
}

static void free_buf_info(struct cfv_info *cfv, struct buf_info *buf_info)
{
	if (!buf_info)
		return;
	gen_pool_free(cfv->genpool, (unsigned long) buf_info->vaddr,
		      buf_info->size);
	kfree(buf_info);
}

/* This is invoked whenever the remote processor completed processing
 * a TX msg we just sent, and the buffer is put back to the used ring.
 */
static void cfv_release_used_buf(struct virtqueue *vq_tx)
{
	struct cfv_info *cfv = vq_tx->vdev->priv;
	unsigned long flags;

	BUG_ON(vq_tx != cfv->vq_tx);

	for (;;) {
		unsigned int len;
		struct buf_info *buf_info;

		/* Get used buffer from used ring to recycle used descriptors */
		spin_lock_irqsave(&cfv->tx_lock, flags);
		buf_info = virtqueue_get_buf(vq_tx, &len);
		spin_unlock_irqrestore(&cfv->tx_lock, flags);

		/* Stop looping if there are no more buffers to free */
		if (!buf_info)
			break;

		free_buf_info(cfv, buf_info);

		/* watermark_tx indicates if we previously stopped the tx
		 * queues. If we have enough free stots in the virtio ring,
		 * re-establish memory reserved and open up tx queues.
		 */
		if (cfv->vq_tx->num_free <= cfv->watermark_tx)
			continue;

		/* Re-establish memory reserve */
		if (cfv->reserved_mem == 0 && cfv->genpool)
			cfv->reserved_mem =
				gen_pool_alloc(cfv->genpool,
					       cfv->reserved_size);

		/* Open up the tx queues */
		if (cfv->reserved_mem) {
			cfv->watermark_tx =
				virtqueue_get_vring_size(cfv->vq_tx);
			netif_tx_wake_all_queues(cfv->ndev);
			/* Buffers are recycled in cfv_netdev_tx, so
			 * disable notifications when queues are opened.
			 */
			virtqueue_disable_cb(cfv->vq_tx);
			++cfv->stats.tx_flow_on;
		} else {
			/* if no memory reserve, wait for more free slots */
			WARN_ON(cfv->watermark_tx >
			       virtqueue_get_vring_size(cfv->vq_tx));
			cfv->watermark_tx +=
				virtqueue_get_vring_size(cfv->vq_tx) / 4;
		}
	}
}

/* Allocate a SKB and copy packet data to it */
static struct sk_buff *cfv_alloc_and_copy_skb(int *err,
					      struct cfv_info *cfv,
					      u8 *frm, u32 frm_len)
{
	struct sk_buff *skb;
	u32 cfpkt_len, pad_len;

	*err = 0;
	/* Verify that packet size with down-link header and mtu size */
	if (frm_len > cfv->mru || frm_len <= cfv->rx_hr + cfv->rx_tr) {
		netdev_err(cfv->ndev,
			   "Invalid frmlen:%u  mtu:%u hr:%d tr:%d\n",
			   frm_len, cfv->mru,  cfv->rx_hr,
			   cfv->rx_tr);
		*err = -EPROTO;
		return NULL;
	}

	cfpkt_len = frm_len - (cfv->rx_hr + cfv->rx_tr);
	pad_len = (unsigned long)(frm + cfv->rx_hr) & (IP_HDR_ALIGN - 1);

	skb = netdev_alloc_skb(cfv->ndev, frm_len + pad_len);
	if (!skb) {
		*err = -ENOMEM;
		return NULL;
	}

	skb_reserve(skb, cfv->rx_hr + pad_len);

	skb_put_data(skb, frm + cfv->rx_hr, cfpkt_len);
	return skb;
}

/* Get packets from the host vring */
static int cfv_rx_poll(struct napi_struct *napi, int quota)
{
	struct cfv_info *cfv = container_of(napi, struct cfv_info, napi);
	int rxcnt = 0;
	int err = 0;
	void *buf;
	struct sk_buff *skb;
	struct vringh_kiov *riov = &cfv->ctx.riov;
	unsigned int skb_len;

	do {
		skb = NULL;

		/* Put the previous iovec back on the used ring and
		 * fetch a new iovec if we have processed all elements.
		 */
		if (riov->i == riov->used) {
			if (cfv->ctx.head != USHRT_MAX) {
				vringh_complete_kern(cfv->vr_rx,
						     cfv->ctx.head,
						     0);
				cfv->ctx.head = USHRT_MAX;
			}

			err = vringh_getdesc_kern(
				cfv->vr_rx,
				riov,
				NULL,
				&cfv->ctx.head,
				GFP_ATOMIC);

			if (err <= 0)
				goto exit;
		}

		buf = phys_to_virt((unsigned long) riov->iov[riov->i].iov_base);
		/* TODO: Add check on valid buffer address */

		skb = cfv_alloc_and_copy_skb(&err, cfv, buf,
					     riov->iov[riov->i].iov_len);
		if (unlikely(err))
			goto exit;

		/* Push received packet up the stack. */
		skb_len = skb->len;
		skb->protocol = htons(ETH_P_CAIF);
		skb_reset_mac_header(skb);
		skb->dev = cfv->ndev;
		err = netif_receive_skb(skb);
		if (unlikely(err)) {
			++cfv->ndev->stats.rx_dropped;
		} else {
			++cfv->ndev->stats.rx_packets;
			cfv->ndev->stats.rx_bytes += skb_len;
		}

		++riov->i;
		++rxcnt;
	} while (rxcnt < quota);

	++cfv->stats.rx_napi_resched;
	goto out;

exit:
	switch (err) {
	case 0:
		++cfv->stats.rx_napi_complete;

		/* Really out of packets? (stolen from virtio_net)*/
		napi_complete(napi);
		if (unlikely(!vringh_notify_enable_kern(cfv->vr_rx)) &&
		    napi_schedule_prep(napi)) {
			vringh_notify_disable_kern(cfv->vr_rx);
			__napi_schedule(napi);
		}
		break;

	case -ENOMEM:
		++cfv->stats.rx_nomem;
		dev_kfree_skb(skb);
		/* Stop NAPI poll on OOM, we hope to be polled later */
		napi_complete(napi);
		vringh_notify_enable_kern(cfv->vr_rx);
		break;

	default:
		/* We're doomed, any modem fault is fatal */
		netdev_warn(cfv->ndev, "Bad ring, disable device\n");
		cfv->ndev->stats.rx_dropped = riov->used - riov->i;
		napi_complete(napi);
		vringh_notify_disable_kern(cfv->vr_rx);
		netif_carrier_off(cfv->ndev);
		break;
	}
out:
	if (rxcnt && vringh_need_notify_kern(cfv->vr_rx) > 0)
		vringh_notify(cfv->vr_rx);
	return rxcnt;
}

static void cfv_recv(struct virtio_device *vdev, struct vringh *vr_rx)
{
	struct cfv_info *cfv = vdev->priv;

	++cfv->stats.rx_kicks;
	vringh_notify_disable_kern(cfv->vr_rx);
	napi_schedule(&cfv->napi);
}

static void cfv_destroy_genpool(struct cfv_info *cfv)
{
	if (cfv->alloc_addr)
		dma_free_coherent(cfv->vdev->dev.parent->parent,
				  cfv->allocsz, cfv->alloc_addr,
				  cfv->alloc_dma);

	if (!cfv->genpool)
		return;
	gen_pool_free(cfv->genpool,  cfv->reserved_mem,
		      cfv->reserved_size);
	gen_pool_destroy(cfv->genpool);
	cfv->genpool = NULL;
}

static int cfv_create_genpool(struct cfv_info *cfv)
{
	int err;

	/* dma_alloc can only allocate whole pages, and we need a more
	 * fine graned allocation so we use genpool. We ask for space needed
	 * by IP and a full ring. If the dma allcoation fails we retry with a
	 * smaller allocation size.
	 */
	err = -ENOMEM;
	cfv->allocsz = (virtqueue_get_vring_size(cfv->vq_tx) *
			(ETH_DATA_LEN + cfv->tx_hr + cfv->tx_tr) * 11)/10;
	if (cfv->allocsz <= (num_possible_cpus() + 1) * cfv->ndev->mtu)
		return -EINVAL;

	for (;;) {
		if (cfv->allocsz <= num_possible_cpus() * cfv->ndev->mtu) {
			netdev_info(cfv->ndev, "Not enough device memory\n");
			return -ENOMEM;
		}

		cfv->alloc_addr = dma_alloc_coherent(
						cfv->vdev->dev.parent->parent,
						cfv->allocsz, &cfv->alloc_dma,
						GFP_ATOMIC);
		if (cfv->alloc_addr)
			break;

		cfv->allocsz = (cfv->allocsz * 3) >> 2;
	}

	netdev_dbg(cfv->ndev, "Allocated %zd bytes from dma-memory\n",
		   cfv->allocsz);

	/* Allocate on 128 bytes boundaries (1 << 7)*/
	cfv->genpool = gen_pool_create(7, -1);
	if (!cfv->genpool)
		goto err;

	err = gen_pool_add_virt(cfv->genpool, (unsigned long)cfv->alloc_addr,
				(phys_addr_t)virt_to_phys(cfv->alloc_addr),
				cfv->allocsz, -1);
	if (err)
		goto err;

	/* Reserve some memory for low memory situations. If we hit the roof
	 * in the memory pool, we stop TX flow and release the reserve.
	 */
	cfv->reserved_size = num_possible_cpus() * cfv->ndev->mtu;
	cfv->reserved_mem = gen_pool_alloc(cfv->genpool,
					   cfv->reserved_size);
	if (!cfv->reserved_mem) {
		err = -ENOMEM;
		goto err;
	}

	cfv->watermark_tx = virtqueue_get_vring_size(cfv->vq_tx);
	return 0;
err:
	cfv_destroy_genpool(cfv);
	return err;
}

/* Enable the CAIF interface and allocate the memory-pool */
static int cfv_netdev_open(struct net_device *netdev)
{
	struct cfv_info *cfv = netdev_priv(netdev);

	if (cfv_create_genpool(cfv))
		return -ENOMEM;

	netif_carrier_on(netdev);
	napi_enable(&cfv->napi);

	/* Schedule NAPI to read any pending packets */
	napi_schedule(&cfv->napi);
	return 0;
}

/* Disable the CAIF interface and free the memory-pool */
static int cfv_netdev_close(struct net_device *netdev)
{
	struct cfv_info *cfv = netdev_priv(netdev);
	unsigned long flags;
	struct buf_info *buf_info;

	/* Disable interrupts, queues and NAPI polling */
	netif_carrier_off(netdev);
	virtqueue_disable_cb(cfv->vq_tx);
	vringh_notify_disable_kern(cfv->vr_rx);
	napi_disable(&cfv->napi);

	/* Release any TX buffers on both used and available rings */
	cfv_release_used_buf(cfv->vq_tx);
	spin_lock_irqsave(&cfv->tx_lock, flags);
	while ((buf_info = virtqueue_detach_unused_buf(cfv->vq_tx)))
		free_buf_info(cfv, buf_info);
	spin_unlock_irqrestore(&cfv->tx_lock, flags);

	/* Release all dma allocated memory and destroy the pool */
	cfv_destroy_genpool(cfv);
	return 0;
}

/* Allocate a buffer in dma-memory and copy skb to it */
static struct buf_info *cfv_alloc_and_copy_to_shm(struct cfv_info *cfv,
						       struct sk_buff *skb,
						       struct scatterlist *sg)
{
	struct caif_payload_info *info = (void *)&skb->cb;
	struct buf_info *buf_info = NULL;
	u8 pad_len, hdr_ofs;

	if (!cfv->genpool)
		goto err;

	if (unlikely(cfv->tx_hr + skb->len + cfv->tx_tr > cfv->mtu)) {
		netdev_warn(cfv->ndev, "Invalid packet len (%d > %d)\n",
			    cfv->tx_hr + skb->len + cfv->tx_tr, cfv->mtu);
		goto err;
	}

	buf_info = kmalloc(sizeof(struct buf_info), GFP_ATOMIC);
	if (unlikely(!buf_info))
		goto err;

	/* Make the IP header aligned in the buffer */
	hdr_ofs = cfv->tx_hr + info->hdr_len;
	pad_len = hdr_ofs & (IP_HDR_ALIGN - 1);
	buf_info->size = cfv->tx_hr + skb->len + cfv->tx_tr + pad_len;

	/* allocate dma memory buffer */
	buf_info->vaddr = (void *)gen_pool_alloc(cfv->genpool, buf_info->size);
	if (unlikely(!buf_info->vaddr))
		goto err;

	/* copy skbuf contents to send buffer */
	skb_copy_bits(skb, 0, buf_info->vaddr + cfv->tx_hr + pad_len, skb->len);
	sg_init_one(sg, buf_info->vaddr + pad_len,
		    skb->len + cfv->tx_hr + cfv->rx_hr);

	return buf_info;
err:
	kfree(buf_info);
	return NULL;
}

/* Put the CAIF packet on the virtio ring and kick the receiver */
static netdev_tx_t cfv_netdev_tx(struct sk_buff *skb, struct net_device *netdev)
{
	struct cfv_info *cfv = netdev_priv(netdev);
	struct buf_info *buf_info;
	struct scatterlist sg;
	unsigned long flags;
	bool flow_off = false;
	int ret;

	/* garbage collect released buffers */
	cfv_release_used_buf(cfv->vq_tx);
	spin_lock_irqsave(&cfv->tx_lock, flags);

	/* Flow-off check takes into account number of cpus to make sure
	 * virtqueue will not be overfilled in any possible smp conditions.
	 *
	 * Flow-on is triggered when sufficient buffers are freed
	 */
	if (unlikely(cfv->vq_tx->num_free <= num_present_cpus())) {
		flow_off = true;
		cfv->stats.tx_full_ring++;
	}

	/* If we run out of memory, we release the memory reserve and retry
	 * allocation.
	 */
	buf_info = cfv_alloc_and_copy_to_shm(cfv, skb, &sg);
	if (unlikely(!buf_info)) {
		cfv->stats.tx_no_mem++;
		flow_off = true;

		if (cfv->reserved_mem && cfv->genpool) {
			gen_pool_free(cfv->genpool,  cfv->reserved_mem,
				      cfv->reserved_size);
			cfv->reserved_mem = 0;
			buf_info = cfv_alloc_and_copy_to_shm(cfv, skb, &sg);
		}
	}

	if (unlikely(flow_off)) {
		/* Turn flow on when a 1/4 of the descriptors are released */
		cfv->watermark_tx = virtqueue_get_vring_size(cfv->vq_tx) / 4;
		/* Enable notifications of recycled TX buffers */
		virtqueue_enable_cb(cfv->vq_tx);
		netif_tx_stop_all_queues(netdev);
	}

	if (unlikely(!buf_info)) {
		/* If the memory reserve does it's job, this shouldn't happen */
		netdev_warn(cfv->ndev, "Out of gen_pool memory\n");
		goto err;
	}

	ret = virtqueue_add_outbuf(cfv->vq_tx, &sg, 1, buf_info, GFP_ATOMIC);
	if (unlikely((ret < 0))) {
		/* If flow control works, this shouldn't happen */
		netdev_warn(cfv->ndev, "Failed adding buffer to TX vring:%d\n",
			    ret);
		goto err;
	}

	/* update netdev statistics */
	cfv->ndev->stats.tx_packets++;
	cfv->ndev->stats.tx_bytes += skb->len;
	spin_unlock_irqrestore(&cfv->tx_lock, flags);

	/* tell the remote processor it has a pending message to read */
	virtqueue_kick(cfv->vq_tx);

	dev_kfree_skb(skb);
	return NETDEV_TX_OK;
err:
	spin_unlock_irqrestore(&cfv->tx_lock, flags);
	cfv->ndev->stats.tx_dropped++;
	free_buf_info(cfv, buf_info);
	dev_kfree_skb(skb);
	return NETDEV_TX_OK;
}

static void cfv_tx_release_tasklet(struct tasklet_struct *t)
{
	struct cfv_info *cfv = from_tasklet(cfv, t, tx_release_tasklet);
	cfv_release_used_buf(cfv->vq_tx);
}

static const struct net_device_ops cfv_netdev_ops = {
	.ndo_open = cfv_netdev_open,
	.ndo_stop = cfv_netdev_close,
	.ndo_start_xmit = cfv_netdev_tx,
};

static void cfv_netdev_setup(struct net_device *netdev)
{
	netdev->netdev_ops = &cfv_netdev_ops;
	netdev->type = ARPHRD_CAIF;
	netdev->tx_queue_len = 100;
	netdev->flags = IFF_POINTOPOINT | IFF_NOARP;
	netdev->mtu = CFV_DEF_MTU_SIZE;
	netdev->needs_free_netdev = true;
}

/* Create debugfs counters for the device */
static inline void debugfs_init(struct cfv_info *cfv)
{
	cfv->debugfs = debugfs_create_dir(netdev_name(cfv->ndev), NULL);

	debugfs_create_u32("rx-napi-complete", 0400, cfv->debugfs,
			   &cfv->stats.rx_napi_complete);
	debugfs_create_u32("rx-napi-resched", 0400, cfv->debugfs,
			   &cfv->stats.rx_napi_resched);
	debugfs_create_u32("rx-nomem", 0400, cfv->debugfs,
			   &cfv->stats.rx_nomem);
	debugfs_create_u32("rx-kicks", 0400, cfv->debugfs,
			   &cfv->stats.rx_kicks);
	debugfs_create_u32("tx-full-ring", 0400, cfv->debugfs,
			   &cfv->stats.tx_full_ring);
	debugfs_create_u32("tx-no-mem", 0400, cfv->debugfs,
			   &cfv->stats.tx_no_mem);
	debugfs_create_u32("tx-kicks", 0400, cfv->debugfs,
			   &cfv->stats.tx_kicks);
	debugfs_create_u32("tx-flow-on", 0400, cfv->debugfs,
			   &cfv->stats.tx_flow_on);
}

/* Setup CAIF for the a virtio device */
static int cfv_probe(struct virtio_device *vdev)
{
	vrh_callback_t *vrh_cbs = cfv_recv;
	const char *cfv_netdev_name = "cfvrt";
	struct net_device *netdev;
	struct cfv_info *cfv;
	int err;

	netdev = alloc_netdev(sizeof(struct cfv_info), cfv_netdev_name,
			      NET_NAME_UNKNOWN, cfv_netdev_setup);
	if (!netdev)
		return -ENOMEM;

	cfv = netdev_priv(netdev);
	cfv->vdev = vdev;
	cfv->ndev = netdev;

	spin_lock_init(&cfv->tx_lock);

	/* Get the RX virtio ring. This is a "host side vring". */
	err = -ENODEV;
	if (!vdev->vringh_config || !vdev->vringh_config->find_vrhs)
		goto err;

	err = vdev->vringh_config->find_vrhs(vdev, 1, &cfv->vr_rx, &vrh_cbs);
	if (err)
		goto err;

	/* Get the TX virtio ring. This is a "guest side vring". */
	cfv->vq_tx = virtio_find_single_vq(vdev, cfv_release_cb, "output");
	if (IS_ERR(cfv->vq_tx)) {
		err = PTR_ERR(cfv->vq_tx);
		goto err;
	}

	/* Get the CAIF configuration from virtio config space, if available */
	if (vdev->config->get) {
		virtio_cread(vdev, struct virtio_caif_transf_config, headroom,
			     &cfv->tx_hr);
		virtio_cread(vdev, struct virtio_caif_transf_config, headroom,
			     &cfv->rx_hr);
		virtio_cread(vdev, struct virtio_caif_transf_config, tailroom,
			     &cfv->tx_tr);
		virtio_cread(vdev, struct virtio_caif_transf_config, tailroom,
			     &cfv->rx_tr);
		virtio_cread(vdev, struct virtio_caif_transf_config, mtu,
			     &cfv->mtu);
		virtio_cread(vdev, struct virtio_caif_transf_config, mtu,
			     &cfv->mru);
	} else {
		cfv->tx_hr = CFV_DEF_HEADROOM;
		cfv->rx_hr = CFV_DEF_HEADROOM;
		cfv->tx_tr = CFV_DEF_TAILROOM;
		cfv->rx_tr = CFV_DEF_TAILROOM;
		cfv->mtu = CFV_DEF_MTU_SIZE;
		cfv->mru = CFV_DEF_MTU_SIZE;
	}

	netdev->needed_headroom = cfv->tx_hr;
	netdev->needed_tailroom = cfv->tx_tr;

	/* Disable buffer release interrupts unless we have stopped TX queues */
	virtqueue_disable_cb(cfv->vq_tx);

	netdev->mtu = cfv->mtu - cfv->tx_tr;
	vdev->priv = cfv;

	/* Initialize NAPI poll context data */
	vringh_kiov_init(&cfv->ctx.riov, NULL, 0);
	cfv->ctx.head = USHRT_MAX;
	netif_napi_add_weight(netdev, &cfv->napi, cfv_rx_poll,
			      CFV_DEFAULT_QUOTA);

	tasklet_setup(&cfv->tx_release_tasklet, cfv_tx_release_tasklet);

	/* Carrier is off until netdevice is opened */
	netif_carrier_off(netdev);

	/* serialize netdev register + virtio_device_ready() with ndo_open() */
	rtnl_lock();

	/* register Netdev */
	err = register_netdevice(netdev);
	if (err) {
		rtnl_unlock();
		dev_err(&vdev->dev, "Unable to register netdev (%d)\n", err);
		goto err;
	}

	virtio_device_ready(vdev);

	rtnl_unlock();

	debugfs_init(cfv);

	return 0;
err:
	netdev_warn(cfv->ndev, "CAIF Virtio probe failed:%d\n", err);

	if (cfv->vr_rx)
		vdev->vringh_config->del_vrhs(cfv->vdev);
	if (cfv->vdev)
		vdev->config->del_vqs(cfv->vdev);
	free_netdev(netdev);
	return err;
}

static void cfv_remove(struct virtio_device *vdev)
{
	struct cfv_info *cfv = vdev->priv;

	rtnl_lock();
	dev_close(cfv->ndev);
	rtnl_unlock();

	tasklet_kill(&cfv->tx_release_tasklet);
	debugfs_remove_recursive(cfv->debugfs);

	vringh_kiov_cleanup(&cfv->ctx.riov);
	virtio_reset_device(vdev);
	vdev->vringh_config->del_vrhs(cfv->vdev);
	cfv->vr_rx = NULL;
	vdev->config->del_vqs(cfv->vdev);
	unregister_netdev(cfv->ndev);
}

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

static unsigned int features[] = {
};

static struct virtio_driver caif_virtio_driver = {
	.feature_table		= features,
	.feature_table_size	= ARRAY_SIZE(features),
	.driver.name		= KBUILD_MODNAME,
	.id_table		= id_table,
	.probe			= cfv_probe,
	.remove			= cfv_remove,
};

module_virtio_driver(caif_virtio_driver);
MODULE_DEVICE_TABLE(virtio, id_table);