1/*
2 * Copyright(c) 2017 - 2020 Intel Corporation.
3 *
4 * This file is provided under a dual BSD/GPLv2 license.  When using or
5 * redistributing this file, you may do so under either license.
6 *
7 * GPL LICENSE SUMMARY
8 *
9 * This program is free software; you can redistribute it and/or modify
10 * it under the terms of version 2 of the GNU General Public License as
11 * published by the Free Software Foundation.
12 *
13 * This program is distributed in the hope that it will be useful, but
14 * WITHOUT ANY WARRANTY; without even the implied warranty of
15 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
16 * General Public License for more details.
17 *
18 * BSD LICENSE
19 *
20 * Redistribution and use in source and binary forms, with or without
21 * modification, are permitted provided that the following conditions
22 * are met:
23 *
24 *  - Redistributions of source code must retain the above copyright
25 *    notice, this list of conditions and the following disclaimer.
26 *  - Redistributions in binary form must reproduce the above copyright
27 *    notice, this list of conditions and the following disclaimer in
28 *    the documentation and/or other materials provided with the
29 *    distribution.
30 *  - Neither the name of Intel Corporation nor the names of its
31 *    contributors may be used to endorse or promote products derived
32 *    from this software without specific prior written permission.
33 *
34 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
35 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
36 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
37 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
38 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
39 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
40 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
41 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
42 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
43 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
44 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
45 *
46 */
47
48/*
49 * This file contains HFI1 support for VNIC functionality
50 */
51
52#include <linux/io.h>
53#include <linux/if_vlan.h>
54
55#include "vnic.h"
56#include "netdev.h"
57
58#define HFI_TX_TIMEOUT_MS 1000
59
60#define HFI1_VNIC_RCV_Q_SIZE   1024
61
62#define HFI1_VNIC_UP 0
63
64static DEFINE_SPINLOCK(vport_cntr_lock);
65
66#define SUM_GRP_COUNTERS(stats, qstats, x_grp) do {            \
67		u64 *src64, *dst64;                            \
68		for (src64 = &qstats->x_grp.unicast,           \
69			dst64 = &stats->x_grp.unicast;         \
70			dst64 <= &stats->x_grp.s_1519_max;) {  \
71			*dst64++ += *src64++;                  \
72		}                                              \
73	} while (0)
74
75#define VNIC_MASK (0xFF)
76#define VNIC_ID(val) ((1ull << 24) | ((val) & VNIC_MASK))
77
78/* hfi1_vnic_update_stats - update statistics */
79static void hfi1_vnic_update_stats(struct hfi1_vnic_vport_info *vinfo,
80				   struct opa_vnic_stats *stats)
81{
82	struct net_device *netdev = vinfo->netdev;
83	u8 i;
84
85	/* add tx counters on different queues */
86	for (i = 0; i < vinfo->num_tx_q; i++) {
87		struct opa_vnic_stats *qstats = &vinfo->stats[i];
88		struct rtnl_link_stats64 *qnstats = &vinfo->stats[i].netstats;
89
90		stats->netstats.tx_fifo_errors += qnstats->tx_fifo_errors;
91		stats->netstats.tx_carrier_errors += qnstats->tx_carrier_errors;
92		stats->tx_drop_state += qstats->tx_drop_state;
93		stats->tx_dlid_zero += qstats->tx_dlid_zero;
94
95		SUM_GRP_COUNTERS(stats, qstats, tx_grp);
96		stats->netstats.tx_packets += qnstats->tx_packets;
97		stats->netstats.tx_bytes += qnstats->tx_bytes;
98	}
99
100	/* add rx counters on different queues */
101	for (i = 0; i < vinfo->num_rx_q; i++) {
102		struct opa_vnic_stats *qstats = &vinfo->stats[i];
103		struct rtnl_link_stats64 *qnstats = &vinfo->stats[i].netstats;
104
105		stats->netstats.rx_fifo_errors += qnstats->rx_fifo_errors;
106		stats->netstats.rx_nohandler += qnstats->rx_nohandler;
107		stats->rx_drop_state += qstats->rx_drop_state;
108		stats->rx_oversize += qstats->rx_oversize;
109		stats->rx_runt += qstats->rx_runt;
110
111		SUM_GRP_COUNTERS(stats, qstats, rx_grp);
112		stats->netstats.rx_packets += qnstats->rx_packets;
113		stats->netstats.rx_bytes += qnstats->rx_bytes;
114	}
115
116	stats->netstats.tx_errors = stats->netstats.tx_fifo_errors +
117				    stats->netstats.tx_carrier_errors +
118				    stats->tx_drop_state + stats->tx_dlid_zero;
119	stats->netstats.tx_dropped = stats->netstats.tx_errors;
120
121	stats->netstats.rx_errors = stats->netstats.rx_fifo_errors +
122				    stats->netstats.rx_nohandler +
123				    stats->rx_drop_state + stats->rx_oversize +
124				    stats->rx_runt;
125	stats->netstats.rx_dropped = stats->netstats.rx_errors;
126
127	netdev->stats.tx_packets = stats->netstats.tx_packets;
128	netdev->stats.tx_bytes = stats->netstats.tx_bytes;
129	netdev->stats.tx_fifo_errors = stats->netstats.tx_fifo_errors;
130	netdev->stats.tx_carrier_errors = stats->netstats.tx_carrier_errors;
131	netdev->stats.tx_errors = stats->netstats.tx_errors;
132	netdev->stats.tx_dropped = stats->netstats.tx_dropped;
133
134	netdev->stats.rx_packets = stats->netstats.rx_packets;
135	netdev->stats.rx_bytes = stats->netstats.rx_bytes;
136	netdev->stats.rx_fifo_errors = stats->netstats.rx_fifo_errors;
137	netdev->stats.multicast = stats->rx_grp.mcastbcast;
138	netdev->stats.rx_length_errors = stats->rx_oversize + stats->rx_runt;
139	netdev->stats.rx_errors = stats->netstats.rx_errors;
140	netdev->stats.rx_dropped = stats->netstats.rx_dropped;
141}
142
143/* update_len_counters - update pkt's len histogram counters */
144static inline void update_len_counters(struct opa_vnic_grp_stats *grp,
145				       int len)
146{
147	/* account for 4 byte FCS */
148	if (len >= 1515)
149		grp->s_1519_max++;
150	else if (len >= 1020)
151		grp->s_1024_1518++;
152	else if (len >= 508)
153		grp->s_512_1023++;
154	else if (len >= 252)
155		grp->s_256_511++;
156	else if (len >= 124)
157		grp->s_128_255++;
158	else if (len >= 61)
159		grp->s_65_127++;
160	else
161		grp->s_64++;
162}
163
164/* hfi1_vnic_update_tx_counters - update transmit counters */
165static void hfi1_vnic_update_tx_counters(struct hfi1_vnic_vport_info *vinfo,
166					 u8 q_idx, struct sk_buff *skb, int err)
167{
168	struct ethhdr *mac_hdr = (struct ethhdr *)skb_mac_header(skb);
169	struct opa_vnic_stats *stats = &vinfo->stats[q_idx];
170	struct opa_vnic_grp_stats *tx_grp = &stats->tx_grp;
171	u16 vlan_tci;
172
173	stats->netstats.tx_packets++;
174	stats->netstats.tx_bytes += skb->len + ETH_FCS_LEN;
175
176	update_len_counters(tx_grp, skb->len);
177
178	/* rest of the counts are for good packets only */
179	if (unlikely(err))
180		return;
181
182	if (is_multicast_ether_addr(mac_hdr->h_dest))
183		tx_grp->mcastbcast++;
184	else
185		tx_grp->unicast++;
186
187	if (!__vlan_get_tag(skb, &vlan_tci))
188		tx_grp->vlan++;
189	else
190		tx_grp->untagged++;
191}
192
193/* hfi1_vnic_update_rx_counters - update receive counters */
194static void hfi1_vnic_update_rx_counters(struct hfi1_vnic_vport_info *vinfo,
195					 u8 q_idx, struct sk_buff *skb, int err)
196{
197	struct ethhdr *mac_hdr = (struct ethhdr *)skb->data;
198	struct opa_vnic_stats *stats = &vinfo->stats[q_idx];
199	struct opa_vnic_grp_stats *rx_grp = &stats->rx_grp;
200	u16 vlan_tci;
201
202	stats->netstats.rx_packets++;
203	stats->netstats.rx_bytes += skb->len + ETH_FCS_LEN;
204
205	update_len_counters(rx_grp, skb->len);
206
207	/* rest of the counts are for good packets only */
208	if (unlikely(err))
209		return;
210
211	if (is_multicast_ether_addr(mac_hdr->h_dest))
212		rx_grp->mcastbcast++;
213	else
214		rx_grp->unicast++;
215
216	if (!__vlan_get_tag(skb, &vlan_tci))
217		rx_grp->vlan++;
218	else
219		rx_grp->untagged++;
220}
221
222/* This function is overloaded for opa_vnic specific implementation */
223static void hfi1_vnic_get_stats64(struct net_device *netdev,
224				  struct rtnl_link_stats64 *stats)
225{
226	struct opa_vnic_stats *vstats = (struct opa_vnic_stats *)stats;
227	struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
228
229	hfi1_vnic_update_stats(vinfo, vstats);
230}
231
232static u64 create_bypass_pbc(u32 vl, u32 dw_len)
233{
234	u64 pbc;
235
236	pbc = ((u64)PBC_IHCRC_NONE << PBC_INSERT_HCRC_SHIFT)
237		| PBC_INSERT_BYPASS_ICRC | PBC_CREDIT_RETURN
238		| PBC_PACKET_BYPASS
239		| ((vl & PBC_VL_MASK) << PBC_VL_SHIFT)
240		| (dw_len & PBC_LENGTH_DWS_MASK) << PBC_LENGTH_DWS_SHIFT;
241
242	return pbc;
243}
244
245/* hfi1_vnic_maybe_stop_tx - stop tx queue if required */
246static void hfi1_vnic_maybe_stop_tx(struct hfi1_vnic_vport_info *vinfo,
247				    u8 q_idx)
248{
249	netif_stop_subqueue(vinfo->netdev, q_idx);
250	if (!hfi1_vnic_sdma_write_avail(vinfo, q_idx))
251		return;
252
253	netif_start_subqueue(vinfo->netdev, q_idx);
254}
255
256static netdev_tx_t hfi1_netdev_start_xmit(struct sk_buff *skb,
257					  struct net_device *netdev)
258{
259	struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
260	u8 pad_len, q_idx = skb->queue_mapping;
261	struct hfi1_devdata *dd = vinfo->dd;
262	struct opa_vnic_skb_mdata *mdata;
263	u32 pkt_len, total_len;
264	int err = -EINVAL;
265	u64 pbc;
266
267	v_dbg("xmit: queue %d skb len %d\n", q_idx, skb->len);
268	if (unlikely(!netif_oper_up(netdev))) {
269		vinfo->stats[q_idx].tx_drop_state++;
270		goto tx_finish;
271	}
272
273	/* take out meta data */
274	mdata = (struct opa_vnic_skb_mdata *)skb->data;
275	skb_pull(skb, sizeof(*mdata));
276	if (unlikely(mdata->flags & OPA_VNIC_SKB_MDATA_ENCAP_ERR)) {
277		vinfo->stats[q_idx].tx_dlid_zero++;
278		goto tx_finish;
279	}
280
281	/* add tail padding (for 8 bytes size alignment) and icrc */
282	pad_len = -(skb->len + OPA_VNIC_ICRC_TAIL_LEN) & 0x7;
283	pad_len += OPA_VNIC_ICRC_TAIL_LEN;
284
285	/*
286	 * pkt_len is how much data we have to write, includes header and data.
287	 * total_len is length of the packet in Dwords plus the PBC should not
288	 * include the CRC.
289	 */
290	pkt_len = (skb->len + pad_len) >> 2;
291	total_len = pkt_len + 2; /* PBC + packet */
292
293	pbc = create_bypass_pbc(mdata->vl, total_len);
294
295	skb_get(skb);
296	v_dbg("pbc 0x%016llX len %d pad_len %d\n", pbc, skb->len, pad_len);
297	err = dd->process_vnic_dma_send(dd, q_idx, vinfo, skb, pbc, pad_len);
298	if (unlikely(err)) {
299		if (err == -ENOMEM)
300			vinfo->stats[q_idx].netstats.tx_fifo_errors++;
301		else if (err != -EBUSY)
302			vinfo->stats[q_idx].netstats.tx_carrier_errors++;
303	}
304	/* remove the header before updating tx counters */
305	skb_pull(skb, OPA_VNIC_HDR_LEN);
306
307	if (unlikely(err == -EBUSY)) {
308		hfi1_vnic_maybe_stop_tx(vinfo, q_idx);
309		dev_kfree_skb_any(skb);
310		return NETDEV_TX_BUSY;
311	}
312
313tx_finish:
314	/* update tx counters */
315	hfi1_vnic_update_tx_counters(vinfo, q_idx, skb, err);
316	dev_kfree_skb_any(skb);
317	return NETDEV_TX_OK;
318}
319
320static u16 hfi1_vnic_select_queue(struct net_device *netdev,
321				  struct sk_buff *skb,
322				  struct net_device *sb_dev)
323{
324	struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
325	struct opa_vnic_skb_mdata *mdata;
326	struct sdma_engine *sde;
327
328	mdata = (struct opa_vnic_skb_mdata *)skb->data;
329	sde = sdma_select_engine_vl(vinfo->dd, mdata->entropy, mdata->vl);
330	return sde->this_idx;
331}
332
333/* hfi1_vnic_decap_skb - strip OPA header from the skb (ethernet) packet */
334static inline int hfi1_vnic_decap_skb(struct hfi1_vnic_rx_queue *rxq,
335				      struct sk_buff *skb)
336{
337	struct hfi1_vnic_vport_info *vinfo = rxq->vinfo;
338	int max_len = vinfo->netdev->mtu + VLAN_ETH_HLEN;
339	int rc = -EFAULT;
340
341	skb_pull(skb, OPA_VNIC_HDR_LEN);
342
343	/* Validate Packet length */
344	if (unlikely(skb->len > max_len))
345		vinfo->stats[rxq->idx].rx_oversize++;
346	else if (unlikely(skb->len < ETH_ZLEN))
347		vinfo->stats[rxq->idx].rx_runt++;
348	else
349		rc = 0;
350	return rc;
351}
352
353static struct hfi1_vnic_vport_info *get_vnic_port(struct hfi1_devdata *dd,
354						  int vesw_id)
355{
356	int vnic_id = VNIC_ID(vesw_id);
357
358	return hfi1_netdev_get_data(dd, vnic_id);
359}
360
361static struct hfi1_vnic_vport_info *get_first_vnic_port(struct hfi1_devdata *dd)
362{
363	struct hfi1_vnic_vport_info *vinfo;
364	int next_id = VNIC_ID(0);
365
366	vinfo = hfi1_netdev_get_first_data(dd, &next_id);
367
368	if (next_id > VNIC_ID(VNIC_MASK))
369		return NULL;
370
371	return vinfo;
372}
373
374void hfi1_vnic_bypass_rcv(struct hfi1_packet *packet)
375{
376	struct hfi1_devdata *dd = packet->rcd->dd;
377	struct hfi1_vnic_vport_info *vinfo = NULL;
378	struct hfi1_vnic_rx_queue *rxq;
379	struct sk_buff *skb;
380	int l4_type, vesw_id = -1, rc;
381	u8 q_idx;
382	unsigned char *pad_info;
383
384	l4_type = hfi1_16B_get_l4(packet->ebuf);
385	if (likely(l4_type == OPA_16B_L4_ETHR)) {
386		vesw_id = HFI1_VNIC_GET_VESWID(packet->ebuf);
387		vinfo = get_vnic_port(dd, vesw_id);
388
389		/*
390		 * In case of invalid vesw id, count the error on
391		 * the first available vport.
392		 */
393		if (unlikely(!vinfo)) {
394			struct hfi1_vnic_vport_info *vinfo_tmp;
395
396			vinfo_tmp = get_first_vnic_port(dd);
397			if (vinfo_tmp) {
398				spin_lock(&vport_cntr_lock);
399				vinfo_tmp->stats[0].netstats.rx_nohandler++;
400				spin_unlock(&vport_cntr_lock);
401			}
402		}
403	}
404
405	if (unlikely(!vinfo)) {
406		dd_dev_warn(dd, "vnic rcv err: l4 %d vesw id %d ctx %d\n",
407			    l4_type, vesw_id, packet->rcd->ctxt);
408		return;
409	}
410
411	q_idx = packet->rcd->vnic_q_idx;
412	rxq = &vinfo->rxq[q_idx];
413	if (unlikely(!netif_oper_up(vinfo->netdev))) {
414		vinfo->stats[q_idx].rx_drop_state++;
415		return;
416	}
417
418	skb = netdev_alloc_skb(vinfo->netdev, packet->tlen);
419	if (unlikely(!skb)) {
420		vinfo->stats[q_idx].netstats.rx_fifo_errors++;
421		return;
422	}
423
424	memcpy(skb->data, packet->ebuf, packet->tlen);
425	skb_put(skb, packet->tlen);
426
427	pad_info = skb->data + skb->len - 1;
428	skb_trim(skb, (skb->len - OPA_VNIC_ICRC_TAIL_LEN -
429		       ((*pad_info) & 0x7)));
430
431	rc = hfi1_vnic_decap_skb(rxq, skb);
432
433	/* update rx counters */
434	hfi1_vnic_update_rx_counters(vinfo, rxq->idx, skb, rc);
435	if (unlikely(rc)) {
436		dev_kfree_skb_any(skb);
437		return;
438	}
439
440	skb_checksum_none_assert(skb);
441	skb->protocol = eth_type_trans(skb, rxq->netdev);
442
443	napi_gro_receive(&rxq->napi, skb);
444}
445
446static int hfi1_vnic_up(struct hfi1_vnic_vport_info *vinfo)
447{
448	struct hfi1_devdata *dd = vinfo->dd;
449	struct net_device *netdev = vinfo->netdev;
450	int rc;
451
452	/* ensure virtual eth switch id is valid */
453	if (!vinfo->vesw_id)
454		return -EINVAL;
455
456	rc = hfi1_netdev_add_data(dd, VNIC_ID(vinfo->vesw_id), vinfo);
457	if (rc < 0)
458		return rc;
459
460	rc = hfi1_netdev_rx_init(dd);
461	if (rc)
462		goto err_remove;
463
464	netif_carrier_on(netdev);
465	netif_tx_start_all_queues(netdev);
466	set_bit(HFI1_VNIC_UP, &vinfo->flags);
467
468	return 0;
469
470err_remove:
471	hfi1_netdev_remove_data(dd, VNIC_ID(vinfo->vesw_id));
472	return rc;
473}
474
475static void hfi1_vnic_down(struct hfi1_vnic_vport_info *vinfo)
476{
477	struct hfi1_devdata *dd = vinfo->dd;
478
479	clear_bit(HFI1_VNIC_UP, &vinfo->flags);
480	netif_carrier_off(vinfo->netdev);
481	netif_tx_disable(vinfo->netdev);
482	hfi1_netdev_remove_data(dd, VNIC_ID(vinfo->vesw_id));
483
484	hfi1_netdev_rx_destroy(dd);
485}
486
487static int hfi1_netdev_open(struct net_device *netdev)
488{
489	struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
490	int rc;
491
492	mutex_lock(&vinfo->lock);
493	rc = hfi1_vnic_up(vinfo);
494	mutex_unlock(&vinfo->lock);
495	return rc;
496}
497
498static int hfi1_netdev_close(struct net_device *netdev)
499{
500	struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
501
502	mutex_lock(&vinfo->lock);
503	if (test_bit(HFI1_VNIC_UP, &vinfo->flags))
504		hfi1_vnic_down(vinfo);
505	mutex_unlock(&vinfo->lock);
506	return 0;
507}
508
509static int hfi1_vnic_init(struct hfi1_vnic_vport_info *vinfo)
510{
511	struct hfi1_devdata *dd = vinfo->dd;
512	int rc = 0;
513
514	mutex_lock(&hfi1_mutex);
515	if (!dd->vnic_num_vports) {
516		rc = hfi1_vnic_txreq_init(dd);
517		if (rc)
518			goto txreq_fail;
519	}
520
521	rc = hfi1_netdev_rx_init(dd);
522	if (rc) {
523		dd_dev_err(dd, "Unable to initialize netdev contexts\n");
524		goto alloc_fail;
525	}
526
527	hfi1_init_vnic_rsm(dd);
528
529	dd->vnic_num_vports++;
530	hfi1_vnic_sdma_init(vinfo);
531
532alloc_fail:
533	if (!dd->vnic_num_vports)
534		hfi1_vnic_txreq_deinit(dd);
535txreq_fail:
536	mutex_unlock(&hfi1_mutex);
537	return rc;
538}
539
540static void hfi1_vnic_deinit(struct hfi1_vnic_vport_info *vinfo)
541{
542	struct hfi1_devdata *dd = vinfo->dd;
543
544	mutex_lock(&hfi1_mutex);
545	if (--dd->vnic_num_vports == 0) {
546		hfi1_deinit_vnic_rsm(dd);
547		hfi1_vnic_txreq_deinit(dd);
548	}
549	mutex_unlock(&hfi1_mutex);
550	hfi1_netdev_rx_destroy(dd);
551}
552
553static void hfi1_vnic_set_vesw_id(struct net_device *netdev, int id)
554{
555	struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
556	bool reopen = false;
557
558	/*
559	 * If vesw_id is being changed, and if the vnic port is up,
560	 * reset the vnic port to ensure new vesw_id gets picked up
561	 */
562	if (id != vinfo->vesw_id) {
563		mutex_lock(&vinfo->lock);
564		if (test_bit(HFI1_VNIC_UP, &vinfo->flags)) {
565			hfi1_vnic_down(vinfo);
566			reopen = true;
567		}
568
569		vinfo->vesw_id = id;
570		if (reopen)
571			hfi1_vnic_up(vinfo);
572
573		mutex_unlock(&vinfo->lock);
574	}
575}
576
577/* netdev ops */
578static const struct net_device_ops hfi1_netdev_ops = {
579	.ndo_open = hfi1_netdev_open,
580	.ndo_stop = hfi1_netdev_close,
581	.ndo_start_xmit = hfi1_netdev_start_xmit,
582	.ndo_select_queue = hfi1_vnic_select_queue,
583	.ndo_get_stats64 = hfi1_vnic_get_stats64,
584};
585
586static void hfi1_vnic_free_rn(struct net_device *netdev)
587{
588	struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
589
590	hfi1_vnic_deinit(vinfo);
591	mutex_destroy(&vinfo->lock);
592	free_netdev(netdev);
593}
594
595struct net_device *hfi1_vnic_alloc_rn(struct ib_device *device,
596				      u8 port_num,
597				      enum rdma_netdev_t type,
598				      const char *name,
599				      unsigned char name_assign_type,
600				      void (*setup)(struct net_device *))
601{
602	struct hfi1_devdata *dd = dd_from_ibdev(device);
603	struct hfi1_vnic_vport_info *vinfo;
604	struct net_device *netdev;
605	struct rdma_netdev *rn;
606	int i, size, rc;
607
608	if (!dd->num_netdev_contexts)
609		return ERR_PTR(-ENOMEM);
610
611	if (!port_num || (port_num > dd->num_pports))
612		return ERR_PTR(-EINVAL);
613
614	if (type != RDMA_NETDEV_OPA_VNIC)
615		return ERR_PTR(-EOPNOTSUPP);
616
617	size = sizeof(struct opa_vnic_rdma_netdev) + sizeof(*vinfo);
618	netdev = alloc_netdev_mqs(size, name, name_assign_type, setup,
619				  chip_sdma_engines(dd),
620				  dd->num_netdev_contexts);
621	if (!netdev)
622		return ERR_PTR(-ENOMEM);
623
624	rn = netdev_priv(netdev);
625	vinfo = opa_vnic_dev_priv(netdev);
626	vinfo->dd = dd;
627	vinfo->num_tx_q = chip_sdma_engines(dd);
628	vinfo->num_rx_q = dd->num_netdev_contexts;
629	vinfo->netdev = netdev;
630	rn->free_rdma_netdev = hfi1_vnic_free_rn;
631	rn->set_id = hfi1_vnic_set_vesw_id;
632
633	netdev->features = NETIF_F_HIGHDMA | NETIF_F_SG;
634	netdev->hw_features = netdev->features;
635	netdev->vlan_features = netdev->features;
636	netdev->watchdog_timeo = msecs_to_jiffies(HFI_TX_TIMEOUT_MS);
637	netdev->netdev_ops = &hfi1_netdev_ops;
638	mutex_init(&vinfo->lock);
639
640	for (i = 0; i < vinfo->num_rx_q; i++) {
641		struct hfi1_vnic_rx_queue *rxq = &vinfo->rxq[i];
642
643		rxq->idx = i;
644		rxq->vinfo = vinfo;
645		rxq->netdev = netdev;
646	}
647
648	rc = hfi1_vnic_init(vinfo);
649	if (rc)
650		goto init_fail;
651
652	return netdev;
653init_fail:
654	mutex_destroy(&vinfo->lock);
655	free_netdev(netdev);
656	return ERR_PTR(rc);
657}
658