Loading...
Note: File does not exist in v3.5.6.
1// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
2/*
3 * Copyright(c) 2017 - 2020 Intel Corporation.
4 */
5
6/*
7 * This file contains HFI1 support for VNIC functionality
8 */
9
10#include <linux/io.h>
11#include <linux/if_vlan.h>
12
13#include "vnic.h"
14#include "netdev.h"
15
16#define HFI_TX_TIMEOUT_MS 1000
17
18#define HFI1_VNIC_RCV_Q_SIZE 1024
19
20#define HFI1_VNIC_UP 0
21
22static DEFINE_SPINLOCK(vport_cntr_lock);
23
24#define SUM_GRP_COUNTERS(stats, qstats, x_grp) do { \
25 u64 *src64, *dst64; \
26 for (src64 = &qstats->x_grp.unicast, \
27 dst64 = &stats->x_grp.unicast; \
28 dst64 <= &stats->x_grp.s_1519_max;) { \
29 *dst64++ += *src64++; \
30 } \
31 } while (0)
32
33#define VNIC_MASK (0xFF)
34#define VNIC_ID(val) ((1ull << 24) | ((val) & VNIC_MASK))
35
36/* hfi1_vnic_update_stats - update statistics */
37static void hfi1_vnic_update_stats(struct hfi1_vnic_vport_info *vinfo,
38 struct opa_vnic_stats *stats)
39{
40 struct net_device *netdev = vinfo->netdev;
41 u8 i;
42
43 /* add tx counters on different queues */
44 for (i = 0; i < vinfo->num_tx_q; i++) {
45 struct opa_vnic_stats *qstats = &vinfo->stats[i];
46 struct rtnl_link_stats64 *qnstats = &vinfo->stats[i].netstats;
47
48 stats->netstats.tx_fifo_errors += qnstats->tx_fifo_errors;
49 stats->netstats.tx_carrier_errors += qnstats->tx_carrier_errors;
50 stats->tx_drop_state += qstats->tx_drop_state;
51 stats->tx_dlid_zero += qstats->tx_dlid_zero;
52
53 SUM_GRP_COUNTERS(stats, qstats, tx_grp);
54 stats->netstats.tx_packets += qnstats->tx_packets;
55 stats->netstats.tx_bytes += qnstats->tx_bytes;
56 }
57
58 /* add rx counters on different queues */
59 for (i = 0; i < vinfo->num_rx_q; i++) {
60 struct opa_vnic_stats *qstats = &vinfo->stats[i];
61 struct rtnl_link_stats64 *qnstats = &vinfo->stats[i].netstats;
62
63 stats->netstats.rx_fifo_errors += qnstats->rx_fifo_errors;
64 stats->netstats.rx_nohandler += qnstats->rx_nohandler;
65 stats->rx_drop_state += qstats->rx_drop_state;
66 stats->rx_oversize += qstats->rx_oversize;
67 stats->rx_runt += qstats->rx_runt;
68
69 SUM_GRP_COUNTERS(stats, qstats, rx_grp);
70 stats->netstats.rx_packets += qnstats->rx_packets;
71 stats->netstats.rx_bytes += qnstats->rx_bytes;
72 }
73
74 stats->netstats.tx_errors = stats->netstats.tx_fifo_errors +
75 stats->netstats.tx_carrier_errors +
76 stats->tx_drop_state + stats->tx_dlid_zero;
77 stats->netstats.tx_dropped = stats->netstats.tx_errors;
78
79 stats->netstats.rx_errors = stats->netstats.rx_fifo_errors +
80 stats->netstats.rx_nohandler +
81 stats->rx_drop_state + stats->rx_oversize +
82 stats->rx_runt;
83 stats->netstats.rx_dropped = stats->netstats.rx_errors;
84
85 netdev->stats.tx_packets = stats->netstats.tx_packets;
86 netdev->stats.tx_bytes = stats->netstats.tx_bytes;
87 netdev->stats.tx_fifo_errors = stats->netstats.tx_fifo_errors;
88 netdev->stats.tx_carrier_errors = stats->netstats.tx_carrier_errors;
89 netdev->stats.tx_errors = stats->netstats.tx_errors;
90 netdev->stats.tx_dropped = stats->netstats.tx_dropped;
91
92 netdev->stats.rx_packets = stats->netstats.rx_packets;
93 netdev->stats.rx_bytes = stats->netstats.rx_bytes;
94 netdev->stats.rx_fifo_errors = stats->netstats.rx_fifo_errors;
95 netdev->stats.multicast = stats->rx_grp.mcastbcast;
96 netdev->stats.rx_length_errors = stats->rx_oversize + stats->rx_runt;
97 netdev->stats.rx_errors = stats->netstats.rx_errors;
98 netdev->stats.rx_dropped = stats->netstats.rx_dropped;
99}
100
101/* update_len_counters - update pkt's len histogram counters */
102static inline void update_len_counters(struct opa_vnic_grp_stats *grp,
103 int len)
104{
105 /* account for 4 byte FCS */
106 if (len >= 1515)
107 grp->s_1519_max++;
108 else if (len >= 1020)
109 grp->s_1024_1518++;
110 else if (len >= 508)
111 grp->s_512_1023++;
112 else if (len >= 252)
113 grp->s_256_511++;
114 else if (len >= 124)
115 grp->s_128_255++;
116 else if (len >= 61)
117 grp->s_65_127++;
118 else
119 grp->s_64++;
120}
121
122/* hfi1_vnic_update_tx_counters - update transmit counters */
123static void hfi1_vnic_update_tx_counters(struct hfi1_vnic_vport_info *vinfo,
124 u8 q_idx, struct sk_buff *skb, int err)
125{
126 struct ethhdr *mac_hdr = (struct ethhdr *)skb_mac_header(skb);
127 struct opa_vnic_stats *stats = &vinfo->stats[q_idx];
128 struct opa_vnic_grp_stats *tx_grp = &stats->tx_grp;
129 u16 vlan_tci;
130
131 stats->netstats.tx_packets++;
132 stats->netstats.tx_bytes += skb->len + ETH_FCS_LEN;
133
134 update_len_counters(tx_grp, skb->len);
135
136 /* rest of the counts are for good packets only */
137 if (unlikely(err))
138 return;
139
140 if (is_multicast_ether_addr(mac_hdr->h_dest))
141 tx_grp->mcastbcast++;
142 else
143 tx_grp->unicast++;
144
145 if (!__vlan_get_tag(skb, &vlan_tci))
146 tx_grp->vlan++;
147 else
148 tx_grp->untagged++;
149}
150
151/* hfi1_vnic_update_rx_counters - update receive counters */
152static void hfi1_vnic_update_rx_counters(struct hfi1_vnic_vport_info *vinfo,
153 u8 q_idx, struct sk_buff *skb, int err)
154{
155 struct ethhdr *mac_hdr = (struct ethhdr *)skb->data;
156 struct opa_vnic_stats *stats = &vinfo->stats[q_idx];
157 struct opa_vnic_grp_stats *rx_grp = &stats->rx_grp;
158 u16 vlan_tci;
159
160 stats->netstats.rx_packets++;
161 stats->netstats.rx_bytes += skb->len + ETH_FCS_LEN;
162
163 update_len_counters(rx_grp, skb->len);
164
165 /* rest of the counts are for good packets only */
166 if (unlikely(err))
167 return;
168
169 if (is_multicast_ether_addr(mac_hdr->h_dest))
170 rx_grp->mcastbcast++;
171 else
172 rx_grp->unicast++;
173
174 if (!__vlan_get_tag(skb, &vlan_tci))
175 rx_grp->vlan++;
176 else
177 rx_grp->untagged++;
178}
179
180/* This function is overloaded for opa_vnic specific implementation */
181static void hfi1_vnic_get_stats64(struct net_device *netdev,
182 struct rtnl_link_stats64 *stats)
183{
184 struct opa_vnic_stats *vstats = (struct opa_vnic_stats *)stats;
185 struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
186
187 hfi1_vnic_update_stats(vinfo, vstats);
188}
189
190static u64 create_bypass_pbc(u32 vl, u32 dw_len)
191{
192 u64 pbc;
193
194 pbc = ((u64)PBC_IHCRC_NONE << PBC_INSERT_HCRC_SHIFT)
195 | PBC_INSERT_BYPASS_ICRC | PBC_CREDIT_RETURN
196 | PBC_PACKET_BYPASS
197 | ((vl & PBC_VL_MASK) << PBC_VL_SHIFT)
198 | (dw_len & PBC_LENGTH_DWS_MASK) << PBC_LENGTH_DWS_SHIFT;
199
200 return pbc;
201}
202
203/* hfi1_vnic_maybe_stop_tx - stop tx queue if required */
204static void hfi1_vnic_maybe_stop_tx(struct hfi1_vnic_vport_info *vinfo,
205 u8 q_idx)
206{
207 netif_stop_subqueue(vinfo->netdev, q_idx);
208 if (!hfi1_vnic_sdma_write_avail(vinfo, q_idx))
209 return;
210
211 netif_start_subqueue(vinfo->netdev, q_idx);
212}
213
214static netdev_tx_t hfi1_netdev_start_xmit(struct sk_buff *skb,
215 struct net_device *netdev)
216{
217 struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
218 u8 pad_len, q_idx = skb->queue_mapping;
219 struct hfi1_devdata *dd = vinfo->dd;
220 struct opa_vnic_skb_mdata *mdata;
221 u32 pkt_len, total_len;
222 int err = -EINVAL;
223 u64 pbc;
224
225 v_dbg("xmit: queue %d skb len %d\n", q_idx, skb->len);
226 if (unlikely(!netif_oper_up(netdev))) {
227 vinfo->stats[q_idx].tx_drop_state++;
228 goto tx_finish;
229 }
230
231 /* take out meta data */
232 mdata = (struct opa_vnic_skb_mdata *)skb->data;
233 skb_pull(skb, sizeof(*mdata));
234 if (unlikely(mdata->flags & OPA_VNIC_SKB_MDATA_ENCAP_ERR)) {
235 vinfo->stats[q_idx].tx_dlid_zero++;
236 goto tx_finish;
237 }
238
239 /* add tail padding (for 8 bytes size alignment) and icrc */
240 pad_len = -(skb->len + OPA_VNIC_ICRC_TAIL_LEN) & 0x7;
241 pad_len += OPA_VNIC_ICRC_TAIL_LEN;
242
243 /*
244 * pkt_len is how much data we have to write, includes header and data.
245 * total_len is length of the packet in Dwords plus the PBC should not
246 * include the CRC.
247 */
248 pkt_len = (skb->len + pad_len) >> 2;
249 total_len = pkt_len + 2; /* PBC + packet */
250
251 pbc = create_bypass_pbc(mdata->vl, total_len);
252
253 skb_get(skb);
254 v_dbg("pbc 0x%016llX len %d pad_len %d\n", pbc, skb->len, pad_len);
255 err = dd->process_vnic_dma_send(dd, q_idx, vinfo, skb, pbc, pad_len);
256 if (unlikely(err)) {
257 if (err == -ENOMEM)
258 vinfo->stats[q_idx].netstats.tx_fifo_errors++;
259 else if (err != -EBUSY)
260 vinfo->stats[q_idx].netstats.tx_carrier_errors++;
261 }
262 /* remove the header before updating tx counters */
263 skb_pull(skb, OPA_VNIC_HDR_LEN);
264
265 if (unlikely(err == -EBUSY)) {
266 hfi1_vnic_maybe_stop_tx(vinfo, q_idx);
267 dev_kfree_skb_any(skb);
268 return NETDEV_TX_BUSY;
269 }
270
271tx_finish:
272 /* update tx counters */
273 hfi1_vnic_update_tx_counters(vinfo, q_idx, skb, err);
274 dev_kfree_skb_any(skb);
275 return NETDEV_TX_OK;
276}
277
278static u16 hfi1_vnic_select_queue(struct net_device *netdev,
279 struct sk_buff *skb,
280 struct net_device *sb_dev)
281{
282 struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
283 struct opa_vnic_skb_mdata *mdata;
284 struct sdma_engine *sde;
285
286 mdata = (struct opa_vnic_skb_mdata *)skb->data;
287 sde = sdma_select_engine_vl(vinfo->dd, mdata->entropy, mdata->vl);
288 return sde->this_idx;
289}
290
291/* hfi1_vnic_decap_skb - strip OPA header from the skb (ethernet) packet */
292static inline int hfi1_vnic_decap_skb(struct hfi1_vnic_rx_queue *rxq,
293 struct sk_buff *skb)
294{
295 struct hfi1_vnic_vport_info *vinfo = rxq->vinfo;
296 int max_len = vinfo->netdev->mtu + VLAN_ETH_HLEN;
297 int rc = -EFAULT;
298
299 skb_pull(skb, OPA_VNIC_HDR_LEN);
300
301 /* Validate Packet length */
302 if (unlikely(skb->len > max_len))
303 vinfo->stats[rxq->idx].rx_oversize++;
304 else if (unlikely(skb->len < ETH_ZLEN))
305 vinfo->stats[rxq->idx].rx_runt++;
306 else
307 rc = 0;
308 return rc;
309}
310
311static struct hfi1_vnic_vport_info *get_vnic_port(struct hfi1_devdata *dd,
312 int vesw_id)
313{
314 int vnic_id = VNIC_ID(vesw_id);
315
316 return hfi1_netdev_get_data(dd, vnic_id);
317}
318
319static struct hfi1_vnic_vport_info *get_first_vnic_port(struct hfi1_devdata *dd)
320{
321 struct hfi1_vnic_vport_info *vinfo;
322 int next_id = VNIC_ID(0);
323
324 vinfo = hfi1_netdev_get_first_data(dd, &next_id);
325
326 if (next_id > VNIC_ID(VNIC_MASK))
327 return NULL;
328
329 return vinfo;
330}
331
332void hfi1_vnic_bypass_rcv(struct hfi1_packet *packet)
333{
334 struct hfi1_devdata *dd = packet->rcd->dd;
335 struct hfi1_vnic_vport_info *vinfo = NULL;
336 struct hfi1_vnic_rx_queue *rxq;
337 struct sk_buff *skb;
338 int l4_type, vesw_id = -1, rc;
339 u8 q_idx;
340 unsigned char *pad_info;
341
342 l4_type = hfi1_16B_get_l4(packet->ebuf);
343 if (likely(l4_type == OPA_16B_L4_ETHR)) {
344 vesw_id = HFI1_VNIC_GET_VESWID(packet->ebuf);
345 vinfo = get_vnic_port(dd, vesw_id);
346
347 /*
348 * In case of invalid vesw id, count the error on
349 * the first available vport.
350 */
351 if (unlikely(!vinfo)) {
352 struct hfi1_vnic_vport_info *vinfo_tmp;
353
354 vinfo_tmp = get_first_vnic_port(dd);
355 if (vinfo_tmp) {
356 spin_lock(&vport_cntr_lock);
357 vinfo_tmp->stats[0].netstats.rx_nohandler++;
358 spin_unlock(&vport_cntr_lock);
359 }
360 }
361 }
362
363 if (unlikely(!vinfo)) {
364 dd_dev_warn(dd, "vnic rcv err: l4 %d vesw id %d ctx %d\n",
365 l4_type, vesw_id, packet->rcd->ctxt);
366 return;
367 }
368
369 q_idx = packet->rcd->vnic_q_idx;
370 rxq = &vinfo->rxq[q_idx];
371 if (unlikely(!netif_oper_up(vinfo->netdev))) {
372 vinfo->stats[q_idx].rx_drop_state++;
373 return;
374 }
375
376 skb = netdev_alloc_skb(vinfo->netdev, packet->tlen);
377 if (unlikely(!skb)) {
378 vinfo->stats[q_idx].netstats.rx_fifo_errors++;
379 return;
380 }
381
382 memcpy(skb->data, packet->ebuf, packet->tlen);
383 skb_put(skb, packet->tlen);
384
385 pad_info = skb->data + skb->len - 1;
386 skb_trim(skb, (skb->len - OPA_VNIC_ICRC_TAIL_LEN -
387 ((*pad_info) & 0x7)));
388
389 rc = hfi1_vnic_decap_skb(rxq, skb);
390
391 /* update rx counters */
392 hfi1_vnic_update_rx_counters(vinfo, rxq->idx, skb, rc);
393 if (unlikely(rc)) {
394 dev_kfree_skb_any(skb);
395 return;
396 }
397
398 skb_checksum_none_assert(skb);
399 skb->protocol = eth_type_trans(skb, rxq->netdev);
400
401 napi_gro_receive(&rxq->napi, skb);
402}
403
404static int hfi1_vnic_up(struct hfi1_vnic_vport_info *vinfo)
405{
406 struct hfi1_devdata *dd = vinfo->dd;
407 struct net_device *netdev = vinfo->netdev;
408 int rc;
409
410 /* ensure virtual eth switch id is valid */
411 if (!vinfo->vesw_id)
412 return -EINVAL;
413
414 rc = hfi1_netdev_add_data(dd, VNIC_ID(vinfo->vesw_id), vinfo);
415 if (rc < 0)
416 return rc;
417
418 rc = hfi1_netdev_rx_init(dd);
419 if (rc)
420 goto err_remove;
421
422 netif_carrier_on(netdev);
423 netif_tx_start_all_queues(netdev);
424 set_bit(HFI1_VNIC_UP, &vinfo->flags);
425
426 return 0;
427
428err_remove:
429 hfi1_netdev_remove_data(dd, VNIC_ID(vinfo->vesw_id));
430 return rc;
431}
432
433static void hfi1_vnic_down(struct hfi1_vnic_vport_info *vinfo)
434{
435 struct hfi1_devdata *dd = vinfo->dd;
436
437 clear_bit(HFI1_VNIC_UP, &vinfo->flags);
438 netif_carrier_off(vinfo->netdev);
439 netif_tx_disable(vinfo->netdev);
440 hfi1_netdev_remove_data(dd, VNIC_ID(vinfo->vesw_id));
441
442 hfi1_netdev_rx_destroy(dd);
443}
444
445static int hfi1_netdev_open(struct net_device *netdev)
446{
447 struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
448 int rc;
449
450 mutex_lock(&vinfo->lock);
451 rc = hfi1_vnic_up(vinfo);
452 mutex_unlock(&vinfo->lock);
453 return rc;
454}
455
456static int hfi1_netdev_close(struct net_device *netdev)
457{
458 struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
459
460 mutex_lock(&vinfo->lock);
461 if (test_bit(HFI1_VNIC_UP, &vinfo->flags))
462 hfi1_vnic_down(vinfo);
463 mutex_unlock(&vinfo->lock);
464 return 0;
465}
466
467static int hfi1_vnic_init(struct hfi1_vnic_vport_info *vinfo)
468{
469 struct hfi1_devdata *dd = vinfo->dd;
470 int rc = 0;
471
472 mutex_lock(&hfi1_mutex);
473 if (!dd->vnic_num_vports) {
474 rc = hfi1_vnic_txreq_init(dd);
475 if (rc)
476 goto txreq_fail;
477 }
478
479 rc = hfi1_netdev_rx_init(dd);
480 if (rc) {
481 dd_dev_err(dd, "Unable to initialize netdev contexts\n");
482 goto alloc_fail;
483 }
484
485 hfi1_init_vnic_rsm(dd);
486
487 dd->vnic_num_vports++;
488 hfi1_vnic_sdma_init(vinfo);
489
490alloc_fail:
491 if (!dd->vnic_num_vports)
492 hfi1_vnic_txreq_deinit(dd);
493txreq_fail:
494 mutex_unlock(&hfi1_mutex);
495 return rc;
496}
497
498static void hfi1_vnic_deinit(struct hfi1_vnic_vport_info *vinfo)
499{
500 struct hfi1_devdata *dd = vinfo->dd;
501
502 mutex_lock(&hfi1_mutex);
503 if (--dd->vnic_num_vports == 0) {
504 hfi1_deinit_vnic_rsm(dd);
505 hfi1_vnic_txreq_deinit(dd);
506 }
507 mutex_unlock(&hfi1_mutex);
508 hfi1_netdev_rx_destroy(dd);
509}
510
511static void hfi1_vnic_set_vesw_id(struct net_device *netdev, int id)
512{
513 struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
514 bool reopen = false;
515
516 /*
517 * If vesw_id is being changed, and if the vnic port is up,
518 * reset the vnic port to ensure new vesw_id gets picked up
519 */
520 if (id != vinfo->vesw_id) {
521 mutex_lock(&vinfo->lock);
522 if (test_bit(HFI1_VNIC_UP, &vinfo->flags)) {
523 hfi1_vnic_down(vinfo);
524 reopen = true;
525 }
526
527 vinfo->vesw_id = id;
528 if (reopen)
529 hfi1_vnic_up(vinfo);
530
531 mutex_unlock(&vinfo->lock);
532 }
533}
534
535/* netdev ops */
536static const struct net_device_ops hfi1_netdev_ops = {
537 .ndo_open = hfi1_netdev_open,
538 .ndo_stop = hfi1_netdev_close,
539 .ndo_start_xmit = hfi1_netdev_start_xmit,
540 .ndo_select_queue = hfi1_vnic_select_queue,
541 .ndo_get_stats64 = hfi1_vnic_get_stats64,
542};
543
544static void hfi1_vnic_free_rn(struct net_device *netdev)
545{
546 struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
547
548 hfi1_vnic_deinit(vinfo);
549 mutex_destroy(&vinfo->lock);
550 free_netdev(netdev);
551}
552
553struct net_device *hfi1_vnic_alloc_rn(struct ib_device *device,
554 u32 port_num,
555 enum rdma_netdev_t type,
556 const char *name,
557 unsigned char name_assign_type,
558 void (*setup)(struct net_device *))
559{
560 struct hfi1_devdata *dd = dd_from_ibdev(device);
561 struct hfi1_vnic_vport_info *vinfo;
562 struct net_device *netdev;
563 struct rdma_netdev *rn;
564 int i, size, rc;
565
566 if (!dd->num_netdev_contexts)
567 return ERR_PTR(-ENOMEM);
568
569 if (!port_num || (port_num > dd->num_pports))
570 return ERR_PTR(-EINVAL);
571
572 if (type != RDMA_NETDEV_OPA_VNIC)
573 return ERR_PTR(-EOPNOTSUPP);
574
575 size = sizeof(struct opa_vnic_rdma_netdev) + sizeof(*vinfo);
576 netdev = alloc_netdev_mqs(size, name, name_assign_type, setup,
577 chip_sdma_engines(dd),
578 dd->num_netdev_contexts);
579 if (!netdev)
580 return ERR_PTR(-ENOMEM);
581
582 rn = netdev_priv(netdev);
583 vinfo = opa_vnic_dev_priv(netdev);
584 vinfo->dd = dd;
585 vinfo->num_tx_q = chip_sdma_engines(dd);
586 vinfo->num_rx_q = dd->num_netdev_contexts;
587 vinfo->netdev = netdev;
588 rn->free_rdma_netdev = hfi1_vnic_free_rn;
589 rn->set_id = hfi1_vnic_set_vesw_id;
590
591 netdev->features = NETIF_F_HIGHDMA | NETIF_F_SG;
592 netdev->hw_features = netdev->features;
593 netdev->vlan_features = netdev->features;
594 netdev->watchdog_timeo = msecs_to_jiffies(HFI_TX_TIMEOUT_MS);
595 netdev->netdev_ops = &hfi1_netdev_ops;
596 mutex_init(&vinfo->lock);
597
598 for (i = 0; i < vinfo->num_rx_q; i++) {
599 struct hfi1_vnic_rx_queue *rxq = &vinfo->rxq[i];
600
601 rxq->idx = i;
602 rxq->vinfo = vinfo;
603 rxq->netdev = netdev;
604 }
605
606 rc = hfi1_vnic_init(vinfo);
607 if (rc)
608 goto init_fail;
609
610 return netdev;
611init_fail:
612 mutex_destroy(&vinfo->lock);
613 free_netdev(netdev);
614 return ERR_PTR(rc);
615}