aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/net/fm10k/fm10k_rxtx.c
blob: 32cc7ff9a40b1644c4082f3454e760e071bd77ea (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
/*-
 *   BSD LICENSE
 *
 *   Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
 *   All rights reserved.
 *
 *   Redistribution and use in source and binary forms, with or without
 *   modification, are permitted provided that the following conditions
 *   are met:
 *
 *     * Redistributions of source code must retain the above copyright
 *       notice, this list of conditions and the following disclaimer.
 *     * Redistributions in binary form must reproduce the above copyright
 *       notice, this list of conditions and the following disclaimer in
 *       the documentation and/or other materials provided with the
 *       distribution.
 *     * Neither the name of Intel Corporation nor the names of its
 *       contributors may be used to endorse or promote products derived
 *       from this software without specific prior written permission.
 *
 *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#include <inttypes.h>

#include <rte_ethdev.h>
#include <rte_common.h>
#include "fm10k.h"
#include "base/fm10k_type.h"

#ifdef RTE_PMD_PACKET_PREFETCH
#define rte_packet_prefetch(p)  rte_prefetch1(p)
#else
#define rte_packet_prefetch(p)  do {} while (0)
#endif

#ifdef RTE_LIBRTE_FM10K_DEBUG_RX
static inline void dump_rxd(union fm10k_rx_desc *rxd)
{
	PMD_RX_LOG(DEBUG, "+----------------|----------------+");
	PMD_RX_LOG(DEBUG, "|     GLORT      | PKT HDR & TYPE |");
	PMD_RX_LOG(DEBUG, "|   0x%08x   |   0x%08x   |", rxd->d.glort,
			rxd->d.data);
	PMD_RX_LOG(DEBUG, "+----------------|----------------+");
	PMD_RX_LOG(DEBUG, "|   VLAN & LEN   |     STATUS     |");
	PMD_RX_LOG(DEBUG, "|   0x%08x   |   0x%08x   |", rxd->d.vlan_len,
			rxd->d.staterr);
	PMD_RX_LOG(DEBUG, "+----------------|----------------+");
	PMD_RX_LOG(DEBUG, "|    RESERVED    |    RSS_HASH    |");
	PMD_RX_LOG(DEBUG, "|   0x%08x   |   0x%08x   |", 0, rxd->d.rss);
	PMD_RX_LOG(DEBUG, "+----------------|----------------+");
	PMD_RX_LOG(DEBUG, "|            TIME TAG             |");
	PMD_RX_LOG(DEBUG, "|       0x%016"PRIx64"        |", rxd->q.timestamp);
	PMD_RX_LOG(DEBUG, "+----------------|----------------+");
}
#endif

/* @note: When this function is changed, make corresponding change to
 * fm10k_dev_supported_ptypes_get()
 */
static inline void
rx_desc_to_ol_flags(struct rte_mbuf *m, const union fm10k_rx_desc *d)
{
	static const uint32_t
		ptype_table[FM10K_RXD_PKTTYPE_MASK >> FM10K_RXD_PKTTYPE_SHIFT]
			__rte_cache_aligned = {
		[FM10K_PKTTYPE_OTHER] = RTE_PTYPE_L2_ETHER,
		[FM10K_PKTTYPE_IPV4] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4,
		[FM10K_PKTTYPE_IPV4_EX] = RTE_PTYPE_L2_ETHER |
			RTE_PTYPE_L3_IPV4_EXT,
		[FM10K_PKTTYPE_IPV6] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6,
		[FM10K_PKTTYPE_IPV6_EX] = RTE_PTYPE_L2_ETHER |
			RTE_PTYPE_L3_IPV6_EXT,
		[FM10K_PKTTYPE_IPV4 | FM10K_PKTTYPE_TCP] = RTE_PTYPE_L2_ETHER |
			RTE_PTYPE_L3_IPV4 | RTE_PTYPE_L4_TCP,
		[FM10K_PKTTYPE_IPV6 | FM10K_PKTTYPE_TCP] = RTE_PTYPE_L2_ETHER |
			RTE_PTYPE_L3_IPV6 | RTE_PTYPE_L4_TCP,
		[FM10K_PKTTYPE_IPV4 | FM10K_PKTTYPE_UDP] = RTE_PTYPE_L2_ETHER |
			RTE_PTYPE_L3_IPV4 | RTE_PTYPE_L4_UDP,
		[FM10K_PKTTYPE_IPV6 | FM10K_PKTTYPE_UDP] = RTE_PTYPE_L2_ETHER |
			RTE_PTYPE_L3_IPV6 | RTE_PTYPE_L4_UDP,
	};

	m->packet_type = ptype_table[(d->w.pkt_info & FM10K_RXD_PKTTYPE_MASK)
						>> FM10K_RXD_PKTTYPE_SHIFT];

	if (d->w.pkt_info & FM10K_RXD_RSSTYPE_MASK)
		m->ol_flags |= PKT_RX_RSS_HASH;

	if (unlikely((d->d.staterr &
		(FM10K_RXD_STATUS_IPCS | FM10K_RXD_STATUS_IPE)) ==
		(FM10K_RXD_STATUS_IPCS | FM10K_RXD_STATUS_IPE)))
		m->ol_flags |= PKT_RX_IP_CKSUM_BAD;
	else
		m->ol_flags |= PKT_RX_IP_CKSUM_GOOD;

	if (unlikely((d->d.staterr &
		(FM10K_RXD_STATUS_L4CS | FM10K_RXD_STATUS_L4E)) ==
		(FM10K_RXD_STATUS_L4CS | FM10K_RXD_STATUS_L4E)))
		m->ol_flags |= PKT_RX_L4_CKSUM_BAD;
	else
		m->ol_flags |= PKT_RX_L4_CKSUM_GOOD;
}

uint16_t
fm10k_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
	uint16_t nb_pkts)
{
	struct rte_mbuf *mbuf;
	union fm10k_rx_desc desc;
	struct fm10k_rx_queue *q = rx_queue;
	uint16_t count = 0;
	int alloc = 0;
	uint16_t next_dd;
	int ret;

	next_dd = q->next_dd;

	nb_pkts = RTE_MIN(nb_pkts, q->alloc_thresh);
	for (count = 0; count < nb_pkts; ++count) {
		if (!(q->hw_ring[next_dd].d.staterr & FM10K_RXD_STATUS_DD))
			break;
		mbuf = q->sw_ring[next_dd];
		desc = q->hw_ring[next_dd];
#ifdef RTE_LIBRTE_FM10K_DEBUG_RX
		dump_rxd(&desc);
#endif
		rte_pktmbuf_pkt_len(mbuf) = desc.w.length;
		rte_pktmbuf_data_len(mbuf) = desc.w.length;

		mbuf->ol_flags = 0;
#ifdef RTE_LIBRTE_FM10K_RX_OLFLAGS_ENABLE
		rx_desc_to_ol_flags(mbuf, &desc);
#endif

		mbuf->hash.rss = desc.d.rss;
		/**
		 * Packets in fm10k device always carry at least one VLAN tag.
		 * For those packets coming in without VLAN tag,
		 * the port default VLAN tag will be used.
		 * So, always PKT_RX_VLAN_PKT flag is set and vlan_tci
		 * is valid for each RX packet's mbuf.
		 */
		mbuf->ol_flags |= PKT_RX_VLAN_PKT;
		mbuf->vlan_tci = desc.w.vlan;
		/**
		 * mbuf->vlan_tci_outer is an idle field in fm10k driver,
		 * so it can be selected to store sglort value.
		 */
		if (q->rx_ftag_en)
			mbuf->vlan_tci_outer = rte_le_to_cpu_16(desc.w.sglort);

		rx_pkts[count] = mbuf;
		if (++next_dd == q->nb_desc) {
			next_dd = 0;
			alloc = 1;
		}

		/* Prefetch next mbuf while processing current one. */
		rte_prefetch0(q->sw_ring[next_dd]);

		/*
		 * When next RX descriptor is on a cache-line boundary,
		 * prefetch the next 4 RX descriptors and the next 8 pointers
		 * to mbufs.
		 */
		if ((next_dd & 0x3) == 0) {
			rte_prefetch0(&q->hw_ring[next_dd]);
			rte_prefetch0(&q->sw_ring[next_dd]);
		}
	}

	q->next_dd = next_dd;

	if ((q->next_dd > q->next_trigger) || (alloc == 1)) {
		ret = rte_mempool_get_bulk(q->mp,
					(void **)&q->sw_ring[q->next_alloc],
					q->alloc_thresh);

		if (unlikely(ret != 0)) {
			uint8_t port = q->port_id;
			PMD_RX_LOG(ERR, "Failed to alloc mbuf");
			/*
			 * Need to restore next_dd if we cannot allocate new
			 * buffers to replenish the old ones.
			 */
			q->next_dd = (q->next_dd + q->nb_desc - count) %
								q->nb_desc;
			rte_eth_devices[port].data->rx_mbuf_alloc_failed++;
			return 0;
		}

		for (; q->next_alloc <= q->next_trigger; ++q->next_alloc) {
			mbuf = q->sw_ring[q->next_alloc];

			/* setup static mbuf fields */
			fm10k_pktmbuf_reset(mbuf, q->port_id);

			/* write descriptor */
			desc.q.pkt_addr = MBUF_DMA_ADDR_DEFAULT(mbuf);
			desc.q.hdr_addr = MBUF_DMA_ADDR_DEFAULT(mbuf);
			q->hw_ring[q->next_alloc] = desc;
		}
		FM10K_PCI_REG_WRITE(q->tail_ptr, q->next_trigger);
		q->next_trigger += q->alloc_thresh;
		if (q->next_trigger >= q->nb_desc) {
			q->next_trigger = q->alloc_thresh - 1;
			q->next_alloc = 0;
		}
	}

	return count;
}

uint16_t
fm10k_recv_scattered_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
				uint16_t nb_pkts)
{
	struct rte_mbuf *mbuf;
	union fm10k_rx_desc desc;
	struct fm10k_rx_queue *q = rx_queue;
	uint16_t count = 0;
	uint16_t nb_rcv, nb_seg;
	int alloc = 0;
	uint16_t next_dd;
	struct rte_mbuf *first_seg = q->pkt_first_seg;
	struct rte_mbuf *last_seg = q->pkt_last_seg;
	int ret;

	next_dd = q->next_dd;
	nb_rcv = 0;

	nb_seg = RTE_MIN(nb_pkts, q->alloc_thresh);
	for (count = 0; count < nb_seg; count++) {
		if (!(q->hw_ring[next_dd].d.staterr & FM10K_RXD_STATUS_DD))
			break;
		mbuf = q->sw_ring[next_dd];
		desc = q->hw_ring[next_dd];
#ifdef RTE_LIBRTE_FM10K_DEBUG_RX
		dump_rxd(&desc);
#endif

		if (++next_dd == q->nb_desc) {
			next_dd = 0;
			alloc = 1;
		}

		/* Prefetch next mbuf while processing current one. */
		rte_prefetch0(q->sw_ring[next_dd]);

		/*
		 * When next RX descriptor is on a cache-line boundary,
		 * prefetch the next 4 RX descriptors and the next 8 pointers
		 * to mbufs.
		 */
		if ((next_dd & 0x3) == 0) {
			rte_prefetch0(&q->hw_ring[next_dd]);
			rte_prefetch0(&q->sw_ring[next_dd]);
		}

		/* Fill data length */
		rte_pktmbuf_data_len(mbuf) = desc.w.length;

		/*
		 * If this is the first buffer of the received packet,
		 * set the pointer to the first mbuf of the packet and
		 * initialize its context.
		 * Otherwise, update the total length and the number of segments
		 * of the current scattered packet, and update the pointer to
		 * the last mbuf of the current packet.
		 */
		if (!first_seg) {
			first_seg = mbuf;
			first_seg->pkt_len = desc.w.length;
		} else {
			first_seg->pkt_len =
					(uint16_t)(first_seg->pkt_len +
					rte_pktmbuf_data_len(mbuf));
			first_seg->nb_segs++;
			last_seg->next = mbuf;
		}

		/*
		 * If this is not the last buffer of the received packet,
		 * update the pointer to the last mbuf of the current scattered
		 * packet and continue to parse the RX ring.
		 */
		if (!(desc.d.staterr & FM10K_RXD_STATUS_EOP)) {
			last_seg = mbuf;
			continue;
		}

		first_seg->ol_flags = 0;
#ifdef RTE_LIBRTE_FM10K_RX_OLFLAGS_ENABLE
		rx_desc_to_ol_flags(first_seg, &desc);
#endif
		first_seg->hash.rss = desc.d.rss;
		/**
		 * Packets in fm10k device always carry at least one VLAN tag.
		 * For those packets coming in without VLAN tag,
		 * the port default VLAN tag will be used.
		 * So, always PKT_RX_VLAN_PKT flag is set and vlan_tci
		 * is valid for each RX packet's mbuf.
		 */
		first_seg->ol_flags |= PKT_RX_VLAN_PKT;
		first_seg->vlan_tci = desc.w.vlan;
		/**
		 * mbuf->vlan_tci_outer is an idle field in fm10k driver,
		 * so it can be selected to store sglort value.
		 */
		if (q->rx_ftag_en)
			first_seg->vlan_tci_outer =
				rte_le_to_cpu_16(desc.w.sglort);

		/* Prefetch data of first segment, if configured to do so. */
		rte_packet_prefetch((char *)first_seg->buf_addr +
			first_seg->data_off);

		/*
		 * Store the mbuf address into the next entry of the array
		 * of returned packets.
		 */
		rx_pkts[nb_rcv++] = first_seg;

		/*
		 * Setup receipt context for a new packet.
		 */
		first_seg = NULL;
	}

	q->next_dd = next_dd;

	if ((q->next_dd > q->next_trigger) || (alloc == 1)) {
		ret = rte_mempool_get_bulk(q->mp,
					(void **)&q->sw_ring[q->next_alloc],
					q->alloc_thresh);

		if (unlikely(ret != 0)) {
			uint8_t port = q->port_id;
			PMD_RX_LOG(ERR, "Failed to alloc mbuf");
			/*
			 * Need to restore next_dd if we cannot allocate new
			 * buffers to replenish the old ones.
			 */
			q->next_dd = (q->next_dd + q->nb_desc - count) %
								q->nb_desc;
			rte_eth_devices[port].data->rx_mbuf_alloc_failed++;
			return 0;
		}

		for (; q->next_alloc <= q->next_trigger; ++q->next_alloc) {
			mbuf = q->sw_ring[q->next_alloc];

			/* setup static mbuf fields */
			fm10k_pktmbuf_reset(mbuf, q->port_id);

			/* write descriptor */
			desc.q.pkt_addr = MBUF_DMA_ADDR_DEFAULT(mbuf);
			desc.q.hdr_addr = MBUF_DMA_ADDR_DEFAULT(mbuf);
			q->hw_ring[q->next_alloc] = desc;
		}
		FM10K_PCI_REG_WRITE(q->tail_ptr, q->next_trigger);
		q->next_trigger += q->alloc_thresh;
		if (q->next_trigger >= q->nb_desc) {
			q->next_trigger = q->alloc_thresh - 1;
			q->next_alloc = 0;
		}
	}

	q->pkt_first_seg = first_seg;
	q->pkt_last_seg = last_seg;

	return nb_rcv;
}

int
fm10k_dev_rx_descriptor_done(void *rx_queue, uint16_t offset)
{
	volatile union fm10k_rx_desc *rxdp;
	struct fm10k_rx_queue *rxq = rx_queue;
	uint16_t desc;
	int ret;

	if (unlikely(offset >= rxq->nb_desc)) {
		PMD_DRV_LOG(ERR, "Invalid RX descriptor offset %u", offset);
		return 0;
	}

	desc = rxq->next_dd + offset;
	if (desc >= rxq->nb_desc)
		desc -= rxq->nb_desc;

	rxdp = &rxq->hw_ring[desc];

	ret = !!(rxdp->w.status &
			rte_cpu_to_le_16(FM10K_RXD_STATUS_DD));

	return ret;
}

/*
 * Free multiple TX mbuf at a time if they are in the same pool
 *
 * @txep: software desc ring index that starts to free
 * @num: number of descs to free
 *
 */
static inline void tx_free_bulk_mbuf(struct rte_mbuf **txep, int num)
{
	struct rte_mbuf *m, *free[RTE_FM10K_TX_MAX_FREE_BUF_SZ];
	int i;
	int nb_free = 0;

	if (unlikely(num == 0))
		return;

	m = __rte_pktmbuf_prefree_seg(txep[0]);
	if (likely(m != NULL)) {
		free[0] = m;
		nb_free = 1;
		for (i = 1; i < num; i++) {
			m = __rte_pktmbuf_prefree_seg(txep[i]);
			if (likely(m != NULL)) {
				if (likely(m->pool == free[0]->pool))
					free[nb_free++] = m;
				else {
					rte_mempool_put_bulk(free[0]->pool,
							(void *)free, nb_free);
					free[0] = m;
					nb_free = 1;
				}
			}
			txep[i] = NULL;
		}
		rte_mempool_put_bulk(free[0]->pool, (void **)free, nb_free);
	} else {
		for (i = 1; i < num; i++) {
			m = __rte_pktmbuf_prefree_seg(txep[i]);
			if (m != NULL)
				rte_mempool_put(m->pool, m);
			txep[i] = NULL;
		}
	}
}

static inline void tx_free_descriptors(struct fm10k_tx_queue *q)
{
	uint16_t next_rs, count = 0;

	next_rs = fifo_peek(&q->rs_tracker);
	if (!(q->hw_ring[next_rs].flags & FM10K_TXD_FLAG_DONE))
		return;

	/* the DONE flag is set on this descriptor so remove the ID
	 * from the RS bit tracker and free the buffers */
	fifo_remove(&q->rs_tracker);

	/* wrap around? if so, free buffers from last_free up to but NOT
	 * including nb_desc */
	if (q->last_free > next_rs) {
		count = q->nb_desc - q->last_free;
		tx_free_bulk_mbuf(&q->sw_ring[q->last_free], count);
		q->last_free = 0;
	}

	/* adjust free descriptor count before the next loop */
	q->nb_free += count + (next_rs + 1 - q->last_free);

	/* free buffers from last_free, up to and including next_rs */
	if (q->last_free <= next_rs) {
		count = next_rs - q->last_free + 1;
		tx_free_bulk_mbuf(&q->sw_ring[q->last_free], count);
		q->last_free += count;
	}

	if (q->last_free == q->nb_desc)
		q->last_free = 0;
}

static inline void tx_xmit_pkt(struct fm10k_tx_queue *q, struct rte_mbuf *mb)
{
	uint16_t last_id;
	uint8_t flags, hdrlen;

	/* always set the LAST flag on the last descriptor used to
	 * transmit the packet */
	flags = FM10K_TXD_FLAG_LAST;
	last_id = q->next_free + mb->nb_segs - 1;
	if (last_id >= q->nb_desc)
		last_id = last_id - q->nb_desc;

	/* but only set the RS flag on the last descriptor if rs_thresh
	 * descriptors will be used since the RS flag was last set */
	if ((q->nb_used + mb->nb_segs) >= q->rs_thresh) {
		flags |= FM10K_TXD_FLAG_RS;
		fifo_insert(&q->rs_tracker, last_id);
		q->nb_used = 0;
	} else {
		q->nb_used = q->nb_used + mb->nb_segs;
	}

	q->nb_free -= mb->nb_segs;

	q->hw_ring[q->next_free].flags = 0;
	if (q->tx_ftag_en)
		q->hw_ring[q->next_free].flags |= FM10K_TXD_FLAG_FTAG;
	/* set checksum flags on first descriptor of packet. SCTP checksum
	 * offload is not supported, but we do not explicitly check for this
	 * case in favor of greatly simplified processing. */
	if (mb->ol_flags & (PKT_TX_IP_CKSUM | PKT_TX_L4_MASK | PKT_TX_TCP_SEG))
		q->hw_ring[q->next_free].flags |= FM10K_TXD_FLAG_CSUM;

	/* set vlan if requested */
	if (mb->ol_flags & PKT_TX_VLAN_PKT)
		q->hw_ring[q->next_free].vlan = mb->vlan_tci;

	q->sw_ring[q->next_free] = mb;
	q->hw_ring[q->next_free].buffer_addr =
			rte_cpu_to_le_64(MBUF_DMA_ADDR(mb));
	q->hw_ring[q->next_free].buflen =
			rte_cpu_to_le_16(rte_pktmbuf_data_len(mb));

	if (mb->ol_flags & PKT_TX_TCP_SEG) {
		hdrlen = mb->outer_l2_len + mb->outer_l3_len + mb->l2_len +
			mb->l3_len + mb->l4_len;
		if (q->hw_ring[q->next_free].flags & FM10K_TXD_FLAG_FTAG)
			hdrlen += sizeof(struct fm10k_ftag);

		if (likely((hdrlen >= FM10K_TSO_MIN_HEADERLEN) &&
				(hdrlen <= FM10K_TSO_MAX_HEADERLEN) &&
				(mb->tso_segsz >= FM10K_TSO_MINMSS))) {
			q->hw_ring[q->next_free].mss = mb->tso_segsz;
			q->hw_ring[q->next_free].hdrlen = hdrlen;
		}
	}

	if (++q->next_free == q->nb_desc)
		q->next_free = 0;

	/* fill up the rings */
	for (mb = mb->next; mb != NULL; mb = mb->next) {
		q->sw_ring[q->next_free] = mb;
		q->hw_ring[q->next_free].buffer_addr =
				rte_cpu_to_le_64(MBUF_DMA_ADDR(mb));
		q->hw_ring[q->next_free].buflen =
				rte_cpu_to_le_16(rte_pktmbuf_data_len(mb));
		q->hw_ring[q->next_free].flags = 0;
		if (++q->next_free == q->nb_desc)
			q->next_free = 0;
	}

	q->hw_ring[last_id].flags |= flags;
}

uint16_t
fm10k_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
	uint16_t nb_pkts)
{
	struct fm10k_tx_queue *q = tx_queue;
	struct rte_mbuf *mb;
	uint16_t count;

	for (count = 0; count < nb_pkts; ++count) {
		mb = tx_pkts[count];

		/* running low on descriptors? try to free some... */
		if (q->nb_free < q->free_thresh)
			tx_free_descriptors(q);

		/* make sure there are enough free descriptors to transmit the
		 * entire packet before doing anything */
		if (q->nb_free < mb->nb_segs)
			break;

		/* sanity check to make sure the mbuf is valid */
		if ((mb->nb_segs == 0) ||
		    ((mb->nb_segs > 1) && (mb->next == NULL)))
			break;

		/* process the packet */
		tx_xmit_pkt(q, mb);
	}

	/* update the tail pointer if any packets were processed */
	if (likely(count > 0))
		FM10K_PCI_REG_WRITE(q->tail_ptr, q->next_free);

	return count;
}