summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
blob: bfe95ce0bd7f37e6915ce630e64896b1d50753c3 (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
792
793
// SPDX-License-Identifier: GPL-2.0
/* Copyright(c) 2018 Intel Corporation. */

#include <linux/bpf_trace.h>
#include <net/xdp_sock.h>
#include <net/xdp.h>

#include "ixgbe.h"
#include "ixgbe_txrx_common.h"

struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter,
				struct ixgbe_ring *ring)
{
	bool xdp_on = READ_ONCE(adapter->xdp_prog);
	int qid = ring->ring_idx;

	if (!adapter->xsk_umems || !adapter->xsk_umems[qid] ||
	    qid >= adapter->num_xsk_umems || !xdp_on)
		return NULL;

	return adapter->xsk_umems[qid];
}

static int ixgbe_alloc_xsk_umems(struct ixgbe_adapter *adapter)
{
	if (adapter->xsk_umems)
		return 0;

	adapter->num_xsk_umems_used = 0;
	adapter->num_xsk_umems = adapter->num_rx_queues;
	adapter->xsk_umems = kcalloc(adapter->num_xsk_umems,
				     sizeof(*adapter->xsk_umems),
				     GFP_KERNEL);
	if (!adapter->xsk_umems) {
		adapter->num_xsk_umems = 0;
		return -ENOMEM;
	}

	return 0;
}

static int ixgbe_add_xsk_umem(struct ixgbe_adapter *adapter,
			      struct xdp_umem *umem,
			      u16 qid)
{
	int err;

	err = ixgbe_alloc_xsk_umems(adapter);
	if (err)
		return err;

	adapter->xsk_umems[qid] = umem;
	adapter->num_xsk_umems_used++;

	return 0;
}

static void ixgbe_remove_xsk_umem(struct ixgbe_adapter *adapter, u16 qid)
{
	adapter->xsk_umems[qid] = NULL;
	adapter->num_xsk_umems_used--;

	if (adapter->num_xsk_umems == 0) {
		kfree(adapter->xsk_umems);
		adapter->xsk_umems = NULL;
		adapter->num_xsk_umems = 0;
	}
}

static int ixgbe_xsk_umem_dma_map(struct ixgbe_adapter *adapter,
				  struct xdp_umem *umem)
{
	struct device *dev = &adapter->pdev->dev;
	unsigned int i, j;
	dma_addr_t dma;

	for (i = 0; i < umem->npgs; i++) {
		dma = dma_map_page_attrs(dev, umem->pgs[i], 0, PAGE_SIZE,
					 DMA_BIDIRECTIONAL, IXGBE_RX_DMA_ATTR);
		if (dma_mapping_error(dev, dma))
			goto out_unmap;

		umem->pages[i].dma = dma;
	}

	return 0;

out_unmap:
	for (j = 0; j < i; j++) {
		dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE,
				     DMA_BIDIRECTIONAL, IXGBE_RX_DMA_ATTR);
		umem->pages[i].dma = 0;
	}

	return -1;
}

static void ixgbe_xsk_umem_dma_unmap(struct ixgbe_adapter *adapter,
				     struct xdp_umem *umem)
{
	struct device *dev = &adapter->pdev->dev;
	unsigned int i;

	for (i = 0; i < umem->npgs; i++) {
		dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE,
				     DMA_BIDIRECTIONAL, IXGBE_RX_DMA_ATTR);

		umem->pages[i].dma = 0;
	}
}

static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter,
				 struct xdp_umem *umem,
				 u16 qid)
{
	struct xdp_umem_fq_reuse *reuseq;
	bool if_running;
	int err;

	if (qid >= adapter->num_rx_queues)
		return -EINVAL;

	if (adapter->xsk_umems) {
		if (qid >= adapter->num_xsk_umems)
			return -EINVAL;
		if (adapter->xsk_umems[qid])
			return -EBUSY;
	}

	reuseq = xsk_reuseq_prepare(adapter->rx_ring[0]->count);
	if (!reuseq)
		return -ENOMEM;

	xsk_reuseq_free(xsk_reuseq_swap(umem, reuseq));

	err = ixgbe_xsk_umem_dma_map(adapter, umem);
	if (err)
		return err;

	if_running = netif_running(adapter->netdev) &&
		     READ_ONCE(adapter->xdp_prog);

	if (if_running)
		ixgbe_txrx_ring_disable(adapter, qid);

	err = ixgbe_add_xsk_umem(adapter, umem, qid);
	if (err)
		return err;

	if (if_running) {
		ixgbe_txrx_ring_enable(adapter, qid);

		/* Kick start the NAPI context so that receiving will start */
		err = ixgbe_xsk_async_xmit(adapter->netdev, qid);
		if (err)
			return err;
	}

	return 0;
}

static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid)
{
	bool if_running;

	if (!adapter->xsk_umems || qid >= adapter->num_xsk_umems ||
	    !adapter->xsk_umems[qid])
		return -EINVAL;

	if_running = netif_running(adapter->netdev) &&
		     READ_ONCE(adapter->xdp_prog);

	if (if_running)
		ixgbe_txrx_ring_disable(adapter, qid);

	ixgbe_xsk_umem_dma_unmap(adapter, adapter->xsk_umems[qid]);
	ixgbe_remove_xsk_umem(adapter, qid);

	if (if_running)
		ixgbe_txrx_ring_enable(adapter, qid);

	return 0;
}

int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem,
			 u16 qid)
{
	return umem ? ixgbe_xsk_umem_enable(adapter, umem, qid) :
		ixgbe_xsk_umem_disable(adapter, qid);
}

static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
			    struct ixgbe_ring *rx_ring,
			    struct xdp_buff *xdp)
{
	int err, result = IXGBE_XDP_PASS;
	struct bpf_prog *xdp_prog;
	struct xdp_frame *xdpf;
	u32 act;

	rcu_read_lock();
	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
	act = bpf_prog_run_xdp(xdp_prog, xdp);
	xdp->handle += xdp->data - xdp->data_hard_start;
	switch (act) {
	case XDP_PASS:
		break;
	case XDP_TX:
		xdpf = convert_to_xdp_frame(xdp);
		if (unlikely(!xdpf)) {
			result = IXGBE_XDP_CONSUMED;
			break;
		}
		result = ixgbe_xmit_xdp_ring(adapter, xdpf);
		break;
	case XDP_REDIRECT:
		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
		result = !err ? IXGBE_XDP_REDIR : IXGBE_XDP_CONSUMED;
		break;
	default:
		bpf_warn_invalid_xdp_action(act);
		/* fallthrough */
	case XDP_ABORTED:
		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
		/* fallthrough -- handle aborts by dropping packet */
	case XDP_DROP:
		result = IXGBE_XDP_CONSUMED;
		break;
	}
	rcu_read_unlock();
	return result;
}

static struct
ixgbe_rx_buffer *ixgbe_get_rx_buffer_zc(struct ixgbe_ring *rx_ring,
					unsigned int size)
{
	struct ixgbe_rx_buffer *bi;

	bi = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];

	/* we are reusing so sync this buffer for CPU use */
	dma_sync_single_range_for_cpu(rx_ring->dev,
				      bi->dma, 0,
				      size,
				      DMA_BIDIRECTIONAL);

	return bi;
}

static void ixgbe_reuse_rx_buffer_zc(struct ixgbe_ring *rx_ring,
				     struct ixgbe_rx_buffer *obi)
{
	unsigned long mask = (unsigned long)rx_ring->xsk_umem->chunk_mask;
	u64 hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM;
	u16 nta = rx_ring->next_to_alloc;
	struct ixgbe_rx_buffer *nbi;

	nbi = &rx_ring->rx_buffer_info[rx_ring->next_to_alloc];
	/* update, and store next to alloc */
	nta++;
	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;

	/* transfer page from old buffer to new buffer */
	nbi->dma = obi->dma & mask;
	nbi->dma += hr;

	nbi->addr = (void *)((unsigned long)obi->addr & mask);
	nbi->addr += hr;

	nbi->handle = obi->handle & mask;
	nbi->handle += rx_ring->xsk_umem->headroom;

	obi->addr = NULL;
	obi->skb = NULL;
}

void ixgbe_zca_free(struct zero_copy_allocator *alloc, unsigned long handle)
{
	struct ixgbe_rx_buffer *bi;
	struct ixgbe_ring *rx_ring;
	u64 hr, mask;
	u16 nta;

	rx_ring = container_of(alloc, struct ixgbe_ring, zca);
	hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM;
	mask = rx_ring->xsk_umem->chunk_mask;

	nta = rx_ring->next_to_alloc;
	bi = rx_ring->rx_buffer_info;

	nta++;
	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;

	handle &= mask;

	bi->dma = xdp_umem_get_dma(rx_ring->xsk_umem, handle);
	bi->dma += hr;

	bi->addr = xdp_umem_get_data(rx_ring->xsk_umem, handle);
	bi->addr += hr;

	bi->handle = (u64)handle + rx_ring->xsk_umem->headroom;
}

static bool ixgbe_alloc_buffer_zc(struct ixgbe_ring *rx_ring,
				  struct ixgbe_rx_buffer *bi)
{
	struct xdp_umem *umem = rx_ring->xsk_umem;
	void *addr = bi->addr;
	u64 handle, hr;

	if (addr)
		return true;

	if (!xsk_umem_peek_addr(umem, &handle)) {
		rx_ring->rx_stats.alloc_rx_page_failed++;
		return false;
	}

	hr = umem->headroom + XDP_PACKET_HEADROOM;

	bi->dma = xdp_umem_get_dma(umem, handle);
	bi->dma += hr;

	bi->addr = xdp_umem_get_data(umem, handle);
	bi->addr += hr;

	bi->handle = handle + umem->headroom;

	xsk_umem_discard_addr(umem);
	return true;
}

static bool ixgbe_alloc_buffer_slow_zc(struct ixgbe_ring *rx_ring,
				       struct ixgbe_rx_buffer *bi)
{
	struct xdp_umem *umem = rx_ring->xsk_umem;
	u64 handle, hr;

	if (!xsk_umem_peek_addr_rq(umem, &handle)) {
		rx_ring->rx_stats.alloc_rx_page_failed++;
		return false;
	}

	handle &= rx_ring->xsk_umem->chunk_mask;

	hr = umem->headroom + XDP_PACKET_HEADROOM;

	bi->dma = xdp_umem_get_dma(umem, handle);
	bi->dma += hr;

	bi->addr = xdp_umem_get_data(umem, handle);
	bi->addr += hr;

	bi->handle = handle + umem->headroom;

	xsk_umem_discard_addr_rq(umem);
	return true;
}

static __always_inline bool
__ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count,
			    bool alloc(struct ixgbe_ring *rx_ring,
				       struct ixgbe_rx_buffer *bi))
{
	union ixgbe_adv_rx_desc *rx_desc;
	struct ixgbe_rx_buffer *bi;
	u16 i = rx_ring->next_to_use;
	bool ok = true;

	/* nothing to do */
	if (!cleaned_count)
		return true;

	rx_desc = IXGBE_RX_DESC(rx_ring, i);
	bi = &rx_ring->rx_buffer_info[i];
	i -= rx_ring->count;

	do {
		if (!alloc(rx_ring, bi)) {
			ok = false;
			break;
		}

		/* sync the buffer for use by the device */
		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
						 bi->page_offset,
						 rx_ring->rx_buf_len,
						 DMA_BIDIRECTIONAL);

		/* Refresh the desc even if buffer_addrs didn't change
		 * because each write-back erases this info.
		 */
		rx_desc->read.pkt_addr = cpu_to_le64(bi->dma);

		rx_desc++;
		bi++;
		i++;
		if (unlikely(!i)) {
			rx_desc = IXGBE_RX_DESC(rx_ring, 0);
			bi = rx_ring->rx_buffer_info;
			i -= rx_ring->count;
		}

		/* clear the length for the next_to_use descriptor */
		rx_desc->wb.upper.length = 0;

		cleaned_count--;
	} while (cleaned_count);

	i += rx_ring->count;

	if (rx_ring->next_to_use != i) {
		rx_ring->next_to_use = i;

		/* update next to alloc since we have filled the ring */
		rx_ring->next_to_alloc = i;

		/* Force memory writes to complete before letting h/w
		 * know there are new descriptors to fetch.  (Only
		 * applicable for weak-ordered memory model archs,
		 * such as IA-64).
		 */
		wmb();
		writel(i, rx_ring->tail);
	}

	return ok;
}

void ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 count)
{
	__ixgbe_alloc_rx_buffers_zc(rx_ring, count,
				    ixgbe_alloc_buffer_slow_zc);
}

static bool ixgbe_alloc_rx_buffers_fast_zc(struct ixgbe_ring *rx_ring,
					   u16 count)
{
	return __ixgbe_alloc_rx_buffers_zc(rx_ring, count,
					   ixgbe_alloc_buffer_zc);
}

static struct sk_buff *ixgbe_construct_skb_zc(struct ixgbe_ring *rx_ring,
					      struct ixgbe_rx_buffer *bi,
					      struct xdp_buff *xdp)
{
	unsigned int metasize = xdp->data - xdp->data_meta;
	unsigned int datasize = xdp->data_end - xdp->data;
	struct sk_buff *skb;

	/* allocate a skb to store the frags */
	skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
			       xdp->data_end - xdp->data_hard_start,
			       GFP_ATOMIC | __GFP_NOWARN);
	if (unlikely(!skb))
		return NULL;

	skb_reserve(skb, xdp->data - xdp->data_hard_start);
	memcpy(__skb_put(skb, datasize), xdp->data, datasize);
	if (metasize)
		skb_metadata_set(skb, metasize);

	ixgbe_reuse_rx_buffer_zc(rx_ring, bi);
	return skb;
}

static void ixgbe_inc_ntc(struct ixgbe_ring *rx_ring)
{
	u32 ntc = rx_ring->next_to_clean + 1;

	ntc = (ntc < rx_ring->count) ? ntc : 0;
	rx_ring->next_to_clean = ntc;
	prefetch(IXGBE_RX_DESC(rx_ring, ntc));
}

int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
			  struct ixgbe_ring *rx_ring,
			  const int budget)
{
	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
	struct ixgbe_adapter *adapter = q_vector->adapter;
	u16 cleaned_count = ixgbe_desc_unused(rx_ring);
	unsigned int xdp_res, xdp_xmit = 0;
	bool failure = false;
	struct sk_buff *skb;
	struct xdp_buff xdp;

	xdp.rxq = &rx_ring->xdp_rxq;

	while (likely(total_rx_packets < budget)) {
		union ixgbe_adv_rx_desc *rx_desc;
		struct ixgbe_rx_buffer *bi;
		unsigned int size;

		/* return some buffers to hardware, one at a time is too slow */
		if (cleaned_count >= IXGBE_RX_BUFFER_WRITE) {
			failure = failure ||
				  !ixgbe_alloc_rx_buffers_fast_zc(rx_ring,
								 cleaned_count);
			cleaned_count = 0;
		}

		rx_desc = IXGBE_RX_DESC(rx_ring, rx_ring->next_to_clean);
		size = le16_to_cpu(rx_desc->wb.upper.length);
		if (!size)
			break;

		/* This memory barrier is needed to keep us from reading
		 * any other fields out of the rx_desc until we know the
		 * descriptor has been written back
		 */
		dma_rmb();

		bi = ixgbe_get_rx_buffer_zc(rx_ring, size);

		if (unlikely(!ixgbe_test_staterr(rx_desc,
						 IXGBE_RXD_STAT_EOP))) {
			struct ixgbe_rx_buffer *next_bi;

			ixgbe_reuse_rx_buffer_zc(rx_ring, bi);
			ixgbe_inc_ntc(rx_ring);
			next_bi =
			       &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
			next_bi->skb = ERR_PTR(-EINVAL);
			continue;
		}

		if (unlikely(bi->skb)) {
			ixgbe_reuse_rx_buffer_zc(rx_ring, bi);
			ixgbe_inc_ntc(rx_ring);
			continue;
		}

		xdp.data = bi->addr;
		xdp.data_meta = xdp.data;
		xdp.data_hard_start = xdp.data - XDP_PACKET_HEADROOM;
		xdp.data_end = xdp.data + size;
		xdp.handle = bi->handle;

		xdp_res = ixgbe_run_xdp_zc(adapter, rx_ring, &xdp);

		if (xdp_res) {
			if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) {
				xdp_xmit |= xdp_res;
				bi->addr = NULL;
				bi->skb = NULL;
			} else {
				ixgbe_reuse_rx_buffer_zc(rx_ring, bi);
			}
			total_rx_packets++;
			total_rx_bytes += size;

			cleaned_count++;
			ixgbe_inc_ntc(rx_ring);
			continue;
		}

		/* XDP_PASS path */
		skb = ixgbe_construct_skb_zc(rx_ring, bi, &xdp);
		if (!skb) {
			rx_ring->rx_stats.alloc_rx_buff_failed++;
			break;
		}

		cleaned_count++;
		ixgbe_inc_ntc(rx_ring);

		if (eth_skb_pad(skb))
			continue;

		total_rx_bytes += skb->len;
		total_rx_packets++;

		ixgbe_process_skb_fields(rx_ring, rx_desc, skb);
		ixgbe_rx_skb(q_vector, skb);
	}

	if (xdp_xmit & IXGBE_XDP_REDIR)
		xdp_do_flush_map();

	if (xdp_xmit & IXGBE_XDP_TX) {
		struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()];

		/* Force memory writes to complete before letting h/w
		 * know there are new descriptors to fetch.
		 */
		wmb();
		writel(ring->next_to_use, ring->tail);
	}

	u64_stats_update_begin(&rx_ring->syncp);
	rx_ring->stats.packets += total_rx_packets;
	rx_ring->stats.bytes += total_rx_bytes;
	u64_stats_update_end(&rx_ring->syncp);
	q_vector->rx.total_packets += total_rx_packets;
	q_vector->rx.total_bytes += total_rx_bytes;

	return failure ? budget : (int)total_rx_packets;
}

void ixgbe_xsk_clean_rx_ring(struct ixgbe_ring *rx_ring)
{
	u16 i = rx_ring->next_to_clean;
	struct ixgbe_rx_buffer *bi = &rx_ring->rx_buffer_info[i];

	while (i != rx_ring->next_to_alloc) {
		xsk_umem_fq_reuse(rx_ring->xsk_umem, bi->handle);
		i++;
		bi++;
		if (i == rx_ring->count) {
			i = 0;
			bi = rx_ring->rx_buffer_info;
		}
	}
}

static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
{
	union ixgbe_adv_tx_desc *tx_desc = NULL;
	struct ixgbe_tx_buffer *tx_bi;
	bool work_done = true;
	u32 len, cmd_type;
	dma_addr_t dma;

	while (budget-- > 0) {
		if (unlikely(!ixgbe_desc_unused(xdp_ring)) ||
		    !netif_carrier_ok(xdp_ring->netdev)) {
			work_done = false;
			break;
		}

		if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &dma, &len))
			break;

		dma_sync_single_for_device(xdp_ring->dev, dma, len,
					   DMA_BIDIRECTIONAL);

		tx_bi = &xdp_ring->tx_buffer_info[xdp_ring->next_to_use];
		tx_bi->bytecount = len;
		tx_bi->xdpf = NULL;

		tx_desc = IXGBE_TX_DESC(xdp_ring, xdp_ring->next_to_use);
		tx_desc->read.buffer_addr = cpu_to_le64(dma);

		/* put descriptor type bits */
		cmd_type = IXGBE_ADVTXD_DTYP_DATA |
			   IXGBE_ADVTXD_DCMD_DEXT |
			   IXGBE_ADVTXD_DCMD_IFCS;
		cmd_type |= len | IXGBE_TXD_CMD;
		tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type);
		tx_desc->read.olinfo_status =
			cpu_to_le32(len << IXGBE_ADVTXD_PAYLEN_SHIFT);

		xdp_ring->next_to_use++;
		if (xdp_ring->next_to_use == xdp_ring->count)
			xdp_ring->next_to_use = 0;
	}

	if (tx_desc) {
		ixgbe_xdp_ring_update_tail(xdp_ring);
		xsk_umem_consume_tx_done(xdp_ring->xsk_umem);
	}

	return !!budget && work_done;
}

static void ixgbe_clean_xdp_tx_buffer(struct ixgbe_ring *tx_ring,
				      struct ixgbe_tx_buffer *tx_bi)
{
	xdp_return_frame(tx_bi->xdpf);
	dma_unmap_single(tx_ring->dev,
			 dma_unmap_addr(tx_bi, dma),
			 dma_unmap_len(tx_bi, len), DMA_TO_DEVICE);
	dma_unmap_len_set(tx_bi, len, 0);
}

bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector,
			    struct ixgbe_ring *tx_ring, int napi_budget)
{
	unsigned int total_packets = 0, total_bytes = 0;
	u32 i = tx_ring->next_to_clean, xsk_frames = 0;
	unsigned int budget = q_vector->tx.work_limit;
	struct xdp_umem *umem = tx_ring->xsk_umem;
	union ixgbe_adv_tx_desc *tx_desc;
	struct ixgbe_tx_buffer *tx_bi;
	bool xmit_done;

	tx_bi = &tx_ring->tx_buffer_info[i];
	tx_desc = IXGBE_TX_DESC(tx_ring, i);
	i -= tx_ring->count;

	do {
		if (!(tx_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD)))
			break;

		total_bytes += tx_bi->bytecount;
		total_packets += tx_bi->gso_segs;

		if (tx_bi->xdpf)
			ixgbe_clean_xdp_tx_buffer(tx_ring, tx_bi);
		else
			xsk_frames++;

		tx_bi->xdpf = NULL;
		total_bytes += tx_bi->bytecount;

		tx_bi++;
		tx_desc++;
		i++;
		if (unlikely(!i)) {
			i -= tx_ring->count;
			tx_bi = tx_ring->tx_buffer_info;
			tx_desc = IXGBE_TX_DESC(tx_ring, 0);
		}

		/* issue prefetch for next Tx descriptor */
		prefetch(tx_desc);

		/* update budget accounting */
		budget--;
	} while (likely(budget));

	i += tx_ring->count;
	tx_ring->next_to_clean = i;

	u64_stats_update_begin(&tx_ring->syncp);
	tx_ring->stats.bytes += total_bytes;
	tx_ring->stats.packets += total_packets;
	u64_stats_update_end(&tx_ring->syncp);
	q_vector->tx.total_bytes += total_bytes;
	q_vector->tx.total_packets += total_packets;

	if (xsk_frames)
		xsk_umem_complete_tx(umem, xsk_frames);

	xmit_done = ixgbe_xmit_zc(tx_ring, q_vector->tx.work_limit);
	return budget > 0 && xmit_done;
}

int ixgbe_xsk_async_xmit(struct net_device *dev, u32 qid)
{
	struct ixgbe_adapter *adapter = netdev_priv(dev);
	struct ixgbe_ring *ring;

	if (test_bit(__IXGBE_DOWN, &adapter->state))
		return -ENETDOWN;

	if (!READ_ONCE(adapter->xdp_prog))
		return -ENXIO;

	if (qid >= adapter->num_xdp_queues)
		return -ENXIO;

	if (!adapter->xsk_umems || !adapter->xsk_umems[qid])
		return -ENXIO;

	ring = adapter->xdp_ring[qid];
	if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) {
		u64 eics = BIT_ULL(ring->q_vector->v_idx);

		ixgbe_irq_rearm_queues(adapter, eics);
	}

	return 0;
}

void ixgbe_xsk_clean_tx_ring(struct ixgbe_ring *tx_ring)
{
	u16 ntc = tx_ring->next_to_clean, ntu = tx_ring->next_to_use;
	struct xdp_umem *umem = tx_ring->xsk_umem;
	struct ixgbe_tx_buffer *tx_bi;
	u32 xsk_frames = 0;

	while (ntc != ntu) {
		tx_bi = &tx_ring->tx_buffer_info[ntc];

		if (tx_bi->xdpf)
			ixgbe_clean_xdp_tx_buffer(tx_ring, tx_bi);
		else
			xsk_frames++;

		tx_bi->xdpf = NULL;

		ntc++;
		if (ntc == tx_ring->count)
			ntc = 0;
	}

	if (xsk_frames)
		xsk_umem_complete_tx(umem, xsk_frames);
}