summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/intel/ice/ice_xsk.c
blob: 2b1873061912dfd5837b2add8243e0f15c05f497 (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
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019, Intel Corporation. */

#include <linux/bpf_trace.h>
#include <net/xdp_sock_drv.h>
#include <net/xdp.h>
#include "ice.h"
#include "ice_base.h"
#include "ice_type.h"
#include "ice_xsk.h"
#include "ice_txrx.h"
#include "ice_txrx_lib.h"
#include "ice_lib.h"

/**
 * ice_qp_reset_stats - Resets all stats for rings of given index
 * @vsi: VSI that contains rings of interest
 * @q_idx: ring index in array
 */
static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx)
{
	memset(&vsi->rx_rings[q_idx]->rx_stats, 0,
	       sizeof(vsi->rx_rings[q_idx]->rx_stats));
	memset(&vsi->tx_rings[q_idx]->stats, 0,
	       sizeof(vsi->tx_rings[q_idx]->stats));
	if (ice_is_xdp_ena_vsi(vsi))
		memset(&vsi->xdp_rings[q_idx]->stats, 0,
		       sizeof(vsi->xdp_rings[q_idx]->stats));
}

/**
 * ice_qp_clean_rings - Cleans all the rings of a given index
 * @vsi: VSI that contains rings of interest
 * @q_idx: ring index in array
 */
static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx)
{
	ice_clean_tx_ring(vsi->tx_rings[q_idx]);
	if (ice_is_xdp_ena_vsi(vsi)) {
		synchronize_rcu();
		ice_clean_tx_ring(vsi->xdp_rings[q_idx]);
	}
	ice_clean_rx_ring(vsi->rx_rings[q_idx]);
}

/**
 * ice_qvec_toggle_napi - Enables/disables NAPI for a given q_vector
 * @vsi: VSI that has netdev
 * @q_vector: q_vector that has NAPI context
 * @enable: true for enable, false for disable
 */
static void
ice_qvec_toggle_napi(struct ice_vsi *vsi, struct ice_q_vector *q_vector,
		     bool enable)
{
	if (!vsi->netdev || !q_vector)
		return;

	if (enable)
		napi_enable(&q_vector->napi);
	else
		napi_disable(&q_vector->napi);
}

/**
 * ice_qvec_dis_irq - Mask off queue interrupt generation on given ring
 * @vsi: the VSI that contains queue vector being un-configured
 * @rx_ring: Rx ring that will have its IRQ disabled
 * @q_vector: queue vector
 */
static void
ice_qvec_dis_irq(struct ice_vsi *vsi, struct ice_ring *rx_ring,
		 struct ice_q_vector *q_vector)
{
	struct ice_pf *pf = vsi->back;
	struct ice_hw *hw = &pf->hw;
	int base = vsi->base_vector;
	u16 reg;
	u32 val;

	/* QINT_TQCTL is being cleared in ice_vsi_stop_tx_ring, so handle
	 * here only QINT_RQCTL
	 */
	reg = rx_ring->reg_idx;
	val = rd32(hw, QINT_RQCTL(reg));
	val &= ~QINT_RQCTL_CAUSE_ENA_M;
	wr32(hw, QINT_RQCTL(reg), val);

	if (q_vector) {
		u16 v_idx = q_vector->v_idx;

		wr32(hw, GLINT_DYN_CTL(q_vector->reg_idx), 0);
		ice_flush(hw);
		synchronize_irq(pf->msix_entries[v_idx + base].vector);
	}
}

/**
 * ice_qvec_cfg_msix - Enable IRQ for given queue vector
 * @vsi: the VSI that contains queue vector
 * @q_vector: queue vector
 */
static void
ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
{
	u16 reg_idx = q_vector->reg_idx;
	struct ice_pf *pf = vsi->back;
	struct ice_hw *hw = &pf->hw;
	struct ice_ring *ring;

	ice_cfg_itr(hw, q_vector);

	ice_for_each_ring(ring, q_vector->tx)
		ice_cfg_txq_interrupt(vsi, ring->reg_idx, reg_idx,
				      q_vector->tx.itr_idx);

	ice_for_each_ring(ring, q_vector->rx)
		ice_cfg_rxq_interrupt(vsi, ring->reg_idx, reg_idx,
				      q_vector->rx.itr_idx);

	ice_flush(hw);
}

/**
 * ice_qvec_ena_irq - Enable IRQ for given queue vector
 * @vsi: the VSI that contains queue vector
 * @q_vector: queue vector
 */
static void ice_qvec_ena_irq(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
{
	struct ice_pf *pf = vsi->back;
	struct ice_hw *hw = &pf->hw;

	ice_irq_dynamic_ena(hw, vsi, q_vector);

	ice_flush(hw);
}

/**
 * ice_qp_dis - Disables a queue pair
 * @vsi: VSI of interest
 * @q_idx: ring index in array
 *
 * Returns 0 on success, negative on failure.
 */
static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
{
	struct ice_txq_meta txq_meta = { };
	struct ice_ring *tx_ring, *rx_ring;
	struct ice_q_vector *q_vector;
	int timeout = 50;
	int err;

	if (q_idx >= vsi->num_rxq || q_idx >= vsi->num_txq)
		return -EINVAL;

	tx_ring = vsi->tx_rings[q_idx];
	rx_ring = vsi->rx_rings[q_idx];
	q_vector = rx_ring->q_vector;

	while (test_and_set_bit(ICE_CFG_BUSY, vsi->state)) {
		timeout--;
		if (!timeout)
			return -EBUSY;
		usleep_range(1000, 2000);
	}
	netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx));

	ice_qvec_dis_irq(vsi, rx_ring, q_vector);

	ice_fill_txq_meta(vsi, tx_ring, &txq_meta);
	err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, tx_ring, &txq_meta);
	if (err)
		return err;
	if (ice_is_xdp_ena_vsi(vsi)) {
		struct ice_ring *xdp_ring = vsi->xdp_rings[q_idx];

		memset(&txq_meta, 0, sizeof(txq_meta));
		ice_fill_txq_meta(vsi, xdp_ring, &txq_meta);
		err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, xdp_ring,
					   &txq_meta);
		if (err)
			return err;
	}
	err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true);
	if (err)
		return err;

	ice_qvec_toggle_napi(vsi, q_vector, false);
	ice_qp_clean_rings(vsi, q_idx);
	ice_qp_reset_stats(vsi, q_idx);

	return 0;
}

/**
 * ice_qp_ena - Enables a queue pair
 * @vsi: VSI of interest
 * @q_idx: ring index in array
 *
 * Returns 0 on success, negative on failure.
 */
static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
{
	struct ice_aqc_add_tx_qgrp *qg_buf;
	struct ice_ring *tx_ring, *rx_ring;
	struct ice_q_vector *q_vector;
	u16 size;
	int err;

	if (q_idx >= vsi->num_rxq || q_idx >= vsi->num_txq)
		return -EINVAL;

	size = struct_size(qg_buf, txqs, 1);
	qg_buf = kzalloc(size, GFP_KERNEL);
	if (!qg_buf)
		return -ENOMEM;

	qg_buf->num_txqs = 1;

	tx_ring = vsi->tx_rings[q_idx];
	rx_ring = vsi->rx_rings[q_idx];
	q_vector = rx_ring->q_vector;

	err = ice_vsi_cfg_txq(vsi, tx_ring, qg_buf);
	if (err)
		goto free_buf;

	if (ice_is_xdp_ena_vsi(vsi)) {
		struct ice_ring *xdp_ring = vsi->xdp_rings[q_idx];

		memset(qg_buf, 0, size);
		qg_buf->num_txqs = 1;
		err = ice_vsi_cfg_txq(vsi, xdp_ring, qg_buf);
		if (err)
			goto free_buf;
		ice_set_ring_xdp(xdp_ring);
		xdp_ring->xsk_pool = ice_xsk_pool(xdp_ring);
	}

	err = ice_vsi_cfg_rxq(rx_ring);
	if (err)
		goto free_buf;

	ice_qvec_cfg_msix(vsi, q_vector);

	err = ice_vsi_ctrl_one_rx_ring(vsi, true, q_idx, true);
	if (err)
		goto free_buf;

	clear_bit(ICE_CFG_BUSY, vsi->state);
	ice_qvec_toggle_napi(vsi, q_vector, true);
	ice_qvec_ena_irq(vsi, q_vector);

	netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
free_buf:
	kfree(qg_buf);
	return err;
}

/**
 * ice_xsk_pool_disable - disable a buffer pool region
 * @vsi: Current VSI
 * @qid: queue ID
 *
 * Returns 0 on success, negative on failure
 */
static int ice_xsk_pool_disable(struct ice_vsi *vsi, u16 qid)
{
	struct xsk_buff_pool *pool = xsk_get_pool_from_qid(vsi->netdev, qid);

	if (!pool)
		return -EINVAL;

	clear_bit(qid, vsi->af_xdp_zc_qps);
	xsk_pool_dma_unmap(pool, ICE_RX_DMA_ATTR);

	return 0;
}

/**
 * ice_xsk_pool_enable - enable a buffer pool region
 * @vsi: Current VSI
 * @pool: pointer to a requested buffer pool region
 * @qid: queue ID
 *
 * Returns 0 on success, negative on failure
 */
static int
ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
{
	int err;

	if (vsi->type != ICE_VSI_PF)
		return -EINVAL;

	if (qid >= vsi->netdev->real_num_rx_queues ||
	    qid >= vsi->netdev->real_num_tx_queues)
		return -EINVAL;

	err = xsk_pool_dma_map(pool, ice_pf_to_dev(vsi->back),
			       ICE_RX_DMA_ATTR);
	if (err)
		return err;

	set_bit(qid, vsi->af_xdp_zc_qps);

	return 0;
}

/**
 * ice_xsk_pool_setup - enable/disable a buffer pool region depending on its state
 * @vsi: Current VSI
 * @pool: buffer pool to enable/associate to a ring, NULL to disable
 * @qid: queue ID
 *
 * Returns 0 on success, negative on failure
 */
int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
{
	bool if_running, pool_present = !!pool;
	int ret = 0, pool_failure = 0;

	if_running = netif_running(vsi->netdev) && ice_is_xdp_ena_vsi(vsi);

	if (if_running) {
		ret = ice_qp_dis(vsi, qid);
		if (ret) {
			netdev_err(vsi->netdev, "ice_qp_dis error = %d\n", ret);
			goto xsk_pool_if_up;
		}
	}

	pool_failure = pool_present ? ice_xsk_pool_enable(vsi, pool, qid) :
				      ice_xsk_pool_disable(vsi, qid);

xsk_pool_if_up:
	if (if_running) {
		ret = ice_qp_ena(vsi, qid);
		if (!ret && pool_present)
			napi_schedule(&vsi->xdp_rings[qid]->q_vector->napi);
		else if (ret)
			netdev_err(vsi->netdev, "ice_qp_ena error = %d\n", ret);
	}

	if (pool_failure) {
		netdev_err(vsi->netdev, "Could not %sable buffer pool, error = %d\n",
			   pool_present ? "en" : "dis", pool_failure);
		return pool_failure;
	}

	return ret;
}

/**
 * ice_alloc_rx_bufs_zc - allocate a number of Rx buffers
 * @rx_ring: Rx ring
 * @count: The number of buffers to allocate
 *
 * This function allocates a number of Rx buffers from the fill ring
 * or the internal recycle mechanism and places them on the Rx ring.
 *
 * Returns true if all allocations were successful, false if any fail.
 */
bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count)
{
	union ice_32b_rx_flex_desc *rx_desc;
	u16 ntu = rx_ring->next_to_use;
	struct xdp_buff **xdp;
	bool ok = true;
	dma_addr_t dma;

	if (!count)
		return true;

	rx_desc = ICE_RX_DESC(rx_ring, ntu);
	xdp = &rx_ring->xdp_buf[ntu];

	do {
		*xdp = xsk_buff_alloc(rx_ring->xsk_pool);
		if (!xdp) {
			ok = false;
			break;
		}

		dma = xsk_buff_xdp_get_dma(*xdp);
		rx_desc->read.pkt_addr = cpu_to_le64(dma);
		rx_desc->wb.status_error0 = 0;

		rx_desc++;
		xdp++;
		ntu++;

		if (unlikely(ntu == rx_ring->count)) {
			rx_desc = ICE_RX_DESC(rx_ring, 0);
			xdp = rx_ring->xdp_buf;
			ntu = 0;
		}
	} while (--count);

	if (rx_ring->next_to_use != ntu) {
		/* clear the status bits for the next_to_use descriptor */
		rx_desc->wb.status_error0 = 0;
		ice_release_rx_desc(rx_ring, ntu);
	}

	return ok;
}

/**
 * ice_bump_ntc - Bump the next_to_clean counter of an Rx ring
 * @rx_ring: Rx ring
 */
static void ice_bump_ntc(struct ice_ring *rx_ring)
{
	int ntc = rx_ring->next_to_clean + 1;

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

/**
 * ice_construct_skb_zc - Create an sk_buff from zero-copy buffer
 * @rx_ring: Rx ring
 * @xdp_arr: Pointer to the SW ring of xdp_buff pointers
 *
 * This function allocates a new skb from a zero-copy Rx buffer.
 *
 * Returns the skb on success, NULL on failure.
 */
static struct sk_buff *
ice_construct_skb_zc(struct ice_ring *rx_ring, struct xdp_buff **xdp_arr)
{
	struct xdp_buff *xdp = *xdp_arr;
	unsigned int metasize = xdp->data - xdp->data_meta;
	unsigned int datasize = xdp->data_end - xdp->data;
	unsigned int datasize_hard = xdp->data_end - xdp->data_hard_start;
	struct sk_buff *skb;

	skb = __napi_alloc_skb(&rx_ring->q_vector->napi, datasize_hard,
			       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);

	xsk_buff_free(xdp);
	*xdp_arr = NULL;
	return skb;
}

/**
 * ice_run_xdp_zc - Executes an XDP program in zero-copy path
 * @rx_ring: Rx ring
 * @xdp: xdp_buff used as input to the XDP program
 *
 * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
 */
static int
ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp)
{
	int err, result = ICE_XDP_PASS;
	struct bpf_prog *xdp_prog;
	struct ice_ring *xdp_ring;
	u32 act;

	/* ZC patch is enabled only when XDP program is set,
	 * so here it can not be NULL
	 */
	xdp_prog = READ_ONCE(rx_ring->xdp_prog);

	act = bpf_prog_run_xdp(xdp_prog, xdp);

	if (likely(act == XDP_REDIRECT)) {
		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
		if (err)
			goto out_failure;
		return ICE_XDP_REDIR;
	}

	switch (act) {
	case XDP_PASS:
		break;
	case XDP_TX:
		xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->q_index];
		result = ice_xmit_xdp_buff(xdp, xdp_ring);
		if (result == ICE_XDP_CONSUMED)
			goto out_failure;
		break;
	default:
		bpf_warn_invalid_xdp_action(act);
		fallthrough;
	case XDP_ABORTED:
out_failure:
		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
		fallthrough;
	case XDP_DROP:
		result = ICE_XDP_CONSUMED;
		break;
	}

	return result;
}

/**
 * ice_clean_rx_irq_zc - consumes packets from the hardware ring
 * @rx_ring: AF_XDP Rx ring
 * @budget: NAPI budget
 *
 * Returns number of processed packets on success, remaining budget on failure.
 */
int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget)
{
	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
	u16 cleaned_count = ICE_DESC_UNUSED(rx_ring);
	unsigned int xdp_xmit = 0;
	bool failure = false;

	while (likely(total_rx_packets < (unsigned int)budget)) {
		union ice_32b_rx_flex_desc *rx_desc;
		unsigned int size, xdp_res = 0;
		struct xdp_buff **xdp;
		struct sk_buff *skb;
		u16 stat_err_bits;
		u16 vlan_tag = 0;
		u16 rx_ptype;

		rx_desc = ICE_RX_DESC(rx_ring, rx_ring->next_to_clean);

		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S);
		if (!ice_test_staterr(rx_desc, stat_err_bits))
			break;

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

		size = le16_to_cpu(rx_desc->wb.pkt_len) &
				   ICE_RX_FLX_DESC_PKT_LEN_M;
		if (!size)
			break;

		xdp = &rx_ring->xdp_buf[rx_ring->next_to_clean];
		(*xdp)->data_end = (*xdp)->data + size;
		xsk_buff_dma_sync_for_cpu(*xdp, rx_ring->xsk_pool);

		xdp_res = ice_run_xdp_zc(rx_ring, *xdp);
		if (xdp_res) {
			if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))
				xdp_xmit |= xdp_res;
			else
				xsk_buff_free(*xdp);

			*xdp = NULL;
			total_rx_bytes += size;
			total_rx_packets++;
			cleaned_count++;

			ice_bump_ntc(rx_ring);
			continue;
		}

		/* XDP_PASS path */
		skb = ice_construct_skb_zc(rx_ring, xdp);
		if (!skb) {
			rx_ring->rx_stats.alloc_buf_failed++;
			break;
		}

		cleaned_count++;
		ice_bump_ntc(rx_ring);

		if (eth_skb_pad(skb)) {
			skb = NULL;
			continue;
		}

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

		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_L2TAG1P_S);
		if (ice_test_staterr(rx_desc, stat_err_bits))
			vlan_tag = le16_to_cpu(rx_desc->wb.l2tag1);

		rx_ptype = le16_to_cpu(rx_desc->wb.ptype_flex_flags0) &
				       ICE_RX_FLEX_DESC_PTYPE_M;

		ice_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
		ice_receive_skb(rx_ring, skb, vlan_tag);
	}

	if (cleaned_count >= ICE_RX_BUF_WRITE)
		failure = !ice_alloc_rx_bufs_zc(rx_ring, cleaned_count);

	ice_finalize_xdp_rx(rx_ring, xdp_xmit);
	ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes);

	if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) {
		if (failure || rx_ring->next_to_clean == rx_ring->next_to_use)
			xsk_set_rx_need_wakeup(rx_ring->xsk_pool);
		else
			xsk_clear_rx_need_wakeup(rx_ring->xsk_pool);

		return (int)total_rx_packets;
	}

	return failure ? budget : (int)total_rx_packets;
}

/**
 * ice_xmit_zc - Completes AF_XDP entries, and cleans XDP entries
 * @xdp_ring: XDP Tx ring
 * @budget: max number of frames to xmit
 *
 * Returns true if cleanup/transmission is done.
 */
static bool ice_xmit_zc(struct ice_ring *xdp_ring, int budget)
{
	struct ice_tx_desc *tx_desc = NULL;
	bool work_done = true;
	struct xdp_desc desc;
	dma_addr_t dma;

	while (likely(budget-- > 0)) {
		struct ice_tx_buf *tx_buf;

		if (unlikely(!ICE_DESC_UNUSED(xdp_ring))) {
			xdp_ring->tx_stats.tx_busy++;
			work_done = false;
			break;
		}

		tx_buf = &xdp_ring->tx_buf[xdp_ring->next_to_use];

		if (!xsk_tx_peek_desc(xdp_ring->xsk_pool, &desc))
			break;

		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc.addr);
		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma,
						 desc.len);

		tx_buf->bytecount = desc.len;

		tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_to_use);
		tx_desc->buf_addr = cpu_to_le64(dma);
		tx_desc->cmd_type_offset_bsz =
			ice_build_ctob(ICE_TXD_LAST_DESC_CMD, 0, desc.len, 0);

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

	if (tx_desc) {
		ice_xdp_ring_update_tail(xdp_ring);
		xsk_tx_release(xdp_ring->xsk_pool);
	}

	return budget > 0 && work_done;
}

/**
 * ice_clean_xdp_tx_buf - Free and unmap XDP Tx buffer
 * @xdp_ring: XDP Tx ring
 * @tx_buf: Tx buffer to clean
 */
static void
ice_clean_xdp_tx_buf(struct ice_ring *xdp_ring, struct ice_tx_buf *tx_buf)
{
	xdp_return_frame((struct xdp_frame *)tx_buf->raw_buf);
	dma_unmap_single(xdp_ring->dev, dma_unmap_addr(tx_buf, dma),
			 dma_unmap_len(tx_buf, len), DMA_TO_DEVICE);
	dma_unmap_len_set(tx_buf, len, 0);
}

/**
 * ice_clean_tx_irq_zc - Completes AF_XDP entries, and cleans XDP entries
 * @xdp_ring: XDP Tx ring
 * @budget: NAPI budget
 *
 * Returns true if cleanup/tranmission is done.
 */
bool ice_clean_tx_irq_zc(struct ice_ring *xdp_ring, int budget)
{
	int total_packets = 0, total_bytes = 0;
	s16 ntc = xdp_ring->next_to_clean;
	struct ice_tx_desc *tx_desc;
	struct ice_tx_buf *tx_buf;
	u32 xsk_frames = 0;
	bool xmit_done;

	tx_desc = ICE_TX_DESC(xdp_ring, ntc);
	tx_buf = &xdp_ring->tx_buf[ntc];
	ntc -= xdp_ring->count;

	do {
		if (!(tx_desc->cmd_type_offset_bsz &
		      cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE)))
			break;

		total_bytes += tx_buf->bytecount;
		total_packets++;

		if (tx_buf->raw_buf) {
			ice_clean_xdp_tx_buf(xdp_ring, tx_buf);
			tx_buf->raw_buf = NULL;
		} else {
			xsk_frames++;
		}

		tx_desc->cmd_type_offset_bsz = 0;
		tx_buf++;
		tx_desc++;
		ntc++;

		if (unlikely(!ntc)) {
			ntc -= xdp_ring->count;
			tx_buf = xdp_ring->tx_buf;
			tx_desc = ICE_TX_DESC(xdp_ring, 0);
		}

		prefetch(tx_desc);

	} while (likely(--budget));

	ntc += xdp_ring->count;
	xdp_ring->next_to_clean = ntc;

	if (xsk_frames)
		xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);

	if (xsk_uses_need_wakeup(xdp_ring->xsk_pool))
		xsk_set_tx_need_wakeup(xdp_ring->xsk_pool);

	ice_update_tx_ring_stats(xdp_ring, total_packets, total_bytes);
	xmit_done = ice_xmit_zc(xdp_ring, ICE_DFLT_IRQ_WORK);

	return budget > 0 && xmit_done;
}

/**
 * ice_xsk_wakeup - Implements ndo_xsk_wakeup
 * @netdev: net_device
 * @queue_id: queue to wake up
 * @flags: ignored in our case, since we have Rx and Tx in the same NAPI
 *
 * Returns negative on error, zero otherwise.
 */
int
ice_xsk_wakeup(struct net_device *netdev, u32 queue_id,
	       u32 __always_unused flags)
{
	struct ice_netdev_priv *np = netdev_priv(netdev);
	struct ice_q_vector *q_vector;
	struct ice_vsi *vsi = np->vsi;
	struct ice_ring *ring;

	if (test_bit(ICE_VSI_DOWN, vsi->state))
		return -ENETDOWN;

	if (!ice_is_xdp_ena_vsi(vsi))
		return -ENXIO;

	if (queue_id >= vsi->num_txq)
		return -ENXIO;

	if (!vsi->xdp_rings[queue_id]->xsk_pool)
		return -ENXIO;

	ring = vsi->xdp_rings[queue_id];

	/* The idea here is that if NAPI is running, mark a miss, so
	 * it will run again. If not, trigger an interrupt and
	 * schedule the NAPI from interrupt context. If NAPI would be
	 * scheduled here, the interrupt affinity would not be
	 * honored.
	 */
	q_vector = ring->q_vector;
	if (!napi_if_scheduled_mark_missed(&q_vector->napi))
		ice_trigger_sw_intr(&vsi->back->hw, q_vector);

	return 0;
}

/**
 * ice_xsk_any_rx_ring_ena - Checks if Rx rings have AF_XDP buff pool attached
 * @vsi: VSI to be checked
 *
 * Returns true if any of the Rx rings has an AF_XDP buff pool attached
 */
bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi)
{
	int i;

	ice_for_each_rxq(vsi, i) {
		if (xsk_get_pool_from_qid(vsi->netdev, i))
			return true;
	}

	return false;
}

/**
 * ice_xsk_clean_rx_ring - clean buffer pool queues connected to a given Rx ring
 * @rx_ring: ring to be cleaned
 */
void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring)
{
	u16 count_mask = rx_ring->count - 1;
	u16 ntc = rx_ring->next_to_clean;
	u16 ntu = rx_ring->next_to_use;

	for ( ; ntc != ntu; ntc = (ntc + 1) & count_mask) {
		struct xdp_buff **xdp = &rx_ring->xdp_buf[ntc];

		xsk_buff_free(*xdp);
		*xdp = NULL;
	}
}

/**
 * ice_xsk_clean_xdp_ring - Clean the XDP Tx ring and its buffer pool queues
 * @xdp_ring: XDP_Tx ring
 */
void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring)
{
	u16 ntc = xdp_ring->next_to_clean, ntu = xdp_ring->next_to_use;
	u32 xsk_frames = 0;

	while (ntc != ntu) {
		struct ice_tx_buf *tx_buf = &xdp_ring->tx_buf[ntc];

		if (tx_buf->raw_buf)
			ice_clean_xdp_tx_buf(xdp_ring, tx_buf);
		else
			xsk_frames++;

		tx_buf->raw_buf = NULL;

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

	if (xsk_frames)
		xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);
}