summaryrefslogtreecommitdiff
path: root/drivers/net/ixgbe/ixgbe_pf.c
blob: c88d56e245641b786259ff79d421609831a112d5 (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
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright(c) 2010-2016 Intel Corporation
 */

#include <stdio.h>
#include <errno.h>
#include <stdint.h>
#include <stdlib.h>
#include <unistd.h>
#include <stdarg.h>
#include <inttypes.h>

#include <rte_interrupts.h>
#include <rte_log.h>
#include <rte_debug.h>
#include <rte_eal.h>
#include <rte_ether.h>
#include <rte_ethdev_driver.h>
#include <rte_memcpy.h>
#include <rte_malloc.h>
#include <rte_random.h>

#include "base/ixgbe_common.h"
#include "ixgbe_ethdev.h"
#include "rte_pmd_ixgbe.h"

#define IXGBE_MAX_VFTA     (128)
#define IXGBE_VF_MSG_SIZE_DEFAULT 1
#define IXGBE_VF_GET_QUEUE_MSG_SIZE 5
#define IXGBE_ETHERTYPE_FLOW_CTRL 0x8808

static inline uint16_t
dev_num_vf(struct rte_eth_dev *eth_dev)
{
	struct rte_pci_device *pci_dev = RTE_ETH_DEV_TO_PCI(eth_dev);

	return pci_dev->max_vfs;
}

static inline
int ixgbe_vf_perm_addr_gen(struct rte_eth_dev *dev, uint16_t vf_num)
{
	unsigned char vf_mac_addr[RTE_ETHER_ADDR_LEN];
	struct ixgbe_vf_info *vfinfo =
		*IXGBE_DEV_PRIVATE_TO_P_VFDATA(dev->data->dev_private);
	uint16_t vfn;

	for (vfn = 0; vfn < vf_num; vfn++) {
		rte_eth_random_addr(vf_mac_addr);
		/* keep the random address as default */
		memcpy(vfinfo[vfn].vf_mac_addresses, vf_mac_addr,
			   RTE_ETHER_ADDR_LEN);
	}

	return 0;
}

static inline int
ixgbe_mb_intr_setup(struct rte_eth_dev *dev)
{
	struct ixgbe_interrupt *intr =
		IXGBE_DEV_PRIVATE_TO_INTR(dev->data->dev_private);

	intr->mask |= IXGBE_EICR_MAILBOX;

	return 0;
}

void ixgbe_pf_host_init(struct rte_eth_dev *eth_dev)
{
	struct ixgbe_vf_info **vfinfo =
		IXGBE_DEV_PRIVATE_TO_P_VFDATA(eth_dev->data->dev_private);
	struct ixgbe_mirror_info *mirror_info =
	IXGBE_DEV_PRIVATE_TO_PFDATA(eth_dev->data->dev_private);
	struct ixgbe_uta_info *uta_info =
	IXGBE_DEV_PRIVATE_TO_UTA(eth_dev->data->dev_private);
	struct ixgbe_hw *hw =
		IXGBE_DEV_PRIVATE_TO_HW(eth_dev->data->dev_private);
	uint16_t vf_num;
	uint8_t nb_queue;

	PMD_INIT_FUNC_TRACE();

	RTE_ETH_DEV_SRIOV(eth_dev).active = 0;
	vf_num = dev_num_vf(eth_dev);
	if (vf_num == 0)
		return;

	*vfinfo = rte_zmalloc("vf_info", sizeof(struct ixgbe_vf_info) * vf_num, 0);
	if (*vfinfo == NULL)
		rte_panic("Cannot allocate memory for private VF data\n");

	rte_eth_switch_domain_alloc(&(*vfinfo)->switch_domain_id);

	memset(mirror_info, 0, sizeof(struct ixgbe_mirror_info));
	memset(uta_info, 0, sizeof(struct ixgbe_uta_info));
	hw->mac.mc_filter_type = 0;

	if (vf_num >= ETH_32_POOLS) {
		nb_queue = 2;
		RTE_ETH_DEV_SRIOV(eth_dev).active = ETH_64_POOLS;
	} else if (vf_num >= ETH_16_POOLS) {
		nb_queue = 4;
		RTE_ETH_DEV_SRIOV(eth_dev).active = ETH_32_POOLS;
	} else {
		nb_queue = 8;
		RTE_ETH_DEV_SRIOV(eth_dev).active = ETH_16_POOLS;
	}

	RTE_ETH_DEV_SRIOV(eth_dev).nb_q_per_pool = nb_queue;
	RTE_ETH_DEV_SRIOV(eth_dev).def_vmdq_idx = vf_num;
	RTE_ETH_DEV_SRIOV(eth_dev).def_pool_q_idx = (uint16_t)(vf_num * nb_queue);

	ixgbe_vf_perm_addr_gen(eth_dev, vf_num);

	/* init_mailbox_params */
	hw->mbx.ops.init_params(hw);

	/* set mb interrupt mask */
	ixgbe_mb_intr_setup(eth_dev);
}

void ixgbe_pf_host_uninit(struct rte_eth_dev *eth_dev)
{
	struct ixgbe_vf_info **vfinfo;
	uint16_t vf_num;
	int ret;

	PMD_INIT_FUNC_TRACE();

	RTE_ETH_DEV_SRIOV(eth_dev).active = 0;
	RTE_ETH_DEV_SRIOV(eth_dev).nb_q_per_pool = 0;
	RTE_ETH_DEV_SRIOV(eth_dev).def_vmdq_idx = 0;
	RTE_ETH_DEV_SRIOV(eth_dev).def_pool_q_idx = 0;

	vf_num = dev_num_vf(eth_dev);
	if (vf_num == 0)
		return;

	vfinfo = IXGBE_DEV_PRIVATE_TO_P_VFDATA(eth_dev->data->dev_private);
	if (*vfinfo == NULL)
		return;

	ret = rte_eth_switch_domain_free((*vfinfo)->switch_domain_id);
	if (ret)
		PMD_INIT_LOG(WARNING, "failed to free switch domain: %d", ret);

	rte_free(*vfinfo);
	*vfinfo = NULL;
}

static void
ixgbe_add_tx_flow_control_drop_filter(struct rte_eth_dev *eth_dev)
{
	struct ixgbe_hw *hw =
		IXGBE_DEV_PRIVATE_TO_HW(eth_dev->data->dev_private);
	struct ixgbe_filter_info *filter_info =
		IXGBE_DEV_PRIVATE_TO_FILTER_INFO(eth_dev->data->dev_private);
	uint16_t vf_num;
	int i;
	struct ixgbe_ethertype_filter ethertype_filter;

	if (!hw->mac.ops.set_ethertype_anti_spoofing) {
		RTE_LOG(INFO, PMD, "ether type anti-spoofing is not"
			" supported.\n");
		return;
	}

	i = ixgbe_ethertype_filter_lookup(filter_info,
					  IXGBE_ETHERTYPE_FLOW_CTRL);
	if (i >= 0) {
		RTE_LOG(ERR, PMD, "A ether type filter"
			" entity for flow control already exists!\n");
		return;
	}

	ethertype_filter.ethertype = IXGBE_ETHERTYPE_FLOW_CTRL;
	ethertype_filter.etqf = IXGBE_ETQF_FILTER_EN |
				IXGBE_ETQF_TX_ANTISPOOF |
				IXGBE_ETHERTYPE_FLOW_CTRL;
	ethertype_filter.etqs = 0;
	ethertype_filter.conf = TRUE;
	i = ixgbe_ethertype_filter_insert(filter_info,
					  &ethertype_filter);
	if (i < 0) {
		RTE_LOG(ERR, PMD, "Cannot find an unused ether type filter"
			" entity for flow control.\n");
		return;
	}

	IXGBE_WRITE_REG(hw, IXGBE_ETQF(i),
			(IXGBE_ETQF_FILTER_EN |
			IXGBE_ETQF_TX_ANTISPOOF |
			IXGBE_ETHERTYPE_FLOW_CTRL));

	vf_num = dev_num_vf(eth_dev);
	for (i = 0; i < vf_num; i++)
		hw->mac.ops.set_ethertype_anti_spoofing(hw, true, i);
}

int ixgbe_pf_host_configure(struct rte_eth_dev *eth_dev)
{
	uint32_t vtctl, fcrth;
	uint32_t vfre_slot, vfre_offset;
	uint16_t vf_num;
	const uint8_t VFRE_SHIFT = 5;  /* VFRE 32 bits per slot */
	const uint8_t VFRE_MASK = (uint8_t)((1U << VFRE_SHIFT) - 1);
	struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(eth_dev->data->dev_private);
	uint32_t gpie, gcr_ext;
	uint32_t vlanctrl;
	int i;

	vf_num = dev_num_vf(eth_dev);
	if (vf_num == 0)
		return -1;

	/* enable VMDq and set the default pool for PF */
	vtctl = IXGBE_READ_REG(hw, IXGBE_VT_CTL);
	vtctl |= IXGBE_VMD_CTL_VMDQ_EN;
	vtctl &= ~IXGBE_VT_CTL_POOL_MASK;
	vtctl |= RTE_ETH_DEV_SRIOV(eth_dev).def_vmdq_idx
		<< IXGBE_VT_CTL_POOL_SHIFT;
	vtctl |= IXGBE_VT_CTL_REPLEN;
	IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, vtctl);

	vfre_offset = vf_num & VFRE_MASK;
	vfre_slot = (vf_num >> VFRE_SHIFT) > 0 ? 1 : 0;

	/* Enable pools reserved to PF only */
	IXGBE_WRITE_REG(hw, IXGBE_VFRE(vfre_slot), (~0U) << vfre_offset);
	IXGBE_WRITE_REG(hw, IXGBE_VFRE(vfre_slot ^ 1), vfre_slot - 1);
	IXGBE_WRITE_REG(hw, IXGBE_VFTE(vfre_slot), (~0U) << vfre_offset);
	IXGBE_WRITE_REG(hw, IXGBE_VFTE(vfre_slot ^ 1), vfre_slot - 1);

	/* PFDMA Tx General Switch Control Enables VMDQ loopback */
	IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, IXGBE_PFDTXGSWC_VT_LBEN);

	/* clear VMDq map to perment rar 0 */
	hw->mac.ops.clear_vmdq(hw, 0, IXGBE_CLEAR_VMDQ_ALL);

	/* clear VMDq map to scan rar 127 */
	IXGBE_WRITE_REG(hw, IXGBE_MPSAR_LO(hw->mac.num_rar_entries), 0);
	IXGBE_WRITE_REG(hw, IXGBE_MPSAR_HI(hw->mac.num_rar_entries), 0);

	/* set VMDq map to default PF pool */
	hw->mac.ops.set_vmdq(hw, 0, RTE_ETH_DEV_SRIOV(eth_dev).def_vmdq_idx);

	/*
	 * SW msut set GCR_EXT.VT_Mode the same as GPIE.VT_Mode
	 */
	gcr_ext = IXGBE_READ_REG(hw, IXGBE_GCR_EXT);
	gcr_ext &= ~IXGBE_GCR_EXT_VT_MODE_MASK;

	gpie = IXGBE_READ_REG(hw, IXGBE_GPIE);
	gpie &= ~IXGBE_GPIE_VTMODE_MASK;
	gpie |= IXGBE_GPIE_MSIX_MODE | IXGBE_GPIE_PBA_SUPPORT;

	switch (RTE_ETH_DEV_SRIOV(eth_dev).active) {
	case ETH_64_POOLS:
		gcr_ext |= IXGBE_GCR_EXT_VT_MODE_64;
		gpie |= IXGBE_GPIE_VTMODE_64;
		break;
	case ETH_32_POOLS:
		gcr_ext |= IXGBE_GCR_EXT_VT_MODE_32;
		gpie |= IXGBE_GPIE_VTMODE_32;
		break;
	case ETH_16_POOLS:
		gcr_ext |= IXGBE_GCR_EXT_VT_MODE_16;
		gpie |= IXGBE_GPIE_VTMODE_16;
		break;
	}

	IXGBE_WRITE_REG(hw, IXGBE_GCR_EXT, gcr_ext);
	IXGBE_WRITE_REG(hw, IXGBE_GPIE, gpie);

	/*
	 * enable vlan filtering and allow all vlan tags through
	 */
	vlanctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL);
	vlanctrl |= IXGBE_VLNCTRL_VFE; /* enable vlan filters */
	IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlanctrl);

	/* VFTA - enable all vlan filters */
	for (i = 0; i < IXGBE_MAX_VFTA; i++)
		IXGBE_WRITE_REG(hw, IXGBE_VFTA(i), 0xFFFFFFFF);

	/* Enable MAC Anti-Spoofing */
	hw->mac.ops.set_mac_anti_spoofing(hw, FALSE, vf_num);

	/* set flow control threshold to max to avoid tx switch hang */
	for (i = 0; i < IXGBE_DCB_MAX_TRAFFIC_CLASS; i++) {
		IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(i), 0);
		fcrth = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(i)) - 32;
		IXGBE_WRITE_REG(hw, IXGBE_FCRTH_82599(i), fcrth);
	}

	ixgbe_add_tx_flow_control_drop_filter(eth_dev);

	return 0;
}

static void
set_rx_mode(struct rte_eth_dev *dev)
{
	struct rte_eth_dev_data *dev_data = dev->data;
	struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	u32 fctrl, vmolr = IXGBE_VMOLR_BAM | IXGBE_VMOLR_AUPE;
	uint16_t vfn = dev_num_vf(dev);

	/* Check for Promiscuous and All Multicast modes */
	fctrl = IXGBE_READ_REG(hw, IXGBE_FCTRL);

	/* set all bits that we expect to always be set */
	fctrl &= ~IXGBE_FCTRL_SBP; /* disable store-bad-packets */
	fctrl |= IXGBE_FCTRL_BAM;

	/* clear the bits we are changing the status of */
	fctrl &= ~(IXGBE_FCTRL_UPE | IXGBE_FCTRL_MPE);

	if (dev_data->promiscuous) {
		fctrl |= (IXGBE_FCTRL_UPE | IXGBE_FCTRL_MPE);
		vmolr |= (IXGBE_VMOLR_ROPE | IXGBE_VMOLR_MPE);
	} else {
		if (dev_data->all_multicast) {
			fctrl |= IXGBE_FCTRL_MPE;
			vmolr |= IXGBE_VMOLR_MPE;
		} else {
			vmolr |= IXGBE_VMOLR_ROMPE;
		}
	}

	if (hw->mac.type != ixgbe_mac_82598EB) {
		vmolr |= IXGBE_READ_REG(hw, IXGBE_VMOLR(vfn)) &
			 ~(IXGBE_VMOLR_MPE | IXGBE_VMOLR_ROMPE |
			   IXGBE_VMOLR_ROPE);
		IXGBE_WRITE_REG(hw, IXGBE_VMOLR(vfn), vmolr);
	}

	IXGBE_WRITE_REG(hw, IXGBE_FCTRL, fctrl);

	ixgbe_vlan_hw_strip_config(dev);
}

static inline void
ixgbe_vf_reset_event(struct rte_eth_dev *dev, uint16_t vf)
{
	struct ixgbe_hw *hw =
		IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	struct ixgbe_vf_info *vfinfo =
		*(IXGBE_DEV_PRIVATE_TO_P_VFDATA(dev->data->dev_private));
	int rar_entry = hw->mac.num_rar_entries - (vf + 1);
	uint32_t vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(vf));

	vmolr |= (IXGBE_VMOLR_ROPE |
			IXGBE_VMOLR_BAM | IXGBE_VMOLR_AUPE);
	IXGBE_WRITE_REG(hw, IXGBE_VMOLR(vf), vmolr);

	IXGBE_WRITE_REG(hw, IXGBE_VMVIR(vf), 0);

	/* reset multicast table array for vf */
	vfinfo[vf].num_vf_mc_hashes = 0;

	/* reset rx mode */
	set_rx_mode(dev);

	hw->mac.ops.clear_rar(hw, rar_entry);
}

static inline void
ixgbe_vf_reset_msg(struct rte_eth_dev *dev, uint16_t vf)
{
	struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	uint32_t reg;
	uint32_t reg_offset, vf_shift;
	const uint8_t VFRE_SHIFT = 5;  /* VFRE 32 bits per slot */
	const uint8_t VFRE_MASK = (uint8_t)((1U << VFRE_SHIFT) - 1);
	uint8_t  nb_q_per_pool;
	int i;

	vf_shift = vf & VFRE_MASK;
	reg_offset = (vf >> VFRE_SHIFT) > 0 ? 1 : 0;

	/* enable transmit for vf */
	reg = IXGBE_READ_REG(hw, IXGBE_VFTE(reg_offset));
	reg |= (reg | (1 << vf_shift));
	IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset), reg);

	/* enable all queue drop for IOV */
	nb_q_per_pool = RTE_ETH_DEV_SRIOV(dev).nb_q_per_pool;
	for (i = vf * nb_q_per_pool; i < (vf + 1) * nb_q_per_pool; i++) {
		IXGBE_WRITE_FLUSH(hw);
		reg = IXGBE_QDE_ENABLE | IXGBE_QDE_WRITE;
		reg |= i << IXGBE_QDE_IDX_SHIFT;
		IXGBE_WRITE_REG(hw, IXGBE_QDE, reg);
	}

	/* enable receive for vf */
	reg = IXGBE_READ_REG(hw, IXGBE_VFRE(reg_offset));
	reg |= (reg | (1 << vf_shift));
	IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset), reg);

	/* Enable counting of spoofed packets in the SSVPC register */
	reg = IXGBE_READ_REG(hw, IXGBE_VMECM(reg_offset));
	reg |= (1 << vf_shift);
	IXGBE_WRITE_REG(hw, IXGBE_VMECM(reg_offset), reg);

	ixgbe_vf_reset_event(dev, vf);
}

static int
ixgbe_disable_vf_mc_promisc(struct rte_eth_dev *dev, uint32_t vf)
{
	struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	uint32_t vmolr;

	vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(vf));

	RTE_LOG(INFO, PMD, "VF %u: disabling multicast promiscuous\n", vf);

	vmolr &= ~IXGBE_VMOLR_MPE;

	IXGBE_WRITE_REG(hw, IXGBE_VMOLR(vf), vmolr);

	return 0;
}

static int
ixgbe_vf_reset(struct rte_eth_dev *dev, uint16_t vf, uint32_t *msgbuf)
{
	struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	struct ixgbe_vf_info *vfinfo =
		*(IXGBE_DEV_PRIVATE_TO_P_VFDATA(dev->data->dev_private));
	unsigned char *vf_mac = vfinfo[vf].vf_mac_addresses;
	int rar_entry = hw->mac.num_rar_entries - (vf + 1);
	uint8_t *new_mac = (uint8_t *)(&msgbuf[1]);

	ixgbe_vf_reset_msg(dev, vf);

	hw->mac.ops.set_rar(hw, rar_entry, vf_mac, vf, IXGBE_RAH_AV);

	/* Disable multicast promiscuous at reset */
	ixgbe_disable_vf_mc_promisc(dev, vf);

	/* reply to reset with ack and vf mac address */
	msgbuf[0] = IXGBE_VF_RESET | IXGBE_VT_MSGTYPE_ACK;
	rte_memcpy(new_mac, vf_mac, RTE_ETHER_ADDR_LEN);
	/*
	 * Piggyback the multicast filter type so VF can compute the
	 * correct vectors
	 */
	msgbuf[3] = hw->mac.mc_filter_type;
	ixgbe_write_mbx(hw, msgbuf, IXGBE_VF_PERMADDR_MSG_LEN, vf);

	return 0;
}

static int
ixgbe_vf_set_mac_addr(struct rte_eth_dev *dev, uint32_t vf, uint32_t *msgbuf)
{
	struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	struct ixgbe_vf_info *vfinfo =
		*(IXGBE_DEV_PRIVATE_TO_P_VFDATA(dev->data->dev_private));
	int rar_entry = hw->mac.num_rar_entries - (vf + 1);
	uint8_t *new_mac = (uint8_t *)(&msgbuf[1]);

	if (rte_is_valid_assigned_ether_addr(
			(struct rte_ether_addr *)new_mac)) {
		rte_memcpy(vfinfo[vf].vf_mac_addresses, new_mac, 6);
		return hw->mac.ops.set_rar(hw, rar_entry, new_mac, vf, IXGBE_RAH_AV);
	}
	return -1;
}

static int
ixgbe_vf_set_multicast(struct rte_eth_dev *dev, uint32_t vf, uint32_t *msgbuf)
{
	struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	struct ixgbe_vf_info *vfinfo =
		*(IXGBE_DEV_PRIVATE_TO_P_VFDATA(dev->data->dev_private));
	int nb_entries = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) >>
		IXGBE_VT_MSGINFO_SHIFT;
	uint16_t *hash_list = (uint16_t *)&msgbuf[1];
	uint32_t mta_idx;
	uint32_t mta_shift;
	const uint32_t IXGBE_MTA_INDEX_MASK = 0x7F;
	const uint32_t IXGBE_MTA_BIT_SHIFT = 5;
	const uint32_t IXGBE_MTA_BIT_MASK = (0x1 << IXGBE_MTA_BIT_SHIFT) - 1;
	uint32_t reg_val;
	int i;
	u32 vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(vf));

	/* Disable multicast promiscuous first */
	ixgbe_disable_vf_mc_promisc(dev, vf);

	/* only so many hash values supported */
	nb_entries = RTE_MIN(nb_entries, IXGBE_MAX_VF_MC_ENTRIES);

	/* store the mc entries  */
	vfinfo->num_vf_mc_hashes = (uint16_t)nb_entries;
	for (i = 0; i < nb_entries; i++) {
		vfinfo->vf_mc_hashes[i] = hash_list[i];
	}

	if (nb_entries == 0) {
		vmolr &= ~IXGBE_VMOLR_ROMPE;
		IXGBE_WRITE_REG(hw, IXGBE_VMOLR(vf), vmolr);
		return 0;
	}

	for (i = 0; i < vfinfo->num_vf_mc_hashes; i++) {
		mta_idx = (vfinfo->vf_mc_hashes[i] >> IXGBE_MTA_BIT_SHIFT)
				& IXGBE_MTA_INDEX_MASK;
		mta_shift = vfinfo->vf_mc_hashes[i] & IXGBE_MTA_BIT_MASK;
		reg_val = IXGBE_READ_REG(hw, IXGBE_MTA(mta_idx));
		reg_val |= (1 << mta_shift);
		IXGBE_WRITE_REG(hw, IXGBE_MTA(mta_idx), reg_val);
	}

	vmolr |= IXGBE_VMOLR_ROMPE;
	IXGBE_WRITE_REG(hw, IXGBE_VMOLR(vf), vmolr);

	return 0;
}

static int
ixgbe_vf_set_vlan(struct rte_eth_dev *dev, uint32_t vf, uint32_t *msgbuf)
{
	int add, vid;
	struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	struct ixgbe_vf_info *vfinfo =
		*(IXGBE_DEV_PRIVATE_TO_P_VFDATA(dev->data->dev_private));

	add = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK)
		>> IXGBE_VT_MSGINFO_SHIFT;
	vid = (msgbuf[1] & IXGBE_VLVF_VLANID_MASK);

	if (add)
		vfinfo[vf].vlan_count++;
	else if (vfinfo[vf].vlan_count)
		vfinfo[vf].vlan_count--;
	return hw->mac.ops.set_vfta(hw, vid, vf, (bool)add, false);
}

static int
ixgbe_set_vf_lpe(struct rte_eth_dev *dev, __rte_unused uint32_t vf, uint32_t *msgbuf)
{
	struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	uint32_t new_mtu = msgbuf[1];
	uint32_t max_frs;
	int max_frame = new_mtu + RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN;

	/* X540 and X550 support jumbo frames in IOV mode */
	if (hw->mac.type != ixgbe_mac_X540 &&
		hw->mac.type != ixgbe_mac_X550 &&
		hw->mac.type != ixgbe_mac_X550EM_x &&
		hw->mac.type != ixgbe_mac_X550EM_a)
		return -1;

	if (max_frame < RTE_ETHER_MIN_LEN ||
			max_frame > RTE_ETHER_MAX_JUMBO_FRAME_LEN)
		return -1;

	max_frs = (IXGBE_READ_REG(hw, IXGBE_MAXFRS) &
		   IXGBE_MHADD_MFS_MASK) >> IXGBE_MHADD_MFS_SHIFT;
	if (max_frs < new_mtu) {
		max_frs = new_mtu << IXGBE_MHADD_MFS_SHIFT;
		IXGBE_WRITE_REG(hw, IXGBE_MAXFRS, max_frs);
	}

	return 0;
}

static int
ixgbe_negotiate_vf_api(struct rte_eth_dev *dev, uint32_t vf, uint32_t *msgbuf)
{
	uint32_t api_version = msgbuf[1];
	struct ixgbe_vf_info *vfinfo =
		*IXGBE_DEV_PRIVATE_TO_P_VFDATA(dev->data->dev_private);

	switch (api_version) {
	case ixgbe_mbox_api_10:
	case ixgbe_mbox_api_11:
	case ixgbe_mbox_api_12:
	case ixgbe_mbox_api_13:
		vfinfo[vf].api_version = (uint8_t)api_version;
		return 0;
	default:
		break;
	}

	RTE_LOG(ERR, PMD, "Negotiate invalid api version %u from VF %d\n",
		api_version, vf);

	return -1;
}

static int
ixgbe_get_vf_queues(struct rte_eth_dev *dev, uint32_t vf, uint32_t *msgbuf)
{
	struct ixgbe_vf_info *vfinfo =
		*IXGBE_DEV_PRIVATE_TO_P_VFDATA(dev->data->dev_private);
	uint32_t default_q = vf * RTE_ETH_DEV_SRIOV(dev).nb_q_per_pool;
	struct rte_eth_conf *eth_conf;
	struct rte_eth_vmdq_dcb_tx_conf *vmdq_dcb_tx_conf;
	u8 num_tcs;
	struct ixgbe_hw *hw;
	u32 vmvir;
#define IXGBE_VMVIR_VLANA_MASK		0xC0000000
#define IXGBE_VMVIR_VLAN_VID_MASK	0x00000FFF
#define IXGBE_VMVIR_VLAN_UP_MASK	0x0000E000
#define VLAN_PRIO_SHIFT			13
	u32 vlana;
	u32 vid;
	u32 user_priority;

	/* Verify if the PF supports the mbox APIs version or not */
	switch (vfinfo[vf].api_version) {
	case ixgbe_mbox_api_20:
	case ixgbe_mbox_api_11:
	case ixgbe_mbox_api_12:
		break;
	default:
		return -1;
	}

	/* Notify VF of Rx and Tx queue number */
	msgbuf[IXGBE_VF_RX_QUEUES] = RTE_ETH_DEV_SRIOV(dev).nb_q_per_pool;
	msgbuf[IXGBE_VF_TX_QUEUES] = RTE_ETH_DEV_SRIOV(dev).nb_q_per_pool;

	/* Notify VF of default queue */
	msgbuf[IXGBE_VF_DEF_QUEUE] = default_q;

	/* Notify VF of number of DCB traffic classes */
	eth_conf = &dev->data->dev_conf;
	switch (eth_conf->txmode.mq_mode) {
	case ETH_MQ_TX_NONE:
	case ETH_MQ_TX_DCB:
		RTE_LOG(ERR, PMD, "PF must work with virtualization for VF %u"
			", but its tx mode = %d\n", vf,
			eth_conf->txmode.mq_mode);
		return -1;

	case ETH_MQ_TX_VMDQ_DCB:
		vmdq_dcb_tx_conf = &eth_conf->tx_adv_conf.vmdq_dcb_tx_conf;
		switch (vmdq_dcb_tx_conf->nb_queue_pools) {
		case ETH_16_POOLS:
			num_tcs = ETH_8_TCS;
			break;
		case ETH_32_POOLS:
			num_tcs = ETH_4_TCS;
			break;
		default:
			return -1;
		}
		break;

	/* ETH_MQ_TX_VMDQ_ONLY,  DCB not enabled */
	case ETH_MQ_TX_VMDQ_ONLY:
		hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
		vmvir = IXGBE_READ_REG(hw, IXGBE_VMVIR(vf));
		vlana = vmvir & IXGBE_VMVIR_VLANA_MASK;
		vid = vmvir & IXGBE_VMVIR_VLAN_VID_MASK;
		user_priority =
			(vmvir & IXGBE_VMVIR_VLAN_UP_MASK) >> VLAN_PRIO_SHIFT;
		if ((vlana == IXGBE_VMVIR_VLANA_DEFAULT) &&
			((vid !=  0) || (user_priority != 0)))
			num_tcs = 1;
		else
			num_tcs = 0;
		break;

	default:
		RTE_LOG(ERR, PMD, "PF work with invalid mode = %d\n",
			eth_conf->txmode.mq_mode);
		return -1;
	}
	msgbuf[IXGBE_VF_TRANS_VLAN] = num_tcs;

	return 0;
}

static int
ixgbe_set_vf_mc_promisc(struct rte_eth_dev *dev, uint32_t vf, uint32_t *msgbuf)
{
	struct ixgbe_vf_info *vfinfo =
		*(IXGBE_DEV_PRIVATE_TO_P_VFDATA(dev->data->dev_private));
	struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	int xcast_mode = msgbuf[1];	/* msgbuf contains the flag to enable */
	u32 vmolr, fctrl, disable, enable;

	switch (vfinfo[vf].api_version) {
	case ixgbe_mbox_api_12:
		/* promisc introduced in 1.3 version */
		if (xcast_mode == IXGBEVF_XCAST_MODE_PROMISC)
			return -EOPNOTSUPP;
		break;
		/* Fall threw */
	case ixgbe_mbox_api_13:
		break;
	default:
		return -1;
	}

	if (vfinfo[vf].xcast_mode == xcast_mode)
		goto out;

	switch (xcast_mode) {
	case IXGBEVF_XCAST_MODE_NONE:
		disable = IXGBE_VMOLR_BAM | IXGBE_VMOLR_ROMPE |
			  IXGBE_VMOLR_MPE | IXGBE_VMOLR_UPE | IXGBE_VMOLR_VPE;
		enable = 0;
		break;
	case IXGBEVF_XCAST_MODE_MULTI:
		disable = IXGBE_VMOLR_MPE | IXGBE_VMOLR_UPE | IXGBE_VMOLR_VPE;
		enable = IXGBE_VMOLR_BAM | IXGBE_VMOLR_ROMPE;
		break;
	case IXGBEVF_XCAST_MODE_ALLMULTI:
		disable = IXGBE_VMOLR_UPE | IXGBE_VMOLR_VPE;
		enable = IXGBE_VMOLR_BAM | IXGBE_VMOLR_ROMPE | IXGBE_VMOLR_MPE;
		break;
	case IXGBEVF_XCAST_MODE_PROMISC:
		if (hw->mac.type <= ixgbe_mac_82599EB)
			return -1;

		fctrl = IXGBE_READ_REG(hw, IXGBE_FCTRL);
		if (!(fctrl & IXGBE_FCTRL_UPE)) {
			/* VF promisc requires PF in promisc */
			RTE_LOG(ERR, PMD,
			       "Enabling VF promisc requires PF in promisc\n");
			return -1;
		}

		disable = 0;
		enable = IXGBE_VMOLR_BAM | IXGBE_VMOLR_ROMPE |
			 IXGBE_VMOLR_MPE | IXGBE_VMOLR_UPE | IXGBE_VMOLR_VPE;
		break;
	default:
		return -1;
	}

	vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(vf));
	vmolr &= ~disable;
	vmolr |= enable;
	IXGBE_WRITE_REG(hw, IXGBE_VMOLR(vf), vmolr);
	vfinfo[vf].xcast_mode = xcast_mode;

out:
	msgbuf[1] = xcast_mode;

	return 0;
}

static int
ixgbe_rcv_msg_from_vf(struct rte_eth_dev *dev, uint16_t vf)
{
	uint16_t mbx_size = IXGBE_VFMAILBOX_SIZE;
	uint16_t msg_size = IXGBE_VF_MSG_SIZE_DEFAULT;
	uint32_t msgbuf[IXGBE_VFMAILBOX_SIZE];
	int32_t retval;
	struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	struct ixgbe_vf_info *vfinfo =
		*IXGBE_DEV_PRIVATE_TO_P_VFDATA(dev->data->dev_private);
	struct rte_pmd_ixgbe_mb_event_param ret_param;

	retval = ixgbe_read_mbx(hw, msgbuf, mbx_size, vf);
	if (retval) {
		PMD_DRV_LOG(ERR, "Error mbx recv msg from VF %d", vf);
		return retval;
	}

	/* do nothing with the message already been processed */
	if (msgbuf[0] & (IXGBE_VT_MSGTYPE_ACK | IXGBE_VT_MSGTYPE_NACK))
		return retval;

	/* flush the ack before we write any messages back */
	IXGBE_WRITE_FLUSH(hw);

	/**
	 * initialise structure to send to user application
	 * will return response from user in retval field
	 */
	ret_param.retval = RTE_PMD_IXGBE_MB_EVENT_PROCEED;
	ret_param.vfid = vf;
	ret_param.msg_type = msgbuf[0] & 0xFFFF;
	ret_param.msg = (void *)msgbuf;

	/* perform VF reset */
	if (msgbuf[0] == IXGBE_VF_RESET) {
		int ret = ixgbe_vf_reset(dev, vf, msgbuf);

		vfinfo[vf].clear_to_send = true;

		/* notify application about VF reset */
		_rte_eth_dev_callback_process(dev, RTE_ETH_EVENT_VF_MBOX,
					      &ret_param);
		return ret;
	}

	/**
	 * ask user application if we allowed to perform those functions
	 * if we get ret_param.retval == RTE_PMD_IXGBE_MB_EVENT_PROCEED
	 * then business as usual,
	 * if 0, do nothing and send ACK to VF
	 * if ret_param.retval > 1, do nothing and send NAK to VF
	 */
	_rte_eth_dev_callback_process(dev, RTE_ETH_EVENT_VF_MBOX,
				      &ret_param);

	retval = ret_param.retval;

	/* check & process VF to PF mailbox message */
	switch ((msgbuf[0] & 0xFFFF)) {
	case IXGBE_VF_SET_MAC_ADDR:
		if (retval == RTE_PMD_IXGBE_MB_EVENT_PROCEED)
			retval = ixgbe_vf_set_mac_addr(dev, vf, msgbuf);
		break;
	case IXGBE_VF_SET_MULTICAST:
		if (retval == RTE_PMD_IXGBE_MB_EVENT_PROCEED)
			retval = ixgbe_vf_set_multicast(dev, vf, msgbuf);
		break;
	case IXGBE_VF_SET_LPE:
		if (retval == RTE_PMD_IXGBE_MB_EVENT_PROCEED)
			retval = ixgbe_set_vf_lpe(dev, vf, msgbuf);
		break;
	case IXGBE_VF_SET_VLAN:
		if (retval == RTE_PMD_IXGBE_MB_EVENT_PROCEED)
			retval = ixgbe_vf_set_vlan(dev, vf, msgbuf);
		break;
	case IXGBE_VF_API_NEGOTIATE:
		retval = ixgbe_negotiate_vf_api(dev, vf, msgbuf);
		break;
	case IXGBE_VF_GET_QUEUES:
		retval = ixgbe_get_vf_queues(dev, vf, msgbuf);
		msg_size = IXGBE_VF_GET_QUEUE_MSG_SIZE;
		break;
	case IXGBE_VF_UPDATE_XCAST_MODE:
		if (retval == RTE_PMD_IXGBE_MB_EVENT_PROCEED)
			retval = ixgbe_set_vf_mc_promisc(dev, vf, msgbuf);
		break;
	default:
		PMD_DRV_LOG(DEBUG, "Unhandled Msg %8.8x", (unsigned)msgbuf[0]);
		retval = IXGBE_ERR_MBX;
		break;
	}

	/* response the VF according to the message process result */
	if (retval)
		msgbuf[0] |= IXGBE_VT_MSGTYPE_NACK;
	else
		msgbuf[0] |= IXGBE_VT_MSGTYPE_ACK;

	msgbuf[0] |= IXGBE_VT_MSGTYPE_CTS;

	ixgbe_write_mbx(hw, msgbuf, msg_size, vf);

	return retval;
}

static inline void
ixgbe_rcv_ack_from_vf(struct rte_eth_dev *dev, uint16_t vf)
{
	uint32_t msg = IXGBE_VT_MSGTYPE_NACK;
	struct ixgbe_hw *hw =
		IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	struct ixgbe_vf_info *vfinfo =
		*IXGBE_DEV_PRIVATE_TO_P_VFDATA(dev->data->dev_private);

	if (!vfinfo[vf].clear_to_send)
		ixgbe_write_mbx(hw, &msg, 1, vf);
}

void ixgbe_pf_mbx_process(struct rte_eth_dev *eth_dev)
{
	uint16_t vf;
	struct ixgbe_hw *hw =
		IXGBE_DEV_PRIVATE_TO_HW(eth_dev->data->dev_private);

	for (vf = 0; vf < dev_num_vf(eth_dev); vf++) {
		/* check & process vf function level reset */
		if (!ixgbe_check_for_rst(hw, vf))
			ixgbe_vf_reset_event(eth_dev, vf);

		/* check & process vf mailbox messages */
		if (!ixgbe_check_for_msg(hw, vf))
			ixgbe_rcv_msg_from_vf(eth_dev, vf);

		/* check & process acks from vf */
		if (!ixgbe_check_for_ack(hw, vf))
			ixgbe_rcv_ack_from_vf(eth_dev, vf);
	}
}