summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
blob: 2d971d18696e569d59b522ad4304f57ce52c408a (plain) (blame)
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
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
/*******************************************************************************

  Intel 10 Gigabit PCI Express Linux driver
  Copyright(c) 1999 - 2012 Intel Corporation.

  This program is free software; you can redistribute it and/or modify it
  under the terms and conditions of the GNU General Public License,
  version 2, as published by the Free Software Foundation.

  This program is distributed in the hope it will be useful, but WITHOUT
  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  more details.

  You should have received a copy of the GNU General Public License along with
  this program; if not, write to the Free Software Foundation, Inc.,
  51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.

  The full GNU General Public License is included in this distribution in
  the file called "COPYING".

  Contact Information:
  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497

*******************************************************************************/

#include <linux/types.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/netdevice.h>
#include <linux/vmalloc.h>
#include <linux/string.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/ipv6.h>
#ifdef NETIF_F_HW_VLAN_TX
#include <linux/if_vlan.h>
#endif

#include "ixgbe.h"
#include "ixgbe_type.h"
#include "ixgbe_sriov.h"

#ifdef CONFIG_PCI_IOV
static int ixgbe_find_enabled_vfs(struct ixgbe_adapter *adapter)
{
	struct pci_dev *pdev = adapter->pdev;
	struct pci_dev *pvfdev;
	u16 vf_devfn = 0;
	int device_id;
	int vfs_found = 0;

	switch (adapter->hw.mac.type) {
	case ixgbe_mac_82599EB:
		device_id = IXGBE_DEV_ID_82599_VF;
		break;
	case ixgbe_mac_X540:
		device_id = IXGBE_DEV_ID_X540_VF;
		break;
	default:
		device_id = 0;
		break;
	}

	vf_devfn = pdev->devfn + 0x80;
	pvfdev = pci_get_device(IXGBE_INTEL_VENDOR_ID, device_id, NULL);
	while (pvfdev) {
		if (pvfdev->devfn == vf_devfn &&
		    (pvfdev->bus->number >= pdev->bus->number))
			vfs_found++;
		vf_devfn += 2;
		pvfdev = pci_get_device(IXGBE_INTEL_VENDOR_ID,
					device_id, pvfdev);
	}

	return vfs_found;
}

void ixgbe_enable_sriov(struct ixgbe_adapter *adapter,
			 const struct ixgbe_info *ii)
{
	struct ixgbe_hw *hw = &adapter->hw;
	int err = 0;
	int num_vf_macvlans, i;
	struct vf_macvlans *mv_list;
	int pre_existing_vfs = 0;

	pre_existing_vfs = ixgbe_find_enabled_vfs(adapter);
	if (!pre_existing_vfs && !adapter->num_vfs)
		return;

	/* If there are pre-existing VFs then we have to force
	 * use of that many because they were not deleted the last
	 * time someone removed the PF driver.  That would have
	 * been because they were allocated to guest VMs and can't
	 * be removed.  Go ahead and just re-enable the old amount.
	 * If the user wants to change the number of VFs they can
	 * use ethtool while making sure no VFs are allocated to
	 * guest VMs... i.e. the right way.
	 */
	if (pre_existing_vfs) {
		adapter->num_vfs = pre_existing_vfs;
		dev_warn(&adapter->pdev->dev, "Virtual Functions already "
			 "enabled for this device - Please reload all "
			 "VF drivers to avoid spoofed packet errors\n");
	} else {
		err = pci_enable_sriov(adapter->pdev, adapter->num_vfs);
	}
	if (err) {
		e_err(probe, "Failed to enable PCI sriov: %d\n", err);
		goto err_novfs;
	}
	adapter->flags |= IXGBE_FLAG_SRIOV_ENABLED;

	e_info(probe, "SR-IOV enabled with %d VFs\n", adapter->num_vfs);

	num_vf_macvlans = hw->mac.num_rar_entries -
	(IXGBE_MAX_PF_MACVLANS + 1 + adapter->num_vfs);

	adapter->mv_list = mv_list = kcalloc(num_vf_macvlans,
					     sizeof(struct vf_macvlans),
					     GFP_KERNEL);
	if (mv_list) {
		/* Initialize list of VF macvlans */
		INIT_LIST_HEAD(&adapter->vf_mvs.l);
		for (i = 0; i < num_vf_macvlans; i++) {
			mv_list->vf = -1;
			mv_list->free = true;
			mv_list->rar_entry = hw->mac.num_rar_entries -
				(i + adapter->num_vfs + 1);
			list_add(&mv_list->l, &adapter->vf_mvs.l);
			mv_list++;
		}
	}

	/* If call to enable VFs succeeded then allocate memory
	 * for per VF control structures.
	 */
	adapter->vfinfo =
		kcalloc(adapter->num_vfs,
			sizeof(struct vf_data_storage), GFP_KERNEL);
	if (adapter->vfinfo) {
		/* Now that we're sure SR-IOV is enabled
		 * and memory allocated set up the mailbox parameters
		 */
		ixgbe_init_mbx_params_pf(hw);
		memcpy(&hw->mbx.ops, ii->mbx_ops,
		       sizeof(hw->mbx.ops));

		/* Disable RSC when in SR-IOV mode */
		adapter->flags2 &= ~(IXGBE_FLAG2_RSC_CAPABLE |
				     IXGBE_FLAG2_RSC_ENABLED);
		for (i = 0; i < adapter->num_vfs; i++)
			adapter->vfinfo[i].spoofchk_enabled = true;
		return;
	}

	/* Oh oh */
	e_err(probe, "Unable to allocate memory for VF Data Storage - "
	      "SRIOV disabled\n");
	pci_disable_sriov(adapter->pdev);

err_novfs:
	adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED;
	adapter->num_vfs = 0;
}
#endif /* #ifdef CONFIG_PCI_IOV */

void ixgbe_disable_sriov(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 gcr;
	u32 gpie;
	u32 vmdctl;
	int i;

#ifdef CONFIG_PCI_IOV
	/* disable iov and allow time for transactions to clear */
	pci_disable_sriov(adapter->pdev);
#endif

	/* turn off device IOV mode */
	gcr = IXGBE_READ_REG(hw, IXGBE_GCR_EXT);
	gcr &= ~(IXGBE_GCR_EXT_SRIOV);
	IXGBE_WRITE_REG(hw, IXGBE_GCR_EXT, gcr);
	gpie = IXGBE_READ_REG(hw, IXGBE_GPIE);
	gpie &= ~IXGBE_GPIE_VTMODE_MASK;
	IXGBE_WRITE_REG(hw, IXGBE_GPIE, gpie);

	/* set default pool back to 0 */
	vmdctl = IXGBE_READ_REG(hw, IXGBE_VT_CTL);
	vmdctl &= ~IXGBE_VT_CTL_POOL_MASK;
	IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, vmdctl);
	IXGBE_WRITE_FLUSH(hw);

	/* take a breather then clean up driver data */
	msleep(100);

	/* Release reference to VF devices */
	for (i = 0; i < adapter->num_vfs; i++) {
		if (adapter->vfinfo[i].vfdev)
			pci_dev_put(adapter->vfinfo[i].vfdev);
	}
	kfree(adapter->vfinfo);
	kfree(adapter->mv_list);
	adapter->vfinfo = NULL;

	adapter->num_vfs = 0;
	adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED;
}

static int ixgbe_set_vf_multicasts(struct ixgbe_adapter *adapter,
				   int entries, u16 *hash_list, u32 vf)
{
	struct vf_data_storage *vfinfo = &adapter->vfinfo[vf];
	struct ixgbe_hw *hw = &adapter->hw;
	int i;
	u32 vector_bit;
	u32 vector_reg;
	u32 mta_reg;

	/* only so many hash values supported */
	entries = min(entries, IXGBE_MAX_VF_MC_ENTRIES);

	/*
	 * salt away the number of multi cast addresses assigned
	 * to this VF for later use to restore when the PF multi cast
	 * list changes
	 */
	vfinfo->num_vf_mc_hashes = entries;

	/*
	 * VFs are limited to using the MTA hash table for their multicast
	 * addresses
	 */
	for (i = 0; i < entries; i++) {
		vfinfo->vf_mc_hashes[i] = hash_list[i];
	}

	for (i = 0; i < vfinfo->num_vf_mc_hashes; i++) {
		vector_reg = (vfinfo->vf_mc_hashes[i] >> 5) & 0x7F;
		vector_bit = vfinfo->vf_mc_hashes[i] & 0x1F;
		mta_reg = IXGBE_READ_REG(hw, IXGBE_MTA(vector_reg));
		mta_reg |= (1 << vector_bit);
		IXGBE_WRITE_REG(hw, IXGBE_MTA(vector_reg), mta_reg);
	}

	return 0;
}

static void ixgbe_restore_vf_macvlans(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	struct list_head *pos;
	struct vf_macvlans *entry;

	list_for_each(pos, &adapter->vf_mvs.l) {
		entry = list_entry(pos, struct vf_macvlans, l);
		if (!entry->free)
			hw->mac.ops.set_rar(hw, entry->rar_entry,
					    entry->vf_macvlan,
					    entry->vf, IXGBE_RAH_AV);
	}
}

void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	struct vf_data_storage *vfinfo;
	int i, j;
	u32 vector_bit;
	u32 vector_reg;
	u32 mta_reg;

	for (i = 0; i < adapter->num_vfs; i++) {
		vfinfo = &adapter->vfinfo[i];
		for (j = 0; j < vfinfo->num_vf_mc_hashes; j++) {
			hw->addr_ctrl.mta_in_use++;
			vector_reg = (vfinfo->vf_mc_hashes[j] >> 5) & 0x7F;
			vector_bit = vfinfo->vf_mc_hashes[j] & 0x1F;
			mta_reg = IXGBE_READ_REG(hw, IXGBE_MTA(vector_reg));
			mta_reg |= (1 << vector_bit);
			IXGBE_WRITE_REG(hw, IXGBE_MTA(vector_reg), mta_reg);
		}
	}

	/* Restore any VF macvlans */
	ixgbe_restore_vf_macvlans(adapter);
}

static int ixgbe_set_vf_vlan(struct ixgbe_adapter *adapter, int add, int vid,
			     u32 vf)
{
	return adapter->hw.mac.ops.set_vfta(&adapter->hw, vid, vf, (bool)add);
}

static void ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 *msgbuf)
{
	struct ixgbe_hw *hw = &adapter->hw;
	int new_mtu = msgbuf[1];
	u32 max_frs;
	int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN;

	/* Only X540 supports jumbo frames in IOV mode */
	if (adapter->hw.mac.type != ixgbe_mac_X540)
		return;

	/* MTU < 68 is an error and causes problems on some kernels */
	if ((new_mtu < 68) || (max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE)) {
		e_err(drv, "VF mtu %d out of range\n", new_mtu);
		return;
	}

	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);
	}

	e_info(hw, "VF requests change max MTU to %d\n", new_mtu);
}

static void ixgbe_set_vmolr(struct ixgbe_hw *hw, u32 vf, bool aupe)
{
	u32 vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(vf));
	vmolr |= (IXGBE_VMOLR_ROMPE |
		  IXGBE_VMOLR_BAM);
	if (aupe)
		vmolr |= IXGBE_VMOLR_AUPE;
	else
		vmolr &= ~IXGBE_VMOLR_AUPE;
	IXGBE_WRITE_REG(hw, IXGBE_VMOLR(vf), vmolr);
}

static void ixgbe_set_vmvir(struct ixgbe_adapter *adapter, u32 vid, u32 vf)
{
	struct ixgbe_hw *hw = &adapter->hw;

	if (vid)
		IXGBE_WRITE_REG(hw, IXGBE_VMVIR(vf),
				(vid | IXGBE_VMVIR_VLANA_DEFAULT));
	else
		IXGBE_WRITE_REG(hw, IXGBE_VMVIR(vf), 0);
}

static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf)
{
	struct ixgbe_hw *hw = &adapter->hw;
	int rar_entry = hw->mac.num_rar_entries - (vf + 1);

	/* reset offloads to defaults */
	if (adapter->vfinfo[vf].pf_vlan) {
		ixgbe_set_vf_vlan(adapter, true,
				  adapter->vfinfo[vf].pf_vlan, vf);
		ixgbe_set_vmvir(adapter,
				(adapter->vfinfo[vf].pf_vlan |
				 (adapter->vfinfo[vf].pf_qos <<
				  VLAN_PRIO_SHIFT)), vf);
		ixgbe_set_vmolr(hw, vf, false);
	} else {
		ixgbe_set_vmvir(adapter, 0, vf);
		ixgbe_set_vmolr(hw, vf, true);
	}

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

	/* Flush and reset the mta with the new values */
	ixgbe_set_rx_mode(adapter->netdev);

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

static int ixgbe_set_vf_mac(struct ixgbe_adapter *adapter,
			    int vf, unsigned char *mac_addr)
{
	struct ixgbe_hw *hw = &adapter->hw;
	int rar_entry = hw->mac.num_rar_entries - (vf + 1);

	memcpy(adapter->vfinfo[vf].vf_mac_addresses, mac_addr, 6);
	hw->mac.ops.set_rar(hw, rar_entry, mac_addr, vf, IXGBE_RAH_AV);

	return 0;
}

static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter,
				int vf, int index, unsigned char *mac_addr)
{
	struct ixgbe_hw *hw = &adapter->hw;
	struct list_head *pos;
	struct vf_macvlans *entry;

	if (index <= 1) {
		list_for_each(pos, &adapter->vf_mvs.l) {
			entry = list_entry(pos, struct vf_macvlans, l);
			if (entry->vf == vf) {
				entry->vf = -1;
				entry->free = true;
				entry->is_macvlan = false;
				hw->mac.ops.clear_rar(hw, entry->rar_entry);
			}
		}
	}

	/*
	 * If index was zero then we were asked to clear the uc list
	 * for the VF.  We're done.
	 */
	if (!index)
		return 0;

	entry = NULL;

	list_for_each(pos, &adapter->vf_mvs.l) {
		entry = list_entry(pos, struct vf_macvlans, l);
		if (entry->free)
			break;
	}

	/*
	 * If we traversed the entire list and didn't find a free entry
	 * then we're out of space on the RAR table.  Also entry may
	 * be NULL because the original memory allocation for the list
	 * failed, which is not fatal but does mean we can't support
	 * VF requests for MACVLAN because we couldn't allocate
	 * memory for the list management required.
	 */
	if (!entry || !entry->free)
		return -ENOSPC;

	entry->free = false;
	entry->is_macvlan = true;
	entry->vf = vf;
	memcpy(entry->vf_macvlan, mac_addr, ETH_ALEN);

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

	return 0;
}

int ixgbe_check_vf_assignment(struct ixgbe_adapter *adapter)
{
#ifdef CONFIG_PCI_IOV
	int i;
	for (i = 0; i < adapter->num_vfs; i++) {
		if (adapter->vfinfo[i].vfdev->dev_flags &
				PCI_DEV_FLAGS_ASSIGNED)
			return true;
	}
#endif
	return false;
}

int ixgbe_vf_configuration(struct pci_dev *pdev, unsigned int event_mask)
{
	unsigned char vf_mac_addr[6];
	struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
	unsigned int vfn = (event_mask & 0x3f);
	struct pci_dev *pvfdev;
	unsigned int device_id;
	u16 thisvf_devfn = (pdev->devfn + 0x80 + (vfn << 1)) |
				(pdev->devfn & 1);

	bool enable = ((event_mask & 0x10000000U) != 0);

	if (enable) {
		random_ether_addr(vf_mac_addr);
		e_info(probe, "IOV: VF %d is enabled MAC %pM\n",
		       vfn, vf_mac_addr);
		/*
		 * Store away the VF "permananet" MAC address, it will ask
		 * for it later.
		 */
		memcpy(adapter->vfinfo[vfn].vf_mac_addresses, vf_mac_addr, 6);

		switch (adapter->hw.mac.type) {
		case ixgbe_mac_82599EB:
			device_id = IXGBE_DEV_ID_82599_VF;
			break;
		case ixgbe_mac_X540:
			device_id = IXGBE_DEV_ID_X540_VF;
			break;
		default:
			device_id = 0;
			break;
		}

		pvfdev = pci_get_device(IXGBE_INTEL_VENDOR_ID, device_id, NULL);
		while (pvfdev) {
			if (pvfdev->devfn == thisvf_devfn)
				break;
			pvfdev = pci_get_device(IXGBE_INTEL_VENDOR_ID,
						device_id, pvfdev);
		}
		if (pvfdev)
			adapter->vfinfo[vfn].vfdev = pvfdev;
		else
			e_err(drv, "Couldn't find pci dev ptr for VF %4.4x\n",
			      thisvf_devfn);
	}

	return 0;
}

static inline void ixgbe_vf_reset_msg(struct ixgbe_adapter *adapter, u32 vf)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 reg;
	u32 reg_offset, vf_shift;

	vf_shift = vf % 32;
	reg_offset = vf / 32;

	/* enable transmit and receive 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);

	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(adapter, vf);
}

static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf)
{
	u32 mbx_size = IXGBE_VFMAILBOX_SIZE;
	u32 msgbuf[IXGBE_VFMAILBOX_SIZE];
	struct ixgbe_hw *hw = &adapter->hw;
	s32 retval;
	int entries;
	u16 *hash_list;
	int add, vid, index;
	u8 *new_mac;

	retval = ixgbe_read_mbx(hw, msgbuf, mbx_size, vf);

	if (retval) {
		pr_err("Error receiving message from VF\n");
		return retval;
	}

	/* this is a message we already processed, do nothing */
	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);

	/*
	 * until the vf completes a virtual function reset it should not be
	 * allowed to start any configuration.
	 */

	if (msgbuf[0] == IXGBE_VF_RESET) {
		unsigned char *vf_mac = adapter->vfinfo[vf].vf_mac_addresses;
		new_mac = (u8 *)(&msgbuf[1]);
		e_info(probe, "VF Reset msg received from vf %d\n", vf);
		adapter->vfinfo[vf].clear_to_send = false;
		ixgbe_vf_reset_msg(adapter, vf);
		adapter->vfinfo[vf].clear_to_send = true;

		if (is_valid_ether_addr(new_mac) &&
		    !adapter->vfinfo[vf].pf_set_mac)
			ixgbe_set_vf_mac(adapter, vf, vf_mac);
		else
			ixgbe_set_vf_mac(adapter,
				 vf, adapter->vfinfo[vf].vf_mac_addresses);

		/* reply to reset with ack and vf mac address */
		msgbuf[0] = IXGBE_VF_RESET | IXGBE_VT_MSGTYPE_ACK;
		memcpy(new_mac, vf_mac, ETH_ALEN);
		/*
		 * 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 retval;
	}

	if (!adapter->vfinfo[vf].clear_to_send) {
		msgbuf[0] |= IXGBE_VT_MSGTYPE_NACK;
		ixgbe_write_mbx(hw, msgbuf, 1, vf);
		return retval;
	}

	switch ((msgbuf[0] & 0xFFFF)) {
	case IXGBE_VF_SET_MAC_ADDR:
		new_mac = ((u8 *)(&msgbuf[1]));
		if (is_valid_ether_addr(new_mac) &&
		    !adapter->vfinfo[vf].pf_set_mac) {
			ixgbe_set_vf_mac(adapter, vf, new_mac);
		} else if (memcmp(adapter->vfinfo[vf].vf_mac_addresses,
				  new_mac, ETH_ALEN)) {
			e_warn(drv, "VF %d attempted to override "
			       "administratively set MAC address\nReload "
			       "the VF driver to resume operations\n", vf);
			retval = -1;
		}
		break;
	case IXGBE_VF_SET_MULTICAST:
		entries = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK)
		          >> IXGBE_VT_MSGINFO_SHIFT;
		hash_list = (u16 *)&msgbuf[1];
		retval = ixgbe_set_vf_multicasts(adapter, entries,
		                                 hash_list, vf);
		break;
	case IXGBE_VF_SET_LPE:
		ixgbe_set_vf_lpe(adapter, msgbuf);
		break;
	case IXGBE_VF_SET_VLAN:
		add = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK)
		      >> IXGBE_VT_MSGINFO_SHIFT;
		vid = (msgbuf[1] & IXGBE_VLVF_VLANID_MASK);
		if (adapter->vfinfo[vf].pf_vlan) {
			e_warn(drv, "VF %d attempted to override "
			       "administratively set VLAN configuration\n"
			       "Reload the VF driver to resume operations\n",
			       vf);
			retval = -1;
		} else {
			if (add)
				adapter->vfinfo[vf].vlan_count++;
			else if (adapter->vfinfo[vf].vlan_count)
				adapter->vfinfo[vf].vlan_count--;
			retval = ixgbe_set_vf_vlan(adapter, add, vid, vf);
			if (!retval && adapter->vfinfo[vf].spoofchk_enabled)
				hw->mac.ops.set_vlan_anti_spoofing(hw, true, vf);
		}
		break;
	case IXGBE_VF_SET_MACVLAN:
		index = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) >>
			IXGBE_VT_MSGINFO_SHIFT;
		if (adapter->vfinfo[vf].pf_set_mac && index > 0) {
			e_warn(drv, "VF %d requested MACVLAN filter but is "
				    "administratively denied\n", vf);
			retval = -1;
			break;
		}
		/*
		 * If the VF is allowed to set MAC filters then turn off
		 * anti-spoofing to avoid false positives.  An index
		 * greater than 0 will indicate the VF is setting a
		 * macvlan MAC filter.
		 */
		if (index > 0 && adapter->vfinfo[vf].spoofchk_enabled)
			ixgbe_ndo_set_vf_spoofchk(adapter->netdev, vf, false);
		retval = ixgbe_set_vf_macvlan(adapter, vf, index,
					      (unsigned char *)(&msgbuf[1]));
		if (retval == -ENOSPC)
			e_warn(drv, "VF %d has requested a MACVLAN filter "
				    "but there is no space for it\n", vf);
		break;
	default:
		e_err(drv, "Unhandled Msg %8.8x\n", msgbuf[0]);
		retval = IXGBE_ERR_MBX;
		break;
	}

	/* notify the VF of the results of what it sent us */
	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, 1, vf);

	return retval;
}

static void ixgbe_rcv_ack_from_vf(struct ixgbe_adapter *adapter, u32 vf)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 msg = IXGBE_VT_MSGTYPE_NACK;

	/* if device isn't clear to send it shouldn't be reading either */
	if (!adapter->vfinfo[vf].clear_to_send)
		ixgbe_write_mbx(hw, &msg, 1, vf);
}

void ixgbe_msg_task(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 vf;

	for (vf = 0; vf < adapter->num_vfs; vf++) {
		/* process any reset requests */
		if (!ixgbe_check_for_rst(hw, vf))
			ixgbe_vf_reset_event(adapter, vf);

		/* process any messages pending */
		if (!ixgbe_check_for_msg(hw, vf))
			ixgbe_rcv_msg_from_vf(adapter, vf);

		/* process any acks */
		if (!ixgbe_check_for_ack(hw, vf))
			ixgbe_rcv_ack_from_vf(adapter, vf);
	}
}

void ixgbe_disable_tx_rx(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;

	/* disable transmit and receive for all vfs */
	IXGBE_WRITE_REG(hw, IXGBE_VFTE(0), 0);
	IXGBE_WRITE_REG(hw, IXGBE_VFTE(1), 0);

	IXGBE_WRITE_REG(hw, IXGBE_VFRE(0), 0);
	IXGBE_WRITE_REG(hw, IXGBE_VFRE(1), 0);
}

void ixgbe_ping_all_vfs(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 ping;
	int i;

	for (i = 0 ; i < adapter->num_vfs; i++) {
		ping = IXGBE_PF_CONTROL_MSG;
		if (adapter->vfinfo[i].clear_to_send)
			ping |= IXGBE_VT_MSGTYPE_CTS;
		ixgbe_write_mbx(hw, &ping, 1, i);
	}
}

int ixgbe_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
{
	struct ixgbe_adapter *adapter = netdev_priv(netdev);
	if (!is_valid_ether_addr(mac) || (vf >= adapter->num_vfs))
		return -EINVAL;
	adapter->vfinfo[vf].pf_set_mac = true;
	dev_info(&adapter->pdev->dev, "setting MAC %pM on VF %d\n", mac, vf);
	dev_info(&adapter->pdev->dev, "Reload the VF driver to make this"
				      " change effective.");
	if (test_bit(__IXGBE_DOWN, &adapter->state)) {
		dev_warn(&adapter->pdev->dev, "The VF MAC address has been set,"
			 " but the PF device is not up.\n");
		dev_warn(&adapter->pdev->dev, "Bring the PF device up before"
			 " attempting to use the VF device.\n");
	}
	return ixgbe_set_vf_mac(adapter, vf, mac);
}

int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos)
{
	int err = 0;
	struct ixgbe_adapter *adapter = netdev_priv(netdev);
	struct ixgbe_hw *hw = &adapter->hw;

	if ((vf >= adapter->num_vfs) || (vlan > 4095) || (qos > 7))
		return -EINVAL;
	if (vlan || qos) {
		err = ixgbe_set_vf_vlan(adapter, true, vlan, vf);
		if (err)
			goto out;
		ixgbe_set_vmvir(adapter, vlan | (qos << VLAN_PRIO_SHIFT), vf);
		ixgbe_set_vmolr(hw, vf, false);
		if (adapter->vfinfo[vf].spoofchk_enabled)
			hw->mac.ops.set_vlan_anti_spoofing(hw, true, vf);
		adapter->vfinfo[vf].vlan_count++;
		adapter->vfinfo[vf].pf_vlan = vlan;
		adapter->vfinfo[vf].pf_qos = qos;
		dev_info(&adapter->pdev->dev,
			 "Setting VLAN %d, QOS 0x%x on VF %d\n", vlan, qos, vf);
		if (test_bit(__IXGBE_DOWN, &adapter->state)) {
			dev_warn(&adapter->pdev->dev,
				 "The VF VLAN has been set,"
				 " but the PF device is not up.\n");
			dev_warn(&adapter->pdev->dev,
				 "Bring the PF device up before"
				 " attempting to use the VF device.\n");
		}
	} else {
		err = ixgbe_set_vf_vlan(adapter, false,
					adapter->vfinfo[vf].pf_vlan, vf);
		ixgbe_set_vmvir(adapter, vlan, vf);
		ixgbe_set_vmolr(hw, vf, true);
		hw->mac.ops.set_vlan_anti_spoofing(hw, false, vf);
		if (adapter->vfinfo[vf].vlan_count)
			adapter->vfinfo[vf].vlan_count--;
		adapter->vfinfo[vf].pf_vlan = 0;
		adapter->vfinfo[vf].pf_qos = 0;
       }
out:
       return err;
}

static int ixgbe_link_mbps(int internal_link_speed)
{
	switch (internal_link_speed) {
	case IXGBE_LINK_SPEED_100_FULL:
		return 100;
	case IXGBE_LINK_SPEED_1GB_FULL:
		return 1000;
	case IXGBE_LINK_SPEED_10GB_FULL:
		return 10000;
	default:
		return 0;
	}
}

static void ixgbe_set_vf_rate_limit(struct ixgbe_hw *hw, int vf, int tx_rate,
				    int link_speed)
{
	int rf_dec, rf_int;
	u32 bcnrc_val;

	if (tx_rate != 0) {
		/* Calculate the rate factor values to set */
		rf_int = link_speed / tx_rate;
		rf_dec = (link_speed - (rf_int * tx_rate));
		rf_dec = (rf_dec * (1<<IXGBE_RTTBCNRC_RF_INT_SHIFT)) / tx_rate;

		bcnrc_val = IXGBE_RTTBCNRC_RS_ENA;
		bcnrc_val |= ((rf_int<<IXGBE_RTTBCNRC_RF_INT_SHIFT) &
		               IXGBE_RTTBCNRC_RF_INT_MASK);
		bcnrc_val |= (rf_dec & IXGBE_RTTBCNRC_RF_DEC_MASK);
	} else {
		bcnrc_val = 0;
	}

	IXGBE_WRITE_REG(hw, IXGBE_RTTDQSEL, 2*vf); /* vf Y uses queue 2*Y */
	/*
	 * Set global transmit compensation time to the MMW_SIZE in RTTBCNRM
	 * register. Typically MMW_SIZE=0x014 if 9728-byte jumbo is supported
	 * and 0x004 otherwise.
	 */
	switch (hw->mac.type) {
	case ixgbe_mac_82599EB:
		IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRM, 0x4);
		break;
	case ixgbe_mac_X540:
		IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRM, 0x14);
		break;
	default:
		break;
	}

	IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRC, bcnrc_val);
}

void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter)
{
	int actual_link_speed, i;
	bool reset_rate = false;

	/* VF Tx rate limit was not set */
	if (adapter->vf_rate_link_speed == 0)
		return;

	actual_link_speed = ixgbe_link_mbps(adapter->link_speed);
	if (actual_link_speed != adapter->vf_rate_link_speed) {
		reset_rate = true;
		adapter->vf_rate_link_speed = 0;
		dev_info(&adapter->pdev->dev,
		         "Link speed has been changed. VF Transmit rate "
		         "is disabled\n");
	}

	for (i = 0; i < adapter->num_vfs; i++) {
		if (reset_rate)
			adapter->vfinfo[i].tx_rate = 0;

		ixgbe_set_vf_rate_limit(&adapter->hw, i,
					adapter->vfinfo[i].tx_rate,
					actual_link_speed);
	}
}

int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate)
{
	struct ixgbe_adapter *adapter = netdev_priv(netdev);
	struct ixgbe_hw *hw = &adapter->hw;
	int actual_link_speed;

	actual_link_speed = ixgbe_link_mbps(adapter->link_speed);
	if ((vf >= adapter->num_vfs) || (!adapter->link_up) ||
	    (tx_rate > actual_link_speed) || (actual_link_speed != 10000) ||
	    ((tx_rate != 0) && (tx_rate <= 10)))
	    /* rate limit cannot be set to 10Mb or less in 10Gb adapters */
		return -EINVAL;

	adapter->vf_rate_link_speed = actual_link_speed;
	adapter->vfinfo[vf].tx_rate = (u16)tx_rate;
	ixgbe_set_vf_rate_limit(hw, vf, tx_rate, actual_link_speed);

	return 0;
}

int ixgbe_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting)
{
	struct ixgbe_adapter *adapter = netdev_priv(netdev);
	int vf_target_reg = vf >> 3;
	int vf_target_shift = vf % 8;
	struct ixgbe_hw *hw = &adapter->hw;
	u32 regval;

	adapter->vfinfo[vf].spoofchk_enabled = setting;

	regval = IXGBE_READ_REG(hw, IXGBE_PFVFSPOOF(vf_target_reg));
	regval &= ~(1 << vf_target_shift);
	regval |= (setting << vf_target_shift);
	IXGBE_WRITE_REG(hw, IXGBE_PFVFSPOOF(vf_target_reg), regval);

	if (adapter->vfinfo[vf].vlan_count) {
		vf_target_shift += IXGBE_SPOOF_VLANAS_SHIFT;
		regval = IXGBE_READ_REG(hw, IXGBE_PFVFSPOOF(vf_target_reg));
		regval &= ~(1 << vf_target_shift);
		regval |= (setting << vf_target_shift);
		IXGBE_WRITE_REG(hw, IXGBE_PFVFSPOOF(vf_target_reg), regval);
	}

	return 0;
}

int ixgbe_ndo_get_vf_config(struct net_device *netdev,
			    int vf, struct ifla_vf_info *ivi)
{
	struct ixgbe_adapter *adapter = netdev_priv(netdev);
	if (vf >= adapter->num_vfs)
		return -EINVAL;
	ivi->vf = vf;
	memcpy(&ivi->mac, adapter->vfinfo[vf].vf_mac_addresses, ETH_ALEN);
	ivi->tx_rate = adapter->vfinfo[vf].tx_rate;
	ivi->vlan = adapter->vfinfo[vf].pf_vlan;
	ivi->qos = adapter->vfinfo[vf].pf_qos;
	ivi->spoofchk = adapter->vfinfo[vf].spoofchk_enabled;
	return 0;
}