aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/net/ibmveth.c
blob: 91ec9fdc718482247e5058d74893f61b6e0230e0 (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
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
/**************************************************************************/
/*                                                                        */
/* IBM eServer i/pSeries Virtual Ethernet Device Driver                   */
/* Copyright (C) 2003 IBM Corp.                                           */
/*  Originally written by Dave Larson (larson1@us.ibm.com)                */
/*  Maintained by Santiago Leon (santil@us.ibm.com)                       */
/*                                                                        */
/*  This program is free software; you can redistribute it and/or modify  */
/*  it under the terms of the GNU General Public License as published by  */
/*  the Free Software Foundation; either version 2 of the License, or     */
/*  (at your option) any later version.                                   */
/*                                                                        */
/*  This program is distributed in the hope that 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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  */
/*                                                                   USA  */
/*                                                                        */
/* This module contains the implementation of a virtual ethernet device   */
/* for use with IBM i/pSeries LPAR Linux.  It utilizes the logical LAN    */
/* option of the RS/6000 Platform Architechture to interface with virtual */
/* ethernet NICs that are presented to the partition by the hypervisor.   */
/*                                                                        */
/**************************************************************************/
/*
  TODO:
  - add support for sysfs
  - possibly remove procfs support
*/

#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/ioport.h>
#include <linux/dma-mapping.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/mm.h>
#include <linux/ethtool.h>
#include <linux/proc_fs.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <net/net_namespace.h>
#include <asm/hvcall.h>
#include <asm/atomic.h>
#include <asm/vio.h>
#include <asm/iommu.h>
#include <asm/uaccess.h>
#include <asm/firmware.h>
#include <linux/seq_file.h>

#include "ibmveth.h"

#undef DEBUG

#define ibmveth_printk(fmt, args...) \
  printk(KERN_DEBUG "%s: " fmt, __FILE__, ## args)

#define ibmveth_error_printk(fmt, args...) \
  printk(KERN_ERR "(%s:%3.3d ua:%x) ERROR: " fmt, __FILE__, __LINE__ , adapter->vdev->unit_address, ## args)

#ifdef DEBUG
#define ibmveth_debug_printk_no_adapter(fmt, args...) \
  printk(KERN_DEBUG "(%s:%3.3d): " fmt, __FILE__, __LINE__ , ## args)
#define ibmveth_debug_printk(fmt, args...) \
  printk(KERN_DEBUG "(%s:%3.3d ua:%x): " fmt, __FILE__, __LINE__ , adapter->vdev->unit_address, ## args)
#define ibmveth_assert(expr) \
  if(!(expr)) {                                   \
    printk(KERN_DEBUG "assertion failed (%s:%3.3d ua:%x): %s\n", __FILE__, __LINE__, adapter->vdev->unit_address, #expr); \
    BUG(); \
  }
#else
#define ibmveth_debug_printk_no_adapter(fmt, args...)
#define ibmveth_debug_printk(fmt, args...)
#define ibmveth_assert(expr)
#endif

static int ibmveth_open(struct net_device *dev);
static int ibmveth_close(struct net_device *dev);
static int ibmveth_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd);
static int ibmveth_poll(struct napi_struct *napi, int budget);
static int ibmveth_start_xmit(struct sk_buff *skb, struct net_device *dev);
static void ibmveth_set_multicast_list(struct net_device *dev);
static int ibmveth_change_mtu(struct net_device *dev, int new_mtu);
static void ibmveth_proc_register_driver(void);
static void ibmveth_proc_unregister_driver(void);
static void ibmveth_proc_register_adapter(struct ibmveth_adapter *adapter);
static void ibmveth_proc_unregister_adapter(struct ibmveth_adapter *adapter);
static irqreturn_t ibmveth_interrupt(int irq, void *dev_instance);
static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter);
static unsigned long ibmveth_get_desired_dma(struct vio_dev *vdev);
static struct kobj_type ktype_veth_pool;


#ifdef CONFIG_PROC_FS
#define IBMVETH_PROC_DIR "ibmveth"
static struct proc_dir_entry *ibmveth_proc_dir;
#endif

static const char ibmveth_driver_name[] = "ibmveth";
static const char ibmveth_driver_string[] = "IBM i/pSeries Virtual Ethernet Driver";
#define ibmveth_driver_version "1.03"

MODULE_AUTHOR("Santiago Leon <santil@us.ibm.com>");
MODULE_DESCRIPTION("IBM i/pSeries Virtual Ethernet Driver");
MODULE_LICENSE("GPL");
MODULE_VERSION(ibmveth_driver_version);

struct ibmveth_stat {
	char name[ETH_GSTRING_LEN];
	int offset;
};

#define IBMVETH_STAT_OFF(stat) offsetof(struct ibmveth_adapter, stat)
#define IBMVETH_GET_STAT(a, off) *((u64 *)(((unsigned long)(a)) + off))

struct ibmveth_stat ibmveth_stats[] = {
	{ "replenish_task_cycles", IBMVETH_STAT_OFF(replenish_task_cycles) },
	{ "replenish_no_mem", IBMVETH_STAT_OFF(replenish_no_mem) },
	{ "replenish_add_buff_failure", IBMVETH_STAT_OFF(replenish_add_buff_failure) },
	{ "replenish_add_buff_success", IBMVETH_STAT_OFF(replenish_add_buff_success) },
	{ "rx_invalid_buffer", IBMVETH_STAT_OFF(rx_invalid_buffer) },
	{ "rx_no_buffer", IBMVETH_STAT_OFF(rx_no_buffer) },
	{ "tx_map_failed", IBMVETH_STAT_OFF(tx_map_failed) },
	{ "tx_send_failed", IBMVETH_STAT_OFF(tx_send_failed) },
};

/* simple methods of getting data from the current rxq entry */
static inline u32 ibmveth_rxq_flags(struct ibmveth_adapter *adapter)
{
	return adapter->rx_queue.queue_addr[adapter->rx_queue.index].flags_off;
}

static inline int ibmveth_rxq_toggle(struct ibmveth_adapter *adapter)
{
	return (ibmveth_rxq_flags(adapter) & IBMVETH_RXQ_TOGGLE) >> IBMVETH_RXQ_TOGGLE_SHIFT;
}

static inline int ibmveth_rxq_pending_buffer(struct ibmveth_adapter *adapter)
{
	return (ibmveth_rxq_toggle(adapter) == adapter->rx_queue.toggle);
}

static inline int ibmveth_rxq_buffer_valid(struct ibmveth_adapter *adapter)
{
	return (ibmveth_rxq_flags(adapter) & IBMVETH_RXQ_VALID);
}

static inline int ibmveth_rxq_frame_offset(struct ibmveth_adapter *adapter)
{
	return (ibmveth_rxq_flags(adapter) & IBMVETH_RXQ_OFF_MASK);
}

static inline int ibmveth_rxq_frame_length(struct ibmveth_adapter *adapter)
{
	return (adapter->rx_queue.queue_addr[adapter->rx_queue.index].length);
}

static inline int ibmveth_rxq_csum_good(struct ibmveth_adapter *adapter)
{
	return (ibmveth_rxq_flags(adapter) & IBMVETH_RXQ_CSUM_GOOD);
}

/* setup the initial settings for a buffer pool */
static void ibmveth_init_buffer_pool(struct ibmveth_buff_pool *pool, u32 pool_index, u32 pool_size, u32 buff_size, u32 pool_active)
{
	pool->size = pool_size;
	pool->index = pool_index;
	pool->buff_size = buff_size;
	pool->threshold = pool_size / 2;
	pool->active = pool_active;
}

/* allocate and setup an buffer pool - called during open */
static int ibmveth_alloc_buffer_pool(struct ibmveth_buff_pool *pool)
{
	int i;

	pool->free_map = kmalloc(sizeof(u16) * pool->size, GFP_KERNEL);

	if(!pool->free_map) {
		return -1;
	}

	pool->dma_addr = kmalloc(sizeof(dma_addr_t) * pool->size, GFP_KERNEL);
	if(!pool->dma_addr) {
		kfree(pool->free_map);
		pool->free_map = NULL;
		return -1;
	}

	pool->skbuff = kmalloc(sizeof(void*) * pool->size, GFP_KERNEL);

	if(!pool->skbuff) {
		kfree(pool->dma_addr);
		pool->dma_addr = NULL;

		kfree(pool->free_map);
		pool->free_map = NULL;
		return -1;
	}

	memset(pool->skbuff, 0, sizeof(void*) * pool->size);
	memset(pool->dma_addr, 0, sizeof(dma_addr_t) * pool->size);

	for(i = 0; i < pool->size; ++i) {
		pool->free_map[i] = i;
	}

	atomic_set(&pool->available, 0);
	pool->producer_index = 0;
	pool->consumer_index = 0;

	return 0;
}

/* replenish the buffers for a pool.  note that we don't need to
 * skb_reserve these since they are used for incoming...
 */
static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter, struct ibmveth_buff_pool *pool)
{
	u32 i;
	u32 count = pool->size - atomic_read(&pool->available);
	u32 buffers_added = 0;
	struct sk_buff *skb;
	unsigned int free_index, index;
	u64 correlator;
	unsigned long lpar_rc;
	dma_addr_t dma_addr;

	mb();

	for(i = 0; i < count; ++i) {
		union ibmveth_buf_desc desc;

		skb = alloc_skb(pool->buff_size, GFP_ATOMIC);

		if(!skb) {
			ibmveth_debug_printk("replenish: unable to allocate skb\n");
			adapter->replenish_no_mem++;
			break;
		}

		free_index = pool->consumer_index;
		pool->consumer_index = (pool->consumer_index + 1) % pool->size;
		index = pool->free_map[free_index];

		ibmveth_assert(index != IBM_VETH_INVALID_MAP);
		ibmveth_assert(pool->skbuff[index] == NULL);

		dma_addr = dma_map_single(&adapter->vdev->dev, skb->data,
				pool->buff_size, DMA_FROM_DEVICE);

		if (dma_mapping_error((&adapter->vdev->dev, dma_addr))
			goto failure;

		pool->free_map[free_index] = IBM_VETH_INVALID_MAP;
		pool->dma_addr[index] = dma_addr;
		pool->skbuff[index] = skb;

		correlator = ((u64)pool->index << 32) | index;
		*(u64*)skb->data = correlator;

		desc.fields.flags_len = IBMVETH_BUF_VALID | pool->buff_size;
		desc.fields.address = dma_addr;

		lpar_rc = h_add_logical_lan_buffer(adapter->vdev->unit_address, desc.desc);

		if (lpar_rc != H_SUCCESS)
			goto failure;
		else {
			buffers_added++;
			adapter->replenish_add_buff_success++;
		}
	}

	mb();
	atomic_add(buffers_added, &(pool->available));
	return;

failure:
	pool->free_map[free_index] = index;
	pool->skbuff[index] = NULL;
	if (pool->consumer_index == 0)
		pool->consumer_index = pool->size - 1;
	else
		pool->consumer_index--;
	if (!dma_mapping_error((&adapter->vdev->dev, dma_addr))
		dma_unmap_single(&adapter->vdev->dev,
		                 pool->dma_addr[index], pool->buff_size,
		                 DMA_FROM_DEVICE);
	dev_kfree_skb_any(skb);
	adapter->replenish_add_buff_failure++;

	mb();
	atomic_add(buffers_added, &(pool->available));
}

/* replenish routine */
static void ibmveth_replenish_task(struct ibmveth_adapter *adapter)
{
	int i;

	adapter->replenish_task_cycles++;

	for (i = (IbmVethNumBufferPools - 1); i >= 0; i--)
		if(adapter->rx_buff_pool[i].active)
			ibmveth_replenish_buffer_pool(adapter,
						     &adapter->rx_buff_pool[i]);

	adapter->rx_no_buffer = *(u64*)(((char*)adapter->buffer_list_addr) + 4096 - 8);
}

/* empty and free ana buffer pool - also used to do cleanup in error paths */
static void ibmveth_free_buffer_pool(struct ibmveth_adapter *adapter, struct ibmveth_buff_pool *pool)
{
	int i;

	kfree(pool->free_map);
	pool->free_map = NULL;

	if(pool->skbuff && pool->dma_addr) {
		for(i = 0; i < pool->size; ++i) {
			struct sk_buff *skb = pool->skbuff[i];
			if(skb) {
				dma_unmap_single(&adapter->vdev->dev,
						 pool->dma_addr[i],
						 pool->buff_size,
						 DMA_FROM_DEVICE);
				dev_kfree_skb_any(skb);
				pool->skbuff[i] = NULL;
			}
		}
	}

	if(pool->dma_addr) {
		kfree(pool->dma_addr);
		pool->dma_addr = NULL;
	}

	if(pool->skbuff) {
		kfree(pool->skbuff);
		pool->skbuff = NULL;
	}
}

/* remove a buffer from a pool */
static void ibmveth_remove_buffer_from_pool(struct ibmveth_adapter *adapter, u64 correlator)
{
	unsigned int pool  = correlator >> 32;
	unsigned int index = correlator & 0xffffffffUL;
	unsigned int free_index;
	struct sk_buff *skb;

	ibmveth_assert(pool < IbmVethNumBufferPools);
	ibmveth_assert(index < adapter->rx_buff_pool[pool].size);

	skb = adapter->rx_buff_pool[pool].skbuff[index];

	ibmveth_assert(skb != NULL);

	adapter->rx_buff_pool[pool].skbuff[index] = NULL;

	dma_unmap_single(&adapter->vdev->dev,
			 adapter->rx_buff_pool[pool].dma_addr[index],
			 adapter->rx_buff_pool[pool].buff_size,
			 DMA_FROM_DEVICE);

	free_index = adapter->rx_buff_pool[pool].producer_index;
	adapter->rx_buff_pool[pool].producer_index
		= (adapter->rx_buff_pool[pool].producer_index + 1)
		% adapter->rx_buff_pool[pool].size;
	adapter->rx_buff_pool[pool].free_map[free_index] = index;

	mb();

	atomic_dec(&(adapter->rx_buff_pool[pool].available));
}

/* get the current buffer on the rx queue */
static inline struct sk_buff *ibmveth_rxq_get_buffer(struct ibmveth_adapter *adapter)
{
	u64 correlator = adapter->rx_queue.queue_addr[adapter->rx_queue.index].correlator;
	unsigned int pool = correlator >> 32;
	unsigned int index = correlator & 0xffffffffUL;

	ibmveth_assert(pool < IbmVethNumBufferPools);
	ibmveth_assert(index < adapter->rx_buff_pool[pool].size);

	return adapter->rx_buff_pool[pool].skbuff[index];
}

/* recycle the current buffer on the rx queue */
static void ibmveth_rxq_recycle_buffer(struct ibmveth_adapter *adapter)
{
	u32 q_index = adapter->rx_queue.index;
	u64 correlator = adapter->rx_queue.queue_addr[q_index].correlator;
	unsigned int pool = correlator >> 32;
	unsigned int index = correlator & 0xffffffffUL;
	union ibmveth_buf_desc desc;
	unsigned long lpar_rc;

	ibmveth_assert(pool < IbmVethNumBufferPools);
	ibmveth_assert(index < adapter->rx_buff_pool[pool].size);

	if(!adapter->rx_buff_pool[pool].active) {
		ibmveth_rxq_harvest_buffer(adapter);
		ibmveth_free_buffer_pool(adapter, &adapter->rx_buff_pool[pool]);
		return;
	}

	desc.fields.flags_len = IBMVETH_BUF_VALID |
		adapter->rx_buff_pool[pool].buff_size;
	desc.fields.address = adapter->rx_buff_pool[pool].dma_addr[index];

	lpar_rc = h_add_logical_lan_buffer(adapter->vdev->unit_address, desc.desc);

	if(lpar_rc != H_SUCCESS) {
		ibmveth_debug_printk("h_add_logical_lan_buffer failed during recycle rc=%ld", lpar_rc);
		ibmveth_remove_buffer_from_pool(adapter, adapter->rx_queue.queue_addr[adapter->rx_queue.index].correlator);
	}

	if(++adapter->rx_queue.index == adapter->rx_queue.num_slots) {
		adapter->rx_queue.index = 0;
		adapter->rx_queue.toggle = !adapter->rx_queue.toggle;
	}
}

static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter)
{
	ibmveth_remove_buffer_from_pool(adapter, adapter->rx_queue.queue_addr[adapter->rx_queue.index].correlator);

	if(++adapter->rx_queue.index == adapter->rx_queue.num_slots) {
		adapter->rx_queue.index = 0;
		adapter->rx_queue.toggle = !adapter->rx_queue.toggle;
	}
}

static void ibmveth_cleanup(struct ibmveth_adapter *adapter)
{
	int i;
	struct device *dev = &adapter->vdev->dev;

	if(adapter->buffer_list_addr != NULL) {
		if (!dma_mapping_error(dev, adapter->buffer_list_dma)) {
			dma_unmap_single(dev, adapter->buffer_list_dma, 4096,
					DMA_BIDIRECTIONAL);
			adapter->buffer_list_dma = DMA_ERROR_CODE;
		}
		free_page((unsigned long)adapter->buffer_list_addr);
		adapter->buffer_list_addr = NULL;
	}

	if(adapter->filter_list_addr != NULL) {
		if (!dma_mapping_error(dev, adapter->filter_list_dma)) {
			dma_unmap_single(dev, adapter->filter_list_dma, 4096,
					DMA_BIDIRECTIONAL);
			adapter->filter_list_dma = DMA_ERROR_CODE;
		}
		free_page((unsigned long)adapter->filter_list_addr);
		adapter->filter_list_addr = NULL;
	}

	if(adapter->rx_queue.queue_addr != NULL) {
		if (!dma_mapping_error(dev, adapter->rx_queue.queue_dma)) {
			dma_unmap_single(dev,
					adapter->rx_queue.queue_dma,
					adapter->rx_queue.queue_len,
					DMA_BIDIRECTIONAL);
			adapter->rx_queue.queue_dma = DMA_ERROR_CODE;
		}
		kfree(adapter->rx_queue.queue_addr);
		adapter->rx_queue.queue_addr = NULL;
	}

	for(i = 0; i<IbmVethNumBufferPools; i++)
		if (adapter->rx_buff_pool[i].active)
			ibmveth_free_buffer_pool(adapter,
						 &adapter->rx_buff_pool[i]);

	if (adapter->bounce_buffer != NULL) {
		if (!dma_mapping_error(adapter->bounce_buffer_dma)) {
			dma_unmap_single(&adapter->vdev->dev,
					adapter->bounce_buffer_dma,
					adapter->netdev->mtu + IBMVETH_BUFF_OH,
					DMA_BIDIRECTIONAL);
			adapter->bounce_buffer_dma = DMA_ERROR_CODE;
		}
		kfree(adapter->bounce_buffer);
		adapter->bounce_buffer = NULL;
	}
}

static int ibmveth_register_logical_lan(struct ibmveth_adapter *adapter,
        union ibmveth_buf_desc rxq_desc, u64 mac_address)
{
	int rc, try_again = 1;

	/* After a kexec the adapter will still be open, so our attempt to
	* open it will fail. So if we get a failure we free the adapter and
	* try again, but only once. */
retry:
	rc = h_register_logical_lan(adapter->vdev->unit_address,
				    adapter->buffer_list_dma, rxq_desc.desc,
				    adapter->filter_list_dma, mac_address);

	if (rc != H_SUCCESS && try_again) {
		do {
			rc = h_free_logical_lan(adapter->vdev->unit_address);
		} while (H_IS_LONG_BUSY(rc) || (rc == H_BUSY));

		try_again = 0;
		goto retry;
	}

	return rc;
}

static int ibmveth_open(struct net_device *netdev)
{
	struct ibmveth_adapter *adapter = netdev->priv;
	u64 mac_address = 0;
	int rxq_entries = 1;
	unsigned long lpar_rc;
	int rc;
	union ibmveth_buf_desc rxq_desc;
	int i;
	struct device *dev;

	ibmveth_debug_printk("open starting\n");

	napi_enable(&adapter->napi);

	for(i = 0; i<IbmVethNumBufferPools; i++)
		rxq_entries += adapter->rx_buff_pool[i].size;

	adapter->buffer_list_addr = (void*) get_zeroed_page(GFP_KERNEL);
	adapter->filter_list_addr = (void*) get_zeroed_page(GFP_KERNEL);

	if(!adapter->buffer_list_addr || !adapter->filter_list_addr) {
		ibmveth_error_printk("unable to allocate filter or buffer list pages\n");
		ibmveth_cleanup(adapter);
		napi_disable(&adapter->napi);
		return -ENOMEM;
	}

	adapter->rx_queue.queue_len = sizeof(struct ibmveth_rx_q_entry) * rxq_entries;
	adapter->rx_queue.queue_addr = kmalloc(adapter->rx_queue.queue_len, GFP_KERNEL);

	if(!adapter->rx_queue.queue_addr) {
		ibmveth_error_printk("unable to allocate rx queue pages\n");
		ibmveth_cleanup(adapter);
		napi_disable(&adapter->napi);
		return -ENOMEM;
	}

	dev = &adapter->vdev->dev;

	adapter->buffer_list_dma = dma_map_single(dev,
			adapter->buffer_list_addr, 4096, DMA_BIDIRECTIONAL);
	adapter->filter_list_dma = dma_map_single(dev,
			adapter->filter_list_addr, 4096, DMA_BIDIRECTIONAL);
	adapter->rx_queue.queue_dma = dma_map_single(dev,
			adapter->rx_queue.queue_addr,
			adapter->rx_queue.queue_len, DMA_BIDIRECTIONAL);

	if ((dma_mapping_error(dev, adapter->buffer_list_dma)) ||
	    (dma_mapping_error(dev, adapter->filter_list_dma)) ||
	    (dma_mapping_error(dev, adapter->rx_queue.queue_dma))) {
		ibmveth_error_printk("unable to map filter or buffer list pages\n");
		ibmveth_cleanup(adapter);
		napi_disable(&adapter->napi);
		return -ENOMEM;
	}

	adapter->rx_queue.index = 0;
	adapter->rx_queue.num_slots = rxq_entries;
	adapter->rx_queue.toggle = 1;

	memcpy(&mac_address, netdev->dev_addr, netdev->addr_len);
	mac_address = mac_address >> 16;

	rxq_desc.fields.flags_len = IBMVETH_BUF_VALID | adapter->rx_queue.queue_len;
	rxq_desc.fields.address = adapter->rx_queue.queue_dma;

	ibmveth_debug_printk("buffer list @ 0x%p\n", adapter->buffer_list_addr);
	ibmveth_debug_printk("filter list @ 0x%p\n", adapter->filter_list_addr);
	ibmveth_debug_printk("receive q   @ 0x%p\n", adapter->rx_queue.queue_addr);

	h_vio_signal(adapter->vdev->unit_address, VIO_IRQ_DISABLE);

	lpar_rc = ibmveth_register_logical_lan(adapter, rxq_desc, mac_address);

	if(lpar_rc != H_SUCCESS) {
		ibmveth_error_printk("h_register_logical_lan failed with %ld\n", lpar_rc);
		ibmveth_error_printk("buffer TCE:0x%lx filter TCE:0x%lx rxq desc:0x%lx MAC:0x%lx\n",
				     adapter->buffer_list_dma,
				     adapter->filter_list_dma,
				     rxq_desc.desc,
				     mac_address);
		ibmveth_cleanup(adapter);
		napi_disable(&adapter->napi);
		return -ENONET;
	}

	for(i = 0; i<IbmVethNumBufferPools; i++) {
		if(!adapter->rx_buff_pool[i].active)
			continue;
		if (ibmveth_alloc_buffer_pool(&adapter->rx_buff_pool[i])) {
			ibmveth_error_printk("unable to alloc pool\n");
			adapter->rx_buff_pool[i].active = 0;
			ibmveth_cleanup(adapter);
			napi_disable(&adapter->napi);
			return -ENOMEM ;
		}
	}

	ibmveth_debug_printk("registering irq 0x%x\n", netdev->irq);
	if((rc = request_irq(netdev->irq, &ibmveth_interrupt, 0, netdev->name, netdev)) != 0) {
		ibmveth_error_printk("unable to request irq 0x%x, rc %d\n", netdev->irq, rc);
		do {
			rc = h_free_logical_lan(adapter->vdev->unit_address);
		} while (H_IS_LONG_BUSY(rc) || (rc == H_BUSY));

		ibmveth_cleanup(adapter);
		napi_disable(&adapter->napi);
		return rc;
	}

	adapter->bounce_buffer =
	    kmalloc(netdev->mtu + IBMVETH_BUFF_OH, GFP_KERNEL);
	if (!adapter->bounce_buffer) {
		ibmveth_error_printk("unable to allocate bounce buffer\n");
		ibmveth_cleanup(adapter);
		napi_disable(&adapter->napi);
		return -ENOMEM;
	}
	adapter->bounce_buffer_dma =
	    dma_map_single(&adapter->vdev->dev, adapter->bounce_buffer,
			   netdev->mtu + IBMVETH_BUFF_OH, DMA_BIDIRECTIONAL);
	if (dma_mapping_error(dev, adapter->bounce_buffer_dma)) {
		ibmveth_error_printk("unable to map bounce buffer\n");
		ibmveth_cleanup(adapter);
		napi_disable(&adapter->napi);
		return -ENOMEM;
	}

	ibmveth_debug_printk("initial replenish cycle\n");
	ibmveth_interrupt(netdev->irq, netdev);

	netif_start_queue(netdev);

	ibmveth_debug_printk("open complete\n");

	return 0;
}

static int ibmveth_close(struct net_device *netdev)
{
	struct ibmveth_adapter *adapter = netdev->priv;
	long lpar_rc;

	ibmveth_debug_printk("close starting\n");

	napi_disable(&adapter->napi);

	if (!adapter->pool_config)
		netif_stop_queue(netdev);

	free_irq(netdev->irq, netdev);

	do {
		lpar_rc = h_free_logical_lan(adapter->vdev->unit_address);
	} while (H_IS_LONG_BUSY(lpar_rc) || (lpar_rc == H_BUSY));

	if(lpar_rc != H_SUCCESS)
	{
		ibmveth_error_printk("h_free_logical_lan failed with %lx, continuing with close\n",
				     lpar_rc);
	}

	adapter->rx_no_buffer = *(u64*)(((char*)adapter->buffer_list_addr) + 4096 - 8);

	ibmveth_cleanup(adapter);

	ibmveth_debug_printk("close complete\n");

	return 0;
}

static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) {
	cmd->supported = (SUPPORTED_1000baseT_Full | SUPPORTED_Autoneg | SUPPORTED_FIBRE);
	cmd->advertising = (ADVERTISED_1000baseT_Full | ADVERTISED_Autoneg | ADVERTISED_FIBRE);
	cmd->speed = SPEED_1000;
	cmd->duplex = DUPLEX_FULL;
	cmd->port = PORT_FIBRE;
	cmd->phy_address = 0;
	cmd->transceiver = XCVR_INTERNAL;
	cmd->autoneg = AUTONEG_ENABLE;
	cmd->maxtxpkt = 0;
	cmd->maxrxpkt = 1;
	return 0;
}

static void netdev_get_drvinfo (struct net_device *dev, struct ethtool_drvinfo *info) {
	strncpy(info->driver, ibmveth_driver_name, sizeof(info->driver) - 1);
	strncpy(info->version, ibmveth_driver_version, sizeof(info->version) - 1);
}

static u32 netdev_get_link(struct net_device *dev) {
	return 1;
}

static void ibmveth_set_rx_csum_flags(struct net_device *dev, u32 data)
{
	struct ibmveth_adapter *adapter = dev->priv;

	if (data)
		adapter->rx_csum = 1;
	else {
		/*
		 * Since the ibmveth firmware interface does not have the concept of
		 * separate tx/rx checksum offload enable, if rx checksum is disabled
		 * we also have to disable tx checksum offload. Once we disable rx
		 * checksum offload, we are no longer allowed to send tx buffers that
		 * are not properly checksummed.
		 */
		adapter->rx_csum = 0;
		dev->features &= ~NETIF_F_IP_CSUM;
	}
}

static void ibmveth_set_tx_csum_flags(struct net_device *dev, u32 data)
{
	struct ibmveth_adapter *adapter = dev->priv;

	if (data) {
		dev->features |= NETIF_F_IP_CSUM;
		adapter->rx_csum = 1;
	} else
		dev->features &= ~NETIF_F_IP_CSUM;
}

static int ibmveth_set_csum_offload(struct net_device *dev, u32 data,
				    void (*done) (struct net_device *, u32))
{
	struct ibmveth_adapter *adapter = dev->priv;
	u64 set_attr, clr_attr, ret_attr;
	long ret;
	int rc1 = 0, rc2 = 0;
	int restart = 0;

	if (netif_running(dev)) {
		restart = 1;
		adapter->pool_config = 1;
		ibmveth_close(dev);
		adapter->pool_config = 0;
	}

	set_attr = 0;
	clr_attr = 0;

	if (data)
		set_attr = IBMVETH_ILLAN_IPV4_TCP_CSUM;
	else
		clr_attr = IBMVETH_ILLAN_IPV4_TCP_CSUM;

	ret = h_illan_attributes(adapter->vdev->unit_address, 0, 0, &ret_attr);

	if (ret == H_SUCCESS && !(ret_attr & IBMVETH_ILLAN_ACTIVE_TRUNK) &&
	    !(ret_attr & IBMVETH_ILLAN_TRUNK_PRI_MASK) &&
	    (ret_attr & IBMVETH_ILLAN_PADDED_PKT_CSUM)) {
		ret = h_illan_attributes(adapter->vdev->unit_address, clr_attr,
					 set_attr, &ret_attr);

		if (ret != H_SUCCESS) {
			rc1 = -EIO;
			ibmveth_error_printk("unable to change checksum offload settings."
					     " %d rc=%ld\n", data, ret);

			ret = h_illan_attributes(adapter->vdev->unit_address,
						 set_attr, clr_attr, &ret_attr);
		} else
			done(dev, data);
	} else {
		rc1 = -EIO;
		ibmveth_error_printk("unable to change checksum offload settings."
				     " %d rc=%ld ret_attr=%lx\n", data, ret, ret_attr);
	}

	if (restart)
		rc2 = ibmveth_open(dev);

	return rc1 ? rc1 : rc2;
}

static int ibmveth_set_rx_csum(struct net_device *dev, u32 data)
{
	struct ibmveth_adapter *adapter = dev->priv;

	if ((data && adapter->rx_csum) || (!data && !adapter->rx_csum))
		return 0;

	return ibmveth_set_csum_offload(dev, data, ibmveth_set_rx_csum_flags);
}

static int ibmveth_set_tx_csum(struct net_device *dev, u32 data)
{
	struct ibmveth_adapter *adapter = dev->priv;
	int rc = 0;

	if (data && (dev->features & NETIF_F_IP_CSUM))
		return 0;
	if (!data && !(dev->features & NETIF_F_IP_CSUM))
		return 0;

	if (data && !adapter->rx_csum)
		rc = ibmveth_set_csum_offload(dev, data, ibmveth_set_tx_csum_flags);
	else
		ibmveth_set_tx_csum_flags(dev, data);

	return rc;
}

static u32 ibmveth_get_rx_csum(struct net_device *dev)
{
	struct ibmveth_adapter *adapter = dev->priv;
	return adapter->rx_csum;
}

static void ibmveth_get_strings(struct net_device *dev, u32 stringset, u8 *data)
{
	int i;

	if (stringset != ETH_SS_STATS)
		return;

	for (i = 0; i < ARRAY_SIZE(ibmveth_stats); i++, data += ETH_GSTRING_LEN)
		memcpy(data, ibmveth_stats[i].name, ETH_GSTRING_LEN);
}

static int ibmveth_get_sset_count(struct net_device *dev, int sset)
{
	switch (sset) {
	case ETH_SS_STATS:
		return ARRAY_SIZE(ibmveth_stats);
	default:
		return -EOPNOTSUPP;
	}
}

static void ibmveth_get_ethtool_stats(struct net_device *dev,
				      struct ethtool_stats *stats, u64 *data)
{
	int i;
	struct ibmveth_adapter *adapter = dev->priv;

	for (i = 0; i < ARRAY_SIZE(ibmveth_stats); i++)
		data[i] = IBMVETH_GET_STAT(adapter, ibmveth_stats[i].offset);
}

static const struct ethtool_ops netdev_ethtool_ops = {
	.get_drvinfo		= netdev_get_drvinfo,
	.get_settings		= netdev_get_settings,
	.get_link		= netdev_get_link,
	.set_tx_csum		= ibmveth_set_tx_csum,
	.get_rx_csum		= ibmveth_get_rx_csum,
	.set_rx_csum		= ibmveth_set_rx_csum,
	.get_strings		= ibmveth_get_strings,
	.get_sset_count		= ibmveth_get_sset_count,
	.get_ethtool_stats	= ibmveth_get_ethtool_stats,
};

static int ibmveth_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
	return -EOPNOTSUPP;
}

#define page_offset(v) ((unsigned long)(v) & ((1 << 12) - 1))

static int ibmveth_start_xmit(struct sk_buff *skb, struct net_device *netdev)
{
	struct ibmveth_adapter *adapter = netdev->priv;
	union ibmveth_buf_desc desc;
	unsigned long lpar_rc;
	unsigned long correlator;
	unsigned long flags;
	unsigned int retry_count;
	unsigned int tx_dropped = 0;
	unsigned int tx_bytes = 0;
	unsigned int tx_packets = 0;
	unsigned int tx_send_failed = 0;
	unsigned int tx_map_failed = 0;
	int used_bounce = 0;
	unsigned long data_dma_addr;

	desc.fields.flags_len = IBMVETH_BUF_VALID | skb->len;
	data_dma_addr = dma_map_single(&adapter->vdev->dev, skb->data,
				       skb->len, DMA_TO_DEVICE);

	if (skb->ip_summed == CHECKSUM_PARTIAL &&
	    ip_hdr(skb)->protocol != IPPROTO_TCP && skb_checksum_help(skb)) {
		ibmveth_error_printk("tx: failed to checksum packet\n");
		tx_dropped++;
		goto out;
	}

	if (skb->ip_summed == CHECKSUM_PARTIAL) {
		unsigned char *buf = skb_transport_header(skb) + skb->csum_offset;

		desc.fields.flags_len |= (IBMVETH_BUF_NO_CSUM | IBMVETH_BUF_CSUM_GOOD);

		/* Need to zero out the checksum */
		buf[0] = 0;
		buf[1] = 0;
	}

	if (dma_mapping_error((&adapter->vdev->dev, data_dma_addr)) {
		if (!firmware_has_feature(FW_FEATURE_CMO))
			ibmveth_error_printk("tx: unable to map xmit buffer\n");
		skb_copy_from_linear_data(skb, adapter->bounce_buffer,
					  skb->len);
		desc.fields.address = adapter->bounce_buffer_dma;
		tx_map_failed++;
		used_bounce = 1;
	} else
		desc.fields.address = data_dma_addr;

	/* send the frame. Arbitrarily set retrycount to 1024 */
	correlator = 0;
	retry_count = 1024;
	do {
		lpar_rc = h_send_logical_lan(adapter->vdev->unit_address,
					     desc.desc, 0, 0, 0, 0, 0,
					     correlator, &correlator);
	} while ((lpar_rc == H_BUSY) && (retry_count--));

	if(lpar_rc != H_SUCCESS && lpar_rc != H_DROPPED) {
		ibmveth_error_printk("tx: h_send_logical_lan failed with rc=%ld\n", lpar_rc);
		ibmveth_error_printk("tx: valid=%d, len=%d, address=0x%08x\n",
				     (desc.fields.flags_len & IBMVETH_BUF_VALID) ? 1 : 0,
				     skb->len, desc.fields.address);
		tx_send_failed++;
		tx_dropped++;
	} else {
		tx_packets++;
		tx_bytes += skb->len;
		netdev->trans_start = jiffies;
	}

	if (!used_bounce)
		dma_unmap_single(&adapter->vdev->dev, data_dma_addr,
				 skb->len, DMA_TO_DEVICE);

out:	spin_lock_irqsave(&adapter->stats_lock, flags);
	netdev->stats.tx_dropped += tx_dropped;
	netdev->stats.tx_bytes += tx_bytes;
	netdev->stats.tx_packets += tx_packets;
	adapter->tx_send_failed += tx_send_failed;
	adapter->tx_map_failed += tx_map_failed;
	spin_unlock_irqrestore(&adapter->stats_lock, flags);

	dev_kfree_skb(skb);
	return 0;
}

static int ibmveth_poll(struct napi_struct *napi, int budget)
{
	struct ibmveth_adapter *adapter = container_of(napi, struct ibmveth_adapter, napi);
	struct net_device *netdev = adapter->netdev;
	int frames_processed = 0;
	unsigned long lpar_rc;

 restart_poll:
	do {
		struct sk_buff *skb;

		if (!ibmveth_rxq_pending_buffer(adapter))
			break;

		rmb();
		if (!ibmveth_rxq_buffer_valid(adapter)) {
			wmb(); /* suggested by larson1 */
			adapter->rx_invalid_buffer++;
			ibmveth_debug_printk("recycling invalid buffer\n");
			ibmveth_rxq_recycle_buffer(adapter);
		} else {
			int length = ibmveth_rxq_frame_length(adapter);
			int offset = ibmveth_rxq_frame_offset(adapter);
			int csum_good = ibmveth_rxq_csum_good(adapter);

			skb = ibmveth_rxq_get_buffer(adapter);
			if (csum_good)
				skb->ip_summed = CHECKSUM_UNNECESSARY;

			ibmveth_rxq_harvest_buffer(adapter);

			skb_reserve(skb, offset);
			skb_put(skb, length);
			skb->protocol = eth_type_trans(skb, netdev);

			netif_receive_skb(skb);	/* send it up */

			netdev->stats.rx_packets++;
			netdev->stats.rx_bytes += length;
			frames_processed++;
			netdev->last_rx = jiffies;
		}
	} while (frames_processed < budget);

	ibmveth_replenish_task(adapter);

	if (frames_processed < budget) {
		/* We think we are done - reenable interrupts,
		 * then check once more to make sure we are done.
		 */
		lpar_rc = h_vio_signal(adapter->vdev->unit_address,
				       VIO_IRQ_ENABLE);

		ibmveth_assert(lpar_rc == H_SUCCESS);

		netif_rx_complete(netdev, napi);

		if (ibmveth_rxq_pending_buffer(adapter) &&
		    netif_rx_reschedule(netdev, napi)) {
			lpar_rc = h_vio_signal(adapter->vdev->unit_address,
					       VIO_IRQ_DISABLE);
			goto restart_poll;
		}
	}

	return frames_processed;
}

static irqreturn_t ibmveth_interrupt(int irq, void *dev_instance)
{
	struct net_device *netdev = dev_instance;
	struct ibmveth_adapter *adapter = netdev->priv;
	unsigned long lpar_rc;

	if (netif_rx_schedule_prep(netdev, &adapter->napi)) {
		lpar_rc = h_vio_signal(adapter->vdev->unit_address,
				       VIO_IRQ_DISABLE);
		ibmveth_assert(lpar_rc == H_SUCCESS);
		__netif_rx_schedule(netdev, &adapter->napi);
	}
	return IRQ_HANDLED;
}

static void ibmveth_set_multicast_list(struct net_device *netdev)
{
	struct ibmveth_adapter *adapter = netdev->priv;
	unsigned long lpar_rc;

	if((netdev->flags & IFF_PROMISC) || (netdev->mc_count > adapter->mcastFilterSize)) {
		lpar_rc = h_multicast_ctrl(adapter->vdev->unit_address,
					   IbmVethMcastEnableRecv |
					   IbmVethMcastDisableFiltering,
					   0);
		if(lpar_rc != H_SUCCESS) {
			ibmveth_error_printk("h_multicast_ctrl rc=%ld when entering promisc mode\n", lpar_rc);
		}
	} else {
		struct dev_mc_list *mclist = netdev->mc_list;
		int i;
		/* clear the filter table & disable filtering */
		lpar_rc = h_multicast_ctrl(adapter->vdev->unit_address,
					   IbmVethMcastEnableRecv |
					   IbmVethMcastDisableFiltering |
					   IbmVethMcastClearFilterTable,
					   0);
		if(lpar_rc != H_SUCCESS) {
			ibmveth_error_printk("h_multicast_ctrl rc=%ld when attempting to clear filter table\n", lpar_rc);
		}
		/* add the addresses to the filter table */
		for(i = 0; i < netdev->mc_count; ++i, mclist = mclist->next) {
			// add the multicast address to the filter table
			unsigned long mcast_addr = 0;
			memcpy(((char *)&mcast_addr)+2, mclist->dmi_addr, 6);
			lpar_rc = h_multicast_ctrl(adapter->vdev->unit_address,
						   IbmVethMcastAddFilter,
						   mcast_addr);
			if(lpar_rc != H_SUCCESS) {
				ibmveth_error_printk("h_multicast_ctrl rc=%ld when adding an entry to the filter table\n", lpar_rc);
			}
		}

		/* re-enable filtering */
		lpar_rc = h_multicast_ctrl(adapter->vdev->unit_address,
					   IbmVethMcastEnableFiltering,
					   0);
		if(lpar_rc != H_SUCCESS) {
			ibmveth_error_printk("h_multicast_ctrl rc=%ld when enabling filtering\n", lpar_rc);
		}
	}
}

static int ibmveth_change_mtu(struct net_device *dev, int new_mtu)
{
	struct ibmveth_adapter *adapter = dev->priv;
	struct vio_dev *viodev = adapter->vdev;
	int new_mtu_oh = new_mtu + IBMVETH_BUFF_OH;
	int i;

	if (new_mtu < IBMVETH_MAX_MTU)
		return -EINVAL;

	for (i = 0; i < IbmVethNumBufferPools; i++)
		if (new_mtu_oh < adapter->rx_buff_pool[i].buff_size)
			break;

	if (i == IbmVethNumBufferPools)
		return -EINVAL;

	/* Deactivate all the buffer pools so that the next loop can activate
	   only the buffer pools necessary to hold the new MTU */
	for (i = 0; i < IbmVethNumBufferPools; i++)
		if (adapter->rx_buff_pool[i].active) {
			ibmveth_free_buffer_pool(adapter,
						 &adapter->rx_buff_pool[i]);
			adapter->rx_buff_pool[i].active = 0;
		}

	/* Look for an active buffer pool that can hold the new MTU */
	for(i = 0; i<IbmVethNumBufferPools; i++) {
		adapter->rx_buff_pool[i].active = 1;

		if (new_mtu_oh < adapter->rx_buff_pool[i].buff_size) {
			if (netif_running(adapter->netdev)) {
				adapter->pool_config = 1;
				ibmveth_close(adapter->netdev);
				adapter->pool_config = 0;
				dev->mtu = new_mtu;
				vio_cmo_set_dev_desired(viodev,
						ibmveth_get_desired_dma
						(viodev));
				return ibmveth_open(adapter->netdev);
			}
			dev->mtu = new_mtu;
			vio_cmo_set_dev_desired(viodev,
						ibmveth_get_desired_dma
						(viodev));
			return 0;
		}
	}
	return -EINVAL;
}

#ifdef CONFIG_NET_POLL_CONTROLLER
static void ibmveth_poll_controller(struct net_device *dev)
{
	ibmveth_replenish_task(dev->priv);
	ibmveth_interrupt(dev->irq, dev);
}
#endif

/**
 * ibmveth_get_desired_dma - Calculate IO memory desired by the driver
 *
 * @vdev: struct vio_dev for the device whose desired IO mem is to be returned
 *
 * Return value:
 *	Number of bytes of IO data the driver will need to perform well.
 */
static unsigned long ibmveth_get_desired_dma(struct vio_dev *vdev)
{
	struct net_device *netdev = dev_get_drvdata(&vdev->dev);
	struct ibmveth_adapter *adapter;
	unsigned long ret;
	int i;
	int rxqentries = 1;

	/* netdev inits at probe time along with the structures we need below*/
	if (netdev == NULL)
		return IOMMU_PAGE_ALIGN(IBMVETH_IO_ENTITLEMENT_DEFAULT);

	adapter = netdev_priv(netdev);

	ret = IBMVETH_BUFF_LIST_SIZE + IBMVETH_FILT_LIST_SIZE;
	ret += IOMMU_PAGE_ALIGN(netdev->mtu);

	for (i = 0; i < IbmVethNumBufferPools; i++) {
		/* add the size of the active receive buffers */
		if (adapter->rx_buff_pool[i].active)
			ret +=
			    adapter->rx_buff_pool[i].size *
			    IOMMU_PAGE_ALIGN(adapter->rx_buff_pool[i].
			            buff_size);
		rxqentries += adapter->rx_buff_pool[i].size;
	}
	/* add the size of the receive queue entries */
	ret += IOMMU_PAGE_ALIGN(rxqentries * sizeof(struct ibmveth_rx_q_entry));

	return ret;
}

static int __devinit ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
{
	int rc, i;
	long ret;
	struct net_device *netdev;
	struct ibmveth_adapter *adapter;
	u64 set_attr, ret_attr;

	unsigned char *mac_addr_p;
	unsigned int *mcastFilterSize_p;


	ibmveth_debug_printk_no_adapter("entering ibmveth_probe for UA 0x%x\n",
					dev->unit_address);

	mac_addr_p = (unsigned char *) vio_get_attribute(dev,
						VETH_MAC_ADDR, NULL);
	if(!mac_addr_p) {
		printk(KERN_ERR "(%s:%3.3d) ERROR: Can't find VETH_MAC_ADDR "
				"attribute\n", __FILE__, __LINE__);
		return 0;
	}

	mcastFilterSize_p = (unsigned int *) vio_get_attribute(dev,
						VETH_MCAST_FILTER_SIZE, NULL);
	if(!mcastFilterSize_p) {
		printk(KERN_ERR "(%s:%3.3d) ERROR: Can't find "
				"VETH_MCAST_FILTER_SIZE attribute\n",
				__FILE__, __LINE__);
		return 0;
	}

	netdev = alloc_etherdev(sizeof(struct ibmveth_adapter));

	if(!netdev)
		return -ENOMEM;

	adapter = netdev->priv;
	dev->dev.driver_data = netdev;

	adapter->vdev = dev;
	adapter->netdev = netdev;
	adapter->mcastFilterSize= *mcastFilterSize_p;
	adapter->pool_config = 0;

	netif_napi_add(netdev, &adapter->napi, ibmveth_poll, 16);

	/* 	Some older boxes running PHYP non-natively have an OF that
		returns a 8-byte local-mac-address field (and the first
		2 bytes have to be ignored) while newer boxes' OF return
		a 6-byte field. Note that IEEE 1275 specifies that
		local-mac-address must be a 6-byte field.
		The RPA doc specifies that the first byte must be 10b, so
		we'll just look for it to solve this 8 vs. 6 byte field issue */

	if ((*mac_addr_p & 0x3) != 0x02)
		mac_addr_p += 2;

	adapter->mac_addr = 0;
	memcpy(&adapter->mac_addr, mac_addr_p, 6);

	netdev->irq = dev->irq;
	netdev->open               = ibmveth_open;
	netdev->stop               = ibmveth_close;
	netdev->hard_start_xmit    = ibmveth_start_xmit;
	netdev->set_multicast_list = ibmveth_set_multicast_list;
	netdev->do_ioctl           = ibmveth_ioctl;
	netdev->ethtool_ops           = &netdev_ethtool_ops;
	netdev->change_mtu         = ibmveth_change_mtu;
	SET_NETDEV_DEV(netdev, &dev->dev);
#ifdef CONFIG_NET_POLL_CONTROLLER
	netdev->poll_controller = ibmveth_poll_controller;
#endif
 	netdev->features |= NETIF_F_LLTX;
	spin_lock_init(&adapter->stats_lock);

	memcpy(&netdev->dev_addr, &adapter->mac_addr, netdev->addr_len);

	for(i = 0; i<IbmVethNumBufferPools; i++) {
		struct kobject *kobj = &adapter->rx_buff_pool[i].kobj;
		int error;

		ibmveth_init_buffer_pool(&adapter->rx_buff_pool[i], i,
					 pool_count[i], pool_size[i],
					 pool_active[i]);
		error = kobject_init_and_add(kobj, &ktype_veth_pool,
					     &dev->dev.kobj, "pool%d", i);
		if (!error)
			kobject_uevent(kobj, KOBJ_ADD);
	}

	ibmveth_debug_printk("adapter @ 0x%p\n", adapter);

	adapter->buffer_list_dma = DMA_ERROR_CODE;
	adapter->filter_list_dma = DMA_ERROR_CODE;
	adapter->rx_queue.queue_dma = DMA_ERROR_CODE;

	ibmveth_debug_printk("registering netdev...\n");

	ret = h_illan_attributes(dev->unit_address, 0, 0, &ret_attr);

	if (ret == H_SUCCESS && !(ret_attr & IBMVETH_ILLAN_ACTIVE_TRUNK) &&
	    !(ret_attr & IBMVETH_ILLAN_TRUNK_PRI_MASK) &&
	    (ret_attr & IBMVETH_ILLAN_PADDED_PKT_CSUM)) {
		set_attr = IBMVETH_ILLAN_IPV4_TCP_CSUM;

		ret = h_illan_attributes(dev->unit_address, 0, set_attr, &ret_attr);

		if (ret == H_SUCCESS) {
			adapter->rx_csum = 1;
			netdev->features |= NETIF_F_IP_CSUM;
		} else
			ret = h_illan_attributes(dev->unit_address, set_attr, 0, &ret_attr);
	}

	rc = register_netdev(netdev);

	if(rc) {
		ibmveth_debug_printk("failed to register netdev rc=%d\n", rc);
		free_netdev(netdev);
		return rc;
	}

	ibmveth_debug_printk("registered\n");

	ibmveth_proc_register_adapter(adapter);

	return 0;
}

static int __devexit ibmveth_remove(struct vio_dev *dev)
{
	struct net_device *netdev = dev->dev.driver_data;
	struct ibmveth_adapter *adapter = netdev->priv;
	int i;

	for(i = 0; i<IbmVethNumBufferPools; i++)
		kobject_put(&adapter->rx_buff_pool[i].kobj);

	unregister_netdev(netdev);

	ibmveth_proc_unregister_adapter(adapter);

	free_netdev(netdev);
	dev_set_drvdata(&dev->dev, NULL);

	return 0;
}

#ifdef CONFIG_PROC_FS
static void ibmveth_proc_register_driver(void)
{
	ibmveth_proc_dir = proc_mkdir(IBMVETH_PROC_DIR, init_net.proc_net);
	if (ibmveth_proc_dir) {
	}
}

static void ibmveth_proc_unregister_driver(void)
{
	remove_proc_entry(IBMVETH_PROC_DIR, init_net.proc_net);
}

static int ibmveth_show(struct seq_file *seq, void *v)
{
	struct ibmveth_adapter *adapter = seq->private;
	char *current_mac = ((char*) &adapter->netdev->dev_addr);
	char *firmware_mac = ((char*) &adapter->mac_addr) ;
	DECLARE_MAC_BUF(mac);

	seq_printf(seq, "%s %s\n\n", ibmveth_driver_string, ibmveth_driver_version);

	seq_printf(seq, "Unit Address:    0x%x\n", adapter->vdev->unit_address);
	seq_printf(seq, "Current MAC:     %s\n", print_mac(mac, current_mac));
	seq_printf(seq, "Firmware MAC:    %s\n", print_mac(mac, firmware_mac));

	seq_printf(seq, "\nAdapter Statistics:\n");
	seq_printf(seq, "  TX:  vio_map_single failres:      %ld\n", adapter->tx_map_failed);
	seq_printf(seq, "       send failures:               %ld\n", adapter->tx_send_failed);
	seq_printf(seq, "  RX:  replenish task cycles:       %ld\n", adapter->replenish_task_cycles);
	seq_printf(seq, "       alloc_skb_failures:          %ld\n", adapter->replenish_no_mem);
	seq_printf(seq, "       add buffer failures:         %ld\n", adapter->replenish_add_buff_failure);
	seq_printf(seq, "       invalid buffers:             %ld\n", adapter->rx_invalid_buffer);
	seq_printf(seq, "       no buffers:                  %ld\n", adapter->rx_no_buffer);

	return 0;
}

static int ibmveth_proc_open(struct inode *inode, struct file *file)
{
	return single_open(file, ibmveth_show, PDE(inode)->data);
}

static const struct file_operations ibmveth_proc_fops = {
	.owner	 = THIS_MODULE,
	.open    = ibmveth_proc_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = single_release,
};

static void ibmveth_proc_register_adapter(struct ibmveth_adapter *adapter)
{
	struct proc_dir_entry *entry;
	if (ibmveth_proc_dir) {
		char u_addr[10];
		sprintf(u_addr, "%x", adapter->vdev->unit_address);
		entry = proc_create_data(u_addr, S_IFREG, ibmveth_proc_dir,
					 &ibmveth_proc_fops, adapter);
		if (!entry)
			ibmveth_error_printk("Cannot create adapter proc entry");
	}
	return;
}

static void ibmveth_proc_unregister_adapter(struct ibmveth_adapter *adapter)
{
	if (ibmveth_proc_dir) {
		char u_addr[10];
		sprintf(u_addr, "%x", adapter->vdev->unit_address);
		remove_proc_entry(u_addr, ibmveth_proc_dir);
	}
}

#else /* CONFIG_PROC_FS */
static void ibmveth_proc_register_adapter(struct ibmveth_adapter *adapter)
{
}

static void ibmveth_proc_unregister_adapter(struct ibmveth_adapter *adapter)
{
}
static void ibmveth_proc_register_driver(void)
{
}

static void ibmveth_proc_unregister_driver(void)
{
}
#endif /* CONFIG_PROC_FS */

static struct attribute veth_active_attr;
static struct attribute veth_num_attr;
static struct attribute veth_size_attr;

static ssize_t veth_pool_show(struct kobject * kobj,
                              struct attribute * attr, char * buf)
{
	struct ibmveth_buff_pool *pool = container_of(kobj,
						      struct ibmveth_buff_pool,
						      kobj);

	if (attr == &veth_active_attr)
		return sprintf(buf, "%d\n", pool->active);
	else if (attr == &veth_num_attr)
		return sprintf(buf, "%d\n", pool->size);
	else if (attr == &veth_size_attr)
		return sprintf(buf, "%d\n", pool->buff_size);
	return 0;
}

static ssize_t veth_pool_store(struct kobject * kobj, struct attribute * attr,
const char * buf, size_t count)
{
	struct ibmveth_buff_pool *pool = container_of(kobj,
						      struct ibmveth_buff_pool,
						      kobj);
	struct net_device *netdev =
	    container_of(kobj->parent, struct device, kobj)->driver_data;
	struct ibmveth_adapter *adapter = netdev->priv;
	long value = simple_strtol(buf, NULL, 10);
	long rc;

	if (attr == &veth_active_attr) {
		if (value && !pool->active) {
			if (netif_running(netdev)) {
				if(ibmveth_alloc_buffer_pool(pool)) {
					ibmveth_error_printk("unable to alloc pool\n");
					return -ENOMEM;
				}
				pool->active = 1;
				adapter->pool_config = 1;
				ibmveth_close(netdev);
				adapter->pool_config = 0;
				if ((rc = ibmveth_open(netdev)))
					return rc;
			} else
				pool->active = 1;
		} else if (!value && pool->active) {
			int mtu = netdev->mtu + IBMVETH_BUFF_OH;
			int i;
			/* Make sure there is a buffer pool with buffers that
			   can hold a packet of the size of the MTU */
			for (i = 0; i < IbmVethNumBufferPools; i++) {
				if (pool == &adapter->rx_buff_pool[i])
					continue;
				if (!adapter->rx_buff_pool[i].active)
					continue;
				if (mtu <= adapter->rx_buff_pool[i].buff_size)
					break;
			}

			if (i == IbmVethNumBufferPools) {
				ibmveth_error_printk("no active pool >= MTU\n");
				return -EPERM;
			}

			if (netif_running(netdev)) {
				adapter->pool_config = 1;
				ibmveth_close(netdev);
				pool->active = 0;
				adapter->pool_config = 0;
				if ((rc = ibmveth_open(netdev)))
					return rc;
			}
			pool->active = 0;
		}
	} else if (attr == &veth_num_attr) {
		if (value <= 0 || value > IBMVETH_MAX_POOL_COUNT)
			return -EINVAL;
		else {
			if (netif_running(netdev)) {
				adapter->pool_config = 1;
				ibmveth_close(netdev);
				adapter->pool_config = 0;
				pool->size = value;
				if ((rc = ibmveth_open(netdev)))
					return rc;
			} else
				pool->size = value;
		}
	} else if (attr == &veth_size_attr) {
		if (value <= IBMVETH_BUFF_OH || value > IBMVETH_MAX_BUF_SIZE)
			return -EINVAL;
		else {
			if (netif_running(netdev)) {
				adapter->pool_config = 1;
				ibmveth_close(netdev);
				adapter->pool_config = 0;
				pool->buff_size = value;
				if ((rc = ibmveth_open(netdev)))
					return rc;
			} else
				pool->buff_size = value;
		}
	}

	/* kick the interrupt handler to allocate/deallocate pools */
	ibmveth_interrupt(netdev->irq, netdev);
	return count;
}


#define ATTR(_name, _mode)      \
        struct attribute veth_##_name##_attr = {               \
        .name = __stringify(_name), .mode = _mode, \
        };

static ATTR(active, 0644);
static ATTR(num, 0644);
static ATTR(size, 0644);

static struct attribute * veth_pool_attrs[] = {
	&veth_active_attr,
	&veth_num_attr,
	&veth_size_attr,
	NULL,
};

static struct sysfs_ops veth_pool_ops = {
	.show   = veth_pool_show,
	.store  = veth_pool_store,
};

static struct kobj_type ktype_veth_pool = {
	.release        = NULL,
	.sysfs_ops      = &veth_pool_ops,
	.default_attrs  = veth_pool_attrs,
};


static struct vio_device_id ibmveth_device_table[] __devinitdata= {
	{ "network", "IBM,l-lan"},
	{ "", "" }
};
MODULE_DEVICE_TABLE(vio, ibmveth_device_table);

static struct vio_driver ibmveth_driver = {
	.id_table	= ibmveth_device_table,
	.probe		= ibmveth_probe,
	.remove		= ibmveth_remove,
	.get_desired_dma = ibmveth_get_desired_dma,
	.driver		= {
		.name	= ibmveth_driver_name,
		.owner	= THIS_MODULE,
	}
};

static int __init ibmveth_module_init(void)
{
	ibmveth_printk("%s: %s %s\n", ibmveth_driver_name, ibmveth_driver_string, ibmveth_driver_version);

	ibmveth_proc_register_driver();

	return vio_register_driver(&ibmveth_driver);
}

static void __exit ibmveth_module_exit(void)
{
	vio_unregister_driver(&ibmveth_driver);
	ibmveth_proc_unregister_driver();
}

module_init(ibmveth_module_init);
module_exit(ibmveth_module_exit);