summaryrefslogtreecommitdiff
path: root/drivers/net/xen-netback/netback.c
blob: 0d22cff02ded8ac99d9db018a80bd527c48f5ff1 (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
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
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
/*
 * Back-end of the driver for virtual network devices. This portion of the
 * driver exports a 'unified' network-device interface that can be accessed
 * by any operating system that implements a compatible front end. A
 * reference front-end implementation can be found in:
 *  drivers/net/xen-netfront.c
 *
 * Copyright (c) 2002-2005, K A Fraser
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License version 2
 * as published by the Free Software Foundation; or, when distributed
 * separately from the Linux kernel or incorporated into other
 * software packages, subject to the following license:
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this source file (the "Software"), to deal in the Software without
 * restriction, including without limitation the rights to use, copy, modify,
 * merge, publish, distribute, sublicense, and/or sell copies of the Software,
 * and to permit persons to whom the Software is furnished to do so, subject to
 * the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
 * IN THE SOFTWARE.
 */

#include "common.h"

#include <linux/kthread.h>
#include <linux/if_vlan.h>
#include <linux/udp.h>

#include <net/tcp.h>

#include <xen/events.h>
#include <xen/interface/memory.h>

#include <asm/xen/hypercall.h>
#include <asm/xen/page.h>

struct pending_tx_info {
	struct xen_netif_tx_request req;
	struct xenvif *vif;
};
typedef unsigned int pending_ring_idx_t;

struct netbk_rx_meta {
	int id;
	int size;
	int gso_size;
};

#define MAX_PENDING_REQS 256

/* Discriminate from any valid pending_idx value. */
#define INVALID_PENDING_IDX 0xFFFF

#define MAX_BUFFER_OFFSET PAGE_SIZE

/* extra field used in struct page */
union page_ext {
	struct {
#if BITS_PER_LONG < 64
#define IDX_WIDTH   8
#define GROUP_WIDTH (BITS_PER_LONG - IDX_WIDTH)
		unsigned int group:GROUP_WIDTH;
		unsigned int idx:IDX_WIDTH;
#else
		unsigned int group, idx;
#endif
	} e;
	void *mapping;
};

struct xen_netbk {
	wait_queue_head_t wq;
	struct task_struct *task;

	struct sk_buff_head rx_queue;
	struct sk_buff_head tx_queue;

	struct timer_list net_timer;

	struct page *mmap_pages[MAX_PENDING_REQS];

	pending_ring_idx_t pending_prod;
	pending_ring_idx_t pending_cons;
	struct list_head net_schedule_list;

	/* Protect the net_schedule_list in netif. */
	spinlock_t net_schedule_list_lock;

	atomic_t netfront_count;

	struct pending_tx_info pending_tx_info[MAX_PENDING_REQS];
	struct gnttab_copy tx_copy_ops[MAX_PENDING_REQS];

	u16 pending_ring[MAX_PENDING_REQS];

	/*
	 * Given MAX_BUFFER_OFFSET of 4096 the worst case is that each
	 * head/fragment page uses 2 copy operations because it
	 * straddles two buffers in the frontend.
	 */
	struct gnttab_copy grant_copy_op[2*XEN_NETIF_RX_RING_SIZE];
	struct netbk_rx_meta meta[2*XEN_NETIF_RX_RING_SIZE];
};

static struct xen_netbk *xen_netbk;
static int xen_netbk_group_nr;

void xen_netbk_add_xenvif(struct xenvif *vif)
{
	int i;
	int min_netfront_count;
	int min_group = 0;
	struct xen_netbk *netbk;

	min_netfront_count = atomic_read(&xen_netbk[0].netfront_count);
	for (i = 0; i < xen_netbk_group_nr; i++) {
		int netfront_count = atomic_read(&xen_netbk[i].netfront_count);
		if (netfront_count < min_netfront_count) {
			min_group = i;
			min_netfront_count = netfront_count;
		}
	}

	netbk = &xen_netbk[min_group];

	vif->netbk = netbk;
	atomic_inc(&netbk->netfront_count);
}

void xen_netbk_remove_xenvif(struct xenvif *vif)
{
	struct xen_netbk *netbk = vif->netbk;
	vif->netbk = NULL;
	atomic_dec(&netbk->netfront_count);
}

static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx,
				  u8 status);
static void make_tx_response(struct xenvif *vif,
			     struct xen_netif_tx_request *txp,
			     s8       st);
static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif,
					     u16      id,
					     s8       st,
					     u16      offset,
					     u16      size,
					     u16      flags);

static inline unsigned long idx_to_pfn(struct xen_netbk *netbk,
				       u16 idx)
{
	return page_to_pfn(netbk->mmap_pages[idx]);
}

static inline unsigned long idx_to_kaddr(struct xen_netbk *netbk,
					 u16 idx)
{
	return (unsigned long)pfn_to_kaddr(idx_to_pfn(netbk, idx));
}

/* extra field used in struct page */
static inline void set_page_ext(struct page *pg, struct xen_netbk *netbk,
				unsigned int idx)
{
	unsigned int group = netbk - xen_netbk;
	union page_ext ext = { .e = { .group = group + 1, .idx = idx } };

	BUILD_BUG_ON(sizeof(ext) > sizeof(ext.mapping));
	pg->mapping = ext.mapping;
}

static int get_page_ext(struct page *pg,
			unsigned int *pgroup, unsigned int *pidx)
{
	union page_ext ext = { .mapping = pg->mapping };
	struct xen_netbk *netbk;
	unsigned int group, idx;

	group = ext.e.group - 1;

	if (group < 0 || group >= xen_netbk_group_nr)
		return 0;

	netbk = &xen_netbk[group];

	idx = ext.e.idx;

	if ((idx < 0) || (idx >= MAX_PENDING_REQS))
		return 0;

	if (netbk->mmap_pages[idx] != pg)
		return 0;

	*pgroup = group;
	*pidx = idx;

	return 1;
}

/*
 * This is the amount of packet we copy rather than map, so that the
 * guest can't fiddle with the contents of the headers while we do
 * packet processing on them (netfilter, routing, etc).
 */
#define PKT_PROT_LEN    (ETH_HLEN + \
			 VLAN_HLEN + \
			 sizeof(struct iphdr) + MAX_IPOPTLEN + \
			 sizeof(struct tcphdr) + MAX_TCP_OPTION_SPACE)

static u16 frag_get_pending_idx(skb_frag_t *frag)
{
	return (u16)frag->page_offset;
}

static void frag_set_pending_idx(skb_frag_t *frag, u16 pending_idx)
{
	frag->page_offset = pending_idx;
}

static inline pending_ring_idx_t pending_index(unsigned i)
{
	return i & (MAX_PENDING_REQS-1);
}

static inline pending_ring_idx_t nr_pending_reqs(struct xen_netbk *netbk)
{
	return MAX_PENDING_REQS -
		netbk->pending_prod + netbk->pending_cons;
}

static void xen_netbk_kick_thread(struct xen_netbk *netbk)
{
	wake_up(&netbk->wq);
}

static int max_required_rx_slots(struct xenvif *vif)
{
	int max = DIV_ROUND_UP(vif->dev->mtu, PAGE_SIZE);

	if (vif->can_sg || vif->gso || vif->gso_prefix)
		max += MAX_SKB_FRAGS + 1; /* extra_info + frags */

	return max;
}

int xen_netbk_rx_ring_full(struct xenvif *vif)
{
	RING_IDX peek   = vif->rx_req_cons_peek;
	RING_IDX needed = max_required_rx_slots(vif);

	return ((vif->rx.sring->req_prod - peek) < needed) ||
	       ((vif->rx.rsp_prod_pvt + XEN_NETIF_RX_RING_SIZE - peek) < needed);
}

int xen_netbk_must_stop_queue(struct xenvif *vif)
{
	if (!xen_netbk_rx_ring_full(vif))
		return 0;

	vif->rx.sring->req_event = vif->rx_req_cons_peek +
		max_required_rx_slots(vif);
	mb(); /* request notification /then/ check the queue */

	return xen_netbk_rx_ring_full(vif);
}

/*
 * Returns true if we should start a new receive buffer instead of
 * adding 'size' bytes to a buffer which currently contains 'offset'
 * bytes.
 */
static bool start_new_rx_buffer(int offset, unsigned long size, int head)
{
	/* simple case: we have completely filled the current buffer. */
	if (offset == MAX_BUFFER_OFFSET)
		return true;

	/*
	 * complex case: start a fresh buffer if the current frag
	 * would overflow the current buffer but only if:
	 *     (i)   this frag would fit completely in the next buffer
	 * and (ii)  there is already some data in the current buffer
	 * and (iii) this is not the head buffer.
	 *
	 * Where:
	 * - (i) stops us splitting a frag into two copies
	 *   unless the frag is too large for a single buffer.
	 * - (ii) stops us from leaving a buffer pointlessly empty.
	 * - (iii) stops us leaving the first buffer
	 *   empty. Strictly speaking this is already covered
	 *   by (ii) but is explicitly checked because
	 *   netfront relies on the first buffer being
	 *   non-empty and can crash otherwise.
	 *
	 * This means we will effectively linearise small
	 * frags but do not needlessly split large buffers
	 * into multiple copies tend to give large frags their
	 * own buffers as before.
	 */
	if ((offset + size > MAX_BUFFER_OFFSET) &&
	    (size <= MAX_BUFFER_OFFSET) && offset && !head)
		return true;

	return false;
}

/*
 * Figure out how many ring slots we're going to need to send @skb to
 * the guest. This function is essentially a dry run of
 * netbk_gop_frag_copy.
 */
unsigned int xen_netbk_count_skb_slots(struct xenvif *vif, struct sk_buff *skb)
{
	unsigned int count;
	int i, copy_off;

	count = DIV_ROUND_UP(
			offset_in_page(skb->data)+skb_headlen(skb), PAGE_SIZE);

	copy_off = skb_headlen(skb) % PAGE_SIZE;

	if (skb_shinfo(skb)->gso_size)
		count++;

	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
		unsigned long size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
		unsigned long bytes;
		while (size > 0) {
			BUG_ON(copy_off > MAX_BUFFER_OFFSET);

			if (start_new_rx_buffer(copy_off, size, 0)) {
				count++;
				copy_off = 0;
			}

			bytes = size;
			if (copy_off + bytes > MAX_BUFFER_OFFSET)
				bytes = MAX_BUFFER_OFFSET - copy_off;

			copy_off += bytes;
			size -= bytes;
		}
	}
	return count;
}

struct netrx_pending_operations {
	unsigned copy_prod, copy_cons;
	unsigned meta_prod, meta_cons;
	struct gnttab_copy *copy;
	struct netbk_rx_meta *meta;
	int copy_off;
	grant_ref_t copy_gref;
};

static struct netbk_rx_meta *get_next_rx_buffer(struct xenvif *vif,
						struct netrx_pending_operations *npo)
{
	struct netbk_rx_meta *meta;
	struct xen_netif_rx_request *req;

	req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++);

	meta = npo->meta + npo->meta_prod++;
	meta->gso_size = 0;
	meta->size = 0;
	meta->id = req->id;

	npo->copy_off = 0;
	npo->copy_gref = req->gref;

	return meta;
}

/*
 * Set up the grant operations for this fragment. If it's a flipping
 * interface, we also set up the unmap request from here.
 */
static void netbk_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb,
				struct netrx_pending_operations *npo,
				struct page *page, unsigned long size,
				unsigned long offset, int *head)
{
	struct gnttab_copy *copy_gop;
	struct netbk_rx_meta *meta;
	/*
	 * These variables are used iff get_page_ext returns true,
	 * in which case they are guaranteed to be initialized.
	 */
	unsigned int uninitialized_var(group), uninitialized_var(idx);
	int foreign = get_page_ext(page, &group, &idx);
	unsigned long bytes;

	/* Data must not cross a page boundary. */
	BUG_ON(size + offset > PAGE_SIZE);

	meta = npo->meta + npo->meta_prod - 1;

	while (size > 0) {
		BUG_ON(npo->copy_off > MAX_BUFFER_OFFSET);

		if (start_new_rx_buffer(npo->copy_off, size, *head)) {
			/*
			 * Netfront requires there to be some data in the head
			 * buffer.
			 */
			BUG_ON(*head);

			meta = get_next_rx_buffer(vif, npo);
		}

		bytes = size;
		if (npo->copy_off + bytes > MAX_BUFFER_OFFSET)
			bytes = MAX_BUFFER_OFFSET - npo->copy_off;

		copy_gop = npo->copy + npo->copy_prod++;
		copy_gop->flags = GNTCOPY_dest_gref;
		if (foreign) {
			struct xen_netbk *netbk = &xen_netbk[group];
			struct pending_tx_info *src_pend;

			src_pend = &netbk->pending_tx_info[idx];

			copy_gop->source.domid = src_pend->vif->domid;
			copy_gop->source.u.ref = src_pend->req.gref;
			copy_gop->flags |= GNTCOPY_source_gref;
		} else {
			void *vaddr = page_address(page);
			copy_gop->source.domid = DOMID_SELF;
			copy_gop->source.u.gmfn = virt_to_mfn(vaddr);
		}
		copy_gop->source.offset = offset;
		copy_gop->dest.domid = vif->domid;

		copy_gop->dest.offset = npo->copy_off;
		copy_gop->dest.u.ref = npo->copy_gref;
		copy_gop->len = bytes;

		npo->copy_off += bytes;
		meta->size += bytes;

		offset += bytes;
		size -= bytes;

		/* Leave a gap for the GSO descriptor. */
		if (*head && skb_shinfo(skb)->gso_size && !vif->gso_prefix)
			vif->rx.req_cons++;

		*head = 0; /* There must be something in this buffer now. */

	}
}

/*
 * Prepare an SKB to be transmitted to the frontend.
 *
 * This function is responsible for allocating grant operations, meta
 * structures, etc.
 *
 * It returns the number of meta structures consumed. The number of
 * ring slots used is always equal to the number of meta slots used
 * plus the number of GSO descriptors used. Currently, we use either
 * zero GSO descriptors (for non-GSO packets) or one descriptor (for
 * frontend-side LRO).
 */
static int netbk_gop_skb(struct sk_buff *skb,
			 struct netrx_pending_operations *npo)
{
	struct xenvif *vif = netdev_priv(skb->dev);
	int nr_frags = skb_shinfo(skb)->nr_frags;
	int i;
	struct xen_netif_rx_request *req;
	struct netbk_rx_meta *meta;
	unsigned char *data;
	int head = 1;
	int old_meta_prod;

	old_meta_prod = npo->meta_prod;

	/* Set up a GSO prefix descriptor, if necessary */
	if (skb_shinfo(skb)->gso_size && vif->gso_prefix) {
		req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++);
		meta = npo->meta + npo->meta_prod++;
		meta->gso_size = skb_shinfo(skb)->gso_size;
		meta->size = 0;
		meta->id = req->id;
	}

	req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++);
	meta = npo->meta + npo->meta_prod++;

	if (!vif->gso_prefix)
		meta->gso_size = skb_shinfo(skb)->gso_size;
	else
		meta->gso_size = 0;

	meta->size = 0;
	meta->id = req->id;
	npo->copy_off = 0;
	npo->copy_gref = req->gref;

	data = skb->data;
	while (data < skb_tail_pointer(skb)) {
		unsigned int offset = offset_in_page(data);
		unsigned int len = PAGE_SIZE - offset;

		if (data + len > skb_tail_pointer(skb))
			len = skb_tail_pointer(skb) - data;

		netbk_gop_frag_copy(vif, skb, npo,
				    virt_to_page(data), len, offset, &head);
		data += len;
	}

	for (i = 0; i < nr_frags; i++) {
		netbk_gop_frag_copy(vif, skb, npo,
				    skb_frag_page(&skb_shinfo(skb)->frags[i]),
				    skb_frag_size(&skb_shinfo(skb)->frags[i]),
				    skb_shinfo(skb)->frags[i].page_offset,
				    &head);
	}

	return npo->meta_prod - old_meta_prod;
}

/*
 * This is a twin to netbk_gop_skb.  Assume that netbk_gop_skb was
 * used to set up the operations on the top of
 * netrx_pending_operations, which have since been done.  Check that
 * they didn't give any errors and advance over them.
 */
static int netbk_check_gop(struct xenvif *vif, int nr_meta_slots,
			   struct netrx_pending_operations *npo)
{
	struct gnttab_copy     *copy_op;
	int status = XEN_NETIF_RSP_OKAY;
	int i;

	for (i = 0; i < nr_meta_slots; i++) {
		copy_op = npo->copy + npo->copy_cons++;
		if (copy_op->status != GNTST_okay) {
			netdev_dbg(vif->dev,
				   "Bad status %d from copy to DOM%d.\n",
				   copy_op->status, vif->domid);
			status = XEN_NETIF_RSP_ERROR;
		}
	}

	return status;
}

static void netbk_add_frag_responses(struct xenvif *vif, int status,
				     struct netbk_rx_meta *meta,
				     int nr_meta_slots)
{
	int i;
	unsigned long offset;

	/* No fragments used */
	if (nr_meta_slots <= 1)
		return;

	nr_meta_slots--;

	for (i = 0; i < nr_meta_slots; i++) {
		int flags;
		if (i == nr_meta_slots - 1)
			flags = 0;
		else
			flags = XEN_NETRXF_more_data;

		offset = 0;
		make_rx_response(vif, meta[i].id, status, offset,
				 meta[i].size, flags);
	}
}

struct skb_cb_overlay {
	int meta_slots_used;
};

static void xen_netbk_rx_action(struct xen_netbk *netbk)
{
	struct xenvif *vif = NULL, *tmp;
	s8 status;
	u16 irq, flags;
	struct xen_netif_rx_response *resp;
	struct sk_buff_head rxq;
	struct sk_buff *skb;
	LIST_HEAD(notify);
	int ret;
	int nr_frags;
	int count;
	unsigned long offset;
	struct skb_cb_overlay *sco;

	struct netrx_pending_operations npo = {
		.copy  = netbk->grant_copy_op,
		.meta  = netbk->meta,
	};

	skb_queue_head_init(&rxq);

	count = 0;

	while ((skb = skb_dequeue(&netbk->rx_queue)) != NULL) {
		vif = netdev_priv(skb->dev);
		nr_frags = skb_shinfo(skb)->nr_frags;

		sco = (struct skb_cb_overlay *)skb->cb;
		sco->meta_slots_used = netbk_gop_skb(skb, &npo);

		count += nr_frags + 1;

		__skb_queue_tail(&rxq, skb);

		/* Filled the batch queue? */
		if (count + MAX_SKB_FRAGS >= XEN_NETIF_RX_RING_SIZE)
			break;
	}

	BUG_ON(npo.meta_prod > ARRAY_SIZE(netbk->meta));

	if (!npo.copy_prod)
		return;

	BUG_ON(npo.copy_prod > ARRAY_SIZE(netbk->grant_copy_op));
	ret = HYPERVISOR_grant_table_op(GNTTABOP_copy, &netbk->grant_copy_op,
					npo.copy_prod);
	BUG_ON(ret != 0);

	while ((skb = __skb_dequeue(&rxq)) != NULL) {
		sco = (struct skb_cb_overlay *)skb->cb;

		vif = netdev_priv(skb->dev);

		if (netbk->meta[npo.meta_cons].gso_size && vif->gso_prefix) {
			resp = RING_GET_RESPONSE(&vif->rx,
						vif->rx.rsp_prod_pvt++);

			resp->flags = XEN_NETRXF_gso_prefix | XEN_NETRXF_more_data;

			resp->offset = netbk->meta[npo.meta_cons].gso_size;
			resp->id = netbk->meta[npo.meta_cons].id;
			resp->status = sco->meta_slots_used;

			npo.meta_cons++;
			sco->meta_slots_used--;
		}


		vif->dev->stats.tx_bytes += skb->len;
		vif->dev->stats.tx_packets++;

		status = netbk_check_gop(vif, sco->meta_slots_used, &npo);

		if (sco->meta_slots_used == 1)
			flags = 0;
		else
			flags = XEN_NETRXF_more_data;

		if (skb->ip_summed == CHECKSUM_PARTIAL) /* local packet? */
			flags |= XEN_NETRXF_csum_blank | XEN_NETRXF_data_validated;
		else if (skb->ip_summed == CHECKSUM_UNNECESSARY)
			/* remote but checksummed. */
			flags |= XEN_NETRXF_data_validated;

		offset = 0;
		resp = make_rx_response(vif, netbk->meta[npo.meta_cons].id,
					status, offset,
					netbk->meta[npo.meta_cons].size,
					flags);

		if (netbk->meta[npo.meta_cons].gso_size && !vif->gso_prefix) {
			struct xen_netif_extra_info *gso =
				(struct xen_netif_extra_info *)
				RING_GET_RESPONSE(&vif->rx,
						  vif->rx.rsp_prod_pvt++);

			resp->flags |= XEN_NETRXF_extra_info;

			gso->u.gso.size = netbk->meta[npo.meta_cons].gso_size;
			gso->u.gso.type = XEN_NETIF_GSO_TYPE_TCPV4;
			gso->u.gso.pad = 0;
			gso->u.gso.features = 0;

			gso->type = XEN_NETIF_EXTRA_TYPE_GSO;
			gso->flags = 0;
		}

		netbk_add_frag_responses(vif, status,
					 netbk->meta + npo.meta_cons + 1,
					 sco->meta_slots_used);

		RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->rx, ret);
		irq = vif->irq;
		if (ret && list_empty(&vif->notify_list))
			list_add_tail(&vif->notify_list, &notify);

		xenvif_notify_tx_completion(vif);

		xenvif_put(vif);
		npo.meta_cons += sco->meta_slots_used;
		dev_kfree_skb(skb);
	}

	list_for_each_entry_safe(vif, tmp, &notify, notify_list) {
		notify_remote_via_irq(vif->irq);
		list_del_init(&vif->notify_list);
	}

	/* More work to do? */
	if (!skb_queue_empty(&netbk->rx_queue) &&
			!timer_pending(&netbk->net_timer))
		xen_netbk_kick_thread(netbk);
}

void xen_netbk_queue_tx_skb(struct xenvif *vif, struct sk_buff *skb)
{
	struct xen_netbk *netbk = vif->netbk;

	skb_queue_tail(&netbk->rx_queue, skb);

	xen_netbk_kick_thread(netbk);
}

static void xen_netbk_alarm(unsigned long data)
{
	struct xen_netbk *netbk = (struct xen_netbk *)data;
	xen_netbk_kick_thread(netbk);
}

static int __on_net_schedule_list(struct xenvif *vif)
{
	return !list_empty(&vif->schedule_list);
}

/* Must be called with net_schedule_list_lock held */
static void remove_from_net_schedule_list(struct xenvif *vif)
{
	if (likely(__on_net_schedule_list(vif))) {
		list_del_init(&vif->schedule_list);
		xenvif_put(vif);
	}
}

static struct xenvif *poll_net_schedule_list(struct xen_netbk *netbk)
{
	struct xenvif *vif = NULL;

	spin_lock_irq(&netbk->net_schedule_list_lock);
	if (list_empty(&netbk->net_schedule_list))
		goto out;

	vif = list_first_entry(&netbk->net_schedule_list,
			       struct xenvif, schedule_list);
	if (!vif)
		goto out;

	xenvif_get(vif);

	remove_from_net_schedule_list(vif);
out:
	spin_unlock_irq(&netbk->net_schedule_list_lock);
	return vif;
}

void xen_netbk_schedule_xenvif(struct xenvif *vif)
{
	unsigned long flags;
	struct xen_netbk *netbk = vif->netbk;

	if (__on_net_schedule_list(vif))
		goto kick;

	spin_lock_irqsave(&netbk->net_schedule_list_lock, flags);
	if (!__on_net_schedule_list(vif) &&
	    likely(xenvif_schedulable(vif))) {
		list_add_tail(&vif->schedule_list, &netbk->net_schedule_list);
		xenvif_get(vif);
	}
	spin_unlock_irqrestore(&netbk->net_schedule_list_lock, flags);

kick:
	smp_mb();
	if ((nr_pending_reqs(netbk) < (MAX_PENDING_REQS/2)) &&
	    !list_empty(&netbk->net_schedule_list))
		xen_netbk_kick_thread(netbk);
}

void xen_netbk_deschedule_xenvif(struct xenvif *vif)
{
	struct xen_netbk *netbk = vif->netbk;
	spin_lock_irq(&netbk->net_schedule_list_lock);
	remove_from_net_schedule_list(vif);
	spin_unlock_irq(&netbk->net_schedule_list_lock);
}

void xen_netbk_check_rx_xenvif(struct xenvif *vif)
{
	int more_to_do;

	RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, more_to_do);

	if (more_to_do)
		xen_netbk_schedule_xenvif(vif);
}

static void tx_add_credit(struct xenvif *vif)
{
	unsigned long max_burst, max_credit;

	/*
	 * Allow a burst big enough to transmit a jumbo packet of up to 128kB.
	 * Otherwise the interface can seize up due to insufficient credit.
	 */
	max_burst = RING_GET_REQUEST(&vif->tx, vif->tx.req_cons)->size;
	max_burst = min(max_burst, 131072UL);
	max_burst = max(max_burst, vif->credit_bytes);

	/* Take care that adding a new chunk of credit doesn't wrap to zero. */
	max_credit = vif->remaining_credit + vif->credit_bytes;
	if (max_credit < vif->remaining_credit)
		max_credit = ULONG_MAX; /* wrapped: clamp to ULONG_MAX */

	vif->remaining_credit = min(max_credit, max_burst);
}

static void tx_credit_callback(unsigned long data)
{
	struct xenvif *vif = (struct xenvif *)data;
	tx_add_credit(vif);
	xen_netbk_check_rx_xenvif(vif);
}

static void netbk_tx_err(struct xenvif *vif,
			 struct xen_netif_tx_request *txp, RING_IDX end)
{
	RING_IDX cons = vif->tx.req_cons;

	do {
		make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR);
		if (cons == end)
			break;
		txp = RING_GET_REQUEST(&vif->tx, cons++);
	} while (1);
	vif->tx.req_cons = cons;
	xen_netbk_check_rx_xenvif(vif);
	xenvif_put(vif);
}

static void netbk_fatal_tx_err(struct xenvif *vif)
{
	netdev_err(vif->dev, "fatal error; disabling device\n");
	xenvif_carrier_off(vif);
	xenvif_put(vif);
}

static int netbk_count_requests(struct xenvif *vif,
				struct xen_netif_tx_request *first,
				struct xen_netif_tx_request *txp,
				int work_to_do)
{
	RING_IDX cons = vif->tx.req_cons;
	int frags = 0;

	if (!(first->flags & XEN_NETTXF_more_data))
		return 0;

	do {
		if (frags >= work_to_do) {
			netdev_err(vif->dev, "Need more frags\n");
			netbk_fatal_tx_err(vif);
			return -ENODATA;
		}

		if (unlikely(frags >= MAX_SKB_FRAGS)) {
			netdev_err(vif->dev, "Too many frags\n");
			netbk_fatal_tx_err(vif);
			return -E2BIG;
		}

		memcpy(txp, RING_GET_REQUEST(&vif->tx, cons + frags),
		       sizeof(*txp));
		if (txp->size > first->size) {
			netdev_err(vif->dev, "Frag is bigger than frame.\n");
			netbk_fatal_tx_err(vif);
			return -EIO;
		}

		first->size -= txp->size;
		frags++;

		if (unlikely((txp->offset + txp->size) > PAGE_SIZE)) {
			netdev_err(vif->dev, "txp->offset: %x, size: %u\n",
				 txp->offset, txp->size);
			netbk_fatal_tx_err(vif);
			return -EINVAL;
		}
	} while ((txp++)->flags & XEN_NETTXF_more_data);
	return frags;
}

static struct page *xen_netbk_alloc_page(struct xen_netbk *netbk,
					 u16 pending_idx)
{
	struct page *page;
	page = alloc_page(GFP_KERNEL|__GFP_COLD);
	if (!page)
		return NULL;
	set_page_ext(page, netbk, pending_idx);
	netbk->mmap_pages[pending_idx] = page;
	return page;
}

static struct gnttab_copy *xen_netbk_get_requests(struct xen_netbk *netbk,
						  struct xenvif *vif,
						  struct sk_buff *skb,
						  struct xen_netif_tx_request *txp,
						  struct gnttab_copy *gop)
{
	struct skb_shared_info *shinfo = skb_shinfo(skb);
	skb_frag_t *frags = shinfo->frags;
	u16 pending_idx = *((u16 *)skb->data);
	int i, start;

	/* Skip first skb fragment if it is on same page as header fragment. */
	start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx);

	for (i = start; i < shinfo->nr_frags; i++, txp++) {
		struct page *page;
		pending_ring_idx_t index;
		struct pending_tx_info *pending_tx_info =
			netbk->pending_tx_info;

		index = pending_index(netbk->pending_cons++);
		pending_idx = netbk->pending_ring[index];
		page = xen_netbk_alloc_page(netbk, pending_idx);
		if (!page)
			goto err;

		gop->source.u.ref = txp->gref;
		gop->source.domid = vif->domid;
		gop->source.offset = txp->offset;

		gop->dest.u.gmfn = virt_to_mfn(page_address(page));
		gop->dest.domid = DOMID_SELF;
		gop->dest.offset = txp->offset;

		gop->len = txp->size;
		gop->flags = GNTCOPY_source_gref;

		gop++;

		memcpy(&pending_tx_info[pending_idx].req, txp, sizeof(*txp));
		xenvif_get(vif);
		pending_tx_info[pending_idx].vif = vif;
		frag_set_pending_idx(&frags[i], pending_idx);
	}

	return gop;
err:
	/* Unwind, freeing all pages and sending error responses. */
	while (i-- > start) {
		xen_netbk_idx_release(netbk, frag_get_pending_idx(&frags[i]),
				      XEN_NETIF_RSP_ERROR);
	}
	/* The head too, if necessary. */
	if (start)
		xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_ERROR);

	return NULL;
}

static int xen_netbk_tx_check_gop(struct xen_netbk *netbk,
				  struct sk_buff *skb,
				  struct gnttab_copy **gopp)
{
	struct gnttab_copy *gop = *gopp;
	u16 pending_idx = *((u16 *)skb->data);
	struct skb_shared_info *shinfo = skb_shinfo(skb);
	int nr_frags = shinfo->nr_frags;
	int i, err, start;

	/* Check status of header. */
	err = gop->status;
	if (unlikely(err))
		xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_ERROR);

	/* Skip first skb fragment if it is on same page as header fragment. */
	start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx);

	for (i = start; i < nr_frags; i++) {
		int j, newerr;

		pending_idx = frag_get_pending_idx(&shinfo->frags[i]);

		/* Check error status: if okay then remember grant handle. */
		newerr = (++gop)->status;
		if (likely(!newerr)) {
			/* Had a previous error? Invalidate this fragment. */
			if (unlikely(err))
				xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY);
			continue;
		}

		/* Error on this fragment: respond to client with an error. */
		xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_ERROR);

		/* Not the first error? Preceding frags already invalidated. */
		if (err)
			continue;

		/* First error: invalidate header and preceding fragments. */
		pending_idx = *((u16 *)skb->data);
		xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY);
		for (j = start; j < i; j++) {
			pending_idx = frag_get_pending_idx(&shinfo->frags[j]);
			xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY);
		}

		/* Remember the error: invalidate all subsequent fragments. */
		err = newerr;
	}

	*gopp = gop + 1;
	return err;
}

static void xen_netbk_fill_frags(struct xen_netbk *netbk, struct sk_buff *skb)
{
	struct skb_shared_info *shinfo = skb_shinfo(skb);
	int nr_frags = shinfo->nr_frags;
	int i;

	for (i = 0; i < nr_frags; i++) {
		skb_frag_t *frag = shinfo->frags + i;
		struct xen_netif_tx_request *txp;
		struct page *page;
		u16 pending_idx;

		pending_idx = frag_get_pending_idx(frag);

		txp = &netbk->pending_tx_info[pending_idx].req;
		page = virt_to_page(idx_to_kaddr(netbk, pending_idx));
		__skb_fill_page_desc(skb, i, page, txp->offset, txp->size);
		skb->len += txp->size;
		skb->data_len += txp->size;
		skb->truesize += txp->size;

		/* Take an extra reference to offset xen_netbk_idx_release */
		get_page(netbk->mmap_pages[pending_idx]);
		xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY);
	}
}

static int xen_netbk_get_extras(struct xenvif *vif,
				struct xen_netif_extra_info *extras,
				int work_to_do)
{
	struct xen_netif_extra_info extra;
	RING_IDX cons = vif->tx.req_cons;

	do {
		if (unlikely(work_to_do-- <= 0)) {
			netdev_err(vif->dev, "Missing extra info\n");
			netbk_fatal_tx_err(vif);
			return -EBADR;
		}

		memcpy(&extra, RING_GET_REQUEST(&vif->tx, cons),
		       sizeof(extra));
		if (unlikely(!extra.type ||
			     extra.type >= XEN_NETIF_EXTRA_TYPE_MAX)) {
			vif->tx.req_cons = ++cons;
			netdev_err(vif->dev,
				   "Invalid extra type: %d\n", extra.type);
			netbk_fatal_tx_err(vif);
			return -EINVAL;
		}

		memcpy(&extras[extra.type - 1], &extra, sizeof(extra));
		vif->tx.req_cons = ++cons;
	} while (extra.flags & XEN_NETIF_EXTRA_FLAG_MORE);

	return work_to_do;
}

static int netbk_set_skb_gso(struct xenvif *vif,
			     struct sk_buff *skb,
			     struct xen_netif_extra_info *gso)
{
	if (!gso->u.gso.size) {
		netdev_err(vif->dev, "GSO size must not be zero.\n");
		netbk_fatal_tx_err(vif);
		return -EINVAL;
	}

	/* Currently only TCPv4 S.O. is supported. */
	if (gso->u.gso.type != XEN_NETIF_GSO_TYPE_TCPV4) {
		netdev_err(vif->dev, "Bad GSO type %d.\n", gso->u.gso.type);
		netbk_fatal_tx_err(vif);
		return -EINVAL;
	}

	skb_shinfo(skb)->gso_size = gso->u.gso.size;
	skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;

	/* Header must be checked, and gso_segs computed. */
	skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
	skb_shinfo(skb)->gso_segs = 0;

	return 0;
}

static int checksum_setup(struct xenvif *vif, struct sk_buff *skb)
{
	struct iphdr *iph;
	unsigned char *th;
	int err = -EPROTO;
	int recalculate_partial_csum = 0;

	/*
	 * A GSO SKB must be CHECKSUM_PARTIAL. However some buggy
	 * peers can fail to set NETRXF_csum_blank when sending a GSO
	 * frame. In this case force the SKB to CHECKSUM_PARTIAL and
	 * recalculate the partial checksum.
	 */
	if (skb->ip_summed != CHECKSUM_PARTIAL && skb_is_gso(skb)) {
		vif->rx_gso_checksum_fixup++;
		skb->ip_summed = CHECKSUM_PARTIAL;
		recalculate_partial_csum = 1;
	}

	/* A non-CHECKSUM_PARTIAL SKB does not require setup. */
	if (skb->ip_summed != CHECKSUM_PARTIAL)
		return 0;

	if (skb->protocol != htons(ETH_P_IP))
		goto out;

	iph = (void *)skb->data;
	th = skb->data + 4 * iph->ihl;
	if (th >= skb_tail_pointer(skb))
		goto out;

	skb->csum_start = th - skb->head;
	switch (iph->protocol) {
	case IPPROTO_TCP:
		skb->csum_offset = offsetof(struct tcphdr, check);

		if (recalculate_partial_csum) {
			struct tcphdr *tcph = (struct tcphdr *)th;
			tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
							 skb->len - iph->ihl*4,
							 IPPROTO_TCP, 0);
		}
		break;
	case IPPROTO_UDP:
		skb->csum_offset = offsetof(struct udphdr, check);

		if (recalculate_partial_csum) {
			struct udphdr *udph = (struct udphdr *)th;
			udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
							 skb->len - iph->ihl*4,
							 IPPROTO_UDP, 0);
		}
		break;
	default:
		if (net_ratelimit())
			netdev_err(vif->dev,
				   "Attempting to checksum a non-TCP/UDP packet, dropping a protocol %d packet\n",
				   iph->protocol);
		goto out;
	}

	if ((th + skb->csum_offset + 2) > skb_tail_pointer(skb))
		goto out;

	err = 0;

out:
	return err;
}

static bool tx_credit_exceeded(struct xenvif *vif, unsigned size)
{
	unsigned long now = jiffies;
	unsigned long next_credit =
		vif->credit_timeout.expires +
		msecs_to_jiffies(vif->credit_usec / 1000);

	/* Timer could already be pending in rare cases. */
	if (timer_pending(&vif->credit_timeout))
		return true;

	/* Passed the point where we can replenish credit? */
	if (time_after_eq(now, next_credit)) {
		vif->credit_timeout.expires = now;
		tx_add_credit(vif);
	}

	/* Still too big to send right now? Set a callback. */
	if (size > vif->remaining_credit) {
		vif->credit_timeout.data     =
			(unsigned long)vif;
		vif->credit_timeout.function =
			tx_credit_callback;
		mod_timer(&vif->credit_timeout,
			  next_credit);

		return true;
	}

	return false;
}

static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk)
{
	struct gnttab_copy *gop = netbk->tx_copy_ops, *request_gop;
	struct sk_buff *skb;
	int ret;

	while (((nr_pending_reqs(netbk) + MAX_SKB_FRAGS) < MAX_PENDING_REQS) &&
		!list_empty(&netbk->net_schedule_list)) {
		struct xenvif *vif;
		struct xen_netif_tx_request txreq;
		struct xen_netif_tx_request txfrags[MAX_SKB_FRAGS];
		struct page *page;
		struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX-1];
		u16 pending_idx;
		RING_IDX idx;
		int work_to_do;
		unsigned int data_len;
		pending_ring_idx_t index;

		/* Get a netif from the list with work to do. */
		vif = poll_net_schedule_list(netbk);
		/* This can sometimes happen because the test of
		 * list_empty(net_schedule_list) at the top of the
		 * loop is unlocked.  Just go back and have another
		 * look.
		 */
		if (!vif)
			continue;

		if (vif->tx.sring->req_prod - vif->tx.req_cons >
		    XEN_NETIF_TX_RING_SIZE) {
			netdev_err(vif->dev,
				   "Impossible number of requests. "
				   "req_prod %d, req_cons %d, size %ld\n",
				   vif->tx.sring->req_prod, vif->tx.req_cons,
				   XEN_NETIF_TX_RING_SIZE);
			netbk_fatal_tx_err(vif);
			continue;
		}

		RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, work_to_do);
		if (!work_to_do) {
			xenvif_put(vif);
			continue;
		}

		idx = vif->tx.req_cons;
		rmb(); /* Ensure that we see the request before we copy it. */
		memcpy(&txreq, RING_GET_REQUEST(&vif->tx, idx), sizeof(txreq));

		/* Credit-based scheduling. */
		if (txreq.size > vif->remaining_credit &&
		    tx_credit_exceeded(vif, txreq.size)) {
			xenvif_put(vif);
			continue;
		}

		vif->remaining_credit -= txreq.size;

		work_to_do--;
		vif->tx.req_cons = ++idx;

		memset(extras, 0, sizeof(extras));
		if (txreq.flags & XEN_NETTXF_extra_info) {
			work_to_do = xen_netbk_get_extras(vif, extras,
							  work_to_do);
			idx = vif->tx.req_cons;
			if (unlikely(work_to_do < 0))
				continue;
		}

		ret = netbk_count_requests(vif, &txreq, txfrags, work_to_do);
		if (unlikely(ret < 0))
			continue;

		idx += ret;

		if (unlikely(txreq.size < ETH_HLEN)) {
			netdev_dbg(vif->dev,
				   "Bad packet size: %d\n", txreq.size);
			netbk_tx_err(vif, &txreq, idx);
			continue;
		}

		/* No crossing a page as the payload mustn't fragment. */
		if (unlikely((txreq.offset + txreq.size) > PAGE_SIZE)) {
			netdev_err(vif->dev,
				   "txreq.offset: %x, size: %u, end: %lu\n",
				   txreq.offset, txreq.size,
				   (txreq.offset&~PAGE_MASK) + txreq.size);
			netbk_fatal_tx_err(vif);
			continue;
		}

		index = pending_index(netbk->pending_cons);
		pending_idx = netbk->pending_ring[index];

		data_len = (txreq.size > PKT_PROT_LEN &&
			    ret < MAX_SKB_FRAGS) ?
			PKT_PROT_LEN : txreq.size;

		skb = alloc_skb(data_len + NET_SKB_PAD + NET_IP_ALIGN,
				GFP_ATOMIC | __GFP_NOWARN);
		if (unlikely(skb == NULL)) {
			netdev_dbg(vif->dev,
				   "Can't allocate a skb in start_xmit.\n");
			netbk_tx_err(vif, &txreq, idx);
			break;
		}

		/* Packets passed to netif_rx() must have some headroom. */
		skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);

		if (extras[XEN_NETIF_EXTRA_TYPE_GSO - 1].type) {
			struct xen_netif_extra_info *gso;
			gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1];

			if (netbk_set_skb_gso(vif, skb, gso)) {
				/* Failure in netbk_set_skb_gso is fatal. */
				kfree_skb(skb);
				continue;
			}
		}

		/* XXX could copy straight to head */
		page = xen_netbk_alloc_page(netbk, pending_idx);
		if (!page) {
			kfree_skb(skb);
			netbk_tx_err(vif, &txreq, idx);
			continue;
		}

		gop->source.u.ref = txreq.gref;
		gop->source.domid = vif->domid;
		gop->source.offset = txreq.offset;

		gop->dest.u.gmfn = virt_to_mfn(page_address(page));
		gop->dest.domid = DOMID_SELF;
		gop->dest.offset = txreq.offset;

		gop->len = txreq.size;
		gop->flags = GNTCOPY_source_gref;

		gop++;

		memcpy(&netbk->pending_tx_info[pending_idx].req,
		       &txreq, sizeof(txreq));
		netbk->pending_tx_info[pending_idx].vif = vif;
		*((u16 *)skb->data) = pending_idx;

		__skb_put(skb, data_len);

		skb_shinfo(skb)->nr_frags = ret;
		if (data_len < txreq.size) {
			skb_shinfo(skb)->nr_frags++;
			frag_set_pending_idx(&skb_shinfo(skb)->frags[0],
					     pending_idx);
		} else {
			frag_set_pending_idx(&skb_shinfo(skb)->frags[0],
					     INVALID_PENDING_IDX);
		}

		__skb_queue_tail(&netbk->tx_queue, skb);

		netbk->pending_cons++;

		request_gop = xen_netbk_get_requests(netbk, vif,
						     skb, txfrags, gop);
		if (request_gop == NULL) {
			kfree_skb(skb);
			netbk_tx_err(vif, &txreq, idx);
			continue;
		}
		gop = request_gop;

		vif->tx.req_cons = idx;
		xen_netbk_check_rx_xenvif(vif);

		if ((gop-netbk->tx_copy_ops) >= ARRAY_SIZE(netbk->tx_copy_ops))
			break;
	}

	return gop - netbk->tx_copy_ops;
}

static void xen_netbk_tx_submit(struct xen_netbk *netbk)
{
	struct gnttab_copy *gop = netbk->tx_copy_ops;
	struct sk_buff *skb;

	while ((skb = __skb_dequeue(&netbk->tx_queue)) != NULL) {
		struct xen_netif_tx_request *txp;
		struct xenvif *vif;
		u16 pending_idx;
		unsigned data_len;

		pending_idx = *((u16 *)skb->data);
		vif = netbk->pending_tx_info[pending_idx].vif;
		txp = &netbk->pending_tx_info[pending_idx].req;

		/* Check the remap error code. */
		if (unlikely(xen_netbk_tx_check_gop(netbk, skb, &gop))) {
			netdev_dbg(vif->dev, "netback grant failed.\n");
			skb_shinfo(skb)->nr_frags = 0;
			kfree_skb(skb);
			continue;
		}

		data_len = skb->len;
		memcpy(skb->data,
		       (void *)(idx_to_kaddr(netbk, pending_idx)|txp->offset),
		       data_len);
		if (data_len < txp->size) {
			/* Append the packet payload as a fragment. */
			txp->offset += data_len;
			txp->size -= data_len;
		} else {
			/* Schedule a response immediately. */
			xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY);
		}

		if (txp->flags & XEN_NETTXF_csum_blank)
			skb->ip_summed = CHECKSUM_PARTIAL;
		else if (txp->flags & XEN_NETTXF_data_validated)
			skb->ip_summed = CHECKSUM_UNNECESSARY;

		xen_netbk_fill_frags(netbk, skb);

		/*
		 * If the initial fragment was < PKT_PROT_LEN then
		 * pull through some bytes from the other fragments to
		 * increase the linear region to PKT_PROT_LEN bytes.
		 */
		if (skb_headlen(skb) < PKT_PROT_LEN && skb_is_nonlinear(skb)) {
			int target = min_t(int, skb->len, PKT_PROT_LEN);
			__pskb_pull_tail(skb, target - skb_headlen(skb));
		}

		skb->dev      = vif->dev;
		skb->protocol = eth_type_trans(skb, skb->dev);

		if (checksum_setup(vif, skb)) {
			netdev_dbg(vif->dev,
				   "Can't setup checksum in net_tx_action\n");
			kfree_skb(skb);
			continue;
		}

		vif->dev->stats.rx_bytes += skb->len;
		vif->dev->stats.rx_packets++;

		xenvif_receive_skb(vif, skb);
	}
}

/* Called after netfront has transmitted */
static void xen_netbk_tx_action(struct xen_netbk *netbk)
{
	unsigned nr_gops;
	int ret;

	nr_gops = xen_netbk_tx_build_gops(netbk);

	if (nr_gops == 0)
		return;
	ret = HYPERVISOR_grant_table_op(GNTTABOP_copy,
					netbk->tx_copy_ops, nr_gops);
	BUG_ON(ret);

	xen_netbk_tx_submit(netbk);

}

static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx,
				  u8 status)
{
	struct xenvif *vif;
	struct pending_tx_info *pending_tx_info;
	pending_ring_idx_t index;

	/* Already complete? */
	if (netbk->mmap_pages[pending_idx] == NULL)
		return;

	pending_tx_info = &netbk->pending_tx_info[pending_idx];

	vif = pending_tx_info->vif;

	make_tx_response(vif, &pending_tx_info->req, status);

	index = pending_index(netbk->pending_prod++);
	netbk->pending_ring[index] = pending_idx;

	xenvif_put(vif);

	netbk->mmap_pages[pending_idx]->mapping = 0;
	put_page(netbk->mmap_pages[pending_idx]);
	netbk->mmap_pages[pending_idx] = NULL;
}

static void make_tx_response(struct xenvif *vif,
			     struct xen_netif_tx_request *txp,
			     s8       st)
{
	RING_IDX i = vif->tx.rsp_prod_pvt;
	struct xen_netif_tx_response *resp;
	int notify;

	resp = RING_GET_RESPONSE(&vif->tx, i);
	resp->id     = txp->id;
	resp->status = st;

	if (txp->flags & XEN_NETTXF_extra_info)
		RING_GET_RESPONSE(&vif->tx, ++i)->status = XEN_NETIF_RSP_NULL;

	vif->tx.rsp_prod_pvt = ++i;
	RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->tx, notify);
	if (notify)
		notify_remote_via_irq(vif->irq);
}

static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif,
					     u16      id,
					     s8       st,
					     u16      offset,
					     u16      size,
					     u16      flags)
{
	RING_IDX i = vif->rx.rsp_prod_pvt;
	struct xen_netif_rx_response *resp;

	resp = RING_GET_RESPONSE(&vif->rx, i);
	resp->offset     = offset;
	resp->flags      = flags;
	resp->id         = id;
	resp->status     = (s16)size;
	if (st < 0)
		resp->status = (s16)st;

	vif->rx.rsp_prod_pvt = ++i;

	return resp;
}

static inline int rx_work_todo(struct xen_netbk *netbk)
{
	return !skb_queue_empty(&netbk->rx_queue);
}

static inline int tx_work_todo(struct xen_netbk *netbk)
{

	if (((nr_pending_reqs(netbk) + MAX_SKB_FRAGS) < MAX_PENDING_REQS) &&
			!list_empty(&netbk->net_schedule_list))
		return 1;

	return 0;
}

static int xen_netbk_kthread(void *data)
{
	struct xen_netbk *netbk = data;
	while (!kthread_should_stop()) {
		wait_event_interruptible(netbk->wq,
				rx_work_todo(netbk) ||
				tx_work_todo(netbk) ||
				kthread_should_stop());
		cond_resched();

		if (kthread_should_stop())
			break;

		if (rx_work_todo(netbk))
			xen_netbk_rx_action(netbk);

		if (tx_work_todo(netbk))
			xen_netbk_tx_action(netbk);
	}

	return 0;
}

void xen_netbk_unmap_frontend_rings(struct xenvif *vif)
{
	if (vif->tx.sring)
		xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(vif),
					vif->tx.sring);
	if (vif->rx.sring)
		xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(vif),
					vif->rx.sring);
}

int xen_netbk_map_frontend_rings(struct xenvif *vif,
				 grant_ref_t tx_ring_ref,
				 grant_ref_t rx_ring_ref)
{
	void *addr;
	struct xen_netif_tx_sring *txs;
	struct xen_netif_rx_sring *rxs;

	int err = -ENOMEM;

	err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(vif),
				     tx_ring_ref, &addr);
	if (err)
		goto err;

	txs = (struct xen_netif_tx_sring *)addr;
	BACK_RING_INIT(&vif->tx, txs, PAGE_SIZE);

	err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(vif),
				     rx_ring_ref, &addr);
	if (err)
		goto err;

	rxs = (struct xen_netif_rx_sring *)addr;
	BACK_RING_INIT(&vif->rx, rxs, PAGE_SIZE);

	vif->rx_req_cons_peek = 0;

	return 0;

err:
	xen_netbk_unmap_frontend_rings(vif);
	return err;
}

static int __init netback_init(void)
{
	int i;
	int rc = 0;
	int group;

	if (!xen_domain())
		return -ENODEV;

	xen_netbk_group_nr = num_online_cpus();
	xen_netbk = vzalloc(sizeof(struct xen_netbk) * xen_netbk_group_nr);
	if (!xen_netbk)
		return -ENOMEM;

	for (group = 0; group < xen_netbk_group_nr; group++) {
		struct xen_netbk *netbk = &xen_netbk[group];
		skb_queue_head_init(&netbk->rx_queue);
		skb_queue_head_init(&netbk->tx_queue);

		init_timer(&netbk->net_timer);
		netbk->net_timer.data = (unsigned long)netbk;
		netbk->net_timer.function = xen_netbk_alarm;

		netbk->pending_cons = 0;
		netbk->pending_prod = MAX_PENDING_REQS;
		for (i = 0; i < MAX_PENDING_REQS; i++)
			netbk->pending_ring[i] = i;

		init_waitqueue_head(&netbk->wq);
		netbk->task = kthread_create(xen_netbk_kthread,
					     (void *)netbk,
					     "netback/%u", group);

		if (IS_ERR(netbk->task)) {
			printk(KERN_ALERT "kthread_create() fails at netback\n");
			del_timer(&netbk->net_timer);
			rc = PTR_ERR(netbk->task);
			goto failed_init;
		}

		kthread_bind(netbk->task, group);

		INIT_LIST_HEAD(&netbk->net_schedule_list);

		spin_lock_init(&netbk->net_schedule_list_lock);

		atomic_set(&netbk->netfront_count, 0);

		wake_up_process(netbk->task);
	}

	rc = xenvif_xenbus_init();
	if (rc)
		goto failed_init;

	return 0;

failed_init:
	while (--group >= 0) {
		struct xen_netbk *netbk = &xen_netbk[group];
		for (i = 0; i < MAX_PENDING_REQS; i++) {
			if (netbk->mmap_pages[i])
				__free_page(netbk->mmap_pages[i]);
		}
		del_timer(&netbk->net_timer);
		kthread_stop(netbk->task);
	}
	vfree(xen_netbk);
	return rc;

}

module_init(netback_init);

MODULE_LICENSE("Dual BSD/GPL");
MODULE_ALIAS("xen-backend:vif");