summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/intel/ice/ice_txrx.c
blob: 2c212f64d99f2e392b2f2adc469527aa9162029a (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
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2018, Intel Corporation. */

/* The driver transmit and receive code */

#include <linux/prefetch.h>
#include <linux/mm.h>
#include <linux/bpf_trace.h>
#include <net/xdp.h>
#include "ice_txrx_lib.h"
#include "ice_lib.h"
#include "ice.h"
#include "ice_dcb_lib.h"
#include "ice_xsk.h"

#define ICE_RX_HDR_SIZE		256

/**
 * ice_unmap_and_free_tx_buf - Release a Tx buffer
 * @ring: the ring that owns the buffer
 * @tx_buf: the buffer to free
 */
static void
ice_unmap_and_free_tx_buf(struct ice_ring *ring, struct ice_tx_buf *tx_buf)
{
	if (tx_buf->skb) {
		if (ice_ring_is_xdp(ring))
			page_frag_free(tx_buf->raw_buf);
		else
			dev_kfree_skb_any(tx_buf->skb);
		if (dma_unmap_len(tx_buf, len))
			dma_unmap_single(ring->dev,
					 dma_unmap_addr(tx_buf, dma),
					 dma_unmap_len(tx_buf, len),
					 DMA_TO_DEVICE);
	} else if (dma_unmap_len(tx_buf, len)) {
		dma_unmap_page(ring->dev,
			       dma_unmap_addr(tx_buf, dma),
			       dma_unmap_len(tx_buf, len),
			       DMA_TO_DEVICE);
	}

	tx_buf->next_to_watch = NULL;
	tx_buf->skb = NULL;
	dma_unmap_len_set(tx_buf, len, 0);
	/* tx_buf must be completely set up in the transmit path */
}

static struct netdev_queue *txring_txq(const struct ice_ring *ring)
{
	return netdev_get_tx_queue(ring->netdev, ring->q_index);
}

/**
 * ice_clean_tx_ring - Free any empty Tx buffers
 * @tx_ring: ring to be cleaned
 */
void ice_clean_tx_ring(struct ice_ring *tx_ring)
{
	u16 i;

	if (ice_ring_is_xdp(tx_ring) && tx_ring->xsk_umem) {
		ice_xsk_clean_xdp_ring(tx_ring);
		goto tx_skip_free;
	}

	/* ring already cleared, nothing to do */
	if (!tx_ring->tx_buf)
		return;

	/* Free all the Tx ring sk_buffs */
	for (i = 0; i < tx_ring->count; i++)
		ice_unmap_and_free_tx_buf(tx_ring, &tx_ring->tx_buf[i]);

tx_skip_free:
	memset(tx_ring->tx_buf, 0, sizeof(*tx_ring->tx_buf) * tx_ring->count);

	/* Zero out the descriptor ring */
	memset(tx_ring->desc, 0, tx_ring->size);

	tx_ring->next_to_use = 0;
	tx_ring->next_to_clean = 0;

	if (!tx_ring->netdev)
		return;

	/* cleanup Tx queue statistics */
	netdev_tx_reset_queue(txring_txq(tx_ring));
}

/**
 * ice_free_tx_ring - Free Tx resources per queue
 * @tx_ring: Tx descriptor ring for a specific queue
 *
 * Free all transmit software resources
 */
void ice_free_tx_ring(struct ice_ring *tx_ring)
{
	ice_clean_tx_ring(tx_ring);
	devm_kfree(tx_ring->dev, tx_ring->tx_buf);
	tx_ring->tx_buf = NULL;

	if (tx_ring->desc) {
		dmam_free_coherent(tx_ring->dev, tx_ring->size,
				   tx_ring->desc, tx_ring->dma);
		tx_ring->desc = NULL;
	}
}

/**
 * ice_clean_tx_irq - Reclaim resources after transmit completes
 * @tx_ring: Tx ring to clean
 * @napi_budget: Used to determine if we are in netpoll
 *
 * Returns true if there's any budget left (e.g. the clean is finished)
 */
static bool ice_clean_tx_irq(struct ice_ring *tx_ring, int napi_budget)
{
	unsigned int total_bytes = 0, total_pkts = 0;
	unsigned int budget = ICE_DFLT_IRQ_WORK;
	struct ice_vsi *vsi = tx_ring->vsi;
	s16 i = tx_ring->next_to_clean;
	struct ice_tx_desc *tx_desc;
	struct ice_tx_buf *tx_buf;

	tx_buf = &tx_ring->tx_buf[i];
	tx_desc = ICE_TX_DESC(tx_ring, i);
	i -= tx_ring->count;

	prefetch(&vsi->state);

	do {
		struct ice_tx_desc *eop_desc = tx_buf->next_to_watch;

		/* if next_to_watch is not set then there is no work pending */
		if (!eop_desc)
			break;

		smp_rmb();	/* prevent any other reads prior to eop_desc */

		/* if the descriptor isn't done, no work yet to do */
		if (!(eop_desc->cmd_type_offset_bsz &
		      cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE)))
			break;

		/* clear next_to_watch to prevent false hangs */
		tx_buf->next_to_watch = NULL;

		/* update the statistics for this packet */
		total_bytes += tx_buf->bytecount;
		total_pkts += tx_buf->gso_segs;

		if (ice_ring_is_xdp(tx_ring))
			page_frag_free(tx_buf->raw_buf);
		else
			/* free the skb */
			napi_consume_skb(tx_buf->skb, napi_budget);

		/* unmap skb header data */
		dma_unmap_single(tx_ring->dev,
				 dma_unmap_addr(tx_buf, dma),
				 dma_unmap_len(tx_buf, len),
				 DMA_TO_DEVICE);

		/* clear tx_buf data */
		tx_buf->skb = NULL;
		dma_unmap_len_set(tx_buf, len, 0);

		/* unmap remaining buffers */
		while (tx_desc != eop_desc) {
			tx_buf++;
			tx_desc++;
			i++;
			if (unlikely(!i)) {
				i -= tx_ring->count;
				tx_buf = tx_ring->tx_buf;
				tx_desc = ICE_TX_DESC(tx_ring, 0);
			}

			/* unmap any remaining paged data */
			if (dma_unmap_len(tx_buf, len)) {
				dma_unmap_page(tx_ring->dev,
					       dma_unmap_addr(tx_buf, dma),
					       dma_unmap_len(tx_buf, len),
					       DMA_TO_DEVICE);
				dma_unmap_len_set(tx_buf, len, 0);
			}
		}

		/* move us one more past the eop_desc for start of next pkt */
		tx_buf++;
		tx_desc++;
		i++;
		if (unlikely(!i)) {
			i -= tx_ring->count;
			tx_buf = tx_ring->tx_buf;
			tx_desc = ICE_TX_DESC(tx_ring, 0);
		}

		prefetch(tx_desc);

		/* update budget accounting */
		budget--;
	} while (likely(budget));

	i += tx_ring->count;
	tx_ring->next_to_clean = i;

	ice_update_tx_ring_stats(tx_ring, total_pkts, total_bytes);

	if (ice_ring_is_xdp(tx_ring))
		return !!budget;

	netdev_tx_completed_queue(txring_txq(tx_ring), total_pkts,
				  total_bytes);

#define TX_WAKE_THRESHOLD ((s16)(DESC_NEEDED * 2))
	if (unlikely(total_pkts && netif_carrier_ok(tx_ring->netdev) &&
		     (ICE_DESC_UNUSED(tx_ring) >= TX_WAKE_THRESHOLD))) {
		/* Make sure that anybody stopping the queue after this
		 * sees the new next_to_clean.
		 */
		smp_mb();
		if (__netif_subqueue_stopped(tx_ring->netdev,
					     tx_ring->q_index) &&
		    !test_bit(__ICE_DOWN, vsi->state)) {
			netif_wake_subqueue(tx_ring->netdev,
					    tx_ring->q_index);
			++tx_ring->tx_stats.restart_q;
		}
	}

	return !!budget;
}

/**
 * ice_setup_tx_ring - Allocate the Tx descriptors
 * @tx_ring: the Tx ring to set up
 *
 * Return 0 on success, negative on error
 */
int ice_setup_tx_ring(struct ice_ring *tx_ring)
{
	struct device *dev = tx_ring->dev;

	if (!dev)
		return -ENOMEM;

	/* warn if we are about to overwrite the pointer */
	WARN_ON(tx_ring->tx_buf);
	tx_ring->tx_buf =
		devm_kzalloc(dev, sizeof(*tx_ring->tx_buf) * tx_ring->count,
			     GFP_KERNEL);
	if (!tx_ring->tx_buf)
		return -ENOMEM;

	/* round up to nearest page */
	tx_ring->size = ALIGN(tx_ring->count * sizeof(struct ice_tx_desc),
			      PAGE_SIZE);
	tx_ring->desc = dmam_alloc_coherent(dev, tx_ring->size, &tx_ring->dma,
					    GFP_KERNEL);
	if (!tx_ring->desc) {
		dev_err(dev, "Unable to allocate memory for the Tx descriptor ring, size=%d\n",
			tx_ring->size);
		goto err;
	}

	tx_ring->next_to_use = 0;
	tx_ring->next_to_clean = 0;
	tx_ring->tx_stats.prev_pkt = -1;
	return 0;

err:
	devm_kfree(dev, tx_ring->tx_buf);
	tx_ring->tx_buf = NULL;
	return -ENOMEM;
}

/**
 * ice_clean_rx_ring - Free Rx buffers
 * @rx_ring: ring to be cleaned
 */
void ice_clean_rx_ring(struct ice_ring *rx_ring)
{
	struct device *dev = rx_ring->dev;
	u16 i;

	/* ring already cleared, nothing to do */
	if (!rx_ring->rx_buf)
		return;

	if (rx_ring->xsk_umem) {
		ice_xsk_clean_rx_ring(rx_ring);
		goto rx_skip_free;
	}

	/* Free all the Rx ring sk_buffs */
	for (i = 0; i < rx_ring->count; i++) {
		struct ice_rx_buf *rx_buf = &rx_ring->rx_buf[i];

		if (rx_buf->skb) {
			dev_kfree_skb(rx_buf->skb);
			rx_buf->skb = NULL;
		}
		if (!rx_buf->page)
			continue;

		/* Invalidate cache lines that may have been written to by
		 * device so that we avoid corrupting memory.
		 */
		dma_sync_single_range_for_cpu(dev, rx_buf->dma,
					      rx_buf->page_offset,
					      rx_ring->rx_buf_len,
					      DMA_FROM_DEVICE);

		/* free resources associated with mapping */
		dma_unmap_page_attrs(dev, rx_buf->dma, ice_rx_pg_size(rx_ring),
				     DMA_FROM_DEVICE, ICE_RX_DMA_ATTR);
		__page_frag_cache_drain(rx_buf->page, rx_buf->pagecnt_bias);

		rx_buf->page = NULL;
		rx_buf->page_offset = 0;
	}

rx_skip_free:
	memset(rx_ring->rx_buf, 0, sizeof(*rx_ring->rx_buf) * rx_ring->count);

	/* Zero out the descriptor ring */
	memset(rx_ring->desc, 0, rx_ring->size);

	rx_ring->next_to_alloc = 0;
	rx_ring->next_to_clean = 0;
	rx_ring->next_to_use = 0;
}

/**
 * ice_free_rx_ring - Free Rx resources
 * @rx_ring: ring to clean the resources from
 *
 * Free all receive software resources
 */
void ice_free_rx_ring(struct ice_ring *rx_ring)
{
	ice_clean_rx_ring(rx_ring);
	if (rx_ring->vsi->type == ICE_VSI_PF)
		if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
			xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
	rx_ring->xdp_prog = NULL;
	devm_kfree(rx_ring->dev, rx_ring->rx_buf);
	rx_ring->rx_buf = NULL;

	if (rx_ring->desc) {
		dmam_free_coherent(rx_ring->dev, rx_ring->size,
				   rx_ring->desc, rx_ring->dma);
		rx_ring->desc = NULL;
	}
}

/**
 * ice_setup_rx_ring - Allocate the Rx descriptors
 * @rx_ring: the Rx ring to set up
 *
 * Return 0 on success, negative on error
 */
int ice_setup_rx_ring(struct ice_ring *rx_ring)
{
	struct device *dev = rx_ring->dev;

	if (!dev)
		return -ENOMEM;

	/* warn if we are about to overwrite the pointer */
	WARN_ON(rx_ring->rx_buf);
	rx_ring->rx_buf =
		devm_kzalloc(dev, sizeof(*rx_ring->rx_buf) * rx_ring->count,
			     GFP_KERNEL);
	if (!rx_ring->rx_buf)
		return -ENOMEM;

	/* round up to nearest page */
	rx_ring->size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc),
			      PAGE_SIZE);
	rx_ring->desc = dmam_alloc_coherent(dev, rx_ring->size, &rx_ring->dma,
					    GFP_KERNEL);
	if (!rx_ring->desc) {
		dev_err(dev, "Unable to allocate memory for the Rx descriptor ring, size=%d\n",
			rx_ring->size);
		goto err;
	}

	rx_ring->next_to_use = 0;
	rx_ring->next_to_clean = 0;

	if (ice_is_xdp_ena_vsi(rx_ring->vsi))
		WRITE_ONCE(rx_ring->xdp_prog, rx_ring->vsi->xdp_prog);

	if (rx_ring->vsi->type == ICE_VSI_PF &&
	    !xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
		if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev,
				     rx_ring->q_index))
			goto err;
	return 0;

err:
	devm_kfree(dev, rx_ring->rx_buf);
	rx_ring->rx_buf = NULL;
	return -ENOMEM;
}

/**
 * ice_rx_offset - Return expected offset into page to access data
 * @rx_ring: Ring we are requesting offset of
 *
 * Returns the offset value for ring into the data buffer.
 */
static unsigned int ice_rx_offset(struct ice_ring *rx_ring)
{
	if (ice_ring_uses_build_skb(rx_ring))
		return ICE_SKB_PAD;
	else if (ice_is_xdp_ena_vsi(rx_ring->vsi))
		return XDP_PACKET_HEADROOM;

	return 0;
}

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

	act = bpf_prog_run_xdp(xdp_prog, xdp);
	switch (act) {
	case XDP_PASS:
		break;
	case XDP_TX:
		xdp_ring = rx_ring->vsi->xdp_rings[smp_processor_id()];
		result = ice_xmit_xdp_buff(xdp, xdp_ring);
		break;
	case XDP_REDIRECT:
		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
		result = !err ? ICE_XDP_REDIR : ICE_XDP_CONSUMED;
		break;
	default:
		bpf_warn_invalid_xdp_action(act);
		/* fallthrough -- not supported action */
	case XDP_ABORTED:
		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
		/* fallthrough -- handle aborts by dropping frame */
	case XDP_DROP:
		result = ICE_XDP_CONSUMED;
		break;
	}

	return result;
}

/**
 * ice_xdp_xmit - submit packets to XDP ring for transmission
 * @dev: netdev
 * @n: number of XDP frames to be transmitted
 * @frames: XDP frames to be transmitted
 * @flags: transmit flags
 *
 * Returns number of frames successfully sent. Frames that fail are
 * free'ed via XDP return API.
 * For error cases, a negative errno code is returned and no-frames
 * are transmitted (caller must handle freeing frames).
 */
int
ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
	     u32 flags)
{
	struct ice_netdev_priv *np = netdev_priv(dev);
	unsigned int queue_index = smp_processor_id();
	struct ice_vsi *vsi = np->vsi;
	struct ice_ring *xdp_ring;
	int drops = 0, i;

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

	if (!ice_is_xdp_ena_vsi(vsi) || queue_index >= vsi->num_xdp_txq)
		return -ENXIO;

	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
		return -EINVAL;

	xdp_ring = vsi->xdp_rings[queue_index];
	for (i = 0; i < n; i++) {
		struct xdp_frame *xdpf = frames[i];
		int err;

		err = ice_xmit_xdp_ring(xdpf->data, xdpf->len, xdp_ring);
		if (err != ICE_XDP_TX) {
			xdp_return_frame_rx_napi(xdpf);
			drops++;
		}
	}

	if (unlikely(flags & XDP_XMIT_FLUSH))
		ice_xdp_ring_update_tail(xdp_ring);

	return n - drops;
}

/**
 * ice_alloc_mapped_page - recycle or make a new page
 * @rx_ring: ring to use
 * @bi: rx_buf struct to modify
 *
 * Returns true if the page was successfully allocated or
 * reused.
 */
static bool
ice_alloc_mapped_page(struct ice_ring *rx_ring, struct ice_rx_buf *bi)
{
	struct page *page = bi->page;
	dma_addr_t dma;

	/* since we are recycling buffers we should seldom need to alloc */
	if (likely(page)) {
		rx_ring->rx_stats.page_reuse_count++;
		return true;
	}

	/* alloc new page for storage */
	page = dev_alloc_pages(ice_rx_pg_order(rx_ring));
	if (unlikely(!page)) {
		rx_ring->rx_stats.alloc_page_failed++;
		return false;
	}

	/* map page for use */
	dma = dma_map_page_attrs(rx_ring->dev, page, 0, ice_rx_pg_size(rx_ring),
				 DMA_FROM_DEVICE, ICE_RX_DMA_ATTR);

	/* if mapping failed free memory back to system since
	 * there isn't much point in holding memory we can't use
	 */
	if (dma_mapping_error(rx_ring->dev, dma)) {
		__free_pages(page, ice_rx_pg_order(rx_ring));
		rx_ring->rx_stats.alloc_page_failed++;
		return false;
	}

	bi->dma = dma;
	bi->page = page;
	bi->page_offset = ice_rx_offset(rx_ring);
	page_ref_add(page, USHRT_MAX - 1);
	bi->pagecnt_bias = USHRT_MAX;

	return true;
}

/**
 * ice_alloc_rx_bufs - Replace used receive buffers
 * @rx_ring: ring to place buffers on
 * @cleaned_count: number of buffers to replace
 *
 * Returns false if all allocations were successful, true if any fail. Returning
 * true signals to the caller that we didn't replace cleaned_count buffers and
 * there is more work to do.
 *
 * First, try to clean "cleaned_count" Rx buffers. Then refill the cleaned Rx
 * buffers. Then bump tail at most one time. Grouping like this lets us avoid
 * multiple tail writes per call.
 */
bool ice_alloc_rx_bufs(struct ice_ring *rx_ring, u16 cleaned_count)
{
	union ice_32b_rx_flex_desc *rx_desc;
	u16 ntu = rx_ring->next_to_use;
	struct ice_rx_buf *bi;

	/* do nothing if no valid netdev defined */
	if (!rx_ring->netdev || !cleaned_count)
		return false;

	/* get the Rx descriptor and buffer based on next_to_use */
	rx_desc = ICE_RX_DESC(rx_ring, ntu);
	bi = &rx_ring->rx_buf[ntu];

	do {
		/* if we fail here, we have work remaining */
		if (!ice_alloc_mapped_page(rx_ring, bi))
			break;

		/* sync the buffer for use by the device */
		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
						 bi->page_offset,
						 rx_ring->rx_buf_len,
						 DMA_FROM_DEVICE);

		/* Refresh the desc even if buffer_addrs didn't change
		 * because each write-back erases this info.
		 */
		rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset);

		rx_desc++;
		bi++;
		ntu++;
		if (unlikely(ntu == rx_ring->count)) {
			rx_desc = ICE_RX_DESC(rx_ring, 0);
			bi = rx_ring->rx_buf;
			ntu = 0;
		}

		/* clear the status bits for the next_to_use descriptor */
		rx_desc->wb.status_error0 = 0;

		cleaned_count--;
	} while (cleaned_count);

	if (rx_ring->next_to_use != ntu)
		ice_release_rx_desc(rx_ring, ntu);

	return !!cleaned_count;
}

/**
 * ice_page_is_reserved - check if reuse is possible
 * @page: page struct to check
 */
static bool ice_page_is_reserved(struct page *page)
{
	return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page);
}

/**
 * ice_rx_buf_adjust_pg_offset - Prepare Rx buffer for reuse
 * @rx_buf: Rx buffer to adjust
 * @size: Size of adjustment
 *
 * Update the offset within page so that Rx buf will be ready to be reused.
 * For systems with PAGE_SIZE < 8192 this function will flip the page offset
 * so the second half of page assigned to Rx buffer will be used, otherwise
 * the offset is moved by the @size bytes
 */
static void
ice_rx_buf_adjust_pg_offset(struct ice_rx_buf *rx_buf, unsigned int size)
{
#if (PAGE_SIZE < 8192)
	/* flip page offset to other buffer */
	rx_buf->page_offset ^= size;
#else
	/* move offset up to the next cache line */
	rx_buf->page_offset += size;
#endif
}

/**
 * ice_can_reuse_rx_page - Determine if page can be reused for another Rx
 * @rx_buf: buffer containing the page
 *
 * If page is reusable, we have a green light for calling ice_reuse_rx_page,
 * which will assign the current buffer to the buffer that next_to_alloc is
 * pointing to; otherwise, the DMA mapping needs to be destroyed and
 * page freed
 */
static bool ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf)
{
	unsigned int pagecnt_bias = rx_buf->pagecnt_bias;
	struct page *page = rx_buf->page;

	/* avoid re-using remote pages */
	if (unlikely(ice_page_is_reserved(page)))
		return false;

#if (PAGE_SIZE < 8192)
	/* if we are only owner of page we can reuse it */
	if (unlikely((page_count(page) - pagecnt_bias) > 1))
		return false;
#else
#define ICE_LAST_OFFSET \
	(SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_2048)
	if (rx_buf->page_offset > ICE_LAST_OFFSET)
		return false;
#endif /* PAGE_SIZE < 8192) */

	/* If we have drained the page fragment pool we need to update
	 * the pagecnt_bias and page count so that we fully restock the
	 * number of references the driver holds.
	 */
	if (unlikely(pagecnt_bias == 1)) {
		page_ref_add(page, USHRT_MAX - 1);
		rx_buf->pagecnt_bias = USHRT_MAX;
	}

	return true;
}

/**
 * ice_add_rx_frag - Add contents of Rx buffer to sk_buff as a frag
 * @rx_ring: Rx descriptor ring to transact packets on
 * @rx_buf: buffer containing page to add
 * @skb: sk_buff to place the data into
 * @size: packet length from rx_desc
 *
 * This function will add the data contained in rx_buf->page to the skb.
 * It will just attach the page as a frag to the skb.
 * The function will then update the page offset.
 */
static void
ice_add_rx_frag(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf,
		struct sk_buff *skb, unsigned int size)
{
#if (PAGE_SIZE >= 8192)
	unsigned int truesize = SKB_DATA_ALIGN(size + ice_rx_offset(rx_ring));
#else
	unsigned int truesize = ice_rx_pg_size(rx_ring) / 2;
#endif

	if (!size)
		return;
	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buf->page,
			rx_buf->page_offset, size, truesize);

	/* page is being used so we must update the page offset */
	ice_rx_buf_adjust_pg_offset(rx_buf, truesize);
}

/**
 * ice_reuse_rx_page - page flip buffer and store it back on the ring
 * @rx_ring: Rx descriptor ring to store buffers on
 * @old_buf: donor buffer to have page reused
 *
 * Synchronizes page for reuse by the adapter
 */
static void
ice_reuse_rx_page(struct ice_ring *rx_ring, struct ice_rx_buf *old_buf)
{
	u16 nta = rx_ring->next_to_alloc;
	struct ice_rx_buf *new_buf;

	new_buf = &rx_ring->rx_buf[nta];

	/* update, and store next to alloc */
	nta++;
	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;

	/* Transfer page from old buffer to new buffer.
	 * Move each member individually to avoid possible store
	 * forwarding stalls and unnecessary copy of skb.
	 */
	new_buf->dma = old_buf->dma;
	new_buf->page = old_buf->page;
	new_buf->page_offset = old_buf->page_offset;
	new_buf->pagecnt_bias = old_buf->pagecnt_bias;
}

/**
 * ice_get_rx_buf - Fetch Rx buffer and synchronize data for use
 * @rx_ring: Rx descriptor ring to transact packets on
 * @skb: skb to be used
 * @size: size of buffer to add to skb
 *
 * This function will pull an Rx buffer from the ring and synchronize it
 * for use by the CPU.
 */
static struct ice_rx_buf *
ice_get_rx_buf(struct ice_ring *rx_ring, struct sk_buff **skb,
	       const unsigned int size)
{
	struct ice_rx_buf *rx_buf;

	rx_buf = &rx_ring->rx_buf[rx_ring->next_to_clean];
	prefetchw(rx_buf->page);
	*skb = rx_buf->skb;

	if (!size)
		return rx_buf;
	/* we are reusing so sync this buffer for CPU use */
	dma_sync_single_range_for_cpu(rx_ring->dev, rx_buf->dma,
				      rx_buf->page_offset, size,
				      DMA_FROM_DEVICE);

	/* We have pulled a buffer for use, so decrement pagecnt_bias */
	rx_buf->pagecnt_bias--;

	return rx_buf;
}

/**
 * ice_build_skb - Build skb around an existing buffer
 * @rx_ring: Rx descriptor ring to transact packets on
 * @rx_buf: Rx buffer to pull data from
 * @xdp: xdp_buff pointing to the data
 *
 * This function builds an skb around an existing Rx buffer, taking care
 * to set up the skb correctly and avoid any memcpy overhead.
 */
static struct sk_buff *
ice_build_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf,
	      struct xdp_buff *xdp)
{
	unsigned int metasize = xdp->data - xdp->data_meta;
#if (PAGE_SIZE < 8192)
	unsigned int truesize = ice_rx_pg_size(rx_ring) / 2;
#else
	unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
				SKB_DATA_ALIGN(xdp->data_end -
					       xdp->data_hard_start);
#endif
	struct sk_buff *skb;

	/* Prefetch first cache line of first page. If xdp->data_meta
	 * is unused, this points exactly as xdp->data, otherwise we
	 * likely have a consumer accessing first few bytes of meta
	 * data, and then actual data.
	 */
	prefetch(xdp->data_meta);
#if L1_CACHE_BYTES < 128
	prefetch((void *)(xdp->data + L1_CACHE_BYTES));
#endif
	/* build an skb around the page buffer */
	skb = build_skb(xdp->data_hard_start, truesize);
	if (unlikely(!skb))
		return NULL;

	/* must to record Rx queue, otherwise OS features such as
	 * symmetric queue won't work
	 */
	skb_record_rx_queue(skb, rx_ring->q_index);

	/* update pointers within the skb to store the data */
	skb_reserve(skb, xdp->data - xdp->data_hard_start);
	__skb_put(skb, xdp->data_end - xdp->data);
	if (metasize)
		skb_metadata_set(skb, metasize);

	/* buffer is used by skb, update page_offset */
	ice_rx_buf_adjust_pg_offset(rx_buf, truesize);

	return skb;
}

/**
 * ice_construct_skb - Allocate skb and populate it
 * @rx_ring: Rx descriptor ring to transact packets on
 * @rx_buf: Rx buffer to pull data from
 * @xdp: xdp_buff pointing to the data
 *
 * This function allocates an skb. It then populates it with the page
 * data from the current receive descriptor, taking care to set up the
 * skb correctly.
 */
static struct sk_buff *
ice_construct_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf,
		  struct xdp_buff *xdp)
{
	unsigned int size = xdp->data_end - xdp->data;
	unsigned int headlen;
	struct sk_buff *skb;

	/* prefetch first cache line of first page */
	prefetch(xdp->data);
#if L1_CACHE_BYTES < 128
	prefetch((void *)(xdp->data + L1_CACHE_BYTES));
#endif /* L1_CACHE_BYTES */

	/* allocate a skb to store the frags */
	skb = __napi_alloc_skb(&rx_ring->q_vector->napi, ICE_RX_HDR_SIZE,
			       GFP_ATOMIC | __GFP_NOWARN);
	if (unlikely(!skb))
		return NULL;

	skb_record_rx_queue(skb, rx_ring->q_index);
	/* Determine available headroom for copy */
	headlen = size;
	if (headlen > ICE_RX_HDR_SIZE)
		headlen = eth_get_headlen(skb->dev, xdp->data, ICE_RX_HDR_SIZE);

	/* align pull length to size of long to optimize memcpy performance */
	memcpy(__skb_put(skb, headlen), xdp->data, ALIGN(headlen,
							 sizeof(long)));

	/* if we exhaust the linear part then add what is left as a frag */
	size -= headlen;
	if (size) {
#if (PAGE_SIZE >= 8192)
		unsigned int truesize = SKB_DATA_ALIGN(size);
#else
		unsigned int truesize = ice_rx_pg_size(rx_ring) / 2;
#endif
		skb_add_rx_frag(skb, 0, rx_buf->page,
				rx_buf->page_offset + headlen, size, truesize);
		/* buffer is used by skb, update page_offset */
		ice_rx_buf_adjust_pg_offset(rx_buf, truesize);
	} else {
		/* buffer is unused, reset bias back to rx_buf; data was copied
		 * onto skb's linear part so there's no need for adjusting
		 * page offset and we can reuse this buffer as-is
		 */
		rx_buf->pagecnt_bias++;
	}

	return skb;
}

/**
 * ice_put_rx_buf - Clean up used buffer and either recycle or free
 * @rx_ring: Rx descriptor ring to transact packets on
 * @rx_buf: Rx buffer to pull data from
 *
 * This function will update next_to_clean and then clean up the contents
 * of the rx_buf. It will either recycle the buffer or unmap it and free
 * the associated resources.
 */
static void ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf)
{
	u32 ntc = rx_ring->next_to_clean + 1;

	/* fetch, update, and store next to clean */
	ntc = (ntc < rx_ring->count) ? ntc : 0;
	rx_ring->next_to_clean = ntc;

	if (!rx_buf)
		return;

	if (ice_can_reuse_rx_page(rx_buf)) {
		/* hand second half of page back to the ring */
		ice_reuse_rx_page(rx_ring, rx_buf);
		rx_ring->rx_stats.page_reuse_count++;
	} else {
		/* we are not reusing the buffer so unmap it */
		dma_unmap_page_attrs(rx_ring->dev, rx_buf->dma,
				     ice_rx_pg_size(rx_ring), DMA_FROM_DEVICE,
				     ICE_RX_DMA_ATTR);
		__page_frag_cache_drain(rx_buf->page, rx_buf->pagecnt_bias);
	}

	/* clear contents of buffer_info */
	rx_buf->page = NULL;
	rx_buf->skb = NULL;
}

/**
 * ice_is_non_eop - process handling of non-EOP buffers
 * @rx_ring: Rx ring being processed
 * @rx_desc: Rx descriptor for current buffer
 * @skb: Current socket buffer containing buffer in progress
 *
 * If the buffer is an EOP buffer, this function exits returning false,
 * otherwise return true indicating that this is in fact a non-EOP buffer.
 */
static bool
ice_is_non_eop(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc,
	       struct sk_buff *skb)
{
	/* if we are the last buffer then there is nothing else to do */
#define ICE_RXD_EOF BIT(ICE_RX_FLEX_DESC_STATUS0_EOF_S)
	if (likely(ice_test_staterr(rx_desc, ICE_RXD_EOF)))
		return false;

	/* place skb in next buffer to be received */
	rx_ring->rx_buf[rx_ring->next_to_clean].skb = skb;
	rx_ring->rx_stats.non_eop_descs++;

	return true;
}

/**
 * ice_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
 * @rx_ring: Rx descriptor ring to transact packets on
 * @budget: Total limit on number of packets to process
 *
 * This function provides a "bounce buffer" approach to Rx interrupt
 * processing. The advantage to this is that on systems that have
 * expensive overhead for IOMMU access this provides a means of avoiding
 * it by maintaining the mapping of the page to the system.
 *
 * Returns amount of work completed
 */
static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
{
	unsigned int total_rx_bytes = 0, total_rx_pkts = 0;
	u16 cleaned_count = ICE_DESC_UNUSED(rx_ring);
	unsigned int xdp_res, xdp_xmit = 0;
	struct bpf_prog *xdp_prog = NULL;
	struct xdp_buff xdp;
	bool failure;

	xdp.rxq = &rx_ring->xdp_rxq;

	/* start the loop to process Rx packets bounded by 'budget' */
	while (likely(total_rx_pkts < (unsigned int)budget)) {
		union ice_32b_rx_flex_desc *rx_desc;
		struct ice_rx_buf *rx_buf;
		struct sk_buff *skb;
		unsigned int size;
		u16 stat_err_bits;
		u16 vlan_tag = 0;
		u8 rx_ptype;

		/* get the Rx desc from Rx ring based on 'next_to_clean' */
		rx_desc = ICE_RX_DESC(rx_ring, rx_ring->next_to_clean);

		/* status_error_len will always be zero for unused descriptors
		 * because it's cleared in cleanup, and overlaps with hdr_addr
		 * which is always zero because packet split isn't used, if the
		 * hardware wrote DD then it will be non-zero
		 */
		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S);
		if (!ice_test_staterr(rx_desc, stat_err_bits))
			break;

		/* This memory barrier is needed to keep us from reading
		 * any other fields out of the rx_desc until we know the
		 * DD bit is set.
		 */
		dma_rmb();

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

		/* retrieve a buffer from the ring */
		rx_buf = ice_get_rx_buf(rx_ring, &skb, size);

		if (!size) {
			xdp.data = NULL;
			xdp.data_end = NULL;
			xdp.data_hard_start = NULL;
			xdp.data_meta = NULL;
			goto construct_skb;
		}

		xdp.data = page_address(rx_buf->page) + rx_buf->page_offset;
		xdp.data_hard_start = xdp.data - ice_rx_offset(rx_ring);
		xdp.data_meta = xdp.data;
		xdp.data_end = xdp.data + size;

		rcu_read_lock();
		xdp_prog = READ_ONCE(rx_ring->xdp_prog);
		if (!xdp_prog) {
			rcu_read_unlock();
			goto construct_skb;
		}

		xdp_res = ice_run_xdp(rx_ring, &xdp, xdp_prog);
		rcu_read_unlock();
		if (!xdp_res)
			goto construct_skb;
		if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR)) {
			unsigned int truesize;

#if (PAGE_SIZE < 8192)
			truesize = ice_rx_pg_size(rx_ring) / 2;
#else
			truesize = SKB_DATA_ALIGN(ice_rx_offset(rx_ring) +
						  size);
#endif
			xdp_xmit |= xdp_res;
			ice_rx_buf_adjust_pg_offset(rx_buf, truesize);
		} else {
			rx_buf->pagecnt_bias++;
		}
		total_rx_bytes += size;
		total_rx_pkts++;

		cleaned_count++;
		ice_put_rx_buf(rx_ring, rx_buf);
		continue;
construct_skb:
		if (skb)
			ice_add_rx_frag(rx_ring, rx_buf, skb, size);
		else if (ice_ring_uses_build_skb(rx_ring))
			skb = ice_build_skb(rx_ring, rx_buf, &xdp);
		else
			skb = ice_construct_skb(rx_ring, rx_buf, &xdp);

		/* exit if we failed to retrieve a buffer */
		if (!skb) {
			rx_ring->rx_stats.alloc_buf_failed++;
			if (rx_buf)
				rx_buf->pagecnt_bias++;
			break;
		}

		ice_put_rx_buf(rx_ring, rx_buf);
		cleaned_count++;

		/* skip if it is NOP desc */
		if (ice_is_non_eop(rx_ring, rx_desc, skb))
			continue;

		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S);
		if (unlikely(ice_test_staterr(rx_desc, stat_err_bits))) {
			dev_kfree_skb_any(skb);
			continue;
		}

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

		/* pad the skb if needed, to make a valid ethernet frame */
		if (eth_skb_pad(skb)) {
			skb = NULL;
			continue;
		}

		/* probably a little skewed due to removing CRC */
		total_rx_bytes += skb->len;

		/* populate checksum, VLAN, and protocol */
		rx_ptype = le16_to_cpu(rx_desc->wb.ptype_flex_flags0) &
			ICE_RX_FLEX_DESC_PTYPE_M;

		ice_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);

		/* send completed skb up the stack */
		ice_receive_skb(rx_ring, skb, vlan_tag);

		/* update budget accounting */
		total_rx_pkts++;
	}

	/* return up to cleaned_count buffers to hardware */
	failure = ice_alloc_rx_bufs(rx_ring, cleaned_count);

	if (xdp_prog)
		ice_finalize_xdp_rx(rx_ring, xdp_xmit);

	ice_update_rx_ring_stats(rx_ring, total_rx_pkts, total_rx_bytes);

	/* guarantee a trip back through this routine if there was a failure */
	return failure ? budget : (int)total_rx_pkts;
}

/**
 * ice_adjust_itr_by_size_and_speed - Adjust ITR based on current traffic
 * @port_info: port_info structure containing the current link speed
 * @avg_pkt_size: average size of Tx or Rx packets based on clean routine
 * @itr: ITR value to update
 *
 * Calculate how big of an increment should be applied to the ITR value passed
 * in based on wmem_default, SKB overhead, Ethernet overhead, and the current
 * link speed.
 *
 * The following is a calculation derived from:
 *  wmem_default / (size + overhead) = desired_pkts_per_int
 *  rate / bits_per_byte / (size + Ethernet overhead) = pkt_rate
 *  (desired_pkt_rate / pkt_rate) * usecs_per_sec = ITR value
 *
 * Assuming wmem_default is 212992 and overhead is 640 bytes per
 * packet, (256 skb, 64 headroom, 320 shared info), we can reduce the
 * formula down to:
 *
 *	 wmem_default * bits_per_byte * usecs_per_sec   pkt_size + 24
 * ITR = -------------------------------------------- * --------------
 *			     rate			pkt_size + 640
 */
static unsigned int
ice_adjust_itr_by_size_and_speed(struct ice_port_info *port_info,
				 unsigned int avg_pkt_size,
				 unsigned int itr)
{
	switch (port_info->phy.link_info.link_speed) {
	case ICE_AQ_LINK_SPEED_100GB:
		itr += DIV_ROUND_UP(17 * (avg_pkt_size + 24),
				    avg_pkt_size + 640);
		break;
	case ICE_AQ_LINK_SPEED_50GB:
		itr += DIV_ROUND_UP(34 * (avg_pkt_size + 24),
				    avg_pkt_size + 640);
		break;
	case ICE_AQ_LINK_SPEED_40GB:
		itr += DIV_ROUND_UP(43 * (avg_pkt_size + 24),
				    avg_pkt_size + 640);
		break;
	case ICE_AQ_LINK_SPEED_25GB:
		itr += DIV_ROUND_UP(68 * (avg_pkt_size + 24),
				    avg_pkt_size + 640);
		break;
	case ICE_AQ_LINK_SPEED_20GB:
		itr += DIV_ROUND_UP(85 * (avg_pkt_size + 24),
				    avg_pkt_size + 640);
		break;
	case ICE_AQ_LINK_SPEED_10GB:
		/* fall through */
	default:
		itr += DIV_ROUND_UP(170 * (avg_pkt_size + 24),
				    avg_pkt_size + 640);
		break;
	}

	if ((itr & ICE_ITR_MASK) > ICE_ITR_ADAPTIVE_MAX_USECS) {
		itr &= ICE_ITR_ADAPTIVE_LATENCY;
		itr += ICE_ITR_ADAPTIVE_MAX_USECS;
	}

	return itr;
}

/**
 * ice_update_itr - update the adaptive ITR value based on statistics
 * @q_vector: structure containing interrupt and ring information
 * @rc: structure containing ring performance data
 *
 * Stores a new ITR value based on packets and byte
 * counts during the last interrupt.  The advantage of per interrupt
 * computation is faster updates and more accurate ITR for the current
 * traffic pattern.  Constants in this function were computed
 * based on theoretical maximum wire speed and thresholds were set based
 * on testing data as well as attempting to minimize response time
 * while increasing bulk throughput.
 */
static void
ice_update_itr(struct ice_q_vector *q_vector, struct ice_ring_container *rc)
{
	unsigned long next_update = jiffies;
	unsigned int packets, bytes, itr;
	bool container_is_rx;

	if (!rc->ring || !ITR_IS_DYNAMIC(rc->itr_setting))
		return;

	/* If itr_countdown is set it means we programmed an ITR within
	 * the last 4 interrupt cycles. This has a side effect of us
	 * potentially firing an early interrupt. In order to work around
	 * this we need to throw out any data received for a few
	 * interrupts following the update.
	 */
	if (q_vector->itr_countdown) {
		itr = rc->target_itr;
		goto clear_counts;
	}

	container_is_rx = (&q_vector->rx == rc);
	/* For Rx we want to push the delay up and default to low latency.
	 * for Tx we want to pull the delay down and default to high latency.
	 */
	itr = container_is_rx ?
		ICE_ITR_ADAPTIVE_MIN_USECS | ICE_ITR_ADAPTIVE_LATENCY :
		ICE_ITR_ADAPTIVE_MAX_USECS | ICE_ITR_ADAPTIVE_LATENCY;

	/* If we didn't update within up to 1 - 2 jiffies we can assume
	 * that either packets are coming in so slow there hasn't been
	 * any work, or that there is so much work that NAPI is dealing
	 * with interrupt moderation and we don't need to do anything.
	 */
	if (time_after(next_update, rc->next_update))
		goto clear_counts;

	prefetch(q_vector->vsi->port_info);

	packets = rc->total_pkts;
	bytes = rc->total_bytes;

	if (container_is_rx) {
		/* If Rx there are 1 to 4 packets and bytes are less than
		 * 9000 assume insufficient data to use bulk rate limiting
		 * approach unless Tx is already in bulk rate limiting. We
		 * are likely latency driven.
		 */
		if (packets && packets < 4 && bytes < 9000 &&
		    (q_vector->tx.target_itr & ICE_ITR_ADAPTIVE_LATENCY)) {
			itr = ICE_ITR_ADAPTIVE_LATENCY;
			goto adjust_by_size_and_speed;
		}
	} else if (packets < 4) {
		/* If we have Tx and Rx ITR maxed and Tx ITR is running in
		 * bulk mode and we are receiving 4 or fewer packets just
		 * reset the ITR_ADAPTIVE_LATENCY bit for latency mode so
		 * that the Rx can relax.
		 */
		if (rc->target_itr == ICE_ITR_ADAPTIVE_MAX_USECS &&
		    (q_vector->rx.target_itr & ICE_ITR_MASK) ==
		    ICE_ITR_ADAPTIVE_MAX_USECS)
			goto clear_counts;
	} else if (packets > 32) {
		/* If we have processed over 32 packets in a single interrupt
		 * for Tx assume we need to switch over to "bulk" mode.
		 */
		rc->target_itr &= ~ICE_ITR_ADAPTIVE_LATENCY;
	}

	/* We have no packets to actually measure against. This means
	 * either one of the other queues on this vector is active or
	 * we are a Tx queue doing TSO with too high of an interrupt rate.
	 *
	 * Between 4 and 56 we can assume that our current interrupt delay
	 * is only slightly too low. As such we should increase it by a small
	 * fixed amount.
	 */
	if (packets < 56) {
		itr = rc->target_itr + ICE_ITR_ADAPTIVE_MIN_INC;
		if ((itr & ICE_ITR_MASK) > ICE_ITR_ADAPTIVE_MAX_USECS) {
			itr &= ICE_ITR_ADAPTIVE_LATENCY;
			itr += ICE_ITR_ADAPTIVE_MAX_USECS;
		}
		goto clear_counts;
	}

	if (packets <= 256) {
		itr = min(q_vector->tx.current_itr, q_vector->rx.current_itr);
		itr &= ICE_ITR_MASK;

		/* Between 56 and 112 is our "goldilocks" zone where we are
		 * working out "just right". Just report that our current
		 * ITR is good for us.
		 */
		if (packets <= 112)
			goto clear_counts;

		/* If packet count is 128 or greater we are likely looking
		 * at a slight overrun of the delay we want. Try halving
		 * our delay to see if that will cut the number of packets
		 * in half per interrupt.
		 */
		itr >>= 1;
		itr &= ICE_ITR_MASK;
		if (itr < ICE_ITR_ADAPTIVE_MIN_USECS)
			itr = ICE_ITR_ADAPTIVE_MIN_USECS;

		goto clear_counts;
	}

	/* The paths below assume we are dealing with a bulk ITR since
	 * number of packets is greater than 256. We are just going to have
	 * to compute a value and try to bring the count under control,
	 * though for smaller packet sizes there isn't much we can do as
	 * NAPI polling will likely be kicking in sooner rather than later.
	 */
	itr = ICE_ITR_ADAPTIVE_BULK;

adjust_by_size_and_speed:

	/* based on checks above packets cannot be 0 so division is safe */
	itr = ice_adjust_itr_by_size_and_speed(q_vector->vsi->port_info,
					       bytes / packets, itr);

clear_counts:
	/* write back value */
	rc->target_itr = itr;

	/* next update should occur within next jiffy */
	rc->next_update = next_update + 1;

	rc->total_bytes = 0;
	rc->total_pkts = 0;
}

/**
 * ice_buildreg_itr - build value for writing to the GLINT_DYN_CTL register
 * @itr_idx: interrupt throttling index
 * @itr: interrupt throttling value in usecs
 */
static u32 ice_buildreg_itr(u16 itr_idx, u16 itr)
{
	/* The ITR value is reported in microseconds, and the register value is
	 * recorded in 2 microsecond units. For this reason we only need to
	 * shift by the GLINT_DYN_CTL_INTERVAL_S - ICE_ITR_GRAN_S to apply this
	 * granularity as a shift instead of division. The mask makes sure the
	 * ITR value is never odd so we don't accidentally write into the field
	 * prior to the ITR field.
	 */
	itr &= ICE_ITR_MASK;

	return GLINT_DYN_CTL_INTENA_M | GLINT_DYN_CTL_CLEARPBA_M |
		(itr_idx << GLINT_DYN_CTL_ITR_INDX_S) |
		(itr << (GLINT_DYN_CTL_INTERVAL_S - ICE_ITR_GRAN_S));
}

/* The act of updating the ITR will cause it to immediately trigger. In order
 * to prevent this from throwing off adaptive update statistics we defer the
 * update so that it can only happen so often. So after either Tx or Rx are
 * updated we make the adaptive scheme wait until either the ITR completely
 * expires via the next_update expiration or we have been through at least
 * 3 interrupts.
 */
#define ITR_COUNTDOWN_START 3

/**
 * ice_update_ena_itr - Update ITR and re-enable MSIX interrupt
 * @q_vector: q_vector for which ITR is being updated and interrupt enabled
 */
static void ice_update_ena_itr(struct ice_q_vector *q_vector)
{
	struct ice_ring_container *tx = &q_vector->tx;
	struct ice_ring_container *rx = &q_vector->rx;
	struct ice_vsi *vsi = q_vector->vsi;
	u32 itr_val;

	/* when exiting WB_ON_ITR lets set a low ITR value and trigger
	 * interrupts to expire right away in case we have more work ready to go
	 * already
	 */
	if (q_vector->itr_countdown == ICE_IN_WB_ON_ITR_MODE) {
		itr_val = ice_buildreg_itr(rx->itr_idx, ICE_WB_ON_ITR_USECS);
		wr32(&vsi->back->hw, GLINT_DYN_CTL(q_vector->reg_idx), itr_val);
		/* set target back to last user set value */
		rx->target_itr = rx->itr_setting;
		/* set current to what we just wrote and dynamic if needed */
		rx->current_itr = ICE_WB_ON_ITR_USECS |
			(rx->itr_setting & ICE_ITR_DYNAMIC);
		/* allow normal interrupt flow to start */
		q_vector->itr_countdown = 0;
		return;
	}

	/* This will do nothing if dynamic updates are not enabled */
	ice_update_itr(q_vector, tx);
	ice_update_itr(q_vector, rx);

	/* This block of logic allows us to get away with only updating
	 * one ITR value with each interrupt. The idea is to perform a
	 * pseudo-lazy update with the following criteria.
	 *
	 * 1. Rx is given higher priority than Tx if both are in same state
	 * 2. If we must reduce an ITR that is given highest priority.
	 * 3. We then give priority to increasing ITR based on amount.
	 */
	if (rx->target_itr < rx->current_itr) {
		/* Rx ITR needs to be reduced, this is highest priority */
		itr_val = ice_buildreg_itr(rx->itr_idx, rx->target_itr);
		rx->current_itr = rx->target_itr;
		q_vector->itr_countdown = ITR_COUNTDOWN_START;
	} else if ((tx->target_itr < tx->current_itr) ||
		   ((rx->target_itr - rx->current_itr) <
		    (tx->target_itr - tx->current_itr))) {
		/* Tx ITR needs to be reduced, this is second priority
		 * Tx ITR needs to be increased more than Rx, fourth priority
		 */
		itr_val = ice_buildreg_itr(tx->itr_idx, tx->target_itr);
		tx->current_itr = tx->target_itr;
		q_vector->itr_countdown = ITR_COUNTDOWN_START;
	} else if (rx->current_itr != rx->target_itr) {
		/* Rx ITR needs to be increased, third priority */
		itr_val = ice_buildreg_itr(rx->itr_idx, rx->target_itr);
		rx->current_itr = rx->target_itr;
		q_vector->itr_countdown = ITR_COUNTDOWN_START;
	} else {
		/* Still have to re-enable the interrupts */
		itr_val = ice_buildreg_itr(ICE_ITR_NONE, 0);
		if (q_vector->itr_countdown)
			q_vector->itr_countdown--;
	}

	if (!test_bit(__ICE_DOWN, q_vector->vsi->state))
		wr32(&q_vector->vsi->back->hw,
		     GLINT_DYN_CTL(q_vector->reg_idx),
		     itr_val);
}

/**
 * ice_set_wb_on_itr - set WB_ON_ITR for this q_vector
 * @q_vector: q_vector to set WB_ON_ITR on
 *
 * We need to tell hardware to write-back completed descriptors even when
 * interrupts are disabled. Descriptors will be written back on cache line
 * boundaries without WB_ON_ITR enabled, but if we don't enable WB_ON_ITR
 * descriptors may not be written back if they don't fill a cache line until the
 * next interrupt.
 *
 * This sets the write-back frequency to 2 microseconds as that is the minimum
 * value that's not 0 due to ITR granularity. Also, set the INTENA_MSK bit to
 * make sure hardware knows we aren't meddling with the INTENA_M bit.
 */
static void ice_set_wb_on_itr(struct ice_q_vector *q_vector)
{
	struct ice_vsi *vsi = q_vector->vsi;

	/* already in WB_ON_ITR mode no need to change it */
	if (q_vector->itr_countdown == ICE_IN_WB_ON_ITR_MODE)
		return;

	if (q_vector->num_ring_rx)
		wr32(&vsi->back->hw, GLINT_DYN_CTL(q_vector->reg_idx),
		     ICE_GLINT_DYN_CTL_WB_ON_ITR(ICE_WB_ON_ITR_USECS,
						 ICE_RX_ITR));

	if (q_vector->num_ring_tx)
		wr32(&vsi->back->hw, GLINT_DYN_CTL(q_vector->reg_idx),
		     ICE_GLINT_DYN_CTL_WB_ON_ITR(ICE_WB_ON_ITR_USECS,
						 ICE_TX_ITR));

	q_vector->itr_countdown = ICE_IN_WB_ON_ITR_MODE;
}

/**
 * ice_napi_poll - NAPI polling Rx/Tx cleanup routine
 * @napi: napi struct with our devices info in it
 * @budget: amount of work driver is allowed to do this pass, in packets
 *
 * This function will clean all queues associated with a q_vector.
 *
 * Returns the amount of work done
 */
int ice_napi_poll(struct napi_struct *napi, int budget)
{
	struct ice_q_vector *q_vector =
				container_of(napi, struct ice_q_vector, napi);
	bool clean_complete = true;
	struct ice_ring *ring;
	int budget_per_ring;
	int work_done = 0;

	/* Since the actual Tx work is minimal, we can give the Tx a larger
	 * budget and be more aggressive about cleaning up the Tx descriptors.
	 */
	ice_for_each_ring(ring, q_vector->tx) {
		bool wd = ring->xsk_umem ?
			  ice_clean_tx_irq_zc(ring, budget) :
			  ice_clean_tx_irq(ring, budget);

		if (!wd)
			clean_complete = false;
	}

	/* Handle case where we are called by netpoll with a budget of 0 */
	if (unlikely(budget <= 0))
		return budget;

	/* normally we have 1 Rx ring per q_vector */
	if (unlikely(q_vector->num_ring_rx > 1))
		/* We attempt to distribute budget to each Rx queue fairly, but
		 * don't allow the budget to go below 1 because that would exit
		 * polling early.
		 */
		budget_per_ring = max(budget / q_vector->num_ring_rx, 1);
	else
		/* Max of 1 Rx ring in this q_vector so give it the budget */
		budget_per_ring = budget;

	ice_for_each_ring(ring, q_vector->rx) {
		int cleaned;

		/* A dedicated path for zero-copy allows making a single
		 * comparison in the irq context instead of many inside the
		 * ice_clean_rx_irq function and makes the codebase cleaner.
		 */
		cleaned = ring->xsk_umem ?
			  ice_clean_rx_irq_zc(ring, budget_per_ring) :
			  ice_clean_rx_irq(ring, budget_per_ring);
		work_done += cleaned;
		/* if we clean as many as budgeted, we must not be done */
		if (cleaned >= budget_per_ring)
			clean_complete = false;
	}

	/* If work not completed, return budget and polling will return */
	if (!clean_complete)
		return budget;

	/* Exit the polling mode, but don't re-enable interrupts if stack might
	 * poll us due to busy-polling
	 */
	if (likely(napi_complete_done(napi, work_done)))
		ice_update_ena_itr(q_vector);
	else
		ice_set_wb_on_itr(q_vector);

	return min_t(int, work_done, budget - 1);
}

/**
 * __ice_maybe_stop_tx - 2nd level check for Tx stop conditions
 * @tx_ring: the ring to be checked
 * @size: the size buffer we want to assure is available
 *
 * Returns -EBUSY if a stop is needed, else 0
 */
static int __ice_maybe_stop_tx(struct ice_ring *tx_ring, unsigned int size)
{
	netif_stop_subqueue(tx_ring->netdev, tx_ring->q_index);
	/* Memory barrier before checking head and tail */
	smp_mb();

	/* Check again in a case another CPU has just made room available. */
	if (likely(ICE_DESC_UNUSED(tx_ring) < size))
		return -EBUSY;

	/* A reprieve! - use start_subqueue because it doesn't call schedule */
	netif_start_subqueue(tx_ring->netdev, tx_ring->q_index);
	++tx_ring->tx_stats.restart_q;
	return 0;
}

/**
 * ice_maybe_stop_tx - 1st level check for Tx stop conditions
 * @tx_ring: the ring to be checked
 * @size:    the size buffer we want to assure is available
 *
 * Returns 0 if stop is not needed
 */
static int ice_maybe_stop_tx(struct ice_ring *tx_ring, unsigned int size)
{
	if (likely(ICE_DESC_UNUSED(tx_ring) >= size))
		return 0;

	return __ice_maybe_stop_tx(tx_ring, size);
}

/**
 * ice_tx_map - Build the Tx descriptor
 * @tx_ring: ring to send buffer on
 * @first: first buffer info buffer to use
 * @off: pointer to struct that holds offload parameters
 *
 * This function loops over the skb data pointed to by *first
 * and gets a physical address for each memory location and programs
 * it and the length into the transmit descriptor.
 */
static void
ice_tx_map(struct ice_ring *tx_ring, struct ice_tx_buf *first,
	   struct ice_tx_offload_params *off)
{
	u64 td_offset, td_tag, td_cmd;
	u16 i = tx_ring->next_to_use;
	skb_frag_t *frag;
	unsigned int data_len, size;
	struct ice_tx_desc *tx_desc;
	struct ice_tx_buf *tx_buf;
	struct sk_buff *skb;
	dma_addr_t dma;

	td_tag = off->td_l2tag1;
	td_cmd = off->td_cmd;
	td_offset = off->td_offset;
	skb = first->skb;

	data_len = skb->data_len;
	size = skb_headlen(skb);

	tx_desc = ICE_TX_DESC(tx_ring, i);

	if (first->tx_flags & ICE_TX_FLAGS_HW_VLAN) {
		td_cmd |= (u64)ICE_TX_DESC_CMD_IL2TAG1;
		td_tag = (first->tx_flags & ICE_TX_FLAGS_VLAN_M) >>
			  ICE_TX_FLAGS_VLAN_S;
	}

	dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE);

	tx_buf = first;

	for (frag = &skb_shinfo(skb)->frags[0];; frag++) {
		unsigned int max_data = ICE_MAX_DATA_PER_TXD_ALIGNED;

		if (dma_mapping_error(tx_ring->dev, dma))
			goto dma_error;

		/* record length, and DMA address */
		dma_unmap_len_set(tx_buf, len, size);
		dma_unmap_addr_set(tx_buf, dma, dma);

		/* align size to end of page */
		max_data += -dma & (ICE_MAX_READ_REQ_SIZE - 1);
		tx_desc->buf_addr = cpu_to_le64(dma);

		/* account for data chunks larger than the hardware
		 * can handle
		 */
		while (unlikely(size > ICE_MAX_DATA_PER_TXD)) {
			tx_desc->cmd_type_offset_bsz =
				build_ctob(td_cmd, td_offset, max_data, td_tag);

			tx_desc++;
			i++;

			if (i == tx_ring->count) {
				tx_desc = ICE_TX_DESC(tx_ring, 0);
				i = 0;
			}

			dma += max_data;
			size -= max_data;

			max_data = ICE_MAX_DATA_PER_TXD_ALIGNED;
			tx_desc->buf_addr = cpu_to_le64(dma);
		}

		if (likely(!data_len))
			break;

		tx_desc->cmd_type_offset_bsz = build_ctob(td_cmd, td_offset,
							  size, td_tag);

		tx_desc++;
		i++;

		if (i == tx_ring->count) {
			tx_desc = ICE_TX_DESC(tx_ring, 0);
			i = 0;
		}

		size = skb_frag_size(frag);
		data_len -= size;

		dma = skb_frag_dma_map(tx_ring->dev, frag, 0, size,
				       DMA_TO_DEVICE);

		tx_buf = &tx_ring->tx_buf[i];
	}

	/* record bytecount for BQL */
	netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount);

	/* record SW timestamp if HW timestamp is not available */
	skb_tx_timestamp(first->skb);

	i++;
	if (i == tx_ring->count)
		i = 0;

	/* write last descriptor with RS and EOP bits */
	td_cmd |= (u64)ICE_TXD_LAST_DESC_CMD;
	tx_desc->cmd_type_offset_bsz = build_ctob(td_cmd, td_offset, size,
						  td_tag);

	/* Force memory writes to complete before letting h/w know there
	 * are new descriptors to fetch.
	 *
	 * We also use this memory barrier to make certain all of the
	 * status bits have been updated before next_to_watch is written.
	 */
	wmb();

	/* set next_to_watch value indicating a packet is present */
	first->next_to_watch = tx_desc;

	tx_ring->next_to_use = i;

	ice_maybe_stop_tx(tx_ring, DESC_NEEDED);

	/* notify HW of packet */
	if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
		writel(i, tx_ring->tail);
	}

	return;

dma_error:
	/* clear DMA mappings for failed tx_buf map */
	for (;;) {
		tx_buf = &tx_ring->tx_buf[i];
		ice_unmap_and_free_tx_buf(tx_ring, tx_buf);
		if (tx_buf == first)
			break;
		if (i == 0)
			i = tx_ring->count;
		i--;
	}

	tx_ring->next_to_use = i;
}

/**
 * ice_tx_csum - Enable Tx checksum offloads
 * @first: pointer to the first descriptor
 * @off: pointer to struct that holds offload parameters
 *
 * Returns 0 or error (negative) if checksum offload can't happen, 1 otherwise.
 */
static
int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
{
	u32 l4_len = 0, l3_len = 0, l2_len = 0;
	struct sk_buff *skb = first->skb;
	union {
		struct iphdr *v4;
		struct ipv6hdr *v6;
		unsigned char *hdr;
	} ip;
	union {
		struct tcphdr *tcp;
		unsigned char *hdr;
	} l4;
	__be16 frag_off, protocol;
	unsigned char *exthdr;
	u32 offset, cmd = 0;
	u8 l4_proto = 0;

	if (skb->ip_summed != CHECKSUM_PARTIAL)
		return 0;

	ip.hdr = skb_network_header(skb);
	l4.hdr = skb_transport_header(skb);

	/* compute outer L2 header size */
	l2_len = ip.hdr - skb->data;
	offset = (l2_len / 2) << ICE_TX_DESC_LEN_MACLEN_S;

	if (skb->encapsulation)
		return -1;

	/* Enable IP checksum offloads */
	protocol = vlan_get_protocol(skb);
	if (protocol == htons(ETH_P_IP)) {
		l4_proto = ip.v4->protocol;
		/* the stack computes the IP header already, the only time we
		 * need the hardware to recompute it is in the case of TSO.
		 */
		if (first->tx_flags & ICE_TX_FLAGS_TSO)
			cmd |= ICE_TX_DESC_CMD_IIPT_IPV4_CSUM;
		else
			cmd |= ICE_TX_DESC_CMD_IIPT_IPV4;

	} else if (protocol == htons(ETH_P_IPV6)) {
		cmd |= ICE_TX_DESC_CMD_IIPT_IPV6;
		exthdr = ip.hdr + sizeof(*ip.v6);
		l4_proto = ip.v6->nexthdr;
		if (l4.hdr != exthdr)
			ipv6_skip_exthdr(skb, exthdr - skb->data, &l4_proto,
					 &frag_off);
	} else {
		return -1;
	}

	/* compute inner L3 header size */
	l3_len = l4.hdr - ip.hdr;
	offset |= (l3_len / 4) << ICE_TX_DESC_LEN_IPLEN_S;

	/* Enable L4 checksum offloads */
	switch (l4_proto) {
	case IPPROTO_TCP:
		/* enable checksum offloads */
		cmd |= ICE_TX_DESC_CMD_L4T_EOFT_TCP;
		l4_len = l4.tcp->doff;
		offset |= l4_len << ICE_TX_DESC_LEN_L4_LEN_S;
		break;
	case IPPROTO_UDP:
		/* enable UDP checksum offload */
		cmd |= ICE_TX_DESC_CMD_L4T_EOFT_UDP;
		l4_len = (sizeof(struct udphdr) >> 2);
		offset |= l4_len << ICE_TX_DESC_LEN_L4_LEN_S;
		break;
	case IPPROTO_SCTP:
		/* enable SCTP checksum offload */
		cmd |= ICE_TX_DESC_CMD_L4T_EOFT_SCTP;
		l4_len = sizeof(struct sctphdr) >> 2;
		offset |= l4_len << ICE_TX_DESC_LEN_L4_LEN_S;
		break;

	default:
		if (first->tx_flags & ICE_TX_FLAGS_TSO)
			return -1;
		skb_checksum_help(skb);
		return 0;
	}

	off->td_cmd |= cmd;
	off->td_offset |= offset;
	return 1;
}

/**
 * ice_tx_prepare_vlan_flags - prepare generic Tx VLAN tagging flags for HW
 * @tx_ring: ring to send buffer on
 * @first: pointer to struct ice_tx_buf
 *
 * Checks the skb and set up correspondingly several generic transmit flags
 * related to VLAN tagging for the HW, such as VLAN, DCB, etc.
 *
 * Returns error code indicate the frame should be dropped upon error and the
 * otherwise returns 0 to indicate the flags has been set properly.
 */
static int
ice_tx_prepare_vlan_flags(struct ice_ring *tx_ring, struct ice_tx_buf *first)
{
	struct sk_buff *skb = first->skb;
	__be16 protocol = skb->protocol;

	if (protocol == htons(ETH_P_8021Q) &&
	    !(tx_ring->netdev->features & NETIF_F_HW_VLAN_CTAG_TX)) {
		/* when HW VLAN acceleration is turned off by the user the
		 * stack sets the protocol to 8021q so that the driver
		 * can take any steps required to support the SW only
		 * VLAN handling. In our case the driver doesn't need
		 * to take any further steps so just set the protocol
		 * to the encapsulated ethertype.
		 */
		skb->protocol = vlan_get_protocol(skb);
		return 0;
	}

	/* if we have a HW VLAN tag being added, default to the HW one */
	if (skb_vlan_tag_present(skb)) {
		first->tx_flags |= skb_vlan_tag_get(skb) << ICE_TX_FLAGS_VLAN_S;
		first->tx_flags |= ICE_TX_FLAGS_HW_VLAN;
	} else if (protocol == htons(ETH_P_8021Q)) {
		struct vlan_hdr *vhdr, _vhdr;

		/* for SW VLAN, check the next protocol and store the tag */
		vhdr = (struct vlan_hdr *)skb_header_pointer(skb, ETH_HLEN,
							     sizeof(_vhdr),
							     &_vhdr);
		if (!vhdr)
			return -EINVAL;

		first->tx_flags |= ntohs(vhdr->h_vlan_TCI) <<
				   ICE_TX_FLAGS_VLAN_S;
		first->tx_flags |= ICE_TX_FLAGS_SW_VLAN;
	}

	return ice_tx_prepare_vlan_flags_dcb(tx_ring, first);
}

/**
 * ice_tso - computes mss and TSO length to prepare for TSO
 * @first: pointer to struct ice_tx_buf
 * @off: pointer to struct that holds offload parameters
 *
 * Returns 0 or error (negative) if TSO can't happen, 1 otherwise.
 */
static
int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
{
	struct sk_buff *skb = first->skb;
	union {
		struct iphdr *v4;
		struct ipv6hdr *v6;
		unsigned char *hdr;
	} ip;
	union {
		struct tcphdr *tcp;
		unsigned char *hdr;
	} l4;
	u64 cd_mss, cd_tso_len;
	u32 paylen, l4_start;
	int err;

	if (skb->ip_summed != CHECKSUM_PARTIAL)
		return 0;

	if (!skb_is_gso(skb))
		return 0;

	err = skb_cow_head(skb, 0);
	if (err < 0)
		return err;

	/* cppcheck-suppress unreadVariable */
	ip.hdr = skb_network_header(skb);
	l4.hdr = skb_transport_header(skb);

	/* initialize outer IP header fields */
	if (ip.v4->version == 4) {
		ip.v4->tot_len = 0;
		ip.v4->check = 0;
	} else {
		ip.v6->payload_len = 0;
	}

	/* determine offset of transport header */
	l4_start = l4.hdr - skb->data;

	/* remove payload length from checksum */
	paylen = skb->len - l4_start;
	csum_replace_by_diff(&l4.tcp->check, (__force __wsum)htonl(paylen));

	/* compute length of segmentation header */
	off->header_len = (l4.tcp->doff * 4) + l4_start;

	/* update gso_segs and bytecount */
	first->gso_segs = skb_shinfo(skb)->gso_segs;
	first->bytecount += (first->gso_segs - 1) * off->header_len;

	cd_tso_len = skb->len - off->header_len;
	cd_mss = skb_shinfo(skb)->gso_size;

	/* record cdesc_qw1 with TSO parameters */
	off->cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX |
			     (ICE_TX_CTX_DESC_TSO << ICE_TXD_CTX_QW1_CMD_S) |
			     (cd_tso_len << ICE_TXD_CTX_QW1_TSO_LEN_S) |
			     (cd_mss << ICE_TXD_CTX_QW1_MSS_S));
	first->tx_flags |= ICE_TX_FLAGS_TSO;
	return 1;
}

/**
 * ice_txd_use_count  - estimate the number of descriptors needed for Tx
 * @size: transmit request size in bytes
 *
 * Due to hardware alignment restrictions (4K alignment), we need to
 * assume that we can have no more than 12K of data per descriptor, even
 * though each descriptor can take up to 16K - 1 bytes of aligned memory.
 * Thus, we need to divide by 12K. But division is slow! Instead,
 * we decompose the operation into shifts and one relatively cheap
 * multiply operation.
 *
 * To divide by 12K, we first divide by 4K, then divide by 3:
 *     To divide by 4K, shift right by 12 bits
 *     To divide by 3, multiply by 85, then divide by 256
 *     (Divide by 256 is done by shifting right by 8 bits)
 * Finally, we add one to round up. Because 256 isn't an exact multiple of
 * 3, we'll underestimate near each multiple of 12K. This is actually more
 * accurate as we have 4K - 1 of wiggle room that we can fit into the last
 * segment. For our purposes this is accurate out to 1M which is orders of
 * magnitude greater than our largest possible GSO size.
 *
 * This would then be implemented as:
 *     return (((size >> 12) * 85) >> 8) + ICE_DESCS_FOR_SKB_DATA_PTR;
 *
 * Since multiplication and division are commutative, we can reorder
 * operations into:
 *     return ((size * 85) >> 20) + ICE_DESCS_FOR_SKB_DATA_PTR;
 */
static unsigned int ice_txd_use_count(unsigned int size)
{
	return ((size * 85) >> 20) + ICE_DESCS_FOR_SKB_DATA_PTR;
}

/**
 * ice_xmit_desc_count - calculate number of Tx descriptors needed
 * @skb: send buffer
 *
 * Returns number of data descriptors needed for this skb.
 */
static unsigned int ice_xmit_desc_count(struct sk_buff *skb)
{
	const skb_frag_t *frag = &skb_shinfo(skb)->frags[0];
	unsigned int nr_frags = skb_shinfo(skb)->nr_frags;
	unsigned int count = 0, size = skb_headlen(skb);

	for (;;) {
		count += ice_txd_use_count(size);

		if (!nr_frags--)
			break;

		size = skb_frag_size(frag++);
	}

	return count;
}

/**
 * __ice_chk_linearize - Check if there are more than 8 buffers per packet
 * @skb: send buffer
 *
 * Note: This HW can't DMA more than 8 buffers to build a packet on the wire
 * and so we need to figure out the cases where we need to linearize the skb.
 *
 * For TSO we need to count the TSO header and segment payload separately.
 * As such we need to check cases where we have 7 fragments or more as we
 * can potentially require 9 DMA transactions, 1 for the TSO header, 1 for
 * the segment payload in the first descriptor, and another 7 for the
 * fragments.
 */
static bool __ice_chk_linearize(struct sk_buff *skb)
{
	const skb_frag_t *frag, *stale;
	int nr_frags, sum;

	/* no need to check if number of frags is less than 7 */
	nr_frags = skb_shinfo(skb)->nr_frags;
	if (nr_frags < (ICE_MAX_BUF_TXD - 1))
		return false;

	/* We need to walk through the list and validate that each group
	 * of 6 fragments totals at least gso_size.
	 */
	nr_frags -= ICE_MAX_BUF_TXD - 2;
	frag = &skb_shinfo(skb)->frags[0];

	/* Initialize size to the negative value of gso_size minus 1. We
	 * use this as the worst case scenerio in which the frag ahead
	 * of us only provides one byte which is why we are limited to 6
	 * descriptors for a single transmit as the header and previous
	 * fragment are already consuming 2 descriptors.
	 */
	sum = 1 - skb_shinfo(skb)->gso_size;

	/* Add size of frags 0 through 4 to create our initial sum */
	sum += skb_frag_size(frag++);
	sum += skb_frag_size(frag++);
	sum += skb_frag_size(frag++);
	sum += skb_frag_size(frag++);
	sum += skb_frag_size(frag++);

	/* Walk through fragments adding latest fragment, testing it, and
	 * then removing stale fragments from the sum.
	 */
	stale = &skb_shinfo(skb)->frags[0];
	for (;;) {
		sum += skb_frag_size(frag++);

		/* if sum is negative we failed to make sufficient progress */
		if (sum < 0)
			return true;

		if (!nr_frags--)
			break;

		sum -= skb_frag_size(stale++);
	}

	return false;
}

/**
 * ice_chk_linearize - Check if there are more than 8 fragments per packet
 * @skb:      send buffer
 * @count:    number of buffers used
 *
 * Note: Our HW can't scatter-gather more than 8 fragments to build
 * a packet on the wire and so we need to figure out the cases where we
 * need to linearize the skb.
 */
static bool ice_chk_linearize(struct sk_buff *skb, unsigned int count)
{
	/* Both TSO and single send will work if count is less than 8 */
	if (likely(count < ICE_MAX_BUF_TXD))
		return false;

	if (skb_is_gso(skb))
		return __ice_chk_linearize(skb);

	/* we can support up to 8 data buffers for a single send */
	return count != ICE_MAX_BUF_TXD;
}

/**
 * ice_xmit_frame_ring - Sends buffer on Tx ring
 * @skb: send buffer
 * @tx_ring: ring to send buffer on
 *
 * Returns NETDEV_TX_OK if sent, else an error code
 */
static netdev_tx_t
ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring)
{
	struct ice_tx_offload_params offload = { 0 };
	struct ice_vsi *vsi = tx_ring->vsi;
	struct ice_tx_buf *first;
	unsigned int count;
	int tso, csum;

	count = ice_xmit_desc_count(skb);
	if (ice_chk_linearize(skb, count)) {
		if (__skb_linearize(skb))
			goto out_drop;
		count = ice_txd_use_count(skb->len);
		tx_ring->tx_stats.tx_linearize++;
	}

	/* need: 1 descriptor per page * PAGE_SIZE/ICE_MAX_DATA_PER_TXD,
	 *       + 1 desc for skb_head_len/ICE_MAX_DATA_PER_TXD,
	 *       + 4 desc gap to avoid the cache line where head is,
	 *       + 1 desc for context descriptor,
	 * otherwise try next time
	 */
	if (ice_maybe_stop_tx(tx_ring, count + ICE_DESCS_PER_CACHE_LINE +
			      ICE_DESCS_FOR_CTX_DESC)) {
		tx_ring->tx_stats.tx_busy++;
		return NETDEV_TX_BUSY;
	}

	offload.tx_ring = tx_ring;

	/* record the location of the first descriptor for this packet */
	first = &tx_ring->tx_buf[tx_ring->next_to_use];
	first->skb = skb;
	first->bytecount = max_t(unsigned int, skb->len, ETH_ZLEN);
	first->gso_segs = 1;
	first->tx_flags = 0;

	/* prepare the VLAN tagging flags for Tx */
	if (ice_tx_prepare_vlan_flags(tx_ring, first))
		goto out_drop;

	/* set up TSO offload */
	tso = ice_tso(first, &offload);
	if (tso < 0)
		goto out_drop;

	/* always set up Tx checksum offload */
	csum = ice_tx_csum(first, &offload);
	if (csum < 0)
		goto out_drop;

	/* allow CONTROL frames egress from main VSI if FW LLDP disabled */
	if (unlikely(skb->priority == TC_PRIO_CONTROL &&
		     vsi->type == ICE_VSI_PF &&
		     vsi->port_info->is_sw_lldp))
		offload.cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX |
					ICE_TX_CTX_DESC_SWTCH_UPLINK <<
					ICE_TXD_CTX_QW1_CMD_S);

	if (offload.cd_qw1 & ICE_TX_DESC_DTYPE_CTX) {
		struct ice_tx_ctx_desc *cdesc;
		int i = tx_ring->next_to_use;

		/* grab the next descriptor */
		cdesc = ICE_TX_CTX_DESC(tx_ring, i);
		i++;
		tx_ring->next_to_use = (i < tx_ring->count) ? i : 0;

		/* setup context descriptor */
		cdesc->tunneling_params = cpu_to_le32(offload.cd_tunnel_params);
		cdesc->l2tag2 = cpu_to_le16(offload.cd_l2tag2);
		cdesc->rsvd = cpu_to_le16(0);
		cdesc->qw1 = cpu_to_le64(offload.cd_qw1);
	}

	ice_tx_map(tx_ring, first, &offload);
	return NETDEV_TX_OK;

out_drop:
	dev_kfree_skb_any(skb);
	return NETDEV_TX_OK;
}

/**
 * ice_start_xmit - Selects the correct VSI and Tx queue to send buffer
 * @skb: send buffer
 * @netdev: network interface device structure
 *
 * Returns NETDEV_TX_OK if sent, else an error code
 */
netdev_tx_t ice_start_xmit(struct sk_buff *skb, struct net_device *netdev)
{
	struct ice_netdev_priv *np = netdev_priv(netdev);
	struct ice_vsi *vsi = np->vsi;
	struct ice_ring *tx_ring;

	tx_ring = vsi->tx_rings[skb->queue_mapping];

	/* hardware can't handle really short frames, hardware padding works
	 * beyond this point
	 */
	if (skb_put_padto(skb, ICE_MIN_TX_LEN))
		return NETDEV_TX_OK;

	return ice_xmit_frame_ring(skb, tx_ring);
}