aboutsummaryrefslogtreecommitdiffstats
path: root/libtransport/src/test/test_consumer_producer_rtc.cc
blob: b11a6a388f5621f8e56f2693e244bdc8ea197a7d (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
/*
 * Copyright (c) 2021 Cisco and/or its affiliates.
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at:
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

#include <gtest/gtest.h>
#include <hicn/transport/core/asio_wrapper.h>
#include <hicn/transport/interfaces/global_conf_interface.h>
#include <hicn/transport/interfaces/socket_consumer.h>
#include <hicn/transport/interfaces/socket_options_keys.h>
#include <hicn/transport/interfaces/socket_producer.h>

namespace transport {
namespace interface {

namespace {

class ConsumerProducerTest : public ::testing::Test,
                             public ConsumerSocket::ReadCallback {
  static const constexpr char prefix[] = "b001::1/128";
  static const constexpr char name[] = "b001::1";
  static const constexpr double prod_rate = 1.0e6;
  static const constexpr size_t payload_size = 1200;
  static constexpr std::size_t receive_buffer_size = 1500;
  static const constexpr double prod_interval_microseconds =
      double(payload_size) * 8 * 1e6 / prod_rate;

 public:
  ConsumerProducerTest()
      : io_service_(),
        rtc_timer_(io_service_),
        stop_timer_(io_service_),
        consumer_(TransportProtocolAlgorithms::RTC, io_service_),
        producer_(ProductionProtocolAlgorithms::RTC_PROD, thread_),
        producer_prefix_(prefix),
        consumer_name_(name),
        packets_sent_(0),
        packets_received_(0) {
    global_config::IoModuleConfiguration config;
    config.name = "loopback_module";
    config.set();
  }

  virtual ~ConsumerProducerTest() {
    // You can do clean-up work that doesn't throw exceptions here.
  }

  // If the constructor and destructor are not enough for setting up
  // and cleaning up each test, you can define the following methods:

  virtual void SetUp() override {
    // Code here will be called immediately after the constructor (right
    // before each test).

    auto ret = consumer_.setSocketOption(
        ConsumerCallbacksOptions::READ_CALLBACK, this);
    ASSERT_EQ(ret, SOCKET_OPTION_SET);

    consumer_.connect();
    producer_.registerPrefix(producer_prefix_);
    producer_.connect();
  }

  virtual void TearDown() override {
    // Code here will be called immediately after each test (right
    // before the destructor).
  }

  void setTimer() {
    using namespace std::chrono;
    rtc_timer_.expires_from_now(
        microseconds(unsigned(prod_interval_microseconds)));
    rtc_timer_.async_wait(std::bind(&ConsumerProducerTest::produceRTCPacket,
                                    this, std::placeholders::_1));
  }

  void setStopTimer() {
    using namespace std::chrono;
    stop_timer_.expires_from_now(seconds(unsigned(10)));
    stop_timer_.async_wait(
        std::bind(&ConsumerProducerTest::stop, this, std::placeholders::_1));
  }

  void produceRTCPacket(const std::error_code &ec) {
    if (ec) {
      io_service_.stop();
    }

    producer_.produceDatagram(consumer_name_, payload_, payload_size);
    packets_sent_++;
    setTimer();
  }

  void stop(const std::error_code &ec) {
    rtc_timer_.cancel();
    producer_.stop();
    consumer_.stop();
  }

  // Consumer callback
  bool isBufferMovable() noexcept override { return false; }

  void getReadBuffer(uint8_t **application_buffer,
                     size_t *max_length) override {
    *application_buffer = receive_buffer_;
    *max_length = receive_buffer_size;
  }

  void readDataAvailable(std::size_t length) noexcept override {}

  size_t maxBufferSize() const override { return receive_buffer_size; }

  void readError(const std::error_code &ec) noexcept override {
    io_service_.stop();
    FAIL() << "Error while reading from RTC socket";
  }

  void readSuccess(std::size_t total_size) noexcept override {
    packets_received_++;
  }

  asio::io_service io_service_;
  asio::steady_timer rtc_timer_;
  asio::steady_timer stop_timer_;
  ConsumerSocket consumer_;
  ProducerSocket producer_;
  core::Prefix producer_prefix_;
  core::Name consumer_name_;
  uint8_t payload_[payload_size];
  uint8_t receive_buffer_[payload_size];

  uint64_t packets_sent_;
  uint64_t packets_received_;
};

const char ConsumerProducerTest::prefix[];
const char ConsumerProducerTest::name[];

}  // namespace

TEST_F(ConsumerProducerTest, DISABLED_EndToEnd) {
  produceRTCPacket(std::error_code());
  consumer_.consume(consumer_name_);
  setStopTimer();

  io_service_.run();

  std::cout << "Packet received: " << packets_received_ << std::endl;
  std::cout << "Packet sent: " << packets_sent_ << std::endl;
}

}  // namespace interface

}  // namespace transport
' href='#n883'>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
/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright(c) 2010-2016 Intel Corporation
 */

#include <sys/queue.h>
#include <stdio.h>
#include <errno.h>
#include <stdint.h>
#include <stdarg.h>

#include <rte_common.h>
#include <rte_interrupts.h>
#include <rte_byteorder.h>
#include <rte_debug.h>
#include <rte_pci.h>
#include <rte_bus_pci.h>
#include <rte_ether.h>
#include <rte_ethdev_driver.h>
#include <rte_ethdev_pci.h>
#include <rte_memory.h>
#include <rte_eal.h>
#include <rte_malloc.h>
#include <rte_dev.h>

#include "e1000_logs.h"
#include "base/e1000_api.h"
#include "e1000_ethdev.h"

#define EM_EIAC			0x000DC

#define PMD_ROUNDUP(x,y)	(((x) + (y) - 1)/(y) * (y))


static int eth_em_configure(struct rte_eth_dev *dev);
static int eth_em_start(struct rte_eth_dev *dev);
static void eth_em_stop(struct rte_eth_dev *dev);
static void eth_em_close(struct rte_eth_dev *dev);
static void eth_em_promiscuous_enable(struct rte_eth_dev *dev);
static void eth_em_promiscuous_disable(struct rte_eth_dev *dev);
static void eth_em_allmulticast_enable(struct rte_eth_dev *dev);
static void eth_em_allmulticast_disable(struct rte_eth_dev *dev);
static int eth_em_link_update(struct rte_eth_dev *dev,
				int wait_to_complete);
static int eth_em_stats_get(struct rte_eth_dev *dev,
				struct rte_eth_stats *rte_stats);
static void eth_em_stats_reset(struct rte_eth_dev *dev);
static void eth_em_infos_get(struct rte_eth_dev *dev,
				struct rte_eth_dev_info *dev_info);
static int eth_em_flow_ctrl_get(struct rte_eth_dev *dev,
				struct rte_eth_fc_conf *fc_conf);
static int eth_em_flow_ctrl_set(struct rte_eth_dev *dev,
				struct rte_eth_fc_conf *fc_conf);
static int eth_em_interrupt_setup(struct rte_eth_dev *dev);
static int eth_em_rxq_interrupt_setup(struct rte_eth_dev *dev);
static int eth_em_interrupt_get_status(struct rte_eth_dev *dev);
static int eth_em_interrupt_action(struct rte_eth_dev *dev,
				   struct rte_intr_handle *handle);
static void eth_em_interrupt_handler(void *param);

static int em_hw_init(struct e1000_hw *hw);
static int em_hardware_init(struct e1000_hw *hw);
static void em_hw_control_acquire(struct e1000_hw *hw);
static void em_hw_control_release(struct e1000_hw *hw);
static void em_init_manageability(struct e1000_hw *hw);
static void em_release_manageability(struct e1000_hw *hw);

static int eth_em_mtu_set(struct rte_eth_dev *dev, uint16_t mtu);

static int eth_em_vlan_filter_set(struct rte_eth_dev *dev,
		uint16_t vlan_id, int on);
static int eth_em_vlan_offload_set(struct rte_eth_dev *dev, int mask);
static void em_vlan_hw_filter_enable(struct rte_eth_dev *dev);
static void em_vlan_hw_filter_disable(struct rte_eth_dev *dev);
static void em_vlan_hw_strip_enable(struct rte_eth_dev *dev);
static void em_vlan_hw_strip_disable(struct rte_eth_dev *dev);

/*
static void eth_em_vlan_filter_set(struct rte_eth_dev *dev,
					uint16_t vlan_id, int on);
*/

static int eth_em_rx_queue_intr_enable(struct rte_eth_dev *dev, uint16_t queue_id);
static int eth_em_rx_queue_intr_disable(struct rte_eth_dev *dev, uint16_t queue_id);
static void em_lsc_intr_disable(struct e1000_hw *hw);
static void em_rxq_intr_enable(struct e1000_hw *hw);
static void em_rxq_intr_disable(struct e1000_hw *hw);

static int eth_em_led_on(struct rte_eth_dev *dev);
static int eth_em_led_off(struct rte_eth_dev *dev);

static int em_get_rx_buffer_size(struct e1000_hw *hw);
static int eth_em_rar_set(struct rte_eth_dev *dev, struct ether_addr *mac_addr,
			  uint32_t index, uint32_t pool);
static void eth_em_rar_clear(struct rte_eth_dev *dev, uint32_t index);
static int eth_em_default_mac_addr_set(struct rte_eth_dev *dev,
					 struct ether_addr *addr);

static int eth_em_set_mc_addr_list(struct rte_eth_dev *dev,
				   struct ether_addr *mc_addr_set,
				   uint32_t nb_mc_addr);

#define EM_FC_PAUSE_TIME 0x0680
#define EM_LINK_UPDATE_CHECK_TIMEOUT  90  /* 9s */
#define EM_LINK_UPDATE_CHECK_INTERVAL 100 /* ms */

static enum e1000_fc_mode em_fc_setting = e1000_fc_full;

/*
 * The set of PCI devices this driver supports
 */
static const struct rte_pci_id pci_id_em_map[] = {
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_82540EM) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_82545EM_COPPER) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_82545EM_FIBER) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_82546EB_COPPER) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_82546EB_FIBER) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_82546EB_QUAD_COPPER) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_82571EB_COPPER) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_82571EB_FIBER) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_82571EB_SERDES) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_82571EB_SERDES_DUAL) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_82571EB_SERDES_QUAD) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_82571EB_QUAD_COPPER) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_82571PT_QUAD_COPPER) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_82571EB_QUAD_FIBER) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_82571EB_QUAD_COPPER_LP) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_82572EI_COPPER) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_82572EI_FIBER) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_82572EI_SERDES) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_82572EI) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_82573L) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_82574L) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_82574LA) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_82583V) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_PCH2_LV_LM) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_PCH_LPT_I217_LM) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_PCH_LPT_I217_V) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_PCH_LPTLP_I218_LM) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_PCH_LPTLP_I218_V) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_PCH_I218_LM2) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_PCH_I218_V2) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_PCH_I218_LM3) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_PCH_I218_V3) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_PCH_SPT_I219_LM) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_PCH_SPT_I219_V) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_PCH_SPT_I219_LM2) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_PCH_SPT_I219_V2) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_PCH_LBG_I219_LM3) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_PCH_SPT_I219_LM4) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_PCH_SPT_I219_V4) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_PCH_SPT_I219_LM5) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_PCH_SPT_I219_V5) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_PCH_CNP_I219_LM6) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_PCH_CNP_I219_V6) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_PCH_CNP_I219_LM7) },
	{ RTE_PCI_DEVICE(E1000_INTEL_VENDOR_ID, E1000_DEV_ID_PCH_CNP_I219_V7) },
	{ .vendor_id = 0, /* sentinel */ },
};

static const struct eth_dev_ops eth_em_ops = {
	.dev_configure        = eth_em_configure,
	.dev_start            = eth_em_start,
	.dev_stop             = eth_em_stop,
	.dev_close            = eth_em_close,
	.promiscuous_enable   = eth_em_promiscuous_enable,
	.promiscuous_disable  = eth_em_promiscuous_disable,
	.allmulticast_enable  = eth_em_allmulticast_enable,
	.allmulticast_disable = eth_em_allmulticast_disable,
	.link_update          = eth_em_link_update,
	.stats_get            = eth_em_stats_get,
	.stats_reset          = eth_em_stats_reset,
	.dev_infos_get        = eth_em_infos_get,
	.mtu_set              = eth_em_mtu_set,
	.vlan_filter_set      = eth_em_vlan_filter_set,
	.vlan_offload_set     = eth_em_vlan_offload_set,
	.rx_queue_setup       = eth_em_rx_queue_setup,
	.rx_queue_release     = eth_em_rx_queue_release,
	.rx_queue_count       = eth_em_rx_queue_count,
	.rx_descriptor_done   = eth_em_rx_descriptor_done,
	.rx_descriptor_status = eth_em_rx_descriptor_status,
	.tx_descriptor_status = eth_em_tx_descriptor_status,
	.tx_queue_setup       = eth_em_tx_queue_setup,
	.tx_queue_release     = eth_em_tx_queue_release,
	.rx_queue_intr_enable = eth_em_rx_queue_intr_enable,
	.rx_queue_intr_disable = eth_em_rx_queue_intr_disable,
	.dev_led_on           = eth_em_led_on,
	.dev_led_off          = eth_em_led_off,
	.flow_ctrl_get        = eth_em_flow_ctrl_get,
	.flow_ctrl_set        = eth_em_flow_ctrl_set,
	.mac_addr_set         = eth_em_default_mac_addr_set,
	.mac_addr_add         = eth_em_rar_set,
	.mac_addr_remove      = eth_em_rar_clear,
	.set_mc_addr_list     = eth_em_set_mc_addr_list,
	.rxq_info_get         = em_rxq_info_get,
	.txq_info_get         = em_txq_info_get,
};


/**
 *  eth_em_dev_is_ich8 - Check for ICH8 device
 *  @hw: pointer to the HW structure
 *
 *  return TRUE for ICH8, otherwise FALSE
 **/
static bool
eth_em_dev_is_ich8(struct e1000_hw *hw)
{
	DEBUGFUNC("eth_em_dev_is_ich8");

	switch (hw->device_id) {
	case E1000_DEV_ID_PCH2_LV_LM:
	case E1000_DEV_ID_PCH_LPT_I217_LM:
	case E1000_DEV_ID_PCH_LPT_I217_V:
	case E1000_DEV_ID_PCH_LPTLP_I218_LM:
	case E1000_DEV_ID_PCH_LPTLP_I218_V:
	case E1000_DEV_ID_PCH_I218_V2:
	case E1000_DEV_ID_PCH_I218_LM2:
	case E1000_DEV_ID_PCH_I218_V3:
	case E1000_DEV_ID_PCH_I218_LM3:
	case E1000_DEV_ID_PCH_SPT_I219_LM:
	case E1000_DEV_ID_PCH_SPT_I219_V:
	case E1000_DEV_ID_PCH_SPT_I219_LM2:
	case E1000_DEV_ID_PCH_SPT_I219_V2:
	case E1000_DEV_ID_PCH_LBG_I219_LM3:
	case E1000_DEV_ID_PCH_SPT_I219_LM4:
	case E1000_DEV_ID_PCH_SPT_I219_V4:
	case E1000_DEV_ID_PCH_SPT_I219_LM5:
	case E1000_DEV_ID_PCH_SPT_I219_V5:
	case E1000_DEV_ID_PCH_CNP_I219_LM6:
	case E1000_DEV_ID_PCH_CNP_I219_V6:
	case E1000_DEV_ID_PCH_CNP_I219_LM7:
	case E1000_DEV_ID_PCH_CNP_I219_V7:
		return 1;
	default:
		return 0;
	}
}

static int
eth_em_dev_init(struct rte_eth_dev *eth_dev)
{
	struct rte_pci_device *pci_dev = RTE_ETH_DEV_TO_PCI(eth_dev);
	struct rte_intr_handle *intr_handle = &pci_dev->intr_handle;
	struct e1000_adapter *adapter =
		E1000_DEV_PRIVATE(eth_dev->data->dev_private);
	struct e1000_hw *hw =
		E1000_DEV_PRIVATE_TO_HW(eth_dev->data->dev_private);
	struct e1000_vfta * shadow_vfta =
		E1000_DEV_PRIVATE_TO_VFTA(eth_dev->data->dev_private);

	eth_dev->dev_ops = &eth_em_ops;
	eth_dev->rx_pkt_burst = (eth_rx_burst_t)&eth_em_recv_pkts;
	eth_dev->tx_pkt_burst = (eth_tx_burst_t)&eth_em_xmit_pkts;
	eth_dev->tx_pkt_prepare = (eth_tx_prep_t)&eth_em_prep_pkts;

	/* for secondary processes, we don't initialise any further as primary
	 * has already done this work. Only check we don't need a different
	 * RX function */
	if (rte_eal_process_type() != RTE_PROC_PRIMARY){
		if (eth_dev->data->scattered_rx)
			eth_dev->rx_pkt_burst =
				(eth_rx_burst_t)&eth_em_recv_scattered_pkts;
		return 0;
	}

	rte_eth_copy_pci_info(eth_dev, pci_dev);

	hw->hw_addr = (void *)pci_dev->mem_resource[0].addr;
	hw->device_id = pci_dev->id.device_id;
	adapter->stopped = 0;

	/* For ICH8 support we'll need to map the flash memory BAR */
	if (eth_em_dev_is_ich8(hw))
		hw->flash_address = (void *)pci_dev->mem_resource[1].addr;

	if (e1000_setup_init_funcs(hw, TRUE) != E1000_SUCCESS ||
			em_hw_init(hw) != 0) {
		PMD_INIT_LOG(ERR, "port_id %d vendorID=0x%x deviceID=0x%x: "
			"failed to init HW",
			eth_dev->data->port_id, pci_dev->id.vendor_id,
			pci_dev->id.device_id);
		return -ENODEV;
	}

	/* Allocate memory for storing MAC addresses */
	eth_dev->data->mac_addrs = rte_zmalloc("e1000", ETHER_ADDR_LEN *
			hw->mac.rar_entry_count, 0);
	if (eth_dev->data->mac_addrs == NULL) {
		PMD_INIT_LOG(ERR, "Failed to allocate %d bytes needed to "
			"store MAC addresses",
			ETHER_ADDR_LEN * hw->mac.rar_entry_count);
		return -ENOMEM;
	}

	/* Copy the permanent MAC address */
	ether_addr_copy((struct ether_addr *) hw->mac.addr,
		eth_dev->data->mac_addrs);

	/* initialize the vfta */
	memset(shadow_vfta, 0, sizeof(*shadow_vfta));

	PMD_INIT_LOG(DEBUG, "port_id %d vendorID=0x%x deviceID=0x%x",
		     eth_dev->data->port_id, pci_dev->id.vendor_id,
		     pci_dev->id.device_id);

	rte_intr_callback_register(intr_handle,
				   eth_em_interrupt_handler, eth_dev);

	return 0;
}

static int
eth_em_dev_uninit(struct rte_eth_dev *eth_dev)
{
	struct rte_pci_device *pci_dev = RTE_ETH_DEV_TO_PCI(eth_dev);
	struct e1000_adapter *adapter =
		E1000_DEV_PRIVATE(eth_dev->data->dev_private);
	struct rte_intr_handle *intr_handle = &pci_dev->intr_handle;

	PMD_INIT_FUNC_TRACE();

	if (rte_eal_process_type() != RTE_PROC_PRIMARY)
		return -EPERM;

	if (adapter->stopped == 0)
		eth_em_close(eth_dev);

	eth_dev->dev_ops = NULL;
	eth_dev->rx_pkt_burst = NULL;
	eth_dev->tx_pkt_burst = NULL;

	/* disable uio intr before callback unregister */
	rte_intr_disable(intr_handle);
	rte_intr_callback_unregister(intr_handle,
				     eth_em_interrupt_handler, eth_dev);

	return 0;
}

static int eth_em_pci_probe(struct rte_pci_driver *pci_drv __rte_unused,
	struct rte_pci_device *pci_dev)
{
	return rte_eth_dev_pci_generic_probe(pci_dev,
		sizeof(struct e1000_adapter), eth_em_dev_init);
}

static int eth_em_pci_remove(struct rte_pci_device *pci_dev)
{
	return rte_eth_dev_pci_generic_remove(pci_dev, eth_em_dev_uninit);
}

static struct rte_pci_driver rte_em_pmd = {
	.id_table = pci_id_em_map,
	.drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
		     RTE_PCI_DRV_IOVA_AS_VA,
	.probe = eth_em_pci_probe,
	.remove = eth_em_pci_remove,
};

static int
em_hw_init(struct e1000_hw *hw)
{
	int diag;

	diag = hw->mac.ops.init_params(hw);
	if (diag != 0) {
		PMD_INIT_LOG(ERR, "MAC Initialization Error");
		return diag;
	}
	diag = hw->nvm.ops.init_params(hw);
	if (diag != 0) {
		PMD_INIT_LOG(ERR, "NVM Initialization Error");
		return diag;
	}
	diag = hw->phy.ops.init_params(hw);
	if (diag != 0) {
		PMD_INIT_LOG(ERR, "PHY Initialization Error");
		return diag;
	}
	(void) e1000_get_bus_info(hw);

	hw->mac.autoneg = 1;
	hw->phy.autoneg_wait_to_complete = 0;
	hw->phy.autoneg_advertised = E1000_ALL_SPEED_DUPLEX;

	e1000_init_script_state_82541(hw, TRUE);
	e1000_set_tbi_compatibility_82543(hw, TRUE);

	/* Copper options */
	if (hw->phy.media_type == e1000_media_type_copper) {
		hw->phy.mdix = 0; /* AUTO_ALL_MODES */
		hw->phy.disable_polarity_correction = 0;
		hw->phy.ms_type = e1000_ms_hw_default;
	}

	/*
	 * Start from a known state, this is important in reading the nvm
	 * and mac from that.
	 */
	e1000_reset_hw(hw);

	/* Make sure we have a good EEPROM before we read from it */
	if (e1000_validate_nvm_checksum(hw) < 0) {
		/*
		 * Some PCI-E parts fail the first check due to
		 * the link being in sleep state, call it again,
		 * if it fails a second time its a real issue.
		 */
		diag = e1000_validate_nvm_checksum(hw);
		if (diag < 0) {
			PMD_INIT_LOG(ERR, "EEPROM checksum invalid");
			goto error;
		}
	}

	/* Read the permanent MAC address out of the EEPROM */
	diag = e1000_read_mac_addr(hw);
	if (diag != 0) {
		PMD_INIT_LOG(ERR, "EEPROM error while reading MAC address");
		goto error;
	}

	/* Now initialize the hardware */
	diag = em_hardware_init(hw);
	if (diag != 0) {
		PMD_INIT_LOG(ERR, "Hardware initialization failed");
		goto error;
	}

	hw->mac.get_link_status = 1;

	/* Indicate SOL/IDER usage */
	diag = e1000_check_reset_block(hw);
	if (diag < 0) {
		PMD_INIT_LOG(ERR, "PHY reset is blocked due to "
			"SOL/IDER session");
	}
	return 0;

error:
	em_hw_control_release(hw);
	return diag;
}

static int
eth_em_configure(struct rte_eth_dev *dev)
{
	struct e1000_interrupt *intr =
		E1000_DEV_PRIVATE_TO_INTR(dev->data->dev_private);

	PMD_INIT_FUNC_TRACE();
	intr->flags |= E1000_FLAG_NEED_LINK_UPDATE;

	PMD_INIT_FUNC_TRACE();

	return 0;
}

static void
em_set_pba(struct e1000_hw *hw)
{
	uint32_t pba;

	/*
	 * Packet Buffer Allocation (PBA)
	 * Writing PBA sets the receive portion of the buffer
	 * the remainder is used for the transmit buffer.
	 * Devices before the 82547 had a Packet Buffer of 64K.
	 * After the 82547 the buffer was reduced to 40K.
	 */
	switch (hw->mac.type) {
		case e1000_82547:
		case e1000_82547_rev_2:
		/* 82547: Total Packet Buffer is 40K */
			pba = E1000_PBA_22K; /* 22K for Rx, 18K for Tx */
			break;
		case e1000_82571:
		case e1000_82572:
		case e1000_80003es2lan:
			pba = E1000_PBA_32K; /* 32K for Rx, 16K for Tx */
			break;
		case e1000_82573: /* 82573: Total Packet Buffer is 32K */
			pba = E1000_PBA_12K; /* 12K for Rx, 20K for Tx */
			break;
		case e1000_82574:
		case e1000_82583:
			pba = E1000_PBA_20K; /* 20K for Rx, 20K for Tx */
			break;
		case e1000_ich8lan:
			pba = E1000_PBA_8K;
			break;
		case e1000_ich9lan:
		case e1000_ich10lan:
			pba = E1000_PBA_10K;
			break;
		case e1000_pchlan:
		case e1000_pch2lan:
		case e1000_pch_lpt:
		case e1000_pch_spt:
		case e1000_pch_cnp:
			pba = E1000_PBA_26K;
			break;
		default:
			pba = E1000_PBA_40K; /* 40K for Rx, 24K for Tx */
	}

	E1000_WRITE_REG(hw, E1000_PBA, pba);
}

static void
eth_em_rxtx_control(struct rte_eth_dev *dev,
		    bool enable)
{
	struct e1000_hw *hw =
		E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	uint32_t tctl, rctl;

	tctl = E1000_READ_REG(hw, E1000_TCTL);
	rctl = E1000_READ_REG(hw, E1000_RCTL);
	if (enable) {
		/* enable Tx/Rx */
		tctl |= E1000_TCTL_EN;
		rctl |= E1000_RCTL_EN;
	} else {
		/* disable Tx/Rx */
		tctl &= ~E1000_TCTL_EN;
		rctl &= ~E1000_RCTL_EN;
	}
	E1000_WRITE_REG(hw, E1000_TCTL, tctl);
	E1000_WRITE_REG(hw, E1000_RCTL, rctl);
	E1000_WRITE_FLUSH(hw);
}

static int
eth_em_start(struct rte_eth_dev *dev)
{
	struct e1000_adapter *adapter =
		E1000_DEV_PRIVATE(dev->data->dev_private);
	struct e1000_hw *hw =
		E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	struct rte_pci_device *pci_dev = RTE_ETH_DEV_TO_PCI(dev);
	struct rte_intr_handle *intr_handle = &pci_dev->intr_handle;
	int ret, mask;
	uint32_t intr_vector = 0;
	uint32_t *speeds;
	int num_speeds;
	bool autoneg;

	PMD_INIT_FUNC_TRACE();

	eth_em_stop(dev);

	e1000_power_up_phy(hw);

	/* Set default PBA value */
	em_set_pba(hw);

	/* Put the address into the Receive Address Array */
	e1000_rar_set(hw, hw->mac.addr, 0);

	/*
	 * With the 82571 adapter, RAR[0] may be overwritten
	 * when the other port is reset, we make a duplicate
	 * in RAR[14] for that eventuality, this assures
	 * the interface continues to function.
	 */
	if (hw->mac.type == e1000_82571) {
		e1000_set_laa_state_82571(hw, TRUE);
		e1000_rar_set(hw, hw->mac.addr, E1000_RAR_ENTRIES - 1);
	}

	/* Initialize the hardware */
	if (em_hardware_init(hw)) {
		PMD_INIT_LOG(ERR, "Unable to initialize the hardware");
		return -EIO;
	}

	E1000_WRITE_REG(hw, E1000_VET, ETHER_TYPE_VLAN);

	/* Configure for OS presence */
	em_init_manageability(hw);

	if (dev->data->dev_conf.intr_conf.rxq != 0) {
		intr_vector = dev->data->nb_rx_queues;
		if (rte_intr_efd_enable(intr_handle, intr_vector))
			return -1;
	}

	if (rte_intr_dp_is_en(intr_handle)) {
		intr_handle->intr_vec =
			rte_zmalloc("intr_vec",
					dev->data->nb_rx_queues * sizeof(int), 0);
		if (intr_handle->intr_vec == NULL) {
			PMD_INIT_LOG(ERR, "Failed to allocate %d rx_queues"
						" intr_vec", dev->data->nb_rx_queues);
			return -ENOMEM;
		}

		/* enable rx interrupt */
		em_rxq_intr_enable(hw);
	}

	eth_em_tx_init(dev);

	ret = eth_em_rx_init(dev);
	if (ret) {
		PMD_INIT_LOG(ERR, "Unable to initialize RX hardware");
		em_dev_clear_queues(dev);
		return ret;
	}

	e1000_clear_hw_cntrs_base_generic(hw);

	mask = ETH_VLAN_STRIP_MASK | ETH_VLAN_FILTER_MASK | \
			ETH_VLAN_EXTEND_MASK;
	ret = eth_em_vlan_offload_set(dev, mask);
	if (ret) {
		PMD_INIT_LOG(ERR, "Unable to update vlan offload");
		em_dev_clear_queues(dev);
		return ret;
	}

	/* Set Interrupt Throttling Rate to maximum allowed value. */
	E1000_WRITE_REG(hw, E1000_ITR, UINT16_MAX);

	/* Setup link speed and duplex */
	speeds = &dev->data->dev_conf.link_speeds;
	if (*speeds == ETH_LINK_SPEED_AUTONEG) {
		hw->phy.autoneg_advertised = E1000_ALL_SPEED_DUPLEX;
		hw->mac.autoneg = 1;
	} else {
		num_speeds = 0;
		autoneg = (*speeds & ETH_LINK_SPEED_FIXED) == 0;

		/* Reset */
		hw->phy.autoneg_advertised = 0;

		if (*speeds & ~(ETH_LINK_SPEED_10M_HD | ETH_LINK_SPEED_10M |
				ETH_LINK_SPEED_100M_HD | ETH_LINK_SPEED_100M |
				ETH_LINK_SPEED_1G | ETH_LINK_SPEED_FIXED)) {
			num_speeds = -1;
			goto error_invalid_config;
		}
		if (*speeds & ETH_LINK_SPEED_10M_HD) {
			hw->phy.autoneg_advertised |= ADVERTISE_10_HALF;
			num_speeds++;
		}
		if (*speeds & ETH_LINK_SPEED_10M) {
			hw->phy.autoneg_advertised |= ADVERTISE_10_FULL;
			num_speeds++;
		}
		if (*speeds & ETH_LINK_SPEED_100M_HD) {
			hw->phy.autoneg_advertised |= ADVERTISE_100_HALF;
			num_speeds++;
		}
		if (*speeds & ETH_LINK_SPEED_100M) {
			hw->phy.autoneg_advertised |= ADVERTISE_100_FULL;
			num_speeds++;
		}
		if (*speeds & ETH_LINK_SPEED_1G) {
			hw->phy.autoneg_advertised |= ADVERTISE_1000_FULL;
			num_speeds++;
		}
		if (num_speeds == 0 || (!autoneg && (num_speeds > 1)))
			goto error_invalid_config;

		/* Set/reset the mac.autoneg based on the link speed,
		 * fixed or not
		 */
		if (!autoneg) {
			hw->mac.autoneg = 0;
			hw->mac.forced_speed_duplex =
					hw->phy.autoneg_advertised;
		} else {
			hw->mac.autoneg = 1;
		}
	}

	e1000_setup_link(hw);

	if (rte_intr_allow_others(intr_handle)) {
		/* check if lsc interrupt is enabled */
		if (dev->data->dev_conf.intr_conf.lsc != 0) {
			ret = eth_em_interrupt_setup(dev);
			if (ret) {
				PMD_INIT_LOG(ERR, "Unable to setup interrupts");
				em_dev_clear_queues(dev);
				return ret;
			}
		}
	} else {
		rte_intr_callback_unregister(intr_handle,
						eth_em_interrupt_handler,
						(void *)dev);
		if (dev->data->dev_conf.intr_conf.lsc != 0)
			PMD_INIT_LOG(INFO, "lsc won't enable because of"
				     " no intr multiplexn");
	}
	/* check if rxq interrupt is enabled */
	if (dev->data->dev_conf.intr_conf.rxq != 0)
		eth_em_rxq_interrupt_setup(dev);

	rte_intr_enable(intr_handle);

	adapter->stopped = 0;

	eth_em_rxtx_control(dev, true);
	eth_em_link_update(dev, 0);

	PMD_INIT_LOG(DEBUG, "<<");

	return 0;

error_invalid_config:
	PMD_INIT_LOG(ERR, "Invalid advertised speeds (%u) for port %u",
		     dev->data->dev_conf.link_speeds, dev->data->port_id);
	em_dev_clear_queues(dev);
	return -EINVAL;
}

/*********************************************************************
 *
 *  This routine disables all traffic on the adapter by issuing a
 *  global reset on the MAC.
 *
 **********************************************************************/
static void
eth_em_stop(struct rte_eth_dev *dev)
{
	struct rte_eth_link link;
	struct e1000_hw *hw = E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	struct rte_pci_device *pci_dev = RTE_ETH_DEV_TO_PCI(dev);
	struct rte_intr_handle *intr_handle = &pci_dev->intr_handle;

	eth_em_rxtx_control(dev, false);
	em_rxq_intr_disable(hw);
	em_lsc_intr_disable(hw);

	e1000_reset_hw(hw);
	if (hw->mac.type >= e1000_82544)
		E1000_WRITE_REG(hw, E1000_WUC, 0);

	/* Power down the phy. Needed to make the link go down */
	e1000_power_down_phy(hw);

	em_dev_clear_queues(dev);

	/* clear the recorded link status */
	memset(&link, 0, sizeof(link));
	rte_eth_linkstatus_set(dev, &link);

	if (!rte_intr_allow_others(intr_handle))
		/* resume to the default handler */
		rte_intr_callback_register(intr_handle,
					   eth_em_interrupt_handler,
					   (void *)dev);

	/* Clean datapath event and queue/vec mapping */
	rte_intr_efd_disable(intr_handle);
	if (intr_handle->intr_vec != NULL) {
		rte_free(intr_handle->intr_vec);
		intr_handle->intr_vec = NULL;
	}
}

static void
eth_em_close(struct rte_eth_dev *dev)
{
	struct e1000_hw *hw = E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	struct e1000_adapter *adapter =
		E1000_DEV_PRIVATE(dev->data->dev_private);

	eth_em_stop(dev);
	adapter->stopped = 1;
	em_dev_free_queues(dev);
	e1000_phy_hw_reset(hw);
	em_release_manageability(hw);
	em_hw_control_release(hw);
}

static int
em_get_rx_buffer_size(struct e1000_hw *hw)
{
	uint32_t rx_buf_size;

	rx_buf_size = ((E1000_READ_REG(hw, E1000_PBA) & UINT16_MAX) << 10);
	return rx_buf_size;
}

/*********************************************************************
 *
 *  Initialize the hardware
 *
 **********************************************************************/
static int
em_hardware_init(struct e1000_hw *hw)
{
	uint32_t rx_buf_size;
	int diag;

	/* Issue a global reset */
	e1000_reset_hw(hw);

	/* Let the firmware know the OS is in control */
	em_hw_control_acquire(hw);

	/*
	 * These parameters control the automatic generation (Tx) and
	 * response (Rx) to Ethernet PAUSE frames.
	 * - High water mark should allow for at least two standard size (1518)
	 *   frames to be received after sending an XOFF.
	 * - Low water mark works best when it is very near the high water mark.
	 *   This allows the receiver to restart by sending XON when it has
	 *   drained a bit. Here we use an arbitrary value of 1500 which will
	 *   restart after one full frame is pulled from the buffer. There
	 *   could be several smaller frames in the buffer and if so they will
	 *   not trigger the XON until their total number reduces the buffer
	 *   by 1500.
	 * - The pause time is fairly large at 1000 x 512ns = 512 usec.
	 */
	rx_buf_size = em_get_rx_buffer_size(hw);

	hw->fc.high_water = rx_buf_size - PMD_ROUNDUP(ETHER_MAX_LEN * 2, 1024);
	hw->fc.low_water = hw->fc.high_water - 1500;

	if (hw->mac.type == e1000_80003es2lan)
		hw->fc.pause_time = UINT16_MAX;
	else
		hw->fc.pause_time = EM_FC_PAUSE_TIME;

	hw->fc.send_xon = 1;

	/* Set Flow control, use the tunable location if sane */
	if (em_fc_setting <= e1000_fc_full)
		hw->fc.requested_mode = em_fc_setting;
	else
		hw->fc.requested_mode = e1000_fc_none;

	/* Workaround: no TX flow ctrl for PCH */
	if (hw->mac.type == e1000_pchlan)
		hw->fc.requested_mode = e1000_fc_rx_pause;

	/* Override - settings for PCH2LAN, ya its magic :) */
	if (hw->mac.type == e1000_pch2lan) {
		hw->fc.high_water = 0x5C20;
		hw->fc.low_water = 0x5048;
		hw->fc.pause_time = 0x0650;
		hw->fc.refresh_time = 0x0400;
	} else if (hw->mac.type == e1000_pch_lpt ||
		   hw->mac.type == e1000_pch_spt ||
		   hw->mac.type == e1000_pch_cnp) {
		hw->fc.requested_mode = e1000_fc_full;
	}

	diag = e1000_init_hw(hw);
	if (diag < 0)
		return diag;
	e1000_check_for_link(hw);
	return 0;
}

/* This function is based on em_update_stats_counters() in e1000/if_em.c */
static int
eth_em_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *rte_stats)
{
	struct e1000_hw *hw = E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	struct e1000_hw_stats *stats =
			E1000_DEV_PRIVATE_TO_STATS(dev->data->dev_private);
	int pause_frames;

	if(hw->phy.media_type == e1000_media_type_copper ||
			(E1000_READ_REG(hw, E1000_STATUS) & E1000_STATUS_LU)) {
		stats->symerrs += E1000_READ_REG(hw,E1000_SYMERRS);
		stats->sec += E1000_READ_REG(hw, E1000_SEC);
	}

	stats->crcerrs += E1000_READ_REG(hw, E1000_CRCERRS);
	stats->mpc += E1000_READ_REG(hw, E1000_MPC);
	stats->scc += E1000_READ_REG(hw, E1000_SCC);
	stats->ecol += E1000_READ_REG(hw, E1000_ECOL);

	stats->mcc += E1000_READ_REG(hw, E1000_MCC);
	stats->latecol += E1000_READ_REG(hw, E1000_LATECOL);
	stats->colc += E1000_READ_REG(hw, E1000_COLC);
	stats->dc += E1000_READ_REG(hw, E1000_DC);
	stats->rlec += E1000_READ_REG(hw, E1000_RLEC);
	stats->xonrxc += E1000_READ_REG(hw, E1000_XONRXC);
	stats->xontxc += E1000_READ_REG(hw, E1000_XONTXC);

	/*
	 * For watchdog management we need to know if we have been
	 * paused during the last interval, so capture that here.
	 */
	pause_frames = E1000_READ_REG(hw, E1000_XOFFRXC);
	stats->xoffrxc += pause_frames;
	stats->xofftxc += E1000_READ_REG(hw, E1000_XOFFTXC);
	stats->fcruc += E1000_READ_REG(hw, E1000_FCRUC);
	stats->prc64 += E1000_READ_REG(hw, E1000_PRC64);
	stats->prc127 += E1000_READ_REG(hw, E1000_PRC127);
	stats->prc255 += E1000_READ_REG(hw, E1000_PRC255);
	stats->prc511 += E1000_READ_REG(hw, E1000_PRC511);
	stats->prc1023 += E1000_READ_REG(hw, E1000_PRC1023);
	stats->prc1522 += E1000_READ_REG(hw, E1000_PRC1522);
	stats->gprc += E1000_READ_REG(hw, E1000_GPRC);
	stats->bprc += E1000_READ_REG(hw, E1000_BPRC);
	stats->mprc += E1000_READ_REG(hw, E1000_MPRC);
	stats->gptc += E1000_READ_REG(hw, E1000_GPTC);

	/*
	 * For the 64-bit byte counters the low dword must be read first.
	 * Both registers clear on the read of the high dword.
	 */

	stats->gorc += E1000_READ_REG(hw, E1000_GORCL);
	stats->gorc += ((uint64_t)E1000_READ_REG(hw, E1000_GORCH) << 32);
	stats->gotc += E1000_READ_REG(hw, E1000_GOTCL);
	stats->gotc += ((uint64_t)E1000_READ_REG(hw, E1000_GOTCH) << 32);

	stats->rnbc += E1000_READ_REG(hw, E1000_RNBC);
	stats->ruc += E1000_READ_REG(hw, E1000_RUC);
	stats->rfc += E1000_READ_REG(hw, E1000_RFC);
	stats->roc += E1000_READ_REG(hw, E1000_ROC);
	stats->rjc += E1000_READ_REG(hw, E1000_RJC);

	stats->tor += E1000_READ_REG(hw, E1000_TORH);
	stats->tot += E1000_READ_REG(hw, E1000_TOTH);

	stats->tpr += E1000_READ_REG(hw, E1000_TPR);
	stats->tpt += E1000_READ_REG(hw, E1000_TPT);
	stats->ptc64 += E1000_READ_REG(hw, E1000_PTC64);
	stats->ptc127 += E1000_READ_REG(hw, E1000_PTC127);
	stats->ptc255 += E1000_READ_REG(hw, E1000_PTC255);
	stats->ptc511 += E1000_READ_REG(hw, E1000_PTC511);
	stats->ptc1023 += E1000_READ_REG(hw, E1000_PTC1023);
	stats->ptc1522 += E1000_READ_REG(hw, E1000_PTC1522);
	stats->mptc += E1000_READ_REG(hw, E1000_MPTC);
	stats->bptc += E1000_READ_REG(hw, E1000_BPTC);

	/* Interrupt Counts */

	if (hw->mac.type >= e1000_82571) {
		stats->iac += E1000_READ_REG(hw, E1000_IAC);
		stats->icrxptc += E1000_READ_REG(hw, E1000_ICRXPTC);
		stats->icrxatc += E1000_READ_REG(hw, E1000_ICRXATC);
		stats->ictxptc += E1000_READ_REG(hw, E1000_ICTXPTC);
		stats->ictxatc += E1000_READ_REG(hw, E1000_ICTXATC);
		stats->ictxqec += E1000_READ_REG(hw, E1000_ICTXQEC);
		stats->ictxqmtc += E1000_READ_REG(hw, E1000_ICTXQMTC);
		stats->icrxdmtc += E1000_READ_REG(hw, E1000_ICRXDMTC);
		stats->icrxoc += E1000_READ_REG(hw, E1000_ICRXOC);
	}

	if (hw->mac.type >= e1000_82543) {
		stats->algnerrc += E1000_READ_REG(hw, E1000_ALGNERRC);
		stats->rxerrc += E1000_READ_REG(hw, E1000_RXERRC);
		stats->tncrs += E1000_READ_REG(hw, E1000_TNCRS);
		stats->cexterr += E1000_READ_REG(hw, E1000_CEXTERR);
		stats->tsctc += E1000_READ_REG(hw, E1000_TSCTC);
		stats->tsctfc += E1000_READ_REG(hw, E1000_TSCTFC);
	}

	if (rte_stats == NULL)
		return -EINVAL;

	/* Rx Errors */
	rte_stats->imissed = stats->mpc;
	rte_stats->ierrors = stats->crcerrs +
	                     stats->rlec + stats->ruc + stats->roc +
	                     stats->rxerrc + stats->algnerrc + stats->cexterr;

	/* Tx Errors */
	rte_stats->oerrors = stats->ecol + stats->latecol;

	rte_stats->ipackets = stats->gprc;
	rte_stats->opackets = stats->gptc;
	rte_stats->ibytes   = stats->gorc;
	rte_stats->obytes   = stats->gotc;
	return 0;
}

static void
eth_em_stats_reset(struct rte_eth_dev *dev)
{
	struct e1000_hw_stats *hw_stats =
			E1000_DEV_PRIVATE_TO_STATS(dev->data->dev_private);

	/* HW registers are cleared on read */
	eth_em_stats_get(dev, NULL);

	/* Reset software totals */
	memset(hw_stats, 0, sizeof(*hw_stats));
}

static int
eth_em_rx_queue_intr_enable(struct rte_eth_dev *dev, __rte_unused uint16_t queue_id)
{
	struct e1000_hw *hw = E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	struct rte_pci_device *pci_dev = RTE_ETH_DEV_TO_PCI(dev);
	struct rte_intr_handle *intr_handle = &pci_dev->intr_handle;

	em_rxq_intr_enable(hw);
	rte_intr_enable(intr_handle);

	return 0;
}

static int
eth_em_rx_queue_intr_disable(struct rte_eth_dev *dev, __rte_unused uint16_t queue_id)
{
	struct e1000_hw *hw = E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);

	em_rxq_intr_disable(hw);

	return 0;
}

uint32_t
em_get_max_pktlen(struct rte_eth_dev *dev)
{
	struct e1000_hw *hw = E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);

	switch (hw->mac.type) {
	case e1000_82571:
	case e1000_82572:
	case e1000_ich9lan:
	case e1000_ich10lan:
	case e1000_pch2lan:
	case e1000_pch_lpt:
	case e1000_pch_spt:
	case e1000_pch_cnp:
	case e1000_82574:
	case e1000_80003es2lan: /* 9K Jumbo Frame size */
	case e1000_82583:
		return 0x2412;
	case e1000_pchlan:
		return 0x1000;
	/* Adapters that do not support jumbo frames */
	case e1000_ich8lan:
		return ETHER_MAX_LEN;
	default:
		return MAX_JUMBO_FRAME_SIZE;
	}
}

static void
eth_em_infos_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info)
{
	struct e1000_hw *hw = E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);

	dev_info->min_rx_bufsize = 256; /* See BSIZE field of RCTL register. */
	dev_info->max_rx_pktlen = em_get_max_pktlen(dev);
	dev_info->max_mac_addrs = hw->mac.rar_entry_count;

	/*
	 * Starting with 631xESB hw supports 2 TX/RX queues per port.
	 * Unfortunatelly, all these nics have just one TX context.
	 * So we have few choises for TX:
	 * - Use just one TX queue.
	 * - Allow cksum offload only for one TX queue.
	 * - Don't allow TX cksum offload at all.
	 * For now, option #1 was chosen.
	 * To use second RX queue we have to use extended RX descriptor
	 * (Multiple Receive Queues are mutually exclusive with UDP
	 * fragmentation and are not supported when a legacy receive
	 * descriptor format is used).
	 * Which means separate RX routinies - as legacy nics (82540, 82545)
	 * don't support extended RXD.
	 * To avoid it we support just one RX queue for now (no RSS).
	 */

	dev_info->max_rx_queues = 1;
	dev_info->max_tx_queues = 1;

	dev_info->rx_queue_offload_capa = em_get_rx_queue_offloads_capa(dev);
	dev_info->rx_offload_capa = em_get_rx_port_offloads_capa(dev) |
				    dev_info->rx_queue_offload_capa;
	dev_info->tx_queue_offload_capa = em_get_tx_queue_offloads_capa(dev);
	dev_info->tx_offload_capa = em_get_tx_port_offloads_capa(dev) |
				    dev_info->tx_queue_offload_capa;

	dev_info->rx_desc_lim = (struct rte_eth_desc_lim) {
		.nb_max = E1000_MAX_RING_DESC,
		.nb_min = E1000_MIN_RING_DESC,
		.nb_align = EM_RXD_ALIGN,
	};

	dev_info->tx_desc_lim = (struct rte_eth_desc_lim) {
		.nb_max = E1000_MAX_RING_DESC,
		.nb_min = E1000_MIN_RING_DESC,
		.nb_align = EM_TXD_ALIGN,
		.nb_seg_max = EM_TX_MAX_SEG,
		.nb_mtu_seg_max = EM_TX_MAX_MTU_SEG,
	};

	dev_info->speed_capa = ETH_LINK_SPEED_10M_HD | ETH_LINK_SPEED_10M |
			ETH_LINK_SPEED_100M_HD | ETH_LINK_SPEED_100M |
			ETH_LINK_SPEED_1G;

	/* Preferred queue parameters */
	dev_info->default_rxportconf.nb_queues = 1;
	dev_info->default_txportconf.nb_queues = 1;
	dev_info->default_txportconf.ring_size = 256;
	dev_info->default_rxportconf.ring_size = 256;
}

/* return 0 means link status changed, -1 means not changed */
static int
eth_em_link_update(struct rte_eth_dev *dev, int wait_to_complete)
{
	struct e1000_hw *hw =
		E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	struct rte_eth_link link;
	int link_check, count;

	link_check = 0;
	hw->mac.get_link_status = 1;

	/* possible wait-to-complete in up to 9 seconds */
	for (count = 0; count < EM_LINK_UPDATE_CHECK_TIMEOUT; count ++) {
		/* Read the real link status */
		switch (hw->phy.media_type) {
		case e1000_media_type_copper:
			/* Do the work to read phy */
			e1000_check_for_link(hw);
			link_check = !hw->mac.get_link_status;
			break;

		case e1000_media_type_fiber:
			e1000_check_for_link(hw);
			link_check = (E1000_READ_REG(hw, E1000_STATUS) &
					E1000_STATUS_LU);
			break;

		case e1000_media_type_internal_serdes:
			e1000_check_for_link(hw);
			link_check = hw->mac.serdes_has_link;
			break;

		default:
			break;
		}
		if (link_check || wait_to_complete == 0)
			break;
		rte_delay_ms(EM_LINK_UPDATE_CHECK_INTERVAL);
	}
	memset(&link, 0, sizeof(link));

	/* Now we check if a transition has happened */
	if (link_check && (link.link_status == ETH_LINK_DOWN)) {
		uint16_t duplex, speed;
		hw->mac.ops.get_link_up_info(hw, &speed, &duplex);
		link.link_duplex = (duplex == FULL_DUPLEX) ?
				ETH_LINK_FULL_DUPLEX :
				ETH_LINK_HALF_DUPLEX;
		link.link_speed = speed;
		link.link_status = ETH_LINK_UP;
		link.link_autoneg = !(dev->data->dev_conf.link_speeds &
				ETH_LINK_SPEED_FIXED);
	} else if (!link_check && (link.link_status == ETH_LINK_UP)) {
		link.link_speed = ETH_SPEED_NUM_NONE;
		link.link_duplex = ETH_LINK_HALF_DUPLEX;
		link.link_status = ETH_LINK_DOWN;
		link.link_autoneg = ETH_LINK_FIXED;
	}

	return rte_eth_linkstatus_set(dev, &link);
}

/*
 * em_hw_control_acquire sets {CTRL_EXT|FWSM}:DRV_LOAD bit.
 * For ASF and Pass Through versions of f/w this means
 * that the driver is loaded. For AMT version type f/w
 * this means that the network i/f is open.
 */
static void
em_hw_control_acquire(struct e1000_hw *hw)
{
	uint32_t ctrl_ext, swsm;

	/* Let firmware know the driver has taken over */
	if (hw->mac.type == e1000_82573) {
		swsm = E1000_READ_REG(hw, E1000_SWSM);
		E1000_WRITE_REG(hw, E1000_SWSM, swsm | E1000_SWSM_DRV_LOAD);

	} else {
		ctrl_ext = E1000_READ_REG(hw, E1000_CTRL_EXT);
		E1000_WRITE_REG(hw, E1000_CTRL_EXT,
			ctrl_ext | E1000_CTRL_EXT_DRV_LOAD);
	}
}

/*
 * em_hw_control_release resets {CTRL_EXTT|FWSM}:DRV_LOAD bit.
 * For ASF and Pass Through versions of f/w this means that the
 * driver is no longer loaded. For AMT versions of the
 * f/w this means that the network i/f is closed.
 */
static void
em_hw_control_release(struct e1000_hw *hw)
{
	uint32_t ctrl_ext, swsm;

	/* Let firmware taken over control of h/w */
	if (hw->mac.type == e1000_82573) {
		swsm = E1000_READ_REG(hw, E1000_SWSM);
		E1000_WRITE_REG(hw, E1000_SWSM, swsm & ~E1000_SWSM_DRV_LOAD);
	} else {
		ctrl_ext = E1000_READ_REG(hw, E1000_CTRL_EXT);
		E1000_WRITE_REG(hw, E1000_CTRL_EXT,
			ctrl_ext & ~E1000_CTRL_EXT_DRV_LOAD);
	}
}

/*
 * Bit of a misnomer, what this really means is
 * to enable OS management of the system... aka
 * to disable special hardware management features.
 */
static void
em_init_manageability(struct e1000_hw *hw)
{
	if (e1000_enable_mng_pass_thru(hw)) {
		uint32_t manc2h = E1000_READ_REG(hw, E1000_MANC2H);
		uint32_t manc = E1000_READ_REG(hw, E1000_MANC);

		/* disable hardware interception of ARP */
		manc &= ~(E1000_MANC_ARP_EN);

		/* enable receiving management packets to the host */
		manc |= E1000_MANC_EN_MNG2HOST;
		manc2h |= 1 << 5;  /* Mng Port 623 */
		manc2h |= 1 << 6;  /* Mng Port 664 */
		E1000_WRITE_REG(hw, E1000_MANC2H, manc2h);
		E1000_WRITE_REG(hw, E1000_MANC, manc);
	}
}

/*
 * Give control back to hardware management
 * controller if there is one.
 */
static void
em_release_manageability(struct e1000_hw *hw)
{
	uint32_t manc;

	if (e1000_enable_mng_pass_thru(hw)) {
		manc = E1000_READ_REG(hw, E1000_MANC);

		/* re-enable hardware interception of ARP */
		manc |= E1000_MANC_ARP_EN;
		manc &= ~E1000_MANC_EN_MNG2HOST;

		E1000_WRITE_REG(hw, E1000_MANC, manc);
	}
}

static void
eth_em_promiscuous_enable(struct rte_eth_dev *dev)
{
	struct e1000_hw *hw =
		E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	uint32_t rctl;

	rctl = E1000_READ_REG(hw, E1000_RCTL);
	rctl |= (E1000_RCTL_UPE | E1000_RCTL_MPE);
	E1000_WRITE_REG(hw, E1000_RCTL, rctl);
}

static void
eth_em_promiscuous_disable(struct rte_eth_dev *dev)
{
	struct e1000_hw *hw =
		E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	uint32_t rctl;

	rctl = E1000_READ_REG(hw, E1000_RCTL);
	rctl &= ~(E1000_RCTL_UPE | E1000_RCTL_SBP);
	if (dev->data->all_multicast == 1)
		rctl |= E1000_RCTL_MPE;
	else
		rctl &= (~E1000_RCTL_MPE);
	E1000_WRITE_REG(hw, E1000_RCTL, rctl);
}

static void
eth_em_allmulticast_enable(struct rte_eth_dev *dev)
{
	struct e1000_hw *hw =
		E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	uint32_t rctl;

	rctl = E1000_READ_REG(hw, E1000_RCTL);
	rctl |= E1000_RCTL_MPE;
	E1000_WRITE_REG(hw, E1000_RCTL, rctl);
}

static void
eth_em_allmulticast_disable(struct rte_eth_dev *dev)
{
	struct e1000_hw *hw =
		E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	uint32_t rctl;

	if (dev->data->promiscuous == 1)
		return; /* must remain in all_multicast mode */
	rctl = E1000_READ_REG(hw, E1000_RCTL);
	rctl &= (~E1000_RCTL_MPE);
	E1000_WRITE_REG(hw, E1000_RCTL, rctl);
}

static int
eth_em_vlan_filter_set(struct rte_eth_dev *dev, uint16_t vlan_id, int on)
{
	struct e1000_hw *hw =
		E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	struct e1000_vfta * shadow_vfta =
		E1000_DEV_PRIVATE_TO_VFTA(dev->data->dev_private);
	uint32_t vfta;
	uint32_t vid_idx;
	uint32_t vid_bit;

	vid_idx = (uint32_t) ((vlan_id >> E1000_VFTA_ENTRY_SHIFT) &
			      E1000_VFTA_ENTRY_MASK);
	vid_bit = (uint32_t) (1 << (vlan_id & E1000_VFTA_ENTRY_BIT_SHIFT_MASK));
	vfta = E1000_READ_REG_ARRAY(hw, E1000_VFTA, vid_idx);
	if (on)
		vfta |= vid_bit;
	else
		vfta &= ~vid_bit;
	E1000_WRITE_REG_ARRAY(hw, E1000_VFTA, vid_idx, vfta);

	/* update local VFTA copy */
	shadow_vfta->vfta[vid_idx] = vfta;

	return 0;
}

static void
em_vlan_hw_filter_disable(struct rte_eth_dev *dev)
{
	struct e1000_hw *hw =
		E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	uint32_t reg;

	/* Filter Table Disable */
	reg = E1000_READ_REG(hw, E1000_RCTL);
	reg &= ~E1000_RCTL_CFIEN;
	reg &= ~E1000_RCTL_VFE;
	E1000_WRITE_REG(hw, E1000_RCTL, reg);
}

static void
em_vlan_hw_filter_enable(struct rte_eth_dev *dev)
{
	struct e1000_hw *hw =
		E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	struct e1000_vfta * shadow_vfta =
		E1000_DEV_PRIVATE_TO_VFTA(dev->data->dev_private);
	uint32_t reg;
	int i;

	/* Filter Table Enable, CFI not used for packet acceptance */
	reg = E1000_READ_REG(hw, E1000_RCTL);
	reg &= ~E1000_RCTL_CFIEN;
	reg |= E1000_RCTL_VFE;
	E1000_WRITE_REG(hw, E1000_RCTL, reg);

	/* restore vfta from local copy */
	for (i = 0; i < IGB_VFTA_SIZE; i++)
		E1000_WRITE_REG_ARRAY(hw, E1000_VFTA, i, shadow_vfta->vfta[i]);
}

static void
em_vlan_hw_strip_disable(struct rte_eth_dev *dev)
{
	struct e1000_hw *hw =
		E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	uint32_t reg;

	/* VLAN Mode Disable */
	reg = E1000_READ_REG(hw, E1000_CTRL);
	reg &= ~E1000_CTRL_VME;
	E1000_WRITE_REG(hw, E1000_CTRL, reg);

}

static void
em_vlan_hw_strip_enable(struct rte_eth_dev *dev)
{
	struct e1000_hw *hw =
		E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	uint32_t reg;

	/* VLAN Mode Enable */
	reg = E1000_READ_REG(hw, E1000_CTRL);
	reg |= E1000_CTRL_VME;
	E1000_WRITE_REG(hw, E1000_CTRL, reg);
}

static int
eth_em_vlan_offload_set(struct rte_eth_dev *dev, int mask)
{
	struct rte_eth_rxmode *rxmode;

	rxmode = &dev->data->dev_conf.rxmode;
	if(mask & ETH_VLAN_STRIP_MASK){
		if (rxmode->offloads & DEV_RX_OFFLOAD_VLAN_STRIP)
			em_vlan_hw_strip_enable(dev);
		else
			em_vlan_hw_strip_disable(dev);
	}

	if(mask & ETH_VLAN_FILTER_MASK){
		if (rxmode->offloads & DEV_RX_OFFLOAD_VLAN_FILTER)
			em_vlan_hw_filter_enable(dev);
		else
			em_vlan_hw_filter_disable(dev);
	}

	return 0;
}

/*
 * It enables the interrupt mask and then enable the interrupt.
 *
 * @param dev
 *  Pointer to struct rte_eth_dev.
 *
 * @return
 *  - On success, zero.
 *  - On failure, a negative value.
 */
static int
eth_em_interrupt_setup(struct rte_eth_dev *dev)
{
	uint32_t regval;
	struct e1000_hw *hw =
		E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);

	/* clear interrupt */
	E1000_READ_REG(hw, E1000_ICR);
	regval = E1000_READ_REG(hw, E1000_IMS);
	E1000_WRITE_REG(hw, E1000_IMS,
			regval | E1000_ICR_LSC | E1000_ICR_OTHER);
	return 0;
}

/*
 * It clears the interrupt causes and enables the interrupt.
 * It will be called once only during nic initialized.
 *
 * @param dev
 *  Pointer to struct rte_eth_dev.
 *
 * @return
 *  - On success, zero.
 *  - On failure, a negative value.
 */
static int
eth_em_rxq_interrupt_setup(struct rte_eth_dev *dev)
{
	struct e1000_hw *hw =
	E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);

	E1000_READ_REG(hw, E1000_ICR);
	em_rxq_intr_enable(hw);
	return 0;
}

/*
 * It enable receive packet interrupt.
 * @param hw
 * Pointer to struct e1000_hw
 *
 * @return
 */
static void
em_rxq_intr_enable(struct e1000_hw *hw)
{
	E1000_WRITE_REG(hw, E1000_IMS, E1000_IMS_RXT0);
	E1000_WRITE_FLUSH(hw);
}

/*
 * It disabled lsc interrupt.
 * @param hw
 * Pointer to struct e1000_hw
 *
 * @return
 */
static void
em_lsc_intr_disable(struct e1000_hw *hw)
{
	E1000_WRITE_REG(hw, E1000_IMC, E1000_IMS_LSC | E1000_IMS_OTHER);
	E1000_WRITE_FLUSH(hw);
}

/*
 * It disabled receive packet interrupt.
 * @param hw
 * Pointer to struct e1000_hw
 *
 * @return
 */
static void
em_rxq_intr_disable(struct e1000_hw *hw)
{
	E1000_READ_REG(hw, E1000_ICR);
	E1000_WRITE_REG(hw, E1000_IMC, E1000_IMS_RXT0);
	E1000_WRITE_FLUSH(hw);
}

/*
 * It reads ICR and gets interrupt causes, check it and set a bit flag
 * to update link status.
 *
 * @param dev
 *  Pointer to struct rte_eth_dev.
 *
 * @return
 *  - On success, zero.
 *  - On failure, a negative value.
 */
static int
eth_em_interrupt_get_status(struct rte_eth_dev *dev)
{
	uint32_t icr;
	struct e1000_hw *hw =
		E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	struct e1000_interrupt *intr =
		E1000_DEV_PRIVATE_TO_INTR(dev->data->dev_private);

	/* read-on-clear nic registers here */
	icr = E1000_READ_REG(hw, E1000_ICR);
	if (icr & E1000_ICR_LSC) {
		intr->flags |= E1000_FLAG_NEED_LINK_UPDATE;
	}

	return 0;
}

/*
 * It executes link_update after knowing an interrupt is prsent.
 *
 * @param dev
 *  Pointer to struct rte_eth_dev.
 *
 * @return
 *  - On success, zero.
 *  - On failure, a negative value.
 */
static int
eth_em_interrupt_action(struct rte_eth_dev *dev,
			struct rte_intr_handle *intr_handle)
{
	struct rte_pci_device *pci_dev = RTE_ETH_DEV_TO_PCI(dev);
	struct e1000_hw *hw =
		E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	struct e1000_interrupt *intr =
		E1000_DEV_PRIVATE_TO_INTR(dev->data->dev_private);
	struct rte_eth_link link;
	int ret;

	if (!(intr->flags & E1000_FLAG_NEED_LINK_UPDATE))
		return -1;

	intr->flags &= ~E1000_FLAG_NEED_LINK_UPDATE;
	rte_intr_enable(intr_handle);

	/* set get_link_status to check register later */
	hw->mac.get_link_status = 1;
	ret = eth_em_link_update(dev, 0);

	/* check if link has changed */
	if (ret < 0)
		return 0;

	rte_eth_linkstatus_get(dev, &link);

	if (link.link_status) {
		PMD_INIT_LOG(INFO, " Port %d: Link Up - speed %u Mbps - %s",
			     dev->data->port_id, link.link_speed,
			     link.link_duplex == ETH_LINK_FULL_DUPLEX ?
			     "full-duplex" : "half-duplex");
	} else {
		PMD_INIT_LOG(INFO, " Port %d: Link Down", dev->data->port_id);
	}
	PMD_INIT_LOG(DEBUG, "PCI Address: %04d:%02d:%02d:%d",
		     pci_dev->addr.domain, pci_dev->addr.bus,
		     pci_dev->addr.devid, pci_dev->addr.function);

	return 0;
}

/**
 * Interrupt handler which shall be registered at first.
 *
 * @param handle
 *  Pointer to interrupt handle.
 * @param param
 *  The address of parameter (struct rte_eth_dev *) regsitered before.
 *
 * @return
 *  void
 */
static void
eth_em_interrupt_handler(void *param)
{
	struct rte_eth_dev *dev = (struct rte_eth_dev *)param;

	eth_em_interrupt_get_status(dev);
	eth_em_interrupt_action(dev, dev->intr_handle);
	_rte_eth_dev_callback_process(dev, RTE_ETH_EVENT_INTR_LSC, NULL);
}

static int
eth_em_led_on(struct rte_eth_dev *dev)
{
	struct e1000_hw *hw;

	hw = E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	return e1000_led_on(hw) == E1000_SUCCESS ? 0 : -ENOTSUP;
}

static int
eth_em_led_off(struct rte_eth_dev *dev)
{
	struct e1000_hw *hw;

	hw = E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	return e1000_led_off(hw) == E1000_SUCCESS ? 0 : -ENOTSUP;
}

static int
eth_em_flow_ctrl_get(struct rte_eth_dev *dev, struct rte_eth_fc_conf *fc_conf)
{
	struct e1000_hw *hw;
	uint32_t ctrl;
	int tx_pause;
	int rx_pause;

	hw = E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	fc_conf->pause_time = hw->fc.pause_time;
	fc_conf->high_water = hw->fc.high_water;
	fc_conf->low_water = hw->fc.low_water;
	fc_conf->send_xon = hw->fc.send_xon;
	fc_conf->autoneg = hw->mac.autoneg;

	/*
	 * Return rx_pause and tx_pause status according to actual setting of
	 * the TFCE and RFCE bits in the CTRL register.
	 */
	ctrl = E1000_READ_REG(hw, E1000_CTRL);
	if (ctrl & E1000_CTRL_TFCE)
		tx_pause = 1;
	else
		tx_pause = 0;

	if (ctrl & E1000_CTRL_RFCE)
		rx_pause = 1;
	else
		rx_pause = 0;

	if (rx_pause && tx_pause)
		fc_conf->mode = RTE_FC_FULL;
	else if (rx_pause)
		fc_conf->mode = RTE_FC_RX_PAUSE;
	else if (tx_pause)
		fc_conf->mode = RTE_FC_TX_PAUSE;
	else
		fc_conf->mode = RTE_FC_NONE;

	return 0;
}

static int
eth_em_flow_ctrl_set(struct rte_eth_dev *dev, struct rte_eth_fc_conf *fc_conf)
{
	struct e1000_hw *hw;
	int err;
	enum e1000_fc_mode rte_fcmode_2_e1000_fcmode[] = {
		e1000_fc_none,
		e1000_fc_rx_pause,
		e1000_fc_tx_pause,
		e1000_fc_full
	};
	uint32_t rx_buf_size;
	uint32_t max_high_water;
	uint32_t rctl;

	hw = E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	if (fc_conf->autoneg != hw->mac.autoneg)
		return -ENOTSUP;
	rx_buf_size = em_get_rx_buffer_size(hw);
	PMD_INIT_LOG(DEBUG, "Rx packet buffer size = 0x%x", rx_buf_size);

	/* At least reserve one Ethernet frame for watermark */
	max_high_water = rx_buf_size - ETHER_MAX_LEN;
	if ((fc_conf->high_water > max_high_water) ||
	    (fc_conf->high_water < fc_conf->low_water)) {
		PMD_INIT_LOG(ERR, "e1000 incorrect high/low water value");
		PMD_INIT_LOG(ERR, "high water must <= 0x%x", max_high_water);
		return -EINVAL;
	}

	hw->fc.requested_mode = rte_fcmode_2_e1000_fcmode[fc_conf->mode];
	hw->fc.pause_time     = fc_conf->pause_time;
	hw->fc.high_water     = fc_conf->high_water;
	hw->fc.low_water      = fc_conf->low_water;
	hw->fc.send_xon	      = fc_conf->send_xon;

	err = e1000_setup_link_generic(hw);
	if (err == E1000_SUCCESS) {

		/* check if we want to forward MAC frames - driver doesn't have native
		 * capability to do that, so we'll write the registers ourselves */

		rctl = E1000_READ_REG(hw, E1000_RCTL);

		/* set or clear MFLCN.PMCF bit depending on configuration */
		if (fc_conf->mac_ctrl_frame_fwd != 0)
			rctl |= E1000_RCTL_PMCF;
		else
			rctl &= ~E1000_RCTL_PMCF;

		E1000_WRITE_REG(hw, E1000_RCTL, rctl);
		E1000_WRITE_FLUSH(hw);

		return 0;
	}

	PMD_INIT_LOG(ERR, "e1000_setup_link_generic = 0x%x", err);
	return -EIO;
}

static int
eth_em_rar_set(struct rte_eth_dev *dev, struct ether_addr *mac_addr,
		uint32_t index, __rte_unused uint32_t pool)
{
	struct e1000_hw *hw = E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);

	return e1000_rar_set(hw, mac_addr->addr_bytes, index);
}

static void
eth_em_rar_clear(struct rte_eth_dev *dev, uint32_t index)
{
	uint8_t addr[ETHER_ADDR_LEN];
	struct e1000_hw *hw = E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);

	memset(addr, 0, sizeof(addr));

	e1000_rar_set(hw, addr, index);
}

static int
eth_em_default_mac_addr_set(struct rte_eth_dev *dev,
			    struct ether_addr *addr)
{
	eth_em_rar_clear(dev, 0);

	return eth_em_rar_set(dev, (void *)addr, 0, 0);
}

static int
eth_em_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
{
	struct rte_eth_dev_info dev_info;
	struct e1000_hw *hw;
	uint32_t frame_size;
	uint32_t rctl;

	eth_em_infos_get(dev, &dev_info);
	frame_size = mtu + ETHER_HDR_LEN + ETHER_CRC_LEN + VLAN_TAG_SIZE;

	/* check that mtu is within the allowed range */
	if ((mtu < ETHER_MIN_MTU) || (frame_size > dev_info.max_rx_pktlen))
		return -EINVAL;

	/* refuse mtu that requires the support of scattered packets when this
	 * feature has not been enabled before. */
	if (!dev->data->scattered_rx &&
	    frame_size > dev->data->min_rx_buf_size - RTE_PKTMBUF_HEADROOM)
		return -EINVAL;

	hw = E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	rctl = E1000_READ_REG(hw, E1000_RCTL);

	/* switch to jumbo mode if needed */
	if (frame_size > ETHER_MAX_LEN) {
		dev->data->dev_conf.rxmode.offloads |=
			DEV_RX_OFFLOAD_JUMBO_FRAME;
		rctl |= E1000_RCTL_LPE;
	} else {
		dev->data->dev_conf.rxmode.offloads &=
			~DEV_RX_OFFLOAD_JUMBO_FRAME;
		rctl &= ~E1000_RCTL_LPE;
	}
	E1000_WRITE_REG(hw, E1000_RCTL, rctl);

	/* update max frame size */
	dev->data->dev_conf.rxmode.max_rx_pkt_len = frame_size;
	return 0;
}

static int
eth_em_set_mc_addr_list(struct rte_eth_dev *dev,
			struct ether_addr *mc_addr_set,
			uint32_t nb_mc_addr)
{
	struct e1000_hw *hw;

	hw = E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
	e1000_update_mc_addr_list(hw, (u8 *)mc_addr_set, nb_mc_addr);
	return 0;
}

RTE_PMD_REGISTER_PCI(net_e1000_em, rte_em_pmd);
RTE_PMD_REGISTER_PCI_TABLE(net_e1000_em, pci_id_em_map);
RTE_PMD_REGISTER_KMOD_DEP(net_e1000_em, "* igb_uio | uio_pci_generic | vfio-pci");

/* see e1000_logs.c */
RTE_INIT(igb_init_log)
{
	e1000_igb_init_log();
}