X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fenic%2Fenic_ethdev.c;h=6a3580fefd1a723f94a42af031b616c9c8947372;hb=3c334fcd9e565258667ec052550ab023d0fc9adb;hp=2a289b6a47e0e882ab33d562b7d7c5d05f8c308b;hpb=0f872d31295df39cedf9edfe134f48f3fdcefcbf;p=dpdk.git

diff --git a/drivers/net/enic/enic_ethdev.c b/drivers/net/enic/enic_ethdev.c
index 2a289b6a47..6a3580fefd 100644
--- a/drivers/net/enic/enic_ethdev.c
+++ b/drivers/net/enic/enic_ethdev.c
@@ -11,6 +11,7 @@
 #include <rte_bus_pci.h>
 #include <rte_ethdev_driver.h>
 #include <rte_ethdev_pci.h>
+#include <rte_kvargs.h>
 #include <rte_string_fns.h>
 
 #include "vnic_intr.h"
@@ -20,49 +21,55 @@
 #include "vnic_enet.h"
 #include "enic.h"
 
-int enicpmd_logtype_init;
-int enicpmd_logtype_flow;
-
-#define PMD_INIT_LOG(level, fmt, args...) \
-	rte_log(RTE_LOG_ ## level, enicpmd_logtype_init, \
-		"%s" fmt "\n", __func__, ##args)
-
-#define ENICPMD_FUNC_TRACE() PMD_INIT_LOG(DEBUG, " >>")
-
 /*
  * The set of PCI devices this driver supports
  */
 #define CISCO_PCI_VENDOR_ID 0x1137
 static const struct rte_pci_id pci_id_enic_map[] = {
-	{ RTE_PCI_DEVICE(CISCO_PCI_VENDOR_ID, PCI_DEVICE_ID_CISCO_VIC_ENET) },
-	{ RTE_PCI_DEVICE(CISCO_PCI_VENDOR_ID, PCI_DEVICE_ID_CISCO_VIC_ENET_VF) },
+	{RTE_PCI_DEVICE(CISCO_PCI_VENDOR_ID, PCI_DEVICE_ID_CISCO_VIC_ENET)},
+	{RTE_PCI_DEVICE(CISCO_PCI_VENDOR_ID, PCI_DEVICE_ID_CISCO_VIC_ENET_VF)},
+	{RTE_PCI_DEVICE(CISCO_PCI_VENDOR_ID, PCI_DEVICE_ID_CISCO_VIC_ENET_SN)},
 	{.vendor_id = 0, /* sentinel */},
 };
 
-#define ENIC_TX_OFFLOAD_CAPA (			\
-		DEV_TX_OFFLOAD_VLAN_INSERT |	\
-		DEV_TX_OFFLOAD_IPV4_CKSUM  |	\
-		DEV_TX_OFFLOAD_UDP_CKSUM   |	\
-		DEV_TX_OFFLOAD_TCP_CKSUM   |	\
-		DEV_TX_OFFLOAD_TCP_TSO)
+/* Supported link speeds of production VIC models */
+static const struct vic_speed_capa {
+	uint16_t sub_devid;
+	uint32_t capa;
+} vic_speed_capa_map[] = {
+	{ 0x0043, ETH_LINK_SPEED_10G }, /* VIC */
+	{ 0x0047, ETH_LINK_SPEED_10G }, /* P81E PCIe */
+	{ 0x0048, ETH_LINK_SPEED_10G }, /* M81KR Mezz */
+	{ 0x004f, ETH_LINK_SPEED_10G }, /* 1280 Mezz */
+	{ 0x0084, ETH_LINK_SPEED_10G }, /* 1240 MLOM */
+	{ 0x0085, ETH_LINK_SPEED_10G }, /* 1225 PCIe */
+	{ 0x00cd, ETH_LINK_SPEED_10G | ETH_LINK_SPEED_40G }, /* 1285 PCIe */
+	{ 0x00ce, ETH_LINK_SPEED_10G }, /* 1225T PCIe */
+	{ 0x012a, ETH_LINK_SPEED_40G }, /* M4308 */
+	{ 0x012c, ETH_LINK_SPEED_10G | ETH_LINK_SPEED_40G }, /* 1340 MLOM */
+	{ 0x012e, ETH_LINK_SPEED_10G }, /* 1227 PCIe */
+	{ 0x0137, ETH_LINK_SPEED_10G | ETH_LINK_SPEED_40G }, /* 1380 Mezz */
+	{ 0x014d, ETH_LINK_SPEED_10G | ETH_LINK_SPEED_40G }, /* 1385 PCIe */
+	{ 0x015d, ETH_LINK_SPEED_10G | ETH_LINK_SPEED_40G }, /* 1387 MLOM */
+	{ 0x0215, ETH_LINK_SPEED_10G | ETH_LINK_SPEED_25G |
+		  ETH_LINK_SPEED_40G }, /* 1440 Mezz */
+	{ 0x0216, ETH_LINK_SPEED_10G | ETH_LINK_SPEED_25G |
+		  ETH_LINK_SPEED_40G }, /* 1480 MLOM */
+	{ 0x0217, ETH_LINK_SPEED_10G | ETH_LINK_SPEED_25G }, /* 1455 PCIe */
+	{ 0x0218, ETH_LINK_SPEED_10G | ETH_LINK_SPEED_25G }, /* 1457 MLOM */
+	{ 0x0219, ETH_LINK_SPEED_40G }, /* 1485 PCIe */
+	{ 0x021a, ETH_LINK_SPEED_40G }, /* 1487 MLOM */
+	{ 0x024a, ETH_LINK_SPEED_40G | ETH_LINK_SPEED_100G }, /* 1495 PCIe */
+	{ 0x024b, ETH_LINK_SPEED_40G | ETH_LINK_SPEED_100G }, /* 1497 MLOM */
+	{ 0, 0 }, /* End marker */
+};
 
-#define ENIC_RX_OFFLOAD_CAPA (			\
-		DEV_RX_OFFLOAD_VLAN_STRIP |	\
-		DEV_RX_OFFLOAD_IPV4_CKSUM |	\
-		DEV_RX_OFFLOAD_UDP_CKSUM  |	\
-		DEV_RX_OFFLOAD_TCP_CKSUM)
+#define ENIC_DEVARG_DISABLE_OVERLAY "disable-overlay"
+#define ENIC_DEVARG_ENABLE_AVX2_RX "enable-avx2-rx"
+#define ENIC_DEVARG_GENEVE_OPT "geneve-opt"
+#define ENIC_DEVARG_IG_VLAN_REWRITE "ig-vlan-rewrite"
 
-RTE_INIT(enicpmd_init_log);
-static void
-enicpmd_init_log(void)
-{
-	enicpmd_logtype_init = rte_log_register("pmd.net.enic.init");
-	if (enicpmd_logtype_init >= 0)
-		rte_log_set_level(enicpmd_logtype_init, RTE_LOG_NOTICE);
-	enicpmd_logtype_flow = rte_log_register("pmd.net.enic.flow");
-	if (enicpmd_logtype_flow >= 0)
-		rte_log_set_level(enicpmd_logtype_flow, RTE_LOG_NOTICE);
-}
+RTE_LOG_REGISTER(enic_pmd_logtype, pmd.net.enic, INFO);
 
 static int
 enicpmd_fdir_ctrl_func(struct rte_eth_dev *eth_dev,
@@ -115,15 +122,25 @@ enicpmd_dev_filter_ctrl(struct rte_eth_dev *dev,
 		     enum rte_filter_op filter_op,
 		     void *arg)
 {
+	struct enic *enic = pmd_priv(dev);
 	int ret = 0;
 
 	ENICPMD_FUNC_TRACE();
 
+	/*
+	 * Currently, when Geneve with options offload is enabled, host
+	 * cannot insert match-action rules.
+	 */
+	if (enic->geneve_opt_enabled)
+		return -ENOTSUP;
 	switch (filter_type) {
 	case RTE_ETH_FILTER_GENERIC:
 		if (filter_op != RTE_ETH_FILTER_GET)
 			return -EINVAL;
-		*(const void **)arg = &enic_flow_ops;
+		if (enic->flow_filter_mode == FILTER_FLOWMAN)
+			*(const void **)arg = &enic_fm_flow_ops;
+		else
+			*(const void **)arg = &enic_flow_ops;
 		break;
 	case RTE_ETH_FILTER_FDIR:
 		ret = enicpmd_fdir_ctrl_func(dev, filter_op, arg);
@@ -194,17 +211,21 @@ static int enicpmd_dev_tx_queue_setup(struct rte_eth_dev *eth_dev,
 	uint16_t queue_idx,
 	uint16_t nb_desc,
 	unsigned int socket_id,
-	__rte_unused const struct rte_eth_txconf *tx_conf)
+	const struct rte_eth_txconf *tx_conf)
 {
 	int ret;
 	struct enic *enic = pmd_priv(eth_dev);
+	struct vnic_wq *wq;
 
 	if (rte_eal_process_type() != RTE_PROC_PRIMARY)
 		return -E_RTE_SECONDARY;
 
 	ENICPMD_FUNC_TRACE();
 	RTE_ASSERT(queue_idx < enic->conf_wq_count);
-	eth_dev->data->tx_queues[queue_idx] = (void *)&enic->wq[queue_idx];
+	wq = &enic->wq[queue_idx];
+	wq->offloads = tx_conf->offloads |
+		eth_dev->data->dev_conf.txmode.offloads;
+	eth_dev->data->tx_queues[queue_idx] = (void *)wq;
 
 	ret = enic_alloc_wq(enic, queue_idx, socket_id, nb_desc);
 	if (ret) {
@@ -377,6 +398,11 @@ static int enicpmd_dev_configure(struct rte_eth_dev *eth_dev)
 		return ret;
 	}
 
+	if (eth_dev->data->dev_conf.rxmode.mq_mode & ETH_MQ_RX_RSS_FLAG)
+		eth_dev->data->dev_conf.rxmode.offloads |=
+			DEV_RX_OFFLOAD_RSS_HASH;
+
+	enic->mc_count = 0;
 	enic->hw_ip_checksum = !!(eth_dev->data->dev_conf.rxmode.offloads &
 				  DEV_RX_OFFLOAD_CHECKSUM);
 	/* All vlan offload masks to apply the current settings */
@@ -423,10 +449,9 @@ static void enicpmd_dev_stop(struct rte_eth_dev *eth_dev)
 
 	ENICPMD_FUNC_TRACE();
 	enic_disable(enic);
+
 	memset(&link, 0, sizeof(link));
-	rte_atomic64_cmpset((uint64_t *)&eth_dev->data->dev_link,
-		*(uint64_t *)&eth_dev->data->dev_link,
-		*(uint64_t *)&link);
+	rte_eth_linkstatus_set(eth_dev, &link);
 }
 
 /*
@@ -443,10 +468,8 @@ static void enicpmd_dev_close(struct rte_eth_dev *eth_dev)
 static int enicpmd_dev_link_update(struct rte_eth_dev *eth_dev,
 	__rte_unused int wait_to_complete)
 {
-	struct enic *enic = pmd_priv(eth_dev);
-
 	ENICPMD_FUNC_TRACE();
-	return enic_link_update(enic);
+	return enic_link_update(eth_dev);
 }
 
 static int enicpmd_dev_stats_get(struct rte_eth_dev *eth_dev,
@@ -458,21 +481,44 @@ static int enicpmd_dev_stats_get(struct rte_eth_dev *eth_dev,
 	return enic_dev_stats_get(enic, stats);
 }
 
-static void enicpmd_dev_stats_reset(struct rte_eth_dev *eth_dev)
+static int enicpmd_dev_stats_reset(struct rte_eth_dev *eth_dev)
 {
 	struct enic *enic = pmd_priv(eth_dev);
 
 	ENICPMD_FUNC_TRACE();
-	enic_dev_stats_clear(enic);
+	return enic_dev_stats_clear(enic);
 }
 
-static void enicpmd_dev_info_get(struct rte_eth_dev *eth_dev,
+static uint32_t speed_capa_from_pci_id(struct rte_eth_dev *eth_dev)
+{
+	const struct vic_speed_capa *m;
+	struct rte_pci_device *pdev;
+	uint16_t id;
+
+	pdev = RTE_ETH_DEV_TO_PCI(eth_dev);
+	id = pdev->id.subsystem_device_id;
+	for (m = vic_speed_capa_map; m->sub_devid != 0; m++) {
+		if (m->sub_devid == id)
+			return m->capa;
+	}
+	/* 1300 and later models are at least 40G */
+	if (id >= 0x0100)
+		return ETH_LINK_SPEED_40G;
+	/* VFs have subsystem id 0, check device id */
+	if (id == 0) {
+		/* Newer VF implies at least 40G model */
+		if (pdev->id.device_id == PCI_DEVICE_ID_CISCO_VIC_ENET_SN)
+			return ETH_LINK_SPEED_40G;
+	}
+	return ETH_LINK_SPEED_10G;
+}
+
+static int enicpmd_dev_info_get(struct rte_eth_dev *eth_dev,
 	struct rte_eth_dev_info *device_info)
 {
 	struct enic *enic = pmd_priv(eth_dev);
 
 	ENICPMD_FUNC_TRACE();
-	device_info->pci_dev = RTE_ETH_DEV_TO_PCI(eth_dev);
 	/* Scattered Rx uses two receive queues per rx queue exposed to dpdk */
 	device_info->max_rx_queues = enic->conf_rq_count / 2;
 	device_info->max_tx_queues = enic->conf_wq_count;
@@ -485,15 +531,45 @@ static void enicpmd_dev_info_get(struct rte_eth_dev *eth_dev,
 	 * ignoring vNIC mtu.
 	 */
 	device_info->max_rx_pktlen = enic_mtu_to_max_rx_pktlen(enic->max_mtu);
-	device_info->max_mac_addrs = ENIC_MAX_MAC_ADDR;
-	device_info->rx_offload_capa = ENIC_RX_OFFLOAD_CAPA;
-	device_info->tx_offload_capa = ENIC_TX_OFFLOAD_CAPA;
+	device_info->max_mac_addrs = ENIC_UNICAST_PERFECT_FILTERS;
+	device_info->min_mtu = ENIC_MIN_MTU;
+	device_info->max_mtu = enic->max_mtu;
+	device_info->rx_offload_capa = enic->rx_offload_capa;
+	device_info->tx_offload_capa = enic->tx_offload_capa;
+	device_info->tx_queue_offload_capa = enic->tx_queue_offload_capa;
 	device_info->default_rxconf = (struct rte_eth_rxconf) {
 		.rx_free_thresh = ENIC_DEFAULT_RX_FREE_THRESH
 	};
 	device_info->reta_size = enic->reta_size;
 	device_info->hash_key_size = enic->hash_key_size;
 	device_info->flow_type_rss_offloads = enic->flow_type_rss_offloads;
+	device_info->rx_desc_lim = (struct rte_eth_desc_lim) {
+		.nb_max = enic->config.rq_desc_count,
+		.nb_min = ENIC_MIN_RQ_DESCS,
+		.nb_align = ENIC_ALIGN_DESCS,
+	};
+	device_info->tx_desc_lim = (struct rte_eth_desc_lim) {
+		.nb_max = enic->config.wq_desc_count,
+		.nb_min = ENIC_MIN_WQ_DESCS,
+		.nb_align = ENIC_ALIGN_DESCS,
+		.nb_seg_max = ENIC_TX_XMIT_MAX,
+		.nb_mtu_seg_max = ENIC_NON_TSO_MAX_DESC,
+	};
+	device_info->default_rxportconf = (struct rte_eth_dev_portconf) {
+		.burst_size = ENIC_DEFAULT_RX_BURST,
+		.ring_size = RTE_MIN(device_info->rx_desc_lim.nb_max,
+			ENIC_DEFAULT_RX_RING_SIZE),
+		.nb_queues = ENIC_DEFAULT_RX_RINGS,
+	};
+	device_info->default_txportconf = (struct rte_eth_dev_portconf) {
+		.burst_size = ENIC_DEFAULT_TX_BURST,
+		.ring_size = RTE_MIN(device_info->tx_desc_lim.nb_max,
+			ENIC_DEFAULT_TX_RING_SIZE),
+		.nb_queues = ENIC_DEFAULT_TX_RINGS,
+	};
+	device_info->speed_capa = speed_capa_from_pci_id(eth_dev);
+
+	return 0;
 }
 
 static const uint32_t *enicpmd_dev_supported_ptypes_get(struct rte_eth_dev *dev)
@@ -509,63 +585,108 @@ static const uint32_t *enicpmd_dev_supported_ptypes_get(struct rte_eth_dev *dev)
 		RTE_PTYPE_L4_NONFRAG,
 		RTE_PTYPE_UNKNOWN
 	};
+	static const uint32_t ptypes_overlay[] = {
+		RTE_PTYPE_L2_ETHER,
+		RTE_PTYPE_L2_ETHER_VLAN,
+		RTE_PTYPE_L3_IPV4_EXT_UNKNOWN,
+		RTE_PTYPE_L3_IPV6_EXT_UNKNOWN,
+		RTE_PTYPE_L4_TCP,
+		RTE_PTYPE_L4_UDP,
+		RTE_PTYPE_L4_FRAG,
+		RTE_PTYPE_L4_NONFRAG,
+		RTE_PTYPE_TUNNEL_GRENAT,
+		RTE_PTYPE_INNER_L2_ETHER,
+		RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN,
+		RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN,
+		RTE_PTYPE_INNER_L4_TCP,
+		RTE_PTYPE_INNER_L4_UDP,
+		RTE_PTYPE_INNER_L4_FRAG,
+		RTE_PTYPE_INNER_L4_NONFRAG,
+		RTE_PTYPE_UNKNOWN
+	};
 
-	if (dev->rx_pkt_burst == enic_recv_pkts)
-		return ptypes;
+	if (dev->rx_pkt_burst != enic_dummy_recv_pkts &&
+	    dev->rx_pkt_burst != NULL) {
+		struct enic *enic = pmd_priv(dev);
+		if (enic->overlay_offload)
+			return ptypes_overlay;
+		else
+			return ptypes;
+	}
 	return NULL;
 }
 
-static void enicpmd_dev_promiscuous_enable(struct rte_eth_dev *eth_dev)
+static int enicpmd_dev_promiscuous_enable(struct rte_eth_dev *eth_dev)
 {
 	struct enic *enic = pmd_priv(eth_dev);
+	int ret;
 
 	if (rte_eal_process_type() != RTE_PROC_PRIMARY)
-		return;
+		return -E_RTE_SECONDARY;
 
 	ENICPMD_FUNC_TRACE();
 
 	enic->promisc = 1;
-	enic_add_packet_filter(enic);
+	ret = enic_add_packet_filter(enic);
+	if (ret != 0)
+		enic->promisc = 0;
+
+	return ret;
 }
 
-static void enicpmd_dev_promiscuous_disable(struct rte_eth_dev *eth_dev)
+static int enicpmd_dev_promiscuous_disable(struct rte_eth_dev *eth_dev)
 {
 	struct enic *enic = pmd_priv(eth_dev);
+	int ret;
 
 	if (rte_eal_process_type() != RTE_PROC_PRIMARY)
-		return;
+		return -E_RTE_SECONDARY;
 
 	ENICPMD_FUNC_TRACE();
 	enic->promisc = 0;
-	enic_add_packet_filter(enic);
+	ret = enic_add_packet_filter(enic);
+	if (ret != 0)
+		enic->promisc = 1;
+
+	return ret;
 }
 
-static void enicpmd_dev_allmulticast_enable(struct rte_eth_dev *eth_dev)
+static int enicpmd_dev_allmulticast_enable(struct rte_eth_dev *eth_dev)
 {
 	struct enic *enic = pmd_priv(eth_dev);
+	int ret;
 
 	if (rte_eal_process_type() != RTE_PROC_PRIMARY)
-		return;
+		return -E_RTE_SECONDARY;
 
 	ENICPMD_FUNC_TRACE();
 	enic->allmulti = 1;
-	enic_add_packet_filter(enic);
+	ret = enic_add_packet_filter(enic);
+	if (ret != 0)
+		enic->allmulti = 0;
+
+	return ret;
 }
 
-static void enicpmd_dev_allmulticast_disable(struct rte_eth_dev *eth_dev)
+static int enicpmd_dev_allmulticast_disable(struct rte_eth_dev *eth_dev)
 {
 	struct enic *enic = pmd_priv(eth_dev);
+	int ret;
 
 	if (rte_eal_process_type() != RTE_PROC_PRIMARY)
-		return;
+		return -E_RTE_SECONDARY;
 
 	ENICPMD_FUNC_TRACE();
 	enic->allmulti = 0;
-	enic_add_packet_filter(enic);
+	ret = enic_add_packet_filter(enic);
+	if (ret != 0)
+		enic->allmulti = 1;
+
+	return ret;
 }
 
 static int enicpmd_add_mac_addr(struct rte_eth_dev *eth_dev,
-	struct ether_addr *mac_addr,
+	struct rte_ether_addr *mac_addr,
 	__rte_unused uint32_t index, __rte_unused uint32_t pool)
 {
 	struct enic *enic = pmd_priv(eth_dev);
@@ -585,7 +706,116 @@ static void enicpmd_remove_mac_addr(struct rte_eth_dev *eth_dev, uint32_t index)
 		return;
 
 	ENICPMD_FUNC_TRACE();
-	enic_del_mac_address(enic, index);
+	if (enic_del_mac_address(enic, index))
+		dev_err(enic, "del mac addr failed\n");
+}
+
+static int enicpmd_set_mac_addr(struct rte_eth_dev *eth_dev,
+				struct rte_ether_addr *addr)
+{
+	struct enic *enic = pmd_priv(eth_dev);
+	int ret;
+
+	if (rte_eal_process_type() != RTE_PROC_PRIMARY)
+		return -E_RTE_SECONDARY;
+
+	ENICPMD_FUNC_TRACE();
+	ret = enic_del_mac_address(enic, 0);
+	if (ret)
+		return ret;
+	return enic_set_mac_address(enic, addr->addr_bytes);
+}
+
+static void debug_log_add_del_addr(struct rte_ether_addr *addr, bool add)
+{
+	char mac_str[RTE_ETHER_ADDR_FMT_SIZE];
+
+	rte_ether_format_addr(mac_str, RTE_ETHER_ADDR_FMT_SIZE, addr);
+	ENICPMD_LOG(DEBUG, " %s address %s\n",
+		     add ? "add" : "remove", mac_str);
+}
+
+static int enicpmd_set_mc_addr_list(struct rte_eth_dev *eth_dev,
+				    struct rte_ether_addr *mc_addr_set,
+				    uint32_t nb_mc_addr)
+{
+	struct enic *enic = pmd_priv(eth_dev);
+	char mac_str[RTE_ETHER_ADDR_FMT_SIZE];
+	struct rte_ether_addr *addr;
+	uint32_t i, j;
+	int ret;
+
+	ENICPMD_FUNC_TRACE();
+
+	/* Validate the given addresses first */
+	for (i = 0; i < nb_mc_addr && mc_addr_set != NULL; i++) {
+		addr = &mc_addr_set[i];
+		if (!rte_is_multicast_ether_addr(addr) ||
+		    rte_is_broadcast_ether_addr(addr)) {
+			rte_ether_format_addr(mac_str,
+					RTE_ETHER_ADDR_FMT_SIZE, addr);
+			ENICPMD_LOG(ERR, " invalid multicast address %s\n",
+				     mac_str);
+			return -EINVAL;
+		}
+	}
+
+	/* Flush all if requested */
+	if (nb_mc_addr == 0 || mc_addr_set == NULL) {
+		ENICPMD_LOG(DEBUG, " flush multicast addresses\n");
+		for (i = 0; i < enic->mc_count; i++) {
+			addr = &enic->mc_addrs[i];
+			debug_log_add_del_addr(addr, false);
+			ret = vnic_dev_del_addr(enic->vdev, addr->addr_bytes);
+			if (ret)
+				return ret;
+		}
+		enic->mc_count = 0;
+		return 0;
+	}
+
+	if (nb_mc_addr > ENIC_MULTICAST_PERFECT_FILTERS) {
+		ENICPMD_LOG(ERR, " too many multicast addresses: max=%d\n",
+			     ENIC_MULTICAST_PERFECT_FILTERS);
+		return -ENOSPC;
+	}
+	/*
+	 * devcmd is slow, so apply the difference instead of flushing and
+	 * adding everything.
+	 * 1. Delete addresses on the NIC but not on the host
+	 */
+	for (i = 0; i < enic->mc_count; i++) {
+		addr = &enic->mc_addrs[i];
+		for (j = 0; j < nb_mc_addr; j++) {
+			if (rte_is_same_ether_addr(addr, &mc_addr_set[j]))
+				break;
+		}
+		if (j < nb_mc_addr)
+			continue;
+		debug_log_add_del_addr(addr, false);
+		ret = vnic_dev_del_addr(enic->vdev, addr->addr_bytes);
+		if (ret)
+			return ret;
+	}
+	/* 2. Add addresses on the host but not on the NIC */
+	for (i = 0; i < nb_mc_addr; i++) {
+		addr = &mc_addr_set[i];
+		for (j = 0; j < enic->mc_count; j++) {
+			if (rte_is_same_ether_addr(addr, &enic->mc_addrs[j]))
+				break;
+		}
+		if (j < enic->mc_count)
+			continue;
+		debug_log_add_del_addr(addr, true);
+		ret = vnic_dev_add_addr(enic->vdev, addr->addr_bytes);
+		if (ret)
+			return ret;
+	}
+	/* Keep a copy so we can flush/apply later on.. */
+	memcpy(enic->mc_addrs, mc_addr_set,
+	       nb_mc_addr * sizeof(struct rte_ether_addr));
+	enic->mc_count = nb_mc_addr;
+	return 0;
 }
 
 static int enicpmd_mtu_set(struct rte_eth_dev *eth_dev, uint16_t mtu)
@@ -703,7 +933,7 @@ static void enicpmd_dev_rxq_info_get(struct rte_eth_dev *dev,
 
 	ENICPMD_FUNC_TRACE();
 	sop_queue_idx = enic_rte_rq_idx_to_sop_idx(rx_queue_id);
-	data_queue_idx = enic_rte_rq_idx_to_data_idx(rx_queue_id);
+	data_queue_idx = enic_rte_rq_idx_to_data_idx(rx_queue_id, enic);
 	rq_sop = &enic->rq[sop_queue_idx];
 	rq_data = &enic->rq[data_queue_idx]; /* valid if data_queue_enable */
 	qinfo->mp = rq_sop->mp;
@@ -719,22 +949,23 @@ static void enicpmd_dev_rxq_info_get(struct rte_eth_dev *dev,
 	 * Except VLAN stripping (port setting), all the checksum offloads
 	 * are always enabled.
 	 */
-	conf->offloads = ENIC_RX_OFFLOAD_CAPA;
+	conf->offloads = enic->rx_offload_capa;
 	if (!enic->ig_vlan_strip_en)
 		conf->offloads &= ~DEV_RX_OFFLOAD_VLAN_STRIP;
 	/* rx_thresh and other fields are not applicable for enic */
 }
 
 static void enicpmd_dev_txq_info_get(struct rte_eth_dev *dev,
-				     __rte_unused uint16_t tx_queue_id,
+				     uint16_t tx_queue_id,
 				     struct rte_eth_txq_info *qinfo)
 {
 	struct enic *enic = pmd_priv(dev);
+	struct vnic_wq *wq = &enic->wq[tx_queue_id];
 
 	ENICPMD_FUNC_TRACE();
-	qinfo->nb_desc = enic->config.wq_desc_count;
+	qinfo->nb_desc = wq->ring.desc_count;
 	memset(&qinfo->conf, 0, sizeof(qinfo->conf));
-	qinfo->conf.offloads = ENIC_TX_OFFLOAD_CAPA; /* not configurable */
+	qinfo->conf.offloads = wq->offloads;
 	/* tx_thresh, and all the other fields are not applicable for enic */
 }
 
@@ -758,6 +989,99 @@ static int enicpmd_dev_rx_queue_intr_disable(struct rte_eth_dev *eth_dev,
 	return 0;
 }
 
+static int udp_tunnel_common_check(struct enic *enic,
+				   struct rte_eth_udp_tunnel *tnl)
+{
+	if (tnl->prot_type != RTE_TUNNEL_TYPE_VXLAN)
+		return -ENOTSUP;
+	if (!enic->overlay_offload) {
+		ENICPMD_LOG(DEBUG, " vxlan (overlay offload) is not "
+			     "supported\n");
+		return -ENOTSUP;
+	}
+	return 0;
+}
+
+static int update_vxlan_port(struct enic *enic, uint16_t port)
+{
+	if (vnic_dev_overlay_offload_cfg(enic->vdev,
+					 OVERLAY_CFG_VXLAN_PORT_UPDATE,
+					 port)) {
+		ENICPMD_LOG(DEBUG, " failed to update vxlan port\n");
+		return -EINVAL;
+	}
+	ENICPMD_LOG(DEBUG, " updated vxlan port to %u\n", port);
+	enic->vxlan_port = port;
+	return 0;
+}
+
+static int enicpmd_dev_udp_tunnel_port_add(struct rte_eth_dev *eth_dev,
+					   struct rte_eth_udp_tunnel *tnl)
+{
+	struct enic *enic = pmd_priv(eth_dev);
+	int ret;
+
+	ENICPMD_FUNC_TRACE();
+	ret = udp_tunnel_common_check(enic, tnl);
+	if (ret)
+		return ret;
+	/*
+	 * The NIC has 1 configurable VXLAN port number. "Adding" a new port
+	 * number replaces it.
+	 */
+	if (tnl->udp_port == enic->vxlan_port || tnl->udp_port == 0) {
+		ENICPMD_LOG(DEBUG, " %u is already configured or invalid\n",
+			     tnl->udp_port);
+		return -EINVAL;
+	}
+	return update_vxlan_port(enic, tnl->udp_port);
+}
+
+static int enicpmd_dev_udp_tunnel_port_del(struct rte_eth_dev *eth_dev,
+					   struct rte_eth_udp_tunnel *tnl)
+{
+	struct enic *enic = pmd_priv(eth_dev);
+	int ret;
+
+	ENICPMD_FUNC_TRACE();
+	ret = udp_tunnel_common_check(enic, tnl);
+	if (ret)
+		return ret;
+	/*
+	 * Clear the previously set port number and restore the
+	 * hardware default port number. Some drivers disable VXLAN
+	 * offloads when there are no configured port numbers. But
+	 * enic does not do that as VXLAN is part of overlay offload,
+	 * which is tied to inner RSS and TSO.
+	 */
+	if (tnl->udp_port != enic->vxlan_port) {
+		ENICPMD_LOG(DEBUG, " %u is not a configured vxlan port\n",
+			     tnl->udp_port);
+		return -EINVAL;
+	}
+	return update_vxlan_port(enic, RTE_VXLAN_DEFAULT_PORT);
+}
+
+static int enicpmd_dev_fw_version_get(struct rte_eth_dev *eth_dev,
+				      char *fw_version, size_t fw_size)
+{
+	struct vnic_devcmd_fw_info *info;
+	struct enic *enic;
+	int ret;
+
+	ENICPMD_FUNC_TRACE();
+	if (fw_version == NULL || fw_size <= 0)
+		return -EINVAL;
+	enic = pmd_priv(eth_dev);
+	ret = vnic_dev_fw_info(enic->vdev, &info);
+	if (ret)
+		return ret;
+	snprintf(fw_version, fw_size, "%s %s",
+		 info->fw_version, info->fw_build);
+	fw_version[fw_size - 1] = '\0';
+	return 0;
+}
+
 static const struct eth_dev_ops enicpmd_eth_dev_ops = {
 	.dev_configure        = enicpmd_dev_configure,
 	.dev_start            = enicpmd_dev_start,
@@ -801,14 +1125,114 @@ static const struct eth_dev_ops enicpmd_eth_dev_ops = {
 	.priority_flow_ctrl_set = NULL,
 	.mac_addr_add         = enicpmd_add_mac_addr,
 	.mac_addr_remove      = enicpmd_remove_mac_addr,
+	.mac_addr_set         = enicpmd_set_mac_addr,
+	.set_mc_addr_list     = enicpmd_set_mc_addr_list,
 	.filter_ctrl          = enicpmd_dev_filter_ctrl,
 	.reta_query           = enicpmd_dev_rss_reta_query,
 	.reta_update          = enicpmd_dev_rss_reta_update,
 	.rss_hash_conf_get    = enicpmd_dev_rss_hash_conf_get,
 	.rss_hash_update      = enicpmd_dev_rss_hash_update,
+	.udp_tunnel_port_add  = enicpmd_dev_udp_tunnel_port_add,
+	.udp_tunnel_port_del  = enicpmd_dev_udp_tunnel_port_del,
+	.fw_version_get       = enicpmd_dev_fw_version_get,
 };
 
-struct enic *enicpmd_list_head = NULL;
+static int enic_parse_zero_one(const char *key,
+			       const char *value,
+			       void *opaque)
+{
+	struct enic *enic;
+	bool b;
+
+	enic = (struct enic *)opaque;
+	if (strcmp(value, "0") == 0) {
+		b = false;
+	} else if (strcmp(value, "1") == 0) {
+		b = true;
+	} else {
+		dev_err(enic, "Invalid value for %s"
+			": expected=0|1 given=%s\n", key, value);
+		return -EINVAL;
+	}
+	if (strcmp(key, ENIC_DEVARG_DISABLE_OVERLAY) == 0)
+		enic->disable_overlay = b;
+	if (strcmp(key, ENIC_DEVARG_ENABLE_AVX2_RX) == 0)
+		enic->enable_avx2_rx = b;
+	if (strcmp(key, ENIC_DEVARG_GENEVE_OPT) == 0)
+		enic->geneve_opt_request = b;
+	return 0;
+}
+
+static int enic_parse_ig_vlan_rewrite(__rte_unused const char *key,
+				      const char *value,
+				      void *opaque)
+{
+	struct enic *enic;
+
+	enic = (struct enic *)opaque;
+	if (strcmp(value, "trunk") == 0) {
+		/* Trunk mode: always tag */
+		enic->ig_vlan_rewrite_mode = IG_VLAN_REWRITE_MODE_DEFAULT_TRUNK;
+	} else if (strcmp(value, "untag") == 0) {
+		/* Untag default VLAN mode: untag if VLAN = default VLAN */
+		enic->ig_vlan_rewrite_mode =
+			IG_VLAN_REWRITE_MODE_UNTAG_DEFAULT_VLAN;
+	} else if (strcmp(value, "priority") == 0) {
+		/*
+		 * Priority-tag default VLAN mode: priority tag (VLAN header
+		 * with ID=0) if VLAN = default
+		 */
+		enic->ig_vlan_rewrite_mode =
+			IG_VLAN_REWRITE_MODE_PRIORITY_TAG_DEFAULT_VLAN;
+	} else if (strcmp(value, "pass") == 0) {
+		/* Pass through mode: do not touch tags */
+		enic->ig_vlan_rewrite_mode = IG_VLAN_REWRITE_MODE_PASS_THRU;
+	} else {
+		dev_err(enic, "Invalid value for " ENIC_DEVARG_IG_VLAN_REWRITE
+			": expected=trunk|untag|priority|pass given=%s\n",
+			value);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int enic_check_devargs(struct rte_eth_dev *dev)
+{
+	static const char *const valid_keys[] = {
+		ENIC_DEVARG_DISABLE_OVERLAY,
+		ENIC_DEVARG_ENABLE_AVX2_RX,
+		ENIC_DEVARG_GENEVE_OPT,
+		ENIC_DEVARG_IG_VLAN_REWRITE,
+		NULL};
+	struct enic *enic = pmd_priv(dev);
+	struct rte_kvargs *kvlist;
+
+	ENICPMD_FUNC_TRACE();
+
+	enic->disable_overlay = false;
+	enic->enable_avx2_rx = false;
+	enic->geneve_opt_request = false;
+	enic->ig_vlan_rewrite_mode = IG_VLAN_REWRITE_MODE_PASS_THRU;
+	if (!dev->device->devargs)
+		return 0;
+	kvlist = rte_kvargs_parse(dev->device->devargs->args, valid_keys);
+	if (!kvlist)
+		return -EINVAL;
+	if (rte_kvargs_process(kvlist, ENIC_DEVARG_DISABLE_OVERLAY,
+			       enic_parse_zero_one, enic) < 0 ||
+	    rte_kvargs_process(kvlist, ENIC_DEVARG_ENABLE_AVX2_RX,
+			       enic_parse_zero_one, enic) < 0 ||
+	    rte_kvargs_process(kvlist, ENIC_DEVARG_GENEVE_OPT,
+			       enic_parse_zero_one, enic) < 0 ||
+	    rte_kvargs_process(kvlist, ENIC_DEVARG_IG_VLAN_REWRITE,
+			       enic_parse_ig_vlan_rewrite, enic) < 0) {
+		rte_kvargs_free(kvlist);
+		return -EINVAL;
+	}
+	rte_kvargs_free(kvlist);
+	return 0;
+}
+
 /* Initialize the driver
  * It returns 0 on success.
  */
@@ -817,15 +1241,25 @@ static int eth_enicpmd_dev_init(struct rte_eth_dev *eth_dev)
 	struct rte_pci_device *pdev;
 	struct rte_pci_addr *addr;
 	struct enic *enic = pmd_priv(eth_dev);
+	int err;
 
 	ENICPMD_FUNC_TRACE();
 
-	enic->port_id = eth_dev->data->port_id;
-	enic->rte_dev = eth_dev;
 	eth_dev->dev_ops = &enicpmd_eth_dev_ops;
 	eth_dev->rx_pkt_burst = &enic_recv_pkts;
 	eth_dev->tx_pkt_burst = &enic_xmit_pkts;
 	eth_dev->tx_pkt_prepare = &enic_prep_pkts;
+	if (rte_eal_process_type() != RTE_PROC_PRIMARY) {
+		enic_pick_tx_handler(eth_dev);
+		enic_pick_rx_handler(eth_dev);
+		return 0;
+	}
+	/* Only the primary sets up adapter and other data in shared memory */
+	enic->port_id = eth_dev->data->port_id;
+	enic->rte_dev = eth_dev;
+	enic->dev_data = eth_dev->data;
+	/* Let rte_eth_dev_close() release the port resources */
+	eth_dev->data->dev_flags |= RTE_ETH_DEV_CLOSE_REMOVE;
 
 	pdev = RTE_ETH_DEV_TO_PCI(eth_dev);
 	rte_eth_copy_pci_info(eth_dev, pdev);
@@ -835,6 +1269,9 @@ static int eth_enicpmd_dev_init(struct rte_eth_dev *eth_dev)
 	snprintf(enic->bdf_name, ENICPMD_BDF_LENGTH, "%04x:%02x:%02x.%x",
 		addr->domain, addr->bus, addr->devid, addr->function);
 
+	err = enic_check_devargs(eth_dev);
+	if (err)
+		return err;
 	return enic_probe(enic);
 }
 
@@ -857,6 +1294,16 @@ static struct rte_pci_driver rte_enic_pmd = {
 	.remove = eth_enic_pci_remove,
 };
 
+int dev_is_enic(struct rte_eth_dev *dev)
+{
+	return dev->device->driver == &rte_enic_pmd.driver;
+}
+
 RTE_PMD_REGISTER_PCI(net_enic, rte_enic_pmd);
 RTE_PMD_REGISTER_PCI_TABLE(net_enic, pci_id_enic_map);
 RTE_PMD_REGISTER_KMOD_DEP(net_enic, "* igb_uio | uio_pci_generic | vfio-pci");
+RTE_PMD_REGISTER_PARAM_STRING(net_enic,
+	ENIC_DEVARG_DISABLE_OVERLAY "=0|1 "
+	ENIC_DEVARG_ENABLE_AVX2_RX "=0|1 "
+	ENIC_DEVARG_GENEVE_OPT "=0|1 "
+	ENIC_DEVARG_IG_VLAN_REWRITE "=trunk|untag|priority|pass");