/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright(c) 2010-2017 Intel Corporation
 */

#include <ctype.h>
#include <errno.h>
#include <inttypes.h>
#include <stdbool.h>
#include <stdint.h>
#include <stdlib.h>
#include <string.h>
#include <sys/queue.h>

#include <rte_byteorder.h>
#include <rte_log.h>
#include <rte_debug.h>
#include <rte_interrupts.h>
#include <rte_memory.h>
#include <rte_memcpy.h>
#include <rte_memzone.h>
#include <rte_launch.h>
#include <rte_eal.h>
#include <rte_per_lcore.h>
#include <rte_lcore.h>
#include <rte_branch_prediction.h>
#include <rte_common.h>
#include <rte_mempool.h>
#include <rte_malloc.h>
#include <rte_mbuf.h>
#include <rte_errno.h>
#include <rte_spinlock.h>
#include <rte_string_fns.h>
#include <rte_kvargs.h>
#include <rte_class.h>
#include <rte_ether.h>
#include <rte_telemetry.h>

#include "rte_ethdev_trace.h"
#include "rte_ethdev.h"
#include "ethdev_driver.h"
#include "ethdev_profile.h"
#include "ethdev_private.h"

static const char *MZ_RTE_ETH_DEV_DATA = "rte_eth_dev_data";
struct rte_eth_dev rte_eth_devices[RTE_MAX_ETHPORTS];

/* spinlock for eth device callbacks */
static rte_spinlock_t eth_dev_cb_lock = RTE_SPINLOCK_INITIALIZER;

/* spinlock for add/remove rx callbacks */
static rte_spinlock_t eth_dev_rx_cb_lock = RTE_SPINLOCK_INITIALIZER;

/* spinlock for add/remove tx callbacks */
static rte_spinlock_t eth_dev_tx_cb_lock = RTE_SPINLOCK_INITIALIZER;

/* spinlock for shared data allocation */
static rte_spinlock_t eth_dev_shared_data_lock = RTE_SPINLOCK_INITIALIZER;

/* store statistics names and its offset in stats structure  */
struct rte_eth_xstats_name_off {
        char name[RTE_ETH_XSTATS_NAME_SIZE];
        unsigned offset;
};

/* Shared memory between primary and secondary processes. */
static struct {
        uint64_t next_owner_id;
        rte_spinlock_t ownership_lock;
        struct rte_eth_dev_data data[RTE_MAX_ETHPORTS];
} *eth_dev_shared_data;

static const struct rte_eth_xstats_name_off eth_dev_stats_strings[] = {
        {"rx_good_packets", offsetof(struct rte_eth_stats, ipackets)},
        {"tx_good_packets", offsetof(struct rte_eth_stats, opackets)},
        {"rx_good_bytes", offsetof(struct rte_eth_stats, ibytes)},
        {"tx_good_bytes", offsetof(struct rte_eth_stats, obytes)},
        {"rx_missed_errors", offsetof(struct rte_eth_stats, imissed)},
        {"rx_errors", offsetof(struct rte_eth_stats, ierrors)},
        {"tx_errors", offsetof(struct rte_eth_stats, oerrors)},
        {"rx_mbuf_allocation_errors", offsetof(struct rte_eth_stats,
                rx_nombuf)},
};

#define RTE_NB_STATS RTE_DIM(eth_dev_stats_strings)

static const struct rte_eth_xstats_name_off eth_dev_rxq_stats_strings[] = {
        {"packets", offsetof(struct rte_eth_stats, q_ipackets)},
        {"bytes", offsetof(struct rte_eth_stats, q_ibytes)},
        {"errors", offsetof(struct rte_eth_stats, q_errors)},
};

#define RTE_NB_RXQ_STATS RTE_DIM(eth_dev_rxq_stats_strings)

static const struct rte_eth_xstats_name_off eth_dev_txq_stats_strings[] = {
        {"packets", offsetof(struct rte_eth_stats, q_opackets)},
        {"bytes", offsetof(struct rte_eth_stats, q_obytes)},
};
#define RTE_NB_TXQ_STATS RTE_DIM(eth_dev_txq_stats_strings)

#define RTE_RX_OFFLOAD_BIT2STR(_name)   \
        { DEV_RX_OFFLOAD_##_name, #_name }

#define RTE_ETH_RX_OFFLOAD_BIT2STR(_name)       \
        { RTE_ETH_RX_OFFLOAD_##_name, #_name }

static const struct {
        uint64_t offload;
        const char *name;
} eth_dev_rx_offload_names[] = {
        RTE_RX_OFFLOAD_BIT2STR(VLAN_STRIP),
        RTE_RX_OFFLOAD_BIT2STR(IPV4_CKSUM),
        RTE_RX_OFFLOAD_BIT2STR(UDP_CKSUM),
        RTE_RX_OFFLOAD_BIT2STR(TCP_CKSUM),
        RTE_RX_OFFLOAD_BIT2STR(TCP_LRO),
        RTE_RX_OFFLOAD_BIT2STR(QINQ_STRIP),
        RTE_RX_OFFLOAD_BIT2STR(OUTER_IPV4_CKSUM),
        RTE_RX_OFFLOAD_BIT2STR(MACSEC_STRIP),
        RTE_RX_OFFLOAD_BIT2STR(HEADER_SPLIT),
        RTE_RX_OFFLOAD_BIT2STR(VLAN_FILTER),
        RTE_RX_OFFLOAD_BIT2STR(VLAN_EXTEND),
        RTE_RX_OFFLOAD_BIT2STR(JUMBO_FRAME),
        RTE_RX_OFFLOAD_BIT2STR(SCATTER),
        RTE_RX_OFFLOAD_BIT2STR(TIMESTAMP),
        RTE_RX_OFFLOAD_BIT2STR(SECURITY),
        RTE_RX_OFFLOAD_BIT2STR(KEEP_CRC),
        RTE_RX_OFFLOAD_BIT2STR(SCTP_CKSUM),
        RTE_RX_OFFLOAD_BIT2STR(OUTER_UDP_CKSUM),
        RTE_RX_OFFLOAD_BIT2STR(RSS_HASH),
        RTE_ETH_RX_OFFLOAD_BIT2STR(BUFFER_SPLIT),
};

#undef RTE_RX_OFFLOAD_BIT2STR
#undef RTE_ETH_RX_OFFLOAD_BIT2STR

#define RTE_TX_OFFLOAD_BIT2STR(_name)   \
        { DEV_TX_OFFLOAD_##_name, #_name }

static const struct {
        uint64_t offload;
        const char *name;
} eth_dev_tx_offload_names[] = {
        RTE_TX_OFFLOAD_BIT2STR(VLAN_INSERT),
        RTE_TX_OFFLOAD_BIT2STR(IPV4_CKSUM),
        RTE_TX_OFFLOAD_BIT2STR(UDP_CKSUM),
        RTE_TX_OFFLOAD_BIT2STR(TCP_CKSUM),
        RTE_TX_OFFLOAD_BIT2STR(SCTP_CKSUM),
        RTE_TX_OFFLOAD_BIT2STR(TCP_TSO),
        RTE_TX_OFFLOAD_BIT2STR(UDP_TSO),
        RTE_TX_OFFLOAD_BIT2STR(OUTER_IPV4_CKSUM),
        RTE_TX_OFFLOAD_BIT2STR(QINQ_INSERT),
        RTE_TX_OFFLOAD_BIT2STR(VXLAN_TNL_TSO),
        RTE_TX_OFFLOAD_BIT2STR(GRE_TNL_TSO),
        RTE_TX_OFFLOAD_BIT2STR(IPIP_TNL_TSO),
        RTE_TX_OFFLOAD_BIT2STR(GENEVE_TNL_TSO),
        RTE_TX_OFFLOAD_BIT2STR(MACSEC_INSERT),
        RTE_TX_OFFLOAD_BIT2STR(MT_LOCKFREE),
        RTE_TX_OFFLOAD_BIT2STR(MULTI_SEGS),
        RTE_TX_OFFLOAD_BIT2STR(MBUF_FAST_FREE),
        RTE_TX_OFFLOAD_BIT2STR(SECURITY),
        RTE_TX_OFFLOAD_BIT2STR(UDP_TNL_TSO),
        RTE_TX_OFFLOAD_BIT2STR(IP_TNL_TSO),
        RTE_TX_OFFLOAD_BIT2STR(OUTER_UDP_CKSUM),
        RTE_TX_OFFLOAD_BIT2STR(SEND_ON_TIMESTAMP),
};

#undef RTE_TX_OFFLOAD_BIT2STR

/**
 * The user application callback description.
 *
 * It contains callback address to be registered by user application,
 * the pointer to the parameters for callback, and the event type.
 */
struct rte_eth_dev_callback {
        TAILQ_ENTRY(rte_eth_dev_callback) next; /**< Callbacks list */
        rte_eth_dev_cb_fn cb_fn;                /**< Callback address */
        void *cb_arg;                           /**< Parameter for callback */
        void *ret_param;                        /**< Return parameter */
        enum rte_eth_event_type event;          /**< Interrupt event type */
        uint32_t active;                        /**< Callback is executing */
};

enum {
        STAT_QMAP_TX = 0,
        STAT_QMAP_RX
};

int
rte_eth_iterator_init(struct rte_dev_iterator *iter, const char *devargs_str)
{
        int ret;
        struct rte_devargs devargs;
        const char *bus_param_key;
        char *bus_str = NULL;
        char *cls_str = NULL;
        int str_size;

        if (iter == NULL) {
                RTE_ETHDEV_LOG(ERR, "Cannot initialize NULL iterator\n");
                return -EINVAL;
        }

        if (devargs_str == NULL) {
                RTE_ETHDEV_LOG(ERR,
                        "Cannot initialize iterator from NULL device description string\n");
                return -EINVAL;
        }

        memset(iter, 0, sizeof(*iter));
        memset(&devargs, 0, sizeof(devargs));

        /*
         * The devargs string may use various syntaxes:
         *   - 0000:08:00.0,representor=[1-3]
         *   - pci:0000:06:00.0,representor=[0,5]
         *   - class=eth,mac=00:11:22:33:44:55
         * A new syntax is in development (not yet supported):
         *   - bus=X,paramX=x/class=Y,paramY=y/driver=Z,paramZ=z
         */

        /*
         * Handle pure class filter (i.e. without any bus-level argument),
         * from future new syntax.
         * rte_devargs_parse() is not yet supporting the new syntax,
         * that's why this simple case is temporarily parsed here.
         */
#define iter_anybus_str "class=eth,"
        if (strncmp(devargs_str, iter_anybus_str,
                        strlen(iter_anybus_str)) == 0) {
                iter->cls_str = devargs_str + strlen(iter_anybus_str);
                goto end;
        }

        /* Split bus, device and parameters. */
        ret = rte_devargs_parse(&devargs, devargs_str);
        if (ret != 0)
                goto error;

        /*
         * Assume parameters of old syntax can match only at ethdev level.
         * Extra parameters will be ignored, thanks to "+" prefix.
         */
        str_size = strlen(devargs.args) + 2;
        cls_str = malloc(str_size);
        if (cls_str == NULL) {
                ret = -ENOMEM;
                goto error;
        }
        ret = snprintf(cls_str, str_size, "+%s", devargs.args);
        if (ret != str_size - 1) {
                ret = -EINVAL;
                goto error;
        }
        iter->cls_str = cls_str;

        iter->bus = devargs.bus;
        if (iter->bus->dev_iterate == NULL) {
                ret = -ENOTSUP;
                goto error;
        }

        /* Convert bus args to new syntax for use with new API dev_iterate. */
        if ((strcmp(iter->bus->name, "vdev") == 0) ||
                (strcmp(iter->bus->name, "fslmc") == 0) ||
                (strcmp(iter->bus->name, "dpaa_bus") == 0)) {
                bus_param_key = "name";
        } else if (strcmp(iter->bus->name, "pci") == 0) {
                bus_param_key = "addr";
        } else {
                ret = -ENOTSUP;
                goto error;
        }
        str_size = strlen(bus_param_key) + strlen(devargs.name) + 2;
        bus_str = malloc(str_size);
        if (bus_str == NULL) {
                ret = -ENOMEM;
                goto error;
        }
        ret = snprintf(bus_str, str_size, "%s=%s",
                        bus_param_key, devargs.name);
        if (ret != str_size - 1) {
                ret = -EINVAL;
                goto error;
        }
        iter->bus_str = bus_str;

end:
        iter->cls = rte_class_find_by_name("eth");
        rte_devargs_reset(&devargs);
        return 0;

error:
        if (ret == -ENOTSUP)
                RTE_ETHDEV_LOG(ERR, "Bus %s does not support iterating.\n",
                                iter->bus->name);
        rte_devargs_reset(&devargs);
        free(bus_str);
        free(cls_str);
        return ret;
}

uint16_t
rte_eth_iterator_next(struct rte_dev_iterator *iter)
{
        if (iter == NULL) {
                RTE_ETHDEV_LOG(ERR,
                        "Cannot get next device from NULL iterator\n");
                return RTE_MAX_ETHPORTS;
        }

        if (iter->cls == NULL) /* invalid ethdev iterator */
                return RTE_MAX_ETHPORTS;

        do { /* loop to try all matching rte_device */
                /* If not pure ethdev filter and */
                if (iter->bus != NULL &&
                                /* not in middle of rte_eth_dev iteration, */
                                iter->class_device == NULL) {
                        /* get next rte_device to try. */
                        iter->device = iter->bus->dev_iterate(
                                        iter->device, iter->bus_str, iter);
                        if (iter->device == NULL)
                                break; /* no more rte_device candidate */
                }
                /* A device is matching bus part, need to check ethdev part. */
                iter->class_device = iter->cls->dev_iterate(
                                iter->class_device, iter->cls_str, iter);
                if (iter->class_device != NULL)
                        return eth_dev_to_id(iter->class_device); /* match */
        } while (iter->bus != NULL); /* need to try next rte_device */

        /* No more ethdev port to iterate. */
        rte_eth_iterator_cleanup(iter);
        return RTE_MAX_ETHPORTS;
}

void
rte_eth_iterator_cleanup(struct rte_dev_iterator *iter)
{
        if (iter == NULL) {
                RTE_ETHDEV_LOG(ERR, "Cannot do clean up from NULL iterator\n");
                return;
        }

        if (iter->bus_str == NULL)
                return; /* nothing to free in pure class filter */
        free(RTE_CAST_FIELD(iter, bus_str, char *)); /* workaround const */
        free(RTE_CAST_FIELD(iter, cls_str, char *)); /* workaround const */
        memset(iter, 0, sizeof(*iter));
}

uint16_t
rte_eth_find_next(uint16_t port_id)
{
        while (port_id < RTE_MAX_ETHPORTS &&
                        rte_eth_devices[port_id].state == RTE_ETH_DEV_UNUSED)
                port_id++;

        if (port_id >= RTE_MAX_ETHPORTS)
                return RTE_MAX_ETHPORTS;

        return port_id;
}

/*
 * Macro to iterate over all valid ports for internal usage.
 * Note: RTE_ETH_FOREACH_DEV is different because filtering owned ports.
 */
#define RTE_ETH_FOREACH_VALID_DEV(port_id) \
        for (port_id = rte_eth_find_next(0); \
             port_id < RTE_MAX_ETHPORTS; \
             port_id = rte_eth_find_next(port_id + 1))

uint16_t
rte_eth_find_next_of(uint16_t port_id, const struct rte_device *parent)
{
        port_id = rte_eth_find_next(port_id);
        while (port_id < RTE_MAX_ETHPORTS &&
                        rte_eth_devices[port_id].device != parent)
                port_id = rte_eth_find_next(port_id + 1);

        return port_id;
}

uint16_t
rte_eth_find_next_sibling(uint16_t port_id, uint16_t ref_port_id)
{
        RTE_ETH_VALID_PORTID_OR_ERR_RET(ref_port_id, RTE_MAX_ETHPORTS);
        return rte_eth_find_next_of(port_id,
                        rte_eth_devices[ref_port_id].device);
}

static void
eth_dev_shared_data_prepare(void)
{
        const unsigned flags = 0;
        const struct rte_memzone *mz;

        rte_spinlock_lock(&eth_dev_shared_data_lock);

        if (eth_dev_shared_data == NULL) {
                if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
                        /* Allocate port data and ownership shared memory. */
                        mz = rte_memzone_reserve(MZ_RTE_ETH_DEV_DATA,
                                        sizeof(*eth_dev_shared_data),
                                        rte_socket_id(), flags);
                } else
                        mz = rte_memzone_lookup(MZ_RTE_ETH_DEV_DATA);
                if (mz == NULL)
                        rte_panic("Cannot allocate ethdev shared data\n");

                eth_dev_shared_data = mz->addr;
                if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
                        eth_dev_shared_data->next_owner_id =
                                        RTE_ETH_DEV_NO_OWNER + 1;
                        rte_spinlock_init(&eth_dev_shared_data->ownership_lock);
                        memset(eth_dev_shared_data->data, 0,
                               sizeof(eth_dev_shared_data->data));
                }
        }

        rte_spinlock_unlock(&eth_dev_shared_data_lock);
}

static bool
eth_dev_is_allocated(const struct rte_eth_dev *ethdev)
{
        return ethdev->data->name[0] != '\0';
}

static struct rte_eth_dev *
eth_dev_allocated(const char *name)
{
        uint16_t i;

        RTE_BUILD_BUG_ON(RTE_MAX_ETHPORTS >= UINT16_MAX);

        for (i = 0; i < RTE_MAX_ETHPORTS; i++) {
                if (rte_eth_devices[i].data != NULL &&
                    strcmp(rte_eth_devices[i].data->name, name) == 0)
                        return &rte_eth_devices[i];
        }
        return NULL;
}

struct rte_eth_dev *
rte_eth_dev_allocated(const char *name)
{
        struct rte_eth_dev *ethdev;

        eth_dev_shared_data_prepare();

        rte_spinlock_lock(&eth_dev_shared_data->ownership_lock);

        ethdev = eth_dev_allocated(name);

        rte_spinlock_unlock(&eth_dev_shared_data->ownership_lock);

        return ethdev;
}

static uint16_t
eth_dev_find_free_port(void)
{
        uint16_t i;

        for (i = 0; i < RTE_MAX_ETHPORTS; i++) {
                /* Using shared name field to find a free port. */
                if (eth_dev_shared_data->data[i].name[0] == '\0') {
                        RTE_ASSERT(rte_eth_devices[i].state ==
                                   RTE_ETH_DEV_UNUSED);
                        return i;
                }
        }
        return RTE_MAX_ETHPORTS;
}

static struct rte_eth_dev *
eth_dev_get(uint16_t port_id)
{
        struct rte_eth_dev *eth_dev = &rte_eth_devices[port_id];

        eth_dev->data = &eth_dev_shared_data->data[port_id];

        return eth_dev;
}

struct rte_eth_dev *
rte_eth_dev_allocate(const char *name)
{
        uint16_t port_id;
        struct rte_eth_dev *eth_dev = NULL;
        size_t name_len;

        name_len = strnlen(name, RTE_ETH_NAME_MAX_LEN);
        if (name_len == 0) {
                RTE_ETHDEV_LOG(ERR, "Zero length Ethernet device name\n");
                return NULL;
        }

        if (name_len >= RTE_ETH_NAME_MAX_LEN) {
                RTE_ETHDEV_LOG(ERR, "Ethernet device name is too long\n");
                return NULL;
        }

        eth_dev_shared_data_prepare();

        /* Synchronize port creation between primary and secondary threads. */
        rte_spinlock_lock(&eth_dev_shared_data->ownership_lock);

        if (eth_dev_allocated(name) != NULL) {
                RTE_ETHDEV_LOG(ERR,
                        "Ethernet device with name %s already allocated\n",
                        name);
                goto unlock;
        }

        port_id = eth_dev_find_free_port();
        if (port_id == RTE_MAX_ETHPORTS) {
                RTE_ETHDEV_LOG(ERR,
                        "Reached maximum number of Ethernet ports\n");
                goto unlock;
        }

        eth_dev = eth_dev_get(port_id);
        strlcpy(eth_dev->data->name, name, sizeof(eth_dev->data->name));
        eth_dev->data->port_id = port_id;
        eth_dev->data->mtu = RTE_ETHER_MTU;
        pthread_mutex_init(&eth_dev->data->flow_ops_mutex, NULL);

unlock:
        rte_spinlock_unlock(&eth_dev_shared_data->ownership_lock);

        return eth_dev;
}

/*
 * Attach to a port already registered by the primary process, which
 * makes sure that the same device would have the same port id both
 * in the primary and secondary process.
 */
struct rte_eth_dev *
rte_eth_dev_attach_secondary(const char *name)
{
        uint16_t i;
        struct rte_eth_dev *eth_dev = NULL;

        eth_dev_shared_data_prepare();

        /* Synchronize port attachment to primary port creation and release. */
        rte_spinlock_lock(&eth_dev_shared_data->ownership_lock);

        for (i = 0; i < RTE_MAX_ETHPORTS; i++) {
                if (strcmp(eth_dev_shared_data->data[i].name, name) == 0)
                        break;
        }
        if (i == RTE_MAX_ETHPORTS) {
                RTE_ETHDEV_LOG(ERR,
                        "Device %s is not driven by the primary process\n",
                        name);
        } else {
                eth_dev = eth_dev_get(i);
                RTE_ASSERT(eth_dev->data->port_id == i);
        }

        rte_spinlock_unlock(&eth_dev_shared_data->ownership_lock);
        return eth_dev;
}

int
rte_eth_dev_release_port(struct rte_eth_dev *eth_dev)
{
        if (eth_dev == NULL)
                return -EINVAL;

        eth_dev_shared_data_prepare();

        if (eth_dev->state != RTE_ETH_DEV_UNUSED)
                rte_eth_dev_callback_process(eth_dev,
                                RTE_ETH_EVENT_DESTROY, NULL);

        rte_spinlock_lock(&eth_dev_shared_data->ownership_lock);

        eth_dev->state = RTE_ETH_DEV_UNUSED;
        eth_dev->device = NULL;
        eth_dev->process_private = NULL;
        eth_dev->intr_handle = NULL;
        eth_dev->rx_pkt_burst = NULL;
        eth_dev->tx_pkt_burst = NULL;
        eth_dev->tx_pkt_prepare = NULL;
        eth_dev->rx_queue_count = NULL;
        eth_dev->rx_descriptor_done = NULL;
        eth_dev->rx_descriptor_status = NULL;
        eth_dev->tx_descriptor_status = NULL;
        eth_dev->dev_ops = NULL;

        if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
                rte_free(eth_dev->data->rx_queues);
                rte_free(eth_dev->data->tx_queues);
                rte_free(eth_dev->data->mac_addrs);
                rte_free(eth_dev->data->hash_mac_addrs);
                rte_free(eth_dev->data->dev_private);
                pthread_mutex_destroy(&eth_dev->data->flow_ops_mutex);
                memset(eth_dev->data, 0, sizeof(struct rte_eth_dev_data));
        }

        rte_spinlock_unlock(&eth_dev_shared_data->ownership_lock);

        return 0;
}

int
rte_eth_dev_is_valid_port(uint16_t port_id)
{
        if (port_id >= RTE_MAX_ETHPORTS ||
            (rte_eth_devices[port_id].state == RTE_ETH_DEV_UNUSED))
                return 0;
        else
                return 1;
}

static int
eth_is_valid_owner_id(uint64_t owner_id)
{
        if (owner_id == RTE_ETH_DEV_NO_OWNER ||
            eth_dev_shared_data->next_owner_id <= owner_id)
                return 0;
        return 1;
}

uint64_t
rte_eth_find_next_owned_by(uint16_t port_id, const uint64_t owner_id)
{
        port_id = rte_eth_find_next(port_id);
        while (port_id < RTE_MAX_ETHPORTS &&
                        rte_eth_devices[port_id].data->owner.id != owner_id)
                port_id = rte_eth_find_next(port_id + 1);

        return port_id;
}

int
rte_eth_dev_owner_new(uint64_t *owner_id)
{
        if (owner_id == NULL) {
                RTE_ETHDEV_LOG(ERR, "Cannot get new owner ID to NULL\n");
                return -EINVAL;
        }

        eth_dev_shared_data_prepare();

        rte_spinlock_lock(&eth_dev_shared_data->ownership_lock);

        *owner_id = eth_dev_shared_data->next_owner_id++;

        rte_spinlock_unlock(&eth_dev_shared_data->ownership_lock);
        return 0;
}

static int
eth_dev_owner_set(const uint16_t port_id, const uint64_t old_owner_id,
                       const struct rte_eth_dev_owner *new_owner)
{
        struct rte_eth_dev *ethdev = &rte_eth_devices[port_id];
        struct rte_eth_dev_owner *port_owner;

        if (port_id >= RTE_MAX_ETHPORTS || !eth_dev_is_allocated(ethdev)) {
                RTE_ETHDEV_LOG(ERR, "Port id %"PRIu16" is not allocated\n",
                        port_id);
                return -ENODEV;
        }

        if (new_owner == NULL) {
                RTE_ETHDEV_LOG(ERR,
                        "Cannot set ethdev port %u owner from NULL owner\n",
                        port_id);
                return -EINVAL;
        }

        if (!eth_is_valid_owner_id(new_owner->id) &&
            !eth_is_valid_owner_id(old_owner_id)) {
                RTE_ETHDEV_LOG(ERR,
                        "Invalid owner old_id=%016"PRIx64" new_id=%016"PRIx64"\n",
                       old_owner_id, new_owner->id);
                return -EINVAL;
        }

        port_owner = &rte_eth_devices[port_id].data->owner;
        if (port_owner->id != old_owner_id) {
                RTE_ETHDEV_LOG(ERR,
                        "Cannot set owner to port %u already owned by %s_%016"PRIX64"\n",
                        port_id, port_owner->name, port_owner->id);
                return -EPERM;
        }

        /* can not truncate (same structure) */
        strlcpy(port_owner->name, new_owner->name, RTE_ETH_MAX_OWNER_NAME_LEN);

        port_owner->id = new_owner->id;

        RTE_ETHDEV_LOG(DEBUG, "Port %u owner is %s_%016"PRIx64"\n",
                port_id, new_owner->name, new_owner->id);

        return 0;
}

int
rte_eth_dev_owner_set(const uint16_t port_id,
                      const struct rte_eth_dev_owner *owner)
{
        int ret;

        eth_dev_shared_data_prepare();

        rte_spinlock_lock(&eth_dev_shared_data->ownership_lock);

        ret = eth_dev_owner_set(port_id, RTE_ETH_DEV_NO_OWNER, owner);

        rte_spinlock_unlock(&eth_dev_shared_data->ownership_lock);
        return ret;
}

int
rte_eth_dev_owner_unset(const uint16_t port_id, const uint64_t owner_id)
{
        const struct rte_eth_dev_owner new_owner = (struct rte_eth_dev_owner)
                        {.id = RTE_ETH_DEV_NO_OWNER, .name = ""};
        int ret;

        eth_dev_shared_data_prepare();

        rte_spinlock_lock(&eth_dev_shared_data->ownership_lock);

        ret = eth_dev_owner_set(port_id, owner_id, &new_owner);

        rte_spinlock_unlock(&eth_dev_shared_data->ownership_lock);
        return ret;
}

int
rte_eth_dev_owner_delete(const uint64_t owner_id)
{
        uint16_t port_id;
        int ret = 0;

        eth_dev_shared_data_prepare();

        rte_spinlock_lock(&eth_dev_shared_data->ownership_lock);

        if (eth_is_valid_owner_id(owner_id)) {
                for (port_id = 0; port_id < RTE_MAX_ETHPORTS; port_id++)
                        if (rte_eth_devices[port_id].data->owner.id == owner_id)
                                memset(&rte_eth_devices[port_id].data->owner, 0,
                                       sizeof(struct rte_eth_dev_owner));
                RTE_ETHDEV_LOG(NOTICE,
                        "All port owners owned by %016"PRIx64" identifier have removed\n",
                        owner_id);
        } else {
                RTE_ETHDEV_LOG(ERR,
                               "Invalid owner id=%016"PRIx64"\n",
                               owner_id);
                ret = -EINVAL;
        }

        rte_spinlock_unlock(&eth_dev_shared_data->ownership_lock);

        return ret;
}

int
rte_eth_dev_owner_get(const uint16_t port_id, struct rte_eth_dev_owner *owner)
{
        struct rte_eth_dev *ethdev;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        ethdev = &rte_eth_devices[port_id];

        if (!eth_dev_is_allocated(ethdev)) {
                RTE_ETHDEV_LOG(ERR, "Port id %"PRIu16" is not allocated\n",
                        port_id);
                return -ENODEV;
        }

        if (owner == NULL) {
                RTE_ETHDEV_LOG(ERR, "Cannot get ethdev port %u owner to NULL\n",
                        port_id);
                return -EINVAL;
        }

        eth_dev_shared_data_prepare();

        rte_spinlock_lock(&eth_dev_shared_data->ownership_lock);
        rte_memcpy(owner, &ethdev->data->owner, sizeof(*owner));
        rte_spinlock_unlock(&eth_dev_shared_data->ownership_lock);

        return 0;
}

int
rte_eth_dev_socket_id(uint16_t port_id)
{
        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -1);
        return rte_eth_devices[port_id].data->numa_node;
}

void *
rte_eth_dev_get_sec_ctx(uint16_t port_id)
{
        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, NULL);
        return rte_eth_devices[port_id].security_ctx;
}

uint16_t
rte_eth_dev_count_avail(void)
{
        uint16_t p;
        uint16_t count;

        count = 0;

        RTE_ETH_FOREACH_DEV(p)
                count++;

        return count;
}

uint16_t
rte_eth_dev_count_total(void)
{
        uint16_t port, count = 0;

        RTE_ETH_FOREACH_VALID_DEV(port)
                count++;

        return count;
}

int
rte_eth_dev_get_name_by_port(uint16_t port_id, char *name)
{
        char *tmp;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);

        if (name == NULL) {
                RTE_ETHDEV_LOG(ERR, "Cannot get ethdev port %u name to NULL\n",
                        port_id);
                return -EINVAL;
        }

        /* shouldn't check 'rte_eth_devices[i].data',
         * because it might be overwritten by VDEV PMD */
        tmp = eth_dev_shared_data->data[port_id].name;
        strcpy(name, tmp);
        return 0;
}

int
rte_eth_dev_get_port_by_name(const char *name, uint16_t *port_id)
{
        uint16_t pid;

        if (name == NULL) {
                RTE_ETHDEV_LOG(ERR, "Cannot get port ID from NULL name");
                return -EINVAL;
        }

        if (port_id == NULL) {
                RTE_ETHDEV_LOG(ERR,
                        "Cannot get port ID to NULL for %s\n", name);
                return -EINVAL;
        }

        RTE_ETH_FOREACH_VALID_DEV(pid)
                if (!strcmp(name, eth_dev_shared_data->data[pid].name)) {
                        *port_id = pid;
                        return 0;
                }

        return -ENODEV;
}

static int
eth_err(uint16_t port_id, int ret)
{
        if (ret == 0)
                return 0;
        if (rte_eth_dev_is_removed(port_id))
                return -EIO;
        return ret;
}

static int
eth_dev_rx_queue_config(struct rte_eth_dev *dev, uint16_t nb_queues)
{
        uint16_t old_nb_queues = dev->data->nb_rx_queues;
        void **rxq;
        unsigned i;

        if (dev->data->rx_queues == NULL && nb_queues != 0) { /* first time configuration */
                dev->data->rx_queues = rte_zmalloc("ethdev->rx_queues",
                                sizeof(dev->data->rx_queues[0]) * nb_queues,
                                RTE_CACHE_LINE_SIZE);
                if (dev->data->rx_queues == NULL) {
                        dev->data->nb_rx_queues = 0;
                        return -(ENOMEM);
                }
        } else if (dev->data->rx_queues != NULL && nb_queues != 0) { /* re-configure */
                RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->rx_queue_release, -ENOTSUP);

                rxq = dev->data->rx_queues;

                for (i = nb_queues; i < old_nb_queues; i++)
                        (*dev->dev_ops->rx_queue_release)(rxq[i]);
                rxq = rte_realloc(rxq, sizeof(rxq[0]) * nb_queues,
                                RTE_CACHE_LINE_SIZE);
                if (rxq == NULL)
                        return -(ENOMEM);
                if (nb_queues > old_nb_queues) {
                        uint16_t new_qs = nb_queues - old_nb_queues;

                        memset(rxq + old_nb_queues, 0,
                                sizeof(rxq[0]) * new_qs);
                }

                dev->data->rx_queues = rxq;

        } else if (dev->data->rx_queues != NULL && nb_queues == 0) {
                RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->rx_queue_release, -ENOTSUP);

                rxq = dev->data->rx_queues;

                for (i = nb_queues; i < old_nb_queues; i++)
                        (*dev->dev_ops->rx_queue_release)(rxq[i]);

                rte_free(dev->data->rx_queues);
                dev->data->rx_queues = NULL;
        }
        dev->data->nb_rx_queues = nb_queues;
        return 0;
}

static int
eth_dev_validate_rx_queue(const struct rte_eth_dev *dev, uint16_t rx_queue_id)
{
        uint16_t port_id;

        if (rx_queue_id >= dev->data->nb_rx_queues) {
                port_id = dev->data->port_id;
                RTE_ETHDEV_LOG(ERR,
                               "Invalid Rx queue_id=%u of device with port_id=%u\n",
                               rx_queue_id, port_id);
                return -EINVAL;
        }

        if (dev->data->rx_queues[rx_queue_id] == NULL) {
                port_id = dev->data->port_id;
                RTE_ETHDEV_LOG(ERR,
                               "Queue %u of device with port_id=%u has not been setup\n",
                               rx_queue_id, port_id);
                return -EINVAL;
        }

        return 0;
}

static int
eth_dev_validate_tx_queue(const struct rte_eth_dev *dev, uint16_t tx_queue_id)
{
        uint16_t port_id;

        if (tx_queue_id >= dev->data->nb_tx_queues) {
                port_id = dev->data->port_id;
                RTE_ETHDEV_LOG(ERR,
                               "Invalid Tx queue_id=%u of device with port_id=%u\n",
                               tx_queue_id, port_id);
                return -EINVAL;
        }

        if (dev->data->tx_queues[tx_queue_id] == NULL) {
                port_id = dev->data->port_id;
                RTE_ETHDEV_LOG(ERR,
                               "Queue %u of device with port_id=%u has not been setup\n",
                               tx_queue_id, port_id);
                return -EINVAL;
        }

        return 0;
}

int
rte_eth_dev_rx_queue_start(uint16_t port_id, uint16_t rx_queue_id)
{
        struct rte_eth_dev *dev;
        int ret;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        if (!dev->data->dev_started) {

                RTE_ETHDEV_LOG(ERR,
                        "Port %u must be started before start any queue\n",
                        port_id);
                return -EINVAL;
        }

        ret = eth_dev_validate_rx_queue(dev, rx_queue_id);
        if (ret != 0)
                return ret;

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->rx_queue_start, -ENOTSUP);

        if (rte_eth_dev_is_rx_hairpin_queue(dev, rx_queue_id)) {
                RTE_ETHDEV_LOG(INFO,
                        "Can't start Rx hairpin queue %"PRIu16" of device with port_id=%"PRIu16"\n",
                        rx_queue_id, port_id);
                return -EINVAL;
        }

        if (dev->data->rx_queue_state[rx_queue_id] != RTE_ETH_QUEUE_STATE_STOPPED) {
                RTE_ETHDEV_LOG(INFO,
                        "Queue %"PRIu16" of device with port_id=%"PRIu16" already started\n",
                        rx_queue_id, port_id);
                return 0;
        }

        return eth_err(port_id, dev->dev_ops->rx_queue_start(dev, rx_queue_id));
}

int
rte_eth_dev_rx_queue_stop(uint16_t port_id, uint16_t rx_queue_id)
{
        struct rte_eth_dev *dev;
        int ret;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        ret = eth_dev_validate_rx_queue(dev, rx_queue_id);
        if (ret != 0)
                return ret;

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->rx_queue_stop, -ENOTSUP);

        if (rte_eth_dev_is_rx_hairpin_queue(dev, rx_queue_id)) {
                RTE_ETHDEV_LOG(INFO,
                        "Can't stop Rx hairpin queue %"PRIu16" of device with port_id=%"PRIu16"\n",
                        rx_queue_id, port_id);
                return -EINVAL;
        }

        if (dev->data->rx_queue_state[rx_queue_id] == RTE_ETH_QUEUE_STATE_STOPPED) {
                RTE_ETHDEV_LOG(INFO,
                        "Queue %"PRIu16" of device with port_id=%"PRIu16" already stopped\n",
                        rx_queue_id, port_id);
                return 0;
        }

        return eth_err(port_id, dev->dev_ops->rx_queue_stop(dev, rx_queue_id));
}

int
rte_eth_dev_tx_queue_start(uint16_t port_id, uint16_t tx_queue_id)
{
        struct rte_eth_dev *dev;
        int ret;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        if (!dev->data->dev_started) {
                RTE_ETHDEV_LOG(ERR,
                        "Port %u must be started before start any queue\n",
                        port_id);
                return -EINVAL;
        }

        ret = eth_dev_validate_tx_queue(dev, tx_queue_id);
        if (ret != 0)
                return ret;

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->tx_queue_start, -ENOTSUP);

        if (rte_eth_dev_is_tx_hairpin_queue(dev, tx_queue_id)) {
                RTE_ETHDEV_LOG(INFO,
                        "Can't start Tx hairpin queue %"PRIu16" of device with port_id=%"PRIu16"\n",
                        tx_queue_id, port_id);
                return -EINVAL;
        }

        if (dev->data->tx_queue_state[tx_queue_id] != RTE_ETH_QUEUE_STATE_STOPPED) {
                RTE_ETHDEV_LOG(INFO,
                        "Queue %"PRIu16" of device with port_id=%"PRIu16" already started\n",
                        tx_queue_id, port_id);
                return 0;
        }

        return eth_err(port_id, dev->dev_ops->tx_queue_start(dev, tx_queue_id));
}

int
rte_eth_dev_tx_queue_stop(uint16_t port_id, uint16_t tx_queue_id)
{
        struct rte_eth_dev *dev;
        int ret;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        ret = eth_dev_validate_tx_queue(dev, tx_queue_id);
        if (ret != 0)
                return ret;

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->tx_queue_stop, -ENOTSUP);

        if (rte_eth_dev_is_tx_hairpin_queue(dev, tx_queue_id)) {
                RTE_ETHDEV_LOG(INFO,
                        "Can't stop Tx hairpin queue %"PRIu16" of device with port_id=%"PRIu16"\n",
                        tx_queue_id, port_id);
                return -EINVAL;
        }

        if (dev->data->tx_queue_state[tx_queue_id] == RTE_ETH_QUEUE_STATE_STOPPED) {
                RTE_ETHDEV_LOG(INFO,
                        "Queue %"PRIu16" of device with port_id=%"PRIu16" already stopped\n",
                        tx_queue_id, port_id);
                return 0;
        }

        return eth_err(port_id, dev->dev_ops->tx_queue_stop(dev, tx_queue_id));
}

static int
eth_dev_tx_queue_config(struct rte_eth_dev *dev, uint16_t nb_queues)
{
        uint16_t old_nb_queues = dev->data->nb_tx_queues;
        void **txq;
        unsigned i;

        if (dev->data->tx_queues == NULL && nb_queues != 0) { /* first time configuration */
                dev->data->tx_queues = rte_zmalloc("ethdev->tx_queues",
                                                   sizeof(dev->data->tx_queues[0]) * nb_queues,
                                                   RTE_CACHE_LINE_SIZE);
                if (dev->data->tx_queues == NULL) {
                        dev->data->nb_tx_queues = 0;
                        return -(ENOMEM);
                }
        } else if (dev->data->tx_queues != NULL && nb_queues != 0) { /* re-configure */
                RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->tx_queue_release, -ENOTSUP);

                txq = dev->data->tx_queues;

                for (i = nb_queues; i < old_nb_queues; i++)
                        (*dev->dev_ops->tx_queue_release)(txq[i]);
                txq = rte_realloc(txq, sizeof(txq[0]) * nb_queues,
                                  RTE_CACHE_LINE_SIZE);
                if (txq == NULL)
                        return -ENOMEM;
                if (nb_queues > old_nb_queues) {
                        uint16_t new_qs = nb_queues - old_nb_queues;

                        memset(txq + old_nb_queues, 0,
                               sizeof(txq[0]) * new_qs);
                }

                dev->data->tx_queues = txq;

        } else if (dev->data->tx_queues != NULL && nb_queues == 0) {
                RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->tx_queue_release, -ENOTSUP);

                txq = dev->data->tx_queues;

                for (i = nb_queues; i < old_nb_queues; i++)
                        (*dev->dev_ops->tx_queue_release)(txq[i]);

                rte_free(dev->data->tx_queues);
                dev->data->tx_queues = NULL;
        }
        dev->data->nb_tx_queues = nb_queues;
        return 0;
}

uint32_t
rte_eth_speed_bitflag(uint32_t speed, int duplex)
{
        switch (speed) {
        case ETH_SPEED_NUM_10M:
                return duplex ? ETH_LINK_SPEED_10M : ETH_LINK_SPEED_10M_HD;
        case ETH_SPEED_NUM_100M:
                return duplex ? ETH_LINK_SPEED_100M : ETH_LINK_SPEED_100M_HD;
        case ETH_SPEED_NUM_1G:
                return ETH_LINK_SPEED_1G;
        case ETH_SPEED_NUM_2_5G:
                return ETH_LINK_SPEED_2_5G;
        case ETH_SPEED_NUM_5G:
                return ETH_LINK_SPEED_5G;
        case ETH_SPEED_NUM_10G:
                return ETH_LINK_SPEED_10G;
        case ETH_SPEED_NUM_20G:
                return ETH_LINK_SPEED_20G;
        case ETH_SPEED_NUM_25G:
                return ETH_LINK_SPEED_25G;
        case ETH_SPEED_NUM_40G:
                return ETH_LINK_SPEED_40G;
        case ETH_SPEED_NUM_50G:
                return ETH_LINK_SPEED_50G;
        case ETH_SPEED_NUM_56G:
                return ETH_LINK_SPEED_56G;
        case ETH_SPEED_NUM_100G:
                return ETH_LINK_SPEED_100G;
        case ETH_SPEED_NUM_200G:
                return ETH_LINK_SPEED_200G;
        default:
                return 0;
        }
}

const char *
rte_eth_dev_rx_offload_name(uint64_t offload)
{
        const char *name = "UNKNOWN";
        unsigned int i;

        for (i = 0; i < RTE_DIM(eth_dev_rx_offload_names); ++i) {
                if (offload == eth_dev_rx_offload_names[i].offload) {
                        name = eth_dev_rx_offload_names[i].name;
                        break;
                }
        }

        return name;
}

const char *
rte_eth_dev_tx_offload_name(uint64_t offload)
{
        const char *name = "UNKNOWN";
        unsigned int i;

        for (i = 0; i < RTE_DIM(eth_dev_tx_offload_names); ++i) {
                if (offload == eth_dev_tx_offload_names[i].offload) {
                        name = eth_dev_tx_offload_names[i].name;
                        break;
                }
        }

        return name;
}

static inline int
eth_dev_check_lro_pkt_size(uint16_t port_id, uint32_t config_size,
                   uint32_t max_rx_pkt_len, uint32_t dev_info_size)
{
        int ret = 0;

        if (dev_info_size == 0) {
                if (config_size != max_rx_pkt_len) {
                        RTE_ETHDEV_LOG(ERR, "Ethdev port_id=%d max_lro_pkt_size"
                                       " %u != %u is not allowed\n",
                                       port_id, config_size, max_rx_pkt_len);
                        ret = -EINVAL;
                }
        } else if (config_size > dev_info_size) {
                RTE_ETHDEV_LOG(ERR, "Ethdev port_id=%d max_lro_pkt_size %u "
                               "> max allowed value %u\n", port_id, config_size,
                               dev_info_size);
                ret = -EINVAL;
        } else if (config_size < RTE_ETHER_MIN_LEN) {
                RTE_ETHDEV_LOG(ERR, "Ethdev port_id=%d max_lro_pkt_size %u "
                               "< min allowed value %u\n", port_id, config_size,
                               (unsigned int)RTE_ETHER_MIN_LEN);
                ret = -EINVAL;
        }
        return ret;
}

/*
 * Validate offloads that are requested through rte_eth_dev_configure against
 * the offloads successfully set by the ethernet device.
 *
 * @param port_id
 *   The port identifier of the Ethernet device.
 * @param req_offloads
 *   The offloads that have been requested through `rte_eth_dev_configure`.
 * @param set_offloads
 *   The offloads successfully set by the ethernet device.
 * @param offload_type
 *   The offload type i.e. Rx/Tx string.
 * @param offload_name
 *   The function that prints the offload name.
 * @return
 *   - (0) if validation successful.
 *   - (-EINVAL) if requested offload has been silently disabled.
 *
 */
static int
eth_dev_validate_offloads(uint16_t port_id, uint64_t req_offloads,
                  uint64_t set_offloads, const char *offload_type,
                  const char *(*offload_name)(uint64_t))
{
        uint64_t offloads_diff = req_offloads ^ set_offloads;
        uint64_t offload;
        int ret = 0;

        while (offloads_diff != 0) {
                /* Check if any offload is requested but not enabled. */
                offload = 1ULL << __builtin_ctzll(offloads_diff);
                if (offload & req_offloads) {
                        RTE_ETHDEV_LOG(ERR,
                                "Port %u failed to enable %s offload %s\n",
                                port_id, offload_type, offload_name(offload));
                        ret = -EINVAL;
                }

                /* Check if offload couldn't be disabled. */
                if (offload & set_offloads) {
                        RTE_ETHDEV_LOG(DEBUG,
                                "Port %u %s offload %s is not requested but enabled\n",
                                port_id, offload_type, offload_name(offload));
                }

                offloads_diff &= ~offload;
        }

        return ret;
}

int
rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
                      const struct rte_eth_conf *dev_conf)
{
        struct rte_eth_dev *dev;
        struct rte_eth_dev_info dev_info;
        struct rte_eth_conf orig_conf;
        uint16_t overhead_len;
        int diag;
        int ret;
        uint16_t old_mtu;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        if (dev_conf == NULL) {
                RTE_ETHDEV_LOG(ERR,
                        "Cannot configure ethdev port %u from NULL config\n",
                        port_id);
                return -EINVAL;
        }

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->dev_configure, -ENOTSUP);

        if (dev->data->dev_started) {
                RTE_ETHDEV_LOG(ERR,
                        "Port %u must be stopped to allow configuration\n",
                        port_id);
                return -EBUSY;
        }

        /*
         * Ensure that "dev_configured" is always 0 each time prepare to do
         * dev_configure() to avoid any non-anticipated behaviour.
         * And set to 1 when dev_configure() is executed successfully.
         */
        dev->data->dev_configured = 0;

         /* Store original config, as rollback required on failure */
        memcpy(&orig_conf, &dev->data->dev_conf, sizeof(dev->data->dev_conf));

        /*
         * Copy the dev_conf parameter into the dev structure.
         * rte_eth_dev_info_get() requires dev_conf, copy it before dev_info get
         */
        if (dev_conf != &dev->data->dev_conf)
                memcpy(&dev->data->dev_conf, dev_conf,
                       sizeof(dev->data->dev_conf));

        /* Backup mtu for rollback */
        old_mtu = dev->data->mtu;

        ret = rte_eth_dev_info_get(port_id, &dev_info);
        if (ret != 0)
                goto rollback;

        /* Get the real Ethernet overhead length */
        if (dev_info.max_mtu != UINT16_MAX &&
            dev_info.max_rx_pktlen > dev_info.max_mtu)
                overhead_len = dev_info.max_rx_pktlen - dev_info.max_mtu;
        else
                overhead_len = RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN;

        /* If number of queues specified by application for both Rx and Tx is
         * zero, use driver preferred values. This cannot be done individually
         * as it is valid for either Tx or Rx (but not both) to be zero.
         * If driver does not provide any preferred valued, fall back on
         * EAL defaults.
         */
        if (nb_rx_q == 0 && nb_tx_q == 0) {
                nb_rx_q = dev_info.default_rxportconf.nb_queues;
                if (nb_rx_q == 0)
                        nb_rx_q = RTE_ETH_DEV_FALLBACK_RX_NBQUEUES;
                nb_tx_q = dev_info.default_txportconf.nb_queues;
                if (nb_tx_q == 0)
                        nb_tx_q = RTE_ETH_DEV_FALLBACK_TX_NBQUEUES;
        }

        if (nb_rx_q > RTE_MAX_QUEUES_PER_PORT) {
                RTE_ETHDEV_LOG(ERR,
                        "Number of RX queues requested (%u) is greater than max supported(%d)\n",
                        nb_rx_q, RTE_MAX_QUEUES_PER_PORT);
                ret = -EINVAL;
                goto rollback;
        }

        if (nb_tx_q > RTE_MAX_QUEUES_PER_PORT) {
                RTE_ETHDEV_LOG(ERR,
                        "Number of TX queues requested (%u) is greater than max supported(%d)\n",
                        nb_tx_q, RTE_MAX_QUEUES_PER_PORT);
                ret = -EINVAL;
                goto rollback;
        }

        /*
         * Check that the numbers of RX and TX queues are not greater
         * than the maximum number of RX and TX queues supported by the
         * configured device.
         */
        if (nb_rx_q > dev_info.max_rx_queues) {
                RTE_ETHDEV_LOG(ERR, "Ethdev port_id=%u nb_rx_queues=%u > %u\n",
                        port_id, nb_rx_q, dev_info.max_rx_queues);
                ret = -EINVAL;
                goto rollback;
        }

        if (nb_tx_q > dev_info.max_tx_queues) {
                RTE_ETHDEV_LOG(ERR, "Ethdev port_id=%u nb_tx_queues=%u > %u\n",
                        port_id, nb_tx_q, dev_info.max_tx_queues);
                ret = -EINVAL;
                goto rollback;
        }

        /* Check that the device supports requested interrupts */
        if ((dev_conf->intr_conf.lsc == 1) &&
                        (!(dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC))) {
                RTE_ETHDEV_LOG(ERR, "Driver %s does not support lsc\n",
                        dev->device->driver->name);
                ret = -EINVAL;
                goto rollback;
        }
        if ((dev_conf->intr_conf.rmv == 1) &&
                        (!(dev->data->dev_flags & RTE_ETH_DEV_INTR_RMV))) {
                RTE_ETHDEV_LOG(ERR, "Driver %s does not support rmv\n",
                        dev->device->driver->name);
                ret = -EINVAL;
                goto rollback;
        }

        /*
         * If jumbo frames are enabled, check that the maximum RX packet
         * length is supported by the configured device.
         */
        if (dev_conf->rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
                if (dev_conf->rxmode.max_rx_pkt_len > dev_info.max_rx_pktlen) {
                        RTE_ETHDEV_LOG(ERR,
                                "Ethdev port_id=%u max_rx_pkt_len %u > max valid value %u\n",
                                port_id, dev_conf->rxmode.max_rx_pkt_len,
                                dev_info.max_rx_pktlen);
                        ret = -EINVAL;
                        goto rollback;
                } else if (dev_conf->rxmode.max_rx_pkt_len < RTE_ETHER_MIN_LEN) {
                        RTE_ETHDEV_LOG(ERR,
                                "Ethdev port_id=%u max_rx_pkt_len %u < min valid value %u\n",
                                port_id, dev_conf->rxmode.max_rx_pkt_len,
                                (unsigned int)RTE_ETHER_MIN_LEN);
                        ret = -EINVAL;
                        goto rollback;
                }

                /* Scale the MTU size to adapt max_rx_pkt_len */
                dev->data->mtu = dev->data->dev_conf.rxmode.max_rx_pkt_len -
                                overhead_len;
        } else {
                uint16_t pktlen = dev_conf->rxmode.max_rx_pkt_len;
                if (pktlen < RTE_ETHER_MIN_MTU + overhead_len ||
                    pktlen > RTE_ETHER_MTU + overhead_len)
                        /* Use default value */
                        dev->data->dev_conf.rxmode.max_rx_pkt_len =
                                                RTE_ETHER_MTU + overhead_len;
        }

        /*
         * If LRO is enabled, check that the maximum aggregated packet
         * size is supported by the configured device.
         */
        if (dev_conf->rxmode.offloads & DEV_RX_OFFLOAD_TCP_LRO) {
                if (dev_conf->rxmode.max_lro_pkt_size == 0)
                        dev->data->dev_conf.rxmode.max_lro_pkt_size =
                                dev->data->dev_conf.rxmode.max_rx_pkt_len;
                ret = eth_dev_check_lro_pkt_size(port_id,
                                dev->data->dev_conf.rxmode.max_lro_pkt_size,
                                dev->data->dev_conf.rxmode.max_rx_pkt_len,
                                dev_info.max_lro_pkt_size);
                if (ret != 0)
                        goto rollback;
        }

        /* Any requested offloading must be within its device capabilities */
        if ((dev_conf->rxmode.offloads & dev_info.rx_offload_capa) !=
             dev_conf->rxmode.offloads) {
                RTE_ETHDEV_LOG(ERR,
                        "Ethdev port_id=%u requested Rx offloads 0x%"PRIx64" doesn't match Rx offloads "
                        "capabilities 0x%"PRIx64" in %s()\n",
                        port_id, dev_conf->rxmode.offloads,
                        dev_info.rx_offload_capa,
                        __func__);
                ret = -EINVAL;
                goto rollback;
        }
        if ((dev_conf->txmode.offloads & dev_info.tx_offload_capa) !=
             dev_conf->txmode.offloads) {
                RTE_ETHDEV_LOG(ERR,
                        "Ethdev port_id=%u requested Tx offloads 0x%"PRIx64" doesn't match Tx offloads "
                        "capabilities 0x%"PRIx64" in %s()\n",
                        port_id, dev_conf->txmode.offloads,
                        dev_info.tx_offload_capa,
                        __func__);
                ret = -EINVAL;
                goto rollback;
        }

        dev->data->dev_conf.rx_adv_conf.rss_conf.rss_hf =
                rte_eth_rss_hf_refine(dev_conf->rx_adv_conf.rss_conf.rss_hf);

        /* Check that device supports requested rss hash functions. */
        if ((dev_info.flow_type_rss_offloads |
             dev_conf->rx_adv_conf.rss_conf.rss_hf) !=
            dev_info.flow_type_rss_offloads) {
                RTE_ETHDEV_LOG(ERR,
                        "Ethdev port_id=%u invalid rss_hf: 0x%"PRIx64", valid value: 0x%"PRIx64"\n",
                        port_id, dev_conf->rx_adv_conf.rss_conf.rss_hf,
                        dev_info.flow_type_rss_offloads);
                ret = -EINVAL;
                goto rollback;
        }

        /* Check if Rx RSS distribution is disabled but RSS hash is enabled. */
        if (((dev_conf->rxmode.mq_mode & ETH_MQ_RX_RSS_FLAG) == 0) &&
            (dev_conf->rxmode.offloads & DEV_RX_OFFLOAD_RSS_HASH)) {
                RTE_ETHDEV_LOG(ERR,
                        "Ethdev port_id=%u config invalid Rx mq_mode without RSS but %s offload is requested\n",
                        port_id,
                        rte_eth_dev_rx_offload_name(DEV_RX_OFFLOAD_RSS_HASH));
                ret = -EINVAL;
                goto rollback;
        }

        /*
         * Setup new number of RX/TX queues and reconfigure device.
         */
        diag = eth_dev_rx_queue_config(dev, nb_rx_q);
        if (diag != 0) {
                RTE_ETHDEV_LOG(ERR,
                        "Port%u eth_dev_rx_queue_config = %d\n",
                        port_id, diag);
                ret = diag;
                goto rollback;
        }

        diag = eth_dev_tx_queue_config(dev, nb_tx_q);
        if (diag != 0) {
                RTE_ETHDEV_LOG(ERR,
                        "Port%u eth_dev_tx_queue_config = %d\n",
                        port_id, diag);
                eth_dev_rx_queue_config(dev, 0);
                ret = diag;
                goto rollback;
        }

        diag = (*dev->dev_ops->dev_configure)(dev);
        if (diag != 0) {
                RTE_ETHDEV_LOG(ERR, "Port%u dev_configure = %d\n",
                        port_id, diag);
                ret = eth_err(port_id, diag);
                goto reset_queues;
        }

        /* Initialize Rx profiling if enabled at compilation time. */
        diag = __rte_eth_dev_profile_init(port_id, dev);
        if (diag != 0) {
                RTE_ETHDEV_LOG(ERR, "Port%u __rte_eth_dev_profile_init = %d\n",
                        port_id, diag);
                ret = eth_err(port_id, diag);
                goto reset_queues;
        }

        /* Validate Rx offloads. */
        diag = eth_dev_validate_offloads(port_id,
                        dev_conf->rxmode.offloads,
                        dev->data->dev_conf.rxmode.offloads, "Rx",
                        rte_eth_dev_rx_offload_name);
        if (diag != 0) {
                ret = diag;
                goto reset_queues;
        }

        /* Validate Tx offloads. */
        diag = eth_dev_validate_offloads(port_id,
                        dev_conf->txmode.offloads,
                        dev->data->dev_conf.txmode.offloads, "Tx",
                        rte_eth_dev_tx_offload_name);
        if (diag != 0) {
                ret = diag;
                goto reset_queues;
        }

        dev->data->dev_configured = 1;
        rte_ethdev_trace_configure(port_id, nb_rx_q, nb_tx_q, dev_conf, 0);
        return 0;
reset_queues:
        eth_dev_rx_queue_config(dev, 0);
        eth_dev_tx_queue_config(dev, 0);
rollback:
        memcpy(&dev->data->dev_conf, &orig_conf, sizeof(dev->data->dev_conf));
        if (old_mtu != dev->data->mtu)
                dev->data->mtu = old_mtu;

        rte_ethdev_trace_configure(port_id, nb_rx_q, nb_tx_q, dev_conf, ret);
        return ret;
}

void
rte_eth_dev_internal_reset(struct rte_eth_dev *dev)
{
        if (dev->data->dev_started) {
                RTE_ETHDEV_LOG(ERR, "Port %u must be stopped to allow reset\n",
                        dev->data->port_id);
                return;
        }

        eth_dev_rx_queue_config(dev, 0);
        eth_dev_tx_queue_config(dev, 0);

        memset(&dev->data->dev_conf, 0, sizeof(dev->data->dev_conf));
}

static void
eth_dev_mac_restore(struct rte_eth_dev *dev,
                        struct rte_eth_dev_info *dev_info)
{
        struct rte_ether_addr *addr;
        uint16_t i;
        uint32_t pool = 0;
        uint64_t pool_mask;

        /* replay MAC address configuration including default MAC */
        addr = &dev->data->mac_addrs[0];
        if (*dev->dev_ops->mac_addr_set != NULL)
                (*dev->dev_ops->mac_addr_set)(dev, addr);
        else if (*dev->dev_ops->mac_addr_add != NULL)
                (*dev->dev_ops->mac_addr_add)(dev, addr, 0, pool);

        if (*dev->dev_ops->mac_addr_add != NULL) {
                for (i = 1; i < dev_info->max_mac_addrs; i++) {
                        addr = &dev->data->mac_addrs[i];

                        /* skip zero address */
                        if (rte_is_zero_ether_addr(addr))
                                continue;

                        pool = 0;
                        pool_mask = dev->data->mac_pool_sel[i];

                        do {
                                if (pool_mask & 1ULL)
                                        (*dev->dev_ops->mac_addr_add)(dev,
                                                addr, i, pool);
                                pool_mask >>= 1;
                                pool++;
                        } while (pool_mask);
                }
        }
}

static int
eth_dev_config_restore(struct rte_eth_dev *dev,
                struct rte_eth_dev_info *dev_info, uint16_t port_id)
{
        int ret;

        if (!(*dev_info->dev_flags & RTE_ETH_DEV_NOLIVE_MAC_ADDR))
                eth_dev_mac_restore(dev, dev_info);

        /* replay promiscuous configuration */
        /*
         * use callbacks directly since we don't need port_id check and
         * would like to bypass the same value set
         */
        if (rte_eth_promiscuous_get(port_id) == 1 &&
            *dev->dev_ops->promiscuous_enable != NULL) {
                ret = eth_err(port_id,
                              (*dev->dev_ops->promiscuous_enable)(dev));
                if (ret != 0 && ret != -ENOTSUP) {
                        RTE_ETHDEV_LOG(ERR,
                                "Failed to enable promiscuous mode for device (port %u): %s\n",
                                port_id, rte_strerror(-ret));
                        return ret;
                }
        } else if (rte_eth_promiscuous_get(port_id) == 0 &&
                   *dev->dev_ops->promiscuous_disable != NULL) {
                ret = eth_err(port_id,
                              (*dev->dev_ops->promiscuous_disable)(dev));
                if (ret != 0 && ret != -ENOTSUP) {
                        RTE_ETHDEV_LOG(ERR,
                                "Failed to disable promiscuous mode for device (port %u): %s\n",
                                port_id, rte_strerror(-ret));
                        return ret;
                }
        }

        /* replay all multicast configuration */
        /*
         * use callbacks directly since we don't need port_id check and
         * would like to bypass the same value set
         */
        if (rte_eth_allmulticast_get(port_id) == 1 &&
            *dev->dev_ops->allmulticast_enable != NULL) {
                ret = eth_err(port_id,
                              (*dev->dev_ops->allmulticast_enable)(dev));
                if (ret != 0 && ret != -ENOTSUP) {
                        RTE_ETHDEV_LOG(ERR,
                                "Failed to enable allmulticast mode for device (port %u): %s\n",
                                port_id, rte_strerror(-ret));
                        return ret;
                }
        } else if (rte_eth_allmulticast_get(port_id) == 0 &&
                   *dev->dev_ops->allmulticast_disable != NULL) {
                ret = eth_err(port_id,
                              (*dev->dev_ops->allmulticast_disable)(dev));
                if (ret != 0 && ret != -ENOTSUP) {
                        RTE_ETHDEV_LOG(ERR,
                                "Failed to disable allmulticast mode for device (port %u): %s\n",
                                port_id, rte_strerror(-ret));
                        return ret;
                }
        }

        return 0;
}

int
rte_eth_dev_start(uint16_t port_id)
{
        struct rte_eth_dev *dev;
        struct rte_eth_dev_info dev_info;
        int diag;
        int ret, ret_stop;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->dev_start, -ENOTSUP);

        if (dev->data->dev_configured == 0) {
                RTE_ETHDEV_LOG(INFO,
                        "Device with port_id=%"PRIu16" is not configured.\n",
                        port_id);
                return -EINVAL;
        }

        if (dev->data->dev_started != 0) {
                RTE_ETHDEV_LOG(INFO,
                        "Device with port_id=%"PRIu16" already started\n",
                        port_id);
                return 0;
        }

        ret = rte_eth_dev_info_get(port_id, &dev_info);
        if (ret != 0)
                return ret;

        /* Lets restore MAC now if device does not support live change */
        if (*dev_info.dev_flags & RTE_ETH_DEV_NOLIVE_MAC_ADDR)
                eth_dev_mac_restore(dev, &dev_info);

        diag = (*dev->dev_ops->dev_start)(dev);
        if (diag == 0)
                dev->data->dev_started = 1;
        else
                return eth_err(port_id, diag);

        ret = eth_dev_config_restore(dev, &dev_info, port_id);
        if (ret != 0) {
                RTE_ETHDEV_LOG(ERR,
                        "Error during restoring configuration for device (port %u): %s\n",
                        port_id, rte_strerror(-ret));
                ret_stop = rte_eth_dev_stop(port_id);
                if (ret_stop != 0) {
                        RTE_ETHDEV_LOG(ERR,
                                "Failed to stop device (port %u): %s\n",
                                port_id, rte_strerror(-ret_stop));
                }

                return ret;
        }

        if (dev->data->dev_conf.intr_conf.lsc == 0) {
                RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->link_update, -ENOTSUP);
                (*dev->dev_ops->link_update)(dev, 0);
        }

        rte_ethdev_trace_start(port_id);
        return 0;
}

int
rte_eth_dev_stop(uint16_t port_id)
{
        struct rte_eth_dev *dev;
        int ret;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->dev_stop, -ENOTSUP);

        if (dev->data->dev_started == 0) {
                RTE_ETHDEV_LOG(INFO,
                        "Device with port_id=%"PRIu16" already stopped\n",
                        port_id);
                return 0;
        }

        dev->data->dev_started = 0;
        ret = (*dev->dev_ops->dev_stop)(dev);
        rte_ethdev_trace_stop(port_id, ret);

        return ret;
}

int
rte_eth_dev_set_link_up(uint16_t port_id)
{
        struct rte_eth_dev *dev;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->dev_set_link_up, -ENOTSUP);
        return eth_err(port_id, (*dev->dev_ops->dev_set_link_up)(dev));
}

int
rte_eth_dev_set_link_down(uint16_t port_id)
{
        struct rte_eth_dev *dev;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->dev_set_link_down, -ENOTSUP);
        return eth_err(port_id, (*dev->dev_ops->dev_set_link_down)(dev));
}

int
rte_eth_dev_close(uint16_t port_id)
{
        struct rte_eth_dev *dev;
        int firsterr, binerr;
        int *lasterr = &firsterr;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->dev_close, -ENOTSUP);
        *lasterr = (*dev->dev_ops->dev_close)(dev);
        if (*lasterr != 0)
                lasterr = &binerr;

        rte_ethdev_trace_close(port_id);
        *lasterr = rte_eth_dev_release_port(dev);

        return firsterr;
}

int
rte_eth_dev_reset(uint16_t port_id)
{
        struct rte_eth_dev *dev;
        int ret;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->dev_reset, -ENOTSUP);

        ret = rte_eth_dev_stop(port_id);
        if (ret != 0) {
                RTE_ETHDEV_LOG(ERR,
                        "Failed to stop device (port %u) before reset: %s - ignore\n",
                        port_id, rte_strerror(-ret));
        }
        ret = dev->dev_ops->dev_reset(dev);

        return eth_err(port_id, ret);
}

int
rte_eth_dev_is_removed(uint16_t port_id)
{
        struct rte_eth_dev *dev;
        int ret;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, 0);
        dev = &rte_eth_devices[port_id];

        if (dev->state == RTE_ETH_DEV_REMOVED)
                return 1;

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->is_removed, 0);

        ret = dev->dev_ops->is_removed(dev);
        if (ret != 0)
                /* Device is physically removed. */
                dev->state = RTE_ETH_DEV_REMOVED;

        return ret;
}

static int
rte_eth_rx_queue_check_split(const struct rte_eth_rxseg_split *rx_seg,
                             uint16_t n_seg, uint32_t *mbp_buf_size,
                             const struct rte_eth_dev_info *dev_info)
{
        const struct rte_eth_rxseg_capa *seg_capa = &dev_info->rx_seg_capa;
        struct rte_mempool *mp_first;
        uint32_t offset_mask;
        uint16_t seg_idx;

        if (n_seg > seg_capa->max_nseg) {
                RTE_ETHDEV_LOG(ERR,
                               "Requested Rx segments %u exceed supported %u\n",
                               n_seg, seg_capa->max_nseg);
                return -EINVAL;
        }
        /*
         * Check the sizes and offsets against buffer sizes
         * for each segment specified in extended configuration.
         */
        mp_first = rx_seg[0].mp;
        offset_mask = (1u << seg_capa->offset_align_log2) - 1;
        for (seg_idx = 0; seg_idx < n_seg; seg_idx++) {
                struct rte_mempool *mpl = rx_seg[seg_idx].mp;
                uint32_t length = rx_seg[seg_idx].length;
                uint32_t offset = rx_seg[seg_idx].offset;

                if (mpl == NULL) {
                        RTE_ETHDEV_LOG(ERR, "null mempool pointer\n");
                        return -EINVAL;
                }
                if (seg_idx != 0 && mp_first != mpl &&
                    seg_capa->multi_pools == 0) {
                        RTE_ETHDEV_LOG(ERR, "Receiving to multiple pools is not supported\n");
                        return -ENOTSUP;
                }
                if (offset != 0) {
                        if (seg_capa->offset_allowed == 0) {
                                RTE_ETHDEV_LOG(ERR, "Rx segmentation with offset is not supported\n");
                                return -ENOTSUP;
                        }
                        if (offset & offset_mask) {
                                RTE_ETHDEV_LOG(ERR, "Rx segmentation invalid offset alignment %u, %u\n",
                                               offset,
                                               seg_capa->offset_align_log2);
                                return -EINVAL;
                        }
                }
                if (mpl->private_data_size <
                        sizeof(struct rte_pktmbuf_pool_private)) {
                        RTE_ETHDEV_LOG(ERR,
                                       "%s private_data_size %u < %u\n",
                                       mpl->name, mpl->private_data_size,
                                       (unsigned int)sizeof
                                        (struct rte_pktmbuf_pool_private));
                        return -ENOSPC;
                }
                offset += seg_idx != 0 ? 0 : RTE_PKTMBUF_HEADROOM;
                *mbp_buf_size = rte_pktmbuf_data_room_size(mpl);
                length = length != 0 ? length : *mbp_buf_size;
                if (*mbp_buf_size < length + offset) {
                        RTE_ETHDEV_LOG(ERR,
                                       "%s mbuf_data_room_size %u < %u (segment length=%u + segment offset=%u)\n",
                                       mpl->name, *mbp_buf_size,
                                       length + offset, length, offset);
                        return -EINVAL;
                }
        }
        return 0;
}

int
rte_eth_rx_queue_setup(uint16_t port_id, uint16_t rx_queue_id,

                       uint16_t nb_rx_desc, unsigned int socket_id,
                       const struct rte_eth_rxconf *rx_conf,
                       struct rte_mempool *mp)
{
        int ret;
        uint32_t mbp_buf_size;
        struct rte_eth_dev *dev;
        struct rte_eth_dev_info dev_info;
        struct rte_eth_rxconf local_conf;
        void **rxq;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        if (rx_queue_id >= dev->data->nb_rx_queues) {
                RTE_ETHDEV_LOG(ERR, "Invalid RX queue_id=%u\n", rx_queue_id);
                return -EINVAL;
        }

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->rx_queue_setup, -ENOTSUP);

        ret = rte_eth_dev_info_get(port_id, &dev_info);
        if (ret != 0)
                return ret;

        if (mp != NULL) {
                /* Single pool configuration check. */
                if (rx_conf != NULL && rx_conf->rx_nseg != 0) {
                        RTE_ETHDEV_LOG(ERR,
                                       "Ambiguous segment configuration\n");
                        return -EINVAL;
                }
                /*
                 * Check the size of the mbuf data buffer, this value
                 * must be provided in the private data of the memory pool.
                 * First check that the memory pool(s) has a valid private data.
                 */
                if (mp->private_data_size <
                                sizeof(struct rte_pktmbuf_pool_private)) {
                        RTE_ETHDEV_LOG(ERR, "%s private_data_size %u < %u\n",
                                mp->name, mp->private_data_size,
                                (unsigned int)
                                sizeof(struct rte_pktmbuf_pool_private));
                        return -ENOSPC;
                }
                mbp_buf_size = rte_pktmbuf_data_room_size(mp);
                if (mbp_buf_size < dev_info.min_rx_bufsize +
                                   RTE_PKTMBUF_HEADROOM) {
                        RTE_ETHDEV_LOG(ERR,
                                       "%s mbuf_data_room_size %u < %u (RTE_PKTMBUF_HEADROOM=%u + min_rx_bufsize(dev)=%u)\n",
                                       mp->name, mbp_buf_size,
                                       RTE_PKTMBUF_HEADROOM +
                                       dev_info.min_rx_bufsize,
                                       RTE_PKTMBUF_HEADROOM,
                                       dev_info.min_rx_bufsize);
                        return -EINVAL;
                }
        } else {
                const struct rte_eth_rxseg_split *rx_seg;
                uint16_t n_seg;

                /* Extended multi-segment configuration check. */
                if (rx_conf == NULL || rx_conf->rx_seg == NULL || rx_conf->rx_nseg == 0) {
                        RTE_ETHDEV_LOG(ERR,
                                       "Memory pool is null and no extended configuration provided\n");
                        return -EINVAL;
                }

                rx_seg = (const struct rte_eth_rxseg_split *)rx_conf->rx_seg;
                n_seg = rx_conf->rx_nseg;

                if (rx_conf->offloads & RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT) {
                        ret = rte_eth_rx_queue_check_split(rx_seg, n_seg,
                                                           &mbp_buf_size,
                                                           &dev_info);
                        if (ret != 0)
                                return ret;
                } else {
                        RTE_ETHDEV_LOG(ERR, "No Rx segmentation offload configured\n");
                        return -EINVAL;
                }
        }

        /* Use default specified by driver, if nb_rx_desc is zero */
        if (nb_rx_desc == 0) {
                nb_rx_desc = dev_info.default_rxportconf.ring_size;
                /* If driver default is also zero, fall back on EAL default */
                if (nb_rx_desc == 0)
                        nb_rx_desc = RTE_ETH_DEV_FALLBACK_RX_RINGSIZE;
        }

        if (nb_rx_desc > dev_info.rx_desc_lim.nb_max ||
                        nb_rx_desc < dev_info.rx_desc_lim.nb_min ||
                        nb_rx_desc % dev_info.rx_desc_lim.nb_align != 0) {

                RTE_ETHDEV_LOG(ERR,
                        "Invalid value for nb_rx_desc(=%hu), should be: <= %hu, >= %hu, and a product of %hu\n",
                        nb_rx_desc, dev_info.rx_desc_lim.nb_max,
                        dev_info.rx_desc_lim.nb_min,
                        dev_info.rx_desc_lim.nb_align);
                return -EINVAL;
        }

        if (dev->data->dev_started &&
                !(dev_info.dev_capa &
                        RTE_ETH_DEV_CAPA_RUNTIME_RX_QUEUE_SETUP))
                return -EBUSY;

        if (dev->data->dev_started &&
                (dev->data->rx_queue_state[rx_queue_id] !=
                        RTE_ETH_QUEUE_STATE_STOPPED))
                return -EBUSY;

        rxq = dev->data->rx_queues;
        if (rxq[rx_queue_id]) {
                RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->rx_queue_release,
                                        -ENOTSUP);
                (*dev->dev_ops->rx_queue_release)(rxq[rx_queue_id]);
                rxq[rx_queue_id] = NULL;
        }

        if (rx_conf == NULL)
                rx_conf = &dev_info.default_rxconf;

        local_conf = *rx_conf;

        /*
         * If an offloading has already been enabled in
         * rte_eth_dev_configure(), it has been enabled on all queues,
         * so there is no need to enable it in this queue again.
         * The local_conf.offloads input to underlying PMD only carries
         * those offloadings which are only enabled on this queue and
         * not enabled on all queues.
         */
        local_conf.offloads &= ~dev->data->dev_conf.rxmode.offloads;

        /*
         * New added offloadings for this queue are those not enabled in
         * rte_eth_dev_configure() and they must be per-queue type.
         * A pure per-port offloading can't be enabled on a queue while
         * disabled on another queue. A pure per-port offloading can't
         * be enabled for any queue as new added one if it hasn't been
         * enabled in rte_eth_dev_configure().
         */
        if ((local_conf.offloads & dev_info.rx_queue_offload_capa) !=
             local_conf.offloads) {
                RTE_ETHDEV_LOG(ERR,
                        "Ethdev port_id=%d rx_queue_id=%d, new added offloads 0x%"PRIx64" must be "
                        "within per-queue offload capabilities 0x%"PRIx64" in %s()\n",
                        port_id, rx_queue_id, local_conf.offloads,
                        dev_info.rx_queue_offload_capa,
                        __func__);
                return -EINVAL;
        }

        /*
         * If LRO is enabled, check that the maximum aggregated packet
         * size is supported by the configured device.
         */
        if (local_conf.offloads & DEV_RX_OFFLOAD_TCP_LRO) {
                if (dev->data->dev_conf.rxmode.max_lro_pkt_size == 0)
                        dev->data->dev_conf.rxmode.max_lro_pkt_size =
                                dev->data->dev_conf.rxmode.max_rx_pkt_len;
                int ret = eth_dev_check_lro_pkt_size(port_id,
                                dev->data->dev_conf.rxmode.max_lro_pkt_size,
                                dev->data->dev_conf.rxmode.max_rx_pkt_len,
                                dev_info.max_lro_pkt_size);
                if (ret != 0)
                        return ret;
        }

        ret = (*dev->dev_ops->rx_queue_setup)(dev, rx_queue_id, nb_rx_desc,
                                              socket_id, &local_conf, mp);
        if (!ret) {
                if (!dev->data->min_rx_buf_size ||
                    dev->data->min_rx_buf_size > mbp_buf_size)
                        dev->data->min_rx_buf_size = mbp_buf_size;
        }

        rte_ethdev_trace_rxq_setup(port_id, rx_queue_id, nb_rx_desc, mp,
                rx_conf, ret);
        return eth_err(port_id, ret);
}

int
rte_eth_rx_hairpin_queue_setup(uint16_t port_id, uint16_t rx_queue_id,
                               uint16_t nb_rx_desc,
                               const struct rte_eth_hairpin_conf *conf)
{
        int ret;
        struct rte_eth_dev *dev;
        struct rte_eth_hairpin_cap cap;
        void **rxq;
        int i;
        int count;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        if (rx_queue_id >= dev->data->nb_rx_queues) {
                RTE_ETHDEV_LOG(ERR, "Invalid RX queue_id=%u\n", rx_queue_id);
                return -EINVAL;
        }

        if (conf == NULL) {
                RTE_ETHDEV_LOG(ERR,
                        "Cannot setup ethdev port %u Rx hairpin queue from NULL config\n",
                        port_id);
                return -EINVAL;
        }

        ret = rte_eth_dev_hairpin_capability_get(port_id, &cap);
        if (ret != 0)
                return ret;
        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->rx_hairpin_queue_setup,
                                -ENOTSUP);
        /* if nb_rx_desc is zero use max number of desc from the driver. */
        if (nb_rx_desc == 0)
                nb_rx_desc = cap.max_nb_desc;
        if (nb_rx_desc > cap.max_nb_desc) {
                RTE_ETHDEV_LOG(ERR,
                        "Invalid value for nb_rx_desc(=%hu), should be: <= %hu",
                        nb_rx_desc, cap.max_nb_desc);
                return -EINVAL;
        }
        if (conf->peer_count > cap.max_rx_2_tx) {
                RTE_ETHDEV_LOG(ERR,
                        "Invalid value for number of peers for Rx queue(=%u), should be: <= %hu",
                        conf->peer_count, cap.max_rx_2_tx);
                return -EINVAL;
        }
        if (conf->peer_count == 0) {
                RTE_ETHDEV_LOG(ERR,
                        "Invalid value for number of peers for Rx queue(=%u), should be: > 0",
                        conf->peer_count);
                return -EINVAL;
        }
        for (i = 0, count = 0; i < dev->data->nb_rx_queues &&
             cap.max_nb_queues != UINT16_MAX; i++) {
                if (i == rx_queue_id || rte_eth_dev_is_rx_hairpin_queue(dev, i))
                        count++;
        }
        if (count > cap.max_nb_queues) {
                RTE_ETHDEV_LOG(ERR, "To many Rx hairpin queues max is %d",
                cap.max_nb_queues);
                return -EINVAL;
        }
        if (dev->data->dev_started)
                return -EBUSY;
        rxq = dev->data->rx_queues;
        if (rxq[rx_queue_id] != NULL) {
                RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->rx_queue_release,
                                        -ENOTSUP);
                (*dev->dev_ops->rx_queue_release)(rxq[rx_queue_id]);
                rxq[rx_queue_id] = NULL;
        }
        ret = (*dev->dev_ops->rx_hairpin_queue_setup)(dev, rx_queue_id,
                                                      nb_rx_desc, conf);
        if (ret == 0)
                dev->data->rx_queue_state[rx_queue_id] =
                        RTE_ETH_QUEUE_STATE_HAIRPIN;
        return eth_err(port_id, ret);
}

int
rte_eth_tx_queue_setup(uint16_t port_id, uint16_t tx_queue_id,
                       uint16_t nb_tx_desc, unsigned int socket_id,
                       const struct rte_eth_txconf *tx_conf)
{
        struct rte_eth_dev *dev;
        struct rte_eth_dev_info dev_info;
        struct rte_eth_txconf local_conf;
        void **txq;
        int ret;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        if (tx_queue_id >= dev->data->nb_tx_queues) {
                RTE_ETHDEV_LOG(ERR, "Invalid TX queue_id=%u\n", tx_queue_id);
                return -EINVAL;
        }

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->tx_queue_setup, -ENOTSUP);

        ret = rte_eth_dev_info_get(port_id, &dev_info);
        if (ret != 0)
                return ret;

        /* Use default specified by driver, if nb_tx_desc is zero */
        if (nb_tx_desc == 0) {
                nb_tx_desc = dev_info.default_txportconf.ring_size;
                /* If driver default is zero, fall back on EAL default */
                if (nb_tx_desc == 0)
                        nb_tx_desc = RTE_ETH_DEV_FALLBACK_TX_RINGSIZE;
        }
        if (nb_tx_desc > dev_info.tx_desc_lim.nb_max ||
            nb_tx_desc < dev_info.tx_desc_lim.nb_min ||
            nb_tx_desc % dev_info.tx_desc_lim.nb_align != 0) {
                RTE_ETHDEV_LOG(ERR,
                        "Invalid value for nb_tx_desc(=%hu), should be: <= %hu, >= %hu, and a product of %hu\n",
                        nb_tx_desc, dev_info.tx_desc_lim.nb_max,
                        dev_info.tx_desc_lim.nb_min,
                        dev_info.tx_desc_lim.nb_align);
                return -EINVAL;
        }

        if (dev->data->dev_started &&
                !(dev_info.dev_capa &
                        RTE_ETH_DEV_CAPA_RUNTIME_TX_QUEUE_SETUP))
                return -EBUSY;

        if (dev->data->dev_started &&
                (dev->data->tx_queue_state[tx_queue_id] !=
                        RTE_ETH_QUEUE_STATE_STOPPED))
                return -EBUSY;

        txq = dev->data->tx_queues;
        if (txq[tx_queue_id]) {
                RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->tx_queue_release,
                                        -ENOTSUP);
                (*dev->dev_ops->tx_queue_release)(txq[tx_queue_id]);
                txq[tx_queue_id] = NULL;
        }

        if (tx_conf == NULL)
                tx_conf = &dev_info.default_txconf;

        local_conf = *tx_conf;

        /*
         * If an offloading has already been enabled in
         * rte_eth_dev_configure(), it has been enabled on all queues,
         * so there is no need to enable it in this queue again.
         * The local_conf.offloads input to underlying PMD only carries
         * those offloadings which are only enabled on this queue and
         * not enabled on all queues.
         */
        local_conf.offloads &= ~dev->data->dev_conf.txmode.offloads;

        /*
         * New added offloadings for this queue are those not enabled in
         * rte_eth_dev_configure() and they must be per-queue type.
         * A pure per-port offloading can't be enabled on a queue while
         * disabled on another queue. A pure per-port offloading can't
         * be enabled for any queue as new added one if it hasn't been
         * enabled in rte_eth_dev_configure().
         */
        if ((local_conf.offloads & dev_info.tx_queue_offload_capa) !=
             local_conf.offloads) {
                RTE_ETHDEV_LOG(ERR,
                        "Ethdev port_id=%d tx_queue_id=%d, new added offloads 0x%"PRIx64" must be "
                        "within per-queue offload capabilities 0x%"PRIx64" in %s()\n",
                        port_id, tx_queue_id, local_conf.offloads,
                        dev_info.tx_queue_offload_capa,
                        __func__);
                return -EINVAL;
        }

        rte_ethdev_trace_txq_setup(port_id, tx_queue_id, nb_tx_desc, tx_conf);
        return eth_err(port_id, (*dev->dev_ops->tx_queue_setup)(dev,
                       tx_queue_id, nb_tx_desc, socket_id, &local_conf));
}

int
rte_eth_tx_hairpin_queue_setup(uint16_t port_id, uint16_t tx_queue_id,
                               uint16_t nb_tx_desc,
                               const struct rte_eth_hairpin_conf *conf)
{
        struct rte_eth_dev *dev;
        struct rte_eth_hairpin_cap cap;
        void **txq;
        int i;
        int count;
        int ret;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        if (tx_queue_id >= dev->data->nb_tx_queues) {
                RTE_ETHDEV_LOG(ERR, "Invalid TX queue_id=%u\n", tx_queue_id);
                return -EINVAL;
        }

        if (conf == NULL) {
                RTE_ETHDEV_LOG(ERR,
                        "Cannot setup ethdev port %u Tx hairpin queue from NULL config\n",
                        port_id);
                return -EINVAL;
        }

        ret = rte_eth_dev_hairpin_capability_get(port_id, &cap);
        if (ret != 0)
                return ret;
        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->tx_hairpin_queue_setup,
                                -ENOTSUP);
        /* if nb_rx_desc is zero use max number of desc from the driver. */
        if (nb_tx_desc == 0)
                nb_tx_desc = cap.max_nb_desc;
        if (nb_tx_desc > cap.max_nb_desc) {
                RTE_ETHDEV_LOG(ERR,
                        "Invalid value for nb_tx_desc(=%hu), should be: <= %hu",
                        nb_tx_desc, cap.max_nb_desc);
                return -EINVAL;
        }
        if (conf->peer_count > cap.max_tx_2_rx) {
                RTE_ETHDEV_LOG(ERR,
                        "Invalid value for number of peers for Tx queue(=%u), should be: <= %hu",
                        conf->peer_count, cap.max_tx_2_rx);
                return -EINVAL;
        }
        if (conf->peer_count == 0) {
                RTE_ETHDEV_LOG(ERR,
                        "Invalid value for number of peers for Tx queue(=%u), should be: > 0",
                        conf->peer_count);
                return -EINVAL;
        }
        for (i = 0, count = 0; i < dev->data->nb_tx_queues &&
             cap.max_nb_queues != UINT16_MAX; i++) {
                if (i == tx_queue_id || rte_eth_dev_is_tx_hairpin_queue(dev, i))
                        count++;
        }
        if (count > cap.max_nb_queues) {
                RTE_ETHDEV_LOG(ERR, "To many Tx hairpin queues max is %d",
                cap.max_nb_queues);
                return -EINVAL;
        }
        if (dev->data->dev_started)
                return -EBUSY;
        txq = dev->data->tx_queues;
        if (txq[tx_queue_id] != NULL) {
                RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->tx_queue_release,
                                        -ENOTSUP);
                (*dev->dev_ops->tx_queue_release)(txq[tx_queue_id]);
                txq[tx_queue_id] = NULL;
        }
        ret = (*dev->dev_ops->tx_hairpin_queue_setup)
                (dev, tx_queue_id, nb_tx_desc, conf);
        if (ret == 0)
                dev->data->tx_queue_state[tx_queue_id] =
                        RTE_ETH_QUEUE_STATE_HAIRPIN;
        return eth_err(port_id, ret);
}

int
rte_eth_hairpin_bind(uint16_t tx_port, uint16_t rx_port)
{
        struct rte_eth_dev *dev;
        int ret;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(tx_port, -ENODEV);
        dev = &rte_eth_devices[tx_port];

        if (dev->data->dev_started == 0) {
                RTE_ETHDEV_LOG(ERR, "Tx port %d is not started\n", tx_port);
                return -EBUSY;
        }

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->hairpin_bind, -ENOTSUP);
        ret = (*dev->dev_ops->hairpin_bind)(dev, rx_port);
        if (ret != 0)
                RTE_ETHDEV_LOG(ERR, "Failed to bind hairpin Tx %d"
                               " to Rx %d (%d - all ports)\n",
                               tx_port, rx_port, RTE_MAX_ETHPORTS);

        return ret;
}

int
rte_eth_hairpin_unbind(uint16_t tx_port, uint16_t rx_port)
{
        struct rte_eth_dev *dev;
        int ret;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(tx_port, -ENODEV);
        dev = &rte_eth_devices[tx_port];

        if (dev->data->dev_started == 0) {
                RTE_ETHDEV_LOG(ERR, "Tx port %d is already stopped\n", tx_port);
                return -EBUSY;
        }

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->hairpin_unbind, -ENOTSUP);
        ret = (*dev->dev_ops->hairpin_unbind)(dev, rx_port);
        if (ret != 0)
                RTE_ETHDEV_LOG(ERR, "Failed to unbind hairpin Tx %d"
                               " from Rx %d (%d - all ports)\n",
                               tx_port, rx_port, RTE_MAX_ETHPORTS);

        return ret;
}

int
rte_eth_hairpin_get_peer_ports(uint16_t port_id, uint16_t *peer_ports,
                               size_t len, uint32_t direction)
{
        struct rte_eth_dev *dev;
        int ret;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        if (peer_ports == NULL) {
                RTE_ETHDEV_LOG(ERR,
                        "Cannot get ethdev port %u hairpin peer ports to NULL\n",
                        port_id);
                return -EINVAL;
        }

        if (len == 0) {
                RTE_ETHDEV_LOG(ERR,
                        "Cannot get ethdev port %u hairpin peer ports to array with zero size\n",
                        port_id);
                return -EINVAL;
        }

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->hairpin_get_peer_ports,
                                -ENOTSUP);

        ret = (*dev->dev_ops->hairpin_get_peer_ports)(dev, peer_ports,
                                                      len, direction);
        if (ret < 0)
                RTE_ETHDEV_LOG(ERR, "Failed to get %d hairpin peer %s ports\n",
                               port_id, direction ? "Rx" : "Tx");

        return ret;
}

void
rte_eth_tx_buffer_drop_callback(struct rte_mbuf **pkts, uint16_t unsent,
                void *userdata __rte_unused)
{
        rte_pktmbuf_free_bulk(pkts, unsent);
}

void
rte_eth_tx_buffer_count_callback(struct rte_mbuf **pkts, uint16_t unsent,
                void *userdata)
{
        uint64_t *count = userdata;

        rte_pktmbuf_free_bulk(pkts, unsent);
        *count += unsent;
}

int
rte_eth_tx_buffer_set_err_callback(struct rte_eth_dev_tx_buffer *buffer,
                buffer_tx_error_fn cbfn, void *userdata)
{
        if (buffer == NULL) {
                RTE_ETHDEV_LOG(ERR,
                        "Cannot set Tx buffer error callback to NULL buffer\n");
                return -EINVAL;
        }

        buffer->error_callback = cbfn;
        buffer->error_userdata = userdata;
        return 0;
}

int
rte_eth_tx_buffer_init(struct rte_eth_dev_tx_buffer *buffer, uint16_t size)
{
        int ret = 0;

        if (buffer == NULL) {
                RTE_ETHDEV_LOG(ERR, "Cannot initialize NULL buffer\n");
                return -EINVAL;
        }

        buffer->size = size;
        if (buffer->error_callback == NULL) {
                ret = rte_eth_tx_buffer_set_err_callback(
                        buffer, rte_eth_tx_buffer_drop_callback, NULL);
        }

        return ret;
}

int
rte_eth_tx_done_cleanup(uint16_t port_id, uint16_t queue_id, uint32_t free_cnt)
{
        struct rte_eth_dev *dev;
        int ret;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->tx_done_cleanup, -ENOTSUP);

        /* Call driver to free pending mbufs. */
        ret = (*dev->dev_ops->tx_done_cleanup)(dev->data->tx_queues[queue_id],
                                               free_cnt);
        return eth_err(port_id, ret);
}

int
rte_eth_promiscuous_enable(uint16_t port_id)
{
        struct rte_eth_dev *dev;
        int diag = 0;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        if (dev->data->promiscuous == 1)
                return 0;

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->promiscuous_enable, -ENOTSUP);

        diag = (*dev->dev_ops->promiscuous_enable)(dev);
        dev->data->promiscuous = (diag == 0) ? 1 : 0;

        return eth_err(port_id, diag);
}

int
rte_eth_promiscuous_disable(uint16_t port_id)
{
        struct rte_eth_dev *dev;
        int diag = 0;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        if (dev->data->promiscuous == 0)
                return 0;

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->promiscuous_disable, -ENOTSUP);

        dev->data->promiscuous = 0;
        diag = (*dev->dev_ops->promiscuous_disable)(dev);
        if (diag != 0)
                dev->data->promiscuous = 1;

        return eth_err(port_id, diag);
}

int
rte_eth_promiscuous_get(uint16_t port_id)
{
        struct rte_eth_dev *dev;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        return dev->data->promiscuous;
}

int
rte_eth_allmulticast_enable(uint16_t port_id)
{
        struct rte_eth_dev *dev;
        int diag;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        if (dev->data->all_multicast == 1)
                return 0;

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->allmulticast_enable, -ENOTSUP);
        diag = (*dev->dev_ops->allmulticast_enable)(dev);
        dev->data->all_multicast = (diag == 0) ? 1 : 0;

        return eth_err(port_id, diag);
}

int
rte_eth_allmulticast_disable(uint16_t port_id)
{
        struct rte_eth_dev *dev;
        int diag;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        if (dev->data->all_multicast == 0)
                return 0;

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->allmulticast_disable, -ENOTSUP);
        dev->data->all_multicast = 0;
        diag = (*dev->dev_ops->allmulticast_disable)(dev);
        if (diag != 0)
                dev->data->all_multicast = 1;

        return eth_err(port_id, diag);
}

int
rte_eth_allmulticast_get(uint16_t port_id)
{
        struct rte_eth_dev *dev;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        return dev->data->all_multicast;
}

int
rte_eth_link_get(uint16_t port_id, struct rte_eth_link *eth_link)
{
        struct rte_eth_dev *dev;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        if (eth_link == NULL) {
                RTE_ETHDEV_LOG(ERR, "Cannot get ethdev port %u link to NULL\n",
                        port_id);
                return -EINVAL;
        }

        if (dev->data->dev_conf.intr_conf.lsc && dev->data->dev_started)
                rte_eth_linkstatus_get(dev, eth_link);
        else {
                RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->link_update, -ENOTSUP);
                (*dev->dev_ops->link_update)(dev, 1);
                *eth_link = dev->data->dev_link;
        }

        return 0;
}

int
rte_eth_link_get_nowait(uint16_t port_id, struct rte_eth_link *eth_link)
{
        struct rte_eth_dev *dev;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        if (eth_link == NULL) {
                RTE_ETHDEV_LOG(ERR, "Cannot get ethdev port %u link to NULL\n",
                        port_id);
                return -EINVAL;
        }

        if (dev->data->dev_conf.intr_conf.lsc && dev->data->dev_started)
                rte_eth_linkstatus_get(dev, eth_link);
        else {
                RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->link_update, -ENOTSUP);
                (*dev->dev_ops->link_update)(dev, 0);
                *eth_link = dev->data->dev_link;
        }

        return 0;
}

const char *
rte_eth_link_speed_to_str(uint32_t link_speed)
{
        switch (link_speed) {
        case ETH_SPEED_NUM_NONE: return "None";
        case ETH_SPEED_NUM_10M:  return "10 Mbps";
        case ETH_SPEED_NUM_100M: return "100 Mbps";
        case ETH_SPEED_NUM_1G:   return "1 Gbps";
        case ETH_SPEED_NUM_2_5G: return "2.5 Gbps";
        case ETH_SPEED_NUM_5G:   return "5 Gbps";
        case ETH_SPEED_NUM_10G:  return "10 Gbps";
        case ETH_SPEED_NUM_20G:  return "20 Gbps";
        case ETH_SPEED_NUM_25G:  return "25 Gbps";
        case ETH_SPEED_NUM_40G:  return "40 Gbps";
        case ETH_SPEED_NUM_50G:  return "50 Gbps";
        case ETH_SPEED_NUM_56G:  return "56 Gbps";
        case ETH_SPEED_NUM_100G: return "100 Gbps";
        case ETH_SPEED_NUM_200G: return "200 Gbps";
        case ETH_SPEED_NUM_UNKNOWN: return "Unknown";
        default: return "Invalid";
        }
}

int
rte_eth_link_to_str(char *str, size_t len, const struct rte_eth_link *eth_link)
{
        if (str == NULL) {
                RTE_ETHDEV_LOG(ERR, "Cannot convert link to NULL string\n");
                return -EINVAL;
        }

        if (len == 0) {
                RTE_ETHDEV_LOG(ERR,
                        "Cannot convert link to string with zero size\n");
                return -EINVAL;
        }

        if (eth_link == NULL) {
                RTE_ETHDEV_LOG(ERR, "Cannot convert to string from NULL link\n");
                return -EINVAL;
        }

        if (eth_link->link_status == ETH_LINK_DOWN)
                return snprintf(str, len, "Link down");
        else
                return snprintf(str, len, "Link up at %s %s %s",
                        rte_eth_link_speed_to_str(eth_link->link_speed),
                        (eth_link->link_duplex == ETH_LINK_FULL_DUPLEX) ?
                        "FDX" : "HDX",
                        (eth_link->link_autoneg == ETH_LINK_AUTONEG) ?
                        "Autoneg" : "Fixed");
}

int
rte_eth_stats_get(uint16_t port_id, struct rte_eth_stats *stats)
{
        struct rte_eth_dev *dev;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        if (stats == NULL) {
                RTE_ETHDEV_LOG(ERR, "Cannot get ethdev port %u stats to NULL\n",
                        port_id);
                return -EINVAL;
        }

        memset(stats, 0, sizeof(*stats));

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->stats_get, -ENOTSUP);
        stats->rx_nombuf = dev->data->rx_mbuf_alloc_failed;
        return eth_err(port_id, (*dev->dev_ops->stats_get)(dev, stats));
}

int
rte_eth_stats_reset(uint16_t port_id)
{
        struct rte_eth_dev *dev;
        int ret;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->stats_reset, -ENOTSUP);
        ret = (*dev->dev_ops->stats_reset)(dev);
        if (ret != 0)
                return eth_err(port_id, ret);

        dev->data->rx_mbuf_alloc_failed = 0;

        return 0;
}

static inline int
eth_dev_get_xstats_basic_count(struct rte_eth_dev *dev)
{
        uint16_t nb_rxqs, nb_txqs;
        int count;

        nb_rxqs = RTE_MIN(dev->data->nb_rx_queues, RTE_ETHDEV_QUEUE_STAT_CNTRS);
        nb_txqs = RTE_MIN(dev->data->nb_tx_queues, RTE_ETHDEV_QUEUE_STAT_CNTRS);

        count = RTE_NB_STATS;
        if (dev->data->dev_flags & RTE_ETH_DEV_AUTOFILL_QUEUE_XSTATS) {
                count += nb_rxqs * RTE_NB_RXQ_STATS;
                count += nb_txqs * RTE_NB_TXQ_STATS;
        }

        return count;
}

static int
eth_dev_get_xstats_count(uint16_t port_id)
{
        struct rte_eth_dev *dev;
        int count;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];
        if (dev->dev_ops->xstats_get_names_by_id != NULL) {
                count = (*dev->dev_ops->xstats_get_names_by_id)(dev, NULL,
                                NULL, 0);
                if (count < 0)
                        return eth_err(port_id, count);
        }
        if (dev->dev_ops->xstats_get_names != NULL) {
                count = (*dev->dev_ops->xstats_get_names)(dev, NULL, 0);
                if (count < 0)
                        return eth_err(port_id, count);
        } else
                count = 0;


        count += eth_dev_get_xstats_basic_count(dev);

        return count;
}

int
rte_eth_xstats_get_id_by_name(uint16_t port_id, const char *xstat_name,
                uint64_t *id)
{
        int cnt_xstats, idx_xstat;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);

        if (xstat_name == NULL) {
                RTE_ETHDEV_LOG(ERR,
                        "Cannot get ethdev port %u xstats ID from NULL xstat name\n",
                        port_id);
                return -ENOMEM;
        }

        if (id == NULL) {
                RTE_ETHDEV_LOG(ERR,
                        "Cannot get ethdev port %u xstats ID to NULL\n",
                        port_id);
                return -ENOMEM;
        }

        /* Get count */
        cnt_xstats = rte_eth_xstats_get_names_by_id(port_id, NULL, 0, NULL);
        if (cnt_xstats  < 0) {
                RTE_ETHDEV_LOG(ERR, "Cannot get count of xstats\n");
                return -ENODEV;
        }

        /* Get id-name lookup table */
        struct rte_eth_xstat_name xstats_names[cnt_xstats];

        if (cnt_xstats != rte_eth_xstats_get_names_by_id(
                        port_id, xstats_names, cnt_xstats, NULL)) {
                RTE_ETHDEV_LOG(ERR, "Cannot get xstats lookup\n");
                return -1;
        }

        for (idx_xstat = 0; idx_xstat < cnt_xstats; idx_xstat++) {
                if (!strcmp(xstats_names[idx_xstat].name, xstat_name)) {
                        *id = idx_xstat;
                        return 0;
                };
        }

        return -EINVAL;
}

/* retrieve basic stats names */
static int
eth_basic_stats_get_names(struct rte_eth_dev *dev,
        struct rte_eth_xstat_name *xstats_names)
{
        int cnt_used_entries = 0;
        uint32_t idx, id_queue;
        uint16_t num_q;

        for (idx = 0; idx < RTE_NB_STATS; idx++) {
                strlcpy(xstats_names[cnt_used_entries].name,
                        eth_dev_stats_strings[idx].name,
                        sizeof(xstats_names[0].name));
                cnt_used_entries++;
        }

        if ((dev->data->dev_flags & RTE_ETH_DEV_AUTOFILL_QUEUE_XSTATS) == 0)
                return cnt_used_entries;

        num_q = RTE_MIN(dev->data->nb_rx_queues, RTE_ETHDEV_QUEUE_STAT_CNTRS);
        for (id_queue = 0; id_queue < num_q; id_queue++) {
                for (idx = 0; idx < RTE_NB_RXQ_STATS; idx++) {
                        snprintf(xstats_names[cnt_used_entries].name,
                                sizeof(xstats_names[0].name),
                                "rx_q%u_%s",
                                id_queue, eth_dev_rxq_stats_strings[idx].name);
                        cnt_used_entries++;
                }

        }
        num_q = RTE_MIN(dev->data->nb_tx_queues, RTE_ETHDEV_QUEUE_STAT_CNTRS);
        for (id_queue = 0; id_queue < num_q; id_queue++) {
                for (idx = 0; idx < RTE_NB_TXQ_STATS; idx++) {
                        snprintf(xstats_names[cnt_used_entries].name,
                                sizeof(xstats_names[0].name),
                                "tx_q%u_%s",
                                id_queue, eth_dev_txq_stats_strings[idx].name);
                        cnt_used_entries++;
                }
        }
        return cnt_used_entries;
}

/* retrieve ethdev extended statistics names */
int
rte_eth_xstats_get_names_by_id(uint16_t port_id,
        struct rte_eth_xstat_name *xstats_names, unsigned int size,
        uint64_t *ids)
{
        struct rte_eth_xstat_name *xstats_names_copy;
        unsigned int no_basic_stat_requested = 1;
        unsigned int no_ext_stat_requested = 1;
        unsigned int expected_entries;
        unsigned int basic_count;
        struct rte_eth_dev *dev;
        unsigned int i;
        int ret;

        RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
        dev = &rte_eth_devices[port_id];

        basic_count = eth_dev_get_xstats_basic_count(dev);
        ret = eth_dev_get_xstats_count(port_id);
        if (ret < 0)