#endif
#include <rte_malloc.h>
-#include <rte_ethdev.h>
+#include <rte_ethdev_driver.h>
#include <rte_ethdev_pci.h>
#include <rte_pci.h>
+#include <rte_bus_pci.h>
#include <rte_common.h>
#include <rte_kvargs.h>
/* Device parameter to limit the size of inlining packet. */
#define MLX5_TXQ_MAX_INLINE_LEN "txq_max_inline_len"
-/* Device parameter to enable hardware TSO offload. */
-#define MLX5_TSO "tso"
-
/* Device parameter to enable hardware Tx vector. */
#define MLX5_TX_VEC_EN "tx_vec_en"
/* Device parameter to enable hardware Rx vector. */
#define MLX5_RX_VEC_EN "rx_vec_en"
-/* Default PMD specific parameter value. */
-#define MLX5_ARG_UNSET (-1)
-
-struct mlx5_args {
- int cqe_comp;
- int txq_inline;
- int txqs_inline;
- int mps;
- int mpw_hdr_dseg;
- int inline_max_packet_sz;
- int tso;
- int tx_vec_en;
- int rx_vec_en;
-};
+#ifndef HAVE_IBV_MLX5_MOD_MPW
+#define MLX5DV_CONTEXT_FLAGS_MPW_ALLOWED (1 << 2)
+#define MLX5DV_CONTEXT_FLAGS_ENHANCED_MPW (1 << 3)
+#endif
+
+#ifndef HAVE_IBV_MLX5_MOD_CQE_128B_COMP
+#define MLX5DV_CONTEXT_FLAGS_CQE_128B_COMP (1 << 4)
+#endif
+
/**
* Retrieve integer value from environment variable.
*
return atoi(val);
}
+/**
+ * Verbs callback to allocate a memory. This function should allocate the space
+ * according to the size provided residing inside a huge page.
+ * Please note that all allocation must respect the alignment from libmlx5
+ * (i.e. currently sysconf(_SC_PAGESIZE)).
+ *
+ * @param[in] size
+ * The size in bytes of the memory to allocate.
+ * @param[in] data
+ * A pointer to the callback data.
+ *
+ * @return
+ * a pointer to the allocate space.
+ */
+static void *
+mlx5_alloc_verbs_buf(size_t size, void *data)
+{
+ struct priv *priv = data;
+ void *ret;
+ size_t alignment = sysconf(_SC_PAGESIZE);
+ unsigned int socket = SOCKET_ID_ANY;
+
+ if (priv->verbs_alloc_ctx.type == MLX5_VERBS_ALLOC_TYPE_TX_QUEUE) {
+ const struct mlx5_txq_ctrl *ctrl = priv->verbs_alloc_ctx.obj;
+
+ socket = ctrl->socket;
+ } else if (priv->verbs_alloc_ctx.type ==
+ MLX5_VERBS_ALLOC_TYPE_RX_QUEUE) {
+ const struct mlx5_rxq_ctrl *ctrl = priv->verbs_alloc_ctx.obj;
+
+ socket = ctrl->socket;
+ }
+ assert(data != NULL);
+ ret = rte_malloc_socket(__func__, size, alignment, socket);
+ DEBUG("Extern alloc size: %lu, align: %lu: %p", size, alignment, ret);
+ return ret;
+}
+
+/**
+ * Verbs callback to free a memory.
+ *
+ * @param[in] ptr
+ * A pointer to the memory to free.
+ * @param[in] data
+ * A pointer to the callback data.
+ */
+static void
+mlx5_free_verbs_buf(void *ptr, void *data __rte_unused)
+{
+ assert(data != NULL);
+ DEBUG("Extern free request: %p", ptr);
+ rte_free(ptr);
+}
+
/**
* DPDK callback to close the device.
*
static void
mlx5_dev_close(struct rte_eth_dev *dev)
{
- struct priv *priv = mlx5_get_priv(dev);
+ struct priv *priv = dev->data->dev_private;
unsigned int i;
+ int ret;
priv_lock(priv);
DEBUG("%p: closing device \"%s\"",
((priv->ctx != NULL) ? priv->ctx->device->name : ""));
/* In case mlx5_dev_stop() has not been called. */
priv_dev_interrupt_handler_uninstall(priv, dev);
- priv_special_flow_disable_all(priv);
- priv_mac_addrs_disable(priv);
- priv_destroy_hash_rxqs(priv);
-
- /* Remove flow director elements. */
- priv_fdir_disable(priv);
- priv_fdir_delete_filters_list(priv);
-
+ priv_dev_traffic_disable(priv, dev);
/* Prevent crashes when queues are still in use. */
dev->rx_pkt_burst = removed_rx_burst;
dev->tx_pkt_burst = removed_tx_burst;
if (priv->rxqs != NULL) {
/* XXX race condition if mlx5_rx_burst() is still running. */
usleep(1000);
- for (i = 0; (i != priv->rxqs_n); ++i) {
- struct rxq *rxq = (*priv->rxqs)[i];
- struct rxq_ctrl *rxq_ctrl;
-
- if (rxq == NULL)
- continue;
- rxq_ctrl = container_of(rxq, struct rxq_ctrl, rxq);
- (*priv->rxqs)[i] = NULL;
- rxq_cleanup(rxq_ctrl);
- rte_free(rxq_ctrl);
- }
+ for (i = 0; (i != priv->rxqs_n); ++i)
+ mlx5_priv_rxq_release(priv, i);
priv->rxqs_n = 0;
priv->rxqs = NULL;
}
if (priv->txqs != NULL) {
/* XXX race condition if mlx5_tx_burst() is still running. */
usleep(1000);
- for (i = 0; (i != priv->txqs_n); ++i) {
- struct txq *txq = (*priv->txqs)[i];
- struct txq_ctrl *txq_ctrl;
-
- if (txq == NULL)
- continue;
- txq_ctrl = container_of(txq, struct txq_ctrl, txq);
- (*priv->txqs)[i] = NULL;
- txq_cleanup(txq_ctrl);
- rte_free(txq_ctrl);
- }
+ for (i = 0; (i != priv->txqs_n); ++i)
+ mlx5_priv_txq_release(priv, i);
priv->txqs_n = 0;
priv->txqs = NULL;
}
claim_zero(ibv_close_device(priv->ctx));
} else
assert(priv->ctx == NULL);
- if (priv->rss_conf != NULL) {
- for (i = 0; (i != hash_rxq_init_n); ++i)
- rte_free((*priv->rss_conf)[i]);
- rte_free(priv->rss_conf);
- }
+ if (priv->rss_conf.rss_key != NULL)
+ rte_free(priv->rss_conf.rss_key);
if (priv->reta_idx != NULL)
rte_free(priv->reta_idx);
+ priv_socket_uninit(priv);
+ ret = mlx5_priv_hrxq_ibv_verify(priv);
+ if (ret)
+ WARN("%p: some Hash Rx queue still remain", (void *)priv);
+ ret = mlx5_priv_ind_table_ibv_verify(priv);
+ if (ret)
+ WARN("%p: some Indirection table still remain", (void *)priv);
+ ret = mlx5_priv_rxq_ibv_verify(priv);
+ if (ret)
+ WARN("%p: some Verbs Rx queue still remain", (void *)priv);
+ ret = mlx5_priv_rxq_verify(priv);
+ if (ret)
+ WARN("%p: some Rx Queues still remain", (void *)priv);
+ ret = mlx5_priv_txq_ibv_verify(priv);
+ if (ret)
+ WARN("%p: some Verbs Tx queue still remain", (void *)priv);
+ ret = mlx5_priv_txq_verify(priv);
+ if (ret)
+ WARN("%p: some Tx Queues still remain", (void *)priv);
+ ret = priv_flow_verify(priv);
+ if (ret)
+ WARN("%p: some flows still remain", (void *)priv);
+ ret = priv_mr_verify(priv);
+ if (ret)
+ WARN("%p: some Memory Region still remain", (void *)priv);
priv_unlock(priv);
memset(priv, 0, sizeof(*priv));
}
-static const struct eth_dev_ops mlx5_dev_ops = {
+const struct eth_dev_ops mlx5_dev_ops = {
.dev_configure = mlx5_dev_configure,
.dev_start = mlx5_dev_start,
.dev_stop = mlx5_dev_stop,
.filter_ctrl = mlx5_dev_filter_ctrl,
.rx_descriptor_status = mlx5_rx_descriptor_status,
.tx_descriptor_status = mlx5_tx_descriptor_status,
-#ifdef HAVE_UPDATE_CQ_CI
.rx_queue_intr_enable = mlx5_rx_intr_enable,
.rx_queue_intr_disable = mlx5_rx_intr_disable,
-#endif
+ .is_removed = mlx5_is_removed,
+};
+
+static const struct eth_dev_ops mlx5_dev_sec_ops = {
+ .stats_get = mlx5_stats_get,
+ .stats_reset = mlx5_stats_reset,
+ .xstats_get = mlx5_xstats_get,
+ .xstats_reset = mlx5_xstats_reset,
+ .xstats_get_names = mlx5_xstats_get_names,
+ .dev_infos_get = mlx5_dev_infos_get,
+ .rx_descriptor_status = mlx5_rx_descriptor_status,
+ .tx_descriptor_status = mlx5_tx_descriptor_status,
+};
+
+/* Available operators in flow isolated mode. */
+const struct eth_dev_ops mlx5_dev_ops_isolate = {
+ .dev_configure = mlx5_dev_configure,
+ .dev_start = mlx5_dev_start,
+ .dev_stop = mlx5_dev_stop,
+ .dev_set_link_down = mlx5_set_link_down,
+ .dev_set_link_up = mlx5_set_link_up,
+ .dev_close = mlx5_dev_close,
+ .link_update = mlx5_link_update,
+ .stats_get = mlx5_stats_get,
+ .stats_reset = mlx5_stats_reset,
+ .xstats_get = mlx5_xstats_get,
+ .xstats_reset = mlx5_xstats_reset,
+ .xstats_get_names = mlx5_xstats_get_names,
+ .dev_infos_get = mlx5_dev_infos_get,
+ .dev_supported_ptypes_get = mlx5_dev_supported_ptypes_get,
+ .vlan_filter_set = mlx5_vlan_filter_set,
+ .rx_queue_setup = mlx5_rx_queue_setup,
+ .tx_queue_setup = mlx5_tx_queue_setup,
+ .rx_queue_release = mlx5_rx_queue_release,
+ .tx_queue_release = mlx5_tx_queue_release,
+ .flow_ctrl_get = mlx5_dev_get_flow_ctrl,
+ .flow_ctrl_set = mlx5_dev_set_flow_ctrl,
+ .mac_addr_remove = mlx5_mac_addr_remove,
+ .mac_addr_add = mlx5_mac_addr_add,
+ .mac_addr_set = mlx5_mac_addr_set,
+ .mtu_set = mlx5_dev_set_mtu,
+ .vlan_strip_queue_set = mlx5_vlan_strip_queue_set,
+ .vlan_offload_set = mlx5_vlan_offload_set,
+ .filter_ctrl = mlx5_dev_filter_ctrl,
+ .rx_descriptor_status = mlx5_rx_descriptor_status,
+ .tx_descriptor_status = mlx5_tx_descriptor_status,
+ .rx_queue_intr_enable = mlx5_rx_intr_enable,
+ .rx_queue_intr_disable = mlx5_rx_intr_disable,
+ .is_removed = mlx5_is_removed,
};
static struct {
static int
mlx5_args_check(const char *key, const char *val, void *opaque)
{
- struct mlx5_args *args = opaque;
+ struct mlx5_dev_config *config = opaque;
unsigned long tmp;
errno = 0;
return errno;
}
if (strcmp(MLX5_RXQ_CQE_COMP_EN, key) == 0) {
- args->cqe_comp = !!tmp;
+ config->cqe_comp = !!tmp;
} else if (strcmp(MLX5_TXQ_INLINE, key) == 0) {
- args->txq_inline = tmp;
+ config->txq_inline = tmp;
} else if (strcmp(MLX5_TXQS_MIN_INLINE, key) == 0) {
- args->txqs_inline = tmp;
+ config->txqs_inline = tmp;
} else if (strcmp(MLX5_TXQ_MPW_EN, key) == 0) {
- args->mps = !!tmp;
+ config->mps = !!tmp ? config->mps : 0;
} else if (strcmp(MLX5_TXQ_MPW_HDR_DSEG_EN, key) == 0) {
- args->mpw_hdr_dseg = !!tmp;
+ config->mpw_hdr_dseg = !!tmp;
} else if (strcmp(MLX5_TXQ_MAX_INLINE_LEN, key) == 0) {
- args->inline_max_packet_sz = tmp;
- } else if (strcmp(MLX5_TSO, key) == 0) {
- args->tso = !!tmp;
+ config->inline_max_packet_sz = tmp;
} else if (strcmp(MLX5_TX_VEC_EN, key) == 0) {
- args->tx_vec_en = !!tmp;
+ config->tx_vec_en = !!tmp;
} else if (strcmp(MLX5_RX_VEC_EN, key) == 0) {
- args->rx_vec_en = !!tmp;
+ config->rx_vec_en = !!tmp;
} else {
WARN("%s: unknown parameter", key);
return -EINVAL;
/**
* Parse device parameters.
*
- * @param priv
- * Pointer to private structure.
+ * @param config
+ * Pointer to device configuration structure.
* @param devargs
* Device arguments structure.
*
* 0 on success, errno value on failure.
*/
static int
-mlx5_args(struct mlx5_args *args, struct rte_devargs *devargs)
+mlx5_args(struct mlx5_dev_config *config, struct rte_devargs *devargs)
{
const char **params = (const char *[]){
MLX5_RXQ_CQE_COMP_EN,
MLX5_TXQ_MPW_EN,
MLX5_TXQ_MPW_HDR_DSEG_EN,
MLX5_TXQ_MAX_INLINE_LEN,
- MLX5_TSO,
MLX5_TX_VEC_EN,
MLX5_RX_VEC_EN,
NULL,
for (i = 0; (params[i] != NULL); ++i) {
if (rte_kvargs_count(kvlist, params[i])) {
ret = rte_kvargs_process(kvlist, params[i],
- mlx5_args_check, args);
+ mlx5_args_check, config);
if (ret != 0) {
rte_kvargs_free(kvlist);
return ret;
static struct rte_pci_driver mlx5_driver;
-/**
- * Assign parameters from args into priv, only non default
- * values are considered.
- *
- * @param[out] priv
- * Pointer to private structure.
- * @param[in] args
- * Pointer to args values.
- */
-static void
-mlx5_args_assign(struct priv *priv, struct mlx5_args *args)
-{
- if (args->cqe_comp != MLX5_ARG_UNSET)
- priv->cqe_comp = args->cqe_comp;
- if (args->txq_inline != MLX5_ARG_UNSET)
- priv->txq_inline = args->txq_inline;
- if (args->txqs_inline != MLX5_ARG_UNSET)
- priv->txqs_inline = args->txqs_inline;
- if (args->mps != MLX5_ARG_UNSET)
- priv->mps = args->mps ? priv->mps : 0;
- if (args->mpw_hdr_dseg != MLX5_ARG_UNSET)
- priv->mpw_hdr_dseg = args->mpw_hdr_dseg;
- if (args->inline_max_packet_sz != MLX5_ARG_UNSET)
- priv->inline_max_packet_sz = args->inline_max_packet_sz;
- if (args->tso != MLX5_ARG_UNSET)
- priv->tso = args->tso;
- if (args->tx_vec_en != MLX5_ARG_UNSET)
- priv->tx_vec_en = args->tx_vec_en;
- if (args->rx_vec_en != MLX5_ARG_UNSET)
- priv->rx_vec_en = args->rx_vec_en;
-}
-
/**
* DPDK callback to register a PCI device.
*
struct ibv_device *ibv_dev;
int err = 0;
struct ibv_context *attr_ctx = NULL;
- struct ibv_device_attr device_attr;
+ struct ibv_device_attr_ex device_attr;
unsigned int sriov;
unsigned int mps;
- unsigned int tunnel_en;
+ unsigned int cqe_comp;
+ unsigned int tunnel_en = 0;
int idx;
int i;
+ struct mlx5dv_context attrs_out;
+#ifdef HAVE_IBV_DEVICE_COUNTERS_SET_SUPPORT
+ struct ibv_counter_set_description cs_desc;
+#endif
(void)pci_drv;
assert(pci_drv == &mlx5_driver);
PCI_DEVICE_ID_MELLANOX_CONNECTX5VF) ||
(pci_dev->id.device_id ==
PCI_DEVICE_ID_MELLANOX_CONNECTX5EXVF));
- /*
- * Multi-packet send is supported by ConnectX-4 Lx PF as well
- * as all ConnectX-5 devices.
- */
switch (pci_dev->id.device_id) {
case PCI_DEVICE_ID_MELLANOX_CONNECTX4:
tunnel_en = 1;
- mps = MLX5_MPW_DISABLED;
break;
case PCI_DEVICE_ID_MELLANOX_CONNECTX4LX:
- mps = MLX5_MPW;
- break;
case PCI_DEVICE_ID_MELLANOX_CONNECTX5:
case PCI_DEVICE_ID_MELLANOX_CONNECTX5VF:
case PCI_DEVICE_ID_MELLANOX_CONNECTX5EX:
case PCI_DEVICE_ID_MELLANOX_CONNECTX5EXVF:
tunnel_en = 1;
- mps = MLX5_MPW_ENHANCED;
break;
default:
- mps = MLX5_MPW_DISABLED;
+ break;
}
INFO("PCI information matches, using device \"%s\""
- " (SR-IOV: %s, %sMPS: %s)",
+ " (SR-IOV: %s)",
list[i]->name,
- sriov ? "true" : "false",
- mps == MLX5_MPW_ENHANCED ? "Enhanced " : "",
- mps != MLX5_MPW_DISABLED ? "true" : "false");
+ sriov ? "true" : "false");
attr_ctx = ibv_open_device(list[i]);
err = errno;
break;
ibv_dev = list[i];
DEBUG("device opened");
- if (ibv_query_device(attr_ctx, &device_attr))
+ /*
+ * Multi-packet send is supported by ConnectX-4 Lx PF as well
+ * as all ConnectX-5 devices.
+ */
+ mlx5dv_query_device(attr_ctx, &attrs_out);
+ if (attrs_out.flags & MLX5DV_CONTEXT_FLAGS_MPW_ALLOWED) {
+ if (attrs_out.flags & MLX5DV_CONTEXT_FLAGS_ENHANCED_MPW) {
+ DEBUG("Enhanced MPW is supported");
+ mps = MLX5_MPW_ENHANCED;
+ } else {
+ DEBUG("MPW is supported");
+ mps = MLX5_MPW;
+ }
+ } else {
+ DEBUG("MPW isn't supported");
+ mps = MLX5_MPW_DISABLED;
+ }
+ if (RTE_CACHE_LINE_SIZE == 128 &&
+ !(attrs_out.flags & MLX5DV_CONTEXT_FLAGS_CQE_128B_COMP))
+ cqe_comp = 0;
+ else
+ cqe_comp = 1;
+ if (ibv_query_device_ex(attr_ctx, NULL, &device_attr))
goto error;
- INFO("%u port(s) detected", device_attr.phys_port_cnt);
+ INFO("%u port(s) detected", device_attr.orig_attr.phys_port_cnt);
- for (i = 0; i < device_attr.phys_port_cnt; i++) {
+ for (i = 0; i < device_attr.orig_attr.phys_port_cnt; i++) {
+ char name[RTE_ETH_NAME_MAX_LEN];
+ int len;
uint32_t port = i + 1; /* ports are indexed from one */
uint32_t test = (1 << i);
struct ibv_context *ctx = NULL;
struct ibv_pd *pd = NULL;
struct priv *priv = NULL;
struct rte_eth_dev *eth_dev;
- struct ibv_exp_device_attr exp_device_attr;
+ struct ibv_device_attr_ex device_attr_ex;
struct ether_addr mac;
uint16_t num_vfs = 0;
- struct mlx5_args args = {
- .cqe_comp = MLX5_ARG_UNSET,
+ struct ibv_device_attr_ex device_attr;
+ struct mlx5_dev_config config = {
+ .cqe_comp = cqe_comp,
+ .mps = mps,
+ .tunnel_en = tunnel_en,
+ .tx_vec_en = 1,
+ .rx_vec_en = 1,
+ .mpw_hdr_dseg = 0,
.txq_inline = MLX5_ARG_UNSET,
.txqs_inline = MLX5_ARG_UNSET,
- .mps = MLX5_ARG_UNSET,
- .mpw_hdr_dseg = MLX5_ARG_UNSET,
.inline_max_packet_sz = MLX5_ARG_UNSET,
- .tso = MLX5_ARG_UNSET,
- .tx_vec_en = MLX5_ARG_UNSET,
- .rx_vec_en = MLX5_ARG_UNSET,
};
- exp_device_attr.comp_mask =
- IBV_EXP_DEVICE_ATTR_EXP_CAP_FLAGS |
- IBV_EXP_DEVICE_ATTR_RX_HASH |
- IBV_EXP_DEVICE_ATTR_VLAN_OFFLOADS |
- IBV_EXP_DEVICE_ATTR_RX_PAD_END_ALIGN |
- IBV_EXP_DEVICE_ATTR_TSO_CAPS |
- 0;
+ len = snprintf(name, sizeof(name), PCI_PRI_FMT,
+ pci_dev->addr.domain, pci_dev->addr.bus,
+ pci_dev->addr.devid, pci_dev->addr.function);
+ if (device_attr.orig_attr.phys_port_cnt > 1)
+ snprintf(name + len, sizeof(name), " port %u", i);
+
+ mlx5_dev[idx].ports |= test;
+
+ if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
+ eth_dev = rte_eth_dev_attach_secondary(name);
+ if (eth_dev == NULL) {
+ ERROR("can not attach rte ethdev");
+ err = ENOMEM;
+ goto error;
+ }
+ eth_dev->device = &pci_dev->device;
+ eth_dev->dev_ops = &mlx5_dev_sec_ops;
+ priv = eth_dev->data->dev_private;
+ /* Receive command fd from primary process */
+ err = priv_socket_connect(priv);
+ if (err < 0) {
+ err = -err;
+ goto error;
+ }
+ /* Remap UAR for Tx queues. */
+ err = priv_tx_uar_remap(priv, err);
+ if (err < 0) {
+ err = -err;
+ goto error;
+ }
+ /*
+ * Ethdev pointer is still required as input since
+ * the primary device is not accessible from the
+ * secondary process.
+ */
+ eth_dev->rx_pkt_burst =
+ priv_select_rx_function(priv, eth_dev);
+ eth_dev->tx_pkt_burst =
+ priv_select_tx_function(priv, eth_dev);
+ continue;
+ }
DEBUG("using port %u (%08" PRIx32 ")", port, test);
ctx = ibv_open_device(ibv_dev);
- if (ctx == NULL)
+ if (ctx == NULL) {
+ err = ENODEV;
goto port_error;
+ }
+ ibv_query_device_ex(ctx, NULL, &device_attr);
/* Check port status. */
err = ibv_query_port(ctx, port, &port_attr);
if (err) {
if (port_attr.link_layer != IBV_LINK_LAYER_ETHERNET) {
ERROR("port %d is not configured in Ethernet mode",
port);
+ err = EINVAL;
goto port_error;
}
}
priv->ctx = ctx;
+ strncpy(priv->ibdev_path, priv->ctx->device->ibdev_path,
+ sizeof(priv->ibdev_path));
priv->device_attr = device_attr;
priv->port = port;
priv->pd = pd;
priv->mtu = ETHER_MTU;
- priv->mps = mps; /* Enable MPW by default if supported. */
- priv->cqe_comp = 1; /* Enable compression by default. */
- priv->tunnel_en = tunnel_en;
- /* Enable vector by default if supported. */
- priv->tx_vec_en = 1;
- priv->rx_vec_en = 1;
- err = mlx5_args(&args, pci_dev->device.devargs);
+ err = mlx5_args(&config, pci_dev->device.devargs);
if (err) {
ERROR("failed to process device arguments: %s",
strerror(err));
goto port_error;
}
- mlx5_args_assign(priv, &args);
- if (ibv_exp_query_device(ctx, &exp_device_attr)) {
- ERROR("ibv_exp_query_device() failed");
+ if (ibv_query_device_ex(ctx, NULL, &device_attr_ex)) {
+ ERROR("ibv_query_device_ex() failed");
goto port_error;
}
- priv->hw_csum =
- ((exp_device_attr.exp_device_cap_flags &
- IBV_EXP_DEVICE_RX_CSUM_TCP_UDP_PKT) &&
- (exp_device_attr.exp_device_cap_flags &
- IBV_EXP_DEVICE_RX_CSUM_IP_PKT));
+ config.hw_csum = !!(device_attr_ex.device_cap_flags_ex &
+ IBV_DEVICE_RAW_IP_CSUM);
DEBUG("checksum offloading is %ssupported",
- (priv->hw_csum ? "" : "not "));
+ (config.hw_csum ? "" : "not "));
- priv->hw_csum_l2tun = !!(exp_device_attr.exp_device_cap_flags &
- IBV_EXP_DEVICE_VXLAN_SUPPORT);
- DEBUG("L2 tunnel checksum offloads are %ssupported",
- (priv->hw_csum_l2tun ? "" : "not "));
-
- priv->ind_table_max_size = exp_device_attr.rx_hash_caps.max_rwq_indirection_table_size;
+#ifdef HAVE_IBV_DEVICE_VXLAN_SUPPORT
+ config.hw_csum_l2tun =
+ !!(exp_device_attr.exp_device_cap_flags &
+ IBV_DEVICE_VXLAN_SUPPORT);
+#endif
+ DEBUG("Rx L2 tunnel checksum offloads are %ssupported",
+ (config.hw_csum_l2tun ? "" : "not "));
+
+#ifdef HAVE_IBV_DEVICE_COUNTERS_SET_SUPPORT
+ config.flow_counter_en = !!(device_attr.max_counter_sets);
+ ibv_describe_counter_set(ctx, 0, &cs_desc);
+ DEBUG("counter type = %d, num of cs = %ld, attributes = %d",
+ cs_desc.counter_type, cs_desc.num_of_cs,
+ cs_desc.attributes);
+#endif
+ config.ind_table_max_size =
+ device_attr_ex.rss_caps.max_rwq_indirection_table_size;
/* Remove this check once DPDK supports larger/variable
* indirection tables. */
- if (priv->ind_table_max_size >
+ if (config.ind_table_max_size >
(unsigned int)ETH_RSS_RETA_SIZE_512)
- priv->ind_table_max_size = ETH_RSS_RETA_SIZE_512;
+ config.ind_table_max_size = ETH_RSS_RETA_SIZE_512;
DEBUG("maximum RX indirection table size is %u",
- priv->ind_table_max_size);
- priv->hw_vlan_strip = !!(exp_device_attr.wq_vlan_offloads_cap &
- IBV_EXP_RECEIVE_WQ_CVLAN_STRIP);
+ config.ind_table_max_size);
+ config.hw_vlan_strip = !!(device_attr_ex.raw_packet_caps &
+ IBV_RAW_PACKET_CAP_CVLAN_STRIPPING);
DEBUG("VLAN stripping is %ssupported",
- (priv->hw_vlan_strip ? "" : "not "));
+ (config.hw_vlan_strip ? "" : "not "));
- priv->hw_fcs_strip = !!(exp_device_attr.exp_device_cap_flags &
- IBV_EXP_DEVICE_SCATTER_FCS);
+ config.hw_fcs_strip =
+ !!(device_attr_ex.orig_attr.device_cap_flags &
+ IBV_WQ_FLAGS_SCATTER_FCS);
DEBUG("FCS stripping configuration is %ssupported",
- (priv->hw_fcs_strip ? "" : "not "));
+ (config.hw_fcs_strip ? "" : "not "));
- priv->hw_padding = !!exp_device_attr.rx_pad_end_addr_align;
+#ifdef HAVE_IBV_WQ_FLAG_RX_END_PADDING
+ config.hw_padding = !!device_attr_ex.rx_pad_end_addr_align;
+#endif
DEBUG("hardware RX end alignment padding is %ssupported",
- (priv->hw_padding ? "" : "not "));
+ (config.hw_padding ? "" : "not "));
priv_get_num_vfs(priv, &num_vfs);
- priv->sriov = (num_vfs || sriov);
- priv->tso = ((priv->tso) &&
- (exp_device_attr.tso_caps.max_tso > 0) &&
- (exp_device_attr.tso_caps.supported_qpts &
- (1 << IBV_QPT_RAW_ETH)));
- if (priv->tso)
- priv->max_tso_payload_sz =
- exp_device_attr.tso_caps.max_tso;
- if (priv->mps && !mps) {
+ config.sriov = (num_vfs || sriov);
+ config.tso = ((device_attr_ex.tso_caps.max_tso > 0) &&
+ (device_attr_ex.tso_caps.supported_qpts &
+ (1 << IBV_QPT_RAW_PACKET)));
+ if (config.tso)
+ config.tso_max_payload_sz =
+ device_attr_ex.tso_caps.max_tso;
+ if (config.mps && !mps) {
ERROR("multi-packet send not supported on this device"
" (" MLX5_TXQ_MPW_EN ")");
err = ENOTSUP;
goto port_error;
- } else if (priv->mps && priv->tso) {
- WARN("multi-packet send not supported in conjunction "
- "with TSO. MPS disabled");
- priv->mps = 0;
}
INFO("%sMPS is %s",
- priv->mps == MLX5_MPW_ENHANCED ? "Enhanced " : "",
- priv->mps != MLX5_MPW_DISABLED ? "enabled" : "disabled");
- /* Set default values for Enhanced MPW, a.k.a MPWv2. */
- if (priv->mps == MLX5_MPW_ENHANCED) {
- if (args.txqs_inline == MLX5_ARG_UNSET)
- priv->txqs_inline = MLX5_EMPW_MIN_TXQS;
- if (args.inline_max_packet_sz == MLX5_ARG_UNSET)
- priv->inline_max_packet_sz =
- MLX5_EMPW_MAX_INLINE_LEN;
- if (args.txq_inline == MLX5_ARG_UNSET)
- priv->txq_inline = MLX5_WQE_SIZE_MAX -
- MLX5_WQE_SIZE;
- }
- /* Allocate and register default RSS hash keys. */
- priv->rss_conf = rte_calloc(__func__, hash_rxq_init_n,
- sizeof((*priv->rss_conf)[0]), 0);
- if (priv->rss_conf == NULL) {
- err = ENOMEM;
- goto port_error;
+ config.mps == MLX5_MPW_ENHANCED ? "Enhanced " : "",
+ config.mps != MLX5_MPW_DISABLED ? "enabled" : "disabled");
+ if (config.cqe_comp && !cqe_comp) {
+ WARN("Rx CQE compression isn't supported");
+ config.cqe_comp = 0;
}
- err = rss_hash_rss_conf_new_key(priv,
- rss_hash_default_key,
- rss_hash_default_key_len,
- ETH_RSS_PROTO_MASK);
- if (err)
- goto port_error;
/* Configure the first MAC address by default. */
if (priv_get_mac(priv, &mac.addr_bytes)) {
ERROR("cannot get MAC address, is mlx5_en loaded?"
" (errno: %s)", strerror(errno));
+ err = ENODEV;
goto port_error;
}
INFO("port %u MAC address is %02x:%02x:%02x:%02x:%02x:%02x",
mac.addr_bytes[0], mac.addr_bytes[1],
mac.addr_bytes[2], mac.addr_bytes[3],
mac.addr_bytes[4], mac.addr_bytes[5]);
- /* Register MAC address. */
- claim_zero(priv_mac_addr_add(priv, 0,
- (const uint8_t (*)[ETHER_ADDR_LEN])
- mac.addr_bytes));
- /* Initialize FD filters list. */
- err = fdir_init_filters_list(priv);
- if (err)
- goto port_error;
#ifndef NDEBUG
{
char ifname[IF_NAMESIZE];
priv_get_mtu(priv, &priv->mtu);
DEBUG("port %u MTU is %u", priv->port, priv->mtu);
- /* from rte_ethdev.c */
- {
- char name[RTE_ETH_NAME_MAX_LEN];
-
- snprintf(name, sizeof(name), "%s port %u",
- ibv_get_device_name(ibv_dev), port);
- eth_dev = rte_eth_dev_allocate(name);
- }
+ eth_dev = rte_eth_dev_allocate(name);
if (eth_dev == NULL) {
ERROR("can not allocate rte ethdev");
err = ENOMEM;
eth_dev->data->mac_addrs = priv->mac;
eth_dev->device = &pci_dev->device;
rte_eth_copy_pci_info(eth_dev, pci_dev);
- eth_dev->data->dev_flags |= RTE_ETH_DEV_DETACHABLE;
eth_dev->device->driver = &mlx5_driver.driver;
priv->dev = eth_dev;
eth_dev->dev_ops = &mlx5_dev_ops;
+ /* Register MAC address. */
+ claim_zero(mlx5_mac_addr_add(eth_dev, &mac, 0, 0));
TAILQ_INIT(&priv->flows);
+ TAILQ_INIT(&priv->ctrl_flows);
+
+ /* Hint libmlx5 to use PMD allocator for data plane resources */
+ struct mlx5dv_ctx_allocators alctr = {
+ .alloc = &mlx5_alloc_verbs_buf,
+ .free = &mlx5_free_verbs_buf,
+ .data = priv,
+ };
+ mlx5dv_set_context_attr(ctx, MLX5DV_CTX_ATTR_BUF_ALLOCATORS,
+ (void *)((uintptr_t)&alctr));
/* Bring Ethernet device up. */
DEBUG("forcing Ethernet interface up");
priv_set_flags(priv, ~IFF_UP, IFF_UP);
- mlx5_link_update(priv->dev, 1);
+ /* Store device configuration on private structure. */
+ priv->config = config;
continue;
port_error:
- if (priv) {
- rte_free(priv->rss_conf);
+ if (priv)
rte_free(priv);
- }
if (pd)
claim_zero(ibv_dealloc_pd(pd));
if (ctx)
},
.id_table = mlx5_pci_id_map,
.probe = mlx5_pci_probe,
- .drv_flags = RTE_PCI_DRV_INTR_LSC,
+ .drv_flags = RTE_PCI_DRV_INTR_LSC | RTE_PCI_DRV_INTR_RMV,
};
/**
* using this PMD, which is not supported in forked processes.
*/
setenv("RDMAV_HUGEPAGES_SAFE", "1", 1);
- /* Don't map UAR to WC if BlueFlame is not used.*/
- setenv("MLX5_SHUT_UP_BF", "1", 1);
+ /* Match the size of Rx completion entry to the size of a cacheline. */
+ if (RTE_CACHE_LINE_SIZE == 128)
+ setenv("MLX5_CQE_SIZE", "128", 0);
ibv_fork_init();
rte_pci_register(&mlx5_driver);
}