#include <linux/ethtool.h>
#include <fcntl.h>
-/* Verbs header. */
-/* ISO C doesn't support unnamed structs/unions, disabling -pedantic. */
-#ifdef PEDANTIC
-#pragma GCC diagnostic ignored "-Wpedantic"
-#endif
-#include <infiniband/verbs.h>
-#ifdef PEDANTIC
-#pragma GCC diagnostic error "-Wpedantic"
-#endif
-
#include <rte_malloc.h>
-#include <rte_ethdev_driver.h>
-#include <rte_ethdev_pci.h>
+#include <ethdev_driver.h>
+#include <ethdev_pci.h>
#include <rte_pci.h>
#include <rte_bus_pci.h>
#include <rte_common.h>
#include "mlx5_flow.h"
#include "rte_pmd_mlx5.h"
#include "mlx5_verbs.h"
+#include "mlx5_nl.h"
+#include "mlx5_devx.h"
#define MLX5_TAGS_HLIST_ARRAY_SIZE 8192
#define MLX5DV_CONTEXT_FLAGS_CQE_128B_COMP (1 << 4)
#endif
+static const char *MZ_MLX5_PMD_SHARED_DATA = "mlx5_pmd_shared_data";
+
+/* Spinlock for mlx5_shared_data allocation. */
+static rte_spinlock_t mlx5_shared_data_lock = RTE_SPINLOCK_INITIALIZER;
+
+/* Process local data for secondary processes. */
+static struct mlx5_local_data mlx5_local_data;
+
+/**
+ * Set the completion channel file descriptor interrupt as non-blocking.
+ *
+ * @param[in] rxq_obj
+ * Pointer to RQ channel object, which includes the channel fd
+ *
+ * @param[out] fd
+ * The file descriptor (representing the intetrrupt) used in this channel.
+ *
+ * @return
+ * 0 on successfully setting the fd to non-blocking, non-zero otherwise.
+ */
+int
+mlx5_os_set_nonblock_channel_fd(int fd)
+{
+ int flags;
+
+ flags = fcntl(fd, F_GETFL);
+ return fcntl(fd, F_SETFL, flags | O_NONBLOCK);
+}
+
/**
* Get mlx5 device attributes. The glue function query_device_ex() is called
* with out parameter of type 'struct ibv_device_attr_ex *'. Then fill in mlx5
device_attr->max_qp_wr = attr_ex.orig_attr.max_qp_wr;
device_attr->max_sge = attr_ex.orig_attr.max_sge;
device_attr->max_cq = attr_ex.orig_attr.max_cq;
+ device_attr->max_cqe = attr_ex.orig_attr.max_cqe;
+ device_attr->max_mr = attr_ex.orig_attr.max_mr;
+ device_attr->max_pd = attr_ex.orig_attr.max_pd;
device_attr->max_qp = attr_ex.orig_attr.max_qp;
+ device_attr->max_srq = attr_ex.orig_attr.max_srq;
+ device_attr->max_srq_wr = attr_ex.orig_attr.max_srq_wr;
device_attr->raw_packet_caps = attr_ex.raw_packet_caps;
device_attr->max_rwq_indirection_table_size =
attr_ex.rss_caps.max_rwq_indirection_table_size;
static void *
mlx5_alloc_verbs_buf(size_t size, void *data)
{
- struct mlx5_priv *priv = data;
+ struct mlx5_dev_ctx_shared *sh = data;
void *ret;
- unsigned int socket = SOCKET_ID_ANY;
size_t alignment = rte_mem_page_size();
if (alignment == (size_t)-1) {
DRV_LOG(ERR, "Failed to get mem page size");
return NULL;
}
- 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;
- }
MLX5_ASSERT(data != NULL);
- ret = mlx5_malloc(0, size, alignment, socket);
+ ret = mlx5_malloc(0, size, alignment, sh->numa_node);
if (!ret && size)
rte_errno = ENOMEM;
return ret;
mlx5_alloc_shared_dr(struct mlx5_priv *priv)
{
struct mlx5_dev_ctx_shared *sh = priv->sh;
- char s[MLX5_HLIST_NAMESIZE];
- int err = 0;
+ char s[MLX5_HLIST_NAMESIZE] __rte_unused;
+ int err;
- if (!sh->flow_tbls)
- err = mlx5_alloc_table_hash_list(priv);
- else
- DRV_LOG(DEBUG, "sh->flow_tbls[%p] already created, reuse\n",
- (void *)sh->flow_tbls);
+ MLX5_ASSERT(sh && sh->refcnt);
+ if (sh->refcnt > 1)
+ return 0;
+ err = mlx5_alloc_table_hash_list(priv);
if (err)
- return err;
+ goto error;
+ /* The resources below are only valid with DV support. */
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+ /* Init port id action cache list. */
+ snprintf(s, sizeof(s), "%s_port_id_action_cache", sh->ibdev_name);
+ mlx5_cache_list_init(&sh->port_id_action_list, s, 0, sh,
+ flow_dv_port_id_create_cb,
+ flow_dv_port_id_match_cb,
+ flow_dv_port_id_remove_cb);
+ /* Init push vlan action cache list. */
+ snprintf(s, sizeof(s), "%s_push_vlan_action_cache", sh->ibdev_name);
+ mlx5_cache_list_init(&sh->push_vlan_action_list, s, 0, sh,
+ flow_dv_push_vlan_create_cb,
+ flow_dv_push_vlan_match_cb,
+ flow_dv_push_vlan_remove_cb);
+ /* Init sample action cache list. */
+ snprintf(s, sizeof(s), "%s_sample_action_cache", sh->ibdev_name);
+ mlx5_cache_list_init(&sh->sample_action_list, s, 0, sh,
+ flow_dv_sample_create_cb,
+ flow_dv_sample_match_cb,
+ flow_dv_sample_remove_cb);
+ /* Init dest array action cache list. */
+ snprintf(s, sizeof(s), "%s_dest_array_cache", sh->ibdev_name);
+ mlx5_cache_list_init(&sh->dest_array_list, s, 0, sh,
+ flow_dv_dest_array_create_cb,
+ flow_dv_dest_array_match_cb,
+ flow_dv_dest_array_remove_cb);
/* Create tags hash list table. */
snprintf(s, sizeof(s), "%s_tags", sh->ibdev_name);
- sh->tag_table = mlx5_hlist_create(s, MLX5_TAGS_HLIST_ARRAY_SIZE);
+ sh->tag_table = mlx5_hlist_create(s, MLX5_TAGS_HLIST_ARRAY_SIZE, 0,
+ MLX5_HLIST_WRITE_MOST,
+ flow_dv_tag_create_cb,
+ flow_dv_tag_match_cb,
+ flow_dv_tag_remove_cb);
if (!sh->tag_table) {
DRV_LOG(ERR, "tags with hash creation failed.");
err = ENOMEM;
goto error;
}
+ sh->tag_table->ctx = sh;
+ snprintf(s, sizeof(s), "%s_hdr_modify", sh->ibdev_name);
+ sh->modify_cmds = mlx5_hlist_create(s, MLX5_FLOW_HDR_MODIFY_HTABLE_SZ,
+ 0, MLX5_HLIST_WRITE_MOST |
+ MLX5_HLIST_DIRECT_KEY,
+ flow_dv_modify_create_cb,
+ flow_dv_modify_match_cb,
+ flow_dv_modify_remove_cb);
+ if (!sh->modify_cmds) {
+ DRV_LOG(ERR, "hdr modify hash creation failed");
+ err = ENOMEM;
+ goto error;
+ }
+ sh->modify_cmds->ctx = sh;
+ snprintf(s, sizeof(s), "%s_encaps_decaps", sh->ibdev_name);
+ sh->encaps_decaps = mlx5_hlist_create(s,
+ MLX5_FLOW_ENCAP_DECAP_HTABLE_SZ,
+ 0, MLX5_HLIST_DIRECT_KEY |
+ MLX5_HLIST_WRITE_MOST,
+ flow_dv_encap_decap_create_cb,
+ flow_dv_encap_decap_match_cb,
+ flow_dv_encap_decap_remove_cb);
+ if (!sh->encaps_decaps) {
+ DRV_LOG(ERR, "encap decap hash creation failed");
+ err = ENOMEM;
+ goto error;
+ }
+ sh->encaps_decaps->ctx = sh;
+#endif
#ifdef HAVE_MLX5DV_DR
void *domain;
- if (sh->dv_refcnt) {
- /* Shared DV/DR structures is already initialized. */
- sh->dv_refcnt++;
- priv->dr_shared = 1;
- return 0;
- }
/* Reference counter is zero, we should initialize structures. */
domain = mlx5_glue->dr_create_domain(sh->ctx,
MLX5DV_DR_DOMAIN_TYPE_NIC_RX);
err = errno;
goto error;
}
- pthread_mutex_init(&sh->dv_mutex, NULL);
sh->tx_domain = domain;
#ifdef HAVE_MLX5DV_DR_ESWITCH
if (priv->config.dv_esw_en) {
sh->esw_drop_action = mlx5_glue->dr_create_flow_action_drop();
}
#endif
+ if (!sh->tunnel_hub)
+ err = mlx5_alloc_tunnel_hub(sh);
+ if (err) {
+ DRV_LOG(ERR, "mlx5_alloc_tunnel_hub failed err=%d", err);
+ goto error;
+ }
if (priv->config.reclaim_mode == MLX5_RCM_AGGR) {
mlx5_glue->dr_reclaim_domain_memory(sh->rx_domain, 1);
mlx5_glue->dr_reclaim_domain_memory(sh->tx_domain, 1);
}
sh->pop_vlan_action = mlx5_glue->dr_create_flow_action_pop_vlan();
#endif /* HAVE_MLX5DV_DR */
- sh->dv_refcnt++;
- priv->dr_shared = 1;
+ sh->default_miss_action =
+ mlx5_glue->dr_create_flow_action_default_miss();
+ if (!sh->default_miss_action)
+ DRV_LOG(WARNING, "Default miss action is not supported.");
return 0;
error:
/* Rollback the created objects. */
mlx5_glue->destroy_flow_action(sh->pop_vlan_action);
sh->pop_vlan_action = NULL;
}
+ if (sh->encaps_decaps) {
+ mlx5_hlist_destroy(sh->encaps_decaps);
+ sh->encaps_decaps = NULL;
+ }
+ if (sh->modify_cmds) {
+ mlx5_hlist_destroy(sh->modify_cmds);
+ sh->modify_cmds = NULL;
+ }
if (sh->tag_table) {
/* tags should be destroyed with flow before. */
- mlx5_hlist_destroy(sh->tag_table, NULL, NULL);
+ mlx5_hlist_destroy(sh->tag_table);
sh->tag_table = NULL;
}
+ if (sh->tunnel_hub) {
+ mlx5_release_tunnel_hub(sh, priv->dev_port);
+ sh->tunnel_hub = NULL;
+ }
mlx5_free_table_hash_list(priv);
return err;
}
void
mlx5_os_free_shared_dr(struct mlx5_priv *priv)
{
- struct mlx5_dev_ctx_shared *sh;
+ struct mlx5_dev_ctx_shared *sh = priv->sh;
- if (!priv->dr_shared)
+ MLX5_ASSERT(sh && sh->refcnt);
+ if (sh->refcnt > 1)
return;
- priv->dr_shared = 0;
- sh = priv->sh;
- MLX5_ASSERT(sh);
#ifdef HAVE_MLX5DV_DR
- MLX5_ASSERT(sh->dv_refcnt);
- if (sh->dv_refcnt && --sh->dv_refcnt)
- return;
if (sh->rx_domain) {
mlx5_glue->dr_destroy_domain(sh->rx_domain);
sh->rx_domain = NULL;
mlx5_glue->destroy_flow_action(sh->pop_vlan_action);
sh->pop_vlan_action = NULL;
}
- pthread_mutex_destroy(&sh->dv_mutex);
#endif /* HAVE_MLX5DV_DR */
+ if (sh->default_miss_action)
+ mlx5_glue->destroy_flow_action
+ (sh->default_miss_action);
+ if (sh->encaps_decaps) {
+ mlx5_hlist_destroy(sh->encaps_decaps);
+ sh->encaps_decaps = NULL;
+ }
+ if (sh->modify_cmds) {
+ mlx5_hlist_destroy(sh->modify_cmds);
+ sh->modify_cmds = NULL;
+ }
if (sh->tag_table) {
/* tags should be destroyed with flow before. */
- mlx5_hlist_destroy(sh->tag_table, NULL, NULL);
+ mlx5_hlist_destroy(sh->tag_table);
sh->tag_table = NULL;
}
+ if (sh->tunnel_hub) {
+ mlx5_release_tunnel_hub(sh, priv->dev_port);
+ sh->tunnel_hub = NULL;
+ }
+ mlx5_cache_list_destroy(&sh->port_id_action_list);
+ mlx5_cache_list_destroy(&sh->push_vlan_action_list);
mlx5_free_table_hash_list(priv);
}
+/**
+ * Initialize shared data between primary and secondary process.
+ *
+ * A memzone is reserved by primary process and secondary processes attach to
+ * the memzone.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_init_shared_data(void)
+{
+ const struct rte_memzone *mz;
+ int ret = 0;
+
+ rte_spinlock_lock(&mlx5_shared_data_lock);
+ if (mlx5_shared_data == NULL) {
+ if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
+ /* Allocate shared memory. */
+ mz = rte_memzone_reserve(MZ_MLX5_PMD_SHARED_DATA,
+ sizeof(*mlx5_shared_data),
+ SOCKET_ID_ANY, 0);
+ if (mz == NULL) {
+ DRV_LOG(ERR,
+ "Cannot allocate mlx5 shared data");
+ ret = -rte_errno;
+ goto error;
+ }
+ mlx5_shared_data = mz->addr;
+ memset(mlx5_shared_data, 0, sizeof(*mlx5_shared_data));
+ rte_spinlock_init(&mlx5_shared_data->lock);
+ } else {
+ /* Lookup allocated shared memory. */
+ mz = rte_memzone_lookup(MZ_MLX5_PMD_SHARED_DATA);
+ if (mz == NULL) {
+ DRV_LOG(ERR,
+ "Cannot attach mlx5 shared data");
+ ret = -rte_errno;
+ goto error;
+ }
+ mlx5_shared_data = mz->addr;
+ memset(&mlx5_local_data, 0, sizeof(mlx5_local_data));
+ }
+ }
+error:
+ rte_spinlock_unlock(&mlx5_shared_data_lock);
+ return ret;
+}
+
+/**
+ * PMD global initialization.
+ *
+ * Independent from individual device, this function initializes global
+ * per-PMD data structures distinguishing primary and secondary processes.
+ * Hence, each initialization is called once per a process.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_init_once(void)
+{
+ struct mlx5_shared_data *sd;
+ struct mlx5_local_data *ld = &mlx5_local_data;
+ int ret = 0;
+
+ if (mlx5_init_shared_data())
+ return -rte_errno;
+ sd = mlx5_shared_data;
+ MLX5_ASSERT(sd);
+ rte_spinlock_lock(&sd->lock);
+ switch (rte_eal_process_type()) {
+ case RTE_PROC_PRIMARY:
+ if (sd->init_done)
+ break;
+ LIST_INIT(&sd->mem_event_cb_list);
+ rte_rwlock_init(&sd->mem_event_rwlock);
+ rte_mem_event_callback_register("MLX5_MEM_EVENT_CB",
+ mlx5_mr_mem_event_cb, NULL);
+ ret = mlx5_mp_init_primary(MLX5_MP_NAME,
+ mlx5_mp_os_primary_handle);
+ if (ret)
+ goto out;
+ sd->init_done = true;
+ break;
+ case RTE_PROC_SECONDARY:
+ if (ld->init_done)
+ break;
+ ret = mlx5_mp_init_secondary(MLX5_MP_NAME,
+ mlx5_mp_os_secondary_handle);
+ if (ret)
+ goto out;
+ ++sd->secondary_cnt;
+ ld->init_done = true;
+ break;
+ default:
+ break;
+ }
+out:
+ rte_spinlock_unlock(&sd->lock);
+ return ret;
+}
+
+/**
+ * Create the Tx queue DevX/Verbs object.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param idx
+ * Queue index in DPDK Tx queue array.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_os_txq_obj_new(struct rte_eth_dev *dev, uint16_t idx)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_txq_data *txq_data = (*priv->txqs)[idx];
+ struct mlx5_txq_ctrl *txq_ctrl =
+ container_of(txq_data, struct mlx5_txq_ctrl, txq);
+
+ if (txq_ctrl->type == MLX5_TXQ_TYPE_HAIRPIN)
+ return mlx5_txq_devx_obj_new(dev, idx);
+#ifdef HAVE_MLX5DV_DEVX_UAR_OFFSET
+ if (!priv->config.dv_esw_en)
+ return mlx5_txq_devx_obj_new(dev, idx);
+#endif
+ return mlx5_txq_ibv_obj_new(dev, idx);
+}
+
+/**
+ * Release an Tx DevX/verbs queue object.
+ *
+ * @param txq_obj
+ * DevX/Verbs Tx queue object.
+ */
+static void
+mlx5_os_txq_obj_release(struct mlx5_txq_obj *txq_obj)
+{
+ if (txq_obj->txq_ctrl->type == MLX5_TXQ_TYPE_HAIRPIN) {
+ mlx5_txq_devx_obj_release(txq_obj);
+ return;
+ }
+#ifdef HAVE_MLX5DV_DEVX_UAR_OFFSET
+ if (!txq_obj->txq_ctrl->priv->config.dv_esw_en) {
+ mlx5_txq_devx_obj_release(txq_obj);
+ return;
+ }
+#endif
+ mlx5_txq_ibv_obj_release(txq_obj);
+}
+
+/**
+ * DV flow counter mode detect and config.
+ *
+ * @param dev
+ * Pointer to rte_eth_dev structure.
+ *
+ */
+static void
+mlx5_flow_counter_mode_config(struct rte_eth_dev *dev __rte_unused)
+{
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_dev_ctx_shared *sh = priv->sh;
+ bool fallback;
+
+#ifndef HAVE_IBV_DEVX_ASYNC
+ fallback = true;
+#else
+ fallback = false;
+ if (!priv->config.devx || !priv->config.dv_flow_en ||
+ !priv->config.hca_attr.flow_counters_dump ||
+ !(priv->config.hca_attr.flow_counter_bulk_alloc_bitmap & 0x4) ||
+ (mlx5_flow_dv_discover_counter_offset_support(dev) == -ENOTSUP))
+ fallback = true;
+#endif
+ if (fallback)
+ DRV_LOG(INFO, "Use fall-back DV counter management. Flow "
+ "counter dump:%d, bulk_alloc_bitmap:0x%hhx.",
+ priv->config.hca_attr.flow_counters_dump,
+ priv->config.hca_attr.flow_counter_bulk_alloc_bitmap);
+ /* Initialize fallback mode only on the port initializes sh. */
+ if (sh->refcnt == 1)
+ sh->cmng.counter_fallback = fallback;
+ else if (fallback != sh->cmng.counter_fallback)
+ DRV_LOG(WARNING, "Port %d in sh has different fallback mode "
+ "with others:%d.", PORT_ID(priv), fallback);
+#endif
+}
+
+static void
+mlx5_queue_counter_id_prepare(struct rte_eth_dev *dev)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ void *ctx = priv->sh->ctx;
+
+ priv->q_counters = mlx5_devx_cmd_queue_counter_alloc(ctx);
+ if (!priv->q_counters) {
+ struct ibv_cq *cq = mlx5_glue->create_cq(ctx, 1, NULL, NULL, 0);
+ struct ibv_wq *wq;
+
+ DRV_LOG(DEBUG, "Port %d queue counter object cannot be created "
+ "by DevX - fall-back to use the kernel driver global "
+ "queue counter.", dev->data->port_id);
+ /* Create WQ by kernel and query its queue counter ID. */
+ if (cq) {
+ wq = mlx5_glue->create_wq(ctx,
+ &(struct ibv_wq_init_attr){
+ .wq_type = IBV_WQT_RQ,
+ .max_wr = 1,
+ .max_sge = 1,
+ .pd = priv->sh->pd,
+ .cq = cq,
+ });
+ if (wq) {
+ /* Counter is assigned only on RDY state. */
+ int ret = mlx5_glue->modify_wq(wq,
+ &(struct ibv_wq_attr){
+ .attr_mask = IBV_WQ_ATTR_STATE,
+ .wq_state = IBV_WQS_RDY,
+ });
+
+ if (ret == 0)
+ mlx5_devx_cmd_wq_query(wq,
+ &priv->counter_set_id);
+ claim_zero(mlx5_glue->destroy_wq(wq));
+ }
+ claim_zero(mlx5_glue->destroy_cq(cq));
+ }
+ } else {
+ priv->counter_set_id = priv->q_counters->id;
+ }
+ if (priv->counter_set_id == 0)
+ DRV_LOG(INFO, "Part of the port %d statistics will not be "
+ "available.", dev->data->port_id);
+}
+
/**
* Spawn an Ethernet device from Verbs information.
*
static struct rte_eth_dev *
mlx5_dev_spawn(struct rte_device *dpdk_dev,
struct mlx5_dev_spawn_data *spawn,
- struct mlx5_dev_config config)
+ struct mlx5_dev_config *config)
{
const struct mlx5_switch_info *switch_info = &spawn->info;
struct mlx5_dev_ctx_shared *sh = NULL;
int err = 0;
unsigned int hw_padding = 0;
unsigned int mps;
- unsigned int cqe_comp;
- unsigned int cqe_pad = 0;
unsigned int tunnel_en = 0;
unsigned int mpls_en = 0;
unsigned int swp = 0;
strerror(rte_errno));
return NULL;
}
+ if (eth_da.type == RTE_ETH_REPRESENTOR_NONE) {
+ /* Representor not specified. */
+ rte_errno = EBUSY;
+ return NULL;
+ }
+ if (eth_da.type != RTE_ETH_REPRESENTOR_VF) {
+ rte_errno = ENOTSUP;
+ DRV_LOG(ERR, "unsupported representor type: %s",
+ dpdk_dev->devargs->args);
+ return NULL;
+ }
for (i = 0; i < eth_da.nb_representor_ports; ++i)
if (eth_da.representor_ports[i] ==
(uint16_t)switch_info->port_name)
rte_errno = ENOMEM;
return NULL;
}
- eth_dev->device = dpdk_dev;
- eth_dev->dev_ops = &mlx5_os_dev_sec_ops;
+ priv = eth_dev->data->dev_private;
+ if (priv->sh->bond_dev != UINT16_MAX)
+ /* For bonding port, use primary PCI device. */
+ eth_dev->device =
+ rte_eth_devices[priv->sh->bond_dev].device;
+ else
+ eth_dev->device = dpdk_dev;
+ eth_dev->dev_ops = &mlx5_dev_sec_ops;
+ eth_dev->rx_descriptor_status = mlx5_rx_descriptor_status;
+ eth_dev->tx_descriptor_status = mlx5_tx_descriptor_status;
err = mlx5_proc_priv_init(eth_dev);
if (err)
return NULL;
* devargs here to get ones, and later proceed devargs again
* to override some hardware settings.
*/
- err = mlx5_args(&config, dpdk_dev->devargs);
+ err = mlx5_args(config, dpdk_dev->devargs);
if (err) {
err = rte_errno;
DRV_LOG(ERR, "failed to process device arguments: %s",
strerror(rte_errno));
goto error;
}
- mlx5_malloc_mem_select(config.sys_mem_en);
- sh = mlx5_alloc_shared_dev_ctx(spawn, &config);
+ if (config->dv_miss_info) {
+ if (switch_info->master || switch_info->representor)
+ config->dv_xmeta_en = MLX5_XMETA_MODE_META16;
+ }
+ mlx5_malloc_mem_select(config->sys_mem_en);
+ sh = mlx5_alloc_shared_dev_ctx(spawn, config);
if (!sh)
return NULL;
- config.devx = sh->devx;
+ config->devx = sh->devx;
#ifdef HAVE_MLX5DV_DR_ACTION_DEST_DEVX_TIR
- config.dest_tir = 1;
+ config->dest_tir = 1;
#endif
#ifdef HAVE_IBV_MLX5_MOD_SWP
dv_attr.comp_mask |= MLX5DV_CONTEXT_MASK_SWP;
swp = dv_attr.sw_parsing_caps.sw_parsing_offloads;
DRV_LOG(DEBUG, "SWP support: %u", swp);
#endif
- config.swp = !!swp;
+ config->swp = !!swp;
#ifdef HAVE_IBV_DEVICE_STRIDING_RQ_SUPPORT
if (dv_attr.comp_mask & MLX5DV_CONTEXT_MASK_STRIDING_RQ) {
struct mlx5dv_striding_rq_caps mprq_caps =
mprq_caps.max_single_wqe_log_num_of_strides;
}
#endif
- if (RTE_CACHE_LINE_SIZE == 128 &&
- !(dv_attr.flags & MLX5DV_CONTEXT_FLAGS_CQE_128B_COMP))
- cqe_comp = 0;
- else
- cqe_comp = 1;
- config.cqe_comp = cqe_comp;
-#ifdef HAVE_IBV_MLX5_MOD_CQE_128B_PAD
- /* Whether device supports 128B Rx CQE padding. */
- cqe_pad = RTE_CACHE_LINE_SIZE == 128 &&
- (dv_attr.flags & MLX5DV_CONTEXT_FLAGS_CQE_128B_PAD);
-#endif
+ /* Rx CQE compression is enabled by default. */
+ config->cqe_comp = 1;
#ifdef HAVE_IBV_DEVICE_TUNNEL_SUPPORT
if (dv_attr.comp_mask & MLX5DV_CONTEXT_MASK_TUNNEL_OFFLOADS) {
tunnel_en = ((dv_attr.tunnel_offloads_caps &
DRV_LOG(WARNING,
"tunnel offloading disabled due to old OFED/rdma-core version");
#endif
- config.tunnel_en = tunnel_en;
+ config->tunnel_en = tunnel_en;
#ifdef HAVE_IBV_DEVICE_MPLS_SUPPORT
mpls_en = ((dv_attr.tunnel_offloads_caps &
MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_CW_MPLS_OVER_GRE) &&
DRV_LOG(WARNING, "MPLS over GRE/UDP tunnel offloading disabled due to"
" old OFED/rdma-core version or firmware configuration");
#endif
- config.mpls_en = mpls_en;
+ config->mpls_en = mpls_en;
/* Check port status. */
err = mlx5_glue->query_port(sh->ctx, spawn->phys_port, &port_attr);
if (err) {
priv->dev_port = spawn->phys_port;
priv->pci_dev = spawn->pci_dev;
priv->mtu = RTE_ETHER_MTU;
- priv->mp_id.port_id = port_id;
- strlcpy(priv->mp_id.name, MLX5_MP_NAME, RTE_MP_MAX_NAME_LEN);
/* Some internal functions rely on Netlink sockets, open them now. */
priv->nl_socket_rdma = mlx5_nl_init(NETLINK_RDMA);
priv->nl_socket_route = mlx5_nl_init(NETLINK_ROUTE);
own_domain_id = 1;
}
/* Override some values set by hardware configuration. */
- mlx5_args(&config, dpdk_dev->devargs);
- err = mlx5_dev_check_sibling_config(priv, &config);
+ mlx5_args(config, dpdk_dev->devargs);
+ err = mlx5_dev_check_sibling_config(priv, config);
if (err)
goto error;
- config.hw_csum = !!(sh->device_attr.device_cap_flags_ex &
+ config->hw_csum = !!(sh->device_attr.device_cap_flags_ex &
IBV_DEVICE_RAW_IP_CSUM);
DRV_LOG(DEBUG, "checksum offloading is %ssupported",
- (config.hw_csum ? "" : "not "));
+ (config->hw_csum ? "" : "not "));
#if !defined(HAVE_IBV_DEVICE_COUNTERS_SET_V42) && \
!defined(HAVE_IBV_DEVICE_COUNTERS_SET_V45)
DRV_LOG(DEBUG, "counters are not supported");
#endif
#if !defined(HAVE_IBV_FLOW_DV_SUPPORT) || !defined(HAVE_MLX5DV_DR)
- if (config.dv_flow_en) {
+ if (config->dv_flow_en) {
DRV_LOG(WARNING, "DV flow is not supported");
- config.dv_flow_en = 0;
+ config->dv_flow_en = 0;
}
#endif
- config.ind_table_max_size =
+ config->ind_table_max_size =
sh->device_attr.max_rwq_indirection_table_size;
/*
* Remove this check once DPDK supports larger/variable
* indirection tables.
*/
- if (config.ind_table_max_size > (unsigned int)ETH_RSS_RETA_SIZE_512)
- config.ind_table_max_size = ETH_RSS_RETA_SIZE_512;
+ if (config->ind_table_max_size > (unsigned int)ETH_RSS_RETA_SIZE_512)
+ config->ind_table_max_size = ETH_RSS_RETA_SIZE_512;
DRV_LOG(DEBUG, "maximum Rx indirection table size is %u",
- config.ind_table_max_size);
- config.hw_vlan_strip = !!(sh->device_attr.raw_packet_caps &
+ config->ind_table_max_size);
+ config->hw_vlan_strip = !!(sh->device_attr.raw_packet_caps &
IBV_RAW_PACKET_CAP_CVLAN_STRIPPING);
DRV_LOG(DEBUG, "VLAN stripping is %ssupported",
- (config.hw_vlan_strip ? "" : "not "));
- config.hw_fcs_strip = !!(sh->device_attr.raw_packet_caps &
+ (config->hw_vlan_strip ? "" : "not "));
+ config->hw_fcs_strip = !!(sh->device_attr.raw_packet_caps &
IBV_RAW_PACKET_CAP_SCATTER_FCS);
#if defined(HAVE_IBV_WQ_FLAG_RX_END_PADDING)
hw_padding = !!sh->device_attr.rx_pad_end_addr_align;
hw_padding = !!(sh->device_attr.device_cap_flags_ex &
IBV_DEVICE_PCI_WRITE_END_PADDING);
#endif
- if (config.hw_padding && !hw_padding) {
+ if (config->hw_padding && !hw_padding) {
DRV_LOG(DEBUG, "Rx end alignment padding isn't supported");
- config.hw_padding = 0;
- } else if (config.hw_padding) {
+ config->hw_padding = 0;
+ } else if (config->hw_padding) {
DRV_LOG(DEBUG, "Rx end alignment padding is enabled");
}
- config.tso = (sh->device_attr.max_tso > 0 &&
+ config->tso = (sh->device_attr.max_tso > 0 &&
(sh->device_attr.tso_supported_qpts &
(1 << IBV_QPT_RAW_PACKET)));
- if (config.tso)
- config.tso_max_payload_sz = sh->device_attr.max_tso;
+ if (config->tso)
+ config->tso_max_payload_sz = sh->device_attr.max_tso;
/*
* MPW is disabled by default, while the Enhanced MPW is enabled
* by default.
*/
- if (config.mps == MLX5_ARG_UNSET)
- config.mps = (mps == MLX5_MPW_ENHANCED) ? MLX5_MPW_ENHANCED :
+ if (config->mps == MLX5_ARG_UNSET)
+ config->mps = (mps == MLX5_MPW_ENHANCED) ? MLX5_MPW_ENHANCED :
MLX5_MPW_DISABLED;
else
- config.mps = config.mps ? mps : MLX5_MPW_DISABLED;
+ config->mps = config->mps ? mps : MLX5_MPW_DISABLED;
DRV_LOG(INFO, "%sMPS is %s",
- config.mps == MLX5_MPW_ENHANCED ? "enhanced " :
- config.mps == MLX5_MPW ? "legacy " : "",
- config.mps != MLX5_MPW_DISABLED ? "enabled" : "disabled");
- if (config.cqe_comp && !cqe_comp) {
- DRV_LOG(WARNING, "Rx CQE compression isn't supported");
- config.cqe_comp = 0;
- }
- if (config.cqe_pad && !cqe_pad) {
- DRV_LOG(WARNING, "Rx CQE padding isn't supported");
- config.cqe_pad = 0;
- } else if (config.cqe_pad) {
- DRV_LOG(INFO, "Rx CQE padding is enabled");
- }
- if (config.devx) {
- priv->counter_fallback = 0;
- err = mlx5_devx_cmd_query_hca_attr(sh->ctx, &config.hca_attr);
+ config->mps == MLX5_MPW_ENHANCED ? "enhanced " :
+ config->mps == MLX5_MPW ? "legacy " : "",
+ config->mps != MLX5_MPW_DISABLED ? "enabled" : "disabled");
+ if (config->devx) {
+ err = mlx5_devx_cmd_query_hca_attr(sh->ctx, &config->hca_attr);
if (err) {
err = -err;
goto error;
}
- if (!config.hca_attr.flow_counters_dump)
- priv->counter_fallback = 1;
-#ifndef HAVE_IBV_DEVX_ASYNC
- priv->counter_fallback = 1;
-#endif
- if (priv->counter_fallback)
- DRV_LOG(INFO, "Use fall-back DV counter management");
+ /* Check relax ordering support. */
+ if (!haswell_broadwell_cpu) {
+ sh->cmng.relaxed_ordering_write =
+ config->hca_attr.relaxed_ordering_write;
+ sh->cmng.relaxed_ordering_read =
+ config->hca_attr.relaxed_ordering_read;
+ } else {
+ sh->cmng.relaxed_ordering_read = 0;
+ sh->cmng.relaxed_ordering_write = 0;
+ }
+ sh->rq_ts_format = config->hca_attr.rq_ts_format;
+ sh->sq_ts_format = config->hca_attr.sq_ts_format;
+ sh->qp_ts_format = config->hca_attr.qp_ts_format;
/* Check for LRO support. */
- if (config.dest_tir && config.hca_attr.lro_cap &&
- config.dv_flow_en) {
+ if (config->dest_tir && config->hca_attr.lro_cap &&
+ config->dv_flow_en) {
/* TBD check tunnel lro caps. */
- config.lro.supported = config.hca_attr.lro_cap;
+ config->lro.supported = config->hca_attr.lro_cap;
DRV_LOG(DEBUG, "Device supports LRO");
/*
* If LRO timeout is not configured by application,
* use the minimal supported value.
*/
- if (!config.lro.timeout)
- config.lro.timeout =
- config.hca_attr.lro_timer_supported_periods[0];
+ if (!config->lro.timeout)
+ config->lro.timeout =
+ config->hca_attr.lro_timer_supported_periods[0];
DRV_LOG(DEBUG, "LRO session timeout set to %d usec",
- config.lro.timeout);
+ config->lro.timeout);
+ DRV_LOG(DEBUG, "LRO minimal size of TCP segment "
+ "required for coalescing is %d bytes",
+ config->hca_attr.lro_min_mss_size);
}
#if defined(HAVE_MLX5DV_DR) && defined(HAVE_MLX5_DR_CREATE_ACTION_FLOW_METER)
- if (config.hca_attr.qos.sup && config.hca_attr.qos.srtcm_sup &&
- config.dv_flow_en) {
+ if (config->hca_attr.qos.sup &&
+ config->hca_attr.qos.flow_meter_old &&
+ config->dv_flow_en) {
uint8_t reg_c_mask =
- config.hca_attr.qos.flow_meter_reg_c_ids;
+ config->hca_attr.qos.flow_meter_reg_c_ids;
/*
* Meter needs two REG_C's for color match and pre-sfx
* flow match. Here get the REG_C for color match.
DRV_LOG(WARNING, "No available register for"
" meter.");
} else {
- priv->mtr_color_reg = ffs(reg_c_mask) - 1 +
- REG_C_0;
+ /*
+ * The meter color register is used by the
+ * flow-hit feature as well.
+ * The flow-hit feature must use REG_C_3
+ * Prefer REG_C_3 if it is available.
+ */
+ if (reg_c_mask & (1 << (REG_C_3 - REG_C_0)))
+ priv->mtr_color_reg = REG_C_3;
+ else
+ priv->mtr_color_reg = ffs(reg_c_mask)
+ - 1 + REG_C_0;
priv->mtr_en = 1;
priv->mtr_reg_share =
- config.hca_attr.qos.flow_meter_reg_share;
+ config->hca_attr.qos.flow_meter;
DRV_LOG(DEBUG, "The REG_C meter uses is %d",
priv->mtr_color_reg);
}
}
+#endif
+#ifdef HAVE_MLX5_DR_CREATE_ACTION_ASO
+ if (config->hca_attr.flow_hit_aso &&
+ priv->mtr_color_reg == REG_C_3) {
+ sh->flow_hit_aso_en = 1;
+ err = mlx5_flow_aso_age_mng_init(sh);
+ if (err) {
+ err = -err;
+ goto error;
+ }
+ DRV_LOG(DEBUG, "Flow Hit ASO is supported.");
+ }
+#endif /* HAVE_MLX5_DR_CREATE_ACTION_ASO */
+#if defined(HAVE_MLX5DV_DR) && defined(HAVE_MLX5_DR_CREATE_ACTION_FLOW_SAMPLE)
+ if (config->hca_attr.log_max_ft_sampler_num > 0 &&
+ config->dv_flow_en) {
+ priv->sampler_en = 1;
+ DRV_LOG(DEBUG, "Sampler enabled!");
+ } else {
+ priv->sampler_en = 0;
+ if (!config->hca_attr.log_max_ft_sampler_num)
+ DRV_LOG(WARNING,
+ "No available register for sampler.");
+ else
+ DRV_LOG(DEBUG, "DV flow is not supported!");
+ }
#endif
}
- if (config.tx_pp) {
+ if (config->cqe_comp && RTE_CACHE_LINE_SIZE == 128 &&
+ !(dv_attr.flags & MLX5DV_CONTEXT_FLAGS_CQE_128B_COMP)) {
+ DRV_LOG(WARNING, "Rx CQE 128B compression is not supported");
+ config->cqe_comp = 0;
+ }
+ if (config->cqe_comp_fmt == MLX5_CQE_RESP_FORMAT_FTAG_STRIDX &&
+ (!config->devx || !config->hca_attr.mini_cqe_resp_flow_tag)) {
+ DRV_LOG(WARNING, "Flow Tag CQE compression"
+ " format isn't supported.");
+ config->cqe_comp = 0;
+ }
+ if (config->cqe_comp_fmt == MLX5_CQE_RESP_FORMAT_L34H_STRIDX &&
+ (!config->devx || !config->hca_attr.mini_cqe_resp_l3_l4_tag)) {
+ DRV_LOG(WARNING, "L3/L4 Header CQE compression"
+ " format isn't supported.");
+ config->cqe_comp = 0;
+ }
+ DRV_LOG(DEBUG, "Rx CQE compression is %ssupported",
+ config->cqe_comp ? "" : "not ");
+ if (config->tx_pp) {
DRV_LOG(DEBUG, "Timestamp counter frequency %u kHz",
- config.hca_attr.dev_freq_khz);
+ config->hca_attr.dev_freq_khz);
DRV_LOG(DEBUG, "Packet pacing is %ssupported",
- config.hca_attr.qos.packet_pacing ? "" : "not ");
+ config->hca_attr.qos.packet_pacing ? "" : "not ");
DRV_LOG(DEBUG, "Cross channel ops are %ssupported",
- config.hca_attr.cross_channel ? "" : "not ");
+ config->hca_attr.cross_channel ? "" : "not ");
DRV_LOG(DEBUG, "WQE index ignore is %ssupported",
- config.hca_attr.wqe_index_ignore ? "" : "not ");
+ config->hca_attr.wqe_index_ignore ? "" : "not ");
DRV_LOG(DEBUG, "Non-wire SQ feature is %ssupported",
- config.hca_attr.non_wire_sq ? "" : "not ");
+ config->hca_attr.non_wire_sq ? "" : "not ");
DRV_LOG(DEBUG, "Static WQE SQ feature is %ssupported (%d)",
- config.hca_attr.log_max_static_sq_wq ? "" : "not ",
- config.hca_attr.log_max_static_sq_wq);
+ config->hca_attr.log_max_static_sq_wq ? "" : "not ",
+ config->hca_attr.log_max_static_sq_wq);
DRV_LOG(DEBUG, "WQE rate PP mode is %ssupported",
- config.hca_attr.qos.wqe_rate_pp ? "" : "not ");
- if (!config.devx) {
+ config->hca_attr.qos.wqe_rate_pp ? "" : "not ");
+ if (!config->devx) {
DRV_LOG(ERR, "DevX is required for packet pacing");
err = ENODEV;
goto error;
}
- if (!config.hca_attr.qos.packet_pacing) {
+ if (!config->hca_attr.qos.packet_pacing) {
DRV_LOG(ERR, "Packet pacing is not supported");
err = ENODEV;
goto error;
}
- if (!config.hca_attr.cross_channel) {
+ if (!config->hca_attr.cross_channel) {
DRV_LOG(ERR, "Cross channel operations are"
" required for packet pacing");
err = ENODEV;
goto error;
}
- if (!config.hca_attr.wqe_index_ignore) {
+ if (!config->hca_attr.wqe_index_ignore) {
DRV_LOG(ERR, "WQE index ignore feature is"
" required for packet pacing");
err = ENODEV;
goto error;
}
- if (!config.hca_attr.non_wire_sq) {
+ if (!config->hca_attr.non_wire_sq) {
DRV_LOG(ERR, "Non-wire SQ feature is"
" required for packet pacing");
err = ENODEV;
goto error;
}
- if (!config.hca_attr.log_max_static_sq_wq) {
+ if (!config->hca_attr.log_max_static_sq_wq) {
DRV_LOG(ERR, "Static WQE SQ feature is"
" required for packet pacing");
err = ENODEV;
goto error;
}
- if (!config.hca_attr.qos.wqe_rate_pp) {
+ if (!config->hca_attr.qos.wqe_rate_pp) {
DRV_LOG(ERR, "WQE rate mode is required"
" for packet pacing");
err = ENODEV;
goto error;
#endif
}
- if (config.devx) {
+ if (config->devx) {
uint32_t reg[MLX5_ST_SZ_DW(register_mtutc)];
- err = mlx5_devx_cmd_register_read
- (sh->ctx, MLX5_REGISTER_ID_MTUTC, 0,
- reg, MLX5_ST_SZ_DW(register_mtutc));
+ err = config->hca_attr.access_register_user ?
+ mlx5_devx_cmd_register_read
+ (sh->ctx, MLX5_REGISTER_ID_MTUTC, 0,
+ reg, MLX5_ST_SZ_DW(register_mtutc)) : ENOTSUP;
if (!err) {
uint32_t ts_mode;
ts_mode = MLX5_GET(register_mtutc, reg,
time_stamp_mode);
if (ts_mode == MLX5_MTUTC_TIMESTAMP_MODE_REAL_TIME)
- config.rt_timestamp = 1;
+ config->rt_timestamp = 1;
} else {
/* Kernel does not support register reading. */
- if (config.hca_attr.dev_freq_khz ==
+ if (config->hca_attr.dev_freq_khz ==
(NS_PER_S / MS_PER_S))
- config.rt_timestamp = 1;
+ config->rt_timestamp = 1;
}
}
/*
* scatter FCS, and decapsulation is needed, clear the hw_fcs_strip
* bit. Then DEV_RX_OFFLOAD_KEEP_CRC bit will not be set anymore.
*/
- if (config.hca_attr.scatter_fcs_w_decap_disable && config.decap_en)
- config.hw_fcs_strip = 0;
+ if (config->hca_attr.scatter_fcs_w_decap_disable && config->decap_en)
+ config->hw_fcs_strip = 0;
DRV_LOG(DEBUG, "FCS stripping configuration is %ssupported",
- (config.hw_fcs_strip ? "" : "not "));
- if (config.mprq.enabled && mprq) {
- if (config.mprq.stride_num_n &&
- (config.mprq.stride_num_n > mprq_max_stride_num_n ||
- config.mprq.stride_num_n < mprq_min_stride_num_n)) {
- config.mprq.stride_num_n =
+ (config->hw_fcs_strip ? "" : "not "));
+ if (config->mprq.enabled && mprq) {
+ if (config->mprq.stride_num_n &&
+ (config->mprq.stride_num_n > mprq_max_stride_num_n ||
+ config->mprq.stride_num_n < mprq_min_stride_num_n)) {
+ config->mprq.stride_num_n =
RTE_MIN(RTE_MAX(MLX5_MPRQ_STRIDE_NUM_N,
mprq_min_stride_num_n),
mprq_max_stride_num_n);
"the number of strides"
" for Multi-Packet RQ is out of range,"
" setting default value (%u)",
- 1 << config.mprq.stride_num_n);
+ 1 << config->mprq.stride_num_n);
}
- if (config.mprq.stride_size_n &&
- (config.mprq.stride_size_n > mprq_max_stride_size_n ||
- config.mprq.stride_size_n < mprq_min_stride_size_n)) {
- config.mprq.stride_size_n =
+ if (config->mprq.stride_size_n &&
+ (config->mprq.stride_size_n > mprq_max_stride_size_n ||
+ config->mprq.stride_size_n < mprq_min_stride_size_n)) {
+ config->mprq.stride_size_n =
RTE_MIN(RTE_MAX(MLX5_MPRQ_STRIDE_SIZE_N,
mprq_min_stride_size_n),
mprq_max_stride_size_n);
"the size of a stride"
" for Multi-Packet RQ is out of range,"
" setting default value (%u)",
- 1 << config.mprq.stride_size_n);
+ 1 << config->mprq.stride_size_n);
}
- config.mprq.min_stride_size_n = mprq_min_stride_size_n;
- config.mprq.max_stride_size_n = mprq_max_stride_size_n;
- } else if (config.mprq.enabled && !mprq) {
+ config->mprq.min_stride_size_n = mprq_min_stride_size_n;
+ config->mprq.max_stride_size_n = mprq_max_stride_size_n;
+ } else if (config->mprq.enabled && !mprq) {
DRV_LOG(WARNING, "Multi-Packet RQ isn't supported");
- config.mprq.enabled = 0;
+ config->mprq.enabled = 0;
}
- if (config.max_dump_files_num == 0)
- config.max_dump_files_num = 128;
+ if (config->max_dump_files_num == 0)
+ config->max_dump_files_num = 128;
eth_dev = rte_eth_dev_allocate(name);
if (eth_dev == NULL) {
DRV_LOG(ERR, "can not allocate rte ethdev");
err = ENOMEM;
goto error;
}
- /* Flag to call rte_eth_dev_release_port() in rte_eth_dev_close(). */
- eth_dev->data->dev_flags |= RTE_ETH_DEV_CLOSE_REMOVE;
if (priv->representor) {
eth_dev->data->dev_flags |= RTE_ETH_DEV_REPRESENTOR;
eth_dev->data->representor_id = priv->representor_id;
}
+ priv->mp_id.port_id = eth_dev->data->port_id;
+ strlcpy(priv->mp_id.name, MLX5_MP_NAME, RTE_MP_MAX_NAME_LEN);
/*
* Store associated network device interface index. This index
* is permanent throughout the lifetime of device. So, we may store
*/
MLX5_ASSERT(spawn->ifindex);
priv->if_index = spawn->ifindex;
+ if (priv->pf_bond >= 0 && priv->master) {
+ /* Get bond interface info */
+ err = mlx5_sysfs_bond_info(priv->if_index,
+ &priv->bond_ifindex,
+ priv->bond_name);
+ if (err)
+ DRV_LOG(ERR, "unable to get bond info: %s",
+ strerror(rte_errno));
+ else
+ DRV_LOG(INFO, "PF device %u, bond device %u(%s)",
+ priv->if_index, priv->bond_ifindex,
+ priv->bond_name);
+ }
eth_dev->data->dev_private = priv;
priv->dev_data = eth_dev->data;
eth_dev->data->mac_addrs = priv->mac;
- eth_dev->device = dpdk_dev;
+ if (spawn->pf_bond < 0) {
+ eth_dev->device = dpdk_dev;
+ } else {
+ /* Use primary bond PCI as device. */
+ if (sh->bond_dev == UINT16_MAX) {
+ sh->bond_dev = eth_dev->data->port_id;
+ eth_dev->device = dpdk_dev;
+ } else {
+ eth_dev->device = rte_eth_devices[sh->bond_dev].device;
+ }
+ }
+ eth_dev->data->dev_flags |= RTE_ETH_DEV_AUTOFILL_QUEUE_XSTATS;
/* Configure the first MAC address by default. */
if (mlx5_get_mac(eth_dev, &mac.addr_bytes)) {
DRV_LOG(ERR,
mac.addr_bytes[4], mac.addr_bytes[5]);
#ifdef RTE_LIBRTE_MLX5_DEBUG
{
- char ifname[IF_NAMESIZE];
+ char ifname[MLX5_NAMESIZE];
if (mlx5_get_ifname(eth_dev, &ifname) == 0)
DRV_LOG(DEBUG, "port %u ifname is \"%s\"",
/* Initialize burst functions to prevent crashes before link-up. */
eth_dev->rx_pkt_burst = removed_rx_burst;
eth_dev->tx_pkt_burst = removed_tx_burst;
- eth_dev->dev_ops = &mlx5_os_dev_ops;
+ eth_dev->dev_ops = &mlx5_dev_ops;
+ eth_dev->rx_descriptor_status = mlx5_rx_descriptor_status;
+ eth_dev->tx_descriptor_status = mlx5_tx_descriptor_status;
+ eth_dev->rx_queue_count = mlx5_rx_queue_count;
/* Register MAC address. */
claim_zero(mlx5_mac_addr_add(eth_dev, &mac, 0, 0));
- if (config.vf && config.vf_nl_en)
+ if (config->vf && config->vf_nl_en)
mlx5_nl_mac_addr_sync(priv->nl_socket_route,
mlx5_ifindex(eth_dev),
eth_dev->data->mac_addrs,
MLX5_MAX_MAC_ADDRESSES);
priv->flows = 0;
priv->ctrl_flows = 0;
+ rte_spinlock_init(&priv->flow_list_lock);
TAILQ_INIT(&priv->flow_meters);
TAILQ_INIT(&priv->flow_meter_profiles);
/* Hint libmlx5 to use PMD allocator for data plane resources */
(void *)((uintptr_t)&(struct mlx5dv_ctx_allocators){
.alloc = &mlx5_alloc_verbs_buf,
.free = &mlx5_free_verbs_buf,
- .data = priv,
+ .data = sh,
}));
/* Bring Ethernet device up. */
DRV_LOG(DEBUG, "port %u forcing Ethernet interface up",
*/
mlx5_link_update(eth_dev, 0);
#ifdef HAVE_MLX5DV_DR_ESWITCH
- if (!(config.hca_attr.eswitch_manager && config.dv_flow_en &&
+ if (!(config->hca_attr.eswitch_manager && config->dv_flow_en &&
(switch_info->representor || switch_info->master)))
- config.dv_esw_en = 0;
+ config->dv_esw_en = 0;
#else
- config.dv_esw_en = 0;
+ config->dv_esw_en = 0;
#endif
/* Detect minimal data bytes to inline. */
- mlx5_set_min_inline(spawn, &config);
+ mlx5_set_min_inline(spawn, config);
/* Store device configuration on private structure. */
- priv->config = config;
+ priv->config = *config;
/* Create context for virtual machine VLAN workaround. */
priv->vmwa_context = mlx5_vlan_vmwa_init(eth_dev, spawn->ifindex);
- if (config.dv_flow_en) {
+ if (config->dv_flow_en) {
err = mlx5_alloc_shared_dr(priv);
if (err)
goto error;
- /*
- * RSS id is shared with meter flow id. Meter flow id can only
- * use the 24 MSB of the register.
- */
- priv->qrss_id_pool = mlx5_flow_id_pool_alloc(UINT32_MAX >>
- MLX5_MTR_COLOR_BITS);
- if (!priv->qrss_id_pool) {
- DRV_LOG(ERR, "can't create flow id pool");
- err = ENOMEM;
- goto error;
- }
}
+ if (config->devx && config->dv_flow_en && config->dest_tir) {
+ priv->obj_ops = devx_obj_ops;
+ priv->obj_ops.drop_action_create =
+ ibv_obj_ops.drop_action_create;
+ priv->obj_ops.drop_action_destroy =
+ ibv_obj_ops.drop_action_destroy;
+#ifndef HAVE_MLX5DV_DEVX_UAR_OFFSET
+ priv->obj_ops.txq_obj_modify = ibv_obj_ops.txq_obj_modify;
+#else
+ if (config->dv_esw_en)
+ priv->obj_ops.txq_obj_modify =
+ ibv_obj_ops.txq_obj_modify;
+#endif
+ /* Use specific wrappers for Tx object. */
+ priv->obj_ops.txq_obj_new = mlx5_os_txq_obj_new;
+ priv->obj_ops.txq_obj_release = mlx5_os_txq_obj_release;
+ mlx5_queue_counter_id_prepare(eth_dev);
+
+ } else {
+ priv->obj_ops = ibv_obj_ops;
+ }
+ priv->drop_queue.hrxq = mlx5_drop_action_create(eth_dev);
+ if (!priv->drop_queue.hrxq)
+ goto error;
/* Supported Verbs flow priority number detection. */
err = mlx5_flow_discover_priorities(eth_dev);
if (err < 0) {
err = ENOTSUP;
goto error;
}
- /*
- * Allocate the buffer for flow creating, just once.
- * The allocation must be done before any flow creating.
- */
- mlx5_flow_alloc_intermediate(eth_dev);
+ mlx5_cache_list_init(&priv->hrxqs, "hrxq", 0, eth_dev,
+ mlx5_hrxq_create_cb,
+ mlx5_hrxq_match_cb,
+ mlx5_hrxq_remove_cb);
/* Query availability of metadata reg_c's. */
err = mlx5_flow_discover_mreg_c(eth_dev);
if (err < 0) {
mlx5_flow_ext_mreg_supported(eth_dev) &&
priv->sh->dv_regc0_mask) {
priv->mreg_cp_tbl = mlx5_hlist_create(MLX5_FLOW_MREG_HNAME,
- MLX5_FLOW_MREG_HTABLE_SZ);
+ MLX5_FLOW_MREG_HTABLE_SZ,
+ 0, 0,
+ flow_dv_mreg_create_cb,
+ flow_dv_mreg_match_cb,
+ flow_dv_mreg_remove_cb);
if (!priv->mreg_cp_tbl) {
err = ENOMEM;
goto error;
}
+ priv->mreg_cp_tbl->ctx = eth_dev;
}
+ rte_spinlock_init(&priv->shared_act_sl);
+ mlx5_flow_counter_mode_config(eth_dev);
+ if (priv->config.dv_flow_en)
+ eth_dev->data->dev_flags |= RTE_ETH_DEV_FLOW_OPS_THREAD_SAFE;
return eth_dev;
error:
if (priv) {
if (priv->mreg_cp_tbl)
- mlx5_hlist_destroy(priv->mreg_cp_tbl, NULL, NULL);
+ mlx5_hlist_destroy(priv->mreg_cp_tbl);
if (priv->sh)
mlx5_os_free_shared_dr(priv);
if (priv->nl_socket_route >= 0)
close(priv->nl_socket_rdma);
if (priv->vmwa_context)
mlx5_vlan_vmwa_exit(priv->vmwa_context);
- if (priv->qrss_id_pool)
- mlx5_flow_id_pool_release(priv->qrss_id_pool);
+ if (eth_dev && priv->drop_queue.hrxq)
+ mlx5_drop_action_destroy(eth_dev);
if (own_domain_id)
claim_zero(rte_eth_switch_domain_free(priv->domain_id));
+ mlx5_cache_list_destroy(&priv->hrxqs);
mlx5_free(priv);
if (eth_dev != NULL)
eth_dev->data->dev_private = NULL;
int bd = -1;
struct mlx5_dev_spawn_data *list = NULL;
struct mlx5_dev_config dev_config;
+ unsigned int dev_config_vf;
int ret;
- if (mlx5_class_get(pci_dev->device.devargs) != MLX5_CLASS_NET) {
- DRV_LOG(DEBUG, "Skip probing - should be probed by other mlx5"
- " driver.");
- return 1;
- }
if (rte_eal_process_type() == RTE_PROC_PRIMARY)
mlx5_pmd_socket_init();
ret = mlx5_init_once();
strerror(rte_errno));
return -rte_errno;
}
- MLX5_ASSERT(pci_drv == &mlx5_driver);
errno = 0;
ibv_list = mlx5_glue->get_device_list(&ret);
if (!ibv_list) {
(list[ns].ifindex,
&list[ns].info);
}
+#ifdef HAVE_MLX5DV_DR_DEVX_PORT
if (!ret && bd >= 0) {
switch (list[ns].info.name_type) {
case MLX5_PHYS_PORT_NAME_TYPE_UPLINK:
}
continue;
}
+#endif
if (!ret && (list[ns].info.representor ^
list[ns].info.master))
ns++;
* (i.e. master first, then representors from lowest to highest ID).
*/
qsort(list, ns, sizeof(*list), mlx5_dev_spawn_data_cmp);
- /* Default configuration. */
- dev_config = (struct mlx5_dev_config){
- .hw_padding = 0,
- .mps = MLX5_ARG_UNSET,
- .dbnc = MLX5_ARG_UNSET,
- .rx_vec_en = 1,
- .txq_inline_max = MLX5_ARG_UNSET,
- .txq_inline_min = MLX5_ARG_UNSET,
- .txq_inline_mpw = MLX5_ARG_UNSET,
- .txqs_inline = MLX5_ARG_UNSET,
- .vf_nl_en = 1,
- .mr_ext_memseg_en = 1,
- .mprq = {
- .enabled = 0, /* Disabled by default. */
- .stride_num_n = 0,
- .stride_size_n = 0,
- .max_memcpy_len = MLX5_MPRQ_MEMCPY_DEFAULT_LEN,
- .min_rxqs_num = MLX5_MPRQ_MIN_RXQS,
- },
- .dv_esw_en = 1,
- .dv_flow_en = 1,
- .decap_en = 1,
- .log_hp_size = MLX5_ARG_UNSET,
- };
/* Device specific configuration. */
switch (pci_dev->id.device_id) {
case PCI_DEVICE_ID_MELLANOX_CONNECTX4VF:
case PCI_DEVICE_ID_MELLANOX_CONNECTX5EXVF:
case PCI_DEVICE_ID_MELLANOX_CONNECTX5BFVF:
case PCI_DEVICE_ID_MELLANOX_CONNECTX6VF:
- case PCI_DEVICE_ID_MELLANOX_CONNECTX6DXVF:
- dev_config.vf = 1;
+ case PCI_DEVICE_ID_MELLANOX_CONNECTXVF:
+ dev_config_vf = 1;
break;
default:
+ dev_config_vf = 0;
break;
}
for (i = 0; i != ns; ++i) {
uint32_t restore;
+ /* Default configuration. */
+ memset(&dev_config, 0, sizeof(struct mlx5_dev_config));
+ dev_config.vf = dev_config_vf;
+ dev_config.mps = MLX5_ARG_UNSET;
+ dev_config.dbnc = MLX5_ARG_UNSET;
+ dev_config.rx_vec_en = 1;
+ dev_config.txq_inline_max = MLX5_ARG_UNSET;
+ dev_config.txq_inline_min = MLX5_ARG_UNSET;
+ dev_config.txq_inline_mpw = MLX5_ARG_UNSET;
+ dev_config.txqs_inline = MLX5_ARG_UNSET;
+ dev_config.vf_nl_en = 1;
+ dev_config.mr_ext_memseg_en = 1;
+ dev_config.mprq.max_memcpy_len = MLX5_MPRQ_MEMCPY_DEFAULT_LEN;
+ dev_config.mprq.min_rxqs_num = MLX5_MPRQ_MIN_RXQS;
+ dev_config.dv_esw_en = 1;
+ dev_config.dv_flow_en = 1;
+ dev_config.decap_en = 1;
+ dev_config.log_hp_size = MLX5_ARG_UNSET;
list[i].eth_dev = mlx5_dev_spawn(&pci_dev->device,
&list[i],
- dev_config);
+ &dev_config);
if (!list[i].eth_dev) {
if (rte_errno != EBUSY && rte_errno != EEXIST)
break;
DRV_LOG(DEBUG, "DevX is NOT supported");
err = 0;
}
+ if (!err && sh->ctx) {
+ /* Hint libmlx5 to use PMD allocator for data plane resources */
+ mlx5_glue->dv_set_context_attr(sh->ctx,
+ MLX5DV_CTX_ATTR_BUF_ALLOCATORS,
+ (void *)((uintptr_t)&(struct mlx5dv_ctx_allocators){
+ .alloc = &mlx5_alloc_verbs_buf,
+ .free = &mlx5_free_verbs_buf,
+ .data = sh,
+ }));
+ }
return err;
}
int fd;
if (priv->sh) {
+ if (priv->q_counters != NULL &&
+ strcmp(ctr_name, "out_of_buffer") == 0)
+ return mlx5_devx_cmd_queue_counter_query(priv->sh->ctx,
+ 0, (uint32_t *)stat);
MKSTR(path, "%s/ports/%d/hw_counters/%s",
- priv->sh->ibdev_path,
- priv->dev_port,
- ctr_name);
+ priv->sh->ibdev_path,
+ priv->dev_port,
+ ctr_name);
fd = open(path, O_RDONLY);
+ /*
+ * in switchdev the file location is not per port
+ * but rather in <ibdev_path>/hw_counters/<file_name>.
+ */
+ if (fd == -1) {
+ MKSTR(path1, "%s/hw_counters/%s",
+ priv->sh->ibdev_path,
+ ctr_name);
+ fd = open(path1, O_RDONLY);
+ }
if (fd != -1) {
char buf[21] = {'\0'};
ssize_t n = read(fd, buf, sizeof(buf));
mlx5_os_set_reg_mr_cb(mlx5_reg_mr_t *reg_mr_cb,
mlx5_dereg_mr_t *dereg_mr_cb)
{
- *reg_mr_cb = mlx5_verbs_ops.reg_mr;
- *dereg_mr_cb = mlx5_verbs_ops.dereg_mr;
+ *reg_mr_cb = mlx5_mr_verbs_ops.reg_mr;
+ *dereg_mr_cb = mlx5_mr_verbs_ops.dereg_mr;
}
/**
mlx5_ifindex(dev), !!enable);
}
-const struct eth_dev_ops mlx5_os_dev_ops = {
- .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,
- .promiscuous_enable = mlx5_promiscuous_enable,
- .promiscuous_disable = mlx5_promiscuous_disable,
- .allmulticast_enable = mlx5_allmulticast_enable,
- .allmulticast_disable = mlx5_allmulticast_disable,
- .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,
- .fw_version_get = mlx5_fw_version_get,
- .dev_infos_get = mlx5_dev_infos_get,
- .read_clock = mlx5_txpp_read_clock,
- .dev_supported_ptypes_get = mlx5_dev_supported_ptypes_get,
- .vlan_filter_set = mlx5_vlan_filter_set,
- .rx_queue_setup = mlx5_rx_queue_setup,
- .rx_hairpin_queue_setup = mlx5_rx_hairpin_queue_setup,
- .tx_queue_setup = mlx5_tx_queue_setup,
- .tx_hairpin_queue_setup = mlx5_tx_hairpin_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,
- .set_mc_addr_list = mlx5_set_mc_addr_list,
- .mtu_set = mlx5_dev_set_mtu,
- .vlan_strip_queue_set = mlx5_vlan_strip_queue_set,
- .vlan_offload_set = mlx5_vlan_offload_set,
- .reta_update = mlx5_dev_rss_reta_update,
- .reta_query = mlx5_dev_rss_reta_query,
- .rss_hash_update = mlx5_rss_hash_update,
- .rss_hash_conf_get = mlx5_rss_hash_conf_get,
- .filter_ctrl = mlx5_dev_filter_ctrl,
- .rx_descriptor_status = mlx5_rx_descriptor_status,
- .tx_descriptor_status = mlx5_tx_descriptor_status,
- .rxq_info_get = mlx5_rxq_info_get,
- .txq_info_get = mlx5_txq_info_get,
- .rx_burst_mode_get = mlx5_rx_burst_mode_get,
- .tx_burst_mode_get = mlx5_tx_burst_mode_get,
- .rx_queue_count = mlx5_rx_queue_count,
- .rx_queue_intr_enable = mlx5_rx_intr_enable,
- .rx_queue_intr_disable = mlx5_rx_intr_disable,
- .is_removed = mlx5_is_removed,
- .udp_tunnel_port_add = mlx5_udp_tunnel_port_add,
- .get_module_info = mlx5_get_module_info,
- .get_module_eeprom = mlx5_get_module_eeprom,
- .hairpin_cap_get = mlx5_hairpin_cap_get,
- .mtr_ops_get = mlx5_flow_meter_ops_get,
-};
-
-/* Available operations from secondary process. */
-const struct eth_dev_ops mlx5_os_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,
- .fw_version_get = mlx5_fw_version_get,
- .dev_infos_get = mlx5_dev_infos_get,
- .read_clock = mlx5_txpp_read_clock,
- .rx_descriptor_status = mlx5_rx_descriptor_status,
- .tx_descriptor_status = mlx5_tx_descriptor_status,
- .rxq_info_get = mlx5_rxq_info_get,
- .txq_info_get = mlx5_txq_info_get,
- .rx_burst_mode_get = mlx5_rx_burst_mode_get,
- .tx_burst_mode_get = mlx5_tx_burst_mode_get,
- .get_module_info = mlx5_get_module_info,
- .get_module_eeprom = mlx5_get_module_eeprom,
-};
-
-/* Available operations in flow isolated mode. */
-const struct eth_dev_ops mlx5_os_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,
- .promiscuous_enable = mlx5_promiscuous_enable,
- .promiscuous_disable = mlx5_promiscuous_disable,
- .allmulticast_enable = mlx5_allmulticast_enable,
- .allmulticast_disable = mlx5_allmulticast_disable,
- .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,
- .fw_version_get = mlx5_fw_version_get,
- .dev_infos_get = mlx5_dev_infos_get,
- .read_clock = mlx5_txpp_read_clock,
- .dev_supported_ptypes_get = mlx5_dev_supported_ptypes_get,
- .vlan_filter_set = mlx5_vlan_filter_set,
- .rx_queue_setup = mlx5_rx_queue_setup,
- .rx_hairpin_queue_setup = mlx5_rx_hairpin_queue_setup,
- .tx_queue_setup = mlx5_tx_queue_setup,
- .tx_hairpin_queue_setup = mlx5_tx_hairpin_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,
- .set_mc_addr_list = mlx5_set_mc_addr_list,
- .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,
- .rxq_info_get = mlx5_rxq_info_get,
- .txq_info_get = mlx5_txq_info_get,
- .rx_burst_mode_get = mlx5_rx_burst_mode_get,
- .tx_burst_mode_get = mlx5_tx_burst_mode_get,
- .rx_queue_intr_enable = mlx5_rx_intr_enable,
- .rx_queue_intr_disable = mlx5_rx_intr_disable,
- .is_removed = mlx5_is_removed,
- .get_module_info = mlx5_get_module_info,
- .get_module_eeprom = mlx5_get_module_eeprom,
- .hairpin_cap_get = mlx5_hairpin_cap_get,
- .mtr_ops_get = mlx5_flow_meter_ops_get,
-};
+/**
+ * Flush device MAC addresses
+ *
+ * @param dev
+ * Pointer to Ethernet device structure.
+ *
+ */
+void
+mlx5_os_mac_addr_flush(struct rte_eth_dev *dev)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+
+ mlx5_nl_mac_addr_flush(priv->nl_socket_route, mlx5_ifindex(dev),
+ dev->data->mac_addrs,
+ MLX5_MAX_MAC_ADDRESSES, priv->mac_own);
+}