#include <errno.h>
#include <net/if.h>
#include <sys/mman.h>
-#include <linux/netlink.h>
#include <linux/rtnetlink.h>
/* Verbs header. */
#include <rte_rwlock.h>
#include <rte_spinlock.h>
#include <rte_string_fns.h>
+#include <rte_alarm.h>
#include "mlx5.h"
#include "mlx5_utils.h"
#include "mlx5_defs.h"
#include "mlx5_glue.h"
#include "mlx5_mr.h"
+#include "mlx5_flow.h"
/* Device parameter to enable RX completion queue compression. */
#define MLX5_RXQ_CQE_COMP_EN "rxq_cqe_comp_en"
+/* Device parameter to enable RX completion entry padding to 128B. */
+#define MLX5_RXQ_CQE_PAD_EN "rxq_cqe_pad_en"
+
+/* Device parameter to enable padding Rx packet to cacheline size. */
+#define MLX5_RXQ_PKT_PAD_EN "rxq_pkt_pad_en"
+
/* Device parameter to enable Multi-Packet Rx queue. */
#define MLX5_RX_MPRQ_EN "mprq_en"
/* Device parameter to set the minimum number of Rx queues to enable MPRQ. */
#define MLX5_RXQS_MIN_MPRQ "rxqs_min_mprq"
-/* Device parameter to configure inline send. */
+/* Device parameter to configure inline send. Deprecated, ignored.*/
#define MLX5_TXQ_INLINE "txq_inline"
+/* Device parameter to limit packet size to inline with ordinary SEND. */
+#define MLX5_TXQ_INLINE_MAX "txq_inline_max"
+
+/* Device parameter to configure minimal data size to inline. */
+#define MLX5_TXQ_INLINE_MIN "txq_inline_min"
+
+/* Device parameter to limit packet size to inline with Enhanced MPW. */
+#define MLX5_TXQ_INLINE_MPW "txq_inline_mpw"
+
/*
* Device parameter to configure the number of TX queues threshold for
* enabling inline send.
*/
#define MLX5_TXQS_MIN_INLINE "txqs_min_inline"
+/*
+ * Device parameter to configure the number of TX queues threshold for
+ * enabling vectorized Tx, deprecated, ignored (no vectorized Tx routines).
+ */
+#define MLX5_TXQS_MAX_VEC "txqs_max_vec"
+
/* Device parameter to enable multi-packet send WQEs. */
#define MLX5_TXQ_MPW_EN "txq_mpw_en"
-/* Device parameter to include 2 dsegs in the title WQEBB. */
+/*
+ * Device parameter to include 2 dsegs in the title WQEBB.
+ * Deprecated, ignored.
+ */
#define MLX5_TXQ_MPW_HDR_DSEG_EN "txq_mpw_hdr_dseg_en"
-/* Device parameter to limit the size of inlining packet. */
+/*
+ * Device parameter to limit the size of inlining packet.
+ * Deprecated, ignored.
+ */
#define MLX5_TXQ_MAX_INLINE_LEN "txq_max_inline_len"
-/* Device parameter to enable hardware Tx vector. */
+/*
+ * Device parameter to enable hardware Tx vector.
+ * Deprecated, ignored (no vectorized Tx routines anymore).
+ */
#define MLX5_TX_VEC_EN "tx_vec_en"
/* Device parameter to enable hardware Rx vector. */
/* Allow L3 VXLAN flow creation. */
#define MLX5_L3_VXLAN_EN "l3_vxlan_en"
+/* Activate DV E-Switch flow steering. */
+#define MLX5_DV_ESW_EN "dv_esw_en"
+
+/* Activate DV flow steering. */
+#define MLX5_DV_FLOW_EN "dv_flow_en"
+
/* Activate Netlink support in VF mode. */
#define MLX5_VF_NL_EN "vf_nl_en"
+/* Enable extending memsegs when creating a MR. */
+#define MLX5_MR_EXT_MEMSEG_EN "mr_ext_memseg_en"
+
/* Select port representors to instantiate. */
#define MLX5_REPRESENTOR "representor"
+/* Device parameter to configure the maximum number of dump files per queue. */
+#define MLX5_MAX_DUMP_FILES_NUM "max_dump_files_num"
+
+/* Configure timeout of LRO session (in microseconds). */
+#define MLX5_LRO_TIMEOUT_USEC "lro_timeout_usec"
+
#ifndef HAVE_IBV_MLX5_MOD_MPW
#define MLX5DV_CONTEXT_FLAGS_MPW_ALLOWED (1 << 2)
#define MLX5DV_CONTEXT_FLAGS_ENHANCED_MPW (1 << 3)
/* 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;
+
/** Driver-specific log messages type. */
int mlx5_logtype;
+/** Data associated with devices to spawn. */
+struct mlx5_dev_spawn_data {
+ uint32_t ifindex; /**< Network interface index. */
+ uint32_t max_port; /**< IB device maximal port index. */
+ uint32_t ibv_port; /**< IB device physical port index. */
+ struct mlx5_switch_info info; /**< Switch information. */
+ struct ibv_device *ibv_dev; /**< Associated IB device. */
+ struct rte_eth_dev *eth_dev; /**< Associated Ethernet device. */
+ struct rte_pci_device *pci_dev; /**< Backend PCI device. */
+};
+
+static LIST_HEAD(, mlx5_ibv_shared) mlx5_ibv_list = LIST_HEAD_INITIALIZER();
+static pthread_mutex_t mlx5_ibv_list_mutex = PTHREAD_MUTEX_INITIALIZER;
+
+/**
+ * Initialize the counters management structure.
+ *
+ * @param[in] sh
+ * Pointer to mlx5_ibv_shared object to free
+ */
+static void
+mlx5_flow_counters_mng_init(struct mlx5_ibv_shared *sh)
+{
+ uint8_t i;
+
+ TAILQ_INIT(&sh->cmng.flow_counters);
+ for (i = 0; i < RTE_DIM(sh->cmng.ccont); ++i)
+ TAILQ_INIT(&sh->cmng.ccont[i].pool_list);
+}
+
+/**
+ * Destroy all the resources allocated for a counter memory management.
+ *
+ * @param[in] mng
+ * Pointer to the memory management structure.
+ */
+static void
+mlx5_flow_destroy_counter_stat_mem_mng(struct mlx5_counter_stats_mem_mng *mng)
+{
+ uint8_t *mem = (uint8_t *)(uintptr_t)mng->raws[0].data;
+
+ LIST_REMOVE(mng, next);
+ claim_zero(mlx5_devx_cmd_destroy(mng->dm));
+ claim_zero(mlx5_glue->devx_umem_dereg(mng->umem));
+ rte_free(mem);
+}
+
+/**
+ * Close and release all the resources of the counters management.
+ *
+ * @param[in] sh
+ * Pointer to mlx5_ibv_shared object to free.
+ */
+static void
+mlx5_flow_counters_mng_close(struct mlx5_ibv_shared *sh)
+{
+ struct mlx5_counter_stats_mem_mng *mng;
+ uint8_t i;
+ int j;
+ int retries = 1024;
+
+ rte_errno = 0;
+ while (--retries) {
+ rte_eal_alarm_cancel(mlx5_flow_query_alarm, sh);
+ if (rte_errno != EINPROGRESS)
+ break;
+ rte_pause();
+ }
+ for (i = 0; i < RTE_DIM(sh->cmng.ccont); ++i) {
+ struct mlx5_flow_counter_pool *pool;
+ uint32_t batch = !!(i % 2);
+
+ if (!sh->cmng.ccont[i].pools)
+ continue;
+ pool = TAILQ_FIRST(&sh->cmng.ccont[i].pool_list);
+ while (pool) {
+ if (batch) {
+ if (pool->min_dcs)
+ claim_zero
+ (mlx5_devx_cmd_destroy(pool->min_dcs));
+ }
+ for (j = 0; j < MLX5_COUNTERS_PER_POOL; ++j) {
+ if (pool->counters_raw[j].action)
+ claim_zero
+ (mlx5_glue->destroy_flow_action
+ (pool->counters_raw[j].action));
+ if (!batch && pool->counters_raw[j].dcs)
+ claim_zero(mlx5_devx_cmd_destroy
+ (pool->counters_raw[j].dcs));
+ }
+ TAILQ_REMOVE(&sh->cmng.ccont[i].pool_list, pool,
+ next);
+ rte_free(pool);
+ pool = TAILQ_FIRST(&sh->cmng.ccont[i].pool_list);
+ }
+ rte_free(sh->cmng.ccont[i].pools);
+ }
+ mng = LIST_FIRST(&sh->cmng.mem_mngs);
+ while (mng) {
+ mlx5_flow_destroy_counter_stat_mem_mng(mng);
+ mng = LIST_FIRST(&sh->cmng.mem_mngs);
+ }
+ memset(&sh->cmng, 0, sizeof(sh->cmng));
+}
+
+/**
+ * Extract pdn of PD object using DV API.
+ *
+ * @param[in] pd
+ * Pointer to the verbs PD object.
+ * @param[out] pdn
+ * Pointer to the PD object number variable.
+ *
+ * @return
+ * 0 on success, error value otherwise.
+ */
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+static int
+mlx5_get_pdn(struct ibv_pd *pd __rte_unused, uint32_t *pdn __rte_unused)
+{
+ struct mlx5dv_obj obj;
+ struct mlx5dv_pd pd_info;
+ int ret = 0;
+
+ obj.pd.in = pd;
+ obj.pd.out = &pd_info;
+ ret = mlx5_glue->dv_init_obj(&obj, MLX5DV_OBJ_PD);
+ if (ret) {
+ DRV_LOG(DEBUG, "Fail to get PD object info");
+ return ret;
+ }
+ *pdn = pd_info.pdn;
+ return 0;
+}
+#endif /* HAVE_IBV_FLOW_DV_SUPPORT */
+
+/**
+ * Allocate shared IB device context. If there is multiport device the
+ * master and representors will share this context, if there is single
+ * port dedicated IB device, the context will be used by only given
+ * port due to unification.
+ *
+ * Routine first searches the context for the specified IB device name,
+ * if found the shared context assumed and reference counter is incremented.
+ * If no context found the new one is created and initialized with specified
+ * IB device context and parameters.
+ *
+ * @param[in] spawn
+ * Pointer to the IB device attributes (name, port, etc).
+ *
+ * @return
+ * Pointer to mlx5_ibv_shared object on success,
+ * otherwise NULL and rte_errno is set.
+ */
+static struct mlx5_ibv_shared *
+mlx5_alloc_shared_ibctx(const struct mlx5_dev_spawn_data *spawn)
+{
+ struct mlx5_ibv_shared *sh;
+ int err = 0;
+ uint32_t i;
+
+ assert(spawn);
+ /* Secondary process should not create the shared context. */
+ assert(rte_eal_process_type() == RTE_PROC_PRIMARY);
+ pthread_mutex_lock(&mlx5_ibv_list_mutex);
+ /* Search for IB context by device name. */
+ LIST_FOREACH(sh, &mlx5_ibv_list, next) {
+ if (!strcmp(sh->ibdev_name, spawn->ibv_dev->name)) {
+ sh->refcnt++;
+ goto exit;
+ }
+ }
+ /* No device found, we have to create new shared context. */
+ assert(spawn->max_port);
+ sh = rte_zmalloc("ethdev shared ib context",
+ sizeof(struct mlx5_ibv_shared) +
+ spawn->max_port *
+ sizeof(struct mlx5_ibv_shared_port),
+ RTE_CACHE_LINE_SIZE);
+ if (!sh) {
+ DRV_LOG(ERR, "shared context allocation failure");
+ rte_errno = ENOMEM;
+ goto exit;
+ }
+ /* Try to open IB device with DV first, then usual Verbs. */
+ errno = 0;
+ sh->ctx = mlx5_glue->dv_open_device(spawn->ibv_dev);
+ if (sh->ctx) {
+ sh->devx = 1;
+ DRV_LOG(DEBUG, "DevX is supported");
+ } else {
+ sh->ctx = mlx5_glue->open_device(spawn->ibv_dev);
+ if (!sh->ctx) {
+ err = errno ? errno : ENODEV;
+ goto error;
+ }
+ DRV_LOG(DEBUG, "DevX is NOT supported");
+ }
+ err = mlx5_glue->query_device_ex(sh->ctx, NULL, &sh->device_attr);
+ if (err) {
+ DRV_LOG(DEBUG, "ibv_query_device_ex() failed");
+ goto error;
+ }
+ sh->refcnt = 1;
+ sh->max_port = spawn->max_port;
+ strncpy(sh->ibdev_name, sh->ctx->device->name,
+ sizeof(sh->ibdev_name));
+ strncpy(sh->ibdev_path, sh->ctx->device->ibdev_path,
+ sizeof(sh->ibdev_path));
+ sh->pci_dev = spawn->pci_dev;
+ pthread_mutex_init(&sh->intr_mutex, NULL);
+ /*
+ * Setting port_id to max unallowed value means
+ * there is no interrupt subhandler installed for
+ * the given port index i.
+ */
+ for (i = 0; i < sh->max_port; i++)
+ sh->port[i].ih_port_id = RTE_MAX_ETHPORTS;
+ sh->pd = mlx5_glue->alloc_pd(sh->ctx);
+ if (sh->pd == NULL) {
+ DRV_LOG(ERR, "PD allocation failure");
+ err = ENOMEM;
+ goto error;
+ }
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+ err = mlx5_get_pdn(sh->pd, &sh->pdn);
+ if (err) {
+ DRV_LOG(ERR, "Fail to extract pdn from PD");
+ goto error;
+ }
+#endif /* HAVE_IBV_FLOW_DV_SUPPORT */
+ /*
+ * Once the device is added to the list of memory event
+ * callback, its global MR cache table cannot be expanded
+ * on the fly because of deadlock. If it overflows, lookup
+ * should be done by searching MR list linearly, which is slow.
+ *
+ * At this point the device is not added to the memory
+ * event list yet, context is just being created.
+ */
+ err = mlx5_mr_btree_init(&sh->mr.cache,
+ MLX5_MR_BTREE_CACHE_N * 2,
+ sh->pci_dev->device.numa_node);
+ if (err) {
+ err = rte_errno;
+ goto error;
+ }
+ mlx5_flow_counters_mng_init(sh);
+ /* Add device to memory callback list. */
+ rte_rwlock_write_lock(&mlx5_shared_data->mem_event_rwlock);
+ LIST_INSERT_HEAD(&mlx5_shared_data->mem_event_cb_list,
+ sh, mem_event_cb);
+ rte_rwlock_write_unlock(&mlx5_shared_data->mem_event_rwlock);
+ /* Add context to the global device list. */
+ LIST_INSERT_HEAD(&mlx5_ibv_list, sh, next);
+exit:
+ pthread_mutex_unlock(&mlx5_ibv_list_mutex);
+ return sh;
+error:
+ pthread_mutex_unlock(&mlx5_ibv_list_mutex);
+ assert(sh);
+ if (sh->pd)
+ claim_zero(mlx5_glue->dealloc_pd(sh->pd));
+ if (sh->ctx)
+ claim_zero(mlx5_glue->close_device(sh->ctx));
+ rte_free(sh);
+ assert(err > 0);
+ rte_errno = err;
+ return NULL;
+}
+
+/**
+ * Free shared IB device context. Decrement counter and if zero free
+ * all allocated resources and close handles.
+ *
+ * @param[in] sh
+ * Pointer to mlx5_ibv_shared object to free
+ */
+static void
+mlx5_free_shared_ibctx(struct mlx5_ibv_shared *sh)
+{
+ pthread_mutex_lock(&mlx5_ibv_list_mutex);
+#ifndef NDEBUG
+ /* Check the object presence in the list. */
+ struct mlx5_ibv_shared *lctx;
+
+ LIST_FOREACH(lctx, &mlx5_ibv_list, next)
+ if (lctx == sh)
+ break;
+ assert(lctx);
+ if (lctx != sh) {
+ DRV_LOG(ERR, "Freeing non-existing shared IB context");
+ goto exit;
+ }
+#endif
+ assert(sh);
+ assert(sh->refcnt);
+ /* Secondary process should not free the shared context. */
+ assert(rte_eal_process_type() == RTE_PROC_PRIMARY);
+ if (--sh->refcnt)
+ goto exit;
+ /* Release created Memory Regions. */
+ mlx5_mr_release(sh);
+ /* Remove from memory callback device list. */
+ rte_rwlock_write_lock(&mlx5_shared_data->mem_event_rwlock);
+ LIST_REMOVE(sh, mem_event_cb);
+ rte_rwlock_write_unlock(&mlx5_shared_data->mem_event_rwlock);
+ /* Remove context from the global device list. */
+ LIST_REMOVE(sh, next);
+ /*
+ * Ensure there is no async event handler installed.
+ * Only primary process handles async device events.
+ **/
+ mlx5_flow_counters_mng_close(sh);
+ assert(!sh->intr_cnt);
+ if (sh->intr_cnt)
+ mlx5_intr_callback_unregister
+ (&sh->intr_handle, mlx5_dev_interrupt_handler, sh);
+ pthread_mutex_destroy(&sh->intr_mutex);
+ if (sh->pd)
+ claim_zero(mlx5_glue->dealloc_pd(sh->pd));
+ if (sh->ctx)
+ claim_zero(mlx5_glue->close_device(sh->ctx));
+ rte_free(sh);
+exit:
+ pthread_mutex_unlock(&mlx5_ibv_list_mutex);
+}
+
/**
- * Prepare shared data between primary and secondary process.
+ * Initialize DR related data within private structure.
+ * Routine checks the reference counter and does actual
+ * resources creation/initialization only if counter is zero.
+ *
+ * @param[in] priv
+ * Pointer to the private device data structure.
+ *
+ * @return
+ * Zero on success, positive error code otherwise.
+ */
+static int
+mlx5_alloc_shared_dr(struct mlx5_priv *priv)
+{
+#ifdef HAVE_MLX5DV_DR
+ struct mlx5_ibv_shared *sh = priv->sh;
+ int err = 0;
+ void *domain;
+
+ assert(sh);
+ 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);
+ if (!domain) {
+ DRV_LOG(ERR, "ingress mlx5dv_dr_create_domain failed");
+ err = errno;
+ goto error;
+ }
+ sh->rx_domain = domain;
+ domain = mlx5_glue->dr_create_domain(sh->ctx,
+ MLX5DV_DR_DOMAIN_TYPE_NIC_TX);
+ if (!domain) {
+ DRV_LOG(ERR, "egress mlx5dv_dr_create_domain failed");
+ 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) {
+ domain = mlx5_glue->dr_create_domain
+ (sh->ctx, MLX5DV_DR_DOMAIN_TYPE_FDB);
+ if (!domain) {
+ DRV_LOG(ERR, "FDB mlx5dv_dr_create_domain failed");
+ err = errno;
+ goto error;
+ }
+ sh->fdb_domain = domain;
+ sh->esw_drop_action = mlx5_glue->dr_create_flow_action_drop();
+ }
+#endif
+ sh->dv_refcnt++;
+ priv->dr_shared = 1;
+ return 0;
+
+error:
+ /* Rollback the created objects. */
+ if (sh->rx_domain) {
+ mlx5_glue->dr_destroy_domain(sh->rx_domain);
+ sh->rx_domain = NULL;
+ }
+ if (sh->tx_domain) {
+ mlx5_glue->dr_destroy_domain(sh->tx_domain);
+ sh->tx_domain = NULL;
+ }
+ if (sh->fdb_domain) {
+ mlx5_glue->dr_destroy_domain(sh->fdb_domain);
+ sh->fdb_domain = NULL;
+ }
+ if (sh->esw_drop_action) {
+ mlx5_glue->destroy_flow_action(sh->esw_drop_action);
+ sh->esw_drop_action = NULL;
+ }
+ return err;
+#else
+ (void)priv;
+ return 0;
+#endif
+}
+
+/**
+ * Destroy DR related data within private structure.
+ *
+ * @param[in] priv
+ * Pointer to the private device data structure.
*/
static void
-mlx5_prepare_shared_data(void)
+mlx5_free_shared_dr(struct mlx5_priv *priv)
+{
+#ifdef HAVE_MLX5DV_DR
+ struct mlx5_ibv_shared *sh;
+
+ if (!priv->dr_shared)
+ return;
+ priv->dr_shared = 0;
+ sh = priv->sh;
+ assert(sh);
+ 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;
+ }
+ if (sh->tx_domain) {
+ mlx5_glue->dr_destroy_domain(sh->tx_domain);
+ sh->tx_domain = NULL;
+ }
+#ifdef HAVE_MLX5DV_DR_ESWITCH
+ if (sh->fdb_domain) {
+ mlx5_glue->dr_destroy_domain(sh->fdb_domain);
+ sh->fdb_domain = NULL;
+ }
+ if (sh->esw_drop_action) {
+ mlx5_glue->destroy_flow_action(sh->esw_drop_action);
+ sh->esw_drop_action = NULL;
+ }
+#endif
+ pthread_mutex_destroy(&sh->dv_mutex);
+#else
+ (void)priv;
+#endif
+}
+
+/**
+ * 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) {
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\n");
+ 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\n");
+ ret = -rte_errno;
+ goto error;
+ }
+ mlx5_shared_data = mz->addr;
+ memset(&mlx5_local_data, 0, sizeof(mlx5_local_data));
}
- if (mz == NULL)
- rte_panic("Cannot allocate mlx5 shared data\n");
- mlx5_shared_data = mz->addr;
- /* Initialize shared data. */
- if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
- LIST_INIT(&mlx5_shared_data->mem_event_cb_list);
- rte_rwlock_init(&mlx5_shared_data->mem_event_rwlock);
- }
- rte_mem_event_callback_register("MLX5_MEM_EVENT_CB",
- mlx5_mr_mem_event_cb, NULL);
}
+error:
rte_spinlock_unlock(&mlx5_shared_data_lock);
+ return ret;
}
/**
static void *
mlx5_alloc_verbs_buf(size_t size, void *data)
{
- struct priv *priv = data;
+ struct mlx5_priv *priv = data;
void *ret;
size_t alignment = sysconf(_SC_PAGESIZE);
unsigned int socket = SOCKET_ID_ANY;
rte_free(ptr);
}
+/**
+ * DPDK callback to add udp tunnel port
+ *
+ * @param[in] dev
+ * A pointer to eth_dev
+ * @param[in] udp_tunnel
+ * A pointer to udp tunnel
+ *
+ * @return
+ * 0 on valid udp ports and tunnels, -ENOTSUP otherwise.
+ */
+int
+mlx5_udp_tunnel_port_add(struct rte_eth_dev *dev __rte_unused,
+ struct rte_eth_udp_tunnel *udp_tunnel)
+{
+ assert(udp_tunnel != NULL);
+ if (udp_tunnel->prot_type == RTE_TUNNEL_TYPE_VXLAN &&
+ udp_tunnel->udp_port == 4789)
+ return 0;
+ if (udp_tunnel->prot_type == RTE_TUNNEL_TYPE_VXLAN_GPE &&
+ udp_tunnel->udp_port == 4790)
+ return 0;
+ return -ENOTSUP;
+}
+
+/**
+ * Initialize process private data structure.
+ *
+ * @param dev
+ * Pointer to Ethernet device structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_proc_priv_init(struct rte_eth_dev *dev)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_proc_priv *ppriv;
+ size_t ppriv_size;
+
+ /*
+ * UAR register table follows the process private structure. BlueFlame
+ * registers for Tx queues are stored in the table.
+ */
+ ppriv_size =
+ sizeof(struct mlx5_proc_priv) + priv->txqs_n * sizeof(void *);
+ ppriv = rte_malloc_socket("mlx5_proc_priv", ppriv_size,
+ RTE_CACHE_LINE_SIZE, dev->device->numa_node);
+ if (!ppriv) {
+ rte_errno = ENOMEM;
+ return -rte_errno;
+ }
+ ppriv->uar_table_sz = ppriv_size;
+ dev->process_private = ppriv;
+ return 0;
+}
+
+/**
+ * Un-initialize process private data structure.
+ *
+ * @param dev
+ * Pointer to Ethernet device structure.
+ */
+static void
+mlx5_proc_priv_uninit(struct rte_eth_dev *dev)
+{
+ if (!dev->process_private)
+ return;
+ rte_free(dev->process_private);
+ dev->process_private = NULL;
+}
+
/**
* DPDK callback to close the device.
*
static void
mlx5_dev_close(struct rte_eth_dev *dev)
{
- struct priv *priv = dev->data->dev_private;
+ struct mlx5_priv *priv = dev->data->dev_private;
unsigned int i;
int ret;
DRV_LOG(DEBUG, "port %u closing device \"%s\"",
dev->data->port_id,
- ((priv->ctx != NULL) ? priv->ctx->device->name : ""));
+ ((priv->sh->ctx != NULL) ? priv->sh->ctx->device->name : ""));
/* In case mlx5_dev_stop() has not been called. */
mlx5_dev_interrupt_handler_uninstall(dev);
mlx5_traffic_disable(dev);
/* Prevent crashes when queues are still in use. */
dev->rx_pkt_burst = removed_rx_burst;
dev->tx_pkt_burst = removed_tx_burst;
+ rte_wmb();
+ /* Disable datapath on secondary process. */
+ mlx5_mp_req_stop_rxtx(dev);
if (priv->rxqs != NULL) {
/* XXX race condition if mlx5_rx_burst() is still running. */
usleep(1000);
priv->txqs_n = 0;
priv->txqs = NULL;
}
+ mlx5_proc_priv_uninit(dev);
mlx5_mprq_free_mp(dev);
- mlx5_mr_release(dev);
- if (priv->pd != NULL) {
- assert(priv->ctx != NULL);
- claim_zero(mlx5_glue->dealloc_pd(priv->pd));
- claim_zero(mlx5_glue->close_device(priv->ctx));
- } else
- assert(priv->ctx == NULL);
+ mlx5_free_shared_dr(priv);
if (priv->rss_conf.rss_key != NULL)
rte_free(priv->rss_conf.rss_key);
if (priv->reta_idx != NULL)
rte_free(priv->reta_idx);
- if (priv->primary_socket)
- mlx5_socket_uninit(dev);
if (priv->config.vf)
mlx5_nl_mac_addr_flush(dev);
if (priv->nl_socket_route >= 0)
close(priv->nl_socket_route);
if (priv->nl_socket_rdma >= 0)
close(priv->nl_socket_rdma);
- if (priv->mnl_socket)
- mlx5_nl_flow_socket_destroy(priv->mnl_socket);
- ret = mlx5_hrxq_ibv_verify(dev);
+ if (priv->vmwa_context)
+ mlx5_vlan_vmwa_exit(priv->vmwa_context);
+ if (priv->sh) {
+ /*
+ * Free the shared context in last turn, because the cleanup
+ * routines above may use some shared fields, like
+ * mlx5_nl_mac_addr_flush() uses ibdev_path for retrieveing
+ * ifindex if Netlink fails.
+ */
+ mlx5_free_shared_ibctx(priv->sh);
+ priv->sh = NULL;
+ }
+ ret = mlx5_hrxq_verify(dev);
if (ret)
DRV_LOG(WARNING, "port %u some hash Rx queue still remain",
dev->data->port_id);
- ret = mlx5_ind_table_ibv_verify(dev);
+ ret = mlx5_ind_table_obj_verify(dev);
if (ret)
DRV_LOG(WARNING, "port %u some indirection table still remain",
dev->data->port_id);
- ret = mlx5_rxq_ibv_verify(dev);
+ ret = mlx5_rxq_obj_verify(dev);
if (ret)
- DRV_LOG(WARNING, "port %u some Verbs Rx queue still remain",
+ DRV_LOG(WARNING, "port %u some Rx queue objects still remain",
dev->data->port_id);
ret = mlx5_rxq_verify(dev);
if (ret)
dev->data->port_id);
if (priv->domain_id != RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID) {
unsigned int c = 0;
- unsigned int i = mlx5_dev_to_port_id(dev->device, NULL, 0);
- uint16_t port_id[i];
+ uint16_t port_id;
- i = RTE_MIN(mlx5_dev_to_port_id(dev->device, port_id, i), i);
- while (i--) {
- struct priv *opriv =
- rte_eth_devices[port_id[i]].data->dev_private;
+ RTE_ETH_FOREACH_DEV_OF(port_id, dev->device) {
+ struct mlx5_priv *opriv =
+ rte_eth_devices[port_id].data->dev_private;
if (!opriv ||
opriv->domain_id != priv->domain_id ||
- &rte_eth_devices[port_id[i]] == dev)
+ &rte_eth_devices[port_id] == dev)
continue;
++c;
}
}
memset(priv, 0, sizeof(*priv));
priv->domain_id = RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID;
+ /*
+ * Reset mac_addrs to NULL such that it is not freed as part of
+ * rte_eth_dev_release_port(). mac_addrs is part of dev_private so
+ * it is freed when dev_private is freed.
+ */
+ dev->data->mac_addrs = NULL;
}
const struct eth_dev_ops mlx5_dev_ops = {
.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_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,
.filter_ctrl = mlx5_dev_filter_ctrl,
.rx_descriptor_status = mlx5_rx_descriptor_status,
.tx_descriptor_status = mlx5_tx_descriptor_status,
+ .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,
};
+/* Available operations from secondary process. */
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,
+ .fw_version_get = mlx5_fw_version_get,
.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. */
+/* Available operations in flow isolated mode. */
const struct eth_dev_ops mlx5_dev_ops_isolate = {
.dev_configure = mlx5_dev_configure,
.dev_start = mlx5_dev_start,
.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,
.dev_supported_ptypes_get = mlx5_dev_supported_ptypes_get,
.vlan_filter_set = mlx5_vlan_filter_set,
}
if (strcmp(MLX5_RXQ_CQE_COMP_EN, key) == 0) {
config->cqe_comp = !!tmp;
+ } else if (strcmp(MLX5_RXQ_CQE_PAD_EN, key) == 0) {
+ config->cqe_pad = !!tmp;
+ } else if (strcmp(MLX5_RXQ_PKT_PAD_EN, key) == 0) {
+ config->hw_padding = !!tmp;
} else if (strcmp(MLX5_RX_MPRQ_EN, key) == 0) {
config->mprq.enabled = !!tmp;
} else if (strcmp(MLX5_RX_MPRQ_LOG_STRIDE_NUM, key) == 0) {
} else if (strcmp(MLX5_RXQS_MIN_MPRQ, key) == 0) {
config->mprq.min_rxqs_num = tmp;
} else if (strcmp(MLX5_TXQ_INLINE, key) == 0) {
- config->txq_inline = tmp;
+ DRV_LOG(WARNING, "%s: deprecated parameter,"
+ " converted to txq_inline_max", key);
+ config->txq_inline_max = tmp;
+ } else if (strcmp(MLX5_TXQ_INLINE_MAX, key) == 0) {
+ config->txq_inline_max = tmp;
+ } else if (strcmp(MLX5_TXQ_INLINE_MIN, key) == 0) {
+ config->txq_inline_min = tmp;
+ } else if (strcmp(MLX5_TXQ_INLINE_MPW, key) == 0) {
+ config->txq_inline_mpw = tmp;
} else if (strcmp(MLX5_TXQS_MIN_INLINE, key) == 0) {
config->txqs_inline = tmp;
+ } else if (strcmp(MLX5_TXQS_MAX_VEC, key) == 0) {
+ DRV_LOG(WARNING, "%s: deprecated parameter, ignored", key);
} else if (strcmp(MLX5_TXQ_MPW_EN, key) == 0) {
- config->mps = !!tmp ? config->mps : 0;
+ config->mps = !!tmp;
} else if (strcmp(MLX5_TXQ_MPW_HDR_DSEG_EN, key) == 0) {
- config->mpw_hdr_dseg = !!tmp;
+ DRV_LOG(WARNING, "%s: deprecated parameter, ignored", key);
} else if (strcmp(MLX5_TXQ_MAX_INLINE_LEN, key) == 0) {
- config->inline_max_packet_sz = tmp;
+ DRV_LOG(WARNING, "%s: deprecated parameter,"
+ " converted to txq_inline_mpw", key);
+ config->txq_inline_mpw = tmp;
} else if (strcmp(MLX5_TX_VEC_EN, key) == 0) {
- config->tx_vec_en = !!tmp;
+ DRV_LOG(WARNING, "%s: deprecated parameter, ignored", key);
} else if (strcmp(MLX5_RX_VEC_EN, key) == 0) {
config->rx_vec_en = !!tmp;
} else if (strcmp(MLX5_L3_VXLAN_EN, key) == 0) {
config->l3_vxlan_en = !!tmp;
} else if (strcmp(MLX5_VF_NL_EN, key) == 0) {
config->vf_nl_en = !!tmp;
+ } else if (strcmp(MLX5_DV_ESW_EN, key) == 0) {
+ config->dv_esw_en = !!tmp;
+ } else if (strcmp(MLX5_DV_FLOW_EN, key) == 0) {
+ config->dv_flow_en = !!tmp;
+ } else if (strcmp(MLX5_MR_EXT_MEMSEG_EN, key) == 0) {
+ config->mr_ext_memseg_en = !!tmp;
+ } else if (strcmp(MLX5_MAX_DUMP_FILES_NUM, key) == 0) {
+ config->max_dump_files_num = tmp;
+ } else if (strcmp(MLX5_LRO_TIMEOUT_USEC, key) == 0) {
+ config->lro.timeout = tmp;
} else {
DRV_LOG(WARNING, "%s: unknown parameter", key);
rte_errno = EINVAL;
{
const char **params = (const char *[]){
MLX5_RXQ_CQE_COMP_EN,
+ MLX5_RXQ_CQE_PAD_EN,
+ MLX5_RXQ_PKT_PAD_EN,
MLX5_RX_MPRQ_EN,
MLX5_RX_MPRQ_LOG_STRIDE_NUM,
MLX5_RX_MPRQ_MAX_MEMCPY_LEN,
MLX5_RXQS_MIN_MPRQ,
MLX5_TXQ_INLINE,
+ MLX5_TXQ_INLINE_MIN,
+ MLX5_TXQ_INLINE_MAX,
+ MLX5_TXQ_INLINE_MPW,
MLX5_TXQS_MIN_INLINE,
+ MLX5_TXQS_MAX_VEC,
MLX5_TXQ_MPW_EN,
MLX5_TXQ_MPW_HDR_DSEG_EN,
MLX5_TXQ_MAX_INLINE_LEN,
MLX5_RX_VEC_EN,
MLX5_L3_VXLAN_EN,
MLX5_VF_NL_EN,
+ MLX5_DV_ESW_EN,
+ MLX5_DV_FLOW_EN,
+ MLX5_MR_EXT_MEMSEG_EN,
MLX5_REPRESENTOR,
+ MLX5_MAX_DUMP_FILES_NUM,
+ MLX5_LRO_TIMEOUT_USEC,
NULL,
};
struct rte_kvargs *kvlist;
return 0;
/* Following UGLY cast is done to pass checkpatch. */
kvlist = rte_kvargs_parse(devargs->args, params);
- if (kvlist == NULL)
- return 0;
+ if (kvlist == NULL) {
+ rte_errno = EINVAL;
+ return -rte_errno;
+ }
/* Process parameters. */
for (i = 0; (params[i] != NULL); ++i) {
if (rte_kvargs_count(kvlist, params[i])) {
static struct rte_pci_driver mlx5_driver;
-/*
- * Reserved UAR address space for TXQ UAR(hw doorbell) mapping, process
- * local resource used by both primary and secondary to avoid duplicate
- * reservation.
- * The space has to be available on both primary and secondary process,
- * TXQ UAR maps to this area using fixed mmap w/o double check.
+/**
+ * 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 void *uar_base;
-
static int
-find_lower_va_bound(const struct rte_memseg_list *msl __rte_unused,
- const struct rte_memseg *ms, void *arg)
+mlx5_init_once(void)
{
- void **addr = arg;
+ struct mlx5_shared_data *sd;
+ struct mlx5_local_data *ld = &mlx5_local_data;
+ int ret = 0;
- if (*addr == NULL)
- *addr = ms->addr;
- else
- *addr = RTE_MIN(*addr, ms->addr);
+ if (mlx5_init_shared_data())
+ return -rte_errno;
+ sd = mlx5_shared_data;
+ 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();
+ if (ret)
+ goto out;
+ sd->init_done = true;
+ break;
+ case RTE_PROC_SECONDARY:
+ if (ld->init_done)
+ break;
+ ret = mlx5_mp_init_secondary();
+ if (ret)
+ goto out;
+ ++sd->secondary_cnt;
+ ld->init_done = true;
+ break;
+ default:
+ break;
+ }
+out:
+ rte_spinlock_unlock(&sd->lock);
+ return ret;
+}
- return 0;
+/**
+ * Configures the minimal amount of data to inline into WQE
+ * while sending packets.
+ *
+ * - the txq_inline_min has the maximal priority, if this
+ * key is specified in devargs
+ * - if DevX is enabled the inline mode is queried from the
+ * device (HCA attributes and NIC vport context if needed).
+ * - otherwise L2 mode (18 bytes) is assumed for ConnectX-4/4LX
+ * and none (0 bytes) for other NICs
+ *
+ * @param spawn
+ * Verbs device parameters (name, port, switch_info) to spawn.
+ * @param config
+ * Device configuration parameters.
+ */
+static void
+mlx5_set_min_inline(struct mlx5_dev_spawn_data *spawn,
+ struct mlx5_dev_config *config)
+{
+ if (config->txq_inline_min != MLX5_ARG_UNSET) {
+ /* Application defines size of inlined data explicitly. */
+ switch (spawn->pci_dev->id.device_id) {
+ case PCI_DEVICE_ID_MELLANOX_CONNECTX4:
+ case PCI_DEVICE_ID_MELLANOX_CONNECTX4VF:
+ if (config->txq_inline_min <
+ (int)MLX5_INLINE_HSIZE_L2) {
+ DRV_LOG(DEBUG,
+ "txq_inline_mix aligned to minimal"
+ " ConnectX-4 required value %d",
+ (int)MLX5_INLINE_HSIZE_L2);
+ config->txq_inline_min = MLX5_INLINE_HSIZE_L2;
+ }
+ break;
+ }
+ goto exit;
+ }
+ if (config->hca_attr.eth_net_offloads) {
+ /* We have DevX enabled, inline mode queried successfully. */
+ switch (config->hca_attr.wqe_inline_mode) {
+ case MLX5_CAP_INLINE_MODE_L2:
+ /* outer L2 header must be inlined. */
+ config->txq_inline_min = MLX5_INLINE_HSIZE_L2;
+ goto exit;
+ case MLX5_CAP_INLINE_MODE_NOT_REQUIRED:
+ /* No inline data are required by NIC. */
+ config->txq_inline_min = MLX5_INLINE_HSIZE_NONE;
+ config->hw_vlan_insert =
+ config->hca_attr.wqe_vlan_insert;
+ DRV_LOG(DEBUG, "Tx VLAN insertion is supported");
+ goto exit;
+ case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT:
+ /* inline mode is defined by NIC vport context. */
+ if (!config->hca_attr.eth_virt)
+ break;
+ switch (config->hca_attr.vport_inline_mode) {
+ case MLX5_INLINE_MODE_NONE:
+ config->txq_inline_min =
+ MLX5_INLINE_HSIZE_NONE;
+ goto exit;
+ case MLX5_INLINE_MODE_L2:
+ config->txq_inline_min =
+ MLX5_INLINE_HSIZE_L2;
+ goto exit;
+ case MLX5_INLINE_MODE_IP:
+ config->txq_inline_min =
+ MLX5_INLINE_HSIZE_L3;
+ goto exit;
+ case MLX5_INLINE_MODE_TCP_UDP:
+ config->txq_inline_min =
+ MLX5_INLINE_HSIZE_L4;
+ goto exit;
+ case MLX5_INLINE_MODE_INNER_L2:
+ config->txq_inline_min =
+ MLX5_INLINE_HSIZE_INNER_L2;
+ goto exit;
+ case MLX5_INLINE_MODE_INNER_IP:
+ config->txq_inline_min =
+ MLX5_INLINE_HSIZE_INNER_L3;
+ goto exit;
+ case MLX5_INLINE_MODE_INNER_TCP_UDP:
+ config->txq_inline_min =
+ MLX5_INLINE_HSIZE_INNER_L4;
+ goto exit;
+ }
+ }
+ }
+ /*
+ * We get here if we are unable to deduce
+ * inline data size with DevX. Try PCI ID
+ * to determine old NICs.
+ */
+ switch (spawn->pci_dev->id.device_id) {
+ case PCI_DEVICE_ID_MELLANOX_CONNECTX4:
+ case PCI_DEVICE_ID_MELLANOX_CONNECTX4VF:
+ case PCI_DEVICE_ID_MELLANOX_CONNECTX4LX:
+ case PCI_DEVICE_ID_MELLANOX_CONNECTX4LXVF:
+ config->txq_inline_min = MLX5_INLINE_HSIZE_L2;
+ config->hw_vlan_insert = 0;
+ 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:
+ /*
+ * These NICs support VLAN insertion from WQE and
+ * report the wqe_vlan_insert flag. But there is the bug
+ * and PFC control may be broken, so disable feature.
+ */
+ config->hw_vlan_insert = 0;
+ config->txq_inline_min = MLX5_INLINE_HSIZE_NONE;
+ break;
+ default:
+ config->txq_inline_min = MLX5_INLINE_HSIZE_NONE;
+ break;
+ }
+exit:
+ DRV_LOG(DEBUG, "min tx inline configured: %d", config->txq_inline_min);
}
/**
- * Reserve UAR address space for primary process.
+ * Allocate page of door-bells and register it using DevX API.
*
- * @param[in] dev
+ * @param [in] dev
* Pointer to Ethernet device.
*
* @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
+ * Pointer to new page on success, NULL otherwise.
*/
-static int
-mlx5_uar_init_primary(struct rte_eth_dev *dev)
+static struct mlx5_devx_dbr_page *
+mlx5_alloc_dbr_page(struct rte_eth_dev *dev)
{
- struct priv *priv = dev->data->dev_private;
- void *addr = (void *)0;
-
- if (uar_base) { /* UAR address space mapped. */
- priv->uar_base = uar_base;
- return 0;
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_devx_dbr_page *page;
+
+ /* Allocate space for door-bell page and management data. */
+ page = rte_calloc_socket(__func__, 1, sizeof(struct mlx5_devx_dbr_page),
+ RTE_CACHE_LINE_SIZE, dev->device->numa_node);
+ if (!page) {
+ DRV_LOG(ERR, "port %u cannot allocate dbr page",
+ dev->data->port_id);
+ return NULL;
}
- /* find out lower bound of hugepage segments */
- rte_memseg_walk(find_lower_va_bound, &addr);
-
- /* keep distance to hugepages to minimize potential conflicts. */
- addr = RTE_PTR_SUB(addr, (uintptr_t)(MLX5_UAR_OFFSET + MLX5_UAR_SIZE));
- /* anonymous mmap, no real memory consumption. */
- addr = mmap(addr, MLX5_UAR_SIZE,
- PROT_NONE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
- if (addr == MAP_FAILED) {
- DRV_LOG(ERR,
- "port %u failed to reserve UAR address space, please"
- " adjust MLX5_UAR_SIZE or try --base-virtaddr",
+ /* Register allocated memory. */
+ page->umem = mlx5_glue->devx_umem_reg(priv->sh->ctx, page->dbrs,
+ MLX5_DBR_PAGE_SIZE, 0);
+ if (!page->umem) {
+ DRV_LOG(ERR, "port %u cannot umem reg dbr page",
dev->data->port_id);
- rte_errno = ENOMEM;
- return -rte_errno;
+ rte_free(page);
+ return NULL;
}
- /* Accept either same addr or a new addr returned from mmap if target
- * range occupied.
- */
- DRV_LOG(INFO, "port %u reserved UAR address space: %p",
- dev->data->port_id, addr);
- priv->uar_base = addr; /* for primary and secondary UAR re-mmap. */
- uar_base = addr; /* process local, don't reserve again. */
- return 0;
+ return page;
}
/**
- * Reserve UAR address space for secondary process, align with
- * primary process.
+ * Find the next available door-bell, allocate new page if needed.
*
- * @param[in] dev
+ * @param [in] dev
* Pointer to Ethernet device.
+ * @param [out] dbr_page
+ * Door-bell page containing the page data.
*
* @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
+ * Door-bell address offset on success, a negative error value otherwise.
*/
-static int
-mlx5_uar_init_secondary(struct rte_eth_dev *dev)
+int64_t
+mlx5_get_dbr(struct rte_eth_dev *dev, struct mlx5_devx_dbr_page **dbr_page)
{
- struct priv *priv = dev->data->dev_private;
- void *addr;
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_devx_dbr_page *page = NULL;
+ uint32_t i, j;
- assert(priv->uar_base);
- if (uar_base) { /* already reserved. */
- assert(uar_base == priv->uar_base);
- return 0;
- }
- /* anonymous mmap, no real memory consumption. */
- addr = mmap(priv->uar_base, MLX5_UAR_SIZE,
- PROT_NONE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
- if (addr == MAP_FAILED) {
- DRV_LOG(ERR, "port %u UAR mmap failed: %p size: %llu",
- dev->data->port_id, priv->uar_base, MLX5_UAR_SIZE);
- rte_errno = ENXIO;
- return -rte_errno;
+ LIST_FOREACH(page, &priv->dbrpgs, next)
+ if (page->dbr_count < MLX5_DBR_PER_PAGE)
+ break;
+ if (!page) { /* No page with free door-bell exists. */
+ page = mlx5_alloc_dbr_page(dev);
+ if (!page) /* Failed to allocate new page. */
+ return (-1);
+ LIST_INSERT_HEAD(&priv->dbrpgs, page, next);
}
- if (priv->uar_base != addr) {
- DRV_LOG(ERR,
- "port %u UAR address %p size %llu occupied, please"
- " adjust MLX5_UAR_OFFSET or try EAL parameter"
- " --base-virtaddr",
- dev->data->port_id, priv->uar_base, MLX5_UAR_SIZE);
- rte_errno = ENXIO;
- return -rte_errno;
+ /* Loop to find bitmap part with clear bit. */
+ for (i = 0;
+ i < MLX5_DBR_BITMAP_SIZE && page->dbr_bitmap[i] == UINT64_MAX;
+ i++)
+ ; /* Empty. */
+ /* Find the first clear bit. */
+ j = rte_bsf64(~page->dbr_bitmap[i]);
+ assert(i < (MLX5_DBR_PER_PAGE / 64));
+ page->dbr_bitmap[i] |= (1 << j);
+ page->dbr_count++;
+ *dbr_page = page;
+ return (((i * 64) + j) * sizeof(uint64_t));
+}
+
+/**
+ * Release a door-bell record.
+ *
+ * @param [in] dev
+ * Pointer to Ethernet device.
+ * @param [in] umem_id
+ * UMEM ID of page containing the door-bell record to release.
+ * @param [in] offset
+ * Offset of door-bell record in page.
+ *
+ * @return
+ * 0 on success, a negative error value otherwise.
+ */
+int32_t
+mlx5_release_dbr(struct rte_eth_dev *dev, uint32_t umem_id, uint64_t offset)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_devx_dbr_page *page = NULL;
+ int ret = 0;
+
+ LIST_FOREACH(page, &priv->dbrpgs, next)
+ /* Find the page this address belongs to. */
+ if (page->umem->umem_id == umem_id)
+ break;
+ if (!page)
+ return -EINVAL;
+ page->dbr_count--;
+ if (!page->dbr_count) {
+ /* Page not used, free it and remove from list. */
+ LIST_REMOVE(page, next);
+ if (page->umem)
+ ret = -mlx5_glue->devx_umem_dereg(page->umem);
+ rte_free(page);
+ } else {
+ /* Mark in bitmap that this door-bell is not in use. */
+ offset /= MLX5_DBR_SIZE;
+ int i = offset / 64;
+ int j = offset % 64;
+
+ page->dbr_bitmap[i] &= ~(1 << j);
}
- uar_base = addr; /* process local, don't reserve again */
- DRV_LOG(INFO, "port %u reserved UAR address space: %p",
- dev->data->port_id, addr);
- return 0;
+ return ret;
}
/**
*
* @param dpdk_dev
* Backing DPDK device.
- * @param ibv_dev
- * Verbs device.
- * @param vf
- * If nonzero, enable VF-specific features.
- * @param[in] switch_info
- * Switch properties of Ethernet device.
+ * @param spawn
+ * Verbs device parameters (name, port, switch_info) to spawn.
+ * @param config
+ * Device configuration parameters.
*
* @return
* A valid Ethernet device object on success, NULL otherwise and rte_errno
- * is set. The following error is defined:
+ * is set. The following errors are defined:
*
- * EBUSY: device is not supposed to be spawned.
- */
-static struct rte_eth_dev *
-mlx5_dev_spawn(struct rte_device *dpdk_dev,
- struct ibv_device *ibv_dev,
- int vf,
- const struct mlx5_switch_info *switch_info)
-{
- struct ibv_context *ctx;
- struct ibv_device_attr_ex attr;
- struct ibv_port_attr port_attr;
- struct ibv_pd *pd = NULL;
- struct mlx5dv_context dv_attr = { .comp_mask = 0 };
- struct mlx5_dev_config config = {
- .vf = !!vf,
- .tx_vec_en = 1,
- .rx_vec_en = 1,
- .mpw_hdr_dseg = 0,
- .txq_inline = MLX5_ARG_UNSET,
- .txqs_inline = MLX5_ARG_UNSET,
- .inline_max_packet_sz = MLX5_ARG_UNSET,
- .vf_nl_en = 1,
- .mprq = {
- .enabled = 0,
- .stride_num_n = MLX5_MPRQ_STRIDE_NUM_N,
- .max_memcpy_len = MLX5_MPRQ_MEMCPY_DEFAULT_LEN,
- .min_rxqs_num = MLX5_MPRQ_MIN_RXQS,
- },
- };
+ * EBUSY: device is not supposed to be spawned.
+ * EEXIST: device is already spawned
+ */
+static struct rte_eth_dev *
+mlx5_dev_spawn(struct rte_device *dpdk_dev,
+ struct mlx5_dev_spawn_data *spawn,
+ struct mlx5_dev_config config)
+{
+ const struct mlx5_switch_info *switch_info = &spawn->info;
+ struct mlx5_ibv_shared *sh = NULL;
+ struct ibv_port_attr port_attr;
+ struct mlx5dv_context dv_attr = { .comp_mask = 0 };
struct rte_eth_dev *eth_dev = NULL;
- struct priv *priv = NULL;
+ struct mlx5_priv *priv = 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;
unsigned int mprq_max_stride_size_n = 0;
unsigned int mprq_min_stride_num_n = 0;
unsigned int mprq_max_stride_num_n = 0;
-#ifdef HAVE_IBV_DEVICE_COUNTERS_SET_SUPPORT
- struct ibv_counter_set_description cs_desc = { .counter_type = 0 };
-#endif
- struct ether_addr mac;
+ struct rte_ether_addr mac;
char name[RTE_ETH_NAME_MAX_LEN];
int own_domain_id = 0;
+ uint16_t port_id;
unsigned int i;
/* Determine if this port representor is supposed to be spawned. */
return NULL;
}
}
- /* Prepare shared data between primary and secondary process. */
- mlx5_prepare_shared_data();
- errno = 0;
- ctx = mlx5_glue->open_device(ibv_dev);
- if (!ctx) {
- rte_errno = errno ? errno : ENODEV;
+ /* Build device name. */
+ if (!switch_info->representor)
+ strlcpy(name, dpdk_dev->name, sizeof(name));
+ else
+ snprintf(name, sizeof(name), "%s_representor_%u",
+ dpdk_dev->name, switch_info->port_name);
+ /* check if the device is already spawned */
+ if (rte_eth_dev_get_port_by_name(name, &port_id) == 0) {
+ rte_errno = EEXIST;
return NULL;
}
+ DRV_LOG(DEBUG, "naming Ethernet device \"%s\"", name);
+ if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
+ eth_dev = rte_eth_dev_attach_secondary(name);
+ if (eth_dev == NULL) {
+ DRV_LOG(ERR, "can not attach rte ethdev");
+ rte_errno = ENOMEM;
+ return NULL;
+ }
+ eth_dev->device = dpdk_dev;
+ eth_dev->dev_ops = &mlx5_dev_sec_ops;
+ err = mlx5_proc_priv_init(eth_dev);
+ if (err)
+ return NULL;
+ /* Receive command fd from primary process */
+ err = mlx5_mp_req_verbs_cmd_fd(eth_dev);
+ if (err < 0)
+ return NULL;
+ /* Remap UAR for Tx queues. */
+ err = mlx5_tx_uar_init_secondary(eth_dev, err);
+ if (err)
+ return NULL;
+ /*
+ * Ethdev pointer is still required as input since
+ * the primary device is not accessible from the
+ * secondary process.
+ */
+ eth_dev->rx_pkt_burst = mlx5_select_rx_function(eth_dev);
+ eth_dev->tx_pkt_burst = mlx5_select_tx_function(eth_dev);
+ return eth_dev;
+ }
+ sh = mlx5_alloc_shared_ibctx(spawn);
+ if (!sh)
+ return NULL;
+ config.devx = sh->devx;
+#ifdef HAVE_MLX5DV_DR_ACTION_DEST_DEVX_TIR
+ config.dest_tir = 1;
+#endif
#ifdef HAVE_IBV_MLX5_MOD_SWP
dv_attr.comp_mask |= MLX5DV_CONTEXT_MASK_SWP;
#endif
#ifdef HAVE_IBV_DEVICE_STRIDING_RQ_SUPPORT
dv_attr.comp_mask |= MLX5DV_CONTEXT_MASK_STRIDING_RQ;
#endif
- mlx5_glue->dv_query_device(ctx, &dv_attr);
+ mlx5_glue->dv_query_device(sh->ctx, &dv_attr);
if (dv_attr.flags & MLX5DV_CONTEXT_FLAGS_MPW_ALLOWED) {
if (dv_attr.flags & MLX5DV_CONTEXT_FLAGS_ENHANCED_MPW) {
DRV_LOG(DEBUG, "enhanced MPW is supported");
DRV_LOG(DEBUG, "MPW isn't supported");
mps = MLX5_MPW_DISABLED;
}
- config.mps = mps;
#ifdef HAVE_IBV_MLX5_MOD_SWP
if (dv_attr.comp_mask & MLX5DV_CONTEXT_MASK_SWP)
swp = dv_attr.sw_parsing_caps.sw_parsing_offloads;
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
#ifdef HAVE_IBV_DEVICE_TUNNEL_SUPPORT
if (dv_attr.comp_mask & MLX5DV_CONTEXT_MASK_TUNNEL_OFFLOADS) {
tunnel_en = ((dv_attr.tunnel_offloads_caps &
" old OFED/rdma-core version or firmware configuration");
#endif
config.mpls_en = mpls_en;
- err = mlx5_glue->query_device_ex(ctx, NULL, &attr);
- if (err) {
- DEBUG("ibv_query_device_ex() failed");
- goto error;
- }
- if (!switch_info->representor)
- rte_strlcpy(name, dpdk_dev->name, sizeof(name));
- else
- snprintf(name, sizeof(name), "%s_representor_%u",
- dpdk_dev->name, switch_info->port_name);
- DRV_LOG(DEBUG, "naming Ethernet device \"%s\"", name);
- if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
- eth_dev = rte_eth_dev_attach_secondary(name);
- if (eth_dev == NULL) {
- DRV_LOG(ERR, "can not attach rte ethdev");
- rte_errno = ENOMEM;
- err = rte_errno;
- goto error;
- }
- eth_dev->device = dpdk_dev;
- eth_dev->dev_ops = &mlx5_dev_sec_ops;
- err = mlx5_uar_init_secondary(eth_dev);
- if (err) {
- err = rte_errno;
- goto error;
- }
- /* Receive command fd from primary process */
- err = mlx5_socket_connect(eth_dev);
- if (err < 0) {
- err = rte_errno;
- goto error;
- }
- /* Remap UAR for Tx queues. */
- err = mlx5_tx_uar_remap(eth_dev, err);
- if (err) {
- err = rte_errno;
- 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 = mlx5_select_rx_function(eth_dev);
- eth_dev->tx_pkt_burst = mlx5_select_tx_function(eth_dev);
- claim_zero(mlx5_glue->close_device(ctx));
- return eth_dev;
- }
/* Check port status. */
- err = mlx5_glue->query_port(ctx, 1, &port_attr);
+ err = mlx5_glue->query_port(sh->ctx, spawn->ibv_port, &port_attr);
if (err) {
DRV_LOG(ERR, "port query failed: %s", strerror(err));
goto error;
DRV_LOG(DEBUG, "port is not active: \"%s\" (%d)",
mlx5_glue->port_state_str(port_attr.state),
port_attr.state);
- /* Allocate protection domain. */
- pd = mlx5_glue->alloc_pd(ctx);
- if (pd == NULL) {
- DRV_LOG(ERR, "PD allocation failure");
- err = ENOMEM;
- goto error;
- }
+ /* Allocate private eth device data. */
priv = rte_zmalloc("ethdev private structure",
sizeof(*priv),
RTE_CACHE_LINE_SIZE);
err = ENOMEM;
goto error;
}
- priv->ctx = ctx;
- strncpy(priv->ibdev_name, priv->ctx->device->name,
- sizeof(priv->ibdev_name));
- strncpy(priv->ibdev_path, priv->ctx->device->ibdev_path,
- sizeof(priv->ibdev_path));
- priv->device_attr = attr;
- priv->pd = pd;
- priv->mtu = ETHER_MTU;
+ priv->sh = sh;
+ priv->ibv_port = spawn->ibv_port;
+ priv->mtu = RTE_ETHER_MTU;
#ifndef RTE_ARCH_64
/* Initialize UAR access locks for 32bit implementations. */
rte_spinlock_init(&priv->uar_lock_cq);
priv->nl_socket_route = mlx5_nl_init(NETLINK_ROUTE);
priv->nl_sn = 0;
priv->representor = !!switch_info->representor;
+ priv->master = !!switch_info->master;
priv->domain_id = RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID;
- priv->representor_id =
- switch_info->representor ? switch_info->port_name : -1;
+ /*
+ * Currently we support single E-Switch per PF configurations
+ * only and vport_id field contains the vport index for
+ * associated VF, which is deduced from representor port name.
+ * For example, let's have the IB device port 10, it has
+ * attached network device eth0, which has port name attribute
+ * pf0vf2, we can deduce the VF number as 2, and set vport index
+ * as 3 (2+1). This assigning schema should be changed if the
+ * multiple E-Switch instances per PF configurations or/and PCI
+ * subfunctions are added.
+ */
+ priv->vport_id = switch_info->representor ?
+ switch_info->port_name + 1 : -1;
+ /* representor_id field keeps the unmodified port/VF index. */
+ priv->representor_id = switch_info->representor ?
+ switch_info->port_name : -1;
/*
* Look for sibling devices in order to reuse their switch domain
* if any, otherwise allocate one.
*/
- i = mlx5_dev_to_port_id(dpdk_dev, NULL, 0);
- if (i > 0) {
- uint16_t port_id[i];
-
- i = RTE_MIN(mlx5_dev_to_port_id(dpdk_dev, port_id, i), i);
- while (i--) {
- const struct priv *opriv =
- rte_eth_devices[port_id[i]].data->dev_private;
+ RTE_ETH_FOREACH_DEV_OF(port_id, dpdk_dev) {
+ const struct mlx5_priv *opriv =
+ rte_eth_devices[port_id].data->dev_private;
- if (!opriv ||
- opriv->domain_id ==
- RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID)
- continue;
- priv->domain_id = opriv->domain_id;
- break;
- }
+ if (!opriv ||
+ opriv->domain_id ==
+ RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID)
+ continue;
+ priv->domain_id = opriv->domain_id;
+ break;
}
if (priv->domain_id == RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID) {
err = rte_eth_switch_domain_alloc(&priv->domain_id);
strerror(rte_errno));
goto error;
}
- config.hw_csum = !!(attr.device_cap_flags_ex & IBV_DEVICE_RAW_IP_CSUM);
+ 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 "));
-#ifdef HAVE_IBV_DEVICE_COUNTERS_SET_SUPPORT
- config.flow_counter_en = !!attr.max_counter_sets;
- mlx5_glue->describe_counter_set(ctx, 0, &cs_desc);
- DRV_LOG(DEBUG, "counter type = %d, num of cs = %ld, attributes = %d",
- cs_desc.counter_type, cs_desc.num_of_cs,
- cs_desc.attributes);
+#if !defined(HAVE_IBV_DEVICE_COUNTERS_SET_V42) && \
+ !defined(HAVE_IBV_DEVICE_COUNTERS_SET_V45)
+ DRV_LOG(DEBUG, "counters are not supported");
+#endif
+#ifndef HAVE_IBV_FLOW_DV_SUPPORT
+ if (config.dv_flow_en) {
+ DRV_LOG(WARNING, "DV flow is not supported");
+ config.dv_flow_en = 0;
+ }
#endif
config.ind_table_max_size =
- attr.rss_caps.max_rwq_indirection_table_size;
+ sh->device_attr.rss_caps.max_rwq_indirection_table_size;
/*
* Remove this check once DPDK supports larger/variable
* indirection tables.
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 = !!(attr.raw_packet_caps &
+ 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 = !!(attr.raw_packet_caps &
+ config.hw_fcs_strip = !!(sh->device_attr.raw_packet_caps &
IBV_RAW_PACKET_CAP_SCATTER_FCS);
DRV_LOG(DEBUG, "FCS stripping configuration is %ssupported",
(config.hw_fcs_strip ? "" : "not "));
-#ifdef HAVE_IBV_WQ_FLAG_RX_END_PADDING
- config.hw_padding = !!attr.rx_pad_end_addr_align;
+#if defined(HAVE_IBV_WQ_FLAG_RX_END_PADDING)
+ hw_padding = !!sh->device_attr.rx_pad_end_addr_align;
+#elif defined(HAVE_IBV_WQ_FLAGS_PCI_WRITE_END_PADDING)
+ hw_padding = !!(sh->device_attr.device_cap_flags_ex &
+ IBV_DEVICE_PCI_WRITE_END_PADDING);
#endif
- DRV_LOG(DEBUG, "hardware Rx end alignment padding is %ssupported",
- (config.hw_padding ? "" : "not "));
- config.tso = (attr.tso_caps.max_tso > 0 &&
- (attr.tso_caps.supported_qpts &
+ 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) {
+ DRV_LOG(DEBUG, "Rx end alignment padding is enabled");
+ }
+ config.tso = (sh->device_attr.tso_caps.max_tso > 0 &&
+ (sh->device_attr.tso_caps.supported_qpts &
(1 << IBV_QPT_RAW_PACKET)));
if (config.tso)
- config.tso_max_payload_sz = attr.tso_caps.max_tso;
- if (config.mps && !mps) {
- DRV_LOG(ERR,
- "multi-packet send not supported on this device"
- " (" MLX5_TXQ_MPW_EN ")");
- err = ENOTSUP;
- goto error;
- }
+ config.tso_max_payload_sz = sh->device_attr.tso_caps.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 :
+ MLX5_MPW_DISABLED;
+ else
+ config.mps = config.mps ? mps : MLX5_MPW_DISABLED;
DRV_LOG(INFO, "%sMPS is %s",
config.mps == MLX5_MPW_ENHANCED ? "enhanced " : "",
config.mps != MLX5_MPW_DISABLED ? "enabled" : "disabled");
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);
+ 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\n");
+ /* Check for LRO support. */
+ if (config.dest_tir && config.hca_attr.lro_cap) {
+ /* TBD check tunnel lro caps. */
+ 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];
+ DRV_LOG(DEBUG, "LRO session timeout set to %d usec",
+ config.lro.timeout);
+ }
+ }
if (config.mprq.enabled && mprq) {
if (config.mprq.stride_num_n > mprq_max_stride_num_n ||
config.mprq.stride_num_n < mprq_min_stride_num_n) {
DRV_LOG(WARNING, "Multi-Packet RQ isn't supported");
config.mprq.enabled = 0;
}
+ 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;
}
- if (priv->representor)
+ /* 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;
+ }
+ /*
+ * Store associated network device interface index. This index
+ * is permanent throughout the lifetime of device. So, we may store
+ * the ifindex here and use the cached value further.
+ */
+ assert(spawn->ifindex);
+ priv->if_index = spawn->ifindex;
eth_dev->data->dev_private = priv;
priv->dev_data = eth_dev->data;
eth_dev->data->mac_addrs = priv->mac;
eth_dev->device = dpdk_dev;
- eth_dev->device->driver = &mlx5_driver.driver;
- err = mlx5_uar_init_primary(eth_dev);
- if (err) {
- err = rte_errno;
- goto error;
- }
/* Configure the first MAC address by default. */
if (mlx5_get_mac(eth_dev, &mac.addr_bytes)) {
DRV_LOG(ERR,
eth_dev->dev_ops = &mlx5_dev_ops;
/* Register MAC address. */
claim_zero(mlx5_mac_addr_add(eth_dev, &mac, 0, 0));
- if (vf && config.vf_nl_en)
+ if (config.vf && config.vf_nl_en)
mlx5_nl_mac_addr_sync(eth_dev);
- priv->mnl_socket = mlx5_nl_flow_socket_create();
- if (!priv->mnl_socket) {
- err = -rte_errno;
- DRV_LOG(WARNING,
- "flow rules relying on switch offloads will not be"
- " supported: cannot open libmnl socket: %s",
- strerror(rte_errno));
- } else {
- struct rte_flow_error error;
- unsigned int ifindex = mlx5_ifindex(eth_dev);
-
- if (!ifindex) {
- err = -rte_errno;
- error.message =
- "cannot retrieve network interface index";
- } else {
- err = mlx5_nl_flow_init(priv->mnl_socket, ifindex,
- &error);
- }
- if (err) {
- DRV_LOG(WARNING,
- "flow rules relying on switch offloads will"
- " not be supported: %s: %s",
- error.message, strerror(rte_errno));
- mlx5_nl_flow_socket_destroy(priv->mnl_socket);
- priv->mnl_socket = NULL;
- }
- }
TAILQ_INIT(&priv->flows);
TAILQ_INIT(&priv->ctrl_flows);
/* Hint libmlx5 to use PMD allocator for data plane resources */
.free = &mlx5_free_verbs_buf,
.data = priv,
};
- mlx5_glue->dv_set_context_attr(ctx, MLX5DV_CTX_ATTR_BUF_ALLOCATORS,
+ mlx5_glue->dv_set_context_attr(sh->ctx,
+ MLX5DV_CTX_ATTR_BUF_ALLOCATORS,
(void *)((uintptr_t)&alctr));
/* Bring Ethernet device up. */
DRV_LOG(DEBUG, "port %u forcing Ethernet interface up",
mlx5_set_link_up(eth_dev);
/*
* Even though the interrupt handler is not installed yet,
- * interrupts will still trigger on the asyn_fd from
+ * interrupts will still trigger on the async_fd from
* Verbs context returned by ibv_open_device().
*/
mlx5_link_update(eth_dev, 0);
+#ifdef HAVE_MLX5DV_DR_ESWITCH
+ if (!(config.hca_attr.eswitch_manager && config.dv_flow_en &&
+ (switch_info->representor || switch_info->master)))
+ config.dv_esw_en = 0;
+#else
+ config.dv_esw_en = 0;
+#endif
+ /* Detect minimal data bytes to inline. */
+ mlx5_set_min_inline(spawn, &config);
/* Store device configuration on private structure. */
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) {
+ err = mlx5_alloc_shared_dr(priv);
+ if (err)
+ goto error;
+ }
/* Supported Verbs flow priority number detection. */
err = mlx5_flow_discover_priorities(eth_dev);
- if (err < 0)
- goto error;
- priv->config.flow_prio = err;
- /*
- * Once the device is added to the list of memory event
- * callback, its global MR cache table cannot be expanded
- * on the fly because of deadlock. If it overflows, lookup
- * should be done by searching MR list linearly, which is slow.
- */
- err = mlx5_mr_btree_init(&priv->mr.cache,
- MLX5_MR_BTREE_CACHE_N * 2,
- eth_dev->device->numa_node);
- if (err) {
- err = rte_errno;
+ if (err < 0) {
+ err = -err;
goto error;
}
- /* Add device to memory callback list. */
- rte_rwlock_write_lock(&mlx5_shared_data->mem_event_rwlock);
- LIST_INSERT_HEAD(&mlx5_shared_data->mem_event_cb_list,
- priv, mem_event_cb);
- rte_rwlock_write_unlock(&mlx5_shared_data->mem_event_rwlock);
+ priv->config.flow_prio = err;
return eth_dev;
error:
if (priv) {
+ if (priv->sh)
+ mlx5_free_shared_dr(priv);
if (priv->nl_socket_route >= 0)
close(priv->nl_socket_route);
if (priv->nl_socket_rdma >= 0)
close(priv->nl_socket_rdma);
- if (priv->mnl_socket)
- mlx5_nl_flow_socket_destroy(priv->mnl_socket);
+ if (priv->vmwa_context)
+ mlx5_vlan_vmwa_exit(priv->vmwa_context);
if (own_domain_id)
claim_zero(rte_eth_switch_domain_free(priv->domain_id));
rte_free(priv);
+ if (eth_dev != NULL)
+ eth_dev->data->dev_private = NULL;
}
- if (pd)
- claim_zero(mlx5_glue->dealloc_pd(pd));
- if (eth_dev)
+ if (eth_dev != NULL) {
+ /* mac_addrs must not be freed alone because part of dev_private */
+ eth_dev->data->mac_addrs = NULL;
rte_eth_dev_release_port(eth_dev);
- if (ctx)
- claim_zero(mlx5_glue->close_device(ctx));
+ }
+ if (sh)
+ mlx5_free_shared_ibctx(sh);
assert(err > 0);
rte_errno = err;
return NULL;
}
-/** Data associated with devices to spawn. */
-struct mlx5_dev_spawn_data {
- unsigned int ifindex; /**< Network interface index. */
- struct mlx5_switch_info info; /**< Switch information. */
- struct ibv_device *ibv_dev; /**< Associated IB device. */
- struct rte_eth_dev *eth_dev; /**< Associated Ethernet device. */
-};
-
/**
* Comparison callback to sort device data.
*
struct rte_pci_device *pci_dev)
{
struct ibv_device **ibv_list;
- unsigned int n = 0;
- int vf;
+ /*
+ * Number of found IB Devices matching with requested PCI BDF.
+ * nd != 1 means there are multiple IB devices over the same
+ * PCI device and we have representors and master.
+ */
+ unsigned int nd = 0;
+ /*
+ * Number of found IB device Ports. nd = 1 and np = 1..n means
+ * we have the single multiport IB device, and there may be
+ * representors attached to some of found ports.
+ */
+ unsigned int np = 0;
+ /*
+ * Number of DPDK ethernet devices to Spawn - either over
+ * multiple IB devices or multiple ports of single IB device.
+ * Actually this is the number of iterations to spawn.
+ */
+ unsigned int ns = 0;
+ struct mlx5_dev_config dev_config;
int ret;
+ ret = mlx5_init_once();
+ if (ret) {
+ DRV_LOG(ERR, "unable to init PMD global data: %s",
+ strerror(rte_errno));
+ return -rte_errno;
+ }
assert(pci_drv == &mlx5_driver);
errno = 0;
ibv_list = mlx5_glue->get_device_list(&ret);
DRV_LOG(ERR, "cannot list devices, is ib_uverbs loaded?");
return -rte_errno;
}
-
+ /*
+ * First scan the list of all Infiniband devices to find
+ * matching ones, gathering into the list.
+ */
struct ibv_device *ibv_match[ret + 1];
+ int nl_route = -1;
+ int nl_rdma = -1;
+ unsigned int i;
while (ret-- > 0) {
struct rte_pci_addr pci_addr;
continue;
DRV_LOG(INFO, "PCI information matches for device \"%s\"",
ibv_list[ret]->name);
- ibv_match[n++] = ibv_list[ret];
+ ibv_match[nd++] = ibv_list[ret];
+ }
+ ibv_match[nd] = NULL;
+ if (!nd) {
+ /* No device matches, just complain and bail out. */
+ mlx5_glue->free_device_list(ibv_list);
+ DRV_LOG(WARNING,
+ "no Verbs device matches PCI device " PCI_PRI_FMT ","
+ " are kernel drivers loaded?",
+ pci_dev->addr.domain, pci_dev->addr.bus,
+ pci_dev->addr.devid, pci_dev->addr.function);
+ rte_errno = ENOENT;
+ ret = -rte_errno;
+ return ret;
+ }
+ nl_route = mlx5_nl_init(NETLINK_ROUTE);
+ nl_rdma = mlx5_nl_init(NETLINK_RDMA);
+ if (nd == 1) {
+ /*
+ * Found single matching device may have multiple ports.
+ * Each port may be representor, we have to check the port
+ * number and check the representors existence.
+ */
+ if (nl_rdma >= 0)
+ np = mlx5_nl_portnum(nl_rdma, ibv_match[0]->name);
+ if (!np)
+ DRV_LOG(WARNING, "can not get IB device \"%s\""
+ " ports number", ibv_match[0]->name);
}
- ibv_match[n] = NULL;
-
- struct mlx5_dev_spawn_data list[n];
- int nl_route = n ? mlx5_nl_init(NETLINK_ROUTE) : -1;
- int nl_rdma = n ? mlx5_nl_init(NETLINK_RDMA) : -1;
- unsigned int i;
- unsigned int u;
-
/*
- * The existence of several matching entries (n > 1) means port
- * representors have been instantiated. No existing Verbs call nor
- * /sys entries can tell them apart, this can only be done through
- * Netlink calls assuming kernel drivers are recent enough to
- * support them.
- *
- * In the event of identification failure through Netlink, try again
- * through sysfs, then either:
- *
- * 1. No device matches (n == 0), complain and bail out.
- * 2. A single IB device matches (n == 1) and is not a representor,
- * assume no switch support.
- * 3. Otherwise no safe assumptions can be made; complain louder and
- * bail out.
+ * Now we can determine the maximal
+ * amount of devices to be spawned.
*/
- for (i = 0; i != n; ++i) {
- list[i].ibv_dev = ibv_match[i];
- list[i].eth_dev = NULL;
- if (nl_rdma < 0)
- list[i].ifindex = 0;
- else
- list[i].ifindex = mlx5_nl_ifindex
- (nl_rdma, list[i].ibv_dev->name);
- if (nl_route < 0 ||
- !list[i].ifindex ||
- mlx5_nl_switch_info(nl_route, list[i].ifindex,
- &list[i].info) ||
- ((!list[i].info.representor && !list[i].info.master) &&
- mlx5_sysfs_switch_info(list[i].ifindex, &list[i].info))) {
- list[i].ifindex = 0;
- memset(&list[i].info, 0, sizeof(list[i].info));
- continue;
+ struct mlx5_dev_spawn_data list[np ? np : nd];
+
+ if (np > 1) {
+ /*
+ * Single IB device with multiple ports found,
+ * it may be E-Switch master device and representors.
+ * We have to perform identification trough the ports.
+ */
+ assert(nl_rdma >= 0);
+ assert(ns == 0);
+ assert(nd == 1);
+ for (i = 1; i <= np; ++i) {
+ list[ns].max_port = np;
+ list[ns].ibv_port = i;
+ list[ns].ibv_dev = ibv_match[0];
+ list[ns].eth_dev = NULL;
+ list[ns].pci_dev = pci_dev;
+ list[ns].ifindex = mlx5_nl_ifindex
+ (nl_rdma, list[ns].ibv_dev->name, i);
+ if (!list[ns].ifindex) {
+ /*
+ * No network interface index found for the
+ * specified port, it means there is no
+ * representor on this port. It's OK,
+ * there can be disabled ports, for example
+ * if sriov_numvfs < sriov_totalvfs.
+ */
+ continue;
+ }
+ ret = -1;
+ if (nl_route >= 0)
+ ret = mlx5_nl_switch_info
+ (nl_route,
+ list[ns].ifindex,
+ &list[ns].info);
+ if (ret || (!list[ns].info.representor &&
+ !list[ns].info.master)) {
+ /*
+ * We failed to recognize representors with
+ * Netlink, let's try to perform the task
+ * with sysfs.
+ */
+ ret = mlx5_sysfs_switch_info
+ (list[ns].ifindex,
+ &list[ns].info);
+ }
+ if (!ret && (list[ns].info.representor ^
+ list[ns].info.master))
+ ns++;
}
- }
- if (nl_rdma >= 0)
- close(nl_rdma);
- if (nl_route >= 0)
- close(nl_route);
- /* Count unidentified devices. */
- for (u = 0, i = 0; i != n; ++i)
- if (!list[i].info.master && !list[i].info.representor)
- ++u;
- if (u) {
- if (n == 1 && u == 1) {
- /* Case #2. */
- DRV_LOG(INFO, "no switch support detected");
- } else {
- /* Case #3. */
+ if (!ns) {
+ DRV_LOG(ERR,
+ "unable to recognize master/representors"
+ " on the IB device with multiple ports");
+ rte_errno = ENOENT;
+ ret = -rte_errno;
+ goto exit;
+ }
+ } else {
+ /*
+ * The existence of several matching entries (nd > 1) means
+ * port representors have been instantiated. No existing Verbs
+ * call nor sysfs entries can tell them apart, this can only
+ * be done through Netlink calls assuming kernel drivers are
+ * recent enough to support them.
+ *
+ * In the event of identification failure through Netlink,
+ * try again through sysfs, then:
+ *
+ * 1. A single IB device matches (nd == 1) with single
+ * port (np=0/1) and is not a representor, assume
+ * no switch support.
+ *
+ * 2. Otherwise no safe assumptions can be made;
+ * complain louder and bail out.
+ */
+ np = 1;
+ for (i = 0; i != nd; ++i) {
+ memset(&list[ns].info, 0, sizeof(list[ns].info));
+ list[ns].max_port = 1;
+ list[ns].ibv_port = 1;
+ list[ns].ibv_dev = ibv_match[i];
+ list[ns].eth_dev = NULL;
+ list[ns].pci_dev = pci_dev;
+ list[ns].ifindex = 0;
+ if (nl_rdma >= 0)
+ list[ns].ifindex = mlx5_nl_ifindex
+ (nl_rdma, list[ns].ibv_dev->name, 1);
+ if (!list[ns].ifindex) {
+ char ifname[IF_NAMESIZE];
+
+ /*
+ * Netlink failed, it may happen with old
+ * ib_core kernel driver (before 4.16).
+ * We can assume there is old driver because
+ * here we are processing single ports IB
+ * devices. Let's try sysfs to retrieve
+ * the ifindex. The method works for
+ * master device only.
+ */
+ if (nd > 1) {
+ /*
+ * Multiple devices found, assume
+ * representors, can not distinguish
+ * master/representor and retrieve
+ * ifindex via sysfs.
+ */
+ continue;
+ }
+ ret = mlx5_get_master_ifname
+ (ibv_match[i]->ibdev_path, &ifname);
+ if (!ret)
+ list[ns].ifindex =
+ if_nametoindex(ifname);
+ if (!list[ns].ifindex) {
+ /*
+ * No network interface index found
+ * for the specified device, it means
+ * there it is neither representor
+ * nor master.
+ */
+ continue;
+ }
+ }
+ ret = -1;
+ if (nl_route >= 0)
+ ret = mlx5_nl_switch_info
+ (nl_route,
+ list[ns].ifindex,
+ &list[ns].info);
+ if (ret || (!list[ns].info.representor &&
+ !list[ns].info.master)) {
+ /*
+ * We failed to recognize representors with
+ * Netlink, let's try to perform the task
+ * with sysfs.
+ */
+ ret = mlx5_sysfs_switch_info
+ (list[ns].ifindex,
+ &list[ns].info);
+ }
+ if (!ret && (list[ns].info.representor ^
+ list[ns].info.master)) {
+ ns++;
+ } else if ((nd == 1) &&
+ !list[ns].info.representor &&
+ !list[ns].info.master) {
+ /*
+ * Single IB device with
+ * one physical port and
+ * attached network device.
+ * May be SRIOV is not enabled
+ * or there is no representors.
+ */
+ DRV_LOG(INFO, "no E-Switch support detected");
+ ns++;
+ break;
+ }
+ }
+ if (!ns) {
DRV_LOG(ERR,
- "unable to tell which of the matching devices"
- " is the master (lack of kernel support?)");
- n = 0;
+ "unable to recognize master/representors"
+ " on the multiple IB devices");
+ rte_errno = ENOENT;
+ ret = -rte_errno;
+ goto exit;
}
}
+ assert(ns);
/*
* Sort list to probe devices in natural order for users convenience
* (i.e. master first, then representors from lowest to highest ID).
*/
- if (n)
- qsort(list, n, sizeof(*list), mlx5_dev_spawn_data_cmp);
+ 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,
+ .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 = MLX5_MPRQ_STRIDE_NUM_N,
+ .max_memcpy_len = MLX5_MPRQ_MEMCPY_DEFAULT_LEN,
+ .min_rxqs_num = MLX5_MPRQ_MIN_RXQS,
+ },
+ .dv_esw_en = 1,
+ };
+ /* Device specific configuration. */
switch (pci_dev->id.device_id) {
case PCI_DEVICE_ID_MELLANOX_CONNECTX4VF:
case PCI_DEVICE_ID_MELLANOX_CONNECTX4LXVF:
case PCI_DEVICE_ID_MELLANOX_CONNECTX5VF:
case PCI_DEVICE_ID_MELLANOX_CONNECTX5EXVF:
- vf = 1;
+ dev_config.vf = 1;
break;
default:
- vf = 0;
+ break;
}
- for (i = 0; i != n; ++i) {
+ for (i = 0; i != ns; ++i) {
uint32_t restore;
- list[i].eth_dev = mlx5_dev_spawn
- (&pci_dev->device, list[i].ibv_dev, vf, &list[i].info);
+ list[i].eth_dev = mlx5_dev_spawn(&pci_dev->device,
+ &list[i],
+ dev_config);
if (!list[i].eth_dev) {
- if (rte_errno != EBUSY)
+ if (rte_errno != EBUSY && rte_errno != EEXIST)
break;
- /* Device is disabled, ignore it. */
+ /* Device is disabled or already spawned. Ignore it. */
continue;
}
restore = list[i].eth_dev->data->dev_flags;
list[i].eth_dev->data->dev_flags |= restore;
rte_eth_dev_probing_finish(list[i].eth_dev);
}
- mlx5_glue->free_device_list(ibv_list);
- if (!n) {
- DRV_LOG(WARNING,
- "no Verbs device matches PCI device " PCI_PRI_FMT ","
- " are kernel drivers loaded?",
- pci_dev->addr.domain, pci_dev->addr.bus,
- pci_dev->addr.devid, pci_dev->addr.function);
- rte_errno = ENOENT;
- ret = -rte_errno;
- } else if (i != n) {
+ if (i != ns) {
DRV_LOG(ERR,
"probe of PCI device " PCI_PRI_FMT " aborted after"
" encountering an error: %s",
if (!list[i].eth_dev)
continue;
mlx5_dev_close(list[i].eth_dev);
- if (rte_eal_process_type() == RTE_PROC_PRIMARY)
- rte_free(list[i].eth_dev->data->dev_private);
+ /* mac_addrs must not be freed because in dev_private */
+ list[i].eth_dev->data->mac_addrs = NULL;
claim_zero(rte_eth_dev_release_port(list[i].eth_dev));
}
/* Restore original error. */
} else {
ret = 0;
}
+exit:
+ /*
+ * Do the routine cleanup:
+ * - close opened Netlink sockets
+ * - free the Infiniband device list
+ */
+ if (nl_rdma >= 0)
+ close(nl_rdma);
+ if (nl_route >= 0)
+ close(nl_route);
+ assert(ibv_list);
+ mlx5_glue->free_device_list(ibv_list);
return ret;
}
+/**
+ * DPDK callback to remove a PCI device.
+ *
+ * This function removes all Ethernet devices belong to a given PCI device.
+ *
+ * @param[in] pci_dev
+ * Pointer to the PCI device.
+ *
+ * @return
+ * 0 on success, the function cannot fail.
+ */
+static int
+mlx5_pci_remove(struct rte_pci_device *pci_dev)
+{
+ uint16_t port_id;
+
+ RTE_ETH_FOREACH_DEV_OF(port_id, &pci_dev->device)
+ rte_eth_dev_close(port_id);
+ return 0;
+}
+
static const struct rte_pci_id mlx5_pci_id_map[] = {
{
RTE_PCI_DEVICE(PCI_VENDOR_ID_MELLANOX,
RTE_PCI_DEVICE(PCI_VENDOR_ID_MELLANOX,
PCI_DEVICE_ID_MELLANOX_CONNECTX5BF)
},
+ {
+ RTE_PCI_DEVICE(PCI_VENDOR_ID_MELLANOX,
+ PCI_DEVICE_ID_MELLANOX_CONNECTX5BFVF)
+ },
+ {
+ RTE_PCI_DEVICE(PCI_VENDOR_ID_MELLANOX,
+ PCI_DEVICE_ID_MELLANOX_CONNECTX6)
+ },
+ {
+ RTE_PCI_DEVICE(PCI_VENDOR_ID_MELLANOX,
+ PCI_DEVICE_ID_MELLANOX_CONNECTX6VF)
+ },
{
.vendor_id = 0
}
},
.id_table = mlx5_pci_id_map,
.probe = mlx5_pci_probe,
- .drv_flags = RTE_PCI_DRV_INTR_LSC | RTE_PCI_DRV_INTR_RMV,
+ .remove = mlx5_pci_remove,
+ .dma_map = mlx5_dma_map,
+ .dma_unmap = mlx5_dma_unmap,
+ .drv_flags = RTE_PCI_DRV_INTR_LSC | RTE_PCI_DRV_INTR_RMV |
+ RTE_PCI_DRV_PROBE_AGAIN,
};
-#ifdef RTE_LIBRTE_MLX5_DLOPEN_DEPS
+#ifdef RTE_IBVERBS_LINK_DLOPEN
/**
* Suffix RTE_EAL_PMD_PATH with "-glue".
* cleanup all the Verbs resources even when the device was removed.
*/
setenv("MLX5_DEVICE_FATAL_CLEANUP", "1", 1);
-#ifdef RTE_LIBRTE_MLX5_DLOPEN_DEPS
+#ifdef RTE_IBVERBS_LINK_DLOPEN
if (mlx5_glue_init())
return;
assert(mlx5_glue);
git.droids-corp.org / dpdk.git / blobdiff