#include <sys/mman.h>
#include <linux/rtnetlink.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 <mlx5_common.h>
#include <mlx5_common_os.h>
#include <mlx5_common_mp.h>
+#include <mlx5_common_pci.h>
+#include <mlx5_malloc.h>
#include "mlx5_defs.h"
#include "mlx5.h"
*/
#define MLX5_TXQ_MAX_INLINE_LEN "txq_max_inline_len"
+/*
+ * Device parameter to enable Tx scheduling on timestamps
+ * and specify the packet pacing granularity in nanoseconds.
+ */
+#define MLX5_TX_PP "tx_pp"
+
+/*
+ * Device parameter to specify skew in nanoseconds on Tx datapath,
+ * it represents the time between SQ start WQE processing and
+ * appearing actual packet data on the wire.
+ */
+#define MLX5_TX_SKEW "tx_skew"
+
/*
* Device parameter to enable hardware Tx vector.
* Deprecated, ignored (no vectorized Tx routines anymore).
/* Flow memory reclaim mode. */
#define MLX5_RECLAIM_MEM "reclaim_mem_mode"
-static const char *MZ_MLX5_PMD_SHARED_DATA = "mlx5_pmd_shared_data";
+/* The default memory allocator used in PMD. */
+#define MLX5_SYS_MEM_EN "sys_mem_en"
+/* Decap will be used or not. */
+#define MLX5_DECAP_EN "decap_en"
/* Shared memory between primary and secondary processes. */
struct mlx5_shared_data *mlx5_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;
+/** Driver-specific log messages type. */
+int mlx5_logtype;
static LIST_HEAD(, mlx5_dev_ctx_shared) mlx5_dev_ctx_list =
LIST_HEAD_INITIALIZER();
.grow_shift = 2,
.need_lock = 0,
.release_mem_en = 1,
- .malloc = rte_malloc_socket,
- .free = rte_free,
+ .malloc = mlx5_malloc,
+ .free = mlx5_free,
.type = "mlx5_encap_decap_ipool",
},
{
.grow_shift = 2,
.need_lock = 0,
.release_mem_en = 1,
- .malloc = rte_malloc_socket,
- .free = rte_free,
+ .malloc = mlx5_malloc,
+ .free = mlx5_free,
.type = "mlx5_push_vlan_ipool",
},
{
.grow_shift = 2,
.need_lock = 0,
.release_mem_en = 1,
- .malloc = rte_malloc_socket,
- .free = rte_free,
+ .malloc = mlx5_malloc,
+ .free = mlx5_free,
.type = "mlx5_tag_ipool",
},
{
.grow_shift = 2,
.need_lock = 0,
.release_mem_en = 1,
- .malloc = rte_malloc_socket,
- .free = rte_free,
+ .malloc = mlx5_malloc,
+ .free = mlx5_free,
.type = "mlx5_port_id_ipool",
},
{
.grow_shift = 2,
.need_lock = 0,
.release_mem_en = 1,
- .malloc = rte_malloc_socket,
- .free = rte_free,
+ .malloc = mlx5_malloc,
+ .free = mlx5_free,
.type = "mlx5_jump_ipool",
},
#endif
.grow_shift = 2,
.need_lock = 0,
.release_mem_en = 1,
- .malloc = rte_malloc_socket,
- .free = rte_free,
+ .malloc = mlx5_malloc,
+ .free = mlx5_free,
.type = "mlx5_meter_ipool",
},
{
.grow_shift = 2,
.need_lock = 0,
.release_mem_en = 1,
- .malloc = rte_malloc_socket,
- .free = rte_free,
+ .malloc = mlx5_malloc,
+ .free = mlx5_free,
.type = "mlx5_mcp_ipool",
},
{
.grow_shift = 2,
.need_lock = 0,
.release_mem_en = 1,
- .malloc = rte_malloc_socket,
- .free = rte_free,
+ .malloc = mlx5_malloc,
+ .free = mlx5_free,
.type = "mlx5_hrxq_ipool",
},
{
.grow_shift = 2,
.need_lock = 0,
.release_mem_en = 1,
- .malloc = rte_malloc_socket,
- .free = rte_free,
+ .malloc = mlx5_malloc,
+ .free = mlx5_free,
.type = "mlx5_flow_handle_ipool",
},
{
.trunk_size = 4096,
.need_lock = 1,
.release_mem_en = 1,
- .malloc = rte_malloc_socket,
- .free = rte_free,
+ .malloc = mlx5_malloc,
+ .free = mlx5_free,
.type = "rte_flow_ipool",
},
};
struct mlx5_flow_id_pool *pool;
void *mem;
- pool = rte_zmalloc("id pool allocation", sizeof(*pool),
- RTE_CACHE_LINE_SIZE);
+ pool = mlx5_malloc(MLX5_MEM_ZERO, sizeof(*pool),
+ RTE_CACHE_LINE_SIZE, SOCKET_ID_ANY);
if (!pool) {
DRV_LOG(ERR, "can't allocate id pool");
rte_errno = ENOMEM;
return NULL;
}
- mem = rte_zmalloc("", MLX5_FLOW_MIN_ID_POOL_SIZE * sizeof(uint32_t),
- RTE_CACHE_LINE_SIZE);
+ mem = mlx5_malloc(MLX5_MEM_ZERO,
+ MLX5_FLOW_MIN_ID_POOL_SIZE * sizeof(uint32_t),
+ RTE_CACHE_LINE_SIZE, SOCKET_ID_ANY);
if (!mem) {
DRV_LOG(ERR, "can't allocate mem for id pool");
rte_errno = ENOMEM;
pool->max_id = max_id;
return pool;
error:
- rte_free(pool);
+ mlx5_free(pool);
return NULL;
}
void
mlx5_flow_id_pool_release(struct mlx5_flow_id_pool *pool)
{
- rte_free(pool->free_arr);
- rte_free(pool);
+ mlx5_free(pool->free_arr);
+ mlx5_free(pool);
}
/**
size = pool->curr - pool->free_arr;
size2 = size * MLX5_ID_GENERATION_ARRAY_FACTOR;
MLX5_ASSERT(size2 > size);
- mem = rte_malloc("", size2 * sizeof(uint32_t), 0);
+ mem = mlx5_malloc(0, size2 * sizeof(uint32_t), 0,
+ SOCKET_ID_ANY);
if (!mem) {
DRV_LOG(ERR, "can't allocate mem for id pool");
rte_errno = ENOMEM;
return -rte_errno;
}
memcpy(mem, pool->free_arr, size * sizeof(uint32_t));
- rte_free(pool->free_arr);
+ mlx5_free(pool->free_arr);
pool->free_arr = mem;
pool->curr = pool->free_arr + size;
pool->last = pool->free_arr + size2;
LIST_REMOVE(mng, next);
claim_zero(mlx5_devx_cmd_destroy(mng->dm));
claim_zero(mlx5_glue->devx_umem_dereg(mng->umem));
- rte_free(mem);
+ mlx5_free(mem);
}
/**
(pool, j)->dcs));
}
TAILQ_REMOVE(&sh->cmng.ccont[i].pool_list, pool, next);
- rte_free(pool);
+ mlx5_free(pool);
pool = TAILQ_FIRST(&sh->cmng.ccont[i].pool_list);
}
- rte_free(sh->cmng.ccont[i].pools);
+ mlx5_free(sh->cmng.ccont[i].pools);
}
mng = LIST_FIRST(&sh->cmng.mem_mngs);
while (mng) {
mlx5_ipool_destroy(sh->ipool[i]);
}
+/*
+ * Check if dynamic flex parser for eCPRI already exists.
+ *
+ * @param dev
+ * Pointer to Ethernet device structure.
+ *
+ * @return
+ * true on exists, false on not.
+ */
+bool
+mlx5_flex_parser_ecpri_exist(struct rte_eth_dev *dev)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_flex_parser_profiles *prf =
+ &priv->sh->fp[MLX5_FLEX_PARSER_ECPRI_0];
+
+ return !!prf->obj;
+}
+
+/*
+ * Allocation of a flex parser for eCPRI. Once created, this parser related
+ * resources will be held until the device is closed.
+ *
+ * @param dev
+ * Pointer to Ethernet device structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_flex_parser_ecpri_alloc(struct rte_eth_dev *dev)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_flex_parser_profiles *prf =
+ &priv->sh->fp[MLX5_FLEX_PARSER_ECPRI_0];
+ struct mlx5_devx_graph_node_attr node = {
+ .modify_field_select = 0,
+ };
+ uint32_t ids[8];
+ int ret;
+
+ if (!priv->config.hca_attr.parse_graph_flex_node) {
+ DRV_LOG(ERR, "Dynamic flex parser is not supported "
+ "for device %s.", priv->dev_data->name);
+ return -ENOTSUP;
+ }
+ node.header_length_mode = MLX5_GRAPH_NODE_LEN_FIXED;
+ /* 8 bytes now: 4B common header + 4B message body header. */
+ node.header_length_base_value = 0x8;
+ /* After MAC layer: Ether / VLAN. */
+ node.in[0].arc_parse_graph_node = MLX5_GRAPH_ARC_NODE_MAC;
+ /* Type of compared condition should be 0xAEFE in the L2 layer. */
+ node.in[0].compare_condition_value = RTE_ETHER_TYPE_ECPRI;
+ /* Sample #0: type in common header. */
+ node.sample[0].flow_match_sample_en = 1;
+ /* Fixed offset. */
+ node.sample[0].flow_match_sample_offset_mode = 0x0;
+ /* Only the 2nd byte will be used. */
+ node.sample[0].flow_match_sample_field_base_offset = 0x0;
+ /* Sample #1: message payload. */
+ node.sample[1].flow_match_sample_en = 1;
+ /* Fixed offset. */
+ node.sample[1].flow_match_sample_offset_mode = 0x0;
+ /*
+ * Only the first two bytes will be used right now, and its offset will
+ * start after the common header that with the length of a DW(u32).
+ */
+ node.sample[1].flow_match_sample_field_base_offset = sizeof(uint32_t);
+ prf->obj = mlx5_devx_cmd_create_flex_parser(priv->sh->ctx, &node);
+ if (!prf->obj) {
+ DRV_LOG(ERR, "Failed to create flex parser node object.");
+ return (rte_errno == 0) ? -ENODEV : -rte_errno;
+ }
+ prf->num = 2;
+ ret = mlx5_devx_cmd_query_parse_samples(prf->obj, ids, prf->num);
+ if (ret) {
+ DRV_LOG(ERR, "Failed to query sample IDs.");
+ return (rte_errno == 0) ? -ENODEV : -rte_errno;
+ }
+ prf->offset[0] = 0x0;
+ prf->offset[1] = sizeof(uint32_t);
+ prf->ids[0] = ids[0];
+ prf->ids[1] = ids[1];
+ return 0;
+}
+
+/*
+ * Destroy the flex parser node, including the parser itself, input / output
+ * arcs and DW samples. Resources could be reused then.
+ *
+ * @param dev
+ * Pointer to Ethernet device structure.
+ */
+static void
+mlx5_flex_parser_ecpri_release(struct rte_eth_dev *dev)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_flex_parser_profiles *prf =
+ &priv->sh->fp[MLX5_FLEX_PARSER_ECPRI_0];
+
+ if (prf->obj)
+ mlx5_devx_cmd_destroy(prf->obj);
+ prf->obj = NULL;
+}
+
+/*
+ * Allocate Rx and Tx UARs in robust fashion.
+ * This routine handles the following UAR allocation issues:
+ *
+ * - tries to allocate the UAR with the most appropriate memory
+ * mapping type from the ones supported by the host
+ *
+ * - tries to allocate the UAR with non-NULL base address
+ * OFED 5.0.x and Upstream rdma_core before v29 returned the NULL as
+ * UAR base address if UAR was not the first object in the UAR page.
+ * It caused the PMD failure and we should try to get another UAR
+ * till we get the first one with non-NULL base address returned.
+ */
+static int
+mlx5_alloc_rxtx_uars(struct mlx5_dev_ctx_shared *sh,
+ const struct mlx5_dev_config *config)
+{
+ uint32_t uar_mapping, retry;
+ int err = 0;
+
+ for (retry = 0; retry < MLX5_ALLOC_UAR_RETRY; ++retry) {
+#ifdef MLX5DV_UAR_ALLOC_TYPE_NC
+ /* Control the mapping type according to the settings. */
+ uar_mapping = (config->dbnc == MLX5_TXDB_NCACHED) ?
+ MLX5DV_UAR_ALLOC_TYPE_NC :
+ MLX5DV_UAR_ALLOC_TYPE_BF;
+#else
+ RTE_SET_USED(config);
+ /*
+ * It seems we have no way to control the memory mapping type
+ * for the UAR, the default "Write-Combining" type is supposed.
+ * The UAR initialization on queue creation queries the
+ * actual mapping type done by Verbs/kernel and setups the
+ * PMD datapath accordingly.
+ */
+ uar_mapping = 0;
+#endif
+ sh->tx_uar = mlx5_glue->devx_alloc_uar(sh->ctx, uar_mapping);
+#ifdef MLX5DV_UAR_ALLOC_TYPE_NC
+ if (!sh->tx_uar &&
+ uar_mapping == MLX5DV_UAR_ALLOC_TYPE_BF) {
+ if (config->dbnc == MLX5_TXDB_CACHED ||
+ config->dbnc == MLX5_TXDB_HEURISTIC)
+ DRV_LOG(WARNING, "Devarg tx_db_nc setting "
+ "is not supported by DevX");
+ /*
+ * In some environments like virtual machine
+ * the Write Combining mapped might be not supported
+ * and UAR allocation fails. We try "Non-Cached"
+ * mapping for the case. The tx_burst routines take
+ * the UAR mapping type into account on UAR setup
+ * on queue creation.
+ */
+ DRV_LOG(WARNING, "Failed to allocate Tx DevX UAR (BF)");
+ uar_mapping = MLX5DV_UAR_ALLOC_TYPE_NC;
+ sh->tx_uar = mlx5_glue->devx_alloc_uar
+ (sh->ctx, uar_mapping);
+ } else if (!sh->tx_uar &&
+ uar_mapping == MLX5DV_UAR_ALLOC_TYPE_NC) {
+ if (config->dbnc == MLX5_TXDB_NCACHED)
+ DRV_LOG(WARNING, "Devarg tx_db_nc settings "
+ "is not supported by DevX");
+ /*
+ * If Verbs/kernel does not support "Non-Cached"
+ * try the "Write-Combining".
+ */
+ DRV_LOG(WARNING, "Failed to allocate Tx DevX UAR (NC)");
+ uar_mapping = MLX5DV_UAR_ALLOC_TYPE_BF;
+ sh->tx_uar = mlx5_glue->devx_alloc_uar
+ (sh->ctx, uar_mapping);
+ }
+#endif
+ if (!sh->tx_uar) {
+ DRV_LOG(ERR, "Failed to allocate Tx DevX UAR (BF/NC)");
+ err = ENOMEM;
+ goto exit;
+ }
+ if (sh->tx_uar->base_addr)
+ break;
+ /*
+ * The UARs are allocated by rdma_core within the
+ * IB device context, on context closure all UARs
+ * will be freed, should be no memory/object leakage.
+ */
+ DRV_LOG(WARNING, "Retrying to allocate Tx DevX UAR");
+ sh->tx_uar = NULL;
+ }
+ /* Check whether we finally succeeded with valid UAR allocation. */
+ if (!sh->tx_uar) {
+ DRV_LOG(ERR, "Failed to allocate Tx DevX UAR (NULL base)");
+ err = ENOMEM;
+ goto exit;
+ }
+ for (retry = 0; retry < MLX5_ALLOC_UAR_RETRY; ++retry) {
+ uar_mapping = 0;
+ sh->devx_rx_uar = mlx5_glue->devx_alloc_uar
+ (sh->ctx, uar_mapping);
+#ifdef MLX5DV_UAR_ALLOC_TYPE_NC
+ if (!sh->devx_rx_uar &&
+ uar_mapping == MLX5DV_UAR_ALLOC_TYPE_BF) {
+ /*
+ * Rx UAR is used to control interrupts only,
+ * should be no datapath noticeable impact,
+ * can try "Non-Cached" mapping safely.
+ */
+ DRV_LOG(WARNING, "Failed to allocate Rx DevX UAR (BF)");
+ uar_mapping = MLX5DV_UAR_ALLOC_TYPE_NC;
+ sh->devx_rx_uar = mlx5_glue->devx_alloc_uar
+ (sh->ctx, uar_mapping);
+ }
+#endif
+ if (!sh->devx_rx_uar) {
+ DRV_LOG(ERR, "Failed to allocate Rx DevX UAR (BF/NC)");
+ err = ENOMEM;
+ goto exit;
+ }
+ if (sh->devx_rx_uar->base_addr)
+ break;
+ /*
+ * The UARs are allocated by rdma_core within the
+ * IB device context, on context closure all UARs
+ * will be freed, should be no memory/object leakage.
+ */
+ DRV_LOG(WARNING, "Retrying to allocate Rx DevX UAR");
+ sh->devx_rx_uar = NULL;
+ }
+ /* Check whether we finally succeeded with valid UAR allocation. */
+ if (!sh->devx_rx_uar) {
+ DRV_LOG(ERR, "Failed to allocate Rx DevX UAR (NULL base)");
+ err = ENOMEM;
+ }
+exit:
+ return err;
+}
+
/**
* Allocate shared device context. If there is multiport device the
* master and representors will share this context, if there is single
}
/* No device found, we have to create new shared context. */
MLX5_ASSERT(spawn->max_port);
- sh = rte_zmalloc("ethdev shared ib context",
+ sh = mlx5_malloc(MLX5_MEM_ZERO | MLX5_MEM_RTE,
sizeof(struct mlx5_dev_ctx_shared) +
spawn->max_port *
sizeof(struct mlx5_dev_shared_port),
- RTE_CACHE_LINE_SIZE);
+ RTE_CACHE_LINE_SIZE, SOCKET_ID_ANY);
if (!sh) {
DRV_LOG(ERR, "shared context allocation failure");
rte_errno = ENOMEM;
err = ENOMEM;
goto error;
}
+ err = mlx5_alloc_rxtx_uars(sh, config);
+ if (err)
+ goto error;
+ MLX5_ASSERT(sh->tx_uar && sh->tx_uar->base_addr);
+ MLX5_ASSERT(sh->devx_rx_uar && sh->devx_rx_uar->base_addr);
}
sh->flow_id_pool = mlx5_flow_id_pool_alloc
((1 << HAIRPIN_FLOW_ID_BITS) - 1);
err = ENOMEM;
goto error;
}
+#ifndef RTE_ARCH_64
+ /* Initialize UAR access locks for 32bit implementations. */
+ rte_spinlock_init(&sh->uar_lock_cq);
+ for (i = 0; i < MLX5_UAR_PAGE_NUM_MAX; i++)
+ rte_spinlock_init(&sh->uar_lock[i]);
+#endif
/*
* Once the device is added to the list of memory event
* callback, its global MR cache table cannot be expanded
pthread_mutex_unlock(&mlx5_dev_ctx_list_mutex);
return sh;
error:
+ pthread_mutex_destroy(&sh->txpp.mutex);
pthread_mutex_unlock(&mlx5_dev_ctx_list_mutex);
MLX5_ASSERT(sh);
- if (sh->cnt_id_tbl) {
+ if (sh->cnt_id_tbl)
mlx5_l3t_destroy(sh->cnt_id_tbl);
- sh->cnt_id_tbl = NULL;
- }
if (sh->tis)
claim_zero(mlx5_devx_cmd_destroy(sh->tis));
if (sh->td)
claim_zero(mlx5_devx_cmd_destroy(sh->td));
+ if (sh->devx_rx_uar)
+ mlx5_glue->devx_free_uar(sh->devx_rx_uar);
+ if (sh->tx_uar)
+ mlx5_glue->devx_free_uar(sh->tx_uar);
if (sh->pd)
claim_zero(mlx5_glue->dealloc_pd(sh->pd));
if (sh->ctx)
claim_zero(mlx5_glue->close_device(sh->ctx));
if (sh->flow_id_pool)
mlx5_flow_id_pool_release(sh->flow_id_pool);
- rte_free(sh);
+ mlx5_free(sh);
MLX5_ASSERT(err > 0);
rte_errno = err;
return NULL;
mlx5_mr_release_cache(&sh->share_cache);
/* Remove context from the global device list. */
LIST_REMOVE(sh, next);
+ pthread_mutex_unlock(&mlx5_dev_ctx_list_mutex);
/*
* Ensure there is no async event handler installed.
* Only primary process handles async device events.
mlx5_l3t_destroy(sh->cnt_id_tbl);
sh->cnt_id_tbl = NULL;
}
+ if (sh->tx_uar) {
+ mlx5_glue->devx_free_uar(sh->tx_uar);
+ sh->tx_uar = NULL;
+ }
if (sh->pd)
claim_zero(mlx5_glue->dealloc_pd(sh->pd));
if (sh->tis)
claim_zero(mlx5_devx_cmd_destroy(sh->tis));
if (sh->td)
claim_zero(mlx5_devx_cmd_destroy(sh->td));
+ if (sh->devx_rx_uar)
+ mlx5_glue->devx_free_uar(sh->devx_rx_uar);
if (sh->ctx)
claim_zero(mlx5_glue->close_device(sh->ctx));
if (sh->flow_id_pool)
mlx5_flow_id_pool_release(sh->flow_id_pool);
- rte_free(sh);
+ pthread_mutex_destroy(&sh->txpp.mutex);
+ mlx5_free(sh);
+ return;
exit:
pthread_mutex_unlock(&mlx5_dev_ctx_list_mutex);
}
entry);
MLX5_ASSERT(tbl_data);
mlx5_hlist_remove(sh->flow_tbls, pos);
- rte_free(tbl_data);
+ mlx5_free(tbl_data);
}
table_key.direction = 1;
pos = mlx5_hlist_lookup(sh->flow_tbls, table_key.v64);
entry);
MLX5_ASSERT(tbl_data);
mlx5_hlist_remove(sh->flow_tbls, pos);
- rte_free(tbl_data);
+ mlx5_free(tbl_data);
}
table_key.direction = 0;
table_key.domain = 1;
entry);
MLX5_ASSERT(tbl_data);
mlx5_hlist_remove(sh->flow_tbls, pos);
- rte_free(tbl_data);
+ mlx5_free(tbl_data);
}
mlx5_hlist_destroy(sh->flow_tbls, NULL, NULL);
}
.direction = 0,
}
};
- struct mlx5_flow_tbl_data_entry *tbl_data = rte_zmalloc(NULL,
- sizeof(*tbl_data), 0);
+ struct mlx5_flow_tbl_data_entry *tbl_data = mlx5_malloc(MLX5_MEM_ZERO,
+ sizeof(*tbl_data), 0,
+ SOCKET_ID_ANY);
if (!tbl_data) {
err = ENOMEM;
rte_atomic32_init(&tbl_data->tbl.refcnt);
rte_atomic32_inc(&tbl_data->tbl.refcnt);
table_key.direction = 1;
- tbl_data = rte_zmalloc(NULL, sizeof(*tbl_data), 0);
+ tbl_data = mlx5_malloc(MLX5_MEM_ZERO, sizeof(*tbl_data), 0,
+ SOCKET_ID_ANY);
if (!tbl_data) {
err = ENOMEM;
goto error;
rte_atomic32_inc(&tbl_data->tbl.refcnt);
table_key.direction = 0;
table_key.domain = 1;
- tbl_data = rte_zmalloc(NULL, sizeof(*tbl_data), 0);
+ tbl_data = mlx5_malloc(MLX5_MEM_ZERO, sizeof(*tbl_data), 0,
+ SOCKET_ID_ANY);
if (!tbl_data) {
err = ENOMEM;
goto error;
return err;
}
-/**
- * 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;
-}
-
/**
* Retrieve integer value from environment variable.
*
*/
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);
+ ppriv = mlx5_malloc(MLX5_MEM_RTE, ppriv_size, RTE_CACHE_LINE_SIZE,
+ dev->device->numa_node);
if (!ppriv) {
rte_errno = ENOMEM;
return -rte_errno;
{
if (!dev->process_private)
return;
- rte_free(dev->process_private);
+ mlx5_free(dev->process_private);
dev->process_private = NULL;
}
dev->tx_pkt_burst = removed_tx_burst;
rte_wmb();
/* Disable datapath on secondary process. */
- mlx5_mp_req_stop_rxtx(dev);
+ mlx5_mp_os_req_stop_rxtx(dev);
+ /* Free the eCPRI flex parser resource. */
+ mlx5_flex_parser_ecpri_release(dev);
if (priv->rxqs != NULL) {
/* XXX race condition if mlx5_rx_burst() is still running. */
usleep(1000);
mlx5_mprq_free_mp(dev);
mlx5_os_free_shared_dr(priv);
if (priv->rss_conf.rss_key != NULL)
- rte_free(priv->rss_conf.rss_key);
+ mlx5_free(priv->rss_conf.rss_key);
if (priv->reta_idx != NULL)
- rte_free(priv->reta_idx);
+ mlx5_free(priv->reta_idx);
if (priv->config.vf)
mlx5_nl_mac_addr_flush(priv->nl_socket_route, mlx5_ifindex(dev),
dev->data->mac_addrs,
mlx5_args_check(const char *key, const char *val, void *opaque)
{
struct mlx5_dev_config *config = opaque;
- unsigned long tmp;
+ unsigned long mod;
+ signed long tmp;
/* No-op, port representors are processed in mlx5_dev_spawn(). */
if (!strcmp(MLX5_REPRESENTOR, key))
return 0;
errno = 0;
- tmp = strtoul(val, NULL, 0);
+ tmp = strtol(val, NULL, 0);
if (errno) {
rte_errno = errno;
DRV_LOG(WARNING, "%s: \"%s\" is not a valid integer", key, val);
return -rte_errno;
}
+ if (tmp < 0 && strcmp(MLX5_TX_PP, key) && strcmp(MLX5_TX_SKEW, key)) {
+ /* Negative values are acceptable for some keys only. */
+ rte_errno = EINVAL;
+ DRV_LOG(WARNING, "%s: invalid negative value \"%s\"", key, val);
+ return -rte_errno;
+ }
+ mod = tmp >= 0 ? tmp : -tmp;
if (strcmp(MLX5_RXQ_CQE_COMP_EN, key) == 0) {
config->cqe_comp = !!tmp;
} else if (strcmp(MLX5_RXQ_CQE_PAD_EN, key) == 0) {
config->txq_inline_mpw = tmp;
} else if (strcmp(MLX5_TX_VEC_EN, key) == 0) {
DRV_LOG(WARNING, "%s: deprecated parameter, ignored", key);
+ } else if (strcmp(MLX5_TX_PP, key) == 0) {
+ if (!mod) {
+ DRV_LOG(ERR, "Zero Tx packet pacing parameter");
+ rte_errno = EINVAL;
+ return -rte_errno;
+ }
+ config->tx_pp = tmp;
+ } else if (strcmp(MLX5_TX_SKEW, key) == 0) {
+ config->tx_skew = tmp;
} else if (strcmp(MLX5_RX_VEC_EN, key) == 0) {
config->rx_vec_en = !!tmp;
} else if (strcmp(MLX5_L3_VXLAN_EN, key) == 0) {
return -rte_errno;
}
config->reclaim_mode = tmp;
+ } else if (strcmp(MLX5_SYS_MEM_EN, key) == 0) {
+ config->sys_mem_en = !!tmp;
+ } else if (strcmp(MLX5_DECAP_EN, key) == 0) {
+ config->decap_en = !!tmp;
} else {
DRV_LOG(WARNING, "%s: unknown parameter", key);
rte_errno = EINVAL;
MLX5_TXQ_MPW_HDR_DSEG_EN,
MLX5_TXQ_MAX_INLINE_LEN,
MLX5_TX_DB_NC,
+ MLX5_TX_PP,
+ MLX5_TX_SKEW,
MLX5_TX_VEC_EN,
MLX5_RX_VEC_EN,
MLX5_L3_VXLAN_EN,
MLX5_CLASS_ARG_NAME,
MLX5_HP_BUF_SIZE,
MLX5_RECLAIM_MEM,
+ MLX5_SYS_MEM_EN,
+ MLX5_DECAP_EN,
NULL,
};
struct rte_kvargs *kvlist;
return 0;
}
-/**
- * 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.
- */
-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_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_secondary_handle);
- if (ret)
- goto out;
- ++sd->secondary_cnt;
- ld->init_done = true;
- break;
- default:
- break;
- }
-out:
- rte_spinlock_unlock(&sd->lock);
- return ret;
-}
-
/**
* Configures the minimal amount of data to inline into WQE
* while sending packets.
{
static const char *const dynf_names[] = {
RTE_PMD_MLX5_FINE_GRANULARITY_INLINE,
- RTE_MBUF_DYNFLAG_METADATA_NAME
+ RTE_MBUF_DYNFLAG_METADATA_NAME,
+ RTE_MBUF_DYNFLAG_TX_TIMESTAMP_NAME
};
unsigned int i;
}
};
-struct rte_pci_driver mlx5_driver = {
- .driver = {
- .name = MLX5_DRIVER_NAME
+static struct mlx5_pci_driver mlx5_driver = {
+ .driver_class = MLX5_CLASS_NET,
+ .pci_driver = {
+ .driver = {
+ .name = MLX5_DRIVER_NAME,
+ },
+ .id_table = mlx5_pci_id_map,
+ .probe = mlx5_os_pci_probe,
+ .remove = mlx5_pci_remove,
+ .dma_map = mlx5_dma_map,
+ .dma_unmap = mlx5_dma_unmap,
+ .drv_flags = PCI_DRV_FLAGS,
},
- .id_table = mlx5_pci_id_map,
- .probe = mlx5_os_pci_probe,
- .remove = mlx5_pci_remove,
- .dma_map = mlx5_dma_map,
- .dma_unmap = mlx5_dma_unmap,
- .drv_flags = PCI_DRV_FLAGS,
};
/* Initialize driver log type. */
*/
RTE_INIT(rte_mlx5_pmd_init)
{
+ mlx5_common_init();
/* Build the static tables for Verbs conversion. */
mlx5_set_ptype_table();
mlx5_set_cksum_table();
mlx5_set_swp_types_table();
if (mlx5_glue)
- rte_pci_register(&mlx5_driver);
+ mlx5_pci_driver_register(&mlx5_driver);
}
RTE_PMD_EXPORT_NAME(net_mlx5, __COUNTER__);
git.droids-corp.org / dpdk.git / blobdiff