X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fmlx4%2Fmlx4.c;h=315640a6d782dbafbbde2e8a73566b933f3fc2de;hb=0203d33a105982da3eeff5a890f4d60f23234304;hp=a29814b3b30e0da593bfbfe36be14e5d0de7bdb9;hpb=4423d4a112e29b5db48c2be349c9b3a5e245ca51;p=dpdk.git

diff --git a/drivers/net/mlx4/mlx4.c b/drivers/net/mlx4/mlx4.c
index a29814b3b3..315640a6d7 100644
--- a/drivers/net/mlx4/mlx4.c
+++ b/drivers/net/mlx4/mlx4.c
@@ -17,6 +17,7 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <sys/mman.h>
 #include <unistd.h>
 
 /* Verbs headers do not support -pedantic. */
@@ -48,10 +49,16 @@
 #include "mlx4_rxtx.h"
 #include "mlx4_utils.h"
 
-struct mlx4_dev_list mlx4_mem_event_cb_list =
-	LIST_HEAD_INITIALIZER(mlx4_mem_event_cb_list);
+static const char *MZ_MLX4_PMD_SHARED_DATA = "mlx4_pmd_shared_data";
 
-rte_rwlock_t mlx4_mem_event_rwlock = RTE_RWLOCK_INITIALIZER;
+/* Shared memory between primary and secondary processes. */
+struct mlx4_shared_data *mlx4_shared_data;
+
+/* Spinlock for mlx4_shared_data allocation. */
+static rte_spinlock_t mlx4_shared_data_lock = RTE_SPINLOCK_INITIALIZER;
+
+/* Process local data for secondary processes. */
+static struct mlx4_local_data mlx4_local_data;
 
 /** Configuration structure for device arguments. */
 struct mlx4_conf {
@@ -69,6 +76,133 @@ const char *pmd_mlx4_init_params[] = {
 
 static void mlx4_dev_stop(struct rte_eth_dev *dev);
 
+/**
+ * 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
+mlx4_init_shared_data(void)
+{
+	const struct rte_memzone *mz;
+	int ret = 0;
+
+	rte_spinlock_lock(&mlx4_shared_data_lock);
+	if (mlx4_shared_data == NULL) {
+		if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
+			/* Allocate shared memory. */
+			mz = rte_memzone_reserve(MZ_MLX4_PMD_SHARED_DATA,
+						 sizeof(*mlx4_shared_data),
+						 SOCKET_ID_ANY, 0);
+			if (mz == NULL) {
+				ERROR("Cannot allocate mlx4 shared data\n");
+				ret = -rte_errno;
+				goto error;
+			}
+			mlx4_shared_data = mz->addr;
+			memset(mlx4_shared_data, 0, sizeof(*mlx4_shared_data));
+			rte_spinlock_init(&mlx4_shared_data->lock);
+		} else {
+			/* Lookup allocated shared memory. */
+			mz = rte_memzone_lookup(MZ_MLX4_PMD_SHARED_DATA);
+			if (mz == NULL) {
+				ERROR("Cannot attach mlx4 shared data\n");
+				ret = -rte_errno;
+				goto error;
+			}
+			mlx4_shared_data = mz->addr;
+			memset(&mlx4_local_data, 0, sizeof(mlx4_local_data));
+		}
+	}
+error:
+	rte_spinlock_unlock(&mlx4_shared_data_lock);
+	return ret;
+}
+
+/**
+ * Uninitialize shared data between primary and secondary process.
+ *
+ * The pointer of secondary process is dereferenced and primary process frees
+ * the memzone.
+ */
+static void
+mlx4_uninit_shared_data(void)
+{
+	const struct rte_memzone *mz;
+
+	rte_spinlock_lock(&mlx4_shared_data_lock);
+	if (mlx4_shared_data) {
+		if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
+			mz = rte_memzone_lookup(MZ_MLX4_PMD_SHARED_DATA);
+			rte_memzone_free(mz);
+		} else {
+			memset(&mlx4_local_data, 0, sizeof(mlx4_local_data));
+		}
+		mlx4_shared_data = NULL;
+	}
+	rte_spinlock_unlock(&mlx4_shared_data_lock);
+}
+
+#ifdef HAVE_IBV_MLX4_BUF_ALLOCATORS
+/**
+ * Verbs callback to allocate a memory. This function should allocate the space
+ * according to the size provided residing inside a huge page.
+ * Please note that all allocation must respect the alignment from libmlx4
+ * (i.e. currently sysconf(_SC_PAGESIZE)).
+ *
+ * @param[in] size
+ *   The size in bytes of the memory to allocate.
+ * @param[in] data
+ *   A pointer to the callback data.
+ *
+ * @return
+ *   Allocated buffer, NULL otherwise and rte_errno is set.
+ */
+static void *
+mlx4_alloc_verbs_buf(size_t size, void *data)
+{
+	struct mlx4_priv *priv = data;
+	void *ret;
+	size_t alignment = sysconf(_SC_PAGESIZE);
+	unsigned int socket = SOCKET_ID_ANY;
+
+	if (priv->verbs_alloc_ctx.type == MLX4_VERBS_ALLOC_TYPE_TX_QUEUE) {
+		const struct txq *txq = priv->verbs_alloc_ctx.obj;
+
+		socket = txq->socket;
+	} else if (priv->verbs_alloc_ctx.type ==
+		   MLX4_VERBS_ALLOC_TYPE_RX_QUEUE) {
+		const struct rxq *rxq = priv->verbs_alloc_ctx.obj;
+
+		socket = rxq->socket;
+	}
+	assert(data != NULL);
+	ret = rte_malloc_socket(__func__, size, alignment, socket);
+	if (!ret && size)
+		rte_errno = ENOMEM;
+	return ret;
+}
+
+/**
+ * Verbs callback to free a memory.
+ *
+ * @param[in] ptr
+ *   A pointer to the memory to free.
+ * @param[in] data
+ *   A pointer to the callback data.
+ */
+static void
+mlx4_free_verbs_buf(void *ptr, void *data __rte_unused)
+{
+	assert(data != NULL);
+	rte_free(ptr);
+}
+#endif
+
 /**
  * DPDK callback for Ethernet device configuration.
  *
@@ -81,7 +215,7 @@ static void mlx4_dev_stop(struct rte_eth_dev *dev);
 static int
 mlx4_dev_configure(struct rte_eth_dev *dev)
 {
-	struct priv *priv = dev->data->dev_private;
+	struct mlx4_priv *priv = dev->data->dev_private;
 	struct rte_flow_error error;
 	int ret;
 
@@ -117,7 +251,7 @@ exit:
 static int
 mlx4_dev_start(struct rte_eth_dev *dev)
 {
-	struct priv *priv = dev->data->dev_private;
+	struct mlx4_priv *priv = dev->data->dev_private;
 	struct rte_flow_error error;
 	int ret;
 
@@ -125,6 +259,11 @@ mlx4_dev_start(struct rte_eth_dev *dev)
 		return 0;
 	DEBUG("%p: attaching configured flows to all RX queues", (void *)dev);
 	priv->started = 1;
+	ret = mlx4_tx_uar_remap(dev, priv->ctx->cmd_fd);
+	if (ret) {
+		ERROR("%p: cannot remap UAR", (void *)dev);
+		goto err;
+	}
 	ret = mlx4_rss_init(priv);
 	if (ret) {
 		ERROR("%p: cannot initialize RSS resources: %s",
@@ -152,6 +291,8 @@ mlx4_dev_start(struct rte_eth_dev *dev)
 	rte_wmb();
 	dev->tx_pkt_burst = mlx4_tx_burst;
 	dev->rx_pkt_burst = mlx4_rx_burst;
+	/* Enable datapath on secondary process. */
+	mlx4_mp_req_start_rxtx(dev);
 	return 0;
 err:
 	mlx4_dev_stop(dev);
@@ -169,7 +310,9 @@ err:
 static void
 mlx4_dev_stop(struct rte_eth_dev *dev)
 {
-	struct priv *priv = dev->data->dev_private;
+	struct mlx4_priv *priv = dev->data->dev_private;
+	const size_t page_size = sysconf(_SC_PAGESIZE);
+	int i;
 
 	if (!priv->started)
 		return;
@@ -178,9 +321,20 @@ mlx4_dev_stop(struct rte_eth_dev *dev)
 	dev->tx_pkt_burst = mlx4_tx_burst_removed;
 	dev->rx_pkt_burst = mlx4_rx_burst_removed;
 	rte_wmb();
+	/* Disable datapath on secondary process. */
+	mlx4_mp_req_stop_rxtx(dev);
 	mlx4_flow_sync(priv, NULL);
 	mlx4_rxq_intr_disable(priv);
 	mlx4_rss_deinit(priv);
+	for (i = 0; i != dev->data->nb_tx_queues; ++i) {
+		struct txq *txq;
+
+		txq = dev->data->tx_queues[i];
+		if (!txq)
+			continue;
+		munmap((void *)RTE_ALIGN_FLOOR((uintptr_t)txq->msq.db,
+					       page_size), page_size);
+	}
 }
 
 /**
@@ -194,7 +348,7 @@ mlx4_dev_stop(struct rte_eth_dev *dev)
 static void
 mlx4_dev_close(struct rte_eth_dev *dev)
 {
-	struct priv *priv = dev->data->dev_private;
+	struct mlx4_priv *priv = dev->data->dev_private;
 	unsigned int i;
 
 	DEBUG("%p: closing device \"%s\"",
@@ -203,6 +357,8 @@ mlx4_dev_close(struct rte_eth_dev *dev)
 	dev->rx_pkt_burst = mlx4_rx_burst_removed;
 	dev->tx_pkt_burst = mlx4_tx_burst_removed;
 	rte_wmb();
+	/* Disable datapath on secondary process. */
+	mlx4_mp_req_stop_rxtx(dev);
 	mlx4_flow_clean(priv);
 	mlx4_rss_deinit(priv);
 	for (i = 0; i != dev->data->nb_rx_queues; ++i)
@@ -237,6 +393,7 @@ static const struct eth_dev_ops mlx4_dev_ops = {
 	.mac_addr_set = mlx4_mac_addr_set,
 	.stats_get = mlx4_stats_get,
 	.stats_reset = mlx4_stats_reset,
+	.fw_version_get = mlx4_fw_version_get,
 	.dev_infos_get = mlx4_dev_infos_get,
 	.dev_supported_ptypes_get = mlx4_dev_supported_ptypes_get,
 	.vlan_filter_set = mlx4_vlan_filter_set,
@@ -253,6 +410,14 @@ static const struct eth_dev_ops mlx4_dev_ops = {
 	.is_removed = mlx4_is_removed,
 };
 
+/* Available operations from secondary process. */
+static const struct eth_dev_ops mlx4_dev_sec_ops = {
+	.stats_get = mlx4_stats_get,
+	.stats_reset = mlx4_stats_reset,
+	.fw_version_get = mlx4_fw_version_get,
+	.dev_infos_get = mlx4_dev_infos_get,
+};
+
 /**
  * Get PCI information from struct ibv_device.
  *
@@ -492,6 +657,200 @@ mlx4_hw_rss_sup(struct ibv_context *ctx, struct ibv_pd *pd,
 
 static struct rte_pci_driver mlx4_driver;
 
+static int
+find_lower_va_bound(const struct rte_memseg_list *msl,
+		const struct rte_memseg *ms, void *arg)
+{
+	void **addr = arg;
+
+	if (msl->external)
+		return 0;
+	if (*addr == NULL)
+		*addr = ms->addr;
+	else
+		*addr = RTE_MIN(*addr, ms->addr);
+
+	return 0;
+}
+
+/**
+ * Reserve UAR address space for primary process.
+ *
+ * Process local resource is 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.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx4_uar_init_primary(void)
+{
+	struct mlx4_shared_data *sd = mlx4_shared_data;
+	void *addr = (void *)0;
+
+	if (sd->uar_base)
+		return 0;
+	/* 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)(MLX4_UAR_OFFSET + MLX4_UAR_SIZE));
+	/* anonymous mmap, no real memory consumption. */
+	addr = mmap(addr, MLX4_UAR_SIZE,
+		    PROT_NONE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	if (addr == MAP_FAILED) {
+		ERROR("failed to reserve UAR address space, please"
+		      " adjust MLX4_UAR_SIZE or try --base-virtaddr");
+		rte_errno = ENOMEM;
+		return -rte_errno;
+	}
+	/* Accept either same addr or a new addr returned from mmap if target
+	 * range occupied.
+	 */
+	INFO("reserved UAR address space: %p", addr);
+	sd->uar_base = addr; /* for primary and secondary UAR re-mmap. */
+	return 0;
+}
+
+/**
+ * Unmap UAR address space reserved for primary process.
+ */
+static void
+mlx4_uar_uninit_primary(void)
+{
+	struct mlx4_shared_data *sd = mlx4_shared_data;
+
+	if (!sd->uar_base)
+		return;
+	munmap(sd->uar_base, MLX4_UAR_SIZE);
+	sd->uar_base = NULL;
+}
+
+/**
+ * Reserve UAR address space for secondary process, align with primary process.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx4_uar_init_secondary(void)
+{
+	struct mlx4_shared_data *sd = mlx4_shared_data;
+	struct mlx4_local_data *ld = &mlx4_local_data;
+	void *addr;
+
+	if (ld->uar_base) { /* Already reserved. */
+		assert(sd->uar_base == ld->uar_base);
+		return 0;
+	}
+	assert(sd->uar_base);
+	/* anonymous mmap, no real memory consumption. */
+	addr = mmap(sd->uar_base, MLX4_UAR_SIZE,
+		    PROT_NONE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	if (addr == MAP_FAILED) {
+		ERROR("UAR mmap failed: %p size: %llu",
+		      sd->uar_base, MLX4_UAR_SIZE);
+		rte_errno = ENXIO;
+		return -rte_errno;
+	}
+	if (sd->uar_base != addr) {
+		ERROR("UAR address %p size %llu occupied, please"
+		      " adjust MLX4_UAR_OFFSET or try EAL parameter"
+		      " --base-virtaddr",
+		      sd->uar_base, MLX4_UAR_SIZE);
+		rte_errno = ENXIO;
+		return -rte_errno;
+	}
+	ld->uar_base = addr;
+	INFO("reserved UAR address space: %p", addr);
+	return 0;
+}
+
+/**
+ * Unmap UAR address space reserved for secondary process.
+ */
+static void
+mlx4_uar_uninit_secondary(void)
+{
+	struct mlx4_local_data *ld = &mlx4_local_data;
+
+	if (!ld->uar_base)
+		return;
+	munmap(ld->uar_base, MLX4_UAR_SIZE);
+	ld->uar_base = NULL;
+}
+
+/**
+ * PMD global initialization.
+ *
+ * Independent from individual device, this function initializes global
+ * per-PMD data structures distinguishing primary and secondary processes.
+ * Hence, each initialization is called once per a process.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx4_init_once(void)
+{
+	struct mlx4_shared_data *sd;
+	struct mlx4_local_data *ld = &mlx4_local_data;
+	int ret;
+
+	if (mlx4_init_shared_data())
+		return -rte_errno;
+	sd = mlx4_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("MLX4_MEM_EVENT_CB",
+						mlx4_mr_mem_event_cb, NULL);
+		mlx4_mp_init_primary();
+		ret = mlx4_uar_init_primary();
+		if (ret)
+			goto error;
+		sd->init_done = true;
+		break;
+	case RTE_PROC_SECONDARY:
+		if (ld->init_done)
+			break;
+		mlx4_mp_init_secondary();
+		ret = mlx4_uar_init_secondary();
+		if (ret)
+			goto error;
+		++sd->secondary_cnt;
+		ld->init_done = true;
+		break;
+	default:
+		break;
+	}
+	rte_spinlock_unlock(&sd->lock);
+	return 0;
+error:
+	switch (rte_eal_process_type()) {
+	case RTE_PROC_PRIMARY:
+		mlx4_uar_uninit_primary();
+		mlx4_mp_uninit_primary();
+		rte_mem_event_callback_unregister("MLX4_MEM_EVENT_CB", NULL);
+		break;
+	case RTE_PROC_SECONDARY:
+		mlx4_uar_uninit_secondary();
+		mlx4_mp_uninit_secondary();
+		break;
+	default:
+		break;
+	}
+	rte_spinlock_unlock(&sd->lock);
+	mlx4_uninit_shared_data();
+	return -rte_errno;
+}
+
 /**
  * DPDK callback to register a PCI device.
  *
@@ -522,6 +881,12 @@ mlx4_pci_probe(struct rte_pci_driver *pci_drv, struct rte_pci_device *pci_dev)
 	int i;
 
 	(void)pci_drv;
+	err = mlx4_init_once();
+	if (err) {
+		ERROR("unable to init PMD global data: %s",
+		      strerror(rte_errno));
+		return -rte_errno;
+	}
 	assert(pci_drv == &mlx4_driver);
 	list = mlx4_glue->get_device_list(&i);
 	if (list == NULL) {
@@ -575,14 +940,14 @@ mlx4_pci_probe(struct rte_pci_driver *pci_drv, struct rte_pci_device *pci_dev)
 	ibv_dev = list[i];
 	DEBUG("device opened");
 	if (mlx4_glue->query_device(attr_ctx, &device_attr)) {
-		rte_errno = ENODEV;
+		err = ENODEV;
 		goto error;
 	}
 	INFO("%u port(s) detected", device_attr.phys_port_cnt);
 	conf.ports.present |= (UINT64_C(1) << device_attr.phys_port_cnt) - 1;
 	if (mlx4_args(pci_dev->device.devargs, &conf)) {
 		ERROR("failed to process device arguments");
-		rte_errno = EINVAL;
+		err = EINVAL;
 		goto error;
 	}
 	/* Use all ports when none are defined */
@@ -590,7 +955,7 @@ mlx4_pci_probe(struct rte_pci_driver *pci_drv, struct rte_pci_device *pci_dev)
 		conf.ports.enabled = conf.ports.present;
 	/* Retrieve extended device attributes. */
 	if (mlx4_glue->query_device_ex(attr_ctx, NULL, &device_attr_ex)) {
-		rte_errno = ENODEV;
+		err = ENODEV;
 		goto error;
 	}
 	assert(device_attr.max_sge >= MLX4_MAX_SGE);
@@ -599,9 +964,10 @@ mlx4_pci_probe(struct rte_pci_driver *pci_drv, struct rte_pci_device *pci_dev)
 		struct ibv_context *ctx = NULL;
 		struct ibv_port_attr port_attr;
 		struct ibv_pd *pd = NULL;
-		struct priv *priv = NULL;
+		struct mlx4_priv *priv = NULL;
 		struct rte_eth_dev *eth_dev = NULL;
 		struct ether_addr mac;
+		char name[RTE_ETH_NAME_MAX_LEN];
 
 		/* If port is not enabled, skip. */
 		if (!(conf.ports.enabled & (1 << i)))
@@ -609,18 +975,63 @@ mlx4_pci_probe(struct rte_pci_driver *pci_drv, struct rte_pci_device *pci_dev)
 		DEBUG("using port %u", port);
 		ctx = mlx4_glue->open_device(ibv_dev);
 		if (ctx == NULL) {
-			rte_errno = ENODEV;
+			err = ENODEV;
 			goto port_error;
 		}
+		snprintf(name, sizeof(name), "%s port %u",
+			 mlx4_glue->get_device_name(ibv_dev), port);
+		if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
+			eth_dev = rte_eth_dev_attach_secondary(name);
+			if (eth_dev == NULL) {
+				ERROR("can not attach rte ethdev");
+				rte_errno = ENOMEM;
+				err = rte_errno;
+				goto error;
+			}
+			priv = eth_dev->data->dev_private;
+			if (!priv->verbs_alloc_ctx.enabled) {
+				ERROR("secondary process is not supported"
+				      " due to lack of external allocator"
+				      " from Verbs");
+				rte_errno = ENOTSUP;
+				err = rte_errno;
+				goto error;
+			}
+			eth_dev->device = &pci_dev->device;
+			eth_dev->dev_ops = &mlx4_dev_sec_ops;
+			/* Receive command fd from primary process. */
+			err = mlx4_mp_req_verbs_cmd_fd(eth_dev);
+			if (err < 0) {
+				err = rte_errno;
+				goto error;
+			}
+			/* Remap UAR for Tx queues. */
+			err = mlx4_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->tx_pkt_burst = mlx4_tx_burst;
+			eth_dev->rx_pkt_burst = mlx4_rx_burst;
+			claim_zero(mlx4_glue->close_device(ctx));
+			rte_eth_copy_pci_info(eth_dev, pci_dev);
+			rte_eth_dev_probing_finish(eth_dev);
+			continue;
+		}
 		/* Check port status. */
 		err = mlx4_glue->query_port(ctx, port, &port_attr);
 		if (err) {
-			rte_errno = err;
-			ERROR("port query failed: %s", strerror(rte_errno));
+			err = ENODEV;
+			ERROR("port query failed: %s", strerror(err));
 			goto port_error;
 		}
 		if (port_attr.link_layer != IBV_LINK_LAYER_ETHERNET) {
-			rte_errno = ENOTSUP;
+			err = ENOTSUP;
 			ERROR("port %d is not configured in Ethernet mode",
 			      port);
 			goto port_error;
@@ -630,15 +1041,16 @@ mlx4_pci_probe(struct rte_pci_driver *pci_drv, struct rte_pci_device *pci_dev)
 			      port, mlx4_glue->port_state_str(port_attr.state),
 			      port_attr.state);
 		/* Make asynchronous FD non-blocking to handle interrupts. */
-		if (mlx4_fd_set_non_blocking(ctx->async_fd) < 0) {
+		err = mlx4_fd_set_non_blocking(ctx->async_fd);
+		if (err) {
 			ERROR("cannot make asynchronous FD non-blocking: %s",
-			      strerror(rte_errno));
+			      strerror(err));
 			goto port_error;
 		}
 		/* Allocate protection domain. */
 		pd = mlx4_glue->alloc_pd(ctx);
 		if (pd == NULL) {
-			rte_errno = ENOMEM;
+			err = ENOMEM;
 			ERROR("PD allocation failure");
 			goto port_error;
 		}
@@ -647,7 +1059,7 @@ mlx4_pci_probe(struct rte_pci_driver *pci_drv, struct rte_pci_device *pci_dev)
 				   sizeof(*priv),
 				   RTE_CACHE_LINE_SIZE);
 		if (priv == NULL) {
-			rte_errno = ENOMEM;
+			err = ENOMEM;
 			ERROR("priv allocation failure");
 			goto port_error;
 		}
@@ -672,14 +1084,27 @@ mlx4_pci_probe(struct rte_pci_driver *pci_drv, struct rte_pci_device *pci_dev)
 						   &device_attr_ex);
 		DEBUG("supported RSS hash fields mask: %016" PRIx64,
 		      priv->hw_rss_sup);
+		priv->hw_rss_max_qps =
+			device_attr_ex.rss_caps.max_rwq_indirection_table_size;
+		DEBUG("MAX RSS queues %d", priv->hw_rss_max_qps);
 		priv->hw_fcs_strip = !!(device_attr_ex.raw_packet_caps &
 					IBV_RAW_PACKET_CAP_SCATTER_FCS);
 		DEBUG("FCS stripping toggling is %ssupported",
 		      priv->hw_fcs_strip ? "" : "not ");
+		priv->tso =
+			((device_attr_ex.tso_caps.max_tso > 0) &&
+			 (device_attr_ex.tso_caps.supported_qpts &
+			  (1 << IBV_QPT_RAW_PACKET)));
+		if (priv->tso)
+			priv->tso_max_payload_sz =
+					device_attr_ex.tso_caps.max_tso;
+		DEBUG("TSO is %ssupported",
+		      priv->tso ? "" : "not ");
 		/* Configure the first MAC address by default. */
-		if (mlx4_get_mac(priv, &mac.addr_bytes)) {
+		err = mlx4_get_mac(priv, &mac.addr_bytes);
+		if (err) {
 			ERROR("cannot get MAC address, is mlx4_en loaded?"
-			      " (rte_errno: %s)", strerror(rte_errno));
+			      " (error: %s)", strerror(err));
 			goto port_error;
 		}
 		INFO("port %u MAC address is %02x:%02x:%02x:%02x:%02x:%02x",
@@ -703,24 +1128,16 @@ mlx4_pci_probe(struct rte_pci_driver *pci_drv, struct rte_pci_device *pci_dev)
 		/* Get actual MTU if possible. */
 		mlx4_mtu_get(priv, &priv->mtu);
 		DEBUG("port %u MTU is %u", priv->port, priv->mtu);
-		/* from rte_ethdev.c */
-		{
-			char name[RTE_ETH_NAME_MAX_LEN];
-
-			snprintf(name, sizeof(name), "%s port %u",
-				 mlx4_glue->get_device_name(ibv_dev), port);
-			eth_dev = rte_eth_dev_allocate(name);
-		}
+		eth_dev = rte_eth_dev_allocate(name);
 		if (eth_dev == NULL) {
+			err = ENOMEM;
 			ERROR("can not allocate rte ethdev");
-			rte_errno = ENOMEM;
 			goto port_error;
 		}
 		eth_dev->data->dev_private = priv;
 		eth_dev->data->mac_addrs = priv->mac;
 		eth_dev->device = &pci_dev->device;
 		rte_eth_copy_pci_info(eth_dev, pci_dev);
-		eth_dev->device->driver = &mlx4_driver.driver;
 		/* Initialize local interrupt handle for current port. */
 		priv->intr_handle = (struct rte_intr_handle){
 			.fd = -1,
@@ -739,11 +1156,26 @@ mlx4_pci_probe(struct rte_pci_driver *pci_drv, struct rte_pci_device *pci_dev)
 		 * handled by rte_intr_rx_ctl().
 		 */
 		eth_dev->intr_handle = &priv->intr_handle;
-		priv->dev = eth_dev;
+		priv->dev_data = eth_dev->data;
 		eth_dev->dev_ops = &mlx4_dev_ops;
+#ifdef HAVE_IBV_MLX4_BUF_ALLOCATORS
+		/* Hint libmlx4 to use PMD allocator for data plane resources */
+		struct mlx4dv_ctx_allocators alctr = {
+			.alloc = &mlx4_alloc_verbs_buf,
+			.free = &mlx4_free_verbs_buf,
+			.data = priv,
+		};
+		err = mlx4_glue->dv_set_context_attr
+			(ctx, MLX4DV_SET_CTX_ATTR_BUF_ALLOCATORS,
+			 (void *)((uintptr_t)&alctr));
+		if (err)
+			WARN("Verbs external allocator is not supported");
+		else
+			priv->verbs_alloc_ctx.enabled = 1;
+#endif
 		/* Bring Ethernet device up. */
 		DEBUG("forcing Ethernet interface up");
-		mlx4_dev_set_link_up(priv->dev);
+		mlx4_dev_set_link_up(eth_dev);
 		/* Update link status once if waiting for LSC. */
 		if (eth_dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC)
 			mlx4_link_update(eth_dev, 0);
@@ -761,23 +1193,27 @@ mlx4_pci_probe(struct rte_pci_driver *pci_drv, struct rte_pci_device *pci_dev)
 			goto port_error;
 		}
 		/* Add device to memory callback list. */
-		rte_rwlock_write_lock(&mlx4_mem_event_rwlock);
-		LIST_INSERT_HEAD(&mlx4_mem_event_cb_list, priv, mem_event_cb);
-		rte_rwlock_write_unlock(&mlx4_mem_event_rwlock);
+		rte_rwlock_write_lock(&mlx4_shared_data->mem_event_rwlock);
+		LIST_INSERT_HEAD(&mlx4_shared_data->mem_event_cb_list,
+				 priv, mem_event_cb);
+		rte_rwlock_write_unlock(&mlx4_shared_data->mem_event_rwlock);
 		rte_eth_dev_probing_finish(eth_dev);
 		continue;
 port_error:
 		rte_free(priv);
+		if (eth_dev != NULL)
+			eth_dev->data->dev_private = NULL;
 		if (pd)
 			claim_zero(mlx4_glue->dealloc_pd(pd));
 		if (ctx)
 			claim_zero(mlx4_glue->close_device(ctx));
-		if (eth_dev)
+		if (eth_dev != NULL) {
+			/* mac_addrs must not be freed because part of dev_private */
+			eth_dev->data->mac_addrs = NULL;
 			rte_eth_dev_release_port(eth_dev);
+		}
 		break;
 	}
-	if (i == device_attr.phys_port_cnt)
-		return 0;
 	/*
 	 * XXX if something went wrong in the loop above, there is a resource
 	 * leak (ctx, pd, priv, dpdk ethdev) but we can do nothing about it as
@@ -789,8 +1225,9 @@ error:
 		claim_zero(mlx4_glue->close_device(attr_ctx));
 	if (list)
 		mlx4_glue->free_device_list(list);
-	assert(rte_errno >= 0);
-	return -rte_errno;
+	if (err)
+		rte_errno = err;
+	return -err;
 }
 
 static const struct rte_pci_id mlx4_pci_id_map[] = {
@@ -821,7 +1258,7 @@ static struct rte_pci_driver mlx4_driver = {
 		     RTE_PCI_DRV_INTR_RMV,
 };
 
-#ifdef RTE_LIBRTE_MLX4_DLOPEN_DEPS
+#ifdef RTE_IBVERBS_LINK_DLOPEN
 
 /**
  * Suffix RTE_EAL_PMD_PATH with "-glue".
@@ -954,9 +1391,7 @@ glue_error:
 /**
  * Driver initialization routine.
  */
-RTE_INIT(rte_mlx4_pmd_init);
-static void
-rte_mlx4_pmd_init(void)
+RTE_INIT(rte_mlx4_pmd_init)
 {
 	/*
 	 * MLX4_DEVICE_FATAL_CLEANUP tells ibv_destroy functions we
@@ -971,7 +1406,7 @@ rte_mlx4_pmd_init(void)
 	 * using this PMD, which is not supported in forked processes.
 	 */
 	setenv("RDMAV_HUGEPAGES_SAFE", "1", 1);
-#ifdef RTE_LIBRTE_MLX4_DLOPEN_DEPS
+#ifdef RTE_IBVERBS_LINK_DLOPEN
 	if (mlx4_glue_init())
 		return;
 	assert(mlx4_glue);
@@ -992,8 +1427,6 @@ rte_mlx4_pmd_init(void)
 	}
 	mlx4_glue->fork_init();
 	rte_pci_register(&mlx4_driver);
-	rte_mem_event_callback_register("MLX4_MEM_EVENT_CB",
-					mlx4_mr_mem_event_cb, NULL);
 }
 
 RTE_PMD_EXPORT_NAME(net_mlx4, __COUNTER__);