[PATCH v5 4/5] drivers/net: not use private eth dev data

[Jianfeng Tan <jianfeng.tan@intel.com>]

We introduced private rte_eth_dev_data to allow vdev to be created
both in primary process and secondary process(es). This is not
friendly to multi-process model, for example, it leads to port id
contention issue if two processes both find the data entry is free.

And to get stats of primary vdev in secondary, we must allocate
from the pre-defined array so that we can find it.

Cc: John W. Linville <linville@tuxdriver.com>
Cc: Ferruh Yigit <ferruh.yigit@intel.com>
Cc: Tetsuya Mukawa <mtetsuyah@gmail.com>
Cc: Santosh Shukla <santosh.shukla@caviumnetworks.com>
Cc: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Cc: Pascal Mazon <pascal.mazon@6wind.com>
Cc: Maxime Coquelin <maxime.coquelin@redhat.com>
Cc: Bruce Richardson <bruce.richardson@intel.com>
Cc: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>

Suggested-by: Bruce Richardson <bruce.richardson@intel.com>
Signed-off-by: Jianfeng Tan <jianfeng.tan@intel.com>
Reviewed-by: Qi Zhang <qi.z.zhang@intel.com>
---
 drivers/net/af_packet/rte_eth_af_packet.c | 26 +++++++-------------------
 drivers/net/cxgbe/cxgbe_main.c            |  1 -
 drivers/net/kni/rte_eth_kni.c             | 14 ++------------
 drivers/net/null/rte_eth_null.c           | 19 ++++---------------
 drivers/net/octeontx/octeontx_ethdev.c    | 15 ++-------------
 drivers/net/pcap/rte_eth_pcap.c           | 19 +++----------------
 drivers/net/ring/rte_eth_ring.c           | 17 +----------------
 drivers/net/tap/rte_eth_tap.c             | 11 +----------
 drivers/net/vhost/rte_eth_vhost.c         | 19 ++-----------------
 9 files changed, 22 insertions(+), 119 deletions(-)

diff --git a/drivers/net/af_packet/rte_eth_af_packet.c b/drivers/net/af_packet/rte_eth_af_packet.c
index 57eccfd..110e8a5 100644
--- a/drivers/net/af_packet/rte_eth_af_packet.c
+++ b/drivers/net/af_packet/rte_eth_af_packet.c
@@ -564,25 +564,17 @@ rte_pmd_init_internals(struct rte_vdev_device *dev,
 		RTE_LOG(ERR, PMD,
 			"%s: no interface specified for AF_PACKET ethdev\n",
 		        name);
-		goto error_early;
+		return -1;
 	}
 
 	RTE_LOG(INFO, PMD,
 		"%s: creating AF_PACKET-backed ethdev on numa socket %u\n",
 		name, numa_node);
 
-	/*
-	 * now do all data allocation - for eth_dev structure, dummy pci driver
-	 * and internal (private) data
-	 */
-	data = rte_zmalloc_socket(name, sizeof(*data), 0, numa_node);
-	if (data == NULL)
-		goto error_early;
-
 	*internals = rte_zmalloc_socket(name, sizeof(**internals),
 	                                0, numa_node);
 	if (*internals == NULL)
-		goto error_early;
+		return -1;
 
 	for (q = 0; q < nb_queues; q++) {
 		(*internals)->rx_queue[q].map = MAP_FAILED;
@@ -604,24 +596,24 @@ rte_pmd_init_internals(struct rte_vdev_device *dev,
 		RTE_LOG(ERR, PMD,
 			"%s: I/F name too long (%s)\n",
 			name, pair->value);
-		goto error_early;
+		return -1;
 	}
 	if (ioctl(sockfd, SIOCGIFINDEX, &ifr) == -1) {
 		RTE_LOG(ERR, PMD,
 			"%s: ioctl failed (SIOCGIFINDEX)\n",
 		        name);
-		goto error_early;
+		return -1;
 	}
 	(*internals)->if_name = strdup(pair->value);
 	if ((*internals)->if_name == NULL)
-		goto error_early;
+		return -1;
 	(*internals)->if_index = ifr.ifr_ifindex;
 
 	if (ioctl(sockfd, SIOCGIFHWADDR, &ifr) == -1) {
 		RTE_LOG(ERR, PMD,
 			"%s: ioctl failed (SIOCGIFHWADDR)\n",
 		        name);
-		goto error_early;
+		return -1;
 	}
 	memcpy(&(*internals)->eth_addr, ifr.ifr_hwaddr.sa_data, ETH_ALEN);
 
@@ -775,14 +767,13 @@ rte_pmd_init_internals(struct rte_vdev_device *dev,
 
 	(*internals)->nb_queues = nb_queues;
 
-	rte_memcpy(data, (*eth_dev)->data, sizeof(*data));
+	data = (*eth_dev)->data;
 	data->dev_private = *internals;
 	data->nb_rx_queues = (uint16_t)nb_queues;
 	data->nb_tx_queues = (uint16_t)nb_queues;
 	data->dev_link = pmd_link;
 	data->mac_addrs = &(*internals)->eth_addr;
 
-	(*eth_dev)->data = data;
 	(*eth_dev)->dev_ops = &ops;
 
 	return 0;
@@ -802,8 +793,6 @@ rte_pmd_init_internals(struct rte_vdev_device *dev,
 	}
 	free((*internals)->if_name);
 	rte_free(*internals);
-error_early:
-	rte_free(data);
 	return -1;
 }
 
@@ -985,7 +974,6 @@ rte_pmd_af_packet_remove(struct rte_vdev_device *dev)
 	free(internals->if_name);
 
 	rte_free(eth_dev->data->dev_private);
-	rte_free(eth_dev->data);
 
 	rte_eth_dev_release_port(eth_dev);
 
diff --git a/drivers/net/cxgbe/cxgbe_main.c b/drivers/net/cxgbe/cxgbe_main.c
index c786a1a..74bccd5 100644
--- a/drivers/net/cxgbe/cxgbe_main.c
+++ b/drivers/net/cxgbe/cxgbe_main.c
@@ -29,7 +29,6 @@
 #include <rte_ether.h>
 #include <rte_ethdev_driver.h>
 #include <rte_ethdev_pci.h>
-#include <rte_malloc.h>
 #include <rte_random.h>
 #include <rte_dev.h>
 #include <rte_kvargs.h>
diff --git a/drivers/net/kni/rte_eth_kni.c b/drivers/net/kni/rte_eth_kni.c
index c10e970..b7897b6 100644
--- a/drivers/net/kni/rte_eth_kni.c
+++ b/drivers/net/kni/rte_eth_kni.c
@@ -336,25 +336,17 @@ eth_kni_create(struct rte_vdev_device *vdev,
 	struct pmd_internals *internals;
 	struct rte_eth_dev_data *data;
 	struct rte_eth_dev *eth_dev;
-	const char *name;
 
 	RTE_LOG(INFO, PMD, "Creating kni ethdev on numa socket %u\n",
 			numa_node);
 
-	name = rte_vdev_device_name(vdev);
-	data = rte_zmalloc_socket(name, sizeof(*data), 0, numa_node);
-	if (data == NULL)
-		return NULL;
-
 	/* reserve an ethdev entry */
 	eth_dev = rte_eth_vdev_allocate(vdev, sizeof(*internals));
-	if (eth_dev == NULL) {
-		rte_free(data);
+	if (!eth_dev)
 		return NULL;
-	}
 
 	internals = eth_dev->data->dev_private;
-	rte_memcpy(data, eth_dev->data, sizeof(*data));
+	data = eth_dev->data;
 	data->nb_rx_queues = 1;
 	data->nb_tx_queues = 1;
 	data->dev_link = pmd_link;
@@ -362,7 +354,6 @@ eth_kni_create(struct rte_vdev_device *vdev,
 
 	eth_random_addr(internals->eth_addr.addr_bytes);
 
-	eth_dev->data = data;
 	eth_dev->dev_ops = &eth_kni_ops;
 
 	internals->no_request_thread = args->no_request_thread;
@@ -458,7 +449,6 @@ eth_kni_remove(struct rte_vdev_device *vdev)
 	rte_kni_release(internals->kni);
 
 	rte_free(internals);
-	rte_free(eth_dev->data);
 
 	rte_eth_dev_release_port(eth_dev);
 
diff --git a/drivers/net/null/rte_eth_null.c b/drivers/net/null/rte_eth_null.c
index 74dde95..7d89a32 100644
--- a/drivers/net/null/rte_eth_null.c
+++ b/drivers/net/null/rte_eth_null.c
@@ -495,7 +495,7 @@ eth_dev_null_create(struct rte_vdev_device *dev,
 {
 	const unsigned nb_rx_queues = 1;
 	const unsigned nb_tx_queues = 1;
-	struct rte_eth_dev_data *data = NULL;
+	struct rte_eth_dev_data *data;
 	struct pmd_internals *internals = NULL;
 	struct rte_eth_dev *eth_dev = NULL;
 
@@ -512,19 +512,10 @@ eth_dev_null_create(struct rte_vdev_device *dev,
 	RTE_LOG(INFO, PMD, "Creating null ethdev on numa socket %u\n",
 		dev->device.numa_node);
 
-	/* now do all data allocation - for eth_dev structure, dummy pci driver
-	 * and internal (private) data
-	 */
-	data = rte_zmalloc_socket(rte_vdev_device_name(dev), sizeof(*data), 0,
-		dev->device.numa_node);
-	if (!data)
-		return -ENOMEM;
-
 	eth_dev = rte_eth_vdev_allocate(dev, sizeof(*internals));
-	if (!eth_dev) {
-		rte_free(data);
+	if (!eth_dev)
 		return -ENOMEM;
-	}
+
 	/* now put it all together
 	 * - store queue data in internals,
 	 * - store numa_node info in ethdev data
@@ -545,13 +536,12 @@ eth_dev_null_create(struct rte_vdev_device *dev,
 
 	rte_memcpy(internals->rss_key, default_rss_key, 40);
 
-	rte_memcpy(data, eth_dev->data, sizeof(*data));
+	data = eth_dev->data;
 	data->nb_rx_queues = (uint16_t)nb_rx_queues;
 	data->nb_tx_queues = (uint16_t)nb_tx_queues;
 	data->dev_link = pmd_link;
 	data->mac_addrs = &internals->eth_addr;
 
-	eth_dev->data = data;
 	eth_dev->dev_ops = &ops;
 
 	/* finally assign rx and tx ops */
@@ -669,7 +659,6 @@ rte_pmd_null_remove(struct rte_vdev_device *dev)
 		return -1;
 
 	rte_free(eth_dev->data->dev_private);
-	rte_free(eth_dev->data);
 
 	rte_eth_dev_release_port(eth_dev);
 
diff --git a/drivers/net/octeontx/octeontx_ethdev.c b/drivers/net/octeontx/octeontx_ethdev.c
index 6d67d25..ee06cd3 100644
--- a/drivers/net/octeontx/octeontx_ethdev.c
+++ b/drivers/net/octeontx/octeontx_ethdev.c
@@ -1068,7 +1068,7 @@ octeontx_create(struct rte_vdev_device *dev, int port, uint8_t evdev,
 	char octtx_name[OCTEONTX_MAX_NAME_LEN];
 	struct octeontx_nic *nic = NULL;
 	struct rte_eth_dev *eth_dev = NULL;
-	struct rte_eth_dev_data *data = NULL;
+	struct rte_eth_dev_data *data;
 	const char *name = rte_vdev_device_name(dev);
 
 	PMD_INIT_FUNC_TRACE();
@@ -1084,13 +1084,6 @@ octeontx_create(struct rte_vdev_device *dev, int port, uint8_t evdev,
 		return 0;
 	}
 
-	data = rte_zmalloc_socket(octtx_name, sizeof(*data), 0, socket_id);
-	if (data == NULL) {
-		octeontx_log_err("failed to allocate devdata");
-		res = -ENOMEM;
-		goto err;
-	}
-
 	nic = rte_zmalloc_socket(octtx_name, sizeof(*nic), 0, socket_id);
 	if (nic == NULL) {
 		octeontx_log_err("failed to allocate nic structure");
@@ -1126,11 +1119,9 @@ octeontx_create(struct rte_vdev_device *dev, int port, uint8_t evdev,
 	eth_dev->data->kdrv = RTE_KDRV_NONE;
 	eth_dev->data->numa_node = dev->device.numa_node;
 
-	rte_memcpy(data, (eth_dev)->data, sizeof(*data));
+	data = eth_dev->data;
 	data->dev_private = nic;
-
 	data->port_id = eth_dev->data->port_id;
-	snprintf(data->name, sizeof(data->name), "%s", eth_dev->data->name);
 
 	nic->ev_queues = 1;
 	nic->ev_ports = 1;
@@ -1149,7 +1140,6 @@ octeontx_create(struct rte_vdev_device *dev, int port, uint8_t evdev,
 		goto err;
 	}
 
-	eth_dev->data = data;
 	eth_dev->dev_ops = &octeontx_dev_ops;
 
 	/* Finally save ethdev pointer to the NIC structure */
@@ -1217,7 +1207,6 @@ octeontx_remove(struct rte_vdev_device *dev)
 
 		rte_free(eth_dev->data->mac_addrs);
 		rte_free(eth_dev->data->dev_private);
-		rte_free(eth_dev->data);
 		rte_eth_dev_release_port(eth_dev);
 		rte_event_dev_close(nic->evdev);
 	}
diff --git a/drivers/net/pcap/rte_eth_pcap.c b/drivers/net/pcap/rte_eth_pcap.c
index c1571e1..8740d52 100644
--- a/drivers/net/pcap/rte_eth_pcap.c
+++ b/drivers/net/pcap/rte_eth_pcap.c
@@ -773,27 +773,16 @@ pmd_init_internals(struct rte_vdev_device *vdev,
 		struct pmd_internals **internals,
 		struct rte_eth_dev **eth_dev)
 {
-	struct rte_eth_dev_data *data = NULL;
+	struct rte_eth_dev_data *data;
 	unsigned int numa_node = vdev->device.numa_node;
-	const char *name;
 
-	name = rte_vdev_device_name(vdev);
 	RTE_LOG(INFO, PMD, "Creating pcap-backed ethdev on numa socket %d\n",
 		numa_node);
 
-	/* now do all data allocation - for eth_dev structure
-	 * and internal (private) data
-	 */
-	data = rte_zmalloc_socket(name, sizeof(*data), 0, numa_node);
-	if (data == NULL)
-		return -1;
-
 	/* reserve an ethdev entry */
 	*eth_dev = rte_eth_vdev_allocate(vdev, sizeof(**internals));
-	if (*eth_dev == NULL) {
-		rte_free(data);
+	if (!(*eth_dev))
 		return -1;
-	}
 
 	/* now put it all together
 	 * - store queue data in internals,
@@ -802,7 +791,7 @@ pmd_init_internals(struct rte_vdev_device *vdev,
 	 * - and point eth_dev structure to new eth_dev_data structure
 	 */
 	*internals = (*eth_dev)->data->dev_private;
-	rte_memcpy(data, (*eth_dev)->data, sizeof(*data));
+	data = (*eth_dev)->data;
 	data->nb_rx_queues = (uint16_t)nb_rx_queues;
 	data->nb_tx_queues = (uint16_t)nb_tx_queues;
 	data->dev_link = pmd_link;
@@ -812,7 +801,6 @@ pmd_init_internals(struct rte_vdev_device *vdev,
 	 * NOTE: we'll replace the data element, of originally allocated
 	 * eth_dev so the rings are local per-process
 	 */
-	(*eth_dev)->data = data;
 	(*eth_dev)->dev_ops = &ops;
 
 	return 0;
@@ -1020,7 +1008,6 @@ pmd_pcap_remove(struct rte_vdev_device *dev)
 		return -1;
 
 	rte_free(eth_dev->data->dev_private);
-	rte_free(eth_dev->data);
 
 	rte_eth_dev_release_port(eth_dev);
 
diff --git a/drivers/net/ring/rte_eth_ring.c b/drivers/net/ring/rte_eth_ring.c
index df13c44..e53823a 100644
--- a/drivers/net/ring/rte_eth_ring.c
+++ b/drivers/net/ring/rte_eth_ring.c
@@ -259,15 +259,6 @@ do_eth_dev_ring_create(const char *name,
 	RTE_LOG(INFO, PMD, "Creating rings-backed ethdev on numa socket %u\n",
 			numa_node);
 
-	/* now do all data allocation - for eth_dev structure, dummy pci driver
-	 * and internal (private) data
-	 */
-	data = rte_zmalloc_socket(name, sizeof(*data), 0, numa_node);
-	if (data == NULL) {
-		rte_errno = ENOMEM;
-		goto error;
-	}
-
 	rx_queues_local = rte_zmalloc_socket(name,
 			sizeof(void *) * nb_rx_queues, 0, numa_node);
 	if (rx_queues_local == NULL) {
@@ -301,10 +292,8 @@ do_eth_dev_ring_create(const char *name,
 	 * - point eth_dev_data to internals
 	 * - and point eth_dev structure to new eth_dev_data structure
 	 */
-	/* NOTE: we'll replace the data element, of originally allocated eth_dev
-	 * so the rings are local per-process */
 
-	rte_memcpy(data, eth_dev->data, sizeof(*data));
+	data = eth_dev->data;
 	data->rx_queues = rx_queues_local;
 	data->tx_queues = tx_queues_local;
 
@@ -326,7 +315,6 @@ do_eth_dev_ring_create(const char *name,
 	data->dev_link = pmd_link;
 	data->mac_addrs = &internals->address;
 
-	eth_dev->data = data;
 	eth_dev->dev_ops = &ops;
 	data->kdrv = RTE_KDRV_NONE;
 	data->numa_node = numa_node;
@@ -342,7 +330,6 @@ do_eth_dev_ring_create(const char *name,
 error:
 	rte_free(rx_queues_local);
 	rte_free(tx_queues_local);
-	rte_free(data);
 	rte_free(internals);
 
 	return -1;
@@ -675,8 +662,6 @@ rte_pmd_ring_remove(struct rte_vdev_device *dev)
 	rte_free(eth_dev->data->tx_queues);
 	rte_free(eth_dev->data->dev_private);
 
-	rte_free(eth_dev->data);
-
 	rte_eth_dev_release_port(eth_dev);
 	return 0;
 }
diff --git a/drivers/net/tap/rte_eth_tap.c b/drivers/net/tap/rte_eth_tap.c
index 915d937..b18efd8 100644
--- a/drivers/net/tap/rte_eth_tap.c
+++ b/drivers/net/tap/rte_eth_tap.c
@@ -1386,12 +1386,6 @@ eth_dev_tap_create(struct rte_vdev_device *vdev, char *tap_name,
 	RTE_LOG(DEBUG, PMD, "%s device on numa %u\n",
 			tuntap_name, rte_socket_id());
 
-	data = rte_zmalloc_socket(tap_name, sizeof(*data), 0, numa_node);
-	if (!data) {
-		RTE_LOG(ERR, PMD, "%s Failed to allocate data\n", tuntap_name);
-		goto error_exit_nodev;
-	}
-
 	dev = rte_eth_vdev_allocate(vdev, sizeof(*pmd));
 	if (!dev) {
 		RTE_LOG(ERR, PMD, "%s Unable to allocate device struct\n",
@@ -1412,7 +1406,7 @@ eth_dev_tap_create(struct rte_vdev_device *vdev, char *tap_name,
 	}
 
 	/* Setup some default values */
-	rte_memcpy(data, dev->data, sizeof(*data));
+	data = dev->data;
 	data->dev_private = pmd;
 	data->dev_flags = RTE_ETH_DEV_INTR_LSC;
 	data->numa_node = numa_node;
@@ -1423,7 +1417,6 @@ eth_dev_tap_create(struct rte_vdev_device *vdev, char *tap_name,
 	data->nb_rx_queues = 0;
 	data->nb_tx_queues = 0;
 
-	dev->data = data;
 	dev->dev_ops = &ops;
 	dev->rx_pkt_burst = pmd_rx_burst;
 	dev->tx_pkt_burst = pmd_tx_burst;
@@ -1574,7 +1567,6 @@ eth_dev_tap_create(struct rte_vdev_device *vdev, char *tap_name,
 	RTE_LOG(ERR, PMD, "%s Unable to initialize %s\n",
 		tuntap_name, rte_vdev_device_name(vdev));
 
-	rte_free(data);
 	return -EINVAL;
 }
 
@@ -1828,7 +1820,6 @@ rte_pmd_tap_remove(struct rte_vdev_device *dev)
 
 	close(internals->ioctl_sock);
 	rte_free(eth_dev->data->dev_private);
-	rte_free(eth_dev->data);
 
 	rte_eth_dev_release_port(eth_dev);
 
diff --git a/drivers/net/vhost/rte_eth_vhost.c b/drivers/net/vhost/rte_eth_vhost.c
index d7d44a0..fea13eb 100644
--- a/drivers/net/vhost/rte_eth_vhost.c
+++ b/drivers/net/vhost/rte_eth_vhost.c
@@ -1227,7 +1227,7 @@ eth_dev_vhost_create(struct rte_vdev_device *dev, char *iface_name,
 	int16_t queues, const unsigned int numa_node, uint64_t flags)
 {
 	const char *name = rte_vdev_device_name(dev);
-	struct rte_eth_dev_data *data = NULL;
+	struct rte_eth_dev_data *data;
 	struct pmd_internal *internal = NULL;
 	struct rte_eth_dev *eth_dev = NULL;
 	struct ether_addr *eth_addr = NULL;
@@ -1237,13 +1237,6 @@ eth_dev_vhost_create(struct rte_vdev_device *dev, char *iface_name,
 	RTE_LOG(INFO, PMD, "Creating VHOST-USER backend on numa socket %u\n",
 		numa_node);
 
-	/* now do all data allocation - for eth_dev structure and internal
-	 * (private) data
-	 */
-	data = rte_zmalloc_socket(name, sizeof(*data), 0, numa_node);
-	if (data == NULL)
-		goto error;
-
 	list = rte_zmalloc_socket(name, sizeof(*list), 0, numa_node);
 	if (list == NULL)
 		goto error;
@@ -1285,12 +1278,7 @@ eth_dev_vhost_create(struct rte_vdev_device *dev, char *iface_name,
 	rte_spinlock_init(&vring_state->lock);
 	vring_states[eth_dev->data->port_id] = vring_state;
 
-	/* We'll replace the 'data' originally allocated by eth_dev. So the
-	 * vhost PMD resources won't be shared between multi processes.
-	 */
-	rte_memcpy(data, eth_dev->data, sizeof(*data));
-	eth_dev->data = data;
-
+	data = eth_dev->data;
 	data->nb_rx_queues = queues;
 	data->nb_tx_queues = queues;
 	internal->max_queues = queues;
@@ -1331,7 +1319,6 @@ eth_dev_vhost_create(struct rte_vdev_device *dev, char *iface_name,
 		rte_eth_dev_release_port(eth_dev);
 	rte_free(internal);
 	rte_free(list);
-	rte_free(data);
 
 	return -1;
 }
@@ -1462,8 +1449,6 @@ rte_pmd_vhost_remove(struct rte_vdev_device *dev)
 	rte_free(vring_states[eth_dev->data->port_id]);
 	vring_states[eth_dev->data->port_id] = NULL;
 
-	rte_free(eth_dev->data);
-
 	rte_eth_dev_release_port(eth_dev);
 
 	return 0;
-- 
2.7.4