From: Or Ami Date: Mon, 23 Nov 2015 14:44:42 +0000 (+0100) Subject: mlx4: allow operation in secondary processes X-Git-Tag: spdx-start~7982 X-Git-Url: http://git.droids-corp.org/?a=commitdiff_plain;h=e9d39be873d710e1b5d1ccf6926eca44475a6f34;p=dpdk.git mlx4: allow operation in secondary processes Secondary processes are expected to use queues and other resources allocated by the primary, however Verbs resources can only be shared between processes when inherited through fork(). This limitation can be worked around for TX by configuring separate queues from secondary processes. Signed-off-by: Or Ami Signed-off-by: Adrien Mazarguil --- diff --git a/drivers/net/mlx4/mlx4.c b/drivers/net/mlx4/mlx4.c index 4f57e2d74d..207bfe2aae 100644 --- a/drivers/net/mlx4/mlx4.c +++ b/drivers/net/mlx4/mlx4.c @@ -299,6 +299,46 @@ struct priv { rte_spinlock_t lock; /* Lock for control functions. */ }; +/* Local storage for secondary process data. */ +struct mlx4_secondary_data { + struct rte_eth_dev_data data; /* Local device data. */ + struct priv *primary_priv; /* Private structure from primary. */ + struct rte_eth_dev_data *shared_dev_data; /* Shared device data. */ + rte_spinlock_t lock; /* Port configuration lock. */ +} mlx4_secondary_data[RTE_MAX_ETHPORTS]; + +/** + * Check if running as a secondary process. + * + * @return + * Nonzero if running as a secondary process. + */ +static inline int +mlx4_is_secondary(void) +{ + return rte_eal_process_type() != RTE_PROC_PRIMARY; +} + +/** + * Return private structure associated with an Ethernet device. + * + * @param dev + * Pointer to Ethernet device structure. + * + * @return + * Pointer to private structure. + */ +static struct priv * +mlx4_get_priv(struct rte_eth_dev *dev) +{ + struct mlx4_secondary_data *sd; + + if (!mlx4_is_secondary()) + return dev->data->dev_private; + sd = &mlx4_secondary_data[dev->data->port_id]; + return sd->data.dev_private; +} + /** * Lock private structure to protect it from concurrent access in the * control path. @@ -658,6 +698,13 @@ priv_set_flags(struct priv *priv, unsigned int keep, unsigned int flags) /* Device configuration. */ +static int +txq_setup(struct rte_eth_dev *dev, struct txq *txq, uint16_t desc, + unsigned int socket, const struct rte_eth_txconf *conf); + +static void +txq_cleanup(struct txq *txq); + static int rxq_setup(struct rte_eth_dev *dev, struct rxq *rxq, uint16_t desc, unsigned int socket, const struct rte_eth_rxconf *conf, @@ -756,6 +803,8 @@ mlx4_dev_configure(struct rte_eth_dev *dev) struct priv *priv = dev->data->dev_private; int ret; + if (mlx4_is_secondary()) + return -E_RTE_SECONDARY; priv_lock(priv); ret = dev_configure(dev); assert(ret >= 0); @@ -763,6 +812,160 @@ mlx4_dev_configure(struct rte_eth_dev *dev) return -ret; } +static uint16_t mlx4_tx_burst(void *, struct rte_mbuf **, uint16_t); +static uint16_t removed_rx_burst(void *, struct rte_mbuf **, uint16_t); + +/** + * Configure secondary process queues from a private data pointer (primary + * or secondary) and update burst callbacks. Can take place only once. + * + * All queues must have been previously created by the primary process to + * avoid undefined behavior. + * + * @param priv + * Private data pointer from either primary or secondary process. + * + * @return + * Private data pointer from secondary process, NULL in case of error. + */ +static struct priv * +mlx4_secondary_data_setup(struct priv *priv) +{ + unsigned int port_id = 0; + struct mlx4_secondary_data *sd; + void **tx_queues; + void **rx_queues; + unsigned int nb_tx_queues; + unsigned int nb_rx_queues; + unsigned int i; + + /* priv must be valid at this point. */ + assert(priv != NULL); + /* priv->dev must also be valid but may point to local memory from + * another process, possibly with the same address and must not + * be dereferenced yet. */ + assert(priv->dev != NULL); + /* Determine port ID by finding out where priv comes from. */ + while (1) { + sd = &mlx4_secondary_data[port_id]; + rte_spinlock_lock(&sd->lock); + /* Primary process? */ + if (sd->primary_priv == priv) + break; + /* Secondary process? */ + if (sd->data.dev_private == priv) + break; + rte_spinlock_unlock(&sd->lock); + if (++port_id == RTE_DIM(mlx4_secondary_data)) + port_id = 0; + } + /* Switch to secondary private structure. If private data has already + * been updated by another thread, there is nothing else to do. */ + priv = sd->data.dev_private; + if (priv->dev->data == &sd->data) + goto end; + /* Sanity checks. Secondary private structure is supposed to point + * to local eth_dev, itself still pointing to the shared device data + * structure allocated by the primary process. */ + assert(sd->shared_dev_data != &sd->data); + assert(sd->data.nb_tx_queues == 0); + assert(sd->data.tx_queues == NULL); + assert(sd->data.nb_rx_queues == 0); + assert(sd->data.rx_queues == NULL); + assert(priv != sd->primary_priv); + assert(priv->dev->data == sd->shared_dev_data); + assert(priv->txqs_n == 0); + assert(priv->txqs == NULL); + assert(priv->rxqs_n == 0); + assert(priv->rxqs == NULL); + nb_tx_queues = sd->shared_dev_data->nb_tx_queues; + nb_rx_queues = sd->shared_dev_data->nb_rx_queues; + /* Allocate local storage for queues. */ + tx_queues = rte_zmalloc("secondary ethdev->tx_queues", + sizeof(sd->data.tx_queues[0]) * nb_tx_queues, + RTE_CACHE_LINE_SIZE); + rx_queues = rte_zmalloc("secondary ethdev->rx_queues", + sizeof(sd->data.rx_queues[0]) * nb_rx_queues, + RTE_CACHE_LINE_SIZE); + if (tx_queues == NULL || rx_queues == NULL) + goto error; + /* Lock to prevent control operations during setup. */ + priv_lock(priv); + /* TX queues. */ + for (i = 0; i != nb_tx_queues; ++i) { + struct txq *primary_txq = (*sd->primary_priv->txqs)[i]; + struct txq *txq; + + if (primary_txq == NULL) + continue; + txq = rte_calloc_socket("TXQ", 1, sizeof(*txq), 0, + primary_txq->socket); + if (txq != NULL) { + if (txq_setup(priv->dev, + txq, + primary_txq->elts_n * MLX4_PMD_SGE_WR_N, + primary_txq->socket, + NULL) == 0) { + txq->stats.idx = primary_txq->stats.idx; + tx_queues[i] = txq; + continue; + } + rte_free(txq); + } + while (i) { + txq = tx_queues[--i]; + txq_cleanup(txq); + rte_free(txq); + } + goto error; + } + /* RX queues. */ + for (i = 0; i != nb_rx_queues; ++i) { + struct rxq *primary_rxq = (*sd->primary_priv->rxqs)[i]; + + if (primary_rxq == NULL) + continue; + /* Not supported yet. */ + rx_queues[i] = NULL; + } + /* Update everything. */ + priv->txqs = (void *)tx_queues; + priv->txqs_n = nb_tx_queues; + priv->rxqs = (void *)rx_queues; + priv->rxqs_n = nb_rx_queues; + sd->data.rx_queues = rx_queues; + sd->data.tx_queues = tx_queues; + sd->data.nb_rx_queues = nb_rx_queues; + sd->data.nb_tx_queues = nb_tx_queues; + sd->data.dev_link = sd->shared_dev_data->dev_link; + sd->data.mtu = sd->shared_dev_data->mtu; + memcpy(sd->data.rx_queue_state, sd->shared_dev_data->rx_queue_state, + sizeof(sd->data.rx_queue_state)); + memcpy(sd->data.tx_queue_state, sd->shared_dev_data->tx_queue_state, + sizeof(sd->data.tx_queue_state)); + sd->data.dev_flags = sd->shared_dev_data->dev_flags; + /* Use local data from now on. */ + rte_mb(); + priv->dev->data = &sd->data; + rte_mb(); + priv->dev->tx_pkt_burst = mlx4_tx_burst; + priv->dev->rx_pkt_burst = removed_rx_burst; + priv_unlock(priv); +end: + /* More sanity checks. */ + assert(priv->dev->tx_pkt_burst == mlx4_tx_burst); + assert(priv->dev->rx_pkt_burst == removed_rx_burst); + assert(priv->dev->data == &sd->data); + rte_spinlock_unlock(&sd->lock); + return priv; +error: + priv_unlock(priv); + rte_free(tx_queues); + rte_free(rx_queues); + rte_spinlock_unlock(&sd->lock); + return NULL; +} + /* TX queues handling. */ /** @@ -1467,6 +1670,46 @@ stop: return i; } +/** + * DPDK callback for TX in secondary processes. + * + * This function configures all queues from primary process information + * if necessary before reverting to the normal TX burst callback. + * + * @param dpdk_txq + * Generic pointer to TX queue structure. + * @param[in] pkts + * Packets to transmit. + * @param pkts_n + * Number of packets in array. + * + * @return + * Number of packets successfully transmitted (<= pkts_n). + */ +static uint16_t +mlx4_tx_burst_secondary_setup(void *dpdk_txq, struct rte_mbuf **pkts, + uint16_t pkts_n) +{ + struct txq *txq = dpdk_txq; + struct priv *priv = mlx4_secondary_data_setup(txq->priv); + struct priv *primary_priv; + unsigned int index; + + if (priv == NULL) + return 0; + primary_priv = + mlx4_secondary_data[priv->dev->data->port_id].primary_priv; + /* Look for queue index in both private structures. */ + for (index = 0; index != priv->txqs_n; ++index) + if (((*primary_priv->txqs)[index] == txq) || + ((*priv->txqs)[index] == txq)) + break; + if (index == priv->txqs_n) + return 0; + txq = (*priv->txqs)[index]; + return priv->dev->tx_pkt_burst(txq, pkts, pkts_n); +} + /** * Configure a TX queue. * @@ -1488,7 +1731,7 @@ static int txq_setup(struct rte_eth_dev *dev, struct txq *txq, uint16_t desc, unsigned int socket, const struct rte_eth_txconf *conf) { - struct priv *priv = dev->data->dev_private; + struct priv *priv = mlx4_get_priv(dev); struct txq tmpl = { .priv = priv, .socket = socket @@ -1504,6 +1747,8 @@ txq_setup(struct rte_eth_dev *dev, struct txq *txq, uint16_t desc, int ret = 0; (void)conf; /* Thresholds configuration (ignored). */ + if (priv == NULL) + return EINVAL; if ((desc == 0) || (desc % MLX4_PMD_SGE_WR_N)) { ERROR("%p: invalid number of TX descriptors (must be a" " multiple of %d)", (void *)dev, MLX4_PMD_SGE_WR_N); @@ -1682,6 +1927,8 @@ mlx4_tx_queue_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc, struct txq *txq = (*priv->txqs)[idx]; int ret; + if (mlx4_is_secondary()) + return -E_RTE_SECONDARY; priv_lock(priv); DEBUG("%p: configuring queue %u for %u descriptors", (void *)dev, idx, desc); @@ -1737,6 +1984,8 @@ mlx4_tx_queue_release(void *dpdk_txq) struct priv *priv; unsigned int i; + if (mlx4_is_secondary()) + return; if (txq == NULL) return; priv = txq->priv; @@ -3035,6 +3284,46 @@ repost: return pkts_ret; } +/** + * DPDK callback for RX in secondary processes. + * + * This function configures all queues from primary process information + * if necessary before reverting to the normal RX burst callback. + * + * @param dpdk_rxq + * Generic pointer to RX queue structure. + * @param[out] pkts + * Array to store received packets. + * @param pkts_n + * Maximum number of packets in array. + * + * @return + * Number of packets successfully received (<= pkts_n). + */ +static uint16_t +mlx4_rx_burst_secondary_setup(void *dpdk_rxq, struct rte_mbuf **pkts, + uint16_t pkts_n) +{ + struct rxq *rxq = dpdk_rxq; + struct priv *priv = mlx4_secondary_data_setup(rxq->priv); + struct priv *primary_priv; + unsigned int index; + + if (priv == NULL) + return 0; + primary_priv = + mlx4_secondary_data[priv->dev->data->port_id].primary_priv; + /* Look for queue index in both private structures. */ + for (index = 0; index != priv->rxqs_n; ++index) + if (((*primary_priv->rxqs)[index] == rxq) || + ((*priv->rxqs)[index] == rxq)) + break; + if (index == priv->rxqs_n) + return 0; + rxq = (*priv->rxqs)[index]; + return priv->dev->rx_pkt_burst(rxq, pkts, pkts_n); +} + /** * Allocate a Queue Pair. * Optionally setup inline receive if supported. @@ -3613,6 +3902,8 @@ mlx4_rx_queue_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc, struct rxq *rxq = (*priv->rxqs)[idx]; int ret; + if (mlx4_is_secondary()) + return -E_RTE_SECONDARY; priv_lock(priv); DEBUG("%p: configuring queue %u for %u descriptors", (void *)dev, idx, desc); @@ -3671,6 +3962,8 @@ mlx4_rx_queue_release(void *dpdk_rxq) struct priv *priv; unsigned int i; + if (mlx4_is_secondary()) + return; if (rxq == NULL) return; priv = rxq->priv; @@ -3710,6 +4003,8 @@ mlx4_dev_start(struct rte_eth_dev *dev) unsigned int r; struct rxq *rxq; + if (mlx4_is_secondary()) + return -E_RTE_SECONDARY; priv_lock(priv); if (priv->started) { priv_unlock(priv); @@ -3774,6 +4069,8 @@ mlx4_dev_stop(struct rte_eth_dev *dev) unsigned int r; struct rxq *rxq; + if (mlx4_is_secondary()) + return; priv_lock(priv); if (!priv->started) { priv_unlock(priv); @@ -3864,10 +4161,12 @@ priv_dev_interrupt_handler_uninstall(struct priv *, struct rte_eth_dev *); static void mlx4_dev_close(struct rte_eth_dev *dev) { - struct priv *priv = dev->data->dev_private; + struct priv *priv = mlx4_get_priv(dev); void *tmp; unsigned int i; + if (priv == NULL) + return; priv_lock(priv); DEBUG("%p: closing device \"%s\"", (void *)dev, @@ -3929,10 +4228,12 @@ mlx4_dev_close(struct rte_eth_dev *dev) static void mlx4_dev_infos_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *info) { - struct priv *priv = dev->data->dev_private; + struct priv *priv = mlx4_get_priv(dev); unsigned int max; char ifname[IF_NAMESIZE]; + if (priv == NULL) + return; priv_lock(priv); /* FIXME: we should ask the device for these values. */ info->min_rx_bufsize = 32; @@ -3978,11 +4279,13 @@ mlx4_dev_infos_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *info) static void mlx4_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats) { - struct priv *priv = dev->data->dev_private; + struct priv *priv = mlx4_get_priv(dev); struct rte_eth_stats tmp = {0}; unsigned int i; unsigned int idx; + if (priv == NULL) + return; priv_lock(priv); /* Add software counters. */ for (i = 0; (i != priv->rxqs_n); ++i) { @@ -4041,10 +4344,12 @@ mlx4_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats) static void mlx4_stats_reset(struct rte_eth_dev *dev) { - struct priv *priv = dev->data->dev_private; + struct priv *priv = mlx4_get_priv(dev); unsigned int i; unsigned int idx; + if (priv == NULL) + return; priv_lock(priv); for (i = 0; (i != priv->rxqs_n); ++i) { if ((*priv->rxqs)[i] == NULL) @@ -4079,6 +4384,8 @@ mlx4_mac_addr_remove(struct rte_eth_dev *dev, uint32_t index) { struct priv *priv = dev->data->dev_private; + if (mlx4_is_secondary()) + return; priv_lock(priv); DEBUG("%p: removing MAC address from index %" PRIu32, (void *)dev, index); @@ -4108,6 +4415,8 @@ mlx4_mac_addr_add(struct rte_eth_dev *dev, struct ether_addr *mac_addr, { struct priv *priv = dev->data->dev_private; + if (mlx4_is_secondary()) + return; (void)vmdq; priv_lock(priv); DEBUG("%p: adding MAC address at index %" PRIu32, @@ -4135,6 +4444,8 @@ mlx4_promiscuous_enable(struct rte_eth_dev *dev) unsigned int i; int ret; + if (mlx4_is_secondary()) + return; priv_lock(priv); if (priv->promisc) { priv_unlock(priv); @@ -4181,6 +4492,8 @@ mlx4_promiscuous_disable(struct rte_eth_dev *dev) struct priv *priv = dev->data->dev_private; unsigned int i; + if (mlx4_is_secondary()) + return; priv_lock(priv); if (!priv->promisc) { priv_unlock(priv); @@ -4211,6 +4524,8 @@ mlx4_allmulticast_enable(struct rte_eth_dev *dev) unsigned int i; int ret; + if (mlx4_is_secondary()) + return; priv_lock(priv); if (priv->allmulti) { priv_unlock(priv); @@ -4257,6 +4572,8 @@ mlx4_allmulticast_disable(struct rte_eth_dev *dev) struct priv *priv = dev->data->dev_private; unsigned int i; + if (mlx4_is_secondary()) + return; priv_lock(priv); if (!priv->allmulti) { priv_unlock(priv); @@ -4285,7 +4602,7 @@ end: static int mlx4_link_update_unlocked(struct rte_eth_dev *dev, int wait_to_complete) { - struct priv *priv = dev->data->dev_private; + struct priv *priv = mlx4_get_priv(dev); struct ethtool_cmd edata = { .cmd = ETHTOOL_GSET }; @@ -4293,6 +4610,8 @@ mlx4_link_update_unlocked(struct rte_eth_dev *dev, int wait_to_complete) struct rte_eth_link dev_link; int link_speed = 0; + if (priv == NULL) + return -EINVAL; (void)wait_to_complete; if (priv_ifreq(priv, SIOCGIFFLAGS, &ifr)) { WARN("ioctl(SIOCGIFFLAGS) failed: %s", strerror(errno)); @@ -4334,9 +4653,11 @@ mlx4_link_update_unlocked(struct rte_eth_dev *dev, int wait_to_complete) static int mlx4_link_update(struct rte_eth_dev *dev, int wait_to_complete) { - struct priv *priv = dev->data->dev_private; + struct priv *priv = mlx4_get_priv(dev); int ret; + if (priv == NULL) + return -EINVAL; priv_lock(priv); ret = mlx4_link_update_unlocked(dev, wait_to_complete); priv_unlock(priv); @@ -4369,6 +4690,8 @@ mlx4_dev_set_mtu(struct rte_eth_dev *dev, uint16_t mtu) uint16_t (*rx_func)(void *, struct rte_mbuf **, uint16_t) = mlx4_rx_burst; + if (mlx4_is_secondary()) + return -E_RTE_SECONDARY; priv_lock(priv); /* Set kernel interface MTU first. */ if (priv_set_mtu(priv, mtu)) { @@ -4452,6 +4775,8 @@ mlx4_dev_get_flow_ctrl(struct rte_eth_dev *dev, struct rte_eth_fc_conf *fc_conf) }; int ret; + if (mlx4_is_secondary()) + return -E_RTE_SECONDARY; ifr.ifr_data = ðpause; priv_lock(priv); if (priv_ifreq(priv, SIOCETHTOOL, &ifr)) { @@ -4500,6 +4825,8 @@ mlx4_dev_set_flow_ctrl(struct rte_eth_dev *dev, struct rte_eth_fc_conf *fc_conf) }; int ret; + if (mlx4_is_secondary()) + return -E_RTE_SECONDARY; ifr.ifr_data = ðpause; ethpause.autoneg = fc_conf->autoneg; if (((fc_conf->mode & RTE_FC_FULL) == RTE_FC_FULL) || @@ -4639,6 +4966,8 @@ mlx4_vlan_filter_set(struct rte_eth_dev *dev, uint16_t vlan_id, int on) struct priv *priv = dev->data->dev_private; int ret; + if (mlx4_is_secondary()) + return -E_RTE_SECONDARY; priv_lock(priv); ret = vlan_filter_set(dev, vlan_id, on); priv_unlock(priv); @@ -5058,7 +5387,7 @@ mlx4_pci_devinit(struct rte_pci_driver *pci_drv, struct rte_pci_device *pci_dev) struct ibv_port_attr port_attr; struct ibv_pd *pd = NULL; struct priv *priv = NULL; - struct rte_eth_dev *eth_dev; + struct rte_eth_dev *eth_dev = NULL; #ifdef HAVE_EXP_QUERY_DEVICE struct ibv_exp_device_attr exp_device_attr; #endif /* HAVE_EXP_QUERY_DEVICE */ @@ -5234,18 +5563,46 @@ mlx4_pci_devinit(struct rte_pci_driver *pci_drv, struct rte_pci_device *pci_dev) goto port_error; } - eth_dev->data->dev_private = priv; + /* Secondary processes have to use local storage for their + * private data as well as a copy of eth_dev->data, but this + * pointer must not be modified before burst functions are + * actually called. */ + if (mlx4_is_secondary()) { + struct mlx4_secondary_data *sd = + &mlx4_secondary_data[eth_dev->data->port_id]; + + sd->primary_priv = eth_dev->data->dev_private; + if (sd->primary_priv == NULL) { + ERROR("no private data for port %u", + eth_dev->data->port_id); + err = EINVAL; + goto port_error; + } + sd->shared_dev_data = eth_dev->data; + rte_spinlock_init(&sd->lock); + memcpy(sd->data.name, sd->shared_dev_data->name, + sizeof(sd->data.name)); + sd->data.dev_private = priv; + sd->data.rx_mbuf_alloc_failed = 0; + sd->data.mtu = ETHER_MTU; + sd->data.port_id = sd->shared_dev_data->port_id; + sd->data.mac_addrs = priv->mac; + eth_dev->tx_pkt_burst = mlx4_tx_burst_secondary_setup; + eth_dev->rx_pkt_burst = mlx4_rx_burst_secondary_setup; + } else { + eth_dev->data->dev_private = priv; + eth_dev->data->rx_mbuf_alloc_failed = 0; + eth_dev->data->mtu = ETHER_MTU; + eth_dev->data->mac_addrs = priv->mac; + } eth_dev->pci_dev = pci_dev; rte_eth_copy_pci_info(eth_dev, pci_dev); eth_dev->driver = &mlx4_driver; - eth_dev->data->rx_mbuf_alloc_failed = 0; - eth_dev->data->mtu = ETHER_MTU; priv->dev = eth_dev; eth_dev->dev_ops = &mlx4_dev_ops; - eth_dev->data->mac_addrs = priv->mac; TAILQ_INIT(ð_dev->link_intr_cbs); /* Bring Ethernet device up. */ @@ -5259,6 +5616,8 @@ port_error: claim_zero(ibv_dealloc_pd(pd)); if (ctx) claim_zero(ibv_close_device(ctx)); + if (eth_dev) + rte_eth_dev_release_port(eth_dev); break; }