[Patch v9 01/18] net/mana: add basic driver with build environment and doc
Ferruh Yigit
ferruh.yigit at amd.com
Tue Oct 4 19:47:03 CEST 2022
On 9/24/2022 3:45 AM, longli at linuxonhyperv.com wrote:
>
> From: Long Li <longli at microsoft.com>
>
> MANA is a PCI device. It uses IB verbs to access hardware through the
> kernel RDMA layer. This patch introduces build environment and basic
> device probe functions.
>
> Signed-off-by: Long Li <longli at microsoft.com>
<...>
> +++ b/doc/guides/nics/mana.rst
> @@ -0,0 +1,69 @@
> +.. SPDX-License-Identifier: BSD-3-Clause
> + Copyright 2022 Microsoft Corporation
> +
> +MANA poll mode driver library
> +=============================
> +
> +The MANA poll mode driver library (**librte_net_mana**) implements support
> +for Microsoft Azure Network Adapter VF in SR-IOV context.
> +
> +Features
> +--------
> +
> +Features of the MANA Ethdev PMD are:
> +
> +Prerequisites
> +-------------
> +
> +This driver relies on external libraries and kernel drivers for resources
> +allocations and initialization. The following dependencies are not part of
> +DPDK and must be installed separately:
> +
> +- **libibverbs** (provided by rdma-core package)
> +
Does it make sense to provide rdma-core git repo link?
<...>
> +
> +static const char * const mana_init_args[] = {
> + "mac",
It is better to define a macro for the devarg string to be able to reuse
it in 'RTE_PMD_REGISTER_PARAM_STRING' (please see below).
#define ETH_MANA_MAC_ARG "mac"
static const char * const mana_init_args[] = {
ETH_MANA_MAC_ARG,
NULL,
};
<...>
> +
> +/*
> + * Goes through the IB device list to look for the IB port matching the
> + * mac_addr. If found, create a rte_eth_dev for it.
> + */
> +static int
> +mana_pci_probe_mac(struct rte_pci_device *pci_dev,
> + struct rte_ether_addr *mac_addr)
> +{
> + struct ibv_device **ibv_list;
> + int ibv_idx;
> + struct ibv_context *ctx;
> + struct ibv_device_attr_ex dev_attr;
> + int num_devices;
> + int ret = 0;
> + uint8_t port;
> + struct mana_priv *priv = NULL;
> + struct rte_eth_dev *eth_dev = NULL;
> + bool found_port;
> +
> + ibv_list = ibv_get_device_list(&num_devices);
> + for (ibv_idx = 0; ibv_idx < num_devices; ibv_idx++) {
> + struct ibv_device *ibdev = ibv_list[ibv_idx];
> + struct rte_pci_addr pci_addr;
> +
> + DRV_LOG(INFO, "Probe device name %s dev_name %s ibdev_path %s",
> + ibdev->name, ibdev->dev_name, ibdev->ibdev_path);
> +
> + if (mana_ibv_device_to_pci_addr(ibdev, &pci_addr))
> + continue;
> +
> + /* Ignore if this IB device is not this PCI device */
> + if (pci_dev->addr.domain != pci_addr.domain ||
> + pci_dev->addr.bus != pci_addr.bus ||
> + pci_dev->addr.devid != pci_addr.devid ||
> + pci_dev->addr.function != pci_addr.function)
> + continue;
> +
> + ctx = ibv_open_device(ibdev);
> + if (!ctx) {
> + DRV_LOG(ERR, "Failed to open IB device %s",
> + ibdev->name);
> + continue;
> + }
> +
> + ret = ibv_query_device_ex(ctx, NULL, &dev_attr);
> + DRV_LOG(INFO, "dev_attr.orig_attr.phys_port_cnt %u",
> + dev_attr.orig_attr.phys_port_cnt);
> + found_port = false;
> +
> + for (port = 1; port <= dev_attr.orig_attr.phys_port_cnt;
> + port++) {
> + struct ibv_parent_domain_init_attr attr = {0};
> + struct rte_ether_addr addr;
> + char address[64];
> + char name[RTE_ETH_NAME_MAX_LEN];
> +
> + ret = get_port_mac(ibdev, port, &addr);
> + if (ret)
> + continue;
> +
> + if (mac_addr && !rte_is_same_ether_addr(&addr, mac_addr))
> + continue;
> +
> + rte_ether_format_addr(address, sizeof(address), &addr);
> + DRV_LOG(INFO, "device located port %u address %s",
> + port, address);
> + found_port = true;
> +
> + priv = rte_zmalloc_socket(NULL, sizeof(*priv),
> + RTE_CACHE_LINE_SIZE,
> + SOCKET_ID_ANY);
> + if (!priv) {
> + ret = -ENOMEM;
> + goto failed;
> + }
> +
> + snprintf(name, sizeof(name), "%s_port%d",
> + pci_dev->device.name, port);
> +
> + if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
> + int fd;
> +
> + eth_dev = rte_eth_dev_attach_secondary(name);
> + if (!eth_dev) {
> + DRV_LOG(ERR, "Can't attach to dev %s",
> + name);
> + ret = -ENOMEM;
> + goto failed;
> + }
> +
> + eth_dev->device = &pci_dev->device;
> + eth_dev->dev_ops = &mana_dev_secondary_ops;
> + ret = mana_proc_priv_init(eth_dev);
> + if (ret)
> + goto failed;
> + priv->process_priv = eth_dev->process_private;
> +
> + /* Get the IB FD from the primary process */
> + fd = mana_mp_req_verbs_cmd_fd(eth_dev);
> + if (fd < 0) {
> + DRV_LOG(ERR, "Failed to get FD %d", fd);
> + ret = -ENODEV;
> + goto failed;
> + }
> +
> + ret = mana_map_doorbell_secondary(eth_dev, fd);
> + if (ret) {
> + DRV_LOG(ERR, "Failed secondary map %d",
> + fd);
The indentation level (and lenght) of this functions hints that some
part of it can be seprated as function, like probe one 'ibv_device' can
be on its own function.
Can you refactor the function, to increase readability? It is control
path, so there is no restriction to have function calls.
> + goto failed;
> + }
> +
> + /* fd is no not used after mapping doorbell */
> + close(fd);
> +
> + rte_spinlock_lock(&mana_shared_data->lock);
> + mana_shared_data->secondary_cnt++;
> + mana_local_data.secondary_cnt++;
> + rte_spinlock_unlock(&mana_shared_data->lock);
> +
> + rte_eth_copy_pci_info(eth_dev, pci_dev);
> + rte_eth_dev_probing_finish(eth_dev);
> +
> + /* Impossible to have more than one port
> + * matching a MAC address
> + */
> + continue;
> + }
> +
> + eth_dev = rte_eth_dev_allocate(name);
> + if (!eth_dev) {
> + ret = -ENOMEM;
> + goto failed;
> + }
> +
> + eth_dev->data->mac_addrs =
> + rte_calloc("mana_mac", 1,
> + sizeof(struct rte_ether_addr), 0);
> + if (!eth_dev->data->mac_addrs) {
> + ret = -ENOMEM;
> + goto failed;
> + }
> +
> + rte_ether_addr_copy(&addr, eth_dev->data->mac_addrs);
> +
> + priv->ib_pd = ibv_alloc_pd(ctx);
> + if (!priv->ib_pd) {
> + DRV_LOG(ERR, "ibv_alloc_pd failed port %d", port);
> + ret = -ENOMEM;
> + goto failed;
> + }
> +
> + /* Create a parent domain with the port number */
> + attr.pd = priv->ib_pd;
> + attr.comp_mask = IBV_PARENT_DOMAIN_INIT_ATTR_PD_CONTEXT;
> + attr.pd_context = (void *)(uint64_t)port;
> + priv->ib_parent_pd = ibv_alloc_parent_domain(ctx, &attr);
> + if (!priv->ib_parent_pd) {
> + DRV_LOG(ERR,
> + "ibv_alloc_parent_domain failed port %d",
> + port);
> + ret = -ENOMEM;
> + goto failed;
> + }
> +
> + priv->ib_ctx = ctx;
> + priv->port_id = eth_dev->data->port_id;
> + priv->dev_port = port;
> + eth_dev->data->dev_private = priv;
> + priv->dev_data = eth_dev->data;
> +
> + priv->max_rx_queues = dev_attr.orig_attr.max_qp;
> + priv->max_tx_queues = dev_attr.orig_attr.max_qp;
> +
> + priv->max_rx_desc =
> + RTE_MIN(dev_attr.orig_attr.max_qp_wr,
> + dev_attr.orig_attr.max_cqe);
> + priv->max_tx_desc =
> + RTE_MIN(dev_attr.orig_attr.max_qp_wr,
> + dev_attr.orig_attr.max_cqe);
> +
> + priv->max_send_sge = dev_attr.orig_attr.max_sge;
> + priv->max_recv_sge = dev_attr.orig_attr.max_sge;
> +
> + priv->max_mr = dev_attr.orig_attr.max_mr;
> + priv->max_mr_size = dev_attr.orig_attr.max_mr_size;
> +
> + DRV_LOG(INFO, "dev %s max queues %d desc %d sge %d",
> + name, priv->max_rx_queues, priv->max_rx_desc,
> + priv->max_send_sge);
> +
> + rte_spinlock_lock(&mana_shared_data->lock);
> + mana_shared_data->primary_cnt++;
> + rte_spinlock_unlock(&mana_shared_data->lock);
> +
> + eth_dev->data->dev_flags |= RTE_ETH_DEV_INTR_RMV;
> +
This assignment already done by 'rte_eth_copy_pci_info()' when
'RTE_PCI_DRV_INTR_RMV' driver flag set which this PMD sets, so
assignment is redundant.
<...>
> +
> +RTE_PMD_REGISTER_PCI(net_mana, mana_pci_driver);
> +RTE_PMD_REGISTER_PCI_TABLE(net_mana, mana_pci_id_map);
> +RTE_PMD_REGISTER_KMOD_DEP(net_mana, "* ib_uverbs & mana_ib");
> +RTE_LOG_REGISTER_SUFFIX(mana_logtype_init, init, NOTICE);
> +RTE_LOG_REGISTER_SUFFIX(mana_logtype_driver, driver, NOTICE);
Can you please add 'RTE_PMD_REGISTER_PARAM_STRING' macro for 'mac' devarg?
> diff --git a/drivers/net/mana/mana.h b/drivers/net/mana/mana.h
> new file mode 100644
> index 0000000000..a2021ceb4a
> --- /dev/null
> +++ b/drivers/net/mana/mana.h
> @@ -0,0 +1,102 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright 2022 Microsoft Corporation
> + */
> +
> +#ifndef __MANA_H__
> +#define __MANA_H__
> +
> +enum {
> + PCI_VENDOR_ID_MICROSOFT = 0x1414,
> +};
> +
> +enum {
> + PCI_DEVICE_ID_MICROSOFT_MANA = 0x00ba,
> +};
There is a common guidance to prefer enums against define BUT,
I tend to use enums for related cases, or when underneath numerical
value doesn't matter.
For PCI IDs I would use #define, although both works same, what do you
think to update them to define?
More information about the dev
mailing list