[Patch v4 01/17] net/mana: add basic driver, build environment and doc

[Ferruh Yigit]

On 7/9/2022 12:49 AM, longli at linuxonhyperv.com wrote:
> CAUTION: This message has originated from an External Source. Please use proper judgment and caution when opening attachments, clicking links, or responding to this email.
> 
> 
> 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>
> ---
> Change log:
> v2:
> Fix typos.
> Make the driver build only on x86-64 and Linux.
> Remove unused header files.
> Change port definition to uint16_t or uint8_t (for IB).
> Use getline() in place of fgets() to read and truncate a line.
> v3:
> Add meson build check for required functions from RDMA direct verb header file
> v4:
> Remove extra "\n" in logging code.
> Use "r" in place of "rb" in fopen() to read text files.
> 

<...>

> --- /dev/null
> +++ b/doc/guides/nics/mana.rst
> @@ -0,0 +1,66 @@
> +..  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.
> +

Can you please provide any link to an official product description? As a 
reference point for anybody interested more with the product details.


<..>

> +
> +Netvsc PMD arguments > +--------------------

'Netvsc'? Do you mean 'MANA'?
j
> +
> +The user can specify below argument in devargs.
> +
> +#.  ``mac``:
> +
> +    Specify the MAC address for this device. If it is set, the driver
> +    probes and loads the NIC with a matching mac address. If it is not
> +    set, the driver probes on all the NICs on the PCI device. The default
> +    value is not set, meaning all the NICs will be probed and loaded.


Code accepts up to 8 mac value, should this be documented?

Also why this devarg is needed?

> diff --git a/drivers/net/mana/mana.c b/drivers/net/mana/mana.c
> new file mode 100644
> index 0000000000..cb59eb6882
> --- /dev/null
> +++ b/drivers/net/mana/mana.c
> @@ -0,0 +1,704 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright 2022 Microsoft Corporation
> + */
> +
> +#include <unistd.h>
> +#include <dirent.h>
> +#include <fcntl.h>
> +#include <sys/mman.h>
> +
> +#include <ethdev_driver.h>
> +#include <ethdev_pci.h>
> +#include <rte_kvargs.h>
> +#include <rte_eal_paging.h>
> +
> +#include <infiniband/verbs.h>
> +#include <infiniband/manadv.h>
> +
> +#include <assert.h>
> +
> +#include "mana.h"
> +
> +/* Shared memory between primary/secondary processes, per driver */
> +struct mana_shared_data *mana_shared_data;
> +const struct rte_memzone *mana_shared_mz;

If these global variables are not used by other compilation units, 
please try to make them static as much as possible.

> +static const char *MZ_MANA_SHARED_DATA = "mana_shared_data";
> +
> +struct mana_shared_data mana_local_data;
> +

Can you put some comment to this global variables?

> +/* Spinlock for mana_shared_data */
> +static rte_spinlock_t mana_shared_data_lock = RTE_SPINLOCK_INITIALIZER;
> +
> +/* Allocate a buffer on the stack and fill it with a printf format string. */
> +#define MKSTR(name, ...) \
> +       int mkstr_size_##name = snprintf(NULL, 0, "" __VA_ARGS__); \
> +       char name[mkstr_size_##name + 1]; \
> +       \
> +       memset(name, 0, mkstr_size_##name + 1); \
> +       snprintf(name, sizeof(name), "" __VA_ARGS__)
> +
> +int mana_logtype_driver;
> +int mana_logtype_init;
> +
> +const struct eth_dev_ops mana_dev_ops = {
> +};
> +
> +const struct eth_dev_ops mana_dev_sec_ops = {
> +};

It may be better to expand 'sec' to secondary to not confuse with 
security etc...

> +
> +uint16_t
> +mana_rx_burst_removed(void *dpdk_rxq __rte_unused,
> +                     struct rte_mbuf **pkts __rte_unused,
> +                     uint16_t pkts_n __rte_unused)
> +{
> +       rte_mb();
> +       return 0;
> +}
> +
> +uint16_t
> +mana_tx_burst_removed(void *dpdk_rxq __rte_unused,
> +                     struct rte_mbuf **pkts __rte_unused,
> +                     uint16_t pkts_n __rte_unused)
> +{
> +       rte_mb();
> +       return 0;
> +}
> +
> +static const char *mana_init_args[] = {
> +       "mac",
> +       NULL,
> +};
> +
> +/* Support of parsing up to 8 mac address from EAL command line */
> +#define MAX_NUM_ADDRESS 8
> +struct mana_conf {
> +       struct rte_ether_addr mac_array[MAX_NUM_ADDRESS];
> +       unsigned int index;
> +};
> +
> +static int mana_arg_parse_callback(const char *key, const char *val,
> +                                  void *private)

Since this is new driver, better to follow the coding convention:
https://doc.dpdk.org/guides/contributing/coding_style.html

Please put return type to another line:

static int
mana_arg_parse_callback(const char *key, const char *val, void *private)

> +{
> +       struct mana_conf *conf = (struct mana_conf *)private;
> +       int ret;
> +
> +       DRV_LOG(INFO, "key=%s value=%s index=%d", key, val, conf->index);
> +
> +       if (conf->index >= MAX_NUM_ADDRESS) {
> +               DRV_LOG(ERR, "Exceeding max MAC address");
> +               return 1;
> +       }
> +
> +       ret = rte_ether_unformat_addr(val, &conf->mac_array[conf->index]);
> +       if (ret) {
> +               DRV_LOG(ERR, "Invalid MAC address %s", val);
> +               return ret;
> +       }
> +
> +       conf->index++;
> +
> +       return 0;
> +}
> +

<...>

> +static int get_port_mac(struct ibv_device *device, unsigned int port,
> +                       struct rte_ether_addr *addr)
> +{
> +       FILE *file;
> +       int ret = 0;
> +       DIR *dir;
> +       struct dirent *dent;
> +       unsigned int dev_port;
> +       char mac[20];
> +
> +       MKSTR(path, "%s/device/net", device->ibdev_path);
> +
> +       dir = opendir(path);
> +       if (!dir)
> +               return -ENOENT;
> +
> +       while ((dent = readdir(dir))) {
> +               char *name = dent->d_name;
> +
> +               MKSTR(filepath, "%s/%s/dev_port", path, name);
> +
> +               /* Ignore . and .. */
> +               if ((name[0] == '.') &&
> +                   ((name[1] == '\0') ||
> +                    ((name[1] == '.') && (name[2] == '\0'))))
> +                       continue;
> +
> +               file = fopen(filepath, "r");
> +               if (!file)
> +                       continue;
> +
> +               ret = fscanf(file, "%u", &dev_port);
> +               fclose(file);
> +
> +               if (ret != 1)
> +                       continue;
> +
> +               /* Ethernet ports start at 0, IB port start at 1 */
> +               if (dev_port == port - 1) {
> +                       MKSTR(filepath, "%s/%s/address", path, name);


'MKSTR' macro adds two variables related with first argument, 'filepath' 
already used above. Yes there is a new scope but better to not define 
new variables, can you select a new name here?

<...>

> +
> +static int mana_pci_probe_mac(struct rte_pci_driver *pci_drv __rte_unused,

This is a static function, if you don't use 'pci_drv', why not drop it 
from the argument list.

> +                             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;
> +

As far as I understand, intention of this loop is to find 'ibdev' 
matching this device, code gooes through all "ibv device list" for this, 
I wonder if there is a easy way for doing this, like a sysfs entry to 
help getting this information?
And how mlx4/5 does this?

> +               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 };" for portability.

<...>

> +static int mana_pci_probe(struct rte_pci_driver *pci_drv __rte_unused,
> +                         struct rte_pci_device *pci_dev)
> +{
> +       struct rte_devargs *args = pci_dev->device.devargs;
> +       struct mana_conf conf = {};

afaik, this is not part of c spec yet, why not initialize as " = {0}".

> +       unsigned int i;
> +       int ret;
> +
> +       if (args && args->args) {

You can prefer 'args->drv_str', which is newer name of the args.

<...>

> +static const struct rte_pci_id mana_pci_id_map[] = {
> +       {
> +               RTE_PCI_DEVICE(PCI_VENDOR_ID_MICROSOFT,
> +                              PCI_DEVICE_ID_MICROSOFT_MANA)
> +       },

PCI ID list should be terminated with ".vendor_id = 0", otherwise PCI 
bus scan loop may behave unexpectedly.

> +};
> +
> +static struct rte_pci_driver mana_pci_driver = {
> +       .driver = {
> +               .name = "mana_pci",

driver names are mostly like 'net_<driver_name>', is there a reason to 
diverge from it?
Also if you use 'RTE_PMD_REGISTER_PCI' macro, it will be standardised 
anyway.

> +       },
> +       .id_table = mana_pci_id_map,
> +       .probe = mana_pci_probe,
> +       .remove = mana_pci_remove,
> +       .drv_flags = RTE_PCI_DRV_INTR_RMV,
> +};
> +
> +RTE_INIT(rte_mana_pmd_init)
> +{
> +       rte_pci_register(&mana_pci_driver);
> +}
> +

Why not using 'RTE_PMD_REGISTER_PCI()' macro instead?

> +RTE_PMD_EXPORT_NAME(net_mana, __COUNTER__);
> +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);
> diff --git a/drivers/net/mana/mana.h b/drivers/net/mana/mana.h
> new file mode 100644
> index 0000000000..e30c030b4e
> --- /dev/null
> +++ b/drivers/net/mana/mana.h
> @@ -0,0 +1,210 @@
> +/* 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,
> +};
> +
> +/* Shared data between primary/secondary processes */
> +struct mana_shared_data {
> +       rte_spinlock_t lock;
> +       int init_done;
> +       unsigned int primary_cnt;
> +       unsigned int secondary_cnt;
> +};
> +
> +#define MIN_RX_BUF_SIZE        1024
> +#define MAX_FRAME_SIZE RTE_ETHER_MAX_LEN
> +#define BNIC_MAX_MAC_ADDR 1
> +

What 'BNIC_' prefix stands for? If it is related to the PMD, what do you 
think to use 'MANA_' as prefix?
Same for multiple macros below.

<...>

> +
> +#define PMD_INIT_FUNC_TRACE() PMD_INIT_LOG(DEBUG, " >>")
> +
> +const uint32_t *mana_supported_ptypes(struct rte_eth_dev *dev);
> +

This function is not defined in this patch, so can drop declarataion.

<...>

> diff --git a/drivers/net/mana/version.map b/drivers/net/mana/version.map
> new file mode 100644
> index 0000000000..c2e0723b4c
> --- /dev/null
> +++ b/drivers/net/mana/version.map
> @@ -0,0 +1,3 @@
> +DPDK_22 {

It is 'DPDK_23' now.