* [dpdk-stable] [PATCH 17.11] net/mlx5: use PCI address as port name
@ 2018-02-11 3:35 Yuanhan Liu
2018-02-11 3:38 ` Yuanhan Liu
0 siblings, 1 reply; 2+ messages in thread
From: Yuanhan Liu @ 2018-02-11 3:35 UTC (permalink / raw)
To: stable; +Cc: Yuanhan Liu
[ backported from upstream commit ad831a1176538f726428ebfe70f6607d7d854197 ]
It is suggested to use PCI BDF to identify a port for port addition
in OVS-DPDK. While mlx5 has its own naming style: name it by ib dev
name. This breaks the typical OVS DPDK use case and brings more puzzle
to the end users.
To fix it, this patch changes it to use PCI BDF as the name, too.
Also, a postfix " port %u" is added, just in case their might be more
than 1 port associated with a PCI device.
Signed-off-by: Yuanhan Liu <yliu@fridaylinux.org>
Acked-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
---
drivers/net/mlx5/mlx5.c | 20 +++++++-------------
1 file changed, 7 insertions(+), 13 deletions(-)
diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c
index a5eb3fd..912e53c 100644
--- a/drivers/net/mlx5/mlx5.c
+++ b/drivers/net/mlx5/mlx5.c
@@ -662,6 +662,8 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv, struct rte_pci_device *pci_dev)
INFO("%u port(s) detected", device_attr.orig_attr.phys_port_cnt);
for (i = 0; i < device_attr.orig_attr.phys_port_cnt; i++) {
+ char name[RTE_ETH_NAME_MAX_LEN];
+ int len;
uint32_t port = i + 1; /* ports are indexed from one */
uint32_t test = (1 << i);
struct ibv_context *ctx = NULL;
@@ -685,14 +687,13 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv, struct rte_pci_device *pci_dev)
.rx_vec_en = MLX5_ARG_UNSET,
};
+ len = snprintf(name, sizeof(name), PCI_PRI_FMT,
+ pci_dev->addr.domain, pci_dev->addr.bus,
+ pci_dev->addr.devid, pci_dev->addr.function);
+
mlx5_dev[idx].ports |= test;
if (mlx5_is_secondary()) {
- /* from rte_ethdev.c */
- char name[RTE_ETH_NAME_MAX_LEN];
-
- snprintf(name, sizeof(name), "%s port %u",
- ibv_get_device_name(ibv_dev), port);
eth_dev = rte_eth_dev_attach_secondary(name);
if (eth_dev == NULL) {
ERROR("can not attach rte ethdev");
@@ -902,14 +903,7 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv, struct rte_pci_device *pci_dev)
priv_get_mtu(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",
- ibv_get_device_name(ibv_dev), port);
- eth_dev = rte_eth_dev_allocate(name);
- }
+ eth_dev = rte_eth_dev_allocate(name);
if (eth_dev == NULL) {
ERROR("can not allocate rte ethdev");
err = ENOMEM;
--
2.7.4
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: [dpdk-stable] [PATCH 17.11] net/mlx5: use PCI address as port name
2018-02-11 3:35 [dpdk-stable] [PATCH 17.11] net/mlx5: use PCI address as port name Yuanhan Liu
@ 2018-02-11 3:38 ` Yuanhan Liu
0 siblings, 0 replies; 2+ messages in thread
From: Yuanhan Liu @ 2018-02-11 3:38 UTC (permalink / raw)
To: stable
On Sun, Feb 11, 2018 at 11:35:32AM +0800, Yuanhan Liu wrote:
> [ backported from upstream commit ad831a1176538f726428ebfe70f6607d7d854197 ]
Applied to dpdk-stable/17.11.
--yliu
>
> It is suggested to use PCI BDF to identify a port for port addition
> in OVS-DPDK. While mlx5 has its own naming style: name it by ib dev
> name. This breaks the typical OVS DPDK use case and brings more puzzle
> to the end users.
>
> To fix it, this patch changes it to use PCI BDF as the name, too.
> Also, a postfix " port %u" is added, just in case their might be more
> than 1 port associated with a PCI device.
>
> Signed-off-by: Yuanhan Liu <yliu@fridaylinux.org>
> Acked-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
> ---
> drivers/net/mlx5/mlx5.c | 20 +++++++-------------
> 1 file changed, 7 insertions(+), 13 deletions(-)
>
> diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c
> index a5eb3fd..912e53c 100644
> --- a/drivers/net/mlx5/mlx5.c
> +++ b/drivers/net/mlx5/mlx5.c
> @@ -662,6 +662,8 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv, struct rte_pci_device *pci_dev)
> INFO("%u port(s) detected", device_attr.orig_attr.phys_port_cnt);
>
> for (i = 0; i < device_attr.orig_attr.phys_port_cnt; i++) {
> + char name[RTE_ETH_NAME_MAX_LEN];
> + int len;
> uint32_t port = i + 1; /* ports are indexed from one */
> uint32_t test = (1 << i);
> struct ibv_context *ctx = NULL;
> @@ -685,14 +687,13 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv, struct rte_pci_device *pci_dev)
> .rx_vec_en = MLX5_ARG_UNSET,
> };
>
> + len = snprintf(name, sizeof(name), PCI_PRI_FMT,
> + pci_dev->addr.domain, pci_dev->addr.bus,
> + pci_dev->addr.devid, pci_dev->addr.function);
> +
> mlx5_dev[idx].ports |= test;
>
> if (mlx5_is_secondary()) {
> - /* from rte_ethdev.c */
> - char name[RTE_ETH_NAME_MAX_LEN];
> -
> - snprintf(name, sizeof(name), "%s port %u",
> - ibv_get_device_name(ibv_dev), port);
> eth_dev = rte_eth_dev_attach_secondary(name);
> if (eth_dev == NULL) {
> ERROR("can not attach rte ethdev");
> @@ -902,14 +903,7 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv, struct rte_pci_device *pci_dev)
> priv_get_mtu(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",
> - ibv_get_device_name(ibv_dev), port);
> - eth_dev = rte_eth_dev_allocate(name);
> - }
> + eth_dev = rte_eth_dev_allocate(name);
> if (eth_dev == NULL) {
> ERROR("can not allocate rte ethdev");
> err = ENOMEM;
> --
> 2.7.4
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2018-02-11 3:38 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-02-11 3:35 [dpdk-stable] [PATCH 17.11] net/mlx5: use PCI address as port name Yuanhan Liu
2018-02-11 3:38 ` Yuanhan Liu
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).