linux-kernel - Re: [PATCH v3 for-next] RDMA/core: Get IB width and speed from netdev

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Date:   Wed, 12 Jul 2023 15:35:30 +0300
From:   Leon Romanovsky <leon@...nel.org>
To:     Junxian Huang <huangjunxian6@...ilicon.com>
Cc:     jgg@...dia.com, linux-rdma@...r.kernel.org, linuxarm@...wei.com,
        linux-kernel@...r.kernel.org
Subject: Re: [PATCH v3 for-next] RDMA/core: Get IB width and speed from netdev

On Fri, Jul 07, 2023 at 06:56:34PM +0800, Junxian Huang wrote:
> From: Haoyue Xu <xuhaoyue1@...ilicon.com>
> 
> Previously, there was no way to query the number of lanes for a network
> card, so the same netdev_speed would result in a fixed pair of width and
> speed. As network card specifications become more diverse, such fixed
> mode is no longer suitable, so a method is needed to obtain the correct
> width and speed based on the number of lanes.
> 
> This patch retrieves netdev lanes and speed from net_device and
> translates them to IB width and speed. Also, add a generic function
> to translating netdev speed to IB speed.
> 
> Signed-off-by: Haoyue Xu <xuhaoyue1@...ilicon.com>
> Signed-off-by: Luoyouming <luoyouming@...wei.com>
> Signed-off-by: Junxian Huang <huangjunxian6@...ilicon.com>
> ---
>  drivers/infiniband/core/verbs.c | 17 +++++++++++++++--
>  include/rdma/ib_verbs.h         | 26 ++++++++++++++++++++++++++
>  2 files changed, 41 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
> index b99b3cc283b6..55a3ac9d01e2 100644
> --- a/drivers/infiniband/core/verbs.c
> +++ b/drivers/infiniband/core/verbs.c
> @@ -1880,6 +1880,13 @@ int ib_modify_qp_with_udata(struct ib_qp *ib_qp, struct ib_qp_attr *attr,
>  }
>  EXPORT_SYMBOL(ib_modify_qp_with_udata);
>  
> +static void ib_get_width_and_speed(u32 netdev_speed, u32 lanes,
> +				   u16 *speed, u8 *width)
> +{
> +	*width = ib_int_to_ib_width(lanes);
> +	*speed = ib_eth_to_ib_speed(netdev_speed / lanes);
> +}
> +
>  int ib_get_eth_speed(struct ib_device *dev, u32 port_num, u16 *speed, u8 *width)
>  {
>  	int rc;
> @@ -1902,10 +1909,16 @@ int ib_get_eth_speed(struct ib_device *dev, u32 port_num, u16 *speed, u8 *width)
>  
>  	if (!rc && lksettings.base.speed != (u32)SPEED_UNKNOWN) {
>  		netdev_speed = lksettings.base.speed;
> +		if (lksettings.lanes) {
> +			ib_get_width_and_speed(netdev_speed, lksettings.lanes,
> +					       speed, width);

Please move this function to be after "if {} else {}" section and combine
with *width/*speed calculations at the bottom of ib_get_eth_speed()
function.

> +			return 0;
> +		}
>  	} else {
>  		netdev_speed = SPEED_1000;
> -		pr_warn("%s speed is unknown, defaulting to %u\n", netdev->name,
> -			netdev_speed);
> +		if (rc)

No need to remove this if ().

> +			pr_warn("%s speed is unknown, defaulting to %u\n",
> +				netdev->name, netdev_speed);
>  	}
>  
>  	if (netdev_speed <= SPEED_1000) {
> diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
> index 1e7774ac808f..7dc926ec7fee 100644
> --- a/include/rdma/ib_verbs.h
> +++ b/include/rdma/ib_verbs.h
> @@ -552,6 +552,18 @@ static inline int ib_width_enum_to_int(enum ib_port_width width)
>  	}
>  }
>  
> +static inline int ib_int_to_ib_width(u32 lanes)
> +{

<...>

> +static inline int ib_eth_to_ib_speed(u32 speed)
> +{

These two functions shouldn't be part in global include file.

Please embed them into ib_get_width_and_speed().

Thanks