Message-ID:
 <DS7PR21MB3102B97C4255CD9417983F7ECE77A@DS7PR21MB3102.namprd21.prod.outlook.com>
Date: Fri, 13 Jun 2025 17:04:03 +0000
From: Long Li <longli@...rosoft.com>
To: Erni Sri Satya Vennela <ernis@...ux.microsoft.com>, KY Srinivasan
	<kys@...rosoft.com>, Haiyang Zhang <haiyangz@...rosoft.com>,
	"wei.liu@...nel.org" <wei.liu@...nel.org>, Dexuan Cui <decui@...rosoft.com>,
	"andrew+netdev@...n.ch" <andrew+netdev@...n.ch>, "davem@...emloft.net"
	<davem@...emloft.net>, "edumazet@...gle.com" <edumazet@...gle.com>,
	"kuba@...nel.org" <kuba@...nel.org>, "pabeni@...hat.com" <pabeni@...hat.com>,
	Konstantin Taranov <kotaranov@...rosoft.com>, "horms@...nel.org"
	<horms@...nel.org>, Shiraz Saleem <shirazsaleem@...rosoft.com>,
	"leon@...nel.org" <leon@...nel.org>, "shradhagupta@...ux.microsoft.com"
	<shradhagupta@...ux.microsoft.com>, "schakrabarti@...ux.microsoft.com"
	<schakrabarti@...ux.microsoft.com>, "gerhard@...leder-embedded.com"
	<gerhard@...leder-embedded.com>, "rosenp@...il.com" <rosenp@...il.com>,
	"sdf@...ichev.me" <sdf@...ichev.me>, "linux-hyperv@...r.kernel.org"
	<linux-hyperv@...r.kernel.org>, "netdev@...r.kernel.org"
	<netdev@...r.kernel.org>, "linux-kernel@...r.kernel.org"
	<linux-kernel@...r.kernel.org>, "linux-rdma@...r.kernel.org"
	<linux-rdma@...r.kernel.org>
Subject: RE: [PATCH net-next v2 2/4] net: mana: Add support for net_shaper_ops

> Subject: [PATCH net-next v2 2/4] net: mana: Add support for net_shaper_ops
> 
> Introduce support for net_shaper_ops in the MANA driver, enabling configuration
> of rate limiting on the MANA NIC.
> 
> To apply rate limiting, the driver issues a HWC command via
> mana_set_bw_clamp() and updates the corresponding shaper object in the
> net_shaper cache. If an error occurs during this process, the driver restores the
> previous speed by querying the current link configuration using
> mana_query_link_cfg().
> 
> The minimum supported bandwidth is 100 Mbps, and only values that are exact
> multiples of 100 Mbps are allowed. Any other values are rejected.
> 
> To remove a shaper, the driver resets the bandwidth to the maximum supported
> by the SKU using mana_set_bw_clamp() and clears the associated cache entry. If
> an error occurs during this process, the shaper details are retained.
> 
> On the hardware that does not support these APIs, the net-shaper calls to set
> speed would fail.
> 
> Set the speed:
> ./tools/net/ynl/pyynl/cli.py \
>  --spec Documentation/netlink/specs/net_shaper.yaml \  --do set --json
> '{"ifindex":'$IFINDEX',
> 		   "handle":{"scope": "netdev", "id":'$ID' },
> 		   "bw-max": 200000000 }'
> 
> Get the shaper details:
> ./tools/net/ynl/pyynl/cli.py \
>  --spec Documentation/netlink/specs/net_shaper.yaml \  --do get --json
> '{"ifindex":'$IFINDEX',
> 		      "handle":{"scope": "netdev", "id":'$ID' }}'
> 
> > {'bw-max': 200000000,
> > 'handle': {'scope': 'netdev'},
> > 'ifindex': $IFINDEX,
> > 'metric': 'bps'}
> 
> Delete the shaper object:
> ./tools/net/ynl/pyynl/cli.py \
>  --spec Documentation/netlink/specs/net_shaper.yaml \  --do delete --json
> '{"ifindex":'$IFINDEX',
> 		      "handle":{"scope": "netdev","id":'$ID' }}'
> 
> Signed-off-by: Erni Sri Satya Vennela <ernis@...ux.microsoft.com>
> Reviewed-by: Haiyang Zhang <haiyangz@...rosoft.com>
> Reviewed-by: Shradha Gupta <shradhagupta@...ux.microsoft.com>
> Reviewed-by: Saurabh Singh Sengar <ssengar@...ux.microsoft.com>

Reviewed-by: Long Li <longli@...rosoft.com>

> ---
> Changes in v2:
> * No change.
> ---
>  drivers/net/ethernet/microsoft/mana/mana_en.c | 155 ++++++++++++++++++
>  include/net/mana/mana.h                       |  40 +++++
>  2 files changed, 195 insertions(+)
> 
> diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c
> b/drivers/net/ethernet/microsoft/mana/mana_en.c
> index ca5e9c3d374b..7e8bc2c6a194 100644
> --- a/drivers/net/ethernet/microsoft/mana/mana_en.c
> +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
> @@ -719,6 +719,78 @@ static int mana_change_mtu(struct net_device *ndev,
> int new_mtu)
>  	return err;
>  }
> 
> +static int mana_shaper_set(struct net_shaper_binding *binding,
> +			   const struct net_shaper *shaper,
> +			   struct netlink_ext_ack *extack)
> +{
> +	struct mana_port_context *apc = netdev_priv(binding->netdev);
> +	u32 old_speed, rate;
> +	int err;
> +
> +	if (shaper->handle.scope != NET_SHAPER_SCOPE_NETDEV) {
> +		NL_SET_ERR_MSG_MOD(extack, "net shaper scope should be
> netdev");
> +		return -EINVAL;
> +	}
> +
> +	if (apc->handle.id && shaper->handle.id != apc->handle.id) {
> +		NL_SET_ERR_MSG_MOD(extack, "Cannot create multiple
> shapers");
> +		return -EOPNOTSUPP;
> +	}
> +
> +	if (!shaper->bw_max || (shaper->bw_max % 100000000)) {
> +		NL_SET_ERR_MSG_MOD(extack, "Please use multiples of
> 100Mbps for bandwidth");
> +		return -EINVAL;
> +	}
> +
> +	rate = div_u64(shaper->bw_max, 1000); /* Convert bps to Kbps */
> +	rate = div_u64(rate, 1000);	      /* Convert Kbps to Mbps */
> +
> +	/* Get current speed */
> +	err = mana_query_link_cfg(apc);
> +	old_speed = (err) ? SPEED_UNKNOWN : apc->speed;
> +
> +	if (!err) {
> +		err = mana_set_bw_clamp(apc, rate, TRI_STATE_TRUE);
> +		apc->speed = (err) ? old_speed : rate;
> +		apc->handle = (err) ? apc->handle : shaper->handle;
> +	}
> +
> +	return err;
> +}
> +
> +static int mana_shaper_del(struct net_shaper_binding *binding,
> +			   const struct net_shaper_handle *handle,
> +			   struct netlink_ext_ack *extack)
> +{
> +	struct mana_port_context *apc = netdev_priv(binding->netdev);
> +	int err;
> +
> +	err = mana_set_bw_clamp(apc, 0, TRI_STATE_FALSE);
> +
> +	if (!err) {
> +		/* Reset mana port context parameters */
> +		apc->handle.id = 0;
> +		apc->handle.scope = NET_SHAPER_SCOPE_UNSPEC;
> +		apc->speed = 0;
> +	}
> +
> +	return err;
> +}
> +
> +static void mana_shaper_cap(struct net_shaper_binding *binding,
> +			    enum net_shaper_scope scope,
> +			    unsigned long *flags)
> +{
> +	*flags = BIT(NET_SHAPER_A_CAPS_SUPPORT_BW_MAX) |
> +		 BIT(NET_SHAPER_A_CAPS_SUPPORT_METRIC_BPS);
> +}
> +
> +static const struct net_shaper_ops mana_shaper_ops = {
> +	.set = mana_shaper_set,
> +	.delete = mana_shaper_del,
> +	.capabilities = mana_shaper_cap,
> +};
> +
>  static const struct net_device_ops mana_devops = {
>  	.ndo_open		= mana_open,
>  	.ndo_stop		= mana_close,
> @@ -729,6 +801,7 @@ static const struct net_device_ops mana_devops = {
>  	.ndo_bpf		= mana_bpf,
>  	.ndo_xdp_xmit		= mana_xdp_xmit,
>  	.ndo_change_mtu		= mana_change_mtu,
> +	.net_shaper_ops         = &mana_shaper_ops,
>  };
> 
>  static void mana_cleanup_port_context(struct mana_port_context *apc) @@ -
> 1162,6 +1235,86 @@ static int mana_cfg_vport_steering(struct
> mana_port_context *apc,
>  	return err;
>  }
> 
> +int mana_query_link_cfg(struct mana_port_context *apc) {
> +	struct net_device *ndev = apc->ndev;
> +	struct mana_query_link_config_resp resp = {};
> +	struct mana_query_link_config_req req = {};
> +	int err;
> +
> +	mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_LINK_CONFIG,
> +			     sizeof(req), sizeof(resp));
> +
> +	req.vport = apc->port_handle;
> +	req.hdr.resp.msg_version = GDMA_MESSAGE_V2;
> +
> +	err = mana_send_request(apc->ac, &req, sizeof(req), &resp,
> +				sizeof(resp));
> +
> +	if (err) {
> +		netdev_err(ndev, "Failed to query link config: %d\n", err);
> +		return err;
> +	}
> +
> +	err = mana_verify_resp_hdr(&resp.hdr, MANA_QUERY_LINK_CONFIG,
> +				   sizeof(resp));
> +
> +	if (err || resp.hdr.status) {
> +		netdev_err(ndev, "Failed to query link config: %d, 0x%x\n", err,
> +			   resp.hdr.status);
> +		if (!err)
> +			err = -EOPNOTSUPP;
> +		return err;
> +	}
> +
> +	if (resp.qos_unconfigured) {
> +		err = -EINVAL;
> +		return err;
> +	}
> +	apc->speed = resp.link_speed_mbps;
> +	return 0;
> +}
> +
> +int mana_set_bw_clamp(struct mana_port_context *apc, u32 speed,
> +		      int enable_clamping)
> +{
> +	struct mana_set_bw_clamp_resp resp = {};
> +	struct mana_set_bw_clamp_req req = {};
> +	struct net_device *ndev = apc->ndev;
> +	int err;
> +
> +	mana_gd_init_req_hdr(&req.hdr, MANA_SET_BW_CLAMP,
> +			     sizeof(req), sizeof(resp));
> +	req.vport = apc->port_handle;
> +	req.link_speed_mbps = speed;
> +	req.enable_clamping = enable_clamping;
> +
> +	err = mana_send_request(apc->ac, &req, sizeof(req), &resp,
> +				sizeof(resp));
> +
> +	if (err) {
> +		netdev_err(ndev, "Failed to set bandwidth clamp for speed %u,
> err = %d",
> +			   speed, err);
> +		return err;
> +	}
> +
> +	err = mana_verify_resp_hdr(&resp.hdr, MANA_SET_BW_CLAMP,
> +				   sizeof(resp));
> +
> +	if (err || resp.hdr.status) {
> +		netdev_err(ndev, "Failed to set bandwidth clamp: %d, 0x%x\n",
> err,
> +			   resp.hdr.status);
> +		if (!err)
> +			err = -EOPNOTSUPP;
> +		return err;
> +	}
> +
> +	if (resp.qos_unconfigured)
> +		netdev_info(ndev, "QoS is unconfigured\n");
> +
> +	return 0;
> +}
> +
>  int mana_create_wq_obj(struct mana_port_context *apc,
>  		       mana_handle_t vport,
>  		       u32 wq_type, struct mana_obj_spec *wq_spec, @@ -3013,6
> +3166,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
>  		goto free_indir;
>  	}
> 
> +	debugfs_create_u32("current_speed", 0400, apc->mana_port_debugfs,
> +&apc->speed);
> +
>  	return 0;
> 
>  free_indir:
> diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index
> 4176edf1be71..038b18340e51 100644
> --- a/include/net/mana/mana.h
> +++ b/include/net/mana/mana.h
> @@ -5,6 +5,7 @@
>  #define _MANA_H
> 
>  #include <net/xdp.h>
> +#include <net/net_shaper.h>
> 
>  #include "gdma.h"
>  #include "hw_channel.h"
> @@ -526,7 +527,12 @@ struct mana_port_context {
>  	struct mutex vport_mutex;
>  	int vport_use_count;
> 
> +	/* Net shaper handle*/
> +	struct net_shaper_handle handle;
> +
>  	u16 port_idx;
> +	/* Currently configured speed (mbps) */
> +	u32 speed;
> 
>  	bool port_is_up;
>  	bool port_st_save; /* Saved port state */ @@ -562,6 +568,9 @@ struct
> bpf_prog *mana_xdp_get(struct mana_port_context *apc);  void
> mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog);  int
> mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf);  void
> mana_query_gf_stats(struct mana_port_context *apc);
> +int mana_query_link_cfg(struct mana_port_context *apc); int
> +mana_set_bw_clamp(struct mana_port_context *apc, u32 speed,
> +		      int enable_clamping);
>  void mana_query_phy_stats(struct mana_port_context *apc);  int
> mana_pre_alloc_rxbufs(struct mana_port_context *apc, int mtu, int
> num_queues);  void mana_pre_dealloc_rxbufs(struct mana_port_context *apc);
> @@ -589,6 +598,8 @@ enum mana_command_code {
>  	MANA_FENCE_RQ		= 0x20006,
>  	MANA_CONFIG_VPORT_RX	= 0x20007,
>  	MANA_QUERY_VPORT_CONFIG	= 0x20008,
> +	MANA_QUERY_LINK_CONFIG	= 0x2000A,
> +	MANA_SET_BW_CLAMP	= 0x2000B,
>  	MANA_QUERY_PHY_STAT     = 0x2000c,
> 
>  	/* Privileged commands for the PF mode */ @@ -598,6 +609,35 @@
> enum mana_command_code {
>  	MANA_DEREGISTER_HW_PORT	= 0x28004,
>  };
> 
> +/* Query Link Configuration*/
> +struct mana_query_link_config_req {
> +	struct gdma_req_hdr hdr;
> +	mana_handle_t vport;
> +}; /* HW DATA */
> +
> +struct mana_query_link_config_resp {
> +	struct gdma_resp_hdr hdr;
> +	u32 qos_speed_mbps;
> +	u8 qos_unconfigured;
> +	u8 reserved1[3];
> +	u32 link_speed_mbps;
> +	u8 reserved2[4];
> +}; /* HW DATA */
> +
> +/* Set Bandwidth Clamp*/
> +struct mana_set_bw_clamp_req {
> +	struct gdma_req_hdr hdr;
> +	mana_handle_t vport;
> +	enum TRI_STATE enable_clamping;
> +	u32 link_speed_mbps;
> +}; /* HW DATA */
> +
> +struct mana_set_bw_clamp_resp {
> +	struct gdma_resp_hdr hdr;
> +	u8 qos_unconfigured;
> +	u8 reserved[7];
> +}; /* HW DATA */
> +
>  /* Query Device Configuration */
>  struct mana_query_device_cfg_req {
>  	struct gdma_req_hdr hdr;
> --
> 2.34.1

Powered by blists - more mailing lists