Merge branch 'support-bandwidth-clamping-in-mana-using-net-shapers'

Erni Sri Satya Vennela says:

====================
Support bandwidth clamping in mana using net shapers

This patchset introduces hardware-backed bandwidth rate limiting
for MANA NICs via the net_shaper_ops interface, enabling efficient and
fine-grained traffic shaping directly on the device.

Previously, MANA lacked a mechanism for user-configurable bandwidth
control. With this addition, users can now configure shaping parameters,
allowing better traffic management and performance isolation.

The implementation includes the net_shaper_ops callbacks in the MANA
driver and supports one shaper per vport. Add shaping support via
mana_set_bw_clamp(), allowing the configuration of bandwidth rates
in 100 Mbps increments (minimum 100 Mbps). The driver validates input
and rejects unsupported values. On failure, it restores the previous
configuration which is queried using mana_query_link_cfg() or
retains the current state.

To prevent potential deadlocks introduced by net_shaper_ops, switch to
_locked variants of NAPI APIs when netdevops_lock is held during
VF setup and teardown.

Also, Add support for ethtool get_link_ksettings to report the maximum
link speed supported by the SKU in mbps.

These APIs when invoked on hardware that are older or that do
not support these APIs, the speed would be reported as UNKNOWN and
the net-shaper calls to set speed would fail.
====================

Link: https://patch.msgid.link/[e-mail]
Signed-off-by: Paolo Abeni <[e-mail]>

drivers/net/ethernet/microsoft/mana/hw_channel.c

···
 	}
 
 	if (ctx->status_code && ctx->status_code != GDMA_STATUS_MORE_ENTRIES) {
+		if (ctx->status_code == GDMA_STATUS_CMD_UNSUPPORTED) {
+			err = -EOPNOTSUPP;
+			goto out;
+		}
 		if (req_msg->req.msg_type != MANA_QUERY_PHY_STAT)
 			dev_err(hwc->dev, "HWC: Failed hw_channel req: 0x%x\n",
 				ctx->status_code);

drivers/net/ethernet/microsoft/mana/mana_en.c

···
 	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,
···
 	.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)
···
 	err = mana_gd_send_request(gc, in_len, in_buf, out_len,
 				   out_buf);
 	if (err || resp->status) {
+		if (err == -EOPNOTSUPP)
+			return err;
+
 		if (req->req.msg_type != MANA_QUERY_PHY_STAT)
 			dev_err(dev, "Failed to send mana message: %d, 0x%x\n",
 				err, resp->status);
···
 out:
 	kfree(req);
 	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) {
+		if (err == -EOPNOTSUPP) {
+			netdev_info_once(ndev, "MANA_QUERY_LINK_CONFIG not supported\n");
+			return 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;
+	apc->max_speed = resp.qos_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) {
+		if (err == -EOPNOTSUPP) {
+			netdev_info_once(ndev, "MANA_SET_BW_CLAMP not supported\n");
+			return 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,
···
 		napi = &apc->tx_qp[i].tx_cq.napi;
 		if (apc->tx_qp[i].txq.napi_initialized) {
 			napi_synchronize(napi);
-			napi_disable(napi);
-			netif_napi_del(napi);
+			netdev_lock_ops_to_full(napi->dev);
+			napi_disable_locked(napi);
+			netif_napi_del_locked(napi);
+			netdev_unlock_full_to_ops(napi->dev);
 			apc->tx_qp[i].txq.napi_initialized = false;
 		}
 		mana_destroy_wq_obj(apc, GDMA_SQ, apc->tx_qp[i].tx_object);
···
 
 		mana_create_txq_debugfs(apc, i);
 
-		netif_napi_add_tx(net, &cq->napi, mana_poll);
-		napi_enable(&cq->napi);
+		set_bit(NAPI_STATE_NO_BUSY_POLL, &cq->napi.state);
+		netdev_lock_ops_to_full(net);
+		netif_napi_add_locked(net, &cq->napi, mana_poll);
+		napi_enable_locked(&cq->napi);
+		netdev_unlock_full_to_ops(net);
 		txq->napi_initialized = true;
 
 		mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT);
···
 	if (napi_initialized) {
 		napi_synchronize(napi);
 
-		napi_disable(napi);
-
-		netif_napi_del(napi);
+		netdev_lock_ops_to_full(napi->dev);
+		napi_disable_locked(napi);
+		netif_napi_del_locked(napi);
+		netdev_unlock_full_to_ops(napi->dev);
 	}
 	xdp_rxq_info_unreg(&rxq->xdp_rxq);
 
···
 
 	gc->cq_table[cq->gdma_id] = cq->gdma_cq;
 
-	netif_napi_add_weight(ndev, &cq->napi, mana_poll, 1);
+	netdev_lock_ops_to_full(ndev);
+	netif_napi_add_weight_locked(ndev, &cq->napi, mana_poll, 1);
+	netdev_unlock_full_to_ops(ndev);
 
 	WARN_ON(xdp_rxq_info_reg(&rxq->xdp_rxq, ndev, rxq_idx,
 				 cq->napi.napi_id));
 	WARN_ON(xdp_rxq_info_reg_mem_model(&rxq->xdp_rxq, MEM_TYPE_PAGE_POOL,
 					   rxq->page_pool));
 
-	napi_enable(&cq->napi);
+	netdev_lock_ops_to_full(ndev);
+	napi_enable_locked(&cq->napi);
+	netdev_unlock_full_to_ops(ndev);
 
 	mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT);
 out:
···
 		netdev_err(ndev, "Unable to register netdev.\n");
 		goto free_indir;
 	}
+
+	debugfs_create_u32("current_speed", 0400, apc->mana_port_debugfs, &apc->speed);
 
 	return 0;
 

drivers/net/ethernet/microsoft/mana/mana_ethtool.c

···
 static int mana_get_link_ksettings(struct net_device *ndev,
 				   struct ethtool_link_ksettings *cmd)
 {
+	struct mana_port_context *apc = netdev_priv(ndev);
+	int err;
+
+	err = mana_query_link_cfg(apc);
+	cmd->base.speed = (err) ? SPEED_UNKNOWN : apc->max_speed;
+
 	cmd->base.duplex = DUPLEX_FULL;
 	cmd->base.port = PORT_OTHER;
 

include/net/mana/gdma.h

···
 #include "shm_channel.h"
 
 #define GDMA_STATUS_MORE_ENTRIES	0x00000105
+#define GDMA_STATUS_CMD_UNSUPPORTED	0xffffffff
 
 /* Structures labeled with "HW DATA" are exchanged with the hardware. All of
  * them are naturally aligned and hence don't need __packed.

include/net/mana/mana.h

···
 #define _MANA_H
 
 #include <net/xdp.h>
+#include <net/net_shaper.h>
 
 #include "gdma.h"
 #include "hw_channel.h"
···
 	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;
+	/* Maximum speed supported by the SKU (mbps) */
+	u32 max_speed;
 
 	bool port_is_up;
 	bool port_st_save; /* Saved port state */
···
 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);
···
 	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 */
···
 	MANA_REGISTER_HW_PORT	= 0x28003,
 	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 {