iavf: Add net_shaper_ops support

Implement net_shaper_ops support for IAVF. This enables configuration
of rate limiting on per queue basis. Customer intends to enforce
bandwidth limit on Tx traffic steered to the queue by configuring
rate limits on the queue.

To set rate limiting for a queue, update shaper object of given queues
in driver and send VIRTCHNL_OP_CONFIG_QUEUE_BW to PF to update HW
configuration.

Deleting shaper configured for queue is nothing but configuring shaper
with bw_max 0. The PF restores the default rate limiting config
when bw_max is zero.

Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Sudheer Mogilappagari <sudheer.mogilappagari@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Link: https://patch.msgid.link/5a882cb51998c4c2c3d21fed521498eba1c8f079.1728460186.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/intel/Kconfig

@@ -258,6 +258,7 @@ config I40E_DCB
 config IAVF
 	tristate
 	select LIBIE
+	select NET_SHAPER
 
 config I40EVF
 	tristate "Intel(R) Ethernet Adaptive Virtual Function support"

drivers/net/ethernet/intel/iavf/iavf.h

@@ -34,6 +34,7 @@
 #include <net/tc_act/tc_gact.h>
 #include <net/tc_act/tc_mirred.h>
 #include <net/tc_act/tc_skbedit.h>
+#include <net/net_shaper.h>
 
 #include "iavf_type.h"
 #include <linux/avf/virtchnl.h>
@@ -336,6 +337,7 @@ struct iavf_adapter {
 #define IAVF_FLAG_AQ_DISABLE_CTAG_VLAN_INSERTION	BIT_ULL(36)
 #define IAVF_FLAG_AQ_ENABLE_STAG_VLAN_INSERTION		BIT_ULL(37)
 #define IAVF_FLAG_AQ_DISABLE_STAG_VLAN_INSERTION	BIT_ULL(38)
+#define IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW		BIT_ULL(39)
 
 	/* flags for processing extended capability messages during
 	 * __IAVF_INIT_EXTENDED_CAPS. Each capability exchange requires
@@ -581,6 +583,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 int iavf_config_rss(struct iavf_adapter *adapter);
 int iavf_lan_add_device(struct iavf_adapter *adapter);
 int iavf_lan_del_device(struct iavf_adapter *adapter);
+void iavf_cfg_queues_bw(struct iavf_adapter *adapter);
 void iavf_enable_channels(struct iavf_adapter *adapter);
 void iavf_disable_channels(struct iavf_adapter *adapter);
 void iavf_add_cloud_filter(struct iavf_adapter *adapter);

drivers/net/ethernet/intel/iavf/iavf_main.c

@@ -1972,8 +1972,11 @@ static void iavf_finish_config(struct work_struct *work)
 
 	adapter = container_of(work, struct iavf_adapter, finish_config);
 
-	/* Always take RTNL first to prevent circular lock dependency */
+	/* Always take RTNL first to prevent circular lock dependency;
+	 * The dev->lock is needed to update the queue number
+	 */
 	rtnl_lock();
+	mutex_lock(&adapter->netdev->lock);
 	mutex_lock(&adapter->crit_lock);
 
 	if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES) &&
@@ -2017,6 +2020,7 @@ static void iavf_finish_config(struct work_struct *work)
 
 out:
 	mutex_unlock(&adapter->crit_lock);
+	mutex_unlock(&adapter->netdev->lock);
 	rtnl_unlock();
 }
 
@@ -2085,6 +2089,11 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter)
 		return 0;
 	}
 
+	if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW) {
+		iavf_cfg_queues_bw(adapter);
+		return 0;
+	}
+
 	if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_QUEUES) {
 		iavf_configure_queues(adapter);
 		return 0;
@@ -2918,6 +2927,30 @@ static void iavf_disable_vf(struct iavf_adapter *adapter)
 	dev_info(&adapter->pdev->dev, "Reset task did not complete, VF disabled\n");
 }
 
+/**
+ * iavf_reconfig_qs_bw - Call-back task to handle hardware reset
+ * @adapter: board private structure
+ *
+ * After a reset, the shaper parameters of queues need to be replayed again.
+ * Since the net_shaper object inside TX rings persists across reset,
+ * set the update flag for all queues so that the virtchnl message is triggered
+ * for all queues.
+ **/
+static void iavf_reconfig_qs_bw(struct iavf_adapter *adapter)
+{
+	int i, num = 0;
+
+	for (i = 0; i < adapter->num_active_queues; i++)
+		if (adapter->tx_rings[i].q_shaper.bw_min ||
+		    adapter->tx_rings[i].q_shaper.bw_max) {
+			adapter->tx_rings[i].q_shaper_update = true;
+			num++;
+		}
+
+	if (num)
+		adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW;
+}
+
 /**
  * iavf_reset_task - Call-back task to handle hardware reset
  * @work: pointer to work_struct
@@ -2944,10 +2977,12 @@ static void iavf_reset_task(struct work_struct *work)
 	/* When device is being removed it doesn't make sense to run the reset
 	 * task, just return in such a case.
 	 */
+	mutex_lock(&netdev->lock);
 	if (!mutex_trylock(&adapter->crit_lock)) {
 		if (adapter->state != __IAVF_REMOVE)
 			queue_work(adapter->wq, &adapter->reset_task);
 
+		mutex_unlock(&netdev->lock);
 		return;
 	}
 
@@ -2995,6 +3030,7 @@ static void iavf_reset_task(struct work_struct *work)
 			reg_val);
 		iavf_disable_vf(adapter);
 		mutex_unlock(&adapter->crit_lock);
+		mutex_unlock(&netdev->lock);
 		return; /* Do not attempt to reinit. It's dead, Jim. */
 	}
 
@@ -3124,6 +3160,8 @@ static void iavf_reset_task(struct work_struct *work)
 		iavf_up_complete(adapter);
 
 		iavf_irq_enable(adapter, true);
+
+		iavf_reconfig_qs_bw(adapter);
 	} else {
 		iavf_change_state(adapter, __IAVF_DOWN);
 		wake_up(&adapter->down_waitqueue);
@@ -3133,6 +3171,7 @@ static void iavf_reset_task(struct work_struct *work)
 
 	wake_up(&adapter->reset_waitqueue);
 	mutex_unlock(&adapter->crit_lock);
+	mutex_unlock(&netdev->lock);
 
 	return;
 reset_err:
@@ -3143,6 +3182,7 @@ static void iavf_reset_task(struct work_struct *work)
 	iavf_disable_vf(adapter);
 
 	mutex_unlock(&adapter->crit_lock);
+	mutex_unlock(&netdev->lock);
 	dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n");
 }
 
@@ -3614,8 +3654,10 @@ static int __iavf_setup_tc(struct net_device *netdev, void *type_data)
 	if (test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section))
 		return 0;
 
+	mutex_lock(&netdev->lock);
 	netif_set_real_num_rx_queues(netdev, total_qps);
 	netif_set_real_num_tx_queues(netdev, total_qps);
+	mutex_unlock(&netdev->lock);
 
 	return ret;
 }
@@ -4893,6 +4935,73 @@ static netdev_features_t iavf_fix_features(struct net_device *netdev,
 	return iavf_fix_strip_features(adapter, features);
 }
 
+static int
+iavf_shaper_set(struct net_shaper_binding *binding,
+		const struct net_shaper *shaper,
+		struct netlink_ext_ack *extack)
+{
+	struct iavf_adapter *adapter = netdev_priv(binding->netdev);
+	const struct net_shaper_handle *handle = &shaper->handle;
+	struct iavf_ring *tx_ring;
+
+	mutex_lock(&adapter->crit_lock);
+	if (handle->id >= adapter->num_active_queues)
+		goto unlock;
+
+	tx_ring = &adapter->tx_rings[handle->id];
+
+	tx_ring->q_shaper.bw_min = div_u64(shaper->bw_min, 1000);
+	tx_ring->q_shaper.bw_max = div_u64(shaper->bw_max, 1000);
+	tx_ring->q_shaper_update = true;
+
+	adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW;
+
+unlock:
+	mutex_unlock(&adapter->crit_lock);
+	return 0;
+}
+
+static int iavf_shaper_del(struct net_shaper_binding *binding,
+			   const struct net_shaper_handle *handle,
+			   struct netlink_ext_ack *extack)
+{
+	struct iavf_adapter *adapter = netdev_priv(binding->netdev);
+	struct iavf_ring *tx_ring;
+
+	mutex_lock(&adapter->crit_lock);
+	if (handle->id >= adapter->num_active_queues)
+		goto unlock;
+
+	tx_ring = &adapter->tx_rings[handle->id];
+	tx_ring->q_shaper.bw_min = 0;
+	tx_ring->q_shaper.bw_max = 0;
+	tx_ring->q_shaper_update = true;
+
+	adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW;
+
+unlock:
+	mutex_unlock(&adapter->crit_lock);
+	return 0;
+}
+
+static void iavf_shaper_cap(struct net_shaper_binding *binding,
+			    enum net_shaper_scope scope,
+			    unsigned long *flags)
+{
+	if (scope != NET_SHAPER_SCOPE_QUEUE)
+		return;
+
+	*flags = BIT(NET_SHAPER_A_CAPS_SUPPORT_BW_MIN) |
+		 BIT(NET_SHAPER_A_CAPS_SUPPORT_BW_MAX) |
+		 BIT(NET_SHAPER_A_CAPS_SUPPORT_METRIC_BPS);
+}
+
+static const struct net_shaper_ops iavf_shaper_ops = {
+	.set = iavf_shaper_set,
+	.delete = iavf_shaper_del,
+	.capabilities = iavf_shaper_cap,
+};
+
 static const struct net_device_ops iavf_netdev_ops = {
 	.ndo_open		= iavf_open,
 	.ndo_stop		= iavf_close,
@@ -4908,6 +5017,7 @@ static const struct net_device_ops iavf_netdev_ops = {
 	.ndo_fix_features	= iavf_fix_features,
 	.ndo_set_features	= iavf_set_features,
 	.ndo_setup_tc		= iavf_setup_tc,
+	.net_shaper_ops		= &iavf_shaper_ops,
 };
 
 /**

drivers/net/ethernet/intel/iavf/iavf_txrx.h

@@ -296,6 +296,8 @@ struct iavf_ring {
 					 */
 
 	u32 rx_buf_len;
+	struct net_shaper q_shaper;
+	bool q_shaper_update;
 } ____cacheline_internodealigned_in_smp;
 
 #define IAVF_ITR_ADAPTIVE_MIN_INC	0x0002

drivers/net/ethernet/intel/iavf/iavf_virtchnl.c

@@ -1507,6 +1507,60 @@ iavf_set_adapter_link_speed_from_vpe(struct iavf_adapter *adapter,
 		adapter->link_speed = vpe->event_data.link_event.link_speed;
 }
 
+/**
+ * iavf_cfg_queues_bw - configure bandwidth of allocated queues
+ * @adapter: iavf adapter structure instance
+ *
+ * This function requests PF to configure queue bandwidth of allocated queues
+ */
+void iavf_cfg_queues_bw(struct iavf_adapter *adapter)
+{
+	struct virtchnl_queues_bw_cfg *qs_bw_cfg;
+	struct net_shaper *q_shaper;
+	int qs_to_update = 0;
+	int i, inx = 0;
+	size_t len;
+
+	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
+		/* bail because we already have a command pending */
+		dev_err(&adapter->pdev->dev,
+			"Cannot set tc queue bw, command %d pending\n",
+			adapter->current_op);
+		return;
+	}
+
+	for (i = 0; i < adapter->num_active_queues; i++) {
+		if (adapter->tx_rings[i].q_shaper_update)
+			qs_to_update++;
+	}
+	len = struct_size(qs_bw_cfg, cfg, qs_to_update);
+	qs_bw_cfg = kzalloc(len, GFP_KERNEL);
+	if (!qs_bw_cfg)
+		return;
+
+	qs_bw_cfg->vsi_id = adapter->vsi.id;
+	qs_bw_cfg->num_queues = qs_to_update;
+
+	for (i = 0; i < adapter->num_active_queues; i++) {
+		struct iavf_ring *tx_ring = &adapter->tx_rings[i];
+
+		q_shaper = &tx_ring->q_shaper;
+		if (tx_ring->q_shaper_update) {
+			qs_bw_cfg->cfg[inx].queue_id = i;
+			qs_bw_cfg->cfg[inx].shaper.peak = q_shaper->bw_max;
+			qs_bw_cfg->cfg[inx].shaper.committed = q_shaper->bw_min;
+			qs_bw_cfg->cfg[inx].tc = 0;
+			inx++;
+		}
+	}
+
+	adapter->current_op = VIRTCHNL_OP_CONFIG_QUEUE_BW;
+	adapter->aq_required &= ~IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW;
+	iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_QUEUE_BW,
+			 (u8 *)qs_bw_cfg, len);
+	kfree(qs_bw_cfg);
+}
+
 /**
  * iavf_enable_channels
  * @adapter: adapter structure
@@ -2227,6 +2281,10 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 					VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC;
 
 			break;
+		case VIRTCHNL_OP_CONFIG_QUEUE_BW:
+			dev_warn(&adapter->pdev->dev, "Failed to Config Queue BW, error %s\n",
+				 iavf_stat_str(&adapter->hw, v_retval));
+			break;
 		default:
 			dev_err(&adapter->pdev->dev, "PF returned error %d (%s) to our request %d\n",
 				v_retval, iavf_stat_str(&adapter->hw, v_retval),
@@ -2569,6 +2627,13 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 		if (!v_retval)
 			iavf_netdev_features_vlan_strip_set(netdev, false);
 		break;
+	case VIRTCHNL_OP_CONFIG_QUEUE_BW: {
+		int i;
+		/* shaper configuration is successful for all queues */
+		for (i = 0; i < adapter->num_active_queues; i++)
+			adapter->tx_rings[i].q_shaper_update = false;
+	}
+		break;
 	default:
 		if (adapter->current_op && (v_opcode != adapter->current_op))
 			dev_warn(&adapter->pdev->dev, "Expected response %d from PF, received %d\n",