Merge branch 'net-introduce-tx-h-w-shaping-api'

Paolo Abeni says:

====================
net: introduce TX H/W shaping API

We have a plurality of shaping-related drivers API, but none flexible
enough to meet existing demand from vendors[1].

This series introduces new device APIs to configure in a flexible way
TX H/W shaping. The new functionalities are exposed via a newly
defined generic netlink interface and include introspection
capabilities. Some self-tests are included, on top of a dummy
netdevsim implementation. Finally a basic implementation for the iavf
driver is provided.

Some usage examples:

* Configure shaping on a given queue:

./tools/net/ynl/cli.py --spec Documentation/netlink/specs/shaper.yaml \
	--do set --json '{"ifindex": '$IFINDEX',
			  "shaper": {"handle":
				     {"scope": "queue", "id":'$QUEUEID'},
			  "bw-max": 2000000}}'

* Container B/W sharing

The orchestration infrastructure wants to group the
container-related queues under a RR scheduling and limit the aggregate
bandwidth:

./tools/net/ynl/cli.py --spec Documentation/netlink/specs/shaper.yaml \
	--do group --json '{"ifindex": '$IFINDEX',
			"leaves": [
			  {"handle": {"scope": "queue", "id":'$QID1'},
			   "weight": '$W1'},
			  {"handle": {"scope": "queue", "id":'$QID2'},
			   "weight": '$W2'}],
			  {"handle": {"scope": "queue", "id":'$QID3'},
			   "weight": '$W3'}],
			"handle": {"scope":"node"},
			"bw-max": 10000000}'
{'ifindex': $IFINDEX, 'handle': {'scope': 'node', 'id': 0}}

Q1 \
    \
Q2 -- node 0 -------  netdev
    / (bw-max: 10M)
Q3 /

* Delegation

A containers wants to limit the aggregate B/W bandwidth of 2 of the 3
queues it owns - the starting configuration is the one from the
previous point:

SPEC=Documentation/netlink/specs/net_shaper.yaml
./tools/net/ynl/cli.py --spec $SPEC \
	--do group --json '{"ifindex": '$IFINDEX',
			"leaves": [
			  {"handle": {"scope": "queue", "id":'$QID1'},
			   "weight": '$W1'},
			  {"handle": {"scope": "queue", "id":'$QID2'},
			   "weight": '$W2'}],
			"handle": {"scope": "node"},
			"bw-max": 5000000 }'
{'ifindex': $IFINDEX, 'handle': {'scope': 'node', 'id': 1}}

Q1 -- node 1 --------\
    / (bw-max: 5M)    \
Q2 /                   node 0 -------  netdev
                      /(bw-max: 10M)
Q3 ------------------/

In a group operation, when prior to the op itself, the leaves have
different parents, the user must specify the parent handle for the
group. I.e., starting from the previous config:

./tools/net/ynl/cli.py --spec $SPEC \
	--do group --json '{"ifindex": '$IFINDEX',
			"leaves": [
			  {"handle": {"scope": "queue", "id":'$QID1'},
			   "weight": '$W1'},
			  {"handle": {"scope": "queue", "id":'$QID3'},
			   "weight": '$W3'}],
			"handle": {"scope": "node"},
			"bw-max": 3000000 }'
Netlink error: Invalid argument
nl_len = 96 (80) nl_flags = 0x300 nl_type = 2
	error: -22
	extack: {'msg': 'All the leaves shapers must have the same old parent'}

./tools/net/ynl/cli.py --spec $SPEC \
	--do group --json '{"ifindex": '$IFINDEX',
			"leaves": [
			  {"handle": {"scope": "queue", "id":'$QID1'},
			   "weight": '$W1'},
			  {"handle": {"scope": "queue", "id":'$QID3'},
			   "weight": '$W3'}],
			"handle": {"scope": "node"},
			"parent": {"scope": "node", "id": 1},
			"bw-max": 3000000 }
{'ifindex': $IFINDEX, 'handle': {'scope': 'node', 'id': 2}}

Q1 -- node 2 ---
    /(bw-max:3M)\
Q3 /             \
         ---- node 1 \
        / (bw-max: 5M)\
      Q2              node 0 -------  netdev
                      (bw-max: 10M)

* Cleanup:

Still starting from config 1To delete a single queue shaper

./tools/net/ynl/cli.py --spec $SPEC --do delete --json \
	'{"ifindex": '$IFINDEX',
	  "handle": {"scope": "queue", "id":'$QID3'}}'

Q1 -- node 2 ---
     (bw-max:3M)\
                 \
         ---- node 1 \
        / (bw-max: 5M)\
      Q2              node 0 -------  netdev
                      (bw-max: 10M)

Deleting a node shaper relinks all its leaves to the node's parent:

./tools/net/ynl/cli.py --spec $SPEC --do delete --json \
	'{"ifindex": '$IFINDEX',
	  "handle": {"scope": "node", "id":2}}'

Q1 ---\
       \
        node 1----- \
       / (bw-max: 5M)\
Q2----/              node 0 -------  netdev
                     (bw-max: 10M)

Deleting the last shaper under a node shaper deletes the node, too:

./tools/net/ynl/cli.py --spec $SPEC --do delete --json \
	'{"ifindex": '$IFINDEX',
	  "handle": {"scope": "queue", "id":'$QID1'}}'
./tools/net/ynl/cli.py --spec $SPEC --do delete --json \
	'{"ifindex": '$IFINDEX',
	  "handle": {"scope": "queue", "id":'$QID2'}}'
./tools/net/ynl/cli.py --spec $SPEC --do get --json \
	'{"ifindex": '$IFINDEX',
	  "handle": {"scope": "node", "id": 1}}'
Netlink error: No such file or directory
nl_len = 44 (28) nl_flags = 0x300 nl_type = 2
	error: -2
	extack: {'bad-attr': '.handle'}

Such delete recurses on parents that are left over with no leaves:

./tools/net/ynl/cli.py --spec $SPEC --do get --json \
	'{"ifindex": '$IFINDEX',
	  "handle": {"scope": "node", "id": 0}}'
Netlink error: No such file or directory
nl_len = 44 (28) nl_flags = 0x300 nl_type = 2
	error: -2
	extack: {'bad-attr': '.handle'}

v8: https://lore.kernel.org/cover.1727704215.git.pabeni@redhat.com
v7: https://lore.kernel.org/cover.1725919039.git.pabeni@redhat.com
v6: https://lore.kernel.org/cover.1725457317.git.pabeni@redhat.com
v5: https://lore.kernel.org/cover.1724944116.git.pabeni@redhat.com
v4: https://lore.kernel.org/cover.1724165948.git.pabeni@redhat.com
v3: https://lore.kernel.org/cover.1722357745.git.pabeni@redhat.com
RFC v2: https://lore.kernel.org/cover.1721851988.git.pabeni@redhat.com
RFC v1: https://lore.kernel.org/cover.1719518113.git.pabeni@redhat.com
====================

Link: https://patch.msgid.link/cover.1728460186.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

15 files changed, 726 insertions, 3 deletions

diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index 0375c7448a57..20bc40eec487 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/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"
diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index 95b1d8f62304..532a0a595fe8 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/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>
@@ -250,6 +251,9 @@ struct iavf_cloud_filter {
 #define IAVF_RESET_WAIT_DETECTED_COUNT 500
 #define IAVF_RESET_WAIT_COMPLETE_COUNT 2000
 
+#define IAVF_MAX_QOS_TC_NUM		8
+#define IAVF_DEFAULT_QUANTA_SIZE	1024
+
 /* board specific private data structure */
 struct iavf_adapter {
 	struct workqueue_struct *wq;
@@ -336,6 +340,9 @@ 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)
+#define IAVF_FLAG_AQ_CFG_QUEUES_QUANTA_SIZE		BIT_ULL(40)
+#define IAVF_FLAG_AQ_GET_QOS_CAPS			BIT_ULL(41)
 
 	/* flags for processing extended capability messages during
 	 * __IAVF_INIT_EXTENDED_CAPS. Each capability exchange requires
@@ -408,6 +415,8 @@ struct iavf_adapter {
 			       VIRTCHNL_VF_OFFLOAD_FDIR_PF)
 #define ADV_RSS_SUPPORT(_a) ((_a)->vf_res->vf_cap_flags & \
 			     VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF)
+#define QOS_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \
+			 VIRTCHNL_VF_OFFLOAD_QOS)
 	struct virtchnl_vf_resource *vf_res; /* incl. all VSIs */
 	struct virtchnl_vsi_resource *vsi_res; /* our LAN VSI */
 	struct virtchnl_version_info pf_version;
@@ -416,6 +425,7 @@ struct iavf_adapter {
 	struct virtchnl_vlan_caps vlan_v2_caps;
 	u16 msg_enable;
 	struct iavf_eth_stats current_stats;
+	struct virtchnl_qos_cap_list *qos_caps;
 	struct iavf_vsi vsi;
 	u32 aq_wait_count;
 	/* RSS stuff */
@@ -571,6 +581,9 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 			      enum virtchnl_ops v_opcode,
 			      enum iavf_status v_retval, u8 *msg, u16 msglen);
 int iavf_config_rss(struct iavf_adapter *adapter);
+void iavf_cfg_queues_bw(struct iavf_adapter *adapter);
+void iavf_cfg_queues_quanta_size(struct iavf_adapter *adapter);
+void iavf_get_qos_caps(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);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index f782402cd789..12ef160425aa 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/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 +2089,21 @@ 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_GET_QOS_CAPS) {
+		iavf_get_qos_caps(adapter);
+		return 0;
+	}
+
+	if (adapter->aq_required & IAVF_FLAG_AQ_CFG_QUEUES_QUANTA_SIZE) {
+		iavf_cfg_queues_quanta_size(adapter);
+		return 0;
+	}
+
 	if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_QUEUES) {
 		iavf_configure_queues(adapter);
 		return 0;
@@ -2670,6 +2689,9 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter)
 		/* request initial VLAN offload settings */
 		iavf_set_vlan_offload_features(adapter, 0, netdev->features);
 
+	if (QOS_ALLOWED(adapter))
+		adapter->aq_required |= IAVF_FLAG_AQ_GET_QOS_CAPS;
+
 	iavf_schedule_finish_config(adapter);
 	return;
 
@@ -2919,6 +2941,30 @@ static void iavf_disable_vf(struct iavf_adapter *adapter)
 }
 
 /**
+ * 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 +2990,12 @@ 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 +3043,7 @@ 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 +3173,8 @@ continue_reset:
 		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 +3184,7 @@ continue_reset:
 
 	wake_up(&adapter->reset_waitqueue);
 	mutex_unlock(&adapter->crit_lock);
+	mutex_unlock(&netdev->lock);
 
 	return;
 reset_err:
@@ -3143,6 +3195,7 @@ reset_err:
 	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 +3667,10 @@ exit:
 	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 +4948,98 @@ static netdev_features_t iavf_fix_features(struct net_device *netdev,
 	return iavf_fix_strip_features(adapter, features);
 }
 
+static int
+iavf_verify_shaper(struct net_shaper_binding *binding,
+		   const struct net_shaper *shaper,
+		   struct netlink_ext_ack *extack)
+{
+	struct iavf_adapter *adapter = netdev_priv(binding->netdev);
+	u64 vf_max;
+
+	if (shaper->handle.scope == NET_SHAPER_SCOPE_QUEUE) {
+		vf_max = adapter->qos_caps->cap[0].shaper.peak;
+		if (vf_max && shaper->bw_max > vf_max) {
+			NL_SET_ERR_MSG_FMT(extack, "Max rate (%llu) of queue %d can't exceed max TX rate of VF (%llu kbps)",
+					   shaper->bw_max, shaper->handle.id,
+					   vf_max);
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+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;
+	int ret = 0;
+
+	mutex_lock(&adapter->crit_lock);
+	if (handle->id >= adapter->num_active_queues)
+		goto unlock;
+
+	ret = iavf_verify_shaper(binding, shaper, extack);
+	if (ret)
+		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 ret;
+}
+
+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 +5055,7 @@ 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,
 };
 
 /**
@@ -5054,7 +5202,7 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct net_device *netdev;
 	struct iavf_adapter *adapter = NULL;
 	struct iavf_hw *hw = NULL;
-	int err;
+	int err, len;
 
 	err = pci_enable_device(pdev);
 	if (err)
@@ -5122,6 +5270,13 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	hw->bus.func = PCI_FUNC(pdev->devfn);
 	hw->bus.bus_id = pdev->bus->number;
 
+	len = struct_size(adapter->qos_caps, cap, IAVF_MAX_QOS_TC_NUM);
+	adapter->qos_caps = kzalloc(len, GFP_KERNEL);
+	if (!adapter->qos_caps) {
+		err = -ENOMEM;
+		goto err_alloc_qos_cap;
+	}
+
 	/* set up the locks for the AQ, do this only once in probe
 	 * and destroy them only once in remove
 	 */
@@ -5160,6 +5315,8 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Initialization goes on in the work. Do not add more of it below. */
 	return 0;
 
+err_alloc_qos_cap:
+	iounmap(hw->hw_addr);
 err_ioremap:
 	destroy_workqueue(adapter->wq);
 err_alloc_wq:
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
index d7b5587aeb8e..f97c702c0802 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h
+++ b/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
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 7e810b65380c..15d388b431c5 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -151,7 +151,8 @@ int iavf_send_vf_config_msg(struct iavf_adapter *adapter)
 	       VIRTCHNL_VF_OFFLOAD_USO |
 	       VIRTCHNL_VF_OFFLOAD_FDIR_PF |
 	       VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF |
-	       VIRTCHNL_VF_CAP_ADV_LINK_SPEED;
+	       VIRTCHNL_VF_CAP_ADV_LINK_SPEED |
+	       VIRTCHNL_VF_OFFLOAD_QOS;
 
 	adapter->current_op = VIRTCHNL_OP_GET_VF_RESOURCES;
 	adapter->aq_required &= ~IAVF_FLAG_AQ_GET_CONFIG;
@@ -1508,6 +1509,130 @@ iavf_set_adapter_link_speed_from_vpe(struct iavf_adapter *adapter,
 }
 
 /**
+ * iavf_get_qos_caps - get qos caps support
+ * @adapter: iavf adapter struct instance
+ *
+ * This function requests PF for Supported QoS Caps.
+ */
+void iavf_get_qos_caps(struct iavf_adapter *adapter)
+{
+	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
+		/* bail because we already have a command pending */
+		dev_err(&adapter->pdev->dev,
+			"Cannot get qos caps, command %d pending\n",
+			adapter->current_op);
+		return;
+	}
+
+	adapter->current_op = VIRTCHNL_OP_GET_QOS_CAPS;
+	adapter->aq_required &= ~IAVF_FLAG_AQ_GET_QOS_CAPS;
+	iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_QOS_CAPS, NULL, 0);
+}
+
+/**
+ * iavf_set_quanta_size - set quanta size of queue chunk
+ * @adapter: iavf adapter struct instance
+ * @quanta_size: quanta size in bytes
+ * @queue_index: starting index of queue chunk
+ * @num_queues: number of queues in the queue chunk
+ *
+ * This function requests PF to set quanta size of queue chunk
+ * starting at queue_index.
+ */
+static void
+iavf_set_quanta_size(struct iavf_adapter *adapter, u16 quanta_size,
+		     u16 queue_index, u16 num_queues)
+{
+	struct virtchnl_quanta_cfg quanta_cfg;
+
+	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
+		/* bail because we already have a command pending */
+		dev_err(&adapter->pdev->dev,
+			"Cannot set queue quanta size, command %d pending\n",
+			adapter->current_op);
+		return;
+	}
+
+	adapter->current_op = VIRTCHNL_OP_CONFIG_QUANTA;
+	quanta_cfg.quanta_size = quanta_size;
+	quanta_cfg.queue_select.type = VIRTCHNL_QUEUE_TYPE_TX;
+	quanta_cfg.queue_select.start_queue_id = queue_index;
+	quanta_cfg.queue_select.num_queues = num_queues;
+	adapter->aq_required &= ~IAVF_FLAG_AQ_CFG_QUEUES_QUANTA_SIZE;
+	iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_QUANTA,
+			 (u8 *)&quanta_cfg, sizeof(quanta_cfg));
+}
+
+/**
+ * iavf_cfg_queues_quanta_size - configure quanta size of queues
+ * @adapter: adapter structure
+ *
+ * Request that the PF configure quanta size of allocated queues.
+ **/
+void iavf_cfg_queues_quanta_size(struct iavf_adapter *adapter)
+{
+	int quanta_size = IAVF_DEFAULT_QUANTA_SIZE;
+
+	/* Set Queue Quanta Size to default */
+	iavf_set_quanta_size(adapter, quanta_size, 0,
+			     adapter->num_active_queues);
+}
+
+/**
+ * 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 +2352,18 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 					VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC;
 
 			break;
+		case VIRTCHNL_OP_GET_QOS_CAPS:
+			dev_warn(&adapter->pdev->dev, "Failed to Get Qos CAPs, error %s\n",
+				 iavf_stat_str(&adapter->hw, v_retval));
+			break;
+		case VIRTCHNL_OP_CONFIG_QUANTA:
+			dev_warn(&adapter->pdev->dev, "Failed to Config Quanta, error %s\n",
+				 iavf_stat_str(&adapter->hw, v_retval));
+			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 +2706,24 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 		if (!v_retval)
 			iavf_netdev_features_vlan_strip_set(netdev, false);
 		break;
+	case VIRTCHNL_OP_GET_QOS_CAPS: {
+		u16 len = struct_size(adapter->qos_caps, cap,
+				      IAVF_MAX_QOS_TC_NUM);
+
+		memcpy(adapter->qos_caps, msg, min(msglen, len));
+
+		adapter->aq_required |= IAVF_FLAG_AQ_CFG_QUEUES_QUANTA_SIZE;
+		}
+		break;
+	case VIRTCHNL_OP_CONFIG_QUANTA:
+		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",
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 0e699a0432c5..680a81961ba1 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -667,6 +667,8 @@ struct ice_pf {
 	struct ice_agg_node vf_agg_node[ICE_MAX_VF_AGG_NODES];
 	struct ice_dplls dplls;
 	struct device *hwmon_dev;
+
+	u8 num_quanta_prof_used;
 };
 
 extern struct workqueue_struct *ice_lag_wq;
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 98c3764fed39..3a8e156d7d86 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -347,6 +347,8 @@ ice_setup_tx_ctx(struct ice_tx_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf
 		break;
 	}
 
+	tlan_ctx->quanta_prof_idx = ring->quanta_prof_id;
+
 	tlan_ctx->tso_ena = ICE_TX_LEGACY;
 	tlan_ctx->tso_qnum = pf_q;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 009716a12a26..b22e71dc59d4 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -2437,6 +2437,25 @@ ice_parse_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
 }
 
 /**
+ * ice_func_id_to_logical_id - map from function id to logical pf id
+ * @active_function_bitmap: active function bitmap
+ * @pf_id: function number of device
+ *
+ * Return: logical PF ID.
+ */
+static int ice_func_id_to_logical_id(u32 active_function_bitmap, u8 pf_id)
+{
+	u8 logical_id = 0;
+	u8 i;
+
+	for (i = 0; i < pf_id; i++)
+		if (active_function_bitmap & BIT(i))
+			logical_id++;
+
+	return logical_id;
+}
+
+/**
  * ice_parse_valid_functions_cap - Parse ICE_AQC_CAPS_VALID_FUNCTIONS caps
  * @hw: pointer to the HW struct
  * @dev_p: pointer to device capabilities structure
@@ -2453,6 +2472,8 @@ ice_parse_valid_functions_cap(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
 	dev_p->num_funcs = hweight32(number);
 	ice_debug(hw, ICE_DBG_INIT, "dev caps: num_funcs = %d\n",
 		  dev_p->num_funcs);
+
+	hw->logical_pf_id = ice_func_id_to_logical_id(number, hw->pf_id);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index 8d31bfe28cc8..dc88aea9f473 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -6,6 +6,14 @@
 #ifndef _ICE_HW_AUTOGEN_H_
 #define _ICE_HW_AUTOGEN_H_
 
+#define GLCOMM_QUANTA_PROF(_i)			(0x002D2D68 + ((_i) * 4))
+#define GLCOMM_QUANTA_PROF_MAX_INDEX		15
+#define GLCOMM_QUANTA_PROF_QUANTA_SIZE_S	0
+#define GLCOMM_QUANTA_PROF_QUANTA_SIZE_M	ICE_M(0x3FFF, 0)
+#define GLCOMM_QUANTA_PROF_MAX_CMD_S		16
+#define GLCOMM_QUANTA_PROF_MAX_CMD_M		ICE_M(0xFF, 16)
+#define GLCOMM_QUANTA_PROF_MAX_DESC_S		24
+#define GLCOMM_QUANTA_PROF_MAX_DESC_M		ICE_M(0x3F, 24)
 #define QTX_COMM_DBELL(_DBQM)			(0x002C0000 + ((_DBQM) * 4))
 #define QTX_COMM_HEAD(_DBQM)			(0x000E0000 + ((_DBQM) * 4))
 #define QTX_COMM_HEAD_HEAD_S			0
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index 67153f5b6891..cb347c852ba9 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -407,6 +407,7 @@ struct ice_tx_ring {
 #define ICE_TX_FLAGS_RING_VLAN_L2TAG2	BIT(2)
 	u8 flags;
 	u8 dcb_tc;			/* Traffic class of ring */
+	u16 quanta_prof_id;
 } ____cacheline_internodealigned_in_smp;
 
 static inline bool ice_ring_uses_build_skb(struct ice_rx_ring *ring)
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 45768796691f..adb168860711 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -905,6 +905,7 @@ struct ice_hw {
 	u8 revision_id;
 
 	u8 pf_id;		/* device profile info */
+	u8 logical_pf_id;
 
 	u16 max_burst_size;	/* driver sets this value */
 
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h
index be4266899690..4261fe1c2bcd 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h
@@ -59,6 +59,13 @@ struct ice_fdir_prof_info {
 	u64 fdir_active_cnt;
 };
 
+struct ice_vf_qs_bw {
+	u32 committed;
+	u32 peak;
+	u16 queue_id;
+	u8 tc;
+};
+
 /* VF operations */
 struct ice_vf_ops {
 	enum ice_disq_rst_src reset_type;
@@ -140,6 +147,7 @@ struct ice_vf {
 	struct devlink_port devlink_port;
 
 	u16 num_msix;			/* num of MSI-X configured on this VF */
+	struct ice_vf_qs_bw qs_bw[ICE_MAX_RSS_QS_PER_VF];
 };
 
 /* Flags for controlling behavior of ice_reset_vf */
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index a230859584c2..aa2080747714 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -495,6 +495,9 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg)
 	if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_USO)
 		vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_USO;
 
+	if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_QOS)
+		vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_QOS;
+
 	vfres->num_vsis = 1;
 	/* Tx and Rx queue are equal for VF */
 	vfres->num_queue_pairs = vsi->num_txq;
@@ -1035,6 +1038,191 @@ error_param:
 }
 
 /**
+ * ice_vc_get_qos_caps - Get current QoS caps from PF
+ * @vf: pointer to the VF info
+ *
+ * Get VF's QoS capabilities, such as TC number, arbiter and
+ * bandwidth from PF.
+ *
+ * Return: 0 on success or negative error value.
+ */
+static int ice_vc_get_qos_caps(struct ice_vf *vf)
+{
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+	struct virtchnl_qos_cap_list *cap_list = NULL;
+	u8 tc_prio[ICE_MAX_TRAFFIC_CLASS] = { 0 };
+	struct virtchnl_qos_cap_elem *cfg = NULL;
+	struct ice_vsi_ctx *vsi_ctx;
+	struct ice_pf *pf = vf->pf;
+	struct ice_port_info *pi;
+	struct ice_vsi *vsi;
+	u8 numtc, tc;
+	u16 len = 0;
+	int ret, i;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	pi = pf->hw.port_info;
+	numtc = vsi->tc_cfg.numtc;
+
+	vsi_ctx = ice_get_vsi_ctx(pi->hw, vf->lan_vsi_idx);
+	if (!vsi_ctx) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	len = struct_size(cap_list, cap, numtc);
+	cap_list = kzalloc(len, GFP_KERNEL);
+	if (!cap_list) {
+		v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY;
+		len = 0;
+		goto err;
+	}
+
+	cap_list->vsi_id = vsi->vsi_num;
+	cap_list->num_elem = numtc;
+
+	/* Store the UP2TC configuration from DCB to a user priority bitmap
+	 * of each TC. Each element of prio_of_tc represents one TC. Each
+	 * bitmap indicates the user priorities belong to this TC.
+	 */
+	for (i = 0; i < ICE_MAX_USER_PRIORITY; i++) {
+		tc = pi->qos_cfg.local_dcbx_cfg.etscfg.prio_table[i];
+		tc_prio[tc] |= BIT(i);
+	}
+
+	for (i = 0; i < numtc; i++) {
+		cfg = &cap_list->cap[i];
+		cfg->tc_num = i;
+		cfg->tc_prio = tc_prio[i];
+		cfg->arbiter = pi->qos_cfg.local_dcbx_cfg.etscfg.tsatable[i];
+		cfg->weight = VIRTCHNL_STRICT_WEIGHT;
+		cfg->type = VIRTCHNL_BW_SHAPER;
+		cfg->shaper.committed = vsi_ctx->sched.bw_t_info[i].cir_bw.bw;
+		cfg->shaper.peak = vsi_ctx->sched.bw_t_info[i].eir_bw.bw;
+	}
+
+err:
+	ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_QOS_CAPS, v_ret,
+				    (u8 *)cap_list, len);
+	kfree(cap_list);
+	return ret;
+}
+
+/**
+ * ice_vf_cfg_qs_bw - Configure per queue bandwidth
+ * @vf: pointer to the VF info
+ * @num_queues: number of queues to be configured
+ *
+ * Configure per queue bandwidth.
+ *
+ * Return: 0 on success or negative error value.
+ */
+static int ice_vf_cfg_qs_bw(struct ice_vf *vf, u16 num_queues)
+{
+	struct ice_hw *hw = &vf->pf->hw;
+	struct ice_vsi *vsi;
+	int ret;
+	u16 i;
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi)
+		return -EINVAL;
+
+	for (i = 0; i < num_queues; i++) {
+		u32 p_rate, min_rate;
+		u8 tc;
+
+		p_rate = vf->qs_bw[i].peak;
+		min_rate = vf->qs_bw[i].committed;
+		tc = vf->qs_bw[i].tc;
+		if (p_rate)
+			ret = ice_cfg_q_bw_lmt(hw->port_info, vsi->idx, tc,
+					       vf->qs_bw[i].queue_id,
+					       ICE_MAX_BW, p_rate);
+		else
+			ret = ice_cfg_q_bw_dflt_lmt(hw->port_info, vsi->idx, tc,
+						    vf->qs_bw[i].queue_id,
+						    ICE_MAX_BW);
+		if (ret)
+			return ret;
+
+		if (min_rate)
+			ret = ice_cfg_q_bw_lmt(hw->port_info, vsi->idx, tc,
+					       vf->qs_bw[i].queue_id,
+					       ICE_MIN_BW, min_rate);
+		else
+			ret = ice_cfg_q_bw_dflt_lmt(hw->port_info, vsi->idx, tc,
+						    vf->qs_bw[i].queue_id,
+						    ICE_MIN_BW);
+
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_vf_cfg_q_quanta_profile - Configure quanta profile
+ * @vf: pointer to the VF info
+ * @quanta_prof_idx: pointer to the quanta profile index
+ * @quanta_size: quanta size to be set
+ *
+ * This function chooses available quanta profile and configures the register.
+ * The quanta profile is evenly divided by the number of device ports, and then
+ * available to the specific PF and VFs. The first profile for each PF is a
+ * reserved default profile. Only quanta size of the rest unused profile can be
+ * modified.
+ *
+ * Return: 0 on success or negative error value.
+ */
+static int ice_vf_cfg_q_quanta_profile(struct ice_vf *vf, u16 quanta_size,
+				       u16 *quanta_prof_idx)
+{
+	const u16 n_desc = calc_quanta_desc(quanta_size);
+	struct ice_hw *hw = &vf->pf->hw;
+	const u16 n_cmd = 2 * n_desc;
+	struct ice_pf *pf = vf->pf;
+	u16 per_pf, begin_id;
+	u8 n_used;
+	u32 reg;
+
+	begin_id = (GLCOMM_QUANTA_PROF_MAX_INDEX + 1) / hw->dev_caps.num_funcs *
+		   hw->logical_pf_id;
+
+	if (quanta_size == ICE_DFLT_QUANTA) {
+		*quanta_prof_idx = begin_id;
+	} else {
+		per_pf = (GLCOMM_QUANTA_PROF_MAX_INDEX + 1) /
+			 hw->dev_caps.num_funcs;
+		n_used = pf->num_quanta_prof_used;
+		if (n_used < per_pf) {
+			*quanta_prof_idx = begin_id + 1 + n_used;
+			pf->num_quanta_prof_used++;
+		} else {
+			return -EINVAL;
+		}
+	}
+
+	reg = FIELD_PREP(GLCOMM_QUANTA_PROF_QUANTA_SIZE_M, quanta_size) |
+	      FIELD_PREP(GLCOMM_QUANTA_PROF_MAX_CMD_M, n_cmd) |
+	      FIELD_PREP(GLCOMM_QUANTA_PROF_MAX_DESC_M, n_desc);
+	wr32(hw, GLCOMM_QUANTA_PROF(*quanta_prof_idx), reg);
+
+	return 0;
+}
+
+/**
  * ice_vc_cfg_promiscuous_mode_msg
  * @vf: pointer to the VF info
  * @msg: pointer to the msg buffer
@@ -1636,6 +1824,141 @@ error_param:
 }
 
 /**
+ * ice_vc_cfg_q_bw - Configure per queue bandwidth
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer which holds the command descriptor
+ *
+ * Configure VF queues bandwidth.
+ *
+ * Return: 0 on success or negative error value.
+ */
+static int ice_vc_cfg_q_bw(struct ice_vf *vf, u8 *msg)
+{
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+	struct virtchnl_queues_bw_cfg *qbw =
+		(struct virtchnl_queues_bw_cfg *)msg;
+	struct ice_vsi *vsi;
+	u16 i;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) ||
+	    !ice_vc_isvalid_vsi_id(vf, qbw->vsi_id)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	if (qbw->num_queues > ICE_MAX_RSS_QS_PER_VF ||
+	    qbw->num_queues > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) {
+		dev_err(ice_pf_to_dev(vf->pf), "VF-%d trying to configure more than allocated number of queues: %d\n",
+			vf->vf_id, min_t(u16, vsi->alloc_txq, vsi->alloc_rxq));
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	for (i = 0; i < qbw->num_queues; i++) {
+		if (qbw->cfg[i].shaper.peak != 0 && vf->max_tx_rate != 0 &&
+		    qbw->cfg[i].shaper.peak > vf->max_tx_rate)
+			dev_warn(ice_pf_to_dev(vf->pf), "The maximum queue %d rate limit configuration may not take effect because the maximum TX rate for VF-%d is %d\n",
+				 qbw->cfg[i].queue_id, vf->vf_id,
+				 vf->max_tx_rate);
+		if (qbw->cfg[i].shaper.committed != 0 && vf->min_tx_rate != 0 &&
+		    qbw->cfg[i].shaper.committed < vf->min_tx_rate)
+			dev_warn(ice_pf_to_dev(vf->pf), "The minimum queue %d rate limit configuration may not take effect because the minimum TX rate for VF-%d is %d\n",
+				 qbw->cfg[i].queue_id, vf->vf_id,
+				 vf->max_tx_rate);
+	}
+
+	for (i = 0; i < qbw->num_queues; i++) {
+		vf->qs_bw[i].queue_id = qbw->cfg[i].queue_id;
+		vf->qs_bw[i].peak = qbw->cfg[i].shaper.peak;
+		vf->qs_bw[i].committed = qbw->cfg[i].shaper.committed;
+		vf->qs_bw[i].tc = qbw->cfg[i].tc;
+	}
+
+	if (ice_vf_cfg_qs_bw(vf, qbw->num_queues))
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+
+err:
+	/* send the response to the VF */
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_QUEUE_BW,
+				    v_ret, NULL, 0);
+}
+
+/**
+ * ice_vc_cfg_q_quanta - Configure per queue quanta
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer which holds the command descriptor
+ *
+ * Configure VF queues quanta.
+ *
+ * Return: 0 on success or negative error value.
+ */
+static int ice_vc_cfg_q_quanta(struct ice_vf *vf, u8 *msg)
+{
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+	u16 quanta_prof_id, quanta_size, start_qid, end_qid, i;
+	struct virtchnl_quanta_cfg *qquanta =
+		(struct virtchnl_quanta_cfg *)msg;
+	struct ice_vsi *vsi;
+	int ret;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	end_qid = qquanta->queue_select.start_queue_id +
+		  qquanta->queue_select.num_queues;
+	if (end_qid > ICE_MAX_RSS_QS_PER_VF ||
+	    end_qid > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) {
+		dev_err(ice_pf_to_dev(vf->pf), "VF-%d trying to configure more than allocated number of queues: %d\n",
+			vf->vf_id, min_t(u16, vsi->alloc_txq, vsi->alloc_rxq));
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	quanta_size = qquanta->quanta_size;
+	if (quanta_size > ICE_MAX_QUANTA_SIZE ||
+	    quanta_size < ICE_MIN_QUANTA_SIZE) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	if (quanta_size % 64) {
+		dev_err(ice_pf_to_dev(vf->pf), "quanta size should be the product of 64\n");
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
+	ret = ice_vf_cfg_q_quanta_profile(vf, quanta_size,
+					  &quanta_prof_id);
+	if (ret) {
+		v_ret = VIRTCHNL_STATUS_ERR_NOT_SUPPORTED;
+		goto err;
+	}
+
+	start_qid = qquanta->queue_select.start_queue_id;
+	for (i = start_qid; i < end_qid; i++)
+		vsi->tx_rings[i]->quanta_prof_id = quanta_prof_id;
+
+err:
+	/* send the response to the VF */
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_QUANTA,
+				     v_ret, NULL, 0);
+}
+
+/**
  * ice_vc_cfg_qs_msg
  * @vf: pointer to the VF info
  * @msg: pointer to the msg buffer
@@ -3819,6 +4142,9 @@ static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = {
 	.dis_vlan_stripping_v2_msg = ice_vc_dis_vlan_stripping_v2_msg,
 	.ena_vlan_insertion_v2_msg = ice_vc_ena_vlan_insertion_v2_msg,
 	.dis_vlan_insertion_v2_msg = ice_vc_dis_vlan_insertion_v2_msg,
+	.get_qos_caps = ice_vc_get_qos_caps,
+	.cfg_q_bw = ice_vc_cfg_q_bw,
+	.cfg_q_quanta = ice_vc_cfg_q_quanta,
 };
 
 /**
@@ -4177,6 +4503,15 @@ error_handler:
 	case VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2:
 		err = ops->dis_vlan_insertion_v2_msg(vf, msg);
 		break;
+	case VIRTCHNL_OP_GET_QOS_CAPS:
+		err = ops->get_qos_caps(vf);
+		break;
+	case VIRTCHNL_OP_CONFIG_QUEUE_BW:
+		err = ops->cfg_q_bw(vf, msg);
+		break;
+	case VIRTCHNL_OP_CONFIG_QUANTA:
+		err = ops->cfg_q_quanta(vf, msg);
+		break;
 	case VIRTCHNL_OP_UNKNOWN:
 	default:
 		dev_err(dev, "Unsupported opcode %d from VF %d\n", v_opcode,
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.h b/drivers/net/ethernet/intel/ice/ice_virtchnl.h
index 3a4115869153..0c629aef9baf 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.h
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.h
@@ -13,6 +13,13 @@
 /* Restrict number of MAC Addr and VLAN that non-trusted VF can programmed */
 #define ICE_MAX_VLAN_PER_VF		8
 
+#define ICE_DFLT_QUANTA 1024
+#define ICE_MAX_QUANTA_SIZE 4096
+#define ICE_MIN_QUANTA_SIZE 256
+
+#define calc_quanta_desc(x)	\
+	max_t(u16, 12, min_t(u16, 63, (((x) + 66) / 132) * 2 + 4))
+
 /* MAC filters: 1 is reserved for the VF's default/perm_addr/LAA MAC, 1 for
  * broadcast, and 16 for additional unicast/multicast filters
  */
@@ -61,6 +68,10 @@ struct ice_virtchnl_ops {
 	int (*dis_vlan_stripping_v2_msg)(struct ice_vf *vf, u8 *msg);
 	int (*ena_vlan_insertion_v2_msg)(struct ice_vf *vf, u8 *msg);
 	int (*dis_vlan_insertion_v2_msg)(struct ice_vf *vf, u8 *msg);
+	int (*get_qos_caps)(struct ice_vf *vf);
+	int (*cfg_q_tc_map)(struct ice_vf *vf, u8 *msg);
+	int (*cfg_q_bw)(struct ice_vf *vf, u8 *msg);
+	int (*cfg_q_quanta)(struct ice_vf *vf, u8 *msg);
 };
 
 #ifdef CONFIG_PCI_IOV
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
index d796dbd2a440..c105a82ee136 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
@@ -84,6 +84,11 @@ static const u32 fdir_pf_allowlist_opcodes[] = {
 	VIRTCHNL_OP_ADD_FDIR_FILTER, VIRTCHNL_OP_DEL_FDIR_FILTER,
 };
 
+static const u32 tc_allowlist_opcodes[] = {
+	VIRTCHNL_OP_GET_QOS_CAPS, VIRTCHNL_OP_CONFIG_QUEUE_BW,
+	VIRTCHNL_OP_CONFIG_QUANTA,
+};
+
 struct allowlist_opcode_info {
 	const u32 *opcodes;
 	size_t size;
@@ -104,6 +109,7 @@ static const struct allowlist_opcode_info allowlist_opcodes[] = {
 	ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF, adv_rss_pf_allowlist_opcodes),
 	ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_FDIR_PF, fdir_pf_allowlist_opcodes),
 	ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_VLAN_V2, vlan_v2_allowlist_opcodes),
+	ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_QOS, tc_allowlist_opcodes),
 };
 
 /**