diff --git a/drivers/infiniband/hw/mana/counters.c b/drivers/infiniband/hw/mana/counters.c
index e533ce21013db..e964e74be48da 100644
--- a/drivers/infiniband/hw/mana/counters.c
+++ b/drivers/infiniband/hw/mana/counters.c
@@ -32,8 +32,32 @@ static const struct rdma_stat_desc mana_ib_port_stats_desc[] = {
 	[MANA_IB_RATE_INC_EVENTS].name = "rate_inc_events",
 	[MANA_IB_NUM_QPS_RECOVERED].name = "num_qps_recovered",
 	[MANA_IB_CURRENT_RATE].name = "current_rate",
+	[MANA_IB_DUP_RX_REQ].name = "dup_rx_requests",
+	[MANA_IB_TX_BYTES].name = "tx_bytes",
+	[MANA_IB_RX_BYTES].name = "rx_bytes",
+	[MANA_IB_RX_SEND_REQ].name = "rx_send_requests",
+	[MANA_IB_RX_WRITE_REQ].name = "rx_write_requests",
+	[MANA_IB_RX_READ_REQ].name = "rx_read_requests",
+	[MANA_IB_TX_PKT].name = "tx_packets",
+	[MANA_IB_RX_PKT].name = "rx_packets",
 };
 
+static const struct rdma_stat_desc mana_ib_device_stats_desc[] = {
+	[MANA_IB_SENT_CNPS].name = "sent_cnps",
+	[MANA_IB_RECEIVED_ECNS].name = "received_ecns",
+	[MANA_IB_RECEIVED_CNP_COUNT].name = "received_cnp_count",
+	[MANA_IB_QP_CONGESTED_EVENTS].name = "qp_congested_events",
+	[MANA_IB_QP_RECOVERED_EVENTS].name = "qp_recovered_events",
+	[MANA_IB_DEV_RATE_INC_EVENTS].name = "rate_inc_events",
+};
+
+struct rdma_hw_stats *mana_ib_alloc_hw_device_stats(struct ib_device *ibdev)
+{
+	return rdma_alloc_hw_stats_struct(mana_ib_device_stats_desc,
+					  ARRAY_SIZE(mana_ib_device_stats_desc),
+					  RDMA_HW_STATS_DEFAULT_LIFESPAN);
+}
+
 struct rdma_hw_stats *mana_ib_alloc_hw_port_stats(struct ib_device *ibdev,
 						  u32 port_num)
 {
@@ -42,8 +66,39 @@ struct rdma_hw_stats *mana_ib_alloc_hw_port_stats(struct ib_device *ibdev,
 					  RDMA_HW_STATS_DEFAULT_LIFESPAN);
 }
 
-int mana_ib_get_hw_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats,
-			 u32 port_num, int index)
+static int mana_ib_get_hw_device_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats)
+{
+	struct mana_ib_dev *mdev = container_of(ibdev, struct mana_ib_dev,
+						ib_dev);
+	struct mana_rnic_query_device_cntrs_resp resp = {};
+	struct mana_rnic_query_device_cntrs_req req = {};
+	int err;
+
+	mana_gd_init_req_hdr(&req.hdr, MANA_IB_QUERY_DEVICE_COUNTERS,
+			     sizeof(req), sizeof(resp));
+	req.hdr.dev_id = mdev->gdma_dev->dev_id;
+	req.adapter = mdev->adapter_handle;
+
+	err = mana_gd_send_request(mdev_to_gc(mdev), sizeof(req), &req,
+				   sizeof(resp), &resp);
+	if (err) {
+		ibdev_err(&mdev->ib_dev, "Failed to query device counters err %d",
+			  err);
+		return err;
+	}
+
+	stats->value[MANA_IB_SENT_CNPS] = resp.sent_cnps;
+	stats->value[MANA_IB_RECEIVED_ECNS] = resp.received_ecns;
+	stats->value[MANA_IB_RECEIVED_CNP_COUNT] = resp.received_cnp_count;
+	stats->value[MANA_IB_QP_CONGESTED_EVENTS] = resp.qp_congested_events;
+	stats->value[MANA_IB_QP_RECOVERED_EVENTS] = resp.qp_recovered_events;
+	stats->value[MANA_IB_DEV_RATE_INC_EVENTS] = resp.rate_inc_events;
+
+	return ARRAY_SIZE(mana_ib_device_stats_desc);
+}
+
+static int mana_ib_get_hw_port_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats,
+				     u32 port_num)
 {
 	struct mana_ib_dev *mdev = container_of(ibdev, struct mana_ib_dev,
 						ib_dev);
@@ -53,6 +108,7 @@ int mana_ib_get_hw_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats,
 
 	mana_gd_init_req_hdr(&req.hdr, MANA_IB_QUERY_VF_COUNTERS,
 			     sizeof(req), sizeof(resp));
+	req.hdr.resp.msg_version = GDMA_MESSAGE_V2;
 	req.hdr.dev_id = mdev->gdma_dev->dev_id;
 	req.adapter = mdev->adapter_handle;
 
@@ -101,5 +157,23 @@ int mana_ib_get_hw_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats,
 	stats->value[MANA_IB_NUM_QPS_RECOVERED] = resp.num_qps_recovered;
 	stats->value[MANA_IB_CURRENT_RATE] = resp.current_rate;
 
+	stats->value[MANA_IB_DUP_RX_REQ] = resp.dup_rx_req;
+	stats->value[MANA_IB_TX_BYTES] = resp.tx_bytes;
+	stats->value[MANA_IB_RX_BYTES] = resp.rx_bytes;
+	stats->value[MANA_IB_RX_SEND_REQ] = resp.rx_send_req;
+	stats->value[MANA_IB_RX_WRITE_REQ] = resp.rx_write_req;
+	stats->value[MANA_IB_RX_READ_REQ] = resp.rx_read_req;
+	stats->value[MANA_IB_TX_PKT] = resp.tx_pkt;
+	stats->value[MANA_IB_RX_PKT] = resp.rx_pkt;
+
 	return ARRAY_SIZE(mana_ib_port_stats_desc);
 }
+
+int mana_ib_get_hw_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats,
+			 u32 port_num, int index)
+{
+	if (!port_num)
+		return mana_ib_get_hw_device_stats(ibdev, stats);
+	else
+		return mana_ib_get_hw_port_stats(ibdev, stats, port_num);
+}
diff --git a/drivers/infiniband/hw/mana/counters.h b/drivers/infiniband/hw/mana/counters.h
index 7ff92d27f6c3a..f68e776bb41d7 100644
--- a/drivers/infiniband/hw/mana/counters.h
+++ b/drivers/infiniband/hw/mana/counters.h
@@ -35,10 +35,28 @@ enum mana_ib_port_counters {
 	MANA_IB_RATE_INC_EVENTS,
 	MANA_IB_NUM_QPS_RECOVERED,
 	MANA_IB_CURRENT_RATE,
+	MANA_IB_DUP_RX_REQ,
+	MANA_IB_TX_BYTES,
+	MANA_IB_RX_BYTES,
+	MANA_IB_RX_SEND_REQ,
+	MANA_IB_RX_WRITE_REQ,
+	MANA_IB_RX_READ_REQ,
+	MANA_IB_TX_PKT,
+	MANA_IB_RX_PKT,
+};
+
+enum mana_ib_device_counters {
+	MANA_IB_SENT_CNPS,
+	MANA_IB_RECEIVED_ECNS,
+	MANA_IB_RECEIVED_CNP_COUNT,
+	MANA_IB_QP_CONGESTED_EVENTS,
+	MANA_IB_QP_RECOVERED_EVENTS,
+	MANA_IB_DEV_RATE_INC_EVENTS,
 };
 
 struct rdma_hw_stats *mana_ib_alloc_hw_port_stats(struct ib_device *ibdev,
 						  u32 port_num);
+struct rdma_hw_stats *mana_ib_alloc_hw_device_stats(struct ib_device *ibdev);
 int mana_ib_get_hw_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats,
 			 u32 port_num, int index);
 #endif /* _COUNTERS_H_ */
diff --git a/drivers/infiniband/hw/mana/cq.c b/drivers/infiniband/hw/mana/cq.c
index 28e154bbb50f8..1becc87791235 100644
--- a/drivers/infiniband/hw/mana/cq.c
+++ b/drivers/infiniband/hw/mana/cq.c
@@ -291,6 +291,32 @@ static int mana_process_completions(struct mana_ib_cq *cq, int nwc, struct ib_wc
 	return wc_index;
 }
 
+void mana_drain_gsi_sqs(struct mana_ib_dev *mdev)
+{
+	struct mana_ib_qp *qp = mana_get_qp_ref(mdev, MANA_GSI_QPN, false);
+	struct ud_sq_shadow_wqe *shadow_wqe;
+	struct mana_ib_cq *cq;
+	unsigned long flags;
+
+	if (!qp)
+		return;
+
+	cq = container_of(qp->ibqp.send_cq, struct mana_ib_cq, ibcq);
+
+	spin_lock_irqsave(&cq->cq_lock, flags);
+	while ((shadow_wqe = shadow_queue_get_next_to_complete(&qp->shadow_sq))
+			!= NULL) {
+		shadow_wqe->header.error_code = IB_WC_GENERAL_ERR;
+		shadow_queue_advance_next_to_complete(&qp->shadow_sq);
+	}
+	spin_unlock_irqrestore(&cq->cq_lock, flags);
+
+	if (cq->ibcq.comp_handler)
+		cq->ibcq.comp_handler(&cq->ibcq, cq->ibcq.cq_context);
+
+	mana_put_qp_ref(qp);
+}
+
 int mana_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
 {
 	struct mana_ib_cq *cq = container_of(ibcq, struct mana_ib_cq, ibcq);
diff --git a/drivers/infiniband/hw/mana/device.c b/drivers/infiniband/hw/mana/device.c
index 165c0a1e67d14..eceb6fca4c6aa 100644
--- a/drivers/infiniband/hw/mana/device.c
+++ b/drivers/infiniband/hw/mana/device.c
@@ -65,6 +65,10 @@ static const struct ib_device_ops mana_ib_stats_ops = {
 	.get_hw_stats = mana_ib_get_hw_stats,
 };
 
+static const struct ib_device_ops mana_ib_device_stats_ops = {
+	.alloc_hw_device_stats = mana_ib_alloc_hw_device_stats,
+};
+
 static int mana_ib_netdev_event(struct notifier_block *this,
 				unsigned long event, void *ptr)
 {
@@ -153,6 +157,8 @@ static int mana_ib_probe(struct auxiliary_device *adev,
 		}
 
 		ib_set_device_ops(&dev->ib_dev, &mana_ib_stats_ops);
+		if (dev->adapter_caps.feature_flags & MANA_IB_FEATURE_DEV_COUNTERS_SUPPORT)
+			ib_set_device_ops(&dev->ib_dev, &mana_ib_device_stats_ops);
 
 		ret = mana_ib_create_eqs(dev);
 		if (ret) {
@@ -218,6 +224,9 @@ static void mana_ib_remove(struct auxiliary_device *adev)
 {
 	struct mana_ib_dev *dev = dev_get_drvdata(&adev->dev);
 
+	if (mana_ib_is_rnic(dev))
+		mana_drain_gsi_sqs(dev);
+
 	ib_unregister_device(&dev->ib_dev);
 	dma_pool_destroy(dev->av_pool);
 	if (mana_ib_is_rnic(dev)) {
diff --git a/drivers/infiniband/hw/mana/mana_ib.h b/drivers/infiniband/hw/mana/mana_ib.h
index 42bebd6cd4f7a..38ea58fe411c7 100644
--- a/drivers/infiniband/hw/mana/mana_ib.h
+++ b/drivers/infiniband/hw/mana/mana_ib.h
@@ -43,6 +43,8 @@
  */
 #define MANA_AV_BUFFER_SIZE	64
 
+#define MANA_GSI_QPN		(1)
+
 struct mana_ib_adapter_caps {
 	u32 max_sq_id;
 	u32 max_rq_id;
@@ -210,6 +212,7 @@ enum mana_ib_command_code {
 	MANA_IB_DESTROY_RC_QP   = 0x3000b,
 	MANA_IB_SET_QP_STATE	= 0x3000d,
 	MANA_IB_QUERY_VF_COUNTERS = 0x30022,
+	MANA_IB_QUERY_DEVICE_COUNTERS = 0x30023,
 };
 
 struct mana_ib_query_adapter_caps_req {
@@ -218,6 +221,7 @@ struct mana_ib_query_adapter_caps_req {
 
 enum mana_ib_adapter_features {
 	MANA_IB_FEATURE_CLIENT_ERROR_CQE_SUPPORT = BIT(4),
+	MANA_IB_FEATURE_DEV_COUNTERS_SUPPORT = BIT(5),
 };
 
 struct mana_ib_query_adapter_caps_resp {
@@ -407,7 +411,7 @@ struct mana_ib_ah_attr {
 	u8 traffic_class;
 	u16 src_port;
 	u16 dest_port;
-	u32 reserved;
+	u32 flow_label;
 };
 
 struct mana_rnic_set_qp_state_req {
@@ -424,8 +428,15 @@ struct mana_rnic_set_qp_state_req {
 	u32 retry_cnt;
 	u32 rnr_retry;
 	u32 min_rnr_timer;
-	u32 reserved;
+	u32 rate_limit;
 	struct mana_ib_ah_attr ah_attr;
+	u64 reserved1;
+	u32 qkey;
+	u32 qp_access_flags;
+	u8 local_ack_timeout;
+	u8 max_rd_atomic;
+	u16 reserved2;
+	u32 reserved3;
 }; /* HW Data */
 
 struct mana_rnic_set_qp_state_resp {
@@ -514,6 +525,31 @@ struct mana_rnic_query_vf_cntrs_resp {
 	u64 rate_inc_events;
 	u64 num_qps_recovered;
 	u64 current_rate;
+	u64 dup_rx_req;
+	u64 tx_bytes;
+	u64 rx_bytes;
+	u64 rx_send_req;
+	u64 rx_write_req;
+	u64 rx_read_req;
+	u64 tx_pkt;
+	u64 rx_pkt;
+}; /* HW Data */
+
+struct mana_rnic_query_device_cntrs_req {
+	struct gdma_req_hdr hdr;
+	mana_handle_t adapter;
+}; /* HW Data */
+
+struct mana_rnic_query_device_cntrs_resp {
+	struct gdma_resp_hdr hdr;
+	u32 sent_cnps;
+	u32 received_ecns;
+	u32 reserved1;
+	u32 received_cnp_count;
+	u32 qp_congested_events;
+	u32 qp_recovered_events;
+	u32 rate_inc_events;
+	u32 reserved2;
 }; /* HW Data */
 
 static inline struct gdma_context *mdev_to_gc(struct mana_ib_dev *mdev)
@@ -689,6 +725,7 @@ int mana_ib_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr,
 int mana_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 		      const struct ib_send_wr **bad_wr);
 
+void mana_drain_gsi_sqs(struct mana_ib_dev *mdev);
 int mana_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc);
 int mana_ib_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags);
 
diff --git a/drivers/infiniband/hw/mana/qp.c b/drivers/infiniband/hw/mana/qp.c
index a6bf4d539e670..48c1f4977f218 100644
--- a/drivers/infiniband/hw/mana/qp.c
+++ b/drivers/infiniband/hw/mana/qp.c
@@ -735,6 +735,8 @@ static int mana_ib_gd_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	int err;
 
 	mana_gd_init_req_hdr(&req.hdr, MANA_IB_SET_QP_STATE, sizeof(req), sizeof(resp));
+
+	req.hdr.req.msg_version = GDMA_MESSAGE_V3;
 	req.hdr.dev_id = mdev->gdma_dev->dev_id;
 	req.adapter = mdev->adapter_handle;
 	req.qp_handle = qp->qp_handle;
@@ -748,6 +750,12 @@ static int mana_ib_gd_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	req.retry_cnt = attr->retry_cnt;
 	req.rnr_retry = attr->rnr_retry;
 	req.min_rnr_timer = attr->min_rnr_timer;
+	req.rate_limit = attr->rate_limit;
+	req.qkey = attr->qkey;
+	req.local_ack_timeout = attr->timeout;
+	req.qp_access_flags = attr->qp_access_flags;
+	req.max_rd_atomic = attr->max_rd_atomic;
+
 	if (attr_mask & IB_QP_AV) {
 		ndev = mana_ib_get_netdev(&mdev->ib_dev, ibqp->port);
 		if (!ndev) {
@@ -774,6 +782,7 @@ static int mana_ib_gd_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 							  ibqp->qp_num, attr->dest_qp_num);
 		req.ah_attr.traffic_class = attr->ah_attr.grh.traffic_class >> 2;
 		req.ah_attr.hop_limit = attr->ah_attr.grh.hop_limit;
+		req.ah_attr.flow_label = attr->ah_attr.grh.flow_label;
 	}
 
 	err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
diff --git a/drivers/net/ethernet/microsoft/Kconfig b/drivers/net/ethernet/microsoft/Kconfig
index 901fbffbf718e..3f36ee6a8ecee 100644
--- a/drivers/net/ethernet/microsoft/Kconfig
+++ b/drivers/net/ethernet/microsoft/Kconfig
@@ -22,6 +22,7 @@ config MICROSOFT_MANA
 	depends on PCI_HYPERV
 	select AUXILIARY_BUS
 	select PAGE_POOL
+	select NET_SHAPER
 	help
 	  This driver supports Microsoft Azure Network Adapter (MANA).
 	  So far, the driver is only supported on X86_64.
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 7cb9360c05156..a468cd8e5f361 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -6,6 +6,8 @@
 #include <linux/pci.h>
 #include <linux/utsname.h>
 #include <linux/version.h>
+#include <linux/msi.h>
+#include <linux/irqdomain.h>
 
 #include <net/mana/mana.h>
 #include <net/mana/hw_channel.h>
@@ -102,8 +104,15 @@ static int mana_gd_query_max_resources(struct pci_dev *pdev)
 		return err ? err : -EPROTO;
 	}
 
-	if (gc->num_msix_usable > resp.max_msix)
-		gc->num_msix_usable = resp.max_msix;
+	if (!pci_msix_can_alloc_dyn(pdev)) {
+		if (gc->num_msix_usable > resp.max_msix)
+			gc->num_msix_usable = resp.max_msix;
+	} else {
+		/* If dynamic allocation is enabled we have already allocated
+		 * hwc msi
+		 */
+		gc->num_msix_usable = min(resp.max_msix, num_online_cpus() + 1);
+	}
 
 	if (gc->num_msix_usable <= 1)
 		return -ENOSPC;
@@ -637,7 +646,9 @@ static int mana_gd_register_irq(struct gdma_queue *queue,
 	}
 
 	queue->eq.msix_index = msi_index;
-	gic = &gc->irq_contexts[msi_index];
+	gic = xa_load(&gc->irq_contexts, msi_index);
+	if (WARN_ON(!gic))
+		return -EINVAL;
 
 	spin_lock_irqsave(&gic->lock, flags);
 	list_add_rcu(&queue->entry, &gic->eq_list);
@@ -662,7 +673,10 @@ static void mana_gd_deregiser_irq(struct gdma_queue *queue)
 	if (WARN_ON(msix_index >= gc->num_msix_usable))
 		return;
 
-	gic = &gc->irq_contexts[msix_index];
+	gic = xa_load(&gc->irq_contexts, msix_index);
+	if (WARN_ON(!gic))
+		return;
+
 	spin_lock_irqsave(&gic->lock, flags);
 	list_for_each_entry_rcu(eq, &gic->eq_list, entry) {
 		if (queue == eq) {
@@ -1445,7 +1459,49 @@ void mana_gd_free_res_map(struct gdma_resource *r)
 	r->size = 0;
 }
 
-static int irq_setup(unsigned int *irqs, unsigned int len, int node)
+/*
+ * Spread on CPUs with the following heuristics:
+ *
+ * 1. No more than one IRQ per CPU, if possible;
+ * 2. NUMA locality is the second priority;
+ * 3. Sibling dislocality is the last priority.
+ *
+ * Let's consider this topology:
+ *
+ * Node            0               1
+ * Core        0       1       2       3
+ * CPU       0   1   2   3   4   5   6   7
+ *
+ * The most performant IRQ distribution based on the above topology
+ * and heuristics may look like this:
+ *
+ * IRQ     Nodes   Cores   CPUs
+ * 0       1       0       0-1
+ * 1       1       1       2-3
+ * 2       1       0       0-1
+ * 3       1       1       2-3
+ * 4       2       2       4-5
+ * 5       2       3       6-7
+ * 6       2       2       4-5
+ * 7       2       3       6-7
+ *
+ * The heuristics is implemented as follows.
+ *
+ * The outer for_each() loop resets the 'weight' to the actual number
+ * of CPUs in the hop. Then inner for_each() loop decrements it by the
+ * number of sibling groups (cores) while assigning first set of IRQs
+ * to each group. IRQs 0 and 1 above are distributed this way.
+ *
+ * Now, because NUMA locality is more important, we should walk the
+ * same set of siblings and assign 2nd set of IRQs (2 and 3), and it's
+ * implemented by the medium while() loop. We do like this unless the
+ * number of IRQs assigned on this hop will not become equal to number
+ * of CPUs in the hop (weight == 0). Then we switch to the next hop and
+ * do the same thing.
+ */
+
+static int irq_setup(unsigned int *irqs, unsigned int len, int node,
+		     bool skip_first_cpu)
 {
 	const struct cpumask *next, *prev = cpu_none_mask;
 	cpumask_var_t cpus __free(free_cpumask_var);
@@ -1460,11 +1516,18 @@ static int irq_setup(unsigned int *irqs, unsigned int len, int node)
 		while (weight > 0) {
 			cpumask_andnot(cpus, next, prev);
 			for_each_cpu(cpu, cpus) {
+				cpumask_andnot(cpus, cpus, topology_sibling_cpumask(cpu));
+				--weight;
+
+				if (unlikely(skip_first_cpu)) {
+					skip_first_cpu = false;
+					continue;
+				}
+
 				if (len-- == 0)
 					goto done;
+
 				irq_set_affinity_and_hint(*irqs++, topology_sibling_cpumask(cpu));
-				cpumask_andnot(cpus, cpus, topology_sibling_cpumask(cpu));
-				--weight;
 			}
 		}
 		prev = next;
@@ -1474,47 +1537,108 @@ static int irq_setup(unsigned int *irqs, unsigned int len, int node)
 	return 0;
 }
 
-static int mana_gd_setup_irqs(struct pci_dev *pdev)
+static int mana_gd_setup_dyn_irqs(struct pci_dev *pdev, int nvec)
 {
 	struct gdma_context *gc = pci_get_drvdata(pdev);
-	unsigned int max_queues_per_port;
 	struct gdma_irq_context *gic;
-	unsigned int max_irqs, cpu;
-	int start_irq_index = 1;
-	int nvec, *irqs, irq;
-	int err, i = 0, j;
+	bool skip_first_cpu = false;
+	int *irqs, irq, err, i;
 
-	cpus_read_lock();
-	max_queues_per_port = num_online_cpus();
-	if (max_queues_per_port > MANA_MAX_NUM_QUEUES)
-		max_queues_per_port = MANA_MAX_NUM_QUEUES;
+	irqs = kmalloc_array(nvec, sizeof(int), GFP_KERNEL);
+	if (!irqs)
+		return -ENOMEM;
+
+	/*
+	 * While processing the next pci irq vector, we start with index 1,
+	 * as IRQ vector at index 0 is already processed for HWC.
+	 * However, the population of irqs array starts with index 0, to be
+	 * further used in irq_setup()
+	 */
+	for (i = 1; i <= nvec; i++) {
+		gic = kzalloc(sizeof(*gic), GFP_KERNEL);
+		if (!gic) {
+			err = -ENOMEM;
+			goto free_irq;
+		}
+		gic->handler = mana_gd_process_eq_events;
+		INIT_LIST_HEAD(&gic->eq_list);
+		spin_lock_init(&gic->lock);
 
-	/* Need 1 interrupt for the Hardware communication Channel (HWC) */
-	max_irqs = max_queues_per_port + 1;
+		snprintf(gic->name, MANA_IRQ_NAME_SZ, "mana_q%d@pci:%s",
+			 i - 1, pci_name(pdev));
 
-	nvec = pci_alloc_irq_vectors(pdev, 2, max_irqs, PCI_IRQ_MSIX);
-	if (nvec < 0) {
-		cpus_read_unlock();
-		return nvec;
+		/* one pci vector is already allocated for HWC */
+		irqs[i - 1] = pci_irq_vector(pdev, i);
+		if (irqs[i - 1] < 0) {
+			err = irqs[i - 1];
+			goto free_current_gic;
+		}
+
+		err = request_irq(irqs[i - 1], mana_gd_intr, 0, gic->name, gic);
+		if (err)
+			goto free_current_gic;
+
+		xa_store(&gc->irq_contexts, i, gic, GFP_KERNEL);
 	}
-	if (nvec <= num_online_cpus())
-		start_irq_index = 0;
 
-	irqs = kmalloc_array((nvec - start_irq_index), sizeof(int), GFP_KERNEL);
-	if (!irqs) {
-		err = -ENOMEM;
-		goto free_irq_vector;
+	/*
+	 * When calling irq_setup() for dynamically added IRQs, if number of
+	 * CPUs is more than or equal to allocated MSI-X, we need to skip the
+	 * first CPU sibling group since they are already affinitized to HWC IRQ
+	 */
+	cpus_read_lock();
+	if (gc->num_msix_usable <= num_online_cpus())
+		skip_first_cpu = true;
+
+	err = irq_setup(irqs, nvec, gc->numa_node, skip_first_cpu);
+	if (err) {
+		cpus_read_unlock();
+		goto free_irq;
 	}
 
-	gc->irq_contexts = kcalloc(nvec, sizeof(struct gdma_irq_context),
-				   GFP_KERNEL);
-	if (!gc->irq_contexts) {
-		err = -ENOMEM;
-		goto free_irq_array;
+	cpus_read_unlock();
+	kfree(irqs);
+	return 0;
+
+free_current_gic:
+	kfree(gic);
+free_irq:
+	for (i -= 1; i > 0; i--) {
+		irq = pci_irq_vector(pdev, i);
+		gic = xa_load(&gc->irq_contexts, i);
+		if (WARN_ON(!gic))
+			continue;
+
+		irq_update_affinity_hint(irq, NULL);
+		free_irq(irq, gic);
+		xa_erase(&gc->irq_contexts, i);
+		kfree(gic);
 	}
+	kfree(irqs);
+	return err;
+}
+
+static int mana_gd_setup_irqs(struct pci_dev *pdev, int nvec)
+{
+	struct gdma_context *gc = pci_get_drvdata(pdev);
+	struct gdma_irq_context *gic;
+	int *irqs, *start_irqs, irq;
+	unsigned int cpu;
+	int err, i;
+
+	irqs = kmalloc_array(nvec, sizeof(int), GFP_KERNEL);
+	if (!irqs)
+		return -ENOMEM;
+
+	start_irqs = irqs;
 
 	for (i = 0; i < nvec; i++) {
-		gic = &gc->irq_contexts[i];
+		gic = kzalloc(sizeof(*gic), GFP_KERNEL);
+		if (!gic) {
+			err = -ENOMEM;
+			goto free_irq;
+		}
+
 		gic->handler = mana_gd_process_eq_events;
 		INIT_LIST_HEAD(&gic->eq_list);
 		spin_lock_init(&gic->lock);
@@ -1526,69 +1650,128 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev)
 			snprintf(gic->name, MANA_IRQ_NAME_SZ, "mana_q%d@pci:%s",
 				 i - 1, pci_name(pdev));
 
-		irq = pci_irq_vector(pdev, i);
-		if (irq < 0) {
-			err = irq;
-			goto free_irq;
+		irqs[i] = pci_irq_vector(pdev, i);
+		if (irqs[i] < 0) {
+			err = irqs[i];
+			goto free_current_gic;
 		}
 
-		if (!i) {
-			err = request_irq(irq, mana_gd_intr, 0, gic->name, gic);
-			if (err)
-				goto free_irq;
-
-			/* If number of IRQ is one extra than number of online CPUs,
-			 * then we need to assign IRQ0 (hwc irq) and IRQ1 to
-			 * same CPU.
-			 * Else we will use different CPUs for IRQ0 and IRQ1.
-			 * Also we are using cpumask_local_spread instead of
-			 * cpumask_first for the node, because the node can be
-			 * mem only.
-			 */
-			if (start_irq_index) {
-				cpu = cpumask_local_spread(i, gc->numa_node);
-				irq_set_affinity_and_hint(irq, cpumask_of(cpu));
-			} else {
-				irqs[start_irq_index] = irq;
-			}
-		} else {
-			irqs[i - start_irq_index] = irq;
-			err = request_irq(irqs[i - start_irq_index], mana_gd_intr, 0,
-					  gic->name, gic);
-			if (err)
-				goto free_irq;
-		}
+		err = request_irq(irqs[i], mana_gd_intr, 0, gic->name, gic);
+		if (err)
+			goto free_current_gic;
+
+		xa_store(&gc->irq_contexts, i, gic, GFP_KERNEL);
 	}
 
-	err = irq_setup(irqs, (nvec - start_irq_index), gc->numa_node);
-	if (err)
+	/* If number of IRQ is one extra than number of online CPUs,
+	 * then we need to assign IRQ0 (hwc irq) and IRQ1 to
+	 * same CPU.
+	 * Else we will use different CPUs for IRQ0 and IRQ1.
+	 * Also we are using cpumask_local_spread instead of
+	 * cpumask_first for the node, because the node can be
+	 * mem only.
+	 */
+	cpus_read_lock();
+	if (nvec > num_online_cpus()) {
+		cpu = cpumask_local_spread(0, gc->numa_node);
+		irq_set_affinity_and_hint(irqs[0], cpumask_of(cpu));
+		irqs++;
+		nvec -= 1;
+	}
+
+	err = irq_setup(irqs, nvec, gc->numa_node, false);
+	if (err) {
+		cpus_read_unlock();
 		goto free_irq;
+	}
 
-	gc->max_num_msix = nvec;
-	gc->num_msix_usable = nvec;
 	cpus_read_unlock();
-	kfree(irqs);
+	kfree(start_irqs);
 	return 0;
 
+free_current_gic:
+	kfree(gic);
 free_irq:
-	for (j = i - 1; j >= 0; j--) {
-		irq = pci_irq_vector(pdev, j);
-		gic = &gc->irq_contexts[j];
+	for (i -= 1; i >= 0; i--) {
+		irq = pci_irq_vector(pdev, i);
+		gic = xa_load(&gc->irq_contexts, i);
+		if (WARN_ON(!gic))
+			continue;
 
 		irq_update_affinity_hint(irq, NULL);
 		free_irq(irq, gic);
+		xa_erase(&gc->irq_contexts, i);
+		kfree(gic);
 	}
 
-	kfree(gc->irq_contexts);
-	gc->irq_contexts = NULL;
-free_irq_array:
-	kfree(irqs);
-free_irq_vector:
-	cpus_read_unlock();
-	pci_free_irq_vectors(pdev);
+	kfree(start_irqs);
 	return err;
 }
 
+static int mana_gd_setup_hwc_irqs(struct pci_dev *pdev)
+{
+	struct gdma_context *gc = pci_get_drvdata(pdev);
+	unsigned int max_irqs, min_irqs;
+	int nvec, err;
+
+	if (pci_msix_can_alloc_dyn(pdev)) {
+		max_irqs = 1;
+		min_irqs = 1;
+	} else {
+		/* Need 1 interrupt for HWC */
+		max_irqs = min(num_online_cpus(), MANA_MAX_NUM_QUEUES) + 1;
+		min_irqs = 2;
+	}
+
+	nvec = pci_alloc_irq_vectors(pdev, min_irqs, max_irqs, PCI_IRQ_MSIX);
+	if (nvec < 0)
+		return nvec;
+
+	err = mana_gd_setup_irqs(pdev, nvec);
+	if (err) {
+		pci_free_irq_vectors(pdev);
+		return err;
+	}
+
+	gc->num_msix_usable = nvec;
+	gc->max_num_msix = nvec;
+
+	return 0;
+}
+
+static int mana_gd_setup_remaining_irqs(struct pci_dev *pdev)
+{
+	struct gdma_context *gc = pci_get_drvdata(pdev);
+	struct msi_map irq_map;
+	int max_irqs, i, err;
+
+	if (!pci_msix_can_alloc_dyn(pdev))
+		/* remain irqs are already allocated with HWC IRQ */
+		return 0;
+
+	/* allocate only remaining IRQs*/
+	max_irqs = gc->num_msix_usable - 1;
+
+	for (i = 1; i <= max_irqs; i++) {
+		irq_map = pci_msix_alloc_irq_at(pdev, i, NULL);
+		if (!irq_map.virq) {
+			err = irq_map.index;
+			/* caller will handle cleaning up all allocated
+			 * irqs, after HWC is destroyed
+			 */
+			return err;
+		}
+	}
+
+	err = mana_gd_setup_dyn_irqs(pdev, max_irqs);
+	if (err)
+		return err;
+
+	gc->max_num_msix = gc->max_num_msix + max_irqs;
+
+	return 0;
+}
+
 static void mana_gd_remove_irqs(struct pci_dev *pdev)
 {
 	struct gdma_context *gc = pci_get_drvdata(pdev);
@@ -1603,19 +1786,21 @@ static void mana_gd_remove_irqs(struct pci_dev *pdev)
 		if (irq < 0)
 			continue;
 
-		gic = &gc->irq_contexts[i];
+		gic = xa_load(&gc->irq_contexts, i);
+		if (WARN_ON(!gic))
+			continue;
 
 		/* Need to clear the hint before free_irq */
 		irq_update_affinity_hint(irq, NULL);
 		free_irq(irq, gic);
+		xa_erase(&gc->irq_contexts, i);
+		kfree(gic);
 	}
 
 	pci_free_irq_vectors(pdev);
 
 	gc->max_num_msix = 0;
 	gc->num_msix_usable = 0;
-	kfree(gc->irq_contexts);
-	gc->irq_contexts = NULL;
 }
 
 static int mana_gd_setup(struct pci_dev *pdev)
@@ -1630,9 +1815,10 @@ static int mana_gd_setup(struct pci_dev *pdev)
 	if (!gc->service_wq)
 		return -ENOMEM;
 
-	err = mana_gd_setup_irqs(pdev);
+	err = mana_gd_setup_hwc_irqs(pdev);
 	if (err) {
-		dev_err(gc->dev, "Failed to setup IRQs: %d\n", err);
+		dev_err(gc->dev, "Failed to setup IRQs for HWC creation: %d\n",
+			err);
 		goto free_workqueue;
 	}
 
@@ -1648,6 +1834,12 @@ static int mana_gd_setup(struct pci_dev *pdev)
 	if (err)
 		goto destroy_hwc;
 
+	err = mana_gd_setup_remaining_irqs(pdev);
+	if (err) {
+		dev_err(gc->dev, "Failed to setup remaining IRQs: %d", err);
+		goto destroy_hwc;
+	}
+
 	err = mana_gd_detect_devices(pdev);
 	if (err)
 		goto destroy_hwc;
@@ -1728,6 +1920,7 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	gc->is_pf = mana_is_pf(pdev->device);
 	gc->bar0_va = bar0_va;
 	gc->dev = &pdev->dev;
+	xa_init(&gc->irq_contexts);
 
 	if (gc->is_pf)
 		gc->mana_pci_debugfs = debugfs_create_dir("0", mana_debugfs_root);
@@ -1762,6 +1955,7 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 */
 	debugfs_remove_recursive(gc->mana_pci_debugfs);
 	gc->mana_pci_debugfs = NULL;
+	xa_destroy(&gc->irq_contexts);
 	pci_iounmap(pdev, bar0_va);
 free_gc:
 	pci_set_drvdata(pdev, NULL);
@@ -1787,6 +1981,8 @@ static void mana_gd_remove(struct pci_dev *pdev)
 
 	gc->mana_pci_debugfs = NULL;
 
+	xa_destroy(&gc->irq_contexts);
+
 	pci_iounmap(pdev, gc->bar0_va);
 
 	vfree(gc);
diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c
index ef072e24c46d0..ada6c78a2bef4 100644
--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
+++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
@@ -881,7 +881,12 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
 	if (!wait_for_completion_timeout(&ctx->comp_event,
 					 (msecs_to_jiffies(hwc->hwc_timeout)))) {
 		if (hwc->hwc_timeout != 0)
-			dev_err(hwc->dev, "HWC: Request timed out!\n");
+			dev_err(hwc->dev, "HWC: Request timed out: %u ms\n",
+				hwc->hwc_timeout);
+
+		/* Reduce further waiting if HWC no response */
+		if (hwc->hwc_timeout > 1)
+			hwc->hwc_timeout = 1;
 
 		err = -ETIMEDOUT;
 		goto out;
diff --git a/drivers/net/ethernet/microsoft/mana/mana_bpf.c b/drivers/net/ethernet/microsoft/mana/mana_bpf.c
index d30721d4516fc..7697c9b52ed34 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_bpf.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_bpf.c
@@ -174,6 +174,7 @@ static int mana_xdp_set(struct net_device *ndev, struct bpf_prog *prog,
 	struct mana_port_context *apc = netdev_priv(ndev);
 	struct bpf_prog *old_prog;
 	struct gdma_context *gc;
+	int err;
 
 	gc = apc->ac->gdma_dev->gdma_context;
 
@@ -195,11 +196,45 @@ static int mana_xdp_set(struct net_device *ndev, struct bpf_prog *prog,
 	 */
 	apc->bpf_prog = prog;
 
-	if (old_prog)
-		bpf_prog_put(old_prog);
+	if (apc->port_is_up) {
+		/* Re-create rxq's after xdp prog was loaded or unloaded.
+		 * Ex: re create rxq's to switch from full pages to smaller
+		 * size page fragments when xdp prog is unloaded and
+		 * vice-versa.
+		 */
+
+		/* Pre-allocate buffers to prevent failure in mana_attach */
+		err = mana_pre_alloc_rxbufs(apc, ndev->mtu, apc->num_queues);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "XDP: Insufficient memory for tx/rx re-config");
+			return err;
+		}
+
+		err = mana_detach(ndev, false);
+		if (err) {
+			netdev_err(ndev,
+				   "mana_detach failed at xdp set: %d\n", err);
+			NL_SET_ERR_MSG_MOD(extack,
+					   "XDP: Re-config failed at detach");
+			goto err_dealloc_rxbuffs;
+		}
+
+		err = mana_attach(ndev);
+		if (err) {
+			netdev_err(ndev,
+				   "mana_attach failed at xdp set: %d\n", err);
+			NL_SET_ERR_MSG_MOD(extack,
+					   "XDP: Re-config failed at attach");
+			goto err_dealloc_rxbuffs;
+		}
 
-	if (apc->port_is_up)
 		mana_chn_setxdp(apc, prog);
+		mana_pre_dealloc_rxbufs(apc);
+	}
+
+	if (old_prog)
+		bpf_prog_put(old_prog);
 
 	if (prog)
 		ndev->max_mtu = MANA_XDP_MTU_MAX;
@@ -207,6 +242,11 @@ static int mana_xdp_set(struct net_device *ndev, struct bpf_prog *prog,
 		ndev->max_mtu = gc->adapter_mtu - ETH_HLEN;
 
 	return 0;
+
+err_dealloc_rxbuffs:
+	apc->bpf_prog = old_prog;
+	mana_pre_dealloc_rxbufs(apc);
+	return err;
 }
 
 int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf)
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 721d049c54de2..fdb32551833cd 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -55,6 +55,15 @@ static bool mana_en_need_log(struct mana_port_context *apc, int err)
 		return true;
 }
 
+static void mana_put_rx_page(struct mana_rxq *rxq, struct page *page,
+			     bool from_pool)
+{
+	if (from_pool)
+		page_pool_put_full_page(rxq->page_pool, page, false);
+	else
+		put_page(page);
+}
+
 /* Microsoft Azure Network Adapter (MANA) functions */
 
 static int mana_open(struct net_device *ndev)
@@ -628,21 +637,40 @@ static void *mana_get_rxbuf_pre(struct mana_rxq *rxq, dma_addr_t *da)
 }
 
 /* Get RX buffer's data size, alloc size, XDP headroom based on MTU */
-static void mana_get_rxbuf_cfg(int mtu, u32 *datasize, u32 *alloc_size,
-			       u32 *headroom)
+static void mana_get_rxbuf_cfg(struct mana_port_context *apc,
+			       int mtu, u32 *datasize, u32 *alloc_size,
+			       u32 *headroom, u32 *frag_count)
 {
-	if (mtu > MANA_XDP_MTU_MAX)
-		*headroom = 0; /* no support for XDP */
-	else
-		*headroom = XDP_PACKET_HEADROOM;
+	u32 len, buf_size;
 
-	*alloc_size = SKB_DATA_ALIGN(mtu + MANA_RXBUF_PAD + *headroom);
+	/* Calculate datasize first (consistent across all cases) */
+	*datasize = mtu + ETH_HLEN;
 
-	/* Using page pool in this case, so alloc_size is PAGE_SIZE */
-	if (*alloc_size < PAGE_SIZE)
-		*alloc_size = PAGE_SIZE;
+	/* For xdp and jumbo frames make sure only one packet fits per page */
+	if (mtu + MANA_RXBUF_PAD > PAGE_SIZE / 2 || mana_xdp_get(apc)) {
+		if (mana_xdp_get(apc)) {
+			*headroom = XDP_PACKET_HEADROOM;
+			*alloc_size = PAGE_SIZE;
+		} else {
+			*headroom = 0; /* no support for XDP */
+			*alloc_size = SKB_DATA_ALIGN(mtu + MANA_RXBUF_PAD +
+						     *headroom);
+		}
 
-	*datasize = mtu + ETH_HLEN;
+		*frag_count = 1;
+		return;
+	}
+
+	/* Standard MTU case - optimize for multiple packets per page */
+	*headroom = 0;
+
+	/* Calculate base buffer size needed */
+	len = SKB_DATA_ALIGN(mtu + MANA_RXBUF_PAD + *headroom);
+	buf_size = ALIGN(len, MANA_RX_FRAG_ALIGNMENT);
+
+	/* Calculate how many packets can fit in a page */
+	*frag_count = PAGE_SIZE / buf_size;
+	*alloc_size = buf_size;
 }
 
 int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu, int num_queues)
@@ -654,8 +682,9 @@ int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu, int num_qu
 	void *va;
 	int i;
 
-	mana_get_rxbuf_cfg(new_mtu, &mpc->rxbpre_datasize,
-			   &mpc->rxbpre_alloc_size, &mpc->rxbpre_headroom);
+	mana_get_rxbuf_cfg(mpc, new_mtu, &mpc->rxbpre_datasize,
+			   &mpc->rxbpre_alloc_size, &mpc->rxbpre_headroom,
+			   &mpc->rxbpre_frag_count);
 
 	dev = mpc->ac->gdma_dev->gdma_context->dev;
 
@@ -731,6 +760,78 @@ 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,
@@ -741,6 +842,7 @@ 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)
@@ -1184,6 +1286,95 @@ 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) {
+		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,
 		       mana_handle_t vport,
 		       u32 wq_type, struct mana_obj_spec *wq_spec,
@@ -1678,8 +1869,11 @@ static void mana_rx_skb(void *buf_va, bool from_pool,
 
 drop:
 	if (from_pool) {
-		page_pool_recycle_direct(rxq->page_pool,
-					 virt_to_head_page(buf_va));
+		if (rxq->frag_count == 1)
+			page_pool_recycle_direct(rxq->page_pool,
+						 virt_to_head_page(buf_va));
+		else
+			page_pool_free_va(rxq->page_pool, buf_va, true);
 	} else {
 		WARN_ON_ONCE(rxq->xdp_save_va);
 		/* Save for reuse */
@@ -1695,33 +1889,46 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev,
 			     dma_addr_t *da, bool *from_pool)
 {
 	struct page *page;
+	u32 offset;
 	void *va;
-
 	*from_pool = false;
 
-	/* Reuse XDP dropped page if available */
-	if (rxq->xdp_save_va) {
-		va = rxq->xdp_save_va;
-		rxq->xdp_save_va = NULL;
-	} else {
-		page = page_pool_dev_alloc_pages(rxq->page_pool);
-		if (!page)
+	/* Don't use fragments for jumbo frames or XDP where it's 1 fragment
+	 * per page.
+	 */
+	if (rxq->frag_count == 1) {
+		/* Reuse XDP dropped page if available */
+		if (rxq->xdp_save_va) {
+			va = rxq->xdp_save_va;
+			page = virt_to_head_page(va);
+			rxq->xdp_save_va = NULL;
+		} else {
+			page = page_pool_dev_alloc_pages(rxq->page_pool);
+			if (!page)
+				return NULL;
+
+			*from_pool = true;
+			va = page_to_virt(page);
+		}
+
+		*da = dma_map_single(dev, va + rxq->headroom, rxq->datasize,
+				     DMA_FROM_DEVICE);
+		if (dma_mapping_error(dev, *da)) {
+			mana_put_rx_page(rxq, page, *from_pool);
 			return NULL;
+		}
 
-		*from_pool = true;
-		va = page_to_virt(page);
+		return va;
 	}
 
-	*da = dma_map_single(dev, va + rxq->headroom, rxq->datasize,
-			     DMA_FROM_DEVICE);
-	if (dma_mapping_error(dev, *da)) {
-		if (*from_pool)
-			page_pool_put_full_page(rxq->page_pool, page, false);
-		else
-			put_page(virt_to_head_page(va));
-
+	page =  page_pool_dev_alloc_frag(rxq->page_pool, &offset,
+					 rxq->alloc_size);
+	if (!page)
 		return NULL;
-	}
+
+	va  = page_to_virt(page) + offset;
+	*da = page_pool_get_dma_addr(page) + offset + rxq->headroom;
+	*from_pool = true;
 
 	return va;
 }
@@ -1738,9 +1945,9 @@ static void mana_refill_rx_oob(struct device *dev, struct mana_rxq *rxq,
 	va = mana_get_rxfrag(rxq, dev, &da, &from_pool);
 	if (!va)
 		return;
-
-	dma_unmap_single(dev, rxoob->sgl[0].address, rxq->datasize,
-			 DMA_FROM_DEVICE);
+	if (!rxoob->from_pool || rxq->frag_count == 1)
+		dma_unmap_single(dev, rxoob->sgl[0].address, rxq->datasize,
+				 DMA_FROM_DEVICE);
 	*old_buf = rxoob->buf_va;
 	*old_fp = rxoob->from_pool;
 
@@ -2145,15 +2352,15 @@ static void mana_destroy_rxq(struct mana_port_context *apc,
 		if (!rx_oob->buf_va)
 			continue;
 
-		dma_unmap_single(dev, rx_oob->sgl[0].address,
-				 rx_oob->sgl[0].size, DMA_FROM_DEVICE);
-
 		page = virt_to_head_page(rx_oob->buf_va);
 
-		if (rx_oob->from_pool)
-			page_pool_put_full_page(rxq->page_pool, page, false);
-		else
-			put_page(page);
+		if (rxq->frag_count == 1 || !rx_oob->from_pool) {
+			dma_unmap_single(dev, rx_oob->sgl[0].address,
+					 rx_oob->sgl[0].size, DMA_FROM_DEVICE);
+			mana_put_rx_page(rxq, page, rx_oob->from_pool);
+		} else {
+			page_pool_free_va(rxq->page_pool, rx_oob->buf_va, true);
+		}
 
 		rx_oob->buf_va = NULL;
 	}
@@ -2259,11 +2466,21 @@ static int mana_create_page_pool(struct mana_rxq *rxq, struct gdma_context *gc)
 	struct page_pool_params pprm = {};
 	int ret;
 
-	pprm.pool_size = mpc->rx_queue_size;
+	pprm.pool_size = mpc->rx_queue_size / rxq->frag_count + 1;
 	pprm.nid = gc->numa_node;
 	pprm.napi = &rxq->rx_cq.napi;
 	pprm.netdev = rxq->ndev;
 	pprm.order = get_order(rxq->alloc_size);
+	pprm.dev = gc->dev;
+
+	/* Let the page pool do the dma map when page sharing with multiple
+	 * fragments enabled for rx buffers.
+	 */
+	if (rxq->frag_count > 1) {
+		pprm.flags =  PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
+		pprm.max_len = PAGE_SIZE;
+		pprm.dma_dir = DMA_FROM_DEVICE;
+	}
 
 	rxq->page_pool = page_pool_create(&pprm);
 
@@ -2302,9 +2519,8 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,
 	rxq->rxq_idx = rxq_idx;
 	rxq->rxobj = INVALID_MANA_HANDLE;
 
-	mana_get_rxbuf_cfg(ndev->mtu, &rxq->datasize, &rxq->alloc_size,
-			   &rxq->headroom);
-
+	mana_get_rxbuf_cfg(apc, ndev->mtu, &rxq->datasize, &rxq->alloc_size,
+			   &rxq->headroom, &rxq->frag_count);
 	/* Create page pool for RX queue */
 	err = mana_create_page_pool(rxq, gc);
 	if (err) {
@@ -3024,6 +3240,8 @@ 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/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
index 4fb3a04994a2d..a1afa75a94631 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
@@ -495,6 +495,12 @@ static int mana_set_ringparam(struct net_device *ndev,
 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;
 
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 720104661d7f2..60a4629fe6ba7 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -1812,6 +1812,11 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 
 	/* Enable NAPI handler before init callbacks */
 	netif_napi_add(ndev, &net_device->chan_table[0].napi, netvsc_poll);
+	napi_enable(&net_device->chan_table[0].napi);
+	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_RX,
+			     &net_device->chan_table[0].napi);
+	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_TX,
+			     &net_device->chan_table[0].napi);
 
 	/* Open the channel */
 	device->channel->next_request_id_callback = vmbus_next_request_id;
@@ -1831,12 +1836,6 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 	/* Channel is opened */
 	netdev_dbg(ndev, "hv_netvsc channel opened successfully\n");
 
-	napi_enable(&net_device->chan_table[0].napi);
-	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_RX,
-			     &net_device->chan_table[0].napi);
-	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_TX,
-			     &net_device->chan_table[0].napi);
-
 	/* Connect with the NetVsp */
 	ret = netvsc_connect_vsp(device, net_device, device_info);
 	if (ret != 0) {
@@ -1854,14 +1853,14 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 
 close:
 	RCU_INIT_POINTER(net_device_ctx->nvdev, NULL);
-	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_TX, NULL);
-	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_RX, NULL);
-	napi_disable(&net_device->chan_table[0].napi);
 
 	/* Now, we can close the channel safely */
 	vmbus_close(device->channel);
 
 cleanup:
+	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_TX, NULL);
+	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_RX, NULL);
+	napi_disable(&net_device->chan_table[0].napi);
 	netif_napi_del(&net_device->chan_table[0].napi);
 
 cleanup2:
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 9e73959e61ee0..c35f9685b6bf0 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1252,17 +1252,26 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc)
 	new_sc->rqstor_size = netvsc_rqstor_size(netvsc_ring_bytes);
 	new_sc->max_pkt_size = NETVSC_MAX_PKT_SIZE;
 
+	/* Enable napi before opening the vmbus channel to avoid races
+	 * as the host placing data on the host->guest ring may be left
+	 * out if napi was not enabled.
+	 */
+	napi_enable(&nvchan->napi);
+	netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_RX,
+			     &nvchan->napi);
+	netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_TX,
+			     &nvchan->napi);
+
 	ret = vmbus_open(new_sc, netvsc_ring_bytes,
 			 netvsc_ring_bytes, NULL, 0,
 			 netvsc_channel_cb, nvchan);
-	if (ret == 0) {
-		napi_enable(&nvchan->napi);
-		netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_RX,
-				     &nvchan->napi);
-		netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_TX,
-				     &nvchan->napi);
-	} else {
+	if (ret != 0) {
 		netdev_notice(ndev, "sub channel open failed: %d\n", ret);
+		netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_TX,
+				     NULL);
+		netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_RX,
+				     NULL);
+		napi_disable(&nvchan->napi);
 	}
 
 	if (atomic_inc_return(&nvscdev->open_chn) == nvscdev->num_chn)
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index 37fac5a42587b..3312a9cb13889 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -2061,6 +2061,7 @@ static struct irq_chip hv_msi_irq_chip = {
 static struct msi_domain_ops hv_msi_ops = {
 	.msi_prepare	= hv_msi_prepare,
 	.msi_free	= hv_msi_free,
+	.prepare_desc	= pci_msix_prepare_desc,
 };
 
 /**
@@ -2082,7 +2083,7 @@ static int hv_pcie_init_irq_domain(struct hv_pcibus_device *hbus)
 	hbus->msi_info.ops = &hv_msi_ops;
 	hbus->msi_info.flags = (MSI_FLAG_USE_DEF_DOM_OPS |
 		MSI_FLAG_USE_DEF_CHIP_OPS | MSI_FLAG_MULTI_PCI_MSI |
-		MSI_FLAG_PCI_MSIX);
+		MSI_FLAG_PCI_MSIX | MSI_FLAG_PCI_MSIX_ALLOC_DYN);
 	hbus->msi_info.handler = FLOW_HANDLER;
 	hbus->msi_info.handler_name = FLOW_NAME;
 	hbus->msi_info.data = hbus;
diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c
index d7ba8795d60f8..43129aa6d6c75 100644
--- a/drivers/pci/msi/irqdomain.c
+++ b/drivers/pci/msi/irqdomain.c
@@ -222,13 +222,14 @@ static void pci_irq_unmask_msix(struct irq_data *data)
 	pci_msix_unmask(irq_data_get_msi_desc(data));
 }
 
-static void pci_msix_prepare_desc(struct irq_domain *domain, msi_alloc_info_t *arg,
-				  struct msi_desc *desc)
+void pci_msix_prepare_desc(struct irq_domain *domain, msi_alloc_info_t *arg,
+			   struct msi_desc *desc)
 {
 	/* Don't fiddle with preallocated MSI descriptors */
 	if (!desc->pci.mask_base)
 		msix_prepare_msi_desc(to_pci_dev(desc->dev), desc);
 }
+EXPORT_SYMBOL_GPL(pci_msix_prepare_desc);
 
 static const struct msi_domain_template pci_msix_template = {
 	.chip = {
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 3284f52ab1fec..82d73214c3b32 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1406,14 +1406,19 @@ static struct vmbus_channel *get_og_chn(struct storvsc_device *stor_device,
 	}
 
 	/*
-	 * Our channel array is sparsley populated and we
+	 * Our channel array could be sparsley populated and we
 	 * initiated I/O on a processor/hw-q that does not
 	 * currently have a designated channel. Fix this.
 	 * The strategy is simple:
-	 * I. Ensure NUMA locality
-	 * II. Distribute evenly (best effort)
+	 * I. Prefer the channel associated with the current CPU
+	 * II. Ensure NUMA locality
+	 * III. Distribute evenly (best effort)
 	 */
 
+	/* Prefer the channel on the I/O issuing processor/hw-q */
+	if (cpumask_test_cpu(q_num, &stor_device->alloced_cpus))
+		return stor_device->stor_chns[q_num];
+
 	node_mask = cpumask_of_node(cpu_to_node(q_num));
 
 	num_channels = 0;
@@ -1469,59 +1474,48 @@ static int storvsc_do_io(struct hv_device *device,
 	/* See storvsc_change_target_cpu(). */
 	outgoing_channel = READ_ONCE(stor_device->stor_chns[q_num]);
 	if (outgoing_channel != NULL) {
-		if (outgoing_channel->target_cpu == q_num) {
-			/*
-			 * Ideally, we want to pick a different channel if
-			 * available on the same NUMA node.
-			 */
-			node_mask = cpumask_of_node(cpu_to_node(q_num));
-			for_each_cpu_wrap(tgt_cpu,
-				 &stor_device->alloced_cpus, q_num + 1) {
-				if (!cpumask_test_cpu(tgt_cpu, node_mask))
-					continue;
-				if (tgt_cpu == q_num)
-					continue;
-				channel = READ_ONCE(
-					stor_device->stor_chns[tgt_cpu]);
-				if (channel == NULL)
-					continue;
-				if (hv_get_avail_to_write_percent(
-							&channel->outbound)
-						> ring_avail_percent_lowater) {
-					outgoing_channel = channel;
-					goto found_channel;
-				}
-			}
+		if (hv_get_avail_to_write_percent(&outgoing_channel->outbound)
+				> ring_avail_percent_lowater)
+			goto found_channel;
 
-			/*
-			 * All the other channels on the same NUMA node are
-			 * busy. Try to use the channel on the current CPU
-			 */
-			if (hv_get_avail_to_write_percent(
-						&outgoing_channel->outbound)
-					> ring_avail_percent_lowater)
+		/*
+		 * Channel is busy, try to find a channel on the same NUMA node
+		 */
+		node_mask = cpumask_of_node(cpu_to_node(q_num));
+		for_each_cpu_wrap(tgt_cpu, &stor_device->alloced_cpus,
+				  q_num + 1) {
+			if (!cpumask_test_cpu(tgt_cpu, node_mask))
+				continue;
+			channel = READ_ONCE(stor_device->stor_chns[tgt_cpu]);
+			if (!channel)
+				continue;
+			if (hv_get_avail_to_write_percent(&channel->outbound)
+					> ring_avail_percent_lowater) {
+				outgoing_channel = channel;
 				goto found_channel;
+			}
+		}
 
-			/*
-			 * If we reach here, all the channels on the current
-			 * NUMA node are busy. Try to find a channel in
-			 * other NUMA nodes
-			 */
-			for_each_cpu(tgt_cpu, &stor_device->alloced_cpus) {
-				if (cpumask_test_cpu(tgt_cpu, node_mask))
-					continue;
-				channel = READ_ONCE(
-					stor_device->stor_chns[tgt_cpu]);
-				if (channel == NULL)
-					continue;
-				if (hv_get_avail_to_write_percent(
-							&channel->outbound)
-						> ring_avail_percent_lowater) {
-					outgoing_channel = channel;
-					goto found_channel;
-				}
+		/*
+		 * If we reach here, all the channels on the current
+		 * NUMA node are busy. Try to find a channel in
+		 * all NUMA nodes
+		 */
+		for_each_cpu_wrap(tgt_cpu, &stor_device->alloced_cpus,
+				  q_num + 1) {
+			channel = READ_ONCE(stor_device->stor_chns[tgt_cpu]);
+			if (!channel)
+				continue;
+			if (hv_get_avail_to_write_percent(&channel->outbound)
+					> ring_avail_percent_lowater) {
+				outgoing_channel = channel;
+				goto found_channel;
 			}
 		}
+		/*
+		 * If we reach here, all the channels are busy. Use the
+		 * original channel found.
+		 */
 	} else {
 		spin_lock_irqsave(&stor_device->lock, flags);
 		outgoing_channel = stor_device->stor_chns[q_num];
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 8d97b890faeca..b3d17b7ebdbec 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -679,6 +679,8 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode,
 					     struct irq_domain *parent);
 u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev);
 struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev);
+void pci_msix_prepare_desc(struct irq_domain *domain, msi_alloc_info_t *arg,
+			   struct msi_desc *desc);
 #else /* CONFIG_PCI_MSI */
 static inline struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev)
 {
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 79516db61bcae..6c300fd325237 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -390,7 +390,7 @@ struct gdma_context {
 	unsigned int		max_num_queues;
 	unsigned int		max_num_msix;
 	unsigned int		num_msix_usable;
-	struct gdma_irq_context	*irq_contexts;
+	struct xarray		irq_contexts;
 
 	/* L2 MTU */
 	u16 adapter_mtu;
@@ -582,18 +582,23 @@ enum {
 /* Driver can handle holes (zeros) in the device list */
 #define GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP BIT(11)
 
+/* Driver supports dynamic MSI-X vector allocation */
+#define GDMA_DRV_CAP_FLAG_1_DYNAMIC_IRQ_ALLOC_SUPPORT BIT(13)
+
 /* Driver can self reset on EQE notification */
 #define GDMA_DRV_CAP_FLAG_1_SELF_RESET_ON_EQE BIT(14)
 
 /* Driver can self reset on FPGA Reconfig EQE notification */
 #define GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE BIT(17)
 
+
 #define GDMA_DRV_CAP_FLAGS1 \
 	(GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \
 	 GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX | \
 	 GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG | \
 	 GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT | \
 	 GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP | \
+	 GDMA_DRV_CAP_FLAG_1_DYNAMIC_IRQ_ALLOC_SUPPORT | \
 	 GDMA_DRV_CAP_FLAG_1_SELF_RESET_ON_EQE | \
 	 GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE)
 
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 4176edf1be719..0921485565c05 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"
@@ -64,6 +65,8 @@ enum TRI_STATE {
 #define MANA_STATS_RX_COUNT 5
 #define MANA_STATS_TX_COUNT 11
 
+#define MANA_RX_FRAG_ALIGNMENT 64
+
 struct mana_stats_rx {
 	u64 packets;
 	u64 bytes;
@@ -327,6 +330,7 @@ struct mana_rxq {
 	u32 datasize;
 	u32 alloc_size;
 	u32 headroom;
+	u32 frag_count;
 
 	mana_handle_t rxobj;
 
@@ -509,6 +513,7 @@ struct mana_port_context {
 	u32 rxbpre_datasize;
 	u32 rxbpre_alloc_size;
 	u32 rxbpre_headroom;
+	u32 rxbpre_frag_count;
 
 	struct bpf_prog *bpf_prog;
 
@@ -526,7 +531,14 @@ 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;
+	/* Maximum speed supported by the SKU (mbps) */
+	u32 max_speed;
 
 	bool port_is_up;
 	bool port_st_save; /* Saved port state */
@@ -562,6 +574,9 @@ 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 +604,8 @@ 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 +615,35 @@ 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;