diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index a0fdd052d7f1..e8b7ffb47eb9 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -210,6 +210,8 @@ static int mana_gd_query_max_resources(struct pci_dev *pdev)
 	} else {
 		/* If dynamic allocation is enabled we have already allocated
 		 * hwc msi
+		 * Also, we make sure in this case the following is always true
+		 * (num_msix_usable - 1 HWC) <= num_online_cpus()
 		 */
 		gc->num_msix_usable = min(resp.max_msix, num_online_cpus() + 1);
 	}
@@ -1909,8 +1911,8 @@ void mana_gd_free_res_map(struct gdma_resource *r)
  * do the same thing.
  */
 
-static int irq_setup(unsigned int *irqs, unsigned int len, int node,
-		     bool skip_first_cpu)
+static int mana_irq_setup_numa_aware(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);
@@ -1946,11 +1948,24 @@ static int irq_setup(unsigned int *irqs, unsigned int len, int node,
 	return 0;
 }
 
+/* must be called with cpus_read_lock() held */
+static void mana_irq_setup_linear(unsigned int *irqs, unsigned int len)
+{
+	int cpu;
+
+	for_each_online_cpu(cpu) {
+		if (len == 0)
+			break;
+
+		irq_set_affinity_and_hint(*irqs++, cpumask_of(cpu));
+		len--;
+	}
+}
+
 static int mana_gd_setup_dyn_irqs(struct pci_dev *pdev, int nvec)
 {
 	struct gdma_context *gc = pci_get_drvdata(pdev);
 	struct gdma_irq_context *gic;
-	bool skip_first_cpu = false;
 	int *irqs, err, i, msi;
 
 	irqs = kmalloc_objs(int, nvec);
@@ -1958,10 +1973,12 @@ static int mana_gd_setup_dyn_irqs(struct pci_dev *pdev, int nvec)
 		return -ENOMEM;
 
 	/*
+	 * In this function, num_msix_usable = HWC IRQ + Queue IRQ.
+	 * nvec is only Queue IRQ (HWC already setup).
 	 * 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()
+	 * further used in mana_irq_setup_numa_aware()
 	 */
 	for (i = 1; i <= nvec; i++) {
 		msi = i;
@@ -1975,18 +1992,51 @@ static int mana_gd_setup_dyn_irqs(struct pci_dev *pdev, int nvec)
 	}
 
 	/*
-	 * 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
+	 * When calling mana_irq_setup_numa_aware() 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;
+	if (gc->num_msix_usable <= num_online_cpus()) {
+		err = mana_irq_setup_numa_aware(irqs, nvec, gc->numa_node,
+						true);
+		if (err) {
+			cpus_read_unlock();
+			goto free_irq;
+		}
+	} else {
+		/*
+		 * When num_msix_usable are more than num_online_cpus, our
+		 * queue IRQs should be equal to num of online vCPUs.
+		 * We try to make sure queue IRQs spread across all vCPUs.
+		 * In such a case NUMA or CPU core affinity does not matter.
+		 * Note: in this case the total mana IRQ should always be
+		 * num_online_cpus + 1. The first HWC IRQ is already handled
+		 * in HWC setup calls
+		 * However, if CPUs went offline since num_msix_usable was
+		 * computed, queue IRQs will be more than num_online_cpus().
+		 * In such cases remaining extra IRQs will retain their default
+		 * affinity.
+		 */
+		int first_unassigned = num_online_cpus();
 
-	err = irq_setup(irqs, nvec, gc->numa_node, skip_first_cpu);
-	if (err) {
-		cpus_read_unlock();
-		goto free_irq;
+		if (nvec > first_unassigned) {
+			char buf[32];
+
+			if (first_unassigned == nvec - 1)
+				snprintf(buf, sizeof(buf), "%d",
+					 first_unassigned);
+			else
+				snprintf(buf, sizeof(buf), "%d-%d",
+					 first_unassigned, nvec - 1);
+
+			dev_dbg(&pdev->dev,
+				"MANA IRQ indices #%s will retain the default CPU affinity\n",
+				buf);
+		}
+
+		mana_irq_setup_linear(irqs, nvec);
 	}
 
 	cpus_read_unlock();
@@ -2041,7 +2091,7 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev, int nvec)
 		nvec -= 1;
 	}
 
-	err = irq_setup(irqs, nvec, gc->numa_node, false);
+	err = mana_irq_setup_numa_aware(irqs, nvec, gc->numa_node, false);
 	if (err) {
 		cpus_read_unlock();
 		goto free_irq;