1 files changed, 451 insertions, 97 deletions

diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 3504507477c6..43f034e180c4 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -6,8 +6,12 @@
 #include <linux/pci.h>
 #include <linux/utsname.h>
 #include <linux/version.h>
+#include <linux/msi.h>
+#include <linux/irqdomain.h>
+#include <linux/export.h>
 
 #include <net/mana/mana.h>
+#include <net/mana/hw_channel.h>
 
 struct dentry *mana_debugfs_root;
 
@@ -31,6 +35,9 @@ static void mana_gd_init_pf_regs(struct pci_dev *pdev)
 	gc->db_page_base = gc->bar0_va +
 				mana_gd_r64(gc, GDMA_PF_REG_DB_PAGE_OFF);
 
+	gc->phys_db_page_base = gc->bar0_pa +
+				mana_gd_r64(gc, GDMA_PF_REG_DB_PAGE_OFF);
+
 	sriov_base_off = mana_gd_r64(gc, GDMA_SRIOV_REG_CFG_BASE_OFF);
 
 	sriov_base_va = gc->bar0_va + sriov_base_off;
@@ -63,6 +70,24 @@ static void mana_gd_init_registers(struct pci_dev *pdev)
 		mana_gd_init_vf_regs(pdev);
 }
 
+/* Suppress logging when we set timeout to zero */
+bool mana_need_log(struct gdma_context *gc, int err)
+{
+	struct hw_channel_context *hwc;
+
+	if (err != -ETIMEDOUT)
+		return true;
+
+	if (!gc)
+		return true;
+
+	hwc = gc->hwc.driver_data;
+	if (hwc && hwc->hwc_timeout == 0)
+		return false;
+
+	return true;
+}
+
 static int mana_gd_query_max_resources(struct pci_dev *pdev)
 {
 	struct gdma_context *gc = pci_get_drvdata(pdev);
@@ -80,8 +105,15 @@ 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;
@@ -266,8 +298,9 @@ static int mana_gd_disable_queue(struct gdma_queue *queue)
 
 	err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
 	if (err || resp.hdr.status) {
-		dev_err(gc->dev, "Failed to disable queue: %d, 0x%x\n", err,
-			resp.hdr.status);
+		if (mana_need_log(gc, err))
+			dev_err(gc->dev, "Failed to disable queue: %d, 0x%x\n", err,
+				resp.hdr.status);
 		return err ? err : -EPROTO;
 	}
 
@@ -352,11 +385,113 @@ void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit)
 }
 EXPORT_SYMBOL_NS(mana_gd_ring_cq, "NET_MANA");
 
+#define MANA_SERVICE_PERIOD 10
+
+static void mana_serv_fpga(struct pci_dev *pdev)
+{
+	struct pci_bus *bus, *parent;
+
+	pci_lock_rescan_remove();
+
+	bus = pdev->bus;
+	if (!bus) {
+		dev_err(&pdev->dev, "MANA service: no bus\n");
+		goto out;
+	}
+
+	parent = bus->parent;
+	if (!parent) {
+		dev_err(&pdev->dev, "MANA service: no parent bus\n");
+		goto out;
+	}
+
+	pci_stop_and_remove_bus_device(bus->self);
+
+	msleep(MANA_SERVICE_PERIOD * 1000);
+
+	pci_rescan_bus(parent);
+
+out:
+	pci_unlock_rescan_remove();
+}
+
+static void mana_serv_reset(struct pci_dev *pdev)
+{
+	struct gdma_context *gc = pci_get_drvdata(pdev);
+	struct hw_channel_context *hwc;
+
+	if (!gc) {
+		dev_err(&pdev->dev, "MANA service: no GC\n");
+		return;
+	}
+
+	hwc = gc->hwc.driver_data;
+	if (!hwc) {
+		dev_err(&pdev->dev, "MANA service: no HWC\n");
+		goto out;
+	}
+
+	/* HWC is not responding in this case, so don't wait */
+	hwc->hwc_timeout = 0;
+
+	dev_info(&pdev->dev, "MANA reset cycle start\n");
+
+	mana_gd_suspend(pdev, PMSG_SUSPEND);
+
+	msleep(MANA_SERVICE_PERIOD * 1000);
+
+	mana_gd_resume(pdev);
+
+	dev_info(&pdev->dev, "MANA reset cycle completed\n");
+
+out:
+	gc->in_service = false;
+}
+
+struct mana_serv_work {
+	struct work_struct serv_work;
+	struct pci_dev *pdev;
+	enum gdma_eqe_type type;
+};
+
+static void mana_serv_func(struct work_struct *w)
+{
+	struct mana_serv_work *mns_wk;
+	struct pci_dev *pdev;
+
+	mns_wk = container_of(w, struct mana_serv_work, serv_work);
+	pdev = mns_wk->pdev;
+
+	if (!pdev)
+		goto out;
+
+	switch (mns_wk->type) {
+	case GDMA_EQE_HWC_FPGA_RECONFIG:
+		mana_serv_fpga(pdev);
+		break;
+
+	case GDMA_EQE_HWC_RESET_REQUEST:
+		mana_serv_reset(pdev);
+		break;
+
+	default:
+		dev_err(&pdev->dev, "MANA service: unknown type %d\n",
+			mns_wk->type);
+		break;
+	}
+
+out:
+	pci_dev_put(pdev);
+	kfree(mns_wk);
+	module_put(THIS_MODULE);
+}
+
 static void mana_gd_process_eqe(struct gdma_queue *eq)
 {
 	u32 head = eq->head % (eq->queue_size / GDMA_EQE_SIZE);
 	struct gdma_context *gc = eq->gdma_dev->gdma_context;
 	struct gdma_eqe *eq_eqe_ptr = eq->queue_mem_ptr;
+	struct mana_serv_work *mns_wk;
 	union gdma_eqe_info eqe_info;
 	enum gdma_eqe_type type;
 	struct gdma_event event;
@@ -401,6 +536,35 @@ static void mana_gd_process_eqe(struct gdma_queue *eq)
 		eq->eq.callback(eq->eq.context, eq, &event);
 		break;
 
+	case GDMA_EQE_HWC_FPGA_RECONFIG:
+	case GDMA_EQE_HWC_RESET_REQUEST:
+		dev_info(gc->dev, "Recv MANA service type:%d\n", type);
+
+		if (gc->in_service) {
+			dev_info(gc->dev, "Already in service\n");
+			break;
+		}
+
+		if (!try_module_get(THIS_MODULE)) {
+			dev_info(gc->dev, "Module is unloading\n");
+			break;
+		}
+
+		mns_wk = kzalloc(sizeof(*mns_wk), GFP_ATOMIC);
+		if (!mns_wk) {
+			module_put(THIS_MODULE);
+			break;
+		}
+
+		dev_info(gc->dev, "Start MANA service type:%d\n", type);
+		gc->in_service = true;
+		mns_wk->pdev = to_pci_dev(gc->dev);
+		mns_wk->type = type;
+		pci_dev_get(mns_wk->pdev);
+		INIT_WORK(&mns_wk->serv_work, mana_serv_func);
+		schedule_work(&mns_wk->serv_work);
+		break;
+
 	default:
 		break;
 	}
@@ -483,7 +647,9 @@ 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);
@@ -492,7 +658,7 @@ static int mana_gd_register_irq(struct gdma_queue *queue,
 	return 0;
 }
 
-static void mana_gd_deregiser_irq(struct gdma_queue *queue)
+static void mana_gd_deregister_irq(struct gdma_queue *queue)
 {
 	struct gdma_dev *gd = queue->gdma_dev;
 	struct gdma_irq_context *gic;
@@ -508,7 +674,10 @@ 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) {
@@ -542,7 +711,8 @@ int mana_gd_test_eq(struct gdma_context *gc, struct gdma_queue *eq)
 
 	err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
 	if (err) {
-		dev_err(dev, "test_eq failed: %d\n", err);
+		if (mana_need_log(gc, err))
+			dev_err(dev, "test_eq failed: %d\n", err);
 		goto out;
 	}
 
@@ -577,11 +747,11 @@ static void mana_gd_destroy_eq(struct gdma_context *gc, bool flush_evenets,
 
 	if (flush_evenets) {
 		err = mana_gd_test_eq(gc, queue);
-		if (err)
+		if (err && mana_need_log(gc, err))
 			dev_warn(gc->dev, "Failed to flush EQ: %d\n", err);
 	}
 
-	mana_gd_deregiser_irq(queue);
+	mana_gd_deregister_irq(queue);
 
 	if (queue->eq.disable_needed)
 		mana_gd_disable_queue(queue);
@@ -723,8 +893,9 @@ int mana_gd_destroy_dma_region(struct gdma_context *gc, u64 dma_region_handle)
 
 	err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
 	if (err || resp.hdr.status) {
-		dev_err(gc->dev, "Failed to destroy DMA region: %d, 0x%x\n",
-			err, resp.hdr.status);
+		if (mana_need_log(gc, err))
+			dev_err(gc->dev, "Failed to destroy DMA region: %d, 0x%x\n",
+				err, resp.hdr.status);
 		return -EPROTO;
 	}
 
@@ -1024,8 +1195,9 @@ int mana_gd_deregister_device(struct gdma_dev *gd)
 
 	err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
 	if (err || resp.hdr.status) {
-		dev_err(gc->dev, "Failed to deregister device: %d, 0x%x\n",
-			err, resp.hdr.status);
+		if (mana_need_log(gc, err))
+			dev_err(gc->dev, "Failed to deregister device: %d, 0x%x\n",
+				err, resp.hdr.status);
 		if (!err)
 			err = -EPROTO;
 	}
@@ -1288,7 +1460,49 @@ 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);
@@ -1303,11 +1517,18 @@ 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;
@@ -1317,47 +1538,108 @@ done:
 	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);
@@ -1369,69 +1651,128 @@ 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);
@@ -1446,19 +1787,21 @@ 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)
@@ -1473,9 +1816,10 @@ 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;
 	}
 
@@ -1491,6 +1835,12 @@ 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;
@@ -1571,6 +1921,7 @@ 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);
@@ -1605,6 +1956,7 @@ unmap_bar:
 	 */
 	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);
@@ -1630,6 +1982,8 @@ 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);
@@ -1641,7 +1995,7 @@ static void mana_gd_remove(struct pci_dev *pdev)
 }
 
 /* The 'state' parameter is not used. */
-static int mana_gd_suspend(struct pci_dev *pdev, pm_message_t state)
+int mana_gd_suspend(struct pci_dev *pdev, pm_message_t state)
 {
 	struct gdma_context *gc = pci_get_drvdata(pdev);
 
@@ -1657,7 +2011,7 @@ static int mana_gd_suspend(struct pci_dev *pdev, pm_message_t state)
  * fail -- if this happens, it's safer to just report an error than try to undo
  * what has been done.
  */
-static int mana_gd_resume(struct pci_dev *pdev)
+int mana_gd_resume(struct pci_dev *pdev)
 {
 	struct gdma_context *gc = pci_get_drvdata(pdev);
 	int err;