19 files changed, 343 insertions, 163 deletions

diff --git a/Documentation/networking/scaling.rst b/Documentation/networking/scaling.rst
index 6984700cec6a..99b6a61e5e31 100644
--- a/Documentation/networking/scaling.rst
+++ b/Documentation/networking/scaling.rst
@@ -434,8 +434,10 @@ rps_dev_flow_table. The stack consults a CPU to hardware queue map which
 is maintained by the NIC driver. This is an auto-generated reverse map of
 the IRQ affinity table shown by /proc/interrupts. Drivers can use
 functions in the cpu_rmap (“CPU affinity reverse map”) kernel library
-to populate the map. For each CPU, the corresponding queue in the map is
-set to be one whose processing CPU is closest in cache locality.
+to populate the map. Alternatively, drivers can delegate the cpu_rmap
+management to the Kernel by calling netif_enable_cpu_rmap(). For each CPU,
+the corresponding queue in the map is set to be one whose processing CPU is
+closest in cache locality.
 
 
 Accelerated RFS Configuration
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index c1295dfad0d0..6aab85a7c60a 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -5,9 +5,6 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#ifdef CONFIG_RFS_ACCEL
-#include <linux/cpu_rmap.h>
-#endif /* CONFIG_RFS_ACCEL */
 #include <linux/ethtool.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -162,30 +159,6 @@ int ena_xmit_common(struct ena_adapter *adapter,
 	return 0;
 }
 
-static int ena_init_rx_cpu_rmap(struct ena_adapter *adapter)
-{
-#ifdef CONFIG_RFS_ACCEL
-	u32 i;
-	int rc;
-
-	adapter->netdev->rx_cpu_rmap = alloc_irq_cpu_rmap(adapter->num_io_queues);
-	if (!adapter->netdev->rx_cpu_rmap)
-		return -ENOMEM;
-	for (i = 0; i < adapter->num_io_queues; i++) {
-		int irq_idx = ENA_IO_IRQ_IDX(i);
-
-		rc = irq_cpu_rmap_add(adapter->netdev->rx_cpu_rmap,
-				      pci_irq_vector(adapter->pdev, irq_idx));
-		if (rc) {
-			free_irq_cpu_rmap(adapter->netdev->rx_cpu_rmap);
-			adapter->netdev->rx_cpu_rmap = NULL;
-			return rc;
-		}
-	}
-#endif /* CONFIG_RFS_ACCEL */
-	return 0;
-}
-
 static void ena_init_io_rings_common(struct ena_adapter *adapter,
 				     struct ena_ring *ring, u16 qid)
 {
@@ -1596,7 +1569,7 @@ static int ena_enable_msix(struct ena_adapter *adapter)
 		adapter->num_io_queues = irq_cnt - ENA_ADMIN_MSIX_VEC;
 	}
 
-	if (ena_init_rx_cpu_rmap(adapter))
+	if (netif_enable_cpu_rmap(adapter->netdev, adapter->num_io_queues))
 		netif_warn(adapter, probe, adapter->netdev,
 			   "Failed to map IRQs to CPUs\n");
 
@@ -1742,13 +1715,6 @@ static void ena_free_io_irq(struct ena_adapter *adapter)
 	struct ena_irq *irq;
 	int i;
 
-#ifdef CONFIG_RFS_ACCEL
-	if (adapter->msix_vecs >= 1) {
-		free_irq_cpu_rmap(adapter->netdev->rx_cpu_rmap);
-		adapter->netdev->rx_cpu_rmap = NULL;
-	}
-#endif /* CONFIG_RFS_ACCEL */
-
 	for (i = ENA_IO_IRQ_FIRST_IDX; i < ENA_MAX_MSIX_VEC(io_queue_count); i++) {
 		irq = &adapter->irq_tbl[i];
 		irq_set_affinity_hint(irq->vector, NULL);
@@ -4131,13 +4097,6 @@ static void __ena_shutoff(struct pci_dev *pdev, bool shutdown)
 	ena_dev = adapter->ena_dev;
 	netdev = adapter->netdev;
 
-#ifdef CONFIG_RFS_ACCEL
-	if ((adapter->msix_vecs >= 1) && (netdev->rx_cpu_rmap)) {
-		free_irq_cpu_rmap(netdev->rx_cpu_rmap);
-		netdev->rx_cpu_rmap = NULL;
-	}
-
-#endif /* CONFIG_RFS_ACCEL */
 	/* Make sure timer and reset routine won't be called after
 	 * freeing device resources.
 	 */
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index c9104b13e1d2..5ceeae664598 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -475,9 +475,6 @@ struct ice_q_vector {
 	struct ice_ring_container rx;
 	struct ice_ring_container tx;
 
-	cpumask_t affinity_mask;
-	struct irq_affinity_notify affinity_notify;
-
 	struct ice_channel *ch;
 
 	char name[ICE_INT_NAME_STR_LEN];
diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c
index 7cee365cc7d1..171cdec741c2 100644
--- a/drivers/net/ethernet/intel/ice/ice_arfs.c
+++ b/drivers/net/ethernet/intel/ice/ice_arfs.c
@@ -571,25 +571,6 @@ void ice_clear_arfs(struct ice_vsi *vsi)
 }
 
 /**
- * ice_free_cpu_rx_rmap - free setup CPU reverse map
- * @vsi: the VSI to be forwarded to
- */
-void ice_free_cpu_rx_rmap(struct ice_vsi *vsi)
-{
-	struct net_device *netdev;
-
-	if (!vsi || vsi->type != ICE_VSI_PF)
-		return;
-
-	netdev = vsi->netdev;
-	if (!netdev || !netdev->rx_cpu_rmap)
-		return;
-
-	free_irq_cpu_rmap(netdev->rx_cpu_rmap);
-	netdev->rx_cpu_rmap = NULL;
-}
-
-/**
  * ice_set_cpu_rx_rmap - setup CPU reverse map for each queue
  * @vsi: the VSI to be forwarded to
  */
@@ -597,7 +578,6 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi)
 {
 	struct net_device *netdev;
 	struct ice_pf *pf;
-	int i;
 
 	if (!vsi || vsi->type != ICE_VSI_PF)
 		return 0;
@@ -610,18 +590,7 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi)
 	netdev_dbg(netdev, "Setup CPU RMAP: vsi type 0x%x, ifname %s, q_vectors %d\n",
 		   vsi->type, netdev->name, vsi->num_q_vectors);
 
-	netdev->rx_cpu_rmap = alloc_irq_cpu_rmap(vsi->num_q_vectors);
-	if (unlikely(!netdev->rx_cpu_rmap))
-		return -EINVAL;
-
-	ice_for_each_q_vector(vsi, i)
-		if (irq_cpu_rmap_add(netdev->rx_cpu_rmap,
-				     vsi->q_vectors[i]->irq.virq)) {
-			ice_free_cpu_rx_rmap(vsi);
-			return -EINVAL;
-		}
-
-	return 0;
+	return netif_enable_cpu_rmap(netdev, vsi->num_q_vectors);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.h b/drivers/net/ethernet/intel/ice/ice_arfs.h
index 9669ad9bf7b5..9706293128c3 100644
--- a/drivers/net/ethernet/intel/ice/ice_arfs.h
+++ b/drivers/net/ethernet/intel/ice/ice_arfs.h
@@ -45,7 +45,6 @@ int
 ice_rx_flow_steer(struct net_device *netdev, const struct sk_buff *skb,
 		  u16 rxq_idx, u32 flow_id);
 void ice_clear_arfs(struct ice_vsi *vsi);
-void ice_free_cpu_rx_rmap(struct ice_vsi *vsi);
 void ice_init_arfs(struct ice_vsi *vsi);
 void ice_sync_arfs_fltrs(struct ice_pf *pf);
 int ice_set_cpu_rx_rmap(struct ice_vsi *vsi);
@@ -56,7 +55,6 @@ ice_is_arfs_using_perfect_flow(struct ice_hw *hw,
 			       enum ice_fltr_ptype flow_type);
 #else
 static inline void ice_clear_arfs(struct ice_vsi *vsi) { }
-static inline void ice_free_cpu_rx_rmap(struct ice_vsi *vsi) { }
 static inline void ice_init_arfs(struct ice_vsi *vsi) { }
 static inline void ice_sync_arfs_fltrs(struct ice_pf *pf) { }
 static inline void ice_remove_arfs(struct ice_pf *pf) { }
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index b3234a55a253..6db4ad8fc70b 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -147,10 +147,6 @@ skip_alloc:
 	q_vector->reg_idx = q_vector->irq.index;
 	q_vector->vf_reg_idx = q_vector->irq.index;
 
-	/* only set affinity_mask if the CPU is online */
-	if (cpu_online(v_idx))
-		cpumask_set_cpu(v_idx, &q_vector->affinity_mask);
-
 	/* This will not be called in the driver load path because the netdev
 	 * will not be created yet. All other cases with register the NAPI
 	 * handler here (i.e. resume, reset/rebuild, etc.)
@@ -276,7 +272,8 @@ static void ice_cfg_xps_tx_ring(struct ice_tx_ring *ring)
 	if (test_and_set_bit(ICE_TX_XPS_INIT_DONE, ring->xps_state))
 		return;
 
-	netif_set_xps_queue(ring->netdev, &ring->q_vector->affinity_mask,
+	netif_set_xps_queue(ring->netdev,
+			    &ring->q_vector->napi.config->affinity_mask,
 			    ring->q_index);
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 7f5b229cab05..715efd8a359f 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2592,7 +2592,6 @@ void ice_vsi_free_irq(struct ice_vsi *vsi)
 		return;
 
 	vsi->irqs_ready = false;
-	ice_free_cpu_rx_rmap(vsi);
 
 	ice_for_each_q_vector(vsi, i) {
 		int irq_num;
@@ -2605,12 +2604,6 @@ void ice_vsi_free_irq(struct ice_vsi *vsi)
 		      vsi->q_vectors[i]->num_ring_rx))
 			continue;
 
-		/* clear the affinity notifier in the IRQ descriptor */
-		if (!IS_ENABLED(CONFIG_RFS_ACCEL))
-			irq_set_affinity_notifier(irq_num, NULL);
-
-		/* clear the affinity_hint in the IRQ descriptor */
-		irq_update_affinity_hint(irq_num, NULL);
 		synchronize_irq(irq_num);
 		devm_free_irq(ice_pf_to_dev(pf), irq_num, vsi->q_vectors[i]);
 	}
@@ -2765,11 +2758,18 @@ void ice_vsi_set_napi_queues(struct ice_vsi *vsi)
 void ice_vsi_clear_napi_queues(struct ice_vsi *vsi)
 {
 	struct net_device *netdev = vsi->netdev;
-	int q_idx;
+	int q_idx, v_idx;
 
 	if (!netdev)
 		return;
 
+	/* Clear the NAPI's interrupt number */
+	ice_for_each_q_vector(vsi, v_idx) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
+
+		netif_napi_set_irq(&q_vector->napi, -1);
+	}
+
 	ice_for_each_txq(vsi, q_idx)
 		netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX, NULL);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index b084839eb811..eff4afabeef6 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2528,34 +2528,6 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset)
 }
 
 /**
- * ice_irq_affinity_notify - Callback for affinity changes
- * @notify: context as to what irq was changed
- * @mask: the new affinity mask
- *
- * This is a callback function used by the irq_set_affinity_notifier function
- * so that we may register to receive changes to the irq affinity masks.
- */
-static void
-ice_irq_affinity_notify(struct irq_affinity_notify *notify,
-			const cpumask_t *mask)
-{
-	struct ice_q_vector *q_vector =
-		container_of(notify, struct ice_q_vector, affinity_notify);
-
-	cpumask_copy(&q_vector->affinity_mask, mask);
-}
-
-/**
- * ice_irq_affinity_release - Callback for affinity notifier release
- * @ref: internal core kernel usage
- *
- * This is a callback function used by the irq_set_affinity_notifier function
- * to inform the current notification subscriber that they will no longer
- * receive notifications.
- */
-static void ice_irq_affinity_release(struct kref __always_unused *ref) {}
-
-/**
  * ice_vsi_ena_irq - Enable IRQ for the given VSI
  * @vsi: the VSI being configured
  */
@@ -2618,19 +2590,6 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
 				   err);
 			goto free_q_irqs;
 		}
-
-		/* register for affinity change notifications */
-		if (!IS_ENABLED(CONFIG_RFS_ACCEL)) {
-			struct irq_affinity_notify *affinity_notify;
-
-			affinity_notify = &q_vector->affinity_notify;
-			affinity_notify->notify = ice_irq_affinity_notify;
-			affinity_notify->release = ice_irq_affinity_release;
-			irq_set_affinity_notifier(irq_num, affinity_notify);
-		}
-
-		/* assign the mask for this irq */
-		irq_update_affinity_hint(irq_num, &q_vector->affinity_mask);
 	}
 
 	err = ice_set_cpu_rx_rmap(vsi);
@@ -2646,9 +2605,6 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
 free_q_irqs:
 	while (vector--) {
 		irq_num = vsi->q_vectors[vector]->irq.virq;
-		if (!IS_ENABLED(CONFIG_RFS_ACCEL))
-			irq_set_affinity_notifier(irq_num, NULL);
-		irq_update_affinity_hint(irq_num, NULL);
 		devm_free_irq(dev, irq_num, &vsi->q_vectors[vector]);
 	}
 	return err;
@@ -3675,6 +3631,9 @@ void ice_set_netdev_features(struct net_device *netdev)
 	 */
 	netdev->hw_features |= NETIF_F_RXFCS;
 
+	/* Allow core to manage IRQs affinity */
+	netif_set_affinity_auto(netdev);
+
 	netif_set_tso_max_size(netdev, ICE_MAX_TSO_SIZE);
 }
 
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index a3d6b8f198a8..f3aea7bcdaa3 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -814,6 +814,7 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
 	netdev->hw_features |= dflt_features | offloads;
 	netdev->hw_enc_features |= dflt_features | offloads;
 	idpf_set_ethtool_ops(netdev);
+	netif_set_affinity_auto(netdev);
 	SET_NETDEV_DEV(netdev, &adapter->pdev->dev);
 
 	/* carrier off on init to avoid Tx hangs */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 2747dc69999a..672dfad1fb21 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -3551,8 +3551,6 @@ void idpf_vport_intr_rel(struct idpf_vport *vport)
 		q_vector->tx = NULL;
 		kfree(q_vector->rx);
 		q_vector->rx = NULL;
-
-		free_cpumask_var(q_vector->affinity_mask);
 	}
 
 	kfree(vport->q_vectors);
@@ -3579,8 +3577,6 @@ static void idpf_vport_intr_rel_irq(struct idpf_vport *vport)
 		vidx = vport->q_vector_idxs[vector];
 		irq_num = adapter->msix_entries[vidx].vector;
 
-		/* clear the affinity_mask in the IRQ descriptor */
-		irq_set_affinity_hint(irq_num, NULL);
 		kfree(free_irq(irq_num, q_vector));
 	}
 }
@@ -3768,8 +3764,6 @@ static int idpf_vport_intr_req_irq(struct idpf_vport *vport)
 				   "Request_irq failed, error: %d\n", err);
 			goto free_q_irqs;
 		}
-		/* assign the mask for this irq */
-		irq_set_affinity_hint(irq_num, q_vector->affinity_mask);
 	}
 
 	return 0;
@@ -4181,7 +4175,8 @@ static int idpf_vport_intr_init_vec_idx(struct idpf_vport *vport)
 static void idpf_vport_intr_napi_add_all(struct idpf_vport *vport)
 {
 	int (*napi_poll)(struct napi_struct *napi, int budget);
-	u16 v_idx;
+	u16 v_idx, qv_idx;
+	int irq_num;
 
 	if (idpf_is_queue_model_split(vport->txq_model))
 		napi_poll = idpf_vport_splitq_napi_poll;
@@ -4190,12 +4185,12 @@ static void idpf_vport_intr_napi_add_all(struct idpf_vport *vport)
 
 	for (v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) {
 		struct idpf_q_vector *q_vector = &vport->q_vectors[v_idx];
+		qv_idx = vport->q_vector_idxs[v_idx];
+		irq_num = vport->adapter->msix_entries[qv_idx].vector;
 
-		netif_napi_add(vport->netdev, &q_vector->napi, napi_poll);
-
-		/* only set affinity_mask if the CPU is online */
-		if (cpu_online(v_idx))
-			cpumask_set_cpu(v_idx, q_vector->affinity_mask);
+		netif_napi_add_config(vport->netdev, &q_vector->napi,
+				      napi_poll, v_idx);
+		netif_napi_set_irq(&q_vector->napi, irq_num);
 	}
 }
 
@@ -4239,9 +4234,6 @@ int idpf_vport_intr_alloc(struct idpf_vport *vport)
 		q_vector->rx_intr_mode = IDPF_ITR_DYNAMIC;
 		q_vector->rx_itr_idx = VIRTCHNL2_ITR_IDX_0;
 
-		if (!zalloc_cpumask_var(&q_vector->affinity_mask, GFP_KERNEL))
-			goto error;
-
 		q_vector->tx = kcalloc(txqs_per_vector, sizeof(*q_vector->tx),
 				       GFP_KERNEL);
 		if (!q_vector->tx)
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index cd9a20c9cc7f..b029f566e57c 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -382,7 +382,6 @@ struct idpf_intr_reg {
  * @rx_intr_mode: Dynamic ITR or not
  * @rx_itr_idx: RX ITR index
  * @v_idx: Vector index
- * @affinity_mask: CPU affinity mask
  */
 struct idpf_q_vector {
 	__cacheline_group_begin_aligned(read_mostly);
@@ -419,13 +418,12 @@ struct idpf_q_vector {
 	__cacheline_group_begin_aligned(cold);
 	u16 v_idx;
 
-	cpumask_var_t affinity_mask;
 	__cacheline_group_end_aligned(cold);
 };
 libeth_cacheline_set_assert(struct idpf_q_vector, 120,
 			    24 + sizeof(struct napi_struct) +
 			    2 * sizeof(struct dim),
-			    8 + sizeof(cpumask_var_t));
+			    8);
 
 struct idpf_rx_queue_stats {
 	u64_stats_t packets;
@@ -921,7 +919,7 @@ static inline int idpf_q_vector_to_mem(const struct idpf_q_vector *q_vector)
 	if (!q_vector)
 		return NUMA_NO_NODE;
 
-	cpu = cpumask_first(q_vector->affinity_mask);
+	cpu = cpumask_first(&q_vector->napi.config->affinity_mask);
 
 	return cpu < nr_cpu_ids ? cpu_to_mem(cpu) : NUMA_NO_NODE;
 }
diff --git a/include/linux/cpu_rmap.h b/include/linux/cpu_rmap.h
index 20b5729903d7..2fd7ba75362a 100644
--- a/include/linux/cpu_rmap.h
+++ b/include/linux/cpu_rmap.h
@@ -32,6 +32,7 @@ struct cpu_rmap {
 #define CPU_RMAP_DIST_INF 0xffff
 
 extern struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags);
+extern void cpu_rmap_get(struct cpu_rmap *rmap);
 extern int cpu_rmap_put(struct cpu_rmap *rmap);
 
 extern int cpu_rmap_add(struct cpu_rmap *rmap, void *obj);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9a387d456592..2094d3edda73 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -352,6 +352,7 @@ struct napi_config {
 	u64 gro_flush_timeout;
 	u64 irq_suspend_timeout;
 	u32 defer_hard_irqs;
+	cpumask_t affinity_mask;
 	unsigned int napi_id;
 };
 
@@ -394,6 +395,8 @@ struct napi_struct {
 	struct list_head	dev_list;
 	struct hlist_node	napi_hash_node;
 	int			irq;
+	struct irq_affinity_notify notify;
+	int			napi_rmap_idx;
 	int			index;
 	struct napi_config	*config;
 };
@@ -409,6 +412,7 @@ enum {
 	NAPI_STATE_PREFER_BUSY_POLL,	/* prefer busy-polling over softirq processing*/
 	NAPI_STATE_THREADED,		/* The poll is performed inside its own thread*/
 	NAPI_STATE_SCHED_THREADED,	/* Napi is currently scheduled in threaded mode */
+	NAPI_STATE_HAS_NOTIFIER,	/* Napi has an IRQ notifier */
 };
 
 enum {
@@ -422,6 +426,7 @@ enum {
 	NAPIF_STATE_PREFER_BUSY_POLL	= BIT(NAPI_STATE_PREFER_BUSY_POLL),
 	NAPIF_STATE_THREADED		= BIT(NAPI_STATE_THREADED),
 	NAPIF_STATE_SCHED_THREADED	= BIT(NAPI_STATE_SCHED_THREADED),
+	NAPIF_STATE_HAS_NOTIFIER	= BIT(NAPI_STATE_HAS_NOTIFIER),
 };
 
 enum gro_result {
@@ -1989,6 +1994,15 @@ enum netdev_reg_state {
  *
  *	@threaded:	napi threaded mode is enabled
  *
+ *	@irq_affinity_auto: driver wants the core to store and re-assign the IRQ
+ *			    affinity. Set by netif_enable_irq_affinity(), then
+ *			    the driver must create a persistent napi by
+ *			    netif_napi_add_config() and finally bind the napi to
+ *			    IRQ (via netif_napi_set_irq()).
+ *
+ *	@rx_cpu_rmap_auto: driver wants the core to manage the ARFS rmap.
+ *	                   Set by calling netif_enable_cpu_rmap().
+ *
  *	@see_all_hwtstamp_requests: device wants to see calls to
  *			ndo_hwtstamp_set() for all timestamp requests
  *			regardless of source, even if those aren't
@@ -2396,6 +2410,8 @@ struct net_device {
 	struct lock_class_key	*qdisc_tx_busylock;
 	bool			proto_down;
 	bool			threaded;
+	bool			irq_affinity_auto;
+	bool			rx_cpu_rmap_auto;
 
 	/* priv_flags_slow, ungrouped to save space */
 	unsigned long		see_all_hwtstamp_requests:1;
@@ -2724,10 +2740,7 @@ static inline void netdev_assert_locked_or_invisible(struct net_device *dev)
 		netdev_assert_locked(dev);
 }
 
-static inline void netif_napi_set_irq_locked(struct napi_struct *napi, int irq)
-{
-	napi->irq = irq;
-}
+void netif_napi_set_irq_locked(struct napi_struct *napi, int irq);
 
 static inline void netif_napi_set_irq(struct napi_struct *napi, int irq)
 {
@@ -2865,6 +2878,9 @@ static inline void netif_napi_del(struct napi_struct *napi)
 	synchronize_net();
 }
 
+int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs);
+void netif_set_affinity_auto(struct net_device *dev);
+
 struct packet_type {
 	__be16			type;	/* This is really htons(ether_type). */
 	bool			ignore_outgoing;
diff --git a/lib/cpu_rmap.c b/lib/cpu_rmap.c
index 4c348670da31..f03d9be3f06b 100644
--- a/lib/cpu_rmap.c
+++ b/lib/cpu_rmap.c
@@ -73,7 +73,7 @@ static void cpu_rmap_release(struct kref *ref)
  * cpu_rmap_get - internal helper to get new ref on a cpu_rmap
  * @rmap: reverse-map allocated with alloc_cpu_rmap()
  */
-static inline void cpu_rmap_get(struct cpu_rmap *rmap)
+void cpu_rmap_get(struct cpu_rmap *rmap)
 {
 	kref_get(&rmap->refcount);
 }
diff --git a/net/core/dev.c b/net/core/dev.c
index 3f525278a871..b0ab0169f507 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6943,11 +6943,175 @@ void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index,
 }
 EXPORT_SYMBOL(netif_queue_set_napi);
 
+static void
+netif_napi_irq_notify(struct irq_affinity_notify *notify,
+		      const cpumask_t *mask)
+{
+	struct napi_struct *napi =
+		container_of(notify, struct napi_struct, notify);
+#ifdef CONFIG_RFS_ACCEL
+	struct cpu_rmap *rmap = napi->dev->rx_cpu_rmap;
+	int err;
+#endif
+
+	if (napi->config && napi->dev->irq_affinity_auto)
+		cpumask_copy(&napi->config->affinity_mask, mask);
+
+#ifdef CONFIG_RFS_ACCEL
+	if (napi->dev->rx_cpu_rmap_auto) {
+		err = cpu_rmap_update(rmap, napi->napi_rmap_idx, mask);
+		if (err)
+			netdev_warn(napi->dev, "RMAP update failed (%d)\n",
+				    err);
+	}
+#endif
+}
+
+#ifdef CONFIG_RFS_ACCEL
+static void netif_napi_affinity_release(struct kref *ref)
+{
+	struct napi_struct *napi =
+		container_of(ref, struct napi_struct, notify.kref);
+	struct cpu_rmap *rmap = napi->dev->rx_cpu_rmap;
+
+	netdev_assert_locked(napi->dev);
+	WARN_ON(test_and_clear_bit(NAPI_STATE_HAS_NOTIFIER,
+				   &napi->state));
+
+	if (!napi->dev->rx_cpu_rmap_auto)
+		return;
+	rmap->obj[napi->napi_rmap_idx] = NULL;
+	napi->napi_rmap_idx = -1;
+	cpu_rmap_put(rmap);
+}
+
+int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs)
+{
+	if (dev->rx_cpu_rmap_auto)
+		return 0;
+
+	dev->rx_cpu_rmap = alloc_irq_cpu_rmap(num_irqs);
+	if (!dev->rx_cpu_rmap)
+		return -ENOMEM;
+
+	dev->rx_cpu_rmap_auto = true;
+	return 0;
+}
+EXPORT_SYMBOL(netif_enable_cpu_rmap);
+
+static void netif_del_cpu_rmap(struct net_device *dev)
+{
+	struct cpu_rmap *rmap = dev->rx_cpu_rmap;
+
+	if (!dev->rx_cpu_rmap_auto)
+		return;
+
+	/* Free the rmap */
+	cpu_rmap_put(rmap);
+	dev->rx_cpu_rmap = NULL;
+	dev->rx_cpu_rmap_auto = false;
+}
+
+#else
+static void netif_napi_affinity_release(struct kref *ref)
+{
+}
+
+int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs)
+{
+	return 0;
+}
+EXPORT_SYMBOL(netif_enable_cpu_rmap);
+
+static void netif_del_cpu_rmap(struct net_device *dev)
+{
+}
+#endif
+
+void netif_set_affinity_auto(struct net_device *dev)
+{
+	unsigned int i, maxqs, numa;
+
+	maxqs = max(dev->num_tx_queues, dev->num_rx_queues);
+	numa = dev_to_node(&dev->dev);
+
+	for (i = 0; i < maxqs; i++)
+		cpumask_set_cpu(cpumask_local_spread(i, numa),
+				&dev->napi_config[i].affinity_mask);
+
+	dev->irq_affinity_auto = true;
+}
+EXPORT_SYMBOL(netif_set_affinity_auto);
+
+void netif_napi_set_irq_locked(struct napi_struct *napi, int irq)
+{
+	int rc;
+
+	netdev_assert_locked_or_invisible(napi->dev);
+
+	if (napi->irq == irq)
+		return;
+
+	/* Remove existing resources */
+	if (test_and_clear_bit(NAPI_STATE_HAS_NOTIFIER, &napi->state))
+		irq_set_affinity_notifier(napi->irq, NULL);
+
+	napi->irq = irq;
+	if (irq < 0 ||
+	    (!napi->dev->rx_cpu_rmap_auto && !napi->dev->irq_affinity_auto))
+		return;
+
+	/* Abort for buggy drivers */
+	if (napi->dev->irq_affinity_auto && WARN_ON_ONCE(!napi->config))
+		return;
+
+#ifdef CONFIG_RFS_ACCEL
+	if (napi->dev->rx_cpu_rmap_auto) {
+		rc = cpu_rmap_add(napi->dev->rx_cpu_rmap, napi);
+		if (rc < 0)
+			return;
+
+		cpu_rmap_get(napi->dev->rx_cpu_rmap);
+		napi->napi_rmap_idx = rc;
+	}
+#endif
+
+	/* Use core IRQ notifier */
+	napi->notify.notify = netif_napi_irq_notify;
+	napi->notify.release = netif_napi_affinity_release;
+	rc = irq_set_affinity_notifier(irq, &napi->notify);
+	if (rc) {
+		netdev_warn(napi->dev, "Unable to set IRQ notifier (%d)\n",
+			    rc);
+		goto put_rmap;
+	}
+
+	set_bit(NAPI_STATE_HAS_NOTIFIER, &napi->state);
+	return;
+
+put_rmap:
+#ifdef CONFIG_RFS_ACCEL
+	if (napi->dev->rx_cpu_rmap_auto) {
+		cpu_rmap_put(napi->dev->rx_cpu_rmap);
+		napi->dev->rx_cpu_rmap->obj[napi->napi_rmap_idx] = NULL;
+		napi->napi_rmap_idx = -1;
+	}
+#endif
+	napi->notify.notify = NULL;
+	napi->notify.release = NULL;
+}
+EXPORT_SYMBOL(netif_napi_set_irq_locked);
+
 static void napi_restore_config(struct napi_struct *n)
 {
 	n->defer_hard_irqs = n->config->defer_hard_irqs;
 	n->gro_flush_timeout = n->config->gro_flush_timeout;
 	n->irq_suspend_timeout = n->config->irq_suspend_timeout;
+
+	if (n->dev->irq_affinity_auto &&
+	    test_bit(NAPI_STATE_HAS_NOTIFIER, &n->state))
+		irq_set_affinity(n->irq, &n->config->affinity_mask);
+
 	/* a NAPI ID might be stored in the config, if so use it. if not, use
 	 * napi_hash_add to generate one for us.
 	 */
@@ -7168,6 +7332,9 @@ void __netif_napi_del_locked(struct napi_struct *napi)
 	/* Make sure NAPI is disabled (or was never enabled). */
 	WARN_ON(!test_bit(NAPI_STATE_SCHED, &napi->state));
 
+	if (test_and_clear_bit(NAPI_STATE_HAS_NOTIFIER, &napi->state))
+		irq_set_affinity_notifier(napi->irq, NULL);
+
 	if (napi->config) {
 		napi->index = -1;
 		napi->config = NULL;
@@ -11720,6 +11887,8 @@ void free_netdev(struct net_device *dev)
 
 	netdev_napi_exit(dev);
 
+	netif_del_cpu_rmap(dev);
+
 	ref_tracker_dir_exit(&dev->refcnt_tracker);
 #ifdef CONFIG_PCPU_DEV_REFCNT
 	free_percpu(dev->pcpu_refcnt);
diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile
index b2be14d0cc56..cde5814ff9a7 100644
--- a/tools/testing/selftests/drivers/net/hw/Makefile
+++ b/tools/testing/selftests/drivers/net/hw/Makefile
@@ -10,6 +10,7 @@ TEST_PROGS = \
 	ethtool_rmon.sh \
 	hw_stats_l3.sh \
 	hw_stats_l3_gre.sh \
+	irq.py \
 	loopback.sh \
 	nic_link_layer.py \
 	nic_performance.py \
@@ -34,9 +35,12 @@ TEST_INCLUDES := \
 # YNL files, must be before "include ..lib.mk"
 YNL_GEN_FILES := ncdevmem
 TEST_GEN_FILES += $(YNL_GEN_FILES)
+TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c))
 
 include ../../../lib.mk
 
 # YNL build
 YNL_GENS := ethtool netdev
 include ../../../net/ynl.mk
+
+include ../../../net/bpf.mk
diff --git a/tools/testing/selftests/drivers/net/hw/irq.py b/tools/testing/selftests/drivers/net/hw/irq.py
new file mode 100755
index 000000000000..42ab98370245
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/irq.py
@@ -0,0 +1,99 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+from lib.py import ksft_run, ksft_exit
+from lib.py import ksft_ge, ksft_eq
+from lib.py import KsftSkipEx
+from lib.py import ksft_disruptive
+from lib.py import EthtoolFamily, NetdevFamily
+from lib.py import NetDrvEnv
+from lib.py import cmd, ip, defer
+
+
+def read_affinity(irq) -> str:
+    with open(f'/proc/irq/{irq}/smp_affinity', 'r') as fp:
+        return fp.read().lstrip("0,").strip()
+
+
+def write_affinity(irq, what) -> str:
+    if what != read_affinity(irq):
+        with open(f'/proc/irq/{irq}/smp_affinity', 'w') as fp:
+            fp.write(what)
+
+
+def check_irqs_reported(cfg) -> None:
+    """ Check that device reports IRQs for NAPI instances """
+    napis = cfg.netnl.napi_get({"ifindex": cfg.ifindex}, dump=True)
+    irqs = sum(['irq' in x for x in napis])
+
+    ksft_ge(irqs, 1)
+    ksft_eq(irqs, len(napis))
+
+
+def _check_reconfig(cfg, reconfig_cb) -> None:
+    napis = cfg.netnl.napi_get({"ifindex": cfg.ifindex}, dump=True)
+    for n in reversed(napis):
+        if 'irq' in n:
+            break
+    else:
+        raise KsftSkipEx(f"Device has no NAPI with IRQ attribute (#napis: {len(napis)}")
+
+    old = read_affinity(n['irq'])
+    # pick an affinity that's not the current one
+    new = "3" if old != "3" else "5"
+    write_affinity(n['irq'], new)
+    defer(write_affinity, n['irq'], old)
+
+    reconfig_cb(cfg)
+
+    ksft_eq(read_affinity(n['irq']), new, comment="IRQ affinity changed after reconfig")
+
+
+def check_reconfig_queues(cfg) -> None:
+    def reconfig(cfg) -> None:
+        channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}})
+        if channels['combined-count'] == 0:
+            rx_type = 'rx'
+        else:
+            rx_type = 'combined'
+        cur_queue_cnt = channels[f'{rx_type}-count']
+        max_queue_cnt = channels[f'{rx_type}-max']
+
+        cmd(f"ethtool -L {cfg.ifname} {rx_type} 1")
+        cmd(f"ethtool -L {cfg.ifname} {rx_type} {max_queue_cnt}")
+        cmd(f"ethtool -L {cfg.ifname} {rx_type} {cur_queue_cnt}")
+
+    _check_reconfig(cfg, reconfig)
+
+
+def check_reconfig_xdp(cfg) -> None:
+    def reconfig(cfg) -> None:
+        ip(f"link set dev %s xdp obj %s sec xdp" %
+            (cfg.ifname, cfg.rpath("xdp_dummy.bpf.o")))
+        ip(f"link set dev %s xdp off" % cfg.ifname)
+
+    _check_reconfig(cfg, reconfig)
+
+
+@ksft_disruptive
+def check_down(cfg) -> None:
+    def reconfig(cfg) -> None:
+        ip("link set dev %s down" % cfg.ifname)
+        ip("link set dev %s up" % cfg.ifname)
+
+    _check_reconfig(cfg, reconfig)
+
+
+def main() -> None:
+    with NetDrvEnv(__file__, nsim_test=False) as cfg:
+        cfg.ethnl = EthtoolFamily()
+        cfg.netnl = NetdevFamily()
+
+        ksft_run([check_irqs_reported, check_reconfig_queues,
+                  check_reconfig_xdp, check_down],
+                 args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/hw/xdp_dummy.bpf.c b/tools/testing/selftests/drivers/net/hw/xdp_dummy.bpf.c
new file mode 100644
index 000000000000..d988b2e0cee8
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/xdp_dummy.bpf.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define KBUILD_MODNAME "xdp_dummy"
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+SEC("xdp")
+int xdp_dummy_prog(struct xdp_md *ctx)
+{
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py
index 96b33b5ef9dd..fd4d674e6c72 100644
--- a/tools/testing/selftests/drivers/net/lib/py/env.py
+++ b/tools/testing/selftests/drivers/net/lib/py/env.py
@@ -58,14 +58,20 @@ class NetDrvEnv(NetDrvEnvBase):
     """
     Class for a single NIC / host env, with no remote end
     """
-    def __init__(self, src_path, **kwargs):
+    def __init__(self, src_path, nsim_test=None, **kwargs):
         super().__init__(src_path)
 
         self._ns = None
 
         if 'NETIF' in self.env:
+            if nsim_test is True:
+                raise KsftXfailEx("Test only works on netdevsim")
+
             self.dev = ip("-d link show dev " + self.env['NETIF'], json=True)[0]
         else:
+            if nsim_test is False:
+                raise KsftXfailEx("Test does not work on netdevsim")
+
             self._ns = NetdevSimDev(**kwargs)
             self.dev = self._ns.nsims[0].dev
         self.ifname = self.dev['ifname']