Merge tag 'v6.11' into for-6.12/block

Merge in 6.11 final to get the fix for preventing deadlocks on an
elevator switch, as there's a fixup for that patch.

* tag 'v6.11': (1788 commits)
  Linux 6.11
  Revert "KVM: VMX: Always honor guest PAT on CPUs that support self-snoop"
  pinctrl: pinctrl-cy8c95x0: Fix regcache
  cifs: Fix signature miscalculation
  mm: avoid leaving partial pfn mappings around in error case
  drm/xe/client: add missing bo locking in show_meminfo()
  drm/xe/client: fix deadlock in show_meminfo()
  drm/xe/oa: Enable Xe2+ PES disaggregation
  drm/xe/display: fix compat IS_DISPLAY_STEP() range end
  drm/xe: Fix access_ok check in user_fence_create
  drm/xe: Fix possible UAF in guc_exec_queue_process_msg
  drm/xe: Remove fence check from send_tlb_invalidation
  drm/xe/gt: Remove double include
  net: netfilter: move nf flowtable bpf initialization in nf_flow_table_module_init()
  PCI: Fix potential deadlock in pcim_intx()
  workqueue: Clear worker->pool in the worker thread context
  net: tighten bad gso csum offset check in virtio_net_hdr
  netlink: specs: mptcp: fix port endianness
  net: dpaa: Pad packets to ETH_ZLEN
  mptcp: pm: Fix uaf in __timer_delete_sync
  ...

12 files changed, 292 insertions, 310 deletions

diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
index 00fed5a61d62..62ef8e2fb5f1 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
@@ -337,7 +337,7 @@ int ice_devlink_create_pf_port(struct ice_pf *pf)
 		return -EIO;
 
 	attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
-	attrs.phys.port_number = pf->hw.bus.func;
+	attrs.phys.port_number = pf->hw.pf_id;
 
 	/* As FW supports only port split options for whole device,
 	 * set port split options only for first PF.
@@ -455,7 +455,7 @@ int ice_devlink_create_vf_port(struct ice_vf *vf)
 		return -EINVAL;
 
 	attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_VF;
-	attrs.pci_vf.pf = pf->hw.bus.func;
+	attrs.pci_vf.pf = pf->hw.pf_id;
 	attrs.pci_vf.vf = vf->vf_id;
 
 	ice_devlink_set_switch_id(pf, &attrs.switch_id);
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 99a75a59078e..ce8b5505b16d 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -318,6 +318,7 @@ enum ice_vsi_state {
 	ICE_VSI_UMAC_FLTR_CHANGED,
 	ICE_VSI_MMAC_FLTR_CHANGED,
 	ICE_VSI_PROMISC_CHANGED,
+	ICE_VSI_REBUILD_PENDING,
 	ICE_VSI_STATE_NBITS		/* must be last */
 };
 
@@ -411,6 +412,7 @@ struct ice_vsi {
 	struct ice_tx_ring **xdp_rings;	 /* XDP ring array */
 	u16 num_xdp_txq;		 /* Used XDP queues */
 	u8 xdp_mapping_mode;		 /* ICE_MAP_MODE_[CONTIG|SCATTER] */
+	struct mutex xdp_state_lock;
 
 	struct net_device **target_netdevs;
 
@@ -765,18 +767,17 @@ static inline struct xsk_buff_pool *ice_get_xp_from_qid(struct ice_vsi *vsi,
 }
 
 /**
- * ice_xsk_pool - get XSK buffer pool bound to a ring
+ * ice_rx_xsk_pool - assign XSK buff pool to Rx ring
  * @ring: Rx ring to use
  *
- * Returns a pointer to xsk_buff_pool structure if there is a buffer pool
- * present, NULL otherwise.
+ * Sets XSK buff pool pointer on Rx ring.
  */
-static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring)
+static inline void ice_rx_xsk_pool(struct ice_rx_ring *ring)
 {
 	struct ice_vsi *vsi = ring->vsi;
 	u16 qid = ring->q_index;
 
-	return ice_get_xp_from_qid(vsi, qid);
+	WRITE_ONCE(ring->xsk_pool, ice_get_xp_from_qid(vsi, qid));
 }
 
 /**
@@ -801,7 +802,7 @@ static inline void ice_tx_xsk_pool(struct ice_vsi *vsi, u16 qid)
 	if (!ring)
 		return;
 
-	ring->xsk_pool = ice_get_xp_from_qid(vsi, qid);
+	WRITE_ONCE(ring->xsk_pool, ice_get_xp_from_qid(vsi, qid));
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 5d396c1a7731..c158749a80e0 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -190,16 +190,11 @@ static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx)
 	}
 	q_vector = vsi->q_vectors[v_idx];
 
-	ice_for_each_tx_ring(tx_ring, q_vector->tx) {
-		ice_queue_set_napi(vsi, tx_ring->q_index, NETDEV_QUEUE_TYPE_TX,
-				   NULL);
+	ice_for_each_tx_ring(tx_ring, vsi->q_vectors[v_idx]->tx)
 		tx_ring->q_vector = NULL;
-	}
-	ice_for_each_rx_ring(rx_ring, q_vector->rx) {
-		ice_queue_set_napi(vsi, rx_ring->q_index, NETDEV_QUEUE_TYPE_RX,
-				   NULL);
+
+	ice_for_each_rx_ring(rx_ring, vsi->q_vectors[v_idx]->rx)
 		rx_ring->q_vector = NULL;
-	}
 
 	/* only VSI with an associated netdev is set up with NAPI */
 	if (vsi->netdev)
@@ -513,6 +508,25 @@ static void ice_xsk_pool_fill_cb(struct ice_rx_ring *ring)
 }
 
 /**
+ * ice_get_frame_sz - calculate xdp_buff::frame_sz
+ * @rx_ring: the ring being configured
+ *
+ * Return frame size based on underlying PAGE_SIZE
+ */
+static unsigned int ice_get_frame_sz(struct ice_rx_ring *rx_ring)
+{
+	unsigned int frame_sz;
+
+#if (PAGE_SIZE >= 8192)
+	frame_sz = rx_ring->rx_buf_len;
+#else
+	frame_sz = ice_rx_pg_size(rx_ring) / 2;
+#endif
+
+	return frame_sz;
+}
+
+/**
  * ice_vsi_cfg_rxq - Configure an Rx queue
  * @ring: the ring being configured
  *
@@ -536,7 +550,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 				return err;
 		}
 
-		ring->xsk_pool = ice_xsk_pool(ring);
+		ice_rx_xsk_pool(ring);
 		if (ring->xsk_pool) {
 			xdp_rxq_info_unreg(&ring->xdp_rxq);
 
@@ -576,7 +590,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 		}
 	}
 
-	xdp_init_buff(&ring->xdp, ice_rx_pg_size(ring) / 2, &ring->xdp_rxq);
+	xdp_init_buff(&ring->xdp, ice_get_frame_sz(ring), &ring->xdp_rxq);
 	ring->xdp.data = NULL;
 	ring->xdp_ext.pkt_ctx = &ring->pkt_ctx;
 	err = ice_setup_rx_ctx(ring);
@@ -597,7 +611,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 			return 0;
 		}
 
-		ok = ice_alloc_rx_bufs_zc(ring, num_bufs);
+		ok = ice_alloc_rx_bufs_zc(ring, ring->xsk_pool, num_bufs);
 		if (!ok) {
 			u16 pf_q = ring->vsi->rxq_map[ring->q_index];
 
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 8c990c976132..bc79ba974e49 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -4673,10 +4673,10 @@ static int ice_get_port_fec_stats(struct ice_hw *hw, u16 pcs_quad, u16 pcs_port,
 	if (err)
 		return err;
 
-	fec_stats->uncorrectable_blocks.total = (fec_corr_high_val << 16) +
-						 fec_corr_low_val;
-	fec_stats->corrected_blocks.total = (fec_uncorr_high_val << 16) +
-					     fec_uncorr_low_val;
+	fec_stats->corrected_blocks.total = (fec_corr_high_val << 16) +
+					     fec_corr_low_val;
+	fec_stats->uncorrectable_blocks.total = (fec_uncorr_high_val << 16) +
+						 fec_uncorr_low_val;
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index f559e60992fa..2405e5ed9128 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -447,6 +447,7 @@ static void ice_vsi_free(struct ice_vsi *vsi)
 
 	ice_vsi_free_stats(vsi);
 	ice_vsi_free_arrays(vsi);
+	mutex_destroy(&vsi->xdp_state_lock);
 	mutex_unlock(&pf->sw_mutex);
 	devm_kfree(dev, vsi);
 }
@@ -626,6 +627,8 @@ static struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf)
 	pf->next_vsi = ice_get_free_slot(pf->vsi, pf->num_alloc_vsi,
 					 pf->next_vsi);
 
+	mutex_init(&vsi->xdp_state_lock);
+
 unlock_pf:
 	mutex_unlock(&pf->sw_mutex);
 	return vsi;
@@ -2286,9 +2289,6 @@ static int ice_vsi_cfg_def(struct ice_vsi *vsi)
 
 		ice_vsi_map_rings_to_vectors(vsi);
 
-		/* Associate q_vector rings to napi */
-		ice_vsi_set_napi_queues(vsi);
-
 		vsi->stat_offsets_loaded = false;
 
 		/* ICE_VSI_CTRL does not need RSS so skip RSS processing */
@@ -2413,20 +2413,13 @@ void ice_vsi_decfg(struct ice_vsi *vsi)
 	struct ice_pf *pf = vsi->back;
 	int err;
 
-	/* The Rx rule will only exist to remove if the LLDP FW
-	 * engine is currently stopped
-	 */
-	if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF &&
-	    !test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags))
-		ice_cfg_sw_lldp(vsi, false, false);
-
 	ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx);
 	err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx);
 	if (err)
 		dev_err(ice_pf_to_dev(pf), "Failed to remove RDMA scheduler config for VSI %u, err %d\n",
 			vsi->vsi_num, err);
 
-	if (ice_is_xdp_ena_vsi(vsi))
+	if (vsi->xdp_rings)
 		/* return value check can be skipped here, it always returns
 		 * 0 if reset is in progress
 		 */
@@ -2528,7 +2521,7 @@ static void ice_vsi_release_msix(struct ice_vsi *vsi)
 		for (q = 0; q < q_vector->num_ring_tx; q++) {
 			ice_write_itr(&q_vector->tx, 0);
 			wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), 0);
-			if (ice_is_xdp_ena_vsi(vsi)) {
+			if (vsi->xdp_rings) {
 				u32 xdp_txq = txq + vsi->num_xdp_txq;
 
 				wr32(hw, QINT_TQCTL(vsi->txq_map[xdp_txq]), 0);
@@ -2628,6 +2621,7 @@ void ice_vsi_close(struct ice_vsi *vsi)
 	if (!test_and_set_bit(ICE_VSI_DOWN, vsi->state))
 		ice_down(vsi);
 
+	ice_vsi_clear_napi_queues(vsi);
 	ice_vsi_free_irq(vsi);
 	ice_vsi_free_tx_rings(vsi);
 	ice_vsi_free_rx_rings(vsi);
@@ -2671,8 +2665,7 @@ int ice_ena_vsi(struct ice_vsi *vsi, bool locked)
  */
 void ice_dis_vsi(struct ice_vsi *vsi, bool locked)
 {
-	if (test_bit(ICE_VSI_DOWN, vsi->state))
-		return;
+	bool already_down = test_bit(ICE_VSI_DOWN, vsi->state);
 
 	set_bit(ICE_VSI_NEEDS_RESTART, vsi->state);
 
@@ -2680,134 +2673,70 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked)
 		if (netif_running(vsi->netdev)) {
 			if (!locked)
 				rtnl_lock();
-
-			ice_vsi_close(vsi);
+			already_down = test_bit(ICE_VSI_DOWN, vsi->state);
+			if (!already_down)
+				ice_vsi_close(vsi);
 
 			if (!locked)
 				rtnl_unlock();
-		} else {
+		} else if (!already_down) {
 			ice_vsi_close(vsi);
 		}
-	} else if (vsi->type == ICE_VSI_CTRL) {
+	} else if (vsi->type == ICE_VSI_CTRL && !already_down) {
 		ice_vsi_close(vsi);
 	}
 }
 
 /**
- * __ice_queue_set_napi - Set the napi instance for the queue
- * @dev: device to which NAPI and queue belong
- * @queue_index: Index of queue
- * @type: queue type as RX or TX
- * @napi: NAPI context
- * @locked: is the rtnl_lock already held
- *
- * Set the napi instance for the queue. Caller indicates the lock status.
- */
-static void
-__ice_queue_set_napi(struct net_device *dev, unsigned int queue_index,
-		     enum netdev_queue_type type, struct napi_struct *napi,
-		     bool locked)
-{
-	if (!locked)
-		rtnl_lock();
-	netif_queue_set_napi(dev, queue_index, type, napi);
-	if (!locked)
-		rtnl_unlock();
-}
-
-/**
- * ice_queue_set_napi - Set the napi instance for the queue
- * @vsi: VSI being configured
- * @queue_index: Index of queue
- * @type: queue type as RX or TX
- * @napi: NAPI context
+ * ice_vsi_set_napi_queues - associate netdev queues with napi
+ * @vsi: VSI pointer
  *
- * Set the napi instance for the queue. The rtnl lock state is derived from the
- * execution path.
+ * Associate queue[s] with napi for all vectors.
+ * The caller must hold rtnl_lock.
  */
-void
-ice_queue_set_napi(struct ice_vsi *vsi, unsigned int queue_index,
-		   enum netdev_queue_type type, struct napi_struct *napi)
+void ice_vsi_set_napi_queues(struct ice_vsi *vsi)
 {
-	struct ice_pf *pf = vsi->back;
+	struct net_device *netdev = vsi->netdev;
+	int q_idx, v_idx;
 
-	if (!vsi->netdev)
+	if (!netdev)
 		return;
 
-	if (current_work() == &pf->serv_task ||
-	    test_bit(ICE_PREPARED_FOR_RESET, pf->state) ||
-	    test_bit(ICE_DOWN, pf->state) ||
-	    test_bit(ICE_SUSPENDED, pf->state))
-		__ice_queue_set_napi(vsi->netdev, queue_index, type, napi,
-				     false);
-	else
-		__ice_queue_set_napi(vsi->netdev, queue_index, type, napi,
-				     true);
-}
-
-/**
- * __ice_q_vector_set_napi_queues - Map queue[s] associated with the napi
- * @q_vector: q_vector pointer
- * @locked: is the rtnl_lock already held
- *
- * Associate the q_vector napi with all the queue[s] on the vector.
- * Caller indicates the lock status.
- */
-void __ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked)
-{
-	struct ice_rx_ring *rx_ring;
-	struct ice_tx_ring *tx_ring;
-
-	ice_for_each_rx_ring(rx_ring, q_vector->rx)
-		__ice_queue_set_napi(q_vector->vsi->netdev, rx_ring->q_index,
-				     NETDEV_QUEUE_TYPE_RX, &q_vector->napi,
-				     locked);
+	ice_for_each_rxq(vsi, q_idx)
+		netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX,
+				     &vsi->rx_rings[q_idx]->q_vector->napi);
 
-	ice_for_each_tx_ring(tx_ring, q_vector->tx)
-		__ice_queue_set_napi(q_vector->vsi->netdev, tx_ring->q_index,
-				     NETDEV_QUEUE_TYPE_TX, &q_vector->napi,
-				     locked);
+	ice_for_each_txq(vsi, q_idx)
+		netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX,
+				     &vsi->tx_rings[q_idx]->q_vector->napi);
 	/* Also set the interrupt number for the NAPI */
-	netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq);
-}
-
-/**
- * ice_q_vector_set_napi_queues - Map queue[s] associated with the napi
- * @q_vector: q_vector pointer
- *
- * Associate the q_vector napi with all the queue[s] on the vector
- */
-void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector)
-{
-	struct ice_rx_ring *rx_ring;
-	struct ice_tx_ring *tx_ring;
-
-	ice_for_each_rx_ring(rx_ring, q_vector->rx)
-		ice_queue_set_napi(q_vector->vsi, rx_ring->q_index,
-				   NETDEV_QUEUE_TYPE_RX, &q_vector->napi);
+	ice_for_each_q_vector(vsi, v_idx) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
 
-	ice_for_each_tx_ring(tx_ring, q_vector->tx)
-		ice_queue_set_napi(q_vector->vsi, tx_ring->q_index,
-				   NETDEV_QUEUE_TYPE_TX, &q_vector->napi);
-	/* Also set the interrupt number for the NAPI */
-	netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq);
+		netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq);
+	}
 }
 
 /**
- * ice_vsi_set_napi_queues
+ * ice_vsi_clear_napi_queues - dissociate netdev queues from napi
  * @vsi: VSI pointer
  *
- * Associate queue[s] with napi for all vectors
+ * Clear the association between all VSI queues queue[s] and napi.
+ * The caller must hold rtnl_lock.
  */
-void ice_vsi_set_napi_queues(struct ice_vsi *vsi)
+void ice_vsi_clear_napi_queues(struct ice_vsi *vsi)
 {
-	int i;
+	struct net_device *netdev = vsi->netdev;
+	int q_idx;
 
-	if (!vsi->netdev)
+	if (!netdev)
 		return;
 
-	ice_for_each_q_vector(vsi, i)
-		ice_q_vector_set_napi_queues(vsi->q_vectors[i]);
+	ice_for_each_txq(vsi, q_idx)
+		netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX, NULL);
+
+	ice_for_each_rxq(vsi, q_idx)
+		netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX, NULL);
 }
 
 /**
@@ -2828,6 +2757,14 @@ int ice_vsi_release(struct ice_vsi *vsi)
 		ice_rss_clean(vsi);
 
 	ice_vsi_close(vsi);
+
+	/* The Rx rule will only exist to remove if the LLDP FW
+	 * engine is currently stopped
+	 */
+	if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF &&
+	    !test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags))
+		ice_cfg_sw_lldp(vsi, false, false);
+
 	ice_vsi_decfg(vsi);
 
 	/* retain SW VSI data structure since it is needed to unregister and
@@ -3039,19 +2976,23 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags)
 	if (WARN_ON(vsi->type == ICE_VSI_VF && !vsi->vf))
 		return -EINVAL;
 
+	mutex_lock(&vsi->xdp_state_lock);
+
 	ret = ice_vsi_realloc_stat_arrays(vsi);
 	if (ret)
-		goto err_vsi_cfg;
+		goto unlock;
 
 	ice_vsi_decfg(vsi);
 	ret = ice_vsi_cfg_def(vsi);
 	if (ret)
-		goto err_vsi_cfg;
+		goto unlock;
 
 	coalesce = kcalloc(vsi->num_q_vectors,
 			   sizeof(struct ice_coalesce_stored), GFP_KERNEL);
-	if (!coalesce)
-		return -ENOMEM;
+	if (!coalesce) {
+		ret = -ENOMEM;
+		goto decfg;
+	}
 
 	prev_num_q_vectors = ice_vsi_rebuild_get_coalesce(vsi, coalesce);
 
@@ -3059,22 +3000,23 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags)
 	if (ret) {
 		if (vsi_flags & ICE_VSI_FLAG_INIT) {
 			ret = -EIO;
-			goto err_vsi_cfg_tc_lan;
+			goto free_coalesce;
 		}
 
-		kfree(coalesce);
-		return ice_schedule_reset(pf, ICE_RESET_PFR);
+		ret = ice_schedule_reset(pf, ICE_RESET_PFR);
+		goto free_coalesce;
 	}
 
 	ice_vsi_rebuild_set_coalesce(vsi, coalesce, prev_num_q_vectors);
-	kfree(coalesce);
-
-	return 0;
+	clear_bit(ICE_VSI_REBUILD_PENDING, vsi->state);
 
-err_vsi_cfg_tc_lan:
-	ice_vsi_decfg(vsi);
+free_coalesce:
 	kfree(coalesce);
-err_vsi_cfg:
+decfg:
+	if (ret)
+		ice_vsi_decfg(vsi);
+unlock:
+	mutex_unlock(&vsi->xdp_state_lock);
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index 94ce8964dda6..36d86535695d 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -44,16 +44,10 @@ void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc);
 struct ice_vsi *
 ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params);
 
-void
-ice_queue_set_napi(struct ice_vsi *vsi, unsigned int queue_index,
-		   enum netdev_queue_type type, struct napi_struct *napi);
-
-void __ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked);
-
-void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector);
-
 void ice_vsi_set_napi_queues(struct ice_vsi *vsi);
 
+void ice_vsi_clear_napi_queues(struct ice_vsi *vsi);
+
 int ice_vsi_release(struct ice_vsi *vsi);
 
 void ice_vsi_close(struct ice_vsi *vsi);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index ec636be4d17d..ea780d468579 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -559,6 +559,8 @@ ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
 	if (test_bit(ICE_PREPARED_FOR_RESET, pf->state))
 		return;
 
+	synchronize_irq(pf->oicr_irq.virq);
+
 	ice_unplug_aux_dev(pf);
 
 	/* Notify VFs of impending reset */
@@ -606,11 +608,15 @@ ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
 			memset(&vsi->mqprio_qopt, 0, sizeof(vsi->mqprio_qopt));
 		}
 	}
+
+	if (vsi->netdev)
+		netif_device_detach(vsi->netdev);
 skip:
 
 	/* clear SW filtering DB */
 	ice_clear_hw_tbls(hw);
 	/* disable the VSIs and their queues that are not already DOWN */
+	set_bit(ICE_VSI_REBUILD_PENDING, ice_get_main_vsi(pf)->state);
 	ice_pf_dis_all_vsi(pf, false);
 
 	if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags))
@@ -2948,7 +2954,7 @@ static void ice_vsi_rx_napi_schedule(struct ice_vsi *vsi)
 	ice_for_each_rxq(vsi, i) {
 		struct ice_rx_ring *rx_ring = vsi->rx_rings[i];
 
-		if (rx_ring->xsk_pool)
+		if (READ_ONCE(rx_ring->xsk_pool))
 			napi_schedule(&rx_ring->q_vector->napi);
 	}
 }
@@ -2999,8 +3005,8 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
 		   struct netlink_ext_ack *extack)
 {
 	unsigned int frame_size = vsi->netdev->mtu + ICE_ETH_PKT_HDR_PAD;
-	bool if_running = netif_running(vsi->netdev);
 	int ret = 0, xdp_ring_err = 0;
+	bool if_running;
 
 	if (prog && !prog->aux->xdp_has_frags) {
 		if (frame_size > ice_max_xdp_frame_size(vsi)) {
@@ -3011,13 +3017,17 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
 	}
 
 	/* hot swap progs and avoid toggling link */
-	if (ice_is_xdp_ena_vsi(vsi) == !!prog) {
+	if (ice_is_xdp_ena_vsi(vsi) == !!prog ||
+	    test_bit(ICE_VSI_REBUILD_PENDING, vsi->state)) {
 		ice_vsi_assign_bpf_prog(vsi, prog);
 		return 0;
 	}
 
+	if_running = netif_running(vsi->netdev) &&
+		     !test_and_set_bit(ICE_VSI_DOWN, vsi->state);
+
 	/* need to stop netdev while setting up the program for Rx rings */
-	if (if_running && !test_and_set_bit(ICE_VSI_DOWN, vsi->state)) {
+	if (if_running) {
 		ret = ice_down(vsi);
 		if (ret) {
 			NL_SET_ERR_MSG_MOD(extack, "Preparing device for XDP attach failed");
@@ -3083,21 +3093,28 @@ static int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	struct ice_netdev_priv *np = netdev_priv(dev);
 	struct ice_vsi *vsi = np->vsi;
+	int ret;
 
 	if (vsi->type != ICE_VSI_PF) {
 		NL_SET_ERR_MSG_MOD(xdp->extack, "XDP can be loaded only on PF VSI");
 		return -EINVAL;
 	}
 
+	mutex_lock(&vsi->xdp_state_lock);
+
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
-		return ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack);
+		ret = ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack);
+		break;
 	case XDP_SETUP_XSK_POOL:
-		return ice_xsk_pool_setup(vsi, xdp->xsk.pool,
-					  xdp->xsk.queue_id);
+		ret = ice_xsk_pool_setup(vsi, xdp->xsk.pool, xdp->xsk.queue_id);
+		break;
 	default:
-		return -EINVAL;
+		ret = -EINVAL;
 	}
+
+	mutex_unlock(&vsi->xdp_state_lock);
+	return ret;
 }
 
 /**
@@ -3553,11 +3570,9 @@ static void ice_napi_add(struct ice_vsi *vsi)
 	if (!vsi->netdev)
 		return;
 
-	ice_for_each_q_vector(vsi, v_idx) {
+	ice_for_each_q_vector(vsi, v_idx)
 		netif_napi_add(vsi->netdev, &vsi->q_vectors[v_idx]->napi,
 			       ice_napi_poll);
-		__ice_q_vector_set_napi_queues(vsi->q_vectors[v_idx], false);
-	}
 }
 
 /**
@@ -5348,7 +5363,6 @@ err_load:
 	ice_deinit(pf);
 err_init:
 	ice_adapter_put(pdev);
-	pci_disable_device(pdev);
 	return err;
 }
 
@@ -5455,7 +5469,6 @@ static void ice_remove(struct pci_dev *pdev)
 	ice_set_wake(pf);
 
 	ice_adapter_put(pdev);
-	pci_disable_device(pdev);
 }
 
 /**
@@ -5535,7 +5548,9 @@ static int ice_reinit_interrupt_scheme(struct ice_pf *pf)
 		if (ret)
 			goto err_reinit;
 		ice_vsi_map_rings_to_vectors(pf->vsi[v]);
+		rtnl_lock();
 		ice_vsi_set_napi_queues(pf->vsi[v]);
+		rtnl_unlock();
 	}
 
 	ret = ice_req_irq_msix_misc(pf);
@@ -5549,8 +5564,12 @@ static int ice_reinit_interrupt_scheme(struct ice_pf *pf)
 
 err_reinit:
 	while (v--)
-		if (pf->vsi[v])
+		if (pf->vsi[v]) {
+			rtnl_lock();
+			ice_vsi_clear_napi_queues(pf->vsi[v]);
+			rtnl_unlock();
 			ice_vsi_free_q_vectors(pf->vsi[v]);
+		}
 
 	return ret;
 }
@@ -5615,6 +5634,9 @@ static int ice_suspend(struct device *dev)
 	ice_for_each_vsi(pf, v) {
 		if (!pf->vsi[v])
 			continue;
+		rtnl_lock();
+		ice_vsi_clear_napi_queues(pf->vsi[v]);
+		rtnl_unlock();
 		ice_vsi_free_q_vectors(pf->vsi[v]);
 	}
 	ice_clear_interrupt_scheme(pf);
@@ -7228,7 +7250,7 @@ int ice_down(struct ice_vsi *vsi)
 	if (tx_err)
 		netdev_err(vsi->netdev, "Failed stop Tx rings, VSI %d error %d\n",
 			   vsi->vsi_num, tx_err);
-	if (!tx_err && ice_is_xdp_ena_vsi(vsi)) {
+	if (!tx_err && vsi->xdp_rings) {
 		tx_err = ice_vsi_stop_xdp_tx_rings(vsi);
 		if (tx_err)
 			netdev_err(vsi->netdev, "Failed stop XDP rings, VSI %d error %d\n",
@@ -7245,7 +7267,7 @@ int ice_down(struct ice_vsi *vsi)
 	ice_for_each_txq(vsi, i)
 		ice_clean_tx_ring(vsi->tx_rings[i]);
 
-	if (ice_is_xdp_ena_vsi(vsi))
+	if (vsi->xdp_rings)
 		ice_for_each_xdp_txq(vsi, i)
 			ice_clean_tx_ring(vsi->xdp_rings[i]);
 
@@ -7450,6 +7472,8 @@ int ice_vsi_open(struct ice_vsi *vsi)
 		err = netif_set_real_num_rx_queues(vsi->netdev, vsi->num_rxq);
 		if (err)
 			goto err_set_qs;
+
+		ice_vsi_set_napi_queues(vsi);
 	}
 
 	err = ice_up_complete(vsi);
@@ -7587,6 +7611,7 @@ static void ice_update_pf_netdev_link(struct ice_pf *pf)
  */
 static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 {
+	struct ice_vsi *vsi = ice_get_main_vsi(pf);
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_hw *hw = &pf->hw;
 	bool dvm;
@@ -7729,6 +7754,9 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 		ice_rebuild_arfs(pf);
 	}
 
+	if (vsi && vsi->netdev)
+		netif_device_attach(vsi->netdev);
+
 	ice_update_pf_netdev_link(pf);
 
 	/* tell the firmware we are up */
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index e2786cc13286..ef2e858f49bb 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -1477,6 +1477,10 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup)
 	/* Update cached link status for this port immediately */
 	ptp_port->link_up = linkup;
 
+	/* Skip HW writes if reset is in progress */
+	if (pf->hw.reset_ongoing)
+		return;
+
 	switch (hw->ptp.phy_model) {
 	case ICE_PHY_E810:
 		/* Do not reconfigure E810 PHY */
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index fe8847184cb1..79d91e95358c 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -3194,7 +3194,7 @@ ice_add_update_vsi_list(struct ice_hw *hw,
 
 		/* A rule already exists with the new VSI being added */
 		if (test_bit(vsi_handle, m_entry->vsi_list_info->vsi_map))
-			return 0;
+			return -EEXIST;
 
 		/* Update the previously created VSI list set with
 		 * the new VSI ID passed in
@@ -3264,7 +3264,7 @@ ice_find_vsi_list_entry(struct ice_hw *hw, u8 recp_id, u16 vsi_handle,
 
 	list_head = &sw->recp_list[recp_id].filt_rules;
 	list_for_each_entry(list_itr, list_head, list_entry) {
-		if (list_itr->vsi_list_info) {
+		if (list_itr->vsi_count == 1 && list_itr->vsi_list_info) {
 			map_info = list_itr->vsi_list_info;
 			if (test_bit(vsi_handle, map_info->vsi_map)) {
 				*vsi_list_id = map_info->vsi_list_id;
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 8bb743f78fcb..c9bc3f1add5d 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -456,7 +456,7 @@ void ice_free_rx_ring(struct ice_rx_ring *rx_ring)
 	if (rx_ring->vsi->type == ICE_VSI_PF)
 		if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
 			xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
-	rx_ring->xdp_prog = NULL;
+	WRITE_ONCE(rx_ring->xdp_prog, NULL);
 	if (rx_ring->xsk_pool) {
 		kfree(rx_ring->xdp_buf);
 		rx_ring->xdp_buf = NULL;
@@ -522,30 +522,6 @@ err:
 }
 
 /**
- * ice_rx_frame_truesize
- * @rx_ring: ptr to Rx ring
- * @size: size
- *
- * calculate the truesize with taking into the account PAGE_SIZE of
- * underlying arch
- */
-static unsigned int
-ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, const unsigned int size)
-{
-	unsigned int truesize;
-
-#if (PAGE_SIZE < 8192)
-	truesize = ice_rx_pg_size(rx_ring) / 2; /* Must be power-of-2 */
-#else
-	truesize = rx_ring->rx_offset ?
-		SKB_DATA_ALIGN(rx_ring->rx_offset + size) +
-		SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) :
-		SKB_DATA_ALIGN(size);
-#endif
-	return truesize;
-}
-
-/**
  * ice_run_xdp - Executes an XDP program on initialized xdp_buff
  * @rx_ring: Rx ring
  * @xdp: xdp_buff used as input to the XDP program
@@ -837,16 +813,15 @@ ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf)
 	if (!dev_page_is_reusable(page))
 		return false;
 
-#if (PAGE_SIZE < 8192)
 	/* if we are only owner of page we can reuse it */
 	if (unlikely(rx_buf->pgcnt - pagecnt_bias > 1))
 		return false;
-#else
+#if (PAGE_SIZE >= 8192)
 #define ICE_LAST_OFFSET \
-	(SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_2048)
+	(SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_3072)
 	if (rx_buf->page_offset > ICE_LAST_OFFSET)
 		return false;
-#endif /* PAGE_SIZE < 8192) */
+#endif /* PAGE_SIZE >= 8192) */
 
 	/* If we have drained the page fragment pool we need to update
 	 * the pagecnt_bias and page count so that we fully restock the
@@ -949,12 +924,7 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size,
 	struct ice_rx_buf *rx_buf;
 
 	rx_buf = &rx_ring->rx_buf[ntc];
-	rx_buf->pgcnt =
-#if (PAGE_SIZE < 8192)
-		page_count(rx_buf->page);
-#else
-		0;
-#endif
+	rx_buf->pgcnt = page_count(rx_buf->page);
 	prefetchw(rx_buf->page);
 
 	if (!size)
@@ -1160,11 +1130,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 	bool failure;
 	u32 first;
 
-	/* Frame size depend on rx_ring setup when PAGE_SIZE=4K */
-#if (PAGE_SIZE < 8192)
-	xdp->frame_sz = ice_rx_frame_truesize(rx_ring, 0);
-#endif
-
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 	if (xdp_prog) {
 		xdp_ring = rx_ring->xdp_ring;
@@ -1223,10 +1188,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 			hard_start = page_address(rx_buf->page) + rx_buf->page_offset -
 				     offset;
 			xdp_prepare_buff(xdp, hard_start, offset, size, !!offset);
-#if (PAGE_SIZE > 4096)
-			/* At larger PAGE_SIZE, frame_sz depend on len size */
-			xdp->frame_sz = ice_rx_frame_truesize(rx_ring, size);
-#endif
 			xdp_buff_clear_frags_flag(xdp);
 		} else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) {
 			break;
@@ -1521,10 +1482,11 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 	 * budget and be more aggressive about cleaning up the Tx descriptors.
 	 */
 	ice_for_each_tx_ring(tx_ring, q_vector->tx) {
+		struct xsk_buff_pool *xsk_pool = READ_ONCE(tx_ring->xsk_pool);
 		bool wd;
 
-		if (tx_ring->xsk_pool)
-			wd = ice_xmit_zc(tx_ring);
+		if (xsk_pool)
+			wd = ice_xmit_zc(tx_ring, xsk_pool);
 		else if (ice_ring_is_xdp(tx_ring))
 			wd = true;
 		else
@@ -1550,6 +1512,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 		budget_per_ring = budget;
 
 	ice_for_each_rx_ring(rx_ring, q_vector->rx) {
+		struct xsk_buff_pool *xsk_pool = READ_ONCE(rx_ring->xsk_pool);
 		int cleaned;
 
 		/* A dedicated path for zero-copy allows making a single
@@ -1557,7 +1520,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 		 * ice_clean_rx_irq function and makes the codebase cleaner.
 		 */
 		cleaned = rx_ring->xsk_pool ?
-			  ice_clean_rx_irq_zc(rx_ring, budget_per_ring) :
+			  ice_clean_rx_irq_zc(rx_ring, xsk_pool, budget_per_ring) :
 			  ice_clean_rx_irq(rx_ring, budget_per_ring);
 		work_done += cleaned;
 		/* if we clean as many as budgeted, we must not be done */
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index a65955eb23c0..5dee829bfc47 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -39,7 +39,7 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx)
 	       sizeof(vsi_stat->rx_ring_stats[q_idx]->rx_stats));
 	memset(&vsi_stat->tx_ring_stats[q_idx]->stats, 0,
 	       sizeof(vsi_stat->tx_ring_stats[q_idx]->stats));
-	if (ice_is_xdp_ena_vsi(vsi))
+	if (vsi->xdp_rings)
 		memset(&vsi->xdp_rings[q_idx]->ring_stats->stats, 0,
 		       sizeof(vsi->xdp_rings[q_idx]->ring_stats->stats));
 }
@@ -52,10 +52,8 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx)
 static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx)
 {
 	ice_clean_tx_ring(vsi->tx_rings[q_idx]);
-	if (ice_is_xdp_ena_vsi(vsi)) {
-		synchronize_rcu();
+	if (vsi->xdp_rings)
 		ice_clean_tx_ring(vsi->xdp_rings[q_idx]);
-	}
 	ice_clean_rx_ring(vsi->rx_rings[q_idx]);
 }
 
@@ -112,25 +110,29 @@ ice_qvec_dis_irq(struct ice_vsi *vsi, struct ice_rx_ring *rx_ring,
  * ice_qvec_cfg_msix - Enable IRQ for given queue vector
  * @vsi: the VSI that contains queue vector
  * @q_vector: queue vector
+ * @qid: queue index
  */
 static void
-ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
+ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector, u16 qid)
 {
 	u16 reg_idx = q_vector->reg_idx;
 	struct ice_pf *pf = vsi->back;
 	struct ice_hw *hw = &pf->hw;
-	struct ice_tx_ring *tx_ring;
-	struct ice_rx_ring *rx_ring;
+	int q, _qid = qid;
 
 	ice_cfg_itr(hw, q_vector);
 
-	ice_for_each_tx_ring(tx_ring, q_vector->tx)
-		ice_cfg_txq_interrupt(vsi, tx_ring->reg_idx, reg_idx,
-				      q_vector->tx.itr_idx);
+	for (q = 0; q < q_vector->num_ring_tx; q++) {
+		ice_cfg_txq_interrupt(vsi, _qid, reg_idx, q_vector->tx.itr_idx);
+		_qid++;
+	}
+
+	_qid = qid;
 
-	ice_for_each_rx_ring(rx_ring, q_vector->rx)
-		ice_cfg_rxq_interrupt(vsi, rx_ring->reg_idx, reg_idx,
-				      q_vector->rx.itr_idx);
+	for (q = 0; q < q_vector->num_ring_rx; q++) {
+		ice_cfg_rxq_interrupt(vsi, _qid, reg_idx, q_vector->rx.itr_idx);
+		_qid++;
+	}
 
 	ice_flush(hw);
 }
@@ -163,7 +165,7 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
 	struct ice_q_vector *q_vector;
 	struct ice_tx_ring *tx_ring;
 	struct ice_rx_ring *rx_ring;
-	int timeout = 50;
+	int fail = 0;
 	int err;
 
 	if (q_idx >= vsi->num_rxq || q_idx >= vsi->num_txq)
@@ -173,40 +175,33 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
 	rx_ring = vsi->rx_rings[q_idx];
 	q_vector = rx_ring->q_vector;
 
-	while (test_and_set_bit(ICE_CFG_BUSY, vsi->state)) {
-		timeout--;
-		if (!timeout)
-			return -EBUSY;
-		usleep_range(1000, 2000);
-	}
+	synchronize_net();
+	netif_carrier_off(vsi->netdev);
+	netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
 
 	ice_qvec_dis_irq(vsi, rx_ring, q_vector);
 	ice_qvec_toggle_napi(vsi, q_vector, false);
 
-	netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
-
 	ice_fill_txq_meta(vsi, tx_ring, &txq_meta);
 	err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, tx_ring, &txq_meta);
-	if (err)
-		return err;
-	if (ice_is_xdp_ena_vsi(vsi)) {
+	if (!fail)
+		fail = err;
+	if (vsi->xdp_rings) {
 		struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx];
 
 		memset(&txq_meta, 0, sizeof(txq_meta));
 		ice_fill_txq_meta(vsi, xdp_ring, &txq_meta);
 		err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, xdp_ring,
 					   &txq_meta);
-		if (err)
-			return err;
+		if (!fail)
+			fail = err;
 	}
-	err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true);
-	if (err)
-		return err;
 
+	ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, false);
 	ice_qp_clean_rings(vsi, q_idx);
 	ice_qp_reset_stats(vsi, q_idx);
 
-	return 0;
+	return fail;
 }
 
 /**
@@ -219,40 +214,47 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
 static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
 {
 	struct ice_q_vector *q_vector;
+	int fail = 0;
+	bool link_up;
 	int err;
 
 	err = ice_vsi_cfg_single_txq(vsi, vsi->tx_rings, q_idx);
-	if (err)
-		return err;
+	if (!fail)
+		fail = err;
 
 	if (ice_is_xdp_ena_vsi(vsi)) {
 		struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx];
 
 		err = ice_vsi_cfg_single_txq(vsi, vsi->xdp_rings, q_idx);
-		if (err)
-			return err;
+		if (!fail)
+			fail = err;
 		ice_set_ring_xdp(xdp_ring);
 		ice_tx_xsk_pool(vsi, q_idx);
 	}
 
 	err = ice_vsi_cfg_single_rxq(vsi, q_idx);
-	if (err)
-		return err;
+	if (!fail)
+		fail = err;
 
 	q_vector = vsi->rx_rings[q_idx]->q_vector;
-	ice_qvec_cfg_msix(vsi, q_vector);
+	ice_qvec_cfg_msix(vsi, q_vector, q_idx);
 
 	err = ice_vsi_ctrl_one_rx_ring(vsi, true, q_idx, true);
-	if (err)
-		return err;
+	if (!fail)
+		fail = err;
 
 	ice_qvec_toggle_napi(vsi, q_vector, true);
 	ice_qvec_ena_irq(vsi, q_vector);
 
-	netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
-	clear_bit(ICE_CFG_BUSY, vsi->state);
+	/* make sure NAPI sees updated ice_{t,x}_ring::xsk_pool */
+	synchronize_net();
+	ice_get_link_status(vsi->port_info, &link_up);
+	if (link_up) {
+		netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
+		netif_carrier_on(vsi->netdev);
+	}
 
-	return 0;
+	return fail;
 }
 
 /**
@@ -379,7 +381,8 @@ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
 		goto failure;
 	}
 
-	if_running = netif_running(vsi->netdev) && ice_is_xdp_ena_vsi(vsi);
+	if_running = !test_bit(ICE_VSI_DOWN, vsi->state) &&
+		     ice_is_xdp_ena_vsi(vsi);
 
 	if (if_running) {
 		struct ice_rx_ring *rx_ring = vsi->rx_rings[qid];
@@ -459,6 +462,7 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
 /**
  * __ice_alloc_rx_bufs_zc - allocate a number of Rx buffers
  * @rx_ring: Rx ring
+ * @xsk_pool: XSK buffer pool to pick buffers to be filled by HW
  * @count: The number of buffers to allocate
  *
  * Place the @count of descriptors onto Rx ring. Handle the ring wrap
@@ -467,7 +471,8 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
  *
  * Returns true if all allocations were successful, false if any fail.
  */
-static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
+static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
+				   struct xsk_buff_pool *xsk_pool, u16 count)
 {
 	u32 nb_buffs_extra = 0, nb_buffs = 0;
 	union ice_32b_rx_flex_desc *rx_desc;
@@ -479,8 +484,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 	xdp = ice_xdp_buf(rx_ring, ntu);
 
 	if (ntu + count >= rx_ring->count) {
-		nb_buffs_extra = ice_fill_rx_descs(rx_ring->xsk_pool, xdp,
-						   rx_desc,
+		nb_buffs_extra = ice_fill_rx_descs(xsk_pool, xdp, rx_desc,
 						   rx_ring->count - ntu);
 		if (nb_buffs_extra != rx_ring->count - ntu) {
 			ntu += nb_buffs_extra;
@@ -493,7 +497,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 		ice_release_rx_desc(rx_ring, 0);
 	}
 
-	nb_buffs = ice_fill_rx_descs(rx_ring->xsk_pool, xdp, rx_desc, count);
+	nb_buffs = ice_fill_rx_descs(xsk_pool, xdp, rx_desc, count);
 
 	ntu += nb_buffs;
 	if (ntu == rx_ring->count)
@@ -509,6 +513,7 @@ exit:
 /**
  * ice_alloc_rx_bufs_zc - allocate a number of Rx buffers
  * @rx_ring: Rx ring
+ * @xsk_pool: XSK buffer pool to pick buffers to be filled by HW
  * @count: The number of buffers to allocate
  *
  * Wrapper for internal allocation routine; figure out how many tail
@@ -516,7 +521,8 @@ exit:
  *
  * Returns true if all calls to internal alloc routine succeeded
  */
-bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
+bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
+			  struct xsk_buff_pool *xsk_pool, u16 count)
 {
 	u16 rx_thresh = ICE_RING_QUARTER(rx_ring);
 	u16 leftover, i, tail_bumps;
@@ -525,9 +531,9 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 	leftover = count - (tail_bumps * rx_thresh);
 
 	for (i = 0; i < tail_bumps; i++)
-		if (!__ice_alloc_rx_bufs_zc(rx_ring, rx_thresh))
+		if (!__ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, rx_thresh))
 			return false;
-	return __ice_alloc_rx_bufs_zc(rx_ring, leftover);
+	return __ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, leftover);
 }
 
 /**
@@ -596,8 +602,10 @@ out:
 /**
  * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ
  * @xdp_ring: XDP Tx ring
+ * @xsk_pool: AF_XDP buffer pool pointer
  */
-static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
+static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring,
+				struct xsk_buff_pool *xsk_pool)
 {
 	u16 ntc = xdp_ring->next_to_clean;
 	struct ice_tx_desc *tx_desc;
@@ -648,7 +656,7 @@ skip:
 	if (xdp_ring->next_to_clean >= cnt)
 		xdp_ring->next_to_clean -= cnt;
 	if (xsk_frames)
-		xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);
+		xsk_tx_completed(xsk_pool, xsk_frames);
 
 	return completed_frames;
 }
@@ -657,6 +665,7 @@ skip:
  * ice_xmit_xdp_tx_zc - AF_XDP ZC handler for XDP_TX
  * @xdp: XDP buffer to xmit
  * @xdp_ring: XDP ring to produce descriptor onto
+ * @xsk_pool: AF_XDP buffer pool pointer
  *
  * note that this function works directly on xdp_buff, no need to convert
  * it to xdp_frame. xdp_buff pointer is stored to ice_tx_buf so that cleaning
@@ -666,7 +675,8 @@ skip:
  * was not enough space on XDP ring
  */
 static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
-			      struct ice_tx_ring *xdp_ring)
+			      struct ice_tx_ring *xdp_ring,
+			      struct xsk_buff_pool *xsk_pool)
 {
 	struct skb_shared_info *sinfo = NULL;
 	u32 size = xdp->data_end - xdp->data;
@@ -680,7 +690,7 @@ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
 
 	free_space = ICE_DESC_UNUSED(xdp_ring);
 	if (free_space < ICE_RING_QUARTER(xdp_ring))
-		free_space += ice_clean_xdp_irq_zc(xdp_ring);
+		free_space += ice_clean_xdp_irq_zc(xdp_ring, xsk_pool);
 
 	if (unlikely(!free_space))
 		goto busy;
@@ -700,7 +710,7 @@ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
 		dma_addr_t dma;
 
 		dma = xsk_buff_xdp_get_dma(xdp);
-		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size);
+		xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, size);
 
 		tx_buf->xdp = xdp;
 		tx_buf->type = ICE_TX_BUF_XSK_TX;
@@ -742,12 +752,14 @@ busy:
  * @xdp: xdp_buff used as input to the XDP program
  * @xdp_prog: XDP program to run
  * @xdp_ring: ring to be used for XDP_TX action
+ * @xsk_pool: AF_XDP buffer pool pointer
  *
  * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
  */
 static int
 ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
-	       struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring)
+	       struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring,
+	       struct xsk_buff_pool *xsk_pool)
 {
 	int err, result = ICE_XDP_PASS;
 	u32 act;
@@ -758,7 +770,7 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
 		if (!err)
 			return ICE_XDP_REDIR;
-		if (xsk_uses_need_wakeup(rx_ring->xsk_pool) && err == -ENOBUFS)
+		if (xsk_uses_need_wakeup(xsk_pool) && err == -ENOBUFS)
 			result = ICE_XDP_EXIT;
 		else
 			result = ICE_XDP_CONSUMED;
@@ -769,7 +781,7 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 	case XDP_PASS:
 		break;
 	case XDP_TX:
-		result = ice_xmit_xdp_tx_zc(xdp, xdp_ring);
+		result = ice_xmit_xdp_tx_zc(xdp, xdp_ring, xsk_pool);
 		if (result == ICE_XDP_CONSUMED)
 			goto out_failure;
 		break;
@@ -821,14 +833,16 @@ ice_add_xsk_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *first,
 /**
  * ice_clean_rx_irq_zc - consumes packets from the hardware ring
  * @rx_ring: AF_XDP Rx ring
+ * @xsk_pool: AF_XDP buffer pool pointer
  * @budget: NAPI budget
  *
  * Returns number of processed packets on success, remaining budget on failure.
  */
-int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
+int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring,
+			struct xsk_buff_pool *xsk_pool,
+			int budget)
 {
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
-	struct xsk_buff_pool *xsk_pool = rx_ring->xsk_pool;
 	u32 ntc = rx_ring->next_to_clean;
 	u32 ntu = rx_ring->next_to_use;
 	struct xdp_buff *first = NULL;
@@ -891,7 +905,8 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 		if (ice_is_non_eop(rx_ring, rx_desc))
 			continue;
 
-		xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring);
+		xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring,
+					 xsk_pool);
 		if (likely(xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))) {
 			xdp_xmit |= xdp_res;
 		} else if (xdp_res == ICE_XDP_EXIT) {
@@ -940,7 +955,8 @@ construct_skb:
 	rx_ring->next_to_clean = ntc;
 	entries_to_alloc = ICE_RX_DESC_UNUSED(rx_ring);
 	if (entries_to_alloc > ICE_RING_QUARTER(rx_ring))
-		failure |= !ice_alloc_rx_bufs_zc(rx_ring, entries_to_alloc);
+		failure |= !ice_alloc_rx_bufs_zc(rx_ring, xsk_pool,
+						 entries_to_alloc);
 
 	ice_finalize_xdp_rx(xdp_ring, xdp_xmit, 0);
 	ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes);
@@ -963,17 +979,19 @@ construct_skb:
 /**
  * ice_xmit_pkt - produce a single HW Tx descriptor out of AF_XDP descriptor
  * @xdp_ring: XDP ring to produce the HW Tx descriptor on
+ * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW
  * @desc: AF_XDP descriptor to pull the DMA address and length from
  * @total_bytes: bytes accumulator that will be used for stats update
  */
-static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc,
+static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring,
+			 struct xsk_buff_pool *xsk_pool, struct xdp_desc *desc,
 			 unsigned int *total_bytes)
 {
 	struct ice_tx_desc *tx_desc;
 	dma_addr_t dma;
 
-	dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc->addr);
-	xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc->len);
+	dma = xsk_buff_raw_get_dma(xsk_pool, desc->addr);
+	xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, desc->len);
 
 	tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_to_use++);
 	tx_desc->buf_addr = cpu_to_le64(dma);
@@ -986,10 +1004,13 @@ static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc,
 /**
  * ice_xmit_pkt_batch - produce a batch of HW Tx descriptors out of AF_XDP descriptors
  * @xdp_ring: XDP ring to produce the HW Tx descriptors on
+ * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW
  * @descs: AF_XDP descriptors to pull the DMA addresses and lengths from
  * @total_bytes: bytes accumulator that will be used for stats update
  */
-static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs,
+static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring,
+			       struct xsk_buff_pool *xsk_pool,
+			       struct xdp_desc *descs,
 			       unsigned int *total_bytes)
 {
 	u16 ntu = xdp_ring->next_to_use;
@@ -999,8 +1020,8 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de
 	loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) {
 		dma_addr_t dma;
 
-		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, descs[i].addr);
-		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, descs[i].len);
+		dma = xsk_buff_raw_get_dma(xsk_pool, descs[i].addr);
+		xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, descs[i].len);
 
 		tx_desc = ICE_TX_DESC(xdp_ring, ntu++);
 		tx_desc->buf_addr = cpu_to_le64(dma);
@@ -1016,60 +1037,69 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de
 /**
  * ice_fill_tx_hw_ring - produce the number of Tx descriptors onto ring
  * @xdp_ring: XDP ring to produce the HW Tx descriptors on
+ * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW
  * @descs: AF_XDP descriptors to pull the DMA addresses and lengths from
  * @nb_pkts: count of packets to be send
  * @total_bytes: bytes accumulator that will be used for stats update
  */
-static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs,
-				u32 nb_pkts, unsigned int *total_bytes)
+static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring,
+				struct xsk_buff_pool *xsk_pool,
+				struct xdp_desc *descs, u32 nb_pkts,
+				unsigned int *total_bytes)
 {
 	u32 batched, leftover, i;
 
 	batched = ALIGN_DOWN(nb_pkts, PKTS_PER_BATCH);
 	leftover = nb_pkts & (PKTS_PER_BATCH - 1);
 	for (i = 0; i < batched; i += PKTS_PER_BATCH)
-		ice_xmit_pkt_batch(xdp_ring, &descs[i], total_bytes);
+		ice_xmit_pkt_batch(xdp_ring, xsk_pool, &descs[i], total_bytes);
 	for (; i < batched + leftover; i++)
-		ice_xmit_pkt(xdp_ring, &descs[i], total_bytes);
+		ice_xmit_pkt(xdp_ring, xsk_pool, &descs[i], total_bytes);
 }
 
 /**
  * ice_xmit_zc - take entries from XSK Tx ring and place them onto HW Tx ring
  * @xdp_ring: XDP ring to produce the HW Tx descriptors on
+ * @xsk_pool: AF_XDP buffer pool pointer
  *
  * Returns true if there is no more work that needs to be done, false otherwise
  */
-bool ice_xmit_zc(struct ice_tx_ring *xdp_ring)
+bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, struct xsk_buff_pool *xsk_pool)
 {
-	struct xdp_desc *descs = xdp_ring->xsk_pool->tx_descs;
+	struct xdp_desc *descs = xsk_pool->tx_descs;
 	u32 nb_pkts, nb_processed = 0;
 	unsigned int total_bytes = 0;
 	int budget;
 
-	ice_clean_xdp_irq_zc(xdp_ring);
+	ice_clean_xdp_irq_zc(xdp_ring, xsk_pool);
+
+	if (!netif_carrier_ok(xdp_ring->vsi->netdev) ||
+	    !netif_running(xdp_ring->vsi->netdev))
+		return true;
 
 	budget = ICE_DESC_UNUSED(xdp_ring);
 	budget = min_t(u16, budget, ICE_RING_QUARTER(xdp_ring));
 
-	nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, budget);
+	nb_pkts = xsk_tx_peek_release_desc_batch(xsk_pool, budget);
 	if (!nb_pkts)
 		return true;
 
 	if (xdp_ring->next_to_use + nb_pkts >= xdp_ring->count) {
 		nb_processed = xdp_ring->count - xdp_ring->next_to_use;
-		ice_fill_tx_hw_ring(xdp_ring, descs, nb_processed, &total_bytes);
+		ice_fill_tx_hw_ring(xdp_ring, xsk_pool, descs, nb_processed,
+				    &total_bytes);
 		xdp_ring->next_to_use = 0;
 	}
 
-	ice_fill_tx_hw_ring(xdp_ring, &descs[nb_processed], nb_pkts - nb_processed,
-			    &total_bytes);
+	ice_fill_tx_hw_ring(xdp_ring, xsk_pool, &descs[nb_processed],
+			    nb_pkts - nb_processed, &total_bytes);
 
 	ice_set_rs_bit(xdp_ring);
 	ice_xdp_ring_update_tail(xdp_ring);
 	ice_update_tx_ring_stats(xdp_ring, nb_pkts, total_bytes);
 
-	if (xsk_uses_need_wakeup(xdp_ring->xsk_pool))
-		xsk_set_tx_need_wakeup(xdp_ring->xsk_pool);
+	if (xsk_uses_need_wakeup(xsk_pool))
+		xsk_set_tx_need_wakeup(xsk_pool);
 
 	return nb_pkts < budget;
 }
@@ -1091,7 +1121,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id,
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_tx_ring *ring;
 
-	if (test_bit(ICE_VSI_DOWN, vsi->state))
+	if (test_bit(ICE_VSI_DOWN, vsi->state) || !netif_carrier_ok(netdev))
 		return -ENETDOWN;
 
 	if (!ice_is_xdp_ena_vsi(vsi))
@@ -1102,7 +1132,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id,
 
 	ring = vsi->rx_rings[queue_id]->xdp_ring;
 
-	if (!ring->xsk_pool)
+	if (!READ_ONCE(ring->xsk_pool))
 		return -EINVAL;
 
 	/* The idea here is that if NAPI is running, mark a miss, so
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h
index 6fa181f080ef..45adeb513253 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.h
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.h
@@ -20,16 +20,20 @@ struct ice_vsi;
 #ifdef CONFIG_XDP_SOCKETS
 int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool,
 		       u16 qid);
-int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget);
+int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring,
+			struct xsk_buff_pool *xsk_pool,
+			int budget);
 int ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, u32 flags);
-bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count);
+bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
+			  struct xsk_buff_pool *xsk_pool, u16 count);
 bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi);
 void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring);
 void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring);
-bool ice_xmit_zc(struct ice_tx_ring *xdp_ring);
+bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, struct xsk_buff_pool *xsk_pool);
 int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc);
 #else
-static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring)
+static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring,
+			       struct xsk_buff_pool __always_unused *xsk_pool)
 {
 	return false;
 }
@@ -44,6 +48,7 @@ ice_xsk_pool_setup(struct ice_vsi __always_unused *vsi,
 
 static inline int
 ice_clean_rx_irq_zc(struct ice_rx_ring __always_unused *rx_ring,
+		    struct xsk_buff_pool __always_unused *xsk_pool,
 		    int __always_unused budget)
 {
 	return 0;
@@ -51,6 +56,7 @@ ice_clean_rx_irq_zc(struct ice_rx_ring __always_unused *rx_ring,
 
 static inline bool
 ice_alloc_rx_bufs_zc(struct ice_rx_ring __always_unused *rx_ring,
+		     struct xsk_buff_pool __always_unused *xsk_pool,
 		     u16 __always_unused count)
 {
 	return false;