1 files changed, 199 insertions, 99 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index e109cb93886b..0f6718719453 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3093,7 +3093,8 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 
 	if (oicr & PFINT_OICR_TSYN_TX_M) {
 		ena_mask &= ~PFINT_OICR_TSYN_TX_M;
-		ice_ptp_process_ts(pf);
+		if (!hw->reset_ongoing)
+			ret = IRQ_WAKE_THREAD;
 	}
 
 	if (oicr & PFINT_OICR_TSYN_EVNT_M) {
@@ -3128,7 +3129,8 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 			ice_service_task_schedule(pf);
 		}
 	}
-	ret = IRQ_HANDLED;
+	if (!ret)
+		ret = IRQ_HANDLED;
 
 	ice_service_task_schedule(pf);
 	ice_irq_dynamic_ena(hw, NULL, NULL);
@@ -3137,6 +3139,24 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 }
 
 /**
+ * ice_misc_intr_thread_fn - misc interrupt thread function
+ * @irq: interrupt number
+ * @data: pointer to a q_vector
+ */
+static irqreturn_t ice_misc_intr_thread_fn(int __always_unused irq, void *data)
+{
+	irqreturn_t ret = IRQ_HANDLED;
+	struct ice_pf *pf = data;
+	bool irq_handled;
+
+	irq_handled = ice_ptp_process_ts(pf);
+	if (!irq_handled)
+		ret = IRQ_WAKE_THREAD;
+
+	return ret;
+}
+
+/**
  * ice_dis_ctrlq_interrupts - disable control queue interrupts
  * @hw: pointer to HW structure
  */
@@ -3248,10 +3268,12 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf)
 	pf->num_avail_sw_msix -= 1;
 	pf->oicr_idx = (u16)oicr_idx;
 
-	err = devm_request_irq(dev, pf->msix_entries[pf->oicr_idx].vector,
-			       ice_misc_intr, 0, pf->int_name, pf);
+	err = devm_request_threaded_irq(dev,
+					pf->msix_entries[pf->oicr_idx].vector,
+					ice_misc_intr, ice_misc_intr_thread_fn,
+					0, pf->int_name, pf);
 	if (err) {
-		dev_err(dev, "devm_request_irq for %s failed: %d\n",
+		dev_err(dev, "devm_request_threaded_irq for %s failed: %d\n",
 			pf->int_name, err);
 		ice_free_res(pf->irq_tracker, 1, ICE_RES_MISC_VEC_ID);
 		pf->num_avail_sw_msix += 1;
@@ -3288,7 +3310,7 @@ static void ice_napi_add(struct ice_vsi *vsi)
 
 	ice_for_each_q_vector(vsi, v_idx)
 		netif_napi_add(vsi->netdev, &vsi->q_vectors[v_idx]->napi,
-			       ice_napi_poll, NAPI_POLL_WEIGHT);
+			       ice_napi_poll);
 }
 
 /**
@@ -3391,6 +3413,11 @@ static void ice_set_netdev_features(struct net_device *netdev)
 	if (is_dvm_ena)
 		netdev->hw_features |= NETIF_F_HW_VLAN_STAG_RX |
 			NETIF_F_HW_VLAN_STAG_TX;
+
+	/* Leave CRC / FCS stripping enabled by default, but allow the value to
+	 * be changed at runtime
+	 */
+	netdev->hw_features |= NETIF_F_RXFCS;
 }
 
 /**
@@ -3923,87 +3950,134 @@ static int ice_init_pf(struct ice_pf *pf)
 }
 
 /**
+ * ice_reduce_msix_usage - Reduce usage of MSI-X vectors
+ * @pf: board private structure
+ * @v_remain: number of remaining MSI-X vectors to be distributed
+ *
+ * Reduce the usage of MSI-X vectors when entire request cannot be fulfilled.
+ * pf->num_lan_msix and pf->num_rdma_msix values are set based on number of
+ * remaining vectors.
+ */
+static void ice_reduce_msix_usage(struct ice_pf *pf, int v_remain)
+{
+	int v_rdma;
+
+	if (!ice_is_rdma_ena(pf)) {
+		pf->num_lan_msix = v_remain;
+		return;
+	}
+
+	/* RDMA needs at least 1 interrupt in addition to AEQ MSIX */
+	v_rdma = ICE_RDMA_NUM_AEQ_MSIX + 1;
+
+	if (v_remain < ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_RDMA_MSIX) {
+		dev_warn(ice_pf_to_dev(pf), "Not enough MSI-X vectors to support RDMA.\n");
+		clear_bit(ICE_FLAG_RDMA_ENA, pf->flags);
+
+		pf->num_rdma_msix = 0;
+		pf->num_lan_msix = ICE_MIN_LAN_TXRX_MSIX;
+	} else if ((v_remain < ICE_MIN_LAN_TXRX_MSIX + v_rdma) ||
+		   (v_remain - v_rdma < v_rdma)) {
+		/* Support minimum RDMA and give remaining vectors to LAN MSIX */
+		pf->num_rdma_msix = ICE_MIN_RDMA_MSIX;
+		pf->num_lan_msix = v_remain - ICE_MIN_RDMA_MSIX;
+	} else {
+		/* Split remaining MSIX with RDMA after accounting for AEQ MSIX
+		 */
+		pf->num_rdma_msix = (v_remain - ICE_RDMA_NUM_AEQ_MSIX) / 2 +
+				    ICE_RDMA_NUM_AEQ_MSIX;
+		pf->num_lan_msix = v_remain - pf->num_rdma_msix;
+	}
+}
+
+/**
  * ice_ena_msix_range - Request a range of MSIX vectors from the OS
  * @pf: board private structure
  *
- * compute the number of MSIX vectors required (v_budget) and request from
- * the OS. Return the number of vectors reserved or negative on failure
+ * Compute the number of MSIX vectors wanted and request from the OS. Adjust
+ * device usage if there are not enough vectors. Return the number of vectors
+ * reserved or negative on failure.
  */
 static int ice_ena_msix_range(struct ice_pf *pf)
 {
-	int num_cpus, v_left, v_actual, v_other, v_budget = 0;
+	int num_cpus, hw_num_msix, v_other, v_wanted, v_actual;
 	struct device *dev = ice_pf_to_dev(pf);
-	int needed, err, i;
+	int err, i;
 
-	v_left = pf->hw.func_caps.common_cap.num_msix_vectors;
+	hw_num_msix = pf->hw.func_caps.common_cap.num_msix_vectors;
 	num_cpus = num_online_cpus();
 
-	/* reserve for LAN miscellaneous handler */
-	needed = ICE_MIN_LAN_OICR_MSIX;
-	if (v_left < needed)
-		goto no_hw_vecs_left_err;
-	v_budget += needed;
-	v_left -= needed;
+	/* LAN miscellaneous handler */
+	v_other = ICE_MIN_LAN_OICR_MSIX;
 
-	/* reserve for flow director */
-	if (test_bit(ICE_FLAG_FD_ENA, pf->flags)) {
-		needed = ICE_FDIR_MSIX;
-		if (v_left < needed)
-			goto no_hw_vecs_left_err;
-		v_budget += needed;
-		v_left -= needed;
-	}
-
-	/* reserve for switchdev */
-	needed = ICE_ESWITCH_MSIX;
-	if (v_left < needed)
-		goto no_hw_vecs_left_err;
-	v_budget += needed;
-	v_left -= needed;
-
-	/* total used for non-traffic vectors */
-	v_other = v_budget;
-
-	/* reserve vectors for LAN traffic */
-	needed = num_cpus;
-	if (v_left < needed)
-		goto no_hw_vecs_left_err;
-	pf->num_lan_msix = needed;
-	v_budget += needed;
-	v_left -= needed;
-
-	/* reserve vectors for RDMA auxiliary driver */
+	/* Flow Director */
+	if (test_bit(ICE_FLAG_FD_ENA, pf->flags))
+		v_other += ICE_FDIR_MSIX;
+
+	/* switchdev */
+	v_other += ICE_ESWITCH_MSIX;
+
+	v_wanted = v_other;
+
+	/* LAN traffic */
+	pf->num_lan_msix = num_cpus;
+	v_wanted += pf->num_lan_msix;
+
+	/* RDMA auxiliary driver */
 	if (ice_is_rdma_ena(pf)) {
-		needed = num_cpus + ICE_RDMA_NUM_AEQ_MSIX;
-		if (v_left < needed)
-			goto no_hw_vecs_left_err;
-		pf->num_rdma_msix = needed;
-		v_budget += needed;
-		v_left -= needed;
+		pf->num_rdma_msix = num_cpus + ICE_RDMA_NUM_AEQ_MSIX;
+		v_wanted += pf->num_rdma_msix;
 	}
 
-	pf->msix_entries = devm_kcalloc(dev, v_budget,
+	if (v_wanted > hw_num_msix) {
+		int v_remain;
+
+		dev_warn(dev, "not enough device MSI-X vectors. wanted = %d, available = %d\n",
+			 v_wanted, hw_num_msix);
+
+		if (hw_num_msix < ICE_MIN_MSIX) {
+			err = -ERANGE;
+			goto exit_err;
+		}
+
+		v_remain = hw_num_msix - v_other;
+		if (v_remain < ICE_MIN_LAN_TXRX_MSIX) {
+			v_other = ICE_MIN_MSIX - ICE_MIN_LAN_TXRX_MSIX;
+			v_remain = ICE_MIN_LAN_TXRX_MSIX;
+		}
+
+		ice_reduce_msix_usage(pf, v_remain);
+		v_wanted = pf->num_lan_msix + pf->num_rdma_msix + v_other;
+
+		dev_notice(dev, "Reducing request to %d MSI-X vectors for LAN traffic.\n",
+			   pf->num_lan_msix);
+		if (ice_is_rdma_ena(pf))
+			dev_notice(dev, "Reducing request to %d MSI-X vectors for RDMA.\n",
+				   pf->num_rdma_msix);
+	}
+
+	pf->msix_entries = devm_kcalloc(dev, v_wanted,
 					sizeof(*pf->msix_entries), GFP_KERNEL);
 	if (!pf->msix_entries) {
 		err = -ENOMEM;
 		goto exit_err;
 	}
 
-	for (i = 0; i < v_budget; i++)
+	for (i = 0; i < v_wanted; i++)
 		pf->msix_entries[i].entry = i;
 
 	/* actually reserve the vectors */
 	v_actual = pci_enable_msix_range(pf->pdev, pf->msix_entries,
-					 ICE_MIN_MSIX, v_budget);
+					 ICE_MIN_MSIX, v_wanted);
 	if (v_actual < 0) {
 		dev_err(dev, "unable to reserve MSI-X vectors\n");
 		err = v_actual;
 		goto msix_err;
 	}
 
-	if (v_actual < v_budget) {
+	if (v_actual < v_wanted) {
 		dev_warn(dev, "not enough OS MSI-X vectors. requested = %d, obtained = %d\n",
-			 v_budget, v_actual);
+			 v_wanted, v_actual);
 
 		if (v_actual < ICE_MIN_MSIX) {
 			/* error if we can't get minimum vectors */
@@ -4012,38 +4086,11 @@ static int ice_ena_msix_range(struct ice_pf *pf)
 			goto msix_err;
 		} else {
 			int v_remain = v_actual - v_other;
-			int v_rdma = 0, v_min_rdma = 0;
 
-			if (ice_is_rdma_ena(pf)) {
-				/* Need at least 1 interrupt in addition to
-				 * AEQ MSIX
-				 */
-				v_rdma = ICE_RDMA_NUM_AEQ_MSIX + 1;
-				v_min_rdma = ICE_MIN_RDMA_MSIX;
-			}
+			if (v_remain < ICE_MIN_LAN_TXRX_MSIX)
+				v_remain = ICE_MIN_LAN_TXRX_MSIX;
 
-			if (v_actual == ICE_MIN_MSIX ||
-			    v_remain < ICE_MIN_LAN_TXRX_MSIX + v_min_rdma) {
-				dev_warn(dev, "Not enough MSI-X vectors to support RDMA.\n");
-				clear_bit(ICE_FLAG_RDMA_ENA, pf->flags);
-
-				pf->num_rdma_msix = 0;
-				pf->num_lan_msix = ICE_MIN_LAN_TXRX_MSIX;
-			} else if ((v_remain < ICE_MIN_LAN_TXRX_MSIX + v_rdma) ||
-				   (v_remain - v_rdma < v_rdma)) {
-				/* Support minimum RDMA and give remaining
-				 * vectors to LAN MSIX
-				 */
-				pf->num_rdma_msix = v_min_rdma;
-				pf->num_lan_msix = v_remain - v_min_rdma;
-			} else {
-				/* Split remaining MSIX with RDMA after
-				 * accounting for AEQ MSIX
-				 */
-				pf->num_rdma_msix = (v_remain - ICE_RDMA_NUM_AEQ_MSIX) / 2 +
-						    ICE_RDMA_NUM_AEQ_MSIX;
-				pf->num_lan_msix = v_remain - pf->num_rdma_msix;
-			}
+			ice_reduce_msix_usage(pf, v_remain);
 
 			dev_notice(dev, "Enabled %d MSI-X vectors for LAN traffic.\n",
 				   pf->num_lan_msix);
@@ -4058,12 +4105,7 @@ static int ice_ena_msix_range(struct ice_pf *pf)
 
 msix_err:
 	devm_kfree(dev, pf->msix_entries);
-	goto exit_err;
 
-no_hw_vecs_left_err:
-	dev_err(dev, "not enough device MSI-X vectors. requested = %d, available = %d\n",
-		needed, v_left);
-	err = -ERANGE;
 exit_err:
 	pf->num_rdma_msix = 0;
 	pf->num_lan_msix = 0;
@@ -4557,6 +4599,10 @@ static int ice_register_netdev(struct ice_pf *pf)
 	if (!vsi || !vsi->netdev)
 		return -EIO;
 
+	err = ice_devlink_create_pf_port(pf);
+	if (err)
+		goto err_devlink_create;
+
 	err = register_netdev(vsi->netdev);
 	if (err)
 		goto err_register_netdev;
@@ -4564,17 +4610,13 @@ static int ice_register_netdev(struct ice_pf *pf)
 	set_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state);
 	netif_carrier_off(vsi->netdev);
 	netif_tx_stop_all_queues(vsi->netdev);
-	err = ice_devlink_create_pf_port(pf);
-	if (err)
-		goto err_devlink_create;
 
 	devlink_port_type_eth_set(&pf->devlink_port, vsi->netdev);
 
 	return 0;
-err_devlink_create:
-	unregister_netdev(vsi->netdev);
-	clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state);
 err_register_netdev:
+	ice_devlink_destroy_pf_port(pf);
+err_devlink_create:
 	free_netdev(vsi->netdev);
 	vsi->netdev = NULL;
 	clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state);
@@ -4682,8 +4724,6 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 		ice_set_safe_mode_caps(hw);
 	}
 
-	hw->ucast_shared = true;
-
 	err = ice_init_pf(pf);
 	if (err) {
 		dev_err(dev, "ice_init_pf failed: %d\n", err);
@@ -5742,6 +5782,9 @@ ice_fdb_del(struct ndmsg *ndm, __always_unused struct nlattr *tb[],
 					 NETIF_F_HW_VLAN_STAG_RX | \
 					 NETIF_F_HW_VLAN_STAG_TX)
 
+#define NETIF_VLAN_STRIPPING_FEATURES	(NETIF_F_HW_VLAN_CTAG_RX | \
+					 NETIF_F_HW_VLAN_STAG_RX)
+
 #define NETIF_VLAN_FILTERING_FEATURES	(NETIF_F_HW_VLAN_CTAG_FILTER | \
 					 NETIF_F_HW_VLAN_STAG_FILTER)
 
@@ -5828,6 +5871,14 @@ ice_fix_features(struct net_device *netdev, netdev_features_t features)
 			      NETIF_F_HW_VLAN_STAG_TX);
 	}
 
+	if (!(netdev->features & NETIF_F_RXFCS) &&
+	    (features & NETIF_F_RXFCS) &&
+	    (features & NETIF_VLAN_STRIPPING_FEATURES) &&
+	    !ice_vsi_has_non_zero_vlans(np->vsi)) {
+		netdev_warn(netdev, "Disabling VLAN stripping as FCS/CRC stripping is also disabled and there is no VLAN configured\n");
+		features &= ~NETIF_VLAN_STRIPPING_FEATURES;
+	}
+
 	return features;
 }
 
@@ -5921,6 +5972,13 @@ ice_set_vlan_features(struct net_device *netdev, netdev_features_t features)
 	current_vlan_features = netdev->features & NETIF_VLAN_OFFLOAD_FEATURES;
 	requested_vlan_features = features & NETIF_VLAN_OFFLOAD_FEATURES;
 	if (current_vlan_features ^ requested_vlan_features) {
+		if ((features & NETIF_F_RXFCS) &&
+		    (features & NETIF_VLAN_STRIPPING_FEATURES)) {
+			dev_err(ice_pf_to_dev(vsi->back),
+				"To enable VLAN stripping, you must first enable FCS/CRC stripping\n");
+			return -EIO;
+		}
+
 		err = ice_set_vlan_offload_features(vsi, features);
 		if (err)
 			return err;
@@ -6002,6 +6060,23 @@ ice_set_features(struct net_device *netdev, netdev_features_t features)
 	if (ret)
 		return ret;
 
+	/* Turn on receive of FCS aka CRC, and after setting this
+	 * flag the packet data will have the 4 byte CRC appended
+	 */
+	if (changed & NETIF_F_RXFCS) {
+		if ((features & NETIF_F_RXFCS) &&
+		    (features & NETIF_VLAN_STRIPPING_FEATURES)) {
+			dev_err(ice_pf_to_dev(vsi->back),
+				"To disable FCS/CRC stripping, you must first disable VLAN stripping\n");
+			return -EIO;
+		}
+
+		ice_vsi_cfg_crc_strip(vsi, !!(features & NETIF_F_RXFCS));
+		ret = ice_down_up(vsi);
+		if (ret)
+			return ret;
+	}
+
 	if (changed & NETIF_F_NTUPLE) {
 		bool ena = !!(features & NETIF_F_NTUPLE);
 
@@ -6699,6 +6774,31 @@ int ice_down(struct ice_vsi *vsi)
 }
 
 /**
+ * ice_down_up - shutdown the VSI connection and bring it up
+ * @vsi: the VSI to be reconnected
+ */
+int ice_down_up(struct ice_vsi *vsi)
+{
+	int ret;
+
+	/* if DOWN already set, nothing to do */
+	if (test_and_set_bit(ICE_VSI_DOWN, vsi->state))
+		return 0;
+
+	ret = ice_down(vsi);
+	if (ret)
+		return ret;
+
+	ret = ice_up(vsi);
+	if (ret) {
+		netdev_err(vsi->netdev, "reallocating resources failed during netdev features change, may need to reload driver\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+/**
  * ice_vsi_setup_tx_rings - Allocate VSI Tx queue resources
  * @vsi: VSI having resources allocated
  *