1 files changed, 139 insertions, 135 deletions
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 0ab35607e5d5..049edeb60104 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -14,7 +14,7 @@
 #include "ice_dcb_lib.h"
 #include "ice_dcb_nl.h"
 #include "devlink/devlink.h"
-#include "devlink/devlink_port.h"
+#include "devlink/port.h"
 #include "ice_sf_eth.h"
 #include "ice_hwmon.h"
 /* Including ice_trace.h with CREATE_TRACE_POINTS defined will generate the
@@ -1144,7 +1144,7 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up,
 	if (link_up == old_link && link_speed == old_link_speed)
 		return 0;
 
-	ice_ptp_link_change(pf, pf->hw.pf_id, link_up);
+	ice_ptp_link_change(pf, link_up);
 
 	if (ice_is_dcb_active(pf)) {
 		if (test_bit(ICE_FLAG_DCB_ENA, pf->flags))
@@ -1567,6 +1567,9 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
 		case ice_aqc_opc_lldp_set_mib_change:
 			ice_dcb_process_lldp_set_mib_change(pf, &event);
 			break;
+		case ice_aqc_opc_get_health_status:
+			ice_process_health_status_event(pf, &event);
+			break;
 		default:
 			dev_dbg(dev, "%s Receive Queue unknown event 0x%04x ignored\n",
 				qtype, opcode);
@@ -1816,6 +1819,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 		if (netif_msg_tx_err(pf))
 			dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n",
 				 event, queue, pf_num, vf_num);
+		ice_report_mdd_event(pf, ICE_MDD_SRC_TX_PQM, pf_num, vf_num,
+				     event, queue);
 		wr32(hw, GL_MDET_TX_PQM, 0xffffffff);
 	}
 
@@ -1829,6 +1834,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 		if (netif_msg_tx_err(pf))
 			dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n",
 				 event, queue, pf_num, vf_num);
+		ice_report_mdd_event(pf, ICE_MDD_SRC_TX_TCLAN, pf_num, vf_num,
+				     event, queue);
 		wr32(hw, GL_MDET_TX_TCLAN_BY_MAC(hw), U32_MAX);
 	}
 
@@ -1842,6 +1849,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 		if (netif_msg_rx_err(pf))
 			dev_info(dev, "Malicious Driver Detection event %d on RX queue %d PF# %d VF# %d\n",
 				 event, queue, pf_num, vf_num);
+		ice_report_mdd_event(pf, ICE_MDD_SRC_RX, pf_num, vf_num, event,
+				     queue);
 		wr32(hw, GL_MDET_RX, 0xffffffff);
 	}
 
@@ -2355,6 +2364,18 @@ static void ice_check_media_subtask(struct ice_pf *pf)
 	}
 }
 
+static void ice_service_task_recovery_mode(struct work_struct *work)
+{
+	struct ice_pf *pf = container_of(work, struct ice_pf, serv_task);
+
+	set_bit(ICE_ADMINQ_EVENT_PENDING, pf->state);
+	ice_clean_adminq_subtask(pf);
+
+	ice_service_task_complete(pf);
+
+	mod_timer(&pf->serv_tmr, jiffies + msecs_to_jiffies(100));
+}
+
 /**
  * ice_service_task - manage and run subtasks
  * @work: pointer to work_struct contained by the PF struct
@@ -2364,9 +2385,11 @@ static void ice_service_task(struct work_struct *work)
 	struct ice_pf *pf = container_of(work, struct ice_pf, serv_task);
 	unsigned long start_time = jiffies;
 
-	/* subtasks */
+	if (pf->health_reporters.tx_hang_buf.tx_ring) {
+		ice_report_tx_hang(pf);
+		pf->health_reporters.tx_hang_buf.tx_ring = NULL;
+	}
 
-	/* process reset requests first */
 	ice_reset_subtask(pf);
 
 	/* bail if a reset/recovery cycle is pending or rebuild failed */
@@ -2505,34 +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
  */
@@ -2595,19 +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);
@@ -2623,9 +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;
@@ -3281,22 +3260,8 @@ 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;
-		if (ice_pf_state_is_nominal(pf) &&
-		    pf->hw.dev_caps.ts_dev_info.ts_ll_int_read) {
-			struct ice_ptp_tx *tx = &pf->ptp.port.tx;
-			unsigned long flags;
-			u8 idx;
-
-			spin_lock_irqsave(&tx->lock, flags);
-			idx = find_next_bit_wrap(tx->in_use, tx->len,
-						 tx->last_ll_ts_idx_read + 1);
-			if (idx != tx->len)
-				ice_ptp_req_tx_single_tstamp(tx, idx);
-			spin_unlock_irqrestore(&tx->lock, flags);
-		} else if (ice_ptp_pf_handles_tx_interrupt(pf)) {
-			set_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread);
-			ret = IRQ_WAKE_THREAD;
-		}
+
+		ret = ice_ptp_ts_irq(pf);
 	}
 
 	if (oicr & PFINT_OICR_TSYN_EVNT_M) {
@@ -3666,6 +3631,15 @@ 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);
+
+	/* Mutual exclusivity for TSO and GCS is enforced by the set features
+	 * ndo callback.
+	 */
+	if (ice_is_feature_supported(pf, ICE_F_GCS))
+		netdev->hw_features |= NETIF_F_HW_CSUM;
+
 	netif_set_tso_max_size(netdev, ICE_MAX_TSO_SIZE);
 }
 
@@ -4043,8 +4017,7 @@ static void ice_set_pf_caps(struct ice_pf *pf)
 	}
 
 	clear_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags);
-	if (func_caps->common_cap.ieee_1588 &&
-	    !(pf->hw.mac_type == ICE_MAC_E830))
+	if (func_caps->common_cap.ieee_1588)
 		set_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags);
 
 	pf->max_pf_txqs = func_caps->common_cap.num_txq;
@@ -4741,55 +4714,12 @@ static void ice_decfg_netdev(struct ice_vsi *vsi)
 	vsi->netdev = NULL;
 }
 
-/**
- * ice_wait_for_fw - wait for full FW readiness
- * @hw: pointer to the hardware structure
- * @timeout: milliseconds that can elapse before timing out
- */
-static int ice_wait_for_fw(struct ice_hw *hw, u32 timeout)
-{
-	int fw_loading;
-	u32 elapsed = 0;
-
-	while (elapsed <= timeout) {
-		fw_loading = rd32(hw, GL_MNG_FWSM) & GL_MNG_FWSM_FW_LOADING_M;
-
-		/* firmware was not yet loaded, we have to wait more */
-		if (fw_loading) {
-			elapsed += 100;
-			msleep(100);
-			continue;
-		}
-		return 0;
-	}
-
-	return -ETIMEDOUT;
-}
-
 int ice_init_dev(struct ice_pf *pf)
 {
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_hw *hw = &pf->hw;
 	int err;
 
-	err = ice_init_hw(hw);
-	if (err) {
-		dev_err(dev, "ice_init_hw failed: %d\n", err);
-		return err;
-	}
-
-	/* Some cards require longer initialization times
-	 * due to necessity of loading FW from an external source.
-	 * This can take even half a minute.
-	 */
-	if (ice_is_pf_c827(hw)) {
-		err = ice_wait_for_fw(hw, 30000);
-		if (err) {
-			dev_err(dev, "ice_wait_for_fw timed out");
-			return err;
-		}
-	}
-
 	ice_init_feature_support(pf);
 
 	err = ice_init_ddp_config(hw, pf);
@@ -4810,7 +4740,7 @@ int ice_init_dev(struct ice_pf *pf)
 	err = ice_init_pf(pf);
 	if (err) {
 		dev_err(dev, "ice_init_pf failed: %d\n", err);
-		goto err_init_pf;
+		return err;
 	}
 
 	pf->hw.udp_tunnel_nic.set_port = ice_udp_tunnel_set_port;
@@ -4834,7 +4764,7 @@ int ice_init_dev(struct ice_pf *pf)
 	if (err) {
 		dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err);
 		err = -EIO;
-		goto err_init_interrupt_scheme;
+		goto unroll_pf_init;
 	}
 
 	/* In case of MSIX we are going to setup the misc vector right here
@@ -4845,17 +4775,15 @@ int ice_init_dev(struct ice_pf *pf)
 	err = ice_req_irq_msix_misc(pf);
 	if (err) {
 		dev_err(dev, "setup of misc vector failed: %d\n", err);
-		goto err_req_irq_msix_misc;
+		goto unroll_irq_scheme_init;
 	}
 
 	return 0;
 
-err_req_irq_msix_misc:
+unroll_irq_scheme_init:
 	ice_clear_interrupt_scheme(pf);
-err_init_interrupt_scheme:
+unroll_pf_init:
 	ice_deinit_pf(pf);
-err_init_pf:
-	ice_deinit_hw(hw);
 	return err;
 }
 
@@ -5088,12 +5016,14 @@ static int ice_init_devlink(struct ice_pf *pf)
 
 	ice_devlink_init_regions(pf);
 	ice_devlink_register(pf);
+	ice_health_init(pf);
 
 	return 0;
 }
 
 static void ice_deinit_devlink(struct ice_pf *pf)
 {
+	ice_health_deinit(pf);
 	ice_devlink_unregister(pf);
 	ice_devlink_destroy_regions(pf);
 	ice_devlink_unregister_params(pf);
@@ -5107,6 +5037,12 @@ static int ice_init(struct ice_pf *pf)
 	if (err)
 		return err;
 
+	if (pf->hw.mac_type == ICE_MAC_E830) {
+		err = pci_enable_ptm(pf->pdev, NULL);
+		if (err)
+			dev_dbg(ice_pf_to_dev(pf), "PCIe PTM not supported by PCIe bus/controller\n");
+	}
+
 	err = ice_alloc_vsis(pf);
 	if (err)
 		goto err_alloc_vsis;
@@ -5206,11 +5142,12 @@ int ice_load(struct ice_pf *pf)
 
 	ice_napi_add(vsi);
 
+	ice_init_features(pf);
+
 	err = ice_init_rdma(pf);
 	if (err)
 		goto err_init_rdma;
 
-	ice_init_features(pf);
 	ice_service_task_restart(pf);
 
 	clear_bit(ICE_DOWN, pf->state);
@@ -5218,6 +5155,7 @@ int ice_load(struct ice_pf *pf)
 	return 0;
 
 err_init_rdma:
+	ice_deinit_features(pf);
 	ice_tc_indir_block_unregister(vsi);
 err_tc_indir_block_register:
 	ice_unregister_netdev(vsi);
@@ -5241,14 +5179,44 @@ void ice_unload(struct ice_pf *pf)
 
 	devl_assert_locked(priv_to_devlink(pf));
 
-	ice_deinit_features(pf);
 	ice_deinit_rdma(pf);
+	ice_deinit_features(pf);
 	ice_tc_indir_block_unregister(vsi);
 	ice_unregister_netdev(vsi);
 	ice_devlink_destroy_pf_port(pf);
 	ice_decfg_netdev(vsi);
 }
 
+static int ice_probe_recovery_mode(struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	int err;
+
+	dev_err(dev, "Firmware recovery mode detected. Limiting functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode\n");
+
+	INIT_HLIST_HEAD(&pf->aq_wait_list);
+	spin_lock_init(&pf->aq_wait_lock);
+	init_waitqueue_head(&pf->aq_wait_queue);
+
+	timer_setup(&pf->serv_tmr, ice_service_timer, 0);
+	pf->serv_tmr_period = HZ;
+	INIT_WORK(&pf->serv_task, ice_service_task_recovery_mode);
+	clear_bit(ICE_SERVICE_SCHED, pf->state);
+	err = ice_create_all_ctrlq(&pf->hw);
+	if (err)
+		return err;
+
+	scoped_guard(devl, priv_to_devlink(pf)) {
+		err = ice_init_devlink(pf);
+		if (err)
+			return err;
+	}
+
+	ice_service_task_restart(pf);
+
+	return 0;
+}
+
 /**
  * ice_probe - Device initialization routine
  * @pdev: PCI device information struct
@@ -5312,13 +5280,7 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 	}
 
 	pci_set_master(pdev);
-
-	adapter = ice_adapter_get(pdev);
-	if (IS_ERR(adapter))
-		return PTR_ERR(adapter);
-
 	pf->pdev = pdev;
-	pf->adapter = adapter;
 	pci_set_drvdata(pdev, pf);
 	set_bit(ICE_DOWN, pf->state);
 	/* Disable service task until DOWN bit is cleared */
@@ -5346,29 +5308,47 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 		hw->debug_mask = debug;
 #endif
 
+	if (ice_is_recovery_mode(hw))
+		return ice_probe_recovery_mode(pf);
+
+	err = ice_init_hw(hw);
+	if (err) {
+		dev_err(dev, "ice_init_hw failed: %d\n", err);
+		return err;
+	}
+
+	adapter = ice_adapter_get(pdev);
+	if (IS_ERR(adapter)) {
+		err = PTR_ERR(adapter);
+		goto unroll_hw_init;
+	}
+	pf->adapter = adapter;
+
 	err = ice_init(pf);
 	if (err)
-		goto err_init;
+		goto unroll_adapter;
 
 	devl_lock(priv_to_devlink(pf));
 	err = ice_load(pf);
 	if (err)
-		goto err_load;
+		goto unroll_init;
 
 	err = ice_init_devlink(pf);
 	if (err)
-		goto err_init_devlink;
+		goto unroll_load;
 	devl_unlock(priv_to_devlink(pf));
 
 	return 0;
 
-err_init_devlink:
+unroll_load:
 	ice_unload(pf);
-err_load:
+unroll_init:
 	devl_unlock(priv_to_devlink(pf));
 	ice_deinit(pf);
-err_init:
+unroll_adapter:
 	ice_adapter_put(pdev);
+unroll_hw_init:
+	ice_deinit_hw(hw);
 	return err;
 }
 
@@ -5448,6 +5428,14 @@ static void ice_remove(struct pci_dev *pdev)
 		msleep(100);
 	}
 
+	if (ice_is_recovery_mode(&pf->hw)) {
+		ice_service_task_stop(pf);
+		scoped_guard(devl, priv_to_devlink(pf)) {
+			ice_deinit_devlink(pf);
+		}
+		return;
+	}
+
 	if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) {
 		set_bit(ICE_VF_RESETS_DISABLED, pf->state);
 		ice_free_vfs(pf);
@@ -6567,6 +6555,18 @@ ice_set_features(struct net_device *netdev, netdev_features_t features)
 	if (changed & NETIF_F_LOOPBACK)
 		ret = ice_set_loopback(vsi, !!(features & NETIF_F_LOOPBACK));
 
+	/* Due to E830 hardware limitations, TSO (NETIF_F_ALL_TSO) with GCS
+	 * (NETIF_F_HW_CSUM) is not supported.
+	 */
+	if (ice_is_feature_supported(pf, ICE_F_GCS) &&
+	    ((features & NETIF_F_HW_CSUM) && (features & NETIF_F_ALL_TSO))) {
+		if (netdev->features & NETIF_F_HW_CSUM)
+			dev_err(ice_pf_to_dev(pf), "To enable TSO, you must first disable HW checksum.\n");
+		else
+			dev_err(ice_pf_to_dev(pf), "To enable HW checksum, you must first disable TSO.\n");
+		return -EIO;
+	}
+
 	return ret;
 }
 
@@ -6790,7 +6790,7 @@ static int ice_up_complete(struct ice_vsi *vsi)
 		ice_print_link_msg(vsi, true);
 		netif_tx_start_all_queues(vsi->netdev);
 		netif_carrier_on(vsi->netdev);
-		ice_ptp_link_change(pf, pf->hw.pf_id, true);
+		ice_ptp_link_change(pf, true);
 	}
 
 	/* Perform an initial read of the statistics registers now to
@@ -7260,7 +7260,7 @@ int ice_down(struct ice_vsi *vsi)
 
 	if (vsi->netdev) {
 		vlan_err = ice_vsi_del_vlan_zero(vsi);
-		ice_ptp_link_change(vsi->back, vsi->back->hw.pf_id, false);
+		ice_ptp_link_change(vsi->back, false);
 		netif_carrier_off(vsi->netdev);
 		netif_tx_disable(vsi->netdev);
 	}
@@ -7793,6 +7793,8 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 	/* if we get here, reset flow is successful */
 	clear_bit(ICE_RESET_FAILED, pf->state);
 
+	ice_health_clear(pf);
+
 	ice_plug_aux_dev(pf);
 	if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG))
 		ice_lag_rebuild(pf);
@@ -8283,16 +8285,18 @@ void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 
 	if (tx_ring) {
 		struct ice_hw *hw = &pf->hw;
-		u32 head, val = 0;
+		u32 head, intr = 0;
 
 		head = FIELD_GET(QTX_COMM_HEAD_HEAD_M,
 				 rd32(hw, QTX_COMM_HEAD(vsi->txq_map[txqueue])));
 		/* Read interrupt register */
-		val = rd32(hw, GLINT_DYN_CTL(tx_ring->q_vector->reg_idx));
+		intr = rd32(hw, GLINT_DYN_CTL(tx_ring->q_vector->reg_idx));
 
 		netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %u, NTC: 0x%x, HW_HEAD: 0x%x, NTU: 0x%x, INT: 0x%x\n",
 			    vsi->vsi_num, txqueue, tx_ring->next_to_clean,
-			    head, tx_ring->next_to_use, val);
+			    head, tx_ring->next_to_use, intr);
+
+		ice_prep_tx_hang_report(pf, tx_ring, vsi->vsi_num, head, intr);
 	}
 
 	pf->tx_timeout_last_recovery = jiffies;