1 files changed, 401 insertions, 202 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 6607fa6fe556..5d7660bc8846 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -14,6 +14,7 @@
 #include "ice_dcb_lib.h"
 #include "ice_dcb_nl.h"
 #include "ice_devlink.h"
+#include "ice_hwmon.h"
 /* Including ice_trace.h with CREATE_TRACE_POINTS defined will generate the
  * ice tracepoint functions. This must be done exactly once across the
  * ice driver.
@@ -612,7 +613,7 @@ skip:
 	ice_pf_dis_all_vsi(pf, false);
 
 	if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags))
-		ice_ptp_prepare_for_reset(pf);
+		ice_ptp_prepare_for_reset(pf, reset_type);
 
 	if (ice_is_feature_supported(pf, ICE_F_GNSS))
 		ice_gnss_exit(pf);
@@ -979,7 +980,7 @@ static void ice_set_dflt_mib(struct ice_pf *pf)
 	 * Octets 13 - 20 are TSA values - leave as zeros
 	 */
 	buf[5] = 0x64;
-	len = (typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S;
+	len = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen);
 	offset += len + 2;
 	tlv = (struct ice_lldp_org_tlv *)
 		((char *)tlv + sizeof(tlv->typelen) + len);
@@ -1013,7 +1014,7 @@ static void ice_set_dflt_mib(struct ice_pf *pf)
 
 	/* Octet 1 left as all zeros - PFC disabled */
 	buf[0] = 0x08;
-	len = (typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S;
+	len = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen);
 	offset += len + 2;
 
 	if (ice_aq_set_lldp_mib(hw, mib_type, (void *)lldpmib, offset, NULL))
@@ -1252,6 +1253,32 @@ ice_handle_link_event(struct ice_pf *pf, struct ice_rq_event_info *event)
 }
 
 /**
+ * ice_get_fwlog_data - copy the FW log data from ARQ event
+ * @pf: PF that the FW log event is associated with
+ * @event: event structure containing FW log data
+ */
+static void
+ice_get_fwlog_data(struct ice_pf *pf, struct ice_rq_event_info *event)
+{
+	struct ice_fwlog_data *fwlog;
+	struct ice_hw *hw = &pf->hw;
+
+	fwlog = &hw->fwlog_ring.rings[hw->fwlog_ring.tail];
+
+	memset(fwlog->data, 0, PAGE_SIZE);
+	fwlog->data_size = le16_to_cpu(event->desc.datalen);
+
+	memcpy(fwlog->data, event->msg_buf, fwlog->data_size);
+	ice_fwlog_ring_increment(&hw->fwlog_ring.tail, hw->fwlog_ring.size);
+
+	if (ice_fwlog_ring_full(&hw->fwlog_ring)) {
+		/* the rings are full so bump the head to create room */
+		ice_fwlog_ring_increment(&hw->fwlog_ring.head,
+					 hw->fwlog_ring.size);
+	}
+}
+
+/**
  * ice_aq_prep_for_event - Prepare to wait for an AdminQ event from firmware
  * @pf: pointer to the PF private structure
  * @task: intermediate helper storage and identifier for waiting
@@ -1532,8 +1559,8 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
 
 			ice_vc_process_vf_msg(pf, &event, &data);
 			break;
-		case ice_aqc_opc_fw_logging:
-			ice_output_fw_log(hw, &event.desc, event.msg_buf);
+		case ice_aqc_opc_fw_logs_event:
+			ice_get_fwlog_data(pf, &event);
 			break;
 		case ice_aqc_opc_lldp_set_mib_change:
 			ice_dcb_process_lldp_set_mib_change(pf, &event);
@@ -1622,8 +1649,10 @@ static void ice_clean_sbq_subtask(struct ice_pf *pf)
 {
 	struct ice_hw *hw = &pf->hw;
 
-	/* Nothing to do here if sideband queue is not supported */
-	if (!ice_is_sbq_supported(hw)) {
+	/* if mac_type is not generic, sideband is not supported
+	 * and there's nothing to do here
+	 */
+	if (!ice_is_generic_mac(hw)) {
 		clear_bit(ICE_SIDEBANDQ_EVENT_PENDING, pf->state);
 		return;
 	}
@@ -1744,14 +1773,10 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 	/* find what triggered an MDD event */
 	reg = rd32(hw, GL_MDET_TX_PQM);
 	if (reg & GL_MDET_TX_PQM_VALID_M) {
-		u8 pf_num = (reg & GL_MDET_TX_PQM_PF_NUM_M) >>
-				GL_MDET_TX_PQM_PF_NUM_S;
-		u16 vf_num = (reg & GL_MDET_TX_PQM_VF_NUM_M) >>
-				GL_MDET_TX_PQM_VF_NUM_S;
-		u8 event = (reg & GL_MDET_TX_PQM_MAL_TYPE_M) >>
-				GL_MDET_TX_PQM_MAL_TYPE_S;
-		u16 queue = ((reg & GL_MDET_TX_PQM_QNUM_M) >>
-				GL_MDET_TX_PQM_QNUM_S);
+		u8 pf_num = FIELD_GET(GL_MDET_TX_PQM_PF_NUM_M, reg);
+		u16 vf_num = FIELD_GET(GL_MDET_TX_PQM_VF_NUM_M, reg);
+		u8 event = FIELD_GET(GL_MDET_TX_PQM_MAL_TYPE_M, reg);
+		u16 queue = FIELD_GET(GL_MDET_TX_PQM_QNUM_M, reg);
 
 		if (netif_msg_tx_err(pf))
 			dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n",
@@ -1761,14 +1786,10 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 
 	reg = rd32(hw, GL_MDET_TX_TCLAN_BY_MAC(hw));
 	if (reg & GL_MDET_TX_TCLAN_VALID_M) {
-		u8 pf_num = (reg & GL_MDET_TX_TCLAN_PF_NUM_M) >>
-				GL_MDET_TX_TCLAN_PF_NUM_S;
-		u16 vf_num = (reg & GL_MDET_TX_TCLAN_VF_NUM_M) >>
-				GL_MDET_TX_TCLAN_VF_NUM_S;
-		u8 event = (reg & GL_MDET_TX_TCLAN_MAL_TYPE_M) >>
-				GL_MDET_TX_TCLAN_MAL_TYPE_S;
-		u16 queue = ((reg & GL_MDET_TX_TCLAN_QNUM_M) >>
-				GL_MDET_TX_TCLAN_QNUM_S);
+		u8 pf_num = FIELD_GET(GL_MDET_TX_TCLAN_PF_NUM_M, reg);
+		u16 vf_num = FIELD_GET(GL_MDET_TX_TCLAN_VF_NUM_M, reg);
+		u8 event = FIELD_GET(GL_MDET_TX_TCLAN_MAL_TYPE_M, reg);
+		u16 queue = FIELD_GET(GL_MDET_TX_TCLAN_QNUM_M, reg);
 
 		if (netif_msg_tx_err(pf))
 			dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n",
@@ -1778,14 +1799,10 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 
 	reg = rd32(hw, GL_MDET_RX);
 	if (reg & GL_MDET_RX_VALID_M) {
-		u8 pf_num = (reg & GL_MDET_RX_PF_NUM_M) >>
-				GL_MDET_RX_PF_NUM_S;
-		u16 vf_num = (reg & GL_MDET_RX_VF_NUM_M) >>
-				GL_MDET_RX_VF_NUM_S;
-		u8 event = (reg & GL_MDET_RX_MAL_TYPE_M) >>
-				GL_MDET_RX_MAL_TYPE_S;
-		u16 queue = ((reg & GL_MDET_RX_QNUM_M) >>
-				GL_MDET_RX_QNUM_S);
+		u8 pf_num = FIELD_GET(GL_MDET_RX_PF_NUM_M, reg);
+		u16 vf_num = FIELD_GET(GL_MDET_RX_VF_NUM_M, reg);
+		u8 event = FIELD_GET(GL_MDET_RX_MAL_TYPE_M, reg);
+		u16 queue = FIELD_GET(GL_MDET_RX_QNUM_M, reg);
 
 		if (netif_msg_rx_err(pf))
 			dev_info(dev, "Malicious Driver Detection event %d on RX queue %d PF# %d VF# %d\n",
@@ -2146,7 +2163,7 @@ static int ice_configure_phy(struct ice_vsi *vsi)
 
 	/* Ensure we have media as we cannot configure a medialess port */
 	if (!(phy->link_info.link_info & ICE_AQ_MEDIA_AVAILABLE))
-		return -EPERM;
+		return -ENOMEDIUM;
 
 	ice_print_topo_conflict(vsi);
 
@@ -3031,6 +3048,7 @@ static int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 static void ice_ena_misc_vector(struct ice_pf *pf)
 {
 	struct ice_hw *hw = &pf->hw;
+	u32 pf_intr_start_offset;
 	u32 val;
 
 	/* Disable anti-spoof detection interrupt to prevent spurious event
@@ -3059,6 +3077,47 @@ static void ice_ena_misc_vector(struct ice_pf *pf)
 	/* SW_ITR_IDX = 0, but don't change INTENA */
 	wr32(hw, GLINT_DYN_CTL(pf->oicr_irq.index),
 	     GLINT_DYN_CTL_SW_ITR_INDX_M | GLINT_DYN_CTL_INTENA_MSK_M);
+
+	if (!pf->hw.dev_caps.ts_dev_info.ts_ll_int_read)
+		return;
+	pf_intr_start_offset = rd32(hw, PFINT_ALLOC) & PFINT_ALLOC_FIRST;
+	wr32(hw, GLINT_DYN_CTL(pf->ll_ts_irq.index + pf_intr_start_offset),
+	     GLINT_DYN_CTL_SW_ITR_INDX_M | GLINT_DYN_CTL_INTENA_MSK_M);
+}
+
+/**
+ * ice_ll_ts_intr - ll_ts interrupt handler
+ * @irq: interrupt number
+ * @data: pointer to a q_vector
+ */
+static irqreturn_t ice_ll_ts_intr(int __always_unused irq, void *data)
+{
+	struct ice_pf *pf = data;
+	u32 pf_intr_start_offset;
+	struct ice_ptp_tx *tx;
+	unsigned long flags;
+	struct ice_hw *hw;
+	u32 val;
+	u8 idx;
+
+	hw = &pf->hw;
+	tx = &pf->ptp.port.tx;
+	spin_lock_irqsave(&tx->lock, flags);
+	ice_ptp_complete_tx_single_tstamp(tx);
+
+	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);
+
+	val = GLINT_DYN_CTL_INTENA_M | GLINT_DYN_CTL_CLEARPBA_M |
+	      (ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S);
+	pf_intr_start_offset = rd32(hw, PFINT_ALLOC) & PFINT_ALLOC_FIRST;
+	wr32(hw, GLINT_DYN_CTL(pf->ll_ts_irq.index + pf_intr_start_offset),
+	     val);
+
+	return IRQ_HANDLED;
 }
 
 /**
@@ -3069,6 +3128,7 @@ static void ice_ena_misc_vector(struct ice_pf *pf)
 static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 {
 	struct ice_pf *pf = (struct ice_pf *)data;
+	irqreturn_t ret = IRQ_HANDLED;
 	struct ice_hw *hw = &pf->hw;
 	struct device *dev;
 	u32 oicr, ena_mask;
@@ -3108,8 +3168,8 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 
 		/* we have a reset warning */
 		ena_mask &= ~PFINT_OICR_GRST_M;
-		reset = (rd32(hw, GLGEN_RSTAT) & GLGEN_RSTAT_RESET_TYPE_M) >>
-			GLGEN_RSTAT_RESET_TYPE_S;
+		reset = FIELD_GET(GLGEN_RSTAT_RESET_TYPE_M,
+				  rd32(hw, GLGEN_RSTAT));
 
 		if (reset == ICE_RESET_CORER)
 			pf->corer_count++;
@@ -3150,8 +3210,22 @@ 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 (!hw->reset_ongoing && ice_ptp_pf_handles_tx_interrupt(pf))
+		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;
+		}
 	}
 
 	if (oicr & PFINT_OICR_TSYN_EVNT_M) {
@@ -3167,7 +3241,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 					       GLTSYN_STAT_EVENT1_M |
 					       GLTSYN_STAT_EVENT2_M);
 
-			set_bit(ICE_MISC_THREAD_EXTTS_EVENT, pf->misc_thread);
+			ice_ptp_extts_event(pf);
 		}
 	}
 
@@ -3190,8 +3264,11 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 			set_bit(ICE_PFR_REQ, pf->state);
 		}
 	}
+	ice_service_task_schedule(pf);
+	if (ret == IRQ_HANDLED)
+		ice_irq_dynamic_ena(hw, NULL, NULL);
 
-	return IRQ_WAKE_THREAD;
+	return ret;
 }
 
 /**
@@ -3207,12 +3284,7 @@ static irqreturn_t ice_misc_intr_thread_fn(int __always_unused irq, void *data)
 	hw = &pf->hw;
 
 	if (ice_is_reset_in_progress(pf->state))
-		return IRQ_HANDLED;
-
-	ice_service_task_schedule(pf);
-
-	if (test_and_clear_bit(ICE_MISC_THREAD_EXTTS_EVENT, pf->misc_thread))
-		ice_ptp_extts_event(pf);
+		goto skip_irq;
 
 	if (test_and_clear_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread)) {
 		/* Process outstanding Tx timestamps. If there is more work,
@@ -3224,6 +3296,7 @@ static irqreturn_t ice_misc_intr_thread_fn(int __always_unused irq, void *data)
 		}
 	}
 
+skip_irq:
 	ice_irq_dynamic_ena(hw, NULL, NULL);
 
 	return IRQ_HANDLED;
@@ -3254,6 +3327,20 @@ static void ice_dis_ctrlq_interrupts(struct ice_hw *hw)
 }
 
 /**
+ * ice_free_irq_msix_ll_ts- Unroll ll_ts vector setup
+ * @pf: board private structure
+ */
+static void ice_free_irq_msix_ll_ts(struct ice_pf *pf)
+{
+	int irq_num = pf->ll_ts_irq.virq;
+
+	synchronize_irq(irq_num);
+	devm_free_irq(ice_pf_to_dev(pf), irq_num, pf);
+
+	ice_free_irq(pf, pf->ll_ts_irq);
+}
+
+/**
  * ice_free_irq_msix_misc - Unroll misc vector setup
  * @pf: board private structure
  */
@@ -3272,6 +3359,8 @@ static void ice_free_irq_msix_misc(struct ice_pf *pf)
 	devm_free_irq(ice_pf_to_dev(pf), misc_irq_num, pf);
 
 	ice_free_irq(pf, pf->oicr_irq);
+	if (pf->hw.dev_caps.ts_dev_info.ts_ll_int_read)
+		ice_free_irq_msix_ll_ts(pf);
 }
 
 /**
@@ -3297,10 +3386,12 @@ static void ice_ena_ctrlq_interrupts(struct ice_hw *hw, u16 reg_idx)
 	       PFINT_MBX_CTL_CAUSE_ENA_M);
 	wr32(hw, PFINT_MBX_CTL, val);
 
-	/* This enables Sideband queue Interrupt causes */
-	val = ((reg_idx & PFINT_SB_CTL_MSIX_INDX_M) |
-	       PFINT_SB_CTL_CAUSE_ENA_M);
-	wr32(hw, PFINT_SB_CTL, val);
+	if (!hw->dev_caps.ts_dev_info.ts_ll_int_read) {
+		/* enable Sideband queue Interrupt causes */
+		val = ((reg_idx & PFINT_SB_CTL_MSIX_INDX_M) |
+		       PFINT_SB_CTL_CAUSE_ENA_M);
+		wr32(hw, PFINT_SB_CTL, val);
+	}
 
 	ice_flush(hw);
 }
@@ -3317,13 +3408,17 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf)
 {
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_hw *hw = &pf->hw;
-	struct msi_map oicr_irq;
+	u32 pf_intr_start_offset;
+	struct msi_map irq;
 	int err = 0;
 
 	if (!pf->int_name[0])
 		snprintf(pf->int_name, sizeof(pf->int_name) - 1, "%s-%s:misc",
 			 dev_driver_string(dev), dev_name(dev));
 
+	if (!pf->int_name_ll_ts[0])
+		snprintf(pf->int_name_ll_ts, sizeof(pf->int_name_ll_ts) - 1,
+			 "%s-%s:ll_ts", dev_driver_string(dev), dev_name(dev));
 	/* Do not request IRQ but do enable OICR interrupt since settings are
 	 * lost during reset. Note that this function is called only during
 	 * rebuild path and not while reset is in progress.
@@ -3332,11 +3427,11 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf)
 		goto skip_req_irq;
 
 	/* reserve one vector in irq_tracker for misc interrupts */
-	oicr_irq = ice_alloc_irq(pf, false);
-	if (oicr_irq.index < 0)
-		return oicr_irq.index;
+	irq = ice_alloc_irq(pf, false);
+	if (irq.index < 0)
+		return irq.index;
 
-	pf->oicr_irq = oicr_irq;
+	pf->oicr_irq = irq;
 	err = devm_request_threaded_irq(dev, pf->oicr_irq.virq, ice_misc_intr,
 					ice_misc_intr_thread_fn, 0,
 					pf->int_name, pf);
@@ -3347,10 +3442,34 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf)
 		return err;
 	}
 
+	/* reserve one vector in irq_tracker for ll_ts interrupt */
+	if (!pf->hw.dev_caps.ts_dev_info.ts_ll_int_read)
+		goto skip_req_irq;
+
+	irq = ice_alloc_irq(pf, false);
+	if (irq.index < 0)
+		return irq.index;
+
+	pf->ll_ts_irq = irq;
+	err = devm_request_irq(dev, pf->ll_ts_irq.virq, ice_ll_ts_intr, 0,
+			       pf->int_name_ll_ts, pf);
+	if (err) {
+		dev_err(dev, "devm_request_irq for %s failed: %d\n",
+			pf->int_name_ll_ts, err);
+		ice_free_irq(pf, pf->ll_ts_irq);
+		return err;
+	}
+
 skip_req_irq:
 	ice_ena_misc_vector(pf);
 
 	ice_ena_ctrlq_interrupts(hw, pf->oicr_irq.index);
+	/* This enables LL TS interrupt */
+	pf_intr_start_offset = rd32(hw, PFINT_ALLOC) & PFINT_ALLOC_FIRST;
+	if (pf->hw.dev_caps.ts_dev_info.ts_ll_int_read)
+		wr32(hw, PFINT_SB_CTL,
+		     ((pf->ll_ts_irq.index + pf_intr_start_offset) &
+		      PFINT_SB_CTL_MSIX_INDX_M) | PFINT_SB_CTL_CAUSE_ENA_M);
 	wr32(hw, GLINT_ITR(ICE_RX_ITR, pf->oicr_irq.index),
 	     ITR_REG_ALIGN(ICE_ITR_8K) >> ICE_ITR_GRAN_S);
 
@@ -3375,9 +3494,11 @@ 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);
+	}
 }
 
 /**
@@ -3397,6 +3518,7 @@ static void ice_set_ops(struct ice_vsi *vsi)
 
 	netdev->netdev_ops = &ice_netdev_ops;
 	netdev->udp_tunnel_nic_info = &pf->hw.udp_tunnel_nic;
+	netdev->xdp_metadata_ops = &ice_xdp_md_ops;
 	ice_set_ethtool_ops(netdev);
 
 	if (vsi->type != ICE_VSI_PF)
@@ -4361,6 +4483,19 @@ static void ice_print_wake_reason(struct ice_pf *pf)
 }
 
 /**
+ * ice_pf_fwlog_update_module - update 1 module
+ * @pf: pointer to the PF struct
+ * @log_level: log_level to use for the @module
+ * @module: module to update
+ */
+void ice_pf_fwlog_update_module(struct ice_pf *pf, int log_level, int module)
+{
+	struct ice_hw *hw = &pf->hw;
+
+	hw->fwlog_cfg.module_entries[module].log_level = log_level;
+}
+
+/**
  * ice_register_netdev - register netdev
  * @vsi: pointer to the VSI struct
  */
@@ -4439,90 +4574,6 @@ static void ice_decfg_netdev(struct ice_vsi *vsi)
 	vsi->netdev = NULL;
 }
 
-static int ice_start_eth(struct ice_vsi *vsi)
-{
-	int err;
-
-	err = ice_init_mac_fltr(vsi->back);
-	if (err)
-		return err;
-
-	err = ice_vsi_open(vsi);
-	if (err)
-		ice_fltr_remove_all(vsi);
-
-	return err;
-}
-
-static void ice_stop_eth(struct ice_vsi *vsi)
-{
-	ice_fltr_remove_all(vsi);
-	ice_vsi_close(vsi);
-}
-
-static int ice_init_eth(struct ice_pf *pf)
-{
-	struct ice_vsi *vsi = ice_get_main_vsi(pf);
-	int err;
-
-	if (!vsi)
-		return -EINVAL;
-
-	/* init channel list */
-	INIT_LIST_HEAD(&vsi->ch_list);
-
-	err = ice_cfg_netdev(vsi);
-	if (err)
-		return err;
-	/* Setup DCB netlink interface */
-	ice_dcbnl_setup(vsi);
-
-	err = ice_init_mac_fltr(pf);
-	if (err)
-		goto err_init_mac_fltr;
-
-	err = ice_devlink_create_pf_port(pf);
-	if (err)
-		goto err_devlink_create_pf_port;
-
-	SET_NETDEV_DEVLINK_PORT(vsi->netdev, &pf->devlink_port);
-
-	err = ice_register_netdev(vsi);
-	if (err)
-		goto err_register_netdev;
-
-	err = ice_tc_indir_block_register(vsi);
-	if (err)
-		goto err_tc_indir_block_register;
-
-	ice_napi_add(vsi);
-
-	return 0;
-
-err_tc_indir_block_register:
-	ice_unregister_netdev(vsi);
-err_register_netdev:
-	ice_devlink_destroy_pf_port(pf);
-err_devlink_create_pf_port:
-err_init_mac_fltr:
-	ice_decfg_netdev(vsi);
-	return err;
-}
-
-static void ice_deinit_eth(struct ice_pf *pf)
-{
-	struct ice_vsi *vsi = ice_get_main_vsi(pf);
-
-	if (!vsi)
-		return;
-
-	ice_vsi_close(vsi);
-	ice_unregister_netdev(vsi);
-	ice_devlink_destroy_pf_port(pf);
-	ice_tc_indir_block_unregister(vsi);
-	ice_decfg_netdev(vsi);
-}
-
 /**
  * ice_wait_for_fw - wait for full FW readiness
  * @hw: pointer to the hardware structure
@@ -4548,7 +4599,7 @@ static int ice_wait_for_fw(struct ice_hw *hw, u32 timeout)
 	return -ETIMEDOUT;
 }
 
-static int ice_init_dev(struct ice_pf *pf)
+int ice_init_dev(struct ice_pf *pf)
 {
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_hw *hw = &pf->hw;
@@ -4641,7 +4692,7 @@ err_init_pf:
 	return err;
 }
 
-static void ice_deinit_dev(struct ice_pf *pf)
+void ice_deinit_dev(struct ice_pf *pf)
 {
 	ice_free_irq_msix_misc(pf);
 	ice_deinit_pf(pf);
@@ -4685,6 +4736,8 @@ static void ice_init_features(struct ice_pf *pf)
 
 	if (ice_init_lag(pf))
 		dev_warn(dev, "Failed to init link aggregation support\n");
+
+	ice_hwmon_init(pf);
 }
 
 static void ice_deinit_features(struct ice_pf *pf)
@@ -4702,6 +4755,8 @@ static void ice_deinit_features(struct ice_pf *pf)
 		ice_ptp_release(pf);
 	if (test_bit(ICE_FLAG_DPLL, pf->flags))
 		ice_dpll_deinit(pf);
+	if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV)
+		xa_destroy(&pf->eswitch.reprs);
 }
 
 static void ice_init_wakeup(struct ice_pf *pf)
@@ -4942,31 +4997,47 @@ static void ice_deinit(struct ice_pf *pf)
 /**
  * ice_load - load pf by init hw and starting VSI
  * @pf: pointer to the pf instance
+ *
+ * This function has to be called under devl_lock.
  */
 int ice_load(struct ice_pf *pf)
 {
-	struct ice_vsi_cfg_params params = {};
 	struct ice_vsi *vsi;
 	int err;
 
-	err = ice_init_dev(pf);
+	devl_assert_locked(priv_to_devlink(pf));
+
+	vsi = ice_get_main_vsi(pf);
+
+	/* init channel list */
+	INIT_LIST_HEAD(&vsi->ch_list);
+
+	err = ice_cfg_netdev(vsi);
 	if (err)
 		return err;
 
-	vsi = ice_get_main_vsi(pf);
+	/* Setup DCB netlink interface */
+	ice_dcbnl_setup(vsi);
 
-	params = ice_vsi_to_params(vsi);
-	params.flags = ICE_VSI_FLAG_INIT;
+	err = ice_init_mac_fltr(pf);
+	if (err)
+		goto err_init_mac_fltr;
 
-	rtnl_lock();
-	err = ice_vsi_cfg(vsi, &params);
+	err = ice_devlink_create_pf_port(pf);
 	if (err)
-		goto err_vsi_cfg;
+		goto err_devlink_create_pf_port;
 
-	err = ice_start_eth(ice_get_main_vsi(pf));
+	SET_NETDEV_DEVLINK_PORT(vsi->netdev, &pf->devlink_port);
+
+	err = ice_register_netdev(vsi);
+	if (err)
+		goto err_register_netdev;
+
+	err = ice_tc_indir_block_register(vsi);
 	if (err)
-		goto err_start_eth;
-	rtnl_unlock();
+		goto err_tc_indir_block_register;
+
+	ice_napi_add(vsi);
 
 	err = ice_init_rdma(pf);
 	if (err)
@@ -4980,29 +5051,35 @@ int ice_load(struct ice_pf *pf)
 	return 0;
 
 err_init_rdma:
-	ice_vsi_close(ice_get_main_vsi(pf));
-	rtnl_lock();
-err_start_eth:
-	ice_vsi_decfg(ice_get_main_vsi(pf));
-err_vsi_cfg:
-	rtnl_unlock();
-	ice_deinit_dev(pf);
+	ice_tc_indir_block_unregister(vsi);
+err_tc_indir_block_register:
+	ice_unregister_netdev(vsi);
+err_register_netdev:
+	ice_devlink_destroy_pf_port(pf);
+err_devlink_create_pf_port:
+err_init_mac_fltr:
+	ice_decfg_netdev(vsi);
 	return err;
 }
 
 /**
  * ice_unload - unload pf by stopping VSI and deinit hw
  * @pf: pointer to the pf instance
+ *
+ * This function has to be called under devl_lock.
  */
 void ice_unload(struct ice_pf *pf)
 {
+	struct ice_vsi *vsi = ice_get_main_vsi(pf);
+
+	devl_assert_locked(priv_to_devlink(pf));
+
 	ice_deinit_features(pf);
 	ice_deinit_rdma(pf);
-	rtnl_lock();
-	ice_stop_eth(ice_get_main_vsi(pf));
-	ice_vsi_decfg(ice_get_main_vsi(pf));
-	rtnl_unlock();
-	ice_deinit_dev(pf);
+	ice_tc_indir_block_unregister(vsi);
+	ice_unregister_netdev(vsi);
+	ice_devlink_destroy_pf_port(pf);
+	ice_decfg_netdev(vsi);
 }
 
 /**
@@ -5100,27 +5177,23 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 	if (err)
 		goto err_init;
 
-	err = ice_init_eth(pf);
+	devl_lock(priv_to_devlink(pf));
+	err = ice_load(pf);
+	devl_unlock(priv_to_devlink(pf));
 	if (err)
-		goto err_init_eth;
-
-	err = ice_init_rdma(pf);
-	if (err)
-		goto err_init_rdma;
+		goto err_load;
 
 	err = ice_init_devlink(pf);
 	if (err)
 		goto err_init_devlink;
 
-	ice_init_features(pf);
-
 	return 0;
 
 err_init_devlink:
-	ice_deinit_rdma(pf);
-err_init_rdma:
-	ice_deinit_eth(pf);
-err_init_eth:
+	devl_lock(priv_to_devlink(pf));
+	ice_unload(pf);
+	devl_unlock(priv_to_devlink(pf));
+err_load:
 	ice_deinit(pf);
 err_init:
 	pci_disable_device(pdev);
@@ -5208,18 +5281,22 @@ static void ice_remove(struct pci_dev *pdev)
 		ice_free_vfs(pf);
 	}
 
+	ice_hwmon_exit(pf);
+
 	ice_service_task_stop(pf);
 	ice_aq_cancel_waiting_tasks(pf);
 	set_bit(ICE_DOWN, pf->state);
 
 	if (!ice_is_safe_mode(pf))
 		ice_remove_arfs(pf);
-	ice_deinit_features(pf);
+
 	ice_deinit_devlink(pf);
-	ice_deinit_rdma(pf);
-	ice_deinit_eth(pf);
-	ice_deinit(pf);
 
+	devl_lock(priv_to_devlink(pf));
+	ice_unload(pf);
+	devl_unlock(priv_to_devlink(pf));
+
+	ice_deinit(pf);
 	ice_vsi_release_all(pf);
 
 	ice_setup_mc_magic_wake(pf);
@@ -5306,6 +5383,7 @@ static int ice_reinit_interrupt_scheme(struct ice_pf *pf)
 		if (ret)
 			goto err_reinit;
 		ice_vsi_map_rings_to_vectors(pf->vsi[v]);
+		ice_vsi_set_napi_queues(pf->vsi[v]);
 	}
 
 	ret = ice_req_irq_msix_misc(pf);
@@ -5611,6 +5689,10 @@ static const struct pci_device_id ice_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_1GBE) },
 	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_QSFP) },
 	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E822_SI_DFLT) },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E825C_BACKPLANE), },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E825C_QSFP), },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E825C_SFP), },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E825C_SGMII), },
 	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_BACKPLANE) },
 	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_QSFP56) },
 	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_SFP) },
@@ -5672,6 +5754,8 @@ static int __init ice_module_init(void)
 		goto err_dest_wq;
 	}
 
+	ice_debugfs_init();
+
 	status = pci_register_driver(&ice_driver);
 	if (status) {
 		pr_err("failed to register PCI driver, err %d\n", status);
@@ -5682,6 +5766,7 @@ static int __init ice_module_init(void)
 
 err_dest_lag_wq:
 	destroy_workqueue(ice_lag_wq);
+	ice_debugfs_exit();
 err_dest_wq:
 	destroy_workqueue(ice_wq);
 	return status;
@@ -5697,6 +5782,7 @@ module_init(ice_module_init);
 static void __exit ice_module_exit(void)
 {
 	pci_unregister_driver(&ice_driver);
+	ice_debugfs_exit();
 	destroy_workqueue(ice_wq);
 	destroy_workqueue(ice_lag_wq);
 	pr_info("module unloaded\n");
@@ -6041,6 +6127,23 @@ ice_fix_features(struct net_device *netdev, netdev_features_t features)
 }
 
 /**
+ * ice_set_rx_rings_vlan_proto - update rings with new stripped VLAN proto
+ * @vsi: PF's VSI
+ * @vlan_ethertype: VLAN ethertype (802.1Q or 802.1ad) in network byte order
+ *
+ * Store current stripped VLAN proto in ring packet context,
+ * so it can be accessed more efficiently by packet processing code.
+ */
+static void
+ice_set_rx_rings_vlan_proto(struct ice_vsi *vsi, __be16 vlan_ethertype)
+{
+	u16 i;
+
+	ice_for_each_alloc_rxq(vsi, i)
+		vsi->rx_rings[i]->pkt_ctx.vlan_proto = vlan_ethertype;
+}
+
+/**
  * ice_set_vlan_offload_features - set VLAN offload features for the PF VSI
  * @vsi: PF's VSI
  * @features: features used to determine VLAN offload settings
@@ -6082,6 +6185,9 @@ ice_set_vlan_offload_features(struct ice_vsi *vsi, netdev_features_t features)
 	if (strip_err || insert_err)
 		return -EIO;
 
+	ice_set_rx_rings_vlan_proto(vsi, enable_stripping ?
+				    htons(vlan_ethertype) : 0);
+
 	return 0;
 }
 
@@ -6670,13 +6776,11 @@ void ice_update_vsi_stats(struct ice_vsi *vsi)
 		cur_ns->rx_crc_errors = pf->stats.crc_errors;
 		cur_ns->rx_errors = pf->stats.crc_errors +
 				    pf->stats.illegal_bytes +
-				    pf->stats.rx_len_errors +
 				    pf->stats.rx_undersize +
 				    pf->hw_csum_rx_error +
 				    pf->stats.rx_jabber +
 				    pf->stats.rx_fragments +
 				    pf->stats.rx_oversize;
-		cur_ns->rx_length_errors = pf->stats.rx_len_errors;
 		/* record drops from the port level */
 		cur_ns->rx_missed_errors = pf->stats.eth.rx_discards;
 	}
@@ -6816,9 +6920,6 @@ void ice_update_pf_stats(struct ice_pf *pf)
 			  &prev_ps->mac_remote_faults,
 			  &cur_ps->mac_remote_faults);
 
-	ice_stat_update32(hw, GLPRT_RLEC(port), pf->stat_prev_loaded,
-			  &prev_ps->rx_len_errors, &cur_ps->rx_len_errors);
-
 	ice_stat_update32(hw, GLPRT_RUC(port), pf->stat_prev_loaded,
 			  &prev_ps->rx_undersize, &cur_ps->rx_undersize);
 
@@ -6901,6 +7002,50 @@ static void ice_napi_disable_all(struct ice_vsi *vsi)
 }
 
 /**
+ * ice_vsi_dis_irq - Mask off queue interrupt generation on the VSI
+ * @vsi: the VSI being un-configured
+ */
+static void ice_vsi_dis_irq(struct ice_vsi *vsi)
+{
+	struct ice_pf *pf = vsi->back;
+	struct ice_hw *hw = &pf->hw;
+	u32 val;
+	int i;
+
+	/* disable interrupt causation from each Rx queue; Tx queues are
+	 * handled in ice_vsi_stop_tx_ring()
+	 */
+	if (vsi->rx_rings) {
+		ice_for_each_rxq(vsi, i) {
+			if (vsi->rx_rings[i]) {
+				u16 reg;
+
+				reg = vsi->rx_rings[i]->reg_idx;
+				val = rd32(hw, QINT_RQCTL(reg));
+				val &= ~QINT_RQCTL_CAUSE_ENA_M;
+				wr32(hw, QINT_RQCTL(reg), val);
+			}
+		}
+	}
+
+	/* disable each interrupt */
+	ice_for_each_q_vector(vsi, i) {
+		if (!vsi->q_vectors[i])
+			continue;
+		wr32(hw, GLINT_DYN_CTL(vsi->q_vectors[i]->reg_idx), 0);
+	}
+
+	ice_flush(hw);
+
+	/* don't call synchronize_irq() for VF's from the host */
+	if (vsi->type == ICE_VSI_VF)
+		return;
+
+	ice_for_each_q_vector(vsi, i)
+		synchronize_irq(vsi->q_vectors[i]->irq.virq);
+}
+
+/**
  * ice_down - Shutdown the connection
  * @vsi: The VSI being stopped
  *
@@ -7389,7 +7534,7 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 	 * fail.
 	 */
 	if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags))
-		ice_ptp_reset(pf);
+		ice_ptp_rebuild(pf, reset_type);
 
 	if (ice_is_feature_supported(pf, ICE_F_GNSS))
 		ice_gnss_init(pf);
@@ -7401,18 +7546,9 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 		goto err_vsi_rebuild;
 	}
 
-	/* configure PTP timestamping after VSI rebuild */
-	if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) {
-		if (pf->ptp.tx_interrupt_mode == ICE_PTP_TX_INTERRUPT_SELF)
-			ice_ptp_cfg_timestamp(pf, false);
-		else if (pf->ptp.tx_interrupt_mode == ICE_PTP_TX_INTERRUPT_ALL)
-			/* for E82x PHC owner always need to have interrupts */
-			ice_ptp_cfg_timestamp(pf, true);
-	}
-
-	err = ice_vsi_rebuild_by_type(pf, ICE_VSI_SWITCHDEV_CTRL);
+	err = ice_eswitch_rebuild(pf);
 	if (err) {
-		dev_err(dev, "Switchdev CTRL VSI rebuild failed: %d\n", err);
+		dev_err(dev, "Switchdev rebuild failed: %d\n", err);
 		goto err_vsi_rebuild;
 	}
 
@@ -7461,6 +7597,9 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 	ice_plug_aux_dev(pf);
 	if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG))
 		ice_lag_rebuild(pf);
+
+	/* Restore timestamp mode settings after VSI rebuild */
+	ice_ptp_restore_timestamp_mode(pf);
 	return;
 
 err_vsi_rebuild:
@@ -7710,6 +7849,59 @@ int ice_get_rss_key(struct ice_vsi *vsi, u8 *seed)
 }
 
 /**
+ * ice_set_rss_hfunc - Set RSS HASH function
+ * @vsi: Pointer to VSI structure
+ * @hfunc: hash function (ICE_AQ_VSI_Q_OPT_RSS_*)
+ *
+ * Returns 0 on success, negative on failure
+ */
+int ice_set_rss_hfunc(struct ice_vsi *vsi, u8 hfunc)
+{
+	struct ice_hw *hw = &vsi->back->hw;
+	struct ice_vsi_ctx *ctx;
+	bool symm;
+	int err;
+
+	if (hfunc == vsi->rss_hfunc)
+		return 0;
+
+	if (hfunc != ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ &&
+	    hfunc != ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ)
+		return -EOPNOTSUPP;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_Q_OPT_VALID);
+	ctx->info.q_opt_rss = vsi->info.q_opt_rss;
+	ctx->info.q_opt_rss &= ~ICE_AQ_VSI_Q_OPT_RSS_HASH_M;
+	ctx->info.q_opt_rss |=
+		FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_HASH_M, hfunc);
+	ctx->info.q_opt_tc = vsi->info.q_opt_tc;
+	ctx->info.q_opt_flags = vsi->info.q_opt_rss;
+
+	err = ice_update_vsi(hw, vsi->idx, ctx, NULL);
+	if (err) {
+		dev_err(ice_pf_to_dev(vsi->back), "Failed to configure RSS hash for VSI %d, error %d\n",
+			vsi->vsi_num, err);
+	} else {
+		vsi->info.q_opt_rss = ctx->info.q_opt_rss;
+		vsi->rss_hfunc = hfunc;
+		netdev_info(vsi->netdev, "Hash function set to: %sToeplitz\n",
+			    hfunc == ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ ?
+			    "Symmetric " : "");
+	}
+	kfree(ctx);
+	if (err)
+		return err;
+
+	/* Fix the symmetry setting for all existing RSS configurations */
+	symm = !!(hfunc == ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ);
+	return ice_set_rss_cfg_symm(hw, vsi, symm);
+}
+
+/**
  * ice_bridge_getlink - Get the hardware bridge mode
  * @skb: skb buff
  * @pid: process ID
@@ -7806,6 +7998,8 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
 	pf_sw = pf->first_sw;
 	/* find the attribute in the netlink message */
 	br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
+	if (!br_spec)
+		return -EINVAL;
 
 	nla_for_each_nested(attr, br_spec, rem) {
 		__u16 mode;
@@ -7895,8 +8089,8 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 		struct ice_hw *hw = &pf->hw;
 		u32 head, val = 0;
 
-		head = (rd32(hw, QTX_COMM_HEAD(vsi->txq_map[txqueue])) &
-			QTX_COMM_HEAD_HEAD_M) >> QTX_COMM_HEAD_HEAD_S;
+		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));
 
@@ -8144,13 +8338,12 @@ static int ice_add_vsi_to_fdir(struct ice_pf *pf, struct ice_vsi *vsi)
 
 		for (tun = 0; tun < ICE_FD_HW_SEG_MAX; tun++) {
 			enum ice_flow_priority prio;
-			u64 prof_id;
 
 			/* add this VSI to FDir profile for this flow */
 			prio = ICE_FLOW_PRIO_NORMAL;
 			prof = hw->fdir_prof[flow];
-			prof_id = flow + tun * ICE_FLTR_PTYPE_MAX;
-			status = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id,
+			status = ice_flow_add_entry(hw, ICE_BLK_FD,
+						    prof->prof_id[tun],
 						    prof->vsi_h[0], vsi->idx,
 						    prio, prof->fdir_seg[tun],
 						    &entry_h);
@@ -9193,8 +9386,14 @@ int ice_stop(struct net_device *netdev)
 		int link_err = ice_force_phys_link_state(vsi, false);
 
 		if (link_err) {
-			netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n",
-				   vsi->vsi_num, link_err);
+			if (link_err == -ENOMEDIUM)
+				netdev_info(vsi->netdev, "Skipping link reconfig - no media attached, VSI %d\n",
+					    vsi->vsi_num);
+			else
+				netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n",
+					   vsi->vsi_num, link_err);
+
+			ice_vsi_close(vsi);
 			return -EIO;
 		}
 	}