1 files changed, 73 insertions, 304 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index a1f7c8edc22f..93979ab18bc1 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2490,7 +2490,6 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
 {
 	int q_vectors = vsi->num_q_vectors;
 	struct ice_pf *pf = vsi->back;
-	int base = vsi->base_vector;
 	struct device *dev;
 	int rx_int_idx = 0;
 	int tx_int_idx = 0;
@@ -2501,7 +2500,7 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
 	for (vector = 0; vector < q_vectors; vector++) {
 		struct ice_q_vector *q_vector = vsi->q_vectors[vector];
 
-		irq_num = pf->msix_entries[base + vector].vector;
+		irq_num = q_vector->irq.virq;
 
 		if (q_vector->tx.tx_ring && q_vector->rx.rx_ring) {
 			snprintf(q_vector->name, sizeof(q_vector->name) - 1,
@@ -2555,9 +2554,8 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
 	return 0;
 
 free_q_irqs:
-	while (vector) {
-		vector--;
-		irq_num = pf->msix_entries[base + vector].vector;
+	while (vector--) {
+		irq_num = vsi->q_vectors[vector]->irq.virq;
 		if (!IS_ENABLED(CONFIG_RFS_ACCEL))
 			irq_set_affinity_notifier(irq_num, NULL);
 		irq_set_affinity_hint(irq_num, NULL);
@@ -2635,11 +2633,11 @@ static void ice_vsi_assign_bpf_prog(struct ice_vsi *vsi, struct bpf_prog *prog)
 	int i;
 
 	old_prog = xchg(&vsi->xdp_prog, prog);
-	if (old_prog)
-		bpf_prog_put(old_prog);
-
 	ice_for_each_rxq(vsi, i)
 		WRITE_ONCE(vsi->rx_rings[i]->xdp_prog, vsi->xdp_prog);
+
+	if (old_prog)
+		bpf_prog_put(old_prog);
 }
 
 /**
@@ -2924,6 +2922,12 @@ 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) {
+		ice_vsi_assign_bpf_prog(vsi, prog);
+		return 0;
+	}
+
 	/* need to stop netdev while setting up the program for Rx rings */
 	if (if_running && !test_and_set_bit(ICE_VSI_DOWN, vsi->state)) {
 		ret = ice_down(vsi);
@@ -2956,13 +2960,6 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
 		xdp_ring_err = ice_realloc_zc_buf(vsi, false);
 		if (xdp_ring_err)
 			NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Rx resources failed");
-	} else {
-		/* safe to call even when prog == vsi->xdp_prog as
-		 * dev_xdp_install in net/core/dev.c incremented prog's
-		 * refcount so corresponding bpf_prog_put won't cause
-		 * underflow
-		 */
-		ice_vsi_assign_bpf_prog(vsi, prog);
 	}
 
 	if (if_running)
@@ -3047,7 +3044,7 @@ static void ice_ena_misc_vector(struct ice_pf *pf)
 	wr32(hw, PFINT_OICR_ENA, val);
 
 	/* SW_ITR_IDX = 0, but don't change INTENA */
-	wr32(hw, GLINT_DYN_CTL(pf->oicr_idx),
+	wr32(hw, GLINT_DYN_CTL(pf->oicr_irq.index),
 	     GLINT_DYN_CTL_SW_ITR_INDX_M | GLINT_DYN_CTL_INTENA_MSK_M);
 }
 
@@ -3060,7 +3057,6 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 {
 	struct ice_pf *pf = (struct ice_pf *)data;
 	struct ice_hw *hw = &pf->hw;
-	irqreturn_t ret = IRQ_NONE;
 	struct device *dev;
 	u32 oicr, ena_mask;
 
@@ -3142,19 +3138,24 @@ 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)
-			ret = IRQ_WAKE_THREAD;
+			set_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread);
 	}
 
 	if (oicr & PFINT_OICR_TSYN_EVNT_M) {
 		u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
 		u32 gltsyn_stat = rd32(hw, GLTSYN_STAT(tmr_idx));
 
-		/* Save EVENTs from GTSYN register */
-		pf->ptp.ext_ts_irq |= gltsyn_stat & (GLTSYN_STAT_EVENT0_M |
-						     GLTSYN_STAT_EVENT1_M |
-						     GLTSYN_STAT_EVENT2_M);
 		ena_mask &= ~PFINT_OICR_TSYN_EVNT_M;
-		kthread_queue_work(pf->ptp.kworker, &pf->ptp.extts_work);
+
+		if (hw->func_caps.ts_func_info.src_tmr_owned) {
+			/* Save EVENTs from GLTSYN register */
+			pf->ptp.ext_ts_irq |= gltsyn_stat &
+					      (GLTSYN_STAT_EVENT0_M |
+					       GLTSYN_STAT_EVENT1_M |
+					       GLTSYN_STAT_EVENT2_M);
+
+			set_bit(ICE_MISC_THREAD_EXTTS_EVENT, pf->misc_thread);
+		}
 	}
 
 #define ICE_AUX_CRIT_ERR (PFINT_OICR_PE_CRITERR_M | PFINT_OICR_HMC_ERR_M | PFINT_OICR_PE_PUSH_M)
@@ -3174,16 +3175,10 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 		if (oicr & (PFINT_OICR_PCI_EXCEPTION_M |
 			    PFINT_OICR_ECC_ERR_M)) {
 			set_bit(ICE_PFR_REQ, pf->state);
-			ice_service_task_schedule(pf);
 		}
 	}
-	if (!ret)
-		ret = IRQ_HANDLED;
-
-	ice_service_task_schedule(pf);
-	ice_irq_dynamic_ena(hw, NULL, NULL);
 
-	return ret;
+	return IRQ_WAKE_THREAD;
 }
 
 /**
@@ -3194,12 +3189,29 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 static irqreturn_t ice_misc_intr_thread_fn(int __always_unused irq, void *data)
 {
 	struct ice_pf *pf = data;
+	struct ice_hw *hw;
+
+	hw = &pf->hw;
 
 	if (ice_is_reset_in_progress(pf->state))
 		return IRQ_HANDLED;
 
-	while (!ice_ptp_process_ts(pf))
-		usleep_range(50, 100);
+	ice_service_task_schedule(pf);
+
+	if (test_and_clear_bit(ICE_MISC_THREAD_EXTTS_EVENT, pf->misc_thread))
+		ice_ptp_extts_event(pf);
+
+	if (test_and_clear_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread)) {
+		/* Process outstanding Tx timestamps. If there is more work,
+		 * re-arm the interrupt to trigger again.
+		 */
+		if (ice_ptp_process_ts(pf) == ICE_TX_TSTAMP_WORK_PENDING) {
+			wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M);
+			ice_flush(hw);
+		}
+	}
+
+	ice_irq_dynamic_ena(hw, NULL, NULL);
 
 	return IRQ_HANDLED;
 }
@@ -3234,6 +3246,7 @@ static void ice_dis_ctrlq_interrupts(struct ice_hw *hw)
  */
 static void ice_free_irq_msix_misc(struct ice_pf *pf)
 {
+	int misc_irq_num = pf->oicr_irq.virq;
 	struct ice_hw *hw = &pf->hw;
 
 	ice_dis_ctrlq_interrupts(hw);
@@ -3242,14 +3255,10 @@ static void ice_free_irq_msix_misc(struct ice_pf *pf)
 	wr32(hw, PFINT_OICR_ENA, 0);
 	ice_flush(hw);
 
-	if (pf->msix_entries) {
-		synchronize_irq(pf->msix_entries[pf->oicr_idx].vector);
-		devm_free_irq(ice_pf_to_dev(pf),
-			      pf->msix_entries[pf->oicr_idx].vector, pf);
-	}
+	synchronize_irq(misc_irq_num);
+	devm_free_irq(ice_pf_to_dev(pf), misc_irq_num, pf);
 
-	pf->num_avail_sw_msix += 1;
-	ice_free_res(pf->irq_tracker, pf->oicr_idx, ICE_RES_MISC_VEC_ID);
+	ice_free_irq(pf, pf->oicr_irq);
 }
 
 /**
@@ -3295,7 +3304,8 @@ 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;
-	int oicr_idx, err = 0;
+	struct msi_map oicr_irq;
+	int err = 0;
 
 	if (!pf->int_name[0])
 		snprintf(pf->int_name, sizeof(pf->int_name) - 1, "%s-%s:misc",
@@ -3309,30 +3319,26 @@ 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_idx = ice_get_res(pf, pf->irq_tracker, 1, ICE_RES_MISC_VEC_ID);
-	if (oicr_idx < 0)
-		return oicr_idx;
-
-	pf->num_avail_sw_msix -= 1;
-	pf->oicr_idx = (u16)oicr_idx;
-
-	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);
+	oicr_irq = ice_alloc_irq(pf, false);
+	if (oicr_irq.index < 0)
+		return oicr_irq.index;
+
+	pf->oicr_irq = oicr_irq;
+	err = devm_request_threaded_irq(dev, pf->oicr_irq.virq, ice_misc_intr,
+					ice_misc_intr_thread_fn, 0,
+					pf->int_name, pf);
 	if (err) {
 		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;
+		ice_free_irq(pf, pf->oicr_irq);
 		return err;
 	}
 
 skip_req_irq:
 	ice_ena_misc_vector(pf);
 
-	ice_ena_ctrlq_interrupts(hw, pf->oicr_idx);
-	wr32(hw, GLINT_ITR(ICE_RX_ITR, pf->oicr_idx),
+	ice_ena_ctrlq_interrupts(hw, pf->oicr_irq.index);
+	wr32(hw, GLINT_ITR(ICE_RX_ITR, pf->oicr_irq.index),
 	     ITR_REG_ALIGN(ICE_ITR_8K) >> ICE_ITR_GRAN_S);
 
 	ice_flush(hw);
@@ -3901,224 +3907,6 @@ 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 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, hw_num_msix, v_other, v_wanted, v_actual;
-	struct device *dev = ice_pf_to_dev(pf);
-	int err, i;
-
-	hw_num_msix = pf->hw.func_caps.common_cap.num_msix_vectors;
-	num_cpus = num_online_cpus();
-
-	/* LAN miscellaneous handler */
-	v_other = ICE_MIN_LAN_OICR_MSIX;
-
-	/* 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)) {
-		pf->num_rdma_msix = num_cpus + ICE_RDMA_NUM_AEQ_MSIX;
-		v_wanted += pf->num_rdma_msix;
-	}
-
-	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_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_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_wanted) {
-		dev_warn(dev, "not enough OS MSI-X vectors. requested = %d, obtained = %d\n",
-			 v_wanted, v_actual);
-
-		if (v_actual < ICE_MIN_MSIX) {
-			/* error if we can't get minimum vectors */
-			pci_disable_msix(pf->pdev);
-			err = -ERANGE;
-			goto msix_err;
-		} else {
-			int v_remain = v_actual - v_other;
-
-			if (v_remain < ICE_MIN_LAN_TXRX_MSIX)
-				v_remain = ICE_MIN_LAN_TXRX_MSIX;
-
-			ice_reduce_msix_usage(pf, v_remain);
-
-			dev_notice(dev, "Enabled %d MSI-X vectors for LAN traffic.\n",
-				   pf->num_lan_msix);
-
-			if (ice_is_rdma_ena(pf))
-				dev_notice(dev, "Enabled %d MSI-X vectors for RDMA.\n",
-					   pf->num_rdma_msix);
-		}
-	}
-
-	return v_actual;
-
-msix_err:
-	devm_kfree(dev, pf->msix_entries);
-
-exit_err:
-	pf->num_rdma_msix = 0;
-	pf->num_lan_msix = 0;
-	return err;
-}
-
-/**
- * ice_dis_msix - Disable MSI-X interrupt setup in OS
- * @pf: board private structure
- */
-static void ice_dis_msix(struct ice_pf *pf)
-{
-	pci_disable_msix(pf->pdev);
-	devm_kfree(ice_pf_to_dev(pf), pf->msix_entries);
-	pf->msix_entries = NULL;
-}
-
-/**
- * ice_clear_interrupt_scheme - Undo things done by ice_init_interrupt_scheme
- * @pf: board private structure
- */
-static void ice_clear_interrupt_scheme(struct ice_pf *pf)
-{
-	ice_dis_msix(pf);
-
-	if (pf->irq_tracker) {
-		devm_kfree(ice_pf_to_dev(pf), pf->irq_tracker);
-		pf->irq_tracker = NULL;
-	}
-}
-
-/**
- * ice_init_interrupt_scheme - Determine proper interrupt scheme
- * @pf: board private structure to initialize
- */
-static int ice_init_interrupt_scheme(struct ice_pf *pf)
-{
-	int vectors;
-
-	vectors = ice_ena_msix_range(pf);
-
-	if (vectors < 0)
-		return vectors;
-
-	/* set up vector assignment tracking */
-	pf->irq_tracker = devm_kzalloc(ice_pf_to_dev(pf),
-				       struct_size(pf->irq_tracker, list, vectors),
-				       GFP_KERNEL);
-	if (!pf->irq_tracker) {
-		ice_dis_msix(pf);
-		return -ENOMEM;
-	}
-
-	/* populate SW interrupts pool with number of OS granted IRQs. */
-	pf->num_avail_sw_msix = (u16)vectors;
-	pf->irq_tracker->num_entries = (u16)vectors;
-	pf->irq_tracker->end = pf->irq_tracker->num_entries;
-
-	return 0;
-}
-
-/**
  * ice_is_wol_supported - check if WoL is supported
  * @hw: pointer to hardware info
  *
@@ -4802,9 +4590,13 @@ err_init_pf:
 static void ice_deinit_dev(struct ice_pf *pf)
 {
 	ice_free_irq_msix_misc(pf);
-	ice_clear_interrupt_scheme(pf);
 	ice_deinit_pf(pf);
 	ice_deinit_hw(&pf->hw);
+
+	/* Service task is already stopped, so call reset directly. */
+	ice_reset(&pf->hw, ICE_RESET_PFR);
+	pci_wait_for_pending_transaction(pf->pdev);
+	ice_clear_interrupt_scheme(pf);
 }
 
 static void ice_init_features(struct ice_pf *pf)
@@ -5094,10 +4886,6 @@ int ice_load(struct ice_pf *pf)
 	struct ice_vsi *vsi;
 	int err;
 
-	err = ice_reset(&pf->hw, ICE_RESET_PFR);
-	if (err)
-		return err;
-
 	err = ice_init_dev(pf);
 	if (err)
 		return err;
@@ -5354,12 +5142,6 @@ static void ice_remove(struct pci_dev *pdev)
 	ice_setup_mc_magic_wake(pf);
 	ice_set_wake(pf);
 
-	/* Issue a PFR as part of the prescribed driver unload flow.  Do not
-	 * do it via ice_schedule_reset() since there is no need to rebuild
-	 * and the service task is already stopped.
-	 */
-	ice_reset(&pf->hw, ICE_RESET_PFR);
-	pci_wait_for_pending_transaction(pdev);
 	pci_disable_device(pdev);
 }
 
@@ -5841,11 +5623,6 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi)
 	if (!is_valid_ether_addr(mac))
 		return -EADDRNOTAVAIL;
 
-	if (ether_addr_equal(netdev->dev_addr, mac)) {
-		netdev_dbg(netdev, "already using mac %pM\n", mac);
-		return 0;
-	}
-
 	if (test_bit(ICE_DOWN, pf->state) ||
 	    ice_is_reset_in_progress(pf->state)) {
 		netdev_err(netdev, "can't set mac %pM. device not ready\n",
@@ -7056,6 +6833,10 @@ 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))
+		ice_for_each_xdp_txq(vsi, i)
+			ice_clean_tx_ring(vsi->xdp_rings[i]);
+
 	ice_for_each_rxq(vsi, i)
 		ice_clean_rx_ring(vsi->rx_rings[i]);
 
@@ -7631,21 +7412,9 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu)
 	}
 
 	netdev->mtu = (unsigned int)new_mtu;
-
-	/* if VSI is up, bring it down and then back up */
-	if (!test_and_set_bit(ICE_VSI_DOWN, vsi->state)) {
-		err = ice_down(vsi);
-		if (err) {
-			netdev_err(netdev, "change MTU if_down err %d\n", err);
-			return err;
-		}
-
-		err = ice_up(vsi);
-		if (err) {
-			netdev_err(netdev, "change MTU if_up err %d\n", err);
-			return err;
-		}
-	}
+	err = ice_down_up(vsi);
+	if (err)
+		return err;
 
 	netdev_dbg(netdev, "changed MTU to %d\n", new_mtu);
 	set_bit(ICE_FLAG_MTU_CHANGED, pf->flags);