Merge branch 'intel-wired-lan-driver-updates-2024-05-28-e1000e-i40e-ice'

Jacob Keller says:

====================
Intel Wired LAN Driver Updates 2024-05-28 (e1000e, i40e, ice) [part]

This series includes a variety of fixes that have been accumulating on the
Intel Wired LAN dev-queue.

Hui Wang provides a fix for suspend/resume on e1000e due to failure
to correctly setup the SMBUS in enable_ulp().

Thinh Tran provides a fix for EEH I/O suspend/resume on i40e to
ensure that I/O operations can continue after a resume. To avoid duplicate
code, the common logic is factored out of i40e_suspend and i40e_resume.

Paul Greenwalt provides a fix to correctly map the 200G PHY types to link
speeds in the ice driver.

Dave Ertman provides a fix correcting devlink parameter unregistration in
the event that the driver loads in safe mode and some of the parameters
were not registered.
====================

Link: https://lore.kernel.org/r/20240528-net-2024-05-28-intel-net-fixes-v1-0-dc8593d2bbc6@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

5 files changed, 195 insertions, 144 deletions

diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index f9e94be36e97..2e98a2a0bead 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -1225,6 +1225,28 @@ s32 e1000_enable_ulp_lpt_lp(struct e1000_hw *hw, bool to_sx)
 	}
 
 release:
+	/* Switching PHY interface always returns MDI error
+	 * so disable retry mechanism to avoid wasting time
+	 */
+	e1000e_disable_phy_retry(hw);
+
+	/* Force SMBus mode in PHY */
+	ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &phy_reg);
+	if (ret_val) {
+		e1000e_enable_phy_retry(hw);
+		hw->phy.ops.release(hw);
+		goto out;
+	}
+	phy_reg |= CV_SMB_CTRL_FORCE_SMBUS;
+	e1000_write_phy_reg_hv_locked(hw, CV_SMB_CTRL, phy_reg);
+
+	e1000e_enable_phy_retry(hw);
+
+	/* Force SMBus mode in MAC */
+	mac_reg = er32(CTRL_EXT);
+	mac_reg |= E1000_CTRL_EXT_FORCE_SMBUS;
+	ew32(CTRL_EXT, mac_reg);
+
 	hw->phy.ops.release(hw);
 out:
 	if (ret_val)
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 220d62fca55d..da5c59daf8ba 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -6623,7 +6623,6 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
 	struct e1000_hw *hw = &adapter->hw;
 	u32 ctrl, ctrl_ext, rctl, status, wufc;
 	int retval = 0;
-	u16 smb_ctrl;
 
 	/* Runtime suspend should only enable wakeup for link changes */
 	if (runtime)
@@ -6697,23 +6696,6 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
 			if (retval)
 				return retval;
 		}
-
-		/* Force SMBUS to allow WOL */
-		/* Switching PHY interface always returns MDI error
-		 * so disable retry mechanism to avoid wasting time
-		 */
-		e1000e_disable_phy_retry(hw);
-
-		e1e_rphy(hw, CV_SMB_CTRL, &smb_ctrl);
-		smb_ctrl |= CV_SMB_CTRL_FORCE_SMBUS;
-		e1e_wphy(hw, CV_SMB_CTRL, smb_ctrl);
-
-		e1000e_enable_phy_retry(hw);
-
-		/* Force SMBus mode in MAC */
-		ctrl_ext = er32(CTRL_EXT);
-		ctrl_ext |= E1000_CTRL_EXT_FORCE_SMBUS;
-		ew32(CTRL_EXT, ctrl_ext);
 	}
 
 	/* Ensure that the appropriate bits are set in LPI_CTRL
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 1f188c052828..284c3fad5a6e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -11171,6 +11171,8 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit,
 	ret = i40e_reset(pf);
 	if (!ret)
 		i40e_rebuild(pf, reinit, lock_acquired);
+	else
+		dev_err(&pf->pdev->dev, "%s: i40e_reset() FAILED", __func__);
 }
 
 /**
@@ -16335,6 +16337,139 @@ unmap:
 }
 
 /**
+ * i40e_enable_mc_magic_wake - enable multicast magic packet wake up
+ * using the mac_address_write admin q function
+ * @pf: pointer to i40e_pf struct
+ **/
+static void i40e_enable_mc_magic_wake(struct i40e_pf *pf)
+{
+	struct i40e_vsi *main_vsi = i40e_pf_get_main_vsi(pf);
+	struct i40e_hw *hw = &pf->hw;
+	u8 mac_addr[6];
+	u16 flags = 0;
+	int ret;
+
+	/* Get current MAC address in case it's an LAA */
+	if (main_vsi && main_vsi->netdev) {
+		ether_addr_copy(mac_addr, main_vsi->netdev->dev_addr);
+	} else {
+		dev_err(&pf->pdev->dev,
+			"Failed to retrieve MAC address; using default\n");
+		ether_addr_copy(mac_addr, hw->mac.addr);
+	}
+
+	/* The FW expects the mac address write cmd to first be called with
+	 * one of these flags before calling it again with the multicast
+	 * enable flags.
+	 */
+	flags = I40E_AQC_WRITE_TYPE_LAA_WOL;
+
+	if (hw->func_caps.flex10_enable && hw->partition_id != 1)
+		flags = I40E_AQC_WRITE_TYPE_LAA_ONLY;
+
+	ret = i40e_aq_mac_address_write(hw, flags, mac_addr, NULL);
+	if (ret) {
+		dev_err(&pf->pdev->dev,
+			"Failed to update MAC address registers; cannot enable Multicast Magic packet wake up");
+		return;
+	}
+
+	flags = I40E_AQC_MC_MAG_EN
+			| I40E_AQC_WOL_PRESERVE_ON_PFR
+			| I40E_AQC_WRITE_TYPE_UPDATE_MC_MAG;
+	ret = i40e_aq_mac_address_write(hw, flags, mac_addr, NULL);
+	if (ret)
+		dev_err(&pf->pdev->dev,
+			"Failed to enable Multicast Magic Packet wake up\n");
+}
+
+/**
+ * i40e_io_suspend - suspend all IO operations
+ * @pf: pointer to i40e_pf struct
+ *
+ **/
+static int i40e_io_suspend(struct i40e_pf *pf)
+{
+	struct i40e_hw *hw = &pf->hw;
+
+	set_bit(__I40E_DOWN, pf->state);
+
+	/* Ensure service task will not be running */
+	del_timer_sync(&pf->service_timer);
+	cancel_work_sync(&pf->service_task);
+
+	/* Client close must be called explicitly here because the timer
+	 * has been stopped.
+	 */
+	i40e_notify_client_of_netdev_close(pf, false);
+
+	if (test_bit(I40E_HW_CAP_WOL_MC_MAGIC_PKT_WAKE, pf->hw.caps) &&
+	    pf->wol_en)
+		i40e_enable_mc_magic_wake(pf);
+
+	/* Since we're going to destroy queues during the
+	 * i40e_clear_interrupt_scheme() we should hold the RTNL lock for this
+	 * whole section
+	 */
+	rtnl_lock();
+
+	i40e_prep_for_reset(pf);
+
+	wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0));
+	wr32(hw, I40E_PFPM_WUFC, (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0));
+
+	/* Clear the interrupt scheme and release our IRQs so that the system
+	 * can safely hibernate even when there are a large number of CPUs.
+	 * Otherwise hibernation might fail when mapping all the vectors back
+	 * to CPU0.
+	 */
+	i40e_clear_interrupt_scheme(pf);
+
+	rtnl_unlock();
+
+	return 0;
+}
+
+/**
+ * i40e_io_resume - resume IO operations
+ * @pf: pointer to i40e_pf struct
+ *
+ **/
+static int i40e_io_resume(struct i40e_pf *pf)
+{
+	struct device *dev = &pf->pdev->dev;
+	int err;
+
+	/* We need to hold the RTNL lock prior to restoring interrupt schemes,
+	 * since we're going to be restoring queues
+	 */
+	rtnl_lock();
+
+	/* We cleared the interrupt scheme when we suspended, so we need to
+	 * restore it now to resume device functionality.
+	 */
+	err = i40e_restore_interrupt_scheme(pf);
+	if (err) {
+		dev_err(dev, "Cannot restore interrupt scheme: %d\n",
+			err);
+	}
+
+	clear_bit(__I40E_DOWN, pf->state);
+	i40e_reset_and_rebuild(pf, false, true);
+
+	rtnl_unlock();
+
+	/* Clear suspended state last after everything is recovered */
+	clear_bit(__I40E_SUSPENDED, pf->state);
+
+	/* Restart the service task */
+	mod_timer(&pf->service_timer,
+		  round_jiffies(jiffies + pf->service_timer_period));
+
+	return 0;
+}
+
+/**
  * i40e_pci_error_detected - warning that something funky happened in PCI land
  * @pdev: PCI device information struct
  * @error: the type of PCI error
@@ -16358,7 +16493,7 @@ static pci_ers_result_t i40e_pci_error_detected(struct pci_dev *pdev,
 
 	/* shutdown all operations */
 	if (!test_bit(__I40E_SUSPENDED, pf->state))
-		i40e_prep_for_reset(pf);
+		i40e_io_suspend(pf);
 
 	/* Request a slot reset */
 	return PCI_ERS_RESULT_NEED_RESET;
@@ -16380,7 +16515,8 @@ static pci_ers_result_t i40e_pci_error_slot_reset(struct pci_dev *pdev)
 	u32 reg;
 
 	dev_dbg(&pdev->dev, "%s\n", __func__);
-	if (pci_enable_device_mem(pdev)) {
+	/* enable I/O and memory of the device  */
+	if (pci_enable_device(pdev)) {
 		dev_info(&pdev->dev,
 			 "Cannot re-enable PCI device after reset.\n");
 		result = PCI_ERS_RESULT_DISCONNECT;
@@ -16443,54 +16579,7 @@ static void i40e_pci_error_resume(struct pci_dev *pdev)
 	if (test_bit(__I40E_SUSPENDED, pf->state))
 		return;
 
-	i40e_handle_reset_warning(pf, false);
-}
-
-/**
- * i40e_enable_mc_magic_wake - enable multicast magic packet wake up
- * using the mac_address_write admin q function
- * @pf: pointer to i40e_pf struct
- **/
-static void i40e_enable_mc_magic_wake(struct i40e_pf *pf)
-{
-	struct i40e_vsi *main_vsi = i40e_pf_get_main_vsi(pf);
-	struct i40e_hw *hw = &pf->hw;
-	u8 mac_addr[6];
-	u16 flags = 0;
-	int ret;
-
-	/* Get current MAC address in case it's an LAA */
-	if (main_vsi && main_vsi->netdev) {
-		ether_addr_copy(mac_addr, main_vsi->netdev->dev_addr);
-	} else {
-		dev_err(&pf->pdev->dev,
-			"Failed to retrieve MAC address; using default\n");
-		ether_addr_copy(mac_addr, hw->mac.addr);
-	}
-
-	/* The FW expects the mac address write cmd to first be called with
-	 * one of these flags before calling it again with the multicast
-	 * enable flags.
-	 */
-	flags = I40E_AQC_WRITE_TYPE_LAA_WOL;
-
-	if (hw->func_caps.flex10_enable && hw->partition_id != 1)
-		flags = I40E_AQC_WRITE_TYPE_LAA_ONLY;
-
-	ret = i40e_aq_mac_address_write(hw, flags, mac_addr, NULL);
-	if (ret) {
-		dev_err(&pf->pdev->dev,
-			"Failed to update MAC address registers; cannot enable Multicast Magic packet wake up");
-		return;
-	}
-
-	flags = I40E_AQC_MC_MAG_EN
-			| I40E_AQC_WOL_PRESERVE_ON_PFR
-			| I40E_AQC_WRITE_TYPE_UPDATE_MC_MAG;
-	ret = i40e_aq_mac_address_write(hw, flags, mac_addr, NULL);
-	if (ret)
-		dev_err(&pf->pdev->dev,
-			"Failed to enable Multicast Magic Packet wake up\n");
+	i40e_io_resume(pf);
 }
 
 /**
@@ -16552,48 +16641,11 @@ static void i40e_shutdown(struct pci_dev *pdev)
 static int i40e_suspend(struct device *dev)
 {
 	struct i40e_pf *pf = dev_get_drvdata(dev);
-	struct i40e_hw *hw = &pf->hw;
 
 	/* If we're already suspended, then there is nothing to do */
 	if (test_and_set_bit(__I40E_SUSPENDED, pf->state))
 		return 0;
-
-	set_bit(__I40E_DOWN, pf->state);
-
-	/* Ensure service task will not be running */
-	del_timer_sync(&pf->service_timer);
-	cancel_work_sync(&pf->service_task);
-
-	/* Client close must be called explicitly here because the timer
-	 * has been stopped.
-	 */
-	i40e_notify_client_of_netdev_close(pf, false);
-
-	if (test_bit(I40E_HW_CAP_WOL_MC_MAGIC_PKT_WAKE, pf->hw.caps) &&
-	    pf->wol_en)
-		i40e_enable_mc_magic_wake(pf);
-
-	/* Since we're going to destroy queues during the
-	 * i40e_clear_interrupt_scheme() we should hold the RTNL lock for this
-	 * whole section
-	 */
-	rtnl_lock();
-
-	i40e_prep_for_reset(pf);
-
-	wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0));
-	wr32(hw, I40E_PFPM_WUFC, (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0));
-
-	/* Clear the interrupt scheme and release our IRQs so that the system
-	 * can safely hibernate even when there are a large number of CPUs.
-	 * Otherwise hibernation might fail when mapping all the vectors back
-	 * to CPU0.
-	 */
-	i40e_clear_interrupt_scheme(pf);
-
-	rtnl_unlock();
-
-	return 0;
+	return i40e_io_suspend(pf);
 }
 
 /**
@@ -16603,39 +16655,11 @@ static int i40e_suspend(struct device *dev)
 static int i40e_resume(struct device *dev)
 {
 	struct i40e_pf *pf = dev_get_drvdata(dev);
-	int err;
 
 	/* If we're not suspended, then there is nothing to do */
 	if (!test_bit(__I40E_SUSPENDED, pf->state))
 		return 0;
-
-	/* We need to hold the RTNL lock prior to restoring interrupt schemes,
-	 * since we're going to be restoring queues
-	 */
-	rtnl_lock();
-
-	/* We cleared the interrupt scheme when we suspended, so we need to
-	 * restore it now to resume device functionality.
-	 */
-	err = i40e_restore_interrupt_scheme(pf);
-	if (err) {
-		dev_err(dev, "Cannot restore interrupt scheme: %d\n",
-			err);
-	}
-
-	clear_bit(__I40E_DOWN, pf->state);
-	i40e_reset_and_rebuild(pf, false, true);
-
-	rtnl_unlock();
-
-	/* Clear suspended state last after everything is recovered */
-	clear_bit(__I40E_SUSPENDED, pf->state);
-
-	/* Restart the service task */
-	mod_timer(&pf->service_timer,
-		  round_jiffies(jiffies + pf->service_timer_period));
-
-	return 0;
+	return i40e_io_resume(pf);
 }
 
 static const struct pci_error_handlers i40e_err_handler = {
diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c
index c4b69655cdf5..704e9ad5144e 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c
@@ -1388,7 +1388,7 @@ enum ice_param_id {
 	ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS,
 };
 
-static const struct devlink_param ice_devlink_params[] = {
+static const struct devlink_param ice_dvl_rdma_params[] = {
 	DEVLINK_PARAM_GENERIC(ENABLE_ROCE, BIT(DEVLINK_PARAM_CMODE_RUNTIME),
 			      ice_devlink_enable_roce_get,
 			      ice_devlink_enable_roce_set,
@@ -1397,6 +1397,9 @@ static const struct devlink_param ice_devlink_params[] = {
 			      ice_devlink_enable_iw_get,
 			      ice_devlink_enable_iw_set,
 			      ice_devlink_enable_iw_validate),
+};
+
+static const struct devlink_param ice_dvl_sched_params[] = {
 	DEVLINK_PARAM_DRIVER(ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS,
 			     "tx_scheduling_layers",
 			     DEVLINK_PARAM_TYPE_U8,
@@ -1464,21 +1467,31 @@ int ice_devlink_register_params(struct ice_pf *pf)
 {
 	struct devlink *devlink = priv_to_devlink(pf);
 	struct ice_hw *hw = &pf->hw;
-	size_t params_size;
+	int status;
 
-	params_size =  ARRAY_SIZE(ice_devlink_params);
+	status = devl_params_register(devlink, ice_dvl_rdma_params,
+				      ARRAY_SIZE(ice_dvl_rdma_params));
+	if (status)
+		return status;
 
-	if (!hw->func_caps.common_cap.tx_sched_topo_comp_mode_en)
-		params_size--;
+	if (hw->func_caps.common_cap.tx_sched_topo_comp_mode_en)
+		status = devl_params_register(devlink, ice_dvl_sched_params,
+					      ARRAY_SIZE(ice_dvl_sched_params));
 
-	return devl_params_register(devlink, ice_devlink_params,
-				    params_size);
+	return status;
 }
 
 void ice_devlink_unregister_params(struct ice_pf *pf)
 {
-	devl_params_unregister(priv_to_devlink(pf), ice_devlink_params,
-			       ARRAY_SIZE(ice_devlink_params));
+	struct devlink *devlink = priv_to_devlink(pf);
+	struct ice_hw *hw = &pf->hw;
+
+	devl_params_unregister(devlink, ice_dvl_rdma_params,
+			       ARRAY_SIZE(ice_dvl_rdma_params));
+
+	if (hw->func_caps.common_cap.tx_sched_topo_comp_mode_en)
+		devl_params_unregister(devlink, ice_dvl_sched_params,
+				       ARRAY_SIZE(ice_dvl_sched_params));
 }
 
 #define ICE_DEVLINK_READ_BLK_SIZE (1024 * 1024)
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 5649b257e631..24716a3b494c 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -3148,6 +3148,16 @@ ice_get_link_speed_based_on_phy_type(u64 phy_type_low, u64 phy_type_high)
 	case ICE_PHY_TYPE_HIGH_100G_AUI2:
 		speed_phy_type_high = ICE_AQ_LINK_SPEED_100GB;
 		break;
+	case ICE_PHY_TYPE_HIGH_200G_CR4_PAM4:
+	case ICE_PHY_TYPE_HIGH_200G_SR4:
+	case ICE_PHY_TYPE_HIGH_200G_FR4:
+	case ICE_PHY_TYPE_HIGH_200G_LR4:
+	case ICE_PHY_TYPE_HIGH_200G_DR4:
+	case ICE_PHY_TYPE_HIGH_200G_KR4_PAM4:
+	case ICE_PHY_TYPE_HIGH_200G_AUI4_AOC_ACC:
+	case ICE_PHY_TYPE_HIGH_200G_AUI4:
+		speed_phy_type_high = ICE_AQ_LINK_SPEED_200GB;
+		break;
 	default:
 		speed_phy_type_high = ICE_AQ_LINK_SPEED_UNKNOWN;
 		break;