Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from David Miller:

 1) Support IPV6 RA Captive Portal Identifier, from Maciej Żenczykowski.

 2) Use bio_vec in the networking instead of custom skb_frag_t, from
    Matthew Wilcox.

 3) Make use of xmit_more in r8169 driver, from Heiner Kallweit.

 4) Add devmap_hash to xdp, from Toke Høiland-Jørgensen.

 5) Support all variants of 5750X bnxt_en chips, from Michael Chan.

 6) More RTNL avoidance work in the core and mlx5 driver, from Vlad
    Buslov.

 7) Add TCP syn cookies bpf helper, from Petar Penkov.

 8) Add 'nettest' to selftests and use it, from David Ahern.

 9) Add extack support to drop_monitor, add packet alert mode and
    support for HW drops, from Ido Schimmel.

10) Add VLAN offload to stmmac, from Jose Abreu.

11) Lots of devm_platform_ioremap_resource() conversions, from
    YueHaibing.

12) Add IONIC driver, from Shannon Nelson.

13) Several kTLS cleanups, from Jakub Kicinski.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1930 commits)
  mlxsw: spectrum_buffers: Add the ability to query the CPU port's shared buffer
  mlxsw: spectrum: Register CPU port with devlink
  mlxsw: spectrum_buffers: Prevent changing CPU port's configuration
  net: ena: fix incorrect update of intr_delay_resolution
  net: ena: fix retrieval of nonadaptive interrupt moderation intervals
  net: ena: fix update of interrupt moderation register
  net: ena: remove all old adaptive rx interrupt moderation code from ena_com
  net: ena: remove ena_restore_ethtool_params() and relevant fields
  net: ena: remove old adaptive interrupt moderation code from ena_netdev
  net: ena: remove code duplication in ena_com_update_nonadaptive_moderation_interval _*()
  net: ena: enable the interrupt_moderation in driver_supported_features
  net: ena: reimplement set/get_coalesce()
  net: ena: switch to dim algorithm for rx adaptive interrupt moderation
  net: ena: add intr_moder_rx_interval to struct ena_com_dev and use it
  net: phy: adin: implement Energy Detect Powerdown mode via phy-tunable
  ethtool: implement Energy Detect Powerdown support via phy-tunable
  xen-netfront: do not assume sk_buff_head list is empty in error handling
  s390/ctcm: Delete unnecessary checks before the macro call “dev_kfree_skb”
  net: ena: don't wake up tx queue when down
  drop_monitor: Better sanitize notified packets
  ...

1 files changed, 117 insertions, 74 deletions

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 9ebbe3da61bb..6031223eafab 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -73,6 +73,7 @@ static const struct pci_device_id i40e_pci_tbl[] = {
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_C), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T4), 0},
+	{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T_BC), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_SFP), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_B), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_KX_X722), 0},
@@ -534,6 +535,10 @@ void i40e_pf_reset_stats(struct i40e_pf *pf)
 			       sizeof(pf->veb[i]->stats));
 			memset(&pf->veb[i]->stats_offsets, 0,
 			       sizeof(pf->veb[i]->stats_offsets));
+			memset(&pf->veb[i]->tc_stats, 0,
+			       sizeof(pf->veb[i]->tc_stats));
+			memset(&pf->veb[i]->tc_stats_offsets, 0,
+			       sizeof(pf->veb[i]->tc_stats_offsets));
 			pf->veb[i]->stat_offsets_loaded = false;
 		}
 	}
@@ -677,7 +682,7 @@ void i40e_update_eth_stats(struct i40e_vsi *vsi)
  * i40e_update_veb_stats - Update Switch component statistics
  * @veb: the VEB being updated
  **/
-static void i40e_update_veb_stats(struct i40e_veb *veb)
+void i40e_update_veb_stats(struct i40e_veb *veb)
 {
 	struct i40e_pf *pf = veb->pf;
 	struct i40e_hw *hw = &pf->hw;
@@ -2530,6 +2535,10 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 				 vsi_name,
 				 i40e_stat_str(hw, aq_ret),
 				 i40e_aq_str(hw, hw->aq.asq_last_status));
+		} else {
+			dev_info(&pf->pdev->dev, "%s is %s allmulti mode.\n",
+				 vsi->netdev->name,
+				 cur_multipromisc ? "entering" : "leaving");
 		}
 	}
 
@@ -2583,6 +2592,10 @@ static void i40e_sync_filters_subtask(struct i40e_pf *pf)
 		return;
 	if (!test_and_clear_bit(__I40E_MACVLAN_SYNC_PENDING, pf->state))
 		return;
+	if (test_and_set_bit(__I40E_VF_DISABLE, pf->state)) {
+		set_bit(__I40E_MACVLAN_SYNC_PENDING, pf->state);
+		return;
+	}
 
 	for (v = 0; v < pf->num_alloc_vsi; v++) {
 		if (pf->vsi[v] &&
@@ -2597,6 +2610,7 @@ static void i40e_sync_filters_subtask(struct i40e_pf *pf)
 			}
 		}
 	}
+	clear_bit(__I40E_VF_DISABLE, pf->state);
 }
 
 /**
@@ -3360,7 +3374,7 @@ static int i40e_vsi_configure_tx(struct i40e_vsi *vsi)
 	for (i = 0; (i < vsi->num_queue_pairs) && !err; i++)
 		err = i40e_configure_tx_ring(vsi->tx_rings[i]);
 
-	if (!i40e_enabled_xdp_vsi(vsi))
+	if (err || !i40e_enabled_xdp_vsi(vsi))
 		return err;
 
 	for (i = 0; (i < vsi->num_queue_pairs) && !err; i++)
@@ -6412,50 +6426,6 @@ static int i40e_resume_port_tx(struct i40e_pf *pf)
 }
 
 /**
- * i40e_update_dcb_config
- * @hw: pointer to the HW struct
- * @enable_mib_change: enable MIB change event
- *
- * Update DCB configuration from the firmware
- **/
-static enum i40e_status_code
-i40e_update_dcb_config(struct i40e_hw *hw, bool enable_mib_change)
-{
-	struct i40e_lldp_variables lldp_cfg;
-	i40e_status ret;
-
-	if (!hw->func_caps.dcb)
-		return I40E_NOT_SUPPORTED;
-
-	/* Read LLDP NVM area */
-	ret = i40e_read_lldp_cfg(hw, &lldp_cfg);
-	if (ret)
-		return I40E_ERR_NOT_READY;
-
-	/* Get DCBX status */
-	ret = i40e_get_dcbx_status(hw, &hw->dcbx_status);
-	if (ret)
-		return ret;
-
-	/* Check the DCBX Status */
-	if (hw->dcbx_status == I40E_DCBX_STATUS_DONE ||
-	    hw->dcbx_status == I40E_DCBX_STATUS_IN_PROGRESS) {
-		/* Get current DCBX configuration */
-		ret = i40e_get_dcb_config(hw);
-		if (ret)
-			return ret;
-	} else if (hw->dcbx_status == I40E_DCBX_STATUS_DISABLED) {
-		return I40E_ERR_NOT_READY;
-	}
-
-	/* Configure the LLDP MIB change event */
-	if (enable_mib_change)
-		ret = i40e_aq_cfg_lldp_mib_change_event(hw, true, NULL);
-
-	return ret;
-}
-
-/**
  * i40e_init_pf_dcb - Initialize DCB configuration
  * @pf: PF being configured
  *
@@ -6477,7 +6447,7 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf)
 		goto out;
 	}
 
-	err = i40e_update_dcb_config(hw, true);
+	err = i40e_init_dcb(hw, true);
 	if (!err) {
 		/* Device/Function is not DCBX capable */
 		if ((!hw->func_caps.dcb) ||
@@ -6599,19 +6569,19 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup)
 	}
 
 	if (pf->hw.phy.link_info.link_speed == I40E_LINK_SPEED_25GB) {
-		req_fec = ", Requested FEC: None";
-		fec = ", FEC: None";
-		an = ", Autoneg: False";
+		req_fec = "None";
+		fec = "None";
+		an = "False";
 
 		if (pf->hw.phy.link_info.an_info & I40E_AQ_AN_COMPLETED)
-			an = ", Autoneg: True";
+			an = "True";
 
 		if (pf->hw.phy.link_info.fec_info &
 		    I40E_AQ_CONFIG_FEC_KR_ENA)
-			fec = ", FEC: CL74 FC-FEC/BASE-R";
+			fec = "CL74 FC-FEC/BASE-R";
 		else if (pf->hw.phy.link_info.fec_info &
 			 I40E_AQ_CONFIG_FEC_RS_ENA)
-			fec = ", FEC: CL108 RS-FEC";
+			fec = "CL108 RS-FEC";
 
 		/* 'CL108 RS-FEC' should be displayed when RS is requested, or
 		 * both RS and FC are requested
@@ -6620,14 +6590,19 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup)
 		    (I40E_AQ_REQUEST_FEC_KR | I40E_AQ_REQUEST_FEC_RS)) {
 			if (vsi->back->hw.phy.link_info.req_fec_info &
 			    I40E_AQ_REQUEST_FEC_RS)
-				req_fec = ", Requested FEC: CL108 RS-FEC";
+				req_fec = "CL108 RS-FEC";
 			else
-				req_fec = ", Requested FEC: CL74 FC-FEC/BASE-R";
+				req_fec = "CL74 FC-FEC/BASE-R";
 		}
+		netdev_info(vsi->netdev,
+			    "NIC Link is Up, %sbps Full Duplex, Requested FEC: %s, Negotiated FEC: %s, Autoneg: %s, Flow Control: %s\n",
+			    speed, req_fec, fec, an, fc);
+	} else {
+		netdev_info(vsi->netdev,
+			    "NIC Link is Up, %sbps Full Duplex, Flow Control: %s\n",
+			    speed, fc);
 	}
 
-	netdev_info(vsi->netdev, "NIC Link is Up, %sbps Full Duplex%s%s%s, Flow Control: %s\n",
-		    speed, req_fec, fec, an, fc);
 }
 
 /**
@@ -8486,6 +8461,11 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired)
 		dev_dbg(&pf->pdev->dev, "PFR requested\n");
 		i40e_handle_reset_warning(pf, lock_acquired);
 
+		dev_info(&pf->pdev->dev,
+			 pf->flags & I40E_FLAG_DISABLE_FW_LLDP ?
+			 "FW LLDP is disabled\n" :
+			 "FW LLDP is enabled\n");
+
 	} else if (reset_flags & BIT_ULL(__I40E_REINIT_REQUESTED)) {
 		int v;
 
@@ -12561,7 +12541,8 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi,
 	if (need_reset && prog)
 		for (i = 0; i < vsi->num_queue_pairs; i++)
 			if (vsi->xdp_rings[i]->xsk_umem)
-				(void)i40e_xsk_async_xmit(vsi->netdev, i);
+				(void)i40e_xsk_wakeup(vsi->netdev, i,
+						      XDP_WAKEUP_RX);
 
 	return 0;
 }
@@ -12883,7 +12864,7 @@ static const struct net_device_ops i40e_netdev_ops = {
 	.ndo_bridge_setlink	= i40e_ndo_bridge_setlink,
 	.ndo_bpf		= i40e_xdp,
 	.ndo_xdp_xmit		= i40e_xdp_xmit,
-	.ndo_xsk_async_xmit	= i40e_xsk_async_xmit,
+	.ndo_xsk_wakeup	        = i40e_xsk_wakeup,
 	.ndo_dfwd_add_station	= i40e_fwd_add,
 	.ndo_dfwd_del_station	= i40e_fwd_del,
 };
@@ -14569,9 +14550,20 @@ void i40e_set_fec_in_flags(u8 fec_cfg, u32 *flags)
  **/
 static bool i40e_check_recovery_mode(struct i40e_pf *pf)
 {
-	u32 val = rd32(&pf->hw, I40E_GL_FWSTS);
-
-	if (val & I40E_GL_FWSTS_FWS1B_MASK) {
+	u32 val = rd32(&pf->hw, I40E_GL_FWSTS) & I40E_GL_FWSTS_FWS1B_MASK;
+	bool is_recovery_mode = false;
+
+	if (pf->hw.mac.type == I40E_MAC_XL710)
+		is_recovery_mode =
+		val == I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_CORER_MASK ||
+		val == I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_GLOBR_MASK ||
+		val == I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_TRANSITION_MASK ||
+		val == I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_NVM_MASK;
+	if (pf->hw.mac.type == I40E_MAC_X722)
+		is_recovery_mode =
+		val == I40E_X722_GL_FWSTS_FWS1B_REC_MOD_CORER_MASK ||
+		val == I40E_X722_GL_FWSTS_FWS1B_REC_MOD_GLOBR_MASK;
+	if (is_recovery_mode) {
 		dev_notice(&pf->pdev->dev, "Firmware recovery mode detected. Limiting functionality.\n");
 		dev_notice(&pf->pdev->dev, "Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode.\n");
 		set_bit(__I40E_RECOVERY_MODE, pf->state);
@@ -14585,6 +14577,51 @@ static bool i40e_check_recovery_mode(struct i40e_pf *pf)
 }
 
 /**
+ * i40e_pf_loop_reset - perform reset in a loop.
+ * @pf: board private structure
+ *
+ * This function is useful when a NIC is about to enter recovery mode.
+ * When a NIC's internal data structures are corrupted the NIC's
+ * firmware is going to enter recovery mode.
+ * Right after a POR it takes about 7 minutes for firmware to enter
+ * recovery mode. Until that time a NIC is in some kind of intermediate
+ * state. After that time period the NIC almost surely enters
+ * recovery mode. The only way for a driver to detect intermediate
+ * state is to issue a series of pf-resets and check a return value.
+ * If a PF reset returns success then the firmware could be in recovery
+ * mode so the caller of this code needs to check for recovery mode
+ * if this function returns success. There is a little chance that
+ * firmware will hang in intermediate state forever.
+ * Since waiting 7 minutes is quite a lot of time this function waits
+ * 10 seconds and then gives up by returning an error.
+ *
+ * Return 0 on success, negative on failure.
+ **/
+static i40e_status i40e_pf_loop_reset(struct i40e_pf *pf)
+{
+	const unsigned short MAX_CNT = 1000;
+	const unsigned short MSECS = 10;
+	struct i40e_hw *hw = &pf->hw;
+	i40e_status ret;
+	int cnt;
+
+	for (cnt = 0; cnt < MAX_CNT; ++cnt) {
+		ret = i40e_pf_reset(hw);
+		if (!ret)
+			break;
+		msleep(MSECS);
+	}
+
+	if (cnt == MAX_CNT) {
+		dev_info(&pf->pdev->dev, "PF reset failed: %d\n", ret);
+		return ret;
+	}
+
+	pf->pfr_count++;
+	return ret;
+}
+
+/**
  * i40e_init_recovery_mode - initialize subsystems needed in recovery mode
  * @pf: board private structure
  * @hw: ptr to the hardware info
@@ -14812,14 +14849,22 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	/* Reset here to make sure all is clean and to define PF 'n' */
 	i40e_clear_hw(hw);
-	if (!i40e_check_recovery_mode(pf)) {
-		err = i40e_pf_reset(hw);
-		if (err) {
-			dev_info(&pdev->dev, "Initial pf_reset failed: %d\n", err);
-			goto err_pf_reset;
-		}
-		pf->pfr_count++;
+
+	err = i40e_set_mac_type(hw);
+	if (err) {
+		dev_warn(&pdev->dev, "unidentified MAC or BLANK NVM: %d\n",
+			 err);
+		goto err_pf_reset;
 	}
+
+	err = i40e_pf_loop_reset(pf);
+	if (err) {
+		dev_info(&pdev->dev, "Initial pf_reset failed: %d\n", err);
+		goto err_pf_reset;
+	}
+
+	i40e_check_recovery_mode(pf);
+
 	hw->aq.num_arq_entries = I40E_AQ_LEN;
 	hw->aq.num_asq_entries = I40E_AQ_LEN;
 	hw->aq.arq_buf_size = I40E_MAX_AQ_BUF_SIZE;
@@ -15605,8 +15650,7 @@ static void i40e_shutdown(struct pci_dev *pdev)
  **/
 static int __maybe_unused i40e_suspend(struct device *dev)
 {
-	struct pci_dev *pdev = to_pci_dev(dev);
-	struct i40e_pf *pf = pci_get_drvdata(pdev);
+	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 */
@@ -15656,8 +15700,7 @@ static int __maybe_unused i40e_suspend(struct device *dev)
  **/
 static int __maybe_unused i40e_resume(struct device *dev)
 {
-	struct pci_dev *pdev = to_pci_dev(dev);
-	struct i40e_pf *pf = pci_get_drvdata(pdev);
+	struct i40e_pf *pf = dev_get_drvdata(dev);
 	int err;
 
 	/* If we're not suspended, then there is nothing to do */
@@ -15674,7 +15717,7 @@ static int __maybe_unused i40e_resume(struct device *dev)
 	 */
 	err = i40e_restore_interrupt_scheme(pf);
 	if (err) {
-		dev_err(&pdev->dev, "Cannot restore interrupt scheme: %d\n",
+		dev_err(dev, "Cannot restore interrupt scheme: %d\n",
 			err);
 	}