Merge branch '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue

Jeff Kirsher says:

====================
100GbE Intel Wired LAN Driver Updates 2019-09-03

This series contains updates to ice driver only.

Anirudh adds the ability for the driver to handle EMP resets correctly
by adding the logic to the existing ice_reset_subtask().

Jeb fixes up the logic to properly free up the resources for a switch
rule whether or not it was successful in the removal.

Brett fixes up the reporting of ITR values to let the user know odd ITR
values are not allowed.  Fixes the driver to only disable VLAN pruning
on VLAN deletion when the VLAN being deleted is the last VLAN on the VF
VSI.

Chinh updates the driver to determine the TSA value from the priority
value when in CEE mode.

Bruce aligns the driver with the hardware specification by ensuring that
a PF reset is done as part of the unload logic.  Also update the driver
unloading field, based on the latest hardware specification, which
allows us to remove an unnecessary endian conversion.  Moves #defines
based on their need in the code.

Jesse adds the current state of auto-negotiation in the link up message.
In addition, adds additional information to inform the user of an issue
with the topology/configuration of the link.

Usha updates the driver to allow the maximum TCs that the firmware
supports, rather than hard coding to a set value.

Dave updates the DCB initialization flow to handle the case of an actual
error during DCB init.  Updated the driver to report the current stats,
even when the netdev is down, which aligns with our other drivers.

Mitch fixes the VF reset code flows to ensure that it properly calls
ice_dis_vsi_txq() to notify the firmware that the VF is being reset.

Michal fixes the driver so the DCB is not enabled when the SW LLDP is
activated, which was causing a communication issue with other NICs.  The
problem lies in that DCB was being enabled without checking the number
of TCs.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/intel/ice/ice_adminq_cmd.h

@@ -35,9 +35,9 @@ struct ice_aqc_get_ver {
 
 /* Queue Shutdown (direct 0x0003) */
 struct ice_aqc_q_shutdown {
-	__le32 driver_unloading;
+	u8 driver_unloading;
 #define ICE_AQC_DRIVER_UNLOADING	BIT(0)
-	u8 reserved[12];
+	u8 reserved[15];
 };
 
 /* Request resource ownership (direct 0x0008)
@@ -91,6 +91,7 @@ struct ice_aqc_list_caps_elem {
 #define ICE_AQC_CAPS_SRIOV				0x0012
 #define ICE_AQC_CAPS_VF					0x0013
 #define ICE_AQC_CAPS_VSI				0x0017
+#define ICE_AQC_CAPS_DCB				0x0018
 #define ICE_AQC_CAPS_RSS				0x0040
 #define ICE_AQC_CAPS_RXQS				0x0041
 #define ICE_AQC_CAPS_TXQS				0x0042

drivers/net/ethernet/intel/ice/ice_common.c

@@ -1275,7 +1275,7 @@ enum ice_status ice_aq_q_shutdown(struct ice_hw *hw, bool unloading)
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_q_shutdown);
 
 	if (unloading)
-		cmd->driver_unloading = cpu_to_le32(ICE_AQC_DRIVER_UNLOADING);
+		cmd->driver_unloading = ICE_AQC_DRIVER_UNLOADING;
 
 	return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
 }
@@ -1594,6 +1594,18 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count,
 					  prefix, func_p->guar_num_vsi);
 			}
 			break;
+		case ICE_AQC_CAPS_DCB:
+			caps->dcb = (number == 1);
+			caps->active_tc_bitmap = logical_id;
+			caps->maxtc = phys_id;
+			ice_debug(hw, ICE_DBG_INIT,
+				  "%s: DCB = %d\n", prefix, caps->dcb);
+			ice_debug(hw, ICE_DBG_INIT,
+				  "%s: active TC bitmap = %d\n", prefix,
+				  caps->active_tc_bitmap);
+			ice_debug(hw, ICE_DBG_INIT,
+				  "%s: TC max = %d\n", prefix, caps->maxtc);
+			break;
 		case ICE_AQC_CAPS_RSS:
 			caps->rss_table_size = number;
 			caps->rss_table_entry_width = logical_id;

drivers/net/ethernet/intel/ice/ice_dcb.c

@@ -444,9 +444,15 @@ ice_parse_cee_pgcfg_tlv(struct ice_cee_feat_tlv *tlv,
 	 *        |pg0|pg1|pg2|pg3|pg4|pg5|pg6|pg7|
 	 *        ---------------------------------
 	 */
-	ice_for_each_traffic_class(i)
+	ice_for_each_traffic_class(i) {
 		etscfg->tcbwtable[i] = buf[offset++];
 
+		if (etscfg->prio_table[i] == ICE_CEE_PGID_STRICT)
+			dcbcfg->etscfg.tsatable[i] = ICE_IEEE_TSA_STRICT;
+		else
+			dcbcfg->etscfg.tsatable[i] = ICE_IEEE_TSA_ETS;
+	}
+
 	/* Number of TCs supported (1 octet) */
 	etscfg->maxtcs = buf[offset];
 }

drivers/net/ethernet/intel/ice/ice_dcb_lib.c

@@ -413,7 +413,7 @@ static int ice_dcb_sw_dflt_cfg(struct ice_pf *pf, bool locked)
 	memset(&pi->local_dcbx_cfg, 0, sizeof(*dcbcfg));
 
 	dcbcfg->etscfg.willing = 1;
-	dcbcfg->etscfg.maxtcs = 8;
+	dcbcfg->etscfg.maxtcs = hw->func_caps.common_cap.maxtc;
 	dcbcfg->etscfg.tcbwtable[0] = 100;
 	dcbcfg->etscfg.tsatable[0] = ICE_IEEE_TSA_ETS;
 
@@ -422,7 +422,7 @@ static int ice_dcb_sw_dflt_cfg(struct ice_pf *pf, bool locked)
 	dcbcfg->etsrec.willing = 0;
 
 	dcbcfg->pfc.willing = 1;
-	dcbcfg->pfc.pfccap = IEEE_8021QAZ_MAX_TCS;
+	dcbcfg->pfc.pfccap = hw->func_caps.common_cap.maxtc;
 
 	dcbcfg->numapps = 1;
 	dcbcfg->app[0].selector = ICE_APP_SEL_ETHTYPE;
@@ -452,11 +452,18 @@ int ice_init_pf_dcb(struct ice_pf *pf, bool locked)
 	port_info = hw->port_info;
 
 	err = ice_init_dcb(hw);
+	if (err && !port_info->is_sw_lldp) {
+		dev_err(&pf->pdev->dev, "Error initializing DCB %d\n", err);
+		goto dcb_init_err;
+	}
+
+	dev_info(&pf->pdev->dev,
+		 "DCB is enabled in the hardware, max number of TCs supported on this port are %d\n",
+		 pf->hw.func_caps.common_cap.maxtc);
 	if (err) {
 		/* FW LLDP is disabled, activate SW DCBX/LLDP mode */
 		dev_info(&pf->pdev->dev,
 			 "FW LLDP is disabled, DCBx/LLDP in SW mode.\n");
-		port_info->is_sw_lldp = true;
 		clear_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags);
 		err = ice_dcb_sw_dflt_cfg(pf, locked);
 		if (err) {
@@ -468,11 +475,9 @@ int ice_init_pf_dcb(struct ice_pf *pf, bool locked)
 
 		pf->dcbx_cap = DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_IEEE;
 		set_bit(ICE_FLAG_DCB_CAPABLE, pf->flags);
-		set_bit(ICE_FLAG_DCB_ENA, pf->flags);
 		return 0;
 	}
 
-	port_info->is_sw_lldp = false;
 	set_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags);
 
 	/* DCBX in FW and LLDP enabled in FW */
@@ -484,7 +489,6 @@ int ice_init_pf_dcb(struct ice_pf *pf, bool locked)
 	if (err)
 		goto dcb_init_err;
 
-	dev_info(&pf->pdev->dev, "DCBX offload supported\n");
 	return err;
 
 dcb_init_err:

drivers/net/ethernet/intel/ice/ice_ethtool.c

@@ -3253,25 +3253,25 @@ static int
 ice_set_rc_coalesce(enum ice_container_type c_type, struct ethtool_coalesce *ec,
 		    struct ice_ring_container *rc, struct ice_vsi *vsi)
 {
+	const char *c_type_str = (c_type == ICE_RX_CONTAINER) ? "rx" : "tx";
+	u32 use_adaptive_coalesce, coalesce_usecs;
 	struct ice_pf *pf = vsi->back;
 	u16 itr_setting;
 
 	if (!rc->ring)
 		return -EINVAL;
 
-	itr_setting = rc->itr_setting & ~ICE_ITR_DYNAMIC;
-
 	switch (c_type) {
 	case ICE_RX_CONTAINER:
 		if (ec->rx_coalesce_usecs_high > ICE_MAX_INTRL ||
 		    (ec->rx_coalesce_usecs_high &&
 		     ec->rx_coalesce_usecs_high < pf->hw.intrl_gran)) {
 			netdev_info(vsi->netdev,
-				    "Invalid value, rx-usecs-high valid values are 0 (disabled), %d-%d\n",
-				    pf->hw.intrl_gran, ICE_MAX_INTRL);
+				    "Invalid value, %s-usecs-high valid values are 0 (disabled), %d-%d\n",
+				    c_type_str, pf->hw.intrl_gran,
+				    ICE_MAX_INTRL);
 			return -EINVAL;
 		}
-
 		if (ec->rx_coalesce_usecs_high != rc->ring->q_vector->intrl) {
 			rc->ring->q_vector->intrl = ec->rx_coalesce_usecs_high;
 			wr32(&pf->hw, GLINT_RATE(rc->ring->q_vector->reg_idx),
@@ -3279,60 +3279,60 @@ ice_set_rc_coalesce(enum ice_container_type c_type, struct ethtool_coalesce *ec,
 						   pf->hw.intrl_gran));
 		}
 
-		if (ec->rx_coalesce_usecs != itr_setting &&
-		    ec->use_adaptive_rx_coalesce) {
-			netdev_info(vsi->netdev,
-				    "Rx interrupt throttling cannot be changed if adaptive-rx is enabled\n");
-			return -EINVAL;
-		}
+		use_adaptive_coalesce = ec->use_adaptive_rx_coalesce;
+		coalesce_usecs = ec->rx_coalesce_usecs;
 
-		if (ec->rx_coalesce_usecs > ICE_ITR_MAX) {
-			netdev_info(vsi->netdev,
-				    "Invalid value, rx-usecs range is 0-%d\n",
-				   ICE_ITR_MAX);
-			return -EINVAL;
-		}
-
-		if (ec->use_adaptive_rx_coalesce) {
-			rc->itr_setting |= ICE_ITR_DYNAMIC;
-		} else {
-			rc->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs);
-			rc->target_itr = ITR_TO_REG(rc->itr_setting);
-		}
 		break;
 	case ICE_TX_CONTAINER:
 		if (ec->tx_coalesce_usecs_high) {
 			netdev_info(vsi->netdev,
-				    "setting tx-usecs-high is not supported\n");
-			return -EINVAL;
-		}
-
-		if (ec->tx_coalesce_usecs != itr_setting &&
-		    ec->use_adaptive_tx_coalesce) {
-			netdev_info(vsi->netdev,
-				    "Tx interrupt throttling cannot be changed if adaptive-tx is enabled\n");
+				    "setting %s-usecs-high is not supported\n",
+				    c_type_str);
 			return -EINVAL;
 		}
 
-		if (ec->tx_coalesce_usecs > ICE_ITR_MAX) {
-			netdev_info(vsi->netdev,
-				    "Invalid value, tx-usecs range is 0-%d\n",
-				   ICE_ITR_MAX);
-			return -EINVAL;
-		}
+		use_adaptive_coalesce = ec->use_adaptive_tx_coalesce;
+		coalesce_usecs = ec->tx_coalesce_usecs;
 
-		if (ec->use_adaptive_tx_coalesce) {
-			rc->itr_setting |= ICE_ITR_DYNAMIC;
-		} else {
-			rc->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs);
-			rc->target_itr = ITR_TO_REG(rc->itr_setting);
-		}
 		break;
 	default:
 		dev_dbg(&pf->pdev->dev, "Invalid container type %d\n", c_type);
 		return -EINVAL;
 	}
 
+	itr_setting = rc->itr_setting & ~ICE_ITR_DYNAMIC;
+	if (coalesce_usecs != itr_setting && use_adaptive_coalesce) {
+		netdev_info(vsi->netdev,
+			    "%s interrupt throttling cannot be changed if adaptive-%s is enabled\n",
+			    c_type_str, c_type_str);
+		return -EINVAL;
+	}
+
+	if (coalesce_usecs > ICE_ITR_MAX) {
+		netdev_info(vsi->netdev,
+			    "Invalid value, %s-usecs range is 0-%d\n",
+			    c_type_str, ICE_ITR_MAX);
+		return -EINVAL;
+	}
+
+	/* hardware only supports an ITR granularity of 2us */
+	if (coalesce_usecs % 2 != 0) {
+		netdev_info(vsi->netdev,
+			    "Invalid value, %s-usecs must be even\n",
+			    c_type_str);
+		return -EINVAL;
+	}
+
+	if (use_adaptive_coalesce) {
+		rc->itr_setting |= ICE_ITR_DYNAMIC;
+	} else {
+		/* store user facing value how it was set */
+		rc->itr_setting = coalesce_usecs;
+		/* set to static and convert to value HW understands */
+		rc->target_itr =
+			ITR_TO_REG(ITR_REG_ALIGN(rc->itr_setting));
+	}
+
 	return 0;
 }
 

drivers/net/ethernet/intel/ice/ice_main.c

@@ -567,6 +567,8 @@ static void ice_reset_subtask(struct ice_pf *pf)
 			reset_type = ICE_RESET_CORER;
 		if (test_and_clear_bit(__ICE_GLOBR_RECV, pf->state))
 			reset_type = ICE_RESET_GLOBR;
+		if (test_and_clear_bit(__ICE_EMPR_RECV, pf->state))
+			reset_type = ICE_RESET_EMPR;
 		/* return if no valid reset type requested */
 		if (reset_type == ICE_RESET_INVAL)
 			return;
@@ -611,6 +613,22 @@ static void ice_reset_subtask(struct ice_pf *pf)
 	}
 }
 
+/**
+ * ice_print_topo_conflict - print topology conflict message
+ * @vsi: the VSI whose topology status is being checked
+ */
+static void ice_print_topo_conflict(struct ice_vsi *vsi)
+{
+	switch (vsi->port_info->phy.link_info.topo_media_conflict) {
+	case ICE_AQ_LINK_TOPO_CONFLICT:
+	case ICE_AQ_LINK_MEDIA_CONFLICT:
+		netdev_info(vsi->netdev, "Possible mis-configuration of the Ethernet port detected, please use the Intel(R) Ethernet Port Configuration Tool application to address the issue.\n");
+		break;
+	default:
+		break;
+	}
+}
+
 /**
  * ice_print_link_msg - print link up or down message
  * @vsi: the VSI whose link status is being queried
@@ -624,6 +642,7 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup)
 	const char *speed;
 	const char *fec;
 	const char *fc;
+	const char *an;
 
 	if (!vsi)
 		return;
@@ -707,6 +726,12 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup)
 		break;
 	}
 
+	/* check if autoneg completed, might be false due to not supported */
+	if (vsi->port_info->phy.link_info.an_info & ICE_AQ_AN_COMPLETED)
+		an = "True";
+	else
+		an = "False";
+
 	/* Get FEC mode requested based on PHY caps last SW configuration */
 	caps = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*caps), GFP_KERNEL);
 	if (!caps) {
@@ -731,8 +756,9 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup)
 	devm_kfree(&vsi->back->pdev->dev, caps);
 
 done:
-	netdev_info(vsi->netdev, "NIC Link is up %sbps, Requested FEC: %s, FEC: %s, Flow Control: %s\n",
-		    speed, fec_req, fec, fc);
+	netdev_info(vsi->netdev, "NIC Link is up %sbps, Requested FEC: %s, FEC: %s, Autoneg: %s, Flow Control: %s\n",
+		    speed, fec_req, fec, an, fc);
+	ice_print_topo_conflict(vsi);
 }
 
 /**
@@ -2636,6 +2662,11 @@ static void ice_remove(struct pci_dev *pdev)
 	ice_deinit_pf(pf);
 	ice_deinit_hw(&pf->hw);
 	ice_clear_interrupt_scheme(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_disable_pcie_error_reporting(pdev);
 }
 
@@ -3446,12 +3477,16 @@ void ice_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats)
 
 	vsi_stats = &vsi->net_stats;
 
-	if (test_bit(__ICE_DOWN, vsi->state) || !vsi->num_txq || !vsi->num_rxq)
+	if (!vsi->num_txq || !vsi->num_rxq)
 		return;
+
 	/* netdev packet/byte stats come from ring counter. These are obtained
 	 * by summing up ring counters (done by ice_update_vsi_ring_stats).
+	 * But, only call the update routine and read the registers if VSI is
+	 * not down.
 	 */
-	ice_update_vsi_ring_stats(vsi);
+	if (!test_bit(__ICE_DOWN, vsi->state))
+		ice_update_vsi_ring_stats(vsi);
 	stats->tx_packets = vsi_stats->tx_packets;
 	stats->tx_bytes = vsi_stats->tx_bytes;
 	stats->rx_packets = vsi_stats->rx_packets;

drivers/net/ethernet/intel/ice/ice_switch.c

@@ -1623,12 +1623,13 @@ ice_remove_rule_internal(struct ice_hw *hw, u8 recp_id,
 		status = ice_aq_sw_rules(hw, s_rule,
 					 ICE_SW_RULE_RX_TX_NO_HDR_SIZE, 1,
 					 ice_aqc_opc_remove_sw_rules, NULL);
-		if (status)
-			goto exit;
 
 		/* Remove a book keeping from the list */
 		devm_kfree(ice_hw_to_dev(hw), s_rule);
 
+		if (status)
+			goto exit;
+
 		list_del(&list_elem->list_entry);
 		devm_kfree(ice_hw_to_dev(hw), list_elem);
 	}

drivers/net/ethernet/intel/ice/ice_type.h

@@ -4,15 +4,15 @@
 #ifndef _ICE_TYPE_H_
 #define _ICE_TYPE_H_
 
+#define ICE_BYTES_PER_WORD	2
+#define ICE_BYTES_PER_DWORD	4
+
 #include "ice_status.h"
 #include "ice_hw_autogen.h"
 #include "ice_osdep.h"
 #include "ice_controlq.h"
 #include "ice_lan_tx_rx.h"
 
-#define ICE_BYTES_PER_WORD	2
-#define ICE_BYTES_PER_DWORD	4
-
 static inline bool ice_is_tc_ena(unsigned long bitmap, u8 tc)
 {
 	return test_bit(tc, &bitmap);
@@ -139,6 +139,9 @@ struct ice_phy_info {
 /* Common HW capabilities for SW use */
 struct ice_hw_common_caps {
 	u32 valid_functions;
+	/* DCB capabilities */
+	u32 active_tc_bitmap;
+	u32 maxtc;
 
 	/* Tx/Rx queues */
 	u16 num_rxq;		/* Number/Total Rx queues */

drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c

@@ -1074,9 +1074,16 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr)
 	for (v = 0; v < pf->num_alloc_vfs; v++)
 		ice_trigger_vf_reset(&pf->vf[v], is_vflr);
 
-	for (v = 0; v < pf->num_alloc_vfs; v++)
-		if (test_bit(ICE_VF_STATE_QS_ENA, pf->vf[v].vf_states))
-			ice_dis_vf_qs(&pf->vf[v]);
+	for (v = 0; v < pf->num_alloc_vfs; v++) {
+		struct ice_vsi *vsi;
+
+		vf = &pf->vf[v];
+		vsi = pf->vsi[vf->lan_vsi_idx];
+		if (test_bit(ICE_VF_STATE_QS_ENA, vf->vf_states))
+			ice_dis_vf_qs(vf);
+		ice_dis_vsi_txq(vsi->port_info, vsi->idx, 0, 0, NULL, NULL,
+				NULL, ICE_VF_RESET, vf->vf_id, NULL);
+	}
 
 	/* HW requires some time to make sure it can flush the FIFO for a VF
 	 * when it resets it. Poll the VPGEN_VFRSTAT register for each VF in
@@ -1171,12 +1178,12 @@ static bool ice_reset_vf(struct ice_vf *vf, bool is_vflr)
 
 	if (test_bit(ICE_VF_STATE_QS_ENA, vf->vf_states))
 		ice_dis_vf_qs(vf);
-	else
-		/* Call Disable LAN Tx queue AQ call even when queues are not
-		 * enabled. This is needed for successful completion of VFR
-		 */
-		ice_dis_vsi_txq(vsi->port_info, vsi->idx, 0, 0, NULL, NULL,
-				NULL, ICE_VF_RESET, vf->vf_id, NULL);
+
+	/* Call Disable LAN Tx queue AQ whether or not queues are
+	 * enabled. This is needed for successful completion of VFR.
+	 */
+	ice_dis_vsi_txq(vsi->port_info, vsi->idx, 0, 0, NULL, NULL,
+			NULL, ICE_VF_RESET, vf->vf_id, NULL);
 
 	hw = &pf->hw;
 	/* poll VPGEN_VFRSTAT reg to make sure
@@ -2760,8 +2767,9 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v)
 			}
 
 			vf->num_vlan--;
-			/* Disable VLAN pruning when removing VLAN */
-			ice_cfg_vlan_pruning(vsi, false, false);
+			/* Disable VLAN pruning when the last VLAN is removed */
+			if (!vf->num_vlan)
+				ice_cfg_vlan_pruning(vsi, false, false);
 
 			/* Disable Unicast/Multicast VLAN promiscuous mode */
 			if (vlan_promisc) {