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 2019-09-05

This series contains updates to ice driver.

Brett fixes the setting of num_q_vectors by using the maximum number
between the allocated transmit and receive queues.

Anirudh simplifies the code to use a helper function to return the main
VSI, which is the first element in the pf->vsi array.  Adds a pointer
check to prevent a NULL pointer dereference.  Adds a check to ensure we
do not initialize DCB on devices that are not DCB capable.  Does some
housekeeping on the code to remove unnecessary indirection and reduce
the PF structure by removing elements that are not needed since the
values they were storing can be readily gotten from
ice_get_avail_*_count()'s.  Updates the printed strings to make it
easier to search the logs for driver capabilities.

Jesse cleans up unnecessary function arguments.  Updated the code to use
prefetch() to add some efficiency to the driver to avoid a cache miss.
Did some housekeeping on the code to remove the configurable transmit
work limit via ethtool which ended up creating performance overhead.
Made additional performance enhancements by updating the driver to start
out with a reasonable number of descriptors by changing the default to
2048.

Mitch fixes the reset logic for VFs by clearing VF_MBX_ARQLEN register
when the source of the reset is not PFR.

Lukasz updates the driver to include a similar fix for the i40e driver
by reporting link down for VF's when the PF queues are not enabled.

Akeem updates the driver to report the VF link status once we get VF
resources so that we can reflect the link status similarly to how the PF
reports link speed.

Ashish updates the transmit context structure based on recent changes to
the hardware specification.

Dave updates the DCB logic to allow a delayed registration for MIB
change events so that the driver is not accepting events before it is
ready for them.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

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

@@ -47,23 +47,8 @@ extern const char ice_drv_ver[];
 #define ICE_MIN_NUM_DESC	64
 #define ICE_MAX_NUM_DESC	8160
 #define ICE_DFLT_MIN_RX_DESC	512
-/* if the default number of Rx descriptors between ICE_MAX_NUM_DESC and the
- * number of descriptors to fill up an entire page is greater than or equal to
- * ICE_DFLT_MIN_RX_DESC set it based on page size, otherwise set it to
- * ICE_DFLT_MIN_RX_DESC
- */
-#define ICE_DFLT_NUM_RX_DESC \
-	min_t(u16, ICE_MAX_NUM_DESC, \
-	      max_t(u16, ALIGN(PAGE_SIZE / sizeof(union ice_32byte_rx_desc), \
-			       ICE_REQ_DESC_MULTIPLE), \
-		    ICE_DFLT_MIN_RX_DESC))
-/* set default number of Tx descriptors to the minimum between ICE_MAX_NUM_DESC
- * and the number of descriptors to fill up an entire page
- */
-#define ICE_DFLT_NUM_TX_DESC	min_t(u16, ICE_MAX_NUM_DESC, \
-				      ALIGN(PAGE_SIZE / \
-					    sizeof(struct ice_tx_desc), \
-					    ICE_REQ_DESC_MULTIPLE))
+#define ICE_DFLT_NUM_TX_DESC	256
+#define ICE_DFLT_NUM_RX_DESC	2048
 
 #define ICE_DFLT_TRAFFIC_CLASS	BIT(0)
 #define ICE_INT_NAME_STR_LEN	(IFNAMSIZ + 16)
@@ -247,9 +232,6 @@ struct ice_vsi {
 	u16 vsi_num;			/* HW (absolute) index of this VSI */
 	u16 idx;			/* software index in pf->vsi[] */
 
-	/* Interrupt thresholds */
-	u16 work_lmt;
-
 	s16 vf_id;			/* VF ID for SR-IOV VSIs */
 
 	u16 ethtype;			/* Ethernet protocol for pause frame */
@@ -371,8 +353,6 @@ struct ice_pf {
 	u32 num_lan_msix;	/* Total MSIX vectors for base driver */
 	u16 num_lan_tx;		/* num LAN Tx queues setup */
 	u16 num_lan_rx;		/* num LAN Rx queues setup */
-	u16 q_left_tx;		/* remaining num Tx queues left unclaimed */
-	u16 q_left_rx;		/* remaining num Rx queues left unclaimed */
 	u16 next_vsi;		/* Next free slot in pf->vsi[] - 0-based! */
 	u16 num_alloc_vsi;
 	u16 corer_count;	/* Core reset count */
@@ -425,21 +405,15 @@ ice_irq_dynamic_ena(struct ice_hw *hw, struct ice_vsi *vsi,
 }
 
 /**
- * ice_find_vsi_by_type - Find and return VSI of a given type
- * @pf: PF to search for VSI
- * @type: Value indicating type of VSI we are looking for
+ * ice_get_main_vsi - Get the PF VSI
+ * @pf: PF instance
+ *
+ * returns pf->vsi[0], which by definition is the PF VSI
  */
-static inline struct ice_vsi *
-ice_find_vsi_by_type(struct ice_pf *pf, enum ice_vsi_type type)
+static inline struct ice_vsi *ice_get_main_vsi(struct ice_pf *pf)
 {
-	int i;
-
-	for (i = 0; i < pf->num_alloc_vsi; i++) {
-		struct ice_vsi *vsi = pf->vsi[i];
-
-		if (vsi && vsi->type == type)
-			return vsi;
-	}
+	if (pf->vsi)
+		return pf->vsi[0];
 
 	return NULL;
 }
@@ -447,6 +421,8 @@ ice_find_vsi_by_type(struct ice_pf *pf, enum ice_vsi_type type)
 int ice_vsi_setup_tx_rings(struct ice_vsi *vsi);
 int ice_vsi_setup_rx_rings(struct ice_vsi *vsi);
 void ice_set_ethtool_ops(struct net_device *netdev);
+u16 ice_get_avail_txq_count(struct ice_pf *pf);
+u16 ice_get_avail_rxq_count(struct ice_pf *pf);
 void ice_update_vsi_stats(struct ice_vsi *vsi);
 void ice_update_pf_stats(struct ice_pf *pf);
 int ice_up(struct ice_vsi *vsi);

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

@@ -1132,6 +1132,7 @@ const struct ice_ctx_ele ice_tlan_ctx_info[] = {
 	ICE_CTX_STORE(ice_tlan_ctx, vmvf_type,			2,	78),
 	ICE_CTX_STORE(ice_tlan_ctx, src_vsi,			10,	80),
 	ICE_CTX_STORE(ice_tlan_ctx, tsyn_ena,			1,	90),
+	ICE_CTX_STORE(ice_tlan_ctx, internal_usage_flag,	1,	91),
 	ICE_CTX_STORE(ice_tlan_ctx, alt_vlan,			1,	92),
 	ICE_CTX_STORE(ice_tlan_ctx, cpuid,			8,	93),
 	ICE_CTX_STORE(ice_tlan_ctx, wb_mode,			1,	101),
@@ -1150,7 +1151,7 @@ const struct ice_ctx_ele ice_tlan_ctx_info[] = {
 	ICE_CTX_STORE(ice_tlan_ctx, drop_ena,			1,	165),
 	ICE_CTX_STORE(ice_tlan_ctx, cache_prof_idx,		2,	166),
 	ICE_CTX_STORE(ice_tlan_ctx, pkt_shaper_prof_idx,	3,	168),
-	ICE_CTX_STORE(ice_tlan_ctx, int_q_state,		110,	171),
+	ICE_CTX_STORE(ice_tlan_ctx, int_q_state,		122,	171),
 	{ 0 }
 };
 
@@ -1550,29 +1551,29 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count,
 		case ICE_AQC_CAPS_VALID_FUNCTIONS:
 			caps->valid_functions = number;
 			ice_debug(hw, ICE_DBG_INIT,
-				  "%s: valid functions = %d\n", prefix,
+				  "%s: valid_functions (bitmap) = %d\n", prefix,
 				  caps->valid_functions);
 			break;
 		case ICE_AQC_CAPS_SRIOV:
 			caps->sr_iov_1_1 = (number == 1);
 			ice_debug(hw, ICE_DBG_INIT,
-				  "%s: SR-IOV = %d\n", prefix,
+				  "%s: sr_iov_1_1 = %d\n", prefix,
 				  caps->sr_iov_1_1);
 			break;
 		case ICE_AQC_CAPS_VF:
 			if (dev_p) {
 				dev_p->num_vfs_exposed = number;
 				ice_debug(hw, ICE_DBG_INIT,
-					  "%s: VFs exposed = %d\n", prefix,
+					  "%s: num_vfs_exposed = %d\n", prefix,
 					  dev_p->num_vfs_exposed);
 			} else if (func_p) {
 				func_p->num_allocd_vfs = number;
 				func_p->vf_base_id = logical_id;
 				ice_debug(hw, ICE_DBG_INIT,
-					  "%s: VFs allocated = %d\n", prefix,
+					  "%s: num_allocd_vfs = %d\n", prefix,
 					  func_p->num_allocd_vfs);
 				ice_debug(hw, ICE_DBG_INIT,
-					  "%s: VF base_id = %d\n", prefix,
+					  "%s: vf_base_id = %d\n", prefix,
 					  func_p->vf_base_id);
 			}
 			break;
@@ -1580,17 +1581,17 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count,
 			if (dev_p) {
 				dev_p->num_vsi_allocd_to_host = number;
 				ice_debug(hw, ICE_DBG_INIT,
-					  "%s: num VSI alloc to host = %d\n",
+					  "%s: num_vsi_allocd_to_host = %d\n",
 					  prefix,
 					  dev_p->num_vsi_allocd_to_host);
 			} else if (func_p) {
 				func_p->guar_num_vsi =
 					ice_get_num_per_func(hw, ICE_MAX_VSI);
 				ice_debug(hw, ICE_DBG_INIT,
-					  "%s: num guaranteed VSI (fw) = %d\n",
+					  "%s: guar_num_vsi (fw) = %d\n",
 					  prefix, number);
 				ice_debug(hw, ICE_DBG_INIT,
-					  "%s: num guaranteed VSI = %d\n",
+					  "%s: guar_num_vsi = %d\n",
 					  prefix, func_p->guar_num_vsi);
 			}
 			break;
@@ -1599,56 +1600,56 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count,
 			caps->active_tc_bitmap = logical_id;
 			caps->maxtc = phys_id;
 			ice_debug(hw, ICE_DBG_INIT,
-				  "%s: DCB = %d\n", prefix, caps->dcb);
+				  "%s: dcb = %d\n", prefix, caps->dcb);
 			ice_debug(hw, ICE_DBG_INIT,
-				  "%s: active TC bitmap = %d\n", prefix,
+				  "%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);
+				  "%s: maxtc = %d\n", prefix, caps->maxtc);
 			break;
 		case ICE_AQC_CAPS_RSS:
 			caps->rss_table_size = number;
 			caps->rss_table_entry_width = logical_id;
 			ice_debug(hw, ICE_DBG_INIT,
-				  "%s: RSS table size = %d\n", prefix,
+				  "%s: rss_table_size = %d\n", prefix,
 				  caps->rss_table_size);
 			ice_debug(hw, ICE_DBG_INIT,
-				  "%s: RSS table width = %d\n", prefix,
+				  "%s: rss_table_entry_width = %d\n", prefix,
 				  caps->rss_table_entry_width);
 			break;
 		case ICE_AQC_CAPS_RXQS:
 			caps->num_rxq = number;
 			caps->rxq_first_id = phys_id;
 			ice_debug(hw, ICE_DBG_INIT,
-				  "%s: num Rx queues = %d\n", prefix,
+				  "%s: num_rxq = %d\n", prefix,
 				  caps->num_rxq);
 			ice_debug(hw, ICE_DBG_INIT,
-				  "%s: Rx first queue ID = %d\n", prefix,
+				  "%s: rxq_first_id = %d\n", prefix,
 				  caps->rxq_first_id);
 			break;
 		case ICE_AQC_CAPS_TXQS:
 			caps->num_txq = number;
 			caps->txq_first_id = phys_id;
 			ice_debug(hw, ICE_DBG_INIT,
-				  "%s: num Tx queues = %d\n", prefix,
+				  "%s: num_txq = %d\n", prefix,
 				  caps->num_txq);
 			ice_debug(hw, ICE_DBG_INIT,
-				  "%s: Tx first queue ID = %d\n", prefix,
+				  "%s: txq_first_id = %d\n", prefix,
 				  caps->txq_first_id);
 			break;
 		case ICE_AQC_CAPS_MSIX:
 			caps->num_msix_vectors = number;
 			caps->msix_vector_first_id = phys_id;
 			ice_debug(hw, ICE_DBG_INIT,
-				  "%s: MSIX vector count = %d\n", prefix,
+				  "%s: num_msix_vectors = %d\n", prefix,
 				  caps->num_msix_vectors);
 			ice_debug(hw, ICE_DBG_INIT,
-				  "%s: MSIX first vector index = %d\n", prefix,
+				  "%s: msix_vector_first_id = %d\n", prefix,
 				  caps->msix_vector_first_id);
 			break;
 		case ICE_AQC_CAPS_MAX_MTU:
 			caps->max_mtu = number;
-			ice_debug(hw, ICE_DBG_INIT, "%s: max MTU = %d\n",
+			ice_debug(hw, ICE_DBG_INIT, "%s: max_mtu = %d\n",
 				  prefix, caps->max_mtu);
 			break;
 		default:

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

@@ -60,7 +60,7 @@ ice_aq_get_lldp_mib(struct ice_hw *hw, u8 bridge_type, u8 mib_type, void *buf,
  * Enable or Disable posting of an event on ARQ when LLDP MIB
  * associated with the interface changes (0x0A01)
  */
-enum ice_status
+static enum ice_status
 ice_aq_cfg_lldp_mib_change(struct ice_hw *hw, bool ena_update,
 			   struct ice_sq_cd *cd)
 {
@@ -943,10 +943,11 @@ enum ice_status ice_get_dcb_cfg(struct ice_port_info *pi)
 /**
  * ice_init_dcb
  * @hw: pointer to the HW struct
+ * @enable_mib_change: enable MIB change event
  *
  * Update DCB configuration from the Firmware
  */
-enum ice_status ice_init_dcb(struct ice_hw *hw)
+enum ice_status ice_init_dcb(struct ice_hw *hw, bool enable_mib_change)
 {
 	struct ice_port_info *pi = hw->port_info;
 	enum ice_status ret = 0;
@@ -972,9 +973,39 @@ enum ice_status ice_init_dcb(struct ice_hw *hw)
 	}
 
 	/* Configure the LLDP MIB change event */
-	ret = ice_aq_cfg_lldp_mib_change(hw, true, NULL);
+	if (enable_mib_change) {
+		ret = ice_aq_cfg_lldp_mib_change(hw, true, NULL);
+		if (!ret)
+			pi->is_sw_lldp = false;
+	}
+
+	return ret;
+}
+
+/**
+ * ice_cfg_lldp_mib_change
+ * @hw: pointer to the HW struct
+ * @ena_mib: enable/disable MIB change event
+ *
+ * Configure (disable/enable) MIB
+ */
+enum ice_status ice_cfg_lldp_mib_change(struct ice_hw *hw, bool ena_mib)
+{
+	struct ice_port_info *pi = hw->port_info;
+	enum ice_status ret;
+
+	if (!hw->func_caps.common_cap.dcb)
+		return ICE_ERR_NOT_SUPPORTED;
+
+	/* Get DCBX status */
+	pi->dcbx_status = ice_get_dcbx_status(hw);
+
+	if (pi->dcbx_status == ICE_DCBX_STATUS_DIS)
+		return ICE_ERR_NOT_READY;
+
+	ret = ice_aq_cfg_lldp_mib_change(hw, ena_mib, NULL);
 	if (!ret)
-		pi->is_sw_lldp = false;
+		pi->is_sw_lldp = !ena_mib;
 
 	return ret;
 }

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

@@ -125,7 +125,7 @@ ice_aq_get_dcb_cfg(struct ice_hw *hw, u8 mib_type, u8 bridgetype,
 		   struct ice_dcbx_cfg *dcbcfg);
 enum ice_status ice_get_dcb_cfg(struct ice_port_info *pi);
 enum ice_status ice_set_dcb_cfg(struct ice_port_info *pi);
-enum ice_status ice_init_dcb(struct ice_hw *hw);
+enum ice_status ice_init_dcb(struct ice_hw *hw, bool enable_mib_change);
 enum ice_status
 ice_query_port_ets(struct ice_port_info *pi,
 		   struct ice_aqc_port_ets_elem *buf, u16 buf_size,
@@ -139,9 +139,7 @@ ice_aq_start_lldp(struct ice_hw *hw, bool persist, struct ice_sq_cd *cd);
 enum ice_status
 ice_aq_start_stop_dcbx(struct ice_hw *hw, bool start_dcbx_agent,
 		       bool *dcbx_agent_status, struct ice_sq_cd *cd);
-enum ice_status
-ice_aq_cfg_lldp_mib_change(struct ice_hw *hw, bool ena_update,
-			   struct ice_sq_cd *cd);
+enum ice_status ice_cfg_lldp_mib_change(struct ice_hw *hw, bool ena_mib);
 #else /* CONFIG_DCB */
 static inline enum ice_status
 ice_aq_stop_lldp(struct ice_hw __always_unused *hw,
@@ -172,9 +170,8 @@ ice_aq_start_stop_dcbx(struct ice_hw __always_unused *hw,
 }
 
 static inline enum ice_status
-ice_aq_cfg_lldp_mib_change(struct ice_hw __always_unused *hw,
-			   bool __always_unused ena_update,
-			   struct ice_sq_cd __always_unused *cd)
+ice_cfg_lldp_mib_change(struct ice_hw __always_unused *hw,
+			bool __always_unused ena_mib)
 {
 	return 0;
 }

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

@@ -318,7 +318,7 @@ void ice_dcb_rebuild(struct ice_pf *pf)
 		goto dcb_error;
 	}
 
-	ice_init_dcb(&pf->hw);
+	ice_init_dcb(&pf->hw, true);
 	if (pf->hw.port_info->dcbx_status == ICE_DCBX_STATUS_DIS)
 		pf->hw.port_info->is_sw_lldp = true;
 	else
@@ -451,7 +451,7 @@ int ice_init_pf_dcb(struct ice_pf *pf, bool locked)
 
 	port_info = hw->port_info;
 
-	err = ice_init_dcb(hw);
+	err = ice_init_dcb(hw, false);
 	if (err && !port_info->is_sw_lldp) {
 		dev_err(&pf->pdev->dev, "Error initializing DCB %d\n", err);
 		goto dcb_init_err;
@@ -474,7 +474,6 @@ 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);
 		return 0;
 	}
 
@@ -483,8 +482,6 @@ int ice_init_pf_dcb(struct ice_pf *pf, bool locked)
 	/* DCBX in FW and LLDP enabled in FW */
 	pf->dcbx_cap = DCB_CAP_DCBX_LLD_MANAGED | DCB_CAP_DCBX_VER_IEEE;
 
-	set_bit(ICE_FLAG_DCB_CAPABLE, pf->flags);
-
 	err = ice_dcb_init_cfg(pf, locked);
 	if (err)
 		goto dcb_init_err;

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

@@ -1206,8 +1206,8 @@ static int ice_set_priv_flags(struct net_device *netdev, u32 flags)
 			enum ice_status status;
 
 			/* Disable FW LLDP engine */
-			status = ice_aq_cfg_lldp_mib_change(&pf->hw, false,
-							    NULL);
+			status = ice_cfg_lldp_mib_change(&pf->hw, false);
+
 			/* If unregistering for LLDP events fails, this is
 			 * not an error state, as there shouldn't be any
 			 * events to respond to.
@@ -1273,6 +1273,12 @@ static int ice_set_priv_flags(struct net_device *netdev, u32 flags)
 			 * The FW LLDP engine will now be consuming them.
 			 */
 			ice_cfg_sw_lldp(vsi, false, false);
+
+			/* Register for MIB change events */
+			status = ice_cfg_lldp_mib_change(&pf->hw, true);
+			if (status)
+				dev_dbg(&pf->pdev->dev,
+					"Fail to enable MIB change events\n");
 		}
 	}
 	clear_bit(ICE_FLAG_ETHTOOL_CTXT, pf->flags);
@@ -3214,12 +3220,6 @@ __ice_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec,
 	if (ice_get_q_coalesce(vsi, ec, q_num))
 		return -EINVAL;
 
-	if (q_num < vsi->num_txq)
-		ec->tx_max_coalesced_frames_irq = vsi->work_lmt;
-
-	if (q_num < vsi->num_rxq)
-		ec->rx_max_coalesced_frames_irq = vsi->work_lmt;
-
 	return 0;
 }
 
@@ -3399,17 +3399,13 @@ __ice_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec,
 			if (ice_set_q_coalesce(vsi, ec, i))
 				return -EINVAL;
 		}
-		goto set_work_lmt;
+		goto set_complete;
 	}
 
 	if (ice_set_q_coalesce(vsi, ec, q_num))
 		return -EINVAL;
 
-set_work_lmt:
-
-	if (ec->tx_max_coalesced_frames_irq || ec->rx_max_coalesced_frames_irq)
-		vsi->work_lmt = max(ec->tx_max_coalesced_frames_irq,
-				    ec->rx_max_coalesced_frames_irq);
+set_complete:
 
 	return 0;
 }

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

@@ -428,6 +428,7 @@ struct ice_tlan_ctx {
 #define ICE_TLAN_CTX_VMVF_TYPE_PF	2
 	u16 src_vsi;
 	u8 tsyn_ena;
+	u8 internal_usage_flag;
 	u8 alt_vlan;
 	u16 cpuid;		/* bigger than needed, see above for reason */
 	u8 wb_mode;

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

@@ -343,9 +343,21 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id)
 
 	switch (vsi->type) {
 	case ICE_VSI_PF:
-		vsi->alloc_txq = pf->num_lan_tx;
-		vsi->alloc_rxq = pf->num_lan_rx;
-		vsi->num_q_vectors = max_t(int, pf->num_lan_rx, pf->num_lan_tx);
+		vsi->alloc_txq = min_t(int, ice_get_avail_txq_count(pf),
+				       num_online_cpus());
+
+		pf->num_lan_tx = vsi->alloc_txq;
+
+		/* only 1 Rx queue unless RSS is enabled */
+		if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags))
+			vsi->alloc_rxq = 1;
+		else
+			vsi->alloc_rxq = min_t(int, ice_get_avail_rxq_count(pf),
+					       num_online_cpus());
+
+		pf->num_lan_rx = vsi->alloc_rxq;
+
+		vsi->num_q_vectors = max_t(int, vsi->alloc_rxq, vsi->alloc_txq);
 		break;
 	case ICE_VSI_VF:
 		vf = &pf->vf[vsi->vf_id];
@@ -548,8 +560,8 @@ ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type type, u16 vf_id)
 	vsi->type = type;
 	vsi->back = pf;
 	set_bit(__ICE_DOWN, vsi->state);
+
 	vsi->idx = pf->next_vsi;
-	vsi->work_lmt = ICE_DFLT_IRQ_WORK;
 
 	if (type == ICE_VSI_VF)
 		ice_vsi_set_num_qs(vsi, vf_id);
@@ -2577,9 +2589,6 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 		if (ret)
 			goto unroll_vector_base;
 
-		pf->q_left_tx -= vsi->alloc_txq;
-		pf->q_left_rx -= vsi->alloc_rxq;
-
 		/* Do not exit if configuring RSS had an issue, at least
 		 * receive traffic on first queue. Hence no need to capture
 		 * return value
@@ -2643,8 +2652,6 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 	ice_vsi_delete(vsi);
 unroll_get_qs:
 	ice_vsi_put_qs(vsi);
-	pf->q_left_tx += vsi->alloc_txq;
-	pf->q_left_rx += vsi->alloc_rxq;
 	ice_vsi_clear(vsi);
 
 	return NULL;
@@ -2992,8 +2999,6 @@ int ice_vsi_release(struct ice_vsi *vsi)
 	ice_vsi_clear_rings(vsi);
 
 	ice_vsi_put_qs(vsi);
-	pf->q_left_tx += vsi->alloc_txq;
-	pf->q_left_rx += vsi->alloc_rxq;
 
 	/* retain SW VSI data structure since it is needed to unregister and
 	 * free VSI netdev when PF is not in reset recovery pending state,\
@@ -3102,8 +3107,6 @@ int ice_vsi_rebuild(struct ice_vsi *vsi)
 		if (ret)
 			goto err_vectors;
 
-		pf->q_left_tx -= vsi->alloc_txq;
-		pf->q_left_rx -= vsi->alloc_rxq;
 		break;
 	default:
 		break;

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

@@ -120,7 +120,7 @@ static int ice_init_mac_fltr(struct ice_pf *pf)
 	u8 broadcast[ETH_ALEN];
 	struct ice_vsi *vsi;
 
-	vsi = ice_find_vsi_by_type(pf, ICE_VSI_PF);
+	vsi = ice_get_main_vsi(pf);
 	if (!vsi)
 		return -EINVAL;
 
@@ -826,7 +826,7 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up,
 	if (link_up == old_link && link_speed == old_link_speed)
 		return result;
 
-	vsi = ice_find_vsi_by_type(pf, ICE_VSI_PF);
+	vsi = ice_get_main_vsi(pf);
 	if (!vsi || !vsi->port_info)
 		return -EINVAL;
 
@@ -1439,7 +1439,7 @@ static void ice_check_media_subtask(struct ice_pf *pf)
 	struct ice_vsi *vsi;
 	int err;
 
-	vsi = ice_find_vsi_by_type(pf, ICE_VSI_PF);
+	vsi = ice_get_main_vsi(pf);
 	if (!vsi)
 		return;
 
@@ -2192,36 +2192,48 @@ static int ice_setup_pf_sw(struct ice_pf *pf)
 		ice_vsi_free_q_vectors(vsi);
 		ice_vsi_delete(vsi);
 		ice_vsi_put_qs(vsi);
-		pf->q_left_tx += vsi->alloc_txq;
-		pf->q_left_rx += vsi->alloc_rxq;
 		ice_vsi_clear(vsi);
 	}
 	return status;
 }
 
 /**
- * ice_determine_q_usage - Calculate queue distribution
- * @pf: board private structure
- *
- * Return -ENOMEM if we don't get enough queues for all ports
+ * ice_get_avail_q_count - Get count of queues in use
+ * @pf_qmap: bitmap to get queue use count from
+ * @lock: pointer to a mutex that protects access to pf_qmap
+ * @size: size of the bitmap
  */
-static void ice_determine_q_usage(struct ice_pf *pf)
+static u16
+ice_get_avail_q_count(unsigned long *pf_qmap, struct mutex *lock, u16 size)
 {
-	u16 q_left_tx, q_left_rx;
+	u16 count = 0, bit;
 
-	q_left_tx = pf->hw.func_caps.common_cap.num_txq;
-	q_left_rx = pf->hw.func_caps.common_cap.num_rxq;
+	mutex_lock(lock);
+	for_each_clear_bit(bit, pf_qmap, size)
+		count++;
+	mutex_unlock(lock);
 
-	pf->num_lan_tx = min_t(int, q_left_tx, num_online_cpus());
+	return count;
+}
 
-	/* only 1 Rx queue unless RSS is enabled */
-	if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags))
-		pf->num_lan_rx = 1;
-	else
-		pf->num_lan_rx = min_t(int, q_left_rx, num_online_cpus());
+/**
+ * ice_get_avail_txq_count - Get count of Tx queues in use
+ * @pf: pointer to an ice_pf instance
+ */
+u16 ice_get_avail_txq_count(struct ice_pf *pf)
+{
+	return ice_get_avail_q_count(pf->avail_txqs, &pf->avail_q_mutex,
+				     pf->max_pf_txqs);
+}
 
-	pf->q_left_tx = q_left_tx - pf->num_lan_tx;
-	pf->q_left_rx = q_left_rx - pf->num_lan_rx;
+/**
+ * ice_get_avail_rxq_count - Get count of Rx queues in use
+ * @pf: pointer to an ice_pf instance
+ */
+u16 ice_get_avail_rxq_count(struct ice_pf *pf)
+{
+	return ice_get_avail_q_count(pf->avail_rxqs, &pf->avail_q_mutex,
+				     pf->max_pf_rxqs);
 }
 
 /**
@@ -2252,6 +2264,8 @@ static void ice_deinit_pf(struct ice_pf *pf)
 static int ice_init_pf(struct ice_pf *pf)
 {
 	bitmap_zero(pf->flags, ICE_PF_FLAGS_NBITS);
+	if (pf->hw.func_caps.common_cap.dcb)
+		set_bit(ICE_FLAG_DCB_CAPABLE, pf->flags);
 #ifdef CONFIG_PCI_IOV
 	if (pf->hw.func_caps.common_cap.sr_iov_1_1) {
 		struct ice_hw *hw = &pf->hw;
@@ -2529,17 +2543,16 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 		goto err_init_pf_unroll;
 	}
 
-	err = ice_init_pf_dcb(pf, false);
-	if (err) {
-		clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags);
-		clear_bit(ICE_FLAG_DCB_ENA, pf->flags);
-
-		/* do not fail overall init if DCB init fails */
-		err = 0;
+	if (test_bit(ICE_FLAG_DCB_CAPABLE, pf->flags)) {
+		/* Note: DCB init failure is non-fatal to load */
+		if (ice_init_pf_dcb(pf, false)) {
+			clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags);
+			clear_bit(ICE_FLAG_DCB_ENA, pf->flags);
+		} else {
+			ice_cfg_lldp_mib_change(&pf->hw, true);
+		}
 	}
 
-	ice_determine_q_usage(pf);
-
 	pf->num_alloc_vsi = hw->func_caps.guar_num_vsi;
 	if (!pf->num_alloc_vsi) {
 		err = -EIO;

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

@@ -284,7 +284,7 @@ struct ice_sched_node *ice_sched_get_tc_node(struct ice_port_info *pi, u8 tc)
 {
 	u8 i;
 
-	if (!pi)
+	if (!pi || !pi->root)
 		return NULL;
 	for (i = 0; i < pi->root->num_children; i++)
 		if (pi->root->children[i]->tc_num == tc)

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

@@ -95,17 +95,16 @@ void ice_free_tx_ring(struct ice_ring *tx_ring)
 
 /**
  * ice_clean_tx_irq - Reclaim resources after transmit completes
- * @vsi: the VSI we care about
  * @tx_ring: Tx ring to clean
  * @napi_budget: Used to determine if we are in netpoll
  *
  * Returns true if there's any budget left (e.g. the clean is finished)
  */
-static bool
-ice_clean_tx_irq(struct ice_vsi *vsi, struct ice_ring *tx_ring, int napi_budget)
+static bool ice_clean_tx_irq(struct ice_ring *tx_ring, int napi_budget)
 {
 	unsigned int total_bytes = 0, total_pkts = 0;
-	unsigned int budget = vsi->work_lmt;
+	unsigned int budget = ICE_DFLT_IRQ_WORK;
+	struct ice_vsi *vsi = tx_ring->vsi;
 	s16 i = tx_ring->next_to_clean;
 	struct ice_tx_desc *tx_desc;
 	struct ice_tx_buf *tx_buf;
@@ -114,6 +113,8 @@ ice_clean_tx_irq(struct ice_vsi *vsi, struct ice_ring *tx_ring, int napi_budget)
 	tx_desc = ICE_TX_DESC(tx_ring, i);
 	i -= tx_ring->count;
 
+	prefetch(&vsi->state);
+
 	do {
 		struct ice_tx_desc *eop_desc = tx_buf->next_to_watch;
 
@@ -206,7 +207,7 @@ ice_clean_tx_irq(struct ice_vsi *vsi, struct ice_ring *tx_ring, int napi_budget)
 		smp_mb();
 		if (__netif_subqueue_stopped(tx_ring->netdev,
 					     tx_ring->q_index) &&
-		   !test_bit(__ICE_DOWN, vsi->state)) {
+		    !test_bit(__ICE_DOWN, vsi->state)) {
 			netif_wake_subqueue(tx_ring->netdev,
 					    tx_ring->q_index);
 			++tx_ring->tx_stats.restart_q;
@@ -879,7 +880,7 @@ ice_rx_hash(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc,
 
 /**
  * ice_rx_csum - Indicate in skb if checksum is good
- * @vsi: the VSI we care about
+ * @ring: the ring we care about
  * @skb: skb currently being received and modified
  * @rx_desc: the receive descriptor
  * @ptype: the packet type decoded by hardware
@@ -887,7 +888,7 @@ ice_rx_hash(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc,
  * skb->protocol must be set before this function is called
  */
 static void
-ice_rx_csum(struct ice_vsi *vsi, struct sk_buff *skb,
+ice_rx_csum(struct ice_ring *ring, struct sk_buff *skb,
 	    union ice_32b_rx_flex_desc *rx_desc, u8 ptype)
 {
 	struct ice_rx_ptype_decoded decoded;
@@ -904,7 +905,7 @@ ice_rx_csum(struct ice_vsi *vsi, struct sk_buff *skb,
 	skb_checksum_none_assert(skb);
 
 	/* check if Rx checksum is enabled */
-	if (!(vsi->netdev->features & NETIF_F_RXCSUM))
+	if (!(ring->netdev->features & NETIF_F_RXCSUM))
 		return;
 
 	/* check if HW has decoded the packet and checksum */
@@ -944,7 +945,7 @@ ice_rx_csum(struct ice_vsi *vsi, struct sk_buff *skb,
 	return;
 
 checksum_fail:
-	vsi->back->hw_csum_rx_error++;
+	ring->vsi->back->hw_csum_rx_error++;
 }
 
 /**
@@ -968,7 +969,7 @@ ice_process_skb_fields(struct ice_ring *rx_ring,
 	/* modifies the skb - consumes the enet header */
 	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
 
-	ice_rx_csum(rx_ring->vsi, skb, rx_desc, ptype);
+	ice_rx_csum(rx_ring, skb, rx_desc, ptype);
 }
 
 /**
@@ -1067,9 +1068,6 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 			continue;
 		}
 
-		rx_ptype = le16_to_cpu(rx_desc->wb.ptype_flex_flags0) &
-			ICE_RX_FLEX_DESC_PTYPE_M;
-
 		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_L2TAG1P_S);
 		if (ice_test_staterr(rx_desc, stat_err_bits))
 			vlan_tag = le16_to_cpu(rx_desc->wb.l2tag1);
@@ -1086,6 +1084,9 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 		total_rx_bytes += skb->len;
 
 		/* populate checksum, VLAN, and protocol */
+		rx_ptype = le16_to_cpu(rx_desc->wb.ptype_flex_flags0) &
+			ICE_RX_FLEX_DESC_PTYPE_M;
+
 		ice_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
 
 		/* send completed skb up the stack */
@@ -1225,6 +1226,8 @@ ice_update_itr(struct ice_q_vector *q_vector, struct ice_ring_container *rc)
 	if (time_after(next_update, rc->next_update))
 		goto clear_counts;
 
+	prefetch(q_vector->vsi->port_info);
+
 	packets = rc->total_pkts;
 	bytes = rc->total_bytes;
 
@@ -1354,14 +1357,13 @@ static u32 ice_buildreg_itr(u16 itr_idx, u16 itr)
 
 /**
  * ice_update_ena_itr - Update ITR and re-enable MSIX interrupt
- * @vsi: the VSI associated with the q_vector
  * @q_vector: q_vector for which ITR is being updated and interrupt enabled
  */
-static void
-ice_update_ena_itr(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
+static void ice_update_ena_itr(struct ice_q_vector *q_vector)
 {
 	struct ice_ring_container *tx = &q_vector->tx;
 	struct ice_ring_container *rx = &q_vector->rx;
+	struct ice_vsi *vsi = q_vector->vsi;
 	u32 itr_val;
 
 	/* when exiting WB_ON_ITR lets set a low ITR value and trigger
@@ -1419,15 +1421,14 @@ ice_update_ena_itr(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
 			q_vector->itr_countdown--;
 	}
 
-	if (!test_bit(__ICE_DOWN, vsi->state))
-		wr32(&vsi->back->hw,
+	if (!test_bit(__ICE_DOWN, q_vector->vsi->state))
+		wr32(&q_vector->vsi->back->hw,
 		     GLINT_DYN_CTL(q_vector->reg_idx),
 		     itr_val);
 }
 
 /**
  * ice_set_wb_on_itr - set WB_ON_ITR for this q_vector
- * @vsi: pointer to the VSI structure
  * @q_vector: q_vector to set WB_ON_ITR on
  *
  * We need to tell hardware to write-back completed descriptors even when
@@ -1440,9 +1441,10 @@ ice_update_ena_itr(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
  * value that's not 0 due to ITR granularity. Also, set the INTENA_MSK bit to
  * make sure hardware knows we aren't meddling with the INTENA_M bit.
  */
-static void
-ice_set_wb_on_itr(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
+static void ice_set_wb_on_itr(struct ice_q_vector *q_vector)
 {
+	struct ice_vsi *vsi = q_vector->vsi;
+
 	/* already in WB_ON_ITR mode no need to change it */
 	if (q_vector->itr_countdown == ICE_IN_WB_ON_ITR_MODE)
 		return;
@@ -1473,7 +1475,6 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct ice_q_vector *q_vector =
 				container_of(napi, struct ice_q_vector, napi);
-	struct ice_vsi *vsi = q_vector->vsi;
 	bool clean_complete = true;
 	struct ice_ring *ring;
 	int budget_per_ring;
@@ -1483,11 +1484,11 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 	 * budget and be more aggressive about cleaning up the Tx descriptors.
 	 */
 	ice_for_each_ring(ring, q_vector->tx)
-		if (!ice_clean_tx_irq(vsi, ring, budget))
+		if (!ice_clean_tx_irq(ring, budget))
 			clean_complete = false;
 
 	/* Handle case where we are called by netpoll with a budget of 0 */
-	if (budget <= 0)
+	if (unlikely(budget <= 0))
 		return budget;
 
 	/* normally we have 1 Rx ring per q_vector */
@@ -1519,9 +1520,9 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 	 * poll us due to busy-polling
 	 */
 	if (likely(napi_complete_done(napi, work_done)))
-		ice_update_ena_itr(vsi, q_vector);
+		ice_update_ena_itr(q_vector);
 	else
-		ice_set_wb_on_itr(vsi, q_vector);
+		ice_set_wb_on_itr(q_vector);
 
 	return min_t(int, work_done, budget - 1);
 }

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

@@ -129,7 +129,10 @@ static void ice_vc_notify_vf_link_state(struct ice_vf *vf)
 	pfe.event = VIRTCHNL_EVENT_LINK_CHANGE;
 	pfe.severity = PF_EVENT_SEVERITY_INFO;
 
-	if (vf->link_forced)
+	/* Always report link is down if the VF queues aren't enabled */
+	if (!vf->num_qs_ena)
+		ice_set_pfe_link(vf, &pfe, ICE_AQ_LINK_SPEED_UNKNOWN, false);
+	else if (vf->link_forced)
 		ice_set_pfe_link_forced(vf, &pfe, vf->link_up);
 	else
 		ice_set_pfe_link(vf, &pfe, ls->link_speed, ls->link_info &
@@ -353,12 +356,13 @@ void ice_free_vfs(struct ice_pf *pf)
  * ice_trigger_vf_reset - Reset a VF on HW
  * @vf: pointer to the VF structure
  * @is_vflr: true if VFLR was issued, false if not
+ * @is_pfr: true if the reset was triggered due to a previous PFR
  *
  * Trigger hardware to start a reset for a particular VF. Expects the caller
  * to wait the proper amount of time to allow hardware to reset the VF before
  * it cleans up and restores VF functionality.
  */
-static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr)
+static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr, bool is_pfr)
 {
 	struct ice_pf *pf = vf->pf;
 	u32 reg, reg_idx, bit_idx;
@@ -379,10 +383,13 @@ static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr)
 	 */
 	clear_bit(ICE_VF_STATE_INIT, vf->vf_states);
 
-	/* Clear the VF's ARQLEN register. This is how the VF detects reset,
-	 * since the VFGEN_RSTAT register doesn't stick at 0 after reset.
+	/* VF_MBX_ARQLEN is cleared by PFR, so the driver needs to clear it
+	 * in the case of VFR. If this is done for PFR, it can mess up VF
+	 * resets because the VF driver may already have started cleanup
+	 * by the time we get here.
 	 */
-	wr32(hw, VF_MBX_ARQLEN(vf_abs_id), 0);
+	if (!is_pfr)
+		wr32(hw, VF_MBX_ARQLEN(vf_abs_id), 0);
 
 	/* In the case of a VFLR, the HW has already reset the VF and we
 	 * just need to clean up, so don't hit the VFRTRIG register.
@@ -588,7 +595,8 @@ static int ice_alloc_vf_res(struct ice_vf *vf)
 	/* Update number of VF queues, in case VF had requested for queue
 	 * changes
 	 */
-	tx_rx_queue_left = min_t(int, pf->q_left_tx, pf->q_left_rx);
+	tx_rx_queue_left = min_t(int, ice_get_avail_txq_count(pf),
+				 ice_get_avail_rxq_count(pf));
 	tx_rx_queue_left += ICE_DFLT_QS_PER_VF;
 	if (vf->num_req_qs && vf->num_req_qs <= tx_rx_queue_left &&
 	    vf->num_req_qs != vf->num_vf_qs)
@@ -891,11 +899,11 @@ static int ice_check_avail_res(struct ice_pf *pf)
 	 * at runtime through Virtchnl, that is the reason we start by reserving
 	 * few queues.
 	 */
-	num_txq = ice_determine_res(pf, pf->q_left_tx, ICE_DFLT_QS_PER_VF,
-				    ICE_MIN_QS_PER_VF);
+	num_txq = ice_determine_res(pf, ice_get_avail_txq_count(pf),
+				    ICE_DFLT_QS_PER_VF, ICE_MIN_QS_PER_VF);
 
-	num_rxq = ice_determine_res(pf, pf->q_left_rx, ICE_DFLT_QS_PER_VF,
-				    ICE_MIN_QS_PER_VF);
+	num_rxq = ice_determine_res(pf, ice_get_avail_rxq_count(pf),
+				    ICE_DFLT_QS_PER_VF, ICE_MIN_QS_PER_VF);
 
 	if (!num_txq || !num_rxq)
 		return -EIO;
@@ -1072,7 +1080,7 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr)
 
 	/* Begin reset on all VFs at once */
 	for (v = 0; v < pf->num_alloc_vfs; v++)
-		ice_trigger_vf_reset(&pf->vf[v], is_vflr);
+		ice_trigger_vf_reset(&pf->vf[v], is_vflr, true);
 
 	for (v = 0; v < pf->num_alloc_vfs; v++) {
 		struct ice_vsi *vsi;
@@ -1172,7 +1180,7 @@ static bool ice_reset_vf(struct ice_vf *vf, bool is_vflr)
 	if (test_and_set_bit(ICE_VF_STATE_DIS, vf->vf_states))
 		return false;
 
-	ice_trigger_vf_reset(vf, is_vflr);
+	ice_trigger_vf_reset(vf, is_vflr, false);
 
 	vsi = pf->vsi[vf->lan_vsi_idx];
 
@@ -2504,7 +2512,8 @@ static int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg)
 	}
 
 	cur_queues = vf->num_vf_qs;
-	tx_rx_queue_left = min_t(u16, pf->q_left_tx, pf->q_left_rx);
+	tx_rx_queue_left = min_t(u16, ice_get_avail_txq_count(pf),
+				 ice_get_avail_rxq_count(pf));
 	max_allowed_vf_queues = tx_rx_queue_left + cur_queues;
 	if (!req_queues) {
 		dev_err(&pf->pdev->dev,
@@ -2927,6 +2936,7 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event)
 		break;
 	case VIRTCHNL_OP_GET_VF_RESOURCES:
 		err = ice_vc_get_vf_res_msg(vf, msg);
+		ice_vc_notify_vf_link_state(vf);
 		break;
 	case VIRTCHNL_OP_RESET_VF:
 		ice_vc_reset_vf_msg(vf);