ice: Add initial support framework for LAG

Add the framework and initial implementation for receiving and processing
netdev bonding events.  This is only the software support and the
implementation of the HW offload for bonding support will be coming at a
later time.  There are some architectural gaps that need to be closed
before that happens.

Because this is a software only solution that supports in kernel bonding,
SR-IOV is not supported with this implementation.
Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>

drivers/net/ethernet/intel/ice/Makefile

@@ -24,6 +24,7 @@ ice-y := ice_main.o	\
 	 ice_flow.o	\
 	 ice_devlink.o	\
 	 ice_fw_update.o \
+	 ice_lag.o	\
 	 ice_ethtool.o
 ice-$(CONFIG_PCI_IOV) += ice_virtchnl_pf.o ice_sriov.o
 ice-$(CONFIG_DCB) += ice_dcb.o ice_dcb_nl.o ice_dcb_lib.o

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

@@ -56,6 +56,7 @@
 #include "ice_fdir.h"
 #include "ice_xsk.h"
 #include "ice_arfs.h"
+#include "ice_lag.h"
 
 #define ICE_BAR0		0
 #define ICE_REQ_DESC_MULTIPLE	32
@@ -453,6 +454,7 @@ struct ice_pf {
 	__le64 nvm_phy_type_lo; /* NVM PHY type low */
 	__le64 nvm_phy_type_hi; /* NVM PHY type high */
 	struct ice_link_default_override_tlv link_dflt_override;
+	struct ice_lag *lag; /* Link Aggregation information */
 };
 
 struct ice_netdev_priv {
@@ -553,11 +555,31 @@ static inline struct ice_vsi *ice_get_ctrl_vsi(struct ice_pf *pf)
 	return pf->vsi[pf->ctrl_vsi_idx];
 }
 
+/**
+ * ice_set_sriov_cap - enable SRIOV in PF flags
+ * @pf: PF struct
+ */
+static inline void ice_set_sriov_cap(struct ice_pf *pf)
+{
+	if (pf->hw.func_caps.common_cap.sr_iov_1_1)
+		set_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags);
+}
+
+/**
+ * ice_clear_sriov_cap - disable SRIOV in PF flags
+ * @pf: PF struct
+ */
+static inline void ice_clear_sriov_cap(struct ice_pf *pf)
+{
+	clear_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags);
+}
+
 #define ICE_FD_STAT_CTR_BLOCK_COUNT	256
 #define ICE_FD_STAT_PF_IDX(base_idx) \
 			((base_idx) * ICE_FD_STAT_CTR_BLOCK_COUNT)
 #define ICE_FD_SB_STAT_IDX(base_idx) ICE_FD_STAT_PF_IDX(base_idx)
 
+bool netif_is_ice(struct net_device *dev);
 int ice_vsi_setup_tx_rings(struct ice_vsi *vsi);
 int ice_vsi_setup_rx_rings(struct ice_vsi *vsi);
 int ice_vsi_open_ctrl(struct ice_vsi *vsi);

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

+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2018-2021, Intel Corporation. */
+
+#ifndef _ICE_LAG_H_
+#define _ICE_LAG_H_
+
+#include <linux/netdevice.h>
+
+/* LAG roles for netdev */
+enum ice_lag_role {
+	ICE_LAG_NONE,
+	ICE_LAG_PRIMARY,
+	ICE_LAG_BACKUP,
+	ICE_LAG_UNSET
+};
+
+struct ice_pf;
+
+/* LAG info struct */
+struct ice_lag {
+	struct ice_pf *pf; /* backlink to PF struct */
+	struct net_device *netdev; /* this PF's netdev */
+	struct net_device *peer_netdev;
+	struct net_device *upper_netdev; /* upper bonding netdev */
+	struct notifier_block notif_block;
+	u8 bonded:1; /* currently bonded */
+	u8 master:1; /* this is a master */
+	u8 handler:1; /* did we register a rx_netdev_handler */
+	/* each thing blocking bonding will increment this value by one.
+	 * If this value is zero, then bonding is allowed.
+	 */
+	u16 dis_lag;
+	u8 role;
+};
+
+int ice_init_lag(struct ice_pf *pf);
+void ice_deinit_lag(struct ice_pf *pf);
+rx_handler_result_t ice_lag_nop_handler(struct sk_buff **pskb);
+
+/**
+ * ice_disable_lag - increment LAG disable count
+ * @lag: LAG struct
+ */
+static inline void ice_disable_lag(struct ice_lag *lag)
+{
+	/* If LAG this PF is not already disabled, disable it */
+	rtnl_lock();
+	if (!netdev_is_rx_handler_busy(lag->netdev)) {
+		if (!netdev_rx_handler_register(lag->netdev,
+						ice_lag_nop_handler,
+						NULL))
+			lag->handler = true;
+	}
+	rtnl_unlock();
+	lag->dis_lag++;
+}
+
+/**
+ * ice_enable_lag - decrement disable count for a PF
+ * @lag: LAG struct
+ *
+ * Decrement the disable counter for a port, and if that count reaches
+ * zero, then remove the no-op Rx handler from that netdev
+ */
+static inline void ice_enable_lag(struct ice_lag *lag)
+{
+	if (lag->dis_lag)
+		lag->dis_lag--;
+	if (!lag->dis_lag && lag->handler) {
+		rtnl_lock();
+		netdev_rx_handler_unregister(lag->netdev);
+		rtnl_unlock();
+		lag->handler = false;
+	}
+}
+
+/**
+ * ice_is_lag_dis - is LAG disabled
+ * @lag: LAG struct
+ *
+ * Return true if bonding is disabled
+ */
+static inline bool ice_is_lag_dis(struct ice_lag *lag)
+{
+	return !!(lag->dis_lag);
+}
+#endif /* _ICE_LAG_H_ */

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

@@ -2349,6 +2349,8 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 unroll_get_qs:
 	ice_vsi_put_qs(vsi);
 unroll_vsi_alloc:
+	if (vsi_type == ICE_VSI_VF)
+		ice_enable_lag(pf->lag);
 	ice_vsi_clear(vsi);
 
 	return NULL;

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

@@ -44,6 +44,11 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type);
 
 static void ice_vsi_release_all(struct ice_pf *pf);
 
+bool netif_is_ice(struct net_device *dev)
+{
+	return dev && (dev->netdev_ops == &ice_netdev_ops);
+}
+
 /**
  * ice_get_tx_pending - returns number of Tx descriptors not processed
  * @ring: the ring of descriptors
@@ -4235,6 +4240,9 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 		ice_cfg_lldp_mib_change(&pf->hw, true);
 	}
 
+	if (ice_init_lag(pf))
+		dev_warn(dev, "Failed to init link aggregation support\n");
+
 	/* print PCI link speed and width */
 	pcie_print_link_status(pf->pdev);
 
@@ -4357,6 +4365,7 @@ static void ice_remove(struct pci_dev *pdev)
 	ice_aq_cancel_waiting_tasks(pf);
 
 	mutex_destroy(&(&pf->hw)->fdir_fltr_lock);
+	ice_deinit_lag(pf);
 	if (!ice_is_safe_mode(pf))
 		ice_remove_arfs(pf);
 	ice_setup_mc_magic_wake(pf);

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

@@ -1677,6 +1677,8 @@ int ice_sriov_configure(struct pci_dev *pdev, int num_vfs)
 	if (!num_vfs) {
 		if (!pci_vfs_assigned(pdev)) {
 			ice_free_vfs(pf);
+			if (pf->lag)
+				ice_enable_lag(pf->lag);
 			return 0;
 		}
 
@@ -1688,6 +1690,8 @@ int ice_sriov_configure(struct pci_dev *pdev, int num_vfs)
 	if (err)
 		return err;
 
+	if (pf->lag)
+		ice_disable_lag(pf->lag);
 	return num_vfs;
 }