Merge tag 'mlx5-updates-2022-05-09' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed  Mahameed says:

====================
mlx5-updates-2022-05-09

1) Gavin Li, adds exit route from waiting for FW init on device boot and
   increases FW init timeout on health recovery flow

2) Support 4 ports HCAs LAG mode

Mark Bloch Says:
================

This series adds to mlx5 drivers support for 4 ports HCAs.
Starting with ConnectX-7 HCAs with 4 ports are possible.

As most driver parts aren't affected by such configuration most driver
code is unchanged.

Specially the only affected areas are:
- Lag
- Devcom
- Merged E-Switch
- Single FDB E-Switch

Lag was chosen to be converted first. Creating hardware LAG when all 4
ports are added to the same bond device.

Devom, merge E-Switch and single FDB E-Switch, are marked as supporting
only 2 ports HCAs and future patches will add support for 4 ports HCAs.

In order to activate the hardware lag a user can execute the:

ip link add bond0 type bond
ip link set bond0 type bond miimon 100 mode 2
ip link set eth2 master bond0
ip link set eth3 master bond0
ip link set eth4 master bond0
ip link set eth5 master bond0

Where eth2, eth3, eth4 and eth5 are the PFs of the same HCA.

================

====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

drivers/infiniband/hw/mlx5/gsi.c

@@ -100,7 +100,7 @@ int mlx5_ib_create_gsi(struct ib_pd *pd, struct mlx5_ib_qp *mqp,
 				 port_type) == MLX5_CAP_PORT_TYPE_IB)
 			num_qps = pd->device->attrs.max_pkeys;
 		else if (dev->lag_active)
-			num_qps = MLX5_MAX_PORTS;
+			num_qps = dev->lag_ports;
 	}
 
 	gsi = &mqp->gsi;

drivers/infiniband/hw/mlx5/main.c

@@ -2991,6 +2991,7 @@ static int mlx5_eth_lag_init(struct mlx5_ib_dev *dev)
 	}
 
 	dev->flow_db->lag_demux_ft = ft;
+	dev->lag_ports = mlx5_lag_get_num_ports(mdev);
 	dev->lag_active = true;
 	return 0;
 

drivers/infiniband/hw/mlx5/mlx5_ib.h

@@ -1131,6 +1131,7 @@ struct mlx5_ib_dev {
 	struct xarray sig_mrs;
 	struct mlx5_port_caps port_caps[MLX5_MAX_PORTS];
 	u16 pkey_table_len;
+	u8 lag_ports;
 };
 
 static inline struct mlx5_ib_cq *to_mibcq(struct mlx5_core_cq *mcq)

drivers/infiniband/hw/mlx5/qp.c

@@ -3907,7 +3907,7 @@ static unsigned int get_tx_affinity_rr(struct mlx5_ib_dev *dev,
 		tx_port_affinity = &dev->port[port_num].roce.tx_port_affinity;
 
 	return (unsigned int)atomic_add_return(1, tx_port_affinity) %
-		MLX5_MAX_PORTS + 1;
+		(dev->lag_active ? dev->lag_ports : MLX5_CAP_GEN(dev->mdev, num_lag_ports)) + 1;
 }
 
 static bool qp_supports_affinity(struct mlx5_ib_qp *qp)

drivers/net/ethernet/mellanox/mlx5/core/Makefile

@@ -14,7 +14,7 @@ obj-$(CONFIG_MLX5_CORE) += mlx5_core.o
 mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		health.o mcg.o cq.o alloc.o port.o mr.o pd.o \
 		transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \
-		fs_counters.o fs_ft_pool.o rl.o lag/lag.o dev.o events.o wq.o lib/gid.o \
+		fs_counters.o fs_ft_pool.o rl.o lag/debugfs.o lag/lag.o dev.o events.o wq.o lib/gid.o \
 		lib/devcom.o lib/pci_vsc.o lib/dm.o lib/fs_ttc.o diag/fs_tracepoint.o \
 		diag/fw_tracer.o diag/crdump.o devlink.o diag/rsc_dump.o \
 		fw_reset.o qos.o lib/tout.o

drivers/net/ethernet/mellanox/mlx5/core/dev.c

@@ -555,12 +555,9 @@ static u32 mlx5_gen_pci_id(const struct mlx5_core_dev *dev)
 		     PCI_SLOT(dev->pdev->devfn));
 }
 
-static int next_phys_dev(struct device *dev, const void *data)
+static int _next_phys_dev(struct mlx5_core_dev *mdev,
+			  const struct mlx5_core_dev *curr)
 {
-	struct mlx5_adev *madev = container_of(dev, struct mlx5_adev, adev.dev);
-	struct mlx5_core_dev *mdev = madev->mdev;
-	const struct mlx5_core_dev *curr = data;
-
 	if (!mlx5_core_is_pf(mdev))
 		return 0;
 
@@ -574,16 +571,38 @@ static int next_phys_dev(struct device *dev, const void *data)
 	return 1;
 }
 
-/* Must be called with intf_mutex held */
-struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev)
+static int next_phys_dev(struct device *dev, const void *data)
+{
+	struct mlx5_adev *madev = container_of(dev, struct mlx5_adev, adev.dev);
+	struct mlx5_core_dev *mdev = madev->mdev;
+
+	return _next_phys_dev(mdev, data);
+}
+
+static int next_phys_dev_lag(struct device *dev, const void *data)
+{
+	struct mlx5_adev *madev = container_of(dev, struct mlx5_adev, adev.dev);
+	struct mlx5_core_dev *mdev = madev->mdev;
+
+	if (!MLX5_CAP_GEN(mdev, vport_group_manager) ||
+	    !MLX5_CAP_GEN(mdev, lag_master) ||
+	    (MLX5_CAP_GEN(mdev, num_lag_ports) > MLX5_MAX_PORTS ||
+	     MLX5_CAP_GEN(mdev, num_lag_ports) <= 1))
+		return 0;
+
+	return _next_phys_dev(mdev, data);
+}
+
+static struct mlx5_core_dev *mlx5_get_next_dev(struct mlx5_core_dev *dev,
+					       int (*match)(struct device *dev, const void *data))
 {
 	struct auxiliary_device *adev;
 	struct mlx5_adev *madev;
 
 	if (!mlx5_core_is_pf(dev))
 		return NULL;
 
-	adev = auxiliary_find_device(NULL, dev, &next_phys_dev);
+	adev = auxiliary_find_device(NULL, dev, match);
 	if (!adev)
 		return NULL;
 
@@ -592,6 +611,20 @@ struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev)
 	return madev->mdev;
 }
 
+/* Must be called with intf_mutex held */
+struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev)
+{
+	lockdep_assert_held(&mlx5_intf_mutex);
+	return mlx5_get_next_dev(dev, &next_phys_dev);
+}
+
+/* Must be called with intf_mutex held */
+struct mlx5_core_dev *mlx5_get_next_phys_dev_lag(struct mlx5_core_dev *dev)
+{
+	lockdep_assert_held(&mlx5_intf_mutex);
+	return mlx5_get_next_dev(dev, &next_phys_dev_lag);
+}
+
 void mlx5_dev_list_lock(void)
 {
 	mutex_lock(&mlx5_intf_mutex);

drivers/net/ethernet/mellanox/mlx5/core/devlink.c

@@ -178,13 +178,13 @@ static int mlx5_devlink_reload_up(struct devlink *devlink, enum devlink_reload_a
 	*actions_performed = BIT(action);
 	switch (action) {
 	case DEVLINK_RELOAD_ACTION_DRIVER_REINIT:
-		return mlx5_load_one(dev);
+		return mlx5_load_one(dev, false);
 	case DEVLINK_RELOAD_ACTION_FW_ACTIVATE:
 		if (limit == DEVLINK_RELOAD_LIMIT_NO_RESET)
 			break;
 		/* On fw_activate action, also driver is reloaded and reinit performed */
 		*actions_performed |= BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT);
-		return mlx5_load_one(dev);
+		return mlx5_load_one(dev, false);
 	default:
 		/* Unsupported action should not get to this function */
 		WARN_ON(1);

drivers/net/ethernet/mellanox/mlx5/core/eswitch.c

@@ -1569,9 +1569,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	ida_init(&esw->offloads.vport_metadata_ida);
 	xa_init_flags(&esw->offloads.vhca_map, XA_FLAGS_ALLOC);
 	mutex_init(&esw->state_lock);
-	lockdep_register_key(&esw->mode_lock_key);
 	init_rwsem(&esw->mode_lock);
-	lockdep_set_class(&esw->mode_lock, &esw->mode_lock_key);
 	refcount_set(&esw->qos.refcnt, 0);
 
 	esw->enabled_vports = 0;
@@ -1615,7 +1613,6 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
 	esw->dev->priv.eswitch = NULL;
 	destroy_workqueue(esw->work_queue);
 	WARN_ON(refcount_read(&esw->qos.refcnt));
-	lockdep_unregister_key(&esw->mode_lock_key);
 	mutex_destroy(&esw->state_lock);
 	WARN_ON(!xa_empty(&esw->offloads.vhca_map));
 	xa_destroy(&esw->offloads.vhca_map);
@@ -1893,17 +1890,6 @@ mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev)
 }
 EXPORT_SYMBOL(mlx5_eswitch_get_encap_mode);
 
-bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, struct mlx5_core_dev *dev1)
-{
-	if ((dev0->priv.eswitch->mode == MLX5_ESWITCH_NONE &&
-	     dev1->priv.eswitch->mode == MLX5_ESWITCH_NONE) ||
-	    (dev0->priv.eswitch->mode == MLX5_ESWITCH_OFFLOADS &&
-	     dev1->priv.eswitch->mode == MLX5_ESWITCH_OFFLOADS))
-		return true;
-
-	return false;
-}
-
 bool mlx5_esw_multipath_prereq(struct mlx5_core_dev *dev0,
 			       struct mlx5_core_dev *dev1)
 {
@@ -2014,17 +2000,6 @@ void mlx5_esw_unlock(struct mlx5_eswitch *esw)
 	up_write(&esw->mode_lock);
 }
 
-/**
- * mlx5_esw_lock() - Take write lock on esw mode lock
- * @esw: eswitch device.
- */
-void mlx5_esw_lock(struct mlx5_eswitch *esw)
-{
-	if (!mlx5_esw_allowed(esw))
-		return;
-	down_write(&esw->mode_lock);
-}
-
 /**
  * mlx5_eswitch_get_total_vports - Get total vports of the eswitch
  *

drivers/net/ethernet/mellanox/mlx5/core/eswitch.h

@@ -331,7 +331,6 @@ struct mlx5_eswitch {
 		u32             large_group_num;
 	}  params;
 	struct blocking_notifier_head n_head;
-	struct lock_class_key mode_lock_key;
 };
 
 void esw_offloads_disable(struct mlx5_eswitch *esw);
@@ -518,8 +517,6 @@ static inline bool mlx5_eswitch_vlan_actions_supported(struct mlx5_core_dev *dev
 		MLX5_CAP_ESW_FLOWTABLE_FDB(dev, push_vlan_2);
 }
 
-bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0,
-			 struct mlx5_core_dev *dev1);
 bool mlx5_esw_multipath_prereq(struct mlx5_core_dev *dev0,
 			       struct mlx5_core_dev *dev1);
 
@@ -706,7 +703,6 @@ void mlx5_esw_get(struct mlx5_core_dev *dev);
 void mlx5_esw_put(struct mlx5_core_dev *dev);
 int mlx5_esw_try_lock(struct mlx5_eswitch *esw);
 void mlx5_esw_unlock(struct mlx5_eswitch *esw);
-void mlx5_esw_lock(struct mlx5_eswitch *esw);
 
 void esw_vport_change_handle_locked(struct mlx5_vport *vport);
 
@@ -724,7 +720,6 @@ static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
 static inline void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) {}
 static inline int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) { return 0; }
 static inline void mlx5_eswitch_disable(struct mlx5_eswitch *esw, bool clear_vf) {}
-static inline bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, struct mlx5_core_dev *dev1) { return true; }
 static inline bool mlx5_eswitch_is_funcs_handler(struct mlx5_core_dev *dev) { return false; }
 static inline
 int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, u16 vport, int link_state) { return 0; }
@@ -733,9 +728,6 @@ static inline const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev)
 	return ERR_PTR(-EOPNOTSUPP);
 }
 
-static inline void mlx5_esw_unlock(struct mlx5_eswitch *esw) { return; }
-static inline void mlx5_esw_lock(struct mlx5_eswitch *esw) { return; }
-
 static inline struct mlx5_flow_handle *
 esw_add_restore_rule(struct mlx5_eswitch *esw, u32 tag)
 {

drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c

@@ -148,7 +148,7 @@ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev)
 	if (test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags)) {
 		complete(&fw_reset->done);
 	} else {
-		mlx5_load_one(dev);
+		mlx5_load_one(dev, false);
 		devlink_remote_reload_actions_performed(priv_to_devlink(dev), 0,
 							BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) |
 							BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE));