Merge remote-tracking branch 'mlx5-next/mlx5-next' into HEAD

Take mlx5-next so we can take a dependent two patch series next.
Signed-off-by: Doug Ledford <dledford@redhat.com>

drivers/infiniband/hw/mlx5/ib_rep.c

@@ -60,7 +60,7 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	if (!__mlx5_ib_add(ibdev, profile))
 		return -EINVAL;
 
-	rep->rep_if[REP_IB].priv = ibdev;
+	rep->rep_data[REP_IB].priv = ibdev;
 
 	return 0;
 }
@@ -70,13 +70,13 @@ mlx5_ib_vport_rep_unload(struct mlx5_eswitch_rep *rep)
 {
 	struct mlx5_ib_dev *dev;
 
-	if (!rep->rep_if[REP_IB].priv ||
+	if (!rep->rep_data[REP_IB].priv ||
 	    rep->vport != MLX5_VPORT_UPLINK)
 		return;
 
 	dev = mlx5_ib_rep_to_dev(rep);
 	__mlx5_ib_remove(dev, dev->profile, MLX5_IB_STAGE_MAX);
-	rep->rep_if[REP_IB].priv = NULL;
+	rep->rep_data[REP_IB].priv = NULL;
 }
 
 static void *mlx5_ib_vport_get_proto_dev(struct mlx5_eswitch_rep *rep)
@@ -84,16 +84,17 @@ static void *mlx5_ib_vport_get_proto_dev(struct mlx5_eswitch_rep *rep)
 	return mlx5_ib_rep_to_dev(rep);
 }
 
+static const struct mlx5_eswitch_rep_ops rep_ops = {
+	.load = mlx5_ib_vport_rep_load,
+	.unload = mlx5_ib_vport_rep_unload,
+	.get_proto_dev = mlx5_ib_vport_get_proto_dev,
+};
+
 void mlx5_ib_register_vport_reps(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_eswitch *esw = mdev->priv.eswitch;
-	struct mlx5_eswitch_rep_if rep_if = {};
-
-	rep_if.load = mlx5_ib_vport_rep_load;
-	rep_if.unload = mlx5_ib_vport_rep_unload;
-	rep_if.get_proto_dev = mlx5_ib_vport_get_proto_dev;
 
-	mlx5_eswitch_register_vport_reps(esw, &rep_if, REP_IB);
+	mlx5_eswitch_register_vport_reps(esw, &rep_ops, REP_IB);
 }
 
 void mlx5_ib_unregister_vport_reps(struct mlx5_core_dev *mdev)

drivers/infiniband/hw/mlx5/ib_rep.h

@@ -72,6 +72,6 @@ struct net_device *mlx5_ib_get_rep_netdev(struct mlx5_eswitch *esw,
 static inline
 struct mlx5_ib_dev *mlx5_ib_rep_to_dev(struct mlx5_eswitch_rep *rep)
 {
-	return (struct mlx5_ib_dev *)rep->rep_if[REP_IB].priv;
+	return rep->rep_data[REP_IB].priv;
 }
 #endif /* __MLX5_IB_REP_H__ */

drivers/infiniband/hw/mlx5/mlx5_ib.h

@@ -920,6 +920,7 @@ struct mlx5_ib_lb_state {
 };
 
 struct mlx5_ib_pf_eq {
+	struct notifier_block irq_nb;
 	struct mlx5_ib_dev *dev;
 	struct mlx5_eq *core;
 	struct work_struct work;

drivers/infiniband/hw/mlx5/odp.c

@@ -1485,9 +1485,11 @@ static void mlx5_ib_eq_pf_process(struct mlx5_ib_pf_eq *eq)
 	mlx5_eq_update_ci(eq->core, cc, 1);
 }
 
-static irqreturn_t mlx5_ib_eq_pf_int(int irq, void *eq_ptr)
+static int mlx5_ib_eq_pf_int(struct notifier_block *nb, unsigned long type,
+			     void *data)
 {
-	struct mlx5_ib_pf_eq *eq = eq_ptr;
+	struct mlx5_ib_pf_eq *eq =
+		container_of(nb, struct mlx5_ib_pf_eq, irq_nb);
 	unsigned long flags;
 
 	if (spin_trylock_irqsave(&eq->lock, flags)) {
@@ -1550,20 +1552,26 @@ mlx5_ib_create_pf_eq(struct mlx5_ib_dev *dev, struct mlx5_ib_pf_eq *eq)
 		goto err_mempool;
 	}
 
+	eq->irq_nb.notifier_call = mlx5_ib_eq_pf_int;
 	param = (struct mlx5_eq_param) {
-		.index = MLX5_EQ_PFAULT_IDX,
+		.irq_index = 0,
 		.mask = 1 << MLX5_EVENT_TYPE_PAGE_FAULT,
 		.nent = MLX5_IB_NUM_PF_EQE,
-		.context = eq,
-		.handler = mlx5_ib_eq_pf_int
 	};
-	eq->core = mlx5_eq_create_generic(dev->mdev, "mlx5_ib_page_fault_eq", &param);
+	eq->core = mlx5_eq_create_generic(dev->mdev, &param);
 	if (IS_ERR(eq->core)) {
 		err = PTR_ERR(eq->core);
 		goto err_wq;
 	}
+	err = mlx5_eq_enable(dev->mdev, eq->core, &eq->irq_nb);
+	if (err) {
+		mlx5_ib_err(dev, "failed to enable odp EQ %d\n", err);
+		goto err_eq;
+	}
 
 	return 0;
+err_eq:
+	mlx5_eq_destroy_generic(dev->mdev, eq->core);
 err_wq:
 	destroy_workqueue(eq->wq);
 err_mempool:
@@ -1576,6 +1584,7 @@ mlx5_ib_destroy_pf_eq(struct mlx5_ib_dev *dev, struct mlx5_ib_pf_eq *eq)
 {
 	int err;
 
+	mlx5_eq_disable(dev->mdev, eq->core, &eq->irq_nb);
 	err = mlx5_eq_destroy_generic(dev->mdev, eq->core);
 	cancel_work_sync(&eq->work);
 	destroy_workqueue(eq->wq);

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

@@ -13,7 +13,7 @@ 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 qp.o port.o mr.o pd.o \
-		transobj.o vport.o sriov.o fs_cmd.o fs_core.o \
+		transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \
 		fs_counters.o rl.o lag.o dev.o events.o wq.o lib/gid.o \
 		lib/devcom.o diag/fs_tracepoint.o diag/fw_tracer.o
 

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

@@ -316,7 +316,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_DESTROY_GENERAL_OBJECT:
 	case MLX5_CMD_OP_DEALLOC_MEMIC:
 	case MLX5_CMD_OP_PAGE_FAULT_RESUME:
-	case MLX5_CMD_OP_QUERY_HOST_PARAMS:
+	case MLX5_CMD_OP_QUERY_ESW_FUNCTIONS:
 		return MLX5_CMD_STAT_OK;
 
 	case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -628,7 +628,7 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(QUERY_MODIFY_HEADER_CONTEXT);
 	MLX5_COMMAND_STR_CASE(ALLOC_MEMIC);
 	MLX5_COMMAND_STR_CASE(DEALLOC_MEMIC);
-	MLX5_COMMAND_STR_CASE(QUERY_HOST_PARAMS);
+	MLX5_COMMAND_STR_CASE(QUERY_ESW_FUNCTIONS);
 	default: return "unknown command opcode";
 	}
 }

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

@@ -83,30 +83,3 @@ void mlx5_ec_cleanup(struct mlx5_core_dev *dev)
 
 	mlx5_peer_pf_cleanup(dev);
 }
-
-static int mlx5_query_host_params_context(struct mlx5_core_dev *dev,
-					  u32 *out, int outlen)
-{
-	u32 in[MLX5_ST_SZ_DW(query_host_params_in)] = {};
-
-	MLX5_SET(query_host_params_in, in, opcode,
-		 MLX5_CMD_OP_QUERY_HOST_PARAMS);
-
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
-}
-
-int mlx5_query_host_params_num_vfs(struct mlx5_core_dev *dev, int *num_vf)
-{
-	u32 out[MLX5_ST_SZ_DW(query_host_params_out)] = {};
-	int err;
-
-	err = mlx5_query_host_params_context(dev, out, sizeof(out));
-	if (err)
-		return err;
-
-	*num_vf = MLX5_GET(query_host_params_out, out,
-			   host_params_context.host_num_of_vfs);
-	mlx5_core_dbg(dev, "host_num_of_vfs %d\n", *num_vf);
-
-	return 0;
-}

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

@@ -16,7 +16,6 @@ enum {
 bool mlx5_read_embedded_cpu(struct mlx5_core_dev *dev);
 int mlx5_ec_init(struct mlx5_core_dev *dev);
 void mlx5_ec_cleanup(struct mlx5_core_dev *dev);
-int mlx5_query_host_params_num_vfs(struct mlx5_core_dev *dev, int *num_vf);
 
 #else  /* CONFIG_MLX5_ESWITCH */
 
@@ -24,9 +23,6 @@ static inline bool
 mlx5_read_embedded_cpu(struct mlx5_core_dev *dev) { return false; }
 static inline int mlx5_ec_init(struct mlx5_core_dev *dev) { return 0; }
 static inline void mlx5_ec_cleanup(struct mlx5_core_dev *dev) {}
-static inline int
-mlx5_query_host_params_num_vfs(struct mlx5_core_dev *dev, int *num_vf)
-{ return -EOPNOTSUPP; }
 
 #endif /* CONFIG_MLX5_ESWITCH */
 

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

@@ -1752,7 +1752,7 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	}
 
 	rpriv->netdev = netdev;
-	rep->rep_if[REP_ETH].priv = rpriv;
+	rep->rep_data[REP_ETH].priv = rpriv;
 	INIT_LIST_HEAD(&rpriv->vport_sqs_list);
 
 	if (rep->vport == MLX5_VPORT_UPLINK) {
@@ -1826,16 +1826,17 @@ static void *mlx5e_vport_rep_get_proto_dev(struct mlx5_eswitch_rep *rep)
 	return rpriv->netdev;
 }
 
+static const struct mlx5_eswitch_rep_ops rep_ops = {
+	.load = mlx5e_vport_rep_load,
+	.unload = mlx5e_vport_rep_unload,
+	.get_proto_dev = mlx5e_vport_rep_get_proto_dev
+};
+
 void mlx5e_rep_register_vport_reps(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_eswitch *esw = mdev->priv.eswitch;
-	struct mlx5_eswitch_rep_if rep_if = {};
-
-	rep_if.load = mlx5e_vport_rep_load;
-	rep_if.unload = mlx5e_vport_rep_unload;
-	rep_if.get_proto_dev = mlx5e_vport_rep_get_proto_dev;
 
-	mlx5_eswitch_register_vport_reps(esw, &rep_if, REP_ETH);
+	mlx5_eswitch_register_vport_reps(esw, &rep_ops, REP_ETH);
 }
 
 void mlx5e_rep_unregister_vport_reps(struct mlx5_core_dev *mdev)

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

@@ -91,7 +91,7 @@ struct mlx5e_rep_priv {
 static inline
 struct mlx5e_rep_priv *mlx5e_rep_to_rep_priv(struct mlx5_eswitch_rep *rep)
 {
-	return (struct mlx5e_rep_priv *)rep->rep_if[REP_ETH].priv;
+	return rep->rep_data[REP_ETH].priv;
 }
 
 struct mlx5e_neigh {

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

@@ -1686,13 +1686,23 @@ static int eswitch_vport_event(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
+int mlx5_esw_query_functions(struct mlx5_core_dev *dev, u32 *out, int outlen)
+{
+	u32 in[MLX5_ST_SZ_DW(query_esw_functions_in)] = {};
+
+	MLX5_SET(query_esw_functions_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_ESW_FUNCTIONS);
+
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
+}
+
 /* Public E-Switch API */
 #define ESW_ALLOWED(esw) ((esw) && MLX5_ESWITCH_MANAGER((esw)->dev))
 
 int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 {
-	int vf_nvports = 0, total_nvports = 0;
 	struct mlx5_vport *vport;
+	int total_nvports = 0;
 	int err;
 	int i, enabled_events;
 
@@ -1711,16 +1721,11 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 	esw_info(esw->dev, "E-Switch enable SRIOV: nvfs(%d) mode (%d)\n", nvfs, mode);
 
 	if (mode == SRIOV_OFFLOADS) {
-		if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
-			err = mlx5_query_host_params_num_vfs(esw->dev, &vf_nvports);
-			if (err)
-				return err;
+		if (mlx5_core_is_ecpf_esw_manager(esw->dev))
 			total_nvports = esw->total_vports;
-		} else {
-			vf_nvports = nvfs;
+		else
 			total_nvports = nvfs + MLX5_SPECIAL_VPORTS(esw->dev);
 	}
-	}
 
 	esw->mode = mode;
 
@@ -1733,7 +1738,7 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 	} else {
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH);
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
-		err = esw_offloads_init(esw, vf_nvports, total_nvports);
+		err = esw_offloads_init(esw, nvfs, total_nvports);
 	}
 
 	if (err)
@@ -2452,6 +2457,17 @@ u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw)
 }
 EXPORT_SYMBOL_GPL(mlx5_eswitch_mode);
 
+enum devlink_eswitch_encap_mode
+mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev)
+{
+	struct mlx5_eswitch *esw;
+
+	esw = dev->priv.eswitch;
+	return ESW_ALLOWED(esw) ? esw->offloads.encap :
+		DEVLINK_ESWITCH_ENCAP_MODE_NONE;
+}
+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 == SRIOV_NONE &&

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

@@ -173,9 +173,10 @@ struct mlx5_esw_offload {
 	struct mutex peer_mutex;
 	DECLARE_HASHTABLE(encap_tbl, 8);
 	DECLARE_HASHTABLE(mod_hdr_tbl, 8);
+	const struct mlx5_eswitch_rep_ops *rep_ops[NUM_REP_TYPES];
 	u8 inline_mode;
 	u64 num_flows;
-	u8 encap;
+	enum devlink_eswitch_encap_mode encap;
 };
 
 /* E-Switch MC FDB table hash node */
@@ -190,7 +191,7 @@ struct mlx5_host_work {
 	struct mlx5_eswitch	*esw;
 };
 
-struct mlx5_host_info {
+struct mlx5_esw_functions {
 	struct mlx5_nb		nb;
 	u16			num_vfs;
 };
@@ -219,7 +220,7 @@ struct mlx5_eswitch {
 	int                     mode;
 	int                     nvports;
 	u16                     manager_vport;
-	struct mlx5_host_info	host_info;
+	struct mlx5_esw_functions esw_funcs;
 };
 
 void esw_offloads_cleanup(struct mlx5_eswitch *esw);
@@ -356,9 +357,11 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode,
 					 struct netlink_ext_ack *extack);
 int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode);
 int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode);
-int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap,
+int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink,
+					enum devlink_eswitch_encap_mode encap,
 					struct netlink_ext_ack *extack);
-int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, u8 *encap);
+int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink,
+					enum devlink_eswitch_encap_mode *encap);
 void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type);
 
 int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
@@ -386,6 +389,8 @@ bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0,
 bool mlx5_esw_multipath_prereq(struct mlx5_core_dev *dev0,
 			       struct mlx5_core_dev *dev1);
 
+int mlx5_esw_query_functions(struct mlx5_core_dev *dev, u32 *out, int outlen);
+
 #define MLX5_DEBUG_ESWITCH_MASK BIT(3)
 
 #define esw_info(__dev, format, ...)			\
@@ -404,6 +409,18 @@ static inline u16 mlx5_eswitch_manager_vport(struct mlx5_core_dev *dev)
 		MLX5_VPORT_ECPF : MLX5_VPORT_PF;
 }
 
+static inline bool mlx5_eswitch_is_funcs_handler(struct mlx5_core_dev *dev)
+{
+	/* Ideally device should have the functions changed supported
+	 * capability regardless of it being ECPF or PF wherever such
+	 * event should be processed such as on eswitch manager device.
+	 * However, some ECPF based device might not have this capability
+	 * set. Hence OR for ECPF check to cover such device.
+	 */
+	return MLX5_CAP_ESW(dev, esw_functions_changed) ||
+	       mlx5_core_is_ecpf_esw_manager(dev);
+}
+
 static inline int mlx5_eswitch_uplink_idx(struct mlx5_eswitch *esw)
 {
 	/* Uplink always locate at the last element of the array.*/
@@ -498,6 +515,12 @@ static inline void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) {}
 static inline int  mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) { return 0; }
 static inline void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) {}
 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_esw_query_functions(struct mlx5_core_dev *dev, u32 *out, int outlen)
+{
+	return -EOPNOTSUPP;
+}
 
 #define FDB_MAX_CHAIN 1
 #define FDB_SLOW_PATH_CHAIN (FDB_MAX_CHAIN + 1)

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

@@ -108,8 +108,8 @@ static const char *eqe_type_str(u8 type)
 		return "MLX5_EVENT_TYPE_STALL_EVENT";
 	case MLX5_EVENT_TYPE_CMD:
 		return "MLX5_EVENT_TYPE_CMD";
-	case MLX5_EVENT_TYPE_HOST_PARAMS_CHANGE:
-		return "MLX5_EVENT_TYPE_HOST_PARAMS_CHANGE";
+	case MLX5_EVENT_TYPE_ESW_FUNCTIONS_CHANGED:
+		return "MLX5_EVENT_TYPE_ESW_FUNCTIONS_CHANGED";
 	case MLX5_EVENT_TYPE_PAGE_REQUEST:
 		return "MLX5_EVENT_TYPE_PAGE_REQUEST";
 	case MLX5_EVENT_TYPE_PAGE_FAULT:

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

@@ -147,6 +147,7 @@ static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns,
 {
 	int en_encap = !!(ft->flags & MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT);
 	int en_decap = !!(ft->flags & MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);
+	int term = !!(ft->flags & MLX5_FLOW_TABLE_TERMINATION);
 	u32 out[MLX5_ST_SZ_DW(create_flow_table_out)] = {0};
 	u32 in[MLX5_ST_SZ_DW(create_flow_table_in)]   = {0};
 	struct mlx5_core_dev *dev = ns->dev;
@@ -167,6 +168,8 @@ static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns,
 		 en_decap);
 	MLX5_SET(create_flow_table_in, in, flow_table_context.reformat_en,
 		 en_encap);
+	MLX5_SET(create_flow_table_in, in, flow_table_context.termination_table,
+		 term);
 
 	switch (ft->op_mod) {
 	case FS_FT_OP_MOD_NORMAL:

drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h

@@ -7,7 +7,6 @@
 #include <linux/mlx5/eq.h>
 #include <linux/mlx5/cq.h>
 
-#define MLX5_MAX_IRQ_NAME   (32)
 #define MLX5_EQE_SIZE       (sizeof(struct mlx5_eqe))
 
 struct mlx5_eq_tasklet {
@@ -36,8 +35,14 @@ struct mlx5_eq {
 	struct mlx5_rsc_debug   *dbg;
 };
 
+struct mlx5_eq_async {
+	struct mlx5_eq          core;
+	struct notifier_block   irq_nb;
+};
+
 struct mlx5_eq_comp {
-	struct mlx5_eq          core; /* Must be first */
+	struct mlx5_eq          core;
+	struct notifier_block   irq_nb;
 	struct mlx5_eq_tasklet  tasklet_ctx;
 	struct list_head        list;
 };

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

@@ -169,18 +169,28 @@ static struct mlx5_profile profile[] = {
 
 #define FW_INIT_TIMEOUT_MILI		2000
 #define FW_INIT_WAIT_MS			2
-#define FW_PRE_INIT_TIMEOUT_MILI	10000
+#define FW_PRE_INIT_TIMEOUT_MILI	120000
+#define FW_INIT_WARN_MESSAGE_INTERVAL	20000
 
-static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili)
+static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili,
+			u32 warn_time_mili)
 {
+	unsigned long warn = jiffies + msecs_to_jiffies(warn_time_mili);
 	unsigned long end = jiffies + msecs_to_jiffies(max_wait_mili);
 	int err = 0;
 
+	BUILD_BUG_ON(FW_PRE_INIT_TIMEOUT_MILI < FW_INIT_WARN_MESSAGE_INTERVAL);
+
 	while (fw_initializing(dev)) {
 		if (time_after(jiffies, end)) {
 			err = -EBUSY;
 			break;
 		}
+		if (warn_time_mili && time_after(jiffies, warn)) {
+			mlx5_core_warn(dev, "Waiting for FW initialization, timeout abort in %ds\n",
+				       jiffies_to_msecs(end - warn) / 1000);
+			warn = jiffies + msecs_to_jiffies(warn_time_mili);
+		}
 		msleep(FW_INIT_WAIT_MS);
 	}
 
@@ -794,10 +804,16 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 		goto err_devcom;
 	}
 
+	err = mlx5_irq_table_init(dev);
+	if (err) {
+		mlx5_core_err(dev, "failed to initialize irq table\n");
+		goto err_devcom;
+	}
+
 	err = mlx5_eq_table_init(dev);
 	if (err) {
 		mlx5_core_err(dev, "failed to initialize eq\n");
-		goto err_devcom;
+		goto err_irq_cleanup;
 	}
 
 	err = mlx5_events_init(dev);
@@ -834,32 +850,32 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 		goto err_rl_cleanup;
 	}
 
-	err = mlx5_eswitch_init(dev);
+	err = mlx5_sriov_init(dev);
 	if (err) {
-		mlx5_core_err(dev, "Failed to init eswitch %d\n", err);
+		mlx5_core_err(dev, "Failed to init sriov %d\n", err);
 		goto err_mpfs_cleanup;
 	}
 
-	err = mlx5_sriov_init(dev);
+	err = mlx5_eswitch_init(dev);
 	if (err) {
-		mlx5_core_err(dev, "Failed to init sriov %d\n", err);
-		goto err_eswitch_cleanup;
+		mlx5_core_err(dev, "Failed to init eswitch %d\n", err);
+		goto err_sriov_cleanup;
 	}
 
 	err = mlx5_fpga_init(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed to init fpga device %d\n", err);
-		goto err_sriov_cleanup;
+		goto err_eswitch_cleanup;
 	}
 
 	dev->tracer = mlx5_fw_tracer_create(dev);
 
 	return 0;
 
-err_sriov_cleanup:
-	mlx5_sriov_cleanup(dev);
 err_eswitch_cleanup:
 	mlx5_eswitch_cleanup(dev->priv.eswitch);
+err_sriov_cleanup:
+	mlx5_sriov_cleanup(dev);
 err_mpfs_cleanup:
 	mlx5_mpfs_cleanup(dev);
 err_rl_cleanup:
@@ -873,6 +889,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 	mlx5_events_cleanup(dev);
 err_eq_cleanup:
 	mlx5_eq_table_cleanup(dev);
+err_irq_cleanup:
+	mlx5_irq_table_cleanup(dev);
 err_devcom:
 	mlx5_devcom_unregister_device(dev->priv.devcom);
 
@@ -883,8 +901,8 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 {
 	mlx5_fw_tracer_destroy(dev->tracer);
 	mlx5_fpga_cleanup(dev);
-	mlx5_sriov_cleanup(dev);
 	mlx5_eswitch_cleanup(dev->priv.eswitch);
+	mlx5_sriov_cleanup(dev);
 	mlx5_mpfs_cleanup(dev);
 	mlx5_cleanup_rl_table(dev);
 	mlx5_vxlan_destroy(dev->vxlan);
@@ -895,6 +913,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_cq_debugfs_cleanup(dev);
 	mlx5_events_cleanup(dev);
 	mlx5_eq_table_cleanup(dev);
+	mlx5_irq_table_cleanup(dev);
 	mlx5_devcom_unregister_device(dev->priv.devcom);
 }
 
@@ -911,7 +930,7 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot)
 
 	/* wait for firmware to accept initialization segments configurations
 	 */
-	err = wait_fw_init(dev, FW_PRE_INIT_TIMEOUT_MILI);
+	err = wait_fw_init(dev, FW_PRE_INIT_TIMEOUT_MILI, FW_INIT_WARN_MESSAGE_INTERVAL);
 	if (err) {
 		mlx5_core_err(dev, "Firmware over %d MS in pre-initializing state, aborting\n",
 			      FW_PRE_INIT_TIMEOUT_MILI);
@@ -924,7 +943,7 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot)
 		return err;
 	}
 
-	err = wait_fw_init(dev, FW_INIT_TIMEOUT_MILI);
+	err = wait_fw_init(dev, FW_INIT_TIMEOUT_MILI, 0);
 	if (err) {
 		mlx5_core_err(dev, "Firmware over %d MS in initializing state, aborting\n",
 			      FW_INIT_TIMEOUT_MILI);
@@ -1028,6 +1047,12 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 	mlx5_events_start(dev);
 	mlx5_pagealloc_start(dev);
 
+	err = mlx5_irq_table_create(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to alloc IRQs\n");
+		goto err_irq_table;
+	}
+
 	err = mlx5_eq_table_create(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed to create EQs\n");
@@ -1099,6 +1124,8 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 err_fw_tracer:
 	mlx5_eq_table_destroy(dev);
 err_eq_table:
+	mlx5_irq_table_destroy(dev);
+err_irq_table:
 	mlx5_pagealloc_stop(dev);
 	mlx5_events_stop(dev);
 	mlx5_put_uars_page(dev, dev->priv.uar);
@@ -1115,6 +1142,7 @@ static void mlx5_unload(struct mlx5_core_dev *dev)
 	mlx5_fpga_device_stop(dev);
 	mlx5_fw_tracer_cleanup(dev->tracer);
 	mlx5_eq_table_destroy(dev);
+	mlx5_irq_table_destroy(dev);
 	mlx5_pagealloc_stop(dev);
 	mlx5_events_stop(dev);
 	mlx5_put_uars_page(dev, dev->priv.uar);

drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h

@@ -153,6 +153,19 @@ int mlx5_query_qcam_reg(struct mlx5_core_dev *mdev, u32 *qcam,
 void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev);
 void mlx5_lag_remove(struct mlx5_core_dev *dev);
 
+int mlx5_irq_table_init(struct mlx5_core_dev *dev);
+void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev);
+int mlx5_irq_table_create(struct mlx5_core_dev *dev);
+void mlx5_irq_table_destroy(struct mlx5_core_dev *dev);
+int mlx5_irq_attach_nb(struct mlx5_irq_table *irq_table, int vecidx,
+		       struct notifier_block *nb);
+int mlx5_irq_detach_nb(struct mlx5_irq_table *irq_table, int vecidx,
+		       struct notifier_block *nb);
+struct cpumask *
+mlx5_irq_get_affinity_mask(struct mlx5_irq_table *irq_table, int vecidx);
+struct cpu_rmap *mlx5_irq_get_rmap(struct mlx5_irq_table *table);
+int mlx5_irq_get_num_comp(struct mlx5_irq_table *table);
+
 int mlx5_events_init(struct mlx5_core_dev *dev);
 void mlx5_events_cleanup(struct mlx5_core_dev *dev);
 void mlx5_events_start(struct mlx5_core_dev *dev);

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

+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include <linux/interrupt.h>
+#include <linux/notifier.h>
+#include <linux/module.h>
+#include <linux/mlx5/driver.h>
+#include "mlx5_core.h"
+#ifdef CONFIG_RFS_ACCEL
+#include <linux/cpu_rmap.h>
+#endif
+
+#define MLX5_MAX_IRQ_NAME (32)
+
+struct mlx5_irq {
+	struct atomic_notifier_head nh;
+	cpumask_var_t mask;
+	char name[MLX5_MAX_IRQ_NAME];
+};
+
+struct mlx5_irq_table {
+	struct mlx5_irq *irq;
+	int nvec;
+#ifdef CONFIG_RFS_ACCEL
+	struct cpu_rmap *rmap;
+#endif
+};
+
+int mlx5_irq_table_init(struct mlx5_core_dev *dev)
+{
+	struct mlx5_irq_table *irq_table;
+
+	irq_table = kvzalloc(sizeof(*irq_table), GFP_KERNEL);
+	if (!irq_table)
+		return -ENOMEM;
+
+	dev->priv.irq_table = irq_table;
+	return 0;
+}
+
+void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev)
+{
+	kvfree(dev->priv.irq_table);
+}
+
+int mlx5_irq_get_num_comp(struct mlx5_irq_table *table)
+{
+	return table->nvec - MLX5_IRQ_VEC_COMP_BASE;
+}
+
+static struct mlx5_irq *mlx5_irq_get(struct mlx5_core_dev *dev, int vecidx)
+{
+	struct mlx5_irq_table *irq_table = dev->priv.irq_table;
+
+	return &irq_table->irq[vecidx];
+}
+
+int mlx5_irq_attach_nb(struct mlx5_irq_table *irq_table, int vecidx,
+		       struct notifier_block *nb)
+{
+	struct mlx5_irq *irq;
+
+	irq = &irq_table->irq[vecidx];
+	return atomic_notifier_chain_register(&irq->nh, nb);
+}
+
+int mlx5_irq_detach_nb(struct mlx5_irq_table *irq_table, int vecidx,
+		       struct notifier_block *nb)
+{
+	struct mlx5_irq *irq;
+
+	irq = &irq_table->irq[vecidx];
+	return atomic_notifier_chain_unregister(&irq->nh, nb);
+}
+
+static irqreturn_t mlx5_irq_int_handler(int irq, void *nh)
+{
+	atomic_notifier_call_chain(nh, 0, NULL);
+	return IRQ_HANDLED;
+}
+
+static void irq_set_name(char *name, int vecidx)
+{
+	if (vecidx == 0) {
+		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_async");
+		return;
+	}
+
+	snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d",
+		 vecidx - MLX5_IRQ_VEC_COMP_BASE);
+	return;
+}
+
+static int request_irqs(struct mlx5_core_dev *dev, int nvec)
+{
+	char name[MLX5_MAX_IRQ_NAME];
+	int err;
+	int i;
+
+	for (i = 0; i < nvec; i++) {
+		struct mlx5_irq *irq = mlx5_irq_get(dev, i);
+		int irqn = pci_irq_vector(dev->pdev, i);
+
+		irq_set_name(name, i);
+		ATOMIC_INIT_NOTIFIER_HEAD(&irq->nh);
+		snprintf(irq->name, MLX5_MAX_IRQ_NAME,
+			 "%s@pci:%s", name, pci_name(dev->pdev));
+		err = request_irq(irqn, mlx5_irq_int_handler, 0, irq->name,
+				  &irq->nh);
+		if (err) {
+			mlx5_core_err(dev, "Failed to request irq\n");
+			goto err_request_irq;
+		}
+	}
+	return 0;
+
+err_request_irq:
+	for (; i >= 0; i--) {
+		struct mlx5_irq *irq = mlx5_irq_get(dev, i);
+		int irqn = pci_irq_vector(dev->pdev, i);
+
+		free_irq(irqn, &irq->nh);
+	}
+	return  err;
+}
+
+static void irq_clear_rmap(struct mlx5_core_dev *dev)
+{
+#ifdef CONFIG_RFS_ACCEL
+	struct mlx5_irq_table *irq_table = dev->priv.irq_table;
+
+	free_irq_cpu_rmap(irq_table->rmap);
+#endif
+}
+
+static int irq_set_rmap(struct mlx5_core_dev *mdev)
+{
+	int err = 0;
+#ifdef CONFIG_RFS_ACCEL
+	struct mlx5_irq_table *irq_table = mdev->priv.irq_table;
+	int num_affinity_vec;
+	int vecidx;
+
+	num_affinity_vec = mlx5_irq_get_num_comp(irq_table);
+	irq_table->rmap = alloc_irq_cpu_rmap(num_affinity_vec);
+	if (!irq_table->rmap) {
+		err = -ENOMEM;
+		mlx5_core_err(mdev, "Failed to allocate cpu_rmap. err %d", err);
+		goto err_out;
+	}
+
+	vecidx = MLX5_IRQ_VEC_COMP_BASE;
+	for (; vecidx < irq_table->nvec; vecidx++) {
+		err = irq_cpu_rmap_add(irq_table->rmap,
+				       pci_irq_vector(mdev->pdev, vecidx));
+		if (err) {
+			mlx5_core_err(mdev, "irq_cpu_rmap_add failed. err %d",
+				      err);
+			goto err_irq_cpu_rmap_add;
+		}
+	}
+	return 0;
+
+err_irq_cpu_rmap_add:
+	irq_clear_rmap(mdev);
+err_out:
+#endif
+	return err;
+}
+
+/* Completion IRQ vectors */
+
+static int set_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
+{
+	int vecidx = MLX5_IRQ_VEC_COMP_BASE + i;
+	struct mlx5_irq *irq;
+	int irqn;
+
+	irq = mlx5_irq_get(mdev, vecidx);
+	irqn = pci_irq_vector(mdev->pdev, vecidx);
+	if (!zalloc_cpumask_var(&irq->mask, GFP_KERNEL)) {
+		mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
+		return -ENOMEM;
+	}
+
+	cpumask_set_cpu(cpumask_local_spread(i, mdev->priv.numa_node),
+			irq->mask);
+	if (IS_ENABLED(CONFIG_SMP) &&
+	    irq_set_affinity_hint(irqn, irq->mask))
+		mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x",
+			       irqn);
+
+	return 0;
+}
+
+static void clear_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
+{
+	int vecidx = MLX5_IRQ_VEC_COMP_BASE + i;
+	struct mlx5_irq *irq;
+	int irqn;
+
+	irq = mlx5_irq_get(mdev, vecidx);
+	irqn = pci_irq_vector(mdev->pdev, vecidx);
+	irq_set_affinity_hint(irqn, NULL);
+	free_cpumask_var(irq->mask);
+}
+
+static int set_comp_irq_affinity_hints(struct mlx5_core_dev *mdev)
+{
+	int nvec = mlx5_irq_get_num_comp(mdev->priv.irq_table);
+	int err;
+	int i;
+
+	for (i = 0; i < nvec; i++) {
+		err = set_comp_irq_affinity_hint(mdev, i);
+		if (err)
+			goto err_out;
+	}
+
+	return 0;
+
+err_out:
+	for (i--; i >= 0; i--)
+		clear_comp_irq_affinity_hint(mdev, i);
+
+	return err;
+}
+
+static void clear_comp_irqs_affinity_hints(struct mlx5_core_dev *mdev)
+{
+	int nvec = mlx5_irq_get_num_comp(mdev->priv.irq_table);
+	int i;
+
+	for (i = 0; i < nvec; i++)
+		clear_comp_irq_affinity_hint(mdev, i);
+}
+
+struct cpumask *
+mlx5_irq_get_affinity_mask(struct mlx5_irq_table *irq_table, int vecidx)
+{
+	return irq_table->irq[vecidx].mask;
+}
+
+#ifdef CONFIG_RFS_ACCEL
+struct cpu_rmap *mlx5_irq_get_rmap(struct mlx5_irq_table *irq_table)
+{
+	return irq_table->rmap;
+}
+#endif
+
+static void unrequest_irqs(struct mlx5_core_dev *dev)
+{
+	struct mlx5_irq_table *table = dev->priv.irq_table;
+	int i;
+
+	for (i = 0; i < table->nvec; i++)
+		free_irq(pci_irq_vector(dev->pdev, i),
+			 &mlx5_irq_get(dev, i)->nh);
+}
+
+int mlx5_irq_table_create(struct mlx5_core_dev *dev)
+{
+	struct mlx5_priv *priv = &dev->priv;
+	struct mlx5_irq_table *table = priv->irq_table;
+	int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ?
+		      MLX5_CAP_GEN(dev, max_num_eqs) :
+		      1 << MLX5_CAP_GEN(dev, log_max_eq);
+	int nvec;
+	int err;
+
+	nvec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() +
+	       MLX5_IRQ_VEC_COMP_BASE;
+	nvec = min_t(int, nvec, num_eqs);
+	if (nvec <= MLX5_IRQ_VEC_COMP_BASE)
+		return -ENOMEM;
+
+	table->irq = kcalloc(nvec, sizeof(*table->irq), GFP_KERNEL);
+	if (!table->irq)
+		return -ENOMEM;
+
+	nvec = pci_alloc_irq_vectors(dev->pdev, MLX5_IRQ_VEC_COMP_BASE + 1,
+				     nvec, PCI_IRQ_MSIX);
+	if (nvec < 0) {
+		err = nvec;
+		goto err_free_irq;
+	}
+
+	table->nvec = nvec;
+
+	err = irq_set_rmap(dev);
+	if (err)
+		goto err_set_rmap;
+
+	err = request_irqs(dev, nvec);
+	if (err)
+		goto err_request_irqs;
+
+	err = set_comp_irq_affinity_hints(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to alloc affinity hint cpumask\n");
+		goto err_set_affinity;
+	}
+
+	return 0;
+
+err_set_affinity:
+	unrequest_irqs(dev);
+err_request_irqs:
+	irq_clear_rmap(dev);
+err_set_rmap:
+	pci_free_irq_vectors(dev->pdev);
+err_free_irq:
+	kfree(table->irq);
+	return err;
+}
+
+void mlx5_irq_table_destroy(struct mlx5_core_dev *dev)
+{
+	struct mlx5_irq_table *table = dev->priv.irq_table;
+	int i;
+
+	/* free_irq requires that affinity and rmap will be cleared
+	 * before calling it. This is why there is asymmetry with set_rmap
+	 * which should be called after alloc_irq but before request_irq.
+	 */
+	irq_clear_rmap(dev);
+	clear_comp_irqs_affinity_hints(dev);
+	for (i = 0; i < table->nvec; i++)
+		free_irq(pci_irq_vector(dev->pdev, i),
+			 &mlx5_irq_get(dev, i)->nh);
+	pci_free_irq_vectors(dev->pdev);
+	kfree(table->irq);
+}
+

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

@@ -106,10 +106,10 @@ static int mlx5_rdma_enable_roce_steering(struct mlx5_core_dev *dev)
 
 	return 0;
 
-destroy_flow_table:
-	mlx5_destroy_flow_table(ft);
 destroy_flow_group:
 	mlx5_destroy_flow_group(fg);
+destroy_flow_table:
+	mlx5_destroy_flow_table(ft);
 free:
 	kvfree(spec);
 	kvfree(flow_group_in);

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

@@ -208,6 +208,27 @@ void mlx5_sriov_detach(struct mlx5_core_dev *dev)
 	mlx5_device_disable_sriov(dev);
 }
 
+static u16 mlx5_get_max_vfs(struct mlx5_core_dev *dev)
+{
+	u32 out[MLX5_ST_SZ_DW(query_esw_functions_out)] = {};
+	u16 host_total_vfs;
+	int err;
+
+	if (mlx5_core_is_ecpf_esw_manager(dev)) {
+		err = mlx5_esw_query_functions(dev, out, sizeof(out));
+		host_total_vfs = MLX5_GET(query_esw_functions_out, out,
+					  host_params_context.host_total_vfs);
+
+		/* Old FW doesn't support getting total_vfs from esw func
+		 * but supports getting it from pci_sriov.
+		 */
+		if (!err && host_total_vfs)
+			return host_total_vfs;
+	}
+
+	return pci_sriov_get_totalvfs(dev->pdev);
+}
+
 int mlx5_sriov_init(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_sriov *sriov = &dev->priv.sriov;
@@ -218,6 +239,7 @@ int mlx5_sriov_init(struct mlx5_core_dev *dev)
 		return 0;
 
 	total_vfs = pci_sriov_get_totalvfs(pdev);
+	sriov->max_vfs = mlx5_get_max_vfs(dev);
 	sriov->num_vfs = pci_num_vf(pdev);
 	sriov->vfs_ctx = kcalloc(total_vfs, sizeof(*sriov->vfs_ctx), GFP_KERNEL);
 	if (!sriov->vfs_ctx)

include/linux/mlx5/device.h

@@ -342,7 +342,7 @@ enum mlx5_event {
 	MLX5_EVENT_TYPE_PAGE_FAULT	   = 0xc,
 	MLX5_EVENT_TYPE_NIC_VPORT_CHANGE   = 0xd,
 
-	MLX5_EVENT_TYPE_HOST_PARAMS_CHANGE = 0xe,
+	MLX5_EVENT_TYPE_ESW_FUNCTIONS_CHANGED = 0xe,
 
 	MLX5_EVENT_TYPE_DCT_DRAINED        = 0x1c,
 

include/linux/mlx5/driver.h

@@ -107,6 +107,7 @@ enum {
 	MLX5_REG_FPGA_CAP	 = 0x4022,
 	MLX5_REG_FPGA_CTRL	 = 0x4023,
 	MLX5_REG_FPGA_ACCESS_REG = 0x4024,
+	MLX5_REG_CORE_DUMP	 = 0x402e,
 	MLX5_REG_PCAP		 = 0x5001,
 	MLX5_REG_PMTU		 = 0x5003,
 	MLX5_REG_PTYS		 = 0x5004,
@@ -469,6 +470,7 @@ struct mlx5_core_sriov {
 	struct mlx5_vf_context	*vfs_ctx;
 	int			num_vfs;
 	int			enabled_vfs;
+	u16			max_vfs;
 };
 
 struct mlx5_fc_stats {
@@ -490,6 +492,7 @@ struct mlx5_eswitch;
 struct mlx5_lag;
 struct mlx5_devcom;
 struct mlx5_eq_table;
+struct mlx5_irq_table;
 
 struct mlx5_rate_limit {
 	u32			rate;
@@ -519,6 +522,8 @@ struct mlx5_core_roce {
 };
 
 struct mlx5_priv {
+	/* IRQ table valid only for real pci devices PF or VF */
+	struct mlx5_irq_table   *irq_table;
 	struct mlx5_eq_table	*eq_table;
 
 	/* pages stuff */
@@ -1102,13 +1107,9 @@ static inline bool mlx5_ecpf_vport_exists(struct mlx5_core_dev *dev)
 	return mlx5_core_is_pf(dev) && MLX5_CAP_ESW(dev, ecpf_vport_exists);
 }
 
-#define MLX5_HOST_PF_MAX_VFS	(127u)
 static inline u16 mlx5_core_max_vfs(struct mlx5_core_dev *dev)
 {
-	if (mlx5_core_is_ecpf_esw_manager(dev))
-		return MLX5_HOST_PF_MAX_VFS;
-	else
-		return pci_sriov_get_totalvfs(dev->pdev);
+	return dev->priv.sriov.max_vfs;
 }
 
 static inline int mlx5_get_gid_table_len(u16 param)

include/linux/mlx5/eq.h

@@ -4,17 +4,7 @@
 #ifndef MLX5_CORE_EQ_H
 #define MLX5_CORE_EQ_H
 
-enum {
-	MLX5_EQ_PAGEREQ_IDX        = 0,
-	MLX5_EQ_CMD_IDX            = 1,
-	MLX5_EQ_ASYNC_IDX          = 2,
-	/* reserved to be used by mlx5_core ulps (mlx5e/mlx5_ib) */
-	MLX5_EQ_PFAULT_IDX         = 3,
-	MLX5_EQ_MAX_ASYNC_EQS,
-	/* completion eqs vector indices start here */
-	MLX5_EQ_VEC_COMP_BASE = MLX5_EQ_MAX_ASYNC_EQS,
-};
-
+#define MLX5_IRQ_VEC_COMP_BASE 1
 #define MLX5_NUM_CMD_EQE   (32)
 #define MLX5_NUM_ASYNC_EQE (0x1000)
 #define MLX5_NUM_SPARE_EQE (0x80)
@@ -23,18 +13,19 @@ struct mlx5_eq;
 struct mlx5_core_dev;
 
 struct mlx5_eq_param {
-	u8             index;
+	u8             irq_index;
 	int            nent;
 	u64            mask;
-	void          *context;
-	irq_handler_t  handler;
 };
 
 struct mlx5_eq *
-mlx5_eq_create_generic(struct mlx5_core_dev *dev, const char *name,
-		       struct mlx5_eq_param *param);
+mlx5_eq_create_generic(struct mlx5_core_dev *dev, struct mlx5_eq_param *param);
 int
 mlx5_eq_destroy_generic(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
+int mlx5_eq_enable(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
+		   struct notifier_block *nb);
+void mlx5_eq_disable(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
+		     struct notifier_block *nb);
 
 struct mlx5_eqe *mlx5_eq_get_eqe(struct mlx5_eq *eq, u32 cc);
 void mlx5_eq_update_ci(struct mlx5_eq *eq, u32 cc, bool arm);

include/linux/mlx5/eswitch.h

@@ -7,6 +7,7 @@
 #define _MLX5_ESWITCH_
 
 #include <linux/mlx5/driver.h>
+#include <net/devlink.h>
 
 #define MLX5_ESWITCH_MANAGER(mdev) MLX5_CAP_GEN(mdev, eswitch_manager)
 
@@ -29,17 +30,19 @@ enum {
 };
 
 struct mlx5_eswitch_rep;
-struct mlx5_eswitch_rep_if {
-	int		       (*load)(struct mlx5_core_dev *dev,
-				       struct mlx5_eswitch_rep *rep);
+struct mlx5_eswitch_rep_ops {
+	int (*load)(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep);
 	void (*unload)(struct mlx5_eswitch_rep *rep);
 	void *(*get_proto_dev)(struct mlx5_eswitch_rep *rep);
+};
+
+struct mlx5_eswitch_rep_data {
 	void *priv;
 	atomic_t state;
 };
 
 struct mlx5_eswitch_rep {
-	struct mlx5_eswitch_rep_if rep_if[NUM_REP_TYPES];
+	struct mlx5_eswitch_rep_data rep_data[NUM_REP_TYPES];
 	u16		       vport;
 	u8		       hw_id[ETH_ALEN];
 	u16		       vlan;
@@ -47,7 +50,7 @@ struct mlx5_eswitch_rep {
 };
 
 void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw,
-				      struct mlx5_eswitch_rep_if *rep_if,
+				      const struct mlx5_eswitch_rep_ops *ops,
 				      u8 rep_type);
 void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type);
 void *mlx5_eswitch_get_proto_dev(struct mlx5_eswitch *esw,
@@ -60,4 +63,15 @@ u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw);
 struct mlx5_flow_handle *
 mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw,
 				    int vport, u32 sqn);
+
+#ifdef CONFIG_MLX5_ESWITCH
+enum devlink_eswitch_encap_mode
+mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev);
+#else  /* CONFIG_MLX5_ESWITCH */
+static inline enum devlink_eswitch_encap_mode
+mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev)
+{
+	return DEVLINK_ESWITCH_ENCAP_MODE_NONE;
+}
+#endif /* CONFIG_MLX5_ESWITCH */
 #endif

include/linux/mlx5/fs.h

@@ -47,6 +47,7 @@ enum {
 enum {
 	MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT = BIT(0),
 	MLX5_FLOW_TABLE_TUNNEL_EN_DECAP = BIT(1),
+	MLX5_FLOW_TABLE_TERMINATION = BIT(2),
 };
 
 #define LEFTOVERS_RULE_NUM	 2

include/linux/mlx5/mlx5_ifc.h

@@ -155,7 +155,7 @@ enum {
 	MLX5_CMD_OP_QUERY_XRQ_DC_PARAMS_ENTRY     = 0x725,
 	MLX5_CMD_OP_SET_XRQ_DC_PARAMS_ENTRY       = 0x726,
 	MLX5_CMD_OP_QUERY_XRQ_ERROR_PARAMS        = 0x727,
-	MLX5_CMD_OP_QUERY_HOST_PARAMS             = 0x740,
+	MLX5_CMD_OP_QUERY_ESW_FUNCTIONS           = 0x740,
 	MLX5_CMD_OP_QUERY_VPORT_STATE             = 0x750,
 	MLX5_CMD_OP_MODIFY_VPORT_STATE            = 0x751,
 	MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT       = 0x752,
@@ -382,7 +382,8 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
 	u8	   reformat_and_modify_action[0x1];
 	u8         reserved_at_15[0x2];
 	u8	   table_miss_action_domain[0x1];
-	u8         reserved_at_18[0x8];
+	u8         termination_table[0x1];
+	u8         reserved_at_19[0x7];
 	u8         reserved_at_20[0x2];
 	u8         log_max_ft_size[0x6];
 	u8         log_max_modify_header_context[0x8];
@@ -664,7 +665,9 @@ struct mlx5_ifc_e_switch_cap_bits {
 	u8         vport_svlan_insert[0x1];
 	u8         vport_cvlan_insert_if_not_exist[0x1];
 	u8         vport_cvlan_insert_overwrite[0x1];
-	u8         reserved_at_5[0x16];
+	u8         reserved_at_5[0x14];
+	u8         esw_functions_changed[0x1];
+	u8         reserved_at_1a[0x1];
 	u8         ecpf_vport_exists[0x1];
 	u8         counter_eswitch_affinity[0x1];
 	u8         merged_eswitch[0x1];
@@ -715,7 +718,9 @@ struct mlx5_ifc_qos_cap_bits {
 };
 
 struct mlx5_ifc_debug_cap_bits {
-	u8         reserved_at_0[0x20];
+	u8         core_dump_general[0x1];
+	u8         core_dump_qp[0x1];
+	u8         reserved_at_2[0x1e];
 
 	u8         reserved_at_20[0x2];
 	u8         stall_detect[0x1];
@@ -2531,6 +2536,7 @@ union mlx5_ifc_hca_cap_union_bits {
 	struct mlx5_ifc_e_switch_cap_bits e_switch_cap;
 	struct mlx5_ifc_vector_calc_cap_bits vector_calc_cap;
 	struct mlx5_ifc_qos_cap_bits qos_cap;
+	struct mlx5_ifc_debug_cap_bits debug_cap;
 	struct mlx5_ifc_fpga_cap_bits fpga_cap;
 	u8         reserved_at_0[0x8000];
 };
@@ -7236,7 +7242,8 @@ struct mlx5_ifc_create_flow_table_out_bits {
 struct mlx5_ifc_flow_table_context_bits {
 	u8         reformat_en[0x1];
 	u8         decap_en[0x1];
-	u8         reserved_at_2[0x2];
+	u8         reserved_at_2[0x1];
+	u8         termination_table[0x1];
 	u8         table_miss_action[0x4];
 	u8         level[0x8];
 	u8         reserved_at_10[0x8];
@@ -8546,6 +8553,18 @@ struct mlx5_ifc_qcam_reg_bits {
 	u8         reserved_at_1c0[0x80];
 };
 
+struct mlx5_ifc_core_dump_reg_bits {
+	u8         reserved_at_0[0x18];
+	u8         core_dump_type[0x8];
+
+	u8         reserved_at_20[0x30];
+	u8         vhca_id[0x10];
+
+	u8         reserved_at_60[0x8];
+	u8         qpn[0x18];
+	u8         reserved_at_80[0x180];
+};
+
 struct mlx5_ifc_pcap_reg_bits {
 	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
@@ -9692,7 +9711,7 @@ struct mlx5_ifc_host_params_context_bits {
 	u8         reserved_at_8[0x8];
 	u8         host_num_of_vfs[0x10];
 
-	u8         reserved_at_20[0x10];
+	u8         host_total_vfs[0x10];
 	u8         host_pci_bus[0x10];
 
 	u8         reserved_at_40[0x10];
@@ -9704,7 +9723,7 @@ struct mlx5_ifc_host_params_context_bits {
 	u8         reserved_at_80[0x180];
 };
 
-struct mlx5_ifc_query_host_params_in_bits {
+struct mlx5_ifc_query_esw_functions_in_bits {
 	u8         opcode[0x10];
 	u8         reserved_at_10[0x10];
 
@@ -9714,7 +9733,7 @@ struct mlx5_ifc_query_host_params_in_bits {
 	u8         reserved_at_40[0x40];
 };
 
-struct mlx5_ifc_query_host_params_out_bits {
+struct mlx5_ifc_query_esw_functions_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
 

include/net/devlink.h

@@ -530,8 +530,10 @@ struct devlink_ops {
 	int (*eswitch_inline_mode_get)(struct devlink *devlink, u8 *p_inline_mode);
 	int (*eswitch_inline_mode_set)(struct devlink *devlink, u8 inline_mode,
 				       struct netlink_ext_ack *extack);
-	int (*eswitch_encap_mode_get)(struct devlink *devlink, u8 *p_encap_mode);
-	int (*eswitch_encap_mode_set)(struct devlink *devlink, u8 encap_mode,
+	int (*eswitch_encap_mode_get)(struct devlink *devlink,
+				      enum devlink_eswitch_encap_mode *p_encap_mode);
+	int (*eswitch_encap_mode_set)(struct devlink *devlink,
+				      enum devlink_eswitch_encap_mode encap_mode,
 				      struct netlink_ext_ack *extack);
 	int (*info_get)(struct devlink *devlink, struct devlink_info_req *req,
 			struct netlink_ext_ack *extack);

net/core/devlink.c

@@ -1552,7 +1552,8 @@ static int devlink_nl_eswitch_fill(struct sk_buff *msg, struct devlink *devlink,
 				   u32 seq, int flags)
 {
 	const struct devlink_ops *ops = devlink->ops;
-	u8 inline_mode, encap_mode;
+	enum devlink_eswitch_encap_mode encap_mode;
+	u8 inline_mode;
 	void *hdr;
 	int err = 0;
 	u16 mode;
@@ -1628,7 +1629,8 @@ static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb,
 {
 	struct devlink *devlink = info->user_ptr[0];
 	const struct devlink_ops *ops = devlink->ops;
-	u8 inline_mode, encap_mode;
+	enum devlink_eswitch_encap_mode encap_mode;
+	u8 inline_mode;
 	int err = 0;
 	u16 mode;