Merge branch 'mlx5-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux

This merge commit includes some misc shared code updates from mlx5-next branch needed
for net-next.

1) From Aya: Enable general events on all physical link types and
   restrict general event handling of subtype DELAY_DROP_TIMEOUT in mlx5 rdma
   driver to ethernet links only as it was intended.

2) From Eli: Introduce low level bits for prio tag mode

3) From Maor: Low level steering updates to support RDMA RX flow
   steering and enables RoCE loopback traffic when switchdev is enabled.

4) From Vu and Parav: Two small mlx5 core cleanups

5) From Yevgeny add HW definitions of geneve offloads
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

drivers/infiniband/hw/mlx5/main.c

@@ -181,7 +181,7 @@ static int mlx5_netdev_event(struct notifier_block *this,
 							  ibdev->rep->vport);
 			if (rep_ndev == ndev)
 				roce->netdev = ndev;
-		} else if (ndev->dev.parent == &mdev->pdev->dev) {
+		} else if (ndev->dev.parent == mdev->device) {
 			roce->netdev = ndev;
 		}
 		write_unlock(&roce->netdev_lock);
@@ -4354,8 +4354,12 @@ static void delay_drop_handler(struct work_struct *work)
 static void handle_general_event(struct mlx5_ib_dev *ibdev, struct mlx5_eqe *eqe,
 				 struct ib_event *ibev)
 {
+	u8 port = (eqe->data.port.port >> 4) & 0xf;
+
 	switch (eqe->sub_type) {
 	case MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT:
+		if (mlx5_ib_port_link_layer(&ibdev->ib_dev, port) ==
+					    IB_LINK_LAYER_ETHERNET)
 			schedule_work(&ibdev->delay_drop.delay_drop_work);
 		break;
 	default: /* do nothing */
@@ -5673,7 +5677,8 @@ static int mlx5_ib_init_multiport_master(struct mlx5_ib_dev *dev)
 			}
 
 			if (bound) {
-				dev_dbg(&mpi->mdev->pdev->dev, "removing port from unaffiliated list.\n");
+				dev_dbg(mpi->mdev->device,
+					"removing port from unaffiliated list.\n");
 				mlx5_ib_dbg(dev, "port %d bound\n", i + 1);
 				list_del(&mpi->list);
 				break;
@@ -5872,7 +5877,7 @@ int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 	dev->ib_dev.local_dma_lkey	= 0 /* not supported for now */;
 	dev->ib_dev.phys_port_cnt	= dev->num_ports;
 	dev->ib_dev.num_comp_vectors    = mlx5_comp_vectors_count(mdev);
-	dev->ib_dev.dev.parent		= &mdev->pdev->dev;
+	dev->ib_dev.dev.parent		= mdev->device;
 
 	mutex_init(&dev->cap_mask_mutex);
 	INIT_LIST_HEAD(&dev->qp_list);
@@ -6561,7 +6566,8 @@ static void *mlx5_ib_add_slave_port(struct mlx5_core_dev *mdev)
 
 	if (!bound) {
 		list_add_tail(&mpi->list, &mlx5_ib_unaffiliated_port_list);
-		dev_dbg(&mdev->pdev->dev, "no suitable IB device found to bind to, added to unaffiliated list.\n");
+		dev_dbg(mdev->device,
+			"no suitable IB device found to bind to, added to unaffiliated list.\n");
 	}
 	mutex_unlock(&mlx5_ib_multiport_mutex);
 

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

@@ -36,7 +36,7 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o en/tc_tun.o lib/port_tu
 #
 # Core extra
 #
-mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o ecpf.o
+mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o ecpf.o rdma.o
 mlx5_core-$(CONFIG_MLX5_MPFS)      += lib/mpfs.o
 mlx5_core-$(CONFIG_VXLAN)          += lib/vxlan.o
 mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o

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

@@ -57,15 +57,16 @@ static void *mlx5_dma_zalloc_coherent_node(struct mlx5_core_dev *dev,
 					   int node)
 {
 	struct mlx5_priv *priv = &dev->priv;
+	struct device *device = dev->device;
 	int original_node;
 	void *cpu_handle;
 
 	mutex_lock(&priv->alloc_mutex);
-	original_node = dev_to_node(&dev->pdev->dev);
-	set_dev_node(&dev->pdev->dev, node);
-	cpu_handle = dma_alloc_coherent(&dev->pdev->dev, size, dma_handle,
+	original_node = dev_to_node(device);
+	set_dev_node(device, node);
+	cpu_handle = dma_alloc_coherent(device, size, dma_handle,
 					GFP_KERNEL);
-	set_dev_node(&dev->pdev->dev, original_node);
+	set_dev_node(device, original_node);
 	mutex_unlock(&priv->alloc_mutex);
 	return cpu_handle;
 }
@@ -110,7 +111,7 @@ EXPORT_SYMBOL(mlx5_buf_alloc);
 
 void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf)
 {
-	dma_free_coherent(&dev->pdev->dev, buf->size, buf->frags->buf,
+	dma_free_coherent(dev->device, buf->size, buf->frags->buf,
 			  buf->frags->map);
 
 	kfree(buf->frags);
@@ -139,7 +140,7 @@ int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size,
 		if (!frag->buf)
 			goto err_free_buf;
 		if (frag->map & ((1 << buf->page_shift) - 1)) {
-			dma_free_coherent(&dev->pdev->dev, frag_sz,
+			dma_free_coherent(dev->device, frag_sz,
 					  buf->frags[i].buf, buf->frags[i].map);
 			mlx5_core_warn(dev, "unexpected map alignment: %pad, page_shift=%d\n",
 				       &frag->map, buf->page_shift);
@@ -152,7 +153,7 @@ int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size,
 
 err_free_buf:
 	while (i--)
-		dma_free_coherent(&dev->pdev->dev, PAGE_SIZE, buf->frags[i].buf,
+		dma_free_coherent(dev->device, PAGE_SIZE, buf->frags[i].buf,
 				  buf->frags[i].map);
 	kfree(buf->frags);
 err_out:
@@ -168,7 +169,7 @@ void mlx5_frag_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf)
 	for (i = 0; i < buf->npages; i++) {
 		int frag_sz = min_t(int, size, PAGE_SIZE);
 
-		dma_free_coherent(&dev->pdev->dev, frag_sz, buf->frags[i].buf,
+		dma_free_coherent(dev->device, frag_sz, buf->frags[i].buf,
 				  buf->frags[i].map);
 		size -= frag_sz;
 	}
@@ -274,7 +275,7 @@ void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db)
 	__set_bit(db->index, db->u.pgdir->bitmap);
 
 	if (bitmap_full(db->u.pgdir->bitmap, db_per_page)) {
-		dma_free_coherent(&(dev->pdev->dev), PAGE_SIZE,
+		dma_free_coherent(dev->device, PAGE_SIZE,
 				  db->u.pgdir->db_page, db->u.pgdir->db_dma);
 		list_del(&db->u.pgdir->list);
 		bitmap_free(db->u.pgdir->bitmap);

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

@@ -1347,7 +1347,7 @@ static void set_wqname(struct mlx5_core_dev *dev)
 	struct mlx5_cmd *cmd = &dev->cmd;
 
 	snprintf(cmd->wq_name, sizeof(cmd->wq_name), "mlx5_cmd_%s",
-		 dev->priv.name);
+		 dev_name(dev->device));
 }
 
 static void clean_debug_files(struct mlx5_core_dev *dev)
@@ -1852,7 +1852,7 @@ static void create_msg_cache(struct mlx5_core_dev *dev)
 
 static int alloc_cmd_page(struct mlx5_core_dev *dev, struct mlx5_cmd *cmd)
 {
-	struct device *ddev = &dev->pdev->dev;
+	struct device *ddev = dev->device;
 
 	cmd->cmd_alloc_buf = dma_alloc_coherent(ddev, MLX5_ADAPTER_PAGE_SIZE,
 						&cmd->alloc_dma, GFP_KERNEL);
@@ -1883,7 +1883,7 @@ static int alloc_cmd_page(struct mlx5_core_dev *dev, struct mlx5_cmd *cmd)
 
 static void free_cmd_page(struct mlx5_core_dev *dev, struct mlx5_cmd *cmd)
 {
-	struct device *ddev = &dev->pdev->dev;
+	struct device *ddev = dev->device;
 
 	dma_free_coherent(ddev, cmd->alloc_size, cmd->cmd_alloc_buf,
 			  cmd->alloc_dma);
@@ -1908,8 +1908,7 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 		return -EINVAL;
 	}
 
-	cmd->pool = dma_pool_create("mlx5_cmd", &dev->pdev->dev, size, align,
-				    0);
+	cmd->pool = dma_pool_create("mlx5_cmd", dev->device, size, align, 0);
 	if (!cmd->pool)
 		return -ENOMEM;
 

drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h

@@ -47,7 +47,7 @@ TRACE_EVENT(mlx5_fw,
 	TP_ARGS(tracer, trace_timestamp, lost, event_id, msg),
 
 	TP_STRUCT__entry(
-		__string(dev_name, tracer->dev->priv.name)
+		__string(dev_name, dev_name(tracer->dev->device))
 		__field(u64, trace_timestamp)
 		__field(bool, lost)
 		__field(u8, event_id)
@@ -55,7 +55,8 @@ TRACE_EVENT(mlx5_fw,
 	),
 
 	TP_fast_assign(
-		__assign_str(dev_name, tracer->dev->priv.name);
+		__assign_str(dev_name,
+			     dev_name(tracer->dev->device));
 		__entry->trace_timestamp = trace_timestamp;
 		__entry->lost = lost;
 		__entry->event_id = event_id;

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

@@ -1794,7 +1794,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->tstamp   = &priv->tstamp;
 	c->ix       = ix;
 	c->cpu      = cpu;
-	c->pdev     = &priv->mdev->pdev->dev;
+	c->pdev     = priv->mdev->device;
 	c->netdev   = priv->netdev;
 	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key);
 	c->num_tc   = params->num_tc;
@@ -2047,7 +2047,7 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
 	MLX5_SET(rqc, rqc, vsd,            params->vlan_strip_disable);
 	MLX5_SET(rqc, rqc, scatter_fcs,    params->scatter_fcs_en);
 
-	param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev);
+	param->wq.buf_numa_node = dev_to_node(mdev->device);
 }
 
 static void mlx5e_build_drop_rq_param(struct mlx5e_priv *priv,
@@ -2062,7 +2062,7 @@ static void mlx5e_build_drop_rq_param(struct mlx5e_priv *priv,
 		 mlx5e_get_rqwq_log_stride(MLX5_WQ_TYPE_CYCLIC, 1));
 	MLX5_SET(rqc, rqc, counter_set_id, priv->drop_rq_q_counter);
 
-	param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev);
+	param->wq.buf_numa_node = dev_to_node(mdev->device);
 }
 
 static void mlx5e_build_sq_param_common(struct mlx5e_priv *priv,
@@ -2074,7 +2074,7 @@ static void mlx5e_build_sq_param_common(struct mlx5e_priv *priv,
 	MLX5_SET(wq, wq, log_wq_stride, ilog2(MLX5_SEND_WQE_BB));
 	MLX5_SET(wq, wq, pd,            priv->mdev->mlx5e_res.pdn);
 
-	param->wq.buf_numa_node = dev_to_node(&priv->mdev->pdev->dev);
+	param->wq.buf_numa_node = dev_to_node(priv->mdev->device);
 }
 
 static void mlx5e_build_sq_param(struct mlx5e_priv *priv,
@@ -3001,8 +3001,8 @@ static int mlx5e_alloc_drop_cq(struct mlx5_core_dev *mdev,
 			       struct mlx5e_cq *cq,
 			       struct mlx5e_cq_param *param)
 {
-	param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev);
-	param->wq.db_numa_node  = dev_to_node(&mdev->pdev->dev);
+	param->wq.buf_numa_node = dev_to_node(mdev->device);
+	param->wq.db_numa_node  = dev_to_node(mdev->device);
 
 	return mlx5e_alloc_cq_common(mdev, param, cq);
 }
@@ -4600,7 +4600,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	bool fcs_supported;
 	bool fcs_enabled;
 
-	SET_NETDEV_DEV(netdev, &mdev->pdev->dev);
+	SET_NETDEV_DEV(netdev, mdev->device);
 
 	netdev->netdev_ops = &mlx5e_netdev_ops;
 

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

@@ -1390,7 +1390,7 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev)
 	struct mlx5_core_dev *mdev = priv->mdev;
 
 	if (rep->vport == MLX5_VPORT_UPLINK) {
-		SET_NETDEV_DEV(netdev, &priv->mdev->pdev->dev);
+		SET_NETDEV_DEV(netdev, mdev->device);
 		netdev->netdev_ops = &mlx5e_netdev_ops_uplink_rep;
 		/* we want a persistent mac for the uplink rep */
 		mlx5_query_nic_vport_mac_address(mdev, 0, netdev->dev_addr);

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

@@ -664,7 +664,8 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv,
 	}
 
 	netdev_dbg(priv->netdev, "add hairpin: tirn %x rqn %x peer %s sqn %x prio %d (log) data %d packets %d\n",
-		   hp->tirn, hp->pair->rqn[0], hp->pair->peer_mdev->priv.name,
+		   hp->tirn, hp->pair->rqn[0],
+		   dev_name(hp->pair->peer_mdev->device),
 		   hp->pair->sqn[0], match_prio, params.log_data_size, params.log_num_packets);
 
 	hpe->hp = hp;
@@ -701,7 +702,7 @@ static void mlx5e_hairpin_flow_del(struct mlx5e_priv *priv,
 		hpe = list_entry(next, struct mlx5e_hairpin_entry, flows);
 
 		netdev_dbg(priv->netdev, "del hairpin: peer %s\n",
-			   hpe->hp->pair->peer_mdev->priv.name);
+			   dev_name(hpe->hp->pair->peer_mdev->device));
 
 		mlx5e_hairpin_destroy(hpe->hp);
 		hash_del(&hpe->hairpin_hlist);

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

@@ -504,8 +504,7 @@ static u64 gather_async_events_mask(struct mlx5_core_dev *dev)
 	if (MLX5_VPORT_MANAGER(dev))
 		async_event_mask |= (1ull << MLX5_EVENT_TYPE_NIC_VPORT_CHANGE);
 
-	if (MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH &&
-	    MLX5_CAP_GEN(dev, general_notification_event))
+	if (MLX5_CAP_GEN(dev, general_notification_event))
 		async_event_mask |= (1ull << MLX5_EVENT_TYPE_GENERAL_EVENT);
 
 	if (MLX5_CAP_GEN(dev, port_module_event))

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

@@ -376,11 +376,11 @@ bool mlx5_esw_multipath_prereq(struct mlx5_core_dev *dev0,
 
 #define MLX5_DEBUG_ESWITCH_MASK BIT(3)
 
-#define esw_info(dev, format, ...)				\
-	pr_info("(%s): E-Switch: " format, (dev)->priv.name, ##__VA_ARGS__)
+#define esw_info(__dev, format, ...)			\
+	dev_info((__dev)->device, "E-Switch: " format, ##__VA_ARGS__)
 
-#define esw_warn(dev, format, ...)				\
-	pr_warn("(%s): E-Switch: " format, (dev)->priv.name, ##__VA_ARGS__)
+#define esw_warn(__dev, format, ...)			\
+	dev_warn((__dev)->device, "E-Switch: " format, ##__VA_ARGS__)
 
 #define esw_debug(dev, format, ...)				\
 	mlx5_core_dbg_mask(dev, MLX5_DEBUG_ESWITCH_MASK, format, ##__VA_ARGS__)

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

@@ -37,6 +37,7 @@
 #include <linux/mlx5/fs.h>
 #include "mlx5_core.h"
 #include "eswitch.h"
+#include "rdma.h"
 #include "en.h"
 #include "fs_core.h"
 #include "lib/devcom.h"
@@ -1710,6 +1711,8 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int vf_nvports,
 		esw->host_info.num_vfs = vf_nvports;
 	}
 
+	mlx5_rdma_enable_roce(esw->dev);
+
 	return 0;
 
 err_reps:
@@ -1748,6 +1751,7 @@ void esw_offloads_cleanup(struct mlx5_eswitch *esw)
 		num_vfs = esw->dev->priv.sriov.num_vfs;
 	}
 
+	mlx5_rdma_disable_roce(esw->dev);
 	esw_offloads_devcom_cleanup(esw);
 	esw_offloads_unload_all_reps(esw, num_vfs);
 	esw_offloads_steering_cleanup(esw);

drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c

@@ -989,32 +989,33 @@ static enum fs_flow_table_type egress_to_fs_ft(bool egress)
 	return egress ? FS_FT_NIC_TX : FS_FT_NIC_RX;
 }
 
-static int fpga_ipsec_fs_create_flow_group(struct mlx5_core_dev *dev,
+static int fpga_ipsec_fs_create_flow_group(struct mlx5_flow_root_namespace *ns,
 					   struct mlx5_flow_table *ft,
 					   u32 *in,
-					   unsigned int *group_id,
+					   struct mlx5_flow_group *fg,
 					   bool is_egress)
 {
-	int (*create_flow_group)(struct mlx5_core_dev *dev,
+	int (*create_flow_group)(struct mlx5_flow_root_namespace *ns,
 				 struct mlx5_flow_table *ft, u32 *in,
-				 unsigned int *group_id) =
+				 struct mlx5_flow_group *fg) =
 		mlx5_fs_cmd_get_default(egress_to_fs_ft(is_egress))->create_flow_group;
 	char *misc_params_c = MLX5_ADDR_OF(create_flow_group_in, in,
 					   match_criteria.misc_parameters);
+	struct mlx5_core_dev *dev = ns->dev;
 	u32 saved_outer_esp_spi_mask;
 	u8 match_criteria_enable;
 	int ret;
 
 	if (MLX5_CAP_FLOWTABLE(dev,
 			       flow_table_properties_nic_receive.ft_field_support.outer_esp_spi))
-		return create_flow_group(dev, ft, in, group_id);
+		return create_flow_group(ns, ft, in, fg);
 
 	match_criteria_enable =
 		MLX5_GET(create_flow_group_in, in, match_criteria_enable);
 	saved_outer_esp_spi_mask =
 		MLX5_GET(fte_match_set_misc, misc_params_c, outer_esp_spi);
 	if (!match_criteria_enable || !saved_outer_esp_spi_mask)
-		return create_flow_group(dev, ft, in, group_id);
+		return create_flow_group(ns, ft, in, fg);
 
 	MLX5_SET(fte_match_set_misc, misc_params_c, outer_esp_spi, 0);
 
@@ -1023,7 +1024,7 @@ static int fpga_ipsec_fs_create_flow_group(struct mlx5_core_dev *dev,
 		MLX5_SET(create_flow_group_in, in, match_criteria_enable,
 			 match_criteria_enable & ~MLX5_MATCH_MISC_PARAMETERS);
 
-	ret = create_flow_group(dev, ft, in, group_id);
+	ret = create_flow_group(ns, ft, in, fg);
 
 	MLX5_SET(fte_match_set_misc, misc_params_c, outer_esp_spi, saved_outer_esp_spi_mask);
 	MLX5_SET(create_flow_group_in, in, match_criteria_enable, match_criteria_enable);
@@ -1031,17 +1032,18 @@ static int fpga_ipsec_fs_create_flow_group(struct mlx5_core_dev *dev,
 	return ret;
 }
 
-static int fpga_ipsec_fs_create_fte(struct mlx5_core_dev *dev,
+static int fpga_ipsec_fs_create_fte(struct mlx5_flow_root_namespace *ns,
 				    struct mlx5_flow_table *ft,
 				    struct mlx5_flow_group *fg,
 				    struct fs_fte *fte,
 				    bool is_egress)
 {
-	int (*create_fte)(struct mlx5_core_dev *dev,
+	int (*create_fte)(struct mlx5_flow_root_namespace *ns,
 			  struct mlx5_flow_table *ft,
 			  struct mlx5_flow_group *fg,
 			  struct fs_fte *fte) =
 		mlx5_fs_cmd_get_default(egress_to_fs_ft(is_egress))->create_fte;
+	struct mlx5_core_dev *dev = ns->dev;
 	struct mlx5_fpga_device *fdev = dev->fpga;
 	struct mlx5_fpga_ipsec *fipsec = fdev->ipsec;
 	struct mlx5_fpga_ipsec_rule *rule;
@@ -1053,7 +1055,7 @@ static int fpga_ipsec_fs_create_fte(struct mlx5_core_dev *dev,
 	    !(fte->action.action &
 	      (MLX5_FLOW_CONTEXT_ACTION_ENCRYPT |
 	       MLX5_FLOW_CONTEXT_ACTION_DECRYPT)))
-		return create_fte(dev, ft, fg, fte);
+		return create_fte(ns, ft, fg, fte);
 
 	rule = kzalloc(sizeof(*rule), GFP_KERNEL);
 	if (!rule)
@@ -1070,7 +1072,7 @@ static int fpga_ipsec_fs_create_fte(struct mlx5_core_dev *dev,
 	WARN_ON(rule_insert(fipsec, rule));
 
 	modify_spec_mailbox(dev, fte, &mbox_mod);
-	ret = create_fte(dev, ft, fg, fte);
+	ret = create_fte(ns, ft, fg, fte);
 	restore_spec_mailbox(fte, &mbox_mod);
 	if (ret) {
 		_rule_delete(fipsec, rule);
@@ -1081,19 +1083,20 @@ static int fpga_ipsec_fs_create_fte(struct mlx5_core_dev *dev,
 	return ret;
 }
 
-static int fpga_ipsec_fs_update_fte(struct mlx5_core_dev *dev,
+static int fpga_ipsec_fs_update_fte(struct mlx5_flow_root_namespace *ns,
 				    struct mlx5_flow_table *ft,
-				    unsigned int group_id,
+				    struct mlx5_flow_group *fg,
 				    int modify_mask,
 				    struct fs_fte *fte,
 				    bool is_egress)
 {
-	int (*update_fte)(struct mlx5_core_dev *dev,
+	int (*update_fte)(struct mlx5_flow_root_namespace *ns,
 			  struct mlx5_flow_table *ft,
-			  unsigned int group_id,
+			  struct mlx5_flow_group *fg,
 			  int modify_mask,
 			  struct fs_fte *fte) =
 		mlx5_fs_cmd_get_default(egress_to_fs_ft(is_egress))->update_fte;
+	struct mlx5_core_dev *dev = ns->dev;
 	bool is_esp = fte->action.esp_id;
 	struct mailbox_mod mbox_mod;
 	int ret;
@@ -1102,24 +1105,25 @@ static int fpga_ipsec_fs_update_fte(struct mlx5_core_dev *dev,
 	    !(fte->action.action &
 	      (MLX5_FLOW_CONTEXT_ACTION_ENCRYPT |
 	       MLX5_FLOW_CONTEXT_ACTION_DECRYPT)))
-		return update_fte(dev, ft, group_id, modify_mask, fte);
+		return update_fte(ns, ft, fg, modify_mask, fte);
 
 	modify_spec_mailbox(dev, fte, &mbox_mod);
-	ret = update_fte(dev, ft, group_id, modify_mask, fte);
+	ret = update_fte(ns, ft, fg, modify_mask, fte);
 	restore_spec_mailbox(fte, &mbox_mod);
 
 	return ret;
 }
 
-static int fpga_ipsec_fs_delete_fte(struct mlx5_core_dev *dev,
+static int fpga_ipsec_fs_delete_fte(struct mlx5_flow_root_namespace *ns,
 				    struct mlx5_flow_table *ft,
 				    struct fs_fte *fte,
 				    bool is_egress)
 {
-	int (*delete_fte)(struct mlx5_core_dev *dev,
+	int (*delete_fte)(struct mlx5_flow_root_namespace *ns,
 			  struct mlx5_flow_table *ft,
 			  struct fs_fte *fte) =
 		mlx5_fs_cmd_get_default(egress_to_fs_ft(is_egress))->delete_fte;
+	struct mlx5_core_dev *dev = ns->dev;
 	struct mlx5_fpga_device *fdev = dev->fpga;
 	struct mlx5_fpga_ipsec *fipsec = fdev->ipsec;
 	struct mlx5_fpga_ipsec_rule *rule;
@@ -1131,7 +1135,7 @@ static int fpga_ipsec_fs_delete_fte(struct mlx5_core_dev *dev,
 	    !(fte->action.action &
 	      (MLX5_FLOW_CONTEXT_ACTION_ENCRYPT |
 	       MLX5_FLOW_CONTEXT_ACTION_DECRYPT)))
-		return delete_fte(dev, ft, fte);
+		return delete_fte(ns, ft, fte);
 
 	rule = rule_search(fipsec, fte);
 	if (!rule)
@@ -1141,84 +1145,84 @@ static int fpga_ipsec_fs_delete_fte(struct mlx5_core_dev *dev,
 	rule_delete(fipsec, rule);
 
 	modify_spec_mailbox(dev, fte, &mbox_mod);
-	ret = delete_fte(dev, ft, fte);
+	ret = delete_fte(ns, ft, fte);
 	restore_spec_mailbox(fte, &mbox_mod);
 
 	return ret;
 }
 
 static int
-mlx5_fpga_ipsec_fs_create_flow_group_egress(struct mlx5_core_dev *dev,
+mlx5_fpga_ipsec_fs_create_flow_group_egress(struct mlx5_flow_root_namespace *ns,
 					    struct mlx5_flow_table *ft,
 					    u32 *in,
-					    unsigned int *group_id)
+					    struct mlx5_flow_group *fg)
 {
-	return fpga_ipsec_fs_create_flow_group(dev, ft, in, group_id, true);
+	return fpga_ipsec_fs_create_flow_group(ns, ft, in, fg, true);
 }
 
 static int
-mlx5_fpga_ipsec_fs_create_fte_egress(struct mlx5_core_dev *dev,
+mlx5_fpga_ipsec_fs_create_fte_egress(struct mlx5_flow_root_namespace *ns,
 				     struct mlx5_flow_table *ft,
 				     struct mlx5_flow_group *fg,
 				     struct fs_fte *fte)
 {
-	return fpga_ipsec_fs_create_fte(dev, ft, fg, fte, true);
+	return fpga_ipsec_fs_create_fte(ns, ft, fg, fte, true);
 }
 
 static int
-mlx5_fpga_ipsec_fs_update_fte_egress(struct mlx5_core_dev *dev,
+mlx5_fpga_ipsec_fs_update_fte_egress(struct mlx5_flow_root_namespace *ns,
 				     struct mlx5_flow_table *ft,
-				     unsigned int group_id,
+				     struct mlx5_flow_group *fg,
 				     int modify_mask,
 				     struct fs_fte *fte)
 {
-	return fpga_ipsec_fs_update_fte(dev, ft, group_id, modify_mask, fte,
+	return fpga_ipsec_fs_update_fte(ns, ft, fg, modify_mask, fte,
 					true);
 }
 
 static int
-mlx5_fpga_ipsec_fs_delete_fte_egress(struct mlx5_core_dev *dev,
+mlx5_fpga_ipsec_fs_delete_fte_egress(struct mlx5_flow_root_namespace *ns,
 				     struct mlx5_flow_table *ft,
 				     struct fs_fte *fte)
 {
-	return fpga_ipsec_fs_delete_fte(dev, ft, fte, true);
+	return fpga_ipsec_fs_delete_fte(ns, ft, fte, true);
 }
 
 static int
-mlx5_fpga_ipsec_fs_create_flow_group_ingress(struct mlx5_core_dev *dev,
+mlx5_fpga_ipsec_fs_create_flow_group_ingress(struct mlx5_flow_root_namespace *ns,
 					     struct mlx5_flow_table *ft,
 					     u32 *in,
-					     unsigned int *group_id)
+					     struct mlx5_flow_group *fg)
 {
-	return fpga_ipsec_fs_create_flow_group(dev, ft, in, group_id, false);
+	return fpga_ipsec_fs_create_flow_group(ns, ft, in, fg, false);
 }
 
 static int
-mlx5_fpga_ipsec_fs_create_fte_ingress(struct mlx5_core_dev *dev,
+mlx5_fpga_ipsec_fs_create_fte_ingress(struct mlx5_flow_root_namespace *ns,
 				      struct mlx5_flow_table *ft,
 				      struct mlx5_flow_group *fg,
 				      struct fs_fte *fte)
 {
-	return fpga_ipsec_fs_create_fte(dev, ft, fg, fte, false);
+	return fpga_ipsec_fs_create_fte(ns, ft, fg, fte, false);
 }
 
 static int
-mlx5_fpga_ipsec_fs_update_fte_ingress(struct mlx5_core_dev *dev,
+mlx5_fpga_ipsec_fs_update_fte_ingress(struct mlx5_flow_root_namespace *ns,
 				      struct mlx5_flow_table *ft,
-				      unsigned int group_id,
+				      struct mlx5_flow_group *fg,
 				      int modify_mask,
 				      struct fs_fte *fte)
 {
-	return fpga_ipsec_fs_update_fte(dev, ft, group_id, modify_mask, fte,
+	return fpga_ipsec_fs_update_fte(ns, ft, fg, modify_mask, fte,
 					false);
 }
 
 static int
-mlx5_fpga_ipsec_fs_delete_fte_ingress(struct mlx5_core_dev *dev,
+mlx5_fpga_ipsec_fs_delete_fte_ingress(struct mlx5_flow_root_namespace *ns,
 				      struct mlx5_flow_table *ft,
 				      struct fs_fte *fte)
 {
-	return fpga_ipsec_fs_delete_fte(dev, ft, fte, false);
+	return fpga_ipsec_fs_delete_fte(ns, ft, fte, false);
 }
 
 static struct mlx5_flow_cmds fpga_ipsec_ingress;

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

@@ -36,45 +36,42 @@
 #include "fs_core.h"
 
 struct mlx5_flow_cmds {
-	int (*create_flow_table)(struct mlx5_core_dev *dev,
-				 u16 vport,
-				 enum fs_flow_table_op_mod op_mod,
-				 enum fs_flow_table_type type,
-				 unsigned int level, unsigned int log_size,
-				 struct mlx5_flow_table *next_ft,
-				 unsigned int *table_id, u32 flags);
-	int (*destroy_flow_table)(struct mlx5_core_dev *dev,
+	int (*create_flow_table)(struct mlx5_flow_root_namespace *ns,
+				 struct mlx5_flow_table *ft,
+				 unsigned int log_size,
+				 struct mlx5_flow_table *next_ft);
+	int (*destroy_flow_table)(struct mlx5_flow_root_namespace *ns,
 				  struct mlx5_flow_table *ft);
 
-	int (*modify_flow_table)(struct mlx5_core_dev *dev,
+	int (*modify_flow_table)(struct mlx5_flow_root_namespace *ns,
 				 struct mlx5_flow_table *ft,
 				 struct mlx5_flow_table *next_ft);
 
-	int (*create_flow_group)(struct mlx5_core_dev *dev,
+	int (*create_flow_group)(struct mlx5_flow_root_namespace *ns,
 				 struct mlx5_flow_table *ft,
 				 u32 *in,
-				 unsigned int *group_id);
+				 struct mlx5_flow_group *fg);
 
-	int (*destroy_flow_group)(struct mlx5_core_dev *dev,
+	int (*destroy_flow_group)(struct mlx5_flow_root_namespace *ns,
 				  struct mlx5_flow_table *ft,
-				  unsigned int group_id);
+				  struct mlx5_flow_group *fg);
 
-	int (*create_fte)(struct mlx5_core_dev *dev,
+	int (*create_fte)(struct mlx5_flow_root_namespace *ns,
 			  struct mlx5_flow_table *ft,
 			  struct mlx5_flow_group *fg,
 			  struct fs_fte *fte);
 
-	int (*update_fte)(struct mlx5_core_dev *dev,
+	int (*update_fte)(struct mlx5_flow_root_namespace *ns,
 			  struct mlx5_flow_table *ft,
-			  unsigned int group_id,
+			  struct mlx5_flow_group *fg,
 			  int modify_mask,
 			  struct fs_fte *fte);
 
-	int (*delete_fte)(struct mlx5_core_dev *dev,
+	int (*delete_fte)(struct mlx5_flow_root_namespace *ns,
 			  struct mlx5_flow_table *ft,
 			  struct fs_fte *fte);
 
-	int (*update_root_ft)(struct mlx5_core_dev *dev,
+	int (*update_root_ft)(struct mlx5_flow_root_namespace *ns,
 			      struct mlx5_flow_table *ft,
 			      u32 underlay_qpn,
 			      bool disconnect);

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

@@ -403,7 +403,7 @@ static void del_hw_flow_table(struct fs_node *node)
 	trace_mlx5_fs_del_ft(ft);
 
 	if (node->active) {
-		err = root->cmds->destroy_flow_table(dev, ft);
+		err = root->cmds->destroy_flow_table(root, ft);
 		if (err)
 			mlx5_core_warn(dev, "flow steering can't destroy ft\n");
 	}
@@ -435,7 +435,7 @@ static void modify_fte(struct fs_fte *fte)
 	dev = get_dev(&fte->node);
 
 	root = find_root(&ft->node);
-	err = root->cmds->update_fte(dev, ft, fg->id, fte->modify_mask, fte);
+	err = root->cmds->update_fte(root, ft, fg, fte->modify_mask, fte);
 	if (err)
 		mlx5_core_warn(dev,
 			       "%s can't del rule fg id=%d fte_index=%d\n",
@@ -492,7 +492,7 @@ static void del_hw_fte(struct fs_node *node)
 	dev = get_dev(&ft->node);
 	root = find_root(&ft->node);
 	if (node->active) {
-		err = root->cmds->delete_fte(dev, ft, fte);
+		err = root->cmds->delete_fte(root, ft, fte);
 		if (err)
 			mlx5_core_warn(dev,
 				       "flow steering can't delete fte in index %d of flow group id %d\n",
@@ -532,7 +532,7 @@ static void del_hw_flow_group(struct fs_node *node)
 	trace_mlx5_fs_del_fg(fg);
 
 	root = find_root(&ft->node);
-	if (fg->node.active && root->cmds->destroy_flow_group(dev, ft, fg->id))
+	if (fg->node.active && root->cmds->destroy_flow_group(root, ft, fg))
 		mlx5_core_warn(dev, "flow steering can't destroy fg %d of ft %d\n",
 			       fg->id, ft->id);
 }
@@ -783,7 +783,7 @@ static int connect_fts_in_prio(struct mlx5_core_dev *dev,
 
 	fs_for_each_ft(iter, prio) {
 		i++;
-		err = root->cmds->modify_flow_table(dev, iter, ft);
+		err = root->cmds->modify_flow_table(root, iter, ft);
 		if (err) {
 			mlx5_core_warn(dev, "Failed to modify flow table %d\n",
 				       iter->id);
@@ -831,11 +831,11 @@ static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio
 	if (list_empty(&root->underlay_qpns)) {
 		/* Don't set any QPN (zero) in case QPN list is empty */
 		qpn = 0;
-		err = root->cmds->update_root_ft(root->dev, ft, qpn, false);
+		err = root->cmds->update_root_ft(root, ft, qpn, false);
 	} else {
 		list_for_each_entry(uqp, &root->underlay_qpns, list) {
 			qpn = uqp->qpn;
-			err = root->cmds->update_root_ft(root->dev, ft,
+			err = root->cmds->update_root_ft(root, ft,
 							 qpn, false);
 			if (err)
 				break;
@@ -871,7 +871,7 @@ static int _mlx5_modify_rule_destination(struct mlx5_flow_rule *rule,
 
 	memcpy(&rule->dest_attr, dest, sizeof(*dest));
 	root = find_root(&ft->node);
-	err = root->cmds->update_fte(get_dev(&ft->node), ft, fg->id,
+	err = root->cmds->update_fte(root, ft, fg,
 				     modify_mask, fte);
 	up_write_ref_node(&fte->node, false);
 
@@ -1013,9 +1013,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa
 	tree_init_node(&ft->node, del_hw_flow_table, del_sw_flow_table);
 	log_table_sz = ft->max_fte ? ilog2(ft->max_fte) : 0;
 	next_ft = find_next_chained_ft(fs_prio);
-	err = root->cmds->create_flow_table(root->dev, ft->vport, ft->op_mod,
-					    ft->type, ft->level, log_table_sz,
-					    next_ft, &ft->id, ft->flags);
+	err = root->cmds->create_flow_table(root, ft, log_table_sz, next_ft);
 	if (err)
 		goto free_ft;
 
@@ -1032,7 +1030,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa
 	trace_mlx5_fs_add_ft(ft);
 	return ft;
 destroy_ft:
-	root->cmds->destroy_flow_table(root->dev, ft);
+	root->cmds->destroy_flow_table(root, ft);
 free_ft:
 	kfree(ft);
 unlock_root:
@@ -1114,7 +1112,6 @@ struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft,
 				   start_flow_index);
 	int end_index = MLX5_GET(create_flow_group_in, fg_in,
 				 end_flow_index);
-	struct mlx5_core_dev *dev = get_dev(&ft->node);
 	struct mlx5_flow_group *fg;
 	int err;
 
@@ -1129,7 +1126,7 @@ struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft,
 	if (IS_ERR(fg))
 		return fg;
 
-	err = root->cmds->create_flow_group(dev, ft, fg_in, &fg->id);
+	err = root->cmds->create_flow_group(root, ft, fg_in, fg);
 	if (err) {
 		tree_put_node(&fg->node, false);
 		return ERR_PTR(err);
@@ -1269,11 +1266,9 @@ add_rule_fte(struct fs_fte *fte,
 	fs_get_obj(ft, fg->node.parent);
 	root = find_root(&fg->node);
 	if (!(fte->status & FS_FTE_STATUS_EXISTING))
-		err = root->cmds->create_fte(get_dev(&ft->node),
-					     ft, fg, fte);
+		err = root->cmds->create_fte(root, ft, fg, fte);
 	else
-		err = root->cmds->update_fte(get_dev(&ft->node), ft, fg->id,
-						     modify_mask, fte);
+		err = root->cmds->update_fte(root, ft, fg, modify_mask, fte);
 	if (err)
 		goto free_handle;
 
@@ -1339,7 +1334,6 @@ static int create_auto_flow_group(struct mlx5_flow_table *ft,
 				  struct mlx5_flow_group *fg)
 {
 	struct mlx5_flow_root_namespace *root = find_root(&ft->node);
-	struct mlx5_core_dev *dev = get_dev(&ft->node);
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	void *match_criteria_addr;
 	u8 src_esw_owner_mask_on;
@@ -1369,7 +1363,7 @@ static int create_auto_flow_group(struct mlx5_flow_table *ft,
 	memcpy(match_criteria_addr, fg->mask.match_criteria,
 	       sizeof(fg->mask.match_criteria));
 
-	err = root->cmds->create_flow_group(dev, ft, in, &fg->id);
+	err = root->cmds->create_flow_group(root, ft, in, fg);
 	if (!err) {
 		fg->node.active = true;
 		trace_mlx5_fs_add_fg(fg);
@@ -1941,12 +1935,12 @@ static int update_root_ft_destroy(struct mlx5_flow_table *ft)
 	if (list_empty(&root->underlay_qpns)) {
 		/* Don't set any QPN (zero) in case QPN list is empty */
 		qpn = 0;
-		err = root->cmds->update_root_ft(root->dev, new_root_ft,
+		err = root->cmds->update_root_ft(root, new_root_ft,
 						 qpn, false);
 	} else {
 		list_for_each_entry(uqp, &root->underlay_qpns, list) {
 			qpn = uqp->qpn;
-			err = root->cmds->update_root_ft(root->dev,
+			err = root->cmds->update_root_ft(root,
 							 new_root_ft, qpn,
 							 false);
 			if (err)
@@ -2060,6 +2054,10 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev,
 		if (steering->sniffer_tx_root_ns)
 			return &steering->sniffer_tx_root_ns->ns;
 		return NULL;
+	case MLX5_FLOW_NAMESPACE_RDMA_RX:
+		if (steering->rdma_rx_root_ns)
+			return &steering->rdma_rx_root_ns->ns;
+		return NULL;
 	default:
 		break;
 	}
@@ -2456,6 +2454,7 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev)
 	steering->fdb_sub_ns = NULL;
 	cleanup_root_ns(steering->sniffer_rx_root_ns);
 	cleanup_root_ns(steering->sniffer_tx_root_ns);
+	cleanup_root_ns(steering->rdma_rx_root_ns);
 	cleanup_root_ns(steering->egress_root_ns);
 	mlx5_cleanup_fc_stats(dev);
 	kmem_cache_destroy(steering->ftes_cache);
@@ -2497,6 +2496,25 @@ static int init_sniffer_rx_root_ns(struct mlx5_flow_steering *steering)
 	return 0;
 }
 
+static int init_rdma_rx_root_ns(struct mlx5_flow_steering *steering)
+{
+	struct fs_prio *prio;
+
+	steering->rdma_rx_root_ns = create_root_ns(steering, FS_FT_RDMA_RX);
+	if (!steering->rdma_rx_root_ns)
+		return -ENOMEM;
+
+	steering->rdma_rx_root_ns->def_miss_action =
+		MLX5_FLOW_TABLE_MISS_ACTION_SWITCH_DOMAIN;
+
+	/* Create single prio */
+	prio = fs_create_prio(&steering->rdma_rx_root_ns->ns, 0, 1);
+	if (IS_ERR(prio)) {
+		cleanup_root_ns(steering->rdma_rx_root_ns);
+		return PTR_ERR(prio);
+	}
+	return 0;
+}
 static int init_fdb_root_ns(struct mlx5_flow_steering *steering)
 {
 	struct mlx5_flow_namespace *ns;
@@ -2733,6 +2751,13 @@ int mlx5_init_fs(struct mlx5_core_dev *dev)
 			goto err;
 	}
 
+	if (MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support) &&
+	    MLX5_CAP_FLOWTABLE_RDMA_RX(dev, table_miss_action_domain)) {
+		err = init_rdma_rx_root_ns(steering);
+		if (err)
+			goto err;
+	}
+
 	if (MLX5_IPSEC_DEV(dev) || MLX5_CAP_FLOWTABLE_NIC_TX(dev, ft_support)) {
 		err = init_egress_root_ns(steering);
 		if (err)
@@ -2762,7 +2787,7 @@ int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn)
 		goto update_ft_fail;
 	}
 
-	err = root->cmds->update_root_ft(dev, root->root_ft, underlay_qpn,
+	err = root->cmds->update_root_ft(root, root->root_ft, underlay_qpn,
 					 false);
 	if (err) {
 		mlx5_core_warn(dev, "Failed adding underlay QPN (%u) to root FT err(%d)\n",
@@ -2806,7 +2831,7 @@ int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn)
 		goto out;
 	}
 
-	err = root->cmds->update_root_ft(dev, root->root_ft, underlay_qpn,
+	err = root->cmds->update_root_ft(root, root->root_ft, underlay_qpn,
 					 true);
 	if (err)
 		mlx5_core_warn(dev, "Failed removing underlay QPN (%u) from root FT err(%d)\n",

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

@@ -67,6 +67,7 @@ enum fs_flow_table_type {
 	FS_FT_FDB             = 0X4,
 	FS_FT_SNIFFER_RX	= 0X5,
 	FS_FT_SNIFFER_TX	= 0X6,
+	FS_FT_RDMA_RX		= 0X7,
 	FS_FT_MAX_TYPE = FS_FT_SNIFFER_TX,
 };
 
@@ -90,6 +91,7 @@ struct mlx5_flow_steering {
 	struct mlx5_flow_root_namespace **esw_ingress_root_ns;
 	struct mlx5_flow_root_namespace	*sniffer_tx_root_ns;
 	struct mlx5_flow_root_namespace	*sniffer_rx_root_ns;
+	struct mlx5_flow_root_namespace	*rdma_rx_root_ns;
 	struct mlx5_flow_root_namespace	*egress_root_ns;
 };
 
@@ -150,7 +152,7 @@ struct mlx5_ft_underlay_qp {
 	u32 qpn;
 };
 
-#define MLX5_FTE_MATCH_PARAM_RESERVED	reserved_at_800
+#define MLX5_FTE_MATCH_PARAM_RESERVED	reserved_at_a00
 /* Calculate the fte_match_param length and without the reserved length.
  * Make sure the reserved field is the last.
  */
@@ -216,6 +218,7 @@ struct mlx5_flow_root_namespace {
 	struct mutex			chain_lock;
 	struct list_head		underlay_qpns;
 	const struct mlx5_flow_cmds	*cmds;
+	enum mlx5_flow_table_miss_action def_miss_action;
 };
 
 int mlx5_init_fc_stats(struct mlx5_core_dev *dev);

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

@@ -380,7 +380,7 @@ int mlx5_health_init(struct mlx5_core_dev *dev)
 		return -ENOMEM;
 
 	strcpy(name, "mlx5_health");
-	strcat(name, dev->priv.name);
+	strcat(name, dev_name(dev->device));
 	health->wq = create_singlethread_workqueue(name);
 	kfree(name);
 	if (!health->wq)

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

@@ -721,7 +721,6 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev,
 	struct mlx5_priv *priv = &dev->priv;
 	int err = 0;
 
-	dev->pdev = pdev;
 	priv->pci_dev_data = id->driver_data;
 
 	pci_set_drvdata(dev->pdev, dev);
@@ -1222,14 +1221,11 @@ static const struct devlink_ops mlx5_devlink_ops = {
 #endif
 };
 
-static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx, const char *name)
+static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 {
 	struct mlx5_priv *priv = &dev->priv;
 	int err;
 
-	strncpy(priv->name, name, MLX5_MAX_NAME_LEN);
-	priv->name[MLX5_MAX_NAME_LEN - 1] = 0;
-
 	dev->profile = &profile[profile_idx];
 
 	INIT_LIST_HEAD(&priv->ctx_list);
@@ -1247,9 +1243,10 @@ static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx, const char
 	INIT_LIST_HEAD(&priv->pgdir_list);
 	spin_lock_init(&priv->mkey_lock);
 
-	priv->dbg_root = debugfs_create_dir(name, mlx5_debugfs_root);
+	priv->dbg_root = debugfs_create_dir(dev_name(dev->device),
+					    mlx5_debugfs_root);
 	if (!priv->dbg_root) {
-		pr_err("mlx5_core: %s error, Cannot create debugfs dir, aborting\n", name);
+		dev_err(dev->device, "mlx5_core: error, Cannot create debugfs dir, aborting\n");
 		return -ENOMEM;
 	}
 
@@ -1292,8 +1289,10 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	}
 
 	dev = devlink_priv(devlink);
+	dev->device = &pdev->dev;
+	dev->pdev = pdev;
 
-	err = mlx5_mdev_init(dev, prof_sel, dev_name(&pdev->dev));
+	err = mlx5_mdev_init(dev, prof_sel);
 	if (err)
 		goto mdev_init_err;
 

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

@@ -41,6 +41,7 @@
 #include <linux/ptp_clock_kernel.h>
 #include <linux/mlx5/cq.h>
 #include <linux/mlx5/fs.h>
+#include <linux/mlx5/driver.h>
 
 #define DRIVER_NAME "mlx5_core"
 #define DRIVER_VERSION "5.0-0"
@@ -48,12 +49,13 @@
 extern uint mlx5_core_debug_mask;
 
 #define mlx5_core_dbg(__dev, format, ...)				\
-	pr_debug("%s:%s:%d:(pid %d): " format, (__dev)->priv.name,      \
+	dev_dbg((__dev)->device, "%s:%d:(pid %d): " format,		\
 		 __func__, __LINE__, current->pid,			\
 		 ##__VA_ARGS__)
 
 #define mlx5_core_dbg_once(__dev, format, ...)		\
-	pr_debug_once("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \
+	dev_dbg_once((__dev)->device,		\
+		     "%s:%d:(pid %d): " format,		\
 		     __func__, __LINE__, current->pid,	\
 		     ##__VA_ARGS__)
 
@@ -64,35 +66,38 @@ do {									\
 } while (0)
 
 #define mlx5_core_err(__dev, format, ...)			\
-	pr_err("%s:%s:%d:(pid %d): " format, (__dev)->priv.name,        \
+	dev_err((__dev)->device, "%s:%d:(pid %d): " format,	\
 		__func__, __LINE__, current->pid,		\
 	       ##__VA_ARGS__)
 
 #define mlx5_core_err_rl(__dev, format, ...)			\
-	pr_err_ratelimited("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \
+	dev_err_ratelimited((__dev)->device,			\
+			    "%s:%d:(pid %d): " format,		\
 			    __func__, __LINE__, current->pid,	\
 			    ##__VA_ARGS__)
 
 #define mlx5_core_warn(__dev, format, ...)			\
-	pr_warn("%s:%s:%d:(pid %d): " format, (__dev)->priv.name,       \
+	dev_warn((__dev)->device, "%s:%d:(pid %d): " format,	\
 		 __func__, __LINE__, current->pid,		\
 		 ##__VA_ARGS__)
 
 #define mlx5_core_warn_once(__dev, format, ...)				\
-	pr_warn_once("%s:%s:%d:(pid %d): " format, (__dev)->priv.name,  \
+	dev_warn_once((__dev)->device, "%s:%d:(pid %d): " format,	\
 		      __func__, __LINE__, current->pid,			\
 		      ##__VA_ARGS__)
 
 #define mlx5_core_warn_rl(__dev, format, ...)			\
-	pr_warn_ratelimited("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \
+	dev_warn_ratelimited((__dev)->device,			\
+			     "%s:%d:(pid %d): " format,		\
 			     __func__, __LINE__, current->pid,	\
 			     ##__VA_ARGS__)
 
 #define mlx5_core_info(__dev, format, ...)		\
-	pr_info("%s " format, (__dev)->priv.name, ##__VA_ARGS__)
+	dev_info((__dev)->device, format, ##__VA_ARGS__)
 
 #define mlx5_core_info_rl(__dev, format, ...)			\
-	pr_info_ratelimited("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \
+	dev_info_ratelimited((__dev)->device,			\
+			     "%s:%d:(pid %d): " format,		\
 			     __func__, __LINE__, current->pid,	\
 			     ##__VA_ARGS__)
 

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

@@ -200,7 +200,7 @@ static void free_4k(struct mlx5_core_dev *dev, u64 addr)
 		rb_erase(&fwp->rb_node, &dev->priv.page_root);
 		if (fwp->free_count != 1)
 			list_del(&fwp->list);
-		dma_unmap_page(&dev->pdev->dev, addr & MLX5_U64_4K_PAGE_MASK,
+		dma_unmap_page(dev->device, addr & MLX5_U64_4K_PAGE_MASK,
 			       PAGE_SIZE, DMA_BIDIRECTIONAL);
 		__free_page(fwp->page);
 		kfree(fwp);
@@ -211,11 +211,12 @@ static void free_4k(struct mlx5_core_dev *dev, u64 addr)
 
 static int alloc_system_page(struct mlx5_core_dev *dev, u16 func_id)
 {
+	struct device *device = dev->device;
+	int nid = dev_to_node(device);
 	struct page *page;
 	u64 zero_addr = 1;
 	u64 addr;
 	int err;
-	int nid = dev_to_node(&dev->pdev->dev);
 
 	page = alloc_pages_node(nid, GFP_HIGHUSER, 0);
 	if (!page) {
@@ -223,9 +224,8 @@ static int alloc_system_page(struct mlx5_core_dev *dev, u16 func_id)
 		return -ENOMEM;
 	}
 map:
-	addr = dma_map_page(&dev->pdev->dev, page, 0,
-			    PAGE_SIZE, DMA_BIDIRECTIONAL);
-	if (dma_mapping_error(&dev->pdev->dev, addr)) {
+	addr = dma_map_page(device, page, 0, PAGE_SIZE, DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(device, addr)) {
 		mlx5_core_warn(dev, "failed dma mapping page\n");
 		err = -ENOMEM;
 		goto err_mapping;
@@ -240,8 +240,7 @@ static int alloc_system_page(struct mlx5_core_dev *dev, u16 func_id)
 	err = insert_page(dev, addr, page, func_id);
 	if (err) {
 		mlx5_core_err(dev, "failed to track allocated page\n");
-		dma_unmap_page(&dev->pdev->dev, addr, PAGE_SIZE,
-			       DMA_BIDIRECTIONAL);
+		dma_unmap_page(device, addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
 	}
 
 err_mapping:
@@ -249,7 +248,7 @@ static int alloc_system_page(struct mlx5_core_dev *dev, u16 func_id)
 		__free_page(page);
 
 	if (zero_addr == 0)
-		dma_unmap_page(&dev->pdev->dev, zero_addr, PAGE_SIZE,
+		dma_unmap_page(device, zero_addr, PAGE_SIZE,
 			       DMA_BIDIRECTIONAL);
 
 	return err;
@@ -600,8 +599,7 @@ int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages)
 		return 0;
 	}
 
-	mlx5_core_dbg(dev, "Waiting for %d pages from %s\n", prev_pages,
-		      dev->priv.name);
+	mlx5_core_dbg(dev, "Waiting for %d pages\n", prev_pages);
 	while (*pages) {
 		if (time_after(jiffies, end)) {
 			mlx5_core_warn(dev, "aborting while there are %d pending pages\n", *pages);
@@ -614,6 +612,6 @@ int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages)
 		msleep(50);
 	}
 
-	mlx5_core_dbg(dev, "All pages received from %s\n", dev->priv.name);
+	mlx5_core_dbg(dev, "All pages received\n");
 	return 0;
 }

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

+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies */
+
+#include <linux/mlx5/vport.h>
+#include <rdma/ib_verbs.h>
+#include <net/addrconf.h>
+
+#include "lib/mlx5.h"
+#include "eswitch.h"
+#include "fs_core.h"
+#include "rdma.h"
+
+static void mlx5_rdma_disable_roce_steering(struct mlx5_core_dev *dev)
+{
+	struct mlx5_core_roce *roce = &dev->priv.roce;
+
+	if (!roce->ft)
+		return;
+
+	mlx5_del_flow_rules(roce->allow_rule);
+	mlx5_destroy_flow_group(roce->fg);
+	mlx5_destroy_flow_table(roce->ft);
+}
+
+static int mlx5_rdma_enable_roce_steering(struct mlx5_core_dev *dev)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_core_roce *roce = &dev->priv.roce;
+	struct mlx5_flow_handle *flow_rule = NULL;
+	struct mlx5_flow_table_attr ft_attr = {};
+	struct mlx5_flow_namespace *ns = NULL;
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_spec *spec;
+	struct mlx5_flow_table *ft;
+	struct mlx5_flow_group *fg;
+	void *match_criteria;
+	u32 *flow_group_in;
+	void *misc;
+	int err;
+
+	if (!(MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support) &&
+	      MLX5_CAP_FLOWTABLE_RDMA_RX(dev, table_miss_action_domain)))
+		return -EOPNOTSUPP;
+
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!flow_group_in)
+		return -ENOMEM;
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec) {
+		kvfree(flow_group_in);
+		return -ENOMEM;
+	}
+
+	ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_RDMA_RX);
+	if (!ns) {
+		mlx5_core_err(dev, "Failed to get RDMA RX namespace");
+		err = -EOPNOTSUPP;
+		goto free;
+	}
+
+	ft_attr.max_fte = 1;
+	ft = mlx5_create_flow_table(ns, &ft_attr);
+	if (IS_ERR(ft)) {
+		mlx5_core_err(dev, "Failed to create RDMA RX flow table");
+		err = PTR_ERR(ft);
+		goto free;
+	}
+
+	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
+		 MLX5_MATCH_MISC_PARAMETERS);
+	match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in,
+				      match_criteria);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+			 misc_parameters.source_port);
+
+	fg = mlx5_create_flow_group(ft, flow_group_in);
+	if (IS_ERR(fg)) {
+		err = PTR_ERR(fg);
+		mlx5_core_err(dev, "Failed to create RDMA RX flow group err(%d)\n", err);
+		goto destroy_flow_table;
+	}
+
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+			    misc_parameters);
+	MLX5_SET(fte_match_set_misc, misc, source_port,
+		 dev->priv.eswitch->manager_vport);
+	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+			    misc_parameters);
+	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+	flow_rule = mlx5_add_flow_rules(ft, spec, &flow_act, NULL, 0);
+	if (IS_ERR(flow_rule)) {
+		err = PTR_ERR(flow_rule);
+		mlx5_core_err(dev, "Failed to add RoCE allow rule, err=%d\n",
+			      err);
+		goto destroy_flow_group;
+	}
+
+	kvfree(spec);
+	kvfree(flow_group_in);
+	roce->ft = ft;
+	roce->fg = fg;
+	roce->allow_rule = flow_rule;
+
+	return 0;
+
+destroy_flow_table:
+	mlx5_destroy_flow_table(ft);
+destroy_flow_group:
+	mlx5_destroy_flow_group(fg);
+free:
+	kvfree(spec);
+	kvfree(flow_group_in);
+	return err;
+}
+
+static void mlx5_rdma_del_roce_addr(struct mlx5_core_dev *dev)
+{
+	mlx5_core_roce_gid_set(dev, 0, 0, 0,
+			       NULL, NULL, false, 0, 0);
+}
+
+static void mlx5_rdma_make_default_gid(struct mlx5_core_dev *dev, union ib_gid *gid)
+{
+	u8 hw_id[ETH_ALEN];
+
+	mlx5_query_nic_vport_mac_address(dev, 0, hw_id);
+	gid->global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL);
+	addrconf_addr_eui48(&gid->raw[8], hw_id);
+}
+
+static int mlx5_rdma_add_roce_addr(struct mlx5_core_dev *dev)
+{
+	union ib_gid gid;
+	u8 mac[ETH_ALEN];
+
+	mlx5_rdma_make_default_gid(dev, &gid);
+	return mlx5_core_roce_gid_set(dev, 0,
+				      MLX5_ROCE_VERSION_1,
+				      0, gid.raw, mac,
+				      false, 0, 1);
+}
+
+void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev)
+{
+	mlx5_rdma_disable_roce_steering(dev);
+	mlx5_rdma_del_roce_addr(dev);
+	mlx5_nic_vport_disable_roce(dev);
+}
+
+void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev)
+{
+	int err;
+
+	err = mlx5_nic_vport_enable_roce(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to enable RoCE: %d\n", err);
+		return;
+	}
+
+	err = mlx5_rdma_add_roce_addr(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to add RoCE address: %d\n", err);
+		goto disable_roce;
+	}
+
+	err = mlx5_rdma_enable_roce_steering(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to enable RoCE steering: %d\n", err);
+		goto del_roce_addr;
+	}
+
+	return;
+
+del_roce_addr:
+	mlx5_rdma_del_roce_addr(dev);
+disable_roce:
+	mlx5_nic_vport_disable_roce(dev);
+	return;
+}

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

+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5_RDMA_H__
+#define __MLX5_RDMA_H__
+
+#include "mlx5_core.h"
+
+#ifdef CONFIG_MLX5_ESWITCH
+
+void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev);
+void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev);
+
+#else /* CONFIG_MLX5_ESWITCH */
+
+static inline void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev) {}
+static inline void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev) {}
+
+#endif /* CONFIG_MLX5_ESWITCH */
+#endif /* __MLX5_RDMA_H__ */

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

@@ -182,16 +182,24 @@ int mlx5_core_query_sq_state(struct mlx5_core_dev *dev, u32 sqn, u8 *state)
 }
 EXPORT_SYMBOL_GPL(mlx5_core_query_sq_state);
 
+int mlx5_core_create_tir_out(struct mlx5_core_dev *dev,
+			     u32 *in, int inlen,
+			     u32 *out, int outlen)
+{
+	MLX5_SET(create_tir_in, in, opcode, MLX5_CMD_OP_CREATE_TIR);
+
+	return mlx5_cmd_exec(dev, in, inlen, out, outlen);
+}
+EXPORT_SYMBOL(mlx5_core_create_tir_out);
+
 int mlx5_core_create_tir(struct mlx5_core_dev *dev, u32 *in, int inlen,
 			 u32 *tirn)
 {
-	u32 out[MLX5_ST_SZ_DW(create_tir_out)] = {0};
+	u32 out[MLX5_ST_SZ_DW(create_tir_out)] = {};
 	int err;
 
-	MLX5_SET(create_tir_in, in, opcode, MLX5_CMD_OP_CREATE_TIR);
-
-	memset(out, 0, sizeof(out));
-	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
+	err = mlx5_core_create_tir_out(dev, in, inlen,
+				       out, sizeof(out));
 	if (!err)
 		*tirn = MLX5_GET(create_tir_out, out, tirn);
 

include/linux/mlx5/device.h

@@ -1002,7 +1002,8 @@ enum {
 	MLX5_MATCH_OUTER_HEADERS	= 1 << 0,
 	MLX5_MATCH_MISC_PARAMETERS	= 1 << 1,
 	MLX5_MATCH_INNER_HEADERS	= 1 << 2,
-
+	MLX5_MATCH_MISC_PARAMETERS_2	= 1 << 3,
+	MLX5_MATCH_MISC_PARAMETERS_3	= 1 << 4,
 };
 
 enum {
@@ -1046,6 +1047,7 @@ enum mlx5_mpls_supported_fields {
 };
 
 enum mlx5_flex_parser_protos {
+	MLX5_FLEX_PROTO_GENEVE	      = 1 << 3,
 	MLX5_FLEX_PROTO_CW_MPLS_GRE   = 1 << 4,
 	MLX5_FLEX_PROTO_CW_MPLS_UDP   = 1 << 5,
 };
@@ -1167,6 +1169,12 @@ enum mlx5_qcam_feature_groups {
 #define MLX5_CAP_FLOWTABLE_SNIFFER_TX_MAX(mdev, cap) \
 	MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_transmit_sniffer.cap)
 
+#define MLX5_CAP_FLOWTABLE_RDMA_RX(mdev, cap) \
+	MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive_rdma.cap)
+
+#define MLX5_CAP_FLOWTABLE_RDMA_RX_MAX(mdev, cap) \
+	MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive_rdma.cap)
+
 #define MLX5_CAP_ESW_FLOWTABLE(mdev, cap) \
 	MLX5_GET(flow_table_eswitch_cap, \
 		 mdev->caps.hca_cur[MLX5_CAP_ESWITCH_FLOW_TABLE], cap)

include/linux/mlx5/driver.h

@@ -56,7 +56,6 @@
 
 enum {
 	MLX5_BOARD_ID_LEN = 64,
-	MLX5_MAX_NAME_LEN = 16,
 };
 
 enum {
@@ -513,8 +512,13 @@ struct mlx5_rl_table {
 	struct mlx5_rl_entry   *rl_entry;
 };
 
+struct mlx5_core_roce {
+	struct mlx5_flow_table *ft;
+	struct mlx5_flow_group *fg;
+	struct mlx5_flow_handle *allow_rule;
+};
+
 struct mlx5_priv {
-	char			name[MLX5_MAX_NAME_LEN];
 	struct mlx5_eq_table	*eq_table;
 
 	/* pages stuff */
@@ -567,6 +571,7 @@ struct mlx5_priv {
 	struct mlx5_lag		*lag;
 	struct mlx5_devcom	*devcom;
 	unsigned long		pci_dev_data;
+	struct mlx5_core_roce	roce;
 	struct mlx5_fc_stats		fc_stats;
 	struct mlx5_rl_table            rl_table;
 
@@ -643,6 +648,7 @@ struct mlx5_fw_tracer;
 struct mlx5_vxlan;
 
 struct mlx5_core_dev {
+	struct device *device;
 	struct pci_dev	       *pdev;
 	/* sync pci state */
 	struct mutex		pci_status_mutex;

include/linux/mlx5/fs.h

@@ -73,6 +73,7 @@ enum mlx5_flow_namespace_type {
 	MLX5_FLOW_NAMESPACE_SNIFFER_RX,
 	MLX5_FLOW_NAMESPACE_SNIFFER_TX,
 	MLX5_FLOW_NAMESPACE_EGRESS,
+	MLX5_FLOW_NAMESPACE_RDMA_RX,
 };
 
 enum {

include/linux/mlx5/mlx5_ifc.h

@@ -80,6 +80,19 @@ enum {
 	MLX5_SHARED_RESOURCE_UID = 0xffff,
 };
 
+enum {
+	MLX5_OBJ_TYPE_SW_ICM = 0x0008,
+};
+
+enum {
+	MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM = (1ULL << MLX5_OBJ_TYPE_SW_ICM),
+	MLX5_GENERAL_OBJ_TYPES_CAP_GENEVE_TLV_OPT = (1ULL << 11),
+};
+
+enum {
+	MLX5_OBJ_TYPE_GENEVE_TLV_OPT = 0x000b,
+};
+
 enum {
 	MLX5_CMD_OP_QUERY_HCA_CAP                 = 0x100,
 	MLX5_CMD_OP_QUERY_ADAPTER                 = 0x101,
@@ -299,7 +312,11 @@ struct mlx5_ifc_flow_table_fields_supported_bits {
 	u8         outer_gre_protocol[0x1];
 	u8         outer_gre_key[0x1];
 	u8         outer_vxlan_vni[0x1];
-	u8         reserved_at_1a[0x5];
+	u8         outer_geneve_vni[0x1];
+	u8         outer_geneve_oam[0x1];
+	u8         outer_geneve_protocol_type[0x1];
+	u8         outer_geneve_opt_len[0x1];
+	u8         reserved_at_1e[0x1];
 	u8         source_eswitch_port[0x1];
 
 	u8         inner_dmac[0x1];
@@ -327,7 +344,8 @@ struct mlx5_ifc_flow_table_fields_supported_bits {
 	u8         inner_tcp_flags[0x1];
 	u8         reserved_at_37[0x9];
 
-	u8         reserved_at_40[0x5];
+	u8         geneve_tlv_option_0_data[0x1];
+	u8         reserved_at_41[0x4];
 	u8         outer_first_mpls_over_udp[0x4];
 	u8         outer_first_mpls_over_gre[0x4];
 	u8         inner_first_mpls[0x4];
@@ -357,11 +375,14 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
 	u8         pop_vlan_2[0x1];
 	u8         push_vlan_2[0x1];
 	u8	   reformat_and_vlan_action[0x1];
-	u8	   reserved_at_10[0x2];
+	u8	   reserved_at_10[0x1];
+	u8         sw_owner[0x1];
 	u8	   reformat_l3_tunnel_to_l2[0x1];
 	u8	   reformat_l2_to_l3_tunnel[0x1];
 	u8	   reformat_and_modify_action[0x1];
-	u8         reserved_at_15[0xb];
+	u8         reserved_at_15[0x2];
+	u8	   table_miss_action_domain[0x1];
+	u8         reserved_at_18[0x8];
 	u8         reserved_at_20[0x2];
 	u8         log_max_ft_size[0x6];
 	u8         log_max_modify_header_context[0x8];
@@ -469,7 +490,9 @@ struct mlx5_ifc_fte_match_set_misc_bits {
 	u8         vxlan_vni[0x18];
 	u8         reserved_at_b8[0x8];
 
-	u8         reserved_at_c0[0x20];
+	u8         geneve_vni[0x18];
+	u8         reserved_at_d8[0x7];
+	u8         geneve_oam[0x1];
 
 	u8         reserved_at_e0[0xc];
 	u8         outer_ipv6_flow_label[0x14];
@@ -477,7 +500,11 @@ struct mlx5_ifc_fte_match_set_misc_bits {
 	u8         reserved_at_100[0xc];
 	u8         inner_ipv6_flow_label[0x14];
 
-	u8         reserved_at_120[0x28];
+	u8         reserved_at_120[0xa];
+	u8         geneve_opt_len[0x6];
+	u8         geneve_protocol_type[0x10];
+
+	u8         reserved_at_140[0x8];
 	u8         bth_dst_qp[0x18];
 	u8	   reserved_at_160[0x20];
 	u8	   outer_esp_spi[0x20];
@@ -507,6 +534,12 @@ struct mlx5_ifc_fte_match_set_misc2_bits {
 	u8         reserved_at_1a0[0x60];
 };
 
+struct mlx5_ifc_fte_match_set_misc3_bits {
+	u8         reserved_at_0[0x120];
+	u8         geneve_tlv_option_0_data[0x20];
+	u8         reserved_at_140[0xc0];
+};
+
 struct mlx5_ifc_cmd_pas_bits {
 	u8         pa_h[0x20];
 
@@ -589,7 +622,7 @@ struct mlx5_ifc_flow_table_nic_cap_bits {
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive;
 
-	u8         reserved_at_400[0x200];
+	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive_rdma;
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive_sniffer;
 
@@ -770,7 +803,19 @@ struct mlx5_ifc_device_mem_cap_bits {
 
 	u8         max_memic_size[0x20];
 
-	u8         reserved_at_c0[0x740];
+	u8         steering_sw_icm_start_address[0x40];
+
+	u8         reserved_at_100[0x8];
+	u8         log_header_modify_sw_icm_size[0x8];
+	u8         reserved_at_110[0x2];
+	u8         log_sw_icm_alloc_granularity[0x6];
+	u8         log_steering_sw_icm_size[0x8];
+
+	u8         reserved_at_120[0x20];
+
+	u8         header_modify_sw_icm_start_address[0x40];
+
+	u8         reserved_at_180[0x680];
 };
 
 enum {
@@ -919,6 +964,7 @@ enum {
 
 enum {
 	MLX5_UCTX_CAP_RAW_TX = 1UL << 0,
+	MLX5_UCTX_CAP_INTERNAL_DEV_RES = 1UL << 1,
 };
 
 struct mlx5_ifc_cmd_hca_cap_bits {
@@ -929,7 +975,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         log_max_srq_sz[0x8];
 	u8         log_max_qp_sz[0x8];
-	u8         reserved_at_90[0xb];
+	u8         reserved_at_90[0x8];
+	u8         prio_tag_required[0x1];
+	u8         reserved_at_99[0x2];
 	u8         log_max_qp[0x5];
 
 	u8         reserved_at_a0[0xb];
@@ -1211,7 +1259,11 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8	   num_of_uars_per_page[0x20];
 
 	u8         flex_parser_protocols[0x20];
-	u8         reserved_at_560[0x20];
+
+	u8         max_geneve_tlv_options[0x8];
+	u8         reserved_at_568[0x3];
+	u8         max_geneve_tlv_option_data_len[0x5];
+	u8         reserved_at_570[0x10];
 
 	u8         reserved_at_580[0x3c];
 	u8         mini_cqe_resp_stride_index[0x1];
@@ -1247,7 +1299,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         uctx_cap[0x20];
 
-	u8	   reserved_at_6c0[0x140];
+	u8         reserved_at_6c0[0x4];
+	u8         flex_parser_id_geneve_tlv_option_0[0x4];
+	u8         reserved_at_6c8[0x138];
 };
 
 enum mlx5_flow_destination_type {
@@ -1260,6 +1314,12 @@ enum mlx5_flow_destination_type {
 	MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM = 0x101,
 };
 
+enum mlx5_flow_table_miss_action {
+	MLX5_FLOW_TABLE_MISS_ACTION_DEF,
+	MLX5_FLOW_TABLE_MISS_ACTION_FWD,
+	MLX5_FLOW_TABLE_MISS_ACTION_SWITCH_DOMAIN,
+};
+
 struct mlx5_ifc_dest_format_struct_bits {
 	u8         destination_type[0x8];
 	u8         destination_id[0x18];
@@ -1299,7 +1359,9 @@ struct mlx5_ifc_fte_match_param_bits {
 
 	struct mlx5_ifc_fte_match_set_misc2_bits misc_parameters_2;
 
-	u8         reserved_at_800[0x800];
+	struct mlx5_ifc_fte_match_set_misc3_bits misc_parameters_3;
+
+	u8         reserved_at_a00[0x600];
 };
 
 enum {
@@ -2920,6 +2982,7 @@ enum {
 	MLX5_MKC_ACCESS_MODE_MTT   = 0x1,
 	MLX5_MKC_ACCESS_MODE_KLMS  = 0x2,
 	MLX5_MKC_ACCESS_MODE_KSM   = 0x3,
+	MLX5_MKC_ACCESS_MODE_SW_ICM = 0x4,
 	MLX5_MKC_ACCESS_MODE_MEMIC = 0x5,
 };
 
@@ -4807,6 +4870,7 @@ enum {
 	MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS  = 0x1,
 	MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_INNER_HEADERS    = 0x2,
 	MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_2 = 0x3,
+	MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_3 = 0x4,
 };
 
 struct mlx5_ifc_query_flow_group_out_bits {
@@ -6875,14 +6939,14 @@ struct mlx5_ifc_create_tis_in_bits {
 
 struct mlx5_ifc_create_tir_out_bits {
 	u8         status[0x8];
-	u8         reserved_at_8[0x18];
+	u8         icm_address_63_40[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_at_40[0x8];
+	u8         icm_address_39_32[0x8];
 	u8         tirn[0x18];
 
-	u8         reserved_at_60[0x20];
+	u8         icm_address_31_0[0x20];
 };
 
 struct mlx5_ifc_create_tir_in_bits {
@@ -9492,6 +9556,33 @@ struct mlx5_ifc_uctx_bits {
 	u8         reserved_at_20[0x160];
 };
 
+struct mlx5_ifc_sw_icm_bits {
+	u8         modify_field_select[0x40];
+
+	u8	   reserved_at_40[0x18];
+	u8         log_sw_icm_size[0x8];
+
+	u8         reserved_at_60[0x20];
+
+	u8         sw_icm_start_addr[0x40];
+
+	u8         reserved_at_c0[0x140];
+};
+
+struct mlx5_ifc_geneve_tlv_option_bits {
+	u8         modify_field_select[0x40];
+
+	u8         reserved_at_40[0x18];
+	u8         geneve_option_fte_index[0x8];
+
+	u8         option_class[0x10];
+	u8         option_type[0x8];
+	u8         reserved_at_78[0x3];
+	u8         option_data_length[0x5];
+
+	u8         reserved_at_80[0x180];
+};
+
 struct mlx5_ifc_create_umem_in_bits {
 	u8         opcode[0x10];
 	u8         uid[0x10];
@@ -9529,6 +9620,16 @@ struct mlx5_ifc_destroy_uctx_in_bits {
 	u8         reserved_at_60[0x20];
 };
 
+struct mlx5_ifc_create_sw_icm_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits   hdr;
+	struct mlx5_ifc_sw_icm_bits		      sw_icm;
+};
+
+struct mlx5_ifc_create_geneve_tlv_option_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits   hdr;
+	struct mlx5_ifc_geneve_tlv_option_bits        geneve_tlv_opt;
+};
+
 struct mlx5_ifc_mtrc_string_db_param_bits {
 	u8         string_db_base_address[0x20];
 

include/linux/mlx5/transobj.h

@@ -50,6 +50,9 @@ int mlx5_core_query_sq(struct mlx5_core_dev *dev, u32 sqn, u32 *out);
 int mlx5_core_query_sq_state(struct mlx5_core_dev *dev, u32 sqn, u8 *state);
 int mlx5_core_create_tir(struct mlx5_core_dev *dev, u32 *in, int inlen,
 			 u32 *tirn);
+int mlx5_core_create_tir_out(struct mlx5_core_dev *dev,
+			     u32 *in, int inlen,
+			     u32 *out, int outlen);
 int mlx5_core_modify_tir(struct mlx5_core_dev *dev, u32 tirn, u32 *in,
 			 int inlen);
 void mlx5_core_destroy_tir(struct mlx5_core_dev *dev, u32 tirn);