[dpdk-dev] [PATCH v5] net/mlx5: implement tunnel offload API

Gregory Etelson getelson at nvidia.com
Sun Oct 25 15:08:09 CET 2020


Tunnel Offload API provides hardware independent, unified model
to offload tunneled traffic. Key model elements are:
 - apply matches to both outer and inner packet headers
   during entire offload procedure;
 - restore outer header of partially offloaded packet;
 - model is implemented as a set of helper functions.

Implementation details:
* tunnel_offload PMD parameter must be set to 1 to enable the feature.
* application cannot use MARK and META flow actions whith tunnel.
* offload JUMP action is restricted to steering tunnel rule only.

Signed-off-by: Gregory Etelson <getelson at nvidia.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo at nvidia.com>
---
 doc/guides/nics/mlx5.rst         |   3 +
 drivers/net/mlx5/linux/mlx5_os.c |  18 +
 drivers/net/mlx5/mlx5.c          |   8 +-
 drivers/net/mlx5/mlx5.h          |   3 +
 drivers/net/mlx5/mlx5_defs.h     |   2 +
 drivers/net/mlx5/mlx5_flow.c     | 681 ++++++++++++++++++++++++++++++-
 drivers/net/mlx5/mlx5_flow.h     | 171 +++++++-
 drivers/net/mlx5/mlx5_flow_dv.c  | 254 ++++++++++--
 8 files changed, 1086 insertions(+), 54 deletions(-)

diff --git a/doc/guides/nics/mlx5.rst b/doc/guides/nics/mlx5.rst
index e4e607c9ea..66524f1262 100644
--- a/doc/guides/nics/mlx5.rst
+++ b/doc/guides/nics/mlx5.rst
@@ -788,6 +788,9 @@ Driver options
     24 bits. The actual supported width can be retrieved in runtime by
     series of rte_flow_validate() trials.
 
+  - 3, this engages tunnel offload mode. In E-Switch configuration, that
+    mode implicitly activates ``dv_xmeta_en=1``.
+
   +------+-----------+-----------+-------------+-------------+
   | Mode | ``MARK``  | ``META``  | ``META`` Tx | FDB/Through |
   +======+===========+===========+=============+=============+
diff --git a/drivers/net/mlx5/linux/mlx5_os.c b/drivers/net/mlx5/linux/mlx5_os.c
index 40f9446d43..ed3f020d82 100644
--- a/drivers/net/mlx5/linux/mlx5_os.c
+++ b/drivers/net/mlx5/linux/mlx5_os.c
@@ -291,6 +291,12 @@ mlx5_alloc_shared_dr(struct mlx5_priv *priv)
 		sh->esw_drop_action = mlx5_glue->dr_create_flow_action_drop();
 	}
 #endif
+	if (!sh->tunnel_hub)
+		err = mlx5_alloc_tunnel_hub(sh);
+	if (err) {
+		DRV_LOG(ERR, "mlx5_alloc_tunnel_hub failed err=%d", err);
+		goto error;
+	}
 	if (priv->config.reclaim_mode == MLX5_RCM_AGGR) {
 		mlx5_glue->dr_reclaim_domain_memory(sh->rx_domain, 1);
 		mlx5_glue->dr_reclaim_domain_memory(sh->tx_domain, 1);
@@ -335,6 +341,10 @@ mlx5_alloc_shared_dr(struct mlx5_priv *priv)
 		mlx5_hlist_destroy(sh->tag_table, NULL, NULL);
 		sh->tag_table = NULL;
 	}
+	if (sh->tunnel_hub) {
+		mlx5_release_tunnel_hub(sh, priv->dev_port);
+		sh->tunnel_hub = NULL;
+	}
 	mlx5_free_table_hash_list(priv);
 	return err;
 }
@@ -391,6 +401,10 @@ mlx5_os_free_shared_dr(struct mlx5_priv *priv)
 		mlx5_hlist_destroy(sh->tag_table, NULL, NULL);
 		sh->tag_table = NULL;
 	}
+	if (sh->tunnel_hub) {
+		mlx5_release_tunnel_hub(sh, priv->dev_port);
+		sh->tunnel_hub = NULL;
+	}
 	mlx5_free_table_hash_list(priv);
 }
 
@@ -733,6 +747,10 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 			strerror(rte_errno));
 		goto error;
 	}
+	if (config->dv_miss_info) {
+		if (switch_info->master || switch_info->representor)
+			config->dv_xmeta_en = MLX5_XMETA_MODE_META16;
+	}
 	mlx5_malloc_mem_select(config->sys_mem_en);
 	sh = mlx5_alloc_shared_dev_ctx(spawn, config);
 	if (!sh)
diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c
index 2484251b2f..6c422e8b4a 100644
--- a/drivers/net/mlx5/mlx5.c
+++ b/drivers/net/mlx5/mlx5.c
@@ -1619,13 +1619,17 @@ mlx5_args_check(const char *key, const char *val, void *opaque)
 	} else if (strcmp(MLX5_DV_XMETA_EN, key) == 0) {
 		if (tmp != MLX5_XMETA_MODE_LEGACY &&
 		    tmp != MLX5_XMETA_MODE_META16 &&
-		    tmp != MLX5_XMETA_MODE_META32) {
+		    tmp != MLX5_XMETA_MODE_META32 &&
+		    tmp != MLX5_XMETA_MODE_MISS_INFO) {
 			DRV_LOG(ERR, "invalid extensive "
 				     "metadata parameter");
 			rte_errno = EINVAL;
 			return -rte_errno;
 		}
-		config->dv_xmeta_en = tmp;
+		if (tmp != MLX5_XMETA_MODE_MISS_INFO)
+			config->dv_xmeta_en = tmp;
+		else
+			config->dv_miss_info = 1;
 	} else if (strcmp(MLX5_LACP_BY_USER, key) == 0) {
 		config->lacp_by_user = !!tmp;
 	} else if (strcmp(MLX5_MR_EXT_MEMSEG_EN, key) == 0) {
diff --git a/drivers/net/mlx5/mlx5.h b/drivers/net/mlx5/mlx5.h
index 658533de6f..bb954c41bb 100644
--- a/drivers/net/mlx5/mlx5.h
+++ b/drivers/net/mlx5/mlx5.h
@@ -208,6 +208,7 @@ struct mlx5_dev_config {
 	unsigned int rt_timestamp:1; /* realtime timestamp format. */
 	unsigned int sys_mem_en:1; /* The default memory allocator. */
 	unsigned int decap_en:1; /* Whether decap will be used or not. */
+	unsigned int dv_miss_info:1; /* restore packet after partial hw miss */
 	struct {
 		unsigned int enabled:1; /* Whether MPRQ is enabled. */
 		unsigned int stride_num_n; /* Number of strides. */
@@ -644,6 +645,8 @@ struct mlx5_dev_ctx_shared {
 	/* UAR same-page access control required in 32bit implementations. */
 #endif
 	struct mlx5_hlist *flow_tbls;
+	struct rte_hash *flow_tbl_map; /* app group-to-flow table map */
+	struct mlx5_flow_tunnel_hub *tunnel_hub;
 	/* Direct Rules tables for FDB, NIC TX+RX */
 	void *esw_drop_action; /* Pointer to DR E-Switch drop action. */
 	void *pop_vlan_action; /* Pointer to DR pop VLAN action. */
diff --git a/drivers/net/mlx5/mlx5_defs.h b/drivers/net/mlx5/mlx5_defs.h
index 22e41df1eb..42916ed7a7 100644
--- a/drivers/net/mlx5/mlx5_defs.h
+++ b/drivers/net/mlx5/mlx5_defs.h
@@ -165,6 +165,8 @@
 #define MLX5_XMETA_MODE_LEGACY 0
 #define MLX5_XMETA_MODE_META16 1
 #define MLX5_XMETA_MODE_META32 2
+/* Provide info on patrial hw miss. Implies MLX5_XMETA_MODE_META16 */
+#define MLX5_XMETA_MODE_MISS_INFO 3
 
 /* MLX5_TX_DB_NC supported values. */
 #define MLX5_TXDB_CACHED 0
diff --git a/drivers/net/mlx5/mlx5_flow.c b/drivers/net/mlx5/mlx5_flow.c
index 6077685430..949b9ced9b 100644
--- a/drivers/net/mlx5/mlx5_flow.c
+++ b/drivers/net/mlx5/mlx5_flow.c
@@ -19,6 +19,7 @@
 #include <rte_flow_driver.h>
 #include <rte_malloc.h>
 #include <rte_ip.h>
+#include <rte_hash.h>
 
 #include <mlx5_glue.h>
 #include <mlx5_devx_cmds.h>
@@ -32,6 +33,18 @@
 #include "mlx5_rxtx.h"
 #include "mlx5_common_os.h"
 
+static struct mlx5_flow_tunnel *
+mlx5_find_tunnel_id(struct rte_eth_dev *dev, uint32_t id);
+static void
+mlx5_flow_tunnel_free(struct rte_eth_dev *dev, struct mlx5_flow_tunnel *tunnel);
+static const struct mlx5_flow_tbl_data_entry  *
+tunnel_mark_decode(struct rte_eth_dev *dev, uint32_t mark);
+static int
+mlx5_get_flow_tunnel(struct rte_eth_dev *dev,
+		     const struct rte_flow_tunnel *app_tunnel,
+		     struct mlx5_flow_tunnel **tunnel);
+
+
 /** Device flow drivers. */
 extern const struct mlx5_flow_driver_ops mlx5_flow_verbs_drv_ops;
 
@@ -567,6 +580,162 @@ static int mlx5_shared_action_query
 				 const struct rte_flow_shared_action *action,
 				 void *data,
 				 struct rte_flow_error *error);
+static inline bool
+mlx5_flow_tunnel_validate(struct rte_eth_dev *dev,
+			  struct rte_flow_tunnel *tunnel,
+			  const char *err_msg)
+{
+	err_msg = NULL;
+	if (!is_tunnel_offload_active(dev)) {
+		err_msg = "tunnel offload was not activated";
+		goto out;
+	} else if (!tunnel) {
+		err_msg = "no application tunnel";
+		goto out;
+	}
+
+	switch (tunnel->type) {
+	default:
+		err_msg = "unsupported tunnel type";
+		goto out;
+	case RTE_FLOW_ITEM_TYPE_VXLAN:
+		break;
+	}
+
+out:
+	return !err_msg;
+}
+
+
+static int
+mlx5_flow_tunnel_decap_set(struct rte_eth_dev *dev,
+		    struct rte_flow_tunnel *app_tunnel,
+		    struct rte_flow_action **actions,
+		    uint32_t *num_of_actions,
+		    struct rte_flow_error *error)
+{
+	int ret;
+	struct mlx5_flow_tunnel *tunnel;
+	const char *err_msg = NULL;
+	bool verdict = mlx5_flow_tunnel_validate(dev, app_tunnel, err_msg);
+
+	if (!verdict)
+		return rte_flow_error_set(error, EINVAL,
+					  RTE_FLOW_ERROR_TYPE_ACTION_CONF, NULL,
+					  err_msg);
+	ret = mlx5_get_flow_tunnel(dev, app_tunnel, &tunnel);
+	if (ret < 0) {
+		return rte_flow_error_set(error, ret,
+					  RTE_FLOW_ERROR_TYPE_ACTION_CONF, NULL,
+					  "failed to initialize pmd tunnel");
+	}
+	*actions = &tunnel->action;
+	*num_of_actions = 1;
+	return 0;
+}
+
+static int
+mlx5_flow_tunnel_match(struct rte_eth_dev *dev,
+		       struct rte_flow_tunnel *app_tunnel,
+		       struct rte_flow_item **items,
+		       uint32_t *num_of_items,
+		       struct rte_flow_error *error)
+{
+	int ret;
+	struct mlx5_flow_tunnel *tunnel;
+	const char *err_msg = NULL;
+	bool verdict = mlx5_flow_tunnel_validate(dev, app_tunnel, err_msg);
+
+	if (!verdict)
+		return rte_flow_error_set(error, EINVAL,
+					  RTE_FLOW_ERROR_TYPE_HANDLE, NULL,
+					  err_msg);
+	ret = mlx5_get_flow_tunnel(dev, app_tunnel, &tunnel);
+	if (ret < 0) {
+		return rte_flow_error_set(error, ret,
+					  RTE_FLOW_ERROR_TYPE_HANDLE, NULL,
+					  "failed to initialize pmd tunnel");
+	}
+	*items = &tunnel->item;
+	*num_of_items = 1;
+	return 0;
+}
+
+static int
+mlx5_flow_item_release(struct rte_eth_dev *dev,
+		       struct rte_flow_item *pmd_items,
+		       uint32_t num_items, struct rte_flow_error *err)
+{
+	struct mlx5_flow_tunnel_hub *thub = mlx5_tunnel_hub(dev);
+	struct mlx5_flow_tunnel *tun;
+
+	LIST_FOREACH(tun, &thub->tunnels, chain) {
+		if (&tun->item == pmd_items)
+			break;
+	}
+	if (!tun || num_items != 1)
+		return rte_flow_error_set(err, EINVAL,
+					  RTE_FLOW_ERROR_TYPE_HANDLE, NULL,
+					  "invalid argument");
+	if (!__atomic_sub_fetch(&tun->refctn, 1, __ATOMIC_RELAXED))
+		mlx5_flow_tunnel_free(dev, tun);
+	return 0;
+}
+
+static int
+mlx5_flow_action_release(struct rte_eth_dev *dev,
+			 struct rte_flow_action *pmd_actions,
+			 uint32_t num_actions, struct rte_flow_error *err)
+{
+	struct mlx5_flow_tunnel_hub *thub = mlx5_tunnel_hub(dev);
+	struct mlx5_flow_tunnel *tun;
+
+	LIST_FOREACH(tun, &thub->tunnels, chain) {
+		if (&tun->action == pmd_actions)
+			break;
+	}
+	if (!tun || num_actions != 1)
+		return rte_flow_error_set(err, EINVAL,
+					  RTE_FLOW_ERROR_TYPE_HANDLE, NULL,
+					  "invalid argument");
+	if (!__atomic_sub_fetch(&tun->refctn, 1, __ATOMIC_RELAXED))
+		mlx5_flow_tunnel_free(dev, tun);
+
+	return 0;
+}
+
+static int
+mlx5_flow_tunnel_get_restore_info(struct rte_eth_dev *dev,
+				  struct rte_mbuf *m,
+				  struct rte_flow_restore_info *info,
+				  struct rte_flow_error *err)
+{
+	uint64_t ol_flags = m->ol_flags;
+	const struct mlx5_flow_tbl_data_entry *tble;
+	const uint64_t mask = PKT_RX_FDIR | PKT_RX_FDIR_ID;
+
+	if ((ol_flags & mask) != mask)
+		goto err;
+	tble = tunnel_mark_decode(dev, m->hash.fdir.hi);
+	if (!tble) {
+		DRV_LOG(DEBUG, "port %u invalid miss tunnel mark %#x",
+			dev->data->port_id, m->hash.fdir.hi);
+		goto err;
+	}
+	MLX5_ASSERT(tble->tunnel);
+	memcpy(&info->tunnel, &tble->tunnel->app_tunnel, sizeof(info->tunnel));
+	info->group_id = tble->group_id;
+	info->flags = RTE_FLOW_RESTORE_INFO_TUNNEL |
+		      RTE_FLOW_RESTORE_INFO_GROUP_ID |
+		      RTE_FLOW_RESTORE_INFO_ENCAPSULATED;
+
+	return 0;
+
+err:
+	return rte_flow_error_set(err, EINVAL,
+				  RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
+				  "failed to get restore info");
+}
 
 static const struct rte_flow_ops mlx5_flow_ops = {
 	.validate = mlx5_flow_validate,
@@ -581,6 +750,11 @@ static const struct rte_flow_ops mlx5_flow_ops = {
 	.shared_action_destroy = mlx5_shared_action_destroy,
 	.shared_action_update = mlx5_shared_action_update,
 	.shared_action_query = mlx5_shared_action_query,
+	.tunnel_decap_set = mlx5_flow_tunnel_decap_set,
+	.tunnel_match = mlx5_flow_tunnel_match,
+	.tunnel_action_decap_release = mlx5_flow_action_release,
+	.tunnel_item_release = mlx5_flow_item_release,
+	.get_restore_info = mlx5_flow_tunnel_get_restore_info,
 };
 
 /* Convert FDIR request to Generic flow. */
@@ -4065,6 +4239,142 @@ flow_hairpin_split(struct rte_eth_dev *dev,
 	return 0;
 }
 
+__extension__
+union tunnel_offload_mark {
+	uint32_t val;
+	struct {
+		uint32_t app_reserve:8;
+		uint32_t table_id:15;
+		uint32_t transfer:1;
+		uint32_t _unused_:8;
+	};
+};
+
+struct tunnel_default_miss_ctx {
+	uint16_t *queue;
+	__extension__
+	union {
+		struct rte_flow_action_rss action_rss;
+		struct rte_flow_action_queue miss_queue;
+		struct rte_flow_action_jump miss_jump;
+		uint8_t raw[0];
+	};
+};
+
+static int
+flow_tunnel_add_default_miss(struct rte_eth_dev *dev,
+			     struct rte_flow *flow,
+			     const struct rte_flow_attr *attr,
+			     const struct rte_flow_action *app_actions,
+			     uint32_t flow_idx,
+			     struct tunnel_default_miss_ctx *ctx,
+			     struct rte_flow_error *error)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct mlx5_flow *dev_flow;
+	struct rte_flow_attr miss_attr = *attr;
+	const struct mlx5_flow_tunnel *tunnel = app_actions[0].conf;
+	const struct rte_flow_item miss_items[2] = {
+		{
+			.type = RTE_FLOW_ITEM_TYPE_ETH,
+			.spec = NULL,
+			.last = NULL,
+			.mask = NULL
+		},
+		{
+			.type = RTE_FLOW_ITEM_TYPE_END,
+			.spec = NULL,
+			.last = NULL,
+			.mask = NULL
+		}
+	};
+	union tunnel_offload_mark mark_id;
+	struct rte_flow_action_mark miss_mark;
+	struct rte_flow_action miss_actions[3] = {
+		[0] = { .type = RTE_FLOW_ACTION_TYPE_MARK, .conf = &miss_mark },
+		[2] = { .type = RTE_FLOW_ACTION_TYPE_END,  .conf = NULL }
+	};
+	const struct rte_flow_action_jump *jump_data;
+	uint32_t i, flow_table = 0; /* prevent compilation warning */
+	struct flow_grp_info grp_info = {
+		.external = 1,
+		.transfer = attr->transfer,
+		.fdb_def_rule = !!priv->fdb_def_rule,
+		.std_tbl_fix = 0,
+	};
+	int ret;
+
+	if (!attr->transfer) {
+		uint32_t q_size;
+
+		miss_actions[1].type = RTE_FLOW_ACTION_TYPE_RSS;
+		q_size = priv->reta_idx_n * sizeof(ctx->queue[0]);
+		ctx->queue = mlx5_malloc(MLX5_MEM_SYS | MLX5_MEM_ZERO, q_size,
+					 0, SOCKET_ID_ANY);
+		if (!ctx->queue)
+			return rte_flow_error_set
+				(error, ENOMEM,
+				RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+				NULL, "invalid default miss RSS");
+		ctx->action_rss.func = RTE_ETH_HASH_FUNCTION_DEFAULT,
+		ctx->action_rss.level = 0,
+		ctx->action_rss.types = priv->rss_conf.rss_hf,
+		ctx->action_rss.key_len = priv->rss_conf.rss_key_len,
+		ctx->action_rss.queue_num = priv->reta_idx_n,
+		ctx->action_rss.key = priv->rss_conf.rss_key,
+		ctx->action_rss.queue = ctx->queue;
+		if (!priv->reta_idx_n || !priv->rxqs_n)
+			return rte_flow_error_set
+				(error, EINVAL,
+				RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+				NULL, "invalid port configuration");
+		if (!(dev->data->dev_conf.rxmode.mq_mode & ETH_MQ_RX_RSS_FLAG))
+			ctx->action_rss.types = 0;
+		for (i = 0; i != priv->reta_idx_n; ++i)
+			ctx->queue[i] = (*priv->reta_idx)[i];
+	} else {
+		miss_actions[1].type = RTE_FLOW_ACTION_TYPE_JUMP;
+		ctx->miss_jump.group = MLX5_TNL_MISS_FDB_JUMP_GRP;
+	}
+	miss_actions[1].conf = (typeof(miss_actions[1].conf))ctx->raw;
+	for (; app_actions->type != RTE_FLOW_ACTION_TYPE_JUMP; app_actions++);
+	jump_data = app_actions->conf;
+	miss_attr.priority = MLX5_TNL_MISS_RULE_PRIORITY;
+	miss_attr.group = jump_data->group;
+	ret = mlx5_flow_group_to_table(dev, tunnel, jump_data->group,
+				       &flow_table, grp_info, error);
+	if (ret)
+		return rte_flow_error_set(error, EINVAL,
+					  RTE_FLOW_ERROR_TYPE_ACTION_CONF,
+					  NULL, "invalid tunnel id");
+	mark_id.app_reserve = 0;
+	mark_id.table_id = tunnel_flow_tbl_to_id(flow_table);
+	mark_id.transfer = !!attr->transfer;
+	mark_id._unused_ = 0;
+	miss_mark.id = mark_id.val;
+	dev_flow = flow_drv_prepare(dev, flow, &miss_attr,
+				    miss_items, miss_actions, flow_idx, error);
+	if (!dev_flow)
+		return -rte_errno;
+	dev_flow->flow = flow;
+	dev_flow->external = true;
+	dev_flow->tunnel = tunnel;
+	/* Subflow object was created, we must include one in the list. */
+	SILIST_INSERT(&flow->dev_handles, dev_flow->handle_idx,
+		      dev_flow->handle, next);
+	DRV_LOG(DEBUG,
+		"port %u tunnel type=%d id=%u miss rule priority=%u group=%u",
+		dev->data->port_id, tunnel->app_tunnel.type,
+		tunnel->tunnel_id, miss_attr.priority, miss_attr.group);
+	ret = flow_drv_translate(dev, dev_flow, &miss_attr, miss_items,
+				  miss_actions, error);
+	if (!ret)
+		ret = flow_mreg_update_copy_table(dev, flow, miss_actions,
+						  error);
+
+	return ret;
+}
+
 /**
  * The last stage of splitting chain, just creates the subflow
  * without any modification.
@@ -5187,6 +5497,27 @@ flow_create_split_outer(struct rte_eth_dev *dev,
 	return ret;
 }
 
+static struct mlx5_flow_tunnel *
+flow_tunnel_from_rule(struct rte_eth_dev *dev,
+		      const struct rte_flow_attr *attr,
+		      const struct rte_flow_item items[],
+		      const struct rte_flow_action actions[])
+{
+	struct mlx5_flow_tunnel *tunnel;
+
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wcast-qual"
+	if (is_flow_tunnel_match_rule(dev, attr, items, actions))
+		tunnel = (struct mlx5_flow_tunnel *)items[0].spec;
+	else if (is_flow_tunnel_steer_rule(dev, attr, items, actions))
+		tunnel = (struct mlx5_flow_tunnel *)actions[0].conf;
+	else
+		tunnel = NULL;
+#pragma GCC diagnostic pop
+
+	return tunnel;
+}
+
 /**
  * Create a flow and add it to @p list.
  *
@@ -5253,6 +5584,8 @@ flow_list_create(struct rte_eth_dev *dev, uint32_t *list,
 	struct rte_flow_attr attr_factor = {0};
 	const struct rte_flow_action *actions;
 	struct rte_flow_action *translated_actions = NULL;
+	struct mlx5_flow_tunnel *tunnel;
+	struct tunnel_default_miss_ctx default_miss_ctx = { 0, };
 	int ret = flow_shared_actions_translate(original_actions,
 						shared_actions,
 						&shared_actions_n,
@@ -5264,8 +5597,6 @@ flow_list_create(struct rte_eth_dev *dev, uint32_t *list,
 	}
 	actions = translated_actions ? translated_actions : original_actions;
 	memcpy((void *)&attr_factor, (const void *)attr, sizeof(*attr));
-	if (external)
-		attr_factor.group *= MLX5_FLOW_TABLE_FACTOR;
 	p_actions_rx = actions;
 	hairpin_flow = flow_check_hairpin_split(dev, &attr_factor, actions);
 	ret = flow_drv_validate(dev, &attr_factor, items, p_actions_rx,
@@ -5340,6 +5671,19 @@ flow_list_create(struct rte_eth_dev *dev, uint32_t *list,
 					      error);
 		if (ret < 0)
 			goto error;
+		if (is_flow_tunnel_steer_rule(dev, attr,
+					      buf->entry[i].pattern,
+					      p_actions_rx)) {
+			ret = flow_tunnel_add_default_miss(dev, flow, attr,
+							   p_actions_rx,
+							   idx,
+							   &default_miss_ctx,
+							   error);
+			if (ret < 0) {
+				mlx5_free(default_miss_ctx.queue);
+				goto error;
+			}
+		}
 	}
 	/* Create the tx flow. */
 	if (hairpin_flow) {
@@ -5395,6 +5739,13 @@ flow_list_create(struct rte_eth_dev *dev, uint32_t *list,
 	priv->flow_idx = priv->flow_nested_idx;
 	if (priv->flow_nested_idx)
 		priv->flow_nested_idx = 0;
+	tunnel = flow_tunnel_from_rule(dev, attr, items, actions);
+	if (tunnel) {
+		flow->tunnel = 1;
+		flow->tunnel_id = tunnel->tunnel_id;
+		__atomic_add_fetch(&tunnel->refctn, 1, __ATOMIC_RELAXED);
+		mlx5_free(default_miss_ctx.queue);
+	}
 	return idx;
 error:
 	MLX5_ASSERT(flow);
@@ -5530,6 +5881,7 @@ mlx5_flow_create(struct rte_eth_dev *dev,
 				   "port not started");
 		return NULL;
 	}
+
 	return (void *)(uintptr_t)flow_list_create(dev, &priv->flows,
 				  attr, items, actions, true, error);
 }
@@ -5584,6 +5936,13 @@ flow_list_destroy(struct rte_eth_dev *dev, uint32_t *list,
 		}
 	}
 	mlx5_ipool_free(priv->sh->ipool[MLX5_IPOOL_RTE_FLOW], flow_idx);
+	if (flow->tunnel) {
+		struct mlx5_flow_tunnel *tunnel;
+		tunnel = mlx5_find_tunnel_id(dev, flow->tunnel_id);
+		RTE_VERIFY(tunnel);
+		if (!__atomic_sub_fetch(&tunnel->refctn, 1, __ATOMIC_RELAXED))
+			mlx5_flow_tunnel_free(dev, tunnel);
+	}
 }
 
 /**
@@ -7118,19 +7477,122 @@ mlx5_flow_async_pool_query_handle(struct mlx5_dev_ctx_shared *sh,
 	sh->cmng.pending_queries--;
 }
 
+static const struct mlx5_flow_tbl_data_entry  *
+tunnel_mark_decode(struct rte_eth_dev *dev, uint32_t mark)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	struct mlx5_dev_ctx_shared *sh = priv->sh;
+	struct mlx5_hlist_entry *he;
+	union tunnel_offload_mark mbits = { .val = mark };
+	union mlx5_flow_tbl_key table_key = {
+		{
+			.table_id = tunnel_id_to_flow_tbl(mbits.table_id),
+			.reserved = 0,
+			.domain = !!mbits.transfer,
+			.direction = 0,
+		}
+	};
+	he = mlx5_hlist_lookup(sh->flow_tbls, table_key.v64);
+	return he ?
+	       container_of(he, struct mlx5_flow_tbl_data_entry, entry) : NULL;
+}
+
+static uint32_t
+tunnel_flow_group_to_flow_table(struct rte_eth_dev *dev,
+				const struct mlx5_flow_tunnel *tunnel,
+				uint32_t group, uint32_t *table,
+				struct rte_flow_error *error)
+{
+	struct mlx5_hlist_entry *he;
+	struct tunnel_tbl_entry *tte;
+	union tunnel_tbl_key key = {
+		.tunnel_id = tunnel ? tunnel->tunnel_id : 0,
+		.group = group
+	};
+	struct mlx5_flow_tunnel_hub *thub = mlx5_tunnel_hub(dev);
+	struct mlx5_hlist *group_hash;
+
+	group_hash = tunnel ? tunnel->groups : thub->groups;
+	he = mlx5_hlist_lookup(group_hash, key.val);
+	if (!he) {
+		int ret;
+		tte = mlx5_malloc(MLX5_MEM_SYS | MLX5_MEM_ZERO,
+				  sizeof(*tte), 0,
+				  SOCKET_ID_ANY);
+		if (!tte)
+			goto err;
+		tte->hash.key = key.val;
+		ret = mlx5_flow_id_get(thub->table_ids, &tte->flow_table);
+		if (ret) {
+			mlx5_free(tte);
+			goto err;
+		}
+		tte->flow_table = tunnel_id_to_flow_tbl(tte->flow_table);
+		mlx5_hlist_insert(group_hash, &tte->hash);
+	} else {
+		tte = container_of(he, typeof(*tte), hash);
+	}
+	*table = tte->flow_table;
+	DRV_LOG(DEBUG, "port %u tunnel %u group=%#x table=%#x",
+		dev->data->port_id, key.tunnel_id, group, *table);
+	return 0;
+
+err:
+	return rte_flow_error_set(error, EINVAL, RTE_FLOW_ERROR_TYPE_ATTR_GROUP,
+				  NULL, "tunnel group index not supported");
+}
+
+static int
+flow_group_to_table(uint32_t port_id, uint32_t group, uint32_t *table,
+		    struct flow_grp_info grp_info, struct rte_flow_error *error)
+{
+	if (grp_info.transfer && grp_info.external && grp_info.fdb_def_rule) {
+		if (group == UINT32_MAX)
+			return rte_flow_error_set
+						(error, EINVAL,
+						 RTE_FLOW_ERROR_TYPE_ATTR_GROUP,
+						 NULL,
+						 "group index not supported");
+		*table = group + 1;
+	} else {
+		*table = group;
+	}
+	DRV_LOG(DEBUG, "port %u group=%#x table=%#x", port_id, group, *table);
+	return 0;
+}
+
 /**
  * Translate the rte_flow group index to HW table value.
  *
- * @param[in] attributes
- *   Pointer to flow attributes
- * @param[in] external
- *   Value is part of flow rule created by request external to PMD.
+ * If tunnel offload is disabled, all group ids coverted to flow table
+ * id using the standard method.
+ * If tunnel offload is enabled, group id can be converted using the
+ * standard or tunnel conversion method. Group conversion method
+ * selection depends on flags in `grp_info` parameter:
+ * - Internal (grp_info.external == 0) groups conversion uses the
+ *   standard method.
+ * - Group ids in JUMP action converted with the tunnel conversion.
+ * - Group id in rule attribute conversion depends on a rule type and
+ *   group id value:
+ *   ** non zero group attributes converted with the tunnel method
+ *   ** zero group attribute in non-tunnel rule is converted using the
+ *      standard method - there's only one root table
+ *   ** zero group attribute in steer tunnel rule is converted with the
+ *      standard method - single root table
+ *   ** zero group attribute in match tunnel rule is a special OvS
+ *      case: that value is used for portability reasons. That group
+ *      id is converted with the tunnel conversion method.
+ *
+ * @param[in] dev
+ *   Port device
+ * @param[in] tunnel
+ *   PMD tunnel offload object
  * @param[in] group
  *   rte_flow group index value.
- * @param[out] fdb_def_rule
- *   Whether fdb jump to table 1 is configured.
  * @param[out] table
  *   HW table value.
+ * @param[in] grp_info
+ *   flags used for conversion
  * @param[out] error
  *   Pointer to error structure.
  *
@@ -7138,22 +7600,36 @@ mlx5_flow_async_pool_query_handle(struct mlx5_dev_ctx_shared *sh,
  *   0 on success, a negative errno value otherwise and rte_errno is set.
  */
 int
-mlx5_flow_group_to_table(const struct rte_flow_attr *attributes, bool external,
-			 uint32_t group, bool fdb_def_rule, uint32_t *table,
+mlx5_flow_group_to_table(struct rte_eth_dev *dev,
+			 const struct mlx5_flow_tunnel *tunnel,
+			 uint32_t group, uint32_t *table,
+			 struct flow_grp_info grp_info,
 			 struct rte_flow_error *error)
 {
-	if (attributes->transfer && external && fdb_def_rule) {
-		if (group == UINT32_MAX)
-			return rte_flow_error_set
-						(error, EINVAL,
-						 RTE_FLOW_ERROR_TYPE_ATTR_GROUP,
-						 NULL,
-						 "group index not supported");
-		*table = group + 1;
+	int ret;
+	bool standard_translation;
+
+	if (grp_info.external && group < MLX5_MAX_TABLES_EXTERNAL)
+		group *= MLX5_FLOW_TABLE_FACTOR;
+	if (is_tunnel_offload_active(dev)) {
+		standard_translation = !grp_info.external ||
+					grp_info.std_tbl_fix;
 	} else {
-		*table = group;
+		standard_translation = true;
 	}
-	return 0;
+	DRV_LOG(DEBUG,
+		"port %u group=%#x transfer=%d external=%d fdb_def_rule=%d translate=%s",
+		dev->data->port_id, group, grp_info.transfer,
+		grp_info.external, grp_info.fdb_def_rule,
+		standard_translation ? "STANDARD" : "TUNNEL");
+	if (standard_translation)
+		ret = flow_group_to_table(dev->data->port_id, group, table,
+					  grp_info, error);
+	else
+		ret = tunnel_flow_group_to_flow_table(dev, tunnel, group,
+						      table, error);
+
+	return ret;
 }
 
 /**
@@ -7524,3 +8000,168 @@ mlx5_shared_action_flush(struct rte_eth_dev *dev)
 	}
 	return ret;
 }
+
+static void
+mlx5_flow_tunnel_free(struct rte_eth_dev *dev,
+		      struct mlx5_flow_tunnel *tunnel)
+{
+	struct mlx5_flow_tunnel_hub *thub = mlx5_tunnel_hub(dev);
+	struct mlx5_flow_id_pool *id_pool = thub->tunnel_ids;
+
+	DRV_LOG(DEBUG, "port %u release pmd tunnel id=0x%x",
+		dev->data->port_id, tunnel->tunnel_id);
+	RTE_VERIFY(!__atomic_load_n(&tunnel->refctn, __ATOMIC_RELAXED));
+	LIST_REMOVE(tunnel, chain);
+	mlx5_flow_id_release(id_pool, tunnel->tunnel_id);
+	mlx5_hlist_destroy(tunnel->groups, NULL, NULL);
+	mlx5_free(tunnel);
+}
+
+static struct mlx5_flow_tunnel *
+mlx5_find_tunnel_id(struct rte_eth_dev *dev, uint32_t id)
+{
+	struct mlx5_flow_tunnel_hub *thub = mlx5_tunnel_hub(dev);
+	struct mlx5_flow_tunnel *tun;
+
+	LIST_FOREACH(tun, &thub->tunnels, chain) {
+		if (tun->tunnel_id == id)
+			break;
+	}
+
+	return tun;
+}
+
+static struct mlx5_flow_tunnel *
+mlx5_flow_tunnel_allocate(struct rte_eth_dev *dev,
+			  const struct rte_flow_tunnel *app_tunnel)
+{
+	int ret;
+	struct mlx5_flow_tunnel *tunnel;
+	struct mlx5_flow_tunnel_hub *thub = mlx5_tunnel_hub(dev);
+	struct mlx5_flow_id_pool *id_pool = thub->tunnel_ids;
+	uint32_t id;
+
+	ret = mlx5_flow_id_get(id_pool, &id);
+	if (ret)
+		return NULL;
+	/**
+	 * mlx5 flow tunnel is an auxlilary data structure
+	 * It's not part of IO. No need to allocate it from
+	 * huge pages pools dedicated for IO
+	 */
+	tunnel = mlx5_malloc(MLX5_MEM_SYS | MLX5_MEM_ZERO, sizeof(*tunnel),
+			     0, SOCKET_ID_ANY);
+	if (!tunnel) {
+		mlx5_flow_id_pool_release(id_pool);
+		return NULL;
+	}
+	tunnel->groups = mlx5_hlist_create("tunnel groups", 1024);
+	if (!tunnel->groups) {
+		mlx5_flow_id_pool_release(id_pool);
+		mlx5_free(tunnel);
+		return NULL;
+	}
+	/* initiate new PMD tunnel */
+	memcpy(&tunnel->app_tunnel, app_tunnel, sizeof(*app_tunnel));
+	tunnel->tunnel_id = id;
+	tunnel->action.type = (typeof(tunnel->action.type))
+			      MLX5_RTE_FLOW_ACTION_TYPE_TUNNEL_SET;
+	tunnel->action.conf = tunnel;
+	tunnel->item.type = (typeof(tunnel->item.type))
+			    MLX5_RTE_FLOW_ITEM_TYPE_TUNNEL;
+	tunnel->item.spec = tunnel;
+	tunnel->item.last = NULL;
+	tunnel->item.mask = NULL;
+
+	DRV_LOG(DEBUG, "port %u new pmd tunnel id=0x%x",
+		dev->data->port_id, tunnel->tunnel_id);
+
+	return tunnel;
+}
+
+static int
+mlx5_get_flow_tunnel(struct rte_eth_dev *dev,
+		     const struct rte_flow_tunnel *app_tunnel,
+		     struct mlx5_flow_tunnel **tunnel)
+{
+	int ret;
+	struct mlx5_flow_tunnel_hub *thub = mlx5_tunnel_hub(dev);
+	struct mlx5_flow_tunnel *tun;
+
+	LIST_FOREACH(tun, &thub->tunnels, chain) {
+		if (!memcmp(app_tunnel, &tun->app_tunnel,
+			    sizeof(*app_tunnel))) {
+			*tunnel = tun;
+			ret = 0;
+			break;
+		}
+	}
+	if (!tun) {
+		tun = mlx5_flow_tunnel_allocate(dev, app_tunnel);
+		if (tun) {
+			LIST_INSERT_HEAD(&thub->tunnels, tun, chain);
+			*tunnel = tun;
+		} else {
+			ret = -ENOMEM;
+		}
+	}
+	if (tun)
+		__atomic_add_fetch(&tun->refctn, 1, __ATOMIC_RELAXED);
+
+	return ret;
+}
+
+void mlx5_release_tunnel_hub(struct mlx5_dev_ctx_shared *sh, uint16_t port_id)
+{
+	struct mlx5_flow_tunnel_hub *thub = sh->tunnel_hub;
+
+	if (!thub)
+		return;
+	if (!LIST_EMPTY(&thub->tunnels))
+		DRV_LOG(WARNING, "port %u tunnels present\n", port_id);
+	mlx5_flow_id_pool_release(thub->tunnel_ids);
+	mlx5_flow_id_pool_release(thub->table_ids);
+	mlx5_hlist_destroy(thub->groups, NULL, NULL);
+	mlx5_free(thub);
+}
+
+int mlx5_alloc_tunnel_hub(struct mlx5_dev_ctx_shared *sh)
+{
+	int err;
+	struct mlx5_flow_tunnel_hub *thub;
+
+	thub = mlx5_malloc(MLX5_MEM_SYS | MLX5_MEM_ZERO, sizeof(*thub),
+			   0, SOCKET_ID_ANY);
+	if (!thub)
+		return -ENOMEM;
+	LIST_INIT(&thub->tunnels);
+	thub->tunnel_ids = mlx5_flow_id_pool_alloc(MLX5_MAX_TUNNELS);
+	if (!thub->tunnel_ids) {
+		err = -rte_errno;
+		goto err;
+	}
+	thub->table_ids = mlx5_flow_id_pool_alloc(MLX5_MAX_TABLES);
+	if (!thub->table_ids) {
+		err = -rte_errno;
+		goto err;
+	}
+	thub->groups = mlx5_hlist_create("flow groups", MLX5_MAX_TABLES);
+	if (!thub->groups) {
+		err = -rte_errno;
+		goto err;
+	}
+	sh->tunnel_hub = thub;
+
+	return 0;
+
+err:
+	if (thub->groups)
+		mlx5_hlist_destroy(thub->groups, NULL, NULL);
+	if (thub->table_ids)
+		mlx5_flow_id_pool_release(thub->table_ids);
+	if (thub->tunnel_ids)
+		mlx5_flow_id_pool_release(thub->tunnel_ids);
+	if (thub)
+		mlx5_free(thub);
+	return err;
+}
diff --git a/drivers/net/mlx5/mlx5_flow.h b/drivers/net/mlx5/mlx5_flow.h
index 7faab43fe6..20beb96193 100644
--- a/drivers/net/mlx5/mlx5_flow.h
+++ b/drivers/net/mlx5/mlx5_flow.h
@@ -26,6 +26,7 @@ enum mlx5_rte_flow_item_type {
 	MLX5_RTE_FLOW_ITEM_TYPE_TAG,
 	MLX5_RTE_FLOW_ITEM_TYPE_TX_QUEUE,
 	MLX5_RTE_FLOW_ITEM_TYPE_VLAN,
+	MLX5_RTE_FLOW_ITEM_TYPE_TUNNEL,
 };
 
 /* Private (internal) rte flow actions. */
@@ -36,6 +37,7 @@ enum mlx5_rte_flow_action_type {
 	MLX5_RTE_FLOW_ACTION_TYPE_COPY_MREG,
 	MLX5_RTE_FLOW_ACTION_TYPE_DEFAULT_MISS,
 	MLX5_RTE_FLOW_ACTION_TYPE_SHARED_RSS,
+	MLX5_RTE_FLOW_ACTION_TYPE_TUNNEL_SET,
 };
 
 /* Matches on selected register. */
@@ -74,7 +76,6 @@ enum mlx5_feature_name {
 	MLX5_MTR_SFX,
 };
 
-/* Pattern outer Layer bits. */
 #define MLX5_FLOW_LAYER_OUTER_L2 (1u << 0)
 #define MLX5_FLOW_LAYER_OUTER_L3_IPV4 (1u << 1)
 #define MLX5_FLOW_LAYER_OUTER_L3_IPV6 (1u << 2)
@@ -202,6 +203,8 @@ enum mlx5_feature_name {
 #define MLX5_FLOW_ACTION_AGE (1ull << 34)
 #define MLX5_FLOW_ACTION_DEFAULT_MISS (1ull << 35)
 #define MLX5_FLOW_ACTION_SAMPLE (1ull << 36)
+#define MLX5_FLOW_ACTION_TUNNEL_SET (1ull << 37)
+#define MLX5_FLOW_ACTION_TUNNEL_MATCH (1ull << 38)
 
 #define MLX5_FLOW_FATE_ACTIONS \
 	(MLX5_FLOW_ACTION_DROP | MLX5_FLOW_ACTION_QUEUE | \
@@ -531,6 +534,10 @@ struct mlx5_flow_tbl_data_entry {
 	struct mlx5_flow_dv_jump_tbl_resource jump;
 	/**< jump resource, at most one for each table created. */
 	uint32_t idx; /**< index for the indexed mempool. */
+	/**< tunnel offload */
+	const struct mlx5_flow_tunnel *tunnel;
+	uint32_t group_id;
+	bool external;
 };
 
 /* Sub rdma-core actions list. */
@@ -769,6 +776,7 @@ struct mlx5_flow {
 	};
 	struct mlx5_flow_handle *handle;
 	uint32_t handle_idx; /* Index of the mlx5 flow handle memory. */
+	const struct mlx5_flow_tunnel *tunnel;
 };
 
 /* Flow meter state. */
@@ -914,6 +922,112 @@ struct mlx5_fdir_flow {
 
 #define HAIRPIN_FLOW_ID_BITS 28
 
+#define MLX5_MAX_TUNNELS 256
+#define MLX5_TNL_MISS_RULE_PRIORITY 3
+#define MLX5_TNL_MISS_FDB_JUMP_GRP  0x1234faac
+
+/*
+ * When tunnel offload is active, all JUMP group ids are converted
+ * using the same method. That conversion is applied both to tunnel and
+ * regular rule types.
+ * Group ids used in tunnel rules are relative to it's tunnel (!).
+ * Application can create number of steer rules, using the same
+ * tunnel, with different group id in each rule.
+ * Each tunnel stores its groups internally in PMD tunnel object.
+ * Groups used in regular rules do not belong to any tunnel and are stored
+ * in tunnel hub.
+ */
+
+struct mlx5_flow_tunnel {
+	LIST_ENTRY(mlx5_flow_tunnel) chain;
+	struct rte_flow_tunnel app_tunnel;	/** app tunnel copy */
+	uint32_t tunnel_id;			/** unique tunnel ID */
+	uint32_t refctn;
+	struct rte_flow_action action;
+	struct rte_flow_item item;
+	struct mlx5_hlist *groups;		/** tunnel groups */
+};
+
+/** PMD tunnel related context */
+struct mlx5_flow_tunnel_hub {
+	LIST_HEAD(, mlx5_flow_tunnel) tunnels;
+	struct mlx5_flow_id_pool *tunnel_ids;
+	struct mlx5_flow_id_pool *table_ids;
+	struct mlx5_hlist *groups;		/** non tunnel groups */
+};
+
+/* convert jump group to flow table ID in tunnel rules */
+struct tunnel_tbl_entry {
+	struct mlx5_hlist_entry hash;
+	uint32_t flow_table;
+};
+
+static inline uint32_t
+tunnel_id_to_flow_tbl(uint32_t id)
+{
+	return id | (1u << 16);
+}
+
+static inline uint32_t
+tunnel_flow_tbl_to_id(uint32_t flow_tbl)
+{
+	return flow_tbl & ~(1u << 16);
+}
+
+union tunnel_tbl_key {
+	uint64_t val;
+	struct {
+		uint32_t tunnel_id;
+		uint32_t group;
+	};
+};
+
+static inline struct mlx5_flow_tunnel_hub *
+mlx5_tunnel_hub(struct rte_eth_dev *dev)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	return priv->sh->tunnel_hub;
+}
+
+static inline bool
+is_tunnel_offload_active(struct rte_eth_dev *dev)
+{
+	struct mlx5_priv *priv = dev->data->dev_private;
+	return !!priv->config.dv_miss_info;
+}
+
+static inline bool
+is_flow_tunnel_match_rule(__rte_unused struct rte_eth_dev *dev,
+			  __rte_unused const struct rte_flow_attr *attr,
+			  __rte_unused const struct rte_flow_item items[],
+			  __rte_unused const struct rte_flow_action actions[])
+{
+	return (items[0].type == (typeof(items[0].type))
+				 MLX5_RTE_FLOW_ITEM_TYPE_TUNNEL);
+}
+
+static inline bool
+is_flow_tunnel_steer_rule(__rte_unused struct rte_eth_dev *dev,
+			  __rte_unused const struct rte_flow_attr *attr,
+			  __rte_unused const struct rte_flow_item items[],
+			  __rte_unused const struct rte_flow_action actions[])
+{
+	return (actions[0].type == (typeof(actions[0].type))
+				   MLX5_RTE_FLOW_ACTION_TYPE_TUNNEL_SET);
+}
+
+static inline const struct mlx5_flow_tunnel *
+flow_actions_to_tunnel(const struct rte_flow_action actions[])
+{
+	return actions[0].conf;
+}
+
+static inline const struct mlx5_flow_tunnel *
+flow_items_to_tunnel(const struct rte_flow_item items[])
+{
+	return items[0].spec;
+}
+
 /* Flow structure. */
 struct rte_flow {
 	ILIST_ENTRY(uint32_t)next; /**< Index to the next flow structure. */
@@ -922,12 +1036,14 @@ struct rte_flow {
 	/**< Device flow handles that are part of the flow. */
 	uint32_t drv_type:2; /**< Driver type. */
 	uint32_t fdir:1; /**< Identifier of associated FDIR if any. */
+	uint32_t tunnel:1;
 	uint32_t hairpin_flow_id:HAIRPIN_FLOW_ID_BITS;
 	/**< The flow id used for hairpin. */
 	uint32_t copy_applied:1; /**< The MARK copy Flow os applied. */
 	uint32_t rix_mreg_copy;
 	/**< Index to metadata register copy table resource. */
 	uint32_t counter; /**< Holds flow counter. */
+	uint32_t tunnel_id;  /**< Tunnel id */
 	uint16_t meter; /**< Holds flow meter id. */
 } __rte_packed;
 
@@ -1089,9 +1205,54 @@ void mlx5_flow_id_pool_release(struct mlx5_flow_id_pool *pool);
 uint32_t mlx5_flow_id_get(struct mlx5_flow_id_pool *pool, uint32_t *id);
 uint32_t mlx5_flow_id_release(struct mlx5_flow_id_pool *pool,
 			      uint32_t id);
-int mlx5_flow_group_to_table(const struct rte_flow_attr *attributes,
-			     bool external, uint32_t group, bool fdb_def_rule,
-			     uint32_t *table, struct rte_flow_error *error);
+__extension__
+struct flow_grp_info {
+	uint64_t external:1;
+	uint64_t transfer:1;
+	uint64_t fdb_def_rule:1;
+	/* force standard group translation */
+	uint64_t std_tbl_fix:1;
+};
+
+static inline bool
+tunnel_use_standard_attr_group_translate
+		    (struct rte_eth_dev *dev,
+		     const struct mlx5_flow_tunnel *tunnel,
+		     const struct rte_flow_attr *attr,
+		     const struct rte_flow_item items[],
+		     const struct rte_flow_action actions[])
+{
+	bool verdict;
+
+	if (!is_tunnel_offload_active(dev))
+		/* no tunnel offload API */
+		verdict = true;
+	else if (tunnel) {
+		/*
+		 * OvS will use jump to group 0 in tunnel steer rule.
+		 * If tunnel steer rule starts from group 0 (attr.group == 0)
+		 * that 0 group must be traslated with standard method.
+		 * attr.group == 0 in tunnel match rule translated with tunnel
+		 * method
+		 */
+		verdict = !attr->group &&
+			  is_flow_tunnel_steer_rule(dev, attr, items, actions);
+	} else {
+		/*
+		 * non-tunnel group translation uses standard method for
+		 * root group only: attr.group == 0
+		 */
+		verdict = !attr->group;
+	}
+
+	return verdict;
+}
+
+int mlx5_flow_group_to_table(struct rte_eth_dev *dev,
+			     const struct mlx5_flow_tunnel *tunnel,
+			     uint32_t group, uint32_t *table,
+			     struct flow_grp_info flags,
+				 struct rte_flow_error *error);
 uint64_t mlx5_flow_hashfields_adjust(struct mlx5_flow_rss_desc *rss_desc,
 				     int tunnel, uint64_t layer_types,
 				     uint64_t hash_fields);
@@ -1231,4 +1392,6 @@ int mlx5_flow_meter_flush(struct rte_eth_dev *dev,
 int mlx5_flow_dv_discover_counter_offset_support(struct rte_eth_dev *dev);
 struct rte_flow_shared_action *mlx5_flow_get_shared_rss(struct rte_flow *flow);
 int mlx5_shared_action_flush(struct rte_eth_dev *dev);
+void mlx5_release_tunnel_hub(struct mlx5_dev_ctx_shared *sh, uint16_t port_id);
+int mlx5_alloc_tunnel_hub(struct mlx5_dev_ctx_shared *sh);
 #endif /* RTE_PMD_MLX5_FLOW_H_ */
diff --git a/drivers/net/mlx5/mlx5_flow_dv.c b/drivers/net/mlx5/mlx5_flow_dv.c
index 66d81e9598..504d842c09 100644
--- a/drivers/net/mlx5/mlx5_flow_dv.c
+++ b/drivers/net/mlx5/mlx5_flow_dv.c
@@ -3947,14 +3947,21 @@ flow_dv_validate_action_modify_ttl(const uint64_t action_flags,
  *   0 on success, a negative errno value otherwise and rte_errno is set.
  */
 static int
-flow_dv_validate_action_jump(const struct rte_flow_action *action,
+flow_dv_validate_action_jump(struct rte_eth_dev *dev,
+			     const struct mlx5_flow_tunnel *tunnel,
+			     const struct rte_flow_action *action,
 			     uint64_t action_flags,
 			     const struct rte_flow_attr *attributes,
 			     bool external, struct rte_flow_error *error)
 {
 	uint32_t target_group, table;
 	int ret = 0;
-
+	struct flow_grp_info grp_info = {
+		.external = !!external,
+		.transfer = !!attributes->transfer,
+		.fdb_def_rule = 1,
+		.std_tbl_fix = 0
+	};
 	if (action_flags & (MLX5_FLOW_FATE_ACTIONS |
 			    MLX5_FLOW_FATE_ESWITCH_ACTIONS))
 		return rte_flow_error_set(error, EINVAL,
@@ -3977,11 +3984,13 @@ flow_dv_validate_action_jump(const struct rte_flow_action *action,
 					  NULL, "action configuration not set");
 	target_group =
 		((const struct rte_flow_action_jump *)action->conf)->group;
-	ret = mlx5_flow_group_to_table(attributes, external, target_group,
-				       true, &table, error);
+	ret = mlx5_flow_group_to_table(dev, tunnel, target_group, &table,
+				       grp_info, error);
 	if (ret)
 		return ret;
-	if (attributes->group == target_group)
+	if (attributes->group == target_group &&
+	    !(action_flags & (MLX5_FLOW_ACTION_TUNNEL_SET |
+			      MLX5_FLOW_ACTION_TUNNEL_MATCH)))
 		return rte_flow_error_set(error, EINVAL,
 					  RTE_FLOW_ERROR_TYPE_ACTION, NULL,
 					  "target group must be other than"
@@ -5160,8 +5169,9 @@ flow_dv_counter_release(struct rte_eth_dev *dev, uint32_t counter)
  */
 static int
 flow_dv_validate_attributes(struct rte_eth_dev *dev,
+			    const struct mlx5_flow_tunnel *tunnel,
 			    const struct rte_flow_attr *attributes,
-			    bool external __rte_unused,
+			    struct flow_grp_info grp_info,
 			    struct rte_flow_error *error)
 {
 	struct mlx5_priv *priv = dev->data->dev_private;
@@ -5169,6 +5179,8 @@ flow_dv_validate_attributes(struct rte_eth_dev *dev,
 	int ret = 0;
 
 #ifndef HAVE_MLX5DV_DR
+	RTE_SET_USED(tunnel);
+	RTE_SET_USED(grp_info);
 	if (attributes->group)
 		return rte_flow_error_set(error, ENOTSUP,
 					  RTE_FLOW_ERROR_TYPE_ATTR_GROUP,
@@ -5177,9 +5189,8 @@ flow_dv_validate_attributes(struct rte_eth_dev *dev,
 #else
 	uint32_t table = 0;
 
-	ret = mlx5_flow_group_to_table(attributes, external,
-				       attributes->group, !!priv->fdb_def_rule,
-				       &table, error);
+	ret = mlx5_flow_group_to_table(dev, tunnel, attributes->group, &table,
+				       grp_info, error);
 	if (ret)
 		return ret;
 	if (!table)
@@ -5293,10 +5304,28 @@ flow_dv_validate(struct rte_eth_dev *dev, const struct rte_flow_attr *attr,
 	const struct rte_flow_item_vlan *vlan_m = NULL;
 	int16_t rw_act_num = 0;
 	uint64_t is_root;
+	const struct mlx5_flow_tunnel *tunnel;
+	struct flow_grp_info grp_info = {
+		.external = !!external,
+		.transfer = !!attr->transfer,
+		.fdb_def_rule = !!priv->fdb_def_rule,
+	};
 
 	if (items == NULL)
 		return -1;
-	ret = flow_dv_validate_attributes(dev, attr, external, error);
+	if (is_flow_tunnel_match_rule(dev, attr, items, actions)) {
+		tunnel = flow_items_to_tunnel(items);
+		action_flags |= MLX5_FLOW_ACTION_TUNNEL_MATCH |
+				MLX5_FLOW_ACTION_DECAP;
+	} else if (is_flow_tunnel_steer_rule(dev, attr, items, actions)) {
+		tunnel = flow_actions_to_tunnel(actions);
+		action_flags |= MLX5_FLOW_ACTION_TUNNEL_SET;
+	} else {
+		tunnel = NULL;
+	}
+	grp_info.std_tbl_fix = tunnel_use_standard_attr_group_translate
+				(dev, tunnel, attr, items, actions);
+	ret = flow_dv_validate_attributes(dev, tunnel, attr, grp_info, error);
 	if (ret < 0)
 		return ret;
 	is_root = (uint64_t)ret;
@@ -5309,6 +5338,15 @@ flow_dv_validate(struct rte_eth_dev *dev, const struct rte_flow_attr *attr,
 						  RTE_FLOW_ERROR_TYPE_ITEM,
 						  NULL, "item not supported");
 		switch (type) {
+		case MLX5_RTE_FLOW_ITEM_TYPE_TUNNEL:
+			if (items[0].type != (typeof(items[0].type))
+						MLX5_RTE_FLOW_ITEM_TYPE_TUNNEL)
+				return rte_flow_error_set
+						(error, EINVAL,
+						RTE_FLOW_ERROR_TYPE_ITEM,
+						NULL, "MLX5 private items "
+						"must be the first");
+			break;
 		case RTE_FLOW_ITEM_TYPE_VOID:
 			break;
 		case RTE_FLOW_ITEM_TYPE_PORT_ID:
@@ -5894,7 +5932,7 @@ flow_dv_validate(struct rte_eth_dev *dev, const struct rte_flow_attr *attr,
 			rw_act_num += MLX5_ACT_NUM_MDF_TTL;
 			break;
 		case RTE_FLOW_ACTION_TYPE_JUMP:
-			ret = flow_dv_validate_action_jump(actions,
+			ret = flow_dv_validate_action_jump(dev, tunnel, actions,
 							   action_flags,
 							   attr, external,
 							   error);
@@ -6003,6 +6041,17 @@ flow_dv_validate(struct rte_eth_dev *dev, const struct rte_flow_attr *attr,
 			action_flags |= MLX5_FLOW_ACTION_SAMPLE;
 			++actions_n;
 			break;
+		case MLX5_RTE_FLOW_ACTION_TYPE_TUNNEL_SET:
+			if (actions[0].type != (typeof(actions[0].type))
+				MLX5_RTE_FLOW_ACTION_TYPE_TUNNEL_SET)
+				return rte_flow_error_set
+						(error, EINVAL,
+						RTE_FLOW_ERROR_TYPE_ACTION,
+						NULL, "MLX5 private action "
+						"must be the first");
+
+			action_flags |= MLX5_FLOW_ACTION_TUNNEL_SET;
+			break;
 		default:
 			return rte_flow_error_set(error, ENOTSUP,
 						  RTE_FLOW_ERROR_TYPE_ACTION,
@@ -6010,6 +6059,54 @@ flow_dv_validate(struct rte_eth_dev *dev, const struct rte_flow_attr *attr,
 						  "action not supported");
 		}
 	}
+	/*
+	 * Validate actions in flow rules
+	 * - Explicit decap action is prohibited by the tunnel offload API.
+	 * - Drop action in tunnel steer rule is prohibited by the API.
+	 * - Application cannot use MARK action because it's value can mask
+	 *   tunnel default miss nitification.
+	 * - JUMP in tunnel match rule has no support in current PMD
+	 *   implementation.
+	 * - TAG & META are reserved for future uses.
+	 */
+	if (action_flags & MLX5_FLOW_ACTION_TUNNEL_SET) {
+		uint64_t bad_actions_mask = MLX5_FLOW_ACTION_DECAP    |
+					    MLX5_FLOW_ACTION_MARK     |
+					    MLX5_FLOW_ACTION_SET_TAG  |
+					    MLX5_FLOW_ACTION_SET_META |
+					    MLX5_FLOW_ACTION_DROP;
+
+		if (action_flags & bad_actions_mask)
+			return rte_flow_error_set
+					(error, EINVAL,
+					RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+					"Invalid RTE action in tunnel "
+					"set decap rule");
+		if (!(action_flags & MLX5_FLOW_ACTION_JUMP))
+			return rte_flow_error_set
+					(error, EINVAL,
+					RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+					"tunnel set decap rule must terminate "
+					"with JUMP");
+		if (!attr->ingress)
+			return rte_flow_error_set
+					(error, EINVAL,
+					RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+					"tunnel flows for ingress traffic only");
+	}
+	if (action_flags & MLX5_FLOW_ACTION_TUNNEL_MATCH) {
+		uint64_t bad_actions_mask = MLX5_FLOW_ACTION_JUMP    |
+					    MLX5_FLOW_ACTION_MARK    |
+					    MLX5_FLOW_ACTION_SET_TAG |
+					    MLX5_FLOW_ACTION_SET_META;
+
+		if (action_flags & bad_actions_mask)
+			return rte_flow_error_set
+					(error, EINVAL,
+					RTE_FLOW_ERROR_TYPE_ACTION, NULL,
+					"Invalid RTE action in tunnel "
+					"set match rule");
+	}
 	/*
 	 * Validate the drop action mutual exclusion with other actions.
 	 * Drop action is mutually-exclusive with any other action, except for
@@ -7876,6 +7973,9 @@ static struct mlx5_flow_tbl_resource *
 flow_dv_tbl_resource_get(struct rte_eth_dev *dev,
 			 uint32_t table_id, uint8_t egress,
 			 uint8_t transfer,
+			 bool external,
+			 const struct mlx5_flow_tunnel *tunnel,
+			 uint32_t group_id,
 			 struct rte_flow_error *error)
 {
 	struct mlx5_priv *priv = dev->data->dev_private;
@@ -7912,6 +8012,9 @@ flow_dv_tbl_resource_get(struct rte_eth_dev *dev,
 		return NULL;
 	}
 	tbl_data->idx = idx;
+	tbl_data->tunnel = tunnel;
+	tbl_data->group_id = group_id;
+	tbl_data->external = external;
 	tbl = &tbl_data->tbl;
 	pos = &tbl_data->entry;
 	if (transfer)
@@ -7975,6 +8078,41 @@ flow_dv_tbl_resource_release(struct rte_eth_dev *dev,
 
 		mlx5_flow_os_destroy_flow_tbl(tbl->obj);
 		tbl->obj = NULL;
+		if (is_tunnel_offload_active(dev) && tbl_data->external) {
+			struct mlx5_hlist_entry *he;
+			struct mlx5_hlist *tunnel_grp_hash;
+			struct mlx5_flow_tunnel_hub *thub =
+							mlx5_tunnel_hub(dev);
+			union tunnel_tbl_key tunnel_key = {
+				.tunnel_id = tbl_data->tunnel ?
+						tbl_data->tunnel->tunnel_id : 0,
+				.group = tbl_data->group_id
+			};
+			union mlx5_flow_tbl_key table_key = {
+				.v64 = pos->key
+			};
+			uint32_t table_id = table_key.table_id;
+
+			tunnel_grp_hash = tbl_data->tunnel ?
+						tbl_data->tunnel->groups :
+						thub->groups;
+			he = mlx5_hlist_lookup(tunnel_grp_hash, tunnel_key.val);
+			if (he) {
+				struct tunnel_tbl_entry *tte;
+				tte = container_of(he, typeof(*tte), hash);
+				MLX5_ASSERT(tte->flow_table == table_id);
+				mlx5_hlist_remove(tunnel_grp_hash, he);
+				mlx5_free(tte);
+			}
+			mlx5_flow_id_release(mlx5_tunnel_hub(dev)->table_ids,
+					     tunnel_flow_tbl_to_id(table_id));
+			DRV_LOG(DEBUG,
+				"port %u release table_id %#x tunnel %u group %u",
+				dev->data->port_id, table_id,
+				tbl_data->tunnel ?
+				tbl_data->tunnel->tunnel_id : 0,
+				tbl_data->group_id);
+		}
 		/* remove the entry from the hash list and free memory. */
 		mlx5_hlist_remove(sh->flow_tbls, pos);
 		mlx5_ipool_free(priv->sh->ipool[MLX5_IPOOL_JUMP],
@@ -8020,7 +8158,7 @@ flow_dv_matcher_register(struct rte_eth_dev *dev,
 	int ret;
 
 	tbl = flow_dv_tbl_resource_get(dev, key->table_id, key->direction,
-				       key->domain, error);
+				       key->domain, false, NULL, 0, error);
 	if (!tbl)
 		return -rte_errno;	/* No need to refill the error info */
 	tbl_data = container_of(tbl, struct mlx5_flow_tbl_data_entry, tbl);
@@ -8511,7 +8649,8 @@ flow_dv_sample_resource_register(struct rte_eth_dev *dev,
 	*cache_resource = *resource;
 	/* Create normal path table level */
 	tbl = flow_dv_tbl_resource_get(dev, next_ft_id,
-					attr->egress, attr->transfer, error);
+					attr->egress, attr->transfer,
+					dev_flow->external, NULL, 0, error);
 	if (!tbl) {
 		rte_flow_error_set(error, ENOMEM,
 					  RTE_FLOW_ERROR_TYPE_UNSPECIFIED,
@@ -9123,6 +9262,12 @@ __flow_dv_translate(struct rte_eth_dev *dev,
 	int tmp_actions_n = 0;
 	uint32_t table;
 	int ret = 0;
+	const struct mlx5_flow_tunnel *tunnel;
+	struct flow_grp_info grp_info = {
+		.external = !!dev_flow->external,
+		.transfer = !!attr->transfer,
+		.fdb_def_rule = !!priv->fdb_def_rule,
+	};
 
 	memset(&mdest_res, 0, sizeof(struct mlx5_flow_dv_dest_array_resource));
 	memset(&sample_res, 0, sizeof(struct mlx5_flow_dv_sample_resource));
@@ -9130,8 +9275,17 @@ __flow_dv_translate(struct rte_eth_dev *dev,
 					   MLX5DV_FLOW_TABLE_TYPE_NIC_RX;
 	/* update normal path action resource into last index of array */
 	sample_act = &mdest_res.sample_act[MLX5_MAX_DEST_NUM - 1];
-	ret = mlx5_flow_group_to_table(attr, dev_flow->external, attr->group,
-				       !!priv->fdb_def_rule, &table, error);
+	tunnel = is_flow_tunnel_match_rule(dev, attr, items, actions) ?
+		 flow_items_to_tunnel(items) :
+		 is_flow_tunnel_steer_rule(dev, attr, items, actions) ?
+		 flow_actions_to_tunnel(actions) :
+		 dev_flow->tunnel ? dev_flow->tunnel : NULL;
+	mhdr_res->ft_type = attr->egress ? MLX5DV_FLOW_TABLE_TYPE_NIC_TX :
+					   MLX5DV_FLOW_TABLE_TYPE_NIC_RX;
+	grp_info.std_tbl_fix = tunnel_use_standard_attr_group_translate
+				(dev, tunnel, attr, items, actions);
+	ret = mlx5_flow_group_to_table(dev, tunnel, attr->group, &table,
+				       grp_info, error);
 	if (ret)
 		return ret;
 	dev_flow->dv.group = table;
@@ -9141,6 +9295,45 @@ __flow_dv_translate(struct rte_eth_dev *dev,
 		priority = dev_conf->flow_prio - 1;
 	/* number of actions must be set to 0 in case of dirty stack. */
 	mhdr_res->actions_num = 0;
+	if (is_flow_tunnel_match_rule(dev, attr, items, actions)) {
+		/*
+		 * do not add decap action if match rule drops packet
+		 * HW rejects rules with decap & drop
+		 */
+		bool add_decap = true;
+		const struct rte_flow_action *ptr = actions;
+		struct mlx5_flow_tbl_resource *tbl;
+
+		for (; ptr->type != RTE_FLOW_ACTION_TYPE_END; ptr++) {
+			if (ptr->type == RTE_FLOW_ACTION_TYPE_DROP) {
+				add_decap = false;
+				break;
+			}
+		}
+		if (add_decap) {
+			if (flow_dv_create_action_l2_decap(dev, dev_flow,
+							   attr->transfer,
+							   error))
+				return -rte_errno;
+			dev_flow->dv.actions[actions_n++] =
+					dev_flow->dv.encap_decap->action;
+			action_flags |= MLX5_FLOW_ACTION_DECAP;
+		}
+		/*
+		 * bind table_id with <group, table> for tunnel match rule.
+		 * Tunnel set rule establishes that bind in JUMP action handler.
+		 * Required for scenario when application creates tunnel match
+		 * rule before tunnel set rule.
+		 */
+		tbl = flow_dv_tbl_resource_get(dev, table, attr->egress,
+					       attr->transfer,
+					       !!dev_flow->external, tunnel,
+					       attr->group, error);
+		if (!tbl)
+			return rte_flow_error_set
+			       (error, EINVAL, RTE_FLOW_ERROR_TYPE_ACTION,
+			       actions, "cannot register tunnel group");
+	}
 	for (; !actions_end ; actions++) {
 		const struct rte_flow_action_queue *queue;
 		const struct rte_flow_action_rss *rss;
@@ -9161,6 +9354,9 @@ __flow_dv_translate(struct rte_eth_dev *dev,
 						  actions,
 						  "action not supported");
 		switch (action_type) {
+		case MLX5_RTE_FLOW_ACTION_TYPE_TUNNEL_SET:
+			action_flags |= MLX5_FLOW_ACTION_TUNNEL_SET;
+			break;
 		case RTE_FLOW_ACTION_TYPE_VOID:
 			break;
 		case RTE_FLOW_ACTION_TYPE_PORT_ID:
@@ -9404,18 +9600,18 @@ __flow_dv_translate(struct rte_eth_dev *dev,
 		case RTE_FLOW_ACTION_TYPE_JUMP:
 			jump_group = ((const struct rte_flow_action_jump *)
 							action->conf)->group;
-			if (dev_flow->external && jump_group <
-					MLX5_MAX_TABLES_EXTERNAL)
-				jump_group *= MLX5_FLOW_TABLE_FACTOR;
-			ret = mlx5_flow_group_to_table(attr, dev_flow->external,
+			grp_info.std_tbl_fix = 0;
+			ret = mlx5_flow_group_to_table(dev, tunnel,
 						       jump_group,
-						       !!priv->fdb_def_rule,
-						       &table, error);
+						       &table,
+						       grp_info, error);
 			if (ret)
 				return ret;
-			tbl = flow_dv_tbl_resource_get(dev, table,
-						       attr->egress,
-						       attr->transfer, error);
+			tbl = flow_dv_tbl_resource_get(dev, table, attr->egress,
+						       attr->transfer,
+						       !!dev_flow->external,
+						       tunnel, jump_group,
+						       error);
 			if (!tbl)
 				return rte_flow_error_set
 						(error, errno,
@@ -11439,7 +11635,8 @@ flow_dv_prepare_mtr_tables(struct rte_eth_dev *dev,
 		dtb = &mtb->ingress;
 	/* Create the meter table with METER level. */
 	dtb->tbl = flow_dv_tbl_resource_get(dev, MLX5_FLOW_TABLE_LEVEL_METER,
-					    egress, transfer, &error);
+					    egress, transfer, false, NULL, 0,
+					    &error);
 	if (!dtb->tbl) {
 		DRV_LOG(ERR, "Failed to create meter policer table.");
 		return -1;
@@ -11447,7 +11644,8 @@ flow_dv_prepare_mtr_tables(struct rte_eth_dev *dev,
 	/* Create the meter suffix table with SUFFIX level. */
 	dtb->sfx_tbl = flow_dv_tbl_resource_get(dev,
 					    MLX5_FLOW_TABLE_LEVEL_SUFFIX,
-					    egress, transfer, &error);
+					    egress, transfer, false, NULL, 0,
+					    &error);
 	if (!dtb->sfx_tbl) {
 		DRV_LOG(ERR, "Failed to create meter suffix table.");
 		return -1;
@@ -11766,10 +11964,10 @@ mlx5_flow_dv_discover_counter_offset_support(struct rte_eth_dev *dev)
 	void *flow = NULL;
 	int i, ret = -1;
 
-	tbl = flow_dv_tbl_resource_get(dev, 0, 0, 0, NULL);
+	tbl = flow_dv_tbl_resource_get(dev, 0, 0, 0, false, NULL, 0, NULL);
 	if (!tbl)
 		goto err;
-	dest_tbl = flow_dv_tbl_resource_get(dev, 1, 0, 0, NULL);
+	dest_tbl = flow_dv_tbl_resource_get(dev, 1, 0, 0, false, NULL, 0, NULL);
 	if (!dest_tbl)
 		goto err;
 	dcs = mlx5_devx_cmd_flow_counter_alloc(priv->sh->ctx, 0x4);
-- 
2.28.0



More information about the dev mailing list