[dpdk-dev] [PATCH 09/20] net/mlx5: add devarg for extensive metadata support

[Viacheslav Ovsiienko]

The PMD parameter dv_xmeta_en is added to control extensive
metadata support. A nonzero value enables extensive flow
metadata support if device is capable and driver supports it.
This can enable extensive support of MARK and META item of
rte_flow. The newly introduced SET_TAG and SET_META actions
do not depend on dv_xmeta_en parameter, because there is
no compatibility issue for new entities. The dv_xmeta_en is
disabled by default.

There are some possible configurations, depending on parameter
value:

- 0, this is default value, defines the legacy mode, the MARK
  and META related actions and items operate only within NIC Tx
  and NIC Rx steering domains, no MARK and META information
  crosses the domain boundaries. The MARK item is 24 bits wide,
  the META item is 32 bits wide.

- 1, this engages extensive metadata mode, the MARK and META
  related actions and items operate within all supported steering
  domains, including FDB, MARK and META information may cross
  the domain boundaries. The ``MARK`` item is 24 bits wide, the
  META item width depends on kernel and firmware configurations
  and might be 0, 16 or 32 bits. Within NIC Tx domain META data
  width is 32 bits for compatibility, the actual width of data
  transferred to the FDB domain depends on kernel configuration
  and may be vary. The actual supported width can be retrieved
  in runtime by series of rte_flow_validate() trials.

- 2, this engages extensive metadata mode, the MARK and META
  related actions and items operate within all supported steering
  domains, including FDB, MARK and META information may cross
  the domain boundaries. The META item is 32 bits wide, the MARK
  item width depends on kernel and firmware configurations and
  might be 0, 16 or 24 bits. The actual supported width can be
  retrieved in runtime by series of rte_flow_validate() trials.

If there is no E-Switch configuration the ``dv_xmeta_en`` parameter is
ignored and the device is configured to operate in legacy mode (0).

Signed-off-by: Yongseok Koh <yskoh at mellanox.com>
Signed-off-by: Viacheslav Ovsiienko <viacheslavo at mellanox.com>
Acked-by: Matan Azrad <matan at mellanox.com>
---
 doc/guides/nics/mlx5.rst     | 49 ++++++++++++++++++++++++++++++++++++++++++++
 drivers/net/mlx5/mlx5.c      | 33 +++++++++++++++++++++++++++++
 drivers/net/mlx5/mlx5.h      |  1 +
 drivers/net/mlx5/mlx5_defs.h |  4 ++++
 drivers/net/mlx5/mlx5_prm.h  |  3 +++
 5 files changed, 90 insertions(+)

diff --git a/doc/guides/nics/mlx5.rst b/doc/guides/nics/mlx5.rst
index 4f1093f..8870969 100644
--- a/doc/guides/nics/mlx5.rst
+++ b/doc/guides/nics/mlx5.rst
@@ -578,6 +578,55 @@ Run-time configuration
 
   Disabled by default.
 
+- ``dv_xmeta_en`` parameter [int]
+
+  A nonzero value enables extensive flow metadata support if device is
+  capable and driver supports it. This can enable extensive support of
+  ``MARK`` and ``META`` item of ``rte_flow``. The newly introduced
+  ``SET_TAG`` and ``SET_META`` actions do not depend on ``dv_xmeta_en``.
+
+  There are some possible configurations, depending on parameter value:
+
+  - 0, this is default value, defines the legacy mode, the ``MARK`` and
+    ``META`` related actions and items operate only within NIC Tx and
+    NIC Rx steering domains, no ``MARK`` and ``META`` information crosses
+    the domain boundaries. The ``MARK`` item is 24 bits wide, the ``META``
+    item is 32 bits wide.
+
+  - 1, this engages extensive metadata mode, the ``MARK`` and ``META``
+    related actions and items operate within all supported steering domains,
+    including FDB, ``MARK`` and ``META`` information may cross the domain
+    boundaries. The ``MARK`` item is 24 bits wide, the ``META`` item width
+    depends on kernel and firmware configurations and might be 0, 16 or
+    32 bits. Within NIC Tx domain ``META`` data width is 32 bits for
+    compatibility, the actual width of data transferred to the FDB domain
+    depends on kernel configuration and may be vary. The actual supported
+    width can be retrieved in runtime by series of rte_flow_validate()
+    trials.
+
+  - 2, this engages extensive metadata mode, the ``MARK`` and ``META``
+    related actions and items operate within all supported steering domains,
+    including FDB, ``MARK`` and ``META`` information may cross the domain
+    boundaries. The ``META`` item is 32 bits wide, the ``MARK`` item width
+    depends on kernel and firmware configurations and might be 0, 16 or
+    24 bits. The actual supported width can be retrieved in runtime by
+    series of rte_flow_validate() trials.
+
+  +------+-----------+-----------+-------------+-------------+
+  | Mode | ``MARK``  | ``META``  | ``META`` Tx | FDB/Through |
+  +======+===========+===========+=============+=============+
+  | 0    | 24 bits   | 32 bits   | 32 bits     | no          |
+  +------+-----------+-----------+-------------+-------------+
+  | 1    | 24 bits   | vary 0-32 | 32 bits     | yes         |
+  +------+-----------+-----------+-------------+-------------+
+  | 2    | vary 0-32 | 32 bits   | 32 bits     | yes         |
+  +------+-----------+-----------+-------------+-------------+
+
+  If there is no E-Switch configuration the ``dv_xmeta_en`` parameter is
+  ignored and the device is configured to operate in legacy mode (0).
+
+  Disabled by default (set to 0).
+
 - ``dv_flow_en`` parameter [int]
 
   A nonzero value enables the DV flow steering assuming it is supported
diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c
index 1b86b7b..943d0e8 100644
--- a/drivers/net/mlx5/mlx5.c
+++ b/drivers/net/mlx5/mlx5.c
@@ -125,6 +125,9 @@
 /* Activate DV flow steering. */
 #define MLX5_DV_FLOW_EN "dv_flow_en"
 
+/* Enable extensive flow metadata support. */
+#define MLX5_DV_XMETA_EN "dv_xmeta_en"
+
 /* Activate Netlink support in VF mode. */
 #define MLX5_VF_NL_EN "vf_nl_en"
 
@@ -1310,6 +1313,16 @@ struct mlx5_flow_id_pool *
 		config->dv_esw_en = !!tmp;
 	} else if (strcmp(MLX5_DV_FLOW_EN, key) == 0) {
 		config->dv_flow_en = !!tmp;
+	} 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) {
+			DRV_LOG(WARNING, "invalid extensive "
+					 "metadata parameter");
+			rte_errno = EINVAL;
+			return -rte_errno;
+		}
+		config->dv_xmeta_en = tmp;
 	} else if (strcmp(MLX5_MR_EXT_MEMSEG_EN, key) == 0) {
 		config->mr_ext_memseg_en = !!tmp;
 	} else if (strcmp(MLX5_MAX_DUMP_FILES_NUM, key) == 0) {
@@ -1361,6 +1374,7 @@ struct mlx5_flow_id_pool *
 		MLX5_VF_NL_EN,
 		MLX5_DV_ESW_EN,
 		MLX5_DV_FLOW_EN,
+		MLX5_DV_XMETA_EN,
 		MLX5_MR_EXT_MEMSEG_EN,
 		MLX5_REPRESENTOR,
 		MLX5_MAX_DUMP_FILES_NUM,
@@ -1734,6 +1748,12 @@ struct mlx5_flow_id_pool *
 		rte_errno = EINVAL;
 		return rte_errno;
 	}
+	if (sh_conf->dv_xmeta_en ^ config->dv_xmeta_en) {
+		DRV_LOG(ERR, "\"dv_xmeta_en\" configuration mismatch"
+			     " for shared %s context", sh->ibdev_name);
+		rte_errno = EINVAL;
+		return rte_errno;
+	}
 	return 0;
 }
 /**
@@ -2347,10 +2367,23 @@ struct mlx5_flow_id_pool *
 		err = -err;
 		goto error;
 	}
+	if (!priv->config.dv_esw_en &&
+	    priv->config.dv_xmeta_en != MLX5_XMETA_MODE_LEGACY) {
+		DRV_LOG(WARNING, "metadata mode %u is not supported "
+				 "(no E-Switch)", priv->config.dv_xmeta_en);
+		priv->config.dv_xmeta_en = MLX5_XMETA_MODE_LEGACY;
+	}
 	if (!mlx5_flow_ext_mreg_supported(eth_dev)) {
 		DRV_LOG(DEBUG,
 			"port %u extensive metadata register is not supported",
 			eth_dev->data->port_id);
+		if (priv->config.dv_xmeta_en != MLX5_XMETA_MODE_LEGACY) {
+			DRV_LOG(ERR, "metadata mode %u is not supported "
+				     "(no metadata registers available)",
+				     priv->config.dv_xmeta_en);
+			err = ENOTSUP;
+			goto error;
+		}
 	}
 	return eth_dev;
 error:
diff --git a/drivers/net/mlx5/mlx5.h b/drivers/net/mlx5/mlx5.h
index 6b82c6d..e59f8f6 100644
--- a/drivers/net/mlx5/mlx5.h
+++ b/drivers/net/mlx5/mlx5.h
@@ -238,6 +238,7 @@ struct mlx5_dev_config {
 	unsigned int vf_nl_en:1; /* Enable Netlink requests in VF mode. */
 	unsigned int dv_esw_en:1; /* Enable E-Switch DV flow. */
 	unsigned int dv_flow_en:1; /* Enable DV flow. */
+	unsigned int dv_xmeta_en:2; /* Enable extensive flow metadata. */
 	unsigned int swp:1; /* Tx generic tunnel checksum and TSO offload. */
 	unsigned int devx:1; /* Whether devx interface is available or not. */
 	unsigned int dest_tir:1; /* Whether advanced DR API is available. */
diff --git a/drivers/net/mlx5/mlx5_defs.h b/drivers/net/mlx5/mlx5_defs.h
index e36ab55..a77c430 100644
--- a/drivers/net/mlx5/mlx5_defs.h
+++ b/drivers/net/mlx5/mlx5_defs.h
@@ -141,6 +141,10 @@
 /* Cache size of mempool for Multi-Packet RQ. */
 #define MLX5_MPRQ_MP_CACHE_SZ 32U
 
+#define MLX5_XMETA_MODE_LEGACY 0
+#define MLX5_XMETA_MODE_META16 1
+#define MLX5_XMETA_MODE_META32 2
+
 /* Definition of static_assert found in /usr/include/assert.h */
 #ifndef HAVE_STATIC_ASSERT
 #define static_assert _Static_assert
diff --git a/drivers/net/mlx5/mlx5_prm.h b/drivers/net/mlx5/mlx5_prm.h
index c17ba66..b405cb6 100644
--- a/drivers/net/mlx5/mlx5_prm.h
+++ b/drivers/net/mlx5/mlx5_prm.h
@@ -226,6 +226,9 @@
 /* Default mark value used when none is provided. */
 #define MLX5_FLOW_MARK_DEFAULT 0xffffff
 
+/* Default mark mask for metadata legacy mode. */
+#define MLX5_FLOW_MARK_MASK 0xffffff
+
 /* Maximum number of DS in WQE. Limited by 6-bit field. */
 #define MLX5_DSEG_MAX 63
 
-- 
1.8.3.1