[dpdk-dev] [PATCH v3 09/16] ethdev: add encap level to RSS flow API action

[Adrien Mazarguil <adrien.mazarguil@6wind.com>]

RSS hash types (ETH_RSS_* macros defined in rte_ethdev.h) describe the
protocol header fields of a packet that must be taken into account while
computing RSS.

When facing encapsulated (e.g. tunneled) packets, there is an ambiguity as
to whether these should apply to inner or outer packets. Applications need
the ability to tell exactly "where" RSS must be performed.

This is addressed by adding encapsulation level information to the RSS flow
action. Its default value is 0 and stands for the usual unspecified
behavior. Other values provide a specific encapsulation level.

Contrary to the change announced by commit 676b605182a5 ("doc: announce
ethdev API change for RSS configuration"), this patch does not affect
struct rte_eth_rss_conf but struct rte_flow_action_rss as the former is not
used anymore by the RSS flow action. ABI impact is therefore limited to
rte_flow.

This breaks ABI compatibility for the following public functions:

- rte_flow_copy()
- rte_flow_create()
- rte_flow_query()
- rte_flow_validate()

Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Cc: Xueming Li <xuemingl@mellanox.com>
Cc: Ferruh Yigit <ferruh.yigit@intel.com>
Cc: Thomas Monjalon <thomas@monjalon.net>
Cc: Wenzhuo Lu <wenzhuo.lu@intel.com>
Cc: Jingjing Wu <jingjing.wu@intel.com>
Cc: Beilei Xing <beilei.xing@intel.com>
Cc: Qi Zhang <qi.z.zhang@intel.com>
Cc: Konstantin Ananyev <konstantin.ananyev@intel.com>
Cc: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
Cc: Yongseok Koh <yskoh@mellanox.com>
Cc: Andrew Rybchenko <arybchenko@solarflare.com>
Cc: Pascal Mazon <pascal.mazon@6wind.com>
---
 app/test-pmd/cmdline_flow.c                 | 13 ++++++++++++
 app/test-pmd/config.c                       |  1 +
 doc/guides/prog_guide/rte_flow.rst          | 24 ++++++++++++++++++++++
 doc/guides/testpmd_app_ug/testpmd_funcs.rst |  2 ++
 drivers/net/e1000/igb_flow.c                |  4 ++++
 drivers/net/e1000/igb_rxtx.c                |  2 ++
 drivers/net/i40e/i40e_ethdev.c              |  2 ++
 drivers/net/i40e/i40e_flow.c                |  4 ++++
 drivers/net/ixgbe/ixgbe_flow.c              |  4 ++++
 drivers/net/ixgbe/ixgbe_rxtx.c              |  2 ++
 drivers/net/mlx4/mlx4_flow.c                |  6 ++++++
 drivers/net/mlx5/mlx5_flow.c                | 11 ++++++++++
 drivers/net/sfc/sfc_flow.c                  |  3 +++
 drivers/net/tap/tap_flow.c                  |  6 +++++-
 lib/librte_ether/rte_flow.c                 |  1 +
 lib/librte_ether/rte_flow.h                 | 26 ++++++++++++++++++++++++
 16 files changed, 110 insertions(+), 1 deletion(-)

diff --git a/app/test-pmd/cmdline_flow.c b/app/test-pmd/cmdline_flow.c
index 34f33f671..9b6004176 100644
--- a/app/test-pmd/cmdline_flow.c
+++ b/app/test-pmd/cmdline_flow.c
@@ -167,6 +167,7 @@ enum index {
 	ACTION_COUNT,
 	ACTION_RSS,
 	ACTION_RSS_FUNC,
+	ACTION_RSS_LEVEL,
 	ACTION_RSS_FUNC_DEFAULT,
 	ACTION_RSS_FUNC_TOEPLITZ,
 	ACTION_RSS_FUNC_SIMPLE_XOR,
@@ -638,6 +639,7 @@ static const enum index action_queue[] = {
 
 static const enum index action_rss[] = {
 	ACTION_RSS_FUNC,
+	ACTION_RSS_LEVEL,
 	ACTION_RSS_TYPES,
 	ACTION_RSS_KEY,
 	ACTION_RSS_KEY_LEN,
@@ -1616,6 +1618,16 @@ static const struct token token_list[] = {
 		.help = "simple XOR hash function",
 		.call = parse_vc_action_rss_func,
 	},
+	[ACTION_RSS_LEVEL] = {
+		.name = "level",
+		.help = "encapsulation level for \"types\"",
+		.next = NEXT(action_rss, NEXT_ENTRY(UNSIGNED)),
+		.args = ARGS(ARGS_ENTRY_ARB
+			     (offsetof(struct action_rss_data, conf) +
+			      offsetof(struct rte_flow_action_rss, level),
+			      sizeof(((struct rte_flow_action_rss *)0)->
+				     level))),
+	},
 	[ACTION_RSS_TYPES] = {
 		.name = "types",
 		.help = "specific RSS hash types",
@@ -2107,6 +2119,7 @@ parse_vc_action_rss(struct context *ctx, const struct token *token,
 	*action_rss_data = (struct action_rss_data){
 		.conf = (struct rte_flow_action_rss){
 			.func = RTE_ETH_HASH_FUNCTION_DEFAULT,
+			.level = 0,
 			.types = rss_hf,
 			.key_len = sizeof(action_rss_data->key),
 			.queue_num = RTE_MIN(nb_rxq, ACTION_RSS_QUEUE_NUM),
diff --git a/app/test-pmd/config.c b/app/test-pmd/config.c
index b258c93e8..c0fefe475 100644
--- a/app/test-pmd/config.c
+++ b/app/test-pmd/config.c
@@ -1085,6 +1085,7 @@ flow_action_conf_copy(void *buf, const struct rte_flow_action *action)
 		if (dst.rss)
 			*dst.rss = (struct rte_flow_action_rss){
 				.func = src.rss->func,
+				.level = src.rss->level,
 				.types = src.rss->types,
 				.key_len = src.rss->key_len,
 				.queue_num = src.rss->queue_num,
diff --git a/doc/guides/prog_guide/rte_flow.rst b/doc/guides/prog_guide/rte_flow.rst
index e0c68495c..1a09e8a0f 100644
--- a/doc/guides/prog_guide/rte_flow.rst
+++ b/doc/guides/prog_guide/rte_flow.rst
@@ -1311,6 +1311,28 @@ Note: RSS hash result is stored in the ``hash.rss`` mbuf field which
 overlaps ``hash.fdir.lo``. Since `Action: MARK`_ sets the ``hash.fdir.hi``
 field only, both can be requested simultaneously.
 
+Also, regarding packet encapsulation ``level``:
+
+- ``0`` requests the default behavior. Depending on the packet type, it can
+  mean outermost, innermost, anything in between or even no RSS.
+
+  It basically stands for the innermost encapsulation level RSS can be
+  performed on according to PMD and device capabilities.
+
+- ``1`` requests RSS to be performed on the outermost packet encapsulation
+  level.
+
+- ``2`` and subsequent values request RSS to be performed on the specified
+   inner packet encapsulation level, from outermost to innermost (lower to
+   higher values).
+
+Values other than ``0`` are not necessarily supported.
+
+Requesting a specific RSS level on unrecognized traffic results in undefined
+behavior. For predictable results, it is recommended to make the flow rule
+pattern match packet headers up to the requested encapsulation level so that
+only matching traffic goes through.
+
 .. _table_rte_flow_action_rss:
 
 .. table:: RSS
@@ -1320,6 +1342,8 @@ field only, both can be requested simultaneously.
    +===============+=============================================+
    | ``func``      | RSS hash function to apply                  |
    +---------------+---------------------------------------------+
+   | ``level``     | encapsulation level for ``types``           |
+   +---------------+---------------------------------------------+
    | ``types``     | specific RSS hash types (see ``ETH_RSS_*``) |
    +---------------+---------------------------------------------+
    | ``key_len``   | hash key length in bytes                    |
diff --git a/doc/guides/testpmd_app_ug/testpmd_funcs.rst b/doc/guides/testpmd_app_ug/testpmd_funcs.rst
index 546ef3ab7..3b1073bfc 100644
--- a/doc/guides/testpmd_app_ug/testpmd_funcs.rst
+++ b/doc/guides/testpmd_app_ug/testpmd_funcs.rst
@@ -3401,6 +3401,8 @@ This section lists supported actions and their attributes, if any.
   - ``func {hash function}``: RSS hash function to apply, allowed tokens are
     the same as `set_hash_global_config`_.
 
+  - ``level {unsigned}``: encapsulation level for ``types``.
+
   - ``types [{RSS hash type} [...]] end``: specific RSS hash types, allowed
     tokens are the same as `set_hash_input_set`_, except that an empty list
     does not disable RSS but instead requests unspecified "best-effort"
diff --git a/drivers/net/e1000/igb_flow.c b/drivers/net/e1000/igb_flow.c
index 82307ec5d..d1c0b4b8d 100644
--- a/drivers/net/e1000/igb_flow.c
+++ b/drivers/net/e1000/igb_flow.c
@@ -1314,6 +1314,10 @@ igb_parse_rss_filter(struct rte_eth_dev *dev,
 		return rte_flow_error_set
 			(error, ENOTSUP, RTE_FLOW_ERROR_TYPE_ACTION, act,
 			 "non-default RSS hash functions are not supported");
+	if (rss->level)
+		return rte_flow_error_set
+			(error, ENOTSUP, RTE_FLOW_ERROR_TYPE_ACTION, act,
+			 "a nonzero RSS encapsulation level is not supported");
 	if (rss->key_len && rss->key_len != RTE_DIM(rss_conf->key))
 		return rte_flow_error_set
 			(error, ENOTSUP, RTE_FLOW_ERROR_TYPE_ACTION, act,
diff --git a/drivers/net/e1000/igb_rxtx.c b/drivers/net/e1000/igb_rxtx.c
index d5c1cd3d3..a3776a0d7 100644
--- a/drivers/net/e1000/igb_rxtx.c
+++ b/drivers/net/e1000/igb_rxtx.c
@@ -2906,6 +2906,7 @@ igb_rss_conf_init(struct igb_rte_flow_rss_conf *out,
 		return -EINVAL;
 	out->conf = (struct rte_flow_action_rss){
 		.func = in->func,
+		.level = in->level,
 		.types = in->types,
 		.key_len = in->key_len,
 		.queue_num = in->queue_num,
@@ -2921,6 +2922,7 @@ igb_action_rss_same(const struct rte_flow_action_rss *comp,
 		    const struct rte_flow_action_rss *with)
 {
 	return (comp->func == with->func &&
+		comp->level == with->level &&
 		comp->types == with->types &&
 		comp->key_len == with->key_len &&
 		comp->queue_num == with->queue_num &&
diff --git a/drivers/net/i40e/i40e_ethdev.c b/drivers/net/i40e/i40e_ethdev.c
index 5e313950c..b104b551c 100644
--- a/drivers/net/i40e/i40e_ethdev.c
+++ b/drivers/net/i40e/i40e_ethdev.c
@@ -11975,6 +11975,7 @@ i40e_rss_conf_init(struct i40e_rte_flow_rss_conf *out,
 		return -EINVAL;
 	out->conf = (struct rte_flow_action_rss){
 		.func = in->func,
+		.level = in->level,
 		.types = in->types,
 		.key_len = in->key_len,
 		.queue_num = in->queue_num,
@@ -11990,6 +11991,7 @@ i40e_action_rss_same(const struct rte_flow_action_rss *comp,
 		     const struct rte_flow_action_rss *with)
 {
 	return (comp->func == with->func &&
+		comp->level == with->level &&
 		comp->types == with->types &&
 		comp->key_len == with->key_len &&
 		comp->queue_num == with->queue_num &&
diff --git a/drivers/net/i40e/i40e_flow.c b/drivers/net/i40e/i40e_flow.c
index 33f77cc80..fef812c6b 100644
--- a/drivers/net/i40e/i40e_flow.c
+++ b/drivers/net/i40e/i40e_flow.c
@@ -4356,6 +4356,10 @@ i40e_flow_parse_rss_action(struct rte_eth_dev *dev,
 		return rte_flow_error_set
 			(error, ENOTSUP, RTE_FLOW_ERROR_TYPE_ACTION, act,
 			 "non-default RSS hash functions are not supported");
+	if (rss->level)
+		return rte_flow_error_set
+			(error, ENOTSUP, RTE_FLOW_ERROR_TYPE_ACTION, act,
+			 "a nonzero RSS encapsulation level is not supported");
 	if (rss->key_len && rss->key_len > RTE_DIM(rss_config->key))
 		return rte_flow_error_set
 			(error, ENOTSUP, RTE_FLOW_ERROR_TYPE_ACTION, act,
diff --git a/drivers/net/ixgbe/ixgbe_flow.c b/drivers/net/ixgbe/ixgbe_flow.c
index 00d975b93..438bfcdfb 100644
--- a/drivers/net/ixgbe/ixgbe_flow.c
+++ b/drivers/net/ixgbe/ixgbe_flow.c
@@ -2783,6 +2783,10 @@ ixgbe_parse_rss_filter(struct rte_eth_dev *dev,
 		return rte_flow_error_set
 			(error, ENOTSUP, RTE_FLOW_ERROR_TYPE_ACTION, act,
 			 "non-default RSS hash functions are not supported");
+	if (rss->level)
+		return rte_flow_error_set
+			(error, ENOTSUP, RTE_FLOW_ERROR_TYPE_ACTION, act,
+			 "a nonzero RSS encapsulation level is not supported");
 	if (rss->key_len && rss->key_len != RTE_DIM(rss_conf->key))
 		return rte_flow_error_set
 			(error, ENOTSUP, RTE_FLOW_ERROR_TYPE_ACTION, act,
diff --git a/drivers/net/ixgbe/ixgbe_rxtx.c b/drivers/net/ixgbe/ixgbe_rxtx.c
index e17f5a433..23af21712 100644
--- a/drivers/net/ixgbe/ixgbe_rxtx.c
+++ b/drivers/net/ixgbe/ixgbe_rxtx.c
@@ -5683,6 +5683,7 @@ ixgbe_rss_conf_init(struct ixgbe_rte_flow_rss_conf *out,
 		return -EINVAL;
 	out->conf = (struct rte_flow_action_rss){
 		.func = in->func,
+		.level = in->level,
 		.types = in->types,
 		.key_len = in->key_len,
 		.queue_num = in->queue_num,
@@ -5698,6 +5699,7 @@ ixgbe_action_rss_same(const struct rte_flow_action_rss *comp,
 		      const struct rte_flow_action_rss *with)
 {
 	return (comp->func == with->func &&
+		comp->level == with->level &&
 		comp->types == with->types &&
 		comp->key_len == with->key_len &&
 		comp->queue_num == with->queue_num &&
diff --git a/drivers/net/mlx4/mlx4_flow.c b/drivers/net/mlx4/mlx4_flow.c
index dcaf8df44..779641e11 100644
--- a/drivers/net/mlx4/mlx4_flow.c
+++ b/drivers/net/mlx4/mlx4_flow.c
@@ -796,6 +796,11 @@ mlx4_flow_prepare(struct priv *priv,
 					" is Toeplitz";
 				goto exit_action_not_supported;
 			}
+			if (rss->level) {
+				msg = "a nonzero RSS encapsulation level is"
+					" not supported";
+				goto exit_action_not_supported;
+			}
 			rte_errno = 0;
 			fields = mlx4_conv_rss_types(priv, rss->types);
 			if (fields == (uint64_t)-1 && rte_errno) {
@@ -1290,6 +1295,7 @@ mlx4_flow_internal(struct priv *priv, struct rte_flow_error *error)
 	uint16_t queue[queues];
 	struct rte_flow_action_rss action_rss = {
 		.func = RTE_ETH_HASH_FUNCTION_DEFAULT,
+		.level = 0,
 		.types = -1,
 		.key_len = MLX4_RSS_HASH_KEY_SIZE,
 		.queue_num = queues,
diff --git a/drivers/net/mlx5/mlx5_flow.c b/drivers/net/mlx5/mlx5_flow.c
index 0771ad339..bc1176819 100644
--- a/drivers/net/mlx5/mlx5_flow.c
+++ b/drivers/net/mlx5/mlx5_flow.c
@@ -644,6 +644,14 @@ mlx5_flow_convert_actions(struct rte_eth_dev *dev,
 						   " function is Toeplitz");
 				return -rte_errno;
 			}
+			if (rss->level) {
+				rte_flow_error_set(error, EINVAL,
+						   RTE_FLOW_ERROR_TYPE_ACTION,
+						   actions,
+						   "a nonzero RSS encapsulation"
+						   " level is not supported");
+				return -rte_errno;
+			}
 			if (rss->types & MLX5_RSS_HF_MASK) {
 				rte_flow_error_set(error, EINVAL,
 						   RTE_FLOW_ERROR_TYPE_ACTION,
@@ -694,6 +702,7 @@ mlx5_flow_convert_actions(struct rte_eth_dev *dev,
 			}
 			parser->rss_conf = (struct rte_flow_action_rss){
 				.func = RTE_ETH_HASH_FUNCTION_DEFAULT,
+				.level = 0,
 				.types = rss->types,
 				.key_len = rss_key_len,
 				.queue_num = rss->queue_num,
@@ -1927,6 +1936,7 @@ mlx5_flow_list_create(struct rte_eth_dev *dev,
 	flow->queues = (uint16_t (*)[])(flow + 1);
 	flow->rss_conf = (struct rte_flow_action_rss){
 		.func = RTE_ETH_HASH_FUNCTION_DEFAULT,
+		.level = 0,
 		.types = parser.rss_conf.types,
 		.key_len = parser.rss_conf.key_len,
 		.queue_num = parser.rss_conf.queue_num,
@@ -2442,6 +2452,7 @@ mlx5_ctrl_flow_vlan(struct rte_eth_dev *dev,
 	uint16_t queue[priv->reta_idx_n];
 	struct rte_flow_action_rss action_rss = {
 		.func = RTE_ETH_HASH_FUNCTION_DEFAULT,
+		.level = 0,
 		.types = priv->rss_conf.rss_hf,
 		.key_len = priv->rss_conf.rss_key_len,
 		.queue_num = priv->reta_idx_n,
diff --git a/drivers/net/sfc/sfc_flow.c b/drivers/net/sfc/sfc_flow.c
index 779edad0c..3028efbf9 100644
--- a/drivers/net/sfc/sfc_flow.c
+++ b/drivers/net/sfc/sfc_flow.c
@@ -1269,6 +1269,9 @@ sfc_flow_parse_rss(struct sfc_adapter *sa,
 		return -EINVAL;
 	}
 
+	if (rss->level)
+		return -EINVAL;
+
 	if ((rss->types & ~SFC_RSS_OFFLOADS) != 0)
 		return -EINVAL;
 
diff --git a/drivers/net/tap/tap_flow.c b/drivers/net/tap/tap_flow.c
index 7abf49ab1..1caefff43 100644
--- a/drivers/net/tap/tap_flow.c
+++ b/drivers/net/tap/tap_flow.c
@@ -2055,11 +2055,15 @@ static int rss_add_actions(struct rte_flow *flow, struct pmd_internals *pmd,
 	struct rss_key rss_entry = { .hash_fields = 0,
 				     .key_size = 0 };
 
-	/* Check supported hash functions */
+	/* Check supported RSS features */
 	if (rss->func != RTE_ETH_HASH_FUNCTION_DEFAULT)
 		return rte_flow_error_set
 			(error, ENOTSUP, RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
 			 "non-default RSS hash functions are not supported");
+	if (rss->level)
+		return rte_flow_error_set
+			(error, ENOTSUP, RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
+			 "a nonzero RSS encapsulation level is not supported");
 
 	/* Get a new map key for a new RSS rule */
 	err = bpf_rss_key(KEY_CMD_GET, &flow->key_idx);
diff --git a/lib/librte_ether/rte_flow.c b/lib/librte_ether/rte_flow.c
index 0a2c0ac00..1f247d656 100644
--- a/lib/librte_ether/rte_flow.c
+++ b/lib/librte_ether/rte_flow.c
@@ -331,6 +331,7 @@ flow_action_conf_copy(void *buf, const struct rte_flow_action *action)
 		if (dst.rss)
 			*dst.rss = (struct rte_flow_action_rss){
 				.func = src.rss->func,
+				.level = src.rss->level,
 				.types = src.rss->types,
 				.key_len = src.rss->key_len,
 				.queue_num = src.rss->queue_num,
diff --git a/lib/librte_ether/rte_flow.h b/lib/librte_ether/rte_flow.h
index acf6031ec..cf4a3faf2 100644
--- a/lib/librte_ether/rte_flow.h
+++ b/lib/librte_ether/rte_flow.h
@@ -1046,6 +1046,32 @@ struct rte_flow_query_count {
  */
 struct rte_flow_action_rss {
 	enum rte_eth_hash_function func; /**< RSS hash function to apply. */
+	/**
+	 * Packet encapsulation level RSS hash @p types apply to.
+	 *
+	 * - @p 0 requests the default behavior. Depending on the packet
+	 *   type, it can mean outermost, innermost, anything in between or
+	 *   even no RSS.
+	 *
+	 *   It basically stands for the innermost encapsulation level RSS
+	 *   can be performed on according to PMD and device capabilities.
+	 *
+	 * - @p 1 requests RSS to be performed on the outermost packet
+	 *   encapsulation level.
+	 *
+	 * - @p 2 and subsequent values request RSS to be performed on the
+	 *   specified inner packet encapsulation level, from outermost to
+	 *   innermost (lower to higher values).
+	 *
+	 * Values other than @p 0 are not necessarily supported.
+	 *
+	 * Requesting a specific RSS level on unrecognized traffic results
+	 * in undefined behavior. For predictable results, it is recommended
+	 * to make the flow rule pattern match packet headers up to the
+	 * requested encapsulation level so that only matching traffic goes
+	 * through.
+	 */
+	uint32_t level;
 	uint64_t types; /**< Specific RSS hash types (see ETH_RSS_*). */
 	uint32_t key_len; /**< Hash key length in bytes. */
 	uint32_t queue_num; /**< Number of entries in @p queue. */
-- 
2.11.0