[PATCH 0/6] net/dpaa2: RSS fixes and improvements

[PATCH 0/6] net/dpaa2: RSS fixes and improvements

[Maxime Leroy]

A set of RSS fixes and improvements for the dpaa2 PMD.

Patches 1 and 2 fix the RSS hash key: the L4 destination port was never
added (both extracts used the source port), and SCTP now uses the same L4
port extraction as TCP/UDP. Both are tagged for stable.

Patches 3 and 4 are small cleanups in the key builder (a dead num_extracts
increment, and the unset PPPoE guard flag).

Patch 5 honours RTE_ETH_RSS_LEVEL_INNERMOST so tunnelled traffic hashes on
the inner IP header. Patch 6 implements reta_query / reta_update as an
emulation over the HW distribution-size mechanism, since dpaa2 has no
software-visible indirection table.

Tested on LX2160A (lx2160acex7).

Maxime Leroy (6):
  net/dpaa2: add L4 destination port to the RSS hash key
  net/dpaa2: use L4 port extraction for SCTP RSS
  net/dpaa2: drop stray extract count bump in RSS key build
  net/dpaa2: set PPPoE configured flag in RSS key build
  net/dpaa2: support inner RSS level for tunnelled traffic
  net/dpaa2: implement RSS RETA query and update

 doc/guides/nics/features/dpaa2.ini     |   1 +
 doc/guides/rel_notes/release_26_07.rst |   5 +
 drivers/net/dpaa2/base/dpaa2_hw_dpni.c |  94 +++++++-----
 drivers/net/dpaa2/dpaa2_ethdev.c       | 204 ++++++++++++++++++++++++-
 drivers/net/dpaa2/dpaa2_ethdev.h       |   9 ++
 5 files changed, 272 insertions(+), 41 deletions(-)

-- 
2.43.0

[PATCH 1/6] net/dpaa2: add L4 destination port to the RSS hash key

[Maxime Leroy]

The TCP/UDP case of the RSS key builder added two extracts but both used
NH_FLD_TCP_PORT_SRC, so the L4 destination port was never part of the
hash. Use NH_FLD_TCP_PORT_DST for the second extract so both source and
destination ports contribute.

NET_PROT_TCP is kept: it maps to the hardware's generic L4 port
extraction (parser L4 offset, valid for TCP/UDP/SCTP), so this also
covers UDP traffic.

Fixes: 89c2ea8f5408 ("net/dpaa2: add RSS flow distribution")
Cc: stable@dpdk.org

Signed-off-by: Maxime Leroy <maxime@leroys.fr>
---
 drivers/net/dpaa2/base/dpaa2_hw_dpni.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dpaa2/base/dpaa2_hw_dpni.c b/drivers/net/dpaa2/base/dpaa2_hw_dpni.c
index 13825046d8..e7578b7576 100644
--- a/drivers/net/dpaa2/base/dpaa2_hw_dpni.c
+++ b/drivers/net/dpaa2/base/dpaa2_hw_dpni.c
@@ -425,7 +425,7 @@ dpaa2_distset_to_dpkg_profile_cfg(
 				kg_cfg->extracts[i].extract.from_hdr.prot =
 					NET_PROT_TCP;
 				kg_cfg->extracts[i].extract.from_hdr.field =
-					NH_FLD_TCP_PORT_SRC;
+					NH_FLD_TCP_PORT_DST;
 				kg_cfg->extracts[i].type =
 					DPKG_EXTRACT_FROM_HDR;
 				kg_cfg->extracts[i].extract.from_hdr.type =
-- 
2.43.0

[PATCH 2/6] net/dpaa2: use L4 port extraction for SCTP RSS

[Maxime Leroy]

DPAA2 hardware exposes L4 source and destination port fields at the parser
L4 offset. These fields are valid when TCP, UDP, SCTP or DCCP is present.

The driver already uses the TCP port fields for the TCP/UDP RSS case.
Handle SCTP in the same L4 RSS case, so SCTP packets use the same L4
source and destination port extraction.

Fixes: 89c2ea8f5408 ("net/dpaa2: add RSS flow distribution")
Cc: stable@dpdk.org

Signed-off-by: Maxime Leroy <maxime@leroys.fr>
---
 drivers/net/dpaa2/base/dpaa2_hw_dpni.c | 32 +++-----------------------
 1 file changed, 3 insertions(+), 29 deletions(-)

diff --git a/drivers/net/dpaa2/base/dpaa2_hw_dpni.c b/drivers/net/dpaa2/base/dpaa2_hw_dpni.c
index e7578b7576..4df66d8f33 100644
--- a/drivers/net/dpaa2/base/dpaa2_hw_dpni.c
+++ b/drivers/net/dpaa2/base/dpaa2_hw_dpni.c
@@ -228,7 +228,7 @@ dpaa2_distset_to_dpkg_profile_cfg(
 	uint32_t loop = 0, i = 0;
 	uint64_t dist_field = 0;
 	int l2_configured = 0, l3_configured = 0;
-	int l4_configured = 0, sctp_configured = 0;
+	int l4_configured = 0;
 	int mpls_configured = 0;
 	int vlan_configured = 0;
 	int esp_configured = 0;
@@ -407,6 +407,8 @@ dpaa2_distset_to_dpkg_profile_cfg(
 			case RTE_ETH_RSS_NONFRAG_IPV6_UDP:
 			case RTE_ETH_RSS_IPV6_TCP_EX:
 			case RTE_ETH_RSS_IPV6_UDP_EX:
+			case RTE_ETH_RSS_NONFRAG_IPV4_SCTP:
+			case RTE_ETH_RSS_NONFRAG_IPV6_SCTP:
 
 				if (l4_configured)
 					break;
@@ -433,34 +435,6 @@ dpaa2_distset_to_dpkg_profile_cfg(
 				i++;
 				break;
 
-			case RTE_ETH_RSS_NONFRAG_IPV4_SCTP:
-			case RTE_ETH_RSS_NONFRAG_IPV6_SCTP:
-
-				if (sctp_configured)
-					break;
-				sctp_configured = 1;
-
-				kg_cfg->extracts[i].extract.from_hdr.prot =
-					NET_PROT_SCTP;
-				kg_cfg->extracts[i].extract.from_hdr.field =
-					NH_FLD_SCTP_PORT_SRC;
-				kg_cfg->extracts[i].type =
-					DPKG_EXTRACT_FROM_HDR;
-				kg_cfg->extracts[i].extract.from_hdr.type =
-					DPKG_FULL_FIELD;
-				i++;
-
-				kg_cfg->extracts[i].extract.from_hdr.prot =
-					NET_PROT_SCTP;
-				kg_cfg->extracts[i].extract.from_hdr.field =
-					NH_FLD_SCTP_PORT_DST;
-				kg_cfg->extracts[i].type =
-					DPKG_EXTRACT_FROM_HDR;
-				kg_cfg->extracts[i].extract.from_hdr.type =
-					DPKG_FULL_FIELD;
-				i++;
-				break;
-
 			default:
 				DPAA2_PMD_WARN(
 				      "unsupported flow dist option 0x%" PRIx64,
-- 
2.43.0

[PATCH 3/6] net/dpaa2: drop stray extract count bump in RSS key build

[Maxime Leroy]

The IPv4/IPv6 L3 case bumped kg_cfg->num_extracts once in the middle of
the loop, while every other case relies on the final
'kg_cfg->num_extracts = i' that overwrites it. The increment was dead and
misleading; remove it.

Signed-off-by: Maxime Leroy <maxime@leroys.fr>
---
 drivers/net/dpaa2/base/dpaa2_hw_dpni.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/dpaa2/base/dpaa2_hw_dpni.c b/drivers/net/dpaa2/base/dpaa2_hw_dpni.c
index 4df66d8f33..f1d670f213 100644
--- a/drivers/net/dpaa2/base/dpaa2_hw_dpni.c
+++ b/drivers/net/dpaa2/base/dpaa2_hw_dpni.c
@@ -397,7 +397,6 @@ dpaa2_distset_to_dpkg_profile_cfg(
 					DPKG_EXTRACT_FROM_HDR;
 				kg_cfg->extracts[i].extract.from_hdr.type =
 					DPKG_FULL_FIELD;
-				kg_cfg->num_extracts++;
 				i++;
 			break;
 
-- 
2.43.0

[PATCH 4/6] net/dpaa2: set PPPoE configured flag in RSS key build

[Maxime Leroy]

The RTE_ETH_RSS_PPPOE case tested pppoe_configured as a guard against
adding the extract twice, but never set it, leaving the guard dead. Set
it like the other protocol cases.

Signed-off-by: Maxime Leroy <maxime@leroys.fr>
---
 drivers/net/dpaa2/base/dpaa2_hw_dpni.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/dpaa2/base/dpaa2_hw_dpni.c b/drivers/net/dpaa2/base/dpaa2_hw_dpni.c
index f1d670f213..2724672a5e 100644
--- a/drivers/net/dpaa2/base/dpaa2_hw_dpni.c
+++ b/drivers/net/dpaa2/base/dpaa2_hw_dpni.c
@@ -260,6 +260,8 @@ dpaa2_distset_to_dpkg_profile_cfg(
 			case RTE_ETH_RSS_PPPOE:
 				if (pppoe_configured)
 					break;
+				pppoe_configured = 1;
+
 				kg_cfg->extracts[i].extract.from_hdr.prot =
 					NET_PROT_PPPOE;
 				kg_cfg->extracts[i].extract.from_hdr.field =
-- 
2.43.0

[PATCH 5/6] net/dpaa2: support inner RSS level for tunnelled traffic

[Maxime Leroy]

Honour RTE_ETH_RSS_LEVEL_INNERMOST in the RSS configuration. When it is
set, program the IP extracts with hdr_index = HDR_INDEX_LAST so the RSS
key uses the innermost IP header instead of the outer one.

This is useful for tunnelled traffic whose outer headers are fixed,
leaving no entropy for an outer IP hash. Hashing on the inner IP
addresses spreads such flows.

The hdr_index field is only defined for IP/IPv4/IPv6, VLAN and MPLS
extracts, so this patch only controls the IP extracts. L4 extracts do not
have a header-instance selector and keep hdr_index 0; they continue to
use the parser-selected L4 offset.

The RSS level is carried in the high bits of rss_hf; extract it and strip
the level bits before walking the protocol bits so they are not mistaken
for an unsupported hash type. The level is also advertised in
flow_type_rss_offloads, otherwise ethdev rejects an rss_hf carrying it.

Signed-off-by: Maxime Leroy <maxime@leroys.fr>
---
 doc/guides/rel_notes/release_26_07.rst |  4 ++++
 drivers/net/dpaa2/base/dpaa2_hw_dpni.c | 23 +++++++++++++++++++++++
 drivers/net/dpaa2/dpaa2_ethdev.c       |  3 ++-
 3 files changed, 29 insertions(+), 1 deletion(-)

diff --git a/doc/guides/rel_notes/release_26_07.rst b/doc/guides/rel_notes/release_26_07.rst
index 5d7aa8d1bf..39f3988198 100644
--- a/doc/guides/rel_notes/release_26_07.rst
+++ b/doc/guides/rel_notes/release_26_07.rst
@@ -140,6 +140,10 @@ New Features
 
   * Added support for selective Rx in scalar SPRQ Rx path.
 
+* **Updated NXP dpaa2 driver.**
+
+  * Added inner RSS level support for tunnelled traffic.
+
 * **Updated PCAP ethernet driver.**
 
   * Added support for VLAN insertion and stripping.
diff --git a/drivers/net/dpaa2/base/dpaa2_hw_dpni.c b/drivers/net/dpaa2/base/dpaa2_hw_dpni.c
index 2724672a5e..8a05253bbd 100644
--- a/drivers/net/dpaa2/base/dpaa2_hw_dpni.c
+++ b/drivers/net/dpaa2/base/dpaa2_hw_dpni.c
@@ -220,6 +220,13 @@ dpaa2_remove_flow_dist(struct rte_eth_dev *eth_dev,
 	return ret;
 }
 
+/* dpkg from_hdr.hdr_index value selecting the innermost IP instance (see
+ * fsl_dpkg.h, where hdr_index is only defined for NET_PROT_IP/IPv4/IPv6/
+ * VLAN/MPLS). Used to hash on the inner IP of tunnelled traffic when
+ * RTE_ETH_RSS_LEVEL_INNERMOST is requested.
+ */
+#define DPAA2_DIST_HDR_INDEX_LAST 0xff
+
 int
 dpaa2_distset_to_dpkg_profile_cfg(
 		uint64_t req_dist_set,
@@ -234,8 +241,18 @@ dpaa2_distset_to_dpkg_profile_cfg(
 	int esp_configured = 0;
 	int ah_configured = 0;
 	int pppoe_configured = 0;
+	uint8_t hdr_index = 0;
 
 	memset(kg_cfg, 0, sizeof(struct dpkg_profile_cfg));
+
+	/* RTE_ETH_RSS_LEVEL_INNERMOST asks for the inner header to be hashed.
+	 * Map it to the innermost IP instance in the key extracts; the level
+	 * bits are not protocol bits, so strip them before the loop.
+	 */
+	if ((req_dist_set & RTE_ETH_RSS_LEVEL_MASK) == RTE_ETH_RSS_LEVEL_INNERMOST)
+		hdr_index = DPAA2_DIST_HDR_INDEX_LAST;
+	req_dist_set &= ~RTE_ETH_RSS_LEVEL_MASK;
+
 	while (req_dist_set) {
 		if (req_dist_set % 2 != 0) {
 			dist_field = 1ULL << loop;
@@ -373,6 +390,8 @@ dpaa2_distset_to_dpkg_profile_cfg(
 
 				kg_cfg->extracts[i].extract.from_hdr.prot =
 					NET_PROT_IP;
+				kg_cfg->extracts[i].extract.from_hdr.hdr_index =
+					hdr_index;
 				kg_cfg->extracts[i].extract.from_hdr.field =
 					NH_FLD_IP_SRC;
 				kg_cfg->extracts[i].type =
@@ -383,6 +402,8 @@ dpaa2_distset_to_dpkg_profile_cfg(
 
 				kg_cfg->extracts[i].extract.from_hdr.prot =
 					NET_PROT_IP;
+				kg_cfg->extracts[i].extract.from_hdr.hdr_index =
+					hdr_index;
 				kg_cfg->extracts[i].extract.from_hdr.field =
 					NH_FLD_IP_DST;
 				kg_cfg->extracts[i].type =
@@ -393,6 +414,8 @@ dpaa2_distset_to_dpkg_profile_cfg(
 
 				kg_cfg->extracts[i].extract.from_hdr.prot =
 					NET_PROT_IP;
+				kg_cfg->extracts[i].extract.from_hdr.hdr_index =
+					hdr_index;
 				kg_cfg->extracts[i].extract.from_hdr.field =
 					NH_FLD_IP_PROTO;
 				kg_cfg->extracts[i].type =
diff --git a/drivers/net/dpaa2/dpaa2_ethdev.c b/drivers/net/dpaa2/dpaa2_ethdev.c
index 803a8321e0..c19736fb80 100644
--- a/drivers/net/dpaa2/dpaa2_ethdev.c
+++ b/drivers/net/dpaa2/dpaa2_ethdev.c
@@ -424,7 +424,8 @@ dpaa2_dev_info_get(struct rte_eth_dev *dev,
 	dev_info->max_hash_mac_addrs = 0;
 	dev_info->max_vfs = 0;
 	dev_info->max_vmdq_pools = RTE_ETH_16_POOLS;
-	dev_info->flow_type_rss_offloads = DPAA2_RSS_OFFLOAD_ALL;
+	dev_info->flow_type_rss_offloads = DPAA2_RSS_OFFLOAD_ALL |
+		RTE_ETH_RSS_LEVEL_OUTERMOST | RTE_ETH_RSS_LEVEL_INNERMOST;
 
 	dev_info->default_rxportconf.burst_size = dpaa2_dqrr_size;
 	/* same is rx size for best perf */
-- 
2.43.0

[PATCH 6/6] net/dpaa2: implement RSS RETA query and update

[Maxime Leroy]

DPAA2 dispatches RX frames to FQs using 'queue_id = hash % dist_size',
where dist_size is set per-TC via the dpni_set_rx_hash_dist MC command.
There is no software-visible indirection table, so the standard DPDK
RETA API has never been exposed by this PMD.

Implement reta_update / reta_query as an emulation on top of
dpni_set_rx_hash_dist. The emulation accepts only the uniform pattern
'reta[i] = i % N' for some N in the HW-allowed set (1, 2, 3, 4, 6, 7,
8, 12, 14, 16, 24, ...). Non-uniform or weighted patterns are rejected
with -ENOTSUP, as the HW has no arbitrary indirection table.

Changing N sets the size of the contiguous queue subset that RSS
spreads traffic over; the queues above N are left out of the hash
distribution. This covers the patterns that matter here, e.g. growing
or shrinking the active subset to scale CPU cores with load, or
reserving the upper queues for specific traffic that rte_flow steers
there for dedicated polling or QoS handling on its own core.

Refactor the existing dpaa2_setup_flow_dist() to delegate to a new
helper dpaa2_setup_flow_dist_size() that takes the dist_size explicitly
and caches it in priv->dist_size_cur[tc] so reta_query() can report it.

reta_query() returns reta[i] = i % N: this is representative, not
bit-exact, as the HW maps the hash to a queue through its distribution
size encoding rather than a plain modulo. reta_update() takes the RSS
hash set from dev_conf (rx_adv_conf.rss_conf.rss_hf); a prior
rss_hash_update() with a different hf is not re-read.

The advertised reta_size is 64 (one rte_eth_rss_reta_entry64 group), the
smallest legal value and enough for all HW-permitted N values up to 64.

Signed-off-by: Maxime Leroy <maxime@leroys.fr>
---
 doc/guides/nics/features/dpaa2.ini     |   1 +
 doc/guides/rel_notes/release_26_07.rst |   1 +
 drivers/net/dpaa2/base/dpaa2_hw_dpni.c |  34 +++--
 drivers/net/dpaa2/dpaa2_ethdev.c       | 201 +++++++++++++++++++++++++
 drivers/net/dpaa2/dpaa2_ethdev.h       |   9 ++
 5 files changed, 237 insertions(+), 9 deletions(-)

diff --git a/doc/guides/nics/features/dpaa2.ini b/doc/guides/nics/features/dpaa2.ini
index 5f9c587847..5def653d1d 100644
--- a/doc/guides/nics/features/dpaa2.ini
+++ b/doc/guides/nics/features/dpaa2.ini
@@ -15,6 +15,7 @@ Promiscuous mode     = Y
 Allmulticast mode    = Y
 Unicast MAC filter   = Y
 RSS hash             = Y
+RSS reta update      = Y
 VLAN filter          = Y
 Flow control         = Y
 Traffic manager      = Y
diff --git a/doc/guides/rel_notes/release_26_07.rst b/doc/guides/rel_notes/release_26_07.rst
index 39f3988198..b22ba4d6f0 100644
--- a/doc/guides/rel_notes/release_26_07.rst
+++ b/doc/guides/rel_notes/release_26_07.rst
@@ -143,6 +143,7 @@ New Features
 * **Updated NXP dpaa2 driver.**
 
   * Added inner RSS level support for tunnelled traffic.
+  * Added RSS RETA query and update support.
 
 * **Updated PCAP ethernet driver.**
 
diff --git a/drivers/net/dpaa2/base/dpaa2_hw_dpni.c b/drivers/net/dpaa2/base/dpaa2_hw_dpni.c
index 8a05253bbd..07f4a3d414 100644
--- a/drivers/net/dpaa2/base/dpaa2_hw_dpni.c
+++ b/drivers/net/dpaa2/base/dpaa2_hw_dpni.c
@@ -103,15 +103,10 @@ dpaa2_setup_flow_dist(struct rte_eth_dev *eth_dev,
 	uint64_t req_dist_set, int tc_index)
 {
 	struct dpaa2_dev_priv *priv = eth_dev->data->dev_private;
-	struct fsl_mc_io *dpni = eth_dev->process_private;
-	struct dpni_rx_dist_cfg tc_cfg;
-	struct dpkg_profile_cfg kg_cfg;
-	void *p_params;
-	int ret, tc_dist_queues;
+	int tc_dist_queues;
 
-	/*TC distribution size is set with dist_queues or
-	 * nb_rx_queues % dist_queues in order of TC priority index.
-	 * Calculating dist size for this tc_index:-
+	/* TC distribution size is set with dist_queues or
+	 * (nb_rx_queues - tc_index*dist_queues) in order of TC priority index.
 	 */
 	tc_dist_queues = eth_dev->data->nb_rx_queues -
 		tc_index * priv->dist_queues;
@@ -123,6 +118,24 @@ dpaa2_setup_flow_dist(struct rte_eth_dev *eth_dev,
 	if (tc_dist_queues > priv->dist_queues)
 		tc_dist_queues = priv->dist_queues;
 
+	return dpaa2_setup_flow_dist_size(eth_dev, req_dist_set,
+					   tc_index, tc_dist_queues);
+}
+
+int
+dpaa2_setup_flow_dist_size(struct rte_eth_dev *eth_dev,
+	uint64_t req_dist_set, int tc_index, uint16_t dist_size)
+{
+	struct dpaa2_dev_priv *priv = eth_dev->data->dev_private;
+	struct fsl_mc_io *dpni = eth_dev->process_private;
+	struct dpni_rx_dist_cfg tc_cfg;
+	struct dpkg_profile_cfg kg_cfg;
+	void *p_params;
+	int ret;
+
+	if (dist_size == 0)
+		return 0;
+
 	p_params = rte_malloc(NULL,
 		DIST_PARAM_IOVA_SIZE, RTE_CACHE_LINE_SIZE);
 	if (!p_params) {
@@ -150,7 +163,7 @@ dpaa2_setup_flow_dist(struct rte_eth_dev *eth_dev,
 		return -ENOBUFS;
 	}
 
-	tc_cfg.dist_size = tc_dist_queues;
+	tc_cfg.dist_size = dist_size;
 	tc_cfg.enable = true;
 	tc_cfg.tc = tc_index;
 
@@ -168,6 +181,9 @@ dpaa2_setup_flow_dist(struct rte_eth_dev *eth_dev,
 		return ret;
 	}
 
+	if (tc_index < MAX_TCS)
+		priv->dist_size_cur[tc_index] = dist_size;
+
 	return 0;
 }
 
diff --git a/drivers/net/dpaa2/dpaa2_ethdev.c b/drivers/net/dpaa2/dpaa2_ethdev.c
index c19736fb80..56682717cf 100644
--- a/drivers/net/dpaa2/dpaa2_ethdev.c
+++ b/drivers/net/dpaa2/dpaa2_ethdev.c
@@ -80,6 +80,33 @@ bool dpaa2_print_parser_result;
 #define MAX_NB_RX_DESC_IN_PEB	11264
 static int total_nb_rx_desc;
 
+/* Size of the RETA (Redirection Table) we expose to the standard DPDK API.
+ * Must be a multiple of RTE_ETH_RETA_GROUP_SIZE (64). DPAA2 has no actual
+ * indirection table in HW; this is the granularity at which uniform RSS
+ * patterns are inspected by dpaa2_dev_rss_reta_update().
+ */
+#define DPAA2_RETA_SIZE		64
+
+/* Values of dist_size accepted by the DPNI 'dpni_set_rx_hash_dist' MC command.
+ * Source: fsl_dpni.h, "struct dpni_rx_dist_cfg::dist_size" documentation.
+ * Used by dpaa2_dev_rss_reta_update() to validate user-requested patterns.
+ */
+static const uint16_t dpaa2_dist_size_allowed[] = {
+	1, 2, 3, 4, 6, 7, 8, 12, 14, 16, 24, 28, 32, 48, 56, 64,
+	96, 112, 128, 192, 224, 256, 384, 448, 512, 768, 896, 1024,
+};
+
+static bool
+dpaa2_dist_size_is_supported(uint16_t n)
+{
+	size_t i;
+	for (i = 0; i < RTE_DIM(dpaa2_dist_size_allowed); i++) {
+		if (dpaa2_dist_size_allowed[i] == n)
+			return true;
+	}
+	return false;
+}
+
 int dpaa2_valid_dev;
 struct rte_mempool *dpaa2_tx_sg_pool;
 
@@ -426,6 +453,14 @@ dpaa2_dev_info_get(struct rte_eth_dev *dev,
 	dev_info->max_vmdq_pools = RTE_ETH_16_POOLS;
 	dev_info->flow_type_rss_offloads = DPAA2_RSS_OFFLOAD_ALL |
 		RTE_ETH_RSS_LEVEL_OUTERMOST | RTE_ETH_RSS_LEVEL_INNERMOST;
+	/* DPAA2 has no software-visible indirection table: incoming packets are
+	 * dispatched to FQs via 'queue_id = hash % dist_size'. We expose the
+	 * standard RETA API as an emulation that only accepts uniform patterns
+	 * 'reta[i] = i % N' and translates them into a dpni_set_rx_hash_dist
+	 * command with dist_size=N. See dpaa2_dev_rss_reta_update().
+	 */
+	dev_info->reta_size = DPAA2_RETA_SIZE;
+	dev_info->hash_key_size = 0;
 
 	dev_info->default_rxportconf.burst_size = dpaa2_dqrr_size;
 	/* same is rx size for best perf */
@@ -2509,6 +2544,170 @@ dpaa2_dev_rss_hash_conf_get(struct rte_eth_dev *dev,
 	return 0;
 }
 
+/* Emulation of the standard DPDK RETA API on top of DPAA2's
+ * dpni_set_rx_hash_dist MC command.
+ *
+ * DPAA2 hardware dispatches incoming frames using 'queue_id = hash % dist_size'
+ * (no software-visible indirection table). To expose the standard
+ * rte_eth_dev_rss_reta_update() interface, we accept ONLY uniform patterns of
+ * the form 'reta[i] = i % N' where N is in the HW-allowed dist_size list. Any
+ * other pattern (weighted RSS, non-contiguous queue IDs, gaps) is rejected
+ * with -ENOTSUP. This is enough to support dynamic RSS scale-up/down across
+ * a contiguous queue subset, which is the main use case for adaptive
+ * dataplane CPU usage.
+ *
+ * Applies the new dist_size on every configured RX TC, mirroring the
+ * behavior of dpaa2_dev_rss_hash_update().
+ */
+static int
+dpaa2_dev_rss_reta_update(struct rte_eth_dev *dev,
+			  struct rte_eth_rss_reta_entry64 *reta_conf,
+			  uint16_t reta_size)
+{
+	struct dpaa2_dev_priv *priv = dev->data->dev_private;
+	struct rte_eth_conf *eth_conf = &dev->data->dev_conf;
+	uint16_t i, max_q = 0, n;
+	int tc_index, ret;
+	bool any_set = false;
+
+	PMD_INIT_FUNC_TRACE();
+
+	if (reta_size != DPAA2_RETA_SIZE) {
+		DPAA2_PMD_ERR("Invalid reta_size %u (expected %u)",
+			      reta_size, DPAA2_RETA_SIZE);
+		return -EINVAL;
+	}
+
+	/* dpaa2 cannot merge a partial RETA into the live table, so only a
+	 * full update (every entry of every group) is accepted.
+	 */
+	for (i = 0; i < reta_size / RTE_ETH_RETA_GROUP_SIZE; i++) {
+		if (reta_conf[i].mask != UINT64_MAX) {
+			DPAA2_PMD_ERR("partial RETA update not supported; set all %u entries",
+				      DPAA2_RETA_SIZE);
+			return -ENOTSUP;
+		}
+	}
+
+	/* First pass: validate queue IDs, find max, and require at least
+	 * one slot to be selected via the per-group mask.
+	 */
+	for (i = 0; i < reta_size; i++) {
+		uint16_t grp = i / RTE_ETH_RETA_GROUP_SIZE;
+		uint16_t pos = i % RTE_ETH_RETA_GROUP_SIZE;
+		uint16_t q;
+
+		if (!(reta_conf[grp].mask & (1ULL << pos)))
+			continue;
+		any_set = true;
+
+		q = reta_conf[grp].reta[pos];
+		if (q >= dev->data->nb_rx_queues) {
+			DPAA2_PMD_ERR("reta[%u] = %u out of range (max %u)",
+				i, q, dev->data->nb_rx_queues - 1);
+			return -EINVAL;
+		}
+		if (q > max_q)
+			max_q = q;
+	}
+
+	if (!any_set) {
+		DPAA2_PMD_WARN("reta_update called with empty mask, no-op");
+		return 0;
+	}
+
+	n = max_q + 1;
+
+	/* Second pass: enforce the uniform pattern reta[i] = i % n on every
+	 * slot the user has selected. dpaa2 HW cannot honor any other layout.
+	 */
+	for (i = 0; i < reta_size; i++) {
+		uint16_t grp = i / RTE_ETH_RETA_GROUP_SIZE;
+		uint16_t pos = i % RTE_ETH_RETA_GROUP_SIZE;
+		uint16_t expected = i % n;
+		uint16_t q;
+
+		if (!(reta_conf[grp].mask & (1ULL << pos)))
+			continue;
+
+		q = reta_conf[grp].reta[pos];
+		if (q != expected) {
+			DPAA2_PMD_ERR("Non-uniform RETA pattern at slot %u "
+				"(got queue %u, expected %u). dpaa2 HW "
+				"only supports queue_id = hash mod N with "
+				"contiguous queues 0..N-1.",
+				i, q, expected);
+			return -ENOTSUP;
+		}
+	}
+
+	if (!dpaa2_dist_size_is_supported(n)) {
+		DPAA2_PMD_ERR("dist_size %u not supported by HW. Allowed: "
+			"1,2,3,4,6,7,8,12,14,16,24,28,32,48,56,64,...",
+			n);
+		return -ENOTSUP;
+	}
+
+	/* Apply on every configured RX TC, matching rss_hash_update behavior. */
+	for (tc_index = 0; tc_index < priv->num_rx_tc; tc_index++) {
+		ret = dpaa2_setup_flow_dist_size(dev,
+				eth_conf->rx_adv_conf.rss_conf.rss_hf,
+				tc_index, n);
+		if (ret) {
+			DPAA2_PMD_ERR("Failed to apply dist_size=%u on tc%d (err=%d)",
+				n, tc_index, ret);
+			return ret;
+		}
+	}
+
+	DPAA2_PMD_DEBUG("RETA updated: dist_size now %u on %u TC(s)",
+			n, priv->num_rx_tc);
+	return 0;
+}
+
+/* Synthesizes a RETA snapshot from the currently-active dist_size on TC 0.
+ * Since DPAA2 always uses uniform 'hash mod N' distribution, the returned
+ * RETA is reta[i] = i % dist_size_cur[0].
+ */
+static int
+dpaa2_dev_rss_reta_query(struct rte_eth_dev *dev,
+			 struct rte_eth_rss_reta_entry64 *reta_conf,
+			 uint16_t reta_size)
+{
+	struct dpaa2_dev_priv *priv = dev->data->dev_private;
+	uint16_t i, n;
+
+	PMD_INIT_FUNC_TRACE();
+
+	if (reta_size != DPAA2_RETA_SIZE) {
+		DPAA2_PMD_ERR("Invalid reta_size %u (expected %u)",
+			      reta_size, DPAA2_RETA_SIZE);
+		return -EINVAL;
+	}
+
+	/* Use the cached dist_size on TC 0 (representative). Fall back to the
+	 * default (nb_rx_queues clamped to dist_queues) when never programmed.
+	 */
+	n = priv->dist_size_cur[0];
+	if (n == 0) {
+		n = priv->dist_queues;
+		if (n > dev->data->nb_rx_queues)
+			n = dev->data->nb_rx_queues;
+	}
+	if (n == 0)
+		return -EINVAL;
+
+	for (i = 0; i < reta_size; i++) {
+		uint16_t grp = i / RTE_ETH_RETA_GROUP_SIZE;
+		uint16_t pos = i % RTE_ETH_RETA_GROUP_SIZE;
+
+		if (reta_conf[grp].mask & (1ULL << pos))
+			reta_conf[grp].reta[pos] = i % n;
+	}
+
+	return 0;
+}
+
 RTE_EXPORT_INTERNAL_SYMBOL(dpaa2_eth_eventq_attach)
 int dpaa2_eth_eventq_attach(const struct rte_eth_dev *dev,
 		int eth_rx_queue_id,
@@ -2737,6 +2936,8 @@ static struct eth_dev_ops dpaa2_ethdev_ops = {
 	.mac_addr_set         = dpaa2_dev_set_mac_addr,
 	.rss_hash_update      = dpaa2_dev_rss_hash_update,
 	.rss_hash_conf_get    = dpaa2_dev_rss_hash_conf_get,
+	.reta_update          = dpaa2_dev_rss_reta_update,
+	.reta_query           = dpaa2_dev_rss_reta_query,
 	.flow_ops_get         = dpaa2_dev_flow_ops_get,
 	.rxq_info_get	      = dpaa2_rxq_info_get,
 	.txq_info_get	      = dpaa2_txq_info_get,
diff --git a/drivers/net/dpaa2/dpaa2_ethdev.h b/drivers/net/dpaa2/dpaa2_ethdev.h
index 4da47a543a..3f224c654e 100644
--- a/drivers/net/dpaa2/dpaa2_ethdev.h
+++ b/drivers/net/dpaa2/dpaa2_ethdev.h
@@ -412,6 +412,12 @@ struct dpaa2_dev_priv {
 	uint8_t max_cgs;
 	uint8_t cgid_in_use[MAX_RX_QUEUES];
 
+	/* Current hash distribution size per RX TC, written by
+	 * dpaa2_setup_flow_dist_size() and read by reta_query / reta_update.
+	 * Zero means "use default" (= nb_rx_queues clamped to dist_queues).
+	 */
+	uint16_t dist_size_cur[MAX_TCS];
+
 	uint16_t dpni_ver_major;
 	uint16_t dpni_ver_minor;
 	uint32_t speed_capa;
@@ -468,6 +474,9 @@ int dpaa2_distset_to_dpkg_profile_cfg(uint64_t req_dist_set,
 int dpaa2_setup_flow_dist(struct rte_eth_dev *eth_dev,
 		uint64_t req_dist_set, int tc_index);
 
+int dpaa2_setup_flow_dist_size(struct rte_eth_dev *eth_dev,
+		uint64_t req_dist_set, int tc_index, uint16_t dist_size);
+
 int dpaa2_remove_flow_dist(struct rte_eth_dev *eth_dev,
 			   uint8_t tc_index);
 
-- 
2.43.0

Re: [PATCH 0/6] net/dpaa2: RSS fixes and improvements

[Stephen Hemminger]

On Tue, 16 Jun 2026 12:47:09 +0200
Maxime Leroy <maxime@leroys.fr> wrote:

> A set of RSS fixes and improvements for the dpaa2 PMD.
> 
> Patches 1 and 2 fix the RSS hash key: the L4 destination port was never
> added (both extracts used the source port), and SCTP now uses the same L4
> port extraction as TCP/UDP. Both are tagged for stable.
> 
> Patches 3 and 4 are small cleanups in the key builder (a dead num_extracts
> increment, and the unset PPPoE guard flag).
> 
> Patch 5 honours RTE_ETH_RSS_LEVEL_INNERMOST so tunnelled traffic hashes on
> the inner IP header. Patch 6 implements reta_query / reta_update as an
> emulation over the HW distribution-size mechanism, since dpaa2 has no
> software-visible indirection table.
> 
> Tested on LX2160A (lx2160acex7).

Applied to next-net