[PATCH 0/2] iavf: use ptype for LLDP and add AVX2 ctx paths

[PATCH 0/2] iavf: use ptype for LLDP and add AVX2 ctx paths

[Ciara Loftus]

This series changes the iavf driver to use the mbuf packet type
field instead of a dynamic field for LLDP packets, and adds new AVX2
context descriptor Tx paths which support LLDP.

Ciara Loftus (2):
  net/iavf: use mbuf packet type instead of dynfield for LLDP
  net/iavf: add AVX2 context descriptor Tx paths

 doc/guides/nics/intel_vf.rst                |  16 +-
 doc/guides/rel_notes/release_26_03.rst      |   2 +
 drivers/net/intel/iavf/iavf.h               |   2 +
 drivers/net/intel/iavf/iavf_ethdev.c        |  13 +-
 drivers/net/intel/iavf/iavf_rxtx.c          |  21 +-
 drivers/net/intel/iavf/iavf_rxtx.h          |  12 +-
 drivers/net/intel/iavf/iavf_rxtx_vec_avx2.c | 386 ++++++++++++++++++++
 drivers/net/intel/iavf/iavf_testpmd.c       |  20 +-
 drivers/net/intel/iavf/rte_pmd_iavf.h       |  10 +
 9 files changed, 448 insertions(+), 34 deletions(-)

-- 
2.43.0

[PATCH 1/2] net/iavf: use mbuf packet type instead of dynfield for LLDP

[Ciara Loftus]

Instead of using a dynamic mbuf field to flag a packet as LLDP, instead
utilise the mbuf packet type field as the identifier instead. If the
type is RTE_PTYPE_L2_ETHER_LLDP the packet is identified as LLDP. This
approach is preferable because the use of dynamic mbuf fields should be
reserved for features that are not easily implemented using the existing
mbuf infrastructure. No negative performance impacts were observed with
the new approach.

Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
---
 doc/guides/nics/intel_vf.rst           | 16 +++++++++-------
 doc/guides/rel_notes/release_26_03.rst |  1 +
 drivers/net/intel/iavf/iavf_ethdev.c   | 13 ++++++++-----
 drivers/net/intel/iavf/iavf_rxtx.c     |  3 +--
 drivers/net/intel/iavf/iavf_rxtx.h     |  8 +++-----
 drivers/net/intel/iavf/iavf_testpmd.c  | 20 +++++---------------
 drivers/net/intel/iavf/rte_pmd_iavf.h  | 10 ++++++++++
 7 files changed, 37 insertions(+), 34 deletions(-)

diff --git a/doc/guides/nics/intel_vf.rst b/doc/guides/nics/intel_vf.rst
index bc600e4b58..197918b2e8 100644
--- a/doc/guides/nics/intel_vf.rst
+++ b/doc/guides/nics/intel_vf.rst
@@ -668,19 +668,21 @@ Inline IPsec Support
 Diagnostic Utilities
 --------------------
 
-Register mbuf dynfield to test Tx LLDP
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Enable Tx LLDP
+~~~~~~~~~~~~~~
 
-Register an mbuf dynfield ``IAVF_TX_LLDP_DYNFIELD`` on ``dev_start``
-to indicate the need to send LLDP packet.
-This dynfield needs to be set to 1 when preparing packet.
-
-For ``dpdk-testpmd`` application, it needs to stop and restart Tx port to take effect.
+In order for the iavf PMD to transmit LLDP packets, two conditions must be met:
+1. mbufs carrying LLDP packets must have their ptype set to RTE_PTYPE_L2_ETHER_LLDP
+2. LLDP needs to be explicitly enabled eg. via ``dpdk-testpmd``:
 
 Usage::
 
     testpmd> set tx lldp on
 
+Note: the feature should be enabled before the device is started, so that a transmit
+path that is capable of transmitting LLDP packets is selected ie. one that supports
+context descriptors.
+
 
 Limitations or Knowing issues
 -----------------------------
diff --git a/doc/guides/rel_notes/release_26_03.rst b/doc/guides/rel_notes/release_26_03.rst
index a0f89b5ea2..c58c5cebd0 100644
--- a/doc/guides/rel_notes/release_26_03.rst
+++ b/doc/guides/rel_notes/release_26_03.rst
@@ -62,6 +62,7 @@ New Features
 * **Updated Intel iavf driver.**
 
   * Added support for pre and post VF reset callbacks.
+  * Changed LLDP packet detection from dynamic mbuf field to mbuf packet_type.
 
 
 Removed Items
diff --git a/drivers/net/intel/iavf/iavf_ethdev.c b/drivers/net/intel/iavf/iavf_ethdev.c
index 802e095174..ae5fd86171 100644
--- a/drivers/net/intel/iavf/iavf_ethdev.c
+++ b/drivers/net/intel/iavf/iavf_ethdev.c
@@ -45,7 +45,7 @@
 #define IAVF_MBUF_CHECK_ARG       "mbuf_check"
 uint64_t iavf_timestamp_dynflag;
 int iavf_timestamp_dynfield_offset = -1;
-int rte_pmd_iavf_tx_lldp_dynfield_offset = -1;
+bool iavf_tx_lldp_enabled;
 
 static const char * const iavf_valid_args[] = {
 	IAVF_PROTO_XTR_ARG,
@@ -1024,10 +1024,6 @@ iavf_dev_start(struct rte_eth_dev *dev)
 		}
 	}
 
-	/* Check Tx LLDP dynfield */
-	rte_pmd_iavf_tx_lldp_dynfield_offset =
-		rte_mbuf_dynfield_lookup(IAVF_TX_LLDP_DYNFIELD, NULL);
-
 	if (iavf_init_queues(dev) != 0) {
 		PMD_DRV_LOG(ERR, "failed to do Queue init");
 		return -1;
@@ -3203,6 +3199,13 @@ rte_pmd_iavf_reinit(uint16_t port)
 	return 0;
 }
 
+RTE_EXPORT_EXPERIMENTAL_SYMBOL(rte_pmd_iavf_enable_tx_lldp, 26.03)
+void
+rte_pmd_iavf_enable_tx_lldp(bool enable)
+{
+	iavf_tx_lldp_enabled = enable;
+}
+
 static int
 iavf_validate_reset_cb(uint16_t port, void *cb, void *cb_arg)
 {
diff --git a/drivers/net/intel/iavf/iavf_rxtx.c b/drivers/net/intel/iavf/iavf_rxtx.c
index 4b763627bc..2fdd0f5ffe 100644
--- a/drivers/net/intel/iavf/iavf_rxtx.c
+++ b/drivers/net/intel/iavf/iavf_rxtx.c
@@ -4243,8 +4243,7 @@ iavf_set_tx_function(struct rte_eth_dev *dev)
 	if (iavf_tx_vec_dev_check(dev) != -1)
 		req_features.simd_width = iavf_get_max_simd_bitwidth();
 
-	if (rte_pmd_iavf_tx_lldp_dynfield_offset > 0)
-		req_features.ctx_desc = true;
+	req_features.ctx_desc = iavf_tx_lldp_enabled;
 
 	for (i = 0; i < dev->data->nb_tx_queues; i++) {
 		txq = dev->data->tx_queues[i];
diff --git a/drivers/net/intel/iavf/iavf_rxtx.h b/drivers/net/intel/iavf/iavf_rxtx.h
index e1f78dcde0..f8d75abe35 100644
--- a/drivers/net/intel/iavf/iavf_rxtx.h
+++ b/drivers/net/intel/iavf/iavf_rxtx.h
@@ -168,14 +168,12 @@
 
 #define IAVF_TX_LLDP_DYNFIELD "intel_pmd_dynfield_tx_lldp"
 #define IAVF_CHECK_TX_LLDP(m) \
-	((rte_pmd_iavf_tx_lldp_dynfield_offset > 0) && \
-	(*RTE_MBUF_DYNFIELD((m), \
-			rte_pmd_iavf_tx_lldp_dynfield_offset, \
-			uint8_t *)))
+	(iavf_tx_lldp_enabled && \
+	((m)->packet_type & RTE_PTYPE_L2_MASK) == RTE_PTYPE_L2_ETHER_LLDP)
 
 extern uint64_t iavf_timestamp_dynflag;
 extern int iavf_timestamp_dynfield_offset;
-extern int rte_pmd_iavf_tx_lldp_dynfield_offset;
+extern bool iavf_tx_lldp_enabled;
 
 typedef void (*iavf_rxd_to_pkt_fields_t)(struct ci_rx_queue *rxq,
 				struct rte_mbuf *mb,
diff --git a/drivers/net/intel/iavf/iavf_testpmd.c b/drivers/net/intel/iavf/iavf_testpmd.c
index 4731d0b61b..44dc568e91 100644
--- a/drivers/net/intel/iavf/iavf_testpmd.c
+++ b/drivers/net/intel/iavf/iavf_testpmd.c
@@ -39,21 +39,11 @@ cmd_enable_tx_lldp_parsed(void *parsed_result,
 	__rte_unused struct cmdline *cl, __rte_unused void *data)
 {
 	struct cmd_enable_tx_lldp_result *res = parsed_result;
-	const struct rte_mbuf_dynfield iavf_tx_lldp_dynfield = {
-		.name = IAVF_TX_LLDP_DYNFIELD,
-		.size = sizeof(uint8_t),
-		.align = alignof(uint8_t),
-		.flags = 0
-	};
-	int offset;
-
-	if (strncmp(res->what, "on", 2) == 0) {
-		offset = rte_mbuf_dynfield_register(&iavf_tx_lldp_dynfield);
-		printf("rte_pmd_iavf_tx_lldp_dynfield_offset: %d", offset);
-		if (offset < 0)
-			fprintf(stderr,
-				"rte mbuf dynfield register failed, offset: %d", offset);
-	}
+	bool enable = strncmp(res->what, "on", 2) == 0;
+
+	rte_pmd_iavf_enable_tx_lldp(enable);
+
+	printf("Tx LLDP %s on iavf driver\n", enable ? "enabled" : "disabled");
 }
 
 static cmdline_parse_inst_t cmd_enable_tx_lldp = {
diff --git a/drivers/net/intel/iavf/rte_pmd_iavf.h b/drivers/net/intel/iavf/rte_pmd_iavf.h
index df4e947e85..2ae83dcbce 100644
--- a/drivers/net/intel/iavf/rte_pmd_iavf.h
+++ b/drivers/net/intel/iavf/rte_pmd_iavf.h
@@ -154,6 +154,16 @@ int rte_pmd_iavf_register_post_reset_cb(uint16_t port,
 					iavf_post_reset_cb_t post_reset_cb,
 					void *post_reset_cb_arg);
 
+/**
+ * Enable or disable Tx LLDP on the iavf driver.
+ *
+ * @param enable
+ *   Set to true to enable Tx LLDP, false to disable.
+ */
+__rte_experimental
+void
+rte_pmd_iavf_enable_tx_lldp(bool enable);
+
 /**
  * The mbuf dynamic field pointer for flexible descriptor's extraction metadata.
  */
-- 
2.43.0

[PATCH 2/2] net/iavf: add AVX2 context descriptor Tx paths

[Ciara Loftus]

Prior to this commit the transmit paths implemented for AVX2 used the
transmit descriptor only, making some offloads and features unavailable
on the AVX2 path, like LLDP. Enable two new AVX2 transmit paths, both
of which support using a context descriptor, one which performs offload
and the other which does not.

Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
---
 doc/guides/rel_notes/release_26_03.rst      |   1 +
 drivers/net/intel/iavf/iavf.h               |   2 +
 drivers/net/intel/iavf/iavf_rxtx.c          |  18 +
 drivers/net/intel/iavf/iavf_rxtx.h          |   4 +
 drivers/net/intel/iavf/iavf_rxtx_vec_avx2.c | 386 ++++++++++++++++++++
 5 files changed, 411 insertions(+)

diff --git a/doc/guides/rel_notes/release_26_03.rst b/doc/guides/rel_notes/release_26_03.rst
index c58c5cebd0..3b16f0b00c 100644
--- a/doc/guides/rel_notes/release_26_03.rst
+++ b/doc/guides/rel_notes/release_26_03.rst
@@ -63,6 +63,7 @@ New Features
 
   * Added support for pre and post VF reset callbacks.
   * Changed LLDP packet detection from dynamic mbuf field to mbuf packet_type.
+  * Implemented AVX2 context descriptor transmit paths.
 
 
 Removed Items
diff --git a/drivers/net/intel/iavf/iavf.h b/drivers/net/intel/iavf/iavf.h
index 39949acc11..d4dd48d520 100644
--- a/drivers/net/intel/iavf/iavf.h
+++ b/drivers/net/intel/iavf/iavf.h
@@ -357,6 +357,8 @@ enum iavf_tx_func_type {
 	IAVF_TX_DEFAULT,
 	IAVF_TX_AVX2,
 	IAVF_TX_AVX2_OFFLOAD,
+	IAVF_TX_AVX2_CTX,
+	IAVF_TX_AVX2_CTX_OFFLOAD,
 	IAVF_TX_AVX512,
 	IAVF_TX_AVX512_OFFLOAD,
 	IAVF_TX_AVX512_CTX,
diff --git a/drivers/net/intel/iavf/iavf_rxtx.c b/drivers/net/intel/iavf/iavf_rxtx.c
index 2fdd0f5ffe..6effc97c07 100644
--- a/drivers/net/intel/iavf/iavf_rxtx.c
+++ b/drivers/net/intel/iavf/iavf_rxtx.c
@@ -3974,6 +3974,24 @@ static const struct ci_tx_path_info iavf_tx_path_infos[] = {
 			.simd_width = RTE_VECT_SIMD_256
 		}
 	},
+	[IAVF_TX_AVX2_CTX] = {
+		.pkt_burst = iavf_xmit_pkts_vec_avx2_ctx,
+		.info = "Vector AVX2 Ctx",
+		.features = {
+			.tx_offloads = IAVF_TX_VECTOR_OFFLOADS,
+			.simd_width = RTE_VECT_SIMD_256,
+			.ctx_desc = true
+		}
+	},
+	[IAVF_TX_AVX2_CTX_OFFLOAD] = {
+		.pkt_burst = iavf_xmit_pkts_vec_avx2_ctx_offload,
+		.info = "Vector AVX2 Ctx Offload",
+		.features = {
+			.tx_offloads = IAVF_TX_VECTOR_CTX_OFFLOAD_OFFLOADS,
+			.simd_width = RTE_VECT_SIMD_256,
+			.ctx_desc = true
+		}
+	},
 #ifdef CC_AVX512_SUPPORT
 	[IAVF_TX_AVX512] = {
 		.pkt_burst = iavf_xmit_pkts_vec_avx512,
diff --git a/drivers/net/intel/iavf/iavf_rxtx.h b/drivers/net/intel/iavf/iavf_rxtx.h
index f8d75abe35..147f1d03f1 100644
--- a/drivers/net/intel/iavf/iavf_rxtx.h
+++ b/drivers/net/intel/iavf/iavf_rxtx.h
@@ -609,6 +609,10 @@ uint16_t iavf_xmit_pkts_vec_avx2(void *tx_queue, struct rte_mbuf **tx_pkts,
 				 uint16_t nb_pkts);
 uint16_t iavf_xmit_pkts_vec_avx2_offload(void *tx_queue, struct rte_mbuf **tx_pkts,
 					 uint16_t nb_pkts);
+uint16_t iavf_xmit_pkts_vec_avx2_ctx(void *tx_queue, struct rte_mbuf **tx_pkts,
+				  uint16_t nb_pkts);
+uint16_t iavf_xmit_pkts_vec_avx2_ctx_offload(void *tx_queue, struct rte_mbuf **tx_pkts,
+				  uint16_t nb_pkts);
 int iavf_get_monitor_addr(void *rx_queue, struct rte_power_monitor_cond *pmc);
 int iavf_rx_vec_dev_check(struct rte_eth_dev *dev);
 int iavf_tx_vec_dev_check(struct rte_eth_dev *dev);
diff --git a/drivers/net/intel/iavf/iavf_rxtx_vec_avx2.c b/drivers/net/intel/iavf/iavf_rxtx_vec_avx2.c
index e29958e0bc..8c2bc73819 100644
--- a/drivers/net/intel/iavf/iavf_rxtx_vec_avx2.c
+++ b/drivers/net/intel/iavf/iavf_rxtx_vec_avx2.c
@@ -1774,6 +1774,392 @@ iavf_xmit_fixed_burst_vec_avx2(void *tx_queue, struct rte_mbuf **tx_pkts,
 	return nb_pkts;
 }
 
+static inline void
+iavf_fill_ctx_desc_tunneling_avx2(uint64_t *low_ctx_qw, struct rte_mbuf *pkt)
+{
+	if (pkt->ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK) {
+		uint64_t eip_typ = IAVF_TX_CTX_DESC_EIPT_NONE;
+		uint64_t eip_len = 0;
+		uint64_t eip_noinc = 0;
+		/* Default - IP_ID is increment in each segment of LSO */
+
+		switch (pkt->ol_flags & (RTE_MBUF_F_TX_OUTER_IPV4 |
+				RTE_MBUF_F_TX_OUTER_IPV6 |
+				RTE_MBUF_F_TX_OUTER_IP_CKSUM)) {
+		case RTE_MBUF_F_TX_OUTER_IPV4:
+			eip_typ = IAVF_TX_CTX_DESC_EIPT_IPV4_NO_CHECKSUM_OFFLOAD;
+			eip_len = pkt->outer_l3_len >> 2;
+		break;
+		case RTE_MBUF_F_TX_OUTER_IPV4 | RTE_MBUF_F_TX_OUTER_IP_CKSUM:
+			eip_typ = IAVF_TX_CTX_DESC_EIPT_IPV4_CHECKSUM_OFFLOAD;
+			eip_len = pkt->outer_l3_len >> 2;
+		break;
+		case RTE_MBUF_F_TX_OUTER_IPV6:
+			eip_typ = IAVF_TX_CTX_DESC_EIPT_IPV6;
+			eip_len = pkt->outer_l3_len >> 2;
+		break;
+		}
+
+		/* L4TUNT: L4 Tunneling Type */
+		switch (pkt->ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK) {
+		case RTE_MBUF_F_TX_TUNNEL_IPIP:
+			/* for non UDP / GRE tunneling, set to 00b */
+			break;
+		case RTE_MBUF_F_TX_TUNNEL_VXLAN:
+		case RTE_MBUF_F_TX_TUNNEL_VXLAN_GPE:
+		case RTE_MBUF_F_TX_TUNNEL_GTP:
+		case RTE_MBUF_F_TX_TUNNEL_GENEVE:
+			eip_typ |= IAVF_TXD_CTX_UDP_TUNNELING;
+			break;
+		case RTE_MBUF_F_TX_TUNNEL_GRE:
+			eip_typ |= IAVF_TXD_CTX_GRE_TUNNELING;
+			break;
+		default:
+			PMD_TX_LOG(ERR, "Tunnel type not supported");
+			return;
+		}
+
+		/* L4TUNLEN: L4 Tunneling Length, in Words
+		 *
+		 * We depend on app to set rte_mbuf.l2_len correctly.
+		 * For IP in GRE it should be set to the length of the GRE
+		 * header;
+		 * For MAC in GRE or MAC in UDP it should be set to the length
+		 * of the GRE or UDP headers plus the inner MAC up to including
+		 * its last Ethertype.
+		 * If MPLS labels exists, it should include them as well.
+		 */
+		eip_typ |= (pkt->l2_len >> 1) << IAVF_TXD_CTX_QW0_NATLEN_SHIFT;
+
+		/**
+		 * Calculate the tunneling UDP checksum.
+		 * Shall be set only if L4TUNT = 01b and EIPT is not zero
+		 */
+		if ((eip_typ & (IAVF_TX_CTX_EXT_IP_IPV4 |
+					IAVF_TX_CTX_EXT_IP_IPV6 |
+					IAVF_TX_CTX_EXT_IP_IPV4_NO_CSUM)) &&
+				(eip_typ & IAVF_TXD_CTX_UDP_TUNNELING) &&
+				(pkt->ol_flags & RTE_MBUF_F_TX_OUTER_UDP_CKSUM))
+			eip_typ |= IAVF_TXD_CTX_QW0_L4T_CS_MASK;
+
+		*low_ctx_qw = eip_typ << IAVF_TXD_CTX_QW0_TUN_PARAMS_EIPT_SHIFT |
+			eip_len << IAVF_TXD_CTX_QW0_TUN_PARAMS_EIPLEN_SHIFT |
+			eip_noinc << IAVF_TXD_CTX_QW0_TUN_PARAMS_EIP_NOINC_SHIFT;
+
+	} else {
+		*low_ctx_qw = 0;
+	}
+}
+
+static inline void
+iavf_fill_ctx_desc_tunneling_field(volatile uint64_t *qw0,
+		const struct rte_mbuf *m)
+{
+	uint64_t eip_typ = IAVF_TX_CTX_DESC_EIPT_NONE;
+	uint64_t eip_len = 0;
+	uint64_t eip_noinc = 0;
+	/* Default - IP_ID is increment in each segment of LSO */
+
+	switch (m->ol_flags & (RTE_MBUF_F_TX_OUTER_IPV4 |
+			RTE_MBUF_F_TX_OUTER_IPV6 |
+			RTE_MBUF_F_TX_OUTER_IP_CKSUM)) {
+	case RTE_MBUF_F_TX_OUTER_IPV4:
+		eip_typ = IAVF_TX_CTX_DESC_EIPT_IPV4_NO_CHECKSUM_OFFLOAD;
+		eip_len = m->outer_l3_len >> 2;
+	break;
+	case RTE_MBUF_F_TX_OUTER_IPV4 | RTE_MBUF_F_TX_OUTER_IP_CKSUM:
+		eip_typ = IAVF_TX_CTX_DESC_EIPT_IPV4_CHECKSUM_OFFLOAD;
+		eip_len = m->outer_l3_len >> 2;
+	break;
+	case RTE_MBUF_F_TX_OUTER_IPV6:
+		eip_typ = IAVF_TX_CTX_DESC_EIPT_IPV6;
+		eip_len = m->outer_l3_len >> 2;
+	break;
+	}
+
+	/* L4TUNT: L4 Tunneling Type */
+	switch (m->ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK) {
+	case RTE_MBUF_F_TX_TUNNEL_IPIP:
+		/* for non UDP / GRE tunneling, set to 00b */
+		break;
+	case RTE_MBUF_F_TX_TUNNEL_VXLAN:
+	case RTE_MBUF_F_TX_TUNNEL_VXLAN_GPE:
+	case RTE_MBUF_F_TX_TUNNEL_GTP:
+	case RTE_MBUF_F_TX_TUNNEL_GENEVE:
+		eip_typ |= IAVF_TXD_CTX_UDP_TUNNELING;
+		break;
+	case RTE_MBUF_F_TX_TUNNEL_GRE:
+		eip_typ |= IAVF_TXD_CTX_GRE_TUNNELING;
+		break;
+	default:
+		PMD_TX_LOG(ERR, "Tunnel type not supported");
+		return;
+	}
+
+	/* L4TUNLEN: L4 Tunneling Length, in Words
+	 *
+	 * We depend on app to set rte_mbuf.l2_len correctly.
+	 * For IP in GRE it should be set to the length of the GRE
+	 * header;
+	 * For MAC in GRE or MAC in UDP it should be set to the length
+	 * of the GRE or UDP headers plus the inner MAC up to including
+	 * its last Ethertype.
+	 * If MPLS labels exists, it should include them as well.
+	 */
+	eip_typ |= (m->l2_len >> 1) << IAVF_TXD_CTX_QW0_NATLEN_SHIFT;
+
+	/**
+	 * Calculate the tunneling UDP checksum.
+	 * Shall be set only if L4TUNT = 01b and EIPT is not zero
+	 */
+	if ((eip_typ & (IAVF_TX_CTX_EXT_IP_IPV6 |
+				IAVF_TX_CTX_EXT_IP_IPV4 |
+				IAVF_TX_CTX_EXT_IP_IPV4_NO_CSUM)) &&
+			(eip_typ & IAVF_TXD_CTX_UDP_TUNNELING) &&
+			(m->ol_flags & RTE_MBUF_F_TX_OUTER_UDP_CKSUM))
+		eip_typ |= IAVF_TXD_CTX_QW0_L4T_CS_MASK;
+
+	*qw0 = eip_typ << IAVF_TXD_CTX_QW0_TUN_PARAMS_EIPT_SHIFT |
+		eip_len << IAVF_TXD_CTX_QW0_TUN_PARAMS_EIPLEN_SHIFT |
+		eip_noinc << IAVF_TXD_CTX_QW0_TUN_PARAMS_EIP_NOINC_SHIFT;
+}
+
+static __rte_always_inline void
+ctx_vtx1(volatile struct iavf_tx_desc *txdp, struct rte_mbuf *pkt,
+		uint64_t flags, bool offload, uint8_t vlan_flag)
+{
+	uint64_t high_ctx_qw = IAVF_TX_DESC_DTYPE_CONTEXT;
+	uint64_t low_ctx_qw = 0;
+
+	if (offload) {
+		iavf_fill_ctx_desc_tunneling_avx2(&low_ctx_qw, pkt);
+#ifdef IAVF_TX_VLAN_QINQ_OFFLOAD
+		if (pkt->ol_flags & RTE_MBUF_F_TX_QINQ) {
+			uint64_t qinq_tag = vlan_flag & IAVF_TX_FLAGS_VLAN_TAG_LOC_L2TAG2 ?
+				(uint64_t)pkt->vlan_tci_outer :
+				(uint64_t)pkt->vlan_tci;
+			high_ctx_qw |= IAVF_TX_CTX_DESC_IL2TAG2 << IAVF_TXD_CTX_QW1_CMD_SHIFT;
+			low_ctx_qw |= qinq_tag << IAVF_TXD_CTX_QW0_L2TAG2_PARAM;
+		} else if ((pkt->ol_flags & RTE_MBUF_F_TX_VLAN) &&
+				vlan_flag & IAVF_TX_FLAGS_VLAN_TAG_LOC_L2TAG2) {
+			high_ctx_qw |= IAVF_TX_CTX_DESC_IL2TAG2 << IAVF_TXD_CTX_QW1_CMD_SHIFT;
+			low_ctx_qw |= (uint64_t)pkt->vlan_tci << IAVF_TXD_CTX_QW0_L2TAG2_PARAM;
+		}
+#endif
+	}
+	if (IAVF_CHECK_TX_LLDP(pkt))
+		high_ctx_qw |= IAVF_TX_CTX_DESC_SWTCH_UPLINK << IAVF_TXD_CTX_QW1_CMD_SHIFT;
+	uint64_t high_data_qw = (IAVF_TX_DESC_DTYPE_DATA |
+				((uint64_t)flags  << IAVF_TXD_QW1_CMD_SHIFT) |
+				((uint64_t)pkt->data_len << IAVF_TXD_QW1_TX_BUF_SZ_SHIFT));
+	if (offload)
+		iavf_txd_enable_offload(pkt, &high_data_qw, vlan_flag);
+
+	__m256i ctx_data_desc = _mm256_set_epi64x(high_data_qw, pkt->buf_iova + pkt->data_off,
+							high_ctx_qw, low_ctx_qw);
+
+	_mm256_storeu_si256(RTE_CAST_PTR(__m256i *, txdp), ctx_data_desc);
+}
+
+static __rte_always_inline void
+ctx_vtx(volatile struct iavf_tx_desc *txdp,
+		struct rte_mbuf **pkt, uint16_t nb_pkts,  uint64_t flags,
+		bool offload, uint8_t vlan_flag)
+{
+	uint64_t hi_data_qw_tmpl = (IAVF_TX_DESC_DTYPE_DATA |
+					((uint64_t)flags  << IAVF_TXD_QW1_CMD_SHIFT));
+
+	/* if unaligned on 32-bit boundary, do one to align */
+	if (((uintptr_t)txdp & 0x1F) != 0 && nb_pkts != 0) {
+		ctx_vtx1(txdp, *pkt, flags, offload, vlan_flag);
+		nb_pkts--, txdp++, pkt++;
+	}
+
+	for (; nb_pkts > 1; txdp += 4, pkt += 2, nb_pkts -= 2) {
+		uint64_t hi_ctx_qw1 = IAVF_TX_DESC_DTYPE_CONTEXT;
+		uint64_t hi_ctx_qw0 = IAVF_TX_DESC_DTYPE_CONTEXT;
+		uint64_t low_ctx_qw1 = 0;
+		uint64_t low_ctx_qw0 = 0;
+		uint64_t hi_data_qw1 = 0;
+		uint64_t hi_data_qw0 = 0;
+
+		hi_data_qw1 = hi_data_qw_tmpl |
+				((uint64_t)pkt[1]->data_len <<
+					IAVF_TXD_QW1_TX_BUF_SZ_SHIFT);
+		hi_data_qw0 = hi_data_qw_tmpl |
+				((uint64_t)pkt[0]->data_len <<
+					IAVF_TXD_QW1_TX_BUF_SZ_SHIFT);
+
+#ifdef IAVF_TX_VLAN_QINQ_OFFLOAD
+		if (offload) {
+			if (pkt[1]->ol_flags & RTE_MBUF_F_TX_QINQ) {
+				uint64_t qinq_tag = vlan_flag & IAVF_TX_FLAGS_VLAN_TAG_LOC_L2TAG2 ?
+					(uint64_t)pkt[1]->vlan_tci :
+					(uint64_t)pkt[1]->vlan_tci_outer;
+				hi_ctx_qw1 |= IAVF_TX_CTX_DESC_IL2TAG2 <<
+						IAVF_TXD_CTX_QW1_CMD_SHIFT;
+				low_ctx_qw1 |= qinq_tag << IAVF_TXD_CTX_QW0_L2TAG2_PARAM;
+			} else if (pkt[1]->ol_flags & RTE_MBUF_F_TX_VLAN &&
+					vlan_flag & IAVF_TX_FLAGS_VLAN_TAG_LOC_L2TAG2) {
+				hi_ctx_qw1 |=
+					IAVF_TX_CTX_DESC_IL2TAG2 << IAVF_TXD_CTX_QW1_CMD_SHIFT;
+				low_ctx_qw1 |=
+					(uint64_t)pkt[1]->vlan_tci << IAVF_TXD_CTX_QW0_L2TAG2_PARAM;
+			}
+		}
+#endif
+		if (IAVF_CHECK_TX_LLDP(pkt[1]))
+			hi_ctx_qw1 |= IAVF_TX_CTX_DESC_SWTCH_UPLINK << IAVF_TXD_CTX_QW1_CMD_SHIFT;
+
+#ifdef IAVF_TX_VLAN_QINQ_OFFLOAD
+		if (offload) {
+			if (pkt[0]->ol_flags & RTE_MBUF_F_TX_QINQ) {
+				uint64_t qinq_tag = vlan_flag & IAVF_TX_FLAGS_VLAN_TAG_LOC_L2TAG2 ?
+					(uint64_t)pkt[0]->vlan_tci :
+					(uint64_t)pkt[0]->vlan_tci_outer;
+				hi_ctx_qw0 |= IAVF_TX_CTX_DESC_IL2TAG2 <<
+						IAVF_TXD_CTX_QW1_CMD_SHIFT;
+				low_ctx_qw0 |= qinq_tag << IAVF_TXD_CTX_QW0_L2TAG2_PARAM;
+			} else if (pkt[0]->ol_flags & RTE_MBUF_F_TX_VLAN &&
+					vlan_flag & IAVF_TX_FLAGS_VLAN_TAG_LOC_L2TAG2) {
+				hi_ctx_qw0 |=
+					IAVF_TX_CTX_DESC_IL2TAG2 << IAVF_TXD_CTX_QW1_CMD_SHIFT;
+				low_ctx_qw0 |=
+					(uint64_t)pkt[0]->vlan_tci << IAVF_TXD_CTX_QW0_L2TAG2_PARAM;
+			}
+		}
+#endif
+		if (IAVF_CHECK_TX_LLDP(pkt[0]))
+			hi_ctx_qw0 |= IAVF_TX_CTX_DESC_SWTCH_UPLINK << IAVF_TXD_CTX_QW1_CMD_SHIFT;
+
+		if (offload) {
+			iavf_txd_enable_offload(pkt[1], &hi_data_qw1, vlan_flag);
+			iavf_txd_enable_offload(pkt[0], &hi_data_qw0, vlan_flag);
+			iavf_fill_ctx_desc_tunneling_field(&low_ctx_qw1, pkt[1]);
+			iavf_fill_ctx_desc_tunneling_field(&low_ctx_qw0, pkt[0]);
+		}
+
+		__m256i desc2_3 =
+			_mm256_set_epi64x
+				(hi_data_qw1, pkt[1]->buf_iova + pkt[1]->data_off,
+				 hi_ctx_qw1, low_ctx_qw1);
+		__m256i desc0_1 =
+			_mm256_set_epi64x
+				(hi_data_qw0, pkt[0]->buf_iova + pkt[0]->data_off,
+				 hi_ctx_qw0, low_ctx_qw0);
+		_mm256_store_si256(RTE_CAST_PTR(__m256i *, txdp + 2), desc2_3);
+		_mm256_store_si256(RTE_CAST_PTR(__m256i *, txdp), desc0_1);
+	}
+
+	if (nb_pkts)
+		ctx_vtx1(txdp, *pkt, flags, offload, vlan_flag);
+}
+
+static __rte_always_inline uint16_t
+iavf_xmit_fixed_burst_vec_avx2_ctx(void *tx_queue, struct rte_mbuf **tx_pkts,
+				 uint16_t nb_pkts, bool offload)
+{
+	struct ci_tx_queue *txq = (struct ci_tx_queue *)tx_queue;
+	volatile struct iavf_tx_desc *txdp;
+	struct ci_tx_entry_vec *txep;
+	uint16_t n, nb_commit, nb_mbuf, tx_id;
+	/* bit2 is reserved and must be set to 1 according to Spec */
+	uint64_t flags = IAVF_TX_DESC_CMD_EOP | IAVF_TX_DESC_CMD_ICRC;
+	uint64_t rs = IAVF_TX_DESC_CMD_RS | flags;
+
+	if (txq->nb_tx_free < txq->tx_free_thresh)
+		ci_tx_free_bufs_vec(txq, iavf_tx_desc_done, true);
+
+	nb_commit = (uint16_t)RTE_MIN(txq->nb_tx_free, nb_pkts << 1);
+	nb_commit &= 0xFFFE;
+	if (unlikely(nb_commit == 0))
+		return 0;
+
+	nb_pkts = nb_commit >> 1;
+	tx_id = txq->tx_tail;
+	txdp = &txq->iavf_tx_ring[tx_id];
+	txep = (void *)txq->sw_ring;
+	txep += (tx_id >> 1);
+
+	txq->nb_tx_free = (uint16_t)(txq->nb_tx_free - nb_commit);
+	n = (uint16_t)(txq->nb_tx_desc - tx_id);
+
+	if (n != 0 && nb_commit >= n) {
+		nb_mbuf = n >> 1;
+		ci_tx_backlog_entry_vec(txep, tx_pkts, nb_mbuf);
+
+		ctx_vtx(txdp, tx_pkts, nb_mbuf - 1, flags, offload, txq->vlan_flag);
+		tx_pkts += (nb_mbuf - 1);
+		txdp += (n - 2);
+		ctx_vtx1(txdp, *tx_pkts++, rs, offload, txq->vlan_flag);
+
+		nb_commit = (uint16_t)(nb_commit - n);
+
+		txq->tx_next_rs = (uint16_t)(txq->tx_rs_thresh - 1);
+		tx_id = 0;
+		/* avoid reach the end of ring */
+		txdp = txq->iavf_tx_ring;
+		txep = (void *)txq->sw_ring;
+	}
+
+	nb_mbuf = nb_commit >> 1;
+	ci_tx_backlog_entry_vec(txep, tx_pkts, nb_mbuf);
+
+	ctx_vtx(txdp, tx_pkts, nb_mbuf, flags, offload, txq->vlan_flag);
+	tx_id = (uint16_t)(tx_id + nb_commit);
+
+	if (tx_id > txq->tx_next_rs) {
+		txq->iavf_tx_ring[txq->tx_next_rs].cmd_type_offset_bsz |=
+			rte_cpu_to_le_64(((uint64_t)IAVF_TX_DESC_CMD_RS) <<
+					 IAVF_TXD_QW1_CMD_SHIFT);
+		txq->tx_next_rs =
+			(uint16_t)(txq->tx_next_rs + txq->tx_rs_thresh);
+	}
+
+	txq->tx_tail = tx_id;
+
+	IAVF_PCI_REG_WC_WRITE(txq->qtx_tail, txq->tx_tail);
+	return nb_pkts;
+}
+
+static __rte_always_inline uint16_t
+iavf_xmit_pkts_vec_avx2_ctx_cmn(void *tx_queue, struct rte_mbuf **tx_pkts,
+				  uint16_t nb_pkts, bool offload)
+{
+	uint16_t nb_tx = 0;
+	struct ci_tx_queue *txq = (struct ci_tx_queue *)tx_queue;
+
+	while (nb_pkts) {
+		uint16_t ret, num;
+
+		/* cross rs_thresh boundary is not allowed */
+		num = (uint16_t)RTE_MIN(nb_pkts << 1, txq->tx_rs_thresh);
+		num = num >> 1;
+		ret = iavf_xmit_fixed_burst_vec_avx2_ctx(tx_queue, &tx_pkts[nb_tx],
+						       num, offload);
+		nb_tx += ret;
+		nb_pkts -= ret;
+		if (ret < num)
+			break;
+	}
+
+	return nb_tx;
+}
+
+uint16_t
+iavf_xmit_pkts_vec_avx2_ctx(void *tx_queue, struct rte_mbuf **tx_pkts,
+				  uint16_t nb_pkts)
+{
+	return iavf_xmit_pkts_vec_avx2_ctx_cmn(tx_queue, tx_pkts, nb_pkts, false);
+}
+
+uint16_t
+iavf_xmit_pkts_vec_avx2_ctx_offload(void *tx_queue, struct rte_mbuf **tx_pkts,
+				  uint16_t nb_pkts)
+{
+	return iavf_xmit_pkts_vec_avx2_ctx_cmn(tx_queue, tx_pkts, nb_pkts, true);
+}
+
 static __rte_always_inline uint16_t
 iavf_xmit_pkts_vec_avx2_common(void *tx_queue, struct rte_mbuf **tx_pkts,
 			       uint16_t nb_pkts, bool offload)
-- 
2.43.0

Re: [PATCH 1/2] net/iavf: use mbuf packet type instead of dynfield for LLDP

[Bruce Richardson]

On Mon, Feb 09, 2026 at 03:20:48PM +0000, Ciara Loftus wrote:
> Instead of using a dynamic mbuf field to flag a packet as LLDP, instead
> utilise the mbuf packet type field as the identifier instead. If the
> type is RTE_PTYPE_L2_ETHER_LLDP the packet is identified as LLDP. This
> approach is preferable because the use of dynamic mbuf fields should be
> reserved for features that are not easily implemented using the existing
> mbuf infrastructure. No negative performance impacts were observed with
> the new approach.
> 
> Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>

For ABI compatibility, though, I think we need to keep the old method of
identifying LLDP packets there too. While I completely agree that using
packet types is the better approach, we need to go through a deprecation
process for the old dynamic field method, though.

> ---
>  doc/guides/nics/intel_vf.rst           | 16 +++++++++-------
>  doc/guides/rel_notes/release_26_03.rst |  1 +
>  drivers/net/intel/iavf/iavf_ethdev.c   | 13 ++++++++-----
>  drivers/net/intel/iavf/iavf_rxtx.c     |  3 +--
>  drivers/net/intel/iavf/iavf_rxtx.h     |  8 +++-----
>  drivers/net/intel/iavf/iavf_testpmd.c  | 20 +++++---------------
>  drivers/net/intel/iavf/rte_pmd_iavf.h  | 10 ++++++++++
>  7 files changed, 37 insertions(+), 34 deletions(-)
> 
> diff --git a/doc/guides/nics/intel_vf.rst b/doc/guides/nics/intel_vf.rst
> index bc600e4b58..197918b2e8 100644
> --- a/doc/guides/nics/intel_vf.rst
> +++ b/doc/guides/nics/intel_vf.rst
> @@ -668,19 +668,21 @@ Inline IPsec Support
>  Diagnostic Utilities
>  --------------------
>  

<snip>
>  

> +RTE_EXPORT_EXPERIMENTAL_SYMBOL(rte_pmd_iavf_enable_tx_lldp, 26.03)
> +void
> +rte_pmd_iavf_enable_tx_lldp(bool enable)
> +{
> +	iavf_tx_lldp_enabled = enable;
> +}
> +
Rather than a private function, this looks something that should be a
feature flag or capability somewhere, e.g. like TSO.

RE: [PATCH 1/2] net/iavf: use mbuf packet type instead of dynfield for LLDP

[Loftus, Ciara]

> Subject: Re: [PATCH 1/2] net/iavf: use mbuf packet type instead of dynfield for
> LLDP
> 
> On Mon, Feb 09, 2026 at 03:20:48PM +0000, Ciara Loftus wrote:
> > Instead of using a dynamic mbuf field to flag a packet as LLDP, instead
> > utilise the mbuf packet type field as the identifier instead. If the
> > type is RTE_PTYPE_L2_ETHER_LLDP the packet is identified as LLDP. This
> > approach is preferable because the use of dynamic mbuf fields should be
> > reserved for features that are not easily implemented using the existing
> > mbuf infrastructure. No negative performance impacts were observed with
> > the new approach.
> >
> > Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
> 
> For ABI compatibility, though, I think we need to keep the old method of
> identifying LLDP packets there too. While I completely agree that using
> packet types is the better approach, we need to go through a deprecation
> process for the old dynamic field method, though.

I will submit a v2 supporting both the dynfield and ptype approach, and a
deprecation notice flagging the future removal of the dynfield.

> 
> > ---
> >  doc/guides/nics/intel_vf.rst           | 16 +++++++++-------
> >  doc/guides/rel_notes/release_26_03.rst |  1 +
> >  drivers/net/intel/iavf/iavf_ethdev.c   | 13 ++++++++-----
> >  drivers/net/intel/iavf/iavf_rxtx.c     |  3 +--
> >  drivers/net/intel/iavf/iavf_rxtx.h     |  8 +++-----
> >  drivers/net/intel/iavf/iavf_testpmd.c  | 20 +++++---------------
> >  drivers/net/intel/iavf/rte_pmd_iavf.h  | 10 ++++++++++
> >  7 files changed, 37 insertions(+), 34 deletions(-)
> >
> > diff --git a/doc/guides/nics/intel_vf.rst b/doc/guides/nics/intel_vf.rst
> > index bc600e4b58..197918b2e8 100644
> > --- a/doc/guides/nics/intel_vf.rst
> > +++ b/doc/guides/nics/intel_vf.rst
> > @@ -668,19 +668,21 @@ Inline IPsec Support
> >  Diagnostic Utilities
> >  --------------------
> >
> 
> <snip>
> >
> 
> > +RTE_EXPORT_EXPERIMENTAL_SYMBOL(rte_pmd_iavf_enable_tx_lldp,
> 26.03)
> > +void
> > +rte_pmd_iavf_enable_tx_lldp(bool enable)
> > +{
> > +	iavf_tx_lldp_enabled = enable;
> > +}
> > +
> Rather than a private function, this looks something that should be a
> feature flag or capability somewhere, e.g. like TSO.

I think that would be a neater solution for iavf, but I
can't find any evidence of any other driver requiring this
sort of explicit enabling of LLDP as a feature. So it would
be hard to justify adding such a feature flag/capability
when it looks like there might only be one driver to use it.
I will consider this some more.
Since we are keeping the dynfield implementation for now,
registering the dynfield is equivalent to enabling the
feature so we don't need an API like this in the v2. When we
eventually remove the dynfield I will try to find a better
solution for enabling the feature, that isn't a private
function.

[PATCH v2 0/3] iavf: LLDP ptype and AVX2 ctx paths

[Ciara Loftus]

This series adds another way to detect LLDP packets in the Tx paths
of the iavf PMD, which is based on the mbuf packet type field. This is
in addition to the existing method of using a dynamic field. The series
also adds new AVX2 context descriptor Tx paths that support LLDP. Finally,
a deprecation notice is added to the documentation to flag that the
dynamic mbuf field method of LLDP packet detection will be removed in a
future release.

v2:
* Support both dynfield and ptype to preserve ABI
* Add deprecation notice for dynfield approach

Ciara Loftus (3):
  net/iavf: support LLDP Tx based on mbuf ptype or dynfield
  net/iavf: add AVX2 context descriptor Tx paths
  doc: announce change to LLDP packet detection in iavf PMD

 doc/guides/nics/intel_vf.rst                |   6 +
 doc/guides/rel_notes/deprecation.rst        |   4 +
 doc/guides/rel_notes/release_26_03.rst      |   2 +
 drivers/net/intel/iavf/iavf.h               |   2 +
 drivers/net/intel/iavf/iavf_rxtx.c          |  18 +
 drivers/net/intel/iavf/iavf_rxtx.h          |   9 +-
 drivers/net/intel/iavf/iavf_rxtx_vec_avx2.c | 386 ++++++++++++++++++++
 7 files changed, 424 insertions(+), 3 deletions(-)

-- 
2.43.0

[PATCH v2 1/3] net/iavf: support LLDP Tx based on mbuf ptype or dynfield

[Ciara Loftus]

Prior to this commit the only way to flag to the iavf PMD that an mbuf
contained an LLDP packet intended for transmission was to register and
set a dynamic mbuf field. This commit introduces an alternative
approach: rather than setting the dynamic mbuf field, the user may
instead set the packet type of the mbuf to RTE_PTYPE_L2_ETHER_LLDP. If
the LLDP feature is enabled (ie. if the dynamic mbuf field is
registered), on Tx the driver will check both the dynamic mbuf field and
the packet type, and if either indicates that the packet is an LLDP
packet, it will be transmitted.

Using the packet type to identify an LLDP packet instead of the dynamic
mbuf field is preferred because the use of dynamic mbuf fields should be
reserved for features that are not easily implemented using the existing
mbuf infrastructure. Also, it may remove some overhead in the
application if the Rx driver sets the packet type to LLDP as that would
remove the burden from the application to explicitly set any fields
before Tx. It is intended that the dynamic mbuf field approach will be
removed in a future release, at which point only the packet type
approach will be supported. A deprecation notice announcing this
intention will be submitted separately.

Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
---
v2:
* Support both dynfield and ptype methods to preserve ABI
---
 doc/guides/nics/intel_vf.rst           | 6 ++++++
 doc/guides/rel_notes/release_26_03.rst | 1 +
 drivers/net/intel/iavf/iavf_rxtx.h     | 5 ++---
 3 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/doc/guides/nics/intel_vf.rst b/doc/guides/nics/intel_vf.rst
index bc600e4b58..ad25389521 100644
--- a/doc/guides/nics/intel_vf.rst
+++ b/doc/guides/nics/intel_vf.rst
@@ -681,6 +681,12 @@ Usage::
 
     testpmd> set tx lldp on
 
+An alternative method for transmitting LLDP packets is to register the dynamic field as
+above and, rather than setting the dynfield value, set the ``packet_type`` of the mbuf to
+``RTE_PTYPE_L2_ETHER_LLDP``. The driver will check both the dynamic field and the packet
+type, and if either indicates that the packet is an LLDP packet, the driver will transmit
+it.
+
 
 Limitations or Knowing issues
 -----------------------------
diff --git a/doc/guides/rel_notes/release_26_03.rst b/doc/guides/rel_notes/release_26_03.rst
index 884d2535df..5ad531aef5 100644
--- a/doc/guides/rel_notes/release_26_03.rst
+++ b/doc/guides/rel_notes/release_26_03.rst
@@ -80,6 +80,7 @@ New Features
 * **Updated Intel iavf driver.**
 
   * Added support for pre and post VF reset callbacks.
+  * Added support for transmitting LLDP packets based on mbuf packet type.
 
 * **Updated Intel ice driver.**
 
diff --git a/drivers/net/intel/iavf/iavf_rxtx.h b/drivers/net/intel/iavf/iavf_rxtx.h
index 80b06518b0..1db1267eec 100644
--- a/drivers/net/intel/iavf/iavf_rxtx.h
+++ b/drivers/net/intel/iavf/iavf_rxtx.h
@@ -158,9 +158,8 @@
 #define IAVF_TX_LLDP_DYNFIELD "intel_pmd_dynfield_tx_lldp"
 #define IAVF_CHECK_TX_LLDP(m) \
 	((rte_pmd_iavf_tx_lldp_dynfield_offset > 0) && \
-	(*RTE_MBUF_DYNFIELD((m), \
-			rte_pmd_iavf_tx_lldp_dynfield_offset, \
-			uint8_t *)))
+	((*RTE_MBUF_DYNFIELD((m), rte_pmd_iavf_tx_lldp_dynfield_offset, uint8_t *)) || \
+	((m)->packet_type & RTE_PTYPE_L2_MASK) == RTE_PTYPE_L2_ETHER_LLDP))
 
 extern uint64_t iavf_timestamp_dynflag;
 extern int iavf_timestamp_dynfield_offset;
-- 
2.43.0

[PATCH v2 2/3] net/iavf: add AVX2 context descriptor Tx paths

[Ciara Loftus]

Prior to this commit the transmit paths implemented for AVX2 used the
transmit descriptor only, making some offloads and features unavailable
on the AVX2 path, like LLDP. Enable two new AVX2 transmit paths, both
of which support using a context descriptor, one which performs offload
and the other which does not.

Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
---
 doc/guides/rel_notes/release_26_03.rst      |   1 +
 drivers/net/intel/iavf/iavf.h               |   2 +
 drivers/net/intel/iavf/iavf_rxtx.c          |  18 +
 drivers/net/intel/iavf/iavf_rxtx.h          |   4 +
 drivers/net/intel/iavf/iavf_rxtx_vec_avx2.c | 386 ++++++++++++++++++++
 5 files changed, 411 insertions(+)

diff --git a/doc/guides/rel_notes/release_26_03.rst b/doc/guides/rel_notes/release_26_03.rst
index 5ad531aef5..bf21bd9d01 100644
--- a/doc/guides/rel_notes/release_26_03.rst
+++ b/doc/guides/rel_notes/release_26_03.rst
@@ -81,6 +81,7 @@ New Features
 
   * Added support for pre and post VF reset callbacks.
   * Added support for transmitting LLDP packets based on mbuf packet type.
+  * Implemented AVX2 context descriptor transmit paths.
 
 * **Updated Intel ice driver.**
 
diff --git a/drivers/net/intel/iavf/iavf.h b/drivers/net/intel/iavf/iavf.h
index 403c61e2e8..153275a51b 100644
--- a/drivers/net/intel/iavf/iavf.h
+++ b/drivers/net/intel/iavf/iavf.h
@@ -357,6 +357,8 @@ enum iavf_tx_func_type {
 	IAVF_TX_DEFAULT,
 	IAVF_TX_AVX2,
 	IAVF_TX_AVX2_OFFLOAD,
+	IAVF_TX_AVX2_CTX,
+	IAVF_TX_AVX2_CTX_OFFLOAD,
 	IAVF_TX_AVX512,
 	IAVF_TX_AVX512_OFFLOAD,
 	IAVF_TX_AVX512_CTX,
diff --git a/drivers/net/intel/iavf/iavf_rxtx.c b/drivers/net/intel/iavf/iavf_rxtx.c
index 4ff6c18dc4..6079d2e030 100644
--- a/drivers/net/intel/iavf/iavf_rxtx.c
+++ b/drivers/net/intel/iavf/iavf_rxtx.c
@@ -3616,6 +3616,24 @@ static const struct ci_tx_path_info iavf_tx_path_infos[] = {
 			.simd_width = RTE_VECT_SIMD_256
 		}
 	},
+	[IAVF_TX_AVX2_CTX] = {
+		.pkt_burst = iavf_xmit_pkts_vec_avx2_ctx,
+		.info = "Vector AVX2 Ctx",
+		.features = {
+			.tx_offloads = IAVF_TX_VECTOR_OFFLOADS,
+			.simd_width = RTE_VECT_SIMD_256,
+			.ctx_desc = true
+		}
+	},
+	[IAVF_TX_AVX2_CTX_OFFLOAD] = {
+		.pkt_burst = iavf_xmit_pkts_vec_avx2_ctx_offload,
+		.info = "Vector AVX2 Ctx Offload",
+		.features = {
+			.tx_offloads = IAVF_TX_VECTOR_CTX_OFFLOAD_OFFLOADS,
+			.simd_width = RTE_VECT_SIMD_256,
+			.ctx_desc = true
+		}
+	},
 #ifdef CC_AVX512_SUPPORT
 	[IAVF_TX_AVX512] = {
 		.pkt_burst = iavf_xmit_pkts_vec_avx512,
diff --git a/drivers/net/intel/iavf/iavf_rxtx.h b/drivers/net/intel/iavf/iavf_rxtx.h
index 1db1267eec..6729cd4d45 100644
--- a/drivers/net/intel/iavf/iavf_rxtx.h
+++ b/drivers/net/intel/iavf/iavf_rxtx.h
@@ -587,6 +587,10 @@ uint16_t iavf_xmit_pkts_vec_avx2(void *tx_queue, struct rte_mbuf **tx_pkts,
 				 uint16_t nb_pkts);
 uint16_t iavf_xmit_pkts_vec_avx2_offload(void *tx_queue, struct rte_mbuf **tx_pkts,
 					 uint16_t nb_pkts);
+uint16_t iavf_xmit_pkts_vec_avx2_ctx(void *tx_queue, struct rte_mbuf **tx_pkts,
+				  uint16_t nb_pkts);
+uint16_t iavf_xmit_pkts_vec_avx2_ctx_offload(void *tx_queue, struct rte_mbuf **tx_pkts,
+				  uint16_t nb_pkts);
 int iavf_get_monitor_addr(void *rx_queue, struct rte_power_monitor_cond *pmc);
 int iavf_rx_vec_dev_check(struct rte_eth_dev *dev);
 int iavf_tx_vec_dev_check(struct rte_eth_dev *dev);
diff --git a/drivers/net/intel/iavf/iavf_rxtx_vec_avx2.c b/drivers/net/intel/iavf/iavf_rxtx_vec_avx2.c
index db0462f0f5..2e7fe96d2b 100644
--- a/drivers/net/intel/iavf/iavf_rxtx_vec_avx2.c
+++ b/drivers/net/intel/iavf/iavf_rxtx_vec_avx2.c
@@ -1763,6 +1763,392 @@ iavf_xmit_fixed_burst_vec_avx2(void *tx_queue, struct rte_mbuf **tx_pkts,
 	return nb_pkts;
 }
 
+static inline void
+iavf_fill_ctx_desc_tunneling_avx2(uint64_t *low_ctx_qw, struct rte_mbuf *pkt)
+{
+	if (pkt->ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK) {
+		uint64_t eip_typ = IAVF_TX_CTX_DESC_EIPT_NONE;
+		uint64_t eip_len = 0;
+		uint64_t eip_noinc = 0;
+		/* Default - IP_ID is increment in each segment of LSO */
+
+		switch (pkt->ol_flags & (RTE_MBUF_F_TX_OUTER_IPV4 |
+				RTE_MBUF_F_TX_OUTER_IPV6 |
+				RTE_MBUF_F_TX_OUTER_IP_CKSUM)) {
+		case RTE_MBUF_F_TX_OUTER_IPV4:
+			eip_typ = IAVF_TX_CTX_DESC_EIPT_IPV4_NO_CHECKSUM_OFFLOAD;
+			eip_len = pkt->outer_l3_len >> 2;
+		break;
+		case RTE_MBUF_F_TX_OUTER_IPV4 | RTE_MBUF_F_TX_OUTER_IP_CKSUM:
+			eip_typ = IAVF_TX_CTX_DESC_EIPT_IPV4_CHECKSUM_OFFLOAD;
+			eip_len = pkt->outer_l3_len >> 2;
+		break;
+		case RTE_MBUF_F_TX_OUTER_IPV6:
+			eip_typ = IAVF_TX_CTX_DESC_EIPT_IPV6;
+			eip_len = pkt->outer_l3_len >> 2;
+		break;
+		}
+
+		/* L4TUNT: L4 Tunneling Type */
+		switch (pkt->ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK) {
+		case RTE_MBUF_F_TX_TUNNEL_IPIP:
+			/* for non UDP / GRE tunneling, set to 00b */
+			break;
+		case RTE_MBUF_F_TX_TUNNEL_VXLAN:
+		case RTE_MBUF_F_TX_TUNNEL_VXLAN_GPE:
+		case RTE_MBUF_F_TX_TUNNEL_GTP:
+		case RTE_MBUF_F_TX_TUNNEL_GENEVE:
+			eip_typ |= IAVF_TXD_CTX_UDP_TUNNELING;
+			break;
+		case RTE_MBUF_F_TX_TUNNEL_GRE:
+			eip_typ |= IAVF_TXD_CTX_GRE_TUNNELING;
+			break;
+		default:
+			PMD_TX_LOG(ERR, "Tunnel type not supported");
+			return;
+		}
+
+		/* L4TUNLEN: L4 Tunneling Length, in Words
+		 *
+		 * We depend on app to set rte_mbuf.l2_len correctly.
+		 * For IP in GRE it should be set to the length of the GRE
+		 * header;
+		 * For MAC in GRE or MAC in UDP it should be set to the length
+		 * of the GRE or UDP headers plus the inner MAC up to including
+		 * its last Ethertype.
+		 * If MPLS labels exists, it should include them as well.
+		 */
+		eip_typ |= (pkt->l2_len >> 1) << IAVF_TXD_CTX_QW0_NATLEN_SHIFT;
+
+		/**
+		 * Calculate the tunneling UDP checksum.
+		 * Shall be set only if L4TUNT = 01b and EIPT is not zero
+		 */
+		if ((eip_typ & (IAVF_TX_CTX_EXT_IP_IPV4 |
+					IAVF_TX_CTX_EXT_IP_IPV6 |
+					IAVF_TX_CTX_EXT_IP_IPV4_NO_CSUM)) &&
+				(eip_typ & IAVF_TXD_CTX_UDP_TUNNELING) &&
+				(pkt->ol_flags & RTE_MBUF_F_TX_OUTER_UDP_CKSUM))
+			eip_typ |= IAVF_TXD_CTX_QW0_L4T_CS_MASK;
+
+		*low_ctx_qw = eip_typ << IAVF_TXD_CTX_QW0_TUN_PARAMS_EIPT_SHIFT |
+			eip_len << IAVF_TXD_CTX_QW0_TUN_PARAMS_EIPLEN_SHIFT |
+			eip_noinc << IAVF_TXD_CTX_QW0_TUN_PARAMS_EIP_NOINC_SHIFT;
+
+	} else {
+		*low_ctx_qw = 0;
+	}
+}
+
+static inline void
+iavf_fill_ctx_desc_tunneling_field(volatile uint64_t *qw0,
+		const struct rte_mbuf *m)
+{
+	uint64_t eip_typ = IAVF_TX_CTX_DESC_EIPT_NONE;
+	uint64_t eip_len = 0;
+	uint64_t eip_noinc = 0;
+	/* Default - IP_ID is increment in each segment of LSO */
+
+	switch (m->ol_flags & (RTE_MBUF_F_TX_OUTER_IPV4 |
+			RTE_MBUF_F_TX_OUTER_IPV6 |
+			RTE_MBUF_F_TX_OUTER_IP_CKSUM)) {
+	case RTE_MBUF_F_TX_OUTER_IPV4:
+		eip_typ = IAVF_TX_CTX_DESC_EIPT_IPV4_NO_CHECKSUM_OFFLOAD;
+		eip_len = m->outer_l3_len >> 2;
+	break;
+	case RTE_MBUF_F_TX_OUTER_IPV4 | RTE_MBUF_F_TX_OUTER_IP_CKSUM:
+		eip_typ = IAVF_TX_CTX_DESC_EIPT_IPV4_CHECKSUM_OFFLOAD;
+		eip_len = m->outer_l3_len >> 2;
+	break;
+	case RTE_MBUF_F_TX_OUTER_IPV6:
+		eip_typ = IAVF_TX_CTX_DESC_EIPT_IPV6;
+		eip_len = m->outer_l3_len >> 2;
+	break;
+	}
+
+	/* L4TUNT: L4 Tunneling Type */
+	switch (m->ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK) {
+	case RTE_MBUF_F_TX_TUNNEL_IPIP:
+		/* for non UDP / GRE tunneling, set to 00b */
+		break;
+	case RTE_MBUF_F_TX_TUNNEL_VXLAN:
+	case RTE_MBUF_F_TX_TUNNEL_VXLAN_GPE:
+	case RTE_MBUF_F_TX_TUNNEL_GTP:
+	case RTE_MBUF_F_TX_TUNNEL_GENEVE:
+		eip_typ |= IAVF_TXD_CTX_UDP_TUNNELING;
+		break;
+	case RTE_MBUF_F_TX_TUNNEL_GRE:
+		eip_typ |= IAVF_TXD_CTX_GRE_TUNNELING;
+		break;
+	default:
+		PMD_TX_LOG(ERR, "Tunnel type not supported");
+		return;
+	}
+
+	/* L4TUNLEN: L4 Tunneling Length, in Words
+	 *
+	 * We depend on app to set rte_mbuf.l2_len correctly.
+	 * For IP in GRE it should be set to the length of the GRE
+	 * header;
+	 * For MAC in GRE or MAC in UDP it should be set to the length
+	 * of the GRE or UDP headers plus the inner MAC up to including
+	 * its last Ethertype.
+	 * If MPLS labels exists, it should include them as well.
+	 */
+	eip_typ |= (m->l2_len >> 1) << IAVF_TXD_CTX_QW0_NATLEN_SHIFT;
+
+	/**
+	 * Calculate the tunneling UDP checksum.
+	 * Shall be set only if L4TUNT = 01b and EIPT is not zero
+	 */
+	if ((eip_typ & (IAVF_TX_CTX_EXT_IP_IPV6 |
+				IAVF_TX_CTX_EXT_IP_IPV4 |
+				IAVF_TX_CTX_EXT_IP_IPV4_NO_CSUM)) &&
+			(eip_typ & IAVF_TXD_CTX_UDP_TUNNELING) &&
+			(m->ol_flags & RTE_MBUF_F_TX_OUTER_UDP_CKSUM))
+		eip_typ |= IAVF_TXD_CTX_QW0_L4T_CS_MASK;
+
+	*qw0 = eip_typ << IAVF_TXD_CTX_QW0_TUN_PARAMS_EIPT_SHIFT |
+		eip_len << IAVF_TXD_CTX_QW0_TUN_PARAMS_EIPLEN_SHIFT |
+		eip_noinc << IAVF_TXD_CTX_QW0_TUN_PARAMS_EIP_NOINC_SHIFT;
+}
+
+static __rte_always_inline void
+ctx_vtx1(volatile struct ci_tx_desc *txdp, struct rte_mbuf *pkt,
+		uint64_t flags, bool offload, uint8_t vlan_flag)
+{
+	uint64_t high_ctx_qw = IAVF_TX_DESC_DTYPE_CONTEXT;
+	uint64_t low_ctx_qw = 0;
+
+	if (offload) {
+		iavf_fill_ctx_desc_tunneling_avx2(&low_ctx_qw, pkt);
+#ifdef IAVF_TX_VLAN_QINQ_OFFLOAD
+		if (pkt->ol_flags & RTE_MBUF_F_TX_QINQ) {
+			uint64_t qinq_tag = vlan_flag & IAVF_TX_FLAGS_VLAN_TAG_LOC_L2TAG2 ?
+				(uint64_t)pkt->vlan_tci_outer :
+				(uint64_t)pkt->vlan_tci;
+			high_ctx_qw |= IAVF_TX_CTX_DESC_IL2TAG2 << IAVF_TXD_CTX_QW1_CMD_SHIFT;
+			low_ctx_qw |= qinq_tag << IAVF_TXD_CTX_QW0_L2TAG2_PARAM;
+		} else if ((pkt->ol_flags & RTE_MBUF_F_TX_VLAN) &&
+				vlan_flag & IAVF_TX_FLAGS_VLAN_TAG_LOC_L2TAG2) {
+			high_ctx_qw |= IAVF_TX_CTX_DESC_IL2TAG2 << IAVF_TXD_CTX_QW1_CMD_SHIFT;
+			low_ctx_qw |= (uint64_t)pkt->vlan_tci << IAVF_TXD_CTX_QW0_L2TAG2_PARAM;
+		}
+#endif
+	}
+	if (IAVF_CHECK_TX_LLDP(pkt))
+		high_ctx_qw |= IAVF_TX_CTX_DESC_SWTCH_UPLINK << IAVF_TXD_CTX_QW1_CMD_SHIFT;
+	uint64_t high_data_qw = (IAVF_TX_DESC_DTYPE_DATA |
+				((uint64_t)flags  << IAVF_TXD_QW1_CMD_SHIFT) |
+				((uint64_t)pkt->data_len << IAVF_TXD_QW1_TX_BUF_SZ_SHIFT));
+	if (offload)
+		iavf_txd_enable_offload(pkt, &high_data_qw, vlan_flag);
+
+	__m256i ctx_data_desc = _mm256_set_epi64x(high_data_qw, pkt->buf_iova + pkt->data_off,
+							high_ctx_qw, low_ctx_qw);
+
+	_mm256_storeu_si256(RTE_CAST_PTR(__m256i *, txdp), ctx_data_desc);
+}
+
+static __rte_always_inline void
+ctx_vtx(volatile struct ci_tx_desc *txdp,
+		struct rte_mbuf **pkt, uint16_t nb_pkts, uint64_t flags,
+		bool offload, uint8_t vlan_flag)
+{
+	uint64_t hi_data_qw_tmpl = (IAVF_TX_DESC_DTYPE_DATA |
+					((uint64_t)flags  << IAVF_TXD_QW1_CMD_SHIFT));
+
+	/* if unaligned on 32-bit boundary, do one to align */
+	if (((uintptr_t)txdp & 0x1F) != 0 && nb_pkts != 0) {
+		ctx_vtx1(txdp, *pkt, flags, offload, vlan_flag);
+		nb_pkts--, txdp++, pkt++;
+	}
+
+	for (; nb_pkts > 1; txdp += 4, pkt += 2, nb_pkts -= 2) {
+		uint64_t hi_ctx_qw1 = IAVF_TX_DESC_DTYPE_CONTEXT;
+		uint64_t hi_ctx_qw0 = IAVF_TX_DESC_DTYPE_CONTEXT;
+		uint64_t low_ctx_qw1 = 0;
+		uint64_t low_ctx_qw0 = 0;
+		uint64_t hi_data_qw1 = 0;
+		uint64_t hi_data_qw0 = 0;
+
+		hi_data_qw1 = hi_data_qw_tmpl |
+				((uint64_t)pkt[1]->data_len <<
+					IAVF_TXD_QW1_TX_BUF_SZ_SHIFT);
+		hi_data_qw0 = hi_data_qw_tmpl |
+				((uint64_t)pkt[0]->data_len <<
+					IAVF_TXD_QW1_TX_BUF_SZ_SHIFT);
+
+#ifdef IAVF_TX_VLAN_QINQ_OFFLOAD
+		if (offload) {
+			if (pkt[1]->ol_flags & RTE_MBUF_F_TX_QINQ) {
+				uint64_t qinq_tag = vlan_flag & IAVF_TX_FLAGS_VLAN_TAG_LOC_L2TAG2 ?
+					(uint64_t)pkt[1]->vlan_tci_outer :
+					(uint64_t)pkt[1]->vlan_tci;
+				hi_ctx_qw1 |= IAVF_TX_CTX_DESC_IL2TAG2 <<
+						IAVF_TXD_CTX_QW1_CMD_SHIFT;
+				low_ctx_qw1 |= qinq_tag << IAVF_TXD_CTX_QW0_L2TAG2_PARAM;
+			} else if (pkt[1]->ol_flags & RTE_MBUF_F_TX_VLAN &&
+					vlan_flag & IAVF_TX_FLAGS_VLAN_TAG_LOC_L2TAG2) {
+				hi_ctx_qw1 |=
+					IAVF_TX_CTX_DESC_IL2TAG2 << IAVF_TXD_CTX_QW1_CMD_SHIFT;
+				low_ctx_qw1 |=
+					(uint64_t)pkt[1]->vlan_tci << IAVF_TXD_CTX_QW0_L2TAG2_PARAM;
+			}
+		}
+#endif
+		if (IAVF_CHECK_TX_LLDP(pkt[1]))
+			hi_ctx_qw1 |= IAVF_TX_CTX_DESC_SWTCH_UPLINK << IAVF_TXD_CTX_QW1_CMD_SHIFT;
+
+#ifdef IAVF_TX_VLAN_QINQ_OFFLOAD
+		if (offload) {
+			if (pkt[0]->ol_flags & RTE_MBUF_F_TX_QINQ) {
+				uint64_t qinq_tag = vlan_flag & IAVF_TX_FLAGS_VLAN_TAG_LOC_L2TAG2 ?
+					(uint64_t)pkt[0]->vlan_tci_outer :
+					(uint64_t)pkt[0]->vlan_tci;
+				hi_ctx_qw0 |= IAVF_TX_CTX_DESC_IL2TAG2 <<
+						IAVF_TXD_CTX_QW1_CMD_SHIFT;
+				low_ctx_qw0 |= qinq_tag << IAVF_TXD_CTX_QW0_L2TAG2_PARAM;
+			} else if (pkt[0]->ol_flags & RTE_MBUF_F_TX_VLAN &&
+					vlan_flag & IAVF_TX_FLAGS_VLAN_TAG_LOC_L2TAG2) {
+				hi_ctx_qw0 |=
+					IAVF_TX_CTX_DESC_IL2TAG2 << IAVF_TXD_CTX_QW1_CMD_SHIFT;
+				low_ctx_qw0 |=
+					(uint64_t)pkt[0]->vlan_tci << IAVF_TXD_CTX_QW0_L2TAG2_PARAM;
+			}
+		}
+#endif
+		if (IAVF_CHECK_TX_LLDP(pkt[0]))
+			hi_ctx_qw0 |= IAVF_TX_CTX_DESC_SWTCH_UPLINK << IAVF_TXD_CTX_QW1_CMD_SHIFT;
+
+		if (offload) {
+			iavf_txd_enable_offload(pkt[1], &hi_data_qw1, vlan_flag);
+			iavf_txd_enable_offload(pkt[0], &hi_data_qw0, vlan_flag);
+			iavf_fill_ctx_desc_tunneling_field(&low_ctx_qw1, pkt[1]);
+			iavf_fill_ctx_desc_tunneling_field(&low_ctx_qw0, pkt[0]);
+		}
+
+		__m256i desc2_3 =
+			_mm256_set_epi64x
+				(hi_data_qw1, pkt[1]->buf_iova + pkt[1]->data_off,
+				 hi_ctx_qw1, low_ctx_qw1);
+		__m256i desc0_1 =
+			_mm256_set_epi64x
+				(hi_data_qw0, pkt[0]->buf_iova + pkt[0]->data_off,
+				 hi_ctx_qw0, low_ctx_qw0);
+		_mm256_store_si256(RTE_CAST_PTR(__m256i *, txdp + 2), desc2_3);
+		_mm256_store_si256(RTE_CAST_PTR(__m256i *, txdp), desc0_1);
+	}
+
+	if (nb_pkts)
+		ctx_vtx1(txdp, *pkt, flags, offload, vlan_flag);
+}
+
+static __rte_always_inline uint16_t
+iavf_xmit_fixed_burst_vec_avx2_ctx(void *tx_queue, struct rte_mbuf **tx_pkts,
+				 uint16_t nb_pkts, bool offload)
+{
+	struct ci_tx_queue *txq = (struct ci_tx_queue *)tx_queue;
+	volatile struct ci_tx_desc *txdp;
+	struct ci_tx_entry_vec *txep;
+	uint16_t n, nb_commit, nb_mbuf, tx_id;
+	/* bit2 is reserved and must be set to 1 according to Spec */
+	uint64_t flags = IAVF_TX_DESC_CMD_EOP | IAVF_TX_DESC_CMD_ICRC;
+	uint64_t rs = IAVF_TX_DESC_CMD_RS | flags;
+
+	if (txq->nb_tx_free < txq->tx_free_thresh)
+		ci_tx_free_bufs_vec(txq, iavf_tx_desc_done, true);
+
+	nb_commit = (uint16_t)RTE_MIN(txq->nb_tx_free, nb_pkts << 1);
+	nb_commit &= 0xFFFE;
+	if (unlikely(nb_commit == 0))
+		return 0;
+
+	nb_pkts = nb_commit >> 1;
+	tx_id = txq->tx_tail;
+	txdp = &txq->ci_tx_ring[tx_id];
+	txep = (void *)txq->sw_ring;
+	txep += (tx_id >> 1);
+
+	txq->nb_tx_free = (uint16_t)(txq->nb_tx_free - nb_commit);
+	n = (uint16_t)(txq->nb_tx_desc - tx_id);
+
+	if (n != 0 && nb_commit >= n) {
+		nb_mbuf = n >> 1;
+		ci_tx_backlog_entry_vec(txep, tx_pkts, nb_mbuf);
+
+		ctx_vtx(txdp, tx_pkts, nb_mbuf - 1, flags, offload, txq->vlan_flag);
+		tx_pkts += (nb_mbuf - 1);
+		txdp += (n - 2);
+		ctx_vtx1(txdp, *tx_pkts++, rs, offload, txq->vlan_flag);
+
+		nb_commit = (uint16_t)(nb_commit - n);
+
+		txq->tx_next_rs = (uint16_t)(txq->tx_rs_thresh - 1);
+		tx_id = 0;
+		/* avoid reach the end of ring */
+		txdp = txq->ci_tx_ring;
+		txep = (void *)txq->sw_ring;
+	}
+
+	nb_mbuf = nb_commit >> 1;
+	ci_tx_backlog_entry_vec(txep, tx_pkts, nb_mbuf);
+
+	ctx_vtx(txdp, tx_pkts, nb_mbuf, flags, offload, txq->vlan_flag);
+	tx_id = (uint16_t)(tx_id + nb_commit);
+
+	if (tx_id > txq->tx_next_rs) {
+		txq->ci_tx_ring[txq->tx_next_rs].cmd_type_offset_bsz |=
+			rte_cpu_to_le_64(((uint64_t)IAVF_TX_DESC_CMD_RS) <<
+					 IAVF_TXD_QW1_CMD_SHIFT);
+		txq->tx_next_rs =
+			(uint16_t)(txq->tx_next_rs + txq->tx_rs_thresh);
+	}
+
+	txq->tx_tail = tx_id;
+
+	IAVF_PCI_REG_WC_WRITE(txq->qtx_tail, txq->tx_tail);
+	return nb_pkts;
+}
+
+static __rte_always_inline uint16_t
+iavf_xmit_pkts_vec_avx2_ctx_cmn(void *tx_queue, struct rte_mbuf **tx_pkts,
+				  uint16_t nb_pkts, bool offload)
+{
+	uint16_t nb_tx = 0;
+	struct ci_tx_queue *txq = (struct ci_tx_queue *)tx_queue;
+
+	while (nb_pkts) {
+		uint16_t ret, num;
+
+		/* cross rs_thresh boundary is not allowed */
+		num = (uint16_t)RTE_MIN(nb_pkts << 1, txq->tx_rs_thresh);
+		num = num >> 1;
+		ret = iavf_xmit_fixed_burst_vec_avx2_ctx(tx_queue, &tx_pkts[nb_tx],
+						       num, offload);
+		nb_tx += ret;
+		nb_pkts -= ret;
+		if (ret < num)
+			break;
+	}
+
+	return nb_tx;
+}
+
+uint16_t
+iavf_xmit_pkts_vec_avx2_ctx(void *tx_queue, struct rte_mbuf **tx_pkts,
+				  uint16_t nb_pkts)
+{
+	return iavf_xmit_pkts_vec_avx2_ctx_cmn(tx_queue, tx_pkts, nb_pkts, false);
+}
+
+uint16_t
+iavf_xmit_pkts_vec_avx2_ctx_offload(void *tx_queue, struct rte_mbuf **tx_pkts,
+				  uint16_t nb_pkts)
+{
+	return iavf_xmit_pkts_vec_avx2_ctx_cmn(tx_queue, tx_pkts, nb_pkts, true);
+}
+
 static __rte_always_inline uint16_t
 iavf_xmit_pkts_vec_avx2_common(void *tx_queue, struct rte_mbuf **tx_pkts,
 			       uint16_t nb_pkts, bool offload)
-- 
2.43.0

[PATCH v2 3/3] doc: announce change to LLDP packet detection in iavf PMD

[Ciara Loftus]

The iavf PMD transmit paths currently use two methods to
identify if an mbuf holds an LLDP packet: a dynamic mbuf
field and the mbuf ptype. A future release will remove the
dynamic mbuf field approach at which point the ptype will be
the only approach used.

Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
---
 doc/guides/rel_notes/deprecation.rst | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/doc/guides/rel_notes/deprecation.rst b/doc/guides/rel_notes/deprecation.rst
index ac667e91a6..e450f9e56d 100644
--- a/doc/guides/rel_notes/deprecation.rst
+++ b/doc/guides/rel_notes/deprecation.rst
@@ -139,3 +139,7 @@ Deprecation Notices
 * bus/vmbus: Starting DPDK 25.11, all the vmbus API defined in
   ``drivers/bus/vmbus/rte_bus_vmbus.h`` will become internal to DPDK.
   Those API functions are used internally by DPDK core and netvsc PMD.
+
+* net/iavf: The method of detecting an LLDP packet on the transmit path
+  in the iavf PMD will be changed. Instead of using either a dynamic mbuf
+  field or the mbuf ptype, only the mbuf ptype will be used.
-- 
2.43.0