[dpdk-dev] [PATCH 12/12] net/sfc: support tunnel TSO on EF10 native Tx datapath

[Andrew Rybchenko <arybchenko@solarflare.com>]

From: Ivan Malov <ivan.malov@oktetlabs.ru>

Handle VXLAN and GENEVE TSO on EF10 native Tx datapath.

Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
---
 doc/guides/nics/sfc_efx.rst            |  2 +-
 doc/guides/rel_notes/release_19_05.rst |  1 +
 drivers/net/sfc/sfc.c                  |  6 ++++++
 drivers/net/sfc/sfc.h                  |  1 +
 drivers/net/sfc/sfc_dp_tx.h            | 18 +++++++++++++++++-
 drivers/net/sfc/sfc_ef10_tx.c          | 22 ++++++++++++++++------
 drivers/net/sfc/sfc_tx.c               | 17 +++++++++++++++--
 7 files changed, 57 insertions(+), 10 deletions(-)

diff --git a/doc/guides/nics/sfc_efx.rst b/doc/guides/nics/sfc_efx.rst
index 028c92cc3..eb47f25e3 100644
--- a/doc/guides/nics/sfc_efx.rst
+++ b/doc/guides/nics/sfc_efx.rst
@@ -66,7 +66,7 @@ SFC EFX PMD has support for:
 
 - Allmulticast mode
 
-- TCP segmentation offload (TSO)
+- TCP segmentation offload (TSO) including VXLAN and GENEVE encapsulated
 
 - Multicast MAC filter
 
diff --git a/doc/guides/rel_notes/release_19_05.rst b/doc/guides/rel_notes/release_19_05.rst
index 173c852c8..f434c4823 100644
--- a/doc/guides/rel_notes/release_19_05.rst
+++ b/doc/guides/rel_notes/release_19_05.rst
@@ -74,6 +74,7 @@ New Features
     process.
   * Added support for Rx packet types list in a secondary process.
   * Added Tx prepare to do Tx offloads checks.
+  * Added support for VXLAN and GENEVE encapsulated TSO.
 
 * **Updated Mellanox drivers.**
 
diff --git a/drivers/net/sfc/sfc.c b/drivers/net/sfc/sfc.c
index dee468f89..406386a8c 100644
--- a/drivers/net/sfc/sfc.c
+++ b/drivers/net/sfc/sfc.c
@@ -750,6 +750,12 @@ sfc_attach(struct sfc_adapter *sa)
 			sfc_info(sa, "TSO support isn't available on this adapter");
 	}
 
+	if (sa->tso && sa->priv.dp_tx->features & SFC_DP_TX_FEAT_TSO_ENCAP) {
+		sa->tso_encap = encp->enc_fw_assisted_tso_v2_encap_enabled;
+		if (!sa->tso_encap)
+			sfc_info(sa, "Encapsulated TSO support isn't available on this adapter");
+	}
+
 	sfc_log_init(sa, "estimate resource limits");
 	rc = sfc_estimate_resource_limits(sa);
 	if (rc != 0)
diff --git a/drivers/net/sfc/sfc.h b/drivers/net/sfc/sfc.h
index a4b9a3f33..ecd20e546 100644
--- a/drivers/net/sfc/sfc.h
+++ b/drivers/net/sfc/sfc.h
@@ -286,6 +286,7 @@ struct sfc_adapter {
 	struct sfc_txq			*txq_ctrl;
 
 	boolean_t			tso;
+	boolean_t			tso_encap;
 
 	uint32_t			rxd_wait_timeout_ns;
 };
diff --git a/drivers/net/sfc/sfc_dp_tx.h b/drivers/net/sfc/sfc_dp_tx.h
index ae5524f24..72a69149b 100644
--- a/drivers/net/sfc/sfc_dp_tx.h
+++ b/drivers/net/sfc/sfc_dp_tx.h
@@ -163,6 +163,7 @@ struct sfc_dp_tx {
 #define SFC_DP_TX_FEAT_MULTI_PROCESS	0x8
 #define SFC_DP_TX_FEAT_MULTI_POOL	0x10
 #define SFC_DP_TX_FEAT_REFCNT		0x20
+#define SFC_DP_TX_FEAT_TSO_ENCAP	0x40
 	sfc_dp_tx_get_dev_info_t	*get_dev_info;
 	sfc_dp_tx_qsize_up_rings_t	*qsize_up_rings;
 	sfc_dp_tx_qcreate_t		*qcreate;
@@ -220,7 +221,22 @@ sfc_dp_tx_prepare_pkt(struct rte_mbuf *m,
 
 	if (m->ol_flags & PKT_TX_TCP_SEG) {
 		unsigned int tcph_off = m->l2_len + m->l3_len;
-		unsigned int header_len = tcph_off + m->l4_len;
+		unsigned int header_len;
+
+		switch (m->ol_flags & PKT_TX_TUNNEL_MASK) {
+		case 0:
+			break;
+		case PKT_TX_TUNNEL_VXLAN:
+			/* FALLTHROUGH */
+		case PKT_TX_TUNNEL_GENEVE:
+			if (!(m->ol_flags &
+			      (PKT_TX_OUTER_IPV4 | PKT_TX_OUTER_IPV6)))
+				return EINVAL;
+
+			tcph_off += m->outer_l2_len + m->outer_l3_len;
+		}
+
+		header_len = tcph_off + m->l4_len;
 
 		if (unlikely(tcph_off > tso_tcp_header_offset_limit))
 			return EINVAL;
diff --git a/drivers/net/sfc/sfc_ef10_tx.c b/drivers/net/sfc/sfc_ef10_tx.c
index bcbd15d55..055389efe 100644
--- a/drivers/net/sfc/sfc_ef10_tx.c
+++ b/drivers/net/sfc/sfc_ef10_tx.c
@@ -366,13 +366,16 @@ sfc_ef10_xmit_tso_pkt(struct sfc_ef10_txq * const txq, struct rte_mbuf *m_seg,
 		      unsigned int *added, unsigned int *dma_desc_space,
 		      bool *reap_done)
 {
-	size_t iph_off = m_seg->l2_len;
-	size_t tcph_off = m_seg->l2_len + m_seg->l3_len;
-	size_t header_len = m_seg->l2_len + m_seg->l3_len + m_seg->l4_len;
+	size_t iph_off = ((m_seg->ol_flags & PKT_TX_TUNNEL_MASK) ?
+			  m_seg->outer_l2_len + m_seg->outer_l3_len : 0) +
+			 m_seg->l2_len;
+	size_t tcph_off = iph_off + m_seg->l3_len;
+	size_t header_len = tcph_off + m_seg->l4_len;
 	/* Offset of the payload in the last segment that contains the header */
 	size_t in_off = 0;
 	const struct tcp_hdr *th;
 	uint16_t packet_id = 0;
+	uint16_t outer_packet_id = 0;
 	uint32_t sent_seq;
 	uint8_t *hdr_addr;
 	rte_iova_t hdr_iova;
@@ -482,12 +485,16 @@ sfc_ef10_xmit_tso_pkt(struct sfc_ef10_txq * const txq, struct rte_mbuf *m_seg,
 	if (first_m_seg->ol_flags & PKT_TX_IPV4)
 		packet_id = sfc_tso_ip4_get_ipid(hdr_addr, iph_off);
 
+	if (first_m_seg->ol_flags & PKT_TX_OUTER_IPV4)
+		outer_packet_id = sfc_tso_ip4_get_ipid(hdr_addr,
+						first_m_seg->outer_l2_len);
+
 	th = (const struct tcp_hdr *)(hdr_addr + tcph_off);
 	rte_memcpy(&sent_seq, &th->sent_seq, sizeof(uint32_t));
 	sent_seq = rte_be_to_cpu_32(sent_seq);
 
-	sfc_ef10_tx_qdesc_tso2_create(txq, *added, packet_id, 0, sent_seq,
-			first_m_seg->tso_segsz);
+	sfc_ef10_tx_qdesc_tso2_create(txq, *added, packet_id, outer_packet_id,
+			sent_seq, first_m_seg->tso_segsz);
 	(*added) += SFC_EF10_TSO_OPT_DESCS_NUM;
 
 	sfc_ef10_tx_qdesc_dma_create(hdr_iova, header_len, false,
@@ -927,7 +934,9 @@ sfc_ef10_tx_qcreate(uint16_t port_id, uint16_t queue_id,
 	if (txq->sw_ring == NULL)
 		goto fail_sw_ring_alloc;
 
-	if (info->offloads & DEV_TX_OFFLOAD_TCP_TSO) {
+	if (info->offloads & (DEV_TX_OFFLOAD_TCP_TSO |
+			      DEV_TX_OFFLOAD_VXLAN_TNL_TSO |
+			      DEV_TX_OFFLOAD_GENEVE_TNL_TSO)) {
 		txq->tsoh = rte_calloc_socket("sfc-ef10-txq-tsoh",
 					      info->txq_entries,
 					      SFC_TSOH_STD_LEN,
@@ -1090,6 +1099,7 @@ struct sfc_dp_tx sfc_ef10_tx = {
 		.hw_fw_caps	= SFC_DP_HW_FW_CAP_EF10,
 	},
 	.features		= SFC_DP_TX_FEAT_TSO |
+				  SFC_DP_TX_FEAT_TSO_ENCAP |
 				  SFC_DP_TX_FEAT_MULTI_SEG |
 				  SFC_DP_TX_FEAT_MULTI_POOL |
 				  SFC_DP_TX_FEAT_REFCNT |
diff --git a/drivers/net/sfc/sfc_tx.c b/drivers/net/sfc/sfc_tx.c
index 4037802e6..e1ef00cc7 100644
--- a/drivers/net/sfc/sfc_tx.c
+++ b/drivers/net/sfc/sfc_tx.c
@@ -70,6 +70,10 @@ sfc_tx_get_queue_offload_caps(struct sfc_adapter *sa)
 	if (sa->tso)
 		caps |= DEV_TX_OFFLOAD_TCP_TSO;
 
+	if (sa->tso_encap)
+		caps |= (DEV_TX_OFFLOAD_VXLAN_TNL_TSO |
+			 DEV_TX_OFFLOAD_GENEVE_TNL_TSO);
+
 	return caps;
 }
 
@@ -469,7 +473,9 @@ sfc_tx_qstart(struct sfc_adapter *sa, unsigned int sw_index)
 			flags |= EFX_TXQ_CKSUM_INNER_TCPUDP;
 	}
 
-	if (txq_info->offloads & DEV_TX_OFFLOAD_TCP_TSO)
+	if (txq_info->offloads & (DEV_TX_OFFLOAD_TCP_TSO |
+				  DEV_TX_OFFLOAD_VXLAN_TNL_TSO |
+				  DEV_TX_OFFLOAD_GENEVE_TNL_TSO))
 		flags |= EFX_TXQ_FATSOV2;
 
 	rc = efx_tx_qcreate(sa->nic, txq->hw_index, 0, &txq->mem,
@@ -588,18 +594,25 @@ int
 sfc_tx_start(struct sfc_adapter *sa)
 {
 	struct sfc_adapter_shared * const sas = sfc_sa2shared(sa);
+	const efx_nic_cfg_t *encp = efx_nic_cfg_get(sa->nic);
 	unsigned int sw_index;
 	int rc = 0;
 
 	sfc_log_init(sa, "txq_count = %u", sas->txq_count);
 
 	if (sa->tso) {
-		if (!efx_nic_cfg_get(sa->nic)->enc_fw_assisted_tso_v2_enabled) {
+		if (!encp->enc_fw_assisted_tso_v2_enabled) {
 			sfc_warn(sa, "TSO support was unable to be restored");
 			sa->tso = B_FALSE;
+			sa->tso_encap = B_FALSE;
 		}
 	}
 
+	if (sa->tso_encap && !encp->enc_fw_assisted_tso_v2_encap_enabled) {
+		sfc_warn(sa, "Encapsulated TSO support was unable to be restored");
+		sa->tso_encap = B_FALSE;
+	}
+
 	rc = efx_tx_init(sa->nic);
 	if (rc != 0)
 		goto fail_efx_tx_init;
-- 
2.17.1