[dpdk-dev] [PATCH v4 0/5] event/octeontx2: add Rx/Tx adapter support

[dpdk-dev] [PATCH v4 0/5] event/octeontx2: add Rx/Tx adapter support

[pbhagavatula]

From: Pavan Nikhilesh <pbhagavatula@marvell.com>

This patchset adds event eth Rx/Tx adapter support for OCTEONTX2 event
device, depends on:
http://patches.dpdk.org/project/dpdk/list/?series=5302

v4 Changes:
- Squash documentation patch.
- Remove unnessary net/octeontx2 library dependency.

v3 Changes:
- rebase patches to v3 of net/octeontx2.
- remove shared function between net/octeontx2 and event/octeontx2.

v2 Changes:
- add missing patch.

Harman Kalra (1):
  event/octeontx2: add PTP support for SSO

Pavan Nikhilesh (4):
  event/octeontx2: add event eth Rx adapter support
  event/octeontx2: resize SSO inflight event buffers
  event/octeontx2: add event eth Rx adapter fastpath ops
  event/octeontx2: add Tx adadpter support

 doc/guides/eventdevs/octeontx2.rst         |   6 +
 drivers/event/octeontx2/Makefile           |   2 +-
 drivers/event/octeontx2/meson.build        |   2 +-
 drivers/event/octeontx2/otx2_evdev.c       | 391 ++++++++++++++++++-
 drivers/event/octeontx2/otx2_evdev.h       | 161 +++++++-
 drivers/event/octeontx2/otx2_evdev_adptr.c | 418 +++++++++++++++++++++
 drivers/event/octeontx2/otx2_worker.c      | 207 +++++++---
 drivers/event/octeontx2/otx2_worker.h      |  98 ++++-
 drivers/event/octeontx2/otx2_worker_dual.c | 257 ++++++++++---
 drivers/event/octeontx2/otx2_worker_dual.h |  25 +-
 10 files changed, 1412 insertions(+), 155 deletions(-)

--
2.22.0

[dpdk-dev] [PATCH v4 1/5] event/octeontx2: add event eth Rx adapter support

[pbhagavatula]

From: Pavan Nikhilesh <pbhagavatula@marvell.com>

Add event eth Rx adapter capabilities, queue add and delete functions.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
---
 doc/guides/eventdevs/octeontx2.rst         |   6 +
 drivers/event/octeontx2/Makefile           |   2 +-
 drivers/event/octeontx2/meson.build        |   2 +-
 drivers/event/octeontx2/otx2_evdev.c       |   4 +
 drivers/event/octeontx2/otx2_evdev.h       |  15 ++
 drivers/event/octeontx2/otx2_evdev_adptr.c | 254 +++++++++++++++++++++
 6 files changed, 281 insertions(+), 2 deletions(-)

diff --git a/doc/guides/eventdevs/octeontx2.rst b/doc/guides/eventdevs/octeontx2.rst
index e5624ba23..fad84cf42 100644
--- a/doc/guides/eventdevs/octeontx2.rst
+++ b/doc/guides/eventdevs/octeontx2.rst
@@ -32,6 +32,12 @@ Features of the OCTEON TX2 SSO PMD are:
   time granularity of 2.5us.
 - Up to 256 TIM rings aka event timer adapters.
 - Up to 8 rings traversed in parallel.
+- HW managed packets enqueued from ethdev to eventdev exposed through event eth
+  RX adapter.
+- N:1 ethernet device Rx queue to Event queue mapping.
+- Lockfree Tx from event eth Tx adapter using ``DEV_TX_OFFLOAD_MT_LOCKFREE``
+  capability while maintaining receive packet order.
+- Full Rx/Tx offload support defined through ethdev queue config.
 
 Prerequisites and Compilation procedure
 ---------------------------------------
diff --git a/drivers/event/octeontx2/Makefile b/drivers/event/octeontx2/Makefile
index aac238bff..8289f617a 100644
--- a/drivers/event/octeontx2/Makefile
+++ b/drivers/event/octeontx2/Makefile
@@ -43,7 +43,7 @@ SRCS-$(CONFIG_RTE_LIBRTE_PMD_OCTEONTX2_EVENTDEV) += otx2_evdev_selftest.c
 SRCS-$(CONFIG_RTE_LIBRTE_PMD_OCTEONTX2_EVENTDEV) += otx2_evdev_irq.c
 
 LDLIBS += -lrte_eal -lrte_bus_pci -lrte_pci -lrte_kvargs
-LDLIBS += -lrte_mempool -lrte_eventdev -lrte_mbuf
+LDLIBS += -lrte_mempool -lrte_eventdev -lrte_mbuf -lrte_ethdev
 LDLIBS += -lrte_common_octeontx2 -lrte_mempool_octeontx2
 
 include $(RTE_SDK)/mk/rte.lib.mk
diff --git a/drivers/event/octeontx2/meson.build b/drivers/event/octeontx2/meson.build
index bdb5beed6..e94bc5944 100644
--- a/drivers/event/octeontx2/meson.build
+++ b/drivers/event/octeontx2/meson.build
@@ -26,4 +26,4 @@ foreach flag: extra_flags
 	endif
 endforeach
 
-deps += ['bus_pci', 'common_octeontx2', 'mempool_octeontx2']
+deps += ['bus_pci', 'common_octeontx2', 'mempool_octeontx2', 'pmd_octeontx2']
diff --git a/drivers/event/octeontx2/otx2_evdev.c b/drivers/event/octeontx2/otx2_evdev.c
index 914869b6c..2956a572d 100644
--- a/drivers/event/octeontx2/otx2_evdev.c
+++ b/drivers/event/octeontx2/otx2_evdev.c
@@ -1123,6 +1123,10 @@ static struct rte_eventdev_ops otx2_sso_ops = {
 	.port_unlink      = otx2_sso_port_unlink,
 	.timeout_ticks    = otx2_sso_timeout_ticks,
 
+	.eth_rx_adapter_caps_get  = otx2_sso_rx_adapter_caps_get,
+	.eth_rx_adapter_queue_add = otx2_sso_rx_adapter_queue_add,
+	.eth_rx_adapter_queue_del = otx2_sso_rx_adapter_queue_del,
+
 	.timer_adapter_caps_get = otx2_tim_caps_get,
 
 	.xstats_get       = otx2_sso_xstats_get,
diff --git a/drivers/event/octeontx2/otx2_evdev.h b/drivers/event/octeontx2/otx2_evdev.h
index ba3aae5ba..8bee8c737 100644
--- a/drivers/event/octeontx2/otx2_evdev.h
+++ b/drivers/event/octeontx2/otx2_evdev.h
@@ -6,9 +6,12 @@
 #define __OTX2_EVDEV_H__
 
 #include <rte_eventdev.h>
+#include <rte_eventdev_pmd.h>
+#include <rte_event_eth_rx_adapter.h>
 
 #include "otx2_common.h"
 #include "otx2_dev.h"
+#include "otx2_ethdev.h"
 #include "otx2_mempool.h"
 
 #define EVENTDEV_NAME_OCTEONTX2_PMD otx2_eventdev
@@ -249,6 +252,18 @@ void sso_updt_xae_cnt(struct otx2_sso_evdev *dev, void *data,
 		      uint32_t event_type);
 int sso_xae_reconfigure(struct rte_eventdev *event_dev);
 void sso_fastpath_fns_set(struct rte_eventdev *event_dev);
+
+int otx2_sso_rx_adapter_caps_get(const struct rte_eventdev *event_dev,
+				 const struct rte_eth_dev *eth_dev,
+				 uint32_t *caps);
+int otx2_sso_rx_adapter_queue_add(const struct rte_eventdev *event_dev,
+				  const struct rte_eth_dev *eth_dev,
+				  int32_t rx_queue_id,
+		const struct rte_event_eth_rx_adapter_queue_conf *queue_conf);
+int otx2_sso_rx_adapter_queue_del(const struct rte_eventdev *event_dev,
+				  const struct rte_eth_dev *eth_dev,
+				  int32_t rx_queue_id);
+
 /* Clean up API's */
 typedef void (*otx2_handle_event_t)(void *arg, struct rte_event ev);
 void ssogws_flush_events(struct otx2_ssogws *ws, uint8_t queue_id,
diff --git a/drivers/event/octeontx2/otx2_evdev_adptr.c b/drivers/event/octeontx2/otx2_evdev_adptr.c
index 810722f89..ce5621f37 100644
--- a/drivers/event/octeontx2/otx2_evdev_adptr.c
+++ b/drivers/event/octeontx2/otx2_evdev_adptr.c
@@ -4,6 +4,197 @@
 
 #include "otx2_evdev.h"
 
+int
+otx2_sso_rx_adapter_caps_get(const struct rte_eventdev *event_dev,
+			     const struct rte_eth_dev *eth_dev, uint32_t *caps)
+{
+	int rc;
+
+	RTE_SET_USED(event_dev);
+	rc = strncmp(eth_dev->device->driver->name, "net_octeontx2", 13);
+	if (rc)
+		*caps = RTE_EVENT_ETH_RX_ADAPTER_SW_CAP;
+	else
+		*caps = RTE_EVENT_ETH_RX_ADAPTER_CAP_INTERNAL_PORT;
+
+	return 0;
+}
+
+static inline int
+sso_rxq_enable(struct otx2_eth_dev *dev, uint16_t qid, uint8_t tt, uint8_t ggrp,
+	       uint16_t eth_port_id)
+{
+	struct otx2_mbox *mbox = dev->mbox;
+	struct nix_aq_enq_req *aq;
+	int rc;
+
+	aq = otx2_mbox_alloc_msg_nix_aq_enq(mbox);
+	aq->qidx = qid;
+	aq->ctype = NIX_AQ_CTYPE_CQ;
+	aq->op = NIX_AQ_INSTOP_WRITE;
+
+	aq->cq.ena = 0;
+	aq->cq.caching = 0;
+
+	otx2_mbox_memset(&aq->cq_mask, 0, sizeof(struct nix_cq_ctx_s));
+	aq->cq_mask.ena = ~(aq->cq_mask.ena);
+	aq->cq_mask.caching = ~(aq->cq_mask.caching);
+
+	rc = otx2_mbox_process(mbox);
+	if (rc < 0) {
+		otx2_err("Failed to disable cq context");
+		goto fail;
+	}
+
+	aq = otx2_mbox_alloc_msg_nix_aq_enq(mbox);
+	aq->qidx = qid;
+	aq->ctype = NIX_AQ_CTYPE_RQ;
+	aq->op = NIX_AQ_INSTOP_WRITE;
+
+	aq->rq.sso_ena = 1;
+	aq->rq.sso_tt = tt;
+	aq->rq.sso_grp = ggrp;
+	aq->rq.ena_wqwd = 1;
+	/* Mbuf Header generation :
+	 * > FIRST_SKIP is a super set of WQE_SKIP, dont modify first skip as
+	 * it already has data related to mbuf size, headroom, private area.
+	 * > Using WQE_SKIP we can directly assign
+	 *		mbuf = wqe - sizeof(struct mbuf);
+	 * so that mbuf header will not have unpredicted values while headroom
+	 * and private data starts at the beginning of wqe_data.
+	 */
+	aq->rq.wqe_skip = 1;
+	aq->rq.wqe_caching = 1;
+	aq->rq.spb_ena = 0;
+	aq->rq.flow_tagw = 20; /* 20-bits */
+
+	/* Flow Tag calculation :
+	 *
+	 * rq_tag <31:24> = good/bad_tag<8:0>;
+	 * rq_tag  <23:0> = [ltag]
+	 *
+	 * flow_tag_mask<31:0> =  (1 << flow_tagw) - 1; <31:20>
+	 * tag<31:0> = (~flow_tag_mask & rq_tag) | (flow_tag_mask & flow_tag);
+	 *
+	 * Setup :
+	 * ltag<23:0> = (eth_port_id & 0xF) << 20;
+	 * good/bad_tag<8:0> =
+	 *	((eth_port_id >> 4) & 0xF) | (RTE_EVENT_TYPE_ETHDEV << 4);
+	 *
+	 * TAG<31:0> on getwork = <31:28>(RTE_EVENT_TYPE_ETHDEV) |
+	 *				<27:20> (eth_port_id) | <20:0> [TAG]
+	 */
+
+	aq->rq.ltag = (eth_port_id & 0xF) << 20;
+	aq->rq.good_utag = ((eth_port_id >> 4) & 0xF) |
+				(RTE_EVENT_TYPE_ETHDEV << 4);
+	aq->rq.bad_utag = aq->rq.good_utag;
+
+	aq->rq.ena = 0;		 /* Don't enable RQ yet */
+	aq->rq.pb_caching = 0x2; /* First cache aligned block to LLC */
+	aq->rq.xqe_imm_size = 0; /* No pkt data copy to CQE */
+
+	otx2_mbox_memset(&aq->rq_mask, 0, sizeof(struct nix_rq_ctx_s));
+	/* mask the bits to write. */
+	aq->rq_mask.sso_ena      = ~(aq->rq_mask.sso_ena);
+	aq->rq_mask.sso_tt       = ~(aq->rq_mask.sso_tt);
+	aq->rq_mask.sso_grp      = ~(aq->rq_mask.sso_grp);
+	aq->rq_mask.ena_wqwd     = ~(aq->rq_mask.ena_wqwd);
+	aq->rq_mask.wqe_skip     = ~(aq->rq_mask.wqe_skip);
+	aq->rq_mask.wqe_caching  = ~(aq->rq_mask.wqe_caching);
+	aq->rq_mask.spb_ena      = ~(aq->rq_mask.spb_ena);
+	aq->rq_mask.flow_tagw    = ~(aq->rq_mask.flow_tagw);
+	aq->rq_mask.ltag         = ~(aq->rq_mask.ltag);
+	aq->rq_mask.good_utag    = ~(aq->rq_mask.good_utag);
+	aq->rq_mask.bad_utag     = ~(aq->rq_mask.bad_utag);
+	aq->rq_mask.ena          = ~(aq->rq_mask.ena);
+	aq->rq_mask.pb_caching   = ~(aq->rq_mask.pb_caching);
+	aq->rq_mask.xqe_imm_size = ~(aq->rq_mask.xqe_imm_size);
+
+	rc = otx2_mbox_process(mbox);
+	if (rc < 0) {
+		otx2_err("Failed to init rx adapter context");
+		goto fail;
+	}
+
+	return 0;
+fail:
+	return rc;
+}
+
+static inline int
+sso_rxq_disable(struct otx2_eth_dev *dev, uint16_t qid)
+{
+	struct otx2_mbox *mbox = dev->mbox;
+	struct nix_aq_enq_req *aq;
+	int rc;
+
+	aq = otx2_mbox_alloc_msg_nix_aq_enq(mbox);
+	aq->qidx = qid;
+	aq->ctype = NIX_AQ_CTYPE_CQ;
+	aq->op = NIX_AQ_INSTOP_INIT;
+
+	aq->cq.ena = 1;
+	aq->cq.caching = 1;
+
+	otx2_mbox_memset(&aq->cq_mask, 0, sizeof(struct nix_cq_ctx_s));
+	aq->cq_mask.ena = ~(aq->cq_mask.ena);
+	aq->cq_mask.caching = ~(aq->cq_mask.caching);
+
+	rc = otx2_mbox_process(mbox);
+	if (rc < 0) {
+		otx2_err("Failed to init cq context");
+		goto fail;
+	}
+
+	aq = otx2_mbox_alloc_msg_nix_aq_enq(mbox);
+	aq->qidx = qid;
+	aq->ctype = NIX_AQ_CTYPE_RQ;
+	aq->op = NIX_AQ_INSTOP_WRITE;
+
+	aq->rq.sso_ena = 0;
+	aq->rq.sso_tt = SSO_TT_UNTAGGED;
+	aq->rq.sso_grp = 0;
+	aq->rq.ena_wqwd = 0;
+	aq->rq.wqe_caching = 0;
+	aq->rq.wqe_skip = 0;
+	aq->rq.spb_ena = 0;
+	aq->rq.flow_tagw = 0x20;
+	aq->rq.ltag = 0;
+	aq->rq.good_utag = 0;
+	aq->rq.bad_utag = 0;
+	aq->rq.ena = 1;
+	aq->rq.pb_caching = 0x2; /* First cache aligned block to LLC */
+	aq->rq.xqe_imm_size = 0; /* No pkt data copy to CQE */
+
+	otx2_mbox_memset(&aq->rq_mask, 0, sizeof(struct nix_rq_ctx_s));
+	/* mask the bits to write. */
+	aq->rq_mask.sso_ena      = ~(aq->rq_mask.sso_ena);
+	aq->rq_mask.sso_tt       = ~(aq->rq_mask.sso_tt);
+	aq->rq_mask.sso_grp      = ~(aq->rq_mask.sso_grp);
+	aq->rq_mask.ena_wqwd     = ~(aq->rq_mask.ena_wqwd);
+	aq->rq_mask.wqe_caching  = ~(aq->rq_mask.wqe_caching);
+	aq->rq_mask.wqe_skip     = ~(aq->rq_mask.wqe_skip);
+	aq->rq_mask.spb_ena      = ~(aq->rq_mask.spb_ena);
+	aq->rq_mask.flow_tagw    = ~(aq->rq_mask.flow_tagw);
+	aq->rq_mask.ltag         = ~(aq->rq_mask.ltag);
+	aq->rq_mask.good_utag    = ~(aq->rq_mask.good_utag);
+	aq->rq_mask.bad_utag     = ~(aq->rq_mask.bad_utag);
+	aq->rq_mask.ena          = ~(aq->rq_mask.ena);
+	aq->rq_mask.pb_caching   = ~(aq->rq_mask.pb_caching);
+	aq->rq_mask.xqe_imm_size = ~(aq->rq_mask.xqe_imm_size);
+
+	rc = otx2_mbox_process(mbox);
+	if (rc < 0) {
+		otx2_err("Failed to clear rx adapter context");
+		goto fail;
+	}
+
+	return 0;
+fail:
+	return rc;
+}
+
 void
 sso_updt_xae_cnt(struct otx2_sso_evdev *dev, void *data, uint32_t event_type)
 {
@@ -17,3 +208,66 @@ sso_updt_xae_cnt(struct otx2_sso_evdev *dev, void *data, uint32_t event_type)
 		break;
 	}
 }
+
+int
+otx2_sso_rx_adapter_queue_add(const struct rte_eventdev *event_dev,
+			      const struct rte_eth_dev *eth_dev,
+			      int32_t rx_queue_id,
+		const struct rte_event_eth_rx_adapter_queue_conf *queue_conf)
+{
+	struct otx2_eth_dev *otx2_eth_dev = eth_dev->data->dev_private;
+	uint16_t port = eth_dev->data->port_id;
+	int i, rc;
+
+	RTE_SET_USED(event_dev);
+	rc = strncmp(eth_dev->device->driver->name, "net_octeontx2", 13);
+	if (rc)
+		return -EINVAL;
+
+	if (rx_queue_id < 0) {
+		for (i = 0 ; i < eth_dev->data->nb_rx_queues; i++) {
+			rc |= sso_rxq_enable(otx2_eth_dev, i,
+					     queue_conf->ev.sched_type,
+					     queue_conf->ev.queue_id, port);
+		}
+	} else {
+		rc |= sso_rxq_enable(otx2_eth_dev, (uint16_t)rx_queue_id,
+				     queue_conf->ev.sched_type,
+				     queue_conf->ev.queue_id, port);
+	}
+
+	if (rc < 0) {
+		otx2_err("Failed to configure Rx adapter port=%d, q=%d", port,
+			 queue_conf->ev.queue_id);
+		return rc;
+	}
+
+	return 0;
+}
+
+int
+otx2_sso_rx_adapter_queue_del(const struct rte_eventdev *event_dev,
+			      const struct rte_eth_dev *eth_dev,
+			      int32_t rx_queue_id)
+{
+	struct otx2_eth_dev *dev = eth_dev->data->dev_private;
+	int i, rc;
+
+	RTE_SET_USED(event_dev);
+	rc = strncmp(eth_dev->device->driver->name, "net_octeontx2", 13);
+	if (rc)
+		return -EINVAL;
+
+	if (rx_queue_id < 0) {
+		for (i = 0 ; i < eth_dev->data->nb_rx_queues; i++)
+			rc = sso_rxq_disable(dev, i);
+	} else {
+		rc = sso_rxq_disable(dev, (uint16_t)rx_queue_id);
+	}
+
+	if (rc < 0)
+		otx2_err("Failed to clear Rx adapter config port=%d, q=%d",
+			 eth_dev->data->port_id, rx_queue_id);
+
+	return rc;
+}
-- 
2.22.0

[dpdk-dev] [PATCH v4 2/5] event/octeontx2: resize SSO inflight event buffers

[pbhagavatula]

From: Pavan Nikhilesh <pbhagavatula@marvell.com>

Resize SSO internal in-flight buffer count based on the Rx queues
mempool size connected to event queues.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
---
 drivers/event/octeontx2/otx2_evdev.h       |  2 ++
 drivers/event/octeontx2/otx2_evdev_adptr.c | 34 +++++++++++++++++++++-
 2 files changed, 35 insertions(+), 1 deletion(-)

diff --git a/drivers/event/octeontx2/otx2_evdev.h b/drivers/event/octeontx2/otx2_evdev.h
index 8bee8c737..107aa79d4 100644
--- a/drivers/event/octeontx2/otx2_evdev.h
+++ b/drivers/event/octeontx2/otx2_evdev.h
@@ -132,7 +132,9 @@ struct otx2_sso_evdev {
 	uint64_t nb_xaq_cfg;
 	rte_iova_t fc_iova;
 	struct rte_mempool *xaq_pool;
+	uint16_t rx_adptr_pool_cnt;
 	uint32_t adptr_xae_cnt;
+	uint64_t *rx_adptr_pools;
 	/* Dev args */
 	uint8_t dual_ws;
 	uint8_t selftest;
diff --git a/drivers/event/octeontx2/otx2_evdev_adptr.c b/drivers/event/octeontx2/otx2_evdev_adptr.c
index ce5621f37..12469fade 100644
--- a/drivers/event/octeontx2/otx2_evdev_adptr.c
+++ b/drivers/event/octeontx2/otx2_evdev_adptr.c
@@ -199,6 +199,29 @@ void
 sso_updt_xae_cnt(struct otx2_sso_evdev *dev, void *data, uint32_t event_type)
 {
 	switch (event_type) {
+	case RTE_EVENT_TYPE_ETHDEV:
+	{
+		struct otx2_eth_rxq *rxq = data;
+		int i, match = false;
+
+		for (i = 0; i < dev->rx_adptr_pool_cnt; i++) {
+			if ((uint64_t)rxq->pool == dev->rx_adptr_pools[i])
+				match = true;
+		}
+
+		if (!match) {
+			dev->rx_adptr_pool_cnt++;
+			dev->rx_adptr_pools = rte_realloc(dev->rx_adptr_pools,
+							  sizeof(uint64_t) *
+							  dev->rx_adptr_pool_cnt
+							  , 0);
+			dev->rx_adptr_pools[dev->rx_adptr_pool_cnt - 1] =
+				(uint64_t)rxq->pool;
+
+			dev->adptr_xae_cnt += rxq->pool->size;
+		}
+		break;
+	}
 	case RTE_EVENT_TYPE_TIMER:
 	{
 		dev->adptr_xae_cnt += (*(uint64_t *)data);
@@ -216,21 +239,30 @@ otx2_sso_rx_adapter_queue_add(const struct rte_eventdev *event_dev,
 		const struct rte_event_eth_rx_adapter_queue_conf *queue_conf)
 {
 	struct otx2_eth_dev *otx2_eth_dev = eth_dev->data->dev_private;
+	struct otx2_sso_evdev *dev = sso_pmd_priv(event_dev);
 	uint16_t port = eth_dev->data->port_id;
+	struct otx2_eth_rxq *rxq;
 	int i, rc;
 
-	RTE_SET_USED(event_dev);
 	rc = strncmp(eth_dev->device->driver->name, "net_octeontx2", 13);
 	if (rc)
 		return -EINVAL;
 
 	if (rx_queue_id < 0) {
 		for (i = 0 ; i < eth_dev->data->nb_rx_queues; i++) {
+			rxq = eth_dev->data->rx_queues[i];
+			sso_updt_xae_cnt(dev, rxq, RTE_EVENT_TYPE_ETHDEV);
+			rc = sso_xae_reconfigure((struct rte_eventdev *)
+						 (uintptr_t)event_dev);
 			rc |= sso_rxq_enable(otx2_eth_dev, i,
 					     queue_conf->ev.sched_type,
 					     queue_conf->ev.queue_id, port);
 		}
 	} else {
+		rxq = eth_dev->data->rx_queues[rx_queue_id];
+		sso_updt_xae_cnt(dev, rxq, RTE_EVENT_TYPE_ETHDEV);
+		rc = sso_xae_reconfigure((struct rte_eventdev *)
+					 (uintptr_t)event_dev);
 		rc |= sso_rxq_enable(otx2_eth_dev, (uint16_t)rx_queue_id,
 				     queue_conf->ev.sched_type,
 				     queue_conf->ev.queue_id, port);
-- 
2.22.0

[dpdk-dev] [PATCH v4 3/5] event/octeontx2: add event eth Rx adapter fastpath ops

[pbhagavatula]

From: Pavan Nikhilesh <pbhagavatula@marvell.com>

Add support for event eth Rx adapter fastpath operations.

Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
---
 drivers/event/octeontx2/otx2_evdev.c       | 308 ++++++++++++++++++++-
 drivers/event/octeontx2/otx2_evdev.h       | 108 ++++++--
 drivers/event/octeontx2/otx2_evdev_adptr.c |  45 +++
 drivers/event/octeontx2/otx2_worker.c      | 178 ++++++++----
 drivers/event/octeontx2/otx2_worker.h      |  43 ++-
 drivers/event/octeontx2/otx2_worker_dual.c | 220 ++++++++++-----
 drivers/event/octeontx2/otx2_worker_dual.h |  22 +-
 7 files changed, 767 insertions(+), 157 deletions(-)

diff --git a/drivers/event/octeontx2/otx2_evdev.c b/drivers/event/octeontx2/otx2_evdev.c
index 2956a572d..f45fc008d 100644
--- a/drivers/event/octeontx2/otx2_evdev.c
+++ b/drivers/event/octeontx2/otx2_evdev.c
@@ -43,17 +43,199 @@ void
 sso_fastpath_fns_set(struct rte_eventdev *event_dev)
 {
 	struct otx2_sso_evdev *dev = sso_pmd_priv(event_dev);
+	/* Single WS modes */
+	const event_dequeue_t ssogws_deq[2][2][2][2][2][2] = {
+#define R(name, f5, f4, f3, f2, f1, f0, flags)				\
+		[f5][f4][f3][f2][f1][f0] = otx2_ssogws_deq_ ##name,
+SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
+#undef R
+	};
+
+	const event_dequeue_burst_t ssogws_deq_burst[2][2][2][2][2][2] = {
+#define R(name, f5, f4, f3, f2, f1, f0, flags)				\
+		[f5][f4][f3][f2][f1][f0] = otx2_ssogws_deq_burst_ ##name,
+SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
+#undef R
+	};
+
+	const event_dequeue_t ssogws_deq_timeout[2][2][2][2][2][2] = {
+#define R(name, f5, f4, f3, f2, f1, f0, flags)				\
+		[f5][f4][f3][f2][f1][f0] = otx2_ssogws_deq_timeout_ ##name,
+SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
+#undef R
+	};
+
+	const event_dequeue_burst_t
+		ssogws_deq_timeout_burst[2][2][2][2][2][2] = {
+#define R(name, f5, f4, f3, f2, f1, f0, flags)				\
+		[f5][f4][f3][f2][f1][f0] =				\
+			otx2_ssogws_deq_timeout_burst_ ##name,
+SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
+#undef R
+	};
+
+	const event_dequeue_t ssogws_deq_seg[2][2][2][2][2][2] = {
+#define R(name, f5, f4, f3, f2, f1, f0, flags)				\
+		[f5][f4][f3][f2][f1][f0] = otx2_ssogws_deq_seg_ ##name,
+SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
+#undef R
+	};
+
+	const event_dequeue_burst_t ssogws_deq_seg_burst[2][2][2][2][2][2] = {
+#define R(name, f5, f4, f3, f2, f1, f0, flags)				\
+		[f5][f4][f3][f2][f1][f0] = otx2_ssogws_deq_seg_burst_ ##name,
+SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
+#undef R
+	};
+
+	const event_dequeue_t ssogws_deq_seg_timeout[2][2][2][2][2][2] = {
+#define R(name, f5, f4, f3, f2, f1, f0, flags)				\
+		[f5][f4][f3][f2][f1][f0] = otx2_ssogws_deq_seg_timeout_ ##name,
+SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
+#undef R
+	};
+
+	const event_dequeue_burst_t
+		ssogws_deq_seg_timeout_burst[2][2][2][2][2][2] = {
+#define R(name, f5, f4, f3, f2, f1, f0, flags)				\
+		[f5][f4][f3][f2][f1][f0] =				\
+				otx2_ssogws_deq_seg_timeout_burst_ ##name,
+SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
+#undef R
+	};
+
+
+	/* Dual WS modes */
+	const event_dequeue_t ssogws_dual_deq[2][2][2][2][2][2] = {
+#define R(name, f5, f4, f3, f2, f1, f0, flags)				\
+		[f5][f4][f3][f2][f1][f0] = otx2_ssogws_dual_deq_ ##name,
+SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
+#undef R
+	};
+
+	const event_dequeue_burst_t ssogws_dual_deq_burst[2][2][2][2][2][2] = {
+#define R(name, f5, f4, f3, f2, f1, f0, flags)				\
+		[f5][f4][f3][f2][f1][f0] = otx2_ssogws_dual_deq_burst_ ##name,
+SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
+#undef R
+	};
+
+	const event_dequeue_t ssogws_dual_deq_timeout[2][2][2][2][2][2] = {
+#define R(name, f5, f4, f3, f2, f1, f0, flags)				\
+		[f5][f4][f3][f2][f1][f0] = otx2_ssogws_dual_deq_timeout_ ##name,
+SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
+#undef R
+	};
+
+	const event_dequeue_burst_t
+		ssogws_dual_deq_timeout_burst[2][2][2][2][2][2] = {
+#define R(name, f5, f4, f3, f2, f1, f0, flags)				\
+	[f5][f4][f3][f2][f1][f0] = otx2_ssogws_dual_deq_timeout_burst_ ##name,
+SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
+#undef R
+	};
+
+	const event_dequeue_t ssogws_dual_deq_seg[2][2][2][2][2][2] = {
+#define R(name, f5, f4, f3, f2, f1, f0, flags)				\
+		[f5][f4][f3][f2][f1][f0] = otx2_ssogws_dual_deq_seg_ ##name,
+SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
+#undef R
+	};
+
+	const event_dequeue_burst_t
+		ssogws_dual_deq_seg_burst[2][2][2][2][2][2] = {
+#define R(name, f5, f4, f3, f2, f1, f0, flags)				\
+		[f5][f4][f3][f2][f1][f0] =				\
+				otx2_ssogws_dual_deq_seg_burst_ ##name,
+SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
+#undef R
+	};
+
+	const event_dequeue_t ssogws_dual_deq_seg_timeout[2][2][2][2][2][2] = {
+#define R(name, f5, f4, f3, f2, f1, f0, flags)				\
+		[f5][f4][f3][f2][f1][f0] =				\
+				otx2_ssogws_dual_deq_seg_timeout_ ##name,
+SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
+#undef R
+	};
+
+	const event_dequeue_burst_t
+		ssogws_dual_deq_seg_timeout_burst[2][2][2][2][2][2] = {
+#define R(name, f5, f4, f3, f2, f1, f0, flags)				\
+	[f5][f4][f3][f2][f1][f0] =					\
+		otx2_ssogws_dual_deq_seg_timeout_burst_ ##name,
+SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
+#undef R
+	};
 
 	event_dev->enqueue			= otx2_ssogws_enq;
 	event_dev->enqueue_burst		= otx2_ssogws_enq_burst;
 	event_dev->enqueue_new_burst		= otx2_ssogws_enq_new_burst;
 	event_dev->enqueue_forward_burst	= otx2_ssogws_enq_fwd_burst;
-
-	event_dev->dequeue			= otx2_ssogws_deq;
-	event_dev->dequeue_burst		= otx2_ssogws_deq_burst;
-	if (dev->is_timeout_deq) {
-		event_dev->dequeue		= otx2_ssogws_deq_timeout;
-		event_dev->dequeue_burst	= otx2_ssogws_deq_timeout_burst;
+	if (dev->rx_offloads & NIX_RX_MULTI_SEG_F) {
+		event_dev->dequeue		= ssogws_deq_seg
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_TSTAMP_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_MARK_UPDATE_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_VLAN_STRIP_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_CHECKSUM_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_PTYPE_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_RSS_F)];
+		event_dev->dequeue_burst	= ssogws_deq_seg_burst
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_TSTAMP_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_MARK_UPDATE_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_VLAN_STRIP_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_CHECKSUM_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_PTYPE_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_RSS_F)];
+		if (dev->is_timeout_deq) {
+			event_dev->dequeue	= ssogws_deq_seg_timeout
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_TSTAMP_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_MARK_UPDATE_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_VLAN_STRIP_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_CHECKSUM_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_PTYPE_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_RSS_F)];
+			event_dev->dequeue_burst	=
+				ssogws_deq_seg_timeout_burst
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_TSTAMP_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_MARK_UPDATE_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_VLAN_STRIP_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_CHECKSUM_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_PTYPE_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_RSS_F)];
+		}
+	} else {
+		event_dev->dequeue			= ssogws_deq
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_TSTAMP_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_MARK_UPDATE_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_VLAN_STRIP_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_CHECKSUM_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_PTYPE_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_RSS_F)];
+		event_dev->dequeue_burst		= ssogws_deq_burst
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_TSTAMP_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_MARK_UPDATE_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_VLAN_STRIP_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_CHECKSUM_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_PTYPE_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_RSS_F)];
+		if (dev->is_timeout_deq) {
+			event_dev->dequeue		= ssogws_deq_timeout
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_TSTAMP_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_MARK_UPDATE_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_VLAN_STRIP_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_CHECKSUM_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_PTYPE_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_RSS_F)];
+			event_dev->dequeue_burst	=
+				ssogws_deq_timeout_burst
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_TSTAMP_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_MARK_UPDATE_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_VLAN_STRIP_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_CHECKSUM_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_PTYPE_F)]
+			[!!(dev->rx_offloads & NIX_RX_OFFLOAD_RSS_F)];
+		}
 	}
 
 	if (dev->dual_ws) {
@@ -63,12 +245,112 @@ sso_fastpath_fns_set(struct rte_eventdev *event_dev)
 					otx2_ssogws_dual_enq_new_burst;
 		event_dev->enqueue_forward_burst =
 					otx2_ssogws_dual_enq_fwd_burst;
-		event_dev->dequeue		= otx2_ssogws_dual_deq;
-		event_dev->dequeue_burst	= otx2_ssogws_dual_deq_burst;
-		if (dev->is_timeout_deq) {
-			event_dev->dequeue	= otx2_ssogws_dual_deq_timeout;
-			event_dev->dequeue_burst =
-					otx2_ssogws_dual_deq_timeout_burst;
+
+		if (dev->rx_offloads & NIX_RX_MULTI_SEG_F) {
+			event_dev->dequeue	= ssogws_dual_deq_seg
+				[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_TSTAMP_F)]
+				[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_MARK_UPDATE_F)]
+				[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_VLAN_STRIP_F)]
+				[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_CHECKSUM_F)]
+				[!!(dev->rx_offloads & NIX_RX_OFFLOAD_PTYPE_F)]
+				[!!(dev->rx_offloads & NIX_RX_OFFLOAD_RSS_F)];
+			event_dev->dequeue_burst = ssogws_dual_deq_seg_burst
+				[!!(dev->rx_offloads & NIX_RX_OFFLOAD_TSTAMP_F)]
+				[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_MARK_UPDATE_F)]
+				[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_VLAN_STRIP_F)]
+				[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_CHECKSUM_F)]
+				[!!(dev->rx_offloads & NIX_RX_OFFLOAD_PTYPE_F)]
+				[!!(dev->rx_offloads & NIX_RX_OFFLOAD_RSS_F)];
+			if (dev->is_timeout_deq) {
+				event_dev->dequeue	=
+					ssogws_dual_deq_seg_timeout
+					[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_TSTAMP_F)]
+					[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_MARK_UPDATE_F)]
+					[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_VLAN_STRIP_F)]
+					[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_CHECKSUM_F)]
+					[!!(dev->rx_offloads &
+							NIX_RX_OFFLOAD_PTYPE_F)]
+					[!!(dev->rx_offloads &
+							NIX_RX_OFFLOAD_RSS_F)];
+				event_dev->dequeue_burst =
+					ssogws_dual_deq_seg_timeout_burst
+					[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_TSTAMP_F)]
+					[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_MARK_UPDATE_F)]
+					[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_VLAN_STRIP_F)]
+					[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_CHECKSUM_F)]
+					[!!(dev->rx_offloads &
+							NIX_RX_OFFLOAD_PTYPE_F)]
+					[!!(dev->rx_offloads &
+							NIX_RX_OFFLOAD_RSS_F)];
+			}
+		} else {
+			event_dev->dequeue		= ssogws_dual_deq
+				[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_TSTAMP_F)]
+				[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_MARK_UPDATE_F)]
+				[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_VLAN_STRIP_F)]
+				[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_CHECKSUM_F)]
+				[!!(dev->rx_offloads & NIX_RX_OFFLOAD_PTYPE_F)]
+				[!!(dev->rx_offloads & NIX_RX_OFFLOAD_RSS_F)];
+			event_dev->dequeue_burst	= ssogws_dual_deq_burst
+				[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_TSTAMP_F)]
+				[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_MARK_UPDATE_F)]
+				[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_VLAN_STRIP_F)]
+				[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_CHECKSUM_F)]
+				[!!(dev->rx_offloads & NIX_RX_OFFLOAD_PTYPE_F)]
+				[!!(dev->rx_offloads & NIX_RX_OFFLOAD_RSS_F)];
+			if (dev->is_timeout_deq) {
+				event_dev->dequeue	=
+					ssogws_dual_deq_timeout
+					[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_TSTAMP_F)]
+					[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_MARK_UPDATE_F)]
+					[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_VLAN_STRIP_F)]
+					[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_CHECKSUM_F)]
+					[!!(dev->rx_offloads &
+							NIX_RX_OFFLOAD_PTYPE_F)]
+					[!!(dev->rx_offloads &
+							NIX_RX_OFFLOAD_RSS_F)];
+				event_dev->dequeue_burst =
+					ssogws_dual_deq_timeout_burst
+					[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_TSTAMP_F)]
+					[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_MARK_UPDATE_F)]
+					[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_VLAN_STRIP_F)]
+					[!!(dev->rx_offloads &
+						NIX_RX_OFFLOAD_CHECKSUM_F)]
+					[!!(dev->rx_offloads &
+							NIX_RX_OFFLOAD_PTYPE_F)]
+					[!!(dev->rx_offloads &
+							NIX_RX_OFFLOAD_RSS_F)];
+			}
 		}
 	}
 	rte_mb();
@@ -1126,6 +1408,8 @@ static struct rte_eventdev_ops otx2_sso_ops = {
 	.eth_rx_adapter_caps_get  = otx2_sso_rx_adapter_caps_get,
 	.eth_rx_adapter_queue_add = otx2_sso_rx_adapter_queue_add,
 	.eth_rx_adapter_queue_del = otx2_sso_rx_adapter_queue_del,
+	.eth_rx_adapter_start = otx2_sso_rx_adapter_start,
+	.eth_rx_adapter_stop = otx2_sso_rx_adapter_stop,
 
 	.timer_adapter_caps_get = otx2_tim_caps_get,
 
diff --git a/drivers/event/octeontx2/otx2_evdev.h b/drivers/event/octeontx2/otx2_evdev.h
index 107aa79d4..a81a8be6f 100644
--- a/drivers/event/octeontx2/otx2_evdev.h
+++ b/drivers/event/octeontx2/otx2_evdev.h
@@ -132,6 +132,7 @@ struct otx2_sso_evdev {
 	uint64_t nb_xaq_cfg;
 	rte_iova_t fc_iova;
 	struct rte_mempool *xaq_pool;
+	uint64_t rx_offloads;
 	uint16_t rx_adptr_pool_cnt;
 	uint32_t adptr_xae_cnt;
 	uint64_t *rx_adptr_pools;
@@ -166,6 +167,7 @@ struct otx2_ssogws {
 	/* Get Work Fastpath data */
 	OTX2_SSOGWS_OPS;
 	uint8_t swtag_req;
+	void *lookup_mem;
 	uint8_t port;
 	/* Add Work Fastpath data */
 	uint64_t xaq_lmt __rte_cache_aligned;
@@ -182,6 +184,7 @@ struct otx2_ssogws_dual {
 	struct otx2_ssogws_state ws_state[2]; /* Ping and Pong */
 	uint8_t swtag_req;
 	uint8_t vws; /* Ping pong bit */
+	void *lookup_mem;
 	uint8_t port;
 	/* Add Work Fastpath data */
 	uint64_t xaq_lmt __rte_cache_aligned;
@@ -195,6 +198,28 @@ sso_pmd_priv(const struct rte_eventdev *event_dev)
 	return event_dev->data->dev_private;
 }
 
+static const union mbuf_initializer mbuf_init = {
+	.fields = {
+		.data_off = RTE_PKTMBUF_HEADROOM,
+		.refcnt = 1,
+		.nb_segs = 1,
+		.port = 0
+	}
+};
+
+static __rte_always_inline void
+otx2_wqe_to_mbuf(uint64_t get_work1, const uint64_t mbuf, uint8_t port_id,
+		 const uint32_t tag, const uint32_t flags,
+		 const void * const lookup_mem)
+{
+	struct nix_wqe_hdr_s *wqe = (struct nix_wqe_hdr_s *)get_work1;
+
+	otx2_nix_cqe_to_mbuf((struct nix_cqe_hdr_s *)wqe, tag,
+			     (struct rte_mbuf *)mbuf, lookup_mem,
+			     mbuf_init.value | (uint64_t)port_id << 48, flags);
+
+}
+
 static inline int
 parse_kvargs_flag(const char *key, const char *value, void *opaque)
 {
@@ -213,6 +238,9 @@ parse_kvargs_value(const char *key, const char *value, void *opaque)
 	return 0;
 }
 
+#define SSO_RX_ADPTR_ENQ_FASTPATH_FUNC	NIX_RX_FASTPATH_MODES
+#define SSO_TX_ADPTR_ENQ_FASTPATH_FUNC	NIX_TX_FASTPATH_MODES
+
 /* Single WS API's */
 uint16_t otx2_ssogws_enq(void *port, const struct rte_event *ev);
 uint16_t otx2_ssogws_enq_burst(void *port, const struct rte_event ev[],
@@ -222,15 +250,6 @@ uint16_t otx2_ssogws_enq_new_burst(void *port, const struct rte_event ev[],
 uint16_t otx2_ssogws_enq_fwd_burst(void *port, const struct rte_event ev[],
 				   uint16_t nb_events);
 
-uint16_t otx2_ssogws_deq(void *port, struct rte_event *ev,
-			 uint64_t timeout_ticks);
-uint16_t otx2_ssogws_deq_burst(void *port, struct rte_event ev[],
-			       uint16_t nb_events, uint64_t timeout_ticks);
-uint16_t otx2_ssogws_deq_timeout(void *port, struct rte_event *ev,
-				 uint64_t timeout_ticks);
-uint16_t otx2_ssogws_deq_timeout_burst(void *port, struct rte_event ev[],
-				       uint16_t nb_events,
-				       uint64_t timeout_ticks);
 /* Dual WS API's */
 uint16_t otx2_ssogws_dual_enq(void *port, const struct rte_event *ev);
 uint16_t otx2_ssogws_dual_enq_burst(void *port, const struct rte_event ev[],
@@ -240,15 +259,63 @@ uint16_t otx2_ssogws_dual_enq_new_burst(void *port, const struct rte_event ev[],
 uint16_t otx2_ssogws_dual_enq_fwd_burst(void *port, const struct rte_event ev[],
 					uint16_t nb_events);
 
-uint16_t otx2_ssogws_dual_deq(void *port, struct rte_event *ev,
-			      uint64_t timeout_ticks);
-uint16_t otx2_ssogws_dual_deq_burst(void *port, struct rte_event ev[],
-				    uint16_t nb_events, uint64_t timeout_ticks);
-uint16_t otx2_ssogws_dual_deq_timeout(void *port, struct rte_event *ev,
-				      uint64_t timeout_ticks);
-uint16_t otx2_ssogws_dual_deq_timeout_burst(void *port, struct rte_event ev[],
-					    uint16_t nb_events,
-					    uint64_t timeout_ticks);
+/* Auto generated API's */
+#define R(name, f5, f4, f3, f2, f1, f0, flags)				       \
+uint16_t otx2_ssogws_deq_ ##name(void *port, struct rte_event *ev,	       \
+				 uint64_t timeout_ticks);		       \
+uint16_t otx2_ssogws_deq_burst_ ##name(void *port, struct rte_event ev[],      \
+				       uint16_t nb_events,		       \
+				       uint64_t timeout_ticks);		       \
+uint16_t otx2_ssogws_deq_timeout_ ##name(void *port,			       \
+					 struct rte_event *ev,		       \
+					 uint64_t timeout_ticks);	       \
+uint16_t otx2_ssogws_deq_timeout_burst_ ##name(void *port,		       \
+					       struct rte_event ev[],	       \
+					       uint16_t nb_events,	       \
+					       uint64_t timeout_ticks);	       \
+uint16_t otx2_ssogws_deq_seg_ ##name(void *port, struct rte_event *ev,	       \
+				     uint64_t timeout_ticks);		       \
+uint16_t otx2_ssogws_deq_seg_burst_ ##name(void *port,			       \
+					   struct rte_event ev[],	       \
+					   uint16_t nb_events,		       \
+					   uint64_t timeout_ticks);	       \
+uint16_t otx2_ssogws_deq_seg_timeout_ ##name(void *port,		       \
+					     struct rte_event *ev,	       \
+					     uint64_t timeout_ticks);	       \
+uint16_t otx2_ssogws_deq_seg_timeout_burst_ ##name(void *port,		       \
+						   struct rte_event ev[],      \
+						   uint16_t nb_events,	       \
+						   uint64_t timeout_ticks);    \
+									       \
+uint16_t otx2_ssogws_dual_deq_ ##name(void *port, struct rte_event *ev,	       \
+				      uint64_t timeout_ticks);		       \
+uint16_t otx2_ssogws_dual_deq_burst_ ##name(void *port,			       \
+					    struct rte_event ev[],	       \
+					    uint16_t nb_events,		       \
+					    uint64_t timeout_ticks);	       \
+uint16_t otx2_ssogws_dual_deq_timeout_ ##name(void *port,		       \
+					      struct rte_event *ev,	       \
+					      uint64_t timeout_ticks);	       \
+uint16_t otx2_ssogws_dual_deq_timeout_burst_ ##name(void *port,		       \
+						    struct rte_event ev[],     \
+						    uint16_t nb_events,	       \
+						    uint64_t timeout_ticks);   \
+uint16_t otx2_ssogws_dual_deq_seg_ ##name(void *port, struct rte_event *ev,    \
+					  uint64_t timeout_ticks);	       \
+uint16_t otx2_ssogws_dual_deq_seg_burst_ ##name(void *port,		       \
+						struct rte_event ev[],	       \
+						uint16_t nb_events,	       \
+						uint64_t timeout_ticks);       \
+uint16_t otx2_ssogws_dual_deq_seg_timeout_ ##name(void *port,		       \
+						  struct rte_event *ev,	       \
+						  uint64_t timeout_ticks);     \
+uint16_t otx2_ssogws_dual_deq_seg_timeout_burst_ ##name(void *port,	       \
+							struct rte_event ev[], \
+							uint16_t nb_events,    \
+						       uint64_t timeout_ticks);\
+
+SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
+#undef R
 
 void sso_updt_xae_cnt(struct otx2_sso_evdev *dev, void *data,
 		      uint32_t event_type);
@@ -265,7 +332,10 @@ int otx2_sso_rx_adapter_queue_add(const struct rte_eventdev *event_dev,
 int otx2_sso_rx_adapter_queue_del(const struct rte_eventdev *event_dev,
 				  const struct rte_eth_dev *eth_dev,
 				  int32_t rx_queue_id);
-
+int otx2_sso_rx_adapter_start(const struct rte_eventdev *event_dev,
+			      const struct rte_eth_dev *eth_dev);
+int otx2_sso_rx_adapter_stop(const struct rte_eventdev *event_dev,
+			     const struct rte_eth_dev *eth_dev);
 /* Clean up API's */
 typedef void (*otx2_handle_event_t)(void *arg, struct rte_event ev);
 void ssogws_flush_events(struct otx2_ssogws *ws, uint8_t queue_id,
diff --git a/drivers/event/octeontx2/otx2_evdev_adptr.c b/drivers/event/octeontx2/otx2_evdev_adptr.c
index 12469fade..e605fd1d4 100644
--- a/drivers/event/octeontx2/otx2_evdev_adptr.c
+++ b/drivers/event/octeontx2/otx2_evdev_adptr.c
@@ -232,6 +232,25 @@ sso_updt_xae_cnt(struct otx2_sso_evdev *dev, void *data, uint32_t event_type)
 	}
 }
 
+static inline void
+sso_updt_lookup_mem(const struct rte_eventdev *event_dev, void *lookup_mem)
+{
+	struct otx2_sso_evdev *dev = sso_pmd_priv(event_dev);
+	int i;
+
+	for (i = 0; i < dev->nb_event_ports; i++) {
+		if (dev->dual_ws) {
+			struct otx2_ssogws_dual *ws = event_dev->data->ports[i];
+
+			ws->lookup_mem = lookup_mem;
+		} else {
+			struct otx2_ssogws *ws = event_dev->data->ports[i];
+
+			ws->lookup_mem = lookup_mem;
+		}
+	}
+}
+
 int
 otx2_sso_rx_adapter_queue_add(const struct rte_eventdev *event_dev,
 			      const struct rte_eth_dev *eth_dev,
@@ -258,6 +277,8 @@ otx2_sso_rx_adapter_queue_add(const struct rte_eventdev *event_dev,
 					     queue_conf->ev.sched_type,
 					     queue_conf->ev.queue_id, port);
 		}
+		rxq = eth_dev->data->rx_queues[0];
+		sso_updt_lookup_mem(event_dev, rxq->lookup_mem);
 	} else {
 		rxq = eth_dev->data->rx_queues[rx_queue_id];
 		sso_updt_xae_cnt(dev, rxq, RTE_EVENT_TYPE_ETHDEV);
@@ -266,6 +287,7 @@ otx2_sso_rx_adapter_queue_add(const struct rte_eventdev *event_dev,
 		rc |= sso_rxq_enable(otx2_eth_dev, (uint16_t)rx_queue_id,
 				     queue_conf->ev.sched_type,
 				     queue_conf->ev.queue_id, port);
+		sso_updt_lookup_mem(event_dev, rxq->lookup_mem);
 	}
 
 	if (rc < 0) {
@@ -274,6 +296,9 @@ otx2_sso_rx_adapter_queue_add(const struct rte_eventdev *event_dev,
 		return rc;
 	}
 
+	dev->rx_offloads |= otx2_eth_dev->rx_offload_flags;
+	sso_fastpath_fns_set((struct rte_eventdev *)(uintptr_t)event_dev);
+
 	return 0;
 }
 
@@ -303,3 +328,23 @@ otx2_sso_rx_adapter_queue_del(const struct rte_eventdev *event_dev,
 
 	return rc;
 }
+
+int
+otx2_sso_rx_adapter_start(const struct rte_eventdev *event_dev,
+			  const struct rte_eth_dev *eth_dev)
+{
+	RTE_SET_USED(event_dev);
+	RTE_SET_USED(eth_dev);
+
+	return 0;
+}
+
+int
+otx2_sso_rx_adapter_stop(const struct rte_eventdev *event_dev,
+			 const struct rte_eth_dev *eth_dev)
+{
+	RTE_SET_USED(event_dev);
+	RTE_SET_USED(eth_dev);
+
+	return 0;
+}
diff --git a/drivers/event/octeontx2/otx2_worker.c b/drivers/event/octeontx2/otx2_worker.c
index 7a6d4cad2..ea2d0b5a4 100644
--- a/drivers/event/octeontx2/otx2_worker.c
+++ b/drivers/event/octeontx2/otx2_worker.c
@@ -81,60 +81,132 @@ otx2_ssogws_release_event(struct otx2_ssogws *ws)
 	otx2_ssogws_swtag_flush(ws);
 }
 
-uint16_t __hot
-otx2_ssogws_deq(void *port, struct rte_event *ev, uint64_t timeout_ticks)
-{
-	struct otx2_ssogws *ws = port;
-
-	RTE_SET_USED(timeout_ticks);
-
-	if (ws->swtag_req) {
-		ws->swtag_req = 0;
-		otx2_ssogws_swtag_wait(ws);
-		return 1;
-	}
-
-	return otx2_ssogws_get_work(ws, ev);
+#define R(name, f5, f4, f3, f2, f1, f0, flags)				\
+uint16_t __hot								\
+otx2_ssogws_deq_ ##name(void *port, struct rte_event *ev,		\
+			uint64_t timeout_ticks)				\
+{									\
+	struct otx2_ssogws *ws = port;					\
+									\
+	RTE_SET_USED(timeout_ticks);					\
+									\
+	if (ws->swtag_req) {						\
+		ws->swtag_req = 0;					\
+		otx2_ssogws_swtag_wait(ws);				\
+		return 1;						\
+	}								\
+									\
+	return otx2_ssogws_get_work(ws, ev, flags, ws->lookup_mem);	\
+}									\
+									\
+uint16_t __hot								\
+otx2_ssogws_deq_burst_ ##name(void *port, struct rte_event ev[],	\
+			      uint16_t nb_events,			\
+			      uint64_t timeout_ticks)			\
+{									\
+	RTE_SET_USED(nb_events);					\
+									\
+	return otx2_ssogws_deq_ ##name(port, ev, timeout_ticks);	\
+}									\
+									\
+uint16_t __hot								\
+otx2_ssogws_deq_timeout_ ##name(void *port, struct rte_event *ev,	\
+				uint64_t timeout_ticks)			\
+{									\
+	struct otx2_ssogws *ws = port;					\
+	uint16_t ret = 1;						\
+	uint64_t iter;							\
+									\
+	if (ws->swtag_req) {						\
+		ws->swtag_req = 0;					\
+		otx2_ssogws_swtag_wait(ws);				\
+		return ret;						\
+	}								\
+									\
+	ret = otx2_ssogws_get_work(ws, ev, flags, ws->lookup_mem);	\
+	for (iter = 1; iter < timeout_ticks && (ret == 0); iter++)	\
+		ret = otx2_ssogws_get_work(ws, ev, flags,		\
+					   ws->lookup_mem);		\
+									\
+	return ret;							\
+}									\
+									\
+uint16_t __hot								\
+otx2_ssogws_deq_timeout_burst_ ##name(void *port, struct rte_event ev[],\
+				      uint16_t nb_events,		\
+				      uint64_t timeout_ticks)		\
+{									\
+	RTE_SET_USED(nb_events);					\
+									\
+	return otx2_ssogws_deq_timeout_ ##name(port, ev, timeout_ticks);\
+}									\
+									\
+uint16_t __hot								\
+otx2_ssogws_deq_seg_ ##name(void *port, struct rte_event *ev,		\
+			    uint64_t timeout_ticks)			\
+{									\
+	struct otx2_ssogws *ws = port;					\
+									\
+	RTE_SET_USED(timeout_ticks);					\
+									\
+	if (ws->swtag_req) {						\
+		ws->swtag_req = 0;					\
+		otx2_ssogws_swtag_wait(ws);				\
+		return 1;						\
+	}								\
+									\
+	return otx2_ssogws_get_work(ws, ev, flags | NIX_RX_MULTI_SEG_F,	\
+				    ws->lookup_mem);			\
+}									\
+									\
+uint16_t __hot								\
+otx2_ssogws_deq_seg_burst_ ##name(void *port, struct rte_event ev[],	\
+				  uint16_t nb_events,			\
+				  uint64_t timeout_ticks)		\
+{									\
+	RTE_SET_USED(nb_events);					\
+									\
+	return otx2_ssogws_deq_seg_ ##name(port, ev, timeout_ticks);	\
+}									\
+									\
+uint16_t __hot								\
+otx2_ssogws_deq_seg_timeout_ ##name(void *port, struct rte_event *ev,	\
+				    uint64_t timeout_ticks)		\
+{									\
+	struct otx2_ssogws *ws = port;					\
+	uint16_t ret = 1;						\
+	uint64_t iter;							\
+									\
+	if (ws->swtag_req) {						\
+		ws->swtag_req = 0;					\
+		otx2_ssogws_swtag_wait(ws);				\
+		return ret;						\
+	}								\
+									\
+	ret = otx2_ssogws_get_work(ws, ev, flags | NIX_RX_MULTI_SEG_F,	\
+				   ws->lookup_mem);			\
+	for (iter = 1; iter < timeout_ticks && (ret == 0); iter++)	\
+		ret = otx2_ssogws_get_work(ws, ev,			\
+					   flags | NIX_RX_MULTI_SEG_F,	\
+					   ws->lookup_mem);		\
+									\
+	return ret;							\
+}									\
+									\
+uint16_t __hot								\
+otx2_ssogws_deq_seg_timeout_burst_ ##name(void *port,			\
+					  struct rte_event ev[],	\
+					  uint16_t nb_events,		\
+					  uint64_t timeout_ticks)	\
+{									\
+	RTE_SET_USED(nb_events);					\
+									\
+	return otx2_ssogws_deq_seg_timeout_ ##name(port, ev,		\
+						   timeout_ticks);	\
 }
 
-uint16_t __hot
-otx2_ssogws_deq_burst(void *port, struct rte_event ev[], uint16_t nb_events,
-		      uint64_t timeout_ticks)
-{
-	RTE_SET_USED(nb_events);
-
-	return otx2_ssogws_deq(port, ev, timeout_ticks);
-}
-
-uint16_t __hot
-otx2_ssogws_deq_timeout(void *port, struct rte_event *ev,
-			uint64_t timeout_ticks)
-{
-	struct otx2_ssogws *ws = port;
-	uint16_t ret = 1;
-	uint64_t iter;
-
-	if (ws->swtag_req) {
-		ws->swtag_req = 0;
-		otx2_ssogws_swtag_wait(ws);
-		return ret;
-	}
-
-	ret = otx2_ssogws_get_work(ws, ev);
-	for (iter = 1; iter < timeout_ticks && (ret == 0); iter++)
-		ret = otx2_ssogws_get_work(ws, ev);
-
-	return ret;
-}
-
-uint16_t __hot
-otx2_ssogws_deq_timeout_burst(void *port, struct rte_event ev[],
-			      uint16_t nb_events, uint64_t timeout_ticks)
-{
-	RTE_SET_USED(nb_events);
-
-	return otx2_ssogws_deq_timeout(port, ev, timeout_ticks);
-}
+SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
+#undef R
 
 uint16_t __hot
 otx2_ssogws_enq(void *port, const struct rte_event *ev)
@@ -221,7 +293,7 @@ ssogws_flush_events(struct otx2_ssogws *ws, uint8_t queue_id, uintptr_t base,
 
 	while (aq_cnt || cq_ds_cnt || ds_cnt) {
 		otx2_write64(val, ws->getwrk_op);
-		otx2_ssogws_get_work_empty(ws, &ev);
+		otx2_ssogws_get_work_empty(ws, &ev, 0);
 		if (fn != NULL && ev.u64 != 0)
 			fn(arg, ev);
 		if (ev.sched_type != SSO_TT_EMPTY)
diff --git a/drivers/event/octeontx2/otx2_worker.h b/drivers/event/octeontx2/otx2_worker.h
index f06ff064e..accf7f956 100644
--- a/drivers/event/octeontx2/otx2_worker.h
+++ b/drivers/event/octeontx2/otx2_worker.h
@@ -14,15 +14,19 @@
 /* SSO Operations */
 
 static __rte_always_inline uint16_t
-otx2_ssogws_get_work(struct otx2_ssogws *ws, struct rte_event *ev)
+otx2_ssogws_get_work(struct otx2_ssogws *ws, struct rte_event *ev,
+		     const uint32_t flags, const void * const lookup_mem)
 {
 	union otx2_sso_event event;
 	uint64_t get_work1;
+	uint64_t mbuf;
 
 	otx2_write64(BIT_ULL(16) | /* wait for work. */
 		     1, /* Use Mask set 0. */
 		     ws->getwrk_op);
 
+	if (flags & NIX_RX_OFFLOAD_PTYPE_F)
+		rte_prefetch_non_temporal(lookup_mem);
 #ifdef RTE_ARCH_ARM64
 	asm volatile(
 			"		ldr %[tag], [%[tag_loc]]	\n"
@@ -34,9 +38,12 @@ otx2_ssogws_get_work(struct otx2_ssogws *ws, struct rte_event *ev)
 			"		ldr %[wqp], [%[wqp_loc]]	\n"
 			"		tbnz %[tag], 63, rty%=		\n"
 			"done%=:	dmb ld				\n"
-			"		prfm pldl1keep, [%[wqp]]	\n"
+			"		prfm pldl1keep, [%[wqp], #8]	\n"
+			"		sub %[mbuf], %[wqp], #0x80	\n"
+			"		prfm pldl1keep, [%[mbuf]]	\n"
 			: [tag] "=&r" (event.get_work0),
-			  [wqp] "=&r" (get_work1)
+			  [wqp] "=&r" (get_work1),
+			  [mbuf] "=&r" (mbuf)
 			: [tag_loc] "r" (ws->tag_op),
 			  [wqp_loc] "r" (ws->wqp_op)
 			);
@@ -47,6 +54,8 @@ otx2_ssogws_get_work(struct otx2_ssogws *ws, struct rte_event *ev)
 
 	get_work1 = otx2_read64(ws->wqp_op);
 	rte_prefetch0((const void *)get_work1);
+	mbuf = (uint64_t)((char *)get_work1 - sizeof(struct rte_mbuf));
+	rte_prefetch0((const void *)mbuf);
 #endif
 
 	event.get_work0 = (event.get_work0 & (0x3ull << 32)) << 6 |
@@ -55,6 +64,12 @@ otx2_ssogws_get_work(struct otx2_ssogws *ws, struct rte_event *ev)
 	ws->cur_tt = event.sched_type;
 	ws->cur_grp = event.queue_id;
 
+	if (event.sched_type != SSO_TT_EMPTY &&
+	    event.event_type == RTE_EVENT_TYPE_ETHDEV) {
+		otx2_wqe_to_mbuf(get_work1, mbuf, event.sub_event_type,
+				 (uint32_t) event.get_work0, flags, lookup_mem);
+		get_work1 = mbuf;
+	}
 
 	ev->event = event.get_work0;
 	ev->u64 = get_work1;
@@ -64,10 +79,12 @@ otx2_ssogws_get_work(struct otx2_ssogws *ws, struct rte_event *ev)
 
 /* Used in cleaning up workslot. */
 static __rte_always_inline uint16_t
-otx2_ssogws_get_work_empty(struct otx2_ssogws *ws, struct rte_event *ev)
+otx2_ssogws_get_work_empty(struct otx2_ssogws *ws, struct rte_event *ev,
+			   const uint32_t flags)
 {
 	union otx2_sso_event event;
 	uint64_t get_work1;
+	uint64_t mbuf;
 
 #ifdef RTE_ARCH_ARM64
 	asm volatile(
@@ -80,9 +97,12 @@ otx2_ssogws_get_work_empty(struct otx2_ssogws *ws, struct rte_event *ev)
 			"		ldr %[wqp], [%[wqp_loc]]	\n"
 			"		tbnz %[tag], 63, rty%=		\n"
 			"done%=:	dmb ld				\n"
-			"		prfm pldl1keep, [%[wqp]]	\n"
+			"		prfm pldl1keep, [%[wqp], #8]	\n"
+			"		sub %[mbuf], %[wqp], #0x80	\n"
+			"		prfm pldl1keep, [%[mbuf]]	\n"
 			: [tag] "=&r" (event.get_work0),
-			  [wqp] "=&r" (get_work1)
+			  [wqp] "=&r" (get_work1),
+			  [mbuf] "=&r" (mbuf)
 			: [tag_loc] "r" (ws->tag_op),
 			  [wqp_loc] "r" (ws->wqp_op)
 			);
@@ -92,7 +112,9 @@ otx2_ssogws_get_work_empty(struct otx2_ssogws *ws, struct rte_event *ev)
 		event.get_work0 = otx2_read64(ws->tag_op);
 
 	get_work1 = otx2_read64(ws->wqp_op);
-	rte_prefetch0((const void *)get_work1);
+	rte_prefetch_non_temporal((const void *)get_work1);
+	mbuf = (uint64_t)((char *)get_work1 - sizeof(struct rte_mbuf));
+	rte_prefetch_non_temporal((const void *)mbuf);
 #endif
 
 	event.get_work0 = (event.get_work0 & (0x3ull << 32)) << 6 |
@@ -101,6 +123,13 @@ otx2_ssogws_get_work_empty(struct otx2_ssogws *ws, struct rte_event *ev)
 	ws->cur_tt = event.sched_type;
 	ws->cur_grp = event.queue_id;
 
+	if (event.sched_type != SSO_TT_EMPTY &&
+	    event.event_type == RTE_EVENT_TYPE_ETHDEV) {
+		otx2_wqe_to_mbuf(get_work1, mbuf, event.sub_event_type,
+				 (uint32_t) event.get_work0, flags, NULL);
+		get_work1 = mbuf;
+	}
+
 	ev->event = event.get_work0;
 	ev->u64 = get_work1;
 
diff --git a/drivers/event/octeontx2/otx2_worker_dual.c b/drivers/event/octeontx2/otx2_worker_dual.c
index 58fd588f6..b5cf9ac12 100644
--- a/drivers/event/octeontx2/otx2_worker_dual.c
+++ b/drivers/event/octeontx2/otx2_worker_dual.c
@@ -140,68 +140,162 @@ otx2_ssogws_dual_enq_fwd_burst(void *port, const struct rte_event ev[],
 	return 1;
 }
 
-uint16_t __hot
-otx2_ssogws_dual_deq(void *port, struct rte_event *ev, uint64_t timeout_ticks)
-{
-	struct otx2_ssogws_dual *ws = port;
-	uint8_t gw;
-
-	RTE_SET_USED(timeout_ticks);
-	if (ws->swtag_req) {
-		otx2_ssogws_swtag_wait((struct otx2_ssogws *)
-				       &ws->ws_state[!ws->vws]);
-		ws->swtag_req = 0;
-		return 1;
-	}
-
-	gw = otx2_ssogws_dual_get_work(&ws->ws_state[ws->vws],
-				       &ws->ws_state[!ws->vws], ev);
-	ws->vws = !ws->vws;
-
-	return gw;
-}
-
-uint16_t __hot
-otx2_ssogws_dual_deq_burst(void *port, struct rte_event ev[],
-			   uint16_t nb_events, uint64_t timeout_ticks)
-{
-	RTE_SET_USED(nb_events);
-
-	return otx2_ssogws_dual_deq(port, ev, timeout_ticks);
-}
-
-uint16_t __hot
-otx2_ssogws_dual_deq_timeout(void *port, struct rte_event *ev,
-			     uint64_t timeout_ticks)
-{
-	struct otx2_ssogws_dual *ws = port;
-	uint64_t iter;
-	uint8_t gw;
-
-	if (ws->swtag_req) {
-		otx2_ssogws_swtag_wait((struct otx2_ssogws *)
-				       &ws->ws_state[!ws->vws]);
-		ws->swtag_req = 0;
-		return 1;
-	}
-
-	gw = otx2_ssogws_dual_get_work(&ws->ws_state[ws->vws],
-				       &ws->ws_state[!ws->vws], ev);
-	ws->vws = !ws->vws;
-	for (iter = 1; iter < timeout_ticks && (gw == 0); iter++) {
-		gw = otx2_ssogws_dual_get_work(&ws->ws_state[ws->vws],
-					       &ws->ws_state[!ws->vws], ev);
-		ws->vws = !ws->vws;
-	}
-
-	return gw;
+#define R(name, f5, f4, f3, f2, f1, f0, flags)				\
+uint16_t __hot								\
+otx2_ssogws_dual_deq_ ##name(void *port, struct rte_event *ev,		\
+			     uint64_t timeout_ticks)			\
+{									\
+	struct otx2_ssogws_dual *ws = port;				\
+	uint8_t gw;							\
+									\
+	RTE_SET_USED(timeout_ticks);					\
+	if (ws->swtag_req) {						\
+		otx2_ssogws_swtag_wait((struct otx2_ssogws *)		\
+				       &ws->ws_state[!ws->vws]);	\
+		ws->swtag_req = 0;					\
+		return 1;						\
+	}								\
+									\
+	gw = otx2_ssogws_dual_get_work(&ws->ws_state[ws->vws],		\
+				       &ws->ws_state[!ws->vws], ev,	\
+				       flags, ws->lookup_mem);		\
+	ws->vws = !ws->vws;						\
+									\
+	return gw;							\
+}									\
+									\
+uint16_t __hot								\
+otx2_ssogws_dual_deq_burst_ ##name(void *port, struct rte_event ev[],	\
+				   uint16_t nb_events,			\
+				   uint64_t timeout_ticks)		\
+{									\
+	RTE_SET_USED(nb_events);					\
+									\
+	return otx2_ssogws_dual_deq_ ##name(port, ev, timeout_ticks);	\
+}									\
+									\
+uint16_t __hot								\
+otx2_ssogws_dual_deq_timeout_ ##name(void *port, struct rte_event *ev,	\
+				     uint64_t timeout_ticks)		\
+{									\
+	struct otx2_ssogws_dual *ws = port;				\
+	uint64_t iter;							\
+	uint8_t gw;							\
+									\
+	if (ws->swtag_req) {						\
+		otx2_ssogws_swtag_wait((struct otx2_ssogws *)		\
+				       &ws->ws_state[!ws->vws]);	\
+		ws->swtag_req = 0;					\
+		return 1;						\
+	}								\
+									\
+	gw = otx2_ssogws_dual_get_work(&ws->ws_state[ws->vws],		\
+				       &ws->ws_state[!ws->vws], ev,	\
+				       flags, ws->lookup_mem);		\
+	ws->vws = !ws->vws;						\
+	for (iter = 1; iter < timeout_ticks && (gw == 0); iter++) {	\
+		gw = otx2_ssogws_dual_get_work(&ws->ws_state[ws->vws],	\
+					       &ws->ws_state[!ws->vws],	\
+					       ev, flags,		\
+					       ws->lookup_mem);		\
+		ws->vws = !ws->vws;					\
+	}								\
+									\
+	return gw;							\
+}									\
+									\
+uint16_t __hot								\
+otx2_ssogws_dual_deq_timeout_burst_ ##name(void *port,			\
+					   struct rte_event ev[],	\
+					   uint16_t nb_events,		\
+					   uint64_t timeout_ticks)	\
+{									\
+	RTE_SET_USED(nb_events);					\
+									\
+	return otx2_ssogws_dual_deq_timeout_ ##name(port, ev,		\
+						    timeout_ticks);	\
+}									\
+									\
+uint16_t __hot								\
+otx2_ssogws_dual_deq_seg_ ##name(void *port, struct rte_event *ev,	\
+				 uint64_t timeout_ticks)		\
+{									\
+	struct otx2_ssogws_dual *ws = port;				\
+	uint8_t gw;							\
+									\
+	RTE_SET_USED(timeout_ticks);					\
+	if (ws->swtag_req) {						\
+		otx2_ssogws_swtag_wait((struct otx2_ssogws *)		\
+				       &ws->ws_state[!ws->vws]);	\
+		ws->swtag_req = 0;					\
+		return 1;						\
+	}								\
+									\
+	gw = otx2_ssogws_dual_get_work(&ws->ws_state[ws->vws],		\
+				       &ws->ws_state[!ws->vws], ev,	\
+				       flags | NIX_RX_MULTI_SEG_F,	\
+				       ws->lookup_mem);			\
+	ws->vws = !ws->vws;						\
+									\
+	return gw;							\
+}									\
+									\
+uint16_t __hot								\
+otx2_ssogws_dual_deq_seg_burst_ ##name(void *port,			\
+				       struct rte_event ev[],		\
+				       uint16_t nb_events,		\
+				       uint64_t timeout_ticks)		\
+{									\
+	RTE_SET_USED(nb_events);					\
+									\
+	return otx2_ssogws_dual_deq_seg_ ##name(port, ev,		\
+						timeout_ticks);		\
+}									\
+									\
+uint16_t __hot								\
+otx2_ssogws_dual_deq_seg_timeout_ ##name(void *port,			\
+					 struct rte_event *ev,		\
+					 uint64_t timeout_ticks)	\
+{									\
+	struct otx2_ssogws_dual *ws = port;				\
+	uint64_t iter;							\
+	uint8_t gw;							\
+									\
+	if (ws->swtag_req) {						\
+		otx2_ssogws_swtag_wait((struct otx2_ssogws *)		\
+				       &ws->ws_state[!ws->vws]);	\
+		ws->swtag_req = 0;					\
+		return 1;						\
+	}								\
+									\
+	gw = otx2_ssogws_dual_get_work(&ws->ws_state[ws->vws],		\
+				       &ws->ws_state[!ws->vws], ev,	\
+				       flags | NIX_RX_MULTI_SEG_F,	\
+				       ws->lookup_mem);			\
+	ws->vws = !ws->vws;						\
+	for (iter = 1; iter < timeout_ticks && (gw == 0); iter++) {	\
+		gw = otx2_ssogws_dual_get_work(&ws->ws_state[ws->vws],	\
+					       &ws->ws_state[!ws->vws],	\
+					       ev, flags |		\
+					       NIX_RX_MULTI_SEG_F,	\
+					       ws->lookup_mem);		\
+		ws->vws = !ws->vws;					\
+	}								\
+									\
+	return gw;							\
+}									\
+									\
+uint16_t __hot								\
+otx2_ssogws_dual_deq_seg_timeout_burst_ ##name(void *port,		\
+					       struct rte_event ev[],	\
+					       uint16_t nb_events,	\
+					       uint64_t timeout_ticks)	\
+{									\
+	RTE_SET_USED(nb_events);					\
+									\
+	return otx2_ssogws_dual_deq_seg_timeout_ ##name(port, ev,	\
+							timeout_ticks);	\
 }
 
-uint16_t __hot
-otx2_ssogws_dual_deq_timeout_burst(void *port, struct rte_event ev[],
-				   uint16_t nb_events, uint64_t timeout_ticks)
-{
-	RTE_SET_USED(nb_events);
-
-	return otx2_ssogws_dual_deq_timeout(port, ev, timeout_ticks);
-}
+SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
+#undef R
diff --git a/drivers/event/octeontx2/otx2_worker_dual.h b/drivers/event/octeontx2/otx2_worker_dual.h
index d8453d1f7..32fe61b44 100644
--- a/drivers/event/octeontx2/otx2_worker_dual.h
+++ b/drivers/event/octeontx2/otx2_worker_dual.h
@@ -15,12 +15,16 @@
 static __rte_always_inline uint16_t
 otx2_ssogws_dual_get_work(struct otx2_ssogws_state *ws,
 			  struct otx2_ssogws_state *ws_pair,
-			  struct rte_event *ev)
+			  struct rte_event *ev, const uint32_t flags,
+			  const void * const lookup_mem)
 {
 	const uint64_t set_gw = BIT_ULL(16) | 1;
 	union otx2_sso_event event;
 	uint64_t get_work1;
+	uint64_t mbuf;
 
+	if (flags & NIX_RX_OFFLOAD_PTYPE_F)
+		rte_prefetch_non_temporal(lookup_mem);
 #ifdef RTE_ARCH_ARM64
 	asm volatile(
 			"        ldr %[tag], [%[tag_loc]]    \n"
@@ -33,9 +37,12 @@ otx2_ssogws_dual_get_work(struct otx2_ssogws_state *ws,
 			"        tbnz %[tag], 63, rty%=      \n"
 			"done%=: str %[gw], [%[pong]]        \n"
 			"        dmb ld                      \n"
-			"        prfm pldl1keep, [%[wqp]]    \n"
+			"        prfm pldl1keep, [%[wqp], #8]\n"
+			"        sub %[mbuf], %[wqp], #0x80  \n"
+			"        prfm pldl1keep, [%[mbuf]]   \n"
 			: [tag] "=&r" (event.get_work0),
-			  [wqp] "=&r" (get_work1)
+			  [wqp] "=&r" (get_work1),
+			  [mbuf] "=&r" (mbuf)
 			: [tag_loc] "r" (ws->tag_op),
 			  [wqp_loc] "r" (ws->wqp_op),
 			  [gw] "r" (set_gw),
@@ -49,6 +56,8 @@ otx2_ssogws_dual_get_work(struct otx2_ssogws_state *ws,
 	otx2_write64(set_gw, ws_pair->getwrk_op);
 
 	rte_prefetch0((const void *)get_work1);
+	mbuf = (uint64_t)((char *)get_work1 - sizeof(struct rte_mbuf));
+	rte_prefetch0((const void *)mbuf);
 #endif
 	event.get_work0 = (event.get_work0 & (0x3ull << 32)) << 6 |
 		(event.get_work0 & (0x3FFull << 36)) << 4 |
@@ -56,6 +65,13 @@ otx2_ssogws_dual_get_work(struct otx2_ssogws_state *ws,
 	ws->cur_tt = event.sched_type;
 	ws->cur_grp = event.queue_id;
 
+	if (event.sched_type != SSO_TT_EMPTY &&
+	    event.event_type == RTE_EVENT_TYPE_ETHDEV) {
+		otx2_wqe_to_mbuf(get_work1, mbuf, event.sub_event_type,
+				 (uint32_t) event.get_work0, flags, lookup_mem);
+		get_work1 = mbuf;
+	}
+
 	ev->event = event.get_work0;
 	ev->u64 = get_work1;
 
-- 
2.22.0

[dpdk-dev] [PATCH v4 4/5] event/octeontx2: add PTP support for SSO

[pbhagavatula]

From: Harman Kalra <hkalra@marvell.com>

Add PTP support for SSO based on rx_offloads of the queue connected to
it.

Signed-off-by: Harman Kalra <hkalra@marvell.com>
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
---
 drivers/event/octeontx2/otx2_evdev.c       |  2 ++
 drivers/event/octeontx2/otx2_evdev.h       |  6 ++++++
 drivers/event/octeontx2/otx2_evdev_adptr.c |  1 +
 drivers/event/octeontx2/otx2_worker.h      |  6 ++++++
 drivers/event/octeontx2/otx2_worker_dual.c | 18 ++++++++++++------
 drivers/event/octeontx2/otx2_worker_dual.h |  5 ++++-
 6 files changed, 31 insertions(+), 7 deletions(-)

diff --git a/drivers/event/octeontx2/otx2_evdev.c b/drivers/event/octeontx2/otx2_evdev.c
index f45fc008d..ca75e4215 100644
--- a/drivers/event/octeontx2/otx2_evdev.c
+++ b/drivers/event/octeontx2/otx2_evdev.c
@@ -1095,6 +1095,7 @@ otx2_sso_port_setup(struct rte_eventdev *event_dev, uint8_t port_id,
 			   sizeof(uintptr_t) * OTX2_SSO_MAX_VHGRP);
 		ws->fc_mem = dev->fc_mem;
 		ws->xaq_lmt = dev->xaq_lmt;
+		ws->tstamp = dev->tstamp;
 		otx2_write64(val, OTX2_SSOW_GET_BASE_ADDR(
 			     ws->ws_state[0].getwrk_op) + SSOW_LF_GWS_NW_TIM);
 		otx2_write64(val, OTX2_SSOW_GET_BASE_ADDR(
@@ -1107,6 +1108,7 @@ otx2_sso_port_setup(struct rte_eventdev *event_dev, uint8_t port_id,
 			   sizeof(uintptr_t) * OTX2_SSO_MAX_VHGRP);
 		ws->fc_mem = dev->fc_mem;
 		ws->xaq_lmt = dev->xaq_lmt;
+		ws->tstamp = dev->tstamp;
 		otx2_write64(val, base + SSOW_LF_GWS_NW_TIM);
 	}
 
diff --git a/drivers/event/octeontx2/otx2_evdev.h b/drivers/event/octeontx2/otx2_evdev.h
index a81a8be6f..2df9ec468 100644
--- a/drivers/event/octeontx2/otx2_evdev.h
+++ b/drivers/event/octeontx2/otx2_evdev.h
@@ -149,6 +149,8 @@ struct otx2_sso_evdev {
 	/* MSIX offsets */
 	uint16_t sso_msixoff[OTX2_SSO_MAX_VHGRP];
 	uint16_t ssow_msixoff[OTX2_SSO_MAX_VHWS];
+	/* PTP timestamp */
+	struct otx2_timesync_info *tstamp;
 } __rte_cache_aligned;
 
 #define OTX2_SSOGWS_OPS \
@@ -173,6 +175,8 @@ struct otx2_ssogws {
 	uint64_t xaq_lmt __rte_cache_aligned;
 	uint64_t *fc_mem;
 	uintptr_t grps_base[OTX2_SSO_MAX_VHGRP];
+	/* PTP timestamp */
+	struct otx2_timesync_info *tstamp;
 } __rte_cache_aligned;
 
 struct otx2_ssogws_state {
@@ -190,6 +194,8 @@ struct otx2_ssogws_dual {
 	uint64_t xaq_lmt __rte_cache_aligned;
 	uint64_t *fc_mem;
 	uintptr_t grps_base[OTX2_SSO_MAX_VHGRP];
+	/* PTP timestamp */
+	struct otx2_timesync_info *tstamp;
 } __rte_cache_aligned;
 
 static inline struct otx2_sso_evdev *
diff --git a/drivers/event/octeontx2/otx2_evdev_adptr.c b/drivers/event/octeontx2/otx2_evdev_adptr.c
index e605fd1d4..e5aaa67b6 100644
--- a/drivers/event/octeontx2/otx2_evdev_adptr.c
+++ b/drivers/event/octeontx2/otx2_evdev_adptr.c
@@ -297,6 +297,7 @@ otx2_sso_rx_adapter_queue_add(const struct rte_eventdev *event_dev,
 	}
 
 	dev->rx_offloads |= otx2_eth_dev->rx_offload_flags;
+	dev->tstamp = &otx2_eth_dev->tstamp;
 	sso_fastpath_fns_set((struct rte_eventdev *)(uintptr_t)event_dev);
 
 	return 0;
diff --git a/drivers/event/octeontx2/otx2_worker.h b/drivers/event/octeontx2/otx2_worker.h
index accf7f956..1e1e947ef 100644
--- a/drivers/event/octeontx2/otx2_worker.h
+++ b/drivers/event/octeontx2/otx2_worker.h
@@ -68,6 +68,9 @@ otx2_ssogws_get_work(struct otx2_ssogws *ws, struct rte_event *ev,
 	    event.event_type == RTE_EVENT_TYPE_ETHDEV) {
 		otx2_wqe_to_mbuf(get_work1, mbuf, event.sub_event_type,
 				 (uint32_t) event.get_work0, flags, lookup_mem);
+		/* Extracting tstamp, if PTP enabled*/
+		otx2_nix_mbuf_to_tstamp((struct rte_mbuf *)mbuf, ws->tstamp,
+					flags);
 		get_work1 = mbuf;
 	}
 
@@ -127,6 +130,9 @@ otx2_ssogws_get_work_empty(struct otx2_ssogws *ws, struct rte_event *ev,
 	    event.event_type == RTE_EVENT_TYPE_ETHDEV) {
 		otx2_wqe_to_mbuf(get_work1, mbuf, event.sub_event_type,
 				 (uint32_t) event.get_work0, flags, NULL);
+		/* Extracting tstamp, if PTP enabled*/
+		otx2_nix_mbuf_to_tstamp((struct rte_mbuf *)mbuf, ws->tstamp,
+					flags);
 		get_work1 = mbuf;
 	}
 
diff --git a/drivers/event/octeontx2/otx2_worker_dual.c b/drivers/event/octeontx2/otx2_worker_dual.c
index b5cf9ac12..cbe03c1bb 100644
--- a/drivers/event/octeontx2/otx2_worker_dual.c
+++ b/drivers/event/octeontx2/otx2_worker_dual.c
@@ -158,7 +158,8 @@ otx2_ssogws_dual_deq_ ##name(void *port, struct rte_event *ev,		\
 									\
 	gw = otx2_ssogws_dual_get_work(&ws->ws_state[ws->vws],		\
 				       &ws->ws_state[!ws->vws], ev,	\
-				       flags, ws->lookup_mem);		\
+				       flags, ws->lookup_mem,		\
+				       ws->tstamp);			\
 	ws->vws = !ws->vws;						\
 									\
 	return gw;							\
@@ -191,13 +192,15 @@ otx2_ssogws_dual_deq_timeout_ ##name(void *port, struct rte_event *ev,	\
 									\
 	gw = otx2_ssogws_dual_get_work(&ws->ws_state[ws->vws],		\
 				       &ws->ws_state[!ws->vws], ev,	\
-				       flags, ws->lookup_mem);		\
+				       flags, ws->lookup_mem,		\
+				       ws->tstamp);			\
 	ws->vws = !ws->vws;						\
 	for (iter = 1; iter < timeout_ticks && (gw == 0); iter++) {	\
 		gw = otx2_ssogws_dual_get_work(&ws->ws_state[ws->vws],	\
 					       &ws->ws_state[!ws->vws],	\
 					       ev, flags,		\
-					       ws->lookup_mem);		\
+					       ws->lookup_mem,		\
+					       ws->tstamp);		\
 		ws->vws = !ws->vws;					\
 	}								\
 									\
@@ -234,7 +237,8 @@ otx2_ssogws_dual_deq_seg_ ##name(void *port, struct rte_event *ev,	\
 	gw = otx2_ssogws_dual_get_work(&ws->ws_state[ws->vws],		\
 				       &ws->ws_state[!ws->vws], ev,	\
 				       flags | NIX_RX_MULTI_SEG_F,	\
-				       ws->lookup_mem);			\
+				       ws->lookup_mem,			\
+				       ws->tstamp);			\
 	ws->vws = !ws->vws;						\
 									\
 	return gw;							\
@@ -271,14 +275,16 @@ otx2_ssogws_dual_deq_seg_timeout_ ##name(void *port,			\
 	gw = otx2_ssogws_dual_get_work(&ws->ws_state[ws->vws],		\
 				       &ws->ws_state[!ws->vws], ev,	\
 				       flags | NIX_RX_MULTI_SEG_F,	\
-				       ws->lookup_mem);			\
+				       ws->lookup_mem,			\
+				       ws->tstamp);			\
 	ws->vws = !ws->vws;						\
 	for (iter = 1; iter < timeout_ticks && (gw == 0); iter++) {	\
 		gw = otx2_ssogws_dual_get_work(&ws->ws_state[ws->vws],	\
 					       &ws->ws_state[!ws->vws],	\
 					       ev, flags |		\
 					       NIX_RX_MULTI_SEG_F,	\
-					       ws->lookup_mem);		\
+					       ws->lookup_mem,		\
+					       ws->tstamp);		\
 		ws->vws = !ws->vws;					\
 	}								\
 									\
diff --git a/drivers/event/octeontx2/otx2_worker_dual.h b/drivers/event/octeontx2/otx2_worker_dual.h
index 32fe61b44..4a72f424d 100644
--- a/drivers/event/octeontx2/otx2_worker_dual.h
+++ b/drivers/event/octeontx2/otx2_worker_dual.h
@@ -16,7 +16,8 @@ static __rte_always_inline uint16_t
 otx2_ssogws_dual_get_work(struct otx2_ssogws_state *ws,
 			  struct otx2_ssogws_state *ws_pair,
 			  struct rte_event *ev, const uint32_t flags,
-			  const void * const lookup_mem)
+			  const void * const lookup_mem,
+			  struct otx2_timesync_info * const tstamp)
 {
 	const uint64_t set_gw = BIT_ULL(16) | 1;
 	union otx2_sso_event event;
@@ -69,6 +70,8 @@ otx2_ssogws_dual_get_work(struct otx2_ssogws_state *ws,
 	    event.event_type == RTE_EVENT_TYPE_ETHDEV) {
 		otx2_wqe_to_mbuf(get_work1, mbuf, event.sub_event_type,
 				 (uint32_t) event.get_work0, flags, lookup_mem);
+		/* Extracting tstamp, if PTP enabled*/
+		otx2_nix_mbuf_to_tstamp((struct rte_mbuf *)mbuf, tstamp, flags);
 		get_work1 = mbuf;
 	}
 
-- 
2.22.0

[dpdk-dev] [PATCH v4 5/5] event/octeontx2: add Tx adadpter support

[pbhagavatula]

From: Pavan Nikhilesh <pbhagavatula@marvell.com>

Add event eth Tx adapter support to octeontx2 SSO.

Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
---
 drivers/event/octeontx2/otx2_evdev.c       | 79 ++++++++++++++++++++
 drivers/event/octeontx2/otx2_evdev.h       | 32 ++++++++
 drivers/event/octeontx2/otx2_evdev_adptr.c | 86 ++++++++++++++++++++++
 drivers/event/octeontx2/otx2_worker.c      | 29 ++++++++
 drivers/event/octeontx2/otx2_worker.h      | 49 ++++++++++++
 drivers/event/octeontx2/otx2_worker_dual.c | 35 +++++++++
 6 files changed, 310 insertions(+)

diff --git a/drivers/event/octeontx2/otx2_evdev.c b/drivers/event/octeontx2/otx2_evdev.c
index ca75e4215..56716c2ac 100644
--- a/drivers/event/octeontx2/otx2_evdev.c
+++ b/drivers/event/octeontx2/otx2_evdev.c
@@ -168,6 +168,39 @@ SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
 #undef R
 	};
 
+	/* Tx modes */
+	const event_tx_adapter_enqueue ssogws_tx_adptr_enq[2][2][2][2][2] = {
+#define T(name, f4, f3, f2, f1, f0, sz, flags)				\
+		[f4][f3][f2][f1][f0] =  otx2_ssogws_tx_adptr_enq_ ## name,
+SSO_TX_ADPTR_ENQ_FASTPATH_FUNC
+#undef T
+	};
+
+	const event_tx_adapter_enqueue
+		ssogws_tx_adptr_enq_seg[2][2][2][2][2] = {
+#define T(name, f4, f3, f2, f1, f0, sz, flags)				\
+		[f4][f3][f2][f1][f0] =  otx2_ssogws_tx_adptr_enq_seg_ ## name,
+SSO_TX_ADPTR_ENQ_FASTPATH_FUNC
+#undef T
+	};
+
+	const event_tx_adapter_enqueue
+		ssogws_dual_tx_adptr_enq[2][2][2][2][2] = {
+#define T(name, f4, f3, f2, f1, f0, sz, flags)				\
+		[f4][f3][f2][f1][f0] =  otx2_ssogws_dual_tx_adptr_enq_ ## name,
+SSO_TX_ADPTR_ENQ_FASTPATH_FUNC
+#undef T
+	};
+
+	const event_tx_adapter_enqueue
+		ssogws_dual_tx_adptr_enq_seg[2][2][2][2][2] = {
+#define T(name, f4, f3, f2, f1, f0, sz, flags)				\
+		[f4][f3][f2][f1][f0] =					\
+			otx2_ssogws_dual_tx_adptr_enq_seg_ ## name,
+SSO_TX_ADPTR_ENQ_FASTPATH_FUNC
+#undef T
+	};
+
 	event_dev->enqueue			= otx2_ssogws_enq;
 	event_dev->enqueue_burst		= otx2_ssogws_enq_burst;
 	event_dev->enqueue_new_burst		= otx2_ssogws_enq_new_burst;
@@ -238,6 +271,23 @@ SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
 		}
 	}
 
+	if (dev->tx_offloads & NIX_TX_MULTI_SEG_F) {
+		/* [TSMP] [MBUF_NOFF] [VLAN] [OL3_L4_CSUM] [L3_L4_CSUM] */
+		event_dev->txa_enqueue = ssogws_tx_adptr_enq_seg
+			[!!(dev->tx_offloads & NIX_TX_OFFLOAD_TSTAMP_F)]
+			[!!(dev->tx_offloads & NIX_TX_OFFLOAD_MBUF_NOFF_F)]
+			[!!(dev->tx_offloads & NIX_TX_OFFLOAD_VLAN_QINQ_F)]
+			[!!(dev->tx_offloads & NIX_TX_OFFLOAD_OL3_OL4_CSUM_F)]
+			[!!(dev->tx_offloads & NIX_TX_OFFLOAD_L3_L4_CSUM_F)];
+	} else {
+		event_dev->txa_enqueue = ssogws_tx_adptr_enq
+			[!!(dev->tx_offloads & NIX_TX_OFFLOAD_TSTAMP_F)]
+			[!!(dev->tx_offloads & NIX_TX_OFFLOAD_MBUF_NOFF_F)]
+			[!!(dev->tx_offloads & NIX_TX_OFFLOAD_VLAN_QINQ_F)]
+			[!!(dev->tx_offloads & NIX_TX_OFFLOAD_OL3_OL4_CSUM_F)]
+			[!!(dev->tx_offloads & NIX_TX_OFFLOAD_L3_L4_CSUM_F)];
+	}
+
 	if (dev->dual_ws) {
 		event_dev->enqueue		= otx2_ssogws_dual_enq;
 		event_dev->enqueue_burst	= otx2_ssogws_dual_enq_burst;
@@ -352,6 +402,31 @@ SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
 							NIX_RX_OFFLOAD_RSS_F)];
 			}
 		}
+
+		if (dev->tx_offloads & NIX_TX_MULTI_SEG_F) {
+		/* [TSMP] [MBUF_NOFF] [VLAN] [OL3_L4_CSUM] [L3_L4_CSUM] */
+			event_dev->txa_enqueue = ssogws_dual_tx_adptr_enq_seg
+				[!!(dev->tx_offloads & NIX_TX_OFFLOAD_TSTAMP_F)]
+				[!!(dev->tx_offloads &
+						NIX_TX_OFFLOAD_MBUF_NOFF_F)]
+				[!!(dev->tx_offloads &
+						NIX_TX_OFFLOAD_VLAN_QINQ_F)]
+				[!!(dev->tx_offloads &
+						NIX_TX_OFFLOAD_OL3_OL4_CSUM_F)]
+				[!!(dev->tx_offloads &
+						NIX_TX_OFFLOAD_L3_L4_CSUM_F)];
+		} else {
+			event_dev->txa_enqueue = ssogws_dual_tx_adptr_enq
+				[!!(dev->tx_offloads & NIX_TX_OFFLOAD_TSTAMP_F)]
+				[!!(dev->tx_offloads &
+						NIX_TX_OFFLOAD_MBUF_NOFF_F)]
+				[!!(dev->tx_offloads &
+						NIX_TX_OFFLOAD_VLAN_QINQ_F)]
+				[!!(dev->tx_offloads &
+						NIX_TX_OFFLOAD_OL3_OL4_CSUM_F)]
+				[!!(dev->tx_offloads &
+						NIX_TX_OFFLOAD_L3_L4_CSUM_F)];
+		}
 	}
 	rte_mb();
 }
@@ -1413,6 +1488,10 @@ static struct rte_eventdev_ops otx2_sso_ops = {
 	.eth_rx_adapter_start = otx2_sso_rx_adapter_start,
 	.eth_rx_adapter_stop = otx2_sso_rx_adapter_stop,
 
+	.eth_tx_adapter_caps_get = otx2_sso_tx_adapter_caps_get,
+	.eth_tx_adapter_queue_add = otx2_sso_tx_adapter_queue_add,
+	.eth_tx_adapter_queue_del = otx2_sso_tx_adapter_queue_del,
+
 	.timer_adapter_caps_get = otx2_tim_caps_get,
 
 	.xstats_get       = otx2_sso_xstats_get,
diff --git a/drivers/event/octeontx2/otx2_evdev.h b/drivers/event/octeontx2/otx2_evdev.h
index 2df9ec468..9c9718f6f 100644
--- a/drivers/event/octeontx2/otx2_evdev.h
+++ b/drivers/event/octeontx2/otx2_evdev.h
@@ -8,6 +8,7 @@
 #include <rte_eventdev.h>
 #include <rte_eventdev_pmd.h>
 #include <rte_event_eth_rx_adapter.h>
+#include <rte_event_eth_tx_adapter.h>
 
 #include "otx2_common.h"
 #include "otx2_dev.h"
@@ -21,6 +22,7 @@
 #define OTX2_SSO_MAX_VHGRP                  RTE_EVENT_MAX_QUEUES_PER_DEV
 #define OTX2_SSO_MAX_VHWS                   (UINT8_MAX)
 #define OTX2_SSO_FC_NAME                    "otx2_evdev_xaq_fc"
+#define OTX2_SSO_SQB_LIMIT                  (0x180)
 #define OTX2_SSO_XAQ_SLACK                  (8)
 #define OTX2_SSO_XAQ_CACHE_CNT              (0x7)
 
@@ -133,6 +135,7 @@ struct otx2_sso_evdev {
 	rte_iova_t fc_iova;
 	struct rte_mempool *xaq_pool;
 	uint64_t rx_offloads;
+	uint64_t tx_offloads;
 	uint16_t rx_adptr_pool_cnt;
 	uint32_t adptr_xae_cnt;
 	uint64_t *rx_adptr_pools;
@@ -323,6 +326,22 @@ uint16_t otx2_ssogws_dual_deq_seg_timeout_burst_ ##name(void *port,	       \
 SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
 #undef R
 
+#define T(name, f4, f3, f2, f1, f0, sz, flags)				     \
+uint16_t otx2_ssogws_tx_adptr_enq_ ## name(void *port, struct rte_event ev[],\
+					   uint16_t nb_events);		     \
+uint16_t otx2_ssogws_tx_adptr_enq_seg_ ## name(void *port,		     \
+					       struct rte_event ev[],	     \
+					       uint16_t nb_events);	     \
+uint16_t otx2_ssogws_dual_tx_adptr_enq_ ## name(void *port,		     \
+						struct rte_event ev[],	     \
+						uint16_t nb_events);	     \
+uint16_t otx2_ssogws_dual_tx_adptr_enq_seg_ ## name(void *port,		     \
+						    struct rte_event ev[],   \
+						    uint16_t nb_events);     \
+
+SSO_TX_ADPTR_ENQ_FASTPATH_FUNC
+#undef T
+
 void sso_updt_xae_cnt(struct otx2_sso_evdev *dev, void *data,
 		      uint32_t event_type);
 int sso_xae_reconfigure(struct rte_eventdev *event_dev);
@@ -342,6 +361,19 @@ int otx2_sso_rx_adapter_start(const struct rte_eventdev *event_dev,
 			      const struct rte_eth_dev *eth_dev);
 int otx2_sso_rx_adapter_stop(const struct rte_eventdev *event_dev,
 			     const struct rte_eth_dev *eth_dev);
+int otx2_sso_tx_adapter_caps_get(const struct rte_eventdev *dev,
+				 const struct rte_eth_dev *eth_dev,
+				 uint32_t *caps);
+int otx2_sso_tx_adapter_queue_add(uint8_t id,
+				  const struct rte_eventdev *event_dev,
+				  const struct rte_eth_dev *eth_dev,
+				  int32_t tx_queue_id);
+
+int otx2_sso_tx_adapter_queue_del(uint8_t id,
+				  const struct rte_eventdev *event_dev,
+				  const struct rte_eth_dev *eth_dev,
+				  int32_t tx_queue_id);
+
 /* Clean up API's */
 typedef void (*otx2_handle_event_t)(void *arg, struct rte_event ev);
 void ssogws_flush_events(struct otx2_ssogws *ws, uint8_t queue_id,
diff --git a/drivers/event/octeontx2/otx2_evdev_adptr.c b/drivers/event/octeontx2/otx2_evdev_adptr.c
index e5aaa67b6..0c4f18ec2 100644
--- a/drivers/event/octeontx2/otx2_evdev_adptr.c
+++ b/drivers/event/octeontx2/otx2_evdev_adptr.c
@@ -349,3 +349,89 @@ otx2_sso_rx_adapter_stop(const struct rte_eventdev *event_dev,
 
 	return 0;
 }
+
+int
+otx2_sso_tx_adapter_caps_get(const struct rte_eventdev *dev,
+			     const struct rte_eth_dev *eth_dev, uint32_t *caps)
+{
+	int ret;
+
+	RTE_SET_USED(dev);
+	ret = strncmp(eth_dev->device->driver->name, "net_octeontx2,", 13);
+	if (ret)
+		*caps = 0;
+	else
+		*caps = RTE_EVENT_ETH_TX_ADAPTER_CAP_INTERNAL_PORT;
+
+	return 0;
+}
+
+static int
+sso_sqb_aura_limit_edit(struct rte_mempool *mp, uint16_t nb_sqb_bufs)
+{
+	struct otx2_npa_lf *npa_lf = otx2_intra_dev_get_cfg()->npa_lf;
+	struct npa_aq_enq_req *aura_req;
+
+	aura_req = otx2_mbox_alloc_msg_npa_aq_enq(npa_lf->mbox);
+	aura_req->aura_id = npa_lf_aura_handle_to_aura(mp->pool_id);
+	aura_req->ctype = NPA_AQ_CTYPE_AURA;
+	aura_req->op = NPA_AQ_INSTOP_WRITE;
+
+	aura_req->aura.limit = nb_sqb_bufs;
+	aura_req->aura_mask.limit = ~(aura_req->aura_mask.limit);
+
+	return otx2_mbox_process(npa_lf->mbox);
+}
+
+int
+otx2_sso_tx_adapter_queue_add(uint8_t id, const struct rte_eventdev *event_dev,
+			      const struct rte_eth_dev *eth_dev,
+			      int32_t tx_queue_id)
+{
+	struct otx2_eth_dev *otx2_eth_dev = eth_dev->data->dev_private;
+	struct otx2_sso_evdev *dev = sso_pmd_priv(event_dev);
+	struct otx2_eth_txq *txq;
+	int i;
+
+	RTE_SET_USED(id);
+	if (tx_queue_id < 0) {
+		for (i = 0 ; i < eth_dev->data->nb_tx_queues; i++) {
+			txq = eth_dev->data->tx_queues[i];
+			sso_sqb_aura_limit_edit(txq->sqb_pool,
+						OTX2_SSO_SQB_LIMIT);
+		}
+	} else {
+		txq = eth_dev->data->tx_queues[tx_queue_id];
+		sso_sqb_aura_limit_edit(txq->sqb_pool, OTX2_SSO_SQB_LIMIT);
+	}
+
+	dev->tx_offloads |= otx2_eth_dev->tx_offload_flags;
+	sso_fastpath_fns_set((struct rte_eventdev *)(uintptr_t)event_dev);
+
+	return 0;
+}
+
+int
+otx2_sso_tx_adapter_queue_del(uint8_t id, const struct rte_eventdev *event_dev,
+			      const struct rte_eth_dev *eth_dev,
+			      int32_t tx_queue_id)
+{
+	struct otx2_eth_txq *txq;
+	int i;
+
+	RTE_SET_USED(id);
+	RTE_SET_USED(eth_dev);
+	RTE_SET_USED(event_dev);
+	if (tx_queue_id < 0) {
+		for (i = 0 ; i < eth_dev->data->nb_tx_queues; i++) {
+			txq = eth_dev->data->tx_queues[i];
+			sso_sqb_aura_limit_edit(txq->sqb_pool,
+						txq->nb_sqb_bufs);
+		}
+	} else {
+		txq = eth_dev->data->tx_queues[tx_queue_id];
+		sso_sqb_aura_limit_edit(txq->sqb_pool, txq->nb_sqb_bufs);
+	}
+
+	return 0;
+}
diff --git a/drivers/event/octeontx2/otx2_worker.c b/drivers/event/octeontx2/otx2_worker.c
index ea2d0b5a4..cd14cd3d2 100644
--- a/drivers/event/octeontx2/otx2_worker.c
+++ b/drivers/event/octeontx2/otx2_worker.c
@@ -267,6 +267,35 @@ otx2_ssogws_enq_fwd_burst(void *port, const struct rte_event ev[],
 	return 1;
 }
 
+#define T(name, f4, f3, f2, f1, f0, sz, flags)				\
+uint16_t __hot								\
+otx2_ssogws_tx_adptr_enq_ ## name(void *port, struct rte_event ev[],	\
+				  uint16_t nb_events)			\
+{									\
+	struct otx2_ssogws *ws = port;					\
+	uint64_t cmd[sz];						\
+									\
+	RTE_SET_USED(nb_events);					\
+	return otx2_ssogws_event_tx(ws, ev, cmd, flags);		\
+}
+SSO_TX_ADPTR_ENQ_FASTPATH_FUNC
+#undef T
+
+#define T(name, f4, f3, f2, f1, f0, sz, flags)				\
+uint16_t __hot								\
+otx2_ssogws_tx_adptr_enq_seg_ ## name(void *port, struct rte_event ev[],\
+				      uint16_t nb_events)		\
+{									\
+	struct otx2_ssogws *ws = port;					\
+	uint64_t cmd[(sz) + NIX_TX_MSEG_SG_DWORDS - 2];			\
+									\
+	RTE_SET_USED(nb_events);					\
+	return otx2_ssogws_event_tx(ws, ev, cmd, (flags) |		\
+				    NIX_TX_MULTI_SEG_F);		\
+}
+SSO_TX_ADPTR_ENQ_FASTPATH_FUNC
+#undef T
+
 void
 ssogws_flush_events(struct otx2_ssogws *ws, uint8_t queue_id, uintptr_t base,
 		    otx2_handle_event_t fn, void *arg)
diff --git a/drivers/event/octeontx2/otx2_worker.h b/drivers/event/octeontx2/otx2_worker.h
index 1e1e947ef..3c847d223 100644
--- a/drivers/event/octeontx2/otx2_worker.h
+++ b/drivers/event/octeontx2/otx2_worker.h
@@ -219,4 +219,53 @@ otx2_ssogws_swtag_wait(struct otx2_ssogws *ws)
 #endif
 }
 
+static __rte_always_inline void
+otx2_ssogws_head_wait(struct otx2_ssogws *ws, const uint8_t wait_flag)
+{
+	while (wait_flag && !(otx2_read64(ws->tag_op) & BIT_ULL(35)))
+		;
+
+	rte_cio_wmb();
+}
+
+static __rte_always_inline const struct otx2_eth_txq *
+otx2_ssogws_xtract_meta(struct rte_mbuf *m)
+{
+	return rte_eth_devices[m->port].data->tx_queues[
+			rte_event_eth_tx_adapter_txq_get(m)];
+}
+
+static __rte_always_inline void
+otx2_ssogws_prepare_pkt(const struct otx2_eth_txq *txq, struct rte_mbuf *m,
+			uint64_t *cmd, const uint32_t flags)
+{
+	otx2_lmt_mov(cmd, txq->cmd, otx2_nix_tx_ext_subs(flags));
+	otx2_nix_xmit_prepare(m, cmd, flags);
+}
+
+static __rte_always_inline uint16_t
+otx2_ssogws_event_tx(struct otx2_ssogws *ws, struct rte_event ev[],
+		     uint64_t *cmd, const uint32_t flags)
+{
+	struct rte_mbuf *m = ev[0].mbuf;
+	const struct otx2_eth_txq *txq = otx2_ssogws_xtract_meta(m);
+
+	otx2_ssogws_head_wait(ws, !ev->sched_type);
+	otx2_ssogws_prepare_pkt(txq, m, cmd, flags);
+
+	if (flags & NIX_TX_MULTI_SEG_F) {
+		const uint16_t segdw = otx2_nix_prepare_mseg(m, cmd, flags);
+		otx2_nix_xmit_prepare_tstamp(cmd, &txq->cmd[0],
+					     m->ol_flags, segdw, flags);
+		otx2_nix_xmit_mseg_one(cmd, txq->lmt_addr, txq->io_addr, segdw);
+	} else {
+		/* Passing no of segdw as 4: HDR + EXT + SG + SMEM */
+		otx2_nix_xmit_prepare_tstamp(cmd, &txq->cmd[0],
+					     m->ol_flags, 4, flags);
+		otx2_nix_xmit_one(cmd, txq->lmt_addr, txq->io_addr, flags);
+	}
+
+	return 1;
+}
+
 #endif
diff --git a/drivers/event/octeontx2/otx2_worker_dual.c b/drivers/event/octeontx2/otx2_worker_dual.c
index cbe03c1bb..37c274a54 100644
--- a/drivers/event/octeontx2/otx2_worker_dual.c
+++ b/drivers/event/octeontx2/otx2_worker_dual.c
@@ -305,3 +305,38 @@ otx2_ssogws_dual_deq_seg_timeout_burst_ ##name(void *port,		\
 
 SSO_RX_ADPTR_ENQ_FASTPATH_FUNC
 #undef R
+
+#define T(name, f4, f3, f2, f1, f0, sz, flags)				\
+uint16_t __hot								\
+otx2_ssogws_dual_tx_adptr_enq_ ## name(void *port,			\
+				       struct rte_event ev[],		\
+				       uint16_t nb_events)		\
+{									\
+	struct otx2_ssogws_dual *ws = port;				\
+	struct otx2_ssogws *vws =					\
+		(struct otx2_ssogws *)&ws->ws_state[!ws->vws];		\
+	uint64_t cmd[sz];						\
+									\
+	RTE_SET_USED(nb_events);					\
+	return otx2_ssogws_event_tx(vws, ev, cmd, flags);		\
+}
+SSO_TX_ADPTR_ENQ_FASTPATH_FUNC
+#undef T
+
+#define T(name, f4, f3, f2, f1, f0, sz, flags)				\
+uint16_t __hot								\
+otx2_ssogws_dual_tx_adptr_enq_seg_ ## name(void *port,			\
+					   struct rte_event ev[],	\
+					   uint16_t nb_events)		\
+{									\
+	struct otx2_ssogws_dual *ws = port;				\
+	struct otx2_ssogws *vws =					\
+		(struct otx2_ssogws *)&ws->ws_state[!ws->vws];		\
+	uint64_t cmd[(sz) + NIX_TX_MSEG_SG_DWORDS - 2];			\
+									\
+	RTE_SET_USED(nb_events);					\
+	return otx2_ssogws_event_tx(vws, ev, cmd, (flags) |		\
+				    NIX_TX_MULTI_SEG_F);		\
+}
+SSO_TX_ADPTR_ENQ_FASTPATH_FUNC
+#undef T
-- 
2.22.0

Re: [dpdk-dev] [PATCH v4 5/5] event/octeontx2: add Tx adadpter support

[Jerin Jacob Kollanukkaran]

> -----Original Message-----
> From: pbhagavatula@marvell.com <pbhagavatula@marvell.com>
> Sent: Thursday, July 4, 2019 7:50 AM
> To: Jerin Jacob Kollanukkaran <jerinj@marvell.com>; Pavan Nikhilesh
> Bhagavatula <pbhagavatula@marvell.com>
> Cc: dev@dpdk.org; Nithin Kumar Dabilpuram <ndabilpuram@marvell.com>
> Subject: [dpdk-dev] [PATCH v4 5/5] event/octeontx2: add Tx adadpter support


Fixed adadpter typo.

Series applied to dpdk-next-eventdev/master. Thanks.


> 
> From: Pavan Nikhilesh <pbhagavatula@marvell.com>
> 
> Add event eth Tx adapter support to octeontx2 SSO.
>