[dpdk-dev] [PATCH v3 09/13] event/cnxk: add Tx adapter support

[<pbhagavatula@marvell.com>]

From: Pavan Nikhilesh <pbhagavatula@marvell.com>

Add support for event eth Tx adapter.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
---
 doc/guides/eventdevs/cnxk.rst            |   4 +-
 doc/guides/rel_notes/release_21_08.rst   |   6 +-
 drivers/event/cnxk/cn10k_eventdev.c      |  91 ++++++++++++++++++
 drivers/event/cnxk/cn9k_eventdev.c       | 117 +++++++++++++++++++++++
 drivers/event/cnxk/cnxk_eventdev.h       |  21 +++-
 drivers/event/cnxk/cnxk_eventdev_adptr.c | 106 ++++++++++++++++++++
 6 files changed, 339 insertions(+), 6 deletions(-)

diff --git a/doc/guides/eventdevs/cnxk.rst b/doc/guides/eventdevs/cnxk.rst
index b7e82c1273..6fdccc2ab4 100644
--- a/doc/guides/eventdevs/cnxk.rst
+++ b/doc/guides/eventdevs/cnxk.rst
@@ -42,7 +42,9 @@ Features of the OCTEON cnxk SSO PMD are:
 - HW managed packets enqueued from ethdev to eventdev exposed through event eth
   RX adapter.
 - N:1 ethernet device Rx queue to Event queue mapping.
-- Full Rx offload support defined through ethdev queue configuration.
+- 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 configuration.
 
 Prerequisites and Compilation procedure
 ---------------------------------------
diff --git a/doc/guides/rel_notes/release_21_08.rst b/doc/guides/rel_notes/release_21_08.rst
index 3892c8017a..80ff93269c 100644
--- a/doc/guides/rel_notes/release_21_08.rst
+++ b/doc/guides/rel_notes/release_21_08.rst
@@ -60,10 +60,10 @@ New Features
   * Added net/cnxk driver which provides the support for the integrated ethernet
     device.
 
-* **Added support for Marvell CN10K, CN9K, event Rx adapter.**
+* **Added support for Marvell CN10K, CN9K, event Rx/Tx adapter.**
 
-  * Added Rx adapter support for event/cnxk when the ethernet device requested is
-    net/cnxk.
+  * Added Rx/Tx adapter support for event/cnxk when the ethernet device requested
+    is net/cnxk.
 
 
 Removed Items
diff --git a/drivers/event/cnxk/cn10k_eventdev.c b/drivers/event/cnxk/cn10k_eventdev.c
index ba7d95fff7..8a9b04a3db 100644
--- a/drivers/event/cnxk/cn10k_eventdev.c
+++ b/drivers/event/cnxk/cn10k_eventdev.c
@@ -44,6 +44,7 @@ cn10k_sso_init_hws_mem(void *arg, uint8_t port_id)
 	/* First cache line is reserved for cookie */
 	ws = (struct cn10k_sso_hws *)((uint8_t *)ws + RTE_CACHE_LINE_SIZE);
 	ws->base = roc_sso_hws_base_get(&dev->sso, port_id);
+	ws->tx_base = ws->base;
 	ws->hws_id = port_id;
 	ws->swtag_req = 0;
 	ws->gw_wdata = cn10k_sso_gw_mode_wdata(dev);
@@ -233,6 +234,39 @@ cn10k_sso_rsrc_init(void *arg, uint8_t hws, uint8_t hwgrp)
 	return roc_sso_rsrc_init(&dev->sso, hws, hwgrp);
 }
 
+static int
+cn10k_sso_updt_tx_adptr_data(const struct rte_eventdev *event_dev)
+{
+	struct cnxk_sso_evdev *dev = cnxk_sso_pmd_priv(event_dev);
+	int i;
+
+	if (dev->tx_adptr_data == NULL)
+		return 0;
+
+	for (i = 0; i < dev->nb_event_ports; i++) {
+		struct cn10k_sso_hws *ws = event_dev->data->ports[i];
+		void *ws_cookie;
+
+		ws_cookie = cnxk_sso_hws_get_cookie(ws);
+		ws_cookie = rte_realloc_socket(
+			ws_cookie,
+			sizeof(struct cnxk_sso_hws_cookie) +
+				sizeof(struct cn10k_sso_hws) +
+				(sizeof(uint64_t) * (dev->max_port_id + 1) *
+				 RTE_MAX_QUEUES_PER_PORT),
+			RTE_CACHE_LINE_SIZE, SOCKET_ID_ANY);
+		if (ws_cookie == NULL)
+			return -ENOMEM;
+		ws = RTE_PTR_ADD(ws_cookie, sizeof(struct cnxk_sso_hws_cookie));
+		memcpy(&ws->tx_adptr_data, dev->tx_adptr_data,
+		       sizeof(uint64_t) * (dev->max_port_id + 1) *
+			       RTE_MAX_QUEUES_PER_PORT);
+		event_dev->data->ports[i] = ws;
+	}
+
+	return 0;
+}
+
 static void
 cn10k_sso_fp_fns_set(struct rte_eventdev *event_dev)
 {
@@ -493,6 +527,10 @@ cn10k_sso_start(struct rte_eventdev *event_dev)
 {
 	int rc;
 
+	rc = cn10k_sso_updt_tx_adptr_data(event_dev);
+	if (rc < 0)
+		return rc;
+
 	rc = cnxk_sso_start(event_dev, cn10k_sso_hws_reset,
 			    cn10k_sso_hws_flush_events);
 	if (rc < 0)
@@ -595,6 +633,55 @@ cn10k_sso_rx_adapter_queue_del(const struct rte_eventdev *event_dev,
 	return cnxk_sso_rx_adapter_queue_del(event_dev, eth_dev, rx_queue_id);
 }
 
+static int
+cn10k_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_cn10k", 8);
+	if (ret)
+		*caps = 0;
+	else
+		*caps = RTE_EVENT_ETH_TX_ADAPTER_CAP_INTERNAL_PORT;
+
+	return 0;
+}
+
+static int
+cn10k_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 rc;
+
+	RTE_SET_USED(id);
+	rc = cnxk_sso_tx_adapter_queue_add(event_dev, eth_dev, tx_queue_id);
+	if (rc < 0)
+		return rc;
+	rc = cn10k_sso_updt_tx_adptr_data(event_dev);
+	if (rc < 0)
+		return rc;
+	cn10k_sso_fp_fns_set((struct rte_eventdev *)(uintptr_t)event_dev);
+
+	return 0;
+}
+
+static int
+cn10k_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)
+{
+	int rc;
+
+	RTE_SET_USED(id);
+	rc = cnxk_sso_tx_adapter_queue_del(event_dev, eth_dev, tx_queue_id);
+	if (rc < 0)
+		return rc;
+	return cn10k_sso_updt_tx_adptr_data(event_dev);
+}
+
 static struct rte_eventdev_ops cn10k_sso_dev_ops = {
 	.dev_infos_get = cn10k_sso_info_get,
 	.dev_configure = cn10k_sso_dev_configure,
@@ -614,6 +701,10 @@ static struct rte_eventdev_ops cn10k_sso_dev_ops = {
 	.eth_rx_adapter_start = cnxk_sso_rx_adapter_start,
 	.eth_rx_adapter_stop = cnxk_sso_rx_adapter_stop,
 
+	.eth_tx_adapter_caps_get = cn10k_sso_tx_adapter_caps_get,
+	.eth_tx_adapter_queue_add = cn10k_sso_tx_adapter_queue_add,
+	.eth_tx_adapter_queue_del = cn10k_sso_tx_adapter_queue_del,
+
 	.timer_adapter_caps_get = cnxk_tim_caps_get,
 
 	.dump = cnxk_sso_dump,
diff --git a/drivers/event/cnxk/cn9k_eventdev.c b/drivers/event/cnxk/cn9k_eventdev.c
index e386cb784a..bdc5632235 100644
--- a/drivers/event/cnxk/cn9k_eventdev.c
+++ b/drivers/event/cnxk/cn9k_eventdev.c
@@ -248,6 +248,66 @@ cn9k_sso_rsrc_init(void *arg, uint8_t hws, uint8_t hwgrp)
 	return roc_sso_rsrc_init(&dev->sso, hws, hwgrp);
 }
 
+static int
+cn9k_sso_updt_tx_adptr_data(const struct rte_eventdev *event_dev)
+{
+	struct cnxk_sso_evdev *dev = cnxk_sso_pmd_priv(event_dev);
+	int i;
+
+	if (dev->tx_adptr_data == NULL)
+		return 0;
+
+	for (i = 0; i < dev->nb_event_ports; i++) {
+		if (dev->dual_ws) {
+			struct cn9k_sso_hws_dual *dws =
+				event_dev->data->ports[i];
+			void *ws_cookie;
+
+			ws_cookie = cnxk_sso_hws_get_cookie(dws);
+			ws_cookie = rte_realloc_socket(
+				ws_cookie,
+				sizeof(struct cnxk_sso_hws_cookie) +
+					sizeof(struct cn9k_sso_hws_dual) +
+					(sizeof(uint64_t) *
+					 (dev->max_port_id + 1) *
+					 RTE_MAX_QUEUES_PER_PORT),
+				RTE_CACHE_LINE_SIZE, SOCKET_ID_ANY);
+			if (ws_cookie == NULL)
+				return -ENOMEM;
+			dws = RTE_PTR_ADD(ws_cookie,
+					  sizeof(struct cnxk_sso_hws_cookie));
+			memcpy(&dws->tx_adptr_data, dev->tx_adptr_data,
+			       sizeof(uint64_t) * (dev->max_port_id + 1) *
+				       RTE_MAX_QUEUES_PER_PORT);
+			event_dev->data->ports[i] = dws;
+		} else {
+			struct cn9k_sso_hws *ws = event_dev->data->ports[i];
+			void *ws_cookie;
+
+			ws_cookie = cnxk_sso_hws_get_cookie(ws);
+			ws_cookie = rte_realloc_socket(
+				ws_cookie,
+				sizeof(struct cnxk_sso_hws_cookie) +
+					sizeof(struct cn9k_sso_hws_dual) +
+					(sizeof(uint64_t) *
+					 (dev->max_port_id + 1) *
+					 RTE_MAX_QUEUES_PER_PORT),
+				RTE_CACHE_LINE_SIZE, SOCKET_ID_ANY);
+			if (ws_cookie == NULL)
+				return -ENOMEM;
+			ws = RTE_PTR_ADD(ws_cookie,
+					 sizeof(struct cnxk_sso_hws_cookie));
+			memcpy(&ws->tx_adptr_data, dev->tx_adptr_data,
+			       sizeof(uint64_t) * (dev->max_port_id + 1) *
+				       RTE_MAX_QUEUES_PER_PORT);
+			event_dev->data->ports[i] = ws;
+		}
+	}
+	rte_mb();
+
+	return 0;
+}
+
 static void
 cn9k_sso_fp_fns_set(struct rte_eventdev *event_dev)
 {
@@ -734,6 +794,10 @@ cn9k_sso_start(struct rte_eventdev *event_dev)
 {
 	int rc;
 
+	rc = cn9k_sso_updt_tx_adptr_data(event_dev);
+	if (rc < 0)
+		return rc;
+
 	rc = cnxk_sso_start(event_dev, cn9k_sso_hws_reset,
 			    cn9k_sso_hws_flush_events);
 	if (rc < 0)
@@ -844,6 +908,55 @@ cn9k_sso_rx_adapter_queue_del(const struct rte_eventdev *event_dev,
 	return cnxk_sso_rx_adapter_queue_del(event_dev, eth_dev, rx_queue_id);
 }
 
+static int
+cn9k_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_cn9k", 8);
+	if (ret)
+		*caps = 0;
+	else
+		*caps = RTE_EVENT_ETH_TX_ADAPTER_CAP_INTERNAL_PORT;
+
+	return 0;
+}
+
+static int
+cn9k_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 rc;
+
+	RTE_SET_USED(id);
+	rc = cnxk_sso_tx_adapter_queue_add(event_dev, eth_dev, tx_queue_id);
+	if (rc < 0)
+		return rc;
+	rc = cn9k_sso_updt_tx_adptr_data(event_dev);
+	if (rc < 0)
+		return rc;
+	cn9k_sso_fp_fns_set((struct rte_eventdev *)(uintptr_t)event_dev);
+
+	return 0;
+}
+
+static int
+cn9k_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)
+{
+	int rc;
+
+	RTE_SET_USED(id);
+	rc = cnxk_sso_tx_adapter_queue_del(event_dev, eth_dev, tx_queue_id);
+	if (rc < 0)
+		return rc;
+	return cn9k_sso_updt_tx_adptr_data(event_dev);
+}
+
 static struct rte_eventdev_ops cn9k_sso_dev_ops = {
 	.dev_infos_get = cn9k_sso_info_get,
 	.dev_configure = cn9k_sso_dev_configure,
@@ -863,6 +976,10 @@ static struct rte_eventdev_ops cn9k_sso_dev_ops = {
 	.eth_rx_adapter_start = cnxk_sso_rx_adapter_start,
 	.eth_rx_adapter_stop = cnxk_sso_rx_adapter_stop,
 
+	.eth_tx_adapter_caps_get = cn9k_sso_tx_adapter_caps_get,
+	.eth_tx_adapter_queue_add = cn9k_sso_tx_adapter_queue_add,
+	.eth_tx_adapter_queue_del = cn9k_sso_tx_adapter_queue_del,
+
 	.timer_adapter_caps_get = cnxk_tim_caps_get,
 
 	.dump = cnxk_sso_dump,
diff --git a/drivers/event/cnxk/cnxk_eventdev.h b/drivers/event/cnxk/cnxk_eventdev.h
index 9d5d2d0339..458fdc8d92 100644
--- a/drivers/event/cnxk/cnxk_eventdev.h
+++ b/drivers/event/cnxk/cnxk_eventdev.h
@@ -8,6 +8,7 @@
 #include <rte_devargs.h>
 #include <rte_ethdev.h>
 #include <rte_event_eth_rx_adapter.h>
+#include <rte_event_eth_tx_adapter.h>
 #include <rte_kvargs.h>
 #include <rte_mbuf_pool_ops.h>
 #include <rte_pci.h>
@@ -86,9 +87,12 @@ struct cnxk_sso_evdev {
 	rte_iova_t fc_iova;
 	struct rte_mempool *xaq_pool;
 	uint64_t rx_offloads;
+	uint64_t tx_offloads;
 	uint64_t adptr_xae_cnt;
 	uint16_t rx_adptr_pool_cnt;
 	uint64_t *rx_adptr_pools;
+	uint64_t *tx_adptr_data;
+	uint16_t max_port_id;
 	uint16_t tim_adptr_ring_cnt;
 	uint16_t *timer_adptr_rings;
 	uint64_t *timer_adptr_sz;
@@ -115,7 +119,10 @@ struct cn10k_sso_hws {
 	uint64_t xaq_lmt __rte_cache_aligned;
 	uint64_t *fc_mem;
 	uintptr_t grps_base[CNXK_SSO_MAX_HWGRP];
+	/* Tx Fastpath data */
+	uint64_t tx_base __rte_cache_aligned;
 	uintptr_t lmt_base;
+	uint8_t tx_adptr_data[];
 } __rte_cache_aligned;
 
 /* CN9K HWS ops */
@@ -140,7 +147,9 @@ struct cn9k_sso_hws {
 	uint64_t xaq_lmt __rte_cache_aligned;
 	uint64_t *fc_mem;
 	uintptr_t grps_base[CNXK_SSO_MAX_HWGRP];
-	uint64_t base;
+	/* Tx Fastpath data */
+	uint64_t base __rte_cache_aligned;
+	uint8_t tx_adptr_data[];
 } __rte_cache_aligned;
 
 struct cn9k_sso_hws_state {
@@ -160,7 +169,9 @@ struct cn9k_sso_hws_dual {
 	uint64_t xaq_lmt __rte_cache_aligned;
 	uint64_t *fc_mem;
 	uintptr_t grps_base[CNXK_SSO_MAX_HWGRP];
-	uint64_t base[2];
+	/* Tx Fastpath data */
+	uint64_t base[2] __rte_cache_aligned;
+	uint8_t tx_adptr_data[];
 } __rte_cache_aligned;
 
 struct cnxk_sso_hws_cookie {
@@ -267,5 +278,11 @@ int cnxk_sso_rx_adapter_start(const struct rte_eventdev *event_dev,
 			      const struct rte_eth_dev *eth_dev);
 int cnxk_sso_rx_adapter_stop(const struct rte_eventdev *event_dev,
 			     const struct rte_eth_dev *eth_dev);
+int cnxk_sso_tx_adapter_queue_add(const struct rte_eventdev *event_dev,
+				  const struct rte_eth_dev *eth_dev,
+				  int32_t tx_queue_id);
+int cnxk_sso_tx_adapter_queue_del(const struct rte_eventdev *event_dev,
+				  const struct rte_eth_dev *eth_dev,
+				  int32_t tx_queue_id);
 
 #endif /* __CNXK_EVENTDEV_H__ */
diff --git a/drivers/event/cnxk/cnxk_eventdev_adptr.c b/drivers/event/cnxk/cnxk_eventdev_adptr.c
index 24bfd985e7..548d7b81ce 100644
--- a/drivers/event/cnxk/cnxk_eventdev_adptr.c
+++ b/drivers/event/cnxk/cnxk_eventdev_adptr.c
@@ -5,6 +5,8 @@
 #include "cnxk_ethdev.h"
 #include "cnxk_eventdev.h"
 
+#define CNXK_SSO_SQB_LIMIT (0x180)
+
 void
 cnxk_sso_updt_xae_cnt(struct cnxk_sso_evdev *dev, void *data,
 		      uint32_t event_type)
@@ -241,3 +243,107 @@ cnxk_sso_rx_adapter_stop(const struct rte_eventdev *event_dev,
 
 	return 0;
 }
+
+static int
+cnxk_sso_sqb_aura_limit_edit(struct roc_nix_sq *sq, uint16_t nb_sqb_bufs)
+{
+	uint16_t sqb_limit;
+
+	sqb_limit = RTE_MIN(nb_sqb_bufs, sq->nb_sqb_bufs);
+	return roc_npa_aura_limit_modify(sq->aura_handle, sqb_limit);
+}
+
+static int
+cnxk_sso_updt_tx_queue_data(const struct rte_eventdev *event_dev,
+			    uint16_t eth_port_id, uint16_t tx_queue_id,
+			    void *txq)
+{
+	struct cnxk_sso_evdev *dev = cnxk_sso_pmd_priv(event_dev);
+	uint16_t max_port_id = dev->max_port_id;
+	uint64_t *txq_data = dev->tx_adptr_data;
+
+	if (txq_data == NULL || eth_port_id > max_port_id) {
+		max_port_id = RTE_MAX(max_port_id, eth_port_id);
+		txq_data = rte_realloc_socket(
+			txq_data,
+			(sizeof(uint64_t) * (max_port_id + 1) *
+			 RTE_MAX_QUEUES_PER_PORT),
+			RTE_CACHE_LINE_SIZE, event_dev->data->socket_id);
+		if (txq_data == NULL)
+			return -ENOMEM;
+	}
+
+	((uint64_t(*)[RTE_MAX_QUEUES_PER_PORT])
+		 txq_data)[eth_port_id][tx_queue_id] = (uint64_t)txq;
+	dev->max_port_id = max_port_id;
+	dev->tx_adptr_data = txq_data;
+	return 0;
+}
+
+int
+cnxk_sso_tx_adapter_queue_add(const struct rte_eventdev *event_dev,
+			      const struct rte_eth_dev *eth_dev,
+			      int32_t tx_queue_id)
+{
+	struct cnxk_eth_dev *cnxk_eth_dev = eth_dev->data->dev_private;
+	struct cnxk_sso_evdev *dev = cnxk_sso_pmd_priv(event_dev);
+	struct roc_nix_sq *sq;
+	int i, ret;
+	void *txq;
+
+	if (tx_queue_id < 0) {
+		for (i = 0; i < eth_dev->data->nb_tx_queues; i++) {
+			txq = eth_dev->data->tx_queues[i];
+			sq = &cnxk_eth_dev->sqs[i];
+			cnxk_sso_sqb_aura_limit_edit(sq, CNXK_SSO_SQB_LIMIT);
+			ret = cnxk_sso_updt_tx_queue_data(
+				event_dev, eth_dev->data->port_id, i, txq);
+			if (ret < 0)
+				return ret;
+		}
+	} else {
+		txq = eth_dev->data->tx_queues[tx_queue_id];
+		sq = &cnxk_eth_dev->sqs[tx_queue_id];
+		cnxk_sso_sqb_aura_limit_edit(sq, CNXK_SSO_SQB_LIMIT);
+		ret = cnxk_sso_updt_tx_queue_data(
+			event_dev, eth_dev->data->port_id, tx_queue_id, txq);
+		if (ret < 0)
+			return ret;
+	}
+
+	dev->tx_offloads |= cnxk_eth_dev->tx_offload_flags;
+
+	return 0;
+}
+
+int
+cnxk_sso_tx_adapter_queue_del(const struct rte_eventdev *event_dev,
+			      const struct rte_eth_dev *eth_dev,
+			      int32_t tx_queue_id)
+{
+	struct cnxk_eth_dev *cnxk_eth_dev = eth_dev->data->dev_private;
+	struct roc_nix_sq *sq;
+	int i, ret;
+
+	RTE_SET_USED(event_dev);
+	if (tx_queue_id < 0) {
+		for (i = 0; i < eth_dev->data->nb_tx_queues; i++) {
+			sq = &cnxk_eth_dev->sqs[i];
+			cnxk_sso_sqb_aura_limit_edit(sq, sq->nb_sqb_bufs);
+			ret = cnxk_sso_updt_tx_queue_data(
+				event_dev, eth_dev->data->port_id, tx_queue_id,
+				NULL);
+			if (ret < 0)
+				return ret;
+		}
+	} else {
+		sq = &cnxk_eth_dev->sqs[tx_queue_id];
+		cnxk_sso_sqb_aura_limit_edit(sq, sq->nb_sqb_bufs);
+		ret = cnxk_sso_updt_tx_queue_data(
+			event_dev, eth_dev->data->port_id, tx_queue_id, NULL);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
-- 
2.17.1