[PATCH v3 3/3] net/cnxk: introduce pool sort capability

[Hanumanth Pothula <hpothula@marvell.com>]

Presently, HW is programmed only to receive packets from LPB pool.
Making all packets received from LPB pool.

But, CNXK HW supports two pools,
 - SPB -> packets with smaller size (less than 4K)
 - LPB -> packets with bigger size (greater than 4K)

Patch enables pool sorting capability, pool is selected based on
packet's length. So, basically, PMD programs HW for receiving
packets from both SPB and LPB pools based on the packet's length.

This is achieved by enabling rx buffer split offload,
RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT. This allows the application to send
more than one pool(in our case two) to the driver, with different
segment(packet) lengths, which helps the driver to configure both
pools based on segment lengths.

This is often useful for saving the memory where the application
can create a different pool to steer the specific size of the
packet, thus enabling effective use of memory.

Signed-off-by: Hanumanth Pothula <hpothula@marvell.com>
---
 doc/guides/nics/features/cnxk.ini     |  1 +
 doc/guides/nics/features/cnxk_vec.ini |  1 +
 drivers/net/cnxk/cnxk_ethdev.c        | 93 ++++++++++++++++++++++++---
 drivers/net/cnxk/cnxk_ethdev.h        |  4 +-
 drivers/net/cnxk/cnxk_ethdev_ops.c    |  7 ++
 5 files changed, 96 insertions(+), 10 deletions(-)

diff --git a/doc/guides/nics/features/cnxk.ini b/doc/guides/nics/features/cnxk.ini
index 1876fe86c7..e1584ed740 100644
--- a/doc/guides/nics/features/cnxk.ini
+++ b/doc/guides/nics/features/cnxk.ini
@@ -4,6 +4,7 @@
 ; Refer to default.ini for the full list of available PMD features.
 ;
 [Features]
+pool sort	     = Y
 Speed capabilities   = Y
 Rx interrupt         = Y
 Lock-free Tx queue   = Y
diff --git a/doc/guides/nics/features/cnxk_vec.ini b/doc/guides/nics/features/cnxk_vec.ini
index 5d0976e6ce..a63d35aae7 100644
--- a/doc/guides/nics/features/cnxk_vec.ini
+++ b/doc/guides/nics/features/cnxk_vec.ini
@@ -4,6 +4,7 @@
 ; Refer to default.ini for the full list of available PMD features.
 ;
 [Features]
+pool sort	     = Y
 Speed capabilities   = Y
 Rx interrupt         = Y
 Lock-free Tx queue   = Y
diff --git a/drivers/net/cnxk/cnxk_ethdev.c b/drivers/net/cnxk/cnxk_ethdev.c
index cfcc4df916..376c5274d3 100644
--- a/drivers/net/cnxk/cnxk_ethdev.c
+++ b/drivers/net/cnxk/cnxk_ethdev.c
@@ -537,6 +537,64 @@ cnxk_nix_tx_queue_release(struct rte_eth_dev *eth_dev, uint16_t qid)
 	plt_free(txq_sp);
 }
 
+static int
+cnxk_nix_process_rx_conf(const struct rte_eth_rxconf *rx_conf,
+			 struct rte_mempool **lpb_pool, struct rte_mempool **spb_pool,
+			 uint16_t *lpb_len, uint16_t *spb_len)
+{
+	struct rte_eth_rxseg_sort rx_seg0;
+	struct rte_eth_rxseg_sort rx_seg1;
+	const char *platform_ops;
+	struct rte_mempool_ops *ops;
+
+	if (*lpb_pool || !rx_conf->rx_seg || rx_conf->rx_nseg != CNXK_NIX_NUM_POOLS_MAX ||
+	    !rx_conf->rx_seg[0].sort.mp || !rx_conf->rx_seg[1].sort.mp) {
+		plt_err("invalid arguments");
+		return -EINVAL;
+	}
+
+	rx_seg0 = rx_conf->rx_seg[0].sort;
+	rx_seg1 = rx_conf->rx_seg[1].sort;
+
+	if (rx_seg0.length >= rx_seg0.mp->elt_size || rx_seg1.length >= rx_seg1.mp->elt_size) {
+		plt_err("mismatch in packet length & pool length seg0_len:%u pool0_len:%u"\
+			"seg1_len:%u pool1_len:%u", rx_seg0.length, rx_seg0.mp->elt_size,
+			rx_seg1.length, rx_seg1.mp->elt_size);
+		return -EINVAL;
+	}
+
+	if (rx_seg0.length > rx_seg1.length) {
+		*lpb_pool = rx_seg0.mp;
+		*spb_pool = rx_seg1.mp;
+
+		*lpb_len = rx_seg0.length;
+		*spb_len = rx_seg1.length;
+	} else {
+		*lpb_pool = rx_seg1.mp;
+		*spb_pool = rx_seg0.mp;
+
+		*lpb_len = rx_seg1.length;
+		*spb_len = rx_seg0.length;
+	}
+
+	if ((*spb_pool)->pool_id == 0) {
+		plt_err("Invalid pool_id");
+		return -EINVAL;
+	}
+
+	platform_ops = rte_mbuf_platform_mempool_ops();
+	ops = rte_mempool_get_ops((*spb_pool)->ops_index);
+	if (strncmp(ops->name, platform_ops, RTE_MEMPOOL_OPS_NAMESIZE)) {
+		plt_err("mempool ops should be of cnxk_npa type");
+		return -EINVAL;
+	}
+
+	plt_info("spb_pool:%s lpb_pool:%s lpb_len:%u spb_len:%u\n", (*spb_pool)->name,
+		 (*lpb_pool)->name, *lpb_len, *spb_len);
+
+	return 0;
+}
+
 int
 cnxk_nix_rx_queue_setup(struct rte_eth_dev *eth_dev, uint16_t qid,
 			uint32_t nb_desc, uint16_t fp_rx_q_sz,
@@ -553,6 +611,10 @@ cnxk_nix_rx_queue_setup(struct rte_eth_dev *eth_dev, uint16_t qid,
 	uint16_t first_skip;
 	int rc = -EINVAL;
 	size_t rxq_sz;
+	uint16_t lpb_len = 0;
+	uint16_t spb_len = 0;
+	struct rte_mempool *lpb_pool = mp;
+	struct rte_mempool *spb_pool = NULL;
 
 	/* Sanity checks */
 	if (rx_conf->rx_deferred_start == 1) {
@@ -560,15 +622,22 @@ cnxk_nix_rx_queue_setup(struct rte_eth_dev *eth_dev, uint16_t qid,
 		goto fail;
 	}
 
+	if (dev->rx_offloads & RTE_ETH_RX_OFFLOAD_BUFFER_SORT) {
+		rc = cnxk_nix_process_rx_conf(rx_conf, &lpb_pool, &spb_pool,
+					      &lpb_len, &spb_len);
+		if (rc)
+			goto fail;
+	}
+
 	platform_ops = rte_mbuf_platform_mempool_ops();
 	/* This driver needs cnxk_npa mempool ops to work */
-	ops = rte_mempool_get_ops(mp->ops_index);
+	ops = rte_mempool_get_ops(lpb_pool->ops_index);
 	if (strncmp(ops->name, platform_ops, RTE_MEMPOOL_OPS_NAMESIZE)) {
 		plt_err("mempool ops should be of cnxk_npa type");
 		goto fail;
 	}
 
-	if (mp->pool_id == 0) {
+	if (lpb_pool->pool_id == 0) {
 		plt_err("Invalid pool_id");
 		goto fail;
 	}
@@ -585,13 +654,13 @@ cnxk_nix_rx_queue_setup(struct rte_eth_dev *eth_dev, uint16_t qid,
 	/* Its a no-op when inline device is not used */
 	if (dev->rx_offloads & RTE_ETH_RX_OFFLOAD_SECURITY ||
 	    dev->tx_offloads & RTE_ETH_TX_OFFLOAD_SECURITY)
-		roc_nix_inl_dev_xaq_realloc(mp->pool_id);
+		roc_nix_inl_dev_xaq_realloc(lpb_pool->pool_id);
 
 	/* Increase CQ size to Aura size to avoid CQ overflow and
 	 * then CPT buffer leak.
 	 */
 	if (dev->rx_offloads & RTE_ETH_RX_OFFLOAD_SECURITY)
-		nb_desc = nix_inl_cq_sz_clamp_up(nix, mp, nb_desc);
+		nb_desc = nix_inl_cq_sz_clamp_up(nix, lpb_pool, nb_desc);
 
 	/* Setup ROC CQ */
 	cq = &dev->cqs[qid];
@@ -606,23 +675,29 @@ cnxk_nix_rx_queue_setup(struct rte_eth_dev *eth_dev, uint16_t qid,
 	/* Setup ROC RQ */
 	rq = &dev->rqs[qid];
 	rq->qid = qid;
-	rq->aura_handle = mp->pool_id;
+	rq->aura_handle = lpb_pool->pool_id;
 	rq->flow_tag_width = 32;
 	rq->sso_ena = false;
 
 	/* Calculate first mbuf skip */
 	first_skip = (sizeof(struct rte_mbuf));
 	first_skip += RTE_PKTMBUF_HEADROOM;
-	first_skip += rte_pktmbuf_priv_size(mp);
+	first_skip += rte_pktmbuf_priv_size(lpb_pool);
 	rq->first_skip = first_skip;
 	rq->later_skip = sizeof(struct rte_mbuf);
-	rq->lpb_size = mp->elt_size;
+	rq->lpb_size = lpb_len ? lpb_len : lpb_pool->elt_size;
 	rq->lpb_drop_ena = !(dev->rx_offloads & RTE_ETH_RX_OFFLOAD_SECURITY);
 
 	/* Enable Inline IPSec on RQ, will not be used for Poll mode */
 	if (roc_nix_inl_inb_is_enabled(nix))
 		rq->ipsech_ena = true;
 
+	if (spb_pool) {
+		rq->spb_ena = 1;
+		rq->spb_aura_handle = spb_pool->pool_id;
+		rq->spb_size = spb_len;
+	}
+
 	rc = roc_nix_rq_init(&dev->nix, rq, !!eth_dev->data->dev_started);
 	if (rc) {
 		plt_err("Failed to init roc rq for rq=%d, rc=%d", qid, rc);
@@ -645,7 +720,7 @@ cnxk_nix_rx_queue_setup(struct rte_eth_dev *eth_dev, uint16_t qid,
 	/* Queue config should reflect global offloads */
 	rxq_sp->qconf.conf.rx.offloads = dev->rx_offloads;
 	rxq_sp->qconf.nb_desc = nb_desc;
-	rxq_sp->qconf.mp = mp;
+	rxq_sp->qconf.mp = lpb_pool;
 	rxq_sp->tc = 0;
 	rxq_sp->tx_pause = (dev->fc_cfg.mode == RTE_ETH_FC_FULL ||
 			    dev->fc_cfg.mode == RTE_ETH_FC_TX_PAUSE);
@@ -664,7 +739,7 @@ cnxk_nix_rx_queue_setup(struct rte_eth_dev *eth_dev, uint16_t qid,
 			goto free_mem;
 	}
 
-	plt_nix_dbg("rq=%d pool=%s nb_desc=%d->%d", qid, mp->name, nb_desc,
+	plt_nix_dbg("rq=%d pool=%s nb_desc=%d->%d", qid, lpb_pool->name, nb_desc,
 		    cq->nb_desc);
 
 	/* Store start of fast path area */
diff --git a/drivers/net/cnxk/cnxk_ethdev.h b/drivers/net/cnxk/cnxk_ethdev.h
index f11a9a0b63..4b0c11b7d2 100644
--- a/drivers/net/cnxk/cnxk_ethdev.h
+++ b/drivers/net/cnxk/cnxk_ethdev.h
@@ -44,6 +44,8 @@
 #define CNXK_NIX_RX_DEFAULT_RING_SZ 4096
 /* Max supported SQB count */
 #define CNXK_NIX_TX_MAX_SQB 512
+/* LPB & SPB */
+#define CNXK_NIX_NUM_POOLS_MAX 2
 
 /* If PTP is enabled additional SEND MEM DESC is required which
  * takes 2 words, hence max 7 iova address are possible
@@ -83,7 +85,7 @@
 	 RTE_ETH_RX_OFFLOAD_OUTER_IPV4_CKSUM | RTE_ETH_RX_OFFLOAD_SCATTER |    \
 	 RTE_ETH_RX_OFFLOAD_OUTER_UDP_CKSUM | RTE_ETH_RX_OFFLOAD_RSS_HASH |    \
 	 RTE_ETH_RX_OFFLOAD_TIMESTAMP | RTE_ETH_RX_OFFLOAD_VLAN_STRIP |        \
-	 RTE_ETH_RX_OFFLOAD_SECURITY)
+	 RTE_ETH_RX_OFFLOAD_BUFFER_SORT | RTE_ETH_RX_OFFLOAD_SECURITY)
 
 #define RSS_IPV4_ENABLE                                                        \
 	(RTE_ETH_RSS_IPV4 | RTE_ETH_RSS_FRAG_IPV4 |                            \
diff --git a/drivers/net/cnxk/cnxk_ethdev_ops.c b/drivers/net/cnxk/cnxk_ethdev_ops.c
index 1592971073..6174a586be 100644
--- a/drivers/net/cnxk/cnxk_ethdev_ops.c
+++ b/drivers/net/cnxk/cnxk_ethdev_ops.c
@@ -69,6 +69,13 @@ cnxk_nix_info_get(struct rte_eth_dev *eth_dev, struct rte_eth_dev_info *devinfo)
 	devinfo->dev_capa = RTE_ETH_DEV_CAPA_RUNTIME_RX_QUEUE_SETUP |
 			    RTE_ETH_DEV_CAPA_RUNTIME_TX_QUEUE_SETUP |
 			    RTE_ETH_DEV_CAPA_FLOW_RULE_KEEP;
+
+	devinfo->rx_seg_capa = (struct rte_eth_rxseg_capa){
+		.mode_sort = 1,
+		.multi_pools = 1,
+		.max_npool = CNXK_NIX_NUM_POOLS_MAX,
+	};
+
 	return 0;
 }
 
-- 
2.25.1