[PATCH v5 24/28] net/cnxk: add support for flow control for outbound inline

[Nithin Dabilpuram <ndabilpuram@marvell.com>]

Add support for flow control in outbound inline path using
fc updates from CPT.

Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
---
 drivers/net/cnxk/cn10k_ethdev.c |  3 +++
 drivers/net/cnxk/cn10k_ethdev.h |  1 +
 drivers/net/cnxk/cn10k_tx.h     | 37 ++++++++++++++++++++++++++++++++++++-
 drivers/net/cnxk/cnxk_ethdev.c  | 13 +++++++++++++
 drivers/net/cnxk/cnxk_ethdev.h  |  3 +++
 5 files changed, 56 insertions(+), 1 deletion(-)

diff --git a/drivers/net/cnxk/cn10k_ethdev.c b/drivers/net/cnxk/cn10k_ethdev.c
index d04b9eb..de688f0 100644
--- a/drivers/net/cnxk/cn10k_ethdev.c
+++ b/drivers/net/cnxk/cn10k_ethdev.c
@@ -204,6 +204,9 @@ cn10k_nix_tx_queue_setup(struct rte_eth_dev *eth_dev, uint16_t qid,
 
 		txq->cpt_io_addr = inl_lf->io_addr;
 		txq->cpt_fc = inl_lf->fc_addr;
+		txq->cpt_fc_sw = (int32_t *)((uintptr_t)dev->outb.fc_sw_mem +
+					     crypto_qid * RTE_CACHE_LINE_SIZE);
+
 		txq->cpt_desc = inl_lf->nb_desc * 0.7;
 		txq->sa_base = (uint64_t)dev->outb.sa_base;
 		txq->sa_base |= eth_dev->data->port_id;
diff --git a/drivers/net/cnxk/cn10k_ethdev.h b/drivers/net/cnxk/cn10k_ethdev.h
index c8666ce..acfdbb6 100644
--- a/drivers/net/cnxk/cn10k_ethdev.h
+++ b/drivers/net/cnxk/cn10k_ethdev.h
@@ -19,6 +19,7 @@ struct cn10k_eth_txq {
 	uint64_t sa_base;
 	uint64_t *cpt_fc;
 	uint16_t cpt_desc;
+	int32_t *cpt_fc_sw;
 	uint64_t lso_tun_fmt;
 	uint64_t ts_mem;
 	uint64_t mark_flag : 8;
diff --git a/drivers/net/cnxk/cn10k_tx.h b/drivers/net/cnxk/cn10k_tx.h
index ec8b027..ea13866 100644
--- a/drivers/net/cnxk/cn10k_tx.h
+++ b/drivers/net/cnxk/cn10k_tx.h
@@ -209,6 +209,37 @@ cn10k_nix_tx_skeleton(struct cn10k_eth_txq *txq, uint64_t *cmd,
 }
 
 static __rte_always_inline void
+cn10k_nix_sec_fc_wait(struct cn10k_eth_txq *txq, uint16_t nb_pkts)
+{
+	int32_t nb_desc, val, newval;
+	int32_t *fc_sw;
+	volatile uint64_t *fc;
+
+	/* Check if there is any CPT instruction to submit */
+	if (!nb_pkts)
+		return;
+
+again:
+	fc_sw = txq->cpt_fc_sw;
+	val = __atomic_sub_fetch(fc_sw, nb_pkts, __ATOMIC_RELAXED);
+	if (likely(val >= 0))
+		return;
+
+	nb_desc = txq->cpt_desc;
+	fc = txq->cpt_fc;
+	while (true) {
+		newval = nb_desc - __atomic_load_n(fc, __ATOMIC_RELAXED);
+		newval -= nb_pkts;
+		if (newval >= 0)
+			break;
+	}
+
+	if (!__atomic_compare_exchange_n(fc_sw, &val, newval, false,
+					 __ATOMIC_RELAXED, __ATOMIC_RELAXED))
+		goto again;
+}
+
+static __rte_always_inline void
 cn10k_nix_sec_steorl(uintptr_t io_addr, uint32_t lmt_id, uint8_t lnum,
 		     uint8_t loff, uint8_t shft)
 {
@@ -995,6 +1026,7 @@ cn10k_nix_xmit_pkts(void *tx_queue, uint64_t *ws, struct rte_mbuf **tx_pkts,
 	if (flags & NIX_TX_OFFLOAD_SECURITY_F) {
 		/* Reduce pkts to be sent to CPT */
 		burst -= ((c_lnum << 1) + c_loff);
+		cn10k_nix_sec_fc_wait(txq, (c_lnum << 1) + c_loff);
 		cn10k_nix_sec_steorl(c_io_addr, c_lmt_id, c_lnum, c_loff,
 				     c_shft);
 	}
@@ -1138,6 +1170,7 @@ cn10k_nix_xmit_pkts_mseg(void *tx_queue, uint64_t *ws,
 	if (flags & NIX_TX_OFFLOAD_SECURITY_F) {
 		/* Reduce pkts to be sent to CPT */
 		burst -= ((c_lnum << 1) + c_loff);
+		cn10k_nix_sec_fc_wait(txq, (c_lnum << 1) + c_loff);
 		cn10k_nix_sec_steorl(c_io_addr, c_lmt_id, c_lnum, c_loff,
 				     c_shft);
 	}
@@ -2682,9 +2715,11 @@ cn10k_nix_xmit_pkts_vector(void *tx_queue, uint64_t *ws,
 	left -= burst;
 
 	/* Submit CPT instructions if any */
-	if (flags & NIX_TX_OFFLOAD_SECURITY_F)
+	if (flags & NIX_TX_OFFLOAD_SECURITY_F) {
+		cn10k_nix_sec_fc_wait(txq, (c_lnum << 1) + c_loff);
 		cn10k_nix_sec_steorl(c_io_addr, c_lmt_id, c_lnum, c_loff,
 				     c_shft);
+	}
 
 	/* Trigger LMTST */
 	if (lnum > 16) {
diff --git a/drivers/net/cnxk/cnxk_ethdev.c b/drivers/net/cnxk/cnxk_ethdev.c
index e1b1e16..12ff30f 100644
--- a/drivers/net/cnxk/cnxk_ethdev.c
+++ b/drivers/net/cnxk/cnxk_ethdev.c
@@ -155,9 +155,19 @@ nix_security_setup(struct cnxk_eth_dev *dev)
 		dev->outb.sa_base = roc_nix_inl_outb_sa_base_get(nix);
 		dev->outb.sa_bmap_mem = mem;
 		dev->outb.sa_bmap = bmap;
+
+		dev->outb.fc_sw_mem = plt_zmalloc(dev->outb.nb_crypto_qs *
+							  RTE_CACHE_LINE_SIZE,
+						  RTE_CACHE_LINE_SIZE);
+		if (!dev->outb.fc_sw_mem) {
+			plt_err("Outbound fc sw mem alloc failed");
+			goto sa_bmap_free;
+		}
 	}
 	return 0;
 
+sa_bmap_free:
+	plt_free(dev->outb.sa_bmap_mem);
 sa_dptr_free:
 	if (dev->inb.sa_dptr)
 		plt_free(dev->inb.sa_dptr);
@@ -253,6 +263,9 @@ nix_security_release(struct cnxk_eth_dev *dev)
 			plt_free(dev->outb.sa_dptr);
 			dev->outb.sa_dptr = NULL;
 		}
+
+		plt_free(dev->outb.fc_sw_mem);
+		dev->outb.fc_sw_mem = NULL;
 	}
 
 	dev->inb.inl_dev = false;
diff --git a/drivers/net/cnxk/cnxk_ethdev.h b/drivers/net/cnxk/cnxk_ethdev.h
index f2a3bad..00ac32f 100644
--- a/drivers/net/cnxk/cnxk_ethdev.h
+++ b/drivers/net/cnxk/cnxk_ethdev.h
@@ -321,6 +321,9 @@ struct cnxk_eth_dev_sec_outb {
 	/* Crypto queues => CPT lf count */
 	uint16_t nb_crypto_qs;
 
+	/* FC sw mem */
+	uint64_t *fc_sw_mem;
+
 	/* Active sessions */
 	uint16_t nb_sess;
 
-- 
2.8.4