[dpdk-dev] [PATCH v3 55/62] net/cnxk: add base PTP timesync support

[Nithin Dabilpuram <ndabilpuram@marvell.com>]

From: Sunil Kumar Kori <skori@marvell.com>

Base PTP timesync support is added for cn9k and cn10k platforms.

Signed-off-by: Sunil Kumar Kori <skori@marvell.com>
---
 drivers/net/cnxk/cn10k_ethdev.c  |  31 +++++
 drivers/net/cnxk/cn10k_ethdev.h  |   1 +
 drivers/net/cnxk/cn10k_rx.c      |  32 ++---
 drivers/net/cnxk/cn10k_rx.h      |  61 +++++++---
 drivers/net/cnxk/cn10k_rx_mseg.c |   2 +-
 drivers/net/cnxk/cn10k_rx_vec.c  |   5 +-
 drivers/net/cnxk/cn10k_tx.c      |  28 +++--
 drivers/net/cnxk/cn10k_tx.h      | 193 +++++++++++++++++++++++------
 drivers/net/cnxk/cn10k_tx_mseg.c |   2 +-
 drivers/net/cnxk/cn10k_tx_vec.c  |   3 +-
 drivers/net/cnxk/cn9k_ethdev.c   |  34 +++++-
 drivers/net/cnxk/cn9k_ethdev.h   |   1 +
 drivers/net/cnxk/cn9k_rx.c       |  32 ++---
 drivers/net/cnxk/cn9k_rx.h       |  61 +++++++---
 drivers/net/cnxk/cn9k_rx_mseg.c  |   2 +-
 drivers/net/cnxk/cn9k_rx_vec.c   |   5 +-
 drivers/net/cnxk/cn9k_tx.c       |  28 +++--
 drivers/net/cnxk/cn9k_tx.h       | 253 ++++++++++++++++++++++++++++-----------
 drivers/net/cnxk/cn9k_tx_mseg.c  |   2 +-
 drivers/net/cnxk/cn9k_tx_vec.c   |   3 +-
 drivers/net/cnxk/cnxk_ethdev.c   |  36 +++++-
 drivers/net/cnxk/cnxk_ethdev.h   |  64 +++++++++-
 drivers/net/cnxk/cnxk_ptp.c      | 169 ++++++++++++++++++++++++++
 drivers/net/cnxk/meson.build     |   1 +
 24 files changed, 834 insertions(+), 215 deletions(-)
 create mode 100644 drivers/net/cnxk/cnxk_ptp.c

diff --git a/drivers/net/cnxk/cn10k_ethdev.c b/drivers/net/cnxk/cn10k_ethdev.c
index bddb7fb..5e0de13 100644
--- a/drivers/net/cnxk/cn10k_ethdev.c
+++ b/drivers/net/cnxk/cn10k_ethdev.c
@@ -30,6 +30,9 @@ nix_rx_offload_flags(struct rte_eth_dev *eth_dev)
 	if (dev->rx_offloads & DEV_RX_OFFLOAD_SCATTER)
 		flags |= NIX_RX_MULTI_SEG_F;
 
+	if ((dev->rx_offloads & DEV_RX_OFFLOAD_TIMESTAMP))
+		flags |= NIX_RX_OFFLOAD_TSTAMP_F;
+
 	if (!dev->ptype_disable)
 		flags |= NIX_RX_OFFLOAD_PTYPE_F;
 
@@ -95,6 +98,9 @@ nix_tx_offload_flags(struct rte_eth_dev *eth_dev)
 		flags |= (NIX_TX_OFFLOAD_TSO_F | NIX_TX_OFFLOAD_OL3_OL4_CSUM_F |
 			  NIX_TX_OFFLOAD_L3_L4_CSUM_F);
 
+	if ((dev->rx_offloads & DEV_RX_OFFLOAD_TIMESTAMP))
+		flags |= NIX_TX_OFFLOAD_TSTAMP_F;
+
 	return flags;
 }
 
@@ -121,6 +127,7 @@ nix_form_default_desc(struct cnxk_eth_dev *dev, struct cn10k_eth_txq *txq,
 {
 	struct nix_send_ext_s *send_hdr_ext;
 	union nix_send_hdr_w0_u send_hdr_w0;
+	struct nix_send_mem_s *send_mem;
 	union nix_send_sg_s sg_w0;
 
 	RTE_SET_USED(dev);
@@ -136,6 +143,22 @@ nix_form_default_desc(struct cnxk_eth_dev *dev, struct cn10k_eth_txq *txq,
 
 		send_hdr_ext = (struct nix_send_ext_s *)&txq->cmd[0];
 		send_hdr_ext->w0.subdc = NIX_SUBDC_EXT;
+		if (dev->tx_offload_flags & NIX_TX_OFFLOAD_TSTAMP_F) {
+			/* Default: one seg packet would have:
+			 * 2(HDR) + 2(EXT) + 1(SG) + 1(IOVA) + 2(MEM)
+			 * => 8/2 - 1 = 3
+			 */
+			send_hdr_w0.sizem1 = 3;
+			send_hdr_ext->w0.tstmp = 1;
+
+			/* To calculate the offset for send_mem,
+			 * send_hdr->w0.sizem1 * 2
+			 */
+			send_mem = (struct nix_send_mem_s *)(txq->cmd + 2);
+			send_mem->w0.subdc = NIX_SUBDC_MEM;
+			send_mem->w0.alg = NIX_SENDMEMALG_SETTSTMP;
+			send_mem->addr = dev->tstamp.tx_tstamp_iova;
+		}
 	} else {
 		/* 2(HDR) + 1(SG) + 1(IOVA) = 4/2 - 1 = 1 */
 		send_hdr_w0.sizem1 = 1;
@@ -221,6 +244,7 @@ cn10k_nix_rx_queue_setup(struct rte_eth_dev *eth_dev, uint16_t qid,
 	rxq->wdata = cq->wdata;
 	rxq->head = cq->head;
 	rxq->qmask = cq->qmask;
+	rxq->tstamp = &dev->tstamp;
 
 	/* Data offset from data to start of mbuf is first_skip */
 	rxq->data_off = rq->first_skip;
@@ -342,6 +366,7 @@ static int
 cn10k_nix_dev_start(struct rte_eth_dev *eth_dev)
 {
 	struct cnxk_eth_dev *dev = cnxk_eth_pmd_priv(eth_dev);
+	struct roc_nix *nix = &dev->nix;
 	int rc;
 
 	/* Common eth dev start */
@@ -349,6 +374,12 @@ cn10k_nix_dev_start(struct rte_eth_dev *eth_dev)
 	if (rc)
 		return rc;
 
+	/* Update VF about data off shifted by 8 bytes if PTP already
+	 * enabled in PF owning this VF
+	 */
+	if (dev->ptp_en && (!roc_nix_is_pf(nix) && (!roc_nix_is_sdp(nix))))
+		nix_ptp_enable_vf(eth_dev);
+
 	/* Setting up the rx[tx]_offload_flags due to change
 	 * in rx[tx]_offloads.
 	 */
diff --git a/drivers/net/cnxk/cn10k_ethdev.h b/drivers/net/cnxk/cn10k_ethdev.h
index d39ca31..8b6e0f2 100644
--- a/drivers/net/cnxk/cn10k_ethdev.h
+++ b/drivers/net/cnxk/cn10k_ethdev.h
@@ -31,6 +31,7 @@ struct cn10k_eth_rxq {
 	uint32_t available;
 	uint16_t data_off;
 	uint16_t rq;
+	struct cnxk_timesync_info *tstamp;
 } __plt_cache_aligned;
 
 /* Rx and Tx routines */
diff --git a/drivers/net/cnxk/cn10k_rx.c b/drivers/net/cnxk/cn10k_rx.c
index 0598111..c9744e2 100644
--- a/drivers/net/cnxk/cn10k_rx.c
+++ b/drivers/net/cnxk/cn10k_rx.c
@@ -5,7 +5,7 @@
 #include "cn10k_ethdev.h"
 #include "cn10k_rx.h"
 
-#define R(name, f3, f2, f1, f0, flags)					       \
+#define R(name, f4, f3, f2, f1, f0, flags)				       \
 	uint16_t __rte_noinline __rte_hot cn10k_nix_recv_pkts_##name(	       \
 		void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t pkts)      \
 	{                                                                      \
@@ -17,12 +17,13 @@ NIX_RX_FASTPATH_MODES
 
 static inline void
 pick_rx_func(struct rte_eth_dev *eth_dev,
-	     const eth_rx_burst_t rx_burst[2][2][2][2])
+	     const eth_rx_burst_t rx_burst[2][2][2][2][2])
 {
 	struct cnxk_eth_dev *dev = cnxk_eth_pmd_priv(eth_dev);
 
-	/* [MARK] [CKSUM] [PTYPE] [RSS] */
+	/* [TSP] [MARK] [CKSUM] [PTYPE] [RSS] */
 	eth_dev->rx_pkt_burst = rx_burst
+		[!!(dev->rx_offload_flags & NIX_RX_OFFLOAD_TSTAMP_F)]
 		[!!(dev->rx_offload_flags & NIX_RX_OFFLOAD_MARK_UPDATE_F)]
 		[!!(dev->rx_offload_flags & NIX_RX_OFFLOAD_CHECKSUM_F)]
 		[!!(dev->rx_offload_flags & NIX_RX_OFFLOAD_PTYPE_F)]
@@ -34,31 +35,34 @@ cn10k_eth_set_rx_function(struct rte_eth_dev *eth_dev)
 {
 	struct cnxk_eth_dev *dev = cnxk_eth_pmd_priv(eth_dev);
 
-	const eth_rx_burst_t nix_eth_rx_burst[2][2][2][2] = {
-#define R(name, f3, f2, f1, f0, flags)					      \
-	[f3][f2][f1][f0] = cn10k_nix_recv_pkts_##name,
+	const eth_rx_burst_t nix_eth_rx_burst[2][2][2][2][2] = {
+#define R(name, f4, f3, f2, f1, f0, flags)				       \
+	[f4][f3][f2][f1][f0] = cn10k_nix_recv_pkts_##name,
 
 		NIX_RX_FASTPATH_MODES
 #undef R
 	};
 
-	const eth_rx_burst_t nix_eth_rx_burst_mseg[2][2][2][2] = {
-#define R(name, f3, f2, f1, f0, flags)					      \
-	[f3][f2][f1][f0] = cn10k_nix_recv_pkts_mseg_##name,
+	const eth_rx_burst_t nix_eth_rx_burst_mseg[2][2][2][2][2] = {
+#define R(name, f4, f3, f2, f1, f0, flags)				       \
+	[f4][f3][f2][f1][f0] = cn10k_nix_recv_pkts_mseg_##name,
 
 		NIX_RX_FASTPATH_MODES
 #undef R
 	};
 
-	const eth_rx_burst_t nix_eth_rx_vec_burst[2][2][2][2] = {
-#define R(name, f3, f2, f1, f0, flags)					      \
-	[f3][f2][f1][f0] = cn10k_nix_recv_pkts_vec_##name,
+	const eth_rx_burst_t nix_eth_rx_vec_burst[2][2][2][2][2] = {
+#define R(name, f4, f3, f2, f1, f0, flags)				       \
+	[f4][f3][f2][f1][f0] = cn10k_nix_recv_pkts_vec_##name,
 
 		NIX_RX_FASTPATH_MODES
 #undef R
 	};
 
-	if (dev->scalar_ena)
+	/* For PTP enabled, scalar rx function should be chosen as most of the
+	 * PTP apps are implemented to rx burst 1 pkt.
+	 */
+	if (dev->scalar_ena || dev->rx_offloads & DEV_RX_OFFLOAD_TIMESTAMP)
 		pick_rx_func(eth_dev, nix_eth_rx_burst);
 	else
 		pick_rx_func(eth_dev, nix_eth_rx_vec_burst);
@@ -69,6 +73,6 @@ cn10k_eth_set_rx_function(struct rte_eth_dev *eth_dev)
 	/* Copy multi seg version with no offload for tear down sequence */
 	if (rte_eal_process_type() == RTE_PROC_PRIMARY)
 		dev->rx_pkt_burst_no_offload =
-			nix_eth_rx_burst_mseg[0][0][0][0];
+			nix_eth_rx_burst_mseg[0][0][0][0][0];
 	rte_mb();
 }
diff --git a/drivers/net/cnxk/cn10k_rx.h b/drivers/net/cnxk/cn10k_rx.h
index 29ee0ac..c09ccdf 100644
--- a/drivers/net/cnxk/cn10k_rx.h
+++ b/drivers/net/cnxk/cn10k_rx.h
@@ -7,6 +7,8 @@
 #include <rte_ether.h>
 #include <rte_vect.h>
 
+#include <cnxk_ethdev.h>
+
 #define NIX_RX_OFFLOAD_NONE	     (0)
 #define NIX_RX_OFFLOAD_RSS_F	     BIT(0)
 #define NIX_RX_OFFLOAD_PTYPE_F	     BIT(1)
@@ -250,6 +252,10 @@ cn10k_nix_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t pkts,
 
 		cn10k_nix_cqe_to_mbuf(cq, cq->tag, mbuf, lookup_mem, mbuf_init,
 				      flags);
+		cnxk_nix_mbuf_to_tstamp(mbuf, rxq->tstamp,
+					(flags & NIX_RX_OFFLOAD_TSTAMP_F),
+					(uint64_t *)((uint8_t *)mbuf + data_off)
+					);
 		rx_pkts[packets++] = mbuf;
 		roc_prefetch_store_keep(mbuf);
 		head++;
@@ -487,27 +493,44 @@ cn10k_nix_recv_pkts_vector(void *rx_queue, struct rte_mbuf **rx_pkts,
 #define PTYPE_F	  NIX_RX_OFFLOAD_PTYPE_F
 #define CKSUM_F	  NIX_RX_OFFLOAD_CHECKSUM_F
 #define MARK_F	  NIX_RX_OFFLOAD_MARK_UPDATE_F
+#define TS_F      NIX_RX_OFFLOAD_TSTAMP_F
 
-/* [MARK] [CKSUM] [PTYPE] [RSS] */
-#define NIX_RX_FASTPATH_MODES					       \
-R(no_offload,			0, 0, 0, 0, NIX_RX_OFFLOAD_NONE)       \
-R(rss,				0, 0, 0, 1, RSS_F)		       \
-R(ptype,			0, 0, 1, 0, PTYPE_F)		       \
-R(ptype_rss,			0, 0, 1, 1, PTYPE_F | RSS_F)	       \
-R(cksum,			0, 1, 0, 0, CKSUM_F)		       \
-R(cksum_rss,			0, 1, 0, 1, CKSUM_F | RSS_F)	       \
-R(cksum_ptype,			0, 1, 1, 0, CKSUM_F | PTYPE_F)	       \
-R(cksum_ptype_rss,		0, 1, 1, 1, CKSUM_F | PTYPE_F | RSS_F) \
-R(mark,				1, 0, 0, 0, MARK_F)		       \
-R(mark_rss,			1, 0, 0, 1, MARK_F | RSS_F)	       \
-R(mark_ptype,			1, 0, 1, 0, MARK_F | PTYPE_F)	       \
-R(mark_ptype_rss,		1, 0, 1, 1, MARK_F | PTYPE_F | RSS_F)  \
-R(mark_cksum,			1, 1, 0, 0, MARK_F | CKSUM_F)	       \
-R(mark_cksum_rss,		1, 1, 0, 1, MARK_F | CKSUM_F | RSS_F)  \
-R(mark_cksum_ptype,		1, 1, 1, 0, MARK_F | CKSUM_F | PTYPE_F)\
-R(mark_cksum_ptype_rss,		1, 1, 1, 1, MARK_F | CKSUM_F | PTYPE_F | RSS_F)
+/* [TS] [MARK] [CKSUM] [PTYPE] [RSS] */
+#define NIX_RX_FASTPATH_MODES						       \
+R(no_offload,			0, 0, 0, 0, 0, NIX_RX_OFFLOAD_NONE)	       \
+R(rss,				0, 0, 0, 0, 1, RSS_F)			       \
+R(ptype,			0, 0, 0, 1, 0, PTYPE_F)			       \
+R(ptype_rss,			0, 0, 0, 1, 1, PTYPE_F | RSS_F)		       \
+R(cksum,			0, 0, 1, 0, 0, CKSUM_F)			       \
+R(cksum_rss,			0, 0, 1, 0, 1, CKSUM_F | RSS_F)		       \
+R(cksum_ptype,			0, 0, 1, 1, 0, CKSUM_F | PTYPE_F)	       \
+R(cksum_ptype_rss,		0, 0, 1, 1, 1, CKSUM_F | PTYPE_F | RSS_F)      \
+R(mark,				0, 1, 0, 0, 0, MARK_F)			       \
+R(mark_rss,			0, 1, 0, 0, 1, MARK_F | RSS_F)		       \
+R(mark_ptype,			0, 1, 0, 1, 0, MARK_F | PTYPE_F)	       \
+R(mark_ptype_rss,		0, 1, 0, 1, 1, MARK_F | PTYPE_F | RSS_F)       \
+R(mark_cksum,			0, 1, 1, 0, 0, MARK_F | CKSUM_F)	       \
+R(mark_cksum_rss,		0, 1, 1, 0, 1, MARK_F | CKSUM_F | RSS_F)       \
+R(mark_cksum_ptype,		0, 1, 1, 1, 0, MARK_F | CKSUM_F | PTYPE_F)     \
+R(mark_cksum_ptype_rss,		0, 1, 1, 1, 1, MARK_F | CKSUM_F | PTYPE_F | RSS_F)\
+R(ts,				1, 0, 0, 0, 0, TS_F)			       \
+R(ts_rss,			1, 0, 0, 0, 1, TS_F | RSS_F)		       \
+R(ts_ptype,			1, 0, 0, 1, 0, TS_F | PTYPE_F)		       \
+R(ts_ptype_rss,			1, 0, 0, 1, 1, TS_F | PTYPE_F | RSS_F)	       \
+R(ts_cksum,			1, 0, 1, 0, 0, TS_F | CKSUM_F)		       \
+R(ts_cksum_rss,			1, 0, 1, 0, 1, TS_F | CKSUM_F | RSS_F)	       \
+R(ts_cksum_ptype,		1, 0, 1, 1, 0, TS_F | CKSUM_F | PTYPE_F)       \
+R(ts_cksum_ptype_rss,		1, 0, 1, 1, 1, TS_F | CKSUM_F | PTYPE_F | RSS_F)\
+R(ts_mark,			1, 1, 0, 0, 0, TS_F | MARK_F)		       \
+R(ts_mark_rss,			1, 1, 0, 0, 1, TS_F | MARK_F | RSS_F)	       \
+R(ts_mark_ptype,		1, 1, 0, 1, 0, TS_F | MARK_F | PTYPE_F)	       \
+R(ts_mark_ptype_rss,		1, 1, 0, 1, 1, TS_F | MARK_F | PTYPE_F | RSS_F)\
+R(ts_mark_cksum,		1, 1, 1, 0, 0, TS_F | MARK_F | CKSUM_F)	       \
+R(ts_mark_cksum_rss,		1, 1, 1, 0, 1, TS_F | MARK_F | CKSUM_F | RSS_F)\
+R(ts_mark_cksum_ptype,		1, 1, 1, 1, 0, TS_F | MARK_F | CKSUM_F | PTYPE_F)\
+R(ts_mark_cksum_ptype_rss,	1, 1, 1, 1, 1, TS_F | MARK_F | CKSUM_F | PTYPE_F | RSS_F)
 
-#define R(name, f3, f2, f1, f0, flags)                                         \
+#define R(name, f4, f3, f2, f1, f0, flags)				       \
 	uint16_t __rte_noinline __rte_hot cn10k_nix_recv_pkts_##name(          \
 		void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t pkts);     \
 									       \
diff --git a/drivers/net/cnxk/cn10k_rx_mseg.c b/drivers/net/cnxk/cn10k_rx_mseg.c
index 9d283f7..b67d21f 100644
--- a/drivers/net/cnxk/cn10k_rx_mseg.c
+++ b/drivers/net/cnxk/cn10k_rx_mseg.c
@@ -5,7 +5,7 @@
 #include "cn10k_ethdev.h"
 #include "cn10k_rx.h"
 
-#define R(name, f3, f2, f1, f0, flags)                                         \
+#define R(name, f4, f3, f2, f1, f0, flags)                                     \
 	uint16_t __rte_noinline __rte_hot cn10k_nix_recv_pkts_mseg_##name(     \
 		void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t pkts)      \
 	{                                                                      \
diff --git a/drivers/net/cnxk/cn10k_rx_vec.c b/drivers/net/cnxk/cn10k_rx_vec.c
index 0fa079c..1330235 100644
--- a/drivers/net/cnxk/cn10k_rx_vec.c
+++ b/drivers/net/cnxk/cn10k_rx_vec.c
@@ -5,12 +5,15 @@
 #include "cn10k_ethdev.h"
 #include "cn10k_rx.h"
 
-#define R(name, f3, f2, f1, f0, flags)					       \
+#define R(name, f4, f3, f2, f1, f0, flags)				       \
 	uint16_t __rte_noinline __rte_hot				       \
 		cn10k_nix_recv_pkts_vec_##name(void *rx_queue,                 \
 					       struct rte_mbuf **rx_pkts,      \
 					       uint16_t pkts)                  \
 	{                                                                      \
+		/* TSTMP is not supported by vector */                         \
+		if ((flags) & NIX_RX_OFFLOAD_TSTAMP_F)                         \
+			return 0;                                              \
 		return cn10k_nix_recv_pkts_vector(rx_queue, rx_pkts, pkts,     \
 						  (flags));		       \
 	}
diff --git a/drivers/net/cnxk/cn10k_tx.c b/drivers/net/cnxk/cn10k_tx.c
index e6eb101..18694dc 100644
--- a/drivers/net/cnxk/cn10k_tx.c
+++ b/drivers/net/cnxk/cn10k_tx.c
@@ -5,7 +5,7 @@
 #include "cn10k_ethdev.h"
 #include "cn10k_tx.h"
 
-#define T(name, f4, f3, f2, f1, f0, sz, flags)				       \
+#define T(name, f5, f4, f3, f2, f1, f0, sz, flags)			       \
 	uint16_t __rte_noinline __rte_hot cn10k_nix_xmit_pkts_##name(	       \
 		void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t pkts)      \
 	{                                                                      \
@@ -24,12 +24,13 @@ NIX_TX_FASTPATH_MODES
 
 static inline void
 pick_tx_func(struct rte_eth_dev *eth_dev,
-	     const eth_tx_burst_t tx_burst[2][2][2][2][2])
+	     const eth_tx_burst_t tx_burst[2][2][2][2][2][2])
 {
 	struct cnxk_eth_dev *dev = cnxk_eth_pmd_priv(eth_dev);
 
-	/* [TSO] [NOFF] [VLAN] [OL3_OL4_CSUM] [IL3_IL4_CSUM] */
+	/* [TSP] [TSO] [NOFF] [VLAN] [OL3_OL4_CSUM] [IL3_IL4_CSUM] */
 	eth_dev->tx_pkt_burst = tx_burst
+		[!!(dev->tx_offload_flags & NIX_TX_OFFLOAD_TSTAMP_F)]
 		[!!(dev->tx_offload_flags & NIX_TX_OFFLOAD_TSO_F)]
 		[!!(dev->tx_offload_flags & NIX_TX_OFFLOAD_MBUF_NOFF_F)]
 		[!!(dev->tx_offload_flags & NIX_TX_OFFLOAD_VLAN_QINQ_F)]
@@ -42,25 +43,25 @@ cn10k_eth_set_tx_function(struct rte_eth_dev *eth_dev)
 {
 	struct cnxk_eth_dev *dev = cnxk_eth_pmd_priv(eth_dev);
 
-	const eth_tx_burst_t nix_eth_tx_burst[2][2][2][2][2] = {
-#define T(name, f4, f3, f2, f1, f0, sz, flags)                         \
-	[f4][f3][f2][f1][f0] = cn10k_nix_xmit_pkts_##name,
+	const eth_tx_burst_t nix_eth_tx_burst[2][2][2][2][2][2] = {
+#define T(name, f5, f4, f3, f2, f1, f0, sz, flags)                             \
+	[f5][f4][f3][f2][f1][f0] = cn10k_nix_xmit_pkts_##name,
 
 		NIX_TX_FASTPATH_MODES
 #undef T
 	};
 
-	const eth_tx_burst_t nix_eth_tx_burst_mseg[2][2][2][2][2] = {
-#define T(name, f4, f3, f2, f1, f0, sz, flags)				\
-	[f4][f3][f2][f1][f0] = cn10k_nix_xmit_pkts_mseg_##name,
+	const eth_tx_burst_t nix_eth_tx_burst_mseg[2][2][2][2][2][2] = {
+#define T(name, f5, f4, f3, f2, f1, f0, sz, flags)			       \
+	[f5][f4][f3][f2][f1][f0] = cn10k_nix_xmit_pkts_mseg_##name,
 
 		NIX_TX_FASTPATH_MODES
 #undef T
 	};
 
-	const eth_tx_burst_t nix_eth_tx_vec_burst[2][2][2][2][2] = {
-#define T(name, f4, f3, f2, f1, f0, sz, flags)                         \
-	[f4][f3][f2][f1][f0] = cn10k_nix_xmit_pkts_vec_##name,
+	const eth_tx_burst_t nix_eth_tx_vec_burst[2][2][2][2][2][2] = {
+#define T(name, f5, f4, f3, f2, f1, f0, sz, flags)                             \
+	[f5][f4][f3][f2][f1][f0] = cn10k_nix_xmit_pkts_vec_##name,
 
 		NIX_TX_FASTPATH_MODES
 #undef T
@@ -68,7 +69,8 @@ cn10k_eth_set_tx_function(struct rte_eth_dev *eth_dev)
 
 	if (dev->scalar_ena ||
 	    (dev->tx_offload_flags &
-	     (NIX_TX_OFFLOAD_VLAN_QINQ_F | NIX_TX_OFFLOAD_TSO_F)))
+	     (NIX_TX_OFFLOAD_VLAN_QINQ_F | NIX_TX_OFFLOAD_TSTAMP_F |
+	      NIX_TX_OFFLOAD_TSO_F)))
 		pick_tx_func(eth_dev, nix_eth_tx_burst);
 	else
 		pick_tx_func(eth_dev, nix_eth_tx_vec_burst);
diff --git a/drivers/net/cnxk/cn10k_tx.h b/drivers/net/cnxk/cn10k_tx.h
index b74df10..8b1446f 100644
--- a/drivers/net/cnxk/cn10k_tx.h
+++ b/drivers/net/cnxk/cn10k_tx.h
@@ -12,6 +12,7 @@
 #define NIX_TX_OFFLOAD_VLAN_QINQ_F    BIT(2)
 #define NIX_TX_OFFLOAD_MBUF_NOFF_F    BIT(3)
 #define NIX_TX_OFFLOAD_TSO_F	      BIT(4)
+#define NIX_TX_OFFLOAD_TSTAMP_F	      BIT(5)
 
 /* Flags to control xmit_prepare function.
  * Defining it from backwards to denote its been
@@ -24,7 +25,8 @@
 	 NIX_TX_OFFLOAD_VLAN_QINQ_F | NIX_TX_OFFLOAD_TSO_F)
 
 #define NIX_TX_NEED_EXT_HDR                                                    \
-	(NIX_TX_OFFLOAD_VLAN_QINQ_F | NIX_TX_OFFLOAD_TSO_F)
+	(NIX_TX_OFFLOAD_VLAN_QINQ_F | NIX_TX_OFFLOAD_TSTAMP_F |                \
+	 NIX_TX_OFFLOAD_TSO_F)
 
 #define NIX_XMIT_FC_OR_RETURN(txq, pkts)                                       \
 	do {                                                                   \
@@ -49,8 +51,12 @@
 static __rte_always_inline int
 cn10k_nix_tx_ext_subs(const uint16_t flags)
 {
-	return (flags &
-		(NIX_TX_OFFLOAD_VLAN_QINQ_F | NIX_TX_OFFLOAD_TSO_F)) ? 1 : 0;
+	return (flags & NIX_TX_OFFLOAD_TSTAMP_F)
+		       ? 2
+		       : ((flags &
+			   (NIX_TX_OFFLOAD_VLAN_QINQ_F | NIX_TX_OFFLOAD_TSO_F))
+				  ? 1
+				  : 0);
 }
 
 static __rte_always_inline uint8_t
@@ -380,6 +386,45 @@ cn10k_nix_xmit_prepare(struct rte_mbuf *m, uint64_t *cmd, uintptr_t lmt_addr,
 	*(rte_iova_t *)(lmt_addr + 8) = *(rte_iova_t *)(sg + 1);
 }
 
+static __rte_always_inline void
+cn10k_nix_xmit_prepare_tstamp(uintptr_t lmt_addr, const uint64_t *cmd,
+			      const uint64_t ol_flags, const uint16_t no_segdw,
+			      const uint16_t flags)
+{
+	if (flags & NIX_TX_OFFLOAD_TSTAMP_F) {
+		const uint8_t is_ol_tstamp = !(ol_flags & PKT_TX_IEEE1588_TMST);
+		struct nix_send_ext_s *send_hdr_ext =
+					(struct nix_send_ext_s *)lmt_addr + 16;
+		uint64_t *lmt = (uint64_t *)lmt_addr;
+		uint16_t off = (no_segdw - 1) << 1;
+		struct nix_send_mem_s *send_mem;
+
+		send_mem = (struct nix_send_mem_s *)(lmt + off);
+		send_hdr_ext->w0.subdc = NIX_SUBDC_EXT;
+		send_hdr_ext->w0.tstmp = 1;
+		if (flags & NIX_TX_MULTI_SEG_F) {
+			/* Retrieving the default desc values */
+			lmt[off] = cmd[2];
+
+			/* Using compiler barier to avoid voilation of C
+			 * aliasing rules.
+			 */
+			rte_compiler_barrier();
+		}
+
+		/* Packets for which PKT_TX_IEEE1588_TMST is not set, tx tstamp
+		 * should not be recorded, hence changing the alg type to
+		 * NIX_SENDMEMALG_SET and also changing send mem addr field to
+		 * next 8 bytes as it corrpt the actual tx tstamp registered
+		 * address.
+		 */
+		send_mem->w0.subdc = NIX_SUBDC_MEM;
+		send_mem->w0.alg = NIX_SENDMEMALG_SETTSTMP - (is_ol_tstamp);
+		send_mem->addr =
+			(rte_iova_t)(((uint64_t *)cmd[3]) + is_ol_tstamp);
+	}
+}
+
 static __rte_always_inline uint16_t
 cn10k_nix_prepare_mseg(struct rte_mbuf *m, uint64_t *cmd, const uint16_t flags)
 {
@@ -445,7 +490,7 @@ cn10k_nix_prepare_mseg(struct rte_mbuf *m, uint64_t *cmd, const uint16_t flags)
 	/* Roundup extra dwords to multiple of 2 */
 	segdw = (segdw >> 1) + (segdw & 0x1);
 	/* Default dwords */
-	segdw += (off >> 1) + 1;
+	segdw += (off >> 1) + 1 + !!(flags & NIX_TX_OFFLOAD_TSTAMP_F);
 	send_hdr->w0.sizem1 = segdw - 1;
 
 	return segdw;
@@ -487,6 +532,8 @@ cn10k_nix_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t pkts,
 
 		cn10k_nix_xmit_prepare(tx_pkts[i], cmd, lmt_addr, flags,
 				       lso_tun_fmt);
+		cn10k_nix_xmit_prepare_tstamp(lmt_addr, &txq->cmd[0],
+					      tx_pkts[i]->ol_flags, 4, flags);
 		lmt_addr += (1ULL << ROC_LMT_LINE_SIZE_LOG2);
 	}
 
@@ -576,6 +623,9 @@ cn10k_nix_xmit_pkts_mseg(void *tx_queue, struct rte_mbuf **tx_pkts,
 		/* Store sg list directly on lmt line */
 		segdw = cn10k_nix_prepare_mseg(tx_pkts[i], (uint64_t *)lmt_addr,
 					       flags);
+		cn10k_nix_xmit_prepare_tstamp(lmt_addr, &txq->cmd[0],
+					      tx_pkts[i]->ol_flags, segdw,
+					      flags);
 		lmt_addr += (1ULL << ROC_LMT_LINE_SIZE_LOG2);
 		data128 |= (((__uint128_t)(segdw - 1)) << shft);
 		shft += 3;
@@ -1406,75 +1456,140 @@ cn10k_nix_xmit_pkts_vector(void *tx_queue, struct rte_mbuf **tx_pkts,
 #define VLAN_F	     NIX_TX_OFFLOAD_VLAN_QINQ_F
 #define NOFF_F	     NIX_TX_OFFLOAD_MBUF_NOFF_F
 #define TSO_F	     NIX_TX_OFFLOAD_TSO_F
+#define TSP_F	     NIX_TX_OFFLOAD_TSTAMP_F
 
-/* [TSO] [NOFF] [VLAN] [OL3OL4CSUM] [L3L4CSUM] */
+/* [TSP] [TSO] [NOFF] [VLAN] [OL3OL4CSUM] [L3L4CSUM] */
 #define NIX_TX_FASTPATH_MODES						\
-T(no_offload,				0, 0, 0, 0, 0,	4,		\
+T(no_offload,				0, 0, 0, 0, 0, 0,	4,	\
 		NIX_TX_OFFLOAD_NONE)					\
-T(l3l4csum,				0, 0, 0, 0, 1,	4,		\
+T(l3l4csum,				0, 0, 0, 0, 0, 1,	4,	\
 		L3L4CSUM_F)						\
-T(ol3ol4csum,				0, 0, 0, 1, 0,	4,		\
+T(ol3ol4csum,				0, 0, 0, 0, 1, 0,	4,	\
 		OL3OL4CSUM_F)						\
-T(ol3ol4csum_l3l4csum,			0, 0, 0, 1, 1,	4,		\
+T(ol3ol4csum_l3l4csum,			0, 0, 0, 0, 1, 1,	4,	\
 		OL3OL4CSUM_F | L3L4CSUM_F)				\
-T(vlan,					0, 0, 1, 0, 0,	6,		\
+T(vlan,					0, 0, 0, 1, 0, 0,	6,	\
 		VLAN_F)							\
-T(vlan_l3l4csum,			0, 0, 1, 0, 1,	6,		\
+T(vlan_l3l4csum,			0, 0, 0, 1, 0, 1,	6,	\
 		VLAN_F | L3L4CSUM_F)					\
-T(vlan_ol3ol4csum,			0, 0, 1, 1, 0,	6,		\
+T(vlan_ol3ol4csum,			0, 0, 0, 1, 1, 0,	6,	\
 		VLAN_F | OL3OL4CSUM_F)					\
-T(vlan_ol3ol4csum_l3l4csum,		0, 0, 1, 1, 1,	6,		\
+T(vlan_ol3ol4csum_l3l4csum,		0, 0, 0, 1, 1, 1,	6,	\
 		VLAN_F | OL3OL4CSUM_F |	L3L4CSUM_F)			\
-T(noff,					0, 1, 0, 0, 0,	4,		\
+T(noff,					0, 0, 1, 0, 0, 0,	4,	\
 		NOFF_F)							\
-T(noff_l3l4csum,			0, 1, 0, 0, 1,	4,		\
+T(noff_l3l4csum,			0, 0, 1, 0, 0, 1,	4,	\
 		NOFF_F | L3L4CSUM_F)					\
-T(noff_ol3ol4csum,			0, 1, 0, 1, 0,	4,		\
+T(noff_ol3ol4csum,			0, 0, 1, 0, 1, 0,	4,	\
 		NOFF_F | OL3OL4CSUM_F)					\
-T(noff_ol3ol4csum_l3l4csum,		0, 1, 0, 1, 1,	4,		\
+T(noff_ol3ol4csum_l3l4csum,		0, 0, 1, 0, 1, 1,	4,	\
 		NOFF_F | OL3OL4CSUM_F |	L3L4CSUM_F)			\
-T(noff_vlan,				0, 1, 1, 0, 0,	6,		\
+T(noff_vlan,				0, 0, 1, 1, 0, 0,	6,	\
 		NOFF_F | VLAN_F)					\
-T(noff_vlan_l3l4csum,			0, 1, 1, 0, 1,	6,		\
+T(noff_vlan_l3l4csum,			0, 0, 1, 1, 0, 1,	6,	\
 		NOFF_F | VLAN_F | L3L4CSUM_F)				\
-T(noff_vlan_ol3ol4csum,			0, 1, 1, 1, 0,	6,		\
+T(noff_vlan_ol3ol4csum,			0, 0, 1, 1, 1, 0,	6,	\
 		NOFF_F | VLAN_F | OL3OL4CSUM_F)				\
-T(noff_vlan_ol3ol4csum_l3l4csum,	0, 1, 1, 1, 1,	6,		\
+T(noff_vlan_ol3ol4csum_l3l4csum,	0, 0, 1, 1, 1, 1,	6,	\
 		NOFF_F | VLAN_F | OL3OL4CSUM_F | L3L4CSUM_F)		\
-T(tso,					1, 0, 0, 0, 0,	6,		\
+T(tso,					0, 1, 0, 0, 0, 0,	6,	\
 		TSO_F)							\
-T(tso_l3l4csum,				1, 0, 0, 0, 1,	6,		\
+T(tso_l3l4csum,				0, 1, 0, 0, 0, 1,	6,	\
 		TSO_F | L3L4CSUM_F)					\
-T(tso_ol3ol4csum,			1, 0, 0, 1, 0,	6,		\
+T(tso_ol3ol4csum,			0, 1, 0, 0, 1, 0,	6,	\
 		TSO_F | OL3OL4CSUM_F)					\
-T(tso_ol3ol4csum_l3l4csum,		1, 0, 0, 1, 1,	6,		\
+T(tso_ol3ol4csum_l3l4csum,		0, 1, 0, 0, 1, 1,	6,	\
 		TSO_F | OL3OL4CSUM_F | L3L4CSUM_F)			\
-T(tso_vlan,				1, 0, 1, 0, 0,	6,		\
+T(tso_vlan,				0, 1, 0, 1, 0, 0,	6,	\
 		TSO_F | VLAN_F)						\
-T(tso_vlan_l3l4csum,			1, 0, 1, 0, 1,	6,		\
+T(tso_vlan_l3l4csum,			0, 1, 0, 1, 0, 1,	6,	\
 		TSO_F | VLAN_F | L3L4CSUM_F)				\
-T(tso_vlan_ol3ol4csum,			1, 0, 1, 1, 0,	6,		\
+T(tso_vlan_ol3ol4csum,			0, 1, 0, 1, 1, 0,	6,	\
 		TSO_F | VLAN_F | OL3OL4CSUM_F)				\
-T(tso_vlan_ol3ol4csum_l3l4csum,		1, 0, 1, 1, 1,	6,		\
+T(tso_vlan_ol3ol4csum_l3l4csum,		0, 1, 0, 1, 1, 1,	6,	\
 		TSO_F | VLAN_F | OL3OL4CSUM_F |	L3L4CSUM_F)		\
-T(tso_noff,				1, 1, 0, 0, 0,	6,		\
+T(tso_noff,				0, 1, 1, 0, 0, 0,	6,	\
 		TSO_F | NOFF_F)						\
-T(tso_noff_l3l4csum,			1, 1, 0, 0, 1,	6,		\
+T(tso_noff_l3l4csum,			0, 1, 1, 0, 0, 1,	6,	\
 		TSO_F | NOFF_F | L3L4CSUM_F)				\
-T(tso_noff_ol3ol4csum,			1, 1, 0, 1, 0,	6,		\
+T(tso_noff_ol3ol4csum,			0, 1, 1, 0, 1, 0,	6,	\
 		TSO_F | NOFF_F | OL3OL4CSUM_F)				\
-T(tso_noff_ol3ol4csum_l3l4csum,		1, 1, 0, 1, 1,	6,		\
+T(tso_noff_ol3ol4csum_l3l4csum,		0, 1, 1, 0, 1, 1,	6,	\
 		TSO_F | NOFF_F | OL3OL4CSUM_F |	L3L4CSUM_F)		\
-T(tso_noff_vlan,			1, 1, 1, 0, 0,	6,		\
+T(tso_noff_vlan,			0, 1, 1, 1, 0, 0,	6,	\
 		TSO_F | NOFF_F | VLAN_F)				\
-T(tso_noff_vlan_l3l4csum,		1, 1, 1, 0, 1,	6,		\
+T(tso_noff_vlan_l3l4csum,		0, 1, 1, 1, 0, 1,	6,	\
 		TSO_F | NOFF_F | VLAN_F | L3L4CSUM_F)			\
-T(tso_noff_vlan_ol3ol4csum,		1, 1, 1, 1, 0,	6,		\
+T(tso_noff_vlan_ol3ol4csum,		0, 1, 1, 1, 1, 0,	6,	\
 		TSO_F | NOFF_F | VLAN_F | OL3OL4CSUM_F)			\
-T(tso_noff_vlan_ol3ol4csum_l3l4csum,	1, 1, 1, 1, 1,	6,		\
-		TSO_F | NOFF_F | VLAN_F | OL3OL4CSUM_F | L3L4CSUM_F)
+T(tso_noff_vlan_ol3ol4csum_l3l4csum,	0, 1, 1, 1, 1, 1,	6,	\
+		TSO_F | NOFF_F | VLAN_F | OL3OL4CSUM_F | L3L4CSUM_F)	\
+T(ts,					1, 0, 0, 0, 0, 0,	8,	\
+		TSP_F)							\
+T(ts_l3l4csum,				1, 0, 0, 0, 0, 1,	8,	\
+		TSP_F | L3L4CSUM_F)					\
+T(ts_ol3ol4csum,			1, 0, 0, 0, 1, 0,	8,	\
+		TSP_F | OL3OL4CSUM_F)					\
+T(ts_ol3ol4csum_l3l4csum,		1, 0, 0, 0, 1, 1,	8,	\
+		TSP_F | OL3OL4CSUM_F | L3L4CSUM_F)			\
+T(ts_vlan,				1, 0, 0, 1, 0, 0,	8,	\
+		TSP_F | VLAN_F)						\
+T(ts_vlan_l3l4csum,			1, 0, 0, 1, 0, 1,	8,	\
+		TSP_F | VLAN_F | L3L4CSUM_F)				\
+T(ts_vlan_ol3ol4csum,			1, 0, 0, 1, 1, 0,	8,	\
+		TSP_F | VLAN_F | OL3OL4CSUM_F)				\
+T(ts_vlan_ol3ol4csum_l3l4csum,		1, 0, 0, 1, 1, 1,	8,	\
+		TSP_F | VLAN_F | OL3OL4CSUM_F |	L3L4CSUM_F)		\
+T(ts_noff,				1, 0, 1, 0, 0, 0,	8,	\
+		TSP_F | NOFF_F)						\
+T(ts_noff_l3l4csum,			1, 0, 1, 0, 0, 1,	8,	\
+		TSP_F | NOFF_F | L3L4CSUM_F)				\
+T(ts_noff_ol3ol4csum,			1, 0, 1, 0, 1, 0,	8,	\
+		TSP_F | NOFF_F | OL3OL4CSUM_F)				\
+T(ts_noff_ol3ol4csum_l3l4csum,		1, 0, 1, 0, 1, 1,	8,	\
+		TSP_F | NOFF_F | OL3OL4CSUM_F |	L3L4CSUM_F)		\
+T(ts_noff_vlan,				1, 0, 1, 1, 0, 0,	8,	\
+		TSP_F | NOFF_F | VLAN_F)				\
+T(ts_noff_vlan_l3l4csum,		1, 0, 1, 1, 0, 1,	8,	\
+		TSP_F | NOFF_F | VLAN_F | L3L4CSUM_F)			\
+T(ts_noff_vlan_ol3ol4csum,		1, 0, 1, 1, 1, 0,	8,	\
+		TSP_F | NOFF_F | VLAN_F | OL3OL4CSUM_F)			\
+T(ts_noff_vlan_ol3ol4csum_l3l4csum,	1, 0, 1, 1, 1, 1,	8,	\
+		TSP_F | NOFF_F | VLAN_F | OL3OL4CSUM_F | L3L4CSUM_F)	\
+T(ts_tso,				1, 1, 0, 0, 0, 0,	8,	\
+		TSP_F | TSO_F)						\
+T(ts_tso_l3l4csum,			1, 1, 0, 0, 0, 1,	8,	\
+		TSP_F | TSO_F | L3L4CSUM_F)				\
+T(ts_tso_ol3ol4csum,			1, 1, 0, 0, 1, 0,	8,	\
+		TSP_F | TSO_F | OL3OL4CSUM_F)				\
+T(ts_tso_ol3ol4csum_l3l4csum,		1, 1, 0, 0, 1, 1,	8,	\
+		TSP_F | TSO_F | OL3OL4CSUM_F | L3L4CSUM_F)		\
+T(ts_tso_vlan,				1, 1, 0, 1, 0, 0,	8,	\
+		TSP_F | TSO_F | VLAN_F)					\
+T(ts_tso_vlan_l3l4csum,			1, 1, 0, 1, 0, 1,	8,	\
+		TSP_F | TSO_F | VLAN_F | L3L4CSUM_F)			\
+T(ts_tso_vlan_ol3ol4csum,		1, 1, 0, 1, 1, 0,	8,	\
+		TSP_F | TSO_F | VLAN_F | OL3OL4CSUM_F)			\
+T(ts_tso_vlan_ol3ol4csum_l3l4csum,	1, 1, 0, 1, 1, 1,	8,	\
+		TSP_F | TSO_F | VLAN_F | OL3OL4CSUM_F |	L3L4CSUM_F)	\
+T(ts_tso_noff,				1, 1, 1, 0, 0, 0,	8,	\
+		TSP_F | TSO_F | NOFF_F)					\
+T(ts_tso_noff_l3l4csum,			1, 1, 1, 0, 0, 1,	8,	\
+		TSP_F | TSO_F | NOFF_F | L3L4CSUM_F)			\
+T(ts_tso_noff_ol3ol4csum,		1, 1, 1, 0, 1, 0,	8,	\
+		TSP_F | TSO_F | NOFF_F | OL3OL4CSUM_F)			\
+T(ts_tso_noff_ol3ol4csum_l3l4csum,	1, 1, 1, 0, 1, 1,	8,	\
+		TSP_F | TSO_F | NOFF_F | OL3OL4CSUM_F |	L3L4CSUM_F)	\
+T(ts_tso_noff_vlan,			1, 1, 1, 1, 0, 0,	8,	\
+		TSP_F | TSO_F | NOFF_F | VLAN_F)			\
+T(ts_tso_noff_vlan_l3l4csum,		1, 1, 1, 1, 0, 1,	8,	\
+		TSP_F | TSO_F | NOFF_F | VLAN_F | L3L4CSUM_F)		\
+T(ts_tso_noff_vlan_ol3ol4csum,		1, 1, 1, 1, 1, 0,	8,	\
+		TSP_F | TSO_F | NOFF_F | VLAN_F | OL3OL4CSUM_F)		\
+T(ts_tso_noff_vlan_ol3ol4csum_l3l4csum,	1, 1, 1, 1, 1, 1,	8,	\
+		TSP_F | TSO_F | NOFF_F | VLAN_F | OL3OL4CSUM_F | L3L4CSUM_F)
 
-#define T(name, f4, f3, f2, f1, f0, sz, flags)                                 \
+#define T(name, f5, f4, f3, f2, f1, f0, sz, flags)			       \
 	uint16_t __rte_noinline __rte_hot cn10k_nix_xmit_pkts_##name(          \
 		void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t pkts);     \
 									       \
diff --git a/drivers/net/cnxk/cn10k_tx_mseg.c b/drivers/net/cnxk/cn10k_tx_mseg.c
index 6ae6907..33f6754 100644
--- a/drivers/net/cnxk/cn10k_tx_mseg.c
+++ b/drivers/net/cnxk/cn10k_tx_mseg.c
@@ -5,7 +5,7 @@
 #include "cn10k_ethdev.h"
 #include "cn10k_tx.h"
 
-#define T(name, f4, f3, f2, f1, f0, sz, flags)				       \
+#define T(name, f5, f4, f3, f2, f1, f0, sz, flags)			       \
 	uint16_t __rte_noinline __rte_hot				       \
 		cn10k_nix_xmit_pkts_mseg_##name(void *tx_queue,                \
 						struct rte_mbuf **tx_pkts,     \
diff --git a/drivers/net/cnxk/cn10k_tx_vec.c b/drivers/net/cnxk/cn10k_tx_vec.c
index 42baeb5..7453f3b 100644
--- a/drivers/net/cnxk/cn10k_tx_vec.c
+++ b/drivers/net/cnxk/cn10k_tx_vec.c
@@ -5,7 +5,7 @@
 #include "cn10k_ethdev.h"
 #include "cn10k_tx.h"
 
-#define T(name, f4, f3, f2, f1, f0, sz, flags)				       \
+#define T(name, f5, f4, f3, f2, f1, f0, sz, flags)			       \
 	uint16_t __rte_noinline __rte_hot				       \
 		cn10k_nix_xmit_pkts_vec_##name(void *tx_queue,                 \
 					       struct rte_mbuf **tx_pkts,      \
@@ -15,6 +15,7 @@
 									       \
 		/* VLAN, TSTMP, TSO is not supported by vec */                 \
 		if ((flags) & NIX_TX_OFFLOAD_VLAN_QINQ_F ||		       \
+		    (flags) & NIX_TX_OFFLOAD_TSTAMP_F ||		       \
 		    (flags) & NIX_TX_OFFLOAD_TSO_F)			       \
 			return 0;                                              \
 		return cn10k_nix_xmit_pkts_vector(tx_queue, tx_pkts, pkts, cmd,\
diff --git a/drivers/net/cnxk/cn9k_ethdev.c b/drivers/net/cnxk/cn9k_ethdev.c
index fc3054d..924b747 100644
--- a/drivers/net/cnxk/cn9k_ethdev.c
+++ b/drivers/net/cnxk/cn9k_ethdev.c
@@ -30,6 +30,9 @@ nix_rx_offload_flags(struct rte_eth_dev *eth_dev)
 	if (dev->rx_offloads & DEV_RX_OFFLOAD_SCATTER)
 		flags |= NIX_RX_MULTI_SEG_F;
 
+	if ((dev->rx_offloads & DEV_RX_OFFLOAD_TIMESTAMP))
+		flags |= NIX_RX_OFFLOAD_TSTAMP_F;
+
 	if (!dev->ptype_disable)
 		flags |= NIX_RX_OFFLOAD_PTYPE_F;
 
@@ -95,6 +98,9 @@ nix_tx_offload_flags(struct rte_eth_dev *eth_dev)
 		flags |= (NIX_TX_OFFLOAD_TSO_F | NIX_TX_OFFLOAD_OL3_OL4_CSUM_F |
 			  NIX_TX_OFFLOAD_L3_L4_CSUM_F);
 
+	if ((dev->rx_offloads & DEV_RX_OFFLOAD_TIMESTAMP))
+		flags |= NIX_TX_OFFLOAD_TSTAMP_F;
+
 	return flags;
 }
 
@@ -121,10 +127,9 @@ nix_form_default_desc(struct cnxk_eth_dev *dev, struct cn9k_eth_txq *txq,
 {
 	struct nix_send_ext_s *send_hdr_ext;
 	struct nix_send_hdr_s *send_hdr;
+	struct nix_send_mem_s *send_mem;
 	union nix_send_sg_s *sg;
 
-	RTE_SET_USED(dev);
-
 	/* Initialize the fields based on basic single segment packet */
 	memset(&txq->cmd, 0, sizeof(txq->cmd));
 
@@ -135,6 +140,23 @@ nix_form_default_desc(struct cnxk_eth_dev *dev, struct cn9k_eth_txq *txq,
 
 		send_hdr_ext = (struct nix_send_ext_s *)&txq->cmd[2];
 		send_hdr_ext->w0.subdc = NIX_SUBDC_EXT;
+		if (dev->tx_offload_flags & NIX_TX_OFFLOAD_TSTAMP_F) {
+			/* Default: one seg packet would have:
+			 * 2(HDR) + 2(EXT) + 1(SG) + 1(IOVA) + 2(MEM)
+			 * => 8/2 - 1 = 3
+			 */
+			send_hdr->w0.sizem1 = 3;
+			send_hdr_ext->w0.tstmp = 1;
+
+			/* To calculate the offset for send_mem,
+			 * send_hdr->w0.sizem1 * 2
+			 */
+			send_mem = (struct nix_send_mem_s *)
+				(txq->cmd + (send_hdr->w0.sizem1 << 1));
+			send_mem->w0.cn9k.subdc = NIX_SUBDC_MEM;
+			send_mem->w0.cn9k.alg = NIX_SENDMEMALG_SETTSTMP;
+			send_mem->addr = dev->tstamp.tx_tstamp_iova;
+		}
 		sg = (union nix_send_sg_s *)&txq->cmd[4];
 	} else {
 		send_hdr = (struct nix_send_hdr_s *)&txq->cmd[0];
@@ -219,6 +241,7 @@ cn9k_nix_rx_queue_setup(struct rte_eth_dev *eth_dev, uint16_t qid,
 	rxq->wdata = cq->wdata;
 	rxq->head = cq->head;
 	rxq->qmask = cq->qmask;
+	rxq->tstamp = &dev->tstamp;
 
 	/* Data offset from data to start of mbuf is first_skip */
 	rxq->data_off = rq->first_skip;
@@ -351,6 +374,7 @@ static int
 cn9k_nix_dev_start(struct rte_eth_dev *eth_dev)
 {
 	struct cnxk_eth_dev *dev = cnxk_eth_pmd_priv(eth_dev);
+	struct roc_nix *nix = &dev->nix;
 	int rc;
 
 	/* Common eth dev start */
@@ -358,6 +382,12 @@ cn9k_nix_dev_start(struct rte_eth_dev *eth_dev)
 	if (rc)
 		return rc;
 
+	/* Update VF about data off shifted by 8 bytes if PTP already
+	 * enabled in PF owning this VF
+	 */
+	if (dev->ptp_en && (!roc_nix_is_pf(nix) && (!roc_nix_is_sdp(nix))))
+		nix_ptp_enable_vf(eth_dev);
+
 	/* Setting up the rx[tx]_offload_flags due to change
 	 * in rx[tx]_offloads.
 	 */
diff --git a/drivers/net/cnxk/cn9k_ethdev.h b/drivers/net/cnxk/cn9k_ethdev.h
index b92f3fc..f481b3a 100644
--- a/drivers/net/cnxk/cn9k_ethdev.h
+++ b/drivers/net/cnxk/cn9k_ethdev.h
@@ -29,6 +29,7 @@ struct cn9k_eth_rxq {
 	uint32_t qmask;
 	uint32_t available;
 	uint16_t rq;
+	struct cnxk_timesync_info *tstamp;
 } __plt_cache_aligned;
 
 /* Rx and Tx routines */
diff --git a/drivers/net/cnxk/cn9k_rx.c b/drivers/net/cnxk/cn9k_rx.c
index 01eb21f..a15428d 100644
--- a/drivers/net/cnxk/cn9k_rx.c
+++ b/drivers/net/cnxk/cn9k_rx.c
@@ -5,7 +5,7 @@
 #include "cn9k_ethdev.h"
 #include "cn9k_rx.h"
 
-#define R(name, f3, f2, f1, f0, flags)					       \
+#define R(name, f4, f3, f2, f1, f0, flags)				       \
 	uint16_t __rte_noinline __rte_hot cn9k_nix_recv_pkts_##name(	       \
 		void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t pkts)      \
 	{                                                                      \
@@ -17,12 +17,13 @@ NIX_RX_FASTPATH_MODES
 
 static inline void
 pick_rx_func(struct rte_eth_dev *eth_dev,
-	     const eth_rx_burst_t rx_burst[2][2][2][2])
+	     const eth_rx_burst_t rx_burst[2][2][2][2][2])
 {
 	struct cnxk_eth_dev *dev = cnxk_eth_pmd_priv(eth_dev);
 
-	/* [MARK] [CKSUM] [PTYPE] [RSS] */
+	/* [TSP] [MARK] [CKSUM] [PTYPE] [RSS] */
 	eth_dev->rx_pkt_burst = rx_burst
+		[!!(dev->rx_offload_flags & NIX_RX_OFFLOAD_TSTAMP_F)]
 		[!!(dev->rx_offload_flags & NIX_RX_OFFLOAD_MARK_UPDATE_F)]
 		[!!(dev->rx_offload_flags & NIX_RX_OFFLOAD_CHECKSUM_F)]
 		[!!(dev->rx_offload_flags & NIX_RX_OFFLOAD_PTYPE_F)]
@@ -34,31 +35,34 @@ cn9k_eth_set_rx_function(struct rte_eth_dev *eth_dev)
 {
 	struct cnxk_eth_dev *dev = cnxk_eth_pmd_priv(eth_dev);
 
-	const eth_rx_burst_t nix_eth_rx_burst[2][2][2][2] = {
-#define R(name, f3, f2, f1, f0, flags)					\
-	[f3][f2][f1][f0] = cn9k_nix_recv_pkts_##name,
+	const eth_rx_burst_t nix_eth_rx_burst[2][2][2][2][2] = {
+#define R(name, f4, f3, f2, f1, f0, flags)				       \
+	[f4][f3][f2][f1][f0] = cn9k_nix_recv_pkts_##name,
 
 		NIX_RX_FASTPATH_MODES
 #undef R
 	};
 
-	const eth_rx_burst_t nix_eth_rx_burst_mseg[2][2][2][2] = {
-#define R(name, f3, f2, f1, f0, flags)					\
-	[f3][f2][f1][f0] = cn9k_nix_recv_pkts_mseg_##name,
+	const eth_rx_burst_t nix_eth_rx_burst_mseg[2][2][2][2][2] = {
+#define R(name, f4, f3, f2, f1, f0, flags)				       \
+	[f4][f3][f2][f1][f0] = cn9k_nix_recv_pkts_mseg_##name,
 
 		NIX_RX_FASTPATH_MODES
 #undef R
 	};
 
-	const eth_rx_burst_t nix_eth_rx_vec_burst[2][2][2][2] = {
-#define R(name, f3, f2, f1, f0, flags)					\
-	[f3][f2][f1][f0] = cn9k_nix_recv_pkts_vec_##name,
+	const eth_rx_burst_t nix_eth_rx_vec_burst[2][2][2][2][2] = {
+#define R(name, f4, f3, f2, f1, f0, flags)				       \
+	[f4][f3][f2][f1][f0] = cn9k_nix_recv_pkts_vec_##name,
 
 		NIX_RX_FASTPATH_MODES
 #undef R
 	};
 
-	if (dev->scalar_ena)
+	/* For PTP enabled, scalar rx function should be chosen as most of the
+	 * PTP apps are implemented to rx burst 1 pkt.
+	 */
+	if (dev->scalar_ena || dev->rx_offloads & DEV_RX_OFFLOAD_TIMESTAMP)
 		pick_rx_func(eth_dev, nix_eth_rx_burst);
 	else
 		pick_rx_func(eth_dev, nix_eth_rx_vec_burst);
@@ -69,6 +73,6 @@ cn9k_eth_set_rx_function(struct rte_eth_dev *eth_dev)
 	/* Copy multi seg version with no offload for tear down sequence */
 	if (rte_eal_process_type() == RTE_PROC_PRIMARY)
 		dev->rx_pkt_burst_no_offload =
-			nix_eth_rx_burst_mseg[0][0][0][0];
+			nix_eth_rx_burst_mseg[0][0][0][0][0];
 	rte_mb();
 }
diff --git a/drivers/net/cnxk/cn9k_rx.h b/drivers/net/cnxk/cn9k_rx.h
index f4b3282..c5ad5db 100644
--- a/drivers/net/cnxk/cn9k_rx.h
+++ b/drivers/net/cnxk/cn9k_rx.h
@@ -8,6 +8,8 @@
 #include <rte_ether.h>
 #include <rte_vect.h>
 
+#include <cnxk_ethdev.h>
+
 #define NIX_RX_OFFLOAD_NONE	     (0)
 #define NIX_RX_OFFLOAD_RSS_F	     BIT(0)
 #define NIX_RX_OFFLOAD_PTYPE_F	     BIT(1)
@@ -253,6 +255,10 @@ cn9k_nix_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t pkts,
 
 		cn9k_nix_cqe_to_mbuf(cq, cq->tag, mbuf, lookup_mem, mbuf_init,
 				     flags);
+		cnxk_nix_mbuf_to_tstamp(mbuf, rxq->tstamp,
+					(flags & NIX_RX_OFFLOAD_TSTAMP_F),
+					(uint64_t *)((uint8_t *)mbuf + data_off)
+					);
 		rx_pkts[packets++] = mbuf;
 		roc_prefetch_store_keep(mbuf);
 		head++;
@@ -489,27 +495,44 @@ cn9k_nix_recv_pkts_vector(void *rx_queue, struct rte_mbuf **rx_pkts,
 #define PTYPE_F	  NIX_RX_OFFLOAD_PTYPE_F
 #define CKSUM_F	  NIX_RX_OFFLOAD_CHECKSUM_F
 #define MARK_F	  NIX_RX_OFFLOAD_MARK_UPDATE_F
+#define TS_F	  NIX_RX_OFFLOAD_TSTAMP_F
 
-/* [MARK] [CKSUM] [PTYPE] [RSS] */
-#define NIX_RX_FASTPATH_MODES					       \
-R(no_offload,			0, 0, 0, 0, NIX_RX_OFFLOAD_NONE)       \
-R(rss,				0, 0, 0, 1, RSS_F)		       \
-R(ptype,			0, 0, 1, 0, PTYPE_F)		       \
-R(ptype_rss,			0, 0, 1, 1, PTYPE_F | RSS_F)	       \
-R(cksum,			0, 1, 0, 0, CKSUM_F)		       \
-R(cksum_rss,			0, 1, 0, 1, CKSUM_F | RSS_F)	       \
-R(cksum_ptype,			0, 1, 1, 0, CKSUM_F | PTYPE_F)	       \
-R(cksum_ptype_rss,		0, 1, 1, 1, CKSUM_F | PTYPE_F | RSS_F) \
-R(mark,				1, 0, 0, 0, MARK_F)		       \
-R(mark_rss,			1, 0, 0, 1, MARK_F | RSS_F)	       \
-R(mark_ptype,			1, 0, 1, 0, MARK_F | PTYPE_F)	       \
-R(mark_ptype_rss,		1, 0, 1, 1, MARK_F | PTYPE_F | RSS_F)  \
-R(mark_cksum,			1, 1, 0, 0, MARK_F | CKSUM_F)	       \
-R(mark_cksum_rss,		1, 1, 0, 1, MARK_F | CKSUM_F | RSS_F)  \
-R(mark_cksum_ptype,		1, 1, 1, 0, MARK_F | CKSUM_F | PTYPE_F)\
-R(mark_cksum_ptype_rss,		1, 1, 1, 1, MARK_F | CKSUM_F | PTYPE_F | RSS_F)
+/* [TS] [MARK] [CKSUM] [PTYPE] [RSS] */
+#define NIX_RX_FASTPATH_MODES						       \
+R(no_offload,			0, 0, 0, 0, 0, NIX_RX_OFFLOAD_NONE)	       \
+R(rss,				0, 0, 0, 0, 1, RSS_F)			       \
+R(ptype,			0, 0, 0, 1, 0, PTYPE_F)			       \
+R(ptype_rss,			0, 0, 0, 1, 1, PTYPE_F | RSS_F)		       \
+R(cksum,			0, 0, 1, 0, 0, CKSUM_F)			       \
+R(cksum_rss,			0, 0, 1, 0, 1, CKSUM_F | RSS_F)		       \
+R(cksum_ptype,			0, 0, 1, 1, 0, CKSUM_F | PTYPE_F)	       \
+R(cksum_ptype_rss,		0, 0, 1, 1, 1, CKSUM_F | PTYPE_F | RSS_F)      \
+R(mark,				0, 1, 0, 0, 0, MARK_F)			       \
+R(mark_rss,			0, 1, 0, 0, 1, MARK_F | RSS_F)		       \
+R(mark_ptype,			0, 1, 0, 1, 0, MARK_F | PTYPE_F)	       \
+R(mark_ptype_rss,		0, 1, 0, 1, 1, MARK_F | PTYPE_F | RSS_F)       \
+R(mark_cksum,			0, 1, 1, 0, 0, MARK_F | CKSUM_F)	       \
+R(mark_cksum_rss,		0, 1, 1, 0, 1, MARK_F | CKSUM_F | RSS_F)       \
+R(mark_cksum_ptype,		0, 1, 1, 1, 0, MARK_F | CKSUM_F | PTYPE_F)     \
+R(mark_cksum_ptype_rss,		0, 1, 1, 1, 1, MARK_F | CKSUM_F | PTYPE_F | RSS_F)\
+R(ts,				1, 0, 0, 0, 0, TS_F)			       \
+R(ts_rss,			1, 0, 0, 0, 1, TS_F | RSS_F)		       \
+R(ts_ptype,			1, 0, 0, 1, 0, TS_F | PTYPE_F)		       \
+R(ts_ptype_rss,			1, 0, 0, 1, 1, TS_F | PTYPE_F | RSS_F)	       \
+R(ts_cksum,			1, 0, 1, 0, 0, TS_F | CKSUM_F)		       \
+R(ts_cksum_rss,			1, 0, 1, 0, 1, TS_F | CKSUM_F | RSS_F)	       \
+R(ts_cksum_ptype,		1, 0, 1, 1, 0, TS_F | CKSUM_F | PTYPE_F)       \
+R(ts_cksum_ptype_rss,		1, 0, 1, 1, 1, TS_F | CKSUM_F | PTYPE_F | RSS_F)\
+R(ts_mark,			1, 1, 0, 0, 0, TS_F | MARK_F)		       \
+R(ts_mark_rss,			1, 1, 0, 0, 1, TS_F | MARK_F | RSS_F)	       \
+R(ts_mark_ptype,		1, 1, 0, 1, 0, TS_F | MARK_F | PTYPE_F)	       \
+R(ts_mark_ptype_rss,		1, 1, 0, 1, 1, TS_F | MARK_F | PTYPE_F | RSS_F)\
+R(ts_mark_cksum,		1, 1, 1, 0, 0, TS_F | MARK_F | CKSUM_F)	       \
+R(ts_mark_cksum_rss,		1, 1, 1, 0, 1, TS_F | MARK_F | CKSUM_F | RSS_F)\
+R(ts_mark_cksum_ptype,		1, 1, 1, 1, 0, TS_F | MARK_F | CKSUM_F | PTYPE_F)\
+R(ts_mark_cksum_ptype_rss,	1, 1, 1, 1, 1, TS_F | MARK_F | CKSUM_F | PTYPE_F | RSS_F)
 
-#define R(name, f3, f2, f1, f0, flags)                                         \
+#define R(name, f4, f3, f2, f1, f0, flags)				       \
 	uint16_t __rte_noinline __rte_hot cn9k_nix_recv_pkts_##name(           \
 		void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t pkts);     \
 									       \
diff --git a/drivers/net/cnxk/cn9k_rx_mseg.c b/drivers/net/cnxk/cn9k_rx_mseg.c
index 6ad8c1d..3b26962 100644
--- a/drivers/net/cnxk/cn9k_rx_mseg.c
+++ b/drivers/net/cnxk/cn9k_rx_mseg.c
@@ -5,7 +5,7 @@
 #include "cn9k_ethdev.h"
 #include "cn9k_rx.h"
 
-#define R(name, f3, f2, f1, f0, flags)                                         \
+#define R(name, f4, f3, f2, f1, f0, flags)                                     \
 	uint16_t __rte_noinline __rte_hot cn9k_nix_recv_pkts_mseg_##name(      \
 		void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t pkts)      \
 	{                                                                      \
diff --git a/drivers/net/cnxk/cn9k_rx_vec.c b/drivers/net/cnxk/cn9k_rx_vec.c
index 997177f..b19c7f3 100644
--- a/drivers/net/cnxk/cn9k_rx_vec.c
+++ b/drivers/net/cnxk/cn9k_rx_vec.c
@@ -5,10 +5,13 @@
 #include "cn9k_ethdev.h"
 #include "cn9k_rx.h"
 
-#define R(name, f3, f2, f1, f0, flags)                                         \
+#define R(name, f4, f3, f2, f1, f0, flags)				       \
 	uint16_t __rte_noinline __rte_hot cn9k_nix_recv_pkts_vec_##name(       \
 		void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t pkts)      \
 	{                                                                      \
+		/* TSTMP is not supported by vector */                         \
+		if ((flags) & NIX_RX_OFFLOAD_TSTAMP_F)                         \
+			return 0;                                              \
 		return cn9k_nix_recv_pkts_vector(rx_queue, rx_pkts, pkts,      \
 						 (flags));                     \
 	}
diff --git a/drivers/net/cnxk/cn9k_tx.c b/drivers/net/cnxk/cn9k_tx.c
index 2ff9720..b802606 100644
--- a/drivers/net/cnxk/cn9k_tx.c
+++ b/drivers/net/cnxk/cn9k_tx.c
@@ -5,7 +5,7 @@
 #include "cn9k_ethdev.h"
 #include "cn9k_tx.h"
 
-#define T(name, f4, f3, f2, f1, f0, sz, flags)				       \
+#define T(name, f5, f4, f3, f2, f1, f0, sz, flags)			       \
 	uint16_t __rte_noinline __rte_hot cn9k_nix_xmit_pkts_##name(	       \
 		void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t pkts)      \
 	{                                                                      \
@@ -23,12 +23,13 @@ NIX_TX_FASTPATH_MODES
 
 static inline void
 pick_tx_func(struct rte_eth_dev *eth_dev,
-	     const eth_tx_burst_t tx_burst[2][2][2][2][2])
+	     const eth_tx_burst_t tx_burst[2][2][2][2][2][2])
 {
 	struct cnxk_eth_dev *dev = cnxk_eth_pmd_priv(eth_dev);
 
-	/* [TSO] [NOFF] [VLAN] [OL3_OL4_CSUM] [IL3_IL4_CSUM] */
+	/* [TS] [TSO] [NOFF] [VLAN] [OL3_OL4_CSUM] [IL3_IL4_CSUM] */
 	eth_dev->tx_pkt_burst = tx_burst
+		[!!(dev->tx_offload_flags & NIX_TX_OFFLOAD_TSTAMP_F)]
 		[!!(dev->tx_offload_flags & NIX_TX_OFFLOAD_TSO_F)]
 		[!!(dev->tx_offload_flags & NIX_TX_OFFLOAD_MBUF_NOFF_F)]
 		[!!(dev->tx_offload_flags & NIX_TX_OFFLOAD_VLAN_QINQ_F)]
@@ -41,25 +42,25 @@ cn9k_eth_set_tx_function(struct rte_eth_dev *eth_dev)
 {
 	struct cnxk_eth_dev *dev = cnxk_eth_pmd_priv(eth_dev);
 
-	const eth_tx_burst_t nix_eth_tx_burst[2][2][2][2][2] = {
-#define T(name, f4, f3, f2, f1, f0, sz, flags)				       \
-	[f4][f3][f2][f1][f0] = cn9k_nix_xmit_pkts_##name,
+	const eth_tx_burst_t nix_eth_tx_burst[2][2][2][2][2][2] = {
+#define T(name, f5, f4, f3, f2, f1, f0, sz, flags)			       \
+	[f5][f4][f3][f2][f1][f0] = cn9k_nix_xmit_pkts_##name,
 
 		NIX_TX_FASTPATH_MODES
 #undef T
 	};
 
-	const eth_tx_burst_t nix_eth_tx_burst_mseg[2][2][2][2][2] = {
-#define T(name, f4, f3, f2, f1, f0, sz, flags)				       \
-	[f4][f3][f2][f1][f0] = cn9k_nix_xmit_pkts_mseg_##name,
+	const eth_tx_burst_t nix_eth_tx_burst_mseg[2][2][2][2][2][2] = {
+#define T(name, f5, f4, f3, f2, f1, f0, sz, flags)			       \
+	[f5][f4][f3][f2][f1][f0] = cn9k_nix_xmit_pkts_mseg_##name,
 
 		NIX_TX_FASTPATH_MODES
 #undef T
 	};
 
-	const eth_tx_burst_t nix_eth_tx_vec_burst[2][2][2][2][2] = {
-#define T(name, f4, f3, f2, f1, f0, sz, flags)				       \
-	[f4][f3][f2][f1][f0] = cn9k_nix_xmit_pkts_vec_##name,
+	const eth_tx_burst_t nix_eth_tx_vec_burst[2][2][2][2][2][2] = {
+#define T(name, f5, f4, f3, f2, f1, f0, sz, flags)			       \
+	[f5][f4][f3][f2][f1][f0] = cn9k_nix_xmit_pkts_vec_##name,
 
 		NIX_TX_FASTPATH_MODES
 #undef T
@@ -67,7 +68,8 @@ cn9k_eth_set_tx_function(struct rte_eth_dev *eth_dev)
 
 	if (dev->scalar_ena ||
 	    (dev->tx_offload_flags &
-	     (NIX_TX_OFFLOAD_VLAN_QINQ_F | NIX_TX_OFFLOAD_TSO_F)))
+	     (NIX_TX_OFFLOAD_VLAN_QINQ_F | NIX_TX_OFFLOAD_TSTAMP_F |
+	      NIX_TX_OFFLOAD_TSO_F)))
 		pick_tx_func(eth_dev, nix_eth_tx_burst);
 	else
 		pick_tx_func(eth_dev, nix_eth_tx_vec_burst);
diff --git a/drivers/net/cnxk/cn9k_tx.h b/drivers/net/cnxk/cn9k_tx.h
index 7b0d536..1899d66 100644
--- a/drivers/net/cnxk/cn9k_tx.h
+++ b/drivers/net/cnxk/cn9k_tx.h
@@ -12,6 +12,7 @@
 #define NIX_TX_OFFLOAD_VLAN_QINQ_F    BIT(2)
 #define NIX_TX_OFFLOAD_MBUF_NOFF_F    BIT(3)
 #define NIX_TX_OFFLOAD_TSO_F	      BIT(4)
+#define NIX_TX_OFFLOAD_TSTAMP_F	      BIT(5)
 
 /* Flags to control xmit_prepare function.
  * Defining it from backwards to denote its been
@@ -24,7 +25,8 @@
 	 NIX_TX_OFFLOAD_VLAN_QINQ_F | NIX_TX_OFFLOAD_TSO_F)
 
 #define NIX_TX_NEED_EXT_HDR                                                    \
-	(NIX_TX_OFFLOAD_VLAN_QINQ_F | NIX_TX_OFFLOAD_TSO_F)
+	(NIX_TX_OFFLOAD_VLAN_QINQ_F | NIX_TX_OFFLOAD_TSTAMP_F |                \
+	 NIX_TX_OFFLOAD_TSO_F)
 
 #define NIX_XMIT_FC_OR_RETURN(txq, pkts)                                       \
 	do {                                                                   \
@@ -46,8 +48,12 @@
 static __rte_always_inline int
 cn9k_nix_tx_ext_subs(const uint16_t flags)
 {
-	return (flags &
-		(NIX_TX_OFFLOAD_VLAN_QINQ_F | NIX_TX_OFFLOAD_TSO_F)) ? 1 : 0;
+	return (flags & NIX_TX_OFFLOAD_TSTAMP_F)
+		       ? 2
+		       : ((flags &
+			   (NIX_TX_OFFLOAD_VLAN_QINQ_F | NIX_TX_OFFLOAD_TSO_F))
+				  ? 1
+				  : 0);
 }
 
 static __rte_always_inline void
@@ -283,6 +289,41 @@ cn9k_nix_xmit_prepare(struct rte_mbuf *m, uint64_t *cmd, const uint16_t flags,
 }
 
 static __rte_always_inline void
+cn9k_nix_xmit_prepare_tstamp(uint64_t *cmd, const uint64_t *send_mem_desc,
+			     const uint64_t ol_flags, const uint16_t no_segdw,
+			     const uint16_t flags)
+{
+	if (flags & NIX_TX_OFFLOAD_TSTAMP_F) {
+		struct nix_send_mem_s *send_mem;
+		uint16_t off = (no_segdw - 1) << 1;
+		const uint8_t is_ol_tstamp = !(ol_flags & PKT_TX_IEEE1588_TMST);
+
+		send_mem = (struct nix_send_mem_s *)(cmd + off);
+		if (flags & NIX_TX_MULTI_SEG_F) {
+			/* Retrieving the default desc values */
+			cmd[off] = send_mem_desc[6];
+
+			/* Using compiler barier to avoid voilation of C
+			 * aliasing rules.
+			 */
+			rte_compiler_barrier();
+		}
+
+		/* Packets for which PKT_TX_IEEE1588_TMST is not set, tx tstamp
+		 * should not be recorded, hence changing the alg type to
+		 * NIX_SENDMEMALG_SET and also changing send mem addr field to
+		 * next 8 bytes as it corrpt the actual tx tstamp registered
+		 * address.
+		 */
+		send_mem->w0.cn9k.alg =
+			NIX_SENDMEMALG_SETTSTMP - (is_ol_tstamp);
+
+		send_mem->addr = (rte_iova_t)((uint64_t *)send_mem_desc[7] +
+					      (is_ol_tstamp));
+	}
+}
+
+static __rte_always_inline void
 cn9k_nix_xmit_one(uint64_t *cmd, void *lmt_addr, const rte_iova_t io_addr,
 		  const uint32_t flags)
 {
@@ -380,7 +421,7 @@ cn9k_nix_prepare_mseg(struct rte_mbuf *m, uint64_t *cmd, const uint16_t flags)
 	/* Roundup extra dwords to multiple of 2 */
 	segdw = (segdw >> 1) + (segdw & 0x1);
 	/* Default dwords */
-	segdw += (off >> 1) + 1;
+	segdw += (off >> 1) + 1 + !!(flags & NIX_TX_OFFLOAD_TSTAMP_F);
 	send_hdr->w0.sizem1 = segdw - 1;
 
 	return segdw;
@@ -447,6 +488,8 @@ cn9k_nix_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t pkts,
 
 	for (i = 0; i < pkts; i++) {
 		cn9k_nix_xmit_prepare(tx_pkts[i], cmd, flags, lso_tun_fmt);
+		cn9k_nix_xmit_prepare_tstamp(cmd, &txq->cmd[0],
+					     tx_pkts[i]->ol_flags, 4, flags);
 		cn9k_nix_xmit_one(cmd, lmt_addr, io_addr, flags);
 	}
 
@@ -488,6 +531,9 @@ cn9k_nix_xmit_pkts_mseg(void *tx_queue, struct rte_mbuf **tx_pkts,
 	for (i = 0; i < pkts; i++) {
 		cn9k_nix_xmit_prepare(tx_pkts[i], cmd, flags, lso_tun_fmt);
 		segdw = cn9k_nix_prepare_mseg(tx_pkts[i], cmd, flags);
+		cn9k_nix_xmit_prepare_tstamp(cmd, &txq->cmd[0],
+					     tx_pkts[i]->ol_flags, segdw,
+					     flags);
 		cn9k_nix_xmit_mseg_one(cmd, lmt_addr, io_addr, segdw);
 	}
 
@@ -1241,75 +1287,140 @@ cn9k_nix_xmit_pkts_vector(void *tx_queue, struct rte_mbuf **tx_pkts,
 #define VLAN_F	     NIX_TX_OFFLOAD_VLAN_QINQ_F
 #define NOFF_F	     NIX_TX_OFFLOAD_MBUF_NOFF_F
 #define TSO_F	     NIX_TX_OFFLOAD_TSO_F
+#define TSP_F	     NIX_TX_OFFLOAD_TSTAMP_F
 
-/* [TSO] [NOFF] [VLAN] [OL3OL4CSUM] [L3L4CSUM] */
-#define NIX_TX_FASTPATH_MODES						\
-T(no_offload,				0, 0, 0, 0, 0,	4,		\
-		NIX_TX_OFFLOAD_NONE)					\
-T(l3l4csum,				0, 0, 0, 0, 1,	4,		\
-		L3L4CSUM_F)						\
-T(ol3ol4csum,				0, 0, 0, 1, 0,	4,		\
-		OL3OL4CSUM_F)						\
-T(ol3ol4csum_l3l4csum,			0, 0, 0, 1, 1,	4,		\
-		OL3OL4CSUM_F | L3L4CSUM_F)				\
-T(vlan,					0, 0, 1, 0, 0,	6,		\
-		VLAN_F)							\
-T(vlan_l3l4csum,			0, 0, 1, 0, 1,	6,		\
-		VLAN_F | L3L4CSUM_F)					\
-T(vlan_ol3ol4csum,			0, 0, 1, 1, 0,	6,		\
-		VLAN_F | OL3OL4CSUM_F)					\
-T(vlan_ol3ol4csum_l3l4csum,		0, 0, 1, 1, 1,	6,		\
-		VLAN_F | OL3OL4CSUM_F |	L3L4CSUM_F)			\
-T(noff,					0, 1, 0, 0, 0,	4,		\
-		NOFF_F)							\
-T(noff_l3l4csum,			0, 1, 0, 0, 1,	4,		\
-		NOFF_F | L3L4CSUM_F)					\
-T(noff_ol3ol4csum,			0, 1, 0, 1, 0,	4,		\
-		NOFF_F | OL3OL4CSUM_F)					\
-T(noff_ol3ol4csum_l3l4csum,		0, 1, 0, 1, 1,	4,		\
-		NOFF_F | OL3OL4CSUM_F |	L3L4CSUM_F)			\
-T(noff_vlan,				0, 1, 1, 0, 0,	6,		\
-		NOFF_F | VLAN_F)					\
-T(noff_vlan_l3l4csum,			0, 1, 1, 0, 1,	6,		\
-		NOFF_F | VLAN_F | L3L4CSUM_F)				\
-T(noff_vlan_ol3ol4csum,			0, 1, 1, 1, 0,	6,		\
-		NOFF_F | VLAN_F | OL3OL4CSUM_F)				\
-T(noff_vlan_ol3ol4csum_l3l4csum,	0, 1, 1, 1, 1,	6,		\
-		NOFF_F | VLAN_F | OL3OL4CSUM_F | L3L4CSUM_F)		\
-T(tso,					1, 0, 0, 0, 0,	6,		\
-		TSO_F)							\
-T(tso_l3l4csum,				1, 0, 0, 0, 1,	6,		\
-		TSO_F | L3L4CSUM_F)					\
-T(tso_ol3ol4csum,			1, 0, 0, 1, 0,	6,		\
-		TSO_F | OL3OL4CSUM_F)					\
-T(tso_ol3ol4csum_l3l4csum,		1, 0, 0, 1, 1,	6,		\
-		TSO_F | OL3OL4CSUM_F | L3L4CSUM_F)			\
-T(tso_vlan,				1, 0, 1, 0, 0,	6,		\
-		TSO_F | VLAN_F)						\
-T(tso_vlan_l3l4csum,			1, 0, 1, 0, 1,	6,		\
-		TSO_F | VLAN_F | L3L4CSUM_F)				\
-T(tso_vlan_ol3ol4csum,			1, 0, 1, 1, 0,	6,		\
-		TSO_F | VLAN_F | OL3OL4CSUM_F)				\
-T(tso_vlan_ol3ol4csum_l3l4csum,		1, 0, 1, 1, 1,	6,		\
-		TSO_F | VLAN_F | OL3OL4CSUM_F |	L3L4CSUM_F)		\
-T(tso_noff,				1, 1, 0, 0, 0,	6,		\
-		TSO_F | NOFF_F)						\
-T(tso_noff_l3l4csum,			1, 1, 0, 0, 1,	6,		\
-		TSO_F | NOFF_F | L3L4CSUM_F)				\
-T(tso_noff_ol3ol4csum,			1, 1, 0, 1, 0,	6,		\
-		TSO_F | NOFF_F | OL3OL4CSUM_F)				\
-T(tso_noff_ol3ol4csum_l3l4csum,		1, 1, 0, 1, 1,	6,		\
-		TSO_F | NOFF_F | OL3OL4CSUM_F |	L3L4CSUM_F)		\
-T(tso_noff_vlan,			1, 1, 1, 0, 0,	6,		\
-		TSO_F | NOFF_F | VLAN_F)				\
-T(tso_noff_vlan_l3l4csum,		1, 1, 1, 0, 1,	6,		\
-		TSO_F | NOFF_F | VLAN_F | L3L4CSUM_F)			\
-T(tso_noff_vlan_ol3ol4csum,		1, 1, 1, 1, 0,	6,		\
-		TSO_F | NOFF_F | VLAN_F | OL3OL4CSUM_F)			\
-T(tso_noff_vlan_ol3ol4csum_l3l4csum,	1, 1, 1, 1, 1,	6,		\
-		TSO_F | NOFF_F | VLAN_F | OL3OL4CSUM_F | L3L4CSUM_F)
+/* [TSP] [TSO] [NOFF] [VLAN] [OL3OL4CSUM] [L3L4CSUM] */
+#define NIX_TX_FASTPATH_MODES						       \
+T(no_offload,				0, 0, 0, 0, 0, 0,	4,	       \
+		NIX_TX_OFFLOAD_NONE)					       \
+T(l3l4csum,				0, 0, 0, 0, 0, 1,	4,	       \
+		L3L4CSUM_F)						       \
+T(ol3ol4csum,				0, 0, 0, 0, 1, 0,	4,	       \
+		OL3OL4CSUM_F)						       \
+T(ol3ol4csum_l3l4csum,			0, 0, 0, 0, 1, 1,	4,	       \
+		OL3OL4CSUM_F | L3L4CSUM_F)				       \
+T(vlan,					0, 0, 0, 1, 0, 0,	6,	       \
+		VLAN_F)							       \
+T(vlan_l3l4csum,			0, 0, 0, 1, 0, 1,	6,	       \
+		VLAN_F | L3L4CSUM_F)					       \
+T(vlan_ol3ol4csum,			0, 0, 0, 1, 1, 0,	6,	       \
+		VLAN_F | OL3OL4CSUM_F)					       \
+T(vlan_ol3ol4csum_l3l4csum,		0, 0, 0, 1, 1, 1,	6,	       \
+		VLAN_F | OL3OL4CSUM_F |	L3L4CSUM_F)			       \
+T(noff,					0, 0, 1, 0, 0, 0,	4,	       \
+		NOFF_F)							       \
+T(noff_l3l4csum,			0, 0, 1, 0, 0, 1,	4,	       \
+		NOFF_F | L3L4CSUM_F)					       \
+T(noff_ol3ol4csum,			0, 0, 1, 0, 1, 0,	4,	       \
+		NOFF_F | OL3OL4CSUM_F)					       \
+T(noff_ol3ol4csum_l3l4csum,		0, 0, 1, 0, 1, 1,	4,	       \
+		NOFF_F | OL3OL4CSUM_F |	L3L4CSUM_F)			       \
+T(noff_vlan,				0, 0, 1, 1, 0, 0,	6,	       \
+		NOFF_F | VLAN_F)					       \
+T(noff_vlan_l3l4csum,			0, 0, 1, 1, 0, 1,	6,	       \
+		NOFF_F | VLAN_F | L3L4CSUM_F)				       \
+T(noff_vlan_ol3ol4csum,			0, 0, 1, 1, 1, 0,	6,	       \
+		NOFF_F | VLAN_F | OL3OL4CSUM_F)				       \
+T(noff_vlan_ol3ol4csum_l3l4csum,	0, 0, 1, 1, 1, 1,	6,	       \
+		NOFF_F | VLAN_F | OL3OL4CSUM_F | L3L4CSUM_F)		       \
+T(tso,					0, 1, 0, 0, 0, 0,	6,	       \
+		TSO_F)							       \
+T(tso_l3l4csum,				0, 1, 0, 0, 0, 1,	6,	       \
+		TSO_F | L3L4CSUM_F)					       \
+T(tso_ol3ol4csum,			0, 1, 0, 0, 1, 0,	6,	       \
+		TSO_F | OL3OL4CSUM_F)					       \
+T(tso_ol3ol4csum_l3l4csum,		0, 1, 0, 0, 1, 1,	6,	       \
+		TSO_F | OL3OL4CSUM_F | L3L4CSUM_F)			       \
+T(tso_vlan,				0, 1, 0, 1, 0, 0,	6,	       \
+		TSO_F | VLAN_F)						       \
+T(tso_vlan_l3l4csum,			0, 1, 0, 1, 0, 1,	6,	       \
+		TSO_F | VLAN_F | L3L4CSUM_F)				       \
+T(tso_vlan_ol3ol4csum,			0, 1, 0, 1, 1, 0,	6,	       \
+		TSO_F | VLAN_F | OL3OL4CSUM_F)				       \
+T(tso_vlan_ol3ol4csum_l3l4csum,		0, 1, 0, 1, 1, 1,	6,	       \
+		TSO_F | VLAN_F | OL3OL4CSUM_F |	L3L4CSUM_F)		       \
+T(tso_noff,				0, 1, 1, 0, 0, 0,	6,	       \
+		TSO_F | NOFF_F)						       \
+T(tso_noff_l3l4csum,			0, 1, 1, 0, 0, 1,	6,	       \
+		TSO_F | NOFF_F | L3L4CSUM_F)				       \
+T(tso_noff_ol3ol4csum,			0, 1, 1, 0, 1, 0,	6,	       \
+		TSO_F | NOFF_F | OL3OL4CSUM_F)				       \
+T(tso_noff_ol3ol4csum_l3l4csum,		0, 1, 1, 0, 1, 1,	6,	       \
+		TSO_F | NOFF_F | OL3OL4CSUM_F |	L3L4CSUM_F)		       \
+T(tso_noff_vlan,			0, 1, 1, 1, 0, 0,	6,	       \
+		TSO_F | NOFF_F | VLAN_F)				       \
+T(tso_noff_vlan_l3l4csum,		0, 1, 1, 1, 0, 1,	6,	       \
+		TSO_F | NOFF_F | VLAN_F | L3L4CSUM_F)			       \
+T(tso_noff_vlan_ol3ol4csum,		0, 1, 1, 1, 1, 0,	6,	       \
+		TSO_F | NOFF_F | VLAN_F | OL3OL4CSUM_F)			       \
+T(tso_noff_vlan_ol3ol4csum_l3l4csum,	0, 1, 1, 1, 1, 1,	6,	       \
+		TSO_F | NOFF_F | VLAN_F | OL3OL4CSUM_F | L3L4CSUM_F)	       \
+T(ts,					1, 0, 0, 0, 0, 0,	8,	       \
+		TSP_F)							       \
+T(ts_l3l4csum,				1, 0, 0, 0, 0, 1,	8,	       \
+		TSP_F | L3L4CSUM_F)					       \
+T(ts_ol3ol4csum,			1, 0, 0, 0, 1, 0,	8,	       \
+		TSP_F | OL3OL4CSUM_F)					       \
+T(ts_ol3ol4csum_l3l4csum,		1, 0, 0, 0, 1, 1,	8,	       \
+		TSP_F | OL3OL4CSUM_F | L3L4CSUM_F)			       \
+T(ts_vlan,				1, 0, 0, 1, 0, 0,	8,	       \
+		TSP_F | VLAN_F)						       \
+T(ts_vlan_l3l4csum,			1, 0, 0, 1, 0, 1,	8,	       \
+		TSP_F | VLAN_F | L3L4CSUM_F)				       \
+T(ts_vlan_ol3ol4csum,			1, 0, 0, 1, 1, 0,	8,	       \
+		TSP_F | VLAN_F | OL3OL4CSUM_F)				       \
+T(ts_vlan_ol3ol4csum_l3l4csum,		1, 0, 0, 1, 1, 1,	8,	       \
+		TSP_F | VLAN_F | OL3OL4CSUM_F |	L3L4CSUM_F)		       \
+T(ts_noff,				1, 0, 1, 0, 0, 0,	8,	       \
+		TSP_F | NOFF_F)						       \
+T(ts_noff_l3l4csum,			1, 0, 1, 0, 0, 1,	8,	       \
+		TSP_F | NOFF_F | L3L4CSUM_F)				       \
+T(ts_noff_ol3ol4csum,			1, 0, 1, 0, 1, 0,	8,	       \
+		TSP_F | NOFF_F | OL3OL4CSUM_F)				       \
+T(ts_noff_ol3ol4csum_l3l4csum,		1, 0, 1, 0, 1, 1,	8,	       \
+		TSP_F | NOFF_F | OL3OL4CSUM_F |	L3L4CSUM_F)		       \
+T(ts_noff_vlan,				1, 0, 1, 1, 0, 0,	8,	       \
+		TSP_F | NOFF_F | VLAN_F)				       \
+T(ts_noff_vlan_l3l4csum,		1, 0, 1, 1, 0, 1,	8,	       \
+		TSP_F | NOFF_F | VLAN_F | L3L4CSUM_F)			       \
+T(ts_noff_vlan_ol3ol4csum,		1, 0, 1, 1, 1, 0,	8,	       \
+		TSP_F | NOFF_F | VLAN_F | OL3OL4CSUM_F)			       \
+T(ts_noff_vlan_ol3ol4csum_l3l4csum,	1, 0, 1, 1, 1, 1,	8,	       \
+		TSP_F | NOFF_F | VLAN_F | OL3OL4CSUM_F | L3L4CSUM_F)	       \
+T(ts_tso,				1, 1, 0, 0, 0, 0,	8,	       \
+		TSP_F | TSO_F)						       \
+T(ts_tso_l3l4csum,			1, 1, 0, 0, 0, 1,	8,	       \
+		TSP_F | TSO_F | L3L4CSUM_F)				       \
+T(ts_tso_ol3ol4csum,			1, 1, 0, 0, 1, 0,	8,	       \
+		TSP_F | TSO_F | OL3OL4CSUM_F)				       \
+T(ts_tso_ol3ol4csum_l3l4csum,		1, 1, 0, 0, 1, 1,	8,	       \
+		TSP_F | TSO_F | OL3OL4CSUM_F | L3L4CSUM_F)		       \
+T(ts_tso_vlan,				1, 1, 0, 1, 0, 0,	8,	       \
+		TSP_F | TSO_F | VLAN_F)					       \
+T(ts_tso_vlan_l3l4csum,			1, 1, 0, 1, 0, 1,	8,	       \
+		TSP_F | TSO_F | VLAN_F | L3L4CSUM_F)			       \
+T(ts_tso_vlan_ol3ol4csum,		1, 1, 0, 1, 1, 0,	8,	       \
+		TSP_F | TSO_F | VLAN_F | OL3OL4CSUM_F)			       \
+T(ts_tso_vlan_ol3ol4csum_l3l4csum,	1, 1, 0, 1, 1, 1,	8,	       \
+		TSP_F | TSO_F | VLAN_F | OL3OL4CSUM_F |	L3L4CSUM_F)	       \
+T(ts_tso_noff,				1, 1, 1, 0, 0, 0,	8,	       \
+		TSP_F | TSO_F | NOFF_F)					       \
+T(ts_tso_noff_l3l4csum,			1, 1, 1, 0, 0, 1,	8,	       \
+		TSP_F | TSO_F | NOFF_F | L3L4CSUM_F)			       \
+T(ts_tso_noff_ol3ol4csum,		1, 1, 1, 0, 1, 0,	8,	       \
+		TSP_F | TSO_F | NOFF_F | OL3OL4CSUM_F)			       \
+T(ts_tso_noff_ol3ol4csum_l3l4csum,	1, 1, 1, 0, 1, 1,	8,	       \
+		TSP_F | TSO_F | NOFF_F | OL3OL4CSUM_F |	L3L4CSUM_F)	       \
+T(ts_tso_noff_vlan,			1, 1, 1, 1, 0, 0,	8,	       \
+		TSP_F | TSO_F | NOFF_F | VLAN_F)			       \
+T(ts_tso_noff_vlan_l3l4csum,		1, 1, 1, 1, 0, 1,	8,	       \
+		TSP_F | TSO_F | NOFF_F | VLAN_F | L3L4CSUM_F)		       \
+T(ts_tso_noff_vlan_ol3ol4csum,		1, 1, 1, 1, 1, 0,	8,	       \
+		TSP_F | TSO_F | NOFF_F | VLAN_F | OL3OL4CSUM_F)		       \
+T(ts_tso_noff_vlan_ol3ol4csum_l3l4csum,	1, 1, 1, 1, 1, 1,	8,	       \
+		TSP_F | TSO_F | NOFF_F | VLAN_F | OL3OL4CSUM_F | L3L4CSUM_F)
 
-#define T(name, f4, f3, f2, f1, f0, sz, flags)                                 \
+#define T(name, f5, f4, f3, f2, f1, f0, sz, flags)			       \
 	uint16_t __rte_noinline __rte_hot cn9k_nix_xmit_pkts_##name(           \
 		void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t pkts);     \
 									       \
diff --git a/drivers/net/cnxk/cn9k_tx_mseg.c b/drivers/net/cnxk/cn9k_tx_mseg.c
index 65c5f36..f3c427c 100644
--- a/drivers/net/cnxk/cn9k_tx_mseg.c
+++ b/drivers/net/cnxk/cn9k_tx_mseg.c
@@ -5,7 +5,7 @@
 #include "cn9k_ethdev.h"
 #include "cn9k_tx.h"
 
-#define T(name, f4, f3, f2, f1, f0, sz, flags)				       \
+#define T(name, f5, f4, f3, f2, f1, f0, sz, flags)			       \
 	uint16_t __rte_noinline __rte_hot				       \
 		cn9k_nix_xmit_pkts_mseg_##name(void *tx_queue,                 \
 					       struct rte_mbuf **tx_pkts,      \
diff --git a/drivers/net/cnxk/cn9k_tx_vec.c b/drivers/net/cnxk/cn9k_tx_vec.c
index 21ffc2c..a6e7c9e 100644
--- a/drivers/net/cnxk/cn9k_tx_vec.c
+++ b/drivers/net/cnxk/cn9k_tx_vec.c
@@ -5,7 +5,7 @@
 #include "cn9k_ethdev.h"
 #include "cn9k_tx.h"
 
-#define T(name, f4, f3, f2, f1, f0, sz, flags)				       \
+#define T(name, f5, f4, f3, f2, f1, f0, sz, flags)			       \
 	uint16_t __rte_noinline __rte_hot				       \
 		cn9k_nix_xmit_pkts_vec_##name(void *tx_queue,                  \
 					      struct rte_mbuf **tx_pkts,       \
@@ -15,6 +15,7 @@
 									       \
 		/* VLAN, TSTMP, TSO is not supported by vec */                 \
 		if ((flags) & NIX_TX_OFFLOAD_VLAN_QINQ_F ||		       \
+		    (flags) & NIX_TX_OFFLOAD_TSTAMP_F ||		       \
 		    (flags) & NIX_TX_OFFLOAD_TSO_F)			       \
 			return 0;                                              \
 		return cn9k_nix_xmit_pkts_vector(tx_queue, tx_pkts, pkts, cmd, \
diff --git a/drivers/net/cnxk/cnxk_ethdev.c b/drivers/net/cnxk/cnxk_ethdev.c
index 094f1cb..71d567a 100644
--- a/drivers/net/cnxk/cnxk_ethdev.c
+++ b/drivers/net/cnxk/cnxk_ethdev.c
@@ -150,7 +150,8 @@ cnxk_nix_rxq_mbuf_setup(struct cnxk_eth_dev *dev)
 				 offsetof(struct rte_mbuf, data_off) !=
 			 6);
 	mb_def.nb_segs = 1;
-	mb_def.data_off = RTE_PKTMBUF_HEADROOM;
+	mb_def.data_off = RTE_PKTMBUF_HEADROOM +
+			  (dev->ptp_en * CNXK_NIX_TIMESYNC_RX_OFFSET);
 	mb_def.port = port_id;
 	rte_mbuf_refcnt_set(&mb_def, 1);
 
@@ -356,6 +357,18 @@ cnxk_nix_rx_queue_setup(struct rte_eth_dev *eth_dev, uint16_t qid,
 	eth_dev->data->rx_queues[qid] = rxq_sp + 1;
 	eth_dev->data->rx_queue_state[qid] = RTE_ETH_QUEUE_STATE_STOPPED;
 
+	/* Calculating delta and freq mult between PTP HI clock and tsc.
+	 * These are needed in deriving raw clock value from tsc counter.
+	 * read_clock eth op returns raw clock value.
+	 */
+	if ((dev->rx_offloads & DEV_RX_OFFLOAD_TIMESTAMP) || dev->ptp_en) {
+		rc = cnxk_nix_tsc_convert(dev);
+		if (rc) {
+			plt_err("Failed to calculate delta and freq mult");
+			goto rq_fini;
+		}
+	}
+
 	return 0;
 rq_fini:
 	rc |= roc_nix_rq_fini(rq);
@@ -1112,7 +1125,7 @@ cnxk_nix_dev_start(struct rte_eth_dev *eth_dev)
 	struct cnxk_eth_dev *dev = cnxk_eth_pmd_priv(eth_dev);
 	int rc, i;
 
-	if (eth_dev->data->nb_rx_queues != 0) {
+	if (eth_dev->data->nb_rx_queues != 0 && !dev->ptp_en) {
 		rc = nix_recalc_mtu(eth_dev);
 		if (rc)
 			return rc;
@@ -1157,6 +1170,25 @@ cnxk_nix_dev_start(struct rte_eth_dev *eth_dev)
 		}
 	}
 
+	/* Enable PTP if it is requested by the user or already
+	 * enabled on PF owning this VF
+	 */
+	memset(&dev->tstamp, 0, sizeof(struct cnxk_timesync_info));
+	if ((dev->rx_offloads & DEV_RX_OFFLOAD_TIMESTAMP) || dev->ptp_en)
+		cnxk_eth_dev_ops.timesync_enable(eth_dev);
+	else
+		cnxk_eth_dev_ops.timesync_disable(eth_dev);
+
+	if (dev->rx_offloads & DEV_RX_OFFLOAD_TIMESTAMP) {
+		rc = rte_mbuf_dyn_rx_timestamp_register
+			(&dev->tstamp.tstamp_dynfield_offset,
+			 &dev->tstamp.rx_tstamp_dynflag);
+		if (rc != 0) {
+			plt_err("Failed to register Rx timestamp field/flag");
+			goto rx_disable;
+		}
+	}
+
 	cnxk_nix_toggle_flag_link_cfg(dev, false);
 
 	return 0;
diff --git a/drivers/net/cnxk/cnxk_ethdev.h b/drivers/net/cnxk/cnxk_ethdev.h
index 1c41dcb..de6d533 100644
--- a/drivers/net/cnxk/cnxk_ethdev.h
+++ b/drivers/net/cnxk/cnxk_ethdev.h
@@ -13,6 +13,7 @@
 #include <rte_mbuf.h>
 #include <rte_mbuf_pool_ops.h>
 #include <rte_mempool.h>
+#include <rte_time.h>
 
 #include "roc_api.h"
 
@@ -75,7 +76,7 @@
 	(DEV_RX_OFFLOAD_CHECKSUM | DEV_RX_OFFLOAD_SCTP_CKSUM |                 \
 	 DEV_RX_OFFLOAD_OUTER_IPV4_CKSUM | DEV_RX_OFFLOAD_SCATTER |            \
 	 DEV_RX_OFFLOAD_JUMBO_FRAME | DEV_RX_OFFLOAD_OUTER_UDP_CKSUM |         \
-	 DEV_RX_OFFLOAD_RSS_HASH)
+	 DEV_RX_OFFLOAD_RSS_HASH | DEV_RX_OFFLOAD_TIMESTAMP)
 
 #define RSS_IPV4_ENABLE                                                        \
 	(ETH_RSS_IPV4 | ETH_RSS_FRAG_IPV4 | ETH_RSS_NONFRAG_IPV4_UDP |         \
@@ -100,7 +101,10 @@
 /* Default mark value used when none is provided. */
 #define CNXK_FLOW_ACTION_FLAG_DEFAULT 0xffff
 
+/* Default cycle counter mask */
+#define CNXK_CYCLECOUNTER_MASK     0xffffffffffffffffULL
 #define CNXK_NIX_TIMESYNC_RX_OFFSET 8
+
 #define PTYPE_NON_TUNNEL_WIDTH	  16
 #define PTYPE_TUNNEL_WIDTH	  12
 #define PTYPE_NON_TUNNEL_ARRAY_SZ BIT(PTYPE_NON_TUNNEL_WIDTH)
@@ -130,6 +134,16 @@ struct cnxk_eth_qconf {
 	uint8_t valid;
 };
 
+struct cnxk_timesync_info {
+	uint64_t rx_tstamp_dynflag;
+	rte_iova_t tx_tstamp_iova;
+	uint64_t *tx_tstamp;
+	uint64_t rx_tstamp;
+	int tstamp_dynfield_offset;
+	uint8_t tx_ready;
+	uint8_t rx_ready;
+} __plt_cache_aligned;
+
 struct cnxk_eth_dev {
 	/* ROC NIX */
 	struct roc_nix nix;
@@ -188,6 +202,14 @@ struct cnxk_eth_dev {
 	/* Flow control configuration */
 	struct cnxk_fc_cfg fc_cfg;
 
+	/* PTP Counters */
+	struct cnxk_timesync_info tstamp;
+	struct rte_timecounter systime_tc;
+	struct rte_timecounter rx_tstamp_tc;
+	struct rte_timecounter tx_tstamp_tc;
+	double clk_freq_mult;
+	uint64_t clk_delta;
+
 	/* Rx burst for cleanup(Only Primary) */
 	eth_rx_burst_t rx_pkt_burst_no_offload;
 
@@ -288,6 +310,9 @@ int cnxk_nix_rx_queue_setup(struct rte_eth_dev *eth_dev, uint16_t qid,
 int cnxk_nix_tx_queue_start(struct rte_eth_dev *eth_dev, uint16_t qid);
 int cnxk_nix_tx_queue_stop(struct rte_eth_dev *eth_dev, uint16_t qid);
 int cnxk_nix_dev_start(struct rte_eth_dev *eth_dev);
+int cnxk_nix_timesync_enable(struct rte_eth_dev *eth_dev);
+int cnxk_nix_timesync_disable(struct rte_eth_dev *eth_dev);
+int cnxk_nix_tsc_convert(struct cnxk_eth_dev *dev);
 
 uint64_t cnxk_nix_rxq_mbuf_setup(struct cnxk_eth_dev *dev);
 
@@ -404,4 +429,41 @@ cnxk_nix_prefree_seg(struct rte_mbuf *m)
 	return 1;
 }
 
+static inline rte_mbuf_timestamp_t *
+cnxk_nix_timestamp_dynfield(struct rte_mbuf *mbuf,
+			    struct cnxk_timesync_info *info)
+{
+	return RTE_MBUF_DYNFIELD(mbuf, info->tstamp_dynfield_offset,
+				 rte_mbuf_timestamp_t *);
+}
+
+static __rte_always_inline void
+cnxk_nix_mbuf_to_tstamp(struct rte_mbuf *mbuf,
+			struct cnxk_timesync_info *tstamp, bool ts_enable,
+			uint64_t *tstamp_ptr)
+{
+	if (ts_enable &&
+	    (mbuf->data_off ==
+	     RTE_PKTMBUF_HEADROOM + CNXK_NIX_TIMESYNC_RX_OFFSET)) {
+		mbuf->pkt_len -= CNXK_NIX_TIMESYNC_RX_OFFSET;
+
+		/* Reading the rx timestamp inserted by CGX, viz at
+		 * starting of the packet data.
+		 */
+		*cnxk_nix_timestamp_dynfield(mbuf, tstamp) =
+			rte_be_to_cpu_64(*tstamp_ptr);
+		/* PKT_RX_IEEE1588_TMST flag needs to be set only in case
+		 * PTP packets are received.
+		 */
+		if (mbuf->packet_type == RTE_PTYPE_L2_ETHER_TIMESYNC) {
+			tstamp->rx_tstamp =
+				*cnxk_nix_timestamp_dynfield(mbuf, tstamp);
+			tstamp->rx_ready = 1;
+			mbuf->ol_flags |= PKT_RX_IEEE1588_PTP |
+					  PKT_RX_IEEE1588_TMST |
+					  tstamp->rx_tstamp_dynflag;
+		}
+	}
+}
+
 #endif /* __CNXK_ETHDEV_H__ */
diff --git a/drivers/net/cnxk/cnxk_ptp.c b/drivers/net/cnxk/cnxk_ptp.c
new file mode 100644
index 0000000..fc317965
--- /dev/null
+++ b/drivers/net/cnxk/cnxk_ptp.c
@@ -0,0 +1,169 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(C) 2021 Marvell.
+ */
+
+#include "cnxk_ethdev.h"
+
+/* This function calculates two parameters "clk_freq_mult" and
+ * "clk_delta" which is useful in deriving PTP HI clock from
+ * timestamp counter (tsc) value.
+ */
+int
+cnxk_nix_tsc_convert(struct cnxk_eth_dev *dev)
+{
+	uint64_t ticks_base = 0, ticks = 0, tsc = 0, t_freq;
+	struct roc_nix *nix = &dev->nix;
+	int rc, val;
+
+	/* Calculating the frequency at which PTP HI clock is running */
+	rc = roc_nix_ptp_clock_read(nix, &ticks_base, &tsc, false);
+	if (rc) {
+		plt_err("Failed to read the raw clock value: %d", rc);
+		goto fail;
+	}
+
+	rte_delay_ms(100);
+
+	rc = roc_nix_ptp_clock_read(nix, &ticks, &tsc, false);
+	if (rc) {
+		plt_err("Failed to read the raw clock value: %d", rc);
+		goto fail;
+	}
+
+	t_freq = (ticks - ticks_base) * 10;
+
+	/* Calculating the freq multiplier viz the ratio between the
+	 * frequency at which PTP HI clock works and tsc clock runs
+	 */
+	dev->clk_freq_mult =
+		(double)pow(10, floor(log10(t_freq))) / rte_get_timer_hz();
+
+	val = false;
+#ifdef RTE_ARM_EAL_RDTSC_USE_PMU
+	val = true;
+#endif
+	rc = roc_nix_ptp_clock_read(nix, &ticks, &tsc, val);
+	if (rc) {
+		plt_err("Failed to read the raw clock value: %d", rc);
+		goto fail;
+	}
+
+	/* Calculating delta between PTP HI clock and tsc */
+	dev->clk_delta = ((uint64_t)(ticks / dev->clk_freq_mult) - tsc);
+
+fail:
+	return rc;
+}
+
+int
+cnxk_nix_timesync_enable(struct rte_eth_dev *eth_dev)
+{
+	struct cnxk_eth_dev *dev = cnxk_eth_pmd_priv(eth_dev);
+	struct cnxk_timesync_info *tstamp = &dev->tstamp;
+	struct roc_nix *nix = &dev->nix;
+	const struct rte_memzone *ts;
+	int rc = 0;
+
+	/* If we are VF/SDP/LBK, ptp cannot not be enabled */
+	if (roc_nix_is_vf_or_sdp(nix) || roc_nix_is_lbk(nix)) {
+		plt_err("PTP cannot be enabled for VF/SDP/LBK");
+		return -EINVAL;
+	}
+
+	if (dev->ptp_en)
+		return rc;
+
+	if (dev->ptype_disable) {
+		plt_err("Ptype offload is disabled, it should be enabled");
+		return -EINVAL;
+	}
+
+	if (dev->npc.switch_header_type == ROC_PRIV_FLAGS_HIGIG) {
+		plt_err("Both PTP and switch header cannot be enabled");
+		return -EINVAL;
+	}
+
+	/* Allocating a iova address for tx tstamp */
+	ts = rte_eth_dma_zone_reserve(eth_dev, "cnxk_ts", 0, 128, 128, 0);
+	if (ts == NULL) {
+		plt_err("Failed to allocate mem for tx tstamp addr");
+		return -ENOMEM;
+	}
+
+	tstamp->tx_tstamp_iova = ts->iova;
+	tstamp->tx_tstamp = ts->addr;
+
+	rc = rte_mbuf_dyn_rx_timestamp_register(&tstamp->tstamp_dynfield_offset,
+						&tstamp->rx_tstamp_dynflag);
+	if (rc) {
+		plt_err("Failed to register Rx timestamp field/flag");
+		goto error;
+	}
+
+	/* System time should be already on by default */
+	memset(&dev->systime_tc, 0, sizeof(struct rte_timecounter));
+	memset(&dev->rx_tstamp_tc, 0, sizeof(struct rte_timecounter));
+	memset(&dev->tx_tstamp_tc, 0, sizeof(struct rte_timecounter));
+
+	dev->systime_tc.cc_mask = CNXK_CYCLECOUNTER_MASK;
+	dev->rx_tstamp_tc.cc_mask = CNXK_CYCLECOUNTER_MASK;
+	dev->tx_tstamp_tc.cc_mask = CNXK_CYCLECOUNTER_MASK;
+
+	dev->rx_offloads |= DEV_RX_OFFLOAD_TIMESTAMP;
+
+	rc = roc_nix_ptp_rx_ena_dis(nix, true);
+	if (!rc) {
+		rc = roc_nix_ptp_tx_ena_dis(nix, true);
+		if (rc) {
+			roc_nix_ptp_rx_ena_dis(nix, false);
+			goto error;
+		}
+	}
+
+	rc = nix_recalc_mtu(eth_dev);
+	if (rc) {
+		plt_err("Failed to set MTU size for ptp");
+		goto error;
+	}
+
+	return rc;
+
+error:
+	rte_eth_dma_zone_free(eth_dev, "cnxk_ts", 0);
+	dev->tstamp.tx_tstamp_iova = 0;
+	dev->tstamp.tx_tstamp = NULL;
+	return rc;
+}
+
+int
+cnxk_nix_timesync_disable(struct rte_eth_dev *eth_dev)
+{
+	struct cnxk_eth_dev *dev = cnxk_eth_pmd_priv(eth_dev);
+	uint64_t rx_offloads = DEV_RX_OFFLOAD_TIMESTAMP;
+	struct roc_nix *nix = &dev->nix;
+	int rc = 0;
+
+	/* If we are VF/SDP/LBK, ptp cannot not be disabled */
+	if (roc_nix_is_vf_or_sdp(nix) || roc_nix_is_lbk(nix))
+		return -EINVAL;
+
+	if (!dev->ptp_en)
+		return rc;
+
+	dev->rx_offloads &= ~rx_offloads;
+
+	rc = roc_nix_ptp_rx_ena_dis(nix, false);
+	if (!rc) {
+		rc = roc_nix_ptp_tx_ena_dis(nix, false);
+		if (rc) {
+			roc_nix_ptp_rx_ena_dis(nix, true);
+			return rc;
+		}
+	}
+
+	rc = nix_recalc_mtu(eth_dev);
+	if (rc)
+		plt_err("Failed to set MTU size for ptp");
+
+	return rc;
+}
diff --git a/drivers/net/cnxk/meson.build b/drivers/net/cnxk/meson.build
index df953fd..2071d0d 100644
--- a/drivers/net/cnxk/meson.build
+++ b/drivers/net/cnxk/meson.build
@@ -13,6 +13,7 @@ sources = files('cnxk_ethdev.c',
 		'cnxk_ethdev_devargs.c',
 		'cnxk_link.c',
 		'cnxk_lookup.c',
+		'cnxk_ptp.c',
 		'cnxk_rte_flow.c',
 		'cnxk_stats.c')
 
-- 
2.8.4