[PATCH v1 0/6] Add TxPP Support for E830

[PATCH v1 0/6] Add TxPP Support for E830

[Soumyadeep Hore]

Added TxPP support for E830 adapters.

Paul Greenwalt (1):
  net/intel: update E830 Tx Time Queue Context Structure

Soumyadeep Hore (5):
  net/intel: add read clock feature in ICE
  net/intel: add TxPP Support for E830
  net/intel: add AVX2 Support for TxPP
  net/intel: add AVX512 Support for TxPP
  doc: announce TxPP support for E830 adapters

 doc/guides/nics/ice.rst                     |  16 ++
 drivers/net/intel/common/tx.h               |  14 ++
 drivers/net/intel/ice/base/ice_common.c     |  22 +-
 drivers/net/intel/ice/base/ice_lan_tx_rx.h  |   4 +
 drivers/net/intel/ice/ice_ethdev.c          |  16 +-
 drivers/net/intel/ice/ice_ethdev.h          |  12 +
 drivers/net/intel/ice/ice_rxtx.c            | 233 +++++++++++++++++++-
 drivers/net/intel/ice/ice_rxtx.h            |   9 +
 drivers/net/intel/ice/ice_rxtx_vec_avx2.c   | 134 ++++++++++-
 drivers/net/intel/ice/ice_rxtx_vec_avx512.c | 205 ++++++++++++++++-
 drivers/net/intel/ice/ice_rxtx_vec_common.h |  17 ++
 11 files changed, 657 insertions(+), 25 deletions(-)

-- 
2.43.0

[PATCH v1 1/6] net/intel: update E830 Tx Time Queue Context Structure

[Soumyadeep Hore]

From: Paul Greenwalt <paul.greenwalt@intel.com>

Updated the Tx Time Queue Context Structure to align with HAS.

Signed-off-by: Soumyadeep Hore <soumyadeep.hore@intel.com>
Signed-off-by: Paul Greenwalt <paul.greenwalt@intel.com>
---
 drivers/net/intel/ice/base/ice_common.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/net/intel/ice/base/ice_common.c b/drivers/net/intel/ice/base/ice_common.c
index fce9b070cf..d6be991fe3 100644
--- a/drivers/net/intel/ice/base/ice_common.c
+++ b/drivers/net/intel/ice/base/ice_common.c
@@ -1671,17 +1671,17 @@ const struct ice_ctx_ele ice_txtime_ctx_info[] = {
 	ICE_CTX_STORE(ice_txtime_ctx, cpuid,			8,	82),
 	ICE_CTX_STORE(ice_txtime_ctx, tphrd_desc,		1,	90),
 	ICE_CTX_STORE(ice_txtime_ctx, qlen,			13,	91),
-	ICE_CTX_STORE(ice_txtime_ctx, timer_num,		3,	104),
-	ICE_CTX_STORE(ice_txtime_ctx, txtime_ena_q,		1,	107),
-	ICE_CTX_STORE(ice_txtime_ctx, drbell_mode_32,		1,	108),
-	ICE_CTX_STORE(ice_txtime_ctx, ts_res,			4,	109),
-	ICE_CTX_STORE(ice_txtime_ctx, ts_round_type,		2,	113),
-	ICE_CTX_STORE(ice_txtime_ctx, ts_pacing_slot,		3,	115),
-	ICE_CTX_STORE(ice_txtime_ctx, merging_ena,		1,	118),
-	ICE_CTX_STORE(ice_txtime_ctx, ts_fetch_prof_id,		4,	119),
-	ICE_CTX_STORE(ice_txtime_ctx, ts_fetch_cache_line_aln_thld, 4,	123),
-	ICE_CTX_STORE(ice_txtime_ctx, tx_pipe_delay_mode,	1,	127),
-	ICE_CTX_STORE(ice_txtime_ctx, int_q_state,		70,	128),
+	ICE_CTX_STORE(ice_txtime_ctx, timer_num,		1,	104),
+	ICE_CTX_STORE(ice_txtime_ctx, txtime_ena_q,		1,	105),
+	ICE_CTX_STORE(ice_txtime_ctx, drbell_mode_32,		1,	106),
+	ICE_CTX_STORE(ice_txtime_ctx, ts_res,			4,	107),
+	ICE_CTX_STORE(ice_txtime_ctx, ts_round_type,		2,	111),
+	ICE_CTX_STORE(ice_txtime_ctx, ts_pacing_slot,		3,	113),
+	ICE_CTX_STORE(ice_txtime_ctx, merging_ena,		1,	116),
+	ICE_CTX_STORE(ice_txtime_ctx, ts_fetch_prof_id,		4,	117),
+	ICE_CTX_STORE(ice_txtime_ctx, ts_fetch_cache_line_aln_thld, 4,	121),
+	ICE_CTX_STORE(ice_txtime_ctx, tx_pipe_delay_mode,	1,	125),
+	ICE_CTX_STORE(ice_txtime_ctx, int_q_state,		70,	126),
 	{ 0 }
 };
 
-- 
2.43.0

[PATCH v1 2/6] net/intel: add read clock feature in ICE

[Soumyadeep Hore]

Adding eth_ice_read_clock() feature to get current time
for scheduling Packets based on Tx time.

Signed-off-by: Soumyadeep Hore <soumyadeep.hore@intel.com>
---
 drivers/net/intel/ice/ice_ethdev.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/net/intel/ice/ice_ethdev.c b/drivers/net/intel/ice/ice_ethdev.c
index 7cc083ca32..9478ba92df 100644
--- a/drivers/net/intel/ice/ice_ethdev.c
+++ b/drivers/net/intel/ice/ice_ethdev.c
@@ -187,6 +187,7 @@ static int ice_timesync_read_time(struct rte_eth_dev *dev,
 static int ice_timesync_write_time(struct rte_eth_dev *dev,
 				   const struct timespec *timestamp);
 static int ice_timesync_disable(struct rte_eth_dev *dev);
+static int eth_ice_read_clock(struct rte_eth_dev *dev, uint64_t *clock);
 static int ice_fec_get_capability(struct rte_eth_dev *dev, struct rte_eth_fec_capa *speed_fec_capa,
 			   unsigned int num);
 static int ice_fec_get(struct rte_eth_dev *dev, uint32_t *fec_capa);
@@ -317,6 +318,7 @@ static const struct eth_dev_ops ice_eth_dev_ops = {
 	.timesync_read_time           = ice_timesync_read_time,
 	.timesync_write_time          = ice_timesync_write_time,
 	.timesync_disable             = ice_timesync_disable,
+	.read_clock					  = eth_ice_read_clock,
 	.tm_ops_get                   = ice_tm_ops_get,
 	.fec_get_capability           = ice_fec_get_capability,
 	.fec_get                      = ice_fec_get,
@@ -6935,6 +6937,17 @@ ice_timesync_disable(struct rte_eth_dev *dev)
 	return 0;
 }
 
+static int
+eth_ice_read_clock(__rte_unused struct rte_eth_dev *dev, uint64_t *clock)
+{
+	struct timespec system_time;
+
+	clock_gettime(CLOCK_REALTIME, &system_time);
+	*clock = system_time.tv_sec * NSEC_PER_SEC + system_time.tv_nsec;
+
+	return 0;
+}
+
 static const uint32_t *
 ice_buffer_split_supported_hdr_ptypes_get(struct rte_eth_dev *dev __rte_unused,
 					  size_t *no_of_elements)
-- 
2.43.0

[PATCH v1 3/6] net/intel: add TxPP Support for E830

[Soumyadeep Hore]

Add support for Tx Time based queues. This is used to schedule
packets based on Tx timestamp.

Signed-off-by: Soumyadeep Hore <soumyadeep.hore@intel.com>
---
 drivers/net/intel/common/tx.h              |  14 ++
 drivers/net/intel/ice/base/ice_lan_tx_rx.h |   4 +
 drivers/net/intel/ice/ice_ethdev.c         |   3 +-
 drivers/net/intel/ice/ice_ethdev.h         |  12 ++
 drivers/net/intel/ice/ice_rxtx.c           | 233 ++++++++++++++++++++-
 drivers/net/intel/ice/ice_rxtx.h           |   9 +
 6 files changed, 265 insertions(+), 10 deletions(-)

diff --git a/drivers/net/intel/common/tx.h b/drivers/net/intel/common/tx.h
index b0a68bae44..8b958bf8e5 100644
--- a/drivers/net/intel/common/tx.h
+++ b/drivers/net/intel/common/tx.h
@@ -30,6 +30,19 @@ struct ci_tx_entry_vec {
 
 typedef void (*ice_tx_release_mbufs_t)(struct ci_tx_queue *txq);
 
+/**
+ * Structure associated with Tx Time based queue
+ */
+struct ice_txtime {
+	volatile struct ice_ts_desc	*ice_ts_ring;  /* Tx time ring virtual address */
+	uint16_t nb_ts_desc;	/* number of Tx Time descriptors */
+	uint16_t ts_tail;  /* current value of tail register */
+	rte_iova_t ts_ring_dma;	/* TX time ring DMA address */
+	const struct rte_memzone *ts_mz;
+	int ts_offset;	/* dynamic mbuf Tx timestamp field offset */
+	uint64_t ts_flag;	/* dynamic mbuf Tx timestamp flag */
+};
+
 struct ci_tx_queue {
 	union { /* TX ring virtual address */
 		volatile struct i40e_tx_desc *i40e_tx_ring;
@@ -77,6 +90,7 @@ struct ci_tx_queue {
 	union {
 		struct { /* ICE driver specific values */
 			uint32_t q_teid; /* TX schedule node id. */
+			struct ice_txtime tsq; /* Tx Time based queue */
 		};
 		struct { /* I40E driver specific values */
 			uint8_t dcb_tc;
diff --git a/drivers/net/intel/ice/base/ice_lan_tx_rx.h b/drivers/net/intel/ice/base/ice_lan_tx_rx.h
index f92382346f..8b6c1a07a3 100644
--- a/drivers/net/intel/ice/base/ice_lan_tx_rx.h
+++ b/drivers/net/intel/ice/base/ice_lan_tx_rx.h
@@ -1278,6 +1278,8 @@ struct ice_ts_desc {
 #define ICE_TXTIME_MAX_QUEUE		2047
 #define ICE_SET_TXTIME_MAX_Q_AMOUNT	127
 #define ICE_OP_TXTIME_MAX_Q_AMOUNT	2047
+#define ICE_TXTIME_FETCH_TS_DESC_DFLT	8
+#define ICE_TXTIME_FETCH_PROFILE_CNT	16
 /* Tx Time queue context data
  *
  * The sizes of the variables may be larger than needed due to crossing byte
@@ -1303,8 +1305,10 @@ struct ice_txtime_ctx {
 	u8 drbell_mode_32;
 #define ICE_TXTIME_CTX_DRBELL_MODE_32	1
 	u8 ts_res;
+#define ICE_TXTIME_CTX_RESOLUTION_128NS 7
 	u8 ts_round_type;
 	u8 ts_pacing_slot;
+#define ICE_TXTIME_CTX_FETCH_PROF_ID_0 0
 	u8 merging_ena;
 	u8 ts_fetch_prof_id;
 	u8 ts_fetch_cache_line_aln_thld;
diff --git a/drivers/net/intel/ice/ice_ethdev.c b/drivers/net/intel/ice/ice_ethdev.c
index 9478ba92df..3af9f6ba38 100644
--- a/drivers/net/intel/ice/ice_ethdev.c
+++ b/drivers/net/intel/ice/ice_ethdev.c
@@ -4139,7 +4139,8 @@ ice_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info)
 			RTE_ETH_TX_OFFLOAD_VXLAN_TNL_TSO |
 			RTE_ETH_TX_OFFLOAD_GRE_TNL_TSO |
 			RTE_ETH_TX_OFFLOAD_IPIP_TNL_TSO |
-			RTE_ETH_TX_OFFLOAD_GENEVE_TNL_TSO;
+			RTE_ETH_TX_OFFLOAD_GENEVE_TNL_TSO |
+			RTE_ETH_TX_OFFLOAD_SEND_ON_TIMESTAMP;
 		dev_info->flow_type_rss_offloads |= ICE_RSS_OFFLOAD_ALL;
 	}
 
diff --git a/drivers/net/intel/ice/ice_ethdev.h b/drivers/net/intel/ice/ice_ethdev.h
index bfe093afca..dd86bd030c 100644
--- a/drivers/net/intel/ice/ice_ethdev.h
+++ b/drivers/net/intel/ice/ice_ethdev.h
@@ -17,6 +17,18 @@
 #include "base/ice_flow.h"
 #include "base/ice_sched.h"
 
+#define __bf_shf(x) rte_bsf32(x)
+#define FIELD_GET(_mask, _reg) \
+	(__extension__ ({ \
+		typeof(_mask) _x = (_mask); \
+		(typeof(_x))(((_reg) & (_x)) >> __bf_shf(_x)); \
+	}))
+#define FIELD_PREP(_mask, _val) \
+	(__extension__ ({ \
+		typeof(_mask) _x = (_mask); \
+		((typeof(_x))(_val) << __bf_shf(_x)) & (_x); \
+	}))
+
 #define ICE_ADMINQ_LEN               32
 #define ICE_SBIOQ_LEN                32
 #define ICE_MAILBOXQ_LEN             32
diff --git a/drivers/net/intel/ice/ice_rxtx.c b/drivers/net/intel/ice/ice_rxtx.c
index ba1435b9de..b256a1b5b8 100644
--- a/drivers/net/intel/ice/ice_rxtx.c
+++ b/drivers/net/intel/ice/ice_rxtx.c
@@ -740,6 +740,53 @@ ice_rx_queue_stop(struct rte_eth_dev *dev, uint16_t rx_queue_id)
 	return 0;
 }
 
+/**
+ * ice_setup_txtime_ctx - setup a struct ice_txtime_ctx instance
+ * @txq: The queue on which tstamp ring to configure
+ * @txtime_ctx: Pointer to the Tx time queue context structure to be initialized
+ * @txtime_ena: Tx time enable flag, set to true if Tx time should be enabled
+ */
+static int
+ice_setup_txtime_ctx(struct ci_tx_queue *txq,
+		     struct ice_txtime_ctx *txtime_ctx, bool txtime_ena)
+{
+	struct ice_vsi *vsi = txq->ice_vsi;
+	struct ice_hw *hw = ICE_VSI_TO_HW(vsi);
+
+	txtime_ctx->base = txq->tsq.ts_ring_dma >> ICE_TX_CMPLTNQ_CTX_BASE_S;
+
+	/* Tx time Queue Length */
+	txtime_ctx->qlen = txq->tsq.nb_ts_desc;
+
+	if (txtime_ena)
+		txtime_ctx->txtime_ena_q = 1;
+
+	/* PF number */
+	txtime_ctx->pf_num = hw->pf_id;
+
+	switch (vsi->type) {
+	case ICE_VSI_LB:
+	case ICE_VSI_CTRL:
+	case ICE_VSI_ADI:
+	case ICE_VSI_PF:
+		txtime_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_PF;
+		break;
+	default:
+		PMD_DRV_LOG(ERR, "Unable to set VMVF type for VSI type %d",
+				vsi->type);
+		return -EINVAL;
+	}
+
+	/* make sure the context is associated with the right VSI */
+	txtime_ctx->src_vsi = vsi->vsi_id;
+
+	txtime_ctx->ts_res = ICE_TXTIME_CTX_RESOLUTION_128NS;
+	txtime_ctx->drbell_mode_32 = ICE_TXTIME_CTX_DRBELL_MODE_32;
+	txtime_ctx->ts_fetch_prof_id = ICE_TXTIME_CTX_FETCH_PROF_ID_0;
+
+	return 0;
+}
+
 int
 ice_tx_queue_start(struct rte_eth_dev *dev, uint16_t tx_queue_id)
 {
@@ -799,11 +846,6 @@ ice_tx_queue_start(struct rte_eth_dev *dev, uint16_t tx_queue_id)
 	ice_set_ctx(hw, (uint8_t *)&tx_ctx, txq_elem->txqs[0].txq_ctx,
 		    ice_tlan_ctx_info);
 
-	txq->qtx_tail = hw->hw_addr + QTX_COMM_DBELL(txq->reg_idx);
-
-	/* Init the Tx tail register*/
-	ICE_PCI_REG_WRITE(txq->qtx_tail, 0);
-
 	/* Fix me, we assume TC always 0 here */
 	err = ice_ena_vsi_txq(hw->port_info, vsi->idx, 0, tx_queue_id, 1,
 			txq_elem, buf_len, NULL);
@@ -826,6 +868,40 @@ ice_tx_queue_start(struct rte_eth_dev *dev, uint16_t tx_queue_id)
 	/* record what kind of descriptor cleanup we need on teardown */
 	txq->vector_tx = ad->tx_vec_allowed;
 
+	if (txq->tsq.ts_flag > 0) {
+		struct ice_aqc_set_txtime_qgrp *ts_elem;
+		u8 ts_buf_len = ice_struct_size(ts_elem, txtimeqs, 1);
+		struct ice_txtime_ctx txtime_ctx = { 0 };
+
+		ts_elem = ice_malloc(hw, ts_buf_len);
+		ice_setup_txtime_ctx(txq, &txtime_ctx,
+						true);
+		ice_set_ctx(hw, (u8 *)&txtime_ctx,
+				ts_elem->txtimeqs[0].txtime_ctx,
+				ice_txtime_ctx_info);
+
+		txq->qtx_tail = hw->hw_addr +
+					E830_GLQTX_TXTIME_DBELL_LSB(txq->reg_idx);
+
+		/* Init the Tx time tail register*/
+		ICE_PCI_REG_WRITE(txq->qtx_tail, 0);
+
+		err = ice_aq_set_txtimeq(hw, txq->reg_idx, 1, ts_elem,
+								ts_buf_len, NULL);
+		if (err) {
+			PMD_DRV_LOG(ERR, "Failed to set Tx Time queue context, error: %d", err);
+			rte_free(txq_elem);
+			rte_free(ts_elem);
+			return err;
+		}
+		rte_free(ts_elem);
+	} else {
+		txq->qtx_tail = hw->hw_addr + QTX_COMM_DBELL(txq->reg_idx);
+
+		/* Init the Tx tail register*/
+		ICE_PCI_REG_WRITE(txq->qtx_tail, 0);
+	}
+
 	dev->data->tx_queue_state[tx_queue_id] = RTE_ETH_QUEUE_STATE_STARTED;
 
 	rte_free(txq_elem);
@@ -1046,6 +1122,20 @@ ice_reset_tx_queue(struct ci_tx_queue *txq)
 
 	txq->last_desc_cleaned = (uint16_t)(txq->nb_tx_desc - 1);
 	txq->nb_tx_free = (uint16_t)(txq->nb_tx_desc - 1);
+
+	if (txq->tsq.ts_flag > 0) {
+		size = sizeof(struct ice_ts_desc) * txq->tsq.nb_ts_desc;
+		for (i = 0; i < size; i++)
+			((volatile char *)txq->tsq.ice_ts_ring)[i] = 0;
+
+		for (i = 0; i < txq->tsq.nb_ts_desc; i++) {
+			volatile struct ice_ts_desc *tsd =
+							&txq->tsq.ice_ts_ring[i];
+			tsd->tx_desc_idx_tstamp = 0;
+		}
+
+		txq->tsq.ts_tail = 0;
+	}
 }
 
 int
@@ -1080,6 +1170,19 @@ ice_tx_queue_stop(struct rte_eth_dev *dev, uint16_t tx_queue_id)
 	q_ids[0] = txq->reg_idx;
 	q_teids[0] = txq->q_teid;
 
+	if (txq->tsq.ts_flag > 0) {
+		struct ice_aqc_ena_dis_txtime_qgrp txtime_pg;
+		status = ice_aq_ena_dis_txtimeq(hw, q_ids[0], 1, 0,
+					     &txtime_pg, NULL);
+		if (status != ICE_SUCCESS) {
+			PMD_DRV_LOG(DEBUG, "Failed to disable Tx time queue");
+			return -EINVAL;
+		}
+		txq->tsq.ts_flag = 0;
+		txq->tsq.ts_offset = -1;
+		dev->dev_ops->timesync_disable(dev);
+	}
+
 	/* Fix me, we assume TC always 0 here */
 	status = ice_dis_vsi_txq(hw->port_info, vsi->idx, 0, 1, &q_handle,
 				q_ids, q_teids, ICE_NO_RESET, 0, NULL);
@@ -1166,6 +1269,7 @@ ice_rx_queue_setup(struct rte_eth_dev *dev,
 		   struct rte_mempool *mp)
 {
 	struct ice_pf *pf = ICE_DEV_PRIVATE_TO_PF(dev->data->dev_private);
+	struct ice_hw *hw = ICE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
 	struct ice_adapter *ad =
 		ICE_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
 	struct ice_vsi *vsi = pf->main_vsi;
@@ -1249,7 +1353,7 @@ ice_rx_queue_setup(struct rte_eth_dev *dev,
 	rxq->xtr_field_offs = ad->devargs.xtr_field_offs;
 
 	/* Allocate the maximum number of RX ring hardware descriptor. */
-	len = ICE_MAX_RING_DESC;
+	len = ICE_MAX_NUM_DESC_BY_MAC(hw);
 
 	/**
 	 * Allocating a little more memory because vectorized/bulk_alloc Rx
@@ -1337,6 +1441,36 @@ ice_rx_queue_release(void *rxq)
 	rte_free(q);
 }
 
+/**
+ * ice_calc_ts_ring_count - Calculate the number of timestamp descriptors
+ * @hw: pointer to the hardware structure
+ * @tx_desc_count: number of Tx descriptors in the ring
+ *
+ * Return: the number of timestamp descriptors
+ */
+static uint16_t ice_calc_ts_ring_count(struct ice_hw *hw, u16 tx_desc_count)
+{
+	u16 prof = ICE_TXTIME_CTX_FETCH_PROF_ID_0;
+	u16 max_fetch_desc = 0;
+	u16 fetch;
+	u32 reg;
+	u16 i;
+
+	for (i = 0; i < ICE_TXTIME_FETCH_PROFILE_CNT; i++) {
+		reg = rd32(hw, E830_GLTXTIME_FETCH_PROFILE(prof, 0));
+		fetch = FIELD_GET(E830_GLTXTIME_FETCH_PROFILE_FETCH_TS_DESC_M,
+				  reg);
+		max_fetch_desc = max(fetch, max_fetch_desc);
+	}
+
+	if (!max_fetch_desc)
+		max_fetch_desc = ICE_TXTIME_FETCH_TS_DESC_DFLT;
+
+	max_fetch_desc = RTE_ALIGN(max_fetch_desc, ICE_REQ_DESC_MULTIPLE);
+
+	return tx_desc_count + max_fetch_desc;
+}
+
 int
 ice_tx_queue_setup(struct rte_eth_dev *dev,
 		   uint16_t queue_idx,
@@ -1345,6 +1479,7 @@ ice_tx_queue_setup(struct rte_eth_dev *dev,
 		   const struct rte_eth_txconf *tx_conf)
 {
 	struct ice_pf *pf = ICE_DEV_PRIVATE_TO_PF(dev->data->dev_private);
+	struct ice_hw *hw = ICE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
 	struct ice_vsi *vsi = pf->main_vsi;
 	struct ci_tx_queue *txq;
 	const struct rte_memzone *tz;
@@ -1469,7 +1604,8 @@ ice_tx_queue_setup(struct rte_eth_dev *dev,
 	}
 
 	/* Allocate TX hardware ring descriptors. */
-	ring_size = sizeof(struct ice_tx_desc) * ICE_MAX_RING_DESC;
+	ring_size = sizeof(struct ice_tx_desc) *
+				ICE_MAX_NUM_DESC_BY_MAC(hw);
 	ring_size = RTE_ALIGN(ring_size, ICE_DMA_MEM_ALIGN);
 	tz = rte_eth_dma_zone_reserve(dev, "ice_tx_ring", queue_idx,
 				      ring_size, ICE_RING_BASE_ALIGN,
@@ -1507,6 +1643,42 @@ ice_tx_queue_setup(struct rte_eth_dev *dev,
 		return -ENOMEM;
 	}
 
+	if (vsi->type == ICE_VSI_PF &&
+		(offloads & RTE_ETH_TX_OFFLOAD_SEND_ON_TIMESTAMP) &&
+		txq->tsq.ts_offset == 0 && hw->phy_model == ICE_PHY_E830) {
+		int ret =
+			rte_mbuf_dyn_tx_timestamp_register(&txq->tsq.ts_offset,
+							 &txq->tsq.ts_flag);
+		if (ret) {
+			PMD_INIT_LOG(ERR, "Cannot register Tx mbuf field/flag "
+							"for timestamp");
+			return -EINVAL;
+		}
+		dev->dev_ops->timesync_enable(dev);
+
+		ring_size = sizeof(struct ice_ts_desc) *
+					ICE_MAX_NUM_DESC_BY_MAC(hw);
+		ring_size = RTE_ALIGN(ring_size, ICE_DMA_MEM_ALIGN);
+		const struct rte_memzone *ts_z =
+					rte_eth_dma_zone_reserve(dev, "ice_tstamp_ring",
+					queue_idx, ring_size, ICE_RING_BASE_ALIGN,
+				    socket_id);
+		if (!ts_z) {
+			ice_tx_queue_release(txq);
+			PMD_INIT_LOG(ERR, "Failed to reserve DMA memory "
+							"for TX timestamp");
+			return -ENOMEM;
+		}
+		txq->tsq.ts_mz = ts_z;
+		txq->tsq.ice_ts_ring = ts_z->addr;
+		txq->tsq.ts_ring_dma = ts_z->iova;
+		txq->tsq.nb_ts_desc =
+				ice_calc_ts_ring_count(ICE_VSI_TO_HW(vsi),
+							txq->nb_tx_desc);
+	} else {
+		txq->tsq.ice_ts_ring = NULL;
+	}
+
 	ice_reset_tx_queue(txq);
 	txq->q_set = true;
 	dev->data->tx_queues[queue_idx] = txq;
@@ -1539,6 +1711,8 @@ ice_tx_queue_release(void *txq)
 
 	ci_txq_release_all_mbufs(q, false);
 	rte_free(q->sw_ring);
+	if (q->tsq.ts_mz)
+		rte_memzone_free(q->tsq.ts_mz);
 	rte_memzone_free(q->mz);
 	rte_free(q);
 }
@@ -2960,7 +3134,7 @@ ice_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
 	struct rte_mbuf *tx_pkt;
 	struct rte_mbuf *m_seg;
 	uint32_t cd_tunneling_params;
-	uint16_t tx_id;
+	uint16_t tx_id, ts_id;
 	uint16_t nb_tx;
 	uint16_t nb_used;
 	uint16_t nb_ctx;
@@ -2979,6 +3153,9 @@ ice_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
 	tx_id = txq->tx_tail;
 	txe = &sw_ring[tx_id];
 
+	if (txq->tsq.ts_flag > 0)
+		ts_id = txq->tsq.ts_tail;
+
 	/* Check if the descriptor ring needs to be cleaned. */
 	if (txq->nb_tx_free < txq->tx_free_thresh)
 		(void)ice_xmit_cleanup(txq);
@@ -3166,10 +3343,48 @@ ice_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
 		txd->cmd_type_offset_bsz |=
 			rte_cpu_to_le_64(((uint64_t)td_cmd) <<
 					 ICE_TXD_QW1_CMD_S);
+
+		if (txq->tsq.ts_flag > 0) {
+			uint64_t txtime = *RTE_MBUF_DYNFIELD(tx_pkt,
+					txq->tsq.ts_offset, uint64_t *);
+			uint32_t tstamp = (uint32_t)(txtime % NS_PER_S) >>
+						ICE_TXTIME_CTX_RESOLUTION_128NS;
+			if (tx_id == 0)
+				txq->tsq.ice_ts_ring[ts_id].tx_desc_idx_tstamp =
+				rte_cpu_to_le_32(FIELD_PREP(ICE_TXTIME_TX_DESC_IDX_M,
+				txq->nb_tx_desc) | FIELD_PREP(ICE_TXTIME_STAMP_M,
+				tstamp));
+			else
+				txq->tsq.ice_ts_ring[ts_id].tx_desc_idx_tstamp =
+				rte_cpu_to_le_32(FIELD_PREP(ICE_TXTIME_TX_DESC_IDX_M,
+				tx_id) | FIELD_PREP(ICE_TXTIME_STAMP_M, tstamp));
+			ts_id++;
+			/* Handling MDD issue causing Tx Hang */
+			if (ts_id == txq->tsq.nb_ts_desc) {
+				uint16_t fetch = txq->tsq.nb_ts_desc - txq->nb_tx_desc;
+				ts_id = 0;
+				for (; ts_id < fetch; ts_id++) {
+					if (tx_id == 0)
+						txq->tsq.ice_ts_ring[ts_id].tx_desc_idx_tstamp =
+						rte_cpu_to_le_32(FIELD_PREP(ICE_TXTIME_TX_DESC_IDX_M,
+						txq->nb_tx_desc) | FIELD_PREP(ICE_TXTIME_STAMP_M,
+						tstamp));
+					else
+						txq->tsq.ice_ts_ring[ts_id].tx_desc_idx_tstamp =
+						rte_cpu_to_le_32(FIELD_PREP(ICE_TXTIME_TX_DESC_IDX_M,
+						tx_id) | FIELD_PREP(ICE_TXTIME_STAMP_M, tstamp));
+				}
+			}
+		}
 	}
 end_of_tx:
 	/* update Tail register */
-	ICE_PCI_REG_WRITE(txq->qtx_tail, tx_id);
+	if (txq->tsq.ts_flag > 0) {
+		ICE_PCI_REG_WRITE(txq->qtx_tail, ts_id);
+		txq->tsq.ts_tail = ts_id;
+	} else {
+		ICE_PCI_REG_WRITE(txq->qtx_tail, tx_id);
+	}
 	txq->tx_tail = tx_id;
 
 	return nb_tx;
diff --git a/drivers/net/intel/ice/ice_rxtx.h b/drivers/net/intel/ice/ice_rxtx.h
index 500d630679..a9e8b5c5e9 100644
--- a/drivers/net/intel/ice/ice_rxtx.h
+++ b/drivers/net/intel/ice/ice_rxtx.h
@@ -11,9 +11,18 @@
 #define ICE_ALIGN_RING_DESC  32
 #define ICE_MIN_RING_DESC    64
 #define ICE_MAX_RING_DESC    (8192 - 32)
+#define ICE_MAX_RING_DESC_E830	  8096
+#define ICE_MAX_NUM_DESC_BY_MAC(hw) ((hw)->phy_model == \
+					ICE_PHY_E830 ? \
+				    ICE_MAX_RING_DESC_E830 : \
+				    ICE_MAX_RING_DESC)
 #define ICE_DMA_MEM_ALIGN    4096
 #define ICE_RING_BASE_ALIGN  128
 
+#define ICE_TXTIME_TX_DESC_IDX_M	RTE_GENMASK32(12, 0)
+#define ICE_TXTIME_STAMP_M		RTE_GENMASK32(31, 13)
+#define ICE_REQ_DESC_MULTIPLE	32
+
 #define ICE_RX_MAX_BURST 32
 #define ICE_TX_MAX_BURST 32
 
-- 
2.43.0

[PATCH v1 4/6] net/intel: add AVX2 Support for TxPP

[Soumyadeep Hore]

Tx Time based queues are supported using AVX2 vector.

Signed-off-by: Soumyadeep Hore <soumyadeep.hore@intel.com>
---
 drivers/net/intel/ice/ice_rxtx_vec_avx2.c   | 134 +++++++++++++++++++-
 drivers/net/intel/ice/ice_rxtx_vec_common.h |  17 +++
 2 files changed, 149 insertions(+), 2 deletions(-)

diff --git a/drivers/net/intel/ice/ice_rxtx_vec_avx2.c b/drivers/net/intel/ice/ice_rxtx_vec_avx2.c
index 0c54b325c6..56274b9135 100644
--- a/drivers/net/intel/ice/ice_rxtx_vec_avx2.c
+++ b/drivers/net/intel/ice/ice_rxtx_vec_avx2.c
@@ -848,6 +848,127 @@ ice_vtx(volatile struct ice_tx_desc *txdp,
 	}
 }
 
+static __rte_always_inline void
+ice_vts1(volatile struct ice_ts_desc *ts, struct rte_mbuf *pkt,
+		uint16_t tx_tail, uint16_t nb_tx_desc, int ts_offset)
+{
+	ts->tx_desc_idx_tstamp = ice_get_ts_queue_desc(pkt,
+						tx_tail, nb_tx_desc, ts_offset);
+}
+
+static __rte_always_inline void
+ice_vts4(volatile struct ice_ts_desc *ts, struct rte_mbuf **pkt,
+	uint16_t nb_pkts, uint16_t tx_tail, uint16_t nb_tx_desc,
+	int ts_offset)
+{
+	uint16_t tx_id;
+
+	for (; nb_pkts > 3; ts += 4, pkt += 4, nb_pkts -= 4,
+			tx_tail += 4) {
+		tx_id = tx_tail + 4;
+		uint32_t ts_dsc3 = ice_get_ts_queue_desc(pkt[3],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 3;
+		uint32_t ts_dsc2 = ice_get_ts_queue_desc(pkt[2],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 2;
+		uint32_t ts_dsc1 = ice_get_ts_queue_desc(pkt[1],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 1;
+		uint32_t ts_dsc0 = ice_get_ts_queue_desc(pkt[0],
+						tx_id, nb_tx_desc, ts_offset);
+		__m128i desc0_3 = _mm_set_epi32(ts_dsc3, ts_dsc2,
+						ts_dsc1, ts_dsc0);
+		_mm_store_si128(RTE_CAST_PTR(void *, ts), desc0_3);
+	}
+
+	/* do any last ones */
+	while (nb_pkts) {
+		tx_tail++;
+		ice_vts1(ts, *pkt, tx_tail, nb_tx_desc, ts_offset);
+		ts++, pkt++, nb_pkts--;
+	}
+}
+
+static __rte_always_inline void
+ice_vts(volatile struct ice_ts_desc *ts, struct rte_mbuf **pkt,
+	uint16_t nb_pkts, uint16_t tx_tail, uint16_t nb_tx_desc,
+	int ts_offset)
+{
+	uint16_t tx_id;
+
+	for (; nb_pkts > 7; ts += 8, pkt += 8, nb_pkts -= 8,
+			tx_tail += 8) {
+		tx_id = tx_tail + 8;
+		uint32_t ts_dsc7 = ice_get_ts_queue_desc(pkt[7],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 7;
+		uint32_t ts_dsc6 = ice_get_ts_queue_desc(pkt[6],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 6;
+		uint32_t ts_dsc5 = ice_get_ts_queue_desc(pkt[5],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 5;
+		uint32_t ts_dsc4 = ice_get_ts_queue_desc(pkt[4],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 4;
+		uint32_t ts_dsc3 = ice_get_ts_queue_desc(pkt[3],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 3;
+		uint32_t ts_dsc2 = ice_get_ts_queue_desc(pkt[2],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 2;
+		uint32_t ts_dsc1 = ice_get_ts_queue_desc(pkt[1],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 1;
+		uint32_t ts_dsc0 = ice_get_ts_queue_desc(pkt[0],
+						tx_id, nb_tx_desc, ts_offset);
+		__m256i desc0_7 = _mm256_set_epi32(ts_dsc7, ts_dsc6,
+						ts_dsc5, ts_dsc4, ts_dsc3, ts_dsc2,
+						ts_dsc1, ts_dsc0);
+		_mm256_storeu_si256(RTE_CAST_PTR(void *, ts), desc0_7);
+	}
+
+	/* do any last ones */
+	if (nb_pkts)
+		ice_vts4(ts, pkt, nb_pkts, tx_tail, nb_tx_desc,
+				ts_offset);
+}
+
+static __rte_always_inline uint16_t
+ice_xmit_fixed_ts_burst_vec_avx512(struct ci_tx_queue *txq,
+				struct rte_mbuf **tx_pkts, uint16_t nb_pkts,
+				uint16_t tx_tail)
+{
+	volatile struct ice_ts_desc *ts;
+	uint16_t n, ts_id, fetch;
+
+	ts_id = txq->tsq.ts_tail;
+	ts = &txq->tsq.ice_ts_ring[ts_id];
+
+	n = (uint16_t)(txq->tsq.nb_ts_desc - ts_id);
+	if (nb_pkts >= n) {
+		ice_vts(ts, tx_pkts, n, txq->tx_tail, txq->nb_tx_desc,
+				txq->tsq.ts_offset);
+		tx_pkts += n;
+		ts += n;
+		tx_tail += n;
+		nb_pkts = (uint16_t)(nb_pkts - n);
+		ts_id = 0;
+		ts = &txq->tsq.ice_ts_ring[ts_id];
+		fetch = txq->tsq.nb_ts_desc - txq->nb_tx_desc;
+		for (; ts_id < fetch; ts_id++, ts++)
+			ice_vts1(ts, *tx_pkts, tx_tail + 1,
+					txq->nb_tx_desc, txq->tsq.ts_offset);
+	}
+
+	ice_vts(ts, tx_pkts, nb_pkts, tx_tail, txq->nb_tx_desc,
+			txq->tsq.ts_offset);
+	ts_id = (uint16_t)(ts_id + nb_pkts);
+
+	return ts_id;
+}
+
 static __rte_always_inline uint16_t
 ice_xmit_fixed_burst_vec_avx2(void *tx_queue, struct rte_mbuf **tx_pkts,
 			      uint16_t nb_pkts, bool offload)
@@ -855,7 +976,7 @@ ice_xmit_fixed_burst_vec_avx2(void *tx_queue, struct rte_mbuf **tx_pkts,
 	struct ci_tx_queue *txq = (struct ci_tx_queue *)tx_queue;
 	volatile struct ice_tx_desc *txdp;
 	struct ci_tx_entry_vec *txep;
-	uint16_t n, nb_commit, tx_id;
+	uint16_t n, nb_commit, tx_id, ts_id;
 	uint64_t flags = ICE_TD_CMD;
 	uint64_t rs = ICE_TX_DESC_CMD_RS | ICE_TD_CMD;
 
@@ -875,6 +996,10 @@ ice_xmit_fixed_burst_vec_avx2(void *tx_queue, struct rte_mbuf **tx_pkts,
 
 	txq->nb_tx_free = (uint16_t)(txq->nb_tx_free - nb_pkts);
 
+	if (txq->tsq.ts_flag > 0)
+		ts_id = ice_xmit_fixed_ts_burst_vec_avx512(txq,
+								tx_pkts, nb_commit, tx_id);
+
 	n = (uint16_t)(txq->nb_tx_desc - tx_id);
 	if (nb_commit >= n) {
 		ci_tx_backlog_entry_vec(txep, tx_pkts, n);
@@ -910,7 +1035,12 @@ ice_xmit_fixed_burst_vec_avx2(void *tx_queue, struct rte_mbuf **tx_pkts,
 
 	txq->tx_tail = tx_id;
 
-	ICE_PCI_REG_WC_WRITE(txq->qtx_tail, txq->tx_tail);
+	if (txq->tsq.ts_flag > 0) {
+		ICE_PCI_REG_WC_WRITE(txq->qtx_tail, ts_id);
+		txq->tsq.ts_tail = ts_id;
+	} else {
+		ICE_PCI_REG_WC_WRITE(txq->qtx_tail, txq->tx_tail);
+	}
 
 	return nb_pkts;
 }
diff --git a/drivers/net/intel/ice/ice_rxtx_vec_common.h b/drivers/net/intel/ice/ice_rxtx_vec_common.h
index 7933c26366..9166a0408a 100644
--- a/drivers/net/intel/ice/ice_rxtx_vec_common.h
+++ b/drivers/net/intel/ice/ice_rxtx_vec_common.h
@@ -215,4 +215,21 @@ ice_txd_enable_offload(struct rte_mbuf *tx_pkt,
 
 	*txd_hi |= ((uint64_t)td_cmd) << ICE_TXD_QW1_CMD_S;
 }
+
+static inline uint32_t
+ice_get_ts_queue_desc(struct rte_mbuf *pkt, uint16_t tx_tail,
+					uint16_t nb_tx_desc, int ts_offset)
+{
+	uint64_t txtime;
+	uint32_t tstamp, ts_desc;
+
+	tx_tail = (tx_tail > nb_tx_desc) ? (tx_tail - nb_tx_desc) :
+			tx_tail;
+	txtime = *RTE_MBUF_DYNFIELD(pkt, ts_offset, uint64_t *);
+	tstamp = (uint32_t)(txtime % NS_PER_S) >>
+			ICE_TXTIME_CTX_RESOLUTION_128NS;
+	ts_desc = rte_cpu_to_le_32(FIELD_PREP(ICE_TXTIME_TX_DESC_IDX_M,
+			(tx_tail)) | FIELD_PREP(ICE_TXTIME_STAMP_M, tstamp));
+	return ts_desc;
+}
 #endif
-- 
2.43.0

[PATCH v1 5/6] net/intel: add AVX512 Support for TxPP

[Soumyadeep Hore]

Tx Time based queues are supported using AVX512 vector.

Signed-off-by: Soumyadeep Hore <soumyadeep.hore@intel.com>
---
 drivers/net/intel/ice/ice_rxtx_vec_avx512.c | 205 +++++++++++++++++++-
 1 file changed, 203 insertions(+), 2 deletions(-)

diff --git a/drivers/net/intel/ice/ice_rxtx_vec_avx512.c b/drivers/net/intel/ice/ice_rxtx_vec_avx512.c
index bd49be07c9..6cdd368c38 100644
--- a/drivers/net/intel/ice/ice_rxtx_vec_avx512.c
+++ b/drivers/net/intel/ice/ice_rxtx_vec_avx512.c
@@ -912,6 +912,198 @@ ice_vtx(volatile struct ice_tx_desc *txdp, struct rte_mbuf **pkt,
 	}
 }
 
+static __rte_always_inline void
+ice_vts1(volatile struct ice_ts_desc *ts, struct rte_mbuf *pkt,
+		uint16_t tx_tail, uint16_t nb_tx_desc, int ts_offset)
+{
+	ts->tx_desc_idx_tstamp = ice_get_ts_queue_desc(pkt,
+						tx_tail, nb_tx_desc, ts_offset);
+}
+
+static __rte_always_inline void
+ice_vts4(volatile struct ice_ts_desc *ts, struct rte_mbuf **pkt,
+	uint16_t nb_pkts, uint16_t tx_tail, uint16_t nb_tx_desc,
+	int ts_offset)
+{
+	uint16_t tx_id;
+
+	for (; nb_pkts > 3; ts += 4, pkt += 4, nb_pkts -= 4,
+			tx_tail += 4) {
+		tx_id = tx_tail + 4;
+		uint32_t ts_dsc3 = ice_get_ts_queue_desc(pkt[3],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 3;
+		uint32_t ts_dsc2 = ice_get_ts_queue_desc(pkt[2],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 2;
+		uint32_t ts_dsc1 = ice_get_ts_queue_desc(pkt[1],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 1;
+		uint32_t ts_dsc0 = ice_get_ts_queue_desc(pkt[0],
+						tx_id, nb_tx_desc, ts_offset);
+		__m128i desc0_3 = _mm_set_epi32(ts_dsc3, ts_dsc2,
+						ts_dsc1, ts_dsc0);
+		_mm_store_si128(RTE_CAST_PTR(void *, ts), desc0_3);
+	}
+
+	/* do any last ones */
+	while (nb_pkts) {
+		tx_tail++;
+		ice_vts1(ts, *pkt, tx_tail, nb_tx_desc, ts_offset);
+		ts++, pkt++, nb_pkts--;
+	}
+}
+
+static __rte_always_inline void
+ice_vts8(volatile struct ice_ts_desc *ts, struct rte_mbuf **pkt,
+	uint16_t nb_pkts, uint16_t tx_tail, uint16_t nb_tx_desc,
+	int ts_offset)
+{
+	uint16_t tx_id;
+
+	for (; nb_pkts > 7; ts += 8, pkt += 8, nb_pkts -= 8,
+			tx_tail += 8) {
+		tx_id = tx_tail + 8;
+		uint32_t ts_dsc7 = ice_get_ts_queue_desc(pkt[7],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 7;
+		uint32_t ts_dsc6 = ice_get_ts_queue_desc(pkt[6],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 6;
+		uint32_t ts_dsc5 = ice_get_ts_queue_desc(pkt[5],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 5;
+		uint32_t ts_dsc4 = ice_get_ts_queue_desc(pkt[4],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 4;
+		uint32_t ts_dsc3 = ice_get_ts_queue_desc(pkt[3],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 3;
+		uint32_t ts_dsc2 = ice_get_ts_queue_desc(pkt[2],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 2;
+		uint32_t ts_dsc1 = ice_get_ts_queue_desc(pkt[1],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 1;
+		uint32_t ts_dsc0 = ice_get_ts_queue_desc(pkt[0],
+						tx_id, nb_tx_desc, ts_offset);
+		__m256i desc0_7 = _mm256_set_epi32(ts_dsc7, ts_dsc6,
+						ts_dsc5, ts_dsc4, ts_dsc3, ts_dsc2,
+						ts_dsc1, ts_dsc0);
+		_mm256_storeu_si256(RTE_CAST_PTR(void *, ts), desc0_7);
+	}
+
+	/* do any last ones */
+	if (nb_pkts)
+		ice_vts4(ts, pkt, nb_pkts, tx_tail, nb_tx_desc,
+				ts_offset);
+}
+
+static __rte_always_inline void
+ice_vts(volatile struct ice_ts_desc *ts, struct rte_mbuf **pkt,
+	uint16_t nb_pkts, uint16_t tx_tail, uint16_t nb_tx_desc,
+	int ts_offset)
+{
+	uint16_t tx_id;
+
+	for (; nb_pkts > 15; ts += 16, pkt += 16, nb_pkts -= 16,
+			tx_tail += 16) {
+		tx_id = tx_tail + 16;
+		uint32_t ts_dsc15 = ice_get_ts_queue_desc(pkt[15],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 15;
+		uint32_t ts_dsc14 = ice_get_ts_queue_desc(pkt[14],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 14;
+		uint32_t ts_dsc13 = ice_get_ts_queue_desc(pkt[13],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 13;
+		uint32_t ts_dsc12 = ice_get_ts_queue_desc(pkt[12],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 12;
+		uint32_t ts_dsc11 = ice_get_ts_queue_desc(pkt[11],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 11;
+		uint32_t ts_dsc10 = ice_get_ts_queue_desc(pkt[10],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 10;
+		uint32_t ts_dsc9 = ice_get_ts_queue_desc(pkt[9],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 9;
+		uint32_t ts_dsc8 = ice_get_ts_queue_desc(pkt[8],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 8;
+		uint32_t ts_dsc7 = ice_get_ts_queue_desc(pkt[7],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 7;
+		uint32_t ts_dsc6 = ice_get_ts_queue_desc(pkt[6],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 6;
+		uint32_t ts_dsc5 = ice_get_ts_queue_desc(pkt[5],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 5;
+		uint32_t ts_dsc4 = ice_get_ts_queue_desc(pkt[4],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 4;
+		uint32_t ts_dsc3 = ice_get_ts_queue_desc(pkt[3],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 3;
+		uint32_t ts_dsc2 = ice_get_ts_queue_desc(pkt[2],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 2;
+		uint32_t ts_dsc1 = ice_get_ts_queue_desc(pkt[1],
+						tx_id, nb_tx_desc, ts_offset);
+		tx_id = tx_tail + 1;
+		uint32_t ts_dsc0 = ice_get_ts_queue_desc(pkt[0],
+						tx_id, nb_tx_desc, ts_offset);
+		__m512i desc0_15 = _mm512_set_epi32(ts_dsc15, ts_dsc14,
+						ts_dsc13, ts_dsc12, ts_dsc11, ts_dsc10,
+						ts_dsc9, ts_dsc8, ts_dsc7, ts_dsc6,
+						ts_dsc5, ts_dsc4, ts_dsc3, ts_dsc2,
+						ts_dsc1, ts_dsc0);
+		_mm512_storeu_si512(RTE_CAST_PTR(void *, ts), desc0_15);
+	}
+
+	/* do any last ones */
+	if (nb_pkts)
+		ice_vts8(ts, pkt, nb_pkts, tx_tail, nb_tx_desc,
+				ts_offset);
+}
+
+static __rte_always_inline uint16_t
+ice_xmit_fixed_ts_burst_vec_avx512(struct ci_tx_queue *txq,
+				struct rte_mbuf **tx_pkts, uint16_t nb_pkts,
+				uint16_t tx_tail)
+{
+	volatile struct ice_ts_desc *ts;
+	uint16_t n, ts_id, fetch;
+
+	ts_id = txq->tsq.ts_tail;
+	ts = &txq->tsq.ice_ts_ring[ts_id];
+
+	n = (uint16_t)(txq->tsq.nb_ts_desc - ts_id);
+	if (nb_pkts >= n) {
+		ice_vts(ts, tx_pkts, n, txq->tx_tail, txq->nb_tx_desc,
+				txq->tsq.ts_offset);
+		tx_pkts += n;
+		ts += n;
+		tx_tail += n;
+		nb_pkts = (uint16_t)(nb_pkts - n);
+		ts_id = 0;
+		ts = &txq->tsq.ice_ts_ring[ts_id];
+		fetch = txq->tsq.nb_ts_desc - txq->nb_tx_desc;
+		for (; ts_id < fetch; ts_id++, ts++)
+			ice_vts1(ts, *tx_pkts, tx_tail + 1,
+					txq->nb_tx_desc, txq->tsq.ts_offset);
+	}
+
+	ice_vts(ts, tx_pkts, nb_pkts, tx_tail, txq->nb_tx_desc,
+			txq->tsq.ts_offset);
+	ts_id = (uint16_t)(ts_id + nb_pkts);
+
+	return ts_id;
+}
+
 static __rte_always_inline uint16_t
 ice_xmit_fixed_burst_vec_avx512(void *tx_queue, struct rte_mbuf **tx_pkts,
 				uint16_t nb_pkts, bool do_offload)
@@ -919,7 +1111,7 @@ ice_xmit_fixed_burst_vec_avx512(void *tx_queue, struct rte_mbuf **tx_pkts,
 	struct ci_tx_queue *txq = (struct ci_tx_queue *)tx_queue;
 	volatile struct ice_tx_desc *txdp;
 	struct ci_tx_entry_vec *txep;
-	uint16_t n, nb_commit, tx_id;
+	uint16_t n, nb_commit, tx_id, ts_id;
 	uint64_t flags = ICE_TD_CMD;
 	uint64_t rs = ICE_TX_DESC_CMD_RS | ICE_TD_CMD;
 
@@ -940,6 +1132,10 @@ ice_xmit_fixed_burst_vec_avx512(void *tx_queue, struct rte_mbuf **tx_pkts,
 
 	txq->nb_tx_free = (uint16_t)(txq->nb_tx_free - nb_pkts);
 
+	if (txq->tsq.ts_flag > 0)
+		ts_id = ice_xmit_fixed_ts_burst_vec_avx512(txq,
+								tx_pkts, nb_commit, tx_id);
+
 	n = (uint16_t)(txq->nb_tx_desc - tx_id);
 	if (nb_commit >= n) {
 		ci_tx_backlog_entry_vec(txep, tx_pkts, n);
@@ -975,7 +1171,12 @@ ice_xmit_fixed_burst_vec_avx512(void *tx_queue, struct rte_mbuf **tx_pkts,
 
 	txq->tx_tail = tx_id;
 
-	ICE_PCI_REG_WC_WRITE(txq->qtx_tail, txq->tx_tail);
+	if (txq->tsq.ts_flag > 0) {
+		ICE_PCI_REG_WC_WRITE(txq->qtx_tail, ts_id);
+		txq->tsq.ts_tail = ts_id;
+	} else {
+		ICE_PCI_REG_WC_WRITE(txq->qtx_tail, txq->tx_tail);
+	}
 
 	return nb_pkts;
 }
-- 
2.43.0

[PATCH v1 6/6] doc: announce TxPP support for E830 adapters

[Soumyadeep Hore]

E830 adapters currently support Tx Time based queues.

Signed-off-by: Soumyadeep Hore <soumyadeep.hore@intel.com>
---
 doc/guides/nics/ice.rst | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/doc/guides/nics/ice.rst b/doc/guides/nics/ice.rst
index 77985ae5a2..73c5477946 100644
--- a/doc/guides/nics/ice.rst
+++ b/doc/guides/nics/ice.rst
@@ -415,6 +415,22 @@ and add the ``--force-max-simd-bitwidth=64`` startup parameter to disable vector
 
    examples/dpdk-ptpclient -c f -n 3 -a 0000:ec:00.1 --force-max-simd-bitwidth=64 -- -T 1 -p 0x1 -c 1
 
+Tx Packet Pacing
+~~~~~~~~~~~~~~~~
+
+In order to deliver the timestamp with every packet, a special type of Tx Host Queue is
+used, the TS Queue. This feature is currently supported only in E830 adapters.
+
+The tx_offload ``RTE_ETH_TX_OFFLOAD_SEND_ON_TIMESTAMP`` is used to enable the feature.
+For example:
+
+.. code-block:: console
+
+   dpdk-testpmd -a 0000:31:00.0 -c f -n 4 -- -i --tx-offloads=0x200000
+   set fwd txonly
+   set txtimes 30000000,1000000
+   start
+
 Generic Flow Support
 ~~~~~~~~~~~~~~~~~~~~
 
-- 
2.43.0