[PATCH] net/e1000: support launchtime feature

[Chuanyu Xue <chuanyu.xue@uconn.edu>]

Enable the time-based scheduled Tx of packets based on the
RTE_ETH_TX_OFFLOAD_SEND_ON_TIMESTAMP flag. The launchtime defines the
packet transmission time based on PTP clock at MAC layer, which should
be set to the advanced transmit descriptor.

Signed-off-by: Chuanyu Xue <chuanyu.xue@uconn.edu>
---
 drivers/net/e1000/base/e1000_regs.h |  1 +
 drivers/net/e1000/e1000_ethdev.h    |  3 ++
 drivers/net/e1000/igb_ethdev.c      | 28 ++++++++++++++++++
 drivers/net/e1000/igb_rxtx.c        | 44 ++++++++++++++++++++++++-----
 4 files changed, 69 insertions(+), 7 deletions(-)

diff --git a/drivers/net/e1000/base/e1000_regs.h b/drivers/net/e1000/base/e1000_regs.h
index d44de59c29..092d9d71e6 100644
--- a/drivers/net/e1000/base/e1000_regs.h
+++ b/drivers/net/e1000/base/e1000_regs.h
@@ -162,6 +162,7 @@
 
 /* QAV Tx mode control register */
 #define E1000_I210_TQAVCTRL	0x3570
+#define E1000_I210_LAUNCH_OS0 0x3578
 
 /* QAV Tx mode control register bitfields masks */
 /* QAV enable */
diff --git a/drivers/net/e1000/e1000_ethdev.h b/drivers/net/e1000/e1000_ethdev.h
index 718a9746ed..174f7aaf52 100644
--- a/drivers/net/e1000/e1000_ethdev.h
+++ b/drivers/net/e1000/e1000_ethdev.h
@@ -382,6 +382,9 @@ extern struct igb_rss_filter_list igb_filter_rss_list;
 TAILQ_HEAD(igb_flow_mem_list, igb_flow_mem);
 extern struct igb_flow_mem_list igb_flow_list;
 
+extern uint64_t igb_tx_timestamp_dynflag;
+extern int igb_tx_timestamp_dynfield_offset;
+
 extern const struct rte_flow_ops igb_flow_ops;
 
 /*
diff --git a/drivers/net/e1000/igb_ethdev.c b/drivers/net/e1000/igb_ethdev.c
index 8858f975f8..4d3d8ae30a 100644
--- a/drivers/net/e1000/igb_ethdev.c
+++ b/drivers/net/e1000/igb_ethdev.c
@@ -223,6 +223,7 @@ static int igb_timesync_read_time(struct rte_eth_dev *dev,
 				  struct timespec *timestamp);
 static int igb_timesync_write_time(struct rte_eth_dev *dev,
 				   const struct timespec *timestamp);
+static int eth_igb_read_clock(__rte_unused struct rte_eth_dev *dev, uint64_t *clock);
 static int eth_igb_rx_queue_intr_enable(struct rte_eth_dev *dev,
 					uint16_t queue_id);
 static int eth_igb_rx_queue_intr_disable(struct rte_eth_dev *dev,
@@ -313,6 +314,9 @@ static const struct rte_pci_id pci_id_igbvf_map[] = {
 	{ .vendor_id = 0, /* sentinel */ },
 };
 
+uint64_t igb_tx_timestamp_dynflag;
+int igb_tx_timestamp_dynfield_offset = -1;
+
 static const struct rte_eth_desc_lim rx_desc_lim = {
 	.nb_max = E1000_MAX_RING_DESC,
 	.nb_min = E1000_MIN_RING_DESC,
@@ -389,6 +393,7 @@ static const struct eth_dev_ops eth_igb_ops = {
 	.timesync_adjust_time = igb_timesync_adjust_time,
 	.timesync_read_time   = igb_timesync_read_time,
 	.timesync_write_time  = igb_timesync_write_time,
+	.read_clock		      = eth_igb_read_clock,
 };
 
 /*
@@ -1198,6 +1203,7 @@ eth_igb_start(struct rte_eth_dev *dev)
 	struct rte_pci_device *pci_dev = RTE_ETH_DEV_TO_PCI(dev);
 	struct rte_intr_handle *intr_handle = pci_dev->intr_handle;
 	int ret, mask;
+	uint32_t tqavctrl;
 	uint32_t intr_vector = 0;
 	uint32_t ctrl_ext;
 	uint32_t *speeds;
@@ -1281,6 +1287,15 @@ eth_igb_start(struct rte_eth_dev *dev)
 		return ret;
 	}
 
+	if (igb_tx_timestamp_dynflag > 0) {
+		tqavctrl = E1000_READ_REG(hw, E1000_I210_TQAVCTRL);
+		tqavctrl |= E1000_TQAVCTRL_MODE;
+		tqavctrl |= E1000_TQAVCTRL_FETCH_ARB; /* Fetch the queue most empty, no Round Robin*/
+		tqavctrl |= E1000_TQAVCTRL_LAUNCH_TIMER_ENABLE; /* Enable launch time */
+		E1000_WRITE_REG(hw, E1000_I210_TQAVCTRL, tqavctrl);
+		E1000_WRITE_REG(hw, E1000_I210_LAUNCH_OS0, 1ULL << 31); /* Set launch offset to default */
+	}
+
 	e1000_clear_hw_cntrs_base_generic(hw);
 
 	/*
@@ -4882,6 +4897,19 @@ igb_timesync_read_tx_timestamp(struct rte_eth_dev *dev,
 	return  0;
 }
 
+static int
+eth_igb_read_clock(__rte_unused struct rte_eth_dev *dev, uint64_t *clock)
+{
+	uint64_t systime_cycles;
+	struct e1000_adapter *adapter = dev->data->dev_private;
+
+	systime_cycles = igb_read_systime_cyclecounter(dev);
+	uint64_t ns = rte_timecounter_update(&adapter->systime_tc, systime_cycles);
+	*clock = ns;
+
+	return 0;
+}
+
 static int
 eth_igb_get_reg_length(struct rte_eth_dev *dev __rte_unused)
 {
diff --git a/drivers/net/e1000/igb_rxtx.c b/drivers/net/e1000/igb_rxtx.c
index 448c4b7d9d..e5da8e250d 100644
--- a/drivers/net/e1000/igb_rxtx.c
+++ b/drivers/net/e1000/igb_rxtx.c
@@ -212,6 +212,9 @@ struct igb_tx_queue {
 #define IGB_TSO_MAX_HDRLEN			(512)
 #define IGB_TSO_MAX_MSS				(9216)
 
+/* Macro to compensate latency in launch time offloading*/
+#define E1000_I210_LT_LATENCY		0x41F9
+
 /*********************************************************************
  *
  *  TX function
@@ -244,12 +247,13 @@ check_tso_para(uint64_t ol_req, union igb_tx_offload ol_para)
 static inline void
 igbe_set_xmit_ctx(struct igb_tx_queue* txq,
 		volatile struct e1000_adv_tx_context_desc *ctx_txd,
-		uint64_t ol_flags, union igb_tx_offload tx_offload)
+		uint64_t ol_flags, union igb_tx_offload tx_offload, uint64_t txtime)
 {
 	uint32_t type_tucmd_mlhl;
 	uint32_t mss_l4len_idx;
 	uint32_t ctx_idx, ctx_curr;
 	uint32_t vlan_macip_lens;
+	uint32_t launch_time;
 	union igb_tx_offload tx_offload_mask;
 
 	ctx_curr = txq->ctx_curr;
@@ -312,16 +316,25 @@ igbe_set_xmit_ctx(struct igb_tx_queue* txq,
 		}
 	}
 
-	txq->ctx_cache[ctx_curr].flags = ol_flags;
-	txq->ctx_cache[ctx_curr].tx_offload.data =
-		tx_offload_mask.data & tx_offload.data;
-	txq->ctx_cache[ctx_curr].tx_offload_mask = tx_offload_mask;
+	if (!txtime) {
+		txq->ctx_cache[ctx_curr].flags = ol_flags;
+		txq->ctx_cache[ctx_curr].tx_offload.data =
+			tx_offload_mask.data & tx_offload.data;
+		txq->ctx_cache[ctx_curr].tx_offload_mask = tx_offload_mask;
+	}
 
 	ctx_txd->type_tucmd_mlhl = rte_cpu_to_le_32(type_tucmd_mlhl);
 	vlan_macip_lens = (uint32_t)tx_offload.data;
 	ctx_txd->vlan_macip_lens = rte_cpu_to_le_32(vlan_macip_lens);
 	ctx_txd->mss_l4len_idx = rte_cpu_to_le_32(mss_l4len_idx);
 	ctx_txd->u.seqnum_seed = 0;
+
+	if (txtime) {
+		launch_time = (txtime - E1000_I210_LT_LATENCY) % NSEC_PER_SEC;
+		ctx_txd->u.launch_time = rte_cpu_to_le_32(launch_time / 32);
+	} else {
+		ctx_txd->u.launch_time = 0;
+	}
 }
 
 /*
@@ -400,6 +413,7 @@ eth_igb_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
 	uint32_t new_ctx = 0;
 	uint32_t ctx = 0;
 	union igb_tx_offload tx_offload = {0};
+	uint64_t ts;
 
 	txq = tx_queue;
 	sw_ring = txq->sw_ring;
@@ -552,7 +566,12 @@ eth_igb_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
 					txe->mbuf = NULL;
 				}
 
-				igbe_set_xmit_ctx(txq, ctx_txd, tx_ol_req, tx_offload);
+				if (igb_tx_timestamp_dynflag > 0) {
+					ts = *RTE_MBUF_DYNFIELD(tx_pkt, igb_tx_timestamp_dynfield_offset, uint64_t *);
+					igbe_set_xmit_ctx(txq, ctx_txd, tx_ol_req, tx_offload, ts);
+				} else {
+					igbe_set_xmit_ctx(txq, ctx_txd, tx_ol_req, tx_offload, 0);
+				}
 
 				txe->last_id = tx_last;
 				tx_id = txe->next_id;
@@ -1464,7 +1483,8 @@ igb_get_tx_port_offloads_capa(struct rte_eth_dev *dev)
 			  RTE_ETH_TX_OFFLOAD_TCP_CKSUM   |
 			  RTE_ETH_TX_OFFLOAD_SCTP_CKSUM  |
 			  RTE_ETH_TX_OFFLOAD_TCP_TSO     |
-			  RTE_ETH_TX_OFFLOAD_MULTI_SEGS;
+			  RTE_ETH_TX_OFFLOAD_MULTI_SEGS  |
+			  RTE_ETH_TX_OFFLOAD_SEND_ON_TIMESTAMP;
 
 	return tx_offload_capa;
 }
@@ -2579,9 +2599,11 @@ eth_igb_tx_init(struct rte_eth_dev *dev)
 {
 	struct e1000_hw     *hw;
 	struct igb_tx_queue *txq;
+	uint64_t offloads = dev->data->dev_conf.txmode.offloads;
 	uint32_t tctl;
 	uint32_t txdctl;
 	uint16_t i;
+	int err;
 
 	hw = E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private);
 
@@ -2612,6 +2634,14 @@ eth_igb_tx_init(struct rte_eth_dev *dev)
 		dev->data->tx_queue_state[i] = RTE_ETH_QUEUE_STATE_STARTED;
 	}
 
+	if (offloads & RTE_ETH_TX_OFFLOAD_SEND_ON_TIMESTAMP) {
+		err = rte_mbuf_dyn_tx_timestamp_register(
+			&igb_tx_timestamp_dynfield_offset,
+			&igb_tx_timestamp_dynflag);
+		if (err)
+			PMD_DRV_LOG(ERR, "Failed to register tx timestamp dynamic field");
+	}
+
 	/* Program the Transmit Control Register. */
 	tctl = E1000_READ_REG(hw, E1000_TCTL);
 	tctl &= ~E1000_TCTL_CT;
-- 
2.25.1