net/iavf: improve performance of Rx timestamp offload

In this patch, We use CPU ticks instead of HW register
to determine whether low 32 bits timestamp has turned
over. It can avoid requesting register value frequently
and improve receiving performance.

Signed-off-by: Wenjun Wu <wenjun1.wu@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>

diff --git a/drivers/net/iavf/iavf.h b/drivers/net/iavf/iavf.h
index 3255c93..dd83567 100644 (file)
--- a/drivers/net/iavf/iavf.h
+++ b/drivers/net/iavf/iavf.h
@@ -315,6 +315,7 @@ struct iavf_adapter {
        uint16_t fdir_ref_cnt;
        struct iavf_devargs devargs;
        uint64_t phc_time;
+       uint64_t hw_time_update;
 };
 
 /* IAVF_DEV_PRIVATE_TO */

diff --git a/drivers/net/iavf/iavf_ethdev.c b/drivers/net/iavf/iavf_ethdev.c
index 89e4240..d1a2b53 100644 (file)
--- a/drivers/net/iavf/iavf_ethdev.c
+++ b/drivers/net/iavf/iavf_ethdev.c
@@ -1019,6 +1019,15 @@ iavf_dev_start(struct rte_eth_dev *dev)
                goto err_mac;
        }
 
+       if (dev->data->dev_conf.rxmode.offloads &
+           RTE_ETH_RX_OFFLOAD_TIMESTAMP) {
+               if (iavf_get_phc_time(adapter)) {
+                       PMD_DRV_LOG(ERR, "get physical time failed");
+                       goto err_mac;
+               }
+               adapter->hw_time_update = rte_get_timer_cycles() / (rte_get_timer_hz() / 1000);
+       }
+
        return 0;
 
 err_mac:

diff --git a/drivers/net/iavf/iavf_rxtx.c b/drivers/net/iavf/iavf_rxtx.c
index 4c731e7..345f6ae 100644 (file)
--- a/drivers/net/iavf/iavf_rxtx.c
+++ b/drivers/net/iavf/iavf_rxtx.c
@@ -1433,8 +1433,14 @@ iavf_recv_pkts_flex_rxd(void *rx_queue,
        struct iavf_adapter *ad = rxq->vsi->adapter;
        uint64_t ts_ns;
 
-       if (rxq->offloads & RTE_ETH_RX_OFFLOAD_TIMESTAMP)
-               rxq->hw_register_set = 1;
+       if (rxq->offloads & RTE_ETH_RX_OFFLOAD_TIMESTAMP) {
+               uint64_t sw_cur_time = rte_get_timer_cycles() / (rte_get_timer_hz() / 1000);
+               if (sw_cur_time - ad->hw_time_update > 4) {
+                       if (iavf_get_phc_time(ad))
+                               PMD_DRV_LOG(ERR, "get physical time failed");
+                       ad->hw_time_update = sw_cur_time;
+               }
+       }
 
        while (nb_rx < nb_pkts) {
                rxdp = (volatile union iavf_rx_flex_desc *)&rx_ring[rx_id];
@@ -1499,13 +1505,12 @@ iavf_recv_pkts_flex_rxd(void *rx_queue,
                pkt_flags = iavf_flex_rxd_error_to_pkt_flags(rx_stat_err0);
 
                if (iavf_timestamp_dynflag > 0) {
-                       if (rxq->hw_register_set)
-                               iavf_get_phc_time(ad);
-
-                       rxq->hw_register_set = 0;
                        ts_ns = iavf_tstamp_convert_32b_64b(ad->phc_time,
                                rte_le_to_cpu_32(rxd.wb.flex_ts.ts_high));
 
+                       ad->phc_time = ts_ns;
+                       ad->hw_time_update = rte_get_timer_cycles() / (rte_get_timer_hz() / 1000);
+
                        *RTE_MBUF_DYNFIELD(rxm,
                                iavf_timestamp_dynfield_offset,
                                rte_mbuf_timestamp_t *) = ts_ns;
@@ -1547,8 +1552,14 @@ iavf_recv_scattered_pkts_flex_rxd(void *rx_queue, struct rte_mbuf **rx_pkts,
        volatile union iavf_rx_flex_desc *rxdp;
        const uint32_t *ptype_tbl = rxq->vsi->adapter->ptype_tbl;
 
-       if (rxq->offloads & RTE_ETH_RX_OFFLOAD_TIMESTAMP)
-               rxq->hw_register_set = 1;
+       if (rxq->offloads & RTE_ETH_RX_OFFLOAD_TIMESTAMP) {
+               uint64_t sw_cur_time = rte_get_timer_cycles() / (rte_get_timer_hz() / 1000);
+               if (sw_cur_time - ad->hw_time_update > 4) {
+                       if (iavf_get_phc_time(ad))
+                               PMD_DRV_LOG(ERR, "get physical time failed");
+                       ad->hw_time_update = sw_cur_time;
+               }
+       }
 
        while (nb_rx < nb_pkts) {
                rxdp = (volatile union iavf_rx_flex_desc *)&rx_ring[rx_id];
@@ -1663,13 +1674,12 @@ iavf_recv_scattered_pkts_flex_rxd(void *rx_queue, struct rte_mbuf **rx_pkts,
                pkt_flags = iavf_flex_rxd_error_to_pkt_flags(rx_stat_err0);
 
                if (iavf_timestamp_dynflag > 0) {
-                       if (rxq->hw_register_set)
-                               iavf_get_phc_time(ad);
-
-                       rxq->hw_register_set = 0;
                        ts_ns = iavf_tstamp_convert_32b_64b(ad->phc_time,
                                rte_le_to_cpu_32(rxd.wb.flex_ts.ts_high));
 
+                       ad->phc_time = ts_ns;
+                       ad->hw_time_update = rte_get_timer_cycles() / (rte_get_timer_hz() / 1000);
+
                        *RTE_MBUF_DYNFIELD(first_seg,
                                iavf_timestamp_dynfield_offset,
                                rte_mbuf_timestamp_t *) = ts_ns;
@@ -1883,8 +1893,14 @@ iavf_rx_scan_hw_ring_flex_rxd(struct iavf_rx_queue *rxq,
        if (!(stat_err0 & (1 << IAVF_RX_FLEX_DESC_STATUS0_DD_S)))
                return 0;
 
-       if (rxq->offloads & RTE_ETH_RX_OFFLOAD_TIMESTAMP)
-               rxq->hw_register_set = 1;
+       if (rxq->offloads & RTE_ETH_RX_OFFLOAD_TIMESTAMP) {
+               uint64_t sw_cur_time = rte_get_timer_cycles() / (rte_get_timer_hz() / 1000);
+               if (sw_cur_time - ad->hw_time_update > 4) {
+                       if (iavf_get_phc_time(ad))
+                               PMD_DRV_LOG(ERR, "get physical time failed");
+                       ad->hw_time_update = sw_cur_time;
+               }
+       }
 
        /* Scan LOOK_AHEAD descriptors at a time to determine which
         * descriptors reference packets that are ready to be received.
@@ -1943,13 +1959,12 @@ iavf_rx_scan_hw_ring_flex_rxd(struct iavf_rx_queue *rxq,
                        pkt_flags = iavf_flex_rxd_error_to_pkt_flags(stat_err0);
 
                        if (iavf_timestamp_dynflag > 0) {
-                               if (rxq->hw_register_set)
-                                       iavf_get_phc_time(ad);
-
-                               rxq->hw_register_set = 0;
                                ts_ns = iavf_tstamp_convert_32b_64b(ad->phc_time,
                                        rte_le_to_cpu_32(rxdp[j].wb.flex_ts.ts_high));
 
+                               ad->phc_time = ts_ns;
+                               ad->hw_time_update = rte_get_timer_cycles() / (rte_get_timer_hz() / 1000);
+
                                *RTE_MBUF_DYNFIELD(mb,
                                        iavf_timestamp_dynfield_offset,
                                        rte_mbuf_timestamp_t *) = ts_ns;

diff --git a/drivers/net/iavf/iavf_rxtx.h b/drivers/net/iavf/iavf_rxtx.h
index 37453c4..642b9a7 100644 (file)
--- a/drivers/net/iavf/iavf_rxtx.h
+++ b/drivers/net/iavf/iavf_rxtx.h
@@ -222,7 +222,6 @@ struct iavf_rx_queue {
                /* flexible descriptor metadata extraction offload flag */
        struct iavf_rx_queue_stats stats;
        uint64_t offloads;
-       uint32_t hw_register_set;
 };
 
 struct iavf_tx_entry {