net/virtio: add vectorized packed ring NEON Tx

[dpdk.git] / drivers / net / i40e / i40e_rxtx_vec_neon.c

diff --git a/drivers/net/i40e/i40e_rxtx_vec_neon.c b/drivers/net/i40e/i40e_rxtx_vec_neon.c
index 67158f1..f094de6 100644 (file)
--- a/drivers/net/i40e/i40e_rxtx_vec_neon.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_neon.c
@@ -72,7 +72,7 @@ i40e_rxq_rearm(struct i40e_rx_queue *rxq)
        rx_id = (uint16_t)((rxq->rxrearm_start == 0) ?
                             (rxq->nb_rx_desc - 1) : (rxq->rxrearm_start - 1));
 
-       rte_cio_wmb();
+       rte_io_wmb();
        /* Update the tail pointer on the NIC */
        I40E_PCI_REG_WRITE_RELAXED(rxq->qrx_tail, rx_id);
 }
@@ -172,8 +172,8 @@ desc_to_olflags_v(struct i40e_rx_queue *rxq, uint64x2_t descs[4],
 #define I40E_UINT16_BIT (CHAR_BIT * sizeof(uint16_t))
 
 static inline void
-desc_to_ptype_v(uint64x2_t descs[4], struct rte_mbuf **__restrict rx_pkts,
-               uint32_t *__restrict ptype_tbl)
+desc_to_ptype_v(uint64x2_t descs[4], struct rte_mbuf **__rte_restrict rx_pkts,
+               uint32_t *__rte_restrict ptype_tbl)
 {
        int i;
        uint8_t ptype;
@@ -187,15 +187,17 @@ desc_to_ptype_v(uint64x2_t descs[4], struct rte_mbuf **__restrict rx_pkts,
 
 }
 
- /*
+/**
+ * vPMD raw receive routine, only accept(nb_pkts >= RTE_I40E_DESCS_PER_LOOP)
+ *
  * Notice:
  * - nb_pkts < RTE_I40E_DESCS_PER_LOOP, just return no packet
- * - nb_pkts > RTE_I40E_VPMD_RX_BURST, only scan RTE_I40E_VPMD_RX_BURST
- *   numbers of DD bits
+ * - floor align nb_pkts to a RTE_I40E_DESCS_PER_LOOP power-of-two
  */
 static inline uint16_t
-_recv_raw_pkts_vec(struct i40e_rx_queue *__restrict rxq, struct rte_mbuf
-       **__restrict rx_pkts, uint16_t nb_pkts, uint8_t *split_packet)
+_recv_raw_pkts_vec(struct i40e_rx_queue *__rte_restrict rxq,
+                  struct rte_mbuf **__rte_restrict rx_pkts,
+                  uint16_t nb_pkts, uint8_t *split_packet)
 {
        volatile union i40e_rx_desc *rxdp;
        struct i40e_rx_entry *sw_ring;
@@ -229,9 +231,6 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *__restrict rxq, struct rte_mbuf
                0, 0, 0       /* ignore non-length fields */
                };
 
-       /* nb_pkts shall be less equal than RTE_I40E_MAX_RX_BURST */
-       nb_pkts = RTE_MIN(nb_pkts, RTE_I40E_MAX_RX_BURST);
-
        /* nb_pkts has to be floor-aligned to RTE_I40E_DESCS_PER_LOOP */
        nb_pkts = RTE_ALIGN_FLOOR(nb_pkts, RTE_I40E_DESCS_PER_LOOP);
 
@@ -432,21 +431,21 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *__restrict rxq, struct rte_mbuf
  *   numbers of DD bits
  */
 uint16_t
-i40e_recv_pkts_vec(void *__restrict rx_queue,
-               struct rte_mbuf **__restrict rx_pkts, uint16_t nb_pkts)
+i40e_recv_pkts_vec(void *__rte_restrict rx_queue,
+               struct rte_mbuf **__rte_restrict rx_pkts, uint16_t nb_pkts)
 {
        return _recv_raw_pkts_vec(rx_queue, rx_pkts, nb_pkts, NULL);
 }
 
- /* vPMD receive routine that reassembles scattered packets
+/**
+ * vPMD receive routine that reassembles single burst of 32 scattered packets
+ *
  * Notice:
  * - nb_pkts < RTE_I40E_DESCS_PER_LOOP, just return no packet
- * - nb_pkts > RTE_I40E_VPMD_RX_BURST, only scan RTE_I40E_VPMD_RX_BURST
- *   numbers of DD bits
  */
-uint16_t
-i40e_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
-                            uint16_t nb_pkts)
+static uint16_t
+i40e_recv_scattered_burst_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+                             uint16_t nb_pkts)
 {
 
        struct i40e_rx_queue *rxq = rx_queue;
@@ -481,6 +480,32 @@ i40e_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
                &split_flags[i]);
 }
 
+/**
+ * vPMD receive routine that reassembles scattered packets.
+ */
+uint16_t
+i40e_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+                            uint16_t nb_pkts)
+{
+       uint16_t retval = 0;
+
+       while (nb_pkts > RTE_I40E_VPMD_RX_BURST) {
+               uint16_t burst;
+
+               burst = i40e_recv_scattered_burst_vec(rx_queue,
+                                                     rx_pkts + retval,
+                                                     RTE_I40E_VPMD_RX_BURST);
+               retval += burst;
+               nb_pkts -= burst;
+               if (burst < RTE_I40E_VPMD_RX_BURST)
+                       return retval;
+       }
+
+       return retval + i40e_recv_scattered_burst_vec(rx_queue,
+                                                     rx_pkts + retval,
+                                                     nb_pkts);
+}
+
 static inline void
 vtx1(volatile struct i40e_tx_desc *txdp,
                struct rte_mbuf *pkt, uint64_t flags)
@@ -504,8 +529,8 @@ vtx(volatile struct i40e_tx_desc *txdp, struct rte_mbuf **pkt,
 }
 
 uint16_t
-i40e_xmit_fixed_burst_vec(void *__restrict tx_queue,
-       struct rte_mbuf **__restrict tx_pkts, uint16_t nb_pkts)
+i40e_xmit_fixed_burst_vec(void *__rte_restrict tx_queue,
+       struct rte_mbuf **__rte_restrict tx_pkts, uint16_t nb_pkts)
 {
        struct i40e_tx_queue *txq = (struct i40e_tx_queue *)tx_queue;
        volatile struct i40e_tx_desc *txdp;
@@ -565,7 +590,7 @@ i40e_xmit_fixed_burst_vec(void *__restrict tx_queue,
 
        txq->tx_tail = tx_id;
 
-       rte_cio_wmb();
+       rte_io_wmb();
        I40E_PCI_REG_WRITE_RELAXED(txq->qtx_tail, tx_id);
 
        return nb_pkts;