net/i40e: fix global register recovery

[dpdk.git] / drivers / net / i40e / i40e_rxtx_vec_sse.c

diff --git a/drivers/net/i40e/i40e_rxtx_vec_sse.c b/drivers/net/i40e/i40e_rxtx_vec_sse.c
index 6ab0bb0..0bcb48e 100644 (file)
--- a/drivers/net/i40e/i40e_rxtx_vec_sse.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_sse.c
@@ -86,7 +86,7 @@ i40e_rxq_rearm(struct i40e_rx_queue *rxq)
                             (rxq->nb_rx_desc - 1) : (rxq->rxrearm_start - 1));
 
        /* Update the tail pointer on the NIC */
-       I40E_PCI_REG_WRITE(rxq->qrx_tail, rx_id);
+       I40E_PCI_REG_WC_WRITE(rxq->qrx_tail, rx_id);
 }
 
 #ifndef RTE_LIBRTE_I40E_16BYTE_RX_DESC
@@ -254,16 +254,18 @@ desc_to_olflags_v(struct i40e_rx_queue *rxq, volatile union i40e_rx_desc *rxdp,
 
        const __m128i l3_l4e_flags = _mm_set_epi8(0, 0, 0, 0, 0, 0, 0, 0,
                        /* shift right 1 bit to make sure it not exceed 255 */
-                       (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
+                       (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD  |
                         PKT_RX_IP_CKSUM_BAD) >> 1,
-                       (PKT_RX_IP_CKSUM_GOOD | PKT_RX_EIP_CKSUM_BAD |
-                        PKT_RX_L4_CKSUM_BAD) >> 1,
-                       (PKT_RX_EIP_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
-                       (PKT_RX_IP_CKSUM_GOOD | PKT_RX_EIP_CKSUM_BAD) >> 1,
-                       (PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
-                       (PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD) >> 1,
-                       PKT_RX_IP_CKSUM_BAD >> 1,
-                       (PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_GOOD) >> 1);
+                       (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD  |
+                        PKT_RX_IP_CKSUM_GOOD) >> 1,
+                       (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD |
+                        PKT_RX_IP_CKSUM_BAD) >> 1,
+                       (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD |
+                        PKT_RX_IP_CKSUM_GOOD) >> 1,
+                       (PKT_RX_L4_CKSUM_BAD  | PKT_RX_IP_CKSUM_BAD) >> 1,
+                       (PKT_RX_L4_CKSUM_BAD  | PKT_RX_IP_CKSUM_GOOD) >> 1,
+                       (PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD) >> 1,
+                       (PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_GOOD) >> 1);
 
        /* Unpack "status" from quadword 1, bits 0:32 */
        vlan0 = _mm_unpackhi_epi32(descs[0], descs[1]);
@@ -342,11 +344,12 @@ desc_to_ptype_v(__m128i descs[4], struct rte_mbuf **rx_pkts,
        rx_pkts[3]->packet_type = ptype_tbl[_mm_extract_epi8(ptype1, 8)];
 }
 
- /*
+/**
+ * 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 *rxq, struct rte_mbuf **rx_pkts,
@@ -378,9 +381,6 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_pkts,
                        offsetof(struct rte_mbuf, rx_descriptor_fields1) + 8);
        __m128i dd_check, eop_check;
 
-       /* 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);
 
@@ -605,15 +605,15 @@ i40e_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_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;
@@ -648,6 +648,32 @@ 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)
@@ -733,30 +759,30 @@ i40e_xmit_fixed_burst_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
 
        txq->tx_tail = tx_id;
 
-       I40E_PCI_REG_WRITE(txq->qtx_tail, txq->tx_tail);
+       I40E_PCI_REG_WC_WRITE(txq->qtx_tail, txq->tx_tail);
 
        return nb_pkts;
 }
 
-void __attribute__((cold))
+void __rte_cold
 i40e_rx_queue_release_mbufs_vec(struct i40e_rx_queue *rxq)
 {
        _i40e_rx_queue_release_mbufs_vec(rxq);
 }
 
-int __attribute__((cold))
+int __rte_cold
 i40e_rxq_vec_setup(struct i40e_rx_queue *rxq)
 {
        return i40e_rxq_vec_setup_default(rxq);
 }
 
-int __attribute__((cold))
+int __rte_cold
 i40e_txq_vec_setup(struct i40e_tx_queue __rte_unused *txq)
 {
        return 0;
 }
 
-int __attribute__((cold))
+int __rte_cold
 i40e_rx_vec_dev_conf_condition_check(struct rte_eth_dev *dev)
 {
        return i40e_rx_vec_dev_conf_condition_check_default(dev);