net/bnxt: update TruFlow core index table

[dpdk.git] / drivers / net / fm10k / fm10k_rxtx_vec.c

diff --git a/drivers/net/fm10k/fm10k_rxtx_vec.c b/drivers/net/fm10k/fm10k_rxtx_vec.c
index d76dfd1..83af01d 100644 (file)
--- a/drivers/net/fm10k/fm10k_rxtx_vec.c
+++ b/drivers/net/fm10k/fm10k_rxtx_vec.c
@@ -4,7 +4,7 @@
 
 #include <inttypes.h>
 
-#include <rte_ethdev_driver.h>
+#include <ethdev_driver.h>
 #include <rte_common.h>
 #include "fm10k.h"
 #include "base/fm10k_type.h"
@@ -203,7 +203,7 @@ fm10k_desc_to_pktype_v(__m128i descs[4], struct rte_mbuf **rx_pkts)
 #define fm10k_desc_to_pktype_v(desc, rx_pkts) do {} while (0)
 #endif
 
-int __attribute__((cold))
+int __rte_cold
 fm10k_rx_vec_condition_check(struct rte_eth_dev *dev)
 {
 #ifndef RTE_LIBRTE_IEEE1588
@@ -231,7 +231,7 @@ fm10k_rx_vec_condition_check(struct rte_eth_dev *dev)
 #endif
 }
 
-int __attribute__((cold))
+int __rte_cold
 fm10k_rxq_vec_setup(struct fm10k_rx_queue *rxq)
 {
        uintptr_t p;
@@ -349,7 +349,7 @@ fm10k_rxq_rearm(struct fm10k_rx_queue *rxq)
        FM10K_PCI_REG_WRITE(rxq->tail_ptr, rx_id);
 }
 
-void __attribute__((cold))
+void __rte_cold
 fm10k_rx_queue_release_mbufs_vec(struct fm10k_rx_queue *rxq)
 {
        const unsigned mask = rxq->nb_desc - 1;
@@ -472,7 +472,7 @@ fm10k_recv_raw_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
                mbp1 = _mm_loadu_si128((__m128i *)&mbufp[pos]);
 
                /* Read desc statuses backwards to avoid race condition */
-               /* A.1 load 4 pkts desc */
+               /* A.1 load desc[3] */
                descs0[3] = _mm_loadu_si128((__m128i *)(rxdp + 3));
                rte_compiler_barrier();
 
@@ -484,9 +484,9 @@ fm10k_recv_raw_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
                mbp2 = _mm_loadu_si128((__m128i *)&mbufp[pos+2]);
 #endif
 
+               /* A.1 load desc[2-0] */
                descs0[2] = _mm_loadu_si128((__m128i *)(rxdp + 2));
                rte_compiler_barrier();
-               /* B.1 load 2 mbuf point */
                descs0[1] = _mm_loadu_si128((__m128i *)(rxdp + 1));
                rte_compiler_barrier();
                descs0[0] = _mm_loadu_si128((__m128i *)(rxdp));
@@ -544,7 +544,7 @@ fm10k_recv_raw_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
                        /* and with mask to extract bits, flipping 1-0 */
                        __m128i eop_bits = _mm_andnot_si128(staterr, eop_check);
                        /* the staterr values are not in order, as the count
-                        * count of dd bits doesn't care. However, for end of
+                        * of dd bits doesn't care. However, for end of
                         * packet tracking, we do care, so shuffle. This also
                         * compresses the 32-bit values to 8-bit
                         */
@@ -645,18 +645,15 @@ fm10k_reassemble_packets(struct fm10k_rx_queue *rxq,
        return pkt_idx;
 }
 
-/*
- * vPMD receive routine that reassembles scattered packets
+/**
+ * vPMD receive routine that reassembles single burst of 32 scattered packets
  *
  * Notice:
  * - don't support ol_flags for rss and csum err
- * - nb_pkts > RTE_FM10K_MAX_RX_BURST, only scan RTE_FM10K_MAX_RX_BURST
- *   numbers of DD bit
  */
-uint16_t
-fm10k_recv_scattered_pkts_vec(void *rx_queue,
-                               struct rte_mbuf **rx_pkts,
-                               uint16_t nb_pkts)
+static uint16_t
+fm10k_recv_scattered_burst_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+                              uint16_t nb_pkts)
 {
        struct fm10k_rx_queue *rxq = rx_queue;
        uint8_t split_flags[RTE_FM10K_MAX_RX_BURST] = {0};
@@ -691,17 +688,43 @@ fm10k_recv_scattered_pkts_vec(void *rx_queue,
                &split_flags[i]);
 }
 
+/**
+ * vPMD receive routine that reassembles scattered packets.
+ */
+uint16_t
+fm10k_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+                             uint16_t nb_pkts)
+{
+       uint16_t retval = 0;
+
+       while (nb_pkts > RTE_FM10K_MAX_RX_BURST) {
+               uint16_t burst;
+
+               burst = fm10k_recv_scattered_burst_vec(rx_queue,
+                                                      rx_pkts + retval,
+                                                      RTE_FM10K_MAX_RX_BURST);
+               retval += burst;
+               nb_pkts -= burst;
+               if (burst < RTE_FM10K_MAX_RX_BURST)
+                       return retval;
+       }
+
+       return retval + fm10k_recv_scattered_burst_vec(rx_queue,
+                                                      rx_pkts + retval,
+                                                      nb_pkts);
+}
+
 static const struct fm10k_txq_ops vec_txq_ops = {
        .reset = fm10k_reset_tx_queue,
 };
 
-void __attribute__((cold))
+void __rte_cold
 fm10k_txq_vec_setup(struct fm10k_tx_queue *txq)
 {
        txq->ops = &vec_txq_ops;
 }
 
-int __attribute__((cold))
+int __rte_cold
 fm10k_tx_vec_condition_check(struct fm10k_tx_queue *txq)
 {
        /* Vector TX can't offload any features yet */
@@ -864,7 +887,7 @@ fm10k_xmit_fixed_burst_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
        return nb_pkts;
 }
 
-static void __attribute__((cold))
+static void __rte_cold
 fm10k_reset_tx_queue(struct fm10k_tx_queue *txq)
 {
        static const struct fm10k_tx_desc zeroed_desc = {0};