app/testpmd: use Tx preparation in checksum engine

Since all current drivers supports Tx preparation API, it is used
in csum forwarding engine by default for all drivers.

Adding additional step to the csum engine costs about 3-4% of performance
drop, on my setup with ixgbe driver. It's caused mostly by the need
of reaccessing and modification of packet data.

Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>

diff --git a/app/test-pmd/csumonly.c b/app/test-pmd/csumonly.c
index dd67ebf..88cc842 100644 (file)
--- a/app/test-pmd/csumonly.c
+++ b/app/test-pmd/csumonly.c
@@ -112,15 +112,6 @@ struct simple_gre_hdr {
        uint16_t proto;
 } __attribute__((__packed__));
 
-static uint16_t
-get_psd_sum(void *l3_hdr, uint16_t ethertype, uint64_t ol_flags)
-{
-       if (ethertype == _htons(ETHER_TYPE_IPv4))
-               return rte_ipv4_phdr_cksum(l3_hdr, ol_flags);
-       else /* assume ethertype == ETHER_TYPE_IPv6 */
-               return rte_ipv6_phdr_cksum(l3_hdr, ol_flags);
-}
-
 static uint16_t
 get_udptcp_checksum(void *l3_hdr, void *l4_hdr, uint16_t ethertype)
 {
@@ -371,11 +362,9 @@ process_inner_cksums(void *l3_hdr, const struct testpmd_offload_info *info,
                /* do not recalculate udp cksum if it was 0 */
                if (udp_hdr->dgram_cksum != 0) {
                        udp_hdr->dgram_cksum = 0;
-                       if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_UDP_CKSUM) {
+                       if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_UDP_CKSUM)
                                ol_flags |= PKT_TX_UDP_CKSUM;
-                               udp_hdr->dgram_cksum = get_psd_sum(l3_hdr,
-                                       info->ethertype, ol_flags);
-                       } else {
+                       else {
                                udp_hdr->dgram_cksum =
                                        get_udptcp_checksum(l3_hdr, udp_hdr,
                                                info->ethertype);
@@ -384,15 +373,11 @@ process_inner_cksums(void *l3_hdr, const struct testpmd_offload_info *info,
        } else if (info->l4_proto == IPPROTO_TCP) {
                tcp_hdr = (struct tcp_hdr *)((char *)l3_hdr + info->l3_len);
                tcp_hdr->cksum = 0;
-               if (tso_segsz) {
+               if (tso_segsz)
                        ol_flags |= PKT_TX_TCP_SEG;
-                       tcp_hdr->cksum = get_psd_sum(l3_hdr, info->ethertype,
-                               ol_flags);
-               } else if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_TCP_CKSUM) {
+               else if (testpmd_ol_flags & TESTPMD_TX_OFFLOAD_TCP_CKSUM)
                        ol_flags |= PKT_TX_TCP_CKSUM;
-                       tcp_hdr->cksum = get_psd_sum(l3_hdr, info->ethertype,
-                               ol_flags);
-               } else {
+               else {
                        tcp_hdr->cksum =
                                get_udptcp_checksum(l3_hdr, tcp_hdr,
                                        info->ethertype);
@@ -649,6 +634,7 @@ pkt_burst_checksum_forward(struct fwd_stream *fs)
        void *l3_hdr = NULL, *outer_l3_hdr = NULL; /* can be IPv4 or IPv6 */
        uint16_t nb_rx;
        uint16_t nb_tx;
+       uint16_t nb_prep;
        uint16_t i;
        uint64_t rx_ol_flags, tx_ol_flags;
        uint16_t testpmd_ol_flags;
@@ -858,7 +844,16 @@ pkt_burst_checksum_forward(struct fwd_stream *fs)
                        printf("\n");
                }
        }
-       nb_tx = rte_eth_tx_burst(fs->tx_port, fs->tx_queue, pkts_burst, nb_rx);
+
+       nb_prep = rte_eth_tx_prepare(fs->tx_port, fs->tx_queue,
+                       pkts_burst, nb_rx);
+       if (nb_prep != nb_rx)
+               printf("Preparing packet burst to transmit failed: %s\n",
+                               rte_strerror(rte_errno));
+
+       nb_tx = rte_eth_tx_burst(fs->tx_port, fs->tx_queue, pkts_burst,
+                       nb_prep);
+
        /*
         * Retry if necessary
         */