net/tap: fix rx cksum flags on IP options packets

[dpdk.git] / drivers / net / tap / rte_eth_tap.c

diff --git a/drivers/net/tap/rte_eth_tap.c b/drivers/net/tap/rte_eth_tap.c
index 2d1e4e3..e7b185a 100644 (file)
--- a/drivers/net/tap/rte_eth_tap.c
+++ b/drivers/net/tap/rte_eth_tap.c
@@ -7,8 +7,8 @@
 #include <rte_byteorder.h>
 #include <rte_common.h>
 #include <rte_mbuf.h>
-#include <rte_ethdev_driver.h>
-#include <rte_ethdev_vdev.h>
+#include <ethdev_driver.h>
+#include <ethdev_vdev.h>
 #include <rte_malloc.h>
 #include <rte_bus_vdev.h>
 #include <rte_kvargs.h>
@@ -72,6 +72,10 @@
 
 static int tap_devices_count;
 
+static const char *tuntap_types[ETH_TUNTAP_TYPE_MAX] = {
+       "UNKNOWN", "TUN", "TAP"
+};
+
 static const char *valid_arguments[] = {
        ETH_TAP_IFACE_ARG,
        ETH_TAP_REMOTE_ARG,
@@ -299,6 +303,7 @@ tap_verify_csum(struct rte_mbuf *mbuf)
        uint16_t cksum = 0;
        void *l3_hdr;
        void *l4_hdr;
+       struct rte_udp_hdr *udp_hdr;
 
        if (l2 == RTE_PTYPE_L2_ETHER_VLAN)
                l2_len += 4;
@@ -312,8 +317,7 @@ tap_verify_csum(struct rte_mbuf *mbuf)
        if (l3 == RTE_PTYPE_L3_IPV4 || l3 == RTE_PTYPE_L3_IPV4_EXT) {
                struct rte_ipv4_hdr *iph = l3_hdr;
 
-               /* ihl contains the number of 4-byte words in the header */
-               l3_len = 4 * (iph->version_ihl & 0xf);
+               l3_len = rte_ipv4_hdr_len(iph);
                if (unlikely(l2_len + l3_len > rte_pktmbuf_data_len(mbuf)))
                        return;
                /* check that the total length reported by header is not
@@ -346,10 +350,23 @@ tap_verify_csum(struct rte_mbuf *mbuf)
                /* Don't verify checksum for multi-segment packets. */
                if (mbuf->nb_segs > 1)
                        return;
-               if (l3 == RTE_PTYPE_L3_IPV4)
+               if (l3 == RTE_PTYPE_L3_IPV4 || l3 == RTE_PTYPE_L3_IPV4_EXT) {
+                       if (l4 == RTE_PTYPE_L4_UDP) {
+                               udp_hdr = (struct rte_udp_hdr *)l4_hdr;
+                               if (udp_hdr->dgram_cksum == 0) {
+                                       /*
+                                        * For IPv4, a zero UDP checksum
+                                        * indicates that the sender did not
+                                        * generate one [RFC 768].
+                                        */
+                                       mbuf->ol_flags |= PKT_RX_L4_CKSUM_NONE;
+                                       return;
+                               }
+                       }
                        cksum = ~rte_ipv4_udptcp_cksum(l3_hdr, l4_hdr);
-               else if (l3 == RTE_PTYPE_L3_IPV6)
+               } else { /* l3 == RTE_PTYPE_L3_IPV6, checked above */
                        cksum = ~rte_ipv6_udptcp_cksum(l3_hdr, l4_hdr);
+               }
                mbuf->ol_flags |= cksum ?
                        PKT_RX_L4_CKSUM_BAD :
                        PKT_RX_L4_CKSUM_GOOD;
@@ -748,8 +765,16 @@ pmd_tx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
                        if (num_tso_mbufs < 0)
                                break;
 
-                       mbuf = gso_mbufs;
-                       num_mbufs = num_tso_mbufs;
+                       if (num_tso_mbufs >= 1) {
+                               mbuf = gso_mbufs;
+                               num_mbufs = num_tso_mbufs;
+                       } else {
+                               /* 0 means it can be transmitted directly
+                                * without gso.
+                                */
+                               mbuf = &mbuf_in;
+                               num_mbufs = 1;
+                       }
                } else {
                        /* stats.errs will be incremented */
                        if (rte_pktmbuf_pkt_len(mbuf_in) > max_size)
@@ -897,7 +922,7 @@ tap_dev_start(struct rte_eth_dev *dev)
 
 /* This function gets called when the current port gets stopped.
  */
-static void
+static int
 tap_dev_stop(struct rte_eth_dev *dev)
 {
        int i;
@@ -909,6 +934,8 @@ tap_dev_stop(struct rte_eth_dev *dev)
 
        tap_intr_handle_set(dev, 0);
        tap_link_set_down(dev);
+
+       return 0;
 }
 
 static int
@@ -1075,6 +1102,11 @@ tap_dev_close(struct rte_eth_dev *dev)
        struct pmd_process_private *process_private = dev->process_private;
        struct rx_queue *rxq;
 
+       if (rte_eal_process_type() != RTE_PROC_PRIMARY) {
+               rte_free(dev->process_private);
+               return 0;
+       }
+
        tap_link_set_down(dev);
        if (internals->nlsk_fd != -1) {
                tap_flow_flush(dev, NULL);
@@ -1112,6 +1144,22 @@ tap_dev_close(struct rte_eth_dev *dev)
                close(internals->ka_fd);
                internals->ka_fd = -1;
        }
+
+       /* mac_addrs must not be freed alone because part of dev_private */
+       dev->data->mac_addrs = NULL;
+
+       internals = dev->data->dev_private;
+       TAP_LOG(DEBUG, "Closing %s Ethernet device on numa %u",
+               tuntap_types[internals->type], rte_socket_id());
+
+       if (internals->ioctl_sock != -1) {
+               close(internals->ioctl_sock);
+               internals->ioctl_sock = -1;
+       }
+       rte_free(dev->process_private);
+       if (tap_devices_count == 1)
+               rte_mp_action_unregister(TAP_MP_KEY);
+       tap_devices_count--;
        /*
         * Since TUN device has no more opened file descriptors
         * it will be removed from kernel
@@ -1842,11 +1890,7 @@ static const struct eth_dev_ops ops = {
        .stats_reset            = tap_stats_reset,
        .dev_supported_ptypes_get = tap_dev_supported_ptypes_get,
        .rss_hash_update        = tap_rss_hash_update,
-       .filter_ctrl            = tap_dev_filter_ctrl,
-};
-
-static const char *tuntap_types[ETH_TUNTAP_TYPE_MAX] = {
-       "UNKNOWN", "TUN", "TAP"
+       .flow_ops_get           = tap_dev_flow_ops_get,
 };
 
 static int
@@ -1900,7 +1944,8 @@ eth_dev_tap_create(struct rte_vdev_device *vdev, const char *tap_name,
        /* Setup some default values */
        data = dev->data;
        data->dev_private = pmd;
-       data->dev_flags = RTE_ETH_DEV_INTR_LSC;
+       data->dev_flags = RTE_ETH_DEV_INTR_LSC |
+                               RTE_ETH_DEV_AUTOFILL_QUEUE_XSTATS;
        data->numa_node = numa_node;
 
        data->dev_link = pmd_link;
@@ -2492,30 +2537,13 @@ static int
 rte_pmd_tap_remove(struct rte_vdev_device *dev)
 {
        struct rte_eth_dev *eth_dev = NULL;
-       struct pmd_internals *internals;
 
        /* find the ethdev entry */
        eth_dev = rte_eth_dev_allocated(rte_vdev_device_name(dev));
        if (!eth_dev)
-               return -ENODEV;
-
-       /* mac_addrs must not be freed alone because part of dev_private */
-       eth_dev->data->mac_addrs = NULL;
-
-       if (rte_eal_process_type() != RTE_PROC_PRIMARY)
-               return rte_eth_dev_release_port(eth_dev);
+               return 0;
 
        tap_dev_close(eth_dev);
-
-       internals = eth_dev->data->dev_private;
-       TAP_LOG(DEBUG, "Closing %s Ethernet device on numa %u",
-               tuntap_types[internals->type], rte_socket_id());
-
-       close(internals->ioctl_sock);
-       rte_free(eth_dev->process_private);
-       if (tap_devices_count == 1)
-               rte_mp_action_unregister(TAP_MP_KEY);
-       tap_devices_count--;
        rte_eth_dev_release_port(eth_dev);
 
        return 0;