-/*-
- * BSD LICENSE
- *
- * Copyright(c) 2016-2017 Intel Corporation. All rights reserved.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2016-2017 Intel Corporation
*/
#include <rte_atomic.h>
#include <rte_byteorder.h>
#include <rte_common.h>
#include <rte_mbuf.h>
-#include <rte_ethdev.h>
+#include <rte_ethdev_driver.h>
#include <rte_ethdev_vdev.h>
#include <rte_malloc.h>
-#include <rte_vdev.h>
+#include <rte_bus_vdev.h>
#include <rte_kvargs.h>
#include <rte_net.h>
#include <rte_debug.h>
#include <rte_ip.h>
+#include <rte_string_fns.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/mman.h>
#include <errno.h>
#include <signal.h>
+#include <stdbool.h>
#include <stdint.h>
#include <sys/uio.h>
#include <unistd.h>
#include <net/if.h>
#include <linux/if_tun.h>
#include <linux/if_ether.h>
-#include <linux/version.h>
#include <fcntl.h>
#include <rte_eth_tap.h>
#define DEFAULT_TAP_NAME "dtap"
#define ETH_TAP_IFACE_ARG "iface"
-#define ETH_TAP_SPEED_ARG "speed"
#define ETH_TAP_REMOTE_ARG "remote"
#define ETH_TAP_MAC_ARG "mac"
#define ETH_TAP_MAC_FIXED "fixed"
-#define FLOWER_KERNEL_VERSION KERNEL_VERSION(4, 2, 0)
-#define FLOWER_VLAN_KERNEL_VERSION KERNEL_VERSION(4, 9, 0)
+#define ETH_TAP_USR_MAC_FMT "xx:xx:xx:xx:xx:xx"
+#define ETH_TAP_CMP_MAC_FMT "0123456789ABCDEFabcdef"
+#define ETH_TAP_MAC_ARG_FMT ETH_TAP_MAC_FIXED "|" ETH_TAP_USR_MAC_FMT
static struct rte_vdev_driver pmd_tap_drv;
static const char *valid_arguments[] = {
ETH_TAP_IFACE_ARG,
- ETH_TAP_SPEED_ARG,
ETH_TAP_REMOTE_ARG,
ETH_TAP_MAC_ARG,
NULL
.link_speed = ETH_SPEED_NUM_10G,
.link_duplex = ETH_LINK_FULL_DUPLEX,
.link_status = ETH_LINK_DOWN,
- .link_autoneg = ETH_LINK_SPEED_AUTONEG
+ .link_autoneg = ETH_LINK_AUTONEG
};
static void
}
}
+static uint64_t
+tap_rx_offload_get_port_capa(void)
+{
+ /*
+ * In order to support legacy apps,
+ * report capabilities also as port capabilities.
+ */
+ return DEV_RX_OFFLOAD_SCATTER |
+ DEV_RX_OFFLOAD_IPV4_CKSUM |
+ DEV_RX_OFFLOAD_UDP_CKSUM |
+ DEV_RX_OFFLOAD_TCP_CKSUM |
+ DEV_RX_OFFLOAD_CRC_STRIP;
+}
+
+static uint64_t
+tap_rx_offload_get_queue_capa(void)
+{
+ return DEV_RX_OFFLOAD_SCATTER |
+ DEV_RX_OFFLOAD_IPV4_CKSUM |
+ DEV_RX_OFFLOAD_UDP_CKSUM |
+ DEV_RX_OFFLOAD_TCP_CKSUM |
+ DEV_RX_OFFLOAD_CRC_STRIP;
+}
+
+static bool
+tap_rxq_are_offloads_valid(struct rte_eth_dev *dev, uint64_t offloads)
+{
+ uint64_t port_offloads = dev->data->dev_conf.rxmode.offloads;
+ uint64_t queue_supp_offloads = tap_rx_offload_get_queue_capa();
+ uint64_t port_supp_offloads = tap_rx_offload_get_port_capa();
+
+ if ((offloads & (queue_supp_offloads | port_supp_offloads)) !=
+ offloads)
+ return false;
+ if ((port_offloads ^ offloads) & port_supp_offloads)
+ return false;
+ return true;
+}
+
/* Callback to handle the rx burst of packets to the correct interface and
* file descriptor(s) in a multi-queue setup.
*/
int len;
len = readv(rxq->fd, *rxq->iovecs,
- 1 + (rxq->rxmode->enable_scatter ?
- rxq->nb_rx_desc : 1));
+ 1 +
+ (rxq->rxmode->offloads & DEV_RX_OFFLOAD_SCATTER ?
+ rxq->nb_rx_desc : 1));
if (len < (int)sizeof(struct tun_pi))
break;
seg->next = NULL;
mbuf->packet_type = rte_net_get_ptype(mbuf, NULL,
RTE_PTYPE_ALL_MASK);
- if (rxq->rxmode->hw_ip_checksum)
+ if (rxq->rxmode->offloads & DEV_RX_OFFLOAD_CHECKSUM)
tap_verify_csum(mbuf);
/* account for the receive frame */
return num_rx;
}
+static uint64_t
+tap_tx_offload_get_port_capa(void)
+{
+ /*
+ * In order to support legacy apps,
+ * report capabilities also as port capabilities.
+ */
+ return DEV_TX_OFFLOAD_MULTI_SEGS |
+ DEV_TX_OFFLOAD_IPV4_CKSUM |
+ DEV_TX_OFFLOAD_UDP_CKSUM |
+ DEV_TX_OFFLOAD_TCP_CKSUM;
+}
+
+static uint64_t
+tap_tx_offload_get_queue_capa(void)
+{
+ return DEV_TX_OFFLOAD_MULTI_SEGS |
+ DEV_TX_OFFLOAD_IPV4_CKSUM |
+ DEV_TX_OFFLOAD_UDP_CKSUM |
+ DEV_TX_OFFLOAD_TCP_CKSUM;
+}
+
+static bool
+tap_txq_are_offloads_valid(struct rte_eth_dev *dev, uint64_t offloads)
+{
+ uint64_t port_offloads = dev->data->dev_conf.txmode.offloads;
+ uint64_t queue_supp_offloads = tap_tx_offload_get_queue_capa();
+ uint64_t port_supp_offloads = tap_tx_offload_get_port_capa();
+
+ if ((offloads & (queue_supp_offloads | port_supp_offloads)) !=
+ offloads)
+ return false;
+ /* Verify we have no conflict with port offloads */
+ if ((port_offloads ^ offloads) & port_supp_offloads)
+ return false;
+ return true;
+}
+
static void
tap_tx_offload(char *packet, uint64_t ol_flags, unsigned int l2_len,
unsigned int l3_len)
rte_pktmbuf_mtod(seg, void *);
seg = seg->next;
}
- if (mbuf->ol_flags & (PKT_TX_IP_CKSUM | PKT_TX_IPV4) ||
- (mbuf->ol_flags & PKT_TX_L4_MASK) == PKT_TX_UDP_CKSUM ||
- (mbuf->ol_flags & PKT_TX_L4_MASK) == PKT_TX_TCP_CKSUM) {
+ if (txq->csum &&
+ ((mbuf->ol_flags & (PKT_TX_IP_CKSUM | PKT_TX_IPV4) ||
+ (mbuf->ol_flags & PKT_TX_L4_MASK) == PKT_TX_UDP_CKSUM ||
+ (mbuf->ol_flags & PKT_TX_L4_MASK) == PKT_TX_TCP_CKSUM))) {
/* Support only packets with all data in the same seg */
if (mbuf->nb_segs > 1)
break;
static int
tap_dev_configure(struct rte_eth_dev *dev)
{
+ uint64_t supp_tx_offloads = tap_tx_offload_get_port_capa();
+ uint64_t tx_offloads = dev->data->dev_conf.txmode.offloads;
+
+ if ((tx_offloads & supp_tx_offloads) != tx_offloads) {
+ rte_errno = ENOTSUP;
+ RTE_LOG(ERR, PMD,
+ "Some Tx offloads are not supported "
+ "requested 0x%" PRIx64 " supported 0x%" PRIx64 "\n",
+ tx_offloads, supp_tx_offloads);
+ return -rte_errno;
+ }
if (dev->data->nb_rx_queues > RTE_PMD_TAP_MAX_QUEUES) {
RTE_LOG(ERR, PMD,
"%s: number of rx queues %d exceeds max num of queues %d\n",
dev_info->min_rx_bufsize = 0;
dev_info->pci_dev = NULL;
dev_info->speed_capa = tap_dev_speed_capa();
- dev_info->rx_offload_capa = (DEV_RX_OFFLOAD_IPV4_CKSUM |
- DEV_RX_OFFLOAD_UDP_CKSUM |
- DEV_RX_OFFLOAD_TCP_CKSUM);
- dev_info->tx_offload_capa =
- (DEV_TX_OFFLOAD_IPV4_CKSUM |
- DEV_TX_OFFLOAD_UDP_CKSUM |
- DEV_TX_OFFLOAD_TCP_CKSUM);
+ dev_info->rx_queue_offload_capa = tap_rx_offload_get_queue_capa();
+ dev_info->rx_offload_capa = tap_rx_offload_get_port_capa() |
+ dev_info->rx_queue_offload_capa;
+ dev_info->tx_queue_offload_capa = tap_tx_offload_get_queue_capa();
+ dev_info->tx_offload_capa = tap_tx_offload_get_port_capa() |
+ dev_info->tx_queue_offload_capa;
}
static int
return -1;
}
+ /* Verify application offloads are valid for our port and queue. */
+ if (!tap_rxq_are_offloads_valid(dev, rx_conf->offloads)) {
+ rte_errno = ENOTSUP;
+ RTE_LOG(ERR, PMD,
+ "%p: Rx queue offloads 0x%" PRIx64
+ " don't match port offloads 0x%" PRIx64
+ " or supported offloads 0x%" PRIx64 "\n",
+ (void *)dev, rx_conf->offloads,
+ dev->data->dev_conf.rxmode.offloads,
+ (tap_rx_offload_get_port_capa() |
+ tap_rx_offload_get_queue_capa()));
+ return -rte_errno;
+ }
rxq->mp = mp;
rxq->trigger_seen = 1; /* force initial burst */
rxq->in_port = dev->data->port_id;
uint16_t tx_queue_id,
uint16_t nb_tx_desc __rte_unused,
unsigned int socket_id __rte_unused,
- const struct rte_eth_txconf *tx_conf __rte_unused)
+ const struct rte_eth_txconf *tx_conf)
{
struct pmd_internals *internals = dev->data->dev_private;
+ struct tx_queue *txq;
int ret;
if (tx_queue_id >= dev->data->nb_tx_queues)
return -1;
-
dev->data->tx_queues[tx_queue_id] = &internals->txq[tx_queue_id];
+ txq = dev->data->tx_queues[tx_queue_id];
+ /*
+ * Don't verify port offloads for application which
+ * use the old API.
+ */
+ if (tx_conf != NULL &&
+ !!(tx_conf->txq_flags & ETH_TXQ_FLAGS_IGNORE)) {
+ if (tap_txq_are_offloads_valid(dev, tx_conf->offloads)) {
+ txq->csum = !!(tx_conf->offloads &
+ (DEV_TX_OFFLOAD_IPV4_CKSUM |
+ DEV_TX_OFFLOAD_UDP_CKSUM |
+ DEV_TX_OFFLOAD_TCP_CKSUM));
+ } else {
+ rte_errno = ENOTSUP;
+ RTE_LOG(ERR, PMD,
+ "%p: Tx queue offloads 0x%" PRIx64
+ " don't match port offloads 0x%" PRIx64
+ " or supported offloads 0x%" PRIx64,
+ (void *)dev, tx_conf->offloads,
+ dev->data->dev_conf.txmode.offloads,
+ tap_tx_offload_get_port_capa());
+ return -rte_errno;
+ }
+ }
ret = tap_setup_queue(dev, internals, tx_queue_id, 0);
if (ret == -1)
return -1;
-
- RTE_LOG(DEBUG, PMD, " TX TAP device name %s, qid %d on fd %d\n",
- internals->name, tx_queue_id, internals->txq[tx_queue_id].fd);
+ RTE_LOG(DEBUG, PMD,
+ " TX TAP device name %s, qid %d on fd %d csum %s\n",
+ internals->name, tx_queue_id, internals->txq[tx_queue_id].fd,
+ txq->csum ? "on" : "off");
return 0;
}
struct rte_eth_dev *dev = cb_arg;
struct pmd_internals *pmd = dev->data->dev_private;
- nl_recv(pmd->intr_handle.fd, tap_nl_msg_handler, dev);
+ tap_nl_recv(pmd->intr_handle.fd, tap_nl_msg_handler, dev);
}
static int
-tap_intr_handle_set(struct rte_eth_dev *dev, int set)
+tap_lsc_intr_handle_set(struct rte_eth_dev *dev, int set)
{
struct pmd_internals *pmd = dev->data->dev_private;
/* In any case, disable interrupt if the conf is no longer there. */
if (!dev->data->dev_conf.intr_conf.lsc) {
if (pmd->intr_handle.fd != -1) {
- nl_final(pmd->intr_handle.fd);
+ tap_nl_final(pmd->intr_handle.fd);
rte_intr_callback_unregister(&pmd->intr_handle,
tap_dev_intr_handler, dev);
}
return 0;
}
if (set) {
- pmd->intr_handle.fd = nl_init(RTMGRP_LINK);
+ pmd->intr_handle.fd = tap_nl_init(RTMGRP_LINK);
if (unlikely(pmd->intr_handle.fd == -1))
return -EBADF;
return rte_intr_callback_register(
&pmd->intr_handle, tap_dev_intr_handler, dev);
}
- nl_final(pmd->intr_handle.fd);
+ tap_nl_final(pmd->intr_handle.fd);
return rte_intr_callback_unregister(&pmd->intr_handle,
tap_dev_intr_handler, dev);
}
+static int
+tap_intr_handle_set(struct rte_eth_dev *dev, int set)
+{
+ int err;
+
+ err = tap_lsc_intr_handle_set(dev, set);
+ if (err)
+ return err;
+ err = tap_rx_intr_vec_set(dev, set);
+ if (err && set)
+ tap_lsc_intr_handle_set(dev, 0);
+ return err;
+}
+
static const uint32_t*
tap_dev_supported_ptypes_get(struct rte_eth_dev *dev __rte_unused)
{
static int
eth_dev_tap_create(struct rte_vdev_device *vdev, char *tap_name,
- char *remote_iface, int fixed_mac_type)
+ char *remote_iface, struct ether_addr *mac_addr)
{
int numa_node = rte_socket_id();
struct rte_eth_dev *dev;
data = rte_zmalloc_socket(tap_name, sizeof(*data), 0, numa_node);
if (!data) {
RTE_LOG(ERR, PMD, "TAP Failed to allocate data\n");
- goto error_exit;
+ goto error_exit_nodev;
}
dev = rte_eth_vdev_allocate(vdev, sizeof(*pmd));
if (!dev) {
RTE_LOG(ERR, PMD, "TAP Unable to allocate device struct\n");
- goto error_exit;
+ goto error_exit_nodev;
}
pmd = dev->data->dev_private;
/* Setup some default values */
rte_memcpy(data, dev->data, sizeof(*data));
data->dev_private = pmd;
- data->dev_flags = RTE_ETH_DEV_DETACHABLE | RTE_ETH_DEV_INTR_LSC;
+ data->dev_flags = RTE_ETH_DEV_INTR_LSC;
data->numa_node = numa_node;
data->dev_link = pmd_link;
pmd->intr_handle.type = RTE_INTR_HANDLE_EXT;
pmd->intr_handle.fd = -1;
+ dev->intr_handle = &pmd->intr_handle;
/* Presetup the fds to -1 as being not valid */
for (i = 0; i < RTE_PMD_TAP_MAX_QUEUES; i++) {
pmd->txq[i].fd = -1;
}
- if (fixed_mac_type) {
- /* fixed mac = 00:64:74:61:70:<iface_idx> */
- static int iface_idx;
- char mac[ETHER_ADDR_LEN] = "\0dtap";
-
- mac[ETHER_ADDR_LEN - 1] = iface_idx++;
- rte_memcpy(&pmd->eth_addr, mac, ETHER_ADDR_LEN);
- } else {
+ if (is_zero_ether_addr(mac_addr))
eth_random_addr((uint8_t *)&pmd->eth_addr);
- }
+ else
+ rte_memcpy(&pmd->eth_addr, mac_addr, sizeof(mac_addr));
/* Immediately create the netdevice (this will create the 1st queue). */
/* rx queue */
* - rte_flow actual/implicit lists
* - implicit rules
*/
- pmd->nlsk_fd = nl_init(0);
+ pmd->nlsk_fd = tap_nl_init(0);
if (pmd->nlsk_fd == -1) {
RTE_LOG(WARNING, PMD, "%s: failed to create netlink socket.\n",
pmd->name);
tap_flow_implicit_flush(pmd, NULL);
error_exit:
+ if (pmd->ioctl_sock > 0)
+ close(pmd->ioctl_sock);
+ rte_eth_dev_release_port(dev);
+
+error_exit_nodev:
RTE_LOG(ERR, PMD, "TAP Unable to initialize %s\n",
rte_vdev_device_name(vdev));
char *name = (char *)extra_args;
if (value)
- snprintf(name, RTE_ETH_NAME_MAX_LEN - 1, "%s", value);
+ strlcpy(name, value, RTE_ETH_NAME_MAX_LEN - 1);
else
snprintf(name, RTE_ETH_NAME_MAX_LEN - 1, "%s%d",
DEFAULT_TAP_NAME, (tap_unit - 1));
return 0;
}
-static int
-set_interface_speed(const char *key __rte_unused,
- const char *value,
- void *extra_args)
-{
- *(int *)extra_args = (value) ? atoi(value) : ETH_SPEED_NUM_10G;
-
- return 0;
-}
-
static int
set_remote_iface(const char *key __rte_unused,
const char *value,
char *name = (char *)extra_args;
if (value)
- snprintf(name, RTE_ETH_NAME_MAX_LEN, "%s", value);
+ strlcpy(name, value, RTE_ETH_NAME_MAX_LEN);
return 0;
}
+static int parse_user_mac(struct ether_addr *user_mac,
+ const char *value)
+{
+ unsigned int index = 0;
+ char mac_temp[strlen(ETH_TAP_USR_MAC_FMT) + 1], *mac_byte = NULL;
+
+ if (user_mac == NULL || value == NULL)
+ return 0;
+
+ strlcpy(mac_temp, value, sizeof(mac_temp));
+ mac_byte = strtok(mac_temp, ":");
+
+ while ((mac_byte != NULL) &&
+ (strlen(mac_byte) <= 2) &&
+ (strlen(mac_byte) == strspn(mac_byte,
+ ETH_TAP_CMP_MAC_FMT))) {
+ user_mac->addr_bytes[index++] = strtoul(mac_byte, NULL, 16);
+ mac_byte = strtok(NULL, ":");
+ }
+
+ return index;
+}
+
static int
set_mac_type(const char *key __rte_unused,
const char *value,
void *extra_args)
{
- if (value &&
- !strncasecmp(ETH_TAP_MAC_FIXED, value, strlen(ETH_TAP_MAC_FIXED)))
- *(int *)extra_args = 1;
+ struct ether_addr *user_mac = extra_args;
+
+ if (!value)
+ return 0;
+
+ if (!strncasecmp(ETH_TAP_MAC_FIXED, value, strlen(ETH_TAP_MAC_FIXED))) {
+ static int iface_idx;
+
+ /* fixed mac = 00:64:74:61:70:<iface_idx> */
+ memcpy((char *)user_mac->addr_bytes, "\0dtap", ETHER_ADDR_LEN);
+ user_mac->addr_bytes[ETHER_ADDR_LEN - 1] = iface_idx++ + '0';
+ goto success;
+ }
+
+ if (parse_user_mac(user_mac, value) != 6)
+ goto error;
+success:
+ RTE_LOG(DEBUG, PMD, "TAP user MAC param (%s)\n", value);
return 0;
+
+error:
+ RTE_LOG(ERR, PMD, "TAP user MAC (%s) is not in format (%s|%s)\n",
+ value, ETH_TAP_MAC_FIXED, ETH_TAP_USR_MAC_FMT);
+ return -1;
}
/* Open a TAP interface device.
int speed;
char tap_name[RTE_ETH_NAME_MAX_LEN];
char remote_iface[RTE_ETH_NAME_MAX_LEN];
- int fixed_mac_type = 0;
+ struct ether_addr user_mac = { .addr_bytes = {0} };
name = rte_vdev_device_name(dev);
params = rte_vdev_device_args(dev);
kvlist = rte_kvargs_parse(params, valid_arguments);
if (kvlist) {
- if (rte_kvargs_count(kvlist, ETH_TAP_SPEED_ARG) == 1) {
- ret = rte_kvargs_process(kvlist,
- ETH_TAP_SPEED_ARG,
- &set_interface_speed,
- &speed);
- if (ret == -1)
- goto leave;
- }
-
if (rte_kvargs_count(kvlist, ETH_TAP_IFACE_ARG) == 1) {
ret = rte_kvargs_process(kvlist,
ETH_TAP_IFACE_ARG,
ret = rte_kvargs_process(kvlist,
ETH_TAP_MAC_ARG,
&set_mac_type,
- &fixed_mac_type);
+ &user_mac);
if (ret == -1)
goto leave;
}
RTE_LOG(NOTICE, PMD, "Initializing pmd_tap for %s as %s\n",
name, tap_name);
- ret = eth_dev_tap_create(dev, tap_name, remote_iface, fixed_mac_type);
+ ret = eth_dev_tap_create(dev, tap_name, remote_iface, &user_mac);
leave:
if (ret == -1) {
if (internals->nlsk_fd) {
tap_flow_flush(eth_dev, NULL);
tap_flow_implicit_flush(internals, NULL);
- nl_final(internals->nlsk_fd);
+ tap_nl_final(internals->nlsk_fd);
}
for (i = 0; i < RTE_PMD_TAP_MAX_QUEUES; i++) {
if (internals->rxq[i].fd != -1) {
RTE_PMD_REGISTER_ALIAS(net_tap, eth_tap);
RTE_PMD_REGISTER_PARAM_STRING(net_tap,
ETH_TAP_IFACE_ARG "=<string> "
- ETH_TAP_SPEED_ARG "=<int> "
- ETH_TAP_MAC_ARG "=" ETH_TAP_MAC_FIXED " "
+ ETH_TAP_MAC_ARG "=" ETH_TAP_MAC_ARG_FMT " "
ETH_TAP_REMOTE_ARG "=<string>");
git.droids-corp.org / dpdk.git / blobdiff