#include <rte_debug.h>
#include <rte_ip.h>
#include <rte_string_fns.h>
+#include <rte_ethdev.h>
+#include <rte_errno.h>
#include <assert.h>
#include <sys/types.h>
#include <linux/if_tun.h>
#include <linux/if_ether.h>
#include <fcntl.h>
+#include <ctype.h>
#include <tap_rss.h>
#include <rte_eth_tap.h>
#define TAP_GSO_MBUFS_NUM \
(TAP_GSO_MBUFS_PER_CORE * TAP_GSO_MBUF_CACHE_SIZE)
+/* IPC key for queue fds sync */
+#define TAP_MP_KEY "tap_mp_sync_queues"
+
+#define TAP_IOV_DEFAULT_MAX 1024
+
+static int tap_devices_count;
static struct rte_vdev_driver pmd_tap_drv;
static struct rte_vdev_driver pmd_tun_drv;
NULL
};
-static unsigned int tap_unit;
-static unsigned int tun_unit;
-
-static char tuntap_name[8];
-
static volatile uint32_t tap_trigger; /* Rx trigger */
static struct rte_eth_link pmd_link = {
REMOTE_ONLY,
};
+/* Message header to synchronize queues via IPC */
+struct ipc_queues {
+ char port_name[RTE_DEV_NAME_MAX_LEN];
+ int rxq_count;
+ int txq_count;
+ /*
+ * The file descriptors are in the dedicated part
+ * of the Unix message to be translated by the kernel.
+ */
+};
+
static int tap_intr_handle_set(struct rte_eth_dev *dev, int set);
/**
*/
ifr.ifr_flags = (pmd->type == ETH_TUNTAP_TYPE_TAP) ?
IFF_TAP : IFF_TUN | IFF_POINTOPOINT;
- snprintf(ifr.ifr_name, IFNAMSIZ, "%s", pmd->name);
-
- TAP_LOG(DEBUG, "ifr_name '%s'", ifr.ifr_name);
+ strlcpy(ifr.ifr_name, pmd->name, IFNAMSIZ);
fd = open(TUN_TAP_DEV_PATH, O_RDWR);
if (fd < 0) {
- TAP_LOG(ERR, "Unable to create %s interface", tuntap_name);
+ TAP_LOG(ERR, "Unable to open %s interface", TUN_TAP_DEV_PATH);
goto error;
}
#ifdef IFF_MULTI_QUEUE
/* Grab the TUN features to verify we can work multi-queue */
if (ioctl(fd, TUNGETFEATURES, &features) < 0) {
- TAP_LOG(ERR, "%s unable to get TUN/TAP features",
- tuntap_name);
+ TAP_LOG(ERR, "unable to get TUN/TAP features");
goto error;
}
- TAP_LOG(DEBUG, "%s Features %08x", tuntap_name, features);
+ TAP_LOG(DEBUG, "%s Features %08x", TUN_TAP_DEV_PATH, features);
if (features & IFF_MULTI_QUEUE) {
TAP_LOG(DEBUG, " Multi-queue support for %d queues",
goto error;
}
+ /*
+ * Name passed to kernel might be wildcard like dtun%d
+ * and need to find the resulting device.
+ */
+ TAP_LOG(DEBUG, "Device name is '%s'", ifr.ifr_name);
+ strlcpy(pmd->name, ifr.ifr_name, RTE_ETH_NAME_MAX_LEN);
+
if (is_keepalive) {
/*
* Detach the TUN/TAP keep-alive queue
return fd;
error:
- if (fd > 0)
+ if (fd >= 0)
close(fd);
return -1;
}
uint32_t l2 = mbuf->packet_type & RTE_PTYPE_L2_MASK;
uint32_t l3 = mbuf->packet_type & RTE_PTYPE_L3_MASK;
uint32_t l4 = mbuf->packet_type & RTE_PTYPE_L4_MASK;
- unsigned int l2_len = sizeof(struct ether_hdr);
+ unsigned int l2_len = sizeof(struct rte_ether_hdr);
unsigned int l3_len;
uint16_t cksum = 0;
void *l3_hdr;
l3_len = 4 * (iph->version_ihl & 0xf);
if (unlikely(l2_len + l3_len > rte_pktmbuf_data_len(mbuf)))
return;
+ /* check that the total length reported by header is not
+ * greater than the total received size
+ */
+ if (l2_len + rte_be_to_cpu_16(iph->total_length) >
+ rte_pktmbuf_data_len(mbuf))
+ return;
cksum = ~rte_raw_cksum(iph, l3_len);
mbuf->ol_flags |= cksum ?
PKT_RX_IP_CKSUM_BAD :
PKT_RX_IP_CKSUM_GOOD;
} else if (l3 == RTE_PTYPE_L3_IPV6) {
+ struct ipv6_hdr *iph = l3_hdr;
+
l3_len = sizeof(struct ipv6_hdr);
+ /* check that the total length reported by header is not
+ * greater than the total received size
+ */
+ if (l2_len + l3_len + rte_be_to_cpu_16(iph->payload_len) >
+ rte_pktmbuf_data_len(mbuf))
+ return;
} else {
/* IPv6 extensions are not supported */
return;
*/
apply:
if (remote)
- snprintf(ifr->ifr_name, IFNAMSIZ, "%s", pmd->remote_iface);
+ strlcpy(ifr->ifr_name, pmd->remote_iface, IFNAMSIZ);
else if (mode == LOCAL_ONLY || mode == LOCAL_AND_REMOTE)
- snprintf(ifr->ifr_name, IFNAMSIZ, "%s", pmd->name);
+ strlcpy(ifr->ifr_name, pmd->name, IFNAMSIZ);
switch (request) {
case SIOCSIFFLAGS:
/* fetch current flags to leave other flags untouched */
static int
tap_dev_configure(struct rte_eth_dev *dev)
{
+ struct pmd_internals *pmd = dev->data->dev_private;
+
if (dev->data->nb_rx_queues > RTE_PMD_TAP_MAX_QUEUES) {
TAP_LOG(ERR,
"%s: number of rx queues %d exceeds max num of queues %d",
return -1;
}
- TAP_LOG(INFO, "%s: %p: TX configured queues number: %u",
- dev->device->name, (void *)dev, dev->data->nb_tx_queues);
+ TAP_LOG(INFO, "%s: %s: TX configured queues number: %u",
+ dev->device->name, pmd->name, dev->data->nb_tx_queues);
- TAP_LOG(INFO, "%s: %p: RX configured queues number: %u",
- dev->device->name, (void *)dev, dev->data->nb_rx_queues);
+ TAP_LOG(INFO, "%s: %s: RX configured queues number: %u",
+ dev->device->name, pmd->name, dev->data->nb_rx_queues);
return 0;
}
}
static int
-tap_mac_set(struct rte_eth_dev *dev, struct ether_addr *mac_addr)
+tap_mac_set(struct rte_eth_dev *dev, struct rte_ether_addr *mac_addr)
{
struct pmd_internals *pmd = dev->data->dev_private;
enum ioctl_mode mode = LOCAL_ONLY;
ret = tap_ioctl(pmd, SIOCGIFHWADDR, &ifr, 0, LOCAL_ONLY);
if (ret < 0)
return ret;
- if (is_same_ether_addr((struct ether_addr *)&ifr.ifr_hwaddr.sa_data,
+ if (is_same_ether_addr((struct rte_ether_addr *)&ifr.ifr_hwaddr.sa_data,
mac_addr))
return 0;
/* Check the current MAC address on the remote */
ret = tap_ioctl(pmd, SIOCGIFHWADDR, &ifr, 0, REMOTE_ONLY);
if (ret < 0)
return ret;
- if (!is_same_ether_addr((struct ether_addr *)&ifr.ifr_hwaddr.sa_data,
- mac_addr))
+ if (!is_same_ether_addr(
+ (struct rte_ether_addr *)&ifr.ifr_hwaddr.sa_data,
+ mac_addr))
mode = LOCAL_AND_REMOTE;
ifr.ifr_hwaddr.sa_family = AF_LOCAL;
rte_memcpy(ifr.ifr_hwaddr.sa_data, mac_addr, ETHER_ADDR_LEN);
struct rx_queue *rxq = &internals->rxq[rx_queue_id];
struct rte_mbuf **tmp = &rxq->pool;
long iov_max = sysconf(_SC_IOV_MAX);
+
+ if (iov_max <= 0) {
+ TAP_LOG(WARNING,
+ "_SC_IOV_MAX is not defined. Using %d as default",
+ TAP_IOV_DEFAULT_MAX);
+ iov_max = TAP_IOV_DEFAULT_MAX;
+ }
uint16_t nb_desc = RTE_MIN(nb_rx_desc, iov_max - 1);
struct iovec (*iovecs)[nb_desc + 1];
int data_off = RTE_PKTMBUF_HEADROOM;
static int
tap_set_mc_addr_list(struct rte_eth_dev *dev __rte_unused,
- struct ether_addr *mc_addr_set __rte_unused,
+ struct rte_ether_addr *mc_addr_set __rte_unused,
uint32_t nb_mc_addr __rte_unused)
{
/*
.filter_ctrl = tap_dev_filter_ctrl,
};
+static const char *tuntap_types[ETH_TUNTAP_TYPE_MAX] = {
+ "UNKNOWN", "TUN", "TAP"
+};
+
static int
-eth_dev_tap_create(struct rte_vdev_device *vdev, char *tap_name,
- char *remote_iface, struct ether_addr *mac_addr,
+eth_dev_tap_create(struct rte_vdev_device *vdev, const char *tap_name,
+ char *remote_iface, struct rte_ether_addr *mac_addr,
enum rte_tuntap_type type)
{
int numa_node = rte_socket_id();
struct rte_eth_dev *dev;
struct pmd_internals *pmd;
struct pmd_process_private *process_private;
+ const char *tuntap_name = tuntap_types[type];
struct rte_eth_dev_data *data;
struct ifreq ifr;
int i;
- TAP_LOG(DEBUG, "%s device on numa %u",
- tuntap_name, rte_socket_id());
+ TAP_LOG(DEBUG, "%s device on numa %u", tuntap_name, rte_socket_id());
dev = rte_eth_vdev_allocate(vdev, sizeof(*pmd));
if (!dev) {
pmd = dev->data->dev_private;
dev->process_private = process_private;
pmd->dev = dev;
- snprintf(pmd->name, sizeof(pmd->name), "%s", tap_name);
+ strlcpy(pmd->name, tap_name, sizeof(pmd->name));
pmd->type = type;
pmd->ioctl_sock = socket(AF_INET, SOCK_DGRAM, 0);
TAP_LOG(ERR, "Unable to create %s interface", tuntap_name);
goto error_exit;
}
+ TAP_LOG(DEBUG, "allocated %s", pmd->name);
ifr.ifr_mtu = dev->data->mtu;
if (tap_ioctl(pmd, SIOCSIFMTU, &ifr, 1, LOCAL_AND_REMOTE) < 0)
pmd->name, remote_iface);
goto error_remote;
}
- snprintf(pmd->remote_iface, RTE_ETH_NAME_MAX_LEN,
- "%s", remote_iface);
+ strlcpy(pmd->remote_iface, remote_iface, RTE_ETH_NAME_MAX_LEN);
/* Save state of remote device */
tap_ioctl(pmd, SIOCGIFFLAGS, &pmd->remote_initial_flags, 0, REMOTE_ONLY);
TAP_LOG(ERR, "Remote feature requires flow support.");
goto error_exit;
}
+ rte_eth_dev_probing_finish(dev);
return 0;
error_remote:
error_exit:
if (pmd->ioctl_sock > 0)
close(pmd->ioctl_sock);
+ /* mac_addrs must not be freed alone because part of dev_private */
+ dev->data->mac_addrs = NULL;
rte_eth_dev_release_port(dev);
error_exit_nodev:
return -EINVAL;
}
+/* make sure name is a possible Linux network device name */
+static bool
+is_valid_iface(const char *name)
+{
+ if (*name == '\0')
+ return false;
+
+ if (strnlen(name, IFNAMSIZ) == IFNAMSIZ)
+ return false;
+
+ while (*name) {
+ if (*name == '/' || *name == ':' || isspace(*name))
+ return false;
+ name++;
+ }
+ return true;
+}
+
static int
set_interface_name(const char *key __rte_unused,
const char *value,
{
char *name = (char *)extra_args;
- if (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));
-
+ if (value) {
+ if (!is_valid_iface(value)) {
+ TAP_LOG(ERR, "TAP invalid remote interface name (%s)",
+ value);
+ return -1;
+ }
+ strlcpy(name, value, RTE_ETH_NAME_MAX_LEN);
+ } else {
+ /* use tap%d which causes kernel to choose next available */
+ strlcpy(name, DEFAULT_TAP_NAME "%d", RTE_ETH_NAME_MAX_LEN);
+ }
return 0;
}
{
char *name = (char *)extra_args;
- if (value)
+ if (value) {
+ if (!is_valid_iface(value)) {
+ TAP_LOG(ERR, "TAP invalid remote interface name (%s)",
+ value);
+ return -1;
+ }
strlcpy(name, value, RTE_ETH_NAME_MAX_LEN);
+ }
return 0;
}
-static int parse_user_mac(struct ether_addr *user_mac,
+static int parse_user_mac(struct rte_ether_addr *user_mac,
const char *value)
{
unsigned int index = 0;
const char *value,
void *extra_args)
{
- struct ether_addr *user_mac = extra_args;
+ struct rte_ether_addr *user_mac = extra_args;
if (!value)
return 0;
char remote_iface[RTE_ETH_NAME_MAX_LEN];
struct rte_eth_dev *eth_dev;
- strcpy(tuntap_name, "TUN");
-
name = rte_vdev_device_name(dev);
params = rte_vdev_device_args(dev);
memset(remote_iface, 0, RTE_ETH_NAME_MAX_LEN);
return 0;
}
- snprintf(tun_name, sizeof(tun_name), "%s%u",
- DEFAULT_TUN_NAME, tun_unit++);
+ /* use tun%d which causes kernel to choose next available */
+ strlcpy(tun_name, DEFAULT_TUN_NAME "%d", RTE_ETH_NAME_MAX_LEN);
if (params && (params[0] != '\0')) {
TAP_LOG(DEBUG, "parameters (%s)", params);
}
pmd_link.link_speed = ETH_SPEED_NUM_10G;
- TAP_LOG(NOTICE, "Initializing pmd_tun for %s as %s",
- name, tun_name);
+ TAP_LOG(DEBUG, "Initializing pmd_tun for %s", name);
ret = eth_dev_tap_create(dev, tun_name, remote_iface, 0,
- ETH_TUNTAP_TYPE_TUN);
+ ETH_TUNTAP_TYPE_TUN);
leave:
if (ret == -1) {
TAP_LOG(ERR, "Failed to create pmd for %s as %s",
name, tun_name);
- tun_unit--; /* Restore the unit number */
}
rte_kvargs_free(kvlist);
return ret;
}
+/* Request queue file descriptors from secondary to primary. */
+static int
+tap_mp_attach_queues(const char *port_name, struct rte_eth_dev *dev)
+{
+ int ret;
+ struct timespec timeout = {.tv_sec = 1, .tv_nsec = 0};
+ struct rte_mp_msg request, *reply;
+ struct rte_mp_reply replies;
+ struct ipc_queues *request_param = (struct ipc_queues *)request.param;
+ struct ipc_queues *reply_param;
+ struct pmd_process_private *process_private = dev->process_private;
+ int queue, fd_iterator;
+
+ /* Prepare the request */
+ memset(&request, 0, sizeof(request));
+ strlcpy(request.name, TAP_MP_KEY, sizeof(request.name));
+ strlcpy(request_param->port_name, port_name,
+ sizeof(request_param->port_name));
+ request.len_param = sizeof(*request_param);
+ /* Send request and receive reply */
+ ret = rte_mp_request_sync(&request, &replies, &timeout);
+ if (ret < 0 || replies.nb_received != 1) {
+ TAP_LOG(ERR, "Failed to request queues from primary: %d",
+ rte_errno);
+ return -1;
+ }
+ reply = &replies.msgs[0];
+ reply_param = (struct ipc_queues *)reply->param;
+ TAP_LOG(DEBUG, "Received IPC reply for %s", reply_param->port_name);
+
+ /* Attach the queues from received file descriptors */
+ if (reply_param->rxq_count + reply_param->txq_count != reply->num_fds) {
+ TAP_LOG(ERR, "Unexpected number of fds received");
+ return -1;
+ }
+
+ dev->data->nb_rx_queues = reply_param->rxq_count;
+ dev->data->nb_tx_queues = reply_param->txq_count;
+ fd_iterator = 0;
+ for (queue = 0; queue < reply_param->rxq_count; queue++)
+ process_private->rxq_fds[queue] = reply->fds[fd_iterator++];
+ for (queue = 0; queue < reply_param->txq_count; queue++)
+ process_private->txq_fds[queue] = reply->fds[fd_iterator++];
+ free(reply);
+ return 0;
+}
+
+/* Send the queue file descriptors from the primary process to secondary. */
+static int
+tap_mp_sync_queues(const struct rte_mp_msg *request, const void *peer)
+{
+ struct rte_eth_dev *dev;
+ struct pmd_process_private *process_private;
+ struct rte_mp_msg reply;
+ const struct ipc_queues *request_param =
+ (const struct ipc_queues *)request->param;
+ struct ipc_queues *reply_param =
+ (struct ipc_queues *)reply.param;
+ uint16_t port_id;
+ int queue;
+ int ret;
+
+ /* Get requested port */
+ TAP_LOG(DEBUG, "Received IPC request for %s", request_param->port_name);
+ ret = rte_eth_dev_get_port_by_name(request_param->port_name, &port_id);
+ if (ret) {
+ TAP_LOG(ERR, "Failed to get port id for %s",
+ request_param->port_name);
+ return -1;
+ }
+ dev = &rte_eth_devices[port_id];
+ process_private = dev->process_private;
+
+ /* Fill file descriptors for all queues */
+ reply.num_fds = 0;
+ reply_param->rxq_count = 0;
+ if (dev->data->nb_rx_queues + dev->data->nb_tx_queues >
+ RTE_MP_MAX_FD_NUM){
+ TAP_LOG(ERR, "Number of rx/tx queues exceeds max number of fds");
+ return -1;
+ }
+
+ for (queue = 0; queue < dev->data->nb_rx_queues; queue++) {
+ reply.fds[reply.num_fds++] = process_private->rxq_fds[queue];
+ reply_param->rxq_count++;
+ }
+ RTE_ASSERT(reply_param->rxq_count == dev->data->nb_rx_queues);
+
+ reply_param->txq_count = 0;
+ for (queue = 0; queue < dev->data->nb_tx_queues; queue++) {
+ reply.fds[reply.num_fds++] = process_private->txq_fds[queue];
+ reply_param->txq_count++;
+ }
+ RTE_ASSERT(reply_param->txq_count == dev->data->nb_tx_queues);
+
+ /* Send reply */
+ strlcpy(reply.name, request->name, sizeof(reply.name));
+ strlcpy(reply_param->port_name, request_param->port_name,
+ sizeof(reply_param->port_name));
+ reply.len_param = sizeof(*reply_param);
+ if (rte_mp_reply(&reply, peer) < 0) {
+ TAP_LOG(ERR, "Failed to reply an IPC request to sync queues");
+ return -1;
+ }
+ return 0;
+}
+
/* Open a TAP interface device.
*/
static int
int speed;
char tap_name[RTE_ETH_NAME_MAX_LEN];
char remote_iface[RTE_ETH_NAME_MAX_LEN];
- struct ether_addr user_mac = { .addr_bytes = {0} };
+ struct rte_ether_addr user_mac = { .addr_bytes = {0} };
struct rte_eth_dev *eth_dev;
-
- strcpy(tuntap_name, "TAP");
+ int tap_devices_count_increased = 0;
name = rte_vdev_device_name(dev);
params = rte_vdev_device_args(dev);
TAP_LOG(ERR, "Failed to probe %s", name);
return -1;
}
- /* TODO: request info from primary to set up Rx and Tx */
eth_dev->dev_ops = &ops;
eth_dev->device = &dev->device;
+ eth_dev->rx_pkt_burst = pmd_rx_burst;
+ eth_dev->tx_pkt_burst = pmd_tx_burst;
+ if (!rte_eal_primary_proc_alive(NULL)) {
+ TAP_LOG(ERR, "Primary process is missing");
+ return -1;
+ }
+ eth_dev->process_private = (struct pmd_process_private *)
+ rte_zmalloc_socket(name,
+ sizeof(struct pmd_process_private),
+ RTE_CACHE_LINE_SIZE,
+ eth_dev->device->numa_node);
+ if (eth_dev->process_private == NULL) {
+ TAP_LOG(ERR,
+ "Failed to alloc memory for process private");
+ return -1;
+ }
+
+ ret = tap_mp_attach_queues(name, eth_dev);
+ if (ret != 0)
+ return -1;
rte_eth_dev_probing_finish(eth_dev);
return 0;
}
speed = ETH_SPEED_NUM_10G;
- snprintf(tap_name, sizeof(tap_name), "%s%u",
- DEFAULT_TAP_NAME, tap_unit++);
+
+ /* use tap%d which causes kernel to choose next available */
+ strlcpy(tap_name, DEFAULT_TAP_NAME "%d", RTE_ETH_NAME_MAX_LEN);
memset(remote_iface, 0, RTE_ETH_NAME_MAX_LEN);
if (params && (params[0] != '\0')) {
}
pmd_link.link_speed = speed;
- TAP_LOG(NOTICE, "Initializing pmd_tap for %s as %s",
- name, tap_name);
+ TAP_LOG(DEBUG, "Initializing pmd_tap for %s", name);
+ /* Register IPC feed callback */
+ if (!tap_devices_count) {
+ ret = rte_mp_action_register(TAP_MP_KEY, tap_mp_sync_queues);
+ if (ret < 0) {
+ TAP_LOG(ERR, "tap: Failed to register IPC callback: %s",
+ strerror(rte_errno));
+ goto leave;
+ }
+ }
+ tap_devices_count++;
+ tap_devices_count_increased = 1;
ret = eth_dev_tap_create(dev, tap_name, remote_iface, &user_mac,
ETH_TUNTAP_TYPE_TAP);
if (ret == -1) {
TAP_LOG(ERR, "Failed to create pmd for %s as %s",
name, tap_name);
- tap_unit--; /* Restore the unit number */
+ if (tap_devices_count_increased == 1) {
+ if (tap_devices_count == 1)
+ rte_mp_action_unregister(TAP_MP_KEY);
+ tap_devices_count--;
+ }
}
rte_kvargs_free(kvlist);
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_secondary(eth_dev);
+ return rte_eth_dev_release_port(eth_dev);
internals = eth_dev->data->dev_private;
process_private = eth_dev->process_private;
TAP_LOG(DEBUG, "Closing %s Ethernet device on numa %u",
- (internals->type == ETH_TUNTAP_TYPE_TAP) ? "TAP" : "TUN",
- rte_socket_id());
+ tuntap_types[internals->type], rte_socket_id());
if (internals->nlsk_fd) {
tap_flow_flush(eth_dev, NULL);
}
close(internals->ioctl_sock);
- rte_free(eth_dev->data->dev_private);
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);
if (internals->ka_fd != -1) {
git.droids-corp.org / dpdk.git / blobdiff