#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 <sys/stat.h>
#include <sys/socket.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 ETH_TAP_CMP_MAC_FMT "0123456789ABCDEFabcdef"
#define ETH_TAP_MAC_ARG_FMT ETH_TAP_MAC_FIXED "|" ETH_TAP_USR_MAC_FMT
+#define TAP_GSO_MBUFS_PER_CORE 128
+#define TAP_GSO_MBUF_SEG_SIZE 128
+#define TAP_GSO_MBUF_CACHE_SIZE 4
+#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 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);
-/* Tun/Tap allocation routine
+/**
+ * Tun/Tap allocation routine
+ *
+ * @param[in] pmd
+ * Pointer to private structure.
+ *
+ * @param[in] is_keepalive
+ * Keepalive flag
*
- * name is the number of the interface to use, unless NULL to take the host
- * supplied name.
+ * @return
+ * -1 on failure, fd on success
*/
static int
-tun_alloc(struct pmd_internals *pmd)
+tun_alloc(struct pmd_internals *pmd, int is_keepalive)
{
struct ifreq ifr;
#ifdef IFF_MULTI_QUEUE
*/
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
+ * to avoid traffic through it
+ */
+ ifr.ifr_flags = IFF_DETACH_QUEUE;
+ if (ioctl(fd, TUNSETQUEUE, (void *)&ifr) < 0) {
+ TAP_LOG(WARNING,
+ "Unable to detach keep-alive queue for %s: %s",
+ ifr.ifr_name, strerror(errno));
+ goto error;
+ }
+ }
+
/* Always set the file descriptor to non-blocking */
if (fcntl(fd, F_SETFL, O_NONBLOCK) < 0) {
TAP_LOG(WARNING,
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;
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;
+ DEV_RX_OFFLOAD_TCP_CKSUM;
}
/* Callback to handle the rx burst of packets to the correct interface and
pmd_rx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
{
struct rx_queue *rxq = queue;
+ struct pmd_process_private *process_private;
uint16_t num_rx;
unsigned long num_rx_bytes = 0;
uint32_t trigger = tap_trigger;
return 0;
if (trigger)
rxq->trigger_seen = trigger;
+ process_private = rte_eth_devices[rxq->in_port].process_private;
rte_compiler_barrier();
for (num_rx = 0; num_rx < nb_pkts; ) {
struct rte_mbuf *mbuf = rxq->pool;
uint16_t data_off = rte_pktmbuf_headroom(mbuf);
int len;
- len = readv(rxq->fd, *rxq->iovecs,
- 1 +
- (rxq->rxmode->offloads & DEV_RX_OFFLOAD_SCATTER ?
+ len = readv(process_private->rxq_fds[rxq->queue_id],
+ *rxq->iovecs,
+ 1 + (rxq->rxmode->offloads & DEV_RX_OFFLOAD_SCATTER ?
rxq->nb_rx_desc : 1));
if (len < (int)sizeof(struct tun_pi))
break;
return DEV_TX_OFFLOAD_MULTI_SEGS |
DEV_TX_OFFLOAD_IPV4_CKSUM |
DEV_TX_OFFLOAD_UDP_CKSUM |
- DEV_TX_OFFLOAD_TCP_CKSUM;
+ DEV_TX_OFFLOAD_TCP_CKSUM |
+ DEV_TX_OFFLOAD_TCP_TSO;
+}
+
+/* Finalize l4 checksum calculation */
+static void
+tap_tx_l4_cksum(uint16_t *l4_cksum, uint16_t l4_phdr_cksum,
+ uint32_t l4_raw_cksum)
+{
+ if (l4_cksum) {
+ uint32_t cksum;
+
+ cksum = __rte_raw_cksum_reduce(l4_raw_cksum);
+ cksum += l4_phdr_cksum;
+
+ cksum = ((cksum & 0xffff0000) >> 16) + (cksum & 0xffff);
+ cksum = (~cksum) & 0xffff;
+ if (cksum == 0)
+ cksum = 0xffff;
+ *l4_cksum = cksum;
+ }
+}
+
+/* Accumaulate L4 raw checksums */
+static void
+tap_tx_l4_add_rcksum(char *l4_data, unsigned int l4_len, uint16_t *l4_cksum,
+ uint32_t *l4_raw_cksum)
+{
+ if (l4_cksum == NULL)
+ return;
+
+ *l4_raw_cksum = __rte_raw_cksum(l4_data, l4_len, *l4_raw_cksum);
}
+/* L3 and L4 pseudo headers checksum offloads */
static void
-tap_tx_offload(char *packet, uint64_t ol_flags, unsigned int l2_len,
- unsigned int l3_len)
+tap_tx_l3_cksum(char *packet, uint64_t ol_flags, unsigned int l2_len,
+ unsigned int l3_len, unsigned int l4_len, uint16_t **l4_cksum,
+ uint16_t *l4_phdr_cksum, uint32_t *l4_raw_cksum)
{
void *l3_hdr = packet + l2_len;
iph->hdr_checksum = (cksum == 0xffff) ? cksum : ~cksum;
}
if (ol_flags & PKT_TX_L4_MASK) {
- uint16_t l4_len;
- uint32_t cksum;
- uint16_t *l4_cksum;
void *l4_hdr;
l4_hdr = packet + l2_len + l3_len;
if ((ol_flags & PKT_TX_L4_MASK) == PKT_TX_UDP_CKSUM)
- l4_cksum = &((struct udp_hdr *)l4_hdr)->dgram_cksum;
+ *l4_cksum = &((struct udp_hdr *)l4_hdr)->dgram_cksum;
else if ((ol_flags & PKT_TX_L4_MASK) == PKT_TX_TCP_CKSUM)
- l4_cksum = &((struct tcp_hdr *)l4_hdr)->cksum;
+ *l4_cksum = &((struct tcp_hdr *)l4_hdr)->cksum;
else
return;
- *l4_cksum = 0;
- if (ol_flags & PKT_TX_IPV4) {
- struct ipv4_hdr *iph = l3_hdr;
-
- l4_len = rte_be_to_cpu_16(iph->total_length) - l3_len;
- cksum = rte_ipv4_phdr_cksum(l3_hdr, 0);
- } else {
- struct ipv6_hdr *ip6h = l3_hdr;
-
- /* payload_len does not include ext headers */
- l4_len = rte_be_to_cpu_16(ip6h->payload_len) -
- l3_len + sizeof(struct ipv6_hdr);
- cksum = rte_ipv6_phdr_cksum(l3_hdr, 0);
- }
- cksum += rte_raw_cksum(l4_hdr, l4_len);
- cksum = ((cksum & 0xffff0000) >> 16) + (cksum & 0xffff);
- cksum = (~cksum) & 0xffff;
- if (cksum == 0)
- cksum = 0xffff;
- *l4_cksum = cksum;
+ **l4_cksum = 0;
+ if (ol_flags & PKT_TX_IPV4)
+ *l4_phdr_cksum = rte_ipv4_phdr_cksum(l3_hdr, 0);
+ else
+ *l4_phdr_cksum = rte_ipv6_phdr_cksum(l3_hdr, 0);
+ *l4_raw_cksum = __rte_raw_cksum(l4_hdr, l4_len, 0);
}
}
-/* Callback to handle sending packets from the tap interface
- */
-static uint16_t
-pmd_tx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
+static inline void
+tap_write_mbufs(struct tx_queue *txq, uint16_t num_mbufs,
+ struct rte_mbuf **pmbufs,
+ uint16_t *num_packets, unsigned long *num_tx_bytes)
{
- struct tx_queue *txq = queue;
- uint16_t num_tx = 0;
- unsigned long num_tx_bytes = 0;
- uint32_t max_size;
int i;
+ uint16_t l234_hlen;
+ struct pmd_process_private *process_private;
- if (unlikely(nb_pkts == 0))
- return 0;
+ process_private = rte_eth_devices[txq->out_port].process_private;
- max_size = *txq->mtu + (ETHER_HDR_LEN + ETHER_CRC_LEN + 4);
- for (i = 0; i < nb_pkts; i++) {
- struct rte_mbuf *mbuf = bufs[num_tx];
- struct iovec iovecs[mbuf->nb_segs + 1];
+ for (i = 0; i < num_mbufs; i++) {
+ struct rte_mbuf *mbuf = pmbufs[i];
+ struct iovec iovecs[mbuf->nb_segs + 2];
struct tun_pi pi = { .flags = 0, .proto = 0x00 };
struct rte_mbuf *seg = mbuf;
char m_copy[mbuf->data_len];
+ int proto;
int n;
int j;
-
- /* stats.errs will be incremented */
- if (rte_pktmbuf_pkt_len(mbuf) > max_size)
- break;
-
+ int k; /* current index in iovecs for copying segments */
+ uint16_t seg_len; /* length of first segment */
+ uint16_t nb_segs;
+ uint16_t *l4_cksum; /* l4 checksum (pseudo header + payload) */
+ uint32_t l4_raw_cksum = 0; /* TCP/UDP payload raw checksum */
+ uint16_t l4_phdr_cksum = 0; /* TCP/UDP pseudo header checksum */
+ uint16_t is_cksum = 0; /* in case cksum should be offloaded */
+
+ l4_cksum = NULL;
if (txq->type == ETH_TUNTAP_TYPE_TUN) {
/*
* TUN and TAP are created with IFF_NO_PI disabled.
* is 4 or 6, then protocol field is updated.
*/
char *buff_data = rte_pktmbuf_mtod(seg, void *);
- j = (*buff_data & 0xf0);
- pi.proto = (j == 0x40) ? rte_cpu_to_be_16(ETHER_TYPE_IPv4) :
- (j == 0x60) ? rte_cpu_to_be_16(ETHER_TYPE_IPv6) : 0x00;
+ proto = (*buff_data & 0xf0);
+ pi.proto = (proto == 0x40) ?
+ rte_cpu_to_be_16(ETHER_TYPE_IPv4) :
+ ((proto == 0x60) ?
+ rte_cpu_to_be_16(ETHER_TYPE_IPv6) :
+ 0x00);
}
- iovecs[0].iov_base = π
- iovecs[0].iov_len = sizeof(pi);
- for (j = 1; j <= mbuf->nb_segs; j++) {
- iovecs[j].iov_len = rte_pktmbuf_data_len(seg);
- iovecs[j].iov_base =
- rte_pktmbuf_mtod(seg, void *);
- seg = seg->next;
- }
+ k = 0;
+ iovecs[k].iov_base = π
+ iovecs[k].iov_len = sizeof(pi);
+ k++;
+
+ nb_segs = mbuf->nb_segs;
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)
+ is_cksum = 1;
+
+ /* Support only packets with at least layer 4
+ * header included in the first segment
+ */
+ seg_len = rte_pktmbuf_data_len(mbuf);
+ l234_hlen = mbuf->l2_len + mbuf->l3_len + mbuf->l4_len;
+ if (seg_len < l234_hlen)
break;
- /* To change checksums, work on a copy of data. */
+
+ /* To change checksums, work on a * copy of l2, l3
+ * headers + l4 pseudo header
+ */
rte_memcpy(m_copy, rte_pktmbuf_mtod(mbuf, void *),
- rte_pktmbuf_data_len(mbuf));
- tap_tx_offload(m_copy, mbuf->ol_flags,
- mbuf->l2_len, mbuf->l3_len);
- iovecs[1].iov_base = m_copy;
+ l234_hlen);
+ tap_tx_l3_cksum(m_copy, mbuf->ol_flags,
+ mbuf->l2_len, mbuf->l3_len, mbuf->l4_len,
+ &l4_cksum, &l4_phdr_cksum,
+ &l4_raw_cksum);
+ iovecs[k].iov_base = m_copy;
+ iovecs[k].iov_len = l234_hlen;
+ k++;
+
+ /* Update next iovecs[] beyond l2, l3, l4 headers */
+ if (seg_len > l234_hlen) {
+ iovecs[k].iov_len = seg_len - l234_hlen;
+ iovecs[k].iov_base =
+ rte_pktmbuf_mtod(seg, char *) +
+ l234_hlen;
+ tap_tx_l4_add_rcksum(iovecs[k].iov_base,
+ iovecs[k].iov_len, l4_cksum,
+ &l4_raw_cksum);
+ k++;
+ nb_segs++;
+ }
+ seg = seg->next;
+ }
+
+ for (j = k; j <= nb_segs; j++) {
+ iovecs[j].iov_len = rte_pktmbuf_data_len(seg);
+ iovecs[j].iov_base = rte_pktmbuf_mtod(seg, void *);
+ if (is_cksum)
+ tap_tx_l4_add_rcksum(iovecs[j].iov_base,
+ iovecs[j].iov_len, l4_cksum,
+ &l4_raw_cksum);
+ seg = seg->next;
}
+
+ if (is_cksum)
+ tap_tx_l4_cksum(l4_cksum, l4_phdr_cksum, l4_raw_cksum);
+
/* copy the tx frame data */
- n = writev(txq->fd, iovecs, mbuf->nb_segs + 1);
+ n = writev(process_private->txq_fds[txq->queue_id], iovecs, j);
if (n <= 0)
break;
+ (*num_packets)++;
+ (*num_tx_bytes) += rte_pktmbuf_pkt_len(mbuf);
+ }
+}
+/* Callback to handle sending packets from the tap interface
+ */
+static uint16_t
+pmd_tx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
+{
+ struct tx_queue *txq = queue;
+ uint16_t num_tx = 0;
+ uint16_t num_packets = 0;
+ unsigned long num_tx_bytes = 0;
+ uint32_t max_size;
+ int i;
+
+ if (unlikely(nb_pkts == 0))
+ return 0;
+
+ struct rte_mbuf *gso_mbufs[MAX_GSO_MBUFS];
+ max_size = *txq->mtu + (ETHER_HDR_LEN + ETHER_CRC_LEN + 4);
+ for (i = 0; i < nb_pkts; i++) {
+ struct rte_mbuf *mbuf_in = bufs[num_tx];
+ struct rte_mbuf **mbuf;
+ uint16_t num_mbufs = 0;
+ uint16_t tso_segsz = 0;
+ int ret;
+ uint16_t hdrs_len;
+ int j;
+ uint64_t tso;
+
+ tso = mbuf_in->ol_flags & PKT_TX_TCP_SEG;
+ if (tso) {
+ struct rte_gso_ctx *gso_ctx = &txq->gso_ctx;
+
+ assert(gso_ctx != NULL);
+
+ /* TCP segmentation implies TCP checksum offload */
+ mbuf_in->ol_flags |= PKT_TX_TCP_CKSUM;
+
+ /* gso size is calculated without ETHER_CRC_LEN */
+ hdrs_len = mbuf_in->l2_len + mbuf_in->l3_len +
+ mbuf_in->l4_len;
+ tso_segsz = mbuf_in->tso_segsz + hdrs_len;
+ if (unlikely(tso_segsz == hdrs_len) ||
+ tso_segsz > *txq->mtu) {
+ txq->stats.errs++;
+ break;
+ }
+ gso_ctx->gso_size = tso_segsz;
+ ret = rte_gso_segment(mbuf_in, /* packet to segment */
+ gso_ctx, /* gso control block */
+ (struct rte_mbuf **)&gso_mbufs, /* out mbufs */
+ RTE_DIM(gso_mbufs)); /* max tso mbufs */
+
+ /* ret contains the number of new created mbufs */
+ if (ret < 0)
+ break;
+
+ mbuf = gso_mbufs;
+ num_mbufs = ret;
+ } else {
+ /* stats.errs will be incremented */
+ if (rte_pktmbuf_pkt_len(mbuf_in) > max_size)
+ break;
+
+ /* ret 0 indicates no new mbufs were created */
+ ret = 0;
+ mbuf = &mbuf_in;
+ num_mbufs = 1;
+ }
+
+ tap_write_mbufs(txq, num_mbufs, mbuf,
+ &num_packets, &num_tx_bytes);
num_tx++;
- num_tx_bytes += mbuf->pkt_len;
- rte_pktmbuf_free(mbuf);
+ /* free original mbuf */
+ rte_pktmbuf_free(mbuf_in);
+ /* free tso mbufs */
+ for (j = 0; j < ret; j++)
+ rte_pktmbuf_free(mbuf[j]);
}
- txq->stats.opackets += num_tx;
+ txq->stats.opackets += num_packets;
txq->stats.errs += nb_pkts - num_tx;
txq->stats.obytes += num_tx_bytes;
- return num_tx;
+ return num_packets;
}
static const char *
*/
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_start(struct rte_eth_dev *dev)
{
- int err;
+ int err, i;
err = tap_intr_handle_set(dev, 1);
if (err)
return err;
- return tap_link_set_up(dev);
+
+ err = tap_link_set_up(dev);
+ if (err)
+ return err;
+
+ for (i = 0; i < dev->data->nb_tx_queues; i++)
+ dev->data->tx_queue_state[i] = RTE_ETH_QUEUE_STATE_STARTED;
+ for (i = 0; i < dev->data->nb_rx_queues; i++)
+ dev->data->rx_queue_state[i] = RTE_ETH_QUEUE_STATE_STARTED;
+
+ return err;
}
/* This function gets called when the current port gets stopped.
static void
tap_dev_stop(struct rte_eth_dev *dev)
{
+ int i;
+
+ for (i = 0; i < dev->data->nb_tx_queues; i++)
+ dev->data->tx_queue_state[i] = RTE_ETH_QUEUE_STATE_STOPPED;
+ for (i = 0; i < dev->data->nb_rx_queues; i++)
+ dev->data->rx_queue_state[i] = RTE_ETH_QUEUE_STATE_STOPPED;
+
tap_intr_handle_set(dev, 0);
tap_link_set_down(dev);
}
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;
}
{
int i;
struct pmd_internals *internals = dev->data->dev_private;
+ struct pmd_process_private *process_private = dev->process_private;
tap_link_set_down(dev);
tap_flow_flush(dev, NULL);
tap_flow_implicit_flush(internals, NULL);
for (i = 0; i < RTE_PMD_TAP_MAX_QUEUES; i++) {
- if (internals->rxq[i].fd != -1) {
- close(internals->rxq[i].fd);
- internals->rxq[i].fd = -1;
+ if (process_private->rxq_fds[i] != -1) {
+ close(process_private->rxq_fds[i]);
+ process_private->rxq_fds[i] = -1;
}
- if (internals->txq[i].fd != -1) {
- close(internals->txq[i].fd);
- internals->txq[i].fd = -1;
+ if (process_private->txq_fds[i] != -1) {
+ close(process_private->txq_fds[i]);
+ process_private->txq_fds[i] = -1;
}
}
tap_rx_queue_release(void *queue)
{
struct rx_queue *rxq = queue;
+ struct pmd_process_private *process_private;
- if (rxq && (rxq->fd > 0)) {
- close(rxq->fd);
- rxq->fd = -1;
+ if (!rxq)
+ return;
+ process_private = rte_eth_devices[rxq->in_port].process_private;
+ if (process_private->rxq_fds[rxq->queue_id] > 0) {
+ close(process_private->rxq_fds[rxq->queue_id]);
+ process_private->rxq_fds[rxq->queue_id] = -1;
rte_pktmbuf_free(rxq->pool);
rte_free(rxq->iovecs);
rxq->pool = NULL;
tap_tx_queue_release(void *queue)
{
struct tx_queue *txq = queue;
+ struct pmd_process_private *process_private;
+
+ if (!txq)
+ return;
+ process_private = rte_eth_devices[txq->out_port].process_private;
- if (txq && (txq->fd > 0)) {
- close(txq->fd);
- txq->fd = -1;
+ if (process_private->txq_fds[txq->queue_id] > 0) {
+ close(process_private->txq_fds[txq->queue_id]);
+ process_private->txq_fds[txq->queue_id] = -1;
}
}
}
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);
return 0;
}
+static int
+tap_gso_ctx_setup(struct rte_gso_ctx *gso_ctx, struct rte_eth_dev *dev)
+{
+ uint32_t gso_types;
+ char pool_name[64];
+
+ /*
+ * Create private mbuf pool with TAP_GSO_MBUF_SEG_SIZE bytes
+ * size per mbuf use this pool for both direct and indirect mbufs
+ */
+
+ struct rte_mempool *mp; /* Mempool for GSO packets */
+
+ /* initialize GSO context */
+ gso_types = DEV_TX_OFFLOAD_TCP_TSO;
+ snprintf(pool_name, sizeof(pool_name), "mp_%s", dev->device->name);
+ mp = rte_mempool_lookup((const char *)pool_name);
+ if (!mp) {
+ mp = rte_pktmbuf_pool_create(pool_name, TAP_GSO_MBUFS_NUM,
+ TAP_GSO_MBUF_CACHE_SIZE, 0,
+ RTE_PKTMBUF_HEADROOM + TAP_GSO_MBUF_SEG_SIZE,
+ SOCKET_ID_ANY);
+ if (!mp) {
+ struct pmd_internals *pmd = dev->data->dev_private;
+ RTE_LOG(DEBUG, PMD, "%s: failed to create mbuf pool for device %s\n",
+ pmd->name, dev->device->name);
+ return -1;
+ }
+ }
+
+ gso_ctx->direct_pool = mp;
+ gso_ctx->indirect_pool = mp;
+ gso_ctx->gso_types = gso_types;
+ gso_ctx->gso_size = 0; /* gso_size is set in tx_burst() per packet */
+ gso_ctx->flag = 0;
+
+ return 0;
+}
+
static int
tap_setup_queue(struct rte_eth_dev *dev,
struct pmd_internals *internals,
uint16_t qid,
int is_rx)
{
+ int ret;
int *fd;
int *other_fd;
const char *dir;
struct pmd_internals *pmd = dev->data->dev_private;
+ struct pmd_process_private *process_private = dev->process_private;
struct rx_queue *rx = &internals->rxq[qid];
struct tx_queue *tx = &internals->txq[qid];
+ struct rte_gso_ctx *gso_ctx;
if (is_rx) {
- fd = &rx->fd;
- other_fd = &tx->fd;
+ fd = &process_private->rxq_fds[qid];
+ other_fd = &process_private->txq_fds[qid];
dir = "rx";
+ gso_ctx = NULL;
} else {
- fd = &tx->fd;
- other_fd = &rx->fd;
+ fd = &process_private->txq_fds[qid];
+ other_fd = &process_private->rxq_fds[qid];
dir = "tx";
+ gso_ctx = &tx->gso_ctx;
}
if (*fd != -1) {
/* fd for this queue already exists */
TAP_LOG(DEBUG, "%s: fd %d for %s queue qid %d exists",
pmd->name, *fd, dir, qid);
+ gso_ctx = NULL;
} else if (*other_fd != -1) {
/* Only other_fd exists. dup it */
*fd = dup(*other_fd);
pmd->name, *other_fd, dir, qid, *fd);
} else {
/* Both RX and TX fds do not exist (equal -1). Create fd */
- *fd = tun_alloc(pmd);
+ *fd = tun_alloc(pmd, 0);
if (*fd < 0) {
*fd = -1; /* restore original value */
TAP_LOG(ERR, "%s: tun_alloc() failed.", pmd->name);
tx->mtu = &dev->data->mtu;
rx->rxmode = &dev->data->dev_conf.rxmode;
+ if (gso_ctx) {
+ ret = tap_gso_ctx_setup(gso_ctx, dev);
+ if (ret)
+ return -1;
+ }
tx->type = pmd->type;
struct rte_mempool *mp)
{
struct pmd_internals *internals = dev->data->dev_private;
+ struct pmd_process_private *process_private = dev->process_private;
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;
rxq->mp = mp;
rxq->trigger_seen = 1; /* force initial burst */
rxq->in_port = dev->data->port_id;
+ rxq->queue_id = rx_queue_id;
rxq->nb_rx_desc = nb_desc;
iovecs = rte_zmalloc_socket(dev->device->name, sizeof(*iovecs), 0,
socket_id);
}
TAP_LOG(DEBUG, " RX TUNTAP device name %s, qid %d on fd %d",
- internals->name, rx_queue_id, internals->rxq[rx_queue_id].fd);
+ internals->name, rx_queue_id,
+ process_private->rxq_fds[rx_queue_id]);
return 0;
const struct rte_eth_txconf *tx_conf)
{
struct pmd_internals *internals = dev->data->dev_private;
+ struct pmd_process_private *process_private = dev->process_private;
struct tx_queue *txq;
int ret;
uint64_t offloads;
return -1;
dev->data->tx_queues[tx_queue_id] = &internals->txq[tx_queue_id];
txq = dev->data->tx_queues[tx_queue_id];
+ txq->out_port = dev->data->port_id;
+ txq->queue_id = tx_queue_id;
offloads = tx_conf->offloads | dev->data->dev_conf.txmode.offloads;
txq->csum = !!(offloads &
return -1;
TAP_LOG(DEBUG,
" TX TUNTAP device name %s, qid %d on fd %d csum %s",
- internals->name, tx_queue_id, internals->txq[tx_queue_id].fd,
+ internals->name, tx_queue_id,
+ process_private->txq_fds[tx_queue_id],
txq->csum ? "on" : "off");
return 0;
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)
{
/*
return 0;
}
+static int
+tap_rx_queue_start(struct rte_eth_dev *dev, uint16_t rx_queue_id)
+{
+ dev->data->rx_queue_state[rx_queue_id] = RTE_ETH_QUEUE_STATE_STARTED;
+
+ return 0;
+}
+
+static int
+tap_tx_queue_start(struct rte_eth_dev *dev, uint16_t tx_queue_id)
+{
+ dev->data->tx_queue_state[tx_queue_id] = RTE_ETH_QUEUE_STATE_STARTED;
+
+ return 0;
+}
+
+static int
+tap_rx_queue_stop(struct rte_eth_dev *dev, uint16_t rx_queue_id)
+{
+ dev->data->rx_queue_state[rx_queue_id] = RTE_ETH_QUEUE_STATE_STOPPED;
+
+ return 0;
+}
+
+static int
+tap_tx_queue_stop(struct rte_eth_dev *dev, uint16_t tx_queue_id)
+{
+ dev->data->tx_queue_state[tx_queue_id] = RTE_ETH_QUEUE_STATE_STOPPED;
+
+ return 0;
+}
static const struct eth_dev_ops ops = {
.dev_start = tap_dev_start,
.dev_stop = tap_dev_stop,
.dev_infos_get = tap_dev_info,
.rx_queue_setup = tap_rx_queue_setup,
.tx_queue_setup = tap_tx_queue_setup,
+ .rx_queue_start = tap_rx_queue_start,
+ .tx_queue_start = tap_tx_queue_start,
+ .rx_queue_stop = tap_rx_queue_stop,
+ .tx_queue_stop = tap_tx_queue_stop,
.rx_queue_release = tap_rx_queue_release,
.tx_queue_release = tap_tx_queue_release,
.flow_ctrl_get = tap_flow_ctrl_get,
.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) {
goto error_exit_nodev;
}
+ process_private = (struct pmd_process_private *)
+ rte_zmalloc_socket(tap_name, sizeof(struct pmd_process_private),
+ RTE_CACHE_LINE_SIZE, dev->device->numa_node);
+
+ if (process_private == NULL) {
+ TAP_LOG(ERR, "Failed to alloc memory for process private");
+ return -1;
+ }
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);
/* Presetup the fds to -1 as being not valid */
pmd->ka_fd = -1;
for (i = 0; i < RTE_PMD_TAP_MAX_QUEUES; i++) {
- pmd->rxq[i].fd = -1;
- pmd->txq[i].fd = -1;
+ process_private->rxq_fds[i] = -1;
+ process_private->txq_fds[i] = -1;
}
if (pmd->type == ETH_TUNTAP_TYPE_TAP) {
* This keep-alive file descriptor will guarantee that the TUN device
* exists even when all of its queues are closed
*/
- pmd->ka_fd = tun_alloc(pmd);
+ pmd->ka_fd = tun_alloc(pmd, 1);
if (pmd->ka_fd == -1) {
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 -1;
}
eth_dev->dev_ops = &ops;
+ eth_dev->device = &dev->device;
+ rte_eth_dev_probing_finish(eth_dev);
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);
- if (rte_eal_process_type() == RTE_PROC_SECONDARY &&
- strlen(params) == 0) {
+ if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
eth_dev = rte_eth_dev_attach_secondary(name);
if (!eth_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%d",
- 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);
{
struct rte_eth_dev *eth_dev = NULL;
struct pmd_internals *internals;
+ struct pmd_process_private *process_private;
int i;
/* find the ethdev entry */
eth_dev = rte_eth_dev_allocated(rte_vdev_device_name(dev));
if (!eth_dev)
- return 0;
+ 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);
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);
tap_nl_final(internals->nlsk_fd);
}
for (i = 0; i < RTE_PMD_TAP_MAX_QUEUES; i++) {
- if (internals->rxq[i].fd != -1) {
- close(internals->rxq[i].fd);
- internals->rxq[i].fd = -1;
+ if (process_private->rxq_fds[i] != -1) {
+ close(process_private->rxq_fds[i]);
+ process_private->rxq_fds[i] = -1;
}
- if (internals->txq[i].fd != -1) {
- close(internals->txq[i].fd);
- internals->txq[i].fd = -1;
+ if (process_private->txq_fds[i] != -1) {
+ close(process_private->txq_fds[i]);
+ process_private->txq_fds[i] = -1;
}
}
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) {
ETH_TAP_REMOTE_ARG "=<string>");
int tap_logtype;
-RTE_INIT(tap_init_log);
-static void
-tap_init_log(void)
+RTE_INIT(tap_init_log)
{
tap_logtype = rte_log_register("pmd.net.tap");
if (tap_logtype >= 0)
git.droids-corp.org / dpdk.git / blobdiff