#include <rte_ip.h>
#include <rte_string_fns.h>
+#include <assert.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/socket.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)
+
static struct rte_vdev_driver pmd_tap_drv;
static struct rte_vdev_driver pmd_tun_drv;
NULL
};
-static int tap_unit;
-static int tun_unit;
+static unsigned int tap_unit;
+static unsigned int tun_unit;
-static int tap_type;
static char tuntap_name[8];
static volatile uint32_t tap_trigger; /* Rx trigger */
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.
*
- * name is the number of the interface to use, unless NULL to take the host
- * supplied name.
+ * @param[in] is_keepalive
+ * Keepalive flag
+ *
+ * @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
* Do not set IFF_NO_PI as packet information header will be needed
* to check if a received packet has been truncated.
*/
- ifr.ifr_flags = (tap_type) ? IFF_TAP : IFF_TUN | IFF_POINTOPOINT;
+ 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);
goto error;
}
+ 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 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
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_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);
+ }
+}
- 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;
+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)
+{
+ int i;
+ uint16_t l234_hlen;
- /* 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);
+ 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;
+ 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.
+ * For TUN PMD this mandatory as fields are used by
+ * Kernel tun.c to determine whether its IP or non IP
+ * packets.
+ *
+ * The logic fetches the first byte of data from mbuf
+ * then compares whether its v4 or v6. If first byte
+ * is 4 or 6, then protocol field is updated.
+ */
+ char *buff_data = rte_pktmbuf_mtod(seg, void *);
+ 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);
}
- 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;
+
+ 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))) {
+ 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 l2, l3
+ * headers + l4 pseudo header
+ */
+ rte_memcpy(m_copy, rte_pktmbuf_mtod(mbuf, void *),
+ 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, j);
+ if (n <= 0)
+ break;
+ (*num_packets)++;
+ (*num_tx_bytes) += rte_pktmbuf_pkt_len(mbuf);
}
}
{
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 = bufs[num_tx];
- struct iovec iovecs[mbuf->nb_segs + 1];
- struct tun_pi pi = { .flags = 0, .proto = 0x00 };
- struct rte_mbuf *seg = mbuf;
- char m_copy[mbuf->data_len];
- int n;
+ 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;
- /* stats.errs will be incremented */
- if (rte_pktmbuf_pkt_len(mbuf) > max_size)
- break;
+ tso = mbuf_in->ol_flags & PKT_TX_TCP_SEG;
+ if (tso) {
+ struct rte_gso_ctx *gso_ctx = &txq->gso_ctx;
- /*
- * TUN and TAP are created with IFF_NO_PI disabled.
- * For TUN PMD this mandatory as fields are used by
- * Kernel tun.c to determine whether its IP or non IP
- * packets.
- *
- * The logic fetches the first byte of data from mbuf.
- * compares whether its v4 or v6. If none matches default
- * value 0x00 is taken for protocol field.
- */
- char *buff_data = rte_pktmbuf_mtod(seg, void *);
- j = (*buff_data & 0xf0);
- pi.proto = (j == 0x40) ? 0x0008 :
- (j == 0x60) ? 0xdd86 : 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;
- }
- 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)
+ 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;
- /* To change checksums, work on a copy of data. */
- 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;
+ }
+ 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;
}
- /* copy the tx frame data */
- n = writev(txq->fd, iovecs, mbuf->nb_segs + 1);
- if (n <= 0)
- break;
+ 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;
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);
}
dev_info->tx_queue_offload_capa;
dev_info->hash_key_size = TAP_RSS_HASH_KEY_SIZE;
/*
- * limitation: TAP suppors all of the following hash
+ * limitation: TAP supports all of IP, UDP and TCP hash
* functions together and not in partial combinations
*/
- dev_info->flow_type_rss_offloads =
- ETH_RSS_IP | ETH_RSS_UDP | ETH_RSS_TCP;
+ dev_info->flow_type_rss_offloads = ~TAP_RSS_HF_MASK;
}
static int
ioctl(internals->ioctl_sock, SIOCSIFFLAGS,
&internals->remote_initial_flags);
}
+
+ if (internals->ka_fd != -1) {
+ close(internals->ka_fd);
+ internals->ka_fd = -1;
+ }
+ /*
+ * Since TUN device has no more opened file descriptors
+ * it will be removed from kernel
+ */
}
static void
struct ifreq ifr;
int ret;
+ if (pmd->type == ETH_TUNTAP_TYPE_TUN) {
+ TAP_LOG(ERR, "%s: can't MAC address for TUN",
+ dev->device->name);
+ return -ENOTSUP;
+ }
+
if (is_zero_ether_addr(mac_addr)) {
TAP_LOG(ERR, "%s: can't set an empty MAC address",
dev->device->name);
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 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;
dir = "rx";
+ gso_ctx = NULL;
} else {
fd = &tx->fd;
other_fd = &rx->fd;
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;
return *fd;
}
return 0;
}
+/**
+ * DPDK callback to update the RSS hash configuration.
+ *
+ * @param dev
+ * Pointer to Ethernet device structure.
+ * @param[in] rss_conf
+ * RSS configuration data.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+tap_rss_hash_update(struct rte_eth_dev *dev,
+ struct rte_eth_rss_conf *rss_conf)
+{
+ if (rss_conf->rss_hf & TAP_RSS_HF_MASK) {
+ rte_errno = EINVAL;
+ return -rte_errno;
+ }
+ if (rss_conf->rss_key && rss_conf->rss_key_len) {
+ /*
+ * Currently TAP RSS key is hard coded
+ * and cannot be updated
+ */
+ TAP_LOG(ERR,
+ "port %u RSS key cannot be updated",
+ dev->data->port_id);
+ rte_errno = EINVAL;
+ return -rte_errno;
+ }
+ 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,
.stats_get = tap_stats_get,
.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 int
eth_dev_tap_create(struct rte_vdev_device *vdev, char *tap_name,
- char *remote_iface, struct ether_addr *mac_addr)
+ char *remote_iface, struct ether_addr *mac_addr,
+ enum rte_tuntap_type type)
{
int numa_node = rte_socket_id();
struct rte_eth_dev *dev;
pmd = dev->data->dev_private;
pmd->dev = dev;
snprintf(pmd->name, sizeof(pmd->name), "%s", tap_name);
+ pmd->type = type;
pmd->ioctl_sock = socket(AF_INET, SOCK_DGRAM, 0);
if (pmd->ioctl_sock == -1) {
dev->intr_handle = &pmd->intr_handle;
/* 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;
}
- if (tap_type) {
+ if (pmd->type == ETH_TUNTAP_TYPE_TAP) {
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 */
- if (tap_setup_queue(dev, pmd, 0, 1) == -1)
- goto error_exit;
- /* tx queue */
- if (tap_setup_queue(dev, pmd, 0, 0) == -1)
+ /*
+ * Allocate a TUN device keep-alive file descriptor that will only be
+ * closed when the TUN device itself is closed or removed.
+ * 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, 1);
+ if (pmd->ka_fd == -1) {
+ TAP_LOG(ERR, "Unable to create %s interface", tuntap_name);
goto error_exit;
+ }
ifr.ifr_mtu = dev->data->mtu;
if (tap_ioctl(pmd, SIOCSIFMTU, &ifr, 1, LOCAL_AND_REMOTE) < 0)
goto error_exit;
- if (tap_type) {
+ if (pmd->type == ETH_TUNTAP_TYPE_TAP) {
memset(&ifr, 0, sizeof(struct ifreq));
ifr.ifr_hwaddr.sa_family = AF_LOCAL;
rte_memcpy(ifr.ifr_hwaddr.sa_data, &pmd->eth_addr,
}
}
+ rte_eth_dev_probing_finish(dev);
return 0;
disable_rte_flow:
struct rte_kvargs *kvlist = NULL;
char tun_name[RTE_ETH_NAME_MAX_LEN];
char remote_iface[RTE_ETH_NAME_MAX_LEN];
+ struct rte_eth_dev *eth_dev;
- tap_type = 0;
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);
+ if (rte_eal_process_type() == RTE_PROC_SECONDARY &&
+ strlen(params) == 0) {
+ eth_dev = rte_eth_dev_attach_secondary(name);
+ if (!eth_dev) {
+ TAP_LOG(ERR, "Failed to probe %s", name);
+ 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++);
+
if (params && (params[0] != '\0')) {
TAP_LOG(DEBUG, "parameters (%s)", params);
TAP_LOG(NOTICE, "Initializing pmd_tun for %s as %s",
name, tun_name);
- ret = eth_dev_tap_create(dev, tun_name, remote_iface, 0);
+ ret = eth_dev_tap_create(dev, tun_name, remote_iface, 0,
+ ETH_TUNTAP_TYPE_TUN);
leave:
if (ret == -1) {
struct ether_addr user_mac = { .addr_bytes = {0} };
struct rte_eth_dev *eth_dev;
- tap_type = 1;
strcpy(tuntap_name, "TAP");
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);
}
/* TODO: request info from primary to set up Rx and Tx */
eth_dev->dev_ops = &ops;
+ eth_dev->device = &dev->device;
+ rte_eth_dev_probing_finish(eth_dev);
return 0;
}
speed = ETH_SPEED_NUM_10G;
- snprintf(tap_name, sizeof(tap_name), "%s%d",
+ snprintf(tap_name, sizeof(tap_name), "%s%u",
DEFAULT_TAP_NAME, tap_unit++);
memset(remote_iface, 0, RTE_ETH_NAME_MAX_LEN);
TAP_LOG(NOTICE, "Initializing pmd_tap for %s as %s",
name, tap_name);
- ret = eth_dev_tap_create(dev, tap_name, remote_iface, &user_mac);
+ ret = eth_dev_tap_create(dev, tap_name, remote_iface, &user_mac,
+ ETH_TUNTAP_TYPE_TAP);
leave:
if (ret == -1) {
struct pmd_internals *internals;
int i;
- TAP_LOG(DEBUG, "Closing TUN/TAP Ethernet device on numa %u",
- rte_socket_id());
-
/* find the ethdev entry */
eth_dev = rte_eth_dev_allocated(rte_vdev_device_name(dev));
if (!eth_dev)
- return 0;
+ return -ENODEV;
+
+ if (rte_eal_process_type() != RTE_PROC_PRIMARY)
+ return rte_eth_dev_release_port_secondary(eth_dev);
internals = eth_dev->data->dev_private;
+
+ TAP_LOG(DEBUG, "Closing %s Ethernet device on numa %u",
+ (internals->type == ETH_TUNTAP_TYPE_TAP) ? "TAP" : "TUN",
+ rte_socket_id());
+
if (internals->nlsk_fd) {
tap_flow_flush(eth_dev, NULL);
tap_flow_implicit_flush(internals, NULL);
close(internals->ioctl_sock);
rte_free(eth_dev->data->dev_private);
-
rte_eth_dev_release_port(eth_dev);
+ if (internals->ka_fd != -1) {
+ close(internals->ka_fd);
+ internals->ka_fd = -1;
+ }
return 0;
}
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)