struct xsk_umem *umem;
struct rte_ring *buf_ring;
const struct rte_memzone *mz;
+ int pmd_zc;
};
struct rx_stats {
int if_index;
char if_name[IFNAMSIZ];
uint16_t queue_idx;
- struct ether_addr eth_addr;
- struct xsk_umem_info *umem;
+ int pmd_zc;
+ struct rte_ether_addr eth_addr;
struct rte_mempool *mb_pool_share;
struct pkt_rx_queue rx_queues[ETH_AF_XDP_MAX_QUEUE_PAIRS];
#define ETH_AF_XDP_IFACE_ARG "iface"
#define ETH_AF_XDP_QUEUE_IDX_ARG "queue"
+#define ETH_AF_XDP_PMD_ZC_ARG "pmd_zero_copy"
static const char * const valid_arguments[] = {
ETH_AF_XDP_IFACE_ARG,
ETH_AF_XDP_QUEUE_IDX_ARG,
+ ETH_AF_XDP_PMD_ZC_ARG,
NULL
};
};
static inline int
-reserve_fill_queue(struct xsk_umem_info *umem, int reserve_size)
+reserve_fill_queue(struct xsk_umem_info *umem, uint16_t reserve_size)
{
struct xsk_ring_prod *fq = &umem->fq;
+ void *addrs[reserve_size];
uint32_t idx;
- int i, ret;
+ uint16_t i;
- ret = xsk_ring_prod__reserve(fq, reserve_size, &idx);
- if (unlikely(!ret)) {
- AF_XDP_LOG(ERR, "Failed to reserve enough fq descs.\n");
- return ret;
+ if (rte_ring_dequeue_bulk(umem->buf_ring, addrs, reserve_size, NULL)
+ != reserve_size) {
+ AF_XDP_LOG(DEBUG, "Failed to get enough buffers for fq.\n");
+ return -1;
+ }
+
+ if (unlikely(!xsk_ring_prod__reserve(fq, reserve_size, &idx))) {
+ AF_XDP_LOG(DEBUG, "Failed to reserve enough fq descs.\n");
+ rte_ring_enqueue_bulk(umem->buf_ring, addrs,
+ reserve_size, NULL);
+ return -1;
}
for (i = 0; i < reserve_size; i++) {
__u64 *fq_addr;
- void *addr = NULL;
- if (rte_ring_dequeue(umem->buf_ring, &addr)) {
- i--;
- break;
- }
+
fq_addr = xsk_ring_prod__fill_addr(fq, idx++);
- *fq_addr = (uint64_t)addr;
+ *fq_addr = (uint64_t)addrs[i];
}
- xsk_ring_prod__submit(fq, i);
+ xsk_ring_prod__submit(fq, reserve_size);
return 0;
}
+static void
+umem_buf_release_to_fq(void *addr, void *opaque)
+{
+ struct xsk_umem_info *umem = (struct xsk_umem_info *)opaque;
+ uint64_t umem_addr = (uint64_t)addr - umem->mz->addr_64;
+
+ rte_ring_enqueue(umem->buf_ring, (void *)umem_addr);
+}
+
static uint16_t
eth_af_xdp_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
{
struct xsk_ring_prod *fq = &umem->fq;
uint32_t idx_rx = 0;
uint32_t free_thresh = fq->size >> 1;
- struct rte_mbuf *mbufs[ETH_AF_XDP_TX_BATCH_SIZE];
+ int pmd_zc = umem->pmd_zc;
+ struct rte_mbuf *mbufs[ETH_AF_XDP_RX_BATCH_SIZE];
unsigned long dropped = 0;
unsigned long rx_bytes = 0;
- uint16_t count = 0;
int rcvd, i;
- nb_pkts = RTE_MIN(nb_pkts, ETH_AF_XDP_TX_BATCH_SIZE);
+ nb_pkts = RTE_MIN(nb_pkts, ETH_AF_XDP_RX_BATCH_SIZE);
+
+ if (unlikely(rte_pktmbuf_alloc_bulk(rxq->mb_pool, mbufs, nb_pkts) != 0))
+ return 0;
rcvd = xsk_ring_cons__peek(rx, nb_pkts, &idx_rx);
if (rcvd == 0)
- return 0;
+ goto out;
if (xsk_prod_nb_free(fq, free_thresh) >= free_thresh)
(void)reserve_fill_queue(umem, ETH_AF_XDP_RX_BATCH_SIZE);
- if (unlikely(rte_pktmbuf_alloc_bulk(rxq->mb_pool, mbufs, rcvd) != 0))
- return 0;
-
for (i = 0; i < rcvd; i++) {
const struct xdp_desc *desc;
uint64_t addr;
uint32_t len;
void *pkt;
+ uint16_t buf_len = ETH_AF_XDP_FRAME_SIZE;
+ struct rte_mbuf_ext_shared_info *shinfo;
desc = xsk_ring_cons__rx_desc(rx, idx_rx++);
addr = desc->addr;
len = desc->len;
pkt = xsk_umem__get_data(rxq->umem->mz->addr, addr);
- rte_memcpy(rte_pktmbuf_mtod(mbufs[i], void *), pkt, len);
+ if (pmd_zc) {
+ shinfo = rte_pktmbuf_ext_shinfo_init_helper(pkt,
+ &buf_len, umem_buf_release_to_fq, umem);
+
+ rte_pktmbuf_attach_extbuf(mbufs[i], pkt, 0, buf_len,
+ shinfo);
+ } else {
+ rte_memcpy(rte_pktmbuf_mtod(mbufs[i], void *),
+ pkt, len);
+ rte_ring_enqueue(umem->buf_ring, (void *)addr);
+ }
rte_pktmbuf_pkt_len(mbufs[i]) = len;
rte_pktmbuf_data_len(mbufs[i]) = len;
rx_bytes += len;
- bufs[count++] = mbufs[i];
-
- rte_ring_enqueue(umem->buf_ring, (void *)addr);
+ bufs[i] = mbufs[i];
}
xsk_ring_cons__release(rx, rcvd);
rxq->stats.rx_pkts += (rcvd - dropped);
rxq->stats.rx_bytes += rx_bytes;
- return count;
+out:
+ if (rcvd != nb_pkts)
+ rte_mempool_put_bulk(rxq->mb_pool, (void **)&mbufs[rcvd],
+ nb_pkts - rcvd);
+
+ return rcvd;
}
static void
pull_umem_cq(umem, ETH_AF_XDP_TX_BATCH_SIZE);
}
+static inline bool
+in_umem_range(struct xsk_umem_info *umem, uint64_t addr)
+{
+ uint64_t mz_base_addr = umem->mz->addr_64;
+
+ return addr >= mz_base_addr && addr < mz_base_addr + umem->mz->len;
+}
+
static uint16_t
eth_af_xdp_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
{
struct pkt_tx_queue *txq = queue;
struct xsk_umem_info *umem = txq->pair->umem;
struct rte_mbuf *mbuf;
+ int pmd_zc = umem->pmd_zc;
void *addrs[ETH_AF_XDP_TX_BATCH_SIZE];
unsigned long tx_bytes = 0;
- int i, valid = 0;
+ int i;
uint32_t idx_tx;
nb_pkts = RTE_MIN(nb_pkts, ETH_AF_XDP_TX_BATCH_SIZE);
for (i = 0; i < nb_pkts; i++) {
struct xdp_desc *desc;
void *pkt;
- uint32_t buf_len = ETH_AF_XDP_FRAME_SIZE
- - ETH_AF_XDP_DATA_HEADROOM;
+
desc = xsk_ring_prod__tx_desc(&txq->tx, idx_tx + i);
mbuf = bufs[i];
- if (mbuf->pkt_len <= buf_len) {
- desc->addr = (uint64_t)addrs[valid];
- desc->len = mbuf->pkt_len;
+ desc->len = mbuf->pkt_len;
+
+ /*
+ * We need to make sure the external mbuf address is within
+ * current port's umem memzone range
+ */
+ if (pmd_zc && RTE_MBUF_HAS_EXTBUF(mbuf) &&
+ in_umem_range(umem, (uint64_t)mbuf->buf_addr)) {
+ desc->addr = (uint64_t)mbuf->buf_addr -
+ umem->mz->addr_64;
+ mbuf->buf_addr = xsk_umem__get_data(umem->mz->addr,
+ (uint64_t)addrs[i]);
+ } else {
+ desc->addr = (uint64_t)addrs[i];
pkt = xsk_umem__get_data(umem->mz->addr,
- desc->addr);
+ desc->addr);
rte_memcpy(pkt, rte_pktmbuf_mtod(mbuf, void *),
- desc->len);
- valid++;
- tx_bytes += mbuf->pkt_len;
+ desc->len);
}
- rte_pktmbuf_free(mbuf);
+ tx_bytes += mbuf->pkt_len;
}
xsk_ring_prod__submit(&txq->tx, nb_pkts);
kick_tx(txq);
- if (valid < nb_pkts)
- rte_ring_enqueue_bulk(umem->buf_ring, &addrs[valid],
- nb_pkts - valid, NULL);
-
- txq->stats.err_pkts += nb_pkts - valid;
- txq->stats.tx_pkts += valid;
+ txq->stats.tx_pkts += nb_pkts;
txq->stats.tx_bytes += tx_bytes;
+ for (i = 0; i < nb_pkts; i++)
+ rte_pktmbuf_free(bufs[i]);
+
return nb_pkts;
}
dev_info->max_rx_queues = 1;
dev_info->max_tx_queues = 1;
+ dev_info->min_mtu = RTE_ETHER_MIN_MTU;
+ dev_info->max_mtu = ETH_AF_XDP_FRAME_SIZE - ETH_AF_XDP_DATA_HEADROOM;
+
dev_info->default_rxportconf.nb_queues = 1;
dev_info->default_txportconf.nb_queues = 1;
dev_info->default_rxportconf.ring_size = ETH_AF_XDP_DFLT_NUM_DESCS;
XDP_FLAGS_UPDATE_IF_NOEXIST);
}
+static void
+xdp_umem_destroy(struct xsk_umem_info *umem)
+{
+ rte_memzone_free(umem->mz);
+ umem->mz = NULL;
+
+ rte_ring_free(umem->buf_ring);
+ umem->buf_ring = NULL;
+
+ rte_free(umem);
+ umem = NULL;
+}
+
static void
eth_dev_close(struct rte_eth_dev *dev)
{
if (rxq->umem == NULL)
break;
xsk_socket__delete(rxq->xsk);
+ (void)xsk_umem__delete(rxq->umem->umem);
+ xdp_umem_destroy(rxq->umem);
}
- (void)xsk_umem__delete(internals->umem->umem);
+ /*
+ * MAC is not allocated dynamically, setting it to NULL would prevent
+ * from releasing it in rte_eth_dev_release_port.
+ */
+ dev->data->mac_addrs = NULL;
+
remove_xdp_program(internals);
}
return 0;
}
-static void
-xdp_umem_destroy(struct xsk_umem_info *umem)
-{
- rte_memzone_free(umem->mz);
- umem->mz = NULL;
-
- rte_ring_free(umem->buf_ring);
- umem->buf_ring = NULL;
-
- rte_free(umem);
- umem = NULL;
-}
-
static struct
-xsk_umem_info *xdp_umem_configure(void)
+xsk_umem_info *xdp_umem_configure(struct pmd_internals *internals)
{
struct xsk_umem_info *umem;
const struct rte_memzone *mz;
.comp_size = ETH_AF_XDP_DFLT_NUM_DESCS,
.frame_size = ETH_AF_XDP_FRAME_SIZE,
.frame_headroom = ETH_AF_XDP_DATA_HEADROOM };
+ char ring_name[RTE_RING_NAMESIZE];
+ char mz_name[RTE_MEMZONE_NAMESIZE];
int ret;
uint64_t i;
return NULL;
}
- umem->buf_ring = rte_ring_create("af_xdp_ring",
+ snprintf(ring_name, sizeof(ring_name), "af_xdp_ring_%s_%u",
+ internals->if_name, internals->queue_idx);
+ umem->buf_ring = rte_ring_create(ring_name,
ETH_AF_XDP_NUM_BUFFERS,
rte_socket_id(),
0x0);
(void *)(i * ETH_AF_XDP_FRAME_SIZE +
ETH_AF_XDP_DATA_HEADROOM));
- mz = rte_memzone_reserve_aligned("af_xdp uemem",
+ snprintf(mz_name, sizeof(mz_name), "af_xdp_umem_%s_%u",
+ internals->if_name, internals->queue_idx);
+ mz = rte_memzone_reserve_aligned(mz_name,
ETH_AF_XDP_NUM_BUFFERS * ETH_AF_XDP_FRAME_SIZE,
rte_socket_id(), RTE_MEMZONE_IOVA_CONTIG,
getpagesize());
int ret = 0;
int reserve_size;
- rxq->umem = xdp_umem_configure();
+ rxq->umem = xdp_umem_configure(internals);
if (rxq->umem == NULL)
return -ENOMEM;
goto err;
}
- internals->umem = rxq->umem;
+ rxq->umem->pmd_zc = internals->pmd_zc;
dev->data->rx_queues[rx_queue_id] = rxq;
return 0;
}
static int
-parse_parameters(struct rte_kvargs *kvlist,
- char *if_name,
- int *queue_idx)
+parse_parameters(struct rte_kvargs *kvlist, char *if_name, int *queue_idx,
+ int *pmd_zc)
{
int ret;
if (ret < 0)
goto free_kvlist;
+ ret = rte_kvargs_process(kvlist, ETH_AF_XDP_PMD_ZC_ARG,
+ &parse_integer_arg, pmd_zc);
+ if (ret < 0)
+ goto free_kvlist;
+
free_kvlist:
rte_kvargs_free(kvlist);
return ret;
static int
get_iface_info(const char *if_name,
- struct ether_addr *eth_addr,
+ struct rte_ether_addr *eth_addr,
int *if_index)
{
struct ifreq ifr;
if (ioctl(sock, SIOCGIFHWADDR, &ifr))
goto error;
- rte_memcpy(eth_addr, ifr.ifr_hwaddr.sa_data, ETHER_ADDR_LEN);
+ rte_memcpy(eth_addr, ifr.ifr_hwaddr.sa_data, RTE_ETHER_ADDR_LEN);
close(sock);
return 0;
}
static struct rte_eth_dev *
-init_internals(struct rte_vdev_device *dev,
- const char *if_name,
- int queue_idx)
+init_internals(struct rte_vdev_device *dev, const char *if_name, int queue_idx,
+ int pmd_zc)
{
const char *name = rte_vdev_device_name(dev);
const unsigned int numa_node = dev->device.numa_node;
return NULL;
internals->queue_idx = queue_idx;
+ internals->pmd_zc = pmd_zc;
strlcpy(internals->if_name, if_name, IFNAMSIZ);
for (i = 0; i < ETH_AF_XDP_MAX_QUEUE_PAIRS; i++) {
eth_dev->dev_ops = &ops;
eth_dev->rx_pkt_burst = eth_af_xdp_rx;
eth_dev->tx_pkt_burst = eth_af_xdp_tx;
+ /* Let rte_eth_dev_close() release the port resources. */
+ eth_dev->data->dev_flags |= RTE_ETH_DEV_CLOSE_REMOVE;
+
+ if (internals->pmd_zc)
+ AF_XDP_LOG(INFO, "Zero copy between umem and mbuf enabled.\n");
return eth_dev;
int xsk_queue_idx = ETH_AF_XDP_DFLT_QUEUE_IDX;
struct rte_eth_dev *eth_dev = NULL;
const char *name;
+ int pmd_zc = 0;
AF_XDP_LOG(INFO, "Initializing pmd_af_xdp for %s\n",
rte_vdev_device_name(dev));
if (dev->device.numa_node == SOCKET_ID_ANY)
dev->device.numa_node = rte_socket_id();
- if (parse_parameters(kvlist, if_name, &xsk_queue_idx) < 0) {
+ if (parse_parameters(kvlist, if_name, &xsk_queue_idx, &pmd_zc) < 0) {
AF_XDP_LOG(ERR, "Invalid kvargs value\n");
return -EINVAL;
}
return -EINVAL;
}
- eth_dev = init_internals(dev, if_name, xsk_queue_idx);
+ eth_dev = init_internals(dev, if_name, xsk_queue_idx, pmd_zc);
if (eth_dev == NULL) {
AF_XDP_LOG(ERR, "Failed to init internals\n");
return -1;
rte_pmd_af_xdp_remove(struct rte_vdev_device *dev)
{
struct rte_eth_dev *eth_dev = NULL;
- struct pmd_internals *internals;
AF_XDP_LOG(INFO, "Removing AF_XDP ethdev on numa socket %u\n",
rte_socket_id());
/* find the ethdev entry */
eth_dev = rte_eth_dev_allocated(rte_vdev_device_name(dev));
if (eth_dev == NULL)
- return -1;
-
- internals = eth_dev->data->dev_private;
-
- rte_ring_free(internals->umem->buf_ring);
- rte_memzone_free(internals->umem->mz);
- rte_free(internals->umem);
+ return 0;
+ eth_dev_close(eth_dev);
rte_eth_dev_release_port(eth_dev);
RTE_PMD_REGISTER_VDEV(net_af_xdp, pmd_af_xdp_drv);
RTE_PMD_REGISTER_PARAM_STRING(net_af_xdp,
"iface=<string> "
- "queue=<int> ");
+ "queue=<int> "
+ "pmd_zero_copy=<0|1>");
RTE_INIT(af_xdp_init_log)
{
git.droids-corp.org / dpdk.git / blobdiff