static inline void
ixgbe_rxq_rearm(struct ixgbe_rx_queue *rxq)
{
int i;
uint16_t rx_id;
volatile union ixgbe_adv_rx_desc *rxdp;
struct ixgbe_rx_entry *rxep = &rxq->sw_ring[rxq->rxrearm_start];
struct rte_mbuf *mb0, *mb1;
__m128i hdr_room = _mm_set_epi64x(RTE_PKTMBUF_HEADROOM,
RTE_PKTMBUF_HEADROOM);
__m128i dma_addr0, dma_addr1;
const __m128i hba_msk = _mm_set_epi64x(0, UINT64_MAX);
rxdp = rxq->rx_ring + rxq->rxrearm_start;
/* Pull 'n' more MBUFs into the software ring */
if (rte_mempool_get_bulk(rxq->mb_pool,
(void *)rxep,
RTE_IXGBE_RXQ_REARM_THRESH) < 0) {
if (rxq->rxrearm_nb + RTE_IXGBE_RXQ_REARM_THRESH >=
rxq->nb_rx_desc) {
dma_addr0 = _mm_setzero_si128();
for (i = 0; i < RTE_IXGBE_DESCS_PER_LOOP; i++) {
rxep[i].mbuf = &rxq->fake_mbuf;
_mm_store_si128((__m128i *)&rxdp[i].read,
dma_addr0);
}
}
rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed +=
RTE_IXGBE_RXQ_REARM_THRESH;
return;
}
/* Initialize the mbufs in vector, process 2 mbufs in one loop */
for (i = 0; i < RTE_IXGBE_RXQ_REARM_THRESH; i += 2, rxep += 2) {
__m128i vaddr0, vaddr1;
uintptr_t p0, p1;
mb0 = rxep[0].mbuf;
mb1 = rxep[1].mbuf;
/*
* Flush mbuf with pkt template.
* Data to be rearmed is 6 bytes long.
* Though, RX will overwrite ol_flags that are coming next
* anyway. So overwrite whole 8 bytes with one load:
* 6 bytes of rearm_data plus first 2 bytes of ol_flags.
*/
p0 = (uintptr_t)&mb0->rearm_data;
*(uint64_t *)p0 = rxq->mbuf_initializer;
p1 = (uintptr_t)&mb1->rearm_data;
*(uint64_t *)p1 = rxq->mbuf_initializer;
/* load buf_addr(lo 64bit) and buf_physaddr(hi 64bit) */
vaddr0 = _mm_loadu_si128((__m128i *)&(mb0->buf_addr));
vaddr1 = _mm_loadu_si128((__m128i *)&(mb1->buf_addr));
/* convert pa to dma_addr hdr/data */
dma_addr0 = _mm_unpackhi_epi64(vaddr0, vaddr0);
dma_addr1 = _mm_unpackhi_epi64(vaddr1, vaddr1);
/* add headroom to pa values */
dma_addr0 = _mm_add_epi64(dma_addr0, hdr_room);
dma_addr1 = _mm_add_epi64(dma_addr1, hdr_room);
/* set Header Buffer Address to zero */
dma_addr0 = _mm_and_si128(dma_addr0, hba_msk);
dma_addr1 = _mm_and_si128(dma_addr1, hba_msk);
/* flush desc with pa dma_addr */
_mm_store_si128((__m128i *)&rxdp++->read, dma_addr0);
_mm_store_si128((__m128i *)&rxdp++->read, dma_addr1);
}
rxq->rxrearm_start += RTE_IXGBE_RXQ_REARM_THRESH;
if (rxq->rxrearm_start >= rxq->nb_rx_desc)
rxq->rxrearm_start = 0;
rxq->rxrearm_nb -= RTE_IXGBE_RXQ_REARM_THRESH;
rx_id = (uint16_t) ((rxq->rxrearm_start == 0) ?
(rxq->nb_rx_desc - 1) : (rxq->rxrearm_start - 1));
/* Update the tail pointer on the NIC */
IXGBE_PCI_REG_WRITE(rxq->rdt_reg_addr, rx_id);
}
uint16_t
ixgbe_xmit_pkts_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
uint16_t nb_pkts)
{
struct ixgbe_tx_queue *txq = (struct ixgbe_tx_queue *)tx_queue;
volatile union ixgbe_adv_tx_desc *txdp;
struct ixgbe_tx_entry_v *txep;
uint16_t n, nb_commit, tx_id;
uint64_t flags = DCMD_DTYP_FLAGS;
uint64_t rs = IXGBE_ADVTXD_DCMD_RS|DCMD_DTYP_FLAGS;
int i;
/* cross rx_thresh boundary is not allowed */
nb_pkts = RTE_MIN(nb_pkts, txq->tx_rs_thresh);
if (txq->nb_tx_free < txq->tx_free_thresh)
ixgbe_tx_free_bufs(txq);
nb_commit = nb_pkts = (uint16_t)RTE_MIN(txq->nb_tx_free, nb_pkts);
if (unlikely(nb_pkts == 0))
return 0;
tx_id = txq->tx_tail;
txdp = &txq->tx_ring[tx_id];
txep = &txq->sw_ring_v[tx_id];
txq->nb_tx_free = (uint16_t)(txq->nb_tx_free - nb_pkts);
n = (uint16_t)(txq->nb_tx_desc - tx_id);
if (nb_commit >= n) {
tx_backlog_entry(txep, tx_pkts, n);
for (i = 0; i < n - 1; ++i, ++tx_pkts, ++txdp)
vtx1(txdp, *tx_pkts, flags);
vtx1(txdp, *tx_pkts++, rs);
nb_commit = (uint16_t)(nb_commit - n);
tx_id = 0;
txq->tx_next_rs = (uint16_t)(txq->tx_rs_thresh - 1);
/* avoid reach the end of ring */
txdp = &(txq->tx_ring[tx_id]);
txep = &txq->sw_ring_v[tx_id];
}
tx_backlog_entry(txep, tx_pkts, nb_commit);
vtx(txdp, tx_pkts, nb_commit, flags);
tx_id = (uint16_t)(tx_id + nb_commit);
if (tx_id > txq->tx_next_rs) {
txq->tx_ring[txq->tx_next_rs].read.cmd_type_len |=
rte_cpu_to_le_32(IXGBE_ADVTXD_DCMD_RS);
txq->tx_next_rs = (uint16_t)(txq->tx_next_rs +
txq->tx_rs_thresh);
}
txq->tx_tail = tx_id;
IXGBE_PCI_REG_WRITE(txq->tdt_reg_addr, txq->tx_tail);
return nb_pkts;
}
static inline void
ixgbe_rxq_rearm(struct igb_rx_queue *rxq)
{
int i;
uint16_t rx_id;
volatile union ixgbe_adv_rx_desc *rxdp;
struct igb_rx_entry *rxep = &rxq->sw_ring[rxq->rxrearm_start];
struct rte_mbuf *mb0, *mb1;
__m128i hdr_room = _mm_set_epi64x(RTE_PKTMBUF_HEADROOM,
RTE_PKTMBUF_HEADROOM);
__m128i dma_addr0, dma_addr1;
rxdp = rxq->rx_ring + rxq->rxrearm_start;
/* Pull 'n' more MBUFs into the software ring */
if (rte_mempool_get_bulk(rxq->mb_pool,
(void *)rxep,
RTE_IXGBE_RXQ_REARM_THRESH) < 0) {
if (rxq->rxrearm_nb + RTE_IXGBE_RXQ_REARM_THRESH >=
rxq->nb_rx_desc) {
dma_addr0 = _mm_setzero_si128();
for (i = 0; i < RTE_IXGBE_DESCS_PER_LOOP; i++) {
rxep[i].mbuf = &rxq->fake_mbuf;
_mm_store_si128((__m128i *)&rxdp[i].read,
dma_addr0);
}
}
return;
}
/* Initialize the mbufs in vector, process 2 mbufs in one loop */
for (i = 0; i < RTE_IXGBE_RXQ_REARM_THRESH; i += 2, rxep += 2) {
__m128i vaddr0, vaddr1;
mb0 = rxep[0].mbuf;
mb1 = rxep[1].mbuf;
/* flush mbuf with pkt template */
mb0->rearm_data[0] = rxq->mbuf_initializer;
mb1->rearm_data[0] = rxq->mbuf_initializer;
/* load buf_addr(lo 64bit) and buf_physaddr(hi 64bit) */
vaddr0 = _mm_loadu_si128((__m128i *)&(mb0->buf_addr));
vaddr1 = _mm_loadu_si128((__m128i *)&(mb1->buf_addr));
/* convert pa to dma_addr hdr/data */
dma_addr0 = _mm_unpackhi_epi64(vaddr0, vaddr0);
dma_addr1 = _mm_unpackhi_epi64(vaddr1, vaddr1);
/* add headroom to pa values */
dma_addr0 = _mm_add_epi64(dma_addr0, hdr_room);
dma_addr1 = _mm_add_epi64(dma_addr1, hdr_room);
/* flush desc with pa dma_addr */
_mm_store_si128((__m128i *)&rxdp++->read, dma_addr0);
_mm_store_si128((__m128i *)&rxdp++->read, dma_addr1);
}
rxq->rxrearm_start += RTE_IXGBE_RXQ_REARM_THRESH;
if (rxq->rxrearm_start >= rxq->nb_rx_desc)
rxq->rxrearm_start = 0;
rxq->rxrearm_nb -= RTE_IXGBE_RXQ_REARM_THRESH;
rx_id = (uint16_t) ((rxq->rxrearm_start == 0) ?
(rxq->nb_rx_desc - 1) : (rxq->rxrearm_start - 1));
/* Update the tail pointer on the NIC */
IXGBE_PCI_REG_WRITE(rxq->rdt_reg_addr, rx_id);
}