+
+static inline void
+fm10k_rxq_rearm(struct fm10k_rx_queue *rxq)
+{
+ int i;
+ uint16_t rx_id;
+ volatile union fm10k_rx_desc *rxdp;
+ struct rte_mbuf **mb_alloc = &rxq->sw_ring[rxq->rxrearm_start];
+ struct rte_mbuf *mb0, *mb1;
+ __m128i head_off = _mm_set_epi64x(
+ RTE_PKTMBUF_HEADROOM + FM10K_RX_DATABUF_ALIGN - 1,
+ RTE_PKTMBUF_HEADROOM + FM10K_RX_DATABUF_ALIGN - 1);
+ __m128i dma_addr0, dma_addr1;
+ /* Rx buffer need to be aligned with 512 byte */
+ const __m128i hba_msk = _mm_set_epi64x(0,
+ UINT64_MAX - FM10K_RX_DATABUF_ALIGN + 1);
+
+ rxdp = rxq->hw_ring + rxq->rxrearm_start;
+
+ /* Pull 'n' more MBUFs into the software ring */
+ if (rte_mempool_get_bulk(rxq->mp,
+ (void *)mb_alloc,
+ RTE_FM10K_RXQ_REARM_THRESH) < 0) {
+ dma_addr0 = _mm_setzero_si128();
+ /* Clean up all the HW/SW ring content */
+ for (i = 0; i < RTE_FM10K_RXQ_REARM_THRESH; i++) {
+ mb_alloc[i] = &rxq->fake_mbuf;
+ _mm_store_si128((__m128i *)&rxdp[i].q,
+ dma_addr0);
+ }
+
+ rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed +=
+ RTE_FM10K_RXQ_REARM_THRESH;
+ return;
+ }
+
+ /* Initialize the mbufs in vector, process 2 mbufs in one loop */
+ for (i = 0; i < RTE_FM10K_RXQ_REARM_THRESH; i += 2, mb_alloc += 2) {
+ __m128i vaddr0, vaddr1;
+ uintptr_t p0, p1;
+
+ mb0 = mb_alloc[0];
+ mb1 = mb_alloc[1];
+
+ /* Flush mbuf with pkt template.
+ * Data to be rearmed is 6 bytes long.
+ */
+ 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_iova(hi 64bit) */
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, buf_iova) !=
+ offsetof(struct rte_mbuf, buf_addr) + 8);
+ 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, head_off);
+ dma_addr1 = _mm_add_epi64(dma_addr1, head_off);
+
+ /* Do 512 byte alignment to satisfy HW requirement, in the
+ * meanwhile, 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++->q, dma_addr0);
+ _mm_store_si128((__m128i *)&rxdp++->q, dma_addr1);
+
+ /* enforce 512B alignment on default Rx virtual addresses */
+ mb0->data_off = (uint16_t)(RTE_PTR_ALIGN((char *)mb0->buf_addr
+ + RTE_PKTMBUF_HEADROOM, FM10K_RX_DATABUF_ALIGN)
+ - (char *)mb0->buf_addr);
+ mb1->data_off = (uint16_t)(RTE_PTR_ALIGN((char *)mb1->buf_addr
+ + RTE_PKTMBUF_HEADROOM, FM10K_RX_DATABUF_ALIGN)
+ - (char *)mb1->buf_addr);
+ }
+
+ rxq->rxrearm_start += RTE_FM10K_RXQ_REARM_THRESH;
+ if (rxq->rxrearm_start >= rxq->nb_desc)
+ rxq->rxrearm_start = 0;
+
+ rxq->rxrearm_nb -= RTE_FM10K_RXQ_REARM_THRESH;
+
+ rx_id = (uint16_t)((rxq->rxrearm_start == 0) ?
+ (rxq->nb_desc - 1) : (rxq->rxrearm_start - 1));
+
+ /* Update the tail pointer on the NIC */
+ FM10K_PCI_REG_WRITE(rxq->tail_ptr, rx_id);
+}
+
+void __rte_cold
+fm10k_rx_queue_release_mbufs_vec(struct fm10k_rx_queue *rxq)
+{
+ const unsigned mask = rxq->nb_desc - 1;
+ unsigned i;
+
+ if (rxq->sw_ring == NULL || rxq->rxrearm_nb >= rxq->nb_desc)
+ return;
+
+ /* free all mbufs that are valid in the ring */
+ if (rxq->rxrearm_nb == 0) {
+ for (i = 0; i < rxq->nb_desc; i++)
+ if (rxq->sw_ring[i] != NULL)
+ rte_pktmbuf_free_seg(rxq->sw_ring[i]);
+ } else {
+ for (i = rxq->next_dd; i != rxq->rxrearm_start;
+ i = (i + 1) & mask)
+ rte_pktmbuf_free_seg(rxq->sw_ring[i]);
+ }
+ rxq->rxrearm_nb = rxq->nb_desc;
+
+ /* set all entries to NULL */
+ memset(rxq->sw_ring, 0, sizeof(rxq->sw_ring[0]) * rxq->nb_desc);
+}
+
+static inline uint16_t
+fm10k_recv_raw_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts, uint8_t *split_packet)
+{
+ volatile union fm10k_rx_desc *rxdp;
+ struct rte_mbuf **mbufp;
+ uint16_t nb_pkts_recd;
+ int pos;
+ struct fm10k_rx_queue *rxq = rx_queue;
+ uint64_t var;
+ __m128i shuf_msk;
+ __m128i dd_check, eop_check;
+ uint16_t next_dd;
+
+ next_dd = rxq->next_dd;
+
+ /* Just the act of getting into the function from the application is
+ * going to cost about 7 cycles
+ */
+ rxdp = rxq->hw_ring + next_dd;
+
+ rte_prefetch0(rxdp);
+
+ /* See if we need to rearm the RX queue - gives the prefetch a bit
+ * of time to act
+ */
+ if (rxq->rxrearm_nb > RTE_FM10K_RXQ_REARM_THRESH)
+ fm10k_rxq_rearm(rxq);
+
+ /* Before we start moving massive data around, check to see if
+ * there is actually a packet available
+ */
+ if (!(rxdp->d.staterr & FM10K_RXD_STATUS_DD))
+ return 0;
+
+ /* Vecotr RX will process 4 packets at a time, strip the unaligned
+ * tails in case it's not multiple of 4.
+ */
+ nb_pkts = RTE_ALIGN_FLOOR(nb_pkts, RTE_FM10K_DESCS_PER_LOOP);
+
+ /* 4 packets DD mask */
+ dd_check = _mm_set_epi64x(0x0000000100000001LL, 0x0000000100000001LL);
+
+ /* 4 packets EOP mask */
+ eop_check = _mm_set_epi64x(0x0000000200000002LL, 0x0000000200000002LL);
+
+ /* mask to shuffle from desc. to mbuf */
+ shuf_msk = _mm_set_epi8(
+ 7, 6, 5, 4, /* octet 4~7, 32bits rss */
+ 15, 14, /* octet 14~15, low 16 bits vlan_macip */
+ 13, 12, /* octet 12~13, 16 bits data_len */
+ 0xFF, 0xFF, /* skip high 16 bits pkt_len, zero out */
+ 13, 12, /* octet 12~13, low 16 bits pkt_len */
+ 0xFF, 0xFF, /* skip high 16 bits pkt_type */
+ 0xFF, 0xFF /* Skip pkt_type field in shuffle operation */
+ );
+ /*
+ * Compile-time verify the shuffle mask
+ * NOTE: some field positions already verified above, but duplicated
+ * here for completeness in case of future modifications.
+ */
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, pkt_len) !=
+ offsetof(struct rte_mbuf, rx_descriptor_fields1) + 4);
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, data_len) !=
+ offsetof(struct rte_mbuf, rx_descriptor_fields1) + 8);
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, vlan_tci) !=
+ offsetof(struct rte_mbuf, rx_descriptor_fields1) + 10);
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, hash) !=
+ offsetof(struct rte_mbuf, rx_descriptor_fields1) + 12);
+
+ /* Cache is empty -> need to scan the buffer rings, but first move
+ * the next 'n' mbufs into the cache
+ */
+ mbufp = &rxq->sw_ring[next_dd];
+
+ /* A. load 4 packet in one loop
+ * [A*. mask out 4 unused dirty field in desc]
+ * B. copy 4 mbuf point from swring to rx_pkts
+ * C. calc the number of DD bits among the 4 packets
+ * [C*. extract the end-of-packet bit, if requested]
+ * D. fill info. from desc to mbuf
+ */
+ for (pos = 0, nb_pkts_recd = 0; pos < nb_pkts;
+ pos += RTE_FM10K_DESCS_PER_LOOP,
+ rxdp += RTE_FM10K_DESCS_PER_LOOP) {
+ __m128i descs0[RTE_FM10K_DESCS_PER_LOOP];
+ __m128i pkt_mb1, pkt_mb2, pkt_mb3, pkt_mb4;
+ __m128i zero, staterr, sterr_tmp1, sterr_tmp2;
+ __m128i mbp1;
+ /* 2 64 bit or 4 32 bit mbuf pointers in one XMM reg. */
+#if defined(RTE_ARCH_X86_64)
+ __m128i mbp2;
+#endif
+
+ /* B.1 load 2 (64 bit) or 4 (32 bit) mbuf points */
+ mbp1 = _mm_loadu_si128((__m128i *)&mbufp[pos]);
+
+ /* Read desc statuses backwards to avoid race condition */
+ /* A.1 load 4 pkts desc */
+ descs0[3] = _mm_loadu_si128((__m128i *)(rxdp + 3));
+ rte_compiler_barrier();
+
+ /* B.2 copy 2 64 bit or 4 32 bit mbuf point into rx_pkts */
+ _mm_storeu_si128((__m128i *)&rx_pkts[pos], mbp1);
+
+#if defined(RTE_ARCH_X86_64)
+ /* B.1 load 2 64 bit mbuf poitns */
+ mbp2 = _mm_loadu_si128((__m128i *)&mbufp[pos+2]);
+#endif
+
+ descs0[2] = _mm_loadu_si128((__m128i *)(rxdp + 2));
+ rte_compiler_barrier();
+ /* B.1 load 2 mbuf point */
+ descs0[1] = _mm_loadu_si128((__m128i *)(rxdp + 1));
+ rte_compiler_barrier();
+ descs0[0] = _mm_loadu_si128((__m128i *)(rxdp));
+
+#if defined(RTE_ARCH_X86_64)
+ /* B.2 copy 2 mbuf point into rx_pkts */
+ _mm_storeu_si128((__m128i *)&rx_pkts[pos+2], mbp2);
+#endif
+
+ /* avoid compiler reorder optimization */
+ rte_compiler_barrier();
+
+ if (split_packet) {
+ rte_mbuf_prefetch_part2(rx_pkts[pos]);
+ rte_mbuf_prefetch_part2(rx_pkts[pos + 1]);
+ rte_mbuf_prefetch_part2(rx_pkts[pos + 2]);
+ rte_mbuf_prefetch_part2(rx_pkts[pos + 3]);
+ }
+
+ /* D.1 pkt 3,4 convert format from desc to pktmbuf */
+ pkt_mb4 = _mm_shuffle_epi8(descs0[3], shuf_msk);
+ pkt_mb3 = _mm_shuffle_epi8(descs0[2], shuf_msk);
+
+ /* C.1 4=>2 filter staterr info only */
+ sterr_tmp2 = _mm_unpackhi_epi32(descs0[3], descs0[2]);
+ /* C.1 4=>2 filter staterr info only */
+ sterr_tmp1 = _mm_unpackhi_epi32(descs0[1], descs0[0]);
+
+ /* set ol_flags with vlan packet type */
+ fm10k_desc_to_olflags_v(descs0, &rx_pkts[pos]);
+
+ /* D.1 pkt 1,2 convert format from desc to pktmbuf */
+ pkt_mb2 = _mm_shuffle_epi8(descs0[1], shuf_msk);
+ pkt_mb1 = _mm_shuffle_epi8(descs0[0], shuf_msk);
+
+ /* C.2 get 4 pkts staterr value */
+ zero = _mm_xor_si128(dd_check, dd_check);
+ staterr = _mm_unpacklo_epi32(sterr_tmp1, sterr_tmp2);
+
+ /* D.3 copy final 3,4 data to rx_pkts */
+ _mm_storeu_si128((void *)&rx_pkts[pos+3]->rx_descriptor_fields1,
+ pkt_mb4);
+ _mm_storeu_si128((void *)&rx_pkts[pos+2]->rx_descriptor_fields1,
+ pkt_mb3);
+
+ /* C* extract and record EOP bit */
+ if (split_packet) {
+ __m128i eop_shuf_mask = _mm_set_epi8(
+ 0xFF, 0xFF, 0xFF, 0xFF,
+ 0xFF, 0xFF, 0xFF, 0xFF,
+ 0xFF, 0xFF, 0xFF, 0xFF,
+ 0x04, 0x0C, 0x00, 0x08
+ );
+
+ /* and with mask to extract bits, flipping 1-0 */
+ __m128i eop_bits = _mm_andnot_si128(staterr, eop_check);
+ /* the staterr values are not in order, as the count
+ * count of dd bits doesn't care. However, for end of
+ * packet tracking, we do care, so shuffle. This also
+ * compresses the 32-bit values to 8-bit
+ */
+ eop_bits = _mm_shuffle_epi8(eop_bits, eop_shuf_mask);
+ /* store the resulting 32-bit value */
+ *(int *)split_packet = _mm_cvtsi128_si32(eop_bits);
+ split_packet += RTE_FM10K_DESCS_PER_LOOP;
+
+ /* zero-out next pointers */
+ rx_pkts[pos]->next = NULL;
+ rx_pkts[pos + 1]->next = NULL;
+ rx_pkts[pos + 2]->next = NULL;
+ rx_pkts[pos + 3]->next = NULL;
+ }
+
+ /* C.3 calc available number of desc */
+ staterr = _mm_and_si128(staterr, dd_check);
+ staterr = _mm_packs_epi32(staterr, zero);
+
+ /* D.3 copy final 1,2 data to rx_pkts */
+ _mm_storeu_si128((void *)&rx_pkts[pos+1]->rx_descriptor_fields1,
+ pkt_mb2);
+ _mm_storeu_si128((void *)&rx_pkts[pos]->rx_descriptor_fields1,
+ pkt_mb1);
+
+ fm10k_desc_to_pktype_v(descs0, &rx_pkts[pos]);
+
+ /* C.4 calc avaialbe number of desc */
+ var = __builtin_popcountll(_mm_cvtsi128_si64(staterr));
+ nb_pkts_recd += var;
+ if (likely(var != RTE_FM10K_DESCS_PER_LOOP))
+ break;
+ }
+
+ /* Update our internal tail pointer */
+ rxq->next_dd = (uint16_t)(rxq->next_dd + nb_pkts_recd);
+ rxq->next_dd = (uint16_t)(rxq->next_dd & (rxq->nb_desc - 1));
+ rxq->rxrearm_nb = (uint16_t)(rxq->rxrearm_nb + nb_pkts_recd);
+
+ return nb_pkts_recd;
+}
+
+/* vPMD receive routine
+ *
+ * Notice:
+ * - don't support ol_flags for rss and csum err
+ */
+uint16_t
+fm10k_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts)
+{
+ return fm10k_recv_raw_pkts_vec(rx_queue, rx_pkts, nb_pkts, NULL);
+}
+
+static inline uint16_t
+fm10k_reassemble_packets(struct fm10k_rx_queue *rxq,
+ struct rte_mbuf **rx_bufs,
+ uint16_t nb_bufs, uint8_t *split_flags)
+{
+ struct rte_mbuf *pkts[RTE_FM10K_MAX_RX_BURST]; /*finished pkts*/
+ struct rte_mbuf *start = rxq->pkt_first_seg;
+ struct rte_mbuf *end = rxq->pkt_last_seg;
+ unsigned pkt_idx, buf_idx;
+
+ for (buf_idx = 0, pkt_idx = 0; buf_idx < nb_bufs; buf_idx++) {
+ if (end != NULL) {
+ /* processing a split packet */
+ end->next = rx_bufs[buf_idx];
+ start->nb_segs++;
+ start->pkt_len += rx_bufs[buf_idx]->data_len;
+ end = end->next;
+
+ if (!split_flags[buf_idx]) {
+ /* it's the last packet of the set */
+#ifdef RTE_LIBRTE_FM10K_RX_OLFLAGS_ENABLE
+ start->hash = end->hash;
+ start->ol_flags = end->ol_flags;
+ start->packet_type = end->packet_type;
+#endif
+ pkts[pkt_idx++] = start;
+ start = end = NULL;
+ }
+ } else {
+ /* not processing a split packet */
+ if (!split_flags[buf_idx]) {
+ /* not a split packet, save and skip */
+ pkts[pkt_idx++] = rx_bufs[buf_idx];
+ continue;
+ }
+ end = start = rx_bufs[buf_idx];
+ }
+ }
+
+ /* save the partial packet for next time */
+ rxq->pkt_first_seg = start;
+ rxq->pkt_last_seg = end;
+ memcpy(rx_bufs, pkts, pkt_idx * (sizeof(*pkts)));
+ return pkt_idx;
+}
+
+/**
+ * vPMD receive routine that reassembles single burst of 32 scattered packets
+ *
+ * Notice:
+ * - don't support ol_flags for rss and csum err
+ */
+static uint16_t
+fm10k_recv_scattered_burst_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts)
+{
+ struct fm10k_rx_queue *rxq = rx_queue;
+ uint8_t split_flags[RTE_FM10K_MAX_RX_BURST] = {0};
+ unsigned i = 0;
+
+ /* Split_flags only can support max of RTE_FM10K_MAX_RX_BURST */
+ nb_pkts = RTE_MIN(nb_pkts, RTE_FM10K_MAX_RX_BURST);
+ /* get some new buffers */
+ uint16_t nb_bufs = fm10k_recv_raw_pkts_vec(rxq, rx_pkts, nb_pkts,
+ split_flags);
+ if (nb_bufs == 0)
+ return 0;
+
+ /* happy day case, full burst + no packets to be joined */
+ const uint64_t *split_fl64 = (uint64_t *)split_flags;
+
+ if (rxq->pkt_first_seg == NULL &&
+ split_fl64[0] == 0 && split_fl64[1] == 0 &&
+ split_fl64[2] == 0 && split_fl64[3] == 0)
+ return nb_bufs;
+
+ /* reassemble any packets that need reassembly*/
+ if (rxq->pkt_first_seg == NULL) {
+ /* find the first split flag, and only reassemble then*/
+ while (i < nb_bufs && !split_flags[i])
+ i++;
+ if (i == nb_bufs)
+ return nb_bufs;
+ rxq->pkt_first_seg = rx_pkts[i];
+ }
+ return i + fm10k_reassemble_packets(rxq, &rx_pkts[i], nb_bufs - i,
+ &split_flags[i]);
+}
+
+/**
+ * vPMD receive routine that reassembles scattered packets.
+ */
+uint16_t
+fm10k_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts)
+{
+ uint16_t retval = 0;
+
+ while (nb_pkts > RTE_FM10K_MAX_RX_BURST) {
+ uint16_t burst;
+
+ burst = fm10k_recv_scattered_burst_vec(rx_queue,
+ rx_pkts + retval,
+ RTE_FM10K_MAX_RX_BURST);
+ retval += burst;
+ nb_pkts -= burst;
+ if (burst < RTE_FM10K_MAX_RX_BURST)
+ return retval;
+ }
+
+ return retval + fm10k_recv_scattered_burst_vec(rx_queue,
+ rx_pkts + retval,
+ nb_pkts);
+}
+
+static const struct fm10k_txq_ops vec_txq_ops = {
+ .reset = fm10k_reset_tx_queue,
+};
+
+void __rte_cold
+fm10k_txq_vec_setup(struct fm10k_tx_queue *txq)
+{
+ txq->ops = &vec_txq_ops;
+}
+
+int __rte_cold
+fm10k_tx_vec_condition_check(struct fm10k_tx_queue *txq)
+{
+ /* Vector TX can't offload any features yet */
+ if (txq->offloads != 0)
+ return -1;
+
+ if (txq->tx_ftag_en)
+ return -1;
+
+ return 0;
+}
+
+static inline void
+vtx1(volatile struct fm10k_tx_desc *txdp,
+ struct rte_mbuf *pkt, uint64_t flags)
+{
+ __m128i descriptor = _mm_set_epi64x(flags << 56 |
+ (uint64_t)pkt->vlan_tci << 16 | (uint64_t)pkt->data_len,
+ MBUF_DMA_ADDR(pkt));
+ _mm_store_si128((__m128i *)txdp, descriptor);
+}
+
+static inline void
+vtx(volatile struct fm10k_tx_desc *txdp,
+ struct rte_mbuf **pkt, uint16_t nb_pkts, uint64_t flags)
+{
+ int i;
+
+ for (i = 0; i < nb_pkts; ++i, ++txdp, ++pkt)
+ vtx1(txdp, *pkt, flags);
+}
+
+static __rte_always_inline int
+fm10k_tx_free_bufs(struct fm10k_tx_queue *txq)
+{
+ struct rte_mbuf **txep;
+ uint8_t flags;
+ uint32_t n;
+ uint32_t i;
+ int nb_free = 0;
+ struct rte_mbuf *m, *free[RTE_FM10K_TX_MAX_FREE_BUF_SZ];
+
+ /* check DD bit on threshold descriptor */
+ flags = txq->hw_ring[txq->next_dd].flags;
+ if (!(flags & FM10K_TXD_FLAG_DONE))
+ return 0;
+
+ n = txq->rs_thresh;
+
+ /* First buffer to free from S/W ring is at index
+ * next_dd - (rs_thresh-1)
+ */
+ txep = &txq->sw_ring[txq->next_dd - (n - 1)];
+ m = rte_pktmbuf_prefree_seg(txep[0]);
+ if (likely(m != NULL)) {
+ free[0] = m;
+ nb_free = 1;
+ for (i = 1; i < n; i++) {
+ m = rte_pktmbuf_prefree_seg(txep[i]);
+ if (likely(m != NULL)) {
+ if (likely(m->pool == free[0]->pool))
+ free[nb_free++] = m;
+ else {
+ rte_mempool_put_bulk(free[0]->pool,
+ (void *)free, nb_free);
+ free[0] = m;
+ nb_free = 1;
+ }
+ }
+ }
+ rte_mempool_put_bulk(free[0]->pool, (void **)free, nb_free);
+ } else {
+ for (i = 1; i < n; i++) {
+ m = rte_pktmbuf_prefree_seg(txep[i]);
+ if (m != NULL)
+ rte_mempool_put(m->pool, m);
+ }
+ }
+
+ /* buffers were freed, update counters */
+ txq->nb_free = (uint16_t)(txq->nb_free + txq->rs_thresh);
+ txq->next_dd = (uint16_t)(txq->next_dd + txq->rs_thresh);
+ if (txq->next_dd >= txq->nb_desc)
+ txq->next_dd = (uint16_t)(txq->rs_thresh - 1);
+
+ return txq->rs_thresh;
+}
+
+static __rte_always_inline void
+tx_backlog_entry(struct rte_mbuf **txep,
+ struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
+{
+ int i;
+
+ for (i = 0; i < (int)nb_pkts; ++i)
+ txep[i] = tx_pkts[i];
+}
+
+uint16_t
+fm10k_xmit_fixed_burst_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
+ uint16_t nb_pkts)
+{
+ struct fm10k_tx_queue *txq = (struct fm10k_tx_queue *)tx_queue;
+ volatile struct fm10k_tx_desc *txdp;
+ struct rte_mbuf **txep;
+ uint16_t n, nb_commit, tx_id;
+ uint64_t flags = FM10K_TXD_FLAG_LAST;
+ uint64_t rs = FM10K_TXD_FLAG_RS | FM10K_TXD_FLAG_LAST;
+ int i;
+
+ /* cross rx_thresh boundary is not allowed */
+ nb_pkts = RTE_MIN(nb_pkts, txq->rs_thresh);
+
+ if (txq->nb_free < txq->free_thresh)
+ fm10k_tx_free_bufs(txq);
+
+ nb_commit = nb_pkts = (uint16_t)RTE_MIN(txq->nb_free, nb_pkts);
+ if (unlikely(nb_pkts == 0))
+ return 0;
+
+ tx_id = txq->next_free;
+ txdp = &txq->hw_ring[tx_id];
+ txep = &txq->sw_ring[tx_id];
+
+ txq->nb_free = (uint16_t)(txq->nb_free - nb_pkts);
+
+ n = (uint16_t)(txq->nb_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->next_rs = (uint16_t)(txq->rs_thresh - 1);
+
+ /* avoid reach the end of ring */
+ txdp = &(txq->hw_ring[tx_id]);
+ txep = &txq->sw_ring[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->next_rs) {
+ txq->hw_ring[txq->next_rs].flags |= FM10K_TXD_FLAG_RS;
+ txq->next_rs = (uint16_t)(txq->next_rs + txq->rs_thresh);
+ }
+
+ txq->next_free = tx_id;
+
+ FM10K_PCI_REG_WRITE(txq->tail_ptr, txq->next_free);
+
+ return nb_pkts;
+}
+
+static void __rte_cold
+fm10k_reset_tx_queue(struct fm10k_tx_queue *txq)
+{
+ static const struct fm10k_tx_desc zeroed_desc = {0};
+ struct rte_mbuf **txe = txq->sw_ring;
+ uint16_t i;
+
+ /* Zero out HW ring memory */
+ for (i = 0; i < txq->nb_desc; i++)
+ txq->hw_ring[i] = zeroed_desc;
+
+ /* Initialize SW ring entries */
+ for (i = 0; i < txq->nb_desc; i++)
+ txe[i] = NULL;
+
+ txq->next_dd = (uint16_t)(txq->rs_thresh - 1);
+ txq->next_rs = (uint16_t)(txq->rs_thresh - 1);
+
+ txq->next_free = 0;
+ txq->nb_used = 0;
+ /* Always allow 1 descriptor to be un-allocated to avoid
+ * a H/W race condition
+ */
+ txq->nb_free = (uint16_t)(txq->nb_desc - 1);
+ FM10K_PCI_REG_WRITE(txq->tail_ptr, 0);
+}