+/**
+ * vPMD raw receive routine for flex RxD,
+ * only accept(nb_pkts >= IAVF_VPMD_DESCS_PER_LOOP)
+ *
+ * Notice:
+ * - nb_pkts < IAVF_VPMD_DESCS_PER_LOOP, just return no packet
+ * - floor align nb_pkts to a IAVF_VPMD_DESCS_PER_LOOP power-of-two
+ */
+static inline uint16_t
+_recv_raw_pkts_vec_flex_rxd(struct iavf_rx_queue *rxq,
+ struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts, uint8_t *split_packet)
+{
+ volatile union iavf_rx_flex_desc *rxdp;
+ struct rte_mbuf **sw_ring;
+ uint16_t nb_pkts_recd;
+ int pos;
+ uint64_t var;
+ const uint32_t *ptype_tbl = rxq->vsi->adapter->ptype_tbl;
+ __m128i crc_adjust = _mm_set_epi16
+ (0, 0, 0, /* ignore non-length fields */
+ -rxq->crc_len, /* sub crc on data_len */
+ 0, /* ignore high-16bits of pkt_len */
+ -rxq->crc_len, /* sub crc on pkt_len */
+ 0, 0 /* ignore pkt_type field */
+ );
+ const __m128i zero = _mm_setzero_si128();
+ /* mask to shuffle from desc. to mbuf */
+ const __m128i shuf_msk = _mm_set_epi8
+ (0xFF, 0xFF,
+ 0xFF, 0xFF, /* rss hash parsed separately */
+ 11, 10, /* octet 10~11, 16 bits vlan_macip */
+ 5, 4, /* octet 4~5, 16 bits data_len */
+ 0xFF, 0xFF, /* skip high 16 bits pkt_len, zero out */
+ 5, 4, /* octet 4~5, low 16 bits pkt_len */
+ 0xFF, 0xFF, /* pkt_type set as unknown */
+ 0xFF, 0xFF /* pkt_type set as unknown */
+ );
+ const __m128i eop_shuf_mask = _mm_set_epi8(0xFF, 0xFF,
+ 0xFF, 0xFF,
+ 0xFF, 0xFF,
+ 0xFF, 0xFF,
+ 0xFF, 0xFF,
+ 0xFF, 0xFF,
+ 0x04, 0x0C,
+ 0x00, 0x08);
+
+ /**
+ * compile-time check the above crc_adjust layout is correct.
+ * NOTE: the first field (lowest address) is given last in set_epi16
+ * call above.
+ */
+ 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);
+
+ /* 4 packets DD mask */
+ const __m128i dd_check = _mm_set_epi64x(0x0000000100000001LL,
+ 0x0000000100000001LL);
+ /* 4 packets EOP mask */
+ const __m128i eop_check = _mm_set_epi64x(0x0000000200000002LL,
+ 0x0000000200000002LL);
+
+ /* nb_pkts has to be floor-aligned to IAVF_VPMD_DESCS_PER_LOOP */
+ nb_pkts = RTE_ALIGN_FLOOR(nb_pkts, IAVF_VPMD_DESCS_PER_LOOP);
+
+ /* Just the act of getting into the function from the application is
+ * going to cost about 7 cycles
+ */
+ rxdp = (union iavf_rx_flex_desc *)rxq->rx_ring + rxq->rx_tail;
+
+ 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 > rxq->rx_free_thresh)
+ iavf_rxq_rearm(rxq);
+
+ /* Before we start moving massive data around, check to see if
+ * there is actually a packet available
+ */
+ if (!(rxdp->wb.status_error0 &
+ rte_cpu_to_le_32(1 << IAVF_RX_FLEX_DESC_STATUS0_DD_S)))
+ return 0;
+
+ /**
+ * 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
+ */
+ sw_ring = &rxq->sw_ring[rxq->rx_tail];
+
+ /* 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 += IAVF_VPMD_DESCS_PER_LOOP,
+ rxdp += IAVF_VPMD_DESCS_PER_LOOP) {
+ __m128i descs[IAVF_VPMD_DESCS_PER_LOOP];
+ __m128i pkt_mb0, pkt_mb1, pkt_mb2, pkt_mb3;
+ __m128i staterr, sterr_tmp1, sterr_tmp2;
+ /* 2 64 bit or 4 32 bit mbuf pointers in one XMM reg. */
+ __m128i mbp1;
+#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 *)&sw_ring[pos]);
+ /* Read desc statuses backwards to avoid race condition */
+ /* A.1 load 4 pkts desc */
+ descs[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 points */
+ mbp2 = _mm_loadu_si128((__m128i *)&sw_ring[pos + 2]);
+#endif
+
+ descs[2] = _mm_loadu_si128((__m128i *)(rxdp + 2));
+ rte_compiler_barrier();
+ /* B.1 load 2 mbuf point */
+ descs[1] = _mm_loadu_si128((__m128i *)(rxdp + 1));
+ rte_compiler_barrier();
+ descs[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
+
+ 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]);
+ }
+
+ /* avoid compiler reorder optimization */
+ rte_compiler_barrier();
+
+ /* D.1 pkt 3,4 convert format from desc to pktmbuf */
+ pkt_mb3 = _mm_shuffle_epi8(descs[3], shuf_msk);
+ pkt_mb2 = _mm_shuffle_epi8(descs[2], shuf_msk);
+
+ /* D.1 pkt 1,2 convert format from desc to pktmbuf */
+ pkt_mb1 = _mm_shuffle_epi8(descs[1], shuf_msk);
+ pkt_mb0 = _mm_shuffle_epi8(descs[0], shuf_msk);
+
+ /* C.1 4=>2 filter staterr info only */
+ sterr_tmp2 = _mm_unpackhi_epi32(descs[3], descs[2]);
+ /* C.1 4=>2 filter staterr info only */
+ sterr_tmp1 = _mm_unpackhi_epi32(descs[1], descs[0]);
+
+ flex_desc_to_olflags_v(rxq, descs, &rx_pkts[pos]);
+
+ /* D.2 pkt 3,4 set in_port/nb_seg and remove crc */
+ pkt_mb3 = _mm_add_epi16(pkt_mb3, crc_adjust);
+ pkt_mb2 = _mm_add_epi16(pkt_mb2, crc_adjust);
+
+ /* D.2 pkt 1,2 set in_port/nb_seg and remove crc */
+ pkt_mb1 = _mm_add_epi16(pkt_mb1, crc_adjust);
+ pkt_mb0 = _mm_add_epi16(pkt_mb0, crc_adjust);
+
+#ifndef RTE_LIBRTE_IAVF_16BYTE_RX_DESC
+ /**
+ * needs to load 2nd 16B of each desc for RSS hash parsing,
+ * will cause performance drop to get into this context.
+ */
+ if (rxq->vsi->adapter->eth_dev->data->dev_conf.rxmode.offloads &
+ DEV_RX_OFFLOAD_RSS_HASH) {
+ /* load bottom half of every 32B desc */
+ const __m128i raw_desc_bh3 =
+ _mm_load_si128
+ ((void *)(&rxdp[3].wb.status_error1));
+ rte_compiler_barrier();
+ const __m128i raw_desc_bh2 =
+ _mm_load_si128
+ ((void *)(&rxdp[2].wb.status_error1));
+ rte_compiler_barrier();
+ const __m128i raw_desc_bh1 =
+ _mm_load_si128
+ ((void *)(&rxdp[1].wb.status_error1));
+ rte_compiler_barrier();
+ const __m128i raw_desc_bh0 =
+ _mm_load_si128
+ ((void *)(&rxdp[0].wb.status_error1));
+
+ /**
+ * to shift the 32b RSS hash value to the
+ * highest 32b of each 128b before mask
+ */
+ __m128i rss_hash3 =
+ _mm_slli_epi64(raw_desc_bh3, 32);
+ __m128i rss_hash2 =
+ _mm_slli_epi64(raw_desc_bh2, 32);
+ __m128i rss_hash1 =
+ _mm_slli_epi64(raw_desc_bh1, 32);
+ __m128i rss_hash0 =
+ _mm_slli_epi64(raw_desc_bh0, 32);
+
+ __m128i rss_hash_msk =
+ _mm_set_epi32(0xFFFFFFFF, 0, 0, 0);
+
+ rss_hash3 = _mm_and_si128
+ (rss_hash3, rss_hash_msk);
+ rss_hash2 = _mm_and_si128
+ (rss_hash2, rss_hash_msk);
+ rss_hash1 = _mm_and_si128
+ (rss_hash1, rss_hash_msk);
+ rss_hash0 = _mm_and_si128
+ (rss_hash0, rss_hash_msk);
+
+ pkt_mb3 = _mm_or_si128(pkt_mb3, rss_hash3);
+ pkt_mb2 = _mm_or_si128(pkt_mb2, rss_hash2);
+ pkt_mb1 = _mm_or_si128(pkt_mb1, rss_hash1);
+ pkt_mb0 = _mm_or_si128(pkt_mb0, rss_hash0);
+ } /* if() on RSS hash parsing */
+#endif
+
+ /* C.2 get 4 pkts staterr value */
+ 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_mb3);
+ _mm_storeu_si128
+ ((void *)&rx_pkts[pos + 2]->rx_descriptor_fields1,
+ pkt_mb2);
+
+ /* C* extract and record EOP bit */
+ if (split_packet) {
+ /* 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 += IAVF_VPMD_DESCS_PER_LOOP;
+ }
+
+ /* 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_mb1);
+ _mm_storeu_si128((void *)&rx_pkts[pos]->rx_descriptor_fields1,
+ pkt_mb0);
+ flex_desc_to_ptype_v(descs, &rx_pkts[pos], ptype_tbl);
+ /* C.4 calc available number of desc */
+ var = __builtin_popcountll(_mm_cvtsi128_si64(staterr));
+ nb_pkts_recd += var;
+ if (likely(var != IAVF_VPMD_DESCS_PER_LOOP))
+ break;
+ }
+
+ /* Update our internal tail pointer */
+ rxq->rx_tail = (uint16_t)(rxq->rx_tail + nb_pkts_recd);
+ rxq->rx_tail = (uint16_t)(rxq->rx_tail & (rxq->nb_rx_desc - 1));
+ rxq->rxrearm_nb = (uint16_t)(rxq->rxrearm_nb + nb_pkts_recd);
+
+ return nb_pkts_recd;
+}
+