- rx_pkts[0]->ol_flags = _mm_extract_epi16(vlan0, 0);
- rx_pkts[1]->ol_flags = _mm_extract_epi16(vlan0, 2);
- rx_pkts[2]->ol_flags = _mm_extract_epi16(vlan0, 4);
- rx_pkts[3]->ol_flags = _mm_extract_epi16(vlan0, 6);
+ /*
+ * At this point, we have the 4 sets of flags in the low 16-bits
+ * of each 32-bit value in vlan0.
+ * We want to extract these, and merge them with the mbuf init data
+ * so we can do a single 16-byte write to the mbuf to set the flags
+ * and all the other initialization fields. Extracting the
+ * appropriate flags means that we have to do a shift and blend for
+ * each mbuf before we do the write.
+ */
+ rearm0 = _mm_blend_epi16(mbuf_init, _mm_slli_si128(vlan0, 8), 0x10);
+ rearm1 = _mm_blend_epi16(mbuf_init, _mm_slli_si128(vlan0, 4), 0x10);
+ rearm2 = _mm_blend_epi16(mbuf_init, vlan0, 0x10);
+ rearm3 = _mm_blend_epi16(mbuf_init, _mm_srli_si128(vlan0, 4), 0x10);
+
+ /* write the rearm data and the olflags in one write */
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, ol_flags) !=
+ offsetof(struct rte_mbuf, rearm_data) + 8);
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, rearm_data) !=
+ RTE_ALIGN(offsetof(struct rte_mbuf, rearm_data), 16));
+ _mm_store_si128((__m128i *)&rx_pkts[0]->rearm_data, rearm0);
+ _mm_store_si128((__m128i *)&rx_pkts[1]->rearm_data, rearm1);
+ _mm_store_si128((__m128i *)&rx_pkts[2]->rearm_data, rearm2);
+ _mm_store_si128((__m128i *)&rx_pkts[3]->rearm_data, rearm3);