X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fixgbe%2Fixgbe_rxtx_vec_sse.c;h=e704a7f355e764642661a87e9e9d3681d4fc9b31;hb=3b212853e478e45490668ea054ec351da1fbda43;hp=82a68de36b17d85a9da5537d6004c1e15f7eb26e;hpb=dc448dc4609fb82655283c8e51692e33a01d8fe7;p=dpdk.git diff --git a/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c b/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c index 82a68de36b..e704a7f355 100644 --- a/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c +++ b/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c @@ -82,21 +82,13 @@ ixgbe_rxq_rearm(struct ixgbe_rx_queue *rxq) /* 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. - */ - 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) */ + RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, buf_physaddr) != + offsetof(struct rte_mbuf, buf_addr) + 8); vaddr0 = _mm_loadu_si128((__m128i *)&(mb0->buf_addr)); vaddr1 = _mm_loadu_si128((__m128i *)&(mb1->buf_addr)); @@ -130,23 +122,12 @@ ixgbe_rxq_rearm(struct ixgbe_rx_queue *rxq) IXGBE_PCI_REG_WRITE(rxq->rdt_reg_addr, rx_id); } -/* Handling the offload flags (olflags) field takes computation - * time when receiving packets. Therefore we provide a flag to disable - * the processing of the olflags field when they are not needed. This - * gives improved performance, at the cost of losing the offload info - * in the received packet - */ -#ifdef RTE_IXGBE_RX_OLFLAGS_ENABLE - static inline void -desc_to_olflags_v(__m128i descs[4], uint8_t vlan_flags, +desc_to_olflags_v(__m128i descs[4], __m128i mbuf_init, uint8_t vlan_flags, struct rte_mbuf **rx_pkts) { __m128i ptype0, ptype1, vtag0, vtag1, csum; - union { - uint16_t e[4]; - uint64_t dword; - } vol; + __m128i rearm0, rearm1, rearm2, rearm3; /* mask everything except rss type */ const __m128i rsstype_msk = _mm_set_epi16( @@ -225,18 +206,93 @@ desc_to_olflags_v(__m128i descs[4], uint8_t vlan_flags, vtag1 = _mm_or_si128(vtag0, vtag1); vtag1 = _mm_or_si128(ptype0, vtag1); - vol.dword = _mm_cvtsi128_si64(vtag1); - rx_pkts[0]->ol_flags = vol.e[0]; - rx_pkts[1]->ol_flags = vol.e[1]; - rx_pkts[2]->ol_flags = vol.e[2]; - rx_pkts[3]->ol_flags = vol.e[3]; + /* + * At this point, we have the 4 sets of flags in the low 64-bits + * of vtag1 (4x16). + * 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(vtag1, 8), 0x10); + rearm1 = _mm_blend_epi16(mbuf_init, _mm_slli_si128(vtag1, 6), 0x10); + rearm2 = _mm_blend_epi16(mbuf_init, _mm_slli_si128(vtag1, 4), 0x10); + rearm3 = _mm_blend_epi16(mbuf_init, _mm_slli_si128(vtag1, 2), 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); +} + +static inline uint32_t get_packet_type(int index, + uint32_t pkt_info, + uint32_t etqf_check, + uint32_t tunnel_check) +{ + if (etqf_check & (0x02 << (index * RTE_IXGBE_DESCS_PER_LOOP))) + return RTE_PTYPE_UNKNOWN; + + if (tunnel_check & (0x02 << (index * RTE_IXGBE_DESCS_PER_LOOP))) { + pkt_info &= IXGBE_PACKET_TYPE_MASK_TUNNEL; + return ptype_table_tn[pkt_info]; + } + + pkt_info &= IXGBE_PACKET_TYPE_MASK_82599; + return ptype_table[pkt_info]; +} + +static inline void +desc_to_ptype_v(__m128i descs[4], uint16_t pkt_type_mask, + struct rte_mbuf **rx_pkts) +{ + __m128i etqf_mask = _mm_set_epi64x(0x800000008000LL, 0x800000008000LL); + __m128i ptype_mask = _mm_set_epi32( + pkt_type_mask, pkt_type_mask, pkt_type_mask, pkt_type_mask); + __m128i tunnel_mask = + _mm_set_epi64x(0x100000001000LL, 0x100000001000LL); + + uint32_t etqf_check, tunnel_check, pkt_info; + + __m128i ptype0 = _mm_unpacklo_epi32(descs[0], descs[2]); + __m128i ptype1 = _mm_unpacklo_epi32(descs[1], descs[3]); + + /* interleave low 32 bits, + * now we have 4 ptypes in a XMM register + */ + ptype0 = _mm_unpacklo_epi32(ptype0, ptype1); + + /* create a etqf bitmask based on the etqf bit. */ + etqf_check = _mm_movemask_epi8(_mm_and_si128(ptype0, etqf_mask)); + + /* shift left by IXGBE_PACKET_TYPE_SHIFT, and apply ptype mask */ + ptype0 = _mm_and_si128(_mm_srli_epi32(ptype0, IXGBE_PACKET_TYPE_SHIFT), + ptype_mask); + + /* create a tunnel bitmask based on the tunnel bit */ + tunnel_check = _mm_movemask_epi8( + _mm_slli_epi32(_mm_and_si128(ptype0, tunnel_mask), 0x3)); + + pkt_info = _mm_extract_epi32(ptype0, 0); + rx_pkts[0]->packet_type = + get_packet_type(0, pkt_info, etqf_check, tunnel_check); + pkt_info = _mm_extract_epi32(ptype0, 1); + rx_pkts[1]->packet_type = + get_packet_type(1, pkt_info, etqf_check, tunnel_check); + pkt_info = _mm_extract_epi32(ptype0, 2); + rx_pkts[2]->packet_type = + get_packet_type(2, pkt_info, etqf_check, tunnel_check); + pkt_info = _mm_extract_epi32(ptype0, 3); + rx_pkts[3]->packet_type = + get_packet_type(3, pkt_info, etqf_check, tunnel_check); } -#else -#define desc_to_olflags_v(desc, vlan_flags, rx_pkts) do { \ - RTE_SET_USED(vlan_flags); \ - } while (0) -#endif /* * vPMD raw receive routine, only accept(nb_pkts >= RTE_IXGBE_DESCS_PER_LOOP) @@ -264,7 +320,17 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts, -rxq->crc_len, /* sub crc on pkt_len */ 0, 0 /* ignore pkt_type field */ ); + /* + * 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); __m128i dd_check, eop_check; + __m128i mbuf_init; uint8_t vlan_flags; /* nb_pkts shall be less equal than RTE_IXGBE_MAX_RX_BURST */ @@ -309,6 +375,21 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts, 0xFF, 0xFF, /* skip 32 bit pkt_type */ 0xFF, 0xFF ); + /* + * 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); + + mbuf_init = _mm_set_epi64x(0, rxq->mbuf_initializer); /* Cache is empty -> need to scan the buffer rings, but first move * the next 'n' mbufs into the cache @@ -332,9 +413,13 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts, __m128i descs[RTE_IXGBE_DESCS_PER_LOOP]; __m128i pkt_mb1, pkt_mb2, pkt_mb3, pkt_mb4; __m128i zero, staterr, sterr_tmp1, sterr_tmp2; - __m128i mbp1, mbp2; /* two mbuf pointer in one XMM reg. */ + /* 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 1 mbuf point */ + /* 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 */ @@ -342,11 +427,13 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts, descs[3] = _mm_loadu_si128((__m128i *)(rxdp + 3)); rte_compiler_barrier(); - /* B.2 copy 2 mbuf point into rx_pkts */ + /* B.2 copy 2 64 bit or 4 32 bit mbuf point into rx_pkts */ _mm_storeu_si128((__m128i *)&rx_pkts[pos], mbp1); - /* B.1 load 1 mbuf point */ +#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(); @@ -355,8 +442,10 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts, 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]); @@ -382,7 +471,7 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts, sterr_tmp1 = _mm_unpackhi_epi32(descs[1], descs[0]); /* set ol_flags with vlan packet type */ - desc_to_olflags_v(descs, vlan_flags, &rx_pkts[pos]); + desc_to_olflags_v(descs, mbuf_init, vlan_flags, &rx_pkts[pos]); /* D.2 pkt 3,4 set in_port/nb_seg and remove crc */ pkt_mb4 = _mm_add_epi16(pkt_mb4, crc_adjust); @@ -434,6 +523,8 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts, _mm_storeu_si128((void *)&rx_pkts[pos]->rx_descriptor_fields1, pkt_mb1); + desc_to_ptype_v(descs, rxq->pkt_type_mask, &rx_pkts[pos]); + /* C.4 calc avaialbe number of desc */ var = __builtin_popcountll(_mm_cvtsi128_si64(staterr)); nb_pkts_recd += var;