diff options
Diffstat (limited to 'src/dpdk/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c')
| -rw-r--r-- | src/dpdk/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c | 73 |
1 files changed, 56 insertions, 17 deletions
diff --git a/src/dpdk/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c b/src/dpdk/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c index 1c4fd7c1..abbf2841 100644 --- a/src/dpdk/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c +++ b/src/dpdk/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c @@ -145,7 +145,7 @@ static inline void desc_to_olflags_v(__m128i descs[4], uint8_t vlan_flags, struct rte_mbuf **rx_pkts) { - __m128i ptype0, ptype1, vtag0, vtag1; + __m128i ptype0, ptype1, vtag0, vtag1, csum; union { uint16_t e[4]; uint64_t dword; @@ -156,24 +156,45 @@ desc_to_olflags_v(__m128i descs[4], uint8_t vlan_flags, 0x0000, 0x0000, 0x0000, 0x0000, 0x000F, 0x000F, 0x000F, 0x000F); + /* mask the lower byte of ol_flags */ + const __m128i ol_flags_msk = _mm_set_epi16( + 0x0000, 0x0000, 0x0000, 0x0000, + 0x00FF, 0x00FF, 0x00FF, 0x00FF); + /* map rss type to rss hash flag */ const __m128i rss_flags = _mm_set_epi8(PKT_RX_FDIR, 0, 0, 0, 0, 0, 0, PKT_RX_RSS_HASH, PKT_RX_RSS_HASH, 0, PKT_RX_RSS_HASH, 0, PKT_RX_RSS_HASH, PKT_RX_RSS_HASH, PKT_RX_RSS_HASH, 0); - /* mask everything except vlan present bit */ - const __m128i vlan_msk = _mm_set_epi16( - 0x0000, 0x0000, - 0x0000, 0x0000, - IXGBE_RXD_STAT_VP, IXGBE_RXD_STAT_VP, - IXGBE_RXD_STAT_VP, IXGBE_RXD_STAT_VP); - /* map vlan present (0x8) to ol_flags */ - const __m128i vlan_map = _mm_set_epi8( + /* mask everything except vlan present and l4/ip csum error */ + const __m128i vlan_csum_msk = _mm_set_epi16( + (IXGBE_RXDADV_ERR_TCPE | IXGBE_RXDADV_ERR_IPE) >> 16, + (IXGBE_RXDADV_ERR_TCPE | IXGBE_RXDADV_ERR_IPE) >> 16, + (IXGBE_RXDADV_ERR_TCPE | IXGBE_RXDADV_ERR_IPE) >> 16, + (IXGBE_RXDADV_ERR_TCPE | IXGBE_RXDADV_ERR_IPE) >> 16, + IXGBE_RXD_STAT_VP, IXGBE_RXD_STAT_VP, + IXGBE_RXD_STAT_VP, IXGBE_RXD_STAT_VP); + /* map vlan present (0x8), IPE (0x2), L4E (0x1) to ol_flags */ + const __m128i vlan_csum_map_lo = _mm_set_epi8( 0, 0, 0, 0, - 0, 0, 0, vlan_flags, + vlan_flags | PKT_RX_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD, + vlan_flags | PKT_RX_IP_CKSUM_BAD, + vlan_flags | PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD, + vlan_flags | PKT_RX_IP_CKSUM_GOOD, 0, 0, 0, 0, - 0, 0, 0, 0); + PKT_RX_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD, + PKT_RX_IP_CKSUM_BAD, + PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD, + PKT_RX_IP_CKSUM_GOOD); + + const __m128i vlan_csum_map_hi = _mm_set_epi8( + 0, 0, 0, 0, + 0, PKT_RX_L4_CKSUM_GOOD >> sizeof(uint8_t), 0, + PKT_RX_L4_CKSUM_GOOD >> sizeof(uint8_t), + 0, 0, 0, 0, + 0, PKT_RX_L4_CKSUM_GOOD >> sizeof(uint8_t), 0, + PKT_RX_L4_CKSUM_GOOD >> sizeof(uint8_t)); ptype0 = _mm_unpacklo_epi16(descs[0], descs[1]); ptype1 = _mm_unpacklo_epi16(descs[2], descs[3]); @@ -185,8 +206,26 @@ desc_to_olflags_v(__m128i descs[4], uint8_t vlan_flags, ptype0 = _mm_shuffle_epi8(rss_flags, ptype0); vtag1 = _mm_unpacklo_epi32(vtag0, vtag1); - vtag1 = _mm_and_si128(vtag1, vlan_msk); - vtag1 = _mm_shuffle_epi8(vlan_map, vtag1); + vtag1 = _mm_and_si128(vtag1, vlan_csum_msk); + + /* csum bits are in the most significant, to use shuffle we need to + * shift them. Change mask to 0xc000 to 0x0003. + */ + csum = _mm_srli_epi16(vtag1, 14); + + /* now or the most significant 64 bits containing the checksum + * flags with the vlan present flags. + */ + csum = _mm_srli_si128(csum, 8); + vtag1 = _mm_or_si128(csum, vtag1); + + /* convert VP, IPE, L4E to ol_flags */ + vtag0 = _mm_shuffle_epi8(vlan_csum_map_hi, vtag1); + vtag0 = _mm_slli_epi16(vtag0, sizeof(uint8_t)); + + vtag1 = _mm_shuffle_epi8(vlan_csum_map_lo, vtag1); + vtag1 = _mm_and_si128(vtag1, ol_flags_msk); + vtag1 = _mm_or_si128(vtag0, vtag1); vtag1 = _mm_or_si128(ptype0, vtag1); vol.dword = _mm_cvtsi128_si64(vtag1); @@ -210,7 +249,6 @@ desc_to_olflags_v(__m128i descs[4], uint8_t vlan_flags, * - nb_pkts > RTE_IXGBE_MAX_RX_BURST, only scan RTE_IXGBE_MAX_RX_BURST * numbers of DD bit * - floor align nb_pkts to a RTE_IXGBE_DESC_PER_LOOP power-of-two - * - don't support ol_flags for rss and csum err */ static inline uint16_t _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts, @@ -243,7 +281,7 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts, */ rxdp = rxq->rx_ring + rxq->rx_tail; - _mm_prefetch((const void *)rxdp, _MM_HINT_T0); + rte_prefetch0(rxdp); /* See if we need to rearm the RX queue - gives the prefetch a bit * of time to act @@ -305,6 +343,7 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts, /* 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 mbuf point into rx_pkts */ _mm_storeu_si128((__m128i *)&rx_pkts[pos], mbp1); @@ -313,8 +352,10 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts, mbp2 = _mm_loadu_si128((__m128i *)&sw_ring[pos+2]); 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)); /* B.2 copy 2 mbuf point into rx_pkts */ @@ -425,7 +466,6 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts, * - nb_pkts > RTE_IXGBE_MAX_RX_BURST, only scan RTE_IXGBE_MAX_RX_BURST * numbers of DD bit * - floor align nb_pkts to a RTE_IXGBE_DESC_PER_LOOP power-of-two - * - don't support ol_flags for rss and csum err */ uint16_t ixgbe_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts, @@ -438,7 +478,6 @@ ixgbe_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts, * vPMD receive routine that reassembles scattered packets * * Notice: - * - don't support ol_flags for rss and csum err * - nb_pkts < RTE_IXGBE_DESCS_PER_LOOP, just return no packet * - nb_pkts > RTE_IXGBE_MAX_RX_BURST, only scan RTE_IXGBE_MAX_RX_BURST * numbers of DD bit |