ligang/vpp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
vpp/build/external/patches/dpdk_20.02/0010-net-iavf-flexible-Rx-descriptor-support-in-AVX-path.patch
Chenmin Sun 7f83738b46 dpdk: DPDK 20.05 iavf flow director backporting to DPDK 20.02 
0001 ~ 0014 patches are for virtual channel and PMD
0015 is the iavf fdir framework
0016 ~ 0017 are for the iavf fidr driver

Type: feature

Signed-off-by: Chenmin Sun <chenmin.sun@intel.com>
Change-Id: I38e69ca0065a71cc6ba0b44ef7c7db51193a0899
2020-04-22 08:44:56 +00:00

672 lines
23 KiB
Diff
Raw Blame History

From b1138c10d2cd5938f4c0316e0b132caeb7e869dd Mon Sep 17 00:00:00 2001
From: Leyi Rong <leyi.rong@intel.com>
Date: Wed, 8 Apr 2020 14:22:03 +0800
Subject: [DPDK 10/17] net/iavf: flexible Rx descriptor support in AVX path
Support flexible Rx descriptor format in AVX
path of iAVF PMD.
Signed-off-by: Leyi Rong <leyi.rong@intel.com>
---
drivers/net/iavf/iavf_rxtx.c | 24 +-
drivers/net/iavf/iavf_rxtx.h | 6 +
drivers/net/iavf/iavf_rxtx_vec_avx2.c | 550 +++++++++++++++++++++++++-
3 files changed, 570 insertions(+), 10 deletions(-)
diff --git a/drivers/net/iavf/iavf_rxtx.c b/drivers/net/iavf/iavf_rxtx.c
index 67297dcb7..34c41d104 100644
--- a/drivers/net/iavf/iavf_rxtx.c
+++ b/drivers/net/iavf/iavf_rxtx.c
@@ -2081,16 +2081,28 @@ iavf_set_rx_function(struct rte_eth_dev *dev)
"Using %sVector Scattered Rx (port %d).",
use_avx2 ? "avx2 " : "",
dev->data->port_id);
- dev->rx_pkt_burst = use_avx2 ?
- iavf_recv_scattered_pkts_vec_avx2 :
- iavf_recv_scattered_pkts_vec;
+ if (vf->vf_res->vf_cap_flags &
+ VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC)
+ dev->rx_pkt_burst = use_avx2 ?
+ iavf_recv_scattered_pkts_vec_avx2_flex_rxd :
+ iavf_recv_scattered_pkts_vec;
+ else
+ dev->rx_pkt_burst = use_avx2 ?
+ iavf_recv_scattered_pkts_vec_avx2 :
+ iavf_recv_scattered_pkts_vec;
} else {
PMD_DRV_LOG(DEBUG, "Using %sVector Rx (port %d).",
use_avx2 ? "avx2 " : "",
dev->data->port_id);
- dev->rx_pkt_burst = use_avx2 ?
- iavf_recv_pkts_vec_avx2 :
- iavf_recv_pkts_vec;
+ if (vf->vf_res->vf_cap_flags &
+ VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC)
+ dev->rx_pkt_burst = use_avx2 ?
+ iavf_recv_pkts_vec_avx2_flex_rxd :
+ iavf_recv_pkts_vec;
+ else
+ dev->rx_pkt_burst = use_avx2 ?
+ iavf_recv_pkts_vec_avx2 :
+ iavf_recv_pkts_vec;
}
return;
diff --git a/drivers/net/iavf/iavf_rxtx.h b/drivers/net/iavf/iavf_rxtx.h
index f33d1df41..8e1db2588 100644
--- a/drivers/net/iavf/iavf_rxtx.h
+++ b/drivers/net/iavf/iavf_rxtx.h
@@ -413,9 +413,15 @@ uint16_t iavf_xmit_fixed_burst_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
uint16_t nb_pkts);
uint16_t iavf_recv_pkts_vec_avx2(void *rx_queue, struct rte_mbuf **rx_pkts,
uint16_t nb_pkts);
+uint16_t iavf_recv_pkts_vec_avx2_flex_rxd(void *rx_queue,
+ struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts);
uint16_t iavf_recv_scattered_pkts_vec_avx2(void *rx_queue,
struct rte_mbuf **rx_pkts,
uint16_t nb_pkts);
+uint16_t iavf_recv_scattered_pkts_vec_avx2_flex_rxd(void *rx_queue,
+ struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts);
uint16_t iavf_xmit_pkts_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
uint16_t nb_pkts);
uint16_t iavf_xmit_pkts_vec_avx2(void *tx_queue, struct rte_mbuf **tx_pkts,
diff --git a/drivers/net/iavf/iavf_rxtx_vec_avx2.c b/drivers/net/iavf/iavf_rxtx_vec_avx2.c
index 2587083d8..b23188fd3 100644
--- a/drivers/net/iavf/iavf_rxtx_vec_avx2.c
+++ b/drivers/net/iavf/iavf_rxtx_vec_avx2.c
@@ -11,14 +11,16 @@
#endif
static inline void
-iavf_rxq_rearm(struct iavf_rx_queue *rxq)
+iavf_rxq_rearm(struct iavf_rx_queue *rxq, volatile union iavf_rx_desc *rxdp)
{
int i;
uint16_t rx_id;
- volatile union iavf_rx_desc *rxdp;
struct rte_mbuf **rxp = &rxq->sw_ring[rxq->rxrearm_start];
- rxdp = rxq->rx_ring + rxq->rxrearm_start;
+ if (rxq->rxdid == IAVF_RXDID_COMMS_OVS_1) {
+ volatile union iavf_rx_flex_desc *rxdp =
+ (union iavf_rx_flex_desc *)rxdp;
+ }
/* Pull 'n' more MBUFs into the software ring */
if (rte_mempool_get_bulk(rxq->mp,
@@ -160,7 +162,7 @@ _iavf_recv_raw_pkts_vec_avx2(struct iavf_rx_queue *rxq,
* of time to act
*/
if (rxq->rxrearm_nb > IAVF_RXQ_REARM_THRESH)
- iavf_rxq_rearm(rxq);
+ iavf_rxq_rearm(rxq, rxq->rx_ring + rxq->rxrearm_start);
/* Before we start moving massive data around, check to see if
* there is actually a packet available
@@ -614,6 +616,465 @@ _iavf_recv_raw_pkts_vec_avx2(struct iavf_rx_queue *rxq,
return received;
}
+static inline uint16_t
+_iavf_recv_raw_pkts_vec_avx2_flex_rxd(struct iavf_rx_queue *rxq,
+ struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts, uint8_t *split_packet)
+{
+#define IAVF_DESCS_PER_LOOP_AVX 8
+
+ const uint32_t *type_table = rxq->vsi->adapter->ptype_tbl;
+
+ const __m256i mbuf_init = _mm256_set_epi64x(0, 0,
+ 0, rxq->mbuf_initializer);
+ struct rte_mbuf **sw_ring = &rxq->sw_ring[rxq->rx_tail];
+ volatile union iavf_rx_flex_desc *rxdp =
+ (union iavf_rx_flex_desc *)rxq->rx_ring + rxq->rx_tail;
+
+ rte_prefetch0(rxdp);
+
+ /* nb_pkts has to be floor-aligned to IAVF_DESCS_PER_LOOP_AVX */
+ nb_pkts = RTE_ALIGN_FLOOR(nb_pkts, IAVF_DESCS_PER_LOOP_AVX);
+
+ /* See if we need to rearm the RX queue - gives the prefetch a bit
+ * of time to act
+ */
+ if (rxq->rxrearm_nb > IAVF_RXQ_REARM_THRESH)
+ /* iavf_rxq_rearm(rxq); */
+ iavf_rxq_rearm(rxq, rxq->rx_ring + rxq->rxrearm_start);
+
+ /* 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;
+
+ /* constants used in processing loop */
+ const __m256i crc_adjust =
+ _mm256_set_epi16
+ (/* first descriptor */
+ 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 */
+ /* second descriptor */
+ 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 */
+ );
+
+ /* 8 packets DD mask, LSB in each 32-bit value */
+ const __m256i dd_check = _mm256_set1_epi32(1);
+
+ /* 8 packets EOP mask, second-LSB in each 32-bit value */
+ const __m256i eop_check = _mm256_slli_epi32(dd_check,
+ IAVF_RX_FLEX_DESC_STATUS0_EOF_S);
+
+ /* mask to shuffle from desc. to mbuf (2 descriptors)*/
+ const __m256i shuf_msk =
+ _mm256_set_epi8
+ (/* first descriptor */
+ 15, 14,
+ 13, 12, /* octet 12~15, 32 bits rss */
+ 11, 10, /* octet 10~11, 16 bits vlan_macip */
+ 5, 4, /* octet 4~5, 16 bits data_len */
+ 0xFF, 0xFF, /* skip hi 16 bits pkt_len, zero out */
+ 5, 4, /* octet 4~5, 16 bits pkt_len */
+ 0xFF, 0xFF, /* pkt_type set as unknown */
+ 0xFF, 0xFF, /*pkt_type set as unknown */
+ /* second descriptor */
+ 15, 14,
+ 13, 12, /* octet 12~15, 32 bits rss */
+ 11, 10, /* octet 10~11, 16 bits vlan_macip */
+ 5, 4, /* octet 4~5, 16 bits data_len */
+ 0xFF, 0xFF, /* skip hi 16 bits pkt_len, zero out */
+ 5, 4, /* octet 4~5, 16 bits pkt_len */
+ 0xFF, 0xFF, /* pkt_type set as unknown */
+ 0xFF, 0xFF /*pkt_type set as unknown */
+ );
+ /**
+ * compile-time check the above crc and shuffle layout is correct.
+ * NOTE: the first field (lowest address) is given last in set_epi
+ * calls 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);
+ 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);
+
+ /* Status/Error flag masks */
+ /**
+ * mask everything except Checksum Reports, RSS indication
+ * and VLAN indication.
+ * bit6:4 for IP/L4 checksum errors.
+ * bit12 is for RSS indication.
+ * bit13 is for VLAN indication.
+ */
+ const __m256i flags_mask =
+ _mm256_set1_epi32((7 << 4) | (1 << 12) | (1 << 13));
+ /**
+ * data to be shuffled by the result of the flags mask shifted by 4
+ * bits. This gives use the l3_l4 flags.
+ */
+ const __m256i l3_l4_flags_shuf = _mm256_set_epi8(0, 0, 0, 0, 0, 0, 0, 0,
+ /* shift right 1 bit to make sure it not exceed 255 */
+ (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
+ PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
+ PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD |
+ PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD |
+ PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_GOOD) >> 1,
+ /* second 128-bits */
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
+ PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
+ PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD |
+ PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD |
+ PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_GOOD) >> 1);
+ const __m256i cksum_mask =
+ _mm256_set1_epi32(PKT_RX_IP_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD |
+ PKT_RX_L4_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD |
+ PKT_RX_EIP_CKSUM_BAD);
+ /**
+ * data to be shuffled by result of flag mask, shifted down 12.
+ * If RSS(bit12)/VLAN(bit13) are set,
+ * shuffle moves appropriate flags in place.
+ */
+ const __m256i rss_vlan_flags_shuf = _mm256_set_epi8(0, 0, 0, 0,
+ 0, 0, 0, 0,
+ 0, 0, 0, 0,
+ PKT_RX_RSS_HASH | PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED,
+ PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED,
+ PKT_RX_RSS_HASH, 0,
+ /* end up 128-bits */
+ 0, 0, 0, 0,
+ 0, 0, 0, 0,
+ 0, 0, 0, 0,
+ PKT_RX_RSS_HASH | PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED,
+ PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED,
+ PKT_RX_RSS_HASH, 0);
+
+ uint16_t i, received;
+
+ for (i = 0, received = 0; i < nb_pkts;
+ i += IAVF_DESCS_PER_LOOP_AVX,
+ rxdp += IAVF_DESCS_PER_LOOP_AVX) {
+ /* step 1, copy over 8 mbuf pointers to rx_pkts array */
+ _mm256_storeu_si256((void *)&rx_pkts[i],
+ _mm256_loadu_si256((void *)&sw_ring[i]));
+#ifdef RTE_ARCH_X86_64
+ _mm256_storeu_si256
+ ((void *)&rx_pkts[i + 4],
+ _mm256_loadu_si256((void *)&sw_ring[i + 4]));
+#endif
+
+ __m256i raw_desc0_1, raw_desc2_3, raw_desc4_5, raw_desc6_7;
+
+ const __m128i raw_desc7 =
+ _mm_load_si128((void *)(rxdp + 7));
+ rte_compiler_barrier();
+ const __m128i raw_desc6 =
+ _mm_load_si128((void *)(rxdp + 6));
+ rte_compiler_barrier();
+ const __m128i raw_desc5 =
+ _mm_load_si128((void *)(rxdp + 5));
+ rte_compiler_barrier();
+ const __m128i raw_desc4 =
+ _mm_load_si128((void *)(rxdp + 4));
+ rte_compiler_barrier();
+ const __m128i raw_desc3 =
+ _mm_load_si128((void *)(rxdp + 3));
+ rte_compiler_barrier();
+ const __m128i raw_desc2 =
+ _mm_load_si128((void *)(rxdp + 2));
+ rte_compiler_barrier();
+ const __m128i raw_desc1 =
+ _mm_load_si128((void *)(rxdp + 1));
+ rte_compiler_barrier();
+ const __m128i raw_desc0 =
+ _mm_load_si128((void *)(rxdp + 0));
+
+ raw_desc6_7 =
+ _mm256_inserti128_si256
+ (_mm256_castsi128_si256(raw_desc6),
+ raw_desc7, 1);
+ raw_desc4_5 =
+ _mm256_inserti128_si256
+ (_mm256_castsi128_si256(raw_desc4),
+ raw_desc5, 1);
+ raw_desc2_3 =
+ _mm256_inserti128_si256
+ (_mm256_castsi128_si256(raw_desc2),
+ raw_desc3, 1);
+ raw_desc0_1 =
+ _mm256_inserti128_si256
+ (_mm256_castsi128_si256(raw_desc0),
+ raw_desc1, 1);
+
+ if (split_packet) {
+ int j;
+
+ for (j = 0; j < IAVF_DESCS_PER_LOOP_AVX; j++)
+ rte_mbuf_prefetch_part2(rx_pkts[i + j]);
+ }
+
+ /**
+ * convert descriptors 4-7 into mbufs, re-arrange fields.
+ * Then write into the mbuf.
+ */
+ __m256i mb6_7 = _mm256_shuffle_epi8(raw_desc6_7, shuf_msk);
+ __m256i mb4_5 = _mm256_shuffle_epi8(raw_desc4_5, shuf_msk);
+
+ mb6_7 = _mm256_add_epi16(mb6_7, crc_adjust);
+ mb4_5 = _mm256_add_epi16(mb4_5, crc_adjust);
+ /**
+ * to get packet types, ptype is located in bit16-25
+ * of each 128bits
+ */
+ const __m256i ptype_mask =
+ _mm256_set1_epi16(IAVF_RX_FLEX_DESC_PTYPE_M);
+ const __m256i ptypes6_7 =
+ _mm256_and_si256(raw_desc6_7, ptype_mask);
+ const __m256i ptypes4_5 =
+ _mm256_and_si256(raw_desc4_5, ptype_mask);
+ const uint16_t ptype7 = _mm256_extract_epi16(ptypes6_7, 9);
+ const uint16_t ptype6 = _mm256_extract_epi16(ptypes6_7, 1);
+ const uint16_t ptype5 = _mm256_extract_epi16(ptypes4_5, 9);
+ const uint16_t ptype4 = _mm256_extract_epi16(ptypes4_5, 1);
+
+ mb6_7 = _mm256_insert_epi32(mb6_7, type_table[ptype7], 4);
+ mb6_7 = _mm256_insert_epi32(mb6_7, type_table[ptype6], 0);
+ mb4_5 = _mm256_insert_epi32(mb4_5, type_table[ptype5], 4);
+ mb4_5 = _mm256_insert_epi32(mb4_5, type_table[ptype4], 0);
+ /* merge the status bits into one register */
+ const __m256i status4_7 = _mm256_unpackhi_epi32(raw_desc6_7,
+ raw_desc4_5);
+
+ /**
+ * convert descriptors 0-3 into mbufs, re-arrange fields.
+ * Then write into the mbuf.
+ */
+ __m256i mb2_3 = _mm256_shuffle_epi8(raw_desc2_3, shuf_msk);
+ __m256i mb0_1 = _mm256_shuffle_epi8(raw_desc0_1, shuf_msk);
+
+ mb2_3 = _mm256_add_epi16(mb2_3, crc_adjust);
+ mb0_1 = _mm256_add_epi16(mb0_1, crc_adjust);
+ /**
+ * to get packet types, ptype is located in bit16-25
+ * of each 128bits
+ */
+ const __m256i ptypes2_3 =
+ _mm256_and_si256(raw_desc2_3, ptype_mask);
+ const __m256i ptypes0_1 =
+ _mm256_and_si256(raw_desc0_1, ptype_mask);
+ const uint16_t ptype3 = _mm256_extract_epi16(ptypes2_3, 9);
+ const uint16_t ptype2 = _mm256_extract_epi16(ptypes2_3, 1);
+ const uint16_t ptype1 = _mm256_extract_epi16(ptypes0_1, 9);
+ const uint16_t ptype0 = _mm256_extract_epi16(ptypes0_1, 1);
+
+ mb2_3 = _mm256_insert_epi32(mb2_3, type_table[ptype3], 4);
+ mb2_3 = _mm256_insert_epi32(mb2_3, type_table[ptype2], 0);
+ mb0_1 = _mm256_insert_epi32(mb0_1, type_table[ptype1], 4);
+ mb0_1 = _mm256_insert_epi32(mb0_1, type_table[ptype0], 0);
+ /* merge the status bits into one register */
+ const __m256i status0_3 = _mm256_unpackhi_epi32(raw_desc2_3,
+ raw_desc0_1);
+
+ /**
+ * take the two sets of status bits and merge to one
+ * After merge, the packets status flags are in the
+ * order (hi->lo): [1, 3, 5, 7, 0, 2, 4, 6]
+ */
+ __m256i status0_7 = _mm256_unpacklo_epi64(status4_7,
+ status0_3);
+
+ /* now do flag manipulation */
+
+ /* get only flag/error bits we want */
+ const __m256i flag_bits =
+ _mm256_and_si256(status0_7, flags_mask);
+ /**
+ * l3_l4_error flags, shuffle, then shift to correct adjustment
+ * of flags in flags_shuf, and finally mask out extra bits
+ */
+ __m256i l3_l4_flags = _mm256_shuffle_epi8(l3_l4_flags_shuf,
+ _mm256_srli_epi32(flag_bits, 4));
+ l3_l4_flags = _mm256_slli_epi32(l3_l4_flags, 1);
+ l3_l4_flags = _mm256_and_si256(l3_l4_flags, cksum_mask);
+ /* set rss and vlan flags */
+ const __m256i rss_vlan_flag_bits =
+ _mm256_srli_epi32(flag_bits, 12);
+ const __m256i rss_vlan_flags =
+ _mm256_shuffle_epi8(rss_vlan_flags_shuf,
+ rss_vlan_flag_bits);
+
+ /* merge flags */
+ const __m256i mbuf_flags = _mm256_or_si256(l3_l4_flags,
+ rss_vlan_flags);
+ /**
+ * At this point, we have the 8 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 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. However, we can also
+ * add in the previously computed rx_descriptor fields to
+ * make a single 256-bit write per mbuf
+ */
+ /* check the structure matches expectations */
+ 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));
+ /* build up data and do writes */
+ __m256i rearm0, rearm1, rearm2, rearm3, rearm4, rearm5,
+ rearm6, rearm7;
+ rearm6 = _mm256_blend_epi32(mbuf_init,
+ _mm256_slli_si256(mbuf_flags, 8),
+ 0x04);
+ rearm4 = _mm256_blend_epi32(mbuf_init,
+ _mm256_slli_si256(mbuf_flags, 4),
+ 0x04);
+ rearm2 = _mm256_blend_epi32(mbuf_init, mbuf_flags, 0x04);
+ rearm0 = _mm256_blend_epi32(mbuf_init,
+ _mm256_srli_si256(mbuf_flags, 4),
+ 0x04);
+ /* permute to add in the rx_descriptor e.g. rss fields */
+ rearm6 = _mm256_permute2f128_si256(rearm6, mb6_7, 0x20);
+ rearm4 = _mm256_permute2f128_si256(rearm4, mb4_5, 0x20);
+ rearm2 = _mm256_permute2f128_si256(rearm2, mb2_3, 0x20);
+ rearm0 = _mm256_permute2f128_si256(rearm0, mb0_1, 0x20);
+ /* write to mbuf */
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 6]->rearm_data,
+ rearm6);
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 4]->rearm_data,
+ rearm4);
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 2]->rearm_data,
+ rearm2);
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 0]->rearm_data,
+ rearm0);
+
+ /* repeat for the odd mbufs */
+ const __m256i odd_flags =
+ _mm256_castsi128_si256
+ (_mm256_extracti128_si256(mbuf_flags, 1));
+ rearm7 = _mm256_blend_epi32(mbuf_init,
+ _mm256_slli_si256(odd_flags, 8),
+ 0x04);
+ rearm5 = _mm256_blend_epi32(mbuf_init,
+ _mm256_slli_si256(odd_flags, 4),
+ 0x04);
+ rearm3 = _mm256_blend_epi32(mbuf_init, odd_flags, 0x04);
+ rearm1 = _mm256_blend_epi32(mbuf_init,
+ _mm256_srli_si256(odd_flags, 4),
+ 0x04);
+ /* since odd mbufs are already in hi 128-bits use blend */
+ rearm7 = _mm256_blend_epi32(rearm7, mb6_7, 0xF0);
+ rearm5 = _mm256_blend_epi32(rearm5, mb4_5, 0xF0);
+ rearm3 = _mm256_blend_epi32(rearm3, mb2_3, 0xF0);
+ rearm1 = _mm256_blend_epi32(rearm1, mb0_1, 0xF0);
+ /* again write to mbufs */
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 7]->rearm_data,
+ rearm7);
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 5]->rearm_data,
+ rearm5);
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 3]->rearm_data,
+ rearm3);
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 1]->rearm_data,
+ rearm1);
+
+ /* extract and record EOP bit */
+ if (split_packet) {
+ const __m128i eop_mask =
+ _mm_set1_epi16(1 <<
+ IAVF_RX_FLEX_DESC_STATUS0_EOF_S);
+ const __m256i eop_bits256 = _mm256_and_si256(status0_7,
+ eop_check);
+ /* pack status bits into a single 128-bit register */
+ const __m128i eop_bits =
+ _mm_packus_epi32
+ (_mm256_castsi256_si128(eop_bits256),
+ _mm256_extractf128_si256(eop_bits256,
+ 1));
+ /**
+ * flip bits, and mask out the EOP bit, which is now
+ * a split-packet bit i.e. !EOP, rather than EOP one.
+ */
+ __m128i split_bits = _mm_andnot_si128(eop_bits,
+ eop_mask);
+ /**
+ * eop bits are out of order, so we need to shuffle them
+ * back into order again. In doing so, only use low 8
+ * bits, which acts like another pack instruction
+ * The original order is (hi->lo): 1,3,5,7,0,2,4,6
+ * [Since we use epi8, the 16-bit positions are
+ * multiplied by 2 in the eop_shuffle value.]
+ */
+ __m128i eop_shuffle =
+ _mm_set_epi8(/* zero hi 64b */
+ 0xFF, 0xFF, 0xFF, 0xFF,
+ 0xFF, 0xFF, 0xFF, 0xFF,
+ /* move values to lo 64b */
+ 8, 0, 10, 2,
+ 12, 4, 14, 6);
+ split_bits = _mm_shuffle_epi8(split_bits, eop_shuffle);
+ *(uint64_t *)split_packet =
+ _mm_cvtsi128_si64(split_bits);
+ split_packet += IAVF_DESCS_PER_LOOP_AVX;
+ }
+
+ /* perform dd_check */
+ status0_7 = _mm256_and_si256(status0_7, dd_check);
+ status0_7 = _mm256_packs_epi32(status0_7,
+ _mm256_setzero_si256());
+
+ uint64_t burst = __builtin_popcountll
+ (_mm_cvtsi128_si64
+ (_mm256_extracti128_si256
+ (status0_7, 1)));
+ burst += __builtin_popcountll
+ (_mm_cvtsi128_si64
+ (_mm256_castsi256_si128(status0_7)));
+ received += burst;
+ if (burst != IAVF_DESCS_PER_LOOP_AVX)
+ break;
+ }
+
+ /* update tail pointers */
+ rxq->rx_tail += received;
+ rxq->rx_tail &= (rxq->nb_rx_desc - 1);
+ if ((rxq->rx_tail & 1) == 1 && received > 1) { /* keep avx2 aligned */
+ rxq->rx_tail--;
+ received--;
+ }
+ rxq->rxrearm_nb += received;
+ return received;
+}
+
/**
* Notice:
* - nb_pkts < IAVF_DESCS_PER_LOOP, just return no packet
@@ -625,6 +1086,18 @@ iavf_recv_pkts_vec_avx2(void *rx_queue, struct rte_mbuf **rx_pkts,
return _iavf_recv_raw_pkts_vec_avx2(rx_queue, rx_pkts, nb_pkts, NULL);
}
+/**
+ * Notice:
+ * - nb_pkts < IAVF_DESCS_PER_LOOP, just return no packet
+ */
+uint16_t
+iavf_recv_pkts_vec_avx2_flex_rxd(void *rx_queue, struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts)
+{
+ return _iavf_recv_raw_pkts_vec_avx2_flex_rxd(rx_queue, rx_pkts,
+ nb_pkts, NULL);
+}
+
/**
* vPMD receive routine that reassembles single burst of 32 scattered packets
* Notice:
@@ -690,6 +1163,75 @@ iavf_recv_scattered_pkts_vec_avx2(void *rx_queue, struct rte_mbuf **rx_pkts,
rx_pkts + retval, nb_pkts);
}
+/**
+ * vPMD receive routine that reassembles single burst of
+ * 32 scattered packets for flex RxD
+ * Notice:
+ * - nb_pkts < IAVF_DESCS_PER_LOOP, just return no packet
+ */
+static uint16_t
+iavf_recv_scattered_burst_vec_avx2_flex_rxd(void *rx_queue,
+ struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts)
+{
+ struct iavf_rx_queue *rxq = rx_queue;
+ uint8_t split_flags[IAVF_VPMD_RX_MAX_BURST] = {0};
+
+ /* get some new buffers */
+ uint16_t nb_bufs = _iavf_recv_raw_pkts_vec_avx2_flex_rxd(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 &&
+ 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*/
+ unsigned int i = 0;
+
+ if (!rxq->pkt_first_seg) {
+ /* 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 + reassemble_packets(rxq, &rx_pkts[i], nb_bufs - i,
+ &split_flags[i]);
+}
+
+/**
+ * vPMD receive routine that reassembles scattered packets for flex RxD.
+ * Main receive routine that can handle arbitrary burst sizes
+ * Notice:
+ * - nb_pkts < IAVF_DESCS_PER_LOOP, just return no packet
+ */
+uint16_t
+iavf_recv_scattered_pkts_vec_avx2_flex_rxd(void *rx_queue,
+ struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts)
+{
+ uint16_t retval = 0;
+
+ while (nb_pkts > IAVF_VPMD_RX_MAX_BURST) {
+ uint16_t burst =
+ iavf_recv_scattered_burst_vec_avx2_flex_rxd
+ (rx_queue, rx_pkts + retval, IAVF_VPMD_RX_MAX_BURST);
+ retval += burst;
+ nb_pkts -= burst;
+ if (burst < IAVF_VPMD_RX_MAX_BURST)
+ return retval;
+ }
+ return retval + iavf_recv_scattered_burst_vec_avx2_flex_rxd(rx_queue,
+ rx_pkts + retval, nb_pkts);
+}
+
static inline void
iavf_vtx1(volatile struct iavf_tx_desc *txdp,
struct rte_mbuf *pkt, uint64_t flags)
--
2.17.1
Reference in New Issue View Git Blame Copy Permalink