(rxq->nb_rx_desc - 1) : (rxq->rxrearm_start - 1));
/* Update the tail pointer on the NIC */
- ICE_PCI_REG_WRITE(rxq->qrx_tail, rx_id);
+ ICE_PCI_REG_WC_WRITE(rxq->qrx_tail, rx_id);
+}
+
+static inline __m256i
+ice_flex_rxd_to_fdir_flags_vec_avx2(const __m256i fdir_id0_7)
+{
+#define FDID_MIS_MAGIC 0xFFFFFFFF
+ RTE_BUILD_BUG_ON(PKT_RX_FDIR != (1 << 2));
+ RTE_BUILD_BUG_ON(PKT_RX_FDIR_ID != (1 << 13));
+ const __m256i pkt_fdir_bit = _mm256_set1_epi32(PKT_RX_FDIR |
+ PKT_RX_FDIR_ID);
+ /* desc->flow_id field == 0xFFFFFFFF means fdir mismatch */
+ const __m256i fdir_mis_mask = _mm256_set1_epi32(FDID_MIS_MAGIC);
+ __m256i fdir_mask = _mm256_cmpeq_epi32(fdir_id0_7,
+ fdir_mis_mask);
+ /* this XOR op results to bit-reverse the fdir_mask */
+ fdir_mask = _mm256_xor_si256(fdir_mask, fdir_mis_mask);
+ const __m256i fdir_flags = _mm256_and_si256(fdir_mask, pkt_fdir_bit);
+
+ return fdir_flags;
}
static inline uint16_t
const __m256i shuf_msk =
_mm256_set_epi8
(/* first descriptor */
- 15, 14,
- 13, 12, /* octet 12~15, 32 bits rss */
+ 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 hi 16 bits pkt_len, zero out */
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 */
+ 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 hi 16 bits pkt_len, zero out */
* bit13 is for VLAN indication.
*/
const __m256i flags_mask =
- _mm256_set1_epi32((7 << 4) | (1 << 12) | (1 << 13));
+ _mm256_set1_epi32((0xF << 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 l3_l4_flags_shuf =
+ _mm256_set_epi8((PKT_RX_OUTER_L4_CKSUM_BAD >> 20 |
+ PKT_RX_OUTER_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
+ PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_BAD >> 20 | PKT_RX_OUTER_IP_CKSUM_BAD |
+ PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_BAD >> 20 | PKT_RX_OUTER_IP_CKSUM_BAD |
+ PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_BAD >> 20 | PKT_RX_OUTER_IP_CKSUM_BAD |
+ PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_BAD >> 20 | PKT_RX_L4_CKSUM_BAD |
+ PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_BAD >> 20 | PKT_RX_L4_CKSUM_BAD |
+ PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_BAD >> 20 | PKT_RX_L4_CKSUM_GOOD |
+ PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_BAD >> 20 | PKT_RX_L4_CKSUM_GOOD |
+ PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | PKT_RX_OUTER_IP_CKSUM_BAD |
+ PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | PKT_RX_OUTER_IP_CKSUM_BAD |
+ PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | PKT_RX_OUTER_IP_CKSUM_BAD |
+ PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | PKT_RX_OUTER_IP_CKSUM_BAD |
+ PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | PKT_RX_L4_CKSUM_BAD |
+ PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | PKT_RX_L4_CKSUM_BAD |
+ PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | PKT_RX_L4_CKSUM_GOOD |
+ PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | PKT_RX_L4_CKSUM_GOOD |
+ PKT_RX_IP_CKSUM_GOOD) >> 1,
+ /**
+ * second 128-bits
+ * shift right 20 bits to use the low two bits to indicate
+ * outer checksum status
+ * shift right 1 bit to make sure it not exceed 255
+ */
+ (PKT_RX_OUTER_L4_CKSUM_BAD >> 20 | PKT_RX_OUTER_IP_CKSUM_BAD |
+ PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_BAD >> 20 | PKT_RX_OUTER_IP_CKSUM_BAD |
+ PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_BAD >> 20 | PKT_RX_OUTER_IP_CKSUM_BAD |
+ PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_BAD >> 20 | PKT_RX_OUTER_IP_CKSUM_BAD |
+ PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_BAD >> 20 | PKT_RX_L4_CKSUM_BAD |
+ PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_BAD >> 20 | PKT_RX_L4_CKSUM_BAD |
+ PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_BAD >> 20 | PKT_RX_L4_CKSUM_GOOD |
+ PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_BAD >> 20 | PKT_RX_L4_CKSUM_GOOD |
+ PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | PKT_RX_OUTER_IP_CKSUM_BAD |
+ PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | PKT_RX_OUTER_IP_CKSUM_BAD |
+ PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | PKT_RX_OUTER_IP_CKSUM_BAD |
+ PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | PKT_RX_OUTER_IP_CKSUM_BAD |
+ PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | PKT_RX_L4_CKSUM_BAD |
+ PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | PKT_RX_L4_CKSUM_BAD |
+ PKT_RX_IP_CKSUM_GOOD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | PKT_RX_L4_CKSUM_GOOD |
+ PKT_RX_IP_CKSUM_BAD) >> 1,
+ (PKT_RX_OUTER_L4_CKSUM_GOOD >> 20 | 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);
+ _mm256_set1_epi32(PKT_RX_IP_CKSUM_MASK |
+ PKT_RX_L4_CKSUM_MASK |
+ PKT_RX_OUTER_IP_CKSUM_BAD |
+ PKT_RX_OUTER_L4_CKSUM_MASK);
/**
* data to be shuffled by result of flag mask, shifted down 12.
* If RSS(bit12)/VLAN(bit13) are set,
__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);
+
+ __m256i l4_outer_mask = _mm256_set1_epi32(0x6);
+ __m256i l4_outer_flags =
+ _mm256_and_si256(l3_l4_flags, l4_outer_mask);
+ l4_outer_flags = _mm256_slli_epi32(l4_outer_flags, 20);
+
+ __m256i l3_l4_mask = _mm256_set1_epi32(~0x6);
+ l3_l4_flags = _mm256_and_si256(l3_l4_flags, l3_l4_mask);
+ l3_l4_flags = _mm256_or_si256(l3_l4_flags, l4_outer_flags);
l3_l4_flags = _mm256_and_si256(l3_l4_flags, cksum_mask);
/* set rss and vlan flags */
const __m256i rss_vlan_flag_bits =
rss_vlan_flag_bits);
/* merge flags */
- const __m256i mbuf_flags = _mm256_or_si256(l3_l4_flags,
+ __m256i mbuf_flags = _mm256_or_si256(l3_l4_flags,
rss_vlan_flags);
+
+ if (rxq->fdir_enabled) {
+ const __m256i fdir_id4_7 =
+ _mm256_unpackhi_epi32(raw_desc6_7, raw_desc4_5);
+
+ const __m256i fdir_id0_3 =
+ _mm256_unpackhi_epi32(raw_desc2_3, raw_desc0_1);
+
+ const __m256i fdir_id0_7 =
+ _mm256_unpackhi_epi64(fdir_id4_7, fdir_id0_3);
+
+ const __m256i fdir_flags =
+ ice_flex_rxd_to_fdir_flags_vec_avx2(fdir_id0_7);
+
+ /* merge with fdir_flags */
+ mbuf_flags = _mm256_or_si256(mbuf_flags, fdir_flags);
+
+ /* write to mbuf: have to use scalar store here */
+ rx_pkts[i + 0]->hash.fdir.hi =
+ _mm256_extract_epi32(fdir_id0_7, 3);
+
+ rx_pkts[i + 1]->hash.fdir.hi =
+ _mm256_extract_epi32(fdir_id0_7, 7);
+
+ rx_pkts[i + 2]->hash.fdir.hi =
+ _mm256_extract_epi32(fdir_id0_7, 2);
+
+ rx_pkts[i + 3]->hash.fdir.hi =
+ _mm256_extract_epi32(fdir_id0_7, 6);
+
+ rx_pkts[i + 4]->hash.fdir.hi =
+ _mm256_extract_epi32(fdir_id0_7, 1);
+
+ rx_pkts[i + 5]->hash.fdir.hi =
+ _mm256_extract_epi32(fdir_id0_7, 5);
+
+ rx_pkts[i + 6]->hash.fdir.hi =
+ _mm256_extract_epi32(fdir_id0_7, 0);
+
+ rx_pkts[i + 7]->hash.fdir.hi =
+ _mm256_extract_epi32(fdir_id0_7, 4);
+ } /* if() on fdir_enabled */
+
+#ifndef RTE_LIBRTE_ICE_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_bh7 =
+ _mm_load_si128
+ ((void *)(&rxdp[7].wb.status_error1));
+ rte_compiler_barrier();
+ const __m128i raw_desc_bh6 =
+ _mm_load_si128
+ ((void *)(&rxdp[6].wb.status_error1));
+ rte_compiler_barrier();
+ const __m128i raw_desc_bh5 =
+ _mm_load_si128
+ ((void *)(&rxdp[5].wb.status_error1));
+ rte_compiler_barrier();
+ const __m128i raw_desc_bh4 =
+ _mm_load_si128
+ ((void *)(&rxdp[4].wb.status_error1));
+ rte_compiler_barrier();
+ 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));
+
+ __m256i raw_desc_bh6_7 =
+ _mm256_inserti128_si256
+ (_mm256_castsi128_si256(raw_desc_bh6),
+ raw_desc_bh7, 1);
+ __m256i raw_desc_bh4_5 =
+ _mm256_inserti128_si256
+ (_mm256_castsi128_si256(raw_desc_bh4),
+ raw_desc_bh5, 1);
+ __m256i raw_desc_bh2_3 =
+ _mm256_inserti128_si256
+ (_mm256_castsi128_si256(raw_desc_bh2),
+ raw_desc_bh3, 1);
+ __m256i raw_desc_bh0_1 =
+ _mm256_inserti128_si256
+ (_mm256_castsi128_si256(raw_desc_bh0),
+ raw_desc_bh1, 1);
+
+ /**
+ * to shift the 32b RSS hash value to the
+ * highest 32b of each 128b before mask
+ */
+ __m256i rss_hash6_7 =
+ _mm256_slli_epi64(raw_desc_bh6_7, 32);
+ __m256i rss_hash4_5 =
+ _mm256_slli_epi64(raw_desc_bh4_5, 32);
+ __m256i rss_hash2_3 =
+ _mm256_slli_epi64(raw_desc_bh2_3, 32);
+ __m256i rss_hash0_1 =
+ _mm256_slli_epi64(raw_desc_bh0_1, 32);
+
+ __m256i rss_hash_msk =
+ _mm256_set_epi32(0xFFFFFFFF, 0, 0, 0,
+ 0xFFFFFFFF, 0, 0, 0);
+
+ rss_hash6_7 = _mm256_and_si256
+ (rss_hash6_7, rss_hash_msk);
+ rss_hash4_5 = _mm256_and_si256
+ (rss_hash4_5, rss_hash_msk);
+ rss_hash2_3 = _mm256_and_si256
+ (rss_hash2_3, rss_hash_msk);
+ rss_hash0_1 = _mm256_and_si256
+ (rss_hash0_1, rss_hash_msk);
+
+ mb6_7 = _mm256_or_si256(mb6_7, rss_hash6_7);
+ mb4_5 = _mm256_or_si256(mb4_5, rss_hash4_5);
+ mb2_3 = _mm256_or_si256(mb2_3, rss_hash2_3);
+ mb0_1 = _mm256_or_si256(mb0_1, rss_hash0_1);
+ } /* if() on RSS hash parsing */
+#endif
+
/**
* At this point, we have the 8 sets of flags in the low 16-bits
* of each 32-bit value in vlan0.
txq->tx_tail = tx_id;
- ICE_PCI_REG_WRITE(txq->qtx_tail, txq->tx_tail);
+ ICE_PCI_REG_WC_WRITE(txq->qtx_tail, txq->tx_tail);
return nb_pkts;
}
git.droids-corp.org / dpdk.git / blobdiff